72c2634cda
Model: fpadovani/ind-latn-10mb-after-ppt-shuff-dyck-100mb-ckpt500_seed455 Source: Original Platform
6046 lines
164 KiB
JSON
6046 lines
164 KiB
JSON
{
|
|
"best_global_step": null,
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 0.2334176230305388,
|
|
"eval_steps": 3000,
|
|
"global_step": 3000,
|
|
"is_hyper_param_search": false,
|
|
"is_local_process_zero": true,
|
|
"is_world_process_zero": true,
|
|
"log_history": [
|
|
{
|
|
"entropy": 4.9352446556091305,
|
|
"epoch": 0.00038902937171756465,
|
|
"grad_norm": 13.375,
|
|
"learning_rate": 2e-06,
|
|
"loss": 14.3638,
|
|
"mean_token_accuracy": 0.0,
|
|
"num_tokens": 9243.0,
|
|
"step": 5
|
|
},
|
|
{
|
|
"entropy": 4.933586740493775,
|
|
"epoch": 0.0007780587434351293,
|
|
"grad_norm": 13.5625,
|
|
"learning_rate": 4.5e-06,
|
|
"loss": 14.3351,
|
|
"mean_token_accuracy": 0.0,
|
|
"num_tokens": 18424.0,
|
|
"step": 10
|
|
},
|
|
{
|
|
"entropy": 4.954997825622558,
|
|
"epoch": 0.001167088115152694,
|
|
"grad_norm": 14.8125,
|
|
"learning_rate": 7e-06,
|
|
"loss": 14.2409,
|
|
"mean_token_accuracy": 0.0,
|
|
"num_tokens": 27006.0,
|
|
"step": 15
|
|
},
|
|
{
|
|
"entropy": 4.98590784072876,
|
|
"epoch": 0.0015561174868702586,
|
|
"grad_norm": 17.625,
|
|
"learning_rate": 9.5e-06,
|
|
"loss": 14.0569,
|
|
"mean_token_accuracy": 0.0,
|
|
"num_tokens": 35577.0,
|
|
"step": 20
|
|
},
|
|
{
|
|
"entropy": 5.102123737335205,
|
|
"epoch": 0.0019451468585878235,
|
|
"grad_norm": 21.875,
|
|
"learning_rate": 1.2e-05,
|
|
"loss": 13.6317,
|
|
"mean_token_accuracy": 0.0,
|
|
"num_tokens": 43706.0,
|
|
"step": 25
|
|
},
|
|
{
|
|
"entropy": 5.41047158241272,
|
|
"epoch": 0.002334176230305388,
|
|
"grad_norm": 28.25,
|
|
"learning_rate": 1.4500000000000002e-05,
|
|
"loss": 13.0807,
|
|
"mean_token_accuracy": 0.0,
|
|
"num_tokens": 52571.0,
|
|
"step": 30
|
|
},
|
|
{
|
|
"entropy": 6.994736385345459,
|
|
"epoch": 0.0027232056020229526,
|
|
"grad_norm": 23.125,
|
|
"learning_rate": 1.7000000000000003e-05,
|
|
"loss": 11.9622,
|
|
"mean_token_accuracy": 0.0,
|
|
"num_tokens": 61900.0,
|
|
"step": 35
|
|
},
|
|
{
|
|
"entropy": 10.197742652893066,
|
|
"epoch": 0.0031122349737405172,
|
|
"grad_norm": 3.296875,
|
|
"learning_rate": 1.95e-05,
|
|
"loss": 10.8537,
|
|
"mean_token_accuracy": 0.0009407172445207834,
|
|
"num_tokens": 71234.0,
|
|
"step": 40
|
|
},
|
|
{
|
|
"entropy": 10.716931438446045,
|
|
"epoch": 0.003501264345458082,
|
|
"grad_norm": 3.46875,
|
|
"learning_rate": 2.2e-05,
|
|
"loss": 10.6567,
|
|
"mean_token_accuracy": 0.014731284510344268,
|
|
"num_tokens": 79610.0,
|
|
"step": 45
|
|
},
|
|
{
|
|
"entropy": 10.737910270690918,
|
|
"epoch": 0.003890293717175647,
|
|
"grad_norm": 3.0625,
|
|
"learning_rate": 2.4500000000000003e-05,
|
|
"loss": 10.5096,
|
|
"mean_token_accuracy": 0.021222466975450514,
|
|
"num_tokens": 87527.0,
|
|
"step": 50
|
|
},
|
|
{
|
|
"entropy": 10.68083963394165,
|
|
"epoch": 0.004279323088893211,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 2.7e-05,
|
|
"loss": 10.3385,
|
|
"mean_token_accuracy": 0.021166695561259986,
|
|
"num_tokens": 95512.0,
|
|
"step": 55
|
|
},
|
|
{
|
|
"entropy": 10.617268085479736,
|
|
"epoch": 0.004668352460610776,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 2.95e-05,
|
|
"loss": 10.2086,
|
|
"mean_token_accuracy": 0.018889906629920006,
|
|
"num_tokens": 104395.0,
|
|
"step": 60
|
|
},
|
|
{
|
|
"entropy": 10.707407093048095,
|
|
"epoch": 0.0050573818323283405,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 3.2e-05,
|
|
"loss": 10.0297,
|
|
"mean_token_accuracy": 0.02151527740061283,
|
|
"num_tokens": 112562.0,
|
|
"step": 65
|
|
},
|
|
{
|
|
"entropy": 10.726566791534424,
|
|
"epoch": 0.005446411204045905,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 3.4500000000000005e-05,
|
|
"loss": 9.9483,
|
|
"mean_token_accuracy": 0.03697771243751049,
|
|
"num_tokens": 121962.0,
|
|
"step": 70
|
|
},
|
|
{
|
|
"entropy": 10.715249347686768,
|
|
"epoch": 0.00583544057576347,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 3.7e-05,
|
|
"loss": 9.9014,
|
|
"mean_token_accuracy": 0.05064300559461117,
|
|
"num_tokens": 130714.0,
|
|
"step": 75
|
|
},
|
|
{
|
|
"entropy": 10.702756023406982,
|
|
"epoch": 0.0062244699474810344,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 3.95e-05,
|
|
"loss": 9.8032,
|
|
"mean_token_accuracy": 0.03924348317086697,
|
|
"num_tokens": 139674.0,
|
|
"step": 80
|
|
},
|
|
{
|
|
"entropy": 10.711318397521973,
|
|
"epoch": 0.006613499319198599,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 4.2000000000000004e-05,
|
|
"loss": 9.6945,
|
|
"mean_token_accuracy": 0.05025743767619133,
|
|
"num_tokens": 148654.0,
|
|
"step": 85
|
|
},
|
|
{
|
|
"entropy": 10.706228637695313,
|
|
"epoch": 0.007002528690916164,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 4.45e-05,
|
|
"loss": 9.5288,
|
|
"mean_token_accuracy": 0.05727620646357536,
|
|
"num_tokens": 156180.0,
|
|
"step": 90
|
|
},
|
|
{
|
|
"entropy": 10.672399044036865,
|
|
"epoch": 0.007391558062633729,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 4.7000000000000004e-05,
|
|
"loss": 9.5166,
|
|
"mean_token_accuracy": 0.04150119200348854,
|
|
"num_tokens": 165608.0,
|
|
"step": 95
|
|
},
|
|
{
|
|
"entropy": 10.661020946502685,
|
|
"epoch": 0.007780587434351294,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 4.9500000000000004e-05,
|
|
"loss": 9.3671,
|
|
"mean_token_accuracy": 0.052654581516981123,
|
|
"num_tokens": 173871.0,
|
|
"step": 100
|
|
},
|
|
{
|
|
"entropy": 10.639804267883301,
|
|
"epoch": 0.008169616806068859,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 5.2e-05,
|
|
"loss": 9.278,
|
|
"mean_token_accuracy": 0.053280239924788475,
|
|
"num_tokens": 182356.0,
|
|
"step": 105
|
|
},
|
|
{
|
|
"entropy": 10.586706256866455,
|
|
"epoch": 0.008558646177786422,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 5.45e-05,
|
|
"loss": 9.1642,
|
|
"mean_token_accuracy": 0.05218262672424316,
|
|
"num_tokens": 190361.0,
|
|
"step": 110
|
|
},
|
|
{
|
|
"entropy": 10.545366954803466,
|
|
"epoch": 0.008947675549503988,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 5.7e-05,
|
|
"loss": 9.038,
|
|
"mean_token_accuracy": 0.06131550520658493,
|
|
"num_tokens": 199253.0,
|
|
"step": 115
|
|
},
|
|
{
|
|
"entropy": 10.458304595947265,
|
|
"epoch": 0.009336704921221552,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 5.9499999999999996e-05,
|
|
"loss": 8.941,
|
|
"mean_token_accuracy": 0.05900274179875851,
|
|
"num_tokens": 208181.0,
|
|
"step": 120
|
|
},
|
|
{
|
|
"entropy": 10.377948665618897,
|
|
"epoch": 0.009725734292939117,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 6.2e-05,
|
|
"loss": 8.8182,
|
|
"mean_token_accuracy": 0.06022760644555092,
|
|
"num_tokens": 216898.0,
|
|
"step": 125
|
|
},
|
|
{
|
|
"entropy": 10.340231990814209,
|
|
"epoch": 0.010114763664656681,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 6.450000000000001e-05,
|
|
"loss": 8.7216,
|
|
"mean_token_accuracy": 0.059017321839928624,
|
|
"num_tokens": 226051.0,
|
|
"step": 130
|
|
},
|
|
{
|
|
"entropy": 10.248167514801025,
|
|
"epoch": 0.010503793036374246,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 6.7e-05,
|
|
"loss": 8.6303,
|
|
"mean_token_accuracy": 0.05895141884684563,
|
|
"num_tokens": 235018.0,
|
|
"step": 135
|
|
},
|
|
{
|
|
"entropy": 10.186167526245118,
|
|
"epoch": 0.01089282240809181,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 6.950000000000001e-05,
|
|
"loss": 8.4974,
|
|
"mean_token_accuracy": 0.056320498883724215,
|
|
"num_tokens": 244268.0,
|
|
"step": 140
|
|
},
|
|
{
|
|
"entropy": 10.056542587280273,
|
|
"epoch": 0.011281851779809376,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 7.2e-05,
|
|
"loss": 8.401,
|
|
"mean_token_accuracy": 0.05752755627036095,
|
|
"num_tokens": 253545.0,
|
|
"step": 145
|
|
},
|
|
{
|
|
"entropy": 9.921157741546631,
|
|
"epoch": 0.01167088115152694,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 7.45e-05,
|
|
"loss": 8.201,
|
|
"mean_token_accuracy": 0.06480571478605271,
|
|
"num_tokens": 261767.0,
|
|
"step": 150
|
|
},
|
|
{
|
|
"entropy": 9.763555145263672,
|
|
"epoch": 0.012059910523244505,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 7.7e-05,
|
|
"loss": 8.1694,
|
|
"mean_token_accuracy": 0.060174553841352466,
|
|
"num_tokens": 270372.0,
|
|
"step": 155
|
|
},
|
|
{
|
|
"entropy": 9.612780094146729,
|
|
"epoch": 0.012448939894962069,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 7.950000000000001e-05,
|
|
"loss": 8.13,
|
|
"mean_token_accuracy": 0.05902123637497425,
|
|
"num_tokens": 279726.0,
|
|
"step": 160
|
|
},
|
|
{
|
|
"entropy": 9.454668998718262,
|
|
"epoch": 0.012837969266679634,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 8.2e-05,
|
|
"loss": 8.0495,
|
|
"mean_token_accuracy": 0.05770065151154995,
|
|
"num_tokens": 288955.0,
|
|
"step": 165
|
|
},
|
|
{
|
|
"entropy": 9.253509902954102,
|
|
"epoch": 0.013226998638397198,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 8.450000000000001e-05,
|
|
"loss": 7.9255,
|
|
"mean_token_accuracy": 0.05795506499707699,
|
|
"num_tokens": 297898.0,
|
|
"step": 170
|
|
},
|
|
{
|
|
"entropy": 9.027568244934082,
|
|
"epoch": 0.013616028010114764,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 8.7e-05,
|
|
"loss": 7.8475,
|
|
"mean_token_accuracy": 0.06472490318119525,
|
|
"num_tokens": 306189.0,
|
|
"step": 175
|
|
},
|
|
{
|
|
"entropy": 8.855317306518554,
|
|
"epoch": 0.014005057381832327,
|
|
"grad_norm": 0.75390625,
|
|
"learning_rate": 8.95e-05,
|
|
"loss": 7.7903,
|
|
"mean_token_accuracy": 0.05992711745202541,
|
|
"num_tokens": 314881.0,
|
|
"step": 180
|
|
},
|
|
{
|
|
"entropy": 8.634145164489746,
|
|
"epoch": 0.014394086753549893,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 9.2e-05,
|
|
"loss": 7.7628,
|
|
"mean_token_accuracy": 0.05949850864708424,
|
|
"num_tokens": 323357.0,
|
|
"step": 185
|
|
},
|
|
{
|
|
"entropy": 8.52868824005127,
|
|
"epoch": 0.014783116125267459,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 9.45e-05,
|
|
"loss": 7.7934,
|
|
"mean_token_accuracy": 0.06202235743403435,
|
|
"num_tokens": 331799.0,
|
|
"step": 190
|
|
},
|
|
{
|
|
"entropy": 8.411410522460937,
|
|
"epoch": 0.015172145496985022,
|
|
"grad_norm": 0.75390625,
|
|
"learning_rate": 9.7e-05,
|
|
"loss": 7.6607,
|
|
"mean_token_accuracy": 0.06408823989331722,
|
|
"num_tokens": 340320.0,
|
|
"step": 195
|
|
},
|
|
{
|
|
"entropy": 8.311204147338866,
|
|
"epoch": 0.015561174868702588,
|
|
"grad_norm": 0.74609375,
|
|
"learning_rate": 9.95e-05,
|
|
"loss": 7.6695,
|
|
"mean_token_accuracy": 0.06163757778704167,
|
|
"num_tokens": 348990.0,
|
|
"step": 200
|
|
},
|
|
{
|
|
"entropy": 8.226022624969483,
|
|
"epoch": 0.01595020424042015,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.000102,
|
|
"loss": 7.6319,
|
|
"mean_token_accuracy": 0.06188234388828277,
|
|
"num_tokens": 357661.0,
|
|
"step": 205
|
|
},
|
|
{
|
|
"entropy": 8.203551959991454,
|
|
"epoch": 0.016339233612137717,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.00010449999999999999,
|
|
"loss": 7.5957,
|
|
"mean_token_accuracy": 0.06355586163699627,
|
|
"num_tokens": 366099.0,
|
|
"step": 210
|
|
},
|
|
{
|
|
"entropy": 8.117009258270263,
|
|
"epoch": 0.016728262983855283,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.000107,
|
|
"loss": 7.7405,
|
|
"mean_token_accuracy": 0.05980301797389984,
|
|
"num_tokens": 374926.0,
|
|
"step": 215
|
|
},
|
|
{
|
|
"entropy": 8.17076997756958,
|
|
"epoch": 0.017117292355572845,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0001095,
|
|
"loss": 7.6617,
|
|
"mean_token_accuracy": 0.06195650584995747,
|
|
"num_tokens": 383846.0,
|
|
"step": 220
|
|
},
|
|
{
|
|
"entropy": 8.05511932373047,
|
|
"epoch": 0.01750632172729041,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.000112,
|
|
"loss": 7.6259,
|
|
"mean_token_accuracy": 0.06483461409807205,
|
|
"num_tokens": 393678.0,
|
|
"step": 225
|
|
},
|
|
{
|
|
"entropy": 8.157504177093506,
|
|
"epoch": 0.017895351099007976,
|
|
"grad_norm": 0.75390625,
|
|
"learning_rate": 0.0001145,
|
|
"loss": 7.661,
|
|
"mean_token_accuracy": 0.0653709027916193,
|
|
"num_tokens": 401866.0,
|
|
"step": 230
|
|
},
|
|
{
|
|
"entropy": 8.015466785430908,
|
|
"epoch": 0.01828438047072554,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00011700000000000001,
|
|
"loss": 7.6346,
|
|
"mean_token_accuracy": 0.06497575715184212,
|
|
"num_tokens": 411057.0,
|
|
"step": 235
|
|
},
|
|
{
|
|
"entropy": 8.082311630249023,
|
|
"epoch": 0.018673409842443103,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00011949999999999999,
|
|
"loss": 7.6129,
|
|
"mean_token_accuracy": 0.0683998104184866,
|
|
"num_tokens": 419083.0,
|
|
"step": 240
|
|
},
|
|
{
|
|
"entropy": 8.020170497894288,
|
|
"epoch": 0.01906243921416067,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.000122,
|
|
"loss": 7.5134,
|
|
"mean_token_accuracy": 0.06742828860878944,
|
|
"num_tokens": 427503.0,
|
|
"step": 245
|
|
},
|
|
{
|
|
"entropy": 8.029362392425536,
|
|
"epoch": 0.019451468585878234,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0001245,
|
|
"loss": 7.6228,
|
|
"mean_token_accuracy": 0.06421508118510247,
|
|
"num_tokens": 435820.0,
|
|
"step": 250
|
|
},
|
|
{
|
|
"entropy": 7.950299835205078,
|
|
"epoch": 0.0198404979575958,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000127,
|
|
"loss": 7.4872,
|
|
"mean_token_accuracy": 0.07130805253982545,
|
|
"num_tokens": 444692.0,
|
|
"step": 255
|
|
},
|
|
{
|
|
"entropy": 8.0076434135437,
|
|
"epoch": 0.020229527329313362,
|
|
"grad_norm": 0.69140625,
|
|
"learning_rate": 0.0001295,
|
|
"loss": 7.5393,
|
|
"mean_token_accuracy": 0.06418065093457699,
|
|
"num_tokens": 453536.0,
|
|
"step": 260
|
|
},
|
|
{
|
|
"entropy": 7.979480600357055,
|
|
"epoch": 0.020618556701030927,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000132,
|
|
"loss": 7.5602,
|
|
"mean_token_accuracy": 0.06866644658148288,
|
|
"num_tokens": 462264.0,
|
|
"step": 265
|
|
},
|
|
{
|
|
"entropy": 7.999968433380127,
|
|
"epoch": 0.021007586072748493,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00013450000000000002,
|
|
"loss": 7.6853,
|
|
"mean_token_accuracy": 0.06377483941614628,
|
|
"num_tokens": 471819.0,
|
|
"step": 270
|
|
},
|
|
{
|
|
"entropy": 7.984496641159057,
|
|
"epoch": 0.02139661544446606,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.00013700000000000002,
|
|
"loss": 7.5893,
|
|
"mean_token_accuracy": 0.06685386300086975,
|
|
"num_tokens": 480878.0,
|
|
"step": 275
|
|
},
|
|
{
|
|
"entropy": 8.042268657684327,
|
|
"epoch": 0.02178564481618362,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0001395,
|
|
"loss": 7.5368,
|
|
"mean_token_accuracy": 0.0704406276345253,
|
|
"num_tokens": 489454.0,
|
|
"step": 280
|
|
},
|
|
{
|
|
"entropy": 7.937283277511597,
|
|
"epoch": 0.022174674187901186,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.00014199999999999998,
|
|
"loss": 7.4434,
|
|
"mean_token_accuracy": 0.06957585588097573,
|
|
"num_tokens": 498378.0,
|
|
"step": 285
|
|
},
|
|
{
|
|
"entropy": 7.92456955909729,
|
|
"epoch": 0.02256370355961875,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0001445,
|
|
"loss": 7.6546,
|
|
"mean_token_accuracy": 0.06681204475462436,
|
|
"num_tokens": 507638.0,
|
|
"step": 290
|
|
},
|
|
{
|
|
"entropy": 8.000158309936523,
|
|
"epoch": 0.022952732931336317,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.000147,
|
|
"loss": 7.584,
|
|
"mean_token_accuracy": 0.06461342237889767,
|
|
"num_tokens": 517047.0,
|
|
"step": 295
|
|
},
|
|
{
|
|
"entropy": 7.9436469078063965,
|
|
"epoch": 0.02334176230305388,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0001495,
|
|
"loss": 7.5004,
|
|
"mean_token_accuracy": 0.07071815803647041,
|
|
"num_tokens": 525287.0,
|
|
"step": 300
|
|
},
|
|
{
|
|
"entropy": 7.946035575866699,
|
|
"epoch": 0.023730791674771445,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.000152,
|
|
"loss": 7.447,
|
|
"mean_token_accuracy": 0.06887780912220479,
|
|
"num_tokens": 533266.0,
|
|
"step": 305
|
|
},
|
|
{
|
|
"entropy": 7.880048036575317,
|
|
"epoch": 0.02411982104648901,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.00015450000000000001,
|
|
"loss": 7.5603,
|
|
"mean_token_accuracy": 0.07069731503725052,
|
|
"num_tokens": 542448.0,
|
|
"step": 310
|
|
},
|
|
{
|
|
"entropy": 7.958608961105346,
|
|
"epoch": 0.024508850418206576,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000157,
|
|
"loss": 7.4477,
|
|
"mean_token_accuracy": 0.06876055970788002,
|
|
"num_tokens": 550872.0,
|
|
"step": 315
|
|
},
|
|
{
|
|
"entropy": 7.892773580551148,
|
|
"epoch": 0.024897879789924138,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0001595,
|
|
"loss": 7.5034,
|
|
"mean_token_accuracy": 0.07373907268047333,
|
|
"num_tokens": 559616.0,
|
|
"step": 320
|
|
},
|
|
{
|
|
"entropy": 7.829233169555664,
|
|
"epoch": 0.025286909161641703,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000162,
|
|
"loss": 7.4818,
|
|
"mean_token_accuracy": 0.07325205206871033,
|
|
"num_tokens": 568379.0,
|
|
"step": 325
|
|
},
|
|
{
|
|
"entropy": 7.9177818775177,
|
|
"epoch": 0.02567593853335927,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.00016450000000000001,
|
|
"loss": 7.4785,
|
|
"mean_token_accuracy": 0.07421944811940193,
|
|
"num_tokens": 577288.0,
|
|
"step": 330
|
|
},
|
|
{
|
|
"entropy": 7.906116104125976,
|
|
"epoch": 0.026064967905076834,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.00016700000000000002,
|
|
"loss": 7.4467,
|
|
"mean_token_accuracy": 0.06836865991353988,
|
|
"num_tokens": 587054.0,
|
|
"step": 335
|
|
},
|
|
{
|
|
"entropy": 7.869630527496338,
|
|
"epoch": 0.026453997276794396,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.00016950000000000003,
|
|
"loss": 7.5577,
|
|
"mean_token_accuracy": 0.06964600048959255,
|
|
"num_tokens": 595405.0,
|
|
"step": 340
|
|
},
|
|
{
|
|
"entropy": 7.920015335083008,
|
|
"epoch": 0.026843026648511962,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00017199999999999998,
|
|
"loss": 7.4283,
|
|
"mean_token_accuracy": 0.07099934928119182,
|
|
"num_tokens": 604095.0,
|
|
"step": 345
|
|
},
|
|
{
|
|
"entropy": 7.7977094650268555,
|
|
"epoch": 0.027232056020229527,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00017449999999999999,
|
|
"loss": 7.4641,
|
|
"mean_token_accuracy": 0.06749536134302617,
|
|
"num_tokens": 613518.0,
|
|
"step": 350
|
|
},
|
|
{
|
|
"entropy": 7.825807666778564,
|
|
"epoch": 0.027621085391947093,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000177,
|
|
"loss": 7.329,
|
|
"mean_token_accuracy": 0.07268133610486985,
|
|
"num_tokens": 621212.0,
|
|
"step": 355
|
|
},
|
|
{
|
|
"entropy": 7.8151813507080075,
|
|
"epoch": 0.028010114763664655,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0001795,
|
|
"loss": 7.3993,
|
|
"mean_token_accuracy": 0.07544071115553379,
|
|
"num_tokens": 629326.0,
|
|
"step": 360
|
|
},
|
|
{
|
|
"entropy": 7.786165714263916,
|
|
"epoch": 0.02839914413538222,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.000182,
|
|
"loss": 7.4069,
|
|
"mean_token_accuracy": 0.07520471625030041,
|
|
"num_tokens": 637034.0,
|
|
"step": 365
|
|
},
|
|
{
|
|
"entropy": 7.750944328308106,
|
|
"epoch": 0.028788173507099786,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0001845,
|
|
"loss": 7.315,
|
|
"mean_token_accuracy": 0.07539180293679237,
|
|
"num_tokens": 645924.0,
|
|
"step": 370
|
|
},
|
|
{
|
|
"entropy": 7.882585048675537,
|
|
"epoch": 0.02917720287881735,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.000187,
|
|
"loss": 7.5043,
|
|
"mean_token_accuracy": 0.07769677974283695,
|
|
"num_tokens": 655020.0,
|
|
"step": 375
|
|
},
|
|
{
|
|
"entropy": 7.858515930175781,
|
|
