30090 lines
826 KiB
JSON
30090 lines
826 KiB
JSON
{
|
|
"best_global_step": null,
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 1.1670492122155223,
|
|
"eval_steps": 3000,
|
|
"global_step": 15000,
|
|
"is_hyper_param_search": false,
|
|
"is_local_process_zero": true,
|
|
"is_world_process_zero": true,
|
|
"log_history": [
|
|
{
|
|
"entropy": 10.691896057128906,
|
|
"epoch": 0.00038902937171756465,
|
|
"grad_norm": 13.375,
|
|
"learning_rate": 2e-06,
|
|
"loss": 10.7682,
|
|
"mean_token_accuracy": 0.0,
|
|
"num_tokens": 8095.0,
|
|
"step": 5
|
|
},
|
|
{
|
|
"entropy": 10.691933250427246,
|
|
"epoch": 0.0007780587434351293,
|
|
"grad_norm": 12.6875,
|
|
"learning_rate": 4.5e-06,
|
|
"loss": 10.7403,
|
|
"mean_token_accuracy": 0.0006377055658958852,
|
|
"num_tokens": 17329.0,
|
|
"step": 10
|
|
},
|
|
{
|
|
"entropy": 10.69080991744995,
|
|
"epoch": 0.001167088115152694,
|
|
"grad_norm": 10.125,
|
|
"learning_rate": 7e-06,
|
|
"loss": 10.4717,
|
|
"mean_token_accuracy": 0.03278036494739354,
|
|
"num_tokens": 25729.0,
|
|
"step": 15
|
|
},
|
|
{
|
|
"entropy": 10.676905536651612,
|
|
"epoch": 0.0015561174868702586,
|
|
"grad_norm": 6.5625,
|
|
"learning_rate": 9.5e-06,
|
|
"loss": 10.1506,
|
|
"mean_token_accuracy": 0.04596309997141361,
|
|
"num_tokens": 33980.0,
|
|
"step": 20
|
|
},
|
|
{
|
|
"entropy": 10.59173231124878,
|
|
"epoch": 0.0019451468585878235,
|
|
"grad_norm": 4.28125,
|
|
"learning_rate": 1.2e-05,
|
|
"loss": 9.8699,
|
|
"mean_token_accuracy": 0.04366149380803108,
|
|
"num_tokens": 41675.0,
|
|
"step": 25
|
|
},
|
|
{
|
|
"entropy": 10.51305980682373,
|
|
"epoch": 0.002334176230305388,
|
|
"grad_norm": 3.34375,
|
|
"learning_rate": 1.4500000000000002e-05,
|
|
"loss": 9.7305,
|
|
"mean_token_accuracy": 0.046745364740490916,
|
|
"num_tokens": 50277.0,
|
|
"step": 30
|
|
},
|
|
{
|
|
"entropy": 10.490173530578613,
|
|
"epoch": 0.0027232056020229526,
|
|
"grad_norm": 3.046875,
|
|
"learning_rate": 1.7000000000000003e-05,
|
|
"loss": 9.6493,
|
|
"mean_token_accuracy": 0.0512831661850214,
|
|
"num_tokens": 58790.0,
|
|
"step": 35
|
|
},
|
|
{
|
|
"entropy": 10.494702529907226,
|
|
"epoch": 0.0031122349737405172,
|
|
"grad_norm": 2.96875,
|
|
"learning_rate": 1.95e-05,
|
|
"loss": 9.6088,
|
|
"mean_token_accuracy": 0.05120518207550049,
|
|
"num_tokens": 67247.0,
|
|
"step": 40
|
|
},
|
|
{
|
|
"entropy": 10.47821397781372,
|
|
"epoch": 0.003501264345458082,
|
|
"grad_norm": 2.828125,
|
|
"learning_rate": 2.2e-05,
|
|
"loss": 9.5376,
|
|
"mean_token_accuracy": 0.054223894327878955,
|
|
"num_tokens": 75174.0,
|
|
"step": 45
|
|
},
|
|
{
|
|
"entropy": 10.43958568572998,
|
|
"epoch": 0.003890293717175647,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 2.4500000000000003e-05,
|
|
"loss": 9.4437,
|
|
"mean_token_accuracy": 0.06763513237237931,
|
|
"num_tokens": 83203.0,
|
|
"step": 50
|
|
},
|
|
{
|
|
"entropy": 10.308233833312988,
|
|
"epoch": 0.004279323088893211,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 2.7e-05,
|
|
"loss": 9.4079,
|
|
"mean_token_accuracy": 0.06488834656774997,
|
|
"num_tokens": 91798.0,
|
|
"step": 55
|
|
},
|
|
{
|
|
"entropy": 10.269000720977782,
|
|
"epoch": 0.004668352460610776,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 2.95e-05,
|
|
"loss": 9.4289,
|
|
"mean_token_accuracy": 0.06329003609716892,
|
|
"num_tokens": 100869.0,
|
|
"step": 60
|
|
},
|
|
{
|
|
"entropy": 10.361470031738282,
|
|
"epoch": 0.0050573818323283405,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 3.2e-05,
|
|
"loss": 9.3296,
|
|
"mean_token_accuracy": 0.061626766622066495,
|
|
"num_tokens": 109697.0,
|
|
"step": 65
|
|
},
|
|
{
|
|
"entropy": 10.3142409324646,
|
|
"epoch": 0.005446411204045905,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 3.4500000000000005e-05,
|
|
"loss": 9.2921,
|
|
"mean_token_accuracy": 0.06110430583357811,
|
|
"num_tokens": 118656.0,
|
|
"step": 70
|
|
},
|
|
{
|
|
"entropy": 10.19054298400879,
|
|
"epoch": 0.00583544057576347,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 3.7e-05,
|
|
"loss": 9.2586,
|
|
"mean_token_accuracy": 0.060313938185572624,
|
|
"num_tokens": 127748.0,
|
|
"step": 75
|
|
},
|
|
{
|
|
"entropy": 10.34864444732666,
|
|
"epoch": 0.0062244699474810344,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 3.95e-05,
|
|
"loss": 9.1176,
|
|
"mean_token_accuracy": 0.0627338420599699,
|
|
"num_tokens": 136621.0,
|
|
"step": 80
|
|
},
|
|
{
|
|
"entropy": 10.175674057006836,
|
|
"epoch": 0.006613499319198599,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 4.2000000000000004e-05,
|
|
"loss": 8.9517,
|
|
"mean_token_accuracy": 0.06631159856915474,
|
|
"num_tokens": 145793.0,
|
|
"step": 85
|
|
},
|
|
{
|
|
"entropy": 10.162372493743897,
|
|
"epoch": 0.007002528690916164,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 4.45e-05,
|
|
"loss": 8.8629,
|
|
"mean_token_accuracy": 0.06395913921296596,
|
|
"num_tokens": 154466.0,
|
|
"step": 90
|
|
},
|
|
{
|
|
"entropy": 10.15381736755371,
|
|
"epoch": 0.007391558062633729,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 4.7000000000000004e-05,
|
|
"loss": 8.8443,
|
|
"mean_token_accuracy": 0.06343522258102893,
|
|
"num_tokens": 163297.0,
|
|
"step": 95
|
|
},
|
|
{
|
|
"entropy": 10.048249244689941,
|
|
"epoch": 0.007780587434351294,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 4.9500000000000004e-05,
|
|
"loss": 8.696,
|
|
"mean_token_accuracy": 0.06365865133702756,
|
|
"num_tokens": 171747.0,
|
|
"step": 100
|
|
},
|
|
{
|
|
"entropy": 10.09149627685547,
|
|
"epoch": 0.008169616806068859,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 5.2e-05,
|
|
"loss": 8.6166,
|
|
"mean_token_accuracy": 0.06534692756831646,
|
|
"num_tokens": 180499.0,
|
|
"step": 105
|
|
},
|
|
{
|
|
"entropy": 9.920382881164551,
|
|
"epoch": 0.008558646177786422,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 5.45e-05,
|
|
"loss": 8.4788,
|
|
"mean_token_accuracy": 0.06633736491203308,
|
|
"num_tokens": 189227.0,
|
|
"step": 110
|
|
},
|
|
{
|
|
"entropy": 9.86361379623413,
|
|
"epoch": 0.008947675549503988,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 5.7e-05,
|
|
"loss": 8.3439,
|
|
"mean_token_accuracy": 0.07009124867618084,
|
|
"num_tokens": 198388.0,
|
|
"step": 115
|
|
},
|
|
{
|
|
"entropy": 9.680712413787841,
|
|
"epoch": 0.009336704921221552,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 5.9499999999999996e-05,
|
|
"loss": 8.2396,
|
|
"mean_token_accuracy": 0.06940936222672463,
|
|
"num_tokens": 206854.0,
|
|
"step": 120
|
|
},
|
|
{
|
|
"entropy": 9.601908302307129,
|
|
"epoch": 0.009725734292939117,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 6.2e-05,
|
|
"loss": 8.119,
|
|
"mean_token_accuracy": 0.0706846684217453,
|
|
"num_tokens": 215506.0,
|
|
"step": 125
|
|
},
|
|
{
|
|
"entropy": 9.40778636932373,
|
|
"epoch": 0.010114763664656681,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 6.450000000000001e-05,
|
|
"loss": 8.027,
|
|
"mean_token_accuracy": 0.07141325175762177,
|
|
"num_tokens": 223717.0,
|
|
"step": 130
|
|
},
|
|
{
|
|
"entropy": 9.245368766784669,
|
|
"epoch": 0.010503793036374246,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 6.7e-05,
|
|
"loss": 7.9189,
|
|
"mean_token_accuracy": 0.07270697467029094,
|
|
"num_tokens": 232480.0,
|
|
"step": 135
|
|
},
|
|
{
|
|
"entropy": 9.090145778656005,
|
|
"epoch": 0.01089282240809181,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 6.950000000000001e-05,
|
|
"loss": 7.8471,
|
|
"mean_token_accuracy": 0.07338932827115059,
|
|
"num_tokens": 241350.0,
|
|
"step": 140
|
|
},
|
|
{
|
|
"entropy": 8.89556589126587,
|
|
"epoch": 0.011281851779809376,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 7.2e-05,
|
|
"loss": 7.7957,
|
|
"mean_token_accuracy": 0.07191371396183968,
|
|
"num_tokens": 250610.0,
|
|
"step": 145
|
|
},
|
|
{
|
|
"entropy": 8.702104473114014,
|
|
"epoch": 0.01167088115152694,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 7.45e-05,
|
|
"loss": 7.7138,
|
|
"mean_token_accuracy": 0.06948468647897243,
|
|
"num_tokens": 259672.0,
|
|
"step": 150
|
|
},
|
|
{
|
|
"entropy": 8.603777408599854,
|
|
"epoch": 0.012059910523244505,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 7.7e-05,
|
|
"loss": 7.6923,
|
|
"mean_token_accuracy": 0.0712867472320795,
|
|
"num_tokens": 267826.0,
|
|
"step": 155
|
|
},
|
|
{
|
|
"entropy": 8.510001087188721,
|
|
"epoch": 0.012448939894962069,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 7.950000000000001e-05,
|
|
"loss": 7.6847,
|
|
"mean_token_accuracy": 0.06826631203293801,
|
|
"num_tokens": 277324.0,
|
|
"step": 160
|
|
},
|
|
{
|
|
"entropy": 8.372300243377685,
|
|
"epoch": 0.012837969266679634,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 8.2e-05,
|
|
"loss": 7.5139,
|
|
"mean_token_accuracy": 0.07538944780826569,
|
|
"num_tokens": 285482.0,
|
|
"step": 165
|
|
},
|
|
{
|
|
"entropy": 8.333262157440185,
|
|
"epoch": 0.013226998638397198,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 8.450000000000001e-05,
|
|
"loss": 7.5443,
|
|
"mean_token_accuracy": 0.07613336965441704,
|
|
"num_tokens": 293684.0,
|
|
"step": 170
|
|
},
|
|
{
|
|
"entropy": 8.189146041870117,
|
|
"epoch": 0.013616028010114764,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 8.7e-05,
|
|
"loss": 7.4992,
|
|
"mean_token_accuracy": 0.0754831738770008,
|
|
"num_tokens": 302605.0,
|
|
"step": 175
|
|
},
|
|
{
|
|
"entropy": 8.120375633239746,
|
|
"epoch": 0.014005057381832327,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 8.95e-05,
|
|
"loss": 7.5501,
|
|
"mean_token_accuracy": 0.07501808553934097,
|
|
"num_tokens": 310849.0,
|
|
"step": 180
|
|
},
|
|
{
|
|
"entropy": 8.180096626281738,
|
|
"epoch": 0.014394086753549893,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 9.2e-05,
|
|
"loss": 7.5376,
|
|
"mean_token_accuracy": 0.07213864214718342,
|
|
"num_tokens": 319752.0,
|
|
"step": 185
|
|
},
|
|
{
|
|
"entropy": 8.150297737121582,
|
|
"epoch": 0.014783116125267459,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 9.45e-05,
|
|
"loss": 7.5715,
|
|
"mean_token_accuracy": 0.07293041869997978,
|
|
"num_tokens": 328009.0,
|
|
"step": 190
|
|
},
|
|
{
|
|
"entropy": 8.01708698272705,
|
|
"epoch": 0.015172145496985022,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 9.7e-05,
|
|
"loss": 7.4454,
|
|
"mean_token_accuracy": 0.07922360971570015,
|
|
"num_tokens": 337414.0,
|
|
"step": 195
|
|
},
|
|
{
|
|
"entropy": 8.00553069114685,
|
|
"epoch": 0.015561174868702588,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 9.95e-05,
|
|
"loss": 7.4438,
|
|
"mean_token_accuracy": 0.08163341209292412,
|
|
"num_tokens": 345419.0,
|
|
"step": 200
|
|
},
|
|
{
|
|
"entropy": 8.010188388824464,
|
|
"epoch": 0.01595020424042015,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.000102,
|
|
"loss": 7.4176,
|
|
"mean_token_accuracy": 0.08399317860603332,
|
|
"num_tokens": 353435.0,
|
|
"step": 205
|
|
},
|
|
{
|
|
"entropy": 7.945941305160522,
|
|
"epoch": 0.016339233612137717,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00010449999999999999,
|
|
"loss": 7.4398,
|
|
"mean_token_accuracy": 0.07745959497988224,
|
|
"num_tokens": 361840.0,
|
|
"step": 210
|
|
},
|
|
{
|
|
"entropy": 8.018308210372926,
|
|
"epoch": 0.016728262983855283,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000107,
|
|
"loss": 7.5097,
|
|
"mean_token_accuracy": 0.07523712664842605,
|
|
"num_tokens": 370873.0,
|
|
"step": 215
|
|
},
|
|
{
|
|
"entropy": 7.983619546890258,
|
|
"epoch": 0.017117292355572845,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0001095,
|
|
"loss": 7.4308,
|
|
"mean_token_accuracy": 0.07907425090670586,
|
|
"num_tokens": 379558.0,
|
|
"step": 220
|
|
},
|
|
{
|
|
"entropy": 7.867334222793579,
|
|
"epoch": 0.01750632172729041,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.000112,
|
|
"loss": 7.4184,
|
|
"mean_token_accuracy": 0.08053626418113709,
|
|
"num_tokens": 387870.0,
|
|
"step": 225
|
|
},
|
|
{
|
|
"entropy": 7.964390230178833,
|
|
"epoch": 0.017895351099007976,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0001145,
|
|
"loss": 7.4773,
|
|
"mean_token_accuracy": 0.08220710828900338,
|
|
"num_tokens": 396442.0,
|
|
"step": 230
|
|
},
|
|
{
|
|
"entropy": 7.887078332901001,
|
|
"epoch": 0.01828438047072554,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.00011700000000000001,
|
|
"loss": 7.4199,
|
|
"mean_token_accuracy": 0.07810803577303886,
|
|
"num_tokens": 404764.0,
|
|
"step": 235
|
|
},
|
|
{
|
|
"entropy": 7.896487426757813,
|
|
"epoch": 0.018673409842443103,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00011949999999999999,
|
|
"loss": 7.3561,
|
|
"mean_token_accuracy": 0.08208074867725372,
|
|
"num_tokens": 413355.0,
|
|
"step": 240
|
|
},
|
|
{
|
|
"entropy": 7.845146036148071,
|
|
"epoch": 0.01906243921416067,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000122,
|
|
"loss": 7.25,
|
|
"mean_token_accuracy": 0.08628582656383514,
|
|
"num_tokens": 421868.0,
|
|
"step": 245
|
|
},
|
|
{
|
|
"entropy": 7.847237968444825,
|
|
"epoch": 0.019451468585878234,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0001245,
|
|
"loss": 7.2885,
|
|
"mean_token_accuracy": 0.08563556969165802,
|
|
"num_tokens": 431106.0,
|
|
"step": 250
|
|
},
|
|
{
|
|
"entropy": 7.879620504379273,
|
|
"epoch": 0.0198404979575958,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.000127,
|
|
"loss": 7.4271,
|
|
"mean_token_accuracy": 0.0771660901606083,
|
|
"num_tokens": 439459.0,
|
|
"step": 255
|
|
},
|
|
{
|
|
"entropy": 7.715308475494385,
|
|
"epoch": 0.020229527329313362,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0001295,
|
|
"loss": 7.2523,
|
|
"mean_token_accuracy": 0.08652433380484581,
|
|
"num_tokens": 447943.0,
|
|
"step": 260
|
|
},
|
|
{
|
|
"entropy": 7.791458606719971,
|
|
"epoch": 0.020618556701030927,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.000132,
|
|
"loss": 7.3749,
|
|
"mean_token_accuracy": 0.08243331611156464,
|
|
"num_tokens": 456691.0,
|
|
"step": 265
|
|
},
|
|
{
|
|
"entropy": 7.827027750015259,
|
|
"epoch": 0.021007586072748493,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00013450000000000002,
|
|
"loss": 7.2679,
|
|
"mean_token_accuracy": 0.08309322819113732,
|
|
"num_tokens": 466388.0,
|
|
"step": 270
|
|
},
|
|
{
|
|
"entropy": 7.677990436553955,
|
|
"epoch": 0.02139661544446606,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00013700000000000002,
|
|
"loss": 7.3463,
|
|
"mean_token_accuracy": 0.084238101541996,
|
|
"num_tokens": 474544.0,
|
|
"step": 275
|
|
},
|
|
{
|
|
"entropy": 7.855551147460938,
|
|
"epoch": 0.02178564481618362,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0001395,
|
|
"loss": 7.3638,
|
|
"mean_token_accuracy": 0.08487658277153969,
|
|
"num_tokens": 483561.0,
|
|
"step": 280
|
|
},
|
|
{
|
|
"entropy": 7.682491683959961,
|
|
"epoch": 0.022174674187901186,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00014199999999999998,
|
|
"loss": 7.1825,
|
|
"mean_token_accuracy": 0.08649473935365677,
|
|
"num_tokens": 492036.0,
|
|
"step": 285
|
|
},
|
|
{
|
|
"entropy": 7.736964845657349,
|
|
"epoch": 0.02256370355961875,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0001445,
|
|
"loss": 7.3058,
|
|
"mean_token_accuracy": 0.08307258263230324,
|
|
"num_tokens": 500978.0,
|
|
"step": 290
|
|
},
|
|
{
|
|
"entropy": 7.750108766555786,
|
|
"epoch": 0.022952732931336317,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000147,
|
|
"loss": 7.331,
|
|
"mean_token_accuracy": 0.08541621565818787,
|
|
"num_tokens": 509719.0,
|
|
"step": 295
|
|
},
|
|
{
|
|
"entropy": 7.716811800003052,
|
|
"epoch": 0.02334176230305388,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0001495,
|
|
"loss": 7.2418,
|
|
"mean_token_accuracy": 0.0862745113670826,
|
|
"num_tokens": 518422.0,
|
|
"step": 300
|
|
},
|
|
{
|
|
"entropy": 7.7041215896606445,
|
|
"epoch": 0.023730791674771445,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.000152,
|
|
"loss": 7.2726,
|
|
"mean_token_accuracy": 0.08733444213867188,
|
|
"num_tokens": 527172.0,
|
|
"step": 305
|
|
},
|
|
{
|
|
"entropy": 7.661469459533691,
|
|
"epoch": 0.02411982104648901,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00015450000000000001,
|
|
"loss": 7.1871,
|
|
"mean_token_accuracy": 0.08940150961279869,
|
|
"num_tokens": 536070.0,
|
|
"step": 310
|
|
},
|
|
{
|
|
"entropy": 7.650560522079468,
|
|
"epoch": 0.024508850418206576,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.000157,
|
|
"loss": 7.1815,
|
|
"mean_token_accuracy": 0.08751222342252732,
|
|
"num_tokens": 544556.0,
|
|
"step": 315
|
|
},
|
|
{
|
|
"entropy": 7.71123743057251,
|
|
"epoch": 0.024897879789924138,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0001595,
|
|
"loss": 7.1717,
|
|
"mean_token_accuracy": 0.08722432479262351,
|
|
"num_tokens": 553122.0,
|
|
"step": 320
|
|
},
|
|
{
|
|
"entropy": 7.609269285202027,
|
|
"epoch": 0.025286909161641703,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.000162,
|
|
"loss": 7.235,
|
|
"mean_token_accuracy": 0.07931372076272965,
|
|
"num_tokens": 562265.0,
|
|
"step": 325
|
|
},
|
|
{
|
|
"entropy": 7.594164276123047,
|
|
"epoch": 0.02567593853335927,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00016450000000000001,
|
|
"loss": 7.1853,
|
|
"mean_token_accuracy": 0.09104064255952835,
|
|
"num_tokens": 570938.0,
|
|
"step": 330
|
|
},
|
|
{
|
|
"entropy": 7.591356801986694,
|
|
"epoch": 0.026064967905076834,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00016700000000000002,
|
|
"loss": 7.1202,
|
|
"mean_token_accuracy": 0.0924045629799366,
|
|
"num_tokens": 578568.0,
|
|
"step": 335
|
|
},
|
|
{
|
|
"entropy": 7.654570388793945,
|
|
"epoch": 0.026453997276794396,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00016950000000000003,
|
|
"loss": 7.192,
|
|
"mean_token_accuracy": 0.09244821965694427,
|
|
"num_tokens": 587013.0,
|
|
"step": 340
|
|
},
|
|
{
|
|
"entropy": 7.647093391418457,
|
|
"epoch": 0.026843026648511962,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00017199999999999998,
|
|
"loss": 7.2278,
|
|
"mean_token_accuracy": 0.08628092929720879,
|
|
"num_tokens": 595354.0,
|
|
"step": 345
|
|
},
|
|
{
|
|
"entropy": 7.5597922801971436,
|
|
"epoch": 0.027232056020229527,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00017449999999999999,
|
|
"loss": 7.1994,
|
|
"mean_token_accuracy": 0.086347945779562,
|
|
"num_tokens": 603971.0,
|
|
"step": 350
|
|
},
|
|
{
|
|
"entropy": 7.513363790512085,
|
|
"epoch": 0.027621085391947093,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000177,
|
|
"loss": 7.1077,
|
|
"mean_token_accuracy": 0.0958691768348217,
|
|
"num_tokens": 612097.0,
|
|
"step": 355
|
|
},
|
|
{
|
|
"entropy": 7.607126188278198,
|
|
"epoch": 0.028010114763664655,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0001795,
|
|
"loss": 7.1708,
|
|
"mean_token_accuracy": 0.09145483076572418,
|
|
"num_tokens": 621445.0,
|
|
"step": 360
|
|
},
|
|
{
|
|
"entropy": 7.514036798477173,
|
|
"epoch": 0.02839914413538222,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000182,
|
|
"loss": 7.2337,
|
|
"mean_token_accuracy": 0.08651573956012726,
|
|
"num_tokens": 630041.0,
|
|
"step": 365
|
|
},
|
|
{
|
|
"entropy": 7.50714807510376,
|
|
"epoch": 0.028788173507099786,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0001845,
|
|
"loss": 7.0418,
|
|
"mean_token_accuracy": 0.09683061838150024,
|
|
"num_tokens": 638317.0,
|
|
"step": 370
|
|
},
|
|
{
|
|
"entropy": 7.585668706893921,
|
|
"epoch": 0.02917720287881735,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.000187,
|
|
"loss": 7.1733,
|
|
"mean_token_accuracy": 0.09136604964733124,
|
|
"num_tokens": 647297.0,
|
|
"step": 375
|
|
},
|
|
{
|
|
"entropy": 7.613582992553711,
|
|
"epoch": 0.029566232250534917,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0001895,
|
|
"loss": 7.2214,
|
|
"mean_token_accuracy": 0.09044467359781265,
|
|
"num_tokens": 655309.0,
|
|
"step": 380
|
|
},
|
|
{
|
|
"entropy": 7.432076501846313,
|
|
"epoch": 0.02995526162225248,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000192,
|
|
"loss": 7.08,
|
|
"mean_token_accuracy": 0.0861615188419819,
|
|
"num_tokens": 663879.0,
|
|
"step": 385
|
|
},
|
|
{
|
|
"entropy": 7.516607666015625,
|
|
"epoch": 0.030344290993970045,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0001945,
|
|
"loss": 6.9856,
|
|
"mean_token_accuracy": 0.09427314698696136,
|
|
"num_tokens": 672913.0,
|
|
"step": 390
|
|
},
|
|
{
|
|
"entropy": 7.394821453094482,
|
|
"epoch": 0.03073332036568761,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00019700000000000002,
|
|
"loss": 7.0979,
|
|
"mean_token_accuracy": 0.09137862846255303,
|
|
"num_tokens": 682282.0,
|
|
"step": 395
|
|
},
|
|
{
|
|
"entropy": 7.4547014236450195,
|
|
"epoch": 0.031122349737405176,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00019950000000000002,
|
|
"loss": 7.1059,
|
|
"mean_token_accuracy": 0.08515429720282555,
|
|
"num_tokens": 691432.0,
|
|
"step": 400
|
|
},
|
|
{
|
|
"entropy": 7.444170570373535,
|
|
"epoch": 0.03151137910912274,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.000202,
|
|
"loss": 7.102,
|
|
"mean_token_accuracy": 0.08980939239263534,
|
|
"num_tokens": 700639.0,
|
|
"step": 405
|
|
},
|
|
{
|
|
"entropy": 7.551699113845825,
|
|
"epoch": 0.0319004084808403,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.00020449999999999998,
|
|
"loss": 7.184,
|
|
"mean_token_accuracy": 0.0844474621117115,
|
|
"num_tokens": 709200.0,
|
|
"step": 410
|
|
},
|
|
{
|
|
"entropy": 7.30176272392273,
|
|
"epoch": 0.03228943785255787,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.000207,
|
|
"loss": 7.0024,
|
|
"mean_token_accuracy": 0.09402795061469078,
|
|
"num_tokens": 717266.0,
|
|
"step": 415
|
|
},
|
|
{
|
|
"entropy": 7.484861898422241,
|
|
"epoch": 0.032678467224275434,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0002095,
|
|
"loss": 6.9873,
|
|
"mean_token_accuracy": 0.09403469264507294,
|
|
"num_tokens": 725799.0,
|
|
"step": 420
|
|
},
|
|
{
|
|
"entropy": 7.3827354431152346,
|
|
"epoch": 0.033067496595993,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.000212,
|
|
"loss": 7.1101,
|
|
"mean_token_accuracy": 0.09061254039406777,
|
|
"num_tokens": 734375.0,
|
|
"step": 425
|
|
},
|
|
{
|
|
"entropy": 7.475268840789795,
|
|
"epoch": 0.033456525967710565,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0002145,
|
|
"loss": 7.1403,
|
|
"mean_token_accuracy": 0.090643859654665,
|
|
"num_tokens": 743453.0,
|
|
"step": 430
|
|
},
|
|
{
|
|
"entropy": 7.326716709136963,
|
|
"epoch": 0.033845555339428124,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00021700000000000002,
|
|
"loss": 7.0003,
|
|
"mean_token_accuracy": 0.09671235233545303,
|
|
"num_tokens": 752443.0,
|
|
"step": 435
|
|
},
|
|
{
|
|
"entropy": 7.399496269226074,
|
|
"epoch": 0.03423458471114569,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0002195,
|
|
"loss": 6.9699,
|
|
"mean_token_accuracy": 0.09153517037630081,
|
|
"num_tokens": 761294.0,
|
|
"step": 440
|
|
},
|
|
{
|
|
"entropy": 7.355255746841431,
|
|
"epoch": 0.034623614082863255,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.000222,
|
|
"loss": 6.9395,
|
|
"mean_token_accuracy": 0.0974013090133667,
|
|
"num_tokens": 769489.0,
|
|
"step": 445
|
|
},
|
|
{
|
|
"entropy": 7.445426177978516,
|
|
"epoch": 0.03501264345458082,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0002245,
|
|
"loss": 7.0191,
|
|
"mean_token_accuracy": 0.09303558543324471,
|
|
"num_tokens": 777836.0,
|
|
"step": 450
|
|
},
|
|
{
|
|
"entropy": 7.343358373641967,
|
|
"epoch": 0.035401672826298386,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00022700000000000002,
|
|
"loss": 7.0442,
|
|
"mean_token_accuracy": 0.08798035010695457,
|
|
"num_tokens": 786543.0,
|
|
"step": 455
|
|
},
|
|
{
|
|
"entropy": 7.382262325286865,
|
|
"epoch": 0.03579070219801595,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00022950000000000002,
|
|
"loss": 7.1011,
|
|
"mean_token_accuracy": 0.09493663161993027,
|
|
"num_tokens": 794525.0,
|
|
"step": 460
|
|
},
|
|
{
|
|
"entropy": 7.329567766189575,
|
|
"epoch": 0.03617973156973352,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00023200000000000003,
|
|
"loss": 7.0001,
|
|
"mean_token_accuracy": 0.09533165432512761,
|
|
"num_tokens": 803537.0,
|
|
"step": 465
|
|
},
|
|
{
|
|
"entropy": 7.326742553710938,
|
|
"epoch": 0.03656876094145108,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00023449999999999998,
|
|
"loss": 6.9507,
|
|
"mean_token_accuracy": 0.09251324906945228,
|
|
"num_tokens": 811706.0,
|
|
"step": 470
|
|
},
|
|
{
|
|
"entropy": 7.262205600738525,
|
|
"epoch": 0.03695779031316864,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000237,
|
|
"loss": 7.0091,
|
|
"mean_token_accuracy": 0.09699861034750938,
|
|
"num_tokens": 820182.0,
|
|
"step": 475
|
|
},
|
|
{
|
|
"entropy": 7.3125176429748535,
|
|
"epoch": 0.03734681968488621,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0002395,
|
|
"loss": 6.9423,
|
|
"mean_token_accuracy": 0.09304441586136818,
|
|
"num_tokens": 829808.0,
|
|
"step": 480
|
|
},
|
|
{
|
|
"entropy": 7.292161369323731,
|
|
"epoch": 0.03773584905660377,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.000242,
|
|
"loss": 6.8887,
|
|
"mean_token_accuracy": 0.09506509900093078,
|
|
"num_tokens": 838838.0,
|
|
"step": 485
|
|
},
|
|
{
|
|
"entropy": 7.33060131072998,
|
|
"epoch": 0.03812487842832134,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0002445,
|
|
"loss": 6.9833,
|
|
"mean_token_accuracy": 0.09907156899571419,
|
|
"num_tokens": 847800.0,
|
|
"step": 490
|
|
},
|
|
{
|
|
"entropy": 7.394680452346802,
|
|
"epoch": 0.0385139078000389,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.000247,
|
|
"loss": 7.08,
|
|
"mean_token_accuracy": 0.09246540367603302,
|
|
"num_tokens": 856503.0,
|
|
"step": 495
|
|
},
|
|
{
|
|
"entropy": 7.226006984710693,
|
|
"epoch": 0.03890293717175647,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0002495,
|
|
"loss": 6.9683,
|
|
"mean_token_accuracy": 0.09611012637615204,
|
|
"num_tokens": 865245.0,
|
|
"step": 500
|
|
},
|
|
{
|
|
"entropy": 7.303643465042114,
|
|
"epoch": 0.039291966543474034,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.000252,
|
|
"loss": 6.9749,
|
|
"mean_token_accuracy": 0.0949372723698616,
|
|
"num_tokens": 874485.0,
|
|
"step": 505
|
|
},
|
|
{
|
|
"entropy": 7.133185148239136,
|
|
"epoch": 0.0396809959151916,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0002545,
|
|
"loss": 6.8372,
|
|
"mean_token_accuracy": 0.10009809583425522,
|
|
"num_tokens": 883301.0,
|
|
"step": 510
|
|
},
|
|
{
|
|
"entropy": 7.179492998123169,
|
|
"epoch": 0.04007002528690916,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.000257,
|
|
"loss": 6.8987,
|
|
"mean_token_accuracy": 0.09437932819128036,
|
|
"num_tokens": 892387.0,
|
|
"step": 515
|
|
},
|
|
{
|
|
"entropy": 7.161367273330688,
|
|
"epoch": 0.040459054658626724,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0002595,
|
|
"loss": 6.8902,
|
|
"mean_token_accuracy": 0.101420196890831,
|
|
"num_tokens": 901522.0,
|
|
"step": 520
|
|
},
|
|
{
|
|
"entropy": 7.167306137084961,
|
|
"epoch": 0.04084808403034429,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000262,
|
|
"loss": 6.8411,
|
|
"mean_token_accuracy": 0.09641877040266991,
|
|
"num_tokens": 909848.0,
|
|
"step": 525
|
|
},
|
|
{
|
|
"entropy": 7.3447840213775635,
|
|
"epoch": 0.041237113402061855,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00026450000000000003,
|
|
"loss": 7.0797,
|
|
"mean_token_accuracy": 0.09041683003306389,
|
|
"num_tokens": 919079.0,
|
|
"step": 530
|
|
},
|
|
{
|
|
"entropy": 7.150223207473755,
|
|
"epoch": 0.04162614277377942,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00026700000000000004,
|
|
"loss": 6.8357,
|
|
"mean_token_accuracy": 0.10363327041268348,
|
|
"num_tokens": 927807.0,
|
|
"step": 535
|
|
},
|
|
{
|
|
"entropy": 7.154421615600586,
|
|
"epoch": 0.042015172145496986,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00026950000000000005,
|
|
"loss": 6.9331,
|
|
"mean_token_accuracy": 0.10026705339550972,
|
|
"num_tokens": 936498.0,
|
|
"step": 540
|
|
},
|
|
{
|
|
"entropy": 7.247080707550049,
|
|
"epoch": 0.04240420151721455,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00027200000000000005,
|
|
"loss": 7.0055,
|
|
"mean_token_accuracy": 0.10041748508810996,
|
|
"num_tokens": 945436.0,
|
|
"step": 545
|
|
},
|
|
{
|
|
"entropy": 7.224219846725464,
|
|
"epoch": 0.04279323088893212,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0002745,
|
|
"loss": 6.9165,
|
|
"mean_token_accuracy": 0.09951690733432769,
|
|
"num_tokens": 953990.0,
|
|
"step": 550
|
|
},
|
|
{
|
|
"entropy": 7.183721542358398,
|
|
"epoch": 0.04318226026064968,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.000277,
|
|
"loss": 6.8412,
|
|
"mean_token_accuracy": 0.0982144832611084,
|
|
"num_tokens": 962008.0,
|
|
"step": 555
|
|
},
|
|
{
|
|
"entropy": 7.243313407897949,
|
|
"epoch": 0.04357128963236724,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0002795,
|
|
"loss": 7.004,
|
|
"mean_token_accuracy": 0.097385935485363,
|
|
"num_tokens": 970935.0,
|
|
"step": 560
|
|
},
|
|
{
|
|
"entropy": 7.262167167663574,
|
|
"epoch": 0.04396031900408481,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00028199999999999997,
|
|
"loss": 6.9564,
|
|
"mean_token_accuracy": 0.09126960262656211,
|
|
"num_tokens": 979492.0,
|
|
"step": 565
|
|
},
|
|
{
|
|
"entropy": 7.1115397930145265,
|
|
"epoch": 0.04434934837580237,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0002845,
|
|
"loss": 6.8659,
|
|
"mean_token_accuracy": 0.09609195366501808,
|
|
"num_tokens": 987866.0,
|
|
"step": 570
|
|
},
|
|
{
|
|
"entropy": 7.152759647369384,
|
|
"epoch": 0.04473837774751994,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000287,
|
|
"loss": 6.9064,
|
|
"mean_token_accuracy": 0.09902488738298416,
|
|
"num_tokens": 996760.0,
|
|
"step": 575
|
|
},
|
|
{
|
|
"entropy": 7.205654001235962,
|
|
"epoch": 0.0451274071192375,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0002895,
|
|
"loss": 6.8252,
|
|
"mean_token_accuracy": 0.10003674700856209,
|
|
"num_tokens": 1005432.0,
|
|
"step": 580
|
|
},
|
|
{
|
|
"entropy": 7.1957074165344235,
|
|
"epoch": 0.04551643649095507,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.000292,
|
|
"loss": 6.9228,
|
|
"mean_token_accuracy": 0.10067613199353218,
|
|
"num_tokens": 1013729.0,
|
|
"step": 585
|
|
},
|
|
{
|
|
"entropy": 6.997878503799439,
|
|
"epoch": 0.045905465862672634,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0002945,
|
|
"loss": 6.7348,
|
|
"mean_token_accuracy": 0.1082767240703106,
|
|
"num_tokens": 1022485.0,
|
|
"step": 590
|
|
},
|
|
{
|
|
"entropy": 7.08715558052063,
|
|
"epoch": 0.0462944952343902,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.000297,
|
|
"loss": 6.8166,
|
|
"mean_token_accuracy": 0.10034638941287995,
|
|
"num_tokens": 1030523.0,
|
|
"step": 595
|
|
},
|
|
{
|
|
"entropy": 7.2036830425262455,
|
|
"epoch": 0.04668352460610776,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0002995,
|
|
"loss": 6.9339,
|
|
"mean_token_accuracy": 0.09973467364907265,
|
|
"num_tokens": 1039268.0,
|
|
"step": 600
|
|
},
|
|
{
|
|
"entropy": 7.0301995277404785,
|
|
"epoch": 0.047072553977825324,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000302,
|
|
"loss": 6.8202,
|
|
"mean_token_accuracy": 0.10042936652898789,
|
|
"num_tokens": 1048590.0,
|
|
"step": 605
|
|
},
|
|
{
|
|
"entropy": 7.0609663963317875,
|
|
"epoch": 0.04746158334954289,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0003045,
|
|
"loss": 6.7556,
|
|
"mean_token_accuracy": 0.10278418138623238,
|
|
"num_tokens": 1057232.0,
|
|
"step": 610
|
|
},
|
|
{
|
|
"entropy": 7.049582195281983,
|
|
"epoch": 0.047850612721260455,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000307,
|
|
"loss": 6.8216,
|
|
"mean_token_accuracy": 0.09878815785050392,
|
|
"num_tokens": 1066404.0,
|
|
"step": 615
|
|
},
|
|
{
|
|
"entropy": 7.038175964355469,
|
|
"epoch": 0.04823964209297802,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0003095,
|
|
"loss": 6.8842,
|
|
"mean_token_accuracy": 0.0939465455710888,
|
|
"num_tokens": 1075093.0,
|
|
"step": 620
|
|
},
|
|
{
|
|
"entropy": 7.106451797485351,
|
|
"epoch": 0.048628671464695586,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000312,
|
|
"loss": 6.7875,
|
|
"mean_token_accuracy": 0.09886922240257263,
|
|
"num_tokens": 1084454.0,
|
|
"step": 625
|
|
},
|
|
{
|
|
"entropy": 6.990231323242187,
|
|
"epoch": 0.04901770083641315,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0003145,
|
|
"loss": 6.7069,
|
|
"mean_token_accuracy": 0.10300704166293144,
|
|
"num_tokens": 1093452.0,
|
|
"step": 630
|
|
},
|
|
{
|
|
"entropy": 7.079220771789551,
|
|
"epoch": 0.04940673020813072,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.000317,
|
|
"loss": 6.7417,
|
|
"mean_token_accuracy": 0.10723969489336013,
|
|
"num_tokens": 1101814.0,
|
|
"step": 635
|
|
},
|
|
{
|
|
"entropy": 6.995628929138183,
|
|
"epoch": 0.049795759579848276,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0003195,
|
|
"loss": 6.8303,
|
|
"mean_token_accuracy": 0.10031761527061463,
|
|
"num_tokens": 1110386.0,
|
|
"step": 640
|
|
},
|
|
{
|
|
"entropy": 7.119993448257446,
|
|
"epoch": 0.05018478895156584,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000322,
|
|
"loss": 6.9206,
|
|
"mean_token_accuracy": 0.09205639511346816,
|
|
"num_tokens": 1120141.0,
|
|
"step": 645
|
|
},
|
|
{
|
|
"entropy": 7.026125097274781,
|
|
"epoch": 0.05057381832328341,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00032450000000000003,
|
|
"loss": 6.8553,
|
|
"mean_token_accuracy": 0.09914684519171715,
|
|
"num_tokens": 1129920.0,
|
|
"step": 650
|
|
},
|
|
{
|
|
"entropy": 6.9065900325775145,
|
|
"epoch": 0.05096284769500097,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00032700000000000003,
|
|
"loss": 6.7387,
|
|
"mean_token_accuracy": 0.10237120762467385,
|
|
"num_tokens": 1138518.0,
|
|
"step": 655
|
|
},
|
|
{
|
|
"entropy": 7.056087446212769,
|
|
"epoch": 0.05135187706671854,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00032950000000000004,
|
|
"loss": 6.8477,
|
|
"mean_token_accuracy": 0.09784239828586579,
|
|
"num_tokens": 1147113.0,
|
|
"step": 660
|
|
},
|
|
{
|
|
"entropy": 6.963723516464233,
|
|
"epoch": 0.0517409064384361,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00033200000000000005,
|
|
"loss": 6.6747,
|
|
"mean_token_accuracy": 0.10692296847701073,
|
|
"num_tokens": 1155886.0,
|
|
"step": 665
|
|
},
|
|
{
|
|
"entropy": 6.999239587783814,
|
|
"epoch": 0.05212993581015367,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00033450000000000005,
|
|
"loss": 6.8402,
|
|
"mean_token_accuracy": 0.10142037197947502,
|
|
"num_tokens": 1164200.0,
|
|
"step": 670
|
|
},
|
|
{
|
|
"entropy": 6.969135522842407,
|
|
"epoch": 0.052518965181871234,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000337,
|
|
"loss": 6.7113,
|
|
"mean_token_accuracy": 0.10580320581793785,
|
|
"num_tokens": 1172720.0,
|
|
"step": 675
|
|
},
|
|
{
|
|
"entropy": 6.8918328285217285,
|
|
"epoch": 0.05290799455358879,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0003395,
|
|
"loss": 6.6591,
|
|
"mean_token_accuracy": 0.09922505840659142,
|
|
"num_tokens": 1181225.0,
|
|
"step": 680
|
|
},
|
|
{
|
|
"entropy": 7.110291481018066,
|
|
"epoch": 0.05329702392530636,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000342,
|
|
"loss": 6.8661,
|
|
"mean_token_accuracy": 0.1002252757549286,
|
|
"num_tokens": 1190070.0,
|
|
"step": 685
|
|
},
|
|
{
|
|
"entropy": 6.889911794662476,
|
|
"epoch": 0.053686053297023924,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00034449999999999997,
|
|
"loss": 6.745,
|
|
"mean_token_accuracy": 0.09947578459978104,
|
|
"num_tokens": 1198995.0,
|
|
"step": 690
|
|
},
|
|
{
|
|
"entropy": 7.012227392196655,
|
|
"epoch": 0.05407508266874149,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000347,
|
|
"loss": 6.7964,
|
|
"mean_token_accuracy": 0.10564659833908081,
|
|
"num_tokens": 1207664.0,
|
|
"step": 695
|
|
},
|
|
{
|
|
"entropy": 7.011436891555786,
|
|
"epoch": 0.054464112040459055,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0003495,
|
|
"loss": 6.6877,
|
|
"mean_token_accuracy": 0.11616539508104325,
|
|
"num_tokens": 1216232.0,
|
|
"step": 700
|
|
},
|
|
{
|
|
"entropy": 6.915061187744141,
|
|
"epoch": 0.05485314141217662,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.000352,
|
|
"loss": 6.7785,
|
|
"mean_token_accuracy": 0.10488367006182671,
|
|
"num_tokens": 1224106.0,
|
|
"step": 705
|
|
},
|
|
{
|
|
"entropy": 6.85550856590271,
|
|
"epoch": 0.055242170783894186,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0003545,
|
|
"loss": 6.6638,
|
|
"mean_token_accuracy": 0.1070045679807663,
|
|
"num_tokens": 1232514.0,
|
|
"step": 710
|
|
},
|
|
{
|
|
"entropy": 7.0201925277709964,
|
|
"epoch": 0.05563120015561175,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.000357,
|
|
"loss": 6.7192,
|
|
"mean_token_accuracy": 0.1072799600660801,
|
|
"num_tokens": 1240178.0,
|
|
"step": 715
|
|
},
|
|
{
|
|
"entropy": 6.829072189331055,
|
|
"epoch": 0.05602022952732931,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0003595,
|
|
"loss": 6.6433,
|
|
"mean_token_accuracy": 0.10768454670906066,
|
|
"num_tokens": 1248635.0,
|
|
"step": 720
|
|
},
|
|
{
|
|
"entropy": 6.899731540679932,
|
|
"epoch": 0.056409258899046875,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.000362,
|
|
"loss": 6.7462,
|
|
"mean_token_accuracy": 0.10741591677069665,
|
|
"num_tokens": 1256389.0,
|
|
"step": 725
|
|
},
|
|
{
|
|
"entropy": 6.866089391708374,
|
|
"epoch": 0.05679828827076444,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0003645,
|
|
"loss": 6.6941,
|
|
"mean_token_accuracy": 0.1057390108704567,
|
|
"num_tokens": 1264035.0,
|
|
"step": 730
|
|
},
|
|
{
|
|
"entropy": 6.956638479232788,
|
|
"epoch": 0.057187317642482006,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000367,
|
|
"loss": 6.6953,
|
|
"mean_token_accuracy": 0.10426240265369416,
|
|
"num_tokens": 1272941.0,
|
|
"step": 735
|
|
},
|
|
{
|
|
"entropy": 6.688238668441772,
|
|
"epoch": 0.05757634701419957,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0003695,
|
|
"loss": 6.676,
|
|
"mean_token_accuracy": 0.106101393699646,
|
|
"num_tokens": 1281767.0,
|
|
"step": 740
|
|
},
|
|
{
|
|
"entropy": 7.095763778686523,
|
|
"epoch": 0.05796537638591714,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000372,
|
|
"loss": 6.7623,
|
|
"mean_token_accuracy": 0.10797640457749366,
|
|
"num_tokens": 1290049.0,
|
|
"step": 745
|
|
},
|
|
{
|
|
"entropy": 6.762351226806641,
|
|
"epoch": 0.0583544057576347,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0003745,
|
|
"loss": 6.5951,
|
|
"mean_token_accuracy": 0.11266529634594917,
|
|
"num_tokens": 1299032.0,
|
|
"step": 750
|
|
},
|
|
{
|
|
"entropy": 6.872419738769532,
|
|
"epoch": 0.05874343512935227,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000377,
|
|
"loss": 6.851,
|
|
"mean_token_accuracy": 0.10019904971122742,
|
|
"num_tokens": 1308508.0,
|
|
"step": 755
|
|
},
|
|
{
|
|
"entropy": 6.993260669708252,
|
|
"epoch": 0.059132464501069834,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0003795,
|
|
"loss": 6.6769,
|
|
"mean_token_accuracy": 0.10615287944674492,
|
|
"num_tokens": 1317044.0,
|
|
"step": 760
|
|
},
|
|
{
|
|
"entropy": 6.876901865005493,
|
|
"epoch": 0.05952149387278739,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000382,
|
|
"loss": 6.7072,
|
|
"mean_token_accuracy": 0.10667419582605361,
|
|
"num_tokens": 1325554.0,
|
|
"step": 765
|
|
},
|
|
{
|
|
"entropy": 6.8257323741912845,
|
|
"epoch": 0.05991052324450496,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0003845,
|
|
"loss": 6.5916,
|
|
"mean_token_accuracy": 0.10517750829458236,
|
|
"num_tokens": 1334201.0,
|
|
"step": 770
|
|
},
|
|
{
|
|
"entropy": 6.738331365585327,
|
|
"epoch": 0.060299552616222524,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00038700000000000003,
|
|
"loss": 6.6132,
|
|
"mean_token_accuracy": 0.11592961698770524,
|
|
"num_tokens": 1343061.0,
|
|
"step": 775
|
|
},
|
|
{
|
|
"entropy": 6.788525867462158,
|
|
"epoch": 0.06068858198794009,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00038950000000000003,
|
|
"loss": 6.5887,
|
|
"mean_token_accuracy": 0.11328529119491577,
|
|
"num_tokens": 1352262.0,
|
|
"step": 780
|
|
},
|
|
{
|
|
"entropy": 6.766341304779052,
|
|
"epoch": 0.061077611359657655,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00039200000000000004,
|
|
"loss": 6.6355,
|
|
"mean_token_accuracy": 0.10724243074655533,
|
|
"num_tokens": 1361400.0,
|
|
"step": 785
|
|
},
|
|
{
|
|
"entropy": 6.8809511184692385,
|
|
"epoch": 0.06146664073137522,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00039450000000000005,
|
|
"loss": 6.7431,
|
|
"mean_token_accuracy": 0.10390153974294662,
|
|
"num_tokens": 1369850.0,
|
|
"step": 790
|
|
},
|
|
{
|
|
"entropy": 6.770475769042969,
|
|
"epoch": 0.061855670103092786,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00039700000000000005,
|
|
"loss": 6.5993,
|
|
"mean_token_accuracy": 0.11133262068033219,
|
|
"num_tokens": 1378342.0,
|
|
"step": 795
|
|
},
|
|
{
|
|
"entropy": 6.833333206176758,
|
|
"epoch": 0.06224469947481035,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0003995,
|
|
"loss": 6.7006,
|
|
"mean_token_accuracy": 0.10400806367397308,
|
|
"num_tokens": 1386981.0,
|
|
"step": 800
|
|
},
|
|
{
|
|
"entropy": 6.896929168701172,
|
|
"epoch": 0.06263372884652792,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000402,
|
|
"loss": 6.7767,
|
|
"mean_token_accuracy": 0.10226056203246117,
|
|
"num_tokens": 1395801.0,
|
|
"step": 805
|
|
},
|
|
{
|
|
"entropy": 6.881122875213623,
|
|
"epoch": 0.06302275821824548,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004045,
|
|
"loss": 6.6733,
|
|
"mean_token_accuracy": 0.11250713765621186,
|
|
"num_tokens": 1403715.0,
|
|
"step": 810
|
|
},
|
|
{
|
|
"entropy": 6.890682744979858,
|
|
"epoch": 0.06341178758996305,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00040699999999999997,
|
|
"loss": 6.766,
|
|
"mean_token_accuracy": 0.10130376219749451,
|
|
"num_tokens": 1413199.0,
|
|
"step": 815
|
|
},
|
|
{
|
|
"entropy": 6.845803165435791,
|
|
"epoch": 0.0638008169616806,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004095,
|
|
"loss": 6.7297,
|
|
"mean_token_accuracy": 0.10811256021261215,
|
|
"num_tokens": 1421918.0,
|
|
"step": 820
|
|
},
|
|
{
|
|
"entropy": 6.727932119369507,
|
|
"epoch": 0.06418984633339817,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000412,
|
|
"loss": 6.6275,
|
|
"mean_token_accuracy": 0.10078049674630166,
|
|
"num_tokens": 1430625.0,
|
|
"step": 825
|
|
},
|
|
{
|
|
"entropy": 6.839619207382202,
|
|
"epoch": 0.06457887570511574,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004145,
|
|
"loss": 6.6537,
|
|
"mean_token_accuracy": 0.10472832173109055,
|
|
"num_tokens": 1439158.0,
|
|
"step": 830
|
|
},
|
|
{
|
|
"entropy": 6.7103558540344235,
|
|
"epoch": 0.0649679050768333,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000417,
|
|
"loss": 6.6218,
|
|
"mean_token_accuracy": 0.11031484305858612,
|
|
"num_tokens": 1448266.0,
|
|
"step": 835
|
|
},
|
|
{
|
|
"entropy": 6.824801921844482,
|
|
"epoch": 0.06535693444855087,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004195,
|
|
"loss": 6.7042,
|
|
"mean_token_accuracy": 0.10656223520636558,
|
|
"num_tokens": 1457322.0,
|
|
"step": 840
|
|
},
|
|
{
|
|
"entropy": 6.962126445770264,
|
|
"epoch": 0.06574596382026843,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000422,
|
|
"loss": 6.8104,
|
|
"mean_token_accuracy": 0.10119246616959572,
|
|
"num_tokens": 1466120.0,
|
|
"step": 845
|
|
},
|
|
{
|
|
"entropy": 6.734336900711059,
|
|
"epoch": 0.066134993191986,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004245,
|
|
"loss": 6.5668,
|
|
"mean_token_accuracy": 0.10800775364041329,
|
|
"num_tokens": 1474965.0,
|
|
"step": 850
|
|
},
|
|
{
|
|
"entropy": 6.679752445220947,
|
|
"epoch": 0.06652402256370356,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.000427,
|
|
"loss": 6.6775,
|
|
"mean_token_accuracy": 0.10365973934531211,
|
|
"num_tokens": 1483483.0,
|
|
"step": 855
|
|
},
|
|
{
|
|
"entropy": 6.906285905838013,
|
|
"epoch": 0.06691305193542113,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004295,
|
|
"loss": 6.6044,
|
|
"mean_token_accuracy": 0.10145875811576843,
|
|
"num_tokens": 1492313.0,
|
|
"step": 860
|
|
},
|
|
{
|
|
"entropy": 6.7070897102355955,
|
|
"epoch": 0.06730208130713869,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000432,
|
|
"loss": 6.533,
|
|
"mean_token_accuracy": 0.10664732605218888,
|
|
"num_tokens": 1501081.0,
|
|
"step": 865
|
|
},
|
|
{
|
|
"entropy": 6.653385829925537,
|
|
"epoch": 0.06769111067885625,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004345,
|
|
"loss": 6.5538,
|
|
"mean_token_accuracy": 0.10266396701335907,
|
|
"num_tokens": 1510169.0,
|
|
"step": 870
|
|
},
|
|
{
|
|
"entropy": 6.73896050453186,
|
|
"epoch": 0.06808014005057382,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000437,
|
|
"loss": 6.5099,
|
|
"mean_token_accuracy": 0.10998809859156608,
|
|
"num_tokens": 1519546.0,
|
|
"step": 875
|
|
},
|
|
{
|
|
"entropy": 6.610293054580689,
|
|
"epoch": 0.06846916942229138,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004395,
|
|
"loss": 6.6221,
|
|
"mean_token_accuracy": 0.10572586581110954,
|
|
"num_tokens": 1529104.0,
|
|
"step": 880
|
|
},
|
|
{
|
|
"entropy": 6.671034288406372,
|
|
"epoch": 0.06885819879400895,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000442,
|
|
"loss": 6.5747,
|
|
"mean_token_accuracy": 0.11553266048431396,
|
|
"num_tokens": 1537033.0,
|
|
"step": 885
|
|
},
|
|
{
|
|
"entropy": 6.745483112335205,
|
|
"epoch": 0.06924722816572651,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004445,
|
|
"loss": 6.5984,
|
|
"mean_token_accuracy": 0.10939133316278457,
|
|
"num_tokens": 1545059.0,
|
|
"step": 890
|
|
},
|
|
{
|
|
"entropy": 6.75796480178833,
|
|
"epoch": 0.06963625753744408,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000447,
|
|
"loss": 6.5969,
|
|
"mean_token_accuracy": 0.10726859346032143,
|
|
"num_tokens": 1553784.0,
|
|
"step": 895
|
|
},
|
|
{
|
|
"entropy": 6.6265500545501705,
|
|
"epoch": 0.07002528690916164,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00044950000000000003,
|
|
"loss": 6.5325,
|
|
"mean_token_accuracy": 0.1090914063155651,
|
|
"num_tokens": 1562059.0,
|
|
"step": 900
|
|
},
|
|
{
|
|
"entropy": 6.712047672271728,
|
|
"epoch": 0.0704143162808792,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00045200000000000004,
|
|
"loss": 6.591,
|
|
"mean_token_accuracy": 0.10841032788157463,
|
|
"num_tokens": 1570061.0,
|
|
"step": 905
|
|
},
|
|
{
|
|
"entropy": 6.632591104507446,
|
|
"epoch": 0.07080334565259677,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00045450000000000004,
|
|
"loss": 6.5654,
|
|
"mean_token_accuracy": 0.11026803255081177,
|
|
"num_tokens": 1578261.0,
|
|
"step": 910
|
|
},
|
|
{
|
|
"entropy": 6.621666669845581,
|
|
"epoch": 0.07119237502431433,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00045700000000000005,
|
|
"loss": 6.4859,
|
|
"mean_token_accuracy": 0.11358301490545272,
|
|
"num_tokens": 1586260.0,
|
|
"step": 915
|
|
},
|
|
{
|
|
"entropy": 6.711280393600464,
|
|
"epoch": 0.0715814043960319,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00045950000000000006,
|
|
"loss": 6.6821,
|
|
"mean_token_accuracy": 0.10423496067523956,
|
|
"num_tokens": 1595234.0,
|
|
"step": 920
|
|
},
|
|
{
|
|
"entropy": 6.685232305526734,
|
|
"epoch": 0.07197043376774946,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000462,
|
|
"loss": 6.5795,
|
|
"mean_token_accuracy": 0.10836847126483917,
|
|
"num_tokens": 1604212.0,
|
|
"step": 925
|
|
},
|
|
{
|
|
"entropy": 6.730190992355347,
|
|
"epoch": 0.07235946313946703,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004645,
|
|
"loss": 6.6145,
|
|
"mean_token_accuracy": 0.11065342202782631,
|
|
"num_tokens": 1612925.0,
|
|
"step": 930
|
|
},
|
|
{
|
|
"entropy": 6.590854501724243,
|
|
"epoch": 0.07274849251118459,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000467,
|
|
"loss": 6.5066,
|
|
"mean_token_accuracy": 0.10939636155962944,
|
|
"num_tokens": 1621804.0,
|
|
"step": 935
|
|
},
|
|
{
|
|
"entropy": 6.572239732742309,
|
|
"epoch": 0.07313752188290217,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004695,
|
|
"loss": 6.4856,
|
|
"mean_token_accuracy": 0.11304571852087975,
|
|
"num_tokens": 1630943.0,
|
|
"step": 940
|
|
},
|
|
{
|
|
"entropy": 6.617482995986938,
|
|
"epoch": 0.07352655125461972,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000472,
|
|
"loss": 6.3922,
|
|
"mean_token_accuracy": 0.11573764458298683,
|
|
"num_tokens": 1638899.0,
|
|
"step": 945
|
|
},
|
|
{
|
|
"entropy": 6.57882833480835,
|
|
"epoch": 0.07391558062633728,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004745,
|
|
"loss": 6.6125,
|
|
"mean_token_accuracy": 0.11446217894554138,
|
|
"num_tokens": 1647485.0,
|
|
"step": 950
|
|
},
|
|
{
|
|
"entropy": 6.657685661315918,
|
|
"epoch": 0.07430460999805485,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000477,
|
|
"loss": 6.5656,
|
|
"mean_token_accuracy": 0.11251236274838447,
|
|
"num_tokens": 1656290.0,
|
|
"step": 955
|
|
},
|
|
{
|
|
"entropy": 6.712019300460815,
|
|
"epoch": 0.07469363936977241,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004795,
|
|
"loss": 6.5924,
|
|
"mean_token_accuracy": 0.11167355254292488,
|
|
"num_tokens": 1665474.0,
|
|
"step": 960
|
|
},
|
|
{
|
|
"entropy": 6.533619403839111,
|
|
"epoch": 0.07508266874148999,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.000482,
|
|
"loss": 6.464,
|
|
"mean_token_accuracy": 0.1160540908575058,
|
|
"num_tokens": 1673599.0,
|
|
"step": 965
|
|
},
|
|
{
|
|
"entropy": 6.607017183303833,
|
|
"epoch": 0.07547169811320754,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004845,
|
|
"loss": 6.4586,
|
|
"mean_token_accuracy": 0.11052219942212105,
|
|
"num_tokens": 1683282.0,
|
|
"step": 970
|
|
},
|
|
{
|
|
"entropy": 6.630674982070923,
|
|
"epoch": 0.07586072748492512,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000487,
|
|
"loss": 6.5825,
|
|
"mean_token_accuracy": 0.1119205579161644,
|
|
"num_tokens": 1691094.0,
|
|
"step": 975
|
|
},
|
|
{
|
|
"entropy": 6.443245840072632,
|
|
"epoch": 0.07624975685664268,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004895,
|
|
"loss": 6.444,
|
|
"mean_token_accuracy": 0.11762246191501617,
|
|
"num_tokens": 1700053.0,
|
|
"step": 980
|
|
},
|
|
{
|
|
"entropy": 6.574719095230103,
|
|
"epoch": 0.07663878622836025,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000492,
|
|
"loss": 6.3455,
|
|
"mean_token_accuracy": 0.1151976853609085,
|
|
"num_tokens": 1707732.0,
|
|
"step": 985
|
|
},
|
|
{
|
|
"entropy": 6.575902795791626,
|
|
"epoch": 0.0770278156000778,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004945,
|
|
"loss": 6.6179,
|
|
"mean_token_accuracy": 0.10963503271341324,
|
|
"num_tokens": 1716406.0,
|
|
"step": 990
|
|
},
|
|
{
|
|
"entropy": 6.661358880996704,
|
|
"epoch": 0.07741684497179536,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000497,
|
|
"loss": 6.6325,
|
|
"mean_token_accuracy": 0.10895756259560585,
|
|
"num_tokens": 1725832.0,
|
|
"step": 995
|
|
},
|
|
{
|
|
"entropy": 6.733318710327149,
|
|
"epoch": 0.07780587434351294,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004995,
|
|
"loss": 6.5474,
|
|
"mean_token_accuracy": 0.10725341215729714,
|
|
"num_tokens": 1734853.0,
|
|
"step": 1000
|
|
},
|
|
{
|
|
"entropy": 6.559145545959472,
|
|
"epoch": 0.0781949037152305,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004999999989075146,
|
|
"loss": 6.5731,
|
|
"mean_token_accuracy": 0.11213273108005524,
|
|
"num_tokens": 1744240.0,
|
|
"step": 1005
|
|
},
|
|
{
|
|
"entropy": 6.637544441223144,
|
|
"epoch": 0.07858393308694807,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999999944692927,
|
|
"loss": 6.566,
|
|
"mean_token_accuracy": 0.10990296676754951,
|
|
"num_tokens": 1753334.0,
|
|
"step": 1010
|
|
},
|
|
{
|
|
"entropy": 6.47784652709961,
|
|
"epoch": 0.07897296245866563,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000499999986617054,
|
|
"loss": 6.4764,
|
|
"mean_token_accuracy": 0.11047938987612724,
|
|
"num_tokens": 1762032.0,
|
|
"step": 1015
|
|
},
|
|
{
|
|
"entropy": 6.572625017166137,
|
|
"epoch": 0.0793619918303832,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999999753507986,
|
|
"loss": 6.4775,
|
|
"mean_token_accuracy": 0.11230112910270691,
|
|
"num_tokens": 1770508.0,
|
|
"step": 1020
|
|
},
|
|
{
|
|
"entropy": 6.491672945022583,
|
|
"epoch": 0.07975102120210076,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999999606705267,
|
|
"loss": 6.3729,
|
|
"mean_token_accuracy": 0.11614649370312691,
|
|
"num_tokens": 1780167.0,
|
|
"step": 1025
|
|
},
|
|
{
|
|
"entropy": 6.619625043869019,
|
|
"epoch": 0.08014005057381832,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999999425762385,
|
|
"loss": 6.5776,
|
|
"mean_token_accuracy": 0.10773374065756798,
|
|
"num_tokens": 1788809.0,
|
|
"step": 1030
|
|
},
|
|
{
|
|
"entropy": 6.548305225372315,
|
|
"epoch": 0.08052907994553589,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004999999210679344,
|
|
"loss": 6.4943,
|
|
"mean_token_accuracy": 0.11628751307725907,
|
|
"num_tokens": 1797445.0,
|
|
"step": 1035
|
|
},
|
|
{
|
|
"entropy": 6.631950330734253,
|
|
"epoch": 0.08091810931725345,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004999998961456145,
|
|
"loss": 6.5027,
|
|
"mean_token_accuracy": 0.11015650182962418,
|
|
"num_tokens": 1806488.0,
|
|
"step": 1040
|
|
},
|
|
{
|
|
"entropy": 6.501224613189697,
|
|
"epoch": 0.08130713868897102,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999998678092794,
|
|
"loss": 6.5833,
|
|
"mean_token_accuracy": 0.11565212160348892,
|
|
"num_tokens": 1815692.0,
|
|
"step": 1045
|
|
},
|
|
{
|
|
"entropy": 6.625118780136108,
|
|
"epoch": 0.08169616806068858,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004999998360589293,
|
|
"loss": 6.4938,
|
|
"mean_token_accuracy": 0.11357240229845048,
|
|
"num_tokens": 1824599.0,
|
|
"step": 1050
|
|
},
|
|
{
|
|
"entropy": 6.689116191864014,
|
|
"epoch": 0.08208519743240615,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000499999800894565,
|
|
"loss": 6.6448,
|
|
"mean_token_accuracy": 0.11452656835317612,
|
|
"num_tokens": 1833411.0,
|
|
"step": 1055
|
|
},
|
|
{
|
|
"entropy": 6.518345499038697,
|
|
"epoch": 0.08247422680412371,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004999997623161866,
|
|
"loss": 6.4549,
|
|
"mean_token_accuracy": 0.10907695516943931,
|
|
"num_tokens": 1842177.0,
|
|
"step": 1060
|
|
},
|
|
{
|
|
"entropy": 6.470740461349488,
|
|
"epoch": 0.08286325617584128,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999997203237951,
|
|
"loss": 6.4244,
|
|
"mean_token_accuracy": 0.116130381077528,
|
|
"num_tokens": 1850176.0,
|
|
"step": 1065
|
|
},
|
|
{
|
|
"entropy": 6.579597043991089,
|
|
"epoch": 0.08325228554755884,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000499999674917391,
|
|
"loss": 6.4737,
|
|
"mean_token_accuracy": 0.10759498700499534,
|
|
"num_tokens": 1859464.0,
|
|
"step": 1070
|
|
},
|
|
{
|
|
"entropy": 6.453550958633423,
|
|
"epoch": 0.0836413149192764,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999996260969748,
|
|
"loss": 6.3705,
|
|
"mean_token_accuracy": 0.11378242447972298,
|
|
"num_tokens": 1867733.0,
|
|
"step": 1075
|
|
},
|
|
{
|
|
"entropy": 6.466144609451294,
|
|
"epoch": 0.08403034429099397,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999995738625475,
|
|
"loss": 6.3725,
|
|
"mean_token_accuracy": 0.11944899260997772,
|
|
"num_tokens": 1876010.0,
|
|
"step": 1080
|
|
},
|
|
{
|
|
"entropy": 6.499561977386475,
|
|
"epoch": 0.08441937366271153,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999995182141099,
|
|
"loss": 6.5391,
|
|
"mean_token_accuracy": 0.1163535013794899,
|
|
"num_tokens": 1884906.0,
|
|
"step": 1085
|
|
},
|
|
{
|
|
"entropy": 6.527617025375366,
|
|
"epoch": 0.0848084030344291,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999994591516626,
|
|
"loss": 6.4293,
|
|
"mean_token_accuracy": 0.11143236458301545,
|
|
"num_tokens": 1893464.0,
|
|
"step": 1090
|
|
},
|
|
{
|
|
"entropy": 6.541065073013305,
|
|
"epoch": 0.08519743240614666,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999993966752066,
|
|
"loss": 6.4873,
|
|
"mean_token_accuracy": 0.11323103830218315,
|
|
"num_tokens": 1902769.0,
|
|
"step": 1095
|
|
},
|
|
{
|
|
"entropy": 6.517040348052978,
|
|
"epoch": 0.08558646177786423,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000499999330784743,
|
|
"loss": 6.4036,
|
|
"mean_token_accuracy": 0.11408817544579505,
|
|
"num_tokens": 1911968.0,
|
|
"step": 1100
|
|
},
|
|
{
|
|
"entropy": 6.483025693893433,
|
|
"epoch": 0.08597549114958179,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004999992614802725,
|
|
"loss": 6.3911,
|
|
"mean_token_accuracy": 0.11573496237397193,
|
|
"num_tokens": 1920063.0,
|
|
"step": 1105
|
|
},
|
|
{
|
|
"entropy": 6.351643323898315,
|
|
"epoch": 0.08636452052129936,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004999991887617966,
|
|
"loss": 6.3803,
|
|
"mean_token_accuracy": 0.11390967592597008,
|
|
"num_tokens": 1929192.0,
|
|
"step": 1110
|
|
},
|
|
{
|
|
"entropy": 6.570942449569702,
|
|
"epoch": 0.08675354989301692,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999991126293158,
|
|
"loss": 6.5798,
|
|
"mean_token_accuracy": 0.10959510430693627,
|
|
"num_tokens": 1939082.0,
|
|
"step": 1115
|
|
},
|
|
{
|
|
"entropy": 6.373979282379151,
|
|
"epoch": 0.08714257926473448,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999990330828318,
|
|
"loss": 6.43,
|
|
"mean_token_accuracy": 0.1143827423453331,
|
|
"num_tokens": 1948313.0,
|
|
"step": 1120
|
|
},
|
|
{
|
|
"entropy": 6.586628484725952,
|
|
"epoch": 0.08753160863645205,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004999989501223456,
|
|
"loss": 6.4296,
|
|
"mean_token_accuracy": 0.11529109328985214,
|
|
"num_tokens": 1957035.0,
|
|
"step": 1125
|
|
},
|
|
{
|
|
"entropy": 6.405944681167602,
|
|
"epoch": 0.08792063800816961,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999988637478584,
|
|
"loss": 6.4257,
|
|
"mean_token_accuracy": 0.11158483400940895,
|
|
"num_tokens": 1966041.0,
|
|
"step": 1130
|
|
},
|
|
{
|
|
"entropy": 6.511107158660889,
|
|
"epoch": 0.08830966737988719,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004999987739593716,
|
|
"loss": 6.4577,
|
|
"mean_token_accuracy": 0.10981602147221566,
|
|
"num_tokens": 1975019.0,
|
|
"step": 1135
|
|
},
|
|
{
|
|
"entropy": 6.464044380187988,
|
|
"epoch": 0.08869869675160474,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004999986807568865,
|
|
"loss": 6.3725,
|
|
"mean_token_accuracy": 0.12287635952234269,
|
|
"num_tokens": 1982930.0,
|
|
"step": 1140
|
|
},
|
|
{
|
|
"entropy": 6.514709520339966,
|
|
"epoch": 0.08908772612332232,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004999985841404045,
|
|
"loss": 6.4993,
|
|
"mean_token_accuracy": 0.1092392586171627,
|
|
"num_tokens": 1991888.0,
|
|
"step": 1145
|
|
},
|
|
{
|
|
"entropy": 6.3899940013885494,
|
|
"epoch": 0.08947675549503988,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004999984841099271,
|
|
"loss": 6.3541,
|
|
"mean_token_accuracy": 0.11540794596076012,
|
|
"num_tokens": 2000202.0,
|
|
"step": 1150
|
|
},
|
|
{
|
|
"entropy": 6.460285663604736,
|
|
"epoch": 0.08986578486675743,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000499998380665456,
|
|
"loss": 6.3698,
|
|
"mean_token_accuracy": 0.11728540211915969,
|
|
"num_tokens": 2009281.0,
|
|
"step": 1155
|
|
},
|
|
{
|
|
"entropy": 6.4477497100830075,
|
|
"epoch": 0.090254814238475,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999982738069924,
|
|
"loss": 6.3702,
|
|
"mean_token_accuracy": 0.11771893873810768,
|
|
"num_tokens": 2017806.0,
|
|
"step": 1160
|
|
},
|
|
{
|
|
"entropy": 6.440757131576538,
|
|
"epoch": 0.09064384361019256,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999981635345382,
|
|
"loss": 6.4672,
|
|
"mean_token_accuracy": 0.1128288336098194,
|
|
"num_tokens": 2027582.0,
|
|
"step": 1165
|
|
},
|
|
{
|
|
"entropy": 6.436817359924317,
|
|
"epoch": 0.09103287298191014,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999980498480949,
|
|
"loss": 6.3218,
|
|
"mean_token_accuracy": 0.12205893769860268,
|
|
"num_tokens": 2035427.0,
|
|
"step": 1170
|
|
},
|
|
{
|
|
"entropy": 6.547386360168457,
|
|
"epoch": 0.0914219023536277,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999979327476644,
|
|
"loss": 6.5285,
|
|
"mean_token_accuracy": 0.11442452073097228,
|
|
"num_tokens": 2044603.0,
|
|
"step": 1175
|
|
},
|
|
{
|
|
"entropy": 6.3849019527435305,
|
|
"epoch": 0.09181093172534527,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999978122332485,
|
|
"loss": 6.3552,
|
|
"mean_token_accuracy": 0.12413827255368233,
|
|
"num_tokens": 2053272.0,
|
|
"step": 1180
|
|
},
|
|
{
|
|
"entropy": 6.4762718200683596,
|
|
"epoch": 0.09219996109706283,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999976883048487,
|
|
"loss": 6.3797,
|
|
"mean_token_accuracy": 0.11840806007385254,
|
|
"num_tokens": 2061677.0,
|
|
"step": 1185
|
|
},
|
|
{
|
|
"entropy": 6.43572359085083,
|
|
"epoch": 0.0925889904687804,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999975609624673,
|
|
"loss": 6.397,
|
|
"mean_token_accuracy": 0.11727287769317626,
|
|
"num_tokens": 2070282.0,
|
|
"step": 1190
|
|
},
|
|
{
|
|
"entropy": 6.5320531845092775,
|
|
"epoch": 0.09297801984049796,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004999974302061059,
|
|
"loss": 6.5035,
|
|
"mean_token_accuracy": 0.111043381690979,
|
|
"num_tokens": 2078812.0,
|
|
"step": 1195
|
|
},
|
|
{
|
|
"entropy": 6.397515392303466,
|
|
"epoch": 0.09336704921221552,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999972960357666,
|
|
"loss": 6.3813,
|
|
"mean_token_accuracy": 0.11424519494175911,
|
|
"num_tokens": 2087020.0,
|
|
"step": 1200
|
|
},
|
|
{
|
|
"entropy": 6.413018131256104,
|
|
"epoch": 0.09375607858393309,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004999971584514516,
|
|
"loss": 6.3238,
|
|
"mean_token_accuracy": 0.11890219822525978,
|
|
"num_tokens": 2095933.0,
|
|
"step": 1205
|
|
},
|
|
{
|
|
"entropy": 6.320618343353272,
|
|
"epoch": 0.09414510795565065,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999970174531627,
|
|
"loss": 6.3436,
|
|
"mean_token_accuracy": 0.12122933119535446,
|
|
"num_tokens": 2105218.0,
|
|
"step": 1210
|
|
},
|
|
{
|
|
"entropy": 6.293485689163208,
|
|
"epoch": 0.09453413732736822,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004999968730409022,
|
|
"loss": 6.2566,
|
|
"mean_token_accuracy": 0.11917761564254761,
|
|
"num_tokens": 2113808.0,
|
|
"step": 1215
|
|
},
|
|
{
|
|
"entropy": 6.390006256103516,
|
|
"epoch": 0.09492316669908578,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999967252146723,
|
|
"loss": 6.4251,
|
|
"mean_token_accuracy": 0.1174811840057373,
|
|
"num_tokens": 2123014.0,
|
|
"step": 1220
|
|
},
|
|
{
|
|
"entropy": 6.498880815505982,
|
|
"epoch": 0.09531219607080335,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999965739744752,
|
|
"loss": 6.346,
|
|
"mean_token_accuracy": 0.12444588094949723,
|
|
"num_tokens": 2131840.0,
|
|
"step": 1225
|
|
},
|
|
{
|
|
"entropy": 6.458331155776977,
|
|
"epoch": 0.09570122544252091,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004999964193203132,
|
|
"loss": 6.4309,
|
|
"mean_token_accuracy": 0.11823861449956893,
|
|
"num_tokens": 2140467.0,
|
|
"step": 1230
|
|
},
|
|
{
|
|
"entropy": 6.428109121322632,
|
|
"epoch": 0.09609025481423847,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999962612521888,
|
|
"loss": 6.3798,
|
|
"mean_token_accuracy": 0.12282692417502403,
|
|
"num_tokens": 2149282.0,
|
|
"step": 1235
|
|
},
|
|
{
|
|
"entropy": 6.429515647888183,
|
|
"epoch": 0.09647928418595604,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999960997701041,
|
|
"loss": 6.3801,
|
|
"mean_token_accuracy": 0.11871640384197235,
|
|
"num_tokens": 2157781.0,
|
|
"step": 1240
|
|
},
|
|
{
|
|
"entropy": 6.419339513778686,
|
|
"epoch": 0.0968683135576736,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999959348740618,
|
|
"loss": 6.3565,
|
|
"mean_token_accuracy": 0.11975458636879921,
|
|
"num_tokens": 2166482.0,
|
|
"step": 1245
|
|
},
|
|
{
|
|
"entropy": 6.3982480525970455,
|
|
"epoch": 0.09725734292939117,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999957665640641,
|
|
"loss": 6.3726,
|
|
"mean_token_accuracy": 0.11583413928747177,
|
|
"num_tokens": 2174559.0,
|
|
"step": 1250
|
|
},
|
|
{
|
|
"entropy": 6.392813014984131,
|
|
"epoch": 0.09764637230110873,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000499995594840114,
|
|
"loss": 6.2627,
|
|
"mean_token_accuracy": 0.12039380520582199,
|
|
"num_tokens": 2182374.0,
|
|
"step": 1255
|
|
},
|
|
{
|
|
"entropy": 6.315843868255615,
|
|
"epoch": 0.0980354016728263,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999954197022138,
|
|
"loss": 6.3739,
|
|
"mean_token_accuracy": 0.12241144180297851,
|
|
"num_tokens": 2191427.0,
|
|
"step": 1260
|
|
},
|
|
{
|
|
"entropy": 6.491170120239258,
|
|
"epoch": 0.09842443104454386,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999952411503661,
|
|
"loss": 6.4657,
|
|
"mean_token_accuracy": 0.11634750217199326,
|
|
"num_tokens": 2199698.0,
|
|
"step": 1265
|
|
},
|
|
{
|
|
"entropy": 6.412351083755493,
|
|
"epoch": 0.09881346041626143,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999950591845738,
|
|
"loss": 6.2891,
|
|
"mean_token_accuracy": 0.12139204517006874,
|
|
"num_tokens": 2208519.0,
|
|
"step": 1270
|
|
},
|
|
{
|
|
"entropy": 6.28710150718689,
|
|
"epoch": 0.09920248978797899,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999948738048397,
|
|
"loss": 6.3098,
|
|
"mean_token_accuracy": 0.12150795012712479,
|
|
"num_tokens": 2217453.0,
|
|
"step": 1275
|
|
},
|
|
{
|
|
"entropy": 6.34256329536438,
|
|
"epoch": 0.09959151915969655,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999946850111663,
|
|
"loss": 6.4153,
|
|
"mean_token_accuracy": 0.1209065318107605,
|
|
"num_tokens": 2225623.0,
|
|
"step": 1280
|
|
},
|
|
{
|
|
"entropy": 6.43469386100769,
|
|
"epoch": 0.09998054853141412,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999944928035569,
|
|
"loss": 6.3593,
|
|
"mean_token_accuracy": 0.121299659460783,
|
|
"num_tokens": 2234519.0,
|
|
"step": 1285
|
|
},
|
|
{
|
|
"entropy": 6.3267598152160645,
|
|
"epoch": 0.10036957790313168,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.000499994297182014,
|
|
"loss": 6.3602,
|
|
"mean_token_accuracy": 0.11970539391040802,
|
|
"num_tokens": 2242994.0,
|
|
"step": 1290
|
|
},
|
|
{
|
|
"entropy": 6.463318681716919,
|
|
"epoch": 0.10075860727484925,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999940981465408,
|
|
"loss": 6.3755,
|
|
"mean_token_accuracy": 0.11988109499216079,
|
|
"num_tokens": 2251687.0,
|
|
"step": 1295
|
|
},
|
|
{
|
|
"entropy": 6.263813257217407,
|
|
"epoch": 0.10114763664656681,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999938956971404,
|
|
"loss": 6.2951,
|
|
"mean_token_accuracy": 0.12231847047805786,
|
|
"num_tokens": 2260751.0,
|
|
"step": 1300
|
|
},
|
|
{
|
|
"entropy": 6.42852816581726,
|
|
"epoch": 0.10153666601828439,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999936898338156,
|
|
"loss": 6.2395,
|
|
"mean_token_accuracy": 0.1288893111050129,
|
|
"num_tokens": 2269125.0,
|
|
"step": 1305
|
|
},
|
|
{
|
|
"entropy": 6.226840353012085,
|
|
"epoch": 0.10192569539000194,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999934805565698,
|
|
"loss": 6.1775,
|
|
"mean_token_accuracy": 0.12845248058438302,
|
|
"num_tokens": 2277098.0,
|
|
"step": 1310
|
|
},
|
|
{
|
|
"entropy": 6.373805332183838,
|
|
"epoch": 0.10231472476171952,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000499993267865406,
|
|
"loss": 6.455,
|
|
"mean_token_accuracy": 0.11760153844952584,
|
|
"num_tokens": 2285953.0,
|
|
"step": 1315
|
|
},
|
|
{
|
|
"entropy": 6.406149291992188,
|
|
"epoch": 0.10270375413343708,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999930517603275,
|
|
"loss": 6.3714,
|
|
"mean_token_accuracy": 0.12183143571019173,
|
|
"num_tokens": 2294487.0,
|
|
"step": 1320
|
|
},
|
|
{
|
|
"entropy": 6.39051923751831,
|
|
"epoch": 0.10309278350515463,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999928322413374,
|
|
"loss": 6.3909,
|
|
"mean_token_accuracy": 0.11598639711737632,
|
|
"num_tokens": 2302915.0,
|
|
"step": 1325
|
|
},
|
|
{
|
|
"entropy": 6.3545863151550295,
|
|
"epoch": 0.1034818128768722,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999926093084394,
|
|
"loss": 6.3443,
|
|
"mean_token_accuracy": 0.11570636853575707,
|
|
"num_tokens": 2310769.0,
|
|
"step": 1330
|
|
},
|
|
{
|
|
"entropy": 6.3191876888275145,
|
|
"epoch": 0.10387084224858976,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999923829616365,
|
|
"loss": 6.2362,
|
|
"mean_token_accuracy": 0.11870313882827759,
|
|
"num_tokens": 2319987.0,
|
|
"step": 1335
|
|
},
|
|
{
|
|
"entropy": 6.339432001113892,
|
|
"epoch": 0.10425987162030734,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004999921532009323,
|
|
"loss": 6.3474,
|
|
"mean_token_accuracy": 0.11524386182427407,
|
|
"num_tokens": 2328964.0,
|
|
"step": 1340
|
|
},
|
|
{
|
|
"entropy": 6.397040700912475,
|
|
"epoch": 0.1046489009920249,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999919200263304,
|
|
"loss": 6.3133,
|
|
"mean_token_accuracy": 0.11604936346411705,
|
|
"num_tokens": 2337945.0,
|
|
"step": 1345
|
|
},
|
|
{
|
|
"entropy": 6.3518479347229,
|
|
"epoch": 0.10503793036374247,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999916834378342,
|
|
"loss": 6.2137,
|
|
"mean_token_accuracy": 0.1228095144033432,
|
|
"num_tokens": 2345989.0,
|
|
"step": 1350
|
|
},
|
|
{
|
|
"entropy": 6.209484100341797,
|
|
"epoch": 0.10542695973546003,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999914434354472,
|
|
"loss": 6.3234,
|
|
"mean_token_accuracy": 0.12122376561164856,
|
|
"num_tokens": 2353752.0,
|
|
"step": 1355
|
|
},
|
|
{
|
|
"entropy": 6.382920408248902,
|
|
"epoch": 0.10581598910717759,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999912000191733,
|
|
"loss": 6.2872,
|
|
"mean_token_accuracy": 0.11960536614060402,
|
|
"num_tokens": 2361961.0,
|
|
"step": 1360
|
|
},
|
|
{
|
|
"entropy": 6.2765013694763185,
|
|
"epoch": 0.10620501847889516,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000499990953189016,
|
|
"loss": 6.2129,
|
|
"mean_token_accuracy": 0.12653318867087365,
|
|
"num_tokens": 2370148.0,
|
|
"step": 1365
|
|
},
|
|
{
|
|
"entropy": 6.378698635101318,
|
|
"epoch": 0.10659404785061272,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999907029449791,
|
|
"loss": 6.2592,
|
|
"mean_token_accuracy": 0.12621283754706383,
|
|
"num_tokens": 2379105.0,
|
|
"step": 1370
|
|
},
|
|
{
|
|
"entropy": 6.351945304870606,
|
|
"epoch": 0.10698307722233029,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999904492870663,
|
|
"loss": 6.3305,
|
|
"mean_token_accuracy": 0.12122908383607864,
|
|
"num_tokens": 2387417.0,
|
|
"step": 1375
|
|
},
|
|
{
|
|
"entropy": 6.3498913764953615,
|
|
"epoch": 0.10737210659404785,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999901922152816,
|
|
"loss": 6.3536,
|
|
"mean_token_accuracy": 0.12595803663134575,
|
|
"num_tokens": 2396163.0,
|
|
"step": 1380
|
|
},
|
|
{
|
|
"entropy": 6.179137945175171,
|
|
"epoch": 0.10776113596576542,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999899317296288,
|
|
"loss": 6.2105,
|
|
"mean_token_accuracy": 0.12522833421826363,
|
|
"num_tokens": 2404661.0,
|
|
"step": 1385
|
|
},
|
|
{
|
|
"entropy": 6.334095621109009,
|
|
"epoch": 0.10815016533748298,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004999896678301121,
|
|
"loss": 6.302,
|
|
"mean_token_accuracy": 0.11695858612656593,
|
|
"num_tokens": 2413459.0,
|
|
"step": 1390
|
|
},
|
|
{
|
|
"entropy": 6.355089330673218,
|
|
"epoch": 0.10853919470920055,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999894005167352,
|
|
"loss": 6.2443,
|
|
"mean_token_accuracy": 0.12691024467349052,
|
|
"num_tokens": 2421401.0,
|
|
"step": 1395
|
|
},
|
|
{
|
|
"entropy": 6.320974922180175,
|
|
"epoch": 0.10892822408091811,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000499989129789502,
|
|
"loss": 6.252,
|
|
"mean_token_accuracy": 0.1299786426126957,
|
|
"num_tokens": 2429983.0,
|
|
"step": 1400
|
|
},
|
|
{
|
|
"entropy": 6.366431760787964,
|
|
"epoch": 0.10931725345263567,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999888556484172,
|
|
"loss": 6.3893,
|
|
"mean_token_accuracy": 0.11359420493245125,
|
|
"num_tokens": 2439206.0,
|
|
"step": 1405
|
|
},
|
|
{
|
|
"entropy": 6.271417093276978,
|
|
"epoch": 0.10970628282435324,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999885780934845,
|
|
"loss": 6.3147,
|
|
"mean_token_accuracy": 0.13233309537172316,
|
|
"num_tokens": 2448801.0,
|
|
"step": 1410
|
|
},
|
|
{
|
|
"entropy": 6.330869722366333,
|
|
"epoch": 0.1100953121960708,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004999882971247081,
|
|
"loss": 6.3539,
|
|
"mean_token_accuracy": 0.12248845249414445,
|
|
"num_tokens": 2458007.0,
|
|
"step": 1415
|
|
},
|
|
{
|
|
"entropy": 6.32300910949707,
|
|
"epoch": 0.11048434156778837,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004999880127420926,
|
|
"loss": 6.2393,
|
|
"mean_token_accuracy": 0.13286312147974969,
|
|
"num_tokens": 2466574.0,
|
|
"step": 1420
|
|
},
|
|
{
|
|
"entropy": 6.4055665016174315,
|
|
"epoch": 0.11087337093950593,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999877249456421,
|
|
"loss": 6.3219,
|
|
"mean_token_accuracy": 0.12253004312515259,
|
|
"num_tokens": 2475263.0,
|
|
"step": 1425
|
|
},
|
|
{
|
|
"entropy": 6.054247617721558,
|
|
"epoch": 0.1112624003112235,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999874337353609,
|
|
"loss": 6.0664,
|
|
"mean_token_accuracy": 0.12846405506134034,
|
|
"num_tokens": 2483738.0,
|
|
"step": 1430
|
|
},
|
|
{
|
|
"entropy": 6.2588417530059814,
|
|
"epoch": 0.11165142968294106,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999871391112535,
|
|
"loss": 6.187,
|
|
"mean_token_accuracy": 0.1216193564236164,
|
|
"num_tokens": 2492937.0,
|
|
"step": 1435
|
|
},
|
|
{
|
|
"entropy": 6.194214534759522,
|
|
"epoch": 0.11204045905465862,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004999868410733244,
|
|
"loss": 6.2503,
|
|
"mean_token_accuracy": 0.12336413487792015,
|
|
"num_tokens": 2500716.0,
|
|
"step": 1440
|
|
},
|
|
{
|
|
"entropy": 6.254022169113159,
|
|
"epoch": 0.11242948842637619,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000499986539621578,
|
|
"loss": 6.2575,
|
|
"mean_token_accuracy": 0.12012252137064934,
|
|
"num_tokens": 2509385.0,
|
|
"step": 1445
|
|
},
|
|
{
|
|
"entropy": 6.420900154113769,
|
|
"epoch": 0.11281851779809375,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999862347560191,
|
|
"loss": 6.3259,
|
|
"mean_token_accuracy": 0.11690858453512191,
|
|
"num_tokens": 2518179.0,
|
|
"step": 1450
|
|
},
|
|
{
|
|
"entropy": 6.249479198455811,
|
|
"epoch": 0.11320754716981132,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999859264766521,
|
|
"loss": 6.2585,
|
|
"mean_token_accuracy": 0.12355490997433663,
|
|
"num_tokens": 2526644.0,
|
|
"step": 1455
|
|
},
|
|
{
|
|
"entropy": 6.265651607513428,
|
|
"epoch": 0.11359657654152888,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999856147834817,
|
|
"loss": 6.1782,
|
|
"mean_token_accuracy": 0.12229724824428559,
|
|
"num_tokens": 2534998.0,
|
|
"step": 1460
|
|
},
|
|
{
|
|
"entropy": 6.28430061340332,
|
|
"epoch": 0.11398560591324645,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999852996765129,
|
|
"loss": 6.253,
|
|
"mean_token_accuracy": 0.125435870885849,
|
|
"num_tokens": 2543562.0,
|
|
"step": 1465
|
|
},
|
|
{
|
|
"entropy": 6.282908535003662,
|
|
"epoch": 0.11437463528496401,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999849811557502,
|
|
"loss": 6.2506,
|
|
"mean_token_accuracy": 0.1216797761619091,
|
|
"num_tokens": 2551688.0,
|
|
"step": 1470
|
|
},
|
|
{
|
|
"entropy": 6.275887537002563,
|
|
"epoch": 0.11476366465668159,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999846592211984,
|
|
"loss": 6.3275,
|
|
"mean_token_accuracy": 0.12465370073914528,
|
|
"num_tokens": 2560227.0,
|
|
"step": 1475
|
|
},
|
|
{
|
|
"entropy": 6.321870994567871,
|
|
"epoch": 0.11515269402839914,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999843338728626,
|
|
"loss": 6.2034,
|
|
"mean_token_accuracy": 0.12613042816519737,
|
|
"num_tokens": 2569245.0,
|
|
"step": 1480
|
|
},
|
|
{
|
|
"entropy": 6.224797201156616,
|
|
"epoch": 0.1155417234001167,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999840051107476,
|
|
"loss": 6.223,
|
|
"mean_token_accuracy": 0.1265519917011261,
|
|
"num_tokens": 2577706.0,
|
|
"step": 1485
|
|
},
|
|
{
|
|
"entropy": 6.319393301010132,
|
|
"epoch": 0.11593075277183428,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004999836729348584,
|
|
"loss": 6.2579,
|
|
"mean_token_accuracy": 0.12350616082549096,
|
|
"num_tokens": 2586075.0,
|
|
"step": 1490
|
|
},
|
|
{
|
|
"entropy": 6.252358913421631,
|
|
"epoch": 0.11631978214355183,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999833373452,
|
|
"loss": 6.2734,
|
|
"mean_token_accuracy": 0.12134807705879211,
|
|
"num_tokens": 2594965.0,
|
|
"step": 1495
|
|
},
|
|
{
|
|
"entropy": 6.257946348190307,
|
|
"epoch": 0.1167088115152694,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999829983417778,
|
|
"loss": 6.1954,
|
|
"mean_token_accuracy": 0.12667486742138861,
|
|
"num_tokens": 2603355.0,
|
|
"step": 1500
|
|
},
|
|
{
|
|
"entropy": 6.317920351028443,
|
|
"epoch": 0.11709784088698696,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999826559245965,
|
|
"loss": 6.3263,
|
|
"mean_token_accuracy": 0.12176407799124718,
|
|
"num_tokens": 2611697.0,
|
|
"step": 1505
|
|
},
|
|
{
|
|
"entropy": 6.24525089263916,
|
|
"epoch": 0.11748687025870454,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999823100936615,
|
|
"loss": 6.1881,
|
|
"mean_token_accuracy": 0.12955067977309226,
|
|
"num_tokens": 2620821.0,
|
|
"step": 1510
|
|
},
|
|
{
|
|
"entropy": 6.2969574451446535,
|
|
"epoch": 0.1178758996304221,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999819608489781,
|
|
"loss": 6.1926,
|
|
"mean_token_accuracy": 0.1269972711801529,
|
|
"num_tokens": 2628891.0,
|
|
"step": 1515
|
|
},
|
|
{
|
|
"entropy": 6.232346153259277,
|
|
"epoch": 0.11826492900213967,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999816081905515,
|
|
"loss": 6.3299,
|
|
"mean_token_accuracy": 0.12064500376582146,
|
|
"num_tokens": 2638641.0,
|
|
"step": 1520
|
|
},
|
|
{
|
|
"entropy": 6.277464914321899,
|
|
"epoch": 0.11865395837385723,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004999812521183872,
|
|
"loss": 6.2218,
|
|
"mean_token_accuracy": 0.12372512891888618,
|
|
"num_tokens": 2646898.0,
|
|
"step": 1525
|
|
},
|
|
{
|
|
"entropy": 6.343517303466797,
|
|
"epoch": 0.11904298774557479,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999808926324903,
|
|
"loss": 6.2575,
|
|
"mean_token_accuracy": 0.12216506227850914,
|
|
"num_tokens": 2655404.0,
|
|
"step": 1530
|
|
},
|
|
{
|
|
"entropy": 6.174682712554931,
|
|
"epoch": 0.11943201711729236,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999805297328665,
|
|
"loss": 6.1524,
|
|
"mean_token_accuracy": 0.1293441690504551,
|
|
"num_tokens": 2663851.0,
|
|
"step": 1535
|
|
},
|
|
{
|
|
"entropy": 6.2491882801055905,
|
|
"epoch": 0.11982104648900992,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004999801634195214,
|
|
"loss": 6.1957,
|
|
"mean_token_accuracy": 0.12269230708479881,
|
|
"num_tokens": 2672231.0,
|
|
"step": 1540
|
|
},
|
|
{
|
|
"entropy": 6.198257303237915,
|
|
"epoch": 0.12021007586072749,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999797936924603,
|
|
"loss": 6.209,
|
|
"mean_token_accuracy": 0.12302690893411636,
|
|
"num_tokens": 2680198.0,
|
|
"step": 1545
|
|
},
|
|
{
|
|
"entropy": 6.30586805343628,
|
|
"epoch": 0.12059910523244505,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000499979420551689,
|
|
"loss": 6.2377,
|
|
"mean_token_accuracy": 0.12162458598613739,
|
|
"num_tokens": 2689208.0,
|
|
"step": 1550
|
|
},
|
|
{
|
|
"entropy": 6.306586265563965,
|
|
"epoch": 0.12098813460416262,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000499979043997213,
|
|
"loss": 6.2899,
|
|
"mean_token_accuracy": 0.11871301680803299,
|
|
"num_tokens": 2698116.0,
|
|
"step": 1555
|
|
},
|
|
{
|
|
"entropy": 6.267044591903686,
|
|
"epoch": 0.12137716397588018,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999786640290381,
|
|
"loss": 6.1975,
|
|
"mean_token_accuracy": 0.11922681853175163,
|
|
"num_tokens": 2707046.0,
|
|
"step": 1560
|
|
},
|
|
{
|
|
"entropy": 6.23398265838623,
|
|
"epoch": 0.12176619334759774,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999782806471701,
|
|
"loss": 6.192,
|
|
"mean_token_accuracy": 0.1261439874768257,
|
|
"num_tokens": 2714929.0,
|
|
"step": 1565
|
|
},
|
|
{
|
|
"entropy": 6.2020190238952635,
|
|
"epoch": 0.12215522271931531,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999778938516147,
|
|
"loss": 6.2158,
|
|
"mean_token_accuracy": 0.1232543520629406,
|
|
"num_tokens": 2723436.0,
|
|
"step": 1570
|
|
},
|
|
{
|
|
"entropy": 6.223355484008789,
|
|
"epoch": 0.12254425209103287,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000499977503642378,
|
|
"loss": 6.266,
|
|
"mean_token_accuracy": 0.12410560548305512,
|
|
"num_tokens": 2731935.0,
|
|
"step": 1575
|
|
},
|
|
{
|
|
"entropy": 6.175629901885986,
|
|
"epoch": 0.12293328146275044,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999771100194656,
|
|
"loss": 6.0801,
|
|
"mean_token_accuracy": 0.13136413991451262,
|
|
"num_tokens": 2740307.0,
|
|
"step": 1580
|
|
},
|
|
{
|
|
"entropy": 6.136730718612671,
|
|
"epoch": 0.123322310834468,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999767129828837,
|
|
"loss": 6.0848,
|
|
"mean_token_accuracy": 0.13186190873384476,
|
|
"num_tokens": 2749077.0,
|
|
"step": 1585
|
|
},
|
|
{
|
|
"entropy": 6.22774748802185,
|
|
"epoch": 0.12371134020618557,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999763125326383,
|
|
"loss": 6.2122,
|
|
"mean_token_accuracy": 0.1224086344242096,
|
|
"num_tokens": 2758133.0,
|
|
"step": 1590
|
|
},
|
|
{
|
|
"entropy": 6.179558944702149,
|
|
"epoch": 0.12410036957790313,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999759086687355,
|
|
"loss": 6.1341,
|
|
"mean_token_accuracy": 0.1290878973901272,
|
|
"num_tokens": 2766509.0,
|
|
"step": 1595
|
|
},
|
|
{
|
|
"entropy": 6.1690037727355955,
|
|
"epoch": 0.1244893989496207,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999755013911813,
|
|
"loss": 6.308,
|
|
"mean_token_accuracy": 0.12781446427106857,
|
|
"num_tokens": 2775908.0,
|
|
"step": 1600
|
|
},
|
|
{
|
|
"entropy": 6.2387913227081295,
|
|
"epoch": 0.12487842832133826,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000499975090699982,
|
|
"loss": 6.0694,
|
|
"mean_token_accuracy": 0.13497328236699105,
|
|
"num_tokens": 2784803.0,
|
|
"step": 1605
|
|
},
|
|
{
|
|
"entropy": 6.248407363891602,
|
|
"epoch": 0.12526745769305583,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999746765951438,
|
|
"loss": 6.2272,
|
|
"mean_token_accuracy": 0.12323559522628784,
|
|
"num_tokens": 2793897.0,
|
|
"step": 1610
|
|
},
|
|
{
|
|
"entropy": 6.144442796707153,
|
|
"epoch": 0.1256564870647734,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004999742590766729,
|
|
"loss": 6.0709,
|
|
"mean_token_accuracy": 0.12970903664827346,
|
|
"num_tokens": 2802652.0,
|
|
"step": 1615
|
|
},
|
|
{
|
|
"entropy": 6.195466232299805,
|
|
"epoch": 0.12604551643649095,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999738381445757,
|
|
"loss": 6.2156,
|
|
"mean_token_accuracy": 0.12098970115184784,
|
|
"num_tokens": 2811527.0,
|
|
"step": 1620
|
|
},
|
|
{
|
|
"entropy": 6.168512582778931,
|
|
"epoch": 0.1264345458082085,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004999734137988586,
|
|
"loss": 6.0632,
|
|
"mean_token_accuracy": 0.13398998901247977,
|
|
"num_tokens": 2819410.0,
|
|
"step": 1625
|
|
},
|
|
{
|
|
"entropy": 6.040783309936524,
|
|
"epoch": 0.1268235751799261,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000499972986039528,
|
|
"loss": 6.0735,
|
|
"mean_token_accuracy": 0.1366802491247654,
|
|
"num_tokens": 2828079.0,
|
|
"step": 1630
|
|
},
|
|
{
|
|
"entropy": 6.200006103515625,
|
|
"epoch": 0.12721260455164365,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999725548665904,
|
|
"loss": 6.1926,
|
|
"mean_token_accuracy": 0.13287901505827904,
|
|
"num_tokens": 2836326.0,
|
|
"step": 1635
|
|
},
|
|
{
|
|
"entropy": 6.217862844467163,
|
|
"epoch": 0.1276016339233612,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004999721202800524,
|
|
"loss": 6.2434,
|
|
"mean_token_accuracy": 0.12198355495929718,
|
|
"num_tokens": 2845271.0,
|
|
"step": 1640
|
|
},
|
|
{
|
|
"entropy": 6.14015941619873,
|
|
"epoch": 0.12799066329507877,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999716822799206,
|
|
"loss": 6.1008,
|
|
"mean_token_accuracy": 0.13585591837763786,
|
|
"num_tokens": 2853688.0,
|
|
"step": 1645
|
|
},
|
|
{
|
|
"entropy": 6.2203113555908205,
|
|
"epoch": 0.12837969266679633,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999712408662016,
|
|
"loss": 6.1861,
|
|
"mean_token_accuracy": 0.13381585478782654,
|
|
"num_tokens": 2862261.0,
|
|
"step": 1650
|
|
},
|
|
{
|
|
"entropy": 6.182382297515869,
|
|
"epoch": 0.12876872203851392,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999707960389021,
|
|
"loss": 6.1977,
|
|
"mean_token_accuracy": 0.12676158770918847,
|
|
"num_tokens": 2871324.0,
|
|
"step": 1655
|
|
},
|
|
{
|
|
"entropy": 6.26635627746582,
|
|
"epoch": 0.12915775141023147,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004999703477980288,
|
|
"loss": 6.2583,
|
|
"mean_token_accuracy": 0.11872835904359817,
|
|
"num_tokens": 2880268.0,
|
|
"step": 1660
|
|
},
|
|
{
|
|
"entropy": 6.208874273300171,
|
|
"epoch": 0.12954678078194903,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004999698961435885,
|
|
"loss": 6.1612,
|
|
"mean_token_accuracy": 0.12779268771409988,
|
|
"num_tokens": 2888510.0,
|
|
"step": 1665
|
|
},
|
|
{
|
|
"entropy": 6.200055122375488,
|
|
"epoch": 0.1299358101536666,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999694410755882,
|
|
"loss": 6.07,
|
|
"mean_token_accuracy": 0.13593013808131219,
|
|
"num_tokens": 2897616.0,
|
|
"step": 1670
|
|
},
|
|
{
|
|
"entropy": 6.106130218505859,
|
|
"epoch": 0.13032483952538418,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999689825940347,
|
|
"loss": 6.166,
|
|
"mean_token_accuracy": 0.13071656748652458,
|
|
"num_tokens": 2905703.0,
|
|
"step": 1675
|
|
},
|
|
{
|
|
"entropy": 6.1497344970703125,
|
|
"epoch": 0.13071386889710174,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999685206989349,
|
|
"loss": 6.0503,
|
|
"mean_token_accuracy": 0.13300523832440375,
|
|
"num_tokens": 2914881.0,
|
|
"step": 1680
|
|
},
|
|
{
|
|
"entropy": 6.064972543716431,
|
|
"epoch": 0.1311028982688193,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999680553902959,
|
|
"loss": 6.111,
|
|
"mean_token_accuracy": 0.13151929527521133,
|
|
"num_tokens": 2923563.0,
|
|
"step": 1685
|
|
},
|
|
{
|
|
"entropy": 6.2831262111663815,
|
|
"epoch": 0.13149192764053685,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999675866681247,
|
|
"loss": 6.3242,
|
|
"mean_token_accuracy": 0.12403198331594467,
|
|
"num_tokens": 2932821.0,
|
|
"step": 1690
|
|
},
|
|
{
|
|
"entropy": 6.244329929351807,
|
|
"epoch": 0.1318809570122544,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999671145324286,
|
|
"loss": 6.2049,
|
|
"mean_token_accuracy": 0.12842011004686354,
|
|
"num_tokens": 2940926.0,
|
|
"step": 1695
|
|
},
|
|
{
|
|
"entropy": 6.194862365722656,
|
|
"epoch": 0.132269986383972,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999666389832144,
|
|
"loss": 6.1331,
|
|
"mean_token_accuracy": 0.13136012181639672,
|
|
"num_tokens": 2950028.0,
|
|
"step": 1700
|
|
},
|
|
{
|
|
"entropy": 6.151176118850708,
|
|
"epoch": 0.13265901575568956,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999661600204897,
|
|
"loss": 6.1368,
|
|
"mean_token_accuracy": 0.13054827898740767,
|
|
"num_tokens": 2957636.0,
|
|
"step": 1705
|
|
},
|
|
{
|
|
"entropy": 6.0364806175231935,
|
|
"epoch": 0.13304804512740712,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999656776442615,
|
|
"loss": 5.9255,
|
|
"mean_token_accuracy": 0.1334216207265854,
|
|
"num_tokens": 2966544.0,
|
|
"step": 1710
|
|
},
|
|
{
|
|
"entropy": 6.1242743015289305,
|
|
"epoch": 0.13343707449912467,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999651918545372,
|
|
"loss": 6.1605,
|
|
"mean_token_accuracy": 0.12257000207901,
|
|
"num_tokens": 2976236.0,
|
|
"step": 1715
|
|
},
|
|
{
|
|
"entropy": 6.152473640441895,
|
|
"epoch": 0.13382610387084226,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004999647026513243,
|
|
"loss": 6.1172,
|
|
"mean_token_accuracy": 0.13368836417794228,
|
|
"num_tokens": 2984261.0,
|
|
"step": 1720
|
|
},
|
|
{
|
|
"entropy": 6.08830189704895,
|
|
"epoch": 0.13421513324255982,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00049996421003463,
|
|
"loss": 6.0843,
|
|
"mean_token_accuracy": 0.12732574567198754,
|
|
"num_tokens": 2992970.0,
|
|
"step": 1725
|
|
},
|
|
{
|
|
"entropy": 6.202375268936157,
|
|
"epoch": 0.13460416261427738,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004999637140044619,
|
|
"loss": 6.1223,
|
|
"mean_token_accuracy": 0.13581531047821044,
|
|
"num_tokens": 3001356.0,
|
|
"step": 1730
|
|
},
|
|
{
|
|
"entropy": 6.075127840042114,
|
|
"epoch": 0.13499319198599494,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999632145608275,
|
|
"loss": 6.1247,
|
|
"mean_token_accuracy": 0.13326116278767586,
|
|
"num_tokens": 3009509.0,
|
|
"step": 1735
|
|
},
|
|
{
|
|
"entropy": 6.151353645324707,
|
|
"epoch": 0.1353822213577125,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999627117037343,
|
|
"loss": 6.1486,
|
|
"mean_token_accuracy": 0.1305352844297886,
|
|
"num_tokens": 3017675.0,
|
|
"step": 1740
|
|
},
|
|
{
|
|
"entropy": 6.159458446502685,
|
|
"epoch": 0.13577125072943008,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00049996220543319,
|
|
"loss": 6.1111,
|
|
"mean_token_accuracy": 0.13545044139027596,
|
|
"num_tokens": 3025527.0,
|
|
"step": 1745
|
|
},
|
|
{
|
|
"entropy": 6.122771835327148,
|
|
"epoch": 0.13616028010114764,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004999616957492025,
|
|
"loss": 6.0723,
|
|
"mean_token_accuracy": 0.13396283537149428,
|
|
"num_tokens": 3034251.0,
|
|
"step": 1750
|
|
},
|
|
{
|
|
"entropy": 6.054795837402343,
|
|
"epoch": 0.1365493094728652,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999611826517793,
|
|
"loss": 6.3029,
|
|
"mean_token_accuracy": 0.12316446378827095,
|
|
"num_tokens": 3043272.0,
|
|
"step": 1755
|
|
},
|
|
{
|
|
"entropy": 6.303162145614624,
|
|
"epoch": 0.13693833884458276,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999606661409281,
|
|
"loss": 6.1523,
|
|
"mean_token_accuracy": 0.1299624763429165,
|
|
"num_tokens": 3051092.0,
|
|
"step": 1760
|
|
},
|
|
{
|
|
"entropy": 6.103368616104126,
|
|
"epoch": 0.13732736821630034,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999601462166569,
|
|
"loss": 6.1178,
|
|
"mean_token_accuracy": 0.12677409127354622,
|
|
"num_tokens": 3060584.0,
|
|
"step": 1765
|
|
},
|
|
{
|
|
"entropy": 6.161142778396607,
|
|
"epoch": 0.1377163975880179,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999596228789736,
|
|
"loss": 6.1185,
|
|
"mean_token_accuracy": 0.13394217044115067,
|
|
"num_tokens": 3069990.0,
|
|
"step": 1770
|
|
},
|
|
{
|
|
"entropy": 6.1580225944519045,
|
|
"epoch": 0.13810542695973546,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999590961278859,
|
|
"loss": 6.0852,
|
|
"mean_token_accuracy": 0.12508078217506408,
|
|
"num_tokens": 3078837.0,
|
|
"step": 1775
|
|
},
|
|
{
|
|
"entropy": 6.0550312995910645,
|
|
"epoch": 0.13849445633145302,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999585659634021,
|
|
"loss": 6.0777,
|
|
"mean_token_accuracy": 0.1352244459092617,
|
|
"num_tokens": 3087557.0,
|
|
"step": 1780
|
|
},
|
|
{
|
|
"entropy": 6.0994940280914305,
|
|
"epoch": 0.13888348570317058,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999580323855301,
|
|
"loss": 6.1028,
|
|
"mean_token_accuracy": 0.12971555292606354,
|
|
"num_tokens": 3096524.0,
|
|
"step": 1785
|
|
},
|
|
{
|
|
"entropy": 6.242001056671143,
|
|
"epoch": 0.13927251507488816,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999574953942781,
|
|
"loss": 6.164,
|
|
"mean_token_accuracy": 0.12785928025841714,
|
|
"num_tokens": 3105271.0,
|
|
"step": 1790
|
|
},
|
|
{
|
|
"entropy": 6.110553503036499,
|
|
"epoch": 0.13966154444660572,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999569549896541,
|
|
"loss": 6.071,
|
|
"mean_token_accuracy": 0.12340522482991219,
|
|
"num_tokens": 3114479.0,
|
|
"step": 1795
|
|
},
|
|
{
|
|
"entropy": 6.123258876800537,
|
|
"epoch": 0.14005057381832328,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999564111716665,
|
|
"loss": 6.0558,
|
|
"mean_token_accuracy": 0.14115509390830994,
|
|
"num_tokens": 3123319.0,
|
|
"step": 1800
|
|
},
|
|
{
|
|
"entropy": 6.0733929634094235,
|
|
"epoch": 0.14043960319004084,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999558639403232,
|
|
"loss": 6.0825,
|
|
"mean_token_accuracy": 0.13198988437652587,
|
|
"num_tokens": 3132532.0,
|
|
"step": 1805
|
|
},
|
|
{
|
|
"entropy": 6.229814195632935,
|
|
"epoch": 0.1408286325617584,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999553132956328,
|
|
"loss": 6.1592,
|
|
"mean_token_accuracy": 0.12872777804732322,
|
|
"num_tokens": 3140798.0,
|
|
"step": 1810
|
|
},
|
|
{
|
|
"entropy": 6.103444957733155,
|
|
"epoch": 0.14121766193347599,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999547592376035,
|
|
"loss": 6.1475,
|
|
"mean_token_accuracy": 0.13363951444625854,
|
|
"num_tokens": 3149607.0,
|
|
"step": 1815
|
|
},
|
|
{
|
|
"entropy": 6.03386869430542,
|
|
"epoch": 0.14160669130519354,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999542017662438,
|
|
"loss": 5.9717,
|
|
"mean_token_accuracy": 0.13687212467193605,
|
|
"num_tokens": 3157537.0,
|
|
"step": 1820
|
|
},
|
|
{
|
|
"entropy": 6.089433431625366,
|
|
"epoch": 0.1419957206769111,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004999536408815623,
|
|
"loss": 6.1376,
|
|
"mean_token_accuracy": 0.12610816434025765,
|
|
"num_tokens": 3166351.0,
|
|
"step": 1825
|
|
},
|
|
{
|
|
"entropy": 6.060422134399414,
|
|
"epoch": 0.14238475004862866,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999530765835672,
|
|
"loss": 5.9849,
|
|
"mean_token_accuracy": 0.13618941605091095,
|
|
"num_tokens": 3174690.0,
|
|
"step": 1830
|
|
},
|
|
{
|
|
"entropy": 6.075569534301758,
|
|
"epoch": 0.14277377942034625,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999525088722673,
|
|
"loss": 6.1061,
|
|
"mean_token_accuracy": 0.1265280582010746,
|
|
"num_tokens": 3183460.0,
|
|
"step": 1835
|
|
},
|
|
{
|
|
"entropy": 6.1444073677062985,
|
|
"epoch": 0.1431628087920638,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999519377476711,
|
|
"loss": 6.0722,
|
|
"mean_token_accuracy": 0.1317371055483818,
|
|
"num_tokens": 3192183.0,
|
|
"step": 1840
|
|
},
|
|
{
|
|
"entropy": 6.090657949447632,
|
|
"epoch": 0.14355183816378136,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999513632097872,
|
|
"loss": 6.1671,
|
|
"mean_token_accuracy": 0.13313975185155869,
|
|
"num_tokens": 3200875.0,
|
|
"step": 1845
|
|
},
|
|
{
|
|
"entropy": 6.174860572814941,
|
|
"epoch": 0.14394086753549892,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999507852586245,
|
|
"loss": 6.0212,
|
|
"mean_token_accuracy": 0.13179150596261024,
|
|
"num_tokens": 3209797.0,
|
|
"step": 1850
|
|
},
|
|
{
|
|
"entropy": 6.107384920120239,
|
|
"epoch": 0.14432989690721648,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999502038941917,
|
|
"loss": 6.1357,
|
|
"mean_token_accuracy": 0.126478423923254,
|
|
"num_tokens": 3218612.0,
|
|
"step": 1855
|
|
},
|
|
{
|
|
"entropy": 6.0968400001525875,
|
|
"epoch": 0.14471892627893407,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999496191164975,
|
|
"loss": 6.0554,
|
|
"mean_token_accuracy": 0.1293291188776493,
|
|
"num_tokens": 3227364.0,
|
|
"step": 1860
|
|
},
|
|
{
|
|
"entropy": 6.112162446975708,
|
|
"epoch": 0.14510795565065163,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000499949030925551,
|
|
"loss": 6.0761,
|
|
"mean_token_accuracy": 0.12927125319838523,
|
|
"num_tokens": 3236448.0,
|
|
"step": 1865
|
|
},
|
|
{
|
|
"entropy": 6.098051738739014,
|
|
"epoch": 0.14549698502236919,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999484393213609,
|
|
"loss": 6.012,
|
|
"mean_token_accuracy": 0.13607736453413963,
|
|
"num_tokens": 3244957.0,
|
|
"step": 1870
|
|
},
|
|
{
|
|
"entropy": 6.022885847091675,
|
|
"epoch": 0.14588601439408674,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999478443039363,
|
|
"loss": 6.1038,
|
|
"mean_token_accuracy": 0.12877627462148666,
|
|
"num_tokens": 3253250.0,
|
|
"step": 1875
|
|
},
|
|
{
|
|
"entropy": 6.15300350189209,
|
|
"epoch": 0.14627504376580433,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999472458732862,
|
|
"loss": 5.9976,
|
|
"mean_token_accuracy": 0.14316268488764763,
|
|
"num_tokens": 3261455.0,
|
|
"step": 1880
|
|
},
|
|
{
|
|
"entropy": 6.0133215427398685,
|
|
"epoch": 0.1466640731375219,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999466440294198,
|
|
"loss": 6.0574,
|
|
"mean_token_accuracy": 0.13383367732167245,
|
|
"num_tokens": 3270108.0,
|
|
"step": 1885
|
|
},
|
|
{
|
|
"entropy": 6.168636178970337,
|
|
"epoch": 0.14705310250923945,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000499946038772346,
|
|
"loss": 6.1715,
|
|
"mean_token_accuracy": 0.12984701097011567,
|
|
"num_tokens": 3278425.0,
|
|
"step": 1890
|
|
},
|
|
{
|
|
"entropy": 6.1114959716796875,
|
|
"epoch": 0.147442131880957,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999454301020741,
|
|
"loss": 6.1128,
|
|
"mean_token_accuracy": 0.12607192546129226,
|
|
"num_tokens": 3288358.0,
|
|
"step": 1895
|
|
},
|
|
{
|
|
"entropy": 6.106830310821533,
|
|
"epoch": 0.14783116125267456,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004999448180186133,
|
|
"loss": 6.1045,
|
|
"mean_token_accuracy": 0.12614032998681068,
|
|
"num_tokens": 3297199.0,
|
|
"step": 1900
|
|
},
|
|
{
|
|
"entropy": 6.098498821258545,
|
|
"epoch": 0.14822019062439215,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000499944202521973,
|
|
"loss": 6.1129,
|
|
"mean_token_accuracy": 0.12640552148222922,
|
|
"num_tokens": 3306350.0,
|
|
"step": 1905
|
|
},
|
|
{
|
|
"entropy": 6.05791392326355,
|
|
"epoch": 0.1486092199961097,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999435836121624,
|
|
"loss": 5.9412,
|
|
"mean_token_accuracy": 0.13614155799150468,
|
|
"num_tokens": 3314921.0,
|
|
"step": 1910
|
|
},
|
|
{
|
|
"entropy": 5.942939949035645,
|
|
"epoch": 0.14899824936782727,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000499942961289191,
