24079 lines
661 KiB
JSON
24079 lines
661 KiB
JSON
{
|
|
"best_global_step": null,
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 0.9336704921221552,
|
|
"eval_steps": 3000,
|
|
"global_step": 12000,
|
|
"is_hyper_param_search": false,
|
|
"is_local_process_zero": true,
|
|
"is_world_process_zero": true,
|
|
"log_history": [
|
|
{
|
|
"entropy": 10.742087173461915,
|
|
"epoch": 0.00038902937171756465,
|
|
"grad_norm": 5.03125,
|
|
"learning_rate": 2e-06,
|
|
"loss": 10.7355,
|
|
"mean_token_accuracy": 0.0,
|
|
"num_tokens": 8095.0,
|
|
"step": 5
|
|
},
|
|
{
|
|
"entropy": 10.742138862609863,
|
|
"epoch": 0.0007780587434351293,
|
|
"grad_norm": 4.90625,
|
|
"learning_rate": 4.5e-06,
|
|
"loss": 10.7472,
|
|
"mean_token_accuracy": 0.0,
|
|
"num_tokens": 17329.0,
|
|
"step": 10
|
|
},
|
|
{
|
|
"entropy": 10.742084884643555,
|
|
"epoch": 0.001167088115152694,
|
|
"grad_norm": 5.1875,
|
|
"learning_rate": 7e-06,
|
|
"loss": 10.7161,
|
|
"mean_token_accuracy": 0.0,
|
|
"num_tokens": 25729.0,
|
|
"step": 15
|
|
},
|
|
{
|
|
"entropy": 10.74206018447876,
|
|
"epoch": 0.0015561174868702586,
|
|
"grad_norm": 5.03125,
|
|
"learning_rate": 9.5e-06,
|
|
"loss": 10.658,
|
|
"mean_token_accuracy": 0.00011547344038262964,
|
|
"num_tokens": 33980.0,
|
|
"step": 20
|
|
},
|
|
{
|
|
"entropy": 10.741970634460449,
|
|
"epoch": 0.0019451468585878235,
|
|
"grad_norm": 4.71875,
|
|
"learning_rate": 1.2e-05,
|
|
"loss": 10.5514,
|
|
"mean_token_accuracy": 0.0035519652417860927,
|
|
"num_tokens": 41675.0,
|
|
"step": 25
|
|
},
|
|
{
|
|
"entropy": 10.741633415222168,
|
|
"epoch": 0.002334176230305388,
|
|
"grad_norm": 4.1875,
|
|
"learning_rate": 1.4500000000000002e-05,
|
|
"loss": 10.4556,
|
|
"mean_token_accuracy": 0.030741829052567483,
|
|
"num_tokens": 50277.0,
|
|
"step": 30
|
|
},
|
|
{
|
|
"entropy": 10.740493106842042,
|
|
"epoch": 0.0027232056020229526,
|
|
"grad_norm": 3.5625,
|
|
"learning_rate": 1.7000000000000003e-05,
|
|
"loss": 10.3206,
|
|
"mean_token_accuracy": 0.042657143995165826,
|
|
"num_tokens": 58790.0,
|
|
"step": 35
|
|
},
|
|
{
|
|
"entropy": 10.737204456329346,
|
|
"epoch": 0.0031122349737405172,
|
|
"grad_norm": 2.984375,
|
|
"learning_rate": 1.95e-05,
|
|
"loss": 10.1918,
|
|
"mean_token_accuracy": 0.041701832041144374,
|
|
"num_tokens": 67247.0,
|
|
"step": 40
|
|
},
|
|
{
|
|
"entropy": 10.730194187164306,
|
|
"epoch": 0.003501264345458082,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 2.2e-05,
|
|
"loss": 10.0582,
|
|
"mean_token_accuracy": 0.04363730065524578,
|
|
"num_tokens": 75174.0,
|
|
"step": 45
|
|
},
|
|
{
|
|
"entropy": 10.722168254852296,
|
|
"epoch": 0.003890293717175647,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 2.4500000000000003e-05,
|
|
"loss": 9.969,
|
|
"mean_token_accuracy": 0.04705791398882866,
|
|
"num_tokens": 83203.0,
|
|
"step": 50
|
|
},
|
|
{
|
|
"entropy": 10.716745758056641,
|
|
"epoch": 0.004279323088893211,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 2.7e-05,
|
|
"loss": 9.9154,
|
|
"mean_token_accuracy": 0.05126173123717308,
|
|
"num_tokens": 91798.0,
|
|
"step": 55
|
|
},
|
|
{
|
|
"entropy": 10.712809944152832,
|
|
"epoch": 0.004668352460610776,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 2.95e-05,
|
|
"loss": 9.91,
|
|
"mean_token_accuracy": 0.04944804683327675,
|
|
"num_tokens": 100869.0,
|
|
"step": 60
|
|
},
|
|
{
|
|
"entropy": 10.710667610168457,
|
|
"epoch": 0.0050573818323283405,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 3.2e-05,
|
|
"loss": 9.8383,
|
|
"mean_token_accuracy": 0.0466838538646698,
|
|
"num_tokens": 109697.0,
|
|
"step": 65
|
|
},
|
|
{
|
|
"entropy": 10.707512664794923,
|
|
"epoch": 0.005446411204045905,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 3.4500000000000005e-05,
|
|
"loss": 9.7779,
|
|
"mean_token_accuracy": 0.04920548666268587,
|
|
"num_tokens": 118656.0,
|
|
"step": 70
|
|
},
|
|
{
|
|
"entropy": 10.699565601348876,
|
|
"epoch": 0.00583544057576347,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 3.7e-05,
|
|
"loss": 9.758,
|
|
"mean_token_accuracy": 0.047676689177751544,
|
|
"num_tokens": 127748.0,
|
|
"step": 75
|
|
},
|
|
{
|
|
"entropy": 10.6899094581604,
|
|
"epoch": 0.0062244699474810344,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 3.95e-05,
|
|
"loss": 9.6559,
|
|
"mean_token_accuracy": 0.052025371417403224,
|
|
"num_tokens": 136621.0,
|
|
"step": 80
|
|
},
|
|
{
|
|
"entropy": 10.678217601776122,
|
|
"epoch": 0.006613499319198599,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 4.2000000000000004e-05,
|
|
"loss": 9.5282,
|
|
"mean_token_accuracy": 0.06281816884875298,
|
|
"num_tokens": 145793.0,
|
|
"step": 85
|
|
},
|
|
{
|
|
"entropy": 10.661566066741944,
|
|
"epoch": 0.007002528690916164,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 4.45e-05,
|
|
"loss": 9.4566,
|
|
"mean_token_accuracy": 0.06447997651994228,
|
|
"num_tokens": 154466.0,
|
|
"step": 90
|
|
},
|
|
{
|
|
"entropy": 10.639564514160156,
|
|
"epoch": 0.007391558062633729,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 4.7000000000000004e-05,
|
|
"loss": 9.4185,
|
|
"mean_token_accuracy": 0.06300977356731892,
|
|
"num_tokens": 163297.0,
|
|
"step": 95
|
|
},
|
|
{
|
|
"entropy": 10.602224636077882,
|
|
"epoch": 0.007780587434351294,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 4.9500000000000004e-05,
|
|
"loss": 9.2964,
|
|
"mean_token_accuracy": 0.066444294154644,
|
|
"num_tokens": 171747.0,
|
|
"step": 100
|
|
},
|
|
{
|
|
"entropy": 10.547998046875,
|
|
"epoch": 0.008169616806068859,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 5.2e-05,
|
|
"loss": 9.2224,
|
|
"mean_token_accuracy": 0.061835135146975514,
|
|
"num_tokens": 180499.0,
|
|
"step": 105
|
|
},
|
|
{
|
|
"entropy": 10.506940460205078,
|
|
"epoch": 0.008558646177786422,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 5.45e-05,
|
|
"loss": 9.1182,
|
|
"mean_token_accuracy": 0.06274112537503243,
|
|
"num_tokens": 189227.0,
|
|
"step": 110
|
|
},
|
|
{
|
|
"entropy": 10.470497703552246,
|
|
"epoch": 0.008947675549503988,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 5.7e-05,
|
|
"loss": 8.9987,
|
|
"mean_token_accuracy": 0.06519487500190735,
|
|
"num_tokens": 198388.0,
|
|
"step": 115
|
|
},
|
|
{
|
|
"entropy": 10.417663478851319,
|
|
"epoch": 0.009336704921221552,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 5.9499999999999996e-05,
|
|
"loss": 8.8933,
|
|
"mean_token_accuracy": 0.0642558429390192,
|
|
"num_tokens": 206854.0,
|
|
"step": 120
|
|
},
|
|
{
|
|
"entropy": 10.3519455909729,
|
|
"epoch": 0.009725734292939117,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 6.2e-05,
|
|
"loss": 8.7861,
|
|
"mean_token_accuracy": 0.0641202162951231,
|
|
"num_tokens": 215506.0,
|
|
"step": 125
|
|
},
|
|
{
|
|
"entropy": 10.284876441955566,
|
|
"epoch": 0.010114763664656681,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 6.450000000000001e-05,
|
|
"loss": 8.6622,
|
|
"mean_token_accuracy": 0.06737961098551751,
|
|
"num_tokens": 223717.0,
|
|
"step": 130
|
|
},
|
|
{
|
|
"entropy": 10.18412799835205,
|
|
"epoch": 0.010503793036374246,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 6.7e-05,
|
|
"loss": 8.5306,
|
|
"mean_token_accuracy": 0.067349299415946,
|
|
"num_tokens": 232480.0,
|
|
"step": 135
|
|
},
|
|
{
|
|
"entropy": 10.091043281555176,
|
|
"epoch": 0.01089282240809181,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 6.950000000000001e-05,
|
|
"loss": 8.4423,
|
|
"mean_token_accuracy": 0.06387559846043586,
|
|
"num_tokens": 241350.0,
|
|
"step": 140
|
|
},
|
|
{
|
|
"entropy": 9.962540531158448,
|
|
"epoch": 0.011281851779809376,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 7.2e-05,
|
|
"loss": 8.3445,
|
|
"mean_token_accuracy": 0.06567118875682354,
|
|
"num_tokens": 250610.0,
|
|
"step": 145
|
|
},
|
|
{
|
|
"entropy": 9.842002868652344,
|
|
"epoch": 0.01167088115152694,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 7.45e-05,
|
|
"loss": 8.1965,
|
|
"mean_token_accuracy": 0.06004151217639446,
|
|
"num_tokens": 259672.0,
|
|
"step": 150
|
|
},
|
|
{
|
|
"entropy": 9.687075901031495,
|
|
"epoch": 0.012059910523244505,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 7.7e-05,
|
|
"loss": 8.1149,
|
|
"mean_token_accuracy": 0.06366611644625664,
|
|
"num_tokens": 267826.0,
|
|
"step": 155
|
|
},
|
|
{
|
|
"entropy": 9.486919116973876,
|
|
"epoch": 0.012448939894962069,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 7.950000000000001e-05,
|
|
"loss": 8.0603,
|
|
"mean_token_accuracy": 0.06088076755404472,
|
|
"num_tokens": 277324.0,
|
|
"step": 160
|
|
},
|
|
{
|
|
"entropy": 9.344527530670167,
|
|
"epoch": 0.012837969266679634,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 8.2e-05,
|
|
"loss": 7.8628,
|
|
"mean_token_accuracy": 0.06783541738986969,
|
|
"num_tokens": 285482.0,
|
|
"step": 165
|
|
},
|
|
{
|
|
"entropy": 9.084899616241454,
|
|
"epoch": 0.013226998638397198,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 8.450000000000001e-05,
|
|
"loss": 7.8199,
|
|
"mean_token_accuracy": 0.06509357057511807,
|
|
"num_tokens": 293684.0,
|
|
"step": 170
|
|
},
|
|
{
|
|
"entropy": 8.910903358459473,
|
|
"epoch": 0.013616028010114764,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 8.7e-05,
|
|
"loss": 7.7429,
|
|
"mean_token_accuracy": 0.06691662222146988,
|
|
"num_tokens": 302605.0,
|
|
"step": 175
|
|
},
|
|
{
|
|
"entropy": 8.674479103088379,
|
|
"epoch": 0.014005057381832327,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 8.95e-05,
|
|
"loss": 7.7506,
|
|
"mean_token_accuracy": 0.06571518406271934,
|
|
"num_tokens": 310849.0,
|
|
"step": 180
|
|
},
|
|
{
|
|
"entropy": 8.626084232330323,
|
|
"epoch": 0.014394086753549893,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 9.2e-05,
|
|
"loss": 7.7323,
|
|
"mean_token_accuracy": 0.06051843762397766,
|
|
"num_tokens": 319752.0,
|
|
"step": 185
|
|
},
|
|
{
|
|
"entropy": 8.481939506530761,
|
|
"epoch": 0.014783116125267459,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 9.45e-05,
|
|
"loss": 7.749,
|
|
"mean_token_accuracy": 0.06395503841340541,
|
|
"num_tokens": 328009.0,
|
|
"step": 190
|
|
},
|
|
{
|
|
"entropy": 8.346093559265137,
|
|
"epoch": 0.015172145496985022,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 9.7e-05,
|
|
"loss": 7.642,
|
|
"mean_token_accuracy": 0.0676554836332798,
|
|
"num_tokens": 337414.0,
|
|
"step": 195
|
|
},
|
|
{
|
|
"entropy": 8.347679996490479,
|
|
"epoch": 0.015561174868702588,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 9.95e-05,
|
|
"loss": 7.6106,
|
|
"mean_token_accuracy": 0.0668629266321659,
|
|
"num_tokens": 345419.0,
|
|
"step": 200
|
|
},
|
|
{
|
|
"entropy": 8.210858917236328,
|
|
"epoch": 0.01595020424042015,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000102,
|
|
"loss": 7.5878,
|
|
"mean_token_accuracy": 0.07259676679968834,
|
|
"num_tokens": 353435.0,
|
|
"step": 205
|
|
},
|
|
{
|
|
"entropy": 8.228489208221436,
|
|
"epoch": 0.016339233612137717,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00010449999999999999,
|
|
"loss": 7.5984,
|
|
"mean_token_accuracy": 0.07119170576334,
|
|
"num_tokens": 361840.0,
|
|
"step": 210
|
|
},
|
|
{
|
|
"entropy": 8.220147895812989,
|
|
"epoch": 0.016728262983855283,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000107,
|
|
"loss": 7.67,
|
|
"mean_token_accuracy": 0.0687949825078249,
|
|
"num_tokens": 370873.0,
|
|
"step": 215
|
|
},
|
|
{
|
|
"entropy": 8.175065612792968,
|
|
"epoch": 0.017117292355572845,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0001095,
|
|
"loss": 7.5955,
|
|
"mean_token_accuracy": 0.06820659413933754,
|
|
"num_tokens": 379558.0,
|
|
"step": 220
|
|
},
|
|
{
|
|
"entropy": 8.128092670440674,
|
|
"epoch": 0.01750632172729041,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000112,
|
|
"loss": 7.5724,
|
|
"mean_token_accuracy": 0.0715484719723463,
|
|
"num_tokens": 387870.0,
|
|
"step": 225
|
|
},
|
|
{
|
|
"entropy": 8.142854118347168,
|
|
"epoch": 0.017895351099007976,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0001145,
|
|
"loss": 7.6264,
|
|
"mean_token_accuracy": 0.06858488656580448,
|
|
"num_tokens": 396442.0,
|
|
"step": 230
|
|
},
|
|
{
|
|
"entropy": 8.081027698516845,
|
|
"epoch": 0.01828438047072554,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00011700000000000001,
|
|
"loss": 7.5667,
|
|
"mean_token_accuracy": 0.07171515934169292,
|
|
"num_tokens": 404764.0,
|
|
"step": 235
|
|
},
|
|
{
|
|
"entropy": 8.084673309326172,
|
|
"epoch": 0.018673409842443103,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.00011949999999999999,
|
|
"loss": 7.5095,
|
|
"mean_token_accuracy": 0.0741395641118288,
|
|
"num_tokens": 413355.0,
|
|
"step": 240
|
|
},
|
|
{
|
|
"entropy": 8.088351917266845,
|
|
"epoch": 0.01906243921416067,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.000122,
|
|
"loss": 7.4163,
|
|
"mean_token_accuracy": 0.07463119179010391,
|
|
"num_tokens": 421868.0,
|
|
"step": 245
|
|
},
|
|
{
|
|
"entropy": 8.05438003540039,
|
|
"epoch": 0.019451468585878234,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0001245,
|
|
"loss": 7.4493,
|
|
"mean_token_accuracy": 0.07356020472943783,
|
|
"num_tokens": 431106.0,
|
|
"step": 250
|
|
},
|
|
{
|
|
"entropy": 8.085360860824585,
|
|
"epoch": 0.0198404979575958,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000127,
|
|
"loss": 7.5595,
|
|
"mean_token_accuracy": 0.06749935299158097,
|
|
"num_tokens": 439459.0,
|
|
"step": 255
|
|
},
|
|
{
|
|
"entropy": 7.997472143173217,
|
|
"epoch": 0.020229527329313362,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0001295,
|
|
"loss": 7.4074,
|
|
"mean_token_accuracy": 0.07336174622178078,
|
|
"num_tokens": 447943.0,
|
|
"step": 260
|
|
},
|
|
{
|
|
"entropy": 7.982085561752319,
|
|
"epoch": 0.020618556701030927,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000132,
|
|
"loss": 7.5105,
|
|
"mean_token_accuracy": 0.0743416965007782,
|
|
"num_tokens": 456691.0,
|
|
"step": 265
|
|
},
|
|
{
|
|
"entropy": 7.918378829956055,
|
|
"epoch": 0.021007586072748493,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00013450000000000002,
|
|
"loss": 7.4348,
|
|
"mean_token_accuracy": 0.074999488145113,
|
|
"num_tokens": 466388.0,
|
|
"step": 270
|
|
},
|
|
{
|
|
"entropy": 8.023542356491088,
|
|
"epoch": 0.02139661544446606,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00013700000000000002,
|
|
"loss": 7.4804,
|
|
"mean_token_accuracy": 0.07692455723881722,
|
|
"num_tokens": 474544.0,
|
|
"step": 275
|
|
},
|
|
{
|
|
"entropy": 8.005887222290038,
|
|
"epoch": 0.02178564481618362,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0001395,
|
|
"loss": 7.504,
|
|
"mean_token_accuracy": 0.07702539637684822,
|
|
"num_tokens": 483561.0,
|
|
"step": 280
|
|
},
|
|
{
|
|
"entropy": 7.895681428909302,
|
|
"epoch": 0.022174674187901186,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00014199999999999998,
|
|
"loss": 7.3428,
|
|
"mean_token_accuracy": 0.07652496919035912,
|
|
"num_tokens": 492036.0,
|
|
"step": 285
|
|
},
|
|
{
|
|
"entropy": 7.991393566131592,
|
|
"epoch": 0.02256370355961875,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0001445,
|
|
"loss": 7.457,
|
|
"mean_token_accuracy": 0.07459444478154183,
|
|
"num_tokens": 500978.0,
|
|
"step": 290
|
|
},
|
|
{
|
|
"entropy": 7.994901657104492,
|
|
"epoch": 0.022952732931336317,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.000147,
|
|
"loss": 7.4575,
|
|
"mean_token_accuracy": 0.0793934091925621,
|
|
"num_tokens": 509719.0,
|
|
"step": 295
|
|
},
|
|
{
|
|
"entropy": 7.917689561843872,
|
|
"epoch": 0.02334176230305388,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0001495,
|
|
"loss": 7.3986,
|
|
"mean_token_accuracy": 0.07768453806638717,
|
|
"num_tokens": 518422.0,
|
|
"step": 300
|
|
},
|
|
{
|
|
"entropy": 7.879164934158325,
|
|
"epoch": 0.023730791674771445,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000152,
|
|
"loss": 7.4261,
|
|
"mean_token_accuracy": 0.07615871094167233,
|
|
"num_tokens": 527172.0,
|
|
"step": 305
|
|
},
|
|
{
|
|
"entropy": 7.969165182113647,
|
|
"epoch": 0.02411982104648901,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00015450000000000001,
|
|
"loss": 7.335,
|
|
"mean_token_accuracy": 0.08110791519284248,
|
|
"num_tokens": 536070.0,
|
|
"step": 310
|
|
},
|
|
{
|
|
"entropy": 7.876494932174682,
|
|
"epoch": 0.024508850418206576,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000157,
|
|
"loss": 7.3346,
|
|
"mean_token_accuracy": 0.08139037936925889,
|
|
"num_tokens": 544556.0,
|
|
"step": 315
|
|
},
|
|
{
|
|
"entropy": 7.930807495117188,
|
|
"epoch": 0.024897879789924138,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0001595,
|
|
"loss": 7.3277,
|
|
"mean_token_accuracy": 0.0813445694744587,
|
|
"num_tokens": 553122.0,
|
|
"step": 320
|
|
},
|
|
{
|
|
"entropy": 7.847272491455078,
|
|
"epoch": 0.025286909161641703,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.000162,
|
|
"loss": 7.3702,
|
|
"mean_token_accuracy": 0.07732471227645873,
|
|
"num_tokens": 562265.0,
|
|
"step": 325
|
|
},
|
|
{
|
|
"entropy": 7.812228536605835,
|
|
"epoch": 0.02567593853335927,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00016450000000000001,
|
|
"loss": 7.3233,
|
|
"mean_token_accuracy": 0.0869563028216362,
|
|
"num_tokens": 570938.0,
|
|
"step": 330
|
|
},
|
|
{
|
|
"entropy": 7.8487406253814695,
|
|
"epoch": 0.026064967905076834,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00016700000000000002,
|
|
"loss": 7.2682,
|
|
"mean_token_accuracy": 0.08920462355017662,
|
|
"num_tokens": 578568.0,
|
|
"step": 335
|
|
},
|
|
{
|
|
"entropy": 7.874819087982178,
|
|
"epoch": 0.026453997276794396,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00016950000000000003,
|
|
"loss": 7.3216,
|
|
"mean_token_accuracy": 0.0859262391924858,
|
|
"num_tokens": 587013.0,
|
|
"step": 340
|
|
},
|
|
{
|
|
"entropy": 7.878486108779907,
|
|
"epoch": 0.026843026648511962,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00017199999999999998,
|
|
"loss": 7.3504,
|
|
"mean_token_accuracy": 0.08751785308122635,
|
|
"num_tokens": 595354.0,
|
|
"step": 345
|
|
},
|
|
{
|
|
"entropy": 7.822435426712036,
|
|
"epoch": 0.027232056020229527,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00017449999999999999,
|
|
"loss": 7.3303,
|
|
"mean_token_accuracy": 0.08466543480753899,
|
|
"num_tokens": 603971.0,
|
|
"step": 350
|
|
},
|
|
{
|
|
"entropy": 7.758132362365723,
|
|
"epoch": 0.027621085391947093,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000177,
|
|
"loss": 7.2492,
|
|
"mean_token_accuracy": 0.09002660363912582,
|
|
"num_tokens": 612097.0,
|
|
"step": 355
|
|
},
|
|
{
|
|
"entropy": 7.7984230518341064,
|
|
"epoch": 0.028010114763664655,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0001795,
|
|
"loss": 7.2982,
|
|
"mean_token_accuracy": 0.08613273575901985,
|
|
"num_tokens": 621445.0,
|
|
"step": 360
|
|
},
|
|
{
|
|
"entropy": 7.769416999816895,
|
|
"epoch": 0.02839914413538222,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000182,
|
|
"loss": 7.3609,
|
|
"mean_token_accuracy": 0.08488503694534302,
|
|
"num_tokens": 630041.0,
|
|
"step": 365
|
|
},
|
|
{
|
|
"entropy": 7.751703786849975,
|
|
"epoch": 0.028788173507099786,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0001845,
|
|
"loss": 7.1729,
|
|
"mean_token_accuracy": 0.08984732106328011,
|
|
"num_tokens": 638317.0,
|
|
"step": 370
|
|
},
|
|
{
|
|
"entropy": 7.772419214248657,
|
|
"epoch": 0.02917720287881735,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000187,
|
|
"loss": 7.3048,
|
|
"mean_token_accuracy": 0.08521358594298363,
|
|
"num_tokens": 647297.0,
|
|
"step": 375
|
|
},
|
|
{
|
|
"entropy": 7.845639944076538,
|
|
"epoch": 0.029566232250534917,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0001895,
|
|
"loss": 7.3325,
|
|
"mean_token_accuracy": 0.08574758470058441,
|
|
"num_tokens": 655309.0,
|
|
"step": 380
|
|
},
|
|
{
|
|
"entropy": 7.704274225234985,
|
|
"epoch": 0.02995526162225248,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000192,
|
|
"loss": 7.2032,
|
|
"mean_token_accuracy": 0.08063894510269165,
|
|
"num_tokens": 663879.0,
|
|
"step": 385
|
|
},
|
|
{
|
|
"entropy": 7.75761194229126,
|
|
"epoch": 0.030344290993970045,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0001945,
|
|
"loss": 7.1131,
|
|
"mean_token_accuracy": 0.09121661111712456,
|
|
"num_tokens": 672913.0,
|
|
"step": 390
|
|
},
|
|
{
|
|
"entropy": 7.677809333801269,
|
|
"epoch": 0.03073332036568761,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00019700000000000002,
|
|
"loss": 7.2217,
|
|
"mean_token_accuracy": 0.08521161302924156,
|
|
"num_tokens": 682282.0,
|
|
"step": 395
|
|
},
|
|
{
|
|
"entropy": 7.67137598991394,
|
|
"epoch": 0.031122349737405176,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00019950000000000002,
|
|
"loss": 7.2312,
|
|
"mean_token_accuracy": 0.08108669146895409,
|
|
"num_tokens": 691432.0,
|
|
"step": 400
|
|
},
|
|
{
|
|
"entropy": 7.725798177719116,
|
|
"epoch": 0.03151137910912274,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000202,
|
|
"loss": 7.2266,
|
|
"mean_token_accuracy": 0.08599605634808541,
|
|
"num_tokens": 700639.0,
|
|
"step": 405
|
|
},
|
|
{
|
|
"entropy": 7.75080361366272,
|
|
"epoch": 0.0319004084808403,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00020449999999999998,
|
|
"loss": 7.2862,
|
|
"mean_token_accuracy": 0.08474635109305381,
|
|
"num_tokens": 709200.0,
|
|
"step": 410
|
|
},
|
|
{
|
|
"entropy": 7.598263549804687,
|
|
"epoch": 0.03228943785255787,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000207,
|
|
"loss": 7.1093,
|
|
"mean_token_accuracy": 0.09120492935180664,
|
|
"num_tokens": 717266.0,
|
|
"step": 415
|
|
},
|
|
{
|
|
"entropy": 7.665576219558716,
|
|
"epoch": 0.032678467224275434,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0002095,
|
|
"loss": 7.1208,
|
|
"mean_token_accuracy": 0.0892751768231392,
|
|
"num_tokens": 725799.0,
|
|
"step": 420
|
|
},
|
|
{
|
|
"entropy": 7.653212070465088,
|
|
"epoch": 0.033067496595993,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000212,
|
|
"loss": 7.2111,
|
|
"mean_token_accuracy": 0.08835389018058777,
|
|
"num_tokens": 734375.0,
|
|
"step": 425
|
|
},
|
|
{
|
|
"entropy": 7.74424262046814,
|
|
"epoch": 0.033456525967710565,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0002145,
|
|
"loss": 7.2555,
|
|
"mean_token_accuracy": 0.08766974285244941,
|
|
"num_tokens": 743453.0,
|
|
"step": 430
|
|
},
|
|
{
|
|
"entropy": 7.593816137313842,
|
|
"epoch": 0.033845555339428124,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00021700000000000002,
|
|
"loss": 7.1001,
|
|
"mean_token_accuracy": 0.09561214223504066,
|
|
"num_tokens": 752443.0,
|
|
"step": 435
|
|
},
|
|
{
|
|
"entropy": 7.626216220855713,
|
|
"epoch": 0.03423458471114569,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0002195,
|
|
"loss": 7.0988,
|
|
"mean_token_accuracy": 0.08553416356444359,
|
|
"num_tokens": 761294.0,
|
|
"step": 440
|
|
},
|
|
{
|
|
"entropy": 7.621181488037109,
|
|
"epoch": 0.034623614082863255,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000222,
|
|
"loss": 7.0642,
|
|
"mean_token_accuracy": 0.09563054814934731,
|
|
"num_tokens": 769489.0,
|
|
"step": 445
|
|
},
|
|
{
|
|
"entropy": 7.661951541900635,
|
|
"epoch": 0.03501264345458082,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0002245,
|
|
"loss": 7.1244,
|
|
"mean_token_accuracy": 0.09401247352361679,
|
|
"num_tokens": 777836.0,
|
|
"step": 450
|
|
},
|
|
{
|
|
"entropy": 7.584022903442383,
|
|
"epoch": 0.035401672826298386,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00022700000000000002,
|
|
"loss": 7.1516,
|
|
"mean_token_accuracy": 0.08489634171128273,
|
|
"num_tokens": 786543.0,
|
|
"step": 455
|
|
},
|
|
{
|
|
"entropy": 7.590439224243164,
|
|
"epoch": 0.03579070219801595,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00022950000000000002,
|
|
"loss": 7.1911,
|
|
"mean_token_accuracy": 0.09159761071205139,
|
|
"num_tokens": 794525.0,
|
|
"step": 460
|
|
},
|
|
{
|
|
"entropy": 7.574541854858398,
|
|
"epoch": 0.03617973156973352,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00023200000000000003,
|
|
"loss": 7.0976,
|
|
"mean_token_accuracy": 0.0944310788065195,
|
|
"num_tokens": 803537.0,
|
|
"step": 465
|
|
},
|
|
{
|
|
"entropy": 7.611633348464966,
|
|
"epoch": 0.03656876094145108,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00023449999999999998,
|
|
"loss": 7.0519,
|
|
"mean_token_accuracy": 0.09074848592281341,
|
|
"num_tokens": 811706.0,
|
|
"step": 470
|
|
},
|
|
{
|
|
"entropy": 7.562524032592774,
|
|
"epoch": 0.03695779031316864,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000237,
|
|
"loss": 7.1067,
|
|
"mean_token_accuracy": 0.09484568610787392,
|
|
"num_tokens": 820182.0,
|
|
"step": 475
|
|
},
|
|
{
|
|
"entropy": 7.572012710571289,
|
|
"epoch": 0.03734681968488621,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0002395,
|
|
"loss": 7.0488,
|
|
"mean_token_accuracy": 0.09293625578284263,
|
|
"num_tokens": 829808.0,
|
|
"step": 480
|
|
},
|
|
{
|
|
"entropy": 7.545894145965576,
|
|
"epoch": 0.03773584905660377,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000242,
|
|
"loss": 6.9895,
|
|
"mean_token_accuracy": 0.09443094059824944,
|
|
"num_tokens": 838838.0,
|
|
"step": 485
|
|
},
|
|
{
|
|
"entropy": 7.557442235946655,
|
|
"epoch": 0.03812487842832134,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0002445,
|
|
"loss": 7.0937,
|
|
"mean_token_accuracy": 0.09211538061499595,
|
|
"num_tokens": 847800.0,
|
|
"step": 490
|
|
},
|
|
{
|
|
"entropy": 7.60601692199707,
|
|
"epoch": 0.0385139078000389,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000247,
|
|
"loss": 7.1669,
|
|
"mean_token_accuracy": 0.09093088284134865,
|
|
"num_tokens": 856503.0,
|
|
"step": 495
|
|
},
|
|
{
|
|
"entropy": 7.475769996643066,
|
|
"epoch": 0.03890293717175647,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0002495,
|
|
"loss": 7.05,
|
|
"mean_token_accuracy": 0.09106085672974587,
|
|
"num_tokens": 865245.0,
|
|
"step": 500
|
|
},
|
|
{
|
|
"entropy": 7.588863754272461,
|
|
"epoch": 0.039291966543474034,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000252,
|
|
"loss": 7.0721,
|
|
"mean_token_accuracy": 0.09027522280812264,
|
|
"num_tokens": 874485.0,
|
|
"step": 505
|
|
},
|
|
{
|
|
"entropy": 7.418361043930053,
|
|
"epoch": 0.0396809959151916,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0002545,
|
|
"loss": 6.9375,
|
|
"mean_token_accuracy": 0.09956656396389008,
|
|
"num_tokens": 883301.0,
|
|
"step": 510
|
|
},
|
|
{
|
|
"entropy": 7.408757543563842,
|
|
"epoch": 0.04007002528690916,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000257,
|
|
"loss": 6.9846,
|
|
"mean_token_accuracy": 0.0950555182993412,
|
|
"num_tokens": 892387.0,
|
|
"step": 515
|
|
},
|
|
{
|
|
"entropy": 7.48194580078125,
|
|
"epoch": 0.040459054658626724,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0002595,
|
|
"loss": 6.9709,
|
|
"mean_token_accuracy": 0.09912419691681862,
|
|
"num_tokens": 901522.0,
|
|
"step": 520
|
|
},
|
|
{
|
|
"entropy": 7.441246747970581,
|
|
"epoch": 0.04084808403034429,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000262,
|
|
"loss": 6.9292,
|
|
"mean_token_accuracy": 0.0985661618411541,
|
|
"num_tokens": 909848.0,
|
|
"step": 525
|
|
},
|
|
{
|
|
"entropy": 7.562440967559814,
|
|
"epoch": 0.041237113402061855,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00026450000000000003,
|
|
"loss": 7.164,
|
|
"mean_token_accuracy": 0.08993402048945427,
|
|
"num_tokens": 919079.0,
|
|
"step": 530
|
|
},
|
|
{
|
|
"entropy": 7.420489549636841,
|
|
"epoch": 0.04162614277377942,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00026700000000000004,
|
|
"loss": 6.9063,
|
|
"mean_token_accuracy": 0.09894024208188057,
|
|
"num_tokens": 927807.0,
|
|
"step": 535
|
|
},
|
|
{
|
|
"entropy": 7.408330631256104,
|
|
"epoch": 0.042015172145496986,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00026950000000000005,
|
|
"loss": 7.0018,
|
|
"mean_token_accuracy": 0.09915620237588882,
|
|
"num_tokens": 936498.0,
|
|
"step": 540
|
|
},
|
|
{
|
|
"entropy": 7.487834930419922,
|
|
"epoch": 0.04240420151721455,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00027200000000000005,
|
|
"loss": 7.0738,
|
|
"mean_token_accuracy": 0.0998169869184494,
|
|
"num_tokens": 945436.0,
|
|
"step": 545
|
|
},
|
|
{
|
|
"entropy": 7.528131818771362,
|
|
"epoch": 0.04279323088893212,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0002745,
|
|
"loss": 6.9875,
|
|
"mean_token_accuracy": 0.09678835868835449,
|
|
"num_tokens": 953990.0,
|
|
"step": 550
|
|
},
|
|
{
|
|
"entropy": 7.37784481048584,
|
|
"epoch": 0.04318226026064968,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000277,
|
|
"loss": 6.9245,
|
|
"mean_token_accuracy": 0.09856464117765426,
|
|
"num_tokens": 962008.0,
|
|
"step": 555
|
|
},
|
|
{
|
|
"entropy": 7.438614797592163,
|
|
"epoch": 0.04357128963236724,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0002795,
|
|
"loss": 7.0788,
|
|
"mean_token_accuracy": 0.09496510401368141,
|
|
"num_tokens": 970935.0,
|
|
"step": 560
|
|
},
|
|
{
|
|
"entropy": 7.521619749069214,
|
|
"epoch": 0.04396031900408481,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00028199999999999997,
|
|
"loss": 7.0371,
|
|
"mean_token_accuracy": 0.08908204212784768,
|
|
"num_tokens": 979492.0,
|
|
"step": 565
|
|
},
|
|
{
|
|
"entropy": 7.361342287063598,
|
|
"epoch": 0.04434934837580237,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0002845,
|
|
"loss": 6.9321,
|
|
"mean_token_accuracy": 0.09547191262245178,
|
|
"num_tokens": 987866.0,
|
|
"step": 570
|
|
},
|
|
{
|
|
"entropy": 7.397969961166382,
|
|
"epoch": 0.04473837774751994,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000287,
|
|
"loss": 6.9804,
|
|
"mean_token_accuracy": 0.09910744205117225,
|
|
"num_tokens": 996760.0,
|
|
"step": 575
|
|
},
|
|
{
|
|
"entropy": 7.447316217422485,
|
|
"epoch": 0.0451274071192375,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0002895,
|
|
"loss": 6.9028,
|
|
"mean_token_accuracy": 0.10264215171337128,
|
|
"num_tokens": 1005432.0,
|
|
"step": 580
|
|
},
|
|
{
|
|
"entropy": 7.396947145462036,
|
|
"epoch": 0.04551643649095507,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000292,
|
|
"loss": 6.9787,
|
|
"mean_token_accuracy": 0.09953495115041733,
|
|
"num_tokens": 1013729.0,
|
|
"step": 585
|
|
},
|
|
{
|
|
"entropy": 7.278457880020142,
|
|
"epoch": 0.045905465862672634,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0002945,
|
|
"loss": 6.8221,
|
|
"mean_token_accuracy": 0.10534313321113586,
|
|
"num_tokens": 1022485.0,
|
|
"step": 590
|
|
},
|
|
{
|
|
"entropy": 7.3537023067474365,
|
|
"epoch": 0.0462944952343902,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.000297,
|
|
"loss": 6.8869,
|
|
"mean_token_accuracy": 0.0984025850892067,
|
|
"num_tokens": 1030523.0,
|
|
"step": 595
|
|
},
|
|
{
|
|
"entropy": 7.419099044799805,
|
|
"epoch": 0.04668352460610776,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0002995,
|
|
"loss": 6.99,
|
|
"mean_token_accuracy": 0.09814063236117362,
|
|
"num_tokens": 1039268.0,
|
|
"step": 600
|
|
},
|
|
{
|
|
"entropy": 7.301190805435181,
|
|
"epoch": 0.047072553977825324,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000302,
|
|
"loss": 6.8802,
|
|
"mean_token_accuracy": 0.09921084493398666,
|
|
"num_tokens": 1048590.0,
|
|
"step": 605
|
|
},
|
|
{
|
|
"entropy": 7.268998908996582,
|
|
"epoch": 0.04746158334954289,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0003045,
|
|
"loss": 6.811,
|
|
"mean_token_accuracy": 0.10243154391646385,
|
|
"num_tokens": 1057232.0,
|
|
"step": 610
|
|
},
|
|
{
|
|
"entropy": 7.301156949996948,
|
|
"epoch": 0.047850612721260455,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.000307,
|
|
"loss": 6.8863,
|
|
"mean_token_accuracy": 0.09728901833295822,
|
|
"num_tokens": 1066404.0,
|
|
"step": 615
|
|
},
|
|
{
|
|
"entropy": 7.226704359054565,
|
|
"epoch": 0.04823964209297802,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0003095,
|
|
"loss": 6.957,
|
|
"mean_token_accuracy": 0.09339571669697762,
|
|
"num_tokens": 1075093.0,
|
|
"step": 620
|
|
},
|
|
{
|
|
"entropy": 7.38017783164978,
|
|
"epoch": 0.048628671464695586,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000312,
|
|
"loss": 6.864,
|
|
"mean_token_accuracy": 0.09610054194927216,
|
|
"num_tokens": 1084454.0,
|
|
"step": 625
|
|
},
|
|
{
|
|
"entropy": 7.280154037475586,
|
|
"epoch": 0.04901770083641315,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0003145,
|
|
"loss": 6.7866,
|
|
"mean_token_accuracy": 0.10086495503783226,
|
|
"num_tokens": 1093452.0,
|
|
"step": 630
|
|
},
|
|
{
|
|
"entropy": 7.33285608291626,
|
|
"epoch": 0.04940673020813072,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000317,
|
|
"loss": 6.807,
|
|
"mean_token_accuracy": 0.10476917698979378,
|
|
"num_tokens": 1101814.0,
|
|
"step": 635
|
|
},
|
|
{
|
|
"entropy": 7.184072637557984,
|
|
"epoch": 0.049795759579848276,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0003195,
|
|
"loss": 6.8889,
|
|
"mean_token_accuracy": 0.10318943634629249,
|
|
"num_tokens": 1110386.0,
|
|
"step": 640
|
|
},
|
|
{
|
|
"entropy": 7.352627325057983,
|
|
"epoch": 0.05018478895156584,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000322,
|
|
"loss": 6.9831,
|
|
"mean_token_accuracy": 0.0920788213610649,
|
|
"num_tokens": 1120141.0,
|
|
"step": 645
|
|
},
|
|
{
|
|
"entropy": 7.324120092391968,
|
|
"epoch": 0.05057381832328341,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00032450000000000003,
|
|
"loss": 6.9227,
|
|
"mean_token_accuracy": 0.09927786216139793,
|
|
"num_tokens": 1129920.0,
|
|
"step": 650
|
|
},
|
|
{
|
|
"entropy": 7.171842193603515,
|
|
"epoch": 0.05096284769500097,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00032700000000000003,
|
|
"loss": 6.7957,
|
|
"mean_token_accuracy": 0.10289519429206848,
|
|
"num_tokens": 1138518.0,
|
|
"step": 655
|
|
},
|
|
{
|
|
"entropy": 7.32971568107605,
|
|
"epoch": 0.05135187706671854,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00032950000000000004,
|
|
"loss": 6.8899,
|
|
"mean_token_accuracy": 0.1004197433590889,
|
|
"num_tokens": 1147113.0,
|
|
"step": 660
|
|
},
|
|
{
|
|
"entropy": 7.201927232742309,
|
|
"epoch": 0.0517409064384361,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00033200000000000005,
|
|
"loss": 6.7435,
|
|
"mean_token_accuracy": 0.10898910462856293,
|
|
"num_tokens": 1155886.0,
|
|
"step": 665
|
|
},
|
|
{
|
|
"entropy": 7.199523496627807,
|
|
"epoch": 0.05212993581015367,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00033450000000000005,
|
|
"loss": 6.8999,
|
|
"mean_token_accuracy": 0.09887881278991699,
|
|
"num_tokens": 1164200.0,
|
|
"step": 670
|
|
},
|
|
{
|
|
"entropy": 7.209548091888427,
|
|
"epoch": 0.052518965181871234,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000337,
|
|
"loss": 6.7543,
|
|
"mean_token_accuracy": 0.10513453632593155,
|
|
"num_tokens": 1172720.0,
|
|
"step": 675
|
|
},
|
|
{
|
|
"entropy": 7.177516746520996,
|
|
"epoch": 0.05290799455358879,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0003395,
|
|
"loss": 6.7115,
|
|
"mean_token_accuracy": 0.09829143732786179,
|
|
"num_tokens": 1181225.0,
|
|
"step": 680
|
|
},
|
|
{
|
|
"entropy": 7.2649918556213375,
|
|
"epoch": 0.05329702392530636,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000342,
|
|
"loss": 6.9086,
|
|
"mean_token_accuracy": 0.09883515611290931,
|
|
"num_tokens": 1190070.0,
|
|
"step": 685
|
|
},
|
|
{
|
|
"entropy": 7.220799922943115,
|
|
"epoch": 0.053686053297023924,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00034449999999999997,
|
|
"loss": 6.7985,
|
|
"mean_token_accuracy": 0.1037118412554264,
|
|
"num_tokens": 1198995.0,
|
|
"step": 690
|
|
},
|
|
{
|
|
"entropy": 7.23320894241333,
|
|
"epoch": 0.05407508266874149,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000347,
|
|
"loss": 6.8442,
|
|
"mean_token_accuracy": 0.1092130720615387,
|
|
"num_tokens": 1207664.0,
|
|
"step": 695
|
|
},
|
|
{
|
|
"entropy": 7.272186803817749,
|
|
"epoch": 0.054464112040459055,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0003495,
|
|
"loss": 6.7473,
|
|
"mean_token_accuracy": 0.11652912721037864,
|
|
"num_tokens": 1216232.0,
|
|
"step": 700
|
|
},
|
|
{
|
|
"entropy": 7.137939691543579,
|
|
"epoch": 0.05485314141217662,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000352,
|
|
"loss": 6.8328,
|
|
"mean_token_accuracy": 0.1046180248260498,
|
|
"num_tokens": 1224106.0,
|
|
"step": 705
|
|
},
|
|
{
|
|
"entropy": 7.112717533111573,
|
|
"epoch": 0.055242170783894186,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0003545,
|
|
"loss": 6.7241,
|
|
"mean_token_accuracy": 0.1101645365357399,
|
|
"num_tokens": 1232514.0,
|
|
"step": 710
|
|
},
|
|
{
|
|
"entropy": 7.2445765972137455,
|
|
"epoch": 0.05563120015561175,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000357,
|
|
"loss": 6.7763,
|
|
"mean_token_accuracy": 0.10698423609137535,
|
|
"num_tokens": 1240178.0,
|
|
"step": 715
|
|
},
|
|
{
|
|
"entropy": 7.076436710357666,
|
|
"epoch": 0.05602022952732931,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0003595,
|
|
"loss": 6.6795,
|
|
"mean_token_accuracy": 0.10781070590019226,
|
|
"num_tokens": 1248635.0,
|
|
"step": 720
|
|
},
|
|
{
|
|
"entropy": 7.209420871734619,
|
|
"epoch": 0.056409258899046875,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.000362,
|
|
"loss": 6.7874,
|
|
"mean_token_accuracy": 0.1086701013147831,
|
|
"num_tokens": 1256389.0,
|
|
"step": 725
|
|
},
|
|
{
|
|
"entropy": 7.077723169326783,
|
|
"epoch": 0.05679828827076444,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0003645,
|
|
"loss": 6.7275,
|
|
"mean_token_accuracy": 0.10797203481197357,
|
|
"num_tokens": 1264035.0,
|
|
"step": 730
|
|
},
|
|
{
|
|
"entropy": 7.17639570236206,
|
|
"epoch": 0.057187317642482006,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000367,
|
|
"loss": 6.7417,
|
|
"mean_token_accuracy": 0.10852355882525444,
|
|
"num_tokens": 1272941.0,
|
|
"step": 735
|
|
},
|
|
{
|
|
"entropy": 6.992896270751953,
|
|
"epoch": 0.05757634701419957,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0003695,
|
|
"loss": 6.719,
|
|
"mean_token_accuracy": 0.10654684156179428,
|
|
"num_tokens": 1281767.0,
|
|
"step": 740
|
|
},
|
|
{
|
|
"entropy": 7.257743215560913,
|
|
"epoch": 0.05796537638591714,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000372,
|
|
"loss": 6.8008,
|
|
"mean_token_accuracy": 0.10871746987104416,
|
|
"num_tokens": 1290049.0,
|
|
"step": 745
|
|
},
|
|
{
|
|
"entropy": 7.025216960906983,
|
|
"epoch": 0.0583544057576347,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0003745,
|
|
"loss": 6.6344,
|
|
"mean_token_accuracy": 0.11401695236563683,
|
|
"num_tokens": 1299032.0,
|
|
"step": 750
|
|
},
|
|
{
|
|
"entropy": 7.10672435760498,
|
|
"epoch": 0.05874343512935227,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000377,
|
|
"loss": 6.8797,
|
|
"mean_token_accuracy": 0.10258082747459411,
|
|
"num_tokens": 1308508.0,
|
|
"step": 755
|
|
},
|
|
{
|
|
"entropy": 7.206971597671509,
|
|
"epoch": 0.059132464501069834,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0003795,
|
|
"loss": 6.7266,
|
|
"mean_token_accuracy": 0.10653159618377686,
|
|
"num_tokens": 1317044.0,
|
|
"step": 760
|
|
},
|
|
{
|
|
"entropy": 7.129873371124267,
|
|
"epoch": 0.05952149387278739,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000382,
|
|
"loss": 6.7401,
|
|
"mean_token_accuracy": 0.10757752284407615,
|
|
"num_tokens": 1325554.0,
|
|
"step": 765
|
|
},
|
|
{
|
|
"entropy": 7.057963895797729,
|
|
"epoch": 0.05991052324450496,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0003845,
|
|
"loss": 6.6354,
|
|
"mean_token_accuracy": 0.10638404935598374,
|
|
"num_tokens": 1334201.0,
|
|
"step": 770
|
|
},
|
|
{
|
|
"entropy": 7.028696727752686,
|
|
"epoch": 0.060299552616222524,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00038700000000000003,
|
|
"loss": 6.6702,
|
|
"mean_token_accuracy": 0.11282677426934243,
|
|
"num_tokens": 1343061.0,
|
|
"step": 775
|
|
},
|
|
{
|
|
"entropy": 7.1010072231292725,
|
|
"epoch": 0.06068858198794009,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00038950000000000003,
|
|
"loss": 6.6186,
|
|
"mean_token_accuracy": 0.11468041315674782,
|
|
"num_tokens": 1352262.0,
|
|
"step": 780
|
|
},
|
|
{
|
|
"entropy": 7.018054246902466,
|
|
"epoch": 0.061077611359657655,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00039200000000000004,
|
|
"loss": 6.6796,
|
|
"mean_token_accuracy": 0.10959815979003906,
|
|
"num_tokens": 1361400.0,
|
|
"step": 785
|
|
},
|
|
{
|
|
"entropy": 7.052734136581421,
|
|
"epoch": 0.06146664073137522,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00039450000000000005,
|
|
"loss": 6.7896,
|
|
"mean_token_accuracy": 0.10606501176953316,
|
|
"num_tokens": 1369850.0,
|
|
"step": 790
|
|
},
|
|
{
|
|
"entropy": 7.069890785217285,
|
|
"epoch": 0.061855670103092786,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00039700000000000005,
|
|
"loss": 6.6306,
|
|
"mean_token_accuracy": 0.11038519069552422,
|
|
"num_tokens": 1378342.0,
|
|
"step": 795
|
|
},
|
|
{
|
|
"entropy": 7.049418497085571,
|
|
"epoch": 0.06224469947481035,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0003995,
|
|
"loss": 6.7302,
|
|
"mean_token_accuracy": 0.1076231300830841,
|
|
"num_tokens": 1386981.0,
|
|
"step": 800
|
|
},
|
|
{
|
|
"entropy": 7.077835321426392,
|
|
"epoch": 0.06263372884652792,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000402,
|
|
"loss": 6.8099,
|
|
"mean_token_accuracy": 0.10120006203651429,
|
|
"num_tokens": 1395801.0,
|
|
"step": 805
|
|
},
|
|
{
|
|
"entropy": 7.206391859054565,
|
|
"epoch": 0.06302275821824548,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004045,
|
|
"loss": 6.7163,
|
|
"mean_token_accuracy": 0.1102595366537571,
|
|
"num_tokens": 1403715.0,
|
|
"step": 810
|
|
},
|
|
{
|
|
"entropy": 7.088693380355835,
|
|
"epoch": 0.06341178758996305,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00040699999999999997,
|
|
"loss": 6.7922,
|
|
"mean_token_accuracy": 0.10654390528798104,
|
|
"num_tokens": 1413199.0,
|
|
"step": 815
|
|
},
|
|
{
|
|
"entropy": 7.05805082321167,
|
|
"epoch": 0.0638008169616806,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004095,
|
|
"loss": 6.7592,
|
|
"mean_token_accuracy": 0.10669645592570305,
|
|
"num_tokens": 1421918.0,
|
|
"step": 820
|
|
},
|
|
{
|
|
"entropy": 7.013793468475342,
|
|
"epoch": 0.06418984633339817,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000412,
|
|
"loss": 6.6581,
|
|
"mean_token_accuracy": 0.1045446127653122,
|
|
"num_tokens": 1430625.0,
|
|
"step": 825
|
|
},
|
|
{
|
|
"entropy": 6.975633525848389,
|
|
"epoch": 0.06457887570511574,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004145,
|
|
"loss": 6.6945,
|
|
"mean_token_accuracy": 0.1070571556687355,
|
|
"num_tokens": 1439158.0,
|
|
"step": 830
|
|
},
|
|
{
|
|
"entropy": 6.98923978805542,
|
|
"epoch": 0.0649679050768333,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000417,
|
|
"loss": 6.6591,
|
|
"mean_token_accuracy": 0.11569598615169525,
|
|
"num_tokens": 1448266.0,
|
|
"step": 835
|
|
},
|
|
{
|
|
"entropy": 7.057836484909058,
|
|
"epoch": 0.06535693444855087,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004195,
|
|
"loss": 6.7327,
|
|
"mean_token_accuracy": 0.11181987822055817,
|
|
"num_tokens": 1457322.0,
|
|
"step": 840
|
|
},
|
|
{
|
|
"entropy": 7.135942649841309,
|
|
"epoch": 0.06574596382026843,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000422,
|
|
"loss": 6.8529,
|
|
"mean_token_accuracy": 0.10292978584766388,
|
|
"num_tokens": 1466120.0,
|
|
"step": 845
|
|
},
|
|
{
|
|
"entropy": 7.01804838180542,
|
|
"epoch": 0.066134993191986,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004245,
|
|
"loss": 6.6053,
|
|
"mean_token_accuracy": 0.11059460267424584,
|
|
"num_tokens": 1474965.0,
|
|
"step": 850
|
|
},
|
|
{
|
|
"entropy": 6.987716579437256,
|
|
"epoch": 0.06652402256370356,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000427,
|
|
"loss": 6.6871,
|
|
"mean_token_accuracy": 0.10879706963896751,
|
|
"num_tokens": 1483483.0,
|
|
"step": 855
|
|
},
|
|
{
|
|
"entropy": 7.070033025741577,
|
|
"epoch": 0.06691305193542113,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004295,
|
|
"loss": 6.6423,
|
|
"mean_token_accuracy": 0.10447335988283157,
|
|
"num_tokens": 1492313.0,
|
|
"step": 860
|
|
},
|
|
{
|
|
"entropy": 6.95804386138916,
|
|
"epoch": 0.06730208130713869,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000432,
|
|
"loss": 6.5724,
|
|
"mean_token_accuracy": 0.11189851835370064,
|
|
"num_tokens": 1501081.0,
|
|
"step": 865
|
|
},
|
|
{
|
|
"entropy": 6.913361120223999,
|
|
"epoch": 0.06769111067885625,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004345,
|
|
"loss": 6.5954,
|
|
"mean_token_accuracy": 0.10529705733060837,
|
|
"num_tokens": 1510169.0,
|
|
"step": 870
|
|
},
|
|
{
|
|
"entropy": 6.990754508972168,
|
|
"epoch": 0.06808014005057382,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000437,
|
|
"loss": 6.5564,
|
|
"mean_token_accuracy": 0.10811040028929711,
|
|
"num_tokens": 1519546.0,
|
|
"step": 875
|
|
},
|
|
{
|
|
"entropy": 6.92680926322937,
|
|
"epoch": 0.06846916942229138,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004395,
|
|
"loss": 6.6583,
|
|
"mean_token_accuracy": 0.10640382617712021,
|
|
"num_tokens": 1529104.0,
|
|
"step": 880
|
|
},
|
|
{
|
|
"entropy": 6.795887804031372,
|
|
"epoch": 0.06885819879400895,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000442,
|
|
"loss": 6.6051,
|
|
"mean_token_accuracy": 0.1192264623939991,
|
|
"num_tokens": 1537033.0,
|
|
"step": 885
|
|
},
|
|
{
|
|
"entropy": 7.02658314704895,
|
|
"epoch": 0.06924722816572651,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004445,
|
|
"loss": 6.6247,
|
|
"mean_token_accuracy": 0.11063896790146828,
|
|
"num_tokens": 1545059.0,
|
|
"step": 890
|
|
},
|
|
{
|
|
"entropy": 7.039566946029663,
|
|
"epoch": 0.06963625753744408,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000447,
|
|
"loss": 6.6317,
|
|
"mean_token_accuracy": 0.10993520393967629,
|
|
"num_tokens": 1553784.0,
|
|
"step": 895
|
|
},
|
|
{
|
|
"entropy": 6.85557713508606,
|
|
"epoch": 0.07002528690916164,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00044950000000000003,
|
|
"loss": 6.5602,
|
|
"mean_token_accuracy": 0.11566279828548431,
|
|
"num_tokens": 1562059.0,
|
|
"step": 900
|
|
},
|
|
{
|
|
"entropy": 6.923605155944824,
|
|
"epoch": 0.0704143162808792,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00045200000000000004,
|
|
"loss": 6.6166,
|
|
"mean_token_accuracy": 0.10865532159805298,
|
|
"num_tokens": 1570061.0,
|
|
"step": 905
|
|
},
|
|
{
|
|
"entropy": 6.915492105484009,
|
|
"epoch": 0.07080334565259677,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00045450000000000004,
|
|
"loss": 6.5864,
|
|
"mean_token_accuracy": 0.11283667013049126,
|
|
"num_tokens": 1578261.0,
|
|
"step": 910
|
|
},
|
|
{
|
|
"entropy": 6.870081186294556,
|
|
"epoch": 0.07119237502431433,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00045700000000000005,
|
|
"loss": 6.5254,
|
|
"mean_token_accuracy": 0.11373848989605903,
|
|
"num_tokens": 1586260.0,
|
|
"step": 915
|
|
},
|
|
{
|
|
"entropy": 6.957163333892822,
|
|
"epoch": 0.0715814043960319,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00045950000000000006,
|
|
"loss": 6.7037,
|
|
"mean_token_accuracy": 0.10588114485144615,
|
|
"num_tokens": 1595234.0,
|
|
"step": 920
|
|
},
|
|
{
|
|
"entropy": 6.966896820068359,
|
|
"epoch": 0.07197043376774946,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000462,
|
|
"loss": 6.6038,
|
|
"mean_token_accuracy": 0.10876048058271408,
|
|
"num_tokens": 1604212.0,
|
|
"step": 925
|
|
},
|
|
{
|
|
"entropy": 6.890627479553222,
|
|
"epoch": 0.07235946313946703,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004645,
|
|
"loss": 6.6407,
|
|
"mean_token_accuracy": 0.11045560985803604,
|
|
"num_tokens": 1612925.0,
|
|
"step": 930
|
|
},
|
|
{
|
|
"entropy": 6.871489381790161,
|
|
"epoch": 0.07274849251118459,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000467,
|
|
"loss": 6.5285,
|
|
"mean_token_accuracy": 0.111960668861866,
|
|
"num_tokens": 1621804.0,
|
|
"step": 935
|
|
},
|
|
{
|
|
"entropy": 6.901230573654175,
|
|
"epoch": 0.07313752188290217,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004695,
|
|
"loss": 6.5111,
|
|
"mean_token_accuracy": 0.1133945107460022,
|
|
"num_tokens": 1630943.0,
|
|
"step": 940
|
|
},
|
|
{
|
|
"entropy": 6.869029235839844,
|
|
"epoch": 0.07352655125461972,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000472,
|
|
"loss": 6.4213,
|
|
"mean_token_accuracy": 0.11604218557476997,
|
|
"num_tokens": 1638899.0,
|
|
"step": 945
|
|
},
|
|
{
|
|
"entropy": 6.868594026565551,
|
|
"epoch": 0.07391558062633728,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004745,
|
|
"loss": 6.6351,
|
|
"mean_token_accuracy": 0.11411484777927398,
|
|
"num_tokens": 1647485.0,
|
|
"step": 950
|
|
},
|
|
{
|
|
"entropy": 6.925864124298096,
|
|
"epoch": 0.07430460999805485,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000477,
|
|
"loss": 6.6023,
|
|
"mean_token_accuracy": 0.11547646671533585,
|
|
"num_tokens": 1656290.0,
|
|
"step": 955
|
|
},
|
|
{
|
|
"entropy": 6.93121566772461,
|
|
"epoch": 0.07469363936977241,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004795,
|
|
"loss": 6.611,
|
|
"mean_token_accuracy": 0.1147051364183426,
|
|
"num_tokens": 1665474.0,
|
|
"step": 960
|
|
},
|
|
{
|
|
"entropy": 6.733439493179321,
|
|
"epoch": 0.07508266874148999,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000482,
|
|
"loss": 6.4883,
|
|
"mean_token_accuracy": 0.11983574107289315,
|
|
"num_tokens": 1673599.0,
|
|
"step": 965
|
|
},
|
|
{
|
|
"entropy": 6.897821712493896,
|
|
"epoch": 0.07547169811320754,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004845,
|
|
"loss": 6.4739,
|
|
"mean_token_accuracy": 0.11102246791124344,
|
|
"num_tokens": 1683282.0,
|
|
"step": 970
|
|
},
|
|
{
|
|
"entropy": 6.931991624832153,
|
|
"epoch": 0.07586072748492512,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000487,
|
|
"loss": 6.5991,
|
|
"mean_token_accuracy": 0.11667483672499657,
|
|
"num_tokens": 1691094.0,
|
|
"step": 975
|
|
},
|
|
{
|
|
"entropy": 6.752887296676636,
|
|
"epoch": 0.07624975685664268,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004895,
|
|
"loss": 6.4645,
|
|
"mean_token_accuracy": 0.11685017794370652,
|
|
"num_tokens": 1700053.0,
|
|
"step": 980
|
|
},
|
|
{
|
|
"entropy": 6.807966899871826,
|
|
"epoch": 0.07663878622836025,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000492,
|
|
"loss": 6.3961,
|
|
"mean_token_accuracy": 0.11701971888542176,
|
|
"num_tokens": 1707732.0,
|
|
"step": 985
|
|
},
|
|
{
|
|
"entropy": 6.825413990020752,
|
|
"epoch": 0.0770278156000778,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004945,
|
|
"loss": 6.6425,
|
|
"mean_token_accuracy": 0.10670604258775711,
|
|
"num_tokens": 1716406.0,
|
|
"step": 990
|
|
},
|
|
{
|
|
"entropy": 7.002917194366455,
|
|
"epoch": 0.07741684497179536,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000497,
|
|
"loss": 6.6635,
|
|
"mean_token_accuracy": 0.10928485170006752,
|
|
"num_tokens": 1725832.0,
|
|
"step": 995
|
|
},
|
|
{
|
|
"entropy": 6.912725305557251,
|
|
"epoch": 0.07780587434351294,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004995,
|
|
"loss": 6.576,
|
|
"mean_token_accuracy": 0.11019504964351653,
|
|
"num_tokens": 1734853.0,
|
|
"step": 1000
|
|
},
|
|
{
|
|
"entropy": 6.769201183319092,
|
|
"epoch": 0.0781949037152305,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004999999989075146,
|
|
"loss": 6.5842,
|
|
"mean_token_accuracy": 0.11545023322105408,
|
|
"num_tokens": 1744240.0,
|
|
"step": 1005
|
|
},
|
|
{
|
|
"entropy": 6.9675556182861325,
|
|
"epoch": 0.07858393308694807,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999999944692927,
|
|
"loss": 6.6019,
|
|
"mean_token_accuracy": 0.1125156231224537,
|
|
"num_tokens": 1753334.0,
|
|
"step": 1010
|
|
},
|
|
{
|
|
"entropy": 6.70109372138977,
|
|
"epoch": 0.07897296245866563,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000499999986617054,
|
|
"loss": 6.4932,
|
|
"mean_token_accuracy": 0.11150014474987983,
|
|
"num_tokens": 1762032.0,
|
|
"step": 1015
|
|
},
|
|
{
|
|
"entropy": 6.8338549613952635,
|
|
"epoch": 0.0793619918303832,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999999753507986,
|
|
"loss": 6.4863,
|
|
"mean_token_accuracy": 0.11209132522344589,
|
|
"num_tokens": 1770508.0,
|
|
"step": 1020
|
|
},
|
|
{
|
|
"entropy": 6.721220541000366,
|
|
"epoch": 0.07975102120210076,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999999606705267,
|
|
"loss": 6.3881,
|
|
"mean_token_accuracy": 0.12179349660873413,
|
|
"num_tokens": 1780167.0,
|
|
"step": 1025
|
|
},
|
|
{
|
|
"entropy": 6.887646627426148,
|
|
"epoch": 0.08014005057381832,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999999425762385,
|
|
"loss": 6.6013,
|
|
"mean_token_accuracy": 0.10411422997713089,
|
|
"num_tokens": 1788809.0,
|
|
"step": 1030
|
|
},
|
|
{
|
|
"entropy": 6.785115766525268,
|
|
"epoch": 0.08052907994553589,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004999999210679344,
|
|
"loss": 6.4975,
|
|
"mean_token_accuracy": 0.1171350821852684,
|
|
"num_tokens": 1797445.0,
|
|
"step": 1035
|
|
},
|
|
{
|
|
"entropy": 6.8339056968688965,
|
|
"epoch": 0.08091810931725345,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999998961456145,
|
|
"loss": 6.5205,
|
|
"mean_token_accuracy": 0.11023695170879363,
|
|
"num_tokens": 1806488.0,
|
|
"step": 1040
|
|
},
|
|
{
|
|
"entropy": 6.893251085281372,
|
|
"epoch": 0.08130713868897102,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004999998678092794,
|
|
"loss": 6.5876,
|
|
"mean_token_accuracy": 0.11547244265675545,
|
|
"num_tokens": 1815692.0,
|
|
"step": 1045
|
|
},
|
|
{
|
|
"entropy": 6.8416530132293705,
|
|
"epoch": 0.08169616806068858,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004999998360589293,
|
|
"loss": 6.5062,
|
|
"mean_token_accuracy": 0.1161237508058548,
|
|
"num_tokens": 1824599.0,
|
|
"step": 1050
|
|
},
|
|
{
|
|
"entropy": 6.88067593574524,
|
|
"epoch": 0.08208519743240615,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000499999800894565,
|
|
"loss": 6.652,
|
|
"mean_token_accuracy": 0.11225388348102569,
|
|
"num_tokens": 1833411.0,
|
|
"step": 1055
|
|
},
|
|
{
|
|
"entropy": 6.79389796257019,
|
|
"epoch": 0.08247422680412371,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004999997623161866,
|
|
"loss": 6.4656,
|
|
"mean_token_accuracy": 0.11337645724415779,
|
|
"num_tokens": 1842177.0,
|
|
"step": 1060
|
|
},
|
|
{
|
|
"entropy": 6.698552227020263,
|
|
"epoch": 0.08286325617584128,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999997203237951,
|
|
"loss": 6.4423,
|
|
"mean_token_accuracy": 0.12076986059546471,
|
|
"num_tokens": 1850176.0,
|
|
"step": 1065
|
|
},
|
|
{
|
|
"entropy": 6.799434804916382,
|
|
"epoch": 0.08325228554755884,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000499999674917391,
|
|
"loss": 6.5019,
|
|
"mean_token_accuracy": 0.11561930030584336,
|
|
"num_tokens": 1859464.0,
|
|
"step": 1070
|
|
},
|
|
{
|
|
"entropy": 6.655920028686523,
|
|
"epoch": 0.0836413149192764,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999996260969748,
|
|
"loss": 6.4004,
|
|
"mean_token_accuracy": 0.11484229564666748,
|
|
"num_tokens": 1867733.0,
|
|
"step": 1075
|
|
},
|
|
{
|
|
"entropy": 6.747368717193604,
|
|
"epoch": 0.08403034429099397,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999995738625475,
|
|
"loss": 6.3873,
|
|
"mean_token_accuracy": 0.12014570608735084,
|
|
"num_tokens": 1876010.0,
|
|
"step": 1080
|
|
},
|
|
{
|
|
"entropy": 6.721405076980591,
|
|
"epoch": 0.08441937366271153,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999995182141099,
|
|
"loss": 6.5431,
|
|
"mean_token_accuracy": 0.11369292438030243,
|
|
"num_tokens": 1884906.0,
|
|
"step": 1085
|
|
},
|
|
{
|
|
"entropy": 6.796774196624756,
|
|
"epoch": 0.0848084030344291,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999994591516626,
|
|
"loss": 6.4584,
|
|
"mean_token_accuracy": 0.11704446524381637,
|
|
"num_tokens": 1893464.0,
|
|
"step": 1090
|
|
},
|
|
{
|
|
"entropy": 6.746003484725952,
|
|
"epoch": 0.08519743240614666,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999993966752066,
|
|
"loss": 6.5049,
|
|
"mean_token_accuracy": 0.11562549471855163,
|
|
"num_tokens": 1902769.0,
|
|
"step": 1095
|
|
},
|
|
{
|
|
"entropy": 6.790870237350464,
|
|
"epoch": 0.08558646177786423,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000499999330784743,
|
|
"loss": 6.4273,
|
|
"mean_token_accuracy": 0.11782810240983962,
|
|
"num_tokens": 1911968.0,
|
|
"step": 1100
|
|
},
|
|
{
|
|
"entropy": 6.765281391143799,
|
|
"epoch": 0.08597549114958179,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004999992614802725,
|
|
"loss": 6.4144,
|
|
"mean_token_accuracy": 0.11969999745488166,
|
|
"num_tokens": 1920063.0,
|
|
"step": 1105
|
|
},
|
|
{
|
|
"entropy": 6.616898441314698,
|
|
"epoch": 0.08636452052129936,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004999991887617966,
|
|
"loss": 6.3855,
|
|
"mean_token_accuracy": 0.11925996840000153,
|
|
"num_tokens": 1929192.0,
|
|
"step": 1110
|
|
},
|
|
{
|
|
"entropy": 6.807584524154663,
|
|
"epoch": 0.08675354989301692,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999991126293158,
|
|
"loss": 6.5924,
|
|
"mean_token_accuracy": 0.11094593480229378,
|
|
"num_tokens": 1939082.0,
|
|
"step": 1115
|
|
},
|
|
{
|
|
"entropy": 6.590944242477417,
|
|
"epoch": 0.08714257926473448,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999990330828318,
|
|
"loss": 6.4607,
|
|
"mean_token_accuracy": 0.11833893656730651,
|
|
"num_tokens": 1948313.0,
|
|
"step": 1120
|
|
},
|
|
{
|
|
"entropy": 6.887479496002197,
|
|
"epoch": 0.08753160863645205,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004999989501223456,
|
|
"loss": 6.4559,
|
|
"mean_token_accuracy": 0.11990888267755509,
|
|
"num_tokens": 1957035.0,
|
|
"step": 1125
|
|
},
|
|
{
|
|
"entropy": 6.613681793212891,
|
|
"epoch": 0.08792063800816961,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999988637478584,
|
|
"loss": 6.4451,
|
|
"mean_token_accuracy": 0.11189156025648117,
|
|
"num_tokens": 1966041.0,
|
|
"step": 1130
|
|
},
|
|
{
|
|
"entropy": 6.8127364158630375,
|
|
"epoch": 0.08830966737988719,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999987739593716,
|
|
"loss": 6.4775,
|
|
"mean_token_accuracy": 0.10807354152202606,
|
|
"num_tokens": 1975019.0,
|
|
"step": 1135
|
|
},
|
|
{
|
|
"entropy": 6.693046903610229,
|
|
"epoch": 0.08869869675160474,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999986807568865,
|
|
"loss": 6.4086,
|
|
"mean_token_accuracy": 0.12410445287823677,
|
|
"num_tokens": 1982930.0,
|
|
"step": 1140
|
|
},
|
|
{
|
|
"entropy": 6.738013505935669,
|
|
"epoch": 0.08908772612332232,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004999985841404045,
|
|
"loss": 6.5192,
|
|
"mean_token_accuracy": 0.11475513577461242,
|
|
"num_tokens": 1991888.0,
|
|
"step": 1145
|
|
},
|
|
{
|
|
"entropy": 6.7153209209442135,
|
|
"epoch": 0.08947675549503988,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999984841099271,
|
|
"loss": 6.3537,
|
|
"mean_token_accuracy": 0.11961946487426758,
|
|
"num_tokens": 2000202.0,
|
|
"step": 1150
|
|
},
|
|
{
|
|
"entropy": 6.645785331726074,
|
|
"epoch": 0.08986578486675743,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000499998380665456,
|
|
"loss": 6.3866,
|
|
"mean_token_accuracy": 0.11929098591208458,
|
|
"num_tokens": 2009281.0,
|
|
"step": 1155
|
|
},
|
|
{
|
|
"entropy": 6.7169397354125975,
|
|
"epoch": 0.090254814238475,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999982738069924,
|
|
"loss": 6.4005,
|
|
"mean_token_accuracy": 0.1197192907333374,
|
|
"num_tokens": 2017806.0,
|
|
"step": 1160
|
|
},
|
|
{
|
|
"entropy": 6.742453861236572,
|
|
"epoch": 0.09064384361019256,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999981635345382,
|
|
"loss": 6.4894,
|
|
"mean_token_accuracy": 0.11311474218964576,
|
|
"num_tokens": 2027582.0,
|
|
"step": 1165
|
|
},
|
|
{
|
|
"entropy": 6.615994262695312,
|
|
"epoch": 0.09103287298191014,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999980498480949,
|
|
"loss": 6.3583,
|
|
"mean_token_accuracy": 0.12255421206355095,
|
|
"num_tokens": 2035427.0,
|
|
"step": 1170
|
|
},
|
|
{
|
|
"entropy": 6.8117693901062015,
|
|
"epoch": 0.0914219023536277,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999979327476644,
|
|
"loss": 6.5496,
|
|
"mean_token_accuracy": 0.1146990828216076,
|
|
"num_tokens": 2044603.0,
|
|
"step": 1175
|
|
},
|
|
{
|
|
"entropy": 6.670216655731201,
|
|
"epoch": 0.09181093172534527,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999978122332485,
|
|
"loss": 6.3796,
|
|
"mean_token_accuracy": 0.12255444154143333,
|
|
"num_tokens": 2053272.0,
|
|
"step": 1180
|
|
},
|
|
{
|
|
"entropy": 6.7155945777893065,
|
|
"epoch": 0.09219996109706283,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999976883048487,
|
|
"loss": 6.3888,
|
|
"mean_token_accuracy": 0.11783261522650719,
|
|
"num_tokens": 2061677.0,
|
|
"step": 1185
|
|
},
|
|
{
|
|
"entropy": 6.645085716247559,
|
|
"epoch": 0.0925889904687804,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999975609624673,
|
|
"loss": 6.4177,
|
|
"mean_token_accuracy": 0.11735781580209732,
|
|
"num_tokens": 2070282.0,
|
|
"step": 1190
|
|
},
|
|
{
|
|
"entropy": 6.775166654586792,
|
|
"epoch": 0.09297801984049796,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004999974302061059,
|
|
"loss": 6.5046,
|
|
"mean_token_accuracy": 0.11407285407185555,
|
|
"num_tokens": 2078812.0,
|
|
"step": 1195
|
|
},
|
|
{
|
|
"entropy": 6.684069871902466,
|
|
"epoch": 0.09336704921221552,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999972960357666,
|
|
"loss": 6.3885,
|
|
"mean_token_accuracy": 0.11487993374466896,
|
|
"num_tokens": 2087020.0,
|
|
"step": 1200
|
|
},
|
|
{
|
|
"entropy": 6.642553663253784,
|
|
"epoch": 0.09375607858393309,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999971584514516,
|
|
"loss": 6.3448,
|
|
"mean_token_accuracy": 0.12319881394505501,
|
|
"num_tokens": 2095933.0,
|
|
"step": 1205
|
|
},
|
|
{
|
|
"entropy": 6.58814435005188,
|
|
"epoch": 0.09414510795565065,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999970174531627,
|
|
"loss": 6.3534,
|
|
"mean_token_accuracy": 0.1218513771891594,
|
|
"num_tokens": 2105218.0,
|
|
"step": 1210
|
|
},
|
|
{
|
|
"entropy": 6.586796474456787,
|
|
"epoch": 0.09453413732736822,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999968730409022,
|
|
"loss": 6.2685,
|
|
"mean_token_accuracy": 0.12166600152850152,
|
|
"num_tokens": 2113808.0,
|
|
"step": 1215
|
|
},
|
|
{
|
|
"entropy": 6.612871360778809,
|
|
"epoch": 0.09492316669908578,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999967252146723,
|
|
"loss": 6.4393,
|
|
"mean_token_accuracy": 0.11809361055493355,
|
|
"num_tokens": 2123014.0,
|
|
"step": 1220
|
|
},
|
|
{
|
|
"entropy": 6.7797685146331785,
|
|
"epoch": 0.09531219607080335,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999965739744752,
|
|
"loss": 6.3594,
|
|
"mean_token_accuracy": 0.1224447838962078,
|
|
"num_tokens": 2131840.0,
|
|
"step": 1225
|
|
},
|
|
{
|
|
"entropy": 6.6803430080413815,
|
|
"epoch": 0.09570122544252091,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999964193203132,
|
|
"loss": 6.4559,
|
|
"mean_token_accuracy": 0.11718669459223748,
|
|
"num_tokens": 2140467.0,
|
|
"step": 1230
|
|
},
|
|
{
|
|
"entropy": 6.644154119491577,
|
|
"epoch": 0.09609025481423847,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999962612521888,
|
|
"loss": 6.402,
|
|
"mean_token_accuracy": 0.12155328691005707,
|
|
"num_tokens": 2149282.0,
|
|
"step": 1235
|
|
},
|
|
{
|
|
"entropy": 6.682088994979859,
|
|
"epoch": 0.09647928418595604,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999960997701041,
|
|
"loss": 6.3943,
|
|
"mean_token_accuracy": 0.1177689179778099,
|
|
"num_tokens": 2157781.0,
|
|
"step": 1240
|
|
},
|
|
{
|
|
"entropy": 6.6188617706298825,
|
|
"epoch": 0.0968683135576736,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999959348740618,
|
|
"loss": 6.3784,
|
|
"mean_token_accuracy": 0.12058958411216736,
|
|
"num_tokens": 2166482.0,
|
|
"step": 1245
|
|
},
|
|
{
|
|
"entropy": 6.618022489547729,
|
|
"epoch": 0.09725734292939117,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999957665640641,
|
|
"loss": 6.391,
|
|
"mean_token_accuracy": 0.11966572850942611,
|
|
"num_tokens": 2174559.0,
|
|
"step": 1250
|
|
},
|
|
{
|
|
"entropy": 6.600797843933106,
|
|
"epoch": 0.09764637230110873,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000499995594840114,
|
|
"loss": 6.2864,
|
|
"mean_token_accuracy": 0.1250573568046093,
|
|
"num_tokens": 2182374.0,
|
|
"step": 1255
|
|
},
|
|
{
|
|
"entropy": 6.596623373031616,
|
|
"epoch": 0.0980354016728263,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999954197022138,
|
|
"loss": 6.3828,
|
|
"mean_token_accuracy": 0.12434251680970192,
|
|
"num_tokens": 2191427.0,
|
|
"step": 1260
|
|
},
|
|
{
|
|
"entropy": 6.724891614913941,
|
|
"epoch": 0.09842443104454386,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999952411503661,
|
|
"loss": 6.4555,
|
|
"mean_token_accuracy": 0.11615066304802894,
|
|
"num_tokens": 2199698.0,
|
|
"step": 1265
|
|
},
|
|
{
|
|
"entropy": 6.649227571487427,
|
|
"epoch": 0.09881346041626143,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999950591845738,
|
|
"loss": 6.3025,
|
|
"mean_token_accuracy": 0.12375782802700996,
|
|
"num_tokens": 2208519.0,
|
|
"step": 1270
|
|
},
|
|
{
|
|
"entropy": 6.540418243408203,
|
|
"epoch": 0.09920248978797899,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999948738048397,
|
|
"loss": 6.3256,
|
|
"mean_token_accuracy": 0.12646739184856415,
|
|
"num_tokens": 2217453.0,
|
|
"step": 1275
|
|
},
|
|
{
|
|
"entropy": 6.652591800689697,
|
|
"epoch": 0.09959151915969655,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999946850111663,
|
|
"loss": 6.4342,
|
|
"mean_token_accuracy": 0.12071752622723579,
|
|
"num_tokens": 2225623.0,
|
|
"step": 1280
|
|
},
|
|
{
|
|
"entropy": 6.616247844696045,
|
|
"epoch": 0.09998054853141412,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999944928035569,
|
|
"loss": 6.3775,
|
|
"mean_token_accuracy": 0.12225224003195763,
|
|
"num_tokens": 2234519.0,
|
|
"step": 1285
|
|
},
|
|
{
|
|
"entropy": 6.634349060058594,
|
|
"epoch": 0.10036957790313168,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.000499994297182014,
|
|
"loss": 6.3755,
|
|
"mean_token_accuracy": 0.11769431307911873,
|
|
"num_tokens": 2242994.0,
|
|
"step": 1290
|
|
},
|
|
{
|
|
"entropy": 6.680039644241333,
|
|
"epoch": 0.10075860727484925,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999940981465408,
|
|
"loss": 6.3857,
|
|
"mean_token_accuracy": 0.12219717204570771,
|
|
"num_tokens": 2251687.0,
|
|
"step": 1295
|
|
},
|
|
{
|
|
"entropy": 6.514635276794434,
|
|
"epoch": 0.10114763664656681,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999938956971404,
|
|
"loss": 6.3129,
|
|
"mean_token_accuracy": 0.1261261597275734,
|
|
"num_tokens": 2260751.0,
|
|
"step": 1300
|
|
},
|
|
{
|
|
"entropy": 6.620299577713013,
|
|
"epoch": 0.10153666601828439,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999936898338156,
|
|
"loss": 6.2472,
|
|
"mean_token_accuracy": 0.13221826106309892,
|
|
"num_tokens": 2269125.0,
|
|
"step": 1305
|
|
},
|
|
{
|
|
"entropy": 6.51522011756897,
|
|
"epoch": 0.10192569539000194,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999934805565698,
|
|
"loss": 6.1888,
|
|
"mean_token_accuracy": 0.125250905752182,
|
|
"num_tokens": 2277098.0,
|
|
"step": 1310
|
|
},
|
|
{
|
|
"entropy": 6.529193973541259,
|
|
"epoch": 0.10231472476171952,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000499993267865406,
|
|
"loss": 6.4692,
|
|
"mean_token_accuracy": 0.1198497474193573,
|
|
"num_tokens": 2285953.0,
|
|
"step": 1315
|
|
},
|
|
{
|
|
"entropy": 6.745606851577759,
|
|
"epoch": 0.10270375413343708,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999930517603275,
|
|
"loss": 6.3768,
|
|
"mean_token_accuracy": 0.1258055381476879,
|
|
"num_tokens": 2294487.0,
|
|
"step": 1320
|
|
},
|
|
{
|
|
"entropy": 6.622673559188843,
|
|
"epoch": 0.10309278350515463,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999928322413374,
|
|
"loss": 6.4086,
|
|
"mean_token_accuracy": 0.11929989755153655,
|
|
"num_tokens": 2302915.0,
|
|
"step": 1325
|
|
},
|
|
{
|
|
"entropy": 6.561403083801269,
|
|
"epoch": 0.1034818128768722,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999926093084394,
|
|
"loss": 6.3663,
|
|
"mean_token_accuracy": 0.11803061217069626,
|
|
"num_tokens": 2310769.0,
|
|
"step": 1330
|
|
},
|
|
{
|
|
"entropy": 6.5140684127807615,
|
|
"epoch": 0.10387084224858976,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004999923829616365,
|
|
"loss": 6.2494,
|
|
"mean_token_accuracy": 0.12241962403059006,
|
|
"num_tokens": 2319987.0,
|
|
"step": 1335
|
|
},
|
|
{
|
|
"entropy": 6.584002923965454,
|
|
"epoch": 0.10425987162030734,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999921532009323,
|
|
"loss": 6.3661,
|
|
"mean_token_accuracy": 0.11921068355441093,
|
|
"num_tokens": 2328964.0,
|
|
"step": 1340
|
|
},
|
|
{
|
|
"entropy": 6.654835939407349,
|
|
"epoch": 0.1046489009920249,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004999919200263304,
|
|
"loss": 6.3291,
|
|
"mean_token_accuracy": 0.1160627231001854,
|
|
"num_tokens": 2337945.0,
|
|
"step": 1345
|
|
},
|
|
{
|
|
"entropy": 6.591136741638183,
|
|
"epoch": 0.10503793036374247,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004999916834378342,
|
|
"loss": 6.2104,
|
|
"mean_token_accuracy": 0.12765597626566888,
|
|
"num_tokens": 2345989.0,
|
|
"step": 1350
|
|
},
|
|
{
|
|
"entropy": 6.478854656219482,
|
|
"epoch": 0.10542695973546003,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999914434354472,
|
|
"loss": 6.3382,
|
|
"mean_token_accuracy": 0.12092916443943977,
|
|
"num_tokens": 2353752.0,
|
|
"step": 1355
|
|
},
|
|
{
|
|
"entropy": 6.624578857421875,
|
|
"epoch": 0.10581598910717759,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999912000191733,
|
|
"loss": 6.3137,
|
|
"mean_token_accuracy": 0.11746641173958779,
|
|
"num_tokens": 2361961.0,
|
|
"step": 1360
|
|
},
|
|
{
|
|
"entropy": 6.488426542282104,
|
|
"epoch": 0.10620501847889516,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000499990953189016,
|
|
"loss": 6.2343,
|
|
"mean_token_accuracy": 0.12489335536956787,
|
|
"num_tokens": 2370148.0,
|
|
"step": 1365
|
|
},
|
|
{
|
|
"entropy": 6.567029905319214,
|
|
"epoch": 0.10659404785061272,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999907029449791,
|
|
"loss": 6.26,
|
|
"mean_token_accuracy": 0.12806575298309325,
|
|
"num_tokens": 2379105.0,
|
|
"step": 1370
|
|
},
|
|
{
|
|
"entropy": 6.575870656967163,
|
|
"epoch": 0.10698307722233029,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999904492870663,
|
|
"loss": 6.3367,
|
|
"mean_token_accuracy": 0.1279653139412403,
|
|
"num_tokens": 2387417.0,
|
|
"step": 1375
|
|
},
|
|
{
|
|
"entropy": 6.600449657440185,
|
|
"epoch": 0.10737210659404785,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999901922152816,
|
|
"loss": 6.351,
|
|
"mean_token_accuracy": 0.12834431305527688,
|
|
"num_tokens": 2396163.0,
|
|
"step": 1380
|
|
},
|
|
{
|
|
"entropy": 6.425090503692627,
|
|
"epoch": 0.10776113596576542,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999899317296288,
|
|
"loss": 6.2181,
|
|
"mean_token_accuracy": 0.1259994737803936,
|
|
"num_tokens": 2404661.0,
|
|
"step": 1385
|
|
},
|
|
{
|
|
"entropy": 6.521142292022705,
|
|
"epoch": 0.10815016533748298,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004999896678301121,
|
|
"loss": 6.3092,
|
|
"mean_token_accuracy": 0.12282017320394516,
|
|
"num_tokens": 2413459.0,
|
|
"step": 1390
|
|
},
|
|
{
|
|
"entropy": 6.661787652969361,
|
|
"epoch": 0.10853919470920055,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004999894005167352,
|
|
"loss": 6.2619,
|
|
"mean_token_accuracy": 0.1296503096818924,
|
|
"num_tokens": 2421401.0,
|
|
"step": 1395
|
|
},
|
|
{
|
|
"entropy": 6.4945494651794435,
|
|
"epoch": 0.10892822408091811,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000499989129789502,
|
|
"loss": 6.2816,
|
|
"mean_token_accuracy": 0.1270440138876438,
|
|
"num_tokens": 2429983.0,
|
|
"step": 1400
|
|
},
|
|
{
|
|
"entropy": 6.612727165222168,
|
|
"epoch": 0.10931725345263567,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999888556484172,
|
|
"loss": 6.404,
|
|
"mean_token_accuracy": 0.11439228877425194,
|
|
"num_tokens": 2439206.0,
|
|
"step": 1405
|
|
},
|
|
{
|
|
"entropy": 6.542930793762207,
|
|
"epoch": 0.10970628282435324,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999885780934845,
|
|
"loss": 6.322,
|
|
"mean_token_accuracy": 0.13015031218528747,
|
|
"num_tokens": 2448801.0,
|
|
"step": 1410
|
|
},
|
|
{
|
|
"entropy": 6.549044942855835,
|
|
"epoch": 0.1100953121960708,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004999882971247081,
|
|
"loss": 6.3615,
|
|
"mean_token_accuracy": 0.12094596326351166,
|
|
"num_tokens": 2458007.0,
|
|
"step": 1415
|
|
},
|
|
{
|
|
"entropy": 6.577499437332153,
|
|
"epoch": 0.11048434156778837,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999880127420926,
|
|
"loss": 6.2512,
|
|
"mean_token_accuracy": 0.13192354440689086,
|
|
"num_tokens": 2466574.0,
|
|
"step": 1420
|
|
},
|
|
{
|
|
"entropy": 6.569367551803589,
|
|
"epoch": 0.11087337093950593,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999877249456421,
|
|
"loss": 6.3249,
|
|
"mean_token_accuracy": 0.12187402471899986,
|
|
"num_tokens": 2475263.0,
|
|
"step": 1425
|
|
},
|
|
{
|
|
"entropy": 6.3397541522979735,
|
|
"epoch": 0.1112624003112235,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999874337353609,
|
|
"loss": 6.0852,
|
|
"mean_token_accuracy": 0.12592738643288612,
|
|
"num_tokens": 2483738.0,
|
|
"step": 1430
|
|
},
|
|
{
|
|
"entropy": 6.452084875106811,
|
|
"epoch": 0.11165142968294106,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999871391112535,
|
|
"loss": 6.1944,
|
|
"mean_token_accuracy": 0.12284255996346474,
|
|
"num_tokens": 2492937.0,
|
|
"step": 1435
|
|
},
|
|
{
|
|
"entropy": 6.443626451492309,
|
|
"epoch": 0.11204045905465862,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999868410733244,
|
|
"loss": 6.2673,
|
|
"mean_token_accuracy": 0.12350725680589676,
|
|
"num_tokens": 2500716.0,
|
|
"step": 1440
|
|
},
|
|
{
