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": 10.692063236236573,
|
|
"epoch": 0.00038902937171756465,
|
|
"grad_norm": 13.75,
|
|
"learning_rate": 2e-06,
|
|
"loss": 10.8016,
|
|
"mean_token_accuracy": 0.0,
|
|
"num_tokens": 8755.0,
|
|
"step": 5
|
|
},
|
|
{
|
|
"entropy": 10.691958236694337,
|
|
"epoch": 0.0007780587434351293,
|
|
"grad_norm": 14.0625,
|
|
"learning_rate": 4.5e-06,
|
|
"loss": 10.7404,
|
|
"mean_token_accuracy": 0.000141643057577312,
|
|
"num_tokens": 17641.0,
|
|
"step": 10
|
|
},
|
|
{
|
|
"entropy": 10.690918159484863,
|
|
"epoch": 0.001167088115152694,
|
|
"grad_norm": 10.3125,
|
|
"learning_rate": 7e-06,
|
|
"loss": 10.4828,
|
|
"mean_token_accuracy": 0.025441211403813214,
|
|
"num_tokens": 26293.0,
|
|
"step": 15
|
|
},
|
|
{
|
|
"entropy": 10.67647647857666,
|
|
"epoch": 0.0015561174868702586,
|
|
"grad_norm": 6.5,
|
|
"learning_rate": 9.5e-06,
|
|
"loss": 10.2109,
|
|
"mean_token_accuracy": 0.040661663934588435,
|
|
"num_tokens": 35627.0,
|
|
"step": 20
|
|
},
|
|
{
|
|
"entropy": 10.60925121307373,
|
|
"epoch": 0.0019451468585878235,
|
|
"grad_norm": 4.28125,
|
|
"learning_rate": 1.2e-05,
|
|
"loss": 9.8983,
|
|
"mean_token_accuracy": 0.04408857449889183,
|
|
"num_tokens": 43861.0,
|
|
"step": 25
|
|
},
|
|
{
|
|
"entropy": 10.547060012817383,
|
|
"epoch": 0.002334176230305388,
|
|
"grad_norm": 3.625,
|
|
"learning_rate": 1.4500000000000002e-05,
|
|
"loss": 9.7771,
|
|
"mean_token_accuracy": 0.04438098855316639,
|
|
"num_tokens": 52816.0,
|
|
"step": 30
|
|
},
|
|
{
|
|
"entropy": 10.550695419311523,
|
|
"epoch": 0.0027232056020229526,
|
|
"grad_norm": 3.046875,
|
|
"learning_rate": 1.7000000000000003e-05,
|
|
"loss": 9.716,
|
|
"mean_token_accuracy": 0.044043789803981784,
|
|
"num_tokens": 61370.0,
|
|
"step": 35
|
|
},
|
|
{
|
|
"entropy": 10.541547393798828,
|
|
"epoch": 0.0031122349737405172,
|
|
"grad_norm": 2.84375,
|
|
"learning_rate": 1.95e-05,
|
|
"loss": 9.6407,
|
|
"mean_token_accuracy": 0.04505775421857834,
|
|
"num_tokens": 69444.0,
|
|
"step": 40
|
|
},
|
|
{
|
|
"entropy": 10.531424808502198,
|
|
"epoch": 0.003501264345458082,
|
|
"grad_norm": 2.6875,
|
|
"learning_rate": 2.2e-05,
|
|
"loss": 9.591,
|
|
"mean_token_accuracy": 0.04762658141553402,
|
|
"num_tokens": 77892.0,
|
|
"step": 45
|
|
},
|
|
{
|
|
"entropy": 10.512275695800781,
|
|
"epoch": 0.003890293717175647,
|
|
"grad_norm": 2.53125,
|
|
"learning_rate": 2.4500000000000003e-05,
|
|
"loss": 9.5439,
|
|
"mean_token_accuracy": 0.061067067086696625,
|
|
"num_tokens": 86154.0,
|
|
"step": 50
|
|
},
|
|
{
|
|
"entropy": 10.401442527770996,
|
|
"epoch": 0.004279323088893211,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 2.7e-05,
|
|
"loss": 9.4981,
|
|
"mean_token_accuracy": 0.06119193881750107,
|
|
"num_tokens": 95589.0,
|
|
"step": 55
|
|
},
|
|
{
|
|
"entropy": 10.321024227142335,
|
|
"epoch": 0.004668352460610776,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 2.95e-05,
|
|
"loss": 9.4607,
|
|
"mean_token_accuracy": 0.06384341418743134,
|
|
"num_tokens": 105268.0,
|
|
"step": 60
|
|
},
|
|
{
|
|
"entropy": 10.332015323638917,
|
|
"epoch": 0.0050573818323283405,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 3.2e-05,
|
|
"loss": 9.2989,
|
|
"mean_token_accuracy": 0.06944983527064323,
|
|
"num_tokens": 113347.0,
|
|
"step": 65
|
|
},
|
|
{
|
|
"entropy": 10.328180885314941,
|
|
"epoch": 0.005446411204045905,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 3.4500000000000005e-05,
|
|
"loss": 9.2579,
|
|
"mean_token_accuracy": 0.06596625149250031,
|
|
"num_tokens": 121235.0,
|
|
"step": 70
|
|
},
|
|
{
|
|
"entropy": 10.303812599182129,
|
|
"epoch": 0.00583544057576347,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 3.7e-05,
|
|
"loss": 9.152,
|
|
"mean_token_accuracy": 0.06924093440175057,
|
|
"num_tokens": 129529.0,
|
|
"step": 75
|
|
},
|
|
{
|
|
"entropy": 10.268609428405762,
|
|
"epoch": 0.0062244699474810344,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 3.95e-05,
|
|
"loss": 9.0909,
|
|
"mean_token_accuracy": 0.06597104258835315,
|
|
"num_tokens": 137918.0,
|
|
"step": 80
|
|
},
|
|
{
|
|
"entropy": 10.261999797821044,
|
|
"epoch": 0.006613499319198599,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 4.2000000000000004e-05,
|
|
"loss": 8.9463,
|
|
"mean_token_accuracy": 0.06913249380886555,
|
|
"num_tokens": 146445.0,
|
|
"step": 85
|
|
},
|
|
{
|
|
"entropy": 10.207746601104736,
|
|
"epoch": 0.007002528690916164,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 4.45e-05,
|
|
"loss": 8.9607,
|
|
"mean_token_accuracy": 0.0626212403178215,
|
|
"num_tokens": 155904.0,
|
|
"step": 90
|
|
},
|
|
{
|
|
"entropy": 10.237759494781494,
|
|
"epoch": 0.007391558062633729,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 4.7000000000000004e-05,
|
|
"loss": 8.8494,
|
|
"mean_token_accuracy": 0.06117668002843857,
|
|
"num_tokens": 164436.0,
|
|
"step": 95
|
|
},
|
|
{
|
|
"entropy": 10.121377658843993,
|
|
"epoch": 0.007780587434351294,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 4.9500000000000004e-05,
|
|
"loss": 8.7265,
|
|
"mean_token_accuracy": 0.06574496850371361,
|
|
"num_tokens": 172985.0,
|
|
"step": 100
|
|
},
|
|
{
|
|
"entropy": 10.09178113937378,
|
|
"epoch": 0.008169616806068859,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 5.2e-05,
|
|
"loss": 8.5893,
|
|
"mean_token_accuracy": 0.0671191781759262,
|
|
"num_tokens": 182084.0,
|
|
"step": 105
|
|
},
|
|
{
|
|
"entropy": 10.011064624786377,
|
|
"epoch": 0.008558646177786422,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 5.45e-05,
|
|
"loss": 8.4644,
|
|
"mean_token_accuracy": 0.07035542875528336,
|
|
"num_tokens": 190742.0,
|
|
"step": 110
|
|
},
|
|
{
|
|
"entropy": 9.856452560424804,
|
|
"epoch": 0.008947675549503988,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 5.7e-05,
|
|
"loss": 8.3796,
|
|
"mean_token_accuracy": 0.06666092537343501,
|
|
"num_tokens": 199600.0,
|
|
"step": 115
|
|
},
|
|
{
|
|
"entropy": 9.79461441040039,
|
|
"epoch": 0.009336704921221552,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 5.9499999999999996e-05,
|
|
"loss": 8.2817,
|
|
"mean_token_accuracy": 0.06714933924376965,
|
|
"num_tokens": 207883.0,
|
|
"step": 120
|
|
},
|
|
{
|
|
"entropy": 9.610589599609375,
|
|
"epoch": 0.009725734292939117,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 6.2e-05,
|
|
"loss": 8.2106,
|
|
"mean_token_accuracy": 0.06839943863451481,
|
|
"num_tokens": 216216.0,
|
|
"step": 125
|
|
},
|
|
{
|
|
"entropy": 9.441116333007812,
|
|
"epoch": 0.010114763664656681,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 6.450000000000001e-05,
|
|
"loss": 8.0674,
|
|
"mean_token_accuracy": 0.06686468720436096,
|
|
"num_tokens": 225250.0,
|
|
"step": 130
|
|
},
|
|
{
|
|
"entropy": 9.317984580993652,
|
|
"epoch": 0.010503793036374246,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 6.7e-05,
|
|
"loss": 7.9861,
|
|
"mean_token_accuracy": 0.06643427908420563,
|
|
"num_tokens": 233748.0,
|
|
"step": 135
|
|
},
|
|
{
|
|
"entropy": 9.106039714813232,
|
|
"epoch": 0.01089282240809181,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 6.950000000000001e-05,
|
|
"loss": 7.9137,
|
|
"mean_token_accuracy": 0.06834710240364075,
|
|
"num_tokens": 242629.0,
|
|
"step": 140
|
|
},
|
|
{
|
|
"entropy": 9.014894771575928,
|
|
"epoch": 0.011281851779809376,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 7.2e-05,
|
|
"loss": 7.825,
|
|
"mean_token_accuracy": 0.06285446509718895,
|
|
"num_tokens": 251458.0,
|
|
"step": 145
|
|
},
|
|
{
|
|
"entropy": 8.738780689239501,
|
|
"epoch": 0.01167088115152694,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 7.45e-05,
|
|
"loss": 7.7458,
|
|
"mean_token_accuracy": 0.07414877340197563,
|
|
"num_tokens": 260557.0,
|
|
"step": 150
|
|
},
|
|
{
|
|
"entropy": 8.657924938201905,
|
|
"epoch": 0.012059910523244505,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 7.7e-05,
|
|
"loss": 7.7607,
|
|
"mean_token_accuracy": 0.06932397484779358,
|
|
"num_tokens": 269262.0,
|
|
"step": 155
|
|
},
|
|
{
|
|
"entropy": 8.543195724487305,
|
|
"epoch": 0.012448939894962069,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 7.950000000000001e-05,
|
|
"loss": 7.662,
|
|
"mean_token_accuracy": 0.07255172692239284,
|
|
"num_tokens": 277804.0,
|
|
"step": 160
|
|
},
|
|
{
|
|
"entropy": 8.427197933197021,
|
|
"epoch": 0.012837969266679634,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 8.2e-05,
|
|
"loss": 7.6187,
|
|
"mean_token_accuracy": 0.0732395388185978,
|
|
"num_tokens": 287450.0,
|
|
"step": 165
|
|
},
|
|
{
|
|
"entropy": 8.372405529022217,
|
|
"epoch": 0.013226998638397198,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 8.450000000000001e-05,
|
|
"loss": 7.6324,
|
|
"mean_token_accuracy": 0.07173264883458615,
|
|
"num_tokens": 296497.0,
|
|
"step": 170
|
|
},
|
|
{
|
|
"entropy": 8.20972490310669,
|
|
"epoch": 0.013616028010114764,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 8.7e-05,
|
|
"loss": 7.5358,
|
|
"mean_token_accuracy": 0.07566781267523766,
|
|
"num_tokens": 305414.0,
|
|
"step": 175
|
|
},
|
|
{
|
|
"entropy": 8.156252384185791,
|
|
"epoch": 0.014005057381832327,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 8.95e-05,
|
|
"loss": 7.5503,
|
|
"mean_token_accuracy": 0.07218287587165832,
|
|
"num_tokens": 313639.0,
|
|
"step": 180
|
|
},
|
|
{
|
|
"entropy": 8.146188354492187,
|
|
"epoch": 0.014394086753549893,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 9.2e-05,
|
|
"loss": 7.5511,
|
|
"mean_token_accuracy": 0.07190043628215789,
|
|
"num_tokens": 322855.0,
|
|
"step": 185
|
|
},
|
|
{
|
|
"entropy": 8.109641361236573,
|
|
"epoch": 0.014783116125267459,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 9.45e-05,
|
|
"loss": 7.6463,
|
|
"mean_token_accuracy": 0.07696216627955436,
|
|
"num_tokens": 332071.0,
|
|
"step": 190
|
|
},
|
|
{
|
|
"entropy": 8.094918823242187,
|
|
"epoch": 0.015172145496985022,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 9.7e-05,
|
|
"loss": 7.4403,
|
|
"mean_token_accuracy": 0.077825241163373,
|
|
"num_tokens": 339990.0,
|
|
"step": 195
|
|
},
|
|
{
|
|
"entropy": 7.986162710189819,
|
|
"epoch": 0.015561174868702588,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 9.95e-05,
|
|
"loss": 7.489,
|
|
"mean_token_accuracy": 0.0800612710416317,
|
|
"num_tokens": 348581.0,
|
|
"step": 200
|
|
},
|
|
{
|
|
"entropy": 8.061878490447999,
|
|
"epoch": 0.01595020424042015,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000102,
|
|
"loss": 7.4901,
|
|
"mean_token_accuracy": 0.07649841569364071,
|
|
"num_tokens": 357032.0,
|
|
"step": 205
|
|
},
|
|
{
|
|
"entropy": 7.995882654190064,
|
|
"epoch": 0.016339233612137717,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00010449999999999999,
|
|
"loss": 7.4516,
|
|
"mean_token_accuracy": 0.0756280355155468,
|
|
"num_tokens": 366562.0,
|
|
"step": 210
|
|
},
|
|
{
|
|
"entropy": 7.987649202346802,
|
|
"epoch": 0.016728262983855283,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.000107,
|
|
"loss": 7.4428,
|
|
"mean_token_accuracy": 0.07756799235939979,
|
|
"num_tokens": 374555.0,
|
|
"step": 215
|
|
},
|
|
{
|
|
"entropy": 7.977654266357422,
|
|
"epoch": 0.017117292355572845,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0001095,
|
|
"loss": 7.4725,
|
|
"mean_token_accuracy": 0.07444248832762242,
|
|
"num_tokens": 383583.0,
|
|
"step": 220
|
|
},
|
|
{
|
|
"entropy": 7.902964973449707,
|
|
"epoch": 0.01750632172729041,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000112,
|
|
"loss": 7.4967,
|
|
"mean_token_accuracy": 0.07443738169968128,
|
|
"num_tokens": 392932.0,
|
|
"step": 225
|
|
},
|
|
{
|
|
"entropy": 7.966854381561279,
|
|
"epoch": 0.017895351099007976,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0001145,
|
|
"loss": 7.3305,
|
|
"mean_token_accuracy": 0.07826850302517414,
|
|
"num_tokens": 401653.0,
|
|
"step": 230
|
|
},
|
|
{
|
|
"entropy": 7.823260259628296,
|
|
"epoch": 0.01828438047072554,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00011700000000000001,
|
|
"loss": 7.4224,
|
|
"mean_token_accuracy": 0.08165781088173389,
|
|
"num_tokens": 410432.0,
|
|
"step": 235
|
|
},
|
|
{
|
|
"entropy": 7.791707134246826,
|
|
"epoch": 0.018673409842443103,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00011949999999999999,
|
|
"loss": 7.3874,
|
|
"mean_token_accuracy": 0.07677992731332779,
|
|
"num_tokens": 419380.0,
|
|
"step": 240
|
|
},
|
|
{
|
|
"entropy": 7.91221809387207,
|
|
"epoch": 0.01906243921416067,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.000122,
|
|
"loss": 7.2983,
|
|
"mean_token_accuracy": 0.08029103949666024,
|
|
"num_tokens": 427682.0,
|
|
"step": 245
|
|
},
|
|
{
|
|
"entropy": 7.782497692108154,
|
|
"epoch": 0.019451468585878234,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0001245,
|
|
"loss": 7.3944,
|
|
"mean_token_accuracy": 0.07596049457788467,
|
|
"num_tokens": 437708.0,
|
|
"step": 250
|
|
},
|
|
{
|
|
"entropy": 7.839935350418091,
|
|
"epoch": 0.0198404979575958,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.000127,
|
|
"loss": 7.3625,
|
|
"mean_token_accuracy": 0.08329648077487946,
|
|
"num_tokens": 446480.0,
|
|
"step": 255
|
|
},
|
|
{
|
|
"entropy": 7.786860942840576,
|
|
"epoch": 0.020229527329313362,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0001295,
|
|
"loss": 7.3896,
|
|
"mean_token_accuracy": 0.0760398305952549,
|
|
"num_tokens": 455273.0,
|
|
"step": 260
|
|
},
|
|
{
|
|
"entropy": 7.816596269607544,
|
|
"epoch": 0.020618556701030927,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.000132,
|
|
"loss": 7.308,
|
|
"mean_token_accuracy": 0.08219457417726517,
|
|
"num_tokens": 464306.0,
|
|
"step": 265
|
|
},
|
|
{
|
|
"entropy": 7.677759218215942,
|
|
"epoch": 0.021007586072748493,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00013450000000000002,
|
|
"loss": 7.3139,
|
|
"mean_token_accuracy": 0.0749464474618435,
|
|
"num_tokens": 472812.0,
|
|
"step": 270
|
|
},
|
|
{
|
|
"entropy": 7.768700742721558,
|
|
"epoch": 0.02139661544446606,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00013700000000000002,
|
|
"loss": 7.2851,
|
|
"mean_token_accuracy": 0.08093390390276908,
|
|
"num_tokens": 481326.0,
|
|
"step": 275
|
|
},
|
|
{
|
|
"entropy": 7.76422529220581,
|
|
"epoch": 0.02178564481618362,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0001395,
|
|
"loss": 7.2397,
|
|
"mean_token_accuracy": 0.08092119097709656,
|
|
"num_tokens": 489147.0,
|
|
"step": 280
|
|
},
|
|
{
|
|
"entropy": 7.733962726593018,
|
|
"epoch": 0.022174674187901186,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00014199999999999998,
|
|
"loss": 7.2303,
|
|
"mean_token_accuracy": 0.08891455829143524,
|
|
"num_tokens": 497455.0,
|
|
"step": 285
|
|
},
|
|
{
|
|
"entropy": 7.637256097793579,
|
|
"epoch": 0.02256370355961875,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0001445,
|
|
"loss": 7.1567,
|
|
"mean_token_accuracy": 0.08741839975118637,
|
|
"num_tokens": 506735.0,
|
|
"step": 290
|
|
},
|
|
{
|
|
"entropy": 7.682271909713745,
|
|
"epoch": 0.022952732931336317,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.000147,
|
|
"loss": 7.2384,
|
|
"mean_token_accuracy": 0.08303680419921874,
|
|
"num_tokens": 515976.0,
|
|
"step": 295
|
|
},
|
|
{
|
|
"entropy": 7.649052429199219,
|
|
"epoch": 0.02334176230305388,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0001495,
|
|
"loss": 7.2294,
|
|
"mean_token_accuracy": 0.08583831116557121,
|
|
"num_tokens": 524986.0,
|
|
"step": 300
|
|
},
|
|
{
|
|
"entropy": 7.687331056594848,
|
|
"epoch": 0.023730791674771445,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.000152,
|
|
"loss": 7.2415,
|
|
"mean_token_accuracy": 0.09258508980274201,
|
|
"num_tokens": 533146.0,
|
|
"step": 305
|
|
},
|
|
{
|
|
"entropy": 7.660231113433838,
|
|
"epoch": 0.02411982104648901,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00015450000000000001,
|
|
"loss": 7.1305,
|
|
"mean_token_accuracy": 0.09208664670586586,
|
|
"num_tokens": 541704.0,
|
|
"step": 310
|
|
},
|
|
{
|
|
"entropy": 7.569728803634644,
|
|
"epoch": 0.024508850418206576,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.000157,
|
|
"loss": 7.1132,
|
|
"mean_token_accuracy": 0.09219249933958054,
|
|
"num_tokens": 550088.0,
|
|
"step": 315
|
|
},
|
|
{
|
|
"entropy": 7.553810167312622,
|
|
"epoch": 0.024897879789924138,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0001595,
|
|
"loss": 7.1116,
|
|
"mean_token_accuracy": 0.08964145854115486,
|
|
"num_tokens": 558763.0,
|
|
"step": 320
|
|
},
|
|
{
|
|
"entropy": 7.644041442871094,
|
|
"epoch": 0.025286909161641703,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000162,
|
|
"loss": 7.2054,
|
|
"mean_token_accuracy": 0.08601472824811936,
|
|
"num_tokens": 567538.0,
|
|
"step": 325
|
|
},
|
|
{
|
|
"entropy": 7.581082773208618,
|
|
"epoch": 0.02567593853335927,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00016450000000000001,
|
|
"loss": 7.2187,
|
|
"mean_token_accuracy": 0.0808300495147705,
|
|
"num_tokens": 577626.0,
|
|
"step": 330
|
|
},
|
|
{
|
|
"entropy": 7.481959867477417,
|
|
"epoch": 0.026064967905076834,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00016700000000000002,
|
|
"loss": 7.1528,
|
|
"mean_token_accuracy": 0.08528566733002663,
|
|
"num_tokens": 587163.0,
|
|
"step": 335
|
|
},
|
|
{
|
|
"entropy": 7.5628759384155275,
|
|
"epoch": 0.026453997276794396,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00016950000000000003,
|
|
"loss": 7.1352,
|
|
"mean_token_accuracy": 0.08886056169867515,
|
|
"num_tokens": 595896.0,
|
|
"step": 340
|
|
},
|
|
{
|
|
"entropy": 7.6669008255004885,
|
|
"epoch": 0.026843026648511962,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00017199999999999998,
|
|
"loss": 7.1495,
|
|
"mean_token_accuracy": 0.08720074668526649,
|
|
"num_tokens": 603815.0,
|
|
"step": 345
|
|
},
|
|
{
|
|
"entropy": 7.511917448043823,
|
|
"epoch": 0.027232056020229527,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00017449999999999999,
|
|
"loss": 7.1631,
|
|
"mean_token_accuracy": 0.09270136058330536,
|
|
"num_tokens": 612208.0,
|
|
"step": 350
|
|
},
|
|
{
|
|
"entropy": 7.517125844955444,
|
|
"epoch": 0.027621085391947093,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000177,
|
|
"loss": 7.1271,
|
|
"mean_token_accuracy": 0.09068955928087234,
|
|
"num_tokens": 621840.0,
|
|
"step": 355
|
|
},
|
|
{
|
|
"entropy": 7.542174816131592,
|
|
"epoch": 0.028010114763664655,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0001795,
|
|
"loss": 7.1365,
|
|
"mean_token_accuracy": 0.0883019782602787,
|
|
"num_tokens": 630770.0,
|
|
"step": 360
|
|
},
|
|
{
|
|
"entropy": 7.5013352394104,
|
|
"epoch": 0.02839914413538222,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000182,
|
|
"loss": 7.1354,
|
|
"mean_token_accuracy": 0.08821968138217925,
|
|
"num_tokens": 640313.0,
|
|
"step": 365
|
|
},
|
|
{
|
|
"entropy": 7.581635475158691,
|
|
"epoch": 0.028788173507099786,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0001845,
|
|
"loss": 7.1571,
|
|
"mean_token_accuracy": 0.09343784376978874,
|
|
"num_tokens": 648594.0,
|
|
"step": 370
|
|
},
|
|
{
|
|
"entropy": 7.465378761291504,
|
|
"epoch": 0.02917720287881735,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.000187,
|
|
"loss": 7.1645,
|
|
"mean_token_accuracy": 0.09112582504749298,
|
|
"num_tokens": 656478.0,
|
|
"step": 375
|
|
},
|
|
{
|
|
"entropy": 7.526745271682739,
|
|
"epoch": 0.029566232250534917,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0001895,
|
|
"loss": 7.1162,
|
|
"mean_token_accuracy": 0.09759116843342781,
|
|
"num_tokens": 665405.0,
|
|
"step": 380
|
|
},
|
|
{
|
|
"entropy": 7.474437618255616,
|
|
"epoch": 0.02995526162225248,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.000192,