|
|
"loss": 6.0897,
|
|
"mean_token_accuracy": 0.13519461452960968,
|
|
"num_tokens": 3323324.0,
|
|
"step": 1915
|
|
},
|
|
{
|
|
"entropy": 6.268859624862671,
|
|
"epoch": 0.14938727873954483,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004999423355530683,
|
|
"loss": 6.2168,
|
|
"mean_token_accuracy": 0.12899630516767502,
|
|
"num_tokens": 3331614.0,
|
|
"step": 1920
|
|
},
|
|
{
|
|
"entropy": 6.068661069869995,
|
|
"epoch": 0.1497763081112624,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004999417064038035,
|
|
"loss": 6.048,
|
|
"mean_token_accuracy": 0.13625814467668534,
|
|
"num_tokens": 3339573.0,
|
|
"step": 1925
|
|
},
|
|
{
|
|
"entropy": 6.113537693023682,
|
|
"epoch": 0.15016533748297997,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999410738414065,
|
|
"loss": 6.019,
|
|
"mean_token_accuracy": 0.13822999522089957,
|
|
"num_tokens": 3347775.0,
|
|
"step": 1930
|
|
},
|
|
{
|
|
"entropy": 6.026789045333862,
|
|
"epoch": 0.15055436685469753,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999404378658866,
|
|
"loss": 5.9738,
|
|
"mean_token_accuracy": 0.13702433034777642,
|
|
"num_tokens": 3356947.0,
|
|
"step": 1935
|
|
},
|
|
{
|
|
"entropy": 6.101319646835327,
|
|
"epoch": 0.1509433962264151,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999397984772536,
|
|
"loss": 6.067,
|
|
"mean_token_accuracy": 0.1303373880684376,
|
|
"num_tokens": 3365420.0,
|
|
"step": 1940
|
|
},
|
|
{
|
|
"entropy": 6.0900736331939695,
|
|
"epoch": 0.15133242559813265,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999391556755172,
|
|
"loss": 6.1591,
|
|
"mean_token_accuracy": 0.12977703511714936,
|
|
"num_tokens": 3373483.0,
|
|
"step": 1945
|
|
},
|
|
{
|
|
"entropy": 6.1492267608642575,
|
|
"epoch": 0.15172145496985023,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999385094606872,
|
|
"loss": 6.1473,
|
|
"mean_token_accuracy": 0.12746963351964952,
|
|
"num_tokens": 3382557.0,
|
|
"step": 1950
|
|
},
|
|
{
|
|
"entropy": 6.168496370315552,
|
|
"epoch": 0.1521104843415678,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999378598327733,
|
|
"loss": 6.0838,
|
|
"mean_token_accuracy": 0.12692655250430107,
|
|
"num_tokens": 3392079.0,
|
|
"step": 1955
|
|
},
|
|
{
|
|
"entropy": 6.093343210220337,
|
|
"epoch": 0.15249951371328535,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999372067917854,
|
|
"loss": 6.1531,
|
|
"mean_token_accuracy": 0.13067096173763276,
|
|
"num_tokens": 3401070.0,
|
|
"step": 1960
|
|
},
|
|
{
|
|
"entropy": 6.078389596939087,
|
|
"epoch": 0.1528885430850029,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999365503377335,
|
|
"loss": 6.0271,
|
|
"mean_token_accuracy": 0.1348519966006279,
|
|
"num_tokens": 3409921.0,
|
|
"step": 1965
|
|
},
|
|
{
|
|
"entropy": 6.104602289199829,
|
|
"epoch": 0.1532775724567205,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999358904706273,
|
|
"loss": 6.0616,
|
|
"mean_token_accuracy": 0.1285829097032547,
|
|
"num_tokens": 3419149.0,
|
|
"step": 1970
|
|
},
|
|
{
|
|
"entropy": 6.030079126358032,
|
|
"epoch": 0.15366660182843805,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004999352271904771,
|
|
"loss": 5.9462,
|
|
"mean_token_accuracy": 0.13964028134942055,
|
|
"num_tokens": 3427435.0,
|
|
"step": 1975
|
|
},
|
|
{
|
|
"entropy": 6.123502540588379,
|
|
"epoch": 0.1540556312001556,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004999345604972928,
|
|
"loss": 6.1541,
|
|
"mean_token_accuracy": 0.12671427205204963,
|
|
"num_tokens": 3436377.0,
|
|
"step": 1980
|
|
},
|
|
{
|
|
"entropy": 6.069276142120361,
|
|
"epoch": 0.15444466057187317,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999338903910846,
|
|
"loss": 6.0279,
|
|
"mean_token_accuracy": 0.13194865062832833,
|
|
"num_tokens": 3444997.0,
|
|
"step": 1985
|
|
},
|
|
{
|
|
"entropy": 6.103115558624268,
|
|
"epoch": 0.15483368994359073,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999332168718626,
|
|
"loss": 6.104,
|
|
"mean_token_accuracy": 0.1315036803483963,
|
|
"num_tokens": 3454254.0,
|
|
"step": 1990
|
|
},
|
|
{
|
|
"entropy": 6.131479167938233,
|
|
"epoch": 0.15522271931530832,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004999325399396371,
|
|
"loss": 6.0603,
|
|
"mean_token_accuracy": 0.1318090170621872,
|
|
"num_tokens": 3462853.0,
|
|
"step": 1995
|
|
},
|
|
{
|
|
"entropy": 5.984948539733887,
|
|
"epoch": 0.15561174868702587,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999318595944183,
|
|
"loss": 6.0059,
|
|
"mean_token_accuracy": 0.13085325956344604,
|
|
"num_tokens": 3471288.0,
|
|
"step": 2000
|
|
},
|
|
{
|
|
"entropy": 5.977605199813842,
|
|
"epoch": 0.15600077805874343,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004999311758362166,
|
|
"loss": 5.9,
|
|
"mean_token_accuracy": 0.1340898171067238,
|
|
"num_tokens": 3479479.0,
|
|
"step": 2005
|
|
},
|
|
{
|
|
"entropy": 6.000810623168945,
|
|
"epoch": 0.156389807430461,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999304886650422,
|
|
"loss": 5.9227,
|
|
"mean_token_accuracy": 0.13736169710755347,
|
|
"num_tokens": 3488621.0,
|
|
"step": 2010
|
|
},
|
|
{
|
|
"entropy": 6.011513090133667,
|
|
"epoch": 0.15677883680217858,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999297980809058,
|
|
"loss": 5.9912,
|
|
"mean_token_accuracy": 0.1385435238480568,
|
|
"num_tokens": 3497792.0,
|
|
"step": 2015
|
|
},
|
|
{
|
|
"entropy": 5.96446213722229,
|
|
"epoch": 0.15716786617389614,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004999291040838176,
|
|
"loss": 5.9932,
|
|
"mean_token_accuracy": 0.13427436128258705,
|
|
"num_tokens": 3506548.0,
|
|
"step": 2020
|
|
},
|
|
{
|
|
"entropy": 6.073589420318603,
|
|
"epoch": 0.1575568955456137,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999284066737884,
|
|
"loss": 5.9874,
|
|
"mean_token_accuracy": 0.14162887558341025,
|
|
"num_tokens": 3515086.0,
|
|
"step": 2025
|
|
},
|
|
{
|
|
"entropy": 6.079417896270752,
|
|
"epoch": 0.15794592491733125,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999277058508285,
|
|
"loss": 6.025,
|
|
"mean_token_accuracy": 0.13054124414920806,
|
|
"num_tokens": 3523985.0,
|
|
"step": 2030
|
|
},
|
|
{
|
|
"entropy": 6.108053159713745,
|
|
"epoch": 0.1583349542890488,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999270016149486,
|
|
"loss": 6.1046,
|
|
"mean_token_accuracy": 0.1336774356663227,
|
|
"num_tokens": 3532575.0,
|
|
"step": 2035
|
|
},
|
|
{
|
|
"entropy": 6.097129058837891,
|
|
"epoch": 0.1587239836607664,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999262939661596,
|
|
"loss": 6.0793,
|
|
"mean_token_accuracy": 0.13377865329384803,
|
|
"num_tokens": 3541558.0,
|
|
"step": 2040
|
|
},
|
|
{
|
|
"entropy": 6.012680435180664,
|
|
"epoch": 0.15911301303248396,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999255829044721,
|
|
"loss": 5.9951,
|
|
"mean_token_accuracy": 0.1400863155722618,
|
|
"num_tokens": 3549697.0,
|
|
"step": 2045
|
|
},
|
|
{
|
|
"entropy": 6.0912693500518795,
|
|
"epoch": 0.15950204240420152,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999248684298968,
|
|
"loss": 6.1595,
|
|
"mean_token_accuracy": 0.12602965235710145,
|
|
"num_tokens": 3558673.0,
|
|
"step": 2050
|
|
},
|
|
{
|
|
"entropy": 6.175625467300415,
|
|
"epoch": 0.15989107177591907,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999241505424447,
|
|
"loss": 6.022,
|
|
"mean_token_accuracy": 0.13359369337558746,
|
|
"num_tokens": 3567176.0,
|
|
"step": 2055
|
|
},
|
|
{
|
|
"entropy": 6.115584897994995,
|
|
"epoch": 0.16028010114763663,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999234292421265,
|
|
"loss": 6.1588,
|
|
"mean_token_accuracy": 0.12792168632149697,
|
|
"num_tokens": 3576020.0,
|
|
"step": 2060
|
|
},
|
|
{
|
|
"entropy": 6.0277955532073975,
|
|
"epoch": 0.16066913051935422,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004999227045289535,
|
|
"loss": 5.983,
|
|
"mean_token_accuracy": 0.13384223580360413,
|
|
"num_tokens": 3584705.0,
|
|
"step": 2065
|
|
},
|
|
{
|
|
"entropy": 6.09326057434082,
|
|
"epoch": 0.16105815989107178,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999219764029363,
|
|
"loss": 6.1786,
|
|
"mean_token_accuracy": 0.12971396073698999,
|
|
"num_tokens": 3593339.0,
|
|
"step": 2070
|
|
},
|
|
{
|
|
"entropy": 6.074710321426392,
|
|
"epoch": 0.16144718926278934,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999212448640861,
|
|
"loss": 5.9169,
|
|
"mean_token_accuracy": 0.14326073378324508,
|
|
"num_tokens": 3601206.0,
|
|
"step": 2075
|
|
},
|
|
{
|
|
"entropy": 5.917049407958984,
|
|
"epoch": 0.1618362186345069,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999205099124141,
|
|
"loss": 6.0137,
|
|
"mean_token_accuracy": 0.1296630918979645,
|
|
"num_tokens": 3610371.0,
|
|
"step": 2080
|
|
},
|
|
{
|
|
"entropy": 6.166858434677124,
|
|
"epoch": 0.16222524800622448,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999197715479313,
|
|
"loss": 6.0274,
|
|
"mean_token_accuracy": 0.13334443271160126,
|
|
"num_tokens": 3618834.0,
|
|
"step": 2085
|
|
},
|
|
{
|
|
"entropy": 5.907374048233033,
|
|
"epoch": 0.16261427737794204,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999190297706489,
|
|
"loss": 6.0599,
|
|
"mean_token_accuracy": 0.1330284595489502,
|
|
"num_tokens": 3627426.0,
|
|
"step": 2090
|
|
},
|
|
{
|
|
"entropy": 6.1726648807525635,
|
|
"epoch": 0.1630033067496596,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004999182845805783,
|
|
"loss": 6.0783,
|
|
"mean_token_accuracy": 0.1352132059633732,
|
|
"num_tokens": 3636020.0,
|
|
"step": 2095
|
|
},
|
|
{
|
|
"entropy": 6.094464588165283,
|
|
"epoch": 0.16339233612137716,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999175359777306,
|
|
"loss": 6.0024,
|
|
"mean_token_accuracy": 0.13878497257828712,
|
|
"num_tokens": 3644419.0,
|
|
"step": 2100
|
|
},
|
|
{
|
|
"entropy": 5.983648729324341,
|
|
"epoch": 0.16378136549309472,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999167839621174,
|
|
"loss": 6.1132,
|
|
"mean_token_accuracy": 0.12433986812829971,
|
|
"num_tokens": 3653223.0,
|
|
"step": 2105
|
|
},
|
|
{
|
|
"entropy": 6.119035482406616,
|
|
"epoch": 0.1641703948648123,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999160285337501,
|
|
"loss": 6.1165,
|
|
"mean_token_accuracy": 0.12628517150878907,
|
|
"num_tokens": 3662409.0,
|
|
"step": 2110
|
|
},
|
|
{
|
|
"entropy": 6.122584199905395,
|
|
"epoch": 0.16455942423652986,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004999152696926399,
|
|
"loss": 6.0838,
|
|
"mean_token_accuracy": 0.12654283344745637,
|
|
"num_tokens": 3670635.0,
|
|
"step": 2115
|
|
},
|
|
{
|
|
"entropy": 5.966174030303955,
|
|
"epoch": 0.16494845360824742,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999145074387985,
|
|
"loss": 6.0089,
|
|
"mean_token_accuracy": 0.14118071272969246,
|
|
"num_tokens": 3679303.0,
|
|
"step": 2120
|
|
},
|
|
{
|
|
"entropy": 6.192105531692505,
|
|
"epoch": 0.16533748297996498,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999137417722374,
|
|
"loss": 6.1857,
|
|
"mean_token_accuracy": 0.1251898981630802,
|
|
"num_tokens": 3689299.0,
|
|
"step": 2125
|
|
},
|
|
{
|
|
"entropy": 6.109566402435303,
|
|
"epoch": 0.16572651235168256,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999129726929684,
|
|
"loss": 6.088,
|
|
"mean_token_accuracy": 0.13834489807486533,
|
|
"num_tokens": 3697843.0,
|
|
"step": 2130
|
|
},
|
|
{
|
|
"entropy": 6.1182887077331545,
|
|
"epoch": 0.16611554172340012,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999122002010029,
|
|
"loss": 6.0233,
|
|
"mean_token_accuracy": 0.1364858292043209,
|
|
"num_tokens": 3705876.0,
|
|
"step": 2135
|
|
},
|
|
{
|
|
"entropy": 6.109085321426392,
|
|
"epoch": 0.16650457109511768,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004999114242963527,
|
|
"loss": 6.1332,
|
|
"mean_token_accuracy": 0.12421078756451606,
|
|
"num_tokens": 3714835.0,
|
|
"step": 2140
|
|
},
|
|
{
|
|
"entropy": 6.028184270858764,
|
|
"epoch": 0.16689360046683524,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999106449790298,
|
|
"loss": 5.9968,
|
|
"mean_token_accuracy": 0.13307098522782326,
|
|
"num_tokens": 3723421.0,
|
|
"step": 2145
|
|
},
|
|
{
|
|
"entropy": 6.027436256408691,
|
|
"epoch": 0.1672826298385528,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999098622490458,
|
|
"loss": 6.0106,
|
|
"mean_token_accuracy": 0.13246056139469148,
|
|
"num_tokens": 3731590.0,
|
|
"step": 2150
|
|
},
|
|
{
|
|
"entropy": 6.005514812469483,
|
|
"epoch": 0.16767165921027039,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004999090761064125,
|
|
"loss": 5.9387,
|
|
"mean_token_accuracy": 0.13851954340934752,
|
|
"num_tokens": 3740700.0,
|
|
"step": 2155
|
|
},
|
|
{
|
|
"entropy": 6.0273407936096195,
|
|
"epoch": 0.16806068858198794,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000499908286551142,
|
|
"loss": 6.0128,
|
|
"mean_token_accuracy": 0.1371268466114998,
|
|
"num_tokens": 3749516.0,
|
|
"step": 2160
|
|
},
|
|
{
|
|
"entropy": 6.007265949249268,
|
|
"epoch": 0.1684497179537055,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004999074935832463,
|
|
"loss": 5.9506,
|
|
"mean_token_accuracy": 0.14042013585567475,
|
|
"num_tokens": 3757696.0,
|
|
"step": 2165
|
|
},
|
|
{
|
|
"entropy": 6.036279582977295,
|
|
"epoch": 0.16883874732542306,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999066972027373,
|
|
"loss": 6.0279,
|
|
"mean_token_accuracy": 0.13567456975579262,
|
|
"num_tokens": 3765786.0,
|
|
"step": 2170
|
|
},
|
|
{
|
|
"entropy": 5.970781230926514,
|
|
"epoch": 0.16922777669714065,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004999058974096271,
|
|
"loss": 5.9077,
|
|
"mean_token_accuracy": 0.1398158609867096,
|
|
"num_tokens": 3773265.0,
|
|
"step": 2175
|
|
},
|
|
{
|
|
"entropy": 6.03927173614502,
|
|
"epoch": 0.1696168060688582,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000499905094203928,
|
|
"loss": 6.0607,
|
|
"mean_token_accuracy": 0.13150161504745483,
|
|
"num_tokens": 3782402.0,
|
|
"step": 2180
|
|
},
|
|
{
|
|
"entropy": 6.0491118907928465,
|
|
"epoch": 0.17000583544057576,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000499904287585652,
|
|
"loss": 6.1228,
|
|
"mean_token_accuracy": 0.1305118791759014,
|
|
"num_tokens": 3791901.0,
|
|
"step": 2185
|
|
},
|
|
{
|
|
"entropy": 6.073975229263306,
|
|
"epoch": 0.17039486481229332,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999034775548113,
|
|
"loss": 5.9415,
|
|
"mean_token_accuracy": 0.14102055951952935,
|
|
"num_tokens": 3799872.0,
|
|
"step": 2190
|
|
},
|
|
{
|
|
"entropy": 5.967797756195068,
|
|
"epoch": 0.17078389418401088,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999026641114185,
|
|
"loss": 5.8987,
|
|
"mean_token_accuracy": 0.13859765678644181,
|
|
"num_tokens": 3808949.0,
|
|
"step": 2195
|
|
},
|
|
{
|
|
"entropy": 6.072041463851929,
|
|
"epoch": 0.17117292355572847,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004999018472554857,
|
|
"loss": 6.0097,
|
|
"mean_token_accuracy": 0.13413021862506866,
|
|
"num_tokens": 3817429.0,
|
|
"step": 2200
|
|
},
|
|
{
|
|
"entropy": 6.208354568481445,
|
|
"epoch": 0.17156195292744603,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999010269870253,
|
|
"loss": 6.2949,
|
|
"mean_token_accuracy": 0.12197455763816833,
|
|
"num_tokens": 3827101.0,
|
|
"step": 2205
|
|
},
|
|
{
|
|
"entropy": 6.107734298706054,
|
|
"epoch": 0.17195098229916359,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999002033060498,
|
|
"loss": 6.0075,
|
|
"mean_token_accuracy": 0.1353926807641983,
|
|
"num_tokens": 3836147.0,
|
|
"step": 2210
|
|
},
|
|
{
|
|
"entropy": 5.9734382152557375,
|
|
"epoch": 0.17234001167088114,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004998993762125716,
|
|
"loss": 6.0336,
|
|
"mean_token_accuracy": 0.13586182668805122,
|
|
"num_tokens": 3845300.0,
|
|
"step": 2215
|
|
},
|
|
{
|
|
"entropy": 6.102244281768799,
|
|
"epoch": 0.17272904104259873,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004998985457066034,
|
|
"loss": 6.0182,
|
|
"mean_token_accuracy": 0.1369253620505333,
|
|
"num_tokens": 3853620.0,
|
|
"step": 2220
|
|
},
|
|
{
|
|
"entropy": 6.035351324081421,
|
|
"epoch": 0.1731180704143163,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004998977117881576,
|
|
"loss": 6.0209,
|
|
"mean_token_accuracy": 0.13868235647678376,
|
|
"num_tokens": 3861734.0,
|
|
"step": 2225
|
|
},
|
|
{
|
|
"entropy": 6.056541538238525,
|
|
"epoch": 0.17350709978603385,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004998968744572472,
|
|
"loss": 6.0255,
|
|
"mean_token_accuracy": 0.13340835496783257,
|
|
"num_tokens": 3870753.0,
|
|
"step": 2230
|
|
},
|
|
{
|
|
"entropy": 6.01226224899292,
|
|
"epoch": 0.1738961291577514,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004998960337138845,
|
|
"loss": 5.901,
|
|
"mean_token_accuracy": 0.1386076405644417,
|
|
"num_tokens": 3879382.0,
|
|
"step": 2235
|
|
},
|
|
{
|
|
"entropy": 6.042281532287598,
|
|
"epoch": 0.17428515852946896,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004998951895580826,
|
|
"loss": 6.0833,
|
|
"mean_token_accuracy": 0.12960439622402192,
|
|
"num_tokens": 3888417.0,
|
|
"step": 2240
|
|
},
|
|
{
|
|
"entropy": 6.019704818725586,
|
|
"epoch": 0.17467418790118655,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004998943419898542,
|
|
"loss": 5.9544,
|
|
"mean_token_accuracy": 0.13442030027508736,
|
|
"num_tokens": 3897083.0,
|
|
"step": 2245
|
|
},
|
|
{
|
|
"entropy": 5.953819322586059,
|
|
"epoch": 0.1750632172729041,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004998934910092119,
|
|
"loss": 5.9233,
|
|
"mean_token_accuracy": 0.13848119750618934,
|
|
"num_tokens": 3905564.0,
|
|
"step": 2250
|
|
},
|
|
{
|
|
"entropy": 6.029740190505981,
|
|
"epoch": 0.17545224664462167,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004998926366161689,
|
|
"loss": 6.0581,
|
|
"mean_token_accuracy": 0.1252748928964138,
|
|
"num_tokens": 3914896.0,
|
|
"step": 2255
|
|
},
|
|
{
|
|
"entropy": 6.078394889831543,
|
|
"epoch": 0.17584127601633923,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004998917788107383,
|
|
"loss": 6.0724,
|
|
"mean_token_accuracy": 0.13376214429736139,
|
|
"num_tokens": 3924151.0,
|
|
"step": 2260
|
|
},
|
|
{
|
|
"entropy": 6.082054328918457,
|
|
"epoch": 0.17623030538805678,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004998909175929326,
|
|
"loss": 6.0164,
|
|
"mean_token_accuracy": 0.13435427844524384,
|
|
"num_tokens": 3933163.0,
|
|
"step": 2265
|
|
},
|
|
{
|
|
"entropy": 6.003792142868042,
|
|
"epoch": 0.17661933475977437,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004998900529627653,
|
|
"loss": 5.9297,
|
|
"mean_token_accuracy": 0.13886286765336991,
|
|
"num_tokens": 3941120.0,
|
|
"step": 2270
|
|
},
|
|
{
|
|
"entropy": 5.892064476013184,
|
|
"epoch": 0.17700836413149193,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004998891849202495,
|
|
"loss": 5.8359,
|
|
"mean_token_accuracy": 0.1366935320198536,
|
|
"num_tokens": 3949896.0,
|
|
"step": 2275
|
|
},
|
|
{
|
|
"entropy": 6.072416210174561,
|
|
"epoch": 0.1773973935032095,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000499888313465398,
|
|
"loss": 5.974,
|
|
"mean_token_accuracy": 0.14090991467237474,
|
|
"num_tokens": 3958794.0,
|
|
"step": 2280
|
|
},
|
|
{
|
|
"entropy": 5.998848390579224,
|
|
"epoch": 0.17778642287492705,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004998874385982247,
|
|
"loss": 6.0345,
|
|
"mean_token_accuracy": 0.1342969536781311,
|
|
"num_tokens": 3967267.0,
|
|
"step": 2285
|
|
},
|
|
{
|
|
"entropy": 5.955915451049805,
|
|
"epoch": 0.17817545224664463,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004998865603187421,
|
|
"loss": 5.9559,
|
|
"mean_token_accuracy": 0.1364803656935692,
|
|
"num_tokens": 3976536.0,
|
|
"step": 2290
|
|
},
|
|
{
|
|
"entropy": 6.106266164779663,
|
|
"epoch": 0.1785644816183622,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000499885678626964,
|
|
"loss": 6.022,
|
|
"mean_token_accuracy": 0.1321044869720936,
|
|
"num_tokens": 3986006.0,
|
|
"step": 2295
|
|
},
|
|
{
|
|
"entropy": 5.940597105026245,
|
|
"epoch": 0.17895351099007975,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004998847935229038,
|
|
"loss": 5.9638,
|
|
"mean_token_accuracy": 0.13107028752565383,
|
|
"num_tokens": 3994478.0,
|
|
"step": 2300
|
|
},
|
|
{
|
|
"entropy": 6.0922130107879635,
|
|
"epoch": 0.1793425403617973,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998839050065746,
|
|
"loss": 5.9898,
|
|
"mean_token_accuracy": 0.13526349514722824,
|
|
"num_tokens": 4003190.0,
|
|
"step": 2305
|
|
},
|
|
{
|
|
"entropy": 6.025421810150147,
|
|
"epoch": 0.17973156973351487,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998830130779902,
|
|
"loss": 5.9347,
|
|
"mean_token_accuracy": 0.13667116016149522,
|
|
"num_tokens": 4011886.0,
|
|
"step": 2310
|
|
},
|
|
{
|
|
"entropy": 5.891482496261597,
|
|
"epoch": 0.18012059910523245,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000499882117737164,
|
|
"loss": 5.8326,
|
|
"mean_token_accuracy": 0.13485828712582587,
|
|
"num_tokens": 4020792.0,
|
|
"step": 2315
|
|
},
|
|
{
|
|
"entropy": 5.931954765319825,
|
|
"epoch": 0.18050962847695,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004998812189841096,
|
|
"loss": 5.8219,
|
|
"mean_token_accuracy": 0.14047594219446183,
|
|
"num_tokens": 4029235.0,
|
|
"step": 2320
|
|
},
|
|
{
|
|
"entropy": 5.931398057937622,
|
|
"epoch": 0.18089865784866757,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004998803168188407,
|
|
"loss": 6.0385,
|
|
"mean_token_accuracy": 0.13752583786845207,
|
|
"num_tokens": 4037341.0,
|
|
"step": 2325
|
|
},
|
|
{
|
|
"entropy": 5.9774956703186035,
|
|
"epoch": 0.18128768722038513,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004998794112413708,
|
|
"loss": 5.9435,
|
|
"mean_token_accuracy": 0.13515810221433638,
|
|
"num_tokens": 4046324.0,
|
|
"step": 2330
|
|
},
|
|
{
|
|
"entropy": 5.988140821456909,
|
|
"epoch": 0.18167671659210272,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004998785022517137,
|
|
"loss": 5.9935,
|
|
"mean_token_accuracy": 0.13900482952594756,
|
|
"num_tokens": 4054579.0,
|
|
"step": 2335
|
|
},
|
|
{
|
|
"entropy": 6.065921449661255,
|
|
"epoch": 0.18206574596382027,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004998775898498835,
|
|
"loss": 5.9492,
|
|
"mean_token_accuracy": 0.14194765612483023,
|
|
"num_tokens": 4063087.0,
|
|
"step": 2340
|
|
},
|
|
{
|
|
"entropy": 6.072832870483398,
|
|
"epoch": 0.18245477533553783,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004998766740358936,
|
|
"loss": 6.0289,
|
|
"mean_token_accuracy": 0.13890346884727478,
|
|
"num_tokens": 4072309.0,
|
|
"step": 2345
|
|
},
|
|
{
|
|
"entropy": 6.000887250900268,
|
|
"epoch": 0.1828438047072554,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998757548097582,
|
|
"loss": 6.0795,
|
|
"mean_token_accuracy": 0.13404593393206596,
|
|
"num_tokens": 4081017.0,
|
|
"step": 2350
|
|
},
|
|
{
|
|
"entropy": 6.056308937072754,
|
|
"epoch": 0.18323283407897295,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004998748321714911,
|
|
"loss": 6.083,
|
|
"mean_token_accuracy": 0.13330470472574235,
|
|
"num_tokens": 4089799.0,
|
|
"step": 2355
|
|
},
|
|
{
|
|
"entropy": 6.006195831298828,
|
|
"epoch": 0.18362186345069054,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004998739061211065,
|
|
"loss": 6.0072,
|
|
"mean_token_accuracy": 0.1390180394053459,
|
|
"num_tokens": 4097948.0,
|
|
"step": 2360
|
|
},
|
|
{
|
|
"entropy": 6.019151639938355,
|
|
"epoch": 0.1840108928224081,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004998729766586181,
|
|
"loss": 5.8641,
|
|
"mean_token_accuracy": 0.13988614454865456,
|
|
"num_tokens": 4107050.0,
|
|
"step": 2365
|
|
},
|
|
{
|
|
"entropy": 5.934751653671265,
|
|
"epoch": 0.18439992219412565,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004998720437840403,
|
|
"loss": 5.904,
|
|
"mean_token_accuracy": 0.13505125269293786,
|
|
"num_tokens": 4115547.0,
|
|
"step": 2370
|
|
},
|
|
{
|
|
"entropy": 5.9610343933105465,
|
|
"epoch": 0.1847889515658432,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004998711074973871,
|
|
"loss": 5.9015,
|
|
"mean_token_accuracy": 0.13932024538517,
|
|
"num_tokens": 4124047.0,
|
|
"step": 2375
|
|
},
|
|
{
|
|
"entropy": 5.893201923370361,
|
|
"epoch": 0.1851779809375608,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004998701677986728,
|
|
"loss": 5.8559,
|
|
"mean_token_accuracy": 0.1403021939098835,
|
|
"num_tokens": 4132005.0,
|
|
"step": 2380
|
|
},
|
|
{
|
|
"entropy": 6.073483228683472,
|
|
"epoch": 0.18556701030927836,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004998692246879116,
|
|
"loss": 6.0277,
|
|
"mean_token_accuracy": 0.1299221158027649,
|
|
"num_tokens": 4140199.0,
|
|
"step": 2385
|
|
},
|
|
{
|
|
"entropy": 5.97588005065918,
|
|
"epoch": 0.18595603968099592,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004998682781651178,
|
|
"loss": 5.9748,
|
|
"mean_token_accuracy": 0.1365482524037361,
|
|
"num_tokens": 4149353.0,
|
|
"step": 2390
|
|
},
|
|
{
|
|
"entropy": 5.944373273849488,
|
|
"epoch": 0.18634506905271347,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004998673282303059,
|
|
"loss": 5.9579,
|
|
"mean_token_accuracy": 0.13471838161349298,
|
|
"num_tokens": 4158531.0,
|
|
"step": 2395
|
|
},
|
|
{
|
|
"entropy": 5.880623435974121,
|
|
"epoch": 0.18673409842443103,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004998663748834901,
|
|
"loss": 5.7368,
|
|
"mean_token_accuracy": 0.14892419204115867,
|
|
"num_tokens": 4166743.0,
|
|
"step": 2400
|
|
},
|
|
{
|
|
"entropy": 6.018037462234497,
|
|
"epoch": 0.18712312779614862,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004998654181246851,
|
|
"loss": 6.1001,
|
|
"mean_token_accuracy": 0.1294975347816944,
|
|
"num_tokens": 4175416.0,
|
|
"step": 2405
|
|
},
|
|
{
|
|
"entropy": 6.046519470214844,
|
|
"epoch": 0.18751215716786618,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004998644579539052,
|
|
"loss": 6.0364,
|
|
"mean_token_accuracy": 0.1348044417798519,
|
|
"num_tokens": 4185324.0,
|
|
"step": 2410
|
|
},
|
|
{
|
|
"entropy": 5.996607494354248,
|
|
"epoch": 0.18790118653958374,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000499863494371165,
|
|
"loss": 5.9524,
|
|
"mean_token_accuracy": 0.13784608691930772,
|
|
"num_tokens": 4193361.0,
|
|
"step": 2415
|
|
},
|
|
{
|
|
"entropy": 6.035355854034424,
|
|
"epoch": 0.1882902159113013,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004998625273764793,
|
|
"loss": 6.0001,
|
|
"mean_token_accuracy": 0.1302669644355774,
|
|
"num_tokens": 4202553.0,
|
|
"step": 2420
|
|
},
|
|
{
|
|
"entropy": 5.929054594039917,
|
|
"epoch": 0.18867924528301888,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004998615569698626,
|
|
"loss": 5.9479,
|
|
"mean_token_accuracy": 0.1433779552578926,
|
|
"num_tokens": 4211585.0,
|
|
"step": 2425
|
|
},
|
|
{
|
|
"entropy": 6.020910692214966,
|
|
"epoch": 0.18906827465473644,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004998605831513296,
|
|
"loss": 5.98,
|
|
"mean_token_accuracy": 0.13211928457021713,
|
|
"num_tokens": 4220829.0,
|
|
"step": 2430
|
|
},
|
|
{
|
|
"entropy": 5.951228189468384,
|
|
"epoch": 0.189457304026454,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004998596059208953,
|
|
"loss": 5.8953,
|
|
"mean_token_accuracy": 0.13831101283431052,
|
|
"num_tokens": 4228658.0,
|
|
"step": 2435
|
|
},
|
|
{
|
|
"entropy": 5.926197052001953,
|
|
"epoch": 0.18984633339817156,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004998586252785743,
|
|
"loss": 5.9772,
|
|
"mean_token_accuracy": 0.14194808825850486,
|
|
"num_tokens": 4237650.0,
|
|
"step": 2440
|
|
},
|
|
{
|
|
"entropy": 6.0081957340240475,
|
|
"epoch": 0.19023536276988912,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004998576412243816,
|
|
"loss": 5.9425,
|
|
"mean_token_accuracy": 0.13898246958851815,
|
|
"num_tokens": 4246701.0,
|
|
"step": 2445
|
|
},
|
|
{
|
|
"entropy": 5.968480920791626,
|
|
"epoch": 0.1906243921416067,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004998566537583321,
|
|
"loss": 5.9247,
|
|
"mean_token_accuracy": 0.13750442117452621,
|
|
"num_tokens": 4254541.0,
|
|
"step": 2450
|
|
},
|
|
{
|
|
"entropy": 5.9757208824157715,
|
|
"epoch": 0.19101342151332426,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004998556628804408,
|
|
"loss": 5.9488,
|
|
"mean_token_accuracy": 0.13661977127194405,
|
|
"num_tokens": 4263111.0,
|
|
"step": 2455
|
|
},
|
|
{
|
|
"entropy": 5.903095483779907,
|
|
"epoch": 0.19140245088504182,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004998546685907225,
|
|
"loss": 5.98,
|
|
"mean_token_accuracy": 0.13575077131390573,
|
|
"num_tokens": 4272796.0,
|
|
"step": 2460
|
|
},
|
|
{
|
|
"entropy": 5.948573637008667,
|
|
"epoch": 0.19179148025675938,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004998536708891927,
|
|
"loss": 5.8919,
|
|
"mean_token_accuracy": 0.1417429715394974,
|
|
"num_tokens": 4281361.0,
|
|
"step": 2465
|
|
},
|
|
{
|
|
"entropy": 6.026061391830444,
|
|
"epoch": 0.19218050962847694,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004998526697758663,
|
|
"loss": 5.9372,
|
|
"mean_token_accuracy": 0.13869260102510453,
|
|
"num_tokens": 4290470.0,
|
|
"step": 2470
|
|
},
|
|
{
|
|
"entropy": 5.973368835449219,
|
|
"epoch": 0.19256953900019452,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004998516652507585,
|
|
"loss": 5.9896,
|
|
"mean_token_accuracy": 0.1328210227191448,
|
|
"num_tokens": 4299087.0,
|
|
"step": 2475
|
|
},
|
|
{
|
|
"entropy": 5.942784452438355,
|
|
"epoch": 0.19295856837191208,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004998506573138846,
|
|
"loss": 5.8646,
|
|
"mean_token_accuracy": 0.1429189197719097,
|
|
"num_tokens": 4307572.0,
|
|
"step": 2480
|
|
},
|
|
{
|
|
"entropy": 5.963555192947387,
|
|
"epoch": 0.19334759774362964,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004998496459652598,
|
|
"loss": 5.9277,
|
|
"mean_token_accuracy": 0.14059290289878845,
|
|
"num_tokens": 4316337.0,
|
|
"step": 2485
|
|
},
|
|
{
|
|
"entropy": 6.075507640838623,
|
|
"epoch": 0.1937366271153472,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998486312048995,
|
|
"loss": 6.0435,
|
|
"mean_token_accuracy": 0.13950250148773194,
|
|
"num_tokens": 4326258.0,
|
|
"step": 2490
|
|
},
|
|
{
|
|
"entropy": 5.918562126159668,
|
|
"epoch": 0.19412565648706478,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004998476130328193,
|
|
"loss": 5.8813,
|
|
"mean_token_accuracy": 0.14137958139181137,
|
|
"num_tokens": 4334711.0,
|
|
"step": 2495
|
|
},
|
|
{
|
|
"entropy": 5.970353269577027,
|
|
"epoch": 0.19451468585878234,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998465914490343,
|
|
"loss": 5.9743,
|
|
"mean_token_accuracy": 0.13537674471735955,
|
|
"num_tokens": 4343739.0,
|
|
"step": 2500
|
|
},
|
|
{
|
|
"entropy": 5.954079532623291,
|
|
"epoch": 0.1949037152304999,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00049984556645356,
|
|
"loss": 5.9093,
|
|
"mean_token_accuracy": 0.1404120497405529,
|
|
"num_tokens": 4352905.0,
|
|
"step": 2505
|
|
},
|
|
{
|
|
"entropy": 6.014039754867554,
|
|
"epoch": 0.19529274460221746,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004998445380464124,
|
|
"loss": 5.9394,
|
|
"mean_token_accuracy": 0.14536958336830139,
|
|
"num_tokens": 4361333.0,
|
|
"step": 2510
|
|
},
|
|
{
|
|
"entropy": 5.888523912429809,
|
|
"epoch": 0.19568177397393502,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004998435062276066,
|
|
"loss": 5.8983,
|
|
"mean_token_accuracy": 0.13909753113985063,
|
|
"num_tokens": 4369872.0,
|
|
"step": 2515
|
|
},
|
|
{
|
|
"entropy": 5.987714862823486,
|
|
"epoch": 0.1960708033456526,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004998424709971586,
|
|
"loss": 5.965,
|
|
"mean_token_accuracy": 0.1441866084933281,
|
|
"num_tokens": 4378097.0,
|
|
"step": 2520
|
|
},
|
|
{
|
|
"entropy": 5.949221229553222,
|
|
"epoch": 0.19645983271737016,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004998414323550839,
|
|
"loss": 5.8936,
|
|
"mean_token_accuracy": 0.13887374848127365,
|
|
"num_tokens": 4387414.0,
|
|
"step": 2525
|
|
},
|
|
{
|
|
"entropy": 6.000862646102905,
|
|
"epoch": 0.19684886208908772,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004998403903013984,
|
|
"loss": 5.9835,
|
|
"mean_token_accuracy": 0.14411986842751504,
|
|
"num_tokens": 4395922.0,
|
|
"step": 2530
|
|
},
|
|
{
|
|
"entropy": 5.882594108581543,
|
|
"epoch": 0.19723789146080528,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004998393448361179,
|
|
"loss": 5.9476,
|
|
"mean_token_accuracy": 0.13559090122580528,
|
|
"num_tokens": 4404500.0,
|
|
"step": 2535
|
|
},
|
|
{
|
|
"entropy": 5.838614749908447,
|
|
"epoch": 0.19762692083252287,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000499838295959258,
|
|
"loss": 5.9285,
|
|
"mean_token_accuracy": 0.1404655933380127,
|
|
"num_tokens": 4413433.0,
|
|
"step": 2540
|
|
},
|
|
{
|
|
"entropy": 5.985950040817261,
|
|
"epoch": 0.19801595020424043,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000499837243670835,
|
|
"loss": 5.9686,
|
|
"mean_token_accuracy": 0.14125767052173616,
|
|
"num_tokens": 4421789.0,
|
|
"step": 2545
|
|
},
|
|
{
|
|
"entropy": 5.908414649963379,
|
|
"epoch": 0.19840497957595798,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004998361879708646,
|
|
"loss": 5.842,
|
|
"mean_token_accuracy": 0.14500181004405022,
|
|
"num_tokens": 4430256.0,
|
|
"step": 2550
|
|
},
|
|
{
|
|
"entropy": 5.934167671203613,
|
|
"epoch": 0.19879400894767554,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000499835128859363,
|
|
"loss": 5.8883,
|
|
"mean_token_accuracy": 0.13772125393152237,
|
|
"num_tokens": 4438431.0,
|
|
"step": 2555
|
|
},
|
|
{
|
|
"entropy": 5.989070034027099,
|
|
"epoch": 0.1991830383193931,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004998340663363461,
|
|
"loss": 5.9525,
|
|
"mean_token_accuracy": 0.13467848151922227,
|
|
"num_tokens": 4447150.0,
|
|
"step": 2560
|
|
},
|
|
{
|
|
"entropy": 5.908329772949219,
|
|
"epoch": 0.1995720676911107,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004998330004018301,
|
|
"loss": 5.8286,
|
|
"mean_token_accuracy": 0.1427350550889969,
|
|
"num_tokens": 4455181.0,
|
|
"step": 2565
|
|
},
|
|
{
|
|
"entropy": 5.937408065795898,
|
|
"epoch": 0.19996109706282825,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004998319310558312,
|
|
"loss": 5.8475,
|
|
"mean_token_accuracy": 0.14098502844572067,
|
|
"num_tokens": 4463361.0,
|
|
"step": 2570
|
|
},
|
|
{
|
|
"entropy": 5.972924375534058,
|
|
"epoch": 0.2003501264345458,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004998308582983657,
|
|
"loss": 5.9067,
|
|
"mean_token_accuracy": 0.14643627852201463,
|
|
"num_tokens": 4471853.0,
|
|
"step": 2575
|
|
},
|
|
{
|
|
"entropy": 5.81297550201416,
|
|
"epoch": 0.20073915580626336,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004998297821294497,
|
|
"loss": 5.8622,
|
|
"mean_token_accuracy": 0.14285662174224853,
|
|
"num_tokens": 4480812.0,
|
|
"step": 2580
|
|
},
|
|
{
|
|
"entropy": 6.017388820648193,
|
|
"epoch": 0.20112818517798095,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998287025490995,
|
|
"loss": 5.8837,
|
|
"mean_token_accuracy": 0.1472306877374649,
|
|
"num_tokens": 4489180.0,
|
|
"step": 2585
|
|
},
|
|
{
|
|
"entropy": 5.9446248531341555,
|
|
"epoch": 0.2015172145496985,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004998276195573317,
|
|
"loss": 5.9769,
|
|
"mean_token_accuracy": 0.13497108072042466,
|
|
"num_tokens": 4498013.0,
|
|
"step": 2590
|
|
},
|
|
{
|
|
"entropy": 6.0001615524292,
|
|
"epoch": 0.20190624392141607,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004998265331541627,
|
|
"loss": 6.0107,
|
|
"mean_token_accuracy": 0.12803680896759034,
|
|
"num_tokens": 4506767.0,
|
|
"step": 2595
|
|
},
|
|
{
|
|
"entropy": 6.023769521713257,
|
|
"epoch": 0.20229527329313363,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004998254433396088,
|
|
"loss": 6.0163,
|
|
"mean_token_accuracy": 0.13594405427575112,
|
|
"num_tokens": 4516657.0,
|
|
"step": 2600
|
|
},
|
|
{
|
|
"entropy": 5.886989116668701,
|
|
"epoch": 0.20268430266485118,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004998243501136867,
|
|
"loss": 5.8502,
|
|
"mean_token_accuracy": 0.14113568887114525,
|
|
"num_tokens": 4524980.0,
|
|
"step": 2605
|
|
},
|
|
{
|
|
"entropy": 5.9184175491333,
|
|
"epoch": 0.20307333203656877,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004998232534764129,
|
|
"loss": 5.9077,
|
|
"mean_token_accuracy": 0.14252403378486633,
|
|
"num_tokens": 4533236.0,
|
|
"step": 2610
|
|
},
|
|
{
|
|
"entropy": 5.863450002670288,
|
|
"epoch": 0.20346236140828633,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004998221534278041,
|
|
"loss": 5.8162,
|
|
"mean_token_accuracy": 0.14335810765624046,
|
|
"num_tokens": 4541778.0,
|
|
"step": 2615
|
|
},
|
|
{
|
|
"entropy": 5.959815788269043,
|
|
"epoch": 0.2038513907800039,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004998210499678769,
|
|
"loss": 5.923,
|
|
"mean_token_accuracy": 0.13540767207741738,
|
|
"num_tokens": 4551131.0,
|
|
"step": 2620
|
|
},
|
|
{
|
|
"entropy": 5.985937166213989,
|
|
"epoch": 0.20424042015172145,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004998199430966481,
|
|
"loss": 5.9087,
|
|
"mean_token_accuracy": 0.13660723865032195,
|
|
"num_tokens": 4559530.0,
|
|
"step": 2625
|
|
},
|
|
{
|
|
"entropy": 5.76199860572815,
|
|
"epoch": 0.20462944952343903,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004998188328141346,
|
|
"loss": 5.7991,
|
|
"mean_token_accuracy": 0.14168990179896354,
|
|
"num_tokens": 4567533.0,
|
|
"step": 2630
|
|
},
|
|
{
|
|
"entropy": 6.024087429046631,
|
|
"epoch": 0.2050184788951566,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004998177191203531,
|
|
"loss": 5.9456,
|
|
"mean_token_accuracy": 0.13533081263303756,
|
|
"num_tokens": 4576414.0,
|
|
"step": 2635
|
|
},
|
|
{
|
|
"entropy": 5.922002506256104,
|
|
"epoch": 0.20540750826687415,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004998166020153204,
|
|
"loss": 5.8799,
|
|
"mean_token_accuracy": 0.1403877317905426,
|
|
"num_tokens": 4585331.0,
|
|
"step": 2640
|
|
},
|
|
{
|
|
"entropy": 5.909115886688232,
|
|
"epoch": 0.2057965376385917,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004998154814990538,
|
|
"loss": 5.9162,
|
|
"mean_token_accuracy": 0.14347948133945465,
|
|
"num_tokens": 4593526.0,
|
|
"step": 2645
|
|
},
|
|
{
|
|
"entropy": 5.876611804962158,
|
|
"epoch": 0.20618556701030927,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00049981435757157,
|
|
"loss": 5.9093,
|
|
"mean_token_accuracy": 0.1371060587465763,
|
|
"num_tokens": 4602400.0,
|
|
"step": 2650
|
|
},
|
|
{
|
|
"entropy": 5.864795446395874,
|
|
"epoch": 0.20657459638202685,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004998132302328862,
|
|
"loss": 5.8555,
|
|
"mean_token_accuracy": 0.14304873943328858,
|
|
"num_tokens": 4611037.0,
|
|
"step": 2655
|
|
},
|
|
{
|
|
"entropy": 5.906079483032227,
|
|
"epoch": 0.2069636257537444,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004998120994830195,
|
|
"loss": 5.8705,
|
|
"mean_token_accuracy": 0.1427972808480263,
|
|
"num_tokens": 4619030.0,
|
|
"step": 2660
|
|
},
|
|
{
|
|
"entropy": 5.921322631835937,
|
|
"epoch": 0.20735265512546197,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000499810965321987,
|
|
"loss": 5.864,
|
|
"mean_token_accuracy": 0.1356546849012375,
|
|
"num_tokens": 4628649.0,
|
|
"step": 2665
|
|
},
|
|
{
|
|
"entropy": 5.863415861129761,
|
|
"epoch": 0.20774168449717953,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004998098277498059,
|
|
"loss": 5.7696,
|
|
"mean_token_accuracy": 0.14580075666308404,
|
|
"num_tokens": 4636935.0,
|
|
"step": 2670
|
|
},
|
|
{
|
|
"entropy": 5.887133026123047,
|
|
"epoch": 0.2081307138688971,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004998086867664934,
|
|
"loss": 5.9707,
|
|
"mean_token_accuracy": 0.13916994631290436,
|
|
"num_tokens": 4645532.0,
|
|
"step": 2675
|
|
},
|
|
{
|
|
"entropy": 6.022394037246704,
|
|
"epoch": 0.20851974324061467,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000499807542372067,
|
|
"loss": 6.0362,
|
|
"mean_token_accuracy": 0.13294412568211555,
|
|
"num_tokens": 4654433.0,
|
|
"step": 2680
|
|
},
|
|
{
|
|
"entropy": 6.088439798355102,
|
|
"epoch": 0.20890877261233223,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004998063945665439,
|
|
"loss": 6.0405,
|
|
"mean_token_accuracy": 0.1323567308485508,
|
|
"num_tokens": 4662913.0,
|
|
"step": 2685
|
|
},
|
|
{
|
|
"entropy": 5.968340587615967,
|
|
"epoch": 0.2092978019840498,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998052433499416,
|
|
"loss": 6.0029,
|
|
"mean_token_accuracy": 0.13033748045563698,
|
|
"num_tokens": 4672270.0,
|
|
"step": 2690
|
|
},
|
|
{
|
|
"entropy": 6.009377145767212,
|
|
"epoch": 0.20968683135576735,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004998040887222776,
|
|
"loss": 6.045,
|
|
"mean_token_accuracy": 0.1328607678413391,
|
|
"num_tokens": 4681428.0,
|
|
"step": 2695
|
|
},
|
|
{
|
|
"entropy": 5.998253345489502,
|
|
"epoch": 0.21007586072748494,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004998029306835693,
|
|
"loss": 5.8696,
|
|
"mean_token_accuracy": 0.14181804582476615,
|
|
"num_tokens": 4690492.0,
|
|
"step": 2700
|
|
},
|
|
{
|
|
"entropy": 5.976545810699463,
|
|
"epoch": 0.2104648900992025,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004998017692338344,
|
|
"loss": 5.9857,
|
|
"mean_token_accuracy": 0.13384222462773324,
|
|
"num_tokens": 4699667.0,
|
|
"step": 2705
|
|
},
|
|
{
|
|
"entropy": 5.75888295173645,
|
|
"epoch": 0.21085391947092005,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004998006043730905,
|
|
"loss": 5.6552,
|
|
"mean_token_accuracy": 0.1563888520002365,
|
|
"num_tokens": 4708529.0,
|
|
"step": 2710
|
|
},
|
|
{
|
|
"entropy": 5.798262882232666,
|
|
"epoch": 0.2112429488426376,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004997994361013551,
|
|
"loss": 5.9154,
|
|
"mean_token_accuracy": 0.13552722483873367,
|
|
"num_tokens": 4717684.0,
|
|
"step": 2715
|
|
},
|
|
{
|
|
"entropy": 5.907504463195801,
|
|
"epoch": 0.21163197821435517,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004997982644186461,
|
|
"loss": 5.8459,
|
|
"mean_token_accuracy": 0.14533798694610595,
|
|
"num_tokens": 4727067.0,
|
|
"step": 2720
|
|
},
|
|
{
|
|
"entropy": 5.893569469451904,
|
|
"epoch": 0.21202100758607276,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004997970893249813,
|
|
"loss": 5.8291,
|
|
"mean_token_accuracy": 0.14064672365784645,
|
|
"num_tokens": 4735434.0,
|
|
"step": 2725
|
|
},
|
|
{
|
|
"entropy": 5.894484281539917,
|
|
"epoch": 0.21241003695779032,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004997959108203785,
|
|
"loss": 5.8669,
|
|
"mean_token_accuracy": 0.14163699969649315,
|
|
"num_tokens": 4743843.0,
|
|
"step": 2730
|
|
},
|
|
{
|
|
"entropy": 6.0105119228363035,
|
|
"epoch": 0.21279906632950787,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004997947289048554,
|
|
"loss": 5.9142,
|
|
"mean_token_accuracy": 0.1434435725212097,
|
|
"num_tokens": 4753228.0,
|
|
"step": 2735
|
|
},
|
|
{
|
|
"entropy": 5.9337730884552,
|
|
"epoch": 0.21318809570122543,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004997935435784302,
|
|
"loss": 5.9959,
|
|
"mean_token_accuracy": 0.13996100500226022,
|
|
"num_tokens": 4763401.0,
|
|
"step": 2740
|
|
},
|
|
{
|
|
"entropy": 5.934045076370239,
|
|
"epoch": 0.21357712507294302,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004997923548411208,
|
|
"loss": 5.8468,
|
|
"mean_token_accuracy": 0.14104977995157242,
|
|
"num_tokens": 4771812.0,
|
|
"step": 2745
|
|
},
|
|
{
|
|
"entropy": 5.906756114959717,
|
|
"epoch": 0.21396615444466058,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000499791162692945,
|
|
"loss": 5.8769,
|
|
"mean_token_accuracy": 0.14148839563131332,
|
|
"num_tokens": 4780616.0,
|
|
"step": 2750
|
|
},
|
|
{
|
|
"entropy": 5.880796670913696,
|
|
"epoch": 0.21435518381637814,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004997899671339214,
|
|
"loss": 5.8714,
|
|
"mean_token_accuracy": 0.1407567411661148,
|
|
"num_tokens": 4789886.0,
|
|
"step": 2755
|
|
},
|
|
{
|
|
"entropy": 5.902111768722534,
|
|
"epoch": 0.2147442131880957,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004997887681640675,
|
|
"loss": 5.8659,
|
|
"mean_token_accuracy": 0.1388687163591385,
|
|
"num_tokens": 4799189.0,
|
|
"step": 2760
|
|
},
|
|
{
|
|
"entropy": 5.9799223899841305,
|
|
"epoch": 0.21513324255981325,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004997875657834021,
|
|
"loss": 5.9074,
|
|
"mean_token_accuracy": 0.14284486845135688,
|
|
"num_tokens": 4807850.0,
|
|
"step": 2765
|
|
},
|
|
{
|
|
"entropy": 5.920933198928833,
|
|
"epoch": 0.21552227193153084,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004997863599919432,
|
|
"loss": 5.8206,
|
|
"mean_token_accuracy": 0.14280714765191077,
|
|
"num_tokens": 4815742.0,
|
|
"step": 2770
|
|
},
|
|
{
|
|
"entropy": 5.91602783203125,
|
|
"epoch": 0.2159113013032484,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004997851507897089,
|
|
"loss": 5.9167,
|
|
"mean_token_accuracy": 0.14030473083257675,
|
|
"num_tokens": 4824761.0,
|
|
"step": 2775
|
|
},
|
|
{
|
|
"entropy": 6.005980825424194,
|
|
"epoch": 0.21630033067496596,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004997839381767178,
|
|
"loss": 6.023,
|
|
"mean_token_accuracy": 0.13371331468224526,
|
|
"num_tokens": 4832805.0,
|
|
"step": 2780
|
|
},
|
|
{
|
|
"entropy": 5.939170408248901,
|
|
"epoch": 0.21668936004668352,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004997827221529882,
|
|
"loss": 5.8843,
|
|
"mean_token_accuracy": 0.14137587547302247,
|
|
"num_tokens": 4841938.0,
|
|
"step": 2785
|
|
},
|
|
{
|
|
"entropy": 5.92487063407898,
|
|
"epoch": 0.2170783894184011,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004997815027185386,
|
|
"loss": 5.9011,
|
|
"mean_token_accuracy": 0.13681731075048448,
|
|
"num_tokens": 4849932.0,
|
|
"step": 2790
|
|
},
|
|
{
|
|
"entropy": 5.821724700927734,
|
|
"epoch": 0.21746741879011866,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004997802798733874,
|
|
"loss": 5.779,
|
|
"mean_token_accuracy": 0.14767844080924988,
|
|
"num_tokens": 4859054.0,
|
|
"step": 2795
|
|
},
|
|
{
|
|
"entropy": 6.00215711593628,
|
|
"epoch": 0.21785644816183622,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004997790536175534,
|
|
"loss": 5.9348,
|
|
"mean_token_accuracy": 0.14400338754057884,
|
|
"num_tokens": 4867415.0,
|
|
"step": 2800
|
|
},
|
|
{
|
|
"entropy": 5.9811138153076175,
|
|
"epoch": 0.21824547753355378,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004997778239510548,
|
|
"loss": 5.9799,
|
|
"mean_token_accuracy": 0.1346263289451599,
|
|
"num_tokens": 4875965.0,
|
|
"step": 2805
|
|
},
|
|
{
|
|
"entropy": 5.946578025817871,
|
|
"epoch": 0.21863450690527134,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004997765908739106,
|
|
"loss": 5.868,
|
|
"mean_token_accuracy": 0.1421209491789341,
|
|
"num_tokens": 4884629.0,
|
|
"step": 2810
|
|
},
|
|
{
|
|
"entropy": 5.920269346237182,
|
|
"epoch": 0.21902353627698892,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004997753543861395,
|
|
"loss": 5.9236,
|
|
"mean_token_accuracy": 0.14194096624851227,
|
|
"num_tokens": 4893573.0,
|
|
"step": 2815
|
|
},
|
|
{
|
|
"entropy": 5.871851634979248,
|
|
"epoch": 0.21941256564870648,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00049977411448776,
|
|
"loss": 5.8508,
|
|
"mean_token_accuracy": 0.14088700339198112,
|
|
"num_tokens": 4902831.0,
|
|
"step": 2820
|
|
},
|
|
{
|
|
"entropy": 6.002893781661987,
|
|
"epoch": 0.21980159502042404,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004997728711787912,
|
|
"loss": 5.9012,
|
|
"mean_token_accuracy": 0.13369439616799356,
|
|
"num_tokens": 4911360.0,
|
|
"step": 2825
|
|
},
|
|
{
|
|
"entropy": 5.933447265625,
|
|
"epoch": 0.2201906243921416,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004997716244592518,
|
|
"loss": 5.856,
|
|
"mean_token_accuracy": 0.1380616083741188,
|
|
"num_tokens": 4919758.0,
|
|
"step": 2830
|
|
},
|
|
{
|
|
"entropy": 5.814820194244385,
|
|
"epoch": 0.22057965376385918,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004997703743291607,
|
|
"loss": 5.7524,
|
|
"mean_token_accuracy": 0.15023381486535073,
|
|
"num_tokens": 4928934.0,
|
|
"step": 2835
|
|
},
|
|
{
|
|
"entropy": 5.785764932632446,
|
|
"epoch": 0.22096868313557674,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000499769120788537,
|
|
"loss": 5.8125,
|
|
"mean_token_accuracy": 0.1431200847029686,
|
|
"num_tokens": 4937780.0,
|
|
"step": 2840
|
|
},
|
|
{
|
|
"entropy": 6.037427234649658,
|
|
"epoch": 0.2213577125072943,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004997678638373995,
|
|
"loss": 5.9051,
|
|
"mean_token_accuracy": 0.1383948467671871,
|
|
"num_tokens": 4946862.0,
|
|
"step": 2845
|
|
},
|
|
{
|
|
"entropy": 5.868165636062622,
|
|
"epoch": 0.22174674187901186,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004997666034757676,
|
|
"loss": 5.887,
|
|
"mean_token_accuracy": 0.14369800984859465,
|
|
"num_tokens": 4954883.0,
|
|
"step": 2850
|
|
},
|
|
{
|
|
"entropy": 5.797883749008179,
|
|
"epoch": 0.22213577125072942,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004997653397036603,
|
|
"loss": 5.6813,
|
|
"mean_token_accuracy": 0.15522562339901924,
|
|
"num_tokens": 4962840.0,
|
|
"step": 2855
|
|
},
|
|
{
|
|
"entropy": 5.835611629486084,
|
|
"epoch": 0.222524800622447,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004997640725210965,
|
|
"loss": 5.9223,
|
|
"mean_token_accuracy": 0.14193681627511978,
|
|
"num_tokens": 4972334.0,
|
|
"step": 2860
|
|
},
|
|
{
|
|
"entropy": 5.9330864429473875,
|
|
"epoch": 0.22291382999416456,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004997628019280958,
|
|
"loss": 5.8871,
|
|
"mean_token_accuracy": 0.14560381472110748,
|
|
"num_tokens": 4981032.0,
|
|
"step": 2865
|
|
},
|
|
{
|
|
"entropy": 5.886129903793335,
|
|
"epoch": 0.22330285936588212,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004997615279246773,
|
|
"loss": 5.914,
|
|
"mean_token_accuracy": 0.14388557896018028,
|
|
"num_tokens": 4990502.0,
|
|
"step": 2870
|
|
},
|
|
{
|
|
"entropy": 6.024803590774536,
|
|
"epoch": 0.22369188873759968,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004997602505108603,
|
|
"loss": 6.0752,
|
|
"mean_token_accuracy": 0.13173774257302284,
|
|
"num_tokens": 4999121.0,
|
|
"step": 2875
|
|
},
|
|
{
|
|
"entropy": 5.972172689437866,
|
|
"epoch": 0.22408091810931724,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004997589696866644,
|
|
"loss": 5.8406,
|
|
"mean_token_accuracy": 0.14171420633792878,
|
|
"num_tokens": 5007271.0,
|
|
"step": 2880
|
|
},
|
|
{
|
|
"entropy": 5.839230108261108,
|
|
"epoch": 0.22446994748103483,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004997576854521088,
|
|
"loss": 5.8827,
|
|
"mean_token_accuracy": 0.13617974072694777,
|
|
"num_tokens": 5015940.0,
|
|
"step": 2885
|
|
},
|
|
{
|
|
"entropy": 5.812696170806885,
|
|
"epoch": 0.22485897685275238,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000499756397807213,
|
|
"loss": 5.781,
|
|
"mean_token_accuracy": 0.14219485297799112,
|
|
"num_tokens": 5024294.0,
|
|
"step": 2890
|
|
},
|
|
{
|
|
"entropy": 5.876422786712647,
|
|
"epoch": 0.22524800622446994,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004997551067519966,
|
|
"loss": 5.7615,
|
|
"mean_token_accuracy": 0.15088033750653268,
|
|
"num_tokens": 5033401.0,
|
|
"step": 2895
|
|
},
|
|
{
|
|
"entropy": 5.839484453201294,
|
|
"epoch": 0.2256370355961875,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004997538122864792,
|
|
"loss": 5.8552,
|
|
"mean_token_accuracy": 0.1417061373591423,
|
|
"num_tokens": 5041955.0,
|
|
"step": 2900
|
|
},
|
|
{
|
|
"entropy": 5.92848014831543,
|
|
"epoch": 0.2260260649679051,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004997525144106804,
|
|
"loss": 5.898,
|
|
"mean_token_accuracy": 0.13416951149702072,
|
|
"num_tokens": 5051132.0,
|
|
"step": 2905
|
|
},
|
|
{
|
|
"entropy": 5.7870166301727295,
|
|
"epoch": 0.22641509433962265,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00049975121312462,
|
|
"loss": 5.8046,
|
|
"mean_token_accuracy": 0.14889086335897445,
|
|
"num_tokens": 5059492.0,
|
|
"step": 2910
|
|
},
|
|
{
|
|
"entropy": 5.853955602645874,
|
|
"epoch": 0.2268041237113402,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004997499084283177,
|
|
"loss": 5.8692,
|
|
"mean_token_accuracy": 0.143447807431221,
|
|
"num_tokens": 5069015.0,
|
|
"step": 2915
|
|
},
|
|
{
|
|
"entropy": 5.916986465454102,
|
|
"epoch": 0.22719315308305776,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004997486003217932,
|
|
"loss": 5.8649,
|
|
"mean_token_accuracy": 0.14138873815536498,
|
|
"num_tokens": 5077614.0,
|
|
"step": 2920
|
|
},
|
|
{
|
|
"entropy": 5.828479671478272,
|
|
"epoch": 0.22758218245477532,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004997472888050664,
|
|
"loss": 5.8007,
|
|
"mean_token_accuracy": 0.1477051630616188,
|
|
"num_tokens": 5086300.0,
|
|
"step": 2925
|
|
},
|
|
{
|
|
"entropy": 5.84206714630127,
|
|
"epoch": 0.2279712118264929,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004997459738781573,
|
|
"loss": 5.8453,
|
|
"mean_token_accuracy": 0.1453349806368351,
|
|
"num_tokens": 5095967.0,
|
|
"step": 2930
|
|
},
|
|
{
|
|
"entropy": 5.8847919464111325,
|
|
"epoch": 0.22836024119821047,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004997446555410857,
|
|
"loss": 5.8065,
|
|
"mean_token_accuracy": 0.14551942944526672,
|
|
"num_tokens": 5104611.0,
|
|
"step": 2935
|
|
},
|
|
{
|
|
"entropy": 5.818680095672607,
|
|
"epoch": 0.22874927056992803,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004997433337938716,
|
|
"loss": 5.7603,
|
|
"mean_token_accuracy": 0.14727237671613694,
|
|
"num_tokens": 5113452.0,
|
|
"step": 2940
|
|
},
|
|
{
|
|
"entropy": 5.7687592029571535,
|
|
"epoch": 0.22913829994164558,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004997420086365351,
|
|
"loss": 5.7552,
|
|
"mean_token_accuracy": 0.1463024787604809,
|
|
"num_tokens": 5121558.0,
|
|
"step": 2945
|
|
},
|
|
{
|
|
"entropy": 5.800099563598633,
|
|
"epoch": 0.22952732931336317,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004997406800690966,
|
|
"loss": 5.7291,
|
|
"mean_token_accuracy": 0.158209228515625,
|
|
"num_tokens": 5129942.0,
|
|
"step": 2950
|
|
},
|
|
{
|
|
"entropy": 5.918742609024048,
|
|
"epoch": 0.22991635868508073,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004997393480915758,
|
|
"loss": 5.8627,
|
|
"mean_token_accuracy": 0.13658782318234444,
|
|
"num_tokens": 5139012.0,
|
|
"step": 2955
|
|
},
|
|
{
|
|
"entropy": 5.898570966720581,
|
|
"epoch": 0.2303053880567983,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004997380127039931,
|
|
"loss": 5.8623,
|
|
"mean_token_accuracy": 0.1460738256573677,
|
|
"num_tokens": 5148185.0,
|
|
"step": 2960
|
|
},
|
|
{
|
|
"entropy": 5.961733865737915,
|
|
"epoch": 0.23069441742851585,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004997366739063688,
|
|
"loss": 5.8949,
|
|
"mean_token_accuracy": 0.1355762153863907,
|
|
"num_tokens": 5157086.0,
|
|
"step": 2965
|
|
},
|
|
{
|
|
"entropy": 5.97607455253601,
|
|
"epoch": 0.2310834468002334,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004997353316987231,
|
|
"loss": 5.9666,
|
|
"mean_token_accuracy": 0.13954457640647888,
|
|
"num_tokens": 5165842.0,
|
|
"step": 2970
|
|
},
|
|
{
|
|
"entropy": 5.937599039077758,
|
|
"epoch": 0.231472476171951,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004997339860810765,
|
|
"loss": 5.9787,
|
|
"mean_token_accuracy": 0.1414493590593338,
|
|
"num_tokens": 5174161.0,
|
|
"step": 2975
|
|
},
|
|
{
|
|
"entropy": 5.968914127349853,
|
|
"epoch": 0.23186150554366855,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004997326370534495,
|
|
"loss": 5.8987,
|
|
"mean_token_accuracy": 0.1409076064825058,
|
|
"num_tokens": 5183830.0,
|
|
"step": 2980
|
|
},
|
|
{
|
|
"entropy": 5.895692634582519,
|
|
"epoch": 0.2322505349153861,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004997312846158622,
|
|
"loss": 5.8161,
|
|
"mean_token_accuracy": 0.14208230078220369,
|
|
"num_tokens": 5192248.0,
|
|
"step": 2985
|
|
},
|
|
{
|
|
"entropy": 5.817179870605469,
|
|
"epoch": 0.23263956428710367,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004997299287683355,
|
|
"loss": 5.7776,
|
|
"mean_token_accuracy": 0.1490553967654705,
|
|
"num_tokens": 5201212.0,
|
|
"step": 2990
|
|
},
|
|
{
|
|
"entropy": 5.853628253936767,
|
|
"epoch": 0.23302859365882125,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004997285695108898,
|
|
"loss": 5.8421,
|
|
"mean_token_accuracy": 0.14157011210918427,
|
|
"num_tokens": 5209338.0,
|
|
"step": 2995
|
|
},
|
|
{
|
|
"entropy": 5.974374198913575,
|
|
"epoch": 0.2334176230305388,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004997272068435458,
|
|
"loss": 5.8576,
|
|
"mean_token_accuracy": 0.14298054277896882,
|
|
"num_tokens": 5217590.0,
|
|
"step": 3000
|
|
},
|
|
{
|
|
"epoch": 0.2334176230305388,
|
|
"eval_entropy": 5.72153007830417,
|
|
"eval_loss": 5.904752254486084,
|
|
"eval_mean_token_accuracy": 0.14778396588919596,
|
|
"eval_num_tokens": 5217590.0,
|
|
"eval_runtime": 28.7542,
|
|
"eval_samples_per_second": 1445.286,
|
|
"eval_steps_per_second": 180.669,
|
|
"step": 3000
|
|
},
|
|
{
|
|
"entropy": 5.8005329132080075,
|
|
"epoch": 0.23380665240225637,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000499725840766324,
|
|
"loss": 5.7915,
|
|
"mean_token_accuracy": 0.14410673528909684,
|
|
"num_tokens": 5226383.0,
|
|
"step": 3005
|
|
},
|
|
{
|
|
"entropy": 5.920779180526734,
|
|
"epoch": 0.23419568177397393,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004997244712792453,
|
|
"loss": 5.8243,
|
|
"mean_token_accuracy": 0.1450793609023094,
|
|
"num_tokens": 5235517.0,
|
|
"step": 3010
|
|
},
|
|
{
|
|
"entropy": 5.9037463665008545,
|
|
"epoch": 0.2345847111456915,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004997230983823305,
|
|
"loss": 5.799,
|
|
"mean_token_accuracy": 0.15086298882961274,
|
|
"num_tokens": 5243812.0,
|
|
"step": 3015
|
|
},
|
|
{
|
|
"entropy": 5.84418740272522,
|
|
"epoch": 0.23497374051740907,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004997217220756003,
|
|
"loss": 5.817,
|
|
"mean_token_accuracy": 0.14579055458307266,
|
|
"num_tokens": 5252399.0,
|
|
"step": 3020
|
|
},
|
|
{
|
|
"entropy": 5.86341438293457,
|
|
"epoch": 0.23536276988912663,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004997203423590757,
|
|
"loss": 5.8496,
|
|
"mean_token_accuracy": 0.14410731792449952,
|
|
"num_tokens": 5260847.0,
|
|
"step": 3025
|
|
},
|
|
{
|
|
"entropy": 5.9321190357208256,
|
|
"epoch": 0.2357517992608442,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004997189592327775,
|
|
"loss": 5.8993,
|
|
"mean_token_accuracy": 0.13984145000576972,
|
|
"num_tokens": 5268847.0,
|
|
"step": 3030
|
|
},
|
|
{
|
|
"entropy": 5.912533950805664,
|
|
"epoch": 0.23614082863256175,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004997175726967268,
|
|
"loss": 5.8449,
|
|
"mean_token_accuracy": 0.1432294562458992,
|
|
"num_tokens": 5277989.0,
|
|
"step": 3035
|
|
},
|
|
{
|
|
"entropy": 5.807249355316162,
|
|
"epoch": 0.23652985800427934,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004997161827509447,
|
|
"loss": 5.8298,
|
|
"mean_token_accuracy": 0.14517134800553322,
|
|
"num_tokens": 5286272.0,
|
|
"step": 3040
|
|
},
|
|
{
|
|
"entropy": 5.843175888061523,
|
|
"epoch": 0.2369188873759969,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004997147893954521,
|
|
"loss": 5.8561,
|
|
"mean_token_accuracy": 0.14687449485063553,
|
|
"num_tokens": 5295281.0,
|
|
"step": 3045
|
|
},
|
|
{
|
|
"entropy": 5.927417421340943,
|
|
"epoch": 0.23730791674771445,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004997133926302702,
|
|
"loss": 5.7811,
|
|
"mean_token_accuracy": 0.147725660353899,
|
|
"num_tokens": 5303905.0,
|
|
"step": 3050
|
|
},
|
|
{
|
|
"entropy": 5.8274088382720945,
|
|
"epoch": 0.237696946119432,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004997119924554204,
|
|
"loss": 5.7698,
|
|
"mean_token_accuracy": 0.14279649034142494,
|
|
"num_tokens": 5313146.0,
|
|
"step": 3055
|
|
},
|
|
{
|
|
"entropy": 5.812492322921753,
|
|
"epoch": 0.23808597549114957,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004997105888709236,
|
|
"loss": 5.8213,
|
|
"mean_token_accuracy": 0.1478417322039604,
|
|
"num_tokens": 5320838.0,
|
|
"step": 3060
|
|
},
|
|
{
|
|
"entropy": 5.884876251220703,
|
|
"epoch": 0.23847500486286716,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004997091818768015,
|
|
"loss": 5.8272,
|
|
"mean_token_accuracy": 0.14175651222467422,
|
|
"num_tokens": 5329312.0,
|
|
"step": 3065
|
|
},
|
|
{
|
|
"entropy": 5.842220640182495,
|
|
"epoch": 0.23886403423458472,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000499707771473075,
|
|
"loss": 5.8239,
|
|
"mean_token_accuracy": 0.14224815219640732,
|
|
"num_tokens": 5337747.0,
|
|
"step": 3070
|
|
},
|
|
{
|
|
"entropy": 5.890048694610596,
|
|
"epoch": 0.23925306360630227,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004997063576597659,
|
|
"loss": 5.82,
|
|
"mean_token_accuracy": 0.13902755007147788,
|
|
"num_tokens": 5346928.0,
|
|
"step": 3075
|
|
},
|
|
{
|
|
"entropy": 5.860515022277832,
|
|
"epoch": 0.23964209297801983,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004997049404368954,
|
|
"loss": 5.8373,
|
|
"mean_token_accuracy": 0.13793924003839492,
|
|
"num_tokens": 5355827.0,
|
|
"step": 3080
|
|
},
|
|
{
|
|
"entropy": 5.991226482391357,
|
|
"epoch": 0.2400311223497374,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000499703519804485,
|
|
"loss": 5.9741,
|
|
"mean_token_accuracy": 0.13731370642781257,
|
|
"num_tokens": 5364309.0,
|
|
"step": 3085
|
|
},
|
|
{
|
|
"entropy": 5.884651184082031,
|
|
"epoch": 0.24042015172145498,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004997020957625564,
|
|
"loss": 5.868,
|
|
"mean_token_accuracy": 0.1458408921957016,
|
|
"num_tokens": 5372979.0,
|
|
"step": 3090
|
|
},
|
|
{
|
|
"entropy": 5.857665157318115,
|
|
"epoch": 0.24080918109317254,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004997006683111312,
|
|
"loss": 5.8287,
|
|
"mean_token_accuracy": 0.14318791329860686,
|
|
"num_tokens": 5381809.0,
|
|
"step": 3095
|
|
},
|
|
{
|
|
"entropy": 5.925519943237305,
|
|
"epoch": 0.2411982104648901,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000499699237450231,
|
|
"loss": 5.8886,
|
|
"mean_token_accuracy": 0.14159021526575089,
|
|
"num_tokens": 5390036.0,
|
|
"step": 3100
|
|
},
|
|
{
|
|
"entropy": 5.988127946853638,
|
|
"epoch": 0.24158723983660765,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004996978031798774,
|
|
"loss": 5.9362,
|
|
"mean_token_accuracy": 0.13715847954154015,
|
|
"num_tokens": 5398739.0,
|
|
"step": 3105
|
|
},
|
|
{
|
|
"entropy": 5.866925144195557,
|
|
"epoch": 0.24197626920832524,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004996963655000924,
|
|
"loss": 5.8508,
|
|
"mean_token_accuracy": 0.13922770768404008,
|
|
"num_tokens": 5407441.0,
|
|
"step": 3110
|
|
},
|
|
{
|
|
"entropy": 5.887317657470703,
|
|
"epoch": 0.2423652985800428,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004996949244108977,
|
|
"loss": 5.8102,
|
|
"mean_token_accuracy": 0.14160098806023597,
|
|
"num_tokens": 5416534.0,
|
|
"step": 3115
|
|
},
|
|
{
|
|
"entropy": 5.842632818222046,
|
|
"epoch": 0.24275432795176036,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000499693479912315,
|
|
"loss": 5.8628,
|
|
"mean_token_accuracy": 0.14435580223798752,
|
|
"num_tokens": 5425170.0,
|
|
"step": 3120
|
|
},
|
|
{
|
|
"entropy": 5.8731931209564205,
|
|
"epoch": 0.24314335732347792,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004996920320043666,
|
|
"loss": 5.826,
|
|
"mean_token_accuracy": 0.13852888271212577,
|
|
"num_tokens": 5433721.0,
|
|
"step": 3125
|
|
},
|
|
{
|
|
"entropy": 5.938917779922486,
|
|
"epoch": 0.24353238669519547,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004996905806870742,
|
|
"loss": 5.8817,
|
|
"mean_token_accuracy": 0.1431050829589367,
|
|
"num_tokens": 5441708.0,
|
|
"step": 3130
|
|
},
|
|
{
|
|
"entropy": 5.844237279891968,
|
|
"epoch": 0.24392141606691306,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004996891259604598,
|
|
"loss": 5.7866,
|
|
"mean_token_accuracy": 0.14370601251721382,
|
|
"num_tokens": 5449942.0,
|
|
"step": 3135
|
|
},
|
|
{
|
|
"entropy": 5.880588436126709,
|
|
"epoch": 0.24431044543863062,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004996876678245455,
|
|
"loss": 5.7923,
|
|
"mean_token_accuracy": 0.1475344941020012,
|
|
"num_tokens": 5458004.0,
|
|
"step": 3140
|
|
},
|
|
{
|
|
"entropy": 5.9699300765991214,
|
|
"epoch": 0.24469947481034818,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004996862062793536,
|
|
"loss": 5.8779,
|
|
"mean_token_accuracy": 0.1441954031586647,
|
|
"num_tokens": 5467071.0,
|
|
"step": 3145
|
|
},
|
|
{
|
|
"entropy": 5.882994031906128,
|
|
"epoch": 0.24508850418206574,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004996847413249061,
|
|
"loss": 5.8592,
|
|
"mean_token_accuracy": 0.14534298777580262,
|
|
"num_tokens": 5476221.0,
|
|
"step": 3150
|
|
},
|
|
{
|
|
"entropy": 5.889163970947266,
|
|
"epoch": 0.24547753355378332,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004996832729612252,
|
|
"loss": 5.7781,
|
|
"mean_token_accuracy": 0.1421756461262703,
|
|
"num_tokens": 5484549.0,
|
|
"step": 3155
|
|
},
|
|
{
|
|
"entropy": 5.770286703109742,
|
|
"epoch": 0.24586656292550088,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004996818011883333,
|
|
"loss": 5.7796,
|
|
"mean_token_accuracy": 0.1462826058268547,
|
|
"num_tokens": 5492909.0,
|
|
"step": 3160
|
|
},
|
|
{
|
|
"entropy": 5.878460454940796,
|
|
"epoch": 0.24625559229721844,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004996803260062527,
|
|
"loss": 5.8447,
|
|
"mean_token_accuracy": 0.1453042894601822,
|
|
"num_tokens": 5501418.0,
|
|
"step": 3165
|
|
},
|
|
{
|
|
"entropy": 5.947468614578247,
|
|
"epoch": 0.246644621668936,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004996788474150057,
|
|
"loss": 5.8269,
|
|
"mean_token_accuracy": 0.14394153654575348,
|
|
"num_tokens": 5510609.0,
|
|
"step": 3170
|
|
},
|
|
{
|
|
"entropy": 5.731346225738525,
|
|
"epoch": 0.24703365104065356,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004996773654146149,
|
|
"loss": 5.6813,
|
|
"mean_token_accuracy": 0.1574917584657669,
|
|
"num_tokens": 5518349.0,
|
|
"step": 3175
|
|
},
|
|
{
|
|
"entropy": 5.728027200698852,
|
|
"epoch": 0.24742268041237114,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004996758800051026,
|
|
"loss": 5.625,
|
|
"mean_token_accuracy": 0.15064212381839753,
|
|
"num_tokens": 5526972.0,
|
|
"step": 3180
|
|
},
|
|
{
|
|
"entropy": 5.777186107635498,
|
|
"epoch": 0.2478117097840887,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004996743911864916,
|
|
"loss": 5.8014,
|
|
"mean_token_accuracy": 0.14768730401992797,
|
|
"num_tokens": 5535683.0,
|
|
"step": 3185
|
|
},
|
|
{
|
|
"entropy": 5.830631589889526,
|
|
"epoch": 0.24820073915580626,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004996728989588041,
|
|
"loss": 5.7698,
|
|
"mean_token_accuracy": 0.15127997547388078,
|
|
"num_tokens": 5544258.0,
|
|
"step": 3190
|
|
},
|
|
{
|
|
"entropy": 5.7605572700500485,
|
|
"epoch": 0.24858976852752382,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004996714033220632,
|
|
"loss": 5.7839,
|
|
"mean_token_accuracy": 0.14324464723467828,
|
|
"num_tokens": 5552608.0,
|
|
"step": 3195
|
|
},
|
|
{
|
|
"entropy": 5.882555913925171,
|
|
"epoch": 0.2489787978992414,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004996699042762911,
|
|
"loss": 5.911,
|
|
"mean_token_accuracy": 0.13898452371358871,
|
|
"num_tokens": 5561357.0,
|
|
"step": 3200
|
|
},
|
|
{
|
|
"entropy": 5.895790910720825,
|
|
"epoch": 0.24936782727095896,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004996684018215111,
|
|
"loss": 5.7385,
|
|
"mean_token_accuracy": 0.15563871711492538,
|
|
"num_tokens": 5569862.0,
|
|
"step": 3205
|
|
},
|
|
{
|
|
"entropy": 5.797485113143921,
|
|
"epoch": 0.24975685664267652,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004996668959577453,
|
|
"loss": 5.803,
|
|
"mean_token_accuracy": 0.148903951048851,
|
|
"num_tokens": 5578485.0,
|
|
"step": 3210
|
|
},
|
|
{
|
|
"entropy": 5.792536973953247,
|
|
"epoch": 0.2501458860143941,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004996653866850173,
|
|
"loss": 5.7815,
|
|
"mean_token_accuracy": 0.13914278522133827,
|
|
"num_tokens": 5587713.0,
|
|
"step": 3215
|
|
},
|
|
{
|
|
"entropy": 5.876435041427612,
|
|
"epoch": 0.25053491538611167,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004996638740033495,
|
|
"loss": 5.8683,
|
|
"mean_token_accuracy": 0.14536678940057754,
|
|
"num_tokens": 5596541.0,
|
|
"step": 3220
|
|
},
|
|
{
|
|
"entropy": 5.836820125579834,
|
|
"epoch": 0.2509239447578292,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004996623579127651,
|
|
"loss": 5.7374,
|
|
"mean_token_accuracy": 0.1486624523997307,
|
|
"num_tokens": 5605573.0,
|
|
"step": 3225
|
|
},
|
|
{
|
|
"entropy": 5.815556573867798,
|
|
"epoch": 0.2513129741295468,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004996608384132868,
|
|
"loss": 5.7302,
|
|
"mean_token_accuracy": 0.15229415744543076,
|
|
"num_tokens": 5614016.0,
|
|
"step": 3230
|
|
},
|
|
{
|
|
"entropy": 5.929158639907837,
|
|
"epoch": 0.25170200350126437,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000499659315504938,
|
|
"loss": 5.9714,
|
|
"mean_token_accuracy": 0.1410625085234642,
|
|
"num_tokens": 5622451.0,
|
|
"step": 3235
|
|
},
|
|
{
|
|
"entropy": 5.871538591384888,
|
|
"epoch": 0.2520910328729819,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004996577891877417,
|
|
"loss": 5.8263,
|
|
"mean_token_accuracy": 0.1432577043771744,
|
|
"num_tokens": 5631384.0,
|
|
"step": 3240
|
|
},
|
|
{
|
|
"entropy": 5.845392656326294,
|
|
"epoch": 0.2524800622446995,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004996562594617209,
|
|
"loss": 5.787,
|
|
"mean_token_accuracy": 0.14552973359823226,
|
|
"num_tokens": 5640726.0,
|
|
"step": 3245
|
|
},
|
|
{
|
|
"entropy": 5.880887746810913,
|
|
"epoch": 0.252869091616417,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004996547263268991,
|
|
"loss": 5.7875,
|
|
"mean_token_accuracy": 0.14155513122677804,
|
|
"num_tokens": 5648948.0,
|
|
"step": 3250
|
|
},
|
|
{
|
|
"entropy": 5.727876091003418,
|
|
"epoch": 0.2532581209881346,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004996531897832993,
|
|
"loss": 5.7484,
|
|
"mean_token_accuracy": 0.14809300750494003,
|
|
"num_tokens": 5657951.0,
|
|
"step": 3255
|
|
},
|
|
{
|
|
"entropy": 5.896551561355591,
|
|
"epoch": 0.2536471503598522,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000499651649830945,
|
|
"loss": 5.8633,
|
|
"mean_token_accuracy": 0.14910533055663108,
|
|
"num_tokens": 5667476.0,
|
|
"step": 3260
|
|
},
|
|
{
|
|
"entropy": 5.904336595535279,
|
|
"epoch": 0.2540361797315697,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004996501064698593,
|
|
"loss": 5.8708,
|
|
"mean_token_accuracy": 0.14054447636008263,
|
|
"num_tokens": 5676627.0,
|
|
"step": 3265
|
|
},
|
|
{
|
|
"entropy": 5.7955468654632565,
|
|
"epoch": 0.2544252091032873,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000499648559700066,
|
|
"loss": 5.7879,
|
|
"mean_token_accuracy": 0.15155547559261323,
|
|
"num_tokens": 5684376.0,
|
|
"step": 3270
|
|
},
|
|
{
|
|
"entropy": 5.905218029022217,
|
|
"epoch": 0.25481423847500484,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004996470095215884,
|
|
"loss": 5.9569,
|
|
"mean_token_accuracy": 0.133226178586483,
|
|
"num_tokens": 5693629.0,
|
|
"step": 3275
|
|
},
|
|
{
|
|
"entropy": 5.966583728790283,
|
|
"epoch": 0.2552032678467224,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004996454559344498,
|
|
"loss": 5.8397,
|
|
"mean_token_accuracy": 0.14316044747829437,
|
|
"num_tokens": 5702010.0,
|
|
"step": 3280
|
|
},
|
|
{
|
|
"entropy": 5.7592079639434814,
|
|
"epoch": 0.25559229721844,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004996438989386741,
|
|
"loss": 5.7497,
|
|
"mean_token_accuracy": 0.14288737773895263,
|
|
"num_tokens": 5710823.0,
|
|
"step": 3285
|
|
},
|
|
{
|
|
"entropy": 5.851301670074463,
|
|
"epoch": 0.25598132659015754,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004996423385342847,
|
|
"loss": 5.7971,
|
|
"mean_token_accuracy": 0.15071944296360015,
|
|
"num_tokens": 5719389.0,
|
|
"step": 3290
|
|
},
|
|
{
|
|
"entropy": 5.921173000335694,
|
|
"epoch": 0.25637035596187513,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004996407747213055,
|
|
"loss": 5.7838,
|
|
"mean_token_accuracy": 0.14567249342799188,
|
|
"num_tokens": 5727327.0,
|
|
"step": 3295
|
|
},
|
|
{
|
|
"entropy": 5.809784698486328,
|
|
"epoch": 0.25675938533359266,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00049963920749976,
|
|
"loss": 5.6969,
|
|
"mean_token_accuracy": 0.15062555074691772,
|
|
"num_tokens": 5735886.0,
|
|
"step": 3300
|
|
},
|
|
{
|
|
"entropy": 5.797888612747192,
|
|
"epoch": 0.25714841470531025,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004996376368696721,
|
|
"loss": 5.7431,
|
|
"mean_token_accuracy": 0.1468089461326599,
|
|
"num_tokens": 5744656.0,
|
|
"step": 3305
|
|
},
|
|
{
|
|
"entropy": 5.88851490020752,
|
|
"epoch": 0.25753744407702783,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004996360628310656,
|
|
"loss": 5.9045,
|
|
"mean_token_accuracy": 0.13661069944500923,
|
|
"num_tokens": 5753026.0,
|
|
"step": 3310
|
|
},
|
|
{
|
|
"entropy": 5.876181364059448,
|
|
"epoch": 0.25792647344874536,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004996344853839644,
|
|
"loss": 5.8452,
|
|
"mean_token_accuracy": 0.14359349012374878,
|
|
"num_tokens": 5762771.0,
|
|
"step": 3315
|
|
},
|
|
{
|
|
"entropy": 5.826467847824096,
|
|
"epoch": 0.25831550282046295,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004996329045283924,
|
|
"loss": 5.8225,
|
|
"mean_token_accuracy": 0.15036021620035173,
|
|
"num_tokens": 5771151.0,
|
|
"step": 3320
|
|
},
|
|
{
|
|
"entropy": 5.829469013214111,
|
|
"epoch": 0.25870453219218054,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004996313202643737,
|
|
"loss": 5.7301,
|
|
"mean_token_accuracy": 0.14670131206512452,
|
|
"num_tokens": 5780648.0,
|
|
"step": 3325
|
|
},
|
|
{
|
|
"entropy": 5.801216411590576,
|
|
"epoch": 0.25909356156389807,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004996297325919321,
|
|
"loss": 5.7089,
|
|
"mean_token_accuracy": 0.14597562104463577,
|
|
"num_tokens": 5789698.0,
|
|
"step": 3330
|
|
},
|
|
{
|
|
"entropy": 5.902236461639404,
|
|
"epoch": 0.25948259093561565,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004996281415110919,
|
|
"loss": 5.9083,
|
|
"mean_token_accuracy": 0.13697285056114197,
|
|
"num_tokens": 5799218.0,
|
|
"step": 3335
|
|
},
|
|
{
|
|
"entropy": 5.800975608825683,
|
|
"epoch": 0.2598716203073332,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004996265470218773,
|
|
"loss": 5.7761,
|
|
"mean_token_accuracy": 0.14101554378867148,
|
|
"num_tokens": 5808455.0,
|
|
"step": 3340
|
|
},
|
|
{
|
|
"entropy": 5.86399564743042,
|
|
"epoch": 0.26026064967905077,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004996249491243122,
|
|
"loss": 5.8026,
|
|
"mean_token_accuracy": 0.14507102519273757,
|
|
"num_tokens": 5816464.0,
|
|
"step": 3345
|
|
},
|
|
{
|
|
"entropy": 5.831243515014648,
|
|
"epoch": 0.26064967905076836,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004996233478184211,
|
|
"loss": 5.7665,
|
|
"mean_token_accuracy": 0.1419643133878708,
|
|
"num_tokens": 5825188.0,
|
|
"step": 3350
|
|
},
|
|
{
|
|
"entropy": 5.816180896759033,
|
|
"epoch": 0.2610387084224859,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004996217431042282,
|
|
"loss": 5.8148,
|
|
"mean_token_accuracy": 0.14716667979955672,
|
|
"num_tokens": 5834150.0,
|
|
"step": 3355
|
|
},
|
|
{
|
|
"entropy": 5.8475151538848875,
|
|
"epoch": 0.2614277377942035,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000499620134981758,
|
|
"loss": 5.6758,
|
|
"mean_token_accuracy": 0.15172670781612396,
|
|
"num_tokens": 5842801.0,
|
|
"step": 3360
|
|
},
|
|
{
|
|
"entropy": 5.8005210876464846,
|
|
"epoch": 0.261816767165921,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004996185234510346,
|
|
"loss": 5.7071,
|
|
"mean_token_accuracy": 0.15291839390993117,
|
|
"num_tokens": 5851547.0,
|
|
"step": 3365
|
|
},
|
|
{
|
|
"entropy": 5.862095355987549,
|
|
"epoch": 0.2622057965376386,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004996169085120828,
|
|
"loss": 5.8569,
|
|
"mean_token_accuracy": 0.1441195249557495,
|
|
"num_tokens": 5860430.0,
|
|
"step": 3370
|
|
},
|
|
{
|
|
"entropy": 5.778133964538574,
|
|
"epoch": 0.2625948259093562,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004996152901649268,
|
|
"loss": 5.7645,
|
|
"mean_token_accuracy": 0.1446751818060875,
|
|
"num_tokens": 5869648.0,
|
|
"step": 3375
|
|
},
|
|
{
|
|
"entropy": 5.897901725769043,
|
|
"epoch": 0.2629838552810737,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004996136684095913,
|
|
"loss": 5.7754,
|
|
"mean_token_accuracy": 0.14787262827157974,
|
|
"num_tokens": 5878606.0,
|
|
"step": 3380
|
|
},
|
|
{
|
|
"entropy": 5.817872047424316,
|
|
"epoch": 0.2633728846527913,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004996120432461009,
|
|
"loss": 5.8403,
|
|
"mean_token_accuracy": 0.1442799985408783,
|
|
"num_tokens": 5886772.0,
|
|
"step": 3385
|
|
},
|
|
{
|
|
"entropy": 5.80500373840332,
|
|
"epoch": 0.2637619140245088,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004996104146744804,
|
|
"loss": 5.7437,
|
|
"mean_token_accuracy": 0.1436271235346794,
|
|
"num_tokens": 5895007.0,
|
|
"step": 3390
|
|
},
|
|
{
|
|
"entropy": 5.937970876693726,
|
|
"epoch": 0.2641509433962264,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004996087826947541,
|
|
"loss": 5.8675,
|
|
"mean_token_accuracy": 0.13643872514367103,
|
|
"num_tokens": 5904249.0,
|
|
"step": 3395
|
|
},
|
|
{
|
|
"entropy": 5.748004293441772,
|
|
"epoch": 0.264539972767944,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004996071473069471,
|
|
"loss": 5.8357,
|
|
"mean_token_accuracy": 0.1466163992881775,
|
|
"num_tokens": 5911416.0,
|
|
"step": 3400
|
|
},
|
|
{
|
|
"entropy": 5.873762226104736,
|
|
"epoch": 0.26492900213966153,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004996055085110842,
|
|
"loss": 5.875,
|
|
"mean_token_accuracy": 0.14148805439472198,
|
|
"num_tokens": 5920370.0,
|
|
"step": 3405
|
|
},
|
|
{
|
|
"entropy": 5.922806882858277,
|
|
"epoch": 0.2653180315113791,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004996038663071902,
|
|
"loss": 5.8398,
|
|
"mean_token_accuracy": 0.14385833963751793,
|
|
"num_tokens": 5928884.0,
|
|
"step": 3410
|
|
},
|
|
{
|
|
"entropy": 5.857811307907104,
|
|
"epoch": 0.26570706088309665,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004996022206952901,
|
|
"loss": 5.857,
|
|
"mean_token_accuracy": 0.13694723397493364,
|
|
"num_tokens": 5938456.0,
|
|
"step": 3415
|
|
},
|
|
{
|
|
"entropy": 5.915801191329956,
|
|
"epoch": 0.26609609025481423,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004996005716754086,
|
|
"loss": 5.8785,
|
|
"mean_token_accuracy": 0.14502357617020606,
|
|
"num_tokens": 5947157.0,
|
|
"step": 3420
|
|
},
|
|
{
|
|
"entropy": 5.856646108627319,
|
|
"epoch": 0.2664851196265318,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000499598919247571,
|
|
"loss": 5.7374,
|
|
"mean_token_accuracy": 0.15310335159301758,
|
|
"num_tokens": 5956084.0,
|
|
"step": 3425
|
|
},
|
|
{
|
|
"entropy": 5.784454250335694,
|
|
"epoch": 0.26687414899824935,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004995972634118023,
|
|
"loss": 5.7743,
|
|
"mean_token_accuracy": 0.14791329205036163,
|
|
"num_tokens": 5964782.0,
|
|
"step": 3430
|
|
},
|
|
{
|
|
"entropy": 5.885459470748901,
|
|
"epoch": 0.26726317836996694,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004995956041681277,
|
|
"loss": 5.9786,
|
|
"mean_token_accuracy": 0.13400535508990288,
|
|
"num_tokens": 5974013.0,
|
|
"step": 3435
|
|
},
|
|
{
|
|
"entropy": 5.869965076446533,
|
|
"epoch": 0.2676522077416845,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004995939415165722,
|
|
"loss": 5.85,
|
|
"mean_token_accuracy": 0.14296992719173432,
|
|
"num_tokens": 5983351.0,
|
|
"step": 3440
|
|
},
|
|
{
|
|
"entropy": 5.8040210723876955,
|
|
"epoch": 0.26804123711340205,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004995922754571611,
|
|
"loss": 5.6754,
|
|
"mean_token_accuracy": 0.15375011265277863,
|
|
"num_tokens": 5992084.0,
|
|
"step": 3445
|
|
},
|
|
{
|
|
"entropy": 5.711496829986572,
|
|
"epoch": 0.26843026648511964,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004995906059899197,
|
|
"loss": 5.7014,
|
|
"mean_token_accuracy": 0.1504288472235203,
|
|
"num_tokens": 6001043.0,
|
|
"step": 3450
|
|
},
|
|
{
|
|
"entropy": 5.7762144088745115,
|
|
"epoch": 0.26881929585683717,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004995889331148733,
|
|
"loss": 5.7247,
|
|
"mean_token_accuracy": 0.14711771607398988,
|
|
"num_tokens": 6009620.0,
|
|
"step": 3455
|
|
},
|
|
{
|
|
"entropy": 5.789427089691162,
|
|
"epoch": 0.26920832522855476,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004995872568320474,
|
|
"loss": 5.7209,
|
|
"mean_token_accuracy": 0.1434781163930893,
|
|
"num_tokens": 6018278.0,
|
|
"step": 3460
|
|
},
|
|
{
|
|
"entropy": 5.775634527206421,
|
|
"epoch": 0.26959735460027234,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004995855771414673,
|
|
"loss": 5.7694,
|
|
"mean_token_accuracy": 0.14877430200576783,
|
|
"num_tokens": 6026741.0,
|
|
"step": 3465
|
|
},
|
|
{
|
|
"entropy": 5.8912004947662355,
|
|
"epoch": 0.2699863839719899,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004995838940431585,
|
|
"loss": 5.7922,
|
|
"mean_token_accuracy": 0.14324328750371934,
|
|
"num_tokens": 6035370.0,
|
|
"step": 3470
|
|
},
|
|
{
|
|
"entropy": 5.831309652328491,
|
|
"epoch": 0.27037541334370746,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004995822075371466,
|
|
"loss": 5.7808,
|
|
"mean_token_accuracy": 0.1441688671708107,
|
|
"num_tokens": 6044372.0,
|
|
"step": 3475
|
|
},
|
|
{
|
|
"entropy": 5.8337959289550785,
|
|
"epoch": 0.270764442715425,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004995805176234571,
|
|
"loss": 5.7907,
|
|
"mean_token_accuracy": 0.1507210314273834,
|
|
"num_tokens": 6052940.0,
|
|
"step": 3480
|
|
},
|
|
{
|
|
"entropy": 5.863040447235107,
|
|
"epoch": 0.2711534720871426,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004995788243021158,
|
|
"loss": 5.7137,
|
|
"mean_token_accuracy": 0.1456463798880577,
|
|
"num_tokens": 6062048.0,
|
|
"step": 3485
|
|
},
|
|
{
|
|
"entropy": 5.742090702056885,
|
|
"epoch": 0.27154250145886016,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004995771275731483,
|
|
"loss": 5.7422,
|
|
"mean_token_accuracy": 0.14996225386857986,
|
|
"num_tokens": 6071478.0,
|
|
"step": 3490
|
|
},
|
|
{
|
|
"entropy": 5.718463277816772,
|
|
"epoch": 0.2719315308305777,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004995754274365802,
|
|
"loss": 5.6752,
|
|
"mean_token_accuracy": 0.15684566050767898,
|
|
"num_tokens": 6080495.0,
|
|
"step": 3495
|
|
},
|
|
{
|
|
"entropy": 5.880794525146484,
|
|
"epoch": 0.2723205602022953,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004995737238924376,
|
|
"loss": 5.8302,
|
|
"mean_token_accuracy": 0.13611356019973755,
|
|
"num_tokens": 6090141.0,
|
|
"step": 3500
|
|
},
|
|
{
|
|
"entropy": 5.855888843536377,
|
|
"epoch": 0.2727095895740128,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004995720169407461,
|
|
"loss": 5.7909,
|
|
"mean_token_accuracy": 0.14242940098047258,
|
|
"num_tokens": 6099215.0,
|
|
"step": 3505
|
|
},
|
|
{
|
|
"entropy": 5.864683771133423,
|
|
"epoch": 0.2730986189457304,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004995703065815317,
|
|
"loss": 5.8744,
|
|
"mean_token_accuracy": 0.13853381276130677,
|
|
"num_tokens": 6108802.0,
|
|
"step": 3510
|
|
},
|
|
{
|
|
"entropy": 5.982160949707032,
|
|
"epoch": 0.273487648317448,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004995685928148203,
|
|
"loss": 5.8708,
|
|
"mean_token_accuracy": 0.14367551431059838,
|
|
"num_tokens": 6117486.0,
|
|
"step": 3515
|
|
},
|
|
{
|
|
"entropy": 5.751517820358276,
|
|
"epoch": 0.2738766776891655,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.000499566875640638,
|
|
"loss": 5.691,
|
|
"mean_token_accuracy": 0.15760284960269927,
|
|
"num_tokens": 6125248.0,
|
|
"step": 3520
|
|
},
|
|
{
|
|
"entropy": 5.816810512542725,
|
|
"epoch": 0.2742657070608831,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004995651550590108,
|
|
"loss": 5.7458,
|
|
"mean_token_accuracy": 0.14610794484615325,
|
|
"num_tokens": 6134831.0,
|
|
"step": 3525
|
|
},
|
|
{
|
|
"entropy": 5.793434810638428,
|
|
"epoch": 0.2746547364326007,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004995634310699647,
|
|
"loss": 5.8221,
|
|
"mean_token_accuracy": 0.1443501353263855,
|
|
"num_tokens": 6143248.0,
|
|
"step": 3530
|
|
},
|
|
{
|
|
"entropy": 5.8795264720916744,
|
|
"epoch": 0.2750437658043182,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004995617036735261,
|
|
"loss": 5.829,
|
|
"mean_token_accuracy": 0.14278091713786126,
|
|
"num_tokens": 6151768.0,
|
|
"step": 3535
|
|
},
|
|
{
|
|
"entropy": 5.806972646713257,
|
|
"epoch": 0.2754327951760358,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004995599728697211,
|
|
"loss": 5.716,
|
|
"mean_token_accuracy": 0.15529972016811372,
|
|
"num_tokens": 6160091.0,
|
|
"step": 3540
|
|
},
|
|
{
|
|
"entropy": 5.80297966003418,
|
|
"epoch": 0.27582182454775334,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004995582386585759,
|
|
"loss": 5.8261,
|
|
"mean_token_accuracy": 0.1379936493933201,
|
|
"num_tokens": 6169440.0,
|
|
"step": 3545
|
|
},
|
|
{
|
|
"entropy": 5.845169639587402,
|
|
"epoch": 0.2762108539194709,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004995565010401167,
|
|
"loss": 5.7921,
|
|
"mean_token_accuracy": 0.14506490528583527,
|
|
"num_tokens": 6177604.0,
|
|
"step": 3550
|
|
},
|
|
{
|
|
"entropy": 5.884006500244141,
|
|
"epoch": 0.2765998832911885,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004995547600143702,
|
|
"loss": 5.8005,
|
|
"mean_token_accuracy": 0.13861700221896173,
|
|
"num_tokens": 6186252.0,
|
|
"step": 3555
|
|
},
|
|
{
|
|
"entropy": 5.80251636505127,
|
|
"epoch": 0.27698891266290604,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004995530155813625,
|
|
"loss": 5.7424,
|
|
"mean_token_accuracy": 0.1510542720556259,
|
|
"num_tokens": 6194641.0,
|
|
"step": 3560
|
|
},
|
|
{
|
|
"entropy": 5.8658629894256595,
|
|
"epoch": 0.2773779420346236,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004995512677411203,
|
|
"loss": 5.8756,
|
|
"mean_token_accuracy": 0.14317311719059944,
|
|
"num_tokens": 6203925.0,
|
|
"step": 3565
|
|
},
|
|
{
|
|
"entropy": 5.895973205566406,
|
|
"epoch": 0.27776697140634116,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004995495164936698,
|
|
"loss": 5.7566,
|
|
"mean_token_accuracy": 0.14684337750077248,
|
|
"num_tokens": 6213001.0,
|
|
"step": 3570
|
|
},
|
|
{
|
|
"entropy": 5.795819807052612,
|
|
"epoch": 0.27815600077805874,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004995477618390381,
|
|
"loss": 5.7686,
|
|
"mean_token_accuracy": 0.1391209714114666,
|
|
"num_tokens": 6221754.0,
|
|
"step": 3575
|
|
},
|
|
{
|
|
"entropy": 5.763400554656982,
|
|
"epoch": 0.27854503014977633,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004995460037772513,
|
|
"loss": 5.6719,
|
|
"mean_token_accuracy": 0.14914391040802003,
|
|
"num_tokens": 6229792.0,
|
|
"step": 3580
|
|
},
|
|
{
|
|
"entropy": 5.773159742355347,
|
|
"epoch": 0.27893405952149386,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004995442423083365,
|
|
"loss": 5.7772,
|
|
"mean_token_accuracy": 0.14420934915542602,
|
|
"num_tokens": 6238839.0,
|
|
"step": 3585
|
|
},
|
|
{
|
|
"entropy": 5.84812970161438,
|
|
"epoch": 0.27932308889321145,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004995424774323201,
|
|
"loss": 5.6807,
|
|
"mean_token_accuracy": 0.14983972907066345,
|
|
"num_tokens": 6246939.0,
|
|
"step": 3590
|
|
},
|
|
{
|
|
"entropy": 5.830242109298706,
|
|
"epoch": 0.279712118264929,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000499540709149229,
|
|
"loss": 5.8123,
|
|
"mean_token_accuracy": 0.1413383439183235,
|
|
"num_tokens": 6255858.0,
|
|
"step": 3595
|
|
},
|
|
{
|
|
"entropy": 5.772054052352905,
|
|
"epoch": 0.28010114763664656,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004995389374590901,
|
|
"loss": 5.7289,
|
|
"mean_token_accuracy": 0.14664228558540343,
|
|
"num_tokens": 6265137.0,
|
|
"step": 3600
|
|
},
|
|
{
|
|
"entropy": 5.795121526718139,
|
|
"epoch": 0.28049017700836415,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004995371623619301,
|
|
"loss": 5.727,
|
|
"mean_token_accuracy": 0.14856354743242264,
|
|
"num_tokens": 6273286.0,
|
|
"step": 3605
|
|
},
|
|
{
|
|
"entropy": 5.699319839477539,
|
|
"epoch": 0.2808792063800817,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000499535383857776,
|
|
"loss": 5.7434,
|
|
"mean_token_accuracy": 0.1431848406791687,
|
|
"num_tokens": 6282477.0,
|
|
"step": 3610
|
|
},
|
|
{
|
|
"entropy": 5.889150619506836,
|
|
"epoch": 0.28126823575179927,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000499533601946655,
|
|
"loss": 5.7949,
|
|
"mean_token_accuracy": 0.14193343818187715,
|
|
"num_tokens": 6291756.0,
|
|
"step": 3615
|
|
},
|
|
{
|
|
"entropy": 5.8616869926452635,
|
|
"epoch": 0.2816572651235168,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004995318166285938,
|
|
"loss": 5.8663,
|
|
"mean_token_accuracy": 0.13642492145299911,
|
|
"num_tokens": 6301093.0,
|
|
"step": 3620
|
|
},
|
|
{
|
|
"entropy": 5.8186732769012455,
|
|
"epoch": 0.2820462944952344,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004995300279036199,
|
|
"loss": 5.6829,
|
|
"mean_token_accuracy": 0.15127351135015488,
|
|
"num_tokens": 6310379.0,
|
|
"step": 3625
|
|
},
|
|
{
|
|
"entropy": 5.775457906723022,
|
|
"epoch": 0.28243532386695197,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00049952823577176,
|
|
"loss": 5.7066,
|
|
"mean_token_accuracy": 0.1457876168191433,
|
|
"num_tokens": 6318983.0,
|
|
"step": 3630
|
|
},
|
|
{
|
|
"entropy": 5.753813028335571,
|
|
"epoch": 0.2828243532386695,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004995264402330416,
|
|
"loss": 5.7176,
|
|
"mean_token_accuracy": 0.15276553630828857,
|
|
"num_tokens": 6327816.0,
|
|
"step": 3635
|
|
},
|
|
{
|
|
"entropy": 5.794705772399903,
|
|
"epoch": 0.2832133826103871,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004995246412874919,
|
|
"loss": 5.8038,
|
|
"mean_token_accuracy": 0.14400455206632615,
|
|
"num_tokens": 6336693.0,
|
|
"step": 3640
|
|
},
|
|
{
|
|
"entropy": 5.853319835662842,
|
|
"epoch": 0.2836024119821047,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000499522838935138,
|
|
"loss": 5.7451,
|
|
"mean_token_accuracy": 0.14893249571323394,
|
|
"num_tokens": 6345456.0,
|
|
"step": 3645
|
|
},
|
|
{
|
|
"entropy": 5.794118928909302,
|
|
"epoch": 0.2839914413538222,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004995210331760074,
|
|
"loss": 5.7217,
|
|
"mean_token_accuracy": 0.15264002978801727,
|
|
"num_tokens": 6353584.0,
|
|
"step": 3650
|
|
},
|
|
{
|
|
"entropy": 5.727006578445435,
|
|
"epoch": 0.2843804707255398,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004995192240101275,
|
|
"loss": 5.7469,
|
|
"mean_token_accuracy": 0.15091292411088944,
|
|
"num_tokens": 6362258.0,
|
|
"step": 3655
|
|
},
|
|
{
|
|
"entropy": 5.738786602020264,
|
|
"epoch": 0.2847695000972573,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004995174114375258,
|
|
"loss": 5.6761,
|
|
"mean_token_accuracy": 0.15246595144271852,
|
|
"num_tokens": 6371373.0,
|
|
"step": 3660
|
|
},
|
|
{
|
|
"entropy": 5.864908266067505,
|
|
"epoch": 0.2851585294689749,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004995155954582297,
|
|
"loss": 5.7375,
|
|
"mean_token_accuracy": 0.15102535858750343,
|
|
"num_tokens": 6380431.0,
|
|
"step": 3665
|
|
},
|
|
{
|
|
"entropy": 5.861855220794678,
|
|
"epoch": 0.2855475588406925,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004995137760722668,
|
|
"loss": 5.9038,
|
|
"mean_token_accuracy": 0.1457961119711399,
|
|
"num_tokens": 6389305.0,
|
|
"step": 3670
|
|
},
|
|
{
|
|
"entropy": 5.851635265350342,
|
|
"epoch": 0.28593658821241,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004995119532796646,
|
|
"loss": 5.7213,
|
|
"mean_token_accuracy": 0.15150809288024902,
|
|
"num_tokens": 6397065.0,
|
|
"step": 3675
|
|
},
|
|
{
|
|
"entropy": 5.806237506866455,
|
|
"epoch": 0.2863256175841276,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000499510127080451,
|
|
"loss": 5.8472,
|
|
"mean_token_accuracy": 0.13979469537734984,
|
|
"num_tokens": 6407053.0,
|
|
"step": 3680
|
|
},
|
|
{
|
|
"entropy": 5.867288637161255,
|
|
"epoch": 0.28671464695584514,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004995082974746535,
|
|
"loss": 5.8145,
|
|
"mean_token_accuracy": 0.1415085345506668,
|
|
"num_tokens": 6415165.0,
|
|
"step": 3685
|
|
},
|
|
{
|
|
"entropy": 5.869475412368774,
|
|
"epoch": 0.28710367632756273,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004995064644622999,
|
|
"loss": 5.795,
|
|
"mean_token_accuracy": 0.1459844619035721,
|
|
"num_tokens": 6423646.0,
|
|
"step": 3690
|
|
},
|
|
{
|
|
"entropy": 5.868303823471069,
|
|
"epoch": 0.2874927056992803,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004995046280434181,
|
|
"loss": 5.8131,
|
|
"mean_token_accuracy": 0.1465369090437889,
|
|
"num_tokens": 6432134.0,
|
|
"step": 3695
|
|
},
|
|
{
|
|
"entropy": 5.818410873413086,
|
|
"epoch": 0.28788173507099785,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004995027882180358,
|
|
"loss": 5.7027,
|
|
"mean_token_accuracy": 0.1474486768245697,
|
|
"num_tokens": 6440456.0,
|
|
"step": 3700
|
|
},
|
|
{
|
|
"entropy": 5.809641408920288,
|
|
"epoch": 0.28827076444271543,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004995009449861812,
|
|
"loss": 5.7866,
|
|
"mean_token_accuracy": 0.13990482091903686,
|
|
"num_tokens": 6448952.0,
|
|
"step": 3705
|
|
},
|
|
{
|
|
"entropy": 5.804608154296875,
|
|
"epoch": 0.28865979381443296,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000499499098347882,
|
|
"loss": 5.6512,
|
|
"mean_token_accuracy": 0.16037264764308928,
|
|
"num_tokens": 6457225.0,
|
|
"step": 3710
|
|
},
|
|
{
|
|
"entropy": 5.810186100006104,
|
|
"epoch": 0.28904882318615055,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004994972483031662,
|
|
"loss": 5.7833,
|
|
"mean_token_accuracy": 0.1467502385377884,
|
|
"num_tokens": 6465450.0,
|
|
"step": 3715
|
|
},
|
|
{
|
|
"entropy": 5.810656881332397,
|
|
"epoch": 0.28943785255786814,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000499495394852062,
|
|
"loss": 5.8163,
|
|
"mean_token_accuracy": 0.1399491086602211,
|
|
"num_tokens": 6473736.0,
|
|
"step": 3720
|
|
},
|
|
{
|
|
"entropy": 5.83799033164978,
|
|
"epoch": 0.28982688192958567,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004994935379945977,
|
|
"loss": 5.7577,
|
|
"mean_token_accuracy": 0.1468055784702301,
|
|
"num_tokens": 6482092.0,
|
|
"step": 3725
|
|
},
|
|
{
|
|
"entropy": 5.8806088924407955,
|
|
"epoch": 0.29021591130130325,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004994916777308012,
|
|
"loss": 5.7831,
|
|
"mean_token_accuracy": 0.14831546545028687,
|
|
"num_tokens": 6490704.0,
|
|
"step": 3730
|
|
},
|
|
{
|
|
"entropy": 5.850636386871338,
|
|
"epoch": 0.29060494067302084,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004994898140607007,
|
|
"loss": 5.7201,
|
|
"mean_token_accuracy": 0.15038958936929703,
|
|
"num_tokens": 6499634.0,
|
|
"step": 3735
|
|
},
|
|
{
|
|
"entropy": 5.743886566162109,
|
|
"epoch": 0.29099397004473837,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004994879469843247,
|
|
"loss": 5.8767,
|
|
"mean_token_accuracy": 0.13921897560358049,
|
|
"num_tokens": 6509261.0,
|
|
"step": 3740
|
|
},
|
|
{
|
|
"entropy": 5.8543627738952635,
|
|
"epoch": 0.29138299941645596,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004994860765017013,
|
|
"loss": 5.7098,
|
|
"mean_token_accuracy": 0.14895353764295577,
|
|
"num_tokens": 6517542.0,
|
|
"step": 3745
|
|
},
|
|
{
|
|
"entropy": 5.767716026306152,
|
|
"epoch": 0.2917720287881735,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000499484202612859,
|
|
"loss": 5.7096,
|
|
"mean_token_accuracy": 0.14601053446531295,
|
|
"num_tokens": 6525945.0,
|
|
"step": 3750
|
|
},
|
|
{
|
|
"entropy": 5.740671157836914,
|
|
"epoch": 0.2921610581598911,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004994823253178264,
|
|
"loss": 5.7276,
|
|
"mean_token_accuracy": 0.1483728989958763,
|
|
"num_tokens": 6534744.0,
|
|
"step": 3755
|
|
},
|
|
{
|
|
"entropy": 5.7915150165557865,
|
|
"epoch": 0.29255008753160866,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004994804446166317,
|
|
"loss": 5.6894,
|
|
"mean_token_accuracy": 0.15682424753904342,
|
|
"num_tokens": 6542640.0,
|
|
"step": 3760
|
|
},
|
|
{
|
|
"entropy": 5.801311922073364,
|
|
"epoch": 0.2929391169033262,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004994785605093035,
|
|
"loss": 5.747,
|
|
"mean_token_accuracy": 0.15235013365745545,
|
|
"num_tokens": 6551292.0,
|
|
"step": 3765
|
|
},
|
|
{
|
|
"entropy": 5.7961516857147215,
|
|
"epoch": 0.2933281462750438,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004994766729958705,
|
|
"loss": 5.8392,
|
|
"mean_token_accuracy": 0.1455648086965084,
|
|
"num_tokens": 6560760.0,
|
|
"step": 3770
|
|
},
|
|
{
|
|
"entropy": 5.925059127807617,
|
|
"epoch": 0.2937171756467613,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004994747820763612,
|
|
"loss": 5.8572,
|
|
"mean_token_accuracy": 0.13900205940008165,
|
|
"num_tokens": 6570618.0,
|
|
"step": 3775
|
|
},
|
|
{
|
|
"entropy": 5.86215295791626,
|
|
"epoch": 0.2941062050184789,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004994728877508046,
|
|
"loss": 5.7023,
|
|
"mean_token_accuracy": 0.14909525960683823,
|
|
"num_tokens": 6579484.0,
|
|
"step": 3780
|
|
},
|
|
{
|
|
"entropy": 5.818112993240357,
|
|
"epoch": 0.2944952343901965,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004994709900192289,
|
|
"loss": 5.7803,
|
|
"mean_token_accuracy": 0.1460746668279171,
|
|
"num_tokens": 6588531.0,
|
|
"step": 3785
|
|
},
|
|
{
|
|
"entropy": 5.769961595535278,
|
|
"epoch": 0.294884263761914,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004994690888816635,
|
|
"loss": 5.8196,
|
|
"mean_token_accuracy": 0.14704116955399513,