"epoch": 0.029566232250534917,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0001895,
|
|
"loss": 7.3506,
|
|
"mean_token_accuracy": 0.0738551527261734,
|
|
"num_tokens": 663451.0,
|
|
"step": 380
|
|
},
|
|
{
|
|
"entropy": 7.7064581394195555,
|
|
"epoch": 0.02995526162225248,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.000192,
|
|
"loss": 7.4189,
|
|
"mean_token_accuracy": 0.07526476085186004,
|
|
"num_tokens": 671973.0,
|
|
"step": 385
|
|
},
|
|
{
|
|
"entropy": 7.7602927684783936,
|
|
"epoch": 0.030344290993970045,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0001945,
|
|
"loss": 7.3259,
|
|
"mean_token_accuracy": 0.07666941098868847,
|
|
"num_tokens": 680583.0,
|
|
"step": 390
|
|
},
|
|
{
|
|
"entropy": 7.750089979171753,
|
|
"epoch": 0.03073332036568761,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00019700000000000002,
|
|
"loss": 7.3341,
|
|
"mean_token_accuracy": 0.0714889034628868,
|
|
"num_tokens": 689000.0,
|
|
"step": 395
|
|
},
|
|
{
|
|
"entropy": 7.787451219558716,
|
|
"epoch": 0.031122349737405176,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00019950000000000002,
|
|
"loss": 7.3268,
|
|
"mean_token_accuracy": 0.0762193225324154,
|
|
"num_tokens": 698047.0,
|
|
"step": 400
|
|
},
|
|
{
|
|
"entropy": 7.7701332569122314,
|
|
"epoch": 0.03151137910912274,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.000202,
|
|
"loss": 7.4381,
|
|
"mean_token_accuracy": 0.07519823797047138,
|
|
"num_tokens": 707192.0,
|
|
"step": 405
|
|
},
|
|
{
|
|
"entropy": 7.660664463043213,
|
|
"epoch": 0.0319004084808403,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00020449999999999998,
|
|
"loss": 7.2728,
|
|
"mean_token_accuracy": 0.07804172001779079,
|
|
"num_tokens": 715895.0,
|
|
"step": 410
|
|
},
|
|
{
|
|
"entropy": 7.707487344741821,
|
|
"epoch": 0.03228943785255787,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.000207,
|
|
"loss": 7.3356,
|
|
"mean_token_accuracy": 0.07376265488564968,
|
|
"num_tokens": 724891.0,
|
|
"step": 415
|
|
},
|
|
{
|
|
"entropy": 7.820835208892822,
|
|
"epoch": 0.032678467224275434,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0002095,
|
|
"loss": 7.3764,
|
|
"mean_token_accuracy": 0.07474377714097499,
|
|
"num_tokens": 733378.0,
|
|
"step": 420
|
|
},
|
|
{
|
|
"entropy": 7.726008749008178,
|
|
"epoch": 0.033067496595993,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000212,
|
|
"loss": 7.3418,
|
|
"mean_token_accuracy": 0.07988023310899735,
|
|
"num_tokens": 741098.0,
|
|
"step": 425
|
|
},
|
|
{
|
|
"entropy": 7.787885046005249,
|
|
"epoch": 0.033456525967710565,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0002145,
|
|
"loss": 7.3086,
|
|
"mean_token_accuracy": 0.07603151835501194,
|
|
"num_tokens": 749902.0,
|
|
"step": 430
|
|
},
|
|
{
|
|
"entropy": 7.594846105575561,
|
|
"epoch": 0.033845555339428124,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00021700000000000002,
|
|
"loss": 7.2836,
|
|
"mean_token_accuracy": 0.08008698970079423,
|
|
"num_tokens": 758638.0,
|
|
"step": 435
|
|
},
|
|
{
|
|
"entropy": 7.749899053573609,
|
|
"epoch": 0.03423458471114569,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0002195,
|
|
"loss": 7.3592,
|
|
"mean_token_accuracy": 0.07718191593885422,
|
|
"num_tokens": 768170.0,
|
|
"step": 440
|
|
},
|
|
{
|
|
"entropy": 7.675568771362305,
|
|
"epoch": 0.034623614082863255,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.000222,
|
|
"loss": 7.2449,
|
|
"mean_token_accuracy": 0.07738250121474266,
|
|
"num_tokens": 776745.0,
|
|
"step": 445
|
|
},
|
|
{
|
|
"entropy": 7.658681774139405,
|
|
"epoch": 0.03501264345458082,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0002245,
|
|
"loss": 7.3473,
|
|
"mean_token_accuracy": 0.077309750020504,
|
|
"num_tokens": 785030.0,
|
|
"step": 450
|
|
},
|
|
{
|
|
"entropy": 7.6965330123901365,
|
|
"epoch": 0.035401672826298386,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.00022700000000000002,
|
|
"loss": 7.3159,
|
|
"mean_token_accuracy": 0.07549342140555382,
|
|
"num_tokens": 793543.0,
|
|
"step": 455
|
|
},
|
|
{
|
|
"entropy": 7.600979042053223,
|
|
"epoch": 0.03579070219801595,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00022950000000000002,
|
|
"loss": 7.1834,
|
|
"mean_token_accuracy": 0.0792169462889433,
|
|
"num_tokens": 802401.0,
|
|
"step": 460
|
|
},
|
|
{
|
|
"entropy": 7.680768060684204,
|
|
"epoch": 0.03617973156973352,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00023200000000000003,
|
|
"loss": 7.3003,
|
|
"mean_token_accuracy": 0.07450498901307583,
|
|
"num_tokens": 811625.0,
|
|
"step": 465
|
|
},
|
|
{
|
|
"entropy": 7.673035144805908,
|
|
"epoch": 0.03656876094145108,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00023449999999999998,
|
|
"loss": 7.2218,
|
|
"mean_token_accuracy": 0.07750762216746807,
|
|
"num_tokens": 820742.0,
|
|
"step": 470
|
|
},
|
|
{
|
|
"entropy": 7.5899158954620365,
|
|
"epoch": 0.03695779031316864,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.000237,
|
|
"loss": 7.3166,
|
|
"mean_token_accuracy": 0.07351075634360313,
|
|
"num_tokens": 829580.0,
|
|
"step": 475
|
|
},
|
|
{
|
|
"entropy": 7.651634788513183,
|
|
"epoch": 0.03734681968488621,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0002395,
|
|
"loss": 7.257,
|
|
"mean_token_accuracy": 0.07667978703975678,
|
|
"num_tokens": 838818.0,
|
|
"step": 480
|
|
},
|
|
{
|
|
"entropy": 7.68389048576355,
|
|
"epoch": 0.03773584905660377,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.000242,
|
|
"loss": 7.2846,
|
|
"mean_token_accuracy": 0.06978295557200909,
|
|
"num_tokens": 847804.0,
|
|
"step": 485
|
|
},
|
|
{
|
|
"entropy": 7.529942798614502,
|
|
"epoch": 0.03812487842832134,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0002445,
|
|
"loss": 7.0454,
|
|
"mean_token_accuracy": 0.08401452973484994,
|
|
"num_tokens": 856395.0,
|
|
"step": 490
|
|
},
|
|
{
|
|
"entropy": 7.63438572883606,
|
|
"epoch": 0.0385139078000389,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.000247,
|
|
"loss": 7.2677,
|
|
"mean_token_accuracy": 0.08493128195405006,
|
|
"num_tokens": 865219.0,
|
|
"step": 495
|
|
},
|
|
{
|
|
"entropy": 7.5453051090240475,
|
|
"epoch": 0.03890293717175647,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0002495,
|
|
"loss": 7.0764,
|
|
"mean_token_accuracy": 0.08479876518249511,
|
|
"num_tokens": 873868.0,
|
|
"step": 500
|
|
},
|
|
{
|
|
"entropy": 7.546178579330444,
|
|
"epoch": 0.039291966543474034,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000252,
|
|
"loss": 7.1791,
|
|
"mean_token_accuracy": 0.07757280953228474,
|
|
"num_tokens": 882698.0,
|
|
"step": 505
|
|
},
|
|
{
|
|
"entropy": 7.52639946937561,
|
|
"epoch": 0.0396809959151916,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0002545,
|
|
"loss": 7.1175,
|
|
"mean_token_accuracy": 0.08353231772780419,
|
|
"num_tokens": 891280.0,
|
|
"step": 510
|
|
},
|
|
{
|
|
"entropy": 7.560566186904907,
|
|
"epoch": 0.04007002528690916,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000257,
|
|
"loss": 7.1573,
|
|
"mean_token_accuracy": 0.08208137303590775,
|
|
"num_tokens": 900044.0,
|
|
"step": 515
|
|
},
|
|
{
|
|
"entropy": 7.605652093887329,
|
|
"epoch": 0.040459054658626724,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0002595,
|
|
"loss": 7.1293,
|
|
"mean_token_accuracy": 0.08118686527013778,
|
|
"num_tokens": 909297.0,
|
|
"step": 520
|
|
},
|
|
{
|
|
"entropy": 7.494569969177246,
|
|
"epoch": 0.04084808403034429,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000262,
|
|
"loss": 7.1054,
|
|
"mean_token_accuracy": 0.08253288716077804,
|
|
"num_tokens": 917514.0,
|
|
"step": 525
|
|
},
|
|
{
|
|
"entropy": 7.536244630813599,
|
|
"epoch": 0.041237113402061855,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.00026450000000000003,
|
|
"loss": 7.0974,
|
|
"mean_token_accuracy": 0.08544723689556122,
|
|
"num_tokens": 925842.0,
|
|
"step": 530
|
|
},
|
|
{
|
|
"entropy": 7.4475737571716305,
|
|
"epoch": 0.04162614277377942,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00026700000000000004,
|
|
"loss": 7.1702,
|
|
"mean_token_accuracy": 0.07806997671723366,
|
|
"num_tokens": 934676.0,
|
|
"step": 535
|
|
},
|
|
{
|
|
"entropy": 7.52036681175232,
|
|
"epoch": 0.042015172145496986,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00026950000000000005,
|
|
"loss": 7.0967,
|
|
"mean_token_accuracy": 0.08425900638103485,
|
|
"num_tokens": 943763.0,
|
|
"step": 540
|
|
},
|
|
{
|
|
"entropy": 7.469168663024902,
|
|
"epoch": 0.04240420151721455,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00027200000000000005,
|
|
"loss": 7.0821,
|
|
"mean_token_accuracy": 0.0887335106730461,
|
|
"num_tokens": 952721.0,
|
|
"step": 545
|
|
},
|
|
{
|
|
"entropy": 7.503802490234375,
|
|
"epoch": 0.04279323088893212,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0002745,
|
|
"loss": 7.0916,
|
|
"mean_token_accuracy": 0.086705182492733,
|
|
"num_tokens": 960899.0,
|
|
"step": 550
|
|
},
|
|
{
|
|
"entropy": 7.405792284011841,
|
|
"epoch": 0.04318226026064968,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.000277,
|
|
"loss": 7.0739,
|
|
"mean_token_accuracy": 0.08868521377444268,
|
|
"num_tokens": 969362.0,
|
|
"step": 555
|
|
},
|
|
{
|
|
"entropy": 7.486908721923828,
|
|
"epoch": 0.04357128963236724,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0002795,
|
|
"loss": 7.0449,
|
|
"mean_token_accuracy": 0.0890669658780098,
|
|
"num_tokens": 978028.0,
|
|
"step": 560
|
|
},
|
|
{
|
|
"entropy": 7.465371990203858,
|
|
"epoch": 0.04396031900408481,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00028199999999999997,
|
|
"loss": 7.0362,
|
|
"mean_token_accuracy": 0.08907110318541527,
|
|
"num_tokens": 985709.0,
|
|
"step": 565
|
|
},
|
|
{
|
|
"entropy": 7.462168502807617,
|
|
"epoch": 0.04434934837580237,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0002845,
|
|
"loss": 7.1305,
|
|
"mean_token_accuracy": 0.0881653033196926,
|
|
"num_tokens": 994769.0,
|
|
"step": 570
|
|
},
|
|
{
|
|
"entropy": 7.491409683227539,
|
|
"epoch": 0.04473837774751994,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000287,
|
|
"loss": 7.1044,
|
|
"mean_token_accuracy": 0.08935707733035088,
|
|
"num_tokens": 1003997.0,
|
|
"step": 575
|
|
},
|
|
{
|
|
"entropy": 7.457375764846802,
|
|
"epoch": 0.0451274071192375,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0002895,
|
|
"loss": 7.0944,
|
|
"mean_token_accuracy": 0.08739758059382438,
|
|
"num_tokens": 1012931.0,
|
|
"step": 580
|
|
},
|
|
{
|
|
"entropy": 7.459478521347046,
|
|
"epoch": 0.04551643649095507,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.000292,
|
|
"loss": 7.0883,
|
|
"mean_token_accuracy": 0.08481152728199959,
|
|
"num_tokens": 1021149.0,
|
|
"step": 585
|
|
},
|
|
{
|
|
"entropy": 7.538705492019654,
|
|
"epoch": 0.045905465862672634,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0002945,
|
|
"loss": 7.0841,
|
|
"mean_token_accuracy": 0.08799395263195038,
|
|
"num_tokens": 1029421.0,
|
|
"step": 590
|
|
},
|
|
{
|
|
"entropy": 7.462785053253174,
|
|
"epoch": 0.0462944952343902,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000297,
|
|
"loss": 7.1743,
|
|
"mean_token_accuracy": 0.08678501397371292,
|
|
"num_tokens": 1037222.0,
|
|
"step": 595
|
|
},
|
|
{
|
|
"entropy": 7.437726593017578,
|
|
"epoch": 0.04668352460610776,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0002995,
|
|
"loss": 7.0995,
|
|
"mean_token_accuracy": 0.08787578642368317,
|
|
"num_tokens": 1046903.0,
|
|
"step": 600
|
|
},
|
|
{
|
|
"entropy": 7.512172842025757,
|
|
"epoch": 0.047072553977825324,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.000302,
|
|
"loss": 7.1473,
|
|
"mean_token_accuracy": 0.0882769763469696,
|
|
"num_tokens": 1055516.0,
|
|
"step": 605
|
|
},
|
|
{
|
|
"entropy": 7.3588001251220705,
|
|
"epoch": 0.04746158334954289,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0003045,
|
|
"loss": 7.062,
|
|
"mean_token_accuracy": 0.08846223801374435,
|
|
"num_tokens": 1063846.0,
|
|
"step": 610
|
|
},
|
|
{
|
|
"entropy": 7.445447111129761,
|
|
"epoch": 0.047850612721260455,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000307,
|
|
"loss": 7.0266,
|
|
"mean_token_accuracy": 0.08862499296665191,
|
|
"num_tokens": 1072500.0,
|
|
"step": 615
|
|
},
|
|
{
|
|
"entropy": 7.362279796600342,
|
|
"epoch": 0.04823964209297802,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0003095,
|
|
"loss": 7.0448,
|
|
"mean_token_accuracy": 0.08868532851338387,
|
|
"num_tokens": 1081399.0,
|
|
"step": 620
|
|
},
|
|
{
|
|
"entropy": 7.348788785934448,
|
|
"epoch": 0.048628671464695586,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000312,
|
|
"loss": 7.0033,
|
|
"mean_token_accuracy": 0.09508873224258423,
|
|
"num_tokens": 1089666.0,
|
|
"step": 625
|
|
},
|
|
{
|
|
"entropy": 7.375779914855957,
|
|
"epoch": 0.04901770083641315,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0003145,
|
|
"loss": 6.8973,
|
|
"mean_token_accuracy": 0.09559790790081024,
|
|
"num_tokens": 1097496.0,
|
|
"step": 630
|
|
},
|
|
{
|
|
"entropy": 7.29237060546875,
|
|
"epoch": 0.04940673020813072,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000317,
|
|
"loss": 7.0035,
|
|
"mean_token_accuracy": 0.09299874976277352,
|
|
"num_tokens": 1105840.0,
|
|
"step": 635
|
|
},
|
|
{
|
|
"entropy": 7.402494239807129,
|
|
"epoch": 0.049795759579848276,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0003195,
|
|
"loss": 7.0719,
|
|
"mean_token_accuracy": 0.08872134163975716,
|
|
"num_tokens": 1115507.0,
|
|
"step": 640
|
|
},
|
|
{
|
|
"entropy": 7.369076442718506,
|
|
"epoch": 0.05018478895156584,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000322,
|
|
"loss": 7.0236,
|
|
"mean_token_accuracy": 0.0886545293033123,
|
|
"num_tokens": 1124820.0,
|
|
"step": 645
|
|
},
|
|
{
|
|
"entropy": 7.28340630531311,
|
|
"epoch": 0.05057381832328341,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00032450000000000003,
|
|
"loss": 6.874,
|
|
"mean_token_accuracy": 0.09596052095293998,
|
|
"num_tokens": 1133641.0,
|
|
"step": 650
|
|
},
|
|
{
|
|
"entropy": 7.213095664978027,
|
|
"epoch": 0.05096284769500097,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00032700000000000003,
|
|
"loss": 6.9189,
|
|
"mean_token_accuracy": 0.09583729729056359,
|
|
"num_tokens": 1142182.0,
|
|
"step": 655
|
|
},
|
|
{
|
|
"entropy": 7.313646078109741,
|
|
"epoch": 0.05135187706671854,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00032950000000000004,
|
|
"loss": 7.0063,
|
|
"mean_token_accuracy": 0.09615088105201722,
|
|
"num_tokens": 1150737.0,
|
|
"step": 660
|
|
},
|
|
{
|
|
"entropy": 7.298776626586914,
|
|
"epoch": 0.0517409064384361,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00033200000000000005,
|
|
"loss": 6.8665,
|
|
"mean_token_accuracy": 0.09271117597818375,
|
|
"num_tokens": 1158899.0,
|
|
"step": 665
|
|
},
|
|
{
|
|
"entropy": 7.385696363449097,
|
|
"epoch": 0.05212993581015367,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00033450000000000005,
|
|
"loss": 6.949,
|
|
"mean_token_accuracy": 0.10016907081007957,
|
|
"num_tokens": 1167397.0,
|
|
"step": 670
|
|
},
|
|
{
|
|
"entropy": 7.342027235031128,
|
|
"epoch": 0.052518965181871234,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000337,
|
|
"loss": 6.9648,
|
|
"mean_token_accuracy": 0.09081067815423012,
|
|
"num_tokens": 1177044.0,
|
|
"step": 675
|
|
},
|
|
{
|
|
"entropy": 7.156559610366822,
|
|
"epoch": 0.05290799455358879,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0003395,
|
|
"loss": 6.8077,
|
|
"mean_token_accuracy": 0.09764151573181153,
|
|
"num_tokens": 1185740.0,
|
|
"step": 680
|
|
},
|
|
{
|
|
"entropy": 7.273555040359497,
|
|
"epoch": 0.05329702392530636,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.000342,
|
|
"loss": 6.959,
|
|
"mean_token_accuracy": 0.09533077627420425,
|
|
"num_tokens": 1194970.0,
|
|
"step": 685
|
|
},
|
|
{
|
|
"entropy": 7.26585021018982,
|
|
"epoch": 0.053686053297023924,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00034449999999999997,
|
|
"loss": 6.9193,
|
|
"mean_token_accuracy": 0.09548866376280785,
|
|
"num_tokens": 1203565.0,
|
|
"step": 690
|
|
},
|
|
{
|
|
"entropy": 7.345769262313842,
|
|
"epoch": 0.05407508266874149,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000347,
|
|
"loss": 6.9552,
|
|
"mean_token_accuracy": 0.09232278615236282,
|
|
"num_tokens": 1213226.0,
|
|
"step": 695
|
|
},
|
|
{
|
|
"entropy": 7.133775281906128,
|
|
"epoch": 0.054464112040459055,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0003495,
|
|
"loss": 6.8723,
|
|
"mean_token_accuracy": 0.0922174483537674,
|
|
"num_tokens": 1221710.0,
|
|
"step": 700
|
|
},
|
|
{
|
|
"entropy": 7.19491286277771,
|
|
"epoch": 0.05485314141217662,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000352,
|
|
"loss": 6.931,
|
|
"mean_token_accuracy": 0.088956368714571,
|
|
"num_tokens": 1231125.0,
|
|
"step": 705
|
|
},
|
|
{
|
|
"entropy": 7.321548891067505,
|
|
"epoch": 0.055242170783894186,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0003545,
|
|
"loss": 6.8845,
|
|
"mean_token_accuracy": 0.09706432223320008,
|
|
"num_tokens": 1239521.0,
|
|
"step": 710
|
|
},
|
|
{
|
|
"entropy": 7.171043634414673,
|
|
"epoch": 0.05563120015561175,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000357,
|
|
"loss": 6.7669,
|
|
"mean_token_accuracy": 0.10296523198485374,
|
|
"num_tokens": 1247363.0,
|
|
"step": 715
|
|
},
|
|
{
|
|
"entropy": 7.1869182109832765,
|
|
"epoch": 0.05602022952732931,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0003595,
|
|
"loss": 6.8672,
|
|
"mean_token_accuracy": 0.09592388719320297,
|
|
"num_tokens": 1255395.0,
|
|
"step": 720
|
|
},
|
|
{
|
|
"entropy": 7.241849136352539,
|
|
"epoch": 0.056409258899046875,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000362,
|
|
"loss": 6.9361,
|
|
"mean_token_accuracy": 0.09305860325694085,
|
|
"num_tokens": 1264135.0,
|
|
"step": 725
|
|
},
|
|
{
|
|
"entropy": 7.2033219814300535,
|
|
"epoch": 0.05679828827076444,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0003645,
|
|
"loss": 6.858,
|
|
"mean_token_accuracy": 0.09347002804279328,
|
|
"num_tokens": 1272375.0,
|
|
"step": 730
|
|
},
|
|
{
|
|
"entropy": 7.255517768859863,
|
|
"epoch": 0.057187317642482006,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000367,
|
|
"loss": 6.9055,
|
|
"mean_token_accuracy": 0.08993236273527146,
|
|
"num_tokens": 1280960.0,
|
|
"step": 735
|
|
},
|
|
{
|
|
"entropy": 7.214277744293213,
|
|
"epoch": 0.05757634701419957,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0003695,
|
|
"loss": 6.9302,
|
|
"mean_token_accuracy": 0.09800290465354919,
|
|
"num_tokens": 1289273.0,
|
|
"step": 740
|
|
},
|
|
{
|
|
"entropy": 7.18172402381897,
|
|
"epoch": 0.05796537638591714,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000372,
|
|
"loss": 6.8479,
|
|
"mean_token_accuracy": 0.09940816089510918,
|
|
"num_tokens": 1297571.0,
|
|
"step": 745
|
|
},
|
|
{
|
|
"entropy": 7.171477317810059,
|
|
"epoch": 0.0583544057576347,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0003745,
|
|
"loss": 6.9001,
|
|
"mean_token_accuracy": 0.0956696018576622,
|
|
"num_tokens": 1305686.0,
|
|
"step": 750
|
|
},
|
|
{
|
|
"entropy": 7.218287420272827,
|
|
"epoch": 0.05874343512935227,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000377,
|
|
"loss": 6.9046,
|
|
"mean_token_accuracy": 0.09595917537808418,
|
|
"num_tokens": 1314483.0,
|
|
"step": 755
|
|
},
|
|
{
|
|
"entropy": 7.148498582839966,
|
|
"epoch": 0.059132464501069834,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0003795,
|
|
"loss": 6.7823,
|
|
"mean_token_accuracy": 0.09254824668169022,
|
|
"num_tokens": 1323183.0,
|
|
"step": 760
|
|
},
|
|
{
|
|
"entropy": 7.194712829589844,
|
|
"epoch": 0.05952149387278739,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.000382,