|
|
"loss": 7.1315,
|
|
"mean_token_accuracy": 0.09043080434203148,
|
|
"num_tokens": 674301.0,
|
|
"step": 385
|
|
},
|
|
{
|
|
"entropy": 7.500934886932373,
|
|
"epoch": 0.030344290993970045,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0001945,
|
|
"loss": 7.1395,
|
|
"mean_token_accuracy": 0.09345336705446243,
|
|
"num_tokens": 683159.0,
|
|
"step": 390
|
|
},
|
|
{
|
|
"entropy": 7.383391237258911,
|
|
"epoch": 0.03073332036568761,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00019700000000000002,
|
|
"loss": 6.9546,
|
|
"mean_token_accuracy": 0.09936677888035775,
|
|
"num_tokens": 690992.0,
|
|
"step": 395
|
|
},
|
|
{
|
|
"entropy": 7.346968412399292,
|
|
"epoch": 0.031122349737405176,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00019950000000000002,
|
|
"loss": 7.0703,
|
|
"mean_token_accuracy": 0.09284654334187507,
|
|
"num_tokens": 699934.0,
|
|
"step": 400
|
|
},
|
|
{
|
|
"entropy": 7.553390264511108,
|
|
"epoch": 0.03151137910912274,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.000202,
|
|
"loss": 7.1035,
|
|
"mean_token_accuracy": 0.09367862120270729,
|
|
"num_tokens": 708844.0,
|
|
"step": 405
|
|
},
|
|
{
|
|
"entropy": 7.4107770919799805,
|
|
"epoch": 0.0319004084808403,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00020449999999999998,
|
|
"loss": 7.1629,
|
|
"mean_token_accuracy": 0.08833086043596268,
|
|
"num_tokens": 718148.0,
|
|
"step": 410
|
|
},
|
|
{
|
|
"entropy": 7.559677696228027,
|
|
"epoch": 0.03228943785255787,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.000207,
|
|
"loss": 7.0958,
|
|
"mean_token_accuracy": 0.08757410496473313,
|
|
"num_tokens": 726859.0,
|
|
"step": 415
|
|
},
|
|
{
|
|
"entropy": 7.36133918762207,
|
|
"epoch": 0.032678467224275434,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0002095,
|
|
"loss": 7.1026,
|
|
"mean_token_accuracy": 0.09037772119045258,
|
|
"num_tokens": 735045.0,
|
|
"step": 420
|
|
},
|
|
{
|
|
"entropy": 7.265546607971191,
|
|
"epoch": 0.033067496595993,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000212,
|
|
"loss": 6.9826,
|
|
"mean_token_accuracy": 0.0958486907184124,
|
|
"num_tokens": 743538.0,
|
|
"step": 425
|
|
},
|
|
{
|
|
"entropy": 7.454471921920776,
|
|
"epoch": 0.033456525967710565,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0002145,
|
|
"loss": 7.017,
|
|
"mean_token_accuracy": 0.09482243955135346,
|
|
"num_tokens": 752518.0,
|
|
"step": 430
|
|
},
|
|
{
|
|
"entropy": 7.29300708770752,
|
|
"epoch": 0.033845555339428124,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00021700000000000002,
|
|
"loss": 7.0525,
|
|
"mean_token_accuracy": 0.09259525015950203,
|
|
"num_tokens": 760354.0,
|
|
"step": 435
|
|
},
|
|
{
|
|
"entropy": 7.4215178966522215,
|
|
"epoch": 0.03423458471114569,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0002195,
|
|
"loss": 7.1053,
|
|
"mean_token_accuracy": 0.09021464213728905,
|
|
"num_tokens": 769522.0,
|
|
"step": 440
|
|
},
|
|
{
|
|
"entropy": 7.375669765472412,
|
|
"epoch": 0.034623614082863255,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.000222,
|
|
"loss": 7.023,
|
|
"mean_token_accuracy": 0.09649827480316162,
|
|
"num_tokens": 778548.0,
|
|
"step": 445
|
|
},
|
|
{
|
|
"entropy": 7.265977478027343,
|
|
"epoch": 0.03501264345458082,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0002245,
|
|
"loss": 7.0381,
|
|
"mean_token_accuracy": 0.09258587285876274,
|
|
"num_tokens": 787666.0,
|
|
"step": 450
|
|
},
|
|
{
|
|
"entropy": 7.404888343811035,
|
|
"epoch": 0.035401672826298386,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00022700000000000002,
|
|
"loss": 6.9548,
|
|
"mean_token_accuracy": 0.09554951265454292,
|
|
"num_tokens": 796550.0,
|
|
"step": 455
|
|
},
|
|
{
|
|
"entropy": 7.379618072509766,
|
|
"epoch": 0.03579070219801595,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.00022950000000000002,
|
|
"loss": 7.0295,
|
|
"mean_token_accuracy": 0.09436309635639191,
|
|
"num_tokens": 804549.0,
|
|
"step": 460
|
|
},
|
|
{
|
|
"entropy": 7.194296884536743,
|
|
"epoch": 0.03617973156973352,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00023200000000000003,
|
|
"loss": 7.0004,
|
|
"mean_token_accuracy": 0.09524615257978439,
|
|
"num_tokens": 813328.0,
|
|
"step": 465
|
|
},
|
|
{
|
|
"entropy": 7.384324455261231,
|
|
"epoch": 0.03656876094145108,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00023449999999999998,
|
|
"loss": 7.0326,
|
|
"mean_token_accuracy": 0.09230693653225899,
|
|
"num_tokens": 821733.0,
|
|
"step": 470
|
|
},
|
|
{
|
|
"entropy": 7.3139783382415775,
|
|
"epoch": 0.03695779031316864,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000237,
|
|
"loss": 6.9669,
|
|
"mean_token_accuracy": 0.09483846426010131,
|
|
"num_tokens": 830243.0,
|
|
"step": 475
|
|
},
|
|
{
|
|
"entropy": 7.309220647811889,
|
|
"epoch": 0.03734681968488621,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0002395,
|
|
"loss": 6.9553,
|
|
"mean_token_accuracy": 0.09212375655770302,
|
|
"num_tokens": 839059.0,
|
|
"step": 480
|
|
},
|
|
{
|
|
"entropy": 7.19914059638977,
|
|
"epoch": 0.03773584905660377,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000242,
|
|
"loss": 6.8376,
|
|
"mean_token_accuracy": 0.10036729499697686,
|
|
"num_tokens": 846932.0,
|
|
"step": 485
|
|
},
|
|
{
|
|
"entropy": 7.361199140548706,
|
|
"epoch": 0.03812487842832134,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0002445,
|
|
"loss": 7.0514,
|
|
"mean_token_accuracy": 0.08944635763764382,
|
|
"num_tokens": 855333.0,
|
|
"step": 490
|
|
},
|
|
{
|
|
"entropy": 7.1707884788513185,
|
|
"epoch": 0.0385139078000389,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.000247,
|
|
"loss": 6.809,
|
|
"mean_token_accuracy": 0.09626470431685448,
|
|
"num_tokens": 863571.0,
|
|
"step": 495
|
|
},
|
|
{
|
|
"entropy": 7.152101230621338,
|
|
"epoch": 0.03890293717175647,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0002495,
|
|
"loss": 6.8996,
|
|
"mean_token_accuracy": 0.10517843365669251,
|
|
"num_tokens": 872145.0,
|
|
"step": 500
|
|
},
|
|
{
|
|
"entropy": 7.187833833694458,
|
|
"epoch": 0.039291966543474034,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000252,
|
|
"loss": 6.9394,
|
|
"mean_token_accuracy": 0.09892025515437126,
|
|
"num_tokens": 880634.0,
|
|
"step": 505
|
|
},
|
|
{
|
|
"entropy": 7.235556554794312,
|
|
"epoch": 0.0396809959151916,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0002545,
|
|
"loss": 6.8712,
|
|
"mean_token_accuracy": 0.09984394237399101,
|
|
"num_tokens": 889178.0,
|
|
"step": 510
|
|
},
|
|
{
|
|
"entropy": 7.149497556686401,
|
|
"epoch": 0.04007002528690916,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.000257,
|
|
"loss": 6.885,
|
|
"mean_token_accuracy": 0.09859361201524734,
|
|
"num_tokens": 898255.0,
|
|
"step": 515
|
|
},
|
|
{
|
|
"entropy": 7.130793571472168,
|
|
"epoch": 0.040459054658626724,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0002595,
|
|
"loss": 6.9412,
|
|
"mean_token_accuracy": 0.08988485783338547,
|
|
"num_tokens": 907369.0,
|
|
"step": 520
|
|
},
|
|
{
|
|
"entropy": 7.193523645401001,
|
|
"epoch": 0.04084808403034429,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.000262,
|
|
"loss": 6.8381,
|
|
"mean_token_accuracy": 0.0956579439342022,
|
|
"num_tokens": 915946.0,
|
|
"step": 525
|
|
},
|
|
{
|
|
"entropy": 7.214367437362671,
|
|
"epoch": 0.041237113402061855,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00026450000000000003,
|
|
"loss": 6.8968,
|
|
"mean_token_accuracy": 0.09464456140995026,
|
|
"num_tokens": 925579.0,
|
|
"step": 530
|
|
},
|
|
{
|
|
"entropy": 7.194347190856933,
|
|
"epoch": 0.04162614277377942,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00026700000000000004,
|
|
"loss": 6.8929,
|
|
"mean_token_accuracy": 0.09103822857141494,
|
|
"num_tokens": 934732.0,
|
|
"step": 535
|
|
},
|
|
{
|
|
"entropy": 7.1877021312713625,
|
|
"epoch": 0.042015172145496986,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00026950000000000005,
|
|
"loss": 6.9548,
|
|
"mean_token_accuracy": 0.09189340770244599,
|
|
"num_tokens": 943371.0,
|
|
"step": 540
|
|
},
|
|
{
|
|
"entropy": 7.129611682891846,
|
|
"epoch": 0.04240420151721455,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00027200000000000005,
|
|
"loss": 6.7935,
|
|
"mean_token_accuracy": 0.09684587121009827,
|
|
"num_tokens": 951977.0,
|
|
"step": 545
|
|
},
|
|
{
|
|
"entropy": 7.075324392318725,
|
|
"epoch": 0.04279323088893212,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0002745,
|
|
"loss": 6.7956,
|
|
"mean_token_accuracy": 0.09852224737405776,
|
|
"num_tokens": 960474.0,
|
|
"step": 550
|
|
},
|
|
{
|
|
"entropy": 7.242029809951783,
|
|
"epoch": 0.04318226026064968,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000277,
|
|
"loss": 6.921,
|
|
"mean_token_accuracy": 0.09615759328007698,
|
|
"num_tokens": 969823.0,
|
|
"step": 555
|
|
},
|
|
{
|
|
"entropy": 7.148642349243164,
|
|
"epoch": 0.04357128963236724,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0002795,
|
|
"loss": 6.8541,
|
|
"mean_token_accuracy": 0.10372538045048714,
|
|
"num_tokens": 977417.0,
|
|
"step": 560
|
|
},
|
|
{
|
|
"entropy": 7.050511121749878,
|
|
"epoch": 0.04396031900408481,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00028199999999999997,
|
|
"loss": 6.8525,
|
|
"mean_token_accuracy": 0.10765723884105682,
|
|
"num_tokens": 985519.0,
|
|
"step": 565
|
|
},
|
|
{
|
|
"entropy": 7.106280851364136,
|
|
"epoch": 0.04434934837580237,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0002845,
|
|
"loss": 6.8486,
|
|
"mean_token_accuracy": 0.10191520527005196,
|
|
"num_tokens": 994136.0,
|
|
"step": 570
|
|
},
|
|
{
|
|
"entropy": 7.03365535736084,
|
|
"epoch": 0.04473837774751994,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.000287,
|
|
"loss": 6.8207,
|
|
"mean_token_accuracy": 0.09769327566027641,
|
|
"num_tokens": 1002896.0,
|
|
"step": 575
|
|
},
|
|
{
|
|
"entropy": 7.198338603973388,
|
|
"epoch": 0.0451274071192375,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0002895,
|
|
"loss": 6.9061,
|
|
"mean_token_accuracy": 0.10421423837542534,
|
|
"num_tokens": 1011032.0,
|
|
"step": 580
|
|
},
|
|
{
|
|
"entropy": 7.051746559143067,
|
|
"epoch": 0.04551643649095507,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000292,
|
|
"loss": 6.8708,
|
|
"mean_token_accuracy": 0.09394787698984146,
|
|
"num_tokens": 1019901.0,
|
|
"step": 585
|
|
},
|
|
{
|
|
"entropy": 7.067822074890136,
|
|
"epoch": 0.045905465862672634,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0002945,
|
|
"loss": 6.8482,
|
|
"mean_token_accuracy": 0.09919805154204368,
|
|
"num_tokens": 1029049.0,
|
|
"step": 590
|
|
},
|
|
{
|
|
"entropy": 6.9990034103393555,
|
|
"epoch": 0.0462944952343902,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000297,
|
|
"loss": 6.8086,
|
|
"mean_token_accuracy": 0.10822348445653915,
|
|
"num_tokens": 1037580.0,
|
|
"step": 595
|
|
},
|
|
{
|
|
"entropy": 7.196728610992432,
|
|
"epoch": 0.04668352460610776,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0002995,
|
|
"loss": 6.8679,
|
|
"mean_token_accuracy": 0.10288131684064865,
|
|
"num_tokens": 1045804.0,
|
|
"step": 600
|
|
},
|
|
{
|
|
"entropy": 7.0782746315002445,
|
|
"epoch": 0.047072553977825324,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000302,
|
|
"loss": 6.8362,
|
|
"mean_token_accuracy": 0.09710147231817245,
|
|
"num_tokens": 1054719.0,
|
|
"step": 605
|
|
},
|
|
{
|
|
"entropy": 7.09404673576355,
|
|
"epoch": 0.04746158334954289,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0003045,
|
|
"loss": 6.8149,
|
|
"mean_token_accuracy": 0.1012077234685421,
|
|
"num_tokens": 1063373.0,
|
|
"step": 610
|
|
},
|
|
{
|
|
"entropy": 6.984814739227295,
|
|
"epoch": 0.047850612721260455,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000307,
|
|
"loss": 6.8058,
|
|
"mean_token_accuracy": 0.10036636292934417,
|
|
"num_tokens": 1073021.0,
|
|
"step": 615
|
|
},
|
|
{
|
|
"entropy": 7.0786560535430905,
|
|
"epoch": 0.04823964209297802,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0003095,
|
|
"loss": 6.8696,
|
|
"mean_token_accuracy": 0.09600509628653527,
|
|
"num_tokens": 1081547.0,
|
|
"step": 620
|
|
},
|
|
{
|
|
"entropy": 7.0220740795135494,
|
|
"epoch": 0.048628671464695586,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000312,
|
|
"loss": 6.8233,
|
|
"mean_token_accuracy": 0.09918136522173882,
|
|
"num_tokens": 1090695.0,
|
|
"step": 625
|
|
},
|
|
{
|
|
"entropy": 6.9606041431427,
|
|
"epoch": 0.04901770083641315,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0003145,
|
|
"loss": 6.7198,
|
|
"mean_token_accuracy": 0.10607226341962814,
|
|
"num_tokens": 1099563.0,
|
|
"step": 630
|
|
},
|
|
{
|
|
"entropy": 7.042634630203247,
|
|
"epoch": 0.04940673020813072,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000317,
|
|
"loss": 6.8025,
|
|
"mean_token_accuracy": 0.09708617925643921,
|
|
"num_tokens": 1109021.0,
|
|
"step": 635
|
|
},
|
|
{
|
|
"entropy": 7.036008024215699,
|
|
"epoch": 0.049795759579848276,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0003195,
|
|
"loss": 6.7915,
|
|
"mean_token_accuracy": 0.10409486815333366,
|
|
"num_tokens": 1118281.0,
|
|
"step": 640
|
|
},
|
|
{
|
|
"entropy": 7.0259270668029785,
|
|
"epoch": 0.05018478895156584,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000322,
|
|
"loss": 6.8364,
|
|
"mean_token_accuracy": 0.09575799703598023,
|
|
"num_tokens": 1127513.0,
|
|
"step": 645
|
|
},
|
|
{
|
|
"entropy": 6.843554496765137,
|
|
"epoch": 0.05057381832328341,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00032450000000000003,
|
|
"loss": 6.7179,
|
|
"mean_token_accuracy": 0.10220488980412483,
|
|
"num_tokens": 1136140.0,
|
|
"step": 650
|
|
},
|
|
{
|
|
"entropy": 7.010839796066284,
|
|
"epoch": 0.05096284769500097,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00032700000000000003,
|
|
"loss": 6.7449,
|
|
"mean_token_accuracy": 0.10034143850207329,
|
|
"num_tokens": 1144297.0,
|
|
"step": 655
|
|
},
|
|
{
|
|
"entropy": 7.005735111236572,
|
|
"epoch": 0.05135187706671854,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00032950000000000004,
|
|
"loss": 6.8315,
|
|
"mean_token_accuracy": 0.09598958343267441,
|
|
"num_tokens": 1153639.0,
|
|
"step": 660
|
|
},
|
|
{
|
|
"entropy": 7.042137622833252,
|
|
"epoch": 0.0517409064384361,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00033200000000000005,
|
|
"loss": 6.8044,
|
|
"mean_token_accuracy": 0.09692039787769317,
|
|
"num_tokens": 1162825.0,
|
|
"step": 665
|
|
},
|
|
{
|
|
"entropy": 6.893413639068603,
|
|
"epoch": 0.05212993581015367,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00033450000000000005,
|
|
"loss": 6.8242,
|
|
"mean_token_accuracy": 0.10342787951231003,
|
|
"num_tokens": 1171887.0,
|
|
"step": 670
|
|
},
|
|
{
|
|
"entropy": 6.990288639068604,
|
|
"epoch": 0.052518965181871234,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.000337,
|
|
"loss": 6.723,
|
|
"mean_token_accuracy": 0.10218419954180717,
|
|
"num_tokens": 1179963.0,
|
|
"step": 675
|
|
},
|
|
{
|
|
"entropy": 6.915320777893067,
|
|
"epoch": 0.05290799455358879,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0003395,
|
|
"loss": 6.6987,
|
|
"mean_token_accuracy": 0.10984139442443848,
|
|
"num_tokens": 1188408.0,
|
|
"step": 680
|
|
},
|
|
{
|
|
"entropy": 6.944253206253052,
|
|
"epoch": 0.05329702392530636,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000342,
|
|
"loss": 6.7404,
|
|
"mean_token_accuracy": 0.09963250234723091,
|
|
"num_tokens": 1197751.0,
|
|
"step": 685
|
|
},
|
|
{
|
|
"entropy": 6.910943222045899,
|
|
"epoch": 0.053686053297023924,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00034449999999999997,
|
|
"loss": 6.8019,
|
|
"mean_token_accuracy": 0.10173860564827919,
|
|
"num_tokens": 1207101.0,
|
|
"step": 690
|
|
},
|
|
{
|
|
"entropy": 6.96247820854187,
|
|
"epoch": 0.05407508266874149,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000347,
|
|
"loss": 6.7768,
|
|
"mean_token_accuracy": 0.10386782586574554,
|
|
"num_tokens": 1216395.0,
|
|
"step": 695
|
|
},
|
|
{
|
|
"entropy": 6.914447498321533,
|
|
"epoch": 0.054464112040459055,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0003495,
|
|
"loss": 6.7579,
|
|
"mean_token_accuracy": 0.10488244742155076,
|
|
"num_tokens": 1225496.0,
|
|
"step": 700
|
|
},
|
|
{
|
|
"entropy": 6.9863011837005615,
|
|
"epoch": 0.05485314141217662,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000352,
|
|
"loss": 6.8255,
|
|
"mean_token_accuracy": 0.10280769392848015,
|
|
"num_tokens": 1233934.0,
|
|
"step": 705
|
|
},
|
|
{
|
|
"entropy": 6.947722387313843,
|
|
"epoch": 0.055242170783894186,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0003545,
|
|
"loss": 6.6909,
|
|
"mean_token_accuracy": 0.10623404085636139,
|
|
"num_tokens": 1242165.0,
|
|
"step": 710
|
|
},
|
|
{
|
|
"entropy": 6.864742231369019,
|
|
"epoch": 0.05563120015561175,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.000357,
|
|
"loss": 6.7451,
|
|
"mean_token_accuracy": 0.10805843472480774,
|
|
"num_tokens": 1250021.0,
|
|
"step": 715
|
|
},
|
|
{
|
|
"entropy": 6.967834186553955,
|
|
"epoch": 0.05602022952732931,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0003595,
|
|
"loss": 6.7789,
|
|
"mean_token_accuracy": 0.1014004610478878,
|
|
"num_tokens": 1258397.0,
|
|
"step": 720
|
|
},
|
|
{
|
|
"entropy": 6.895936393737793,
|
|
"epoch": 0.056409258899046875,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000362,
|
|
"loss": 6.7594,
|
|
"mean_token_accuracy": 0.10026679039001465,
|
|
"num_tokens": 1266764.0,
|
|
"step": 725
|
|
},
|
|
{
|
|
"entropy": 6.976710271835327,
|
|
"epoch": 0.05679828827076444,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0003645,
|
|
"loss": 6.7604,
|
|
"mean_token_accuracy": 0.10308134779334069,
|
|
"num_tokens": 1275643.0,
|
|
"step": 730
|
|
},
|
|
{
|
|
"entropy": 6.854802751541138,
|
|
"epoch": 0.057187317642482006,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000367,
|
|
"loss": 6.7414,
|
|
"mean_token_accuracy": 0.10123410001397133,
|
|
"num_tokens": 1284379.0,
|
|
"step": 735
|
|
},
|
|
{
|
|
"entropy": 6.858791494369507,
|
|
"epoch": 0.05757634701419957,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0003695,
|
|
"loss": 6.5942,
|
|
"mean_token_accuracy": 0.10925214067101478,
|
|
"num_tokens": 1293115.0,
|
|
"step": 740
|
|
},
|
|
{
|
|
"entropy": 6.892751264572143,
|
|
"epoch": 0.05796537638591714,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.000372,
|
|
"loss": 6.796,
|
|
"mean_token_accuracy": 0.09836092367768287,
|
|
"num_tokens": 1301583.0,
|
|
"step": 745
|
|
},
|
|
{
|
|
"entropy": 6.954816818237305,
|
|
"epoch": 0.0583544057576347,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0003745,
|
|
"loss": 6.7001,
|
|
"mean_token_accuracy": 0.10808140113949775,
|
|
"num_tokens": 1310721.0,
|
|
"step": 750
|
|
},
|
|
{
|
|
"entropy": 6.923498821258545,
|
|
"epoch": 0.05874343512935227,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.000377,
|
|
"loss": 6.8595,
|
|
"mean_token_accuracy": 0.09595380201935769,
|
|
"num_tokens": 1319056.0,
|
|
"step": 755
|
|
},
|
|
{
|
|
"entropy": 6.839234256744385,
|
|
"epoch": 0.059132464501069834,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0003795,
|
|
"loss": 6.7416,
|
|
"mean_token_accuracy": 0.10261751636862755,
|
|
"num_tokens": 1327259.0,
|
|
"step": 760
|
|
},
|
|
{
|
|
"entropy": 6.819512987136841,
|
|
"epoch": 0.05952149387278739,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.000382,
|
|
"loss": 6.6414,
|
|
"mean_token_accuracy": 0.10097026452422142,
|
|
"num_tokens": 1335906.0,
|
|
"step": 765
|
|
},
|
|
{
|
|
"entropy": 6.879472923278809,
|
|
"epoch": 0.05991052324450496,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0003845,