|
|
"num_tokens": 6596862.0,
|
|
"step": 3790
|
|
},
|
|
{
|
|
"entropy": 5.825479936599732,
|
|
"epoch": 0.2952732931336316,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004994671843381367,
|
|
"loss": 5.723,
|
|
"mean_token_accuracy": 0.14900503158569336,
|
|
"num_tokens": 6605594.0,
|
|
"step": 3795
|
|
},
|
|
{
|
|
"entropy": 5.8890174388885494,
|
|
"epoch": 0.29566232250534913,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004994652763886778,
|
|
"loss": 5.7712,
|
|
"mean_token_accuracy": 0.14753982722759246,
|
|
"num_tokens": 6613971.0,
|
|
"step": 3800
|
|
},
|
|
{
|
|
"entropy": 5.812981510162354,
|
|
"epoch": 0.2960513518770667,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004994633650333155,
|
|
"loss": 5.8431,
|
|
"mean_token_accuracy": 0.1393670342862606,
|
|
"num_tokens": 6623116.0,
|
|
"step": 3805
|
|
},
|
|
{
|
|
"entropy": 5.812322998046875,
|
|
"epoch": 0.2964403812487843,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004994614502720792,
|
|
"loss": 5.7277,
|
|
"mean_token_accuracy": 0.1557611882686615,
|
|
"num_tokens": 6631910.0,
|
|
"step": 3810
|
|
},
|
|
{
|
|
"entropy": 5.8097423076629635,
|
|
"epoch": 0.29682941062050183,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004994595321049974,
|
|
"loss": 5.7528,
|
|
"mean_token_accuracy": 0.15263307020068168,
|
|
"num_tokens": 6640882.0,
|
|
"step": 3815
|
|
},
|
|
{
|
|
"entropy": 5.902229881286621,
|
|
"epoch": 0.2972184399922194,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004994576105320994,
|
|
"loss": 5.8396,
|
|
"mean_token_accuracy": 0.1413460522890091,
|
|
"num_tokens": 6649665.0,
|
|
"step": 3820
|
|
},
|
|
{
|
|
"entropy": 5.703270339965821,
|
|
"epoch": 0.29760746936393695,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004994556855534146,
|
|
"loss": 5.6241,
|
|
"mean_token_accuracy": 0.154371440410614,
|
|
"num_tokens": 6658725.0,
|
|
"step": 3825
|
|
},
|
|
{
|
|
"entropy": 5.67880334854126,
|
|
"epoch": 0.29799649873565454,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004994537571689719,
|
|
"loss": 5.6708,
|
|
"mean_token_accuracy": 0.1537424236536026,
|
|
"num_tokens": 6667403.0,
|
|
"step": 3830
|
|
},
|
|
{
|
|
"entropy": 5.888912105560303,
|
|
"epoch": 0.2983855281073721,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004994518253788007,
|
|
"loss": 5.756,
|
|
"mean_token_accuracy": 0.14269450083374977,
|
|
"num_tokens": 6676673.0,
|
|
"step": 3835
|
|
},
|
|
{
|
|
"entropy": 5.810962390899658,
|
|
"epoch": 0.29877455747908965,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004994498901829304,
|
|
"loss": 5.7563,
|
|
"mean_token_accuracy": 0.14370476379990577,
|
|
"num_tokens": 6686212.0,
|
|
"step": 3840
|
|
},
|
|
{
|
|
"entropy": 5.744761562347412,
|
|
"epoch": 0.29916358685080724,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004994479515813903,
|
|
"loss": 5.7617,
|
|
"mean_token_accuracy": 0.14795507341623307,
|
|
"num_tokens": 6694812.0,
|
|
"step": 3845
|
|
},
|
|
{
|
|
"entropy": 5.79722900390625,
|
|
"epoch": 0.2995526162225248,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004994460095742096,
|
|
"loss": 5.7061,
|
|
"mean_token_accuracy": 0.14745592027902604,
|
|
"num_tokens": 6703439.0,
|
|
"step": 3850
|
|
},
|
|
{
|
|
"entropy": 5.837129878997803,
|
|
"epoch": 0.29994164559424236,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000499444064161418,
|
|
"loss": 5.7082,
|
|
"mean_token_accuracy": 0.14777314588427543,
|
|
"num_tokens": 6711465.0,
|
|
"step": 3855
|
|
},
|
|
{
|
|
"entropy": 5.729570055007935,
|
|
"epoch": 0.30033067496595994,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000499442115343045,
|
|
"loss": 5.7249,
|
|
"mean_token_accuracy": 0.14670694693922998,
|
|
"num_tokens": 6720526.0,
|
|
"step": 3860
|
|
},
|
|
{
|
|
"entropy": 5.893850612640381,
|
|
"epoch": 0.3007197043376775,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004994401631191202,
|
|
"loss": 5.9148,
|
|
"mean_token_accuracy": 0.1395176962018013,
|
|
"num_tokens": 6728696.0,
|
|
"step": 3865
|
|
},
|
|
{
|
|
"entropy": 5.797284650802612,
|
|
"epoch": 0.30110873370939506,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004994382074896731,
|
|
"loss": 5.7731,
|
|
"mean_token_accuracy": 0.14963408410549164,
|
|
"num_tokens": 6737955.0,
|
|
"step": 3870
|
|
},
|
|
{
|
|
"entropy": 5.84608416557312,
|
|
"epoch": 0.30149776308111265,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004994362484547335,
|
|
"loss": 5.8347,
|
|
"mean_token_accuracy": 0.14240911602973938,
|
|
"num_tokens": 6746413.0,
|
|
"step": 3875
|
|
},
|
|
{
|
|
"entropy": 5.765618562698364,
|
|
"epoch": 0.3018867924528302,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004994342860143309,
|
|
"loss": 5.6949,
|
|
"mean_token_accuracy": 0.14801103472709656,
|
|
"num_tokens": 6754341.0,
|
|
"step": 3880
|
|
},
|
|
{
|
|
"entropy": 5.667687511444091,
|
|
"epoch": 0.30227582182454776,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004994323201684953,
|
|
"loss": 5.5675,
|
|
"mean_token_accuracy": 0.15506181120872498,
|
|
"num_tokens": 6762623.0,
|
|
"step": 3885
|
|
},
|
|
{
|
|
"entropy": 5.747409772872925,
|
|
"epoch": 0.3026648511962653,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004994303509172566,
|
|
"loss": 5.7186,
|
|
"mean_token_accuracy": 0.14648325890302658,
|
|
"num_tokens": 6771270.0,
|
|
"step": 3890
|
|
},
|
|
{
|
|
"entropy": 5.833155012130737,
|
|
"epoch": 0.3030538805679829,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004994283782606444,
|
|
"loss": 5.7834,
|
|
"mean_token_accuracy": 0.14363724514842033,
|
|
"num_tokens": 6780292.0,
|
|
"step": 3895
|
|
},
|
|
{
|
|
"entropy": 5.880225801467896,
|
|
"epoch": 0.30344290993970047,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004994264021986888,
|
|
"loss": 5.6681,
|
|
"mean_token_accuracy": 0.15166061818599702,
|
|
"num_tokens": 6788580.0,
|
|
"step": 3900
|
|
},
|
|
{
|
|
"entropy": 5.639140987396241,
|
|
"epoch": 0.303831939311418,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004994244227314197,
|
|
"loss": 5.6524,
|
|
"mean_token_accuracy": 0.14872112795710563,
|
|
"num_tokens": 6796801.0,
|
|
"step": 3905
|
|
},
|
|
{
|
|
"entropy": 5.7354284763336185,
|
|
"epoch": 0.3042209686831356,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004994224398588672,
|
|
"loss": 5.6678,
|
|
"mean_token_accuracy": 0.14618211537599562,
|
|
"num_tokens": 6805630.0,
|
|
"step": 3910
|
|
},
|
|
{
|
|
"entropy": 5.683595514297485,
|
|
"epoch": 0.3046099980548531,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004994204535810615,
|
|
"loss": 5.6425,
|
|
"mean_token_accuracy": 0.15028658956289292,
|
|
"num_tokens": 6814316.0,
|
|
"step": 3915
|
|
},
|
|
{
|
|
"entropy": 5.896274042129517,
|
|
"epoch": 0.3049990274265707,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004994184638980326,
|
|
"loss": 5.8131,
|
|
"mean_token_accuracy": 0.14128096029162407,
|
|
"num_tokens": 6823224.0,
|
|
"step": 3920
|
|
},
|
|
{
|
|
"entropy": 5.82032413482666,
|
|
"epoch": 0.3053880567982883,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004994164708098107,
|
|
"loss": 5.8399,
|
|
"mean_token_accuracy": 0.1436244174838066,
|
|
"num_tokens": 6832104.0,
|
|
"step": 3925
|
|
},
|
|
{
|
|
"entropy": 5.832739591598511,
|
|
"epoch": 0.3057770861700058,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000499414474316426,
|
|
"loss": 5.7432,
|
|
"mean_token_accuracy": 0.1472333326935768,
|
|
"num_tokens": 6841208.0,
|
|
"step": 3930
|
|
},
|
|
{
|
|
"entropy": 5.652276039123535,
|
|
"epoch": 0.3061661155417234,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004994124744179088,
|
|
"loss": 5.546,
|
|
"mean_token_accuracy": 0.15998484641313554,
|
|
"num_tokens": 6849622.0,
|
|
"step": 3935
|
|
},
|
|
{
|
|
"entropy": 5.7208733558654785,
|
|
"epoch": 0.306555144913441,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004994104711142896,
|
|
"loss": 5.7513,
|
|
"mean_token_accuracy": 0.1525330901145935,
|
|
"num_tokens": 6857355.0,
|
|
"step": 3940
|
|
},
|
|
{
|
|
"entropy": 5.833088970184326,
|
|
"epoch": 0.3069441742851585,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004994084644055986,
|
|
"loss": 5.764,
|
|
"mean_token_accuracy": 0.15032006576657295,
|
|
"num_tokens": 6866173.0,
|
|
"step": 3945
|
|
},
|
|
{
|
|
"entropy": 5.745790719985962,
|
|
"epoch": 0.3073332036568761,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004994064542918664,
|
|
"loss": 5.7618,
|
|
"mean_token_accuracy": 0.14327194094657897,
|
|
"num_tokens": 6874438.0,
|
|
"step": 3950
|
|
},
|
|
{
|
|
"entropy": 5.838888788223267,
|
|
"epoch": 0.30772223302859364,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004994044407731235,
|
|
"loss": 5.7559,
|
|
"mean_token_accuracy": 0.14924216270446777,
|
|
"num_tokens": 6882790.0,
|
|
"step": 3955
|
|
},
|
|
{
|
|
"entropy": 5.77858567237854,
|
|
"epoch": 0.3081112624003112,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004994024238494002,
|
|
"loss": 5.8004,
|
|
"mean_token_accuracy": 0.13810172826051711,
|
|
"num_tokens": 6891375.0,
|
|
"step": 3960
|
|
},
|
|
{
|
|
"entropy": 5.672658538818359,
|
|
"epoch": 0.3085002917720288,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004994004035207274,
|
|
"loss": 5.7009,
|
|
"mean_token_accuracy": 0.15040683150291442,
|
|
"num_tokens": 6899510.0,
|
|
"step": 3965
|
|
},
|
|
{
|
|
"entropy": 5.849552297592163,
|
|
"epoch": 0.30888932114374634,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004993983797871356,
|
|
"loss": 5.7546,
|
|
"mean_token_accuracy": 0.15272879973053932,
|
|
"num_tokens": 6908311.0,
|
|
"step": 3970
|
|
},
|
|
{
|
|
"entropy": 5.77811074256897,
|
|
"epoch": 0.30927835051546393,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004993963526486555,
|
|
"loss": 5.7107,
|
|
"mean_token_accuracy": 0.14666830450296403,
|
|
"num_tokens": 6917064.0,
|
|
"step": 3975
|
|
},
|
|
{
|
|
"entropy": 5.765193367004395,
|
|
"epoch": 0.30966737988718146,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.000499394322105318,
|
|
"loss": 5.7055,
|
|
"mean_token_accuracy": 0.14877342879772187,
|
|
"num_tokens": 6925705.0,
|
|
"step": 3980
|
|
},
|
|
{
|
|
"entropy": 5.929165410995483,
|
|
"epoch": 0.31005640925889905,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004993922881571538,
|
|
"loss": 5.8505,
|
|
"mean_token_accuracy": 0.14009160473942756,
|
|
"num_tokens": 6934232.0,
|
|
"step": 3985
|
|
},
|
|
{
|
|
"entropy": 5.842931127548217,
|
|
"epoch": 0.31044543863061663,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004993902508041939,
|
|
"loss": 5.7825,
|
|
"mean_token_accuracy": 0.1494826927781105,
|
|
"num_tokens": 6943143.0,
|
|
"step": 3990
|
|
},
|
|
{
|
|
"entropy": 5.784590435028076,
|
|
"epoch": 0.31083446800233416,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000499388210046469,
|
|
"loss": 5.6572,
|
|
"mean_token_accuracy": 0.15119214802980424,
|
|
"num_tokens": 6951613.0,
|
|
"step": 3995
|
|
},
|
|
{
|
|
"entropy": 5.781867980957031,
|
|
"epoch": 0.31122349737405175,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004993861658840102,
|
|
"loss": 5.8635,
|
|
"mean_token_accuracy": 0.144657726585865,
|
|
"num_tokens": 6960531.0,
|
|
"step": 4000
|
|
},
|
|
{
|
|
"entropy": 5.813362073898316,
|
|
"epoch": 0.3116125267457693,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004993841183168484,
|
|
"loss": 5.7836,
|
|
"mean_token_accuracy": 0.14522304087877275,
|
|
"num_tokens": 6969211.0,
|
|
"step": 4005
|
|
},
|
|
{
|
|
"entropy": 5.923810148239136,
|
|
"epoch": 0.31200155611748687,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004993820673450148,
|
|
"loss": 5.8097,
|
|
"mean_token_accuracy": 0.14293079674243928,
|
|
"num_tokens": 6978414.0,
|
|
"step": 4010
|
|
},
|
|
{
|
|
"entropy": 5.676694631576538,
|
|
"epoch": 0.31239058548920445,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004993800129685404,
|
|
"loss": 5.5568,
|
|
"mean_token_accuracy": 0.15368023365736008,
|
|
"num_tokens": 6987350.0,
|
|
"step": 4015
|
|
},
|
|
{
|
|
"entropy": 5.725512933731079,
|
|
"epoch": 0.312779614860922,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004993779551874565,
|
|
"loss": 5.7006,
|
|
"mean_token_accuracy": 0.15659889280796052,
|
|
"num_tokens": 6995817.0,
|
|
"step": 4020
|
|
},
|
|
{
|
|
"entropy": 5.77770471572876,
|
|
"epoch": 0.31316864423263957,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004993758940017943,
|
|
"loss": 5.7712,
|
|
"mean_token_accuracy": 0.14786949157714843,
|
|
"num_tokens": 7004454.0,
|
|
"step": 4025
|
|
},
|
|
{
|
|
"entropy": 5.818613433837891,
|
|
"epoch": 0.31355767360435716,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.000499373829411585,
|
|
"loss": 5.712,
|
|
"mean_token_accuracy": 0.1497095689177513,
|
|
"num_tokens": 7012126.0,
|
|
"step": 4030
|
|
},
|
|
{
|
|
"entropy": 5.80422043800354,
|
|
"epoch": 0.3139467029760747,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00049937176141686,
|
|
"loss": 5.7819,
|
|
"mean_token_accuracy": 0.15036623552441597,
|
|
"num_tokens": 7021232.0,
|
|
"step": 4035
|
|
},
|
|
{
|
|
"entropy": 5.852689599990844,
|
|
"epoch": 0.3143357323477923,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004993696900176506,
|
|
"loss": 5.7645,
|
|
"mean_token_accuracy": 0.14852062985301018,
|
|
"num_tokens": 7029488.0,
|
|
"step": 4040
|
|
},
|
|
{
|
|
"entropy": 5.820941209793091,
|
|
"epoch": 0.3147247617195098,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004993676152139883,
|
|
"loss": 5.7985,
|
|
"mean_token_accuracy": 0.1442652441561222,
|
|
"num_tokens": 7037323.0,
|
|
"step": 4045
|
|
},
|
|
{
|
|
"entropy": 5.7845946788787845,
|
|
"epoch": 0.3151137910912274,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004993655370059046,
|
|
"loss": 5.7531,
|
|
"mean_token_accuracy": 0.14139595925807952,
|
|
"num_tokens": 7045754.0,
|
|
"step": 4050
|
|
},
|
|
{
|
|
"entropy": 5.7826457023620605,
|
|
"epoch": 0.315502820462945,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004993634553934309,
|
|
"loss": 5.6884,
|
|
"mean_token_accuracy": 0.14923796579241752,
|
|
"num_tokens": 7054026.0,
|
|
"step": 4055
|
|
},
|
|
{
|
|
"entropy": 5.715740585327149,
|
|
"epoch": 0.3158918498346625,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004993613703765989,
|
|
"loss": 5.7329,
|
|
"mean_token_accuracy": 0.1490222007036209,
|
|
"num_tokens": 7063383.0,
|
|
"step": 4060
|
|
},
|
|
{
|
|
"entropy": 5.74744987487793,
|
|
"epoch": 0.3162808792063801,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004993592819554402,
|
|
"loss": 5.7028,
|
|
"mean_token_accuracy": 0.15151856541633607,
|
|
"num_tokens": 7071952.0,
|
|
"step": 4065
|
|
},
|
|
{
|
|
"entropy": 5.862038898468017,
|
|
"epoch": 0.3166699085780976,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004993571901299866,
|
|
"loss": 5.7424,
|
|
"mean_token_accuracy": 0.1466784045100212,
|
|
"num_tokens": 7080283.0,
|
|
"step": 4070
|
|
},
|
|
{
|
|
"entropy": 5.658473825454712,
|
|
"epoch": 0.3170589379498152,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004993550949002697,
|
|
"loss": 5.6853,
|
|
"mean_token_accuracy": 0.14666975438594818,
|
|
"num_tokens": 7088669.0,
|
|
"step": 4075
|
|
},
|
|
{
|
|
"entropy": 5.697621583938599,
|
|
"epoch": 0.3174479673215328,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004993529962663213,
|
|
"loss": 5.5697,
|
|
"mean_token_accuracy": 0.16409860402345658,
|
|
"num_tokens": 7097201.0,
|
|
"step": 4080
|
|
},
|
|
{
|
|
"entropy": 5.748375940322876,
|
|
"epoch": 0.31783699669325033,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004993508942281732,
|
|
"loss": 5.7527,
|
|
"mean_token_accuracy": 0.14704224616289138,
|
|
"num_tokens": 7106509.0,
|
|
"step": 4085
|
|
},
|
|
{
|
|
"entropy": 5.772694444656372,
|
|
"epoch": 0.3182260260649679,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004993487887858575,
|
|
"loss": 5.662,
|
|
"mean_token_accuracy": 0.15324160903692247,
|
|
"num_tokens": 7114550.0,
|
|
"step": 4090
|
|
},
|
|
{
|
|
"entropy": 5.823660564422608,
|
|
"epoch": 0.31861505543668545,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000499346679939406,
|
|
"loss": 5.7734,
|
|
"mean_token_accuracy": 0.15043377876281738,
|
|
"num_tokens": 7122875.0,
|
|
"step": 4095
|
|
},
|
|
{
|
|
"entropy": 5.785100364685059,
|
|
"epoch": 0.31900408480840303,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004993445676888507,
|
|
"loss": 5.5858,
|
|
"mean_token_accuracy": 0.14903404712677001,
|
|
"num_tokens": 7132263.0,
|
|
"step": 4100
|
|
},
|
|
{
|
|
"entropy": 5.708623313903809,
|
|
"epoch": 0.3193931141801206,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004993424520342236,
|
|
"loss": 5.8122,
|
|
"mean_token_accuracy": 0.14726694226264953,
|
|
"num_tokens": 7141448.0,
|
|
"step": 4105
|
|
},
|
|
{
|
|
"entropy": 5.757666683197021,
|
|
"epoch": 0.31978214355183815,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004993403329755569,
|
|
"loss": 5.8158,
|
|
"mean_token_accuracy": 0.14173928201198577,
|
|
"num_tokens": 7151021.0,
|
|
"step": 4110
|
|
},
|
|
{
|
|
"entropy": 5.908272171020508,
|
|
"epoch": 0.32017117292355574,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004993382105128828,
|
|
"loss": 5.7724,
|
|
"mean_token_accuracy": 0.14403056129813194,
|
|
"num_tokens": 7160103.0,
|
|
"step": 4115
|
|
},
|
|
{
|
|
"entropy": 5.794647169113159,
|
|
"epoch": 0.32056020229527327,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004993360846462333,
|
|
"loss": 5.7575,
|
|
"mean_token_accuracy": 0.14108945354819297,
|
|
"num_tokens": 7169003.0,
|
|
"step": 4120
|
|
},
|
|
{
|
|
"entropy": 5.856556415557861,
|
|
"epoch": 0.32094923166699085,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004993339553756408,
|
|
"loss": 5.8024,
|
|
"mean_token_accuracy": 0.15243273302912713,
|
|
"num_tokens": 7177086.0,
|
|
"step": 4125
|
|
},
|
|
{
|
|
"entropy": 5.769464302062988,
|
|
"epoch": 0.32133826103870844,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004993318227011378,
|
|
"loss": 5.674,
|
|
"mean_token_accuracy": 0.15314000099897385,
|
|
"num_tokens": 7185772.0,
|
|
"step": 4130
|
|
},
|
|
{
|
|
"entropy": 5.854861259460449,
|
|
"epoch": 0.32172729041042597,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004993296866227562,
|
|
"loss": 5.8114,
|
|
"mean_token_accuracy": 0.14875666797161102,
|
|
"num_tokens": 7194394.0,
|
|
"step": 4135
|
|
},
|
|
{
|
|
"entropy": 5.803802633285523,
|
|
"epoch": 0.32211631978214356,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004993275471405288,
|
|
"loss": 5.6327,
|
|
"mean_token_accuracy": 0.15715198665857316,
|
|
"num_tokens": 7202143.0,
|
|
"step": 4140
|
|
},
|
|
{
|
|
"entropy": 5.6745908737182615,
|
|
"epoch": 0.32250534915386114,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004993254042544879,
|
|
"loss": 5.737,
|
|
"mean_token_accuracy": 0.14759556651115419,
|
|
"num_tokens": 7210645.0,
|
|
"step": 4145
|
|
},
|
|
{
|
|
"entropy": 5.773699808120727,
|
|
"epoch": 0.3228943785255787,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000499323257964666,
|
|
"loss": 5.6711,
|
|
"mean_token_accuracy": 0.15104791671037673,
|
|
"num_tokens": 7218872.0,
|
|
"step": 4150
|
|
},
|
|
{
|
|
"entropy": 5.864423131942749,
|
|
"epoch": 0.32328340789729626,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004993211082710957,
|
|
"loss": 5.8581,
|
|
"mean_token_accuracy": 0.14464571326971054,
|
|
"num_tokens": 7226977.0,
|
|
"step": 4155
|
|
},
|
|
{
|
|
"entropy": 5.803394317626953,
|
|
"epoch": 0.3236724372690138,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004993189551738097,
|
|
"loss": 5.6977,
|
|
"mean_token_accuracy": 0.14795618653297424,
|
|
"num_tokens": 7235635.0,
|
|
"step": 4160
|
|
},
|
|
{
|
|
"entropy": 5.760642957687378,
|
|
"epoch": 0.3240614666407314,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004993167986728405,
|
|
"loss": 5.6863,
|
|
"mean_token_accuracy": 0.15549185127019882,
|
|
"num_tokens": 7244506.0,
|
|
"step": 4165
|
|
},
|
|
{
|
|
"entropy": 5.751373052597046,
|
|
"epoch": 0.32445049601244896,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.000499314638768221,
|
|
"loss": 5.7222,
|
|
"mean_token_accuracy": 0.149913389980793,
|
|
"num_tokens": 7252883.0,
|
|
"step": 4170
|
|
},
|
|
{
|
|
"entropy": 5.821081495285034,
|
|
"epoch": 0.3248395253841665,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004993124754599839,
|
|
"loss": 5.6798,
|
|
"mean_token_accuracy": 0.14590843692421912,
|
|
"num_tokens": 7261580.0,
|
|
"step": 4175
|
|
},
|
|
{
|
|
"entropy": 5.793644857406616,
|
|
"epoch": 0.3252285547558841,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004993103087481619,
|
|
"loss": 5.7723,
|
|
"mean_token_accuracy": 0.1446990892291069,
|
|
"num_tokens": 7270346.0,
|
|
"step": 4180
|
|
},
|
|
{
|
|
"entropy": 5.804017353057861,
|
|
"epoch": 0.3256175841276016,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004993081386327881,
|
|
"loss": 5.8424,
|
|
"mean_token_accuracy": 0.14238107204437256,
|
|
"num_tokens": 7279393.0,
|
|
"step": 4185
|
|
},
|
|
{
|
|
"entropy": 5.733974027633667,
|
|
"epoch": 0.3260066134993192,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004993059651138953,
|
|
"loss": 5.6846,
|
|
"mean_token_accuracy": 0.14898681640625,
|
|
"num_tokens": 7287929.0,
|
|
"step": 4190
|
|
},
|
|
{
|
|
"entropy": 5.858212947845459,
|
|
"epoch": 0.3263956428710368,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004993037881915165,
|
|
"loss": 5.7203,
|
|
"mean_token_accuracy": 0.14945944994688035,
|
|
"num_tokens": 7296336.0,
|
|
"step": 4195
|
|
},
|
|
{
|
|
"entropy": 5.687768888473511,
|
|
"epoch": 0.3267846722427543,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004993016078656847,
|
|
"loss": 5.6126,
|
|
"mean_token_accuracy": 0.15262411832809447,
|
|
"num_tokens": 7304624.0,
|
|
"step": 4200
|
|
},
|
|
{
|
|
"entropy": 5.690052080154419,
|
|
"epoch": 0.3271737016144719,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000499299424136433,
|
|
"loss": 5.7504,
|
|
"mean_token_accuracy": 0.14595601409673692,
|
|
"num_tokens": 7312945.0,
|
|
"step": 4205
|
|
},
|
|
{
|
|
"entropy": 5.824770212173462,
|
|
"epoch": 0.32756273098618943,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004992972370037946,
|
|
"loss": 5.669,
|
|
"mean_token_accuracy": 0.15038443952798844,
|
|
"num_tokens": 7321273.0,
|
|
"step": 4210
|
|
},
|
|
{
|
|
"entropy": 5.8330482006072994,
|
|
"epoch": 0.327951760357907,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004992950464678026,
|
|
"loss": 5.7675,
|
|
"mean_token_accuracy": 0.15167799592018127,
|
|
"num_tokens": 7330446.0,
|
|
"step": 4215
|
|
},
|
|
{
|
|
"entropy": 5.669593095779419,
|
|
"epoch": 0.3283407897296246,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004992928525284903,
|
|
"loss": 5.704,
|
|
"mean_token_accuracy": 0.1521438404917717,
|
|
"num_tokens": 7339282.0,
|
|
"step": 4220
|
|
},
|
|
{
|
|
"entropy": 5.752499961853028,
|
|
"epoch": 0.32872981910134214,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000499290655185891,
|
|
"loss": 5.6707,
|
|
"mean_token_accuracy": 0.14109978452324867,
|
|
"num_tokens": 7347848.0,
|
|
"step": 4225
|
|
},
|
|
{
|
|
"entropy": 5.679991912841797,
|
|
"epoch": 0.3291188484730597,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000499288454440038,
|
|
"loss": 5.6748,
|
|
"mean_token_accuracy": 0.15071465373039244,
|
|
"num_tokens": 7356678.0,
|
|
"step": 4230
|
|
},
|
|
{
|
|
"entropy": 5.791227054595947,
|
|
"epoch": 0.3295078778447773,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004992862502909645,
|
|
"loss": 5.7363,
|
|
"mean_token_accuracy": 0.15067468732595443,
|
|
"num_tokens": 7365411.0,
|
|
"step": 4235
|
|
},
|
|
{
|
|
"entropy": 5.725597524642945,
|
|
"epoch": 0.32989690721649484,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004992840427387043,
|
|
"loss": 5.6558,
|
|
"mean_token_accuracy": 0.15863664150238038,
|
|
"num_tokens": 7373635.0,
|
|
"step": 4240
|
|
},
|
|
{
|
|
"entropy": 5.772441816329956,
|
|
"epoch": 0.3302859365882124,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004992818317832908,
|
|
"loss": 5.7525,
|
|
"mean_token_accuracy": 0.15104876458644867,
|
|
"num_tokens": 7382469.0,
|
|
"step": 4245
|
|
},
|
|
{
|
|
"entropy": 5.791848611831665,
|
|
"epoch": 0.33067496595992996,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004992796174247574,
|
|
"loss": 5.7456,
|
|
"mean_token_accuracy": 0.14663487672805786,
|
|
"num_tokens": 7390712.0,
|
|
"step": 4250
|
|
},
|
|
{
|
|
"entropy": 5.83238000869751,
|
|
"epoch": 0.33106399533164754,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004992773996631378,
|
|
"loss": 5.6763,
|
|
"mean_token_accuracy": 0.14819879531860353,
|
|
"num_tokens": 7398905.0,
|
|
"step": 4255
|
|
},
|
|
{
|
|
"entropy": 5.7469171524047855,
|
|
"epoch": 0.33145302470336513,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004992751784984656,
|
|
"loss": 5.7521,
|
|
"mean_token_accuracy": 0.14595615193247796,
|
|
"num_tokens": 7407242.0,
|
|
"step": 4260
|
|
},
|
|
{
|
|
"entropy": 5.742021656036377,
|
|
"epoch": 0.33184205407508266,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004992729539307745,
|
|
"loss": 5.7694,
|
|
"mean_token_accuracy": 0.1436052680015564,
|
|
"num_tokens": 7416489.0,
|
|
"step": 4265
|
|
},
|
|
{
|
|
"entropy": 5.906120681762696,
|
|
"epoch": 0.33223108344680025,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004992707259600984,
|
|
"loss": 5.7559,
|
|
"mean_token_accuracy": 0.1527278333902359,
|
|
"num_tokens": 7424507.0,
|
|
"step": 4270
|
|
},
|
|
{
|
|
"entropy": 5.736468029022217,
|
|
"epoch": 0.3326201128185178,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004992684945864709,
|
|
"loss": 5.746,
|
|
"mean_token_accuracy": 0.1425243631005287,
|
|
"num_tokens": 7433343.0,
|
|
"step": 4275
|
|
},
|
|
{
|
|
"entropy": 5.7437169551849365,
|
|
"epoch": 0.33300914219023536,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004992662598099261,
|
|
"loss": 5.6856,
|
|
"mean_token_accuracy": 0.15159007757902146,
|
|
"num_tokens": 7441452.0,
|
|
"step": 4280
|
|
},
|
|
{
|
|
"entropy": 5.82387146949768,
|
|
"epoch": 0.33339817156195295,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004992640216304975,
|
|
"loss": 5.7383,
|
|
"mean_token_accuracy": 0.15166881456971168,
|
|
"num_tokens": 7449541.0,
|
|
"step": 4285
|
|
},
|
|
{
|
|
"entropy": 5.772676610946656,
|
|
"epoch": 0.3337872009336705,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004992617800482196,
|
|
"loss": 5.7508,
|
|
"mean_token_accuracy": 0.1446318544447422,
|
|
"num_tokens": 7458812.0,
|
|
"step": 4290
|
|
},
|
|
{
|
|
"entropy": 5.80000319480896,
|
|
"epoch": 0.33417623030538807,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.000499259535063126,
|
|
"loss": 5.6754,
|
|
"mean_token_accuracy": 0.14619821310043335,
|
|
"num_tokens": 7467607.0,
|
|
"step": 4295
|
|
},
|
|
{
|
|
"entropy": 5.712003326416015,
|
|
"epoch": 0.3345652596771056,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.000499257286675251,
|
|
"loss": 5.6227,
|
|
"mean_token_accuracy": 0.1527673527598381,
|
|
"num_tokens": 7476047.0,
|
|
"step": 4300
|
|
},
|
|
{
|
|
"entropy": 5.78293080329895,
|
|
"epoch": 0.3349542890488232,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004992550348846285,
|
|
"loss": 5.6868,
|
|
"mean_token_accuracy": 0.14961570352315903,
|
|
"num_tokens": 7484496.0,
|
|
"step": 4305
|
|
},
|
|
{
|
|
"entropy": 5.65687518119812,
|
|
"epoch": 0.33534331842054077,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004992527796912928,
|
|
"loss": 5.612,
|
|
"mean_token_accuracy": 0.15613239780068397,
|
|
"num_tokens": 7493161.0,
|
|
"step": 4310
|
|
},
|
|
{
|
|
"entropy": 5.699185752868653,
|
|
"epoch": 0.3357323477922583,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004992505210952782,
|
|
"loss": 5.7685,
|
|
"mean_token_accuracy": 0.14365074336528777,
|
|
"num_tokens": 7502122.0,
|
|
"step": 4315
|
|
},
|
|
{
|
|
"entropy": 5.795812940597534,
|
|
"epoch": 0.3361213771639759,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004992482590966188,
|
|
"loss": 5.7234,
|
|
"mean_token_accuracy": 0.14752976670861245,
|
|
"num_tokens": 7510369.0,
|
|
"step": 4320
|
|
},
|
|
{
|
|
"entropy": 5.68804521560669,
|
|
"epoch": 0.3365104065356934,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004992459936953489,
|
|
"loss": 5.6099,
|
|
"mean_token_accuracy": 0.158554507791996,
|
|
"num_tokens": 7519321.0,
|
|
"step": 4325
|
|
},
|
|
{
|
|
"entropy": 5.735086917877197,
|
|
"epoch": 0.336899435907411,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004992437248915032,
|
|
"loss": 5.655,
|
|
"mean_token_accuracy": 0.1553067222237587,
|
|
"num_tokens": 7528196.0,
|
|
"step": 4330
|
|
},
|
|
{
|
|
"entropy": 5.724933862686157,
|
|
"epoch": 0.3372884652791286,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004992414526851157,
|
|
"loss": 5.7136,
|
|
"mean_token_accuracy": 0.1463082104921341,
|
|
"num_tokens": 7536124.0,
|
|
"step": 4335
|
|
},
|
|
{
|
|
"entropy": 5.84370985031128,
|
|
"epoch": 0.3376774946508461,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004992391770762212,
|
|
"loss": 5.8058,
|
|
"mean_token_accuracy": 0.1447911098599434,
|
|
"num_tokens": 7544409.0,
|
|
"step": 4340
|
|
},
|
|
{
|
|
"entropy": 5.809447193145752,
|
|
"epoch": 0.3380665240225637,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000499236898064854,
|
|
"loss": 5.7001,
|
|
"mean_token_accuracy": 0.1530858114361763,
|
|
"num_tokens": 7552803.0,
|
|
"step": 4345
|
|
},
|
|
{
|
|
"entropy": 5.6515076637268065,
|
|
"epoch": 0.3384555533942813,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004992346156510488,
|
|
"loss": 5.6644,
|
|
"mean_token_accuracy": 0.1459401488304138,
|
|
"num_tokens": 7561909.0,
|
|
"step": 4350
|
|
},
|
|
{
|
|
"entropy": 5.825453233718872,
|
|
"epoch": 0.3388445827659988,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004992323298348403,
|
|
"loss": 5.7289,
|
|
"mean_token_accuracy": 0.14583828970789908,
|
|
"num_tokens": 7571759.0,
|
|
"step": 4355
|
|
},
|
|
{
|
|
"entropy": 5.8584259986877445,
|
|
"epoch": 0.3392336121377164,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000499230040616263,
|
|
"loss": 5.8566,
|
|
"mean_token_accuracy": 0.15016695931553842,
|
|
"num_tokens": 7580010.0,
|
|
"step": 4360
|
|
},
|
|
{
|
|
"entropy": 5.782916736602783,
|
|
"epoch": 0.33962264150943394,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004992277479953518,
|
|
"loss": 5.6514,
|
|
"mean_token_accuracy": 0.14859042316675186,
|
|
"num_tokens": 7587841.0,
|
|
"step": 4365
|
|
},
|
|
{
|
|
"entropy": 5.720286655426025,
|
|
"epoch": 0.34001167088115153,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004992254519721414,
|
|
"loss": 5.6889,
|
|
"mean_token_accuracy": 0.14878612980246544,
|
|
"num_tokens": 7596187.0,
|
|
"step": 4370
|
|
},
|
|
{
|
|
"entropy": 5.681316328048706,
|
|
"epoch": 0.3404007002528691,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004992231525466666,
|
|
"loss": 5.6074,
|
|
"mean_token_accuracy": 0.15483227521181106,
|
|
"num_tokens": 7604361.0,
|
|
"step": 4375
|
|
},
|
|
{
|
|
"entropy": 5.770654630661011,
|
|
"epoch": 0.34078972962458665,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004992208497189624,
|
|
"loss": 5.6927,
|
|
"mean_token_accuracy": 0.1531132161617279,
|
|
"num_tokens": 7613173.0,
|
|
"step": 4380
|
|
},
|
|
{
|
|
"entropy": 5.7282201766967775,
|
|
"epoch": 0.34117875899630423,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004992185434890637,
|
|
"loss": 5.7741,
|
|
"mean_token_accuracy": 0.14267738461494445,
|
|
"num_tokens": 7621730.0,
|
|
"step": 4385
|
|
},
|
|
{
|
|
"entropy": 5.8589198112487795,
|
|
"epoch": 0.34156778836802176,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004992162338570055,
|
|
"loss": 5.7414,
|
|
"mean_token_accuracy": 0.15011457800865174,
|
|
"num_tokens": 7630362.0,
|
|
"step": 4390
|
|
},
|
|
{
|
|
"entropy": 5.7542157649993895,
|
|
"epoch": 0.34195681773973935,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004992139208228227,
|
|
"loss": 5.7186,
|
|
"mean_token_accuracy": 0.14609325155615807,
|
|
"num_tokens": 7639368.0,
|
|
"step": 4395
|
|
},
|
|
{
|
|
"entropy": 5.7741481304168705,
|
|
"epoch": 0.34234584711145694,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004992116043865506,
|
|
"loss": 5.7489,
|
|
"mean_token_accuracy": 0.1471161961555481,
|
|
"num_tokens": 7648399.0,
|
|
"step": 4400
|
|
},
|
|
{
|
|
"entropy": 5.7407738208770756,
|
|
"epoch": 0.34273487648317447,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004992092845482244,
|
|
"loss": 5.5847,
|
|
"mean_token_accuracy": 0.15751371681690216,
|
|
"num_tokens": 7657298.0,
|
|
"step": 4405
|
|
},
|
|
{
|
|
"entropy": 5.788975954055786,
|
|
"epoch": 0.34312390585489205,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004992069613078791,
|
|
"loss": 5.7176,
|
|
"mean_token_accuracy": 0.15156893134117128,
|
|
"num_tokens": 7665328.0,
|
|
"step": 4410
|
|
},
|
|
{
|
|
"entropy": 5.724450349807739,
|
|
"epoch": 0.3435129352266096,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004992046346655499,
|
|
"loss": 5.6566,
|
|
"mean_token_accuracy": 0.1507851794362068,
|
|
"num_tokens": 7674610.0,
|
|
"step": 4415
|
|
},
|
|
{
|
|
"entropy": 5.772369146347046,
|
|
"epoch": 0.34390196459832717,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004992023046212723,
|
|
"loss": 5.6962,
|
|
"mean_token_accuracy": 0.15413508117198943,
|
|
"num_tokens": 7682727.0,
|
|
"step": 4420
|
|
},
|
|
{
|
|
"entropy": 5.71473445892334,
|
|
"epoch": 0.34429099397004476,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004991999711750816,
|
|
"loss": 5.6621,
|
|
"mean_token_accuracy": 0.15658219903707504,
|
|
"num_tokens": 7691547.0,
|
|
"step": 4425
|
|
},
|
|
{
|
|
"entropy": 5.73526964187622,
|
|
"epoch": 0.3446800233417623,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004991976343270133,
|
|
"loss": 5.6102,
|
|
"mean_token_accuracy": 0.15017578452825547,
|
|
"num_tokens": 7699987.0,
|
|
"step": 4430
|
|
},
|
|
{
|
|
"entropy": 5.739548635482788,
|
|
"epoch": 0.3450690527134799,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004991952940771026,
|
|
"loss": 5.6789,
|
|
"mean_token_accuracy": 0.15383388996124267,
|
|
"num_tokens": 7708397.0,
|
|
"step": 4435
|
|
},
|
|
{
|
|
"entropy": 5.745605754852295,
|
|
"epoch": 0.34545808208519746,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004991929504253852,
|
|
"loss": 5.6689,
|
|
"mean_token_accuracy": 0.14823864698410033,
|
|
"num_tokens": 7716795.0,
|
|
"step": 4440
|
|
},
|
|
{
|
|
"entropy": 5.750987958908081,
|
|
"epoch": 0.345847111456915,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004991906033718966,
|
|
"loss": 5.6828,
|
|
"mean_token_accuracy": 0.14957790747284888,
|
|
"num_tokens": 7725663.0,
|
|
"step": 4445
|
|
},
|
|
{
|
|
"entropy": 5.786761999130249,
|
|
"epoch": 0.3462361408286326,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004991882529166724,
|
|
"loss": 5.8069,
|
|
"mean_token_accuracy": 0.14756733924150467,
|
|
"num_tokens": 7735175.0,
|
|
"step": 4450
|
|
},
|
|
{
|
|
"entropy": 5.77248911857605,
|
|
"epoch": 0.3466251702003501,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004991858990597483,
|
|
"loss": 5.6742,
|
|
"mean_token_accuracy": 0.15260669961571693,
|
|
"num_tokens": 7744041.0,
|
|
"step": 4455
|
|
},
|
|
{
|
|
"entropy": 5.813203620910644,
|
|
"epoch": 0.3470141995720677,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004991835418011601,
|
|
"loss": 5.7328,
|
|
"mean_token_accuracy": 0.14599995985627173,
|
|
"num_tokens": 7752168.0,
|
|
"step": 4460
|
|
},
|
|
{
|
|
"entropy": 5.774614095687866,
|
|
"epoch": 0.3474032289437853,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004991811811409434,
|
|
"loss": 5.6653,
|
|
"mean_token_accuracy": 0.1525656133890152,
|
|
"num_tokens": 7760746.0,
|
|
"step": 4465
|
|
},
|
|
{
|
|
"entropy": 5.690586090087891,
|
|
"epoch": 0.3477922583155028,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004991788170791341,
|
|
"loss": 5.6782,
|
|
"mean_token_accuracy": 0.15173280835151673,
|
|
"num_tokens": 7769960.0,
|
|
"step": 4470
|
|
},
|
|
{
|
|
"entropy": 5.805200624465942,
|
|
"epoch": 0.3481812876872204,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004991764496157682,
|
|
"loss": 5.7113,
|
|
"mean_token_accuracy": 0.14903471767902374,
|
|
"num_tokens": 7778475.0,
|
|
"step": 4475
|
|
},
|
|
{
|
|
"entropy": 5.694829988479614,
|
|
"epoch": 0.34857031705893793,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004991740787508814,
|
|
"loss": 5.571,
|
|
"mean_token_accuracy": 0.15922194421291352,
|
|
"num_tokens": 7787590.0,
|
|
"step": 4480
|
|
},
|
|
{
|
|
"entropy": 5.716617298126221,
|
|
"epoch": 0.3489593464306555,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004991717044845097,
|
|
"loss": 5.7509,
|
|
"mean_token_accuracy": 0.14409140273928642,
|
|
"num_tokens": 7796841.0,
|
|
"step": 4485
|
|
},
|
|
{
|
|
"entropy": 5.844481468200684,
|
|
"epoch": 0.3493483758023731,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004991693268166892,
|
|
"loss": 5.752,
|
|
"mean_token_accuracy": 0.1473579525947571,
|
|
"num_tokens": 7804889.0,
|
|
"step": 4490
|
|
},
|
|
{
|
|
"entropy": 5.751714563369751,
|
|
"epoch": 0.34973740517409063,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004991669457474559,
|
|
"loss": 5.7307,
|
|
"mean_token_accuracy": 0.1499755159020424,
|
|
"num_tokens": 7813185.0,
|
|
"step": 4495
|
|
},
|
|
{
|
|
"entropy": 5.805147790908814,
|
|
"epoch": 0.3501264345458082,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004991645612768461,
|
|
"loss": 5.7197,
|
|
"mean_token_accuracy": 0.15086604356765748,
|
|
"num_tokens": 7821630.0,
|
|
"step": 4500
|
|
},
|
|
{
|
|
"entropy": 5.836012315750122,
|
|
"epoch": 0.35051546391752575,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004991621734048958,
|
|
"loss": 5.7522,
|
|
"mean_token_accuracy": 0.15427149161696435,
|
|
"num_tokens": 7829941.0,
|
|
"step": 4505
|
|
},
|
|
{
|
|
"entropy": 5.707473087310791,
|
|
"epoch": 0.35090449328924334,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004991597821316415,
|
|
"loss": 5.6936,
|
|
"mean_token_accuracy": 0.15636295527219773,
|
|
"num_tokens": 7838515.0,
|
|
"step": 4510
|
|
},
|
|
{
|
|
"entropy": 5.8055788516998295,
|
|
"epoch": 0.3512935226609609,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004991573874571192,
|
|
"loss": 5.6896,
|
|
"mean_token_accuracy": 0.15325772613286973,
|
|
"num_tokens": 7846575.0,
|
|
"step": 4515
|
|
},
|
|
{
|
|
"entropy": 5.651686334609986,
|
|
"epoch": 0.35168255203267845,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004991549893813653,
|
|
"loss": 5.5803,
|
|
"mean_token_accuracy": 0.1577739804983139,
|
|
"num_tokens": 7854970.0,
|
|
"step": 4520
|
|
},
|
|
{
|
|
"entropy": 5.672727489471436,
|
|
"epoch": 0.35207158140439604,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004991525879044162,
|
|
"loss": 5.6722,
|
|
"mean_token_accuracy": 0.1503447487950325,
|
|
"num_tokens": 7863293.0,
|
|
"step": 4525
|
|
},
|
|
{
|
|
"entropy": 5.777629470825195,
|
|
"epoch": 0.35246061077611357,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004991501830263084,
|
|
"loss": 5.6652,
|
|
"mean_token_accuracy": 0.15367957353591918,
|
|
"num_tokens": 7871029.0,
|
|
"step": 4530
|
|
},
|
|
{
|
|
"entropy": 5.671704244613648,
|
|
"epoch": 0.35284964014783116,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004991477747470783,
|
|
"loss": 5.5294,
|
|
"mean_token_accuracy": 0.1555831491947174,
|
|
"num_tokens": 7879797.0,
|
|
"step": 4535
|
|
},
|
|
{
|
|
"entropy": 5.820374870300293,
|
|
"epoch": 0.35323866951954874,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004991453630667625,
|
|
"loss": 5.8385,
|
|
"mean_token_accuracy": 0.14210431426763534,
|
|
"num_tokens": 7888600.0,
|
|
"step": 4540
|
|
},
|
|
{
|
|
"entropy": 5.752278423309326,
|
|
"epoch": 0.3536276988912663,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004991429479853976,
|
|
"loss": 5.6771,
|
|
"mean_token_accuracy": 0.15561284869909286,
|
|
"num_tokens": 7897794.0,
|
|
"step": 4545
|
|
},
|
|
{
|
|
"entropy": 5.773390102386474,
|
|
"epoch": 0.35401672826298386,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004991405295030202,
|
|
"loss": 5.658,
|
|
"mean_token_accuracy": 0.15940722376108168,
|
|
"num_tokens": 7905822.0,
|
|
"step": 4550
|
|
},
|
|
{
|
|
"entropy": 5.700776815414429,
|
|
"epoch": 0.35440575763470145,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004991381076196671,
|
|
"loss": 5.7223,
|
|
"mean_token_accuracy": 0.1521821677684784,
|
|
"num_tokens": 7914560.0,
|
|
"step": 4555
|
|
},
|
|
{
|
|
"entropy": 5.661709499359131,
|
|
"epoch": 0.354794787006419,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004991356823353748,
|
|
"loss": 5.577,
|
|
"mean_token_accuracy": 0.15658768862485886,
|
|
"num_tokens": 7924058.0,
|
|
"step": 4560
|
|
},
|
|
{
|
|
"entropy": 5.762267398834228,
|
|
"epoch": 0.35518381637813656,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004991332536501804,
|
|
"loss": 5.7225,
|
|
"mean_token_accuracy": 0.1503455936908722,
|
|
"num_tokens": 7932979.0,
|
|
"step": 4565
|
|
},
|
|
{
|
|
"entropy": 5.655368661880493,
|
|
"epoch": 0.3555728457498541,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004991308215641205,
|
|
"loss": 5.4999,
|
|
"mean_token_accuracy": 0.16385250836610793,
|
|
"num_tokens": 7941357.0,
|
|
"step": 4570
|
|
},
|
|
{
|
|
"entropy": 5.6736588954925535,
|
|
"epoch": 0.3559618751215717,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004991283860772323,
|
|
"loss": 5.6739,
|
|
"mean_token_accuracy": 0.15402223020792008,
|
|
"num_tokens": 7949997.0,
|
|
"step": 4575
|
|
},
|
|
{
|
|
"entropy": 5.716558218002319,
|
|
"epoch": 0.35635090449328927,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004991259471895525,
|
|
"loss": 5.6288,
|
|
"mean_token_accuracy": 0.14936613291502,
|
|
"num_tokens": 7958246.0,
|
|
"step": 4580
|
|
},
|
|
{
|
|
"entropy": 5.683485794067383,
|
|
"epoch": 0.3567399338650068,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004991235049011182,
|
|
"loss": 5.7203,
|
|
"mean_token_accuracy": 0.14906762838363646,
|
|
"num_tokens": 7967176.0,
|
|
"step": 4585
|
|
},
|
|
{
|
|
"entropy": 5.747391319274902,
|
|
"epoch": 0.3571289632367244,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004991210592119663,
|
|
"loss": 5.5664,
|
|
"mean_token_accuracy": 0.16120724231004716,
|
|
"num_tokens": 7974761.0,
|
|
"step": 4590
|
|
},
|
|
{
|
|
"entropy": 5.708501148223877,
|
|
"epoch": 0.3575179926084419,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004991186101221342,
|
|
"loss": 5.643,
|
|
"mean_token_accuracy": 0.1528185173869133,
|
|
"num_tokens": 7983155.0,
|
|
"step": 4595
|
|
},
|
|
{
|
|
"entropy": 5.7329905986785885,
|
|
"epoch": 0.3579070219801595,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000499116157631659,
|
|
"loss": 5.6438,
|
|
"mean_token_accuracy": 0.14957136809825897,
|
|
"num_tokens": 7991276.0,
|
|
"step": 4600
|
|
},
|
|
{
|
|
"entropy": 5.790548658370971,
|
|
"epoch": 0.3582960513518771,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004991137017405777,
|
|
"loss": 5.7855,
|
|
"mean_token_accuracy": 0.1485683262348175,
|
|
"num_tokens": 7999488.0,
|
|
"step": 4605
|
|
},
|
|
{
|
|
"entropy": 5.799504184722901,
|
|
"epoch": 0.3586850807235946,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004991112424489277,
|
|
"loss": 5.6554,
|
|
"mean_token_accuracy": 0.1543542042374611,
|
|
"num_tokens": 8008553.0,
|
|
"step": 4610
|
|
},
|
|
{
|
|
"entropy": 5.698079681396484,
|
|
"epoch": 0.3590741100953122,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004991087797567462,
|
|
"loss": 5.6266,
|
|
"mean_token_accuracy": 0.15792726278305053,
|
|
"num_tokens": 8017890.0,
|
|
"step": 4615
|
|
},
|
|
{
|
|
"entropy": 5.748518419265747,
|
|
"epoch": 0.35946313946702974,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004991063136640709,
|
|
"loss": 5.7805,
|
|
"mean_token_accuracy": 0.14351232275366782,
|
|
"num_tokens": 8025782.0,
|
|
"step": 4620
|
|
},
|
|
{
|
|
"entropy": 5.807697534561157,
|
|
"epoch": 0.3598521688387473,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004991038441709388,
|
|
"loss": 5.6364,
|
|
"mean_token_accuracy": 0.15547887086868287,
|
|
"num_tokens": 8034623.0,
|
|
"step": 4625
|
|
},
|
|
{
|
|
"entropy": 5.715529870986939,
|
|
"epoch": 0.3602411982104649,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004991013712773877,
|
|
"loss": 5.6676,
|
|
"mean_token_accuracy": 0.148578180372715,
|
|
"num_tokens": 8043789.0,
|
|
"step": 4630
|
|
},
|
|
{
|
|
"entropy": 5.687366724014282,
|
|
"epoch": 0.36063022758218244,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004990988949834549,
|
|
"loss": 5.6296,
|
|
"mean_token_accuracy": 0.1519090548157692,
|
|
"num_tokens": 8053456.0,
|
|
"step": 4635
|
|
},
|
|
{
|
|
"entropy": 5.633113861083984,
|
|
"epoch": 0.3610192569539,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.000499096415289178,
|
|
"loss": 5.6033,
|
|
"mean_token_accuracy": 0.15289738029241562,
|
|
"num_tokens": 8061692.0,
|
|
"step": 4640
|
|
},
|
|
{
|
|
"entropy": 5.604199457168579,
|
|
"epoch": 0.3614082863256176,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004990939321945948,
|
|
"loss": 5.5536,
|
|
"mean_token_accuracy": 0.15800046771764756,
|
|
"num_tokens": 8069564.0,
|
|
"step": 4645
|
|
},
|
|
{
|
|
"entropy": 5.718245315551758,
|
|
"epoch": 0.36179731569733514,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004990914456997427,
|
|
"loss": 5.6435,
|
|
"mean_token_accuracy": 0.14634049832820892,
|
|
"num_tokens": 8078490.0,
|
|
"step": 4650
|
|
},
|
|
{
|
|
"entropy": 5.722595119476319,
|
|
"epoch": 0.36218634506905273,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004990889558046598,
|
|
"loss": 5.7247,
|
|
"mean_token_accuracy": 0.14826465845108033,
|
|
"num_tokens": 8086858.0,
|
|
"step": 4655
|
|
},
|
|
{
|
|
"entropy": 5.757637453079224,
|
|
"epoch": 0.36257537444077026,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004990864625093836,
|
|
"loss": 5.6636,
|
|
"mean_token_accuracy": 0.1571757525205612,
|
|
"num_tokens": 8094542.0,
|
|
"step": 4660
|
|
},
|
|
{
|
|
"entropy": 5.779032802581787,
|
|
"epoch": 0.36296440381248785,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004990839658139519,
|
|
"loss": 5.7169,
|
|
"mean_token_accuracy": 0.15186462104320525,
|
|
"num_tokens": 8102756.0,
|
|
"step": 4665
|
|
},
|
|
{
|
|
"entropy": 5.825753402709961,
|
|
"epoch": 0.36335343318420543,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004990814657184028,
|
|
"loss": 5.7476,
|
|
"mean_token_accuracy": 0.15559100806713105,
|
|
"num_tokens": 8111258.0,
|
|
"step": 4670
|
|
},
|
|
{
|
|
"entropy": 5.857345867156982,
|
|
"epoch": 0.36374246255592296,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004990789622227741,
|
|
"loss": 5.8447,
|
|
"mean_token_accuracy": 0.144379186630249,
|
|
"num_tokens": 8119624.0,
|
|
"step": 4675
|
|
},
|
|
{
|
|
"entropy": 5.7407505989074705,
|
|
"epoch": 0.36413149192764055,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004990764553271038,
|
|
"loss": 5.6134,
|
|
"mean_token_accuracy": 0.15366872400045395,
|
|
"num_tokens": 8128156.0,
|
|
"step": 4680
|
|
},
|
|
{
|
|
"entropy": 5.72602686882019,
|
|
"epoch": 0.3645205212993581,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004990739450314299,
|
|
"loss": 5.6786,
|
|
"mean_token_accuracy": 0.14902170971035958,
|
|
"num_tokens": 8136080.0,
|
|
"step": 4685
|
|
},
|
|
{
|
|
"entropy": 5.751847553253174,
|
|
"epoch": 0.36490955067107567,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004990714313357906,
|
|
"loss": 5.6585,
|
|
"mean_token_accuracy": 0.15590455532073974,
|
|
"num_tokens": 8144742.0,
|
|
"step": 4690
|
|
},
|
|
{
|
|
"entropy": 5.737034893035888,
|
|
"epoch": 0.36529858004279325,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000499068914240224,
|
|
"loss": 5.7293,
|
|
"mean_token_accuracy": 0.15128549188375473,
|
|
"num_tokens": 8153377.0,
|
|
"step": 4695
|
|
},
|
|
{
|
|
"entropy": 5.796698474884034,
|
|
"epoch": 0.3656876094145108,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004990663937447682,
|
|
"loss": 5.6537,
|
|
"mean_token_accuracy": 0.15566126704216005,
|
|
"num_tokens": 8162169.0,
|
|
"step": 4700
|
|
},
|
|
{
|
|
"entropy": 5.7169088363647464,
|
|
"epoch": 0.36607663878622837,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004990638698494615,
|
|
"loss": 5.6176,
|
|
"mean_token_accuracy": 0.15707356631755828,
|
|
"num_tokens": 8170727.0,
|
|
"step": 4705
|
|
},
|
|
{
|
|
"entropy": 5.605865859985352,
|
|
"epoch": 0.3664656681579459,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004990613425543423,
|
|
"loss": 5.5769,
|
|
"mean_token_accuracy": 0.15790215730667115,
|
|
"num_tokens": 8179013.0,
|
|
"step": 4710
|
|
},
|
|
{
|
|
"entropy": 5.608945417404175,
|
|
"epoch": 0.3668546975296635,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004990588118594487,
|
|
"loss": 5.5506,
|
|
"mean_token_accuracy": 0.16253751665353774,
|
|
"num_tokens": 8187030.0,
|
|
"step": 4715
|
|
},
|
|
{
|
|
"entropy": 5.626094484329224,
|
|
"epoch": 0.3672437269013811,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004990562777648194,
|
|
"loss": 5.5305,
|
|
"mean_token_accuracy": 0.16110363602638245,
|
|
"num_tokens": 8195073.0,
|
|
"step": 4720
|
|
},
|
|
{
|
|
"entropy": 5.708602380752564,
|
|
"epoch": 0.3676327562730986,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004990537402704928,
|
|
"loss": 5.6886,
|
|
"mean_token_accuracy": 0.15165950506925582,
|
|
"num_tokens": 8203626.0,
|
|
"step": 4725
|
|
},
|
|
{
|
|
"entropy": 5.740704441070557,
|
|
"epoch": 0.3680217856448162,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004990511993765071,
|
|
"loss": 5.6818,
|
|
"mean_token_accuracy": 0.15222800001502038,
|
|
"num_tokens": 8212750.0,
|
|
"step": 4730
|
|
},
|
|
{
|
|
"entropy": 5.796080303192139,
|
|
"epoch": 0.3684108150165337,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004990486550829011,
|
|
"loss": 5.6619,
|
|
"mean_token_accuracy": 0.14802802354097366,
|
|
"num_tokens": 8221542.0,
|
|
"step": 4735
|
|
},
|
|
{
|
|
"entropy": 5.622773456573486,
|
|
"epoch": 0.3687998443882513,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004990461073897134,
|
|
"loss": 5.6049,
|
|
"mean_token_accuracy": 0.14905112236738205,
|
|
"num_tokens": 8230574.0,
|
|
"step": 4740
|
|
},
|
|
{
|
|
"entropy": 5.730619859695435,
|
|
"epoch": 0.3691888737599689,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004990435562969827,
|
|
"loss": 5.6972,
|
|
"mean_token_accuracy": 0.14874366521835328,
|
|
"num_tokens": 8239400.0,
|
|
"step": 4745
|
|
},
|
|
{
|
|
"entropy": 5.72901029586792,
|
|
"epoch": 0.3695779031316864,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004990410018047475,
|
|
"loss": 5.5251,
|
|
"mean_token_accuracy": 0.1579698383808136,
|
|
"num_tokens": 8247537.0,
|
|
"step": 4750
|
|
},
|
|
{
|
|
"entropy": 5.6703370094299315,
|
|
"epoch": 0.369966932503404,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004990384439130467,
|
|
"loss": 5.6396,
|
|
"mean_token_accuracy": 0.15181135013699532,
|
|
"num_tokens": 8256551.0,
|
|
"step": 4755
|
|
},
|
|
{
|
|
"entropy": 5.7400750637054445,
|
|
"epoch": 0.3703559618751216,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004990358826219192,
|
|
"loss": 5.6844,
|
|
"mean_token_accuracy": 0.1494295671582222,
|
|
"num_tokens": 8265492.0,
|
|
"step": 4760
|
|
},
|
|
{
|
|
"entropy": 5.737407207489014,
|
|
"epoch": 0.37074499124683913,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004990333179314038,
|
|
"loss": 5.6124,
|
|
"mean_token_accuracy": 0.15380854159593582,
|
|
"num_tokens": 8273798.0,
|
|
"step": 4765
|
|
},
|
|
{
|
|
"entropy": 5.640963745117188,
|
|
"epoch": 0.3711340206185567,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004990307498415393,
|
|
"loss": 5.5995,
|
|
"mean_token_accuracy": 0.1561552718281746,
|
|
"num_tokens": 8281998.0,
|
|
"step": 4770
|
|
},
|
|
{
|
|
"entropy": 5.725772285461426,
|
|
"epoch": 0.37152304999027425,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004990281783523648,
|
|
"loss": 5.7066,
|
|
"mean_token_accuracy": 0.14791832715272904,
|
|
"num_tokens": 8289833.0,
|
|
"step": 4775
|
|
},
|
|
{
|
|
"entropy": 5.670173215866089,
|
|
"epoch": 0.37191207936199183,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004990256034639192,
|
|
"loss": 5.6611,
|
|
"mean_token_accuracy": 0.1593535929918289,
|
|
"num_tokens": 8297562.0,
|
|
"step": 4780
|
|
},
|
|
{
|
|
"entropy": 5.801353979110718,
|
|
"epoch": 0.3723011087337094,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004990230251762418,
|
|
"loss": 5.6676,
|
|
"mean_token_accuracy": 0.15265004262328147,
|
|
"num_tokens": 8305262.0,
|
|
"step": 4785
|
|
},
|
|
{
|
|
"entropy": 5.720134830474853,
|
|
"epoch": 0.37269013810542695,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004990204434893713,
|
|
"loss": 5.5911,
|
|
"mean_token_accuracy": 0.1556418776512146,
|
|
"num_tokens": 8313949.0,
|
|
"step": 4790
|
|
},
|
|
{
|
|
"entropy": 5.650853681564331,
|
|
"epoch": 0.37307916747714454,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004990178584033474,
|
|
"loss": 5.63,
|
|
"mean_token_accuracy": 0.153776678442955,
|
|
"num_tokens": 8322801.0,
|
|
"step": 4795
|
|
},
|
|
{
|
|
"entropy": 5.779564762115479,
|
|
"epoch": 0.37346819684886207,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004990152699182089,
|
|
"loss": 5.62,
|
|
"mean_token_accuracy": 0.1598824217915535,
|
|
"num_tokens": 8331118.0,
|
|
"step": 4800
|
|
},
|
|
{
|
|
"entropy": 5.7409477710723875,
|
|
"epoch": 0.37385722622057965,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004990126780339953,
|
|
"loss": 5.6884,
|
|
"mean_token_accuracy": 0.15528960078954696,
|
|
"num_tokens": 8340498.0,
|
|
"step": 4805
|
|
},
|
|
{
|
|
"entropy": 5.785793113708496,
|
|
"epoch": 0.37424625559229724,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004990100827507459,
|
|
"loss": 5.8207,
|
|
"mean_token_accuracy": 0.14700310155749322,
|
|
"num_tokens": 8349235.0,
|
|
"step": 4810
|
|
},
|
|
{
|
|
"entropy": 5.755542755126953,
|
|
"epoch": 0.37463528496401477,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004990074840684999,
|
|
"loss": 5.6936,
|
|
"mean_token_accuracy": 0.1547679141163826,
|
|
"num_tokens": 8358484.0,
|
|
"step": 4815
|
|
},
|
|
{
|
|
"entropy": 5.776040840148926,
|
|
"epoch": 0.37502431433573236,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004990048819872969,
|
|
"loss": 5.6245,
|
|
"mean_token_accuracy": 0.15924780070781708,
|
|
"num_tokens": 8366894.0,
|
|
"step": 4820
|
|
},
|
|
{
|
|
"entropy": 5.662250757217407,
|
|
"epoch": 0.3754133437074499,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004990022765071765,
|
|
"loss": 5.631,
|
|
"mean_token_accuracy": 0.1452302061021328,
|
|
"num_tokens": 8375271.0,
|
|
"step": 4825
|
|
},
|
|
{
|
|
"entropy": 5.68854022026062,
|
|
"epoch": 0.3758023730791675,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000498999667628178,
|
|
"loss": 5.5764,
|
|
"mean_token_accuracy": 0.15381914377212524,
|
|
"num_tokens": 8383714.0,
|
|
"step": 4830
|
|
},
|
|
{
|
|
"entropy": 5.651234245300293,
|
|
"epoch": 0.37619140245088506,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004989970553503411,
|
|
"loss": 5.6853,
|
|
"mean_token_accuracy": 0.15144770443439484,
|
|
"num_tokens": 8392022.0,
|
|
"step": 4835
|
|
},
|
|
{
|
|
"entropy": 5.759373378753662,
|
|
"epoch": 0.3765804318226026,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004989944396737054,
|
|
"loss": 5.65,
|
|
"mean_token_accuracy": 0.14829441905021667,
|
|
"num_tokens": 8401282.0,
|
|
"step": 4840
|
|
},
|
|
{
|
|
"entropy": 5.729718780517578,
|
|
"epoch": 0.3769694611943202,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004989918205983106,
|
|
"loss": 5.7199,
|
|
"mean_token_accuracy": 0.14889771938323976,
|
|
"num_tokens": 8411147.0,
|
|
"step": 4845
|
|
},
|
|
{
|
|
"entropy": 5.8805125713348385,
|
|
"epoch": 0.37735849056603776,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004989891981241964,
|
|
"loss": 5.7159,
|
|
"mean_token_accuracy": 0.1495855137705803,
|
|
"num_tokens": 8420434.0,
|
|
"step": 4850
|
|
},
|
|
{
|
|
"entropy": 5.745460796356201,
|
|
"epoch": 0.3777475199377553,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004989865722514027,
|
|
"loss": 5.6811,
|
|
"mean_token_accuracy": 0.1509254492819309,
|
|
"num_tokens": 8430022.0,
|
|
"step": 4855
|
|
},
|
|
{
|
|
"entropy": 5.540482044219971,
|
|
"epoch": 0.3781365493094729,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004989839429799692,
|
|
"loss": 5.4636,
|
|
"mean_token_accuracy": 0.16462698578834534,
|
|
"num_tokens": 8438898.0,
|
|
"step": 4860
|
|
},
|
|
{
|
|
"entropy": 5.618959999084472,
|
|
"epoch": 0.3785255786811904,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.000498981310309936,
|
|
"loss": 5.5649,
|
|
"mean_token_accuracy": 0.15923128873109818,
|
|
"num_tokens": 8446931.0,
|
|
"step": 4865
|
|
},
|
|
{
|
|
"entropy": 5.75497031211853,
|
|
"epoch": 0.378914608052908,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004989786742413428,
|
|
"loss": 5.638,
|
|
"mean_token_accuracy": 0.15647049695253373,
|
|
"num_tokens": 8455515.0,
|
|
"step": 4870
|
|
},
|
|
{
|
|
"entropy": 5.714741182327271,
|
|
"epoch": 0.3793036374246256,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004989760347742298,
|
|
"loss": 5.639,
|
|
"mean_token_accuracy": 0.15014245137572288,
|
|
"num_tokens": 8464135.0,
|
|
"step": 4875
|
|
},
|
|
{
|
|
"entropy": 5.76575117111206,
|
|
"epoch": 0.3796926667963431,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004989733919086369,
|
|
"loss": 5.7329,
|
|
"mean_token_accuracy": 0.1491445854306221,
|
|
"num_tokens": 8473222.0,
|
|
"step": 4880
|
|
},
|
|
{
|
|
"entropy": 5.757653379440308,
|
|
"epoch": 0.3800816961680607,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004989707456446043,
|
|
"loss": 5.7107,
|
|
"mean_token_accuracy": 0.15802261978387833,
|
|
"num_tokens": 8481966.0,
|
|
"step": 4885
|
|
},
|
|
{
|
|
"entropy": 5.763038921356201,
|
|
"epoch": 0.38047072553977823,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004989680959821721,
|
|
"loss": 5.7354,
|
|
"mean_token_accuracy": 0.1485402375459671,
|
|
"num_tokens": 8491276.0,
|
|
"step": 4890
|
|
},
|
|
{
|
|
"entropy": 5.71974368095398,
|
|
"epoch": 0.3808597549114958,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004989654429213805,
|
|
"loss": 5.6814,
|
|
"mean_token_accuracy": 0.15291936323046684,
|
|
"num_tokens": 8499926.0,
|
|
"step": 4895
|
|
},
|
|
{
|
|
"entropy": 5.741155004501342,
|
|
"epoch": 0.3812487842832134,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004989627864622699,
|
|
"loss": 5.5594,
|
|
"mean_token_accuracy": 0.15729069113731384,
|
|
"num_tokens": 8508544.0,
|
|
"step": 4900
|
|
},
|
|
{
|
|
"entropy": 5.758600425720215,
|
|
"epoch": 0.38163781365493094,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004989601266048804,
|
|
"loss": 5.682,
|
|
"mean_token_accuracy": 0.1453734003007412,
|
|
"num_tokens": 8517326.0,
|
|
"step": 4905
|
|
},
|
|
{
|
|
"entropy": 5.64643874168396,
|
|
"epoch": 0.3820268430266485,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004989574633492525,
|
|
"loss": 5.6628,
|
|
"mean_token_accuracy": 0.15118559151887895,
|
|
"num_tokens": 8526218.0,
|
|
"step": 4910
|
|
},
|
|
{
|
|
"entropy": 5.787919235229492,
|
|
"epoch": 0.38241587239836605,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004989547966954266,
|
|
"loss": 5.6956,
|
|
"mean_token_accuracy": 0.1465151771903038,
|
|
"num_tokens": 8534708.0,
|
|
"step": 4915
|
|
},
|
|
{
|
|
"entropy": 5.723714780807495,
|
|
"epoch": 0.38280490177008364,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.000498952126643443,
|
|
"loss": 5.6392,
|
|
"mean_token_accuracy": 0.15696539580821992,
|
|
"num_tokens": 8543302.0,
|
|
"step": 4920
|
|
},
|
|
{
|
|
"entropy": 5.613685512542725,
|
|
"epoch": 0.3831939311418012,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004989494531933424,
|
|
"loss": 5.5588,
|
|
"mean_token_accuracy": 0.15237713605165482,
|
|
"num_tokens": 8552586.0,
|
|
"step": 4925
|
|
},
|
|
{
|
|
"entropy": 5.64679446220398,
|
|
"epoch": 0.38358296051351876,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004989467763451652,
|
|
"loss": 5.5374,
|
|
"mean_token_accuracy": 0.15823079496622086,
|
|
"num_tokens": 8561720.0,
|
|
"step": 4930
|
|
},
|
|
{
|
|
"entropy": 5.698852682113648,
|
|
"epoch": 0.38397198988523634,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004989440960989523,
|
|
"loss": 5.529,
|
|
"mean_token_accuracy": 0.15683713406324387,
|
|
"num_tokens": 8570510.0,
|
|
"step": 4935
|
|
},
|
|
{
|
|
"entropy": 5.667657041549683,
|
|
"epoch": 0.3843610192569539,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000498941412454744,
|
|
"loss": 5.6631,
|
|
"mean_token_accuracy": 0.15189100801944733,
|
|
"num_tokens": 8579986.0,
|
|
"step": 4940
|
|
},
|
|
{
|
|
"entropy": 5.660448598861694,
|
|
"epoch": 0.38475004862867146,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004989387254125813,
|
|
"loss": 5.6278,
|
|
"mean_token_accuracy": 0.14973406940698625,
|
|
"num_tokens": 8588507.0,
|
|
"step": 4945
|
|
},
|
|
{
|
|
"entropy": 5.676297044754028,
|
|
"epoch": 0.38513907800038905,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004989360349725049,
|
|
"loss": 5.5545,
|
|
"mean_token_accuracy": 0.1551334172487259,
|
|
"num_tokens": 8596651.0,
|
|
"step": 4950
|
|
},
|
|
{
|
|
"entropy": 5.7129144191741945,
|
|
"epoch": 0.3855281073721066,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004989333411345555,
|
|
"loss": 5.5836,
|
|
"mean_token_accuracy": 0.15729959458112716,
|
|
"num_tokens": 8605080.0,
|
|
"step": 4955
|
|
},
|
|
{
|
|
"entropy": 5.641625881195068,
|
|
"epoch": 0.38591713674382416,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004989306438987742,
|
|
"loss": 5.548,
|
|
"mean_token_accuracy": 0.1537535160779953,
|
|
"num_tokens": 8613017.0,
|
|
"step": 4960
|
|
},
|
|
{
|
|
"entropy": 5.702543449401856,
|
|
"epoch": 0.38630616611554175,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004989279432652018,
|
|
"loss": 5.7241,
|
|
"mean_token_accuracy": 0.1546338826417923,
|
|
"num_tokens": 8621954.0,
|
|
"step": 4965
|
|
},
|
|
{
|
|
"entropy": 5.809708023071289,
|
|
"epoch": 0.3866951954872593,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004989252392338791,
|
|
"loss": 5.6677,
|
|
"mean_token_accuracy": 0.1566025510430336,
|
|
"num_tokens": 8630213.0,
|
|
"step": 4970
|
|
},
|
|
{
|
|
"entropy": 5.784931945800781,
|
|
"epoch": 0.38708422485897687,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004989225318048475,
|
|
"loss": 5.6861,
|
|
"mean_token_accuracy": 0.15659048557281494,
|
|
"num_tokens": 8638360.0,
|
|
"step": 4975
|
|
},
|
|
{
|
|
"entropy": 5.757261753082275,
|
|
"epoch": 0.3874732542306944,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004989198209781478,
|
|
"loss": 5.723,
|
|
"mean_token_accuracy": 0.15046840906143188,
|
|
"num_tokens": 8647778.0,
|
|
"step": 4980
|
|
},
|
|
{
|
|
"entropy": 5.73045597076416,
|
|
"epoch": 0.387862283602412,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004989171067538211,
|
|
"loss": 5.6507,
|
|
"mean_token_accuracy": 0.15228100568056108,
|
|
"num_tokens": 8655584.0,
|
|
"step": 4985
|
|
},
|
|
{
|
|
"entropy": 5.673905515670777,
|
|
"epoch": 0.38825131297412957,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.000498914389131909,
|
|
"loss": 5.6874,
|
|
"mean_token_accuracy": 0.1532427988946438,
|
|
"num_tokens": 8664159.0,
|
|
"step": 4990
|
|
},
|
|
{
|
|
"entropy": 5.718062448501587,
|
|
"epoch": 0.3886403423458471,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004989116681124523,
|
|
"loss": 5.5877,
|
|
"mean_token_accuracy": 0.1540216326713562,
|
|
"num_tokens": 8672488.0,
|
|
"step": 4995
|
|
},
|
|
{
|
|
"entropy": 5.754921197891235,
|
|
"epoch": 0.3890293717175647,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004989089436954924,
|
|
"loss": 5.7203,
|
|
"mean_token_accuracy": 0.1480067603290081,
|
|
"num_tokens": 8681492.0,
|
|
"step": 5000
|
|
},
|
|
{
|
|
"entropy": 5.677997732162476,
|
|
"epoch": 0.3894184010892822,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004989062158810706,
|
|
"loss": 5.606,
|
|
"mean_token_accuracy": 0.15589867532253265,
|
|
"num_tokens": 8690453.0,
|
|
"step": 5005
|
|
},
|
|
{
|
|
"entropy": 5.791937589645386,
|
|
"epoch": 0.3898074304609998,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004989034846692284,
|
|
"loss": 5.6959,
|
|
"mean_token_accuracy": 0.15180487632751466,
|
|
"num_tokens": 8699349.0,
|
|
"step": 5010
|
|
},
|
|
{
|
|
"entropy": 5.6987401962280275,
|
|
"epoch": 0.3901964598327174,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004989007500600073,
|
|
"loss": 5.6942,
|
|
"mean_token_accuracy": 0.1500448077917099,
|
|
"num_tokens": 8707512.0,
|
|
"step": 5015
|
|
},
|
|
{
|
|
"entropy": 5.793087816238403,
|
|
"epoch": 0.3905854892044349,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004988980120534486,
|
|
"loss": 5.717,
|
|
"mean_token_accuracy": 0.14697987586259842,
|
|
"num_tokens": 8715847.0,
|
|
"step": 5020
|
|
},
|
|
{
|
|
"entropy": 5.72705192565918,
|
|
"epoch": 0.3909745185761525,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.000498895270649594,
|
|
"loss": 5.6111,
|
|
"mean_token_accuracy": 0.1572824612259865,
|
|
"num_tokens": 8725548.0,
|
|
"step": 5025
|
|
},
|
|
{
|
|
"entropy": 5.638960075378418,
|
|
"epoch": 0.39136354794787004,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.000498892525848485,
|
|
"loss": 5.564,
|
|
"mean_token_accuracy": 0.16159805804491043,
|
|
"num_tokens": 8733935.0,
|
|
"step": 5030
|
|
},
|
|
{
|
|
"entropy": 5.7204138278961185,
|
|
"epoch": 0.3917525773195876,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004988897776501633,
|
|
"loss": 5.6876,
|
|
"mean_token_accuracy": 0.15322512090206147,
|
|
"num_tokens": 8743110.0,
|
|
"step": 5035
|
|
},
|
|
{
|
|
"entropy": 5.641509246826172,
|
|
"epoch": 0.3921416066913052,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004988870260546705,
|
|
"loss": 5.5112,
|
|
"mean_token_accuracy": 0.1590324655175209,
|
|
"num_tokens": 8751166.0,
|
|
"step": 5040
|
|
},
|
|
{
|
|
"entropy": 5.681423711776733,
|
|
"epoch": 0.39253063606302274,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004988842710620486,
|
|
"loss": 5.7162,
|
|
"mean_token_accuracy": 0.15126417875289916,
|
|
"num_tokens": 8759929.0,
|
|
"step": 5045
|
|
},
|
|
{
|
|
"entropy": 5.837319183349609,
|
|
"epoch": 0.39291966543474033,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004988815126723391,
|
|
"loss": 5.7138,
|
|
"mean_token_accuracy": 0.15048869475722312,
|
|
"num_tokens": 8768541.0,
|
|
"step": 5050
|
|
},
|
|
{
|
|
"entropy": 5.765131187438965,
|
|
"epoch": 0.3933086948064579,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004988787508855841,
|
|
"loss": 5.6237,
|
|
"mean_token_accuracy": 0.153934982419014,
|
|
"num_tokens": 8776803.0,
|
|
"step": 5055
|
|
},
|
|
{
|
|
"entropy": 5.62071008682251,
|
|
"epoch": 0.39369772417817545,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004988759857018253,
|
|
"loss": 5.5955,
|
|
"mean_token_accuracy": 0.1592630684375763,
|
|
"num_tokens": 8784773.0,
|
|
"step": 5060
|
|
},
|
|
{
|
|
"entropy": 5.751138544082641,
|
|
"epoch": 0.39408675354989303,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004988732171211048,
|
|
"loss": 5.655,
|
|
"mean_token_accuracy": 0.15452175438404084,
|
|
"num_tokens": 8793797.0,
|
|
"step": 5065
|
|
},
|
|
{
|
|
"entropy": 5.625418424606323,
|
|
"epoch": 0.39447578292161056,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004988704451434644,
|
|
"loss": 5.5384,
|
|
"mean_token_accuracy": 0.15230093747377396,
|
|
"num_tokens": 8802366.0,
|
|
"step": 5070
|
|
},
|
|
{
|
|
"entropy": 5.739065170288086,
|
|
"epoch": 0.39486481229332815,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004988676697689465,
|
|
"loss": 5.6729,
|
|
"mean_token_accuracy": 0.15218451768159866,
|
|
"num_tokens": 8810975.0,
|
|
"step": 5075
|
|
},
|
|
{
|
|
"entropy": 5.769051790237427,
|
|
"epoch": 0.39525384166504574,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.000498864890997593,
|
|
"loss": 5.6945,
|
|
"mean_token_accuracy": 0.1473867617547512,
|
|
"num_tokens": 8819137.0,
|
|
"step": 5080
|
|
},
|
|
{
|
|
"entropy": 5.685499238967895,
|
|
"epoch": 0.39564287103676327,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004988621088294461,
|
|
"loss": 5.6939,
|
|
"mean_token_accuracy": 0.1510564461350441,
|
|
"num_tokens": 8827676.0,
|
|
"step": 5085
|
|
},
|
|
{
|
|
"entropy": 5.709568500518799,
|
|
"epoch": 0.39603190040848085,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.000498859323264548,
|
|
"loss": 5.6426,
|
|
"mean_token_accuracy": 0.15703052133321763,
|
|
"num_tokens": 8836005.0,
|
|
"step": 5090
|
|
},
|
|
{
|
|
"entropy": 5.636990165710449,
|
|
"epoch": 0.3964209297801984,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.000498856534302941,
|
|
"loss": 5.5295,
|
|
"mean_token_accuracy": 0.1587708003818989,
|
|
"num_tokens": 8844153.0,
|
|
"step": 5095
|
|
},
|
|
{
|
|
"entropy": 5.71082124710083,
|
|
"epoch": 0.39680995915191597,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004988537419446673,
|
|
"loss": 5.644,
|
|
"mean_token_accuracy": 0.153173828125,
|
|
"num_tokens": 8852520.0,
|
|
"step": 5100
|
|
},
|
|
{
|
|
"entropy": 5.714675331115723,
|
|
"epoch": 0.39719898852363356,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004988509461897694,
|
|
"loss": 5.4872,
|
|
"mean_token_accuracy": 0.1576193779706955,
|
|
"num_tokens": 8860609.0,
|
|
"step": 5105
|
|
},
|
|
{
|
|
"entropy": 5.648047876358032,
|
|
"epoch": 0.3975880178953511,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004988481470382897,
|
|
"loss": 5.6664,
|
|
"mean_token_accuracy": 0.1524683952331543,
|
|
"num_tokens": 8869185.0,
|
|
"step": 5110
|
|
},
|
|
{
|
|
"entropy": 5.684601879119873,
|
|
"epoch": 0.3979770472670687,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004988453444902708,
|
|
"loss": 5.537,
|
|
"mean_token_accuracy": 0.152810937166214,
|
|
"num_tokens": 8877758.0,
|
|
"step": 5115
|
|
},
|
|
{
|
|
"entropy": 5.723855924606323,
|
|
"epoch": 0.3983660766387862,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004988425385457549,
|
|
"loss": 5.7168,
|
|
"mean_token_accuracy": 0.15099436789751053,
|
|
"num_tokens": 8887236.0,
|
|
"step": 5120
|
|
},
|
|
{
|
|
"entropy": 5.716874504089356,
|
|
"epoch": 0.3987551060105038,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004988397292047848,
|
|
"loss": 5.6896,
|
|
"mean_token_accuracy": 0.15267200022935867,
|
|
"num_tokens": 8895808.0,
|
|
"step": 5125
|
|
},
|
|
{
|
|
"entropy": 5.7161201477050785,
|
|
"epoch": 0.3991441353822214,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004988369164674032,
|
|
"loss": 5.6626,
|
|
"mean_token_accuracy": 0.1510595954954624,
|
|
"num_tokens": 8904091.0,
|
|
"step": 5130
|
|
},
|
|
{
|
|
"entropy": 5.5925610065460205,
|
|
"epoch": 0.3995331647539389,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004988341003336526,
|
|
"loss": 5.4659,
|
|
"mean_token_accuracy": 0.15727559775114058,
|
|
"num_tokens": 8912046.0,
|
|
"step": 5135
|
|
},
|
|
{
|
|
"entropy": 5.770779085159302,
|
|
"epoch": 0.3999221941256565,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004988312808035757,
|
|
"loss": 5.681,
|
|
"mean_token_accuracy": 0.14915614053606988,
|
|
"num_tokens": 8921060.0,
|
|
"step": 5140
|
|
},
|
|
{
|
|
"entropy": 5.727402973175049,
|
|
"epoch": 0.400311223497374,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004988284578772155,
|
|
"loss": 5.629,
|
|
"mean_token_accuracy": 0.15255586802959442,
|
|
"num_tokens": 8930757.0,
|
|
"step": 5145
|
|
},
|
|
{
|
|
"entropy": 5.825820398330689,
|
|
"epoch": 0.4007002528690916,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004988256315546146,
|
|
"loss": 5.7951,
|
|
"mean_token_accuracy": 0.15042151659727096,
|
|
"num_tokens": 8939544.0,
|
|
"step": 5150
|
|
},
|
|
{
|
|
"entropy": 5.696900844573975,
|
|
"epoch": 0.4010892822408092,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004988228018358161,
|
|
"loss": 5.6018,
|
|
"mean_token_accuracy": 0.15607771426439285,
|
|
"num_tokens": 8949347.0,
|
|
"step": 5155
|
|
},
|
|
{
|
|
"entropy": 5.725059270858765,
|
|
"epoch": 0.40147831161252673,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004988199687208628,
|
|
"loss": 5.6584,
|
|
"mean_token_accuracy": 0.15238844454288483,
|
|
"num_tokens": 8957697.0,
|
|
"step": 5160
|
|
},
|
|
{
|
|
"entropy": 5.740241527557373,
|
|
"epoch": 0.4018673409842443,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004988171322097977,
|
|
"loss": 5.6755,
|
|
"mean_token_accuracy": 0.14611184522509574,
|
|
"num_tokens": 8966107.0,
|
|
"step": 5165
|
|
},
|
|
{
|
|
"entropy": 5.675651693344117,
|
|
"epoch": 0.4022563703559619,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004988142923026638,
|
|
"loss": 5.5825,
|
|
"mean_token_accuracy": 0.15178962647914887,
|
|
"num_tokens": 8974128.0,
|
|
"step": 5170
|
|
},
|
|
{
|
|
"entropy": 5.6408562660217285,
|
|
"epoch": 0.40264539972767943,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004988114489995044,
|
|
"loss": 5.5668,
|
|
"mean_token_accuracy": 0.15450093746185303,
|
|
"num_tokens": 8982564.0,
|
|
"step": 5175
|
|
},
|
|
{
|
|
"entropy": 5.664896154403687,
|
|
"epoch": 0.403034429099397,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004988086023003624,
|
|
"loss": 5.6069,
|
|
"mean_token_accuracy": 0.1550554156303406,
|
|
"num_tokens": 8990924.0,
|
|
"step": 5180
|
|
},
|
|
{
|
|
"entropy": 5.820183563232422,
|
|
"epoch": 0.40342345847111455,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004988057522052811,
|
|
"loss": 5.698,
|
|
"mean_token_accuracy": 0.14887791126966476,
|
|
"num_tokens": 8999827.0,
|
|
"step": 5185
|
|
},
|
|
{
|
|
"entropy": 5.7121435642242435,
|
|
"epoch": 0.40381248784283214,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004988028987143037,
|
|
"loss": 5.5321,
|
|
"mean_token_accuracy": 0.1553960233926773,
|
|
"num_tokens": 9007885.0,
|
|
"step": 5190
|
|
},
|
|
{
|
|
"entropy": 5.6945513725280765,
|
|
"epoch": 0.4042015172145497,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004988000418274736,
|
|
"loss": 5.6351,
|
|
"mean_token_accuracy": 0.15085338950157165,
|
|
"num_tokens": 9016752.0,
|
|
"step": 5195
|
|
},
|
|
{
|
|
"entropy": 5.713669633865356,
|
|
"epoch": 0.40459054658626725,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004987971815448341,
|
|
"loss": 5.6434,
|
|
"mean_token_accuracy": 0.15495601445436477,
|
|
"num_tokens": 9025547.0,
|
|
"step": 5200
|
|
},
|
|
{
|
|
"entropy": 5.741844606399536,
|
|
"epoch": 0.40497957595798484,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004987943178664285,
|
|
"loss": 5.6778,
|
|
"mean_token_accuracy": 0.15183082818984986,
|
|
"num_tokens": 9034711.0,
|
|
"step": 5205
|
|
},
|
|
{
|
|
"entropy": 5.718159914016724,
|
|
"epoch": 0.40536860532970237,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004987914507923004,
|
|
"loss": 5.59,
|
|
"mean_token_accuracy": 0.15771124362945557,
|
|
"num_tokens": 9042565.0,
|
|
"step": 5210
|
|
},
|
|
{
|
|
"entropy": 5.592754888534546,
|
|
"epoch": 0.40575763470141996,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004987885803224931,
|
|
"loss": 5.6583,
|
|
"mean_token_accuracy": 0.14471440464258195,
|
|
"num_tokens": 9051590.0,
|
|
"step": 5215
|
|
},
|
|
{
|
|
"entropy": 5.819624614715576,
|
|
"epoch": 0.40614666407313754,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004987857064570505,
|
|
"loss": 5.7309,
|
|
"mean_token_accuracy": 0.15148103088140488,
|
|
"num_tokens": 9060415.0,
|
|
"step": 5220
|
|
},
|
|
{
|
|
"entropy": 5.640044164657593,
|
|
"epoch": 0.4065356934448551,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004987828291960158,
|
|
"loss": 5.516,
|
|
"mean_token_accuracy": 0.15662309378385544,
|
|
"num_tokens": 9069492.0,
|
|
"step": 5225
|
|
},
|
|
{
|
|
"entropy": 5.608748483657837,
|
|
"epoch": 0.40692472281657266,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000498779948539433,
|
|
"loss": 5.5735,
|
|
"mean_token_accuracy": 0.16103582680225373,
|
|
"num_tokens": 9078183.0,
|
|
"step": 5230
|
|
},
|
|
{
|
|
"entropy": 5.808728265762329,
|
|
"epoch": 0.4073137521882902,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004987770644873455,
|
|
"loss": 5.7835,
|
|
"mean_token_accuracy": 0.14806534647941588,
|
|
"num_tokens": 9086661.0,
|
|
"step": 5235
|
|
},
|
|
{
|
|
"entropy": 5.690426826477051,
|
|
"epoch": 0.4077027815600078,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004987741770397974,
|
|
"loss": 5.5175,
|
|
"mean_token_accuracy": 0.1621639087796211,
|
|
"num_tokens": 9095449.0,
|
|
"step": 5240
|
|
},
|
|
{
|
|
"entropy": 5.665590906143189,
|
|
"epoch": 0.40809181093172536,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004987712861968323,
|
|
"loss": 5.6577,
|
|
"mean_token_accuracy": 0.15061125010252,
|
|
"num_tokens": 9103347.0,
|
|
"step": 5245
|
|
},
|
|
{
|
|
"entropy": 5.572380304336548,
|
|
"epoch": 0.4084808403034429,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000498768391958494,
|
|
"loss": 5.5632,
|
|
"mean_token_accuracy": 0.1605206623673439,
|
|
"num_tokens": 9112382.0,
|
|
"step": 5250
|
|
},
|
|
{
|
|
"entropy": 5.73834261894226,
|
|
"epoch": 0.4088698696751605,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004987654943248266,
|
|
"loss": 5.5031,
|
|
"mean_token_accuracy": 0.15901872366666794,
|
|
"num_tokens": 9120628.0,
|
|
"step": 5255
|
|
},
|
|
{
|
|
"entropy": 5.75648136138916,
|
|
"epoch": 0.40925889904687807,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004987625932958739,
|
|
"loss": 5.6933,
|
|
"mean_token_accuracy": 0.15073462724685668,
|
|
"num_tokens": 9130280.0,
|
|
"step": 5260
|
|
},
|
|
{
|
|
"entropy": 5.856960916519165,
|
|
"epoch": 0.4096479284185956,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004987596888716801,
|
|
"loss": 5.7914,
|
|
"mean_token_accuracy": 0.1458967387676239,
|
|
"num_tokens": 9139720.0,
|
|
"step": 5265
|
|
},
|
|
{
|
|
"entropy": 5.688859844207764,
|
|
"epoch": 0.4100369577903132,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004987567810522892,
|
|
"loss": 5.7051,
|
|
"mean_token_accuracy": 0.149783219397068,
|
|
"num_tokens": 9148537.0,
|
|
"step": 5270
|
|
},
|
|
{
|
|
"entropy": 5.752209806442261,
|
|
"epoch": 0.4104259871620307,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004987538698377451,
|
|
"loss": 5.7694,
|
|
"mean_token_accuracy": 0.15261628925800325,
|
|
"num_tokens": 9156965.0,
|
|
"step": 5275
|
|
},
|
|
{
|
|
"entropy": 5.672241067886352,
|
|
"epoch": 0.4108150165337483,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004987509552280924,
|
|
"loss": 5.4953,
|
|
"mean_token_accuracy": 0.1591440185904503,
|
|
"num_tokens": 9164982.0,
|
|
"step": 5280
|
|
},
|
|
{
|
|
"entropy": 5.738524103164673,
|
|
"epoch": 0.4112040459054659,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.000498748037223375,
|
|
"loss": 5.7207,
|
|
"mean_token_accuracy": 0.14531775191426277,
|
|
"num_tokens": 9173383.0,
|
|
"step": 5285
|
|
},
|
|
{
|
|
"entropy": 5.788292264938354,
|
|
"epoch": 0.4115930752771834,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004987451158236372,
|
|
"loss": 5.7358,
|
|
"mean_token_accuracy": 0.15552923828363419,
|
|
"num_tokens": 9182743.0,
|
|
"step": 5290
|
|
},
|
|
{
|
|
"entropy": 5.747622489929199,
|
|
"epoch": 0.411982104648901,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004987421910289234,
|
|
"loss": 5.6239,
|
|
"mean_token_accuracy": 0.15142476558685303,
|
|
"num_tokens": 9191770.0,
|
|
"step": 5295
|
|
},
|
|
{
|
|
"entropy": 5.5697931289672855,
|
|
"epoch": 0.41237113402061853,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004987392628392781,
|
|
"loss": 5.5785,
|
|
"mean_token_accuracy": 0.15786964744329451,
|
|
"num_tokens": 9200885.0,
|
|
"step": 5300
|
|
},
|
|
{
|
|
"entropy": 5.832540702819824,
|
|
"epoch": 0.4127601633923361,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004987363312547456,
|
|
"loss": 5.6686,
|
|
"mean_token_accuracy": 0.1493069648742676,
|
|
"num_tokens": 9210114.0,
|
|
"step": 5305
|
|
},
|
|
{
|
|
"entropy": 5.745130014419556,
|
|
"epoch": 0.4131491927640537,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004987333962753703,
|
|
"loss": 5.6199,
|
|
"mean_token_accuracy": 0.15895049124956132,
|
|
"num_tokens": 9218608.0,
|
|
"step": 5310
|
|
},
|
|
{
|
|
"entropy": 5.698068571090698,
|
|
"epoch": 0.41353822213577124,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004987304579011967,
|
|
"loss": 5.6659,
|
|
"mean_token_accuracy": 0.15064293891191483,
|
|
"num_tokens": 9227737.0,
|
|
"step": 5315
|
|
},
|
|
{
|
|
"entropy": 5.731441307067871,
|
|
"epoch": 0.4139272515074888,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004987275161322697,
|
|
"loss": 5.5737,
|
|
"mean_token_accuracy": 0.15715447142720224,
|
|
"num_tokens": 9236589.0,
|
|
"step": 5320
|
|
},
|
|
{
|
|
"entropy": 5.67019567489624,
|
|
"epoch": 0.41431628087920636,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004987245709686337,
|
|
"loss": 5.6204,
|
|
"mean_token_accuracy": 0.16002295315265655,
|
|
"num_tokens": 9245313.0,
|
|
"step": 5325
|
|
},
|
|
{
|
|
"entropy": 5.662066316604614,
|
|
"epoch": 0.41470531025092394,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004987216224103334,
|
|
"loss": 5.655,
|
|
"mean_token_accuracy": 0.15002036690711976,
|
|
"num_tokens": 9254001.0,
|
|
"step": 5330
|
|
},
|
|
{
|
|
"entropy": 5.80666069984436,
|
|
"epoch": 0.41509433962264153,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004987186704574136,
|
|
"loss": 5.7102,
|
|
"mean_token_accuracy": 0.14658118188381195,
|
|
"num_tokens": 9262485.0,
|
|
"step": 5335
|
|
},
|
|
{
|
|
"entropy": 5.689135217666626,
|
|
"epoch": 0.41548336899435906,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004987157151099189,
|
|
"loss": 5.5907,
|
|
"mean_token_accuracy": 0.1536131516098976,
|
|
"num_tokens": 9271490.0,
|
|
"step": 5340
|
|
},
|
|
{
|
|
"entropy": 5.625450229644775,
|
|
"epoch": 0.41587239836607665,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004987127563678945,
|
|
"loss": 5.6282,
|
|
"mean_token_accuracy": 0.15292252898216246,
|
|
"num_tokens": 9280595.0,
|
|
"step": 5345
|
|
},
|
|
{
|
|
"entropy": 5.719094228744507,
|
|
"epoch": 0.4162614277377942,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004987097942313852,
|
|
"loss": 5.5414,
|
|
"mean_token_accuracy": 0.1592733532190323,
|
|
"num_tokens": 9289260.0,
|
|
"step": 5350
|
|
},
|
|
{
|
|
"entropy": 5.755507230758667,
|
|
"epoch": 0.41665045710951176,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004987068287004355,
|
|
"loss": 5.7281,
|
|
"mean_token_accuracy": 0.15436695963144303,
|
|
"num_tokens": 9297842.0,
|
|
"step": 5355
|
|
},
|
|
{
|
|
"entropy": 5.752491664886475,
|
|
"epoch": 0.41703948648122935,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004987038597750909,
|
|
"loss": 5.7035,
|
|
"mean_token_accuracy": 0.1510893762111664,
|
|
"num_tokens": 9306533.0,
|
|
"step": 5360
|
|
},
|
|
{
|
|
"entropy": 5.7559339046478275,
|
|
"epoch": 0.4174285158529469,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004987008874553964,
|
|
"loss": 5.5968,
|
|
"mean_token_accuracy": 0.1522625654935837,
|
|
"num_tokens": 9314534.0,
|
|
"step": 5365
|
|
},
|
|
{
|
|
"entropy": 5.749003839492798,
|
|
"epoch": 0.41781754522466447,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004986979117413969,
|
|
"loss": 5.758,
|
|
"mean_token_accuracy": 0.15595654249191285,
|
|
"num_tokens": 9323179.0,
|
|
"step": 5370
|
|
},
|
|
{
|
|
"entropy": 5.687869930267334,
|
|
"epoch": 0.41820657459638205,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004986949326331376,
|
|
"loss": 5.5471,
|
|
"mean_token_accuracy": 0.16193525791168212,
|
|
"num_tokens": 9331265.0,
|
|
"step": 5375
|
|
},
|
|
{
|
|
"entropy": 5.665004444122315,
|
|
"epoch": 0.4185956039680996,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004986919501306638,
|
|
"loss": 5.6089,
|
|
"mean_token_accuracy": 0.15000245124101638,
|
|
"num_tokens": 9340856.0,
|
|
"step": 5380
|
|
},
|
|
{
|
|
"entropy": 5.683504724502564,
|
|
"epoch": 0.41898463333981717,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004986889642340207,
|
|
"loss": 5.6271,
|
|
"mean_token_accuracy": 0.15085209980607034,
|
|
"num_tokens": 9350728.0,
|
|
"step": 5385
|
|
},
|
|
{
|
|
"entropy": 5.813549613952636,
|
|
"epoch": 0.4193736627115347,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004986859749432536,
|
|
"loss": 5.7624,
|
|
"mean_token_accuracy": 0.14495969265699388,
|
|
"num_tokens": 9360109.0,
|
|
"step": 5390
|
|
},
|
|
{
|
|
"entropy": 5.783225584030151,
|
|
"epoch": 0.4197626920832523,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004986829822584078,
|
|
"loss": 5.7253,
|
|
"mean_token_accuracy": 0.1517239674925804,
|
|
"num_tokens": 9369101.0,
|
|
"step": 5395
|
|
},
|
|
{
|
|
"entropy": 5.762203168869019,
|
|
"epoch": 0.4201517214549699,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004986799861795289,
|
|
"loss": 5.6917,
|
|
"mean_token_accuracy": 0.14891715198755265,
|
|
"num_tokens": 9377686.0,
|
|
"step": 5400
|
|
},
|
|
{
|
|
"entropy": 5.774033546447754,
|
|
"epoch": 0.4205407508266874,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004986769867066622,
|
|
"loss": 5.683,
|
|
"mean_token_accuracy": 0.1555148705840111,
|
|
"num_tokens": 9386439.0,
|
|
"step": 5405
|
|
},
|
|
{
|
|
"entropy": 5.68793888092041,
|
|
"epoch": 0.420929780198405,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004986739838398532,
|
|
"loss": 5.717,
|
|
"mean_token_accuracy": 0.15431362837553025,
|
|
"num_tokens": 9395086.0,
|
|
"step": 5410
|
|
},
|
|
{
|
|
"entropy": 5.714366340637207,
|
|
"epoch": 0.4213188095701225,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004986709775791475,
|
|
"loss": 5.5778,
|
|
"mean_token_accuracy": 0.15415338277816773,
|
|
"num_tokens": 9403762.0,
|
|
"step": 5415
|
|
},
|
|
{
|
|
"entropy": 5.662868070602417,
|
|
"epoch": 0.4217078389418401,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004986679679245907,
|
|
"loss": 5.6173,
|
|
"mean_token_accuracy": 0.1550531730055809,
|
|
"num_tokens": 9412386.0,
|
|
"step": 5420
|
|
},
|
|
{
|
|
"entropy": 5.671959304809571,
|
|
"epoch": 0.4220968683135577,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004986649548762286,
|
|
"loss": 5.5757,
|
|
"mean_token_accuracy": 0.16350484043359756,
|
|
"num_tokens": 9420538.0,
|
|
"step": 5425
|
|
},
|
|
{
|
|
"entropy": 5.661460494995117,
|
|
"epoch": 0.4224858976852752,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004986619384341066,
|
|
"loss": 5.5702,
|
|
"mean_token_accuracy": 0.15350655913352967,
|
|
"num_tokens": 9429083.0,
|
|
"step": 5430
|
|
},
|
|
{
|
|
"entropy": 5.733646297454834,
|
|
"epoch": 0.4228749270569928,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004986589185982708,
|
|
"loss": 5.6627,
|
|
"mean_token_accuracy": 0.15776549130678177,
|
|
"num_tokens": 9436892.0,
|
|
"step": 5435
|
|
},
|
|
{
|
|
"entropy": 5.726545667648315,
|
|
"epoch": 0.42326395642871034,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004986558953687671,
|
|
"loss": 5.6756,
|
|
"mean_token_accuracy": 0.1516024351119995,
|
|
"num_tokens": 9445267.0,
|
|
"step": 5440
|
|
},
|
|
{
|
|
"entropy": 5.721020984649658,
|
|
"epoch": 0.42365298580042793,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004986528687456409,
|
|
"loss": 5.685,
|
|
"mean_token_accuracy": 0.15134571343660355,
|
|
"num_tokens": 9454292.0,
|
|
"step": 5445
|
|
},
|
|
{
|
|
"entropy": 5.707912731170654,
|
|
"epoch": 0.4240420151721455,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004986498387289384,
|
|
"loss": 5.5852,
|
|
"mean_token_accuracy": 0.16004859358072282,
|
|
"num_tokens": 9463126.0,
|
|
"step": 5450
|
|
},
|
|
{
|
|
"entropy": 5.679943418502807,
|
|
"epoch": 0.42443104454386305,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004986468053187058,
|
|
"loss": 5.6632,
|
|
"mean_token_accuracy": 0.15489592105150224,
|
|
"num_tokens": 9471703.0,
|
|
"step": 5455
|
|
},
|
|
{
|
|
"entropy": 5.664609098434449,
|
|
"epoch": 0.42482007391558063,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004986437685149887,
|
|
"loss": 5.5365,
|
|
"mean_token_accuracy": 0.1670185387134552,
|
|
"num_tokens": 9480029.0,
|
|
"step": 5460
|
|
},
|
|
{
|
|
"entropy": 5.743315315246582,
|
|
"epoch": 0.4252091032872982,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004986407283178334,
|
|
"loss": 5.6452,
|
|
"mean_token_accuracy": 0.15648874193429946,
|
|
"num_tokens": 9488277.0,
|
|
"step": 5465
|
|
},
|
|
{
|
|
"entropy": 5.725664234161377,
|
|
"epoch": 0.42559813265901575,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004986376847272861,
|
|
"loss": 5.6974,
|
|
"mean_token_accuracy": 0.1544747918844223,
|
|
"num_tokens": 9496096.0,
|
|
"step": 5470
|
|
},
|
|
{
|
|
"entropy": 5.682655239105225,
|
|
"epoch": 0.42598716203073334,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004986346377433929,
|
|
"loss": 5.6116,
|
|
"mean_token_accuracy": 0.16111418157815932,
|
|
"num_tokens": 9504653.0,
|
|
"step": 5475
|
|
},
|
|
{
|
|
"entropy": 5.7783355712890625,
|
|
"epoch": 0.42637619140245087,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004986315873661999,
|
|
"loss": 5.5822,
|
|
"mean_token_accuracy": 0.15282244384288787,
|
|
"num_tokens": 9513088.0,
|
|
"step": 5480
|
|
},
|
|
{
|
|
"entropy": 5.619540166854859,
|
|
"epoch": 0.42676522077416845,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004986285335957536,
|
|
"loss": 5.5013,
|
|
"mean_token_accuracy": 0.15677933245897294,
|
|
"num_tokens": 9521714.0,
|
|
"step": 5485
|
|
},
|
|
{
|
|
"entropy": 5.613918161392212,
|
|
"epoch": 0.42715425014588604,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004986254764321002,
|
|
"loss": 5.6033,
|
|
"mean_token_accuracy": 0.1575162246823311,
|
|
"num_tokens": 9530629.0,
|
|
"step": 5490
|
|
},
|
|
{
|
|
"entropy": 5.701473379135132,
|
|
"epoch": 0.42754327951760357,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004986224158752861,
|
|
"loss": 5.6084,
|
|
"mean_token_accuracy": 0.162319153547287,
|
|
"num_tokens": 9539293.0,
|
|
"step": 5495
|
|
},
|
|
{
|
|
"entropy": 5.623651647567749,
|
|
"epoch": 0.42793230888932116,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004986193519253578,
|
|
"loss": 5.5598,
|
|
"mean_token_accuracy": 0.15547969192266464,
|
|
"num_tokens": 9547628.0,
|
|
"step": 5500
|
|
},
|
|
{
|
|
"entropy": 5.656365871429443,
|
|
"epoch": 0.4283213382610387,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004986162845823618,
|
|
"loss": 5.5529,
|
|
"mean_token_accuracy": 0.16461351811885833,
|
|
"num_tokens": 9557260.0,
|
|
"step": 5505
|
|
},
|
|
{
|
|
"entropy": 5.761644983291626,
|
|
"epoch": 0.4287103676327563,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004986132138463446,
|
|
"loss": 5.5998,
|
|
"mean_token_accuracy": 0.1509658232331276,
|
|
"num_tokens": 9565923.0,
|
|
"step": 5510
|
|
},
|
|
{
|
|
"entropy": 5.653045129776001,
|
|
"epoch": 0.42909939700447386,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004986101397173528,
|
|
"loss": 5.6036,
|
|
"mean_token_accuracy": 0.15777654498815535,
|
|
"num_tokens": 9574373.0,
|
|
"step": 5515
|
|
},
|
|
{
|
|
"entropy": 5.683512020111084,
|
|
"epoch": 0.4294884263761914,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.000498607062195433,
|
|
"loss": 5.6989,
|
|
"mean_token_accuracy": 0.15172723829746246,
|
|
"num_tokens": 9583652.0,
|
|
"step": 5520
|
|
},
|
|
{
|
|
"entropy": 5.723854303359985,
|
|
"epoch": 0.429877455747909,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.000498603981280632,
|
|
"loss": 5.6535,
|
|
"mean_token_accuracy": 0.1534549355506897,
|
|
"num_tokens": 9592625.0,
|
|
"step": 5525
|
|
},
|
|
{
|
|
"entropy": 5.6727447509765625,
|
|
"epoch": 0.4302664851196265,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004986008969729964,
|
|
"loss": 5.5531,
|
|
"mean_token_accuracy": 0.15823169946670532,
|
|
"num_tokens": 9600934.0,
|
|
"step": 5530
|
|
},
|
|
{
|
|
"entropy": 5.625131464004516,
|
|
"epoch": 0.4306555144913441,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004985978092725731,
|
|
"loss": 5.5533,
|
|
"mean_token_accuracy": 0.16186170428991317,
|
|
"num_tokens": 9609481.0,
|
|
"step": 5535
|
|
},
|
|
{
|
|
"entropy": 5.626396179199219,
|
|
"epoch": 0.4310445438630617,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.000498594718179409,
|
|
"loss": 5.525,
|
|
"mean_token_accuracy": 0.16443886905908583,
|
|
"num_tokens": 9618063.0,
|
|
"step": 5540
|
|
},
|
|
{
|
|
"entropy": 5.672539138793946,
|
|
"epoch": 0.4314335732347792,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004985916236935508,
|
|
"loss": 5.6056,
|
|
"mean_token_accuracy": 0.15570127665996553,
|
|
"num_tokens": 9626144.0,
|
|
"step": 5545
|
|
},
|
|
{
|
|
"entropy": 5.569118499755859,
|
|
"epoch": 0.4318226026064968,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004985885258150458,
|
|
"loss": 5.5639,
|
|
"mean_token_accuracy": 0.1569093570113182,
|
|
"num_tokens": 9635328.0,
|
|
"step": 5550
|
|
},
|
|
{
|
|
"entropy": 5.7548158168792725,
|
|
"epoch": 0.43221163197821433,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004985854245439408,
|
|
"loss": 5.7049,
|
|
"mean_token_accuracy": 0.14901985377073287,
|
|
"num_tokens": 9644529.0,
|
|
"step": 5555
|
|
},
|
|
{
|
|
"entropy": 5.743087673187256,
|
|
"epoch": 0.4326006613499319,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004985823198802827,
|
|
"loss": 5.6839,
|
|
"mean_token_accuracy": 0.15375212132930755,
|
|
"num_tokens": 9653763.0,
|
|
"step": 5560
|
|
},
|
|
{
|
|
"entropy": 5.674944353103638,
|
|
"epoch": 0.4329896907216495,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004985792118241188,
|
|
"loss": 5.5095,
|
|
"mean_token_accuracy": 0.1607091173529625,
|
|
"num_tokens": 9661433.0,
|
|
"step": 5565
|
|
},
|
|
{
|
|
"entropy": 5.601434946060181,
|
|
"epoch": 0.43337872009336703,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004985761003754961,
|
|
"loss": 5.5038,
|
|
"mean_token_accuracy": 0.15965722799301146,
|
|
"num_tokens": 9669688.0,
|
|
"step": 5570
|
|
},
|
|
{
|
|
"entropy": 5.7145667552948,
|
|
"epoch": 0.4337677494650846,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004985729855344622,
|
|
"loss": 5.6217,
|
|
"mean_token_accuracy": 0.155311219394207,
|
|
"num_tokens": 9678403.0,
|
|
"step": 5575
|
|
},
|
|
{
|
|
"entropy": 5.7246904373168945,
|
|
"epoch": 0.4341567788368022,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.000498569867301064,
|
|
"loss": 5.7205,
|
|
"mean_token_accuracy": 0.14789665564894677,
|
|
"num_tokens": 9687504.0,
|
|
"step": 5580
|
|
},
|
|
{
|
|
"entropy": 5.7681337833404545,
|
|
"epoch": 0.43454580820851973,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004985667456753489,
|
|
"loss": 5.5273,
|
|
"mean_token_accuracy": 0.1617080509662628,
|
|
"num_tokens": 9695772.0,
|
|
"step": 5585
|
|
},
|
|
{
|
|
"entropy": 5.617122650146484,
|
|
"epoch": 0.4349348375802373,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004985636206573642,
|
|
"loss": 5.5952,
|
|
"mean_token_accuracy": 0.1571861684322357,
|
|
"num_tokens": 9704150.0,
|
|
"step": 5590
|
|
},
|
|
{
|
|
"entropy": 5.557275772094727,
|
|
"epoch": 0.43532386695195485,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004985604922471575,
|
|
"loss": 5.5016,
|
|
"mean_token_accuracy": 0.16332297772169113,
|
|
"num_tokens": 9712245.0,
|
|
"step": 5595
|
|
},
|
|
{
|
|
"entropy": 5.662200260162353,
|
|
"epoch": 0.43571289632367244,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004985573604447761,
|
|
"loss": 5.6432,
|
|
"mean_token_accuracy": 0.1524854212999344,
|
|
"num_tokens": 9721027.0,
|
|
"step": 5600
|
|
},
|
|
{
|
|
"entropy": 5.731251001358032,
|
|
"epoch": 0.43610192569539,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004985542252502676,
|
|
"loss": 5.5657,
|
|
"mean_token_accuracy": 0.1564818188548088,
|
|
"num_tokens": 9728939.0,
|
|
"step": 5605
|
|
},
|
|
{
|
|
"entropy": 5.763981342315674,
|
|
"epoch": 0.43649095506710756,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004985510866636796,
|
|
"loss": 5.7119,
|
|
"mean_token_accuracy": 0.15163636654615403,
|
|
"num_tokens": 9737863.0,
|
|
"step": 5610
|
|
},
|
|
{
|
|
"entropy": 5.688189840316772,
|
|
"epoch": 0.43687998443882514,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004985479446850596,
|
|
"loss": 5.7083,
|
|
"mean_token_accuracy": 0.1486771047115326,
|
|
"num_tokens": 9747666.0,
|
|
"step": 5615
|
|
},
|
|
{
|
|
"entropy": 5.658762121200562,
|
|
"epoch": 0.4372690138105427,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004985447993144554,
|
|
"loss": 5.5646,
|
|
"mean_token_accuracy": 0.1599259227514267,
|
|
"num_tokens": 9756595.0,
|
|
"step": 5620
|
|
},
|
|
{
|
|
"entropy": 5.730542516708374,
|
|
"epoch": 0.43765804318226026,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004985416505519147,
|
|
"loss": 5.5981,
|
|
"mean_token_accuracy": 0.15622531548142432,
|
|
"num_tokens": 9764747.0,
|
|
"step": 5625
|
|
},
|
|
{
|
|
"entropy": 5.640635251998901,
|
|
"epoch": 0.43804707255397785,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004985384983974853,
|
|
"loss": 5.5542,
|
|
"mean_token_accuracy": 0.15800215303897858,
|
|
"num_tokens": 9772992.0,
|
|
"step": 5630
|
|
},
|
|
{
|
|
"entropy": 5.633075332641601,
|
|
"epoch": 0.4384361019256954,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004985353428512148,
|
|
"loss": 5.5335,
|
|
"mean_token_accuracy": 0.1635892003774643,
|
|
"num_tokens": 9781107.0,
|
|
"step": 5635
|
|
},
|
|
{
|
|
"entropy": 5.624766874313354,
|
|
"epoch": 0.43882513129741296,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004985321839131514,
|
|
"loss": 5.6325,
|
|
"mean_token_accuracy": 0.15101755112409593,
|
|
"num_tokens": 9790618.0,
|
|
"step": 5640
|
|
},
|
|
{
|
|
"entropy": 5.734963464736938,
|
|
"epoch": 0.4392141606691305,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004985290215833428,
|
|
"loss": 5.6187,
|
|
"mean_token_accuracy": 0.150974078476429,
|
|
"num_tokens": 9800147.0,
|
|
"step": 5645
|
|
},
|
|
{
|
|
"entropy": 5.785725402832031,
|
|
"epoch": 0.4396031900408481,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004985258558618372,
|
|
"loss": 5.6791,
|
|
"mean_token_accuracy": 0.15372121408581735,
|
|
"num_tokens": 9809056.0,
|
|
"step": 5650
|
|
},
|
|
{
|
|
"entropy": 5.627626085281372,
|
|
"epoch": 0.43999221941256567,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004985226867486825,
|
|
"loss": 5.5326,
|
|
"mean_token_accuracy": 0.15544520765542985,
|
|
"num_tokens": 9817188.0,
|
|
"step": 5655
|
|
},
|
|
{
|
|
"entropy": 5.6710656642913815,
|
|
"epoch": 0.4403812487842832,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004985195142439267,
|
|
"loss": 5.7274,
|
|
"mean_token_accuracy": 0.1486324056982994,
|
|
"num_tokens": 9826904.0,
|
|
"step": 5660
|
|
},
|
|
{
|
|
"entropy": 5.741341066360474,
|
|
"epoch": 0.4407702781560008,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004985163383476181,
|
|
"loss": 5.6834,
|
|
"mean_token_accuracy": 0.1525462031364441,
|
|
"num_tokens": 9835937.0,
|
|
"step": 5665
|
|
},
|
|
{
|
|
"entropy": 5.69437313079834,
|
|
"epoch": 0.44115930752771837,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004985131590598048,
|
|
"loss": 5.5055,
|
|
"mean_token_accuracy": 0.1657673478126526,
|
|
"num_tokens": 9843695.0,
|
|
"step": 5670
|
|
},
|
|
{
|
|
"entropy": 5.693076705932617,
|
|