|
|
"loss": 6.8996,
|
|
"mean_token_accuracy": 0.09819645509123802,
|
|
"num_tokens": 1331964.0,
|
|
"step": 765
|
|
},
|
|
{
|
|
"entropy": 7.1077686786651615,
|
|
"epoch": 0.05991052324450496,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0003845,
|
|
"loss": 6.8611,
|
|
"mean_token_accuracy": 0.09804551675915718,
|
|
"num_tokens": 1340185.0,
|
|
"step": 770
|
|
},
|
|
{
|
|
"entropy": 7.263053369522095,
|
|
"epoch": 0.060299552616222524,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00038700000000000003,
|
|
"loss": 6.9342,
|
|
"mean_token_accuracy": 0.09536710008978844,
|
|
"num_tokens": 1349522.0,
|
|
"step": 775
|
|
},
|
|
{
|
|
"entropy": 7.275899028778076,
|
|
"epoch": 0.06068858198794009,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00038950000000000003,
|
|
"loss": 6.896,
|
|
"mean_token_accuracy": 0.09667107537388801,
|
|
"num_tokens": 1357893.0,
|
|
"step": 780
|
|
},
|
|
{
|
|
"entropy": 7.106265592575073,
|
|
"epoch": 0.061077611359657655,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00039200000000000004,
|
|
"loss": 6.7809,
|
|
"mean_token_accuracy": 0.10025013461709023,
|
|
"num_tokens": 1366685.0,
|
|
"step": 785
|
|
},
|
|
{
|
|
"entropy": 7.080127429962158,
|
|
"epoch": 0.06146664073137522,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00039450000000000005,
|
|
"loss": 6.7265,
|
|
"mean_token_accuracy": 0.09952032342553138,
|
|
"num_tokens": 1375245.0,
|
|
"step": 790
|
|
},
|
|
{
|
|
"entropy": 7.122674369812012,
|
|
"epoch": 0.061855670103092786,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00039700000000000005,
|
|
"loss": 6.8964,
|
|
"mean_token_accuracy": 0.09939667508006096,
|
|
"num_tokens": 1383724.0,
|
|
"step": 795
|
|
},
|
|
{
|
|
"entropy": 7.244520807266236,
|
|
"epoch": 0.06224469947481035,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0003995,
|
|
"loss": 6.888,
|
|
"mean_token_accuracy": 0.09881971329450608,
|
|
"num_tokens": 1392455.0,
|
|
"step": 800
|
|
},
|
|
{
|
|
"entropy": 7.216006183624268,
|
|
"epoch": 0.06263372884652792,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000402,
|
|
"loss": 6.891,
|
|
"mean_token_accuracy": 0.10223213583230972,
|
|
"num_tokens": 1401262.0,
|
|
"step": 805
|
|
},
|
|
{
|
|
"entropy": 7.012789487838745,
|
|
"epoch": 0.06302275821824548,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004045,
|
|
"loss": 6.77,
|
|
"mean_token_accuracy": 0.10305121541023254,
|
|
"num_tokens": 1409991.0,
|
|
"step": 810
|
|
},
|
|
{
|
|
"entropy": 7.0912278175354,
|
|
"epoch": 0.06341178758996305,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00040699999999999997,
|
|
"loss": 6.7739,
|
|
"mean_token_accuracy": 0.10144544690847397,
|
|
"num_tokens": 1418208.0,
|
|
"step": 815
|
|
},
|
|
{
|
|
"entropy": 7.041250562667846,
|
|
"epoch": 0.0638008169616806,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004095,
|
|
"loss": 6.7687,
|
|
"mean_token_accuracy": 0.10150073319673539,
|
|
"num_tokens": 1426665.0,
|
|
"step": 820
|
|
},
|
|
{
|
|
"entropy": 7.040017032623291,
|
|
"epoch": 0.06418984633339817,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.000412,
|
|
"loss": 6.7003,
|
|
"mean_token_accuracy": 0.10085978209972382,
|
|
"num_tokens": 1435247.0,
|
|
"step": 825
|
|
},
|
|
{
|
|
"entropy": 7.063506841659546,
|
|
"epoch": 0.06457887570511574,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004145,
|
|
"loss": 6.7405,
|
|
"mean_token_accuracy": 0.10099377259612083,
|
|
"num_tokens": 1443678.0,
|
|
"step": 830
|
|
},
|
|
{
|
|
"entropy": 7.011990594863891,
|
|
"epoch": 0.0649679050768333,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.000417,
|
|
"loss": 6.6843,
|
|
"mean_token_accuracy": 0.10724351927638054,
|
|
"num_tokens": 1451567.0,
|
|
"step": 835
|
|
},
|
|
{
|
|
"entropy": 7.009270477294922,
|
|
"epoch": 0.06535693444855087,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004195,
|
|
"loss": 6.704,
|
|
"mean_token_accuracy": 0.10393429771065713,
|
|
"num_tokens": 1460618.0,
|
|
"step": 840
|
|
},
|
|
{
|
|
"entropy": 7.021320343017578,
|
|
"epoch": 0.06574596382026843,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000422,
|
|
"loss": 6.7753,
|
|
"mean_token_accuracy": 0.10534258186817169,
|
|
"num_tokens": 1469821.0,
|
|
"step": 845
|
|
},
|
|
{
|
|
"entropy": 6.965624380111694,
|
|
"epoch": 0.066134993191986,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004245,
|
|
"loss": 6.8413,
|
|
"mean_token_accuracy": 0.0993105836212635,
|
|
"num_tokens": 1477989.0,
|
|
"step": 850
|
|
},
|
|
{
|
|
"entropy": 7.1604921340942385,
|
|
"epoch": 0.06652402256370356,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000427,
|
|
"loss": 6.8444,
|
|
"mean_token_accuracy": 0.10425978153944016,
|
|
"num_tokens": 1486822.0,
|
|
"step": 855
|
|
},
|
|
{
|
|
"entropy": 7.088742446899414,
|
|
"epoch": 0.06691305193542113,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004295,
|
|
"loss": 6.7305,
|
|
"mean_token_accuracy": 0.09952922314405441,
|
|
"num_tokens": 1496604.0,
|
|
"step": 860
|
|
},
|
|
{
|
|
"entropy": 7.047960662841797,
|
|
"epoch": 0.06730208130713869,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.000432,
|
|
"loss": 6.7496,
|
|
"mean_token_accuracy": 0.10054385960102082,
|
|
"num_tokens": 1504725.0,
|
|
"step": 865
|
|
},
|
|
{
|
|
"entropy": 6.983655691146851,
|
|
"epoch": 0.06769111067885625,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004345,
|
|
"loss": 6.7616,
|
|
"mean_token_accuracy": 0.10596725270152092,
|
|
"num_tokens": 1513222.0,
|
|
"step": 870
|
|
},
|
|
{
|
|
"entropy": 7.112746620178223,
|
|
"epoch": 0.06808014005057382,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000437,
|
|
"loss": 6.7105,
|
|
"mean_token_accuracy": 0.10374617874622345,
|
|
"num_tokens": 1522183.0,
|
|
"step": 875
|
|
},
|
|
{
|
|
"entropy": 7.01748366355896,
|
|
"epoch": 0.06846916942229138,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004395,
|
|
"loss": 6.7634,
|
|
"mean_token_accuracy": 0.10354626253247261,
|
|
"num_tokens": 1531316.0,
|
|
"step": 880
|
|
},
|
|
{
|
|
"entropy": 7.0218301773071286,
|
|
"epoch": 0.06885819879400895,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000442,
|
|
"loss": 6.8291,
|
|
"mean_token_accuracy": 0.10073515474796295,
|
|
"num_tokens": 1540053.0,
|
|
"step": 885
|
|
},
|
|
{
|
|
"entropy": 7.033105850219727,
|
|
"epoch": 0.06924722816572651,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004445,
|
|
"loss": 6.6775,
|
|
"mean_token_accuracy": 0.11033806353807449,
|
|
"num_tokens": 1549391.0,
|
|
"step": 890
|
|
},
|
|
{
|
|
"entropy": 7.096326446533203,
|
|
"epoch": 0.06963625753744408,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.000447,
|
|
"loss": 6.7919,
|
|
"mean_token_accuracy": 0.10401200950145721,
|
|
"num_tokens": 1557364.0,
|
|
"step": 895
|
|
},
|
|
{
|
|
"entropy": 6.939074897766114,
|
|
"epoch": 0.07002528690916164,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00044950000000000003,
|
|
"loss": 6.6375,
|
|
"mean_token_accuracy": 0.0982839398086071,
|
|
"num_tokens": 1567011.0,
|
|
"step": 900
|
|
},
|
|
{
|
|
"entropy": 6.94973726272583,
|
|
"epoch": 0.0704143162808792,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00045200000000000004,
|
|
"loss": 6.7271,
|
|
"mean_token_accuracy": 0.10176745280623437,
|
|
"num_tokens": 1575441.0,
|
|
"step": 905
|
|
},
|
|
{
|
|
"entropy": 6.9638408660888675,
|
|
"epoch": 0.07080334565259677,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00045450000000000004,
|
|
"loss": 6.6876,
|
|
"mean_token_accuracy": 0.10327148288488389,
|
|
"num_tokens": 1583757.0,
|
|
"step": 910
|
|
},
|
|
{
|
|
"entropy": 7.055232191085816,
|
|
"epoch": 0.07119237502431433,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00045700000000000005,
|
|
"loss": 6.7335,
|
|
"mean_token_accuracy": 0.10632129982113839,
|
|
"num_tokens": 1592406.0,
|
|
"step": 915
|
|
},
|
|
{
|
|
"entropy": 6.91970043182373,
|
|
"epoch": 0.0715814043960319,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00045950000000000006,
|
|
"loss": 6.7293,
|
|
"mean_token_accuracy": 0.10444770827889442,
|
|
"num_tokens": 1601665.0,
|
|
"step": 920
|
|
},
|
|
{
|
|
"entropy": 7.091557741165161,
|
|
"epoch": 0.07197043376774946,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000462,
|
|
"loss": 6.7245,
|
|
"mean_token_accuracy": 0.10248482674360275,
|
|
"num_tokens": 1609788.0,
|
|
"step": 925
|
|
},
|
|
{
|
|
"entropy": 6.889610815048218,
|
|
"epoch": 0.07235946313946703,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004645,
|
|
"loss": 6.7202,
|
|
"mean_token_accuracy": 0.10887994691729545,
|
|
"num_tokens": 1618030.0,
|
|
"step": 930
|
|
},
|
|
{
|
|
"entropy": 6.963936805725098,
|
|
"epoch": 0.07274849251118459,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000467,
|
|
"loss": 6.7281,
|
|
"mean_token_accuracy": 0.10066362768411637,
|
|
"num_tokens": 1626901.0,
|
|
"step": 935
|
|
},
|
|
{
|
|
"entropy": 6.932220506668091,
|
|
"epoch": 0.07313752188290217,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004695,
|
|
"loss": 6.6348,
|
|
"mean_token_accuracy": 0.1041472889482975,
|
|
"num_tokens": 1635372.0,
|
|
"step": 940
|
|
},
|
|
{
|
|
"entropy": 6.882161235809326,
|
|
"epoch": 0.07352655125461972,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000472,
|
|
"loss": 6.6485,
|
|
"mean_token_accuracy": 0.10415024533867837,
|
|
"num_tokens": 1643791.0,
|
|
"step": 945
|
|
},
|
|
{
|
|
"entropy": 6.876175880432129,
|
|
"epoch": 0.07391558062633728,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004745,
|
|
"loss": 6.6031,
|
|
"mean_token_accuracy": 0.11224255934357644,
|
|
"num_tokens": 1652161.0,
|
|
"step": 950
|
|
},
|
|
{
|
|
"entropy": 6.945423316955567,
|
|
"epoch": 0.07430460999805485,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000477,
|
|
"loss": 6.6567,
|
|
"mean_token_accuracy": 0.10526313111186028,
|
|
"num_tokens": 1661077.0,
|
|
"step": 955
|
|
},
|
|
{
|
|
"entropy": 6.903894758224487,
|
|
"epoch": 0.07469363936977241,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004795,
|
|
"loss": 6.6253,
|
|
"mean_token_accuracy": 0.10890860855579376,
|
|
"num_tokens": 1669010.0,
|
|
"step": 960
|
|
},
|
|
{
|
|
"entropy": 6.9699595928192135,
|
|
"epoch": 0.07508266874148999,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000482,
|
|
"loss": 6.8042,
|
|
"mean_token_accuracy": 0.10613740161061287,
|
|
"num_tokens": 1678002.0,
|
|
"step": 965
|
|
},
|
|
{
|
|
"entropy": 6.982291316986084,
|
|
"epoch": 0.07547169811320754,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004845,
|
|
"loss": 6.7491,
|
|
"mean_token_accuracy": 0.10167021304368973,
|
|
"num_tokens": 1687403.0,
|
|
"step": 970
|
|
},
|
|
{
|
|
"entropy": 6.9213052749633786,
|
|
"epoch": 0.07586072748492512,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000487,
|
|
"loss": 6.6526,
|
|
"mean_token_accuracy": 0.10744511783123016,
|
|
"num_tokens": 1695512.0,
|
|
"step": 975
|
|
},
|
|
{
|
|
"entropy": 6.9510541439056395,
|
|
"epoch": 0.07624975685664268,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004895,
|
|
"loss": 6.6685,
|
|
"mean_token_accuracy": 0.10527175143361092,
|
|
"num_tokens": 1705116.0,
|
|
"step": 980
|
|
},
|
|
{
|
|
"entropy": 6.837292337417603,
|
|
"epoch": 0.07663878622836025,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000492,
|
|
"loss": 6.5608,
|
|
"mean_token_accuracy": 0.11234913319349289,
|
|
"num_tokens": 1713715.0,
|
|
"step": 985
|
|
},
|
|
{
|
|
"entropy": 6.849586534500122,
|
|
"epoch": 0.0770278156000778,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004945,
|
|
"loss": 6.6274,
|
|
"mean_token_accuracy": 0.11056514084339142,
|
|
"num_tokens": 1721881.0,
|
|
"step": 990
|
|
},
|
|
{
|
|
"entropy": 6.907543706893921,
|
|
"epoch": 0.07741684497179536,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000497,
|
|
"loss": 6.6461,
|
|
"mean_token_accuracy": 0.11055096238851547,
|
|
"num_tokens": 1730716.0,
|
|
"step": 995
|
|
},
|
|
{
|
|
"entropy": 7.061227083206177,
|
|
"epoch": 0.07780587434351294,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004995,
|
|
"loss": 6.8026,
|
|
"mean_token_accuracy": 0.10393945574760437,
|
|
"num_tokens": 1740257.0,
|
|
"step": 1000
|
|
},
|
|
{
|
|
"entropy": 6.850629186630249,
|
|
"epoch": 0.0781949037152305,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004999999989075146,
|
|
"loss": 6.7019,
|
|
"mean_token_accuracy": 0.10508826747536659,
|
|
"num_tokens": 1749071.0,
|
|
"step": 1005
|
|
},
|
|
{
|
|
"entropy": 6.91280608177185,
|
|
"epoch": 0.07858393308694807,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999999944692927,
|
|
"loss": 6.7081,
|
|
"mean_token_accuracy": 0.09934931620955467,
|
|
"num_tokens": 1757952.0,
|
|
"step": 1010
|
|
},
|
|
{
|
|
"entropy": 6.924489593505859,
|
|
"epoch": 0.07897296245866563,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000499999986617054,
|
|
"loss": 6.6445,
|
|
"mean_token_accuracy": 0.1096059374511242,
|
|
"num_tokens": 1766027.0,
|
|
"step": 1015
|
|
},
|
|
{
|
|
"entropy": 6.844860982894898,
|
|
"epoch": 0.0793619918303832,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999999753507986,
|
|
"loss": 6.6349,
|
|
"mean_token_accuracy": 0.10513899624347686,
|
|
"num_tokens": 1775039.0,
|
|
"step": 1020
|
|
},
|
|
{
|
|
"entropy": 6.822795629501343,
|
|
"epoch": 0.07975102120210076,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999999606705267,
|
|
"loss": 6.6415,
|
|
"mean_token_accuracy": 0.10872110053896904,
|
|
"num_tokens": 1783971.0,
|
|
"step": 1025
|
|
},
|
|
{
|
|
"entropy": 6.864479064941406,
|
|
"epoch": 0.08014005057381832,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999999425762385,
|
|
"loss": 6.5852,
|
|
"mean_token_accuracy": 0.10642140656709671,
|
|
"num_tokens": 1792743.0,
|
|
"step": 1030
|
|
},
|
|
{
|
|
"entropy": 6.888079357147217,
|
|
"epoch": 0.08052907994553589,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999999210679344,
|
|
"loss": 6.7187,
|
|
"mean_token_accuracy": 0.10097150802612305,
|
|
"num_tokens": 1801435.0,
|
|
"step": 1035
|
|
},
|
|
{
|
|
"entropy": 6.943144989013672,
|
|
"epoch": 0.08091810931725345,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999998961456145,
|
|
"loss": 6.6372,
|
|
"mean_token_accuracy": 0.10501615256071091,
|
|
"num_tokens": 1810147.0,
|
|
"step": 1040
|
|
},
|
|
{
|
|
"entropy": 6.91335916519165,
|
|
"epoch": 0.08130713868897102,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999998678092794,
|
|
"loss": 6.5481,
|
|
"mean_token_accuracy": 0.11189196705818176,
|
|
"num_tokens": 1818672.0,
|
|
"step": 1045
|
|
},
|
|
{
|
|
"entropy": 6.825189781188965,
|
|
"epoch": 0.08169616806068858,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999998360589293,
|
|
"loss": 6.7051,
|
|
"mean_token_accuracy": 0.10792158544063568,
|
|
"num_tokens": 1827590.0,
|
|
"step": 1050
|
|
},
|
|
{
|
|
"entropy": 6.842350673675537,
|
|
"epoch": 0.08208519743240615,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000499999800894565,
|
|
"loss": 6.6064,
|
|
"mean_token_accuracy": 0.10936003550887108,
|
|
"num_tokens": 1836467.0,
|
|
"step": 1055
|
|
},
|
|
{
|
|
"entropy": 6.7909856796264645,
|
|
"epoch": 0.08247422680412371,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999997623161866,
|
|
"loss": 6.5501,
|
|
"mean_token_accuracy": 0.1102816753089428,
|
|
"num_tokens": 1845537.0,
|
|
"step": 1060
|
|
},
|
|
{
|
|
"entropy": 6.798137998580932,
|
|
"epoch": 0.08286325617584128,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999997203237951,
|
|
"loss": 6.5568,
|
|
"mean_token_accuracy": 0.11228980720043183,
|
|
"num_tokens": 1854433.0,
|
|
"step": 1065
|
|
},
|
|
{
|
|
"entropy": 6.846316385269165,
|
|
"epoch": 0.08325228554755884,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000499999674917391,
|
|
"loss": 6.6642,
|
|
"mean_token_accuracy": 0.10633082091808319,
|
|
"num_tokens": 1863708.0,
|
|
"step": 1070
|
|
},
|
|
{
|
|
"entropy": 6.800260066986084,
|
|
"epoch": 0.0836413149192764,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999996260969748,
|
|
"loss": 6.5127,
|
|
"mean_token_accuracy": 0.11366265788674354,
|
|
"num_tokens": 1871854.0,
|
|
"step": 1075
|
|
},
|
|
{
|
|
"entropy": 6.745605897903443,
|
|
"epoch": 0.08403034429099397,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999995738625475,
|
|
"loss": 6.4832,
|
|
"mean_token_accuracy": 0.11385836526751518,
|
|
"num_tokens": 1880471.0,
|
|
"step": 1080
|
|
},
|
|
{
|
|
"entropy": 6.780485916137695,
|
|
"epoch": 0.08441937366271153,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999995182141099,
|
|
"loss": 6.5533,
|
|
"mean_token_accuracy": 0.11285655200481415,
|
|
"num_tokens": 1889882.0,
|
|
"step": 1085
|
|
},
|
|
{
|
|
"entropy": 6.703962755203247,
|
|
"epoch": 0.0848084030344291,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004999994591516626,
|
|
"loss": 6.4536,
|
|
"mean_token_accuracy": 0.11884711608290673,
|
|
"num_tokens": 1898701.0,
|
|
"step": 1090
|
|
},
|
|
{
|
|
"entropy": 6.733728122711182,
|
|
"epoch": 0.08519743240614666,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999993966752066,
|
|
"loss": 6.5431,
|
|
"mean_token_accuracy": 0.10564961209893227,
|
|
"num_tokens": 1908165.0,
|
|
"step": 1095
|
|
},
|
|
{
|
|
"entropy": 6.80612211227417,
|
|
"epoch": 0.08558646177786423,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000499999330784743,
|
|
"loss": 6.6478,
|
|
"mean_token_accuracy": 0.1123865082859993,
|
|
"num_tokens": 1916295.0,
|
|
"step": 1100
|
|
},
|
|
{
|
|
"entropy": 6.840036296844483,
|
|
"epoch": 0.08597549114958179,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999992614802725,
|
|
"loss": 6.5403,
|
|
"mean_token_accuracy": 0.1170975498855114,
|
|
"num_tokens": 1924643.0,
|
|
"step": 1105
|
|
},
|
|
{
|
|
"entropy": 6.790605068206787,
|
|
"epoch": 0.08636452052129936,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999991887617966,
|
|
"loss": 6.55,
|
|
"mean_token_accuracy": 0.11264167055487632,
|
|
"num_tokens": 1933822.0,
|
|
"step": 1110
|
|
},
|
|
{
|
|
"entropy": 6.68263874053955,
|
|
"epoch": 0.08675354989301692,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999991126293158,
|
|
"loss": 6.5535,
|
|
"mean_token_accuracy": 0.11057107970118522,
|
|
"num_tokens": 1943278.0,
|
|
"step": 1115
|
|
},
|
|
{
|
|
"entropy": 6.915115308761597,
|
|
"epoch": 0.08714257926473448,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999990330828318,
|
|
"loss": 6.5695,
|
|
"mean_token_accuracy": 0.1134694166481495,
|
|
"num_tokens": 1951883.0,
|
|
"step": 1120
|
|
},
|
|
{
|
|
"entropy": 6.65633978843689,
|
|
"epoch": 0.08753160863645205,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999989501223456,
|
|
"loss": 6.4789,
|
|
"mean_token_accuracy": 0.120311389118433,
|
|
"num_tokens": 1959567.0,
|
|
"step": 1125
|
|
},
|
|
{
|
|
"entropy": 6.808887338638305,
|
|
"epoch": 0.08792063800816961,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999988637478584,
|
|
"loss": 6.534,
|
|
"mean_token_accuracy": 0.11390565186738968,
|
|
"num_tokens": 1968190.0,
|
|
"step": 1130
|
|
},
|
|
{
|
|
"entropy": 6.660136461257935,
|
|
"epoch": 0.08830966737988719,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999987739593716,
|
|
"loss": 6.4539,
|
|
"mean_token_accuracy": 0.1147844597697258,
|
|
"num_tokens": 1977519.0,
|
|
"step": 1135
|
|
},
|
|
{
|
|
"entropy": 6.740057754516601,
|
|
"epoch": 0.08869869675160474,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999986807568865,
|
|
"loss": 6.4617,
|
|
"mean_token_accuracy": 0.11601719185709954,
|
|
"num_tokens": 1985796.0,
|
|
"step": 1140
|
|
},
|
|
{
|
|
"entropy": 6.815498018264771,
|
|
"epoch": 0.08908772612332232,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999985841404045,
|
|
"loss": 6.59,
|
|