|
|
"entropy": 6.534166097640991,
|
|
"epoch": 0.11242948842637619,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000499986539621578,
|
|
"loss": 6.2636,
|
|
"mean_token_accuracy": 0.12070308104157448,
|
|
"num_tokens": 2509385.0,
|
|
"step": 1445
|
|
},
|
|
{
|
|
"entropy": 6.586621427536011,
|
|
"epoch": 0.11281851779809375,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999862347560191,
|
|
"loss": 6.3272,
|
|
"mean_token_accuracy": 0.11826682835817337,
|
|
"num_tokens": 2518179.0,
|
|
"step": 1450
|
|
},
|
|
{
|
|
"entropy": 6.551055431365967,
|
|
"epoch": 0.11320754716981132,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999859264766521,
|
|
"loss": 6.2799,
|
|
"mean_token_accuracy": 0.12288788110017776,
|
|
"num_tokens": 2526644.0,
|
|
"step": 1455
|
|
},
|
|
{
|
|
"entropy": 6.4282551288604735,
|
|
"epoch": 0.11359657654152888,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999856147834817,
|
|
"loss": 6.1961,
|
|
"mean_token_accuracy": 0.12372745499014855,
|
|
"num_tokens": 2534998.0,
|
|
"step": 1460
|
|
},
|
|
{
|
|
"entropy": 6.5795485496521,
|
|
"epoch": 0.11398560591324645,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999852996765129,
|
|
"loss": 6.2592,
|
|
"mean_token_accuracy": 0.1275986485183239,
|
|
"num_tokens": 2543562.0,
|
|
"step": 1465
|
|
},
|
|
{
|
|
"entropy": 6.49003233909607,
|
|
"epoch": 0.11437463528496401,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999849811557502,
|
|
"loss": 6.2683,
|
|
"mean_token_accuracy": 0.12322987839579583,
|
|
"num_tokens": 2551688.0,
|
|
"step": 1470
|
|
},
|
|
{
|
|
"entropy": 6.513979959487915,
|
|
"epoch": 0.11476366465668159,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999846592211984,
|
|
"loss": 6.3312,
|
|
"mean_token_accuracy": 0.12700059562921523,
|
|
"num_tokens": 2560227.0,
|
|
"step": 1475
|
|
},
|
|
{
|
|
"entropy": 6.532626295089722,
|
|
"epoch": 0.11515269402839914,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999843338728626,
|
|
"loss": 6.2152,
|
|
"mean_token_accuracy": 0.12785592749714852,
|
|
"num_tokens": 2569245.0,
|
|
"step": 1480
|
|
},
|
|
{
|
|
"entropy": 6.480125904083252,
|
|
"epoch": 0.1155417234001167,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999840051107476,
|
|
"loss": 6.24,
|
|
"mean_token_accuracy": 0.12533404007554055,
|
|
"num_tokens": 2577706.0,
|
|
"step": 1485
|
|
},
|
|
{
|
|
"entropy": 6.5578601360321045,
|
|
"epoch": 0.11593075277183428,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999836729348584,
|
|
"loss": 6.274,
|
|
"mean_token_accuracy": 0.12649679258465768,
|
|
"num_tokens": 2586075.0,
|
|
"step": 1490
|
|
},
|
|
{
|
|
"entropy": 6.430877065658569,
|
|
"epoch": 0.11631978214355183,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999833373452,
|
|
"loss": 6.2685,
|
|
"mean_token_accuracy": 0.12222606092691421,
|
|
"num_tokens": 2594965.0,
|
|
"step": 1495
|
|
},
|
|
{
|
|
"entropy": 6.507078981399536,
|
|
"epoch": 0.1167088115152694,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999829983417778,
|
|
"loss": 6.1827,
|
|
"mean_token_accuracy": 0.12774747908115386,
|
|
"num_tokens": 2603355.0,
|
|
"step": 1500
|
|
},
|
|
{
|
|
"entropy": 6.502455472946167,
|
|
"epoch": 0.11709784088698696,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999826559245965,
|
|
"loss": 6.3264,
|
|
"mean_token_accuracy": 0.12180719375610352,
|
|
"num_tokens": 2611697.0,
|
|
"step": 1505
|
|
},
|
|
{
|
|
"entropy": 6.491758203506469,
|
|
"epoch": 0.11748687025870454,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999823100936615,
|
|
"loss": 6.2036,
|
|
"mean_token_accuracy": 0.12712125554680825,
|
|
"num_tokens": 2620821.0,
|
|
"step": 1510
|
|
},
|
|
{
|
|
"entropy": 6.50208306312561,
|
|
"epoch": 0.1178758996304221,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999819608489781,
|
|
"loss": 6.2029,
|
|
"mean_token_accuracy": 0.12601106688380243,
|
|
"num_tokens": 2628891.0,
|
|
"step": 1515
|
|
},
|
|
{
|
|
"entropy": 6.50620698928833,
|
|
"epoch": 0.11826492900213967,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999816081905515,
|
|
"loss": 6.3238,
|
|
"mean_token_accuracy": 0.11945099160075187,
|
|
"num_tokens": 2638641.0,
|
|
"step": 1520
|
|
},
|
|
{
|
|
"entropy": 6.499932670593262,
|
|
"epoch": 0.11865395837385723,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999812521183872,
|
|
"loss": 6.2141,
|
|
"mean_token_accuracy": 0.1259573705494404,
|
|
"num_tokens": 2646898.0,
|
|
"step": 1525
|
|
},
|
|
{
|
|
"entropy": 6.5239215850830075,
|
|
"epoch": 0.11904298774557479,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999808926324903,
|
|
"loss": 6.2766,
|
|
"mean_token_accuracy": 0.12060346677899361,
|
|
"num_tokens": 2655404.0,
|
|
"step": 1530
|
|
},
|
|
{
|
|
"entropy": 6.430968427658081,
|
|
"epoch": 0.11943201711729236,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999805297328665,
|
|
"loss": 6.1457,
|
|
"mean_token_accuracy": 0.1309056155383587,
|
|
"num_tokens": 2663851.0,
|
|
"step": 1535
|
|
},
|
|
{
|
|
"entropy": 6.474033451080322,
|
|
"epoch": 0.11982104648900992,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999801634195214,
|
|
"loss": 6.2032,
|
|
"mean_token_accuracy": 0.12700969725847244,
|
|
"num_tokens": 2672231.0,
|
|
"step": 1540
|
|
},
|
|
{
|
|
"entropy": 6.383044147491455,
|
|
"epoch": 0.12021007586072749,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999797936924603,
|
|
"loss": 6.2097,
|
|
"mean_token_accuracy": 0.12720894515514375,
|
|
"num_tokens": 2680198.0,
|
|
"step": 1545
|
|
},
|
|
{
|
|
"entropy": 6.566014909744263,
|
|
"epoch": 0.12059910523244505,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000499979420551689,
|
|
"loss": 6.2435,
|
|
"mean_token_accuracy": 0.12246377095580101,
|
|
"num_tokens": 2689208.0,
|
|
"step": 1550
|
|
},
|
|
{
|
|
"entropy": 6.521243476867676,
|
|
"epoch": 0.12098813460416262,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000499979043997213,
|
|
"loss": 6.2938,
|
|
"mean_token_accuracy": 0.12263652533292771,
|
|
"num_tokens": 2698116.0,
|
|
"step": 1555
|
|
},
|
|
{
|
|
"entropy": 6.459107732772827,
|
|
"epoch": 0.12137716397588018,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999786640290381,
|
|
"loss": 6.2054,
|
|
"mean_token_accuracy": 0.12052173987030983,
|
|
"num_tokens": 2707046.0,
|
|
"step": 1560
|
|
},
|
|
{
|
|
"entropy": 6.418560600280761,
|
|
"epoch": 0.12176619334759774,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999782806471701,
|
|
"loss": 6.177,
|
|
"mean_token_accuracy": 0.12391525506973267,
|
|
"num_tokens": 2714929.0,
|
|
"step": 1565
|
|
},
|
|
{
|
|
"entropy": 6.417961502075196,
|
|
"epoch": 0.12215522271931531,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999778938516147,
|
|
"loss": 6.2133,
|
|
"mean_token_accuracy": 0.12548111602663994,
|
|
"num_tokens": 2723436.0,
|
|
"step": 1570
|
|
},
|
|
{
|
|
"entropy": 6.4104386329650875,
|
|
"epoch": 0.12254425209103287,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000499977503642378,
|
|
"loss": 6.2541,
|
|
"mean_token_accuracy": 0.12425186485052109,
|
|
"num_tokens": 2731935.0,
|
|
"step": 1575
|
|
},
|
|
{
|
|
"entropy": 6.443300056457519,
|
|
"epoch": 0.12293328146275044,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999771100194656,
|
|
"loss": 6.0876,
|
|
"mean_token_accuracy": 0.13300335481762887,
|
|
"num_tokens": 2740307.0,
|
|
"step": 1580
|
|
},
|
|
{
|
|
"entropy": 6.338034725189209,
|
|
"epoch": 0.123322310834468,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999767129828837,
|
|
"loss": 6.1018,
|
|
"mean_token_accuracy": 0.13122726380825042,
|
|
"num_tokens": 2749077.0,
|
|
"step": 1585
|
|
},
|
|
{
|
|
"entropy": 6.4701416969299315,
|
|
"epoch": 0.12371134020618557,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999763125326383,
|
|
"loss": 6.2168,
|
|
"mean_token_accuracy": 0.12340875789523124,
|
|
"num_tokens": 2758133.0,
|
|
"step": 1590
|
|
},
|
|
{
|
|
"entropy": 6.40848298072815,
|
|
"epoch": 0.12410036957790313,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004999759086687355,
|
|
"loss": 6.1445,
|
|
"mean_token_accuracy": 0.13228374421596528,
|
|
"num_tokens": 2766509.0,
|
|
"step": 1595
|
|
},
|
|
{
|
|
"entropy": 6.386842536926269,
|
|
"epoch": 0.1244893989496207,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999755013911813,
|
|
"loss": 6.3118,
|
|
"mean_token_accuracy": 0.1265620172023773,
|
|
"num_tokens": 2775908.0,
|
|
"step": 1600
|
|
},
|
|
{
|
|
"entropy": 6.4204363346099855,
|
|
"epoch": 0.12487842832133826,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000499975090699982,
|
|
"loss": 6.0838,
|
|
"mean_token_accuracy": 0.13560190349817275,
|
|
"num_tokens": 2784803.0,
|
|
"step": 1605
|
|
},
|
|
{
|
|
"entropy": 6.483498287200928,
|
|
"epoch": 0.12526745769305583,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999746765951438,
|
|
"loss": 6.2464,
|
|
"mean_token_accuracy": 0.1212728351354599,
|
|
"num_tokens": 2793897.0,
|
|
"step": 1610
|
|
},
|
|
{
|
|
"entropy": 6.408759880065918,
|
|
"epoch": 0.1256564870647734,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999742590766729,
|
|
"loss": 6.0687,
|
|
"mean_token_accuracy": 0.13336466401815414,
|
|
"num_tokens": 2802652.0,
|
|
"step": 1615
|
|
},
|
|
{
|
|
"entropy": 6.33557162284851,
|
|
"epoch": 0.12604551643649095,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999738381445757,
|
|
"loss": 6.2091,
|
|
"mean_token_accuracy": 0.12232308834791183,
|
|
"num_tokens": 2811527.0,
|
|
"step": 1620
|
|
},
|
|
{
|
|
"entropy": 6.483191967010498,
|
|
"epoch": 0.1264345458082085,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999734137988586,
|
|
"loss": 6.0784,
|
|
"mean_token_accuracy": 0.13252645283937453,
|
|
"num_tokens": 2819410.0,
|
|
"step": 1625
|
|
},
|
|
{
|
|
"entropy": 6.221581315994262,
|
|
"epoch": 0.1268235751799261,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000499972986039528,
|
|
"loss": 6.0676,
|
|
"mean_token_accuracy": 0.13655331283807753,
|
|
"num_tokens": 2828079.0,
|
|
"step": 1630
|
|
},
|
|
{
|
|
"entropy": 6.443491744995117,
|
|
"epoch": 0.12721260455164365,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999725548665904,
|
|
"loss": 6.186,
|
|
"mean_token_accuracy": 0.1318517453968525,
|
|
"num_tokens": 2836326.0,
|
|
"step": 1635
|
|
},
|
|
{
|
|
"entropy": 6.40787935256958,
|
|
"epoch": 0.1276016339233612,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999721202800524,
|
|
"loss": 6.2349,
|
|
"mean_token_accuracy": 0.12275687456130982,
|
|
"num_tokens": 2845271.0,
|
|
"step": 1640
|
|
},
|
|
{
|
|
"entropy": 6.344908809661865,
|
|
"epoch": 0.12799066329507877,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999716822799206,
|
|
"loss": 6.1049,
|
|
"mean_token_accuracy": 0.13598963469266892,
|
|
"num_tokens": 2853688.0,
|
|
"step": 1645
|
|
},
|
|
{
|
|
"entropy": 6.402085828781128,
|
|
"epoch": 0.12837969266679633,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999712408662016,
|
|
"loss": 6.1851,
|
|
"mean_token_accuracy": 0.13216232731938363,
|
|
"num_tokens": 2862261.0,
|
|
"step": 1650
|
|
},
|
|
{
|
|
"entropy": 6.434685897827149,
|
|
"epoch": 0.12876872203851392,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999707960389021,
|
|
"loss": 6.215,
|
|
"mean_token_accuracy": 0.12633103504776955,
|
|
"num_tokens": 2871324.0,
|
|
"step": 1655
|
|
},
|
|
{
|
|
"entropy": 6.462427854537964,
|
|
"epoch": 0.12915775141023147,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999703477980288,
|
|
"loss": 6.2637,
|
|
"mean_token_accuracy": 0.1204333670437336,
|
|
"num_tokens": 2880268.0,
|
|
"step": 1660
|
|
},
|
|
{
|
|
"entropy": 6.463560485839844,
|
|
"epoch": 0.12954678078194903,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999698961435885,
|
|
"loss": 6.1692,
|
|
"mean_token_accuracy": 0.12939711883664132,
|
|
"num_tokens": 2888510.0,
|
|
"step": 1665
|
|
},
|
|
{
|
|
"entropy": 6.391593933105469,
|
|
"epoch": 0.1299358101536666,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999694410755882,
|
|
"loss": 6.0645,
|
|
"mean_token_accuracy": 0.13939797282218933,
|
|
"num_tokens": 2897616.0,
|
|
"step": 1670
|
|
},
|
|
{
|
|
"entropy": 6.344762563705444,
|
|
"epoch": 0.13032483952538418,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999689825940347,
|
|
"loss": 6.1536,
|
|
"mean_token_accuracy": 0.13106709420681,
|
|
"num_tokens": 2905703.0,
|
|
"step": 1675
|
|
},
|
|
{
|
|
"entropy": 6.3409374237060545,
|
|
"epoch": 0.13071386889710174,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999685206989349,
|
|
"loss": 6.0402,
|
|
"mean_token_accuracy": 0.1389915518462658,
|
|
"num_tokens": 2914881.0,
|
|
"step": 1680
|
|
},
|
|
{
|
|
"entropy": 6.31886305809021,
|
|
"epoch": 0.1311028982688193,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999680553902959,
|
|
"loss": 6.0988,
|
|
"mean_token_accuracy": 0.13385162875056267,
|
|
"num_tokens": 2923563.0,
|
|
"step": 1685
|
|
},
|
|
{
|
|
"entropy": 6.459726095199585,
|
|
"epoch": 0.13149192764053685,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999675866681247,
|
|
"loss": 6.3,
|
|
"mean_token_accuracy": 0.12524155154824257,
|
|
"num_tokens": 2932821.0,
|
|
"step": 1690
|
|
},
|
|
{
|
|
"entropy": 6.422298765182495,
|
|
"epoch": 0.1318809570122544,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999671145324286,
|
|
"loss": 6.2041,
|
|
"mean_token_accuracy": 0.12897164598107339,
|
|
"num_tokens": 2940926.0,
|
|
"step": 1695
|
|
},
|
|
{
|
|
"entropy": 6.406879520416259,
|
|
"epoch": 0.132269986383972,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999666389832144,
|
|
"loss": 6.1352,
|
|
"mean_token_accuracy": 0.13091752603650092,
|
|
"num_tokens": 2950028.0,
|
|
"step": 1700
|
|
},
|
|
{
|
|
"entropy": 6.331121397018433,
|
|
"epoch": 0.13265901575568956,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999661600204897,
|
|
"loss": 6.158,
|
|
"mean_token_accuracy": 0.13076577857136726,
|
|
"num_tokens": 2957636.0,
|
|
"step": 1705
|
|
},
|
|
{
|
|
"entropy": 6.264277982711792,
|
|
"epoch": 0.13304804512740712,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999656776442615,
|
|
"loss": 5.9208,
|
|
"mean_token_accuracy": 0.1367864117026329,
|
|
"num_tokens": 2966544.0,
|
|
"step": 1710
|
|
},
|
|
{
|
|
"entropy": 6.367716217041016,
|
|
"epoch": 0.13343707449912467,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999651918545372,
|
|
"loss": 6.156,
|
|
"mean_token_accuracy": 0.12581324428319932,
|
|
"num_tokens": 2976236.0,
|
|
"step": 1715
|
|
},
|
|
{
|
|
"entropy": 6.343806362152099,
|
|
"epoch": 0.13382610387084226,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999647026513243,
|
|
"loss": 6.1055,
|
|
"mean_token_accuracy": 0.1320023201406002,
|
|
"num_tokens": 2984261.0,
|
|
"step": 1720
|
|
},
|
|
{
|
|
"entropy": 6.298451852798462,
|
|
"epoch": 0.13421513324255982,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00049996421003463,
|
|
"loss": 6.101,
|
|
"mean_token_accuracy": 0.1286357559263706,
|
|
"num_tokens": 2992970.0,
|
|
"step": 1725
|
|
},
|
|
{
|
|
"entropy": 6.399670839309692,
|
|
"epoch": 0.13460416261427738,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999637140044619,
|
|
"loss": 6.1143,
|
|
"mean_token_accuracy": 0.13840305656194687,
|
|
"num_tokens": 3001356.0,
|
|
"step": 1730
|
|
},
|
|
{
|
|
"entropy": 6.320483160018921,
|
|
"epoch": 0.13499319198599494,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999632145608275,
|
|
"loss": 6.1338,
|
|
"mean_token_accuracy": 0.13537682592868805,
|
|
"num_tokens": 3009509.0,
|
|
"step": 1735
|
|
},
|
|
{
|
|
"entropy": 6.370671033859253,
|
|
"epoch": 0.1353822213577125,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999627117037343,
|
|
"loss": 6.1434,
|
|
"mean_token_accuracy": 0.12680430486798286,
|
|
"num_tokens": 3017675.0,
|
|
"step": 1740
|
|
},
|
|
{
|
|
"entropy": 6.366966485977173,
|
|
"epoch": 0.13577125072943008,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00049996220543319,
|
|
"loss": 6.1149,
|
|
"mean_token_accuracy": 0.1355073034763336,
|
|
"num_tokens": 3025527.0,
|
|
"step": 1745
|
|
},
|
|
{
|
|
"entropy": 6.313861942291259,
|
|
"epoch": 0.13616028010114764,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999616957492025,
|
|
"loss": 6.0614,
|
|
"mean_token_accuracy": 0.13035932257771493,
|
|
"num_tokens": 3034251.0,
|
|
"step": 1750
|
|
},
|
|
{
|
|
"entropy": 6.291455030441284,
|
|
"epoch": 0.1365493094728652,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999611826517793,
|
|
"loss": 6.2936,
|
|
"mean_token_accuracy": 0.12496695667505264,
|
|
"num_tokens": 3043272.0,
|
|
"step": 1755
|
|
},
|
|
{
|
|
"entropy": 6.394519853591919,
|
|
"epoch": 0.13693833884458276,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999606661409281,
|
|
"loss": 6.1376,
|
|
"mean_token_accuracy": 0.13365355953574182,
|
|
"num_tokens": 3051092.0,
|
|
"step": 1760
|
|
},
|
|
{
|
|
"entropy": 6.389160776138306,
|
|
"epoch": 0.13732736821630034,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999601462166569,
|
|
"loss": 6.1093,
|
|
"mean_token_accuracy": 0.13206425607204436,
|
|
"num_tokens": 3060584.0,
|
|
"step": 1765
|
|
},
|
|
{
|
|
"entropy": 6.292361640930176,
|
|
"epoch": 0.1377163975880179,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999596228789736,
|
|
"loss": 6.112,
|
|
"mean_token_accuracy": 0.13125555962324142,
|
|
"num_tokens": 3069990.0,
|
|
"step": 1770
|
|
},
|
|
{
|
|
"entropy": 6.413235998153686,
|
|
"epoch": 0.13810542695973546,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999590961278859,
|
|
"loss": 6.0901,
|
|
"mean_token_accuracy": 0.1285365678369999,
|
|
"num_tokens": 3078837.0,
|
|
"step": 1775
|
|
},
|
|
{
|
|
"entropy": 6.21497654914856,
|
|
"epoch": 0.13849445633145302,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999585659634021,
|
|
"loss": 6.0786,
|
|
"mean_token_accuracy": 0.1374272361397743,
|
|
"num_tokens": 3087557.0,
|
|
"step": 1780
|
|
},
|
|
{
|
|
"entropy": 6.306288623809815,
|
|
"epoch": 0.13888348570317058,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999580323855301,
|
|
"loss": 6.086,
|
|
"mean_token_accuracy": 0.13215372562408448,
|
|
"num_tokens": 3096524.0,
|
|
"step": 1785
|
|
},
|
|
{
|
|
"entropy": 6.460636615753174,
|
|
"epoch": 0.13927251507488816,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999574953942781,
|
|
"loss": 6.1695,
|
|
"mean_token_accuracy": 0.1295361652970314,
|
|
"num_tokens": 3105271.0,
|
|
"step": 1790
|
|
},
|
|
{
|
|
"entropy": 6.278649234771729,
|
|
"epoch": 0.13966154444660572,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999569549896541,
|
|
"loss": 6.0498,
|
|
"mean_token_accuracy": 0.13072569519281388,
|
|
"num_tokens": 3114479.0,
|
|
"step": 1795
|
|
},
|
|
{
|
|
"entropy": 6.313834571838379,
|
|
"epoch": 0.14005057381832328,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999564111716665,
|
|
"loss": 6.0575,
|
|
"mean_token_accuracy": 0.13794643208384513,
|
|
"num_tokens": 3123319.0,
|
|
"step": 1800
|
|
},
|
|
{
|
|
"entropy": 6.3173986911773685,
|
|
"epoch": 0.14043960319004084,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999558639403232,
|
|
"loss": 6.0822,
|
|
"mean_token_accuracy": 0.13311919420957566,
|
|
"num_tokens": 3132532.0,
|
|
"step": 1805
|
|
},
|
|
{
|
|
"entropy": 6.4103357791900635,
|
|
"epoch": 0.1408286325617584,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999553132956328,
|
|
"loss": 6.155,
|
|
"mean_token_accuracy": 0.13053008466958999,
|
|
"num_tokens": 3140798.0,
|
|
"step": 1810
|
|
},
|
|
{
|
|
"entropy": 6.330409145355224,
|
|
"epoch": 0.14121766193347599,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999547592376035,
|
|
"loss": 6.1438,
|
|
"mean_token_accuracy": 0.13290951102972032,
|
|
"num_tokens": 3149607.0,
|
|
"step": 1815
|
|
},
|
|
{
|
|
"entropy": 6.251868629455567,
|
|
"epoch": 0.14160669130519354,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004999542017662438,
|
|
"loss": 5.9608,
|
|
"mean_token_accuracy": 0.13571959659457206,
|
|
"num_tokens": 3157537.0,
|
|
"step": 1820
|
|
},
|
|
{
|
|
"entropy": 6.296808433532715,
|
|
"epoch": 0.1419957206769111,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999536408815623,
|
|
"loss": 6.119,
|
|
"mean_token_accuracy": 0.13132073506712913,
|
|
"num_tokens": 3166351.0,
|
|
"step": 1825
|
|
},
|
|
{
|
|
"entropy": 6.25454888343811,
|
|
"epoch": 0.14238475004862866,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999530765835672,
|
|
"loss": 5.9837,
|
|
"mean_token_accuracy": 0.13595960065722465,
|
|
"num_tokens": 3174690.0,
|
|
"step": 1830
|
|
},
|
|
{
|
|
"entropy": 6.26420259475708,
|
|
"epoch": 0.14277377942034625,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999525088722673,
|
|
"loss": 6.1311,
|
|
"mean_token_accuracy": 0.12212195172905922,
|
|
"num_tokens": 3183460.0,
|
|
"step": 1835
|
|
},
|
|
{
|
|
"entropy": 6.3232808113098145,
|
|
"epoch": 0.1431628087920638,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999519377476711,
|
|
"loss": 6.0604,
|
|
"mean_token_accuracy": 0.13456608951091767,
|
|
"num_tokens": 3192183.0,
|
|
"step": 1840
|
|
},
|
|
{
|
|
"entropy": 6.307611131668091,
|
|
"epoch": 0.14355183816378136,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999513632097872,
|
|
"loss": 6.1451,
|
|
"mean_token_accuracy": 0.13180193528532982,
|
|
"num_tokens": 3200875.0,
|
|
"step": 1845
|
|
},
|
|
{
|
|
"entropy": 6.305696964263916,
|
|
"epoch": 0.14394086753549892,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999507852586245,
|
|
"loss": 6.0116,
|
|
"mean_token_accuracy": 0.13570416271686553,
|
|
"num_tokens": 3209797.0,
|
|
"step": 1850
|
|
},
|
|
{
|
|
"entropy": 6.369657182693482,
|
|
"epoch": 0.14432989690721648,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999502038941917,
|
|
"loss": 6.1304,
|
|
"mean_token_accuracy": 0.12988198101520537,
|
|
"num_tokens": 3218612.0,
|
|
"step": 1855
|
|
},
|
|
{
|
|
"entropy": 6.262934398651123,
|
|
"epoch": 0.14471892627893407,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999496191164975,
|
|
"loss": 6.0438,
|
|
"mean_token_accuracy": 0.13271042779088021,
|
|
"num_tokens": 3227364.0,
|
|
"step": 1860
|
|
},
|
|
{
|
|
"entropy": 6.2206947803497314,
|
|
"epoch": 0.14510795565065163,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000499949030925551,
|
|
"loss": 6.0766,
|
|
"mean_token_accuracy": 0.13223439678549767,
|
|
"num_tokens": 3236448.0,
|
|
"step": 1865
|
|
},
|
|
{
|
|
"entropy": 6.286829996109009,
|
|
"epoch": 0.14549698502236919,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999484393213609,
|
|
"loss": 6.0017,
|
|
"mean_token_accuracy": 0.1383517123758793,
|
|
"num_tokens": 3244957.0,
|
|
"step": 1870
|
|
},
|
|
{
|
|
"entropy": 6.170301628112793,
|
|
"epoch": 0.14588601439408674,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999478443039363,
|
|
"loss": 6.0811,
|
|
"mean_token_accuracy": 0.12760961875319482,
|
|
"num_tokens": 3253250.0,
|
|
"step": 1875
|
|
},
|
|
{
|
|
"entropy": 6.355124139785767,
|
|
"epoch": 0.14627504376580433,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999472458732862,
|
|
"loss": 5.9909,
|
|
"mean_token_accuracy": 0.13991812169551848,
|
|
"num_tokens": 3261455.0,
|
|
"step": 1880
|
|
},
|
|
{
|
|
"entropy": 6.20726432800293,
|
|
"epoch": 0.1466640731375219,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999466440294198,
|
|
"loss": 6.0483,
|
|
"mean_token_accuracy": 0.13473452106118203,
|
|
"num_tokens": 3270108.0,
|
|
"step": 1885
|
|
},
|
|
{
|
|
"entropy": 6.375078630447388,
|
|
"epoch": 0.14705310250923945,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000499946038772346,
|
|
"loss": 6.1673,
|
|
"mean_token_accuracy": 0.13430963680148125,
|
|
"num_tokens": 3278425.0,
|
|
"step": 1890
|
|
},
|
|
{
|
|
"entropy": 6.323588514328003,
|
|
"epoch": 0.147442131880957,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999454301020741,
|
|
"loss": 6.0903,
|
|
"mean_token_accuracy": 0.13201274499297141,
|
|
"num_tokens": 3288358.0,
|
|
"step": 1895
|
|
},
|
|
{
|
|
"entropy": 6.309664011001587,
|
|
"epoch": 0.14783116125267456,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004999448180186133,
|
|
"loss": 6.0894,
|
|
"mean_token_accuracy": 0.13479083627462388,
|
|
"num_tokens": 3297199.0,
|
|
"step": 1900
|
|
},
|
|
{
|
|
"entropy": 6.2201214790344235,
|
|
"epoch": 0.14822019062439215,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000499944202521973,
|
|
"loss": 6.0839,
|
|
"mean_token_accuracy": 0.13048910349607468,
|
|
"num_tokens": 3306350.0,
|
|
"step": 1905
|
|
},
|
|
{
|
|
"entropy": 6.295196104049682,
|
|
"epoch": 0.1486092199961097,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999435836121624,
|
|
"loss": 5.9272,
|
|
"mean_token_accuracy": 0.1357748366892338,
|
|
"num_tokens": 3314921.0,
|
|
"step": 1910
|
|
},
|
|
{
|
|
"entropy": 6.121889209747314,
|
|
"epoch": 0.14899824936782727,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000499942961289191,
|
|
"loss": 6.0676,
|
|
"mean_token_accuracy": 0.13817773759365082,
|
|
"num_tokens": 3323324.0,
|
|
"step": 1915
|
|
},
|
|
{
|
|
"entropy": 6.420400953292846,
|
|
"epoch": 0.14938727873954483,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999423355530683,
|
|
"loss": 6.1954,
|
|
"mean_token_accuracy": 0.12781462743878363,
|
|
"num_tokens": 3331614.0,
|
|
"step": 1920
|
|
},
|
|
{
|
|
"entropy": 6.316415214538575,
|
|
"epoch": 0.1497763081112624,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004999417064038035,
|
|
"loss": 6.0304,
|
|
"mean_token_accuracy": 0.1352904126048088,
|
|
"num_tokens": 3339573.0,
|
|
"step": 1925
|
|
},
|
|
{
|
|
"entropy": 6.221908378601074,
|
|
"epoch": 0.15016533748297997,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999410738414065,
|
|
"loss": 6.0006,
|
|
"mean_token_accuracy": 0.1410306826233864,
|
|
"num_tokens": 3347775.0,
|
|
"step": 1930
|
|
},
|
|
{
|
|
"entropy": 6.257770204544068,
|
|
"epoch": 0.15055436685469753,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999404378658866,
|
|
"loss": 5.9657,
|
|
"mean_token_accuracy": 0.13755407258868219,
|
|
"num_tokens": 3356947.0,
|
|
"step": 1935
|
|
},
|
|
{
|
|
"entropy": 6.257419776916504,
|
|
"epoch": 0.1509433962264151,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999397984772536,
|
|
"loss": 6.0561,
|
|
"mean_token_accuracy": 0.13719375282526017,
|
|
"num_tokens": 3365420.0,
|
|
"step": 1940
|
|
},
|
|
{
|
|
"entropy": 6.31306824684143,
|
|
"epoch": 0.15133242559813265,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999391556755172,
|
|
"loss": 6.1417,
|
|
"mean_token_accuracy": 0.13246554136276245,
|
|
"num_tokens": 3373483.0,
|
|
"step": 1945
|
|
},
|
|
{
|
|
"entropy": 6.326482582092285,
|
|
"epoch": 0.15172145496985023,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999385094606872,
|
|
"loss": 6.1331,
|
|
"mean_token_accuracy": 0.1271201863884926,
|
|
"num_tokens": 3382557.0,
|
|
"step": 1950
|
|
},
|
|
{
|
|
"entropy": 6.310076713562012,
|
|
"epoch": 0.1521104843415678,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999378598327733,
|
|
"loss": 6.081,
|
|
"mean_token_accuracy": 0.12705598026514053,
|
|
"num_tokens": 3392079.0,
|
|
"step": 1955
|
|
},
|
|
{
|
|
"entropy": 6.259531545639038,
|
|
"epoch": 0.15249951371328535,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999372067917854,
|
|
"loss": 6.1412,
|
|
"mean_token_accuracy": 0.12986933141946794,
|
|
"num_tokens": 3401070.0,
|
|
"step": 1960
|
|
},
|
|
{
|
|
"entropy": 6.24435453414917,
|
|
"epoch": 0.1528885430850029,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999365503377335,
|
|
"loss": 6.0231,
|
|
"mean_token_accuracy": 0.13275498896837234,
|
|
"num_tokens": 3409921.0,
|
|
"step": 1965
|
|
},
|
|
{
|
|
"entropy": 6.3059319972991945,
|
|
"epoch": 0.1532775724567205,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999358904706273,
|
|
"loss": 6.0424,
|
|
"mean_token_accuracy": 0.13057347238063813,
|
|
"num_tokens": 3419149.0,
|
|
"step": 1970
|
|
},
|
|
{
|
|
"entropy": 6.208243465423584,
|
|
"epoch": 0.15366660182843805,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999352271904771,
|
|
"loss": 5.9333,
|
|
"mean_token_accuracy": 0.14223069027066232,
|
|
"num_tokens": 3427435.0,
|
|
"step": 1975
|
|
},
|
|
{
|
|
"entropy": 6.283069849014282,
|
|
"epoch": 0.1540556312001556,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999345604972928,
|
|
"loss": 6.1375,
|
|
"mean_token_accuracy": 0.1275772549211979,
|
|
"num_tokens": 3436377.0,
|
|
"step": 1980
|
|
},
|
|
{
|
|
"entropy": 6.239132833480835,
|
|
"epoch": 0.15444466057187317,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999338903910846,
|
|
"loss": 6.0122,
|
|
"mean_token_accuracy": 0.13495821878314018,
|
|
"num_tokens": 3444997.0,
|
|
"step": 1985
|
|
},
|
|
{
|
|
"entropy": 6.343378400802612,
|
|
"epoch": 0.15483368994359073,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999332168718626,
|
|
"loss": 6.0894,
|
|
"mean_token_accuracy": 0.1357529453933239,
|
|
"num_tokens": 3454254.0,
|
|
"step": 1990
|
|
},
|
|
{
|
|
"entropy": 6.249056434631347,
|
|
"epoch": 0.15522271931530832,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999325399396371,
|
|
"loss": 6.0377,
|
|
"mean_token_accuracy": 0.1396930918097496,
|
|
"num_tokens": 3462853.0,
|
|
"step": 1995
|
|
},
|
|
{
|
|
"entropy": 6.227156352996826,
|
|
"epoch": 0.15561174868702587,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999318595944183,
|
|
"loss": 5.9889,
|
|
"mean_token_accuracy": 0.13459807708859445,
|
|
"num_tokens": 3471288.0,
|
|
"step": 2000
|
|
},
|
|
{
|
|
"entropy": 6.149478435516357,
|
|
"epoch": 0.15600077805874343,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999311758362166,
|
|
"loss": 5.8852,
|
|
"mean_token_accuracy": 0.13669946119189264,
|
|
"num_tokens": 3479479.0,
|
|
"step": 2005
|
|
},
|
|
{
|
|
"entropy": 6.195598793029785,
|
|
"epoch": 0.156389807430461,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999304886650422,
|
|
"loss": 5.9151,
|
|
"mean_token_accuracy": 0.1384771704673767,
|
|
"num_tokens": 3488621.0,
|
|
"step": 2010
|
|
},
|
|
{
|
|
"entropy": 6.179077291488648,
|
|
"epoch": 0.15677883680217858,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999297980809058,
|
|
"loss": 5.9768,
|
|
"mean_token_accuracy": 0.1390062913298607,
|
|
"num_tokens": 3497792.0,
|
|
"step": 2015
|
|
},
|
|
{
|
|
"entropy": 6.147572040557861,
|
|
"epoch": 0.15716786617389614,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999291040838176,
|
|
"loss": 5.9844,
|
|
"mean_token_accuracy": 0.13780189007520677,
|
|
"num_tokens": 3506548.0,
|
|
"step": 2020
|
|
},
|
|
{
|
|
"entropy": 6.185660696029663,
|
|
"epoch": 0.1575568955456137,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999284066737884,
|
|
"loss": 5.973,
|
|
"mean_token_accuracy": 0.14213240072131156,
|
|
"num_tokens": 3515086.0,
|
|
"step": 2025
|
|
},
|
|
{
|
|
"entropy": 6.301659440994262,
|
|
"epoch": 0.15794592491733125,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999277058508285,
|
|
"loss": 6.0185,
|
|
"mean_token_accuracy": 0.13498132154345513,
|
|
"num_tokens": 3523985.0,
|
|
"step": 2030
|
|
},
|
|
{
|
|
"entropy": 6.245706176757812,
|
|
"epoch": 0.1583349542890488,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999270016149486,
|
|
"loss": 6.0751,
|
|
"mean_token_accuracy": 0.13686039298772812,
|
|
"num_tokens": 3532575.0,
|
|
"step": 2035
|
|
},
|
|
{
|
|
"entropy": 6.304662990570068,
|
|
"epoch": 0.1587239836607664,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999262939661596,
|
|
"loss": 6.0697,
|
|
"mean_token_accuracy": 0.13059490993618966,
|
|
"num_tokens": 3541558.0,
|
|
"step": 2040
|
|
},
|
|
{
|
|
"entropy": 6.182402086257935,
|
|
"epoch": 0.15911301303248396,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999255829044721,
|
|
"loss": 5.9798,
|
|
"mean_token_accuracy": 0.13890642076730728,
|
|
"num_tokens": 3549697.0,
|
|
"step": 2045
|
|
},
|
|
{
|
|
"entropy": 6.313886213302612,
|
|
"epoch": 0.15950204240420152,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999248684298968,
|
|
"loss": 6.1551,
|
|
"mean_token_accuracy": 0.12896221354603768,
|
|
"num_tokens": 3558673.0,
|
|
"step": 2050
|
|
},
|
|
{
|
|
"entropy": 6.274616432189942,
|
|
"epoch": 0.15989107177591907,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999241505424447,
|
|
"loss": 6.0047,
|
|
"mean_token_accuracy": 0.13846511095762254,
|
|
"num_tokens": 3567176.0,
|
|
"step": 2055
|
|
},
|
|
{
|
|
"entropy": 6.335512018203735,
|
|
"epoch": 0.16028010114763663,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999234292421265,
|
|
"loss": 6.1437,
|
|
"mean_token_accuracy": 0.13223661482334137,
|
|
"num_tokens": 3576020.0,
|
|
"step": 2060
|
|
},
|
|
{
|
|
"entropy": 6.19822096824646,
|
|
"epoch": 0.16066913051935422,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999227045289535,
|
|
"loss": 5.9723,
|
|
"mean_token_accuracy": 0.13607832789421082,
|
|
"num_tokens": 3584705.0,
|
|
"step": 2065
|
|
},
|
|
{
|
|
"entropy": 6.279978084564209,
|
|
"epoch": 0.16105815989107178,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999219764029363,
|
|
"loss": 6.1605,
|
|
"mean_token_accuracy": 0.1307303138077259,
|
|
"num_tokens": 3593339.0,
|
|
"step": 2070
|
|
},
|
|
{
|
|
"entropy": 6.261270904541016,
|
|
"epoch": 0.16144718926278934,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999212448640861,
|
|
"loss": 5.8723,
|
|
"mean_token_accuracy": 0.14517469108104705,
|
|
"num_tokens": 3601206.0,
|
|
"step": 2075
|
|
},
|
|
{
|
|
"entropy": 6.079396677017212,
|
|
"epoch": 0.1618362186345069,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999205099124141,
|
|
"loss": 5.9946,
|
|
"mean_token_accuracy": 0.13344853073358537,
|
|
"num_tokens": 3610371.0,
|
|
"step": 2080
|
|
},
|
|
{
|
|
"entropy": 6.325978946685791,
|
|
"epoch": 0.16222524800622448,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999197715479313,
|
|
"loss": 6.0037,
|
|
"mean_token_accuracy": 0.1363994300365448,
|
|
"num_tokens": 3618834.0,
|
|
"step": 2085
|
|
},
|
|
{
|
|
"entropy": 6.110661888122559,
|
|
"epoch": 0.16261427737794204,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999190297706489,
|
|
"loss": 6.041,
|
|
"mean_token_accuracy": 0.138499366492033,
|
|
"num_tokens": 3627426.0,
|
|
"step": 2090
|
|
},
|
|
{
|
|
"entropy": 6.259611415863037,
|
|
"epoch": 0.1630033067496596,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999182845805783,
|
|
"loss": 6.0427,
|
|
"mean_token_accuracy": 0.13478516712784766,
|
|
"num_tokens": 3636020.0,
|
|
"step": 2095
|
|
},
|
|
{
|
|
"entropy": 6.348205089569092,
|
|
"epoch": 0.16339233612137716,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999175359777306,
|
|
"loss": 5.9891,
|
|
"mean_token_accuracy": 0.1379244014620781,
|
|
"num_tokens": 3644419.0,
|
|
"step": 2100
|
|
},
|
|
{
|
|
"entropy": 6.189280939102173,
|
|
"epoch": 0.16378136549309472,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999167839621174,
|
|
"loss": 6.0854,
|
|
"mean_token_accuracy": 0.12851483151316642,
|
|
"num_tokens": 3653223.0,
|
|
"step": 2105
|
|
},
|
|
{
|
|
"entropy": 6.301689481735229,
|
|
"epoch": 0.1641703948648123,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999160285337501,
|
|
"loss": 6.1,
|
|
"mean_token_accuracy": 0.1289041444659233,
|
|
"num_tokens": 3662409.0,
|
|
"step": 2110
|
|
},
|
|
{
|
|
"entropy": 6.2754106521606445,
|
|
"epoch": 0.16455942423652986,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004999152696926399,
|
|
"loss": 6.0583,
|
|
"mean_token_accuracy": 0.13341646790504455,
|
|
"num_tokens": 3670635.0,
|
|
"step": 2115
|
|
},
|
|
{
|
|
"entropy": 6.122903490066529,
|
|
"epoch": 0.16494845360824742,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999145074387985,
|
|
"loss": 5.9886,
|
|
"mean_token_accuracy": 0.14272082224488258,
|
|
"num_tokens": 3679303.0,
|
|
"step": 2120
|
|
},
|
|
{
|
|
"entropy": 6.311637830734253,
|
|
"epoch": 0.16533748297996498,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999137417722374,
|
|
"loss": 6.1483,
|
|
"mean_token_accuracy": 0.13292766511440277,
|
|
"num_tokens": 3689299.0,
|
|
"step": 2125
|
|
},
|
|
{
|
|
"entropy": 6.2762187957763675,
|
|
"epoch": 0.16572651235168256,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999129726929684,
|
|
"loss": 6.0652,
|
|
"mean_token_accuracy": 0.13817578107118605,
|
|
"num_tokens": 3697843.0,
|
|
"step": 2130
|
|
},
|
|
{
|
|
"entropy": 6.290596771240234,
|
|
"epoch": 0.16611554172340012,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999122002010029,
|
|
"loss": 5.9937,
|
|
"mean_token_accuracy": 0.1410035215318203,
|
|
"num_tokens": 3705876.0,
|
|
"step": 2135
|
|
},
|
|
{
|
|
"entropy": 6.264617252349853,
|
|
"epoch": 0.16650457109511768,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999114242963527,
|
|
"loss": 6.1131,
|
|
"mean_token_accuracy": 0.12808321714401244,
|
|
"num_tokens": 3714835.0,
|
|
"step": 2140
|
|
},
|
|
{
|
|
"entropy": 6.201760530471802,
|
|
"epoch": 0.16689360046683524,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999106449790298,
|
|
"loss": 5.9684,
|
|
"mean_token_accuracy": 0.13607337027788163,
|
|
"num_tokens": 3723421.0,
|
|
"step": 2145
|
|
},
|
|
{
|
|
"entropy": 6.197750616073608,
|
|
"epoch": 0.1672826298385528,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999098622490458,
|
|
"loss": 5.999,
|
|
"mean_token_accuracy": 0.13562173172831535,
|
|
"num_tokens": 3731590.0,
|
|
"step": 2150
|
|
},
|
|
{
|
|
"entropy": 6.155825185775757,
|
|
"epoch": 0.16767165921027039,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999090761064125,
|
|
"loss": 5.9245,
|
|
"mean_token_accuracy": 0.13581221401691437,
|
|
"num_tokens": 3740700.0,
|
|
"step": 2155
|
|
},
|
|
{
|
|
"entropy": 6.188067531585693,
|
|
"epoch": 0.16806068858198794,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000499908286551142,
|
|
"loss": 5.9976,
|
|
"mean_token_accuracy": 0.14268267750740052,
|
|
"num_tokens": 3749516.0,
|
|
"step": 2160
|
|
},
|
|
{
|
|
"entropy": 6.181734943389893,
|
|
"epoch": 0.1684497179537055,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999074935832463,
|
|
"loss": 5.9116,
|
|
"mean_token_accuracy": 0.1446475252509117,
|
|
"num_tokens": 3757696.0,
|
|
"step": 2165
|
|
},
|
|
{
|
|
"entropy": 6.187936496734619,
|
|
"epoch": 0.16883874732542306,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999066972027373,
|
|
"loss": 6.0052,
|
|
"mean_token_accuracy": 0.13505456671118737,
|
|
"num_tokens": 3765786.0,
|
|
"step": 2170
|
|
},
|
|
{
|
|
"entropy": 6.182317399978638,
|
|
"epoch": 0.16922777669714065,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999058974096271,
|
|
"loss": 5.9076,
|
|
"mean_token_accuracy": 0.14293930530548096,
|
|
"num_tokens": 3773265.0,
|
|
"step": 2175
|
|
},
|
|
{
|
|
"entropy": 6.148977756500244,
|
|
"epoch": 0.1696168060688582,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000499905094203928,
|
|
"loss": 6.029,
|
|
"mean_token_accuracy": 0.13410733118653298,
|
|
"num_tokens": 3782402.0,
|
|
"step": 2180
|
|
},
|
|
{
|
|
"entropy": 6.245903635025025,
|
|
"epoch": 0.17000583544057576,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000499904287585652,
|
|
"loss": 6.0971,
|
|
"mean_token_accuracy": 0.12724517583847045,
|
|
"num_tokens": 3791901.0,
|
|
"step": 2185
|
|
},
|
|
{
|
|
"entropy": 6.184202718734741,
|
|
"epoch": 0.17039486481229332,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999034775548113,
|
|
"loss": 5.9206,
|
|
"mean_token_accuracy": 0.14507496878504753,
|
|
"num_tokens": 3799872.0,
|
|
"step": 2190
|
|
},
|
|
{
|
|
"entropy": 6.159626245498657,
|
|
"epoch": 0.17078389418401088,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999026641114185,
|
|
"loss": 5.858,
|
|
"mean_token_accuracy": 0.14604728296399117,
|
|
"num_tokens": 3808949.0,
|
|
"step": 2195
|
|
},
|
|
{
|
|
"entropy": 6.170258522033691,
|
|
"epoch": 0.17117292355572847,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999018472554857,
|
|
"loss": 5.9815,
|
|
"mean_token_accuracy": 0.13522427454590796,
|
|
"num_tokens": 3817429.0,
|
|
"step": 2200
|
|
},
|
|
{
|
|
"entropy": 6.33716516494751,
|
|
"epoch": 0.17156195292744603,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999010269870253,
|
|
"loss": 6.2642,
|
|
"mean_token_accuracy": 0.12795186191797256,
|
|
"num_tokens": 3827101.0,
|
|
"step": 2205
|
|
},
|
|
{
|
|
"entropy": 6.283813047409057,
|
|
"epoch": 0.17195098229916359,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004999002033060498,
|
|
"loss": 6.0133,
|
|
"mean_token_accuracy": 0.1351143278181553,
|
|
"num_tokens": 3836147.0,
|
|
"step": 2210
|
|
},
|
|
{
|
|
"entropy": 6.136712694168091,
|
|
"epoch": 0.17234001167088114,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998993762125716,
|
|
"loss": 6.0013,
|
|
"mean_token_accuracy": 0.1369711324572563,
|
|
"num_tokens": 3845300.0,
|
|
"step": 2215
|
|
},
|
|
{
|
|
"entropy": 6.282448244094849,
|
|
"epoch": 0.17272904104259873,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004998985457066034,
|
|
"loss": 5.9966,
|
|
"mean_token_accuracy": 0.1379320077598095,
|
|
"num_tokens": 3853620.0,
|
|
"step": 2220
|
|
},
|
|
{
|
|
"entropy": 6.123518180847168,
|
|
"epoch": 0.1731180704143163,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998977117881576,
|
|
"loss": 5.9928,
|
|
"mean_token_accuracy": 0.1383661672472954,
|
|
"num_tokens": 3861734.0,
|
|
"step": 2225
|
|
},
|
|
{
|
|
"entropy": 6.208690977096557,
|
|
"epoch": 0.17350709978603385,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998968744572472,
|
|
"loss": 6.0124,
|
|
"mean_token_accuracy": 0.13703416362404824,
|
|
"num_tokens": 3870753.0,
|
|
"step": 2230
|
|
},
|
|
{
|
|
"entropy": 6.165704917907715,
|
|
"epoch": 0.1738961291577514,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998960337138845,
|
|
"loss": 5.8932,
|
|
"mean_token_accuracy": 0.14122473895549775,
|
|
"num_tokens": 3879382.0,
|
|
"step": 2235
|
|
},
|
|
{
|
|
"entropy": 6.184034299850464,
|
|
"epoch": 0.17428515852946896,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998951895580826,
|
|
"loss": 6.065,
|
|
"mean_token_accuracy": 0.1349945433437824,
|
|
"num_tokens": 3888417.0,
|
|
"step": 2240
|
|
},
|
|
{
|
|
"entropy": 6.127526903152466,
|
|
"epoch": 0.17467418790118655,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998943419898542,
|
|
"loss": 5.9209,
|
|
"mean_token_accuracy": 0.13626997768878937,
|
|
"num_tokens": 3897083.0,
|
|
"step": 2245
|
|
},
|
|
{
|
|
"entropy": 6.1350280284881595,
|
|
"epoch": 0.1750632172729041,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998934910092119,
|
|
"loss": 5.8862,
|
|
"mean_token_accuracy": 0.1451417922973633,
|
|
"num_tokens": 3905564.0,
|
|
"step": 2250
|
|
},
|
|
{
|
|
"entropy": 6.2061069965362545,
|
|
"epoch": 0.17545224664462167,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998926366161689,
|
|
"loss": 6.0361,
|
|
"mean_token_accuracy": 0.1296758010983467,
|
|
"num_tokens": 3914896.0,
|
|
"step": 2255
|
|
},
|
|
{
|
|
"entropy": 6.1870911598205565,
|
|
"epoch": 0.17584127601633923,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004998917788107383,
|
|
"loss": 6.0419,
|
|
"mean_token_accuracy": 0.14005873054265977,
|
|
"num_tokens": 3924151.0,
|
|
"step": 2260
|
|
},
|
|
{
|
|
"entropy": 6.233715152740478,
|
|
"epoch": 0.17623030538805678,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004998909175929326,
|
|
"loss": 5.9814,
|
|
"mean_token_accuracy": 0.14144271165132521,
|
|
"num_tokens": 3933163.0,
|
|
"step": 2265
|
|
},
|
|
{
|
|
"entropy": 6.163707447052002,
|
|
"epoch": 0.17661933475977437,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004998900529627653,
|
|
"loss": 5.9032,
|
|
"mean_token_accuracy": 0.1486126258969307,
|
|
"num_tokens": 3941120.0,
|
|
"step": 2270
|
|
},
|
|
{
|
|
"entropy": 6.058203554153442,
|
|
"epoch": 0.17700836413149193,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998891849202495,
|
|
"loss": 5.7958,
|
|
"mean_token_accuracy": 0.14378746151924132,
|
|
"num_tokens": 3949896.0,
|
|
"step": 2275
|
|
},
|
|
{
|
|
"entropy": 6.195409440994263,
|
|
"epoch": 0.1773973935032095,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000499888313465398,
|
|
"loss": 5.951,
|
|
"mean_token_accuracy": 0.13810205608606338,
|
|
"num_tokens": 3958794.0,
|
|
"step": 2280
|
|
},
|
|
{
|
|
"entropy": 6.186099672317505,
|
|
"epoch": 0.17778642287492705,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998874385982247,
|
|
"loss": 6.0078,
|
|
"mean_token_accuracy": 0.13773410096764566,
|
|
"num_tokens": 3967267.0,
|
|
"step": 2285
|
|
},
|
|
{
|
|
"entropy": 6.139815187454223,
|
|
"epoch": 0.17817545224664463,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004998865603187421,
|
|
"loss": 5.9249,
|
|
"mean_token_accuracy": 0.13793863877654075,
|
|
"num_tokens": 3976536.0,
|
|
"step": 2290
|
|
},
|
|
{
|
|
"entropy": 6.24169807434082,
|
|
"epoch": 0.1785644816183622,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000499885678626964,
|
|
"loss": 5.9947,
|
|
"mean_token_accuracy": 0.1388470858335495,
|
|
"num_tokens": 3986006.0,
|
|
"step": 2295
|
|
},
|
|
{
|
|
"entropy": 6.077307844161988,
|
|
"epoch": 0.17895351099007975,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998847935229038,
|
|
"loss": 5.9394,
|
|
"mean_token_accuracy": 0.1349871888756752,
|
|
"num_tokens": 3994478.0,
|
|
"step": 2300
|
|
},
|
|
{
|
|
"entropy": 6.16282639503479,
|
|
"epoch": 0.1793425403617973,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004998839050065746,
|
|
"loss": 5.9792,
|
|
"mean_token_accuracy": 0.13701414689421654,
|
|
"num_tokens": 4003190.0,
|
|
"step": 2305
|
|
},
|
|
{
|
|
"entropy": 6.2592230319976805,
|
|
"epoch": 0.17973156973351487,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004998830130779902,
|
|
"loss": 5.9066,
|
|
"mean_token_accuracy": 0.13989242389798165,
|
|
"num_tokens": 4011886.0,
|
|
"step": 2310
|
|
},
|
|
{
|
|
"entropy": 6.044191455841064,
|
|
"epoch": 0.18012059910523245,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000499882117737164,
|
|
"loss": 5.8027,
|
|
"mean_token_accuracy": 0.14078635722398758,
|
|
"num_tokens": 4020792.0,
|
|
"step": 2315
|
|
},
|
|
{
|
|
"entropy": 6.006427335739136,
|
|
"epoch": 0.18050962847695,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998812189841096,
|
|
"loss": 5.7981,
|
|
"mean_token_accuracy": 0.1413320556282997,
|
|
"num_tokens": 4029235.0,
|
|
"step": 2320
|
|
},
|
|
{
|
|
"entropy": 6.115646028518677,
|
|
"epoch": 0.18089865784866757,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004998803168188407,
|
|
"loss": 6.0277,
|
|
"mean_token_accuracy": 0.14016879796981813,
|
|
"num_tokens": 4037341.0,
|
|
"step": 2325
|
|
},
|
|
{
|
|
"entropy": 6.140260648727417,
|
|
"epoch": 0.18128768722038513,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004998794112413708,
|
|
"loss": 5.9019,
|
|
"mean_token_accuracy": 0.13752360120415688,
|
|
"num_tokens": 4046324.0,
|
|
"step": 2330
|
|
},
|
|
{
|
|
"entropy": 6.080597591400147,
|
|
"epoch": 0.18167671659210272,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998785022517137,
|
|
"loss": 5.9663,
|
|
"mean_token_accuracy": 0.1393540196120739,
|
|
"num_tokens": 4054579.0,
|
|
"step": 2335
|
|
},
|
|
{
|
|
"entropy": 6.197992992401123,
|
|
"epoch": 0.18206574596382027,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004998775898498835,
|
|
"loss": 5.924,
|
|
"mean_token_accuracy": 0.13897303566336633,
|
|
"num_tokens": 4063087.0,
|
|
"step": 2340
|
|
},
|
|
{
|
|
"entropy": 6.189882612228393,
|
|
"epoch": 0.18245477533553783,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998766740358936,
|
|
"loss": 5.9942,
|
|
"mean_token_accuracy": 0.13766855299472808,
|
|
"num_tokens": 4072309.0,
|
|
"step": 2345
|
|
},
|
|
{
|
|
"entropy": 6.12577452659607,
|
|
"epoch": 0.1828438047072554,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004998757548097582,
|
|
"loss": 6.045,
|
|
"mean_token_accuracy": 0.1355599895119667,
|
|
"num_tokens": 4081017.0,
|
|
"step": 2350
|
|
},
|
|
{
|
|
"entropy": 6.221224927902222,
|
|
"epoch": 0.18323283407897295,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004998748321714911,
|
|
"loss": 6.0571,
|
|
"mean_token_accuracy": 0.13211404532194138,
|
|
"num_tokens": 4089799.0,
|
|
"step": 2355
|
|
},
|
|
{
|
|
"entropy": 6.166183710098267,
|
|
"epoch": 0.18362186345069054,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004998739061211065,
|
|
"loss": 5.9713,
|
|
"mean_token_accuracy": 0.14161632731556892,
|
|
"num_tokens": 4097948.0,
|
|
"step": 2360
|
|
},
|
|
{
|
|
"entropy": 6.114394664764404,
|
|
"epoch": 0.1840108928224081,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998729766586181,
|
|
"loss": 5.8536,
|
|
"mean_token_accuracy": 0.14067127406597138,
|
|
"num_tokens": 4107050.0,
|
|
"step": 2365
|
|
},
|
|
{
|
|
"entropy": 6.107758188247681,
|
|
"epoch": 0.18439992219412565,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004998720437840403,
|
|
"loss": 5.8672,
|
|
"mean_token_accuracy": 0.13855508863925933,
|
|
"num_tokens": 4115547.0,
|
|
"step": 2370
|
|
},
|
|
{
|
|
"entropy": 6.124674224853516,
|
|
"epoch": 0.1847889515658432,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998711074973871,
|
|
"loss": 5.8706,
|
|
"mean_token_accuracy": 0.14566295892000197,
|
|
"num_tokens": 4124047.0,
|
|
"step": 2375
|
|
},
|
|
{
|
|
"entropy": 6.017377805709839,
|
|
"epoch": 0.1851779809375608,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004998701677986728,
|
|
"loss": 5.8272,
|
|
"mean_token_accuracy": 0.14891343787312508,
|
|
"num_tokens": 4132005.0,
|
|
"step": 2380
|
|
},
|
|
{
|
|
"entropy": 6.186097240447998,
|
|
"epoch": 0.18556701030927836,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998692246879116,
|
|
"loss": 6.0144,
|
|
"mean_token_accuracy": 0.13196168541908265,
|
|
"num_tokens": 4140199.0,
|
|
"step": 2385
|
|
},
|
|
{
|
|
"entropy": 6.144238615036011,
|
|
"epoch": 0.18595603968099592,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998682781651178,
|
|
"loss": 5.9401,
|
|
"mean_token_accuracy": 0.14200834929943085,
|
|
"num_tokens": 4149353.0,
|
|
"step": 2390
|
|
},
|
|
{
|
|
"entropy": 6.03447151184082,
|
|
"epoch": 0.18634506905271347,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998673282303059,
|
|
"loss": 5.9088,
|
|
"mean_token_accuracy": 0.14188055396080018,
|
|
"num_tokens": 4158531.0,
|
|
"step": 2395
|
|
},
|
|
{
|
|
"entropy": 6.000899457931519,
|
|
"epoch": 0.18673409842443103,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004998663748834901,
|
|
"loss": 5.7074,
|
|
"mean_token_accuracy": 0.15226681232452394,
|
|
"num_tokens": 4166743.0,
|
|
"step": 2400
|
|
},
|
|
{
|
|
"entropy": 6.190967559814453,
|
|
"epoch": 0.18712312779614862,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004998654181246851,
|
|
"loss": 6.057,
|
|
"mean_token_accuracy": 0.13685035333037376,
|
|
"num_tokens": 4175416.0,
|
|
"step": 2405
|
|
},
|
|
{
|
|
"entropy": 6.181151866912842,
|
|
"epoch": 0.18751215716786618,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998644579539052,
|
|
"loss": 5.9812,
|
|
"mean_token_accuracy": 0.13951558768749237,
|
|
"num_tokens": 4185324.0,
|
|
"step": 2410
|
|
},
|
|
{
|
|
"entropy": 6.096161127090454,
|
|
"epoch": 0.18790118653958374,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000499863494371165,
|
|
"loss": 5.9178,
|
|
"mean_token_accuracy": 0.1447077937424183,
|
|
"num_tokens": 4193361.0,
|
|
"step": 2415
|
|
},
|
|
{
|
|
"entropy": 6.187608957290649,
|
|
"epoch": 0.1882902159113013,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004998625273764793,
|
|
"loss": 5.9679,
|
|
"mean_token_accuracy": 0.13389892131090164,
|
|
"num_tokens": 4202553.0,
|
|
"step": 2420
|
|
},
|
|
{
|
|
"entropy": 6.0965659618377686,
|
|
"epoch": 0.18867924528301888,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004998615569698626,
|
|
"loss": 5.9039,
|
|
"mean_token_accuracy": 0.14300661832094191,
|
|
"num_tokens": 4211585.0,
|
|
"step": 2425
|
|
},
|
|
{
|
|
"entropy": 6.0760973453521725,
|
|
"epoch": 0.18906827465473644,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998605831513296,
|
|
"loss": 5.9462,
|
|
"mean_token_accuracy": 0.13661156445741654,
|
|
"num_tokens": 4220829.0,
|
|
"step": 2430
|
|
},
|
|
{
|
|
"entropy": 6.0929618835449215,
|
|
"epoch": 0.189457304026454,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998596059208953,
|
|
"loss": 5.8543,
|
|
"mean_token_accuracy": 0.14136664643883706,
|
|
"num_tokens": 4228658.0,
|
|
"step": 2435
|
|
},
|
|
{
|
|
"entropy": 6.181618976593017,
|
|
"epoch": 0.18984633339817156,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004998586252785743,
|
|
"loss": 5.9419,
|
|
"mean_token_accuracy": 0.14073347449302673,
|
|
"num_tokens": 4237650.0,
|
|
"step": 2440
|
|
},
|
|
{
|
|
"entropy": 6.056187391281128,
|
|
"epoch": 0.19023536276988912,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998576412243816,
|
|
"loss": 5.9193,
|
|
"mean_token_accuracy": 0.1453680008649826,
|
|
"num_tokens": 4246701.0,
|
|
"step": 2445
|
|
},
|
|
{
|
|
"entropy": 6.117009496688842,
|
|
"epoch": 0.1906243921416067,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004998566537583321,
|
|
"loss": 5.8866,
|
|
"mean_token_accuracy": 0.14391229003667833,
|
|
"num_tokens": 4254541.0,
|
|
"step": 2450
|
|
},
|
|
{
|
|
"entropy": 6.13186469078064,
|
|
"epoch": 0.19101342151332426,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998556628804408,
|
|
"loss": 5.9241,
|
|
"mean_token_accuracy": 0.13888985589146613,
|
|
"num_tokens": 4263111.0,
|
|
"step": 2455
|
|
},
|
|
{
|
|
"entropy": 6.085035181045532,
|
|
"epoch": 0.19140245088504182,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004998546685907225,
|
|
"loss": 5.9222,
|
|
"mean_token_accuracy": 0.1431556224822998,
|
|
"num_tokens": 4272796.0,
|
|
"step": 2460
|
|
},
|
|
{
|
|
"entropy": 6.06772747039795,
|
|
"epoch": 0.19179148025675938,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998536708891927,
|
|
"loss": 5.853,
|
|
"mean_token_accuracy": 0.1444825768470764,
|
|
"num_tokens": 4281361.0,
|
|
"step": 2465
|
|
},
|
|
{
|
|
"entropy": 6.134342861175537,
|
|
"epoch": 0.19218050962847694,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998526697758663,
|
|
"loss": 5.909,
|
|
"mean_token_accuracy": 0.13936054483056068,
|
|
"num_tokens": 4290470.0,
|
|
"step": 2470
|
|
},
|
|
{
|
|
"entropy": 6.100904512405395,
|
|
"epoch": 0.19256953900019452,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998516652507585,
|
|
"loss": 5.9476,
|
|
"mean_token_accuracy": 0.1369578666985035,
|
|
"num_tokens": 4299087.0,
|
|
"step": 2475
|
|
},
|
|
{
|
|
"entropy": 6.05439133644104,
|
|
"epoch": 0.19295856837191208,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998506573138846,
|
|
"loss": 5.8166,
|
|
"mean_token_accuracy": 0.1480974078178406,
|
|
"num_tokens": 4307572.0,
|
|
"step": 2480
|
|
},
|
|
{
|
|
"entropy": 6.066846036911011,
|
|
"epoch": 0.19334759774362964,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998496459652598,
|
|
"loss": 5.9009,
|
|
"mean_token_accuracy": 0.14306523129343987,
|
|
"num_tokens": 4316337.0,
|
|
"step": 2485
|
|
},
|
|
{
|
|
"entropy": 6.15980863571167,
|
|
"epoch": 0.1937366271153472,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004998486312048995,
|
|
"loss": 5.9834,
|
|
"mean_token_accuracy": 0.14186982065439224,
|
|
"num_tokens": 4326258.0,
|
|
"step": 2490
|
|
},
|
|
{
|
|
"entropy": 6.080019283294678,
|
|
"epoch": 0.19412565648706478,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998476130328193,
|
|
"loss": 5.842,
|
|
"mean_token_accuracy": 0.14730110839009286,
|
|
"num_tokens": 4334711.0,
|
|
"step": 2495
|
|
},
|
|
{
|
|
"entropy": 6.140625524520874,
|
|
"epoch": 0.19451468585878234,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004998465914490343,
|
|
"loss": 5.9334,
|
|
"mean_token_accuracy": 0.13907926082611083,
|
|
"num_tokens": 4343739.0,
|
|
"step": 2500
|
|
},
|
|
{
|
|
"entropy": 6.078987503051758,
|
|
"epoch": 0.1949037152304999,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00049984556645356,
|
|
"loss": 5.8735,
|
|
"mean_token_accuracy": 0.14407971054315566,
|
|
"num_tokens": 4352905.0,
|
|
"step": 2505
|
|
},
|
|
{
|
|
"entropy": 6.112984275817871,
|
|
"epoch": 0.19529274460221746,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998445380464124,
|
|
"loss": 5.8965,
|
|
"mean_token_accuracy": 0.14865672141313552,
|
|
"num_tokens": 4361333.0,
|
|
"step": 2510
|
|
},
|
|
{
|
|
"entropy": 6.0111664772033695,
|
|
"epoch": 0.19568177397393502,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004998435062276066,
|
|
"loss": 5.8578,
|
|
"mean_token_accuracy": 0.14098201543092728,
|
|
"num_tokens": 4369872.0,
|
|
"step": 2515
|
|
},
|
|
{
|
|
"entropy": 6.126198101043701,
|
|
"epoch": 0.1960708033456526,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998424709971586,
|
|
"loss": 5.9367,
|
|
"mean_token_accuracy": 0.14096542671322823,
|
|
"num_tokens": 4378097.0,
|
|
"step": 2520
|
|
},
|
|
{
|
|
"entropy": 6.071844673156738,
|
|
"epoch": 0.19645983271737016,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998414323550839,
|
|
"loss": 5.856,
|
|
"mean_token_accuracy": 0.14555131644010544,
|
|
"num_tokens": 4387414.0,
|
|
"step": 2525
|
|
},
|
|
{
|
|
"entropy": 6.103514766693115,
|
|
"epoch": 0.19684886208908772,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004998403903013984,
|
|
"loss": 5.9399,
|
|
"mean_token_accuracy": 0.14774652421474457,
|
|
"num_tokens": 4395922.0,
|
|
"step": 2530
|
|
},
|
|
{
|
|
"entropy": 6.063558340072632,
|
|
"epoch": 0.19723789146080528,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998393448361179,
|
|
"loss": 5.9156,
|
|
"mean_token_accuracy": 0.138917675614357,
|
|
"num_tokens": 4404500.0,
|
|
"step": 2535
|
|
},
|
|
{
|
|
"entropy": 5.985238027572632,
|
|
"epoch": 0.19762692083252287,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000499838295959258,
|
|
"loss": 5.9028,
|
|
"mean_token_accuracy": 0.1411334067583084,
|
|
"num_tokens": 4413433.0,
|
|
"step": 2540
|
|
},
|
|
{
|
|
"entropy": 6.1477453231811525,
|
|
"epoch": 0.19801595020424043,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000499837243670835,
|
|
"loss": 5.928,
|
|
"mean_token_accuracy": 0.14450406208634375,
|
|
"num_tokens": 4421789.0,
|
|
"step": 2545
|
|
},
|
|
{
|
|
"entropy": 6.044068193435669,
|
|
"epoch": 0.19840497957595798,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998361879708646,
|
|
"loss": 5.7949,
|
|
"mean_token_accuracy": 0.15504934936761855,
|
|
"num_tokens": 4430256.0,
|
|
"step": 2550
|
|
},
|
|
{
|
|
"entropy": 6.045944166183472,
|
|
"epoch": 0.19879400894767554,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000499835128859363,
|
|
"loss": 5.8457,
|
|
"mean_token_accuracy": 0.1446925073862076,
|
|
"num_tokens": 4438431.0,
|
|
"step": 2555
|
|
},
|
|
{
|
|
"entropy": 6.091934299468994,
|
|
"epoch": 0.1991830383193931,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998340663363461,
|
|
"loss": 5.9122,
|
|
"mean_token_accuracy": 0.1388619139790535,
|
|
"num_tokens": 4447150.0,
|
|
"step": 2560
|
|
},
|
|
{
|
|
"entropy": 6.038812255859375,
|
|
"epoch": 0.1995720676911107,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004998330004018301,
|
|
"loss": 5.7921,
|
|
"mean_token_accuracy": 0.14743948429822923,
|
|
"num_tokens": 4455181.0,
|
|
"step": 2565
|
|
},
|
|
{
|
|
"entropy": 6.0153632164001465,
|
|
"epoch": 0.19996109706282825,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998319310558312,
|
|
"loss": 5.8176,
|
|
"mean_token_accuracy": 0.1437955118715763,
|
|
"num_tokens": 4463361.0,
|
|
"step": 2570
|
|
},
|
|
{
|
|
"entropy": 6.06419997215271,
|
|
"epoch": 0.2003501264345458,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998308582983657,
|
|
"loss": 5.8634,
|
|
"mean_token_accuracy": 0.14697861596941947,
|
|
"num_tokens": 4471853.0,
|
|
"step": 2575
|
|
},
|
|
{
|
|
"entropy": 5.983008098602295,
|
|
"epoch": 0.20073915580626336,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004998297821294497,
|
|
"loss": 5.8164,
|
|
"mean_token_accuracy": 0.14654360562562943,
|
|
"num_tokens": 4480812.0,
|
|
"step": 2580
|
|
},
|
|
{
|
|
"entropy": 6.073977756500244,
|
|
"epoch": 0.20112818517798095,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004998287025490995,
|
|
"loss": 5.8683,
|
|
"mean_token_accuracy": 0.1451071783900261,
|
|
"num_tokens": 4489180.0,
|
|
"step": 2585
|
|
},
|
|
{
|
|
"entropy": 6.090311336517334,
|
|
"epoch": 0.2015172145496985,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998276195573317,
|
|
"loss": 5.9298,
|
|
"mean_token_accuracy": 0.14020900428295135,
|
|
"num_tokens": 4498013.0,
|
|
"step": 2590
|
|
},
|
|
{
|
|
"entropy": 6.161534404754638,
|
|
"epoch": 0.20190624392141607,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998265331541627,
|
|
"loss": 5.9647,
|
|
"mean_token_accuracy": 0.1288097895681858,
|
|
"num_tokens": 4506767.0,
|
|
"step": 2595
|
|
},
|
|
{
|
|
"entropy": 6.1162800788879395,
|
|
"epoch": 0.20229527329313363,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004998254433396088,
|
|
"loss": 5.9698,
|
|
"mean_token_accuracy": 0.14163854718208313,
|
|
"num_tokens": 4516657.0,
|
|
"step": 2600
|
|
},
|
|
{
|
|
"entropy": 5.995081090927124,
|
|
"epoch": 0.20268430266485118,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004998243501136867,
|
|
"loss": 5.8093,
|
|
"mean_token_accuracy": 0.14900346398353576,
|
|
"num_tokens": 4524980.0,
|
|
"step": 2605
|
|
},
|
|
{
|
|
"entropy": 6.035889768600464,
|
|
"epoch": 0.20307333203656877,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998232534764129,
|
|
"loss": 5.8681,
|
|
"mean_token_accuracy": 0.14729219824075698,
|
|
"num_tokens": 4533236.0,
|
|
"step": 2610
|
|
},
|
|
{
|
|
"entropy": 5.970295190811157,
|
|
"epoch": 0.20346236140828633,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998221534278041,
|
|
"loss": 5.7612,
|
|
"mean_token_accuracy": 0.1461296297609806,
|
|
"num_tokens": 4541778.0,
|
|
"step": 2615
|
|
},
|
|
{
|
|
"entropy": 6.136829423904419,
|
|
"epoch": 0.2038513907800039,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998210499678769,
|
|
"loss": 5.8873,
|
|
"mean_token_accuracy": 0.14116985723376274,
|
|
"num_tokens": 4551131.0,
|
|
"step": 2620
|
|
},
|
|
{
|
|
"entropy": 6.106343078613281,
|
|
"epoch": 0.20424042015172145,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998199430966481,
|
|
"loss": 5.8658,
|
|
"mean_token_accuracy": 0.1418320581316948,
|
|
"num_tokens": 4559530.0,
|
|
"step": 2625
|
|
},
|
|
{
|
|
"entropy": 5.890627050399781,
|
|
"epoch": 0.20462944952343903,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998188328141346,
|
|
"loss": 5.7583,
|
|
"mean_token_accuracy": 0.14722466468811035,
|
|
"num_tokens": 4567533.0,
|
|
"step": 2630
|
|
},
|
|
{
|
|
"entropy": 6.181466436386108,
|
|
"epoch": 0.2050184788951566,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004998177191203531,
|
|
"loss": 5.896,
|
|
"mean_token_accuracy": 0.13903536647558212,
|
|
"num_tokens": 4576414.0,
|
|
"step": 2635
|
|
},
|
|
{
|
|
"entropy": 6.053440952301026,
|
|
"epoch": 0.20540750826687415,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998166020153204,
|
|
"loss": 5.8382,
|
|
"mean_token_accuracy": 0.147342050075531,
|
|
"num_tokens": 4585331.0,
|
|
"step": 2640
|
|
},
|
|
{
|
|
"entropy": 6.052559661865234,
|
|
"epoch": 0.2057965376385917,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998154814990538,
|
|
"loss": 5.8647,
|
|
"mean_token_accuracy": 0.14799018651247026,
|
|
"num_tokens": 4593526.0,
|
|
"step": 2645
|
|
},
|
|
{
|
|
"entropy": 6.026284027099609,
|
|
"epoch": 0.20618556701030927,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00049981435757157,
|
|
"loss": 5.8634,
|
|
"mean_token_accuracy": 0.14488066285848616,
|
|
"num_tokens": 4602400.0,
|
|
"step": 2650
|
|
},
|
|
{
|
|
"entropy": 5.989109945297241,
|
|
"epoch": 0.20657459638202685,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004998132302328862,
|
|
"loss": 5.8003,
|
|
"mean_token_accuracy": 0.14428150430321693,
|
|
"num_tokens": 4611037.0,
|
|
"step": 2655
|
|
},
|
|
{
|
|
"entropy": 6.0565345764160154,
|
|
"epoch": 0.2069636257537444,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998120994830195,
|
|
"loss": 5.8115,
|
|
"mean_token_accuracy": 0.14851100668311118,
|
|
"num_tokens": 4619030.0,
|
|
"step": 2660
|
|
},
|
|
{
|
|
"entropy": 6.032034778594971,
|
|
"epoch": 0.20735265512546197,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000499810965321987,
|
|
"loss": 5.8228,
|
|
"mean_token_accuracy": 0.14074279814958573,
|
|
"num_tokens": 4628649.0,
|
|
"step": 2665
|
|
},
|
|
{
|
|
"entropy": 5.993114280700683,
|
|
"epoch": 0.20774168449717953,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004998098277498059,
|
|
"loss": 5.7309,
|
|
"mean_token_accuracy": 0.14714966639876365,
|
|
"num_tokens": 4636935.0,
|
|
"step": 2670
|
|
},
|
|
{
|
|
"entropy": 6.017863130569458,
|
|
"epoch": 0.2081307138688971,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004998086867664934,
|
|
"loss": 5.9197,
|
|
"mean_token_accuracy": 0.14219892248511315,
|
|
"num_tokens": 4645532.0,
|
|
"step": 2675
|
|
},
|
|
{
|
|
"entropy": 6.1221582889556885,
|
|
"epoch": 0.20851974324061467,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000499807542372067,
|
|
"loss": 5.9851,
|
|
"mean_token_accuracy": 0.13557760491967202,
|
|
"num_tokens": 4654433.0,
|
|
"step": 2680
|
|
},
|
|
{
|
|
"entropy": 6.139663934707642,
|
|
"epoch": 0.20890877261233223,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998063945665439,
|
|
"loss": 5.989,
|
|
"mean_token_accuracy": 0.13590591549873351,
|
|
"num_tokens": 4662913.0,
|
|
"step": 2685
|
|
},
|
|
{
|
|
"entropy": 6.098662042617798,
|
|
"epoch": 0.2092978019840498,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004998052433499416,
|
|
"loss": 5.9612,
|
|
"mean_token_accuracy": 0.1359117828309536,
|
|
"num_tokens": 4672270.0,
|
|
"step": 2690
|
|
},
|
|
{
|
|
"entropy": 6.16609034538269,
|
|
"epoch": 0.20968683135576735,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998040887222776,
|
|
"loss": 5.9854,
|
|
"mean_token_accuracy": 0.1398947387933731,
|
|
"num_tokens": 4681428.0,
|
|
"step": 2695
|
|
},
|
|
{
|
|
"entropy": 6.0872087478637695,
|
|
"epoch": 0.21007586072748494,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998029306835693,
|
|
"loss": 5.8204,
|
|
"mean_token_accuracy": 0.14755907729268075,
|
|
"num_tokens": 4690492.0,
|
|
"step": 2700
|
|
},
|
|
{
|
|
"entropy": 6.07254843711853,
|
|
"epoch": 0.2104648900992025,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004998017692338344,
|
|
"loss": 5.9404,
|
|
"mean_token_accuracy": 0.14041918218135835,
|
|
"num_tokens": 4699667.0,
|
|
"step": 2705
|
|
},
|
|
{
|
|
"entropy": 5.926076602935791,
|
|
"epoch": 0.21085391947092005,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998006043730905,
|
|
"loss": 5.6251,
|
|
"mean_token_accuracy": 0.1608228325843811,
|
|
"num_tokens": 4708529.0,
|
|
"step": 2710
|
|
},
|
|
{
|
|
"entropy": 5.902212381362915,
|
|
"epoch": 0.2112429488426376,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004997994361013551,
|
|
"loss": 5.8837,
|
|
"mean_token_accuracy": 0.13886216133832932,
|
|
"num_tokens": 4717684.0,
|
|
"step": 2715
|
|
},
|
|
{
|
|
"entropy": 6.049212312698364,
|
|
"epoch": 0.21163197821435517,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004997982644186461,
|
|
"loss": 5.8008,
|
|
"mean_token_accuracy": 0.14885463267564775,
|
|
"num_tokens": 4727067.0,
|
|
"step": 2720
|
|
},
|
|
{
|
|
"entropy": 6.025175905227661,
|
|
"epoch": 0.21202100758607276,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004997970893249813,
|
|
"loss": 5.7868,
|
|
"mean_token_accuracy": 0.14974473118782045,
|
|
"num_tokens": 4735434.0,
|
|
"step": 2725
|
|
},
|
|
{
|
|
"entropy": 6.024233770370484,
|
|
"epoch": 0.21241003695779032,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004997959108203785,
|
|
"loss": 5.8227,
|
|
"mean_token_accuracy": 0.14492656514048577,
|
|
"num_tokens": 4743843.0,
|
|
"step": 2730
|
|
},
|
|
{
|
|
"entropy": 6.081152391433716,
|
|
"epoch": 0.21279906632950787,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004997947289048554,
|
|
"loss": 5.8634,
|
|
"mean_token_accuracy": 0.1460092097520828,
|
|
"num_tokens": 4753228.0,
|
|
"step": 2735
|
|
},
|
|
{
|
|
"entropy": 6.036781454086304,
|
|
"epoch": 0.21318809570122543,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004997935435784302,
|
|
"loss": 5.9396,
|
|
"mean_token_accuracy": 0.1427992545068264,
|
|
"num_tokens": 4763401.0,
|
|
"step": 2740
|
|
},
|
|
{
|
|
"entropy": 6.008918571472168,
|
|
"epoch": 0.21357712507294302,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004997923548411208,
|
|
"loss": 5.8139,
|
|
"mean_token_accuracy": 0.1405964434146881,
|
|
"num_tokens": 4771812.0,
|
|
"step": 2745
|
|
},
|
|
{
|
|
"entropy": 5.9517346858978275,
|
|
"epoch": 0.21396615444466058,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000499791162692945,
|
|
"loss": 5.835,
|
|
"mean_token_accuracy": 0.14680606722831727,
|
|
"num_tokens": 4780616.0,
|
|
"step": 2750
|
|
},
|
|
{
|
|
"entropy": 5.967705154418946,
|
|
"epoch": 0.21435518381637814,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004997899671339214,
|
|
"loss": 5.8298,
|
|
"mean_token_accuracy": 0.1467273563146591,
|
|
"num_tokens": 4789886.0,
|
|
"step": 2755
|
|
},
|
|
{
|
|
"entropy": 6.010776853561401,
|
|
"epoch": 0.2147442131880957,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004997887681640675,
|
|
"loss": 5.7924,
|
|
"mean_token_accuracy": 0.15051775872707368,
|
|
"num_tokens": 4799189.0,
|
|
"step": 2760
|
|
},
|
|
{
|
|
"entropy": 6.061824893951416,
|
|
"epoch": 0.21513324255981325,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004997875657834021,
|
|
"loss": 5.8594,
|
|
"mean_token_accuracy": 0.14805168360471727,
|
|
"num_tokens": 4807850.0,
|
|
"step": 2765
|
|
},
|
|
{
|
|
"entropy": 6.05089316368103,
|
|
"epoch": 0.21552227193153084,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004997863599919432,
|
|
"loss": 5.7707,
|
|
"mean_token_accuracy": 0.14720831513404847,
|
|
"num_tokens": 4815742.0,
|
|
"step": 2770
|
|
},
|
|
{
|
|
"entropy": 6.032073307037353,
|
|
"epoch": 0.2159113013032484,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004997851507897089,
|
|
"loss": 5.857,
|
|
"mean_token_accuracy": 0.14828907027840615,
|
|
"num_tokens": 4824761.0,
|
|
"step": 2775
|
|
},
|
|
{
|
|
"entropy": 6.07795557975769,
|
|
"epoch": 0.21630033067496596,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004997839381767178,
|
|
"loss": 5.9915,
|
|
"mean_token_accuracy": 0.1347334012389183,
|
|
"num_tokens": 4832805.0,
|
|
"step": 2780
|
|
},
|
|
{
|
|
"entropy": 5.988602924346924,
|
|
"epoch": 0.21668936004668352,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004997827221529882,
|
|
"loss": 5.8384,
|
|
"mean_token_accuracy": 0.1470751255750656,
|
|
"num_tokens": 4841938.0,
|
|
"step": 2785
|
|
},
|
|
{
|
|
"entropy": 6.045064449310303,
|
|
"epoch": 0.2170783894184011,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004997815027185386,
|
|
"loss": 5.8645,
|
|
"mean_token_accuracy": 0.1436170071363449,
|
|
"num_tokens": 4849932.0,
|
|
"step": 2790
|
|
},
|
|
{
|
|
"entropy": 5.966535568237305,
|
|
"epoch": 0.21746741879011866,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004997802798733874,
|
|
"loss": 5.7285,
|
|
"mean_token_accuracy": 0.1491599291563034,
|
|
"num_tokens": 4859054.0,
|
|
"step": 2795
|
|
},
|
|
{
|
|
"entropy": 6.030629825592041,
|
|
"epoch": 0.21785644816183622,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004997790536175534,
|
|
"loss": 5.8931,
|
|
"mean_token_accuracy": 0.15091775506734847,
|
|
"num_tokens": 4867415.0,
|
|
"step": 2800
|
|
},
|
|
{
|
|
"entropy": 6.073462200164795,
|
|
"epoch": 0.21824547753355378,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004997778239510548,
|
|
"loss": 5.9334,
|
|
"mean_token_accuracy": 0.14272018224000932,
|
|
"num_tokens": 4875965.0,
|
|
"step": 2805
|
|
},
|
|
{
|
|
"entropy": 6.065163946151733,
|
|
"epoch": 0.21863450690527134,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004997765908739106,
|
|
"loss": 5.8328,
|
|
"mean_token_accuracy": 0.14725763201713563,
|
|
"num_tokens": 4884629.0,
|
|
"step": 2810
|
|
},
|
|
{
|
|
"entropy": 6.022565269470215,
|
|
"epoch": 0.21902353627698892,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004997753543861395,
|
|
"loss": 5.8746,
|
|
"mean_token_accuracy": 0.14686051681637763,
|
|
"num_tokens": 4893573.0,
|
|
"step": 2815
|
|
},
|
|
{
|
|
"entropy": 5.940307140350342,
|
|
"epoch": 0.21941256564870648,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00049977411448776,
|
|
"loss": 5.8078,
|
|
"mean_token_accuracy": 0.1442374676465988,
|
|
"num_tokens": 4902831.0,
|
|
"step": 2820
|
|
},
|
|
{
|
|
"entropy": 6.07591495513916,
|
|
"epoch": 0.21980159502042404,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004997728711787912,
|
|
"loss": 5.8593,
|
|
"mean_token_accuracy": 0.13736442774534224,
|
|
"num_tokens": 4911360.0,
|
|
"step": 2825
|
|
},
|
|
{
|
|
"entropy": 6.043661260604859,
|
|
"epoch": 0.2201906243921416,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004997716244592518,
|
|
"loss": 5.8214,
|
|
"mean_token_accuracy": 0.14348886758089066,
|
|
"num_tokens": 4919758.0,
|
|
"step": 2830
|
|
},
|
|
{
|
|
"entropy": 5.896661329269409,
|
|
"epoch": 0.22057965376385918,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004997703743291607,
|
|
"loss": 5.7102,
|
|
"mean_token_accuracy": 0.15584124326705934,
|
|
"num_tokens": 4928934.0,
|
|
"step": 2835
|
|
},
|
|
{
|
|
"entropy": 5.933321142196656,
|
|
"epoch": 0.22096868313557674,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000499769120788537,
|
|
"loss": 5.7655,
|
|
"mean_token_accuracy": 0.14841632395982743,
|
|
"num_tokens": 4937780.0,
|
|
"step": 2840
|
|
},
|
|
{
|
|
"entropy": 6.14625506401062,
|
|
"epoch": 0.2213577125072943,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004997678638373995,
|
|
"loss": 5.8583,
|
|
"mean_token_accuracy": 0.1424436628818512,
|
|
"num_tokens": 4946862.0,
|
|
"step": 2845
|
|
},
|
|
{
|
|
"entropy": 5.994505119323731,
|
|
"epoch": 0.22174674187901186,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004997666034757676,
|
|
"loss": 5.8358,
|
|
"mean_token_accuracy": 0.149576772749424,
|
|
"num_tokens": 4954883.0,
|
|
"step": 2850
|
|
},
|
|
{
|
|
"entropy": 5.885545825958252,
|
|
"epoch": 0.22213577125072942,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004997653397036603,
|
|
"loss": 5.6416,
|
|
"mean_token_accuracy": 0.1590978369116783,
|
|
"num_tokens": 4962840.0,
|
|
"step": 2855
|
|
},
|
|
{
|
|
"entropy": 5.9540290355682375,
|
|
"epoch": 0.222524800622447,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004997640725210965,
|
|
"loss": 5.8776,
|
|
"mean_token_accuracy": 0.14788952842354774,
|
|
"num_tokens": 4972334.0,
|
|
"step": 2860
|
|
},
|
|
{
|
|
"entropy": 6.020223808288574,
|
|