"epoch": 0.4415483368994359,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004985099763805352,
|
|
"loss": 5.6019,
|
|
"mean_token_accuracy": 0.15521264225244522,
|
|
"num_tokens": 9852693.0,
|
|
"step": 5675
|
|
},
|
|
{
|
|
"entropy": 5.6236875534057615,
|
|
"epoch": 0.4419373662711535,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004985067903098574,
|
|
"loss": 5.6014,
|
|
"mean_token_accuracy": 0.15343275368213655,
|
|
"num_tokens": 9860251.0,
|
|
"step": 5680
|
|
},
|
|
{
|
|
"entropy": 5.5922425270080565,
|
|
"epoch": 0.442326395642871,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004985036008478197,
|
|
"loss": 5.5379,
|
|
"mean_token_accuracy": 0.15147336274385453,
|
|
"num_tokens": 9868319.0,
|
|
"step": 5685
|
|
},
|
|
{
|
|
"entropy": 5.629176235198974,
|
|
"epoch": 0.4427154250145886,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004985004079944707,
|
|
"loss": 5.5678,
|
|
"mean_token_accuracy": 0.15566625073552132,
|
|
"num_tokens": 9877119.0,
|
|
"step": 5690
|
|
},
|
|
{
|
|
"entropy": 5.791639518737793,
|
|
"epoch": 0.4431044543863062,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004984972117498587,
|
|
"loss": 5.6647,
|
|
"mean_token_accuracy": 0.15812490731477738,
|
|
"num_tokens": 9886015.0,
|
|
"step": 5695
|
|
},
|
|
{
|
|
"entropy": 5.674712800979615,
|
|
"epoch": 0.4434934837580237,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004984940121140323,
|
|
"loss": 5.602,
|
|
"mean_token_accuracy": 0.1511713407933712,
|
|
"num_tokens": 9894829.0,
|
|
"step": 5700
|
|
},
|
|
{
|
|
"entropy": 5.8527120590209964,
|
|
"epoch": 0.4438825131297413,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00049849080908704,
|
|
"loss": 5.8629,
|
|
"mean_token_accuracy": 0.1408378891646862,
|
|
"num_tokens": 9904840.0,
|
|
"step": 5705
|
|
},
|
|
{
|
|
"entropy": 5.819258117675782,
|
|
"epoch": 0.44427154250145884,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004984876026689302,
|
|
"loss": 5.6971,
|
|
"mean_token_accuracy": 0.1521285057067871,
|
|
"num_tokens": 9913535.0,
|
|
"step": 5710
|
|
},
|
|
{
|
|
"entropy": 5.7410163402557375,
|
|
"epoch": 0.4446605718731764,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000498484392859752,
|
|
"loss": 5.5853,
|
|
"mean_token_accuracy": 0.1592594563961029,
|
|
"num_tokens": 9921676.0,
|
|
"step": 5715
|
|
},
|
|
{
|
|
"entropy": 5.634752941131592,
|
|
"epoch": 0.445049601244894,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004984811796595538,
|
|
"loss": 5.6579,
|
|
"mean_token_accuracy": 0.1542586490511894,
|
|
"num_tokens": 9930321.0,
|
|
"step": 5720
|
|
},
|
|
{
|
|
"entropy": 5.693371438980103,
|
|
"epoch": 0.44543863061661154,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004984779630683843,
|
|
"loss": 5.5919,
|
|
"mean_token_accuracy": 0.15253776609897612,
|
|
"num_tokens": 9939324.0,
|
|
"step": 5725
|
|
},
|
|
{
|
|
"entropy": 5.716857051849365,
|
|
"epoch": 0.44582765998832913,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004984747430862924,
|
|
"loss": 5.6196,
|
|
"mean_token_accuracy": 0.16022590100765227,
|
|
"num_tokens": 9948603.0,
|
|
"step": 5730
|
|
},
|
|
{
|
|
"entropy": 5.600257349014282,
|
|
"epoch": 0.44621668936004666,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004984715197133271,
|
|
"loss": 5.5224,
|
|
"mean_token_accuracy": 0.1616570070385933,
|
|
"num_tokens": 9957165.0,
|
|
"step": 5735
|
|
},
|
|
{
|
|
"entropy": 5.739328241348266,
|
|
"epoch": 0.44660571873176425,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004984682929495371,
|
|
"loss": 5.6943,
|
|
"mean_token_accuracy": 0.14594707265496254,
|
|
"num_tokens": 9966064.0,
|
|
"step": 5740
|
|
},
|
|
{
|
|
"entropy": 5.640423107147217,
|
|
"epoch": 0.44699474810348183,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004984650627949715,
|
|
"loss": 5.5367,
|
|
"mean_token_accuracy": 0.15209029316902162,
|
|
"num_tokens": 9975146.0,
|
|
"step": 5745
|
|
},
|
|
{
|
|
"entropy": 5.680380773544312,
|
|
"epoch": 0.44738377747519936,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004984618292496792,
|
|
"loss": 5.6202,
|
|
"mean_token_accuracy": 0.15602054297924042,
|
|
"num_tokens": 9983725.0,
|
|
"step": 5750
|
|
},
|
|
{
|
|
"entropy": 5.733370542526245,
|
|
"epoch": 0.44777280684691695,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004984585923137093,
|
|
"loss": 5.6747,
|
|
"mean_token_accuracy": 0.15484231412410737,
|
|
"num_tokens": 9992627.0,
|
|
"step": 5755
|
|
},
|
|
{
|
|
"entropy": 5.630478382110596,
|
|
"epoch": 0.4481618362186345,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.000498455351987111,
|
|
"loss": 5.4979,
|
|
"mean_token_accuracy": 0.15697283297777176,
|
|
"num_tokens": 10000801.0,
|
|
"step": 5760
|
|
},
|
|
{
|
|
"entropy": 5.698464012145996,
|
|
"epoch": 0.44855086559035207,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004984521082699333,
|
|
"loss": 5.6096,
|
|
"mean_token_accuracy": 0.160343961417675,
|
|
"num_tokens": 10009421.0,
|
|
"step": 5765
|
|
},
|
|
{
|
|
"entropy": 5.667017126083374,
|
|
"epoch": 0.44893989496206965,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004984488611622256,
|
|
"loss": 5.6474,
|
|
"mean_token_accuracy": 0.15203245729207993,
|
|
"num_tokens": 10018527.0,
|
|
"step": 5770
|
|
},
|
|
{
|
|
"entropy": 5.714696216583252,
|
|
"epoch": 0.4493289243337872,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000498445610664037,
|
|
"loss": 5.5737,
|
|
"mean_token_accuracy": 0.16014605462551118,
|
|
"num_tokens": 10026906.0,
|
|
"step": 5775
|
|
},
|
|
{
|
|
"entropy": 5.624043941497803,
|
|
"epoch": 0.44971795370550477,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000498442356775417,
|
|
"loss": 5.5475,
|
|
"mean_token_accuracy": 0.1580877646803856,
|
|
"num_tokens": 10035972.0,
|
|
"step": 5780
|
|
},
|
|
{
|
|
"entropy": 5.652503919601441,
|
|
"epoch": 0.45010698307722236,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004984390994964148,
|
|
"loss": 5.6497,
|
|
"mean_token_accuracy": 0.14800439924001693,
|
|
"num_tokens": 10044544.0,
|
|
"step": 5785
|
|
},
|
|
{
|
|
"entropy": 5.768403387069702,
|
|
"epoch": 0.4504960124489399,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00049843583882708,
|
|
"loss": 5.6335,
|
|
"mean_token_accuracy": 0.15916564911603928,
|
|
"num_tokens": 10052880.0,
|
|
"step": 5790
|
|
},
|
|
{
|
|
"entropy": 5.7311272621154785,
|
|
"epoch": 0.4508850418206575,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.000498432574767462,
|
|
"loss": 5.6963,
|
|
"mean_token_accuracy": 0.14732673913240432,
|
|
"num_tokens": 10062373.0,
|
|
"step": 5795
|
|
},
|
|
{
|
|
"entropy": 5.6710062503814695,
|
|
"epoch": 0.451274071192375,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004984293073176103,
|
|
"loss": 5.5125,
|
|
"mean_token_accuracy": 0.16145335882902145,
|
|
"num_tokens": 10070473.0,
|
|
"step": 5800
|
|
},
|
|
{
|
|
"entropy": 5.725533723831177,
|
|
"epoch": 0.4516631005640926,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004984260364775744,
|
|
"loss": 5.6547,
|
|
"mean_token_accuracy": 0.15550251305103302,
|
|
"num_tokens": 10079857.0,
|
|
"step": 5805
|
|
},
|
|
{
|
|
"entropy": 5.70276026725769,
|
|
"epoch": 0.4520521299358102,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.000498422762247404,
|
|
"loss": 5.6039,
|
|
"mean_token_accuracy": 0.1518784373998642,
|
|
"num_tokens": 10088326.0,
|
|
"step": 5810
|
|
},
|
|
{
|
|
"entropy": 5.675834608078003,
|
|
"epoch": 0.4524411593075277,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004984194846271489,
|
|
"loss": 5.5466,
|
|
"mean_token_accuracy": 0.15411396324634552,
|
|
"num_tokens": 10097208.0,
|
|
"step": 5815
|
|
},
|
|
{
|
|
"entropy": 5.686789417266846,
|
|
"epoch": 0.4528301886792453,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004984162036168586,
|
|
"loss": 5.6393,
|
|
"mean_token_accuracy": 0.14983187168836593,
|
|
"num_tokens": 10106057.0,
|
|
"step": 5820
|
|
},
|
|
{
|
|
"entropy": 5.659746503829956,
|
|
"epoch": 0.4532192180509628,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004984129192165831,
|
|
"loss": 5.5515,
|
|
"mean_token_accuracy": 0.1533331200480461,
|
|
"num_tokens": 10115384.0,
|
|
"step": 5825
|
|
},
|
|
{
|
|
"entropy": 5.728514289855957,
|
|
"epoch": 0.4536082474226804,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004984096314263722,
|
|
"loss": 5.6365,
|
|
"mean_token_accuracy": 0.14838182777166367,
|
|
"num_tokens": 10123958.0,
|
|
"step": 5830
|
|
},
|
|
{
|
|
"entropy": 5.685654067993164,
|
|
"epoch": 0.453997276794398,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004984063402462757,
|
|
"loss": 5.5811,
|
|
"mean_token_accuracy": 0.16384691447019578,
|
|
"num_tokens": 10133199.0,
|
|
"step": 5835
|
|
},
|
|
{
|
|
"entropy": 5.608744812011719,
|
|
"epoch": 0.45438630616611553,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004984030456763435,
|
|
"loss": 5.5209,
|
|
"mean_token_accuracy": 0.16693407595157622,
|
|
"num_tokens": 10141796.0,
|
|
"step": 5840
|
|
},
|
|
{
|
|
"entropy": 5.632417869567871,
|
|
"epoch": 0.4547753355378331,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004983997477166257,
|
|
"loss": 5.5498,
|
|
"mean_token_accuracy": 0.16132254749536515,
|
|
"num_tokens": 10149941.0,
|
|
"step": 5845
|
|
},
|
|
{
|
|
"entropy": 5.706463146209717,
|
|
"epoch": 0.45516436490955064,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004983964463671723,
|
|
"loss": 5.6488,
|
|
"mean_token_accuracy": 0.15120118111371994,
|
|
"num_tokens": 10158796.0,
|
|
"step": 5850
|
|
},
|
|
{
|
|
"entropy": 5.7029928207397464,
|
|
"epoch": 0.45555339428126823,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004983931416280334,
|
|
"loss": 5.5775,
|
|
"mean_token_accuracy": 0.1588720500469208,
|
|
"num_tokens": 10167328.0,
|
|
"step": 5855
|
|
},
|
|
{
|
|
"entropy": 5.687714672088623,
|
|
"epoch": 0.4559424236529858,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004983898334992591,
|
|
"loss": 5.6381,
|
|
"mean_token_accuracy": 0.1526034250855446,
|
|
"num_tokens": 10175937.0,
|
|
"step": 5860
|
|
},
|
|
{
|
|
"entropy": 5.681948041915893,
|
|
"epoch": 0.45633145302470335,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004983865219808998,
|
|
"loss": 5.5921,
|
|
"mean_token_accuracy": 0.14964849948883058,
|
|
"num_tokens": 10184828.0,
|
|
"step": 5865
|
|
},
|
|
{
|
|
"entropy": 5.637333917617798,
|
|
"epoch": 0.45672048239642093,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004983832070730055,
|
|
"loss": 5.5963,
|
|
"mean_token_accuracy": 0.1577572539448738,
|
|
"num_tokens": 10193871.0,
|
|
"step": 5870
|
|
},
|
|
{
|
|
"entropy": 5.634118127822876,
|
|
"epoch": 0.4571095117681385,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004983798887756265,
|
|
"loss": 5.6008,
|
|
"mean_token_accuracy": 0.15409007370471955,
|
|
"num_tokens": 10202740.0,
|
|
"step": 5875
|
|
},
|
|
{
|
|
"entropy": 5.706058931350708,
|
|
"epoch": 0.45749854113985605,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004983765670888133,
|
|
"loss": 5.5434,
|
|
"mean_token_accuracy": 0.1615920588374138,
|
|
"num_tokens": 10210903.0,
|
|
"step": 5880
|
|
},
|
|
{
|
|
"entropy": 5.608094549179077,
|
|
"epoch": 0.45788757051157364,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004983732420126163,
|
|
"loss": 5.4997,
|
|
"mean_token_accuracy": 0.16220609247684478,
|
|
"num_tokens": 10219305.0,
|
|
"step": 5885
|
|
},
|
|
{
|
|
"entropy": 5.657922029495239,
|
|
"epoch": 0.45827659988329117,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004983699135470858,
|
|
"loss": 5.6679,
|
|
"mean_token_accuracy": 0.14259497374296187,
|
|
"num_tokens": 10228575.0,
|
|
"step": 5890
|
|
},
|
|
{
|
|
"entropy": 5.6840509414672855,
|
|
"epoch": 0.45866562925500876,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004983665816922723,
|
|
"loss": 5.6437,
|
|
"mean_token_accuracy": 0.15515442043542862,
|
|
"num_tokens": 10237813.0,
|
|
"step": 5895
|
|
},
|
|
{
|
|
"entropy": 5.765459394454956,
|
|
"epoch": 0.45905465862672634,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004983632464482267,
|
|
"loss": 5.639,
|
|
"mean_token_accuracy": 0.151662015914917,
|
|
"num_tokens": 10246606.0,
|
|
"step": 5900
|
|
},
|
|
{
|
|
"entropy": 5.665762281417846,
|
|
"epoch": 0.4594436879984439,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004983599078149991,
|
|
"loss": 5.5937,
|
|
"mean_token_accuracy": 0.1628975346684456,
|
|
"num_tokens": 10254996.0,
|
|
"step": 5905
|
|
},
|
|
{
|
|
"entropy": 5.648976230621338,
|
|
"epoch": 0.45983271737016146,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004983565657926405,
|
|
"loss": 5.6435,
|
|
"mean_token_accuracy": 0.15243904292583466,
|
|
"num_tokens": 10263570.0,
|
|
"step": 5910
|
|
},
|
|
{
|
|
"entropy": 5.629678344726562,
|
|
"epoch": 0.460221746741879,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004983532203812017,
|
|
"loss": 5.4759,
|
|
"mean_token_accuracy": 0.16085339486598968,
|
|
"num_tokens": 10272237.0,
|
|
"step": 5915
|
|
},
|
|
{
|
|
"entropy": 5.653153705596924,
|
|
"epoch": 0.4606107761135966,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004983498715807331,
|
|
"loss": 5.6017,
|
|
"mean_token_accuracy": 0.15792696475982665,
|
|
"num_tokens": 10281215.0,
|
|
"step": 5920
|
|
},
|
|
{
|
|
"entropy": 5.727438068389892,
|
|
"epoch": 0.46099980548531416,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004983465193912857,
|
|
"loss": 5.6669,
|
|
"mean_token_accuracy": 0.15387242883443833,
|
|
"num_tokens": 10291054.0,
|
|
"step": 5925
|
|
},
|
|
{
|
|
"entropy": 5.810876703262329,
|
|
"epoch": 0.4613888348570317,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004983431638129104,
|
|
"loss": 5.6472,
|
|
"mean_token_accuracy": 0.1563032776117325,
|
|
"num_tokens": 10299847.0,
|
|
"step": 5930
|
|
},
|
|
{
|
|
"entropy": 5.660638475418091,
|
|
"epoch": 0.4617778642287493,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004983398048456581,
|
|
"loss": 5.5824,
|
|
"mean_token_accuracy": 0.15701979771256447,
|
|
"num_tokens": 10309195.0,
|
|
"step": 5935
|
|
},
|
|
{
|
|
"entropy": 5.640789127349853,
|
|
"epoch": 0.4621668936004668,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004983364424895796,
|
|
"loss": 5.6019,
|
|
"mean_token_accuracy": 0.15272444784641265,
|
|
"num_tokens": 10318386.0,
|
|
"step": 5940
|
|
},
|
|
{
|
|
"entropy": 5.626794528961182,
|
|
"epoch": 0.4625559229721844,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004983330767447262,
|
|
"loss": 5.5244,
|
|
"mean_token_accuracy": 0.1628873825073242,
|
|
"num_tokens": 10327230.0,
|
|
"step": 5945
|
|
},
|
|
{
|
|
"entropy": 5.629368782043457,
|
|
"epoch": 0.462944952343902,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004983297076111489,
|
|
"loss": 5.5165,
|
|
"mean_token_accuracy": 0.15757380425930023,
|
|
"num_tokens": 10335617.0,
|
|
"step": 5950
|
|
},
|
|
{
|
|
"entropy": 5.661604261398315,
|
|
"epoch": 0.4633339817156195,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004983263350888987,
|
|
"loss": 5.5725,
|
|
"mean_token_accuracy": 0.15994318276643754,
|
|
"num_tokens": 10344302.0,
|
|
"step": 5955
|
|
},
|
|
{
|
|
"entropy": 5.681477737426758,
|
|
"epoch": 0.4637230110873371,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004983229591780268,
|
|
"loss": 5.6433,
|
|
"mean_token_accuracy": 0.1517888329923153,
|
|
"num_tokens": 10352490.0,
|
|
"step": 5960
|
|
},
|
|
{
|
|
"entropy": 5.655088281631469,
|
|
"epoch": 0.46411204045905463,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004983195798785844,
|
|
"loss": 5.5766,
|
|
"mean_token_accuracy": 0.16044610887765884,
|
|
"num_tokens": 10361249.0,
|
|
"step": 5965
|
|
},
|
|
{
|
|
"entropy": 5.74783935546875,
|
|
"epoch": 0.4645010698307722,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004983161971906228,
|
|
"loss": 5.6829,
|
|
"mean_token_accuracy": 0.14617585390806198,
|
|
"num_tokens": 10370367.0,
|
|
"step": 5970
|
|
},
|
|
{
|
|
"entropy": 5.724832582473755,
|
|
"epoch": 0.4648900992024898,
|
|
"grad_norm": 2.53125,
|
|
"learning_rate": 0.0004983128111141935,
|
|
"loss": 5.6284,
|
|
"mean_token_accuracy": 0.14997454285621642,
|
|
"num_tokens": 10378429.0,
|
|
"step": 5975
|
|
},
|
|
{
|
|
"entropy": 5.623139333724976,
|
|
"epoch": 0.46527912857420733,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004983094216493475,
|
|
"loss": 5.5512,
|
|
"mean_token_accuracy": 0.15990946292877198,
|
|
"num_tokens": 10386762.0,
|
|
"step": 5980
|
|
},
|
|
{
|
|
"entropy": 5.657111024856567,
|
|
"epoch": 0.4656681579459249,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004983060287961367,
|
|
"loss": 5.5573,
|
|
"mean_token_accuracy": 0.15611529648303984,
|
|
"num_tokens": 10395150.0,
|
|
"step": 5985
|
|
},
|
|
{
|
|
"entropy": 5.686012268066406,
|
|
"epoch": 0.4660571873176425,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004983026325546123,
|
|
"loss": 5.6061,
|
|
"mean_token_accuracy": 0.1571057692170143,
|
|
"num_tokens": 10403941.0,
|
|
"step": 5990
|
|
},
|
|
{
|
|
"entropy": 5.790388917922973,
|
|
"epoch": 0.46644621668936004,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004982992329248257,
|
|
"loss": 5.6699,
|
|
"mean_token_accuracy": 0.14361992180347444,
|
|
"num_tokens": 10413955.0,
|
|
"step": 5995
|
|
},
|
|
{
|
|
"entropy": 5.740258312225341,
|
|
"epoch": 0.4668352460610776,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004982958299068289,
|
|
"loss": 5.576,
|
|
"mean_token_accuracy": 0.15433995723724364,
|
|
"num_tokens": 10421676.0,
|
|
"step": 6000
|
|
},
|
|
{
|
|
"epoch": 0.4668352460610776,
|
|
"eval_entropy": 5.496154374681606,
|
|
"eval_loss": 5.649525165557861,
|
|
"eval_mean_token_accuracy": 0.16116220440296053,
|
|
"eval_num_tokens": 10421676.0,
|
|
"eval_runtime": 28.6748,
|
|
"eval_samples_per_second": 1449.287,
|
|
"eval_steps_per_second": 181.17,
|
|
"step": 6000
|
|
},
|
|
{
|
|
"entropy": 5.599911737442016,
|
|
"epoch": 0.46722427543279516,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.000498292423500673,
|
|
"loss": 5.5414,
|
|
"mean_token_accuracy": 0.15246708691120148,
|
|
"num_tokens": 10430714.0,
|
|
"step": 6005
|
|
},
|
|
{
|
|
"entropy": 5.7318932056427006,
|
|
"epoch": 0.46761330480451274,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004982890137064102,
|
|
"loss": 5.6676,
|
|
"mean_token_accuracy": 0.15135798901319503,
|
|
"num_tokens": 10439089.0,
|
|
"step": 6010
|
|
},
|
|
{
|
|
"entropy": 5.671796178817749,
|
|
"epoch": 0.46800233417623033,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.000498285600524092,
|
|
"loss": 5.5886,
|
|
"mean_token_accuracy": 0.1586393378674984,
|
|
"num_tokens": 10447455.0,
|
|
"step": 6015
|
|
},
|
|
{
|
|
"entropy": 5.6312915802001955,
|
|
"epoch": 0.46839136354794786,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004982821839537701,
|
|
"loss": 5.5752,
|
|
"mean_token_accuracy": 0.154066501557827,
|
|
"num_tokens": 10455936.0,
|
|
"step": 6020
|
|
},
|
|
{
|
|
"entropy": 5.781944608688354,
|
|
"epoch": 0.46878039291966545,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004982787639954966,
|
|
"loss": 5.7007,
|
|
"mean_token_accuracy": 0.14853788390755654,
|
|
"num_tokens": 10465389.0,
|
|
"step": 6025
|
|
},
|
|
{
|
|
"entropy": 5.8027105808258055,
|
|
"epoch": 0.469169422291383,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004982753406493232,
|
|
"loss": 5.5786,
|
|
"mean_token_accuracy": 0.15479041785001754,
|
|
"num_tokens": 10474709.0,
|
|
"step": 6030
|
|
},
|
|
{
|
|
"entropy": 5.6630011081695555,
|
|
"epoch": 0.46955845166310056,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004982719139153018,
|
|
"loss": 5.5814,
|
|
"mean_token_accuracy": 0.152097749710083,
|
|
"num_tokens": 10482972.0,
|
|
"step": 6035
|
|
},
|
|
{
|
|
"entropy": 5.663127374649048,
|
|
"epoch": 0.46994748103481815,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004982684837934845,
|
|
"loss": 5.5797,
|
|
"mean_token_accuracy": 0.15856870114803315,
|
|
"num_tokens": 10490897.0,
|
|
"step": 6040
|
|
},
|
|
{
|
|
"entropy": 5.644709920883178,
|
|
"epoch": 0.4703365104065357,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004982650502839234,
|
|
"loss": 5.5886,
|
|
"mean_token_accuracy": 0.15786385238170625,
|
|
"num_tokens": 10499679.0,
|
|
"step": 6045
|
|
},
|
|
{
|
|
"entropy": 5.725128126144409,
|
|
"epoch": 0.47072553977825327,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004982616133866705,
|
|
"loss": 5.6421,
|
|
"mean_token_accuracy": 0.15326734334230424,
|
|
"num_tokens": 10508775.0,
|
|
"step": 6050
|
|
},
|
|
{
|
|
"entropy": 5.618102359771728,
|
|
"epoch": 0.4711145691499708,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004982581731017779,
|
|
"loss": 5.5447,
|
|
"mean_token_accuracy": 0.16346119344234467,
|
|
"num_tokens": 10517600.0,
|
|
"step": 6055
|
|
},
|
|
{
|
|
"entropy": 5.5527385711669925,
|
|
"epoch": 0.4715035985216884,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004982547294292979,
|
|
"loss": 5.5035,
|
|
"mean_token_accuracy": 0.16293236017227172,
|
|
"num_tokens": 10525674.0,
|
|
"step": 6060
|
|
},
|
|
{
|
|
"entropy": 5.699562311172485,
|
|
"epoch": 0.47189262789340597,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004982512823692828,
|
|
"loss": 5.7015,
|
|
"mean_token_accuracy": 0.14990407973527908,
|
|
"num_tokens": 10533819.0,
|
|
"step": 6065
|
|
},
|
|
{
|
|
"entropy": 5.661665582656861,
|
|
"epoch": 0.4722816572651235,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004982478319217848,
|
|
"loss": 5.5065,
|
|
"mean_token_accuracy": 0.1595573216676712,
|
|
"num_tokens": 10542901.0,
|
|
"step": 6070
|
|
},
|
|
{
|
|
"entropy": 5.691421365737915,
|
|
"epoch": 0.4726706866368411,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004982443780868562,
|
|
"loss": 5.5825,
|
|
"mean_token_accuracy": 0.16080685406923295,
|
|
"num_tokens": 10552388.0,
|
|
"step": 6075
|
|
},
|
|
{
|
|
"entropy": 5.728979778289795,
|
|
"epoch": 0.4730597160085587,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004982409208645496,
|
|
"loss": 5.6839,
|
|
"mean_token_accuracy": 0.15371156632900237,
|
|
"num_tokens": 10561676.0,
|
|
"step": 6080
|
|
},
|
|
{
|
|
"entropy": 5.769681835174561,
|
|
"epoch": 0.4734487453802762,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004982374602549173,
|
|
"loss": 5.5888,
|
|
"mean_token_accuracy": 0.15942396819591523,
|
|
"num_tokens": 10570037.0,
|
|
"step": 6085
|
|
},
|
|
{
|
|
"entropy": 5.650616025924682,
|
|
"epoch": 0.4738377747519938,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004982339962580119,
|
|
"loss": 5.5862,
|
|
"mean_token_accuracy": 0.15037061125040055,
|
|
"num_tokens": 10579140.0,
|
|
"step": 6090
|
|
},
|
|
{
|
|
"entropy": 5.655625486373902,
|
|
"epoch": 0.4742268041237113,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004982305288738859,
|
|
"loss": 5.6288,
|
|
"mean_token_accuracy": 0.15578012466430663,
|
|
"num_tokens": 10587689.0,
|
|
"step": 6095
|
|
},
|
|
{
|
|
"entropy": 5.667337083816529,
|
|
"epoch": 0.4746158334954289,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004982270581025919,
|
|
"loss": 5.5078,
|
|
"mean_token_accuracy": 0.15836172550916672,
|
|
"num_tokens": 10596002.0,
|
|
"step": 6100
|
|
},
|
|
{
|
|
"entropy": 5.702313661575317,
|
|
"epoch": 0.4750048628671465,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004982235839441826,
|
|
"loss": 5.7311,
|
|
"mean_token_accuracy": 0.14916150867938996,
|
|
"num_tokens": 10605895.0,
|
|
"step": 6105
|
|
},
|
|
{
|
|
"entropy": 5.763257837295532,
|
|
"epoch": 0.475393892238864,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004982201063987108,
|
|
"loss": 5.6638,
|
|
"mean_token_accuracy": 0.14756975322961807,
|
|
"num_tokens": 10614641.0,
|
|
"step": 6110
|
|
},
|
|
{
|
|
"entropy": 5.660020637512207,
|
|
"epoch": 0.4757829216105816,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004982166254662292,
|
|
"loss": 5.6378,
|
|
"mean_token_accuracy": 0.1533852770924568,
|
|
"num_tokens": 10624381.0,
|
|
"step": 6115
|
|
},
|
|
{
|
|
"entropy": 5.706807374954224,
|
|
"epoch": 0.47617195098229914,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004982131411467904,
|
|
"loss": 5.5952,
|
|
"mean_token_accuracy": 0.15574658811092376,
|
|
"num_tokens": 10632493.0,
|
|
"step": 6120
|
|
},
|
|
{
|
|
"entropy": 5.704343557357788,
|
|
"epoch": 0.4765609803540167,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004982096534404476,
|
|
"loss": 5.6232,
|
|
"mean_token_accuracy": 0.14914219677448273,
|
|
"num_tokens": 10641556.0,
|
|
"step": 6125
|
|
},
|
|
{
|
|
"entropy": 5.67762017250061,
|
|
"epoch": 0.4769500097257343,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004982061623472535,
|
|
"loss": 5.6904,
|
|
"mean_token_accuracy": 0.15633485242724418,
|
|
"num_tokens": 10649736.0,
|
|
"step": 6130
|
|
},
|
|
{
|
|
"entropy": 5.684682178497314,
|
|
"epoch": 0.47733903909745184,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004982026678672612,
|
|
"loss": 5.5009,
|
|
"mean_token_accuracy": 0.16547404527664183,
|
|
"num_tokens": 10657991.0,
|
|
"step": 6135
|
|
},
|
|
{
|
|
"entropy": 5.596237707138061,
|
|
"epoch": 0.47772806846916943,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004981991700005238,
|
|
"loss": 5.5706,
|
|
"mean_token_accuracy": 0.15123811960220337,
|
|
"num_tokens": 10667310.0,
|
|
"step": 6140
|
|
},
|
|
{
|
|
"entropy": 5.741936254501343,
|
|
"epoch": 0.47811709784088696,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.000498195668747094,
|
|
"loss": 5.6213,
|
|
"mean_token_accuracy": 0.15695492923259735,
|
|
"num_tokens": 10675658.0,
|
|
"step": 6145
|
|
},
|
|
{
|
|
"entropy": 5.638043642044067,
|
|
"epoch": 0.47850612721260455,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004981921641070254,
|
|
"loss": 5.5102,
|
|
"mean_token_accuracy": 0.16681503355503083,
|
|
"num_tokens": 10684016.0,
|
|
"step": 6150
|
|
},
|
|
{
|
|
"entropy": 5.666017532348633,
|
|
"epoch": 0.47889515658432213,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004981886560803708,
|
|
"loss": 5.6281,
|
|
"mean_token_accuracy": 0.15898596942424775,
|
|
"num_tokens": 10692814.0,
|
|
"step": 6155
|
|
},
|
|
{
|
|
"entropy": 5.71913104057312,
|
|
"epoch": 0.47928418595603967,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004981851446671838,
|
|
"loss": 5.6469,
|
|
"mean_token_accuracy": 0.15398247838020324,
|
|
"num_tokens": 10701571.0,
|
|
"step": 6160
|
|
},
|
|
{
|
|
"entropy": 5.743273782730102,
|
|
"epoch": 0.47967321532775725,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004981816298675173,
|
|
"loss": 5.6321,
|
|
"mean_token_accuracy": 0.15258511602878572,
|
|
"num_tokens": 10710569.0,
|
|
"step": 6165
|
|
},
|
|
{
|
|
"entropy": 5.699658441543579,
|
|
"epoch": 0.4800622446994748,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004981781116814248,
|
|
"loss": 5.6556,
|
|
"mean_token_accuracy": 0.15451659709215165,
|
|
"num_tokens": 10719277.0,
|
|
"step": 6170
|
|
},
|
|
{
|
|
"entropy": 5.6413978099822994,
|
|
"epoch": 0.48045127407119237,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004981745901089596,
|
|
"loss": 5.523,
|
|
"mean_token_accuracy": 0.1553031951189041,
|
|
"num_tokens": 10727174.0,
|
|
"step": 6175
|
|
},
|
|
{
|
|
"entropy": 5.652820158004761,
|
|
"epoch": 0.48084030344290996,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004981710651501753,
|
|
"loss": 5.6308,
|
|
"mean_token_accuracy": 0.1499924898147583,
|
|
"num_tokens": 10736072.0,
|
|
"step": 6180
|
|
},
|
|
{
|
|
"entropy": 5.77542290687561,
|
|
"epoch": 0.4812293328146275,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004981675368051254,
|
|
"loss": 5.6366,
|
|
"mean_token_accuracy": 0.1591070920228958,
|
|
"num_tokens": 10745375.0,
|
|
"step": 6185
|
|
},
|
|
{
|
|
"entropy": 5.6705575466156,
|
|
"epoch": 0.4816183621863451,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004981640050738633,
|
|
"loss": 5.6372,
|
|
"mean_token_accuracy": 0.15502333045005798,
|
|
"num_tokens": 10754049.0,
|
|
"step": 6190
|
|
},
|
|
{
|
|
"entropy": 5.6272234439849855,
|
|
"epoch": 0.48200739155806266,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004981604699564426,
|
|
"loss": 5.5709,
|
|
"mean_token_accuracy": 0.15725173354148864,
|
|
"num_tokens": 10763475.0,
|
|
"step": 6195
|
|
},
|
|
{
|
|
"entropy": 5.723629283905029,
|
|
"epoch": 0.4823964209297802,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004981569314529169,
|
|
"loss": 5.6537,
|
|
"mean_token_accuracy": 0.15193783938884736,
|
|
"num_tokens": 10772100.0,
|
|
"step": 6200
|
|
},
|
|
{
|
|
"entropy": 5.624773168563843,
|
|
"epoch": 0.4827854503014978,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00049815338956334,
|
|
"loss": 5.586,
|
|
"mean_token_accuracy": 0.1571911796927452,
|
|
"num_tokens": 10780605.0,
|
|
"step": 6205
|
|
},
|
|
{
|
|
"entropy": 5.688734722137451,
|
|
"epoch": 0.4831744796732153,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004981498442877656,
|
|
"loss": 5.57,
|
|
"mean_token_accuracy": 0.15786497220396994,
|
|
"num_tokens": 10789235.0,
|
|
"step": 6210
|
|
},
|
|
{
|
|
"entropy": 5.692664527893067,
|
|
"epoch": 0.4835635090449329,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004981462956262474,
|
|
"loss": 5.5806,
|
|
"mean_token_accuracy": 0.15071646571159364,
|
|
"num_tokens": 10798078.0,
|
|
"step": 6215
|
|
},
|
|
{
|
|
"entropy": 5.687393140792847,
|
|
"epoch": 0.4839525384166505,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004981427435788396,
|
|
"loss": 5.6054,
|
|
"mean_token_accuracy": 0.14804309904575347,
|
|
"num_tokens": 10807667.0,
|
|
"step": 6220
|
|
},
|
|
{
|
|
"entropy": 5.652494049072265,
|
|
"epoch": 0.484341567788368,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004981391881455957,
|
|
"loss": 5.5685,
|
|
"mean_token_accuracy": 0.14992497563362123,
|
|
"num_tokens": 10816574.0,
|
|
"step": 6225
|
|
},
|
|
{
|
|
"entropy": 5.658774518966675,
|
|
"epoch": 0.4847305971600856,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004981356293265696,
|
|
"loss": 5.5465,
|
|
"mean_token_accuracy": 0.15477658212184905,
|
|
"num_tokens": 10824675.0,
|
|
"step": 6230
|
|
},
|
|
{
|
|
"entropy": 5.645687818527222,
|
|
"epoch": 0.4851196265318031,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004981320671218157,
|
|
"loss": 5.5049,
|
|
"mean_token_accuracy": 0.16456515043973924,
|
|
"num_tokens": 10832855.0,
|
|
"step": 6235
|
|
},
|
|
{
|
|
"entropy": 5.572377777099609,
|
|
"epoch": 0.4855086559035207,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004981285015313877,
|
|
"loss": 5.4122,
|
|
"mean_token_accuracy": 0.1659885361790657,
|
|
"num_tokens": 10841603.0,
|
|
"step": 6240
|
|
},
|
|
{
|
|
"entropy": 5.74435248374939,
|
|
"epoch": 0.4858976852752383,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004981249325553399,
|
|
"loss": 5.7553,
|
|
"mean_token_accuracy": 0.14605401381850242,
|
|
"num_tokens": 10850348.0,
|
|
"step": 6245
|
|
},
|
|
{
|
|
"entropy": 5.7315455913543705,
|
|
"epoch": 0.48628671464695583,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004981213601937264,
|
|
"loss": 5.4984,
|
|
"mean_token_accuracy": 0.15666187256574632,
|
|
"num_tokens": 10858955.0,
|
|
"step": 6250
|
|
},
|
|
{
|
|
"entropy": 5.634166193008423,
|
|
"epoch": 0.4866757440186734,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004981177844466013,
|
|
"loss": 5.5928,
|
|
"mean_token_accuracy": 0.1482228606939316,
|
|
"num_tokens": 10867336.0,
|
|
"step": 6255
|
|
},
|
|
{
|
|
"entropy": 5.68542799949646,
|
|
"epoch": 0.48706477339039095,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004981142053140192,
|
|
"loss": 5.6738,
|
|
"mean_token_accuracy": 0.15138802379369737,
|
|
"num_tokens": 10877043.0,
|
|
"step": 6260
|
|
},
|
|
{
|
|
"entropy": 5.799023103713989,
|
|
"epoch": 0.48745380276210853,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004981106227960339,
|
|
"loss": 5.6314,
|
|
"mean_token_accuracy": 0.15212034434080124,
|
|
"num_tokens": 10885580.0,
|
|
"step": 6265
|
|
},
|
|
{
|
|
"entropy": 5.727660846710205,
|
|
"epoch": 0.4878428321338261,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004981070368927001,
|
|
"loss": 5.7355,
|
|
"mean_token_accuracy": 0.1497201591730118,
|
|
"num_tokens": 10894289.0,
|
|
"step": 6270
|
|
},
|
|
{
|
|
"entropy": 5.723119068145752,
|
|
"epoch": 0.48823186150554365,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.000498103447604072,
|
|
"loss": 5.6595,
|
|
"mean_token_accuracy": 0.14703867062926293,
|
|
"num_tokens": 10902384.0,
|
|
"step": 6275
|
|
},
|
|
{
|
|
"entropy": 5.73089189529419,
|
|
"epoch": 0.48862089087726124,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004980998549302044,
|
|
"loss": 5.5618,
|
|
"mean_token_accuracy": 0.1498264640569687,
|
|
"num_tokens": 10911160.0,
|
|
"step": 6280
|
|
},
|
|
{
|
|
"entropy": 5.621191596984863,
|
|
"epoch": 0.4890099202489788,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004980962588711516,
|
|
"loss": 5.4562,
|
|
"mean_token_accuracy": 0.16945781260728837,
|
|
"num_tokens": 10920066.0,
|
|
"step": 6285
|
|
},
|
|
{
|
|
"entropy": 5.694791412353515,
|
|
"epoch": 0.48939894962069636,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.000498092659426968,
|
|
"loss": 5.635,
|
|
"mean_token_accuracy": 0.15655620992183686,
|
|
"num_tokens": 10928969.0,
|
|
"step": 6290
|
|
},
|
|
{
|
|
"entropy": 5.752533292770385,
|
|
"epoch": 0.48978797899241394,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004980890565977085,
|
|
"loss": 5.627,
|
|
"mean_token_accuracy": 0.1562311053276062,
|
|
"num_tokens": 10936939.0,
|
|
"step": 6295
|
|
},
|
|
{
|
|
"entropy": 5.633117532730102,
|
|
"epoch": 0.4901770083641315,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004980854503834276,
|
|
"loss": 5.5868,
|
|
"mean_token_accuracy": 0.15852609723806382,
|
|
"num_tokens": 10945929.0,
|
|
"step": 6300
|
|
},
|
|
{
|
|
"entropy": 5.663782453536987,
|
|
"epoch": 0.49056603773584906,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004980818407841802,
|
|
"loss": 5.5863,
|
|
"mean_token_accuracy": 0.1573207527399063,
|
|
"num_tokens": 10954849.0,
|
|
"step": 6305
|
|
},
|
|
{
|
|
"entropy": 5.678795623779297,
|
|
"epoch": 0.49095506710756665,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004980782278000207,
|
|
"loss": 5.6407,
|
|
"mean_token_accuracy": 0.15423305928707123,
|
|
"num_tokens": 10963800.0,
|
|
"step": 6310
|
|
},
|
|
{
|
|
"entropy": 5.839993190765381,
|
|
"epoch": 0.4913440964792842,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004980746114310043,
|
|
"loss": 5.6953,
|
|
"mean_token_accuracy": 0.15321774333715438,
|
|
"num_tokens": 10972477.0,
|
|
"step": 6315
|
|
},
|
|
{
|
|
"entropy": 5.829525756835937,
|
|
"epoch": 0.49173312585100176,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004980709916771858,
|
|
"loss": 5.6855,
|
|
"mean_token_accuracy": 0.1555396370589733,
|
|
"num_tokens": 10981437.0,
|
|
"step": 6320
|
|
},
|
|
{
|
|
"entropy": 5.64800500869751,
|
|
"epoch": 0.4921221552227193,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004980673685386198,
|
|
"loss": 5.5357,
|
|
"mean_token_accuracy": 0.15727183669805528,
|
|
"num_tokens": 10989973.0,
|
|
"step": 6325
|
|
},
|
|
{
|
|
"entropy": 5.586803579330445,
|
|
"epoch": 0.4925111845944369,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004980637420153618,
|
|
"loss": 5.5574,
|
|
"mean_token_accuracy": 0.15266730338335038,
|
|
"num_tokens": 10998160.0,
|
|
"step": 6330
|
|
},
|
|
{
|
|
"entropy": 5.676742506027222,
|
|
"epoch": 0.49290021396615447,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004980601121074664,
|
|
"loss": 5.7116,
|
|
"mean_token_accuracy": 0.1521316148340702,
|
|
"num_tokens": 11007127.0,
|
|
"step": 6335
|
|
},
|
|
{
|
|
"entropy": 5.7719337940216064,
|
|
"epoch": 0.493289243337872,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004980564788149889,
|
|
"loss": 5.5615,
|
|
"mean_token_accuracy": 0.15340966284275054,
|
|
"num_tokens": 11015518.0,
|
|
"step": 6340
|
|
},
|
|
{
|
|
"entropy": 5.611857223510742,
|
|
"epoch": 0.4936782727095896,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004980528421379844,
|
|
"loss": 5.4632,
|
|
"mean_token_accuracy": 0.16847451776266098,
|
|
"num_tokens": 11023739.0,
|
|
"step": 6345
|
|
},
|
|
{
|
|
"entropy": 5.586323976516724,
|
|
"epoch": 0.4940673020813071,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.000498049202076508,
|
|
"loss": 5.4961,
|
|
"mean_token_accuracy": 0.16648571491241454,
|
|
"num_tokens": 11032034.0,
|
|
"step": 6350
|
|
},
|
|
{
|
|
"entropy": 5.642065715789795,
|
|
"epoch": 0.4944563314530247,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004980455586306149,
|
|
"loss": 5.4984,
|
|
"mean_token_accuracy": 0.1611510455608368,
|
|
"num_tokens": 11040319.0,
|
|
"step": 6355
|
|
},
|
|
{
|
|
"entropy": 5.604467725753784,
|
|
"epoch": 0.4948453608247423,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004980419118003605,
|
|
"loss": 5.5654,
|
|
"mean_token_accuracy": 0.15740724951028823,
|
|
"num_tokens": 11049459.0,
|
|
"step": 6360
|
|
},
|
|
{
|
|
"entropy": 5.663004446029663,
|
|
"epoch": 0.4952343901964598,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004980382615858001,
|
|
"loss": 5.5489,
|
|
"mean_token_accuracy": 0.15955363661050798,
|
|
"num_tokens": 11058402.0,
|
|
"step": 6365
|
|
},
|
|
{
|
|
"entropy": 5.593869209289551,
|
|
"epoch": 0.4956234195681774,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004980346079869892,
|
|
"loss": 5.4955,
|
|
"mean_token_accuracy": 0.1616832584142685,
|
|
"num_tokens": 11067430.0,
|
|
"step": 6370
|
|
},
|
|
{
|
|
"entropy": 5.668562316894532,
|
|
"epoch": 0.49601244893989493,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.000498030951003983,
|
|
"loss": 5.492,
|
|
"mean_token_accuracy": 0.16149785220623017,
|
|
"num_tokens": 11075594.0,
|
|
"step": 6375
|
|
},
|
|
{
|
|
"entropy": 5.595048952102661,
|
|
"epoch": 0.4964014783116125,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004980272906368371,
|
|
"loss": 5.4584,
|
|
"mean_token_accuracy": 0.1725854143500328,
|
|
"num_tokens": 11083509.0,
|
|
"step": 6380
|
|
},
|
|
{
|
|
"entropy": 5.637046384811401,
|
|
"epoch": 0.4967905076833301,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004980236268856071,
|
|
"loss": 5.6269,
|
|
"mean_token_accuracy": 0.15187471285462378,
|
|
"num_tokens": 11091938.0,
|
|
"step": 6385
|
|
},
|
|
{
|
|
"entropy": 5.681407499313354,
|
|
"epoch": 0.49717953705504764,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004980199597503487,
|
|
"loss": 5.6592,
|
|
"mean_token_accuracy": 0.15273707509040832,
|
|
"num_tokens": 11099974.0,
|
|
"step": 6390
|
|
},
|
|
{
|
|
"entropy": 5.583227300643921,
|
|
"epoch": 0.4975685664267652,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004980162892311171,
|
|
"loss": 5.3097,
|
|
"mean_token_accuracy": 0.1723850205540657,
|
|
"num_tokens": 11107944.0,
|
|
"step": 6395
|
|
},
|
|
{
|
|
"entropy": 5.559449100494385,
|
|
"epoch": 0.4979575957984828,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004980126153279684,
|
|
"loss": 5.603,
|
|
"mean_token_accuracy": 0.1561395511031151,
|
|
"num_tokens": 11116401.0,
|
|
"step": 6400
|
|
},
|
|
{
|
|
"entropy": 5.660170412063598,
|
|
"epoch": 0.49834662517020034,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004980089380409583,
|
|
"loss": 5.5709,
|
|
"mean_token_accuracy": 0.15186020135879516,
|
|
"num_tokens": 11125430.0,
|
|
"step": 6405
|
|
},
|
|
{
|
|
"entropy": 5.715793418884277,
|
|
"epoch": 0.4987356545419179,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004980052573701424,
|
|
"loss": 5.6372,
|
|
"mean_token_accuracy": 0.148736110329628,
|
|
"num_tokens": 11133949.0,
|
|
"step": 6410
|
|
},
|
|
{
|
|
"entropy": 5.731146192550659,
|
|
"epoch": 0.49912468391363546,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004980015733155767,
|
|
"loss": 5.5675,
|
|
"mean_token_accuracy": 0.16028442829847336,
|
|
"num_tokens": 11141749.0,
|
|
"step": 6415
|
|
},
|
|
{
|
|
"entropy": 5.649786901473999,
|
|
"epoch": 0.49951371328535304,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004979978858773171,
|
|
"loss": 5.5657,
|
|
"mean_token_accuracy": 0.15979141891002654,
|
|
"num_tokens": 11150618.0,
|
|
"step": 6420
|
|
},
|
|
{
|
|
"entropy": 5.609336900711059,
|
|
"epoch": 0.49990274265707063,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004979941950554195,
|
|
"loss": 5.5968,
|
|
"mean_token_accuracy": 0.15541461259126663,
|
|
"num_tokens": 11158549.0,
|
|
"step": 6425
|
|
},
|
|
{
|
|
"entropy": 5.672288656234741,
|
|
"epoch": 0.5002917720287882,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004979905008499399,
|
|
"loss": 5.5365,
|
|
"mean_token_accuracy": 0.16468718647956848,
|
|
"num_tokens": 11167131.0,
|
|
"step": 6430
|
|
},
|
|
{
|
|
"entropy": 5.669491386413574,
|
|
"epoch": 0.5006808014005057,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004979868032609344,
|
|
"loss": 5.6143,
|
|
"mean_token_accuracy": 0.15387326255440711,
|
|
"num_tokens": 11175766.0,
|
|
"step": 6435
|
|
},
|
|
{
|
|
"entropy": 5.688392448425293,
|
|
"epoch": 0.5010698307722233,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004979831022884591,
|
|
"loss": 5.5899,
|
|
"mean_token_accuracy": 0.15998782515525817,
|
|
"num_tokens": 11184799.0,
|
|
"step": 6440
|
|
},
|
|
{
|
|
"entropy": 5.594391107559204,
|
|
"epoch": 0.5014588601439409,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004979793979325701,
|
|
"loss": 5.5329,
|
|
"mean_token_accuracy": 0.1567195326089859,
|
|
"num_tokens": 11193083.0,
|
|
"step": 6445
|
|
},
|
|
{
|
|
"entropy": 5.582624864578247,
|
|
"epoch": 0.5018478895156584,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004979756901933236,
|
|
"loss": 5.5276,
|
|
"mean_token_accuracy": 0.16227489709854126,
|
|
"num_tokens": 11201753.0,
|
|
"step": 6450
|
|
},
|
|
{
|
|
"entropy": 5.760551834106446,
|
|
"epoch": 0.502236918887376,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.000497971979070776,
|
|
"loss": 5.619,
|
|
"mean_token_accuracy": 0.15672486275434494,
|
|
"num_tokens": 11209965.0,
|
|
"step": 6455
|
|
},
|
|
{
|
|
"entropy": 5.6459235668182375,
|
|
"epoch": 0.5026259482590936,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004979682645649834,
|
|
"loss": 5.517,
|
|
"mean_token_accuracy": 0.1660740926861763,
|
|
"num_tokens": 11217961.0,
|
|
"step": 6460
|
|
},
|
|
{
|
|
"entropy": 5.661819362640381,
|
|
"epoch": 0.5030149776308112,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004979645466760025,
|
|
"loss": 5.6222,
|
|
"mean_token_accuracy": 0.15498576909303666,
|
|
"num_tokens": 11225803.0,
|
|
"step": 6465
|
|
},
|
|
{
|
|
"entropy": 5.619951629638672,
|
|
"epoch": 0.5034040070025287,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004979608254038892,
|
|
"loss": 5.4606,
|
|
"mean_token_accuracy": 0.16229200810194017,
|
|
"num_tokens": 11234584.0,
|
|
"step": 6470
|
|
},
|
|
{
|
|
"entropy": 5.680429172515869,
|
|
"epoch": 0.5037930363742462,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004979571007487003,
|
|
"loss": 5.6651,
|
|
"mean_token_accuracy": 0.15144428014755248,
|
|
"num_tokens": 11243340.0,
|
|
"step": 6475
|
|
},
|
|
{
|
|
"entropy": 5.62803840637207,
|
|
"epoch": 0.5041820657459638,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004979533727104924,
|
|
"loss": 5.531,
|
|
"mean_token_accuracy": 0.1532328888773918,
|
|
"num_tokens": 11252383.0,
|
|
"step": 6480
|
|
},
|
|
{
|
|
"entropy": 5.630037784576416,
|
|
"epoch": 0.5045710951176814,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.000497949641289322,
|
|
"loss": 5.6087,
|
|
"mean_token_accuracy": 0.15235372483730317,
|
|
"num_tokens": 11261419.0,
|
|
"step": 6485
|
|
},
|
|
{
|
|
"entropy": 5.653547477722168,
|
|
"epoch": 0.504960124489399,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004979459064852456,
|
|
"loss": 5.574,
|
|
"mean_token_accuracy": 0.15386256873607634,
|
|
"num_tokens": 11270743.0,
|
|
"step": 6490
|
|
},
|
|
{
|
|
"entropy": 5.706313419342041,
|
|
"epoch": 0.5053491538611166,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004979421682983197,
|
|
"loss": 5.4868,
|
|
"mean_token_accuracy": 0.15976502299308776,
|
|
"num_tokens": 11279666.0,
|
|
"step": 6495
|
|
},
|
|
{
|
|
"entropy": 5.7113391876220705,
|
|
"epoch": 0.505738183232834,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004979384267286015,
|
|
"loss": 5.6601,
|
|
"mean_token_accuracy": 0.14999309778213502,
|
|
"num_tokens": 11288710.0,
|
|
"step": 6500
|
|
},
|
|
{
|
|
"entropy": 5.6965361595153805,
|
|
"epoch": 0.5061272126045516,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004979346817761475,
|
|
"loss": 5.5297,
|
|
"mean_token_accuracy": 0.15320013761520385,
|
|
"num_tokens": 11297665.0,
|
|
"step": 6505
|
|
},
|
|
{
|
|
"entropy": 5.7402442455291744,
|
|
"epoch": 0.5065162419762692,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004979309334410144,
|
|
"loss": 5.6928,
|
|
"mean_token_accuracy": 0.15129803717136384,
|
|
"num_tokens": 11306751.0,
|
|
"step": 6510
|
|
},
|
|
{
|
|
"entropy": 5.690135049819946,
|
|
"epoch": 0.5069052713479868,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.0004979271817232594,
|
|
"loss": 5.6844,
|
|
"mean_token_accuracy": 0.15013830214738846,
|
|
"num_tokens": 11315659.0,
|
|
"step": 6515
|
|
},
|
|
{
|
|
"entropy": 5.701597547531128,
|
|
"epoch": 0.5072943007197044,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004979234266229391,
|
|
"loss": 5.5613,
|
|
"mean_token_accuracy": 0.1573285400867462,
|
|
"num_tokens": 11323362.0,
|
|
"step": 6520
|
|
},
|
|
{
|
|
"entropy": 5.6727128505706785,
|
|
"epoch": 0.5076833300914219,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004979196681401106,
|
|
"loss": 5.5589,
|
|
"mean_token_accuracy": 0.15374930649995805,
|
|
"num_tokens": 11332343.0,
|
|
"step": 6525
|
|
},
|
|
{
|
|
"entropy": 5.6307044506073,
|
|
"epoch": 0.5080723594631394,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.000497915906274831,
|
|
"loss": 5.5097,
|
|
"mean_token_accuracy": 0.153728187084198,
|
|
"num_tokens": 11340816.0,
|
|
"step": 6530
|
|
},
|
|
{
|
|
"entropy": 5.596715879440308,
|
|
"epoch": 0.508461388834857,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004979121410271574,
|
|
"loss": 5.5076,
|
|
"mean_token_accuracy": 0.1596982181072235,
|
|
"num_tokens": 11349728.0,
|
|
"step": 6535
|
|
},
|
|
{
|
|
"entropy": 5.6834207534790036,
|
|
"epoch": 0.5088504182065746,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004979083723971468,
|
|
"loss": 5.6381,
|
|
"mean_token_accuracy": 0.1554409921169281,
|
|
"num_tokens": 11358477.0,
|
|
"step": 6540
|
|
},
|
|
{
|
|
"entropy": 5.589273118972779,
|
|
"epoch": 0.5092394475782922,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004979046003848564,
|
|
"loss": 5.4559,
|
|
"mean_token_accuracy": 0.166815909743309,
|
|
"num_tokens": 11367183.0,
|
|
"step": 6545
|
|
},
|
|
{
|
|
"entropy": 5.6982262134552,
|
|
"epoch": 0.5096284769500097,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004979008249903435,
|
|
"loss": 5.6663,
|
|
"mean_token_accuracy": 0.1446331888437271,
|
|
"num_tokens": 11376703.0,
|
|
"step": 6550
|
|
},
|
|
{
|
|
"entropy": 5.741359567642212,
|
|
"epoch": 0.5100175063217273,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004978970462136655,
|
|
"loss": 5.6684,
|
|
"mean_token_accuracy": 0.1546018734574318,
|
|
"num_tokens": 11385502.0,
|
|
"step": 6555
|
|
},
|
|
{
|
|
"entropy": 5.686350870132446,
|
|
"epoch": 0.5104065356934449,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004978932640548794,
|
|
"loss": 5.5298,
|
|
"mean_token_accuracy": 0.1591428518295288,
|
|
"num_tokens": 11393947.0,
|
|
"step": 6560
|
|
},
|
|
{
|
|
"entropy": 5.59600796699524,
|
|
"epoch": 0.5107955650651624,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004978894785140429,
|
|
"loss": 5.5188,
|
|
"mean_token_accuracy": 0.164163675904274,
|
|
"num_tokens": 11403077.0,
|
|
"step": 6565
|
|
},
|
|
{
|
|
"entropy": 5.57859468460083,
|
|
"epoch": 0.51118459443688,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004978856895912132,
|
|
"loss": 5.5,
|
|
"mean_token_accuracy": 0.15813149958848954,
|
|
"num_tokens": 11411863.0,
|
|
"step": 6570
|
|
},
|
|
{
|
|
"entropy": 5.681532716751098,
|
|
"epoch": 0.5115736238085975,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004978818972864481,
|
|
"loss": 5.4611,
|
|
"mean_token_accuracy": 0.16052573472261428,
|
|
"num_tokens": 11420030.0,
|
|
"step": 6575
|
|
},
|
|
{
|
|
"entropy": 5.702321243286133,
|
|
"epoch": 0.5119626531803151,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004978781015998048,
|
|
"loss": 5.5644,
|
|
"mean_token_accuracy": 0.15766163170337677,
|
|
"num_tokens": 11428534.0,
|
|
"step": 6580
|
|
},
|
|
{
|
|
"entropy": 5.664851665496826,
|
|
"epoch": 0.5123516825520327,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004978743025313413,
|
|
"loss": 5.5533,
|
|
"mean_token_accuracy": 0.15721214860677718,
|
|
"num_tokens": 11436641.0,
|
|
"step": 6585
|
|
},
|
|
{
|
|
"entropy": 5.631090784072876,
|
|
"epoch": 0.5127407119237503,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004978705000811148,
|
|
"loss": 5.5312,
|
|
"mean_token_accuracy": 0.1598398506641388,
|
|
"num_tokens": 11444595.0,
|
|
"step": 6590
|
|
},
|
|
{
|
|
"entropy": 5.577209997177124,
|
|
"epoch": 0.5131297412954678,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004978666942491832,
|
|
"loss": 5.3865,
|
|
"mean_token_accuracy": 0.16264140456914902,
|
|
"num_tokens": 11453257.0,
|
|
"step": 6595
|
|
},
|
|
{
|
|
"entropy": 5.589799070358277,
|
|
"epoch": 0.5135187706671853,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004978628850356043,
|
|
"loss": 5.5615,
|
|
"mean_token_accuracy": 0.15875291973352432,
|
|
"num_tokens": 11461762.0,
|
|
"step": 6600
|
|
},
|
|
{
|
|
"entropy": 5.649018383026123,
|
|
"epoch": 0.5139078000389029,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004978590724404358,
|
|
"loss": 5.4686,
|
|
"mean_token_accuracy": 0.15878367722034453,
|
|
"num_tokens": 11470602.0,
|
|
"step": 6605
|
|
},
|
|
{
|
|
"entropy": 5.635024499893189,
|
|
"epoch": 0.5142968294106205,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004978552564637356,
|
|
"loss": 5.5583,
|
|
"mean_token_accuracy": 0.15673930644989015,
|
|
"num_tokens": 11479826.0,
|
|
"step": 6610
|
|
},
|
|
{
|
|
"entropy": 5.680516052246094,
|
|
"epoch": 0.5146858587823381,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004978514371055616,
|
|
"loss": 5.6371,
|
|
"mean_token_accuracy": 0.15062430500984192,
|
|
"num_tokens": 11488698.0,
|
|
"step": 6615
|
|
},
|
|
{
|
|
"entropy": 5.728860330581665,
|
|
"epoch": 0.5150748881540557,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004978476143659718,
|
|
"loss": 5.6055,
|
|
"mean_token_accuracy": 0.15783123075962066,
|
|
"num_tokens": 11497434.0,
|
|
"step": 6620
|
|
},
|
|
{
|
|
"entropy": 5.626099395751953,
|
|
"epoch": 0.5154639175257731,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004978437882450241,
|
|
"loss": 5.6226,
|
|
"mean_token_accuracy": 0.15543157532811164,
|
|
"num_tokens": 11506173.0,
|
|
"step": 6625
|
|
},
|
|
{
|
|
"entropy": 5.63395414352417,
|
|
"epoch": 0.5158529468974907,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004978399587427766,
|
|
"loss": 5.5153,
|
|
"mean_token_accuracy": 0.1609303444623947,
|
|
"num_tokens": 11514824.0,
|
|
"step": 6630
|
|
},
|
|
{
|
|
"entropy": 5.634879398345947,
|
|
"epoch": 0.5162419762692083,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004978361258592874,
|
|
"loss": 5.5784,
|
|
"mean_token_accuracy": 0.15130043774843216,
|
|
"num_tokens": 11523634.0,
|
|
"step": 6635
|
|
},
|
|
{
|
|
"entropy": 5.803075313568115,
|
|
"epoch": 0.5166310056409259,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004978322895946147,
|
|
"loss": 5.7006,
|
|
"mean_token_accuracy": 0.15314190834760666,
|
|
"num_tokens": 11531916.0,
|
|
"step": 6640
|
|
},
|
|
{
|
|
"entropy": 5.699688673019409,
|
|
"epoch": 0.5170200350126435,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004978284499488167,
|
|
"loss": 5.5159,
|
|
"mean_token_accuracy": 0.16227565407752992,
|
|
"num_tokens": 11540000.0,
|
|
"step": 6645
|
|
},
|
|
{
|
|
"entropy": 5.699098587036133,
|
|
"epoch": 0.5174090643843611,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004978246069219516,
|
|
"loss": 5.6113,
|
|
"mean_token_accuracy": 0.15647616535425185,
|
|
"num_tokens": 11548760.0,
|
|
"step": 6650
|
|
},
|
|
{
|
|
"entropy": 5.587365961074829,
|
|
"epoch": 0.5177980937560785,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004978207605140777,
|
|
"loss": 5.4321,
|
|
"mean_token_accuracy": 0.16562076658010483,
|
|
"num_tokens": 11557991.0,
|
|
"step": 6655
|
|
},
|
|
{
|
|
"entropy": 5.608901739120483,
|
|
"epoch": 0.5181871231277961,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004978169107252534,
|
|
"loss": 5.4985,
|
|
"mean_token_accuracy": 0.16201310306787492,
|
|
"num_tokens": 11566638.0,
|
|
"step": 6660
|
|
},
|
|
{
|
|
"entropy": 5.53792028427124,
|
|
"epoch": 0.5185761524995137,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004978130575555373,
|
|
"loss": 5.4198,
|
|
"mean_token_accuracy": 0.16330699175596236,
|
|
"num_tokens": 11575106.0,
|
|
"step": 6665
|
|
},
|
|
{
|
|
"entropy": 5.5862060546875,
|
|
"epoch": 0.5189651818712313,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004978092010049877,
|
|
"loss": 5.5869,
|
|
"mean_token_accuracy": 0.1444960653781891,
|
|
"num_tokens": 11583971.0,
|
|
"step": 6670
|
|
},
|
|
{
|
|
"entropy": 5.6814610958099365,
|
|
"epoch": 0.5193542112429489,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.000497805341073663,
|
|
"loss": 5.5944,
|
|
"mean_token_accuracy": 0.1549292489886284,
|
|
"num_tokens": 11592936.0,
|
|
"step": 6675
|
|
},
|
|
{
|
|
"entropy": 5.649386644363403,
|
|
"epoch": 0.5197432406146664,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004978014777616219,
|
|
"loss": 5.4676,
|
|
"mean_token_accuracy": 0.159424264729023,
|
|
"num_tokens": 11602055.0,
|
|
"step": 6680
|
|
},
|
|
{
|
|
"entropy": 5.592701244354248,
|
|
"epoch": 0.520132269986384,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004977976110689229,
|
|
"loss": 5.4963,
|
|
"mean_token_accuracy": 0.15947575122117996,
|
|
"num_tokens": 11610211.0,
|
|
"step": 6685
|
|
},
|
|
{
|
|
"entropy": 5.6688920021057125,
|
|
"epoch": 0.5205212993581015,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.000497793740995625,
|
|
"loss": 5.5579,
|
|
"mean_token_accuracy": 0.15732331275939943,
|
|
"num_tokens": 11619096.0,
|
|
"step": 6690
|
|
},
|
|
{
|
|
"entropy": 5.658513736724854,
|
|
"epoch": 0.5209103287298191,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004977898675417866,
|
|
"loss": 5.6363,
|
|
"mean_token_accuracy": 0.15888825207948684,
|
|
"num_tokens": 11628142.0,
|
|
"step": 6695
|
|
},
|
|
{
|
|
"entropy": 5.700950670242309,
|
|
"epoch": 0.5212993581015367,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004977859907074664,
|
|
"loss": 5.485,
|
|
"mean_token_accuracy": 0.16149185299873353,
|
|
"num_tokens": 11635961.0,
|
|
"step": 6700
|
|
},
|
|
{
|
|
"entropy": 5.6735364437103275,
|
|
"epoch": 0.5216883874732542,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004977821104927236,
|
|
"loss": 5.6212,
|
|
"mean_token_accuracy": 0.1562149181962013,
|
|
"num_tokens": 11644778.0,
|
|
"step": 6705
|
|
},
|
|
{
|
|
"entropy": 5.657710838317871,
|
|
"epoch": 0.5220774168449718,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004977782268976167,
|
|
"loss": 5.5925,
|
|
"mean_token_accuracy": 0.15472943633794783,
|
|
"num_tokens": 11654043.0,
|
|
"step": 6710
|
|
},
|
|
{
|
|
"entropy": 5.711113595962525,
|
|
"epoch": 0.5224664462166894,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004977743399222048,
|
|
"loss": 5.5755,
|
|
"mean_token_accuracy": 0.15707167237997055,
|
|
"num_tokens": 11662794.0,
|
|
"step": 6715
|
|
},
|
|
{
|
|
"entropy": 5.631554222106933,
|
|
"epoch": 0.522855475588407,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004977704495665471,
|
|
"loss": 5.5782,
|
|
"mean_token_accuracy": 0.1574481889605522,
|
|
"num_tokens": 11670624.0,
|
|
"step": 6720
|
|
},
|
|
{
|
|
"entropy": 5.58207483291626,
|
|
"epoch": 0.5232445049601245,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004977665558307023,
|
|
"loss": 5.482,
|
|
"mean_token_accuracy": 0.15776702016592026,
|
|
"num_tokens": 11679366.0,
|
|
"step": 6725
|
|
},
|
|
{
|
|
"entropy": 5.526380920410157,
|
|
"epoch": 0.523633534331842,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004977626587147295,
|
|
"loss": 5.3984,
|
|
"mean_token_accuracy": 0.16687122136354446,
|
|
"num_tokens": 11688137.0,
|
|
"step": 6730
|
|
},
|
|
{
|
|
"entropy": 5.559792566299438,
|
|
"epoch": 0.5240225637035596,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.000497758758218688,
|
|
"loss": 5.5255,
|
|
"mean_token_accuracy": 0.16067289113998412,
|
|
"num_tokens": 11697236.0,
|
|
"step": 6735
|
|
},
|
|
{
|
|
"entropy": 5.669983386993408,
|
|
"epoch": 0.5244115930752772,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004977548543426368,
|
|
"loss": 5.5201,
|
|
"mean_token_accuracy": 0.159443636238575,
|
|
"num_tokens": 11706513.0,
|
|
"step": 6740
|
|
},
|
|
{
|
|
"entropy": 5.647953271865845,
|
|
"epoch": 0.5248006224469948,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004977509470866353,
|
|
"loss": 5.4815,
|
|
"mean_token_accuracy": 0.16161043643951417,
|
|
"num_tokens": 11715239.0,
|
|
"step": 6745
|
|
},
|
|
{
|
|
"entropy": 5.624539852142334,
|
|
"epoch": 0.5251896518187124,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004977470364507427,
|
|
"loss": 5.5067,
|
|
"mean_token_accuracy": 0.1691492259502411,
|
|
"num_tokens": 11724086.0,
|
|
"step": 6750
|
|
},
|
|
{
|
|
"entropy": 5.574176502227783,
|
|
"epoch": 0.5255786811904298,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004977431224350184,
|
|
"loss": 5.5399,
|
|
"mean_token_accuracy": 0.16304653882980347,
|
|
"num_tokens": 11731975.0,
|
|
"step": 6755
|
|
},
|
|
{
|
|
"entropy": 5.606770372390747,
|
|
"epoch": 0.5259677105621474,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004977392050395217,
|
|
"loss": 5.5292,
|
|
"mean_token_accuracy": 0.15769765973091127,
|
|
"num_tokens": 11741172.0,
|
|
"step": 6760
|
|
},
|
|
{
|
|
"entropy": 5.635431337356567,
|
|
"epoch": 0.526356739933865,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004977352842643121,
|
|
"loss": 5.497,
|
|
"mean_token_accuracy": 0.16328567042946815,
|
|
"num_tokens": 11750609.0,
|
|
"step": 6765
|
|
},
|
|
{
|
|
"entropy": 5.648671865463257,
|
|
"epoch": 0.5267457693055826,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.000497731360109449,
|
|
"loss": 5.4808,
|
|
"mean_token_accuracy": 0.164144603908062,
|
|
"num_tokens": 11758901.0,
|
|
"step": 6770
|
|
},
|
|
{
|
|
"entropy": 5.56562385559082,
|
|
"epoch": 0.5271347986773002,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004977274325749922,
|
|
"loss": 5.4329,
|
|
"mean_token_accuracy": 0.16389899849891662,
|
|
"num_tokens": 11767202.0,
|
|
"step": 6775
|
|
},
|
|
{
|
|
"entropy": 5.573253870010376,
|
|
"epoch": 0.5275238280490177,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004977235016610011,
|
|
"loss": 5.5385,
|
|
"mean_token_accuracy": 0.15641603320837022,
|
|
"num_tokens": 11776164.0,
|
|
"step": 6780
|
|
},
|
|
{
|
|
"entropy": 5.63574366569519,
|
|
"epoch": 0.5279128574207352,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004977195673675353,
|
|
"loss": 5.4803,
|
|
"mean_token_accuracy": 0.16279528737068177,
|
|
"num_tokens": 11784548.0,
|
|
"step": 6785
|
|
},
|
|
{
|
|
"entropy": 5.597996187210083,
|
|
"epoch": 0.5283018867924528,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004977156296946545,
|
|
"loss": 5.5534,
|
|
"mean_token_accuracy": 0.15933460593223572,
|
|
"num_tokens": 11793249.0,
|
|
"step": 6790
|
|
},
|
|
{
|
|
"entropy": 5.689667177200318,
|
|
"epoch": 0.5286909161641704,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004977116886424187,
|
|
"loss": 5.6144,
|
|
"mean_token_accuracy": 0.14791540801525116,
|
|
"num_tokens": 11801512.0,
|
|
"step": 6795
|
|
},
|
|
{
|
|
"entropy": 5.639977645874024,
|
|
"epoch": 0.529079945535888,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004977077442108873,
|
|
"loss": 5.4758,
|
|
"mean_token_accuracy": 0.16063254177570344,
|
|
"num_tokens": 11810248.0,
|
|
"step": 6800
|
|
},
|
|
{
|
|
"entropy": 5.584291219711304,
|
|
"epoch": 0.5294689749076055,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004977037964001204,
|
|
"loss": 5.4666,
|
|
"mean_token_accuracy": 0.16245136857032777,
|
|
"num_tokens": 11819190.0,
|
|
"step": 6805
|
|
},
|
|
{
|
|
"entropy": 5.538795900344849,
|
|
"epoch": 0.5298580042793231,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.000497699845210178,
|
|
"loss": 5.5398,
|
|
"mean_token_accuracy": 0.15167467221617698,
|
|
"num_tokens": 11827585.0,
|
|
"step": 6810
|
|
},
|
|
{
|
|
"entropy": 5.7072672843933105,
|
|
"epoch": 0.5302470336510406,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004976958906411197,
|
|
"loss": 5.5459,
|
|
"mean_token_accuracy": 0.1585001215338707,
|
|
"num_tokens": 11836256.0,
|
|
"step": 6815
|
|
},
|
|
{
|
|
"entropy": 5.716243410110474,
|
|
"epoch": 0.5306360630227582,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004976919326930059,
|
|
"loss": 5.6621,
|
|
"mean_token_accuracy": 0.1554935097694397,
|
|
"num_tokens": 11845022.0,
|
|
"step": 6820
|
|
},
|
|
{
|
|
"entropy": 5.5915556907653805,
|
|
"epoch": 0.5310250923944758,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004976879713658964,
|
|
"loss": 5.5293,
|
|
"mean_token_accuracy": 0.15867503434419633,
|
|
"num_tokens": 11853289.0,
|
|
"step": 6825
|
|
},
|
|
{
|
|
"entropy": 5.57533483505249,
|
|
"epoch": 0.5314141217661933,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004976840066598514,
|
|
"loss": 5.4742,
|
|
"mean_token_accuracy": 0.16293567717075347,
|
|
"num_tokens": 11861589.0,
|
|
"step": 6830
|
|
},
|
|
{
|
|
"entropy": 5.715223932266236,
|
|
"epoch": 0.5318031511379109,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004976800385749309,
|
|
"loss": 5.5798,
|
|
"mean_token_accuracy": 0.15770153254270552,
|
|
"num_tokens": 11870313.0,
|
|
"step": 6835
|
|
},
|
|
{
|
|
"entropy": 5.734091663360596,
|
|
"epoch": 0.5321921805096285,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004976760671111954,
|
|
"loss": 5.5738,
|
|
"mean_token_accuracy": 0.15089233294129373,
|
|
"num_tokens": 11879558.0,
|
|
"step": 6840
|
|
},
|
|
{
|
|
"entropy": 5.651639175415039,
|
|
"epoch": 0.532581209881346,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.000497672092268705,
|
|
"loss": 5.5776,
|
|
"mean_token_accuracy": 0.15512731820344924,
|
|
"num_tokens": 11887951.0,
|
|
"step": 6845
|
|
},
|
|
{
|
|
"entropy": 5.729362916946411,
|
|
"epoch": 0.5329702392530636,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.00049766811404752,
|
|
"loss": 5.7686,
|
|
"mean_token_accuracy": 0.15023297369480132,
|
|
"num_tokens": 11896900.0,
|
|
"step": 6850
|
|
},
|
|
{
|
|
"entropy": 5.703069496154785,
|
|
"epoch": 0.5333592686247812,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004976641324477008,
|
|
"loss": 5.5873,
|
|
"mean_token_accuracy": 0.1571554109454155,
|
|
"num_tokens": 11905681.0,
|
|
"step": 6855
|
|
},
|
|
{
|
|
"entropy": 5.608556461334229,
|
|
"epoch": 0.5337482979964987,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004976601474693077,
|
|
"loss": 5.5402,
|
|
"mean_token_accuracy": 0.15932610929012297,
|
|
"num_tokens": 11914662.0,
|
|
"step": 6860
|
|
},
|
|
{
|
|
"entropy": 5.5953371047973635,
|
|
"epoch": 0.5341373273682163,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004976561591124014,
|
|
"loss": 5.5401,
|
|
"mean_token_accuracy": 0.16420037299394608,
|
|
"num_tokens": 11923298.0,
|
|
"step": 6865
|
|
},
|
|
{
|
|
"entropy": 5.679533910751343,
|
|
"epoch": 0.5345263567399339,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004976521673770421,
|
|
"loss": 5.4428,
|
|
"mean_token_accuracy": 0.16081129461526872,
|
|
"num_tokens": 11932206.0,
|
|
"step": 6870
|
|
},
|
|
{
|
|
"entropy": 5.593166303634644,
|
|
"epoch": 0.5349153861116515,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004976481722632907,
|
|
"loss": 5.5182,
|
|
"mean_token_accuracy": 0.16239935159683228,
|
|
"num_tokens": 11940786.0,
|
|
"step": 6875
|
|
},
|
|
{
|
|
"entropy": 5.602063179016113,
|
|
"epoch": 0.535304415483369,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004976441737712076,
|
|
"loss": 5.5302,
|
|
"mean_token_accuracy": 0.15598469376564025,
|
|
"num_tokens": 11949619.0,
|
|
"step": 6880
|
|
},
|
|
{
|
|
"entropy": 5.618106126785278,
|
|
"epoch": 0.5356934448550865,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.0004976401719008536,
|
|
"loss": 5.4673,
|
|
"mean_token_accuracy": 0.16513773053884506,
|
|
"num_tokens": 11957696.0,
|
|
"step": 6885
|
|
},
|
|
{
|
|
"entropy": 5.6020430564880375,
|
|
"epoch": 0.5360824742268041,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004976361666522893,
|
|
"loss": 5.4777,
|
|
"mean_token_accuracy": 0.16478777974843978,
|
|
"num_tokens": 11965622.0,
|
|
"step": 6890
|
|
},
|
|
{
|
|
"entropy": 5.564819049835205,
|
|
"epoch": 0.5364715035985217,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004976321580255755,
|
|
"loss": 5.5604,
|
|
"mean_token_accuracy": 0.15686802566051483,
|
|
"num_tokens": 11973969.0,
|
|
"step": 6895
|
|
},
|
|
{
|
|
"entropy": 5.735695314407349,
|
|
"epoch": 0.5368605329702393,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004976281460207731,
|
|
"loss": 5.5424,
|
|
"mean_token_accuracy": 0.1604687198996544,
|
|
"num_tokens": 11982469.0,
|
|
"step": 6900
|
|
},
|
|
{
|
|
"entropy": 5.748460721969605,
|
|
"epoch": 0.5372495623419569,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.000497624130637943,
|
|
"loss": 5.6423,
|
|
"mean_token_accuracy": 0.15869580954313278,
|
|
"num_tokens": 11990656.0,
|
|
"step": 6905
|
|
},
|
|
{
|
|
"entropy": 5.631741619110107,
|
|
"epoch": 0.5376385917136743,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.000497620111877146,
|
|
"loss": 5.6412,
|
|
"mean_token_accuracy": 0.15766993165016174,
|
|
"num_tokens": 11999394.0,
|
|
"step": 6910
|
|
},
|
|
{
|
|
"entropy": 5.693097543716431,
|
|
"epoch": 0.5380276210853919,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004976160897384431,
|
|
"loss": 5.5945,
|
|
"mean_token_accuracy": 0.1619994305074215,
|
|
"num_tokens": 12007692.0,
|
|
"step": 6915
|
|
},
|
|
{
|
|
"entropy": 5.696098041534424,
|
|
"epoch": 0.5384166504571095,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004976120642218955,
|
|
"loss": 5.581,
|
|
"mean_token_accuracy": 0.15603196769952773,
|
|
"num_tokens": 12016038.0,
|
|
"step": 6920
|
|
},
|
|
{
|
|
"entropy": 5.663388681411743,
|
|
"epoch": 0.5388056798288271,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.000497608035327564,
|
|
"loss": 5.6578,
|
|
"mean_token_accuracy": 0.15578502416610718,
|
|
"num_tokens": 12024504.0,
|
|
"step": 6925
|
|
},
|
|
{
|
|
"entropy": 5.620071315765381,
|
|
"epoch": 0.5391947092005447,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.00049760400305551,
|
|
"loss": 5.5747,
|
|
"mean_token_accuracy": 0.1651473879814148,
|
|
"num_tokens": 12032935.0,
|
|
"step": 6930
|
|
},
|
|
{
|
|
"entropy": 5.692807579040528,
|
|
"epoch": 0.5395837385722622,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004975999674057944,
|
|
"loss": 5.6058,
|
|
"mean_token_accuracy": 0.1548255831003189,
|
|
"num_tokens": 12041907.0,
|
|
"step": 6935
|
|
},
|
|
{
|
|
"entropy": 5.632751417160034,
|
|
"epoch": 0.5399727679439797,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004975959283784787,
|
|
"loss": 5.4339,
|
|
"mean_token_accuracy": 0.1649518758058548,
|
|
"num_tokens": 12050528.0,
|
|
"step": 6940
|
|
},
|
|
{
|
|
"entropy": 5.575006771087646,
|
|
"epoch": 0.5403617973156973,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004975918859736241,
|
|
"loss": 5.4231,
|
|
"mean_token_accuracy": 0.16248443573713303,
|
|
"num_tokens": 12059221.0,
|
|
"step": 6945
|
|
},
|
|
{
|
|
"entropy": 5.634440135955811,
|
|
"epoch": 0.5407508266874149,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004975878401912919,
|
|
"loss": 5.6479,
|
|
"mean_token_accuracy": 0.15099793821573257,
|
|
"num_tokens": 12068131.0,
|
|
"step": 6950
|
|
},
|
|
{
|
|
"entropy": 5.661639404296875,
|
|
"epoch": 0.5411398560591325,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004975837910315436,
|
|
"loss": 5.5298,
|
|
"mean_token_accuracy": 0.1661975249648094,
|
|
"num_tokens": 12076521.0,
|
|
"step": 6955
|
|
},
|
|
{
|
|
"entropy": 5.66230411529541,
|
|
"epoch": 0.54152888543085,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004975797384944405,
|
|
"loss": 5.7098,
|
|
"mean_token_accuracy": 0.15018136128783227,
|
|
"num_tokens": 12085306.0,
|
|
"step": 6960
|
|
},
|
|
{
|
|
"entropy": 5.655632781982422,
|
|
"epoch": 0.5419179148025676,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.000497575682580044,
|
|
"loss": 5.4907,
|
|
"mean_token_accuracy": 0.15574343353509904,
|
|
"num_tokens": 12094409.0,
|
|
"step": 6965
|
|
},
|
|
{
|
|
"entropy": 5.595790147781372,
|
|
"epoch": 0.5423069441742852,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.000497571623288416,
|
|
"loss": 5.5227,
|
|
"mean_token_accuracy": 0.15902038514614106,
|
|
"num_tokens": 12103385.0,
|
|
"step": 6970
|
|
},
|
|
{
|
|
"entropy": 5.695128440856934,
|
|
"epoch": 0.5426959735460027,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004975675606196177,
|
|
"loss": 5.6476,
|
|
"mean_token_accuracy": 0.15420727133750917,
|
|
"num_tokens": 12112452.0,
|
|
"step": 6975
|
|
},
|
|
{
|
|
"entropy": 5.769511127471924,
|
|
"epoch": 0.5430850029177203,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.000497563494573711,
|
|
"loss": 5.6461,
|
|
"mean_token_accuracy": 0.15349312052130698,
|
|
"num_tokens": 12120918.0,
|
|
"step": 6980
|
|
},
|
|
{
|
|
"entropy": 5.665116882324218,
|
|
"epoch": 0.5434740322894378,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004975594251507575,
|
|
"loss": 5.592,
|
|
"mean_token_accuracy": 0.1524340584874153,
|
|
"num_tokens": 12129797.0,
|
|
"step": 6985
|
|
},
|
|
{
|
|
"entropy": 5.638438987731933,
|
|
"epoch": 0.5438630616611554,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.000497555352350819,
|
|
"loss": 5.5875,
|
|
"mean_token_accuracy": 0.1590471237897873,
|
|
"num_tokens": 12139245.0,
|
|
"step": 6990
|
|
},
|
|
{
|
|
"entropy": 5.724023914337158,
|
|
"epoch": 0.544252091032873,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004975512761739572,
|
|
"loss": 5.753,
|
|
"mean_token_accuracy": 0.15055884122848512,
|
|
"num_tokens": 12147409.0,
|
|
"step": 6995
|
|
},
|
|
{
|
|
"entropy": 5.770619010925293,
|
|
"epoch": 0.5446411204045906,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.000497547196620234,
|
|
"loss": 5.5615,
|
|
"mean_token_accuracy": 0.16063691973686217,
|
|
"num_tokens": 12156121.0,
|
|
"step": 7000
|
|
},
|
|
{
|
|
"entropy": 5.601393699645996,
|
|
"epoch": 0.5450301497763081,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004975431136897114,
|
|
"loss": 5.4546,
|
|
"mean_token_accuracy": 0.15758006274700165,
|
|
"num_tokens": 12165307.0,
|
|
"step": 7005
|
|
},
|
|
{
|
|
"entropy": 5.608690309524536,
|
|
"epoch": 0.5454191791480256,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004975390273824512,
|
|
"loss": 5.5458,
|
|
"mean_token_accuracy": 0.1556534193456173,
|
|
"num_tokens": 12173899.0,
|
|
"step": 7010
|
|
},
|
|
{
|
|
"entropy": 5.594245529174804,
|
|
"epoch": 0.5458082085197432,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004975349376985155,
|
|
"loss": 5.532,
|
|
"mean_token_accuracy": 0.157239693403244,
|
|
"num_tokens": 12182898.0,
|
|
"step": 7015
|
|
},
|
|
{
|
|
"entropy": 5.639141654968261,
|
|
"epoch": 0.5461972378914608,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004975308446379663,
|
|
"loss": 5.4257,
|
|
"mean_token_accuracy": 0.1626703605055809,
|
|
"num_tokens": 12191500.0,
|
|
"step": 7020
|
|
},
|
|
{
|
|
"entropy": 5.6254807472229,
|
|
"epoch": 0.5465862672631784,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 0.0004975267482008657,
|
|
"loss": 5.5746,
|
|
"mean_token_accuracy": 0.1632894828915596,
|
|
"num_tokens": 12199420.0,
|
|
"step": 7025
|
|
},
|
|
{
|
|
"entropy": 5.611004114151001,
|
|
"epoch": 0.546975296634896,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.000497522648387276,
|
|
"loss": 5.4928,
|
|
"mean_token_accuracy": 0.16589215099811555,
|
|
"num_tokens": 12207676.0,
|
|
"step": 7030
|
|
},
|
|
{
|
|
"entropy": 5.597789764404297,
|
|
"epoch": 0.5473643260066134,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004975185451972592,
|
|
"loss": 5.5569,
|
|
"mean_token_accuracy": 0.15775526612997054,
|
|
"num_tokens": 12216248.0,
|
|
"step": 7035
|
|
},
|
|
{
|
|
"entropy": 5.665650224685669,
|
|
"epoch": 0.547753355378331,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004975144386308776,
|
|
"loss": 5.588,
|
|
"mean_token_accuracy": 0.15302129238843917,
|
|
"num_tokens": 12224588.0,
|
|
"step": 7040
|
|
},
|
|
{
|
|
"entropy": 5.739396286010742,
|
|
"epoch": 0.5481423847500486,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004975103286881936,
|
|
"loss": 5.5993,
|
|
"mean_token_accuracy": 0.15411234349012376,
|
|
"num_tokens": 12234093.0,
|
|
"step": 7045
|
|
},
|
|
{
|
|
"entropy": 5.782606601715088,
|
|
"epoch": 0.5485314141217662,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004975062153692696,
|
|
"loss": 5.5289,
|
|
"mean_token_accuracy": 0.16654838025569915,
|
|
"num_tokens": 12242164.0,
|
|
"step": 7050
|
|
},
|
|
{
|
|
"entropy": 5.646966361999512,
|
|
"epoch": 0.5489204434934838,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004975020986741678,
|
|
"loss": 5.6246,
|
|
"mean_token_accuracy": 0.15668172687292098,
|
|
"num_tokens": 12251204.0,
|
|
"step": 7055
|
|
},
|
|
{
|
|
"entropy": 5.668913650512695,
|
|
"epoch": 0.5493094728652014,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004974979786029509,
|
|
"loss": 5.5663,
|
|
"mean_token_accuracy": 0.1603537067770958,
|
|
"num_tokens": 12259809.0,
|
|
"step": 7060
|
|
},
|
|
{
|
|
"entropy": 5.653614330291748,
|
|
"epoch": 0.5496985022369189,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004974938551556814,
|
|
"loss": 5.5587,
|
|
"mean_token_accuracy": 0.16657759249210358,
|
|
"num_tokens": 12268668.0,
|
|
"step": 7065
|
|
},
|
|
{
|
|
"entropy": 5.587209415435791,
|
|
"epoch": 0.5500875316086364,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004974897283324217,
|
|
"loss": 5.5027,
|
|
"mean_token_accuracy": 0.16190332025289536,
|
|
"num_tokens": 12276823.0,
|
|
"step": 7070
|
|
},
|
|
{
|
|
"entropy": 5.495704174041748,
|
|
"epoch": 0.550476560980354,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004974855981332343,
|
|
"loss": 5.4501,
|
|
"mean_token_accuracy": 0.16237061023712157,
|
|
"num_tokens": 12285950.0,
|
|
"step": 7075
|
|
},
|
|
{
|
|
"entropy": 5.627369546890259,
|
|
"epoch": 0.5508655903520716,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004974814645581823,
|
|
"loss": 5.5635,
|
|
"mean_token_accuracy": 0.15469660311937333,
|
|
"num_tokens": 12295265.0,
|
|
"step": 7080
|
|
},
|
|
{
|
|
"entropy": 5.76141324043274,
|
|
"epoch": 0.5512546197237892,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.0004974773276073282,
|
|
"loss": 5.5738,
|
|
"mean_token_accuracy": 0.15849540680646895,
|
|
"num_tokens": 12303649.0,
|
|
"step": 7085
|
|
},
|
|
{
|
|
"entropy": 5.638611364364624,
|
|
"epoch": 0.5516436490955067,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004974731872807347,
|
|
"loss": 5.6248,
|
|
"mean_token_accuracy": 0.15033020302653313,
|
|
"num_tokens": 12313303.0,
|
|
"step": 7090
|
|
},
|
|
{
|
|
"entropy": 5.6014965057373045,
|
|
"epoch": 0.5520326784672243,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004974690435784647,
|
|
"loss": 5.5833,
|
|
"mean_token_accuracy": 0.16375116258859634,
|
|
"num_tokens": 12321692.0,
|
|
"step": 7095
|
|
},
|
|
{
|
|
"entropy": 5.572794961929321,
|
|
"epoch": 0.5524217078389418,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004974648965005811,
|
|
"loss": 5.3883,
|
|
"mean_token_accuracy": 0.1655963644385338,
|
|
"num_tokens": 12329908.0,
|
|
"step": 7100
|
|
},
|
|
{
|
|
"entropy": 5.638770723342896,
|
|
"epoch": 0.5528107372106594,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004974607460471466,
|
|
"loss": 5.5623,
|
|
"mean_token_accuracy": 0.15805137604475022,
|
|
"num_tokens": 12339270.0,
|
|
"step": 7105
|
|
},
|
|
{
|
|
"entropy": 5.664997816085815,
|
|
"epoch": 0.553199766582377,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004974565922182246,
|
|
"loss": 5.4481,
|
|
"mean_token_accuracy": 0.15830651968717574,
|
|
"num_tokens": 12347586.0,
|
|
"step": 7110
|
|
},
|
|
{
|
|
"entropy": 5.583152627944946,
|
|
"epoch": 0.5535887959540945,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004974524350138777,
|
|
"loss": 5.4329,
|
|
"mean_token_accuracy": 0.15977163314819337,
|
|
"num_tokens": 12356291.0,
|
|
"step": 7115
|
|
},
|
|
{
|
|
"entropy": 5.618222665786743,
|
|
"epoch": 0.5539778253258121,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004974482744341693,
|
|
"loss": 5.6092,
|
|
"mean_token_accuracy": 0.1476268246769905,
|
|
"num_tokens": 12364948.0,
|
|
"step": 7120
|
|
},
|
|
{
|
|
"entropy": 5.7117523670196535,
|
|
"epoch": 0.5543668546975297,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004974441104791624,
|
|
"loss": 5.5624,
|
|
"mean_token_accuracy": 0.15631393045186998,
|
|
"num_tokens": 12373497.0,
|
|
"step": 7125
|
|
},
|
|
{
|
|
"entropy": 5.684345865249634,
|
|
"epoch": 0.5547558840692473,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004974399431489201,
|
|
"loss": 5.5101,
|
|
"mean_token_accuracy": 0.15973858088254927,
|
|
"num_tokens": 12382198.0,
|
|
"step": 7130
|
|
},
|
|
{
|
|
"entropy": 5.554830026626587,
|
|
"epoch": 0.5551449134409648,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004974357724435057,
|
|
"loss": 5.4866,
|
|
"mean_token_accuracy": 0.1644471228122711,
|
|
"num_tokens": 12391122.0,
|
|
"step": 7135
|
|
},
|
|
{
|
|
"entropy": 5.525238418579102,
|
|
"epoch": 0.5555339428126823,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004974315983629825,
|
|
"loss": 5.4274,
|
|
"mean_token_accuracy": 0.16473395228385926,
|
|
"num_tokens": 12399338.0,
|
|
"step": 7140
|
|
},
|
|
{
|
|
"entropy": 5.615933656692505,
|
|
"epoch": 0.5559229721843999,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004974274209074139,
|
|
"loss": 5.5348,
|
|
"mean_token_accuracy": 0.14955220967531205,
|
|
"num_tokens": 12408561.0,
|
|
"step": 7145
|
|
},
|
|
{
|
|
"entropy": 5.596295118331909,
|
|
"epoch": 0.5563120015561175,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004974232400768632,
|
|
"loss": 5.4188,
|
|
"mean_token_accuracy": 0.16242959946393967,
|
|
"num_tokens": 12417727.0,
|
|
"step": 7150
|
|
},
|
|
{
|
|
"entropy": 5.614875650405883,
|
|
"epoch": 0.5567010309278351,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004974190558713939,
|
|
"loss": 5.4376,
|
|
"mean_token_accuracy": 0.16201478540897368,
|
|
"num_tokens": 12426446.0,
|
|
"step": 7155
|
|
},
|
|
{
|
|
"entropy": 5.5842243194580075,
|
|
"epoch": 0.5570900602995527,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004974148682910694,
|
|
"loss": 5.495,
|
|
"mean_token_accuracy": 0.16075697988271714,
|
|
"num_tokens": 12435124.0,
|
|
"step": 7160
|
|
},
|
|
{
|
|
"entropy": 5.619173288345337,
|
|
"epoch": 0.5574790896712701,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004974106773359533,
|
|
"loss": 5.6183,
|
|
"mean_token_accuracy": 0.15286070257425308,
|
|
"num_tokens": 12444073.0,
|
|
"step": 7165
|
|
},
|
|
{
|
|
"entropy": 5.716760969161987,
|
|
"epoch": 0.5578681190429877,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004974064830061091,
|
|
"loss": 5.5898,
|
|
"mean_token_accuracy": 0.1601371094584465,
|
|
"num_tokens": 12452419.0,
|
|
"step": 7170
|
|
},
|
|
{
|
|
"entropy": 5.706222009658814,
|
|
"epoch": 0.5582571484147053,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004974022853016006,
|
|
"loss": 5.5499,
|
|
"mean_token_accuracy": 0.15545956194400787,
|
|
"num_tokens": 12461488.0,
|
|
"step": 7175
|
|
},
|
|
{
|
|
"entropy": 5.609360027313232,
|
|
"epoch": 0.5586461777864229,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004973980842224913,
|
|
"loss": 5.4911,
|
|
"mean_token_accuracy": 0.15602228343486785,
|
|
"num_tokens": 12470344.0,
|
|
"step": 7180
|
|
},
|
|
{
|
|
"entropy": 5.649265336990356,
|
|
"epoch": 0.5590352071581405,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004973938797688452,
|
|
"loss": 5.4932,
|
|
"mean_token_accuracy": 0.15788175910711288,
|
|
"num_tokens": 12479189.0,
|
|
"step": 7185
|
|
},
|
|
{
|
|
"entropy": 5.640626525878906,
|
|
"epoch": 0.559424236529858,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004973896719407259,
|
|
"loss": 5.5243,
|
|
"mean_token_accuracy": 0.16059497147798538,
|
|
"num_tokens": 12488199.0,
|
|
"step": 7190
|
|
},
|
|
{
|
|
"entropy": 5.557397651672363,
|
|
"epoch": 0.5598132659015755,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004973854607381972,
|
|
"loss": 5.4083,
|
|
"mean_token_accuracy": 0.16683684289455414,
|
|
"num_tokens": 12496704.0,
|
|
"step": 7195
|
|
},
|
|
{
|
|
"entropy": 5.537837314605713,
|
|
"epoch": 0.5602022952732931,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004973812461613232,
|
|
"loss": 5.4111,
|
|
"mean_token_accuracy": 0.16901323050260544,
|
|
"num_tokens": 12504724.0,
|
|
"step": 7200
|
|
},
|
|
{
|
|
"entropy": 5.606007385253906,
|
|
"epoch": 0.5605913246450107,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004973770282101677,
|
|
"loss": 5.595,
|
|
"mean_token_accuracy": 0.15539490282535554,
|
|
"num_tokens": 12514614.0,
|
|
"step": 7205
|
|
},
|
|
{
|
|
"entropy": 5.725541639328003,
|
|
"epoch": 0.5609803540167283,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004973728068847947,
|
|
"loss": 5.6217,
|
|
"mean_token_accuracy": 0.1517338916659355,
|
|
"num_tokens": 12522744.0,
|
|
"step": 7210
|
|
},
|
|
{
|
|
"entropy": 5.629028463363648,
|
|
"epoch": 0.5613693833884458,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004973685821852684,
|
|
"loss": 5.5292,
|
|
"mean_token_accuracy": 0.16160846799612044,
|
|
"num_tokens": 12531783.0,
|
|
"step": 7215
|
|
},
|
|
{
|
|
"entropy": 5.619050025939941,
|
|
"epoch": 0.5617584127601634,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004973643541116528,
|
|
"loss": 5.5904,
|
|
"mean_token_accuracy": 0.1496799409389496,
|
|
"num_tokens": 12541768.0,
|
|
"step": 7220
|
|
},
|
|
{
|
|
"entropy": 5.7859978675842285,
|
|
"epoch": 0.562147442131881,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.000497360122664012,
|
|
"loss": 5.6416,
|
|
"mean_token_accuracy": 0.15416546911001205,
|
|
"num_tokens": 12550684.0,
|
|
"step": 7225
|
|
},
|
|
{
|
|
"entropy": 5.717968082427978,
|
|
"epoch": 0.5625364715035985,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004973558878424104,
|
|
"loss": 5.5466,
|
|
"mean_token_accuracy": 0.15934956967830657,
|
|
"num_tokens": 12559948.0,
|
|
"step": 7230
|
|
},
|
|
{
|
|
"entropy": 5.561044692993164,
|
|
"epoch": 0.5629255008753161,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004973516496469119,
|
|
"loss": 5.4869,
|
|
"mean_token_accuracy": 0.16337195932865142,
|
|
"num_tokens": 12568681.0,
|
|
"step": 7235
|
|
},
|
|
{
|
|
"entropy": 5.691223812103272,
|
|
"epoch": 0.5633145302470336,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004973474080775811,
|
|
"loss": 5.6114,
|
|
"mean_token_accuracy": 0.152906334400177,
|
|
"num_tokens": 12577724.0,
|
|
"step": 7240
|
|
},
|
|
{
|
|
"entropy": 5.76364803314209,
|
|
"epoch": 0.5637035596187512,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004973431631344824,
|
|
"loss": 5.5306,
|
|
"mean_token_accuracy": 0.15633030086755753,
|
|
"num_tokens": 12585994.0,
|
|
"step": 7245
|
|
},
|
|
{
|
|
"entropy": 5.6505897521972654,
|
|
"epoch": 0.5640925889904688,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00049733891481768,
|
|
"loss": 5.6015,
|
|
"mean_token_accuracy": 0.15584657341241837,
|
|
"num_tokens": 12595525.0,
|
|
"step": 7250
|
|
},
|
|
{
|
|
"entropy": 5.647922468185425,
|
|
"epoch": 0.5644816183621864,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004973346631272384,
|
|
"loss": 5.4333,
|
|
"mean_token_accuracy": 0.16841700673103333,
|
|
"num_tokens": 12603645.0,
|
|
"step": 7255
|
|
},
|
|
{
|
|
"entropy": 5.587335395812988,
|
|
"epoch": 0.5648706477339039,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004973304080632222,
|
|
"loss": 5.5055,
|
|
"mean_token_accuracy": 0.15742655992507934,
|
|
"num_tokens": 12612165.0,
|
|
"step": 7260
|
|
},
|
|
{
|
|
"entropy": 5.591152763366699,
|
|
"epoch": 0.5652596771056215,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.000497326149625696,
|
|
"loss": 5.4214,
|
|
"mean_token_accuracy": 0.16940227746963502,
|
|
"num_tokens": 12620678.0,
|
|
"step": 7265
|
|
},
|
|
{
|
|
"entropy": 5.681361198425293,
|
|
"epoch": 0.565648706477339,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004973218878147244,
|
|
"loss": 5.6155,
|
|
"mean_token_accuracy": 0.15588987991213799,
|
|
"num_tokens": 12628745.0,
|
|
"step": 7270
|
|
},
|
|
{
|
|
"entropy": 5.70417628288269,
|
|
"epoch": 0.5660377358490566,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004973176226303719,
|
|
"loss": 5.6584,
|
|
"mean_token_accuracy": 0.1473071962594986,
|
|
"num_tokens": 12637448.0,
|
|
"step": 7275
|
|
},
|
|
{
|
|
"entropy": 5.679449367523193,
|
|
"epoch": 0.5664267652207742,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004973133540727033,
|
|
"loss": 5.5324,
|
|
"mean_token_accuracy": 0.1581710919737816,
|
|
"num_tokens": 12645804.0,
|
|
"step": 7280
|
|
},
|
|
{
|
|
"entropy": 5.655721378326416,
|
|
"epoch": 0.5668157945924918,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004973090821417835,
|
|
"loss": 5.4942,
|
|
"mean_token_accuracy": 0.15874693989753724,
|
|
"num_tokens": 12654156.0,
|
|
"step": 7285
|
|
},
|
|
{
|
|
"entropy": 5.6041888236999515,
|
|
"epoch": 0.5672048239642093,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004973048068376772,
|
|
"loss": 5.4653,
|
|
"mean_token_accuracy": 0.16248227059841155,
|
|
"num_tokens": 12662271.0,
|
|
"step": 7290
|
|
},
|
|
{
|
|
"entropy": 5.724769163131714,
|
|
"epoch": 0.5675938533359268,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004973005281604492,
|
|
"loss": 5.6371,
|
|
"mean_token_accuracy": 0.15151395946741103,
|
|
"num_tokens": 12671016.0,
|
|
"step": 7295
|
|
},
|
|
{
|
|
"entropy": 5.633071088790894,
|
|
"epoch": 0.5679828827076444,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004972962461101646,
|
|
"loss": 5.5932,
|
|
"mean_token_accuracy": 0.15309520661830903,
|
|
"num_tokens": 12679593.0,
|
|
"step": 7300
|
|
},
|
|
{
|
|
"entropy": 5.625471401214599,
|
|
"epoch": 0.568371912079362,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004972919606868883,
|
|
"loss": 5.5179,
|
|
"mean_token_accuracy": 0.16120276600122452,
|
|
"num_tokens": 12688715.0,
|
|
"step": 7305
|
|
},
|
|
{
|
|
"entropy": 5.643703126907349,
|
|
"epoch": 0.5687609414510796,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004972876718906852,
|
|
"loss": 5.5263,
|
|
"mean_token_accuracy": 0.15836018621921538,
|
|
"num_tokens": 12698078.0,
|
|
"step": 7310
|
|
},
|
|
{
|
|
"entropy": 5.5868239402771,
|
|
"epoch": 0.5691499708227972,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004972833797216206,
|
|
"loss": 5.5126,
|
|
"mean_token_accuracy": 0.16403855681419371,
|
|
"num_tokens": 12706375.0,
|
|
"step": 7315
|
|
},
|
|
{
|
|
"entropy": 5.724744892120361,
|
|
"epoch": 0.5695390001945146,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004972790841797595,
|
|
"loss": 5.7066,
|
|
"mean_token_accuracy": 0.15244438797235488,
|
|
"num_tokens": 12715727.0,
|
|
"step": 7320
|
|
},
|
|
{
|
|
"entropy": 5.67259030342102,
|
|
"epoch": 0.5699280295662322,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.000497274785265167,
|
|
"loss": 5.6122,
|
|
"mean_token_accuracy": 0.14762853384017943,
|
|
"num_tokens": 12725565.0,
|
|
"step": 7325
|
|
},
|
|
{
|
|
"entropy": 5.743588399887085,
|
|
"epoch": 0.5703170589379498,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004972704829779086,
|
|
"loss": 5.631,
|
|
"mean_token_accuracy": 0.15871698409318924,
|
|
"num_tokens": 12733498.0,
|
|
"step": 7330
|
|
},
|
|
{
|
|
"entropy": 5.620137357711792,
|
|
"epoch": 0.5707060883096674,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004972661773180492,
|
|
"loss": 5.4476,
|
|
"mean_token_accuracy": 0.1599652126431465,
|
|
"num_tokens": 12741635.0,
|
|
"step": 7335
|
|
},
|
|
{
|
|
"entropy": 5.520822048187256,
|
|
"epoch": 0.571095117681385,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004972618682856545,
|
|
"loss": 5.4631,
|
|
"mean_token_accuracy": 0.16328149437904357,
|
|
"num_tokens": 12750973.0,
|
|
"step": 7340
|
|
},
|
|
{
|
|
"entropy": 5.571967029571534,
|
|
"epoch": 0.5714841470531025,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004972575558807896,
|
|
"loss": 5.5372,
|
|
"mean_token_accuracy": 0.16574114114046096,
|
|
"num_tokens": 12759075.0,
|
|
"step": 7345
|
|
},
|
|
{
|
|
"entropy": 5.700579309463501,
|
|
"epoch": 0.57187317642482,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004972532401035201,
|
|
"loss": 5.5225,
|
|
"mean_token_accuracy": 0.15687755197286607,
|
|
"num_tokens": 12767485.0,
|
|
"step": 7350
|
|
},
|
|
{
|
|
"entropy": 5.705129623413086,
|
|
"epoch": 0.5722622057965376,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004972489209539114,
|
|
"loss": 5.4884,
|
|
"mean_token_accuracy": 0.16281367540359498,
|
|
"num_tokens": 12775128.0,
|
|
"step": 7355
|
|
},
|
|
{
|
|
"entropy": 5.561953735351563,
|
|
"epoch": 0.5726512351682552,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004972445984320292,
|
|
"loss": 5.4076,
|
|
"mean_token_accuracy": 0.1676819458603859,
|
|
"num_tokens": 12783243.0,
|
|
"step": 7360
|
|
},
|
|
{
|
|
"entropy": 5.649951601028443,
|
|
"epoch": 0.5730402645399728,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004972402725379388,
|
|
"loss": 5.6279,
|
|
"mean_token_accuracy": 0.16052431762218475,
|
|
"num_tokens": 12791613.0,
|
|
"step": 7365
|
|
},
|
|
{
|
|
"entropy": 5.6840691566467285,
|
|
"epoch": 0.5734292939116903,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.000497235943271706,
|
|
"loss": 5.559,
|
|
"mean_token_accuracy": 0.15703178942203522,
|
|
"num_tokens": 12799817.0,
|
|
"step": 7370
|
|
},
|
|
{
|
|
"entropy": 5.691116380691528,
|
|
"epoch": 0.5738183232834079,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004972316106333966,
|
|
"loss": 5.5644,
|
|
"mean_token_accuracy": 0.15355917811393738,
|
|
"num_tokens": 12808994.0,
|
|
"step": 7375
|
|
},
|
|
{
|
|
"entropy": 5.637736511230469,
|
|
"epoch": 0.5742073526551255,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004972272746230761,
|
|
"loss": 5.5256,
|
|
"mean_token_accuracy": 0.1580606669187546,
|
|
"num_tokens": 12817191.0,
|
|
"step": 7380
|
|
},
|
|
{
|
|
"entropy": 5.6404008865356445,
|
|
"epoch": 0.574596382026843,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004972229352408104,
|
|
"loss": 5.4956,
|
|
"mean_token_accuracy": 0.15748804658651352,
|
|
"num_tokens": 12825773.0,
|
|
"step": 7385
|
|
},
|
|
{
|
|
"entropy": 5.73073410987854,
|
|
"epoch": 0.5749854113985606,
|
|
"grad_norm": 2.6875,
|
|
"learning_rate": 0.0004972185924866655,
|
|
"loss": 5.5644,
|
|
"mean_token_accuracy": 0.16047893315553666,
|
|
"num_tokens": 12834489.0,
|
|
"step": 7390
|
|
},
|
|
{
|
|
"entropy": 5.677036237716675,
|
|
"epoch": 0.5753744407702781,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004972142463607071,
|
|
"loss": 5.5498,
|
|
"mean_token_accuracy": 0.1610588014125824,
|
|
"num_tokens": 12843179.0,
|
|
"step": 7395
|
|
},
|
|
{
|
|
"entropy": 5.7206519603729244,
|
|
"epoch": 0.5757634701419957,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004972098968630012,
|
|
"loss": 5.5736,
|
|
"mean_token_accuracy": 0.15535116493701934,
|
|
"num_tokens": 12851243.0,
|
|
"step": 7400
|
|
},
|
|
{
|
|
"entropy": 5.598516273498535,
|
|
"epoch": 0.5761524995137133,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004972055439936137,
|
|
"loss": 5.6291,
|
|
"mean_token_accuracy": 0.15630768090486527,
|
|
"num_tokens": 12860267.0,
|
|
"step": 7405
|
|
},
|
|
{
|
|
"entropy": 5.757432508468628,
|
|
"epoch": 0.5765415288854309,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004972011877526109,
|
|
"loss": 5.6497,
|
|
"mean_token_accuracy": 0.15755585208535194,
|
|
"num_tokens": 12870022.0,
|
|
"step": 7410
|
|
},
|
|
{
|
|
"entropy": 5.694835472106933,
|
|
"epoch": 0.5769305582571485,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004971968281400587,
|
|
"loss": 5.5952,
|
|
"mean_token_accuracy": 0.1492684304714203,
|
|
"num_tokens": 12879227.0,
|
|
"step": 7415
|
|
},
|
|
{
|
|
"entropy": 5.661354351043701,
|
|
"epoch": 0.5773195876288659,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004971924651560233,
|
|
"loss": 5.5483,
|
|
"mean_token_accuracy": 0.15837249904870987,
|
|
"num_tokens": 12888180.0,
|
|
"step": 7420
|
|
},
|
|
{
|
|
"entropy": 5.675881195068359,
|
|
"epoch": 0.5777086170005835,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004971880988005709,
|
|
"loss": 5.5394,
|
|
"mean_token_accuracy": 0.16022545620799064,
|
|
"num_tokens": 12896767.0,
|
|
"step": 7425
|
|
},
|
|
{
|
|
"entropy": 5.618383169174194,
|
|
"epoch": 0.5780976463723011,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004971837290737677,
|
|
"loss": 5.4341,
|
|
"mean_token_accuracy": 0.16697876006364823,
|
|
"num_tokens": 12904766.0,
|
|
"step": 7430
|
|
},
|
|
{
|
|
"entropy": 5.529607534408569,
|
|
"epoch": 0.5784866757440187,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004971793559756801,
|
|
"loss": 5.5357,
|
|
"mean_token_accuracy": 0.1580686628818512,
|
|
"num_tokens": 12913808.0,
|
|
"step": 7435
|
|
},
|
|
{
|
|
"entropy": 5.590646886825562,
|
|
"epoch": 0.5788757051157363,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004971749795063744,
|
|
"loss": 5.5143,
|
|
"mean_token_accuracy": 0.15939191728830338,
|
|
"num_tokens": 12923103.0,
|
|
"step": 7440
|
|
},
|
|
{
|
|
"entropy": 5.6191099166870115,
|
|
"epoch": 0.5792647344874537,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.000497170599665917,
|
|
"loss": 5.473,
|
|
"mean_token_accuracy": 0.16246490627527238,
|
|
"num_tokens": 12931168.0,
|
|
"step": 7445
|
|
},
|
|
{
|
|
"entropy": 5.548571968078614,
|
|
"epoch": 0.5796537638591713,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004971662164543743,
|
|
"loss": 5.5678,
|
|
"mean_token_accuracy": 0.16391166001558305,
|
|
"num_tokens": 12939875.0,
|
|
"step": 7450
|
|
},
|
|
{
|
|
"entropy": 5.61009259223938,
|
|
"epoch": 0.5800427932308889,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004971618298718131,
|
|
"loss": 5.4683,
|
|
"mean_token_accuracy": 0.16916644275188447,
|
|
"num_tokens": 12947883.0,
|
|
"step": 7455
|
|
},
|
|
{
|
|
"entropy": 5.789393091201783,
|
|
"epoch": 0.5804318226026065,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004971574399182995,
|
|
"loss": 5.7034,
|
|
"mean_token_accuracy": 0.14763562753796577,
|
|
"num_tokens": 12956940.0,
|
|
"step": 7460
|
|
},
|
|
{
|
|
"entropy": 5.626276636123658,
|
|
"epoch": 0.5808208519743241,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004971530465939005,
|
|
"loss": 5.4359,
|
|
"mean_token_accuracy": 0.1634249910712242,
|
|
"num_tokens": 12965003.0,
|
|
"step": 7465
|
|
},
|
|
{
|
|
"entropy": 5.603636360168457,
|
|
"epoch": 0.5812098813460417,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004971486498986825,
|
|
"loss": 5.4668,
|
|
"mean_token_accuracy": 0.16253004223108292,
|
|
"num_tokens": 12973323.0,
|
|
"step": 7470
|
|
},
|
|
{
|
|
"entropy": 5.600870990753174,
|
|
"epoch": 0.5815989107177592,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004971442498327124,
|
|
"loss": 5.5004,
|
|
"mean_token_accuracy": 0.16327155977487565,
|
|
"num_tokens": 12982654.0,
|
|
"step": 7475
|
|
},
|
|
{
|
|
"entropy": 5.62065544128418,
|
|
"epoch": 0.5819879400894767,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004971398463960568,
|
|
"loss": 5.5431,
|
|
"mean_token_accuracy": 0.16062046885490416,
|
|
"num_tokens": 12991781.0,
|
|
"step": 7480
|
|
},
|
|
{
|
|
"entropy": 5.694522523880005,
|
|
"epoch": 0.5823769694611943,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004971354395887827,
|
|
"loss": 5.6288,
|
|
"mean_token_accuracy": 0.15725939124822616,
|
|
"num_tokens": 13000539.0,
|
|
"step": 7485
|
|
},
|
|
{
|
|
"entropy": 5.702580308914184,
|
|
"epoch": 0.5827659988329119,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004971310294109569,
|
|
"loss": 5.4965,
|
|
"mean_token_accuracy": 0.1644050046801567,
|
|
"num_tokens": 13008638.0,
|
|
"step": 7490
|
|
},
|
|
{
|
|
"entropy": 5.61459527015686,
|
|
"epoch": 0.5831550282046295,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004971266158626461,
|
|
"loss": 5.4854,
|
|
"mean_token_accuracy": 0.16098864525556564,
|
|
"num_tokens": 13017217.0,
|
|
"step": 7495
|
|
},
|
|
{
|
|
"entropy": 5.55291600227356,
|
|
"epoch": 0.583544057576347,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004971221989439177,
|
|
"loss": 5.5311,
|
|
"mean_token_accuracy": 0.15793122053146363,
|
|
"num_tokens": 13025278.0,
|
|
"step": 7500
|
|
},
|
|
{
|
|
"entropy": 5.603717041015625,
|
|
"epoch": 0.5839330869480646,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004971177786548384,
|
|
"loss": 5.5575,
|
|
"mean_token_accuracy": 0.15922897905111313,
|
|
"num_tokens": 13034484.0,
|
|
"step": 7505
|
|
},
|
|
{
|
|
"entropy": 5.727790403366089,
|
|
"epoch": 0.5843221163197821,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004971133549954753,
|
|
"loss": 5.629,
|
|
"mean_token_accuracy": 0.1499597117304802,
|
|
"num_tokens": 13042831.0,
|
|
"step": 7510
|
|
},
|
|
{
|
|
"entropy": 5.727259254455566,
|
|
"epoch": 0.5847111456914997,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004971089279658954,
|
|
"loss": 5.5922,
|
|
"mean_token_accuracy": 0.15369003713130952,
|
|
"num_tokens": 13051614.0,
|
|
"step": 7515
|
|
},
|
|
{
|
|
"entropy": 5.634461355209351,
|
|
"epoch": 0.5851001750632173,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004971044975661663,
|
|
"loss": 5.5506,
|
|
"mean_token_accuracy": 0.15672828108072281,
|
|
"num_tokens": 13060179.0,
|
|
"step": 7520
|
|
},
|
|
{
|
|
"entropy": 5.575223398208618,
|
|
"epoch": 0.5854892044349348,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004971000637963549,
|
|
"loss": 5.4628,
|
|
"mean_token_accuracy": 0.1732001096010208,
|
|
"num_tokens": 13068328.0,
|
|
"step": 7525
|
|
},
|
|
{
|
|
"entropy": 5.537419319152832,
|
|
"epoch": 0.5858782338066524,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004970956266565285,
|
|
"loss": 5.5145,
|
|
"mean_token_accuracy": 0.1610039070248604,
|
|
"num_tokens": 13076879.0,
|
|
"step": 7530
|
|
},
|
|
{
|
|
"entropy": 5.68983154296875,
|
|
"epoch": 0.58626726317837,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004970911861467544,
|
|
"loss": 5.5583,
|
|
"mean_token_accuracy": 0.1535510741174221,
|
|
"num_tokens": 13085123.0,
|
|
"step": 7535
|
|
},
|
|
{
|
|
"entropy": 5.558996152877808,
|
|
"epoch": 0.5866562925500876,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004970867422671002,
|
|
"loss": 5.5188,
|
|
"mean_token_accuracy": 0.16626303195953368,
|
|
"num_tokens": 13093884.0,
|
|
"step": 7540
|
|
},
|
|
{
|
|
"entropy": 5.70104022026062,
|
|