"mean_token_accuracy": 0.10702956765890122,
|
|
"num_tokens": 1993874.0,
|
|
"step": 1145
|
|
},
|
|
{
|
|
"entropy": 6.867396354675293,
|
|
"epoch": 0.08947675549503988,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999984841099271,
|
|
"loss": 6.544,
|
|
"mean_token_accuracy": 0.11298409327864647,
|
|
"num_tokens": 2001663.0,
|
|
"step": 1150
|
|
},
|
|
{
|
|
"entropy": 6.687847232818603,
|
|
"epoch": 0.08986578486675743,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000499998380665456,
|
|
"loss": 6.5284,
|
|
"mean_token_accuracy": 0.11568290889263153,
|
|
"num_tokens": 2010179.0,
|
|
"step": 1155
|
|
},
|
|
{
|
|
"entropy": 6.760761499404907,
|
|
"epoch": 0.090254814238475,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999982738069924,
|
|
"loss": 6.434,
|
|
"mean_token_accuracy": 0.11665870845317841,
|
|
"num_tokens": 2020013.0,
|
|
"step": 1160
|
|
},
|
|
{
|
|
"entropy": 6.742422866821289,
|
|
"epoch": 0.09064384361019256,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004999981635345382,
|
|
"loss": 6.568,
|
|
"mean_token_accuracy": 0.11969253122806549,
|
|
"num_tokens": 2028396.0,
|
|
"step": 1165
|
|
},
|
|
{
|
|
"entropy": 6.825271940231323,
|
|
"epoch": 0.09103287298191014,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999980498480949,
|
|
"loss": 6.6335,
|
|
"mean_token_accuracy": 0.11033851355314254,
|
|
"num_tokens": 2036947.0,
|
|
"step": 1170
|
|
},
|
|
{
|
|
"entropy": 6.715671443939209,
|
|
"epoch": 0.0914219023536277,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999979327476644,
|
|
"loss": 6.4834,
|
|
"mean_token_accuracy": 0.11201950162649155,
|
|
"num_tokens": 2045162.0,
|
|
"step": 1175
|
|
},
|
|
{
|
|
"entropy": 6.766329193115235,
|
|
"epoch": 0.09181093172534527,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004999978122332485,
|
|
"loss": 6.5764,
|
|
"mean_token_accuracy": 0.11277065798640251,
|
|
"num_tokens": 2054198.0,
|
|
"step": 1180
|
|
},
|
|
{
|
|
"entropy": 6.686334037780762,
|
|
"epoch": 0.09219996109706283,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999976883048487,
|
|
"loss": 6.4753,
|
|
"mean_token_accuracy": 0.11509751304984092,
|
|
"num_tokens": 2062558.0,
|
|
"step": 1185
|
|
},
|
|
{
|
|
"entropy": 6.642856502532959,
|
|
"epoch": 0.0925889904687804,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004999975609624673,
|
|
"loss": 6.3676,
|
|
"mean_token_accuracy": 0.11287973672151566,
|
|
"num_tokens": 2070816.0,
|
|
"step": 1190
|
|
},
|
|
{
|
|
"entropy": 6.751265525817871,
|
|
"epoch": 0.09297801984049796,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999974302061059,
|
|
"loss": 6.4407,
|
|
"mean_token_accuracy": 0.11461416780948638,
|
|
"num_tokens": 2079058.0,
|
|
"step": 1195
|
|
},
|
|
{
|
|
"entropy": 6.6414995193481445,
|
|
"epoch": 0.09336704921221552,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004999972960357666,
|
|
"loss": 6.3879,
|
|
"mean_token_accuracy": 0.11782738789916039,
|
|
"num_tokens": 2086679.0,
|
|
"step": 1200
|
|
},
|
|
{
|
|
"entropy": 6.725094270706177,
|
|
"epoch": 0.09375607858393309,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999971584514516,
|
|
"loss": 6.5033,
|
|
"mean_token_accuracy": 0.11564282923936844,
|
|
"num_tokens": 2095788.0,
|
|
"step": 1205
|
|
},
|
|
{
|
|
"entropy": 6.734344482421875,
|
|
"epoch": 0.09414510795565065,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999970174531627,
|
|
"loss": 6.5344,
|
|
"mean_token_accuracy": 0.11681660562753678,
|
|
"num_tokens": 2105435.0,
|
|
"step": 1210
|
|
},
|
|
{
|
|
"entropy": 6.622858190536499,
|
|
"epoch": 0.09453413732736822,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999968730409022,
|
|
"loss": 6.4773,
|
|
"mean_token_accuracy": 0.11257969439029694,
|
|
"num_tokens": 2114318.0,
|
|
"step": 1215
|
|
},
|
|
{
|
|
"entropy": 6.707676362991333,
|
|
"epoch": 0.09492316669908578,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999967252146723,
|
|
"loss": 6.3901,
|
|
"mean_token_accuracy": 0.1280004471540451,
|
|
"num_tokens": 2122707.0,
|
|
"step": 1220
|
|
},
|
|
{
|
|
"entropy": 6.613141632080078,
|
|
"epoch": 0.09531219607080335,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999965739744752,
|
|
"loss": 6.4989,
|
|
"mean_token_accuracy": 0.11614064946770668,
|
|
"num_tokens": 2131176.0,
|
|
"step": 1225
|
|
},
|
|
{
|
|
"entropy": 6.743852138519287,
|
|
"epoch": 0.09570122544252091,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999964193203132,
|
|
"loss": 6.5268,
|
|
"mean_token_accuracy": 0.1201147809624672,
|
|
"num_tokens": 2139872.0,
|
|
"step": 1230
|
|
},
|
|
{
|
|
"entropy": 6.755846691131592,
|
|
"epoch": 0.09609025481423847,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999962612521888,
|
|
"loss": 6.3904,
|
|
"mean_token_accuracy": 0.12232213765382767,
|
|
"num_tokens": 2148668.0,
|
|
"step": 1235
|
|
},
|
|
{
|
|
"entropy": 6.5976697444915775,
|
|
"epoch": 0.09647928418595604,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999960997701041,
|
|
"loss": 6.3884,
|
|
"mean_token_accuracy": 0.12410193756222725,
|
|
"num_tokens": 2156628.0,
|
|
"step": 1240
|
|
},
|
|
{
|
|
"entropy": 6.723433208465576,
|
|
"epoch": 0.0968683135576736,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999959348740618,
|
|
"loss": 6.4816,
|
|
"mean_token_accuracy": 0.11155348718166351,
|
|
"num_tokens": 2165620.0,
|
|
"step": 1245
|
|
},
|
|
{
|
|
"entropy": 6.685586643218994,
|
|
"epoch": 0.09725734292939117,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004999957665640641,
|
|
"loss": 6.5553,
|
|
"mean_token_accuracy": 0.11295825839042664,
|
|
"num_tokens": 2174493.0,
|
|
"step": 1250
|
|
},
|
|
{
|
|
"entropy": 6.718245220184326,
|
|
"epoch": 0.09764637230110873,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000499995594840114,
|
|
"loss": 6.4554,
|
|
"mean_token_accuracy": 0.11334520950913429,
|
|
"num_tokens": 2183258.0,
|
|
"step": 1255
|
|
},
|
|
{
|
|
"entropy": 6.7033568859100345,
|
|
"epoch": 0.0980354016728263,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999954197022138,
|
|
"loss": 6.4894,
|
|
"mean_token_accuracy": 0.11108549013733864,
|
|
"num_tokens": 2192263.0,
|
|
"step": 1260
|
|
},
|
|
{
|
|
"entropy": 6.724197483062744,
|
|
"epoch": 0.09842443104454386,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999952411503661,
|
|
"loss": 6.5465,
|
|
"mean_token_accuracy": 0.1062019944190979,
|
|
"num_tokens": 2201797.0,
|
|
"step": 1265
|
|
},
|
|
{
|
|
"entropy": 6.554443073272705,
|
|
"epoch": 0.09881346041626143,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999950591845738,
|
|
"loss": 6.2769,
|
|
"mean_token_accuracy": 0.12360937595367431,
|
|
"num_tokens": 2209454.0,
|
|
"step": 1270
|
|
},
|
|
{
|
|
"entropy": 6.728240442276001,
|
|
"epoch": 0.09920248978797899,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999948738048397,
|
|
"loss": 6.4715,
|
|
"mean_token_accuracy": 0.12011136263608932,
|
|
"num_tokens": 2217761.0,
|
|
"step": 1275
|
|
},
|
|
{
|
|
"entropy": 6.589418649673462,
|
|
"epoch": 0.09959151915969655,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004999946850111663,
|
|
"loss": 6.4558,
|
|
"mean_token_accuracy": 0.11745724231004714,
|
|
"num_tokens": 2225793.0,
|
|
"step": 1280
|
|
},
|
|
{
|
|
"entropy": 6.725760078430175,
|
|
"epoch": 0.09998054853141412,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999944928035569,
|
|
"loss": 6.3478,
|
|
"mean_token_accuracy": 0.12596990913152695,
|
|
"num_tokens": 2234620.0,
|
|
"step": 1285
|
|
},
|
|
{
|
|
"entropy": 6.576044940948487,
|
|
"epoch": 0.10036957790313168,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000499994297182014,
|
|
"loss": 6.4253,
|
|
"mean_token_accuracy": 0.11709852069616318,
|
|
"num_tokens": 2242829.0,
|
|
"step": 1290
|
|
},
|
|
{
|
|
"entropy": 6.768080854415894,
|
|
"epoch": 0.10075860727484925,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999940981465408,
|
|
"loss": 6.4503,
|
|
"mean_token_accuracy": 0.11201097890734672,
|
|
"num_tokens": 2251356.0,
|
|
"step": 1295
|
|
},
|
|
{
|
|
"entropy": 6.582262754440308,
|
|
"epoch": 0.10114763664656681,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999938956971404,
|
|
"loss": 6.5095,
|
|
"mean_token_accuracy": 0.11508250460028649,
|
|
"num_tokens": 2259327.0,
|
|
"step": 1300
|
|
},
|
|
{
|
|
"entropy": 6.726982116699219,
|
|
"epoch": 0.10153666601828439,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999936898338156,
|
|
"loss": 6.523,
|
|
"mean_token_accuracy": 0.11173656061291695,
|
|
"num_tokens": 2267948.0,
|
|
"step": 1305
|
|
},
|
|
{
|
|
"entropy": 6.588463926315308,
|
|
"epoch": 0.10192569539000194,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999934805565698,
|
|
"loss": 6.3409,
|
|
"mean_token_accuracy": 0.12150438576936722,
|
|
"num_tokens": 2275828.0,
|
|
"step": 1310
|
|
},
|
|
{
|
|
"entropy": 6.558595943450928,
|
|
"epoch": 0.10231472476171952,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000499993267865406,
|
|
"loss": 6.2999,
|
|
"mean_token_accuracy": 0.12410445511341095,
|
|
"num_tokens": 2284246.0,
|
|
"step": 1315
|
|
},
|
|
{
|
|
"entropy": 6.591059923171997,
|
|
"epoch": 0.10270375413343708,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999930517603275,
|
|
"loss": 6.2729,
|
|
"mean_token_accuracy": 0.12803125903010368,
|
|
"num_tokens": 2291837.0,
|
|
"step": 1320
|
|
},
|
|
{
|
|
"entropy": 6.616555118560791,
|
|
"epoch": 0.10309278350515463,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999928322413374,
|
|
"loss": 6.3566,
|
|
"mean_token_accuracy": 0.1179949127137661,
|
|
"num_tokens": 2299853.0,
|
|
"step": 1325
|
|
},
|
|
{
|
|
"entropy": 6.700346422195435,
|
|
"epoch": 0.1034818128768722,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999926093084394,
|
|
"loss": 6.4513,
|
|
"mean_token_accuracy": 0.11860990896821022,
|
|
"num_tokens": 2308416.0,
|
|
"step": 1330
|
|
},
|
|
{
|
|
"entropy": 6.64585771560669,
|
|
"epoch": 0.10387084224858976,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999923829616365,
|
|
"loss": 6.4687,
|
|
"mean_token_accuracy": 0.11745152324438095,
|
|
"num_tokens": 2318104.0,
|
|
"step": 1335
|
|
},
|
|
{
|
|
"entropy": 6.545508909225464,
|
|
"epoch": 0.10425987162030734,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004999921532009323,
|
|
"loss": 6.3939,
|
|
"mean_token_accuracy": 0.11805395260453225,
|
|
"num_tokens": 2326807.0,
|
|
"step": 1340
|
|
},
|
|
{
|
|
"entropy": 6.693354845046997,
|
|
"epoch": 0.1046489009920249,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999919200263304,
|
|
"loss": 6.4063,
|
|
"mean_token_accuracy": 0.11813065260648728,
|
|
"num_tokens": 2335921.0,
|
|
"step": 1345
|
|
},
|
|
{
|
|
"entropy": 6.571820402145386,
|
|
"epoch": 0.10503793036374247,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999916834378342,
|
|
"loss": 6.4246,
|
|
"mean_token_accuracy": 0.11576211974024772,
|
|
"num_tokens": 2344914.0,
|
|
"step": 1350
|
|
},
|
|
{
|
|
"entropy": 6.570094347000122,
|
|
"epoch": 0.10542695973546003,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999914434354472,
|
|
"loss": 6.3649,
|
|
"mean_token_accuracy": 0.11981132701039314,
|
|
"num_tokens": 2353211.0,
|
|
"step": 1355
|
|
},
|
|
{
|
|
"entropy": 6.647089672088623,
|
|
"epoch": 0.10581598910717759,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999912000191733,
|
|
"loss": 6.4694,
|
|
"mean_token_accuracy": 0.11573371812701225,
|
|
"num_tokens": 2361717.0,
|
|
"step": 1360
|
|
},
|
|
{
|
|
"entropy": 6.617790842056275,
|
|
"epoch": 0.10620501847889516,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000499990953189016,
|
|
"loss": 6.4211,
|
|
"mean_token_accuracy": 0.12210528329014778,
|
|
"num_tokens": 2370114.0,
|
|
"step": 1365
|
|
},
|
|
{
|
|
"entropy": 6.682390451431274,
|
|
"epoch": 0.10659404785061272,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999907029449791,
|
|
"loss": 6.4051,
|
|
"mean_token_accuracy": 0.12277124375104904,
|
|
"num_tokens": 2378820.0,
|
|
"step": 1370
|
|
},
|
|
{
|
|
"entropy": 6.514065790176391,
|
|
"epoch": 0.10698307722233029,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999904492870663,
|
|
"loss": 6.3213,
|
|
"mean_token_accuracy": 0.12254384979605674,
|
|
"num_tokens": 2387119.0,
|
|
"step": 1375
|
|
},
|
|
{
|
|
"entropy": 6.626542711257935,
|
|
"epoch": 0.10737210659404785,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999901922152816,
|
|
"loss": 6.3765,
|
|
"mean_token_accuracy": 0.1194961629807949,
|
|
"num_tokens": 2396246.0,
|
|
"step": 1380
|
|
},
|
|
{
|
|
"entropy": 6.501721668243408,
|
|
"epoch": 0.10776113596576542,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999899317296288,
|
|
"loss": 6.4157,
|
|
"mean_token_accuracy": 0.11856927499175071,
|
|
"num_tokens": 2405428.0,
|
|
"step": 1385
|
|
},
|
|
{
|
|
"entropy": 6.596559715270996,
|
|
"epoch": 0.10815016533748298,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999896678301121,
|
|
"loss": 6.3741,
|
|
"mean_token_accuracy": 0.1184548296034336,
|
|
"num_tokens": 2414669.0,
|
|
"step": 1390
|
|
},
|
|
{
|
|
"entropy": 6.705186796188355,
|
|
"epoch": 0.10853919470920055,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999894005167352,
|
|
"loss": 6.4612,
|
|
"mean_token_accuracy": 0.11556609496474265,
|
|
"num_tokens": 2423193.0,
|
|
"step": 1395
|
|
},
|
|
{
|
|
"entropy": 6.6101438999176025,
|
|
"epoch": 0.10892822408091811,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000499989129789502,
|
|
"loss": 6.4064,
|
|
"mean_token_accuracy": 0.11643991023302078,
|
|
"num_tokens": 2431150.0,
|
|
"step": 1400
|
|
},
|
|
{
|
|
"entropy": 6.540600776672363,
|
|
"epoch": 0.10931725345263567,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999888556484172,
|
|
"loss": 6.3807,
|
|
"mean_token_accuracy": 0.11422878503799438,
|
|
"num_tokens": 2440337.0,
|
|
"step": 1405
|
|
},
|
|
{
|
|
"entropy": 6.589718914031982,
|
|
"epoch": 0.10970628282435324,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999885780934845,
|
|
"loss": 6.3226,
|
|
"mean_token_accuracy": 0.12455554753541946,
|
|
"num_tokens": 2449246.0,
|
|
"step": 1410
|
|
},
|
|
{
|
|
"entropy": 6.561670303344727,
|
|
"epoch": 0.1100953121960708,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999882971247081,
|
|
"loss": 6.3256,
|
|
"mean_token_accuracy": 0.12393307089805602,
|
|
"num_tokens": 2457982.0,
|
|
"step": 1415
|
|
},
|
|
{
|
|
"entropy": 6.534701871871948,
|
|
"epoch": 0.11048434156778837,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999880127420926,
|
|
"loss": 6.3142,
|
|
"mean_token_accuracy": 0.12068029120564461,
|
|
"num_tokens": 2466697.0,
|
|
"step": 1420
|
|
},
|
|
{
|
|
"entropy": 6.558716917037964,
|
|
"epoch": 0.11087337093950593,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999877249456421,
|
|
"loss": 6.2992,
|
|
"mean_token_accuracy": 0.12362277731299401,
|
|
"num_tokens": 2475457.0,
|
|
"step": 1425
|
|
},
|
|
{
|
|
"entropy": 6.464503622055053,
|
|
"epoch": 0.1112624003112235,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004999874337353609,
|
|
"loss": 6.2568,
|
|
"mean_token_accuracy": 0.12550607100129127,
|
|
"num_tokens": 2484753.0,
|
|
"step": 1430
|
|
},
|
|
{
|
|
"entropy": 6.553883075714111,
|
|
"epoch": 0.11165142968294106,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999871391112535,
|
|
"loss": 6.3796,
|
|
"mean_token_accuracy": 0.12183060646057128,
|
|
"num_tokens": 2492921.0,
|
|
"step": 1435
|
|
},
|
|
{
|
|
"entropy": 6.573325300216675,
|
|
"epoch": 0.11204045905465862,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999868410733244,
|
|
"loss": 6.3569,
|
|
"mean_token_accuracy": 0.12047385424375534,
|
|
"num_tokens": 2501371.0,
|
|
"step": 1440
|
|
},
|
|
{
|
|
"entropy": 6.570412826538086,
|
|
"epoch": 0.11242948842637619,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000499986539621578,
|
|
"loss": 6.2245,
|
|
"mean_token_accuracy": 0.12222100347280503,
|
|
"num_tokens": 2509521.0,
|
|
"step": 1445
|
|
},
|
|
{
|
|
"entropy": 6.550269222259521,
|
|
"epoch": 0.11281851779809375,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999862347560191,
|
|
"loss": 6.3615,
|
|
"mean_token_accuracy": 0.12241242602467536,
|
|
"num_tokens": 2518316.0,
|
|
"step": 1450
|
|
},
|
|
{
|
|
"entropy": 6.55282735824585,
|
|
"epoch": 0.11320754716981132,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999859264766521,
|
|
"loss": 6.4293,
|
|
"mean_token_accuracy": 0.11907708570361138,
|
|
"num_tokens": 2527549.0,
|
|
"step": 1455
|
|
},
|
|
{
|
|
"entropy": 6.628605079650879,
|
|
"epoch": 0.11359657654152888,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999856147834817,
|
|
"loss": 6.4688,
|
|
"mean_token_accuracy": 0.11421279311180114,
|
|
"num_tokens": 2536341.0,
|
|
"step": 1460
|
|
},
|
|
{
|
|
"entropy": 6.505453729629517,
|
|
"epoch": 0.11398560591324645,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999852996765129,
|
|
"loss": 6.3516,
|
|
"mean_token_accuracy": 0.12754116728901863,
|
|
"num_tokens": 2544869.0,
|
|
"step": 1465
|
|
},
|
|
{
|
|
"entropy": 6.604720211029052,
|
|
"epoch": 0.11437463528496401,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999849811557502,
|
|
"loss": 6.2474,
|
|
"mean_token_accuracy": 0.13095576241612433,
|
|
"num_tokens": 2553432.0,
|
|
"step": 1470
|
|
},
|
|
{
|
|
"entropy": 6.5074522495269775,
|
|
"epoch": 0.11476366465668159,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999846592211984,
|
|
"loss": 6.3718,
|
|
"mean_token_accuracy": 0.1168175496160984,
|
|
"num_tokens": 2561996.0,
|
|
"step": 1475
|
|
},
|
|
{
|
|
"entropy": 6.550441551208496,
|
|
"epoch": 0.11515269402839914,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999843338728626,
|
|
"loss": 6.3114,
|
|
"mean_token_accuracy": 0.12313547134399414,
|
|
"num_tokens": 2571315.0,
|
|
"step": 1480
|
|
},
|
|
{
|
|
"entropy": 6.485339689254761,
|
|
"epoch": 0.1155417234001167,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999840051107476,
|
|
"loss": 6.4213,
|
|
"mean_token_accuracy": 0.12167479395866394,
|
|
"num_tokens": 2579589.0,
|
|
"step": 1485
|
|
},
|
|
{
|
|
"entropy": 6.56643123626709,
|
|
"epoch": 0.11593075277183428,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999836729348584,
|
|
"loss": 6.1891,
|
|
"mean_token_accuracy": 0.12298046126961708,
|
|
"num_tokens": 2588528.0,
|
|
"step": 1490
|
|
},
|
|
{
|
|
"entropy": 6.466246747970581,
|
|
"epoch": 0.11631978214355183,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999833373452,
|
|
"loss": 6.3238,
|
|
"mean_token_accuracy": 0.12104458585381508,
|
|
"num_tokens": 2596820.0,
|
|
"step": 1495
|
|
},
|
|
{
|
|
"entropy": 6.466208410263062,
|
|
"epoch": 0.1167088115152694,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999829983417778,
|
|
"loss": 6.2499,
|
|
"mean_token_accuracy": 0.1204721324145794,
|
|
"num_tokens": 2605502.0,
|
|
"step": 1500
|
|
},
|
|
{
|
|
"entropy": 6.4354174613952635,
|
|
"epoch": 0.11709784088698696,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999826559245965,
|
|
"loss": 6.2334,
|
|
"mean_token_accuracy": 0.13126121312379838,
|
|
"num_tokens": 2613974.0,
|
|
"step": 1505
|
|
},
|
|
{
|
|
"entropy": 6.435812187194824,
|
|
"epoch": 0.11748687025870454,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999823100936615,
|
|
"loss": 6.3333,
|
|
"mean_token_accuracy": 0.12118990495800971,
|
|
"num_tokens": 2622581.0,
|
|
"step": 1510
|
|
},
|
|
{
|
|
"entropy": 6.555751800537109,
|
|
"epoch": 0.1178758996304221,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999819608489781,
|
|
"loss": 6.2104,
|
|
"mean_token_accuracy": 0.1205756813287735,
|
|
"num_tokens": 2631868.0,
|
|
"step": 1515
|
|
},
|
|
{
|
|
"entropy": 6.42847900390625,
|
|
"epoch": 0.11826492900213967,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999816081905515,
|
|
"loss": 6.2463,
|
|
"mean_token_accuracy": 0.12586833164095879,