"epoch": 0.22291382999416456,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004997628019280958,
|
|
"loss": 5.8327,
|
|
"mean_token_accuracy": 0.14812421351671218,
|
|
"num_tokens": 4981032.0,
|
|
"step": 2865
|
|
},
|
|
{
|
|
"entropy": 6.030521392822266,
|
|
"epoch": 0.22330285936588212,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004997615279246773,
|
|
"loss": 5.8324,
|
|
"mean_token_accuracy": 0.14387644529342652,
|
|
"num_tokens": 4990502.0,
|
|
"step": 2870
|
|
},
|
|
{
|
|
"entropy": 6.103343868255616,
|
|
"epoch": 0.22369188873759968,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004997602505108603,
|
|
"loss": 6.0219,
|
|
"mean_token_accuracy": 0.1379172571003437,
|
|
"num_tokens": 4999121.0,
|
|
"step": 2875
|
|
},
|
|
{
|
|
"entropy": 6.037298774719238,
|
|
"epoch": 0.22408091810931724,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004997589696866644,
|
|
"loss": 5.7702,
|
|
"mean_token_accuracy": 0.14713070988655091,
|
|
"num_tokens": 5007271.0,
|
|
"step": 2880
|
|
},
|
|
{
|
|
"entropy": 5.960604190826416,
|
|
"epoch": 0.22446994748103483,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004997576854521088,
|
|
"loss": 5.8223,
|
|
"mean_token_accuracy": 0.1438037596642971,
|
|
"num_tokens": 5015940.0,
|
|
"step": 2885
|
|
},
|
|
{
|
|
"entropy": 5.943349742889405,
|
|
"epoch": 0.22485897685275238,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.000499756397807213,
|
|
"loss": 5.7488,
|
|
"mean_token_accuracy": 0.15114528685808182,
|
|
"num_tokens": 5024294.0,
|
|
"step": 2890
|
|
},
|
|
{
|
|
"entropy": 6.015953445434571,
|
|
"epoch": 0.22524800622446994,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004997551067519966,
|
|
"loss": 5.7094,
|
|
"mean_token_accuracy": 0.1564256578683853,
|
|
"num_tokens": 5033401.0,
|
|
"step": 2895
|
|
},
|
|
{
|
|
"entropy": 5.932667875289917,
|
|
"epoch": 0.2256370355961875,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004997538122864792,
|
|
"loss": 5.8063,
|
|
"mean_token_accuracy": 0.14516399949789047,
|
|
"num_tokens": 5041955.0,
|
|
"step": 2900
|
|
},
|
|
{
|
|
"entropy": 5.982646894454956,
|
|
"epoch": 0.2260260649679051,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004997525144106804,
|
|
"loss": 5.8437,
|
|
"mean_token_accuracy": 0.14041123390197754,
|
|
"num_tokens": 5051132.0,
|
|
"step": 2905
|
|
},
|
|
{
|
|
"entropy": 5.9859472751617435,
|
|
"epoch": 0.22641509433962265,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00049975121312462,
|
|
"loss": 5.7668,
|
|
"mean_token_accuracy": 0.15441568344831466,
|
|
"num_tokens": 5059492.0,
|
|
"step": 2910
|
|
},
|
|
{
|
|
"entropy": 5.891498994827271,
|
|
"epoch": 0.2268041237113402,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004997499084283177,
|
|
"loss": 5.8123,
|
|
"mean_token_accuracy": 0.15069894939661027,
|
|
"num_tokens": 5069015.0,
|
|
"step": 2915
|
|
},
|
|
{
|
|
"entropy": 5.9988916397094725,
|
|
"epoch": 0.22719315308305776,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004997486003217932,
|
|
"loss": 5.8223,
|
|
"mean_token_accuracy": 0.1472141906619072,
|
|
"num_tokens": 5077614.0,
|
|
"step": 2920
|
|
},
|
|
{
|
|
"entropy": 5.993191337585449,
|
|
"epoch": 0.22758218245477532,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004997472888050664,
|
|
"loss": 5.7616,
|
|
"mean_token_accuracy": 0.14898982793092727,
|
|
"num_tokens": 5086300.0,
|
|
"step": 2925
|
|
},
|
|
{
|
|
"entropy": 5.879473543167114,
|
|
"epoch": 0.2279712118264929,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004997459738781573,
|
|
"loss": 5.8034,
|
|
"mean_token_accuracy": 0.1515287682414055,
|
|
"num_tokens": 5095967.0,
|
|
"step": 2930
|
|
},
|
|
{
|
|
"entropy": 6.005168533325195,
|
|
"epoch": 0.22836024119821047,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004997446555410857,
|
|
"loss": 5.7629,
|
|
"mean_token_accuracy": 0.14633936136960984,
|
|
"num_tokens": 5104611.0,
|
|
"step": 2935
|
|
},
|
|
{
|
|
"entropy": 5.9345582008361815,
|
|
"epoch": 0.22874927056992803,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004997433337938716,
|
|
"loss": 5.7352,
|
|
"mean_token_accuracy": 0.14881281405687333,
|
|
"num_tokens": 5113452.0,
|
|
"step": 2940
|
|
},
|
|
{
|
|
"entropy": 5.903948497772217,
|
|
"epoch": 0.22913829994164558,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004997420086365351,
|
|
"loss": 5.7075,
|
|
"mean_token_accuracy": 0.15194878876209258,
|
|
"num_tokens": 5121558.0,
|
|
"step": 2945
|
|
},
|
|
{
|
|
"entropy": 5.9376458644866945,
|
|
"epoch": 0.22952732931336317,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004997406800690966,
|
|
"loss": 5.6743,
|
|
"mean_token_accuracy": 0.16064000129699707,
|
|
"num_tokens": 5129942.0,
|
|
"step": 2950
|
|
},
|
|
{
|
|
"entropy": 5.969931030273438,
|
|
"epoch": 0.22991635868508073,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004997393480915758,
|
|
"loss": 5.8154,
|
|
"mean_token_accuracy": 0.14137779250741006,
|
|
"num_tokens": 5139012.0,
|
|
"step": 2955
|
|
},
|
|
{
|
|
"entropy": 6.0334978103637695,
|
|
"epoch": 0.2303053880567983,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004997380127039931,
|
|
"loss": 5.818,
|
|
"mean_token_accuracy": 0.150064118206501,
|
|
"num_tokens": 5148185.0,
|
|
"step": 2960
|
|
},
|
|
{
|
|
"entropy": 5.993949317932129,
|
|
"epoch": 0.23069441742851585,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004997366739063688,
|
|
"loss": 5.8355,
|
|
"mean_token_accuracy": 0.1448197141289711,
|
|
"num_tokens": 5157086.0,
|
|
"step": 2965
|
|
},
|
|
{
|
|
"entropy": 6.100489139556885,
|
|
"epoch": 0.2310834468002334,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004997353316987231,
|
|
"loss": 5.9076,
|
|
"mean_token_accuracy": 0.14102671518921853,
|
|
"num_tokens": 5165842.0,
|
|
"step": 2970
|
|
},
|
|
{
|
|
"entropy": 6.074266862869263,
|
|
"epoch": 0.231472476171951,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004997339860810765,
|
|
"loss": 5.9076,
|
|
"mean_token_accuracy": 0.14826976209878923,
|
|
"num_tokens": 5174161.0,
|
|
"step": 2975
|
|
},
|
|
{
|
|
"entropy": 5.951193332672119,
|
|
"epoch": 0.23186150554366855,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004997326370534495,
|
|
"loss": 5.8456,
|
|
"mean_token_accuracy": 0.14642503708600998,
|
|
"num_tokens": 5183830.0,
|
|
"step": 2980
|
|
},
|
|
{
|
|
"entropy": 5.981384754180908,
|
|
"epoch": 0.2322505349153861,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004997312846158622,
|
|
"loss": 5.7689,
|
|
"mean_token_accuracy": 0.14501096159219742,
|
|
"num_tokens": 5192248.0,
|
|
"step": 2985
|
|
},
|
|
{
|
|
"entropy": 5.878167724609375,
|
|
"epoch": 0.23263956428710367,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004997299287683355,
|
|
"loss": 5.7312,
|
|
"mean_token_accuracy": 0.1538401484489441,
|
|
"num_tokens": 5201212.0,
|
|
"step": 2990
|
|
},
|
|
{
|
|
"entropy": 5.966686391830445,
|
|
"epoch": 0.23302859365882125,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004997285695108898,
|
|
"loss": 5.7912,
|
|
"mean_token_accuracy": 0.145901557803154,
|
|
"num_tokens": 5209338.0,
|
|
"step": 2995
|
|
},
|
|
{
|
|
"entropy": 6.075098180770874,
|
|
"epoch": 0.2334176230305388,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004997272068435458,
|
|
"loss": 5.8133,
|
|
"mean_token_accuracy": 0.14372822940349578,
|
|
"num_tokens": 5217590.0,
|
|
"step": 3000
|
|
},
|
|
{
|
|
"epoch": 0.2334176230305388,
|
|
"eval_entropy": 5.7649864601561145,
|
|
"eval_loss": 5.838047027587891,
|
|
"eval_mean_token_accuracy": 0.1541939339104814,
|
|
"eval_num_tokens": 5217590.0,
|
|
"eval_runtime": 21.9076,
|
|
"eval_samples_per_second": 1896.968,
|
|
"eval_steps_per_second": 237.132,
|
|
"step": 3000
|
|
},
|
|
{
|
|
"entropy": 5.907944631576538,
|
|
"epoch": 0.23380665240225637,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000499725840766324,
|
|
"loss": 5.7253,
|
|
"mean_token_accuracy": 0.15077031999826432,
|
|
"num_tokens": 5226383.0,
|
|
"step": 3005
|
|
},
|
|
{
|
|
"entropy": 5.9791473865509035,
|
|
"epoch": 0.23419568177397393,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004997244712792453,
|
|
"loss": 5.7687,
|
|
"mean_token_accuracy": 0.1488740026950836,
|
|
"num_tokens": 5235517.0,
|
|
"step": 3010
|
|
},
|
|
{
|
|
"entropy": 6.0556151390075685,
|
|
"epoch": 0.2345847111456915,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004997230983823305,
|
|
"loss": 5.7481,
|
|
"mean_token_accuracy": 0.1573214754462242,
|
|
"num_tokens": 5243812.0,
|
|
"step": 3015
|
|
},
|
|
{
|
|
"entropy": 5.912490129470825,
|
|
"epoch": 0.23497374051740907,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004997217220756003,
|
|
"loss": 5.7598,
|
|
"mean_token_accuracy": 0.14918334409594536,
|
|
"num_tokens": 5252399.0,
|
|
"step": 3020
|
|
},
|
|
{
|
|
"entropy": 5.963000392913818,
|
|
"epoch": 0.23536276988912663,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004997203423590757,
|
|
"loss": 5.7813,
|
|
"mean_token_accuracy": 0.14887740164995195,
|
|
"num_tokens": 5260847.0,
|
|
"step": 3025
|
|
},
|
|
{
|
|
"entropy": 5.998490476608277,
|
|
"epoch": 0.2357517992608442,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004997189592327775,
|
|
"loss": 5.855,
|
|
"mean_token_accuracy": 0.14860740453004836,
|
|
"num_tokens": 5268847.0,
|
|
"step": 3030
|
|
},
|
|
{
|
|
"entropy": 6.0372459411621096,
|
|
"epoch": 0.23614082863256175,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004997175726967268,
|
|
"loss": 5.7837,
|
|
"mean_token_accuracy": 0.14813946485519408,
|
|
"num_tokens": 5277989.0,
|
|
"step": 3035
|
|
},
|
|
{
|
|
"entropy": 5.881270456314087,
|
|
"epoch": 0.23652985800427934,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004997161827509447,
|
|
"loss": 5.7804,
|
|
"mean_token_accuracy": 0.15062111616134644,
|
|
"num_tokens": 5286272.0,
|
|
"step": 3040
|
|
},
|
|
{
|
|
"entropy": 5.935083866119385,
|
|
"epoch": 0.2369188873759969,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004997147893954521,
|
|
"loss": 5.7856,
|
|
"mean_token_accuracy": 0.14935739189386368,
|
|
"num_tokens": 5295281.0,
|
|
"step": 3045
|
|
},
|
|
{
|
|
"entropy": 6.040230655670166,
|
|
"epoch": 0.23730791674771445,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004997133926302702,
|
|
"loss": 5.7326,
|
|
"mean_token_accuracy": 0.15305247008800507,
|
|
"num_tokens": 5303905.0,
|
|
"step": 3050
|
|
},
|
|
{
|
|
"entropy": 5.91657977104187,
|
|
"epoch": 0.237696946119432,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004997119924554204,
|
|
"loss": 5.7193,
|
|
"mean_token_accuracy": 0.1474948540329933,
|
|
"num_tokens": 5313146.0,
|
|
"step": 3055
|
|
},
|
|
{
|
|
"entropy": 5.920493745803833,
|
|
"epoch": 0.23808597549114957,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004997105888709236,
|
|
"loss": 5.755,
|
|
"mean_token_accuracy": 0.14988460689783095,
|
|
"num_tokens": 5320838.0,
|
|
"step": 3060
|
|
},
|
|
{
|
|
"entropy": 5.927872037887573,
|
|
"epoch": 0.23847500486286716,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004997091818768015,
|
|
"loss": 5.7825,
|
|
"mean_token_accuracy": 0.14742809981107713,
|
|
"num_tokens": 5329312.0,
|
|
"step": 3065
|
|
},
|
|
{
|
|
"entropy": 5.909237957000732,
|
|
"epoch": 0.23886403423458472,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000499707771473075,
|
|
"loss": 5.777,
|
|
"mean_token_accuracy": 0.14921307563781738,
|
|
"num_tokens": 5337747.0,
|
|
"step": 3070
|
|
},
|
|
{
|
|
"entropy": 5.979187774658203,
|
|
"epoch": 0.23925306360630227,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004997063576597659,
|
|
"loss": 5.7621,
|
|
"mean_token_accuracy": 0.1467119038105011,
|
|
"num_tokens": 5346928.0,
|
|
"step": 3075
|
|
},
|
|
{
|
|
"entropy": 5.943646335601807,
|
|
"epoch": 0.23964209297801983,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004997049404368954,
|
|
"loss": 5.7875,
|
|
"mean_token_accuracy": 0.1435694396495819,
|
|
"num_tokens": 5355827.0,
|
|
"step": 3080
|
|
},
|
|
{
|
|
"entropy": 6.062672805786133,
|
|
"epoch": 0.2400311223497374,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000499703519804485,
|
|
"loss": 5.9124,
|
|
"mean_token_accuracy": 0.14042111486196518,
|
|
"num_tokens": 5364309.0,
|
|
"step": 3085
|
|
},
|
|
{
|
|
"entropy": 5.996913576126099,
|
|
"epoch": 0.24042015172145498,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004997020957625564,
|
|
"loss": 5.8024,
|
|
"mean_token_accuracy": 0.14950317591428758,
|
|
"num_tokens": 5372979.0,
|
|
"step": 3090
|
|
},
|
|
{
|
|
"entropy": 5.954580926895142,
|
|
"epoch": 0.24080918109317254,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004997006683111312,
|
|
"loss": 5.7816,
|
|
"mean_token_accuracy": 0.1460615485906601,
|
|
"num_tokens": 5381809.0,
|
|
"step": 3095
|
|
},
|
|
{
|
|
"entropy": 6.0027283191680905,
|
|
"epoch": 0.2411982104648901,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000499699237450231,
|
|
"loss": 5.8266,
|
|
"mean_token_accuracy": 0.1532255783677101,
|
|
"num_tokens": 5390036.0,
|
|
"step": 3100
|
|
},
|
|
{
|
|
"entropy": 6.103567266464234,
|
|
"epoch": 0.24158723983660765,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004996978031798774,
|
|
"loss": 5.8904,
|
|
"mean_token_accuracy": 0.14301448315382004,
|
|
"num_tokens": 5398739.0,
|
|
"step": 3105
|
|
},
|
|
{
|
|
"entropy": 5.922081136703492,
|
|
"epoch": 0.24197626920832524,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004996963655000924,
|
|
"loss": 5.8034,
|
|
"mean_token_accuracy": 0.14707928150892258,
|
|
"num_tokens": 5407441.0,
|
|
"step": 3110
|
|
},
|
|
{
|
|
"entropy": 5.998806762695312,
|
|
"epoch": 0.2423652985800428,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004996949244108977,
|
|
"loss": 5.7393,
|
|
"mean_token_accuracy": 0.15036838203668595,
|
|
"num_tokens": 5416534.0,
|
|
"step": 3115
|
|
},
|
|
{
|
|
"entropy": 5.997593593597412,
|
|
"epoch": 0.24275432795176036,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000499693479912315,
|
|
"loss": 5.7991,
|
|
"mean_token_accuracy": 0.14814602732658386,
|
|
"num_tokens": 5425170.0,
|
|
"step": 3120
|
|
},
|
|
{
|
|
"entropy": 5.911679410934449,
|
|
"epoch": 0.24314335732347792,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004996920320043666,
|
|
"loss": 5.7656,
|
|
"mean_token_accuracy": 0.1437433570623398,
|
|
"num_tokens": 5433721.0,
|
|
"step": 3125
|
|
},
|
|
{
|
|
"entropy": 6.002860069274902,
|
|
"epoch": 0.24353238669519547,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004996905806870742,
|
|
"loss": 5.8225,
|
|
"mean_token_accuracy": 0.14360172301530838,
|
|
"num_tokens": 5441708.0,
|
|
"step": 3130
|
|
},
|
|
{
|
|
"entropy": 5.928072738647461,
|
|
"epoch": 0.24392141606691306,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004996891259604598,
|
|
"loss": 5.7297,
|
|
"mean_token_accuracy": 0.15173338651657103,
|
|
"num_tokens": 5449942.0,
|
|
"step": 3135
|
|
},
|
|
{
|
|
"entropy": 5.993139457702637,
|
|
"epoch": 0.24431044543863062,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004996876678245455,
|
|
"loss": 5.751,
|
|
"mean_token_accuracy": 0.14968564808368684,
|
|
"num_tokens": 5458004.0,
|
|
"step": 3140
|
|
},
|
|
{
|
|
"entropy": 6.0081267833709715,
|
|
"epoch": 0.24469947481034818,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004996862062793536,
|
|
"loss": 5.8396,
|
|
"mean_token_accuracy": 0.15170659869909286,
|
|
"num_tokens": 5467071.0,
|
|
"step": 3145
|
|
},
|
|
{
|
|
"entropy": 5.93834810256958,
|
|
"epoch": 0.24508850418206574,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004996847413249061,
|
|
"loss": 5.8085,
|
|
"mean_token_accuracy": 0.14909462928771972,
|
|
"num_tokens": 5476221.0,
|
|
"step": 3150
|
|
},
|
|
{
|
|
"entropy": 5.976137924194336,
|
|
"epoch": 0.24547753355378332,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004996832729612252,
|
|
"loss": 5.7315,
|
|
"mean_token_accuracy": 0.14793778508901595,
|
|
"num_tokens": 5484549.0,
|
|
"step": 3155
|
|
},
|
|
{
|
|
"entropy": 5.853325271606446,
|
|
"epoch": 0.24586656292550088,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004996818011883333,
|
|
"loss": 5.7291,
|
|
"mean_token_accuracy": 0.15456597805023192,
|
|
"num_tokens": 5492909.0,
|
|
"step": 3160
|
|
},
|
|
{
|
|
"entropy": 5.959857606887818,
|
|
"epoch": 0.24625559229721844,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004996803260062527,
|
|
"loss": 5.7712,
|
|
"mean_token_accuracy": 0.15276994407176972,
|
|
"num_tokens": 5501418.0,
|
|
"step": 3165
|
|
},
|
|
{
|
|
"entropy": 5.982174873352051,
|
|
"epoch": 0.246644621668936,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004996788474150057,
|
|
"loss": 5.7809,
|
|
"mean_token_accuracy": 0.14409117698669432,
|
|
"num_tokens": 5510609.0,
|
|
"step": 3170
|
|
},
|
|
{
|
|
"entropy": 5.861660671234131,
|
|
"epoch": 0.24703365104065356,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004996773654146149,
|
|
"loss": 5.6293,
|
|
"mean_token_accuracy": 0.15756507366895675,
|
|
"num_tokens": 5518349.0,
|
|
"step": 3175
|
|
},
|
|
{
|
|
"entropy": 5.857954120635986,
|
|
"epoch": 0.24742268041237114,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004996758800051026,
|
|
"loss": 5.5799,
|
|
"mean_token_accuracy": 0.15771122723817826,
|
|
"num_tokens": 5526972.0,
|
|
"step": 3180
|
|
},
|
|
{
|
|
"entropy": 5.867163467407226,
|
|
"epoch": 0.2478117097840887,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004996743911864916,
|
|
"loss": 5.752,
|
|
"mean_token_accuracy": 0.14744784981012343,
|
|
"num_tokens": 5535683.0,
|
|
"step": 3185
|
|
},
|
|
{
|
|
"entropy": 5.870160245895386,
|
|
"epoch": 0.24820073915580626,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004996728989588041,
|
|
"loss": 5.7191,
|
|
"mean_token_accuracy": 0.1577271744608879,
|
|
"num_tokens": 5544258.0,
|
|
"step": 3190
|
|
},
|
|
{
|
|
"entropy": 5.846530818939209,
|
|
"epoch": 0.24858976852752382,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004996714033220632,
|
|
"loss": 5.7347,
|
|
"mean_token_accuracy": 0.14929380863904954,
|
|
"num_tokens": 5552608.0,
|
|
"step": 3195
|
|
},
|
|
{
|
|
"entropy": 5.937586975097656,
|
|
"epoch": 0.2489787978992414,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004996699042762911,
|
|
"loss": 5.8503,
|
|
"mean_token_accuracy": 0.14045757427811623,
|
|
"num_tokens": 5561357.0,
|
|
"step": 3200
|
|
},
|
|
{
|
|
"entropy": 6.005559206008911,
|
|
"epoch": 0.24936782727095896,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004996684018215111,
|
|
"loss": 5.6715,
|
|
"mean_token_accuracy": 0.16094748824834823,
|
|
"num_tokens": 5569862.0,
|
|
"step": 3205
|
|
},
|
|
{
|
|
"entropy": 5.907440137863159,
|
|
"epoch": 0.24975685664267652,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004996668959577453,
|
|
"loss": 5.7432,
|
|
"mean_token_accuracy": 0.15263464897871018,
|
|
"num_tokens": 5578485.0,
|
|
"step": 3210
|
|
},
|
|
{
|
|
"entropy": 5.875484657287598,
|
|
"epoch": 0.2501458860143941,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004996653866850173,
|
|
"loss": 5.7328,
|
|
"mean_token_accuracy": 0.14682287722826004,
|
|
"num_tokens": 5587713.0,
|
|
"step": 3215
|
|
},
|
|
{
|
|
"entropy": 5.963264131546021,
|
|
"epoch": 0.25053491538611167,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004996638740033495,
|
|
"loss": 5.7997,
|
|
"mean_token_accuracy": 0.15026128888130189,
|
|
"num_tokens": 5596541.0,
|
|
"step": 3220
|
|
},
|
|
{
|
|
"entropy": 5.863694381713867,
|
|
"epoch": 0.2509239447578292,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004996623579127651,
|
|
"loss": 5.6721,
|
|
"mean_token_accuracy": 0.15386685878038406,
|
|
"num_tokens": 5605573.0,
|
|
"step": 3225
|
|
},
|
|
{
|
|
"entropy": 5.923236894607544,
|
|
"epoch": 0.2513129741295468,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004996608384132868,
|
|
"loss": 5.6887,
|
|
"mean_token_accuracy": 0.15542172491550446,
|
|
"num_tokens": 5614016.0,
|
|
"step": 3230
|
|
},
|
|
{
|
|
"entropy": 6.036375427246094,
|
|
"epoch": 0.25170200350126437,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000499659315504938,
|
|
"loss": 5.9137,
|
|
"mean_token_accuracy": 0.1452291265130043,
|
|
"num_tokens": 5622451.0,
|
|
"step": 3235
|
|
},
|
|
{
|
|
"entropy": 5.9037364482879635,
|
|
"epoch": 0.2520910328729819,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004996577891877417,
|
|
"loss": 5.7515,
|
|
"mean_token_accuracy": 0.14964452758431435,
|
|
"num_tokens": 5631384.0,
|
|
"step": 3240
|
|
},
|
|
{
|
|
"entropy": 5.927656078338623,
|
|
"epoch": 0.2524800622446995,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004996562594617209,
|
|
"loss": 5.7129,
|
|
"mean_token_accuracy": 0.1541423261165619,
|
|
"num_tokens": 5640726.0,
|
|
"step": 3245
|
|
},
|
|
{
|
|
"entropy": 5.965122318267822,
|
|
"epoch": 0.252869091616417,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004996547263268991,
|
|
"loss": 5.7332,
|
|
"mean_token_accuracy": 0.14803583323955535,
|
|
"num_tokens": 5648948.0,
|
|
"step": 3250
|
|
},
|
|
{
|
|
"entropy": 5.794720411300659,
|
|
"epoch": 0.2532581209881346,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004996531897832993,
|
|
"loss": 5.6824,
|
|
"mean_token_accuracy": 0.15577371567487716,
|
|
"num_tokens": 5657951.0,
|
|
"step": 3255
|
|
},
|
|
{
|
|
"entropy": 6.0227070331573485,
|
|
"epoch": 0.2536471503598522,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000499651649830945,
|
|
"loss": 5.8137,
|
|
"mean_token_accuracy": 0.1499185547232628,
|
|
"num_tokens": 5667476.0,
|
|
"step": 3260
|
|
},
|
|
{
|
|
"entropy": 5.9482104778289795,
|
|
"epoch": 0.2540361797315697,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004996501064698593,
|
|
"loss": 5.8079,
|
|
"mean_token_accuracy": 0.1510738968849182,
|
|
"num_tokens": 5676627.0,
|
|
"step": 3265
|
|
},
|
|
{
|
|
"entropy": 5.888298082351684,
|
|
"epoch": 0.2544252091032873,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000499648559700066,
|
|
"loss": 5.7389,
|
|
"mean_token_accuracy": 0.15606578439474106,
|
|
"num_tokens": 5684376.0,
|
|
"step": 3270
|
|
},
|
|
{
|
|
"entropy": 5.999397611618042,
|
|
"epoch": 0.25481423847500484,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004996470095215884,
|
|
"loss": 5.8974,
|
|
"mean_token_accuracy": 0.13699436113238334,
|
|
"num_tokens": 5693629.0,
|
|
"step": 3275
|
|
},
|
|
{
|
|
"entropy": 6.0265604019165036,
|
|
"epoch": 0.2552032678467224,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004996454559344498,
|
|
"loss": 5.7848,
|
|
"mean_token_accuracy": 0.1482024610042572,
|
|
"num_tokens": 5702010.0,
|
|
"step": 3280
|
|
},
|
|
{
|
|
"entropy": 5.836571741104126,
|
|
"epoch": 0.25559229721844,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004996438989386741,
|
|
"loss": 5.6821,
|
|
"mean_token_accuracy": 0.15332212150096894,
|
|
"num_tokens": 5710823.0,
|
|
"step": 3285
|
|
},
|
|
{
|
|
"entropy": 5.929405069351196,
|
|
"epoch": 0.25598132659015754,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004996423385342847,
|
|
"loss": 5.7385,
|
|
"mean_token_accuracy": 0.15431096404790878,
|
|
"num_tokens": 5719389.0,
|
|
"step": 3290
|
|
},
|
|
{
|
|
"entropy": 5.9652153015136715,
|
|
"epoch": 0.25637035596187513,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004996407747213055,
|
|
"loss": 5.7513,
|
|
"mean_token_accuracy": 0.14783500358462334,
|
|
"num_tokens": 5727327.0,
|
|
"step": 3295
|
|
},
|
|
{
|
|
"entropy": 5.902391672134399,
|
|
"epoch": 0.25675938533359266,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00049963920749976,
|
|
"loss": 5.6451,
|
|
"mean_token_accuracy": 0.15661601424217225,
|
|
"num_tokens": 5735886.0,
|
|
"step": 3300
|
|
},
|
|
{
|
|
"entropy": 5.874257373809814,
|
|
"epoch": 0.25714841470531025,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004996376368696721,
|
|
"loss": 5.6872,
|
|
"mean_token_accuracy": 0.1504574626684189,
|
|
"num_tokens": 5744656.0,
|
|
"step": 3305
|
|
},
|
|
{
|
|
"entropy": 5.962090301513672,
|
|
"epoch": 0.25753744407702783,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004996360628310656,
|
|
"loss": 5.8558,
|
|
"mean_token_accuracy": 0.14705744832754136,
|
|
"num_tokens": 5753026.0,
|
|
"step": 3310
|
|
},
|
|
{
|
|
"entropy": 5.944463777542114,
|
|
"epoch": 0.25792647344874536,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004996344853839644,
|
|
"loss": 5.7887,
|
|
"mean_token_accuracy": 0.14836156964302064,
|
|
"num_tokens": 5762771.0,
|
|
"step": 3315
|
|
},
|
|
{
|
|
"entropy": 5.880813026428223,
|
|
"epoch": 0.25831550282046295,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004996329045283924,
|
|
"loss": 5.7789,
|
|
"mean_token_accuracy": 0.15456028431653976,
|
|
"num_tokens": 5771151.0,
|
|
"step": 3320
|
|
},
|
|
{
|
|
"entropy": 5.913249826431274,
|
|
"epoch": 0.25870453219218054,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004996313202643737,
|
|
"loss": 5.6723,
|
|
"mean_token_accuracy": 0.15277076810598372,
|
|
"num_tokens": 5780648.0,
|
|
"step": 3325
|
|
},
|
|
{
|
|
"entropy": 5.894395017623902,
|
|
"epoch": 0.25909356156389807,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004996297325919321,
|
|
"loss": 5.6637,
|
|
"mean_token_accuracy": 0.1506694659590721,
|
|
"num_tokens": 5789698.0,
|
|
"step": 3330
|
|
},
|
|
{
|
|
"entropy": 5.952166795730591,
|
|
"epoch": 0.25948259093561565,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004996281415110919,
|
|
"loss": 5.8531,
|
|
"mean_token_accuracy": 0.14342217296361923,
|
|
"num_tokens": 5799218.0,
|
|
"step": 3335
|
|
},
|
|
{
|
|
"entropy": 5.8528892993927,
|
|
"epoch": 0.2598716203073332,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004996265470218773,
|
|
"loss": 5.7224,
|
|
"mean_token_accuracy": 0.14743948727846146,
|
|
"num_tokens": 5808455.0,
|
|
"step": 3340
|
|
},
|
|
{
|
|
"entropy": 5.93385009765625,
|
|
"epoch": 0.26026064967905077,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004996249491243122,
|
|
"loss": 5.7444,
|
|
"mean_token_accuracy": 0.15022578909993173,
|
|
"num_tokens": 5816464.0,
|
|
"step": 3345
|
|
},
|
|
{
|
|
"entropy": 5.881568384170532,
|
|
"epoch": 0.26064967905076836,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004996233478184211,
|
|
"loss": 5.7044,
|
|
"mean_token_accuracy": 0.1526622548699379,
|
|
"num_tokens": 5825188.0,
|
|
"step": 3350
|
|
},
|
|
{
|
|
"entropy": 5.923000812530518,
|
|
"epoch": 0.2610387084224859,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004996217431042282,
|
|
"loss": 5.7652,
|
|
"mean_token_accuracy": 0.15034854263067246,
|
|
"num_tokens": 5834150.0,
|
|
"step": 3355
|
|
},
|
|
{
|
|
"entropy": 5.867080879211426,
|
|
"epoch": 0.2614277377942035,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000499620134981758,
|
|
"loss": 5.6124,
|
|
"mean_token_accuracy": 0.1616185039281845,
|
|
"num_tokens": 5842801.0,
|
|
"step": 3360
|
|
},
|
|
{
|
|
"entropy": 5.886935424804688,
|
|
"epoch": 0.261816767165921,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004996185234510346,
|
|
"loss": 5.6495,
|
|
"mean_token_accuracy": 0.16229631155729293,
|
|
"num_tokens": 5851547.0,
|
|
"step": 3365
|
|
},
|
|
{
|
|
"entropy": 5.927301025390625,
|
|
"epoch": 0.2622057965376386,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004996169085120828,
|
|
"loss": 5.7961,
|
|
"mean_token_accuracy": 0.14882034361362456,
|
|
"num_tokens": 5860430.0,
|
|
"step": 3370
|
|
},
|
|
{
|
|
"entropy": 5.860882091522217,
|
|
"epoch": 0.2625948259093562,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004996152901649268,
|
|
"loss": 5.6934,
|
|
"mean_token_accuracy": 0.15090493410825728,
|
|
"num_tokens": 5869648.0,
|
|
"step": 3375
|
|
},
|
|
{
|
|
"entropy": 6.013001251220703,
|
|
"epoch": 0.2629838552810737,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004996136684095913,
|
|
"loss": 5.705,
|
|
"mean_token_accuracy": 0.15475423485040665,
|
|
"num_tokens": 5878606.0,
|
|
"step": 3380
|
|
},
|
|
{
|
|
"entropy": 5.845886325836181,
|
|
"epoch": 0.2633728846527913,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004996120432461009,
|
|
"loss": 5.7717,
|
|
"mean_token_accuracy": 0.15084365159273147,
|
|
"num_tokens": 5886772.0,
|
|
"step": 3385
|
|
},
|
|
{
|
|
"entropy": 5.840115022659302,
|
|
"epoch": 0.2637619140245088,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004996104146744804,
|
|
"loss": 5.6822,
|
|
"mean_token_accuracy": 0.15241987705230714,
|
|
"num_tokens": 5895007.0,
|
|
"step": 3390
|
|
},
|
|
{
|
|
"entropy": 6.0143967628479,
|
|
"epoch": 0.2641509433962264,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004996087826947541,
|
|
"loss": 5.8116,
|
|
"mean_token_accuracy": 0.14449280947446824,
|
|
"num_tokens": 5904249.0,
|
|
"step": 3395
|
|
},
|
|
{
|
|
"entropy": 5.896013498306274,
|
|
"epoch": 0.264539972767944,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004996071473069471,
|
|
"loss": 5.7678,
|
|
"mean_token_accuracy": 0.14941729232668877,
|
|
"num_tokens": 5911416.0,
|
|
"step": 3400
|
|
},
|
|
{
|
|
"entropy": 5.942146158218383,
|
|
"epoch": 0.26492900213966153,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004996055085110842,
|
|
"loss": 5.8126,
|
|
"mean_token_accuracy": 0.14736545830965042,
|
|
"num_tokens": 5920370.0,
|
|
"step": 3405
|
|
},
|
|
{
|
|
"entropy": 5.916384363174439,
|
|
"epoch": 0.2653180315113791,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004996038663071902,
|
|
"loss": 5.7647,
|
|
"mean_token_accuracy": 0.1517030656337738,
|
|
"num_tokens": 5928884.0,
|
|
"step": 3410
|
|
},
|
|
{
|
|
"entropy": 5.919314765930176,
|
|
"epoch": 0.26570706088309665,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004996022206952901,
|
|
"loss": 5.7914,
|
|
"mean_token_accuracy": 0.1425839588046074,
|
|
"num_tokens": 5938456.0,
|
|
"step": 3415
|
|
},
|
|
{
|
|
"entropy": 6.024834537506104,
|
|
"epoch": 0.26609609025481423,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004996005716754086,
|
|
"loss": 5.8121,
|
|
"mean_token_accuracy": 0.14940155595541,
|
|
"num_tokens": 5947157.0,
|
|
"step": 3420
|
|
},
|
|
{
|
|
"entropy": 5.928007030487061,
|
|
"epoch": 0.2664851196265318,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000499598919247571,
|
|
"loss": 5.6607,
|
|
"mean_token_accuracy": 0.15864564031362532,
|
|
"num_tokens": 5956084.0,
|
|
"step": 3425
|
|
},
|
|
{
|
|
"entropy": 5.8320718765258786,
|
|
"epoch": 0.26687414899824935,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004995972634118023,
|
|
"loss": 5.7006,
|
|
"mean_token_accuracy": 0.15306968986988068,
|
|
"num_tokens": 5964782.0,
|
|
"step": 3430
|
|
},
|
|
{
|
|
"entropy": 5.997024011611939,
|
|
"epoch": 0.26726317836996694,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004995956041681277,
|
|
"loss": 5.926,
|
|
"mean_token_accuracy": 0.13784579634666444,
|
|
"num_tokens": 5974013.0,
|
|
"step": 3435
|
|
},
|
|
{
|
|
"entropy": 6.002984857559204,
|
|
"epoch": 0.2676522077416845,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004995939415165722,
|
|
"loss": 5.7924,
|
|
"mean_token_accuracy": 0.14788678735494615,
|
|
"num_tokens": 5983351.0,
|
|
"step": 3440
|
|
},
|
|
{
|
|
"entropy": 5.827401399612427,
|
|
"epoch": 0.26804123711340205,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004995922754571611,
|
|
"loss": 5.6321,
|
|
"mean_token_accuracy": 0.15837901681661606,
|
|
"num_tokens": 5992084.0,
|
|
"step": 3445
|
|
},
|
|
{
|
|
"entropy": 5.769678592681885,
|
|
"epoch": 0.26843026648511964,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004995906059899197,
|
|
"loss": 5.6461,
|
|
"mean_token_accuracy": 0.15735748410224915,
|
|
"num_tokens": 6001043.0,
|
|
"step": 3450
|
|
},
|
|
{
|
|
"entropy": 5.843425035476685,
|
|
"epoch": 0.26881929585683717,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004995889331148733,
|
|
"loss": 5.6494,
|
|
"mean_token_accuracy": 0.1511452838778496,
|
|
"num_tokens": 6009620.0,
|
|
"step": 3455
|
|
},
|
|
{
|
|
"entropy": 5.837132358551026,
|
|
"epoch": 0.26920832522855476,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004995872568320474,
|
|
"loss": 5.6575,
|
|
"mean_token_accuracy": 0.15076996386051178,
|
|
"num_tokens": 6018278.0,
|
|
"step": 3460
|
|
},
|
|
{
|
|
"entropy": 5.828963851928711,
|
|
"epoch": 0.26959735460027234,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004995855771414673,
|
|
"loss": 5.707,
|
|
"mean_token_accuracy": 0.15559014976024627,
|
|
"num_tokens": 6026741.0,
|
|
"step": 3465
|
|
},
|
|
{
|
|
"entropy": 5.974634027481079,
|
|
"epoch": 0.2699863839719899,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004995838940431585,
|
|
"loss": 5.734,
|
|
"mean_token_accuracy": 0.15174644887447358,
|
|
"num_tokens": 6035370.0,
|
|
"step": 3470
|
|
},
|
|
{
|
|
"entropy": 5.874317741394043,
|
|
"epoch": 0.27037541334370746,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004995822075371466,
|
|
"loss": 5.6988,
|
|
"mean_token_accuracy": 0.15232974737882615,
|
|
"num_tokens": 6044372.0,
|
|
"step": 3475
|
|
},
|
|
{
|
|
"entropy": 5.841263675689698,
|
|
"epoch": 0.270764442715425,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004995805176234571,
|
|
"loss": 5.719,
|
|
"mean_token_accuracy": 0.15163205564022064,
|
|
"num_tokens": 6052940.0,
|
|
"step": 3480
|
|
},
|
|
{
|
|
"entropy": 5.955672836303711,
|
|
"epoch": 0.2711534720871426,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004995788243021158,
|
|
"loss": 5.6464,
|
|
"mean_token_accuracy": 0.1543900951743126,
|
|
"num_tokens": 6062048.0,
|
|
"step": 3485
|
|
},
|
|
{
|
|
"entropy": 5.821571111679077,
|
|
"epoch": 0.27154250145886016,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004995771275731483,
|
|
"loss": 5.6629,
|
|
"mean_token_accuracy": 0.15446282178163528,
|
|
"num_tokens": 6071478.0,
|
|
"step": 3490
|
|
},
|
|
{
|
|
"entropy": 5.770304489135742,
|
|
"epoch": 0.2719315308305777,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004995754274365802,
|
|
"loss": 5.6095,
|
|
"mean_token_accuracy": 0.1592847764492035,
|
|
"num_tokens": 6080495.0,
|
|
"step": 3495
|
|
},
|
|
{
|
|
"entropy": 5.9197368144989015,
|
|
"epoch": 0.2723205602022953,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004995737238924376,
|
|
"loss": 5.7657,
|
|
"mean_token_accuracy": 0.14560676813125611,
|
|
"num_tokens": 6090141.0,
|
|
"step": 3500
|
|
},
|
|
{
|
|
"entropy": 5.924958324432373,
|
|
"epoch": 0.2727095895740128,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004995720169407461,
|
|
"loss": 5.7348,
|
|
"mean_token_accuracy": 0.14742055982351304,
|
|
"num_tokens": 6099215.0,
|
|
"step": 3505
|
|
},
|
|
{
|
|
"entropy": 5.9483616828918455,
|
|
"epoch": 0.2730986189457304,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004995703065815317,
|
|
"loss": 5.81,
|
|
"mean_token_accuracy": 0.1458706870675087,
|
|
"num_tokens": 6108802.0,
|
|
"step": 3510
|
|
},
|
|
{
|
|
"entropy": 5.9493061065673825,
|
|
"epoch": 0.273487648317448,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004995685928148203,
|
|
"loss": 5.7931,
|
|
"mean_token_accuracy": 0.15170633271336556,
|
|
"num_tokens": 6117486.0,
|
|
"step": 3515
|
|
},
|
|
{
|
|
"entropy": 5.855750560760498,
|
|
"epoch": 0.2738766776891655,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000499566875640638,
|
|
"loss": 5.6264,
|
|
"mean_token_accuracy": 0.16193919628858566,
|
|
"num_tokens": 6125248.0,
|
|
"step": 3520
|
|
},
|
|
{
|
|
"entropy": 5.890281057357788,
|
|
"epoch": 0.2742657070608831,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004995651550590108,
|
|
"loss": 5.6826,
|
|
"mean_token_accuracy": 0.1505290001630783,
|
|
"num_tokens": 6134831.0,
|
|
"step": 3525
|
|
},
|
|
{
|
|
"entropy": 5.8330237865448,
|
|
"epoch": 0.2746547364326007,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004995634310699647,
|
|
"loss": 5.7553,
|
|
"mean_token_accuracy": 0.14910198077559472,
|
|
"num_tokens": 6143248.0,
|
|
"step": 3530
|
|
},
|
|
{
|
|
"entropy": 5.999197769165039,
|
|
"epoch": 0.2750437658043182,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004995617036735261,
|
|
"loss": 5.7598,
|
|
"mean_token_accuracy": 0.14741272926330568,
|
|
"num_tokens": 6151768.0,
|
|
"step": 3535
|
|
},
|
|
{
|
|
"entropy": 5.901557064056396,
|
|
"epoch": 0.2754327951760358,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004995599728697211,
|
|
"loss": 5.6402,
|
|
"mean_token_accuracy": 0.15886410027742387,
|
|
"num_tokens": 6160091.0,
|
|
"step": 3540
|
|
},
|
|
{
|
|
"entropy": 5.8741230964660645,
|
|
"epoch": 0.27582182454775334,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004995582386585759,
|
|
"loss": 5.7691,
|
|
"mean_token_accuracy": 0.14154399782419205,
|
|
"num_tokens": 6169440.0,
|
|
"step": 3545
|
|
},
|
|
{
|
|
"entropy": 5.888131856918335,
|
|
"epoch": 0.2762108539194709,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004995565010401167,
|
|
"loss": 5.7,
|
|
"mean_token_accuracy": 0.15860531777143477,
|
|
"num_tokens": 6177604.0,
|
|
"step": 3550
|
|
},
|
|
{
|
|
"entropy": 5.918958330154419,
|
|
"epoch": 0.2765998832911885,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004995547600143702,
|
|
"loss": 5.7376,
|
|
"mean_token_accuracy": 0.1480049178004265,
|
|
"num_tokens": 6186252.0,
|
|
"step": 3555
|
|
},
|
|
{
|
|
"entropy": 5.8245594024658205,
|
|
"epoch": 0.27698891266290604,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004995530155813625,
|
|
"loss": 5.673,
|
|
"mean_token_accuracy": 0.15742629319429396,
|
|
"num_tokens": 6194641.0,
|
|
"step": 3560
|
|
},
|
|
{
|
|
"entropy": 5.962858867645264,
|
|
"epoch": 0.2773779420346236,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004995512677411203,
|
|
"loss": 5.8113,
|
|
"mean_token_accuracy": 0.15001470893621444,
|
|
"num_tokens": 6203925.0,
|
|
"step": 3565
|
|
},
|
|
{
|
|
"entropy": 5.938074159622192,
|
|
"epoch": 0.27776697140634116,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004995495164936698,
|
|
"loss": 5.6963,
|
|
"mean_token_accuracy": 0.1461140424013138,
|
|
"num_tokens": 6213001.0,
|
|
"step": 3570
|
|
},
|
|
{
|
|
"entropy": 5.865621948242188,
|
|
"epoch": 0.27815600077805874,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004995477618390381,
|
|
"loss": 5.719,
|
|
"mean_token_accuracy": 0.14504099935293197,
|
|
"num_tokens": 6221754.0,
|
|
"step": 3575
|
|
},
|
|
{
|
|
"entropy": 5.820681524276734,
|
|
"epoch": 0.27854503014977633,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004995460037772513,
|
|
"loss": 5.6025,
|
|
"mean_token_accuracy": 0.15609883069992064,
|
|
"num_tokens": 6229792.0,
|
|
"step": 3580
|
|
},
|
|
{
|
|
"entropy": 5.836638498306274,
|
|
"epoch": 0.27893405952149386,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004995442423083365,
|
|
"loss": 5.692,
|
|
"mean_token_accuracy": 0.15051042586565017,
|
|
"num_tokens": 6238839.0,
|
|
"step": 3585
|
|
},
|
|
{
|
|
"entropy": 5.886203908920288,
|
|
"epoch": 0.27932308889321145,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004995424774323201,
|
|
"loss": 5.6063,
|
|
"mean_token_accuracy": 0.15578331500291825,
|
|
"num_tokens": 6246939.0,
|
|
"step": 3590
|
|
},
|
|
{
|
|
"entropy": 5.932497596740722,
|
|
"epoch": 0.279712118264929,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.000499540709149229,
|
|
"loss": 5.7214,
|
|
"mean_token_accuracy": 0.15089464485645293,
|
|
"num_tokens": 6255858.0,
|
|
"step": 3595
|
|
},
|
|
{
|
|
"entropy": 5.822576379776001,
|
|
"epoch": 0.28010114763664656,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004995389374590901,
|
|
"loss": 5.6563,
|
|
"mean_token_accuracy": 0.1534334197640419,
|
|
"num_tokens": 6265137.0,
|
|
"step": 3600
|
|
},
|
|
{
|
|
"entropy": 5.808225059509278,
|
|
"epoch": 0.28049017700836415,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004995371623619301,
|
|
"loss": 5.6681,
|
|
"mean_token_accuracy": 0.15250518172979355,
|
|
"num_tokens": 6273286.0,
|
|
"step": 3605
|
|
},
|
|
{
|
|
"entropy": 5.808995914459229,
|
|
"epoch": 0.2808792063800817,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.000499535383857776,
|
|
"loss": 5.6894,
|
|
"mean_token_accuracy": 0.14724815487861634,
|
|
"num_tokens": 6282477.0,
|
|
"step": 3610
|
|
},
|
|
{
|
|
"entropy": 5.928357744216919,
|
|
"epoch": 0.28126823575179927,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000499533601946655,
|
|
"loss": 5.7126,
|
|
"mean_token_accuracy": 0.15294745415449143,
|
|
"num_tokens": 6291756.0,
|
|
"step": 3615
|
|
},
|
|
{
|
|
"entropy": 5.898259210586548,
|
|
"epoch": 0.2816572651235168,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004995318166285938,
|
|
"loss": 5.798,
|
|
"mean_token_accuracy": 0.14731436520814895,
|
|
"num_tokens": 6301093.0,
|
|
"step": 3620
|
|
},
|
|
{
|
|
"entropy": 5.861028814315796,
|
|
"epoch": 0.2820462944952344,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004995300279036199,
|
|
"loss": 5.6083,
|
|
"mean_token_accuracy": 0.1591477006673813,
|
|
"num_tokens": 6310379.0,
|
|
"step": 3625
|
|
},
|
|
{
|
|
"entropy": 5.835546207427979,
|
|
"epoch": 0.28243532386695197,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00049952823577176,
|
|
"loss": 5.6365,
|
|
"mean_token_accuracy": 0.1520713210105896,
|
|
"num_tokens": 6318983.0,
|
|
"step": 3630
|
|
},
|
|
{
|
|
"entropy": 5.810934829711914,
|
|
"epoch": 0.2828243532386695,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004995264402330416,
|
|
"loss": 5.6283,
|
|
"mean_token_accuracy": 0.15358254462480544,
|
|
"num_tokens": 6327816.0,
|
|
"step": 3635
|
|
},
|
|
{
|
|
"entropy": 5.81642746925354,
|
|
"epoch": 0.2832133826103871,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004995246412874919,
|
|
"loss": 5.7195,
|
|
"mean_token_accuracy": 0.14997470676898955,
|
|
"num_tokens": 6336693.0,
|
|
"step": 3640
|
|
},
|
|
{
|
|
"entropy": 5.894272804260254,
|
|
"epoch": 0.2836024119821047,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000499522838935138,
|
|
"loss": 5.654,
|
|
"mean_token_accuracy": 0.15607268661260604,
|
|
"num_tokens": 6345456.0,
|
|
"step": 3645
|
|
},
|
|
{
|
|
"entropy": 5.843640661239624,
|
|
"epoch": 0.2839914413538222,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004995210331760074,
|
|
"loss": 5.6625,
|
|
"mean_token_accuracy": 0.15668386667966844,
|
|
"num_tokens": 6353584.0,
|
|
"step": 3650
|
|
},
|
|
{
|
|
"entropy": 5.790026140213013,
|
|
"epoch": 0.2843804707255398,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004995192240101275,
|
|
"loss": 5.6837,
|
|
"mean_token_accuracy": 0.15414109826087952,
|
|
"num_tokens": 6362258.0,
|
|
"step": 3655
|
|
},
|
|
{
|
|
"entropy": 5.861711740493774,
|
|
"epoch": 0.2847695000972573,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004995174114375258,
|
|
"loss": 5.5981,
|
|
"mean_token_accuracy": 0.1548761434853077,
|
|
"num_tokens": 6371373.0,
|
|
"step": 3660
|
|
},
|
|
{
|
|
"entropy": 5.858789396286011,
|
|
"epoch": 0.2851585294689749,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004995155954582297,
|
|
"loss": 5.6692,
|
|
"mean_token_accuracy": 0.15796693712472915,
|
|
"num_tokens": 6380431.0,
|
|
"step": 3665
|
|
},
|
|
{
|
|
"entropy": 5.9123118877410885,
|
|
"epoch": 0.2855475588406925,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004995137760722668,
|
|
"loss": 5.8339,
|
|
"mean_token_accuracy": 0.1537206545472145,
|
|
"num_tokens": 6389305.0,
|
|
"step": 3670
|
|
},
|
|
{
|
|
"entropy": 5.910440301895141,
|
|
"epoch": 0.28593658821241,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004995119532796646,
|
|
"loss": 5.6487,
|
|
"mean_token_accuracy": 0.16165258288383483,
|
|
"num_tokens": 6397065.0,
|
|
"step": 3675
|
|
},
|
|
{
|
|
"entropy": 5.873527336120605,
|
|
"epoch": 0.2863256175841276,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.000499510127080451,
|
|
"loss": 5.7825,
|
|
"mean_token_accuracy": 0.14846334755420684,
|
|
"num_tokens": 6407053.0,
|
|
"step": 3680
|
|
},
|
|
{
|
|
"entropy": 5.942921543121338,
|
|
"epoch": 0.28671464695584514,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004995082974746535,
|
|
"loss": 5.7547,
|
|
"mean_token_accuracy": 0.15207315981388092,
|
|
"num_tokens": 6415165.0,
|
|
"step": 3685
|
|
},
|
|
{
|
|
"entropy": 5.920436811447144,
|
|
"epoch": 0.28710367632756273,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004995064644622999,
|
|
"loss": 5.7195,
|
|
"mean_token_accuracy": 0.15774022042751312,
|
|
"num_tokens": 6423646.0,
|
|
"step": 3690
|
|
},
|
|
{
|
|
"entropy": 5.878801870346069,
|
|
"epoch": 0.2874927056992803,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004995046280434181,
|
|
"loss": 5.7397,
|
|
"mean_token_accuracy": 0.15159983560442924,
|
|
"num_tokens": 6432134.0,
|
|
"step": 3695
|
|
},
|
|
{
|
|
"entropy": 5.874917507171631,
|
|
"epoch": 0.28788173507099785,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004995027882180358,
|
|
"loss": 5.6316,
|
|
"mean_token_accuracy": 0.15305832773447037,
|
|
"num_tokens": 6440456.0,
|
|
"step": 3700
|
|
},
|
|
{
|
|
"entropy": 5.871138191223144,
|
|
"epoch": 0.28827076444271543,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004995009449861812,
|
|
"loss": 5.7239,
|
|
"mean_token_accuracy": 0.14909188747406005,
|
|
"num_tokens": 6448952.0,
|
|
"step": 3705
|
|
},
|
|
{
|
|
"entropy": 5.826206254959106,
|
|
"epoch": 0.28865979381443296,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.000499499098347882,
|
|
"loss": 5.5762,
|
|
"mean_token_accuracy": 0.16490093022584915,
|
|
"num_tokens": 6457225.0,
|
|
"step": 3710
|
|
},
|
|
{
|
|
"entropy": 5.855531024932861,
|
|
"epoch": 0.28904882318615055,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004994972483031662,
|
|
"loss": 5.7151,
|
|
"mean_token_accuracy": 0.15100376009941102,
|
|
"num_tokens": 6465450.0,
|
|
"step": 3715
|
|
},
|
|
{
|
|
"entropy": 5.889287090301513,
|
|
"epoch": 0.28943785255786814,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000499495394852062,
|
|
"loss": 5.7457,
|
|
"mean_token_accuracy": 0.14744992554187775,
|
|
"num_tokens": 6473736.0,
|
|
"step": 3720
|
|
},
|
|
{
|
|
"entropy": 5.866313505172729,
|
|
"epoch": 0.28982688192958567,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004994935379945977,
|
|
"loss": 5.6836,
|
|
"mean_token_accuracy": 0.1602819576859474,
|
|
"num_tokens": 6482092.0,
|
|
"step": 3725
|
|
},
|
|
{
|
|
"entropy": 5.882090663909912,
|
|
"epoch": 0.29021591130130325,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004994916777308012,
|
|
"loss": 5.689,
|
|
"mean_token_accuracy": 0.15607897639274598,
|
|
"num_tokens": 6490704.0,
|
|
"step": 3730
|
|
},
|
|
{
|
|
"entropy": 5.948546314239502,
|
|
"epoch": 0.29060494067302084,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004994898140607007,
|
|
"loss": 5.6464,
|
|
"mean_token_accuracy": 0.15812035351991655,
|
|
"num_tokens": 6499634.0,
|
|
"step": 3735
|
|
},
|
|
{
|
|
"entropy": 5.787464141845703,
|
|
"epoch": 0.29099397004473837,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004994879469843247,
|
|
"loss": 5.7928,
|
|
"mean_token_accuracy": 0.14925210997462274,
|
|
"num_tokens": 6509261.0,
|
|
"step": 3740
|
|
},
|
|
{
|
|
"entropy": 5.8902843475341795,
|
|
"epoch": 0.29138299941645596,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004994860765017013,
|
|
"loss": 5.6551,
|
|
"mean_token_accuracy": 0.15220843628048897,
|
|
"num_tokens": 6517542.0,
|
|
"step": 3745
|
|
},
|
|
{
|
|
"entropy": 5.859212160110474,
|
|
"epoch": 0.2917720287881735,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000499484202612859,
|
|
"loss": 5.6222,
|
|
"mean_token_accuracy": 0.15824688225984573,
|
|
"num_tokens": 6525945.0,
|
|
"step": 3750
|
|
},
|
|
{
|
|
"entropy": 5.767728281021118,
|
|
"epoch": 0.2921610581598911,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004994823253178264,
|
|
"loss": 5.6484,
|
|
"mean_token_accuracy": 0.15464899092912673,
|
|
"num_tokens": 6534744.0,
|
|
"step": 3755
|
|
},
|
|
{
|
|
"entropy": 5.840261554718017,
|
|
"epoch": 0.29255008753160866,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004994804446166317,
|
|
"loss": 5.608,
|
|
"mean_token_accuracy": 0.16365491300821305,
|
|
"num_tokens": 6542640.0,
|
|
"step": 3760
|
|
},
|
|
{
|
|
"entropy": 5.834035968780517,
|
|
"epoch": 0.2929391169033262,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004994785605093035,
|
|
"loss": 5.6865,
|
|
"mean_token_accuracy": 0.15791385620832443,
|
|
"num_tokens": 6551292.0,
|
|
"step": 3765
|
|
},
|
|
{
|
|
"entropy": 5.875267362594604,
|
|
"epoch": 0.2933281462750438,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004994766729958705,
|
|
"loss": 5.7566,
|
|
"mean_token_accuracy": 0.15267640203237534,
|
|
"num_tokens": 6560760.0,
|
|
"step": 3770
|
|
},
|
|
{
|
|
"entropy": 5.959283542633057,
|
|
"epoch": 0.2937171756467613,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004994747820763612,
|
|
"loss": 5.7681,
|
|
"mean_token_accuracy": 0.14788751378655435,
|
|
"num_tokens": 6570618.0,
|
|
"step": 3775
|
|
},
|
|
{
|
|
"entropy": 5.8953528881073,
|
|
"epoch": 0.2941062050184789,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004994728877508046,
|
|
"loss": 5.6382,
|
|
"mean_token_accuracy": 0.15356697887182236,
|
|
"num_tokens": 6579484.0,
|
|
"step": 3780
|
|
},
|
|
{
|
|
"entropy": 5.866683626174927,
|
|
"epoch": 0.2944952343901965,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004994709900192289,
|
|
"loss": 5.685,
|
|
"mean_token_accuracy": 0.15228400826454164,
|
|
"num_tokens": 6588531.0,
|
|
"step": 3785
|
|
},
|
|
{
|
|
"entropy": 5.870986700057983,
|
|
"epoch": 0.294884263761914,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004994690888816635,
|
|
"loss": 5.7556,
|
|
"mean_token_accuracy": 0.15102168917655945,
|
|
"num_tokens": 6596862.0,
|
|
"step": 3790
|
|
},
|
|
{
|
|
"entropy": 5.837507677078247,
|
|
"epoch": 0.2952732931336316,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004994671843381367,
|
|
"loss": 5.6501,
|
|
"mean_token_accuracy": 0.15472938120365143,
|
|
"num_tokens": 6605594.0,
|
|
"step": 3795
|
|
},
|
|
{
|
|
"entropy": 5.914930200576782,
|
|
"epoch": 0.29566232250534913,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004994652763886778,
|
|
"loss": 5.7024,
|
|
"mean_token_accuracy": 0.15655220597982406,
|
|
"num_tokens": 6613971.0,
|
|
"step": 3800
|
|
},
|
|
{
|
|
"entropy": 5.853056573867798,
|
|
"epoch": 0.2960513518770667,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004994633650333155,
|
|
"loss": 5.7753,
|
|
"mean_token_accuracy": 0.14286859333515167,
|
|
"num_tokens": 6623116.0,
|
|
"step": 3805
|
|
},
|
|
{
|
|
"entropy": 5.893979835510254,
|
|
"epoch": 0.2964403812487843,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004994614502720792,
|
|
"loss": 5.6422,
|
|
"mean_token_accuracy": 0.15770183503627777,
|
|
"num_tokens": 6631910.0,
|
|
"step": 3810
|
|
},
|
|
{
|
|
"entropy": 5.836010408401489,
|
|
"epoch": 0.29682941062050183,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004994595321049974,
|
|
"loss": 5.6728,
|
|
"mean_token_accuracy": 0.16161404103040694,
|
|
"num_tokens": 6640882.0,
|
|
"step": 3815
|
|
},
|
|
{
|
|
"entropy": 5.913960695266724,
|
|
"epoch": 0.2972184399922194,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004994576105320994,
|
|
"loss": 5.7609,
|
|
"mean_token_accuracy": 0.15119977593421935,
|
|
"num_tokens": 6649665.0,
|
|
"step": 3820
|
|
},
|
|
{
|
|
"entropy": 5.831139135360718,
|
|
"epoch": 0.29760746936393695,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004994556855534146,
|
|
"loss": 5.5195,
|
|
"mean_token_accuracy": 0.16653952449560167,
|
|
"num_tokens": 6658725.0,
|
|
"step": 3825
|
|
},
|
|
{
|
|
"entropy": 5.727788639068604,
|
|
"epoch": 0.29799649873565454,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004994537571689719,
|
|
"loss": 5.5859,
|
|
"mean_token_accuracy": 0.1621174305677414,
|
|
"num_tokens": 6667403.0,
|
|
"step": 3830
|
|
},
|
|
{
|
|
"entropy": 5.896328401565552,
|
|
"epoch": 0.2983855281073721,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004994518253788007,
|
|
"loss": 5.6751,
|
|
"mean_token_accuracy": 0.14980594515800477,
|
|
"num_tokens": 6676673.0,
|
|
"step": 3835
|
|
},
|
|
{
|
|
"entropy": 5.914979743957519,
|
|
"epoch": 0.29877455747908965,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004994498901829304,
|
|
"loss": 5.6809,
|
|
"mean_token_accuracy": 0.14734249114990233,
|
|
"num_tokens": 6686212.0,
|
|
"step": 3840
|
|
},
|
|
{
|
|
"entropy": 5.779385614395141,
|
|
"epoch": 0.29916358685080724,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004994479515813903,
|
|
"loss": 5.6692,
|
|
"mean_token_accuracy": 0.15411499589681626,
|
|
"num_tokens": 6694812.0,
|
|
"step": 3845
|
|
},
|
|
{
|
|
"entropy": 5.871626520156861,
|
|
"epoch": 0.2995526162225248,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004994460095742096,
|
|
"loss": 5.644,
|
|
"mean_token_accuracy": 0.15434655100107192,
|
|
"num_tokens": 6703439.0,
|
|
"step": 3850
|
|
},
|
|
{
|
|
"entropy": 5.924510478973389,
|
|
"epoch": 0.29994164559424236,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000499444064161418,
|
|
"loss": 5.6178,
|
|
"mean_token_accuracy": 0.15686172991991043,
|
|
"num_tokens": 6711465.0,
|
|
"step": 3855
|
|
},
|
|
{
|
|
"entropy": 5.810085678100586,
|
|
"epoch": 0.30033067496595994,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.000499442115343045,
|
|
"loss": 5.6527,
|
|
"mean_token_accuracy": 0.15281544029712676,
|
|
"num_tokens": 6720526.0,
|
|
"step": 3860
|
|
},
|
|
{
|
|
"entropy": 5.945318651199341,
|
|
"epoch": 0.3007197043376775,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004994401631191202,
|
|
"loss": 5.8317,
|
|
"mean_token_accuracy": 0.144597065448761,
|
|
"num_tokens": 6728696.0,
|
|
"step": 3865
|
|
},
|
|
{
|
|
"entropy": 5.861696434020996,
|
|
"epoch": 0.30110873370939506,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004994382074896731,
|
|
"loss": 5.6847,
|
|
"mean_token_accuracy": 0.15377849191427231,
|
|
"num_tokens": 6737955.0,
|
|
"step": 3870
|
|
},
|
|
{
|
|
"entropy": 5.861507368087769,
|
|
"epoch": 0.30149776308111265,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004994362484547335,
|
|
"loss": 5.7587,
|
|
"mean_token_accuracy": 0.14718077778816224,
|
|
"num_tokens": 6746413.0,
|
|
"step": 3875
|
|
},
|
|
{
|
|
"entropy": 5.825746250152588,
|
|
"epoch": 0.3018867924528302,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004994342860143309,
|
|
"loss": 5.6077,
|
|
"mean_token_accuracy": 0.15988363325595856,
|
|
"num_tokens": 6754341.0,
|
|
"step": 3880
|
|
},
|
|
{
|
|
"entropy": 5.749278116226196,
|
|
"epoch": 0.30227582182454776,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004994323201684953,
|
|
"loss": 5.4758,
|
|
"mean_token_accuracy": 0.16771773397922515,
|
|
"num_tokens": 6762623.0,
|
|
"step": 3885
|
|
},
|
|
{
|
|
"entropy": 5.770840740203857,
|
|
"epoch": 0.3026648511962653,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004994303509172566,
|
|
"loss": 5.6348,
|
|
"mean_token_accuracy": 0.15647213906049728,
|
|
"num_tokens": 6771270.0,
|
|
"step": 3890
|
|
},
|
|
{
|
|
"entropy": 5.861431550979614,
|
|
"epoch": 0.3030538805679829,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004994283782606444,
|
|
"loss": 5.7011,
|
|
"mean_token_accuracy": 0.15365937054157258,
|
|
"num_tokens": 6780292.0,
|
|
"step": 3895
|
|
},
|
|
{
|
|
"entropy": 5.876373672485352,
|
|
"epoch": 0.30344290993970047,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004994264021986888,
|
|
"loss": 5.5906,
|
|
"mean_token_accuracy": 0.15858400166034697,
|
|
"num_tokens": 6788580.0,
|
|
"step": 3900
|
|
},
|
|
{
|
|
"entropy": 5.7274853706359865,
|
|
"epoch": 0.303831939311418,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004994244227314197,
|
|
"loss": 5.5919,
|
|
"mean_token_accuracy": 0.1546170249581337,
|
|
"num_tokens": 6796801.0,
|
|
"step": 3905
|
|
},
|
|
{
|
|
"entropy": 5.832391262054443,
|
|
"epoch": 0.3042209686831356,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004994224398588672,
|
|
"loss": 5.5681,
|
|
"mean_token_accuracy": 0.15856126993894576,
|
|
"num_tokens": 6805630.0,
|
|
"step": 3910
|
|
},
|
|
{
|
|
"entropy": 5.711365795135498,
|
|
"epoch": 0.3046099980548531,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004994204535810615,
|
|
"loss": 5.5667,
|
|
"mean_token_accuracy": 0.1602591648697853,
|
|
"num_tokens": 6814316.0,
|
|
"step": 3915
|
|
},
|
|
{
|
|
"entropy": 5.901001930236816,
|
|
"epoch": 0.3049990274265707,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004994184638980326,
|
|
"loss": 5.7496,
|
|
"mean_token_accuracy": 0.14583035409450532,
|
|
"num_tokens": 6823224.0,
|
|
"step": 3920
|
|
},
|
|
{
|
|
"entropy": 5.900492429733276,
|
|
"epoch": 0.3053880567982883,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004994164708098107,
|
|
"loss": 5.7687,
|
|
"mean_token_accuracy": 0.14870935082435607,
|
|
"num_tokens": 6832104.0,
|
|
"step": 3925
|
|
},
|
|
{
|
|
"entropy": 5.882292079925537,
|
|
"epoch": 0.3057770861700058,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000499414474316426,
|
|
"loss": 5.6663,
|
|
"mean_token_accuracy": 0.15271729081869126,
|
|
"num_tokens": 6841208.0,
|
|
"step": 3930
|
|
},
|
|
{
|
|
"entropy": 5.716450595855713,
|
|
"epoch": 0.3061661155417234,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004994124744179088,
|
|
"loss": 5.4771,
|
|
"mean_token_accuracy": 0.1640233539044857,
|
|
"num_tokens": 6849622.0,
|
|
"step": 3935
|
|
},
|
|
{
|
|
"entropy": 5.802888536453247,
|
|
"epoch": 0.306555144913441,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004994104711142896,
|
|
"loss": 5.667,
|
|
"mean_token_accuracy": 0.1617858126759529,
|
|
"num_tokens": 6857355.0,
|
|
"step": 3940
|
|
},
|
|
{
|
|
"entropy": 5.862309074401855,
|
|
"epoch": 0.3069441742851585,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004994084644055986,
|
|
"loss": 5.6882,
|
|
"mean_token_accuracy": 0.16067038625478744,
|
|
"num_tokens": 6866173.0,
|
|
"step": 3945
|
|
},
|
|
{
|
|
"entropy": 5.831095552444458,
|
|
"epoch": 0.3073332036568761,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004994064542918664,
|
|
"loss": 5.6897,
|
|
"mean_token_accuracy": 0.14933566004037857,
|
|
"num_tokens": 6874438.0,
|
|
"step": 3950
|
|
},
|
|
{
|
|
"entropy": 5.8412987232208256,
|
|
"epoch": 0.30772223302859364,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004994044407731235,
|
|
"loss": 5.6868,
|
|
"mean_token_accuracy": 0.1510934755206108,
|
|
"num_tokens": 6882790.0,
|
|
"step": 3955
|
|
},
|
|
{
|
|
"entropy": 5.82961597442627,
|
|
"epoch": 0.3081112624003112,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004994024238494002,
|
|
"loss": 5.7089,
|
|
"mean_token_accuracy": 0.14658345580101012,
|
|
"num_tokens": 6891375.0,
|
|
"step": 3960
|
|
},
|
|
{
|
|
"entropy": 5.759390592575073,
|
|
"epoch": 0.3085002917720288,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004994004035207274,
|
|
"loss": 5.6294,
|
|
"mean_token_accuracy": 0.15769621059298516,
|
|
"num_tokens": 6899510.0,
|
|
"step": 3965
|
|
},
|
|
{
|
|
"entropy": 5.903188896179199,
|
|
"epoch": 0.30888932114374634,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004993983797871356,
|
|
"loss": 5.6657,
|
|
"mean_token_accuracy": 0.16147721111774443,
|
|
"num_tokens": 6908311.0,
|
|
"step": 3970
|
|
},
|
|
{
|
|
"entropy": 5.7780393123626705,
|
|
"epoch": 0.30927835051546393,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004993963526486555,
|
|
"loss": 5.6269,
|
|
"mean_token_accuracy": 0.15729546844959258,
|
|
"num_tokens": 6917064.0,
|
|
"step": 3975
|
|
},
|
|
{
|
|
"entropy": 5.798044586181641,
|
|
"epoch": 0.30966737988718146,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000499394322105318,
|
|
"loss": 5.6218,
|
|
"mean_token_accuracy": 0.15905228704214097,
|
|
"num_tokens": 6925705.0,
|
|
"step": 3980
|
|
},
|
|
{
|
|
"entropy": 5.966913938522339,
|
|
"epoch": 0.31005640925889905,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004993922881571538,
|
|
"loss": 5.7681,
|
|
"mean_token_accuracy": 0.15229437053203582,
|
|
"num_tokens": 6934232.0,
|
|
"step": 3985
|
|
},
|
|
{
|
|
"entropy": 5.856652116775512,
|
|
"epoch": 0.31044543863061663,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004993902508041939,
|
|
"loss": 5.7042,
|
|
"mean_token_accuracy": 0.15216735154390335,
|
|
"num_tokens": 6943143.0,
|
|
"step": 3990
|
|
},
|
|
{
|
|
"entropy": 5.810306692123413,
|
|
"epoch": 0.31083446800233416,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000499388210046469,
|
|
"loss": 5.5627,
|
|
"mean_token_accuracy": 0.16006666719913482,
|
|
"num_tokens": 6951613.0,
|
|
"step": 3995
|
|
},
|
|
{
|
|
"entropy": 5.857361268997193,
|
|
"epoch": 0.31122349737405175,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004993861658840102,
|
|
"loss": 5.7684,
|
|
"mean_token_accuracy": 0.15314728766679764,
|
|
"num_tokens": 6960531.0,
|
|
"step": 4000
|
|
},
|
|
{
|
|
"entropy": 5.887679243087769,
|
|
"epoch": 0.3116125267457693,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004993841183168484,
|
|
"loss": 5.7085,
|
|
"mean_token_accuracy": 0.1506664499640465,
|
|
"num_tokens": 6969211.0,
|
|
"step": 4005
|
|
},
|
|
{
|
|
"entropy": 5.951841020584107,
|
|
"epoch": 0.31200155611748687,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004993820673450148,
|
|
"loss": 5.7152,
|
|
"mean_token_accuracy": 0.15019422471523286,
|
|
"num_tokens": 6978414.0,
|
|
"step": 4010
|
|
},
|
|
{
|
|
"entropy": 5.760093832015992,
|
|
"epoch": 0.31239058548920445,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004993800129685404,
|
|
"loss": 5.4743,
|
|
"mean_token_accuracy": 0.16152779161930084,
|
|
"num_tokens": 6987350.0,
|
|
"step": 4015
|
|
},
|
|
{
|
|
"entropy": 5.764507198333741,
|
|
"epoch": 0.312779614860922,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004993779551874565,
|
|
"loss": 5.6139,
|
|
"mean_token_accuracy": 0.16373926550149917,
|
|
"num_tokens": 6995817.0,
|
|
"step": 4020
|
|
},
|
|
{
|
|
"entropy": 5.849539089202881,
|
|
"epoch": 0.31316864423263957,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004993758940017943,
|
|
"loss": 5.7027,
|
|
"mean_token_accuracy": 0.15734892040491105,
|
|
"num_tokens": 7004454.0,
|
|
"step": 4025
|
|
},
|
|
{
|
|
"entropy": 5.8294881820678714,
|
|
"epoch": 0.31355767360435716,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000499373829411585,
|
|
"loss": 5.6349,
|
|
"mean_token_accuracy": 0.15659935623407364,
|
|
"num_tokens": 7012126.0,
|
|
"step": 4030
|
|
},
|
|
{
|
|
"entropy": 5.804521131515503,
|
|
"epoch": 0.3139467029760747,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00049937176141686,
|
|
"loss": 5.7087,
|
|
"mean_token_accuracy": 0.1532567746937275,
|
|
"num_tokens": 7021232.0,
|
|
"step": 4035
|
|
},
|
|
{
|
|
"entropy": 5.915135192871094,
|
|
"epoch": 0.3143357323477923,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004993696900176506,
|
|
"loss": 5.6783,
|
|
"mean_token_accuracy": 0.157207453250885,
|
|
"num_tokens": 7029488.0,
|
|
"step": 4040
|
|
},
|
|
{
|
|
"entropy": 5.854561281204224,
|
|
"epoch": 0.3147247617195098,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004993676152139883,
|
|
"loss": 5.7137,
|
|
"mean_token_accuracy": 0.15398113429546356,
|
|
"num_tokens": 7037323.0,
|
|
"step": 4045
|
|
},
|
|
{
|
|
"entropy": 5.821354532241822,
|
|
"epoch": 0.3151137910912274,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004993655370059046,
|
|
"loss": 5.6607,
|
|
"mean_token_accuracy": 0.15085252672433852,
|
|
"num_tokens": 7045754.0,
|
|
"step": 4050
|
|
},
|
|
{
|
|
"entropy": 5.828005409240722,
|
|
"epoch": 0.315502820462945,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004993634553934309,
|
|
"loss": 5.6072,
|
|
"mean_token_accuracy": 0.15728428959846497,
|
|
"num_tokens": 7054026.0,
|
|
"step": 4055
|
|
},
|
|
{
|
|
"entropy": 5.775190687179565,
|
|
"epoch": 0.3158918498346625,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004993613703765989,
|
|
"loss": 5.6563,
|
|
"mean_token_accuracy": 0.1554763376712799,
|
|
"num_tokens": 7063383.0,
|
|
"step": 4060
|
|
},
|
|
{
|
|
"entropy": 5.774190759658813,
|
|
"epoch": 0.3162808792063801,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004993592819554402,
|
|
"loss": 5.6079,
|
|
"mean_token_accuracy": 0.15743849724531173,
|
|
"num_tokens": 7071952.0,
|
|
"step": 4065
|
|
},
|
|
{
|
|
"entropy": 5.906689405441284,
|
|
"epoch": 0.3166699085780976,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004993571901299866,
|
|
"loss": 5.6592,
|
|
"mean_token_accuracy": 0.15330417454242706,
|
|
"num_tokens": 7080283.0,
|
|
"step": 4070
|
|
},
|
|
{
|
|
"entropy": 5.720599365234375,
|
|
"epoch": 0.3170589379498152,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004993550949002697,
|
|
"loss": 5.5985,
|
|
"mean_token_accuracy": 0.1576405480504036,
|
|
"num_tokens": 7088669.0,
|
|
"step": 4075
|
|
},
|
|
{
|
|
"entropy": 5.744790935516358,
|
|
"epoch": 0.3174479673215328,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004993529962663213,
|
|
"loss": 5.4941,
|
|
"mean_token_accuracy": 0.16759186685085298,
|
|
"num_tokens": 7097201.0,
|
|
"step": 4080
|
|
},
|
|
{
|
|
"entropy": 5.780264663696289,
|
|
"epoch": 0.31783699669325033,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004993508942281732,
|
|
"loss": 5.6673,
|
|
"mean_token_accuracy": 0.1554343432188034,
|
|
"num_tokens": 7106509.0,
|
|
"step": 4085
|
|
},
|
|
{
|
|
"entropy": 5.802187919616699,
|
|
"epoch": 0.3182260260649679,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004993487887858575,
|
|
"loss": 5.5852,
|
|
"mean_token_accuracy": 0.15869487822055817,
|
|
"num_tokens": 7114550.0,
|
|
"step": 4090
|
|
},
|
|
{
|
|
"entropy": 5.869193267822266,
|
|
"epoch": 0.31861505543668545,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.000499346679939406,
|
|
"loss": 5.6906,
|
|
"mean_token_accuracy": 0.1567075952887535,
|
|
"num_tokens": 7122875.0,
|
|
"step": 4095
|
|
},
|
|
{
|
|
"entropy": 5.796186923980713,
|
|
"epoch": 0.31900408480840303,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004993445676888507,
|
|
"loss": 5.5196,
|
|
"mean_token_accuracy": 0.15808596462011337,
|
|
"num_tokens": 7132263.0,
|
|
"step": 4100
|
|
},
|
|
{
|
|
"entropy": 5.770897054672242,
|
|
"epoch": 0.3193931141801206,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004993424520342236,
|
|
"loss": 5.7299,
|
|
"mean_token_accuracy": 0.1540067285299301,
|
|
"num_tokens": 7141448.0,
|
|
"step": 4105
|
|
},
|
|
{
|
|
"entropy": 5.788070201873779,
|
|
"epoch": 0.31978214355183815,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004993403329755569,
|
|
"loss": 5.7435,
|
|
"mean_token_accuracy": 0.150648832321167,
|
|
"num_tokens": 7151021.0,
|
|
"step": 4110
|
|
},
|
|
{
|
|
"entropy": 5.9307338237762455,
|
|
"epoch": 0.32017117292355574,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004993382105128828,
|
|
"loss": 5.6856,
|
|
"mean_token_accuracy": 0.15276920050382614,
|
|
"num_tokens": 7160103.0,
|
|
"step": 4115
|
|
},
|
|
{
|
|
"entropy": 5.851531457901001,
|
|
"epoch": 0.32056020229527327,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004993360846462333,
|
|
"loss": 5.684,
|
|
"mean_token_accuracy": 0.1464504860341549,
|
|
"num_tokens": 7169003.0,
|
|
"step": 4120
|
|
},
|
|
{
|
|
"entropy": 5.868911981582642,
|
|
"epoch": 0.32094923166699085,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004993339553756408,
|
|
"loss": 5.7073,
|
|
"mean_token_accuracy": 0.15806739404797554,
|
|
"num_tokens": 7177086.0,
|
|
"step": 4125
|
|
},
|
|
{
|
|
"entropy": 5.821856737136841,
|
|
"epoch": 0.32133826103870844,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004993318227011378,
|
|
"loss": 5.5928,
|
|
"mean_token_accuracy": 0.1515570119023323,
|
|
"num_tokens": 7185772.0,
|
|
"step": 4130
|
|
},
|
|
{
|
|
"entropy": 5.877510070800781,
|
|
"epoch": 0.32172729041042597,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004993296866227562,
|
|
"loss": 5.7268,
|
|
"mean_token_accuracy": 0.15518796890974046,
|
|
"num_tokens": 7194394.0,
|
|
"step": 4135
|
|
},
|
|
{
|
|
"entropy": 5.814974594116211,
|
|
"epoch": 0.32211631978214356,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004993275471405288,
|
|
"loss": 5.5416,
|
|
"mean_token_accuracy": 0.16767876148223876,
|
|
"num_tokens": 7202143.0,
|
|
"step": 4140
|
|
},
|
|
{
|
|
"entropy": 5.752964830398559,
|
|
"epoch": 0.32250534915386114,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004993254042544879,
|
|
"loss": 5.6563,
|
|
"mean_token_accuracy": 0.15957320481538773,
|
|
"num_tokens": 7210645.0,
|
|
"step": 4145
|
|
},
|
|
{
|
|
"entropy": 5.827418470382691,
|
|
"epoch": 0.3228943785255787,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000499323257964666,
|
|
"loss": 5.6102,
|
|
"mean_token_accuracy": 0.15694079846143721,
|
|
"num_tokens": 7218872.0,
|
|
"step": 4150
|
|
},
|
|
{
|
|
"entropy": 5.85628924369812,
|
|
"epoch": 0.32328340789729626,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004993211082710957,
|
|
"loss": 5.7646,
|
|
"mean_token_accuracy": 0.15412936508655548,
|
|
"num_tokens": 7226977.0,
|
|
"step": 4155
|
|
},
|
|
{
|
|
"entropy": 5.872501277923584,
|
|
"epoch": 0.3236724372690138,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004993189551738097,
|
|
"loss": 5.6297,
|
|
"mean_token_accuracy": 0.15481510162353515,
|
|
"num_tokens": 7235635.0,
|
|
"step": 4160
|
|
},
|
|
{
|
|
"entropy": 5.795789957046509,
|
|
"epoch": 0.3240614666407314,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004993167986728405,
|
|
"loss": 5.6128,
|
|
"mean_token_accuracy": 0.15973446071147918,
|
|
"num_tokens": 7244506.0,
|
|
"step": 4165
|
|
},
|
|
{
|
|
"entropy": 5.761918640136718,
|
|
"epoch": 0.32445049601244896,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000499314638768221,
|
|
"loss": 5.6392,
|
|
"mean_token_accuracy": 0.15619633570313454,
|
|
"num_tokens": 7252883.0,
|
|
"step": 4170
|
|
},
|
|
{
|
|
"entropy": 5.842187452316284,
|
|
"epoch": 0.3248395253841665,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004993124754599839,
|
|
"loss": 5.5918,
|
|
"mean_token_accuracy": 0.15565370470285417,
|
|
"num_tokens": 7261580.0,
|
|
"step": 4175
|
|
},
|
|
{
|
|
"entropy": 5.822684812545776,
|
|
"epoch": 0.3252285547558841,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004993103087481619,
|
|
"loss": 5.6841,
|
|
"mean_token_accuracy": 0.15471784621477128,
|
|
"num_tokens": 7270346.0,
|
|
"step": 4180
|
|
},
|
|
{
|
|
"entropy": 5.890071296691895,
|
|
"epoch": 0.3256175841276016,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004993081386327881,
|
|
"loss": 5.7574,
|
|
"mean_token_accuracy": 0.15108644515275954,
|
|
"num_tokens": 7279393.0,
|
|
"step": 4185
|
|
},
|
|
{
|
|
"entropy": 5.797246932983398,
|
|
"epoch": 0.3260066134993192,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004993059651138953,
|
|
"loss": 5.582,
|
|
"mean_token_accuracy": 0.15682794600725175,
|
|
"num_tokens": 7287929.0,
|
|
"step": 4190
|
|
},
|
|
{
|
|
"entropy": 5.854136514663696,
|
|
"epoch": 0.3263956428710368,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004993037881915165,
|
|
"loss": 5.6517,
|
|
"mean_token_accuracy": 0.1567692741751671,
|
|
"num_tokens": 7296336.0,
|
|
"step": 4195
|
|
},
|
|
{
|
|
"entropy": 5.7092649936676025,
|
|
"epoch": 0.3267846722427543,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004993016078656847,
|
|
"loss": 5.5201,
|
|
"mean_token_accuracy": 0.16174272447824478,
|
|
"num_tokens": 7304624.0,
|
|
"step": 4200
|
|
},
|
|
{
|
|
"entropy": 5.767000961303711,
|
|
"epoch": 0.3271737016144719,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000499299424136433,
|
|
"loss": 5.6565,
|
|
"mean_token_accuracy": 0.15455140471458434,
|
|
"num_tokens": 7312945.0,
|
|
"step": 4205
|
|
},
|
|
{
|
|
"entropy": 5.832268762588501,
|
|
"epoch": 0.32756273098618943,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004992972370037946,
|
|
"loss": 5.5886,
|
|
"mean_token_accuracy": 0.1604722708463669,
|
|
"num_tokens": 7321273.0,
|
|
"step": 4210
|
|
},
|
|
{
|
|
"entropy": 5.838960456848144,
|
|
"epoch": 0.327951760357907,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004992950464678026,
|
|
"loss": 5.6783,
|
|
"mean_token_accuracy": 0.15889862924814224,
|
|
"num_tokens": 7330446.0,
|
|
"step": 4215
|
|
},
|
|
{
|
|
"entropy": 5.706913661956787,
|
|
"epoch": 0.3283407897296246,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004992928525284903,
|
|
"loss": 5.6108,
|
|
"mean_token_accuracy": 0.15890374779701233,
|
|
"num_tokens": 7339282.0,
|
|
"step": 4220
|
|
},
|
|
{
|
|
"entropy": 5.799556303024292,
|
|
"epoch": 0.32872981910134214,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000499290655185891,
|
|
"loss": 5.592,
|
|
"mean_token_accuracy": 0.15030699148774146,
|
|
"num_tokens": 7347848.0,
|
|
"step": 4225
|
|
},
|
|
{
|
|
"entropy": 5.7438140392303465,
|
|
"epoch": 0.3291188484730597,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000499288454440038,
|
|
"loss": 5.5943,
|
|
"mean_token_accuracy": 0.16247443109750748,
|
|
"num_tokens": 7356678.0,
|
|
"step": 4230
|
|
},
|
|
{
|
|
"entropy": 5.805340433120728,
|
|
"epoch": 0.3295078778447773,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004992862502909645,
|
|
"loss": 5.6338,
|
|
"mean_token_accuracy": 0.15882461816072463,
|
|
"num_tokens": 7365411.0,
|
|
"step": 4235
|
|
},
|
|
{
|
|
"entropy": 5.7715576171875,
|
|
"epoch": 0.32989690721649484,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004992840427387043,
|
|
"loss": 5.5521,
|
|
"mean_token_accuracy": 0.16899469047784804,
|
|
"num_tokens": 7373635.0,
|
|
"step": 4240
|
|
},
|
|
{
|
|
"entropy": 5.794749927520752,
|
|
"epoch": 0.3302859365882124,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004992818317832908,
|
|
"loss": 5.6832,
|
|
"mean_token_accuracy": 0.15516672283411026,
|
|
"num_tokens": 7382469.0,
|
|
"step": 4245
|
|
},
|
|
{
|
|
"entropy": 5.831536340713501,
|
|
"epoch": 0.33067496595992996,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004992796174247574,
|
|
"loss": 5.6601,
|
|
"mean_token_accuracy": 0.15788168013095855,
|
|
"num_tokens": 7390712.0,
|
|
"step": 4250
|
|
},
|
|
{
|
|
"entropy": 5.89034333229065,
|
|
"epoch": 0.33106399533164754,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004992773996631378,
|
|
"loss": 5.5945,
|
|
"mean_token_accuracy": 0.15991327166557312,
|
|
"num_tokens": 7398905.0,
|
|
"step": 4255
|
|
},
|
|
{
|
|
"entropy": 5.814719247817993,
|
|
"epoch": 0.33145302470336513,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004992751784984656,
|
|
"loss": 5.6791,
|
|
"mean_token_accuracy": 0.15588037967681884,
|
|
"num_tokens": 7407242.0,
|
|
"step": 4260
|
|
},
|
|
{
|
|
"entropy": 5.787463998794555,
|
|
"epoch": 0.33184205407508266,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004992729539307745,
|
|
"loss": 5.6865,
|
|
"mean_token_accuracy": 0.1521645873785019,
|
|
"num_tokens": 7416489.0,
|
|
"step": 4265
|
|
},
|
|
{
|
|
"entropy": 5.855968618392945,