"epoch": 0.5870453219218051,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.000497082295017633,
|
|
"loss": 5.5751,
|
|
"mean_token_accuracy": 0.16042875796556472,
|
|
"num_tokens": 13102581.0,
|
|
"step": 7545
|
|
},
|
|
{
|
|
"entropy": 5.683917903900147,
|
|
"epoch": 0.5874343512935226,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004970778443984206,
|
|
"loss": 5.5609,
|
|
"mean_token_accuracy": 0.15632733553647996,
|
|
"num_tokens": 13111307.0,
|
|
"step": 7550
|
|
},
|
|
{
|
|
"entropy": 5.681131172180176,
|
|
"epoch": 0.5878233806652402,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004970733904095303,
|
|
"loss": 5.5639,
|
|
"mean_token_accuracy": 0.15917730927467347,
|
|
"num_tokens": 13119279.0,
|
|
"step": 7555
|
|
},
|
|
{
|
|
"entropy": 5.6647991180419925,
|
|
"epoch": 0.5882124100369578,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004970689330510298,
|
|
"loss": 5.5906,
|
|
"mean_token_accuracy": 0.1582401856780052,
|
|
"num_tokens": 13127753.0,
|
|
"step": 7560
|
|
},
|
|
{
|
|
"entropy": 5.680768918991089,
|
|
"epoch": 0.5886014394086754,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004970644723229868,
|
|
"loss": 5.636,
|
|
"mean_token_accuracy": 0.15444589108228685,
|
|
"num_tokens": 13136881.0,
|
|
"step": 7565
|
|
},
|
|
{
|
|
"entropy": 5.652431774139404,
|
|
"epoch": 0.588990468780393,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004970600082254687,
|
|
"loss": 5.4991,
|
|
"mean_token_accuracy": 0.15578779727220535,
|
|
"num_tokens": 13145291.0,
|
|
"step": 7570
|
|
},
|
|
{
|
|
"entropy": 5.579540681838989,
|
|
"epoch": 0.5893794981521104,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004970555407585436,
|
|
"loss": 5.4579,
|
|
"mean_token_accuracy": 0.16331358551979064,
|
|
"num_tokens": 13153560.0,
|
|
"step": 7575
|
|
},
|
|
{
|
|
"entropy": 5.626413154602051,
|
|
"epoch": 0.589768527523828,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.000497051069922279,
|
|
"loss": 5.5139,
|
|
"mean_token_accuracy": 0.15920064300298692,
|
|
"num_tokens": 13162304.0,
|
|
"step": 7580
|
|
},
|
|
{
|
|
"entropy": 5.6824174404144285,
|
|
"epoch": 0.5901575568955456,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004970465957167429,
|
|
"loss": 5.5345,
|
|
"mean_token_accuracy": 0.16362176686525345,
|
|
"num_tokens": 13171404.0,
|
|
"step": 7585
|
|
},
|
|
{
|
|
"entropy": 5.739548587799073,
|
|
"epoch": 0.5905465862672632,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.000497042118142003,
|
|
"loss": 5.6142,
|
|
"mean_token_accuracy": 0.15650009736418724,
|
|
"num_tokens": 13180001.0,
|
|
"step": 7590
|
|
},
|
|
{
|
|
"entropy": 5.686169528961182,
|
|
"epoch": 0.5909356156389808,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004970376371981275,
|
|
"loss": 5.552,
|
|
"mean_token_accuracy": 0.15728999227285384,
|
|
"num_tokens": 13189749.0,
|
|
"step": 7595
|
|
},
|
|
{
|
|
"entropy": 5.586195945739746,
|
|
"epoch": 0.5913246450106983,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004970331528851842,
|
|
"loss": 5.5261,
|
|
"mean_token_accuracy": 0.16812347173690795,
|
|
"num_tokens": 13199169.0,
|
|
"step": 7600
|
|
},
|
|
{
|
|
"entropy": 5.562873315811157,
|
|
"epoch": 0.5917136743824158,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004970286652032412,
|
|
"loss": 5.4885,
|
|
"mean_token_accuracy": 0.16665935814380645,
|
|
"num_tokens": 13207014.0,
|
|
"step": 7605
|
|
},
|
|
{
|
|
"entropy": 5.640641927719116,
|
|
"epoch": 0.5921027037541334,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004970241741523667,
|
|
"loss": 5.4406,
|
|
"mean_token_accuracy": 0.1629709154367447,
|
|
"num_tokens": 13215333.0,
|
|
"step": 7610
|
|
},
|
|
{
|
|
"entropy": 5.642063808441162,
|
|
"epoch": 0.592491733125851,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004970196797326286,
|
|
"loss": 5.5707,
|
|
"mean_token_accuracy": 0.15491992235183716,
|
|
"num_tokens": 13223740.0,
|
|
"step": 7615
|
|
},
|
|
{
|
|
"entropy": 5.596137189865113,
|
|
"epoch": 0.5928807624975686,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004970151819440955,
|
|
"loss": 5.5128,
|
|
"mean_token_accuracy": 0.16230032742023467,
|
|
"num_tokens": 13232065.0,
|
|
"step": 7620
|
|
},
|
|
{
|
|
"entropy": 5.629691648483276,
|
|
"epoch": 0.5932697918692861,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004970106807868351,
|
|
"loss": 5.5009,
|
|
"mean_token_accuracy": 0.1631051391363144,
|
|
"num_tokens": 13241171.0,
|
|
"step": 7625
|
|
},
|
|
{
|
|
"entropy": 5.5375292778015135,
|
|
"epoch": 0.5936588212410037,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.000497006176260916,
|
|
"loss": 5.4181,
|
|
"mean_token_accuracy": 0.16693178415298462,
|
|
"num_tokens": 13249553.0,
|
|
"step": 7630
|
|
},
|
|
{
|
|
"entropy": 5.618206977844238,
|
|
"epoch": 0.5940478506127213,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004970016683664068,
|
|
"loss": 5.4889,
|
|
"mean_token_accuracy": 0.1628669649362564,
|
|
"num_tokens": 13258585.0,
|
|
"step": 7635
|
|
},
|
|
{
|
|
"entropy": 5.637617492675782,
|
|
"epoch": 0.5944368799844388,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004969971571033754,
|
|
"loss": 5.5552,
|
|
"mean_token_accuracy": 0.16011955440044404,
|
|
"num_tokens": 13267317.0,
|
|
"step": 7640
|
|
},
|
|
{
|
|
"entropy": 5.575131750106811,
|
|
"epoch": 0.5948259093561564,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004969926424718906,
|
|
"loss": 5.37,
|
|
"mean_token_accuracy": 0.16295740604400635,
|
|
"num_tokens": 13275705.0,
|
|
"step": 7645
|
|
},
|
|
{
|
|
"entropy": 5.6024312496185305,
|
|
"epoch": 0.5952149387278739,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004969881244720207,
|
|
"loss": 5.5182,
|
|
"mean_token_accuracy": 0.1615263268351555,
|
|
"num_tokens": 13284046.0,
|
|
"step": 7650
|
|
},
|
|
{
|
|
"entropy": 5.58196268081665,
|
|
"epoch": 0.5956039680995915,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004969836031038343,
|
|
"loss": 5.5,
|
|
"mean_token_accuracy": 0.16613336950540541,
|
|
"num_tokens": 13292451.0,
|
|
"step": 7655
|
|
},
|
|
{
|
|
"entropy": 5.714156723022461,
|
|
"epoch": 0.5959929974713091,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004969790783674002,
|
|
"loss": 5.6349,
|
|
"mean_token_accuracy": 0.1574876733124256,
|
|
"num_tokens": 13300788.0,
|
|
"step": 7660
|
|
},
|
|
{
|
|
"entropy": 5.666077136993408,
|
|
"epoch": 0.5963820268430267,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004969745502627868,
|
|
"loss": 5.5477,
|
|
"mean_token_accuracy": 0.16628242731094361,
|
|
"num_tokens": 13309235.0,
|
|
"step": 7665
|
|
},
|
|
{
|
|
"entropy": 5.58871488571167,
|
|
"epoch": 0.5967710562147442,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004969700187900629,
|
|
"loss": 5.4521,
|
|
"mean_token_accuracy": 0.1600484788417816,
|
|
"num_tokens": 13317331.0,
|
|
"step": 7670
|
|
},
|
|
{
|
|
"entropy": 5.575796985626221,
|
|
"epoch": 0.5971600855864618,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004969654839492973,
|
|
"loss": 5.4885,
|
|
"mean_token_accuracy": 0.1504474826157093,
|
|
"num_tokens": 13327296.0,
|
|
"step": 7675
|
|
},
|
|
{
|
|
"entropy": 5.673458480834961,
|
|
"epoch": 0.5975491149581793,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004969609457405588,
|
|
"loss": 5.5549,
|
|
"mean_token_accuracy": 0.15951465219259262,
|
|
"num_tokens": 13336650.0,
|
|
"step": 7680
|
|
},
|
|
{
|
|
"entropy": 5.641073751449585,
|
|
"epoch": 0.5979381443298969,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004969564041639163,
|
|
"loss": 5.5005,
|
|
"mean_token_accuracy": 0.15823953747749328,
|
|
"num_tokens": 13345353.0,
|
|
"step": 7685
|
|
},
|
|
{
|
|
"entropy": 5.656012964248657,
|
|
"epoch": 0.5983271737016145,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004969518592194386,
|
|
"loss": 5.5111,
|
|
"mean_token_accuracy": 0.16030848026275635,
|
|
"num_tokens": 13354302.0,
|
|
"step": 7690
|
|
},
|
|
{
|
|
"entropy": 5.549968671798706,
|
|
"epoch": 0.5987162030733321,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004969473109071946,
|
|
"loss": 5.4504,
|
|
"mean_token_accuracy": 0.163647423684597,
|
|
"num_tokens": 13362950.0,
|
|
"step": 7695
|
|
},
|
|
{
|
|
"entropy": 5.585221242904663,
|
|
"epoch": 0.5991052324450497,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004969427592272535,
|
|
"loss": 5.5745,
|
|
"mean_token_accuracy": 0.1560671731829643,
|
|
"num_tokens": 13371383.0,
|
|
"step": 7700
|
|
},
|
|
{
|
|
"entropy": 5.669369792938232,
|
|
"epoch": 0.5994942618167671,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004969382041796843,
|
|
"loss": 5.5383,
|
|
"mean_token_accuracy": 0.1628669172525406,
|
|
"num_tokens": 13379767.0,
|
|
"step": 7705
|
|
},
|
|
{
|
|
"entropy": 5.655380296707153,
|
|
"epoch": 0.5998832911884847,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.000496933645764556,
|
|
"loss": 5.5267,
|
|
"mean_token_accuracy": 0.15433267802000045,
|
|
"num_tokens": 13387970.0,
|
|
"step": 7710
|
|
},
|
|
{
|
|
"entropy": 5.545374393463135,
|
|
"epoch": 0.6002723205602023,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004969290839819381,
|
|
"loss": 5.4821,
|
|
"mean_token_accuracy": 0.16639994978904724,
|
|
"num_tokens": 13396605.0,
|
|
"step": 7715
|
|
},
|
|
{
|
|
"entropy": 5.582101249694825,
|
|
"epoch": 0.6006613499319199,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004969245188318994,
|
|
"loss": 5.4222,
|
|
"mean_token_accuracy": 0.16884092390537261,
|
|
"num_tokens": 13406028.0,
|
|
"step": 7720
|
|
},
|
|
{
|
|
"entropy": 5.643075370788575,
|
|
"epoch": 0.6010503793036375,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004969199503145093,
|
|
"loss": 5.4808,
|
|
"mean_token_accuracy": 0.16709552854299545,
|
|
"num_tokens": 13414927.0,
|
|
"step": 7725
|
|
},
|
|
{
|
|
"entropy": 5.538677787780761,
|
|
"epoch": 0.601439408675355,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004969153784298374,
|
|
"loss": 5.4197,
|
|
"mean_token_accuracy": 0.16179912090301513,
|
|
"num_tokens": 13423020.0,
|
|
"step": 7730
|
|
},
|
|
{
|
|
"entropy": 5.501712656021118,
|
|
"epoch": 0.6018284380470725,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004969108031779527,
|
|
"loss": 5.4259,
|
|
"mean_token_accuracy": 0.16240470558404924,
|
|
"num_tokens": 13431514.0,
|
|
"step": 7735
|
|
},
|
|
{
|
|
"entropy": 5.627806663513184,
|
|
"epoch": 0.6022174674187901,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004969062245589247,
|
|
"loss": 5.6042,
|
|
"mean_token_accuracy": 0.15487990602850915,
|
|
"num_tokens": 13440333.0,
|
|
"step": 7740
|
|
},
|
|
{
|
|
"entropy": 5.58061785697937,
|
|
"epoch": 0.6026064967905077,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.0004969016425728231,
|
|
"loss": 5.5314,
|
|
"mean_token_accuracy": 0.1586664631962776,
|
|
"num_tokens": 13448841.0,
|
|
"step": 7745
|
|
},
|
|
{
|
|
"entropy": 5.669718933105469,
|
|
"epoch": 0.6029955261622253,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004968970572197172,
|
|
"loss": 5.6055,
|
|
"mean_token_accuracy": 0.15758649706840516,
|
|
"num_tokens": 13457846.0,
|
|
"step": 7750
|
|
},
|
|
{
|
|
"entropy": 5.730754661560058,
|
|
"epoch": 0.6033845555339428,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.0004968924684996765,
|
|
"loss": 5.6091,
|
|
"mean_token_accuracy": 0.15334318280220033,
|
|
"num_tokens": 13466242.0,
|
|
"step": 7755
|
|
},
|
|
{
|
|
"entropy": 5.67420654296875,
|
|
"epoch": 0.6037735849056604,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.000496887876412771,
|
|
"loss": 5.5405,
|
|
"mean_token_accuracy": 0.15616600215435028,
|
|
"num_tokens": 13474639.0,
|
|
"step": 7760
|
|
},
|
|
{
|
|
"entropy": 5.563692665100097,
|
|
"epoch": 0.6041626142773779,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004968832809590701,
|
|
"loss": 5.436,
|
|
"mean_token_accuracy": 0.16429483294487,
|
|
"num_tokens": 13483673.0,
|
|
"step": 7765
|
|
},
|
|
{
|
|
"entropy": 5.667019462585449,
|
|
"epoch": 0.6045516436490955,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004968786821386435,
|
|
"loss": 5.5529,
|
|
"mean_token_accuracy": 0.15738777071237564,
|
|
"num_tokens": 13493001.0,
|
|
"step": 7770
|
|
},
|
|
{
|
|
"entropy": 5.751283121109009,
|
|
"epoch": 0.6049406730208131,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004968740799515611,
|
|
"loss": 5.5688,
|
|
"mean_token_accuracy": 0.15729465782642366,
|
|
"num_tokens": 13500878.0,
|
|
"step": 7775
|
|
},
|
|
{
|
|
"entropy": 5.6461762428283695,
|
|
"epoch": 0.6053297023925306,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004968694743978926,
|
|
"loss": 5.6267,
|
|
"mean_token_accuracy": 0.1560249738395214,
|
|
"num_tokens": 13509945.0,
|
|
"step": 7780
|
|
},
|
|
{
|
|
"entropy": 5.580125570297241,
|
|
"epoch": 0.6057187317642482,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004968648654777081,
|
|
"loss": 5.5488,
|
|
"mean_token_accuracy": 0.16145080476999282,
|
|
"num_tokens": 13520024.0,
|
|
"step": 7785
|
|
},
|
|
{
|
|
"entropy": 5.669335126876831,
|
|
"epoch": 0.6061077611359658,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004968602531910773,
|
|
"loss": 5.644,
|
|
"mean_token_accuracy": 0.15712960958480834,
|
|
"num_tokens": 13529136.0,
|
|
"step": 7790
|
|
},
|
|
{
|
|
"entropy": 5.628845357894898,
|
|
"epoch": 0.6064967905076833,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004968556375380704,
|
|
"loss": 5.452,
|
|
"mean_token_accuracy": 0.16029975712299346,
|
|
"num_tokens": 13537001.0,
|
|
"step": 7795
|
|
},
|
|
{
|
|
"entropy": 5.619492673873902,
|
|
"epoch": 0.6068858198794009,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004968510185187571,
|
|
"loss": 5.4475,
|
|
"mean_token_accuracy": 0.16057668179273604,
|
|
"num_tokens": 13545520.0,
|
|
"step": 7800
|
|
},
|
|
{
|
|
"entropy": 5.581534576416016,
|
|
"epoch": 0.6072748492511184,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.000496846396133208,
|
|
"loss": 5.5005,
|
|
"mean_token_accuracy": 0.1582297757267952,
|
|
"num_tokens": 13554770.0,
|
|
"step": 7805
|
|
},
|
|
{
|
|
"entropy": 5.701692295074463,
|
|
"epoch": 0.607663878622836,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004968417703814928,
|
|
"loss": 5.5476,
|
|
"mean_token_accuracy": 0.15719548612833023,
|
|
"num_tokens": 13562797.0,
|
|
"step": 7810
|
|
},
|
|
{
|
|
"entropy": 5.613367748260498,
|
|
"epoch": 0.6080529079945536,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004968371412636818,
|
|
"loss": 5.5004,
|
|
"mean_token_accuracy": 0.16422986686229707,
|
|
"num_tokens": 13572017.0,
|
|
"step": 7815
|
|
},
|
|
{
|
|
"entropy": 5.6862372875213625,
|
|
"epoch": 0.6084419373662712,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004968325087798453,
|
|
"loss": 5.5231,
|
|
"mean_token_accuracy": 0.1657199665904045,
|
|
"num_tokens": 13580245.0,
|
|
"step": 7820
|
|
},
|
|
{
|
|
"entropy": 5.597463941574096,
|
|
"epoch": 0.6088309667379888,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004968278729300536,
|
|
"loss": 5.4988,
|
|
"mean_token_accuracy": 0.15661692023277282,
|
|
"num_tokens": 13588719.0,
|
|
"step": 7825
|
|
},
|
|
{
|
|
"entropy": 5.66688551902771,
|
|
"epoch": 0.6092199961097062,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004968232337143769,
|
|
"loss": 5.5555,
|
|
"mean_token_accuracy": 0.16355859488248825,
|
|
"num_tokens": 13597345.0,
|
|
"step": 7830
|
|
},
|
|
{
|
|
"entropy": 5.707019233703614,
|
|
"epoch": 0.6096090254814238,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.0004968185911328858,
|
|
"loss": 5.5719,
|
|
"mean_token_accuracy": 0.15881615430116652,
|
|
"num_tokens": 13605468.0,
|
|
"step": 7835
|
|
},
|
|
{
|
|
"entropy": 5.659979629516601,
|
|
"epoch": 0.6099980548531414,
|
|
"grad_norm": 2.734375,
|
|
"learning_rate": 0.0004968139451856506,
|
|
"loss": 5.5829,
|
|
"mean_token_accuracy": 0.15562816858291625,
|
|
"num_tokens": 13614085.0,
|
|
"step": 7840
|
|
},
|
|
{
|
|
"entropy": 5.596334028244018,
|
|
"epoch": 0.610387084224859,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004968092958727419,
|
|
"loss": 5.4023,
|
|
"mean_token_accuracy": 0.16623687595129014,
|
|
"num_tokens": 13622370.0,
|
|
"step": 7845
|
|
},
|
|
{
|
|
"entropy": 5.6452563285827635,
|
|
"epoch": 0.6107761135965766,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.00049680464319423,
|
|
"loss": 5.5358,
|
|
"mean_token_accuracy": 0.162747386097908,
|
|
"num_tokens": 13630615.0,
|
|
"step": 7850
|
|
},
|
|
{
|
|
"entropy": 5.621069622039795,
|
|
"epoch": 0.6111651429682942,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004967999871501858,
|
|
"loss": 5.4597,
|
|
"mean_token_accuracy": 0.16595776081085206,
|
|
"num_tokens": 13638461.0,
|
|
"step": 7855
|
|
},
|
|
{
|
|
"entropy": 5.525365924835205,
|
|
"epoch": 0.6115541723400116,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004967953277406798,
|
|
"loss": 5.5588,
|
|
"mean_token_accuracy": 0.15436985194683076,
|
|
"num_tokens": 13647266.0,
|
|
"step": 7860
|
|
},
|
|
{
|
|
"entropy": 5.577764654159546,
|
|
"epoch": 0.6119432017117292,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004967906649657828,
|
|
"loss": 5.5385,
|
|
"mean_token_accuracy": 0.15356022566556932,
|
|
"num_tokens": 13655930.0,
|
|
"step": 7865
|
|
},
|
|
{
|
|
"entropy": 5.682845115661621,
|
|
"epoch": 0.6123322310834468,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004967859988255655,
|
|
"loss": 5.5266,
|
|
"mean_token_accuracy": 0.1603233262896538,
|
|
"num_tokens": 13664427.0,
|
|
"step": 7870
|
|
},
|
|
{
|
|
"entropy": 5.619559383392334,
|
|
"epoch": 0.6127212604551644,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004967813293200985,
|
|
"loss": 5.5442,
|
|
"mean_token_accuracy": 0.1572070375084877,
|
|
"num_tokens": 13673120.0,
|
|
"step": 7875
|
|
},
|
|
{
|
|
"entropy": 5.572880744934082,
|
|
"epoch": 0.613110289826882,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004967766564494529,
|
|
"loss": 5.3749,
|
|
"mean_token_accuracy": 0.16913995444774627,
|
|
"num_tokens": 13681918.0,
|
|
"step": 7880
|
|
},
|
|
{
|
|
"entropy": 5.554079675674439,
|
|
"epoch": 0.6134993191985995,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004967719802136996,
|
|
"loss": 5.4778,
|
|
"mean_token_accuracy": 0.16967321187257767,
|
|
"num_tokens": 13689904.0,
|
|
"step": 7885
|
|
},
|
|
{
|
|
"entropy": 5.60751166343689,
|
|
"epoch": 0.613888348570317,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004967673006129094,
|
|
"loss": 5.5141,
|
|
"mean_token_accuracy": 0.16323916763067245,
|
|
"num_tokens": 13697861.0,
|
|
"step": 7890
|
|
},
|
|
{
|
|
"entropy": 5.705719375610352,
|
|
"epoch": 0.6142773779420346,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004967626176471536,
|
|
"loss": 5.6527,
|
|
"mean_token_accuracy": 0.15828764587640762,
|
|
"num_tokens": 13706058.0,
|
|
"step": 7895
|
|
},
|
|
{
|
|
"entropy": 5.716040849685669,
|
|
"epoch": 0.6146664073137522,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004967579313165028,
|
|
"loss": 5.5623,
|
|
"mean_token_accuracy": 0.1580530047416687,
|
|
"num_tokens": 13715081.0,
|
|
"step": 7900
|
|
},
|
|
{
|
|
"entropy": 5.621213054656982,
|
|
"epoch": 0.6150554366854698,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004967532416210284,
|
|
"loss": 5.4588,
|
|
"mean_token_accuracy": 0.16525533944368362,
|
|
"num_tokens": 13723311.0,
|
|
"step": 7905
|
|
},
|
|
{
|
|
"entropy": 5.625402641296387,
|
|
"epoch": 0.6154444660571873,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004967485485608016,
|
|
"loss": 5.4866,
|
|
"mean_token_accuracy": 0.15760971158742904,
|
|
"num_tokens": 13731737.0,
|
|
"step": 7910
|
|
},
|
|
{
|
|
"entropy": 5.621528196334839,
|
|
"epoch": 0.6158334954289049,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004967438521358934,
|
|
"loss": 5.5461,
|
|
"mean_token_accuracy": 0.16389579325914383,
|
|
"num_tokens": 13740255.0,
|
|
"step": 7915
|
|
},
|
|
{
|
|
"entropy": 5.610876655578613,
|
|
"epoch": 0.6162225248006225,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004967391523463754,
|
|
"loss": 5.489,
|
|
"mean_token_accuracy": 0.16789331734180452,
|
|
"num_tokens": 13748656.0,
|
|
"step": 7920
|
|
},
|
|
{
|
|
"entropy": 5.564035367965698,
|
|
"epoch": 0.61661155417234,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004967344491923185,
|
|
"loss": 5.5076,
|
|
"mean_token_accuracy": 0.15980468392372132,
|
|
"num_tokens": 13757539.0,
|
|
"step": 7925
|
|
},
|
|
{
|
|
"entropy": 5.659132051467895,
|
|
"epoch": 0.6170005835440576,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004967297426737943,
|
|
"loss": 5.5129,
|
|
"mean_token_accuracy": 0.15738938599824906,
|
|
"num_tokens": 13766569.0,
|
|
"step": 7930
|
|
},
|
|
{
|
|
"entropy": 5.653924655914307,
|
|
"epoch": 0.6173896129157751,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004967250327908742,
|
|
"loss": 5.5366,
|
|
"mean_token_accuracy": 0.16349831819534302,
|
|
"num_tokens": 13775071.0,
|
|
"step": 7935
|
|
},
|
|
{
|
|
"entropy": 5.568353176116943,
|
|
"epoch": 0.6177786422874927,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004967203195436297,
|
|
"loss": 5.5299,
|
|
"mean_token_accuracy": 0.15771082788705826,
|
|
"num_tokens": 13783319.0,
|
|
"step": 7940
|
|
},
|
|
{
|
|
"entropy": 5.554364490509033,
|
|
"epoch": 0.6181676716592103,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004967156029321322,
|
|
"loss": 5.4737,
|
|
"mean_token_accuracy": 0.1636737361550331,
|
|
"num_tokens": 13792746.0,
|
|
"step": 7945
|
|
},
|
|
{
|
|
"entropy": 5.6123247146606445,
|
|
"epoch": 0.6185567010309279,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004967108829564532,
|
|
"loss": 5.4158,
|
|
"mean_token_accuracy": 0.16776807606220245,
|
|
"num_tokens": 13801632.0,
|
|
"step": 7950
|
|
},
|
|
{
|
|
"entropy": 5.608026552200317,
|
|
"epoch": 0.6189457304026454,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004967061596166646,
|
|
"loss": 5.554,
|
|
"mean_token_accuracy": 0.164193557202816,
|
|
"num_tokens": 13810527.0,
|
|
"step": 7955
|
|
},
|
|
{
|
|
"entropy": 5.641494846343994,
|
|
"epoch": 0.6193347597743629,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004967014329128378,
|
|
"loss": 5.4927,
|
|
"mean_token_accuracy": 0.1584918275475502,
|
|
"num_tokens": 13819885.0,
|
|
"step": 7960
|
|
},
|
|
{
|
|
"entropy": 5.602808618545533,
|
|
"epoch": 0.6197237891460805,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004966967028450448,
|
|
"loss": 5.4986,
|
|
"mean_token_accuracy": 0.1619834065437317,
|
|
"num_tokens": 13828509.0,
|
|
"step": 7965
|
|
},
|
|
{
|
|
"entropy": 5.639061784744262,
|
|
"epoch": 0.6201128185177981,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.000496691969413357,
|
|
"loss": 5.4984,
|
|
"mean_token_accuracy": 0.15714405626058578,
|
|
"num_tokens": 13837196.0,
|
|
"step": 7970
|
|
},
|
|
{
|
|
"entropy": 5.626188468933106,
|
|
"epoch": 0.6205018478895157,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004966872326178466,
|
|
"loss": 5.5401,
|
|
"mean_token_accuracy": 0.15958023220300674,
|
|
"num_tokens": 13845849.0,
|
|
"step": 7975
|
|
},
|
|
{
|
|
"entropy": 5.598227500915527,
|
|
"epoch": 0.6208908772612333,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004966824924585851,
|
|
"loss": 5.4759,
|
|
"mean_token_accuracy": 0.1665155291557312,
|
|
"num_tokens": 13853430.0,
|
|
"step": 7980
|
|
},
|
|
{
|
|
"entropy": 5.629713916778565,
|
|
"epoch": 0.6212799066329507,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004966777489356448,
|
|
"loss": 5.6462,
|
|
"mean_token_accuracy": 0.14797311276197433,
|
|
"num_tokens": 13862520.0,
|
|
"step": 7985
|
|
},
|
|
{
|
|
"entropy": 5.67573127746582,
|
|
"epoch": 0.6216689360046683,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004966730020490975,
|
|
"loss": 5.5734,
|
|
"mean_token_accuracy": 0.15468597412109375,
|
|
"num_tokens": 13871064.0,
|
|
"step": 7990
|
|
},
|
|
{
|
|
"entropy": 5.598003816604614,
|
|
"epoch": 0.6220579653763859,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.000496668251799015,
|
|
"loss": 5.4698,
|
|
"mean_token_accuracy": 0.15911296308040618,
|
|
"num_tokens": 13879952.0,
|
|
"step": 7995
|
|
},
|
|
{
|
|
"entropy": 5.624768495559692,
|
|
"epoch": 0.6224469947481035,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004966634981854699,
|
|
"loss": 5.6215,
|
|
"mean_token_accuracy": 0.15347439646720887,
|
|
"num_tokens": 13888054.0,
|
|
"step": 8000
|
|
},
|
|
{
|
|
"entropy": 5.720452976226807,
|
|
"epoch": 0.6228360241198211,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004966587412085339,
|
|
"loss": 5.5917,
|
|
"mean_token_accuracy": 0.15596983581781387,
|
|
"num_tokens": 13897051.0,
|
|
"step": 8005
|
|
},
|
|
{
|
|
"entropy": 5.644585418701172,
|
|
"epoch": 0.6232250534915386,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004966539808682793,
|
|
"loss": 5.5541,
|
|
"mean_token_accuracy": 0.15398771762847902,
|
|
"num_tokens": 13906175.0,
|
|
"step": 8010
|
|
},
|
|
{
|
|
"entropy": 5.594349575042725,
|
|
"epoch": 0.6236140828632561,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004966492171647783,
|
|
"loss": 5.5113,
|
|
"mean_token_accuracy": 0.16241261661052703,
|
|
"num_tokens": 13915283.0,
|
|
"step": 8015
|
|
},
|
|
{
|
|
"entropy": 5.613103246688842,
|
|
"epoch": 0.6240031122349737,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004966444500981032,
|
|
"loss": 5.5599,
|
|
"mean_token_accuracy": 0.15472135916352273,
|
|
"num_tokens": 13924007.0,
|
|
"step": 8020
|
|
},
|
|
{
|
|
"entropy": 5.635571241378784,
|
|
"epoch": 0.6243921416066913,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004966396796683265,
|
|
"loss": 5.4524,
|
|
"mean_token_accuracy": 0.1615746721625328,
|
|
"num_tokens": 13932694.0,
|
|
"step": 8025
|
|
},
|
|
{
|
|
"entropy": 5.6920552253723145,
|
|
"epoch": 0.6247811709784089,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004966349058755204,
|
|
"loss": 5.5668,
|
|
"mean_token_accuracy": 0.1511019714176655,
|
|
"num_tokens": 13941817.0,
|
|
"step": 8030
|
|
},
|
|
{
|
|
"entropy": 5.627501916885376,
|
|
"epoch": 0.6251702003501264,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004966301287197573,
|
|
"loss": 5.4196,
|
|
"mean_token_accuracy": 0.16701409667730333,
|
|
"num_tokens": 13950413.0,
|
|
"step": 8035
|
|
},
|
|
{
|
|
"entropy": 5.68371171951294,
|
|
"epoch": 0.625559229721844,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004966253482011098,
|
|
"loss": 5.5711,
|
|
"mean_token_accuracy": 0.15596165508031845,
|
|
"num_tokens": 13959415.0,
|
|
"step": 8040
|
|
},
|
|
{
|
|
"entropy": 5.586246681213379,
|
|
"epoch": 0.6259482590935616,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004966205643196503,
|
|
"loss": 5.4396,
|
|
"mean_token_accuracy": 0.16483698040246964,
|
|
"num_tokens": 13967889.0,
|
|
"step": 8045
|
|
},
|
|
{
|
|
"entropy": 5.451131200790405,
|
|
"epoch": 0.6263372884652791,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004966157770754516,
|
|
"loss": 5.4298,
|
|
"mean_token_accuracy": 0.16041132509708406,
|
|
"num_tokens": 13976190.0,
|
|
"step": 8050
|
|
},
|
|
{
|
|
"entropy": 5.743996858596802,
|
|
"epoch": 0.6267263178369967,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.000496610986468586,
|
|
"loss": 5.5624,
|
|
"mean_token_accuracy": 0.15470899939537047,
|
|
"num_tokens": 13984940.0,
|
|
"step": 8055
|
|
},
|
|
{
|
|
"entropy": 5.711560821533203,
|
|
"epoch": 0.6271153472087143,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004966061924991267,
|
|
"loss": 5.5669,
|
|
"mean_token_accuracy": 0.15803698003292083,
|
|
"num_tokens": 13993740.0,
|
|
"step": 8060
|
|
},
|
|
{
|
|
"entropy": 5.649155855178833,
|
|
"epoch": 0.6275043765804318,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.000496601395167146,
|
|
"loss": 5.6063,
|
|
"mean_token_accuracy": 0.15621764957904816,
|
|
"num_tokens": 14002401.0,
|
|
"step": 8065
|
|
},
|
|
{
|
|
"entropy": 5.6560780048370365,
|
|
"epoch": 0.6278934059521494,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004965965944727168,
|
|
"loss": 5.589,
|
|
"mean_token_accuracy": 0.16249808073043823,
|
|
"num_tokens": 14011197.0,
|
|
"step": 8070
|
|
},
|
|
{
|
|
"entropy": 5.668906259536743,
|
|
"epoch": 0.628282435323867,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004965917904159121,
|
|
"loss": 5.4433,
|
|
"mean_token_accuracy": 0.16768872141838073,
|
|
"num_tokens": 14020344.0,
|
|
"step": 8075
|
|
},
|
|
{
|
|
"entropy": 5.573599004745484,
|
|
"epoch": 0.6286714646955845,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004965869829968046,
|
|
"loss": 5.4688,
|
|
"mean_token_accuracy": 0.1629825420677662,
|
|
"num_tokens": 14029117.0,
|
|
"step": 8080
|
|
},
|
|
{
|
|
"entropy": 5.550131130218506,
|
|
"epoch": 0.6290604940673021,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004965821722154674,
|
|
"loss": 5.3851,
|
|
"mean_token_accuracy": 0.17250871807336807,
|
|
"num_tokens": 14038395.0,
|
|
"step": 8085
|
|
},
|
|
{
|
|
"entropy": 5.654913759231567,
|
|
"epoch": 0.6294495234390196,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004965773580719734,
|
|
"loss": 5.4818,
|
|
"mean_token_accuracy": 0.1610204964876175,
|
|
"num_tokens": 14046983.0,
|
|
"step": 8090
|
|
},
|
|
{
|
|
"entropy": 5.532347106933594,
|
|
"epoch": 0.6298385528107372,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004965725405663957,
|
|
"loss": 5.3661,
|
|
"mean_token_accuracy": 0.17185525000095367,
|
|
"num_tokens": 14056261.0,
|
|
"step": 8095
|
|
},
|
|
{
|
|
"entropy": 5.560761213302612,
|
|
"epoch": 0.6302275821824548,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004965677196988073,
|
|
"loss": 5.5553,
|
|
"mean_token_accuracy": 0.15718994289636612,
|
|
"num_tokens": 14065371.0,
|
|
"step": 8100
|
|
},
|
|
{
|
|
"entropy": 5.667489385604858,
|
|
"epoch": 0.6306166115541724,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004965628954692815,
|
|
"loss": 5.6046,
|
|
"mean_token_accuracy": 0.15320607796311378,
|
|
"num_tokens": 14074007.0,
|
|
"step": 8105
|
|
},
|
|
{
|
|
"entropy": 5.6024304866790775,
|
|
"epoch": 0.63100564092589,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004965580678778913,
|
|
"loss": 5.4635,
|
|
"mean_token_accuracy": 0.16192514896392823,
|
|
"num_tokens": 14083259.0,
|
|
"step": 8110
|
|
},
|
|
{
|
|
"entropy": 5.5890124320983885,
|
|
"epoch": 0.6313946702976074,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004965532369247102,
|
|
"loss": 5.4472,
|
|
"mean_token_accuracy": 0.16927091628313065,
|
|
"num_tokens": 14090993.0,
|
|
"step": 8115
|
|
},
|
|
{
|
|
"entropy": 5.708404493331909,
|
|
"epoch": 0.631783699669325,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004965484026098111,
|
|
"loss": 5.5798,
|
|
"mean_token_accuracy": 0.16099388897418976,
|
|
"num_tokens": 14099722.0,
|
|
"step": 8120
|
|
},
|
|
{
|
|
"entropy": 5.694318532943726,
|
|
"epoch": 0.6321727290410426,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004965435649332679,
|
|
"loss": 5.5686,
|
|
"mean_token_accuracy": 0.1553332358598709,
|
|
"num_tokens": 14108483.0,
|
|
"step": 8125
|
|
},
|
|
{
|
|
"entropy": 5.700818920135498,
|
|
"epoch": 0.6325617584127602,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004965387238951536,
|
|
"loss": 5.5813,
|
|
"mean_token_accuracy": 0.15432338714599608,
|
|
"num_tokens": 14117187.0,
|
|
"step": 8130
|
|
},
|
|
{
|
|
"entropy": 5.629018354415893,
|
|
"epoch": 0.6329507877844778,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004965338794955418,
|
|
"loss": 5.4165,
|
|
"mean_token_accuracy": 0.16764814108610154,
|
|
"num_tokens": 14125424.0,
|
|
"step": 8135
|
|
},
|
|
{
|
|
"entropy": 5.578190708160401,
|
|
"epoch": 0.6333398171561953,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004965290317345061,
|
|
"loss": 5.4749,
|
|
"mean_token_accuracy": 0.16633348613977433,
|
|
"num_tokens": 14133038.0,
|
|
"step": 8140
|
|
},
|
|
{
|
|
"entropy": 5.669448947906494,
|
|
"epoch": 0.6337288465279128,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004965241806121198,
|
|
"loss": 5.635,
|
|
"mean_token_accuracy": 0.15585788935422898,
|
|
"num_tokens": 14141114.0,
|
|
"step": 8145
|
|
},
|
|
{
|
|
"entropy": 5.701724481582642,
|
|
"epoch": 0.6341178758996304,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004965193261284567,
|
|
"loss": 5.4913,
|
|
"mean_token_accuracy": 0.16475782543420792,
|
|
"num_tokens": 14149681.0,
|
|
"step": 8150
|
|
},
|
|
{
|
|
"entropy": 5.664780807495117,
|
|
"epoch": 0.634506905271348,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004965144682835904,
|
|
"loss": 5.521,
|
|
"mean_token_accuracy": 0.15518609285354615,
|
|
"num_tokens": 14158510.0,
|
|
"step": 8155
|
|
},
|
|
{
|
|
"entropy": 5.62149748802185,
|
|
"epoch": 0.6348959346430656,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004965096070775946,
|
|
"loss": 5.5722,
|
|
"mean_token_accuracy": 0.16341715157032013,
|
|
"num_tokens": 14166897.0,
|
|
"step": 8160
|
|
},
|
|
{
|
|
"entropy": 5.646671915054322,
|
|
"epoch": 0.6352849640147831,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004965047425105431,
|
|
"loss": 5.5112,
|
|
"mean_token_accuracy": 0.16355205327272415,
|
|
"num_tokens": 14174692.0,
|
|
"step": 8165
|
|
},
|
|
{
|
|
"entropy": 5.608004140853882,
|
|
"epoch": 0.6356739933865007,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004964998745825097,
|
|
"loss": 5.5145,
|
|
"mean_token_accuracy": 0.1610356867313385,
|
|
"num_tokens": 14183779.0,
|
|
"step": 8170
|
|
},
|
|
{
|
|
"entropy": 5.618157815933228,
|
|
"epoch": 0.6360630227582182,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004964950032935682,
|
|
"loss": 5.5653,
|
|
"mean_token_accuracy": 0.1621095359325409,
|
|
"num_tokens": 14191809.0,
|
|
"step": 8175
|
|
},
|
|
{
|
|
"entropy": 5.619154691696167,
|
|
"epoch": 0.6364520521299358,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004964901286437927,
|
|
"loss": 5.5212,
|
|
"mean_token_accuracy": 0.1605943337082863,
|
|
"num_tokens": 14200652.0,
|
|
"step": 8180
|
|
},
|
|
{
|
|
"entropy": 5.64874005317688,
|
|
"epoch": 0.6368410815016534,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004964852506332568,
|
|
"loss": 5.4994,
|
|
"mean_token_accuracy": 0.1635741412639618,
|
|
"num_tokens": 14209694.0,
|
|
"step": 8185
|
|
},
|
|
{
|
|
"entropy": 5.67854871749878,
|
|
"epoch": 0.6372301108733709,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.000496480369262035,
|
|
"loss": 5.5653,
|
|
"mean_token_accuracy": 0.15659616738557816,
|
|
"num_tokens": 14218040.0,
|
|
"step": 8190
|
|
},
|
|
{
|
|
"entropy": 5.608455085754395,
|
|
"epoch": 0.6376191402450885,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.000496475484530201,
|
|
"loss": 5.4904,
|
|
"mean_token_accuracy": 0.16435641497373582,
|
|
"num_tokens": 14225908.0,
|
|
"step": 8195
|
|
},
|
|
{
|
|
"entropy": 5.625738477706909,
|
|
"epoch": 0.6380081696168061,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004964705964378292,
|
|
"loss": 5.514,
|
|
"mean_token_accuracy": 0.15561088025569916,
|
|
"num_tokens": 14234140.0,
|
|
"step": 8200
|
|
},
|
|
{
|
|
"entropy": 5.676596355438233,
|
|
"epoch": 0.6383971989885237,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004964657049849934,
|
|
"loss": 5.5588,
|
|
"mean_token_accuracy": 0.161154206097126,
|
|
"num_tokens": 14243590.0,
|
|
"step": 8205
|
|
},
|
|
{
|
|
"entropy": 5.700593566894531,
|
|
"epoch": 0.6387862283602412,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004964608101717681,
|
|
"loss": 5.5236,
|
|
"mean_token_accuracy": 0.1618498295545578,
|
|
"num_tokens": 14252249.0,
|
|
"step": 8210
|
|
},
|
|
{
|
|
"entropy": 5.620331192016602,
|
|
"epoch": 0.6391752577319587,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004964559119982275,
|
|
"loss": 5.4516,
|
|
"mean_token_accuracy": 0.1617949664592743,
|
|
"num_tokens": 14261147.0,
|
|
"step": 8215
|
|
},
|
|
{
|
|
"entropy": 5.61994776725769,
|
|
"epoch": 0.6395642871036763,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.000496451010464446,
|
|
"loss": 5.5242,
|
|
"mean_token_accuracy": 0.16001735627651215,
|
|
"num_tokens": 14270309.0,
|
|
"step": 8220
|
|
},
|
|
{
|
|
"entropy": 5.57561731338501,
|
|
"epoch": 0.6399533164753939,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004964461055704978,
|
|
"loss": 5.511,
|
|
"mean_token_accuracy": 0.15979014486074447,
|
|
"num_tokens": 14279379.0,
|
|
"step": 8225
|
|
},
|
|
{
|
|
"entropy": 5.560876750946045,
|
|
"epoch": 0.6403423458471115,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004964411973164574,
|
|
"loss": 5.4614,
|
|
"mean_token_accuracy": 0.1537440910935402,
|
|
"num_tokens": 14288136.0,
|
|
"step": 8230
|
|
},
|
|
{
|
|
"entropy": 5.591270303726196,
|
|
"epoch": 0.6407313752188291,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004964362857023993,
|
|
"loss": 5.3891,
|
|
"mean_token_accuracy": 0.16101400256156922,
|
|
"num_tokens": 14296437.0,
|
|
"step": 8235
|
|
},
|
|
{
|
|
"entropy": 5.613467645645142,
|
|
"epoch": 0.6411204045905465,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.000496431370728398,
|
|
"loss": 5.4342,
|
|
"mean_token_accuracy": 0.17272723615169525,
|
|
"num_tokens": 14304861.0,
|
|
"step": 8240
|
|
},
|
|
{
|
|
"entropy": 5.53576021194458,
|
|
"epoch": 0.6415094339622641,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004964264523945281,
|
|
"loss": 5.4904,
|
|
"mean_token_accuracy": 0.16508440673351288,
|
|
"num_tokens": 14312861.0,
|
|
"step": 8245
|
|
},
|
|
{
|
|
"entropy": 5.503257942199707,
|
|
"epoch": 0.6418984633339817,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004964215307008643,
|
|
"loss": 5.3573,
|
|
"mean_token_accuracy": 0.16898525953292848,
|
|
"num_tokens": 14321651.0,
|
|
"step": 8250
|
|
},
|
|
{
|
|
"entropy": 5.606548023223877,
|
|
"epoch": 0.6422874927056993,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004964166056474811,
|
|
"loss": 5.5186,
|
|
"mean_token_accuracy": 0.16981685757637024,
|
|
"num_tokens": 14329234.0,
|
|
"step": 8255
|
|
},
|
|
{
|
|
"entropy": 5.63331151008606,
|
|
"epoch": 0.6426765220774169,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004964116772344534,
|
|
"loss": 5.641,
|
|
"mean_token_accuracy": 0.15602685809135436,
|
|
"num_tokens": 14337603.0,
|
|
"step": 8260
|
|
},
|
|
{
|
|
"entropy": 5.645445251464844,
|
|
"epoch": 0.6430655514491345,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 0.0004964067454618559,
|
|
"loss": 5.5221,
|
|
"mean_token_accuracy": 0.16045982241630555,
|
|
"num_tokens": 14346634.0,
|
|
"step": 8265
|
|
},
|
|
{
|
|
"entropy": 5.691012954711914,
|
|
"epoch": 0.6434545808208519,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004964018103297634,
|
|
"loss": 5.5444,
|
|
"mean_token_accuracy": 0.15774981528520585,
|
|
"num_tokens": 14355336.0,
|
|
"step": 8270
|
|
},
|
|
{
|
|
"entropy": 5.637445688247681,
|
|
"epoch": 0.6438436101925695,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004963968718382509,
|
|
"loss": 5.4931,
|
|
"mean_token_accuracy": 0.1598949909210205,
|
|
"num_tokens": 14364434.0,
|
|
"step": 8275
|
|
},
|
|
{
|
|
"entropy": 5.580499696731567,
|
|
"epoch": 0.6442326395642871,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004963919299873931,
|
|
"loss": 5.432,
|
|
"mean_token_accuracy": 0.1723459243774414,
|
|
"num_tokens": 14372454.0,
|
|
"step": 8280
|
|
},
|
|
{
|
|
"entropy": 5.626510953903198,
|
|
"epoch": 0.6446216689360047,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004963869847772653,
|
|
"loss": 5.4967,
|
|
"mean_token_accuracy": 0.1624937891960144,
|
|
"num_tokens": 14381381.0,
|
|
"step": 8285
|
|
},
|
|
{
|
|
"entropy": 5.6586121082305905,
|
|
"epoch": 0.6450106983077223,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004963820362079423,
|
|
"loss": 5.5855,
|
|
"mean_token_accuracy": 0.15776764452457429,
|
|
"num_tokens": 14390853.0,
|
|
"step": 8290
|
|
},
|
|
{
|
|
"entropy": 5.5826750755310055,
|
|
"epoch": 0.6453997276794398,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004963770842794994,
|
|
"loss": 5.4458,
|
|
"mean_token_accuracy": 0.16542210429906845,
|
|
"num_tokens": 14399897.0,
|
|
"step": 8295
|
|
},
|
|
{
|
|
"entropy": 5.546051073074341,
|
|
"epoch": 0.6457887570511573,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004963721289920115,
|
|
"loss": 5.5021,
|
|
"mean_token_accuracy": 0.16482663303613662,
|
|
"num_tokens": 14408192.0,
|
|
"step": 8300
|
|
},
|
|
{
|
|
"entropy": 5.548407506942749,
|
|
"epoch": 0.6461777864228749,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004963671703455538,
|
|
"loss": 5.3852,
|
|
"mean_token_accuracy": 0.17058072835206986,
|
|
"num_tokens": 14416004.0,
|
|
"step": 8305
|
|
},
|
|
{
|
|
"entropy": 5.585981321334839,
|
|
"epoch": 0.6465668157945925,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004963622083402018,
|
|
"loss": 5.4231,
|
|
"mean_token_accuracy": 0.16638686507940292,
|
|
"num_tokens": 14424573.0,
|
|
"step": 8310
|
|
},
|
|
{
|
|
"entropy": 5.536883068084717,
|
|
"epoch": 0.6469558451663101,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004963572429760305,
|
|
"loss": 5.4153,
|
|
"mean_token_accuracy": 0.16832368671894074,
|
|
"num_tokens": 14432756.0,
|
|
"step": 8315
|
|
},
|
|
{
|
|
"entropy": 5.62876329421997,
|
|
"epoch": 0.6473448745380276,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004963522742531155,
|
|
"loss": 5.5143,
|
|
"mean_token_accuracy": 0.15935860425233841,
|
|
"num_tokens": 14441695.0,
|
|
"step": 8320
|
|
},
|
|
{
|
|
"entropy": 5.589247512817383,
|
|
"epoch": 0.6477339039097452,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.000496347302171532,
|
|
"loss": 5.6141,
|
|
"mean_token_accuracy": 0.15695839151740074,
|
|
"num_tokens": 14451233.0,
|
|
"step": 8325
|
|
},
|
|
{
|
|
"entropy": 5.634691572189331,
|
|
"epoch": 0.6481229332814628,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004963423267313554,
|
|
"loss": 5.4841,
|
|
"mean_token_accuracy": 0.16518651098012924,
|
|
"num_tokens": 14459757.0,
|
|
"step": 8330
|
|
},
|
|
{
|
|
"entropy": 5.642829942703247,
|
|
"epoch": 0.6485119626531803,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004963373479326614,
|
|
"loss": 5.5698,
|
|
"mean_token_accuracy": 0.1531238727271557,
|
|
"num_tokens": 14468308.0,
|
|
"step": 8335
|
|
},
|
|
{
|
|
"entropy": 5.619338035583496,
|
|
"epoch": 0.6489009920248979,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004963323657755255,
|
|
"loss": 5.5011,
|
|
"mean_token_accuracy": 0.1637391686439514,
|
|
"num_tokens": 14476654.0,
|
|
"step": 8340
|
|
},
|
|
{
|
|
"entropy": 5.64993805885315,
|
|
"epoch": 0.6492900213966154,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004963273802600231,
|
|
"loss": 5.5943,
|
|
"mean_token_accuracy": 0.16172325909137725,
|
|
"num_tokens": 14484960.0,
|
|
"step": 8345
|
|
},
|
|
{
|
|
"entropy": 5.72280445098877,
|
|
"epoch": 0.649679050768333,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00049632239138623,
|
|
"loss": 5.5754,
|
|
"mean_token_accuracy": 0.1508148118853569,
|
|
"num_tokens": 14493708.0,
|
|
"step": 8350
|
|
},
|
|
{
|
|
"entropy": 5.721679782867431,
|
|
"epoch": 0.6500680801400506,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004963173991542219,
|
|
"loss": 5.531,
|
|
"mean_token_accuracy": 0.16181753277778627,
|
|
"num_tokens": 14502123.0,
|
|
"step": 8355
|
|
},
|
|
{
|
|
"entropy": 5.621743965148926,
|
|
"epoch": 0.6504571095117682,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004963124035640746,
|
|
"loss": 5.5046,
|
|
"mean_token_accuracy": 0.16208697408437728,
|
|
"num_tokens": 14510782.0,
|
|
"step": 8360
|
|
},
|
|
{
|
|
"entropy": 5.53667573928833,
|
|
"epoch": 0.6508461388834857,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004963074046158637,
|
|
"loss": 5.4504,
|
|
"mean_token_accuracy": 0.1645912155508995,
|
|
"num_tokens": 14518560.0,
|
|
"step": 8365
|
|
},
|
|
{
|
|
"entropy": 5.63091254234314,
|
|
"epoch": 0.6512351682552032,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004963024023096652,
|
|
"loss": 5.4836,
|
|
"mean_token_accuracy": 0.1586213417351246,
|
|
"num_tokens": 14527541.0,
|
|
"step": 8370
|
|
},
|
|
{
|
|
"entropy": 5.679382848739624,
|
|
"epoch": 0.6516241976269208,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004962973966455551,
|
|
"loss": 5.5212,
|
|
"mean_token_accuracy": 0.16429576873779297,
|
|
"num_tokens": 14535590.0,
|
|
"step": 8375
|
|
},
|
|
{
|
|
"entropy": 5.476749753952026,
|
|
"epoch": 0.6520132269986384,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004962923876236092,
|
|
"loss": 5.4237,
|
|
"mean_token_accuracy": 0.15991545766592025,
|
|
"num_tokens": 14544929.0,
|
|
"step": 8380
|
|
},
|
|
{
|
|
"entropy": 5.631164979934693,
|
|
"epoch": 0.652402256370356,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004962873752439035,
|
|
"loss": 5.5858,
|
|
"mean_token_accuracy": 0.1527818873524666,
|
|
"num_tokens": 14553883.0,
|
|
"step": 8385
|
|
},
|
|
{
|
|
"entropy": 5.696902561187744,
|
|
"epoch": 0.6527912857420736,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004962823595065141,
|
|
"loss": 5.6022,
|
|
"mean_token_accuracy": 0.15535233467817305,
|
|
"num_tokens": 14563085.0,
|
|
"step": 8390
|
|
},
|
|
{
|
|
"entropy": 5.681191062927246,
|
|
"epoch": 0.653180315113791,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004962773404115172,
|
|
"loss": 5.4552,
|
|
"mean_token_accuracy": 0.16444580256938934,
|
|
"num_tokens": 14571444.0,
|
|
"step": 8395
|
|
},
|
|
{
|
|
"entropy": 5.63764533996582,
|
|
"epoch": 0.6535693444855086,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004962723179589886,
|
|
"loss": 5.5539,
|
|
"mean_token_accuracy": 0.16111520528793336,
|
|
"num_tokens": 14580039.0,
|
|
"step": 8400
|
|
},
|
|
{
|
|
"entropy": 5.579935073852539,
|
|
"epoch": 0.6539583738572262,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.000496267292149005,
|
|
"loss": 5.4336,
|
|
"mean_token_accuracy": 0.16800265163183212,
|
|
"num_tokens": 14588322.0,
|
|
"step": 8405
|
|
},
|
|
{
|
|
"entropy": 5.57730073928833,
|
|
"epoch": 0.6543474032289438,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004962622629816423,
|
|
"loss": 5.3722,
|
|
"mean_token_accuracy": 0.1650988057255745,
|
|
"num_tokens": 14597503.0,
|
|
"step": 8410
|
|
},
|
|
{
|
|
"entropy": 5.609830713272094,
|
|
"epoch": 0.6547364326006614,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.000496257230456977,
|
|
"loss": 5.5037,
|
|
"mean_token_accuracy": 0.15908412784337997,
|
|
"num_tokens": 14605804.0,
|
|
"step": 8415
|
|
},
|
|
{
|
|
"entropy": 5.462103652954101,
|
|
"epoch": 0.6551254619723789,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004962521945750855,
|
|
"loss": 5.4273,
|
|
"mean_token_accuracy": 0.17144200950860977,
|
|
"num_tokens": 14614064.0,
|
|
"step": 8420
|
|
},
|
|
{
|
|
"entropy": 5.612936496734619,
|
|
"epoch": 0.6555144913440965,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.000496247155336044,
|
|
"loss": 5.4338,
|
|
"mean_token_accuracy": 0.16576751172542573,
|
|
"num_tokens": 14622231.0,
|
|
"step": 8425
|
|
},
|
|
{
|
|
"entropy": 5.623867321014404,
|
|
"epoch": 0.655903520715814,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004962421127399291,
|
|
"loss": 5.5545,
|
|
"mean_token_accuracy": 0.1569196030497551,
|
|
"num_tokens": 14631244.0,
|
|
"step": 8430
|
|
},
|
|
{
|
|
"entropy": 5.587360048294068,
|
|
"epoch": 0.6562925500875316,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004962370667868172,
|
|
"loss": 5.4267,
|
|
"mean_token_accuracy": 0.16126427203416824,
|
|
"num_tokens": 14639575.0,
|
|
"step": 8435
|
|
},
|
|
{
|
|
"entropy": 5.58545503616333,
|
|
"epoch": 0.6566815794592492,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004962320174767851,
|
|
"loss": 5.4756,
|
|
"mean_token_accuracy": 0.15965766459703445,
|
|
"num_tokens": 14648810.0,
|
|
"step": 8440
|
|
},
|
|
{
|
|
"entropy": 5.555451202392578,
|
|
"epoch": 0.6570706088309667,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.000496226964809909,
|
|
"loss": 5.3258,
|
|
"mean_token_accuracy": 0.17258747071027755,
|
|
"num_tokens": 14657783.0,
|
|
"step": 8445
|
|
},
|
|
{
|
|
"entropy": 5.624908018112182,
|
|
"epoch": 0.6574596382026843,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.000496221908786266,
|
|
"loss": 5.5276,
|
|
"mean_token_accuracy": 0.15910668671131134,
|
|
"num_tokens": 14666872.0,
|
|
"step": 8450
|
|
},
|
|
{
|
|
"entropy": 5.645132446289063,
|
|
"epoch": 0.6578486675744019,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004962168494059327,
|
|
"loss": 5.6502,
|
|
"mean_token_accuracy": 0.1516483262181282,
|
|
"num_tokens": 14675762.0,
|
|
"step": 8455
|
|
},
|
|
{
|
|
"entropy": 5.561020088195801,
|
|
"epoch": 0.6582376969461194,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004962117866689857,
|
|
"loss": 5.3148,
|
|
"mean_token_accuracy": 0.169151408970356,
|
|
"num_tokens": 14683928.0,
|
|
"step": 8460
|
|
},
|
|
{
|
|
"entropy": 5.6118079662323,
|
|
"epoch": 0.658626726317837,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.000496206720575502,
|
|
"loss": 5.5508,
|
|
"mean_token_accuracy": 0.15828213691711426,
|
|
"num_tokens": 14692411.0,
|
|
"step": 8465
|
|
},
|
|
{
|
|
"entropy": 5.686123466491699,
|
|
"epoch": 0.6590157556895546,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004962016511255584,
|
|
"loss": 5.5501,
|
|
"mean_token_accuracy": 0.15016385316848754,
|
|
"num_tokens": 14701002.0,
|
|
"step": 8470
|
|
},
|
|
{
|
|
"entropy": 5.7460590362548825,
|
|
"epoch": 0.6594047850612721,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004961965783192318,
|
|
"loss": 5.605,
|
|
"mean_token_accuracy": 0.15275918543338776,
|
|
"num_tokens": 14710172.0,
|
|
"step": 8475
|
|
},
|
|
{
|
|
"entropy": 5.595785903930664,
|
|
"epoch": 0.6597938144329897,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004961915021565992,
|
|
"loss": 5.5364,
|
|
"mean_token_accuracy": 0.15851985067129135,
|
|
"num_tokens": 14719446.0,
|
|
"step": 8480
|
|
},
|
|
{
|
|
"entropy": 5.684946155548095,
|
|
"epoch": 0.6601828438047073,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004961864226377377,
|
|
"loss": 5.5389,
|
|
"mean_token_accuracy": 0.1646391198039055,
|
|
"num_tokens": 14728193.0,
|
|
"step": 8485
|
|
},
|
|
{
|
|
"entropy": 5.620755958557129,
|
|
"epoch": 0.6605718731764249,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004961813397627241,
|
|
"loss": 5.434,
|
|
"mean_token_accuracy": 0.15734331607818602,
|
|
"num_tokens": 14736930.0,
|
|
"step": 8490
|
|
},
|
|
{
|
|
"entropy": 5.5294873237609865,
|
|
"epoch": 0.6609609025481424,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004961762535316358,
|
|
"loss": 5.4386,
|
|
"mean_token_accuracy": 0.1667746901512146,
|
|
"num_tokens": 14745995.0,
|
|
"step": 8495
|
|
},
|
|
{
|
|
"entropy": 5.519912528991699,
|
|
"epoch": 0.6613499319198599,
|
|
"grad_norm": 2.59375,
|
|
"learning_rate": 0.0004961711639445499,
|
|
"loss": 5.488,
|
|
"mean_token_accuracy": 0.1612710624933243,
|
|
"num_tokens": 14754827.0,
|
|
"step": 8500
|
|
},
|
|
{
|
|
"entropy": 5.717486047744751,
|
|
"epoch": 0.6617389612915775,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004961660710015435,
|
|
"loss": 5.5755,
|
|
"mean_token_accuracy": 0.15806931331753732,
|
|
"num_tokens": 14763594.0,
|
|
"step": 8505
|
|
},
|
|
{
|
|
"entropy": 5.6062768459320065,
|
|
"epoch": 0.6621279906632951,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004961609747026943,
|
|
"loss": 5.3934,
|
|
"mean_token_accuracy": 0.16947395503520965,
|
|
"num_tokens": 14772366.0,
|
|
"step": 8510
|
|
},
|
|
{
|
|
"entropy": 5.5509490966796875,
|
|
"epoch": 0.6625170200350127,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004961558750480791,
|
|
"loss": 5.4908,
|
|
"mean_token_accuracy": 0.1578017368912697,
|
|
"num_tokens": 14780738.0,
|
|
"step": 8515
|
|
},
|
|
{
|
|
"entropy": 5.560414981842041,
|
|
"epoch": 0.6629060494067303,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004961507720377756,
|
|
"loss": 5.4666,
|
|
"mean_token_accuracy": 0.15795683562755586,
|
|
"num_tokens": 14788982.0,
|
|
"step": 8520
|
|
},
|
|
{
|
|
"entropy": 5.602201271057129,
|
|
"epoch": 0.6632950787784477,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004961456656718611,
|
|
"loss": 5.4556,
|
|
"mean_token_accuracy": 0.1655229315161705,
|
|
"num_tokens": 14797832.0,
|
|
"step": 8525
|
|
},
|
|
{
|
|
"entropy": 5.638581800460815,
|
|
"epoch": 0.6636841081501653,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.000496140555950413,
|
|
"loss": 5.4978,
|
|
"mean_token_accuracy": 0.16762352734804153,
|
|
"num_tokens": 14806391.0,
|
|
"step": 8530
|
|
},
|
|
{
|
|
"entropy": 5.6750490188598635,
|
|
"epoch": 0.6640731375218829,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004961354428735091,
|
|
"loss": 5.5066,
|
|
"mean_token_accuracy": 0.1556483417749405,
|
|
"num_tokens": 14814920.0,
|
|
"step": 8535
|
|
},
|
|
{
|
|
"entropy": 5.574772119522095,
|
|
"epoch": 0.6644621668936005,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004961303264412267,
|
|
"loss": 5.4551,
|
|
"mean_token_accuracy": 0.16089894473552704,
|
|
"num_tokens": 14823541.0,
|
|
"step": 8540
|
|
},
|
|
{
|
|
"entropy": 5.581590223312378,
|
|
"epoch": 0.6648511962653181,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004961252066536437,
|
|
"loss": 5.4229,
|
|
"mean_token_accuracy": 0.1616658866405487,
|
|
"num_tokens": 14832128.0,
|
|
"step": 8545
|
|
},
|
|
{
|
|
"entropy": 5.636154460906982,
|
|
"epoch": 0.6652402256370356,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004961200835108375,
|
|
"loss": 5.5883,
|
|
"mean_token_accuracy": 0.15480114370584488,
|
|
"num_tokens": 14841434.0,
|
|
"step": 8550
|
|
},
|
|
{
|
|
"entropy": 5.655720949172974,
|
|
"epoch": 0.6656292550087531,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.000496114957012886,
|
|
"loss": 5.4972,
|
|
"mean_token_accuracy": 0.16742078512907027,
|
|
"num_tokens": 14850255.0,
|
|
"step": 8555
|
|
},
|
|
{
|
|
"entropy": 5.625656604766846,
|
|
"epoch": 0.6660182843804707,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004961098271598671,
|
|
"loss": 5.5812,
|
|
"mean_token_accuracy": 0.1552358813583851,
|
|
"num_tokens": 14858924.0,
|
|
"step": 8560
|
|
},
|
|
{
|
|
"entropy": 5.646219539642334,
|
|
"epoch": 0.6664073137521883,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004961046939518585,
|
|
"loss": 5.5106,
|
|
"mean_token_accuracy": 0.16416953057050704,
|
|
"num_tokens": 14867426.0,
|
|
"step": 8565
|
|
},
|
|
{
|
|
"entropy": 5.699926424026489,
|
|
"epoch": 0.6667963431239059,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004960995573889379,
|
|
"loss": 5.4714,
|
|
"mean_token_accuracy": 0.16506651192903518,
|
|
"num_tokens": 14876218.0,
|
|
"step": 8570
|
|
},
|
|
{
|
|
"entropy": 5.671121644973755,
|
|
"epoch": 0.6671853724956234,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004960944174711836,
|
|
"loss": 5.5289,
|
|
"mean_token_accuracy": 0.15950822383165358,
|
|
"num_tokens": 14883995.0,
|
|
"step": 8575
|
|
},
|
|
{
|
|
"entropy": 5.540333652496338,
|
|
"epoch": 0.667574401867341,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004960892741986734,
|
|
"loss": 5.5014,
|
|
"mean_token_accuracy": 0.1624891757965088,
|
|
"num_tokens": 14892659.0,
|
|
"step": 8580
|
|
},
|
|
{
|
|
"entropy": 5.664654541015625,
|
|
"epoch": 0.6679634312390585,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004960841275714853,
|
|
"loss": 5.5264,
|
|
"mean_token_accuracy": 0.15727367997169495,
|
|
"num_tokens": 14901518.0,
|
|
"step": 8585
|
|
},
|
|
{
|
|
"entropy": 5.607156229019165,
|
|
"epoch": 0.6683524606107761,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004960789775896975,
|
|
"loss": 5.509,
|
|
"mean_token_accuracy": 0.16244361102581023,
|
|
"num_tokens": 14910171.0,
|
|
"step": 8590
|
|
},
|
|
{
|
|
"entropy": 5.604865503311157,
|
|
"epoch": 0.6687414899824937,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004960738242533881,
|
|
"loss": 5.4873,
|
|
"mean_token_accuracy": 0.16071989834308625,
|
|
"num_tokens": 14918651.0,
|
|
"step": 8595
|
|
},
|
|
{
|
|
"entropy": 5.5974328994750975,
|
|
"epoch": 0.6691305193542112,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004960686675626353,
|
|
"loss": 5.4889,
|
|
"mean_token_accuracy": 0.15908095240592957,
|
|
"num_tokens": 14926951.0,
|
|
"step": 8600
|
|
},
|
|
{
|
|
"entropy": 5.726441287994385,
|
|
"epoch": 0.6695195487259288,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004960635075175173,
|
|
"loss": 5.5811,
|
|
"mean_token_accuracy": 0.15933732837438583,
|
|
"num_tokens": 14935528.0,
|
|
"step": 8605
|
|
},
|
|
{
|
|
"entropy": 5.610484170913696,
|
|
"epoch": 0.6699085780976464,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004960583441181124,
|
|
"loss": 5.4549,
|
|
"mean_token_accuracy": 0.16408660262823105,
|
|
"num_tokens": 14944117.0,
|
|
"step": 8610
|
|
},
|
|
{
|
|
"entropy": 5.582907962799072,
|
|
"epoch": 0.670297607469364,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004960531773644992,
|
|
"loss": 5.4265,
|
|
"mean_token_accuracy": 0.16474046409130097,
|
|
"num_tokens": 14952957.0,
|
|
"step": 8615
|
|
},
|
|
{
|
|
"entropy": 5.647277021408081,
|
|
"epoch": 0.6706866368410815,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004960480072567557,
|
|
"loss": 5.5077,
|
|
"mean_token_accuracy": 0.15832734555006028,
|
|
"num_tokens": 14960942.0,
|
|
"step": 8620
|
|
},
|
|
{
|
|
"entropy": 5.688439846038818,
|
|
"epoch": 0.671075666212799,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004960428337949604,
|
|
"loss": 5.6049,
|
|
"mean_token_accuracy": 0.1537842944264412,
|
|
"num_tokens": 14970579.0,
|
|
"step": 8625
|
|
},
|
|
{
|
|
"entropy": 5.594122982025146,
|
|
"epoch": 0.6714646955845166,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004960376569791921,
|
|
"loss": 5.4374,
|
|
"mean_token_accuracy": 0.15769007354974746,
|
|
"num_tokens": 14979353.0,
|
|
"step": 8630
|
|
},
|
|
{
|
|
"entropy": 5.67335877418518,
|
|
"epoch": 0.6718537249562342,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.0004960324768095291,
|
|
"loss": 5.6024,
|
|
"mean_token_accuracy": 0.16516705453395844,
|
|
"num_tokens": 14988435.0,
|
|
"step": 8635
|
|
},
|
|
{
|
|
"entropy": 5.647039937973022,
|
|
"epoch": 0.6722427543279518,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004960272932860502,
|
|
"loss": 5.5194,
|
|
"mean_token_accuracy": 0.15829846411943435,
|
|
"num_tokens": 14996834.0,
|
|
"step": 8640
|
|
},
|
|
{
|
|
"entropy": 5.670257425308227,
|
|
"epoch": 0.6726317836996694,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004960221064088338,
|
|
"loss": 5.5703,
|
|
"mean_token_accuracy": 0.15692353248596191,
|
|
"num_tokens": 15004988.0,
|
|
"step": 8645
|
|
},
|
|
{
|
|
"entropy": 5.666182184219361,
|
|
"epoch": 0.6730208130713868,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004960169161779588,
|
|
"loss": 5.5264,
|
|
"mean_token_accuracy": 0.1628352239727974,
|
|
"num_tokens": 15013482.0,
|
|
"step": 8650
|
|
},
|
|
{
|
|
"entropy": 5.591054677963257,
|
|
"epoch": 0.6734098424431044,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004960117225935038,
|
|
"loss": 5.4371,
|
|
"mean_token_accuracy": 0.16409590989351272,
|
|
"num_tokens": 15021506.0,
|
|
"step": 8655
|
|
},
|
|
{
|
|
"entropy": 5.586325979232788,
|
|
"epoch": 0.673798871814822,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004960065256555477,
|
|
"loss": 5.4772,
|
|
"mean_token_accuracy": 0.16757019460201264,
|
|
"num_tokens": 15029880.0,
|
|
"step": 8660
|
|
},
|
|
{
|
|
"entropy": 5.585851573944092,
|
|
"epoch": 0.6741879011865396,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004960013253641695,
|
|
"loss": 5.4672,
|
|
"mean_token_accuracy": 0.16203958690166473,
|
|
"num_tokens": 15038080.0,
|
|
"step": 8665
|
|
},
|
|
{
|
|
"entropy": 5.597144031524659,
|
|
"epoch": 0.6745769305582572,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004959961217194477,
|
|
"loss": 5.4829,
|
|
"mean_token_accuracy": 0.1624331921339035,
|
|
"num_tokens": 15046779.0,
|
|
"step": 8670
|
|
},
|
|
{
|
|
"entropy": 5.656364631652832,
|
|
"epoch": 0.6749659599299748,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004959909147214615,
|
|
"loss": 5.5129,
|
|
"mean_token_accuracy": 0.15865243524312972,
|
|
"num_tokens": 15055557.0,
|
|
"step": 8675
|
|
},
|
|
{
|
|
"entropy": 5.579842853546142,
|
|
"epoch": 0.6753549893016922,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004959857043702902,
|
|
"loss": 5.3801,
|
|
"mean_token_accuracy": 0.1640066534280777,
|
|
"num_tokens": 15063054.0,
|
|
"step": 8680
|
|
},
|
|
{
|
|
"entropy": 5.585133504867554,
|
|
"epoch": 0.6757440186734098,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004959804906660124,
|
|
"loss": 5.4688,
|
|
"mean_token_accuracy": 0.16473619192838668,
|
|
"num_tokens": 15071510.0,
|
|
"step": 8685
|
|
},
|
|
{
|
|
"entropy": 5.563712930679321,
|
|
"epoch": 0.6761330480451274,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004959752736087073,
|
|
"loss": 5.4888,
|
|
"mean_token_accuracy": 0.1553959906101227,
|
|
"num_tokens": 15080524.0,
|
|
"step": 8690
|
|
},
|
|
{
|
|
"entropy": 5.669127082824707,
|
|
"epoch": 0.676522077416845,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004959700531984543,
|
|
"loss": 5.5237,
|
|
"mean_token_accuracy": 0.15884414985775946,
|
|
"num_tokens": 15089689.0,
|
|
"step": 8695
|
|
},
|
|
{
|
|
"entropy": 5.576257514953613,
|
|
"epoch": 0.6769111067885626,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004959648294353324,
|
|
"loss": 5.4073,
|
|
"mean_token_accuracy": 0.16998513787984848,
|
|
"num_tokens": 15097970.0,
|
|
"step": 8700
|
|
},
|
|
{
|
|
"entropy": 5.54570426940918,
|
|
"epoch": 0.6773001361602801,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004959596023194208,
|
|
"loss": 5.509,
|
|
"mean_token_accuracy": 0.15639949291944505,
|
|
"num_tokens": 15107786.0,
|
|
"step": 8705
|
|
},
|
|
{
|
|
"entropy": 5.655686950683593,
|
|
"epoch": 0.6776891655319977,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.000495954371850799,
|
|
"loss": 5.4862,
|
|
"mean_token_accuracy": 0.16529091447591782,
|
|
"num_tokens": 15116370.0,
|
|
"step": 8710
|
|
},
|
|
{
|
|
"entropy": 5.68412218093872,
|
|
"epoch": 0.6780781949037152,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004959491380295463,
|
|
"loss": 5.5175,
|
|
"mean_token_accuracy": 0.15937916487455367,
|
|
"num_tokens": 15124961.0,
|
|
"step": 8715
|
|
},
|
|
{
|
|
"entropy": 5.645760822296142,
|
|
"epoch": 0.6784672242754328,
|
|
"grad_norm": 2.609375,
|
|
"learning_rate": 0.0004959439008557422,
|
|
"loss": 5.5278,
|
|
"mean_token_accuracy": 0.15579134672880174,
|
|
"num_tokens": 15134230.0,
|
|
"step": 8720
|
|
},
|
|
{
|
|
"entropy": 5.597600364685059,
|
|
"epoch": 0.6788562536471504,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.000495938660329466,
|
|
"loss": 5.4762,
|
|
"mean_token_accuracy": 0.15846306532621385,
|
|
"num_tokens": 15143585.0,
|
|
"step": 8725
|
|
},
|
|
{
|
|
"entropy": 5.5997742176055905,
|
|
"epoch": 0.6792452830188679,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 0.0004959334164507973,
|
|
"loss": 5.3996,
|
|
"mean_token_accuracy": 0.15709985047578812,
|
|
"num_tokens": 15151834.0,
|
|
"step": 8730
|
|
},
|
|
{
|
|
"entropy": 5.526013803482056,
|
|
"epoch": 0.6796343123905855,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004959281692198155,
|
|
"loss": 5.459,
|
|
"mean_token_accuracy": 0.15873907804489135,
|
|
"num_tokens": 15160630.0,
|
|
"step": 8735
|
|
},
|
|
{
|
|
"entropy": 5.591261196136474,
|
|
"epoch": 0.6800233417623031,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004959229186366007,
|
|
"loss": 5.4203,
|
|
"mean_token_accuracy": 0.16888799667358398,
|
|
"num_tokens": 15168999.0,
|
|
"step": 8740
|
|
},
|
|
{
|
|
"entropy": 5.640165138244629,
|
|
"epoch": 0.6804123711340206,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.000495917664701232,
|
|
"loss": 5.4996,
|
|
"mean_token_accuracy": 0.16761998534202577,
|
|
"num_tokens": 15177507.0,
|
|
"step": 8745
|
|
},
|
|
{
|
|
"entropy": 5.663268566131592,
|
|
"epoch": 0.6808014005057382,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004959124074137894,
|
|
"loss": 5.5497,
|
|
"mean_token_accuracy": 0.15307750552892685,
|
|
"num_tokens": 15186843.0,
|
|
"step": 8750
|
|
},
|
|
{
|
|
"entropy": 5.590552043914795,
|
|
"epoch": 0.6811904298774557,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004959071467743526,
|
|
"loss": 5.4358,
|
|
"mean_token_accuracy": 0.16405264288187027,
|
|
"num_tokens": 15195081.0,
|
|
"step": 8755
|
|
},
|
|
{
|
|
"entropy": 5.632944202423095,
|
|
"epoch": 0.6815794592491733,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004959018827830016,
|
|
"loss": 5.5331,
|
|
"mean_token_accuracy": 0.16543604135513307,
|
|
"num_tokens": 15203538.0,
|
|
"step": 8760
|
|
},
|
|
{
|
|
"entropy": 5.714319372177124,
|
|
"epoch": 0.6819684886208909,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.000495896615439816,
|
|
"loss": 5.5638,
|
|
"mean_token_accuracy": 0.15726466104388237,
|
|
"num_tokens": 15211845.0,
|
|
"step": 8765
|
|
},
|
|
{
|
|
"entropy": 5.64163293838501,
|
|
"epoch": 0.6823575179926085,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004958913447448759,
|
|
"loss": 5.5604,
|
|
"mean_token_accuracy": 0.16496984660625458,
|
|
"num_tokens": 15220128.0,
|
|
"step": 8770
|
|
},
|
|
{
|
|
"entropy": 5.609681749343872,
|
|
"epoch": 0.682746547364326,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004958860706982613,
|
|
"loss": 5.5371,
|
|
"mean_token_accuracy": 0.1546408787369728,
|
|
"num_tokens": 15228741.0,
|
|
"step": 8775
|
|
},
|
|
{
|
|
"entropy": 5.650665616989135,
|
|
"epoch": 0.6831355767360435,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.000495880793300052,
|
|
"loss": 5.5375,
|
|
"mean_token_accuracy": 0.1545580267906189,
|
|
"num_tokens": 15237674.0,
|
|
"step": 8780
|
|
},
|
|
{
|
|
"entropy": 5.608680534362793,
|
|
"epoch": 0.6835246061077611,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004958755125503284,
|
|
"loss": 5.4188,
|
|
"mean_token_accuracy": 0.1603718653321266,
|
|
"num_tokens": 15245727.0,
|
|
"step": 8785
|
|
},
|
|
{
|
|
"entropy": 5.636897563934326,
|
|
"epoch": 0.6839136354794787,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004958702284491703,
|
|
"loss": 5.5221,
|
|
"mean_token_accuracy": 0.1570213332772255,
|
|
"num_tokens": 15254511.0,
|
|
"step": 8790
|
|
},
|
|
{
|
|
"entropy": 5.611495447158814,
|
|
"epoch": 0.6843026648511963,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004958649409966581,
|
|
"loss": 5.4847,
|
|
"mean_token_accuracy": 0.160319522023201,
|
|
"num_tokens": 15263500.0,
|
|
"step": 8795
|
|
},
|
|
{
|
|
"entropy": 5.60971474647522,
|
|
"epoch": 0.6846916942229139,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.000495859650192872,
|
|
"loss": 5.4799,
|
|
"mean_token_accuracy": 0.16392674893140793,
|
|
"num_tokens": 15271960.0,
|
|
"step": 8800
|
|
},
|
|
{
|
|
"entropy": 5.703287553787232,
|
|
"epoch": 0.6850807235946313,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004958543560378922,
|
|
"loss": 5.6659,
|
|
"mean_token_accuracy": 0.15225871056318283,
|
|
"num_tokens": 15280576.0,
|
|
"step": 8805
|
|
},
|
|
{
|
|
"entropy": 5.663115358352661,
|
|
"epoch": 0.6854697529663489,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004958490585317991,
|
|
"loss": 5.5318,
|
|
"mean_token_accuracy": 0.1648571327328682,
|
|
"num_tokens": 15288674.0,
|
|
"step": 8810
|
|
},
|
|
{
|
|
"entropy": 5.625303268432617,
|
|
"epoch": 0.6858587823380665,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.000495843757674673,
|
|
"loss": 5.4181,
|
|
"mean_token_accuracy": 0.16334908306598664,
|
|
"num_tokens": 15296881.0,
|
|
"step": 8815
|
|
},
|
|
{
|
|
"entropy": 5.608910036087036,
|
|
"epoch": 0.6862478117097841,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004958384534665945,
|
|
"loss": 5.4782,
|
|
"mean_token_accuracy": 0.16224911957979202,
|
|
"num_tokens": 15305379.0,
|
|
"step": 8820
|
|
},
|
|
{
|
|
"entropy": 5.6033713817596436,
|
|
"epoch": 0.6866368410815017,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004958331459076438,
|
|
"loss": 5.5691,
|
|
"mean_token_accuracy": 0.15493535324931146,
|
|
"num_tokens": 15314572.0,
|
|
"step": 8825
|
|
},
|
|
{
|
|
"entropy": 5.63705039024353,
|
|
"epoch": 0.6870258704532192,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004958278349979018,
|
|
"loss": 5.5418,
|
|
"mean_token_accuracy": 0.15657844468951226,
|
|
"num_tokens": 15323407.0,
|
|
"step": 8830
|
|
},
|
|
{
|
|
"entropy": 5.627943754196167,
|
|
"epoch": 0.6874148998249368,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004958225207374488,
|
|
"loss": 5.4151,
|
|
"mean_token_accuracy": 0.15650082528591155,
|
|
"num_tokens": 15332208.0,
|
|
"step": 8835
|
|
},
|
|
{
|
|
"entropy": 5.583755350112915,
|
|
"epoch": 0.6878039291966543,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004958172031263655,
|
|
"loss": 5.4595,
|
|
"mean_token_accuracy": 0.1620849221944809,
|
|
"num_tokens": 15340972.0,
|
|
"step": 8840
|
|
},
|
|
{
|
|
"entropy": 5.57933497428894,
|
|
"epoch": 0.6881929585683719,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004958118821647326,
|
|
"loss": 5.4426,
|
|
"mean_token_accuracy": 0.1666816309094429,
|
|
"num_tokens": 15349991.0,
|
|
"step": 8845
|
|
},
|
|
{
|
|
"entropy": 5.530833578109741,
|
|
"epoch": 0.6885819879400895,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004958065578526308,
|
|
"loss": 5.3791,
|
|
"mean_token_accuracy": 0.17523722350597382,
|
|
"num_tokens": 15358194.0,
|
|
"step": 8850
|
|
},
|
|
{
|
|
"entropy": 5.619156074523926,
|
|
"epoch": 0.688971017311807,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.000495801230190141,
|
|
"loss": 5.4257,
|
|
"mean_token_accuracy": 0.163530196249485,
|
|
"num_tokens": 15366954.0,
|
|
"step": 8855
|
|
},
|
|
{
|
|
"entropy": 5.704611015319824,
|
|
"epoch": 0.6893600466835246,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004957958991773441,
|
|
"loss": 5.6093,
|
|
"mean_token_accuracy": 0.15734027922153473,
|
|
"num_tokens": 15376107.0,
|
|
"step": 8860
|
|
},
|
|
{
|
|
"entropy": 5.599389457702637,
|
|
"epoch": 0.6897490760552422,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004957905648143206,
|
|
"loss": 5.4884,
|
|
"mean_token_accuracy": 0.16068901717662812,
|
|
"num_tokens": 15384517.0,
|
|
"step": 8865
|
|
},
|
|
{
|
|
"entropy": 5.707489633560181,
|
|
"epoch": 0.6901381054269597,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004957852271011519,
|
|
"loss": 5.6396,
|
|
"mean_token_accuracy": 0.15333401635289193,
|
|
"num_tokens": 15393544.0,
|
|
"step": 8870
|
|
},
|
|
{
|
|
"entropy": 5.63929591178894,
|
|
"epoch": 0.6905271347986773,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004957798860379187,
|
|
"loss": 5.4442,
|
|
"mean_token_accuracy": 0.1683732807636261,
|
|
"num_tokens": 15402165.0,
|
|
"step": 8875
|
|
},
|
|
{
|
|
"entropy": 5.622973155975342,
|
|
"epoch": 0.6909161641703949,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004957745416247022,
|
|
"loss": 5.4916,
|
|
"mean_token_accuracy": 0.1617909163236618,
|
|
"num_tokens": 15411430.0,
|
|
"step": 8880
|
|
},
|
|
{
|
|
"entropy": 5.629455804824829,
|
|
"epoch": 0.6913051935421124,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004957691938615833,
|
|
"loss": 5.4046,
|
|
"mean_token_accuracy": 0.16690257638692857,
|
|
"num_tokens": 15420346.0,
|
|
"step": 8885
|
|
},
|
|
{
|
|
"entropy": 5.520572233200073,
|
|
"epoch": 0.69169422291383,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004957638427486434,
|
|
"loss": 5.3353,
|
|
"mean_token_accuracy": 0.17267585545778275,
|
|
"num_tokens": 15428747.0,
|
|
"step": 8890
|
|
},
|
|
{
|
|
"entropy": 5.414216136932373,
|
|
"epoch": 0.6920832522855476,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004957584882859636,
|
|
"loss": 5.3316,
|
|
"mean_token_accuracy": 0.16797439754009247,
|
|
"num_tokens": 15437110.0,
|
|
"step": 8895
|
|
},
|
|
{
|
|
"entropy": 5.571062803268433,
|
|
"epoch": 0.6924722816572652,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004957531304736251,
|
|
"loss": 5.4768,
|
|
"mean_token_accuracy": 0.16320954859256745,
|
|
"num_tokens": 15446524.0,
|
|
"step": 8900
|
|
},
|
|
{
|
|
"entropy": 5.65091347694397,
|
|
"epoch": 0.6928613110289827,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004957477693117091,
|
|
"loss": 5.5152,
|
|
"mean_token_accuracy": 0.1618165910243988,
|
|
"num_tokens": 15455372.0,
|
|
"step": 8905
|
|
},
|
|
{
|
|
"entropy": 5.650473690032959,
|
|
"epoch": 0.6932503404007002,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004957424048002971,
|
|
"loss": 5.4078,
|
|
"mean_token_accuracy": 0.16240484565496444,
|
|
"num_tokens": 15463060.0,
|
|
"step": 8910
|
|
},
|
|
{
|
|
"entropy": 5.531956577301026,
|
|
"epoch": 0.6936393697724178,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004957370369394706,
|
|
"loss": 5.5246,
|
|
"mean_token_accuracy": 0.1603606067597866,
|
|
"num_tokens": 15471836.0,
|
|
"step": 8915
|
|
},
|
|
{
|
|
"entropy": 5.662734794616699,
|
|
"epoch": 0.6940283991441354,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004957316657293107,
|
|
"loss": 5.5207,
|
|
"mean_token_accuracy": 0.16369528323411942,
|
|
"num_tokens": 15479819.0,
|
|
"step": 8920
|
|
},
|
|
{
|
|
"entropy": 5.639108276367187,
|
|
"epoch": 0.694417428515853,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004957262911698992,
|
|
"loss": 5.5088,
|
|
"mean_token_accuracy": 0.16640071272850038,
|
|
"num_tokens": 15488562.0,
|
|
"step": 8925
|
|
},
|
|
{
|
|
"entropy": 5.617952966690064,
|
|
"epoch": 0.6948064578875706,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004957209132613175,
|
|
"loss": 5.5899,
|
|
"mean_token_accuracy": 0.15694498494267464,
|
|
"num_tokens": 15497822.0,
|
|
"step": 8930
|
|
},
|
|
{
|
|
"entropy": 5.66477222442627,
|
|
"epoch": 0.695195487259288,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004957155320036473,
|
|
"loss": 5.5297,
|
|
"mean_token_accuracy": 0.15420645251870155,
|
|
"num_tokens": 15506913.0,
|
|
"step": 8935
|
|
},
|
|
{
|
|
"entropy": 5.650326061248779,
|
|
"epoch": 0.6955845166310056,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004957101473969702,
|
|
"loss": 5.4725,
|
|
"mean_token_accuracy": 0.1661776825785637,
|
|
"num_tokens": 15516053.0,
|
|
"step": 8940
|
|
},
|
|
{
|
|
"entropy": 5.649831771850586,
|
|
"epoch": 0.6959735460027232,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.000495704759441368,
|
|
"loss": 5.5135,
|
|
"mean_token_accuracy": 0.15613418817520142,
|
|
"num_tokens": 15524174.0,
|
|
"step": 8945
|
|
},
|
|
{
|
|
"entropy": 5.603764915466309,
|
|
"epoch": 0.6963625753744408,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004956993681369221,
|
|
"loss": 5.4317,
|
|
"mean_token_accuracy": 0.16271826028823852,
|
|
"num_tokens": 15533652.0,
|
|
"step": 8950
|
|
},
|
|
{
|
|
"entropy": 5.661756324768066,
|
|
"epoch": 0.6967516047461584,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004956939734837148,
|
|
"loss": 5.4747,
|
|
"mean_token_accuracy": 0.16325116157531738,
|
|
"num_tokens": 15541644.0,
|
|
"step": 8955
|
|
},
|
|
{
|
|
"entropy": 5.509464406967163,
|
|
"epoch": 0.6971406341178759,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004956885754818277,
|
|
"loss": 5.432,
|
|
"mean_token_accuracy": 0.17381385564804078,
|
|
"num_tokens": 15550298.0,
|
|
"step": 8960
|
|
},
|
|
{
|
|
"entropy": 5.629638576507569,
|
|
"epoch": 0.6975296634895934,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004956831741313427,
|
|
"loss": 5.5018,
|
|
"mean_token_accuracy": 0.1647512845695019,
|
|
"num_tokens": 15559388.0,
|
|
"step": 8965
|
|
},
|
|
{
|
|
"entropy": 5.500730657577515,
|
|
"epoch": 0.697918692861311,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004956777694323418,
|
|
"loss": 5.3335,
|
|
"mean_token_accuracy": 0.16650238931179046,
|
|
"num_tokens": 15567543.0,
|
|
"step": 8970
|
|
},
|
|
{
|
|
"entropy": 5.505261754989624,
|
|
"epoch": 0.6983077222330286,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.000495672361384907,
|
|
"loss": 5.4324,
|
|
"mean_token_accuracy": 0.1692634642124176,
|
|
"num_tokens": 15575365.0,
|
|
"step": 8975
|
|
},
|
|
{
|
|
"entropy": 5.681888818740845,
|
|
"epoch": 0.6986967516047462,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004956669499891202,
|
|
"loss": 5.4978,
|
|
"mean_token_accuracy": 0.16197374761104583,
|
|
"num_tokens": 15584295.0,
|
|
"step": 8980
|
|
},
|
|
{
|
|
"entropy": 5.666158962249756,
|
|
"epoch": 0.6990857809764637,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004956615352450639,
|
|
"loss": 5.5156,
|
|
"mean_token_accuracy": 0.17047316581010818,
|
|
"num_tokens": 15592906.0,
|
|
"step": 8985
|
|
},
|
|
{
|
|
"entropy": 5.530295705795288,
|
|
"epoch": 0.6994748103481813,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.0004956561171528198,
|
|
"loss": 5.4542,
|
|
"mean_token_accuracy": 0.15547731518745422,
|
|
"num_tokens": 15601938.0,
|
|
"step": 8990
|
|
},
|
|
{
|
|
"entropy": 5.546193027496338,
|
|
"epoch": 0.6998638397198989,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004956506957124704,
|
|
"loss": 5.4481,
|
|
"mean_token_accuracy": 0.16723582297563552,
|
|
"num_tokens": 15610173.0,
|
|
"step": 8995
|
|
},
|
|
{
|
|
"entropy": 5.643675851821899,
|
|
"epoch": 0.7002528690916164,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.000495645270924098,
|
|
"loss": 5.5277,
|
|
"mean_token_accuracy": 0.15238175243139268,
|
|
"num_tokens": 15618896.0,
|
|
"step": 9000
|
|
},
|
|
{
|
|
"epoch": 0.7002528690916164,
|
|
"eval_entropy": 5.48892997332326,
|
|
"eval_loss": 5.537880897521973,
|
|
"eval_mean_token_accuracy": 0.16768242414104928,
|
|
"eval_num_tokens": 15618896.0,
|
|
"eval_runtime": 28.6719,
|
|
"eval_samples_per_second": 1449.435,
|
|
"eval_steps_per_second": 181.188,
|
|
"step": 9000
|
|
},
|
|
{
|
|
"entropy": 5.598692321777344,
|
|
"epoch": 0.700641898463334,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004956398427877847,
|
|
"loss": 5.446,
|
|
"mean_token_accuracy": 0.16387993842363358,
|
|
"num_tokens": 15627890.0,
|
|
"step": 9005
|
|
},
|
|
{
|
|
"entropy": 5.573201608657837,
|
|
"epoch": 0.7010309278350515,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.000495634411303613,
|
|
"loss": 5.3828,
|
|
"mean_token_accuracy": 0.1656647354364395,
|
|
"num_tokens": 15636290.0,
|
|
"step": 9010
|
|
},
|
|
{
|
|
"entropy": 5.572251892089843,
|
|
"epoch": 0.7014199572067691,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004956289764716654,
|
|
"loss": 5.4455,
|
|
"mean_token_accuracy": 0.16509263068437577,
|
|
"num_tokens": 15644777.0,
|
|
"step": 9015
|
|
},
|
|
{
|
|
"entropy": 5.600341558456421,
|
|
"epoch": 0.7018089865784867,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004956235382920241,
|
|
"loss": 5.4793,
|
|
"mean_token_accuracy": 0.15838624760508538,
|
|
"num_tokens": 15653333.0,
|
|
"step": 9020
|
|
},
|
|
{
|
|
"entropy": 5.6746580600738525,
|
|
"epoch": 0.7021980159502043,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004956180967647717,
|
|
"loss": 5.4714,
|
|
"mean_token_accuracy": 0.16225895434617996,
|
|
"num_tokens": 15662140.0,
|
|
"step": 9025
|
|
},
|
|
{
|
|
"entropy": 5.617575931549072,
|
|
"epoch": 0.7025870453219218,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004956126518899911,
|
|
"loss": 5.5609,
|
|
"mean_token_accuracy": 0.1655264288187027,
|
|
"num_tokens": 15671387.0,
|
|
"step": 9030
|
|
},
|
|
{
|
|
"entropy": 5.625704574584961,
|
|
"epoch": 0.7029760746936393,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004956072036677644,
|
|
"loss": 5.4991,
|
|
"mean_token_accuracy": 0.1554996997117996,
|
|
"num_tokens": 15680884.0,
|
|
"step": 9035
|
|
},
|
|
{
|
|
"entropy": 5.684255933761596,
|
|
"epoch": 0.7033651040653569,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004956017520981746,
|
|
"loss": 5.4485,
|
|
"mean_token_accuracy": 0.158163383603096,
|
|
"num_tokens": 15690030.0,
|
|
"step": 9040
|
|
},
|
|
{
|
|
"entropy": 5.610305118560791,
|
|
"epoch": 0.7037541334370745,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004955962971813044,
|
|
"loss": 5.467,
|
|
"mean_token_accuracy": 0.1622978761792183,
|
|
"num_tokens": 15698260.0,
|
|
"step": 9045
|
|
},
|
|
{
|
|
"entropy": 5.518650770187378,
|
|
"epoch": 0.7041431628087921,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004955908389172364,
|
|
"loss": 5.3716,
|
|
"mean_token_accuracy": 0.17074191123247145,
|
|
"num_tokens": 15706275.0,
|
|
"step": 9050
|
|
},
|
|
{
|
|
"entropy": 5.656791067123413,
|
|
"epoch": 0.7045321921805097,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004955853773060536,
|
|
"loss": 5.6008,
|
|
"mean_token_accuracy": 0.16207863092422486,
|
|
"num_tokens": 15715086.0,
|
|
"step": 9055
|
|
},
|
|
{
|
|
"entropy": 5.6516862392425535,
|
|
"epoch": 0.7049212215522271,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004955799123478388,
|
|
"loss": 5.4052,
|
|
"mean_token_accuracy": 0.16449855417013168,
|
|
"num_tokens": 15723931.0,
|
|
"step": 9060
|
|
},
|
|
{
|
|
"entropy": 5.590332937240601,
|
|
"epoch": 0.7053102509239447,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004955744440426748,
|
|
"loss": 5.5517,
|
|
"mean_token_accuracy": 0.16194690018892288,
|
|
"num_tokens": 15732905.0,
|
|
"step": 9065
|
|
},
|
|
{
|
|
"entropy": 5.602451610565185,
|
|
"epoch": 0.7056992802956623,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004955689723906448,
|
|
"loss": 5.4469,
|
|
"mean_token_accuracy": 0.1638907566666603,
|
|
"num_tokens": 15742355.0,
|
|
"step": 9070
|
|
},
|
|
{
|
|
"entropy": 5.709460067749023,
|
|
"epoch": 0.7060883096673799,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004955634973918318,
|
|
"loss": 5.521,
|
|
"mean_token_accuracy": 0.16189123094081878,
|
|
"num_tokens": 15750924.0,
|
|
"step": 9075
|
|
},
|
|
{
|
|
"entropy": 5.617863130569458,
|
|
"epoch": 0.7064773390390975,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004955580190463186,
|
|
"loss": 5.4484,
|
|
"mean_token_accuracy": 0.16356792151927949,
|
|
"num_tokens": 15759677.0,
|
|
"step": 9080
|
|
},
|
|
{
|
|
"entropy": 5.595055437088012,
|
|
"epoch": 0.7068663684108151,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004955525373541886,
|
|
"loss": 5.4445,
|
|
"mean_token_accuracy": 0.15860881954431533,
|
|
"num_tokens": 15767875.0,
|
|
"step": 9085
|
|
},
|
|
{
|
|
"entropy": 5.545309209823609,
|
|
"epoch": 0.7072553977825325,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004955470523155249,
|
|
"loss": 5.4341,
|
|
"mean_token_accuracy": 0.16337229758501054,
|
|
"num_tokens": 15776194.0,
|
|
"step": 9090
|
|
},
|
|
{
|
|
"entropy": 5.632459306716919,
|
|
"epoch": 0.7076444271542501,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004955415639304107,
|
|
"loss": 5.5201,
|
|
"mean_token_accuracy": 0.16406060010194778,
|
|
"num_tokens": 15784774.0,
|
|
"step": 9095
|
|
},
|
|
{
|
|
"entropy": 5.611529779434204,
|
|
"epoch": 0.7080334565259677,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004955360721989292,
|
|
"loss": 5.3971,
|
|
"mean_token_accuracy": 0.170825731754303,
|
|
"num_tokens": 15793121.0,
|
|
"step": 9100
|
|
},
|
|
{
|
|
"entropy": 5.703958511352539,
|
|
"epoch": 0.7084224858976853,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004955305771211641,
|
|
"loss": 5.6047,
|
|
"mean_token_accuracy": 0.1560478091239929,
|
|
"num_tokens": 15801518.0,
|
|
"step": 9105
|
|
},
|
|
{
|
|
"entropy": 5.6174711227417,
|
|
"epoch": 0.7088115152694029,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004955250786971982,
|
|
"loss": 5.3588,
|
|
"mean_token_accuracy": 0.1709561228752136,
|
|
"num_tokens": 15809602.0,
|
|
"step": 9110
|
|
},
|
|
{
|
|
"entropy": 5.60283932685852,
|
|
"epoch": 0.7092005446411204,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004955195769271154,
|
|
"loss": 5.5686,
|
|
"mean_token_accuracy": 0.15899789780378343,
|
|
"num_tokens": 15818529.0,
|
|
"step": 9115
|
|
},
|
|
{
|
|
"entropy": 5.648442792892456,
|
|
"epoch": 0.709589574012838,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004955140718109991,
|
|
"loss": 5.4401,
|
|
"mean_token_accuracy": 0.173095266520977,
|
|
"num_tokens": 15827176.0,
|
|
"step": 9120
|
|
},
|
|
{
|
|
"entropy": 5.634540843963623,
|
|
"epoch": 0.7099786033845555,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004955085633489326,
|
|
"loss": 5.521,
|
|
"mean_token_accuracy": 0.1553187772631645,
|
|
"num_tokens": 15837095.0,
|
|
"step": 9125
|
|
},
|
|
{
|
|
"entropy": 5.575646877288818,
|
|
"epoch": 0.7103676327562731,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004955030515409997,
|
|
"loss": 5.4907,
|
|
"mean_token_accuracy": 0.16527149379253386,
|
|
"num_tokens": 15845285.0,
|
|
"step": 9130
|
|
},
|
|
{
|
|
"entropy": 5.5941849708557125,
|
|
"epoch": 0.7107566621279907,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004954975363872838,
|
|
"loss": 5.4942,
|
|
"mean_token_accuracy": 0.16929271966218948,
|
|
"num_tokens": 15853468.0,
|
|
"step": 9135
|
|
},
|
|
{
|
|
"entropy": 5.637126636505127,
|
|
"epoch": 0.7111456914997082,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004954920178878689,
|
|
"loss": 5.431,
|
|
"mean_token_accuracy": 0.16908954679965973,
|
|
"num_tokens": 15861699.0,
|
|
"step": 9140
|
|
},
|
|
{
|
|
"entropy": 5.6686560153961185,
|
|
"epoch": 0.7115347208714258,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004954864960428385,
|
|
"loss": 5.5156,
|
|
"mean_token_accuracy": 0.15655331686139107,
|
|
"num_tokens": 15870401.0,
|
|
"step": 9145
|
|
},
|
|
{
|
|
"entropy": 5.5921454429626465,
|
|
"epoch": 0.7119237502431434,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004954809708522765,
|
|
"loss": 5.3192,
|
|
"mean_token_accuracy": 0.17602779418230058,
|
|
"num_tokens": 15878214.0,
|
|
"step": 9150
|
|
},
|
|
{
|
|
"entropy": 5.578209257125854,
|
|
"epoch": 0.712312779614861,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004954754423162667,
|
|
"loss": 5.5048,
|
|
"mean_token_accuracy": 0.1651099443435669,
|
|
"num_tokens": 15886581.0,
|
|
"step": 9155
|
|
},
|
|
{
|
|
"entropy": 5.6807318210601805,
|
|
"epoch": 0.7127018089865785,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.000495469910434893,
|
|
"loss": 5.6188,
|
|
"mean_token_accuracy": 0.15459591150283813,
|
|
"num_tokens": 15895748.0,
|
|
"step": 9160
|
|
},
|
|
{
|
|
"entropy": 5.697744464874267,
|
|
"epoch": 0.713090838358296,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004954643752082392,
|
|
"loss": 5.4706,
|
|
"mean_token_accuracy": 0.15997869968414308,
|
|
"num_tokens": 15905030.0,
|
|
"step": 9165
|
|
},
|
|
{
|
|
"entropy": 5.5733599185943605,
|
|
"epoch": 0.7134798677300136,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004954588366363896,
|
|
"loss": 5.453,
|
|
"mean_token_accuracy": 0.15960024297237396,
|
|
"num_tokens": 15913430.0,
|
|
"step": 9170
|
|
},
|
|
{
|
|
"entropy": 5.546750068664551,
|
|
"epoch": 0.7138688971017312,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004954532947194279,
|
|
"loss": 5.3884,
|
|
"mean_token_accuracy": 0.16921509355306624,
|
|
"num_tokens": 15921432.0,
|
|
"step": 9175
|
|
},
|
|
{
|
|
"entropy": 5.661558675765991,
|
|
"epoch": 0.7142579264734488,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004954477494574384,
|
|
"loss": 5.4398,
|
|
"mean_token_accuracy": 0.1639270529150963,
|
|
"num_tokens": 15930159.0,
|
|
"step": 9180
|
|
},
|
|
{
|
|
"entropy": 5.588769388198853,
|
|
"epoch": 0.7146469558451664,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004954422008505052,
|
|
"loss": 5.5109,
|
|
"mean_token_accuracy": 0.15652605295181274,
|
|
"num_tokens": 15939911.0,
|
|
"step": 9185
|
|
},
|
|
{
|
|
"entropy": 5.568434810638427,
|
|
"epoch": 0.7150359852168838,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004954366488987125,
|
|
"loss": 5.4305,
|
|
"mean_token_accuracy": 0.16211689561605452,
|
|
"num_tokens": 15948586.0,
|
|
"step": 9190
|
|
},
|
|
{
|
|
"entropy": 5.506918573379517,
|
|
"epoch": 0.7154250145886014,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004954310936021444,
|
|
"loss": 5.3097,
|
|
"mean_token_accuracy": 0.1671778976917267,
|
|
"num_tokens": 15956818.0,
|
|
"step": 9195
|
|
},
|
|
{
|
|
"entropy": 5.614367055892944,
|
|
"epoch": 0.715814043960319,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004954255349608853,
|
|
"loss": 5.5179,
|
|
"mean_token_accuracy": 0.15673997849225998,
|
|
"num_tokens": 15966027.0,
|
|
"step": 9200
|
|
},
|
|
{
|
|
"entropy": 5.669200229644775,
|
|
"epoch": 0.7162030733320366,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004954199729750198,
|
|
"loss": 5.5671,
|
|
"mean_token_accuracy": 0.1588587701320648,
|
|
"num_tokens": 15975186.0,
|
|
"step": 9205
|
|
},
|
|
{
|
|
"entropy": 5.546558856964111,
|
|
"epoch": 0.7165921027037542,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004954144076446318,
|
|
"loss": 5.4239,
|
|
"mean_token_accuracy": 0.1685514986515045,
|
|
"num_tokens": 15983924.0,
|
|
"step": 9210
|
|
},
|
|
{
|
|
"entropy": 5.585919570922852,
|
|
"epoch": 0.7169811320754716,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004954088389698061,
|
|
"loss": 5.4512,
|
|
"mean_token_accuracy": 0.17108927965164183,
|
|
"num_tokens": 15992906.0,
|
|
"step": 9215
|
|
},
|
|
{
|
|
"entropy": 5.5795739650726315,
|
|
"epoch": 0.7173701614471892,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.000495403266950627,
|
|
"loss": 5.4739,
|
|
"mean_token_accuracy": 0.16261557191610337,
|
|
"num_tokens": 16001378.0,
|
|
"step": 9220
|
|
},
|
|
{
|
|
"entropy": 5.598306322097779,
|
|
"epoch": 0.7177591908189068,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004953976915871792,
|
|
"loss": 5.4686,
|
|
"mean_token_accuracy": 0.16207181066274642,
|
|
"num_tokens": 16010704.0,
|
|
"step": 9225
|
|
},
|
|
{
|
|
"entropy": 5.566759204864502,
|
|
"epoch": 0.7181482201906244,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004953921128795472,
|
|
"loss": 5.4508,
|
|
"mean_token_accuracy": 0.1655542552471161,
|
|
"num_tokens": 16018936.0,
|
|
"step": 9230
|
|
},
|
|
{
|
|
"entropy": 5.593916034698486,
|
|
"epoch": 0.718537249562342,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004953865308278156,
|
|
"loss": 5.3588,
|
|
"mean_token_accuracy": 0.1663544625043869,
|
|
"num_tokens": 16027295.0,
|
|
"step": 9235
|
|
},
|
|
{
|
|
"entropy": 5.501459980010987,
|
|
"epoch": 0.7189262789340595,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004953809454320693,
|
|
"loss": 5.3808,
|
|
"mean_token_accuracy": 0.16815916448831558,
|
|
"num_tokens": 16036493.0,
|
|
"step": 9240
|
|
},
|
|
{
|
|
"entropy": 5.560643815994263,
|
|
"epoch": 0.7193153083057771,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004953753566923929,
|
|
"loss": 5.5038,
|
|
"mean_token_accuracy": 0.1660083144903183,
|
|
"num_tokens": 16045406.0,
|
|
"step": 9245
|
|
},
|
|
{
|
|
"entropy": 5.623446416854859,
|
|
"epoch": 0.7197043376774946,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004953697646088712,
|
|
"loss": 5.4826,
|
|
"mean_token_accuracy": 0.16748983412981033,
|
|
"num_tokens": 16054126.0,
|
|
"step": 9250
|
|
},
|
|
{
|
|
"entropy": 5.632719039916992,
|
|
"epoch": 0.7200933670492122,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004953641691815891,
|
|
"loss": 5.5064,
|
|
"mean_token_accuracy": 0.15853000283241273,
|
|
"num_tokens": 16063921.0,
|
|
"step": 9255
|
|
},
|
|
{
|
|
"entropy": 5.6339634418487545,
|
|
"epoch": 0.7204823964209298,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004953585704106315,
|
|
"loss": 5.5061,
|
|
"mean_token_accuracy": 0.16534079760313034,
|
|
"num_tokens": 16072160.0,
|
|
"step": 9260
|
|
},
|
|
{
|
|
"entropy": 5.63057131767273,
|
|
"epoch": 0.7208714257926473,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004953529682960832,
|
|
"loss": 5.4452,
|
|
"mean_token_accuracy": 0.1626740127801895,
|
|
"num_tokens": 16080794.0,
|
|
"step": 9265
|
|
},
|
|
{
|
|
"entropy": 5.553777599334717,
|
|
"epoch": 0.7212604551643649,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004953473628380295,
|
|
"loss": 5.4747,
|
|
"mean_token_accuracy": 0.1672894313931465,
|
|
"num_tokens": 16089615.0,
|
|
"step": 9270
|
|
},
|
|
{
|
|
"entropy": 5.552600383758545,
|
|
"epoch": 0.7216494845360825,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004953417540365553,
|
|
"loss": 5.394,
|
|
"mean_token_accuracy": 0.15982172787189483,
|
|
"num_tokens": 16098363.0,
|
|
"step": 9275
|
|
},
|
|
{
|
|
"entropy": 5.596477413177491,
|
|
"epoch": 0.7220385139078,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004953361418917455,
|
|
"loss": 5.4838,
|
|
"mean_token_accuracy": 0.15724485367536545,
|
|
"num_tokens": 16106837.0,
|
|
"step": 9280
|
|
},
|
|
{
|
|
"entropy": 5.656517791748047,
|
|
"epoch": 0.7224275432795176,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004953305264036856,
|
|
"loss": 5.4247,
|
|
"mean_token_accuracy": 0.1660174235701561,
|
|
"num_tokens": 16114923.0,
|
|
"step": 9285
|
|
},
|
|
{
|
|
"entropy": 5.614937114715576,
|
|
"epoch": 0.7228165726512352,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004953249075724607,
|
|
"loss": 5.4609,
|
|
"mean_token_accuracy": 0.15922097563743592,
|
|
"num_tokens": 16123698.0,
|
|
"step": 9290
|
|
},
|
|
{
|
|
"entropy": 5.586376905441284,
|
|
"epoch": 0.7232056020229527,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004953192853981559,
|
|
"loss": 5.4395,
|
|
"mean_token_accuracy": 0.1639003649353981,
|
|
"num_tokens": 16132361.0,
|
|
"step": 9295
|
|
},
|
|
{
|
|
"entropy": 5.663545083999634,
|
|
"epoch": 0.7235946313946703,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004953136598808566,
|
|
"loss": 5.5057,
|
|
"mean_token_accuracy": 0.1602555587887764,
|
|
"num_tokens": 16141554.0,
|
|
"step": 9300
|
|
},
|
|
{
|
|
"entropy": 5.642953014373779,
|
|
"epoch": 0.7239836607663879,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004953080310206481,
|
|
"loss": 5.4305,
|
|
"mean_token_accuracy": 0.16263717859983445,
|
|
"num_tokens": 16150206.0,
|
|
"step": 9305
|
|
},
|
|
{
|
|
"entropy": 5.631220960617066,
|
|
"epoch": 0.7243726901381055,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004953023988176162,
|
|
"loss": 5.5605,
|
|
"mean_token_accuracy": 0.1562460854649544,
|
|
"num_tokens": 16158995.0,
|
|
"step": 9310
|
|
},
|
|
{
|
|
"entropy": 5.60384202003479,
|
|
"epoch": 0.724761719509823,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004952967632718458,
|
|
"loss": 5.52,
|
|
"mean_token_accuracy": 0.15501880943775176,
|
|
"num_tokens": 16167809.0,
|
|
"step": 9315
|
|
},
|
|
{
|
|
"entropy": 5.793039560317993,
|
|
"epoch": 0.7251507488815405,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004952911243834227,
|
|
"loss": 5.6074,
|
|
"mean_token_accuracy": 0.15796300321817397,
|
|
"num_tokens": 16176257.0,
|
|
"step": 9320
|
|
},
|
|
{
|
|
"entropy": 5.660436630249023,
|
|
"epoch": 0.7255397782532581,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004952854821524324,
|
|
"loss": 5.5777,
|
|
"mean_token_accuracy": 0.15514086186885834,
|
|
"num_tokens": 16185597.0,
|
|
"step": 9325
|
|
},
|
|
{
|
|
"entropy": 5.703607749938965,
|
|
"epoch": 0.7259288076249757,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004952798365789606,
|
|
"loss": 5.5843,
|
|
"mean_token_accuracy": 0.15821659713983535,
|
|
"num_tokens": 16194591.0,
|
|
"step": 9330
|
|
},
|
|
{
|
|
"entropy": 5.749100112915039,
|
|
"epoch": 0.7263178369966933,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004952741876630928,
|
|
"loss": 5.5342,
|
|
"mean_token_accuracy": 0.1550159201025963,
|
|
"num_tokens": 16203073.0,
|
|
"step": 9335
|
|
},
|
|
{
|
|
"entropy": 5.5745586395263675,
|
|
"epoch": 0.7267068663684109,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004952685354049148,
|
|
"loss": 5.497,
|
|
"mean_token_accuracy": 0.1630001738667488,
|
|
"num_tokens": 16211208.0,
|
|
"step": 9340
|
|
},
|
|
{
|
|
"entropy": 5.6307062149047855,
|
|
"epoch": 0.7270958957401283,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004952628798045124,
|
|
"loss": 5.439,
|
|
"mean_token_accuracy": 0.1698139950633049,
|
|
"num_tokens": 16219687.0,
|
|
"step": 9345
|
|
},
|
|
{
|
|
"entropy": 5.658086538314819,
|
|
"epoch": 0.7274849251118459,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004952572208619714,
|
|
"loss": 5.539,
|
|
"mean_token_accuracy": 0.1642148092389107,
|
|
"num_tokens": 16228214.0,
|
|
"step": 9350
|
|
},
|
|
{
|
|
"entropy": 5.654706954956055,
|
|
"epoch": 0.7278739544835635,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004952515585773778,
|
|
"loss": 5.6282,
|
|
"mean_token_accuracy": 0.15758585929870605,
|
|
"num_tokens": 16237765.0,
|
|
"step": 9355
|
|
},
|
|
{
|
|
"entropy": 5.650431346893311,
|
|
"epoch": 0.7282629838552811,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004952458929508171,
|
|
"loss": 5.4818,
|
|
"mean_token_accuracy": 0.17496364265680314,
|
|
"num_tokens": 16245339.0,
|
|
"step": 9360
|
|
},
|
|
{
|
|
"entropy": 5.55873589515686,
|
|
"epoch": 0.7286520132269987,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004952402239823757,
|
|
"loss": 5.4573,
|
|
"mean_token_accuracy": 0.15955497622489928,
|
|
"num_tokens": 16253966.0,
|
|
"step": 9365
|
|
},
|
|
{
|
|
"entropy": 5.583206415176392,
|
|
"epoch": 0.7290410425987162,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004952345516721393,
|
|
"loss": 5.4502,
|
|
"mean_token_accuracy": 0.16356470733880996,
|
|
"num_tokens": 16262859.0,
|
|
"step": 9370
|
|
},
|
|
{
|
|
"entropy": 5.610286617279053,
|
|
"epoch": 0.7294300719704337,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004952288760201942,
|
|
"loss": 5.5051,
|
|
"mean_token_accuracy": 0.16029743254184722,
|
|
"num_tokens": 16271646.0,
|
|
"step": 9375
|
|
},
|
|
{
|
|
"entropy": 5.547354507446289,
|
|
"epoch": 0.7298191013421513,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004952231970266265,
|
|
"loss": 5.4811,
|
|
"mean_token_accuracy": 0.15630216598510743,
|
|
"num_tokens": 16281058.0,
|
|
"step": 9380
|
|
},
|
|
{
|
|
"entropy": 5.652565431594849,
|
|
"epoch": 0.7302081307138689,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004952175146915223,
|
|
"loss": 5.4287,
|
|
"mean_token_accuracy": 0.1669951409101486,
|
|
"num_tokens": 16289039.0,
|
|
"step": 9385
|
|
},
|
|
{
|
|
"entropy": 5.510778188705444,
|
|
"epoch": 0.7305971600855865,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004952118290149679,
|
|
"loss": 5.3194,
|
|
"mean_token_accuracy": 0.17808689475059508,
|
|
"num_tokens": 16297373.0,
|
|
"step": 9390
|
|
},
|
|
{
|
|
"entropy": 5.546924877166748,
|
|
"epoch": 0.730986189457304,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004952061399970492,
|
|
"loss": 5.5022,
|
|
"mean_token_accuracy": 0.15341666340827942,
|
|
"num_tokens": 16306066.0,
|
|
"step": 9395
|
|
},
|
|
{
|
|
"entropy": 5.642647647857666,
|
|
"epoch": 0.7313752188290216,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.000495200447637853,
|
|
"loss": 5.5518,
|
|
"mean_token_accuracy": 0.15412714183330536,
|
|
"num_tokens": 16315282.0,
|
|
"step": 9400
|
|
},
|
|
{
|
|
"entropy": 5.785994386672973,
|
|
"epoch": 0.7317642482007392,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004951947519374655,
|
|
"loss": 5.6386,
|
|
"mean_token_accuracy": 0.15836541950702668,
|
|
"num_tokens": 16324830.0,
|
|
"step": 9405
|
|
},
|
|
{
|
|
"entropy": 5.633684873580933,
|
|
"epoch": 0.7321532775724567,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004951890528959731,
|
|
"loss": 5.4955,
|
|
"mean_token_accuracy": 0.16180311292409896,
|
|
"num_tokens": 16332990.0,
|
|
"step": 9410
|
|
},
|
|
{
|
|
"entropy": 5.587968397140503,
|
|
"epoch": 0.7325423069441743,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004951833505134623,
