12057 lines
329 KiB
JSON
12057 lines
329 KiB
JSON
{
|
|
"best_global_step": null,
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 0.4668352460610776,
|
|
"eval_steps": 3000,
|
|
"global_step": 6000,
|
|
"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
|
|
}
|
|
],
|
|
"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": 1.4145558571008e+16,
|
|
"train_batch_size": 16,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|