|
|
"epoch": 0.33223108344680025,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004992707259600984,
|
|
"loss": 5.6738,
|
|
"mean_token_accuracy": 0.16025874763727188,
|
|
"num_tokens": 7424507.0,
|
|
"step": 4270
|
|
},
|
|
{
|
|
"entropy": 5.7866209030151365,
|
|
"epoch": 0.3326201128185178,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004992684945864709,
|
|
"loss": 5.6618,
|
|
"mean_token_accuracy": 0.15009636729955672,
|
|
"num_tokens": 7433343.0,
|
|
"step": 4275
|
|
},
|
|
{
|
|
"entropy": 5.760308694839478,
|
|
"epoch": 0.33300914219023536,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004992662598099261,
|
|
"loss": 5.5958,
|
|
"mean_token_accuracy": 0.15572042614221573,
|
|
"num_tokens": 7441452.0,
|
|
"step": 4280
|
|
},
|
|
{
|
|
"entropy": 5.8265258312225345,
|
|
"epoch": 0.33339817156195295,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004992640216304975,
|
|
"loss": 5.6566,
|
|
"mean_token_accuracy": 0.16005273461341857,
|
|
"num_tokens": 7449541.0,
|
|
"step": 4285
|
|
},
|
|
{
|
|
"entropy": 5.807859754562378,
|
|
"epoch": 0.3337872009336705,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004992617800482196,
|
|
"loss": 5.6753,
|
|
"mean_token_accuracy": 0.14853483065962791,
|
|
"num_tokens": 7458812.0,
|
|
"step": 4290
|
|
},
|
|
{
|
|
"entropy": 5.822836828231812,
|
|
"epoch": 0.33417623030538807,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000499259535063126,
|
|
"loss": 5.5967,
|
|
"mean_token_accuracy": 0.15647593289613723,
|
|
"num_tokens": 7467607.0,
|
|
"step": 4295
|
|
},
|
|
{
|
|
"entropy": 5.809892272949218,
|
|
"epoch": 0.3345652596771056,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000499257286675251,
|
|
"loss": 5.5287,
|
|
"mean_token_accuracy": 0.15996506363153457,
|
|
"num_tokens": 7476047.0,
|
|
"step": 4300
|
|
},
|
|
{
|
|
"entropy": 5.819800090789795,
|
|
"epoch": 0.3349542890488232,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004992550348846285,
|
|
"loss": 5.5922,
|
|
"mean_token_accuracy": 0.15836444348096848,
|
|
"num_tokens": 7484496.0,
|
|
"step": 4305
|
|
},
|
|
{
|
|
"entropy": 5.6688683986663815,
|
|
"epoch": 0.33534331842054077,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004992527796912928,
|
|
"loss": 5.533,
|
|
"mean_token_accuracy": 0.16347187012434006,
|
|
"num_tokens": 7493161.0,
|
|
"step": 4310
|
|
},
|
|
{
|
|
"entropy": 5.802170896530152,
|
|
"epoch": 0.3357323477922583,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004992505210952782,
|
|
"loss": 5.6606,
|
|
"mean_token_accuracy": 0.15477246642112732,
|
|
"num_tokens": 7502122.0,
|
|
"step": 4315
|
|
},
|
|
{
|
|
"entropy": 5.833450222015381,
|
|
"epoch": 0.3361213771639759,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004992482590966188,
|
|
"loss": 5.6368,
|
|
"mean_token_accuracy": 0.15850246399641038,
|
|
"num_tokens": 7510369.0,
|
|
"step": 4320
|
|
},
|
|
{
|
|
"entropy": 5.6804886817932125,
|
|
"epoch": 0.3365104065356934,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004992459936953489,
|
|
"loss": 5.5165,
|
|
"mean_token_accuracy": 0.1662609502673149,
|
|
"num_tokens": 7519321.0,
|
|
"step": 4325
|
|
},
|
|
{
|
|
"entropy": 5.744986438751221,
|
|
"epoch": 0.336899435907411,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004992437248915032,
|
|
"loss": 5.5699,
|
|
"mean_token_accuracy": 0.16194347888231278,
|
|
"num_tokens": 7528196.0,
|
|
"step": 4330
|
|
},
|
|
{
|
|
"entropy": 5.754108524322509,
|
|
"epoch": 0.3372884652791286,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004992414526851157,
|
|
"loss": 5.621,
|
|
"mean_token_accuracy": 0.15460745245218277,
|
|
"num_tokens": 7536124.0,
|
|
"step": 4335
|
|
},
|
|
{
|
|
"entropy": 5.849008846282959,
|
|
"epoch": 0.3376774946508461,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004992391770762212,
|
|
"loss": 5.7256,
|
|
"mean_token_accuracy": 0.1549411028623581,
|
|
"num_tokens": 7544409.0,
|
|
"step": 4340
|
|
},
|
|
{
|
|
"entropy": 5.797446775436401,
|
|
"epoch": 0.3380665240225637,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000499236898064854,
|
|
"loss": 5.6126,
|
|
"mean_token_accuracy": 0.16186843663454056,
|
|
"num_tokens": 7552803.0,
|
|
"step": 4345
|
|
},
|
|
{
|
|
"entropy": 5.758720970153808,
|
|
"epoch": 0.3384555533942813,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004992346156510488,
|
|
"loss": 5.5929,
|
|
"mean_token_accuracy": 0.15546914786100388,
|
|
"num_tokens": 7561909.0,
|
|
"step": 4350
|
|
},
|
|
{
|
|
"entropy": 5.852308654785157,
|
|
"epoch": 0.3388445827659988,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004992323298348403,
|
|
"loss": 5.633,
|
|
"mean_token_accuracy": 0.15416990593075752,
|
|
"num_tokens": 7571759.0,
|
|
"step": 4355
|
|
},
|
|
{
|
|
"entropy": 5.80660228729248,
|
|
"epoch": 0.3392336121377164,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000499230040616263,
|
|
"loss": 5.7731,
|
|
"mean_token_accuracy": 0.15868831053376198,
|
|
"num_tokens": 7580010.0,
|
|
"step": 4360
|
|
},
|
|
{
|
|
"entropy": 5.827027750015259,
|
|
"epoch": 0.33962264150943394,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004992277479953518,
|
|
"loss": 5.5593,
|
|
"mean_token_accuracy": 0.16013055592775344,
|
|
"num_tokens": 7587841.0,
|
|
"step": 4365
|
|
},
|
|
{
|
|
"entropy": 5.809354829788208,
|
|
"epoch": 0.34001167088115153,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004992254519721414,
|
|
"loss": 5.612,
|
|
"mean_token_accuracy": 0.15086305737495423,
|
|
"num_tokens": 7596187.0,
|
|
"step": 4370
|
|
},
|
|
{
|
|
"entropy": 5.674190807342529,
|
|
"epoch": 0.3404007002528691,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004992231525466666,
|
|
"loss": 5.5284,
|
|
"mean_token_accuracy": 0.1612797573208809,
|
|
"num_tokens": 7604361.0,
|
|
"step": 4375
|
|
},
|
|
{
|
|
"entropy": 5.826938152313232,
|
|
"epoch": 0.34078972962458665,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004992208497189624,
|
|
"loss": 5.618,
|
|
"mean_token_accuracy": 0.1607014164328575,
|
|
"num_tokens": 7613173.0,
|
|
"step": 4380
|
|
},
|
|
{
|
|
"entropy": 5.761354255676269,
|
|
"epoch": 0.34117875899630423,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004992185434890637,
|
|
"loss": 5.704,
|
|
"mean_token_accuracy": 0.14778897613286973,
|
|
"num_tokens": 7621730.0,
|
|
"step": 4385
|
|
},
|
|
{
|
|
"entropy": 5.850599241256714,
|
|
"epoch": 0.34156778836802176,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004992162338570055,
|
|
"loss": 5.6661,
|
|
"mean_token_accuracy": 0.15339594334363937,
|
|
"num_tokens": 7630362.0,
|
|
"step": 4390
|
|
},
|
|
{
|
|
"entropy": 5.847987699508667,
|
|
"epoch": 0.34195681773973935,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004992139208228227,
|
|
"loss": 5.6283,
|
|
"mean_token_accuracy": 0.15436543077230452,
|
|
"num_tokens": 7639368.0,
|
|
"step": 4395
|
|
},
|
|
{
|
|
"entropy": 5.795064401626587,
|
|
"epoch": 0.34234584711145694,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004992116043865506,
|
|
"loss": 5.6495,
|
|
"mean_token_accuracy": 0.15490932613611222,
|
|
"num_tokens": 7648399.0,
|
|
"step": 4400
|
|
},
|
|
{
|
|
"entropy": 5.761918830871582,
|
|
"epoch": 0.34273487648317447,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004992092845482244,
|
|
"loss": 5.4742,
|
|
"mean_token_accuracy": 0.1693703129887581,
|
|
"num_tokens": 7657298.0,
|
|
"step": 4405
|
|
},
|
|
{
|
|
"entropy": 5.842507696151733,
|
|
"epoch": 0.34312390585489205,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004992069613078791,
|
|
"loss": 5.6373,
|
|
"mean_token_accuracy": 0.15960614532232284,
|
|
"num_tokens": 7665328.0,
|
|
"step": 4410
|
|
},
|
|
{
|
|
"entropy": 5.747133731842041,
|
|
"epoch": 0.3435129352266096,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004992046346655499,
|
|
"loss": 5.5813,
|
|
"mean_token_accuracy": 0.16045911759138107,
|
|
"num_tokens": 7674610.0,
|
|
"step": 4415
|
|
},
|
|
{
|
|
"entropy": 5.783457612991333,
|
|
"epoch": 0.34390196459832717,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004992023046212723,
|
|
"loss": 5.6131,
|
|
"mean_token_accuracy": 0.15804652571678163,
|
|
"num_tokens": 7682727.0,
|
|
"step": 4420
|
|
},
|
|
{
|
|
"entropy": 5.768875646591186,
|
|
"epoch": 0.34429099397004476,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004991999711750816,
|
|
"loss": 5.5786,
|
|
"mean_token_accuracy": 0.16525509506464003,
|
|
"num_tokens": 7691547.0,
|
|
"step": 4425
|
|
},
|
|
{
|
|
"entropy": 5.749335050582886,
|
|
"epoch": 0.3446800233417623,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004991976343270133,
|
|
"loss": 5.5455,
|
|
"mean_token_accuracy": 0.15550559759140015,
|
|
"num_tokens": 7699987.0,
|
|
"step": 4430
|
|
},
|
|
{
|
|
"entropy": 5.7058038234710695,
|
|
"epoch": 0.3450690527134799,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004991952940771026,
|
|
"loss": 5.6031,
|
|
"mean_token_accuracy": 0.1601826310157776,
|
|
"num_tokens": 7708397.0,
|
|
"step": 4435
|
|
},
|
|
{
|
|
"entropy": 5.769835519790649,
|
|
"epoch": 0.34545808208519746,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004991929504253852,
|
|
"loss": 5.5657,
|
|
"mean_token_accuracy": 0.15692049711942674,
|
|
"num_tokens": 7716795.0,
|
|
"step": 4440
|
|
},
|
|
{
|
|
"entropy": 5.773987054824829,
|
|
"epoch": 0.345847111456915,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004991906033718966,
|
|
"loss": 5.605,
|
|
"mean_token_accuracy": 0.15687381029129027,
|
|
"num_tokens": 7725663.0,
|
|
"step": 4445
|
|
},
|
|
{
|
|
"entropy": 5.761317873001099,
|
|
"epoch": 0.3462361408286326,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004991882529166724,
|
|
"loss": 5.7216,
|
|
"mean_token_accuracy": 0.15945706516504288,
|
|
"num_tokens": 7735175.0,
|
|
"step": 4450
|
|
},
|
|
{
|
|
"entropy": 5.804883766174316,
|
|
"epoch": 0.3466251702003501,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004991858990597483,
|
|
"loss": 5.5777,
|
|
"mean_token_accuracy": 0.16473341584205628,
|
|
"num_tokens": 7744041.0,
|
|
"step": 4455
|
|
},
|
|
{
|
|
"entropy": 5.812509918212891,
|
|
"epoch": 0.3470141995720677,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004991835418011601,
|
|
"loss": 5.6411,
|
|
"mean_token_accuracy": 0.15453120768070222,
|
|
"num_tokens": 7752168.0,
|
|
"step": 4460
|
|
},
|
|
{
|
|
"entropy": 5.736903429031372,
|
|
"epoch": 0.3474032289437853,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004991811811409434,
|
|
"loss": 5.5876,
|
|
"mean_token_accuracy": 0.158350470662117,
|
|
"num_tokens": 7760746.0,
|
|
"step": 4465
|
|
},
|
|
{
|
|
"entropy": 5.779326963424682,
|
|
"epoch": 0.3477922583155028,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004991788170791341,
|
|
"loss": 5.572,
|
|
"mean_token_accuracy": 0.16289048194885253,
|
|
"num_tokens": 7769960.0,
|
|
"step": 4470
|
|
},
|
|
{
|
|
"entropy": 5.830358695983887,
|
|
"epoch": 0.3481812876872204,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004991764496157682,
|
|
"loss": 5.5927,
|
|
"mean_token_accuracy": 0.16031462252140044,
|
|
"num_tokens": 7778475.0,
|
|
"step": 4475
|
|
},
|
|
{
|
|
"entropy": 5.695111846923828,
|
|
"epoch": 0.34857031705893793,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004991740787508814,
|
|
"loss": 5.477,
|
|
"mean_token_accuracy": 0.1656101241707802,
|
|
"num_tokens": 7787590.0,
|
|
"step": 4480
|
|
},
|
|
{
|
|
"entropy": 5.78382716178894,
|
|
"epoch": 0.3489593464306555,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004991717044845097,
|
|
"loss": 5.6542,
|
|
"mean_token_accuracy": 0.15307689160108567,
|
|
"num_tokens": 7796841.0,
|
|
"step": 4485
|
|
},
|
|
{
|
|
"entropy": 5.872925281524658,
|
|
"epoch": 0.3493483758023731,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004991693268166892,
|
|
"loss": 5.6484,
|
|
"mean_token_accuracy": 0.1591815985739231,
|
|
"num_tokens": 7804889.0,
|
|
"step": 4490
|
|
},
|
|
{
|
|
"entropy": 5.783057069778442,
|
|
"epoch": 0.34973740517409063,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004991669457474559,
|
|
"loss": 5.6415,
|
|
"mean_token_accuracy": 0.16229303032159806,
|
|
"num_tokens": 7813185.0,
|
|
"step": 4495
|
|
},
|
|
{
|
|
"entropy": 5.770741891860962,
|
|
"epoch": 0.3501264345458082,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004991645612768461,
|
|
"loss": 5.6333,
|
|
"mean_token_accuracy": 0.1533343091607094,
|
|
"num_tokens": 7821630.0,
|
|
"step": 4500
|
|
},
|
|
{
|
|
"entropy": 5.817403364181518,
|
|
"epoch": 0.35051546391752575,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004991621734048958,
|
|
"loss": 5.6606,
|
|
"mean_token_accuracy": 0.16137972474098206,
|
|
"num_tokens": 7829941.0,
|
|
"step": 4505
|
|
},
|
|
{
|
|
"entropy": 5.762375736236573,
|
|
"epoch": 0.35090449328924334,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004991597821316415,
|
|
"loss": 5.6094,
|
|
"mean_token_accuracy": 0.15952375829219817,
|
|
"num_tokens": 7838515.0,
|
|
"step": 4510
|
|
},
|
|
{
|
|
"entropy": 5.862095975875855,
|
|
"epoch": 0.3512935226609609,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004991573874571192,
|
|
"loss": 5.6086,
|
|
"mean_token_accuracy": 0.16334310919046402,
|
|
"num_tokens": 7846575.0,
|
|
"step": 4515
|
|
},
|
|
{
|
|
"entropy": 5.700931644439697,
|
|
"epoch": 0.35168255203267845,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004991549893813653,
|
|
"loss": 5.4983,
|
|
"mean_token_accuracy": 0.16833383440971375,
|
|
"num_tokens": 7854970.0,
|
|
"step": 4520
|
|
},
|
|
{
|
|
"entropy": 5.756206512451172,
|
|
"epoch": 0.35207158140439604,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004991525879044162,
|
|
"loss": 5.5846,
|
|
"mean_token_accuracy": 0.16156198233366012,
|
|
"num_tokens": 7863293.0,
|
|
"step": 4525
|
|
},
|
|
{
|
|
"entropy": 5.783585739135742,
|
|
"epoch": 0.35246061077611357,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004991501830263084,
|
|
"loss": 5.5863,
|
|
"mean_token_accuracy": 0.1635638877749443,
|
|
"num_tokens": 7871029.0,
|
|
"step": 4530
|
|
},
|
|
{
|
|
"entropy": 5.69771523475647,
|
|
"epoch": 0.35284964014783116,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004991477747470783,
|
|
"loss": 5.4488,
|
|
"mean_token_accuracy": 0.16581278443336486,
|
|
"num_tokens": 7879797.0,
|
|
"step": 4535
|
|
},
|
|
{
|
|
"entropy": 5.877959823608398,
|
|
"epoch": 0.35323866951954874,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004991453630667625,
|
|
"loss": 5.7541,
|
|
"mean_token_accuracy": 0.15457085222005845,
|
|
"num_tokens": 7888600.0,
|
|
"step": 4540
|
|
},
|
|
{
|
|
"entropy": 5.734695291519165,
|
|
"epoch": 0.3536276988912663,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004991429479853976,
|
|
"loss": 5.5765,
|
|
"mean_token_accuracy": 0.15913326889276505,
|
|
"num_tokens": 7897794.0,
|
|
"step": 4545
|
|
},
|
|
{
|
|
"entropy": 5.809968614578247,
|
|
"epoch": 0.35401672826298386,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004991405295030202,
|
|
"loss": 5.5624,
|
|
"mean_token_accuracy": 0.163884000480175,
|
|
"num_tokens": 7905822.0,
|
|
"step": 4550
|
|
},
|
|
{
|
|
"entropy": 5.694532299041748,
|
|
"epoch": 0.35440575763470145,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004991381076196671,
|
|
"loss": 5.6405,
|
|
"mean_token_accuracy": 0.16143991500139238,
|
|
"num_tokens": 7914560.0,
|
|
"step": 4555
|
|
},
|
|
{
|
|
"entropy": 5.667612600326538,
|
|
"epoch": 0.354794787006419,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004991356823353748,
|
|
"loss": 5.4739,
|
|
"mean_token_accuracy": 0.1684693694114685,
|
|
"num_tokens": 7924058.0,
|
|
"step": 4560
|
|
},
|
|
{
|
|
"entropy": 5.777330732345581,
|
|
"epoch": 0.35518381637813656,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004991332536501804,
|
|
"loss": 5.6355,
|
|
"mean_token_accuracy": 0.15628551989793776,
|
|
"num_tokens": 7932979.0,
|
|
"step": 4565
|
|
},
|
|
{
|
|
"entropy": 5.682309246063232,
|
|
"epoch": 0.3555728457498541,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004991308215641205,
|
|
"loss": 5.4203,
|
|
"mean_token_accuracy": 0.17264385670423507,
|
|
"num_tokens": 7941357.0,
|
|
"step": 4570
|
|
},
|
|
{
|
|
"entropy": 5.712415027618408,
|
|
"epoch": 0.3559618751215717,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004991283860772323,
|
|
"loss": 5.5851,
|
|
"mean_token_accuracy": 0.16359777003526688,
|
|
"num_tokens": 7949997.0,
|
|
"step": 4575
|
|
},
|
|
{
|
|
"entropy": 5.753382682800293,
|
|
"epoch": 0.35635090449328927,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004991259471895525,
|
|
"loss": 5.5255,
|
|
"mean_token_accuracy": 0.15907478630542754,
|
|
"num_tokens": 7958246.0,
|
|
"step": 4580
|
|
},
|
|
{
|
|
"entropy": 5.73652753829956,
|
|
"epoch": 0.3567399338650068,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004991235049011182,
|
|
"loss": 5.6265,
|
|
"mean_token_accuracy": 0.152801451086998,
|
|
"num_tokens": 7967176.0,
|
|
"step": 4585
|
|
},
|
|
{
|
|
"entropy": 5.758307361602784,
|
|
"epoch": 0.3571289632367244,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004991210592119663,
|
|
"loss": 5.4735,
|
|
"mean_token_accuracy": 0.16641369760036467,
|
|
"num_tokens": 7974761.0,
|
|
"step": 4590
|
|
},
|
|
{
|
|
"entropy": 5.68664140701294,
|
|
"epoch": 0.3575179926084419,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004991186101221342,
|
|
"loss": 5.5484,
|
|
"mean_token_accuracy": 0.1624031826853752,
|
|
"num_tokens": 7983155.0,
|
|
"step": 4595
|
|
},
|
|
{
|
|
"entropy": 5.744742155075073,
|
|
"epoch": 0.3579070219801595,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000499116157631659,
|
|
"loss": 5.5798,
|
|
"mean_token_accuracy": 0.15518496334552764,
|
|
"num_tokens": 7991276.0,
|
|
"step": 4600
|
|
},
|
|
{
|
|
"entropy": 5.826719141006469,
|
|
"epoch": 0.3582960513518771,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004991137017405777,
|
|
"loss": 5.6925,
|
|
"mean_token_accuracy": 0.15492383688688277,
|
|
"num_tokens": 7999488.0,
|
|
"step": 4605
|
|
},
|
|
{
|
|
"entropy": 5.794916677474975,
|
|
"epoch": 0.3586850807235946,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004991112424489277,
|
|
"loss": 5.5557,
|
|
"mean_token_accuracy": 0.16608401238918305,
|
|
"num_tokens": 8008553.0,
|
|
"step": 4610
|
|
},
|
|
{
|
|
"entropy": 5.691841983795166,
|
|
"epoch": 0.3590741100953122,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004991087797567462,
|
|
"loss": 5.5454,
|
|
"mean_token_accuracy": 0.15937763601541519,
|
|
"num_tokens": 8017890.0,
|
|
"step": 4615
|
|
},
|
|
{
|
|
"entropy": 5.780169248580933,
|
|
"epoch": 0.35946313946702974,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004991063136640709,
|
|
"loss": 5.6974,
|
|
"mean_token_accuracy": 0.14828183278441429,
|
|
"num_tokens": 8025782.0,
|
|
"step": 4620
|
|
},
|
|
{
|
|
"entropy": 5.8135302543640135,
|
|
"epoch": 0.3598521688387473,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004991038441709388,
|
|
"loss": 5.5441,
|
|
"mean_token_accuracy": 0.16591402292251586,
|
|
"num_tokens": 8034623.0,
|
|
"step": 4625
|
|
},
|
|
{
|
|
"entropy": 5.700853729248047,
|
|
"epoch": 0.3602411982104649,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004991013712773877,
|
|
"loss": 5.5683,
|
|
"mean_token_accuracy": 0.15996278524398805,
|
|
"num_tokens": 8043789.0,
|
|
"step": 4630
|
|
},
|
|
{
|
|
"entropy": 5.704516410827637,
|
|
"epoch": 0.36063022758218244,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004990988949834549,
|
|
"loss": 5.5372,
|
|
"mean_token_accuracy": 0.15648136287927628,
|
|
"num_tokens": 8053456.0,
|
|
"step": 4635
|
|
},
|
|
{
|
|
"entropy": 5.711209392547607,
|
|
"epoch": 0.3610192569539,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000499096415289178,
|
|
"loss": 5.5038,
|
|
"mean_token_accuracy": 0.16059173345565797,
|
|
"num_tokens": 8061692.0,
|
|
"step": 4640
|
|
},
|
|
{
|
|
"entropy": 5.6331850528717045,
|
|
"epoch": 0.3614082863256176,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004990939321945948,
|
|
"loss": 5.4713,
|
|
"mean_token_accuracy": 0.1669237121939659,
|
|
"num_tokens": 8069564.0,
|
|
"step": 4645
|
|
},
|
|
{
|
|
"entropy": 5.751643896102905,
|
|
"epoch": 0.36179731569733514,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004990914456997427,
|
|
"loss": 5.5421,
|
|
"mean_token_accuracy": 0.15623156130313873,
|
|
"num_tokens": 8078490.0,
|
|
"step": 4650
|
|
},
|
|
{
|
|
"entropy": 5.726134777069092,
|
|
"epoch": 0.36218634506905273,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004990889558046598,
|
|
"loss": 5.6331,
|
|
"mean_token_accuracy": 0.15515794157981871,
|
|
"num_tokens": 8086858.0,
|
|
"step": 4655
|
|
},
|
|
{
|
|
"entropy": 5.737401628494263,
|
|
"epoch": 0.36257537444077026,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004990864625093836,
|
|
"loss": 5.5826,
|
|
"mean_token_accuracy": 0.1621963307261467,
|
|
"num_tokens": 8094542.0,
|
|
"step": 4660
|
|
},
|
|
{
|
|
"entropy": 5.820202112197876,
|
|
"epoch": 0.36296440381248785,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004990839658139519,
|
|
"loss": 5.6136,
|
|
"mean_token_accuracy": 0.16103239059448243,
|
|
"num_tokens": 8102756.0,
|
|
"step": 4665
|
|
},
|
|
{
|
|
"entropy": 5.823258686065674,
|
|
"epoch": 0.36335343318420543,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004990814657184028,
|
|
"loss": 5.6456,
|
|
"mean_token_accuracy": 0.1623107150197029,
|
|
"num_tokens": 8111258.0,
|
|
"step": 4670
|
|
},
|
|
{
|
|
"entropy": 5.87000675201416,
|
|
"epoch": 0.36374246255592296,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004990789622227741,
|
|
"loss": 5.7553,
|
|
"mean_token_accuracy": 0.14676559418439866,
|
|
"num_tokens": 8119624.0,
|
|
"step": 4675
|
|
},
|
|
{
|
|
"entropy": 5.73598952293396,
|
|
"epoch": 0.36413149192764055,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004990764553271038,
|
|
"loss": 5.5433,
|
|
"mean_token_accuracy": 0.16665254384279252,
|
|
"num_tokens": 8128156.0,
|
|
"step": 4680
|
|
},
|
|
{
|
|
"entropy": 5.703827667236328,
|
|
"epoch": 0.3645205212993581,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004990739450314299,
|
|
"loss": 5.5895,
|
|
"mean_token_accuracy": 0.15664388835430146,
|
|
"num_tokens": 8136080.0,
|
|
"step": 4685
|
|
},
|
|
{
|
|
"entropy": 5.797719097137451,
|
|
"epoch": 0.36490955067107567,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004990714313357906,
|
|
"loss": 5.5569,
|
|
"mean_token_accuracy": 0.16621064841747285,
|
|
"num_tokens": 8144742.0,
|
|
"step": 4690
|
|
},
|
|
{
|
|
"entropy": 5.77716474533081,
|
|
"epoch": 0.36529858004279325,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000499068914240224,
|
|
"loss": 5.6307,
|
|
"mean_token_accuracy": 0.16047390848398208,
|
|
"num_tokens": 8153377.0,
|
|
"step": 4695
|
|
},
|
|
{
|
|
"entropy": 5.774137258529663,
|
|
"epoch": 0.3656876094145108,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004990663937447682,
|
|
"loss": 5.5609,
|
|
"mean_token_accuracy": 0.16464479267597198,
|
|
"num_tokens": 8162169.0,
|
|
"step": 4700
|
|
},
|
|
{
|
|
"entropy": 5.706748533248901,
|
|
"epoch": 0.36607663878622837,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004990638698494615,
|
|
"loss": 5.5243,
|
|
"mean_token_accuracy": 0.16574703603982927,
|
|
"num_tokens": 8170727.0,
|
|
"step": 4705
|
|
},
|
|
{
|
|
"entropy": 5.653728389739991,
|
|
"epoch": 0.3664656681579459,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004990613425543423,
|
|
"loss": 5.4681,
|
|
"mean_token_accuracy": 0.16673722863197327,
|
|
"num_tokens": 8179013.0,
|
|
"step": 4710
|
|
},
|
|
{
|
|
"entropy": 5.645033836364746,
|
|
"epoch": 0.3668546975296635,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004990588118594487,
|
|
"loss": 5.4449,
|
|
"mean_token_accuracy": 0.17289653271436692,
|
|
"num_tokens": 8187030.0,
|
|
"step": 4715
|
|
},
|
|
{
|
|
"entropy": 5.673836135864258,
|
|
"epoch": 0.3672437269013811,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004990562777648194,
|
|
"loss": 5.4308,
|
|
"mean_token_accuracy": 0.1652565523982048,
|
|
"num_tokens": 8195073.0,
|
|
"step": 4720
|
|
},
|
|
{
|
|
"entropy": 5.671401882171631,
|
|
"epoch": 0.3676327562730986,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004990537402704928,
|
|
"loss": 5.59,
|
|
"mean_token_accuracy": 0.1610963299870491,
|
|
"num_tokens": 8203626.0,
|
|
"step": 4725
|
|
},
|
|
{
|
|
"entropy": 5.764214181900025,
|
|
"epoch": 0.3680217856448162,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004990511993765071,
|
|
"loss": 5.5832,
|
|
"mean_token_accuracy": 0.1626249819993973,
|
|
"num_tokens": 8212750.0,
|
|
"step": 4730
|
|
},
|
|
{
|
|
"entropy": 5.845182847976685,
|
|
"epoch": 0.3684108150165337,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004990486550829011,
|
|
"loss": 5.587,
|
|
"mean_token_accuracy": 0.15327925831079484,
|
|
"num_tokens": 8221542.0,
|
|
"step": 4735
|
|
},
|
|
{
|
|
"entropy": 5.632064485549927,
|
|
"epoch": 0.3687998443882513,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004990461073897134,
|
|
"loss": 5.502,
|
|
"mean_token_accuracy": 0.16081211492419242,
|
|
"num_tokens": 8230574.0,
|
|
"step": 4740
|
|
},
|
|
{
|
|
"entropy": 5.761065196990967,
|
|
"epoch": 0.3691888737599689,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004990435562969827,
|
|
"loss": 5.5967,
|
|
"mean_token_accuracy": 0.15765105038881302,
|
|
"num_tokens": 8239400.0,
|
|
"step": 4745
|
|
},
|
|
{
|
|
"entropy": 5.768282699584961,
|
|
"epoch": 0.3695779031316864,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004990410018047475,
|
|
"loss": 5.4434,
|
|
"mean_token_accuracy": 0.16521641463041306,
|
|
"num_tokens": 8247537.0,
|
|
"step": 4750
|
|
},
|
|
{
|
|
"entropy": 5.690558004379272,
|
|
"epoch": 0.369966932503404,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004990384439130467,
|
|
"loss": 5.5476,
|
|
"mean_token_accuracy": 0.16147579103708268,
|
|
"num_tokens": 8256551.0,
|
|
"step": 4755
|
|
},
|
|
{
|
|
"entropy": 5.780904102325439,
|
|
"epoch": 0.3703559618751216,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004990358826219192,
|
|
"loss": 5.5914,
|
|
"mean_token_accuracy": 0.1590727299451828,
|
|
"num_tokens": 8265492.0,
|
|
"step": 4760
|
|
},
|
|
{
|
|
"entropy": 5.764974880218506,
|
|
"epoch": 0.37074499124683913,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004990333179314038,
|
|
"loss": 5.5202,
|
|
"mean_token_accuracy": 0.16426937580108641,
|
|
"num_tokens": 8273798.0,
|
|
"step": 4765
|
|
},
|
|
{
|
|
"entropy": 5.664842128753662,
|
|
"epoch": 0.3711340206185567,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004990307498415393,
|
|
"loss": 5.5,
|
|
"mean_token_accuracy": 0.16806525439023973,
|
|
"num_tokens": 8281998.0,
|
|
"step": 4770
|
|
},
|
|
{
|
|
"entropy": 5.767178678512574,
|
|
"epoch": 0.37152304999027425,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004990281783523648,
|
|
"loss": 5.6204,
|
|
"mean_token_accuracy": 0.15874530524015426,
|
|
"num_tokens": 8289833.0,
|
|
"step": 4775
|
|
},
|
|
{
|
|
"entropy": 5.6618608951568605,
|
|
"epoch": 0.37191207936199183,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004990256034639192,
|
|
"loss": 5.5905,
|
|
"mean_token_accuracy": 0.16262347549200057,
|
|
"num_tokens": 8297562.0,
|
|
"step": 4780
|
|
},
|
|
{
|
|
"entropy": 5.7884622573852536,
|
|
"epoch": 0.3723011087337094,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004990230251762418,
|
|
"loss": 5.5953,
|
|
"mean_token_accuracy": 0.15986310467123985,
|
|
"num_tokens": 8305262.0,
|
|
"step": 4785
|
|
},
|
|
{
|
|
"entropy": 5.737649822235108,
|
|
"epoch": 0.37269013810542695,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004990204434893713,
|
|
"loss": 5.5056,
|
|
"mean_token_accuracy": 0.16210581809282304,
|
|
"num_tokens": 8313949.0,
|
|
"step": 4790
|
|
},
|
|
{
|
|
"entropy": 5.712923049926758,
|
|
"epoch": 0.37307916747714454,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004990178584033474,
|
|
"loss": 5.5322,
|
|
"mean_token_accuracy": 0.16029467433691025,
|
|
"num_tokens": 8322801.0,
|
|
"step": 4795
|
|
},
|
|
{
|
|
"entropy": 5.791052341461182,
|
|
"epoch": 0.37346819684886207,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004990152699182089,
|
|
"loss": 5.5386,
|
|
"mean_token_accuracy": 0.16195625811815262,
|
|
"num_tokens": 8331118.0,
|
|
"step": 4800
|
|
},
|
|
{
|
|
"entropy": 5.729126834869385,
|
|
"epoch": 0.37385722622057965,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004990126780339953,
|
|
"loss": 5.5936,
|
|
"mean_token_accuracy": 0.16018568128347396,
|
|
"num_tokens": 8340498.0,
|
|
"step": 4805
|
|
},
|
|
{
|
|
"entropy": 5.828460788726806,
|
|
"epoch": 0.37424625559229724,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004990100827507459,
|
|
"loss": 5.7003,
|
|
"mean_token_accuracy": 0.15686605721712113,
|
|
"num_tokens": 8349235.0,
|
|
"step": 4810
|
|
},
|
|
{
|
|
"entropy": 5.707082319259643,
|
|
"epoch": 0.37463528496401477,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004990074840684999,
|
|
"loss": 5.608,
|
|
"mean_token_accuracy": 0.16234321445226668,
|
|
"num_tokens": 8358484.0,
|
|
"step": 4815
|
|
},
|
|
{
|
|
"entropy": 5.752330541610718,
|
|
"epoch": 0.37502431433573236,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004990048819872969,
|
|
"loss": 5.5245,
|
|
"mean_token_accuracy": 0.16454931795597078,
|
|
"num_tokens": 8366894.0,
|
|
"step": 4820
|
|
},
|
|
{
|
|
"entropy": 5.656948280334473,
|
|
"epoch": 0.3754133437074499,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004990022765071765,
|
|
"loss": 5.542,
|
|
"mean_token_accuracy": 0.157652348279953,
|
|
"num_tokens": 8375271.0,
|
|
"step": 4825
|
|
},
|
|
{
|
|
"entropy": 5.720467042922974,
|
|
"epoch": 0.3758023730791675,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000498999667628178,
|
|
"loss": 5.4817,
|
|
"mean_token_accuracy": 0.16052767187356948,
|
|
"num_tokens": 8383714.0,
|
|
"step": 4830
|
|
},
|
|
{
|
|
"entropy": 5.666319561004639,
|
|
"epoch": 0.37619140245088506,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004989970553503411,
|
|
"loss": 5.5777,
|
|
"mean_token_accuracy": 0.16042256951332093,
|
|
"num_tokens": 8392022.0,
|
|
"step": 4835
|
|
},
|
|
{
|
|
"entropy": 5.777729034423828,
|
|
"epoch": 0.3765804318226026,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004989944396737054,
|
|
"loss": 5.5459,
|
|
"mean_token_accuracy": 0.15841610580682755,
|
|
"num_tokens": 8401282.0,
|
|
"step": 4840
|
|
},
|
|
{
|
|
"entropy": 5.724933242797851,
|
|
"epoch": 0.3769694611943202,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004989918205983106,
|
|
"loss": 5.6248,
|
|
"mean_token_accuracy": 0.15712009221315384,
|
|
"num_tokens": 8411147.0,
|
|
"step": 4845
|
|
},
|
|
{
|
|
"entropy": 5.8453539371490475,
|
|
"epoch": 0.37735849056603776,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004989891981241964,
|
|
"loss": 5.6121,
|
|
"mean_token_accuracy": 0.16100065112113954,
|
|
"num_tokens": 8420434.0,
|
|
"step": 4850
|
|
},
|
|
{
|
|
"entropy": 5.798123455047607,
|
|
"epoch": 0.3777475199377553,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004989865722514027,
|
|
"loss": 5.592,
|
|
"mean_token_accuracy": 0.16213036924600602,
|
|
"num_tokens": 8430022.0,
|
|
"step": 4855
|
|
},
|
|
{
|
|
"entropy": 5.573984432220459,
|
|
"epoch": 0.3781365493094729,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004989839429799692,
|
|
"loss": 5.3627,
|
|
"mean_token_accuracy": 0.1748791977763176,
|
|
"num_tokens": 8438898.0,
|
|
"step": 4860
|
|
},
|
|
{
|
|
"entropy": 5.610987806320191,
|
|
"epoch": 0.3785255786811904,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000498981310309936,
|
|
"loss": 5.4613,
|
|
"mean_token_accuracy": 0.16666309237480165,
|
|
"num_tokens": 8446931.0,
|
|
"step": 4865
|
|
},
|
|
{
|
|
"entropy": 5.758994150161743,
|
|
"epoch": 0.378914608052908,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004989786742413428,
|
|
"loss": 5.5365,
|
|
"mean_token_accuracy": 0.16107167899608613,
|
|
"num_tokens": 8455515.0,
|
|
"step": 4870
|
|
},
|
|
{
|
|
"entropy": 5.727382040023803,
|
|
"epoch": 0.3793036374246256,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004989760347742298,
|
|
"loss": 5.5562,
|
|
"mean_token_accuracy": 0.15914236456155778,
|
|
"num_tokens": 8464135.0,
|
|
"step": 4875
|
|
},
|
|
{
|
|
"entropy": 5.804942274093628,
|
|
"epoch": 0.3796926667963431,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004989733919086369,
|
|
"loss": 5.6331,
|
|
"mean_token_accuracy": 0.1614130526781082,
|
|
"num_tokens": 8473222.0,
|
|
"step": 4880
|
|
},
|
|
{
|
|
"entropy": 5.7484547138214115,
|
|
"epoch": 0.3800816961680607,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004989707456446043,
|
|
"loss": 5.6203,
|
|
"mean_token_accuracy": 0.16746980100870132,
|
|
"num_tokens": 8481966.0,
|
|
"step": 4885
|
|
},
|
|
{
|
|
"entropy": 5.753399801254273,
|
|
"epoch": 0.38047072553977823,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004989680959821721,
|
|
"loss": 5.6236,
|
|
"mean_token_accuracy": 0.1553274318575859,
|
|
"num_tokens": 8491276.0,
|
|
"step": 4890
|
|
},
|
|
{
|
|
"entropy": 5.7599554538726805,
|
|
"epoch": 0.3808597549114958,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004989654429213805,
|
|
"loss": 5.5742,
|
|
"mean_token_accuracy": 0.16141808927059173,
|
|
"num_tokens": 8499926.0,
|
|
"step": 4895
|
|
},
|
|
{
|
|
"entropy": 5.728619718551636,
|
|
"epoch": 0.3812487842832134,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004989627864622699,
|
|
"loss": 5.4498,
|
|
"mean_token_accuracy": 0.16520923972129822,
|
|
"num_tokens": 8508544.0,
|
|
"step": 4900
|
|
},
|
|
{
|
|
"entropy": 5.790788269042968,
|
|
"epoch": 0.38163781365493094,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004989601266048804,
|
|
"loss": 5.5876,
|
|
"mean_token_accuracy": 0.15025516003370284,
|
|
"num_tokens": 8517326.0,
|
|
"step": 4905
|
|
},
|
|
{
|
|
"entropy": 5.688605213165284,
|
|
"epoch": 0.3820268430266485,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004989574633492525,
|
|
"loss": 5.5421,
|
|
"mean_token_accuracy": 0.16179005801677704,
|
|
"num_tokens": 8526218.0,
|
|
"step": 4910
|
|
},
|
|
{
|
|
"entropy": 5.771336221694947,
|
|
"epoch": 0.38241587239836605,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004989547966954266,
|
|
"loss": 5.604,
|
|
"mean_token_accuracy": 0.1568916216492653,
|
|
"num_tokens": 8534708.0,
|
|
"step": 4915
|
|
},
|
|
{
|
|
"entropy": 5.659632444381714,
|
|
"epoch": 0.38280490177008364,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000498952126643443,
|
|
"loss": 5.5321,
|
|
"mean_token_accuracy": 0.1615009605884552,
|
|
"num_tokens": 8543302.0,
|
|
"step": 4920
|
|
},
|
|
{
|
|
"entropy": 5.671322584152222,
|
|
"epoch": 0.3831939311418012,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004989494531933424,
|
|
"loss": 5.4603,
|
|
"mean_token_accuracy": 0.16112909615039825,
|
|
"num_tokens": 8552586.0,
|
|
"step": 4925
|
|
},
|
|
{
|
|
"entropy": 5.689733266830444,
|
|
"epoch": 0.38358296051351876,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004989467763451652,
|
|
"loss": 5.4357,
|
|
"mean_token_accuracy": 0.16707136631011962,
|
|
"num_tokens": 8561720.0,
|
|
"step": 4930
|
|
},
|
|
{
|
|
"entropy": 5.715486478805542,
|
|
"epoch": 0.38397198988523634,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004989440960989523,
|
|
"loss": 5.4248,
|
|
"mean_token_accuracy": 0.16847473233938218,
|
|
"num_tokens": 8570510.0,
|
|
"step": 4935
|
|
},
|
|
{
|
|
"entropy": 5.712751865386963,
|
|
"epoch": 0.3843610192569539,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.000498941412454744,
|
|
"loss": 5.5677,
|
|
"mean_token_accuracy": 0.15966854095458985,
|
|
"num_tokens": 8579986.0,
|
|
"step": 4940
|
|
},
|
|
{
|
|
"entropy": 5.700868129730225,
|
|
"epoch": 0.38475004862867146,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004989387254125813,
|
|
"loss": 5.5321,
|
|
"mean_token_accuracy": 0.15932165682315827,
|
|
"num_tokens": 8588507.0,
|
|
"step": 4945
|
|
},
|
|
{
|
|
"entropy": 5.674834966659546,
|
|
"epoch": 0.38513907800038905,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004989360349725049,
|
|
"loss": 5.4326,
|
|
"mean_token_accuracy": 0.16699319183826447,
|
|
"num_tokens": 8596651.0,
|
|
"step": 4950
|
|
},
|
|
{
|
|
"entropy": 5.686874198913574,
|
|
"epoch": 0.3855281073721066,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004989333411345555,
|
|
"loss": 5.4906,
|
|
"mean_token_accuracy": 0.16555775254964827,
|
|
"num_tokens": 8605080.0,
|
|
"step": 4955
|
|
},
|
|
{
|
|
"entropy": 5.640436172485352,
|
|
"epoch": 0.38591713674382416,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004989306438987742,
|
|
"loss": 5.4486,
|
|
"mean_token_accuracy": 0.1623488187789917,
|
|
"num_tokens": 8613017.0,
|
|
"step": 4960
|
|
},
|
|
{
|
|
"entropy": 5.726773118972778,
|
|
"epoch": 0.38630616611554175,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004989279432652018,
|
|
"loss": 5.6315,
|
|
"mean_token_accuracy": 0.16297589987516403,
|
|
"num_tokens": 8621954.0,
|
|
"step": 4965
|
|
},
|
|
{
|
|
"entropy": 5.774969434738159,
|
|
"epoch": 0.3866951954872593,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004989252392338791,
|
|
"loss": 5.577,
|
|
"mean_token_accuracy": 0.16584077328443528,
|
|
"num_tokens": 8630213.0,
|
|
"step": 4970
|
|
},
|
|
{
|
|
"entropy": 5.799734401702881,
|
|
"epoch": 0.38708422485897687,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004989225318048475,
|
|
"loss": 5.5768,
|
|
"mean_token_accuracy": 0.16362085342407226,
|
|
"num_tokens": 8638360.0,
|
|
"step": 4975
|
|
},
|
|
{
|
|
"entropy": 5.744360113143921,
|
|
"epoch": 0.3874732542306944,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004989198209781478,
|
|
"loss": 5.6298,
|
|
"mean_token_accuracy": 0.1597909837961197,
|
|
"num_tokens": 8647778.0,
|
|
"step": 4980
|
|
},
|
|
{
|
|
"entropy": 5.75740761756897,
|
|
"epoch": 0.387862283602412,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004989171067538211,
|
|
"loss": 5.5454,
|
|
"mean_token_accuracy": 0.15761953890323638,
|
|
"num_tokens": 8655584.0,
|
|
"step": 4985
|
|
},
|
|
{
|
|
"entropy": 5.68055944442749,
|
|
"epoch": 0.38825131297412957,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000498914389131909,
|
|
"loss": 5.5936,
|
|
"mean_token_accuracy": 0.1586558610200882,
|
|
"num_tokens": 8664159.0,
|
|
"step": 4990
|
|
},
|
|
{
|
|
"entropy": 5.707244777679444,
|
|
"epoch": 0.3886403423458471,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004989116681124523,
|
|
"loss": 5.4699,
|
|
"mean_token_accuracy": 0.16615322679281236,
|
|
"num_tokens": 8672488.0,
|
|
"step": 4995
|
|
},
|
|
{
|
|
"entropy": 5.778514432907104,
|
|
"epoch": 0.3890293717175647,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004989089436954924,
|
|
"loss": 5.6278,
|
|
"mean_token_accuracy": 0.15830786675214767,
|
|
"num_tokens": 8681492.0,
|
|
"step": 5000
|
|
},
|
|
{
|
|
"entropy": 5.666163063049316,
|
|
"epoch": 0.3894184010892822,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004989062158810706,
|
|
"loss": 5.512,
|
|
"mean_token_accuracy": 0.16376831531524658,
|
|
"num_tokens": 8690453.0,
|
|
"step": 5005
|
|
},
|
|
{
|
|
"entropy": 5.76589002609253,
|
|
"epoch": 0.3898074304609998,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004989034846692284,
|
|
"loss": 5.5933,
|
|
"mean_token_accuracy": 0.16137610152363777,
|
|
"num_tokens": 8699349.0,
|
|
"step": 5010
|
|
},
|
|
{
|
|
"entropy": 5.754378890991211,
|
|
"epoch": 0.3901964598327174,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004989007500600073,
|
|
"loss": 5.5986,
|
|
"mean_token_accuracy": 0.15995216518640518,
|
|
"num_tokens": 8707512.0,
|
|
"step": 5015
|
|
},
|
|
{
|
|
"entropy": 5.804534530639648,
|
|
"epoch": 0.3905854892044349,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004988980120534486,
|
|
"loss": 5.6108,
|
|
"mean_token_accuracy": 0.16278305947780608,
|
|
"num_tokens": 8715847.0,
|
|
"step": 5020
|
|
},
|
|
{
|
|
"entropy": 5.7424171447753904,
|
|
"epoch": 0.3909745185761525,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000498895270649594,
|
|
"loss": 5.5112,
|
|
"mean_token_accuracy": 0.16594649404287337,
|
|
"num_tokens": 8725548.0,
|
|
"step": 5025
|
|
},
|
|
{
|
|
"entropy": 5.649247646331787,
|
|
"epoch": 0.39136354794787004,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000498892525848485,
|
|
"loss": 5.4847,
|
|
"mean_token_accuracy": 0.1618966743350029,
|
|
"num_tokens": 8733935.0,
|
|
"step": 5030
|
|
},
|
|
{
|
|
"entropy": 5.708878135681152,
|
|
"epoch": 0.3917525773195876,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004988897776501633,
|
|
"loss": 5.5927,
|
|
"mean_token_accuracy": 0.16257513165473939,
|
|
"num_tokens": 8743110.0,
|
|
"step": 5035
|
|
},
|
|
{
|
|
"entropy": 5.669124937057495,
|
|
"epoch": 0.3921416066913052,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004988870260546705,
|
|
"loss": 5.4006,
|
|
"mean_token_accuracy": 0.16625102162361144,
|
|
"num_tokens": 8751166.0,
|
|
"step": 5040
|
|
},
|
|
{
|
|
"entropy": 5.723137521743775,
|
|
"epoch": 0.39253063606302274,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004988842710620486,
|
|
"loss": 5.5993,
|
|
"mean_token_accuracy": 0.16078926771879196,
|
|
"num_tokens": 8759929.0,
|
|
"step": 5045
|
|
},
|
|
{
|
|
"entropy": 5.761736011505127,
|
|
"epoch": 0.39291966543474033,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004988815126723391,
|
|
"loss": 5.6206,
|
|
"mean_token_accuracy": 0.15766884982585908,
|
|
"num_tokens": 8768541.0,
|
|
"step": 5050
|
|
},
|
|
{
|
|
"entropy": 5.767947578430176,
|
|
"epoch": 0.3933086948064579,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004988787508855841,
|
|
"loss": 5.5097,
|
|
"mean_token_accuracy": 0.1612896963953972,
|
|
"num_tokens": 8776803.0,
|
|
"step": 5055
|
|
},
|
|
{
|
|
"entropy": 5.694341850280762,
|
|
"epoch": 0.39369772417817545,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004988759857018253,
|
|
"loss": 5.5134,
|
|
"mean_token_accuracy": 0.16799097061157225,
|
|
"num_tokens": 8784773.0,
|
|
"step": 5060
|
|
},
|
|
{
|
|
"entropy": 5.798240900039673,
|
|
"epoch": 0.39408675354989303,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004988732171211048,
|
|
"loss": 5.5555,
|
|
"mean_token_accuracy": 0.167237688601017,
|
|
"num_tokens": 8793797.0,
|
|
"step": 5065
|
|
},
|
|
{
|
|
"entropy": 5.640912485122681,
|
|
"epoch": 0.39447578292161056,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004988704451434644,
|
|
"loss": 5.4366,
|
|
"mean_token_accuracy": 0.1665719836950302,
|
|
"num_tokens": 8802366.0,
|
|
"step": 5070
|
|
},
|
|
{
|
|
"entropy": 5.742262363433838,
|
|
"epoch": 0.39486481229332815,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004988676697689465,
|
|
"loss": 5.5711,
|
|
"mean_token_accuracy": 0.1577314779162407,
|
|
"num_tokens": 8810975.0,
|
|
"step": 5075
|
|
},
|
|
{
|
|
"entropy": 5.745263528823853,
|
|
"epoch": 0.39525384166504574,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000498864890997593,
|
|
"loss": 5.605,
|
|
"mean_token_accuracy": 0.15574074983596803,
|
|
"num_tokens": 8819137.0,
|
|
"step": 5080
|
|
},
|
|
{
|
|
"entropy": 5.761233139038086,
|
|
"epoch": 0.39564287103676327,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004988621088294461,
|
|
"loss": 5.5953,
|
|
"mean_token_accuracy": 0.15754300504922866,
|
|
"num_tokens": 8827676.0,
|
|
"step": 5085
|
|
},
|
|
{
|
|
"entropy": 5.737605571746826,
|
|
"epoch": 0.39603190040848085,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000498859323264548,
|
|
"loss": 5.5405,
|
|
"mean_token_accuracy": 0.16511860489845276,
|
|
"num_tokens": 8836005.0,
|
|
"step": 5090
|
|
},
|
|
{
|
|
"entropy": 5.648690223693848,
|
|
"epoch": 0.3964209297801984,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000498856534302941,
|
|
"loss": 5.4519,
|
|
"mean_token_accuracy": 0.1706383228302002,
|
|
"num_tokens": 8844153.0,
|
|
"step": 5095
|
|
},
|
|
{
|
|
"entropy": 5.726143455505371,
|
|
"epoch": 0.39680995915191597,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004988537419446673,
|
|
"loss": 5.5587,
|
|
"mean_token_accuracy": 0.15934093594551085,
|
|
"num_tokens": 8852520.0,
|
|
"step": 5100
|
|
},
|
|
{
|
|
"entropy": 5.753759431838989,
|
|
"epoch": 0.39719898852363356,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004988509461897694,
|
|
"loss": 5.3908,
|
|
"mean_token_accuracy": 0.17240907102823258,
|
|
"num_tokens": 8860609.0,
|
|
"step": 5105
|
|
},
|
|
{
|
|
"entropy": 5.67409610748291,
|
|
"epoch": 0.3975880178953511,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004988481470382897,
|
|
"loss": 5.568,
|
|
"mean_token_accuracy": 0.1637749418616295,
|
|
"num_tokens": 8869185.0,
|
|
"step": 5110
|
|
},
|
|
{
|
|
"entropy": 5.687503480911255,
|
|
"epoch": 0.3979770472670687,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004988453444902708,
|
|
"loss": 5.4433,
|
|
"mean_token_accuracy": 0.15943183600902558,
|
|
"num_tokens": 8877758.0,
|
|
"step": 5115
|
|
},
|
|
{
|
|
"entropy": 5.7267121315002445,
|
|
"epoch": 0.3983660766387862,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004988425385457549,
|
|
"loss": 5.6056,
|
|
"mean_token_accuracy": 0.16380086094141005,
|
|
"num_tokens": 8887236.0,
|
|
"step": 5120
|
|
},
|
|
{
|
|
"entropy": 5.747417783737182,
|
|
"epoch": 0.3987551060105038,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004988397292047848,
|
|
"loss": 5.5608,
|
|
"mean_token_accuracy": 0.16228044182062148,
|
|
"num_tokens": 8895808.0,
|
|
"step": 5125
|
|
},
|
|
{
|
|
"entropy": 5.716846132278443,
|
|
"epoch": 0.3991441353822214,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004988369164674032,
|
|
"loss": 5.5437,
|
|
"mean_token_accuracy": 0.16444529294967652,
|
|
"num_tokens": 8904091.0,
|
|
"step": 5130
|
|
},
|
|
{
|
|
"entropy": 5.635995244979858,
|
|
"epoch": 0.3995331647539389,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004988341003336526,
|
|
"loss": 5.3688,
|
|
"mean_token_accuracy": 0.16816658526659012,
|
|
"num_tokens": 8912046.0,
|
|
"step": 5135
|
|
},
|
|
{
|
|
"entropy": 5.73875241279602,
|
|
"epoch": 0.3999221941256565,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004988312808035757,
|
|
"loss": 5.5853,
|
|
"mean_token_accuracy": 0.155656835436821,
|
|
"num_tokens": 8921060.0,
|
|
"step": 5140
|
|
},
|
|
{
|
|
"entropy": 5.70735354423523,
|
|
"epoch": 0.400311223497374,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004988284578772155,
|
|
"loss": 5.5182,
|
|
"mean_token_accuracy": 0.1615131378173828,
|
|
"num_tokens": 8930757.0,
|
|
"step": 5145
|
|
},
|
|
{
|
|
"entropy": 5.824063968658447,
|
|
"epoch": 0.4007002528690916,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004988256315546146,
|
|
"loss": 5.6853,
|
|
"mean_token_accuracy": 0.15802342146635057,
|
|
"num_tokens": 8939544.0,
|
|
"step": 5150
|
|
},
|
|
{
|
|
"entropy": 5.655792140960694,
|
|
"epoch": 0.4010892822408092,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004988228018358161,
|
|
"loss": 5.4993,
|
|
"mean_token_accuracy": 0.16780378073453903,
|
|
"num_tokens": 8949347.0,
|
|
"step": 5155
|
|
},
|
|
{
|
|
"entropy": 5.732742404937744,
|
|
"epoch": 0.40147831161252673,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004988199687208628,
|
|
"loss": 5.5399,
|
|
"mean_token_accuracy": 0.16157386302947999,
|
|
"num_tokens": 8957697.0,
|
|
"step": 5160
|
|
},
|
|
{
|
|
"entropy": 5.721534585952758,
|
|
"epoch": 0.4018673409842443,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004988171322097977,
|
|
"loss": 5.5781,
|
|
"mean_token_accuracy": 0.15993378311395645,
|
|
"num_tokens": 8966107.0,
|
|
"step": 5165
|
|
},
|
|
{
|
|
"entropy": 5.672869491577148,
|
|
"epoch": 0.4022563703559619,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004988142923026638,
|
|
"loss": 5.4833,
|
|
"mean_token_accuracy": 0.16639911830425264,
|
|
"num_tokens": 8974128.0,
|
|
"step": 5170
|
|
},
|
|
{
|
|
"entropy": 5.681173467636109,
|
|
"epoch": 0.40264539972767943,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004988114489995044,
|
|
"loss": 5.4719,
|
|
"mean_token_accuracy": 0.16482845544815064,
|
|
"num_tokens": 8982564.0,
|
|
"step": 5175
|
|
},
|
|
{
|
|
"entropy": 5.665506649017334,
|
|
"epoch": 0.403034429099397,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004988086023003624,
|
|
"loss": 5.5017,
|
|
"mean_token_accuracy": 0.16397453844547272,
|
|
"num_tokens": 8990924.0,
|
|
"step": 5180
|
|
},
|
|
{
|
|
"entropy": 5.812045288085938,
|
|
"epoch": 0.40342345847111455,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004988057522052811,
|
|
"loss": 5.6117,
|
|
"mean_token_accuracy": 0.1547340050339699,
|
|
"num_tokens": 8999827.0,
|
|
"step": 5185
|
|
},
|
|
{
|
|
"entropy": 5.705833959579468,
|
|
"epoch": 0.40381248784283214,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004988028987143037,
|
|
"loss": 5.4391,
|
|
"mean_token_accuracy": 0.16634710282087325,
|
|
"num_tokens": 9007885.0,
|
|
"step": 5190
|
|
},
|
|
{
|
|
"entropy": 5.701918840408325,
|
|
"epoch": 0.4042015172145497,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004988000418274736,
|
|
"loss": 5.5358,
|
|
"mean_token_accuracy": 0.15985646843910217,
|
|
"num_tokens": 9016752.0,
|
|
"step": 5195
|
|
},
|
|
{
|
|
"entropy": 5.734607696533203,
|
|
"epoch": 0.40459054658626725,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004987971815448341,
|
|
"loss": 5.5433,
|
|
"mean_token_accuracy": 0.1646374225616455,
|
|
"num_tokens": 9025547.0,
|
|
"step": 5200
|
|
},
|
|
{
|
|
"entropy": 5.75845513343811,
|
|
"epoch": 0.40497957595798484,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004987943178664285,
|
|
"loss": 5.5775,
|
|
"mean_token_accuracy": 0.15561427399516106,
|
|
"num_tokens": 9034711.0,
|
|
"step": 5205
|
|
},
|
|
{
|
|
"entropy": 5.74301700592041,
|
|
"epoch": 0.40536860532970237,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004987914507923004,
|
|
"loss": 5.4833,
|
|
"mean_token_accuracy": 0.16486086398363115,
|
|
"num_tokens": 9042565.0,
|
|
"step": 5210
|
|
},
|
|
{
|
|
"entropy": 5.646585178375244,
|
|
"epoch": 0.40575763470141996,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004987885803224931,
|
|
"loss": 5.5453,
|
|
"mean_token_accuracy": 0.15442499071359633,
|
|
"num_tokens": 9051590.0,
|
|
"step": 5215
|
|
},
|
|
{
|
|
"entropy": 5.764519596099854,
|
|
"epoch": 0.40614666407313754,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004987857064570505,
|
|
"loss": 5.625,
|
|
"mean_token_accuracy": 0.15703439116477966,
|
|
"num_tokens": 9060415.0,
|
|
"step": 5220
|
|
},
|
|
{
|
|
"entropy": 5.677373218536377,
|
|
"epoch": 0.4065356934448551,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004987828291960158,
|
|
"loss": 5.4125,
|
|
"mean_token_accuracy": 0.17174528390169144,
|
|
"num_tokens": 9069492.0,
|
|
"step": 5225
|
|
},
|
|
{
|
|
"entropy": 5.65934419631958,
|
|
"epoch": 0.40692472281657266,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000498779948539433,
|
|
"loss": 5.4867,
|
|
"mean_token_accuracy": 0.1642414942383766,
|
|
"num_tokens": 9078183.0,
|
|
"step": 5230
|
|
},
|
|
{
|
|
"entropy": 5.800519037246704,
|
|
"epoch": 0.4073137521882902,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004987770644873455,
|
|
"loss": 5.6877,
|
|
"mean_token_accuracy": 0.15678185373544692,
|
|
"num_tokens": 9086661.0,
|
|
"step": 5235
|
|
},
|
|
{
|
|
"entropy": 5.681110000610351,
|
|
"epoch": 0.4077027815600078,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004987741770397974,
|
|
"loss": 5.4215,
|
|
"mean_token_accuracy": 0.17047692239284515,
|
|
"num_tokens": 9095449.0,
|
|
"step": 5240
|
|
},
|
|
{
|
|
"entropy": 5.695486783981323,
|
|
"epoch": 0.40809181093172536,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004987712861968323,
|
|
"loss": 5.5524,
|
|
"mean_token_accuracy": 0.16191044598817825,
|
|
"num_tokens": 9103347.0,
|
|
"step": 5245
|
|
},
|
|
{
|
|
"entropy": 5.598839664459229,
|
|
"epoch": 0.4084808403034429,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.000498768391958494,
|
|
"loss": 5.4639,
|
|
"mean_token_accuracy": 0.16898142844438552,
|
|
"num_tokens": 9112382.0,
|
|
"step": 5250
|
|
},
|
|
{
|
|
"entropy": 5.711949586868286,
|
|
"epoch": 0.4088698696751605,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004987654943248266,
|
|
"loss": 5.4157,
|
|
"mean_token_accuracy": 0.16580033898353577,
|
|
"num_tokens": 9120628.0,
|
|
"step": 5255
|
|
},
|
|
{
|
|
"entropy": 5.751555395126343,
|
|
"epoch": 0.40925889904687807,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004987625932958739,
|
|
"loss": 5.5733,
|
|
"mean_token_accuracy": 0.1564086616039276,
|
|
"num_tokens": 9130280.0,
|
|
"step": 5260
|
|
},
|
|
{
|
|
"entropy": 5.876784896850586,
|
|
"epoch": 0.4096479284185956,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004987596888716801,
|
|
"loss": 5.666,
|
|
"mean_token_accuracy": 0.1538259670138359,
|
|
"num_tokens": 9139720.0,
|
|
"step": 5265
|
|
},
|
|
{
|
|
"entropy": 5.685037422180176,
|
|
"epoch": 0.4100369577903132,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004987567810522892,
|
|
"loss": 5.6061,
|
|
"mean_token_accuracy": 0.16040026843547822,
|
|
"num_tokens": 9148537.0,
|
|
"step": 5270
|
|
},
|
|
{
|
|
"entropy": 5.728633642196655,
|
|
"epoch": 0.4104259871620307,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004987538698377451,
|
|
"loss": 5.6672,
|
|
"mean_token_accuracy": 0.16034265160560607,
|
|
"num_tokens": 9156965.0,
|
|
"step": 5275
|
|
},
|
|
{
|
|
"entropy": 5.71022138595581,
|
|
"epoch": 0.4108150165337483,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004987509552280924,
|
|
"loss": 5.3884,
|
|
"mean_token_accuracy": 0.17059710174798964,
|
|
"num_tokens": 9164982.0,
|
|
"step": 5280
|
|
},
|
|
{
|
|
"entropy": 5.721287250518799,
|
|
"epoch": 0.4112040459054659,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000498748037223375,
|
|
"loss": 5.6145,
|
|
"mean_token_accuracy": 0.15953994691371917,
|
|
"num_tokens": 9173383.0,
|
|
"step": 5285
|
|
},
|
|
{
|
|
"entropy": 5.781473302841187,
|
|
"epoch": 0.4115930752771834,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004987451158236372,
|
|
"loss": 5.6148,
|
|
"mean_token_accuracy": 0.1664327308535576,
|
|
"num_tokens": 9182743.0,
|
|
"step": 5290
|
|
},
|
|
{
|
|
"entropy": 5.766506195068359,
|
|
"epoch": 0.411982104648901,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004987421910289234,
|
|
"loss": 5.5047,
|
|
"mean_token_accuracy": 0.1667089506983757,
|
|
"num_tokens": 9191770.0,
|
|
"step": 5295
|
|
},
|
|
{
|
|
"entropy": 5.558193063735962,
|
|
"epoch": 0.41237113402061853,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004987392628392781,
|
|
"loss": 5.484,
|
|
"mean_token_accuracy": 0.17050291001796722,
|
|
"num_tokens": 9200885.0,
|
|
"step": 5300
|
|
},
|
|
{
|
|
"entropy": 5.802951240539551,
|
|
"epoch": 0.4127601633923361,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004987363312547456,
|
|
"loss": 5.5403,
|
|
"mean_token_accuracy": 0.16366390138864517,
|
|
"num_tokens": 9210114.0,
|
|
"step": 5305
|
|
},
|
|
{
|
|
"entropy": 5.761357307434082,
|
|
"epoch": 0.4131491927640537,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004987333962753703,
|
|
"loss": 5.5125,
|
|
"mean_token_accuracy": 0.1661704123020172,
|
|
"num_tokens": 9218608.0,
|
|
"step": 5310
|
|
},
|
|
{
|
|
"entropy": 5.674144315719604,
|
|
"epoch": 0.41353822213577124,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004987304579011967,
|
|
"loss": 5.5575,
|
|
"mean_token_accuracy": 0.1641923874616623,
|
|
"num_tokens": 9227737.0,
|
|
"step": 5315
|
|
},
|
|
{
|
|
"entropy": 5.6867390155792235,
|
|
"epoch": 0.4139272515074888,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004987275161322697,
|
|
"loss": 5.4712,
|
|
"mean_token_accuracy": 0.16756489276885986,
|
|
"num_tokens": 9236589.0,
|
|
"step": 5320
|
|
},
|
|
{
|
|
"entropy": 5.700326871871948,
|
|
"epoch": 0.41431628087920636,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004987245709686337,
|
|
"loss": 5.5047,
|
|
"mean_token_accuracy": 0.16901690065860747,
|
|
"num_tokens": 9245313.0,
|
|
"step": 5325
|
|
},
|
|
{
|
|
"entropy": 5.692599248886109,
|
|
"epoch": 0.41470531025092394,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004987216224103334,
|
|
"loss": 5.5438,
|
|
"mean_token_accuracy": 0.1554454781115055,
|
|
"num_tokens": 9254001.0,
|
|
"step": 5330
|
|
},
|
|
{
|
|
"entropy": 5.778351974487305,
|
|
"epoch": 0.41509433962264153,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004987186704574136,
|
|
"loss": 5.6031,
|
|
"mean_token_accuracy": 0.15538137555122375,
|
|
"num_tokens": 9262485.0,
|
|
"step": 5335
|
|
},
|
|
{
|
|
"entropy": 5.701541996002197,
|
|
"epoch": 0.41548336899435906,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004987157151099189,
|
|
"loss": 5.4901,
|
|
"mean_token_accuracy": 0.1665266901254654,
|
|
"num_tokens": 9271490.0,
|
|
"step": 5340
|
|
},
|
|
{
|
|
"entropy": 5.663458061218262,
|
|
"epoch": 0.41587239836607665,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004987127563678945,
|
|
"loss": 5.5304,
|
|
"mean_token_accuracy": 0.16415161043405532,
|
|
"num_tokens": 9280595.0,
|
|
"step": 5345
|
|
},
|
|
{
|
|
"entropy": 5.679933214187622,
|
|
"epoch": 0.4162614277377942,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004987097942313852,
|
|
"loss": 5.4348,
|
|
"mean_token_accuracy": 0.17057384997606279,
|
|
"num_tokens": 9289260.0,
|
|
"step": 5350
|
|
},
|
|
{
|
|
"entropy": 5.753614616394043,
|
|
"epoch": 0.41665045710951176,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004987068287004355,
|
|
"loss": 5.6049,
|
|
"mean_token_accuracy": 0.16246243417263032,
|
|
"num_tokens": 9297842.0,
|
|
"step": 5355
|
|
},
|
|
{
|
|
"entropy": 5.752865648269653,
|
|
"epoch": 0.41703948648122935,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004987038597750909,
|
|
"loss": 5.5993,
|
|
"mean_token_accuracy": 0.15823685377836227,
|
|
"num_tokens": 9306533.0,
|
|
"step": 5360
|
|
},
|
|
{
|
|
"entropy": 5.759689044952393,
|
|
"epoch": 0.4174285158529469,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004987008874553964,
|
|
"loss": 5.4835,
|
|
"mean_token_accuracy": 0.1640964165329933,
|
|
"num_tokens": 9314534.0,
|
|
"step": 5365
|
|
},
|
|
{
|
|
"entropy": 5.776584053039551,
|
|
"epoch": 0.41781754522466447,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004986979117413969,
|
|
"loss": 5.6455,
|
|
"mean_token_accuracy": 0.16746927350759505,
|
|
"num_tokens": 9323179.0,
|
|
"step": 5370
|
|
},
|
|
{
|
|
"entropy": 5.696486854553223,
|
|
"epoch": 0.41820657459638205,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004986949326331376,
|
|
"loss": 5.4419,
|
|
"mean_token_accuracy": 0.1723403036594391,
|
|
"num_tokens": 9331265.0,
|
|
"step": 5375
|
|
},
|
|
{
|
|
"entropy": 5.697726821899414,
|
|
"epoch": 0.4185956039680996,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004986919501306638,
|
|
"loss": 5.5006,
|
|
"mean_token_accuracy": 0.15892638862133027,
|
|
"num_tokens": 9340856.0,
|
|
"step": 5380
|
|
},
|
|
{
|
|
"entropy": 5.706587934494019,
|
|
"epoch": 0.41898463333981717,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004986889642340207,
|
|
"loss": 5.5348,
|
|
"mean_token_accuracy": 0.15855901688337326,
|
|
"num_tokens": 9350728.0,
|
|
"step": 5385
|
|
},
|
|
{
|
|
"entropy": 5.78882064819336,
|
|
"epoch": 0.4193736627115347,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004986859749432536,
|
|
"loss": 5.6364,
|
|
"mean_token_accuracy": 0.15591242015361786,
|
|
"num_tokens": 9360109.0,
|
|
"step": 5390
|
|
},
|
|
{
|
|
"entropy": 5.7880536079406735,
|
|
"epoch": 0.4197626920832523,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004986829822584078,
|
|
"loss": 5.6202,
|
|
"mean_token_accuracy": 0.16118184924125672,
|
|
"num_tokens": 9369101.0,
|
|
"step": 5395
|
|
},
|
|
{
|
|
"entropy": 5.728350448608398,
|
|
"epoch": 0.4201517214549699,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004986799861795289,
|
|
"loss": 5.5667,
|
|
"mean_token_accuracy": 0.1637089490890503,
|
|
"num_tokens": 9377686.0,
|
|
"step": 5400
|
|
},
|
|
{
|
|
"entropy": 5.76845417022705,
|
|
"epoch": 0.4205407508266874,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004986769867066622,
|
|
"loss": 5.5557,
|
|
"mean_token_accuracy": 0.16162476390600206,
|
|
"num_tokens": 9386439.0,
|
|
"step": 5405
|
|
},
|
|
{
|
|
"entropy": 5.69290337562561,
|
|
"epoch": 0.420929780198405,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004986739838398532,
|
|
"loss": 5.6102,
|
|
"mean_token_accuracy": 0.15639652460813522,
|
|
"num_tokens": 9395086.0,
|
|
"step": 5410
|
|
},
|
|
{
|
|
"entropy": 5.688079404830932,
|
|
"epoch": 0.4213188095701225,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004986709775791475,
|
|
"loss": 5.461,
|
|
"mean_token_accuracy": 0.16996486335992814,
|
|
"num_tokens": 9403762.0,
|
|
"step": 5415
|
|
},
|
|
{
|
|
"entropy": 5.7050965309143065,
|
|
"epoch": 0.4217078389418401,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004986679679245907,
|
|
"loss": 5.5091,
|
|
"mean_token_accuracy": 0.1694752588868141,
|
|
"num_tokens": 9412386.0,
|
|
"step": 5420
|
|
},
|
|
{
|
|
"entropy": 5.69061541557312,
|
|
"epoch": 0.4220968683135577,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004986649548762286,
|
|
"loss": 5.465,
|
|
"mean_token_accuracy": 0.17578306198120117,
|
|
"num_tokens": 9420538.0,
|
|
"step": 5425
|
|
},
|
|
{
|
|
"entropy": 5.612565708160401,
|
|
"epoch": 0.4224858976852752,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004986619384341066,
|
|
"loss": 5.4591,
|
|
"mean_token_accuracy": 0.16782598644495011,
|
|
"num_tokens": 9429083.0,
|
|
"step": 5430
|
|
},
|
|
{
|
|
"entropy": 5.706359767913819,
|
|
"epoch": 0.4228749270569928,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004986589185982708,
|
|
"loss": 5.558,
|
|
"mean_token_accuracy": 0.1694366976618767,
|
|
"num_tokens": 9436892.0,
|
|
"step": 5435
|
|
},
|
|
{
|
|
"entropy": 5.7010246276855465,
|
|
"epoch": 0.42326395642871034,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004986558953687671,
|
|
"loss": 5.5681,
|
|
"mean_token_accuracy": 0.16823252588510512,
|
|
"num_tokens": 9445267.0,
|
|
"step": 5440
|
|
},
|
|
{
|
|
"entropy": 5.742143821716309,
|
|
"epoch": 0.42365298580042793,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004986528687456409,
|
|
"loss": 5.5692,
|
|
"mean_token_accuracy": 0.16173406913876534,
|
|
"num_tokens": 9454292.0,
|
|
"step": 5445
|
|
},
|
|
{
|
|
"entropy": 5.722393798828125,
|
|
"epoch": 0.4240420151721455,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004986498387289384,
|
|
"loss": 5.4642,
|
|
"mean_token_accuracy": 0.17036706805229188,
|
|
"num_tokens": 9463126.0,
|
|
"step": 5450
|
|
},
|
|
{
|
|
"entropy": 5.705404376983642,
|
|
"epoch": 0.42443104454386305,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004986468053187058,
|
|
"loss": 5.5422,
|
|
"mean_token_accuracy": 0.16476629674434662,
|
|
"num_tokens": 9471703.0,
|
|
"step": 5455
|
|
},
|
|
{
|
|
"entropy": 5.6335962295532225,
|
|
"epoch": 0.42482007391558063,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004986437685149887,
|
|
"loss": 5.443,
|
|
"mean_token_accuracy": 0.17423020005226136,
|
|
"num_tokens": 9480029.0,
|
|
"step": 5460
|
|
},
|
|
{
|
|
"entropy": 5.7315908908844,
|
|
"epoch": 0.4252091032872982,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004986407283178334,
|
|
"loss": 5.5504,
|
|
"mean_token_accuracy": 0.16471220105886458,
|
|
"num_tokens": 9488277.0,
|
|
"step": 5465
|
|
},
|
|
{
|
|
"entropy": 5.745454263687134,
|
|
"epoch": 0.42559813265901575,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004986376847272861,
|
|
"loss": 5.5909,
|
|
"mean_token_accuracy": 0.16612172424793242,
|
|
"num_tokens": 9496096.0,
|
|
"step": 5470
|
|
},
|
|
{
|
|
"entropy": 5.671952915191651,
|
|
"epoch": 0.42598716203073334,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004986346377433929,
|
|
"loss": 5.4945,
|
|
"mean_token_accuracy": 0.16573259979486465,
|
|
"num_tokens": 9504653.0,
|
|
"step": 5475
|
|
},
|
|
{
|
|
"entropy": 5.73224778175354,
|
|
"epoch": 0.42637619140245087,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004986315873661999,
|
|
"loss": 5.4778,
|
|
"mean_token_accuracy": 0.16273901611566544,
|
|
"num_tokens": 9513088.0,
|
|
"step": 5480
|
|
},
|
|
{
|
|
"entropy": 5.654418230056763,
|
|
"epoch": 0.42676522077416845,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004986285335957536,
|
|
"loss": 5.3953,
|
|
"mean_token_accuracy": 0.1652171418070793,
|
|
"num_tokens": 9521714.0,
|
|
"step": 5485
|
|
},
|
|
{
|
|
"entropy": 5.628698778152466,
|
|
"epoch": 0.42715425014588604,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004986254764321002,
|
|
"loss": 5.4998,
|
|
"mean_token_accuracy": 0.16910230666399,
|
|
"num_tokens": 9530629.0,
|
|
"step": 5490
|
|
},
|
|
{
|
|
"entropy": 5.6531576156616214,
|
|
"epoch": 0.42754327951760357,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004986224158752861,
|
|
"loss": 5.4805,
|
|
"mean_token_accuracy": 0.17005691379308702,
|
|
"num_tokens": 9539293.0,
|
|
"step": 5495
|
|
},
|
|
{
|
|
"entropy": 5.635426998138428,
|
|
"epoch": 0.42793230888932116,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004986193519253578,
|
|
"loss": 5.4397,
|
|
"mean_token_accuracy": 0.17028937339782715,
|
|
"num_tokens": 9547628.0,
|
|
"step": 5500
|
|
},
|
|
{
|
|
"entropy": 5.638662195205688,
|
|
"epoch": 0.4283213382610387,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004986162845823618,
|
|
"loss": 5.444,
|
|
"mean_token_accuracy": 0.17030109614133834,
|
|
"num_tokens": 9557260.0,
|
|
"step": 5505
|
|
},
|
|
{
|
|
"entropy": 5.762142133712769,
|
|
"epoch": 0.4287103676327563,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004986132138463446,
|
|
"loss": 5.5032,
|
|
"mean_token_accuracy": 0.15915174037218094,
|
|
"num_tokens": 9565923.0,
|
|
"step": 5510
|
|
},
|
|
{
|
|
"entropy": 5.671739196777343,
|
|
"epoch": 0.42909939700447386,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004986101397173528,
|
|
"loss": 5.4809,
|
|
"mean_token_accuracy": 0.16655878871679305,
|
|
"num_tokens": 9574373.0,
|
|
"step": 5515
|
|
},
|
|
{
|
|
"entropy": 5.72672061920166,
|
|
"epoch": 0.4294884263761914,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000498607062195433,
|
|
"loss": 5.5809,
|
|
"mean_token_accuracy": 0.16339072734117507,
|
|
"num_tokens": 9583652.0,
|
|
"step": 5520
|
|
},
|
|
{
|
|
"entropy": 5.714191198348999,
|
|
"epoch": 0.429877455747909,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000498603981280632,
|
|
"loss": 5.5423,
|
|
"mean_token_accuracy": 0.1653921753168106,
|
|
"num_tokens": 9592625.0,
|
|
"step": 5525
|
|
},
|
|
{
|
|
"entropy": 5.62770266532898,
|
|
"epoch": 0.4302664851196265,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004986008969729964,
|
|
"loss": 5.4371,
|
|
"mean_token_accuracy": 0.1678569346666336,
|
|
"num_tokens": 9600934.0,
|
|
"step": 5530
|
|
},
|
|
{
|
|
"entropy": 5.620938158035278,
|
|
"epoch": 0.4306555144913441,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004985978092725731,
|
|
"loss": 5.438,
|
|
"mean_token_accuracy": 0.16914118379354476,
|
|
"num_tokens": 9609481.0,
|
|
"step": 5535
|
|
},
|
|
{
|
|
"entropy": 5.648740673065186,
|
|
"epoch": 0.4310445438630617,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000498594718179409,
|
|
"loss": 5.3986,
|
|
"mean_token_accuracy": 0.17670834958553314,
|
|
"num_tokens": 9618063.0,
|
|
"step": 5540
|
|
},
|
|
{
|
|
"entropy": 5.684520959854126,
|
|
"epoch": 0.4314335732347792,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004985916236935508,
|
|
"loss": 5.4971,
|
|
"mean_token_accuracy": 0.16753216981887817,
|
|
"num_tokens": 9626144.0,
|
|
"step": 5545
|
|
},
|
|
{
|
|
"entropy": 5.505285263061523,
|
|
"epoch": 0.4318226026064968,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004985885258150458,
|
|
"loss": 5.4478,
|
|
"mean_token_accuracy": 0.16409727483987807,
|
|
"num_tokens": 9635328.0,
|
|
"step": 5550
|
|
},
|
|
{
|
|
"entropy": 5.708357429504394,
|
|
"epoch": 0.43221163197821433,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004985854245439408,
|
|
"loss": 5.5821,
|
|
"mean_token_accuracy": 0.15840986222028733,
|
|
"num_tokens": 9644529.0,
|
|
"step": 5555
|
|
},
|
|
{
|
|
"entropy": 5.714259147644043,
|
|
"epoch": 0.4326006613499319,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004985823198802827,
|
|
"loss": 5.5619,
|
|
"mean_token_accuracy": 0.16070234626531602,
|
|
"num_tokens": 9653763.0,
|
|
"step": 5560
|
|
},
|
|
{
|
|
"entropy": 5.677303123474121,
|
|
"epoch": 0.4329896907216495,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004985792118241188,
|
|
"loss": 5.4124,
|
|
"mean_token_accuracy": 0.16904089003801345,
|
|
"num_tokens": 9661433.0,
|
|
"step": 5565
|
|
},
|
|
{
|
|
"entropy": 5.617642974853515,
|
|
"epoch": 0.43337872009336703,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004985761003754961,
|
|
"loss": 5.3728,
|
|
"mean_token_accuracy": 0.17089153975248336,
|
|
"num_tokens": 9669688.0,
|
|
"step": 5570
|
|
},
|
|
{
|
|
"entropy": 5.727176284790039,
|
|
"epoch": 0.4337677494650846,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004985729855344622,
|
|
"loss": 5.501,
|
|
"mean_token_accuracy": 0.1625591918826103,
|
|
"num_tokens": 9678403.0,
|
|
"step": 5575
|
|
},
|
|
{
|
|
"entropy": 5.720705986022949,
|
|
"epoch": 0.4341567788368022,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000498569867301064,
|
|
"loss": 5.6101,
|
|
"mean_token_accuracy": 0.15884283632040025,
|
|
"num_tokens": 9687504.0,
|
|
"step": 5580
|
|
},
|
|
{
|
|
"entropy": 5.6991945743560795,
|
|
"epoch": 0.43454580820851973,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004985667456753489,
|
|
"loss": 5.4131,
|
|
"mean_token_accuracy": 0.17116089910268784,
|
|
"num_tokens": 9695772.0,
|
|
"step": 5585
|
|
},
|
|
{
|
|
"entropy": 5.674344444274903,
|
|
"epoch": 0.4349348375802373,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004985636206573642,
|
|
"loss": 5.5033,
|
|
"mean_token_accuracy": 0.16308315098285675,
|
|
"num_tokens": 9704150.0,
|
|
"step": 5590
|
|
},
|
|
{
|
|
"entropy": 5.590923118591308,
|
|
"epoch": 0.43532386695195485,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004985604922471575,
|
|
"loss": 5.3951,
|
|
"mean_token_accuracy": 0.17157694697380066,
|
|
"num_tokens": 9712245.0,
|
|
"step": 5595
|
|
},
|
|
{
|
|
"entropy": 5.654242897033692,
|
|
"epoch": 0.43571289632367244,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004985573604447761,
|
|
"loss": 5.5305,
|
|
"mean_token_accuracy": 0.16453358978033067,
|
|
"num_tokens": 9721027.0,
|
|
"step": 5600
|
|
},
|
|
{
|
|
"entropy": 5.711980819702148,
|
|
"epoch": 0.43610192569539,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004985542252502676,
|
|
"loss": 5.4444,
|
|
"mean_token_accuracy": 0.16885592490434648,
|
|
"num_tokens": 9728939.0,
|
|
"step": 5605
|
|
},
|
|
{
|
|
"entropy": 5.7844501495361325,
|
|
"epoch": 0.43649095506710756,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004985510866636796,
|
|
"loss": 5.5907,
|
|
"mean_token_accuracy": 0.1631284847855568,
|
|
"num_tokens": 9737863.0,
|
|
"step": 5610
|
|
},
|
|
{
|
|
"entropy": 5.698635053634644,
|
|
"epoch": 0.43687998443882514,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004985479446850596,
|
|
"loss": 5.5837,
|
|
"mean_token_accuracy": 0.1567772939801216,
|
|
"num_tokens": 9747666.0,
|
|
"step": 5615
|
|
},
|
|
{
|
|
"entropy": 5.684486770629883,
|
|
"epoch": 0.4372690138105427,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004985447993144554,
|
|
"loss": 5.4584,
|
|
"mean_token_accuracy": 0.16718821227550507,
|
|
"num_tokens": 9756595.0,
|
|
"step": 5620
|
|
},
|
|
{
|
|
"entropy": 5.712073850631714,
|
|
"epoch": 0.43765804318226026,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004985416505519147,
|
|
"loss": 5.4999,
|
|
"mean_token_accuracy": 0.1649112544953823,
|
|
"num_tokens": 9764747.0,
|
|
"step": 5625
|
|
},
|
|
{
|
|
"entropy": 5.652025318145752,
|
|
"epoch": 0.43804707255397785,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004985384983974853,
|
|
"loss": 5.4463,
|
|
"mean_token_accuracy": 0.16301581412553787,
|
|
"num_tokens": 9772992.0,
|
|
"step": 5630
|
|
},
|
|
{
|
|
"entropy": 5.686571645736694,
|
|
"epoch": 0.4384361019256954,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004985353428512148,
|
|
"loss": 5.4258,
|
|
"mean_token_accuracy": 0.1694833070039749,
|
|
"num_tokens": 9781107.0,
|
|
"step": 5635
|
|
},
|
|
{
|
|
"entropy": 5.647443580627441,
|
|
"epoch": 0.43882513129741296,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004985321839131514,
|
|
"loss": 5.5052,
|
|
"mean_token_accuracy": 0.16307013034820556,
|
|
"num_tokens": 9790618.0,
|
|
"step": 5640
|
|
},
|
|
{
|
|
"entropy": 5.717783784866333,
|
|
"epoch": 0.4392141606691305,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004985290215833428,
|
|
"loss": 5.5156,
|
|
"mean_token_accuracy": 0.16194633543491363,
|
|
"num_tokens": 9800147.0,
|
|
"step": 5645
|
|
},
|
|
{
|
|
"entropy": 5.715721940994262,
|
|
"epoch": 0.4396031900408481,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004985258558618372,
|
|
"loss": 5.5646,
|
|
"mean_token_accuracy": 0.16524495482444762,
|
|
"num_tokens": 9809056.0,
|
|
"step": 5650
|
|
},
|
|
{
|
|
"entropy": 5.618696165084839,
|
|
"epoch": 0.43999221941256567,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004985226867486825,
|
|
"loss": 5.4272,
|
|
"mean_token_accuracy": 0.16408860236406325,
|
|
"num_tokens": 9817188.0,
|
|
"step": 5655
|
|
},
|
|
{
|
|
"entropy": 5.714680242538452,
|
|
"epoch": 0.4403812487842832,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004985195142439267,
|
|
"loss": 5.6097,
|
|
"mean_token_accuracy": 0.15858251750469207,
|
|
"num_tokens": 9826904.0,
|
|
"step": 5660
|
|
},
|
|
{
|
|
"entropy": 5.736992454528808,
|
|
"epoch": 0.4407702781560008,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004985163383476181,
|
|
"loss": 5.5723,
|
|
"mean_token_accuracy": 0.16299885511398315,
|
|
"num_tokens": 9835937.0,
|
|
"step": 5665
|
|
},
|
|
{
|
|
"entropy": 5.683105325698852,
|
|
"epoch": 0.44115930752771837,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004985131590598048,
|
|
"loss": 5.4063,
|
|
"mean_token_accuracy": 0.1738029733300209,
|
|
"num_tokens": 9843695.0,
|
|
"step": 5670
|
|
},
|
|
{
|
|
"entropy": 5.6560663223266605,
|
|
"epoch": 0.4415483368994359,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004985099763805352,
|
|
"loss": 5.4945,
|
|
"mean_token_accuracy": 0.16638974398374556,
|
|
"num_tokens": 9852693.0,
|
|
"step": 5675
|
|
},
|
|
{
|
|
"entropy": 5.623991632461548,
|
|
"epoch": 0.4419373662711535,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004985067903098574,