|
|
"loss": 5.4687,
|
|
"mean_token_accuracy": 0.1543179526925087,
|
|
"num_tokens": 16342115.0,
|
|
"step": 9415
|
|
},
|
|
{
|
|
"entropy": 5.665604782104492,
|
|
"epoch": 0.7329313363158918,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004951776447900196,
|
|
"loss": 5.4552,
|
|
"mean_token_accuracy": 0.16402145326137543,
|
|
"num_tokens": 16350329.0,
|
|
"step": 9420
|
|
},
|
|
{
|
|
"entropy": 5.574960565567016,
|
|
"epoch": 0.7333203656876094,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004951719357257317,
|
|
"loss": 5.5541,
|
|
"mean_token_accuracy": 0.16425096988677979,
|
|
"num_tokens": 16358890.0,
|
|
"step": 9425
|
|
},
|
|
{
|
|
"entropy": 5.708090877532959,
|
|
"epoch": 0.733709395059327,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.000495166223320685,
|
|
"loss": 5.5926,
|
|
"mean_token_accuracy": 0.1554354265332222,
|
|
"num_tokens": 16367338.0,
|
|
"step": 9430
|
|
},
|
|
{
|
|
"entropy": 5.721589708328247,
|
|
"epoch": 0.7340984244310446,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004951605075749662,
|
|
"loss": 5.5067,
|
|
"mean_token_accuracy": 0.16801688820123672,
|
|
"num_tokens": 16375472.0,
|
|
"step": 9435
|
|
},
|
|
{
|
|
"entropy": 5.642661428451538,
|
|
"epoch": 0.7344874538027621,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004951547884886623,
|
|
"loss": 5.4899,
|
|
"mean_token_accuracy": 0.1639014407992363,
|
|
"num_tokens": 16384212.0,
|
|
"step": 9440
|
|
},
|
|
{
|
|
"entropy": 5.571622610092163,
|
|
"epoch": 0.7348764831744796,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004951490660618598,
|
|
"loss": 5.388,
|
|
"mean_token_accuracy": 0.1667047306895256,
|
|
"num_tokens": 16393447.0,
|
|
"step": 9445
|
|
},
|
|
{
|
|
"entropy": 5.558136415481568,
|
|
"epoch": 0.7352655125461972,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004951433402946457,
|
|
"loss": 5.3829,
|
|
"mean_token_accuracy": 0.1678649365901947,
|
|
"num_tokens": 16401876.0,
|
|
"step": 9450
|
|
},
|
|
{
|
|
"entropy": 5.6018385887146,
|
|
"epoch": 0.7356545419179148,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004951376111871068,
|
|
"loss": 5.4963,
|
|
"mean_token_accuracy": 0.17034075856208802,
|
|
"num_tokens": 16411020.0,
|
|
"step": 9455
|
|
},
|
|
{
|
|
"entropy": 5.632222080230713,
|
|
"epoch": 0.7360435712896324,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004951318787393299,
|
|
"loss": 5.5339,
|
|
"mean_token_accuracy": 0.15947003960609435,
|
|
"num_tokens": 16420492.0,
|
|
"step": 9460
|
|
},
|
|
{
|
|
"entropy": 5.598445320129395,
|
|
"epoch": 0.73643260066135,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004951261429514023,
|
|
"loss": 5.4316,
|
|
"mean_token_accuracy": 0.16751165241003035,
|
|
"num_tokens": 16429277.0,
|
|
"step": 9465
|
|
},
|
|
{
|
|
"entropy": 5.616234636306762,
|
|
"epoch": 0.7368216300330674,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004951204038234106,
|
|
"loss": 5.4709,
|
|
"mean_token_accuracy": 0.16523509919643403,
|
|
"num_tokens": 16438008.0,
|
|
"step": 9470
|
|
},
|
|
{
|
|
"entropy": 5.654847097396851,
|
|
"epoch": 0.737210659404785,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004951146613554424,
|
|
"loss": 5.4806,
|
|
"mean_token_accuracy": 0.16680918782949447,
|
|
"num_tokens": 16446791.0,
|
|
"step": 9475
|
|
},
|
|
{
|
|
"entropy": 5.593355751037597,
|
|
"epoch": 0.7375996887765026,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004951089155475843,
|
|
"loss": 5.5062,
|
|
"mean_token_accuracy": 0.16251966655254363,
|
|
"num_tokens": 16455277.0,
|
|
"step": 9480
|
|
},
|
|
{
|
|
"entropy": 5.593828105926514,
|
|
"epoch": 0.7379887181482202,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.000495103166399924,
|
|
"loss": 5.4303,
|
|
"mean_token_accuracy": 0.16394807398319244,
|
|
"num_tokens": 16463310.0,
|
|
"step": 9485
|
|
},
|
|
{
|
|
"entropy": 5.653588676452637,
|
|
"epoch": 0.7383777475199378,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004950974139125484,
|
|
"loss": 5.4723,
|
|
"mean_token_accuracy": 0.1603311374783516,
|
|
"num_tokens": 16472421.0,
|
|
"step": 9490
|
|
},
|
|
{
|
|
"entropy": 5.643746042251587,
|
|
"epoch": 0.7387667768916554,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004950916580855448,
|
|
"loss": 5.5334,
|
|
"mean_token_accuracy": 0.16023790836334229,
|
|
"num_tokens": 16481814.0,
|
|
"step": 9495
|
|
},
|
|
{
|
|
"entropy": 5.6236348152160645,
|
|
"epoch": 0.7391558062633728,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004950858989190007,
|
|
"loss": 5.5019,
|
|
"mean_token_accuracy": 0.15711402893066406,
|
|
"num_tokens": 16490902.0,
|
|
"step": 9500
|
|
},
|
|
{
|
|
"entropy": 5.670229244232178,
|
|
"epoch": 0.7395448356350904,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004950801364130032,
|
|
"loss": 5.4574,
|
|
"mean_token_accuracy": 0.16394625455141068,
|
|
"num_tokens": 16499418.0,
|
|
"step": 9505
|
|
},
|
|
{
|
|
"entropy": 5.550073432922363,
|
|
"epoch": 0.739933865006808,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004950743705676401,
|
|
"loss": 5.3998,
|
|
"mean_token_accuracy": 0.16792995035648345,
|
|
"num_tokens": 16508578.0,
|
|
"step": 9510
|
|
},
|
|
{
|
|
"entropy": 5.5597185611724855,
|
|
"epoch": 0.7403228943785256,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004950686013829987,
|
|
"loss": 5.4663,
|
|
"mean_token_accuracy": 0.16282816976308823,
|
|
"num_tokens": 16517356.0,
|
|
"step": 9515
|
|
},
|
|
{
|
|
"entropy": 5.569721984863281,
|
|
"epoch": 0.7407119237502432,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004950628288591665,
|
|
"loss": 5.4441,
|
|
"mean_token_accuracy": 0.15830240696668624,
|
|
"num_tokens": 16525834.0,
|
|
"step": 9520
|
|
},
|
|
{
|
|
"entropy": 5.61745057106018,
|
|
"epoch": 0.7411009531219607,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004950570529962311,
|
|
"loss": 5.4867,
|
|
"mean_token_accuracy": 0.16102957129478454,
|
|
"num_tokens": 16534513.0,
|
|
"step": 9525
|
|
},
|
|
{
|
|
"entropy": 5.634679746627808,
|
|
"epoch": 0.7414899824936783,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004950512737942803,
|
|
"loss": 5.4562,
|
|
"mean_token_accuracy": 0.1676692172884941,
|
|
"num_tokens": 16543326.0,
|
|
"step": 9530
|
|
},
|
|
{
|
|
"entropy": 5.561607074737549,
|
|
"epoch": 0.7418790118653958,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004950454912534015,
|
|
"loss": 5.4452,
|
|
"mean_token_accuracy": 0.16409103125333785,
|
|
"num_tokens": 16551589.0,
|
|
"step": 9535
|
|
},
|
|
{
|
|
"entropy": 5.591177320480346,
|
|
"epoch": 0.7422680412371134,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004950397053736827,
|
|
"loss": 5.4473,
|
|
"mean_token_accuracy": 0.1670309916138649,
|
|
"num_tokens": 16560261.0,
|
|
"step": 9540
|
|
},
|
|
{
|
|
"entropy": 5.590814447402954,
|
|
"epoch": 0.742657070608831,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004950339161552117,
|
|
"loss": 5.4316,
|
|
"mean_token_accuracy": 0.16776785999536514,
|
|
"num_tokens": 16568645.0,
|
|
"step": 9545
|
|
},
|
|
{
|
|
"entropy": 5.56022047996521,
|
|
"epoch": 0.7430460999805485,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004950281235980761,
|
|
"loss": 5.4474,
|
|
"mean_token_accuracy": 0.16762655973434448,
|
|
"num_tokens": 16577206.0,
|
|
"step": 9550
|
|
},
|
|
{
|
|
"entropy": 5.632214689254761,
|
|
"epoch": 0.7434351293522661,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.000495022327702364,
|
|
"loss": 5.4363,
|
|
"mean_token_accuracy": 0.16455136835575104,
|
|
"num_tokens": 16585011.0,
|
|
"step": 9555
|
|
},
|
|
{
|
|
"entropy": 5.6199352741241455,
|
|
"epoch": 0.7438241587239837,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.0004950165284681631,
|
|
"loss": 5.4862,
|
|
"mean_token_accuracy": 0.1609924092888832,
|
|
"num_tokens": 16593574.0,
|
|
"step": 9560
|
|
},
|
|
{
|
|
"entropy": 5.594768810272217,
|
|
"epoch": 0.7442131880957013,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004950107258955618,
|
|
"loss": 5.4256,
|
|
"mean_token_accuracy": 0.16947073340415955,
|
|
"num_tokens": 16603023.0,
|
|
"step": 9565
|
|
},
|
|
{
|
|
"entropy": 5.702660179138183,
|
|
"epoch": 0.7446022174674188,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004950049199846479,
|
|
"loss": 5.5135,
|
|
"mean_token_accuracy": 0.16235789135098458,
|
|
"num_tokens": 16611963.0,
|
|
"step": 9570
|
|
},
|
|
{
|
|
"entropy": 5.64899435043335,
|
|
"epoch": 0.7449912468391363,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004949991107355095,
|
|
"loss": 5.4564,
|
|
"mean_token_accuracy": 0.16407136619091034,
|
|
"num_tokens": 16619942.0,
|
|
"step": 9575
|
|
},
|
|
{
|
|
"entropy": 5.508935070037841,
|
|
"epoch": 0.7453802762108539,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004949932981482347,
|
|
"loss": 5.3456,
|
|
"mean_token_accuracy": 0.16973289400339125,
|
|
"num_tokens": 16628261.0,
|
|
"step": 9580
|
|
},
|
|
{
|
|
"entropy": 5.684511280059814,
|
|
"epoch": 0.7457693055825715,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004949874822229118,
|
|
"loss": 5.4888,
|
|
"mean_token_accuracy": 0.1607719212770462,
|
|
"num_tokens": 16637290.0,
|
|
"step": 9585
|
|
},
|
|
{
|
|
"entropy": 5.614342832565308,
|
|
"epoch": 0.7461583349542891,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004949816629596288,
|
|
"loss": 5.4721,
|
|
"mean_token_accuracy": 0.1669323280453682,
|
|
"num_tokens": 16646147.0,
|
|
"step": 9590
|
|
},
|
|
{
|
|
"entropy": 5.5784093856811525,
|
|
"epoch": 0.7465473643260067,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004949758403584746,
|
|
"loss": 5.5734,
|
|
"mean_token_accuracy": 0.1605289027094841,
|
|
"num_tokens": 16655299.0,
|
|
"step": 9595
|
|
},
|
|
{
|
|
"entropy": 5.6553062915802,
|
|
"epoch": 0.7469363936977241,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.0004949700144195368,
|
|
"loss": 5.4556,
|
|
"mean_token_accuracy": 0.16472315341234206,
|
|
"num_tokens": 16664091.0,
|
|
"step": 9600
|
|
},
|
|
{
|
|
"entropy": 5.74340591430664,
|
|
"epoch": 0.7473254230694417,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004949641851429043,
|
|
"loss": 5.5141,
|
|
"mean_token_accuracy": 0.16007463932037352,
|
|
"num_tokens": 16672665.0,
|
|
"step": 9605
|
|
},
|
|
{
|
|
"entropy": 5.585549449920654,
|
|
"epoch": 0.7477144524411593,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004949583525286654,
|
|
"loss": 5.4367,
|
|
"mean_token_accuracy": 0.1651037484407425,
|
|
"num_tokens": 16680735.0,
|
|
"step": 9610
|
|
},
|
|
{
|
|
"entropy": 5.609591007232666,
|
|
"epoch": 0.7481034818128769,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004949525165769085,
|
|
"loss": 5.5232,
|
|
"mean_token_accuracy": 0.1619318887591362,
|
|
"num_tokens": 16689560.0,
|
|
"step": 9615
|
|
},
|
|
{
|
|
"entropy": 5.675543212890625,
|
|
"epoch": 0.7484925111845945,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004949466772877224,
|
|
"loss": 5.4672,
|
|
"mean_token_accuracy": 0.16306936591863633,
|
|
"num_tokens": 16698953.0,
|
|
"step": 9620
|
|
},
|
|
{
|
|
"entropy": 5.625356245040893,
|
|
"epoch": 0.748881540556312,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004949408346611955,
|
|
"loss": 5.5121,
|
|
"mean_token_accuracy": 0.16117900460958481,
|
|
"num_tokens": 16707601.0,
|
|
"step": 9625
|
|
},
|
|
{
|
|
"entropy": 5.564679431915283,
|
|
"epoch": 0.7492705699280295,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004949349886974165,
|
|
"loss": 5.4926,
|
|
"mean_token_accuracy": 0.1600220173597336,
|
|
"num_tokens": 16716660.0,
|
|
"step": 9630
|
|
},
|
|
{
|
|
"entropy": 5.647576713562012,
|
|
"epoch": 0.7496595992997471,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004949291393964741,
|
|
"loss": 5.4463,
|
|
"mean_token_accuracy": 0.16327247470617295,
|
|
"num_tokens": 16725274.0,
|
|
"step": 9635
|
|
},
|
|
{
|
|
"entropy": 5.619313144683838,
|
|
"epoch": 0.7500486286714647,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.000494923286758457,
|
|
"loss": 5.4217,
|
|
"mean_token_accuracy": 0.16573825627565383,
|
|
"num_tokens": 16733301.0,
|
|
"step": 9640
|
|
},
|
|
{
|
|
"entropy": 5.66570897102356,
|
|
"epoch": 0.7504376580431823,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.0004949174307834541,
|
|
"loss": 5.4743,
|
|
"mean_token_accuracy": 0.16345229148864746,
|
|
"num_tokens": 16742072.0,
|
|
"step": 9645
|
|
},
|
|
{
|
|
"entropy": 5.661173248291016,
|
|
"epoch": 0.7508266874148998,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004949115714715543,
|
|
"loss": 5.48,
|
|
"mean_token_accuracy": 0.16001084744930266,
|
|
"num_tokens": 16751497.0,
|
|
"step": 9650
|
|
},
|
|
{
|
|
"entropy": 5.544694662094116,
|
|
"epoch": 0.7512157167866174,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004949057088228465,
|
|
"loss": 5.4181,
|
|
"mean_token_accuracy": 0.16923647224903107,
|
|
"num_tokens": 16760518.0,
|
|
"step": 9655
|
|
},
|
|
{
|
|
"entropy": 5.656236028671264,
|
|
"epoch": 0.751604746158335,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004948998428374194,
|
|
"loss": 5.54,
|
|
"mean_token_accuracy": 0.15598669797182083,
|
|
"num_tokens": 16768689.0,
|
|
"step": 9660
|
|
},
|
|
{
|
|
"entropy": 5.614003610610962,
|
|
"epoch": 0.7519937755300525,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004948939735153622,
|
|
"loss": 5.3853,
|
|
"mean_token_accuracy": 0.17029613703489305,
|
|
"num_tokens": 16777047.0,
|
|
"step": 9665
|
|
},
|
|
{
|
|
"entropy": 5.555197858810425,
|
|
"epoch": 0.7523828049017701,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004948881008567641,
|
|
"loss": 5.3616,
|
|
"mean_token_accuracy": 0.17010919004678726,
|
|
"num_tokens": 16785402.0,
|
|
"step": 9670
|
|
},
|
|
{
|
|
"entropy": 5.5848133087158205,
|
|
"epoch": 0.7527718342734876,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004948822248617139,
|
|
"loss": 5.455,
|
|
"mean_token_accuracy": 0.1636451430618763,
|
|
"num_tokens": 16794687.0,
|
|
"step": 9675
|
|
},
|
|
{
|
|
"entropy": 5.694547653198242,
|
|
"epoch": 0.7531608636452052,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.000494876345530301,
|
|
"loss": 5.491,
|
|
"mean_token_accuracy": 0.16249312162399293,
|
|
"num_tokens": 16803762.0,
|
|
"step": 9680
|
|
},
|
|
{
|
|
"entropy": 5.608018636703491,
|
|
"epoch": 0.7535498930169228,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004948704628626145,
|
|
"loss": 5.51,
|
|
"mean_token_accuracy": 0.1589452415704727,
|
|
"num_tokens": 16812872.0,
|
|
"step": 9685
|
|
},
|
|
{
|
|
"entropy": 5.654308128356933,
|
|
"epoch": 0.7539389223886404,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004948645768587437,
|
|
"loss": 5.5666,
|
|
"mean_token_accuracy": 0.15174276679754256,
|
|
"num_tokens": 16821270.0,
|
|
"step": 9690
|
|
},
|
|
{
|
|
"entropy": 5.632787799835205,
|
|
"epoch": 0.7543279517603579,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004948586875187778,
|
|
"loss": 5.4284,
|
|
"mean_token_accuracy": 0.16506413072347642,
|
|
"num_tokens": 16829508.0,
|
|
"step": 9695
|
|
},
|
|
{
|
|
"entropy": 5.59177532196045,
|
|
"epoch": 0.7547169811320755,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004948527948428064,
|
|
"loss": 5.421,
|
|
"mean_token_accuracy": 0.16233740672469138,
|
|
"num_tokens": 16838327.0,
|
|
"step": 9700
|
|
},
|
|
{
|
|
"entropy": 5.598222398757935,
|
|
"epoch": 0.755106010503793,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004948468988309187,
|
|
"loss": 5.4128,
|
|
"mean_token_accuracy": 0.16744261384010314,
|
|
"num_tokens": 16846530.0,
|
|
"step": 9705
|
|
},
|
|
{
|
|
"entropy": 5.502956771850586,
|
|
"epoch": 0.7554950398755106,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004948409994832043,
|
|
"loss": 5.3434,
|
|
"mean_token_accuracy": 0.16664833426475525,
|
|
"num_tokens": 16854825.0,
|
|
"step": 9710
|
|
},
|
|
{
|
|
"entropy": 5.598453044891357,
|
|
"epoch": 0.7558840692472282,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004948350967997526,
|
|
"loss": 5.5003,
|
|
"mean_token_accuracy": 0.1536581963300705,
|
|
"num_tokens": 16864096.0,
|
|
"step": 9715
|
|
},
|
|
{
|
|
"entropy": 5.674967241287232,
|
|
"epoch": 0.7562730986189458,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004948291907806532,
|
|
"loss": 5.5619,
|
|
"mean_token_accuracy": 0.15005003958940505,
|
|
"num_tokens": 16873000.0,
|
|
"step": 9720
|
|
},
|
|
{
|
|
"entropy": 5.726628828048706,
|
|
"epoch": 0.7566621279906633,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004948232814259957,
|
|
"loss": 5.5606,
|
|
"mean_token_accuracy": 0.16236240267753602,
|
|
"num_tokens": 16881374.0,
|
|
"step": 9725
|
|
},
|
|
{
|
|
"entropy": 5.637835550308227,
|
|
"epoch": 0.7570511573623808,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004948173687358699,
|
|
"loss": 5.5264,
|
|
"mean_token_accuracy": 0.15957718193531037,
|
|
"num_tokens": 16889192.0,
|
|
"step": 9730
|
|
},
|
|
{
|
|
"entropy": 5.582265377044678,
|
|
"epoch": 0.7574401867340984,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004948114527103652,
|
|
"loss": 5.5184,
|
|
"mean_token_accuracy": 0.1577650398015976,
|
|
"num_tokens": 16898538.0,
|
|
"step": 9735
|
|
},
|
|
{
|
|
"entropy": 5.630859899520874,
|
|
"epoch": 0.757829216105816,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004948055333495717,
|
|
"loss": 5.5183,
|
|
"mean_token_accuracy": 0.15783605873584747,
|
|
"num_tokens": 16907543.0,
|
|
"step": 9740
|
|
},
|
|
{
|
|
"entropy": 5.654094886779785,
|
|
"epoch": 0.7582182454775336,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004947996106535791,
|
|
"loss": 5.4257,
|
|
"mean_token_accuracy": 0.17062853574752807,
|
|
"num_tokens": 16916140.0,
|
|
"step": 9745
|
|
},
|
|
{
|
|
"entropy": 5.5783079147338865,
|
|
"epoch": 0.7586072748492512,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.0004947936846224773,
|
|
"loss": 5.4182,
|
|
"mean_token_accuracy": 0.1665373921394348,
|
|
"num_tokens": 16925433.0,
|
|
"step": 9750
|
|
},
|
|
{
|
|
"entropy": 5.532951974868775,
|
|
"epoch": 0.7589963042209686,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 0.0004947877552563562,
|
|
"loss": 5.4507,
|
|
"mean_token_accuracy": 0.16356708705425263,
|
|
"num_tokens": 16933598.0,
|
|
"step": 9755
|
|
},
|
|
{
|
|
"entropy": 5.639309597015381,
|
|
"epoch": 0.7593853335926862,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004947818225553056,
|
|
"loss": 5.5459,
|
|
"mean_token_accuracy": 0.1587366744875908,
|
|
"num_tokens": 16942270.0,
|
|
"step": 9760
|
|
},
|
|
{
|
|
"entropy": 5.602426338195801,
|
|
"epoch": 0.7597743629644038,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004947758865194156,
|
|
"loss": 5.3833,
|
|
"mean_token_accuracy": 0.16099860072135924,
|
|
"num_tokens": 16951044.0,
|
|
"step": 9765
|
|
},
|
|
{
|
|
"entropy": 5.673260307312011,
|
|
"epoch": 0.7601633923361214,
|
|
"grad_norm": 2.609375,
|
|
"learning_rate": 0.0004947699471487766,
|
|
"loss": 5.5603,
|
|
"mean_token_accuracy": 0.1531473256647587,
|
|
"num_tokens": 16960215.0,
|
|
"step": 9770
|
|
},
|
|
{
|
|
"entropy": 5.716788911819458,
|
|
"epoch": 0.760552421707839,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004947640044434782,
|
|
"loss": 5.5952,
|
|
"mean_token_accuracy": 0.15658744424581528,
|
|
"num_tokens": 16968515.0,
|
|
"step": 9775
|
|
},
|
|
{
|
|
"entropy": 5.679812908172607,
|
|
"epoch": 0.7609414510795565,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004947580584036109,
|
|
"loss": 5.5651,
|
|
"mean_token_accuracy": 0.15306783169507981,
|
|
"num_tokens": 16977597.0,
|
|
"step": 9780
|
|
},
|
|
{
|
|
"entropy": 5.585596179962158,
|
|
"epoch": 0.761330480451274,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004947521090292649,
|
|
"loss": 5.4231,
|
|
"mean_token_accuracy": 0.1596038371324539,
|
|
"num_tokens": 16987376.0,
|
|
"step": 9785
|
|
},
|
|
{
|
|
"entropy": 5.5853808403015135,
|
|
"epoch": 0.7617195098229916,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004947461563205304,
|
|
"loss": 5.4246,
|
|
"mean_token_accuracy": 0.16407533586025239,
|
|
"num_tokens": 16995976.0,
|
|
"step": 9790
|
|
},
|
|
{
|
|
"entropy": 5.5631688117980955,
|
|
"epoch": 0.7621085391947092,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004947402002774977,
|
|
"loss": 5.4284,
|
|
"mean_token_accuracy": 0.16948177963495253,
|
|
"num_tokens": 17003819.0,
|
|
"step": 9795
|
|
},
|
|
{
|
|
"entropy": 5.549920654296875,
|
|
"epoch": 0.7624975685664268,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004947342409002572,
|
|
"loss": 5.4126,
|
|
"mean_token_accuracy": 0.1728143498301506,
|
|
"num_tokens": 17011632.0,
|
|
"step": 9800
|
|
},
|
|
{
|
|
"entropy": 5.55021185874939,
|
|
"epoch": 0.7628865979381443,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004947282781888994,
|
|
"loss": 5.3461,
|
|
"mean_token_accuracy": 0.1698859602212906,
|
|
"num_tokens": 17019737.0,
|
|
"step": 9805
|
|
},
|
|
{
|
|
"entropy": 5.623792028427124,
|
|
"epoch": 0.7632756273098619,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004947223121435147,
|
|
"loss": 5.5057,
|
|
"mean_token_accuracy": 0.16593750119209288,
|
|
"num_tokens": 17028803.0,
|
|
"step": 9810
|
|
},
|
|
{
|
|
"entropy": 5.5954584121704105,
|
|
"epoch": 0.7636646566815795,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004947163427641936,
|
|
"loss": 5.3402,
|
|
"mean_token_accuracy": 0.16582608968019485,
|
|
"num_tokens": 17036847.0,
|
|
"step": 9815
|
|
},
|
|
{
|
|
"entropy": 5.676225996017456,
|
|
"epoch": 0.764053686053297,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004947103700510268,
|
|
"loss": 5.4853,
|
|
"mean_token_accuracy": 0.1590005040168762,
|
|
"num_tokens": 17045665.0,
|
|
"step": 9820
|
|
},
|
|
{
|
|
"entropy": 5.690594434738159,
|
|
"epoch": 0.7644427154250146,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004947043940041047,
|
|
"loss": 5.4871,
|
|
"mean_token_accuracy": 0.16544217467308045,
|
|
"num_tokens": 17053842.0,
|
|
"step": 9825
|
|
},
|
|
{
|
|
"entropy": 5.657180213928223,
|
|
"epoch": 0.7648317447967321,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004946984146235183,
|
|
"loss": 5.5492,
|
|
"mean_token_accuracy": 0.15866318196058274,
|
|
"num_tokens": 17062287.0,
|
|
"step": 9830
|
|
},
|
|
{
|
|
"entropy": 5.671737289428711,
|
|
"epoch": 0.7652207741684497,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004946924319093579,
|
|
"loss": 5.5675,
|
|
"mean_token_accuracy": 0.16470288038253783,
|
|
"num_tokens": 17071495.0,
|
|
"step": 9835
|
|
},
|
|
{
|
|
"entropy": 5.566572856903076,
|
|
"epoch": 0.7656098035401673,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004946864458617148,
|
|
"loss": 5.495,
|
|
"mean_token_accuracy": 0.1597565859556198,
|
|
"num_tokens": 17080734.0,
|
|
"step": 9840
|
|
},
|
|
{
|
|
"entropy": 5.645231056213379,
|
|
"epoch": 0.7659988329118849,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004946804564806793,
|
|
"loss": 5.5168,
|
|
"mean_token_accuracy": 0.16035535037517548,
|
|
"num_tokens": 17089683.0,
|
|
"step": 9845
|
|
},
|
|
{
|
|
"entropy": 5.651087903976441,
|
|
"epoch": 0.7663878622836025,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004946744637663427,
|
|
"loss": 5.5363,
|
|
"mean_token_accuracy": 0.15783768147230148,
|
|
"num_tokens": 17098203.0,
|
|
"step": 9850
|
|
},
|
|
{
|
|
"entropy": 5.565146541595459,
|
|
"epoch": 0.7667768916553199,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004946684677187956,
|
|
"loss": 5.3894,
|
|
"mean_token_accuracy": 0.16356709450483323,
|
|
"num_tokens": 17107185.0,
|
|
"step": 9855
|
|
},
|
|
{
|
|
"entropy": 5.602199363708496,
|
|
"epoch": 0.7671659210270375,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004946624683381292,
|
|
"loss": 5.4465,
|
|
"mean_token_accuracy": 0.16764336079359055,
|
|
"num_tokens": 17115168.0,
|
|
"step": 9860
|
|
},
|
|
{
|
|
"entropy": 5.595751810073852,
|
|
"epoch": 0.7675549503987551,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004946564656244345,
|
|
"loss": 5.4376,
|
|
"mean_token_accuracy": 0.16738105267286302,
|
|
"num_tokens": 17124037.0,
|
|
"step": 9865
|
|
},
|
|
{
|
|
"entropy": 5.572898054122925,
|
|
"epoch": 0.7679439797704727,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004946504595778026,
|
|
"loss": 5.3668,
|
|
"mean_token_accuracy": 0.16299717128276825,
|
|
"num_tokens": 17132238.0,
|
|
"step": 9870
|
|
},
|
|
{
|
|
"entropy": 5.559570550918579,
|
|
"epoch": 0.7683330091421903,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004946444501983246,
|
|
"loss": 5.5043,
|
|
"mean_token_accuracy": 0.15664197653532028,
|
|
"num_tokens": 17140405.0,
|
|
"step": 9875
|
|
},
|
|
{
|
|
"entropy": 5.5682971477508545,
|
|
"epoch": 0.7687220385139077,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004946384374860916,
|
|
"loss": 5.42,
|
|
"mean_token_accuracy": 0.1662541151046753,
|
|
"num_tokens": 17149207.0,
|
|
"step": 9880
|
|
},
|
|
{
|
|
"entropy": 5.61993441581726,
|
|
"epoch": 0.7691110678856253,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.0004946324214411949,
|
|
"loss": 5.4076,
|
|
"mean_token_accuracy": 0.15628940016031265,
|
|
"num_tokens": 17157680.0,
|
|
"step": 9885
|
|
},
|
|
{
|
|
"entropy": 5.643505573272705,
|
|
"epoch": 0.7695000972573429,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004946264020637259,
|
|
"loss": 5.4463,
|
|
"mean_token_accuracy": 0.16137076020240784,
|
|
"num_tokens": 17166907.0,
|
|
"step": 9890
|
|
},
|
|
{
|
|
"entropy": 5.586683464050293,
|
|
"epoch": 0.7698891266290605,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004946203793537757,
|
|
"loss": 5.4843,
|
|
"mean_token_accuracy": 0.16788864582777024,
|
|
"num_tokens": 17176318.0,
|
|
"step": 9895
|
|
},
|
|
{
|
|
"entropy": 5.6048585891723635,
|
|
"epoch": 0.7702781560007781,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004946143533114358,
|
|
"loss": 5.5217,
|
|
"mean_token_accuracy": 0.15332429856061935,
|
|
"num_tokens": 17185380.0,
|
|
"step": 9900
|
|
},
|
|
{
|
|
"entropy": 5.660828351974487,
|
|
"epoch": 0.7706671853724957,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004946083239367976,
|
|
"loss": 5.4994,
|
|
"mean_token_accuracy": 0.1601640537381172,
|
|
"num_tokens": 17193177.0,
|
|
"step": 9905
|
|
},
|
|
{
|
|
"entropy": 5.5617344856262205,
|
|
"epoch": 0.7710562147442132,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004946022912299527,
|
|
"loss": 5.4757,
|
|
"mean_token_accuracy": 0.15949599891901017,
|
|
"num_tokens": 17201071.0,
|
|
"step": 9910
|
|
},
|
|
{
|
|
"entropy": 5.543600606918335,
|
|
"epoch": 0.7714452441159307,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004945962551909926,
|
|
"loss": 5.3834,
|
|
"mean_token_accuracy": 0.16966844946146012,
|
|
"num_tokens": 17209375.0,
|
|
"step": 9915
|
|
},
|
|
{
|
|
"entropy": 5.601286697387695,
|
|
"epoch": 0.7718342734876483,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004945902158200089,
|
|
"loss": 5.337,
|
|
"mean_token_accuracy": 0.17217303067445755,
|
|
"num_tokens": 17217453.0,
|
|
"step": 9920
|
|
},
|
|
{
|
|
"entropy": 5.601703071594239,
|
|
"epoch": 0.7722233028593659,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004945841731170931,
|
|
"loss": 5.4188,
|
|
"mean_token_accuracy": 0.16042266339063643,
|
|
"num_tokens": 17225671.0,
|
|
"step": 9925
|
|
},
|
|
{
|
|
"entropy": 5.519887161254883,
|
|
"epoch": 0.7726123322310835,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004945781270823369,
|
|
"loss": 5.3674,
|
|
"mean_token_accuracy": 0.16603152453899384,
|
|
"num_tokens": 17234396.0,
|
|
"step": 9930
|
|
},
|
|
{
|
|
"entropy": 5.570225620269776,
|
|
"epoch": 0.773001361602801,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004945720777158323,
|
|
"loss": 5.4813,
|
|
"mean_token_accuracy": 0.1608129024505615,
|
|
"num_tokens": 17243509.0,
|
|
"step": 9935
|
|
},
|
|
{
|
|
"entropy": 5.619941139221192,
|
|
"epoch": 0.7733903909745186,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004945660250176708,
|
|
"loss": 5.4021,
|
|
"mean_token_accuracy": 0.17428109794855118,
|
|
"num_tokens": 17251447.0,
|
|
"step": 9940
|
|
},
|
|
{
|
|
"entropy": 5.535233879089356,
|
|
"epoch": 0.7737794203462361,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004945599689879443,
|
|
"loss": 5.4664,
|
|
"mean_token_accuracy": 0.16355775743722917,
|
|
"num_tokens": 17260240.0,
|
|
"step": 9945
|
|
},
|
|
{
|
|
"entropy": 5.602076053619385,
|
|
"epoch": 0.7741684497179537,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004945539096267448,
|
|
"loss": 5.467,
|
|
"mean_token_accuracy": 0.16678984612226486,
|
|
"num_tokens": 17267835.0,
|
|
"step": 9950
|
|
},
|
|
{
|
|
"entropy": 5.57802038192749,
|
|
"epoch": 0.7745574790896713,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004945478469341642,
|
|
"loss": 5.4616,
|
|
"mean_token_accuracy": 0.16033925563097,
|
|
"num_tokens": 17277069.0,
|
|
"step": 9955
|
|
},
|
|
{
|
|
"entropy": 5.602939796447754,
|
|
"epoch": 0.7749465084613888,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004945417809102944,
|
|
"loss": 5.4513,
|
|
"mean_token_accuracy": 0.16086394041776658,
|
|
"num_tokens": 17285014.0,
|
|
"step": 9960
|
|
},
|
|
{
|
|
"entropy": 5.531858968734741,
|
|
"epoch": 0.7753355378331064,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004945357115552275,
|
|
"loss": 5.3995,
|
|
"mean_token_accuracy": 0.16076785176992417,
|
|
"num_tokens": 17292649.0,
|
|
"step": 9965
|
|
},
|
|
{
|
|
"entropy": 5.668289852142334,
|
|
"epoch": 0.775724567204824,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004945296388690557,
|
|
"loss": 5.5467,
|
|
"mean_token_accuracy": 0.15805940628051757,
|
|
"num_tokens": 17301792.0,
|
|
"step": 9970
|
|
},
|
|
{
|
|
"entropy": 5.5542267799377445,
|
|
"epoch": 0.7761135965765416,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000494523562851871,
|
|
"loss": 5.2994,
|
|
"mean_token_accuracy": 0.16803679764270782,
|
|
"num_tokens": 17310377.0,
|
|
"step": 9975
|
|
},
|
|
{
|
|
"entropy": 5.576317358016968,
|
|
"epoch": 0.7765026259482591,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004945174835037655,
|
|
"loss": 5.5252,
|
|
"mean_token_accuracy": 0.15372655987739564,
|
|
"num_tokens": 17319779.0,
|
|
"step": 9980
|
|
},
|
|
{
|
|
"entropy": 5.755231428146362,
|
|
"epoch": 0.7768916553199766,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004945114008248319,
|
|
"loss": 5.6449,
|
|
"mean_token_accuracy": 0.14884610027074813,
|
|
"num_tokens": 17328210.0,
|
|
"step": 9985
|
|
},
|
|
{
|
|
"entropy": 5.584620618820191,
|
|
"epoch": 0.7772806846916942,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004945053148151619,
|
|
"loss": 5.3651,
|
|
"mean_token_accuracy": 0.1722089931368828,
|
|
"num_tokens": 17336287.0,
|
|
"step": 9990
|
|
},
|
|
{
|
|
"entropy": 5.564840316772461,
|
|
"epoch": 0.7776697140634118,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004944992254748482,
|
|
"loss": 5.4267,
|
|
"mean_token_accuracy": 0.16362099945545197,
|
|
"num_tokens": 17344171.0,
|
|
"step": 9995
|
|
},
|
|
{
|
|
"entropy": 5.535340070724487,
|
|
"epoch": 0.7780587434351294,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004944931328039832,
|
|
"loss": 5.4545,
|
|
"mean_token_accuracy": 0.169051456451416,
|
|
"num_tokens": 17352786.0,
|
|
"step": 10000
|
|
},
|
|
{
|
|
"entropy": 5.541292333602906,
|
|
"epoch": 0.778447772806847,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004944870368026592,
|
|
"loss": 5.4307,
|
|
"mean_token_accuracy": 0.16499633044004441,
|
|
"num_tokens": 17361824.0,
|
|
"step": 10005
|
|
},
|
|
{
|
|
"entropy": 5.592077016830444,
|
|
"epoch": 0.7788368021785644,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004944809374709689,
|
|
"loss": 5.4585,
|
|
"mean_token_accuracy": 0.16586715281009673,
|
|
"num_tokens": 17370249.0,
|
|
"step": 10010
|
|
},
|
|
{
|
|
"entropy": 5.572728633880615,
|
|
"epoch": 0.779225831550282,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004944748348090045,
|
|
"loss": 5.4421,
|
|
"mean_token_accuracy": 0.16339399069547653,
|
|
"num_tokens": 17379650.0,
|
|
"step": 10015
|
|
},
|
|
{
|
|
"entropy": 5.5525439262390135,
|
|
"epoch": 0.7796148609219996,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004944687288168589,
|
|
"loss": 5.4564,
|
|
"mean_token_accuracy": 0.1660699188709259,
|
|
"num_tokens": 17388046.0,
|
|
"step": 10020
|
|
},
|
|
{
|
|
"entropy": 5.638512372970581,
|
|
"epoch": 0.7800038902937172,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004944626194946246,
|
|
"loss": 5.4271,
|
|
"mean_token_accuracy": 0.17610761970281602,
|
|
"num_tokens": 17395851.0,
|
|
"step": 10025
|
|
},
|
|
{
|
|
"entropy": 5.612651348114014,
|
|
"epoch": 0.7803929196654348,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004944565068423945,
|
|
"loss": 5.5025,
|
|
"mean_token_accuracy": 0.1645132765173912,
|
|
"num_tokens": 17404273.0,
|
|
"step": 10030
|
|
},
|
|
{
|
|
"entropy": 5.528199911117554,
|
|
"epoch": 0.7807819490371523,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004944503908602612,
|
|
"loss": 5.4391,
|
|
"mean_token_accuracy": 0.16655797511339188,
|
|
"num_tokens": 17412884.0,
|
|
"step": 10035
|
|
},
|
|
{
|
|
"entropy": 5.565637111663818,
|
|
"epoch": 0.7811709784088698,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004944442715483174,
|
|
"loss": 5.4246,
|
|
"mean_token_accuracy": 0.16185757219791413,
|
|
"num_tokens": 17420939.0,
|
|
"step": 10040
|
|
},
|
|
{
|
|
"entropy": 5.574648046493531,
|
|
"epoch": 0.7815600077805874,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004944381489066561,
|
|
"loss": 5.4762,
|
|
"mean_token_accuracy": 0.16504090428352355,
|
|
"num_tokens": 17429838.0,
|
|
"step": 10045
|
|
},
|
|
{
|
|
"entropy": 5.630850172042846,
|
|
"epoch": 0.781949037152305,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004944320229353702,
|
|
"loss": 5.4576,
|
|
"mean_token_accuracy": 0.16243240088224412,
|
|
"num_tokens": 17439164.0,
|
|
"step": 10050
|
|
},
|
|
{
|
|
"entropy": 5.634826183319092,
|
|
"epoch": 0.7823380665240226,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004944258936345526,
|
|
"loss": 5.4317,
|
|
"mean_token_accuracy": 0.16340447217226028,
|
|
"num_tokens": 17447544.0,
|
|
"step": 10055
|
|
},
|
|
{
|
|
"entropy": 5.478040027618408,
|
|
"epoch": 0.7827270958957401,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004944197610042963,
|
|
"loss": 5.3042,
|
|
"mean_token_accuracy": 0.1662735790014267,
|
|
"num_tokens": 17456270.0,
|
|
"step": 10060
|
|
},
|
|
{
|
|
"entropy": 5.567981147766114,
|
|
"epoch": 0.7831161252674577,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004944136250446944,
|
|
"loss": 5.4864,
|
|
"mean_token_accuracy": 0.16388331800699235,
|
|
"num_tokens": 17465241.0,
|
|
"step": 10065
|
|
},
|
|
{
|
|
"entropy": 5.686744737625122,
|
|
"epoch": 0.7835051546391752,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004944074857558399,
|
|
"loss": 5.4825,
|
|
"mean_token_accuracy": 0.1565874397754669,
|
|
"num_tokens": 17474460.0,
|
|
"step": 10070
|
|
},
|
|
{
|
|
"entropy": 5.599651908874511,
|
|
"epoch": 0.7838941840108928,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004944013431378261,
|
|
"loss": 5.4503,
|
|
"mean_token_accuracy": 0.16428371965885163,
|
|
"num_tokens": 17483256.0,
|
|
"step": 10075
|
|
},
|
|
{
|
|
"entropy": 5.623570966720581,
|
|
"epoch": 0.7842832133826104,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004943951971907461,
|
|
"loss": 5.4704,
|
|
"mean_token_accuracy": 0.16218913793563844,
|
|
"num_tokens": 17491922.0,
|
|
"step": 10080
|
|
},
|
|
{
|
|
"entropy": 5.608122491836548,
|
|
"epoch": 0.7846722427543279,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004943890479146933,
|
|
"loss": 5.4693,
|
|
"mean_token_accuracy": 0.16983896046876906,
|
|
"num_tokens": 17499763.0,
|
|
"step": 10085
|
|
},
|
|
{
|
|
"entropy": 5.619894170761109,
|
|
"epoch": 0.7850612721260455,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004943828953097607,
|
|
"loss": 5.4396,
|
|
"mean_token_accuracy": 0.16675328761339187,
|
|
"num_tokens": 17508682.0,
|
|
"step": 10090
|
|
},
|
|
{
|
|
"entropy": 5.518069171905518,
|
|
"epoch": 0.7854503014977631,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.000494376739376042,
|
|
"loss": 5.3658,
|
|
"mean_token_accuracy": 0.16787486970424653,
|
|
"num_tokens": 17517269.0,
|
|
"step": 10095
|
|
},
|
|
{
|
|
"entropy": 5.444378519058228,
|
|
"epoch": 0.7858393308694807,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004943705801136304,
|
|
"loss": 5.3881,
|
|
"mean_token_accuracy": 0.1697043627500534,
|
|
"num_tokens": 17525135.0,
|
|
"step": 10100
|
|
},
|
|
{
|
|
"entropy": 5.537582588195801,
|
|
"epoch": 0.7862283602411982,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004943644175226193,
|
|
"loss": 5.4714,
|
|
"mean_token_accuracy": 0.1688419073820114,
|
|
"num_tokens": 17534195.0,
|
|
"step": 10105
|
|
},
|
|
{
|
|
"entropy": 5.574254274368286,
|
|
"epoch": 0.7866173896129158,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004943582516031025,
|
|
"loss": 5.3923,
|
|
"mean_token_accuracy": 0.16879581660032272,
|
|
"num_tokens": 17543016.0,
|
|
"step": 10110
|
|
},
|
|
{
|
|
"entropy": 5.642699337005615,
|
|
"epoch": 0.7870064189846333,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004943520823551732,
|
|
"loss": 5.4769,
|
|
"mean_token_accuracy": 0.1671273186802864,
|
|
"num_tokens": 17551854.0,
|
|
"step": 10115
|
|
},
|
|
{
|
|
"entropy": 5.58419017791748,
|
|
"epoch": 0.7873954483563509,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004943459097789252,
|
|
"loss": 5.3816,
|
|
"mean_token_accuracy": 0.1663597121834755,
|
|
"num_tokens": 17560739.0,
|
|
"step": 10120
|
|
},
|
|
{
|
|
"entropy": 5.572810363769531,
|
|
"epoch": 0.7877844777280685,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004943397338744523,
|
|
"loss": 5.4077,
|
|
"mean_token_accuracy": 0.1652447521686554,
|
|
"num_tokens": 17569784.0,
|
|
"step": 10125
|
|
},
|
|
{
|
|
"entropy": 5.651245927810669,
|
|
"epoch": 0.7881735070997861,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.000494333554641848,
|
|
"loss": 5.5803,
|
|
"mean_token_accuracy": 0.15896444022655487,
|
|
"num_tokens": 17579262.0,
|
|
"step": 10130
|
|
},
|
|
{
|
|
"entropy": 5.56685996055603,
|
|
"epoch": 0.7885625364715037,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.000494327372081206,
|
|
"loss": 5.4249,
|
|
"mean_token_accuracy": 0.16502940356731416,
|
|
"num_tokens": 17587984.0,
|
|
"step": 10135
|
|
},
|
|
{
|
|
"entropy": 5.54715485572815,
|
|
"epoch": 0.7889515658432211,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004943211861926204,
|
|
"loss": 5.3763,
|
|
"mean_token_accuracy": 0.17046990543603896,
|
|
"num_tokens": 17596598.0,
|
|
"step": 10140
|
|
},
|
|
{
|
|
"entropy": 5.5723248481750485,
|
|
"epoch": 0.7893405952149387,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004943149969761848,
|
|
"loss": 5.5089,
|
|
"mean_token_accuracy": 0.16314789652824402,
|
|
"num_tokens": 17605768.0,
|
|
"step": 10145
|
|
},
|
|
{
|
|
"entropy": 5.589661455154419,
|
|
"epoch": 0.7897296245866563,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004943088044319932,
|
|
"loss": 5.4277,
|
|
"mean_token_accuracy": 0.16240018904209136,
|
|
"num_tokens": 17614412.0,
|
|
"step": 10150
|
|
},
|
|
{
|
|
"entropy": 5.651829719543457,
|
|
"epoch": 0.7901186539583739,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004943026085601395,
|
|
"loss": 5.4399,
|
|
"mean_token_accuracy": 0.1601569950580597,
|
|
"num_tokens": 17622515.0,
|
|
"step": 10155
|
|
},
|
|
{
|
|
"entropy": 5.587910747528076,
|
|
"epoch": 0.7905076833300915,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004942964093607178,
|
|
"loss": 5.365,
|
|
"mean_token_accuracy": 0.16747316867113113,
|
|
"num_tokens": 17631256.0,
|
|
"step": 10160
|
|
},
|
|
{
|
|
"entropy": 5.6510865688323975,
|
|
"epoch": 0.790896712701809,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004942902068338222,
|
|
"loss": 5.5021,
|
|
"mean_token_accuracy": 0.1550629422068596,
|
|
"num_tokens": 17639648.0,
|
|
"step": 10165
|
|
},
|
|
{
|
|
"entropy": 5.615673446655274,
|
|
"epoch": 0.7912857420735265,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004942840009795466,
|
|
"loss": 5.4277,
|
|
"mean_token_accuracy": 0.1639723613858223,
|
|
"num_tokens": 17648225.0,
|
|
"step": 10170
|
|
},
|
|
{
|
|
"entropy": 5.598308277130127,
|
|
"epoch": 0.7916747714452441,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004942777917979855,
|
|
"loss": 5.4785,
|
|
"mean_token_accuracy": 0.16637687385082245,
|
|
"num_tokens": 17656764.0,
|
|
"step": 10175
|
|
},
|
|
{
|
|
"entropy": 5.592406749725342,
|
|
"epoch": 0.7920638008169617,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.0004942715792892328,
|
|
"loss": 5.4409,
|
|
"mean_token_accuracy": 0.15991899520158767,
|
|
"num_tokens": 17665127.0,
|
|
"step": 10180
|
|
},
|
|
{
|
|
"entropy": 5.562086486816407,
|
|
"epoch": 0.7924528301886793,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.000494265363453383,
|
|
"loss": 5.3483,
|
|
"mean_token_accuracy": 0.1689964562654495,
|
|
"num_tokens": 17673297.0,
|
|
"step": 10185
|
|
},
|
|
{
|
|
"entropy": 5.594065761566162,
|
|
"epoch": 0.7928418595603968,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004942591442905302,
|
|
"loss": 5.4877,
|
|
"mean_token_accuracy": 0.1662108927965164,
|
|
"num_tokens": 17681816.0,
|
|
"step": 10190
|
|
},
|
|
{
|
|
"entropy": 5.619212293624878,
|
|
"epoch": 0.7932308889321144,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004942529218007689,
|
|
"loss": 5.4946,
|
|
"mean_token_accuracy": 0.16034965813159943,
|
|
"num_tokens": 17690588.0,
|
|
"step": 10195
|
|
},
|
|
{
|
|
"entropy": 5.606663799285888,
|
|
"epoch": 0.7936199183038319,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004942466959841936,
|
|
"loss": 5.4009,
|
|
"mean_token_accuracy": 0.16643059998750687,
|
|
"num_tokens": 17699196.0,
|
|
"step": 10200
|
|
},
|
|
{
|
|
"entropy": 5.684493541717529,
|
|
"epoch": 0.7940089476755495,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.0004942404668408985,
|
|
"loss": 5.4966,
|
|
"mean_token_accuracy": 0.16475944668054582,
|
|
"num_tokens": 17708928.0,
|
|
"step": 10205
|
|
},
|
|
{
|
|
"entropy": 5.64884467124939,
|
|
"epoch": 0.7943979770472671,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004942342343709783,
|
|
"loss": 5.3999,
|
|
"mean_token_accuracy": 0.16832922548055648,
|
|
"num_tokens": 17717888.0,
|
|
"step": 10210
|
|
},
|
|
{
|
|
"entropy": 5.6147425174713135,
|
|
"epoch": 0.7947870064189846,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004942279985745275,
|
|
"loss": 5.4201,
|
|
"mean_token_accuracy": 0.1606283888220787,
|
|
"num_tokens": 17726022.0,
|
|
"step": 10215
|
|
},
|
|
{
|
|
"entropy": 5.52122130393982,
|
|
"epoch": 0.7951760357907022,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004942217594516409,
|
|
"loss": 5.3901,
|
|
"mean_token_accuracy": 0.16497442424297332,
|
|
"num_tokens": 17733998.0,
|
|
"step": 10220
|
|
},
|
|
{
|
|
"entropy": 5.584072780609131,
|
|
"epoch": 0.7955650651624198,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.000494215517002413,
|
|
"loss": 5.4461,
|
|
"mean_token_accuracy": 0.1670831933617592,
|
|
"num_tokens": 17742039.0,
|
|
"step": 10225
|
|
},
|
|
{
|
|
"entropy": 5.565745782852173,
|
|
"epoch": 0.7959540945341373,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004942092712269384,
|
|
"loss": 5.3595,
|
|
"mean_token_accuracy": 0.17128196358680725,
|
|
"num_tokens": 17751474.0,
|
|
"step": 10230
|
|
},
|
|
{
|
|
"entropy": 5.531363391876221,
|
|
"epoch": 0.7963431239058549,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004942030221253122,
|
|
"loss": 5.3525,
|
|
"mean_token_accuracy": 0.16915419846773147,
|
|
"num_tokens": 17759483.0,
|
|
"step": 10235
|
|
},
|
|
{
|
|
"entropy": 5.5520336627960205,
|
|
"epoch": 0.7967321532775724,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004941967696976289,
|
|
"loss": 5.4772,
|
|
"mean_token_accuracy": 0.16447118073701858,
|
|
"num_tokens": 17768025.0,
|
|
"step": 10240
|
|
},
|
|
{
|
|
"entropy": 5.5067604064941404,
|
|
"epoch": 0.79712118264929,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004941905139439835,
|
|
"loss": 5.3213,
|
|
"mean_token_accuracy": 0.16718516796827315,
|
|
"num_tokens": 17776861.0,
|
|
"step": 10245
|
|
},
|
|
{
|
|
"entropy": 5.572161340713501,
|
|
"epoch": 0.7975102120210076,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004941842548644712,
|
|
"loss": 5.4757,
|
|
"mean_token_accuracy": 0.165050645172596,
|
|
"num_tokens": 17786221.0,
|
|
"step": 10250
|
|
},
|
|
{
|
|
"entropy": 5.631086683273315,
|
|
"epoch": 0.7978992413927252,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004941779924591864,
|
|
"loss": 5.4619,
|
|
"mean_token_accuracy": 0.15975369215011598,
|
|
"num_tokens": 17794619.0,
|
|
"step": 10255
|
|
},
|
|
{
|
|
"entropy": 5.614037752151489,
|
|
"epoch": 0.7982882707644428,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004941717267282244,
|
|
"loss": 5.4449,
|
|
"mean_token_accuracy": 0.16635915637016296,
|
|
"num_tokens": 17803288.0,
|
|
"step": 10260
|
|
},
|
|
{
|
|
"entropy": 5.569530868530274,
|
|
"epoch": 0.7986773001361602,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004941654576716806,
|
|
"loss": 5.513,
|
|
"mean_token_accuracy": 0.1579871207475662,
|
|
"num_tokens": 17812648.0,
|
|
"step": 10265
|
|
},
|
|
{
|
|
"entropy": 5.544220733642578,
|
|
"epoch": 0.7990663295078778,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004941591852896495,
|
|
"loss": 5.4183,
|
|
"mean_token_accuracy": 0.168813855946064,
|
|
"num_tokens": 17821955.0,
|
|
"step": 10270
|
|
},
|
|
{
|
|
"entropy": 5.671693468093872,
|
|
"epoch": 0.7994553588795954,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004941529095822268,
|
|
"loss": 5.4531,
|
|
"mean_token_accuracy": 0.16473222225904466,
|
|
"num_tokens": 17829987.0,
|
|
"step": 10275
|
|
},
|
|
{
|
|
"entropy": 5.563750839233398,
|
|
"epoch": 0.799844388251313,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004941466305495074,
|
|
"loss": 5.4015,
|
|
"mean_token_accuracy": 0.17213702201843262,
|
|
"num_tokens": 17839298.0,
|
|
"step": 10280
|
|
},
|
|
{
|
|
"entropy": 5.580596446990967,
|
|
"epoch": 0.8002334176230306,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004941403481915867,
|
|
"loss": 5.4335,
|
|
"mean_token_accuracy": 0.16103956699371338,
|
|
"num_tokens": 17847950.0,
|
|
"step": 10285
|
|
},
|
|
{
|
|
"entropy": 5.6678954601287845,
|
|
"epoch": 0.800622446994748,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004941340625085601,
|
|
"loss": 5.5517,
|
|
"mean_token_accuracy": 0.15696440488100052,
|
|
"num_tokens": 17857416.0,
|
|
"step": 10290
|
|
},
|
|
{
|
|
"entropy": 5.685216808319092,
|
|
"epoch": 0.8010114763664656,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004941277735005228,
|
|
"loss": 5.4051,
|
|
"mean_token_accuracy": 0.17213125079870223,
|
|
"num_tokens": 17866516.0,
|
|
"step": 10295
|
|
},
|
|
{
|
|
"entropy": 5.651232957839966,
|
|
"epoch": 0.8014005057381832,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004941214811675702,
|
|
"loss": 5.5713,
|
|
"mean_token_accuracy": 0.1570074513554573,
|
|
"num_tokens": 17875823.0,
|
|
"step": 10300
|
|
},
|
|
{
|
|
"entropy": 5.529204177856445,
|
|
"epoch": 0.8017895351099008,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004941151855097982,
|
|
"loss": 5.4453,
|
|
"mean_token_accuracy": 0.16270828992128372,
|
|
"num_tokens": 17883597.0,
|
|
"step": 10305
|
|
},
|
|
{
|
|
"entropy": 5.655588626861572,
|
|
"epoch": 0.8021785644816184,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004941088865273018,
|
|
"loss": 5.4267,
|
|
"mean_token_accuracy": 0.15925383567810059,
|
|
"num_tokens": 17892053.0,
|
|
"step": 10310
|
|
},
|
|
{
|
|
"entropy": 5.571537494659424,
|
|
"epoch": 0.802567593853336,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004941025842201769,
|
|
"loss": 5.34,
|
|
"mean_token_accuracy": 0.1758824184536934,
|
|
"num_tokens": 17900187.0,
|
|
"step": 10315
|
|
},
|
|
{
|
|
"entropy": 5.566791629791259,
|
|
"epoch": 0.8029566232250535,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004940962785885189,
|
|
"loss": 5.5103,
|
|
"mean_token_accuracy": 0.16310321539640427,
|
|
"num_tokens": 17908608.0,
|
|
"step": 10320
|
|
},
|
|
{
|
|
"entropy": 5.621613883972168,
|
|
"epoch": 0.803345652596771,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004940899696324237,
|
|
"loss": 5.3931,
|
|
"mean_token_accuracy": 0.16399924606084823,
|
|
"num_tokens": 17917331.0,
|
|
"step": 10325
|
|
},
|
|
{
|
|
"entropy": 5.639385461807251,
|
|
"epoch": 0.8037346819684886,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004940836573519868,
|
|
"loss": 5.5026,
|
|
"mean_token_accuracy": 0.16221323907375335,
|
|
"num_tokens": 17925228.0,
|
|
"step": 10330
|
|
},
|
|
{
|
|
"entropy": 5.588077640533447,
|
|
"epoch": 0.8041237113402062,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004940773417473043,
|
|
"loss": 5.386,
|
|
"mean_token_accuracy": 0.16964919567108155,
|
|
"num_tokens": 17934110.0,
|
|
"step": 10335
|
|
},
|
|
{
|
|
"entropy": 5.571057844161987,
|
|
"epoch": 0.8045127407119238,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004940710228184717,
|
|
"loss": 5.4002,
|
|
"mean_token_accuracy": 0.16821952313184738,
|
|
"num_tokens": 17942237.0,
|
|
"step": 10340
|
|
},
|
|
{
|
|
"entropy": 5.536181497573852,
|
|
"epoch": 0.8049017700836413,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.000494064700565585,
|
|
"loss": 5.2754,
|
|
"mean_token_accuracy": 0.17488184869289397,
|
|
"num_tokens": 17951288.0,
|
|
"step": 10345
|
|
},
|
|
{
|
|
"entropy": 5.613046884536743,
|
|
"epoch": 0.8052907994553589,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004940583749887403,
|
|
"loss": 5.5177,
|
|
"mean_token_accuracy": 0.1582699842751026,
|
|
"num_tokens": 17960300.0,
|
|
"step": 10350
|
|
},
|
|
{
|
|
"entropy": 5.569222831726075,
|
|
"epoch": 0.8056798288270764,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.0004940520460880333,
|
|
"loss": 5.388,
|
|
"mean_token_accuracy": 0.16975254267454148,
|
|
"num_tokens": 17968745.0,
|
|
"step": 10355
|
|
},
|
|
{
|
|
"entropy": 5.536905717849732,
|
|
"epoch": 0.806068858198794,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004940457138635601,
|
|
"loss": 5.3868,
|
|
"mean_token_accuracy": 0.17145797312259675,
|
|
"num_tokens": 17976614.0,
|
|
"step": 10360
|
|
},
|
|
{
|
|
"entropy": 5.601132726669311,
|
|
"epoch": 0.8064578875705116,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004940393783154169,
|
|
"loss": 5.5609,
|
|
"mean_token_accuracy": 0.15555154234170915,
|
|
"num_tokens": 17984769.0,
|
|
"step": 10365
|
|
},
|
|
{
|
|
"entropy": 5.637803840637207,
|
|
"epoch": 0.8068469169422291,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004940330394436999,
|
|
"loss": 5.4096,
|
|
"mean_token_accuracy": 0.16131651550531387,
|
|
"num_tokens": 17992885.0,
|
|
"step": 10370
|
|
},
|
|
{
|
|
"entropy": 5.6023236274719235,
|
|
"epoch": 0.8072359463139467,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.000494026697248505,
|
|
"loss": 5.4427,
|
|
"mean_token_accuracy": 0.16060977727174758,
|
|
"num_tokens": 18001752.0,
|
|
"step": 10375
|
|
},
|
|
{
|
|
"entropy": 5.539025354385376,
|
|
"epoch": 0.8076249756856643,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004940203517299287,
|
|
"loss": 5.4514,
|
|
"mean_token_accuracy": 0.16818694472312928,
|
|
"num_tokens": 18009939.0,
|
|
"step": 10380
|
|
},
|
|
{
|
|
"entropy": 5.642893218994141,
|
|
"epoch": 0.8080140050573819,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.000494014002888067,
|
|
"loss": 5.4256,
|
|
"mean_token_accuracy": 0.17641784995794296,
|
|
"num_tokens": 18017993.0,
|
|
"step": 10385
|
|
},
|
|
{
|
|
"entropy": 5.685582017898559,
|
|
"epoch": 0.8084030344290994,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004940076507230166,
|
|
"loss": 5.5275,
|
|
"mean_token_accuracy": 0.1595136985182762,
|
|
"num_tokens": 18027564.0,
|
|
"step": 10390
|
|
},
|
|
{
|
|
"entropy": 5.601905393600464,
|
|
"epoch": 0.8087920638008169,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004940012952348735,
|
|
"loss": 5.4925,
|
|
"mean_token_accuracy": 0.1663194105029106,
|
|
"num_tokens": 18036174.0,
|
|
"step": 10395
|
|
},
|
|
{
|
|
"entropy": 5.584610557556152,
|
|
"epoch": 0.8091810931725345,
|
|
"grad_norm": 2.578125,
|
|
"learning_rate": 0.0004939949364237345,
|
|
"loss": 5.4184,
|
|
"mean_token_accuracy": 0.16337654888629913,
|
|
"num_tokens": 18044994.0,
|
|
"step": 10400
|
|
},
|
|
{
|
|
"entropy": 5.556111240386963,
|
|
"epoch": 0.8095701225442521,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004939885742896958,
|
|
"loss": 5.414,
|
|
"mean_token_accuracy": 0.17001941949129104,
|
|
"num_tokens": 18053789.0,
|
|
"step": 10405
|
|
},
|
|
{
|
|
"entropy": 5.656559991836548,
|
|
"epoch": 0.8099591519159697,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.000493982208832854,
|
|
"loss": 5.5409,
|
|
"mean_token_accuracy": 0.15735476613044738,
|
|
"num_tokens": 18063483.0,
|
|
"step": 10410
|
|
},
|
|
{
|
|
"entropy": 5.597215843200684,
|
|
"epoch": 0.8103481812876873,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004939758400533058,
|
|
"loss": 5.3369,
|
|
"mean_token_accuracy": 0.16720130443572997,
|
|
"num_tokens": 18071952.0,
|
|
"step": 10415
|
|
},
|
|
{
|
|
"entropy": 5.521363878250122,
|
|
"epoch": 0.8107372106594047,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004939694679511478,
|
|
"loss": 5.3825,
|
|
"mean_token_accuracy": 0.16801090091466903,
|
|
"num_tokens": 18080323.0,
|
|
"step": 10420
|
|
},
|
|
{
|
|
"entropy": 5.6019659519195555,
|
|
"epoch": 0.8111262400311223,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004939630925264765,
|
|
"loss": 5.4981,
|
|
"mean_token_accuracy": 0.16568824797868728,
|
|
"num_tokens": 18089458.0,
|
|
"step": 10425
|
|
},
|
|
{
|
|
"entropy": 5.640874862670898,
|
|
"epoch": 0.8115152694028399,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.000493956713779389,
|
|
"loss": 5.4191,
|
|
"mean_token_accuracy": 0.16081434786319732,
|
|
"num_tokens": 18098553.0,
|
|
"step": 10430
|
|
},
|
|
{
|
|
"entropy": 5.577661180496216,
|
|
"epoch": 0.8119042987745575,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004939503317099817,
|
|
"loss": 5.5074,
|
|
"mean_token_accuracy": 0.16271842867136002,
|
|
"num_tokens": 18106794.0,
|
|
"step": 10435
|
|
},
|
|
{
|
|
"entropy": 5.592539739608765,
|
|
"epoch": 0.8122933281462751,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004939439463183517,
|
|
"loss": 5.3803,
|
|
"mean_token_accuracy": 0.1721673861145973,
|
|
"num_tokens": 18115509.0,
|
|
"step": 10440
|
|
},
|
|
{
|
|
"entropy": 5.6062883853912355,
|
|
"epoch": 0.8126823575179926,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004939375576045958,
|
|
"loss": 5.5061,
|
|
"mean_token_accuracy": 0.16080288887023925,
|
|
"num_tokens": 18124548.0,
|
|
"step": 10445
|
|
},
|
|
{
|
|
"entropy": 5.59943413734436,
|
|
"epoch": 0.8130713868897101,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004939311655688109,
|
|
"loss": 5.4267,
|
|
"mean_token_accuracy": 0.16586086750030518,
|
|
"num_tokens": 18132295.0,
|
|
"step": 10450
|
|
},
|
|
{
|
|
"entropy": 5.616068983078003,
|
|
"epoch": 0.8134604162614277,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004939247702110941,
|
|
"loss": 5.5311,
|
|
"mean_token_accuracy": 0.16209654808044432,
|
|
"num_tokens": 18140731.0,
|
|
"step": 10455
|
|
},
|
|
{
|
|
"entropy": 5.633013343811035,
|
|
"epoch": 0.8138494456331453,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004939183715315423,
|
|
"loss": 5.4039,
|
|
"mean_token_accuracy": 0.16486435532569885,
|
|
"num_tokens": 18149834.0,
|
|
"step": 10460
|
|
},
|
|
{
|
|
"entropy": 5.60955114364624,
|
|
"epoch": 0.8142384750048629,
|
|
"grad_norm": 2.734375,
|
|
"learning_rate": 0.0004939119695302526,
|
|
"loss": 5.3614,
|
|
"mean_token_accuracy": 0.17106925398111344,
|
|
"num_tokens": 18158745.0,
|
|
"step": 10465
|
|
},
|
|
{
|
|
"entropy": 5.645635509490967,
|
|
"epoch": 0.8146275043765804,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.0004939055642073224,
|
|
"loss": 5.5618,
|
|
"mean_token_accuracy": 0.15414967238903046,
|
|
"num_tokens": 18168292.0,
|
|
"step": 10470
|
|
},
|
|
{
|
|
"entropy": 5.646367979049683,
|
|
"epoch": 0.815016533748298,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004938991555628484,
|
|
"loss": 5.4561,
|
|
"mean_token_accuracy": 0.15823084786534308,
|
|
"num_tokens": 18177592.0,
|
|
"step": 10475
|
|
},
|
|
{
|
|
"entropy": 5.6279990673065186,
|
|
"epoch": 0.8154055631200156,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004938927435969283,
|
|
"loss": 5.4272,
|
|
"mean_token_accuracy": 0.16151497662067413,
|
|
"num_tokens": 18186845.0,
|
|
"step": 10480
|
|
},
|
|
{
|
|
"entropy": 5.614060544967652,
|
|
"epoch": 0.8157945924917331,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004938863283096592,
|
|
"loss": 5.5079,
|
|
"mean_token_accuracy": 0.15635852068662642,
|
|
"num_tokens": 18195417.0,
|
|
"step": 10485
|
|
},
|
|
{
|
|
"entropy": 5.601277017593384,
|
|
"epoch": 0.8161836218634507,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004938799097011384,
|
|
"loss": 5.4367,
|
|
"mean_token_accuracy": 0.16019178926944733,
|
|
"num_tokens": 18204009.0,
|
|
"step": 10490
|
|
},
|
|
{
|
|
"entropy": 5.568668603897095,
|
|
"epoch": 0.8165726512351682,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004938734877714634,
|
|
"loss": 5.4354,
|
|
"mean_token_accuracy": 0.1707957848906517,
|
|
"num_tokens": 18211927.0,
|
|
"step": 10495
|
|
},
|
|
{
|
|
"entropy": 5.516373252868652,
|
|
"epoch": 0.8169616806068858,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004938670625207317,
|
|
"loss": 5.3591,
|
|
"mean_token_accuracy": 0.17173811048269272,
|
|
"num_tokens": 18220394.0,
|
|
"step": 10500
|
|
},
|
|
{
|
|
"entropy": 5.631072282791138,
|
|
"epoch": 0.8173507099786034,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004938606339490406,
|
|
"loss": 5.4695,
|
|
"mean_token_accuracy": 0.16214495599269868,
|
|
"num_tokens": 18229803.0,
|
|
"step": 10505
|
|
},
|
|
{
|
|
"entropy": 5.617847442626953,
|
|
"epoch": 0.817739739350321,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004938542020564877,
|
|
"loss": 5.4333,
|
|
"mean_token_accuracy": 0.16107070446014404,
|
|
"num_tokens": 18238431.0,
|
|
"step": 10510
|
|
},
|
|
{
|
|
"entropy": 5.549394273757935,
|
|
"epoch": 0.8181287687220385,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004938477668431706,
|
|
"loss": 5.4465,
|
|
"mean_token_accuracy": 0.16725078821182252,
|
|
"num_tokens": 18246745.0,
|
|
"step": 10515
|
|
},
|
|
{
|
|
"entropy": 5.530304431915283,
|
|
"epoch": 0.8185177980937561,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004938413283091871,
|
|
"loss": 5.4062,
|
|
"mean_token_accuracy": 0.1659283459186554,
|
|
"num_tokens": 18255569.0,
|
|
"step": 10520
|
|
},
|
|
{
|
|
"entropy": 5.569682216644287,
|
|
"epoch": 0.8189068274654736,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004938348864546347,
|
|
"loss": 5.3463,
|
|
"mean_token_accuracy": 0.16907418817281722,
|
|
"num_tokens": 18263711.0,
|
|
"step": 10525
|
|
},
|
|
{
|
|
"entropy": 5.705848264694214,
|
|
"epoch": 0.8192958568371912,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004938284412796111,
|
|
"loss": 5.5241,
|
|
"mean_token_accuracy": 0.16439357846975328,
|
|
"num_tokens": 18272220.0,
|
|
"step": 10530
|
|
},
|
|
{
|
|
"entropy": 5.573349475860596,
|
|
"epoch": 0.8196848862089088,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004938219927842144,
|
|
"loss": 5.4329,
|
|
"mean_token_accuracy": 0.163949453830719,
|
|
"num_tokens": 18281107.0,
|
|
"step": 10535
|
|
},
|
|
{
|
|
"entropy": 5.4945001125335695,
|
|
"epoch": 0.8200739155806264,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004938155409685422,
|
|
"loss": 5.3947,
|
|
"mean_token_accuracy": 0.16415611356496812,
|
|
"num_tokens": 18290196.0,
|
|
"step": 10540
|
|
},
|
|
{
|
|
"entropy": 5.641933822631836,
|
|
"epoch": 0.820462944952344,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.0004938090858326923,
|
|
"loss": 5.5487,
|
|
"mean_token_accuracy": 0.16089368164539336,
|
|
"num_tokens": 18299418.0,
|
|
"step": 10545
|
|
},
|
|
{
|
|
"entropy": 5.534397268295288,
|
|
"epoch": 0.8208519743240614,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.000493802627376763,
|
|
"loss": 5.2681,
|
|
"mean_token_accuracy": 0.17511842250823975,
|
|
"num_tokens": 18308171.0,
|
|
"step": 10550
|
|
},
|
|
{
|
|
"entropy": 5.6119359016418455,
|
|
"epoch": 0.821241003695779,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.0004937961656008518,
|
|
"loss": 5.469,
|
|
"mean_token_accuracy": 0.16383302211761475,
|
|
"num_tokens": 18317144.0,
|
|
"step": 10555
|
|
},
|
|
{
|
|
"entropy": 5.598818588256836,
|
|
"epoch": 0.8216300330674966,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004937897005050573,
|
|
"loss": 5.5389,
|
|
"mean_token_accuracy": 0.16111208945512773,
|
|
"num_tokens": 18326648.0,
|
|
"step": 10560
|
|
},
|
|
{
|
|
"entropy": 5.663065338134766,
|
|
"epoch": 0.8220190624392142,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004937832320894772,
|
|
"loss": 5.4837,
|
|
"mean_token_accuracy": 0.16640617996454238,
|
|
"num_tokens": 18335901.0,
|
|
"step": 10565
|
|
},
|
|
{
|
|
"entropy": 5.592900085449219,
|
|
"epoch": 0.8224080918109318,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004937767603542098,
|
|
"loss": 5.4167,
|
|
"mean_token_accuracy": 0.16778741925954818,
|
|
"num_tokens": 18344905.0,
|
|
"step": 10570
|
|
},
|
|
{
|
|
"entropy": 5.480745840072632,
|
|
"epoch": 0.8227971211826492,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004937702852993534,
|
|
"loss": 5.3637,
|
|
"mean_token_accuracy": 0.17065452486276628,
|
|
"num_tokens": 18353422.0,
|
|
"step": 10575
|
|
},
|
|
{
|
|
"entropy": 5.719949340820312,
|
|
"epoch": 0.8231861505543668,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.000493763806925006,
|
|
"loss": 5.5222,
|
|
"mean_token_accuracy": 0.1527490124106407,
|
|
"num_tokens": 18361632.0,
|
|
"step": 10580
|
|
},
|
|
{
|
|
"entropy": 5.584030675888061,
|
|
"epoch": 0.8235751799260844,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.0004937573252312661,
|
|
"loss": 5.3702,
|
|
"mean_token_accuracy": 0.17391784489154816,
|
|
"num_tokens": 18370142.0,
|
|
"step": 10585
|
|
},
|
|
{
|
|
"entropy": 5.516370964050293,
|
|
"epoch": 0.823964209297802,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.000493750840218232,
|
|
"loss": 5.3987,
|
|
"mean_token_accuracy": 0.16997681856155394,
|
|
"num_tokens": 18378245.0,
|
|
"step": 10590
|
|
},
|
|
{
|
|
"entropy": 5.530230712890625,
|
|
"epoch": 0.8243532386695196,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004937443518860021,
|
|
"loss": 5.371,
|
|
"mean_token_accuracy": 0.16971075683832168,
|
|
"num_tokens": 18386814.0,
|
|
"step": 10595
|
|
},
|
|
{
|
|
"entropy": 5.557858180999756,
|
|
"epoch": 0.8247422680412371,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004937378602346747,
|
|
"loss": 5.3934,
|
|
"mean_token_accuracy": 0.16131658852100372,
|
|
"num_tokens": 18396276.0,
|
|
"step": 10600
|
|
},
|
|
{
|
|
"entropy": 5.602482557296753,
|
|
"epoch": 0.8251312974129547,
|
|
"grad_norm": 2.578125,
|
|
"learning_rate": 0.0004937313652643485,
|
|
"loss": 5.4063,
|
|
"mean_token_accuracy": 0.16615637689828872,
|
|
"num_tokens": 18404445.0,
|
|
"step": 10605
|
|
},
|
|
{
|
|
"entropy": 5.520392036437988,
|
|
"epoch": 0.8255203267846722,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.000493724866975122,
|
|
"loss": 5.3031,
|
|
"mean_token_accuracy": 0.1748577743768692,
|
|
"num_tokens": 18412870.0,
|
|
"step": 10610
|
|
},
|
|
{
|
|
"entropy": 5.508503103256226,
|
|
"epoch": 0.8259093561563898,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004937183653670937,
|
|
"loss": 5.4393,
|
|
"mean_token_accuracy": 0.16420634537935258,
|
|
"num_tokens": 18421084.0,
|
|
"step": 10615
|
|
},
|
|
{
|
|
"entropy": 5.564705753326416,
|
|
"epoch": 0.8262983855281074,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004937118604403623,
|
|
"loss": 5.4678,
|
|
"mean_token_accuracy": 0.16587617248296738,
|
|
"num_tokens": 18429869.0,
|
|
"step": 10620
|
|
},
|
|
{
|
|
"entropy": 5.573436832427978,
|
|
"epoch": 0.8266874148998249,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004937053521950266,
|
|
"loss": 5.3284,
|
|
"mean_token_accuracy": 0.16766274869441986,
|
|
"num_tokens": 18438747.0,
|
|
"step": 10625
|
|
},
|
|
{
|
|
"entropy": 5.665083026885986,
|
|
"epoch": 0.8270764442715425,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004936988406311854,
|
|
"loss": 5.5365,
|
|
"mean_token_accuracy": 0.15890450030565262,
|
|
"num_tokens": 18447241.0,
|
|
"step": 10630
|
|
},
|
|
{
|
|
"entropy": 5.7015656471252445,
|
|
"epoch": 0.8274654736432601,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004936923257489373,
|
|
"loss": 5.5596,
|
|
"mean_token_accuracy": 0.15821138247847558,
|
|
"num_tokens": 18455757.0,
|
|
"step": 10635
|
|
},
|
|
{
|
|
"entropy": 5.544709491729736,
|
|
"epoch": 0.8278545030149776,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004936858075483811,
|
|
"loss": 5.3769,
|
|
"mean_token_accuracy": 0.17397935390472413,
|
|
"num_tokens": 18463863.0,
|
|
"step": 10640
|
|
},
|
|
{
|
|
"entropy": 5.556622886657715,
|
|
"epoch": 0.8282435323866952,
|
|
"grad_norm": 3.0625,
|
|
"learning_rate": 0.000493679286029616,
|
|
"loss": 5.557,
|
|
"mean_token_accuracy": 0.1569342777132988,
|
|
"num_tokens": 18472396.0,
|
|
"step": 10645
|
|
},
|
|
{
|
|
"entropy": 5.580170726776123,
|
|
"epoch": 0.8286325617584127,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004936727611927407,
|
|
"loss": 5.4125,
|
|
"mean_token_accuracy": 0.1605270177125931,
|
|
"num_tokens": 18480625.0,
|
|
"step": 10650
|
|
},
|
|
{
|
|
"entropy": 5.61102328300476,
|
|
"epoch": 0.8290215911301303,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004936662330378546,
|
|
"loss": 5.4834,
|
|
"mean_token_accuracy": 0.1617751434445381,
|
|
"num_tokens": 18489878.0,
|
|
"step": 10655
|
|
},
|
|
{
|
|
"entropy": 5.580025768280029,
|
|
"epoch": 0.8294106205018479,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004936597015650561,
|
|
"loss": 5.3825,
|
|
"mean_token_accuracy": 0.16149143129587173,
|
|
"num_tokens": 18498873.0,
|
|
"step": 10660
|
|
},
|
|
{
|
|
"entropy": 5.667516469955444,
|
|
"epoch": 0.8297996498735655,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004936531667744448,
|
|
"loss": 5.514,
|
|
"mean_token_accuracy": 0.15458784252405167,
|
|
"num_tokens": 18507716.0,
|
|
"step": 10665
|
|
},
|
|
{
|
|
"entropy": 5.58152208328247,
|
|
"epoch": 0.8301886792452831,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004936466286661197,
|
|
"loss": 5.3541,
|
|
"mean_token_accuracy": 0.1737774208188057,
|
|
"num_tokens": 18516547.0,
|
|
"step": 10670
|
|
},
|
|
{
|
|
"entropy": 5.597664213180542,
|
|
"epoch": 0.8305777086170005,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00049364008724018,
|
|
"loss": 5.4877,
|
|
"mean_token_accuracy": 0.16016840189695358,
|
|
"num_tokens": 18525714.0,
|
|
"step": 10675
|
|
},
|
|
{
|
|
"entropy": 5.611033296585083,
|
|
"epoch": 0.8309667379887181,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.000493633542496725,
|
|
"loss": 5.5175,
|
|
"mean_token_accuracy": 0.16490766108036042,
|
|
"num_tokens": 18534981.0,
|
|
"step": 10680
|
|
},
|
|
{
|
|
"entropy": 5.605623769760132,
|
|
"epoch": 0.8313557673604357,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004936269944358539,
|
|
"loss": 5.4396,
|
|
"mean_token_accuracy": 0.16582519561052322,
|
|
"num_tokens": 18543599.0,
|
|
"step": 10685
|
|
},
|
|
{
|
|
"entropy": 5.6430579662323,
|
|
"epoch": 0.8317447967321533,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004936204430576664,
|
|
"loss": 5.4097,
|
|
"mean_token_accuracy": 0.17386528998613357,
|
|
"num_tokens": 18552207.0,
|
|
"step": 10690
|
|
},
|
|
{
|
|
"entropy": 5.586783695220947,
|
|
"epoch": 0.8321338261038709,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004936138883622614,
|
|
"loss": 5.4901,
|
|
"mean_token_accuracy": 0.16271726936101913,
|
|
"num_tokens": 18560421.0,
|
|
"step": 10695
|
|
},
|
|
{
|
|
"entropy": 5.592414093017578,
|
|
"epoch": 0.8325228554755884,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004936073303497387,
|
|
"loss": 5.3776,
|
|
"mean_token_accuracy": 0.17105771005153655,
|
|
"num_tokens": 18568812.0,
|
|
"step": 10700
|
|
},
|
|
{
|
|
"entropy": 5.595654630661011,
|
|
"epoch": 0.8329118848473059,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004936007690201976,
|
|
"loss": 5.3693,
|
|
"mean_token_accuracy": 0.16839257776737213,
|
|
"num_tokens": 18577077.0,
|
|
"step": 10705
|
|
},
|
|
{
|
|
"entropy": 5.580293750762939,
|
|
"epoch": 0.8333009142190235,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.000493594204373738,
|
|
"loss": 5.4792,
|
|
"mean_token_accuracy": 0.16489122807979584,
|
|
"num_tokens": 18585754.0,
|
|
"step": 10710
|
|
},
|
|
{
|
|
"entropy": 5.522100019454956,
|
|
"epoch": 0.8336899435907411,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004935876364104591,
|
|
"loss": 5.3631,
|
|
"mean_token_accuracy": 0.16696490049362184,
|
|
"num_tokens": 18594578.0,
|
|
"step": 10715
|
|
},
|
|
{
|
|
"entropy": 5.617912912368775,
|
|
"epoch": 0.8340789729624587,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004935810651304608,
|
|
"loss": 5.4762,
|
|
"mean_token_accuracy": 0.1588385820388794,
|
|
"num_tokens": 18603810.0,
|
|
"step": 10720
|
|
},
|
|
{
|
|
"entropy": 5.6939843654632565,
|
|
"epoch": 0.8344680023341763,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004935744905338427,
|
|
"loss": 5.4456,
|
|
"mean_token_accuracy": 0.161747607588768,
|
|
"num_tokens": 18612870.0,
|
|
"step": 10725
|
|
},
|
|
{
|
|
"entropy": 5.620265007019043,
|
|
"epoch": 0.8348570317058938,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004935679126207046,
|
|
"loss": 5.5157,
|
|
"mean_token_accuracy": 0.1638943523168564,
|
|
"num_tokens": 18621353.0,
|
|
"step": 10730
|
|
},
|
|
{
|
|
"entropy": 5.502186822891235,
|
|
"epoch": 0.8352460610776113,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004935613313911463,
|
|
"loss": 5.3857,
|
|
"mean_token_accuracy": 0.1673603981733322,
|
|
"num_tokens": 18630152.0,
|
|
"step": 10735
|
|
},
|
|
{
|
|
"entropy": 5.562418603897095,
|
|
"epoch": 0.8356350904493289,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004935547468452678,
|
|
"loss": 5.4313,
|
|
"mean_token_accuracy": 0.16592019349336623,
|
|
"num_tokens": 18639278.0,
|
|
"step": 10740
|
|
},
|
|
{
|
|
"entropy": 5.610720300674439,
|
|
"epoch": 0.8360241198210465,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.0004935481589831688,
|
|
"loss": 5.4182,
|
|
"mean_token_accuracy": 0.1697460889816284,
|
|
"num_tokens": 18647436.0,
|
|
"step": 10745
|
|
},
|
|
{
|
|
"entropy": 5.701122903823853,
|
|
"epoch": 0.8364131491927641,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004935415678049492,
|
|
"loss": 5.442,
|
|
"mean_token_accuracy": 0.15971136838197708,
|
|
"num_tokens": 18655532.0,
|
|
"step": 10750
|
|
},
|
|
{
|
|
"entropy": 5.636491298675537,
|
|
"epoch": 0.8368021785644816,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004935349733107094,
|
|
"loss": 5.4711,
|
|
"mean_token_accuracy": 0.16443484872579575,
|
|
"num_tokens": 18664827.0,
|
|
"step": 10755
|
|
},
|
|
{
|
|
"entropy": 5.548076486587524,
|
|
"epoch": 0.8371912079361992,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.000493528375500549,
|
|
"loss": 5.3793,
|
|
"mean_token_accuracy": 0.1734402894973755,
|
|
"num_tokens": 18673535.0,
|
|
"step": 10760
|
|
},
|
|
{
|
|
"entropy": 5.615402460098267,
|
|
"epoch": 0.8375802373079168,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004935217743745685,
|
|
"loss": 5.5589,
|
|
"mean_token_accuracy": 0.15757714211940765,
|
|
"num_tokens": 18682223.0,
|
|
"step": 10765
|
|
},
|
|
{
|
|
"entropy": 5.717745971679688,
|
|
"epoch": 0.8379692666796343,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004935151699328677,
|
|
"loss": 5.4631,
|
|
"mean_token_accuracy": 0.16686998009681703,
|
|
"num_tokens": 18690847.0,
|
|
"step": 10770
|
|
},
|
|
{
|
|
"entropy": 5.659970808029175,
|
|
"epoch": 0.8383582960513519,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004935085621755471,
|
|
"loss": 5.4589,
|
|
"mean_token_accuracy": 0.1638115555047989,
|
|
"num_tokens": 18699658.0,
|
|
"step": 10775
|
|
},
|
|
{
|
|
"entropy": 5.596157026290894,
|
|
"epoch": 0.8387473254230694,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.000493501951102707,
|
|
"loss": 5.4399,
|
|
"mean_token_accuracy": 0.1618892252445221,
|
|
"num_tokens": 18708396.0,
|
|
"step": 10780
|
|
},
|
|
{
|
|
"entropy": 5.562104082107544,
|
|
"epoch": 0.839136354794787,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004934953367144474,
|
|
"loss": 5.4614,
|
|
"mean_token_accuracy": 0.16248811781406403,
|
|
"num_tokens": 18717185.0,
|
|
"step": 10785
|
|
},
|
|
{
|
|
"entropy": 5.659436798095703,
|
|
"epoch": 0.8395253841665046,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004934887190108688,
|
|
"loss": 5.3989,
|
|
"mean_token_accuracy": 0.16952570229768754,
|
|
"num_tokens": 18725493.0,
|
|
"step": 10790
|
|
},
|
|
{
|
|
"entropy": 5.608885335922241,
|
|
"epoch": 0.8399144135382222,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004934820979920719,
|
|
"loss": 5.3988,
|
|
"mean_token_accuracy": 0.16731245517730714,
|
|
"num_tokens": 18733843.0,
|
|
"step": 10795
|
|
},
|
|
{
|
|
"entropy": 5.575446748733521,
|
|
"epoch": 0.8403034429099397,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004934754736581567,
|
|
"loss": 5.4595,
|
|
"mean_token_accuracy": 0.16522205770015716,
|
|
"num_tokens": 18742226.0,
|
|
"step": 10800
|
|
},
|
|
{
|
|
"entropy": 5.669210577011109,
|
|
"epoch": 0.8406924722816572,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.000493468846009224,
|
|
"loss": 5.5991,
|
|
"mean_token_accuracy": 0.15872693657875062,
|
|
"num_tokens": 18751117.0,
|
|
"step": 10805
|
|
},
|
|
{
|
|
"entropy": 5.614519691467285,
|
|
"epoch": 0.8410815016533748,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004934622150453742,
|
|
"loss": 5.4192,
|
|
"mean_token_accuracy": 0.16686538308858873,
|
|
"num_tokens": 18759244.0,
|
|
"step": 10810
|
|
},
|
|
{
|
|
"entropy": 5.567561769485474,
|
|
"epoch": 0.8414705310250924,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.000493455580766708,
|
|
"loss": 5.4834,
|
|
"mean_token_accuracy": 0.16303838342428206,
|
|
"num_tokens": 18768107.0,
|
|
"step": 10815
|
|
},
|
|
{
|
|
"entropy": 5.531203556060791,
|
|
"epoch": 0.84185956039681,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004934489431733262,
|
|
"loss": 5.323,
|
|
"mean_token_accuracy": 0.16933274567127227,
|
|
"num_tokens": 18777419.0,
|
|
"step": 10820
|
|
},
|
|
{
|
|
"entropy": 5.629980516433716,
|
|
"epoch": 0.8422485897685276,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004934423022653293,
|
|
"loss": 5.4494,
|
|
"mean_token_accuracy": 0.16474525183439254,
|
|
"num_tokens": 18786410.0,
|
|
"step": 10825
|
|
},
|
|
{
|
|
"entropy": 5.597207403182983,
|
|
"epoch": 0.842637619140245,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004934356580428182,
|
|
"loss": 5.4088,
|
|
"mean_token_accuracy": 0.1639324113726616,
|
|
"num_tokens": 18794409.0,
|
|
"step": 10830
|
|
},
|
|
{
|
|
"entropy": 5.546269083023072,
|
|
"epoch": 0.8430266485119626,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004934290105058937,
|
|
"loss": 5.4686,
|
|
"mean_token_accuracy": 0.16208438575267792,
|
|
"num_tokens": 18803561.0,
|
|
"step": 10835
|
|
},
|
|
{
|
|
"entropy": 5.5684432029724125,
|
|
"epoch": 0.8434156778836802,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004934223596546565,
|
|
"loss": 5.4267,
|
|
"mean_token_accuracy": 0.16030320823192595,
|
|
"num_tokens": 18812096.0,
|
|
"step": 10840
|
|
},
|
|
{
|
|
"entropy": 5.600976467132568,
|
|
"epoch": 0.8438047072553978,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004934157054892077,
|
|
"loss": 5.4528,
|
|
"mean_token_accuracy": 0.1602882444858551,
|
|
"num_tokens": 18820506.0,
|
|
"step": 10845
|
|
},
|
|
{
|
|
"entropy": 5.616394281387329,
|
|
"epoch": 0.8441937366271154,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004934090480096482,
|
|
"loss": 5.4516,
|
|
"mean_token_accuracy": 0.16456348299980164,
|
|
"num_tokens": 18829437.0,
|
|
"step": 10850
|
|
},
|
|
{
|
|
"entropy": 5.699944686889649,
|
|
"epoch": 0.8445827659988329,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004934023872160791,
|
|
"loss": 5.5665,
|
|
"mean_token_accuracy": 0.16061313152313234,
|
|
"num_tokens": 18838759.0,
|
|
"step": 10855
|
|
},
|
|
{
|
|
"entropy": 5.597001600265503,
|
|
"epoch": 0.8449717953705504,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004933957231086014,
|
|
"loss": 5.4612,
|
|
"mean_token_accuracy": 0.16601901054382323,
|
|
"num_tokens": 18847000.0,
|
|
"step": 10860
|
|
},
|
|
{
|
|
"entropy": 5.601649618148803,
|
|
"epoch": 0.845360824742268,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004933890556873161,
|
|
"loss": 5.5343,
|
|
"mean_token_accuracy": 0.1564929887652397,
|
|
"num_tokens": 18855370.0,
|
|
"step": 10865
|
|
},
|
|
{
|
|
"entropy": 5.698432302474975,
|
|
"epoch": 0.8457498541139856,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004933823849523246,
|
|
"loss": 5.5949,
|
|
"mean_token_accuracy": 0.15831229239702224,
|
|
"num_tokens": 18863825.0,
|
|
"step": 10870
|
|
},
|
|
{
|
|
"entropy": 5.620156240463257,
|
|
"epoch": 0.8461388834857032,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004933757109037279,
|
|
"loss": 5.3282,
|
|
"mean_token_accuracy": 0.1642865091562271,
|
|
"num_tokens": 18872088.0,
|
|
"step": 10875
|
|
},
|
|
{
|
|
"entropy": 5.5633057117462155,
|
|
"epoch": 0.8465279128574207,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004933690335416274,
|
|
"loss": 5.3486,
|
|
"mean_token_accuracy": 0.1773277997970581,
|
|
"num_tokens": 18880472.0,
|
|
"step": 10880
|
|
},
|
|
{
|
|
"entropy": 5.661197471618652,
|
|
"epoch": 0.8469169422291383,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004933623528661245,
|
|
"loss": 5.5364,
|
|
"mean_token_accuracy": 0.16062142550945283,
|
|
"num_tokens": 18889822.0,
|
|
"step": 10885
|
|
},
|
|
{
|
|
"entropy": 5.6680803298950195,
|
|
"epoch": 0.8473059716008559,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004933556688773203,
|
|
"loss": 5.461,
|
|
"mean_token_accuracy": 0.1654386967420578,
|
|
"num_tokens": 18897542.0,
|
|
"step": 10890
|
|
},
|
|
{
|
|
"entropy": 5.52772364616394,
|
|
"epoch": 0.8476950009725734,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004933489815753165,
|
|
"loss": 5.5129,
|
|
"mean_token_accuracy": 0.1636799842119217,
|
|
"num_tokens": 18906330.0,
|
|
"step": 10895
|
|
},
|
|
{
|
|
"entropy": 5.554571342468262,
|
|
"epoch": 0.848084030344291,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004933422909602143,
|
|
"loss": 5.3405,
|
|
"mean_token_accuracy": 0.17273216545581818,
|
|
"num_tokens": 18914176.0,
|
|
"step": 10900
|
|
},
|
|
{
|
|
"entropy": 5.5777268409729,
|
|
"epoch": 0.8484730597160085,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004933355970321155,
|
|
"loss": 5.3792,
|
|
"mean_token_accuracy": 0.17397787570953369,
|
|
"num_tokens": 18922233.0,
|
|
"step": 10905
|
|
},
|
|
{
|
|
"entropy": 5.512351560592651,
|
|
"epoch": 0.8488620890877261,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004933288997911215,
|
|
"loss": 5.4074,
|
|
"mean_token_accuracy": 0.17171715646982194,
|
|
"num_tokens": 18930742.0,
|
|
"step": 10910
|
|
},
|
|
{
|
|
"entropy": 5.58294711112976,
|
|
"epoch": 0.8492511184594437,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004933221992373338,
|
|
"loss": 5.3429,
|
|
"mean_token_accuracy": 0.1723746880888939,
|
|
"num_tokens": 18938879.0,
|
|
"step": 10915
|
|
},
|
|
{
|
|
"entropy": 5.702480030059815,
|
|
"epoch": 0.8496401478311613,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004933154953708544,
|
|
"loss": 5.5466,
|
|
"mean_token_accuracy": 0.1529100403189659,
|
|
"num_tokens": 18947753.0,
|
|
"step": 10920
|
|
},
|
|
{
|
|
"entropy": 5.628855419158936,
|
|
"epoch": 0.8500291772028788,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004933087881917848,
|
|
"loss": 5.4423,
|
|
"mean_token_accuracy": 0.16019981801509858,
|
|
"num_tokens": 18956805.0,
|
|
"step": 10925
|
|
},
|
|
{
|
|
"entropy": 5.513213014602661,
|
|
"epoch": 0.8504182065745964,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004933020777002268,
|
|
"loss": 5.3946,
|
|
"mean_token_accuracy": 0.1699616253376007,
|
|
"num_tokens": 18965683.0,
|
|
"step": 10930
|
|
},
|
|
{
|
|
"entropy": 5.545962190628051,
|
|
"epoch": 0.8508072359463139,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004932953638962823,
|
|
"loss": 5.3836,
|
|
"mean_token_accuracy": 0.1677742287516594,
|
|
"num_tokens": 18973873.0,
|
|
"step": 10935
|
|
},
|
|
{
|
|
"entropy": 5.533621215820313,
|
|
"epoch": 0.8511962653180315,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.000493288646780053,
|
|
"loss": 5.3252,
|
|
"mean_token_accuracy": 0.1759396269917488,
|
|
"num_tokens": 18982097.0,
|
|
"step": 10940
|
|
},
|
|
{
|
|
"entropy": 5.569990348815918,
|
|
"epoch": 0.8515852946897491,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004932819263516409,
|
|
"loss": 5.3822,
|
|
"mean_token_accuracy": 0.16632181257009507,
|
|
"num_tokens": 18991019.0,
|
|
"step": 10945
|
|
},
|
|
{
|
|
"entropy": 5.584324312210083,
|
|
"epoch": 0.8519743240614667,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004932752026111481,
|
|
"loss": 5.3909,
|
|
"mean_token_accuracy": 0.16592037975788115,
|
|
"num_tokens": 18999231.0,
|
|
"step": 10950
|
|
},
|
|
{
|
|
"entropy": 5.627434206008911,
|
|
"epoch": 0.8523633534331843,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004932684755586765,
|
|
"loss": 5.4736,
|
|
"mean_token_accuracy": 0.16317906975746155,
|
|
"num_tokens": 19007807.0,
|
|
"step": 10955
|
|
},
|
|
{
|
|
"entropy": 5.536687231063842,
|
|
"epoch": 0.8527523828049017,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004932617451943282,
|
|
"loss": 5.4578,
|
|
"mean_token_accuracy": 0.16746993213891984,
|
|
"num_tokens": 19017908.0,
|
|
"step": 10960
|
|
},
|
|
{
|
|
"entropy": 5.55510458946228,
|
|
"epoch": 0.8531414121766193,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004932550115182053,
|
|
"loss": 5.4541,
|
|
"mean_token_accuracy": 0.16267437040805816,
|
|
"num_tokens": 19026999.0,
|
|
"step": 10965
|
|
},
|
|
{
|
|
"entropy": 5.516574144363403,
|
|
"epoch": 0.8535304415483369,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.00049324827453041,
|
|
"loss": 5.3652,
|
|
"mean_token_accuracy": 0.17764215916395187,
|
|
"num_tokens": 19035738.0,
|
|
"step": 10970
|
|
},
|
|
{
|
|
"entropy": 5.5748766422271725,
|
|
"epoch": 0.8539194709200545,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004932415342310446,
|
|
"loss": 5.4544,
|
|
"mean_token_accuracy": 0.16744358092546463,
|
|
"num_tokens": 19044530.0,
|
|
"step": 10975
|
|
},
|
|
{
|
|
"entropy": 5.563995313644409,
|
|
"epoch": 0.8543085002917721,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004932347906202111,
|
|
"loss": 5.4462,
|
|
"mean_token_accuracy": 0.16135307550430297,
|
|
"num_tokens": 19053306.0,
|
|
"step": 10980
|
|
},
|
|
{
|
|
"entropy": 5.668405628204345,
|
|
"epoch": 0.8546975296634896,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.000493228043698012,
|
|
"loss": 5.444,
|
|
"mean_token_accuracy": 0.1676616132259369,
|
|
"num_tokens": 19062172.0,
|
|
"step": 10985
|
|
},
|
|
{
|
|
"entropy": 5.448013257980347,
|
|
"epoch": 0.8550865590352071,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004932212934645498,
|
|
"loss": 5.2317,
|
|
"mean_token_accuracy": 0.17657214850187303,
|
|
"num_tokens": 19070804.0,
|
|
"step": 10990
|
|
},
|
|
{
|
|
"entropy": 5.558322095870972,
|
|
"epoch": 0.8554755884069247,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.0004932145399199268,
|
|
"loss": 5.3942,
|
|
"mean_token_accuracy": 0.17129886597394944,
|
|
"num_tokens": 19079055.0,
|
|
"step": 10995
|
|
},
|
|
{
|
|
"entropy": 5.553512859344482,
|
|
"epoch": 0.8558646177786423,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004932077830642455,
|
|
"loss": 5.3717,
|
|
"mean_token_accuracy": 0.16821828484535217,
|
|
"num_tokens": 19087459.0,
|
|
"step": 11000
|
|
},
|
|
{
|
|
"entropy": 5.458574676513672,
|
|
"epoch": 0.8562536471503599,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004932010228976084,
|
|
"loss": 5.2555,
|
|
"mean_token_accuracy": 0.1769370749592781,
|
|
"num_tokens": 19096271.0,
|
|
"step": 11005
|
|
},
|
|
{
|
|
"entropy": 5.552489280700684,
|
|
"epoch": 0.8566426765220774,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.000493194259420118,
|
|
"loss": 5.4576,
|
|
"mean_token_accuracy": 0.1654369756579399,
|
|
"num_tokens": 19105257.0,
|
|
"step": 11010
|
|
},
|
|
{
|
|
"entropy": 5.599417304992675,
|
|
"epoch": 0.857031705893795,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.000493187492631877,
|
|
"loss": 5.4055,
|
|
"mean_token_accuracy": 0.17078562825918198,
|
|
"num_tokens": 19113673.0,
|
|
"step": 11015
|
|
},
|
|
{
|
|
"entropy": 5.586803674697876,
|
|
"epoch": 0.8574207352655125,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.0004931807225329882,
|
|
"loss": 5.3628,
|
|
"mean_token_accuracy": 0.17019713819026946,
|
|
"num_tokens": 19121635.0,
|
|
"step": 11020
|
|
},
|
|
{
|
|
"entropy": 5.576512002944947,
|
|
"epoch": 0.8578097646372301,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004931739491235541,
|
|
"loss": 5.4334,
|
|
"mean_token_accuracy": 0.16907898634672164,
|
|
"num_tokens": 19130097.0,
|
|
"step": 11025
|
|
},
|
|
{
|
|
"entropy": 5.505575513839721,
|
|
"epoch": 0.8581987940089477,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004931671724036777,
|
|
"loss": 5.3411,
|
|
"mean_token_accuracy": 0.17085011452436447,
|
|
"num_tokens": 19138349.0,
|
|
"step": 11030
|
|
},
|
|
{
|
|
"entropy": 5.521160554885864,
|
|
"epoch": 0.8585878233806652,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004931603923734616,
|
|
"loss": 5.431,
|
|
"mean_token_accuracy": 0.16136478036642074,
|
|
"num_tokens": 19146948.0,
|
|
"step": 11035
|
|
},
|
|
{
|
|
"entropy": 5.5303449630737305,
|
|
"epoch": 0.8589768527523828,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004931536090330088,
|
|
"loss": 5.3903,
|
|
"mean_token_accuracy": 0.16915357261896133,
|
|
"num_tokens": 19155372.0,
|
|
"step": 11040
|
|
},
|
|
{
|
|
"entropy": 5.659363651275635,
|
|
"epoch": 0.8593658821241004,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004931468223824222,
|
|
"loss": 5.4744,
|
|
"mean_token_accuracy": 0.16891405135393142,
|
|
"num_tokens": 19163634.0,
|
|
"step": 11045
|
|
},
|
|
{
|
|
"entropy": 5.687005615234375,
|
|
"epoch": 0.859754911495818,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004931400324218048,
|
|
"loss": 5.4874,
|
|
"mean_token_accuracy": 0.16447663456201553,
|
|
"num_tokens": 19171582.0,
|
|
"step": 11050
|
|
},
|
|
{
|
|
"entropy": 5.593333196640015,
|
|
"epoch": 0.8601439408675355,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004931332391512597,
|
|
"loss": 5.4967,
|
|
"mean_token_accuracy": 0.16020538061857223,
|
|
"num_tokens": 19181136.0,
|
|
"step": 11055
|
|
},
|
|
{
|
|
"entropy": 5.567076349258423,
|
|
"epoch": 0.860532970239253,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004931264425708897,
|
|
"loss": 5.4898,
|
|
"mean_token_accuracy": 0.15613535791635513,
|
|
"num_tokens": 19189389.0,
|
|
"step": 11060
|
|
},
|
|
{
|
|
"entropy": 5.629894351959228,
|
|
"epoch": 0.8609219996109706,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004931196426807983,
|
|
"loss": 5.462,
|
|
"mean_token_accuracy": 0.171858774125576,
|
|
"num_tokens": 19198315.0,
|
|
"step": 11065
|
|
},
|
|
{
|
|
"entropy": 5.690217018127441,
|
|
"epoch": 0.8613110289826882,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004931128394810884,
|
|
"loss": 5.4957,
|
|
"mean_token_accuracy": 0.1585194043815136,
|
|
"num_tokens": 19207234.0,
|
|
"step": 11070
|
|
},
|
|
{
|
|
"entropy": 5.594514226913452,
|
|
"epoch": 0.8617000583544058,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004931060329718634,
|
|
"loss": 5.4816,
|
|
"mean_token_accuracy": 0.15357260406017303,
|
|
"num_tokens": 19216552.0,
|
|
"step": 11075
|
|
},
|
|
{
|
|
"entropy": 5.605134344100952,
|
|
"epoch": 0.8620890877261234,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004930992231532265,
|
|
"loss": 5.4304,
|
|
"mean_token_accuracy": 0.15944818556308746,
|
|
"num_tokens": 19225237.0,
|
|
"step": 11080
|
|
},
|
|
{
|
|
"entropy": 5.532908391952515,
|
|
"epoch": 0.8624781170978408,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.000493092410025281,
|
|
"loss": 5.3591,
|
|
"mean_token_accuracy": 0.17342484295368193,
|
|
"num_tokens": 19233246.0,
|
|
"step": 11085
|
|
},
|
|
{
|
|
"entropy": 5.534931993484497,
|
|
"epoch": 0.8628671464695584,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004930855935881302,
|
|
"loss": 5.374,
|
|
"mean_token_accuracy": 0.16980006992816926,
|
|
"num_tokens": 19241748.0,
|
|
"step": 11090
|
|
},
|
|
{
|
|
"entropy": 5.624445199966431,
|
|
"epoch": 0.863256175841276,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004930787738418777,
|
|
"loss": 5.5339,
|
|
"mean_token_accuracy": 0.16268638968467714,
|
|
"num_tokens": 19250259.0,
|
|
"step": 11095
|
|
},
|
|
{
|
|
"entropy": 5.631997871398926,
|
|
"epoch": 0.8636452052129936,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.0004930719507866269,
|
|
"loss": 5.607,
|
|
"mean_token_accuracy": 0.16095600426197051,
|
|
"num_tokens": 19259266.0,
|
|
"step": 11100
|
|
},
|
|
{
|
|
"entropy": 5.629003381729126,
|
|
"epoch": 0.8640342345847112,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004930651244224814,
|
|
"loss": 5.4365,
|
|
"mean_token_accuracy": 0.16444171816110612,
|
|
"num_tokens": 19268099.0,
|
|
"step": 11105
|
|
},
|
|
{
|
|
"entropy": 5.575818014144898,
|
|
"epoch": 0.8644232639564287,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004930582947495448,
|
|
"loss": 5.3094,
|
|
"mean_token_accuracy": 0.17518702149391174,
|
|
"num_tokens": 19276894.0,
|
|
"step": 11110
|
|
},
|
|
{
|
|
"entropy": 5.506184387207031,
|
|
"epoch": 0.8648122933281462,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004930514617679206,
|
|
"loss": 5.4067,
|
|
"mean_token_accuracy": 0.16996466964483262,
|
|
"num_tokens": 19285724.0,
|
|
"step": 11115
|
|
},
|
|
{
|
|
"entropy": 5.595422697067261,
|
|
"epoch": 0.8652013226998638,
|
|
"grad_norm": 2.53125,
|
|
"learning_rate": 0.0004930446254777125,
|
|
"loss": 5.3213,
|
|
"mean_token_accuracy": 0.17358873635530472,
|
|
"num_tokens": 19294468.0,
|
|
"step": 11120
|
|
},
|
|
{
|
|
"entropy": 5.595965957641601,
|
|
"epoch": 0.8655903520715814,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004930377858790242,
|
|
"loss": 5.3934,
|
|
"mean_token_accuracy": 0.16887759119272233,
|
|
"num_tokens": 19303575.0,
|
|
"step": 11125
|
|
},
|
|
{
|
|
"entropy": 5.632161092758179,
|
|
"epoch": 0.865979381443299,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004930309429719595,
|
|
"loss": 5.5483,
|
|
"mean_token_accuracy": 0.1665432259440422,
|
|
"num_tokens": 19312778.0,
|
|
"step": 11130
|
|
},
|
|
{
|
|
"entropy": 5.628087949752808,
|
|
"epoch": 0.8663684108150166,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004930240967566224,
|
|
"loss": 5.4051,
|
|
"mean_token_accuracy": 0.16356466412544252,
|
|
"num_tokens": 19320725.0,
|
|
"step": 11135
|
|
},
|
|
{
|
|
"entropy": 5.617732286453247,
|
|
"epoch": 0.8667574401867341,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004930172472331167,
|
|
"loss": 5.4315,
|
|
"mean_token_accuracy": 0.17228960543870925,
|
|
"num_tokens": 19329842.0,
|
|
"step": 11140
|
|
},
|
|
{
|
|
"entropy": 5.508480453491211,
|
|
"epoch": 0.8671464695584516,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004930103944015463,
|
|
"loss": 5.4311,
|
|
"mean_token_accuracy": 0.1688416540622711,
|
|
"num_tokens": 19338136.0,
|
|
"step": 11145
|
|
},
|
|
{
|
|
"entropy": 5.53710036277771,
|
|
"epoch": 0.8675354989301692,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004930035382620149,
|
|
"loss": 5.3925,
|
|
"mean_token_accuracy": 0.1666646420955658,
|
|
"num_tokens": 19346597.0,
|
|
"step": 11150
|
|
},
|
|
{
|
|
"entropy": 5.604273986816406,
|
|
"epoch": 0.8679245283018868,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.000492996678814627,
|
|
"loss": 5.3847,
|
|
"mean_token_accuracy": 0.16759981960058212,
|
|
"num_tokens": 19355595.0,
|
|
"step": 11155
|
|
},
|
|
{
|
|
"entropy": 5.591334676742553,
|
|
"epoch": 0.8683135576736044,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004929898160594865,
|
|
"loss": 5.4532,
|
|
"mean_token_accuracy": 0.17089799791574478,
|
|
"num_tokens": 19364133.0,
|
|
"step": 11160
|
|
},
|
|
{
|
|
"entropy": 5.59797625541687,
|
|
"epoch": 0.8687025870453219,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004929829499966974,
|
|
"loss": 5.5101,
|
|
"mean_token_accuracy": 0.15949829816818237,
|
|
"num_tokens": 19373628.0,
|
|
"step": 11165
|
|
},
|
|
{
|
|
"entropy": 5.588370513916016,
|
|
"epoch": 0.8690916164170395,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004929760806263641,
|
|
"loss": 5.4369,
|
|
"mean_token_accuracy": 0.16313839703798294,
|
|
"num_tokens": 19381901.0,
|
|
"step": 11170
|
|
},
|
|
{
|
|
"entropy": 5.536091613769531,
|
|
"epoch": 0.8694806457887571,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004929692079485906,
|
|
"loss": 5.527,
|
|
"mean_token_accuracy": 0.1661791443824768,
|
|
"num_tokens": 19390390.0,
|
|
"step": 11175
|
|
},
|
|
{
|
|
"entropy": 5.6095479965209964,
|
|
"epoch": 0.8698696751604746,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004929623319634814,
|
|
"loss": 5.4858,
|
|
"mean_token_accuracy": 0.1574648216366768,
|
|
"num_tokens": 19399858.0,
|
|
"step": 11180
|
|
},
|
|
{
|
|
"entropy": 5.576297378540039,
|
|
"epoch": 0.8702587045321922,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004929554526711407,
|
|
"loss": 5.4277,
|
|
"mean_token_accuracy": 0.16378122717142105,
|
|
"num_tokens": 19409062.0,
|
|
"step": 11185
|
|
},
|
|
{
|
|
"entropy": 5.563224458694458,
|
|
"epoch": 0.8706477339039097,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004929485700716729,
|
|
"loss": 5.4028,
|
|
"mean_token_accuracy": 0.1680426374077797,
|
|
"num_tokens": 19417228.0,
|
|
"step": 11190
|
|
},
|
|
{
|
|
"entropy": 5.610040950775146,
|
|
"epoch": 0.8710367632756273,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004929416841651824,
|
|
"loss": 5.509,
|
|
"mean_token_accuracy": 0.1611345425248146,
|
|
"num_tokens": 19426086.0,
|
|
"step": 11195
|
|
},
|
|
{
|
|
"entropy": 5.659562110900879,
|
|
"epoch": 0.8714257926473449,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004929347949517739,
|
|
"loss": 5.5053,
|
|
"mean_token_accuracy": 0.1610720545053482,
|
|
"num_tokens": 19435363.0,
|
|
"step": 11200
|
|
},
|
|
{
|
|
"entropy": 5.569135046005249,
|
|
"epoch": 0.8718148220190625,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004929279024315516,
|
|
"loss": 5.305,
|
|
"mean_token_accuracy": 0.17181036323308946,
|
|
"num_tokens": 19443355.0,
|
|
"step": 11205
|
|
},
|
|
{
|
|
"entropy": 5.524402189254761,
|
|
"epoch": 0.87220385139078,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004929210066046204,
|
|
"loss": 5.3494,
|
|
"mean_token_accuracy": 0.16735538244247436,
|
|
"num_tokens": 19452217.0,
|
|
"step": 11210
|
|
},
|
|
{
|
|
"entropy": 5.613103628158569,
|
|
"epoch": 0.8725928807624975,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004929141074710847,
|
|
"loss": 5.5384,
|
|
"mean_token_accuracy": 0.156987027823925,
|
|
"num_tokens": 19460034.0,
|
|
"step": 11215
|
|
},
|
|
{
|
|
"entropy": 5.593009805679321,
|
|
"epoch": 0.8729819101342151,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004929072050310491,
|
|
"loss": 5.4874,
|
|
"mean_token_accuracy": 0.1655286356806755,
|
|
"num_tokens": 19468403.0,
|
|
"step": 11220
|
|
},
|
|
{
|
|
"entropy": 5.5963386535644535,
|
|
"epoch": 0.8733709395059327,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004929002992846188,
|
|
"loss": 5.5069,
|
|
"mean_token_accuracy": 0.16459607928991318,
|
|
"num_tokens": 19477551.0,
|
|
"step": 11225
|
|
},
|
|
{
|
|
"entropy": 5.642898416519165,
|
|
"epoch": 0.8737599688776503,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004928933902318981,
|
|
"loss": 5.4011,
|
|
"mean_token_accuracy": 0.16497209072113037,
|
|
"num_tokens": 19486131.0,
|
|
"step": 11230
|
|
},
|
|
{
|
|
"entropy": 5.639529895782471,
|
|
"epoch": 0.8741489982493679,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.000492886477872992,
|
|
"loss": 5.5351,
|
|
"mean_token_accuracy": 0.15575776249170303,
|
|
"num_tokens": 19496212.0,
|
|
"step": 11235
|
|
},
|
|
{
|
|
"entropy": 5.561580181121826,
|
|
"epoch": 0.8745380276210853,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004928795622080054,
|
|
"loss": 5.372,
|
|
"mean_token_accuracy": 0.1667099341750145,
|
|
"num_tokens": 19504556.0,
|
|
"step": 11240
|
|
},
|
|
{
|
|
"entropy": 5.589718866348266,
|
|
"epoch": 0.8749270569928029,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004928726432370434,
|
|
"loss": 5.4418,
|
|
"mean_token_accuracy": 0.1647622615098953,
|
|
"num_tokens": 19512832.0,
|
|
"step": 11245
|
|
},
|
|
{
|
|
"entropy": 5.621614551544189,
|
|
"epoch": 0.8753160863645205,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004928657209602107,
|
|
"loss": 5.4634,
|
|
"mean_token_accuracy": 0.16495981961488723,
|
|
"num_tokens": 19521410.0,
|
|
"step": 11250
|
|
},
|
|
{
|
|
"entropy": 5.576944732666016,
|
|
"epoch": 0.8757051157362381,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004928587953776125,
|
|
"loss": 5.4316,
|
|
"mean_token_accuracy": 0.16559310704469682,
|
|
"num_tokens": 19529935.0,
|
|
"step": 11255
|
|
},
|
|
{
|
|
"entropy": 5.463144540786743,
|
|
"epoch": 0.8760941451079557,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004928518664893538,
|
|
"loss": 5.3266,
|
|
"mean_token_accuracy": 0.17452301383018493,
|
|
"num_tokens": 19538330.0,
|
|
"step": 11260
|
|
},
|
|
{
|
|
"entropy": 5.523600101470947,
|
|
"epoch": 0.8764831744796732,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004928449342955397,
|
|
"loss": 5.3399,
|
|
"mean_token_accuracy": 0.16870104670524597,
|
|
"num_tokens": 19546860.0,
|
|
"step": 11265
|
|
},
|
|
{
|
|
"entropy": 5.629951238632202,
|
|
"epoch": 0.8768722038513908,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004928379987962756,
|
|
"loss": 5.4226,
|
|
"mean_token_accuracy": 0.16777731627225875,
|
|
"num_tokens": 19554945.0,
|
|
"step": 11270
|
|
},
|
|
{
|
|
"entropy": 5.602519750595093,
|
|
"epoch": 0.8772612332231083,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004928310599916666,
|
|
"loss": 5.4509,
|
|
"mean_token_accuracy": 0.16262111216783523,
|
|
"num_tokens": 19563182.0,
|
|
"step": 11275
|
|
},
|
|
{
|
|
"entropy": 5.526263952255249,
|
|
"epoch": 0.8776502625948259,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004928241178818178,
|
|
"loss": 5.4305,
|
|
"mean_token_accuracy": 0.16654721945524215,
|
|
"num_tokens": 19571405.0,
|
|
"step": 11280
|
|
},
|
|
{
|
|
"entropy": 5.725631141662598,
|
|
"epoch": 0.8780392919665435,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004928171724668349,
|
|
"loss": 5.5185,
|
|
"mean_token_accuracy": 0.16668618023395537,
|
|
"num_tokens": 19580053.0,
|
|