|
|
"num_tokens": 2640501.0,
|
|
"step": 1520
|
|
},
|
|
{
|
|
"entropy": 6.500116395950317,
|
|
"epoch": 0.11865395837385723,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999812521183872,
|
|
"loss": 6.2471,
|
|
"mean_token_accuracy": 0.12680162265896797,
|
|
"num_tokens": 2648916.0,
|
|
"step": 1525
|
|
},
|
|
{
|
|
"entropy": 6.536718368530273,
|
|
"epoch": 0.11904298774557479,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999808926324903,
|
|
"loss": 6.3235,
|
|
"mean_token_accuracy": 0.12868664413690567,
|
|
"num_tokens": 2657725.0,
|
|
"step": 1530
|
|
},
|
|
{
|
|
"entropy": 6.425989866256714,
|
|
"epoch": 0.11943201711729236,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999805297328665,
|
|
"loss": 6.2894,
|
|
"mean_token_accuracy": 0.1203535608947277,
|
|
"num_tokens": 2665983.0,
|
|
"step": 1535
|
|
},
|
|
{
|
|
"entropy": 6.5746509552001955,
|
|
"epoch": 0.11982104648900992,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999801634195214,
|
|
"loss": 6.3172,
|
|
"mean_token_accuracy": 0.1309082590043545,
|
|
"num_tokens": 2674546.0,
|
|
"step": 1540
|
|
},
|
|
{
|
|
"entropy": 6.456331253051758,
|
|
"epoch": 0.12021007586072749,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004999797936924603,
|
|
"loss": 6.2295,
|
|
"mean_token_accuracy": 0.1303058944642544,
|
|
"num_tokens": 2684088.0,
|
|
"step": 1545
|
|
},
|
|
{
|
|
"entropy": 6.505995798110962,
|
|
"epoch": 0.12059910523244505,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000499979420551689,
|
|
"loss": 6.2917,
|
|
"mean_token_accuracy": 0.121770840883255,
|
|
"num_tokens": 2693289.0,
|
|
"step": 1550
|
|
},
|
|
{
|
|
"entropy": 6.439859294891358,
|
|
"epoch": 0.12098813460416262,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000499979043997213,
|
|
"loss": 6.2212,
|
|
"mean_token_accuracy": 0.1267593041062355,
|
|
"num_tokens": 2701744.0,
|
|
"step": 1555
|
|
},
|
|
{
|
|
"entropy": 6.472963476181031,
|
|
"epoch": 0.12137716397588018,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999786640290381,
|
|
"loss": 6.266,
|
|
"mean_token_accuracy": 0.12355687320232392,
|
|
"num_tokens": 2710584.0,
|
|
"step": 1560
|
|
},
|
|
{
|
|
"entropy": 6.534983539581299,
|
|
"epoch": 0.12176619334759774,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004999782806471701,
|
|
"loss": 6.287,
|
|
"mean_token_accuracy": 0.1200690247118473,
|
|
"num_tokens": 2719478.0,
|
|
"step": 1565
|
|
},
|
|
{
|
|
"entropy": 6.546087789535522,
|
|
"epoch": 0.12215522271931531,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999778938516147,
|
|
"loss": 6.3619,
|
|
"mean_token_accuracy": 0.11858213022351265,
|
|
"num_tokens": 2729105.0,
|
|
"step": 1570
|
|
},
|
|
{
|
|
"entropy": 6.497035884857178,
|
|
"epoch": 0.12254425209103287,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.000499977503642378,
|
|
"loss": 6.3199,
|
|
"mean_token_accuracy": 0.1214341938495636,
|
|
"num_tokens": 2738300.0,
|
|
"step": 1575
|
|
},
|
|
{
|
|
"entropy": 6.564480495452881,
|
|
"epoch": 0.12293328146275044,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999771100194656,
|
|
"loss": 6.2592,
|
|
"mean_token_accuracy": 0.12089609131217002,
|
|
"num_tokens": 2747236.0,
|
|
"step": 1580
|
|
},
|
|
{
|
|
"entropy": 6.389290761947632,
|
|
"epoch": 0.123322310834468,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999767129828837,
|
|
"loss": 6.1946,
|
|
"mean_token_accuracy": 0.12700149565935134,
|
|
"num_tokens": 2755919.0,
|
|
"step": 1585
|
|
},
|
|
{
|
|
"entropy": 6.3935548782348635,
|
|
"epoch": 0.12371134020618557,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999763125326383,
|
|
"loss": 6.1975,
|
|
"mean_token_accuracy": 0.12940854504704474,
|
|
"num_tokens": 2764469.0,
|
|
"step": 1590
|
|
},
|
|
{
|
|
"entropy": 6.486390113830566,
|
|
"epoch": 0.12410036957790313,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999759086687355,
|
|
"loss": 6.2067,
|
|
"mean_token_accuracy": 0.13023579344153405,
|
|
"num_tokens": 2772663.0,
|
|
"step": 1595
|
|
},
|
|
{
|
|
"entropy": 6.543991231918335,
|
|
"epoch": 0.1244893989496207,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999755013911813,
|
|
"loss": 6.2463,
|
|
"mean_token_accuracy": 0.12318727225065232,
|
|
"num_tokens": 2780719.0,
|
|
"step": 1600
|
|
},
|
|
{
|
|
"entropy": 6.4445489883422855,
|
|
"epoch": 0.12487842832133826,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000499975090699982,
|
|
"loss": 6.2958,
|
|
"mean_token_accuracy": 0.12555501163005828,
|
|
"num_tokens": 2789186.0,
|
|
"step": 1605
|
|
},
|
|
{
|
|
"entropy": 6.420124244689942,
|
|
"epoch": 0.12526745769305583,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999746765951438,
|
|
"loss": 6.208,
|
|
"mean_token_accuracy": 0.12907335609197618,
|
|
"num_tokens": 2797993.0,
|
|
"step": 1610
|
|
},
|
|
{
|
|
"entropy": 6.432662439346314,
|
|
"epoch": 0.1256564870647734,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999742590766729,
|
|
"loss": 6.1669,
|
|
"mean_token_accuracy": 0.12667878344655037,
|
|
"num_tokens": 2806375.0,
|
|
"step": 1615
|
|
},
|
|
{
|
|
"entropy": 6.512080526351928,
|
|
"epoch": 0.12604551643649095,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999738381445757,
|
|
"loss": 6.3037,
|
|
"mean_token_accuracy": 0.13135089427232743,
|
|
"num_tokens": 2814772.0,
|
|
"step": 1620
|
|
},
|
|
{
|
|
"entropy": 6.298824071884155,
|
|
"epoch": 0.1264345458082085,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999734137988586,
|
|
"loss": 6.1753,
|
|
"mean_token_accuracy": 0.13204587176442145,
|
|
"num_tokens": 2824231.0,
|
|
"step": 1625
|
|
},
|
|
{
|
|
"entropy": 6.452016353607178,
|
|
"epoch": 0.1268235751799261,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000499972986039528,
|
|
"loss": 6.2368,
|
|
"mean_token_accuracy": 0.12344342246651649,
|
|
"num_tokens": 2833470.0,
|
|
"step": 1630
|
|
},
|
|
{
|
|
"entropy": 6.50761456489563,
|
|
"epoch": 0.12721260455164365,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004999725548665904,
|
|
"loss": 6.25,
|
|
"mean_token_accuracy": 0.12541535049676894,
|
|
"num_tokens": 2843010.0,
|
|
"step": 1635
|
|
},
|
|
{
|
|
"entropy": 6.404108715057373,
|
|
"epoch": 0.1276016339233612,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999721202800524,
|
|
"loss": 6.1338,
|
|
"mean_token_accuracy": 0.1386566400527954,
|
|
"num_tokens": 2851545.0,
|
|
"step": 1640
|
|
},
|
|
{
|
|
"entropy": 6.3438740253448485,
|
|
"epoch": 0.12799066329507877,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004999716822799206,
|
|
"loss": 6.2906,
|
|
"mean_token_accuracy": 0.11413189694285393,
|
|
"num_tokens": 2861230.0,
|
|
"step": 1645
|
|
},
|
|
{
|
|
"entropy": 6.47772855758667,
|
|
"epoch": 0.12837969266679633,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999712408662016,
|
|
"loss": 6.2534,
|
|
"mean_token_accuracy": 0.1262986846268177,
|
|
"num_tokens": 2869436.0,
|
|
"step": 1650
|
|
},
|
|
{
|
|
"entropy": 6.392445182800293,
|
|
"epoch": 0.12876872203851392,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999707960389021,
|
|
"loss": 6.122,
|
|
"mean_token_accuracy": 0.13018414750695229,
|
|
"num_tokens": 2877688.0,
|
|
"step": 1655
|
|
},
|
|
{
|
|
"entropy": 6.4603923797607425,
|
|
"epoch": 0.12915775141023147,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004999703477980288,
|
|
"loss": 6.2708,
|
|
"mean_token_accuracy": 0.1284830316901207,
|
|
"num_tokens": 2887043.0,
|
|
"step": 1660
|
|
},
|
|
{
|
|
"entropy": 6.430318546295166,
|
|
"epoch": 0.12954678078194903,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999698961435885,
|
|
"loss": 6.1854,
|
|
"mean_token_accuracy": 0.12815706580877304,
|
|
"num_tokens": 2895732.0,
|
|
"step": 1665
|
|
},
|
|
{
|
|
"entropy": 6.3375777244567875,
|
|
"epoch": 0.1299358101536666,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999694410755882,
|
|
"loss": 6.1608,
|
|
"mean_token_accuracy": 0.12703153863549232,
|
|
"num_tokens": 2904162.0,
|
|
"step": 1670
|
|
},
|
|
{
|
|
"entropy": 6.449351215362549,
|
|
"epoch": 0.13032483952538418,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999689825940347,
|
|
"loss": 6.3035,
|
|
"mean_token_accuracy": 0.123183623701334,
|
|
"num_tokens": 2912783.0,
|
|
"step": 1675
|
|
},
|
|
{
|
|
"entropy": 6.479056549072266,
|
|
"epoch": 0.13071386889710174,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999685206989349,
|
|
"loss": 6.1934,
|
|
"mean_token_accuracy": 0.1278615675866604,
|
|
"num_tokens": 2921027.0,
|
|
"step": 1680
|
|
},
|
|
{
|
|
"entropy": 6.411128139495849,
|
|
"epoch": 0.1311028982688193,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999680553902959,
|
|
"loss": 6.2066,
|
|
"mean_token_accuracy": 0.13008249029517174,
|
|
"num_tokens": 2930398.0,
|
|
"step": 1685
|
|
},
|
|
{
|
|
"entropy": 6.392834138870239,
|
|
"epoch": 0.13149192764053685,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999675866681247,
|
|
"loss": 6.2191,
|
|
"mean_token_accuracy": 0.1267761617898941,
|
|
"num_tokens": 2938703.0,
|
|
"step": 1690
|
|
},
|
|
{
|
|
"entropy": 6.381357955932617,
|
|
"epoch": 0.1318809570122544,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999671145324286,
|
|
"loss": 6.1658,
|
|
"mean_token_accuracy": 0.12640352845191954,
|
|
"num_tokens": 2947007.0,
|
|
"step": 1695
|
|
},
|
|
{
|
|
"entropy": 6.427257251739502,
|
|
"epoch": 0.132269986383972,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999666389832144,
|
|
"loss": 6.2931,
|
|
"mean_token_accuracy": 0.12982493937015532,
|
|
"num_tokens": 2955485.0,
|
|
"step": 1700
|
|
},
|
|
{
|
|
"entropy": 6.446907711029053,
|
|
"epoch": 0.13265901575568956,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999661600204897,
|
|
"loss": 6.1536,
|
|
"mean_token_accuracy": 0.13096046820282936,
|
|
"num_tokens": 2964416.0,
|
|
"step": 1705
|
|
},
|
|
{
|
|
"entropy": 6.3575907230377195,
|
|
"epoch": 0.13304804512740712,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999656776442615,
|
|
"loss": 6.1576,
|
|
"mean_token_accuracy": 0.1293207123875618,
|
|
"num_tokens": 2972737.0,
|
|
"step": 1710
|
|
},
|
|
{
|
|
"entropy": 6.409917593002319,
|
|
"epoch": 0.13343707449912467,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999651918545372,
|
|
"loss": 6.1892,
|
|
"mean_token_accuracy": 0.12660456970334052,
|
|
"num_tokens": 2981166.0,
|
|
"step": 1715
|
|
},
|
|
{
|
|
"entropy": 6.444819402694702,
|
|
"epoch": 0.13382610387084226,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999647026513243,
|
|
"loss": 6.2508,
|
|
"mean_token_accuracy": 0.12753460928797722,
|
|
"num_tokens": 2989689.0,
|
|
"step": 1720
|
|
},
|
|
{
|
|
"entropy": 6.436755228042602,
|
|
"epoch": 0.13421513324255982,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00049996421003463,
|
|
"loss": 6.1478,
|
|
"mean_token_accuracy": 0.1300426684319973,
|
|
"num_tokens": 2998793.0,
|
|
"step": 1725
|
|
},
|
|
{
|
|
"entropy": 6.365857887268066,
|
|
"epoch": 0.13460416261427738,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999637140044619,
|
|
"loss": 6.2926,
|
|
"mean_token_accuracy": 0.12362960577011109,
|
|
"num_tokens": 3007320.0,
|
|
"step": 1730
|
|
},
|
|
{
|
|
"entropy": 6.463358211517334,
|
|
"epoch": 0.13499319198599494,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999632145608275,
|
|
"loss": 6.196,
|
|
"mean_token_accuracy": 0.12713374942541122,
|
|
"num_tokens": 3015024.0,
|
|
"step": 1735
|
|
},
|
|
{
|
|
"entropy": 6.4128015518188475,
|
|
"epoch": 0.1353822213577125,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999627117037343,
|
|
"loss": 6.299,
|
|
"mean_token_accuracy": 0.1275800235569477,
|
|
"num_tokens": 3023058.0,
|
|
"step": 1740
|
|
},
|
|
{
|
|
"entropy": 6.471516561508179,
|
|
"epoch": 0.13577125072943008,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00049996220543319,
|
|
"loss": 6.1937,
|
|
"mean_token_accuracy": 0.13457101881504058,
|
|
"num_tokens": 3031308.0,
|
|
"step": 1745
|
|
},
|
|
{
|
|
"entropy": 6.40582799911499,
|
|
"epoch": 0.13616028010114764,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004999616957492025,
|
|
"loss": 6.2654,
|
|
"mean_token_accuracy": 0.12314189150929451,
|
|
"num_tokens": 3039598.0,
|
|
"step": 1750
|
|
},
|
|
{
|
|
"entropy": 6.340579605102539,
|
|
"epoch": 0.1365493094728652,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999611826517793,
|
|
"loss": 6.0849,
|
|
"mean_token_accuracy": 0.13836994841694833,
|
|
"num_tokens": 3047598.0,
|
|
"step": 1755
|
|
},
|
|
{
|
|
"entropy": 6.46547417640686,
|
|
"epoch": 0.13693833884458276,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999606661409281,
|
|
"loss": 6.2395,
|
|
"mean_token_accuracy": 0.12904614359140396,
|
|
"num_tokens": 3055702.0,
|
|
"step": 1760
|
|
},
|
|
{
|
|
"entropy": 6.346052122116089,
|
|
"epoch": 0.13732736821630034,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999601462166569,
|
|
"loss": 6.0973,
|
|
"mean_token_accuracy": 0.13112309873104094,
|
|
"num_tokens": 3063908.0,
|
|
"step": 1765
|
|
},
|
|
{
|
|
"entropy": 6.419245815277099,
|
|
"epoch": 0.1377163975880179,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999596228789736,
|
|
"loss": 6.1888,
|
|
"mean_token_accuracy": 0.12716860547661782,
|
|
"num_tokens": 3072077.0,
|
|
"step": 1770
|
|
},
|
|
{
|
|
"entropy": 6.381726551055908,
|
|
"epoch": 0.13810542695973546,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999590961278859,
|
|
"loss": 6.2046,
|
|
"mean_token_accuracy": 0.12799116969108582,
|
|
"num_tokens": 3080498.0,
|
|
"step": 1775
|
|
},
|
|
{
|
|
"entropy": 6.343014144897461,
|
|
"epoch": 0.13849445633145302,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999585659634021,
|
|
"loss": 6.1964,
|
|
"mean_token_accuracy": 0.13141690641641618,
|
|
"num_tokens": 3089055.0,
|
|
"step": 1780
|
|
},
|
|
{
|
|
"entropy": 6.376903533935547,
|
|
"epoch": 0.13888348570317058,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999580323855301,
|
|
"loss": 6.1916,
|
|
"mean_token_accuracy": 0.13284389600157737,
|
|
"num_tokens": 3096944.0,
|
|
"step": 1785
|
|
},
|
|
{
|
|
"entropy": 6.361277532577515,
|
|
"epoch": 0.13927251507488816,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999574953942781,
|
|
"loss": 6.0802,
|
|
"mean_token_accuracy": 0.13013918548822404,
|
|
"num_tokens": 3105596.0,
|
|
"step": 1790
|
|
},
|
|
{
|
|
"entropy": 6.29228663444519,
|
|
"epoch": 0.13966154444660572,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999569549896541,
|
|
"loss": 6.0716,
|
|
"mean_token_accuracy": 0.13826498091220857,
|
|
"num_tokens": 3114349.0,
|
|
"step": 1795
|
|
},
|
|
{
|
|
"entropy": 6.349193048477173,
|
|
"epoch": 0.14005057381832328,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999564111716665,
|
|
"loss": 6.1805,
|
|
"mean_token_accuracy": 0.12369971498847007,
|
|
"num_tokens": 3122490.0,
|
|
"step": 1800
|
|
},
|
|
{
|
|
"entropy": 6.439586353302002,
|
|
"epoch": 0.14043960319004084,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999558639403232,
|
|
"loss": 6.2334,
|
|
"mean_token_accuracy": 0.1289645791053772,
|
|
"num_tokens": 3130988.0,
|
|
"step": 1805
|
|
},
|
|
{
|
|
"entropy": 6.373170948028564,
|
|
"epoch": 0.1408286325617584,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999553132956328,
|
|
"loss": 6.0905,
|
|
"mean_token_accuracy": 0.12859657481312753,
|
|
"num_tokens": 3139488.0,
|
|
"step": 1810
|
|
},
|
|
{
|
|
"entropy": 6.31482195854187,
|
|
"epoch": 0.14121766193347599,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999547592376035,
|
|
"loss": 6.1537,
|
|
"mean_token_accuracy": 0.1342098221182823,
|
|
"num_tokens": 3147955.0,
|
|
"step": 1815
|
|
},
|
|
{
|
|
"entropy": 6.337986850738526,
|
|
"epoch": 0.14160669130519354,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004999542017662438,
|
|
"loss": 6.1884,
|
|
"mean_token_accuracy": 0.12379184886813163,
|
|
"num_tokens": 3157608.0,
|
|
"step": 1820
|
|
},
|
|
{
|
|
"entropy": 6.413020277023316,
|
|
"epoch": 0.1419957206769111,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004999536408815623,
|
|
"loss": 6.1462,
|
|
"mean_token_accuracy": 0.12497628033161164,
|
|
"num_tokens": 3166124.0,
|
|
"step": 1825
|
|
},
|
|
{
|
|
"entropy": 6.232908296585083,
|
|
"epoch": 0.14238475004862866,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999530765835672,
|
|
"loss": 6.1422,
|
|
"mean_token_accuracy": 0.12837766632437705,
|
|
"num_tokens": 3175069.0,
|
|
"step": 1830
|
|
},
|
|
{
|
|
"entropy": 6.412486600875854,
|
|
"epoch": 0.14277377942034625,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999525088722673,
|
|
"loss": 6.1759,
|
|
"mean_token_accuracy": 0.12886116057634353,
|
|
"num_tokens": 3184259.0,
|
|
"step": 1835
|
|
},
|
|
{
|
|
"entropy": 6.393767547607422,
|
|
"epoch": 0.1431628087920638,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999519377476711,
|
|
"loss": 6.0945,
|
|
"mean_token_accuracy": 0.12900736853480338,
|
|
"num_tokens": 3193015.0,
|
|
"step": 1840
|
|
},
|
|
{
|
|
"entropy": 6.337996959686279,
|
|
"epoch": 0.14355183816378136,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999513632097872,
|
|
"loss": 6.008,
|
|
"mean_token_accuracy": 0.13678519204258918,
|
|
"num_tokens": 3201624.0,
|
|
"step": 1845
|
|
},
|
|
{
|
|
"entropy": 6.311671876907349,
|
|
"epoch": 0.14394086753549892,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999507852586245,
|
|
"loss": 6.1439,
|
|
"mean_token_accuracy": 0.13350687846541404,
|
|
"num_tokens": 3209474.0,
|
|
"step": 1850
|
|
},
|
|
{
|
|
"entropy": 6.269514083862305,
|
|
"epoch": 0.14432989690721648,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999502038941917,
|
|
"loss": 6.1012,
|
|
"mean_token_accuracy": 0.1346833288669586,
|
|
"num_tokens": 3218550.0,
|
|
"step": 1855
|
|
},
|
|
{
|
|
"entropy": 6.209073257446289,
|
|
"epoch": 0.14471892627893407,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004999496191164975,
|
|
"loss": 6.0819,
|
|
"mean_token_accuracy": 0.13349551558494568,
|
|
"num_tokens": 3227108.0,
|
|
"step": 1860
|
|
},
|
|
{
|
|
"entropy": 6.3549457550048825,
|
|
"epoch": 0.14510795565065163,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000499949030925551,
|
|
"loss": 6.1167,
|
|
"mean_token_accuracy": 0.13430884554982186,
|
|
"num_tokens": 3235785.0,
|
|
"step": 1865
|
|
},
|
|
{
|
|
"entropy": 6.429311513900757,
|
|
"epoch": 0.14549698502236919,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999484393213609,
|
|
"loss": 6.1573,
|
|
"mean_token_accuracy": 0.12800115197896958,
|
|
"num_tokens": 3244180.0,
|
|
"step": 1870
|
|
},
|
|
{
|
|
"entropy": 6.257713270187378,
|
|
"epoch": 0.14588601439408674,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999478443039363,
|
|
"loss": 6.0194,
|
|
"mean_token_accuracy": 0.13384133577346802,
|
|
"num_tokens": 3253098.0,
|
|
"step": 1875
|
|
},
|
|
{
|
|
"entropy": 6.351937246322632,
|
|
"epoch": 0.14627504376580433,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999472458732862,
|
|
"loss": 6.0853,
|
|
"mean_token_accuracy": 0.13433253467082978,
|
|
"num_tokens": 3261726.0,
|
|
"step": 1880
|
|
},
|
|
{
|
|
"entropy": 6.313936185836792,
|
|
"epoch": 0.1466640731375219,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999466440294198,
|
|
"loss": 6.029,
|
|
"mean_token_accuracy": 0.13558507710695267,
|
|
"num_tokens": 3270362.0,
|
|
"step": 1885
|
|
},
|
|
{
|
|
"entropy": 6.235980558395386,
|
|
"epoch": 0.14705310250923945,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000499946038772346,
|
|
"loss": 6.0079,
|
|
"mean_token_accuracy": 0.13864972218871116,
|
|
"num_tokens": 3278332.0,
|
|
"step": 1890
|
|
},
|
|
{
|
|
"entropy": 6.265728330612182,
|
|
"epoch": 0.147442131880957,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999454301020741,
|
|
"loss": 6.0011,
|
|
"mean_token_accuracy": 0.13960243612527848,
|
|