|
|
"loss": 6.6938,
|
|
"mean_token_accuracy": 0.09806213229894638,
|
|
"num_tokens": 1344743.0,
|
|
"step": 770
|
|
},
|
|
{
|
|
"entropy": 6.840222930908203,
|
|
"epoch": 0.060299552616222524,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00038700000000000003,
|
|
"loss": 6.6834,
|
|
"mean_token_accuracy": 0.10951419249176979,
|
|
"num_tokens": 1353211.0,
|
|
"step": 775
|
|
},
|
|
{
|
|
"entropy": 6.946290063858032,
|
|
"epoch": 0.06068858198794009,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00038950000000000003,
|
|
"loss": 6.812,
|
|
"mean_token_accuracy": 0.10016649737954139,
|
|
"num_tokens": 1361849.0,
|
|
"step": 780
|
|
},
|
|
{
|
|
"entropy": 6.8946840286254885,
|
|
"epoch": 0.061077611359657655,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.00039200000000000004,
|
|
"loss": 6.7945,
|
|
"mean_token_accuracy": 0.10707032829523086,
|
|
"num_tokens": 1369804.0,
|
|
"step": 785
|
|
},
|
|
{
|
|
"entropy": 6.7396095275878904,
|
|
"epoch": 0.06146664073137522,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00039450000000000005,
|
|
"loss": 6.5766,
|
|
"mean_token_accuracy": 0.10397438257932663,
|
|
"num_tokens": 1378478.0,
|
|
"step": 790
|
|
},
|
|
{
|
|
"entropy": 6.9116943359375,
|
|
"epoch": 0.061855670103092786,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00039700000000000005,
|
|
"loss": 6.6789,
|
|
"mean_token_accuracy": 0.10764730274677277,
|
|
"num_tokens": 1387225.0,
|
|
"step": 795
|
|
},
|
|
{
|
|
"entropy": 6.7650645732879635,
|
|
"epoch": 0.06224469947481035,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0003995,
|
|
"loss": 6.6492,
|
|
"mean_token_accuracy": 0.10592131912708283,
|
|
"num_tokens": 1395338.0,
|
|
"step": 800
|
|
},
|
|
{
|
|
"entropy": 6.821805953979492,
|
|
"epoch": 0.06263372884652792,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000402,
|
|
"loss": 6.63,
|
|
"mean_token_accuracy": 0.10603216290473938,
|
|
"num_tokens": 1403794.0,
|
|
"step": 805
|
|
},
|
|
{
|
|
"entropy": 6.708382701873779,
|
|
"epoch": 0.06302275821824548,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004045,
|
|
"loss": 6.7133,
|
|
"mean_token_accuracy": 0.10304158627986908,
|
|
"num_tokens": 1412522.0,
|
|
"step": 810
|
|
},
|
|
{
|
|
"entropy": 6.788723707199097,
|
|
"epoch": 0.06341178758996305,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00040699999999999997,
|
|
"loss": 6.6937,
|
|
"mean_token_accuracy": 0.10893446058034897,
|
|
"num_tokens": 1421347.0,
|
|
"step": 815
|
|
},
|
|
{
|
|
"entropy": 6.8365006923675535,
|
|
"epoch": 0.0638008169616806,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004095,
|
|
"loss": 6.6695,
|
|
"mean_token_accuracy": 0.11350144445896149,
|
|
"num_tokens": 1429788.0,
|
|
"step": 820
|
|
},
|
|
{
|
|
"entropy": 6.760780572891235,
|
|
"epoch": 0.06418984633339817,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.000412,
|
|
"loss": 6.6727,
|
|
"mean_token_accuracy": 0.10774989053606987,
|
|
"num_tokens": 1437442.0,
|
|
"step": 825
|
|
},
|
|
{
|
|
"entropy": 6.757859325408935,
|
|
"epoch": 0.06457887570511574,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004145,
|
|
"loss": 6.5954,
|
|
"mean_token_accuracy": 0.10944118574261666,
|
|
"num_tokens": 1445604.0,
|
|
"step": 830
|
|
},
|
|
{
|
|
"entropy": 6.786571073532104,
|
|
"epoch": 0.0649679050768333,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000417,
|
|
"loss": 6.6634,
|
|
"mean_token_accuracy": 0.1089187815785408,
|
|
"num_tokens": 1454342.0,
|
|
"step": 835
|
|
},
|
|
{
|
|
"entropy": 6.77791576385498,
|
|
"epoch": 0.06535693444855087,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004195,
|
|
"loss": 6.661,
|
|
"mean_token_accuracy": 0.11053230538964272,
|
|
"num_tokens": 1463189.0,
|
|
"step": 840
|
|
},
|
|
{
|
|
"entropy": 6.787366485595703,
|
|
"epoch": 0.06574596382026843,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000422,
|
|
"loss": 6.7166,
|
|
"mean_token_accuracy": 0.10734177976846696,
|
|
"num_tokens": 1471608.0,
|
|
"step": 845
|
|
},
|
|
{
|
|
"entropy": 6.799466276168824,
|
|
"epoch": 0.066134993191986,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004245,
|
|
"loss": 6.7296,
|
|
"mean_token_accuracy": 0.10613490417599677,
|
|
"num_tokens": 1480452.0,
|
|
"step": 850
|
|
},
|
|
{
|
|
"entropy": 6.822136163711548,
|
|
"epoch": 0.06652402256370356,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000427,
|
|
"loss": 6.6437,
|
|
"mean_token_accuracy": 0.10718747153878212,
|
|
"num_tokens": 1489118.0,
|
|
"step": 855
|
|
},
|
|
{
|
|
"entropy": 6.686193990707397,
|
|
"epoch": 0.06691305193542113,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004295,
|
|
"loss": 6.6342,
|
|
"mean_token_accuracy": 0.10919305682182312,
|
|
"num_tokens": 1498961.0,
|
|
"step": 860
|
|
},
|
|
{
|
|
"entropy": 6.819766521453857,
|
|
"epoch": 0.06730208130713869,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000432,
|
|
"loss": 6.6401,
|
|
"mean_token_accuracy": 0.11007228568196296,
|
|
"num_tokens": 1506772.0,
|
|
"step": 865
|
|
},
|
|
{
|
|
"entropy": 6.681567525863647,
|
|
"epoch": 0.06769111067885625,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004345,
|
|
"loss": 6.5275,
|
|
"mean_token_accuracy": 0.11715472564101219,
|
|
"num_tokens": 1515095.0,
|
|
"step": 870
|
|
},
|
|
{
|
|
"entropy": 6.6687061309814455,
|
|
"epoch": 0.06808014005057382,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000437,
|
|
"loss": 6.5653,
|
|
"mean_token_accuracy": 0.11424972265958785,
|
|
"num_tokens": 1523477.0,
|
|
"step": 875
|
|
},
|
|
{
|
|
"entropy": 6.689616775512695,
|
|
"epoch": 0.06846916942229138,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004395,
|
|
"loss": 6.6037,
|
|
"mean_token_accuracy": 0.10498946905136108,
|
|
"num_tokens": 1531786.0,
|
|
"step": 880
|
|
},
|
|
{
|
|
"entropy": 6.736538553237915,
|
|
"epoch": 0.06885819879400895,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000442,
|
|
"loss": 6.7016,
|
|
"mean_token_accuracy": 0.10352547094225883,
|
|
"num_tokens": 1540737.0,
|
|
"step": 885
|
|
},
|
|
{
|
|
"entropy": 6.637676811218261,
|
|
"epoch": 0.06924722816572651,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004445,
|
|
"loss": 6.5418,
|
|
"mean_token_accuracy": 0.1120985560119152,
|
|
"num_tokens": 1548923.0,
|
|
"step": 890
|
|
},
|
|
{
|
|
"entropy": 6.724155473709106,
|
|
"epoch": 0.06963625753744408,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.000447,
|
|
"loss": 6.5185,
|
|
"mean_token_accuracy": 0.11639119386672973,
|
|
"num_tokens": 1557043.0,
|
|
"step": 895
|
|
},
|
|
{
|
|
"entropy": 6.5780919075012205,
|
|
"epoch": 0.07002528690916164,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00044950000000000003,
|
|
"loss": 6.5535,
|
|
"mean_token_accuracy": 0.11611853837966919,
|
|
"num_tokens": 1564994.0,
|
|
"step": 900
|
|
},
|
|
{
|
|
"entropy": 6.693197536468506,
|
|
"epoch": 0.0704143162808792,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00045200000000000004,
|
|
"loss": 6.5559,
|
|
"mean_token_accuracy": 0.11024467647075653,
|
|
"num_tokens": 1573859.0,
|
|
"step": 905
|
|
},
|
|
{
|
|
"entropy": 6.661924743652344,
|
|
"epoch": 0.07080334565259677,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00045450000000000004,
|
|
"loss": 6.5138,
|
|
"mean_token_accuracy": 0.10926207825541497,
|
|
"num_tokens": 1581947.0,
|
|
"step": 910
|
|
},
|
|
{
|
|
"entropy": 6.66906771659851,
|
|
"epoch": 0.07119237502431433,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00045700000000000005,
|
|
"loss": 6.4995,
|
|
"mean_token_accuracy": 0.11228668987751007,
|
|
"num_tokens": 1589971.0,
|
|
"step": 915
|
|
},
|
|
{
|
|
"entropy": 6.555896234512329,
|
|
"epoch": 0.0715814043960319,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00045950000000000006,
|
|
"loss": 6.4518,
|
|
"mean_token_accuracy": 0.11207407787442207,
|
|
"num_tokens": 1598612.0,
|
|
"step": 920
|
|
},
|
|
{
|
|
"entropy": 6.718100690841675,
|
|
"epoch": 0.07197043376774946,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000462,
|
|
"loss": 6.6111,
|
|
"mean_token_accuracy": 0.10551391988992691,
|
|
"num_tokens": 1607378.0,
|
|
"step": 925
|
|
},
|
|
{
|
|
"entropy": 6.653341817855835,
|
|
"epoch": 0.07235946313946703,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004645,
|
|
"loss": 6.6081,
|
|
"mean_token_accuracy": 0.11038231924176216,
|
|
"num_tokens": 1615987.0,
|
|
"step": 930
|
|
},
|
|
{
|
|
"entropy": 6.486403131484986,
|
|
"epoch": 0.07274849251118459,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000467,
|
|
"loss": 6.4005,
|
|
"mean_token_accuracy": 0.11754591017961502,
|
|
"num_tokens": 1625366.0,
|
|
"step": 935
|
|
},
|
|
{
|
|
"entropy": 6.682313919067383,
|
|
"epoch": 0.07313752188290217,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004695,
|
|
"loss": 6.5758,
|
|
"mean_token_accuracy": 0.11200849413871765,
|
|
"num_tokens": 1633020.0,
|
|
"step": 940
|
|
},
|
|
{
|
|
"entropy": 6.592645740509033,
|
|
"epoch": 0.07352655125461972,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000472,
|
|
"loss": 6.4715,
|
|
"mean_token_accuracy": 0.11014393791556358,
|
|
"num_tokens": 1641518.0,
|
|
"step": 945
|
|
},
|
|
{
|
|
"entropy": 6.5744109630584715,
|
|
"epoch": 0.07391558062633728,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004745,
|
|
"loss": 6.5601,
|
|
"mean_token_accuracy": 0.1099576011300087,
|
|
"num_tokens": 1650472.0,
|
|
"step": 950
|
|
},
|
|
{
|
|
"entropy": 6.645666933059692,
|
|
"epoch": 0.07430460999805485,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000477,
|
|
"loss": 6.5753,
|
|
"mean_token_accuracy": 0.11195494011044502,
|
|
"num_tokens": 1659037.0,
|
|
"step": 955
|
|
},
|
|
{
|
|
"entropy": 6.697547388076782,
|
|
"epoch": 0.07469363936977241,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004795,
|
|
"loss": 6.6649,
|
|
"mean_token_accuracy": 0.11236765310168266,
|
|
"num_tokens": 1667897.0,
|
|
"step": 960
|
|
},
|
|
{
|
|
"entropy": 6.552785778045655,
|
|
"epoch": 0.07508266874148999,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000482,
|
|
"loss": 6.5075,
|
|
"mean_token_accuracy": 0.10858357399702072,
|
|
"num_tokens": 1676535.0,
|
|
"step": 965
|
|
},
|
|
{
|
|
"entropy": 6.665571069717407,
|
|
"epoch": 0.07547169811320754,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004845,
|
|
"loss": 6.5258,
|
|
"mean_token_accuracy": 0.11193247660994529,
|
|
"num_tokens": 1684415.0,
|
|
"step": 970
|
|
},
|
|
{
|
|
"entropy": 6.619773483276367,
|
|
"epoch": 0.07586072748492512,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000487,
|
|
"loss": 6.4873,
|
|
"mean_token_accuracy": 0.1161974124610424,
|
|
"num_tokens": 1692443.0,
|
|
"step": 975
|
|
},
|
|
{
|
|
"entropy": 6.469988203048706,
|
|
"epoch": 0.07624975685664268,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004895,
|
|
"loss": 6.4908,
|
|
"mean_token_accuracy": 0.11075597926974297,
|
|
"num_tokens": 1700814.0,
|
|
"step": 980
|
|
},
|
|
{
|
|
"entropy": 6.469910621643066,
|
|
"epoch": 0.07663878622836025,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000492,
|
|
"loss": 6.3349,
|
|
"mean_token_accuracy": 0.1179271623492241,
|
|
"num_tokens": 1709591.0,
|
|
"step": 985
|
|
},
|
|
{
|
|
"entropy": 6.605605697631836,
|
|
"epoch": 0.0770278156000778,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004945,
|
|
"loss": 6.5879,
|
|
"mean_token_accuracy": 0.10372007116675377,
|
|
"num_tokens": 1718951.0,
|
|
"step": 990
|
|
},
|
|
{
|
|
"entropy": 6.66983380317688,
|
|
"epoch": 0.07741684497179536,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000497,
|
|
"loss": 6.5431,
|
|
"mean_token_accuracy": 0.11147809475660324,
|
|
"num_tokens": 1727481.0,
|
|
"step": 995
|
|
},
|
|
{
|
|
"entropy": 6.5515549659729,
|
|
"epoch": 0.07780587434351294,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004995,
|
|
"loss": 6.5418,
|
|
"mean_token_accuracy": 0.11638221740722657,
|
|
"num_tokens": 1736985.0,
|
|
"step": 1000
|
|
},
|
|
{
|
|
"entropy": 6.616484832763672,
|
|
"epoch": 0.0781949037152305,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999999989075146,
|
|
"loss": 6.5945,
|
|
"mean_token_accuracy": 0.10921485722064972,
|
|
"num_tokens": 1745470.0,
|
|
"step": 1005
|
|
},
|
|
{
|
|
"entropy": 6.620965623855591,
|
|
"epoch": 0.07858393308694807,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004999999944692927,
|
|
"loss": 6.5176,
|
|
"mean_token_accuracy": 0.11291603669524193,
|
|
"num_tokens": 1754185.0,
|
|
"step": 1010
|
|
},
|
|
{
|
|
"entropy": 6.570215940475464,
|
|
"epoch": 0.07897296245866563,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000499999986617054,
|
|
"loss": 6.5153,
|
|
"mean_token_accuracy": 0.11022635996341705,
|
|
"num_tokens": 1762100.0,
|
|
"step": 1015
|
|
},
|
|
{
|
|
"entropy": 6.5821075439453125,
|
|
"epoch": 0.0793619918303832,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004999999753507986,
|
|
"loss": 6.5529,
|
|
"mean_token_accuracy": 0.11068348959088326,
|
|
"num_tokens": 1771070.0,
|
|
"step": 1020
|
|
},
|
|
{
|
|
"entropy": 6.546429920196533,
|
|
"epoch": 0.07975102120210076,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999999606705267,
|
|
"loss": 6.5267,
|
|
"mean_token_accuracy": 0.11509618312120437,
|
|
"num_tokens": 1780085.0,
|
|
"step": 1025
|
|
},
|
|
{
|
|
"entropy": 6.625613689422607,
|
|
"epoch": 0.08014005057381832,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999999425762385,
|
|
"loss": 6.5244,
|
|
"mean_token_accuracy": 0.11561840996146203,
|
|
"num_tokens": 1789316.0,
|
|
"step": 1030
|
|
},
|
|
{
|
|
"entropy": 6.537080764770508,
|
|
"epoch": 0.08052907994553589,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999999210679344,
|
|
"loss": 6.4437,
|
|
"mean_token_accuracy": 0.1176496423780918,
|
|
"num_tokens": 1797975.0,
|
|
"step": 1035
|
|
},
|
|
{
|
|
"entropy": 6.498772668838501,
|
|
"epoch": 0.08091810931725345,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999998961456145,
|
|
"loss": 6.5537,
|
|
"mean_token_accuracy": 0.11998764723539353,
|
|
"num_tokens": 1806129.0,
|
|
"step": 1040
|
|
},
|
|
{
|
|
"entropy": 6.631723117828369,
|
|
"epoch": 0.08130713868897102,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999998678092794,
|
|
"loss": 6.5327,
|
|
"mean_token_accuracy": 0.11050191894173622,
|
|
"num_tokens": 1813956.0,
|
|
"step": 1045
|
|
},
|
|
{
|
|
"entropy": 6.599989175796509,
|
|
"epoch": 0.08169616806068858,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999998360589293,
|
|
"loss": 6.5657,
|
|
"mean_token_accuracy": 0.11095986440777779,
|
|
"num_tokens": 1822572.0,
|
|
"step": 1050
|
|
},
|
|
{
|
|
"entropy": 6.480882072448731,
|
|
"epoch": 0.08208519743240615,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000499999800894565,
|
|
"loss": 6.4681,
|
|
"mean_token_accuracy": 0.11177131086587906,
|
|
"num_tokens": 1831870.0,
|
|
"step": 1055
|
|
},
|
|
{
|
|
"entropy": 6.47617883682251,
|
|
"epoch": 0.08247422680412371,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004999997623161866,
|
|
"loss": 6.5107,
|
|
"mean_token_accuracy": 0.1112887792289257,
|
|
"num_tokens": 1840414.0,
|
|
"step": 1060
|
|
},
|
|
{
|
|
"entropy": 6.575576829910278,
|
|
"epoch": 0.08286325617584128,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999997203237951,
|
|
"loss": 6.527,
|
|
"mean_token_accuracy": 0.1100434735417366,
|
|
"num_tokens": 1850385.0,
|
|
"step": 1065
|
|
},
|
|
{
|
|
"entropy": 6.428466129302978,
|
|
"epoch": 0.08325228554755884,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000499999674917391,
|
|
"loss": 6.4336,
|
|
"mean_token_accuracy": 0.12001706510782242,
|
|
"num_tokens": 1858479.0,
|
|
"step": 1070
|
|
},
|
|
{
|
|
"entropy": 6.507694816589355,
|
|
"epoch": 0.0836413149192764,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999996260969748,
|
|
"loss": 6.4857,
|
|
"mean_token_accuracy": 0.11208872050046921,
|
|
"num_tokens": 1867357.0,
|
|
"step": 1075
|
|
},
|
|
{
|
|
"entropy": 6.512378454208374,
|
|
"epoch": 0.08403034429099397,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004999995738625475,
|
|
"loss": 6.4521,
|
|
"mean_token_accuracy": 0.1077382005751133,
|
|
"num_tokens": 1876211.0,
|
|
"step": 1080
|
|
},
|
|
{
|
|
"entropy": 6.390499639511108,
|
|
"epoch": 0.08441937366271153,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999995182141099,
|
|
"loss": 6.3633,
|
|
"mean_token_accuracy": 0.1128227360546589,
|
|
"num_tokens": 1884301.0,
|
|
"step": 1085
|
|
},
|
|
{
|
|
"entropy": 6.635722494125366,
|
|
"epoch": 0.0848084030344291,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999994591516626,
|
|
"loss": 6.5416,
|
|
"mean_token_accuracy": 0.11540148556232452,
|
|
"num_tokens": 1893191.0,
|
|
"step": 1090
|
|
},
|
|
{
|
|
"entropy": 6.37746410369873,
|
|
"epoch": 0.08519743240614666,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999993966752066,
|
|
"loss": 6.4131,
|
|
"mean_token_accuracy": 0.11306635513901711,
|
|
"num_tokens": 1901434.0,
|
|
"step": 1095
|
|
},
|
|
{
|
|
"entropy": 6.484576797485351,
|
|
"epoch": 0.08558646177786423,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000499999330784743,
|
|
"loss": 6.3908,
|
|
"mean_token_accuracy": 0.12002351284027099,
|
|
"num_tokens": 1910054.0,
|
|
"step": 1100
|
|
},
|
|
{
|
|
"entropy": 6.490119457244873,
|
|
"epoch": 0.08597549114958179,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999992614802725,
|
|
"loss": 6.5397,
|
|
"mean_token_accuracy": 0.11540758833289147,
|
|
"num_tokens": 1918607.0,
|
|
"step": 1105
|
|
},
|
|
{
|
|
"entropy": 6.551545763015747,
|
|
"epoch": 0.08636452052129936,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999991887617966,
|
|
"loss": 6.4828,
|
|
"mean_token_accuracy": 0.11358762234449386,
|
|
"num_tokens": 1927610.0,
|
|
"step": 1110
|
|
},
|
|
{
|
|
"entropy": 6.389538955688477,
|
|
"epoch": 0.08675354989301692,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999991126293158,
|
|
"loss": 6.4366,
|
|
"mean_token_accuracy": 0.11365601867437362,
|
|
"num_tokens": 1936174.0,
|
|
"step": 1115
|
|
},
|
|
{
|
|
"entropy": 6.459973239898682,
|
|
"epoch": 0.08714257926473448,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999990330828318,
|
|
"loss": 6.3439,
|
|
"mean_token_accuracy": 0.12333748191595077,
|
|
"num_tokens": 1944228.0,
|
|
"step": 1120
|
|
},
|
|
{
|
|
"entropy": 6.483522081375122,
|
|
"epoch": 0.08753160863645205,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999989501223456,
|
|
"loss": 6.4502,
|
|
"mean_token_accuracy": 0.11555779352784157,
|
|
"num_tokens": 1953144.0,
|
|
"step": 1125
|
|
},
|
|
{
|
|
"entropy": 6.46024751663208,
|
|
"epoch": 0.08792063800816961,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999988637478584,
|
|
"loss": 6.5161,
|
|
"mean_token_accuracy": 0.1126246102154255,
|
|
"num_tokens": 1961947.0,
|
|
"step": 1130
|
|
},
|
|
{
|
|
"entropy": 6.5634512424469,
|
|
"epoch": 0.08830966737988719,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999987739593716,
|
|
"loss": 6.4809,
|
|
"mean_token_accuracy": 0.11571738943457603,
|
|
"num_tokens": 1970674.0,
|
|
"step": 1135
|
|
},
|
|
{
|
|
"entropy": 6.490915060043335,
|
|
"epoch": 0.08869869675160474,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999986807568865,
|
|
"loss": 6.4496,
|
|
"mean_token_accuracy": 0.11765117347240447,
|
|
"num_tokens": 1979173.0,
|
|
"step": 1140
|
|
},
|
|
{
|
|
"entropy": 6.474772596359253,
|
|
"epoch": 0.08908772612332232,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004999985841404045,
|
|
"loss": 6.4392,
|
|
"mean_token_accuracy": 0.11643676534295082,
|
|
"num_tokens": 1988134.0,
|
|
"step": 1145
|
|
},
|
|
{
|
|
"entropy": 6.441124773025512,
|
|
"epoch": 0.08947675549503988,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999984841099271,
|
|