|
|
"loss": 5.4829,
|
|
"mean_token_accuracy": 0.16771433353424073,
|
|
"num_tokens": 9860251.0,
|
|
"step": 5680
|
|
},
|
|
{
|
|
"entropy": 5.615719366073608,
|
|
"epoch": 0.442326395642871,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004985036008478197,
|
|
"loss": 5.4156,
|
|
"mean_token_accuracy": 0.1630866065621376,
|
|
"num_tokens": 9868319.0,
|
|
"step": 5685
|
|
},
|
|
{
|
|
"entropy": 5.640031862258911,
|
|
"epoch": 0.4427154250145886,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004985004079944707,
|
|
"loss": 5.4628,
|
|
"mean_token_accuracy": 0.16223709285259247,
|
|
"num_tokens": 9877119.0,
|
|
"step": 5690
|
|
},
|
|
{
|
|
"entropy": 5.790488576889038,
|
|
"epoch": 0.4431044543863062,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004984972117498587,
|
|
"loss": 5.5575,
|
|
"mean_token_accuracy": 0.166337251663208,
|
|
"num_tokens": 9886015.0,
|
|
"step": 5695
|
|
},
|
|
{
|
|
"entropy": 5.686664581298828,
|
|
"epoch": 0.4434934837580237,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004984940121140323,
|
|
"loss": 5.4812,
|
|
"mean_token_accuracy": 0.16396376192569734,
|
|
"num_tokens": 9894829.0,
|
|
"step": 5700
|
|
},
|
|
{
|
|
"entropy": 5.795527458190918,
|
|
"epoch": 0.4438825131297413,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00049849080908704,
|
|
"loss": 5.7308,
|
|
"mean_token_accuracy": 0.15216802060604095,
|
|
"num_tokens": 9904840.0,
|
|
"step": 5705
|
|
},
|
|
{
|
|
"entropy": 5.80095853805542,
|
|
"epoch": 0.44427154250145884,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004984876026689302,
|
|
"loss": 5.5701,
|
|
"mean_token_accuracy": 0.15765475034713744,
|
|
"num_tokens": 9913535.0,
|
|
"step": 5710
|
|
},
|
|
{
|
|
"entropy": 5.7146790504455565,
|
|
"epoch": 0.4446605718731764,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000498484392859752,
|
|
"loss": 5.4808,
|
|
"mean_token_accuracy": 0.16396805197000502,
|
|
"num_tokens": 9921676.0,
|
|
"step": 5715
|
|
},
|
|
{
|
|
"entropy": 5.652966928482056,
|
|
"epoch": 0.445049601244894,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004984811796595538,
|
|
"loss": 5.5499,
|
|
"mean_token_accuracy": 0.16289856731891633,
|
|
"num_tokens": 9930321.0,
|
|
"step": 5720
|
|
},
|
|
{
|
|
"entropy": 5.68314380645752,
|
|
"epoch": 0.44543863061661154,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004984779630683843,
|
|
"loss": 5.4838,
|
|
"mean_token_accuracy": 0.16582090109586717,
|
|
"num_tokens": 9939324.0,
|
|
"step": 5725
|
|
},
|
|
{
|
|
"entropy": 5.685439920425415,
|
|
"epoch": 0.44582765998832913,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004984747430862924,
|
|
"loss": 5.5041,
|
|
"mean_token_accuracy": 0.1700365960597992,
|
|
"num_tokens": 9948603.0,
|
|
"step": 5730
|
|
},
|
|
{
|
|
"entropy": 5.616638231277466,
|
|
"epoch": 0.44621668936004666,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004984715197133271,
|
|
"loss": 5.4122,
|
|
"mean_token_accuracy": 0.16867141276597977,
|
|
"num_tokens": 9957165.0,
|
|
"step": 5735
|
|
},
|
|
{
|
|
"entropy": 5.712148952484131,
|
|
"epoch": 0.44660571873176425,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004984682929495371,
|
|
"loss": 5.5817,
|
|
"mean_token_accuracy": 0.1616025224328041,
|
|
"num_tokens": 9966064.0,
|
|
"step": 5740
|
|
},
|
|
{
|
|
"entropy": 5.599972915649414,
|
|
"epoch": 0.44699474810348183,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004984650627949715,
|
|
"loss": 5.4283,
|
|
"mean_token_accuracy": 0.16223059445619584,
|
|
"num_tokens": 9975146.0,
|
|
"step": 5745
|
|
},
|
|
{
|
|
"entropy": 5.67345404624939,
|
|
"epoch": 0.44738377747519936,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004984618292496792,
|
|
"loss": 5.5229,
|
|
"mean_token_accuracy": 0.16647314578294753,
|
|
"num_tokens": 9983725.0,
|
|
"step": 5750
|
|
},
|
|
{
|
|
"entropy": 5.758822822570801,
|
|
"epoch": 0.44777280684691695,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004984585923137093,
|
|
"loss": 5.5541,
|
|
"mean_token_accuracy": 0.16265189945697783,
|
|
"num_tokens": 9992627.0,
|
|
"step": 5755
|
|
},
|
|
{
|
|
"entropy": 5.647780513763427,
|
|
"epoch": 0.4481618362186345,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000498455351987111,
|
|
"loss": 5.379,
|
|
"mean_token_accuracy": 0.17269414216279982,
|
|
"num_tokens": 10000801.0,
|
|
"step": 5760
|
|
},
|
|
{
|
|
"entropy": 5.711228275299073,
|
|
"epoch": 0.44855086559035207,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004984521082699333,
|
|
"loss": 5.5289,
|
|
"mean_token_accuracy": 0.16474660187959672,
|
|
"num_tokens": 10009421.0,
|
|
"step": 5765
|
|
},
|
|
{
|
|
"entropy": 5.624726390838623,
|
|
"epoch": 0.44893989496206965,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004984488611622256,
|
|
"loss": 5.5169,
|
|
"mean_token_accuracy": 0.16462063044309616,
|
|
"num_tokens": 10018527.0,
|
|
"step": 5770
|
|
},
|
|
{
|
|
"entropy": 5.656307363510132,
|
|
"epoch": 0.4493289243337872,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000498445610664037,
|
|
"loss": 5.4476,
|
|
"mean_token_accuracy": 0.1701345145702362,
|
|
"num_tokens": 10026906.0,
|
|
"step": 5775
|
|
},
|
|
{
|
|
"entropy": 5.647906255722046,
|
|
"epoch": 0.44971795370550477,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.000498442356775417,
|
|
"loss": 5.4396,
|
|
"mean_token_accuracy": 0.1710012897849083,
|
|
"num_tokens": 10035972.0,
|
|
"step": 5780
|
|
},
|
|
{
|
|
"entropy": 5.691563510894776,
|
|
"epoch": 0.45010698307722236,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004984390994964148,
|
|
"loss": 5.5341,
|
|
"mean_token_accuracy": 0.15645694434642793,
|
|
"num_tokens": 10044544.0,
|
|
"step": 5785
|
|
},
|
|
{
|
|
"entropy": 5.74356255531311,
|
|
"epoch": 0.4504960124489399,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00049843583882708,
|
|
"loss": 5.5208,
|
|
"mean_token_accuracy": 0.16705722212791443,
|
|
"num_tokens": 10052880.0,
|
|
"step": 5790
|
|
},
|
|
{
|
|
"entropy": 5.725162506103516,
|
|
"epoch": 0.4508850418206575,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.000498432574767462,
|
|
"loss": 5.5795,
|
|
"mean_token_accuracy": 0.1562555268406868,
|
|
"num_tokens": 10062373.0,
|
|
"step": 5795
|
|
},
|
|
{
|
|
"entropy": 5.6625590324401855,
|
|
"epoch": 0.451274071192375,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004984293073176103,
|
|
"loss": 5.3862,
|
|
"mean_token_accuracy": 0.17116446793079376,
|
|
"num_tokens": 10070473.0,
|
|
"step": 5800
|
|
},
|
|
{
|
|
"entropy": 5.719627332687378,
|
|
"epoch": 0.4516631005640926,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004984260364775744,
|
|
"loss": 5.5189,
|
|
"mean_token_accuracy": 0.16526814699172973,
|
|
"num_tokens": 10079857.0,
|
|
"step": 5805
|
|
},
|
|
{
|
|
"entropy": 5.7111578464508055,
|
|
"epoch": 0.4520521299358102,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000498422762247404,
|
|
"loss": 5.4724,
|
|
"mean_token_accuracy": 0.1682709887623787,
|
|
"num_tokens": 10088326.0,
|
|
"step": 5810
|
|
},
|
|
{
|
|
"entropy": 5.700175476074219,
|
|
"epoch": 0.4524411593075277,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004984194846271489,
|
|
"loss": 5.4182,
|
|
"mean_token_accuracy": 0.16691567450761796,
|
|
"num_tokens": 10097208.0,
|
|
"step": 5815
|
|
},
|
|
{
|
|
"entropy": 5.6884301662445065,
|
|
"epoch": 0.4528301886792453,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004984162036168586,
|
|
"loss": 5.5285,
|
|
"mean_token_accuracy": 0.16202297061681747,
|
|
"num_tokens": 10106057.0,
|
|
"step": 5820
|
|
},
|
|
{
|
|
"entropy": 5.6238037109375,
|
|
"epoch": 0.4532192180509628,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004984129192165831,
|
|
"loss": 5.4342,
|
|
"mean_token_accuracy": 0.16660418659448623,
|
|
"num_tokens": 10115384.0,
|
|
"step": 5825
|
|
},
|
|
{
|
|
"entropy": 5.694101476669312,
|
|
"epoch": 0.4536082474226804,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004984096314263722,
|
|
"loss": 5.5278,
|
|
"mean_token_accuracy": 0.16025744676589965,
|
|
"num_tokens": 10123958.0,
|
|
"step": 5830
|
|
},
|
|
{
|
|
"entropy": 5.730915689468384,
|
|
"epoch": 0.453997276794398,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004984063402462757,
|
|
"loss": 5.4673,
|
|
"mean_token_accuracy": 0.1708914190530777,
|
|
"num_tokens": 10133199.0,
|
|
"step": 5835
|
|
},
|
|
{
|
|
"entropy": 5.665083169937134,
|
|
"epoch": 0.45438630616611553,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004984030456763435,
|
|
"loss": 5.4256,
|
|
"mean_token_accuracy": 0.17243075519800186,
|
|
"num_tokens": 10141796.0,
|
|
"step": 5840
|
|
},
|
|
{
|
|
"entropy": 5.650837755203247,
|
|
"epoch": 0.4547753355378331,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004983997477166257,
|
|
"loss": 5.4456,
|
|
"mean_token_accuracy": 0.16942461729049682,
|
|
"num_tokens": 10149941.0,
|
|
"step": 5845
|
|
},
|
|
{
|
|
"entropy": 5.680732202529907,
|
|
"epoch": 0.45516436490955064,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004983964463671723,
|
|
"loss": 5.5194,
|
|
"mean_token_accuracy": 0.16303732842206956,
|
|
"num_tokens": 10158796.0,
|
|
"step": 5850
|
|
},
|
|
{
|
|
"entropy": 5.688786792755127,
|
|
"epoch": 0.45555339428126823,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004983931416280334,
|
|
"loss": 5.4715,
|
|
"mean_token_accuracy": 0.1647087052464485,
|
|
"num_tokens": 10167328.0,
|
|
"step": 5855
|
|
},
|
|
{
|
|
"entropy": 5.686644268035889,
|
|
"epoch": 0.4559424236529858,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004983898334992591,
|
|
"loss": 5.5311,
|
|
"mean_token_accuracy": 0.1607556089758873,
|
|
"num_tokens": 10175937.0,
|
|
"step": 5860
|
|
},
|
|
{
|
|
"entropy": 5.683647871017456,
|
|
"epoch": 0.45633145302470335,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004983865219808998,
|
|
"loss": 5.483,
|
|
"mean_token_accuracy": 0.15861394256353378,
|
|
"num_tokens": 10184828.0,
|
|
"step": 5865
|
|
},
|
|
{
|
|
"entropy": 5.650877952575684,
|
|
"epoch": 0.45672048239642093,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004983832070730055,
|
|
"loss": 5.4828,
|
|
"mean_token_accuracy": 0.17043073177337648,
|
|
"num_tokens": 10193871.0,
|
|
"step": 5870
|
|
},
|
|
{
|
|
"entropy": 5.6467538356781,
|
|
"epoch": 0.4571095117681385,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004983798887756265,
|
|
"loss": 5.4837,
|
|
"mean_token_accuracy": 0.16615234166383744,
|
|
"num_tokens": 10202740.0,
|
|
"step": 5875
|
|
},
|
|
{
|
|
"entropy": 5.667803430557251,
|
|
"epoch": 0.45749854113985605,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004983765670888133,
|
|
"loss": 5.4391,
|
|
"mean_token_accuracy": 0.16772495806217194,
|
|
"num_tokens": 10210903.0,
|
|
"step": 5880
|
|
},
|
|
{
|
|
"entropy": 5.593382549285889,
|
|
"epoch": 0.45788757051157364,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004983732420126163,
|
|
"loss": 5.3811,
|
|
"mean_token_accuracy": 0.17336988300085068,
|
|
"num_tokens": 10219305.0,
|
|
"step": 5885
|
|
},
|
|
{
|
|
"entropy": 5.730053281784057,
|
|
"epoch": 0.45827659988329117,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004983699135470858,
|
|
"loss": 5.5407,
|
|
"mean_token_accuracy": 0.15575051307678223,
|
|
"num_tokens": 10228575.0,
|
|
"step": 5890
|
|
},
|
|
{
|
|
"entropy": 5.724256181716919,
|
|
"epoch": 0.45866562925500876,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004983665816922723,
|
|
"loss": 5.5317,
|
|
"mean_token_accuracy": 0.1638547196984291,
|
|
"num_tokens": 10237813.0,
|
|
"step": 5895
|
|
},
|
|
{
|
|
"entropy": 5.729646492004394,
|
|
"epoch": 0.45905465862672634,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004983632464482267,
|
|
"loss": 5.5239,
|
|
"mean_token_accuracy": 0.1646823763847351,
|
|
"num_tokens": 10246606.0,
|
|
"step": 5900
|
|
},
|
|
{
|
|
"entropy": 5.59196286201477,
|
|
"epoch": 0.4594436879984439,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004983599078149991,
|
|
"loss": 5.4672,
|
|
"mean_token_accuracy": 0.1709397628903389,
|
|
"num_tokens": 10254996.0,
|
|
"step": 5905
|
|
},
|
|
{
|
|
"entropy": 5.6242005825042725,
|
|
"epoch": 0.45983271737016146,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004983565657926405,
|
|
"loss": 5.532,
|
|
"mean_token_accuracy": 0.16023842841386796,
|
|
"num_tokens": 10263570.0,
|
|
"step": 5910
|
|
},
|
|
{
|
|
"entropy": 5.648565435409546,
|
|
"epoch": 0.460221746741879,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004983532203812017,
|
|
"loss": 5.3797,
|
|
"mean_token_accuracy": 0.17313698977231978,
|
|
"num_tokens": 10272237.0,
|
|
"step": 5915
|
|
},
|
|
{
|
|
"entropy": 5.67567548751831,
|
|
"epoch": 0.4606107761135966,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004983498715807331,
|
|
"loss": 5.5043,
|
|
"mean_token_accuracy": 0.1646430239081383,
|
|
"num_tokens": 10281215.0,
|
|
"step": 5920
|
|
},
|
|
{
|
|
"entropy": 5.718982076644897,
|
|
"epoch": 0.46099980548531416,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004983465193912857,
|
|
"loss": 5.5568,
|
|
"mean_token_accuracy": 0.16212098002433778,
|
|
"num_tokens": 10291054.0,
|
|
"step": 5925
|
|
},
|
|
{
|
|
"entropy": 5.757201385498047,
|
|
"epoch": 0.4613888348570317,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004983431638129104,
|
|
"loss": 5.5401,
|
|
"mean_token_accuracy": 0.16678355485200883,
|
|
"num_tokens": 10299847.0,
|
|
"step": 5930
|
|
},
|
|
{
|
|
"entropy": 5.650951480865478,
|
|
"epoch": 0.4617778642287493,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004983398048456581,
|
|
"loss": 5.4622,
|
|
"mean_token_accuracy": 0.17062322944402694,
|
|
"num_tokens": 10309195.0,
|
|
"step": 5935
|
|
},
|
|
{
|
|
"entropy": 5.680678176879883,
|
|
"epoch": 0.4621668936004668,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004983364424895796,
|
|
"loss": 5.4873,
|
|
"mean_token_accuracy": 0.1661696419119835,
|
|
"num_tokens": 10318386.0,
|
|
"step": 5940
|
|
},
|
|
{
|
|
"entropy": 5.628504467010498,
|
|
"epoch": 0.4625559229721844,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004983330767447262,
|
|
"loss": 5.3888,
|
|
"mean_token_accuracy": 0.16944532841444016,
|
|
"num_tokens": 10327230.0,
|
|
"step": 5945
|
|
},
|
|
{
|
|
"entropy": 5.61873197555542,
|
|
"epoch": 0.462944952343902,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004983297076111489,
|
|
"loss": 5.392,
|
|
"mean_token_accuracy": 0.17210619598627092,
|
|
"num_tokens": 10335617.0,
|
|
"step": 5950
|
|
},
|
|
{
|
|
"entropy": 5.669249582290649,
|
|
"epoch": 0.4633339817156195,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004983263350888987,
|
|
"loss": 5.4704,
|
|
"mean_token_accuracy": 0.16894796639680862,
|
|
"num_tokens": 10344302.0,
|
|
"step": 5955
|
|
},
|
|
{
|
|
"entropy": 5.692659473419189,
|
|
"epoch": 0.4637230110873371,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004983229591780268,
|
|
"loss": 5.517,
|
|
"mean_token_accuracy": 0.16277996301651002,
|
|
"num_tokens": 10352490.0,
|
|
"step": 5960
|
|
},
|
|
{
|
|
"entropy": 5.65666241645813,
|
|
"epoch": 0.46411204045905463,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004983195798785844,
|
|
"loss": 5.447,
|
|
"mean_token_accuracy": 0.16850241869688035,
|
|
"num_tokens": 10361249.0,
|
|
"step": 5965
|
|
},
|
|
{
|
|
"entropy": 5.705624389648437,
|
|
"epoch": 0.4645010698307722,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004983161971906228,
|
|
"loss": 5.5381,
|
|
"mean_token_accuracy": 0.160544715821743,
|
|
"num_tokens": 10370367.0,
|
|
"step": 5970
|
|
},
|
|
{
|
|
"entropy": 5.6782958030700685,
|
|
"epoch": 0.4648900992024898,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004983128111141935,
|
|
"loss": 5.5139,
|
|
"mean_token_accuracy": 0.16174531430006028,
|
|
"num_tokens": 10378429.0,
|
|
"step": 5975
|
|
},
|
|
{
|
|
"entropy": 5.658778047561645,
|
|
"epoch": 0.46527912857420733,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004983094216493475,
|
|
"loss": 5.4224,
|
|
"mean_token_accuracy": 0.16716012358665466,
|
|
"num_tokens": 10386762.0,
|
|
"step": 5980
|
|
},
|
|
{
|
|
"entropy": 5.639854764938354,
|
|
"epoch": 0.4656681579459249,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004983060287961367,
|
|
"loss": 5.4453,
|
|
"mean_token_accuracy": 0.1661702111363411,
|
|
"num_tokens": 10395150.0,
|
|
"step": 5985
|
|
},
|
|
{
|
|
"entropy": 5.6702272415161135,
|
|
"epoch": 0.4660571873176425,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004983026325546123,
|
|
"loss": 5.459,
|
|
"mean_token_accuracy": 0.1709236368536949,
|
|
"num_tokens": 10403941.0,
|
|
"step": 5990
|
|
},
|
|
{
|
|
"entropy": 5.759852409362793,
|
|
"epoch": 0.46644621668936004,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004982992329248257,
|
|
"loss": 5.5393,
|
|
"mean_token_accuracy": 0.15724412649869918,
|
|
"num_tokens": 10413955.0,
|
|
"step": 5995
|
|
},
|
|
{
|
|
"entropy": 5.684827375411987,
|
|
"epoch": 0.4668352460610776,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004982958299068289,
|
|
"loss": 5.4739,
|
|
"mean_token_accuracy": 0.1667661651968956,
|
|
"num_tokens": 10421676.0,
|
|
"step": 6000
|
|
},
|
|
{
|
|
"epoch": 0.4668352460610776,
|
|
"eval_entropy": 5.431893091229319,
|
|
"eval_loss": 5.5091681480407715,
|
|
"eval_mean_token_accuracy": 0.17318276160031815,
|
|
"eval_num_tokens": 10421676.0,
|
|
"eval_runtime": 21.796,
|
|
"eval_samples_per_second": 1906.678,
|
|
"eval_steps_per_second": 238.346,
|
|
"step": 6000
|
|
},
|
|
{
|
|
"entropy": 5.608576107025146,
|
|
"epoch": 0.46722427543279516,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000498292423500673,
|
|
"loss": 5.4398,
|
|
"mean_token_accuracy": 0.17045483589172364,
|
|
"num_tokens": 10430714.0,
|
|
"step": 6005
|
|
},
|
|
{
|
|
"entropy": 5.741376781463623,
|
|
"epoch": 0.46761330480451274,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004982890137064102,
|
|
"loss": 5.5471,
|
|
"mean_token_accuracy": 0.16484737694263457,
|
|
"num_tokens": 10439089.0,
|
|
"step": 6010
|
|
},
|
|
{
|
|
"entropy": 5.6508848667144775,
|
|
"epoch": 0.46800233417623033,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000498285600524092,
|
|
"loss": 5.4615,
|
|
"mean_token_accuracy": 0.16931159645318986,
|
|
"num_tokens": 10447455.0,
|
|
"step": 6015
|
|
},
|
|
{
|
|
"entropy": 5.6349437713623045,
|
|
"epoch": 0.46839136354794786,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004982821839537701,
|
|
"loss": 5.4678,
|
|
"mean_token_accuracy": 0.16561769992113112,
|
|
"num_tokens": 10455936.0,
|
|
"step": 6020
|
|
},
|
|
{
|
|
"entropy": 5.75211615562439,
|
|
"epoch": 0.46878039291966545,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004982787639954966,
|
|
"loss": 5.5923,
|
|
"mean_token_accuracy": 0.15538098365068437,
|
|
"num_tokens": 10465389.0,
|
|
"step": 6025
|
|
},
|
|
{
|
|
"entropy": 5.783642387390136,
|
|
"epoch": 0.469169422291383,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004982753406493232,
|
|
"loss": 5.4733,
|
|
"mean_token_accuracy": 0.1611355021595955,
|
|
"num_tokens": 10474709.0,
|
|
"step": 6030
|
|
},
|
|
{
|
|
"entropy": 5.646716070175171,
|
|
"epoch": 0.46955845166310056,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004982719139153018,
|
|
"loss": 5.4636,
|
|
"mean_token_accuracy": 0.16188982576131822,
|
|
"num_tokens": 10482972.0,
|
|
"step": 6035
|
|
},
|
|
{
|
|
"entropy": 5.6523096561431885,
|
|
"epoch": 0.46994748103481815,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004982684837934845,
|
|
"loss": 5.481,
|
|
"mean_token_accuracy": 0.16894741505384445,
|
|
"num_tokens": 10490897.0,
|
|
"step": 6040
|
|
},
|
|
{
|
|
"entropy": 5.619273662567139,
|
|
"epoch": 0.4703365104065357,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004982650502839234,
|
|
"loss": 5.4739,
|
|
"mean_token_accuracy": 0.16739446222782134,
|
|
"num_tokens": 10499679.0,
|
|
"step": 6045
|
|
},
|
|
{
|
|
"entropy": 5.722547817230224,
|
|
"epoch": 0.47072553977825327,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004982616133866705,
|
|
"loss": 5.5225,
|
|
"mean_token_accuracy": 0.1597910165786743,
|
|
"num_tokens": 10508775.0,
|
|
"step": 6050
|
|
},
|
|
{
|
|
"entropy": 5.640441989898681,
|
|
"epoch": 0.4711145691499708,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004982581731017779,
|
|
"loss": 5.4174,
|
|
"mean_token_accuracy": 0.17352351695299148,
|
|
"num_tokens": 10517600.0,
|
|
"step": 6055
|
|
},
|
|
{
|
|
"entropy": 5.526639747619629,
|
|
"epoch": 0.4715035985216884,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004982547294292979,
|
|
"loss": 5.3753,
|
|
"mean_token_accuracy": 0.17222920656204224,
|
|
"num_tokens": 10525674.0,
|
|
"step": 6060
|
|
},
|
|
{
|
|
"entropy": 5.670207786560058,
|
|
"epoch": 0.47189262789340597,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004982512823692828,
|
|
"loss": 5.5764,
|
|
"mean_token_accuracy": 0.1645464688539505,
|
|
"num_tokens": 10533819.0,
|
|
"step": 6065
|
|
},
|
|
{
|
|
"entropy": 5.665865468978882,
|
|
"epoch": 0.4722816572651235,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004982478319217848,
|
|
"loss": 5.3799,
|
|
"mean_token_accuracy": 0.17236743867397308,
|
|
"num_tokens": 10542901.0,
|
|
"step": 6070
|
|
},
|
|
{
|
|
"entropy": 5.668054580688477,
|
|
"epoch": 0.4726706866368411,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004982443780868562,
|
|
"loss": 5.4694,
|
|
"mean_token_accuracy": 0.16793531328439712,
|
|
"num_tokens": 10552388.0,
|
|
"step": 6075
|
|
},
|
|
{
|
|
"entropy": 5.753566884994507,
|
|
"epoch": 0.4730597160085587,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004982409208645496,
|
|
"loss": 5.5524,
|
|
"mean_token_accuracy": 0.1613159030675888,
|
|
"num_tokens": 10561676.0,
|
|
"step": 6080
|
|
},
|
|
{
|
|
"entropy": 5.723232460021973,
|
|
"epoch": 0.4734487453802762,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004982374602549173,
|
|
"loss": 5.4628,
|
|
"mean_token_accuracy": 0.1703447327017784,
|
|
"num_tokens": 10570037.0,
|
|
"step": 6085
|
|
},
|
|
{
|
|
"entropy": 5.613542985916138,
|
|
"epoch": 0.4738377747519938,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004982339962580119,
|
|
"loss": 5.456,
|
|
"mean_token_accuracy": 0.16250336319208145,
|
|
"num_tokens": 10579140.0,
|
|
"step": 6090
|
|
},
|
|
{
|
|
"entropy": 5.643436861038208,
|
|
"epoch": 0.4742268041237113,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004982305288738859,
|
|
"loss": 5.5145,
|
|
"mean_token_accuracy": 0.1653794452548027,
|
|
"num_tokens": 10587689.0,
|
|
"step": 6095
|
|
},
|
|
{
|
|
"entropy": 5.695700597763062,
|
|
"epoch": 0.4746158334954289,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004982270581025919,
|
|
"loss": 5.393,
|
|
"mean_token_accuracy": 0.17702221274375915,
|
|
"num_tokens": 10596002.0,
|
|
"step": 6100
|
|
},
|
|
{
|
|
"entropy": 5.698622703552246,
|
|
"epoch": 0.4750048628671465,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004982235839441826,
|
|
"loss": 5.6104,
|
|
"mean_token_accuracy": 0.1616410955786705,
|
|
"num_tokens": 10605895.0,
|
|
"step": 6105
|
|
},
|
|
{
|
|
"entropy": 5.72393479347229,
|
|
"epoch": 0.475393892238864,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004982201063987108,
|
|
"loss": 5.5397,
|
|
"mean_token_accuracy": 0.16163956373929977,
|
|
"num_tokens": 10614641.0,
|
|
"step": 6110
|
|
},
|
|
{
|
|
"entropy": 5.671689176559449,
|
|
"epoch": 0.4757829216105816,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004982166254662292,
|
|
"loss": 5.5063,
|
|
"mean_token_accuracy": 0.1643342435359955,
|
|
"num_tokens": 10624381.0,
|
|
"step": 6115
|
|
},
|
|
{
|
|
"entropy": 5.658418941497803,
|
|
"epoch": 0.47617195098229914,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004982131411467904,
|
|
"loss": 5.4881,
|
|
"mean_token_accuracy": 0.16424735337495805,
|
|
"num_tokens": 10632493.0,
|
|
"step": 6120
|
|
},
|
|
{
|
|
"entropy": 5.6930074214935305,
|
|
"epoch": 0.4765609803540167,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004982096534404476,
|
|
"loss": 5.4895,
|
|
"mean_token_accuracy": 0.15681614726781845,
|
|
"num_tokens": 10641556.0,
|
|
"step": 6125
|
|
},
|
|
{
|
|
"entropy": 5.681613540649414,
|
|
"epoch": 0.4769500097257343,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004982061623472535,
|
|
"loss": 5.5616,
|
|
"mean_token_accuracy": 0.16099169477820396,
|
|
"num_tokens": 10649736.0,
|
|
"step": 6130
|
|
},
|
|
{
|
|
"entropy": 5.638624572753907,
|
|
"epoch": 0.47733903909745184,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004982026678672612,
|
|
"loss": 5.388,
|
|
"mean_token_accuracy": 0.1735039621591568,
|
|
"num_tokens": 10657991.0,
|
|
"step": 6135
|
|
},
|
|
{
|
|
"entropy": 5.603248023986817,
|
|
"epoch": 0.47772806846916943,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004981991700005238,
|
|
"loss": 5.444,
|
|
"mean_token_accuracy": 0.1621242195367813,
|
|
"num_tokens": 10667310.0,
|
|
"step": 6140
|
|
},
|
|
{
|
|
"entropy": 5.788144159317016,
|
|
"epoch": 0.47811709784088696,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000498195668747094,
|
|
"loss": 5.5048,
|
|
"mean_token_accuracy": 0.16948303282260896,
|
|
"num_tokens": 10675658.0,
|
|
"step": 6145
|
|
},
|
|
{
|
|
"entropy": 5.66076512336731,
|
|
"epoch": 0.47850612721260455,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004981921641070254,
|
|
"loss": 5.3826,
|
|
"mean_token_accuracy": 0.177694571018219,
|
|
"num_tokens": 10684016.0,
|
|
"step": 6150
|
|
},
|
|
{
|
|
"entropy": 5.634742164611817,
|
|
"epoch": 0.47889515658432213,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004981886560803708,
|
|
"loss": 5.5155,
|
|
"mean_token_accuracy": 0.16364313811063766,
|
|
"num_tokens": 10692814.0,
|
|
"step": 6155
|
|
},
|
|
{
|
|
"entropy": 5.703499889373779,
|
|
"epoch": 0.47928418595603967,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004981851446671838,
|
|
"loss": 5.5152,
|
|
"mean_token_accuracy": 0.16615862548351287,
|
|
"num_tokens": 10701571.0,
|
|
"step": 6160
|
|
},
|
|
{
|
|
"entropy": 5.7480603694915775,
|
|
"epoch": 0.47967321532775725,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004981816298675173,
|
|
"loss": 5.4904,
|
|
"mean_token_accuracy": 0.16190893203020096,
|
|
"num_tokens": 10710569.0,
|
|
"step": 6165
|
|
},
|
|
{
|
|
"entropy": 5.704768991470337,
|
|
"epoch": 0.4800622446994748,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004981781116814248,
|
|
"loss": 5.53,
|
|
"mean_token_accuracy": 0.16690579205751419,
|
|
"num_tokens": 10719277.0,
|
|
"step": 6170
|
|
},
|
|
{
|
|
"entropy": 5.611009645462036,
|
|
"epoch": 0.48045127407119237,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004981745901089596,
|
|
"loss": 5.4,
|
|
"mean_token_accuracy": 0.16918960511684417,
|
|
"num_tokens": 10727174.0,
|
|
"step": 6175
|
|
},
|
|
{
|
|
"entropy": 5.668210077285766,
|
|
"epoch": 0.48084030344290996,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004981710651501753,
|
|
"loss": 5.5189,
|
|
"mean_token_accuracy": 0.1595567524433136,
|
|
"num_tokens": 10736072.0,
|
|
"step": 6180
|
|
},
|
|
{
|
|
"entropy": 5.771615982055664,
|
|
"epoch": 0.4812293328146275,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004981675368051254,
|
|
"loss": 5.51,
|
|
"mean_token_accuracy": 0.17003518491983413,
|
|
"num_tokens": 10745375.0,
|
|
"step": 6185
|
|
},
|
|
{
|
|
"entropy": 5.663010454177856,
|
|
"epoch": 0.4816183621863451,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004981640050738633,
|
|
"loss": 5.5023,
|
|
"mean_token_accuracy": 0.16472843140363694,
|
|
"num_tokens": 10754049.0,
|
|
"step": 6190
|
|
},
|
|
{
|
|
"entropy": 5.5936798572540285,
|
|
"epoch": 0.48200739155806266,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004981604699564426,
|
|
"loss": 5.4438,
|
|
"mean_token_accuracy": 0.16255026012659074,
|
|
"num_tokens": 10763475.0,
|
|
"step": 6195
|
|
},
|
|
{
|
|
"entropy": 5.6747595310211185,
|
|
"epoch": 0.4823964209297802,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004981569314529169,
|
|
"loss": 5.5092,
|
|
"mean_token_accuracy": 0.16237585097551346,
|
|
"num_tokens": 10772100.0,
|
|
"step": 6200
|
|
},
|
|
{
|
|
"entropy": 5.661139869689942,
|
|
"epoch": 0.4827854503014978,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00049815338956334,
|
|
"loss": 5.4652,
|
|
"mean_token_accuracy": 0.16773047298192978,
|
|
"num_tokens": 10780605.0,
|
|
"step": 6205
|
|
},
|
|
{
|
|
"entropy": 5.699847602844239,
|
|
"epoch": 0.4831744796732153,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004981498442877656,
|
|
"loss": 5.4378,
|
|
"mean_token_accuracy": 0.1654672622680664,
|
|
"num_tokens": 10789235.0,
|
|
"step": 6210
|
|
},
|
|
{
|
|
"entropy": 5.676222133636474,
|
|
"epoch": 0.4835635090449329,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004981462956262474,
|
|
"loss": 5.4379,
|
|
"mean_token_accuracy": 0.16388014554977418,
|
|
"num_tokens": 10798078.0,
|
|
"step": 6215
|
|
},
|
|
{
|
|
"entropy": 5.701656341552734,
|
|
"epoch": 0.4839525384166505,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004981427435788396,
|
|
"loss": 5.476,
|
|
"mean_token_accuracy": 0.16313115358352662,
|
|
"num_tokens": 10807667.0,
|
|
"step": 6220
|
|
},
|
|
{
|
|
"entropy": 5.659240579605102,
|
|
"epoch": 0.484341567788368,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004981391881455957,
|
|
"loss": 5.4326,
|
|
"mean_token_accuracy": 0.16373479664325713,
|
|
"num_tokens": 10816574.0,
|
|
"step": 6225
|
|
},
|
|
{
|
|
"entropy": 5.602508211135865,
|
|
"epoch": 0.4847305971600856,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004981356293265696,
|
|
"loss": 5.4349,
|
|
"mean_token_accuracy": 0.16597452610731125,
|
|
"num_tokens": 10824675.0,
|
|
"step": 6230
|
|
},
|
|
{
|
|
"entropy": 5.649123811721802,
|
|
"epoch": 0.4851196265318031,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004981320671218157,
|
|
"loss": 5.3892,
|
|
"mean_token_accuracy": 0.17281295508146285,
|
|
"num_tokens": 10832855.0,
|
|
"step": 6235
|
|
},
|
|
{
|
|
"entropy": 5.552571630477905,
|
|
"epoch": 0.4855086559035207,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004981285015313877,
|
|
"loss": 5.2839,
|
|
"mean_token_accuracy": 0.1768725708127022,
|
|
"num_tokens": 10841603.0,
|
|
"step": 6240
|
|
},
|
|
{
|
|
"entropy": 5.722947072982788,
|
|
"epoch": 0.4858976852752383,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004981249325553399,
|
|
"loss": 5.6348,
|
|
"mean_token_accuracy": 0.15403055697679519,
|
|
"num_tokens": 10850348.0,
|
|
"step": 6245
|
|
},
|
|
{
|
|
"entropy": 5.717859220504761,
|
|
"epoch": 0.48628671464695583,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004981213601937264,
|
|
"loss": 5.3645,
|
|
"mean_token_accuracy": 0.17039883732795716,
|
|
"num_tokens": 10858955.0,
|
|
"step": 6250
|
|
},
|
|
{
|
|
"entropy": 5.680239057540893,
|
|
"epoch": 0.4866757440186734,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004981177844466013,
|
|
"loss": 5.4683,
|
|
"mean_token_accuracy": 0.16246459633111954,
|
|
"num_tokens": 10867336.0,
|
|
"step": 6255
|
|
},
|
|
{
|
|
"entropy": 5.667668294906616,
|
|
"epoch": 0.48706477339039095,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004981142053140192,
|
|
"loss": 5.5273,
|
|
"mean_token_accuracy": 0.1636221796274185,
|
|
"num_tokens": 10877043.0,
|
|
"step": 6260
|
|
},
|
|
{
|
|
"entropy": 5.74675612449646,
|
|
"epoch": 0.48745380276210853,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004981106227960339,
|
|
"loss": 5.4924,
|
|
"mean_token_accuracy": 0.16905430257320403,
|
|
"num_tokens": 10885580.0,
|
|
"step": 6265
|
|
},
|
|
{
|
|
"entropy": 5.727813482284546,
|
|
"epoch": 0.4878428321338261,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004981070368927001,
|
|
"loss": 5.6018,
|
|
"mean_token_accuracy": 0.1581639528274536,
|
|
"num_tokens": 10894289.0,
|
|
"step": 6270
|
|
},
|
|
{
|
|
"entropy": 5.715327215194702,
|
|
"epoch": 0.48823186150554365,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000498103447604072,
|
|
"loss": 5.517,
|
|
"mean_token_accuracy": 0.158392234146595,
|
|
"num_tokens": 10902384.0,
|
|
"step": 6275
|
|
},
|
|
{
|
|
"entropy": 5.6708290576934814,
|
|
"epoch": 0.48862089087726124,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004980998549302044,
|
|
"loss": 5.4309,
|
|
"mean_token_accuracy": 0.17125301510095597,
|
|
"num_tokens": 10911160.0,
|
|
"step": 6280
|
|
},
|
|
{
|
|
"entropy": 5.609786701202393,
|
|
"epoch": 0.4890099202489788,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004980962588711516,
|
|
"loss": 5.3262,
|
|
"mean_token_accuracy": 0.17744140475988388,
|
|
"num_tokens": 10920066.0,
|
|
"step": 6285
|
|
},
|
|
{
|
|
"entropy": 5.692303276062011,
|
|
"epoch": 0.48939894962069636,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000498092659426968,
|
|
"loss": 5.5,
|
|
"mean_token_accuracy": 0.16787974089384078,
|
|
"num_tokens": 10928969.0,
|
|
"step": 6290
|
|
},
|
|
{
|
|
"entropy": 5.7058093547821045,
|
|
"epoch": 0.48978797899241394,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004980890565977085,
|
|
"loss": 5.5191,
|
|
"mean_token_accuracy": 0.16595033705234527,
|
|
"num_tokens": 10936939.0,
|
|
"step": 6295
|
|
},
|
|
{
|
|
"entropy": 5.649946308135986,
|
|
"epoch": 0.4901770083641315,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004980854503834276,
|
|
"loss": 5.4424,
|
|
"mean_token_accuracy": 0.16394996643066406,
|
|
"num_tokens": 10945929.0,
|
|
"step": 6300
|
|
},
|
|
{
|
|
"entropy": 5.677580070495606,
|
|
"epoch": 0.49056603773584906,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004980818407841802,
|
|
"loss": 5.4484,
|
|
"mean_token_accuracy": 0.16683558970689774,
|
|
"num_tokens": 10954849.0,
|
|
"step": 6305
|
|
},
|
|
{
|
|
"entropy": 5.665102910995484,
|
|
"epoch": 0.49095506710756665,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004980782278000207,
|
|
"loss": 5.5227,
|
|
"mean_token_accuracy": 0.16242400258779527,
|
|
"num_tokens": 10963800.0,
|
|
"step": 6310
|
|
},
|
|
{
|
|
"entropy": 5.813465976715088,
|
|
"epoch": 0.4913440964792842,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004980746114310043,
|
|
"loss": 5.5629,
|
|
"mean_token_accuracy": 0.16588517874479294,
|
|
"num_tokens": 10972477.0,
|
|
"step": 6315
|
|
},
|
|
{
|
|
"entropy": 5.7394904613494875,
|
|
"epoch": 0.49173312585100176,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004980709916771858,
|
|
"loss": 5.574,
|
|
"mean_token_accuracy": 0.15996729359030723,
|
|
"num_tokens": 10981437.0,
|
|
"step": 6320
|
|
},
|
|
{
|
|
"entropy": 5.64530758857727,
|
|
"epoch": 0.4921221552227193,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004980673685386198,
|
|
"loss": 5.3954,
|
|
"mean_token_accuracy": 0.1674257069826126,
|
|
"num_tokens": 10989973.0,
|
|
"step": 6325
|
|
},
|
|
{
|
|
"entropy": 5.595485687255859,
|
|
"epoch": 0.4925111845944369,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004980637420153618,
|
|
"loss": 5.4387,
|
|
"mean_token_accuracy": 0.1638665169477463,
|
|
"num_tokens": 10998160.0,
|
|
"step": 6330
|
|
},
|
|
{
|
|
"entropy": 5.694740152359008,
|
|
"epoch": 0.49290021396615447,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004980601121074664,
|
|
"loss": 5.5688,
|
|
"mean_token_accuracy": 0.16035808622837067,
|
|
"num_tokens": 11007127.0,
|
|
"step": 6335
|
|
},
|
|
{
|
|
"entropy": 5.693447637557983,
|
|
"epoch": 0.493289243337872,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004980564788149889,
|
|
"loss": 5.4374,
|
|
"mean_token_accuracy": 0.16625568270683289,
|
|
"num_tokens": 11015518.0,
|
|
"step": 6340
|
|
},
|
|
{
|
|
"entropy": 5.559444856643677,
|
|
"epoch": 0.4936782727095896,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004980528421379844,
|
|
"loss": 5.329,
|
|
"mean_token_accuracy": 0.17834123522043227,
|
|
"num_tokens": 11023739.0,
|
|
"step": 6345
|
|
},
|
|
{
|
|
"entropy": 5.590536737442017,
|
|
"epoch": 0.4940673020813071,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.000498049202076508,
|
|
"loss": 5.3573,
|
|
"mean_token_accuracy": 0.17453927546739578,
|
|
"num_tokens": 11032034.0,
|
|
"step": 6350
|
|
},
|
|
{
|
|
"entropy": 5.632488489151001,
|
|
"epoch": 0.4944563314530247,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004980455586306149,
|
|
"loss": 5.3706,
|
|
"mean_token_accuracy": 0.1736905425786972,
|
|
"num_tokens": 11040319.0,
|
|
"step": 6355
|
|
},
|
|
{
|
|
"entropy": 5.537005805969239,
|
|
"epoch": 0.4948453608247423,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004980419118003605,
|
|
"loss": 5.4304,
|
|
"mean_token_accuracy": 0.16703475266695023,
|
|
"num_tokens": 11049459.0,
|
|
"step": 6360
|
|
},
|
|
{
|
|
"entropy": 5.690892553329467,
|
|
"epoch": 0.4952343901964598,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004980382615858001,
|
|
"loss": 5.4235,
|
|
"mean_token_accuracy": 0.16820919662714004,
|
|
"num_tokens": 11058402.0,
|
|
"step": 6365
|
|
},
|
|
{
|
|
"entropy": 5.6239392280578615,
|
|
"epoch": 0.4956234195681774,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004980346079869892,
|
|
"loss": 5.3726,
|
|
"mean_token_accuracy": 0.1734849825501442,
|
|
"num_tokens": 11067430.0,
|
|
"step": 6370
|
|
},
|
|
{
|
|
"entropy": 5.63100643157959,
|
|
"epoch": 0.49601244893989493,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000498030951003983,
|
|
"loss": 5.3758,
|
|
"mean_token_accuracy": 0.16949167847633362,
|
|
"num_tokens": 11075594.0,
|
|
"step": 6375
|
|
},
|
|
{
|
|
"entropy": 5.613965845108032,
|
|
"epoch": 0.4964014783116125,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004980272906368371,
|
|
"loss": 5.3392,
|
|
"mean_token_accuracy": 0.18207351863384247,
|
|
"num_tokens": 11083509.0,
|
|
"step": 6380
|
|
},
|
|
{
|
|
"entropy": 5.684510564804077,
|
|
"epoch": 0.4967905076833301,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004980236268856071,
|
|
"loss": 5.4953,
|
|
"mean_token_accuracy": 0.16970266103744508,
|
|
"num_tokens": 11091938.0,
|
|
"step": 6385
|
|
},
|
|
{
|
|
"entropy": 5.662152528762817,
|
|
"epoch": 0.49717953705504764,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004980199597503487,
|
|
"loss": 5.5107,
|
|
"mean_token_accuracy": 0.1673850014805794,
|
|
"num_tokens": 11099974.0,
|
|
"step": 6390
|
|
},
|
|
{
|
|
"entropy": 5.520812129974365,
|
|
"epoch": 0.4975685664267652,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004980162892311171,
|
|
"loss": 5.1809,
|
|
"mean_token_accuracy": 0.18767566978931427,
|
|
"num_tokens": 11107944.0,
|
|
"step": 6395
|
|
},
|
|
{
|
|
"entropy": 5.561925792694092,
|
|
"epoch": 0.4979575957984828,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004980126153279684,
|
|
"loss": 5.4691,
|
|
"mean_token_accuracy": 0.17101271003484725,
|
|
"num_tokens": 11116401.0,
|
|
"step": 6400
|
|
},
|
|
{
|
|
"entropy": 5.680764198303223,
|
|
"epoch": 0.49834662517020034,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004980089380409583,
|
|
"loss": 5.4385,
|
|
"mean_token_accuracy": 0.16166648268699646,
|
|
"num_tokens": 11125430.0,
|
|
"step": 6405
|
|
},
|
|
{
|
|
"entropy": 5.714994716644287,
|
|
"epoch": 0.4987356545419179,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004980052573701424,
|
|
"loss": 5.5023,
|
|
"mean_token_accuracy": 0.16102435290813447,
|
|
"num_tokens": 11133949.0,
|
|
"step": 6410
|
|
},
|
|
{
|
|
"entropy": 5.671395254135132,
|
|
"epoch": 0.49912468391363546,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004980015733155767,
|
|
"loss": 5.44,
|
|
"mean_token_accuracy": 0.17307015955448152,
|
|
"num_tokens": 11141749.0,
|
|
"step": 6415
|
|
},
|
|
{
|
|
"entropy": 5.613661623001098,
|
|
"epoch": 0.49951371328535304,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004979978858773171,
|
|
"loss": 5.4345,
|
|
"mean_token_accuracy": 0.1723210409283638,
|
|
"num_tokens": 11150618.0,
|
|
"step": 6420
|
|
},
|
|
{
|
|
"entropy": 5.631605768203736,
|
|
"epoch": 0.49990274265707063,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004979941950554195,
|
|
"loss": 5.4654,
|
|
"mean_token_accuracy": 0.17086824923753738,
|
|
"num_tokens": 11158549.0,
|
|
"step": 6425
|
|
},
|
|
{
|
|
"entropy": 5.647154426574707,
|
|
"epoch": 0.5002917720287882,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004979905008499399,
|
|
"loss": 5.4042,
|
|
"mean_token_accuracy": 0.1790368750691414,
|
|
"num_tokens": 11167131.0,
|
|
"step": 6430
|
|
},
|
|
{
|
|
"entropy": 5.637821531295776,
|
|
"epoch": 0.5006808014005057,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004979868032609344,
|
|
"loss": 5.4883,
|
|
"mean_token_accuracy": 0.16543890535831451,
|
|
"num_tokens": 11175766.0,
|
|
"step": 6435
|
|
},
|
|
{
|
|
"entropy": 5.635375261306763,
|
|
"epoch": 0.5010698307722233,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004979831022884591,
|
|
"loss": 5.451,
|
|
"mean_token_accuracy": 0.17667505741119385,
|
|
"num_tokens": 11184799.0,
|
|
"step": 6440
|
|
},
|
|
{
|
|
"entropy": 5.610274791717529,
|
|
"epoch": 0.5014588601439409,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004979793979325701,
|
|
"loss": 5.3767,
|
|
"mean_token_accuracy": 0.16970710307359696,
|
|
"num_tokens": 11193083.0,
|
|
"step": 6445
|
|
},
|
|
{
|
|
"entropy": 5.606352710723877,
|
|
"epoch": 0.5018478895156584,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004979756901933236,
|
|
"loss": 5.3955,
|
|
"mean_token_accuracy": 0.17012580037117003,
|
|
"num_tokens": 11201753.0,
|
|
"step": 6450
|
|
},
|
|
{
|
|
"entropy": 5.6947142601013185,
|
|
"epoch": 0.502236918887376,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000497971979070776,
|
|
"loss": 5.4968,
|
|
"mean_token_accuracy": 0.1657540574669838,
|
|
"num_tokens": 11209965.0,
|
|
"step": 6455
|
|
},
|
|
{
|
|
"entropy": 5.6152198791503904,
|
|
"epoch": 0.5026259482590936,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004979682645649834,
|
|
"loss": 5.3652,
|
|
"mean_token_accuracy": 0.17716653347015382,
|
|
"num_tokens": 11217961.0,
|
|
"step": 6460
|
|
},
|
|
{
|
|
"entropy": 5.634564304351807,
|
|
"epoch": 0.5030149776308112,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004979645466760025,
|
|
"loss": 5.5001,
|
|
"mean_token_accuracy": 0.16121395379304887,
|
|
"num_tokens": 11225803.0,
|
|
"step": 6465
|
|
},
|
|
{
|
|
"entropy": 5.637865304946899,
|
|
"epoch": 0.5034040070025287,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004979608254038892,
|
|
"loss": 5.3456,
|
|
"mean_token_accuracy": 0.17098010927438737,
|
|
"num_tokens": 11234584.0,
|
|
"step": 6470
|
|
},
|
|
{
|
|
"entropy": 5.71119327545166,
|
|
"epoch": 0.5037930363742462,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004979571007487003,
|
|
"loss": 5.536,
|
|
"mean_token_accuracy": 0.16245963275432587,
|
|
"num_tokens": 11243340.0,
|
|
"step": 6475
|
|
},
|
|
{
|
|
"entropy": 5.619586372375489,
|
|
"epoch": 0.5041820657459638,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004979533727104924,
|
|
"loss": 5.3997,
|
|
"mean_token_accuracy": 0.16557498127222062,
|
|
"num_tokens": 11252383.0,
|
|
"step": 6480
|
|
},
|
|
{
|
|
"entropy": 5.646946907043457,
|
|
"epoch": 0.5045710951176814,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000497949641289322,
|
|
"loss": 5.4775,
|
|
"mean_token_accuracy": 0.16912005543708802,
|
|
"num_tokens": 11261419.0,
|
|
"step": 6485
|
|
},
|
|
{
|
|
"entropy": 5.654446411132812,
|
|
"epoch": 0.504960124489399,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004979459064852456,
|
|
"loss": 5.4496,
|
|
"mean_token_accuracy": 0.16540549248456954,
|
|
"num_tokens": 11270743.0,
|
|
"step": 6490
|
|
},
|
|
{
|
|
"entropy": 5.638967895507813,
|
|
"epoch": 0.5053491538611166,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004979421682983197,
|
|
"loss": 5.3424,
|
|
"mean_token_accuracy": 0.17329360842704772,
|
|
"num_tokens": 11279666.0,
|
|
"step": 6495
|
|
},
|
|
{
|
|
"entropy": 5.669098615646362,
|
|
"epoch": 0.505738183232834,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004979384267286015,
|
|
"loss": 5.5363,
|
|
"mean_token_accuracy": 0.16254350841045379,
|
|
"num_tokens": 11288710.0,
|
|
"step": 6500
|
|
},
|
|
{
|
|
"entropy": 5.661252021789551,
|
|
"epoch": 0.5061272126045516,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004979346817761475,
|
|
"loss": 5.4092,
|
|
"mean_token_accuracy": 0.16631939113140107,
|
|
"num_tokens": 11297665.0,
|
|
"step": 6505
|
|
},
|
|
{
|
|
"entropy": 5.697106981277466,
|
|
"epoch": 0.5065162419762692,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004979309334410144,
|
|
"loss": 5.5657,
|
|
"mean_token_accuracy": 0.15991870909929276,
|
|
"num_tokens": 11306751.0,
|
|
"step": 6510
|
|
},
|
|
{
|
|
"entropy": 5.708811950683594,
|
|
"epoch": 0.5069052713479868,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004979271817232594,
|
|
"loss": 5.5537,
|
|
"mean_token_accuracy": 0.15796037316322326,
|
|
"num_tokens": 11315659.0,
|
|
"step": 6515
|
|
},
|
|
{
|
|
"entropy": 5.689514636993408,
|
|
"epoch": 0.5072943007197044,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004979234266229391,
|
|
"loss": 5.4448,
|
|
"mean_token_accuracy": 0.1685910552740097,
|
|
"num_tokens": 11323362.0,
|
|
"step": 6520
|
|
},
|
|
{
|
|
"entropy": 5.656657600402832,
|
|
"epoch": 0.5076833300914219,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004979196681401106,
|
|
"loss": 5.4477,
|
|
"mean_token_accuracy": 0.1603214606642723,
|
|
"num_tokens": 11332343.0,
|
|
"step": 6525
|
|
},
|
|
{
|
|
"entropy": 5.6222803592681885,
|
|
"epoch": 0.5080723594631394,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000497915906274831,
|
|
"loss": 5.3762,
|
|
"mean_token_accuracy": 0.16662061214447021,
|
|
"num_tokens": 11340816.0,
|
|
"step": 6530
|
|
},
|
|
{
|
|
"entropy": 5.590240573883056,
|
|
"epoch": 0.508461388834857,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004979121410271574,
|
|
"loss": 5.3876,
|
|
"mean_token_accuracy": 0.16722644865512848,
|
|
"num_tokens": 11349728.0,
|
|
"step": 6535
|
|
},
|
|
{
|
|
"entropy": 5.669598007202149,
|
|
"epoch": 0.5088504182065746,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004979083723971468,
|
|
"loss": 5.4995,
|
|
"mean_token_accuracy": 0.16796678602695464,
|
|
"num_tokens": 11358477.0,
|
|
"step": 6540
|
|
},
|
|
{
|
|
"entropy": 5.5297510623931885,
|
|
"epoch": 0.5092394475782922,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004979046003848564,
|
|
"loss": 5.3225,
|
|
"mean_token_accuracy": 0.17740241587162017,
|
|
"num_tokens": 11367183.0,
|
|
"step": 6545
|
|
},
|
|
{
|
|
"entropy": 5.656442737579345,
|
|
"epoch": 0.5096284769500097,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004979008249903435,
|
|
"loss": 5.5264,
|
|
"mean_token_accuracy": 0.15788258463144303,
|
|
"num_tokens": 11376703.0,
|
|
"step": 6550
|
|
},
|
|
{
|
|
"entropy": 5.7535947322845455,
|
|
"epoch": 0.5100175063217273,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004978970462136655,
|
|
"loss": 5.5325,
|
|
"mean_token_accuracy": 0.16580595076084137,
|
|
"num_tokens": 11385502.0,
|
|
"step": 6555
|
|
},
|
|
{
|
|
"entropy": 5.637090444564819,
|
|
"epoch": 0.5104065356934449,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004978932640548794,
|
|
"loss": 5.3987,
|
|
"mean_token_accuracy": 0.17354696840047837,
|
|
"num_tokens": 11393947.0,
|
|
"step": 6560
|
|
},
|
|
{
|
|
"entropy": 5.577970886230469,
|
|
"epoch": 0.5107955650651624,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004978894785140429,
|
|
"loss": 5.3901,
|
|
"mean_token_accuracy": 0.17127427607774734,
|
|
"num_tokens": 11403077.0,
|
|
"step": 6565
|
|
},
|
|
{
|
|
"entropy": 5.572803497314453,
|
|
"epoch": 0.51118459443688,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004978856895912132,
|
|
"loss": 5.3867,
|
|
"mean_token_accuracy": 0.1690242201089859,
|
|
"num_tokens": 11411863.0,
|
|
"step": 6570
|
|
},
|
|
{
|
|
"entropy": 5.644185352325439,
|
|
"epoch": 0.5115736238085975,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004978818972864481,
|
|
"loss": 5.3522,
|
|
"mean_token_accuracy": 0.1726667046546936,
|
|
"num_tokens": 11420030.0,
|
|
"step": 6575
|
|
},
|
|
{
|
|
"entropy": 5.679980611801147,
|
|
"epoch": 0.5119626531803151,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004978781015998048,
|
|
"loss": 5.429,
|
|
"mean_token_accuracy": 0.16585396677255632,
|
|
"num_tokens": 11428534.0,
|
|
"step": 6580
|
|
},
|
|
{
|
|
"entropy": 5.6785746097564695,
|
|
"epoch": 0.5123516825520327,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004978743025313413,
|
|
"loss": 5.4153,
|
|
"mean_token_accuracy": 0.17318394929170608,
|
|
"num_tokens": 11436641.0,
|
|
"step": 6585
|
|
},
|
|
{
|
|
"entropy": 5.611976623535156,
|
|
"epoch": 0.5127407119237503,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004978705000811148,
|
|
"loss": 5.4042,
|
|
"mean_token_accuracy": 0.1705085426568985,
|
|
"num_tokens": 11444595.0,
|
|
"step": 6590
|
|
},
|
|
{
|
|
"entropy": 5.578699254989624,
|
|
"epoch": 0.5131297412954678,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004978666942491832,
|
|
"loss": 5.2582,
|
|
"mean_token_accuracy": 0.1794433295726776,
|
|
"num_tokens": 11453257.0,
|
|
"step": 6595
|
|
},
|
|
{
|
|
"entropy": 5.621994495391846,
|
|
"epoch": 0.5135187706671853,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004978628850356043,
|
|
"loss": 5.4233,
|
|
"mean_token_accuracy": 0.17493958324193953,
|
|
"num_tokens": 11461762.0,
|
|
"step": 6600
|
|
},
|
|
{
|
|
"entropy": 5.625024843215942,
|
|
"epoch": 0.5139078000389029,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004978590724404358,
|
|
"loss": 5.3386,
|
|
"mean_token_accuracy": 0.17288504540920258,
|
|
"num_tokens": 11470602.0,
|
|
"step": 6605
|
|
},
|
|
{
|
|
"entropy": 5.679289627075195,
|
|
"epoch": 0.5142968294106205,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004978552564637356,
|
|
"loss": 5.4435,
|
|
"mean_token_accuracy": 0.16734055280685425,
|
|
"num_tokens": 11479826.0,
|
|
"step": 6610
|
|
},
|
|
{
|
|
"entropy": 5.6650903701782225,
|
|
"epoch": 0.5146858587823381,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004978514371055616,
|
|
"loss": 5.4934,
|
|
"mean_token_accuracy": 0.16676056981086732,
|
|
"num_tokens": 11488698.0,
|
|
"step": 6615
|
|
},
|
|
{
|
|
"entropy": 5.700325441360474,
|
|
"epoch": 0.5150748881540557,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004978476143659718,
|
|
"loss": 5.4767,
|
|
"mean_token_accuracy": 0.1701172336935997,
|
|
"num_tokens": 11497434.0,
|
|
"step": 6620
|
|
},
|
|
{
|
|
"entropy": 5.6457771301269535,
|
|
"epoch": 0.5154639175257731,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004978437882450241,
|
|
"loss": 5.4921,
|
|
"mean_token_accuracy": 0.16389915943145753,
|
|
"num_tokens": 11506173.0,
|
|
"step": 6625
|
|
},
|
|
{
|
|
"entropy": 5.666603851318359,
|
|
"epoch": 0.5158529468974907,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004978399587427766,
|
|
"loss": 5.4015,
|
|
"mean_token_accuracy": 0.17104636281728744,
|
|
"num_tokens": 11514824.0,
|
|
"step": 6630
|
|
},
|
|
{
|
|
"entropy": 5.634468507766724,
|
|
"epoch": 0.5162419762692083,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004978361258592874,
|
|
"loss": 5.459,
|
|
"mean_token_accuracy": 0.15855541080236435,
|
|
"num_tokens": 11523634.0,
|
|
"step": 6635
|
|
},
|
|
{
|
|
"entropy": 5.744538164138794,
|
|
"epoch": 0.5166310056409259,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004978322895946147,
|
|
"loss": 5.5689,
|
|
"mean_token_accuracy": 0.16215945929288864,
|
|
"num_tokens": 11531916.0,
|
|
"step": 6640
|
|
},
|
|
{
|
|
"entropy": 5.667070627212524,
|
|
"epoch": 0.5170200350126435,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004978284499488167,
|
|
"loss": 5.3887,
|
|
"mean_token_accuracy": 0.16777578592300416,
|
|
"num_tokens": 11540000.0,
|
|
"step": 6645
|
|
},
|
|
{
|
|
"entropy": 5.720247840881347,
|
|
"epoch": 0.5174090643843611,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004978246069219516,
|
|
"loss": 5.4711,
|
|
"mean_token_accuracy": 0.16854884028434752,
|
|
"num_tokens": 11548760.0,
|
|
"step": 6650
|
|
},
|
|
{
|
|
"entropy": 5.600211334228516,
|
|
"epoch": 0.5177980937560785,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004978207605140777,
|
|
"loss": 5.3013,
|
|
"mean_token_accuracy": 0.17687248587608337,
|
|
"num_tokens": 11557991.0,
|
|
"step": 6655
|
|
},
|
|
{
|
|
"entropy": 5.582965087890625,
|
|
"epoch": 0.5181871231277961,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004978169107252534,
|
|
"loss": 5.375,
|
|
"mean_token_accuracy": 0.17161434441804885,
|
|
"num_tokens": 11566638.0,
|
|
"step": 6660
|
|
},
|
|
{
|
|
"entropy": 5.529303884506225,
|
|
"epoch": 0.5185761524995137,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004978130575555373,
|
|
"loss": 5.3102,
|
|
"mean_token_accuracy": 0.1714066445827484,
|
|
"num_tokens": 11575106.0,
|
|
"step": 6665
|
|
},
|
|
{
|
|
"entropy": 5.571141386032105,
|
|
"epoch": 0.5189651818712313,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004978092010049877,
|
|
"loss": 5.4538,
|
|
"mean_token_accuracy": 0.1577305719256401,
|
|
"num_tokens": 11583971.0,
|
|
"step": 6670
|
|
},
|
|
{
|
|
"entropy": 5.640804672241211,
|
|
"epoch": 0.5193542112429489,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.000497805341073663,
|
|
"loss": 5.4474,
|
|
"mean_token_accuracy": 0.16622724384069443,
|
|
"num_tokens": 11592936.0,
|
|
"step": 6675
|
|
},
|
|
{
|
|
"entropy": 5.64942626953125,
|
|
"epoch": 0.5197432406146664,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004978014777616219,
|
|
"loss": 5.3465,
|
|
"mean_token_accuracy": 0.1758352756500244,
|
|
"num_tokens": 11602055.0,
|
|
"step": 6680
|
|
},
|
|
{
|
|
"entropy": 5.631604099273682,
|
|
"epoch": 0.520132269986384,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004977976110689229,
|
|
"loss": 5.3533,
|
|
"mean_token_accuracy": 0.17612868696451187,
|
|
"num_tokens": 11610211.0,
|
|
"step": 6685
|
|
},
|
|
{
|
|
"entropy": 5.666025066375733,
|
|
"epoch": 0.5205212993581015,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000497793740995625,
|
|
"loss": 5.4378,
|
|
"mean_token_accuracy": 0.1702517494559288,
|
|
"num_tokens": 11619096.0,
|
|
"step": 6690
|
|
},
|
|
{
|
|
"entropy": 5.6196661472320555,
|
|
"epoch": 0.5209103287298191,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004977898675417866,
|
|
"loss": 5.5078,
|
|
"mean_token_accuracy": 0.17089473754167556,
|
|
"num_tokens": 11628142.0,
|
|
"step": 6695
|
|
},
|
|
{
|
|
"entropy": 5.675712394714355,
|
|
"epoch": 0.5212993581015367,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004977859907074664,
|
|
"loss": 5.3536,
|
|
"mean_token_accuracy": 0.1730503797531128,
|
|
"num_tokens": 11635961.0,
|
|
"step": 6700
|
|
},
|
|
{
|
|
"entropy": 5.674269342422486,
|
|
"epoch": 0.5216883874732542,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004977821104927236,
|
|
"loss": 5.4708,
|
|
"mean_token_accuracy": 0.1689344897866249,
|
|
"num_tokens": 11644778.0,
|
|
"step": 6705
|
|
},
|
|
{
|
|
"entropy": 5.628959465026855,
|
|
"epoch": 0.5220774168449718,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004977782268976167,
|
|
"loss": 5.4639,
|
|
"mean_token_accuracy": 0.16584417819976807,
|
|
"num_tokens": 11654043.0,
|
|
"step": 6710
|
|
},
|
|
{
|
|
"entropy": 5.666242885589599,
|
|
"epoch": 0.5224664462166894,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004977743399222048,
|
|
"loss": 5.4486,
|
|
"mean_token_accuracy": 0.16625992506742476,
|
|
"num_tokens": 11662794.0,
|
|
"step": 6715
|
|
},
|
|
{
|
|
"entropy": 5.605064916610718,
|
|
"epoch": 0.522855475588407,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004977704495665471,
|
|
"loss": 5.4409,
|
|
"mean_token_accuracy": 0.17458575814962388,
|
|
"num_tokens": 11670624.0,
|
|
"step": 6720
|
|
},
|
|
{
|
|
"entropy": 5.560970878601074,
|
|
"epoch": 0.5232445049601245,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004977665558307023,
|
|
"loss": 5.3436,
|
|
"mean_token_accuracy": 0.1714425042271614,
|
|
"num_tokens": 11679366.0,
|
|
"step": 6725
|
|
},
|
|
{
|
|
"entropy": 5.57506365776062,
|
|
"epoch": 0.523633534331842,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004977626587147295,
|
|
"loss": 5.2532,
|
|
"mean_token_accuracy": 0.17893183827400208,
|
|
"num_tokens": 11688137.0,
|
|
"step": 6730
|
|
},
|
|
{
|
|
"entropy": 5.5754714012146,
|
|
"epoch": 0.5240225637035596,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000497758758218688,
|
|
"loss": 5.3879,
|
|
"mean_token_accuracy": 0.1726705551147461,
|
|
"num_tokens": 11697236.0,
|
|
"step": 6735
|
|
},
|
|
{
|
|
"entropy": 5.620447826385498,
|
|
"epoch": 0.5244115930752772,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004977548543426368,
|
|
"loss": 5.3889,
|
|
"mean_token_accuracy": 0.1749192327260971,
|
|
"num_tokens": 11706513.0,
|
|
"step": 6740
|
|
},
|
|
{
|
|
"entropy": 5.649651384353637,
|
|
"epoch": 0.5248006224469948,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004977509470866353,
|
|
"loss": 5.3506,
|
|
"mean_token_accuracy": 0.17255444675683976,
|
|
"num_tokens": 11715239.0,
|
|
"step": 6745
|
|
},
|
|
{
|
|
"entropy": 5.605628538131714,
|
|
"epoch": 0.5251896518187124,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004977470364507427,
|
|
"loss": 5.3942,
|
|
"mean_token_accuracy": 0.17865999937057495,
|
|
"num_tokens": 11724086.0,
|
|
"step": 6750
|
|
},
|
|
{
|
|
"entropy": 5.576850509643554,
|
|
"epoch": 0.5255786811904298,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004977431224350184,
|
|
"loss": 5.4121,
|
|
"mean_token_accuracy": 0.17535001784563065,
|
|
"num_tokens": 11731975.0,
|
|
"step": 6755
|
|
},
|
|
{
|
|
"entropy": 5.5735608577728275,
|
|
"epoch": 0.5259677105621474,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004977392050395217,
|
|
"loss": 5.4015,
|
|
"mean_token_accuracy": 0.1689216673374176,
|
|
"num_tokens": 11741172.0,
|
|
"step": 6760
|
|
},
|
|
{
|
|
"entropy": 5.618299150466919,
|
|
"epoch": 0.526356739933865,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004977352842643121,
|
|
"loss": 5.3595,
|
|
"mean_token_accuracy": 0.17527500689029693,
|
|
"num_tokens": 11750609.0,
|
|
"step": 6765
|
|
},
|
|
{
|
|
"entropy": 5.5818558692932125,
|
|
"epoch": 0.5267457693055826,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000497731360109449,
|
|
"loss": 5.3606,
|
|
"mean_token_accuracy": 0.1736464872956276,
|
|
"num_tokens": 11758901.0,
|
|
"step": 6770
|
|
},
|
|
{
|
|
"entropy": 5.52725043296814,
|
|
"epoch": 0.5271347986773002,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004977274325749922,
|
|
"loss": 5.3077,
|
|
"mean_token_accuracy": 0.17586426734924315,
|
|
"num_tokens": 11767202.0,
|
|
"step": 6775
|
|
},
|
|
{
|
|
"entropy": 5.585738468170166,
|
|
"epoch": 0.5275238280490177,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004977235016610011,
|
|
"loss": 5.4002,
|
|
"mean_token_accuracy": 0.17273519486188887,
|
|
"num_tokens": 11776164.0,
|
|
"step": 6780
|
|
},
|
|
{
|
|
"entropy": 5.578510379791259,
|
|
"epoch": 0.5279128574207352,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004977195673675353,
|
|
"loss": 5.3631,
|
|
"mean_token_accuracy": 0.17961377501487732,
|
|
"num_tokens": 11784548.0,
|
|
"step": 6785
|
|
},
|
|
{
|
|
"entropy": 5.582890176773072,
|
|
"epoch": 0.5283018867924528,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004977156296946545,
|
|
"loss": 5.4242,
|
|
"mean_token_accuracy": 0.17239639312028884,
|
|
"num_tokens": 11793249.0,
|
|
"step": 6790
|
|
},
|
|
{
|
|
"entropy": 5.684317922592163,
|
|
"epoch": 0.5286909161641704,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004977116886424187,
|
|
"loss": 5.475,
|
|
"mean_token_accuracy": 0.15826374739408494,
|
|
"num_tokens": 11801512.0,
|
|
"step": 6795
|
|
},
|
|
{
|
|
"entropy": 5.612030124664306,
|
|
"epoch": 0.529079945535888,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004977077442108873,
|
|
"loss": 5.3535,
|
|
"mean_token_accuracy": 0.174309204518795,
|
|
"num_tokens": 11810248.0,
|
|
"step": 6800
|
|
},
|
|
{
|
|
"entropy": 5.599524450302124,
|
|
"epoch": 0.5294689749076055,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004977037964001204,
|
|
"loss": 5.3448,
|
|
"mean_token_accuracy": 0.171326445043087,
|
|
"num_tokens": 11819190.0,
|
|
"step": 6805
|
|
},
|
|
{
|
|
"entropy": 5.583758401870727,
|
|
"epoch": 0.5298580042793231,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000497699845210178,
|
|
"loss": 5.4194,
|
|
"mean_token_accuracy": 0.16252280473709108,
|
|
"num_tokens": 11827585.0,
|
|
"step": 6810
|
|
},
|
|
{
|
|
"entropy": 5.6619100093841555,
|
|
"epoch": 0.5302470336510406,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004976958906411197,
|
|
"loss": 5.4057,
|
|
"mean_token_accuracy": 0.17098232507705688,
|
|
"num_tokens": 11836256.0,
|
|
"step": 6815
|
|
},
|
|
{
|
|
"entropy": 5.672984313964844,
|
|
"epoch": 0.5306360630227582,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004976919326930059,
|
|
"loss": 5.5252,
|
|
"mean_token_accuracy": 0.17031456232070924,
|
|
"num_tokens": 11845022.0,
|
|
"step": 6820
|
|
},
|
|
{
|
|
"entropy": 5.6437376022338865,
|
|
"epoch": 0.5310250923944758,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004976879713658964,
|
|
"loss": 5.3832,
|
|
"mean_token_accuracy": 0.1698227718472481,
|
|
"num_tokens": 11853289.0,
|
|
"step": 6825
|
|
},
|
|
{
|
|
"entropy": 5.568662071228028,
|
|
"epoch": 0.5314141217661933,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004976840066598514,
|
|
"loss": 5.3322,
|
|
"mean_token_accuracy": 0.17991804629564284,
|
|
"num_tokens": 11861589.0,
|
|
"step": 6830
|
|
},
|
|
{
|
|
"entropy": 5.664581918716431,
|
|
"epoch": 0.5318031511379109,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004976800385749309,
|
|
"loss": 5.4406,
|
|
"mean_token_accuracy": 0.17165744453668594,
|
|
"num_tokens": 11870313.0,
|
|
"step": 6835
|
|
},
|
|
{
|
|
"entropy": 5.7209772109985355,
|
|
"epoch": 0.5321921805096285,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004976760671111954,
|
|
"loss": 5.4333,
|
|
"mean_token_accuracy": 0.16864327043294908,
|
|
"num_tokens": 11879558.0,
|
|
"step": 6840
|
|
},
|
|
{
|
|
"entropy": 5.6440380096435545,
|
|
"epoch": 0.532581209881346,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000497672092268705,
|
|
"loss": 5.4412,
|
|
"mean_token_accuracy": 0.1721239373087883,
|
|
"num_tokens": 11887951.0,
|
|
"step": 6845
|
|
},
|
|
{
|
|
"entropy": 5.696996545791626,
|
|
"epoch": 0.5329702392530636,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00049766811404752,
|
|
"loss": 5.638,
|
|
"mean_token_accuracy": 0.15808830112218858,
|
|
"num_tokens": 11896900.0,
|
|
"step": 6850
|
|
},
|
|
{
|
|
"entropy": 5.677005386352539,
|
|
"epoch": 0.5333592686247812,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004976641324477008,
|
|
"loss": 5.469,
|
|
"mean_token_accuracy": 0.1657126635313034,
|
|
"num_tokens": 11905681.0,
|
|
"step": 6855
|
|
},
|
|
{
|
|
"entropy": 5.612731027603149,
|
|
"epoch": 0.5337482979964987,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004976601474693077,
|
|
"loss": 5.4003,
|
|
"mean_token_accuracy": 0.17090844810009004,
|
|
"num_tokens": 11914662.0,
|
|
"step": 6860
|
|
},
|
|
{
|
|
"entropy": 5.567288160324097,
|
|
"epoch": 0.5341373273682163,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004976561591124014,
|
|
"loss": 5.4053,
|
|
"mean_token_accuracy": 0.17699283957481385,
|
|
"num_tokens": 11923298.0,
|
|
"step": 6865
|
|
},
|
|
{
|
|
"entropy": 5.639786863327027,
|
|
"epoch": 0.5345263567399339,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004976521673770421,
|
|
"loss": 5.3198,
|
|
"mean_token_accuracy": 0.17048582732677459,
|
|
"num_tokens": 11932206.0,
|
|
"step": 6870
|
|
},
|
|
{
|
|
"entropy": 5.580082273483276,
|
|
"epoch": 0.5349153861116515,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004976481722632907,
|
|
"loss": 5.3763,
|
|
"mean_token_accuracy": 0.176534940302372,
|
|
"num_tokens": 11940786.0,
|
|
"step": 6875
|
|
},
|
|
{
|
|
"entropy": 5.612260055541992,
|
|
"epoch": 0.535304415483369,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004976441737712076,
|
|
"loss": 5.3854,
|
|
"mean_token_accuracy": 0.1711177110671997,
|
|
"num_tokens": 11949619.0,
|
|
"step": 6880
|
|
},
|
|
{
|
|
"entropy": 5.603137588500976,
|
|
"epoch": 0.5356934448550865,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004976401719008536,
|
|
"loss": 5.3338,
|
|
"mean_token_accuracy": 0.17791433930397033,
|
|
"num_tokens": 11957696.0,
|
|
"step": 6885
|
|
},
|
|
{
|
|
"entropy": 5.576803970336914,
|
|
"epoch": 0.5360824742268041,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004976361666522893,
|
|
"loss": 5.3404,
|
|
"mean_token_accuracy": 0.1796420320868492,
|
|
"num_tokens": 11965622.0,
|
|
"step": 6890
|
|
},
|
|
{
|
|
"entropy": 5.563084983825684,
|
|
"epoch": 0.5364715035985217,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004976321580255755,
|
|
"loss": 5.4238,
|
|
"mean_token_accuracy": 0.17168654203414918,
|
|
"num_tokens": 11973969.0,
|
|
"step": 6895
|
|
},
|
|
{
|
|
"entropy": 5.705384826660156,
|
|
"epoch": 0.5368605329702393,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004976281460207731,
|
|
"loss": 5.41,
|
|
"mean_token_accuracy": 0.1748523712158203,
|
|
"num_tokens": 11982469.0,
|
|
"step": 6900
|
|
},
|
|
{
|
|
"entropy": 5.688539218902588,
|
|
"epoch": 0.5372495623419569,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000497624130637943,
|
|
"loss": 5.5045,
|
|
"mean_token_accuracy": 0.16434845477342605,
|
|
"num_tokens": 11990656.0,
|
|
"step": 6905
|
|
},
|
|
{
|
|
"entropy": 5.645046281814575,
|
|
"epoch": 0.5376385917136743,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000497620111877146,
|
|
"loss": 5.4958,
|
|
"mean_token_accuracy": 0.16131058484315872,
|
|
"num_tokens": 11999394.0,
|
|
"step": 6910
|
|
},
|
|
{
|
|
"entropy": 5.685613632202148,
|
|
"epoch": 0.5380276210853919,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004976160897384431,
|
|
"loss": 5.4609,
|
|
"mean_token_accuracy": 0.17145871371030807,
|
|
"num_tokens": 12007692.0,
|
|
"step": 6915
|
|
},
|
|
{
|
|
"entropy": 5.661275339126587,
|
|
"epoch": 0.5384166504571095,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004976120642218955,
|
|
"loss": 5.4336,
|
|
"mean_token_accuracy": 0.16824211180210114,
|
|
"num_tokens": 12016038.0,
|
|
"step": 6920
|
|
},
|
|
{
|
|
"entropy": 5.650868272781372,
|
|
"epoch": 0.5388056798288271,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000497608035327564,
|
|
"loss": 5.5396,
|
|
"mean_token_accuracy": 0.16747572720050813,
|
|
"num_tokens": 12024504.0,
|
|
"step": 6925
|
|
},
|
|
{
|
|
"entropy": 5.608466005325317,
|
|
"epoch": 0.5391947092005447,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00049760400305551,
|
|
"loss": 5.4369,
|
|
"mean_token_accuracy": 0.17732071429491042,
|
|
"num_tokens": 12032935.0,
|
|
"step": 6930
|
|
},
|
|
{
|
|
"entropy": 5.65435676574707,
|
|
"epoch": 0.5395837385722622,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004975999674057944,
|
|
"loss": 5.4592,
|
|
"mean_token_accuracy": 0.16456467062234878,
|
|
"num_tokens": 12041907.0,
|
|
"step": 6935
|
|
},
|
|
{
|
|
"entropy": 5.607891321182251,
|
|
"epoch": 0.5399727679439797,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004975959283784787,
|
|
"loss": 5.2978,
|
|
"mean_token_accuracy": 0.17626878917217254,
|
|
"num_tokens": 12050528.0,
|
|
"step": 6940
|
|
},
|
|
{
|
|
"entropy": 5.570985174179077,
|
|
"epoch": 0.5403617973156973,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004975918859736241,
|
|
"loss": 5.3011,
|
|
"mean_token_accuracy": 0.1774978369474411,
|
|
"num_tokens": 12059221.0,
|
|
"step": 6945
|
|
},
|
|
{
|
|
"entropy": 5.630969619750976,
|
|
"epoch": 0.5407508266874149,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004975878401912919,
|
|
"loss": 5.5186,
|
|
"mean_token_accuracy": 0.16120119094848634,
|
|
"num_tokens": 12068131.0,
|
|
"step": 6950
|
|
},
|
|
{
|
|
"entropy": 5.698724842071533,
|
|
"epoch": 0.5411398560591325,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004975837910315436,
|
|
"loss": 5.3707,
|
|
"mean_token_accuracy": 0.18022255450487137,
|
|
"num_tokens": 12076521.0,
|
|
"step": 6955
|
|
},
|
|
{
|
|
"entropy": 5.683851289749145,
|
|
"epoch": 0.54152888543085,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004975797384944405,
|
|
"loss": 5.5697,
|
|
"mean_token_accuracy": 0.16650937199592591,
|
|
"num_tokens": 12085306.0,
|
|
"step": 6960
|
|
},
|
|
{
|
|
"entropy": 5.593390607833863,
|
|
"epoch": 0.5419179148025676,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.000497575682580044,
|
|
"loss": 5.3415,
|
|
"mean_token_accuracy": 0.16895500123500823,
|
|
"num_tokens": 12094409.0,
|
|
"step": 6965
|
|
},
|
|
{
|
|
"entropy": 5.617079973220825,
|
|
"epoch": 0.5423069441742852,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000497571623288416,
|
|
"loss": 5.4016,
|
|
"mean_token_accuracy": 0.16630526036024093,
|
|
"num_tokens": 12103385.0,
|
|
"step": 6970
|
|
},
|
|
{
|
|
"entropy": 5.682160234451294,
|
|
"epoch": 0.5426959735460027,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004975675606196177,
|
|
"loss": 5.5081,
|
|
"mean_token_accuracy": 0.1710004076361656,
|
|
"num_tokens": 12112452.0,
|
|
"step": 6975
|
|
},
|
|
{
|
|
"entropy": 5.735922050476074,
|
|
"epoch": 0.5430850029177203,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000497563494573711,
|
|
"loss": 5.501,
|
|
"mean_token_accuracy": 0.16131800562143325,
|
|
"num_tokens": 12120918.0,
|
|
"step": 6980
|
|
},
|
|
{
|
|
"entropy": 5.659406328201294,
|
|
"epoch": 0.5434740322894378,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004975594251507575,
|
|
"loss": 5.4709,
|
|
"mean_token_accuracy": 0.16228864043951036,
|
|
"num_tokens": 12129797.0,
|
|
"step": 6985
|
|
},
|
|
{
|
|
"entropy": 5.619140863418579,
|
|
"epoch": 0.5438630616611554,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000497555352350819,
|
|
"loss": 5.4487,
|
|
"mean_token_accuracy": 0.16991385221481323,
|
|
"num_tokens": 12139245.0,
|
|
"step": 6990
|
|
},
|
|
{
|
|
"entropy": 5.685261535644531,
|
|
"epoch": 0.544252091032873,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004975512761739572,
|
|
"loss": 5.6102,
|
|
"mean_token_accuracy": 0.16088290214538575,
|
|
"num_tokens": 12147409.0,
|
|
"step": 6995
|
|
},
|
|
{
|
|
"entropy": 5.724803781509399,
|
|
"epoch": 0.5446411204045906,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000497547196620234,
|
|
"loss": 5.424,
|
|
"mean_token_accuracy": 0.17047625184059143,
|
|
"num_tokens": 12156121.0,
|
|
"step": 7000
|
|
},
|
|
{
|
|
"entropy": 5.586559152603149,
|
|
"epoch": 0.5450301497763081,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004975431136897114,
|
|
"loss": 5.3186,
|
|
"mean_token_accuracy": 0.17673922777175904,
|
|
"num_tokens": 12165307.0,
|
|
"step": 7005
|
|
},
|
|
{
|
|
"entropy": 5.633096408843994,
|
|
"epoch": 0.5454191791480256,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004975390273824512,
|
|
"loss": 5.3832,
|
|
"mean_token_accuracy": 0.1656043067574501,
|
|
"num_tokens": 12173899.0,
|
|
"step": 7010
|
|
},
|
|
{
|
|
"entropy": 5.560071325302124,
|
|
"epoch": 0.5458082085197432,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004975349376985155,
|
|
"loss": 5.3972,
|
|
"mean_token_accuracy": 0.16830164492130278,
|
|
"num_tokens": 12182898.0,
|
|
"step": 7015
|
|
},
|
|
{
|
|
"entropy": 5.542508268356324,
|
|
"epoch": 0.5461972378914608,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004975308446379663,
|
|
"loss": 5.275,
|
|
"mean_token_accuracy": 0.1712779715657234,
|
|
"num_tokens": 12191500.0,
|
|
"step": 7020
|
|
},
|
|
{
|
|
"entropy": 5.579271554946899,
|
|
"epoch": 0.5465862672631784,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004975267482008657,
|
|
"loss": 5.4364,
|
|
"mean_token_accuracy": 0.17276248931884766,
|
|
"num_tokens": 12199420.0,
|
|
"step": 7025
|
|
},
|
|
{
|
|
"entropy": 5.6312158584594725,
|
|
"epoch": 0.546975296634896,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000497522648387276,
|
|
"loss": 5.3523,
|
|
"mean_token_accuracy": 0.17430415749549866,
|
|
"num_tokens": 12207676.0,
|
|
"step": 7030
|
|
},
|
|
{
|
|
"entropy": 5.647388362884522,
|
|
"epoch": 0.5473643260066134,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004975185451972592,
|
|
"loss": 5.4124,
|
|
"mean_token_accuracy": 0.1714552164077759,
|
|
"num_tokens": 12216248.0,
|
|
"step": 7035
|
|
},
|
|
{
|
|
"entropy": 5.624428606033325,
|
|
"epoch": 0.547753355378331,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004975144386308776,
|
|
"loss": 5.4368,
|
|
"mean_token_accuracy": 0.17158026099205018,
|
|
"num_tokens": 12224588.0,
|
|
"step": 7040
|
|
},
|
|
{
|
|
"entropy": 5.657812929153442,
|
|
"epoch": 0.5481423847500486,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004975103286881936,
|
|
"loss": 5.4578,
|
|
"mean_token_accuracy": 0.1659623846411705,
|
|
"num_tokens": 12234093.0,
|
|
"step": 7045
|
|
},
|
|
{
|
|
"entropy": 5.721933794021607,
|
|
"epoch": 0.5485314141217662,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004975062153692696,
|
|
"loss": 5.3901,
|
|
"mean_token_accuracy": 0.18022023141384125,
|
|
"num_tokens": 12242164.0,
|
|
"step": 7050
|
|
},
|
|
{
|
|
"entropy": 5.649906730651855,
|
|
"epoch": 0.5489204434934838,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004975020986741678,
|
|
"loss": 5.4898,
|
|
"mean_token_accuracy": 0.16861753314733505,
|
|
"num_tokens": 12251204.0,
|
|
"step": 7055
|
|
},
|
|
{
|
|
"entropy": 5.6687757015228275,
|
|
"epoch": 0.5493094728652014,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004974979786029509,
|
|
"loss": 5.4202,
|
|
"mean_token_accuracy": 0.1690824121236801,
|
|
"num_tokens": 12259809.0,
|
|
"step": 7060
|
|
},
|
|
{
|
|
"entropy": 5.624884033203125,
|
|
"epoch": 0.5496985022369189,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004974938551556814,
|
|
"loss": 5.4069,
|
|
"mean_token_accuracy": 0.17586851567029954,
|
|
"num_tokens": 12268668.0,
|
|
"step": 7065
|
|
},
|
|
{
|
|
"entropy": 5.613442516326904,
|
|
"epoch": 0.5500875316086364,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004974897283324217,
|
|
"loss": 5.3819,
|
|
"mean_token_accuracy": 0.17798949629068375,
|
|
"num_tokens": 12276823.0,
|
|
"step": 7070
|
|
},
|
|
{
|
|
"entropy": 5.485236740112304,
|
|
"epoch": 0.550476560980354,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004974855981332343,
|
|
"loss": 5.3098,
|
|
"mean_token_accuracy": 0.1711676076054573,
|
|
"num_tokens": 12285950.0,
|
|
"step": 7075
|
|
},
|
|
{
|
|
"entropy": 5.597700595855713,
|
|
"epoch": 0.5508655903520716,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004974814645581823,
|
|
"loss": 5.4277,
|
|
"mean_token_accuracy": 0.16414272636175156,
|
|
"num_tokens": 12295265.0,