"step": 11285
|
|
},
|
|
{
|
|
"entropy": 5.691386985778808,
|
|
"epoch": 0.878428321338261,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004928102237468229,
|
|
"loss": 5.5353,
|
|
"mean_token_accuracy": 0.16114630401134492,
|
|
"num_tokens": 19588457.0,
|
|
"step": 11290
|
|
},
|
|
{
|
|
"entropy": 5.520010614395142,
|
|
"epoch": 0.8788173507099786,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004928032717218876,
|
|
"loss": 5.3756,
|
|
"mean_token_accuracy": 0.16722139418125154,
|
|
"num_tokens": 19597608.0,
|
|
"step": 11295
|
|
},
|
|
{
|
|
"entropy": 5.5498902797698975,
|
|
"epoch": 0.8792063800816962,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004927963163921343,
|
|
"loss": 5.3957,
|
|
"mean_token_accuracy": 0.17279530167579651,
|
|
"num_tokens": 19605904.0,
|
|
"step": 11300
|
|
},
|
|
{
|
|
"entropy": 5.604985475540161,
|
|
"epoch": 0.8795954094534137,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004927893577576685,
|
|
"loss": 5.3813,
|
|
"mean_token_accuracy": 0.16346621215343476,
|
|
"num_tokens": 19614660.0,
|
|
"step": 11305
|
|
},
|
|
{
|
|
"entropy": 5.506232166290284,
|
|
"epoch": 0.8799844388251313,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004927823958185959,
|
|
"loss": 5.3655,
|
|
"mean_token_accuracy": 0.17348123341798782,
|
|
"num_tokens": 19623210.0,
|
|
"step": 11310
|
|
},
|
|
{
|
|
"entropy": 5.561007976531982,
|
|
"epoch": 0.8803734681968488,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.000492775430575022,
|
|
"loss": 5.4444,
|
|
"mean_token_accuracy": 0.16233074367046357,
|
|
"num_tokens": 19631747.0,
|
|
"step": 11315
|
|
},
|
|
{
|
|
"entropy": 5.64417781829834,
|
|
"epoch": 0.8807624975685664,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004927684620270527,
|
|
"loss": 5.5251,
|
|
"mean_token_accuracy": 0.15691719055175782,
|
|
"num_tokens": 19639902.0,
|
|
"step": 11320
|
|
},
|
|
{
|
|
"entropy": 5.673055934906006,
|
|
"epoch": 0.881151526940284,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004927614901747935,
|
|
"loss": 5.5495,
|
|
"mean_token_accuracy": 0.15953097343444825,
|
|
"num_tokens": 19648478.0,
|
|
"step": 11325
|
|
},
|
|
{
|
|
"entropy": 5.701460456848144,
|
|
"epoch": 0.8815405563120016,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004927545150183503,
|
|
"loss": 5.5502,
|
|
"mean_token_accuracy": 0.16400340497493743,
|
|
"num_tokens": 19657467.0,
|
|
"step": 11330
|
|
},
|
|
{
|
|
"entropy": 5.691887903213501,
|
|
"epoch": 0.8819295856837192,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.000492747536557829,
|
|
"loss": 5.5182,
|
|
"mean_token_accuracy": 0.1579813688993454,
|
|
"num_tokens": 19665382.0,
|
|
"step": 11335
|
|
},
|
|
{
|
|
"entropy": 5.561461162567139,
|
|
"epoch": 0.8823186150554367,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004927405547933353,
|
|
"loss": 5.3391,
|
|
"mean_token_accuracy": 0.16862319111824037,
|
|
"num_tokens": 19674486.0,
|
|
"step": 11340
|
|
},
|
|
{
|
|
"entropy": 5.607643938064575,
|
|
"epoch": 0.8827076444271542,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004927335697249753,
|
|
"loss": 5.3618,
|
|
"mean_token_accuracy": 0.16630233973264694,
|
|
"num_tokens": 19683060.0,
|
|
"step": 11345
|
|
},
|
|
{
|
|
"entropy": 5.49778938293457,
|
|
"epoch": 0.8830966737988718,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004927265813528549,
|
|
"loss": 5.3447,
|
|
"mean_token_accuracy": 0.1723550483584404,
|
|
"num_tokens": 19691634.0,
|
|
"step": 11350
|
|
},
|
|
{
|
|
"entropy": 5.5745201587677,
|
|
"epoch": 0.8834857031705894,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004927195896770804,
|
|
"loss": 5.43,
|
|
"mean_token_accuracy": 0.1592835769057274,
|
|
"num_tokens": 19699975.0,
|
|
"step": 11355
|
|
},
|
|
{
|
|
"entropy": 5.609763813018799,
|
|
"epoch": 0.883874732542307,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004927125946977574,
|
|
"loss": 5.3904,
|
|
"mean_token_accuracy": 0.16351550817489624,
|
|
"num_tokens": 19708431.0,
|
|
"step": 11360
|
|
},
|
|
{
|
|
"entropy": 5.54373517036438,
|
|
"epoch": 0.8842637619140246,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004927055964149923,
|
|
"loss": 5.4088,
|
|
"mean_token_accuracy": 0.16205148696899413,
|
|
"num_tokens": 19717189.0,
|
|
"step": 11365
|
|
},
|
|
{
|
|
"entropy": 5.623295307159424,
|
|
"epoch": 0.884652791285742,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004926985948288914,
|
|
"loss": 5.4746,
|
|
"mean_token_accuracy": 0.1615665078163147,
|
|
"num_tokens": 19725855.0,
|
|
"step": 11370
|
|
},
|
|
{
|
|
"entropy": 5.572314357757568,
|
|
"epoch": 0.8850418206574596,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004926915899395608,
|
|
"loss": 5.373,
|
|
"mean_token_accuracy": 0.1688873991370201,
|
|
"num_tokens": 19734617.0,
|
|
"step": 11375
|
|
},
|
|
{
|
|
"entropy": 5.653919458389282,
|
|
"epoch": 0.8854308500291772,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004926845817471068,
|
|
"loss": 5.5065,
|
|
"mean_token_accuracy": 0.16308294236660004,
|
|
"num_tokens": 19743731.0,
|
|
"step": 11380
|
|
},
|
|
{
|
|
"entropy": 5.674256706237793,
|
|
"epoch": 0.8858198794008948,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004926775702516358,
|
|
"loss": 5.4546,
|
|
"mean_token_accuracy": 0.16395652443170547,
|
|
"num_tokens": 19752336.0,
|
|
"step": 11385
|
|
},
|
|
{
|
|
"entropy": 5.597683382034302,
|
|
"epoch": 0.8862089087726124,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004926705554532541,
|
|
"loss": 5.4435,
|
|
"mean_token_accuracy": 0.16464806348085403,
|
|
"num_tokens": 19761488.0,
|
|
"step": 11390
|
|
},
|
|
{
|
|
"entropy": 5.5336109638214115,
|
|
"epoch": 0.8865979381443299,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004926635373520682,
|
|
"loss": 5.3615,
|
|
"mean_token_accuracy": 0.16801237165927888,
|
|
"num_tokens": 19770330.0,
|
|
"step": 11395
|
|
},
|
|
{
|
|
"entropy": 5.606996393203735,
|
|
"epoch": 0.8869869675160474,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004926565159481845,
|
|
"loss": 5.4215,
|
|
"mean_token_accuracy": 0.1609994277358055,
|
|
"num_tokens": 19779037.0,
|
|
"step": 11400
|
|
},
|
|
{
|
|
"entropy": 5.6447957992553714,
|
|
"epoch": 0.887375996887765,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004926494912417097,
|
|
"loss": 5.4884,
|
|
"mean_token_accuracy": 0.16048842221498488,
|
|
"num_tokens": 19787661.0,
|
|
"step": 11405
|
|
},
|
|
{
|
|
"entropy": 5.582346391677857,
|
|
"epoch": 0.8877650262594826,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004926424632327503,
|
|
"loss": 5.3951,
|
|
"mean_token_accuracy": 0.16768926084041597,
|
|
"num_tokens": 19796421.0,
|
|
"step": 11410
|
|
},
|
|
{
|
|
"entropy": 5.584974193572998,
|
|
"epoch": 0.8881540556312002,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004926354319214129,
|
|
"loss": 5.3981,
|
|
"mean_token_accuracy": 0.16604495644569398,
|
|
"num_tokens": 19805842.0,
|
|
"step": 11415
|
|
},
|
|
{
|
|
"entropy": 5.655823516845703,
|
|
"epoch": 0.8885430850029177,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004926283973078041,
|
|
"loss": 5.4218,
|
|
"mean_token_accuracy": 0.16787973940372466,
|
|
"num_tokens": 19814179.0,
|
|
"step": 11420
|
|
},
|
|
{
|
|
"entropy": 5.613330984115601,
|
|
"epoch": 0.8889321143746353,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004926213593920309,
|
|
"loss": 5.4923,
|
|
"mean_token_accuracy": 0.16426144540309906,
|
|
"num_tokens": 19822435.0,
|
|
"step": 11425
|
|
},
|
|
{
|
|
"entropy": 5.588300609588623,
|
|
"epoch": 0.8893211437463528,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004926143181742,
|
|
"loss": 5.4055,
|
|
"mean_token_accuracy": 0.1616242453455925,
|
|
"num_tokens": 19830300.0,
|
|
"step": 11430
|
|
},
|
|
{
|
|
"entropy": 5.58564510345459,
|
|
"epoch": 0.8897101731180704,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004926072736544181,
|
|
"loss": 5.5159,
|
|
"mean_token_accuracy": 0.16276822090148926,
|
|
"num_tokens": 19839264.0,
|
|
"step": 11435
|
|
},
|
|
{
|
|
"entropy": 5.621684646606445,
|
|
"epoch": 0.890099202489788,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004926002258327922,
|
|
"loss": 5.4597,
|
|
"mean_token_accuracy": 0.16228195577859877,
|
|
"num_tokens": 19848086.0,
|
|
"step": 11440
|
|
},
|
|
{
|
|
"entropy": 5.6392816543579105,
|
|
"epoch": 0.8904882318615055,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004925931747094292,
|
|
"loss": 5.4315,
|
|
"mean_token_accuracy": 0.15673258900642395,
|
|
"num_tokens": 19856571.0,
|
|
"step": 11445
|
|
},
|
|
{
|
|
"entropy": 5.5869261741638185,
|
|
"epoch": 0.8908772612332231,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004925861202844361,
|
|
"loss": 5.4554,
|
|
"mean_token_accuracy": 0.16131344437599182,
|
|
"num_tokens": 19865272.0,
|
|
"step": 11450
|
|
},
|
|
{
|
|
"entropy": 5.5566261291503904,
|
|
"epoch": 0.8912662906049407,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.00049257906255792,
|
|
"loss": 5.4055,
|
|
"mean_token_accuracy": 0.1614033855497837,
|
|
"num_tokens": 19874307.0,
|
|
"step": 11455
|
|
},
|
|
{
|
|
"entropy": 5.58982629776001,
|
|
"epoch": 0.8916553199766583,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.000492572001529988,
|
|
"loss": 5.4526,
|
|
"mean_token_accuracy": 0.16618746519088745,
|
|
"num_tokens": 19882851.0,
|
|
"step": 11460
|
|
},
|
|
{
|
|
"entropy": 5.654384803771973,
|
|
"epoch": 0.8920443493483758,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004925649372007469,
|
|
"loss": 5.3495,
|
|
"mean_token_accuracy": 0.1758921191096306,
|
|
"num_tokens": 19891276.0,
|
|
"step": 11465
|
|
},
|
|
{
|
|
"entropy": 5.620083808898926,
|
|
"epoch": 0.8924333787200933,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004925578695703045,
|
|
"loss": 5.4917,
|
|
"mean_token_accuracy": 0.15829311907291413,
|
|
"num_tokens": 19900551.0,
|
|
"step": 11470
|
|
},
|
|
{
|
|
"entropy": 5.639655208587646,
|
|
"epoch": 0.8928224080918109,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004925507986387676,
|
|
"loss": 5.5149,
|
|
"mean_token_accuracy": 0.16138267070055007,
|
|
"num_tokens": 19909412.0,
|
|
"step": 11475
|
|
},
|
|
{
|
|
"entropy": 5.615196323394775,
|
|
"epoch": 0.8932114374635285,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004925437244062436,
|
|
"loss": 5.3594,
|
|
"mean_token_accuracy": 0.16976200491189958,
|
|
"num_tokens": 19918073.0,
|
|
"step": 11480
|
|
},
|
|
{
|
|
"entropy": 5.482284116744995,
|
|
"epoch": 0.8936004668352461,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004925366468728397,
|
|
"loss": 5.3073,
|
|
"mean_token_accuracy": 0.1825845032930374,
|
|
"num_tokens": 19926040.0,
|
|
"step": 11485
|
|
},
|
|
{
|
|
"entropy": 5.53025107383728,
|
|
"epoch": 0.8939894962069637,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004925295660386635,
|
|
"loss": 5.4712,
|
|
"mean_token_accuracy": 0.16550873219966888,
|
|
"num_tokens": 19934543.0,
|
|
"step": 11490
|
|
},
|
|
{
|
|
"entropy": 5.575025939941407,
|
|
"epoch": 0.8943785255786811,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004925224819038224,
|
|
"loss": 5.4113,
|
|
"mean_token_accuracy": 0.1682252526283264,
|
|
"num_tokens": 19943198.0,
|
|
"step": 11495
|
|
},
|
|
{
|
|
"entropy": 5.554923725128174,
|
|
"epoch": 0.8947675549503987,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004925153944684239,
|
|
"loss": 5.3523,
|
|
"mean_token_accuracy": 0.17520031929016114,
|
|
"num_tokens": 19952319.0,
|
|
"step": 11500
|
|
},
|
|
{
|
|
"entropy": 5.547123098373413,
|
|
"epoch": 0.8951565843221163,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004925083037325754,
|
|
"loss": 5.3438,
|
|
"mean_token_accuracy": 0.16900049149990082,
|
|
"num_tokens": 19961982.0,
|
|
"step": 11505
|
|
},
|
|
{
|
|
"entropy": 5.5912707328796385,
|
|
"epoch": 0.8955456136938339,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004925012096963847,
|
|
"loss": 5.3775,
|
|
"mean_token_accuracy": 0.16102658361196517,
|
|
"num_tokens": 19971055.0,
|
|
"step": 11510
|
|
},
|
|
{
|
|
"entropy": 5.426222467422486,
|
|
"epoch": 0.8959346430655515,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004924941123599593,
|
|
"loss": 5.2642,
|
|
"mean_token_accuracy": 0.1792299598455429,
|
|
"num_tokens": 19979850.0,
|
|
"step": 11515
|
|
},
|
|
{
|
|
"entropy": 5.569857549667359,
|
|
"epoch": 0.896323672437269,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004924870117234069,
|
|
"loss": 5.4525,
|
|
"mean_token_accuracy": 0.16205697506666183,
|
|
"num_tokens": 19989261.0,
|
|
"step": 11520
|
|
},
|
|
{
|
|
"entropy": 5.60758605003357,
|
|
"epoch": 0.8967127018089865,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004924799077868353,
|
|
"loss": 5.3745,
|
|
"mean_token_accuracy": 0.16446672976017,
|
|
"num_tokens": 19998321.0,
|
|
"step": 11525
|
|
},
|
|
{
|
|
"entropy": 5.539510774612427,
|
|
"epoch": 0.8971017311807041,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004924728005503522,
|
|
"loss": 5.4442,
|
|
"mean_token_accuracy": 0.16351263523101806,
|
|
"num_tokens": 20007191.0,
|
|
"step": 11530
|
|
},
|
|
{
|
|
"entropy": 5.566989707946777,
|
|
"epoch": 0.8974907605524217,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004924656900140655,
|
|
"loss": 5.4821,
|
|
"mean_token_accuracy": 0.16563700139522552,
|
|
"num_tokens": 20015805.0,
|
|
"step": 11535
|
|
},
|
|
{
|
|
"entropy": 5.563309526443481,
|
|
"epoch": 0.8978797899241393,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004924585761780831,
|
|
"loss": 5.4314,
|
|
"mean_token_accuracy": 0.1693728670477867,
|
|
"num_tokens": 20024861.0,
|
|
"step": 11540
|
|
},
|
|
{
|
|
"entropy": 5.718994665145874,
|
|
"epoch": 0.8982688192958569,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.000492451459042513,
|
|
"loss": 5.5048,
|
|
"mean_token_accuracy": 0.16540486142039298,
|
|
"num_tokens": 20034208.0,
|
|
"step": 11545
|
|
},
|
|
{
|
|
"entropy": 5.63351469039917,
|
|
"epoch": 0.8986578486675744,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.000492444338607463,
|
|
"loss": 5.4469,
|
|
"mean_token_accuracy": 0.16422081738710403,
|
|
"num_tokens": 20042786.0,
|
|
"step": 11550
|
|
},
|
|
{
|
|
"entropy": 5.641626787185669,
|
|
"epoch": 0.899046878039292,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004924372148730413,
|
|
"loss": 5.5006,
|
|
"mean_token_accuracy": 0.1618044413626194,
|
|
"num_tokens": 20051697.0,
|
|
"step": 11555
|
|
},
|
|
{
|
|
"entropy": 5.640315103530884,
|
|
"epoch": 0.8994359074110095,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.000492430087839356,
|
|
"loss": 5.4725,
|
|
"mean_token_accuracy": 0.1687396615743637,
|
|
"num_tokens": 20059814.0,
|
|
"step": 11560
|
|
},
|
|
{
|
|
"entropy": 5.575307369232178,
|
|
"epoch": 0.8998249367827271,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004924229575065152,
|
|
"loss": 5.4575,
|
|
"mean_token_accuracy": 0.16698689609766007,
|
|
"num_tokens": 20068329.0,
|
|
"step": 11565
|
|
},
|
|
{
|
|
"entropy": 5.614092016220093,
|
|
"epoch": 0.9002139661544447,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.000492415823874627,
|
|
"loss": 5.4582,
|
|
"mean_token_accuracy": 0.1686816081404686,
|
|
"num_tokens": 20076925.0,
|
|
"step": 11570
|
|
},
|
|
{
|
|
"entropy": 5.618636560440064,
|
|
"epoch": 0.9006029955261622,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004924086869437998,
|
|
"loss": 5.477,
|
|
"mean_token_accuracy": 0.15615838915109634,
|
|
"num_tokens": 20085248.0,
|
|
"step": 11575
|
|
},
|
|
{
|
|
"entropy": 5.653695392608642,
|
|
"epoch": 0.9009920248978798,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004924015467141417,
|
|
"loss": 5.4472,
|
|
"mean_token_accuracy": 0.16372430920600892,
|
|
"num_tokens": 20093929.0,
|
|
"step": 11580
|
|
},
|
|
{
|
|
"entropy": 5.575537443161011,
|
|
"epoch": 0.9013810542695974,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004923944031857613,
|
|
"loss": 5.5273,
|
|
"mean_token_accuracy": 0.1625973328948021,
|
|
"num_tokens": 20103141.0,
|
|
"step": 11585
|
|
},
|
|
{
|
|
"entropy": 5.583071327209472,
|
|
"epoch": 0.901770083641315,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004923872563587668,
|
|
"loss": 5.3516,
|
|
"mean_token_accuracy": 0.17516722828149794,
|
|
"num_tokens": 20111938.0,
|
|
"step": 11590
|
|
},
|
|
{
|
|
"entropy": 5.563779306411743,
|
|
"epoch": 0.9021591130130325,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004923801062332666,
|
|
"loss": 5.3575,
|
|
"mean_token_accuracy": 0.17270515710115433,
|
|
"num_tokens": 20120795.0,
|
|
"step": 11595
|
|
},
|
|
{
|
|
"entropy": 5.5637914657592775,
|
|
"epoch": 0.90254814238475,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004923729528093694,
|
|
"loss": 5.4399,
|
|
"mean_token_accuracy": 0.1667784184217453,
|
|
"num_tokens": 20129816.0,
|
|
"step": 11600
|
|
},
|
|
{
|
|
"entropy": 5.681299018859863,
|
|
"epoch": 0.9029371717564676,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004923657960871836,
|
|
"loss": 5.5512,
|
|
"mean_token_accuracy": 0.15675133019685744,
|
|
"num_tokens": 20138380.0,
|
|
"step": 11605
|
|
},
|
|
{
|
|
"entropy": 5.657552194595337,
|
|
"epoch": 0.9033262011281852,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004923586360668178,
|
|
"loss": 5.5556,
|
|
"mean_token_accuracy": 0.16022806912660598,
|
|
"num_tokens": 20147201.0,
|
|
"step": 11610
|
|
},
|
|
{
|
|
"entropy": 5.5744353294372555,
|
|
"epoch": 0.9037152304999028,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004923514727483807,
|
|
"loss": 5.3958,
|
|
"mean_token_accuracy": 0.16239219754934311,
|
|
"num_tokens": 20156744.0,
|
|
"step": 11615
|
|
},
|
|
{
|
|
"entropy": 5.643081378936768,
|
|
"epoch": 0.9041042598716204,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.000492344306131981,
|
|
"loss": 5.4098,
|
|
"mean_token_accuracy": 0.168283312022686,
|
|
"num_tokens": 20165081.0,
|
|
"step": 11620
|
|
},
|
|
{
|
|
"entropy": 5.673436975479126,
|
|
"epoch": 0.9044932892433378,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004923371362177272,
|
|
"loss": 5.4099,
|
|
"mean_token_accuracy": 0.16650529354810714,
|
|
"num_tokens": 20172893.0,
|
|
"step": 11625
|
|
},
|
|
{
|
|
"entropy": 5.595490980148315,
|
|
"epoch": 0.9048823186150554,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004923299630057284,
|
|
"loss": 5.4815,
|
|
"mean_token_accuracy": 0.16391136050224303,
|
|
"num_tokens": 20181351.0,
|
|
"step": 11630
|
|
},
|
|
{
|
|
"entropy": 5.583002185821533,
|
|
"epoch": 0.905271347986773,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004923227864960934,
|
|
"loss": 5.4898,
|
|
"mean_token_accuracy": 0.15725645869970323,
|
|
"num_tokens": 20189650.0,
|
|
"step": 11635
|
|
},
|
|
{
|
|
"entropy": 5.686719799041748,
|
|
"epoch": 0.9056603773584906,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.000492315606688931,
|
|
"loss": 5.4394,
|
|
"mean_token_accuracy": 0.15606636852025985,
|
|
"num_tokens": 20198184.0,
|
|
"step": 11640
|
|
},
|
|
{
|
|
"entropy": 5.691554021835327,
|
|
"epoch": 0.9060494067302082,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.0004923084235843501,
|
|
"loss": 5.3587,
|
|
"mean_token_accuracy": 0.172410349547863,
|
|
"num_tokens": 20206357.0,
|
|
"step": 11645
|
|
},
|
|
{
|
|
"entropy": 5.539533615112305,
|
|
"epoch": 0.9064384361019256,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004923012371824598,
|
|
"loss": 5.4629,
|
|
"mean_token_accuracy": 0.17097723335027695,
|
|
"num_tokens": 20214384.0,
|
|
"step": 11650
|
|
},
|
|
{
|
|
"entropy": 5.616372919082641,
|
|
"epoch": 0.9068274654736432,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.000492294047483369,
|
|
"loss": 5.4746,
|
|
"mean_token_accuracy": 0.16025118231773378,
|
|
"num_tokens": 20224103.0,
|
|
"step": 11655
|
|
},
|
|
{
|
|
"entropy": 5.634894609451294,
|
|
"epoch": 0.9072164948453608,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.0004922868544871869,
|
|
"loss": 5.4794,
|
|
"mean_token_accuracy": 0.165157687664032,
|
|
"num_tokens": 20233414.0,
|
|
"step": 11660
|
|
},
|
|
{
|
|
"entropy": 5.620892858505249,
|
|
"epoch": 0.9076055242170784,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004922796581940227,
|
|
"loss": 5.3324,
|
|
"mean_token_accuracy": 0.17546915560960769,
|
|
"num_tokens": 20240988.0,
|
|
"step": 11665
|
|
},
|
|
{
|
|
"entropy": 5.528362703323364,
|
|
"epoch": 0.907994553588796,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004922724586039855,
|
|
"loss": 5.3643,
|
|
"mean_token_accuracy": 0.1678197294473648,
|
|
"num_tokens": 20250066.0,
|
|
"step": 11670
|
|
},
|
|
{
|
|
"entropy": 5.513184261322022,
|
|
"epoch": 0.9083835829605135,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004922652557171846,
|
|
"loss": 5.3023,
|
|
"mean_token_accuracy": 0.17026133388280867,
|
|
"num_tokens": 20258435.0,
|
|
"step": 11675
|
|
},
|
|
{
|
|
"entropy": 5.593416833877564,
|
|
"epoch": 0.9087726123322311,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004922580495337292,
|
|
"loss": 5.4836,
|
|
"mean_token_accuracy": 0.1679489091038704,
|
|
"num_tokens": 20267345.0,
|
|
"step": 11680
|
|
},
|
|
{
|
|
"entropy": 5.65469651222229,
|
|
"epoch": 0.9091616417039486,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004922508400537288,
|
|
"loss": 5.5081,
|
|
"mean_token_accuracy": 0.16376658529043198,
|
|
"num_tokens": 20275644.0,
|
|
"step": 11685
|
|
},
|
|
{
|
|
"entropy": 5.640007209777832,
|
|
"epoch": 0.9095506710756662,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004922436272772926,
|
|
"loss": 5.476,
|
|
"mean_token_accuracy": 0.16782302558422088,
|
|
"num_tokens": 20284459.0,
|
|
"step": 11690
|
|
},
|
|
{
|
|
"entropy": 5.6208737850189205,
|
|
"epoch": 0.9099397004473838,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004922364112045301,
|
|
"loss": 5.3894,
|
|
"mean_token_accuracy": 0.1607832819223404,
|
|
"num_tokens": 20293088.0,
|
|
"step": 11695
|
|
},
|
|
{
|
|
"entropy": 5.504998254776001,
|
|
"epoch": 0.9103287298191013,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 0.000492229191835551,
|
|
"loss": 5.4,
|
|
"mean_token_accuracy": 0.16904088854789734,
|
|
"num_tokens": 20301811.0,
|
|
"step": 11700
|
|
},
|
|
{
|
|
"entropy": 5.640305519104004,
|
|
"epoch": 0.9107177591908189,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004922219691704645,
|
|
"loss": 5.5325,
|
|
"mean_token_accuracy": 0.15783090144395828,
|
|
"num_tokens": 20310365.0,
|
|
"step": 11705
|
|
},
|
|
{
|
|
"entropy": 5.680600500106811,
|
|
"epoch": 0.9111067885625365,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004922147432093805,
|
|
"loss": 5.4597,
|
|
"mean_token_accuracy": 0.1692796379327774,
|
|
"num_tokens": 20318891.0,
|
|
"step": 11710
|
|
},
|
|
{
|
|
"entropy": 5.569218397140503,
|
|
"epoch": 0.911495817934254,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004922075139524083,
|
|
"loss": 5.3474,
|
|
"mean_token_accuracy": 0.17611400932073593,
|
|
"num_tokens": 20327313.0,
|
|
"step": 11715
|
|
},
|
|
{
|
|
"entropy": 5.541305351257324,
|
|
"epoch": 0.9118848473059716,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 0.000492200281399658,
|
|
"loss": 5.3301,
|
|
"mean_token_accuracy": 0.17205900996923446,
|
|
"num_tokens": 20335511.0,
|
|
"step": 11720
|
|
},
|
|
{
|
|
"entropy": 5.546508932113648,
|
|
"epoch": 0.9122738766776891,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.000492193045551239,
|
|
"loss": 5.3346,
|
|
"mean_token_accuracy": 0.17597660124301912,
|
|
"num_tokens": 20343588.0,
|
|
"step": 11725
|
|
},
|
|
{
|
|
"entropy": 5.595340919494629,
|
|
"epoch": 0.9126629060494067,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004921858064072612,
|
|
"loss": 5.4424,
|
|
"mean_token_accuracy": 0.16616809666156768,
|
|
"num_tokens": 20352793.0,
|
|
"step": 11730
|
|
},
|
|
{
|
|
"entropy": 5.558742332458496,
|
|
"epoch": 0.9130519354211243,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004921785639678347,
|
|
"loss": 5.4892,
|
|
"mean_token_accuracy": 0.16771798133850097,
|
|
"num_tokens": 20362480.0,
|
|
"step": 11735
|
|
},
|
|
{
|
|
"entropy": 5.562952852249145,
|
|
"epoch": 0.9134409647928419,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.000492171318233069,
|
|
"loss": 5.363,
|
|
"mean_token_accuracy": 0.17176808118820192,
|
|
"num_tokens": 20371192.0,
|
|
"step": 11740
|
|
},
|
|
{
|
|
"entropy": 5.651773405075073,
|
|
"epoch": 0.9138299941645595,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004921640692030742,
|
|
"loss": 5.4804,
|
|
"mean_token_accuracy": 0.16320589035749436,
|
|
"num_tokens": 20379322.0,
|
|
"step": 11745
|
|
},
|
|
{
|
|
"entropy": 5.657601451873779,
|
|
"epoch": 0.914219023536277,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004921568168779603,
|
|
"loss": 5.4271,
|
|
"mean_token_accuracy": 0.1589912310242653,
|
|
"num_tokens": 20387976.0,
|
|
"step": 11750
|
|
},
|
|
{
|
|
"entropy": 5.621883726119995,
|
|
"epoch": 0.9146080529079945,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004921495612578374,
|
|
"loss": 5.5132,
|
|
"mean_token_accuracy": 0.1600305199623108,
|
|
"num_tokens": 20397398.0,
|
|
"step": 11755
|
|
},
|
|
{
|
|
"entropy": 5.622820043563843,
|
|
"epoch": 0.9149970822797121,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004921423023428156,
|
|
"loss": 5.424,
|
|
"mean_token_accuracy": 0.16491100639104844,
|
|
"num_tokens": 20406503.0,
|
|
"step": 11760
|
|
},
|
|
{
|
|
"entropy": 5.540057563781739,
|
|
"epoch": 0.9153861116514297,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004921350401330049,
|
|
"loss": 5.3406,
|
|
"mean_token_accuracy": 0.17000339776277543,
|
|
"num_tokens": 20415117.0,
|
|
"step": 11765
|
|
},
|
|
{
|
|
"entropy": 5.543955755233765,
|
|
"epoch": 0.9157751410231473,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004921277746285155,
|
|
"loss": 5.4153,
|
|
"mean_token_accuracy": 0.16678078174591066,
|
|
"num_tokens": 20423519.0,
|
|
"step": 11770
|
|
},
|
|
{
|
|
"entropy": 5.573290872573852,
|
|
"epoch": 0.9161641703948649,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004921205058294579,
|
|
"loss": 5.3659,
|
|
"mean_token_accuracy": 0.16791573017835618,
|
|
"num_tokens": 20431831.0,
|
|
"step": 11775
|
|
},
|
|
{
|
|
"entropy": 5.66247525215149,
|
|
"epoch": 0.9165531997665823,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.000492113233735942,
|
|
"loss": 5.5059,
|
|
"mean_token_accuracy": 0.15884622186422348,
|
|
"num_tokens": 20440927.0,
|
|
"step": 11780
|
|
},
|
|
{
|
|
"entropy": 5.5654441833496096,
|
|
"epoch": 0.9169422291382999,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004921059583480785,
|
|
"loss": 5.3926,
|
|
"mean_token_accuracy": 0.16572857946157454,
|
|
"num_tokens": 20448974.0,
|
|
"step": 11785
|
|
},
|
|
{
|
|
"entropy": 5.515251779556275,
|
|
"epoch": 0.9173312585100175,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004920986796659775,
|
|
"loss": 5.3082,
|
|
"mean_token_accuracy": 0.17805312275886537,
|
|
"num_tokens": 20457955.0,
|
|
"step": 11790
|
|
},
|
|
{
|
|
"entropy": 5.5523580551147464,
|
|
"epoch": 0.9177202878817351,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004920913976897498,
|
|
"loss": 5.3972,
|
|
"mean_token_accuracy": 0.16891333162784578,
|
|
"num_tokens": 20465942.0,
|
|
"step": 11795
|
|
},
|
|
{
|
|
"entropy": 5.5653056621551515,
|
|
"epoch": 0.9181093172534527,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004920841124195055,
|
|
"loss": 5.4712,
|
|
"mean_token_accuracy": 0.1669631913304329,
|
|
"num_tokens": 20474726.0,
|
|
"step": 11800
|
|
},
|
|
{
|
|
"entropy": 5.561779737472534,
|
|
"epoch": 0.9184983466251702,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004920768238553554,
|
|
"loss": 5.416,
|
|
"mean_token_accuracy": 0.16652749478816986,
|
|
"num_tokens": 20483442.0,
|
|
"step": 11805
|
|
},
|
|
{
|
|
"entropy": 5.547149133682251,
|
|
"epoch": 0.9188873759968877,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004920695319974099,
|
|
"loss": 5.3741,
|
|
"mean_token_accuracy": 0.17090764045715331,
|
|
"num_tokens": 20492950.0,
|
|
"step": 11810
|
|
},
|
|
{
|
|
"entropy": 5.61188268661499,
|
|
"epoch": 0.9192764053686053,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004920622368457798,
|
|
"loss": 5.4666,
|
|
"mean_token_accuracy": 0.1626928448677063,
|
|
"num_tokens": 20502035.0,
|
|
"step": 11815
|
|
},
|
|
{
|
|
"entropy": 5.617907381057739,
|
|
"epoch": 0.9196654347403229,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004920549384005759,
|
|
"loss": 5.3446,
|
|
"mean_token_accuracy": 0.17139900624752044,
|
|
"num_tokens": 20510140.0,
|
|
"step": 11820
|
|
},
|
|
{
|
|
"entropy": 5.583600568771362,
|
|
"epoch": 0.9200544641120405,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004920476366619086,
|
|
"loss": 5.4569,
|
|
"mean_token_accuracy": 0.1582721382379532,
|
|
"num_tokens": 20519391.0,
|
|
"step": 11825
|
|
},
|
|
{
|
|
"entropy": 5.664299488067627,
|
|
"epoch": 0.920443493483758,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.000492040331629889,
|
|
"loss": 5.4511,
|
|
"mean_token_accuracy": 0.16522680073976517,
|
|
"num_tokens": 20527635.0,
|
|
"step": 11830
|
|
},
|
|
{
|
|
"entropy": 5.6060832977294925,
|
|
"epoch": 0.9208325228554756,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004920330233046277,
|
|
"loss": 5.4075,
|
|
"mean_token_accuracy": 0.16618909686803818,
|
|
"num_tokens": 20536455.0,
|
|
"step": 11835
|
|
},
|
|
{
|
|
"entropy": 5.636282634735108,
|
|
"epoch": 0.9212215522271932,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004920257116862359,
|
|
"loss": 5.546,
|
|
"mean_token_accuracy": 0.1542813390493393,
|
|
"num_tokens": 20545887.0,
|
|
"step": 11840
|
|
},
|
|
{
|
|
"entropy": 5.57595739364624,
|
|
"epoch": 0.9216105815989107,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004920183967748241,
|
|
"loss": 5.381,
|
|
"mean_token_accuracy": 0.16687051951885223,
|
|
"num_tokens": 20554415.0,
|
|
"step": 11845
|
|
},
|
|
{
|
|
"entropy": 5.616524982452392,
|
|
"epoch": 0.9219996109706283,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004920110785705037,
|
|
"loss": 5.4938,
|
|
"mean_token_accuracy": 0.16545359045267105,
|
|
"num_tokens": 20563081.0,
|
|
"step": 11850
|
|
},
|
|
{
|
|
"entropy": 5.513118267059326,
|
|
"epoch": 0.9223886403423458,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004920037570733857,
|
|
"loss": 5.3445,
|
|
"mean_token_accuracy": 0.17197140008211137,
|
|
"num_tokens": 20571800.0,
|
|
"step": 11855
|
|
},
|
|
{
|
|
"entropy": 5.633137226104736,
|
|
"epoch": 0.9227776697140634,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004919964322835809,
|
|
"loss": 5.4673,
|
|
"mean_token_accuracy": 0.1649052232503891,
|
|
"num_tokens": 20580481.0,
|
|
"step": 11860
|
|
},
|
|
{
|
|
"entropy": 5.6207211971282955,
|
|
"epoch": 0.923166699085781,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004919891042012006,
|
|
"loss": 5.3584,
|
|
"mean_token_accuracy": 0.1680561199784279,
|
|
"num_tokens": 20589575.0,
|
|
"step": 11865
|
|
},
|
|
{
|
|
"entropy": 5.512158679962158,
|
|
"epoch": 0.9235557284574986,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004919817728263562,
|
|
"loss": 5.4403,
|
|
"mean_token_accuracy": 0.1664802387356758,
|
|
"num_tokens": 20598277.0,
|
|
"step": 11870
|
|
},
|
|
{
|
|
"entropy": 5.693507719039917,
|
|
"epoch": 0.9239447578292161,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004919744381591586,
|
|
"loss": 5.5295,
|
|
"mean_token_accuracy": 0.16748165041208268,
|
|
"num_tokens": 20607013.0,
|
|
"step": 11875
|
|
},
|
|
{
|
|
"entropy": 5.640137624740601,
|
|
"epoch": 0.9243337872009336,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004919671001997193,
|
|
"loss": 5.4994,
|
|
"mean_token_accuracy": 0.16177828460931779,
|
|
"num_tokens": 20615605.0,
|
|
"step": 11880
|
|
},
|
|
{
|
|
"entropy": 5.675401878356934,
|
|
"epoch": 0.9247228165726512,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004919597589481497,
|
|
"loss": 5.4499,
|
|
"mean_token_accuracy": 0.15949563086032867,
|
|
"num_tokens": 20624275.0,
|
|
"step": 11885
|
|
},
|
|
{
|
|
"entropy": 5.6085638999938965,
|
|
"epoch": 0.9251118459443688,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.000491952414404561,
|
|
"loss": 5.3888,
|
|
"mean_token_accuracy": 0.1679642006754875,
|
|
"num_tokens": 20632681.0,
|
|
"step": 11890
|
|
},
|
|
{
|
|
"entropy": 5.659155607223511,
|
|
"epoch": 0.9255008753160864,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004919450665690646,
|
|
"loss": 5.4556,
|
|
"mean_token_accuracy": 0.16983082741498948,
|
|
"num_tokens": 20641432.0,
|
|
"step": 11895
|
|
},
|
|
{
|
|
"entropy": 5.585770940780639,
|
|
"epoch": 0.925889904687804,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004919377154417724,
|
|
"loss": 5.4649,
|
|
"mean_token_accuracy": 0.16276452094316482,
|
|
"num_tokens": 20650120.0,
|
|
"step": 11900
|
|
},
|
|
{
|
|
"entropy": 5.545875215530396,
|
|
"epoch": 0.9262789340595214,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004919303610227954,
|
|
"loss": 5.359,
|
|
"mean_token_accuracy": 0.16669993549585344,
|
|
"num_tokens": 20658188.0,
|
|
"step": 11905
|
|
},
|
|
{
|
|
"entropy": 5.514937448501587,
|
|
"epoch": 0.926667963431239,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004919230033122457,
|
|
"loss": 5.2875,
|
|
"mean_token_accuracy": 0.1804579585790634,
|
|
"num_tokens": 20666157.0,
|
|
"step": 11910
|
|
},
|
|
{
|
|
"entropy": 5.547408819198608,
|
|
"epoch": 0.9270569928029566,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.0004919156423102345,
|
|
"loss": 5.4928,
|
|
"mean_token_accuracy": 0.16427554711699485,
|
|
"num_tokens": 20674995.0,
|
|
"step": 11915
|
|
},
|
|
{
|
|
"entropy": 5.641458177566529,
|
|
"epoch": 0.9274460221746742,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004919082780168736,
|
|
"loss": 5.4405,
|
|
"mean_token_accuracy": 0.16236664950847626,
|
|
"num_tokens": 20683786.0,
|
|
"step": 11920
|
|
},
|
|
{
|
|
"entropy": 5.585165119171142,
|
|
"epoch": 0.9278350515463918,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004919009104322751,
|
|
"loss": 5.4596,
|
|
"mean_token_accuracy": 0.16301724314689636,
|
|
"num_tokens": 20692582.0,
|
|
"step": 11925
|
|
},
|
|
{
|
|
"entropy": 5.576903438568115,
|
|
"epoch": 0.9282240809181093,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004918935395565503,
|
|
"loss": 5.4632,
|
|
"mean_token_accuracy": 0.16221937090158461,
|
|
"num_tokens": 20700892.0,
|
|
"step": 11930
|
|
},
|
|
{
|
|
"entropy": 5.551387596130371,
|
|
"epoch": 0.9286131102898268,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004918861653898113,
|
|
"loss": 5.3381,
|
|
"mean_token_accuracy": 0.17207940220832824,
|
|
"num_tokens": 20709521.0,
|
|
"step": 11935
|
|
},
|
|
{
|
|
"entropy": 5.562303304672241,
|
|
"epoch": 0.9290021396615444,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.0004918787879321701,
|
|
"loss": 5.4336,
|
|
"mean_token_accuracy": 0.16194119304418564,
|
|
"num_tokens": 20717614.0,
|
|
"step": 11940
|
|
},
|
|
{
|
|
"entropy": 5.563432693481445,
|
|
"epoch": 0.929391169033262,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004918714071837384,
|
|
"loss": 5.3715,
|
|
"mean_token_accuracy": 0.1687655344605446,
|
|
"num_tokens": 20726624.0,
|
|
"step": 11945
|
|
},
|
|
{
|
|
"entropy": 5.61021842956543,
|
|
"epoch": 0.9297801984049796,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004918640231446282,
|
|
"loss": 5.4828,
|
|
"mean_token_accuracy": 0.16277274787425994,
|
|
"num_tokens": 20734738.0,
|
|
"step": 11950
|
|
},
|
|
{
|
|
"entropy": 5.605218696594238,
|
|
"epoch": 0.9301692277766972,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004918566358149517,
|
|
"loss": 5.3988,
|
|
"mean_token_accuracy": 0.16683424711227418,
|
|
"num_tokens": 20742825.0,
|
|
"step": 11955
|
|
},
|
|
{
|
|
"entropy": 5.578117942810058,
|
|
"epoch": 0.9305582571484147,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.000491849245194821,
|
|
"loss": 5.3779,
|
|
"mean_token_accuracy": 0.1739774078130722,
|
|
"num_tokens": 20752132.0,
|
|
"step": 11960
|
|
},
|
|
{
|
|
"entropy": 5.637444067001343,
|
|
"epoch": 0.9309472865201323,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004918418512843479,
|
|
"loss": 5.5075,
|
|
"mean_token_accuracy": 0.1613238826394081,
|
|
"num_tokens": 20761838.0,
|
|
"step": 11965
|
|
},
|
|
{
|
|
"entropy": 5.56450719833374,
|
|
"epoch": 0.9313363158918498,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004918344540836451,
|
|
"loss": 5.3957,
|
|
"mean_token_accuracy": 0.16996693909168242,
|
|
"num_tokens": 20770405.0,
|
|
"step": 11970
|
|
},
|
|
{
|
|
"entropy": 5.715441370010376,
|
|
"epoch": 0.9317253452635674,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004918270535928244,
|
|
"loss": 5.5864,
|
|
"mean_token_accuracy": 0.15619297772645951,
|
|
"num_tokens": 20780130.0,
|
|
"step": 11975
|
|
},
|
|
{
|
|
"entropy": 5.594107055664063,
|
|
"epoch": 0.932114374635285,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004918196498119984,
|
|
"loss": 5.4561,
|
|
"mean_token_accuracy": 0.17283804416656495,
|
|
"num_tokens": 20788852.0,
|
|
"step": 11980
|
|
},
|
|
{
|
|
"entropy": 5.553250312805176,
|
|
"epoch": 0.9325034040070025,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004918122427412793,
|
|
"loss": 5.3715,
|
|
"mean_token_accuracy": 0.1689470276236534,
|
|
"num_tokens": 20796944.0,
|
|
"step": 11985
|
|
},
|
|
{
|
|
"entropy": 5.54477891921997,
|
|
"epoch": 0.9328924333787201,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004918048323807795,
|
|
"loss": 5.5106,
|
|
"mean_token_accuracy": 0.1635565549135208,
|
|
"num_tokens": 20806118.0,
|
|
"step": 11990
|
|
},
|
|
{
|
|
"entropy": 5.649374771118164,
|
|
"epoch": 0.9332814627504377,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004917974187306114,
|
|
"loss": 5.3038,
|
|
"mean_token_accuracy": 0.17418421804904938,
|
|
"num_tokens": 20814643.0,
|
|
"step": 11995
|
|
},
|
|
{
|
|
"entropy": 5.6086163997650145,
|
|
"epoch": 0.9336704921221552,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.0004917900017908875,
|
|
"loss": 5.3672,
|
|
"mean_token_accuracy": 0.1686716139316559,
|
|
"num_tokens": 20823315.0,
|
|
"step": 12000
|
|
},
|
|
{
|
|
"epoch": 0.9336704921221552,
|
|
"eval_entropy": 5.371572630719799,
|
|
"eval_loss": 5.466134548187256,
|
|
"eval_mean_token_accuracy": 0.1723012616067293,
|
|
"eval_num_tokens": 20823315.0,
|
|
"eval_runtime": 28.5605,
|
|
"eval_samples_per_second": 1455.088,
|
|
"eval_steps_per_second": 181.895,
|
|
"step": 12000
|
|
},
|
|
{
|
|
"entropy": 5.507457256317139,
|
|
"epoch": 0.9340595214938728,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004917825815617205,
|
|
"loss": 5.3884,
|
|
"mean_token_accuracy": 0.17000421285629272,
|
|
"num_tokens": 20832811.0,
|
|
"step": 12005
|
|
},
|
|
{
|
|
"entropy": 5.613448762893677,
|
|
"epoch": 0.9344485508655903,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004917751580432229,
|
|
"loss": 5.4398,
|
|
"mean_token_accuracy": 0.16664963215589523,
|
|
"num_tokens": 20841824.0,
|
|
"step": 12010
|
|
},
|
|
{
|
|
"entropy": 5.599476003646851,
|
|
"epoch": 0.9348375802373079,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004917677312355072,
|
|
"loss": 5.3926,
|
|
"mean_token_accuracy": 0.17509149014949799,
|
|
"num_tokens": 20850220.0,
|
|
"step": 12015
|
|
},
|
|
{
|
|
"entropy": 5.488557815551758,
|
|
"epoch": 0.9352266096090255,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004917603011386863,
|
|
"loss": 5.3347,
|
|
"mean_token_accuracy": 0.17387936115264893,
|
|
"num_tokens": 20859193.0,
|
|
"step": 12020
|
|
},
|
|
{
|
|
"entropy": 5.54458532333374,
|
|
"epoch": 0.9356156389807431,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004917528677528727,
|
|
"loss": 5.3549,
|
|
"mean_token_accuracy": 0.16718203574419022,
|
|
"num_tokens": 20867610.0,
|
|
"step": 12025
|
|
},
|
|
{
|
|
"entropy": 5.615087413787842,
|
|
"epoch": 0.9360046683524607,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004917454310781795,
|
|
"loss": 5.454,
|
|
"mean_token_accuracy": 0.16309396028518677,
|
|
"num_tokens": 20876991.0,
|
|
"step": 12030
|
|
},
|
|
{
|
|
"entropy": 5.541305351257324,
|
|
"epoch": 0.9363936977241781,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004917379911147193,
|
|
"loss": 5.3173,
|
|
"mean_token_accuracy": 0.16801157742738723,
|
|
"num_tokens": 20885794.0,
|
|
"step": 12035
|
|
},
|
|
{
|
|
"entropy": 5.619901990890503,
|
|
"epoch": 0.9367827270958957,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004917305478626049,
|
|
"loss": 5.5104,
|
|
"mean_token_accuracy": 0.16595079600811005,
|
|
"num_tokens": 20893487.0,
|
|
"step": 12040
|
|
},
|
|
{
|
|
"entropy": 5.6008594036102295,
|
|
"epoch": 0.9371717564676133,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004917231013219495,
|
|
"loss": 5.4598,
|
|
"mean_token_accuracy": 0.1607996016740799,
|
|
"num_tokens": 20902587.0,
|
|
"step": 12045
|
|
},
|
|
{
|
|
"entropy": 5.596264743804932,
|
|
"epoch": 0.9375607858393309,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.000491715651492866,
|
|
"loss": 5.3903,
|
|
"mean_token_accuracy": 0.17339229583740234,
|
|
"num_tokens": 20911062.0,
|
|
"step": 12050
|
|
},
|
|
{
|
|
"entropy": 5.620618295669556,
|
|
"epoch": 0.9379498152110485,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004917081983754675,
|
|
"loss": 5.4123,
|
|
"mean_token_accuracy": 0.16720927357673646,
|
|
"num_tokens": 20919369.0,
|
|
"step": 12055
|
|
},
|
|
{
|
|
"entropy": 5.613325119018555,
|
|
"epoch": 0.938338844582766,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004917007419698669,
|
|
"loss": 5.4666,
|
|
"mean_token_accuracy": 0.1663628563284874,
|
|
"num_tokens": 20927514.0,
|
|
"step": 12060
|
|
},
|
|
{
|
|
"entropy": 5.677690505981445,
|
|
"epoch": 0.9387278739544835,
|
|
"grad_norm": 5.875,
|
|
"learning_rate": 0.0004916932822761776,
|
|
"loss": 5.5023,
|
|
"mean_token_accuracy": 0.16759129613637924,
|
|
"num_tokens": 20935750.0,
|
|
"step": 12065
|
|
},
|
|
{
|
|
"entropy": 5.5808741569519045,
|
|
"epoch": 0.9391169033262011,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004916858192945126,
|
|
"loss": 5.3986,
|
|
"mean_token_accuracy": 0.16836540699005126,
|
|
"num_tokens": 20944089.0,
|
|
"step": 12070
|
|
},
|
|
{
|
|
"entropy": 5.581806325912476,
|
|
"epoch": 0.9395059326979187,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004916783530249852,
|
|
"loss": 5.5052,
|
|
"mean_token_accuracy": 0.1604120537638664,
|
|
"num_tokens": 20952704.0,
|
|
"step": 12075
|
|
},
|
|
{
|
|
"entropy": 5.61510329246521,
|
|
"epoch": 0.9398949620696363,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004916708834677086,
|
|
"loss": 5.3592,
|
|
"mean_token_accuracy": 0.16789056211709977,
|
|
"num_tokens": 20960741.0,
|
|
"step": 12080
|
|
},
|
|
{
|
|
"entropy": 5.604568719863892,
|
|
"epoch": 0.9402839914413538,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004916634106227962,
|
|
"loss": 5.3752,
|
|
"mean_token_accuracy": 0.17388292998075486,
|
|
"num_tokens": 20968778.0,
|
|
"step": 12085
|
|
},
|
|
{
|
|
"entropy": 5.603709936141968,
|
|
"epoch": 0.9406730208130714,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004916559344903614,
|
|
"loss": 5.5405,
|
|
"mean_token_accuracy": 0.1607699140906334,
|
|
"num_tokens": 20977993.0,
|
|
"step": 12090
|
|
},
|
|
{
|
|
"entropy": 5.612804269790649,
|
|
"epoch": 0.941062050184789,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004916484550705176,
|
|
"loss": 5.3795,
|
|
"mean_token_accuracy": 0.17117612361907958,
|
|
"num_tokens": 20986974.0,
|
|
"step": 12095
|
|
},
|
|
{
|
|
"entropy": 5.604335594177246,
|
|
"epoch": 0.9414510795565065,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004916409723633785,
|
|
"loss": 5.4724,
|
|
"mean_token_accuracy": 0.16735209971666337,
|
|
"num_tokens": 20995224.0,
|
|
"step": 12100
|
|
},
|
|
{
|
|
"entropy": 5.6226420402526855,
|
|
"epoch": 0.9418401089282241,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004916334863690573,
|
|
"loss": 5.4697,
|
|
"mean_token_accuracy": 0.16305154114961623,
|
|
"num_tokens": 21003270.0,
|
|
"step": 12105
|
|
},
|
|
{
|
|
"entropy": 5.595528697967529,
|
|
"epoch": 0.9422291382999416,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004916259970876678,
|
|
"loss": 5.4472,
|
|
"mean_token_accuracy": 0.16190327256917952,
|
|
"num_tokens": 21012665.0,
|
|
"step": 12110
|
|
},
|
|
{
|
|
"entropy": 5.630600214004517,
|
|
"epoch": 0.9426181676716592,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.0004916185045193237,
|
|
"loss": 5.4708,
|
|
"mean_token_accuracy": 0.1663910672068596,
|
|
"num_tokens": 21021043.0,
|
|
"step": 12115
|
|
},
|
|
{
|
|
"entropy": 5.621525621414184,
|
|
"epoch": 0.9430071970433768,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004916110086641384,
|
|
"loss": 5.3871,
|
|
"mean_token_accuracy": 0.16917871534824372,
|
|
"num_tokens": 21029525.0,
|
|
"step": 12120
|
|
},
|
|
{
|
|
"entropy": 5.529054307937622,
|
|
"epoch": 0.9433962264150944,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004916035095222259,
|
|
"loss": 5.3924,
|
|
"mean_token_accuracy": 0.16976384520530702,
|
|
"num_tokens": 21037687.0,
|
|
"step": 12125
|
|
},
|
|
{
|
|
"entropy": 5.611918115615845,
|
|
"epoch": 0.9437852557868119,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004915960070936999,
|
|
"loss": 5.4768,
|
|
"mean_token_accuracy": 0.16243709176778792,
|
|
"num_tokens": 21046095.0,
|
|
"step": 12130
|
|
},
|
|
{
|
|
"entropy": 5.659605216979981,
|
|
"epoch": 0.9441742851585294,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004915885013786742,
|
|
"loss": 5.433,
|
|
"mean_token_accuracy": 0.16504660099744797,
|
|
"num_tokens": 21054565.0,
|
|
"step": 12135
|
|
},
|
|
{
|
|
"entropy": 5.49802794456482,
|
|
"epoch": 0.944563314530247,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004915809923772628,
|
|
"loss": 5.3443,
|
|
"mean_token_accuracy": 0.17390815615653993,
|
|
"num_tokens": 21062942.0,
|
|
"step": 12140
|
|
},
|
|
{
|
|
"entropy": 5.5965657234191895,
|
|
"epoch": 0.9449523439019646,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004915734800895796,
|
|
"loss": 5.396,
|
|
"mean_token_accuracy": 0.1641937553882599,
|
|
"num_tokens": 21070642.0,
|
|
"step": 12145
|
|
},
|
|
{
|
|
"entropy": 5.623910331726075,
|
|
"epoch": 0.9453413732736822,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004915659645157383,
|
|
"loss": 5.3635,
|
|
"mean_token_accuracy": 0.16894838064908982,
|
|
"num_tokens": 21079007.0,
|
|
"step": 12150
|
|
},
|
|
{
|
|
"entropy": 5.605703544616699,
|
|
"epoch": 0.9457304026453998,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004915584456558535,
|
|
"loss": 5.4377,
|
|
"mean_token_accuracy": 0.16110673993825914,
|
|
"num_tokens": 21087672.0,
|
|
"step": 12155
|
|
},
|
|
{
|
|
"entropy": 5.686621379852295,
|
|
"epoch": 0.9461194320171173,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004915509235100388,
|
|
"loss": 5.376,
|
|
"mean_token_accuracy": 0.16856016516685485,
|
|
"num_tokens": 21095954.0,
|
|
"step": 12160
|
|
},
|
|
{
|
|
"entropy": 5.604067611694336,
|
|
"epoch": 0.9465084613888348,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004915433980784086,
|
|
"loss": 5.3702,
|
|
"mean_token_accuracy": 0.16448871940374374,
|
|
"num_tokens": 21104439.0,
|
|
"step": 12165
|
|
},
|
|
{
|
|
"entropy": 5.524645709991455,
|
|
"epoch": 0.9468974907605524,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004915358693610769,
|
|
"loss": 5.4059,
|
|
"mean_token_accuracy": 0.15946614742279053,
|
|
"num_tokens": 21112933.0,
|
|
"step": 12170
|
|
},
|
|
{
|
|
"entropy": 5.538733863830567,
|
|
"epoch": 0.94728652013227,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004915283373581581,
|
|
"loss": 5.402,
|
|
"mean_token_accuracy": 0.1738529697060585,
|
|
"num_tokens": 21122085.0,
|
|
"step": 12175
|
|
},
|
|
{
|
|
"entropy": 5.634131717681885,
|
|
"epoch": 0.9476755495039876,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004915208020697664,
|
|
"loss": 5.4597,
|
|
"mean_token_accuracy": 0.16466081142425537,
|
|
"num_tokens": 21130994.0,
|
|
"step": 12180
|
|
},
|
|
{
|
|
"entropy": 5.645436811447143,
|
|
"epoch": 0.9480645788757052,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004915132634960162,
|
|
"loss": 5.3834,
|
|
"mean_token_accuracy": 0.17394153475761415,
|
|
"num_tokens": 21139744.0,
|
|
"step": 12185
|
|
},
|
|
{
|
|
"entropy": 5.595538473129272,
|
|
"epoch": 0.9484536082474226,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004915057216370218,
|
|
"loss": 5.3965,
|
|
"mean_token_accuracy": 0.1731519356369972,
|
|
"num_tokens": 21148333.0,
|
|
"step": 12190
|
|
},
|
|
{
|
|
"entropy": 5.519620656967163,
|
|
"epoch": 0.9488426376191402,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004914981764928977,
|
|
"loss": 5.326,
|
|
"mean_token_accuracy": 0.17691762298345565,
|
|
"num_tokens": 21157450.0,
|
|
"step": 12195
|
|
},
|
|
{
|
|
"entropy": 5.648521041870117,
|
|
"epoch": 0.9492316669908578,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004914906280637584,
|
|
"loss": 5.5001,
|
|
"mean_token_accuracy": 0.16335393339395524,
|
|
"num_tokens": 21166410.0,
|
|
"step": 12200
|
|
},
|
|
{
|
|
"entropy": 5.604200220108032,
|
|
"epoch": 0.9496206963625754,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004914830763497183,
|
|
"loss": 5.435,
|
|
"mean_token_accuracy": 0.16810693889856337,
|
|
"num_tokens": 21175104.0,
|
|
"step": 12205
|
|
},
|
|
{
|
|
"entropy": 5.597310638427734,
|
|
"epoch": 0.950009725734293,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004914755213508922,
|
|
"loss": 5.3788,
|
|
"mean_token_accuracy": 0.16749434620141984,
|
|
"num_tokens": 21182597.0,
|
|
"step": 12210
|
|
},
|
|
{
|
|
"entropy": 5.5915443897247314,
|
|
"epoch": 0.9503987551060105,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004914679630673945,
|
|
"loss": 5.4896,
|
|
"mean_token_accuracy": 0.16872426271438598,
|
|
"num_tokens": 21192399.0,
|
|
"step": 12215
|
|
},
|
|
{
|
|
"entropy": 5.56868987083435,
|
|
"epoch": 0.950787784477728,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004914604014993401,
|
|
"loss": 5.3472,
|
|
"mean_token_accuracy": 0.17401702851057052,
|
|
"num_tokens": 21201275.0,
|
|
"step": 12220
|
|
},
|
|
{
|
|
"entropy": 5.5518927574157715,
|
|
"epoch": 0.9511768138494456,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004914528366468436,
|
|
"loss": 5.4565,
|
|
"mean_token_accuracy": 0.16536201536655426,
|
|
"num_tokens": 21210491.0,
|
|
"step": 12225
|
|
},
|
|
{
|
|
"entropy": 5.564200925827026,
|
|
"epoch": 0.9515658432211632,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004914452685100199,
|
|
"loss": 5.4495,
|
|
"mean_token_accuracy": 0.1683812901377678,
|
|
"num_tokens": 21218899.0,
|
|
"step": 12230
|
|
},
|
|
{
|
|
"entropy": 5.501306676864624,
|
|
"epoch": 0.9519548725928808,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004914376970889836,
|
|
"loss": 5.3524,
|
|
"mean_token_accuracy": 0.16297265887260437,
|
|
"num_tokens": 21227640.0,
|
|
"step": 12235
|
|
},
|
|
{
|
|
"entropy": 5.575056791305542,
|
|
"epoch": 0.9523439019645983,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004914301223838497,
|
|
"loss": 5.3197,
|
|
"mean_token_accuracy": 0.16264411211013793,
|
|
"num_tokens": 21236422.0,
|
|
"step": 12240
|
|
},
|
|
{
|
|
"entropy": 5.630202198028565,
|
|
"epoch": 0.9527329313363159,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004914225443947334,
|
|
"loss": 5.4947,
|
|
"mean_token_accuracy": 0.16732407957315446,
|
|
"num_tokens": 21245820.0,
|
|
"step": 12245
|
|
},
|
|
{
|
|
"entropy": 5.647228384017945,
|
|
"epoch": 0.9531219607080335,
|
|
"grad_norm": 3.90625,
|
|
"learning_rate": 0.0004914149631217494,
|
|
"loss": 5.4399,
|
|
"mean_token_accuracy": 0.16611770391464234,
|
|
"num_tokens": 21255570.0,
|
|
"step": 12250
|
|
},
|
|
{
|
|
"entropy": 5.662381029129028,
|
|
"epoch": 0.953510990079751,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004914073785650127,
|
|
"loss": 5.5614,
|
|
"mean_token_accuracy": 0.16004973351955415,
|
|
"num_tokens": 21263712.0,
|
|
"step": 12255
|
|
},
|
|
{
|
|
"entropy": 5.6631018161773685,
|
|
"epoch": 0.9539000194514686,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004913997907246385,
|
|
"loss": 5.436,
|
|
"mean_token_accuracy": 0.17167474776506425,
|
|
"num_tokens": 21272309.0,
|
|
"step": 12260
|
|
},
|
|
{
|
|
"entropy": 5.506390190124511,
|
|
"epoch": 0.9542890488231861,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.000491392199600742,
|
|
"loss": 5.359,
|
|
"mean_token_accuracy": 0.1665118530392647,
|
|
"num_tokens": 21281711.0,
|
|
"step": 12265
|
|
},
|
|
{
|
|
"entropy": 5.51539626121521,
|
|
"epoch": 0.9546780781949037,
|
|
"grad_norm": 3.734375,
|
|
"learning_rate": 0.0004913846051934382,
|
|
"loss": 5.3196,
|
|
"mean_token_accuracy": 0.17208221256732942,
|
|
"num_tokens": 21289524.0,
|
|
"step": 12270
|
|
},
|
|
{
|
|
"entropy": 5.513137531280518,
|
|
"epoch": 0.9550671075666213,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004913770075028425,
|
|
"loss": 5.2626,
|
|
"mean_token_accuracy": 0.17546534538269043,
|
|
"num_tokens": 21298225.0,
|
|
"step": 12275
|
|
},
|
|
{
|
|
"entropy": 5.542500305175781,
|
|
"epoch": 0.9554561369383389,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004913694065290701,
|
|
"loss": 5.2958,
|
|
"mean_token_accuracy": 0.178589104115963,
|
|
"num_tokens": 21306819.0,
|
|
"step": 12280
|
|
},
|
|
{
|
|
"entropy": 5.576265525817871,
|
|
"epoch": 0.9558451663100564,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004913618022722363,
|
|
"loss": 5.4454,
|
|
"mean_token_accuracy": 0.16563066840171814,
|
|
"num_tokens": 21315517.0,
|
|
"step": 12285
|
|
},
|
|
{
|
|
"entropy": 5.614781618118286,
|
|
"epoch": 0.9562341956817739,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004913541947324566,
|
|
"loss": 5.3488,
|
|
"mean_token_accuracy": 0.16864724308252335,
|
|
"num_tokens": 21324144.0,
|
|
"step": 12290
|
|
},
|
|
{
|
|
"entropy": 5.605503416061401,
|
|
"epoch": 0.9566232250534915,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004913465839098463,
|
|
"loss": 5.4197,
|
|
"mean_token_accuracy": 0.17107993364334106,
|
|
"num_tokens": 21333329.0,
|
|
"step": 12295
|
|
},
|
|
{
|
|
"entropy": 5.522213315963745,
|
|
"epoch": 0.9570122544252091,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004913389698045209,
|
|
"loss": 5.3781,
|
|
"mean_token_accuracy": 0.1652178406715393,
|
|
"num_tokens": 21341955.0,
|
|
"step": 12300
|
|
},
|
|
{
|
|
"entropy": 5.586077404022217,
|
|
"epoch": 0.9574012837969267,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.000491331352416596,
|
|
"loss": 5.3473,
|
|
"mean_token_accuracy": 0.16738866716623307,
|
|
"num_tokens": 21350593.0,
|
|
"step": 12305
|
|
},
|
|
{
|
|
"entropy": 5.535979175567627,
|
|
"epoch": 0.9577903131686443,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004913237317461872,
|
|
"loss": 5.4292,
|
|
"mean_token_accuracy": 0.16674810349941255,
|
|
"num_tokens": 21359007.0,
|
|
"step": 12310
|
|
},
|
|
{
|
|
"entropy": 5.549071025848389,
|
|
"epoch": 0.9581793425403617,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00049131610779341,
|
|
"loss": 5.4487,
|
|
"mean_token_accuracy": 0.16577992141246795,
|
|
"num_tokens": 21367645.0,
|
|
"step": 12315
|
|
},
|
|
{
|
|
"entropy": 5.510221481323242,
|
|
"epoch": 0.9585683719120793,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004913084805583803,
|
|
"loss": 5.263,
|
|
"mean_token_accuracy": 0.17191761881113052,
|
|
"num_tokens": 21376040.0,
|
|
"step": 12320
|
|
},
|
|
{
|
|
"entropy": 5.58285551071167,
|
|
"epoch": 0.9589574012837969,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004913008500412136,
|
|
"loss": 5.4068,
|
|
"mean_token_accuracy": 0.17451067715883256,
|
|
"num_tokens": 21385305.0,
|
|
"step": 12325
|
|
},
|
|
{
|
|
"entropy": 5.545878791809082,
|
|
"epoch": 0.9593464306555145,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004912932162420259,
|
|
"loss": 5.3043,
|
|
"mean_token_accuracy": 0.18116566985845567,
|
|
"num_tokens": 21393705.0,
|
|
"step": 12330
|
|
},
|
|
{
|
|
"entropy": 5.582909774780274,
|
|
"epoch": 0.9597354600272321,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004912855791609327,
|
|
"loss": 5.428,
|
|
"mean_token_accuracy": 0.16888475716114043,
|
|
"num_tokens": 21401830.0,
|
|
"step": 12335
|
|
},
|
|
{
|
|
"entropy": 5.569549655914306,
|
|
"epoch": 0.9601244893989496,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004912779387980502,
|
|
"loss": 5.4796,
|
|
"mean_token_accuracy": 0.16422994881868364,
|
|
"num_tokens": 21410398.0,
|
|
"step": 12340
|
|
},
|
|
{
|
|
"entropy": 5.64050612449646,
|
|
"epoch": 0.9605135187706672,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004912702951534942,
|
|
"loss": 5.4314,
|
|
"mean_token_accuracy": 0.16885158866643907,
|
|
"num_tokens": 21419082.0,
|
|
"step": 12345
|
|
},
|
|
{
|
|
"entropy": 5.648242807388305,
|
|
"epoch": 0.9609025481423847,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004912626482273809,
|
|
"loss": 5.427,
|
|
"mean_token_accuracy": 0.1632491961121559,
|
|
"num_tokens": 21427992.0,
|
|
"step": 12350
|
|
},
|
|
{
|
|
"entropy": 5.555550384521484,
|
|
"epoch": 0.9612915775141023,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004912549980198258,
|
|
"loss": 5.3935,
|
|
"mean_token_accuracy": 0.16734340637922288,
|
|
"num_tokens": 21436933.0,
|
|
"step": 12355
|
|
},
|
|
{
|
|
"entropy": 5.5616072654724125,
|
|
"epoch": 0.9616806068858199,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004912473445309455,
|
|
"loss": 5.3882,
|
|
"mean_token_accuracy": 0.16933085173368453,
|
|
"num_tokens": 21445640.0,
|
|
"step": 12360
|
|
},
|
|
{
|
|
"entropy": 5.698657846450805,
|
|
"epoch": 0.9620696362575375,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.000491239687760856,
|
|
"loss": 5.5502,
|
|
"mean_token_accuracy": 0.15852493792772293,
|
|
"num_tokens": 21454511.0,
|
|
"step": 12365
|
|
},
|
|
{
|
|
"entropy": 5.60389199256897,
|
|
"epoch": 0.962458665629255,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004912320277096732,
|
|
"loss": 5.5412,
|
|
"mean_token_accuracy": 0.1576765350997448,
|
|
"num_tokens": 21463851.0,
|
|
"step": 12370
|
|
},
|
|
{
|
|
"entropy": 5.536577939987183,
|
|
"epoch": 0.9628476950009726,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 0.0004912243643775137,
|
|
"loss": 5.3283,
|
|
"mean_token_accuracy": 0.17465019077062607,
|
|
"num_tokens": 21471620.0,
|
|
"step": 12375
|
|
},
|
|
{
|
|
"entropy": 5.570523643493653,
|
|
"epoch": 0.9632367243726901,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004912166977644936,
|
|
"loss": 5.3446,
|
|
"mean_token_accuracy": 0.1683275133371353,
|
|
"num_tokens": 21479944.0,
|
|
"step": 12380
|
|
},
|
|
{
|
|
"entropy": 5.631869506835938,
|
|
"epoch": 0.9636257537444077,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.0004912090278707293,
|
|
"loss": 5.5166,
|
|
"mean_token_accuracy": 0.15817615985870362,
|
|
"num_tokens": 21489175.0,
|
|
"step": 12385
|
|
},
|
|
{
|
|
"entropy": 5.595966625213623,
|
|
"epoch": 0.9640147831161253,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.000491201354696337,
|
|
"loss": 5.4373,
|
|
"mean_token_accuracy": 0.17099682986736298,
|
|
"num_tokens": 21498533.0,
|
|
"step": 12390
|
|
},
|
|
{
|
|
"entropy": 5.68024845123291,
|
|
"epoch": 0.9644038124878428,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004911936782414334,
|
|
"loss": 5.5038,
|
|
"mean_token_accuracy": 0.15963890701532363,
|
|
"num_tokens": 21506771.0,
|
|
"step": 12395
|
|
},
|
|
{
|
|
"entropy": 5.534885454177856,
|
|
"epoch": 0.9647928418595604,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004911859985061348,
|
|
"loss": 5.3038,
|
|
"mean_token_accuracy": 0.1820862114429474,
|
|
"num_tokens": 21515359.0,
|
|
"step": 12400
|
|
},
|
|
{
|
|
"entropy": 5.566308212280274,
|
|
"epoch": 0.965181871231278,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004911783154905577,
|
|
"loss": 5.3759,
|
|
"mean_token_accuracy": 0.16567621976137162,
|
|
"num_tokens": 21524313.0,
|
|
"step": 12405
|
|
},
|
|
{
|
|
"entropy": 5.529404783248902,
|
|
"epoch": 0.9655709006029956,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004911706291948188,
|
|
"loss": 5.3766,
|
|
"mean_token_accuracy": 0.1746726393699646,
|
|
"num_tokens": 21533211.0,
|
|
"step": 12410
|
|
},
|
|
{
|
|
"entropy": 5.5782609462738035,
|
|
"epoch": 0.9659599299747131,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004911629396190348,
|
|
"loss": 5.3304,
|
|
"mean_token_accuracy": 0.17233569473028182,
|
|
"num_tokens": 21541575.0,
|
|
"step": 12415
|
|
},
|
|
{
|
|
"entropy": 5.597880029678345,
|
|
"epoch": 0.9663489593464306,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004911552467633221,
|
|
"loss": 5.4257,
|
|
"mean_token_accuracy": 0.1635533392429352,
|
|
"num_tokens": 21549569.0,
|
|
"step": 12420
|
|
},
|
|
{
|
|
"entropy": 5.5263899803161625,
|
|
"epoch": 0.9667379887181482,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004911475506277976,
|
|
"loss": 5.3771,
|
|
"mean_token_accuracy": 0.16541996747255325,
|
|
"num_tokens": 21557277.0,
|
|
"step": 12425
|
|
},
|
|
{
|
|
"entropy": 5.5775562763214115,
|
|
"epoch": 0.9671270180898658,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.000491139851212578,
|
|
"loss": 5.4123,
|
|
"mean_token_accuracy": 0.16224730163812637,
|
|
"num_tokens": 21566590.0,
|
|
"step": 12430
|
|
},
|
|
{
|
|
"entropy": 5.653618907928466,
|
|
"epoch": 0.9675160474615834,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004911321485177802,
|
|
"loss": 5.479,
|
|
"mean_token_accuracy": 0.15981924384832383,
|
|
"num_tokens": 21575140.0,
|
|
"step": 12435
|
|
},
|
|
{
|
|
"entropy": 5.5106744289398195,
|
|
"epoch": 0.967905076833301,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004911244425435212,
|
|
"loss": 5.4187,
|
|
"mean_token_accuracy": 0.16120911836624147,
|
|
"num_tokens": 21584647.0,
|
|
"step": 12440
|
|
},
|
|
{
|
|
"entropy": 5.612622928619385,
|
|
"epoch": 0.9682941062050184,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004911167332899176,
|
|
"loss": 5.3749,
|
|
"mean_token_accuracy": 0.16861445009708403,
|
|
"num_tokens": 21593609.0,
|
|
"step": 12445
|
|
},
|
|
{
|
|
"entropy": 5.710604286193847,
|
|
"epoch": 0.968683135576736,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004911090207570867,
|
|
"loss": 5.4977,
|
|
"mean_token_accuracy": 0.16604768186807634,
|
|
"num_tokens": 21602584.0,
|
|
"step": 12450
|
|
},
|
|
{
|
|
"entropy": 5.497505331039429,
|
|
"epoch": 0.9690721649484536,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004911013049451453,
|
|
"loss": 5.4567,
|
|
"mean_token_accuracy": 0.1718402773141861,
|
|
"num_tokens": 21611109.0,
|
|
"step": 12455
|
|
},
|
|
{
|
|
"entropy": 5.647250127792359,
|
|
"epoch": 0.9694611943201712,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004910935858542106,
|
|
"loss": 5.4644,
|
|
"mean_token_accuracy": 0.1647668480873108,
|
|
"num_tokens": 21620173.0,
|
|
"step": 12460
|
|
},
|
|
{
|
|
"entropy": 5.57645320892334,
|
|
"epoch": 0.9698502236918888,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004910858634843997,
|
|
"loss": 5.2968,
|
|
"mean_token_accuracy": 0.17491580843925475,
|
|
"num_tokens": 21628318.0,
|
|
"step": 12465
|
|
},
|
|
{
|
|
"entropy": 5.589544105529785,
|
|
"epoch": 0.9702392530636063,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004910781378358297,
|
|
"loss": 5.5078,
|
|
"mean_token_accuracy": 0.164412023127079,
|
|
"num_tokens": 21637102.0,
|
|
"step": 12470
|
|
},
|
|
{
|
|
"entropy": 5.590525102615357,
|
|
"epoch": 0.9706282824353238,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004910704089086178,
|
|
"loss": 5.3554,
|
|
"mean_token_accuracy": 0.17072507441043855,
|
|
"num_tokens": 21645055.0,
|
|
"step": 12475
|
|
},
|
|
{
|
|
"entropy": 5.6012671947479244,
|
|
"epoch": 0.9710173118070414,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004910626767028815,
|
|
"loss": 5.4189,
|
|
"mean_token_accuracy": 0.16050756871700286,
|
|
"num_tokens": 21654106.0,
|
|
"step": 12480
|
|
},
|
|
{
|
|
"entropy": 5.5423140048980715,
|
|
"epoch": 0.971406341178759,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004910549412187379,
|
|
"loss": 5.4081,
|
|
"mean_token_accuracy": 0.17627297341823578,
|
|
"num_tokens": 21663081.0,
|
|
"step": 12485
|
|
},
|
|
{
|
|
"entropy": 5.586370897293091,
|
|
"epoch": 0.9717953705504766,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004910472024563045,
|
|
"loss": 5.3733,
|
|
"mean_token_accuracy": 0.1717690572142601,
|
|
"num_tokens": 21671033.0,
|
|
"step": 12490
|
|
},
|
|
{
|
|
"entropy": 5.61957197189331,
|
|
"epoch": 0.9721843999221941,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004910394604156987,
|
|
"loss": 5.3861,
|
|
"mean_token_accuracy": 0.17137907147407533,
|
|
"num_tokens": 21679167.0,
|
|
"step": 12495
|
|
},
|
|
{
|
|
"entropy": 5.644653844833374,
|
|
"epoch": 0.9725734292939117,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004910317150970379,
|
|
"loss": 5.5172,
|
|
"mean_token_accuracy": 0.16495581418275834,
|
|
"num_tokens": 21688365.0,
|
|
"step": 12500
|
|
},
|
|
{
|
|
"entropy": 5.595451211929321,
|
|
"epoch": 0.9729624586656292,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004910239665004397,
|
|
"loss": 5.3996,
|
|
"mean_token_accuracy": 0.16991671025753022,
|
|
"num_tokens": 21697003.0,
|
|
"step": 12505
|
|
},
|
|
{
|
|
"entropy": 5.587980651855469,
|
|
"epoch": 0.9733514880373468,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004910162146260216,
|
|
"loss": 5.408,
|
|
"mean_token_accuracy": 0.16433726847171784,
|
|
"num_tokens": 21705947.0,
|
|
"step": 12510
|
|
},
|
|
{
|
|
"entropy": 5.568564796447754,
|
|
"epoch": 0.9737405174090644,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004910084594739013,
|
|
"loss": 5.4325,
|
|
"mean_token_accuracy": 0.16390192359685898,
|
|
"num_tokens": 21714153.0,
|
|
"step": 12515
|
|
},
|
|
{
|
|
"entropy": 5.630647468566894,
|
|
"epoch": 0.9741295467807819,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004910007010441964,
|
|
"loss": 5.5104,
|
|
"mean_token_accuracy": 0.16128549575805665,
|
|
"num_tokens": 21723480.0,
|
|
"step": 12520
|
|
},
|
|
{
|
|
"entropy": 5.6597191333770756,
|
|
"epoch": 0.9745185761524995,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004909929393370248,
|
|
"loss": 5.3811,
|
|
"mean_token_accuracy": 0.1717036947607994,
|
|
"num_tokens": 21731297.0,
|
|
"step": 12525
|
|
},
|
|
{
|
|
"entropy": 5.553610706329346,
|
|
"epoch": 0.9749076055242171,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004909851743525041,
|
|
"loss": 5.3617,
|
|
"mean_token_accuracy": 0.16348666846752166,
|
|
"num_tokens": 21740975.0,
|
|
"step": 12530
|
|
},
|
|
{
|
|
"entropy": 5.5200341701507565,
|
|
"epoch": 0.9752966348959347,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.000490977406090752,
|
|
"loss": 5.3565,
|
|
"mean_token_accuracy": 0.16492999494075775,
|
|
"num_tokens": 21749642.0,
|
|
"step": 12535
|
|
},
|
|
{
|
|
"entropy": 5.591656494140625,
|
|
"epoch": 0.9756856642676522,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004909696345518867,
|
|
"loss": 5.3955,
|
|
"mean_token_accuracy": 0.16482315063476563,
|
|
"num_tokens": 21757962.0,
|
|
"step": 12540
|
|
},
|
|
{
|
|
"entropy": 5.629759502410889,
|
|
"epoch": 0.9760746936393697,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004909618597360258,
|
|
"loss": 5.3771,
|
|
"mean_token_accuracy": 0.17003940045833588,
|
|
"num_tokens": 21766053.0,
|
|
"step": 12545
|
|
},
|
|
{
|
|
"entropy": 5.507699871063233,
|
|
"epoch": 0.9764637230110873,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004909540816432876,
|
|
"loss": 5.3511,
|
|
"mean_token_accuracy": 0.16111702620983123,
|
|
"num_tokens": 21774280.0,
|
|
"step": 12550
|
|
},
|
|
{
|
|
"entropy": 5.573996067047119,
|
|
"epoch": 0.9768527523828049,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004909463002737897,
|
|
"loss": 5.3712,
|
|
"mean_token_accuracy": 0.1694996878504753,
|
|
"num_tokens": 21782879.0,
|
|
"step": 12555
|
|
},
|
|
{
|
|
"entropy": 5.654839944839478,
|
|
"epoch": 0.9772417817545225,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004909385156276506,
|
|
"loss": 5.4579,
|
|
"mean_token_accuracy": 0.16924386769533156,
|
|
"num_tokens": 21791294.0,
|
|
"step": 12560
|
|
},
|
|
{
|
|
"entropy": 5.591029214859009,
|
|
"epoch": 0.9776308111262401,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004909307277049881,
|
|
"loss": 5.2873,
|
|
"mean_token_accuracy": 0.17874531745910643,
|
|
"num_tokens": 21799304.0,
|
|
"step": 12565
|
|
},
|
|
{
|
|
"entropy": 5.599150848388672,
|
|
"epoch": 0.9780198404979576,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004909229365059205,
|
|
"loss": 5.5029,
|
|
"mean_token_accuracy": 0.15985802412033082,
|
|
"num_tokens": 21809024.0,
|
|
"step": 12570
|
|
},
|
|
{
|
|
"entropy": 5.582186079025268,
|
|
"epoch": 0.9784088698696751,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004909151420305661,
|
|
"loss": 5.2952,
|
|
"mean_token_accuracy": 0.17661263346672057,
|
|
"num_tokens": 21817412.0,
|
|
"step": 12575
|
|
},
|
|
{
|
|
"entropy": 5.504785776138306,
|
|
"epoch": 0.9787978992413927,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.000490907344279043,
|
|
"loss": 5.3278,
|
|
"mean_token_accuracy": 0.17064658403396607,
|
|
"num_tokens": 21825261.0,
|
|
"step": 12580
|
|
},
|
|
{
|
|
"entropy": 5.61702446937561,
|
|
"epoch": 0.9791869286131103,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004908995432514698,
|
|
"loss": 5.4527,
|
|
"mean_token_accuracy": 0.17164114564657212,
|
|
"num_tokens": 21833318.0,
|
|
"step": 12585
|
|
},
|
|
{
|
|
"entropy": 5.565180969238281,
|
|
"epoch": 0.9795759579848279,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004908917389479645,
|
|
"loss": 5.4065,
|
|
"mean_token_accuracy": 0.17269199788570405,
|
|
"num_tokens": 21841377.0,
|
|
"step": 12590
|
|
},
|
|
{
|
|
"entropy": 5.559814596176148,
|
|
"epoch": 0.9799649873565455,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004908839313686456,
|
|
"loss": 5.3641,
|
|
"mean_token_accuracy": 0.16850048750638963,
|
|
"num_tokens": 21850183.0,
|
|
"step": 12595
|
|
},
|
|
{
|
|
"entropy": 5.67911696434021,
|
|
"epoch": 0.980354016728263,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004908761205136319,
|
|
"loss": 5.4554,
|
|
"mean_token_accuracy": 0.17185364663600922,
|
|
"num_tokens": 21858108.0,
|
|
"step": 12600
|
|
},
|
|
{
|
|
"entropy": 5.575015640258789,
|
|
"epoch": 0.9807430460999805,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004908683063830414,
|
|
"loss": 5.3452,
|
|
"mean_token_accuracy": 0.16938232034444808,
|
|
"num_tokens": 21866330.0,
|
|
"step": 12605
|
|
},
|
|
{
|
|
"entropy": 5.568648910522461,
|
|
"epoch": 0.9811320754716981,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004908604889769932,
|
|
"loss": 5.4134,
|
|
"mean_token_accuracy": 0.16798173189163207,
|
|
"num_tokens": 21875254.0,
|
|
"step": 12610
|
|
},
|
|
{
|
|
"entropy": 5.618528223037719,
|
|
"epoch": 0.9815211048434157,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004908526682956054,
|
|
"loss": 5.4826,
|
|
"mean_token_accuracy": 0.16005044877529145,
|
|
"num_tokens": 21884009.0,
|
|
"step": 12615
|
|
},
|
|
{
|
|
"entropy": 5.646177816390991,
|
|
"epoch": 0.9819101342151333,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004908448443389972,
|
|
"loss": 5.4054,
|
|
"mean_token_accuracy": 0.16468650102615356,
|
|
"num_tokens": 21892428.0,
|
|
"step": 12620
|
|
},
|
|
{
|
|
"entropy": 5.6400901794433596,
|
|
"epoch": 0.9822991635868508,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004908370171072869,
|
|
"loss": 5.4489,
|
|
"mean_token_accuracy": 0.1713656887412071,
|
|
"num_tokens": 21901140.0,
|
|
"step": 12625
|
|
},
|
|
{
|
|
"entropy": 5.524168920516968,
|
|
"epoch": 0.9826881929585684,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004908291866005933,
|
|
"loss": 5.3428,
|
|
"mean_token_accuracy": 0.1827618509531021,
|
|
"num_tokens": 21909072.0,
|
|
"step": 12630
|
|
},
|
|
{
|
|
"entropy": 5.499984264373779,
|
|
"epoch": 0.9830772223302859,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004908213528190355,
|
|
"loss": 5.3942,
|
|
"mean_token_accuracy": 0.16729398667812348,
|
|
"num_tokens": 21917873.0,
|
|
"step": 12635
|
|
},
|
|
{
|
|
"entropy": 5.642496728897095,
|
|
"epoch": 0.9834662517020035,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004908135157627321,
|
|
"loss": 5.5039,
|
|
"mean_token_accuracy": 0.16090389639139174,
|
|
"num_tokens": 21927302.0,
|
|
"step": 12640
|
|
},
|
|
{
|
|
"entropy": 5.616642904281616,
|
|
"epoch": 0.9838552810737211,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004908056754318022,
|
|
"loss": 5.4414,
|
|
"mean_token_accuracy": 0.1711207300424576,
|
|
"num_tokens": 21936440.0,
|
|
"step": 12645
|
|
},
|
|
{
|
|
"entropy": 5.565749645233154,
|
|
"epoch": 0.9842443104454386,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004907978318263646,
|
|
"loss": 5.3079,
|
|
"mean_token_accuracy": 0.16842927783727646,
|
|
"num_tokens": 21944655.0,
|
|
"step": 12650
|
|
},
|
|
{
|
|
"entropy": 5.664102029800415,
|
|
"epoch": 0.9846333398171562,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004907899849465383,
|
|
"loss": 5.5415,
|
|
"mean_token_accuracy": 0.16499512493610383,
|
|
"num_tokens": 21953202.0,
|
|
"step": 12655
|
|
},
|
|
{
|
|
"entropy": 5.607707691192627,
|
|
"epoch": 0.9850223691888738,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004907821347924424,
|
|
"loss": 5.4077,
|
|
"mean_token_accuracy": 0.16860270798206328,
|
|
"num_tokens": 21961889.0,
|
|
"step": 12660
|
|
},
|
|
{
|
|
"entropy": 5.5387133121490475,
|
|
"epoch": 0.9854113985605913,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004907742813641963,
|
|
"loss": 5.2683,
|
|
"mean_token_accuracy": 0.17518474757671357,
|
|
"num_tokens": 21970864.0,
|
|
"step": 12665
|
|
},
|
|
{
|
|
"entropy": 5.5290234088897705,
|
|
"epoch": 0.9858004279323089,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004907664246619187,
|
|
"loss": 5.3742,
|
|
"mean_token_accuracy": 0.16862202137708665,
|
|
"num_tokens": 21979271.0,
|
|
"step": 12670
|
|
},
|
|
{
|
|
"entropy": 5.556199789047241,
|
|
"epoch": 0.9861894573040264,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004907585646857293,
|
|
"loss": 5.2483,
|
|
"mean_token_accuracy": 0.17392691522836684,
|
|
"num_tokens": 21987321.0,
|
|
"step": 12675
|
|
},
|
|
{
|
|
"entropy": 5.612700462341309,
|
|
"epoch": 0.986578486675744,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004907507014357467,
|
|
"loss": 5.5053,
|
|
"mean_token_accuracy": 0.16294969171285628,
|
|
"num_tokens": 21996094.0,
|
|
"step": 12680
|
|
},
|
|
{
|
|
"entropy": 5.541552543640137,
|
|
"epoch": 0.9869675160474616,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004907428349120909,
|
|
"loss": 5.3535,
|
|
"mean_token_accuracy": 0.16713285595178604,
|
|
"num_tokens": 22004095.0,
|
|
"step": 12685
|
|
},
|
|
{
|
|
"entropy": 5.634124612808227,
|
|
"epoch": 0.9873565454191792,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004907349651148809,
|
|
"loss": 5.4669,
|
|
"mean_token_accuracy": 0.1649239957332611,
|
|
"num_tokens": 22013371.0,
|
|
"step": 12690
|
|
},
|
|
{
|
|
"entropy": 5.548127555847168,
|
|
"epoch": 0.9877455747908968,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004907270920442361,
|
|
"loss": 5.3348,
|
|
"mean_token_accuracy": 0.16820223927497863,
|
|
"num_tokens": 22022313.0,
|
|
"step": 12695
|
|
},
|
|
{
|
|
"entropy": 5.640724039077758,
|
|
"epoch": 0.9881346041626142,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004907192157002762,
|
|
"loss": 5.5035,
|
|
"mean_token_accuracy": 0.16597417145967483,
|
|
"num_tokens": 22031690.0,
|
|
"step": 12700
|
|
},
|
|
{
|
|
"entropy": 5.720732975006103,
|
|
"epoch": 0.9885236335343318,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004907113360831204,
|
|
"loss": 5.5498,
|
|
"mean_token_accuracy": 0.15509618520736695,
|
|
"num_tokens": 22040957.0,
|
|
"step": 12705
|
|
},
|
|
{
|
|
"entropy": 5.640105438232422,
|
|
"epoch": 0.9889126629060494,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004907034531928886,
|
|
"loss": 5.384,
|
|
"mean_token_accuracy": 0.16889772564172745,
|
|
"num_tokens": 22049623.0,
|
|
"step": 12710
|
|
},
|
|
{
|
|
"entropy": 5.541781282424926,
|
|
"epoch": 0.989301692277767,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004906955670297001,
|
|
"loss": 5.3755,
|
|
"mean_token_accuracy": 0.16839928478002547,
|
|
"num_tokens": 22058205.0,
|
|
"step": 12715
|
|
},
|
|
{
|
|
"entropy": 5.555943965911865,
|
|
"epoch": 0.9896907216494846,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004906876775936746,
|
|
"loss": 5.2751,
|
|
"mean_token_accuracy": 0.17056004852056503,
|
|
"num_tokens": 22067375.0,
|
|
"step": 12720
|
|
},
|
|
{
|
|
"entropy": 5.523751258850098,
|
|
"epoch": 0.990079751021202,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004906797848849321,
|
|
"loss": 5.3152,
|
|
"mean_token_accuracy": 0.1756708651781082,
|
|
"num_tokens": 22075670.0,
|
|
"step": 12725
|
|
},
|
|
{
|
|
"entropy": 5.517127323150635,
|
|
"epoch": 0.9904687803929196,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.000490671888903592,
|
|
"loss": 5.3986,
|
|
"mean_token_accuracy": 0.16902980208396912,
|
|
"num_tokens": 22084360.0,
|
|
"step": 12730
|
|
},
|
|
{
|
|
"entropy": 5.547106170654297,
|
|
"epoch": 0.9908578097646372,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004906639896497744,
|
|
"loss": 5.4079,
|
|
"mean_token_accuracy": 0.1749236837029457,
|
|
"num_tokens": 22092666.0,
|
|
"step": 12735
|
|
},
|
|
{
|
|
"entropy": 5.639094638824463,
|
|
"epoch": 0.9912468391363548,
|
|
"grad_norm": 3.21875,
|
|
"learning_rate": 0.0004906560871235988,
|
|
"loss": 5.5243,
|
|
"mean_token_accuracy": 0.16201450526714326,
|
|
"num_tokens": 22101311.0,
|
|
"step": 12740
|
|
},
|
|
{
|
|
"entropy": 5.6404026508331295,
|
|
"epoch": 0.9916358685080724,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004906481813251854,
|
|
"loss": 5.3512,
|
|
"mean_token_accuracy": 0.17302687615156173,
|
|
"num_tokens": 22109640.0,
|
|
"step": 12745
|
|
},
|
|
{
|
|
"entropy": 5.558566522598267,
|
|
"epoch": 0.9920248978797899,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004906402722546542,
|
|
"loss": 5.3578,
|
|
"mean_token_accuracy": 0.16336167603731155,
|
|
"num_tokens": 22118721.0,
|
|
"step": 12750
|
|
},
|
|
{
|
|
"entropy": 5.5309693813323975,
|
|
"epoch": 0.9924139272515075,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.000490632359912125,
|
|
"loss": 5.3549,
|
|
"mean_token_accuracy": 0.16795935928821565,
|
|
"num_tokens": 22126745.0,
|
|
"step": 12755
|
|
},
|
|
{
|
|
"entropy": 5.620975685119629,
|
|
"epoch": 0.992802956623225,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.000490624444297718,
|
|
"loss": 5.4324,
|
|
"mean_token_accuracy": 0.16674798727035522,
|
|
"num_tokens": 22135010.0,
|
|
"step": 12760
|
|
},
|
|
{
|
|
"entropy": 5.562928485870361,
|
|
"epoch": 0.9931919859949426,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004906165254115533,
|
|
"loss": 5.3876,
|
|
"mean_token_accuracy": 0.1693186119198799,
|
|
"num_tokens": 22144339.0,
|
|
"step": 12765
|
|
},
|
|
{
|
|
"entropy": 5.504650115966797,
|
|
"epoch": 0.9935810153666602,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.000490608603253751,
|
|
"loss": 5.3311,
|
|
"mean_token_accuracy": 0.17818619459867477,
|
|
"num_tokens": 22153405.0,
|
|
"step": 12770
|
|
},
|
|
{
|
|
"entropy": 5.613975858688354,
|
|
"epoch": 0.9939700447383778,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004906006778244312,
|
|
"loss": 5.3972,
|
|
"mean_token_accuracy": 0.16567289531230928,
|
|
"num_tokens": 22161392.0,
|
|
"step": 12775
|
|
},
|
|
{
|
|
"entropy": 5.626464748382569,
|
|
"epoch": 0.9943590741100953,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004905927491237145,
|
|
"loss": 5.3751,
|
|
"mean_token_accuracy": 0.16952494531869888,
|
|
"num_tokens": 22170635.0,
|
|
"step": 12780
|
|
},
|
|
{
|
|
"entropy": 5.496331119537354,
|
|
"epoch": 0.9947481034818129,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004905848171517208,
|
|
"loss": 5.2583,
|
|
"mean_token_accuracy": 0.17667841017246247,
|
|
"num_tokens": 22178629.0,
|
|
"step": 12785
|
|
},
|
|
{
|
|
"entropy": 5.4876610279083256,
|
|
"epoch": 0.9951371328535304,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004905768819085706,
|
|
"loss": 5.3403,
|
|
"mean_token_accuracy": 0.16736946552991866,
|
|
"num_tokens": 22187142.0,
|
|
"step": 12790
|
|
},
|
|
{
|
|
"entropy": 5.61784143447876,
|
|
"epoch": 0.995526162225248,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004905689433943846,
|
|
"loss": 5.4147,
|
|
"mean_token_accuracy": 0.16835962533950805,
|
|
"num_tokens": 22195249.0,
|
|
"step": 12795
|
|
},
|
|
{
|
|
"entropy": 5.604678726196289,
|
|
"epoch": 0.9959151915969656,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004905610016092828,
|
|
"loss": 5.4356,
|
|
"mean_token_accuracy": 0.17299420088529588,
|
|
"num_tokens": 22203621.0,
|
|
"step": 12800
|
|
},
|
|
{
|
|
"entropy": 5.513427066802978,
|
|
"epoch": 0.9963042209686831,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004905530565533859,
|
|
"loss": 5.3902,
|
|
"mean_token_accuracy": 0.17429412454366683,
|
|
"num_tokens": 22212547.0,
|
|
"step": 12805
|
|
},
|
|
{
|
|
"entropy": 5.576586627960205,
|
|
"epoch": 0.9966932503404007,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004905451082268146,
|
|
"loss": 5.3753,
|
|
"mean_token_accuracy": 0.16535618603229524,
|
|
"num_tokens": 22221642.0,
|
|
"step": 12810
|
|
},
|
|
{
|
|
"entropy": 5.57655897140503,
|
|
"epoch": 0.9970822797121183,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004905371566296891,
|
|
"loss": 5.4221,
|
|
"mean_token_accuracy": 0.16553240567445754,
|
|
"num_tokens": 22230227.0,
|
|
"step": 12815
|
|
},
|
|
{
|
|
"entropy": 5.546317768096924,
|
|
"epoch": 0.9974713090838359,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004905292017621305,
|
|
"loss": 5.379,
|
|
"mean_token_accuracy": 0.17151281237602234,
|
|
"num_tokens": 22238973.0,
|
|
"step": 12820
|
|
},
|
|
{
|
|
"entropy": 5.574538230895996,
|
|
"epoch": 0.9978603384555534,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004905212436242593,
|
|
"loss": 5.3664,
|
|
"mean_token_accuracy": 0.17034893482923508,
|
|
"num_tokens": 22247613.0,
|
|
"step": 12825
|
|
},
|
|
{
|
|
"entropy": 5.531944751739502,
|
|
"epoch": 0.9982493678272709,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004905132822161962,
|
|
"loss": 5.4013,
|
|
"mean_token_accuracy": 0.1644030660390854,
|
|
"num_tokens": 22255707.0,
|
|
"step": 12830
|
|
},
|
|
{
|
|
"entropy": 5.529854869842529,
|
|
"epoch": 0.9986383971989885,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004905053175380621,
|
|
"loss": 5.2829,
|
|
"mean_token_accuracy": 0.17318745702505112,
|
|
"num_tokens": 22264524.0,
|
|
"step": 12835
|
|
},
|
|
{
|
|
"entropy": 5.589191246032715,
|
|
"epoch": 0.9990274265707061,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004904973495899778,
|
|
"loss": 5.4015,
|
|
"mean_token_accuracy": 0.1655420944094658,
|
|
"num_tokens": 22272973.0,
|
|
"step": 12840
|
|
},
|
|
{
|
|
"entropy": 5.55372052192688,
|
|
"epoch": 0.9994164559424237,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004904893783720642,
|
|
"loss": 5.4276,
|
|
"mean_token_accuracy": 0.16893602758646012,
|
|
"num_tokens": 22281545.0,
|
|
"step": 12845
|
|
},
|
|
{
|
|
"entropy": 5.563304615020752,
|
|
"epoch": 0.9998054853141413,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004904814038844424,
|
|
"loss": 5.4281,
|
|
"mean_token_accuracy": 0.17418748140335083,
|
|
"num_tokens": 22289835.0,
|
|
"step": 12850
|
|
},
|
|
{
|
|
"entropy": 5.521205902099609,
|
|
"epoch": 1.000155611748687,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004904734261272332,
|
|
"loss": 5.3891,
|
|
"mean_token_accuracy": 0.16933360861407387,
|
|
"num_tokens": 22297794.0,
|
|
"step": 12855
|
|
},
|
|
{
|
|
"entropy": 5.524118947982788,
|
|
"epoch": 1.0005446411204046,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004904654451005576,
|
|
"loss": 5.3053,
|
|
"mean_token_accuracy": 0.1667938694357872,
|
|
"num_tokens": 22305637.0,
|
|
"step": 12860
|
|
},
|
|
{
|
|
"entropy": 5.5762371063232425,
|
|
"epoch": 1.0009336704921221,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004904574608045369,
|
|
"loss": 5.3809,
|
|
"mean_token_accuracy": 0.16399641185998917,
|
|
"num_tokens": 22314796.0,
|
|
"step": 12865
|
|
},
|
|
{
|
|
"entropy": 5.551935291290283,
|
|
"epoch": 1.0013226998638398,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004904494732392923,
|
|
"loss": 5.3254,
|
|
"mean_token_accuracy": 0.16489121317863464,
|
|
"num_tokens": 22324522.0,
|
|
"step": 12870
|
|
},
|
|
{
|
|
"entropy": 5.583127498626709,
|
|
"epoch": 1.0017117292355573,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004904414824049448,
|
|
"loss": 5.3107,
|
|
"mean_token_accuracy": 0.17289249002933502,
|
|
"num_tokens": 22333404.0,
|
|
"step": 12875
|
|
},
|
|
{
|
|
"entropy": 5.531590461730957,
|
|
"epoch": 1.0021007586072748,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004904334883016156,
|
|
"loss": 5.4215,
|
|
"mean_token_accuracy": 0.16096602827310563,
|
|
"num_tokens": 22343364.0,
|
|
"step": 12880
|
|
},
|
|
{
|
|
"entropy": 5.633839654922485,
|
|
"epoch": 1.0024897879789925,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004904254909294261,
|
|
"loss": 5.3302,
|
|
"mean_token_accuracy": 0.1673327311873436,
|
|
"num_tokens": 22352854.0,
|
|
"step": 12885
|
|
},
|
|
{
|
|
"entropy": 5.585352230072021,
|
|
"epoch": 1.00287881735071,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004904174902884978,
|
|
"loss": 5.2469,
|
|
"mean_token_accuracy": 0.17581924498081208,
|
|
"num_tokens": 22361916.0,
|
|
"step": 12890
|
|
},
|
|
{
|
|
"entropy": 5.492735099792481,
|
|
"epoch": 1.0032678467224276,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004904094863789519,
|
|
"loss": 5.3255,
|
|
"mean_token_accuracy": 0.167428807169199,
|
|
"num_tokens": 22370848.0,
|
|
"step": 12895
|
|
},
|
|
{
|
|
"entropy": 5.497122097015381,
|
|
"epoch": 1.0036568760941451,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.00049040147920091,
|
|
"loss": 5.2529,
|
|
"mean_token_accuracy": 0.1785206213593483,
|
|
"num_tokens": 22379945.0,
|
|
"step": 12900
|
|
},
|
|
{
|
|
"entropy": 5.555041217803955,
|
|
"epoch": 1.0040459054658626,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004903934687544933,
|
|
"loss": 5.2859,
|
|
"mean_token_accuracy": 0.1729058489203453,
|
|
"num_tokens": 22388795.0,
|
|
"step": 12905
|
|
},
|
|
{
|
|
"entropy": 5.58409013748169,
|
|
"epoch": 1.0044349348375803,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004903854550398237,
|
|
"loss": 5.3286,
|
|
"mean_token_accuracy": 0.17441962510347367,
|
|
"num_tokens": 22396960.0,
|
|
"step": 12910
|
|
},
|
|
{
|
|
"entropy": 5.5396336078643795,
|
|
"epoch": 1.0048239642092978,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004903774380570226,
|
|
"loss": 5.2166,
|
|
"mean_token_accuracy": 0.17924095094203948,
|
|
"num_tokens": 22404698.0,
|
|
"step": 12915
|
|
},
|
|
{
|
|
"entropy": 5.519770288467408,
|
|
"epoch": 1.0052129935810155,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004903694178062117,
|
|
"loss": 5.2649,
|
|
"mean_token_accuracy": 0.16885225474834442,
|
|
"num_tokens": 22413391.0,
|
|
"step": 12920
|
|
},
|
|
{
|
|
"entropy": 5.59088659286499,
|
|
"epoch": 1.005602022952733,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004903613942875126,
|
|
"loss": 5.3689,
|
|
"mean_token_accuracy": 0.16756330281496049,
|
|
"num_tokens": 22421357.0,
|
|
"step": 12925
|
|
},
|
|
{
|
|
"entropy": 5.522199535369873,
|
|
"epoch": 1.0059910523244504,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004903533675010472,
|
|
"loss": 5.2402,
|
|
"mean_token_accuracy": 0.17148982286453246,
|
|
"num_tokens": 22430286.0,
|
|
"step": 12930
|
|
},
|
|
{
|
|
"entropy": 5.498510885238647,
|
|
"epoch": 1.006380081696168,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004903453374469373,
|
|
"loss": 5.3072,
|
|
"mean_token_accuracy": 0.17554282248020173,
|
|
"num_tokens": 22439128.0,
|
|
"step": 12935
|
|
},
|
|
{
|
|
"entropy": 5.548002052307129,
|
|
"epoch": 1.0067691110678856,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004903373041253045,
|
|
"loss": 5.2589,
|
|
"mean_token_accuracy": 0.1688343971967697,
|
|
"num_tokens": 22447724.0,
|
|
"step": 12940
|
|
},
|
|
{
|
|
"entropy": 5.5518271923065186,
|
|
"epoch": 1.0071581404396033,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004903292675362709,
|
|
"loss": 5.3047,
|
|
"mean_token_accuracy": 0.17320431768894196,
|
|
"num_tokens": 22456792.0,
|
|
"step": 12945
|
|
},
|
|
{
|
|
"entropy": 5.446905088424683,
|
|
"epoch": 1.0075471698113208,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004903212276799584,
|
|
"loss": 5.2342,
|
|
"mean_token_accuracy": 0.17724946439266204,
|
|
"num_tokens": 22465465.0,
|
|
"step": 12950
|
|
},
|
|
{
|
|
"entropy": 5.501704168319702,
|
|
"epoch": 1.0079361991830382,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004903131845564889,
|
|
"loss": 5.2831,
|
|
"mean_token_accuracy": 0.1737855315208435,
|
|
"num_tokens": 22474498.0,
|
|
"step": 12955
|
|
},
|
|
{
|
|
"entropy": 5.480178499221802,
|
|
"epoch": 1.008325228554756,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004903051381659847,
|
|
"loss": 5.2168,
|
|
"mean_token_accuracy": 0.17675953656435012,
|
|
"num_tokens": 22482926.0,
|
|
"step": 12960
|
|
},
|
|
{
|
|
"entropy": 5.51214280128479,
|
|
"epoch": 1.0087142579264734,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.0004902970885085677,
|
|
"loss": 5.2527,
|
|
"mean_token_accuracy": 0.17354887425899507,
|
|
"num_tokens": 22491984.0,
|
|
"step": 12965
|
|
},
|
|
{
|
|
"entropy": 5.5587738990783695,
|
|
"epoch": 1.009103287298191,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.00049028903558436,
|
|
"loss": 5.2774,
|
|
"mean_token_accuracy": 0.1709383174777031,
|
|
"num_tokens": 22501411.0,
|
|
"step": 12970
|
|
},
|
|
{
|
|
"entropy": 5.599527645111084,
|
|
"epoch": 1.0094923166699086,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004902809793934838,
|
|
"loss": 5.3921,
|
|
"mean_token_accuracy": 0.17097476199269296,
|
|
"num_tokens": 22510289.0,
|
|
"step": 12975
|
|
},
|
|
{
|
|
"entropy": 5.573763227462768,
|
|
"epoch": 1.009881346041626,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004902729199360615,
|
|
"loss": 5.4092,
|
|
"mean_token_accuracy": 0.16954686790704726,
|
|
"num_tokens": 22519061.0,
|
|
"step": 12980
|
|
},
|
|
{
|
|
"entropy": 5.623443698883056,
|
|
"epoch": 1.0102703754133437,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004902648572122153,
|
|
"loss": 5.4159,
|
|
"mean_token_accuracy": 0.16341166198253632,
|
|
"num_tokens": 22528207.0,
|
|
"step": 12985
|
|
},
|
|
{
|
|
"entropy": 5.678278112411499,
|
|
"epoch": 1.0106594047850612,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004902567912220674,
|
|
"loss": 5.3627,
|
|
"mean_token_accuracy": 0.17135710418224334,
|
|
"num_tokens": 22537055.0,
|
|
"step": 12990
|
|
},
|
|
{
|
|
"entropy": 5.484136247634888,
|
|
"epoch": 1.011048434156779,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004902487219657404,
|
|
"loss": 5.3185,
|
|
"mean_token_accuracy": 0.16931733042001723,
|
|
"num_tokens": 22545239.0,
|
|
"step": 12995
|
|
},
|
|
{
|
|
"entropy": 5.575659942626953,
|
|
"epoch": 1.0114374635284964,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004902406494433566,
|
|
"loss": 5.4656,
|
|
"mean_token_accuracy": 0.15858107060194016,
|
|
"num_tokens": 22554850.0,
|
|
"step": 13000
|
|
},
|
|
{
|
|
"entropy": 5.607913684844971,
|
|
"epoch": 1.0118264929002139,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004902325736550386,
|
|
"loss": 5.3069,
|
|
"mean_token_accuracy": 0.168249773979187,
|
|
"num_tokens": 22563799.0,
|
|
"step": 13005
|
|
},
|
|
{
|
|
"entropy": 5.5935163497924805,
|
|
"epoch": 1.0122155222719316,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004902244946009088,
|
|
"loss": 5.4982,
|
|
"mean_token_accuracy": 0.16486130356788636,
|
|
"num_tokens": 22572699.0,
|
|
"step": 13010
|
|
},
|
|
{
|
|
"entropy": 5.699872589111328,
|
|
"epoch": 1.012604551643649,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004902164122810899,
|
|
"loss": 5.4254,
|
|
"mean_token_accuracy": 0.16156801134347915,
|
|
"num_tokens": 22580916.0,
|
|
"step": 13015
|
|
},
|
|
{
|
|
"entropy": 5.599102592468261,
|
|
"epoch": 1.0129935810153667,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004902083266957045,
|
|
"loss": 5.3041,
|
|
"mean_token_accuracy": 0.17652194797992707,
|
|
"num_tokens": 22589525.0,
|
|
"step": 13020
|
|
},
|
|
{
|
|
"entropy": 5.562756013870239,
|
|
"epoch": 1.0133826103870842,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004902002378448753,
|
|
"loss": 5.3147,
|
|
"mean_token_accuracy": 0.1701074570417404,
|
|
"num_tokens": 22597929.0,
|
|
"step": 13025
|
|
},
|
|
{
|
|
"entropy": 5.572381925582886,
|
|
"epoch": 1.0137716397588017,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.000490192145728725,
|
|
"loss": 5.3423,
|
|
"mean_token_accuracy": 0.16986422687768937,
|
|
"num_tokens": 22606500.0,
|
|
"step": 13030
|
|
},
|
|
{
|
|
"entropy": 5.5856163024902346,
|
|
"epoch": 1.0141606691305194,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004901840503473764,
|
|
"loss": 5.3023,
|
|
"mean_token_accuracy": 0.1720694214105606,
|
|
"num_tokens": 22614626.0,
|
|
"step": 13035
|
|
},
|
|
{
|
|
"entropy": 5.555132865905762,
|
|
"epoch": 1.0145496985022369,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004901759517009522,
|
|
"loss": 5.3449,
|
|
"mean_token_accuracy": 0.16404235512018203,
|
|
"num_tokens": 22623488.0,
|
|
"step": 13040
|
|
},
|
|
{
|
|
"entropy": 5.514724254608154,
|
|
"epoch": 1.0149387278739546,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004901678497895755,
|
|
"loss": 5.2677,
|
|
"mean_token_accuracy": 0.17093850672245026,
|
|
"num_tokens": 22632413.0,
|
|
"step": 13045
|
|
},
|
|
{
|
|
"entropy": 5.612932395935059,
|
|
"epoch": 1.015327757245672,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004901597446133692,
|
|
"loss": 5.4009,
|
|
"mean_token_accuracy": 0.16236702352762222,
|
|
"num_tokens": 22640982.0,
|
|
"step": 13050
|
|
},
|
|
{
|
|
"entropy": 5.627354383468628,
|
|
"epoch": 1.0157167866173895,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004901516361724564,
|
|
"loss": 5.3796,
|
|
"mean_token_accuracy": 0.16859890520572662,
|
|
"num_tokens": 22649809.0,
|
|
"step": 13055
|
|
},
|
|
{
|
|
"entropy": 5.535728788375854,
|
|
"epoch": 1.0161058159891072,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004901435244669597,
|
|
"loss": 5.2795,
|
|
"mean_token_accuracy": 0.16824382692575454,
|
|
"num_tokens": 22658292.0,
|
|
"step": 13060
|
|
},
|
|
{
|
|
"entropy": 5.60081639289856,
|
|
"epoch": 1.0164948453608247,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004901354094970025,
|
|
"loss": 5.3647,
|
|
"mean_token_accuracy": 0.17014574706554414,
|
|
"num_tokens": 22667063.0,
|
|
"step": 13065
|
|
},
|
|
{
|
|
"entropy": 5.50766077041626,
|
|
"epoch": 1.0168838747325424,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004901272912627081,
|
|
"loss": 5.2963,
|
|
"mean_token_accuracy": 0.1683926209807396,
|
|
"num_tokens": 22676213.0,
|
|
"step": 13070
|
|
},
|
|
{
|
|
"entropy": 5.399009561538696,
|
|
"epoch": 1.0172729041042599,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004901191697641992,
|
|
"loss": 5.2223,
|
|
"mean_token_accuracy": 0.17431732416152954,
|
|
"num_tokens": 22684948.0,
|
|
"step": 13075
|
|
},
|
|
{
|
|
"entropy": 5.559270000457763,
|
|
"epoch": 1.0176619334759773,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004901110450015994,
|
|
"loss": 5.3226,
|
|
"mean_token_accuracy": 0.16503900289535522,
|
|
"num_tokens": 22693218.0,
|
|
"step": 13080
|
|
},
|
|
{
|
|
"entropy": 5.565805530548095,
|
|
"epoch": 1.018050962847695,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004901029169750319,
|
|
"loss": 5.1915,
|
|
"mean_token_accuracy": 0.17868994325399398,
|
|
"num_tokens": 22701572.0,
|
|
"step": 13085
|
|
},
|
|
{
|
|
"entropy": 5.513815641403198,
|
|
"epoch": 1.0184399922194125,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004900947856846201,
|
|
"loss": 5.2641,
|
|
"mean_token_accuracy": 0.17290471345186234,
|
|
"num_tokens": 22709498.0,
|
|
"step": 13090
|
|
},
|
|
{
|
|
"entropy": 5.539499950408936,
|
|
"epoch": 1.0188290215911302,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.000490086651130487,
|
|
"loss": 5.2725,
|
|
"mean_token_accuracy": 0.17217059284448624,
|
|
"num_tokens": 22717922.0,
|
|
"step": 13095
|
|
},
|
|
{
|
|
"entropy": 5.584228277206421,
|
|
"epoch": 1.0192180509628477,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004900785133127566,
|
|
"loss": 5.298,
|
|
"mean_token_accuracy": 0.174782095849514,
|
|
"num_tokens": 22725933.0,
|
|
"step": 13100
|
|
},
|
|
{
|
|
"entropy": 5.56052885055542,
|
|
"epoch": 1.0196070803345652,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.000490070372231552,
|
|
"loss": 5.2871,
|
|
"mean_token_accuracy": 0.17098522782325745,
|
|
"num_tokens": 22734198.0,
|
|
"step": 13105
|
|
},
|
|
{
|
|
"entropy": 5.549863290786743,
|
|
"epoch": 1.0199961097062828,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004900622278869968,
|
|
"loss": 5.3158,
|
|
"mean_token_accuracy": 0.17081442326307297,
|
|
"num_tokens": 22742419.0,
|
|
"step": 13110
|
|
},
|
|
{
|
|
"entropy": 5.590565347671509,
|
|
"epoch": 1.0203851390780003,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004900540802792146,
|
|
"loss": 5.2721,
|
|
"mean_token_accuracy": 0.17368832975625992,
|
|
"num_tokens": 22750576.0,
|
|
"step": 13115
|
|
},
|
|
{
|
|
"entropy": 5.571694278717041,
|
|
"epoch": 1.020774168449718,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.000490045929408329,
|
|
"loss": 5.443,
|
|
"mean_token_accuracy": 0.17148976922035217,
|
|
"num_tokens": 22759604.0,
|
|
"step": 13120
|
|
},
|
|
{
|
|
"entropy": 5.519921159744262,
|
|
"epoch": 1.0211631978214355,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004900377752744637,
|
|
"loss": 5.2,
|
|
"mean_token_accuracy": 0.1760471448302269,
|
|
"num_tokens": 22768305.0,
|
|
"step": 13125
|
|
},
|
|
{
|
|
"entropy": 5.598498058319092,
|
|
"epoch": 1.021552227193153,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004900296178777426,
|
|
"loss": 5.3585,
|
|
"mean_token_accuracy": 0.16258263885974883,
|
|
"num_tokens": 22777364.0,
|
|
"step": 13130
|
|
},
|
|
{
|
|
"entropy": 5.523081064224243,
|
|
"epoch": 1.0219412565648707,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.000490021457218289,
|
|
"loss": 5.2833,
|
|
"mean_token_accuracy": 0.17148469686508178,
|
|
"num_tokens": 22786192.0,
|
|
"step": 13135
|
|
},
|
|
{
|
|
"entropy": 5.619490909576416,
|
|
"epoch": 1.0223302859365881,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004900132932962272,
|
|
"loss": 5.3412,
|
|
"mean_token_accuracy": 0.17192437499761581,
|
|
"num_tokens": 22794244.0,
|
|
"step": 13140
|
|
},
|
|
{
|
|
"entropy": 5.561174011230468,
|
|
"epoch": 1.0227193153083058,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.000490005126111681,
|
|
"loss": 5.3224,
|
|
"mean_token_accuracy": 0.17580875903367996,
|
|
"num_tokens": 22802543.0,
|
|
"step": 13145
|
|
},
|
|
{
|
|
"entropy": 5.4827522277832035,
|
|
"epoch": 1.0231083446800233,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.000489996955664774,
|
|
"loss": 5.3307,
|
|