"loss": 6.3768,
|
|
"mean_token_accuracy": 0.12014681100845337,
|
|
"num_tokens": 1996977.0,
|
|
"step": 1150
|
|
},
|
|
{
|
|
"entropy": 6.50206184387207,
|
|
"epoch": 0.08986578486675743,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000499998380665456,
|
|
"loss": 6.4588,
|
|
"mean_token_accuracy": 0.1176146350800991,
|
|
"num_tokens": 2005946.0,
|
|
"step": 1155
|
|
},
|
|
{
|
|
"entropy": 6.388955450057983,
|
|
"epoch": 0.090254814238475,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004999982738069924,
|
|
"loss": 6.2831,
|
|
"mean_token_accuracy": 0.12113617286086083,
|
|
"num_tokens": 2014882.0,
|
|
"step": 1160
|
|
},
|
|
{
|
|
"entropy": 6.391384267807007,
|
|
"epoch": 0.09064384361019256,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004999981635345382,
|
|
"loss": 6.4771,
|
|
"mean_token_accuracy": 0.1094152309000492,
|
|
"num_tokens": 2024858.0,
|
|
"step": 1165
|
|
},
|
|
{
|
|
"entropy": 6.371677255630493,
|
|
"epoch": 0.09103287298191014,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004999980498480949,
|
|
"loss": 6.3701,
|
|
"mean_token_accuracy": 0.11717021316289902,
|
|
"num_tokens": 2034072.0,
|
|
"step": 1170
|
|
},
|
|
{
|
|
"entropy": 6.45729169845581,
|
|
"epoch": 0.0914219023536277,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999979327476644,
|
|
"loss": 6.3869,
|
|
"mean_token_accuracy": 0.11678455844521522,
|
|
"num_tokens": 2042649.0,
|
|
"step": 1175
|
|
},
|
|
{
|
|
"entropy": 6.433530855178833,
|
|
"epoch": 0.09181093172534527,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999978122332485,
|
|
"loss": 6.4431,
|
|
"mean_token_accuracy": 0.1181255742907524,
|
|
"num_tokens": 2050866.0,
|
|
"step": 1180
|
|
},
|
|
{
|
|
"entropy": 6.4381969451904295,
|
|
"epoch": 0.09219996109706283,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004999976883048487,
|
|
"loss": 6.4242,
|
|
"mean_token_accuracy": 0.11656152158975601,
|
|
"num_tokens": 2058914.0,
|
|
"step": 1185
|
|
},
|
|
{
|
|
"entropy": 6.419391775131226,
|
|
"epoch": 0.0925889904687804,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999975609624673,
|
|
"loss": 6.362,
|
|
"mean_token_accuracy": 0.11579015702009202,
|
|
"num_tokens": 2068098.0,
|
|
"step": 1190
|
|
},
|
|
{
|
|
"entropy": 6.418846511840821,
|
|
"epoch": 0.09297801984049796,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999974302061059,
|
|
"loss": 6.3645,
|
|
"mean_token_accuracy": 0.11124148517847061,
|
|
"num_tokens": 2077299.0,
|
|
"step": 1195
|
|
},
|
|
{
|
|
"entropy": 6.40845251083374,
|
|
"epoch": 0.09336704921221552,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004999972960357666,
|
|
"loss": 6.4689,
|
|
"mean_token_accuracy": 0.11288349330425262,
|
|
"num_tokens": 2087868.0,
|
|
"step": 1200
|
|
},
|
|
{
|
|
"entropy": 6.447312068939209,
|
|
"epoch": 0.09375607858393309,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999971584514516,
|
|
"loss": 6.3783,
|
|
"mean_token_accuracy": 0.123850879073143,
|
|
"num_tokens": 2096553.0,
|
|
"step": 1205
|
|
},
|
|
{
|
|
"entropy": 6.458125257492066,
|
|
"epoch": 0.09414510795565065,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999970174531627,
|
|
"loss": 6.3609,
|
|
"mean_token_accuracy": 0.11663044691085815,
|
|
"num_tokens": 2104809.0,
|
|
"step": 1210
|
|
},
|
|
{
|
|
"entropy": 6.294647073745727,
|
|
"epoch": 0.09453413732736822,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999968730409022,
|
|
"loss": 6.3464,
|
|
"mean_token_accuracy": 0.11563503369688988,
|
|
"num_tokens": 2113869.0,
|
|
"step": 1215
|
|
},
|
|
{
|
|
"entropy": 6.34133825302124,
|
|
"epoch": 0.09492316669908578,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999967252146723,
|
|
"loss": 6.1603,
|
|
"mean_token_accuracy": 0.11609101369976997,
|
|
"num_tokens": 2121749.0,
|
|
"step": 1220
|
|
},
|
|
{
|
|
"entropy": 6.341687250137329,
|
|
"epoch": 0.09531219607080335,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999965739744752,
|
|
"loss": 6.3824,
|
|
"mean_token_accuracy": 0.11490623876452447,
|
|
"num_tokens": 2130828.0,
|
|
"step": 1225
|
|
},
|
|
{
|
|
"entropy": 6.462488079071045,
|
|
"epoch": 0.09570122544252091,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999964193203132,
|
|
"loss": 6.35,
|
|
"mean_token_accuracy": 0.11846289187669753,
|
|
"num_tokens": 2138928.0,
|
|
"step": 1230
|
|
},
|
|
{
|
|
"entropy": 6.407934045791626,
|
|
"epoch": 0.09609025481423847,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999962612521888,
|
|
"loss": 6.3864,
|
|
"mean_token_accuracy": 0.11911074891686439,
|
|
"num_tokens": 2147643.0,
|
|
"step": 1235
|
|
},
|
|
{
|
|
"entropy": 6.398451328277588,
|
|
"epoch": 0.09647928418595604,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999960997701041,
|
|
"loss": 6.3112,
|
|
"mean_token_accuracy": 0.12286981865763665,
|
|
"num_tokens": 2156766.0,
|
|
"step": 1240
|
|
},
|
|
{
|
|
"entropy": 6.415870094299317,
|
|
"epoch": 0.0968683135576736,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999959348740618,
|
|
"loss": 6.3735,
|
|
"mean_token_accuracy": 0.11572954803705215,
|
|
"num_tokens": 2165517.0,
|
|
"step": 1245
|
|
},
|
|
{
|
|
"entropy": 6.276720762252808,
|
|
"epoch": 0.09725734292939117,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999957665640641,
|
|
"loss": 6.2391,
|
|
"mean_token_accuracy": 0.12221750989556313,
|
|
"num_tokens": 2174812.0,
|
|
"step": 1250
|
|
},
|
|
{
|
|
"entropy": 6.389494466781616,
|
|
"epoch": 0.09764637230110873,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000499995594840114,
|
|
"loss": 6.3961,
|
|
"mean_token_accuracy": 0.1142569437623024,
|
|
"num_tokens": 2183968.0,
|
|
"step": 1255
|
|
},
|
|
{
|
|
"entropy": 6.395362615585327,
|
|
"epoch": 0.0980354016728263,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999954197022138,
|
|
"loss": 6.4207,
|
|
"mean_token_accuracy": 0.12095934301614761,
|
|
"num_tokens": 2191947.0,
|
|
"step": 1260
|
|
},
|
|
{
|
|
"entropy": 6.362047100067139,
|
|
"epoch": 0.09842443104454386,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999952411503661,
|
|
"loss": 6.2524,
|
|
"mean_token_accuracy": 0.12708474695682526,
|
|
"num_tokens": 2199951.0,
|
|
"step": 1265
|
|
},
|
|
{
|
|
"entropy": 6.345381879806519,
|
|
"epoch": 0.09881346041626143,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004999950591845738,
|
|
"loss": 6.4025,
|
|
"mean_token_accuracy": 0.11825087368488311,
|
|
"num_tokens": 2208714.0,
|
|
"step": 1270
|
|
},
|
|
{
|
|
"entropy": 6.296407985687256,
|
|
"epoch": 0.09920248978797899,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999948738048397,
|
|
"loss": 6.2605,
|
|
"mean_token_accuracy": 0.12081179469823837,
|
|
"num_tokens": 2217250.0,
|
|
"step": 1275
|
|
},
|
|
{
|
|
"entropy": 6.371564292907715,
|
|
"epoch": 0.09959151915969655,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004999946850111663,
|
|
"loss": 6.329,
|
|
"mean_token_accuracy": 0.12220223546028137,
|
|
"num_tokens": 2225468.0,
|
|
"step": 1280
|
|
},
|
|
{
|
|
"entropy": 6.248642206192017,
|
|
"epoch": 0.09998054853141412,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999944928035569,
|
|
"loss": 6.2729,
|
|
"mean_token_accuracy": 0.12882675752043724,
|
|
"num_tokens": 2233893.0,
|
|
"step": 1285
|
|
},
|
|
{
|
|
"entropy": 6.485666704177857,
|
|
"epoch": 0.10036957790313168,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000499994297182014,
|
|
"loss": 6.3387,
|
|
"mean_token_accuracy": 0.11729943826794624,
|
|
"num_tokens": 2242487.0,
|
|
"step": 1290
|
|
},
|
|
{
|
|
"entropy": 6.232321691513062,
|
|
"epoch": 0.10075860727484925,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999940981465408,
|
|
"loss": 6.1769,
|
|
"mean_token_accuracy": 0.12584130242466926,
|
|
"num_tokens": 2250518.0,
|
|
"step": 1295
|
|
},
|
|
{
|
|
"entropy": 6.359662485122681,
|
|
"epoch": 0.10114763664656681,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999938956971404,
|
|
"loss": 6.35,
|
|
"mean_token_accuracy": 0.11376101300120353,
|
|
"num_tokens": 2259024.0,
|
|
"step": 1300
|
|
},
|
|
{
|
|
"entropy": 6.315293645858764,
|
|
"epoch": 0.10153666601828439,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999936898338156,
|
|
"loss": 6.406,
|
|
"mean_token_accuracy": 0.11127450317144394,
|
|
"num_tokens": 2267832.0,
|
|
"step": 1305
|
|
},
|
|
{
|
|
"entropy": 6.441192197799682,
|
|
"epoch": 0.10192569539000194,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999934805565698,
|
|
"loss": 6.4422,
|
|
"mean_token_accuracy": 0.11080272123217583,
|
|
"num_tokens": 2276834.0,
|
|
"step": 1310
|
|
},
|
|
{
|
|
"entropy": 6.482887125015258,
|
|
"epoch": 0.10231472476171952,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000499993267865406,
|
|
"loss": 6.3746,
|
|
"mean_token_accuracy": 0.11520213186740876,
|
|
"num_tokens": 2285736.0,
|
|
"step": 1315
|
|
},
|
|
{
|
|
"entropy": 6.384394311904908,
|
|
"epoch": 0.10270375413343708,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999930517603275,
|
|
"loss": 6.3234,
|
|
"mean_token_accuracy": 0.1279608964920044,
|
|
"num_tokens": 2294177.0,
|
|
"step": 1320
|
|
},
|
|
{
|
|
"entropy": 6.272417211532593,
|
|
"epoch": 0.10309278350515463,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004999928322413374,
|
|
"loss": 6.1152,
|
|
"mean_token_accuracy": 0.13164947628974916,
|
|
"num_tokens": 2302784.0,
|
|
"step": 1325
|
|
},
|
|
{
|
|
"entropy": 6.1753613471984865,
|
|
"epoch": 0.1034818128768722,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999926093084394,
|
|
"loss": 6.2247,
|
|
"mean_token_accuracy": 0.1209910273551941,
|
|
"num_tokens": 2311650.0,
|
|
"step": 1330
|
|
},
|
|
{
|
|
"entropy": 6.426689910888672,
|
|
"epoch": 0.10387084224858976,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999923829616365,
|
|
"loss": 6.3461,
|
|
"mean_token_accuracy": 0.12103552594780922,
|
|
"num_tokens": 2319828.0,
|
|
"step": 1335
|
|
},
|
|
{
|
|
"entropy": 6.360848712921142,
|
|
"epoch": 0.10425987162030734,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999921532009323,
|
|
"loss": 6.3423,
|
|
"mean_token_accuracy": 0.11625662669539452,
|
|
"num_tokens": 2328636.0,
|
|
"step": 1340
|
|
},
|
|
{
|
|
"entropy": 6.244861602783203,
|
|
"epoch": 0.1046489009920249,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004999919200263304,
|
|
"loss": 6.2352,
|
|
"mean_token_accuracy": 0.1234541155397892,
|
|
"num_tokens": 2336771.0,
|
|
"step": 1345
|
|
},
|
|
{
|
|
"entropy": 6.352584886550903,
|
|
"epoch": 0.10503793036374247,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999916834378342,
|
|
"loss": 6.3854,
|
|
"mean_token_accuracy": 0.11652181446552276,
|
|
"num_tokens": 2346106.0,
|
|
"step": 1350
|
|
},
|
|
{
|
|
"entropy": 6.42938871383667,
|
|
"epoch": 0.10542695973546003,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999914434354472,
|
|
"loss": 6.3661,
|
|
"mean_token_accuracy": 0.11678783521056176,
|
|
"num_tokens": 2354943.0,
|
|
"step": 1355
|
|
},
|
|
{
|
|
"entropy": 6.208476591110229,
|
|
"epoch": 0.10581598910717759,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999912000191733,
|
|
"loss": 6.2707,
|
|
"mean_token_accuracy": 0.12307048067450524,
|
|
"num_tokens": 2363699.0,
|
|
"step": 1360
|
|
},
|
|
{
|
|
"entropy": 6.340670251846314,
|
|
"epoch": 0.10620501847889516,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000499990953189016,
|
|
"loss": 6.4154,
|
|
"mean_token_accuracy": 0.11648116931319237,
|
|
"num_tokens": 2373316.0,
|
|
"step": 1365
|
|
},
|
|
{
|
|
"entropy": 6.536358499526978,
|
|
"epoch": 0.10659404785061272,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999907029449791,
|
|
"loss": 6.4774,
|
|
"mean_token_accuracy": 0.1135114923119545,
|
|
"num_tokens": 2381550.0,
|
|
"step": 1370
|
|
},
|
|
{
|
|
"entropy": 6.30794472694397,
|
|
"epoch": 0.10698307722233029,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999904492870663,
|
|
"loss": 6.2883,
|
|
"mean_token_accuracy": 0.12282988801598549,
|
|
"num_tokens": 2389546.0,
|
|
"step": 1375
|
|
},
|
|
{
|
|
"entropy": 6.380693864822388,
|
|
"epoch": 0.10737210659404785,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999901922152816,
|
|
"loss": 6.244,
|
|
"mean_token_accuracy": 0.12719449624419213,
|
|
"num_tokens": 2398852.0,
|
|
"step": 1380
|
|
},
|
|
{
|
|
"entropy": 6.272253751754761,
|
|
"epoch": 0.10776113596576542,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999899317296288,
|
|
"loss": 6.3308,
|
|
"mean_token_accuracy": 0.12012203708291054,
|
|
"num_tokens": 2407815.0,
|
|
"step": 1385
|
|
},
|
|
{
|
|
"entropy": 6.317573165893554,
|
|
"epoch": 0.10815016533748298,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999896678301121,
|
|
"loss": 6.1922,
|
|
"mean_token_accuracy": 0.12548744305968285,
|
|
"num_tokens": 2417300.0,
|
|
"step": 1390
|
|
},
|
|
{
|
|
"entropy": 6.297150897979736,
|
|
"epoch": 0.10853919470920055,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999894005167352,
|
|
"loss": 6.3578,
|
|
"mean_token_accuracy": 0.11943556964397431,
|
|
"num_tokens": 2426257.0,
|
|
"step": 1395
|
|
},
|
|
{
|
|
"entropy": 6.4665430068969725,
|
|
"epoch": 0.10892822408091811,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000499989129789502,
|
|
"loss": 6.3817,
|
|
"mean_token_accuracy": 0.12104496955871583,
|
|
"num_tokens": 2434595.0,
|
|
"step": 1400
|
|
},
|
|
{
|
|
"entropy": 6.406263446807861,
|
|
"epoch": 0.10931725345263567,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999888556484172,
|
|
"loss": 6.39,
|
|
"mean_token_accuracy": 0.11528819128870964,
|
|
"num_tokens": 2443945.0,
|
|
"step": 1405
|
|
},
|
|
{
|
|
"entropy": 6.226689291000366,
|
|
"epoch": 0.10970628282435324,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999885780934845,
|
|
"loss": 6.2536,
|
|
"mean_token_accuracy": 0.12194890603423118,
|
|
"num_tokens": 2453141.0,
|
|
"step": 1410
|
|
},
|
|
{
|
|
"entropy": 6.352630996704102,
|
|
"epoch": 0.1100953121960708,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999882971247081,
|
|
"loss": 6.3336,
|
|
"mean_token_accuracy": 0.122190822660923,
|
|
"num_tokens": 2461873.0,
|
|
"step": 1415
|
|
},
|
|
{
|
|
"entropy": 6.317797040939331,
|
|
"epoch": 0.11048434156778837,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999880127420926,
|
|
"loss": 6.3632,
|
|
"mean_token_accuracy": 0.11227262541651725,
|
|
"num_tokens": 2471238.0,
|
|
"step": 1420
|
|
},
|
|
{
|
|
"entropy": 6.334433937072754,
|
|
"epoch": 0.11087337093950593,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004999877249456421,
|
|
"loss": 6.2408,
|
|
"mean_token_accuracy": 0.1272654689848423,
|
|
"num_tokens": 2479412.0,
|
|
"step": 1425
|
|
},
|
|
{
|
|
"entropy": 6.188841533660889,
|
|
"epoch": 0.1112624003112235,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004999874337353609,
|
|
"loss": 6.1292,
|
|
"mean_token_accuracy": 0.12458490431308747,
|
|
"num_tokens": 2488150.0,
|
|
"step": 1430
|
|
},
|
|
{
|
|
"entropy": 6.280575132369995,
|
|
"epoch": 0.11165142968294106,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999871391112535,
|
|
"loss": 6.309,
|
|
"mean_token_accuracy": 0.12516588494181632,
|
|
"num_tokens": 2498103.0,
|
|
"step": 1435
|
|
},
|
|
{
|
|
"entropy": 6.1986839294433596,
|
|
"epoch": 0.11204045905465862,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999868410733244,
|
|
"loss": 6.1695,
|
|
"mean_token_accuracy": 0.125221885740757,
|
|
"num_tokens": 2506211.0,
|
|
"step": 1440
|
|
},
|
|
{
|
|
"entropy": 6.172796535491943,
|
|
"epoch": 0.11242948842637619,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000499986539621578,
|
|
"loss": 6.2162,
|
|
"mean_token_accuracy": 0.12384542673826218,
|
|
"num_tokens": 2514743.0,
|
|
"step": 1445
|
|
},
|
|
{
|
|
"entropy": 6.167073822021484,
|
|
"epoch": 0.11281851779809375,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999862347560191,
|
|
"loss": 6.2027,
|
|
"mean_token_accuracy": 0.12268847003579139,
|
|
"num_tokens": 2523824.0,
|
|
"step": 1450
|
|
},
|
|
{
|
|
"entropy": 6.387971639633179,
|
|
"epoch": 0.11320754716981132,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999859264766521,
|
|
"loss": 6.2719,
|
|
"mean_token_accuracy": 0.12253661304712296,
|
|
"num_tokens": 2532360.0,
|
|
"step": 1455
|
|
},
|
|
{
|
|
"entropy": 6.257190561294555,
|
|
"epoch": 0.11359657654152888,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999856147834817,
|
|
"loss": 6.2217,
|
|
"mean_token_accuracy": 0.1282711908221245,
|
|
"num_tokens": 2540547.0,
|
|
"step": 1460
|
|
},
|
|
{
|
|
"entropy": 6.174588632583618,
|
|
"epoch": 0.11398560591324645,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999852996765129,
|
|
"loss": 6.2459,
|
|
"mean_token_accuracy": 0.12327087596058846,
|
|
"num_tokens": 2549193.0,
|
|
"step": 1465
|
|
},
|
|
{
|
|
"entropy": 6.317156839370727,
|
|
"epoch": 0.11437463528496401,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999849811557502,
|
|
"loss": 6.254,
|
|
"mean_token_accuracy": 0.12232557386159897,
|
|
"num_tokens": 2557553.0,
|
|
"step": 1470
|
|
},
|
|
{
|
|
"entropy": 6.374777555465698,
|
|
"epoch": 0.11476366465668159,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999846592211984,
|
|
"loss": 6.3602,
|
|
"mean_token_accuracy": 0.11835889741778374,
|
|
"num_tokens": 2565945.0,
|
|
"step": 1475
|
|
},
|
|
{
|
|
"entropy": 6.324231147766113,
|
|
"epoch": 0.11515269402839914,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004999843338728626,
|
|
"loss": 6.2285,
|
|
"mean_token_accuracy": 0.11772384941577911,
|
|
"num_tokens": 2574364.0,
|
|
"step": 1480
|
|
},
|
|
{
|
|
"entropy": 6.176779270172119,
|
|
"epoch": 0.1155417234001167,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999840051107476,
|
|
"loss": 6.1531,
|
|
"mean_token_accuracy": 0.1252761095762253,
|
|
"num_tokens": 2582825.0,
|
|
"step": 1485
|
|
},
|
|
{
|
|
"entropy": 6.367834663391113,
|
|
"epoch": 0.11593075277183428,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999836729348584,
|
|
"loss": 6.2943,
|
|
"mean_token_accuracy": 0.12382682561874389,
|
|
"num_tokens": 2591628.0,
|
|
"step": 1490
|
|
},
|
|
{
|
|
"entropy": 6.331791353225708,
|
|
"epoch": 0.11631978214355183,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999833373452,
|
|
"loss": 6.2892,
|
|
"mean_token_accuracy": 0.1190582662820816,
|
|
"num_tokens": 2600436.0,
|
|
"step": 1495
|
|
},
|
|
{
|
|
"entropy": 6.217423963546753,
|
|
"epoch": 0.1167088115152694,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004999829983417778,
|
|
"loss": 6.2596,
|
|
"mean_token_accuracy": 0.12188921868801117,
|
|
"num_tokens": 2609709.0,
|
|
"step": 1500
|
|
},
|
|
{
|
|
"entropy": 6.359324789047241,
|
|
"epoch": 0.11709784088698696,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999826559245965,
|
|
"loss": 6.2586,
|
|
"mean_token_accuracy": 0.12367889285087585,
|
|
"num_tokens": 2617992.0,
|
|
"step": 1505
|
|
},
|
|
{
|
|
"entropy": 6.17459282875061,
|
|
"epoch": 0.11748687025870454,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999823100936615,
|
|
"loss": 6.1695,
|
|
"mean_token_accuracy": 0.12516930997371672,
|
|
"num_tokens": 2626706.0,
|
|
"step": 1510
|
|
},
|
|
{
|
|
"entropy": 6.3931690692901615,
|
|
"epoch": 0.1178758996304221,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004999819608489781,
|
|
"loss": 6.2359,
|
|
"mean_token_accuracy": 0.13169281259179116,
|
|
"num_tokens": 2634642.0,
|
|
"step": 1515
|
|
},
|
|
{
|
|
"entropy": 6.271792840957642,
|
|
"epoch": 0.11826492900213967,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999816081905515,
|
|
"loss": 6.2722,
|
|
"mean_token_accuracy": 0.11658980697393417,
|
|
"num_tokens": 2644160.0,
|
|
"step": 1520
|
|
},
|
|
{
|
|
"entropy": 6.214734745025635,
|
|
"epoch": 0.11865395837385723,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999812521183872,