|
|
"step": 7080
|
|
},
|
|
{
|
|
"entropy": 5.662305927276611,
|
|
"epoch": 0.5512546197237892,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004974773276073282,
|
|
"loss": 5.4386,
|
|
"mean_token_accuracy": 0.1707385465502739,
|
|
"num_tokens": 12303649.0,
|
|
"step": 7085
|
|
},
|
|
{
|
|
"entropy": 5.59878978729248,
|
|
"epoch": 0.5516436490955067,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004974731872807347,
|
|
"loss": 5.4989,
|
|
"mean_token_accuracy": 0.16129840314388275,
|
|
"num_tokens": 12313303.0,
|
|
"step": 7090
|
|
},
|
|
{
|
|
"entropy": 5.6164943218231205,
|
|
"epoch": 0.5520326784672243,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004974690435784647,
|
|
"loss": 5.4422,
|
|
"mean_token_accuracy": 0.1737209215760231,
|
|
"num_tokens": 12321692.0,
|
|
"step": 7095
|
|
},
|
|
{
|
|
"entropy": 5.521945524215698,
|
|
"epoch": 0.5524217078389418,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004974648965005811,
|
|
"loss": 5.2479,
|
|
"mean_token_accuracy": 0.17637658715248108,
|
|
"num_tokens": 12329908.0,
|
|
"step": 7100
|
|
},
|
|
{
|
|
"entropy": 5.562238073348999,
|
|
"epoch": 0.5528107372106594,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004974607460471466,
|
|
"loss": 5.4201,
|
|
"mean_token_accuracy": 0.1720580741763115,
|
|
"num_tokens": 12339270.0,
|
|
"step": 7105
|
|
},
|
|
{
|
|
"entropy": 5.589144849777222,
|
|
"epoch": 0.553199766582377,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004974565922182246,
|
|
"loss": 5.3241,
|
|
"mean_token_accuracy": 0.17368963211774827,
|
|
"num_tokens": 12347586.0,
|
|
"step": 7110
|
|
},
|
|
{
|
|
"entropy": 5.549763822555542,
|
|
"epoch": 0.5535887959540945,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004974524350138777,
|
|
"loss": 5.284,
|
|
"mean_token_accuracy": 0.170064477622509,
|
|
"num_tokens": 12356291.0,
|
|
"step": 7115
|
|
},
|
|
{
|
|
"entropy": 5.640159797668457,
|
|
"epoch": 0.5539778253258121,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004974482744341693,
|
|
"loss": 5.4606,
|
|
"mean_token_accuracy": 0.1634287178516388,
|
|
"num_tokens": 12364948.0,
|
|
"step": 7120
|
|
},
|
|
{
|
|
"entropy": 5.6569324970245365,
|
|
"epoch": 0.5543668546975297,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004974441104791624,
|
|
"loss": 5.407,
|
|
"mean_token_accuracy": 0.17270324677228927,
|
|
"num_tokens": 12373497.0,
|
|
"step": 7125
|
|
},
|
|
{
|
|
"entropy": 5.6427390575408936,
|
|
"epoch": 0.5547558840692473,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004974399431489201,
|
|
"loss": 5.3587,
|
|
"mean_token_accuracy": 0.17324348986148835,
|
|
"num_tokens": 12382198.0,
|
|
"step": 7130
|
|
},
|
|
{
|
|
"entropy": 5.5707135677337645,
|
|
"epoch": 0.5551449134409648,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004974357724435057,
|
|
"loss": 5.3478,
|
|
"mean_token_accuracy": 0.17520179748535156,
|
|
"num_tokens": 12391122.0,
|
|
"step": 7135
|
|
},
|
|
{
|
|
"entropy": 5.504246950149536,
|
|
"epoch": 0.5555339428126823,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004974315983629825,
|
|
"loss": 5.291,
|
|
"mean_token_accuracy": 0.18072783648967744,
|
|
"num_tokens": 12399338.0,
|
|
"step": 7140
|
|
},
|
|
{
|
|
"entropy": 5.615718746185303,
|
|
"epoch": 0.5559229721843999,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004974274209074139,
|
|
"loss": 5.3896,
|
|
"mean_token_accuracy": 0.16674543172121048,
|
|
"num_tokens": 12408561.0,
|
|
"step": 7145
|
|
},
|
|
{
|
|
"entropy": 5.643730163574219,
|
|
"epoch": 0.5563120015561175,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004974232400768632,
|
|
"loss": 5.2761,
|
|
"mean_token_accuracy": 0.1755574345588684,
|
|
"num_tokens": 12417727.0,
|
|
"step": 7150
|
|
},
|
|
{
|
|
"entropy": 5.601311254501343,
|
|
"epoch": 0.5567010309278351,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004974190558713939,
|
|
"loss": 5.3009,
|
|
"mean_token_accuracy": 0.17797841727733613,
|
|
"num_tokens": 12426446.0,
|
|
"step": 7155
|
|
},
|
|
{
|
|
"entropy": 5.574703121185303,
|
|
"epoch": 0.5570900602995527,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004974148682910694,
|
|
"loss": 5.3702,
|
|
"mean_token_accuracy": 0.169679394364357,
|
|
"num_tokens": 12435124.0,
|
|
"step": 7160
|
|
},
|
|
{
|
|
"entropy": 5.632902956008911,
|
|
"epoch": 0.5574790896712701,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004974106773359533,
|
|
"loss": 5.4616,
|
|
"mean_token_accuracy": 0.16738623529672622,
|
|
"num_tokens": 12444073.0,
|
|
"step": 7165
|
|
},
|
|
{
|
|
"entropy": 5.694697999954224,
|
|
"epoch": 0.5578681190429877,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004974064830061091,
|
|
"loss": 5.4502,
|
|
"mean_token_accuracy": 0.17598361372947693,
|
|
"num_tokens": 12452419.0,
|
|
"step": 7170
|
|
},
|
|
{
|
|
"entropy": 5.608331632614136,
|
|
"epoch": 0.5582571484147053,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004974022853016006,
|
|
"loss": 5.3955,
|
|
"mean_token_accuracy": 0.17239612936973572,
|
|
"num_tokens": 12461488.0,
|
|
"step": 7175
|
|
},
|
|
{
|
|
"entropy": 5.6137001514434814,
|
|
"epoch": 0.5586461777864229,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004973980842224913,
|
|
"loss": 5.3359,
|
|
"mean_token_accuracy": 0.16857871264219285,
|
|
"num_tokens": 12470344.0,
|
|
"step": 7180
|
|
},
|
|
{
|
|
"entropy": 5.608567142486573,
|
|
"epoch": 0.5590352071581405,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004973938797688452,
|
|
"loss": 5.347,
|
|
"mean_token_accuracy": 0.17229609936475754,
|
|
"num_tokens": 12479189.0,
|
|
"step": 7185
|
|
},
|
|
{
|
|
"entropy": 5.599718999862671,
|
|
"epoch": 0.559424236529858,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004973896719407259,
|
|
"loss": 5.3849,
|
|
"mean_token_accuracy": 0.17104582041501998,
|
|
"num_tokens": 12488199.0,
|
|
"step": 7190
|
|
},
|
|
{
|
|
"entropy": 5.544893550872803,
|
|
"epoch": 0.5598132659015755,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004973854607381972,
|
|
"loss": 5.2665,
|
|
"mean_token_accuracy": 0.18018234372138978,
|
|
"num_tokens": 12496704.0,
|
|
"step": 7195
|
|
},
|
|
{
|
|
"entropy": 5.496060514450074,
|
|
"epoch": 0.5602022952732931,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004973812461613232,
|
|
"loss": 5.2633,
|
|
"mean_token_accuracy": 0.18417042195796968,
|
|
"num_tokens": 12504724.0,
|
|
"step": 7200
|
|
},
|
|
{
|
|
"entropy": 5.59717960357666,
|
|
"epoch": 0.5605913246450107,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004973770282101677,
|
|
"loss": 5.4681,
|
|
"mean_token_accuracy": 0.1670819789171219,
|
|
"num_tokens": 12514614.0,
|
|
"step": 7205
|
|
},
|
|
{
|
|
"entropy": 5.747423458099365,
|
|
"epoch": 0.5609803540167283,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004973728068847947,
|
|
"loss": 5.4762,
|
|
"mean_token_accuracy": 0.1688718467950821,
|
|
"num_tokens": 12522744.0,
|
|
"step": 7210
|
|
},
|
|
{
|
|
"entropy": 5.6050097942352295,
|
|
"epoch": 0.5613693833884458,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004973685821852684,
|
|
"loss": 5.389,
|
|
"mean_token_accuracy": 0.16972415894269943,
|
|
"num_tokens": 12531783.0,
|
|
"step": 7215
|
|
},
|
|
{
|
|
"entropy": 5.604793548583984,
|
|
"epoch": 0.5617584127601634,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004973643541116528,
|
|
"loss": 5.4463,
|
|
"mean_token_accuracy": 0.16353272944688796,
|
|
"num_tokens": 12541768.0,
|
|
"step": 7220
|
|
},
|
|
{
|
|
"entropy": 5.689733552932739,
|
|
"epoch": 0.562147442131881,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000497360122664012,
|
|
"loss": 5.4659,
|
|
"mean_token_accuracy": 0.16686318814754486,
|
|
"num_tokens": 12550684.0,
|
|
"step": 7225
|
|
},
|
|
{
|
|
"entropy": 5.634374666213989,
|
|
"epoch": 0.5625364715035985,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004973558878424104,
|
|
"loss": 5.4107,
|
|
"mean_token_accuracy": 0.16748277097940445,
|
|
"num_tokens": 12559948.0,
|
|
"step": 7230
|
|
},
|
|
{
|
|
"entropy": 5.570274305343628,
|
|
"epoch": 0.5629255008753161,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004973516496469119,
|
|
"loss": 5.3538,
|
|
"mean_token_accuracy": 0.17910895943641664,
|
|
"num_tokens": 12568681.0,
|
|
"step": 7235
|
|
},
|
|
{
|
|
"entropy": 5.688456439971924,
|
|
"epoch": 0.5633145302470336,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004973474080775811,
|
|
"loss": 5.4826,
|
|
"mean_token_accuracy": 0.1591241553425789,
|
|
"num_tokens": 12577724.0,
|
|
"step": 7240
|
|
},
|
|
{
|
|
"entropy": 5.694258785247802,
|
|
"epoch": 0.5637035596187512,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004973431631344824,
|
|
"loss": 5.4048,
|
|
"mean_token_accuracy": 0.16929993778467178,
|
|
"num_tokens": 12585994.0,
|
|
"step": 7245
|
|
},
|
|
{
|
|
"entropy": 5.627398109436035,
|
|
"epoch": 0.5640925889904688,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.00049733891481768,
|
|
"loss": 5.4558,
|
|
"mean_token_accuracy": 0.16533113718032838,
|
|
"num_tokens": 12595525.0,
|
|
"step": 7250
|
|
},
|
|
{
|
|
"entropy": 5.62390513420105,
|
|
"epoch": 0.5644816183621864,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004973346631272384,
|
|
"loss": 5.2904,
|
|
"mean_token_accuracy": 0.17755208760499955,
|
|
"num_tokens": 12603645.0,
|
|
"step": 7255
|
|
},
|
|
{
|
|
"entropy": 5.567868185043335,
|
|
"epoch": 0.5648706477339039,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004973304080632222,
|
|
"loss": 5.3675,
|
|
"mean_token_accuracy": 0.1723654091358185,
|
|
"num_tokens": 12612165.0,
|
|
"step": 7260
|
|
},
|
|
{
|
|
"entropy": 5.58600640296936,
|
|
"epoch": 0.5652596771056215,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000497326149625696,
|
|
"loss": 5.2778,
|
|
"mean_token_accuracy": 0.18184001594781876,
|
|
"num_tokens": 12620678.0,
|
|
"step": 7265
|
|
},
|
|
{
|
|
"entropy": 5.679574966430664,
|
|
"epoch": 0.565648706477339,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004973218878147244,
|
|
"loss": 5.4693,
|
|
"mean_token_accuracy": 0.173343163728714,
|
|
"num_tokens": 12628745.0,
|
|
"step": 7270
|
|
},
|
|
{
|
|
"entropy": 5.6358977317810055,
|
|
"epoch": 0.5660377358490566,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004973176226303719,
|
|
"loss": 5.5254,
|
|
"mean_token_accuracy": 0.16010626703500747,
|
|
"num_tokens": 12637448.0,
|
|
"step": 7275
|
|
},
|
|
{
|
|
"entropy": 5.626923656463623,
|
|
"epoch": 0.5664267652207742,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004973133540727033,
|
|
"loss": 5.3752,
|
|
"mean_token_accuracy": 0.1741466835141182,
|
|
"num_tokens": 12645804.0,
|
|
"step": 7280
|
|
},
|
|
{
|
|
"entropy": 5.602758455276489,
|
|
"epoch": 0.5668157945924918,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004973090821417835,
|
|
"loss": 5.3544,
|
|
"mean_token_accuracy": 0.173034206032753,
|
|
"num_tokens": 12654156.0,
|
|
"step": 7285
|
|
},
|
|
{
|
|
"entropy": 5.572364473342896,
|
|
"epoch": 0.5672048239642093,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004973048068376772,
|
|
"loss": 5.3077,
|
|
"mean_token_accuracy": 0.17897556275129317,
|
|
"num_tokens": 12662271.0,
|
|
"step": 7290
|
|
},
|
|
{
|
|
"entropy": 5.708192586898804,
|
|
"epoch": 0.5675938533359268,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004973005281604492,
|
|
"loss": 5.4874,
|
|
"mean_token_accuracy": 0.16635391861200333,
|
|
"num_tokens": 12671016.0,
|
|
"step": 7295
|
|
},
|
|
{
|
|
"entropy": 5.639117336273193,
|
|
"epoch": 0.5679828827076444,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004972962461101646,
|
|
"loss": 5.4305,
|
|
"mean_token_accuracy": 0.1690814435482025,
|
|
"num_tokens": 12679593.0,
|
|
"step": 7300
|
|
},
|
|
{
|
|
"entropy": 5.6017145156860355,
|
|
"epoch": 0.568371912079362,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004972919606868883,
|
|
"loss": 5.3721,
|
|
"mean_token_accuracy": 0.1766174241900444,
|
|
"num_tokens": 12688715.0,
|
|
"step": 7305
|
|
},
|
|
{
|
|
"entropy": 5.602231359481811,
|
|
"epoch": 0.5687609414510796,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004972876718906852,
|
|
"loss": 5.3866,
|
|
"mean_token_accuracy": 0.1696537181735039,
|
|
"num_tokens": 12698078.0,
|
|
"step": 7310
|
|
},
|
|
{
|
|
"entropy": 5.563684892654419,
|
|
"epoch": 0.5691499708227972,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004972833797216206,
|
|
"loss": 5.3618,
|
|
"mean_token_accuracy": 0.1765790119767189,
|
|
"num_tokens": 12706375.0,
|
|
"step": 7315
|
|
},
|
|
{
|
|
"entropy": 5.715937089920044,
|
|
"epoch": 0.5695390001945146,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004972790841797595,
|
|
"loss": 5.5603,
|
|
"mean_token_accuracy": 0.16448500901460647,
|
|
"num_tokens": 12715727.0,
|
|
"step": 7320
|
|
},
|
|
{
|
|
"entropy": 5.664407587051391,
|
|
"epoch": 0.5699280295662322,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.000497274785265167,
|
|
"loss": 5.4516,
|
|
"mean_token_accuracy": 0.1611158773303032,
|
|
"num_tokens": 12725565.0,
|
|
"step": 7325
|
|
},
|
|
{
|
|
"entropy": 5.683152484893799,
|
|
"epoch": 0.5703170589379498,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004972704829779086,
|
|
"loss": 5.4712,
|
|
"mean_token_accuracy": 0.1761600434780121,
|
|
"num_tokens": 12733498.0,
|
|
"step": 7330
|
|
},
|
|
{
|
|
"entropy": 5.556344842910766,
|
|
"epoch": 0.5707060883096674,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004972661773180492,
|
|
"loss": 5.3119,
|
|
"mean_token_accuracy": 0.1757061630487442,
|
|
"num_tokens": 12741635.0,
|
|
"step": 7335
|
|
},
|
|
{
|
|
"entropy": 5.554010105133057,
|
|
"epoch": 0.571095117681385,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004972618682856545,
|
|
"loss": 5.3269,
|
|
"mean_token_accuracy": 0.1744554191827774,
|
|
"num_tokens": 12750973.0,
|
|
"step": 7340
|
|
},
|
|
{
|
|
"entropy": 5.582947015762329,
|
|
"epoch": 0.5714841470531025,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004972575558807896,
|
|
"loss": 5.3894,
|
|
"mean_token_accuracy": 0.17799339741468428,
|
|
"num_tokens": 12759075.0,
|
|
"step": 7345
|
|
},
|
|
{
|
|
"entropy": 5.646500492095948,
|
|
"epoch": 0.57187317642482,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004972532401035201,
|
|
"loss": 5.3664,
|
|
"mean_token_accuracy": 0.17144054025411606,
|
|
"num_tokens": 12767485.0,
|
|
"step": 7350
|
|
},
|
|
{
|
|
"entropy": 5.687675714492798,
|
|
"epoch": 0.5722622057965376,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004972489209539114,
|
|
"loss": 5.3616,
|
|
"mean_token_accuracy": 0.17879957854747772,
|
|
"num_tokens": 12775128.0,
|
|
"step": 7355
|
|
},
|
|
{
|
|
"entropy": 5.556820583343506,
|
|
"epoch": 0.5726512351682552,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004972445984320292,
|
|
"loss": 5.2769,
|
|
"mean_token_accuracy": 0.17778964787721635,
|
|
"num_tokens": 12783243.0,
|
|
"step": 7360
|
|
},
|
|
{
|
|
"entropy": 5.63396053314209,
|
|
"epoch": 0.5730402645399728,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004972402725379388,
|
|
"loss": 5.4811,
|
|
"mean_token_accuracy": 0.17174470275640488,
|
|
"num_tokens": 12791613.0,
|
|
"step": 7365
|
|
},
|
|
{
|
|
"entropy": 5.671663236618042,
|
|
"epoch": 0.5734292939116903,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000497235943271706,
|
|
"loss": 5.4198,
|
|
"mean_token_accuracy": 0.1699995830655098,
|
|
"num_tokens": 12799817.0,
|
|
"step": 7370
|
|
},
|
|
{
|
|
"entropy": 5.642856693267822,
|
|
"epoch": 0.5738183232834079,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004972316106333966,
|
|
"loss": 5.4209,
|
|
"mean_token_accuracy": 0.16815965324640275,
|
|
"num_tokens": 12808994.0,
|
|
"step": 7375
|
|
},
|
|
{
|
|
"entropy": 5.642169857025147,
|
|
"epoch": 0.5742073526551255,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004972272746230761,
|
|
"loss": 5.3904,
|
|
"mean_token_accuracy": 0.16785614788532258,
|
|
"num_tokens": 12817191.0,
|
|
"step": 7380
|
|
},
|
|
{
|
|
"entropy": 5.608738899230957,
|
|
"epoch": 0.574596382026843,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004972229352408104,
|
|
"loss": 5.35,
|
|
"mean_token_accuracy": 0.1734204888343811,
|
|
"num_tokens": 12825773.0,
|
|
"step": 7385
|
|
},
|
|
{
|
|
"entropy": 5.678319597244263,
|
|
"epoch": 0.5749854113985606,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004972185924866655,
|
|
"loss": 5.4246,
|
|
"mean_token_accuracy": 0.1701473280787468,
|
|
"num_tokens": 12834489.0,
|
|
"step": 7390
|
|
},
|
|
{
|
|
"entropy": 5.6620612144470215,
|
|
"epoch": 0.5753744407702781,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004972142463607071,
|
|
"loss": 5.4356,
|
|
"mean_token_accuracy": 0.17158037573099136,
|
|
"num_tokens": 12843179.0,
|
|
"step": 7395
|
|
},
|
|
{
|
|
"entropy": 5.712574434280396,
|
|
"epoch": 0.5757634701419957,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004972098968630012,
|
|
"loss": 5.4387,
|
|
"mean_token_accuracy": 0.1631328746676445,
|
|
"num_tokens": 12851243.0,
|
|
"step": 7400
|
|
},
|
|
{
|
|
"entropy": 5.585179996490479,
|
|
"epoch": 0.5761524995137133,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004972055439936137,
|
|
"loss": 5.477,
|
|
"mean_token_accuracy": 0.17327615469694138,
|
|
"num_tokens": 12860267.0,
|
|
"step": 7405
|
|
},
|
|
{
|
|
"entropy": 5.654938220977783,
|
|
"epoch": 0.5765415288854309,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004972011877526109,
|
|
"loss": 5.4859,
|
|
"mean_token_accuracy": 0.1667654201388359,
|
|
"num_tokens": 12870022.0,
|
|
"step": 7410
|
|
},
|
|
{
|
|
"entropy": 5.646070671081543,
|
|
"epoch": 0.5769305582571485,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004971968281400587,
|
|
"loss": 5.4501,
|
|
"mean_token_accuracy": 0.1635710835456848,
|
|
"num_tokens": 12879227.0,
|
|
"step": 7415
|
|
},
|
|
{
|
|
"entropy": 5.667190790176392,
|
|
"epoch": 0.5773195876288659,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004971924651560233,
|
|
"loss": 5.415,
|
|
"mean_token_accuracy": 0.16541746705770494,
|
|
"num_tokens": 12888180.0,
|
|
"step": 7420
|
|
},
|
|
{
|
|
"entropy": 5.6017412662506105,
|
|
"epoch": 0.5777086170005835,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004971880988005709,
|
|
"loss": 5.3977,
|
|
"mean_token_accuracy": 0.17384001314640046,
|
|
"num_tokens": 12896767.0,
|
|
"step": 7425
|
|
},
|
|
{
|
|
"entropy": 5.604390096664429,
|
|
"epoch": 0.5780976463723011,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004971837290737677,
|
|
"loss": 5.2896,
|
|
"mean_token_accuracy": 0.18285758793354034,
|
|
"num_tokens": 12904766.0,
|
|
"step": 7430
|
|
},
|
|
{
|
|
"entropy": 5.549197387695313,
|
|
"epoch": 0.5784866757440187,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004971793559756801,
|
|
"loss": 5.371,
|
|
"mean_token_accuracy": 0.16989658921957015,
|
|
"num_tokens": 12913808.0,
|
|
"step": 7435
|
|
},
|
|
{
|
|
"entropy": 5.551879167556763,
|
|
"epoch": 0.5788757051157363,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004971749795063744,
|
|
"loss": 5.3784,
|
|
"mean_token_accuracy": 0.16979086995124817,
|
|
"num_tokens": 12923103.0,
|
|
"step": 7440
|
|
},
|
|
{
|
|
"entropy": 5.59029188156128,
|
|
"epoch": 0.5792647344874537,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000497170599665917,
|
|
"loss": 5.3343,
|
|
"mean_token_accuracy": 0.17453575134277344,
|
|
"num_tokens": 12931168.0,
|
|
"step": 7445
|
|
},
|
|
{
|
|
"entropy": 5.5925538539886475,
|
|
"epoch": 0.5796537638591713,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004971662164543743,
|
|
"loss": 5.4042,
|
|
"mean_token_accuracy": 0.17637941390275955,
|
|
"num_tokens": 12939875.0,
|
|
"step": 7450
|
|
},
|
|
{
|
|
"entropy": 5.599119186401367,
|
|
"epoch": 0.5800427932308889,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004971618298718131,
|
|
"loss": 5.325,
|
|
"mean_token_accuracy": 0.17663128972053527,
|
|
"num_tokens": 12947883.0,
|
|
"step": 7455
|
|
},
|
|
{
|
|
"entropy": 5.71734848022461,
|
|
"epoch": 0.5804318226026065,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004971574399182995,
|
|
"loss": 5.5659,
|
|
"mean_token_accuracy": 0.16337292790412902,
|
|
"num_tokens": 12956940.0,
|
|
"step": 7460
|
|
},
|
|
{
|
|
"entropy": 5.600492000579834,
|
|
"epoch": 0.5808208519743241,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004971530465939005,
|
|
"loss": 5.3008,
|
|
"mean_token_accuracy": 0.1726179912686348,
|
|
"num_tokens": 12965003.0,
|
|
"step": 7465
|
|
},
|
|
{
|
|
"entropy": 5.57530517578125,
|
|
"epoch": 0.5812098813460417,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004971486498986825,
|
|
"loss": 5.3198,
|
|
"mean_token_accuracy": 0.1755088374018669,
|
|
"num_tokens": 12973323.0,
|
|
"step": 7470
|
|
},
|
|
{
|
|
"entropy": 5.580819034576416,
|
|
"epoch": 0.5815989107177592,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004971442498327124,
|
|
"loss": 5.374,
|
|
"mean_token_accuracy": 0.17628689855337143,
|
|
"num_tokens": 12982654.0,
|
|
"step": 7475
|
|
},
|
|
{
|
|
"entropy": 5.610224342346191,
|
|
"epoch": 0.5819879400894767,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004971398463960568,
|
|
"loss": 5.3965,
|
|
"mean_token_accuracy": 0.16887464374303818,
|
|
"num_tokens": 12991781.0,
|
|
"step": 7480
|
|
},
|
|
{
|
|
"entropy": 5.694233083724976,
|
|
"epoch": 0.5823769694611943,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004971354395887827,
|
|
"loss": 5.4907,
|
|
"mean_token_accuracy": 0.16564130187034606,
|
|
"num_tokens": 13000539.0,
|
|
"step": 7485
|
|
},
|
|
{
|
|
"entropy": 5.639818954467773,
|
|
"epoch": 0.5827659988329119,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004971310294109569,
|
|
"loss": 5.3575,
|
|
"mean_token_accuracy": 0.17220927327871322,
|
|
"num_tokens": 13008638.0,
|
|
"step": 7490
|
|
},
|
|
{
|
|
"entropy": 5.582267093658447,
|
|
"epoch": 0.5831550282046295,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004971266158626461,
|
|
"loss": 5.3337,
|
|
"mean_token_accuracy": 0.17774504721164702,
|
|
"num_tokens": 13017217.0,
|
|
"step": 7495
|
|
},
|
|
{
|
|
"entropy": 5.579143905639649,
|
|
"epoch": 0.583544057576347,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004971221989439177,
|
|
"loss": 5.3991,
|
|
"mean_token_accuracy": 0.1740799993276596,
|
|
"num_tokens": 13025278.0,
|
|
"step": 7500
|
|
},
|
|
{
|
|
"entropy": 5.602803754806518,
|
|
"epoch": 0.5839330869480646,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004971177786548384,
|
|
"loss": 5.4101,
|
|
"mean_token_accuracy": 0.17012534886598588,
|
|
"num_tokens": 13034484.0,
|
|
"step": 7505
|
|
},
|
|
{
|
|
"entropy": 5.68079833984375,
|
|
"epoch": 0.5843221163197821,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004971133549954753,
|
|
"loss": 5.4796,
|
|
"mean_token_accuracy": 0.16569795161485673,
|
|
"num_tokens": 13042831.0,
|
|
"step": 7510
|
|
},
|
|
{
|
|
"entropy": 5.650001335144043,
|
|
"epoch": 0.5847111456914997,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004971089279658954,
|
|
"loss": 5.4474,
|
|
"mean_token_accuracy": 0.16818668842315673,
|
|
"num_tokens": 13051614.0,
|
|
"step": 7515
|
|
},
|
|
{
|
|
"entropy": 5.640414476394653,
|
|
"epoch": 0.5851001750632173,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004971044975661663,
|
|
"loss": 5.4016,
|
|
"mean_token_accuracy": 0.17426666915416716,
|
|
"num_tokens": 13060179.0,
|
|
"step": 7520
|
|
},
|
|
{
|
|
"entropy": 5.551918649673462,
|
|
"epoch": 0.5854892044349348,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004971000637963549,
|
|
"loss": 5.329,
|
|
"mean_token_accuracy": 0.18348958790302278,
|
|
"num_tokens": 13068328.0,
|
|
"step": 7525
|
|
},
|
|
{
|
|
"entropy": 5.5161439895629885,
|
|
"epoch": 0.5858782338066524,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004970956266565285,
|
|
"loss": 5.3816,
|
|
"mean_token_accuracy": 0.17077172845602034,
|
|
"num_tokens": 13076879.0,
|
|
"step": 7530
|
|
},
|
|
{
|
|
"entropy": 5.701922178268433,
|
|
"epoch": 0.58626726317837,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004970911861467544,
|
|
"loss": 5.402,
|
|
"mean_token_accuracy": 0.1686718076467514,
|
|
"num_tokens": 13085123.0,
|
|
"step": 7535
|
|
},
|
|
{
|
|
"entropy": 5.559877395629883,
|
|
"epoch": 0.5866562925500876,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004970867422671002,
|
|
"loss": 5.3854,
|
|
"mean_token_accuracy": 0.17493418753147125,
|
|
"num_tokens": 13093884.0,
|
|
"step": 7540
|
|
},
|
|
{
|
|
"entropy": 5.691018915176391,
|
|
"epoch": 0.5870453219218051,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.000497082295017633,
|
|
"loss": 5.4406,
|
|
"mean_token_accuracy": 0.1709304377436638,
|
|
"num_tokens": 13102581.0,
|
|
"step": 7545
|
|
},
|
|
{
|
|
"entropy": 5.638440179824829,
|
|
"epoch": 0.5874343512935226,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004970778443984206,
|
|
"loss": 5.4096,
|
|
"mean_token_accuracy": 0.17096369117498397,
|
|
"num_tokens": 13111307.0,
|
|
"step": 7550
|
|
},
|
|
{
|
|
"entropy": 5.627034854888916,
|
|
"epoch": 0.5878233806652402,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004970733904095303,
|
|
"loss": 5.4292,
|
|
"mean_token_accuracy": 0.1729509636759758,
|
|
"num_tokens": 13119279.0,
|
|
"step": 7555
|
|
},
|
|
{
|
|
"entropy": 5.680221939086914,
|
|
"epoch": 0.5882124100369578,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004970689330510298,
|
|
"loss": 5.4427,
|
|
"mean_token_accuracy": 0.17425399124622346,
|
|
"num_tokens": 13127753.0,
|
|
"step": 7560
|
|
},
|
|
{
|
|
"entropy": 5.631756019592285,
|
|
"epoch": 0.5886014394086754,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004970644723229868,
|
|
"loss": 5.4736,
|
|
"mean_token_accuracy": 0.16918028891086578,
|
|
"num_tokens": 13136881.0,
|
|
"step": 7565
|
|
},
|
|
{
|
|
"entropy": 5.592969179153442,
|
|
"epoch": 0.588990468780393,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004970600082254687,
|
|
"loss": 5.3553,
|
|
"mean_token_accuracy": 0.1674942895770073,
|
|
"num_tokens": 13145291.0,
|
|
"step": 7570
|
|
},
|
|
{
|
|
"entropy": 5.5917394161224365,
|
|
"epoch": 0.5893794981521104,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004970555407585436,
|
|
"loss": 5.3184,
|
|
"mean_token_accuracy": 0.16939782500267028,
|
|
"num_tokens": 13153560.0,
|
|
"step": 7575
|
|
},
|
|
{
|
|
"entropy": 5.623266267776489,
|
|
"epoch": 0.589768527523828,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000497051069922279,
|
|
"loss": 5.3725,
|
|
"mean_token_accuracy": 0.1684000313282013,
|
|
"num_tokens": 13162304.0,
|
|
"step": 7580
|
|
},
|
|
{
|
|
"entropy": 5.644482421875,
|
|
"epoch": 0.5901575568955456,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004970465957167429,
|
|
"loss": 5.4001,
|
|
"mean_token_accuracy": 0.1760484278202057,
|
|
"num_tokens": 13171404.0,
|
|
"step": 7585
|
|
},
|
|
{
|
|
"entropy": 5.709658241271972,
|
|
"epoch": 0.5905465862672632,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000497042118142003,
|
|
"loss": 5.4724,
|
|
"mean_token_accuracy": 0.17499999850988388,
|
|
"num_tokens": 13180001.0,
|
|
"step": 7590
|
|
},
|
|
{
|
|
"entropy": 5.655188035964966,
|
|
"epoch": 0.5909356156389808,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004970376371981275,
|
|
"loss": 5.4073,
|
|
"mean_token_accuracy": 0.17146350145339967,
|
|
"num_tokens": 13189749.0,
|
|
"step": 7595
|
|
},
|
|
{
|
|
"entropy": 5.583410549163818,
|
|
"epoch": 0.5913246450106983,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004970331528851842,
|
|
"loss": 5.3954,
|
|
"mean_token_accuracy": 0.17423295825719834,
|
|
"num_tokens": 13199169.0,
|
|
"step": 7600
|
|
},
|
|
{
|
|
"entropy": 5.586973857879639,
|
|
"epoch": 0.5917136743824158,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004970286652032412,
|
|
"loss": 5.3387,
|
|
"mean_token_accuracy": 0.17489242255687715,
|
|
"num_tokens": 13207014.0,
|
|
"step": 7605
|
|
},
|
|
{
|
|
"entropy": 5.605558156967163,
|
|
"epoch": 0.5921027037541334,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004970241741523667,
|
|
"loss": 5.2923,
|
|
"mean_token_accuracy": 0.179923477768898,
|
|
"num_tokens": 13215333.0,
|
|
"step": 7610
|
|
},
|
|
{
|
|
"entropy": 5.582746839523315,
|
|
"epoch": 0.592491733125851,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004970196797326286,
|
|
"loss": 5.4311,
|
|
"mean_token_accuracy": 0.16824073791503907,
|
|
"num_tokens": 13223740.0,
|
|
"step": 7615
|
|
},
|
|
{
|
|
"entropy": 5.560179328918457,
|
|
"epoch": 0.5928807624975686,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004970151819440955,
|
|
"loss": 5.3647,
|
|
"mean_token_accuracy": 0.17508744299411774,
|
|
"num_tokens": 13232065.0,
|
|
"step": 7620
|
|
},
|
|
{
|
|
"entropy": 5.6420036315917965,
|
|
"epoch": 0.5932697918692861,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004970106807868351,
|
|
"loss": 5.35,
|
|
"mean_token_accuracy": 0.17854661941528321,
|
|
"num_tokens": 13241171.0,
|
|
"step": 7625
|
|
},
|
|
{
|
|
"entropy": 5.522149991989136,
|
|
"epoch": 0.5936588212410037,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000497006176260916,
|
|
"loss": 5.2764,
|
|
"mean_token_accuracy": 0.18158416748046874,
|
|
"num_tokens": 13249553.0,
|
|
"step": 7630
|
|
},
|
|
{
|
|
"entropy": 5.586422872543335,
|
|
"epoch": 0.5940478506127213,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004970016683664068,
|
|
"loss": 5.3492,
|
|
"mean_token_accuracy": 0.1729905426502228,
|
|
"num_tokens": 13258585.0,
|
|
"step": 7635
|
|
},
|
|
{
|
|
"entropy": 5.614265632629395,
|
|
"epoch": 0.5944368799844388,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004969971571033754,
|
|
"loss": 5.4276,
|
|
"mean_token_accuracy": 0.17271430492401124,
|
|
"num_tokens": 13267317.0,
|
|
"step": 7640
|
|
},
|
|
{
|
|
"entropy": 5.595805406570435,
|
|
"epoch": 0.5948259093561564,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004969926424718906,
|
|
"loss": 5.2315,
|
|
"mean_token_accuracy": 0.17310887724161148,
|
|
"num_tokens": 13275705.0,
|
|
"step": 7645
|
|
},
|
|
{
|
|
"entropy": 5.58509931564331,
|
|
"epoch": 0.5952149387278739,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004969881244720207,
|
|
"loss": 5.3738,
|
|
"mean_token_accuracy": 0.17260442823171615,
|
|
"num_tokens": 13284046.0,
|
|
"step": 7650
|
|
},
|
|
{
|
|
"entropy": 5.564942646026611,
|
|
"epoch": 0.5956039680995915,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004969836031038343,
|
|
"loss": 5.3487,
|
|
"mean_token_accuracy": 0.17941556870937347,
|
|
"num_tokens": 13292451.0,
|
|
"step": 7655
|
|
},
|
|
{
|
|
"entropy": 5.695221996307373,
|
|
"epoch": 0.5959929974713091,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004969790783674002,
|
|
"loss": 5.4852,
|
|
"mean_token_accuracy": 0.1700387567281723,
|
|
"num_tokens": 13300788.0,
|
|
"step": 7660
|
|
},
|
|
{
|
|
"entropy": 5.654481363296509,
|
|
"epoch": 0.5963820268430267,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004969745502627868,
|
|
"loss": 5.397,
|
|
"mean_token_accuracy": 0.17259870916604997,
|
|
"num_tokens": 13309235.0,
|
|
"step": 7665
|
|
},
|
|
{
|
|
"entropy": 5.555170011520386,
|
|
"epoch": 0.5967710562147442,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004969700187900629,
|
|
"loss": 5.307,
|
|
"mean_token_accuracy": 0.17510560154914856,
|
|
"num_tokens": 13317331.0,
|
|
"step": 7670
|
|
},
|
|
{
|
|
"entropy": 5.562815141677857,
|
|
"epoch": 0.5971600855864618,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004969654839492973,
|
|
"loss": 5.3472,
|
|
"mean_token_accuracy": 0.16236402094364166,
|
|
"num_tokens": 13327296.0,
|
|
"step": 7675
|
|
},
|
|
{
|
|
"entropy": 5.660052680969239,
|
|
"epoch": 0.5975491149581793,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004969609457405588,
|
|
"loss": 5.4045,
|
|
"mean_token_accuracy": 0.16961953341960906,
|
|
"num_tokens": 13336650.0,
|
|
"step": 7680
|
|
},
|
|
{
|
|
"entropy": 5.620706462860108,
|
|
"epoch": 0.5979381443298969,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004969564041639163,
|
|
"loss": 5.3521,
|
|
"mean_token_accuracy": 0.17291512042284013,
|
|
"num_tokens": 13345353.0,
|
|
"step": 7685
|
|
},
|
|
{
|
|
"entropy": 5.628172159194946,
|
|
"epoch": 0.5983271737016145,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004969518592194386,
|
|
"loss": 5.3714,
|
|
"mean_token_accuracy": 0.1745850458741188,
|
|
"num_tokens": 13354302.0,
|
|
"step": 7690
|
|
},
|
|
{
|
|
"entropy": 5.6162646293640135,
|
|
"epoch": 0.5987162030733321,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004969473109071946,
|
|
"loss": 5.314,
|
|
"mean_token_accuracy": 0.17899066358804702,
|
|
"num_tokens": 13362950.0,
|
|
"step": 7695
|
|
},
|
|
{
|
|
"entropy": 5.625281095504761,
|
|
"epoch": 0.5991052324450497,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004969427592272535,
|
|
"loss": 5.4219,
|
|
"mean_token_accuracy": 0.16785797625780105,
|
|
"num_tokens": 13371383.0,
|
|
"step": 7700
|
|
},
|
|
{
|
|
"entropy": 5.638612365722656,
|
|
"epoch": 0.5994942618167671,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004969382041796843,
|
|
"loss": 5.3742,
|
|
"mean_token_accuracy": 0.18112112283706666,
|
|
"num_tokens": 13379767.0,
|
|
"step": 7705
|
|
},
|
|
{
|
|
"entropy": 5.630096673965454,
|
|
"epoch": 0.5998832911884847,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000496933645764556,
|
|
"loss": 5.3864,
|
|
"mean_token_accuracy": 0.16946639716625214,
|
|
"num_tokens": 13387970.0,
|
|
"step": 7710
|
|
},
|
|
{
|
|
"entropy": 5.543959760665894,
|
|
"epoch": 0.6002723205602023,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004969290839819381,
|
|
"loss": 5.3336,
|
|
"mean_token_accuracy": 0.1790908545255661,
|
|
"num_tokens": 13396605.0,
|
|
"step": 7715
|
|
},
|
|
{
|
|
"entropy": 5.550653791427612,
|
|
"epoch": 0.6006613499319199,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004969245188318994,
|
|
"loss": 5.2794,
|
|
"mean_token_accuracy": 0.18368381559848784,
|
|
"num_tokens": 13406028.0,
|
|
"step": 7720
|
|
},
|
|
{
|
|
"entropy": 5.612054634094238,
|
|
"epoch": 0.6010503793036375,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004969199503145093,
|
|
"loss": 5.3223,
|
|
"mean_token_accuracy": 0.181209759414196,
|
|
"num_tokens": 13414927.0,
|
|
"step": 7725
|
|
},
|
|
{
|
|
"entropy": 5.531005764007569,
|
|
"epoch": 0.601439408675355,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004969153784298374,
|
|
"loss": 5.284,
|
|
"mean_token_accuracy": 0.1768856644630432,
|
|
"num_tokens": 13423020.0,
|
|
"step": 7730
|
|
},
|
|
{
|
|
"entropy": 5.509295701980591,
|
|
"epoch": 0.6018284380470725,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004969108031779527,
|
|
"loss": 5.2792,
|
|
"mean_token_accuracy": 0.17936475723981857,
|
|
"num_tokens": 13431514.0,
|
|
"step": 7735
|
|
},
|
|
{
|
|
"entropy": 5.622158241271973,
|
|
"epoch": 0.6022174674187901,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004969062245589247,
|
|
"loss": 5.451,
|
|
"mean_token_accuracy": 0.1655518352985382,
|
|
"num_tokens": 13440333.0,
|
|
"step": 7740
|
|
},
|
|
{
|
|
"entropy": 5.601479339599609,
|
|
"epoch": 0.6026064967905077,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004969016425728231,
|
|
"loss": 5.3896,
|
|
"mean_token_accuracy": 0.17400994896888733,
|
|
"num_tokens": 13448841.0,
|
|
"step": 7745
|
|
},
|
|
{
|
|
"entropy": 5.620350360870361,
|
|
"epoch": 0.6029955261622253,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004968970572197172,
|
|
"loss": 5.4691,
|
|
"mean_token_accuracy": 0.16713852137327195,
|
|
"num_tokens": 13457846.0,
|
|
"step": 7750
|
|
},
|
|
{
|
|
"entropy": 5.697343492507935,
|
|
"epoch": 0.6033845555339428,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004968924684996765,
|
|
"loss": 5.4593,
|
|
"mean_token_accuracy": 0.16241354048252105,
|
|
"num_tokens": 13466242.0,
|
|
"step": 7755
|
|
},
|
|
{
|
|
"entropy": 5.621889352798462,
|
|
"epoch": 0.6037735849056604,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000496887876412771,
|
|
"loss": 5.4069,
|
|
"mean_token_accuracy": 0.16790285110473632,
|
|
"num_tokens": 13474639.0,
|
|
"step": 7760
|
|
},
|
|
{
|
|
"entropy": 5.529103708267212,
|
|
"epoch": 0.6041626142773779,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004968832809590701,
|
|
"loss": 5.2877,
|
|
"mean_token_accuracy": 0.1749562978744507,
|
|
"num_tokens": 13483673.0,
|
|
"step": 7765
|
|
},
|
|
{
|
|
"entropy": 5.654218864440918,
|
|
"epoch": 0.6045516436490955,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004968786821386435,
|
|
"loss": 5.403,
|
|
"mean_token_accuracy": 0.16918199509382248,
|
|
"num_tokens": 13493001.0,
|
|
"step": 7770
|
|
},
|
|
{
|
|
"entropy": 5.737928676605224,
|
|
"epoch": 0.6049406730208131,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004968740799515611,
|
|
"loss": 5.4196,
|
|
"mean_token_accuracy": 0.17329576909542083,
|
|
"num_tokens": 13500878.0,
|
|
"step": 7775
|
|
},
|
|
{
|
|
"entropy": 5.644543170928955,
|
|
"epoch": 0.6053297023925306,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004968694743978926,
|
|
"loss": 5.4742,
|
|
"mean_token_accuracy": 0.16776228249073027,
|
|
"num_tokens": 13509945.0,
|
|
"step": 7780
|
|
},
|
|
{
|
|
"entropy": 5.5481706142425535,
|
|
"epoch": 0.6057187317642482,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004968648654777081,
|
|
"loss": 5.4034,
|
|
"mean_token_accuracy": 0.16965004354715346,
|
|
"num_tokens": 13520024.0,
|
|
"step": 7785
|
|
},
|
|
{
|
|
"entropy": 5.619679021835327,
|
|
"epoch": 0.6061077611359658,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004968602531910773,
|
|
"loss": 5.4879,
|
|
"mean_token_accuracy": 0.1689732030034065,
|
|
"num_tokens": 13529136.0,
|
|
"step": 7790
|
|
},
|
|
{
|
|
"entropy": 5.604547309875488,
|
|
"epoch": 0.6064967905076833,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004968556375380704,
|
|
"loss": 5.3067,
|
|
"mean_token_accuracy": 0.17450194507837297,
|
|
"num_tokens": 13537001.0,
|
|
"step": 7795
|
|
},
|
|
{
|
|
"entropy": 5.6026702404022215,
|
|
"epoch": 0.6068858198794009,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004968510185187571,
|
|
"loss": 5.2886,
|
|
"mean_token_accuracy": 0.17515256106853486,
|
|
"num_tokens": 13545520.0,
|
|
"step": 7800
|
|
},
|
|
{
|
|
"entropy": 5.569001913070679,
|
|
"epoch": 0.6072748492511184,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.000496846396133208,
|
|
"loss": 5.3665,
|
|
"mean_token_accuracy": 0.1716013804078102,
|
|
"num_tokens": 13554770.0,
|
|
"step": 7805
|
|
},
|
|
{
|
|
"entropy": 5.668507719039917,
|
|
"epoch": 0.607663878622836,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004968417703814928,
|
|
"loss": 5.4092,
|
|
"mean_token_accuracy": 0.1714569166302681,
|
|
"num_tokens": 13562797.0,
|
|
"step": 7810
|
|
},
|
|
{
|
|
"entropy": 5.597845935821534,
|
|
"epoch": 0.6080529079945536,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004968371412636818,
|
|
"loss": 5.3629,
|
|
"mean_token_accuracy": 0.17308429032564163,
|
|
"num_tokens": 13572017.0,
|
|
"step": 7815
|
|
},
|
|
{
|
|
"entropy": 5.6359875202178955,
|
|
"epoch": 0.6084419373662712,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004968325087798453,
|
|
"loss": 5.3776,
|
|
"mean_token_accuracy": 0.1751322031021118,
|
|
"num_tokens": 13580245.0,
|
|
"step": 7820
|
|
},
|
|
{
|
|
"entropy": 5.610501098632812,
|
|
"epoch": 0.6088309667379888,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004968278729300536,
|
|
"loss": 5.3483,
|
|
"mean_token_accuracy": 0.1653791770339012,
|
|
"num_tokens": 13588719.0,
|
|
"step": 7825
|
|
},
|
|
{
|
|
"entropy": 5.660403871536255,
|
|
"epoch": 0.6092199961097062,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004968232337143769,
|
|
"loss": 5.3892,
|
|
"mean_token_accuracy": 0.17397119104862213,
|
|
"num_tokens": 13597345.0,
|
|
"step": 7830
|
|
},
|
|
{
|
|
"entropy": 5.665544080734253,
|
|
"epoch": 0.6096090254814238,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004968185911328858,
|
|
"loss": 5.4156,
|
|
"mean_token_accuracy": 0.17118645012378692,
|
|
"num_tokens": 13605468.0,
|
|
"step": 7835
|
|
},
|
|
{
|
|
"entropy": 5.653286933898926,
|
|
"epoch": 0.6099980548531414,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004968139451856506,
|
|
"loss": 5.4297,
|
|
"mean_token_accuracy": 0.16750675886869432,
|
|
"num_tokens": 13614085.0,
|
|
"step": 7840
|
|
},
|
|
{
|
|
"entropy": 5.5557215213775635,
|
|
"epoch": 0.610387084224859,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004968092958727419,
|
|
"loss": 5.2759,
|
|
"mean_token_accuracy": 0.17956970781087875,
|
|
"num_tokens": 13622370.0,
|
|
"step": 7845
|
|
},
|
|
{
|
|
"entropy": 5.6002819538116455,
|
|
"epoch": 0.6107761135965766,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00049680464319423,
|
|
"loss": 5.3743,
|
|
"mean_token_accuracy": 0.18000267893075944,
|
|
"num_tokens": 13630615.0,
|
|
"step": 7850
|
|
},
|
|
{
|
|
"entropy": 5.631160593032837,
|
|
"epoch": 0.6111651429682942,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004967999871501858,
|
|
"loss": 5.2997,
|
|
"mean_token_accuracy": 0.18156272917985916,
|
|
"num_tokens": 13638461.0,
|
|
"step": 7855
|
|
},
|
|
{
|
|
"entropy": 5.560482788085937,
|
|
"epoch": 0.6115541723400116,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004967953277406798,
|
|
"loss": 5.4074,
|
|
"mean_token_accuracy": 0.1724785551428795,
|
|
"num_tokens": 13647266.0,
|
|
"step": 7860
|
|
},
|
|
{
|
|
"entropy": 5.554763126373291,
|
|
"epoch": 0.6119432017117292,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004967906649657828,
|
|
"loss": 5.3939,
|
|
"mean_token_accuracy": 0.17485640347003936,
|
|
"num_tokens": 13655930.0,
|
|
"step": 7865
|
|
},
|
|
{
|
|
"entropy": 5.644390821456909,
|
|
"epoch": 0.6123322310834468,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004967859988255655,
|
|
"loss": 5.3716,
|
|
"mean_token_accuracy": 0.17199483066797255,
|
|
"num_tokens": 13664427.0,
|
|
"step": 7870
|
|
},
|
|
{
|
|
"entropy": 5.62963171005249,
|
|
"epoch": 0.6127212604551644,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004967813293200985,
|
|
"loss": 5.4058,
|
|
"mean_token_accuracy": 0.16890444457530976,
|
|
"num_tokens": 13673120.0,
|
|
"step": 7875
|
|
},
|
|
{
|
|
"entropy": 5.534495687484741,
|
|
"epoch": 0.613110289826882,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004967766564494529,
|
|
"loss": 5.2386,
|
|
"mean_token_accuracy": 0.18175663352012633,
|
|
"num_tokens": 13681918.0,
|
|
"step": 7880
|
|
},
|
|
{
|
|
"entropy": 5.55442247390747,
|
|
"epoch": 0.6134993191985995,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004967719802136996,
|
|
"loss": 5.3277,
|
|
"mean_token_accuracy": 0.1815569058060646,
|
|
"num_tokens": 13689904.0,
|
|
"step": 7885
|
|
},
|
|
{
|
|
"entropy": 5.593478679656982,
|
|
"epoch": 0.613888348570317,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004967673006129094,
|
|
"loss": 5.3508,
|
|
"mean_token_accuracy": 0.17641768157482146,
|
|
"num_tokens": 13697861.0,
|
|
"step": 7890
|
|
},
|
|
{
|
|
"entropy": 5.706309461593628,
|
|
"epoch": 0.6142773779420346,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004967626176471536,
|
|
"loss": 5.507,
|
|
"mean_token_accuracy": 0.17445981055498122,
|
|
"num_tokens": 13706058.0,
|
|
"step": 7895
|
|
},
|
|
{
|
|
"entropy": 5.639518213272095,
|
|
"epoch": 0.6146664073137522,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004967579313165028,
|
|
"loss": 5.4266,
|
|
"mean_token_accuracy": 0.17015932351350785,
|
|
"num_tokens": 13715081.0,
|
|
"step": 7900
|
|
},
|
|
{
|
|
"entropy": 5.591048812866211,
|
|
"epoch": 0.6150554366854698,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004967532416210284,
|
|
"loss": 5.3097,
|
|
"mean_token_accuracy": 0.17756472676992416,
|
|
"num_tokens": 13723311.0,
|
|
"step": 7905
|
|
},
|
|
{
|
|
"entropy": 5.636404180526734,
|
|
"epoch": 0.6154444660571873,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004967485485608016,
|
|
"loss": 5.3424,
|
|
"mean_token_accuracy": 0.1731407791376114,
|
|
"num_tokens": 13731737.0,
|
|
"step": 7910
|
|
},
|
|
{
|
|
"entropy": 5.581039142608643,
|
|
"epoch": 0.6158334954289049,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004967438521358934,
|
|
"loss": 5.3939,
|
|
"mean_token_accuracy": 0.18245703727006912,
|
|
"num_tokens": 13740255.0,
|
|
"step": 7915
|
|
},
|
|
{
|
|
"entropy": 5.601918697357178,
|
|
"epoch": 0.6162225248006225,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004967391523463754,
|
|
"loss": 5.3485,
|
|
"mean_token_accuracy": 0.17710966467857361,
|
|
"num_tokens": 13748656.0,
|
|
"step": 7920
|
|
},
|
|
{
|
|
"entropy": 5.601391744613648,
|
|
"epoch": 0.61661155417234,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004967344491923185,
|
|
"loss": 5.3512,
|
|
"mean_token_accuracy": 0.17627048045396804,
|
|
"num_tokens": 13757539.0,
|
|
"step": 7925
|
|
},
|
|
{
|
|
"entropy": 5.63732876777649,
|
|
"epoch": 0.6170005835440576,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004967297426737943,
|
|
"loss": 5.3672,
|
|
"mean_token_accuracy": 0.17479392290115356,
|
|
"num_tokens": 13766569.0,
|
|
"step": 7930
|
|
},
|
|
{
|
|
"entropy": 5.64272632598877,
|
|
"epoch": 0.6173896129157751,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004967250327908742,
|
|
"loss": 5.3842,
|
|
"mean_token_accuracy": 0.17406178414821624,
|
|
"num_tokens": 13775071.0,
|
|
"step": 7935
|
|
},
|
|
{
|
|
"entropy": 5.59261908531189,
|
|
"epoch": 0.6177786422874927,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004967203195436297,
|
|
"loss": 5.3883,
|
|
"mean_token_accuracy": 0.17029981613159179,
|
|
"num_tokens": 13783319.0,
|
|
"step": 7940
|
|
},
|
|
{
|
|
"entropy": 5.504475259780884,
|
|
"epoch": 0.6181676716592103,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004967156029321322,
|
|
"loss": 5.3205,
|
|
"mean_token_accuracy": 0.17850407361984252,
|
|
"num_tokens": 13792746.0,
|
|
"step": 7945
|
|
},
|
|
{
|
|
"entropy": 5.615712118148804,
|
|
"epoch": 0.6185567010309279,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004967108829564532,
|
|
"loss": 5.2708,
|
|
"mean_token_accuracy": 0.1812506452202797,
|
|
"num_tokens": 13801632.0,
|
|
"step": 7950
|
|
},
|
|
{
|
|
"entropy": 5.6048766613006595,
|
|
"epoch": 0.6189457304026454,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004967061596166646,
|
|
"loss": 5.4089,
|
|
"mean_token_accuracy": 0.17564210891723633,
|
|
"num_tokens": 13810527.0,
|
|
"step": 7955
|
|
},
|
|
{
|
|
"entropy": 5.635960817337036,
|
|
"epoch": 0.6193347597743629,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004967014329128378,
|
|
"loss": 5.3415,
|
|
"mean_token_accuracy": 0.17582118660211563,
|
|
"num_tokens": 13819885.0,
|
|
"step": 7960
|
|
},
|
|
{
|
|
"entropy": 5.5821006298065186,
|
|
"epoch": 0.6197237891460805,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004966967028450448,
|
|
"loss": 5.3487,
|
|
"mean_token_accuracy": 0.17456280440092087,
|
|
"num_tokens": 13828509.0,
|
|
"step": 7965
|
|
},
|
|
{
|
|
"entropy": 5.618126344680786,
|
|
"epoch": 0.6201128185177981,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000496691969413357,
|
|
"loss": 5.3499,
|
|
"mean_token_accuracy": 0.1717231258749962,
|
|
"num_tokens": 13837196.0,
|
|
"step": 7970
|
|
},
|
|
{
|
|
"entropy": 5.672095489501953,
|
|
"epoch": 0.6205018478895157,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004966872326178466,
|
|
"loss": 5.4049,
|
|
"mean_token_accuracy": 0.1715243563055992,
|
|
"num_tokens": 13845849.0,
|
|
"step": 7975
|
|
},
|
|
{
|
|
"entropy": 5.6125000476837155,
|
|
"epoch": 0.6208908772612333,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004966824924585851,
|
|
"loss": 5.3245,
|
|
"mean_token_accuracy": 0.18061205595731736,
|
|
"num_tokens": 13853430.0,
|
|
"step": 7980
|
|
},
|
|
{
|
|
"entropy": 5.624846410751343,
|
|
"epoch": 0.6212799066329507,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004966777489356448,
|
|
"loss": 5.501,
|
|
"mean_token_accuracy": 0.16109914481639862,
|
|
"num_tokens": 13862520.0,
|
|
"step": 7985
|
|
},
|
|
{
|
|
"entropy": 5.689003944396973,
|
|
"epoch": 0.6216689360046683,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004966730020490975,
|
|
"loss": 5.4134,
|
|
"mean_token_accuracy": 0.16940829604864122,
|
|
"num_tokens": 13871064.0,
|
|
"step": 7990
|
|
},
|
|
{
|
|
"entropy": 5.604720258712769,
|
|
"epoch": 0.6220579653763859,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000496668251799015,
|
|
"loss": 5.3279,
|
|
"mean_token_accuracy": 0.16955282390117646,
|
|
"num_tokens": 13879952.0,
|
|
"step": 7995
|
|
},
|
|
{
|
|
"entropy": 5.669378137588501,
|
|
"epoch": 0.6224469947481035,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004966634981854699,
|
|
"loss": 5.4718,
|
|
"mean_token_accuracy": 0.16619216203689574,
|
|
"num_tokens": 13888054.0,
|
|
"step": 8000
|
|
},
|
|
{
|
|
"entropy": 5.682370376586914,
|
|
"epoch": 0.6228360241198211,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004966587412085339,
|
|
"loss": 5.4597,
|
|
"mean_token_accuracy": 0.16759533882141114,
|
|
"num_tokens": 13897051.0,
|
|
"step": 8005
|
|
},
|
|
{
|
|
"entropy": 5.615130519866943,
|
|
"epoch": 0.6232250534915386,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004966539808682793,
|
|
"loss": 5.4087,
|
|
"mean_token_accuracy": 0.16823190152645112,
|
|
"num_tokens": 13906175.0,
|
|
"step": 8010
|
|
},
|
|
{
|
|
"entropy": 5.588666582107544,
|
|
"epoch": 0.6236140828632561,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004966492171647783,
|
|
"loss": 5.3684,
|
|
"mean_token_accuracy": 0.17251305282115936,
|
|
"num_tokens": 13915283.0,
|
|
"step": 8015
|
|
},
|
|
{
|
|
"entropy": 5.611092948913575,
|
|
"epoch": 0.6240031122349737,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004966444500981032,
|
|
"loss": 5.4001,
|
|
"mean_token_accuracy": 0.17030985951423644,
|
|
"num_tokens": 13924007.0,
|
|
"step": 8020
|
|
},
|
|
{
|
|
"entropy": 5.601291561126709,
|
|
"epoch": 0.6243921416066913,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004966396796683265,
|
|
"loss": 5.3199,
|
|
"mean_token_accuracy": 0.17982642948627472,
|
|
"num_tokens": 13932694.0,
|
|
"step": 8025
|
|
},
|
|
{
|
|
"entropy": 5.662326431274414,
|
|
"epoch": 0.6247811709784089,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004966349058755204,
|
|
"loss": 5.4443,
|
|
"mean_token_accuracy": 0.16524723023176194,
|
|
"num_tokens": 13941817.0,
|
|
"step": 8030
|
|
},
|
|
{
|
|
"entropy": 5.623727893829345,
|
|
"epoch": 0.6251702003501264,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004966301287197573,
|
|
"loss": 5.267,
|
|
"mean_token_accuracy": 0.17870961129665375,
|
|
"num_tokens": 13950413.0,
|
|
"step": 8035
|
|
},
|
|
{
|
|
"entropy": 5.67491660118103,
|
|
"epoch": 0.625559229721844,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004966253482011098,
|
|
"loss": 5.4348,
|
|
"mean_token_accuracy": 0.16312237679958344,
|
|
"num_tokens": 13959415.0,
|
|
"step": 8040
|
|
},
|
|
{
|
|
"entropy": 5.560367059707642,
|
|
"epoch": 0.6259482590935616,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004966205643196503,
|
|
"loss": 5.2852,
|
|
"mean_token_accuracy": 0.178645259141922,
|
|
"num_tokens": 13967889.0,
|
|
"step": 8045
|
|
},
|
|
{
|
|
"entropy": 5.473169136047363,
|
|
"epoch": 0.6263372884652791,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004966157770754516,
|
|
"loss": 5.2764,
|
|
"mean_token_accuracy": 0.17681868076324464,
|
|
"num_tokens": 13976190.0,
|
|
"step": 8050
|
|
},
|
|
{
|
|
"entropy": 5.687845706939697,
|
|
"epoch": 0.6267263178369967,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000496610986468586,
|
|
"loss": 5.4326,
|
|
"mean_token_accuracy": 0.1652798607945442,
|
|
"num_tokens": 13984940.0,
|
|
"step": 8055
|
|
},
|
|
{
|
|
"entropy": 5.671137046813965,
|
|
"epoch": 0.6271153472087143,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004966061924991267,
|
|
"loss": 5.4124,
|
|
"mean_token_accuracy": 0.16456559300422668,
|
|
"num_tokens": 13993740.0,
|
|
"step": 8060
|
|
},
|
|
{
|
|
"entropy": 5.642599296569824,
|
|
"epoch": 0.6275043765804318,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000496601395167146,
|
|
"loss": 5.4491,
|
|
"mean_token_accuracy": 0.17298204749822615,
|
|
"num_tokens": 14002401.0,
|
|
"step": 8065
|
|
},
|
|
{
|
|
"entropy": 5.631506156921387,
|
|
"epoch": 0.6278934059521494,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004965965944727168,
|
|
"loss": 5.4333,
|
|
"mean_token_accuracy": 0.17514036148786544,
|
|
"num_tokens": 14011197.0,
|
|
"step": 8070
|
|
},
|
|
{
|
|
"entropy": 5.577688980102539,
|
|
"epoch": 0.628282435323867,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004965917904159121,
|
|
"loss": 5.3065,
|
|
"mean_token_accuracy": 0.17777174413204194,
|
|
"num_tokens": 14020344.0,
|
|
"step": 8075
|
|
},
|
|
{
|
|
"entropy": 5.550454330444336,
|
|
"epoch": 0.6286714646955845,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004965869829968046,
|
|
"loss": 5.3266,
|
|
"mean_token_accuracy": 0.17626356929540635,
|
|
"num_tokens": 14029117.0,
|
|
"step": 8080
|
|
},
|
|
{
|
|
"entropy": 5.547106027603149,
|
|
"epoch": 0.6290604940673021,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004965821722154674,
|
|
"loss": 5.2215,
|
|
"mean_token_accuracy": 0.18387194871902465,
|
|
"num_tokens": 14038395.0,
|
|
"step": 8085
|
|
},
|
|
{
|
|
"entropy": 5.582145690917969,
|
|
"epoch": 0.6294495234390196,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004965773580719734,
|
|
"loss": 5.3272,
|
|
"mean_token_accuracy": 0.17480739206075668,
|
|
"num_tokens": 14046983.0,
|
|
"step": 8090
|
|
},
|
|
{
|
|
"entropy": 5.510600614547729,
|
|
"epoch": 0.6298385528107372,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004965725405663957,
|
|
"loss": 5.2224,
|
|
"mean_token_accuracy": 0.18485897183418273,
|
|
"num_tokens": 14056261.0,
|
|
"step": 8095
|
|
},
|
|
{
|
|
"entropy": 5.55096583366394,
|
|
"epoch": 0.6302275821824548,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004965677196988073,
|
|
"loss": 5.3915,
|
|
"mean_token_accuracy": 0.1706537574529648,
|
|
"num_tokens": 14065371.0,
|
|
"step": 8100
|
|
},
|
|
{
|
|
"entropy": 5.64781346321106,
|
|
"epoch": 0.6306166115541724,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004965628954692815,
|
|
"loss": 5.4435,
|
|
"mean_token_accuracy": 0.1682393491268158,
|
|
"num_tokens": 14074007.0,
|
|
"step": 8105
|
|
},
|
|
{
|
|
"entropy": 5.582576656341553,
|
|
"epoch": 0.63100564092589,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004965580678778913,
|
|
"loss": 5.3122,
|
|
"mean_token_accuracy": 0.17798371911048888,
|
|
"num_tokens": 14083259.0,
|
|
"step": 8110
|
|
},
|
|
{
|
|
"entropy": 5.530705070495605,
|
|
"epoch": 0.6313946702976074,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004965532369247102,
|
|
"loss": 5.2977,
|
|
"mean_token_accuracy": 0.1768136814236641,
|
|
"num_tokens": 14090993.0,
|
|
"step": 8115
|
|
},
|
|
{
|
|
"entropy": 5.672610759735107,
|
|
"epoch": 0.631783699669325,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004965484026098111,
|
|
"loss": 5.4582,
|
|
"mean_token_accuracy": 0.17126849442720413,
|
|
"num_tokens": 14099722.0,
|
|
"step": 8120
|
|
},
|
|
{
|
|
"entropy": 5.69265775680542,
|
|
"epoch": 0.6321727290410426,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004965435649332679,
|
|
"loss": 5.4181,
|
|
"mean_token_accuracy": 0.17119095772504805,
|
|
"num_tokens": 14108483.0,
|
|
"step": 8125
|
|
},
|
|
{
|
|
"entropy": 5.676124429702758,
|
|
"epoch": 0.6325617584127602,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004965387238951536,
|
|
"loss": 5.4265,
|
|
"mean_token_accuracy": 0.17131333351135253,
|
|
"num_tokens": 14117187.0,
|
|
"step": 8130
|
|
},
|
|
{
|
|
"entropy": 5.570986270904541,
|
|
"epoch": 0.6329507877844778,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004965338794955418,
|
|
"loss": 5.2384,
|
|
"mean_token_accuracy": 0.18281993120908738,
|
|
"num_tokens": 14125424.0,
|
|
"step": 8135
|
|
},
|
|
{
|
|
"entropy": 5.582561111450195,
|
|
"epoch": 0.6333398171561953,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004965290317345061,
|
|
"loss": 5.3342,
|
|
"mean_token_accuracy": 0.17578710317611695,
|
|
"num_tokens": 14133038.0,
|
|
"step": 8140
|
|
},
|
|
{
|
|
"entropy": 5.64760570526123,
|
|
"epoch": 0.6337288465279128,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004965241806121198,
|
|
"loss": 5.4718,
|
|
"mean_token_accuracy": 0.16664536893367768,
|
|
"num_tokens": 14141114.0,
|
|
"step": 8145
|
|
},
|
|
{
|
|
"entropy": 5.626469612121582,
|
|
"epoch": 0.6341178758996304,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004965193261284567,
|
|
"loss": 5.3448,
|
|
"mean_token_accuracy": 0.17470071762800216,
|
|
"num_tokens": 14149681.0,
|
|
"step": 8150
|
|
},
|
|
{
|
|
"entropy": 5.643252897262573,
|
|
"epoch": 0.634506905271348,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004965144682835904,
|
|
"loss": 5.3751,
|
|
"mean_token_accuracy": 0.17150839567184448,
|
|
"num_tokens": 14158510.0,
|
|
"step": 8155
|
|
},
|
|
{
|
|
"entropy": 5.612422370910645,
|
|
"epoch": 0.6348959346430656,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004965096070775946,
|
|
"loss": 5.4212,
|
|
"mean_token_accuracy": 0.1791756570339203,
|
|
"num_tokens": 14166897.0,
|
|
"step": 8160
|
|
},
|
|
{
|
|
"entropy": 5.6259208679199215,
|
|
"epoch": 0.6352849640147831,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004965047425105431,
|
|
"loss": 5.3637,
|
|
"mean_token_accuracy": 0.17512688934803008,
|
|
"num_tokens": 14174692.0,
|
|
"step": 8165
|
|
},
|
|
{
|
|
"entropy": 5.635723733901978,
|
|
"epoch": 0.6356739933865007,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004964998745825097,
|
|
"loss": 5.3584,
|
|
"mean_token_accuracy": 0.17260195165872574,
|
|
"num_tokens": 14183779.0,
|
|
"step": 8170
|
|
},
|
|
{
|
|
"entropy": 5.611942434310913,
|
|
"epoch": 0.6360630227582182,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004964950032935682,
|
|
"loss": 5.4123,
|
|
"mean_token_accuracy": 0.17239698469638826,
|
|
"num_tokens": 14191809.0,
|
|
"step": 8175
|
|
},
|
|
{
|
|
"entropy": 5.583318996429443,
|
|
"epoch": 0.6364520521299358,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004964901286437927,
|
|
"loss": 5.3605,
|
|
"mean_token_accuracy": 0.16911054253578187,
|
|
"num_tokens": 14200652.0,
|
|
"step": 8180
|
|
},
|
|
{
|
|
"entropy": 5.60642819404602,
|
|
"epoch": 0.6368410815016534,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004964852506332568,
|
|
"loss": 5.3574,
|
|
"mean_token_accuracy": 0.17232050895690917,
|
|
"num_tokens": 14209694.0,
|
|
"step": 8185
|
|
},
|
|
{
|
|
"entropy": 5.61531982421875,
|
|
"epoch": 0.6372301108733709,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000496480369262035,
|
|
"loss": 5.3981,
|
|
"mean_token_accuracy": 0.17275434732437134,
|
|
"num_tokens": 14218040.0,
|
|
"step": 8190
|
|
},
|
|
{
|
|
"entropy": 5.556940221786499,
|
|
"epoch": 0.6376191402450885,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000496475484530201,
|
|
"loss": 5.3365,
|
|
"mean_token_accuracy": 0.1787574052810669,
|
|
"num_tokens": 14225908.0,
|
|
"step": 8195
|
|
},
|
|
{
|
|
"entropy": 5.5955792427062985,
|
|
"epoch": 0.6380081696168061,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004964705964378292,
|
|
"loss": 5.3469,
|
|
"mean_token_accuracy": 0.16975195556879044,
|
|
"num_tokens": 14234140.0,
|
|
"step": 8200
|
|
},
|
|
{
|
|
"entropy": 5.660179615020752,
|
|
"epoch": 0.6383971989885237,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004964657049849934,
|
|
"loss": 5.4016,
|
|
"mean_token_accuracy": 0.17422222793102266,
|
|
"num_tokens": 14243590.0,
|
|
"step": 8205
|
|
},
|
|
{
|
|
"entropy": 5.640476036071777,
|
|
"epoch": 0.6387862283602412,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004964608101717681,
|
|
"loss": 5.3899,
|
|
"mean_token_accuracy": 0.17153700143098832,
|
|
"num_tokens": 14252249.0,
|
|
"step": 8210
|
|
},
|
|
{
|
|
"entropy": 5.5549538135528564,
|
|
"epoch": 0.6391752577319587,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004964559119982275,
|
|
"loss": 5.2946,
|
|
"mean_token_accuracy": 0.1751054957509041,
|
|
"num_tokens": 14261147.0,
|
|
"step": 8215
|
|
},
|
|
{
|
|
"entropy": 5.60577163696289,
|
|
"epoch": 0.6395642871036763,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000496451010464446,
|
|
"loss": 5.381,
|
|
"mean_token_accuracy": 0.17149227261543273,
|
|
"num_tokens": 14270309.0,
|
|
"step": 8220
|
|
},
|
|
{
|
|
"entropy": 5.580153703689575,
|
|
"epoch": 0.6399533164753939,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004964461055704978,
|
|
"loss": 5.3534,
|
|
"mean_token_accuracy": 0.17434841990470887,
|
|
"num_tokens": 14279379.0,
|
|
"step": 8225
|
|
},
|
|
{
|
|
"entropy": 5.578339242935181,
|
|
"epoch": 0.6403423458471115,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004964411973164574,
|
|
"loss": 5.3022,
|
|
"mean_token_accuracy": 0.17278128117322922,
|
|
"num_tokens": 14288136.0,
|
|
"step": 8230
|
|
},
|
|
{
|
|
"entropy": 5.548076820373535,
|
|
"epoch": 0.6407313752188291,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004964362857023993,
|
|
"loss": 5.2367,
|
|
"mean_token_accuracy": 0.1741736575961113,
|
|
"num_tokens": 14296437.0,
|
|
"step": 8235
|
|
},
|
|
{
|
|
"entropy": 5.511275911331177,
|
|
"epoch": 0.6411204045905465,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000496431370728398,
|
|
"loss": 5.2832,
|
|
"mean_token_accuracy": 0.18518003970384597,
|
|
"num_tokens": 14304861.0,
|
|
"step": 8240
|
|
},
|
|
{
|
|
"entropy": 5.499144077301025,
|
|
"epoch": 0.6415094339622641,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004964264523945281,
|
|
"loss": 5.3357,
|
|
"mean_token_accuracy": 0.17871750742197037,
|
|
"num_tokens": 14312861.0,
|
|
"step": 8245
|
|
},
|
|
{
|
|
"entropy": 5.495590162277222,
|
|
"epoch": 0.6418984633339817,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004964215307008643,
|
|
"loss": 5.1809,
|
|
"mean_token_accuracy": 0.1813568279147148,
|
|
"num_tokens": 14321651.0,
|
|
"step": 8250
|
|
},
|
|
{
|
|
"entropy": 5.622010946273804,
|
|
"epoch": 0.6422874927056993,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004964166056474811,
|
|
"loss": 5.3699,
|
|
"mean_token_accuracy": 0.18560284674167632,
|
|
"num_tokens": 14329234.0,
|
|
"step": 8255
|
|
},
|
|
{
|
|
"entropy": 5.614206838607788,
|
|
"epoch": 0.6426765220774169,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004964116772344534,
|
|
"loss": 5.4891,
|
|
"mean_token_accuracy": 0.17152170538902284,
|
|
"num_tokens": 14337603.0,
|
|
"step": 8260
|
|
},
|
|
{
|
|
"entropy": 5.587452936172485,
|
|
"epoch": 0.6430655514491345,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004964067454618559,
|
|
"loss": 5.3606,
|
|
"mean_token_accuracy": 0.17309214770793915,
|
|
"num_tokens": 14346634.0,
|
|
"step": 8265
|
|
},
|
|
{
|
|
"entropy": 5.642218828201294,
|
|
"epoch": 0.6434545808208519,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004964018103297634,
|
|
"loss": 5.3903,
|
|
"mean_token_accuracy": 0.1727163702249527,
|
|
"num_tokens": 14355336.0,
|
|
"step": 8270
|
|
},
|
|
{
|
|
"entropy": 5.588451719284057,
|
|
"epoch": 0.6438436101925695,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004963968718382509,
|
|
"loss": 5.3387,
|
|
"mean_token_accuracy": 0.17309121489524842,
|
|
"num_tokens": 14364434.0,
|
|
"step": 8275
|
|
},
|
|
{
|
|
"entropy": 5.589485788345337,
|
|
"epoch": 0.6442326395642871,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004963919299873931,
|
|
"loss": 5.2902,
|
|
"mean_token_accuracy": 0.1865809217095375,
|
|
"num_tokens": 14372454.0,
|
|
"step": 8280
|
|
},
|
|
{
|
|
"entropy": 5.588171482086182,
|
|
"epoch": 0.6446216689360047,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004963869847772653,
|
|
"loss": 5.3273,
|
|
"mean_token_accuracy": 0.17058257311582564,
|
|
"num_tokens": 14381381.0,
|
|
"step": 8285
|
|
},
|
|
{
|
|
"entropy": 5.633420133590699,
|
|
"epoch": 0.6450106983077223,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004963820362079423,
|
|
"loss": 5.4332,
|
|
"mean_token_accuracy": 0.17251765131950378,
|
|
"num_tokens": 14390853.0,
|
|
"step": 8290
|
|
},
|
|
{
|
|
"entropy": 5.5635377883911135,
|
|
"epoch": 0.6453997276794398,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004963770842794994,
|
|
"loss": 5.2868,
|
|
"mean_token_accuracy": 0.17360883802175522,
|
|
"num_tokens": 14399897.0,
|
|
"step": 8295
|
|
},
|
|
{
|
|
"entropy": 5.515204811096192,
|
|
"epoch": 0.6457887570511573,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004963721289920115,
|
|
"loss": 5.3473,
|
|
"mean_token_accuracy": 0.1733364999294281,
|
|
"num_tokens": 14408192.0,
|
|
"step": 8300
|
|
},
|
|
{
|
|
"entropy": 5.562912654876709,
|
|
"epoch": 0.6461777864228749,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004963671703455538,
|
|
"loss": 5.235,
|
|
"mean_token_accuracy": 0.18256812691688537,
|
|
"num_tokens": 14416004.0,
|
|
"step": 8305
|
|
},
|
|
{
|
|
"entropy": 5.563345527648925,
|
|
"epoch": 0.6465668157945925,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004963622083402018,
|
|
"loss": 5.2775,
|
|
"mean_token_accuracy": 0.1796865537762642,
|
|
"num_tokens": 14424573.0,
|
|
"step": 8310
|
|
},
|
|
{
|
|
"entropy": 5.556096458435059,
|
|
"epoch": 0.6469558451663101,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004963572429760305,
|
|
"loss": 5.2634,
|
|
"mean_token_accuracy": 0.18015891015529634,
|
|
"num_tokens": 14432756.0,
|
|
"step": 8315
|
|
},
|
|
{
|
|
"entropy": 5.625596141815185,
|
|
"epoch": 0.6473448745380276,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004963522742531155,
|
|
"loss": 5.3662,
|
|
"mean_token_accuracy": 0.17505901157855988,
|
|
"num_tokens": 14441695.0,
|
|
"step": 8320
|
|
},
|
|
{
|
|
"entropy": 5.582406759262085,
|
|
"epoch": 0.6477339039097452,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000496347302171532,
|
|
"loss": 5.4448,
|
|
"mean_token_accuracy": 0.1656550168991089,
|
|
"num_tokens": 14451233.0,
|
|
"step": 8325
|
|
},
|
|
{
|
|
"entropy": 5.6259113311767575,
|
|
"epoch": 0.6481229332814628,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004963423267313554,
|
|
"loss": 5.3415,
|
|
"mean_token_accuracy": 0.17475675642490388,
|
|
"num_tokens": 14459757.0,
|
|
"step": 8330
|
|
},
|
|
{
|
|
"entropy": 5.614810228347778,
|
|
"epoch": 0.6485119626531803,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004963373479326614,
|
|
"loss": 5.4108,
|
|
"mean_token_accuracy": 0.16576436012983323,
|
|
"num_tokens": 14468308.0,
|
|
"step": 8335
|
|
},
|
|
{
|
|
"entropy": 5.608193254470825,
|
|
"epoch": 0.6489009920248979,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004963323657755255,
|
|
"loss": 5.3428,
|
|
"mean_token_accuracy": 0.18068965524435043,
|
|
"num_tokens": 14476654.0,
|
|
"step": 8340
|
|
},
|
|
{
|
|
"entropy": 5.615989542007446,
|
|
"epoch": 0.6492900213966154,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004963273802600231,
|
|
"loss": 5.4243,
|
|
"mean_token_accuracy": 0.17392317503690718,
|
|
"num_tokens": 14484960.0,
|
|
"step": 8345
|
|
},
|
|
{
|
|
"entropy": 5.67059440612793,
|
|
"epoch": 0.649679050768333,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00049632239138623,
|
|
"loss": 5.4473,
|
|
"mean_token_accuracy": 0.16484784781932832,
|
|
"num_tokens": 14493708.0,
|
|
"step": 8350
|
|
},
|
|
{
|
|
"entropy": 5.6571794033050535,
|
|
"epoch": 0.6500680801400506,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004963173991542219,
|
|
"loss": 5.3834,
|
|
"mean_token_accuracy": 0.1717427045106888,
|
|
"num_tokens": 14502123.0,
|
|
"step": 8355
|
|
},
|
|
{
|
|
"entropy": 5.606250286102295,
|
|
"epoch": 0.6504571095117682,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004963124035640746,
|
|
"loss": 5.3403,
|
|
"mean_token_accuracy": 0.17879369109869003,
|
|
"num_tokens": 14510782.0,
|
|
"step": 8360
|
|
},
|
|
{
|
|
"entropy": 5.551813840866089,
|
|
"epoch": 0.6508461388834857,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004963074046158637,
|
|
"loss": 5.305,
|
|
"mean_token_accuracy": 0.17476321160793304,
|
|
"num_tokens": 14518560.0,
|
|
"step": 8365
|
|
},
|
|
{
|
|
"entropy": 5.608090591430664,
|
|
"epoch": 0.6512351682552032,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004963024023096652,
|
|
"loss": 5.3185,
|
|
"mean_token_accuracy": 0.17200247645378114,
|
|
"num_tokens": 14527541.0,
|
|
"step": 8370
|
|
},
|
|
{
|
|
"entropy": 5.662448120117188,
|
|
"epoch": 0.6516241976269208,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004962973966455551,
|
|
"loss": 5.3703,
|
|
"mean_token_accuracy": 0.17151203900575637,
|
|
"num_tokens": 14535590.0,
|
|
"step": 8375
|
|
},
|
|
{
|
|
"entropy": 5.5442280769348145,
|
|
"epoch": 0.6520132269986384,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004962923876236092,
|
|
"loss": 5.2649,
|
|
"mean_token_accuracy": 0.17731465846300126,
|
|
"num_tokens": 14544929.0,
|
|
"step": 8380
|
|
},
|
|
{
|
|
"entropy": 5.623966121673584,
|
|
"epoch": 0.652402256370356,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004962873752439035,
|
|
"loss": 5.4207,
|
|
"mean_token_accuracy": 0.16555396616458892,
|
|
"num_tokens": 14553883.0,
|
|
"step": 8385
|
|
},
|
|
{
|
|
"entropy": 5.685714960098267,
|
|
"epoch": 0.6527912857420736,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004962823595065141,
|
|
"loss": 5.4371,
|
|
"mean_token_accuracy": 0.17250010073184968,
|
|
"num_tokens": 14563085.0,
|
|
"step": 8390
|
|
},
|
|
{
|
|
"entropy": 5.634870195388794,
|
|
"epoch": 0.653180315113791,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004962773404115172,
|
|
"loss": 5.3234,
|
|
"mean_token_accuracy": 0.17301514893770217,
|
|
"num_tokens": 14571444.0,
|
|
"step": 8395
|
|
},
|
|
{
|
|
"entropy": 5.61317024230957,
|
|
"epoch": 0.6535693444855086,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004962723179589886,
|
|
"loss": 5.402,
|
|
"mean_token_accuracy": 0.17384381145238875,
|
|
"num_tokens": 14580039.0,
|
|
"step": 8400
|
|
},
|
|
{
|
|
"entropy": 5.569257354736328,
|
|
"epoch": 0.6539583738572262,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000496267292149005,
|
|
"loss": 5.264,
|
|
"mean_token_accuracy": 0.18640352338552474,
|
|
"num_tokens": 14588322.0,
|
|
"step": 8405
|
|
},
|
|
{
|
|
"entropy": 5.545172119140625,
|
|
"epoch": 0.6543474032289438,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004962622629816423,
|
|
"loss": 5.2215,
|
|
"mean_token_accuracy": 0.1789401650428772,
|
|
"num_tokens": 14597503.0,
|
|
"step": 8410
|
|
},
|
|
{
|
|
"entropy": 5.587301301956177,
|
|
"epoch": 0.6547364326006614,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000496257230456977,
|
|
"loss": 5.3655,
|
|
"mean_token_accuracy": 0.17540100067853928,
|
|
"num_tokens": 14605804.0,
|
|
"step": 8415
|
|
},
|
|
{
|
|
"entropy": 5.4942773342132565,
|
|
"epoch": 0.6551254619723789,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004962521945750855,
|
|
"loss": 5.2975,
|
|
"mean_token_accuracy": 0.18086225539445877,
|
|
"num_tokens": 14614064.0,
|
|
"step": 8420
|
|
},
|
|
{
|
|
"entropy": 5.6478150367736815,
|
|
"epoch": 0.6555144913440965,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000496247155336044,
|
|
"loss": 5.2648,
|
|
"mean_token_accuracy": 0.18014039248228073,
|
|
"num_tokens": 14622231.0,
|
|
"step": 8425
|
|
},
|
|
{
|
|
"entropy": 5.552904510498047,
|
|
"epoch": 0.655903520715814,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004962421127399291,
|
|
"loss": 5.4039,
|
|
"mean_token_accuracy": 0.1692470505833626,
|
|
"num_tokens": 14631244.0,
|
|
"step": 8430
|
|
},
|
|
{
|
|
"entropy": 5.524405384063721,
|
|
"epoch": 0.6562925500875316,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004962370667868172,
|
|
"loss": 5.2641,
|
|
"mean_token_accuracy": 0.17578798532485962,
|
|
"num_tokens": 14639575.0,
|
|
"step": 8435
|
|
},
|
|
{
|
|
"entropy": 5.594518995285034,
|
|
"epoch": 0.6566815794592492,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004962320174767851,
|
|
"loss": 5.3199,
|
|
"mean_token_accuracy": 0.17032575458288193,
|
|
"num_tokens": 14648810.0,
|
|
"step": 8440
|
|
},
|
|
{
|
|
"entropy": 5.552857780456543,
|
|
"epoch": 0.6570706088309667,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000496226964809909,
|
|
"loss": 5.1853,
|
|
"mean_token_accuracy": 0.18572386652231215,
|
|
"num_tokens": 14657783.0,
|
|
"step": 8445
|
|
},
|
|
{
|
|
"entropy": 5.627866172790528,
|
|
"epoch": 0.6574596382026843,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000496221908786266,
|
|
"loss": 5.366,
|
|
"mean_token_accuracy": 0.1744003027677536,
|
|
"num_tokens": 14666872.0,
|
|
"step": 8450
|
|
},
|
|
{
|
|
"entropy": 5.640341329574585,
|
|
"epoch": 0.6578486675744019,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004962168494059327,
|
|
"loss": 5.4804,
|
|
"mean_token_accuracy": 0.1615436539053917,
|
|
"num_tokens": 14675762.0,
|
|
"step": 8455
|
|
},
|
|
{
|
|
"entropy": 5.52385983467102,
|
|
"epoch": 0.6582376969461194,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004962117866689857,
|
|
"loss": 5.1544,
|
|
"mean_token_accuracy": 0.18567788302898408,
|
|
"num_tokens": 14683928.0,
|
|
"step": 8460
|
|
},
|
|
{
|
|
"entropy": 5.588550329208374,
|
|
"epoch": 0.658626726317837,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000496206720575502,
|
|
"loss": 5.4038,
|
|
"mean_token_accuracy": 0.17150904834270478,
|
|
"num_tokens": 14692411.0,
|
|
"step": 8465
|
|
},
|
|
{
|
|
"entropy": 5.625606918334961,
|
|
"epoch": 0.6590157556895546,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004962016511255584,
|
|
"loss": 5.3984,
|
|
"mean_token_accuracy": 0.16342231035232543,
|
|
"num_tokens": 14701002.0,
|
|
"step": 8470
|
|
},
|
|
{
|
|
"entropy": 5.719677305221557,
|
|
"epoch": 0.6594047850612721,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004961965783192318,
|
|
"loss": 5.4499,
|
|
"mean_token_accuracy": 0.1649780184030533,
|
|
"num_tokens": 14710172.0,
|
|
"step": 8475
|
|
},
|
|
{
|
|
"entropy": 5.5820893287658695,
|
|
"epoch": 0.6597938144329897,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004961915021565992,
|
|
"loss": 5.372,
|
|
"mean_token_accuracy": 0.174167899787426,
|
|
"num_tokens": 14719446.0,
|
|
"step": 8480
|
|
},
|
|
{
|
|
"entropy": 5.643054580688476,
|
|
"epoch": 0.6601828438047073,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004961864226377377,
|
|
"loss": 5.3936,
|
|
"mean_token_accuracy": 0.17270140647888182,
|
|
"num_tokens": 14728193.0,
|
|
"step": 8485
|
|
},
|
|
{
|
|
"entropy": 5.587178659439087,
|
|
"epoch": 0.6605718731764249,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004961813397627241,
|
|
"loss": 5.2796,
|
|
"mean_token_accuracy": 0.1707806646823883,