"num_tokens": 3286800.0,
|
|
"step": 1895
|
|
},
|
|
{
|
|
"entropy": 6.382432699203491,
|
|
"epoch": 0.14783116125267456,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004999448180186133,
|
|
"loss": 6.2342,
|
|
"mean_token_accuracy": 0.1212337888777256,
|
|
"num_tokens": 3296186.0,
|
|
"step": 1900
|
|
},
|
|
{
|
|
"entropy": 6.223908090591431,
|
|
"epoch": 0.14822019062439215,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000499944202521973,
|
|
"loss": 6.0816,
|
|
"mean_token_accuracy": 0.13997681587934493,
|
|
"num_tokens": 3303973.0,
|
|
"step": 1905
|
|
},
|
|
{
|
|
"entropy": 6.313835668563843,
|
|
"epoch": 0.1486092199961097,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999435836121624,
|
|
"loss": 6.0389,
|
|
"mean_token_accuracy": 0.13727107942104338,
|
|
"num_tokens": 3312550.0,
|
|
"step": 1910
|
|
},
|
|
{
|
|
"entropy": 6.271665716171265,
|
|
"epoch": 0.14899824936782727,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000499942961289191,
|
|
"loss": 6.1037,
|
|
"mean_token_accuracy": 0.13144001960754395,
|
|
"num_tokens": 3321342.0,
|
|
"step": 1915
|
|
},
|
|
{
|
|
"entropy": 6.258928823471069,
|
|
"epoch": 0.14938727873954483,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999423355530683,
|
|
"loss": 5.9791,
|
|
"mean_token_accuracy": 0.14113496989011765,
|
|
"num_tokens": 3329293.0,
|
|
"step": 1920
|
|
},
|
|
{
|
|
"entropy": 6.167897891998291,
|
|
"epoch": 0.1497763081112624,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999417064038035,
|
|
"loss": 6.0517,
|
|
"mean_token_accuracy": 0.13005898594856263,
|
|
"num_tokens": 3338278.0,
|
|
"step": 1925
|
|
},
|
|
{
|
|
"entropy": 6.415949773788452,
|
|
"epoch": 0.15016533748297997,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999410738414065,
|
|
"loss": 6.1416,
|
|
"mean_token_accuracy": 0.13462255373597146,
|
|
"num_tokens": 3346757.0,
|
|
"step": 1930
|
|
},
|
|
{
|
|
"entropy": 6.1904011249542235,
|
|
"epoch": 0.15055436685469753,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999404378658866,
|
|
"loss": 6.1487,
|
|
"mean_token_accuracy": 0.12973785847425462,
|
|
"num_tokens": 3355903.0,
|
|
"step": 1935
|
|
},
|
|
{
|
|
"entropy": 6.28576431274414,
|
|
"epoch": 0.1509433962264151,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999397984772536,
|
|
"loss": 6.1226,
|
|
"mean_token_accuracy": 0.12523171529173852,
|
|
"num_tokens": 3365440.0,
|
|
"step": 1940
|
|
},
|
|
{
|
|
"entropy": 6.344992446899414,
|
|
"epoch": 0.15133242559813265,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999391556755172,
|
|
"loss": 6.0897,
|
|
"mean_token_accuracy": 0.1339936561882496,
|
|
"num_tokens": 3373672.0,
|
|
"step": 1945
|
|
},
|
|
{
|
|
"entropy": 6.230864191055298,
|
|
"epoch": 0.15172145496985023,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999385094606872,
|
|
"loss": 6.0443,
|
|
"mean_token_accuracy": 0.12970422506332396,
|
|
"num_tokens": 3382733.0,
|
|
"step": 1950
|
|
},
|
|
{
|
|
"entropy": 6.247889184951783,
|
|
"epoch": 0.1521104843415678,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004999378598327733,
|
|
"loss": 6.0138,
|
|
"mean_token_accuracy": 0.13647327050566674,
|
|
"num_tokens": 3390842.0,
|
|
"step": 1955
|
|
},
|
|
{
|
|
"entropy": 6.245198822021484,
|
|
"epoch": 0.15249951371328535,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999372067917854,
|
|
"loss": 6.1716,
|
|
"mean_token_accuracy": 0.12445822656154633,
|
|
"num_tokens": 3399761.0,
|
|
"step": 1960
|
|
},
|
|
{
|
|
"entropy": 6.363856220245362,
|
|
"epoch": 0.1528885430850029,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999365503377335,
|
|
"loss": 6.0931,
|
|
"mean_token_accuracy": 0.13199654519557952,
|
|
"num_tokens": 3408986.0,
|
|
"step": 1965
|
|
},
|
|
{
|
|
"entropy": 6.2719300270080565,
|
|
"epoch": 0.1532775724567205,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999358904706273,
|
|
"loss": 6.0483,
|
|
"mean_token_accuracy": 0.12709831818938255,
|
|
"num_tokens": 3418051.0,
|
|
"step": 1970
|
|
},
|
|
{
|
|
"entropy": 6.36472110748291,
|
|
"epoch": 0.15366660182843805,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999352271904771,
|
|
"loss": 6.1339,
|
|
"mean_token_accuracy": 0.13131385445594787,
|
|
"num_tokens": 3427185.0,
|
|
"step": 1975
|
|
},
|
|
{
|
|
"entropy": 6.233695363998413,
|
|
"epoch": 0.1540556312001556,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999345604972928,
|
|
"loss": 6.052,
|
|
"mean_token_accuracy": 0.1370918095111847,
|
|
"num_tokens": 3435367.0,
|
|
"step": 1980
|
|
},
|
|
{
|
|
"entropy": 6.231957864761353,
|
|
"epoch": 0.15444466057187317,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999338903910846,
|
|
"loss": 6.0959,
|
|
"mean_token_accuracy": 0.12951285988092423,
|
|
"num_tokens": 3443451.0,
|
|
"step": 1985
|
|
},
|
|
{
|
|
"entropy": 6.352871370315552,
|
|
"epoch": 0.15483368994359073,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999332168718626,
|
|
"loss": 6.0936,
|
|
"mean_token_accuracy": 0.13427893146872522,
|
|
"num_tokens": 3451038.0,
|
|
"step": 1990
|
|
},
|
|
{
|
|
"entropy": 6.450736808776855,
|
|
"epoch": 0.15522271931530832,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999325399396371,
|
|
"loss": 6.237,
|
|
"mean_token_accuracy": 0.11902682781219483,
|
|
"num_tokens": 3459693.0,
|
|
"step": 1995
|
|
},
|
|
{
|
|
"entropy": 6.391193008422851,
|
|
"epoch": 0.15561174868702587,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999318595944183,
|
|
"loss": 6.1066,
|
|
"mean_token_accuracy": 0.13078132271766663,
|
|
"num_tokens": 3468347.0,
|
|
"step": 2000
|
|
},
|
|
{
|
|
"entropy": 6.26676607131958,
|
|
"epoch": 0.15600077805874343,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999311758362166,
|
|
"loss": 6.0951,
|
|
"mean_token_accuracy": 0.1329476974904537,
|
|
"num_tokens": 3476030.0,
|
|
"step": 2005
|
|
},
|
|
{
|
|
"entropy": 6.2150873184204105,
|
|
"epoch": 0.156389807430461,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999304886650422,
|
|
"loss": 6.0683,
|
|
"mean_token_accuracy": 0.13065901920199394,
|
|
"num_tokens": 3484840.0,
|
|
"step": 2010
|
|
},
|
|
{
|
|
"entropy": 6.414690160751343,
|
|
"epoch": 0.15677883680217858,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999297980809058,
|
|
"loss": 6.1512,
|
|
"mean_token_accuracy": 0.13070376738905906,
|
|
"num_tokens": 3492662.0,
|
|
"step": 2015
|
|
},
|
|
{
|
|
"entropy": 6.281697416305542,
|
|
"epoch": 0.15716786617389614,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999291040838176,
|
|
"loss": 6.0634,
|
|
"mean_token_accuracy": 0.1307703360915184,
|
|
"num_tokens": 3501582.0,
|
|
"step": 2020
|
|
},
|
|
{
|
|
"entropy": 6.290822887420655,
|
|
"epoch": 0.1575568955456137,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999284066737884,
|
|
"loss": 6.0747,
|
|
"mean_token_accuracy": 0.1364296093583107,
|
|
"num_tokens": 3510141.0,
|
|
"step": 2025
|
|
},
|
|
{
|
|
"entropy": 6.335365724563599,
|
|
"epoch": 0.15794592491733125,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999277058508285,
|
|
"loss": 6.0953,
|
|
"mean_token_accuracy": 0.1390254333615303,
|
|
"num_tokens": 3518530.0,
|
|
"step": 2030
|
|
},
|
|
{
|
|
"entropy": 6.226547431945801,
|
|
"epoch": 0.1583349542890488,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999270016149486,
|
|
"loss": 6.0586,
|
|
"mean_token_accuracy": 0.13643356561660766,
|
|
"num_tokens": 3526815.0,
|
|
"step": 2035
|
|
},
|
|
{
|
|
"entropy": 6.253783798217773,
|
|
"epoch": 0.1587239836607664,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004999262939661596,
|
|
"loss": 6.1464,
|
|
"mean_token_accuracy": 0.12736352086067199,
|
|
"num_tokens": 3535840.0,
|
|
"step": 2040
|
|
},
|
|
{
|
|
"entropy": 6.341825342178344,
|
|
"epoch": 0.15911301303248396,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999255829044721,
|
|
"loss": 6.1546,
|
|
"mean_token_accuracy": 0.12908357754349709,
|
|
"num_tokens": 3544876.0,
|
|
"step": 2045
|
|
},
|
|
{
|
|
"entropy": 6.260779571533203,
|
|
"epoch": 0.15950204240420152,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999248684298968,
|
|
"loss": 5.9056,
|
|
"mean_token_accuracy": 0.13816021084785463,
|
|
"num_tokens": 3553018.0,
|
|
"step": 2050
|
|
},
|
|
{
|
|
"entropy": 6.160889387130737,
|
|
"epoch": 0.15989107177591907,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999241505424447,
|
|
"loss": 5.922,
|
|
"mean_token_accuracy": 0.14369428977370263,
|
|
"num_tokens": 3560909.0,
|
|
"step": 2055
|
|
},
|
|
{
|
|
"entropy": 6.215629625320434,
|
|
"epoch": 0.16028010114763663,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999234292421265,
|
|
"loss": 6.102,
|
|
"mean_token_accuracy": 0.1345704235136509,
|
|
"num_tokens": 3569235.0,
|
|
"step": 2060
|
|
},
|
|
{
|
|
"entropy": 6.185765171051026,
|
|
"epoch": 0.16066913051935422,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999227045289535,
|
|
"loss": 5.9789,
|
|
"mean_token_accuracy": 0.13773323893547057,
|
|
"num_tokens": 3577646.0,
|
|
"step": 2065
|
|
},
|
|
{
|
|
"entropy": 6.169071960449219,
|
|
"epoch": 0.16105815989107178,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999219764029363,
|
|
"loss": 6.0667,
|
|
"mean_token_accuracy": 0.13329384997487068,
|
|
"num_tokens": 3586499.0,
|
|
"step": 2070
|
|
},
|
|
{
|
|
"entropy": 6.297885990142822,
|
|
"epoch": 0.16144718926278934,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999212448640861,
|
|
"loss": 6.0712,
|
|
"mean_token_accuracy": 0.13483210131525994,
|
|
"num_tokens": 3595391.0,
|
|
"step": 2075
|
|
},
|
|
{
|
|
"entropy": 6.178416395187378,
|
|
"epoch": 0.1618362186345069,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004999205099124141,
|
|
"loss": 6.0075,
|
|
"mean_token_accuracy": 0.13845352903008462,
|
|
"num_tokens": 3603774.0,
|
|
"step": 2080
|
|
},
|
|
{
|
|
"entropy": 6.350871467590332,
|
|
"epoch": 0.16222524800622448,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999197715479313,
|
|
"loss": 6.0964,
|
|
"mean_token_accuracy": 0.13378985598683357,
|
|
"num_tokens": 3611980.0,
|
|
"step": 2085
|
|
},
|
|
{
|
|
"entropy": 6.227251195907593,
|
|
"epoch": 0.16261427737794204,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999190297706489,
|
|
"loss": 5.9931,
|
|
"mean_token_accuracy": 0.1362592376768589,
|
|
"num_tokens": 3620902.0,
|
|
"step": 2090
|
|
},
|
|
{
|
|
"entropy": 6.393834447860717,
|
|
"epoch": 0.1630033067496596,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999182845805783,
|
|
"loss": 6.274,
|
|
"mean_token_accuracy": 0.12474248632788658,
|
|
"num_tokens": 3628924.0,
|
|
"step": 2095
|
|
},
|
|
{
|
|
"entropy": 6.317929124832153,
|
|
"epoch": 0.16339233612137716,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999175359777306,
|
|
"loss": 6.1134,
|
|
"mean_token_accuracy": 0.13460347801446915,
|
|
"num_tokens": 3637538.0,
|
|
"step": 2100
|
|
},
|
|
{
|
|
"entropy": 6.309267282485962,
|
|
"epoch": 0.16378136549309472,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999167839621174,
|
|
"loss": 6.1316,
|
|
"mean_token_accuracy": 0.12891944050788878,
|
|
"num_tokens": 3646309.0,
|
|
"step": 2105
|
|
},
|
|
{
|
|
"entropy": 6.248872947692871,
|
|
"epoch": 0.1641703948648123,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999160285337501,
|
|
"loss": 5.9786,
|
|
"mean_token_accuracy": 0.13321250006556512,
|
|
"num_tokens": 3655204.0,
|
|
"step": 2110
|
|
},
|
|
{
|
|
"entropy": 6.269497966766357,
|
|
"epoch": 0.16455942423652986,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999152696926399,
|
|
"loss": 6.1226,
|
|
"mean_token_accuracy": 0.13018277511000634,
|
|
"num_tokens": 3663939.0,
|
|
"step": 2115
|
|
},
|
|
{
|
|
"entropy": 6.290651512145996,
|
|
"epoch": 0.16494845360824742,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004999145074387985,
|
|
"loss": 6.0531,
|
|
"mean_token_accuracy": 0.1347106009721756,
|
|
"num_tokens": 3673167.0,
|
|
"step": 2120
|
|
},
|
|
{
|
|
"entropy": 6.206559896469116,
|
|
"epoch": 0.16533748297996498,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999137417722374,
|
|
"loss": 6.0324,
|
|
"mean_token_accuracy": 0.13312025964260102,
|
|
"num_tokens": 3682234.0,
|
|
"step": 2125
|
|
},
|
|
{
|
|
"entropy": 6.218487071990967,
|
|
"epoch": 0.16572651235168256,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999129726929684,
|
|
"loss": 5.9961,
|
|
"mean_token_accuracy": 0.13849076852202416,
|
|
"num_tokens": 3690835.0,
|
|
"step": 2130
|
|
},
|
|
{
|
|
"entropy": 6.239537239074707,
|
|
"epoch": 0.16611554172340012,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999122002010029,
|
|
"loss": 6.0597,
|
|
"mean_token_accuracy": 0.1327889084815979,
|
|
"num_tokens": 3699348.0,
|
|
"step": 2135
|
|
},
|
|
{
|
|
"entropy": 6.185144138336182,
|
|
"epoch": 0.16650457109511768,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999114242963527,
|
|
"loss": 5.9676,
|
|
"mean_token_accuracy": 0.13893314003944396,
|
|
"num_tokens": 3708205.0,
|
|
"step": 2140
|
|
},
|
|
{
|
|
"entropy": 6.18302903175354,
|
|
"epoch": 0.16689360046683524,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999106449790298,
|
|
"loss": 6.0267,
|
|
"mean_token_accuracy": 0.13680716902017592,
|
|
"num_tokens": 3717016.0,
|
|
"step": 2145
|
|
},
|
|
{
|
|
"entropy": 6.388441848754883,
|
|
"epoch": 0.1672826298385528,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999098622490458,
|
|
"loss": 6.0472,
|
|
"mean_token_accuracy": 0.13382177725434302,
|
|
"num_tokens": 3725509.0,
|
|
"step": 2150
|
|
},
|
|
{
|
|
"entropy": 6.247507572174072,
|
|
"epoch": 0.16767165921027039,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999090761064125,
|
|
"loss": 6.1223,
|
|
"mean_token_accuracy": 0.132233477383852,
|
|
"num_tokens": 3734674.0,
|
|
"step": 2155
|
|
},
|
|
{
|
|
"entropy": 6.184755468368531,
|
|
"epoch": 0.16806068858198794,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000499908286551142,
|
|
"loss": 5.9467,
|
|
"mean_token_accuracy": 0.14066505506634713,
|
|
"num_tokens": 3742930.0,
|
|
"step": 2160
|
|
},
|
|
{
|
|
"entropy": 6.189033365249633,
|
|
"epoch": 0.1684497179537055,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999074935832463,
|
|
"loss": 6.0435,
|
|
"mean_token_accuracy": 0.1365055151283741,
|
|
"num_tokens": 3751314.0,
|
|
"step": 2165
|
|
},
|
|
{
|
|
"entropy": 6.396620225906372,
|
|
"epoch": 0.16883874732542306,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999066972027373,
|
|
"loss": 6.1547,
|
|
"mean_token_accuracy": 0.13123885914683342,
|
|
"num_tokens": 3760229.0,
|
|
"step": 2170
|
|
},
|
|
{
|
|
"entropy": 6.372897815704346,
|
|
"epoch": 0.16922777669714065,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999058974096271,
|
|
"loss": 6.1526,
|
|
"mean_token_accuracy": 0.12955897599458693,
|
|
"num_tokens": 3769037.0,
|
|
"step": 2175
|
|
},
|
|
{
|
|
"entropy": 6.131582260131836,
|
|
"epoch": 0.1696168060688582,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000499905094203928,
|
|
"loss": 6.023,
|
|
"mean_token_accuracy": 0.13808971717953683,
|
|
"num_tokens": 3777686.0,
|
|
"step": 2180
|
|
},
|
|
{
|
|
"entropy": 6.375473928451538,
|
|
"epoch": 0.17000583544057576,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000499904287585652,
|
|
"loss": 6.1105,
|
|
"mean_token_accuracy": 0.12939185723662378,
|
|
"num_tokens": 3786412.0,
|
|
"step": 2185
|
|
},
|
|
{
|
|
"entropy": 6.248593330383301,
|
|
"epoch": 0.17039486481229332,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999034775548113,
|
|
"loss": 6.1397,
|
|
"mean_token_accuracy": 0.13407278731465339,
|
|
"num_tokens": 3794981.0,
|
|
"step": 2190
|
|
},
|
|
{
|
|
"entropy": 6.278722524642944,
|
|
"epoch": 0.17078389418401088,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999026641114185,
|
|
"loss": 6.0252,
|
|
"mean_token_accuracy": 0.13181823194026948,
|
|
"num_tokens": 3803069.0,
|
|
"step": 2195
|
|
},
|
|
{
|
|
"entropy": 6.28540301322937,
|
|
"epoch": 0.17117292355572847,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999018472554857,
|
|
"loss": 6.1039,
|
|
"mean_token_accuracy": 0.1345643788576126,
|
|
"num_tokens": 3811986.0,
|
|
"step": 2200
|
|
},
|
|
{
|
|
"entropy": 6.29768214225769,
|
|
"epoch": 0.17156195292744603,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999010269870253,
|
|
"loss": 6.0161,
|
|
"mean_token_accuracy": 0.13579363152384757,
|
|
"num_tokens": 3820626.0,
|
|
"step": 2205
|
|
},
|
|
{
|
|
"entropy": 6.200810480117798,
|
|
"epoch": 0.17195098229916359,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999002033060498,
|
|
"loss": 6.0268,
|
|
"mean_token_accuracy": 0.13920362591743468,
|
|
"num_tokens": 3828608.0,
|
|
"step": 2210
|
|
},
|
|
{
|
|
"entropy": 6.193022918701172,
|
|
"epoch": 0.17234001167088114,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004998993762125716,
|
|
"loss": 5.9785,
|
|
"mean_token_accuracy": 0.13870956525206565,
|
|
"num_tokens": 3837059.0,
|
|
"step": 2215
|
|
},
|
|
{
|
|
"entropy": 6.207073402404785,
|
|
"epoch": 0.17272904104259873,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004998985457066034,
|
|
"loss": 5.9823,
|
|
"mean_token_accuracy": 0.1358140230178833,
|
|
"num_tokens": 3845137.0,
|
|
"step": 2220
|
|
},
|
|
{
|
|
"entropy": 6.209107160568237,
|
|
"epoch": 0.1731180704143163,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998977117881576,
|
|
"loss": 5.9817,
|
|
"mean_token_accuracy": 0.14150308892130853,
|
|
"num_tokens": 3854012.0,
|
|
"step": 2225
|
|
},
|
|
{
|
|
"entropy": 6.067155075073242,
|
|
"epoch": 0.17350709978603385,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998968744572472,
|
|
"loss": 5.9361,
|
|
"mean_token_accuracy": 0.14006831347942353,
|
|
"num_tokens": 3862308.0,
|
|
"step": 2230
|
|
},
|
|
{
|
|
"entropy": 6.171311616897583,
|
|
"epoch": 0.1738961291577514,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004998960337138845,
|
|
"loss": 5.8703,
|
|
"mean_token_accuracy": 0.13672190457582473,
|
|
"num_tokens": 3870975.0,
|
|
"step": 2235
|
|
},
|
|
{
|
|
"entropy": 6.223893642425537,
|
|
"epoch": 0.17428515852946896,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998951895580826,
|
|
"loss": 6.031,
|
|
"mean_token_accuracy": 0.13869215548038483,
|
|
"num_tokens": 3879621.0,
|
|
"step": 2240
|
|
},
|
|
{
|
|
"entropy": 6.188286018371582,
|
|
"epoch": 0.17467418790118655,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004998943419898542,
|
|
"loss": 6.0074,
|
|
"mean_token_accuracy": 0.1369040384888649,
|
|
"num_tokens": 3889214.0,
|
|
"step": 2245
|
|
},
|
|
{
|
|
"entropy": 6.221569967269898,
|
|
"epoch": 0.1750632172729041,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004998934910092119,
|
|
"loss": 6.0449,
|
|
"mean_token_accuracy": 0.13841852992773057,
|
|
"num_tokens": 3898250.0,
|
|
"step": 2250
|
|
},
|
|
{
|
|
"entropy": 6.1772825717926025,
|
|
"epoch": 0.17545224664462167,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004998926366161689,
|
|
"loss": 6.0791,
|
|
"mean_token_accuracy": 0.1358688361942768,
|
|
"num_tokens": 3906971.0,
|
|
"step": 2255
|
|
},
|
|
{
|
|
"entropy": 6.292248201370239,
|
|
"epoch": 0.17584127601633923,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004998917788107383,
|
|
"loss": 6.1077,
|
|
"mean_token_accuracy": 0.13412976861000062,
|
|
"num_tokens": 3916663.0,
|
|
"step": 2260
|
|
},
|
|
{
|
|
"entropy": 6.169425630569458,
|
|
"epoch": 0.17623030538805678,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004998909175929326,
|
|
"loss": 5.9801,
|
|
"mean_token_accuracy": 0.13465463891625404,
|
|
"num_tokens": 3926848.0,
|
|
"step": 2265
|
|
},
|
|
{
|
|
"entropy": 6.196387386322021,
|
|
"epoch": 0.17661933475977437,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998900529627653,
|
|
"loss": 5.9622,
|
|
"mean_token_accuracy": 0.13440250605344772,
|
|
"num_tokens": 3935729.0,
|