|
|
"loss": 6.2285,
|
|
"mean_token_accuracy": 0.1217222385108471,
|
|
"num_tokens": 2653390.0,
|
|
"step": 1525
|
|
},
|
|
{
|
|
"entropy": 6.356004905700684,
|
|
"epoch": 0.11904298774557479,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999808926324903,
|
|
"loss": 6.2785,
|
|
"mean_token_accuracy": 0.12192253395915031,
|
|
"num_tokens": 2662561.0,
|
|
"step": 1530
|
|
},
|
|
{
|
|
"entropy": 6.280083322525025,
|
|
"epoch": 0.11943201711729236,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004999805297328665,
|
|
"loss": 6.2453,
|
|
"mean_token_accuracy": 0.12399770319461823,
|
|
"num_tokens": 2670694.0,
|
|
"step": 1535
|
|
},
|
|
{
|
|
"entropy": 6.214053916931152,
|
|
"epoch": 0.11982104648900992,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999801634195214,
|
|
"loss": 6.1408,
|
|
"mean_token_accuracy": 0.12651772275567055,
|
|
"num_tokens": 2679583.0,
|
|
"step": 1540
|
|
},
|
|
{
|
|
"entropy": 6.181328582763672,
|
|
"epoch": 0.12021007586072749,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999797936924603,
|
|
"loss": 6.1127,
|
|
"mean_token_accuracy": 0.12723355293273925,
|
|
"num_tokens": 2688429.0,
|
|
"step": 1545
|
|
},
|
|
{
|
|
"entropy": 6.365040397644043,
|
|
"epoch": 0.12059910523244505,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000499979420551689,
|
|
"loss": 6.2115,
|
|
"mean_token_accuracy": 0.12122456356883049,
|
|
"num_tokens": 2697134.0,
|
|
"step": 1550
|
|
},
|
|
{
|
|
"entropy": 6.182654905319214,
|
|
"epoch": 0.12098813460416262,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000499979043997213,
|
|
"loss": 6.3483,
|
|
"mean_token_accuracy": 0.11888098418712616,
|
|
"num_tokens": 2705641.0,
|
|
"step": 1555
|
|
},
|
|
{
|
|
"entropy": 6.314460563659668,
|
|
"epoch": 0.12137716397588018,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999786640290381,
|
|
"loss": 6.2908,
|
|
"mean_token_accuracy": 0.12467942461371422,
|
|
"num_tokens": 2714977.0,
|
|
"step": 1560
|
|
},
|
|
{
|
|
"entropy": 6.2193540096282955,
|
|
"epoch": 0.12176619334759774,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004999782806471701,
|
|
"loss": 6.1337,
|
|
"mean_token_accuracy": 0.1347135454416275,
|
|
"num_tokens": 2723120.0,
|
|
"step": 1565
|
|
},
|
|
{
|
|
"entropy": 6.0879443168640135,
|
|
"epoch": 0.12215522271931531,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999778938516147,
|
|
"loss": 6.1317,
|
|
"mean_token_accuracy": 0.13238951042294503,
|
|
"num_tokens": 2731964.0,
|
|
"step": 1570
|
|
},
|
|
{
|
|
"entropy": 6.39334282875061,
|
|
"epoch": 0.12254425209103287,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000499977503642378,
|
|
"loss": 6.1931,
|
|
"mean_token_accuracy": 0.127005735039711,
|
|
"num_tokens": 2741537.0,
|
|
"step": 1575
|
|
},
|
|
{
|
|
"entropy": 6.138741397857666,
|
|
"epoch": 0.12293328146275044,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999771100194656,
|
|
"loss": 6.3277,
|
|
"mean_token_accuracy": 0.1212069720029831,
|
|
"num_tokens": 2751522.0,
|
|
"step": 1580
|
|
},
|
|
{
|
|
"entropy": 6.3773661136627195,
|
|
"epoch": 0.123322310834468,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999767129828837,
|
|
"loss": 6.3125,
|
|
"mean_token_accuracy": 0.11907947659492493,
|
|
"num_tokens": 2761100.0,
|
|
"step": 1585
|
|
},
|
|
{
|
|
"entropy": 6.22048397064209,
|
|
"epoch": 0.12371134020618557,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999763125326383,
|
|
"loss": 6.2478,
|
|
"mean_token_accuracy": 0.12256922721862792,
|
|
"num_tokens": 2769171.0,
|
|
"step": 1590
|
|
},
|
|
{
|
|
"entropy": 6.243303442001343,
|
|
"epoch": 0.12410036957790313,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999759086687355,
|
|
"loss": 6.1867,
|
|
"mean_token_accuracy": 0.12792484536767007,
|
|
"num_tokens": 2778021.0,
|
|
"step": 1595
|
|
},
|
|
{
|
|
"entropy": 6.166972827911377,
|
|
"epoch": 0.1244893989496207,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999755013911813,
|
|
"loss": 6.1195,
|
|
"mean_token_accuracy": 0.13010439202189444,
|
|
"num_tokens": 2787206.0,
|
|
"step": 1600
|
|
},
|
|
{
|
|
"entropy": 6.148937082290649,
|
|
"epoch": 0.12487842832133826,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000499975090699982,
|
|
"loss": 6.1981,
|
|
"mean_token_accuracy": 0.1204142227768898,
|
|
"num_tokens": 2796051.0,
|
|
"step": 1605
|
|
},
|
|
{
|
|
"entropy": 6.247499084472656,
|
|
"epoch": 0.12526745769305583,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999746765951438,
|
|
"loss": 6.144,
|
|
"mean_token_accuracy": 0.12628112062811853,
|
|
"num_tokens": 2804961.0,
|
|
"step": 1610
|
|
},
|
|
{
|
|
"entropy": 6.156633281707764,
|
|
"epoch": 0.1256564870647734,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999742590766729,
|
|
"loss": 6.0863,
|
|
"mean_token_accuracy": 0.13187484741210936,
|
|
"num_tokens": 2813691.0,
|
|
"step": 1615
|
|
},
|
|
{
|
|
"entropy": 6.225268125534058,
|
|
"epoch": 0.12604551643649095,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999738381445757,
|
|
"loss": 6.248,
|
|
"mean_token_accuracy": 0.12675216943025588,
|
|
"num_tokens": 2822248.0,
|
|
"step": 1620
|
|
},
|
|
{
|
|
"entropy": 6.251285171508789,
|
|
"epoch": 0.1264345458082085,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999734137988586,
|
|
"loss": 6.1923,
|
|
"mean_token_accuracy": 0.12956587076187134,
|
|
"num_tokens": 2830826.0,
|
|
"step": 1625
|
|
},
|
|
{
|
|
"entropy": 6.216675090789795,
|
|
"epoch": 0.1268235751799261,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000499972986039528,
|
|
"loss": 6.1839,
|
|
"mean_token_accuracy": 0.12593767046928406,
|
|
"num_tokens": 2839766.0,
|
|
"step": 1630
|
|
},
|
|
{
|
|
"entropy": 6.123473691940307,
|
|
"epoch": 0.12721260455164365,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999725548665904,
|
|
"loss": 6.1228,
|
|
"mean_token_accuracy": 0.13010624870657922,
|
|
"num_tokens": 2848728.0,
|
|
"step": 1635
|
|
},
|
|
{
|
|
"entropy": 6.1722784519195555,
|
|
"epoch": 0.1276016339233612,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999721202800524,
|
|
"loss": 6.1396,
|
|
"mean_token_accuracy": 0.13079047277569772,
|
|
"num_tokens": 2857221.0,
|
|
"step": 1640
|
|
},
|
|
{
|
|
"entropy": 6.263162755966187,
|
|
"epoch": 0.12799066329507877,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999716822799206,
|
|
"loss": 6.2131,
|
|
"mean_token_accuracy": 0.12727918699383736,
|
|
"num_tokens": 2865314.0,
|
|
"step": 1645
|
|
},
|
|
{
|
|
"entropy": 6.1169415473937985,
|
|
"epoch": 0.12837969266679633,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999712408662016,
|
|
"loss": 6.088,
|
|
"mean_token_accuracy": 0.12827678620815278,
|
|
"num_tokens": 2873654.0,
|
|
"step": 1650
|
|
},
|
|
{
|
|
"entropy": 6.114794111251831,
|
|
"epoch": 0.12876872203851392,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999707960389021,
|
|
"loss": 5.9976,
|
|
"mean_token_accuracy": 0.1390816293656826,
|
|
"num_tokens": 2881604.0,
|
|
"step": 1655
|
|
},
|
|
{
|
|
"entropy": 6.175813865661621,
|
|
"epoch": 0.12915775141023147,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999703477980288,
|
|
"loss": 6.1899,
|
|
"mean_token_accuracy": 0.12590051293373108,
|
|
"num_tokens": 2890427.0,
|
|
"step": 1660
|
|
},
|
|
{
|
|
"entropy": 6.176800918579102,
|
|
"epoch": 0.12954678078194903,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999698961435885,
|
|
"loss": 6.1608,
|
|
"mean_token_accuracy": 0.1278068646788597,
|
|
"num_tokens": 2899206.0,
|
|
"step": 1665
|
|
},
|
|
{
|
|
"entropy": 6.1610307693481445,
|
|
"epoch": 0.1299358101536666,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999694410755882,
|
|
"loss": 6.0803,
|
|
"mean_token_accuracy": 0.1307940810918808,
|
|
"num_tokens": 2907738.0,
|
|
"step": 1670
|
|
},
|
|
{
|
|
"entropy": 6.264579439163208,
|
|
"epoch": 0.13032483952538418,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999689825940347,
|
|
"loss": 6.3124,
|
|
"mean_token_accuracy": 0.12490758523344994,
|
|
"num_tokens": 2916881.0,
|
|
"step": 1675
|
|
},
|
|
{
|
|
"entropy": 6.203776741027832,
|
|
"epoch": 0.13071386889710174,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999685206989349,
|
|
"loss": 6.2506,
|
|
"mean_token_accuracy": 0.12321256548166275,
|
|
"num_tokens": 2926467.0,
|
|
"step": 1680
|
|
},
|
|
{
|
|
"entropy": 6.266940355300903,
|
|
"epoch": 0.1311028982688193,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999680553902959,
|
|
"loss": 6.1586,
|
|
"mean_token_accuracy": 0.12849143967032434,
|
|
"num_tokens": 2934671.0,
|
|
"step": 1685
|
|
},
|
|
{
|
|
"entropy": 6.153891229629517,
|
|
"epoch": 0.13149192764053685,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999675866681247,
|
|
"loss": 6.1937,
|
|
"mean_token_accuracy": 0.12307270169258118,
|
|
"num_tokens": 2943925.0,
|
|
"step": 1690
|
|
},
|
|
{
|
|
"entropy": 6.251479959487915,
|
|
"epoch": 0.1318809570122544,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004999671145324286,
|
|
"loss": 6.2351,
|
|
"mean_token_accuracy": 0.12551012486219407,
|
|
"num_tokens": 2952118.0,
|
|
"step": 1695
|
|
},
|
|
{
|
|
"entropy": 6.142472887039185,
|
|
"epoch": 0.132269986383972,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999666389832144,
|
|
"loss": 6.2185,
|
|
"mean_token_accuracy": 0.12478951662778855,
|
|
"num_tokens": 2961110.0,
|
|
"step": 1700
|
|
},
|
|
{
|
|
"entropy": 6.258459663391113,
|
|
"epoch": 0.13265901575568956,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999661600204897,
|
|
"loss": 6.1492,
|
|
"mean_token_accuracy": 0.1310803025960922,
|
|
"num_tokens": 2968877.0,
|
|
"step": 1705
|
|
},
|
|
{
|
|
"entropy": 6.205829286575318,
|
|
"epoch": 0.13304804512740712,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999656776442615,
|
|
"loss": 6.2062,
|
|
"mean_token_accuracy": 0.12969572320580483,
|
|
"num_tokens": 2977346.0,
|
|
"step": 1710
|
|
},
|
|
{
|
|
"entropy": 6.306067752838135,
|
|
"epoch": 0.13343707449912467,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999651918545372,
|
|
"loss": 6.2403,
|
|
"mean_token_accuracy": 0.12232028320431709,
|
|
"num_tokens": 2987494.0,
|
|
"step": 1715
|
|
},
|
|
{
|
|
"entropy": 6.168236112594604,
|
|
"epoch": 0.13382610387084226,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999647026513243,
|
|
"loss": 6.167,
|
|
"mean_token_accuracy": 0.12709078639745713,
|
|
"num_tokens": 2996728.0,
|
|
"step": 1720
|
|
},
|
|
{
|
|
"entropy": 6.16880464553833,
|
|
"epoch": 0.13421513324255982,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00049996421003463,
|
|
"loss": 6.1947,
|
|
"mean_token_accuracy": 0.12163503617048263,
|
|
"num_tokens": 3005810.0,
|
|
"step": 1725
|
|
},
|
|
{
|
|
"entropy": 6.225845766067505,
|
|
"epoch": 0.13460416261427738,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004999637140044619,
|
|
"loss": 6.2057,
|
|
"mean_token_accuracy": 0.12583187147974967,
|
|
"num_tokens": 3014603.0,
|
|
"step": 1730
|
|
},
|
|
{
|
|
"entropy": 6.286410093307495,
|
|
"epoch": 0.13499319198599494,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999632145608275,
|
|
"loss": 6.2073,
|
|
"mean_token_accuracy": 0.12976924255490302,
|
|
"num_tokens": 3023170.0,
|
|
"step": 1735
|
|
},
|
|
{
|
|
"entropy": 6.047111463546753,
|
|
"epoch": 0.1353822213577125,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999627117037343,
|
|
"loss": 5.952,
|
|
"mean_token_accuracy": 0.13934574648737907,
|
|
"num_tokens": 3030565.0,
|
|
"step": 1740
|
|
},
|
|
{
|
|
"entropy": 6.201064538955689,
|
|
"epoch": 0.13577125072943008,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00049996220543319,
|
|
"loss": 6.2296,
|
|
"mean_token_accuracy": 0.1313652738928795,
|
|
"num_tokens": 3040124.0,
|
|
"step": 1745
|
|
},
|
|
{
|
|
"entropy": 6.118889284133911,
|
|
"epoch": 0.13616028010114764,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999616957492025,
|
|
"loss": 6.0833,
|
|
"mean_token_accuracy": 0.1335503078997135,
|
|
"num_tokens": 3048458.0,
|
|
"step": 1750
|
|
},
|
|
{
|
|
"entropy": 6.115156173706055,
|
|
"epoch": 0.1365493094728652,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999611826517793,
|
|
"loss": 6.0529,
|
|
"mean_token_accuracy": 0.12220517992973327,
|
|
"num_tokens": 3057926.0,
|
|
"step": 1755
|
|
},
|
|
{
|
|
"entropy": 6.074193906784058,
|
|
"epoch": 0.13693833884458276,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999606661409281,
|
|
"loss": 6.0902,
|
|
"mean_token_accuracy": 0.12791807651519777,
|
|
"num_tokens": 3066683.0,
|
|
"step": 1760
|
|
},
|
|
{
|
|
"entropy": 6.162175607681275,
|
|
"epoch": 0.13732736821630034,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999601462166569,
|
|
"loss": 6.1736,
|
|
"mean_token_accuracy": 0.12800901383161545,
|
|
"num_tokens": 3075117.0,
|
|
"step": 1765
|
|
},
|
|
{
|
|
"entropy": 6.291727209091187,
|
|
"epoch": 0.1377163975880179,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999596228789736,
|
|
"loss": 6.2362,
|
|
"mean_token_accuracy": 0.12387871071696281,
|
|
"num_tokens": 3084399.0,
|
|
"step": 1770
|
|
},
|
|
{
|
|
"entropy": 6.073335409164429,
|
|
"epoch": 0.13810542695973546,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999590961278859,
|
|
"loss": 6.0154,
|
|
"mean_token_accuracy": 0.13292096480727195,
|
|
"num_tokens": 3093030.0,
|
|
"step": 1775
|
|
},
|
|
{
|
|
"entropy": 6.19185700416565,
|
|
"epoch": 0.13849445633145302,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999585659634021,
|
|
"loss": 6.0716,
|
|
"mean_token_accuracy": 0.13075146377086638,
|
|
"num_tokens": 3101670.0,
|
|
"step": 1780
|
|
},
|
|
{
|
|
"entropy": 6.05259747505188,
|
|
"epoch": 0.13888348570317058,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999580323855301,
|
|
"loss": 6.0614,
|
|
"mean_token_accuracy": 0.13134398460388183,
|
|
"num_tokens": 3109703.0,
|
|
"step": 1785
|
|
},
|
|
{
|
|
"entropy": 6.102718019485474,
|
|
"epoch": 0.13927251507488816,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999574953942781,
|
|
"loss": 6.0242,
|
|
"mean_token_accuracy": 0.13451038673520088,
|
|
"num_tokens": 3118388.0,
|
|
"step": 1790
|
|
},
|
|
{
|
|
"entropy": 6.110586404800415,
|
|
"epoch": 0.13966154444660572,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999569549896541,
|
|
"loss": 6.0341,
|
|
"mean_token_accuracy": 0.13156714141368867,
|
|
"num_tokens": 3126466.0,
|
|
"step": 1795
|
|
},
|
|
{
|
|
"entropy": 6.112448740005493,
|
|
"epoch": 0.14005057381832328,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999564111716665,
|
|
"loss": 6.0781,
|
|
"mean_token_accuracy": 0.1335633009672165,
|
|
"num_tokens": 3135322.0,
|
|
"step": 1800
|
|
},
|
|
{
|
|
"entropy": 6.108473491668701,
|
|
"epoch": 0.14043960319004084,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999558639403232,
|
|
"loss": 6.0755,
|
|
"mean_token_accuracy": 0.13613163232803344,
|
|
"num_tokens": 3144498.0,
|
|
"step": 1805
|
|
},
|
|
{
|
|
"entropy": 6.045802354812622,
|
|
"epoch": 0.1408286325617584,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999553132956328,
|
|
"loss": 6.0512,
|
|
"mean_token_accuracy": 0.12877680659294127,
|
|
"num_tokens": 3153573.0,
|
|
"step": 1810
|
|
},
|
|
{
|
|
"entropy": 6.046996307373047,
|
|
"epoch": 0.14121766193347599,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999547592376035,
|
|
"loss": 5.9939,
|
|
"mean_token_accuracy": 0.1377910055220127,
|
|
"num_tokens": 3161705.0,
|
|
"step": 1815
|
|
},
|
|
{
|
|
"entropy": 6.138423156738281,
|
|
"epoch": 0.14160669130519354,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004999542017662438,
|
|
"loss": 6.1474,
|
|
"mean_token_accuracy": 0.13016104623675345,
|
|
"num_tokens": 3170068.0,
|
|
"step": 1820
|
|
},
|
|
{
|
|
"entropy": 6.134330701828003,
|
|
"epoch": 0.1419957206769111,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999536408815623,
|
|
"loss": 6.152,
|
|
"mean_token_accuracy": 0.12710127755999565,
|
|
"num_tokens": 3178140.0,
|
|
"step": 1825
|
|
},
|
|
{
|
|
"entropy": 6.159389972686768,
|
|
"epoch": 0.14238475004862866,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004999530765835672,
|
|
"loss": 6.117,
|
|
"mean_token_accuracy": 0.1319376789033413,
|
|
"num_tokens": 3186518.0,
|
|
"step": 1830
|
|
},
|
|
{
|
|
"entropy": 6.114027595520019,
|
|
"epoch": 0.14277377942034625,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999525088722673,
|
|
"loss": 6.1086,
|
|
"mean_token_accuracy": 0.126016952842474,
|
|
"num_tokens": 3195246.0,
|
|
"step": 1835
|
|
},
|
|
{
|
|
"entropy": 6.2064361572265625,
|
|
"epoch": 0.1431628087920638,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999519377476711,
|
|
"loss": 6.1239,
|
|
"mean_token_accuracy": 0.12959307059645653,
|
|
"num_tokens": 3203946.0,
|
|
"step": 1840
|
|
},
|
|
{
|
|
"entropy": 6.125613784790039,
|
|
"epoch": 0.14355183816378136,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004999513632097872,
|
|
"loss": 6.1511,
|
|
"mean_token_accuracy": 0.12730584666132927,
|
|
"num_tokens": 3212208.0,
|
|
"step": 1845
|
|
},
|
|
{
|
|
"entropy": 6.112041807174682,
|
|
"epoch": 0.14394086753549892,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999507852586245,
|
|
"loss": 6.078,
|
|
"mean_token_accuracy": 0.12968963086605073,
|
|
"num_tokens": 3221572.0,
|
|
"step": 1850
|
|
},
|
|
{
|
|
"entropy": 6.241564416885376,
|
|
"epoch": 0.14432989690721648,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999502038941917,
|
|
"loss": 6.2186,
|
|
"mean_token_accuracy": 0.11879752650856971,
|
|
"num_tokens": 3230898.0,
|
|
"step": 1855
|
|
},
|
|
{
|
|
"entropy": 6.053813362121582,
|
|
"epoch": 0.14471892627893407,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999496191164975,
|
|
"loss": 6.1755,
|
|
"mean_token_accuracy": 0.12418220117688179,
|
|
"num_tokens": 3240524.0,
|
|
"step": 1860
|
|
},
|
|
{
|
|
"entropy": 6.186307144165039,
|
|
"epoch": 0.14510795565065163,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000499949030925551,
|
|
"loss": 5.9339,
|
|
"mean_token_accuracy": 0.1323039062321186,
|
|
"num_tokens": 3248864.0,
|
|
"step": 1865
|
|
},
|
|
{
|
|
"entropy": 6.05433611869812,
|
|
"epoch": 0.14549698502236919,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999484393213609,
|
|
"loss": 6.1267,
|
|
"mean_token_accuracy": 0.12983283996582032,
|
|
"num_tokens": 3256823.0,
|
|
"step": 1870
|
|
},
|
|
{
|
|
"entropy": 6.093509531021118,
|
|
"epoch": 0.14588601439408674,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999478443039363,
|
|
"loss": 6.0317,
|
|
"mean_token_accuracy": 0.13464081212878226,
|
|
"num_tokens": 3265621.0,
|
|
"step": 1875
|
|
},
|
|
{
|
|
"entropy": 6.031926536560059,
|
|
"epoch": 0.14627504376580433,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999472458732862,
|
|
"loss": 6.0619,
|
|
"mean_token_accuracy": 0.13131768479943276,
|
|
"num_tokens": 3273515.0,
|
|
"step": 1880
|
|
},
|
|
{
|
|
"entropy": 6.207943487167358,
|
|
"epoch": 0.1466640731375219,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999466440294198,
|
|
"loss": 6.131,
|
|
"mean_token_accuracy": 0.12989283427596093,
|
|
"num_tokens": 3282283.0,
|
|
"step": 1885
|
|
},
|
|
{
|
|
"entropy": 6.049416828155517,
|
|
"epoch": 0.14705310250923945,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000499946038772346,
|
|
"loss": 6.1341,
|
|
"mean_token_accuracy": 0.13318516165018082,
|
|
"num_tokens": 3290792.0,
|
|
"step": 1890
|
|
},
|
|
{
|
|
"entropy": 6.044079065322876,
|
|
"epoch": 0.147442131880957,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004999454301020741,
|
|
"loss": 5.9918,
|
|
"mean_token_accuracy": 0.13286386504769326,
|
|
"num_tokens": 3299430.0,
|
|
"step": 1895
|
|
},
|
|
{
|
|
"entropy": 6.067660093307495,
|
|
"epoch": 0.14783116125267456,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999448180186133,