|
|
"num_tokens": 14736930.0,
|
|
"step": 8490
|
|
},
|
|
{
|
|
"entropy": 5.566015577316284,
|
|
"epoch": 0.6609609025481424,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004961762535316358,
|
|
"loss": 5.2835,
|
|
"mean_token_accuracy": 0.18451686799526215,
|
|
"num_tokens": 14745995.0,
|
|
"step": 8495
|
|
},
|
|
{
|
|
"entropy": 5.511094856262207,
|
|
"epoch": 0.6613499319198599,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004961711639445499,
|
|
"loss": 5.3234,
|
|
"mean_token_accuracy": 0.16954112946987152,
|
|
"num_tokens": 14754827.0,
|
|
"step": 8500
|
|
},
|
|
{
|
|
"entropy": 5.64048957824707,
|
|
"epoch": 0.6617389612915775,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004961660710015435,
|
|
"loss": 5.3943,
|
|
"mean_token_accuracy": 0.17115921825170516,
|
|
"num_tokens": 14763594.0,
|
|
"step": 8505
|
|
},
|
|
{
|
|
"entropy": 5.57706847190857,
|
|
"epoch": 0.6621279906632951,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004961609747026943,
|
|
"loss": 5.2597,
|
|
"mean_token_accuracy": 0.18465231359004974,
|
|
"num_tokens": 14772366.0,
|
|
"step": 8510
|
|
},
|
|
{
|
|
"entropy": 5.568675518035889,
|
|
"epoch": 0.6625170200350127,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004961558750480791,
|
|
"loss": 5.3195,
|
|
"mean_token_accuracy": 0.17469608932733535,
|
|
"num_tokens": 14780738.0,
|
|
"step": 8515
|
|
},
|
|
{
|
|
"entropy": 5.560606145858765,
|
|
"epoch": 0.6629060494067303,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004961507720377756,
|
|
"loss": 5.3064,
|
|
"mean_token_accuracy": 0.17217658460140228,
|
|
"num_tokens": 14788982.0,
|
|
"step": 8520
|
|
},
|
|
{
|
|
"entropy": 5.572122621536255,
|
|
"epoch": 0.6632950787784477,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004961456656718611,
|
|
"loss": 5.2772,
|
|
"mean_token_accuracy": 0.18133418411016464,
|
|
"num_tokens": 14797832.0,
|
|
"step": 8525
|
|
},
|
|
{
|
|
"entropy": 5.604490184783936,
|
|
"epoch": 0.6636841081501653,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000496140555950413,
|
|
"loss": 5.3338,
|
|
"mean_token_accuracy": 0.18062032610177994,
|
|
"num_tokens": 14806391.0,
|
|
"step": 8530
|
|
},
|
|
{
|
|
"entropy": 5.632673883438111,
|
|
"epoch": 0.6640731375218829,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004961354428735091,
|
|
"loss": 5.3655,
|
|
"mean_token_accuracy": 0.16731194257736207,
|
|
"num_tokens": 14814920.0,
|
|
"step": 8535
|
|
},
|
|
{
|
|
"entropy": 5.536898851394653,
|
|
"epoch": 0.6644621668936005,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004961303264412267,
|
|
"loss": 5.2996,
|
|
"mean_token_accuracy": 0.1719740927219391,
|
|
"num_tokens": 14823541.0,
|
|
"step": 8540
|
|
},
|
|
{
|
|
"entropy": 5.521430206298828,
|
|
"epoch": 0.6648511962653181,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004961252066536437,
|
|
"loss": 5.2532,
|
|
"mean_token_accuracy": 0.17664670646190644,
|
|
"num_tokens": 14832128.0,
|
|
"step": 8545
|
|
},
|
|
{
|
|
"entropy": 5.618033218383789,
|
|
"epoch": 0.6652402256370356,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004961200835108375,
|
|
"loss": 5.4163,
|
|
"mean_token_accuracy": 0.1642109453678131,
|
|
"num_tokens": 14841434.0,
|
|
"step": 8550
|
|
},
|
|
{
|
|
"entropy": 5.580253076553345,
|
|
"epoch": 0.6656292550087531,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000496114957012886,
|
|
"loss": 5.3437,
|
|
"mean_token_accuracy": 0.17707033604383468,
|
|
"num_tokens": 14850255.0,
|
|
"step": 8555
|
|
},
|
|
{
|
|
"entropy": 5.596495056152344,
|
|
"epoch": 0.6660182843804707,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004961098271598671,
|
|
"loss": 5.4239,
|
|
"mean_token_accuracy": 0.16565164923667908,
|
|
"num_tokens": 14858924.0,
|
|
"step": 8560
|
|
},
|
|
{
|
|
"entropy": 5.557281541824341,
|
|
"epoch": 0.6664073137521883,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004961046939518585,
|
|
"loss": 5.3626,
|
|
"mean_token_accuracy": 0.1835842475295067,
|
|
"num_tokens": 14867426.0,
|
|
"step": 8565
|
|
},
|
|
{
|
|
"entropy": 5.608879566192627,
|
|
"epoch": 0.6667963431239059,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004960995573889379,
|
|
"loss": 5.3233,
|
|
"mean_token_accuracy": 0.17866379916667938,
|
|
"num_tokens": 14876218.0,
|
|
"step": 8570
|
|
},
|
|
{
|
|
"entropy": 5.628923988342285,
|
|
"epoch": 0.6671853724956234,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004960944174711836,
|
|
"loss": 5.3501,
|
|
"mean_token_accuracy": 0.17644556611776352,
|
|
"num_tokens": 14883995.0,
|
|
"step": 8575
|
|
},
|
|
{
|
|
"entropy": 5.531912612915039,
|
|
"epoch": 0.667574401867341,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004960892741986734,
|
|
"loss": 5.3415,
|
|
"mean_token_accuracy": 0.17149577885866166,
|
|
"num_tokens": 14892659.0,
|
|
"step": 8580
|
|
},
|
|
{
|
|
"entropy": 5.603481960296631,
|
|
"epoch": 0.6679634312390585,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004960841275714853,
|
|
"loss": 5.3565,
|
|
"mean_token_accuracy": 0.17346323430538177,
|
|
"num_tokens": 14901518.0,
|
|
"step": 8585
|
|
},
|
|
{
|
|
"entropy": 5.588987255096436,
|
|
"epoch": 0.6683524606107761,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004960789775896975,
|
|
"loss": 5.3539,
|
|
"mean_token_accuracy": 0.17684564739465714,
|
|
"num_tokens": 14910171.0,
|
|
"step": 8590
|
|
},
|
|
{
|
|
"entropy": 5.598988437652588,
|
|
"epoch": 0.6687414899824937,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004960738242533881,
|
|
"loss": 5.3309,
|
|
"mean_token_accuracy": 0.17272143065929413,
|
|
"num_tokens": 14918651.0,
|
|
"step": 8595
|
|
},
|
|
{
|
|
"entropy": 5.54523344039917,
|
|
"epoch": 0.6691305193542112,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004960686675626353,
|
|
"loss": 5.3431,
|
|
"mean_token_accuracy": 0.17127756029367447,
|
|
"num_tokens": 14926951.0,
|
|
"step": 8600
|
|
},
|
|
{
|
|
"entropy": 5.638353586196899,
|
|
"epoch": 0.6695195487259288,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004960635075175173,
|
|
"loss": 5.4229,
|
|
"mean_token_accuracy": 0.17560173869132994,
|
|
"num_tokens": 14935528.0,
|
|
"step": 8605
|
|
},
|
|
{
|
|
"entropy": 5.578430795669556,
|
|
"epoch": 0.6699085780976464,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004960583441181124,
|
|
"loss": 5.2918,
|
|
"mean_token_accuracy": 0.1793479025363922,
|
|
"num_tokens": 14944117.0,
|
|
"step": 8610
|
|
},
|
|
{
|
|
"entropy": 5.4936277866363525,
|
|
"epoch": 0.670297607469364,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004960531773644992,
|
|
"loss": 5.281,
|
|
"mean_token_accuracy": 0.17999966442584991,
|
|
"num_tokens": 14952957.0,
|
|
"step": 8615
|
|
},
|
|
{
|
|
"entropy": 5.590290164947509,
|
|
"epoch": 0.6706866368410815,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004960480072567557,
|
|
"loss": 5.3397,
|
|
"mean_token_accuracy": 0.17372976392507553,
|
|
"num_tokens": 14960942.0,
|
|
"step": 8620
|
|
},
|
|
{
|
|
"entropy": 5.689679288864136,
|
|
"epoch": 0.671075666212799,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004960428337949604,
|
|
"loss": 5.4342,
|
|
"mean_token_accuracy": 0.16590507626533507,
|
|
"num_tokens": 14970579.0,
|
|
"step": 8625
|
|
},
|
|
{
|
|
"entropy": 5.559392261505127,
|
|
"epoch": 0.6714646955845166,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004960376569791921,
|
|
"loss": 5.2691,
|
|
"mean_token_accuracy": 0.1740999326109886,
|
|
"num_tokens": 14979353.0,
|
|
"step": 8630
|
|
},
|
|
{
|
|
"entropy": 5.622280597686768,
|
|
"epoch": 0.6718537249562342,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004960324768095291,
|
|
"loss": 5.4223,
|
|
"mean_token_accuracy": 0.1784879356622696,
|
|
"num_tokens": 14988435.0,
|
|
"step": 8635
|
|
},
|
|
{
|
|
"entropy": 5.572164249420166,
|
|
"epoch": 0.6722427543279518,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004960272932860502,
|
|
"loss": 5.3588,
|
|
"mean_token_accuracy": 0.1725583553314209,
|
|
"num_tokens": 14996834.0,
|
|
"step": 8640
|
|
},
|
|
{
|
|
"entropy": 5.635668087005615,
|
|
"epoch": 0.6726317836996694,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004960221064088338,
|
|
"loss": 5.4251,
|
|
"mean_token_accuracy": 0.1681579142808914,
|
|
"num_tokens": 15004988.0,
|
|
"step": 8645
|
|
},
|
|
{
|
|
"entropy": 5.679348278045654,
|
|
"epoch": 0.6730208130713868,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004960169161779588,
|
|
"loss": 5.364,
|
|
"mean_token_accuracy": 0.1767076998949051,
|
|
"num_tokens": 15013482.0,
|
|
"step": 8650
|
|
},
|
|
{
|
|
"entropy": 5.5645733833312985,
|
|
"epoch": 0.6734098424431044,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004960117225935038,
|
|
"loss": 5.256,
|
|
"mean_token_accuracy": 0.1800806149840355,
|
|
"num_tokens": 15021506.0,
|
|
"step": 8655
|
|
},
|
|
{
|
|
"entropy": 5.573781538009643,
|
|
"epoch": 0.673798871814822,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004960065256555477,
|
|
"loss": 5.3037,
|
|
"mean_token_accuracy": 0.18268021196126938,
|
|
"num_tokens": 15029880.0,
|
|
"step": 8660
|
|
},
|
|
{
|
|
"entropy": 5.5966973304748535,
|
|
"epoch": 0.6741879011865396,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004960013253641695,
|
|
"loss": 5.3186,
|
|
"mean_token_accuracy": 0.171515029668808,
|
|
"num_tokens": 15038080.0,
|
|
"step": 8665
|
|
},
|
|
{
|
|
"entropy": 5.5642539978027346,
|
|
"epoch": 0.6745769305582572,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004959961217194477,
|
|
"loss": 5.3144,
|
|
"mean_token_accuracy": 0.17760654240846635,
|
|
"num_tokens": 15046779.0,
|
|
"step": 8670
|
|
},
|
|
{
|
|
"entropy": 5.587439060211182,
|
|
"epoch": 0.6749659599299748,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004959909147214615,
|
|
"loss": 5.3541,
|
|
"mean_token_accuracy": 0.17869468182325363,
|
|
"num_tokens": 15055557.0,
|
|
"step": 8675
|
|
},
|
|
{
|
|
"entropy": 5.555358219146728,
|
|
"epoch": 0.6753549893016922,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004959857043702902,
|
|
"loss": 5.2256,
|
|
"mean_token_accuracy": 0.17852253168821336,
|
|
"num_tokens": 15063054.0,
|
|
"step": 8680
|
|
},
|
|
{
|
|
"entropy": 5.546805381774902,
|
|
"epoch": 0.6757440186734098,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004959804906660124,
|
|
"loss": 5.3019,
|
|
"mean_token_accuracy": 0.17831941694021225,
|
|
"num_tokens": 15071510.0,
|
|
"step": 8685
|
|
},
|
|
{
|
|
"entropy": 5.582370567321777,
|
|
"epoch": 0.6761330480451274,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004959752736087073,
|
|
"loss": 5.3322,
|
|
"mean_token_accuracy": 0.1665417283773422,
|
|
"num_tokens": 15080524.0,
|
|
"step": 8690
|
|
},
|
|
{
|
|
"entropy": 5.637124013900757,
|
|
"epoch": 0.676522077416845,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004959700531984543,
|
|
"loss": 5.3323,
|
|
"mean_token_accuracy": 0.17430973425507545,
|
|
"num_tokens": 15089689.0,
|
|
"step": 8695
|
|
},
|
|
{
|
|
"entropy": 5.535669374465942,
|
|
"epoch": 0.6769111067885626,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004959648294353324,
|
|
"loss": 5.2417,
|
|
"mean_token_accuracy": 0.18446339964866637,
|
|
"num_tokens": 15097970.0,
|
|
"step": 8700
|
|
},
|
|
{
|
|
"entropy": 5.506096458435058,
|
|
"epoch": 0.6773001361602801,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004959596023194208,
|
|
"loss": 5.3528,
|
|
"mean_token_accuracy": 0.17490625977516175,
|
|
"num_tokens": 15107786.0,
|
|
"step": 8705
|
|
},
|
|
{
|
|
"entropy": 5.624168634414673,
|
|
"epoch": 0.6776891655319977,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000495954371850799,
|
|
"loss": 5.3163,
|
|
"mean_token_accuracy": 0.1771204650402069,
|
|
"num_tokens": 15116370.0,
|
|
"step": 8710
|
|
},
|
|
{
|
|
"entropy": 5.643984079360962,
|
|
"epoch": 0.6780781949037152,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004959491380295463,
|
|
"loss": 5.345,
|
|
"mean_token_accuracy": 0.175424787402153,
|
|
"num_tokens": 15124961.0,
|
|
"step": 8715
|
|
},
|
|
{
|
|
"entropy": 5.587209177017212,
|
|
"epoch": 0.6784672242754328,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004959439008557422,
|
|
"loss": 5.373,
|
|
"mean_token_accuracy": 0.17338978201150895,
|
|
"num_tokens": 15134230.0,
|
|
"step": 8720
|
|
},
|
|
{
|
|
"entropy": 5.556934022903443,
|
|
"epoch": 0.6788562536471504,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000495938660329466,
|
|
"loss": 5.3099,
|
|
"mean_token_accuracy": 0.1693642869591713,
|
|
"num_tokens": 15143585.0,
|
|
"step": 8725
|
|
},
|
|
{
|
|
"entropy": 5.572135066986084,
|
|
"epoch": 0.6792452830188679,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004959334164507973,
|
|
"loss": 5.2502,
|
|
"mean_token_accuracy": 0.1736395001411438,
|
|
"num_tokens": 15151834.0,
|
|
"step": 8730
|
|
},
|
|
{
|
|
"entropy": 5.513864994049072,
|
|
"epoch": 0.6796343123905855,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004959281692198155,
|
|
"loss": 5.3073,
|
|
"mean_token_accuracy": 0.17804726213216782,
|
|
"num_tokens": 15160630.0,
|
|
"step": 8735
|
|
},
|
|
{
|
|
"entropy": 5.5666755676269535,
|
|
"epoch": 0.6800233417623031,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004959229186366007,
|
|
"loss": 5.2752,
|
|
"mean_token_accuracy": 0.17743316441774368,
|
|
"num_tokens": 15168999.0,
|
|
"step": 8740
|
|
},
|
|
{
|
|
"entropy": 5.586798000335693,
|
|
"epoch": 0.6804123711340206,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000495917664701232,
|
|
"loss": 5.3409,
|
|
"mean_token_accuracy": 0.18191014379262924,
|
|
"num_tokens": 15177507.0,
|
|
"step": 8745
|
|
},
|
|
{
|
|
"entropy": 5.586767101287842,
|
|
"epoch": 0.6808014005057382,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004959124074137894,
|
|
"loss": 5.3666,
|
|
"mean_token_accuracy": 0.17173490673303604,
|
|
"num_tokens": 15186843.0,
|
|
"step": 8750
|
|
},
|
|
{
|
|
"entropy": 5.546265268325806,
|
|
"epoch": 0.6811904298774557,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004959071467743526,
|
|
"loss": 5.2778,
|
|
"mean_token_accuracy": 0.1792579934000969,
|
|
"num_tokens": 15195081.0,
|
|
"step": 8755
|
|
},
|
|
{
|
|
"entropy": 5.601288747787476,
|
|
"epoch": 0.6815794592491733,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004959018827830016,
|
|
"loss": 5.3662,
|
|
"mean_token_accuracy": 0.1787705212831497,
|
|
"num_tokens": 15203538.0,
|
|
"step": 8760
|
|
},
|
|
{
|
|
"entropy": 5.646421003341675,
|
|
"epoch": 0.6819684886208909,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000495896615439816,
|
|
"loss": 5.3994,
|
|
"mean_token_accuracy": 0.17273479998111724,
|
|
"num_tokens": 15211845.0,
|
|
"step": 8765
|
|
},
|
|
{
|
|
"entropy": 5.62197904586792,
|
|
"epoch": 0.6823575179926085,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004958913447448759,
|
|
"loss": 5.3891,
|
|
"mean_token_accuracy": 0.1769599959254265,
|
|
"num_tokens": 15220128.0,
|
|
"step": 8770
|
|
},
|
|
{
|
|
"entropy": 5.64114031791687,
|
|
"epoch": 0.682746547364326,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004958860706982613,
|
|
"loss": 5.3817,
|
|
"mean_token_accuracy": 0.17129921019077302,
|
|
"num_tokens": 15228741.0,
|
|
"step": 8775
|
|
},
|
|
{
|
|
"entropy": 5.6234687805175785,
|
|
"epoch": 0.6831355767360435,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000495880793300052,
|
|
"loss": 5.3603,
|
|
"mean_token_accuracy": 0.170152148604393,
|
|
"num_tokens": 15237674.0,
|
|
"step": 8780
|
|
},
|
|
{
|
|
"entropy": 5.567347431182862,
|
|
"epoch": 0.6835246061077611,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004958755125503284,
|
|
"loss": 5.2565,
|
|
"mean_token_accuracy": 0.18037977069616318,
|
|
"num_tokens": 15245727.0,
|
|
"step": 8785
|
|
},
|
|
{
|
|
"entropy": 5.617737531661987,
|
|
"epoch": 0.6839136354794787,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004958702284491703,
|
|
"loss": 5.3467,
|
|
"mean_token_accuracy": 0.17623167634010314,
|
|
"num_tokens": 15254511.0,
|
|
"step": 8790
|
|
},
|
|
{
|
|
"entropy": 5.614225721359253,
|
|
"epoch": 0.6843026648511963,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004958649409966581,
|
|
"loss": 5.3172,
|
|
"mean_token_accuracy": 0.17816694229841232,
|
|
"num_tokens": 15263500.0,
|
|
"step": 8795
|
|
},
|
|
{
|
|
"entropy": 5.543223428726196,
|
|
"epoch": 0.6846916942229139,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000495859650192872,
|
|
"loss": 5.3265,
|
|
"mean_token_accuracy": 0.17604704052209855,
|
|
"num_tokens": 15271960.0,
|
|
"step": 8800
|
|
},
|
|
{
|
|
"entropy": 5.645513439178467,
|
|
"epoch": 0.6850807235946313,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004958543560378922,
|
|
"loss": 5.5038,
|
|
"mean_token_accuracy": 0.16777303814888,
|
|
"num_tokens": 15280576.0,
|
|
"step": 8805
|
|
},
|
|
{
|
|
"entropy": 5.63763108253479,
|
|
"epoch": 0.6854697529663489,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004958490585317991,
|
|
"loss": 5.3633,
|
|
"mean_token_accuracy": 0.17303601950407027,
|
|
"num_tokens": 15288674.0,
|
|
"step": 8810
|
|
},
|
|
{
|
|
"entropy": 5.5421442031860355,
|
|
"epoch": 0.6858587823380665,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000495843757674673,
|
|
"loss": 5.2768,
|
|
"mean_token_accuracy": 0.18115932494401932,
|
|
"num_tokens": 15296881.0,
|
|
"step": 8815
|
|
},
|
|
{
|
|
"entropy": 5.580213451385498,
|
|
"epoch": 0.6862478117097841,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004958384534665945,
|
|
"loss": 5.3204,
|
|
"mean_token_accuracy": 0.17935770750045776,
|
|
"num_tokens": 15305379.0,
|
|
"step": 8820
|
|
},
|
|
{
|
|
"entropy": 5.6232232570648195,
|
|
"epoch": 0.6866368410815017,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004958331459076438,
|
|
"loss": 5.4179,
|
|
"mean_token_accuracy": 0.16529747992753982,
|
|
"num_tokens": 15314572.0,
|
|
"step": 8825
|
|
},
|
|
{
|
|
"entropy": 5.618761348724365,
|
|
"epoch": 0.6870258704532192,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004958278349979018,
|
|
"loss": 5.3705,
|
|
"mean_token_accuracy": 0.1721414342522621,
|
|
"num_tokens": 15323407.0,
|
|
"step": 8830
|
|
},
|
|
{
|
|
"entropy": 5.559399747848511,
|
|
"epoch": 0.6874148998249368,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004958225207374488,
|
|
"loss": 5.2481,
|
|
"mean_token_accuracy": 0.17530919909477233,
|
|
"num_tokens": 15332208.0,
|
|
"step": 8835
|
|
},
|
|
{
|
|
"entropy": 5.6014885902404785,
|
|
"epoch": 0.6878039291966543,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004958172031263655,
|
|
"loss": 5.3014,
|
|
"mean_token_accuracy": 0.175260029733181,
|
|
"num_tokens": 15340972.0,
|
|
"step": 8840
|
|
},
|
|
{
|
|
"entropy": 5.557904386520386,
|
|
"epoch": 0.6881929585683719,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004958118821647326,
|
|
"loss": 5.2855,
|
|
"mean_token_accuracy": 0.18032519072294234,
|
|
"num_tokens": 15349991.0,
|
|
"step": 8845
|
|
},
|
|
{
|
|
"entropy": 5.501622247695923,
|
|
"epoch": 0.6885819879400895,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004958065578526308,
|
|
"loss": 5.239,
|
|
"mean_token_accuracy": 0.18351080715656282,
|
|
"num_tokens": 15358194.0,
|
|
"step": 8850
|
|
},
|
|
{
|
|
"entropy": 5.605360126495361,
|
|
"epoch": 0.688971017311807,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000495801230190141,
|
|
"loss": 5.285,
|
|
"mean_token_accuracy": 0.1786123111844063,
|
|
"num_tokens": 15366954.0,
|
|
"step": 8855
|
|
},
|
|
{
|
|
"entropy": 5.641331720352173,
|
|
"epoch": 0.6893600466835246,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004957958991773441,
|
|
"loss": 5.4584,
|
|
"mean_token_accuracy": 0.16349294632673264,
|
|
"num_tokens": 15376107.0,
|
|
"step": 8860
|
|
},
|
|
{
|
|
"entropy": 5.544419240951538,
|
|
"epoch": 0.6897490760552422,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004957905648143206,
|
|
"loss": 5.3301,
|
|
"mean_token_accuracy": 0.1729828327894211,
|
|
"num_tokens": 15384517.0,
|
|
"step": 8865
|
|
},
|
|
{
|
|
"entropy": 5.690195560455322,
|
|
"epoch": 0.6901381054269597,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004957852271011519,
|
|
"loss": 5.4643,
|
|
"mean_token_accuracy": 0.16566426306962967,
|
|
"num_tokens": 15393544.0,
|
|
"step": 8870
|
|
},
|
|
{
|
|
"entropy": 5.606956481933594,
|
|
"epoch": 0.6905271347986773,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004957798860379187,
|
|
"loss": 5.3012,
|
|
"mean_token_accuracy": 0.17959974557161332,
|
|
"num_tokens": 15402165.0,
|
|
"step": 8875
|
|
},
|
|
{
|
|
"entropy": 5.5568019390106205,
|
|
"epoch": 0.6909161641703949,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004957745416247022,
|
|
"loss": 5.3473,
|
|
"mean_token_accuracy": 0.17562471181154252,
|
|
"num_tokens": 15411430.0,
|
|
"step": 8880
|
|
},
|
|
{
|
|
"entropy": 5.581215810775757,
|
|
"epoch": 0.6913051935421124,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004957691938615833,
|
|
"loss": 5.2477,
|
|
"mean_token_accuracy": 0.1813277468085289,
|
|
"num_tokens": 15420346.0,
|
|
"step": 8885
|
|
},
|
|
{
|
|
"entropy": 5.449936437606811,
|
|
"epoch": 0.69169422291383,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004957638427486434,
|
|
"loss": 5.1729,
|
|
"mean_token_accuracy": 0.1870804876089096,
|
|
"num_tokens": 15428747.0,
|
|
"step": 8890
|
|
},
|
|
{
|
|
"entropy": 5.425696229934692,
|
|
"epoch": 0.6920832522855476,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004957584882859636,
|
|
"loss": 5.198,
|
|
"mean_token_accuracy": 0.1842238187789917,
|
|
"num_tokens": 15437110.0,
|
|
"step": 8895
|
|
},
|
|
{
|
|
"entropy": 5.560818386077881,
|
|
"epoch": 0.6924722816572652,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004957531304736251,
|
|
"loss": 5.3023,
|
|
"mean_token_accuracy": 0.17740701735019684,
|
|
"num_tokens": 15446524.0,
|
|
"step": 8900
|
|
},
|
|
{
|
|
"entropy": 5.557398748397827,
|
|
"epoch": 0.6928613110289827,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004957477693117091,
|
|
"loss": 5.367,
|
|
"mean_token_accuracy": 0.17398437559604646,
|
|
"num_tokens": 15455372.0,
|
|
"step": 8905
|
|
},
|
|
{
|
|
"entropy": 5.5803440570831295,
|
|
"epoch": 0.6932503404007002,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004957424048002971,
|
|
"loss": 5.2479,
|
|
"mean_token_accuracy": 0.17678392976522445,
|
|
"num_tokens": 15463060.0,
|
|
"step": 8910
|
|
},
|
|
{
|
|
"entropy": 5.549173164367676,
|
|
"epoch": 0.6936393697724178,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004957370369394706,
|
|
"loss": 5.3541,
|
|
"mean_token_accuracy": 0.17353209257125854,
|
|
"num_tokens": 15471836.0,
|
|
"step": 8915
|
|
},
|
|
{
|
|
"entropy": 5.622178792953491,
|
|
"epoch": 0.6940283991441354,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004957316657293107,
|
|
"loss": 5.3608,
|
|
"mean_token_accuracy": 0.17495280802249907,
|
|
"num_tokens": 15479819.0,
|
|
"step": 8920
|
|
},
|
|
{
|
|
"entropy": 5.546295309066773,
|
|
"epoch": 0.694417428515853,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004957262911698992,
|
|
"loss": 5.3473,
|
|
"mean_token_accuracy": 0.1786705568432808,
|
|
"num_tokens": 15488562.0,
|
|
"step": 8925
|
|
},
|
|
{
|
|
"entropy": 5.595986986160279,
|
|
"epoch": 0.6948064578875706,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004957209132613175,
|
|
"loss": 5.4397,
|
|
"mean_token_accuracy": 0.1706948459148407,
|
|
"num_tokens": 15497822.0,
|
|
"step": 8930
|
|
},
|
|
{
|
|
"entropy": 5.676778173446655,
|
|
"epoch": 0.695195487259288,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004957155320036473,
|
|
"loss": 5.3754,
|
|
"mean_token_accuracy": 0.17063734531402588,
|
|
"num_tokens": 15506913.0,
|
|
"step": 8935
|
|
},
|
|
{
|
|
"entropy": 5.602615642547607,
|
|
"epoch": 0.6955845166310056,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004957101473969702,
|
|
"loss": 5.305,
|
|
"mean_token_accuracy": 0.1809922933578491,
|
|
"num_tokens": 15516053.0,
|
|
"step": 8940
|
|
},
|
|
{
|
|
"entropy": 5.616203308105469,
|
|
"epoch": 0.6959735460027232,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000495704759441368,
|
|
"loss": 5.3588,
|
|
"mean_token_accuracy": 0.1677024707198143,
|
|
"num_tokens": 15524174.0,
|
|
"step": 8945
|
|
},
|
|
{
|
|
"entropy": 5.590238857269287,
|
|
"epoch": 0.6963625753744408,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004956993681369221,
|
|
"loss": 5.2836,
|
|
"mean_token_accuracy": 0.17359905689954758,
|
|
"num_tokens": 15533652.0,
|
|
"step": 8950
|
|
},
|
|
{
|
|
"entropy": 5.58105239868164,
|
|
"epoch": 0.6967516047461584,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004956939734837148,
|
|
"loss": 5.2959,
|
|
"mean_token_accuracy": 0.1745977059006691,
|
|
"num_tokens": 15541644.0,
|
|
"step": 8955
|
|
},
|
|
{
|
|
"entropy": 5.489080953598022,
|
|
"epoch": 0.6971406341178759,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004956885754818277,
|
|
"loss": 5.2744,
|
|
"mean_token_accuracy": 0.18329184353351594,
|
|
"num_tokens": 15550298.0,
|
|
"step": 8960
|
|
},
|
|
{
|
|
"entropy": 5.608300447463989,
|
|
"epoch": 0.6975296634895934,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004956831741313427,
|
|
"loss": 5.3513,
|
|
"mean_token_accuracy": 0.17609672695398332,
|
|
"num_tokens": 15559388.0,
|
|
"step": 8965
|
|
},
|
|
{
|
|
"entropy": 5.49210147857666,
|
|
"epoch": 0.697918692861311,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004956777694323418,
|
|
"loss": 5.17,
|
|
"mean_token_accuracy": 0.18036870807409286,
|
|
"num_tokens": 15567543.0,
|
|
"step": 8970
|
|
},
|
|
{
|
|
"entropy": 5.508568477630615,
|
|
"epoch": 0.6983077222330286,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000495672361384907,
|
|
"loss": 5.2929,
|
|
"mean_token_accuracy": 0.18176358789205552,
|
|
"num_tokens": 15575365.0,
|
|
"step": 8975
|
|
},
|
|
{
|
|
"entropy": 5.6101562023162845,
|
|
"epoch": 0.6986967516047462,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004956669499891202,
|
|
"loss": 5.3468,
|
|
"mean_token_accuracy": 0.1734916463494301,
|
|
"num_tokens": 15584295.0,
|
|
"step": 8980
|
|
},
|
|
{
|
|
"entropy": 5.615858125686645,
|
|
"epoch": 0.6990857809764637,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004956615352450639,
|
|
"loss": 5.3354,
|
|
"mean_token_accuracy": 0.18506000936031342,
|
|
"num_tokens": 15592906.0,
|
|
"step": 8985
|
|
},
|
|
{
|
|
"entropy": 5.513598918914795,
|
|
"epoch": 0.6994748103481813,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004956561171528198,
|
|
"loss": 5.2893,
|
|
"mean_token_accuracy": 0.17286851853132248,
|
|
"num_tokens": 15601938.0,
|
|
"step": 8990
|
|
},
|
|
{
|
|
"entropy": 5.522141981124878,
|
|
"epoch": 0.6998638397198989,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004956506957124704,
|
|
"loss": 5.2907,
|
|
"mean_token_accuracy": 0.18730715066194534,
|
|
"num_tokens": 15610173.0,
|
|
"step": 8995
|
|
},
|
|
{
|
|
"entropy": 5.591469383239746,
|
|
"epoch": 0.7002528690916164,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000495645270924098,
|
|
"loss": 5.3674,
|
|
"mean_token_accuracy": 0.17109771966934204,
|
|
"num_tokens": 15618896.0,
|
|
"step": 9000
|
|
},
|
|
{
|
|
"epoch": 0.7002528690916164,
|
|
"eval_entropy": 5.334863831241964,
|
|
"eval_loss": 5.353067398071289,
|
|
"eval_mean_token_accuracy": 0.1837482512585238,
|
|
"eval_num_tokens": 15618896.0,
|
|
"eval_runtime": 21.7974,
|
|
"eval_samples_per_second": 1906.557,
|
|
"eval_steps_per_second": 238.331,
|
|
"step": 9000
|
|
},
|
|
{
|
|
"entropy": 5.517790937423706,
|
|
"epoch": 0.700641898463334,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004956398427877847,
|
|
"loss": 5.2849,
|
|
"mean_token_accuracy": 0.18094601929187776,
|
|
"num_tokens": 15627890.0,
|
|
"step": 9005
|
|
},
|
|
{
|
|
"entropy": 5.547005701065063,
|
|
"epoch": 0.7010309278350515,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000495634411303613,
|
|
"loss": 5.2258,
|
|
"mean_token_accuracy": 0.18243036270141602,
|
|
"num_tokens": 15636290.0,
|
|
"step": 9010
|
|
},
|
|
{
|
|
"entropy": 5.5310866355896,
|
|
"epoch": 0.7014199572067691,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004956289764716654,
|
|
"loss": 5.2786,
|
|
"mean_token_accuracy": 0.1766011744737625,
|
|
"num_tokens": 15644777.0,
|
|
"step": 9015
|
|
},
|
|
{
|
|
"entropy": 5.514647483825684,
|
|
"epoch": 0.7018089865784867,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004956235382920241,
|
|
"loss": 5.3011,
|
|
"mean_token_accuracy": 0.178700989484787,
|
|
"num_tokens": 15653333.0,
|
|
"step": 9020
|
|
},
|
|
{
|
|
"entropy": 5.594124031066895,
|
|
"epoch": 0.7021980159502043,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004956180967647717,
|
|
"loss": 5.3055,
|
|
"mean_token_accuracy": 0.17473521530628205,
|
|
"num_tokens": 15662140.0,
|
|
"step": 9025
|
|
},
|
|
{
|
|
"entropy": 5.62333984375,
|
|
"epoch": 0.7025870453219218,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004956126518899911,
|
|
"loss": 5.4156,
|
|
"mean_token_accuracy": 0.18038762211799622,
|
|
"num_tokens": 15671387.0,
|
|
"step": 9030
|
|
},
|
|
{
|
|
"entropy": 5.5569250106811525,
|
|
"epoch": 0.7029760746936393,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004956072036677644,
|
|
"loss": 5.3447,
|
|
"mean_token_accuracy": 0.17347424179315568,
|
|
"num_tokens": 15680884.0,
|
|
"step": 9035
|
|
},
|
|
{
|
|
"entropy": 5.601095056533813,
|
|
"epoch": 0.7033651040653569,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004956017520981746,
|
|
"loss": 5.2769,
|
|
"mean_token_accuracy": 0.17625801861286164,
|
|
"num_tokens": 15690030.0,
|
|
"step": 9040
|
|
},
|
|
{
|
|
"entropy": 5.555998992919922,
|
|
"epoch": 0.7037541334370745,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004955962971813044,
|
|
"loss": 5.3271,
|
|
"mean_token_accuracy": 0.1773602545261383,
|
|
"num_tokens": 15698260.0,
|
|
"step": 9045
|
|
},
|
|
{
|
|
"entropy": 5.484315586090088,
|
|
"epoch": 0.7041431628087921,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004955908389172364,
|
|
"loss": 5.2091,
|
|
"mean_token_accuracy": 0.1841978535056114,
|
|
"num_tokens": 15706275.0,
|
|
"step": 9050
|
|
},
|
|
{
|
|
"entropy": 5.621068859100342,
|
|
"epoch": 0.7045321921805097,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004955853773060536,
|
|
"loss": 5.4395,
|
|
"mean_token_accuracy": 0.17427613586187363,
|
|
"num_tokens": 15715086.0,
|
|
"step": 9055
|
|
},
|
|
{
|
|
"entropy": 5.54253830909729,
|
|
"epoch": 0.7049212215522271,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004955799123478388,
|
|
"loss": 5.2346,
|
|
"mean_token_accuracy": 0.18134862631559373,
|
|
"num_tokens": 15723931.0,
|
|
"step": 9060
|
|
},
|
|
{
|
|
"entropy": 5.513597917556763,
|
|
"epoch": 0.7053102509239447,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004955744440426748,
|
|
"loss": 5.4092,
|
|
"mean_token_accuracy": 0.17476319074630736,
|
|
"num_tokens": 15732905.0,
|
|
"step": 9065
|
|
},
|
|
{
|
|
"entropy": 5.584516191482544,
|
|
"epoch": 0.7056992802956623,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004955689723906448,
|
|
"loss": 5.2782,
|
|
"mean_token_accuracy": 0.1718989536166191,
|
|
"num_tokens": 15742355.0,
|
|
"step": 9070
|
|
},
|
|
{
|
|
"entropy": 5.671843004226685,
|
|
"epoch": 0.7060883096673799,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004955634973918318,
|
|
"loss": 5.348,
|
|
"mean_token_accuracy": 0.1742517203092575,
|
|
"num_tokens": 15750924.0,
|
|
"step": 9075
|
|
},
|
|
{
|
|
"entropy": 5.538636636734009,
|
|
"epoch": 0.7064773390390975,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004955580190463186,
|
|
"loss": 5.2877,
|
|
"mean_token_accuracy": 0.18234916031360626,
|
|
"num_tokens": 15759677.0,
|
|
"step": 9080
|
|
},
|
|
{
|
|
"entropy": 5.52185959815979,
|
|
"epoch": 0.7068663684108151,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004955525373541886,
|
|
"loss": 5.3023,
|
|
"mean_token_accuracy": 0.1736118823289871,
|
|
"num_tokens": 15767875.0,
|
|
"step": 9085
|
|
},
|
|
{
|
|
"entropy": 5.508476829528808,
|
|
"epoch": 0.7072553977825325,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004955470523155249,
|
|
"loss": 5.2568,
|
|
"mean_token_accuracy": 0.18183113485574723,
|
|
"num_tokens": 15776194.0,
|
|
"step": 9090
|
|
},
|
|
{
|
|
"entropy": 5.555586290359497,
|
|
"epoch": 0.7076444271542501,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004955415639304107,
|
|
"loss": 5.3339,
|
|
"mean_token_accuracy": 0.17915569245815277,
|
|
"num_tokens": 15784774.0,
|
|
"step": 9095
|
|
},
|
|
{
|
|
"entropy": 5.571475601196289,
|
|
"epoch": 0.7080334565259677,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004955360721989292,
|
|
"loss": 5.2312,
|
|
"mean_token_accuracy": 0.18535639494657516,
|
|
"num_tokens": 15793121.0,
|
|
"step": 9100
|
|
},
|
|
{
|
|
"entropy": 5.70520281791687,
|
|
"epoch": 0.7084224858976853,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004955305771211641,
|
|
"loss": 5.4456,
|
|
"mean_token_accuracy": 0.17373489290475846,
|
|
"num_tokens": 15801518.0,
|
|
"step": 9105
|
|
},
|
|
{
|
|
"entropy": 5.551429510116577,
|
|
"epoch": 0.7088115152694029,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004955250786971982,
|
|
"loss": 5.2196,
|
|
"mean_token_accuracy": 0.18320250064134597,
|
|
"num_tokens": 15809602.0,
|
|
"step": 9110
|
|
},
|
|
{
|
|
"entropy": 5.551525545120239,
|
|
"epoch": 0.7092005446411204,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004955195769271154,
|
|
"loss": 5.3978,
|
|
"mean_token_accuracy": 0.17417898178100585,
|
|
"num_tokens": 15818529.0,
|
|
"step": 9115
|
|
},
|
|
{
|
|
"entropy": 5.654647159576416,
|
|
"epoch": 0.709589574012838,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004955140718109991,
|
|
"loss": 5.2735,
|
|
"mean_token_accuracy": 0.1795146495103836,
|
|
"num_tokens": 15827176.0,
|
|
"step": 9120
|
|
},
|
|
{
|
|
"entropy": 5.622618007659912,
|
|
"epoch": 0.7099786033845555,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004955085633489326,
|
|
"loss": 5.3541,
|
|
"mean_token_accuracy": 0.1693027675151825,
|
|
"num_tokens": 15837095.0,
|
|
"step": 9125
|
|
},
|
|
{
|
|
"entropy": 5.559453916549683,
|
|
"epoch": 0.7103676327562731,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004955030515409997,
|
|
"loss": 5.3267,
|
|
"mean_token_accuracy": 0.17723278254270552,
|
|
"num_tokens": 15845285.0,
|
|
"step": 9130
|
|
},
|
|
{
|
|
"entropy": 5.569735670089722,
|
|
"epoch": 0.7107566621279907,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004954975363872838,
|
|
"loss": 5.3331,
|
|
"mean_token_accuracy": 0.18113620728254318,
|
|
"num_tokens": 15853468.0,
|
|
"step": 9135
|
|
},
|
|
{
|
|
"entropy": 5.589026069641113,
|
|
"epoch": 0.7111456914997082,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004954920178878689,
|
|
"loss": 5.2715,
|
|
"mean_token_accuracy": 0.1886820301413536,
|
|
"num_tokens": 15861699.0,
|
|
"step": 9140
|
|
},
|
|
{
|
|
"entropy": 5.571455717086792,
|
|
"epoch": 0.7115347208714258,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004954864960428385,
|
|
"loss": 5.3525,
|
|
"mean_token_accuracy": 0.1744161754846573,
|
|
"num_tokens": 15870401.0,
|
|
"step": 9145
|
|
},
|
|
{
|
|
"entropy": 5.542234897613525,
|
|
"epoch": 0.7119237502431434,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004954809708522765,
|
|
"loss": 5.1695,
|
|
"mean_token_accuracy": 0.19075365066528321,
|
|
"num_tokens": 15878214.0,
|
|
"step": 9150
|
|
},
|
|
{
|
|
"entropy": 5.565649938583374,
|
|
"epoch": 0.712312779614861,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004954754423162667,
|
|
"loss": 5.3442,
|
|
"mean_token_accuracy": 0.17487907856702806,
|
|
"num_tokens": 15886581.0,
|
|
"step": 9155
|
|
},
|
|
{
|
|
"entropy": 5.639461469650269,
|
|
"epoch": 0.7127018089865785,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.000495469910434893,
|
|
"loss": 5.4492,
|
|
"mean_token_accuracy": 0.1683066964149475,
|
|
"num_tokens": 15895748.0,
|
|
"step": 9160
|
|
},
|
|
{
|
|
"entropy": 5.583930349349975,
|
|
"epoch": 0.713090838358296,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004954643752082392,
|
|
"loss": 5.3052,
|
|
"mean_token_accuracy": 0.1784547373652458,
|
|
"num_tokens": 15905030.0,
|
|
"step": 9165
|
|
},
|
|
{
|
|
"entropy": 5.546288728713989,
|
|
"epoch": 0.7134798677300136,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004954588366363896,
|
|
"loss": 5.2954,
|
|
"mean_token_accuracy": 0.17823144495487214,
|
|
"num_tokens": 15913430.0,
|
|
"step": 9170
|
|
},
|
|
{
|
|
"entropy": 5.564022445678711,
|
|
"epoch": 0.7138688971017312,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004954532947194279,
|
|
"loss": 5.1921,
|
|
"mean_token_accuracy": 0.18421580493450165,
|
|
"num_tokens": 15921432.0,
|
|
"step": 9175
|
|
},
|
|
{
|
|
"entropy": 5.593471193313599,
|
|
"epoch": 0.7142579264734488,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004954477494574384,
|
|
"loss": 5.2702,
|
|
"mean_token_accuracy": 0.18055691719055175,
|
|
"num_tokens": 15930159.0,
|
|
"step": 9180
|
|
},
|
|
{
|
|
"entropy": 5.570560455322266,
|
|
"epoch": 0.7146469558451664,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004954422008505052,
|
|
"loss": 5.3586,
|
|
"mean_token_accuracy": 0.17044297009706497,
|
|
"num_tokens": 15939911.0,
|
|
"step": 9185
|
|
},
|
|
{
|
|
"entropy": 5.592472934722901,
|
|
"epoch": 0.7150359852168838,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004954366488987125,
|
|
"loss": 5.2855,
|
|
"mean_token_accuracy": 0.17620354592800141,
|
|
"num_tokens": 15948586.0,
|
|
"step": 9190
|
|
},
|
|
{
|
|
"entropy": 5.444886636734009,
|
|
"epoch": 0.7154250145886014,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004954310936021444,
|
|
"loss": 5.1423,
|
|
"mean_token_accuracy": 0.18131237626075744,
|
|
"num_tokens": 15956818.0,
|
|
"step": 9195
|
|
},
|
|
{
|
|
"entropy": 5.540569067001343,
|
|
"epoch": 0.715814043960319,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004954255349608853,
|
|
"loss": 5.3682,
|
|
"mean_token_accuracy": 0.16918419450521469,
|
|
"num_tokens": 15966027.0,
|
|
"step": 9200
|
|
},
|
|
{
|
|
"entropy": 5.643780088424682,
|
|
"epoch": 0.7162030733320366,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004954199729750198,
|
|
"loss": 5.3955,
|
|
"mean_token_accuracy": 0.17508964836597443,
|
|
"num_tokens": 15975186.0,
|
|
"step": 9205
|
|
},
|
|
{
|
|
"entropy": 5.526380300521851,
|
|
"epoch": 0.7165921027037542,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004954144076446318,
|
|
"loss": 5.2527,
|
|
"mean_token_accuracy": 0.1784766599535942,
|
|
"num_tokens": 15983924.0,
|
|
"step": 9210
|
|
},
|
|
{
|
|
"entropy": 5.552653026580811,
|
|
"epoch": 0.7169811320754716,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004954088389698061,
|
|
"loss": 5.2999,
|
|
"mean_token_accuracy": 0.1809309482574463,
|
|
"num_tokens": 15992906.0,
|
|
"step": 9215
|
|
},
|
|
{
|
|
"entropy": 5.587754011154175,
|
|
"epoch": 0.7173701614471892,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000495403266950627,
|
|
"loss": 5.3018,
|
|
"mean_token_accuracy": 0.17490899711847305,
|
|
"num_tokens": 16001378.0,
|
|
"step": 9220
|
|
},
|
|
{
|
|
"entropy": 5.538111400604248,
|
|
"epoch": 0.7177591908189068,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004953976915871792,
|
|
"loss": 5.3068,
|
|
"mean_token_accuracy": 0.17638416737318038,
|
|
"num_tokens": 16010704.0,
|
|
"step": 9225
|
|
},
|
|
{
|
|
"entropy": 5.489271974563598,
|
|
"epoch": 0.7181482201906244,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004953921128795472,
|
|
"loss": 5.2907,
|
|
"mean_token_accuracy": 0.18120024502277374,
|
|
"num_tokens": 16018936.0,
|
|
"step": 9230
|
|
},
|
|
{
|
|
"entropy": 5.587630128860473,
|
|
"epoch": 0.718537249562342,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004953865308278156,
|
|
"loss": 5.19,
|
|
"mean_token_accuracy": 0.17775632292032242,
|
|
"num_tokens": 16027295.0,
|
|
"step": 9235
|
|
},
|
|
{
|
|
"entropy": 5.526306295394898,
|
|
"epoch": 0.7189262789340595,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004953809454320693,
|
|
"loss": 5.2192,
|
|
"mean_token_accuracy": 0.1811777248978615,
|
|
"num_tokens": 16036493.0,
|
|
"step": 9240
|
|
},
|
|
{
|
|
"entropy": 5.5192351818084715,
|
|
"epoch": 0.7193153083057771,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004953753566923929,
|
|
"loss": 5.3434,
|
|
"mean_token_accuracy": 0.1811526209115982,
|
|
"num_tokens": 16045406.0,
|
|
"step": 9245
|
|
},
|
|
{
|
|
"entropy": 5.559315776824951,
|
|
"epoch": 0.7197043376774946,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004953697646088712,
|
|
"loss": 5.3211,
|
|
"mean_token_accuracy": 0.17802902311086655,
|
|
"num_tokens": 16054126.0,
|
|
"step": 9250
|
|
},
|
|
{
|
|
"entropy": 5.60638656616211,
|
|
"epoch": 0.7200933670492122,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004953641691815891,
|
|
"loss": 5.3362,
|
|
"mean_token_accuracy": 0.170424747467041,
|
|
"num_tokens": 16063921.0,
|
|
"step": 9255
|
|
},
|
|
{
|
|
"entropy": 5.560848045349121,
|
|
"epoch": 0.7204823964209298,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004953585704106315,
|
|
"loss": 5.3469,
|
|
"mean_token_accuracy": 0.17578511089086532,
|
|
"num_tokens": 16072160.0,
|
|
"step": 9260
|
|
},
|
|
{
|
|
"entropy": 5.616014766693115,
|
|
"epoch": 0.7208714257926473,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004953529682960832,
|
|
"loss": 5.2744,
|
|
"mean_token_accuracy": 0.17761323899030684,
|
|
"num_tokens": 16080794.0,
|
|
"step": 9265
|
|
},
|
|
{
|
|
"entropy": 5.540022087097168,
|
|
"epoch": 0.7212604551643649,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004953473628380295,
|
|
"loss": 5.3094,
|
|
"mean_token_accuracy": 0.18073517382144927,
|
|
"num_tokens": 16089615.0,
|
|
"step": 9270
|
|
},
|
|
{
|
|
"entropy": 5.527288341522217,
|
|
"epoch": 0.7216494845360825,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004953417540365553,
|
|
"loss": 5.2096,
|
|
"mean_token_accuracy": 0.18059678077697755,
|
|
"num_tokens": 16098363.0,
|
|
"step": 9275
|
|
},
|
|
{
|
|
"entropy": 5.5765989303588865,
|
|
"epoch": 0.7220385139078,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004953361418917455,
|
|
"loss": 5.3158,
|
|
"mean_token_accuracy": 0.17089972347021104,
|
|
"num_tokens": 16106837.0,
|
|
"step": 9280
|
|
},
|
|
{
|
|
"entropy": 5.591169786453247,
|
|
"epoch": 0.7224275432795176,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004953305264036856,
|
|
"loss": 5.2657,
|
|
"mean_token_accuracy": 0.17635613232851027,
|
|
"num_tokens": 16114923.0,
|
|
"step": 9285
|
|
},
|
|
{
|
|
"entropy": 5.5530914783477785,
|
|
"epoch": 0.7228165726512352,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004953249075724607,
|
|
"loss": 5.306,
|
|
"mean_token_accuracy": 0.17418773621320724,
|
|
"num_tokens": 16123698.0,
|
|
"step": 9290
|
|
},
|
|
{
|
|
"entropy": 5.58996548652649,
|
|
"epoch": 0.7232056020229527,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004953192853981559,
|
|
"loss": 5.2645,
|
|
"mean_token_accuracy": 0.17848737239837648,
|
|
"num_tokens": 16132361.0,
|
|
"step": 9295
|
|
},
|
|
{
|
|
"entropy": 5.63656325340271,
|
|
"epoch": 0.7235946313946703,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004953136598808566,
|
|
"loss": 5.3517,
|
|
"mean_token_accuracy": 0.17827641367912292,
|
|
"num_tokens": 16141554.0,
|
|
"step": 9300
|
|
},
|
|
{
|
|
"entropy": 5.569615173339844,
|
|
"epoch": 0.7239836607663879,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004953080310206481,
|
|
"loss": 5.2606,
|
|
"mean_token_accuracy": 0.17871276885271073,
|
|
"num_tokens": 16150206.0,
|
|
"step": 9305
|
|
},
|
|
{
|
|
"entropy": 5.556385135650634,
|
|
"epoch": 0.7243726901381055,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004953023988176162,
|
|
"loss": 5.383,
|
|
"mean_token_accuracy": 0.17167091518640518,
|
|
"num_tokens": 16158995.0,
|
|
"step": 9310
|
|
},
|
|
{
|
|
"entropy": 5.579621839523315,
|
|
"epoch": 0.724761719509823,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004952967632718458,
|
|
"loss": 5.3611,
|
|
"mean_token_accuracy": 0.1680089145898819,
|
|
"num_tokens": 16167809.0,
|
|
"step": 9315
|
|
},
|
|
{
|
|
"entropy": 5.725109624862671,
|
|
"epoch": 0.7251507488815405,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004952911243834227,
|
|
"loss": 5.4358,
|
|
"mean_token_accuracy": 0.1652451917529106,
|
|
"num_tokens": 16176257.0,
|
|
"step": 9320
|
|
},
|
|
{
|
|
"entropy": 5.625408172607422,
|
|
"epoch": 0.7255397782532581,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004952854821524324,
|
|
"loss": 5.3858,
|
|
"mean_token_accuracy": 0.17146064341068268,
|
|
"num_tokens": 16185597.0,
|
|
"step": 9325
|
|
},
|
|
{
|
|
"entropy": 5.643079853057861,
|
|
"epoch": 0.7259288076249757,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004952798365789606,
|
|
"loss": 5.4106,
|
|
"mean_token_accuracy": 0.17838159650564195,
|
|
"num_tokens": 16194591.0,
|
|
"step": 9330
|
|
},
|
|
{
|
|
"entropy": 5.683854055404663,
|
|
"epoch": 0.7263178369966933,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004952741876630928,
|
|
"loss": 5.3713,
|
|
"mean_token_accuracy": 0.1727147802710533,
|
|
"num_tokens": 16203073.0,
|
|
"step": 9335
|
|
},
|
|
{
|
|
"entropy": 5.543218660354614,
|
|
"epoch": 0.7267068663684109,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004952685354049148,
|
|
"loss": 5.3406,
|
|
"mean_token_accuracy": 0.17130525261163712,
|
|
"num_tokens": 16211208.0,
|
|
"step": 9340
|
|
},
|
|
{
|
|
"entropy": 5.565604162216187,
|
|
"epoch": 0.7270958957401283,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004952628798045124,
|
|
"loss": 5.2862,
|
|
"mean_token_accuracy": 0.18018544763326644,
|
|
"num_tokens": 16219687.0,
|
|
"step": 9345
|
|
},
|
|
{
|
|
"entropy": 5.624908447265625,
|
|
"epoch": 0.7274849251118459,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004952572208619714,
|
|
"loss": 5.376,
|
|
"mean_token_accuracy": 0.17842526137828826,
|
|
"num_tokens": 16228214.0,
|
|
"step": 9350
|
|
},
|
|
{
|
|
"entropy": 5.600245380401612,
|
|
"epoch": 0.7278739544835635,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004952515585773778,
|
|
"loss": 5.4571,
|
|
"mean_token_accuracy": 0.16715698540210724,
|
|
"num_tokens": 16237765.0,
|
|
"step": 9355
|
|
},
|
|
{
|
|
"entropy": 5.585886287689209,
|
|
"epoch": 0.7282629838552811,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004952458929508171,
|
|
"loss": 5.3104,
|
|
"mean_token_accuracy": 0.18905370384454728,
|
|
"num_tokens": 16245339.0,
|
|
"step": 9360
|
|
},
|
|
{
|
|
"entropy": 5.537863397598267,
|
|
"epoch": 0.7286520132269987,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004952402239823757,
|
|
"loss": 5.3218,
|
|
"mean_token_accuracy": 0.17315308898687362,
|
|
"num_tokens": 16253966.0,
|
|
"step": 9365
|
|
},
|
|
{
|
|
"entropy": 5.545432424545288,
|
|
"epoch": 0.7290410425987162,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004952345516721393,
|
|
"loss": 5.3002,
|
|
"mean_token_accuracy": 0.17695194780826567,
|
|
"num_tokens": 16262859.0,
|
|
"step": 9370
|
|
},
|
|
{
|
|
"entropy": 5.568144798278809,
|
|
"epoch": 0.7294300719704337,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004952288760201942,
|
|
"loss": 5.3316,
|
|
"mean_token_accuracy": 0.17465603053569795,
|
|
"num_tokens": 16271646.0,
|
|
"step": 9375
|
|
},
|
|
{
|
|
"entropy": 5.563733291625977,
|
|
"epoch": 0.7298191013421513,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004952231970266265,
|
|
"loss": 5.3223,
|
|
"mean_token_accuracy": 0.17299434542655945,
|
|
"num_tokens": 16281058.0,
|
|
"step": 9380
|
|
},
|
|
{
|
|
"entropy": 5.645624017715454,
|
|
"epoch": 0.7302081307138689,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004952175146915223,
|
|
"loss": 5.2648,
|
|
"mean_token_accuracy": 0.18165217638015746,
|
|
"num_tokens": 16289039.0,
|
|
"step": 9385
|
|
},
|
|
{
|
|
"entropy": 5.457538843154907,
|
|
"epoch": 0.7305971600855865,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004952118290149679,
|
|
"loss": 5.1743,
|
|
"mean_token_accuracy": 0.18510949462652207,
|
|
"num_tokens": 16297373.0,
|
|
"step": 9390
|
|
},
|
|
{
|
|
"entropy": 5.541280889511109,
|
|
"epoch": 0.730986189457304,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004952061399970492,
|
|
"loss": 5.3314,
|
|
"mean_token_accuracy": 0.17273576706647872,
|
|
"num_tokens": 16306066.0,
|
|
"step": 9395
|
|
},
|
|
{
|
|
"entropy": 5.610443115234375,
|
|
"epoch": 0.7313752188290216,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000495200447637853,
|
|
"loss": 5.3794,
|
|
"mean_token_accuracy": 0.17505713552236557,
|
|
"num_tokens": 16315282.0,
|
|
"step": 9400
|
|
},
|
|
{
|
|
"entropy": 5.7012941360473635,
|
|
"epoch": 0.7317642482007392,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004951947519374655,
|
|
"loss": 5.4693,
|
|
"mean_token_accuracy": 0.17104714810848237,
|
|
"num_tokens": 16324830.0,
|
|
"step": 9405
|
|
},
|
|
{
|
|
"entropy": 5.596612167358399,
|
|
"epoch": 0.7321532775724567,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004951890528959731,
|
|
"loss": 5.3319,
|
|
"mean_token_accuracy": 0.17324616760015488,
|
|
"num_tokens": 16332990.0,
|
|
"step": 9410
|
|
},
|
|
{
|
|
"entropy": 5.536366128921509,
|
|
"epoch": 0.7325423069441743,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004951833505134623,
|
|
"loss": 5.2832,
|
|
"mean_token_accuracy": 0.17535036206245422,
|
|
"num_tokens": 16342115.0,
|
|
"step": 9415
|
|
},
|
|
{
|
|
"entropy": 5.560042858123779,
|
|
"epoch": 0.7329313363158918,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004951776447900196,
|
|
"loss": 5.2877,
|
|
"mean_token_accuracy": 0.17931381464004517,
|
|
"num_tokens": 16350329.0,
|
|
"step": 9420
|
|
},
|
|
{
|
|
"entropy": 5.573030281066894,
|
|
"epoch": 0.7333203656876094,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004951719357257317,
|
|
"loss": 5.3897,
|
|
"mean_token_accuracy": 0.17676016688346863,
|
|
"num_tokens": 16358890.0,
|
|
"step": 9425
|
|
},
|
|
{
|
|
"entropy": 5.683777379989624,
|
|
"epoch": 0.733709395059327,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000495166223320685,
|
|
"loss": 5.4258,
|
|
"mean_token_accuracy": 0.16870919317007066,
|
|
"num_tokens": 16367338.0,
|
|
"step": 9430
|
|
},
|
|
{
|
|
"entropy": 5.647769021987915,
|
|
"epoch": 0.7340984244310446,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004951605075749662,
|
|
"loss": 5.3249,
|
|
"mean_token_accuracy": 0.1818474978208542,
|
|
"num_tokens": 16375472.0,
|
|
"step": 9435
|
|
},
|
|
{
|
|
"entropy": 5.610141563415527,
|
|
"epoch": 0.7344874538027621,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004951547884886623,
|
|
"loss": 5.3214,
|
|
"mean_token_accuracy": 0.1809833511710167,
|
|
"num_tokens": 16384212.0,
|
|
"step": 9440
|
|
},
|
|
{
|
|
"entropy": 5.5480530738830565,
|
|
"epoch": 0.7348764831744796,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004951490660618598,
|
|
"loss": 5.2098,
|
|
"mean_token_accuracy": 0.18420309871435164,
|
|
"num_tokens": 16393447.0,
|
|
"step": 9445
|
|
},
|
|
{
|
|
"entropy": 5.487442255020142,
|
|
"epoch": 0.7352655125461972,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004951433402946457,
|
|
"loss": 5.2002,
|
|
"mean_token_accuracy": 0.18515112549066542,
|
|
"num_tokens": 16401876.0,
|
|
"step": 9450
|
|
},
|
|
{
|
|
"entropy": 5.539979934692383,
|
|
"epoch": 0.7356545419179148,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004951376111871068,
|
|
"loss": 5.3543,
|
|
"mean_token_accuracy": 0.17673734128475188,
|
|
"num_tokens": 16411020.0,
|
|
"step": 9455
|
|
},
|
|
{
|
|
"entropy": 5.639129781723023,
|
|
"epoch": 0.7360435712896324,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004951318787393299,
|
|
"loss": 5.3708,
|
|
"mean_token_accuracy": 0.17495454996824264,
|
|
"num_tokens": 16420492.0,
|
|
"step": 9460
|
|
},
|
|
{
|
|
"entropy": 5.582475185394287,
|
|
"epoch": 0.73643260066135,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004951261429514023,
|
|
"loss": 5.2833,
|
|
"mean_token_accuracy": 0.18109755516052245,
|
|
"num_tokens": 16429277.0,
|
|
"step": 9465
|
|
},
|
|
{
|
|
"entropy": 5.522632169723511,
|
|
"epoch": 0.7368216300330674,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004951204038234106,
|
|
"loss": 5.3087,
|
|
"mean_token_accuracy": 0.17764748632907867,
|
|
"num_tokens": 16438008.0,
|
|
"step": 9470
|
|
},
|
|
{
|
|
"entropy": 5.581943416595459,
|
|
"epoch": 0.737210659404785,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004951146613554424,
|
|
"loss": 5.3153,
|
|
"mean_token_accuracy": 0.17503933608531952,
|
|
"num_tokens": 16446791.0,
|
|
"step": 9475
|
|
},
|
|
{
|
|
"entropy": 5.578238868713379,
|
|
"epoch": 0.7375996887765026,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004951089155475843,
|
|
"loss": 5.3507,
|
|
"mean_token_accuracy": 0.17409266233444215,
|
|
"num_tokens": 16455277.0,
|
|
"step": 9480
|
|
},
|
|
{
|
|
"entropy": 5.538052940368653,
|
|
"epoch": 0.7379887181482202,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000495103166399924,
|
|
"loss": 5.2642,
|
|
"mean_token_accuracy": 0.17929996103048323,
|
|
"num_tokens": 16463310.0,
|
|
"step": 9485
|
|
},
|
|
{
|
|
"entropy": 5.547290706634522,
|
|
"epoch": 0.7383777475199378,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004950974139125484,
|
|
"loss": 5.313,
|
|
"mean_token_accuracy": 0.17705847173929215,
|
|
"num_tokens": 16472421.0,
|
|
"step": 9490
|
|
},
|
|
{
|
|
"entropy": 5.575832319259644,
|
|
"epoch": 0.7387667768916554,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004950916580855448,
|
|
"loss": 5.3739,
|
|
"mean_token_accuracy": 0.17194296568632125,
|
|
"num_tokens": 16481814.0,
|
|
"step": 9495
|
|
},
|
|
{
|
|
"entropy": 5.583070898056031,
|
|
"epoch": 0.7391558062633728,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004950858989190007,
|
|
"loss": 5.328,
|
|
"mean_token_accuracy": 0.17030642926692963,
|
|
"num_tokens": 16490902.0,
|
|
"step": 9500
|
|
},
|
|
{
|
|
"entropy": 5.6068895816802975,
|
|
"epoch": 0.7395448356350904,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004950801364130032,
|
|
"loss": 5.2863,
|
|
"mean_token_accuracy": 0.17758143097162246,
|
|
"num_tokens": 16499418.0,
|
|
"step": 9505
|
|
},
|
|
{
|
|
"entropy": 5.531932544708252,
|
|
"epoch": 0.739933865006808,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004950743705676401,
|
|
"loss": 5.2203,
|
|
"mean_token_accuracy": 0.18528714179992675,
|
|
"num_tokens": 16508578.0,
|
|
"step": 9510
|
|
},
|
|
{
|
|
"entropy": 5.513550710678101,
|
|
"epoch": 0.7403228943785256,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004950686013829987,
|
|
"loss": 5.284,
|
|
"mean_token_accuracy": 0.17520827203989028,
|
|
"num_tokens": 16517356.0,
|
|
"step": 9515
|
|
},
|
|
{
|
|
"entropy": 5.5130551815032955,
|
|
"epoch": 0.7407119237502432,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004950628288591665,
|
|
"loss": 5.2898,
|
|
"mean_token_accuracy": 0.17843545973300934,
|
|
"num_tokens": 16525834.0,
|
|
"step": 9520
|
|
},
|
|
{
|
|
"entropy": 5.577107238769531,
|
|
"epoch": 0.7411009531219607,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004950570529962311,
|
|
"loss": 5.2891,
|
|
"mean_token_accuracy": 0.1758483812212944,
|
|
"num_tokens": 16534513.0,
|
|
"step": 9525
|
|
},
|
|
{
|
|
"entropy": 5.60887508392334,
|
|
"epoch": 0.7414899824936783,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004950512737942803,
|
|
"loss": 5.2901,
|
|
"mean_token_accuracy": 0.1797830954194069,
|
|
"num_tokens": 16543326.0,
|
|
"step": 9530
|
|
},
|
|
{
|
|
"entropy": 5.548036289215088,
|
|
"epoch": 0.7418790118653958,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004950454912534015,
|
|
"loss": 5.3027,
|
|
"mean_token_accuracy": 0.17792366594076156,
|
|
"num_tokens": 16551589.0,
|
|
"step": 9535
|
|
},
|
|
{
|
|
"entropy": 5.582470273971557,
|
|
"epoch": 0.7422680412371134,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004950397053736827,
|
|
"loss": 5.2813,
|
|
"mean_token_accuracy": 0.1794194683432579,
|
|
"num_tokens": 16560261.0,
|
|
"step": 9540
|
|
},
|
|
{
|
|
"entropy": 5.607489442825317,
|
|
"epoch": 0.742657070608831,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004950339161552117,
|
|
"loss": 5.269,
|
|
"mean_token_accuracy": 0.1809129610657692,
|
|
"num_tokens": 16568645.0,
|
|
"step": 9545
|
|
},
|
|
{
|
|
"entropy": 5.538193416595459,
|
|
"epoch": 0.7430460999805485,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004950281235980761,
|
|
"loss": 5.272,
|
|
"mean_token_accuracy": 0.18645498007535935,
|
|
"num_tokens": 16577206.0,
|
|
"step": 9550
|
|
},
|
|
{
|
|
"entropy": 5.541358613967896,
|
|
"epoch": 0.7434351293522661,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000495022327702364,
|
|
"loss": 5.2744,
|
|
"mean_token_accuracy": 0.17665404379367827,
|
|
"num_tokens": 16585011.0,
|
|
"step": 9555
|
|
},
|
|
{
|
|
"entropy": 5.591173839569092,
|
|
"epoch": 0.7438241587239837,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004950165284681631,
|
|
"loss": 5.3375,
|
|
"mean_token_accuracy": 0.17531904727220535,
|
|
"num_tokens": 16593574.0,
|
|
"step": 9560
|
|
},
|
|
{
|
|
"entropy": 5.570319128036499,
|
|
"epoch": 0.7442131880957013,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004950107258955618,
|
|
"loss": 5.2482,
|
|
"mean_token_accuracy": 0.18688714802265166,
|
|
"num_tokens": 16603023.0,
|
|
"step": 9565
|
|
},
|
|
{
|
|
"entropy": 5.637556695938111,
|
|
"epoch": 0.7446022174674188,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004950049199846479,
|
|
"loss": 5.3453,
|
|
"mean_token_accuracy": 0.17867223173379898,
|
|
"num_tokens": 16611963.0,
|
|
"step": 9570
|
|
},
|
|
{
|
|
"entropy": 5.639278364181519,
|
|
"epoch": 0.7449912468391363,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004949991107355095,
|
|
"loss": 5.2876,
|
|
"mean_token_accuracy": 0.18264320790767669,
|
|
"num_tokens": 16619942.0,
|
|
"step": 9575
|
|
},
|
|
{
|
|
"entropy": 5.478429794311523,
|
|
"epoch": 0.7453802762108539,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004949932981482347,
|
|
"loss": 5.187,
|
|
"mean_token_accuracy": 0.1897456482052803,
|
|
"num_tokens": 16628261.0,
|
|
"step": 9580
|
|
},
|
|
{
|
|
"entropy": 5.585916566848755,
|
|
"epoch": 0.7457693055825715,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004949874822229118,
|
|
"loss": 5.3198,
|
|
"mean_token_accuracy": 0.17921436578035355,
|
|
"num_tokens": 16637290.0,
|
|
"step": 9585
|
|
},
|
|
{
|
|
"entropy": 5.578394842147827,
|
|
"epoch": 0.7461583349542891,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004949816629596288,
|
|
"loss": 5.3102,
|
|
"mean_token_accuracy": 0.17700878232717515,
|
|
"num_tokens": 16646147.0,
|
|
"step": 9590
|
|
},
|
|
{
|
|
"entropy": 5.5497089385986325,
|
|
"epoch": 0.7465473643260067,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004949758403584746,
|
|
"loss": 5.3844,
|
|
"mean_token_accuracy": 0.16975755989551544,
|
|
"num_tokens": 16655299.0,
|
|
"step": 9595
|
|
},
|
|
{
|
|
"entropy": 5.574647665023804,
|
|
"epoch": 0.7469363936977241,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004949700144195368,
|
|
"loss": 5.2742,
|
|
"mean_token_accuracy": 0.18338656425476074,
|
|
"num_tokens": 16664091.0,
|
|
"step": 9600
|
|
},
|
|
{
|
|
"entropy": 5.692896175384521,
|
|
"epoch": 0.7473254230694417,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004949641851429043,
|
|
"loss": 5.3384,
|
|
"mean_token_accuracy": 0.17343031615018845,
|
|
"num_tokens": 16672665.0,
|
|
"step": 9605
|
|
},
|
|
{
|
|
"entropy": 5.559443998336792,
|
|
"epoch": 0.7477144524411593,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004949583525286654,
|
|
"loss": 5.2692,
|
|
"mean_token_accuracy": 0.18353851437568663,
|
|
"num_tokens": 16680735.0,
|
|
"step": 9610
|
|
},
|
|
{
|
|
"entropy": 5.589480638504028,
|
|
"epoch": 0.7481034818128769,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004949525165769085,
|
|
"loss": 5.3597,
|
|
"mean_token_accuracy": 0.1735190451145172,
|
|
"num_tokens": 16689560.0,
|
|
"step": 9615
|
|
},
|
|
{
|
|
"entropy": 5.60034704208374,
|
|
"epoch": 0.7484925111845945,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004949466772877224,
|
|
"loss": 5.3202,
|
|
"mean_token_accuracy": 0.17463106364011766,
|
|
"num_tokens": 16698953.0,
|
|
"step": 9620
|
|
},
|
|
{
|
|
"entropy": 5.597173357009888,
|
|
"epoch": 0.748881540556312,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004949408346611955,
|
|
"loss": 5.3247,
|
|
"mean_token_accuracy": 0.17516023367643357,
|
|
"num_tokens": 16707601.0,
|
|
"step": 9625
|
|
},
|
|
{
|
|
"entropy": 5.54741678237915,
|
|
"epoch": 0.7492705699280295,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004949349886974165,
|
|
"loss": 5.3319,
|
|
"mean_token_accuracy": 0.1804911673069,
|
|
"num_tokens": 16716660.0,
|
|
"step": 9630
|
|
},
|
|
{
|
|
"entropy": 5.554853725433349,
|
|
"epoch": 0.7496595992997471,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004949291393964741,
|
|
"loss": 5.2625,
|
|
"mean_token_accuracy": 0.1796331986784935,
|
|
"num_tokens": 16725274.0,
|
|
"step": 9635
|
|
},
|
|
{
|
|
"entropy": 5.558338928222656,
|
|
"epoch": 0.7500486286714647,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000494923286758457,
|
|
"loss": 5.2656,
|
|
"mean_token_accuracy": 0.17535172253847123,
|
|
"num_tokens": 16733301.0,
|
|
"step": 9640
|
|
},
|
|
{
|
|
"entropy": 5.577684450149536,
|
|
"epoch": 0.7504376580431823,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004949174307834541,
|
|
"loss": 5.2874,
|
|
"mean_token_accuracy": 0.17794075906276702,
|
|
"num_tokens": 16742072.0,
|
|
"step": 9645
|
|
},
|
|
{
|
|
"entropy": 5.61627197265625,
|
|
"epoch": 0.7508266874148998,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004949115714715543,
|
|
"loss": 5.2957,
|
|
"mean_token_accuracy": 0.17773596048355103,
|
|
"num_tokens": 16751497.0,
|
|
"step": 9650
|
|
},
|
|
{
|
|
"entropy": 5.542064380645752,
|
|
"epoch": 0.7512157167866174,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004949057088228465,
|
|
"loss": 5.2547,
|
|
"mean_token_accuracy": 0.183311328291893,
|
|
"num_tokens": 16760518.0,
|
|
"step": 9655
|
|
},
|
|
{
|
|
"entropy": 5.613554763793945,
|
|
"epoch": 0.751604746158335,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004948998428374194,
|
|
"loss": 5.3787,
|
|
"mean_token_accuracy": 0.17053319960832597,
|
|
"num_tokens": 16768689.0,
|
|
"step": 9660
|
|
},
|
|
{
|
|
"entropy": 5.582167243957519,
|
|
"epoch": 0.7519937755300525,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004948939735153622,
|
|
"loss": 5.2153,
|
|
"mean_token_accuracy": 0.19048200994729997,
|
|
"num_tokens": 16777047.0,
|
|
"step": 9665
|
|
},
|
|
{
|
|
"entropy": 5.49366455078125,
|
|
"epoch": 0.7523828049017701,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004948881008567641,
|
|
"loss": 5.1831,
|
|
"mean_token_accuracy": 0.1859971195459366,
|
|
"num_tokens": 16785402.0,
|
|
"step": 9670
|
|
},
|
|
{
|
|
"entropy": 5.553354263305664,
|
|
"epoch": 0.7527718342734876,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004948822248617139,
|
|
"loss": 5.2923,
|
|
"mean_token_accuracy": 0.17727821469306945,
|
|
"num_tokens": 16794687.0,
|
|
"step": 9675
|
|
},
|
|
{
|
|
"entropy": 5.621946334838867,
|
|
"epoch": 0.7531608636452052,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000494876345530301,
|
|
"loss": 5.323,
|
|
"mean_token_accuracy": 0.17618732303380966,
|
|
"num_tokens": 16803762.0,
|
|
"step": 9680
|
|
},
|
|
{
|
|
"entropy": 5.583499431610107,
|
|
"epoch": 0.7535498930169228,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004948704628626145,
|
|
"loss": 5.3521,
|
|
"mean_token_accuracy": 0.171107779443264,
|
|
"num_tokens": 16812872.0,
|
|
"step": 9685
|
|
},
|
|
{
|
|
"entropy": 5.652652168273926,
|
|
"epoch": 0.7539389223886404,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004948645768587437,
|
|
"loss": 5.3799,
|
|
"mean_token_accuracy": 0.16893844902515412,
|
|
"num_tokens": 16821270.0,
|
|
"step": 9690
|
|
},
|
|
{
|
|
"entropy": 5.560877323150635,
|
|
"epoch": 0.7543279517603579,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004948586875187778,
|
|
"loss": 5.2783,
|
|
"mean_token_accuracy": 0.181769460439682,
|
|
"num_tokens": 16829508.0,
|
|
"step": 9695
|
|
},
|
|
{
|
|
"entropy": 5.560929203033448,
|
|
"epoch": 0.7547169811320755,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004948527948428064,
|
|
"loss": 5.2748,
|
|
"mean_token_accuracy": 0.17611613422632216,
|
|
"num_tokens": 16838327.0,
|
|
"step": 9700
|
|
},
|
|
{
|
|
"entropy": 5.599258136749268,
|
|
"epoch": 0.755106010503793,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004948468988309187,
|
|
"loss": 5.2464,
|
|
"mean_token_accuracy": 0.18367060720920564,
|
|
"num_tokens": 16846530.0,
|
|
"step": 9705
|
|
},
|
|
{
|
|
"entropy": 5.504384708404541,
|
|
"epoch": 0.7554950398755106,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004948409994832043,
|
|
"loss": 5.1886,
|
|
"mean_token_accuracy": 0.18293901830911635,
|
|
"num_tokens": 16854825.0,
|
|
"step": 9710
|
|
},
|
|
{
|
|
"entropy": 5.591901350021362,
|
|
"epoch": 0.7558840692472282,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004948350967997526,
|
|
"loss": 5.3453,
|
|
"mean_token_accuracy": 0.16848235130310057,
|
|
"num_tokens": 16864096.0,
|
|
"step": 9715
|
|
},
|
|
{
|
|
"entropy": 5.636907529830933,
|
|
"epoch": 0.7562730986189458,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004948291907806532,
|
|
"loss": 5.391,
|
|
"mean_token_accuracy": 0.16900479644536973,
|
|
"num_tokens": 16873000.0,
|
|
"step": 9720
|
|
},
|
|
{
|
|
"entropy": 5.680421686172485,
|
|
"epoch": 0.7566621279906633,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004948232814259957,
|
|
"loss": 5.3942,
|
|
"mean_token_accuracy": 0.17993731200695037,
|
|
"num_tokens": 16881374.0,
|
|
"step": 9725
|
|
},
|
|
{
|
|
"entropy": 5.630921649932861,
|
|
"epoch": 0.7570511573623808,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004948173687358699,
|
|
"loss": 5.3637,
|
|
"mean_token_accuracy": 0.174547378718853,
|
|
"num_tokens": 16889192.0,
|
|
"step": 9730
|
|
},
|
|
{
|
|
"entropy": 5.5700239658355715,
|
|
"epoch": 0.7574401867340984,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004948114527103652,
|
|
"loss": 5.3546,
|
|
"mean_token_accuracy": 0.17323452830314637,
|
|
"num_tokens": 16898538.0,
|
|
"step": 9735
|
|
},
|
|
{
|
|
"entropy": 5.59753451347351,
|
|
"epoch": 0.757829216105816,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004948055333495717,
|
|
"loss": 5.343,
|
|
"mean_token_accuracy": 0.1698336720466614,
|
|
"num_tokens": 16907543.0,
|
|
"step": 9740
|
|
},
|
|
{
|
|
"entropy": 5.5732612133026125,
|
|
"epoch": 0.7582182454775336,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004947996106535791,
|
|
"loss": 5.2604,
|
|
"mean_token_accuracy": 0.18186050951480864,
|
|
"num_tokens": 16916140.0,
|
|
"step": 9745
|
|
},
|
|
{
|
|
"entropy": 5.5288232326507565,
|
|
"epoch": 0.7586072748492512,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004947936846224773,
|
|
"loss": 5.2556,
|
|
"mean_token_accuracy": 0.18514294773340226,
|
|
"num_tokens": 16925433.0,
|
|
"step": 9750
|
|
},
|
|
{
|
|
"entropy": 5.565367221832275,
|
|
"epoch": 0.7589963042209686,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004947877552563562,
|
|
"loss": 5.2704,
|
|
"mean_token_accuracy": 0.1804751992225647,
|
|
"num_tokens": 16933598.0,
|
|
"step": 9755
|
|
},
|
|
{
|
|
"entropy": 5.6109593391418455,
|
|
"epoch": 0.7593853335926862,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004947818225553056,
|
|
"loss": 5.3761,
|
|
"mean_token_accuracy": 0.1719370514154434,
|
|
"num_tokens": 16942270.0,
|
|
"step": 9760
|
|
},
|
|
{
|
|
"entropy": 5.565868473052978,
|
|
"epoch": 0.7597743629644038,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004947758865194156,
|
|
"loss": 5.2256,
|
|
"mean_token_accuracy": 0.17852199971675872,
|
|
"num_tokens": 16951044.0,
|
|
"step": 9765
|
|
},
|
|
{
|
|
"entropy": 5.646955442428589,
|
|
"epoch": 0.7601633923361214,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004947699471487766,
|
|
"loss": 5.3709,
|
|
"mean_token_accuracy": 0.1720644176006317,
|
|
"num_tokens": 16960215.0,
|
|
"step": 9770
|
|
},
|
|
{
|
|
"entropy": 5.659188556671142,
|
|
"epoch": 0.760552421707839,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004947640044434782,
|
|
"loss": 5.4275,
|
|
"mean_token_accuracy": 0.17238795906305313,
|
|
"num_tokens": 16968515.0,
|
|
"step": 9775
|
|
},
|
|
{
|
|
"entropy": 5.6146856307983395,
|
|
"epoch": 0.7609414510795565,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004947580584036109,
|
|
"loss": 5.4029,
|
|
"mean_token_accuracy": 0.16694126427173614,
|
|
"num_tokens": 16977597.0,
|
|
"step": 9780
|
|
},
|
|
{
|
|
"entropy": 5.572262859344482,
|
|
"epoch": 0.761330480451274,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004947521090292649,
|
|
"loss": 5.2411,
|
|
"mean_token_accuracy": 0.17830000072717667,
|
|
"num_tokens": 16987376.0,
|
|
"step": 9785
|
|
},
|
|
{
|
|
"entropy": 5.551488590240479,
|
|
"epoch": 0.7617195098229916,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004947461563205304,
|
|
"loss": 5.2443,
|
|
"mean_token_accuracy": 0.17933500111103057,
|
|
"num_tokens": 16995976.0,
|
|
"step": 9790
|
|
},
|
|
{
|
|
"entropy": 5.513866138458252,
|
|
"epoch": 0.7621085391947092,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004947402002774977,
|
|
"loss": 5.2625,
|
|
"mean_token_accuracy": 0.18817653954029084,
|
|
"num_tokens": 17003819.0,
|
|
"step": 9795
|
|
},
|
|
{
|
|
"entropy": 5.491230010986328,
|
|
"epoch": 0.7624975685664268,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004947342409002572,
|
|
"loss": 5.2537,
|
|
"mean_token_accuracy": 0.1792891263961792,
|
|
"num_tokens": 17011632.0,
|
|
"step": 9800
|
|
},
|
|
{
|
|
"entropy": 5.5333374500274655,
|
|
"epoch": 0.7628865979381443,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004947282781888994,
|
|
"loss": 5.1616,
|
|
"mean_token_accuracy": 0.1881726309657097,
|
|
"num_tokens": 17019737.0,
|
|
"step": 9805
|
|
},
|
|
{
|
|
"entropy": 5.583590269088745,
|
|
"epoch": 0.7632756273098619,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004947223121435147,
|
|
"loss": 5.3234,
|
|
"mean_token_accuracy": 0.18121691346168517,
|
|
"num_tokens": 17028803.0,
|
|
"step": 9810
|
|
},
|
|
{
|
|
"entropy": 5.554047870635986,
|
|
"epoch": 0.7636646566815795,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004947163427641936,
|
|
"loss": 5.1875,
|
|
"mean_token_accuracy": 0.18053693920373917,
|
|
"num_tokens": 17036847.0,
|
|
"step": 9815
|
|
},
|
|
{
|
|
"entropy": 5.621330976486206,
|
|
"epoch": 0.764053686053297,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004947103700510268,
|
|
"loss": 5.3166,
|
|
"mean_token_accuracy": 0.1728194311261177,
|
|
"num_tokens": 17045665.0,
|
|
"step": 9820
|
|
},
|
|
{
|
|
"entropy": 5.635409545898438,
|
|
"epoch": 0.7644427154250146,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004947043940041047,
|
|
"loss": 5.3207,
|
|
"mean_token_accuracy": 0.18165969252586364,
|
|
"num_tokens": 17053842.0,
|
|
"step": 9825
|
|
},
|
|
{
|
|
"entropy": 5.594769430160523,
|
|
"epoch": 0.7648317447967321,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004946984146235183,
|
|
"loss": 5.3953,
|
|
"mean_token_accuracy": 0.16821860522031784,
|
|
"num_tokens": 17062287.0,
|
|
"step": 9830
|
|
},
|
|
{
|
|
"entropy": 5.6085522174835205,
|
|
"epoch": 0.7652207741684497,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004946924319093579,
|
|
"loss": 5.383,
|
|
"mean_token_accuracy": 0.17949736267328262,
|
|
"num_tokens": 17071495.0,
|
|
"step": 9835
|
|
},
|
|
{
|
|
"entropy": 5.597342872619629,
|
|
"epoch": 0.7656098035401673,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004946864458617148,
|
|
"loss": 5.3294,
|
|
"mean_token_accuracy": 0.1748246893286705,
|
|
"num_tokens": 17080734.0,
|
|
"step": 9840
|
|
},
|
|
{
|
|
"entropy": 5.621782112121582,
|
|
"epoch": 0.7659988329118849,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004946804564806793,
|
|
"loss": 5.3367,
|
|
"mean_token_accuracy": 0.17630306482315064,
|
|
"num_tokens": 17089683.0,
|
|
"step": 9845
|
|
},
|
|
{
|
|
"entropy": 5.594048404693604,
|
|
"epoch": 0.7663878622836025,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004946744637663427,
|
|
"loss": 5.377,
|
|
"mean_token_accuracy": 0.17326258718967438,
|
|
"num_tokens": 17098203.0,
|
|
"step": 9850
|
|
},
|
|
{
|
|
"entropy": 5.5439417362213135,
|
|
"epoch": 0.7667768916553199,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004946684677187956,
|
|
"loss": 5.222,
|
|
"mean_token_accuracy": 0.17714088261127472,
|
|
"num_tokens": 17107185.0,
|
|
"step": 9855
|
|
},
|
|
{
|
|
"entropy": 5.580592250823974,
|
|
"epoch": 0.7671659210270375,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004946624683381292,
|
|
"loss": 5.2691,
|
|
"mean_token_accuracy": 0.18122341930866243,
|
|
"num_tokens": 17115168.0,
|
|
"step": 9860
|
|
},
|
|
{
|
|
"entropy": 5.545770931243896,
|
|
"epoch": 0.7675549503987551,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004946564656244345,
|
|
"loss": 5.2392,
|
|
"mean_token_accuracy": 0.18823157846927643,
|
|
"num_tokens": 17124037.0,
|
|
"step": 9865
|
|
},
|
|
{
|
|
"entropy": 5.5434150218963625,
|
|
"epoch": 0.7679439797704727,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004946504595778026,
|
|
"loss": 5.2068,
|
|
"mean_token_accuracy": 0.18442562073469163,
|
|
"num_tokens": 17132238.0,
|
|
"step": 9870
|
|
},
|
|
{
|
|
"entropy": 5.5897815227508545,
|
|
"epoch": 0.7683330091421903,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004946444501983246,
|
|
"loss": 5.3183,
|
|
"mean_token_accuracy": 0.17456935942173005,
|
|
"num_tokens": 17140405.0,
|
|
"step": 9875
|
|
},
|
|
{
|
|
"entropy": 5.550602149963379,
|
|
"epoch": 0.7687220385139077,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004946384374860916,
|
|
"loss": 5.2457,
|
|
"mean_token_accuracy": 0.18028399348258972,
|
|
"num_tokens": 17149207.0,
|
|
"step": 9880
|
|
},
|
|
{
|
|
"entropy": 5.561654663085937,
|
|
"epoch": 0.7691110678856253,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004946324214411949,
|
|
"loss": 5.2441,
|
|
"mean_token_accuracy": 0.1710297718644142,
|
|
"num_tokens": 17157680.0,
|
|
"step": 9885
|
|
},
|
|
{
|
|
"entropy": 5.574733448028565,
|
|
"epoch": 0.7695000972573429,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004946264020637259,
|
|
"loss": 5.2662,
|
|
"mean_token_accuracy": 0.1798670008778572,
|
|
"num_tokens": 17166907.0,
|
|
"step": 9890
|
|
},
|
|
{
|
|
"entropy": 5.542627191543579,
|
|