|
"step": 2270
|
|
},
|
|
{
|
|
"entropy": 6.222635746002197,
|
|
"epoch": 0.17700836413149193,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998891849202495,
|
|
"loss": 5.9687,
|
|
"mean_token_accuracy": 0.1374209851026535,
|
|
"num_tokens": 3943408.0,
|
|
"step": 2275
|
|
},
|
|
{
|
|
"entropy": 6.188998603820801,
|
|
"epoch": 0.1773973935032095,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000499888313465398,
|
|
"loss": 5.9327,
|
|
"mean_token_accuracy": 0.1366911180317402,
|
|
"num_tokens": 3952473.0,
|
|
"step": 2280
|
|
},
|
|
{
|
|
"entropy": 6.274978828430176,
|
|
"epoch": 0.17778642287492705,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998874385982247,
|
|
"loss": 6.1128,
|
|
"mean_token_accuracy": 0.1279517851769924,
|
|
"num_tokens": 3960878.0,
|
|
"step": 2285
|
|
},
|
|
{
|
|
"entropy": 6.270401048660278,
|
|
"epoch": 0.17817545224664463,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998865603187421,
|
|
"loss": 6.0625,
|
|
"mean_token_accuracy": 0.13058168217539787,
|
|
"num_tokens": 3969282.0,
|
|
"step": 2290
|
|
},
|
|
{
|
|
"entropy": 6.220210218429566,
|
|
"epoch": 0.1785644816183622,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000499885678626964,
|
|
"loss": 6.014,
|
|
"mean_token_accuracy": 0.13722910657525061,
|
|
"num_tokens": 3978516.0,
|
|
"step": 2295
|
|
},
|
|
{
|
|
"entropy": 6.137257432937622,
|
|
"epoch": 0.17895351099007975,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998847935229038,
|
|
"loss": 5.8965,
|
|
"mean_token_accuracy": 0.1428119085729122,
|
|
"num_tokens": 3986580.0,
|
|
"step": 2300
|
|
},
|
|
{
|
|
"entropy": 6.080727529525757,
|
|
"epoch": 0.1793425403617973,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998839050065746,
|
|
"loss": 5.8953,
|
|
"mean_token_accuracy": 0.14140310510993004,
|
|
"num_tokens": 3995144.0,
|
|
"step": 2305
|
|
},
|
|
{
|
|
"entropy": 6.176934671401978,
|
|
"epoch": 0.17973156973351487,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004998830130779902,
|
|
"loss": 5.8921,
|
|
"mean_token_accuracy": 0.1366891786456108,
|
|
"num_tokens": 4003887.0,
|
|
"step": 2310
|
|
},
|
|
{
|
|
"entropy": 6.2093428611755375,
|
|
"epoch": 0.18012059910523245,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000499882117737164,
|
|
"loss": 6.0162,
|
|
"mean_token_accuracy": 0.13656655922532082,
|
|
"num_tokens": 4012607.0,
|
|
"step": 2315
|
|
},
|
|
{
|
|
"entropy": 6.150680923461914,
|
|
"epoch": 0.18050962847695,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004998812189841096,
|
|
"loss": 6.081,
|
|
"mean_token_accuracy": 0.13370702415704727,
|
|
"num_tokens": 4021950.0,
|
|
"step": 2320
|
|
},
|
|
{
|
|
"entropy": 6.2497515201568605,
|
|
"epoch": 0.18089865784866757,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004998803168188407,
|
|
"loss": 6.0404,
|
|
"mean_token_accuracy": 0.13844593837857247,
|
|
"num_tokens": 4031076.0,
|
|
"step": 2325
|
|
},
|
|
{
|
|
"entropy": 6.116616344451904,
|
|
"epoch": 0.18128768722038513,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004998794112413708,
|
|
"loss": 5.8958,
|
|
"mean_token_accuracy": 0.1410272441804409,
|
|
"num_tokens": 4040414.0,
|
|
"step": 2330
|
|
},
|
|
{
|
|
"entropy": 6.26803183555603,
|
|
"epoch": 0.18167671659210272,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998785022517137,
|
|
"loss": 5.9815,
|
|
"mean_token_accuracy": 0.14090483263134956,
|
|
"num_tokens": 4048931.0,
|
|
"step": 2335
|
|
},
|
|
{
|
|
"entropy": 6.045533609390259,
|
|
"epoch": 0.18206574596382027,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004998775898498835,
|
|
"loss": 5.8712,
|
|
"mean_token_accuracy": 0.14119707196950912,
|
|
"num_tokens": 4057688.0,
|
|
"step": 2340
|
|
},
|
|
{
|
|
"entropy": 6.100311326980591,
|
|
"epoch": 0.18245477533553783,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998766740358936,
|
|
"loss": 5.9949,
|
|
"mean_token_accuracy": 0.13843753784894944,
|
|
"num_tokens": 4066365.0,
|
|
"step": 2345
|
|
},
|
|
{
|
|
"entropy": 6.204766511917114,
|
|
"epoch": 0.1828438047072554,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004998757548097582,
|
|
"loss": 5.8852,
|
|
"mean_token_accuracy": 0.14553529024124146,
|
|
"num_tokens": 4075136.0,
|
|
"step": 2350
|
|
},
|
|
{
|
|
"entropy": 6.189942455291748,
|
|
"epoch": 0.18323283407897295,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004998748321714911,
|
|
"loss": 5.9877,
|
|
"mean_token_accuracy": 0.13881198838353156,
|
|
"num_tokens": 4083337.0,
|
|
"step": 2355
|
|
},
|
|
{
|
|
"entropy": 6.132948780059815,
|
|
"epoch": 0.18362186345069054,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998739061211065,
|
|
"loss": 5.9454,
|
|
"mean_token_accuracy": 0.14238794520497322,
|
|
"num_tokens": 4091201.0,
|
|
"step": 2360
|
|
},
|
|
{
|
|
"entropy": 6.194742584228516,
|
|
"epoch": 0.1840108928224081,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004998729766586181,
|
|
"loss": 6.018,
|
|
"mean_token_accuracy": 0.13472261428833007,
|
|
"num_tokens": 4099480.0,
|
|
"step": 2365
|
|
},
|
|
{
|
|
"entropy": 6.089618396759033,
|
|
"epoch": 0.18439992219412565,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004998720437840403,
|
|
"loss": 5.9125,
|
|
"mean_token_accuracy": 0.14144392758607865,
|
|
"num_tokens": 4108151.0,
|
|
"step": 2370
|
|
},
|
|
{
|
|
"entropy": 6.022348308563233,
|
|
"epoch": 0.1847889515658432,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004998711074973871,
|
|
"loss": 5.9047,
|
|
"mean_token_accuracy": 0.13933733105659485,
|
|
"num_tokens": 4117380.0,
|
|
"step": 2375
|
|
},
|
|
{
|
|
"entropy": 6.1961781024932865,
|
|
"epoch": 0.1851779809375608,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004998701677986728,
|
|
"loss": 5.9593,
|
|
"mean_token_accuracy": 0.14379323944449424,
|
|
"num_tokens": 4126757.0,
|
|
"step": 2380
|
|
},
|
|
{
|
|
"entropy": 6.117034149169922,
|
|
"epoch": 0.18556701030927836,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004998692246879116,
|
|
"loss": 5.8844,
|
|
"mean_token_accuracy": 0.13709820285439492,
|
|
"num_tokens": 4135326.0,
|
|
"step": 2385
|
|
},
|
|
{
|
|
"entropy": 6.139100790023804,
|
|
"epoch": 0.18595603968099592,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004998682781651178,
|
|
"loss": 5.9112,
|
|
"mean_token_accuracy": 0.14516514390707017,
|
|
"num_tokens": 4143624.0,
|
|
"step": 2390
|
|
},
|
|
{
|
|
"entropy": 6.090607690811157,
|
|
"epoch": 0.18634506905271347,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004998673282303059,
|
|
"loss": 5.851,
|
|
"mean_token_accuracy": 0.14274040311574937,
|
|
"num_tokens": 4152193.0,
|
|
"step": 2395
|
|
},
|
|
{
|
|
"entropy": 6.108787965774536,
|
|
"epoch": 0.18673409842443103,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998663748834901,
|
|
"loss": 5.9906,
|
|
"mean_token_accuracy": 0.1388832874596119,
|
|
"num_tokens": 4160614.0,
|
|
"step": 2400
|
|
},
|
|
{
|
|
"entropy": 6.251668167114258,
|
|
"epoch": 0.18712312779614862,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004998654181246851,
|
|
"loss": 5.9976,
|
|
"mean_token_accuracy": 0.14036377519369125,
|
|
"num_tokens": 4168715.0,
|
|
"step": 2405
|
|
},
|
|
{
|
|
"entropy": 6.176876354217529,
|
|
"epoch": 0.18751215716786618,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004998644579539052,
|
|
"loss": 6.0395,
|
|
"mean_token_accuracy": 0.14050538837909698,
|
|
"num_tokens": 4176676.0,
|
|
"step": 2410
|
|
},
|
|
{
|
|
"entropy": 6.176787853240967,
|
|
"epoch": 0.18790118653958374,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000499863494371165,
|
|
"loss": 6.0212,
|
|
"mean_token_accuracy": 0.13556102365255357,
|
|
"num_tokens": 4185613.0,
|
|
"step": 2415
|
|
},
|
|
{
|
|
"entropy": 6.17087230682373,
|
|
"epoch": 0.1882902159113013,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998625273764793,
|
|
"loss": 6.0086,
|
|
"mean_token_accuracy": 0.14141924679279327,
|
|
"num_tokens": 4193985.0,
|
|
"step": 2420
|
|
},
|
|
{
|
|
"entropy": 6.127655124664306,
|
|
"epoch": 0.18867924528301888,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004998615569698626,
|
|
"loss": 5.9067,
|
|
"mean_token_accuracy": 0.1402697630226612,
|
|
"num_tokens": 4202713.0,
|
|
"step": 2425
|
|
},
|
|
{
|
|
"entropy": 6.265314626693725,
|
|
"epoch": 0.18906827465473644,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004998605831513296,
|
|
"loss": 6.0448,
|
|
"mean_token_accuracy": 0.13398367688059806,
|
|
"num_tokens": 4210858.0,
|
|
"step": 2430
|
|
},
|
|
{
|
|
"entropy": 6.098290967941284,
|
|
"epoch": 0.189457304026454,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004998596059208953,
|
|
"loss": 5.9564,
|
|
"mean_token_accuracy": 0.14138128459453583,
|
|
"num_tokens": 4219570.0,
|
|
"step": 2435
|
|
},
|
|
{
|
|
"entropy": 6.1270262718200685,
|
|
"epoch": 0.18984633339817156,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998586252785743,
|
|
"loss": 5.8816,
|
|
"mean_token_accuracy": 0.14256712123751641,
|
|
"num_tokens": 4228026.0,
|
|
"step": 2440
|
|
},
|
|
{
|
|
"entropy": 6.123672199249268,
|
|
"epoch": 0.19023536276988912,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998576412243816,
|
|
"loss": 5.8953,
|
|
"mean_token_accuracy": 0.1403258338570595,
|
|
"num_tokens": 4235993.0,
|
|
"step": 2445
|
|
},
|
|
{
|
|
"entropy": 6.104493427276611,
|
|
"epoch": 0.1906243921416067,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998566537583321,
|
|
"loss": 5.8981,
|
|
"mean_token_accuracy": 0.14673311710357667,
|
|
"num_tokens": 4244225.0,
|
|
"step": 2450
|
|
},
|
|
{
|
|
"entropy": 6.084668493270874,
|
|
"epoch": 0.19101342151332426,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998556628804408,
|
|
"loss": 5.8763,
|
|
"mean_token_accuracy": 0.14110946282744408,
|
|
"num_tokens": 4252989.0,
|
|
"step": 2455
|
|
},
|
|
{
|
|
"entropy": 6.1425386428833,
|
|
"epoch": 0.19140245088504182,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998546685907225,
|
|
"loss": 5.917,
|
|
"mean_token_accuracy": 0.14222090542316437,
|
|
"num_tokens": 4261297.0,
|
|
"step": 2460
|
|
},
|
|
{
|
|
"entropy": 6.189026689529419,
|
|
"epoch": 0.19179148025675938,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004998536708891927,
|
|
"loss": 6.0593,
|
|
"mean_token_accuracy": 0.13440425619482993,
|
|
"num_tokens": 4270299.0,
|
|
"step": 2465
|
|
},
|
|
{
|
|
"entropy": 6.250662851333618,
|
|
"epoch": 0.19218050962847694,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004998526697758663,
|
|
"loss": 6.0489,
|
|
"mean_token_accuracy": 0.13370652571320535,
|
|
"num_tokens": 4279662.0,
|
|
"step": 2470
|
|
},
|
|
{
|
|
"entropy": 6.1341468334198,
|
|
"epoch": 0.19256953900019452,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004998516652507585,
|
|
"loss": 5.8811,
|
|
"mean_token_accuracy": 0.14475788101553916,
|
|
"num_tokens": 4287876.0,
|
|
"step": 2475
|
|
},
|
|
{
|
|
"entropy": 6.139857435226441,
|
|
"epoch": 0.19295856837191208,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004998506573138846,
|
|
"loss": 6.0032,
|
|
"mean_token_accuracy": 0.14181941896677017,
|
|
"num_tokens": 4296415.0,
|
|
"step": 2480
|
|
},
|
|
{
|
|
"entropy": 6.04846830368042,
|
|
"epoch": 0.19334759774362964,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004998496459652598,
|
|
"loss": 5.8458,
|
|
"mean_token_accuracy": 0.14211475402116774,
|
|
"num_tokens": 4304434.0,
|
|
"step": 2485
|
|
},
|
|
{
|
|
"entropy": 6.2117273807525635,
|
|
"epoch": 0.1937366271153472,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998486312048995,
|
|
"loss": 6.0062,
|
|
"mean_token_accuracy": 0.13499248623847962,
|
|
"num_tokens": 4313266.0,
|
|
"step": 2490
|
|
},
|
|
{
|
|
"entropy": 6.064237928390503,
|
|
"epoch": 0.19412565648706478,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004998476130328193,
|
|
"loss": 5.8892,
|
|
"mean_token_accuracy": 0.14858543127775192,
|
|
"num_tokens": 4322121.0,
|
|
"step": 2495
|
|
},
|
|
{
|
|
"entropy": 6.075144720077515,
|
|
"epoch": 0.19451468585878234,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998465914490343,
|
|
"loss": 5.9025,
|
|
"mean_token_accuracy": 0.14101851657032966,
|
|
"num_tokens": 4330596.0,
|
|
"step": 2500
|
|
},
|
|
{
|
|
"entropy": 6.195386219024658,
|
|
"epoch": 0.1949037152304999,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00049984556645356,
|
|
"loss": 6.0081,
|
|
"mean_token_accuracy": 0.14117387384176255,
|
|
"num_tokens": 4337779.0,
|
|
"step": 2505
|
|
},
|
|
{
|
|
"entropy": 6.147725248336792,
|
|
"epoch": 0.19529274460221746,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004998445380464124,
|
|
"loss": 5.8344,
|
|
"mean_token_accuracy": 0.14705330207943917,
|
|
"num_tokens": 4346623.0,
|
|
"step": 2510
|
|
},
|
|
{
|
|
"entropy": 6.002147150039673,
|
|
"epoch": 0.19568177397393502,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998435062276066,
|
|
"loss": 5.9455,
|
|
"mean_token_accuracy": 0.13899349197745323,
|
|
"num_tokens": 4355435.0,
|
|
"step": 2515
|
|
},
|
|
{
|
|
"entropy": 6.251942825317383,
|
|
"epoch": 0.1960708033456526,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004998424709971586,
|
|
"loss": 5.9863,
|
|
"mean_token_accuracy": 0.14054905995726585,
|
|
"num_tokens": 4363636.0,
|
|
"step": 2520
|
|
},
|
|
{
|
|
"entropy": 6.0051055431365965,
|
|
"epoch": 0.19645983271737016,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004998414323550839,
|
|
"loss": 5.8011,
|
|
"mean_token_accuracy": 0.1456178233027458,
|
|
"num_tokens": 4372337.0,
|
|
"step": 2525
|
|
},
|
|
{
|
|
"entropy": 6.116535997390747,
|
|
"epoch": 0.19684886208908772,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004998403903013984,
|
|
"loss": 5.8476,
|
|
"mean_token_accuracy": 0.1478264570236206,
|
|
"num_tokens": 4380528.0,
|
|
"step": 2530
|
|
},
|
|
{
|
|
"entropy": 6.055860280990601,
|
|
"epoch": 0.19723789146080528,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998393448361179,
|
|
"loss": 5.9436,
|
|
"mean_token_accuracy": 0.1379445366561413,
|
|
"num_tokens": 4389464.0,
|
|
"step": 2535
|
|
},
|
|
{
|
|
"entropy": 6.178743028640747,
|
|
"epoch": 0.19762692083252287,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000499838295959258,
|
|
"loss": 6.0005,
|
|
"mean_token_accuracy": 0.1344634510576725,
|
|
"num_tokens": 4397879.0,
|
|
"step": 2540
|
|
},
|
|
{
|
|
"entropy": 6.147117757797242,
|
|
"epoch": 0.19801595020424043,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000499837243670835,
|
|
"loss": 6.0062,
|
|
"mean_token_accuracy": 0.13882223516702652,
|
|
"num_tokens": 4406145.0,
|
|
"step": 2545
|
|
},
|
|
{
|
|
"entropy": 6.10461392402649,
|
|
"epoch": 0.19840497957595798,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004998361879708646,
|
|
"loss": 5.9092,
|
|
"mean_token_accuracy": 0.137804589420557,
|
|
"num_tokens": 4415480.0,
|
|
"step": 2550
|
|
},
|
|
{
|
|
"entropy": 6.154189825057983,
|
|
"epoch": 0.19879400894767554,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000499835128859363,
|
|
"loss": 5.9301,
|
|
"mean_token_accuracy": 0.14363658130168916,
|
|
"num_tokens": 4423355.0,
|
|
"step": 2555
|
|
},
|
|
{
|
|
"entropy": 6.089098072052002,
|
|
"epoch": 0.1991830383193931,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004998340663363461,
|
|
"loss": 5.8279,
|
|
"mean_token_accuracy": 0.1488031305372715,
|
|
"num_tokens": 4432059.0,
|
|
"step": 2560
|
|
},
|
|
{
|
|
"entropy": 6.035713958740234,
|
|
"epoch": 0.1995720676911107,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004998330004018301,
|
|
"loss": 5.9177,
|
|
"mean_token_accuracy": 0.13287902176380156,
|
|
"num_tokens": 4441146.0,
|
|
"step": 2565
|
|
},
|
|
{
|
|
"entropy": 6.091567516326904,
|
|
"epoch": 0.19996109706282825,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998319310558312,
|
|
"loss": 5.7498,
|
|
"mean_token_accuracy": 0.15268679708242416,
|
|
"num_tokens": 4448553.0,
|
|
"step": 2570
|
|
},
|
|
{
|
|
"entropy": 5.924048852920532,
|
|
"epoch": 0.2003501264345458,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998308582983657,
|
|
"loss": 5.8311,
|
|
"mean_token_accuracy": 0.1501924604177475,
|
|
"num_tokens": 4456930.0,
|
|
"step": 2575
|
|
},
|
|
{
|
|
"entropy": 6.182810688018799,
|
|
"epoch": 0.20073915580626336,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998297821294497,
|
|
"loss": 6.0141,
|
|
"mean_token_accuracy": 0.14234298169612886,
|
|
"num_tokens": 4464932.0,
|
|
"step": 2580
|
|
},
|
|
{
|
|
"entropy": 6.097385025024414,
|
|
"epoch": 0.20112818517798095,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004998287025490995,
|
|
"loss": 5.7409,
|
|
"mean_token_accuracy": 0.15158229768276216,
|
|
"num_tokens": 4473695.0,
|
|
"step": 2585
|
|
},
|
|
{
|
|
"entropy": 5.993387842178345,
|
|
"epoch": 0.2015172145496985,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004998276195573317,
|
|
"loss": 5.9849,
|
|
"mean_token_accuracy": 0.1368507519364357,
|
|
"num_tokens": 4483375.0,
|
|
"step": 2590
|
|
},
|
|
{
|
|
"entropy": 6.1823647022247314,
|
|
"epoch": 0.20190624392141607,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998265331541627,
|
|
"loss": 6.0034,
|
|
"mean_token_accuracy": 0.13301878720521926,
|
|
"num_tokens": 4491695.0,
|
|
"step": 2595
|
|
},
|
|
{
|
|
"entropy": 6.069152975082398,
|
|
"epoch": 0.20229527329313363,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998254433396088,
|
|
"loss": 5.9566,
|
|
"mean_token_accuracy": 0.14346428364515304,
|
|
"num_tokens": 4500361.0,
|
|
"step": 2600
|
|
},
|
|
{
|
|
"entropy": 6.137755489349365,
|
|
"epoch": 0.20268430266485118,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004998243501136867,
|
|
"loss": 5.891,
|
|
"mean_token_accuracy": 0.14259622395038604,
|
|
"num_tokens": 4509368.0,
|
|
"step": 2605
|
|
},
|
|
{
|
|
"entropy": 6.1446033954620365,
|
|
"epoch": 0.20307333203656877,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004998232534764129,
|
|
"loss": 5.8852,
|
|
"mean_token_accuracy": 0.13794858306646346,
|
|
"num_tokens": 4518146.0,
|
|
"step": 2610
|
|
},
|
|
{
|
|
"entropy": 6.1004749774932865,
|
|
"epoch": 0.20346236140828633,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998221534278041,
|
|
"loss": 5.9193,
|
|
"mean_token_accuracy": 0.1392908826470375,
|
|
"num_tokens": 4526128.0,
|
|
"step": 2615
|
|
},
|
|
{
|
|
"entropy": 6.157025766372681,
|
|
"epoch": 0.2038513907800039,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004998210499678769,
|
|
"loss": 5.9593,
|
|
"mean_token_accuracy": 0.14478977620601655,
|
|
"num_tokens": 4534724.0,
|
|
"step": 2620
|
|
},
|
|
{
|
|
"entropy": 6.023615980148316,
|
|
"epoch": 0.20424042015172145,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004998199430966481,
|
|
"loss": 5.821,
|
|
"mean_token_accuracy": 0.1394574910402298,
|
|
"num_tokens": 4543725.0,
|
|
"step": 2625
|
|
},
|
|
{
|
|
"entropy": 6.114223003387451,
|
|
"epoch": 0.20462944952343903,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004998188328141346,
|
|
"loss": 5.9023,
|
|
"mean_token_accuracy": 0.14211260229349137,
|
|
"num_tokens": 4551758.0,
|
|
"step": 2630
|
|
},
|
|
{
|
|
"entropy": 6.020139360427857,
|
|
"epoch": 0.2050184788951566,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998177191203531,
|
|
"loss": 5.7926,
|
|
"mean_token_accuracy": 0.14570502564311028,
|
|
"num_tokens": 4559990.0,
|
|
"step": 2635
|
|
},
|
|
{
|
|
"entropy": 6.072308111190796,
|
|
"epoch": 0.20540750826687415,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004998166020153204,
|
|
"loss": 5.8326,
|
|
"mean_token_accuracy": 0.1404043950140476,
|
|
"num_tokens": 4568651.0,
|
|
"step": 2640
|
|
},
|
|
{
|
|
"entropy": 5.98312201499939,
|
|
"epoch": 0.2057965376385917,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004998154814990538,
|
|
"loss": 5.7583,
|
|