|
|
"loss": 6.0334,
|
|
"mean_token_accuracy": 0.13755829334259034,
|
|
"num_tokens": 3307949.0,
|
|
"step": 1900
|
|
},
|
|
{
|
|
"entropy": 6.091364002227783,
|
|
"epoch": 0.14822019062439215,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000499944202521973,
|
|
"loss": 6.098,
|
|
"mean_token_accuracy": 0.13308693766593932,
|
|
"num_tokens": 3316900.0,
|
|
"step": 1905
|
|
},
|
|
{
|
|
"entropy": 6.114401006698609,
|
|
"epoch": 0.1486092199961097,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999435836121624,
|
|
"loss": 6.0263,
|
|
"mean_token_accuracy": 0.1365790992975235,
|
|
"num_tokens": 3325656.0,
|
|
"step": 1910
|
|
},
|
|
{
|
|
"entropy": 6.054609870910644,
|
|
"epoch": 0.14899824936782727,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000499942961289191,
|
|
"loss": 6.2408,
|
|
"mean_token_accuracy": 0.11948857307434083,
|
|
"num_tokens": 3334219.0,
|
|
"step": 1915
|
|
},
|
|
{
|
|
"entropy": 6.100892877578735,
|
|
"epoch": 0.14938727873954483,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999423355530683,
|
|
"loss": 5.987,
|
|
"mean_token_accuracy": 0.1356291465461254,
|
|
"num_tokens": 3343637.0,
|
|
"step": 1920
|
|
},
|
|
{
|
|
"entropy": 6.047068405151367,
|
|
"epoch": 0.1497763081112624,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999417064038035,
|
|
"loss": 6.1349,
|
|
"mean_token_accuracy": 0.1278958112001419,
|
|
"num_tokens": 3352624.0,
|
|
"step": 1925
|
|
},
|
|
{
|
|
"entropy": 6.089813709259033,
|
|
"epoch": 0.15016533748297997,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999410738414065,
|
|
"loss": 6.0577,
|
|
"mean_token_accuracy": 0.13661672845482825,
|
|
"num_tokens": 3361394.0,
|
|
"step": 1930
|
|
},
|
|
{
|
|
"entropy": 6.1655097007751465,
|
|
"epoch": 0.15055436685469753,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999404378658866,
|
|
"loss": 6.1106,
|
|
"mean_token_accuracy": 0.13267300873994828,
|
|
"num_tokens": 3369406.0,
|
|
"step": 1935
|
|
},
|
|
{
|
|
"entropy": 6.093273782730103,
|
|
"epoch": 0.1509433962264151,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999397984772536,
|
|
"loss": 6.0514,
|
|
"mean_token_accuracy": 0.1275075666606426,
|
|
"num_tokens": 3377737.0,
|
|
"step": 1940
|
|
},
|
|
{
|
|
"entropy": 6.077555751800537,
|
|
"epoch": 0.15133242559813265,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999391556755172,
|
|
"loss": 6.1175,
|
|
"mean_token_accuracy": 0.12663735300302506,
|
|
"num_tokens": 3385514.0,
|
|
"step": 1945
|
|
},
|
|
{
|
|
"entropy": 6.144791460037231,
|
|
"epoch": 0.15172145496985023,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999385094606872,
|
|
"loss": 6.0261,
|
|
"mean_token_accuracy": 0.13351787775754928,
|
|
"num_tokens": 3394500.0,
|
|
"step": 1950
|
|
},
|
|
{
|
|
"entropy": 6.004178762435913,
|
|
"epoch": 0.1521104843415678,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999378598327733,
|
|
"loss": 6.0057,
|
|
"mean_token_accuracy": 0.13412315174937248,
|
|
"num_tokens": 3403289.0,
|
|
"step": 1955
|
|
},
|
|
{
|
|
"entropy": 6.04636549949646,
|
|
"epoch": 0.15249951371328535,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999372067917854,
|
|
"loss": 5.9441,
|
|
"mean_token_accuracy": 0.14245061874389647,
|
|
"num_tokens": 3410892.0,
|
|
"step": 1960
|
|
},
|
|
{
|
|
"entropy": 5.918894290924072,
|
|
"epoch": 0.1528885430850029,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999365503377335,
|
|
"loss": 6.0281,
|
|
"mean_token_accuracy": 0.13515010178089143,
|
|
"num_tokens": 3420329.0,
|
|
"step": 1965
|
|
},
|
|
{
|
|
"entropy": 6.066119909286499,
|
|
"epoch": 0.1532775724567205,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999358904706273,
|
|
"loss": 6.0257,
|
|
"mean_token_accuracy": 0.13282209038734435,
|
|
"num_tokens": 3429429.0,
|
|
"step": 1970
|
|
},
|
|
{
|
|
"entropy": 6.137219715118408,
|
|
"epoch": 0.15366660182843805,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999352271904771,
|
|
"loss": 6.1381,
|
|
"mean_token_accuracy": 0.12859977707266806,
|
|
"num_tokens": 3438198.0,
|
|
"step": 1975
|
|
},
|
|
{
|
|
"entropy": 6.2691608428955075,
|
|
"epoch": 0.1540556312001556,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999345604972928,
|
|
"loss": 6.2676,
|
|
"mean_token_accuracy": 0.129219963401556,
|
|
"num_tokens": 3447732.0,
|
|
"step": 1980
|
|
},
|
|
{
|
|
"entropy": 6.048369979858398,
|
|
"epoch": 0.15444466057187317,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999338903910846,
|
|
"loss": 6.0545,
|
|
"mean_token_accuracy": 0.13279973939061165,
|
|
"num_tokens": 3456392.0,
|
|
"step": 1985
|
|
},
|
|
{
|
|
"entropy": 6.084347772598266,
|
|
"epoch": 0.15483368994359073,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999332168718626,
|
|
"loss": 6.0832,
|
|
"mean_token_accuracy": 0.1306935466825962,
|
|
"num_tokens": 3464473.0,
|
|
"step": 1990
|
|
},
|
|
{
|
|
"entropy": 6.114197492599487,
|
|
"epoch": 0.15522271931530832,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999325399396371,
|
|
"loss": 6.0531,
|
|
"mean_token_accuracy": 0.1318880908191204,
|
|
"num_tokens": 3473740.0,
|
|
"step": 1995
|
|
},
|
|
{
|
|
"entropy": 5.95880823135376,
|
|
"epoch": 0.15561174868702587,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999318595944183,
|
|
"loss": 5.9461,
|
|
"mean_token_accuracy": 0.13854984045028687,
|
|
"num_tokens": 3482249.0,
|
|
"step": 2000
|
|
},
|
|
{
|
|
"entropy": 6.20720682144165,
|
|
"epoch": 0.15600077805874343,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999311758362166,
|
|
"loss": 6.194,
|
|
"mean_token_accuracy": 0.1284084811806679,
|
|
"num_tokens": 3490753.0,
|
|
"step": 2005
|
|
},
|
|
{
|
|
"entropy": 6.1580390453338625,
|
|
"epoch": 0.156389807430461,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999304886650422,
|
|
"loss": 6.1388,
|
|
"mean_token_accuracy": 0.13328585550189018,
|
|
"num_tokens": 3499373.0,
|
|
"step": 2010
|
|
},
|
|
{
|
|
"entropy": 6.130110073089599,
|
|
"epoch": 0.15677883680217858,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999297980809058,
|
|
"loss": 6.0894,
|
|
"mean_token_accuracy": 0.12947576269507408,
|
|
"num_tokens": 3508344.0,
|
|
"step": 2015
|
|
},
|
|
{
|
|
"entropy": 6.102607488632202,
|
|
"epoch": 0.15716786617389614,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999291040838176,
|
|
"loss": 6.0589,
|
|
"mean_token_accuracy": 0.12978120669722557,
|
|
"num_tokens": 3517009.0,
|
|
"step": 2020
|
|
},
|
|
{
|
|
"entropy": 6.054499006271362,
|
|
"epoch": 0.1575568955456137,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999284066737884,
|
|
"loss": 6.11,
|
|
"mean_token_accuracy": 0.12718966975808144,
|
|
"num_tokens": 3525989.0,
|
|
"step": 2025
|
|
},
|
|
{
|
|
"entropy": 6.133045625686646,
|
|
"epoch": 0.15794592491733125,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004999277058508285,
|
|
"loss": 5.9964,
|
|
"mean_token_accuracy": 0.13161147758364677,
|
|
"num_tokens": 3533947.0,
|
|
"step": 2030
|
|
},
|
|
{
|
|
"entropy": 6.014222860336304,
|
|
"epoch": 0.1583349542890488,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004999270016149486,
|
|
"loss": 6.0552,
|
|
"mean_token_accuracy": 0.135345246642828,
|
|
"num_tokens": 3541974.0,
|
|
"step": 2035
|
|
},
|
|
{
|
|
"entropy": 6.0979108810424805,
|
|
"epoch": 0.1587239836607664,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004999262939661596,
|
|
"loss": 6.0053,
|
|
"mean_token_accuracy": 0.14074506014585494,
|
|
"num_tokens": 3550436.0,
|
|
"step": 2040
|
|
},
|
|
{
|
|
"entropy": 6.0076916217803955,
|
|
"epoch": 0.15911301303248396,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999255829044721,
|
|
"loss": 5.9924,
|
|
"mean_token_accuracy": 0.13720230460166932,
|
|
"num_tokens": 3558283.0,
|
|
"step": 2045
|
|
},
|
|
{
|
|
"entropy": 5.98124508857727,
|
|
"epoch": 0.15950204240420152,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999248684298968,
|
|
"loss": 5.9144,
|
|
"mean_token_accuracy": 0.13598482608795165,
|
|
"num_tokens": 3566968.0,
|
|
"step": 2050
|
|
},
|
|
{
|
|
"entropy": 6.084092378616333,
|
|
"epoch": 0.15989107177591907,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999241505424447,
|
|
"loss": 6.0515,
|
|
"mean_token_accuracy": 0.13149691969156266,
|
|
"num_tokens": 3575580.0,
|
|
"step": 2055
|
|
},
|
|
{
|
|
"entropy": 6.089936590194702,
|
|
"epoch": 0.16028010114763663,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999234292421265,
|
|
"loss": 6.1059,
|
|
"mean_token_accuracy": 0.13127018511295319,
|
|
"num_tokens": 3584389.0,
|
|
"step": 2060
|
|
},
|
|
{
|
|
"entropy": 6.056532669067383,
|
|
"epoch": 0.16066913051935422,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999227045289535,
|
|
"loss": 5.9472,
|
|
"mean_token_accuracy": 0.13698288649320603,
|
|
"num_tokens": 3593009.0,
|
|
"step": 2065
|
|
},
|
|
{
|
|
"entropy": 5.953234529495239,
|
|
"epoch": 0.16105815989107178,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004999219764029363,
|
|
"loss": 5.9771,
|
|
"mean_token_accuracy": 0.13605064973235131,
|
|
"num_tokens": 3601914.0,
|
|
"step": 2070
|
|
},
|
|
{
|
|
"entropy": 5.964067173004151,
|
|
"epoch": 0.16144718926278934,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999212448640861,
|
|
"loss": 5.9458,
|
|
"mean_token_accuracy": 0.1372133381664753,
|
|
"num_tokens": 3609883.0,
|
|
"step": 2075
|
|
},
|
|
{
|
|
"entropy": 5.984559869766235,
|
|
"epoch": 0.1618362186345069,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004999205099124141,
|
|
"loss": 5.8776,
|
|
"mean_token_accuracy": 0.14128663763403893,
|
|
"num_tokens": 3618103.0,
|
|
"step": 2080
|
|
},
|
|
{
|
|
"entropy": 6.163353109359742,
|
|
"epoch": 0.16222524800622448,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999197715479313,
|
|
"loss": 6.1465,
|
|
"mean_token_accuracy": 0.13133149743080139,
|
|
"num_tokens": 3625861.0,
|
|
"step": 2085
|
|
},
|
|
{
|
|
"entropy": 5.983381605148315,
|
|
"epoch": 0.16261427737794204,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999190297706489,
|
|
"loss": 5.9377,
|
|
"mean_token_accuracy": 0.13726572021842004,
|
|
"num_tokens": 3634498.0,
|
|
"step": 2090
|
|
},
|
|
{
|
|
"entropy": 5.900870990753174,
|
|
"epoch": 0.1630033067496596,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999182845805783,
|
|
"loss": 5.903,
|
|
"mean_token_accuracy": 0.13446398749947547,
|
|
"num_tokens": 3644186.0,
|
|
"step": 2095
|
|
},
|
|
{
|
|
"entropy": 5.978477811813354,
|
|
"epoch": 0.16339233612137716,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999175359777306,
|
|
"loss": 6.0346,
|
|
"mean_token_accuracy": 0.13290069103240967,
|
|
"num_tokens": 3652831.0,
|
|
"step": 2100
|
|
},
|
|
{
|
|
"entropy": 6.1047296047210695,
|
|
"epoch": 0.16378136549309472,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999167839621174,
|
|
"loss": 5.9013,
|
|
"mean_token_accuracy": 0.13871957510709762,
|
|
"num_tokens": 3661230.0,
|
|
"step": 2105
|
|
},
|
|
{
|
|
"entropy": 6.000889015197754,
|
|
"epoch": 0.1641703948648123,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999160285337501,
|
|
"loss": 6.0459,
|
|
"mean_token_accuracy": 0.1324700802564621,
|
|
"num_tokens": 3669250.0,
|
|
"step": 2110
|
|
},
|
|
{
|
|
"entropy": 6.074883890151978,
|
|
"epoch": 0.16455942423652986,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999152696926399,
|
|
"loss": 6.0221,
|
|
"mean_token_accuracy": 0.1307499475777149,
|
|
"num_tokens": 3677568.0,
|
|
"step": 2115
|
|
},
|
|
{
|
|
"entropy": 6.026207399368286,
|
|
"epoch": 0.16494845360824742,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999145074387985,
|
|
"loss": 6.0186,
|
|
"mean_token_accuracy": 0.14040926843881607,
|
|
"num_tokens": 3685488.0,
|
|
"step": 2120
|
|
},
|
|
{
|
|
"entropy": 5.997472858428955,
|
|
"epoch": 0.16533748297996498,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999137417722374,
|
|
"loss": 5.9989,
|
|
"mean_token_accuracy": 0.13259485363960266,
|
|
"num_tokens": 3694357.0,
|
|
"step": 2125
|
|
},
|
|
{
|
|
"entropy": 6.097675323486328,
|
|
"epoch": 0.16572651235168256,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004999129726929684,
|
|
"loss": 6.0534,
|
|
"mean_token_accuracy": 0.1371625356376171,
|
|
"num_tokens": 3703173.0,
|
|
"step": 2130
|
|
},
|
|
{
|
|
"entropy": 6.020848321914673,
|
|
"epoch": 0.16611554172340012,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999122002010029,
|
|
"loss": 6.0185,
|
|
"mean_token_accuracy": 0.13592875599861146,
|
|
"num_tokens": 3712070.0,
|
|
"step": 2135
|
|
},
|
|
{
|
|
"entropy": 6.032235813140869,
|
|
"epoch": 0.16650457109511768,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004999114242963527,
|
|
"loss": 5.9062,
|
|
"mean_token_accuracy": 0.14077977910637857,
|
|
"num_tokens": 3720245.0,
|
|
"step": 2140
|
|
},
|
|
{
|
|
"entropy": 5.971114015579223,
|
|
"epoch": 0.16689360046683524,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999106449790298,
|
|
"loss": 6.0256,
|
|
"mean_token_accuracy": 0.1356363706290722,
|
|
"num_tokens": 3730064.0,
|
|
"step": 2145
|
|
},
|
|
{
|
|
"entropy": 6.012196159362793,
|
|
"epoch": 0.1672826298385528,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004999098622490458,
|
|
"loss": 5.9673,
|
|
"mean_token_accuracy": 0.13840274810791015,
|
|
"num_tokens": 3738741.0,
|
|
"step": 2150
|
|
},
|
|
{
|
|
"entropy": 6.0317319393157955,
|
|
"epoch": 0.16767165921027039,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999090761064125,
|
|
"loss": 6.0445,
|
|
"mean_token_accuracy": 0.13798771649599076,
|
|
"num_tokens": 3747472.0,
|
|
"step": 2155
|
|
},
|
|
{
|
|
"entropy": 6.042453670501709,
|
|
"epoch": 0.16806068858198794,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000499908286551142,
|
|
"loss": 6.0614,
|
|
"mean_token_accuracy": 0.1325035110116005,
|
|
"num_tokens": 3756643.0,
|
|
"step": 2160
|
|
},
|
|
{
|
|
"entropy": 6.098313522338867,
|
|
"epoch": 0.1684497179537055,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999074935832463,
|
|
"loss": 6.1743,
|
|
"mean_token_accuracy": 0.1302264779806137,
|
|
"num_tokens": 3765490.0,
|
|
"step": 2165
|
|
},
|
|
{
|
|
"entropy": 6.109912395477295,
|
|
"epoch": 0.16883874732542306,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999066972027373,
|
|
"loss": 5.9293,
|
|
"mean_token_accuracy": 0.13885341733694076,
|
|
"num_tokens": 3773063.0,
|
|
"step": 2170
|
|
},
|
|
{
|
|
"entropy": 6.057087755203247,
|
|
"epoch": 0.16922777669714065,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999058974096271,
|
|
"loss": 6.081,
|
|
"mean_token_accuracy": 0.12848760411143303,
|
|
"num_tokens": 3781763.0,
|
|
"step": 2175
|
|
},
|
|
{
|
|
"entropy": 6.050684452056885,
|
|
"epoch": 0.1696168060688582,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000499905094203928,
|
|
"loss": 6.0706,
|
|
"mean_token_accuracy": 0.13044458702206613,
|
|
"num_tokens": 3790582.0,
|
|
"step": 2180
|
|
},
|
|
{
|
|
"entropy": 5.997987556457519,
|
|
"epoch": 0.17000583544057576,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000499904287585652,
|
|
"loss": 5.8916,
|
|
"mean_token_accuracy": 0.13762697726488113,
|
|
"num_tokens": 3798745.0,
|
|
"step": 2185
|
|
},
|
|
{
|
|
"entropy": 5.99886155128479,
|
|
"epoch": 0.17039486481229332,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999034775548113,
|
|
"loss": 5.9924,
|
|
"mean_token_accuracy": 0.13636661395430566,
|
|
"num_tokens": 3806901.0,
|
|
"step": 2190
|
|
},
|
|
{
|
|
"entropy": 6.0307700634002686,
|
|
"epoch": 0.17078389418401088,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004999026641114185,
|
|
"loss": 5.9387,
|
|
"mean_token_accuracy": 0.14335163310170174,
|
|
"num_tokens": 3815742.0,
|
|
"step": 2195
|
|
},
|
|
{
|
|
"entropy": 5.951791095733642,
|
|
"epoch": 0.17117292355572847,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999018472554857,
|
|
"loss": 6.0196,
|
|
"mean_token_accuracy": 0.13228272050619125,
|
|
"num_tokens": 3824468.0,
|
|
"step": 2200
|
|
},
|
|
{
|
|
"entropy": 6.030127143859863,
|
|
"epoch": 0.17156195292744603,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999010269870253,
|
|
"loss": 5.9848,
|
|
"mean_token_accuracy": 0.14022162035107613,
|
|
"num_tokens": 3832834.0,
|
|
"step": 2205
|
|
},
|
|
{
|
|
"entropy": 6.018565368652344,
|
|
"epoch": 0.17195098229916359,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999002033060498,
|
|
"loss": 6.0239,
|
|
"mean_token_accuracy": 0.14021265134215355,
|
|
"num_tokens": 3841780.0,
|
|
"step": 2210
|
|
},
|
|
{
|
|
"entropy": 6.101462125778198,
|
|
"epoch": 0.17234001167088114,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004998993762125716,
|
|
"loss": 6.1403,
|
|
"mean_token_accuracy": 0.1279483050107956,
|
|
"num_tokens": 3849840.0,
|
|
"step": 2215
|
|
},
|
|
{
|
|
"entropy": 6.102045392990112,
|
|
"epoch": 0.17272904104259873,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004998985457066034,
|
|
"loss": 6.0699,
|
|
"mean_token_accuracy": 0.12550090849399567,
|
|
"num_tokens": 3858204.0,
|
|
"step": 2220
|
|
},
|
|
{
|
|
"entropy": 6.012039756774902,
|
|
"epoch": 0.1731180704143163,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998977117881576,
|
|
"loss": 6.0052,
|
|
"mean_token_accuracy": 0.13568017780780792,
|
|
"num_tokens": 3866615.0,
|
|
"step": 2225
|
|
},
|
|
{
|
|
"entropy": 6.037418842315674,
|
|
"epoch": 0.17350709978603385,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004998968744572472,
|
|
"loss": 6.0343,
|
|
"mean_token_accuracy": 0.13920788690447808,
|
|
"num_tokens": 3876003.0,
|
|
"step": 2230
|
|
},
|
|
{
|
|
"entropy": 6.0176434993743895,
|
|
"epoch": 0.1738961291577514,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004998960337138845,
|
|
"loss": 5.9605,
|
|
"mean_token_accuracy": 0.1377207651734352,
|
|
"num_tokens": 3884362.0,
|
|
"step": 2235
|
|
},
|
|
{
|
|
"entropy": 5.990269565582276,
|
|
"epoch": 0.17428515852946896,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004998951895580826,
|
|
"loss": 5.9158,
|
|
"mean_token_accuracy": 0.13989226818084716,
|
|
"num_tokens": 3893177.0,
|
|
"step": 2240
|
|
},
|
|
{
|
|
"entropy": 6.01600284576416,
|
|
"epoch": 0.17467418790118655,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004998943419898542,
|
|
"loss": 5.9773,
|
|
"mean_token_accuracy": 0.1380767658352852,
|
|
"num_tokens": 3903006.0,
|
|
"step": 2245
|
|
},
|
|
{
|
|
"entropy": 5.9797093868255615,
|
|
"epoch": 0.1750632172729041,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004998934910092119,
|
|
"loss": 5.8372,
|
|
"mean_token_accuracy": 0.13846131414175034,
|
|
"num_tokens": 3912256.0,
|
|
"step": 2250
|
|
},
|
|
{
|
|
"entropy": 5.916180229187011,
|
|
"epoch": 0.17545224664462167,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004998926366161689,
|
|
"loss": 5.9986,
|
|
"mean_token_accuracy": 0.13596335276961327,
|
|
"num_tokens": 3921121.0,
|
|
"step": 2255
|
|
},
|
|
{
|
|
"entropy": 6.018570613861084,
|
|
"epoch": 0.17584127601633923,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004998917788107383,
|
|
"loss": 5.9479,
|
|
"mean_token_accuracy": 0.139829271286726,
|
|
"num_tokens": 3929348.0,
|
|
"step": 2260
|
|
},
|
|
{
|
|
"entropy": 6.029901313781738,
|
|
"epoch": 0.17623030538805678,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004998909175929326,
|
|
"loss": 6.1262,
|
|
"mean_token_accuracy": 0.13413718938827515,
|
|
"num_tokens": 3938073.0,
|
|
"step": 2265
|
|
},
|
|
{
|
|
"entropy": 6.116082048416137,
|
|
"epoch": 0.17661933475977437,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004998900529627653,
|
|
"loss": 6.1048,
|
|
"mean_token_accuracy": 0.13597819358110427,
|
|
"num_tokens": 3946641.0,
|
|
"step": 2270
|
|
},
|
|
{
|
|
"entropy": 6.074714040756225,
|
|
"epoch": 0.17700836413149193,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004998891849202495,