"mean_token_accuracy": 0.1704048439860344,
|
|
"num_tokens": 22811267.0,
|
|
"step": 13150
|
|
},
|
|
{
|
|
"entropy": 5.540749597549438,
|
|
"epoch": 1.023497374051741,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004899887819556306,
|
|
"loss": 5.2402,
|
|
"mean_token_accuracy": 0.17342166900634765,
|
|
"num_tokens": 22820196.0,
|
|
"step": 13155
|
|
},
|
|
{
|
|
"entropy": 5.611469745635986,
|
|
"epoch": 1.0238864034234585,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004899806049843745,
|
|
"loss": 5.4058,
|
|
"mean_token_accuracy": 0.16959395557641982,
|
|
"num_tokens": 22828498.0,
|
|
"step": 13160
|
|
},
|
|
{
|
|
"entropy": 5.590411138534546,
|
|
"epoch": 1.024275432795176,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004899724247511299,
|
|
"loss": 5.3153,
|
|
"mean_token_accuracy": 0.17874199599027635,
|
|
"num_tokens": 22837411.0,
|
|
"step": 13165
|
|
},
|
|
{
|
|
"entropy": 5.43924765586853,
|
|
"epoch": 1.0246644621668937,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.000489964241256021,
|
|
"loss": 5.2425,
|
|
"mean_token_accuracy": 0.174375019967556,
|
|
"num_tokens": 22846265.0,
|
|
"step": 13170
|
|
},
|
|
{
|
|
"entropy": 5.445515918731689,
|
|
"epoch": 1.0250534915386111,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004899560544991718,
|
|
"loss": 5.2115,
|
|
"mean_token_accuracy": 0.17506559789180756,
|
|
"num_tokens": 22854489.0,
|
|
"step": 13175
|
|
},
|
|
{
|
|
"entropy": 5.581643438339233,
|
|
"epoch": 1.0254425209103288,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004899478644807068,
|
|
"loss": 5.4031,
|
|
"mean_token_accuracy": 0.1649957537651062,
|
|
"num_tokens": 22863269.0,
|
|
"step": 13180
|
|
},
|
|
{
|
|
"entropy": 5.599470853805542,
|
|
"epoch": 1.0258315502820463,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004899396712007498,
|
|
"loss": 5.3845,
|
|
"mean_token_accuracy": 0.1650130942463875,
|
|
"num_tokens": 22872304.0,
|
|
"step": 13185
|
|
},
|
|
{
|
|
"entropy": 5.527854061126709,
|
|
"epoch": 1.0262205796537638,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004899314746594256,
|
|
"loss": 5.1749,
|
|
"mean_token_accuracy": 0.17417426705360411,
|
|
"num_tokens": 22881409.0,
|
|
"step": 13190
|
|
},
|
|
{
|
|
"entropy": 5.547877550125122,
|
|
"epoch": 1.0266096090254815,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004899232748568584,
|
|
"loss": 5.2728,
|
|
"mean_token_accuracy": 0.17250572741031647,
|
|
"num_tokens": 22889560.0,
|
|
"step": 13195
|
|
},
|
|
{
|
|
"entropy": 5.515940761566162,
|
|
"epoch": 1.026998638397199,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004899150717931724,
|
|
"loss": 5.3383,
|
|
"mean_token_accuracy": 0.16536664813756943,
|
|
"num_tokens": 22897434.0,
|
|
"step": 13200
|
|
},
|
|
{
|
|
"entropy": 5.558090734481811,
|
|
"epoch": 1.0273876677689167,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004899068654684924,
|
|
"loss": 5.3265,
|
|
"mean_token_accuracy": 0.17122836261987687,
|
|
"num_tokens": 22906050.0,
|
|
"step": 13205
|
|
},
|
|
{
|
|
"entropy": 5.543594074249268,
|
|
"epoch": 1.0277766971406341,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004898986558829428,
|
|
"loss": 5.2867,
|
|
"mean_token_accuracy": 0.17371345311403275,
|
|
"num_tokens": 22914118.0,
|
|
"step": 13210
|
|
},
|
|
{
|
|
"entropy": 5.535507440567017,
|
|
"epoch": 1.0281657265123516,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004898904430366479,
|
|
"loss": 5.3026,
|
|
"mean_token_accuracy": 0.17229761481285094,
|
|
"num_tokens": 22922539.0,
|
|
"step": 13215
|
|
},
|
|
{
|
|
"entropy": 5.513501453399658,
|
|
"epoch": 1.0285547558840693,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004898822269297328,
|
|
"loss": 5.3049,
|
|
"mean_token_accuracy": 0.16814896166324617,
|
|
"num_tokens": 22932371.0,
|
|
"step": 13220
|
|
},
|
|
{
|
|
"entropy": 5.560471725463867,
|
|
"epoch": 1.0289437852557868,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004898740075623218,
|
|
"loss": 5.3368,
|
|
"mean_token_accuracy": 0.17443976998329164,
|
|
"num_tokens": 22940608.0,
|
|
"step": 13225
|
|
},
|
|
{
|
|
"entropy": 5.570888376235962,
|
|
"epoch": 1.0293328146275045,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004898657849345399,
|
|
"loss": 5.3154,
|
|
"mean_token_accuracy": 0.16587201207876207,
|
|
"num_tokens": 22948905.0,
|
|
"step": 13230
|
|
},
|
|
{
|
|
"entropy": 5.490921688079834,
|
|
"epoch": 1.029721843999222,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004898575590465116,
|
|
"loss": 5.2805,
|
|
"mean_token_accuracy": 0.17339199185371398,
|
|
"num_tokens": 22957218.0,
|
|
"step": 13235
|
|
},
|
|
{
|
|
"entropy": 5.541296672821045,
|
|
"epoch": 1.0301108733709394,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004898493298983619,
|
|
"loss": 5.4322,
|
|
"mean_token_accuracy": 0.17029115557670593,
|
|
"num_tokens": 22965700.0,
|
|
"step": 13240
|
|
},
|
|
{
|
|
"entropy": 5.665392017364502,
|
|
"epoch": 1.0304999027426571,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004898410974902155,
|
|
"loss": 5.3734,
|
|
"mean_token_accuracy": 0.1702515408396721,
|
|
"num_tokens": 22973996.0,
|
|
"step": 13245
|
|
},
|
|
{
|
|
"entropy": 5.611515378952026,
|
|
"epoch": 1.0308889321143746,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004898328618221974,
|
|
"loss": 5.3472,
|
|
"mean_token_accuracy": 0.16921236664056777,
|
|
"num_tokens": 22983142.0,
|
|
"step": 13250
|
|
},
|
|
{
|
|
"entropy": 5.511696481704712,
|
|
"epoch": 1.0312779614860923,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.0004898246228944327,
|
|
"loss": 5.3042,
|
|
"mean_token_accuracy": 0.17110096514225007,
|
|
"num_tokens": 22991263.0,
|
|
"step": 13255
|
|
},
|
|
{
|
|
"entropy": 5.589747524261474,
|
|
"epoch": 1.0316669908578098,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004898163807070461,
|
|
"loss": 5.3915,
|
|
"mean_token_accuracy": 0.16521840393543244,
|
|
"num_tokens": 23000068.0,
|
|
"step": 13260
|
|
},
|
|
{
|
|
"entropy": 5.590217065811157,
|
|
"epoch": 1.0320560202295272,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004898081352601629,
|
|
"loss": 5.2952,
|
|
"mean_token_accuracy": 0.1719805970788002,
|
|
"num_tokens": 23007935.0,
|
|
"step": 13265
|
|
},
|
|
{
|
|
"entropy": 5.508534669876099,
|
|
"epoch": 1.032445049601245,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004897998865539082,
|
|
"loss": 5.3762,
|
|
"mean_token_accuracy": 0.1628126934170723,
|
|
"num_tokens": 23017462.0,
|
|
"step": 13270
|
|
},
|
|
{
|
|
"entropy": 5.587372779846191,
|
|
"epoch": 1.0328340789729624,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004897916345884069,
|
|
"loss": 5.3703,
|
|
"mean_token_accuracy": 0.1638731062412262,
|
|
"num_tokens": 23026681.0,
|
|
"step": 13275
|
|
},
|
|
{
|
|
"entropy": 5.562488794326782,
|
|
"epoch": 1.0332231083446801,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004897833793637847,
|
|
"loss": 5.333,
|
|
"mean_token_accuracy": 0.16925524473190307,
|
|
"num_tokens": 23035720.0,
|
|
"step": 13280
|
|
},
|
|
{
|
|
"entropy": 5.599439382553101,
|
|
"epoch": 1.0336121377163976,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004897751208801665,
|
|
"loss": 5.3498,
|
|
"mean_token_accuracy": 0.16761697828769684,
|
|
"num_tokens": 23044491.0,
|
|
"step": 13285
|
|
},
|
|
{
|
|
"entropy": 5.585770988464356,
|
|
"epoch": 1.034001167088115,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004897668591376777,
|
|
"loss": 5.3603,
|
|
"mean_token_accuracy": 0.1694803535938263,
|
|
"num_tokens": 23054034.0,
|
|
"step": 13290
|
|
},
|
|
{
|
|
"entropy": 5.564758253097534,
|
|
"epoch": 1.0343901964598328,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004897585941364436,
|
|
"loss": 5.2971,
|
|
"mean_token_accuracy": 0.1661220148205757,
|
|
"num_tokens": 23062478.0,
|
|
"step": 13295
|
|
},
|
|
{
|
|
"entropy": 5.516941356658935,
|
|
"epoch": 1.0347792258315502,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004897503258765896,
|
|
"loss": 5.3332,
|
|
"mean_token_accuracy": 0.16616709232330323,
|
|
"num_tokens": 23070776.0,
|
|
"step": 13300
|
|
},
|
|
{
|
|
"entropy": 5.580062818527222,
|
|
"epoch": 1.035168255203268,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004897420543582413,
|
|
"loss": 5.3791,
|
|
"mean_token_accuracy": 0.17137093096971512,
|
|
"num_tokens": 23078459.0,
|
|
"step": 13305
|
|
},
|
|
{
|
|
"entropy": 5.574888563156128,
|
|
"epoch": 1.0355572845749854,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.000489733779581524,
|
|
"loss": 5.3411,
|
|
"mean_token_accuracy": 0.17564865797758103,
|
|
"num_tokens": 23087113.0,
|
|
"step": 13310
|
|
},
|
|
{
|
|
"entropy": 5.4958878517150875,
|
|
"epoch": 1.035946313946703,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004897255015465635,
|
|
"loss": 5.2687,
|
|
"mean_token_accuracy": 0.17245230823755264,
|
|
"num_tokens": 23095989.0,
|
|
"step": 13315
|
|
},
|
|
{
|
|
"entropy": 5.522052526473999,
|
|
"epoch": 1.0363353433184206,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004897172202534853,
|
|
"loss": 5.2964,
|
|
"mean_token_accuracy": 0.17018729597330093,
|
|
"num_tokens": 23104578.0,
|
|
"step": 13320
|
|
},
|
|
{
|
|
"entropy": 5.564993953704834,
|
|
"epoch": 1.036724372690138,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.000489708935702415,
|
|
"loss": 5.3517,
|
|
"mean_token_accuracy": 0.16749211847782136,
|
|
"num_tokens": 23114390.0,
|
|
"step": 13325
|
|
},
|
|
{
|
|
"entropy": 5.672108793258667,
|
|
"epoch": 1.0371134020618558,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004897006478934784,
|
|
"loss": 5.2382,
|
|
"mean_token_accuracy": 0.1764823541045189,
|
|
"num_tokens": 23122411.0,
|
|
"step": 13330
|
|
},
|
|
{
|
|
"entropy": 5.504877090454102,
|
|
"epoch": 1.0375024314335732,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004896923568268011,
|
|
"loss": 5.2102,
|
|
"mean_token_accuracy": 0.17106251716613768,
|
|
"num_tokens": 23130801.0,
|
|
"step": 13335
|
|
},
|
|
{
|
|
"entropy": 5.494357776641846,
|
|
"epoch": 1.0378914608052907,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.000489684062502509,
|
|
"loss": 5.2545,
|
|
"mean_token_accuracy": 0.17517763674259185,
|
|
"num_tokens": 23138578.0,
|
|
"step": 13340
|
|
},
|
|
{
|
|
"entropy": 5.535081005096435,
|
|
"epoch": 1.0382804901770084,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004896757649207281,
|
|
"loss": 5.3263,
|
|
"mean_token_accuracy": 0.1695863649249077,
|
|
"num_tokens": 23147135.0,
|
|
"step": 13345
|
|
},
|
|
{
|
|
"entropy": 5.62409987449646,
|
|
"epoch": 1.0386695195487259,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.000489667464081584,
|
|
"loss": 5.3969,
|
|
"mean_token_accuracy": 0.16792264580726624,
|
|
"num_tokens": 23155791.0,
|
|
"step": 13350
|
|
},
|
|
{
|
|
"entropy": 5.559703826904297,
|
|
"epoch": 1.0390585489204436,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004896591599852029,
|
|
"loss": 5.2531,
|
|
"mean_token_accuracy": 0.17504205256700517,
|
|
"num_tokens": 23163674.0,
|
|
"step": 13355
|
|
},
|
|
{
|
|
"entropy": 5.526022291183471,
|
|
"epoch": 1.039447578292161,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004896508526317107,
|
|
"loss": 5.3217,
|
|
"mean_token_accuracy": 0.16219640225172044,
|
|
"num_tokens": 23171931.0,
|
|
"step": 13360
|
|
},
|
|
{
|
|
"entropy": 5.580244541168213,
|
|
"epoch": 1.0398366076638785,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004896425420212334,
|
|
"loss": 5.333,
|
|
"mean_token_accuracy": 0.1642221838235855,
|
|
"num_tokens": 23180195.0,
|
|
"step": 13365
|
|
},
|
|
{
|
|
"entropy": 5.52488956451416,
|
|
"epoch": 1.0402256370355962,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004896342281538973,
|
|
"loss": 5.2704,
|
|
"mean_token_accuracy": 0.1739368423819542,
|
|
"num_tokens": 23189486.0,
|
|
"step": 13370
|
|
},
|
|
{
|
|
"entropy": 5.542613410949707,
|
|
"epoch": 1.0406146664073137,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004896259110298283,
|
|
"loss": 5.3894,
|
|
"mean_token_accuracy": 0.16582002192735673,
|
|
"num_tokens": 23198055.0,
|
|
"step": 13375
|
|
},
|
|
{
|
|
"entropy": 5.539638423919678,
|
|
"epoch": 1.0410036957790314,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004896175906491528,
|
|
"loss": 5.2664,
|
|
"mean_token_accuracy": 0.17826088666915893,
|
|
"num_tokens": 23206092.0,
|
|
"step": 13380
|
|
},
|
|
{
|
|
"entropy": 5.595705842971801,
|
|
"epoch": 1.0413927251507489,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004896092670119968,
|
|
"loss": 5.3396,
|
|
"mean_token_accuracy": 0.17463093847036362,
|
|
"num_tokens": 23214820.0,
|
|
"step": 13385
|
|
},
|
|
{
|
|
"entropy": 5.502323818206787,
|
|
"epoch": 1.0417817545224664,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004896009401184869,
|
|
"loss": 5.3084,
|
|
"mean_token_accuracy": 0.17374697476625442,
|
|
"num_tokens": 23224033.0,
|
|
"step": 13390
|
|
},
|
|
{
|
|
"entropy": 5.497268962860107,
|
|
"epoch": 1.042170783894184,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004895926099687493,
|
|
"loss": 5.2872,
|
|
"mean_token_accuracy": 0.1754576474428177,
|
|
"num_tokens": 23233074.0,
|
|
"step": 13395
|
|
},
|
|
{
|
|
"entropy": 5.507416200637818,
|
|
"epoch": 1.0425598132659015,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004895842765629104,
|
|
"loss": 5.2462,
|
|
"mean_token_accuracy": 0.17499990612268448,
|
|
"num_tokens": 23241167.0,
|
|
"step": 13400
|
|
},
|
|
{
|
|
"entropy": 5.596942138671875,
|
|
"epoch": 1.0429488426376192,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004895759399010966,
|
|
"loss": 5.2753,
|
|
"mean_token_accuracy": 0.16960269212722778,
|
|
"num_tokens": 23249601.0,
|
|
"step": 13405
|
|
},
|
|
{
|
|
"entropy": 5.550609159469604,
|
|
"epoch": 1.0433378720093367,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004895675999834345,
|
|
"loss": 5.368,
|
|
"mean_token_accuracy": 0.1588814824819565,
|
|
"num_tokens": 23257868.0,
|
|
"step": 13410
|
|
},
|
|
{
|
|
"entropy": 5.58900089263916,
|
|
"epoch": 1.0437269013810542,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004895592568100505,
|
|
"loss": 5.3533,
|
|
"mean_token_accuracy": 0.16595737785100936,
|
|
"num_tokens": 23266586.0,
|
|
"step": 13415
|
|
},
|
|
{
|
|
"entropy": 5.614063453674317,
|
|
"epoch": 1.0441159307527719,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004895509103810714,
|
|
"loss": 5.3321,
|
|
"mean_token_accuracy": 0.1688019946217537,
|
|
"num_tokens": 23275114.0,
|
|
"step": 13420
|
|
},
|
|
{
|
|
"entropy": 5.413854789733887,
|
|
"epoch": 1.0445049601244893,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004895425606966237,
|
|
"loss": 5.2248,
|
|
"mean_token_accuracy": 0.17890949547290802,
|
|
"num_tokens": 23283200.0,
|
|
"step": 13425
|
|
},
|
|
{
|
|
"entropy": 5.542884397506714,
|
|
"epoch": 1.044893989496207,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.000489534207756834,
|
|
"loss": 5.4307,
|
|
"mean_token_accuracy": 0.16368771940469742,
|
|
"num_tokens": 23291999.0,
|
|
"step": 13430
|
|
},
|
|
{
|
|
"entropy": 5.607825660705567,
|
|
"epoch": 1.0452830188679245,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004895258515618293,
|
|
"loss": 5.3143,
|
|
"mean_token_accuracy": 0.16850415319204332,
|
|
"num_tokens": 23300514.0,
|
|
"step": 13435
|
|
},
|
|
{
|
|
"entropy": 5.53573431968689,
|
|
"epoch": 1.045672048239642,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004895174921117362,
|
|
"loss": 5.2721,
|
|
"mean_token_accuracy": 0.17205916494131088,
|
|
"num_tokens": 23309543.0,
|
|
"step": 13440
|
|
},
|
|
{
|
|
"entropy": 5.466213941574097,
|
|
"epoch": 1.0460610776113597,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004895091294066816,
|
|
"loss": 5.2948,
|
|
"mean_token_accuracy": 0.1734081506729126,
|
|
"num_tokens": 23319002.0,
|
|
"step": 13445
|
|
},
|
|
{
|
|
"entropy": 5.568212270736694,
|
|
"epoch": 1.0464501069830772,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004895007634467924,
|
|
"loss": 5.346,
|
|
"mean_token_accuracy": 0.1708262339234352,
|
|
"num_tokens": 23326604.0,
|
|
"step": 13450
|
|
},
|
|
{
|
|
"entropy": 5.503519582748413,
|
|
"epoch": 1.0468391363547949,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004894923942321955,
|
|
"loss": 5.2818,
|
|
"mean_token_accuracy": 0.17666701823472977,
|
|
"num_tokens": 23335492.0,
|
|
"step": 13455
|
|
},
|
|
{
|
|
"entropy": 5.5053855895996096,
|
|
"epoch": 1.0472281657265123,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004894840217630179,
|
|
"loss": 5.3065,
|
|
"mean_token_accuracy": 0.17429608553647996,
|
|
"num_tokens": 23343693.0,
|
|
"step": 13460
|
|
},
|
|
{
|
|
"entropy": 5.522336721420288,
|
|
"epoch": 1.0476171950982298,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004894756460393868,
|
|
"loss": 5.2667,
|
|
"mean_token_accuracy": 0.17938611954450606,
|
|
"num_tokens": 23352587.0,
|
|
"step": 13465
|
|
},
|
|
{
|
|
"entropy": 5.547571134567261,
|
|
"epoch": 1.0480062244699475,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.000489467267061429,
|
|
"loss": 5.3455,
|
|
"mean_token_accuracy": 0.1718888908624649,
|
|
"num_tokens": 23361293.0,
|
|
"step": 13470
|
|
},
|
|
{
|
|
"entropy": 5.5730455875396725,
|
|
"epoch": 1.048395253841665,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004894588848292718,
|
|
"loss": 5.3243,
|
|
"mean_token_accuracy": 0.17050171196460723,
|
|
"num_tokens": 23369663.0,
|
|
"step": 13475
|
|
},
|
|
{
|
|
"entropy": 5.535304594039917,
|
|
"epoch": 1.0487842832133827,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004894504993430425,
|
|
"loss": 5.2367,
|
|
"mean_token_accuracy": 0.17066449224948882,
|
|
"num_tokens": 23378224.0,
|
|
"step": 13480
|
|
},
|
|
{
|
|
"entropy": 5.581699514389038,
|
|
"epoch": 1.0491733125851002,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.000489442110602868,
|
|
"loss": 5.4122,
|
|
"mean_token_accuracy": 0.16622019559144974,
|
|
"num_tokens": 23386693.0,
|
|
"step": 13485
|
|
},
|
|
{
|
|
"entropy": 5.533706712722778,
|
|
"epoch": 1.0495623419568176,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004894337186088759,
|
|
"loss": 5.2712,
|
|
"mean_token_accuracy": 0.1727204993367195,
|
|
"num_tokens": 23395226.0,
|
|
"step": 13490
|
|
},
|
|
{
|
|
"entropy": 5.527824020385742,
|
|
"epoch": 1.0499513713285353,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004894253233611934,
|
|
"loss": 5.2939,
|
|
"mean_token_accuracy": 0.16925432831048964,
|
|
"num_tokens": 23403779.0,
|
|
"step": 13495
|
|
},
|
|
{
|
|
"entropy": 5.560998725891113,
|
|
"epoch": 1.0503404007002528,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.000489416924859948,
|
|
"loss": 5.3993,
|
|
"mean_token_accuracy": 0.17176871448755265,
|
|
"num_tokens": 23411807.0,
|
|
"step": 13500
|
|
},
|
|
{
|
|
"entropy": 5.492605113983155,
|
|
"epoch": 1.0507294300719705,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.000489408523105267,
|
|
"loss": 5.2718,
|
|
"mean_token_accuracy": 0.16818220168352127,
|
|
"num_tokens": 23420323.0,
|
|
"step": 13505
|
|
},
|
|
{
|
|
"entropy": 5.528667259216308,
|
|
"epoch": 1.051118459443688,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004894001180972779,
|
|
"loss": 5.2788,
|
|
"mean_token_accuracy": 0.1729546681046486,
|
|
"num_tokens": 23429220.0,
|
|
"step": 13510
|
|
},
|
|
{
|
|
"entropy": 5.546587419509888,
|
|
"epoch": 1.0515074888154055,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004893917098361082,
|
|
"loss": 5.3048,
|
|
"mean_token_accuracy": 0.17642121762037277,
|
|
"num_tokens": 23438471.0,
|
|
"step": 13515
|
|
},
|
|
{
|
|
"entropy": 5.576458263397217,
|
|
"epoch": 1.0518965181871232,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004893832983218856,
|
|
"loss": 5.3738,
|
|
"mean_token_accuracy": 0.17581699937582015,
|
|
"num_tokens": 23447504.0,
|
|
"step": 13520
|
|
},
|
|
{
|
|
"entropy": 5.450729417800903,
|
|
"epoch": 1.0522855475588406,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004893748835547377,
|
|
"loss": 5.113,
|
|
"mean_token_accuracy": 0.185771644115448,
|
|
"num_tokens": 23456065.0,
|
|
"step": 13525
|
|
},
|
|
{
|
|
"entropy": 5.535451936721802,
|
|
"epoch": 1.0526745769305583,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004893664655347921,
|
|
"loss": 5.2961,
|
|
"mean_token_accuracy": 0.17600812017917633,
|
|
"num_tokens": 23463826.0,
|
|
"step": 13530
|
|
},
|
|
{
|
|
"entropy": 5.418683910369873,
|
|
"epoch": 1.0530636063022758,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004893580442621767,
|
|
"loss": 5.2655,
|
|
"mean_token_accuracy": 0.1793366938829422,
|
|
"num_tokens": 23472092.0,
|
|
"step": 13535
|
|
},
|
|
{
|
|
"entropy": 5.565783071517944,
|
|
"epoch": 1.0534526356739935,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.000489349619737019,
|
|
"loss": 5.3779,
|
|
"mean_token_accuracy": 0.16387729495763778,
|
|
"num_tokens": 23480934.0,
|
|
"step": 13540
|
|
},
|
|
{
|
|
"entropy": 5.618014240264893,
|
|
"epoch": 1.053841665045711,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.000489341191959447,
|
|
"loss": 5.325,
|
|
"mean_token_accuracy": 0.1696184165775776,
|
|
"num_tokens": 23490187.0,
|
|
"step": 13545
|
|
},
|
|
{
|
|
"entropy": 5.5481956005096436,
|
|
"epoch": 1.0542306944174284,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004893327609295887,
|
|
"loss": 5.2614,
|
|
"mean_token_accuracy": 0.17242091447114943,
|
|
"num_tokens": 23498330.0,
|
|
"step": 13550
|
|
},
|
|
{
|
|
"entropy": 5.435535097122193,
|
|
"epoch": 1.0546197237891461,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004893243266475719,
|
|
"loss": 5.188,
|
|
"mean_token_accuracy": 0.17514382153749466,
|
|
"num_tokens": 23506219.0,
|
|
"step": 13555
|
|
},
|
|
{
|
|
"entropy": 5.4826188564300535,
|
|
"epoch": 1.0550087531608636,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004893158891135245,
|
|
"loss": 5.2779,
|
|
"mean_token_accuracy": 0.173899045586586,
|
|
"num_tokens": 23514585.0,
|
|
"step": 13560
|
|
},
|
|
{
|
|
"entropy": 5.568767881393432,
|
|
"epoch": 1.055397782532581,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004893074483275746,
|
|
"loss": 5.2323,
|
|
"mean_token_accuracy": 0.1731153279542923,
|
|
"num_tokens": 23522919.0,
|
|
"step": 13565
|
|
},
|
|
{
|
|
"entropy": 5.561643838882446,
|
|
"epoch": 1.0557868119042988,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004892990042898503,
|
|
"loss": 5.4482,
|
|
"mean_token_accuracy": 0.1605902597308159,
|
|
"num_tokens": 23531613.0,
|
|
"step": 13570
|
|
},
|
|
{
|
|
"entropy": 5.564041614532471,
|
|
"epoch": 1.0561758412760163,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004892905570004798,
|
|
"loss": 5.3891,
|
|
"mean_token_accuracy": 0.16505015641450882,
|
|
"num_tokens": 23539865.0,
|
|
"step": 13575
|
|
},
|
|
{
|
|
"entropy": 5.478564691543579,
|
|
"epoch": 1.056564870647734,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.000489282106459591,
|
|
"loss": 5.2238,
|
|
"mean_token_accuracy": 0.18216872662305833,
|
|
"num_tokens": 23548424.0,
|
|
"step": 13580
|
|
},
|
|
{
|
|
"entropy": 5.562547302246093,
|
|
"epoch": 1.0569539000194514,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004892736526673124,
|
|
"loss": 5.3177,
|
|
"mean_token_accuracy": 0.17252922505140306,
|
|
"num_tokens": 23557199.0,
|
|
"step": 13585
|
|
},
|
|
{
|
|
"entropy": 5.565737009048462,
|
|
"epoch": 1.0573429293911691,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004892651956237721,
|
|
"loss": 5.4448,
|
|
"mean_token_accuracy": 0.15989054441452027,
|
|
"num_tokens": 23565979.0,
|
|
"step": 13590
|
|
},
|
|
{
|
|
"entropy": 5.564665126800537,
|
|
"epoch": 1.0577319587628866,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004892567353290986,
|
|
"loss": 5.3022,
|
|
"mean_token_accuracy": 0.16925350278615953,
|
|
"num_tokens": 23575405.0,
|
|
"step": 13595
|
|
},
|
|
{
|
|
"entropy": 5.64054651260376,
|
|
"epoch": 1.058120988134604,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004892482717834201,
|
|
"loss": 5.4364,
|
|
"mean_token_accuracy": 0.15500097647309302,
|
|
"num_tokens": 23584589.0,
|
|
"step": 13600
|
|
},
|
|
{
|
|
"entropy": 5.524608135223389,
|
|
"epoch": 1.0585100175063218,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004892398049868651,
|
|
"loss": 5.2872,
|
|
"mean_token_accuracy": 0.1721488878130913,
|
|
"num_tokens": 23593079.0,
|
|
"step": 13605
|
|
},
|
|
{
|
|
"entropy": 5.564929008483887,
|
|
"epoch": 1.0588990468780393,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.000489231334939562,
|
|
"loss": 5.357,
|
|
"mean_token_accuracy": 0.1696854367852211,
|
|
"num_tokens": 23602010.0,
|
|
"step": 13610
|
|
},
|
|
{
|
|
"entropy": 5.610072231292724,
|
|
"epoch": 1.059288076249757,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004892228616416395,
|
|
"loss": 5.3134,
|
|
"mean_token_accuracy": 0.17270972430706025,
|
|
"num_tokens": 23610707.0,
|
|
"step": 13615
|
|
},
|
|
{
|
|
"entropy": 5.460940933227539,
|
|
"epoch": 1.0596771056214744,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004892143850932259,
|
|
"loss": 5.2961,
|
|
"mean_token_accuracy": 0.16677080243825912,
|
|
"num_tokens": 23619579.0,
|
|
"step": 13620
|
|
},
|
|
{
|
|
"entropy": 5.498000049591065,
|
|
"epoch": 1.060066134993192,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.00048920590529445,
|
|
"loss": 5.2719,
|
|
"mean_token_accuracy": 0.18019049018621444,
|
|
"num_tokens": 23628407.0,
|
|
"step": 13625
|
|
},
|
|
{
|
|
"entropy": 5.489911699295044,
|
|
"epoch": 1.0604551643649096,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004891974222454406,
|
|
"loss": 5.1994,
|
|
"mean_token_accuracy": 0.17532860189676286,
|
|
"num_tokens": 23637094.0,
|
|
"step": 13630
|
|
},
|
|
{
|
|
"entropy": 5.492452001571655,
|
|
"epoch": 1.060844193736627,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004891889359463261,
|
|
"loss": 5.2958,
|
|
"mean_token_accuracy": 0.17481526583433152,
|
|
"num_tokens": 23645823.0,
|
|
"step": 13635
|
|
},
|
|
{
|
|
"entropy": 5.570481586456299,
|
|
"epoch": 1.0612332231083448,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004891804463972354,
|
|
"loss": 5.4054,
|
|
"mean_token_accuracy": 0.16421720683574675,
|
|
"num_tokens": 23655027.0,
|
|
"step": 13640
|
|
},
|
|
{
|
|
"entropy": 5.657866048812866,
|
|
"epoch": 1.0616222524800623,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004891719535982974,
|
|
"loss": 5.4441,
|
|
"mean_token_accuracy": 0.16156262755393982,
|
|
"num_tokens": 23663840.0,
|
|
"step": 13645
|
|
},
|
|
{
|
|
"entropy": 5.62884030342102,
|
|
"epoch": 1.0620112818517797,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004891634575496408,
|
|
"loss": 5.3922,
|
|
"mean_token_accuracy": 0.16663903295993804,
|
|
"num_tokens": 23672795.0,
|
|
"step": 13650
|
|
},
|
|
{
|
|
"entropy": 5.578080129623413,
|
|
"epoch": 1.0624003112234974,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004891549582513946,
|
|
"loss": 5.3172,
|
|
"mean_token_accuracy": 0.16714794635772706,
|
|
"num_tokens": 23681833.0,
|
|
"step": 13655
|
|
},
|
|
{
|
|
"entropy": 5.574814081192017,
|
|
"epoch": 1.062789340595215,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.000489146455703688,
|
|
"loss": 5.2916,
|
|
"mean_token_accuracy": 0.17374734282493592,
|
|
"num_tokens": 23689939.0,
|
|
"step": 13660
|
|
},
|
|
{
|
|
"entropy": 5.514884662628174,
|
|
"epoch": 1.0631783699669326,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004891379499066495,
|
|
"loss": 5.3363,
|
|
"mean_token_accuracy": 0.17417766749858857,
|
|
"num_tokens": 23698535.0,
|
|
"step": 13665
|
|
},
|
|
{
|
|
"entropy": 5.5378015518188475,
|
|
"epoch": 1.06356739933865,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004891294408604087,
|
|
"loss": 5.2683,
|
|
"mean_token_accuracy": 0.17150928527116777,
|
|
"num_tokens": 23707749.0,
|
|
"step": 13670
|
|
},
|
|
{
|
|
"entropy": 5.612474966049194,
|
|
"epoch": 1.0639564287103676,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004891209285650942,
|
|
"loss": 5.414,
|
|
"mean_token_accuracy": 0.1681921124458313,
|
|
"num_tokens": 23716503.0,
|
|
"step": 13675
|
|
},
|
|
{
|
|
"entropy": 5.620874881744385,
|
|
"epoch": 1.0643454580820852,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004891124130208355,
|
|
"loss": 5.353,
|
|
"mean_token_accuracy": 0.17228189632296562,
|
|
"num_tokens": 23724882.0,
|
|
"step": 13680
|
|
},
|
|
{
|
|
"entropy": 5.450166463851929,
|
|
"epoch": 1.0647344874538027,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004891038942277618,
|
|
"loss": 5.3544,
|
|
"mean_token_accuracy": 0.17434402406215668,
|
|
"num_tokens": 23733680.0,
|
|
"step": 13685
|
|
},
|
|
{
|
|
"entropy": 5.5328607082366945,
|
|
"epoch": 1.0651235168255204,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004890953721860022,
|
|
"loss": 5.2802,
|
|
"mean_token_accuracy": 0.1807577818632126,
|
|
"num_tokens": 23742066.0,
|
|
"step": 13690
|
|
},
|
|
{
|
|
"entropy": 5.522846984863281,
|
|
"epoch": 1.065512546197238,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004890868468956862,
|
|
"loss": 5.2014,
|
|
"mean_token_accuracy": 0.1826232448220253,
|
|
"num_tokens": 23750558.0,
|
|
"step": 13695
|
|
},
|
|
{
|
|
"entropy": 5.465801191329956,
|
|
"epoch": 1.0659015755689554,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.000489078318356943,
|
|
"loss": 5.2722,
|
|
"mean_token_accuracy": 0.1692625030875206,
|
|
"num_tokens": 23759120.0,
|
|
"step": 13700
|
|
},
|
|
{
|
|
"entropy": 5.448861455917358,
|
|
"epoch": 1.066290604940673,
|
|
"grad_norm": 5.0,
|
|
"learning_rate": 0.0004890697865699021,
|
|
"loss": 5.3096,
|
|
"mean_token_accuracy": 0.17092404961586,
|
|
"num_tokens": 23768301.0,
|
|
"step": 13705
|
|
},
|
|
{
|
|
"entropy": 5.515306758880615,
|
|
"epoch": 1.0666796343123905,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004890612515346929,
|
|
"loss": 5.2569,
|
|
"mean_token_accuracy": 0.17921047955751418,
|
|
"num_tokens": 23776155.0,
|
|
"step": 13710
|
|
},
|
|
{
|
|
"entropy": 5.566693305969238,
|
|
"epoch": 1.0670686636841082,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004890527132514448,
|
|
"loss": 5.3532,
|
|
"mean_token_accuracy": 0.16514315009117125,
|
|
"num_tokens": 23785363.0,
|
|
"step": 13715
|
|
},
|
|
{
|
|
"entropy": 5.595513248443604,
|
|
"epoch": 1.0674576930558257,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004890441717202876,
|
|
"loss": 5.2999,
|
|
"mean_token_accuracy": 0.17422668337821962,
|
|
"num_tokens": 23793817.0,
|
|
"step": 13720
|
|
},
|
|
{
|
|
"entropy": 5.550647640228272,
|
|
"epoch": 1.0678467224275432,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004890356269413507,
|
|
"loss": 5.356,
|
|
"mean_token_accuracy": 0.16996671706438066,
|
|
"num_tokens": 23802629.0,
|
|
"step": 13725
|
|
},
|
|
{
|
|
"entropy": 5.465928840637207,
|
|
"epoch": 1.068235751799261,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.000489027078914764,
|
|
"loss": 5.1411,
|
|
"mean_token_accuracy": 0.1822621151804924,
|
|
"num_tokens": 23811178.0,
|
|
"step": 13730
|
|
},
|
|
{
|
|
"entropy": 5.53959698677063,
|
|
"epoch": 1.0686247811709784,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004890185276406569,
|
|
"loss": 5.3693,
|
|
"mean_token_accuracy": 0.167016638815403,
|
|
"num_tokens": 23819685.0,
|
|
"step": 13735
|
|
},
|
|
{
|
|
"entropy": 5.419653844833374,
|
|
"epoch": 1.069013810542696,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004890099731191592,
|
|
"loss": 5.239,
|
|
"mean_token_accuracy": 0.17011093348264694,
|
|
"num_tokens": 23828733.0,
|
|
"step": 13740
|
|
},
|
|
{
|
|
"entropy": 5.601557350158691,
|
|
"epoch": 1.0694028399144135,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.000489001415350401,
|
|
"loss": 5.4134,
|
|
"mean_token_accuracy": 0.16911170482635499,
|
|
"num_tokens": 23837095.0,
|
|
"step": 13745
|
|
},
|
|
{
|
|
"entropy": 5.624904584884644,
|
|
"epoch": 1.069791869286131,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004889928543345118,
|
|
"loss": 5.3659,
|
|
"mean_token_accuracy": 0.16807382553815842,
|
|
"num_tokens": 23846637.0,
|
|
"step": 13750
|
|
},
|
|
{
|
|
"entropy": 5.593227338790894,
|
|
"epoch": 1.0701808986578487,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.0004889842900716217,
|
|
"loss": 5.4405,
|
|
"mean_token_accuracy": 0.16046826392412186,
|
|
"num_tokens": 23856042.0,
|
|
"step": 13755
|
|
},
|
|
{
|
|
"entropy": 5.581457424163818,
|
|
"epoch": 1.0705699280295662,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004889757225618606,
|
|
"loss": 5.398,
|
|
"mean_token_accuracy": 0.161847585439682,
|
|
"num_tokens": 23865367.0,
|
|
"step": 13760
|
|
},
|
|
{
|
|
"entropy": 5.560931396484375,
|
|
"epoch": 1.0709589574012839,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004889671518053584,
|
|
"loss": 5.3748,
|
|
"mean_token_accuracy": 0.16762278825044633,
|
|
"num_tokens": 23874740.0,
|
|
"step": 13765
|
|
},
|
|
{
|
|
"entropy": 5.559179353713989,
|
|
"epoch": 1.0713479867730014,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004889585778022453,
|
|
"loss": 5.3194,
|
|
"mean_token_accuracy": 0.17093719094991683,
|
|
"num_tokens": 23884229.0,
|
|
"step": 13770
|
|
},
|
|
{
|
|
"entropy": 5.510400342941284,
|
|
"epoch": 1.0717370161447188,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004889500005526514,
|
|
"loss": 5.23,
|
|
"mean_token_accuracy": 0.17975565642118455,
|
|
"num_tokens": 23892149.0,
|
|
"step": 13775
|
|
},
|
|
{
|
|
"entropy": 5.644508028030396,
|
|
"epoch": 1.0721260455164365,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004889414200567067,
|
|
"loss": 5.4889,
|
|
"mean_token_accuracy": 0.15467537343502044,
|
|
"num_tokens": 23901802.0,
|
|
"step": 13780
|
|
},
|
|
{
|
|
"entropy": 5.592928695678711,
|
|
"epoch": 1.072515074888154,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004889328363145415,
|
|
"loss": 5.3306,
|
|
"mean_token_accuracy": 0.17018810361623765,
|
|
"num_tokens": 23910268.0,
|
|
"step": 13785
|
|
},
|
|
{
|
|
"entropy": 5.456088638305664,
|
|
"epoch": 1.0729041042598717,
|
|
"grad_norm": 3.296875,
|
|
"learning_rate": 0.0004889242493262859,
|
|
"loss": 5.1646,
|
|
"mean_token_accuracy": 0.17440763264894485,
|
|
"num_tokens": 23918351.0,
|
|
"step": 13790
|
|
},
|
|
{
|
|
"entropy": 5.511342859268188,
|
|
"epoch": 1.0732931336315892,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004889156590920704,
|
|
"loss": 5.2312,
|
|
"mean_token_accuracy": 0.17307026088237762,
|
|
"num_tokens": 23927367.0,
|
|
"step": 13795
|
|
},
|
|
{
|
|
"entropy": 5.500313711166382,
|
|
"epoch": 1.0736821630033067,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004889070656120253,
|
|
"loss": 5.3071,
|
|
"mean_token_accuracy": 0.17446416169404982,
|
|
"num_tokens": 23936216.0,
|
|
"step": 13800
|
|
},
|
|
{
|
|
"entropy": 5.636788845062256,
|
|
"epoch": 1.0740711923750244,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004888984688862809,
|
|
"loss": 5.3835,
|
|
"mean_token_accuracy": 0.16611143052577973,
|
|
"num_tokens": 23944344.0,
|
|
"step": 13805
|
|
},
|
|
{
|
|
"entropy": 5.575056076049805,
|
|
"epoch": 1.0744602217467418,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004888898689149677,
|
|
"loss": 5.4094,
|
|
"mean_token_accuracy": 0.15442738458514213,
|
|
"num_tokens": 23953390.0,
|
|
"step": 13810
|
|
},
|
|
{
|
|
"entropy": 5.635413694381714,
|
|
"epoch": 1.0748492511184595,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004888812656982162,
|
|
"loss": 5.3982,
|
|
"mean_token_accuracy": 0.1702481508255005,
|
|
"num_tokens": 23962230.0,
|
|
"step": 13815
|
|
},
|
|
{
|
|
"entropy": 5.562955141067505,
|
|
"epoch": 1.075238280490177,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004888726592361569,
|
|
"loss": 5.2811,
|
|
"mean_token_accuracy": 0.1708732083439827,
|
|
"num_tokens": 23971627.0,
|
|
"step": 13820
|
|
},
|
|
{
|
|
"entropy": 5.496527624130249,
|
|
"epoch": 1.0756273098618945,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004888640495289204,
|
|
"loss": 5.282,
|
|
"mean_token_accuracy": 0.17555358856916428,
|
|
"num_tokens": 23980222.0,
|
|
"step": 13825
|
|
},
|
|
{
|
|
"entropy": 5.5275712490081785,
|
|
"epoch": 1.0760163392336122,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004888554365766374,
|
|
"loss": 5.3474,
|
|
"mean_token_accuracy": 0.1654688909649849,
|
|
"num_tokens": 23988803.0,
|
|
"step": 13830
|
|
},
|
|
{
|
|
"entropy": 5.544680786132813,
|
|
"epoch": 1.0764053686053296,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004888468203794385,
|
|
"loss": 5.3409,
|
|
"mean_token_accuracy": 0.16459826976060868,
|
|
"num_tokens": 23997664.0,
|
|
"step": 13835
|
|
},
|
|
{
|
|
"entropy": 5.532573986053467,
|
|
"epoch": 1.0767943979770473,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004888382009374545,
|
|
"loss": 5.3239,
|
|
"mean_token_accuracy": 0.17208846807479858,
|
|
"num_tokens": 24006641.0,
|
|
"step": 13840
|
|
},
|
|
{
|
|
"entropy": 5.502842378616333,
|
|
"epoch": 1.0771834273487648,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004888295782508161,
|
|
"loss": 5.2714,
|
|
"mean_token_accuracy": 0.16638420522212982,
|
|
"num_tokens": 24014852.0,
|
|
"step": 13845
|
|
},
|
|
{
|
|
"entropy": 5.573114013671875,
|
|
"epoch": 1.0775724567204823,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004888209523196542,
|
|
"loss": 5.2946,
|
|
"mean_token_accuracy": 0.1803032010793686,
|
|
"num_tokens": 24023441.0,
|
|
"step": 13850
|
|
},
|
|
{
|
|
"entropy": 5.620143985748291,
|
|
"epoch": 1.0779614860922,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004888123231440997,
|
|
"loss": 5.3048,
|
|
"mean_token_accuracy": 0.17385974228382112,
|
|
"num_tokens": 24032120.0,
|
|
"step": 13855
|
|
},
|
|
{
|
|
"entropy": 5.561611080169678,
|
|
"epoch": 1.0783505154639175,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004888036907242834,
|
|
"loss": 5.3607,
|
|
"mean_token_accuracy": 0.16757990270853043,
|
|
"num_tokens": 24040264.0,
|
|
"step": 13860
|
|
},
|
|
{
|
|
"entropy": 5.642135095596314,
|
|
"epoch": 1.0787395448356352,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004887950550603366,
|
|
"loss": 5.4115,
|
|
"mean_token_accuracy": 0.16733597069978715,
|
|
"num_tokens": 24049194.0,
|
|
"step": 13865
|
|
},
|
|
{
|
|
"entropy": 5.55846471786499,
|
|
"epoch": 1.0791285742073526,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.0004887864161523901,
|
|
"loss": 5.2732,
|
|
"mean_token_accuracy": 0.17170953005552292,
|
|
"num_tokens": 24058004.0,
|
|
"step": 13870
|
|
},
|
|
{
|
|
"entropy": 5.4610028743743895,
|
|
"epoch": 1.0795176035790701,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004887777740005749,
|
|
"loss": 5.2269,
|
|
"mean_token_accuracy": 0.17321476042270662,
|
|
"num_tokens": 24066871.0,
|
|
"step": 13875
|
|
},
|
|
{
|
|
"entropy": 5.558225488662719,
|
|
"epoch": 1.0799066329507878,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004887691286050224,
|
|
"loss": 5.3347,
|
|
"mean_token_accuracy": 0.16767856925725938,
|
|
"num_tokens": 24075409.0,
|
|
"step": 13880
|
|
},
|
|
{
|
|
"entropy": 5.588159608840942,
|
|
"epoch": 1.0802956623225053,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004887604799658635,
|
|
"loss": 5.2789,
|
|
"mean_token_accuracy": 0.16992218941450118,
|
|
"num_tokens": 24083983.0,
|
|
"step": 13885
|
|
},
|
|
{
|
|
"entropy": 5.536437511444092,
|
|
"epoch": 1.080684691694223,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 0.0004887518280832295,
|
|
"loss": 5.2984,
|
|
"mean_token_accuracy": 0.17002954483032226,
|
|
"num_tokens": 24092225.0,
|
|
"step": 13890
|
|
},
|
|
{
|
|
"entropy": 5.474335479736328,
|
|
"epoch": 1.0810737210659405,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004887431729572519,
|
|
"loss": 5.2265,
|
|
"mean_token_accuracy": 0.18012141734361647,
|
|
"num_tokens": 24100045.0,
|
|
"step": 13895
|
|
},
|
|
{
|
|
"entropy": 5.488373041152954,
|
|
"epoch": 1.081462750437658,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004887345145880617,
|
|
"loss": 5.2988,
|
|
"mean_token_accuracy": 0.1758161962032318,
|
|
"num_tokens": 24108540.0,
|
|
"step": 13900
|
|
},
|
|
{
|
|
"entropy": 5.590416717529297,
|
|
"epoch": 1.0818517798093756,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004887258529757904,
|
|
"loss": 5.3874,
|
|
"mean_token_accuracy": 0.16554994285106658,
|
|
"num_tokens": 24117819.0,
|
|
"step": 13905
|
|
},
|
|
{
|
|
"entropy": 5.5390746116638185,
|
|
"epoch": 1.082240809181093,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004887171881205696,
|
|
"loss": 5.1909,
|
|
"mean_token_accuracy": 0.17586574107408523,
|
|
"num_tokens": 24127000.0,
|
|
"step": 13910
|
|
},
|
|
{
|
|
"entropy": 5.528246259689331,
|
|
"epoch": 1.0826298385528108,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004887085200225306,
|
|
"loss": 5.3117,
|
|
"mean_token_accuracy": 0.16844677478075026,
|
|
"num_tokens": 24135404.0,
|
|
"step": 13915
|
|
},
|
|
{
|
|
"entropy": 5.449680376052856,
|
|
"epoch": 1.0830188679245283,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004886998486818049,
|
|
"loss": 5.1416,
|
|
"mean_token_accuracy": 0.1834289848804474,
|
|
"num_tokens": 24143944.0,
|
|
"step": 13920
|
|
},
|
|
{
|
|
"entropy": 5.510674047470093,
|
|
"epoch": 1.083407897296246,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004886911740985242,
|
|
"loss": 5.2696,
|
|
"mean_token_accuracy": 0.17339787483215333,
|
|
"num_tokens": 24153097.0,
|
|
"step": 13925
|
|
},
|
|
{
|
|
"entropy": 5.570836067199707,
|
|
"epoch": 1.0837969266679635,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.00048868249627282,
|
|
"loss": 5.4283,
|
|
"mean_token_accuracy": 0.16437558084726334,
|
|
"num_tokens": 24162499.0,
|
|
"step": 13930
|
|
},
|
|
{
|
|
"entropy": 5.550439834594727,
|
|
"epoch": 1.084185956039681,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.000488673815204824,
|
|
"loss": 5.2494,
|
|
"mean_token_accuracy": 0.1778493732213974,
|
|
"num_tokens": 24170543.0,
|
|
"step": 13935
|
|
},
|
|
{
|
|
"entropy": 5.554481840133667,
|
|
"epoch": 1.0845749854113986,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004886651308946681,
|
|
"loss": 5.3223,
|
|
"mean_token_accuracy": 0.16854367554187774,
|
|
"num_tokens": 24180871.0,
|
|
"step": 13940
|
|
},
|
|
{
|
|
"entropy": 5.505338907241821,
|
|
"epoch": 1.084964014783116,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004886564433424839,
|
|
"loss": 5.2427,
|
|
"mean_token_accuracy": 0.17851458340883256,
|
|
"num_tokens": 24189075.0,
|
|
"step": 13945
|
|
},
|
|
{
|
|
"entropy": 5.594527339935302,
|
|
"epoch": 1.0853530441548336,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004886477525484032,
|
|
"loss": 5.3365,
|
|
"mean_token_accuracy": 0.1770291283726692,
|
|
"num_tokens": 24197686.0,
|
|
"step": 13950
|
|
},
|
|
{
|
|
"entropy": 5.437126588821411,
|
|
"epoch": 1.0857420735265513,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004886390585125579,
|
|
"loss": 5.2393,
|
|
"mean_token_accuracy": 0.16652272939682006,
|
|
"num_tokens": 24207093.0,
|
|
"step": 13955
|
|
},
|
|
{
|
|
"entropy": 5.627029943466186,
|
|
"epoch": 1.0861311028982688,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004886303612350799,
|
|
"loss": 5.3385,
|
|
"mean_token_accuracy": 0.16592801958322526,
|
|
"num_tokens": 24216447.0,
|
|
"step": 13960
|
|
},
|
|
{
|
|
"entropy": 5.685516357421875,
|
|
"epoch": 1.0865201322699864,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004886216607161013,
|
|
"loss": 5.3846,
|
|
"mean_token_accuracy": 0.16547441035509108,
|
|
"num_tokens": 24225041.0,
|
|
"step": 13965
|
|
},
|
|
{
|
|
"entropy": 5.608265018463134,
|
|
"epoch": 1.086909161641704,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004886129569557538,
|
|
"loss": 5.323,
|
|
"mean_token_accuracy": 0.1650741770863533,
|
|
"num_tokens": 24233686.0,
|
|
"step": 13970
|
|
},
|
|
{
|
|
"entropy": 5.504385042190552,
|
|
"epoch": 1.0872981910134216,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004886042499541699,
|
|
"loss": 5.3341,
|
|
"mean_token_accuracy": 0.17844736874103545,
|
|
"num_tokens": 24242553.0,
|
|
"step": 13975
|
|
},
|
|
{
|
|
"entropy": 5.5233869552612305,
|
|
"epoch": 1.087687220385139,
|
|
"grad_norm": 3.453125,
|
|
"learning_rate": 0.0004885955397114813,
|
|
"loss": 5.2467,
|
|
"mean_token_accuracy": 0.17321914732456206,
|
|
"num_tokens": 24251658.0,
|
|
"step": 13980
|
|
},
|
|
{
|
|
"entropy": 5.637213277816772,
|
|
"epoch": 1.0880762497568566,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004885868262278205,
|
|
"loss": 5.3671,
|
|
"mean_token_accuracy": 0.16639908850193025,
|
|
"num_tokens": 24260397.0,
|
|
"step": 13985
|
|
},
|
|
{
|
|
"entropy": 5.4556975841522215,
|
|
"epoch": 1.0884652791285743,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004885781095033195,
|
|
"loss": 5.2728,
|
|
"mean_token_accuracy": 0.17130138874053955,
|
|
"num_tokens": 24268789.0,
|
|
"step": 13990
|
|
},
|
|
{
|
|
"entropy": 5.530916452407837,
|
|
"epoch": 1.0888543085002917,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004885693895381108,
|
|
"loss": 5.3914,
|
|
"mean_token_accuracy": 0.16509933024644852,
|
|
"num_tokens": 24278050.0,
|
|
"step": 13995
|
|
},
|
|
{
|
|
"entropy": 5.6599335193634035,
|
|
"epoch": 1.0892433378720092,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004885606663323263,
|
|
"loss": 5.3238,
|
|
"mean_token_accuracy": 0.17296088933944703,
|
|
"num_tokens": 24286477.0,
|
|
"step": 14000
|
|
},
|
|
{
|
|
"entropy": 5.442564010620117,
|
|
"epoch": 1.089632367243727,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004885519398860987,
|
|
"loss": 5.195,
|
|
"mean_token_accuracy": 0.17921269088983535,
|
|
"num_tokens": 24295704.0,
|
|
"step": 14005
|
|
},
|
|
{
|
|
"entropy": 5.424733352661133,
|
|
"epoch": 1.0900213966154444,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004885432101995604,
|
|
"loss": 5.2377,
|
|
"mean_token_accuracy": 0.17668494284152986,
|
|
"num_tokens": 24304132.0,
|
|
"step": 14010
|
|
},
|
|
{
|
|
"entropy": 5.582837057113648,
|
|
"epoch": 1.090410425987162,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004885344772728436,
|
|
"loss": 5.3355,
|
|
"mean_token_accuracy": 0.16859273314476014,
|
|
"num_tokens": 24312864.0,
|
|
"step": 14015
|
|
},
|
|
{
|
|
"entropy": 5.586115026473999,
|
|
"epoch": 1.0907994553588796,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004885257411060812,
|
|
"loss": 5.2558,
|
|
"mean_token_accuracy": 0.17344018965959548,
|
|
"num_tokens": 24321745.0,
|
|
"step": 14020
|
|
},
|
|
{
|
|
"entropy": 5.488592529296875,
|
|
"epoch": 1.0911884847305973,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004885170016994053,
|
|
"loss": 5.2762,
|
|
"mean_token_accuracy": 0.16774366945028304,
|
|
"num_tokens": 24331061.0,
|
|
"step": 14025
|
|
},
|
|
{
|
|
"entropy": 5.45854082107544,
|
|
"epoch": 1.0915775141023147,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.0004885082590529489,
|
|
"loss": 5.2893,
|
|
"mean_token_accuracy": 0.17020780444145203,
|
|
"num_tokens": 24339935.0,
|
|
"step": 14030
|
|
},
|
|
{
|
|
"entropy": 5.5863566398620605,
|
|
"epoch": 1.0919665434740322,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004884995131668445,
|
|
"loss": 5.3168,
|
|
"mean_token_accuracy": 0.17068814039230346,
|
|
"num_tokens": 24348876.0,
|
|
"step": 14035
|
|
},
|
|
{
|
|
"entropy": 5.534871435165405,
|
|
"epoch": 1.09235557284575,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004884907640412248,
|
|
"loss": 5.3285,
|
|
"mean_token_accuracy": 0.1675461784005165,
|
|
"num_tokens": 24357094.0,
|
|
"step": 14040
|
|
},
|
|
{
|
|
"entropy": 5.484497451782227,
|
|
"epoch": 1.0927446022174674,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004884820116762225,
|
|
"loss": 5.2759,
|
|
"mean_token_accuracy": 0.1699037507176399,
|
|
"num_tokens": 24366320.0,
|
|
"step": 14045
|
|
},
|
|
{
|
|
"entropy": 5.483876132965088,
|
|
"epoch": 1.093133631589185,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004884732560719706,
|
|
"loss": 5.1662,
|
|
"mean_token_accuracy": 0.17697618752717972,
|
|
"num_tokens": 24374390.0,
|
|
"step": 14050
|
|
},
|
|
{
|
|
"entropy": 5.5002411842346195,
|
|
"epoch": 1.0935226609609026,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004884644972286017,
|
|
"loss": 5.2996,
|
|
"mean_token_accuracy": 0.17514243274927138,
|
|
"num_tokens": 24382804.0,
|
|
"step": 14055
|
|
},
|
|
{
|
|
"entropy": 5.550761318206787,
|
|
"epoch": 1.09391169033262,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004884557351462488,
|
|
"loss": 5.2963,
|
|
"mean_token_accuracy": 0.17130143493413924,
|
|
"num_tokens": 24391352.0,
|
|
"step": 14060
|
|
},
|
|
{
|
|
"entropy": 5.5826669216156,
|
|
"epoch": 1.0943007197043377,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004884469698250449,
|
|
"loss": 5.3724,
|
|
"mean_token_accuracy": 0.16699749678373338,
|
|
"num_tokens": 24400348.0,
|
|
"step": 14065
|
|
},
|
|
{
|
|
"entropy": 5.508634042739868,
|
|
"epoch": 1.0946897490760552,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.000488438201265123,
|
|
"loss": 5.2093,
|
|
"mean_token_accuracy": 0.1748551085591316,
|
|
"num_tokens": 24409628.0,
|
|
"step": 14070
|
|
},
|
|
{
|
|
"entropy": 5.560254621505737,
|
|
"epoch": 1.095078778447773,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004884294294666161,
|
|
"loss": 5.3047,
|
|
"mean_token_accuracy": 0.16498639136552812,
|
|
"num_tokens": 24418379.0,
|
|
"step": 14075
|
|
},
|
|
{
|
|
"entropy": 5.5908811569213865,
|
|
"epoch": 1.0954678078194904,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004884206544296573,
|
|
"loss": 5.4404,
|
|
"mean_token_accuracy": 0.16364881992340088,
|
|
"num_tokens": 24427719.0,
|
|
"step": 14080
|
|
},
|
|
{
|
|
"entropy": 5.611962556838989,
|
|
"epoch": 1.0958568371912079,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004884118761543797,
|
|
"loss": 5.3801,
|
|
"mean_token_accuracy": 0.16736531555652617,
|
|
"num_tokens": 24435938.0,
|
|
"step": 14085
|
|
},
|
|
{
|
|
"entropy": 5.541747426986694,
|
|
"epoch": 1.0962458665629256,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004884030946409167,
|
|
"loss": 5.2742,
|
|
"mean_token_accuracy": 0.17245944291353227,
|
|
"num_tokens": 24444286.0,
|
|
"step": 14090
|
|
},
|
|
{
|
|
"entropy": 5.480231475830078,
|
|
"epoch": 1.096634895934643,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004883943098894013,
|
|
"loss": 5.2212,
|
|
"mean_token_accuracy": 0.1797743782401085,
|
|
"num_tokens": 24452546.0,
|
|
"step": 14095
|
|
},
|
|
{
|
|
"entropy": 5.530523443222046,
|
|
"epoch": 1.0970239253063607,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000488385521899967,
|
|
"loss": 5.3538,
|
|
"mean_token_accuracy": 0.16807045191526412,
|
|
"num_tokens": 24460765.0,
|
|
"step": 14100
|
|
},
|
|
{
|
|
"entropy": 5.508094596862793,
|
|
"epoch": 1.0974129546780782,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.000488376730672747,
|
|
"loss": 5.2161,
|
|
"mean_token_accuracy": 0.1738041266798973,
|
|
"num_tokens": 24470018.0,
|
|
"step": 14105
|
|
},
|
|
{
|
|
"entropy": 5.511989879608154,
|
|
"epoch": 1.0978019840497957,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004883679362078746,
|
|
"loss": 5.1706,
|
|
"mean_token_accuracy": 0.17320188879966736,
|
|
"num_tokens": 24478882.0,
|
|
"step": 14110
|
|
},
|
|
{
|
|
"entropy": 5.533711957931518,
|
|
"epoch": 1.0981910134215134,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004883591385054836,
|
|
"loss": 5.3484,
|
|
"mean_token_accuracy": 0.1637899562716484,
|
|
"num_tokens": 24487801.0,
|
|
"step": 14115
|
|
},
|
|
{
|
|
"entropy": 5.5117205619812015,
|
|
"epoch": 1.0985800427932308,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004883503375657072,
|
|
"loss": 5.3151,
|
|
"mean_token_accuracy": 0.16933534294366837,
|
|
"num_tokens": 24496082.0,
|
|
"step": 14120
|
|
},
|
|
{
|
|
"entropy": 5.497330617904663,
|
|
"epoch": 1.0989690721649485,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004883415333886789,
|
|
"loss": 5.2197,
|
|
"mean_token_accuracy": 0.18041443526744844,
|
|
"num_tokens": 24504664.0,
|
|
"step": 14125
|
|
},
|
|
{
|
|
"entropy": 5.512371015548706,
|
|
"epoch": 1.099358101536666,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004883327259745325,
|
|
"loss": 5.2592,
|
|
"mean_token_accuracy": 0.17645634114742278,
|
|
"num_tokens": 24512797.0,
|
|
"step": 14130
|
|
},
|
|
{
|
|
"entropy": 5.48935284614563,
|
|
"epoch": 1.0997471309083835,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004883239153234015,
|
|
"loss": 5.2479,
|
|
"mean_token_accuracy": 0.1720615178346634,
|
|
"num_tokens": 24520941.0,
|
|
"step": 14135
|
|
},
|
|
{
|
|
"entropy": 5.573987817764282,
|
|
"epoch": 1.1001361602801012,
|
|
"grad_norm": 2.734375,
|
|
"learning_rate": 0.0004883151014354197,
|
|
"loss": 5.3462,
|
|
"mean_token_accuracy": 0.17067505270242692,
|
|
"num_tokens": 24530087.0,
|
|
"step": 14140
|
|
},
|
|
{
|
|
"entropy": 5.512291717529297,
|
|
"epoch": 1.1005251896518187,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004883062843107207,
|
|
"loss": 5.2979,
|
|
"mean_token_accuracy": 0.16665249168872834,
|
|
"num_tokens": 24538593.0,
|
|
"step": 14145
|
|
},
|
|
{
|
|
"entropy": 5.629961347579956,
|
|
"epoch": 1.1009142190235364,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004882974639494383,
|
|
"loss": 5.3658,
|
|
"mean_token_accuracy": 0.1617593139410019,
|
|
"num_tokens": 24547158.0,
|
|
"step": 14150
|
|
},
|
|
{
|
|
"entropy": 5.558168029785156,
|
|
"epoch": 1.1013032483952538,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.0004882886403517065,
|
|
"loss": 5.3639,
|
|
"mean_token_accuracy": 0.1636526554822922,
|
|
"num_tokens": 24556266.0,
|
|
"step": 14155
|
|
},
|
|
{
|
|
"entropy": 5.560190868377686,
|
|
"epoch": 1.1016922777669713,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004882798135176589,
|
|
"loss": 5.4088,
|
|
"mean_token_accuracy": 0.16728487610816956,
|
|
"num_tokens": 24565122.0,
|
|
"step": 14160
|
|
},
|
|
{
|
|
"entropy": 5.498580121994019,
|
|
"epoch": 1.102081307138689,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.00048827098344742973,
|
|
"loss": 5.2514,
|
|
"mean_token_accuracy": 0.1830837294459343,
|
|
"num_tokens": 24573944.0,
|
|
"step": 14165
|
|
},
|
|
{
|
|
"entropy": 5.534769296646118,
|
|
"epoch": 1.1024703365104065,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.0004882621501411528,
|
|
"loss": 5.4202,
|
|
"mean_token_accuracy": 0.16984884440898895,
|
|
"num_tokens": 24582233.0,
|
|
"step": 14170
|
|
},
|
|
{
|
|
"entropy": 5.539715147018432,
|
|
"epoch": 1.1028593658821242,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004882533135989622,
|
|
"loss": 5.2744,
|
|
"mean_token_accuracy": 0.17063359171152115,
|
|
"num_tokens": 24590855.0,
|
|
"step": 14175
|
|
},
|
|
{
|
|
"entropy": 5.675771284103393,
|
|
"epoch": 1.1032483952538417,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.000488244473820992,
|
|
"loss": 5.3394,
|
|
"mean_token_accuracy": 0.15959832072257996,
|
|
"num_tokens": 24599877.0,
|
|
"step": 14180
|
|
},
|
|
{
|
|
"entropy": 5.5097575187683105,
|
|
"epoch": 1.1036374246255591,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.00048823563080737634,
|
|
"loss": 5.2142,
|
|
"mean_token_accuracy": 0.18019939064979554,
|
|
"num_tokens": 24608450.0,
|
|
"step": 14185
|
|
},
|
|
{
|
|
"entropy": 5.470316219329834,
|
|
"epoch": 1.1040264539972768,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004882267845582493,
|
|
"loss": 5.3138,
|
|
"mean_token_accuracy": 0.1766979455947876,
|
|
"num_tokens": 24618018.0,
|
|
"step": 14190
|
|
},
|
|
{
|
|
"entropy": 5.555082178115844,
|
|
"epoch": 1.1044154833689943,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.00048821793507374526,
|
|
"loss": 5.2955,
|
|
"mean_token_accuracy": 0.16985682994127274,
|
|
"num_tokens": 24626388.0,
|
|
"step": 14195
|
|
},
|
|
{
|
|
"entropy": 5.606828451156616,
|
|
"epoch": 1.104804512740712,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004882090823539984,
|
|
"loss": 5.3944,
|
|
"mean_token_accuracy": 0.16266640722751619,
|
|
"num_tokens": 24635284.0,
|
|
"step": 14200
|
|
},
|
|
{
|
|
"entropy": 5.566130876541138,
|
|
"epoch": 1.1051935421124295,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004882002263991431,
|
|
"loss": 5.2479,
|
|
"mean_token_accuracy": 0.17859185934066774,
|
|
"num_tokens": 24644297.0,
|
|
"step": 14205
|
|
},
|
|
{
|
|
"entropy": 5.407494163513183,
|
|
"epoch": 1.105582571484147,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.00048819136720931364,
|
|
"loss": 5.1151,
|
|
"mean_token_accuracy": 0.17962373048067093,
|
|
"num_tokens": 24652965.0,
|
|
"step": 14210
|
|
},
|
|
{
|
|
"entropy": 5.3790207862854,
|
|
"epoch": 1.1059716008558647,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.00048818250478464457,
|
|
"loss": 5.2001,
|
|
"mean_token_accuracy": 0.17739752382040025,
|
|
"num_tokens": 24661034.0,
|
|
"step": 14215
|
|
},
|
|
{
|
|
"entropy": 5.523409461975097,
|
|
"epoch": 1.1063606302275821,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004881736391252703,
|
|
"loss": 5.2802,
|
|
"mean_token_accuracy": 0.17606231421232224,
|
|
"num_tokens": 24669831.0,
|
|
"step": 14220
|
|
},
|
|
{
|
|
"entropy": 5.578432893753051,
|
|
"epoch": 1.1067496595992998,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004881647702313253,
|
|
"loss": 5.3555,
|
|
"mean_token_accuracy": 0.16432537734508515,
|
|
"num_tokens": 24678491.0,
|
|
"step": 14225
|
|
},
|
|
{
|
|
"entropy": 5.539248991012573,
|
|
"epoch": 1.1071386889710173,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.00048815589810294427,
|
|
"loss": 5.293,
|
|
"mean_token_accuracy": 0.173760125041008,
|
|
"num_tokens": 24687308.0,
|
|
"step": 14230
|
|
},
|
|
{
|
|
"entropy": 5.497361469268799,
|
|
"epoch": 1.1075277183427348,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.00048814702274026174,
|
|
"loss": 5.2635,
|
|
"mean_token_accuracy": 0.17785624116659166,
|
|
"num_tokens": 24696080.0,
|
|
"step": 14235
|
|
},
|
|
{
|
|
"entropy": 5.502005767822266,
|
|
"epoch": 1.1079167477144525,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004881381441434124,
|
|
"loss": 5.3353,
|
|
"mean_token_accuracy": 0.1668131798505783,
|
|
"num_tokens": 24704561.0,
|
|
"step": 14240
|
|
},
|
|
{
|
|
"entropy": 5.609838771820068,
|
|
"epoch": 1.10830577708617,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.000488129262312531,
|
|
"loss": 5.3316,
|
|
"mean_token_accuracy": 0.16675823777914048,
|
|
"num_tokens": 24713403.0,
|
|
"step": 14245
|
|
},
|
|
{
|
|
"entropy": 5.606697750091553,
|
|
"epoch": 1.1086948064578876,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.00048812037724775217,
|
|
"loss": 5.3491,
|
|
"mean_token_accuracy": 0.1648279294371605,
|
|
"num_tokens": 24722031.0,
|
|
"step": 14250
|
|
},
|
|
{
|
|
"entropy": 5.531491279602051,
|
|
"epoch": 1.1090838358296051,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004881114889492109,
|
|
"loss": 5.2941,
|
|
"mean_token_accuracy": 0.17142567038536072,
|
|
"num_tokens": 24731176.0,
|
|
"step": 14255
|
|
},
|
|
{
|
|
"entropy": 5.54642653465271,
|
|
"epoch": 1.1094728652013226,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.00048810259741704197,
|
|
"loss": 5.344,
|
|
"mean_token_accuracy": 0.16734461337327958,
|
|
"num_tokens": 24740037.0,
|
|
"step": 14260
|
|
},
|
|
{
|
|
"entropy": 5.627961587905884,
|
|
"epoch": 1.1098618945730403,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004880937026513803,
|
|
"loss": 5.3994,
|
|
"mean_token_accuracy": 0.16683503091335297,
|
|
"num_tokens": 24748778.0,
|
|
"step": 14265
|
|
},
|
|
{
|
|
"entropy": 5.589363050460816,
|
|
"epoch": 1.1102509239447578,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004880848046523609,
|
|
"loss": 5.2414,
|
|
"mean_token_accuracy": 0.17778424322605133,
|
|
"num_tokens": 24757226.0,
|
|
"step": 14270
|
|
},
|
|
{
|
|
"entropy": 5.475401449203491,
|
|
"epoch": 1.1106399533164755,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.00048807590342011875,
|
|
"loss": 5.2835,
|
|
"mean_token_accuracy": 0.17758438140153884,
|
|
"num_tokens": 24765734.0,
|
|
"step": 14275
|
|
},
|
|
{
|
|
"entropy": 5.456071424484253,
|
|
"epoch": 1.111028982688193,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.00048806699895478895,
|
|
"loss": 5.2599,
|
|
"mean_token_accuracy": 0.1693689614534378,
|
|
"num_tokens": 24773773.0,
|
|
"step": 14280
|
|
},
|
|
{
|
|
"entropy": 5.522355270385742,
|
|
"epoch": 1.1114180120599104,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004880580912565065,
|
|
"loss": 5.29,
|
|
"mean_token_accuracy": 0.17302699387073517,
|
|
"num_tokens": 24782563.0,
|
|
"step": 14285
|
|
},
|
|
{
|
|
"entropy": 5.5858558177947994,
|
|
"epoch": 1.1118070414316281,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004880491803254067,
|
|
"loss": 5.3871,
|
|
"mean_token_accuracy": 0.16795666962862016,
|
|
"num_tokens": 24791492.0,
|
|
"step": 14290
|
|
},
|
|
{
|
|
"entropy": 5.493483591079712,
|
|
"epoch": 1.1121960708033456,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004880402661616246,
|
|
"loss": 5.1918,
|
|
"mean_token_accuracy": 0.17944994568824768,
|
|
"num_tokens": 24800229.0,
|
|
"step": 14295
|
|
},
|
|
{
|
|
"entropy": 5.486127138137817,
|
|
"epoch": 1.1125851001750633,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004880313487652956,
|
|
"loss": 5.2656,
|
|
"mean_token_accuracy": 0.17114198803901673,
|
|
"num_tokens": 24809454.0,
|
|
"step": 14300
|
|
},
|
|
{
|
|
"entropy": 5.483691024780273,
|
|
"epoch": 1.1129741295467808,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.00048802242813655503,
|
|
"loss": 5.2698,
|
|
"mean_token_accuracy": 0.17059182226657868,
|
|
"num_tokens": 24817956.0,
|
|
"step": 14305
|
|
},
|
|
{
|
|
"entropy": 5.473423290252685,
|
|
"epoch": 1.1133631589184985,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.000488013504275538,
|
|
"loss": 5.1898,
|
|
"mean_token_accuracy": 0.17933583855628968,
|
|
"num_tokens": 24826288.0,
|
|
"step": 14310
|
|
},
|
|
{
|
|
"entropy": 5.65793080329895,
|
|
"epoch": 1.113752188290216,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004880045771823802,
|
|
"loss": 5.3618,
|
|
"mean_token_accuracy": 0.16813699007034302,
|
|
"num_tokens": 24834720.0,
|
|
"step": 14315
|
|
},
|
|
{
|
|
"entropy": 5.522952938079834,
|
|
"epoch": 1.1141412176619334,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.00048799564685721695,
|
|
"loss": 5.3064,
|
|
"mean_token_accuracy": 0.17395334541797638,
|
|
"num_tokens": 24843000.0,
|
|
"step": 14320
|
|
},
|
|
{
|
|
"entropy": 5.525973606109619,
|
|
"epoch": 1.1145302470336511,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004879867133001837,
|
|
"loss": 5.3015,
|
|
"mean_token_accuracy": 0.16755297631025315,
|
|
"num_tokens": 24851060.0,
|
|
"step": 14325
|
|
},
|
|
{
|
|
"entropy": 5.454747104644776,
|
|
"epoch": 1.1149192764053686,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004879777765114162,
|
|
"loss": 5.2085,
|
|
"mean_token_accuracy": 0.1771145850419998,
|
|
"num_tokens": 24859913.0,
|
|
"step": 14330
|
|
},
|
|
{
|
|
"entropy": 5.609213256835938,
|
|
"epoch": 1.115308305777086,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.00048796883649104996,
|
|
"loss": 5.4089,
|
|
"mean_token_accuracy": 0.16464822739362717,
|
|
"num_tokens": 24869648.0,
|
|
"step": 14335
|
|
},
|
|
{
|
|
"entropy": 5.571947288513184,
|
|
"epoch": 1.1156973351488038,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004879598932392206,
|
|
"loss": 5.3292,
|
|
"mean_token_accuracy": 0.17350474745035172,
|
|
"num_tokens": 24878813.0,
|
|
"step": 14340
|
|
},
|
|
{
|
|
"entropy": 5.5525922775268555,
|
|
"epoch": 1.1160863645205212,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.00048795094675606364,
|
|
"loss": 5.3082,
|
|
"mean_token_accuracy": 0.16897975355386735,
|
|
"num_tokens": 24887714.0,
|
|
"step": 14345
|
|
},
|
|
{
|
|
"entropy": 5.571045875549316,
|
|
"epoch": 1.116475393892239,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004879419970417152,
|
|
"loss": 5.2703,
|
|
"mean_token_accuracy": 0.172675059735775,
|
|
"num_tokens": 24895961.0,
|
|
"step": 14350
|
|
},
|
|
{
|
|
"entropy": 5.55090298652649,
|
|
"epoch": 1.1168644232639564,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00048793304409631077,
|
|
"loss": 5.301,
|
|
"mean_token_accuracy": 0.1732762098312378,
|
|
"num_tokens": 24904873.0,
|
|
"step": 14355
|
|
},
|
|
{
|
|
"entropy": 5.455278730392456,
|
|
"epoch": 1.117253452635674,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004879240879199863,
|
|
"loss": 5.1985,
|
|
"mean_token_accuracy": 0.1836355596780777,
|
|
"num_tokens": 24913486.0,
|
|
"step": 14360
|
|
},
|
|
{
|
|
"entropy": 5.500343942642212,
|
|
"epoch": 1.1176424820073916,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.00048791512851287786,
|
|
"loss": 5.2854,
|
|
"mean_token_accuracy": 0.1700807571411133,
|
|
"num_tokens": 24921943.0,
|
|
"step": 14365
|
|
},
|
|
{
|
|
"entropy": 5.606582069396973,
|
|
"epoch": 1.118031511379109,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.00048790616587512107,
|
|
"loss": 5.3794,
|
|
"mean_token_accuracy": 0.16794403791427612,
|
|
"num_tokens": 24930081.0,
|
|
"step": 14370
|
|
},
|
|
{
|
|
"entropy": 5.658608436584473,
|
|
"epoch": 1.1184205407508268,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004878972000068521,
|
|
"loss": 5.3183,
|
|
"mean_token_accuracy": 0.1709811270236969,
|
|
"num_tokens": 24938985.0,
|
|
"step": 14375
|
|
},
|
|
{
|
|
"entropy": 5.435786533355713,
|
|
"epoch": 1.1188095701225442,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00048788823090820707,
|
|
"loss": 5.1481,
|
|
"mean_token_accuracy": 0.18129525780677797,
|
|
"num_tokens": 24947497.0,
|
|
"step": 14380
|
|
},
|
|
{
|
|
"entropy": 5.550786018371582,
|
|
"epoch": 1.1191985994942617,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.00048787925857932194,
|
|
"loss": 5.3791,
|
|
"mean_token_accuracy": 0.1630413845181465,
|
|
"num_tokens": 24956263.0,
|
|
"step": 14385
|
|
},
|
|
{
|
|
"entropy": 5.653364372253418,
|
|
"epoch": 1.1195876288659794,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.00048787028302033287,
|
|
"loss": 5.4578,
|
|
"mean_token_accuracy": 0.16429930925369263,
|
|
"num_tokens": 24965646.0,
|
|
"step": 14390
|
|
},
|
|
{
|
|
"entropy": 5.579395961761475,
|
|
"epoch": 1.1199766582376969,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.00048786130423137606,
|
|
"loss": 5.3332,
|
|
"mean_token_accuracy": 0.17410521060228348,
|
|
"num_tokens": 24973318.0,
|
|
"step": 14395
|
|
},
|
|
{
|
|
"entropy": 5.562328958511353,
|
|
"epoch": 1.1203656876094146,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004878523222125879,
|
|
"loss": 5.414,
|
|
"mean_token_accuracy": 0.17157252877950668,
|
|
"num_tokens": 24982600.0,
|
|
"step": 14400
|
|
},
|
|
{
|
|
"entropy": 5.674773550033569,
|
|
"epoch": 1.120754716981132,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004878433369641044,
|
|
"loss": 5.3954,
|
|
"mean_token_accuracy": 0.16661668866872786,
|
|
"num_tokens": 24990386.0,
|
|
"step": 14405
|
|
},
|
|
{
|
|
"entropy": 5.459098386764526,
|
|
"epoch": 1.1211437463528497,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004878343484860621,
|
|
"loss": 5.1695,
|
|
"mean_token_accuracy": 0.17870809882879257,
|
|
"num_tokens": 24999064.0,
|
|
"step": 14410
|
|
},
|
|
{
|
|
"entropy": 5.5220627784729,
|
|
"epoch": 1.1215327757245672,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004878253567785972,
|
|
"loss": 5.34,
|
|
"mean_token_accuracy": 0.17166408747434617,
|
|
"num_tokens": 25008448.0,
|
|
"step": 14415
|
|
},
|
|
{
|
|
"entropy": 5.417818355560303,
|
|
"epoch": 1.1219218050962847,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.00048781636184184644,
|
|
"loss": 5.1728,
|
|
"mean_token_accuracy": 0.18554657995700835,
|
|
"num_tokens": 25016722.0,
|
|
"step": 14420
|
|
},
|
|
{
|
|
"entropy": 5.433246850967407,
|
|
"epoch": 1.1223108344680024,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.000487807363675946,
|
|
"loss": 5.2511,
|
|
"mean_token_accuracy": 0.17665931433439255,
|
|
"num_tokens": 25026263.0,
|
|
"step": 14425
|
|
},
|
|
{
|
|
"entropy": 5.568420124053955,
|
|
"epoch": 1.1226998638397199,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004877983622810326,
|
|
"loss": 5.2876,
|
|
"mean_token_accuracy": 0.17753019481897353,
|
|
"num_tokens": 25035202.0,
|
|
"step": 14430
|
|
},
|
|
{
|
|
"entropy": 5.610867261886597,
|
|
"epoch": 1.1230888932114376,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004877893576572427,
|
|
"loss": 5.3618,
|
|
"mean_token_accuracy": 0.17109027057886123,
|
|
"num_tokens": 25044309.0,
|
|
"step": 14435
|
|
},
|
|
{
|
|
"entropy": 5.577419710159302,
|
|
"epoch": 1.123477922583155,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.000487780349804713,
|
|
"loss": 5.3391,
|
|
"mean_token_accuracy": 0.17795383781194687,
|
|
"num_tokens": 25053044.0,
|
|
"step": 14440
|
|
},
|
|
{
|
|
"entropy": 5.42353835105896,
|
|
"epoch": 1.1238669519548725,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004877713387235802,
|
|
"loss": 5.2455,
|
|
"mean_token_accuracy": 0.17633127123117448,
|
|
"num_tokens": 25061869.0,
|
|
"step": 14445
|
|
},
|
|
{
|
|
"entropy": 5.548495864868164,
|
|
"epoch": 1.1242559813265902,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.000487762324413981,
|
|
"loss": 5.4236,
|
|
"mean_token_accuracy": 0.1668712839484215,
|
|
"num_tokens": 25070022.0,
|
|
"step": 14450
|
|
},
|
|
{
|
|
"entropy": 5.605709362030029,
|
|
"epoch": 1.1246450106983077,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.00048775330687605213,
|
|
"loss": 5.3215,
|
|
"mean_token_accuracy": 0.16896626800298692,
|
|
"num_tokens": 25078604.0,
|
|
"step": 14455
|
|
},
|
|
{
|
|
"entropy": 5.547206926345825,
|
|
"epoch": 1.1250340400700254,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004877442861099305,
|
|
"loss": 5.1993,
|
|
"mean_token_accuracy": 0.1766393095254898,
|
|
"num_tokens": 25087256.0,
|
|
"step": 14460
|
|
},
|
|
{
|
|
"entropy": 5.542341804504394,
|
|
"epoch": 1.1254230694417429,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.0004877352621157529,
|
|
"loss": 5.2768,
|
|
"mean_token_accuracy": 0.17198699563741685,
|
|
"num_tokens": 25095593.0,
|
|
"step": 14465
|
|
},
|
|
{
|
|
"entropy": 5.560934972763062,
|
|
"epoch": 1.1258120988134603,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.00048772623489365635,
|
|
"loss": 5.3341,
|
|
"mean_token_accuracy": 0.17415791749954224,
|
|
"num_tokens": 25104852.0,
|
|
"step": 14470
|
|
},
|
|
{
|
|
"entropy": 5.539960718154907,
|
|
"epoch": 1.126201128185178,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004877172044437777,
|
|
"loss": 5.3123,
|
|
"mean_token_accuracy": 0.17148227542638778,
|
|
"num_tokens": 25114453.0,
|
|
"step": 14475
|
|
},
|
|
{
|
|
"entropy": 5.502276039123535,
|
|
"epoch": 1.1265901575568955,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.00048770817076625416,
|
|
"loss": 5.3048,
|
|
"mean_token_accuracy": 0.17388371527194976,
|
|
"num_tokens": 25123733.0,
|
|
"step": 14480
|
|
},
|
|
{
|
|
"entropy": 5.490148496627808,
|
|
"epoch": 1.126979186928613,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.00048769913386122253,
|
|
"loss": 5.2261,
|
|
"mean_token_accuracy": 0.17898911088705063,
|
|
"num_tokens": 25132572.0,
|
|
"step": 14485
|
|
},
|
|
{
|
|
"entropy": 5.45403938293457,
|
|
"epoch": 1.1273682163003307,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004876900937288202,
|
|
"loss": 5.2571,
|
|
"mean_token_accuracy": 0.17854359596967698,
|
|
"num_tokens": 25141494.0,
|
|
"step": 14490
|
|
},
|
|
{
|
|
"entropy": 5.433139324188232,
|
|
"epoch": 1.1277572456720482,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.00048768105036918426,
|
|
"loss": 5.2129,
|
|
"mean_token_accuracy": 0.1757223427295685,
|
|
"num_tokens": 25150186.0,
|
|
"step": 14495
|
|
},
|
|
{
|
|
"entropy": 5.563412809371949,
|
|
"epoch": 1.1281462750437659,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.00048767200378245187,
|
|
"loss": 5.3077,
|
|
"mean_token_accuracy": 0.16997037082910538,
|
|
"num_tokens": 25159251.0,
|
|
"step": 14500
|
|
},
|
|
{
|
|
"entropy": 5.578856515884399,
|
|
"epoch": 1.1285353044154833,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.00048766295396876025,
|
|
"loss": 5.3103,
|
|
"mean_token_accuracy": 0.17455729991197586,
|
|
"num_tokens": 25167780.0,
|
|
"step": 14505
|
|
},
|
|
{
|
|
"entropy": 5.528367328643799,
|
|
"epoch": 1.128924333787201,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.00048765390092824683,
|
|
"loss": 5.2092,
|
|
"mean_token_accuracy": 0.18061490654945372,
|
|
"num_tokens": 25175358.0,
|
|
"step": 14510
|
|
},
|
|
{
|
|
"entropy": 5.4804182052612305,
|
|
"epoch": 1.1293133631589185,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.000487644844661049,
|
|
"loss": 5.2571,
|
|
"mean_token_accuracy": 0.16878363937139512,
|
|
"num_tokens": 25184247.0,
|
|
"step": 14515
|
|
},
|
|
{
|
|
"entropy": 5.45369668006897,
|
|
"epoch": 1.129702392530636,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.000487635785167304,
|
|
"loss": 5.1891,
|
|
"mean_token_accuracy": 0.1781545549631119,
|
|
"num_tokens": 25192311.0,
|
|
"step": 14520
|
|
},
|
|
{
|
|
"entropy": 5.438900709152222,
|
|
"epoch": 1.1300914219023537,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.00048762672244714953,
|
|
"loss": 5.2317,
|
|
"mean_token_accuracy": 0.1773073673248291,
|
|
"num_tokens": 25200861.0,
|
|
"step": 14525
|
|
},
|
|
{
|
|
"entropy": 5.553978395462036,
|
|
"epoch": 1.1304804512740712,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004876176565007229,
|
|
"loss": 5.3739,
|
|
"mean_token_accuracy": 0.17362226843833922,
|
|
"num_tokens": 25208938.0,
|
|
"step": 14530
|
|
},
|
|
{
|
|
"entropy": 5.598419666290283,
|
|
"epoch": 1.1308694806457888,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.00048760858732816174,
|
|
"loss": 5.2705,
|
|
"mean_token_accuracy": 0.1793088510632515,
|
|
"num_tokens": 25216997.0,
|
|
"step": 14535
|
|
},
|
|
{
|
|
"entropy": 5.50171012878418,
|
|
"epoch": 1.1312585100175063,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004875995149296037,
|
|
"loss": 5.1898,
|
|
"mean_token_accuracy": 0.1773835837841034,
|
|
"num_tokens": 25225205.0,
|
|
"step": 14540
|
|
},
|
|
{
|
|
"entropy": 5.476949024200439,
|
|
"epoch": 1.1316475393892238,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004875904393051864,
|
|
"loss": 5.2522,
|
|
"mean_token_accuracy": 0.1770787462592125,
|
|
"num_tokens": 25233807.0,
|
|
"step": 14545
|
|
},
|
|
{
|
|
"entropy": 5.501559400558472,
|
|
"epoch": 1.1320365687609415,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004875813604550476,
|
|
"loss": 5.2673,
|
|
"mean_token_accuracy": 0.169118233025074,
|
|
"num_tokens": 25241715.0,
|
|
"step": 14550
|
|
},
|
|
{
|
|
"entropy": 5.589974689483642,
|
|
"epoch": 1.132425598132659,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.00048757227837932494,
|
|
"loss": 5.3951,
|
|
"mean_token_accuracy": 0.1651352420449257,
|
|
"num_tokens": 25250418.0,
|
|
"step": 14555
|
|
},
|
|
{
|
|
"entropy": 5.5561353206634525,
|
|
"epoch": 1.1328146275043767,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004875631930781563,
|
|
"loss": 5.2879,
|
|
"mean_token_accuracy": 0.1675178065896034,
|
|
"num_tokens": 25259164.0,
|
|
"step": 14560
|
|
},
|
|
{
|
|
"entropy": 5.5276085376739506,
|
|
"epoch": 1.1332036568760941,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.00048755410455167967,
|
|
"loss": 5.3302,
|
|
"mean_token_accuracy": 0.17142942398786545,
|
|
"num_tokens": 25267902.0,
|
|
"step": 14565
|
|
},
|
|
{
|
|
"entropy": 5.522876644134522,
|
|
"epoch": 1.1335926862478116,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004875450128000326,
|
|
"loss": 5.2757,
|
|
"mean_token_accuracy": 0.16805899292230606,
|
|
"num_tokens": 25275991.0,
|
|
"step": 14570
|
|
},
|
|
{
|
|
"entropy": 5.52580041885376,
|
|
"epoch": 1.1339817156195293,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004875359178233534,
|
|
"loss": 5.2765,
|
|
"mean_token_accuracy": 0.17196872234344482,
|
|
"num_tokens": 25284454.0,
|
|
"step": 14575
|
|
},
|
|
{
|
|
"entropy": 5.604035186767578,
|
|
"epoch": 1.1343707449912468,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.00048752681962177985,
|
|
"loss": 5.3838,
|
|
"mean_token_accuracy": 0.16469692885875703,
|
|
"num_tokens": 25292867.0,
|
|
"step": 14580
|
|
},
|
|
{
|
|
"entropy": 5.543754291534424,
|
|
"epoch": 1.1347597743629645,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00048751771819545013,
|
|
"loss": 5.2724,
|
|
"mean_token_accuracy": 0.1736215054988861,
|
|
"num_tokens": 25301486.0,
|
|
"step": 14585
|
|
},
|
|
{
|
|
"entropy": 5.497570991516113,
|
|
"epoch": 1.135148803734682,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.00048750861354450236,
|
|
"loss": 5.2591,
|
|
"mean_token_accuracy": 0.17186922580003738,
|
|
"num_tokens": 25310800.0,
|
|
"step": 14590
|
|
},
|
|
{
|
|
"entropy": 5.563240098953247,
|
|
"epoch": 1.1355378331063994,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004874995056690746,
|
|
"loss": 5.3134,
|
|
"mean_token_accuracy": 0.17563033998012542,
|
|
"num_tokens": 25319063.0,
|
|
"step": 14595
|
|
},
|
|
{
|
|
"entropy": 5.639831590652466,
|
|
"epoch": 1.1359268624781171,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.000487490394569305,
|
|
"loss": 5.364,
|
|
"mean_token_accuracy": 0.16975239664316177,
|
|
"num_tokens": 25327817.0,
|
|
"step": 14600
|
|
},
|
|
{
|
|
"entropy": 5.545086622238159,
|
|
"epoch": 1.1363158918498346,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004874812802453319,
|
|
"loss": 5.1958,
|
|
"mean_token_accuracy": 0.1755492463707924,
|
|
"num_tokens": 25335753.0,
|
|
"step": 14605
|
|
},
|
|
{
|
|
"entropy": 5.520526933670044,
|
|
"epoch": 1.1367049212215523,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004874721626972936,
|
|
"loss": 5.3828,
|
|
"mean_token_accuracy": 0.1666047140955925,
|
|
"num_tokens": 25344514.0,
|
|
"step": 14610
|
|
},
|
|
{
|
|
"entropy": 5.554873514175415,
|
|
"epoch": 1.1370939505932698,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004874630419253284,
|
|
"loss": 5.3061,
|
|
"mean_token_accuracy": 0.17575568705797195,
|
|
"num_tokens": 25353003.0,
|
|
"step": 14615
|
|
},
|
|
{
|
|
"entropy": 5.550239753723145,
|
|
"epoch": 1.1374829799649873,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.00048745391792957474,
|
|
"loss": 5.2843,
|
|
"mean_token_accuracy": 0.1726512610912323,
|
|
"num_tokens": 25361599.0,
|
|
"step": 14620
|
|
},
|
|
{
|
|
"entropy": 5.561546659469604,
|
|
"epoch": 1.137872009336705,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.00048744479071017097,
|
|
"loss": 5.3446,
|
|
"mean_token_accuracy": 0.1625458464026451,
|
|
"num_tokens": 25370566.0,
|
|
"step": 14625
|
|
},
|
|
{
|
|
"entropy": 5.575703144073486,
|
|
"epoch": 1.1382610387084224,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004874356602672556,
|
|
"loss": 5.3284,
|
|
"mean_token_accuracy": 0.17115466445684432,
|
|
"num_tokens": 25379589.0,
|
|
"step": 14630
|
|
},
|
|
{
|
|
"entropy": 5.550799322128296,
|
|
"epoch": 1.1386500680801401,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.0004874265266009673,
|
|
"loss": 5.2631,
|
|
"mean_token_accuracy": 0.17970920950174332,
|
|
"num_tokens": 25387481.0,
|
|
"step": 14635
|
|
},
|
|
{
|
|
"entropy": 5.496348476409912,
|
|
"epoch": 1.1390390974518576,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004874173897114445,
|
|
"loss": 5.2754,
|
|
"mean_token_accuracy": 0.1765144497156143,
|
|
"num_tokens": 25395551.0,
|
|
"step": 14640
|
|
},
|
|
{
|
|
"entropy": 5.548038721084595,
|
|
"epoch": 1.1394281268235753,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00048740824959882603,
|
|
"loss": 5.3307,
|
|
"mean_token_accuracy": 0.1669141337275505,
|
|
"num_tokens": 25404303.0,
|
|
"step": 14645
|
|
},
|
|
{
|
|
"entropy": 5.560009288787842,
|
|
"epoch": 1.1398171561952928,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.0004873991062632504,
|
|
"loss": 5.3259,
|
|
"mean_token_accuracy": 0.16363555788993836,
|
|
"num_tokens": 25412749.0,
|
|
"step": 14650
|
|
},
|
|
{
|
|
"entropy": 5.536481618881226,
|
|
"epoch": 1.1402061855670103,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00048738995970485635,
|
|
"loss": 5.2707,
|
|
"mean_token_accuracy": 0.17230881601572037,
|
|
"num_tokens": 25421075.0,
|
|
"step": 14655
|
|
},
|
|
{
|
|
"entropy": 5.568193054199218,
|
|
"epoch": 1.140595214938728,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004873808099237827,
|
|
"loss": 5.3903,
|
|
"mean_token_accuracy": 0.16511864215135574,
|
|
"num_tokens": 25429750.0,
|
|
"step": 14660
|
|
},
|
|
{
|
|
"entropy": 5.561778736114502,
|
|
"epoch": 1.1409842443104454,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004873716569201684,
|
|
"loss": 5.2846,
|
|
"mean_token_accuracy": 0.17441572099924088,
|
|
"num_tokens": 25437686.0,
|
|
"step": 14665
|
|
},
|
|
{
|
|
"entropy": 5.516694164276123,
|
|
"epoch": 1.141373273682163,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.00048736250069415213,
|
|
"loss": 5.2944,
|
|
"mean_token_accuracy": 0.17406139373779297,
|
|
"num_tokens": 25446050.0,
|
|
"step": 14670
|
|
},
|
|
{
|
|
"entropy": 5.4934525966644285,
|
|
"epoch": 1.1417623030538806,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004873533412458729,
|
|
"loss": 5.3043,
|
|
"mean_token_accuracy": 0.1747289478778839,
|
|
"num_tokens": 25455134.0,
|
|
"step": 14675
|
|
},
|
|
{
|
|
"entropy": 5.469335746765137,
|
|
"epoch": 1.142151332425598,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.00048734417857546986,
|
|
"loss": 5.1802,
|
|
"mean_token_accuracy": 0.17695782482624053,
|
|
"num_tokens": 25463258.0,
|
|
"step": 14680
|
|
},
|
|
{
|
|
"entropy": 5.520489025115967,
|
|
"epoch": 1.1425403617973158,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004873350126830818,
|
|
"loss": 5.2667,
|
|
"mean_token_accuracy": 0.1761361226439476,
|
|
"num_tokens": 25472085.0,
|
|
"step": 14685
|
|
},
|
|
{
|
|
"entropy": 5.560411596298218,
|
|
"epoch": 1.1429293911690332,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004873258435688479,
|
|
"loss": 5.278,
|
|
"mean_token_accuracy": 0.17668423801660538,
|
|
"num_tokens": 25481233.0,
|
|
"step": 14690
|
|
},
|
|
{
|
|
"entropy": 5.53919677734375,
|
|
"epoch": 1.143318420540751,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004873166712329073,
|
|
"loss": 5.2557,
|
|
"mean_token_accuracy": 0.18044089078903197,
|
|
"num_tokens": 25490354.0,
|
|
"step": 14695
|
|
},
|
|
{
|
|
"entropy": 5.53734655380249,
|
|
"epoch": 1.1437074499124684,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.00048730749567539914,
|
|
"loss": 5.3147,
|
|
"mean_token_accuracy": 0.17236823439598084,
|
|
"num_tokens": 25498467.0,
|
|
"step": 14700
|
|
},
|
|
{
|
|
"entropy": 5.552510499954224,
|
|
"epoch": 1.144096479284186,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00048729831689646257,
|
|
"loss": 5.3095,
|
|
"mean_token_accuracy": 0.17018110156059266,
|
|
"num_tokens": 25507543.0,
|
|
"step": 14705
|
|
},
|
|
{
|
|
"entropy": 5.487798404693604,
|
|
"epoch": 1.1444855086559036,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.00048728913489623705,
|
|
"loss": 5.1964,
|
|
"mean_token_accuracy": 0.17983233481645583,
|
|
"num_tokens": 25516070.0,
|
|
"step": 14710
|
|
},
|
|
{
|
|
"entropy": 5.534903049468994,
|
|
"epoch": 1.144874538027621,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004872799496748618,
|
|
"loss": 5.3293,
|
|
"mean_token_accuracy": 0.17175545543432236,
|
|
"num_tokens": 25525216.0,
|
|
"step": 14715
|
|
},
|
|
{
|
|
"entropy": 5.579160737991333,
|
|
"epoch": 1.1452635673993385,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004872707612324761,
|
|
"loss": 5.3436,
|
|
"mean_token_accuracy": 0.1700536385178566,
|
|
"num_tokens": 25533822.0,
|
|
"step": 14720
|
|
},
|
|
{
|
|
"entropy": 5.660882616043091,
|
|
"epoch": 1.1456525967710562,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004872615695692196,
|
|
"loss": 5.3753,
|
|
"mean_token_accuracy": 0.16802987456321716,
|
|
"num_tokens": 25541580.0,
|
|
"step": 14725
|
|
},
|
|
{
|
|
"entropy": 5.484453248977661,
|
|
"epoch": 1.1460416261427737,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004872523746852315,
|
|
"loss": 5.1773,
|
|
"mean_token_accuracy": 0.18269246816635132,
|
|
"num_tokens": 25549860.0,
|
|
"step": 14730
|
|
},
|
|
{
|
|
"entropy": 5.52522029876709,
|
|
"epoch": 1.1464306555144914,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00048724317658065146,
|
|
"loss": 5.3442,
|
|
"mean_token_accuracy": 0.16894873529672622,
|
|
"num_tokens": 25559060.0,
|
|
"step": 14735
|
|
},
|
|
{
|
|
"entropy": 5.63541898727417,
|
|
"epoch": 1.146819684886209,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.00048723397525561916,
|
|
"loss": 5.3874,
|
|
"mean_token_accuracy": 0.16443771123886108,
|
|
"num_tokens": 25567769.0,
|
|
"step": 14740
|
|
},
|
|
{
|
|
"entropy": 5.571277809143067,
|
|
"epoch": 1.1472087142579266,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.00048722477071027394,
|
|
"loss": 5.3654,
|
|
"mean_token_accuracy": 0.1711871936917305,
|
|
"num_tokens": 25577443.0,
|
|
"step": 14745
|
|
},
|
|
{
|
|
"entropy": 5.569605827331543,
|
|
"epoch": 1.147597743629644,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00048721556294475574,
|
|
"loss": 5.2731,
|
|
"mean_token_accuracy": 0.18160714358091354,
|
|
"num_tokens": 25586283.0,
|
|
"step": 14750
|
|
},
|
|
{
|
|
"entropy": 5.551212406158447,
|
|
"epoch": 1.1479867730013615,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.00048720635195920403,
|
|
"loss": 5.3753,
|
|
"mean_token_accuracy": 0.17017149925231934,
|
|
"num_tokens": 25594881.0,
|
|
"step": 14755
|
|
},
|
|
{
|
|
"entropy": 5.50782527923584,
|
|
"epoch": 1.1483758023730792,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004871971377537588,
|
|
"loss": 5.2436,
|
|
"mean_token_accuracy": 0.1762669488787651,
|
|
"num_tokens": 25603738.0,
|
|
"step": 14760
|
|
},
|
|
{
|
|
"entropy": 5.583714962005615,
|
|
"epoch": 1.1487648317447967,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004871879203285597,
|
|
"loss": 5.298,
|
|
"mean_token_accuracy": 0.17087433785200118,
|
|
"num_tokens": 25611780.0,
|
|
"step": 14765
|
|
},
|
|
{
|
|
"entropy": 5.606764793395996,
|
|
"epoch": 1.1491538611165142,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.00048717869968374655,
|
|
"loss": 5.3617,
|
|
"mean_token_accuracy": 0.17412520051002503,
|
|
"num_tokens": 25620489.0,
|
|
"step": 14770
|
|
},
|
|
{
|
|
"entropy": 5.522389936447143,
|
|
"epoch": 1.1495428904882319,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.00048716947581945954,
|
|
"loss": 5.3226,
|
|
"mean_token_accuracy": 0.1770711585879326,
|
|
"num_tokens": 25629113.0,
|
|
"step": 14775
|
|
},
|
|
{
|
|
"entropy": 5.464048576354981,
|
|
"epoch": 1.1499319198599494,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004871602487358383,
|
|
"loss": 5.2657,
|
|
"mean_token_accuracy": 0.1724536433815956,
|
|
"num_tokens": 25637313.0,
|
|
"step": 14780
|
|
},
|
|
{
|
|
"entropy": 5.5214461326599125,
|
|
"epoch": 1.150320949231667,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.000487151018433023,
|
|
"loss": 5.3576,
|
|
"mean_token_accuracy": 0.16645698100328446,
|
|
"num_tokens": 25646522.0,
|
|
"step": 14785
|
|
},
|
|
{
|
|
"entropy": 5.5282148838043215,
|
|
"epoch": 1.1507099786033845,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.00048714178491115367,
|
|
"loss": 5.2638,
|
|
"mean_token_accuracy": 0.17899245619773865,
|
|
"num_tokens": 25656058.0,
|
|
"step": 14790
|
|
},
|
|
{
|
|
"entropy": 5.586183786392212,
|
|
"epoch": 1.1510990079751022,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.00048713254817037046,
|
|
"loss": 5.3711,
|
|
"mean_token_accuracy": 0.17049205154180527,
|
|
"num_tokens": 25665072.0,
|
|
"step": 14795
|
|
},
|
|
{
|
|
"entropy": 5.607844257354737,
|
|
"epoch": 1.1514880373468197,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004871233082108135,
|
|
"loss": 5.4,
|
|
"mean_token_accuracy": 0.1711244061589241,
|
|
"num_tokens": 25673877.0,
|
|
"step": 14800
|
|
},
|
|
{
|
|
"entropy": 5.582855701446533,
|
|
"epoch": 1.1518770667185372,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004871140650326228,
|
|
"loss": 5.2596,
|
|
"mean_token_accuracy": 0.16818197667598725,
|
|
"num_tokens": 25683238.0,
|
|
"step": 14805
|
|
},
|
|
{
|
|
"entropy": 5.579865217208862,
|
|
"epoch": 1.1522660960902549,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004871048186359389,
|
|
"loss": 5.3595,
|
|
"mean_token_accuracy": 0.16232425570487977,
|
|
"num_tokens": 25692654.0,
|
|
"step": 14810
|
|
},
|
|
{
|
|
"entropy": 5.650218391418457,
|
|
"epoch": 1.1526551254619724,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.000487095569020902,
|
|
"loss": 5.3455,
|
|
"mean_token_accuracy": 0.16748398393392563,
|
|
"num_tokens": 25701681.0,
|
|
"step": 14815
|
|
},
|
|
{
|
|
"entropy": 5.566237306594848,
|
|
"epoch": 1.1530441548336898,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004870863161876524,
|
|
"loss": 5.26,
|
|
"mean_token_accuracy": 0.17767535746097565,
|
|
"num_tokens": 25709848.0,
|
|
"step": 14820
|
|
},
|
|
{
|
|
"entropy": 5.603987169265747,
|
|
"epoch": 1.1534331842054075,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004870770601363305,
|
|
"loss": 5.4981,
|
|
"mean_token_accuracy": 0.16868632584810256,
|
|
"num_tokens": 25717993.0,
|
|
"step": 14825
|
|
},
|
|
{
|
|
"entropy": 5.587001705169678,
|
|
"epoch": 1.153822213577125,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.00048706780086707675,
|
|
"loss": 5.3808,
|
|
"mean_token_accuracy": 0.16602419465780258,
|
|
"num_tokens": 25726379.0,
|
|
"step": 14830
|
|
},
|
|
{
|
|
"entropy": 5.568260240554809,
|
|
"epoch": 1.1542112429488427,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004870585383800317,
|
|
"loss": 5.2919,
|
|
"mean_token_accuracy": 0.1783009275794029,
|
|
"num_tokens": 25734968.0,
|
|
"step": 14835
|
|
},
|
|
{
|
|
"entropy": 5.586294174194336,
|
|
"epoch": 1.1546002723205602,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.00048704927267533585,
|
|
"loss": 5.3333,
|
|
"mean_token_accuracy": 0.1721921294927597,
|
|
"num_tokens": 25743315.0,
|
|
"step": 14840
|
|
},
|
|
{
|
|
"entropy": 5.529369783401489,
|
|
"epoch": 1.1549893016922779,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.00048704000375312975,
|
|
"loss": 5.2378,
|
|
"mean_token_accuracy": 0.17137032002210617,
|
|
"num_tokens": 25752396.0,
|
|
"step": 14845
|
|
},
|
|
{
|
|
"entropy": 5.614004516601563,
|
|
"epoch": 1.1553783310639953,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.00048703073161355414,
|
|
"loss": 5.3635,
|
|
"mean_token_accuracy": 0.1709185004234314,
|
|
"num_tokens": 25761142.0,
|
|
"step": 14850
|
|
},
|
|
{
|
|
"entropy": 5.493571329116821,
|
|
"epoch": 1.1557673604357128,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004870214562567497,
|
|
"loss": 5.24,
|
|
"mean_token_accuracy": 0.17272724956274033,
|
|
"num_tokens": 25769514.0,
|
|
"step": 14855
|
|
},
|
|
{
|
|
"entropy": 5.521751976013183,
|
|
"epoch": 1.1561563898074305,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.000487012177682857,
|
|
"loss": 5.2379,
|
|
"mean_token_accuracy": 0.17054518312215805,
|
|
"num_tokens": 25777408.0,
|
|
"step": 14860
|
|
},
|
|
{
|
|
"entropy": 5.4967021465301515,
|
|
"epoch": 1.156545419179148,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004870028958920171,
|
|
"loss": 5.259,
|
|
"mean_token_accuracy": 0.1768237456679344,
|
|
"num_tokens": 25785646.0,
|
|
"step": 14865
|
|
},
|
|
{
|
|
"entropy": 5.544138431549072,
|
|
"epoch": 1.1569344485508655,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004869936108843706,
|
|
"loss": 5.3095,
|
|
"mean_token_accuracy": 0.17224012017250062,
|
|
"num_tokens": 25794007.0,
|
|
"step": 14870
|
|
},
|
|
{
|
|
"entropy": 5.52902307510376,
|
|
"epoch": 1.1573234779225832,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.00048698432266005854,
|
|
"loss": 5.2489,
|
|
"mean_token_accuracy": 0.17344386130571365,
|
|
"num_tokens": 25802765.0,
|
|
"step": 14875
|
|
},
|
|
{
|
|
"entropy": 5.590705871582031,
|
|
"epoch": 1.1577125072943006,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004869750312192217,
|
|
"loss": 5.3886,
|
|
"mean_token_accuracy": 0.16790701746940612,
|
|
"num_tokens": 25811214.0,
|
|
"step": 14880
|
|
},
|
|
{
|
|
"entropy": 5.591983604431152,
|
|
"epoch": 1.1581015366660183,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.00048696573656200123,
|
|
"loss": 5.3748,
|
|
"mean_token_accuracy": 0.16566506028175354,
|
|
"num_tokens": 25820350.0,
|
|
"step": 14885
|
|
},
|
|
{
|
|
"entropy": 5.553336143493652,
|
|
"epoch": 1.1584905660377358,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.00048695643868853806,
|
|
"loss": 5.2935,
|
|
"mean_token_accuracy": 0.18036726415157317,
|
|
"num_tokens": 25828088.0,
|
|
"step": 14890
|
|
},
|
|
{
|
|
"entropy": 5.5192883014678955,
|
|
"epoch": 1.1588795954094535,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 0.0004869471375989733,
|
|
"loss": 5.1599,
|
|
"mean_token_accuracy": 0.181265027821064,
|
|
"num_tokens": 25835909.0,
|
|
"step": 14895
|
|
},
|
|
{
|
|
"entropy": 5.452424430847168,
|
|
"epoch": 1.159268624781171,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004869378332934481,
|
|
"loss": 5.2502,
|
|
"mean_token_accuracy": 0.17498199492692948,
|
|
"num_tokens": 25844360.0,
|
|
"step": 14900
|
|
},
|
|
{
|
|
"entropy": 5.651251745223999,
|
|
"epoch": 1.1596576541528885,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00048692852577210356,
|
|
"loss": 5.3665,
|
|
"mean_token_accuracy": 0.16494977325201035,
|
|
"num_tokens": 25853877.0,
|
|
"step": 14905
|
|
},
|
|
{
|
|
"entropy": 5.559357833862305,
|
|
"epoch": 1.1600466835246062,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.000486919215035081,
|
|
"loss": 5.2664,
|
|
"mean_token_accuracy": 0.175713013112545,
|
|
"num_tokens": 25862200.0,
|
|
"step": 14910
|
|
},
|
|
{
|
|
"entropy": 5.501112365722657,
|
|
"epoch": 1.1604357128963236,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.0004869099010825217,
|
|
"loss": 5.2218,
|
|
"mean_token_accuracy": 0.17241571992635726,
|
|
"num_tokens": 25871112.0,
|
|
"step": 14915
|
|
},
|
|
{
|
|
"entropy": 5.54647421836853,
|
|
"epoch": 1.1608247422680413,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.00048690058391456684,
|
|
"loss": 5.3928,
|
|
"mean_token_accuracy": 0.1711567685008049,
|
|
"num_tokens": 25880135.0,
|
|
"step": 14920
|
|
},
|
|
{
|
|
"entropy": 5.55512957572937,
|
|
"epoch": 1.1612137716397588,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.0004868912635313579,
|
|
"loss": 5.2908,
|
|
"mean_token_accuracy": 0.17410618662834168,
|
|
"num_tokens": 25888609.0,
|
|
"step": 14925
|
|
},
|
|
{
|
|
"entropy": 5.525064182281494,
|
|
"epoch": 1.1616028010114763,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004868819399330364,
|
|
"loss": 5.3393,
|
|
"mean_token_accuracy": 0.16897253096103668,
|
|
"num_tokens": 25897254.0,
|
|
"step": 14930
|
|
},
|
|
{
|
|
"entropy": 5.549260139465332,
|
|
"epoch": 1.161991830383194,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004868726131197436,
|
|
"loss": 5.2525,
|
|
"mean_token_accuracy": 0.18024791330099105,
|
|
"num_tokens": 25905705.0,
|
|
"step": 14935
|
|
},
|
|
{
|
|
"entropy": 5.559958553314209,
|
|
"epoch": 1.1623808597549115,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004868632830916212,
|
|
"loss": 5.3027,
|
|
"mean_token_accuracy": 0.17200768291950225,
|
|
"num_tokens": 25914066.0,
|
|
"step": 14940
|
|
},
|
|
{
|
|
"entropy": 5.540140581130982,
|
|
"epoch": 1.1627698891266292,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004868539498488106,
|
|
"loss": 5.3123,
|
|
"mean_token_accuracy": 0.17349241077899932,
|
|
"num_tokens": 25922949.0,
|
|
"step": 14945
|
|
},
|
|
{
|
|
"entropy": 5.418867826461792,
|
|
"epoch": 1.1631589184983466,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004868446133914536,
|
|
"loss": 5.1618,
|
|
"mean_token_accuracy": 0.1807738795876503,
|
|
"num_tokens": 25931465.0,
|
|
"step": 14950
|
|
},
|
|
{
|
|
"entropy": 5.532193613052368,
|
|
"epoch": 1.163547947870064,
|
|
"grad_norm": 2.59375,
|
|
"learning_rate": 0.00048683527371969185,
|
|
"loss": 5.3353,
|
|
"mean_token_accuracy": 0.16627979129552842,
|
|
"num_tokens": 25941014.0,
|
|
"step": 14955
|
|
},
|
|
{
|
|
"entropy": 5.4955915927886965,
|
|
"epoch": 1.1639369772417818,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.00048682593083366685,
|
|
"loss": 5.1995,
|
|
"mean_token_accuracy": 0.17250516265630722,
|
|
"num_tokens": 25950275.0,
|
|
"step": 14960
|
|
},
|
|
{
|
|
"entropy": 5.443646240234375,
|
|
"epoch": 1.1643260066134993,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.00048681658473352055,
|
|
"loss": 5.3219,
|
|
"mean_token_accuracy": 0.16984528303146362,
|
|
"num_tokens": 25959138.0,
|
|
"step": 14965
|
|
},
|
|
{
|
|
"entropy": 5.578936243057251,
|
|
"epoch": 1.164715035985217,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004868072354193947,
|
|
"loss": 5.2048,
|
|
"mean_token_accuracy": 0.17416904121637344,
|
|
"num_tokens": 25967221.0,
|
|
"step": 14970
|
|
},
|
|
{
|
|
"entropy": 5.571450471878052,
|
|
"epoch": 1.1651040653569344,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004867978828914312,
|
|
"loss": 5.3198,
|
|
"mean_token_accuracy": 0.1704607143998146,
|
|
"num_tokens": 25976194.0,
|
|
"step": 14975
|
|
},
|
|
{
|
|
"entropy": 5.500711488723755,
|
|
"epoch": 1.165493094728652,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004867885271497719,
|
|
"loss": 5.286,
|
|
"mean_token_accuracy": 0.17450777888298036,
|
|
"num_tokens": 25985493.0,
|
|
"step": 14980
|
|
},
|
|
{
|
|
"entropy": 5.583955335617065,
|
|
"epoch": 1.1658821241003696,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004867791681945588,
|
|
"loss": 5.2399,
|
|
"mean_token_accuracy": 0.17097237408161164,
|
|
"num_tokens": 25994213.0,
|
|
"step": 14985
|
|
},
|
|
{
|
|
"entropy": 5.493848705291748,
|
|
"epoch": 1.166271153472087,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.00048676980602593395,
|
|
"loss": 5.2218,
|
|
"mean_token_accuracy": 0.1793581262230873,
|
|
"num_tokens": 26003164.0,
|
|
"step": 14990
|
|
},
|
|
{
|
|
"entropy": 5.572969436645508,
|
|
"epoch": 1.1666601828438048,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.00048676044064403936,
|
|
"loss": 5.3306,
|
|
"mean_token_accuracy": 0.17016486078500748,
|
|
"num_tokens": 26012049.0,
|
|
"step": 14995
|
|
},
|
|
{
|
|
"entropy": 5.645019149780273,
|
|
"epoch": 1.1670492122155223,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.0004867510720490171,
|
|
"loss": 5.4245,
|
|
"mean_token_accuracy": 0.16362651586532592,
|
|
"num_tokens": 26020466.0,
|
|
"step": 15000
|
|
},
|
|
{
|
|
"epoch": 1.1670492122155223,
|
|
"eval_entropy": 5.440363345178305,
|
|
"eval_loss": 5.406432151794434,
|
|
"eval_mean_token_accuracy": 0.17719353199062493,
|
|
"eval_num_tokens": 26020466.0,
|
|
"eval_runtime": 28.5321,
|
|
"eval_samples_per_second": 1456.537,
|
|
"eval_steps_per_second": 182.076,
|
|
"step": 15000
|
|
}
|
|
],
|
|
"logging_steps": 5,
|
|
"max_steps": 128520,
|
|
"num_input_tokens_seen": 0,
|
|
"num_train_epochs": 10,
|
|
"save_steps": 3000,
|
|
"stateful_callbacks": {
|
|
"TrainerControl": {
|
|
"args": {
|
|
"should_epoch_stop": false,
|
|
"should_evaluate": false,
|
|
"should_log": false,
|
|
"should_save": true,
|
|
"should_training_stop": false
|
|
},
|
|
"attributes": {}
|
|
}
|
|
},
|
|
"total_flos": 3.5344720041984e+16,
|
|
"train_batch_size": 16,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|