"mean_token_accuracy": 0.14969710260629654,
|
|
"num_tokens": 4577981.0,
|
|
"step": 2645
|
|
},
|
|
{
|
|
"entropy": 6.022286748886108,
|
|
"epoch": 0.20618556701030927,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00049981435757157,
|
|
"loss": 5.9188,
|
|
"mean_token_accuracy": 0.14773550853133202,
|
|
"num_tokens": 4586480.0,
|
|
"step": 2650
|
|
},
|
|
{
|
|
"entropy": 6.1229582786560055,
|
|
"epoch": 0.20657459638202685,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998132302328862,
|
|
"loss": 5.8035,
|
|
"mean_token_accuracy": 0.15050222277641295,
|
|
"num_tokens": 4595554.0,
|
|
"step": 2655
|
|
},
|
|
{
|
|
"entropy": 6.027739095687866,
|
|
"epoch": 0.2069636257537444,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004998120994830195,
|
|
"loss": 5.8229,
|
|
"mean_token_accuracy": 0.14623611718416213,
|
|
"num_tokens": 4604091.0,
|
|
"step": 2660
|
|
},
|
|
{
|
|
"entropy": 6.164302587509155,
|
|
"epoch": 0.20735265512546197,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000499810965321987,
|
|
"loss": 5.9514,
|
|
"mean_token_accuracy": 0.14055586755275726,
|
|
"num_tokens": 4612603.0,
|
|
"step": 2665
|
|
},
|
|
{
|
|
"entropy": 6.115392780303955,
|
|
"epoch": 0.20774168449717953,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004998098277498059,
|
|
"loss": 5.8343,
|
|
"mean_token_accuracy": 0.14225830659270286,
|
|
"num_tokens": 4621041.0,
|
|
"step": 2670
|
|
},
|
|
{
|
|
"entropy": 5.985233879089355,
|
|
"epoch": 0.2081307138688971,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004998086867664934,
|
|
"loss": 5.8627,
|
|
"mean_token_accuracy": 0.14746104627847673,
|
|
"num_tokens": 4629849.0,
|
|
"step": 2675
|
|
},
|
|
{
|
|
"entropy": 6.099282693862915,
|
|
"epoch": 0.20851974324061467,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.000499807542372067,
|
|
"loss": 5.95,
|
|
"mean_token_accuracy": 0.14111322686076164,
|
|
"num_tokens": 4639426.0,
|
|
"step": 2680
|
|
},
|
|
{
|
|
"entropy": 6.099315929412842,
|
|
"epoch": 0.20890877261233223,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004998063945665439,
|
|
"loss": 5.8792,
|
|
"mean_token_accuracy": 0.14589827060699462,
|
|
"num_tokens": 4647257.0,
|
|
"step": 2685
|
|
},
|
|
{
|
|
"entropy": 6.0904378414154055,
|
|
"epoch": 0.2092978019840498,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004998052433499416,
|
|
"loss": 5.8631,
|
|
"mean_token_accuracy": 0.14348279163241387,
|
|
"num_tokens": 4655773.0,
|
|
"step": 2690
|
|
},
|
|
{
|
|
"entropy": 6.052747917175293,
|
|
"epoch": 0.20968683135576735,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998040887222776,
|
|
"loss": 5.8834,
|
|
"mean_token_accuracy": 0.1426556721329689,
|
|
"num_tokens": 4664292.0,
|
|
"step": 2695
|
|
},
|
|
{
|
|
"entropy": 6.178410577774048,
|
|
"epoch": 0.21007586072748494,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004998029306835693,
|
|
"loss": 5.9237,
|
|
"mean_token_accuracy": 0.1449746683239937,
|
|
"num_tokens": 4672774.0,
|
|
"step": 2700
|
|
},
|
|
{
|
|
"entropy": 6.213541555404663,
|
|
"epoch": 0.2104648900992025,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004998017692338344,
|
|
"loss": 6.0447,
|
|
"mean_token_accuracy": 0.13644783496856688,
|
|
"num_tokens": 4681855.0,
|
|
"step": 2705
|
|
},
|
|
{
|
|
"entropy": 6.082818508148193,
|
|
"epoch": 0.21085391947092005,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998006043730905,
|
|
"loss": 5.814,
|
|
"mean_token_accuracy": 0.14876434952020645,
|
|
"num_tokens": 4689771.0,
|
|
"step": 2710
|
|
},
|
|
{
|
|
"entropy": 6.110875511169434,
|
|
"epoch": 0.2112429488426376,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004997994361013551,
|
|
"loss": 5.9807,
|
|
"mean_token_accuracy": 0.131246355175972,
|
|
"num_tokens": 4698808.0,
|
|
"step": 2715
|
|
},
|
|
{
|
|
"entropy": 6.077038431167603,
|
|
"epoch": 0.21163197821435517,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004997982644186461,
|
|
"loss": 5.8661,
|
|
"mean_token_accuracy": 0.14354205653071403,
|
|
"num_tokens": 4707627.0,
|
|
"step": 2720
|
|
},
|
|
{
|
|
"entropy": 6.0479084014892575,
|
|
"epoch": 0.21202100758607276,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004997970893249813,
|
|
"loss": 5.8537,
|
|
"mean_token_accuracy": 0.14187933951616288,
|
|
"num_tokens": 4716091.0,
|
|
"step": 2725
|
|
},
|
|
{
|
|
"entropy": 6.063355493545532,
|
|
"epoch": 0.21241003695779032,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004997959108203785,
|
|
"loss": 5.871,
|
|
"mean_token_accuracy": 0.1473940022289753,
|
|
"num_tokens": 4724042.0,
|
|
"step": 2730
|
|
},
|
|
{
|
|
"entropy": 5.985284852981567,
|
|
"epoch": 0.21279906632950787,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004997947289048554,
|
|
"loss": 5.7784,
|
|
"mean_token_accuracy": 0.1558399736881256,
|
|
"num_tokens": 4731745.0,
|
|
"step": 2735
|
|
},
|
|
{
|
|
"entropy": 6.077976179122925,
|
|
"epoch": 0.21318809570122543,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004997935435784302,
|
|
"loss": 5.9664,
|
|
"mean_token_accuracy": 0.14258809015154839,
|
|
"num_tokens": 4740386.0,
|
|
"step": 2740
|
|
},
|
|
{
|
|
"entropy": 6.121005344390869,
|
|
"epoch": 0.21357712507294302,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004997923548411208,
|
|
"loss": 5.9529,
|
|
"mean_token_accuracy": 0.135360998660326,
|
|
"num_tokens": 4749809.0,
|
|
"step": 2745
|
|
},
|
|
{
|
|
"entropy": 6.177447128295898,
|
|
"epoch": 0.21396615444466058,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.000499791162692945,
|
|
"loss": 6.0766,
|
|
"mean_token_accuracy": 0.1363483987748623,
|
|
"num_tokens": 4759507.0,
|
|
"step": 2750
|
|
},
|
|
{
|
|
"entropy": 6.055140495300293,
|
|
"epoch": 0.21435518381637814,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004997899671339214,
|
|
"loss": 5.8378,
|
|
"mean_token_accuracy": 0.14012878388166428,
|
|
"num_tokens": 4768793.0,
|
|
"step": 2755
|
|
},
|
|
{
|
|
"entropy": 6.124060440063476,
|
|
"epoch": 0.2147442131880957,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004997887681640675,
|
|
"loss": 5.9864,
|
|
"mean_token_accuracy": 0.136216626316309,
|
|
"num_tokens": 4777344.0,
|
|
"step": 2760
|
|
},
|
|
{
|
|
"entropy": 6.160050868988037,
|
|
"epoch": 0.21513324255981325,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004997875657834021,
|
|
"loss": 5.9176,
|
|
"mean_token_accuracy": 0.14089114516973494,
|
|
"num_tokens": 4785934.0,
|
|
"step": 2765
|
|
},
|
|
{
|
|
"entropy": 6.034284019470215,
|
|
"epoch": 0.21552227193153084,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004997863599919432,
|
|
"loss": 5.8573,
|
|
"mean_token_accuracy": 0.1446565344929695,
|
|
"num_tokens": 4794889.0,
|
|
"step": 2770
|
|
},
|
|
{
|
|
"entropy": 6.02419900894165,
|
|
"epoch": 0.2159113013032484,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004997851507897089,
|
|
"loss": 5.9665,
|
|
"mean_token_accuracy": 0.13921516314148902,
|
|
"num_tokens": 4803597.0,
|
|
"step": 2775
|
|
},
|
|
{
|
|
"entropy": 6.091166543960571,
|
|
"epoch": 0.21630033067496596,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004997839381767178,
|
|
"loss": 5.7469,
|
|
"mean_token_accuracy": 0.15012719631195068,
|
|
"num_tokens": 4812706.0,
|
|
"step": 2780
|
|
},
|
|
{
|
|
"entropy": 5.975925588607788,
|
|
"epoch": 0.21668936004668352,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004997827221529882,
|
|
"loss": 5.8138,
|
|
"mean_token_accuracy": 0.1410752348601818,
|
|
"num_tokens": 4821790.0,
|
|
"step": 2785
|
|
},
|
|
{
|
|
"entropy": 6.095637559890747,
|
|
"epoch": 0.2170783894184011,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004997815027185386,
|
|
"loss": 5.8651,
|
|
"mean_token_accuracy": 0.14362238049507142,
|
|
"num_tokens": 4830123.0,
|
|
"step": 2790
|
|
},
|
|
{
|
|
"entropy": 6.073716259002685,
|
|
"epoch": 0.21746741879011866,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004997802798733874,
|
|
"loss": 5.7984,
|
|
"mean_token_accuracy": 0.14468253999948502,
|
|
"num_tokens": 4838066.0,
|
|
"step": 2795
|
|
},
|
|
{
|
|
"entropy": 6.039735746383667,
|
|
"epoch": 0.21785644816183622,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004997790536175534,
|
|
"loss": 5.8614,
|
|
"mean_token_accuracy": 0.1461779847741127,
|
|
"num_tokens": 4846877.0,
|
|
"step": 2800
|
|
},
|
|
{
|
|
"entropy": 6.086436319351196,
|
|
"epoch": 0.21824547753355378,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004997778239510548,
|
|
"loss": 5.9278,
|
|
"mean_token_accuracy": 0.13898368775844575,
|
|
"num_tokens": 4856960.0,
|
|
"step": 2805
|
|
},
|
|
{
|
|
"entropy": 6.088310766220093,
|
|
"epoch": 0.21863450690527134,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004997765908739106,
|
|
"loss": 5.9417,
|
|
"mean_token_accuracy": 0.14190473333001136,
|
|
"num_tokens": 4865440.0,
|
|
"step": 2810
|
|
},
|
|
{
|
|
"entropy": 6.019820642471314,
|
|
"epoch": 0.21902353627698892,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004997753543861395,
|
|
"loss": 5.8224,
|
|
"mean_token_accuracy": 0.14486733451485634,
|
|
"num_tokens": 4874187.0,
|
|
"step": 2815
|
|
},
|
|
{
|
|
"entropy": 6.17541913986206,
|
|
"epoch": 0.21941256564870648,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.00049977411448776,
|
|
"loss": 5.9681,
|
|
"mean_token_accuracy": 0.13802750185132026,
|
|
"num_tokens": 4883151.0,
|
|
"step": 2820
|
|
},
|
|
{
|
|
"entropy": 6.097297096252442,
|
|
"epoch": 0.21980159502042404,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004997728711787912,
|
|
"loss": 5.8656,
|
|
"mean_token_accuracy": 0.14226908087730408,
|
|
"num_tokens": 4890968.0,
|
|
"step": 2825
|
|
},
|
|
{
|
|
"entropy": 6.005394792556762,
|
|
"epoch": 0.2201906243921416,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004997716244592518,
|
|
"loss": 5.7664,
|
|
"mean_token_accuracy": 0.15000639855861664,
|
|
"num_tokens": 4899389.0,
|
|
"step": 2830
|
|
},
|
|
{
|
|
"entropy": 6.016676950454712,
|
|
"epoch": 0.22057965376385918,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004997703743291607,
|
|
"loss": 5.8472,
|
|
"mean_token_accuracy": 0.14968255087733268,
|
|
"num_tokens": 4907622.0,
|
|
"step": 2835
|
|
},
|
|
{
|
|
"entropy": 6.053238010406494,
|
|
"epoch": 0.22096868313557674,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000499769120788537,
|
|
"loss": 5.8416,
|
|
"mean_token_accuracy": 0.14399737119674683,
|
|
"num_tokens": 4916151.0,
|
|
"step": 2840
|
|
},
|
|
{
|
|
"entropy": 5.965752077102661,
|
|
"epoch": 0.2213577125072943,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004997678638373995,
|
|
"loss": 5.7334,
|
|
"mean_token_accuracy": 0.1568694993853569,
|
|
"num_tokens": 4923938.0,
|
|
"step": 2845
|
|
},
|
|
{
|
|
"entropy": 6.076515531539917,
|
|
"epoch": 0.22174674187901186,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004997666034757676,
|
|
"loss": 5.8339,
|
|
"mean_token_accuracy": 0.15386861115694045,
|
|
"num_tokens": 4932027.0,
|
|
"step": 2850
|
|
},
|
|
{
|
|
"entropy": 6.042121171951294,
|
|
"epoch": 0.22213577125072942,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004997653397036603,
|
|
"loss": 5.8524,
|
|
"mean_token_accuracy": 0.15097130537033082,
|
|
"num_tokens": 4940229.0,
|
|
"step": 2855
|
|
},
|
|
{
|
|
"entropy": 5.992015314102173,
|
|
"epoch": 0.222524800622447,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004997640725210965,
|
|
"loss": 5.9242,
|
|
"mean_token_accuracy": 0.14181902557611464,
|
|
"num_tokens": 4948662.0,
|
|
"step": 2860
|
|
},
|
|
{
|
|
"entropy": 6.072470712661743,
|
|
"epoch": 0.22291382999416456,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004997628019280958,
|
|
"loss": 5.8773,
|
|
"mean_token_accuracy": 0.14416748732328416,
|
|
"num_tokens": 4956847.0,
|
|
"step": 2865
|
|
},
|
|
{
|
|
"entropy": 6.070145511627198,
|
|
"epoch": 0.22330285936588212,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004997615279246773,
|
|
"loss": 5.8031,
|
|
"mean_token_accuracy": 0.14515076130628585,
|
|
"num_tokens": 4965139.0,
|
|
"step": 2870
|
|
},
|
|
{
|
|
"entropy": 6.135627269744873,
|
|
"epoch": 0.22369188873759968,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004997602505108603,
|
|
"loss": 5.9724,
|
|
"mean_token_accuracy": 0.1393357440829277,
|
|
"num_tokens": 4973671.0,
|
|
"step": 2875
|
|
},
|
|
{
|
|
"entropy": 6.075475406646729,
|
|
"epoch": 0.22408091810931724,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004997589696866644,
|
|
"loss": 5.8527,
|
|
"mean_token_accuracy": 0.14160598665475846,
|
|
"num_tokens": 4981970.0,
|
|
"step": 2880
|
|
},
|
|
{
|
|
"entropy": 6.048443412780761,
|
|
"epoch": 0.22446994748103483,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004997576854521088,
|
|
"loss": 5.8601,
|
|
"mean_token_accuracy": 0.14621118903160096,
|
|
"num_tokens": 4990591.0,
|
|
"step": 2885
|
|
},
|
|
{
|
|
"entropy": 6.036798810958862,
|
|
"epoch": 0.22485897685275238,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000499756397807213,
|
|
"loss": 5.8737,
|
|
"mean_token_accuracy": 0.1408968098461628,
|
|
"num_tokens": 4999623.0,
|
|
"step": 2890
|
|
},
|
|
{
|
|
"entropy": 6.154255437850952,
|
|
"epoch": 0.22524800622446994,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004997551067519966,
|
|
"loss": 5.9326,
|
|
"mean_token_accuracy": 0.13853658065199853,
|
|
"num_tokens": 5008387.0,
|
|
"step": 2895
|
|
},
|
|
{
|
|
"entropy": 6.0091872215271,
|
|
"epoch": 0.2256370355961875,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004997538122864792,
|
|
"loss": 5.8513,
|
|
"mean_token_accuracy": 0.1488157957792282,
|
|
"num_tokens": 5016788.0,
|
|
"step": 2900
|
|
},
|
|
{
|
|
"entropy": 6.0877045631408695,
|
|
"epoch": 0.2260260649679051,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004997525144106804,
|
|
"loss": 5.8786,
|
|
"mean_token_accuracy": 0.14177965149283409,
|
|
"num_tokens": 5025508.0,
|
|
"step": 2905
|
|
},
|
|
{
|
|
"entropy": 6.003860330581665,
|
|
"epoch": 0.22641509433962265,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00049975121312462,
|
|
"loss": 5.8675,
|
|
"mean_token_accuracy": 0.13894690126180648,
|
|
"num_tokens": 5035081.0,
|
|
"step": 2910
|
|
},
|
|
{
|
|
"entropy": 6.021999168395996,
|
|
"epoch": 0.2268041237113402,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004997499084283177,
|
|
"loss": 5.7956,
|
|
"mean_token_accuracy": 0.1498025491833687,
|
|
"num_tokens": 5043655.0,
|
|
"step": 2915
|
|
},
|
|
{
|
|
"entropy": 6.045802927017212,
|
|
"epoch": 0.22719315308305776,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004997486003217932,
|
|
"loss": 5.8186,
|
|
"mean_token_accuracy": 0.1467895582318306,
|
|
"num_tokens": 5052080.0,
|
|
"step": 2920
|
|
},
|
|
{
|
|
"entropy": 5.940340852737426,
|
|
"epoch": 0.22758218245477532,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004997472888050664,
|
|
"loss": 5.789,
|
|
"mean_token_accuracy": 0.15500381588935852,
|
|
"num_tokens": 5061325.0,
|
|
"step": 2925
|
|
},
|
|
{
|
|
"entropy": 6.0531168460845945,
|
|
"epoch": 0.2279712118264929,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004997459738781573,
|
|
"loss": 5.8874,
|
|
"mean_token_accuracy": 0.1485513836145401,
|
|
"num_tokens": 5069461.0,
|
|
"step": 2930
|
|
},
|
|
{
|
|
"entropy": 6.08068060874939,
|
|
"epoch": 0.22836024119821047,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004997446555410857,
|
|
"loss": 5.8595,
|
|
"mean_token_accuracy": 0.13977533280849458,
|
|
"num_tokens": 5077747.0,
|
|
"step": 2935
|
|
},
|
|
{
|
|
"entropy": 6.086756801605224,
|
|
"epoch": 0.22874927056992803,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004997433337938716,
|
|
"loss": 5.911,
|
|
"mean_token_accuracy": 0.14513636901974677,
|
|
"num_tokens": 5086300.0,
|
|
"step": 2940
|
|
},
|
|
{
|
|
"entropy": 5.952954530715942,
|
|
"epoch": 0.22913829994164558,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004997420086365351,
|
|
"loss": 5.6668,
|
|
"mean_token_accuracy": 0.15248717218637467,
|
|
"num_tokens": 5094762.0,
|
|
"step": 2945
|
|
},
|
|
{
|
|
"entropy": 5.985451412200928,
|
|
"epoch": 0.22952732931336317,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004997406800690966,
|
|
"loss": 5.856,
|
|
"mean_token_accuracy": 0.14468831270933152,
|
|
"num_tokens": 5103364.0,
|
|
"step": 2950
|
|
},
|
|
{
|
|
"entropy": 6.156504106521607,
|
|
"epoch": 0.22991635868508073,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004997393480915758,
|
|
"loss": 5.9605,
|
|
"mean_token_accuracy": 0.14181874990463256,
|
|
"num_tokens": 5111730.0,
|
|
"step": 2955
|
|
},
|
|
{
|
|
"entropy": 6.056686782836914,
|
|
"epoch": 0.2303053880567983,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004997380127039931,
|
|
"loss": 5.7647,
|
|
"mean_token_accuracy": 0.14477684944868088,
|
|
"num_tokens": 5119878.0,
|
|
"step": 2960
|
|
},
|
|
{
|
|
"entropy": 6.014952659606934,
|
|
"epoch": 0.23069441742851585,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004997366739063688,
|
|
"loss": 5.8686,
|
|
"mean_token_accuracy": 0.14824746251106263,
|
|
"num_tokens": 5129146.0,
|
|
"step": 2965
|
|
},
|
|
{
|
|
"entropy": 6.005827903747559,
|
|
"epoch": 0.2310834468002334,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004997353316987231,
|
|
"loss": 5.8798,
|
|
"mean_token_accuracy": 0.14015825390815734,
|
|
"num_tokens": 5137989.0,
|
|
"step": 2970
|
|
},
|
|
{
|
|
"entropy": 6.11515440940857,
|
|
"epoch": 0.231472476171951,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004997339860810765,
|
|
"loss": 5.9271,
|
|
"mean_token_accuracy": 0.14150395467877389,
|
|
"num_tokens": 5146722.0,
|
|
"step": 2975
|
|
},
|
|
{
|
|
"entropy": 6.122695827484131,
|
|
"epoch": 0.23186150554366855,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004997326370534495,
|
|
"loss": 5.9296,
|
|
"mean_token_accuracy": 0.14121474623680114,
|
|
"num_tokens": 5154902.0,
|
|
"step": 2980
|
|
},
|
|
{
|
|
"entropy": 6.067652940750122,
|
|
"epoch": 0.2322505349153861,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004997312846158622,
|
|
"loss": 5.9035,
|
|
"mean_token_accuracy": 0.14448403418064118,
|
|
"num_tokens": 5163594.0,
|
|
"step": 2985
|
|
},
|
|
{
|
|
"entropy": 6.061365270614624,
|
|
"epoch": 0.23263956428710367,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004997299287683355,
|
|
"loss": 5.7941,
|
|
"mean_token_accuracy": 0.14882556200027466,
|
|
"num_tokens": 5172139.0,
|
|
"step": 2990
|
|
},
|
|
{
|
|
"entropy": 6.065181398391724,
|
|
"epoch": 0.23302859365882125,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004997285695108898,
|
|
"loss": 5.9152,
|
|
"mean_token_accuracy": 0.14413146376609803,
|
|
"num_tokens": 5180077.0,
|
|
"step": 2995
|
|
},
|
|
{
|
|
"entropy": 5.950593709945679,
|
|
"epoch": 0.2334176230305388,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004997272068435458,
|
|
"loss": 5.7547,
|
|
"mean_token_accuracy": 0.1455926775932312,
|
|
"num_tokens": 5188500.0,
|
|
"step": 3000
|
|
},
|
|
{
|
|
"epoch": 0.2334176230305388,
|
|
"eval_entropy": 5.776663673555082,
|
|
"eval_loss": 5.887854099273682,
|
|
"eval_mean_token_accuracy": 0.151562392559616,
|
|
"eval_num_tokens": 5188500.0,
|
|
"eval_runtime": 22.2562,
|
|
"eval_samples_per_second": 1867.253,
|
|
"eval_steps_per_second": 233.418,
|
|
"step": 3000
|
|
}
|
|
],
|
|
"logging_steps": 5,
|
|
"max_steps": 128520,
|
|
"num_input_tokens_seen": 0,
|
|
"num_train_epochs": 10,
|
|
"save_steps": 3000,
|
|
"stateful_callbacks": {
|
|
"TrainerControl": {
|
|
"args": {
|
|
"should_epoch_stop": false,
|
|
"should_evaluate": false,
|
|
"should_log": false,
|
|
"should_save": true,
|
|
"should_training_stop": false
|
|
},
|
|
"attributes": {}
|
|
}
|
|
},
|
|
"total_flos": 1038909989191680.0,
|
|
"train_batch_size": 16,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|