|
|
"loss": 5.9587,
|
|
"mean_token_accuracy": 0.14048855975270272,
|
|
"num_tokens": 3954586.0,
|
|
"step": 2275
|
|
},
|
|
{
|
|
"entropy": 6.009363508224487,
|
|
"epoch": 0.1773973935032095,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000499888313465398,
|
|
"loss": 6.0295,
|
|
"mean_token_accuracy": 0.13712368234992028,
|
|
"num_tokens": 3963745.0,
|
|
"step": 2280
|
|
},
|
|
{
|
|
"entropy": 5.937222337722778,
|
|
"epoch": 0.17778642287492705,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004998874385982247,
|
|
"loss": 5.8522,
|
|
"mean_token_accuracy": 0.1412455268204212,
|
|
"num_tokens": 3972452.0,
|
|
"step": 2285
|
|
},
|
|
{
|
|
"entropy": 5.94044041633606,
|
|
"epoch": 0.17817545224664463,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004998865603187421,
|
|
"loss": 5.9574,
|
|
"mean_token_accuracy": 0.13704333379864692,
|
|
"num_tokens": 3980770.0,
|
|
"step": 2290
|
|
},
|
|
{
|
|
"entropy": 6.060723733901978,
|
|
"epoch": 0.1785644816183622,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000499885678626964,
|
|
"loss": 5.9805,
|
|
"mean_token_accuracy": 0.13396030068397521,
|
|
"num_tokens": 3989545.0,
|
|
"step": 2295
|
|
},
|
|
{
|
|
"entropy": 6.062776803970337,
|
|
"epoch": 0.17895351099007975,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998847935229038,
|
|
"loss": 5.9424,
|
|
"mean_token_accuracy": 0.13457537293434144,
|
|
"num_tokens": 3998034.0,
|
|
"step": 2300
|
|
},
|
|
{
|
|
"entropy": 5.905241298675537,
|
|
"epoch": 0.1793425403617973,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004998839050065746,
|
|
"loss": 5.9822,
|
|
"mean_token_accuracy": 0.14144275784492494,
|
|
"num_tokens": 4007110.0,
|
|
"step": 2305
|
|
},
|
|
{
|
|
"entropy": 6.042173862457275,
|
|
"epoch": 0.17973156973351487,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004998830130779902,
|
|
"loss": 6.0362,
|
|
"mean_token_accuracy": 0.12785631343722342,
|
|
"num_tokens": 4015930.0,
|
|
"step": 2310
|
|
},
|
|
{
|
|
"entropy": 5.92177267074585,
|
|
"epoch": 0.18012059910523245,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000499882117737164,
|
|
"loss": 5.8567,
|
|
"mean_token_accuracy": 0.13938324376940728,
|
|
"num_tokens": 4024510.0,
|
|
"step": 2315
|
|
},
|
|
{
|
|
"entropy": 5.9428199291229244,
|
|
"epoch": 0.18050962847695,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004998812189841096,
|
|
"loss": 5.9629,
|
|
"mean_token_accuracy": 0.13904105722904206,
|
|
"num_tokens": 4033714.0,
|
|
"step": 2320
|
|
},
|
|
{
|
|
"entropy": 6.135042381286621,
|
|
"epoch": 0.18089865784866757,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004998803168188407,
|
|
"loss": 6.1461,
|
|
"mean_token_accuracy": 0.12715203911066056,
|
|
"num_tokens": 4042376.0,
|
|
"step": 2325
|
|
},
|
|
{
|
|
"entropy": 6.03497052192688,
|
|
"epoch": 0.18128768722038513,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004998794112413708,
|
|
"loss": 5.9316,
|
|
"mean_token_accuracy": 0.1389988273382187,
|
|
"num_tokens": 4050521.0,
|
|
"step": 2330
|
|
},
|
|
{
|
|
"entropy": 6.097191667556762,
|
|
"epoch": 0.18167671659210272,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004998785022517137,
|
|
"loss": 6.0873,
|
|
"mean_token_accuracy": 0.13467619195580482,
|
|
"num_tokens": 4059384.0,
|
|
"step": 2335
|
|
},
|
|
{
|
|
"entropy": 5.945719146728516,
|
|
"epoch": 0.18206574596382027,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004998775898498835,
|
|
"loss": 5.947,
|
|
"mean_token_accuracy": 0.1388249836862087,
|
|
"num_tokens": 4067655.0,
|
|
"step": 2340
|
|
},
|
|
{
|
|
"entropy": 6.028331184387207,
|
|
"epoch": 0.18245477533553783,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004998766740358936,
|
|
"loss": 5.9342,
|
|
"mean_token_accuracy": 0.1423063322901726,
|
|
"num_tokens": 4075828.0,
|
|
"step": 2345
|
|
},
|
|
{
|
|
"entropy": 6.014834260940551,
|
|
"epoch": 0.1828438047072554,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004998757548097582,
|
|
"loss": 5.9053,
|
|
"mean_token_accuracy": 0.14048654288053514,
|
|
"num_tokens": 4083796.0,
|
|
"step": 2350
|
|
},
|
|
{
|
|
"entropy": 5.980800151824951,
|
|
"epoch": 0.18323283407897295,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004998748321714911,
|
|
"loss": 6.0421,
|
|
"mean_token_accuracy": 0.13735400661826133,
|
|
"num_tokens": 4092981.0,
|
|
"step": 2355
|
|
},
|
|
{
|
|
"entropy": 6.020400857925415,
|
|
"epoch": 0.18362186345069054,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004998739061211065,
|
|
"loss": 5.8484,
|
|
"mean_token_accuracy": 0.14194852709770203,
|
|
"num_tokens": 4101363.0,
|
|
"step": 2360
|
|
},
|
|
{
|
|
"entropy": 5.96309461593628,
|
|
"epoch": 0.1840108928224081,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004998729766586181,
|
|
"loss": 5.9272,
|
|
"mean_token_accuracy": 0.1333435907959938,
|
|
"num_tokens": 4110164.0,
|
|
"step": 2365
|
|
},
|
|
{
|
|
"entropy": 6.044630527496338,
|
|
"epoch": 0.18439992219412565,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004998720437840403,
|
|
"loss": 6.0444,
|
|
"mean_token_accuracy": 0.13811287730932237,
|
|
"num_tokens": 4119098.0,
|
|
"step": 2370
|
|
},
|
|
{
|
|
"entropy": 5.991950607299804,
|
|
"epoch": 0.1847889515658432,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004998711074973871,
|
|
"loss": 5.9532,
|
|
"mean_token_accuracy": 0.13917487487196922,
|
|
"num_tokens": 4127522.0,
|
|
"step": 2375
|
|
},
|
|
{
|
|
"entropy": 6.0055859088897705,
|
|
"epoch": 0.1851779809375608,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004998701677986728,
|
|
"loss": 5.9803,
|
|
"mean_token_accuracy": 0.14277126044034957,
|
|
"num_tokens": 4136311.0,
|
|
"step": 2380
|
|
},
|
|
{
|
|
"entropy": 5.935305976867676,
|
|
"epoch": 0.18556701030927836,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004998692246879116,
|
|
"loss": 5.9124,
|
|
"mean_token_accuracy": 0.13691533505916595,
|
|
"num_tokens": 4145160.0,
|
|
"step": 2385
|
|
},
|
|
{
|
|
"entropy": 6.005577945709229,
|
|
"epoch": 0.18595603968099592,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004998682781651178,
|
|
"loss": 5.886,
|
|
"mean_token_accuracy": 0.14444762617349624,
|
|
"num_tokens": 4153921.0,
|
|
"step": 2390
|
|
},
|
|
{
|
|
"entropy": 5.912683391571045,
|
|
"epoch": 0.18634506905271347,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004998673282303059,
|
|
"loss": 5.9582,
|
|
"mean_token_accuracy": 0.13400443345308305,
|
|
"num_tokens": 4162580.0,
|
|
"step": 2395
|
|
},
|
|
{
|
|
"entropy": 5.9940591812133786,
|
|
"epoch": 0.18673409842443103,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004998663748834901,
|
|
"loss": 5.9552,
|
|
"mean_token_accuracy": 0.14112788587808608,
|
|
"num_tokens": 4170623.0,
|
|
"step": 2400
|
|
},
|
|
{
|
|
"entropy": 5.947180700302124,
|
|
"epoch": 0.18712312779614862,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004998654181246851,
|
|
"loss": 5.9519,
|
|
"mean_token_accuracy": 0.14752146303653718,
|
|
"num_tokens": 4178724.0,
|
|
"step": 2405
|
|
},
|
|
{
|
|
"entropy": 5.964427280426025,
|
|
"epoch": 0.18751215716786618,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004998644579539052,
|
|
"loss": 5.963,
|
|
"mean_token_accuracy": 0.13656028136610984,
|
|
"num_tokens": 4187773.0,
|
|
"step": 2410
|
|
},
|
|
{
|
|
"entropy": 6.009492588043213,
|
|
"epoch": 0.18790118653958374,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000499863494371165,
|
|
"loss": 5.9618,
|
|
"mean_token_accuracy": 0.13550449684262275,
|
|
"num_tokens": 4196628.0,
|
|
"step": 2415
|
|
},
|
|
{
|
|
"entropy": 5.984348201751709,
|
|
"epoch": 0.1882902159113013,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004998625273764793,
|
|
"loss": 5.9827,
|
|
"mean_token_accuracy": 0.13410525098443032,
|
|
"num_tokens": 4205090.0,
|
|
"step": 2420
|
|
},
|
|
{
|
|
"entropy": 5.990939712524414,
|
|
"epoch": 0.18867924528301888,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004998615569698626,
|
|
"loss": 5.8965,
|
|
"mean_token_accuracy": 0.1415567897260189,
|
|
"num_tokens": 4212757.0,
|
|
"step": 2425
|
|
},
|
|
{
|
|
"entropy": 5.883493232727051,
|
|
"epoch": 0.18906827465473644,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004998605831513296,
|
|
"loss": 5.9637,
|
|
"mean_token_accuracy": 0.14001091420650483,
|
|
"num_tokens": 4221556.0,
|
|
"step": 2430
|
|
},
|
|
{
|
|
"entropy": 5.936648797988892,
|
|
"epoch": 0.189457304026454,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004998596059208953,
|
|
"loss": 5.9587,
|
|
"mean_token_accuracy": 0.13833684399724006,
|
|
"num_tokens": 4231524.0,
|
|
"step": 2435
|
|
},
|
|
{
|
|
"entropy": 6.036439371109009,
|
|
"epoch": 0.18984633339817156,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004998586252785743,
|
|
"loss": 5.9826,
|
|
"mean_token_accuracy": 0.1431053563952446,
|
|
"num_tokens": 4240229.0,
|
|
"step": 2440
|
|
},
|
|
{
|
|
"entropy": 5.956485605239868,
|
|
"epoch": 0.19023536276988912,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004998576412243816,
|
|
"loss": 5.8587,
|
|
"mean_token_accuracy": 0.14437367022037506,
|
|
"num_tokens": 4248053.0,
|
|
"step": 2445
|
|
},
|
|
{
|
|
"entropy": 5.988489770889283,
|
|
"epoch": 0.1906243921416067,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004998566537583321,
|
|
"loss": 5.9007,
|
|
"mean_token_accuracy": 0.13747418969869613,
|
|
"num_tokens": 4256019.0,
|
|
"step": 2450
|
|
},
|
|
{
|
|
"entropy": 5.89534101486206,
|
|
"epoch": 0.19101342151332426,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004998556628804408,
|
|
"loss": 5.8917,
|
|
"mean_token_accuracy": 0.14226853474974632,
|
|
"num_tokens": 4263805.0,
|
|
"step": 2455
|
|
},
|
|
{
|
|
"entropy": 5.958291482925415,
|
|
"epoch": 0.19140245088504182,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004998546685907225,
|
|
"loss": 5.9534,
|
|
"mean_token_accuracy": 0.13563379049301147,
|
|
"num_tokens": 4272712.0,
|
|
"step": 2460
|
|
},
|
|
{
|
|
"entropy": 6.066695690155029,
|
|
"epoch": 0.19179148025675938,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004998536708891927,
|
|
"loss": 5.8824,
|
|
"mean_token_accuracy": 0.14191587790846824,
|
|
"num_tokens": 4281222.0,
|
|
"step": 2465
|
|
},
|
|
{
|
|
"entropy": 5.9650391101837155,
|
|
"epoch": 0.19218050962847694,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004998526697758663,
|
|
"loss": 6.0121,
|
|
"mean_token_accuracy": 0.13257578536868095,
|
|
"num_tokens": 4290558.0,
|
|
"step": 2470
|
|
},
|
|
{
|
|
"entropy": 6.109343481063843,
|
|
"epoch": 0.19256953900019452,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004998516652507585,
|
|
"loss": 6.0253,
|
|
"mean_token_accuracy": 0.13303112387657165,
|
|
"num_tokens": 4299684.0,
|
|
"step": 2475
|
|
},
|
|
{
|
|
"entropy": 5.899087524414062,
|
|
"epoch": 0.19295856837191208,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004998506573138846,
|
|
"loss": 5.9633,
|
|
"mean_token_accuracy": 0.14104458689689636,
|
|
"num_tokens": 4308938.0,
|
|
"step": 2480
|
|
},
|
|
{
|
|
"entropy": 5.9440470218658445,
|
|
"epoch": 0.19334759774362964,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004998496459652598,
|
|
"loss": 5.8208,
|
|
"mean_token_accuracy": 0.14647359624505044,
|
|
"num_tokens": 4317646.0,
|
|
"step": 2485
|
|
},
|
|
{
|
|
"entropy": 5.964761638641358,
|
|
"epoch": 0.1937366271153472,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004998486312048995,
|
|
"loss": 5.9621,
|
|
"mean_token_accuracy": 0.13583191409707068,
|
|
"num_tokens": 4326876.0,
|
|
"step": 2490
|
|
},
|
|
{
|
|
"entropy": 5.967274475097656,
|
|
"epoch": 0.19412565648706478,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998476130328193,
|
|
"loss": 5.931,
|
|
"mean_token_accuracy": 0.13568915724754332,
|
|
"num_tokens": 4335391.0,
|
|
"step": 2495
|
|
},
|
|
{
|
|
"entropy": 6.055395555496216,
|
|
"epoch": 0.19451468585878234,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004998465914490343,
|
|
"loss": 5.9052,
|
|
"mean_token_accuracy": 0.1406179554760456,
|
|
"num_tokens": 4343253.0,
|
|
"step": 2500
|
|
},
|
|
{
|
|
"entropy": 5.760255670547485,
|
|
"epoch": 0.1949037152304999,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00049984556645356,
|
|
"loss": 5.8742,
|
|
"mean_token_accuracy": 0.14200342074036598,
|
|
"num_tokens": 4352161.0,
|
|
"step": 2505
|
|
},
|
|
{
|
|
"entropy": 5.938892364501953,
|
|
"epoch": 0.19529274460221746,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004998445380464124,
|
|
"loss": 5.8385,
|
|
"mean_token_accuracy": 0.1466829337179661,
|
|
"num_tokens": 4360414.0,
|
|
"step": 2510
|
|
},
|
|
{
|
|
"entropy": 5.896971416473389,
|
|
"epoch": 0.19568177397393502,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004998435062276066,
|
|
"loss": 5.8228,
|
|
"mean_token_accuracy": 0.14513540267944336,
|
|
"num_tokens": 4369375.0,
|
|
"step": 2515
|
|
},
|
|
{
|
|
"entropy": 5.903877830505371,
|
|
"epoch": 0.1960708033456526,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004998424709971586,
|
|
"loss": 5.8483,
|
|
"mean_token_accuracy": 0.14223146587610244,
|
|
"num_tokens": 4378638.0,
|
|
"step": 2520
|
|
},
|
|
{
|
|
"entropy": 5.983705711364746,
|
|
"epoch": 0.19645983271737016,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004998414323550839,
|
|
"loss": 5.8616,
|
|
"mean_token_accuracy": 0.14103932306170464,
|
|
"num_tokens": 4388262.0,
|
|
"step": 2525
|
|
},
|
|
{
|
|
"entropy": 5.874213314056396,
|
|
"epoch": 0.19684886208908772,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004998403903013984,
|
|
"loss": 5.8501,
|
|
"mean_token_accuracy": 0.1444000080227852,
|
|
"num_tokens": 4396894.0,
|
|
"step": 2530
|
|
},
|
|
{
|
|
"entropy": 5.949297761917114,
|
|
"epoch": 0.19723789146080528,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998393448361179,
|
|
"loss": 6.0004,
|
|
"mean_token_accuracy": 0.1377578116953373,
|
|
"num_tokens": 4405455.0,
|
|
"step": 2535
|
|
},
|
|
{
|
|
"entropy": 5.937081432342529,
|
|
"epoch": 0.19762692083252287,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.000499838295959258,
|
|
"loss": 5.8999,
|
|
"mean_token_accuracy": 0.13834612667560578,
|
|
"num_tokens": 4414355.0,
|
|
"step": 2540
|
|
},
|
|
{
|
|
"entropy": 5.8034745216369625,
|
|
"epoch": 0.19801595020424043,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000499837243670835,
|
|
"loss": 5.7847,
|
|
"mean_token_accuracy": 0.14933302402496337,
|
|
"num_tokens": 4422305.0,
|
|
"step": 2545
|
|
},
|
|
{
|
|
"entropy": 5.9695093631744385,
|
|
"epoch": 0.19840497957595798,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004998361879708646,
|
|
"loss": 5.9185,
|
|
"mean_token_accuracy": 0.13912818506360053,
|
|
"num_tokens": 4430813.0,
|
|
"step": 2550
|
|
},
|
|
{
|
|
"entropy": 5.963333559036255,
|
|
"epoch": 0.19879400894767554,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000499835128859363,
|
|
"loss": 5.8774,
|
|
"mean_token_accuracy": 0.14088211506605147,
|
|
"num_tokens": 4440229.0,
|
|
"step": 2555
|
|
},
|
|
{
|
|
"entropy": 5.8513782024383545,
|
|
"epoch": 0.1991830383193931,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004998340663363461,
|
|
"loss": 5.9025,
|
|
"mean_token_accuracy": 0.13724920377135277,
|
|
"num_tokens": 4449417.0,
|
|
"step": 2560
|
|
},
|
|
{
|
|
"entropy": 5.9853545188903805,
|
|
"epoch": 0.1995720676911107,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004998330004018301,
|
|
"loss": 5.944,
|
|
"mean_token_accuracy": 0.13790054023265838,
|
|
"num_tokens": 4457377.0,
|
|
"step": 2565
|
|
},
|
|
{
|
|
"entropy": 5.990766906738282,
|
|
"epoch": 0.19996109706282825,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004998319310558312,
|
|
"loss": 5.8617,
|
|
"mean_token_accuracy": 0.14069739058613778,
|
|
"num_tokens": 4466839.0,
|
|
"step": 2570
|
|
},
|
|
{
|
|
"entropy": 5.904648494720459,
|
|
"epoch": 0.2003501264345458,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004998308582983657,
|
|
"loss": 5.9051,
|
|
"mean_token_accuracy": 0.14068260937929153,
|
|
"num_tokens": 4476369.0,
|
|
"step": 2575
|
|
},
|
|
{
|
|
"entropy": 5.9384589195251465,
|
|
"epoch": 0.20073915580626336,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004998297821294497,
|
|
"loss": 5.9575,
|
|
"mean_token_accuracy": 0.13891851380467415,
|
|
"num_tokens": 4485609.0,
|
|
"step": 2580
|
|
},
|
|
{
|
|
"entropy": 5.939151048660278,
|
|
"epoch": 0.20112818517798095,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004998287025490995,
|
|
"loss": 5.9092,
|
|
"mean_token_accuracy": 0.1407192036509514,
|
|
"num_tokens": 4494535.0,
|
|
"step": 2585
|
|
},
|
|
{
|
|
"entropy": 5.945156764984131,
|
|
"epoch": 0.2015172145496985,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998276195573317,
|
|
"loss": 5.8844,
|
|
"mean_token_accuracy": 0.1363791175186634,
|
|
"num_tokens": 4503133.0,
|
|
"step": 2590
|
|
},
|
|
{
|
|
"entropy": 5.885627603530883,
|
|
"epoch": 0.20190624392141607,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998265331541627,
|
|
"loss": 5.7876,
|
|
"mean_token_accuracy": 0.15038875490427017,
|
|
"num_tokens": 4511465.0,
|
|
"step": 2595
|
|
},
|
|
{
|
|
"entropy": 5.883782386779785,
|
|
"epoch": 0.20229527329313363,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004998254433396088,
|
|
"loss": 5.8499,
|
|
"mean_token_accuracy": 0.14612346962094308,
|
|
"num_tokens": 4520177.0,
|
|
"step": 2600
|
|
},
|
|
{
|
|
"entropy": 5.947019147872925,
|
|
"epoch": 0.20268430266485118,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004998243501136867,
|
|
"loss": 6.0221,
|
|
"mean_token_accuracy": 0.13749735280871392,
|
|
"num_tokens": 4528370.0,
|
|
"step": 2605
|
|
},
|
|
{
|
|
"entropy": 6.0327956199646,
|
|
"epoch": 0.20307333203656877,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004998232534764129,
|
|
"loss": 6.0424,
|
|
"mean_token_accuracy": 0.13159574791789055,
|
|
"num_tokens": 4538258.0,
|
|
"step": 2610
|
|
},
|
|
{
|
|
"entropy": 5.933379316329956,
|
|
"epoch": 0.20346236140828633,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004998221534278041,
|
|
"loss": 5.9334,
|
|
"mean_token_accuracy": 0.13688500002026557,
|
|
"num_tokens": 4547300.0,
|
|
"step": 2615
|
|
},
|
|
{
|
|
"entropy": 6.0140650272369385,
|
|
"epoch": 0.2038513907800039,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998210499678769,
|
|
"loss": 5.9854,
|
|
"mean_token_accuracy": 0.1308668576180935,
|
|
"num_tokens": 4556877.0,
|
|
"step": 2620
|
|
},
|
|
{
|
|
"entropy": 5.907776832580566,
|
|
"epoch": 0.20424042015172145,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004998199430966481,
|
|
"loss": 5.8302,
|
|
"mean_token_accuracy": 0.14112840071320534,
|
|
"num_tokens": 4565999.0,
|
|
"step": 2625
|
|
},
|
|
{
|
|
"entropy": 5.913699102401734,
|
|
"epoch": 0.20462944952343903,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004998188328141346,
|
|
"loss": 5.8793,
|
|
"mean_token_accuracy": 0.13416805639863014,
|
|
"num_tokens": 4574027.0,
|
|
"step": 2630
|
|
},
|
|
{
|
|
"entropy": 5.887786960601806,
|
|
"epoch": 0.2050184788951566,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004998177191203531,
|
|
"loss": 5.8994,
|
|
"mean_token_accuracy": 0.1329669289290905,
|
|
"num_tokens": 4582402.0,
|
|
"step": 2635
|
|
},
|
|
{
|
|
"entropy": 5.92496690750122,
|
|
"epoch": 0.20540750826687415,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004998166020153204,
|
|
"loss": 5.8358,
|
|
"mean_token_accuracy": 0.14105968326330184,
|
|
"num_tokens": 4590381.0,
|
|
"step": 2640
|
|
},
|
|
{
|
|
"entropy": 5.917643356323242,
|
|
"epoch": 0.2057965376385917,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004998154814990538,
|
|
"loss": 5.885,
|
|
"mean_token_accuracy": 0.14099830090999604,
|
|
"num_tokens": 4598910.0,
|
|
"step": 2645
|
|
},
|
|
{
|
|
"entropy": 6.011348581314087,
|
|
"epoch": 0.20618556701030927,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00049981435757157,
|
|
"loss": 6.015,
|
|
"mean_token_accuracy": 0.13125852718949318,
|
|
"num_tokens": 4607400.0,
|
|
"step": 2650
|
|
},
|
|
{
|
|
"entropy": 5.917462635040283,
|
|
"epoch": 0.20657459638202685,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998132302328862,
|
|
"loss": 5.9403,
|
|
"mean_token_accuracy": 0.14050790518522263,
|
|
"num_tokens": 4616510.0,
|
|
"step": 2655
|
|
},
|
|
{
|
|
"entropy": 6.007234954833985,
|
|
"epoch": 0.2069636257537444,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004998120994830195,
|
|
"loss": 5.9072,
|
|
"mean_token_accuracy": 0.14376826882362365,
|
|
"num_tokens": 4624529.0,
|
|
"step": 2660
|
|
},
|
|
{
|
|
"entropy": 5.918785476684571,
|
|
"epoch": 0.20735265512546197,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000499810965321987,
|
|
"loss": 5.8346,
|
|
"mean_token_accuracy": 0.14414578527212143,
|
|
"num_tokens": 4632141.0,
|
|
"step": 2665
|
|
},
|
|
{
|
|
"entropy": 5.9577617168426515,
|
|
"epoch": 0.20774168449717953,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004998098277498059,
|
|
"loss": 6.0381,
|
|
"mean_token_accuracy": 0.1350015841424465,
|
|
"num_tokens": 4640378.0,
|
|
"step": 2670
|
|
},
|
|
{
|
|
"entropy": 5.925170755386352,
|
|
"epoch": 0.2081307138688971,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004998086867664934,
|
|
"loss": 5.8409,
|
|
"mean_token_accuracy": 0.1414250299334526,
|
|
"num_tokens": 4649313.0,
|
|
"step": 2675
|
|
},
|
|
{
|
|
"entropy": 5.9586829662323,
|
|
"epoch": 0.20851974324061467,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000499807542372067,
|
|
"loss": 5.9164,
|
|
"mean_token_accuracy": 0.14138886630535125,
|
|
"num_tokens": 4658272.0,
|
|
"step": 2680
|
|
},
|
|
{
|
|
"entropy": 5.856334686279297,
|
|
"epoch": 0.20890877261233223,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004998063945665439,
|
|
"loss": 5.7767,
|
|
"mean_token_accuracy": 0.14743116796016692,
|
|
"num_tokens": 4665970.0,
|
|
"step": 2685
|
|
},
|
|
{
|
|
"entropy": 5.974782228469849,
|
|
"epoch": 0.2092978019840498,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004998052433499416,
|
|
"loss": 6.0326,
|
|
"mean_token_accuracy": 0.13459649160504342,
|
|
"num_tokens": 4675308.0,
|
|
"step": 2690
|
|
},
|
|
{
|
|
"entropy": 5.90858154296875,
|
|
"epoch": 0.20968683135576735,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004998040887222776,
|
|
"loss": 5.8772,
|
|
"mean_token_accuracy": 0.14054309129714965,
|
|
"num_tokens": 4684316.0,
|
|
"step": 2695
|
|
},
|
|
{
|
|
"entropy": 5.852538108825684,
|
|
"epoch": 0.21007586072748494,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004998029306835693,
|
|
"loss": 5.7932,
|
|
"mean_token_accuracy": 0.1447305828332901,
|
|
"num_tokens": 4693029.0,
|
|
"step": 2700
|
|
},
|
|
{
|
|
"entropy": 5.91006441116333,
|
|
"epoch": 0.2104648900992025,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004998017692338344,
|
|
"loss": 5.9919,
|
|
"mean_token_accuracy": 0.1333250030875206,
|
|
"num_tokens": 4702404.0,
|
|
"step": 2705
|
|
},
|
|
{
|
|
"entropy": 5.972537851333618,
|
|
"epoch": 0.21085391947092005,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004998006043730905,
|
|
"loss": 5.9484,
|
|
"mean_token_accuracy": 0.13651543334126473,
|
|
"num_tokens": 4711126.0,
|
|
"step": 2710
|
|
},
|
|
{
|
|
"entropy": 5.994960069656372,
|
|
"epoch": 0.2112429488426376,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004997994361013551,
|
|
"loss": 5.9405,
|
|
"mean_token_accuracy": 0.14613958448171616,
|
|
"num_tokens": 4719816.0,
|
|
"step": 2715
|
|
},
|
|
{
|
|
"entropy": 5.966370105743408,
|
|
"epoch": 0.21163197821435517,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004997982644186461,
|
|
"loss": 5.8798,
|
|
"mean_token_accuracy": 0.13973141759634017,
|
|
"num_tokens": 4728294.0,
|
|
"step": 2720
|
|
},
|
|
{
|
|
"entropy": 5.888756990432739,
|
|
"epoch": 0.21202100758607276,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004997970893249813,
|
|
"loss": 5.8275,
|
|
"mean_token_accuracy": 0.1435457229614258,
|
|
"num_tokens": 4736708.0,
|
|
"step": 2725
|
|
},
|
|
{
|
|
"entropy": 5.873240041732788,
|
|
"epoch": 0.21241003695779032,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004997959108203785,
|
|
"loss": 6.0039,
|
|
"mean_token_accuracy": 0.13070807754993438,
|
|
"num_tokens": 4744893.0,
|
|
"step": 2730
|
|
},
|
|
{
|
|
"entropy": 6.096560430526734,
|
|
"epoch": 0.21279906632950787,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004997947289048554,
|
|
"loss": 5.9623,
|
|
"mean_token_accuracy": 0.13920049890875816,
|
|
"num_tokens": 4753246.0,
|
|
"step": 2735
|
|
},
|
|
{
|
|
"entropy": 5.931299209594727,
|
|
"epoch": 0.21318809570122543,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004997935435784302,
|
|
"loss": 5.8833,
|
|
"mean_token_accuracy": 0.13352058157324792,
|
|
"num_tokens": 4762229.0,
|
|
"step": 2740
|
|
},
|
|
{
|
|
"entropy": 5.805833244323731,
|
|
"epoch": 0.21357712507294302,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004997923548411208,
|
|
"loss": 5.8366,
|
|
"mean_token_accuracy": 0.14200862497091293,
|
|
"num_tokens": 4771315.0,
|
|
"step": 2745
|
|
},
|
|
{
|
|
"entropy": 5.755913734436035,
|
|
"epoch": 0.21396615444466058,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000499791162692945,
|
|
"loss": 5.7604,
|
|
"mean_token_accuracy": 0.15337736159563065,
|
|
"num_tokens": 4779848.0,
|
|
"step": 2750
|
|
},
|
|
{
|
|
"entropy": 5.984225654602051,
|
|
"epoch": 0.21435518381637814,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004997899671339214,
|
|
"loss": 6.0054,
|
|
"mean_token_accuracy": 0.14065569192171096,
|
|
"num_tokens": 4788939.0,
|
|
"step": 2755
|
|
},
|
|
{
|
|
"entropy": 5.942894124984742,
|
|
"epoch": 0.2147442131880957,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004997887681640675,
|
|
"loss": 5.906,
|
|
"mean_token_accuracy": 0.13755589798092843,
|
|
"num_tokens": 4797719.0,
|
|
"step": 2760
|
|
},
|
|
{
|
|
"entropy": 5.928773069381714,
|
|
"epoch": 0.21513324255981325,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004997875657834021,
|
|
"loss": 5.9602,
|
|
"mean_token_accuracy": 0.1399763911962509,
|
|
"num_tokens": 4805601.0,
|
|
"step": 2765
|
|
},
|
|
{
|
|
"entropy": 6.0012726306915285,
|
|
"epoch": 0.21552227193153084,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004997863599919432,
|
|
"loss": 5.9298,
|
|
"mean_token_accuracy": 0.13780287876725197,
|
|
"num_tokens": 4814993.0,
|
|
"step": 2770
|
|
},
|
|
{
|
|
"entropy": 5.983278465270996,
|
|
"epoch": 0.2159113013032484,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004997851507897089,
|
|
"loss": 5.8699,
|
|
"mean_token_accuracy": 0.14026867374777793,
|
|
"num_tokens": 4824156.0,
|
|
"step": 2775
|
|
},
|
|
{
|
|
"entropy": 5.871163606643677,
|
|
"epoch": 0.21630033067496596,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004997839381767178,
|
|
"loss": 5.9559,
|
|
"mean_token_accuracy": 0.13493574261665345,
|
|
"num_tokens": 4833827.0,
|
|
"step": 2780
|
|
},
|
|
{
|
|
"entropy": 5.923353576660157,
|
|
"epoch": 0.21668936004668352,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004997827221529882,
|
|
"loss": 5.9086,
|
|
"mean_token_accuracy": 0.14079293385148048,
|
|
"num_tokens": 4842801.0,
|
|
"step": 2785
|
|
},
|
|
{
|
|
"entropy": 5.858642721176148,
|
|
"epoch": 0.2170783894184011,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004997815027185386,
|
|
"loss": 5.7611,
|
|
"mean_token_accuracy": 0.14427610188722612,
|
|
"num_tokens": 4850928.0,
|
|
"step": 2790
|
|
},
|
|
{
|
|
"entropy": 5.874434089660644,
|
|
"epoch": 0.21746741879011866,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004997802798733874,
|
|
"loss": 5.8683,
|
|
"mean_token_accuracy": 0.14393499940633775,
|
|
"num_tokens": 4859510.0,
|
|
"step": 2795
|
|
},
|
|
{
|
|
"entropy": 5.975643491744995,
|
|
"epoch": 0.21785644816183622,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004997790536175534,
|
|
"loss": 5.9173,
|
|
"mean_token_accuracy": 0.14145495295524596,
|
|
"num_tokens": 4868201.0,
|
|
"step": 2800
|
|
},
|
|
{
|
|
"entropy": 5.86905689239502,
|
|
"epoch": 0.21824547753355378,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004997778239510548,
|
|
"loss": 5.8335,
|
|
"mean_token_accuracy": 0.14240052700042724,
|
|
"num_tokens": 4876896.0,
|
|
"step": 2805
|
|
},
|
|
{
|
|
"entropy": 5.826552057266236,
|
|
"epoch": 0.21863450690527134,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004997765908739106,
|
|
"loss": 5.7898,
|
|
"mean_token_accuracy": 0.15225823372602462,
|
|
"num_tokens": 4885136.0,
|
|
"step": 2810
|
|
},
|
|
{
|
|
"entropy": 5.826451778411865,
|
|
"epoch": 0.21902353627698892,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004997753543861395,
|
|
"loss": 5.8053,
|
|
"mean_token_accuracy": 0.1449057564139366,
|
|
"num_tokens": 4893277.0,
|
|
"step": 2815
|
|
},
|
|
{
|
|
"entropy": 5.87442626953125,
|
|
"epoch": 0.21941256564870648,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00049977411448776,
|
|
"loss": 5.962,
|
|
"mean_token_accuracy": 0.1370394378900528,
|
|
"num_tokens": 4901977.0,
|
|
"step": 2820
|
|
},
|
|
{
|
|
"entropy": 6.066293048858642,
|
|
"epoch": 0.21980159502042404,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004997728711787912,
|
|
"loss": 5.9498,
|
|
"mean_token_accuracy": 0.13320593908429146,
|
|
"num_tokens": 4910888.0,
|
|
"step": 2825
|
|
},
|
|
{
|
|
"entropy": 5.899124479293823,
|
|
"epoch": 0.2201906243921416,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004997716244592518,
|
|
"loss": 5.9556,
|
|
"mean_token_accuracy": 0.13331344723701477,
|
|
"num_tokens": 4920369.0,
|
|
"step": 2830
|
|
},
|
|
{
|
|
"entropy": 5.970640707015991,
|
|
"epoch": 0.22057965376385918,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004997703743291607,
|
|
"loss": 5.9372,
|
|
"mean_token_accuracy": 0.13818638548254966,
|
|
"num_tokens": 4928799.0,
|
|
"step": 2835
|
|
},
|
|
{
|
|
"entropy": 5.959006452560425,
|
|
"epoch": 0.22096868313557674,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000499769120788537,
|
|
"loss": 5.8186,
|
|
"mean_token_accuracy": 0.14796194583177566,
|
|
"num_tokens": 4937194.0,
|
|
"step": 2840
|
|
},
|
|
{
|
|
"entropy": 5.892886638641357,
|
|
"epoch": 0.2213577125072943,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004997678638373995,
|
|
"loss": 5.9246,
|
|
"mean_token_accuracy": 0.13645815178751947,
|
|
"num_tokens": 4946174.0,
|
|
"step": 2845
|
|
},
|
|
{
|
|
"entropy": 5.890604877471924,
|
|
"epoch": 0.22174674187901186,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004997666034757676,
|
|
"loss": 5.8636,
|
|
"mean_token_accuracy": 0.1371280185878277,
|
|
"num_tokens": 4955376.0,
|
|
"step": 2850
|
|
},
|
|
{
|
|
"entropy": 5.896667575836181,
|
|
"epoch": 0.22213577125072942,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004997653397036603,
|
|
"loss": 5.8672,
|
|
"mean_token_accuracy": 0.14396676495671273,
|
|
"num_tokens": 4964138.0,
|
|
"step": 2855
|
|
},
|
|
{
|
|
"entropy": 5.889484786987305,
|
|
"epoch": 0.222524800622447,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004997640725210965,
|
|
"loss": 5.9614,
|
|
"mean_token_accuracy": 0.13742173463106155,
|
|
"num_tokens": 4973868.0,
|
|
"step": 2860
|
|
},
|
|
{
|
|
"entropy": 5.917964696884155,
|
|
"epoch": 0.22291382999416456,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004997628019280958,
|
|
"loss": 5.8382,
|
|
"mean_token_accuracy": 0.1428116887807846,
|
|
"num_tokens": 4982687.0,
|
|
"step": 2865
|
|
},
|
|
{
|
|
"entropy": 5.931079006195068,
|
|
"epoch": 0.22330285936588212,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004997615279246773,
|
|
"loss": 5.8865,
|
|
"mean_token_accuracy": 0.13743261098861695,
|
|
"num_tokens": 4992072.0,
|
|
"step": 2870
|
|
},
|
|
{
|
|
"entropy": 5.911539316177368,
|
|
"epoch": 0.22369188873759968,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004997602505108603,
|
|
"loss": 5.8446,
|
|
"mean_token_accuracy": 0.1401855692267418,
|
|
"num_tokens": 5000551.0,
|
|
"step": 2875
|
|
},
|
|
{
|
|
"entropy": 5.937168121337891,
|
|
"epoch": 0.22408091810931724,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004997589696866644,
|
|
"loss": 5.9994,
|
|
"mean_token_accuracy": 0.13774950057268143,
|
|
"num_tokens": 5009292.0,
|
|
"step": 2880
|
|
},
|
|
{
|
|
"entropy": 5.91554889678955,
|
|
"epoch": 0.22446994748103483,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004997576854521088,
|
|
"loss": 5.8535,
|
|
"mean_token_accuracy": 0.13967245817184448,
|
|
"num_tokens": 5018407.0,
|
|
"step": 2885
|
|
},
|
|
{
|
|
"entropy": 5.8885914325714115,
|
|
"epoch": 0.22485897685275238,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000499756397807213,
|
|
"loss": 5.9008,
|
|
"mean_token_accuracy": 0.1394205868244171,
|
|
"num_tokens": 5027353.0,
|
|
"step": 2890
|
|
},
|
|
{
|
|
"entropy": 6.03417592048645,
|
|
"epoch": 0.22524800622446994,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004997551067519966,
|
|
"loss": 5.9215,
|
|
"mean_token_accuracy": 0.13638510555028915,
|
|
"num_tokens": 5036476.0,
|
|
"step": 2895
|
|
},
|
|
{
|
|
"entropy": 5.861401844024658,
|
|
"epoch": 0.2256370355961875,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004997538122864792,
|
|
"loss": 5.8525,
|
|
"mean_token_accuracy": 0.13833182156085969,
|
|
"num_tokens": 5045132.0,
|
|
"step": 2900
|
|
},
|
|
{
|
|
"entropy": 5.916049289703369,
|
|
"epoch": 0.2260260649679051,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004997525144106804,
|
|
"loss": 5.872,
|
|
"mean_token_accuracy": 0.14037140905857087,
|
|
"num_tokens": 5053665.0,
|
|
"step": 2905
|
|
},
|
|
{
|
|
"entropy": 5.922544813156128,
|
|
"epoch": 0.22641509433962265,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00049975121312462,
|
|
"loss": 5.8271,
|
|
"mean_token_accuracy": 0.14556183218955993,
|
|
"num_tokens": 5062516.0,
|
|
"step": 2910
|
|
},
|
|
{
|
|
"entropy": 5.899590253829956,
|
|
"epoch": 0.2268041237113402,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004997499084283177,
|
|
"loss": 5.8772,
|
|
"mean_token_accuracy": 0.13606662452220916,
|
|
"num_tokens": 5071260.0,
|
|
"step": 2915
|
|
},
|
|
{
|
|
"entropy": 5.827817678451538,
|
|
"epoch": 0.22719315308305776,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004997486003217932,
|
|
"loss": 5.8196,
|
|
"mean_token_accuracy": 0.1497701920568943,
|
|
"num_tokens": 5079215.0,
|
|
"step": 2920
|
|
},
|
|
{
|
|
"entropy": 5.8816290378570555,
|
|
"epoch": 0.22758218245477532,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004997472888050664,
|
|
"loss": 5.8938,
|
|
"mean_token_accuracy": 0.14027459546923637,
|
|
"num_tokens": 5088404.0,
|
|
"step": 2925
|
|
},
|
|
{
|
|
"entropy": 5.900744438171387,
|
|
"epoch": 0.2279712118264929,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004997459738781573,
|
|
"loss": 5.8239,
|
|
"mean_token_accuracy": 0.1431146442890167,
|
|
"num_tokens": 5096756.0,
|
|
"step": 2930
|
|
},
|
|
{
|
|
"entropy": 5.979656934738159,
|
|
"epoch": 0.22836024119821047,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004997446555410857,
|
|
"loss": 5.9904,
|
|
"mean_token_accuracy": 0.13891934603452682,
|
|
"num_tokens": 5106160.0,
|
|
"step": 2935
|
|
},
|
|
{
|
|
"entropy": 5.7854640007019045,
|
|
"epoch": 0.22874927056992803,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004997433337938716,
|
|
"loss": 5.9235,
|
|
"mean_token_accuracy": 0.14122586995363234,
|
|
"num_tokens": 5114915.0,
|
|
"step": 2940
|
|
},
|
|
{
|
|
"entropy": 5.964998531341553,
|
|
"epoch": 0.22913829994164558,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004997420086365351,
|
|
"loss": 5.8379,
|
|
"mean_token_accuracy": 0.1387510970234871,
|
|
"num_tokens": 5123249.0,
|
|
"step": 2945
|
|
},
|
|
{
|
|
"entropy": 5.894250869750977,
|
|
"epoch": 0.22952732931336317,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004997406800690966,
|
|
"loss": 5.8134,
|
|
"mean_token_accuracy": 0.138453159481287,
|
|
"num_tokens": 5131906.0,
|
|
"step": 2950
|
|
},
|
|
{
|
|
"entropy": 5.863798522949219,
|
|
"epoch": 0.22991635868508073,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004997393480915758,
|
|
"loss": 5.8003,
|
|
"mean_token_accuracy": 0.146034524589777,
|
|
"num_tokens": 5140740.0,
|
|
"step": 2955
|
|
},
|
|
{
|
|
"entropy": 5.900701189041138,
|
|
"epoch": 0.2303053880567983,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004997380127039931,
|
|
"loss": 5.9917,
|
|
"mean_token_accuracy": 0.13965021297335625,
|
|
"num_tokens": 5149748.0,
|
|
"step": 2960
|
|
},
|
|
{
|
|
"entropy": 5.876333379745484,
|
|
"epoch": 0.23069441742851585,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004997366739063688,
|
|
"loss": 5.719,
|
|
"mean_token_accuracy": 0.14996112510561943,
|
|
"num_tokens": 5158475.0,
|
|
"step": 2965
|
|
},
|
|
{
|
|
"entropy": 5.8662495613098145,
|
|
"epoch": 0.2310834468002334,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004997353316987231,
|
|
"loss": 5.913,
|
|
"mean_token_accuracy": 0.13812702000141144,
|
|
"num_tokens": 5166593.0,
|
|
"step": 2970
|
|
},
|
|
{
|
|
"entropy": 5.93091893196106,
|
|
"epoch": 0.231472476171951,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004997339860810765,
|
|
"loss": 5.8913,
|
|
"mean_token_accuracy": 0.14304886758327484,
|
|
"num_tokens": 5175557.0,
|
|
"step": 2975
|
|
},
|
|
{
|
|
"entropy": 5.873473691940307,
|
|
"epoch": 0.23186150554366855,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004997326370534495,
|
|
"loss": 5.7973,
|
|
"mean_token_accuracy": 0.14339174702763557,
|
|
"num_tokens": 5184140.0,
|
|
"step": 2980
|
|
},
|
|
{
|
|
"entropy": 5.962021112442017,
|
|
"epoch": 0.2322505349153861,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004997312846158622,
|
|
"loss": 5.8895,
|
|
"mean_token_accuracy": 0.13540481626987458,
|
|
"num_tokens": 5192347.0,
|
|
"step": 2985
|
|
},
|
|
{
|
|
"entropy": 5.857995939254761,
|
|
"epoch": 0.23263956428710367,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004997299287683355,
|
|
"loss": 5.8516,
|
|
"mean_token_accuracy": 0.1456963911652565,
|
|
"num_tokens": 5201327.0,
|
|
"step": 2990
|
|
},
|
|
{
|
|
"entropy": 5.914484262466431,
|
|
"epoch": 0.23302859365882125,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004997285695108898,
|
|
"loss": 5.9333,
|
|
"mean_token_accuracy": 0.14006564170122146,
|
|
"num_tokens": 5209873.0,
|
|
"step": 2995
|
|
},
|
|
{
|
|
"entropy": 5.987733602523804,
|
|
"epoch": 0.2334176230305388,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004997272068435458,
|
|
"loss": 5.8368,
|
|
"mean_token_accuracy": 0.14314770549535752,
|
|
"num_tokens": 5219176.0,
|
|
"step": 3000
|
|
},
|
|
{
|
|
"epoch": 0.2334176230305388,
|
|
"eval_entropy": 5.733757502672417,
|
|
"eval_loss": 5.909061431884766,
|
|
"eval_mean_token_accuracy": 0.1476683286819123,
|
|
"eval_num_tokens": 5219176.0,
|
|
"eval_runtime": 28.6428,
|
|
"eval_samples_per_second": 1450.906,
|
|
"eval_steps_per_second": 181.372,
|
|
"step": 3000
|
|
}
|
|
],
|
|
"logging_steps": 5,
|
|
"max_steps": 128520,
|
|
"num_input_tokens_seen": 0,
|
|
"num_train_epochs": 10,
|
|
"save_steps": 3000,
|
|
"stateful_callbacks": {
|
|
"TrainerControl": {
|
|
"args": {
|
|
"should_epoch_stop": false,
|
|
"should_evaluate": false,
|
|
"should_log": false,
|
|
"should_save": true,
|
|
"should_training_stop": false
|
|
},
|
|
"attributes": {}
|
|
}
|
|
},
|
|
"total_flos": 7097826576384000.0,
|
|
"train_batch_size": 16,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|