"epoch": 0.7698891266290605,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004946203793537757,
|
|
"loss": 5.3096,
|
|
"mean_token_accuracy": 0.18232055008411407,
|
|
"num_tokens": 17176318.0,
|
|
"step": 9895
|
|
},
|
|
{
|
|
"entropy": 5.583697700500489,
|
|
"epoch": 0.7702781560007781,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004946143533114358,
|
|
"loss": 5.3479,
|
|
"mean_token_accuracy": 0.17135487496852875,
|
|
"num_tokens": 17185380.0,
|
|
"step": 9900
|
|
},
|
|
{
|
|
"entropy": 5.611617565155029,
|
|
"epoch": 0.7706671853724957,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004946083239367976,
|
|
"loss": 5.3359,
|
|
"mean_token_accuracy": 0.1717481330037117,
|
|
"num_tokens": 17193177.0,
|
|
"step": 9905
|
|
},
|
|
{
|
|
"entropy": 5.541773319244385,
|
|
"epoch": 0.7710562147442132,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004946022912299527,
|
|
"loss": 5.3038,
|
|
"mean_token_accuracy": 0.1723075658082962,
|
|
"num_tokens": 17201071.0,
|
|
"step": 9910
|
|
},
|
|
{
|
|
"entropy": 5.5032923221588135,
|
|
"epoch": 0.7714452441159307,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004945962551909926,
|
|
"loss": 5.2114,
|
|
"mean_token_accuracy": 0.1849968373775482,
|
|
"num_tokens": 17209375.0,
|
|
"step": 9915
|
|
},
|
|
{
|
|
"entropy": 5.563618803024292,
|
|
"epoch": 0.7718342734876483,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004945902158200089,
|
|
"loss": 5.1621,
|
|
"mean_token_accuracy": 0.1880572259426117,
|
|
"num_tokens": 17217453.0,
|
|
"step": 9920
|
|
},
|
|
{
|
|
"entropy": 5.600003814697265,
|
|
"epoch": 0.7722233028593659,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004945841731170931,
|
|
"loss": 5.2354,
|
|
"mean_token_accuracy": 0.17970992028713226,
|
|
"num_tokens": 17225671.0,
|
|
"step": 9925
|
|
},
|
|
{
|
|
"entropy": 5.5217520236969,
|
|
"epoch": 0.7726123322310835,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004945781270823369,
|
|
"loss": 5.2036,
|
|
"mean_token_accuracy": 0.18175071477890015,
|
|
"num_tokens": 17234396.0,
|
|
"step": 9930
|
|
},
|
|
{
|
|
"entropy": 5.555613374710083,
|
|
"epoch": 0.773001361602801,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004945720777158323,
|
|
"loss": 5.3359,
|
|
"mean_token_accuracy": 0.17705983817577362,
|
|
"num_tokens": 17243509.0,
|
|
"step": 9935
|
|
},
|
|
{
|
|
"entropy": 5.579312658309936,
|
|
"epoch": 0.7733903909745186,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004945660250176708,
|
|
"loss": 5.2496,
|
|
"mean_token_accuracy": 0.18622122406959535,
|
|
"num_tokens": 17251447.0,
|
|
"step": 9940
|
|
},
|
|
{
|
|
"entropy": 5.535455179214478,
|
|
"epoch": 0.7737794203462361,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004945599689879443,
|
|
"loss": 5.3073,
|
|
"mean_token_accuracy": 0.1836530551314354,
|
|
"num_tokens": 17260240.0,
|
|
"step": 9945
|
|
},
|
|
{
|
|
"entropy": 5.5572467803955075,
|
|
"epoch": 0.7741684497179537,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004945539096267448,
|
|
"loss": 5.2901,
|
|
"mean_token_accuracy": 0.1767766907811165,
|
|
"num_tokens": 17267835.0,
|
|
"step": 9950
|
|
},
|
|
{
|
|
"entropy": 5.566209411621093,
|
|
"epoch": 0.7745574790896713,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004945478469341642,
|
|
"loss": 5.3083,
|
|
"mean_token_accuracy": 0.17683991938829421,
|
|
"num_tokens": 17277069.0,
|
|
"step": 9955
|
|
},
|
|
{
|
|
"entropy": 5.575392580032348,
|
|
"epoch": 0.7749465084613888,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004945417809102944,
|
|
"loss": 5.293,
|
|
"mean_token_accuracy": 0.1758789226412773,
|
|
"num_tokens": 17285014.0,
|
|
"step": 9960
|
|
},
|
|
{
|
|
"entropy": 5.5071587562561035,
|
|
"epoch": 0.7753355378331064,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004945357115552275,
|
|
"loss": 5.2308,
|
|
"mean_token_accuracy": 0.18336853235960007,
|
|
"num_tokens": 17292649.0,
|
|
"step": 9965
|
|
},
|
|
{
|
|
"entropy": 5.604107475280761,
|
|
"epoch": 0.775724567204824,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004945296388690557,
|
|
"loss": 5.3879,
|
|
"mean_token_accuracy": 0.1733226954936981,
|
|
"num_tokens": 17301792.0,
|
|
"step": 9970
|
|
},
|
|
{
|
|
"entropy": 5.540673494338989,
|
|
"epoch": 0.7761135965765416,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000494523562851871,
|
|
"loss": 5.1412,
|
|
"mean_token_accuracy": 0.18009239435195923,
|
|
"num_tokens": 17310377.0,
|
|
"step": 9975
|
|
},
|
|
{
|
|
"entropy": 5.568353652954102,
|
|
"epoch": 0.7765026259482591,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004945174835037655,
|
|
"loss": 5.3494,
|
|
"mean_token_accuracy": 0.17051731050014496,
|
|
"num_tokens": 17319779.0,
|
|
"step": 9980
|
|
},
|
|
{
|
|
"entropy": 5.67357063293457,
|
|
"epoch": 0.7768916553199766,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004945114008248319,
|
|
"loss": 5.4623,
|
|
"mean_token_accuracy": 0.1699962943792343,
|
|
"num_tokens": 17328210.0,
|
|
"step": 9985
|
|
},
|
|
{
|
|
"entropy": 5.558511638641358,
|
|
"epoch": 0.7772806846916942,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004945053148151619,
|
|
"loss": 5.2192,
|
|
"mean_token_accuracy": 0.18325317949056624,
|
|
"num_tokens": 17336287.0,
|
|
"step": 9990
|
|
},
|
|
{
|
|
"entropy": 5.536718559265137,
|
|
"epoch": 0.7776697140634118,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004944992254748482,
|
|
"loss": 5.2726,
|
|
"mean_token_accuracy": 0.170750629901886,
|
|
"num_tokens": 17344171.0,
|
|
"step": 9995
|
|
},
|
|
{
|
|
"entropy": 5.516432762145996,
|
|
"epoch": 0.7780587434351294,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004944931328039832,
|
|
"loss": 5.2807,
|
|
"mean_token_accuracy": 0.1826992779970169,
|
|
"num_tokens": 17352786.0,
|
|
"step": 10000
|
|
},
|
|
{
|
|
"entropy": 5.5678215503692625,
|
|
"epoch": 0.778447772806847,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004944870368026592,
|
|
"loss": 5.2731,
|
|
"mean_token_accuracy": 0.1825814127922058,
|
|
"num_tokens": 17361824.0,
|
|
"step": 10005
|
|
},
|
|
{
|
|
"entropy": 5.621897792816162,
|
|
"epoch": 0.7788368021785644,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004944809374709689,
|
|
"loss": 5.2789,
|
|
"mean_token_accuracy": 0.18325003683567048,
|
|
"num_tokens": 17370249.0,
|
|
"step": 10010
|
|
},
|
|
{
|
|
"entropy": 5.564912033081055,
|
|
"epoch": 0.779225831550282,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004944748348090045,
|
|
"loss": 5.2644,
|
|
"mean_token_accuracy": 0.17794045060873032,
|
|
"num_tokens": 17379650.0,
|
|
"step": 10015
|
|
},
|
|
{
|
|
"entropy": 5.543955659866333,
|
|
"epoch": 0.7796148609219996,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004944687288168589,
|
|
"loss": 5.2846,
|
|
"mean_token_accuracy": 0.17984797060489655,
|
|
"num_tokens": 17388046.0,
|
|
"step": 10020
|
|
},
|
|
{
|
|
"entropy": 5.570498132705689,
|
|
"epoch": 0.7800038902937172,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004944626194946246,
|
|
"loss": 5.2616,
|
|
"mean_token_accuracy": 0.1875917673110962,
|
|
"num_tokens": 17395851.0,
|
|
"step": 10025
|
|
},
|
|
{
|
|
"entropy": 5.578702831268311,
|
|
"epoch": 0.7803929196654348,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004944565068423945,
|
|
"loss": 5.3197,
|
|
"mean_token_accuracy": 0.17798285335302352,
|
|
"num_tokens": 17404273.0,
|
|
"step": 10030
|
|
},
|
|
{
|
|
"entropy": 5.5402006149292,
|
|
"epoch": 0.7807819490371523,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004944503908602612,
|
|
"loss": 5.2692,
|
|
"mean_token_accuracy": 0.180065880715847,
|
|
"num_tokens": 17412884.0,
|
|
"step": 10035
|
|
},
|
|
{
|
|
"entropy": 5.602862596511841,
|
|
"epoch": 0.7811709784088698,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004944442715483174,
|
|
"loss": 5.2594,
|
|
"mean_token_accuracy": 0.17478689551353455,
|
|
"num_tokens": 17420939.0,
|
|
"step": 10040
|
|
},
|
|
{
|
|
"entropy": 5.561760759353637,
|
|
"epoch": 0.7815600077805874,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004944381489066561,
|
|
"loss": 5.3074,
|
|
"mean_token_accuracy": 0.1774538889527321,
|
|
"num_tokens": 17429838.0,
|
|
"step": 10045
|
|
},
|
|
{
|
|
"entropy": 5.557232141494751,
|
|
"epoch": 0.781949037152305,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004944320229353702,
|
|
"loss": 5.2628,
|
|
"mean_token_accuracy": 0.17559466063976287,
|
|
"num_tokens": 17439164.0,
|
|
"step": 10050
|
|
},
|
|
{
|
|
"entropy": 5.619220304489136,
|
|
"epoch": 0.7823380665240226,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004944258936345526,
|
|
"loss": 5.2689,
|
|
"mean_token_accuracy": 0.18301373720169067,
|
|
"num_tokens": 17447544.0,
|
|
"step": 10055
|
|
},
|
|
{
|
|
"entropy": 5.492280721664429,
|
|
"epoch": 0.7827270958957401,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004944197610042963,
|
|
"loss": 5.1387,
|
|
"mean_token_accuracy": 0.1840054675936699,
|
|
"num_tokens": 17456270.0,
|
|
"step": 10060
|
|
},
|
|
{
|
|
"entropy": 5.554314136505127,
|
|
"epoch": 0.7831161252674577,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004944136250446944,
|
|
"loss": 5.3176,
|
|
"mean_token_accuracy": 0.17473938763141633,
|
|
"num_tokens": 17465241.0,
|
|
"step": 10065
|
|
},
|
|
{
|
|
"entropy": 5.646536111831665,
|
|
"epoch": 0.7835051546391752,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004944074857558399,
|
|
"loss": 5.3438,
|
|
"mean_token_accuracy": 0.1689807027578354,
|
|
"num_tokens": 17474460.0,
|
|
"step": 10070
|
|
},
|
|
{
|
|
"entropy": 5.56577320098877,
|
|
"epoch": 0.7838941840108928,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004944013431378261,
|
|
"loss": 5.2937,
|
|
"mean_token_accuracy": 0.18041094094514848,
|
|
"num_tokens": 17483256.0,
|
|
"step": 10075
|
|
},
|
|
{
|
|
"entropy": 5.6156011581420895,
|
|
"epoch": 0.7842832133826104,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004943951971907461,
|
|
"loss": 5.3056,
|
|
"mean_token_accuracy": 0.17655237317085265,
|
|
"num_tokens": 17491922.0,
|
|
"step": 10080
|
|
},
|
|
{
|
|
"entropy": 5.613048505783081,
|
|
"epoch": 0.7846722427543279,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004943890479146933,
|
|
"loss": 5.2938,
|
|
"mean_token_accuracy": 0.18363881558179856,
|
|
"num_tokens": 17499763.0,
|
|
"step": 10085
|
|
},
|
|
{
|
|
"entropy": 5.548869562149048,
|
|
"epoch": 0.7850612721260455,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004943828953097607,
|
|
"loss": 5.2761,
|
|
"mean_token_accuracy": 0.17813890874385835,
|
|
"num_tokens": 17508682.0,
|
|
"step": 10090
|
|
},
|
|
{
|
|
"entropy": 5.520614910125732,
|
|
"epoch": 0.7854503014977631,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000494376739376042,
|
|
"loss": 5.2158,
|
|
"mean_token_accuracy": 0.1830417662858963,
|
|
"num_tokens": 17517269.0,
|
|
"step": 10095
|
|
},
|
|
{
|
|
"entropy": 5.505959224700928,
|
|
"epoch": 0.7858393308694807,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004943705801136304,
|
|
"loss": 5.2342,
|
|
"mean_token_accuracy": 0.17939852327108383,
|
|
"num_tokens": 17525135.0,
|
|
"step": 10100
|
|
},
|
|
{
|
|
"entropy": 5.555085182189941,
|
|
"epoch": 0.7862283602411982,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004943644175226193,
|
|
"loss": 5.3091,
|
|
"mean_token_accuracy": 0.18469279259443283,
|
|
"num_tokens": 17534195.0,
|
|
"step": 10105
|
|
},
|
|
{
|
|
"entropy": 5.541886472702027,
|
|
"epoch": 0.7866173896129158,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004943582516031025,
|
|
"loss": 5.2105,
|
|
"mean_token_accuracy": 0.18273035436868668,
|
|
"num_tokens": 17543016.0,
|
|
"step": 10110
|
|
},
|
|
{
|
|
"entropy": 5.5975395202636715,
|
|
"epoch": 0.7870064189846333,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004943520823551732,
|
|
"loss": 5.3202,
|
|
"mean_token_accuracy": 0.18122852444648743,
|
|
"num_tokens": 17551854.0,
|
|
"step": 10115
|
|
},
|
|
{
|
|
"entropy": 5.5274608612060545,
|
|
"epoch": 0.7873954483563509,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004943459097789252,
|
|
"loss": 5.2235,
|
|
"mean_token_accuracy": 0.1863451659679413,
|
|
"num_tokens": 17560739.0,
|
|
"step": 10120
|
|
},
|
|
{
|
|
"entropy": 5.535266923904419,
|
|
"epoch": 0.7877844777280685,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004943397338744523,
|
|
"loss": 5.2287,
|
|
"mean_token_accuracy": 0.18101687282323836,
|
|
"num_tokens": 17569784.0,
|
|
"step": 10125
|
|
},
|
|
{
|
|
"entropy": 5.592965888977051,
|
|
"epoch": 0.7881735070997861,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000494333554641848,
|
|
"loss": 5.3998,
|
|
"mean_token_accuracy": 0.1753152623772621,
|
|
"num_tokens": 17579262.0,
|
|
"step": 10130
|
|
},
|
|
{
|
|
"entropy": 5.508724594116211,
|
|
"epoch": 0.7885625364715037,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000494327372081206,
|
|
"loss": 5.2582,
|
|
"mean_token_accuracy": 0.1788112297654152,
|
|
"num_tokens": 17587984.0,
|
|
"step": 10135
|
|
},
|
|
{
|
|
"entropy": 5.50737943649292,
|
|
"epoch": 0.7889515658432211,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004943211861926204,
|
|
"loss": 5.2049,
|
|
"mean_token_accuracy": 0.18378990292549133,
|
|
"num_tokens": 17596598.0,
|
|
"step": 10140
|
|
},
|
|
{
|
|
"entropy": 5.536486291885376,
|
|
"epoch": 0.7893405952149387,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004943149969761848,
|
|
"loss": 5.3386,
|
|
"mean_token_accuracy": 0.1783975303173065,
|
|
"num_tokens": 17605768.0,
|
|
"step": 10145
|
|
},
|
|
{
|
|
"entropy": 5.597452116012573,
|
|
"epoch": 0.7897296245866563,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004943088044319932,
|
|
"loss": 5.2632,
|
|
"mean_token_accuracy": 0.1779785394668579,
|
|
"num_tokens": 17614412.0,
|
|
"step": 10150
|
|
},
|
|
{
|
|
"entropy": 5.5843816757202145,
|
|
"epoch": 0.7901186539583739,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004943026085601395,
|
|
"loss": 5.2841,
|
|
"mean_token_accuracy": 0.18136109709739684,
|
|
"num_tokens": 17622515.0,
|
|
"step": 10155
|
|
},
|
|
{
|
|
"entropy": 5.504694604873658,
|
|
"epoch": 0.7905076833300915,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004942964093607178,
|
|
"loss": 5.2068,
|
|
"mean_token_accuracy": 0.18027411699295043,
|
|
"num_tokens": 17631256.0,
|
|
"step": 10160
|
|
},
|
|
{
|
|
"entropy": 5.62631516456604,
|
|
"epoch": 0.790896712701809,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004942902068338222,
|
|
"loss": 5.3251,
|
|
"mean_token_accuracy": 0.17326385974884034,
|
|
"num_tokens": 17639648.0,
|
|
"step": 10165
|
|
},
|
|
{
|
|
"entropy": 5.5855039119720455,
|
|
"epoch": 0.7912857420735265,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004942840009795466,
|
|
"loss": 5.2646,
|
|
"mean_token_accuracy": 0.17888859510421753,
|
|
"num_tokens": 17648225.0,
|
|
"step": 10170
|
|
},
|
|
{
|
|
"entropy": 5.58572039604187,
|
|
"epoch": 0.7916747714452441,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004942777917979855,
|
|
"loss": 5.2949,
|
|
"mean_token_accuracy": 0.1864625632762909,
|
|
"num_tokens": 17656764.0,
|
|
"step": 10175
|
|
},
|
|
{
|
|
"entropy": 5.564801359176636,
|
|
"epoch": 0.7920638008169617,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004942715792892328,
|
|
"loss": 5.282,
|
|
"mean_token_accuracy": 0.17569558769464494,
|
|
"num_tokens": 17665127.0,
|
|
"step": 10180
|
|
},
|
|
{
|
|
"entropy": 5.501125431060791,
|
|
"epoch": 0.7924528301886793,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000494265363453383,
|
|
"loss": 5.167,
|
|
"mean_token_accuracy": 0.1871642664074898,
|
|
"num_tokens": 17673297.0,
|
|
"step": 10185
|
|
},
|
|
{
|
|
"entropy": 5.53309645652771,
|
|
"epoch": 0.7928418595603968,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004942591442905302,
|
|
"loss": 5.3145,
|
|
"mean_token_accuracy": 0.1781333178281784,
|
|
"num_tokens": 17681816.0,
|
|
"step": 10190
|
|
},
|
|
{
|
|
"entropy": 5.578197336196899,
|
|
"epoch": 0.7932308889321144,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004942529218007689,
|
|
"loss": 5.3235,
|
|
"mean_token_accuracy": 0.17432713359594346,
|
|
"num_tokens": 17690588.0,
|
|
"step": 10195
|
|
},
|
|
{
|
|
"entropy": 5.577566242218017,
|
|
"epoch": 0.7936199183038319,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004942466959841936,
|
|
"loss": 5.2294,
|
|
"mean_token_accuracy": 0.18250014781951904,
|
|
"num_tokens": 17699196.0,
|
|
"step": 10200
|
|
},
|
|
{
|
|
"entropy": 5.604201364517212,
|
|
"epoch": 0.7940089476755495,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004942404668408985,
|
|
"loss": 5.3432,
|
|
"mean_token_accuracy": 0.17931440323591233,
|
|
"num_tokens": 17708928.0,
|
|
"step": 10205
|
|
},
|
|
{
|
|
"entropy": 5.599688148498535,
|
|
"epoch": 0.7943979770472671,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004942342343709783,
|
|
"loss": 5.2326,
|
|
"mean_token_accuracy": 0.1876217842102051,
|
|
"num_tokens": 17717888.0,
|
|
"step": 10210
|
|
},
|
|
{
|
|
"entropy": 5.620655679702759,
|
|
"epoch": 0.7947870064189846,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004942279985745275,
|
|
"loss": 5.2632,
|
|
"mean_token_accuracy": 0.17752481251955032,
|
|
"num_tokens": 17726022.0,
|
|
"step": 10215
|
|
},
|
|
{
|
|
"entropy": 5.512254524230957,
|
|
"epoch": 0.7951760357907022,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004942217594516409,
|
|
"loss": 5.2353,
|
|
"mean_token_accuracy": 0.18148309588432313,
|
|
"num_tokens": 17733998.0,
|
|
"step": 10220
|
|
},
|
|
{
|
|
"entropy": 5.602106142044067,
|
|
"epoch": 0.7955650651624198,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000494215517002413,
|
|
"loss": 5.2989,
|
|
"mean_token_accuracy": 0.1809411719441414,
|
|
"num_tokens": 17742039.0,
|
|
"step": 10225
|
|
},
|
|
{
|
|
"entropy": 5.5189722061157225,
|
|
"epoch": 0.7959540945341373,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004942092712269384,
|
|
"loss": 5.1802,
|
|
"mean_token_accuracy": 0.18697760850191117,
|
|
"num_tokens": 17751474.0,
|
|
"step": 10230
|
|
},
|
|
{
|
|
"entropy": 5.505219650268555,
|
|
"epoch": 0.7963431239058549,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004942030221253122,
|
|
"loss": 5.2039,
|
|
"mean_token_accuracy": 0.18463034331798553,
|
|
"num_tokens": 17759483.0,
|
|
"step": 10235
|
|
},
|
|
{
|
|
"entropy": 5.534953975677491,
|
|
"epoch": 0.7967321532775724,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004941967696976289,
|
|
"loss": 5.3131,
|
|
"mean_token_accuracy": 0.18131082355976105,
|
|
"num_tokens": 17768025.0,
|
|
"step": 10240
|
|
},
|
|
{
|
|
"entropy": 5.512156438827515,
|
|
"epoch": 0.79712118264929,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004941905139439835,
|
|
"loss": 5.1613,
|
|
"mean_token_accuracy": 0.1847629204392433,
|
|
"num_tokens": 17776861.0,
|
|
"step": 10245
|
|
},
|
|
{
|
|
"entropy": 5.5302856922149655,
|
|
"epoch": 0.7975102120210076,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004941842548644712,
|
|
"loss": 5.2737,
|
|
"mean_token_accuracy": 0.1749660238623619,
|
|
"num_tokens": 17786221.0,
|
|
"step": 10250
|
|
},
|
|
{
|
|
"entropy": 5.623866415023803,
|
|
"epoch": 0.7978992413927252,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004941779924591864,
|
|
"loss": 5.2684,
|
|
"mean_token_accuracy": 0.17311887294054032,
|
|
"num_tokens": 17794619.0,
|
|
"step": 10255
|
|
},
|
|
{
|
|
"entropy": 5.59625391960144,
|
|
"epoch": 0.7982882707644428,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004941717267282244,
|
|
"loss": 5.261,
|
|
"mean_token_accuracy": 0.1823060542345047,
|
|
"num_tokens": 17803288.0,
|
|
"step": 10260
|
|
},
|
|
{
|
|
"entropy": 5.552209997177124,
|
|
"epoch": 0.7986773001361602,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004941654576716806,
|
|
"loss": 5.3259,
|
|
"mean_token_accuracy": 0.16714696437120438,
|
|
"num_tokens": 17812648.0,
|
|
"step": 10265
|
|
},
|
|
{
|
|
"entropy": 5.487466621398926,
|
|
"epoch": 0.7990663295078778,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004941591852896495,
|
|
"loss": 5.2442,
|
|
"mean_token_accuracy": 0.1840747281908989,
|
|
"num_tokens": 17821955.0,
|
|
"step": 10270
|
|
},
|
|
{
|
|
"entropy": 5.648491287231446,
|
|
"epoch": 0.7994553588795954,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004941529095822268,
|
|
"loss": 5.3107,
|
|
"mean_token_accuracy": 0.18278683423995973,
|
|
"num_tokens": 17829987.0,
|
|
"step": 10275
|
|
},
|
|
{
|
|
"entropy": 5.578384351730347,
|
|
"epoch": 0.799844388251313,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004941466305495074,
|
|
"loss": 5.2332,
|
|
"mean_token_accuracy": 0.18437684029340745,
|
|
"num_tokens": 17839298.0,
|
|
"step": 10280
|
|
},
|
|
{
|
|
"entropy": 5.54558835029602,
|
|
"epoch": 0.8002334176230306,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004941403481915867,
|
|
"loss": 5.2554,
|
|
"mean_token_accuracy": 0.17760299891233444,
|
|
"num_tokens": 17847950.0,
|
|
"step": 10285
|
|
},
|
|
{
|
|
"entropy": 5.613780212402344,
|
|
"epoch": 0.800622446994748,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004941340625085601,
|
|
"loss": 5.3839,
|
|
"mean_token_accuracy": 0.17219481319189073,
|
|
"num_tokens": 17857416.0,
|
|
"step": 10290
|
|
},
|
|
{
|
|
"entropy": 5.634960556030274,
|
|
"epoch": 0.8010114763664656,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004941277735005228,
|
|
"loss": 5.2557,
|
|
"mean_token_accuracy": 0.18916381150484085,
|
|
"num_tokens": 17866516.0,
|
|
"step": 10295
|
|
},
|
|
{
|
|
"entropy": 5.681487607955932,
|
|
"epoch": 0.8014005057381832,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004941214811675702,
|
|
"loss": 5.4014,
|
|
"mean_token_accuracy": 0.16773732006549835,
|
|
"num_tokens": 17875823.0,
|
|
"step": 10300
|
|
},
|
|
{
|
|
"entropy": 5.512523746490478,
|
|
"epoch": 0.8017895351099008,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004941151855097982,
|
|
"loss": 5.2769,
|
|
"mean_token_accuracy": 0.17694343477487565,
|
|
"num_tokens": 17883597.0,
|
|
"step": 10305
|
|
},
|
|
{
|
|
"entropy": 5.593393468856812,
|
|
"epoch": 0.8021785644816184,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004941088865273018,
|
|
"loss": 5.2708,
|
|
"mean_token_accuracy": 0.17596012204885483,
|
|
"num_tokens": 17892053.0,
|
|
"step": 10310
|
|
},
|
|
{
|
|
"entropy": 5.583527565002441,
|
|
"epoch": 0.802567593853336,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004941025842201769,
|
|
"loss": 5.1833,
|
|
"mean_token_accuracy": 0.18942164480686188,
|
|
"num_tokens": 17900187.0,
|
|
"step": 10315
|
|
},
|
|
{
|
|
"entropy": 5.563230037689209,
|
|
"epoch": 0.8029566232250535,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004940962785885189,
|
|
"loss": 5.3392,
|
|
"mean_token_accuracy": 0.1744835615158081,
|
|
"num_tokens": 17908608.0,
|
|
"step": 10320
|
|
},
|
|
{
|
|
"entropy": 5.588981246948242,
|
|
"epoch": 0.803345652596771,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004940899696324237,
|
|
"loss": 5.2302,
|
|
"mean_token_accuracy": 0.18067265748977662,
|
|
"num_tokens": 17917331.0,
|
|
"step": 10325
|
|
},
|
|
{
|
|
"entropy": 5.626565408706665,
|
|
"epoch": 0.8037346819684886,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004940836573519868,
|
|
"loss": 5.3506,
|
|
"mean_token_accuracy": 0.17576338946819306,
|
|
"num_tokens": 17925228.0,
|
|
"step": 10330
|
|
},
|
|
{
|
|
"entropy": 5.5760797500610355,
|
|
"epoch": 0.8041237113402062,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004940773417473043,
|
|
"loss": 5.2091,
|
|
"mean_token_accuracy": 0.1828831896185875,
|
|
"num_tokens": 17934110.0,
|
|
"step": 10335
|
|
},
|
|
{
|
|
"entropy": 5.489350032806397,
|
|
"epoch": 0.8045127407119238,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004940710228184717,
|
|
"loss": 5.2238,
|
|
"mean_token_accuracy": 0.18484015315771102,
|
|
"num_tokens": 17942237.0,
|
|
"step": 10340
|
|
},
|
|
{
|
|
"entropy": 5.491905260086059,
|
|
"epoch": 0.8049017700836413,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000494064700565585,
|
|
"loss": 5.0699,
|
|
"mean_token_accuracy": 0.1908535286784172,
|
|
"num_tokens": 17951288.0,
|
|
"step": 10345
|
|
},
|
|
{
|
|
"entropy": 5.618882369995117,
|
|
"epoch": 0.8052907994553589,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004940583749887403,
|
|
"loss": 5.3416,
|
|
"mean_token_accuracy": 0.17543888986110687,
|
|
"num_tokens": 17960300.0,
|
|
"step": 10350
|
|
},
|
|
{
|
|
"entropy": 5.532686710357666,
|
|
"epoch": 0.8056798288270764,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004940520460880333,
|
|
"loss": 5.2459,
|
|
"mean_token_accuracy": 0.18015871644020082,
|
|
"num_tokens": 17968745.0,
|
|
"step": 10355
|
|
},
|
|
{
|
|
"entropy": 5.501589345932007,
|
|
"epoch": 0.806068858198794,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004940457138635601,
|
|
"loss": 5.2277,
|
|
"mean_token_accuracy": 0.18703533113002777,
|
|
"num_tokens": 17976614.0,
|
|
"step": 10360
|
|
},
|
|
{
|
|
"entropy": 5.590014410018921,
|
|
"epoch": 0.8064578875705116,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004940393783154169,
|
|
"loss": 5.3707,
|
|
"mean_token_accuracy": 0.17463206201791764,
|
|
"num_tokens": 17984769.0,
|
|
"step": 10365
|
|
},
|
|
{
|
|
"entropy": 5.55709285736084,
|
|
"epoch": 0.8068469169422291,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004940330394436999,
|
|
"loss": 5.2467,
|
|
"mean_token_accuracy": 0.1752379283308983,
|
|
"num_tokens": 17992885.0,
|
|
"step": 10370
|
|
},
|
|
{
|
|
"entropy": 5.605456304550171,
|
|
"epoch": 0.8072359463139467,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000494026697248505,
|
|
"loss": 5.2807,
|
|
"mean_token_accuracy": 0.17333069145679475,
|
|
"num_tokens": 18001752.0,
|
|
"step": 10375
|
|
},
|
|
{
|
|
"entropy": 5.528792381286621,
|
|
"epoch": 0.8076249756856643,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004940203517299287,
|
|
"loss": 5.2895,
|
|
"mean_token_accuracy": 0.18906021267175674,
|
|
"num_tokens": 18009939.0,
|
|
"step": 10380
|
|
},
|
|
{
|
|
"entropy": 5.631753206253052,
|
|
"epoch": 0.8080140050573819,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000494014002888067,
|
|
"loss": 5.2464,
|
|
"mean_token_accuracy": 0.1893475979566574,
|
|
"num_tokens": 18017993.0,
|
|
"step": 10385
|
|
},
|
|
{
|
|
"entropy": 5.656357955932617,
|
|
"epoch": 0.8084030344290994,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004940076507230166,
|
|
"loss": 5.3562,
|
|
"mean_token_accuracy": 0.1703679695725441,
|
|
"num_tokens": 18027564.0,
|
|
"step": 10390
|
|
},
|
|
{
|
|
"entropy": 5.6072712421417235,
|
|
"epoch": 0.8087920638008169,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004940012952348735,
|
|
"loss": 5.3296,
|
|
"mean_token_accuracy": 0.17833323925733566,
|
|
"num_tokens": 18036174.0,
|
|
"step": 10395
|
|
},
|
|
{
|
|
"entropy": 5.577934980392456,
|
|
"epoch": 0.8091810931725345,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004939949364237345,
|
|
"loss": 5.2453,
|
|
"mean_token_accuracy": 0.1775733470916748,
|
|
"num_tokens": 18044994.0,
|
|
"step": 10400
|
|
},
|
|
{
|
|
"entropy": 5.5368577003479,
|
|
"epoch": 0.8095701225442521,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004939885742896958,
|
|
"loss": 5.2578,
|
|
"mean_token_accuracy": 0.18077761679887772,
|
|
"num_tokens": 18053789.0,
|
|
"step": 10405
|
|
},
|
|
{
|
|
"entropy": 5.596770715713501,
|
|
"epoch": 0.8099591519159697,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000493982208832854,
|
|
"loss": 5.3559,
|
|
"mean_token_accuracy": 0.1795223593711853,
|
|
"num_tokens": 18063483.0,
|
|
"step": 10410
|
|
},
|
|
{
|
|
"entropy": 5.554763412475586,
|
|
"epoch": 0.8103481812876873,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004939758400533058,
|
|
"loss": 5.1755,
|
|
"mean_token_accuracy": 0.1859259694814682,
|
|
"num_tokens": 18071952.0,
|
|
"step": 10415
|
|
},
|
|
{
|
|
"entropy": 5.574611568450928,
|
|
"epoch": 0.8107372106594047,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004939694679511478,
|
|
"loss": 5.2283,
|
|
"mean_token_accuracy": 0.18664990812540055,
|
|
"num_tokens": 18080323.0,
|
|
"step": 10420
|
|
},
|
|
{
|
|
"entropy": 5.606487798690796,
|
|
"epoch": 0.8111262400311223,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004939630925264765,
|
|
"loss": 5.3384,
|
|
"mean_token_accuracy": 0.17754612863063812,
|
|
"num_tokens": 18089458.0,
|
|
"step": 10425
|
|
},
|
|
{
|
|
"entropy": 5.600635194778443,
|
|
"epoch": 0.8115152694028399,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000493956713779389,
|
|
"loss": 5.2474,
|
|
"mean_token_accuracy": 0.1756208136677742,
|
|
"num_tokens": 18098553.0,
|
|
"step": 10430
|
|
},
|
|
{
|
|
"entropy": 5.55400333404541,
|
|
"epoch": 0.8119042987745575,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004939503317099817,
|
|
"loss": 5.357,
|
|
"mean_token_accuracy": 0.17223884910345078,
|
|
"num_tokens": 18106794.0,
|
|
"step": 10435
|
|
},
|
|
{
|
|
"entropy": 5.533067417144776,
|
|
"epoch": 0.8122933281462751,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004939439463183517,
|
|
"loss": 5.1949,
|
|
"mean_token_accuracy": 0.1866455078125,
|
|
"num_tokens": 18115509.0,
|
|
"step": 10440
|
|
},
|
|
{
|
|
"entropy": 5.5484973907470705,
|
|
"epoch": 0.8126823575179926,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004939375576045958,
|
|
"loss": 5.3523,
|
|
"mean_token_accuracy": 0.1700367271900177,
|
|
"num_tokens": 18124548.0,
|
|
"step": 10445
|
|
},
|
|
{
|
|
"entropy": 5.563609457015991,
|
|
"epoch": 0.8130713868897101,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004939311655688109,
|
|
"loss": 5.2722,
|
|
"mean_token_accuracy": 0.17956678569316864,
|
|
"num_tokens": 18132295.0,
|
|
"step": 10450
|
|
},
|
|
{
|
|
"entropy": 5.647200250625611,
|
|
"epoch": 0.8134604162614277,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004939247702110941,
|
|
"loss": 5.3737,
|
|
"mean_token_accuracy": 0.17452162355184556,
|
|
"num_tokens": 18140731.0,
|
|
"step": 10455
|
|
},
|
|
{
|
|
"entropy": 5.566962099075317,
|
|
"epoch": 0.8138494456331453,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004939183715315423,
|
|
"loss": 5.2356,
|
|
"mean_token_accuracy": 0.17991308867931366,
|
|
"num_tokens": 18149834.0,
|
|
"step": 10460
|
|
},
|
|
{
|
|
"entropy": 5.526085138320923,
|
|
"epoch": 0.8142384750048629,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004939119695302526,
|
|
"loss": 5.1763,
|
|
"mean_token_accuracy": 0.19115205854177475,
|
|
"num_tokens": 18158745.0,
|
|
"step": 10465
|
|
},
|
|
{
|
|
"entropy": 5.607345056533814,
|
|
"epoch": 0.8146275043765804,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004939055642073224,
|
|
"loss": 5.3817,
|
|
"mean_token_accuracy": 0.17092738747596742,
|
|
"num_tokens": 18168292.0,
|
|
"step": 10470
|
|
},
|
|
{
|
|
"entropy": 5.592886638641358,
|
|
"epoch": 0.815016533748298,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004938991555628484,
|
|
"loss": 5.2716,
|
|
"mean_token_accuracy": 0.17934371829032897,
|
|
"num_tokens": 18177592.0,
|
|
"step": 10475
|
|
},
|
|
{
|
|
"entropy": 5.5881054401397705,
|
|
"epoch": 0.8154055631200156,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004938927435969283,
|
|
"loss": 5.2454,
|
|
"mean_token_accuracy": 0.17746430188417434,
|
|
"num_tokens": 18186845.0,
|
|
"step": 10480
|
|
},
|
|
{
|
|
"entropy": 5.613975381851196,
|
|
"epoch": 0.8157945924917331,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004938863283096592,
|
|
"loss": 5.3401,
|
|
"mean_token_accuracy": 0.17624317705631257,
|
|
"num_tokens": 18195417.0,
|
|
"step": 10485
|
|
},
|
|
{
|
|
"entropy": 5.5749125480651855,
|
|
"epoch": 0.8161836218634507,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004938799097011384,
|
|
"loss": 5.2681,
|
|
"mean_token_accuracy": 0.17838387191295624,
|
|
"num_tokens": 18204009.0,
|
|
"step": 10490
|
|
},
|
|
{
|
|
"entropy": 5.531589126586914,
|
|
"epoch": 0.8165726512351682,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004938734877714634,
|
|
"loss": 5.2806,
|
|
"mean_token_accuracy": 0.18555265069007873,
|
|
"num_tokens": 18211927.0,
|
|
"step": 10495
|
|
},
|
|
{
|
|
"entropy": 5.482576751708985,
|
|
"epoch": 0.8169616806068858,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004938670625207317,
|
|
"loss": 5.1626,
|
|
"mean_token_accuracy": 0.1902029275894165,
|
|
"num_tokens": 18220394.0,
|
|
"step": 10500
|
|
},
|
|
{
|
|
"entropy": 5.596595764160156,
|
|
"epoch": 0.8173507099786034,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004938606339490406,
|
|
"loss": 5.3268,
|
|
"mean_token_accuracy": 0.17240248173475264,
|
|
"num_tokens": 18229803.0,
|
|
"step": 10505
|
|
},
|
|
{
|
|
"entropy": 5.591364812850952,
|
|
"epoch": 0.817739739350321,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004938542020564877,
|
|
"loss": 5.25,
|
|
"mean_token_accuracy": 0.1745932385325432,
|
|
"num_tokens": 18238431.0,
|
|
"step": 10510
|
|
},
|
|
{
|
|
"entropy": 5.563290119171143,
|
|
"epoch": 0.8181287687220385,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004938477668431706,
|
|
"loss": 5.2631,
|
|
"mean_token_accuracy": 0.1808483213186264,
|
|
"num_tokens": 18246745.0,
|
|
"step": 10515
|
|
},
|
|
{
|
|
"entropy": 5.531867933273316,
|
|
"epoch": 0.8185177980937561,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004938413283091871,
|
|
"loss": 5.2347,
|
|
"mean_token_accuracy": 0.1842041239142418,
|
|
"num_tokens": 18255569.0,
|
|
"step": 10520
|
|
},
|
|
{
|
|
"entropy": 5.529405164718628,
|
|
"epoch": 0.8189068274654736,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004938348864546347,
|
|
"loss": 5.1893,
|
|
"mean_token_accuracy": 0.18322349041700364,
|
|
"num_tokens": 18263711.0,
|
|
"step": 10525
|
|
},
|
|
{
|
|
"entropy": 5.641204309463501,
|
|
"epoch": 0.8192958568371912,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004938284412796111,
|
|
"loss": 5.3469,
|
|
"mean_token_accuracy": 0.1820904418826103,
|
|
"num_tokens": 18272220.0,
|
|
"step": 10530
|
|
},
|
|
{
|
|
"entropy": 5.606492519378662,
|
|
"epoch": 0.8196848862089088,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004938219927842144,
|
|
"loss": 5.2645,
|
|
"mean_token_accuracy": 0.17838217914104462,
|
|
"num_tokens": 18281107.0,
|
|
"step": 10535
|
|
},
|
|
{
|
|
"entropy": 5.482708406448364,
|
|
"epoch": 0.8200739155806264,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004938155409685422,
|
|
"loss": 5.217,
|
|
"mean_token_accuracy": 0.18029659390449523,
|
|
"num_tokens": 18290196.0,
|
|
"step": 10540
|
|
},
|
|
{
|
|
"entropy": 5.607309103012085,
|
|
"epoch": 0.820462944952344,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004938090858326923,
|
|
"loss": 5.3763,
|
|
"mean_token_accuracy": 0.17410530298948287,
|
|
"num_tokens": 18299418.0,
|
|
"step": 10545
|
|
},
|
|
{
|
|
"entropy": 5.490515804290771,
|
|
"epoch": 0.8208519743240614,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000493802627376763,
|
|
"loss": 5.1043,
|
|
"mean_token_accuracy": 0.19295817613601685,
|
|
"num_tokens": 18308171.0,
|
|
"step": 10550
|
|
},
|
|
{
|
|
"entropy": 5.5814563751220705,
|
|
"epoch": 0.821241003695779,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004937961656008518,
|
|
"loss": 5.2829,
|
|
"mean_token_accuracy": 0.18063021302223206,
|
|
"num_tokens": 18317144.0,
|
|
"step": 10555
|
|
},
|
|
{
|
|
"entropy": 5.5784365177154545,
|
|
"epoch": 0.8216300330674966,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004937897005050573,
|
|
"loss": 5.3426,
|
|
"mean_token_accuracy": 0.17652396112680435,
|
|
"num_tokens": 18326648.0,
|
|
"step": 10560
|
|
},
|
|
{
|
|
"entropy": 5.636283016204834,
|
|
"epoch": 0.8220190624392142,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004937832320894772,
|
|
"loss": 5.312,
|
|
"mean_token_accuracy": 0.18171336203813554,
|
|
"num_tokens": 18335901.0,
|
|
"step": 10565
|
|
},
|
|
{
|
|
"entropy": 5.566133880615235,
|
|
"epoch": 0.8224080918109318,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004937767603542098,
|
|
"loss": 5.2277,
|
|
"mean_token_accuracy": 0.18326659202575685,
|
|
"num_tokens": 18344905.0,
|
|
"step": 10570
|
|
},
|
|
{
|
|
"entropy": 5.479534387588501,
|
|
"epoch": 0.8227971211826492,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004937702852993534,
|
|
"loss": 5.1877,
|
|
"mean_token_accuracy": 0.18900362253189087,
|
|
"num_tokens": 18353422.0,
|
|
"step": 10575
|
|
},
|
|
{
|
|
"entropy": 5.695352077484131,
|
|
"epoch": 0.8231861505543668,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000493763806925006,
|
|
"loss": 5.3623,
|
|
"mean_token_accuracy": 0.1664465293288231,
|
|
"num_tokens": 18361632.0,
|
|
"step": 10580
|
|
},
|
|
{
|
|
"entropy": 5.53762264251709,
|
|
"epoch": 0.8235751799260844,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004937573252312661,
|
|
"loss": 5.1894,
|
|
"mean_token_accuracy": 0.19036249071359634,
|
|
"num_tokens": 18370142.0,
|
|
"step": 10585
|
|
},
|
|
{
|
|
"entropy": 5.4955779075622555,
|
|
"epoch": 0.823964209297802,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000493750840218232,
|
|
"loss": 5.2349,
|
|
"mean_token_accuracy": 0.18061405271291733,
|
|
"num_tokens": 18378245.0,
|
|
"step": 10590
|
|
},
|
|
{
|
|
"entropy": 5.531733751296997,
|
|
"epoch": 0.8243532386695196,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004937443518860021,
|
|
"loss": 5.1946,
|
|
"mean_token_accuracy": 0.1911581426858902,
|
|
"num_tokens": 18386814.0,
|
|
"step": 10595
|
|
},
|
|
{
|
|
"entropy": 5.556150722503662,
|
|
"epoch": 0.8247422680412371,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004937378602346747,
|
|
"loss": 5.2209,
|
|
"mean_token_accuracy": 0.18298658430576326,
|
|
"num_tokens": 18396276.0,
|
|
"step": 10600
|
|
},
|
|
{
|
|
"entropy": 5.552563619613648,
|
|
"epoch": 0.8251312974129547,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004937313652643485,
|
|
"loss": 5.2183,
|
|
"mean_token_accuracy": 0.18201106637716294,
|
|
"num_tokens": 18404445.0,
|
|
"step": 10605
|
|
},
|
|
{
|
|
"entropy": 5.528123998641968,
|
|
"epoch": 0.8255203267846722,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000493724866975122,
|
|
"loss": 5.1337,
|
|
"mean_token_accuracy": 0.1917639896273613,
|
|
"num_tokens": 18412870.0,
|
|
"step": 10610
|
|
},
|
|
{
|
|
"entropy": 5.5436375617980955,
|
|
"epoch": 0.8259093561563898,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004937183653670937,
|
|
"loss": 5.2595,
|
|
"mean_token_accuracy": 0.18410644680261612,
|
|
"num_tokens": 18421084.0,
|
|
"step": 10615
|
|
},
|
|
{
|
|
"entropy": 5.524842262268066,
|
|
"epoch": 0.8262983855281074,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004937118604403623,
|
|
"loss": 5.2877,
|
|
"mean_token_accuracy": 0.17960087060928345,
|
|
"num_tokens": 18429869.0,
|
|
"step": 10620
|
|
},
|
|
{
|
|
"entropy": 5.540694093704223,
|
|
"epoch": 0.8266874148998249,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004937053521950266,
|
|
"loss": 5.1499,
|
|
"mean_token_accuracy": 0.1879689648747444,
|
|
"num_tokens": 18438747.0,
|
|
"step": 10625
|
|
},
|
|
{
|
|
"entropy": 5.6041404724121096,
|
|
"epoch": 0.8270764442715425,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004936988406311854,
|
|
"loss": 5.3532,
|
|
"mean_token_accuracy": 0.17607826888561248,
|
|
"num_tokens": 18447241.0,
|
|
"step": 10630
|
|
},
|
|
{
|
|
"entropy": 5.625930404663086,
|
|
"epoch": 0.8274654736432601,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004936923257489373,
|
|
"loss": 5.3744,
|
|
"mean_token_accuracy": 0.17208832800388335,
|
|
"num_tokens": 18455757.0,
|
|
"step": 10635
|
|
},
|
|
{
|
|
"entropy": 5.518155956268311,
|
|
"epoch": 0.8278545030149776,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004936858075483811,
|
|
"loss": 5.211,
|
|
"mean_token_accuracy": 0.1866015300154686,
|
|
"num_tokens": 18463863.0,
|
|
"step": 10640
|
|
},
|
|
{
|
|
"entropy": 5.5533936500549315,
|
|
"epoch": 0.8282435323866952,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000493679286029616,
|
|
"loss": 5.3891,
|
|
"mean_token_accuracy": 0.17119386345148085,
|
|
"num_tokens": 18472396.0,
|
|
"step": 10645
|
|
},
|
|
{
|
|
"entropy": 5.640747547149658,
|
|
"epoch": 0.8286325617584127,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004936727611927407,
|
|
"loss": 5.2427,
|
|
"mean_token_accuracy": 0.175209204852581,
|
|
"num_tokens": 18480625.0,
|
|
"step": 10650
|
|
},
|
|
{
|
|
"entropy": 5.61053056716919,
|
|
"epoch": 0.8290215911301303,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004936662330378546,
|
|
"loss": 5.3087,
|
|
"mean_token_accuracy": 0.1735701560974121,
|
|
"num_tokens": 18489878.0,
|
|
"step": 10655
|
|
},
|
|
{
|
|
"entropy": 5.51786322593689,
|
|
"epoch": 0.8294106205018479,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004936597015650561,
|
|
"loss": 5.2001,
|
|
"mean_token_accuracy": 0.1842064917087555,
|
|
"num_tokens": 18498873.0,
|
|
"step": 10660
|
|
},
|
|
{
|
|
"entropy": 5.62124195098877,
|
|
"epoch": 0.8297996498735655,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004936531667744448,
|
|
"loss": 5.3311,
|
|
"mean_token_accuracy": 0.17280071675777436,
|
|
"num_tokens": 18507716.0,
|
|
"step": 10665
|
|
},
|
|
{
|
|
"entropy": 5.5693971633911135,
|
|
"epoch": 0.8301886792452831,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004936466286661197,
|
|
"loss": 5.1568,
|
|
"mean_token_accuracy": 0.19043404161930083,
|
|
"num_tokens": 18516547.0,
|
|
"step": 10670
|
|
},
|
|
{
|
|
"entropy": 5.5463659286499025,
|
|
"epoch": 0.8305777086170005,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00049364008724018,
|
|
"loss": 5.329,
|
|
"mean_token_accuracy": 0.17302707582712173,
|
|
"num_tokens": 18525714.0,
|
|
"step": 10675
|
|
},
|
|
{
|
|
"entropy": 5.606787633895874,
|
|
"epoch": 0.8309667379887181,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000493633542496725,
|
|
"loss": 5.3393,
|
|
"mean_token_accuracy": 0.18241952061653138,
|
|
"num_tokens": 18534981.0,
|
|
"step": 10680
|
|
},
|
|
{
|
|
"entropy": 5.614515066146851,
|
|
"epoch": 0.8313557673604357,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004936269944358539,
|
|
"loss": 5.2568,
|
|
"mean_token_accuracy": 0.18250710964202882,
|
|
"num_tokens": 18543599.0,
|
|
"step": 10685
|
|
},
|
|
{
|
|
"entropy": 5.5610284328460695,
|
|
"epoch": 0.8317447967321533,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004936204430576664,
|
|
"loss": 5.2429,
|
|
"mean_token_accuracy": 0.18756332397460937,
|
|
"num_tokens": 18552207.0,
|
|
"step": 10690
|
|
},
|
|
{
|
|
"entropy": 5.532431745529175,
|
|
"epoch": 0.8321338261038709,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004936138883622614,
|
|
"loss": 5.2997,
|
|
"mean_token_accuracy": 0.17762846350669861,
|
|
"num_tokens": 18560421.0,
|
|
"step": 10695
|
|
},
|
|
{
|
|
"entropy": 5.552207374572754,
|
|
"epoch": 0.8325228554755884,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004936073303497387,
|
|
"loss": 5.1879,
|
|
"mean_token_accuracy": 0.19418384432792662,
|
|
"num_tokens": 18568812.0,
|
|
"step": 10700
|
|
},
|
|
{
|
|
"entropy": 5.597041654586792,
|
|
"epoch": 0.8329118848473059,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004936007690201976,
|
|
"loss": 5.1809,
|
|
"mean_token_accuracy": 0.18028334379196168,
|
|
"num_tokens": 18577077.0,
|
|
"step": 10705
|
|
},
|
|
{
|
|
"entropy": 5.587600755691528,
|
|
"epoch": 0.8333009142190235,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000493594204373738,
|
|
"loss": 5.3063,
|
|
"mean_token_accuracy": 0.18268045634031296,
|
|
"num_tokens": 18585754.0,
|
|
"step": 10710
|
|
},
|
|
{
|
|
"entropy": 5.5249193668365475,
|
|
"epoch": 0.8336899435907411,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004935876364104591,
|
|
"loss": 5.1758,
|
|
"mean_token_accuracy": 0.18650716692209243,
|
|
"num_tokens": 18594578.0,
|
|
"step": 10715
|
|
},
|
|
{
|
|
"entropy": 5.610929346084594,
|
|
"epoch": 0.8340789729624587,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004935810651304608,
|
|
"loss": 5.2808,
|
|
"mean_token_accuracy": 0.17683386504650117,
|
|
"num_tokens": 18603810.0,
|
|
"step": 10720
|
|
},
|
|
{
|
|
"entropy": 5.6428618907928465,
|
|
"epoch": 0.8344680023341763,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004935744905338427,
|
|
"loss": 5.2707,
|
|
"mean_token_accuracy": 0.1749935641884804,
|
|
"num_tokens": 18612870.0,
|
|
"step": 10725
|
|
},
|
|
{
|
|
"entropy": 5.568986654281616,
|
|
"epoch": 0.8348570317058938,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004935679126207046,
|
|
"loss": 5.321,
|
|
"mean_token_accuracy": 0.183121457695961,
|
|
"num_tokens": 18621353.0,
|
|
"step": 10730
|
|
},
|
|
{
|
|
"entropy": 5.484223747253418,
|
|
"epoch": 0.8352460610776113,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004935613313911463,
|
|
"loss": 5.1993,
|
|
"mean_token_accuracy": 0.18471705168485641,
|
|
"num_tokens": 18630152.0,
|
|
"step": 10735
|
|
},
|
|
{
|
|
"entropy": 5.574936437606811,
|
|
"epoch": 0.8356350904493289,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004935547468452678,
|
|
"loss": 5.2353,
|
|
"mean_token_accuracy": 0.18468862175941467,
|
|
"num_tokens": 18639278.0,
|
|
"step": 10740
|
|
},
|
|
{
|
|
"entropy": 5.602726650238037,
|
|
"epoch": 0.8360241198210465,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004935481589831688,
|
|
"loss": 5.2411,
|
|
"mean_token_accuracy": 0.18399454802274703,
|
|
"num_tokens": 18647436.0,
|
|
"step": 10745
|
|
},
|
|
{
|
|
"entropy": 5.6336143016815186,
|
|
"epoch": 0.8364131491927641,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004935415678049492,
|
|
"loss": 5.2632,
|
|
"mean_token_accuracy": 0.1739118590950966,
|
|
"num_tokens": 18655532.0,
|
|
"step": 10750
|
|
},
|
|
{
|
|
"entropy": 5.601388788223266,
|
|
"epoch": 0.8368021785644816,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004935349733107094,
|
|
"loss": 5.2894,
|
|
"mean_token_accuracy": 0.1812187984585762,
|
|
"num_tokens": 18664827.0,
|
|
"step": 10755
|
|
},
|
|
{
|
|
"entropy": 5.541911458969116,
|
|
"epoch": 0.8371912079361992,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000493528375500549,
|
|
"loss": 5.2215,
|
|
"mean_token_accuracy": 0.1848923996090889,
|
|
"num_tokens": 18673535.0,
|
|
"step": 10760
|
|
},
|
|
{
|
|
"entropy": 5.552118492126465,
|
|
"epoch": 0.8375802373079168,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004935217743745685,
|
|
"loss": 5.3898,
|
|
"mean_token_accuracy": 0.16902155578136444,
|
|
"num_tokens": 18682223.0,
|
|
"step": 10765
|
|
},
|
|
{
|
|
"entropy": 5.61554102897644,
|
|
"epoch": 0.8379692666796343,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004935151699328677,
|
|
"loss": 5.2767,
|
|
"mean_token_accuracy": 0.18176391273736953,
|
|
"num_tokens": 18690847.0,
|
|
"step": 10770
|
|
},
|
|
{
|
|
"entropy": 5.641661310195923,
|
|
"epoch": 0.8383582960513519,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004935085621755471,
|
|
"loss": 5.2966,
|
|
"mean_token_accuracy": 0.17963741570711136,
|
|
"num_tokens": 18699658.0,
|
|
"step": 10775
|
|
},
|
|
{
|
|
"entropy": 5.578431844711304,
|
|
"epoch": 0.8387473254230694,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000493501951102707,
|
|
"loss": 5.2742,
|
|
"mean_token_accuracy": 0.1794950932264328,
|
|
"num_tokens": 18708396.0,
|
|
"step": 10780
|
|
},
|
|
{
|
|
"entropy": 5.544351625442505,
|
|
"epoch": 0.839136354794787,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004934953367144474,
|
|
"loss": 5.2783,
|
|
"mean_token_accuracy": 0.18206384629011155,
|
|
"num_tokens": 18717185.0,
|
|
"step": 10785
|
|
},
|
|
{
|
|
"entropy": 5.63560905456543,
|
|
"epoch": 0.8395253841665046,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004934887190108688,
|
|
"loss": 5.231,
|
|
"mean_token_accuracy": 0.18738207668066026,
|
|
"num_tokens": 18725493.0,
|
|
"step": 10790
|
|
},
|
|
{
|
|
"entropy": 5.556916856765747,
|
|
"epoch": 0.8399144135382222,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004934820979920719,
|
|
"loss": 5.2103,
|
|
"mean_token_accuracy": 0.18609555065631866,
|
|
"num_tokens": 18733843.0,
|
|
"step": 10795
|
|
},
|
|
{
|
|
"entropy": 5.542183446884155,
|
|
"epoch": 0.8403034429099397,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004934754736581567,
|
|
"loss": 5.2885,
|
|
"mean_token_accuracy": 0.17779247760772704,
|
|
"num_tokens": 18742226.0,
|
|
"step": 10800
|
|
},
|
|
{
|
|
"entropy": 5.645714521408081,
|
|
"epoch": 0.8406924722816572,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000493468846009224,
|
|
"loss": 5.3957,
|
|
"mean_token_accuracy": 0.177981199324131,
|
|
"num_tokens": 18751117.0,
|
|
"step": 10805
|
|
},
|
|
{
|
|
"entropy": 5.56971435546875,
|
|
"epoch": 0.8410815016533748,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004934622150453742,
|
|
"loss": 5.2457,
|
|
"mean_token_accuracy": 0.1807874247431755,
|
|
"num_tokens": 18759244.0,
|
|
"step": 10810
|
|
},
|
|
{
|
|
"entropy": 5.562168884277344,
|
|
"epoch": 0.8414705310250924,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000493455580766708,
|
|
"loss": 5.3012,
|
|
"mean_token_accuracy": 0.17611841708421708,
|
|
"num_tokens": 18768107.0,
|
|
"step": 10815
|
|
},
|
|
{
|
|
"entropy": 5.514830827713013,
|
|
"epoch": 0.84185956039681,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004934489431733262,
|
|
"loss": 5.142,
|
|
"mean_token_accuracy": 0.19034633338451384,
|
|
"num_tokens": 18777419.0,
|
|
"step": 10820
|
|
},
|
|
{
|
|
"entropy": 5.557232809066773,
|
|
"epoch": 0.8422485897685276,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004934423022653293,
|
|
"loss": 5.2635,
|
|
"mean_token_accuracy": 0.18100958913564683,
|
|
"num_tokens": 18786410.0,
|
|
"step": 10825
|
|
},
|
|
{
|
|
"entropy": 5.578015851974487,
|
|
"epoch": 0.842637619140245,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004934356580428182,
|
|
"loss": 5.2297,
|
|
"mean_token_accuracy": 0.1862280249595642,
|
|
"num_tokens": 18794409.0,
|
|
"step": 10830
|
|
},
|
|
{
|
|
"entropy": 5.559137439727783,
|
|
"epoch": 0.8430266485119626,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004934290105058937,
|
|
"loss": 5.2897,
|
|
"mean_token_accuracy": 0.17958732396364213,
|
|
"num_tokens": 18803561.0,
|
|
"step": 10835
|
|
},
|
|
{
|
|
"entropy": 5.567430448532105,
|
|
"epoch": 0.8434156778836802,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004934223596546565,
|
|
"loss": 5.2707,
|
|
"mean_token_accuracy": 0.17618342638015747,
|
|
"num_tokens": 18812096.0,
|
|
"step": 10840
|
|
},
|
|
{
|
|
"entropy": 5.5775820255279545,
|
|
"epoch": 0.8438047072553978,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004934157054892077,
|
|
"loss": 5.2837,
|
|
"mean_token_accuracy": 0.17901571393013,
|
|
"num_tokens": 18820506.0,
|
|
"step": 10845
|
|
},
|
|
{
|
|
"entropy": 5.6024017333984375,
|
|
"epoch": 0.8441937366271154,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004934090480096482,
|
|
"loss": 5.2812,
|
|
"mean_token_accuracy": 0.1773514449596405,
|
|
"num_tokens": 18829437.0,
|
|
"step": 10850
|
|
},
|
|
{
|
|
"entropy": 5.66842794418335,
|
|
"epoch": 0.8445827659988329,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004934023872160791,
|
|
"loss": 5.3758,
|
|
"mean_token_accuracy": 0.17594860941171647,
|
|
"num_tokens": 18838759.0,
|
|
"step": 10855
|
|
},
|
|
{
|
|
"entropy": 5.5276306629180905,
|
|
"epoch": 0.8449717953705504,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004933957231086014,
|
|
"loss": 5.2824,
|
|
"mean_token_accuracy": 0.18068666160106658,
|
|
"num_tokens": 18847000.0,
|
|
"step": 10860
|
|
},
|
|
{
|
|
"entropy": 5.623405265808105,
|
|
"epoch": 0.845360824742268,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004933890556873161,
|
|
"loss": 5.3551,
|
|
"mean_token_accuracy": 0.17632968872785568,
|
|
"num_tokens": 18855370.0,
|
|
"step": 10865
|
|
},
|
|
{
|
|
"entropy": 5.687759256362915,
|
|
"epoch": 0.8457498541139856,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004933823849523246,
|
|
"loss": 5.4133,
|
|
"mean_token_accuracy": 0.17654733955860138,
|
|
"num_tokens": 18863825.0,
|
|
"step": 10870
|
|
},
|
|
{
|
|
"entropy": 5.577779293060303,
|
|
"epoch": 0.8461388834857032,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004933757109037279,
|
|
"loss": 5.1649,
|
|
"mean_token_accuracy": 0.18300394713878632,
|
|
"num_tokens": 18872088.0,
|
|
"step": 10875
|
|
},
|
|
{
|
|
"entropy": 5.532320165634156,
|
|
"epoch": 0.8465279128574207,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004933690335416274,
|
|
"loss": 5.1491,
|
|
"mean_token_accuracy": 0.19310869574546813,
|
|
"num_tokens": 18880472.0,
|
|
"step": 10880
|
|
},
|
|
{
|
|
"entropy": 5.597385549545288,
|
|
"epoch": 0.8469169422291383,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004933623528661245,
|
|
"loss": 5.3645,
|
|
"mean_token_accuracy": 0.17753133773803711,
|
|
"num_tokens": 18889822.0,
|
|
"step": 10885
|
|
},
|
|
{
|
|
"entropy": 5.655607271194458,
|
|
"epoch": 0.8473059716008559,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004933556688773203,
|
|
"loss": 5.2962,
|
|
"mean_token_accuracy": 0.17769573032855987,
|
|
"num_tokens": 18897542.0,
|
|
"step": 10890
|
|
},
|
|
{
|
|
"entropy": 5.542865037918091,
|
|
"epoch": 0.8476950009725734,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004933489815753165,
|
|
"loss": 5.3324,
|
|
"mean_token_accuracy": 0.17968873977661132,
|
|
"num_tokens": 18906330.0,
|
|
"step": 10895
|
|
},
|
|
{
|
|
"entropy": 5.562378835678101,
|
|
"epoch": 0.848084030344291,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004933422909602143,
|
|
"loss": 5.1734,
|
|
"mean_token_accuracy": 0.1919698789715767,
|
|
"num_tokens": 18914176.0,
|
|
"step": 10900
|
|
},
|
|
{
|
|
"entropy": 5.519755268096924,
|
|
"epoch": 0.8484730597160085,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004933355970321155,
|
|
"loss": 5.2027,
|
|
"mean_token_accuracy": 0.19044993817806244,
|
|
"num_tokens": 18922233.0,
|
|
"step": 10905
|
|
},
|
|
{
|
|
"entropy": 5.433318853378296,
|
|
"epoch": 0.8488620890877261,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004933288997911215,
|
|
"loss": 5.2367,
|
|
"mean_token_accuracy": 0.18599033653736113,
|
|
"num_tokens": 18930742.0,
|
|
"step": 10910
|
|
},
|
|
{
|
|
"entropy": 5.564408254623413,
|
|
"epoch": 0.8492511184594437,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004933221992373338,
|
|
"loss": 5.1957,
|
|
"mean_token_accuracy": 0.18545434772968292,
|
|
"num_tokens": 18938879.0,
|
|
"step": 10915
|
|
},
|
|
{
|
|
"entropy": 5.717005825042724,
|
|
"epoch": 0.8496401478311613,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004933154953708544,
|
|
"loss": 5.3702,
|
|
"mean_token_accuracy": 0.16363996118307114,
|
|
"num_tokens": 18947753.0,
|
|
"step": 10920
|
|
},
|
|
{
|
|
"entropy": 5.589132356643677,
|
|
"epoch": 0.8500291772028788,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004933087881917848,
|
|
"loss": 5.2418,
|
|
"mean_token_accuracy": 0.17988715022802354,
|
|
"num_tokens": 18956805.0,
|
|
"step": 10925
|
|
},
|
|
{
|
|
"entropy": 5.512399101257325,
|
|
"epoch": 0.8504182065745964,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004933020777002268,
|
|
"loss": 5.2246,
|
|
"mean_token_accuracy": 0.1815769702196121,
|
|
"num_tokens": 18965683.0,
|
|
"step": 10930
|
|
},
|
|
{
|
|
"entropy": 5.5154742240905765,
|
|
"epoch": 0.8508072359463139,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004932953638962823,
|
|
"loss": 5.2143,
|
|
"mean_token_accuracy": 0.18446161597967148,
|
|
"num_tokens": 18973873.0,
|
|
"step": 10935
|
|
},
|
|
{
|
|
"entropy": 5.474437093734741,
|
|
"epoch": 0.8511962653180315,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000493288646780053,
|
|
"loss": 5.1639,
|
|
"mean_token_accuracy": 0.18976201564073564,
|
|
"num_tokens": 18982097.0,
|
|
"step": 10940
|
|
},
|
|
{
|
|
"entropy": 5.501852941513062,
|
|
"epoch": 0.8515852946897491,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004932819263516409,
|
|
"loss": 5.2165,
|
|
"mean_token_accuracy": 0.18093420565128326,
|
|
"num_tokens": 18991019.0,
|
|
"step": 10945
|
|
},
|
|
{
|
|
"entropy": 5.600112009048462,
|
|
"epoch": 0.8519743240614667,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004932752026111481,
|
|
"loss": 5.2165,
|
|
"mean_token_accuracy": 0.18231619596481324,
|
|
"num_tokens": 18999231.0,
|
|
"step": 10950
|
|
},
|
|
{
|
|
"entropy": 5.6302252292633055,
|
|
"epoch": 0.8523633534331843,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004932684755586765,
|
|
"loss": 5.3031,
|
|
"mean_token_accuracy": 0.18163848519325257,
|
|
"num_tokens": 19007807.0,
|
|
"step": 10955
|
|
},
|
|
{
|
|
"entropy": 5.535033559799194,
|
|
"epoch": 0.8527523828049017,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004932617451943282,
|
|
"loss": 5.2752,
|
|
"mean_token_accuracy": 0.1835549756884575,
|
|
"num_tokens": 19017908.0,
|
|
"step": 10960
|
|
},
|
|
{
|
|
"entropy": 5.522093915939331,
|
|
"epoch": 0.8531414121766193,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004932550115182053,
|
|
"loss": 5.2868,
|
|
"mean_token_accuracy": 0.17447712868452073,
|
|
"num_tokens": 19026999.0,
|
|
"step": 10965
|
|
},
|
|
{
|
|
"entropy": 5.500233602523804,
|
|
"epoch": 0.8535304415483369,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00049324827453041,
|
|
"loss": 5.1884,
|
|
"mean_token_accuracy": 0.19003772139549255,
|
|
"num_tokens": 19035738.0,
|
|
"step": 10970
|
|
},
|
|
{
|
|
"entropy": 5.527360963821411,
|
|
"epoch": 0.8539194709200545,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004932415342310446,
|
|
"loss": 5.2773,
|
|
"mean_token_accuracy": 0.18088242411613464,
|
|
"num_tokens": 19044530.0,
|
|
"step": 10975
|
|
},
|
|
{
|
|
"entropy": 5.537290048599243,
|
|
"epoch": 0.8543085002917721,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004932347906202111,
|
|
"loss": 5.2552,
|
|
"mean_token_accuracy": 0.18226035833358764,
|
|
"num_tokens": 19053306.0,
|
|
"step": 10980
|
|
},
|
|
{
|
|
"entropy": 5.610524988174438,
|
|
"epoch": 0.8546975296634896,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000493228043698012,
|
|
"loss": 5.2643,
|
|
"mean_token_accuracy": 0.17798605263233186,
|
|
"num_tokens": 19062172.0,
|
|
"step": 10985
|
|
},
|
|
{
|
|
"entropy": 5.441015672683716,
|
|
"epoch": 0.8550865590352071,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004932212934645498,
|
|
"loss": 5.0494,
|
|
"mean_token_accuracy": 0.1973587304353714,
|
|
"num_tokens": 19070804.0,
|
|
"step": 10990
|
|
},
|
|
{
|
|
"entropy": 5.550571537017822,
|
|
"epoch": 0.8554755884069247,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004932145399199268,
|
|
"loss": 5.2045,
|
|
"mean_token_accuracy": 0.18815929740667342,
|
|
"num_tokens": 19079055.0,
|
|
"step": 10995
|
|
},
|
|
{
|
|
"entropy": 5.519578647613526,
|
|
"epoch": 0.8558646177786423,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004932077830642455,
|
|
"loss": 5.1932,
|
|
"mean_token_accuracy": 0.18200305253267288,
|
|
"num_tokens": 19087459.0,
|
|
"step": 11000
|
|
},
|
|
{
|
|
"entropy": 5.436576414108276,
|
|
"epoch": 0.8562536471503599,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004932010228976084,
|
|
"loss": 5.0968,
|
|
"mean_token_accuracy": 0.18955010622739793,
|
|
"num_tokens": 19096271.0,
|
|
"step": 11005
|
|
},
|
|
{
|
|
"entropy": 5.591752910614014,
|
|
"epoch": 0.8566426765220774,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000493194259420118,
|
|
"loss": 5.2681,
|
|
"mean_token_accuracy": 0.17966681718826294,
|
|
"num_tokens": 19105257.0,
|
|
"step": 11010
|
|
},
|
|
{
|
|
"entropy": 5.586348581314087,
|
|
"epoch": 0.857031705893795,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000493187492631877,
|
|
"loss": 5.2202,
|
|
"mean_token_accuracy": 0.18629482686519622,
|
|
"num_tokens": 19113673.0,
|
|
"step": 11015
|
|
},
|
|
{
|
|
"entropy": 5.532885360717773,
|
|
"epoch": 0.8574207352655125,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004931807225329882,
|
|
"loss": 5.2143,
|
|
"mean_token_accuracy": 0.18833238929510115,
|
|
"num_tokens": 19121635.0,
|
|
"step": 11020
|
|
},
|
|
{
|
|
"entropy": 5.533400058746338,
|
|
"epoch": 0.8578097646372301,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004931739491235541,
|
|
"loss": 5.2485,
|
|
"mean_token_accuracy": 0.18850345611572267,
|
|
"num_tokens": 19130097.0,
|
|
"step": 11025
|
|
},
|
|
{
|
|
"entropy": 5.49743390083313,
|
|
"epoch": 0.8581987940089477,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004931671724036777,
|
|
"loss": 5.1609,
|
|
"mean_token_accuracy": 0.18554106056690217,
|
|
"num_tokens": 19138349.0,
|
|
"step": 11030
|
|
},
|
|
{
|
|
"entropy": 5.522438383102417,
|
|
"epoch": 0.8585878233806652,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004931603923734616,
|
|
"loss": 5.2654,
|
|
"mean_token_accuracy": 0.18063793629407882,
|
|
"num_tokens": 19146948.0,
|
|
"step": 11035
|
|
},
|
|
{
|
|
"entropy": 5.499011421203614,
|
|
"epoch": 0.8589768527523828,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004931536090330088,
|
|
"loss": 5.1995,
|
|
"mean_token_accuracy": 0.19050881117582322,
|
|
"num_tokens": 19155372.0,
|
|
"step": 11040
|
|
},
|
|
{
|
|
"entropy": 5.645586442947388,
|
|
"epoch": 0.8593658821241004,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004931468223824222,
|
|
"loss": 5.3259,
|
|
"mean_token_accuracy": 0.17474284917116165,
|
|
"num_tokens": 19163634.0,
|
|
"step": 11045
|
|
},
|
|
{
|
|
"entropy": 5.665350770950317,
|
|
"epoch": 0.859754911495818,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004931400324218048,
|
|
"loss": 5.3209,
|
|
"mean_token_accuracy": 0.1806083530187607,
|
|
"num_tokens": 19171582.0,
|
|
"step": 11050
|
|
},
|
|
{
|
|
"entropy": 5.589558506011963,
|
|
"epoch": 0.8601439408675355,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004931332391512597,
|
|
"loss": 5.3086,
|
|
"mean_token_accuracy": 0.17354440689086914,
|
|
"num_tokens": 19181136.0,
|
|
"step": 11055
|
|
},
|
|
{
|
|
"entropy": 5.591264867782593,
|
|
"epoch": 0.860532970239253,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004931264425708897,
|
|
"loss": 5.3011,
|
|
"mean_token_accuracy": 0.17281284034252167,
|
|
"num_tokens": 19189389.0,
|
|
"step": 11060
|
|
},
|
|
{
|
|
"entropy": 5.5910852432250975,
|
|
"epoch": 0.8609219996109706,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004931196426807983,
|
|
"loss": 5.2882,
|
|
"mean_token_accuracy": 0.17940365821123122,
|
|
"num_tokens": 19198315.0,
|
|
"step": 11065
|
|
},
|
|
{
|
|
"entropy": 5.651271152496338,
|
|
"epoch": 0.8613110289826882,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004931128394810884,
|
|
"loss": 5.3332,
|
|
"mean_token_accuracy": 0.1748519644141197,
|
|
"num_tokens": 19207234.0,
|
|
"step": 11070
|
|
},
|
|
{
|
|
"entropy": 5.581159782409668,
|
|
"epoch": 0.8617000583544058,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004931060329718634,
|
|
"loss": 5.3228,
|
|
"mean_token_accuracy": 0.17085424363613128,
|
|
"num_tokens": 19216552.0,
|
|
"step": 11075
|
|
},
|
|
{
|
|
"entropy": 5.557453680038452,
|
|
"epoch": 0.8620890877261234,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004930992231532265,
|
|
"loss": 5.2677,
|
|
"mean_token_accuracy": 0.1751312792301178,
|
|
"num_tokens": 19225237.0,
|
|
"step": 11080
|
|
},
|
|
{
|
|
"entropy": 5.515236663818359,
|
|
"epoch": 0.8624781170978408,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000493092410025281,
|
|
"loss": 5.1836,
|
|
"mean_token_accuracy": 0.19219851195812226,
|
|
"num_tokens": 19233246.0,
|
|
"step": 11085
|
|
},
|
|
{
|
|
"entropy": 5.5010457038879395,
|
|
"epoch": 0.8628671464695584,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004930855935881302,
|
|
"loss": 5.2127,
|
|
"mean_token_accuracy": 0.18923863768577576,
|
|
"num_tokens": 19241748.0,
|
|
"step": 11090
|
|
},
|
|
{
|
|
"entropy": 5.624505949020386,
|
|
"epoch": 0.863256175841276,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004930787738418777,
|
|
"loss": 5.3639,
|
|
"mean_token_accuracy": 0.17303334623575212,
|
|
"num_tokens": 19250259.0,
|
|
"step": 11095
|
|
},
|
|
{
|
|
"entropy": 5.683621215820312,
|
|
"epoch": 0.8636452052129936,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004930719507866269,
|
|
"loss": 5.4206,
|
|
"mean_token_accuracy": 0.1744420424103737,
|
|
"num_tokens": 19259266.0,
|
|
"step": 11100
|
|
},
|
|
{
|
|
"entropy": 5.6021300792694095,
|
|
"epoch": 0.8640342345847112,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004930651244224814,
|
|
"loss": 5.2495,
|
|
"mean_token_accuracy": 0.18053482621908187,
|
|
"num_tokens": 19268099.0,
|
|
"step": 11105
|
|
},
|
|
{
|
|
"entropy": 5.544763803482056,
|
|
"epoch": 0.8644232639564287,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004930582947495448,
|
|
"loss": 5.1575,
|
|
"mean_token_accuracy": 0.1893578976392746,
|
|
"num_tokens": 19276894.0,
|
|
"step": 11110
|
|
},
|
|
{
|
|
"entropy": 5.4840662479400635,
|
|
"epoch": 0.8648122933281462,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004930514617679206,
|
|
"loss": 5.2185,
|
|
"mean_token_accuracy": 0.18783557116985322,
|
|
"num_tokens": 19285724.0,
|
|
"step": 11115
|
|
},
|
|
{
|
|
"entropy": 5.5312365055084225,
|
|
"epoch": 0.8652013226998638,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004930446254777125,
|
|
"loss": 5.1477,
|
|
"mean_token_accuracy": 0.19058193862438202,
|
|
"num_tokens": 19294468.0,
|
|
"step": 11120
|
|
},
|
|
{
|
|
"entropy": 5.5762135028839115,
|
|
"epoch": 0.8655903520715814,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004930377858790242,
|
|
"loss": 5.2015,
|
|
"mean_token_accuracy": 0.18814353048801422,
|
|
"num_tokens": 19303575.0,
|
|
"step": 11125
|
|
},
|
|
{
|
|
"entropy": 5.6263727188110355,
|
|
"epoch": 0.865979381443299,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004930309429719595,
|
|
"loss": 5.3576,
|
|
"mean_token_accuracy": 0.1824032887816429,
|
|
"num_tokens": 19312778.0,
|
|
"step": 11130
|
|
},
|
|
{
|
|
"entropy": 5.603872346878052,
|
|
"epoch": 0.8663684108150166,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004930240967566224,
|
|
"loss": 5.2345,
|
|
"mean_token_accuracy": 0.17890094667673112,
|
|
"num_tokens": 19320725.0,
|
|
"step": 11135
|
|
},
|
|
{
|
|
"entropy": 5.565314292907715,
|
|
"epoch": 0.8667574401867341,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004930172472331167,
|
|
"loss": 5.2472,
|
|
"mean_token_accuracy": 0.18859666287899018,
|
|
"num_tokens": 19329842.0,
|
|
"step": 11140
|
|
},
|
|
{
|
|
"entropy": 5.544046688079834,
|
|
"epoch": 0.8671464695584516,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004930103944015463,
|
|
"loss": 5.2522,
|
|
"mean_token_accuracy": 0.18350773751735688,
|
|
"num_tokens": 19338136.0,
|
|
"step": 11145
|
|
},
|
|
{
|
|
"entropy": 5.539253520965576,
|
|
"epoch": 0.8675354989301692,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004930035382620149,
|
|
"loss": 5.218,
|
|
"mean_token_accuracy": 0.18330558389425278,
|
|
"num_tokens": 19346597.0,
|
|
"step": 11150
|
|
},
|
|
{
|
|
"entropy": 5.540123414993286,
|
|
"epoch": 0.8679245283018868,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000492996678814627,
|
|
"loss": 5.2079,
|
|
"mean_token_accuracy": 0.18596190661191941,
|
|
"num_tokens": 19355595.0,
|
|
"step": 11155
|
|
},
|
|
{
|
|
"entropy": 5.5605556011199955,
|
|
"epoch": 0.8683135576736044,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004929898160594865,
|
|
"loss": 5.279,
|
|
"mean_token_accuracy": 0.1812897726893425,
|
|
"num_tokens": 19364133.0,
|
|
"step": 11160
|
|
},
|
|
{
|
|
"entropy": 5.614044094085694,
|
|
"epoch": 0.8687025870453219,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004929829499966974,
|
|
"loss": 5.3125,
|
|
"mean_token_accuracy": 0.17573751956224443,
|
|
"num_tokens": 19373628.0,
|
|
"step": 11165
|
|
},
|
|
{
|
|
"entropy": 5.589564180374145,
|
|
"epoch": 0.8690916164170395,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004929760806263641,
|
|
"loss": 5.2587,
|
|
"mean_token_accuracy": 0.18214433491230012,
|
|
"num_tokens": 19381901.0,
|
|
"step": 11170
|
|
},
|
|
{
|
|
"entropy": 5.577784156799316,
|
|
"epoch": 0.8694806457887571,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004929692079485906,
|
|
"loss": 5.3356,
|
|
"mean_token_accuracy": 0.17620855271816255,
|
|
"num_tokens": 19390390.0,
|
|
"step": 11175
|
|
},
|
|
{
|
|
"entropy": 5.590073919296264,
|
|
"epoch": 0.8698696751604746,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004929623319634814,
|
|
"loss": 5.308,
|
|
"mean_token_accuracy": 0.17319257110357283,
|
|
"num_tokens": 19399858.0,
|
|
"step": 11180
|
|
},
|
|
{
|
|
"entropy": 5.546296644210815,
|
|
"epoch": 0.8702587045321922,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004929554526711407,
|
|
"loss": 5.2542,
|
|
"mean_token_accuracy": 0.17633968144655227,
|
|
"num_tokens": 19409062.0,
|
|
"step": 11185
|
|
},
|
|
{
|
|
"entropy": 5.503489637374878,
|
|
"epoch": 0.8706477339039097,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004929485700716729,
|
|
"loss": 5.218,
|
|
"mean_token_accuracy": 0.18555265814065933,
|
|
"num_tokens": 19417228.0,
|
|
"step": 11190
|
|
},
|
|
{
|
|
"entropy": 5.571311902999878,
|
|
"epoch": 0.8710367632756273,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004929416841651824,
|
|
"loss": 5.3247,
|
|
"mean_token_accuracy": 0.18117835223674775,
|
|
"num_tokens": 19426086.0,
|
|
"step": 11195
|
|
},
|
|
{
|
|
"entropy": 5.61510443687439,
|
|
"epoch": 0.8714257926473449,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004929347949517739,
|
|
"loss": 5.3117,
|
|
"mean_token_accuracy": 0.17909523248672485,
|
|
"num_tokens": 19435363.0,
|
|
"step": 11200
|
|
},
|
|
{
|
|
"entropy": 5.545312356948853,
|
|
"epoch": 0.8718148220190625,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004929279024315516,
|
|
"loss": 5.1139,
|
|
"mean_token_accuracy": 0.18786819279193878,
|
|
"num_tokens": 19443355.0,
|
|
"step": 11205
|
|
},
|
|
{
|
|
"entropy": 5.502433443069458,
|
|
"epoch": 0.87220385139078,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004929210066046204,
|
|
"loss": 5.1687,
|
|
"mean_token_accuracy": 0.1818842500448227,
|
|
"num_tokens": 19452217.0,
|
|
"step": 11210
|
|
},
|
|
{
|
|
"entropy": 5.608479261398315,
|
|
"epoch": 0.8725928807624975,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004929141074710847,
|
|
"loss": 5.3748,
|
|
"mean_token_accuracy": 0.17233697474002838,
|
|
"num_tokens": 19460034.0,
|
|
"step": 11215
|
|
},
|
|
{
|
|
"entropy": 5.5954773902893065,
|
|
"epoch": 0.8729819101342151,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004929072050310491,
|
|
"loss": 5.2977,
|
|
"mean_token_accuracy": 0.18093376159667968,
|
|
"num_tokens": 19468403.0,
|
|
"step": 11220
|
|
},
|
|
{
|
|
"entropy": 5.585196208953858,
|
|
"epoch": 0.8733709395059327,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004929002992846188,
|
|
"loss": 5.3213,
|
|
"mean_token_accuracy": 0.17999297082424165,
|
|
"num_tokens": 19477551.0,
|
|
"step": 11225
|
|
},
|
|
{
|
|
"entropy": 5.598291873931885,
|
|
"epoch": 0.8737599688776503,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004928933902318981,
|
|
"loss": 5.2184,
|
|
"mean_token_accuracy": 0.18642991483211518,
|
|
"num_tokens": 19486131.0,
|
|
"step": 11230
|
|
},
|
|
{
|
|
"entropy": 5.61588864326477,
|
|
"epoch": 0.8741489982493679,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000492886477872992,
|
|
"loss": 5.3513,
|
|
"mean_token_accuracy": 0.1688728526234627,
|
|
"num_tokens": 19496212.0,
|
|
"step": 11235
|
|
},
|
|
{
|
|
"entropy": 5.56214451789856,
|
|
"epoch": 0.8745380276210853,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004928795622080054,
|
|
"loss": 5.2042,
|
|
"mean_token_accuracy": 0.1845085084438324,
|
|
"num_tokens": 19504556.0,
|
|
"step": 11240
|
|
},
|
|
{
|
|
"entropy": 5.617821264266968,
|
|
"epoch": 0.8749270569928029,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004928726432370434,
|
|
"loss": 5.2609,
|
|
"mean_token_accuracy": 0.1788235515356064,
|
|
"num_tokens": 19512832.0,
|
|
"step": 11245
|
|
},
|
|
{
|
|
"entropy": 5.620820713043213,
|
|
"epoch": 0.8753160863645205,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004928657209602107,
|
|
"loss": 5.2655,
|
|
"mean_token_accuracy": 0.18020354360342025,
|
|
"num_tokens": 19521410.0,
|
|
"step": 11250
|
|
},
|
|
{
|
|
"entropy": 5.556787490844727,
|
|
"epoch": 0.8757051157362381,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004928587953776125,
|
|
"loss": 5.2555,
|
|
"mean_token_accuracy": 0.18206322193145752,
|
|
"num_tokens": 19529935.0,
|
|
"step": 11255
|
|
},
|
|
{
|
|
"entropy": 5.491008043289185,
|
|
"epoch": 0.8760941451079557,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004928518664893538,
|
|
"loss": 5.1554,
|
|
"mean_token_accuracy": 0.186825954914093,
|
|
"num_tokens": 19538330.0,
|
|
"step": 11260
|
|
},
|
|
{
|
|
"entropy": 5.522809934616089,
|
|
"epoch": 0.8764831744796732,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004928449342955397,
|
|
"loss": 5.1491,
|
|
"mean_token_accuracy": 0.18726811707019805,
|
|
"num_tokens": 19546860.0,
|
|
"step": 11265
|
|
},
|
|
{
|
|
"entropy": 5.57469539642334,
|
|
"epoch": 0.8768722038513908,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004928379987962756,
|
|
"loss": 5.249,
|
|
"mean_token_accuracy": 0.18167571127414703,
|
|
"num_tokens": 19554945.0,
|
|
"step": 11270
|
|
},
|
|
{
|
|
"entropy": 5.599477624893188,
|
|
"epoch": 0.8772612332231083,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004928310599916666,
|
|
"loss": 5.2726,
|
|
"mean_token_accuracy": 0.18034662455320358,
|
|
"num_tokens": 19563182.0,
|
|
"step": 11275
|
|
},
|
|
{
|
|
"entropy": 5.513549041748047,
|
|
"epoch": 0.8776502625948259,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004928241178818178,
|
|
"loss": 5.2566,
|
|
"mean_token_accuracy": 0.18222971856594086,
|
|
"num_tokens": 19571405.0,
|
|
"step": 11280
|
|
},
|
|
{
|
|
"entropy": 5.65979118347168,
|
|
"epoch": 0.8780392919665435,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004928171724668349,
|
|
"loss": 5.3253,
|
|
"mean_token_accuracy": 0.18145942240953444,
|
|
"num_tokens": 19580053.0,
|
|
"step": 11285
|
|
},
|
|
{
|
|
"entropy": 5.6746344566345215,
|
|
"epoch": 0.878428321338261,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004928102237468229,
|
|
"loss": 5.3502,
|
|
"mean_token_accuracy": 0.17783455401659012,
|
|
"num_tokens": 19588457.0,
|
|
"step": 11290
|
|
},
|
|
{
|
|
"entropy": 5.510228490829467,
|
|
"epoch": 0.8788173507099786,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004928032717218876,
|
|
"loss": 5.191,
|
|
"mean_token_accuracy": 0.18567302823066711,
|
|
"num_tokens": 19597608.0,
|
|
"step": 11295
|
|
},
|
|
{
|
|
"entropy": 5.530666351318359,
|
|
"epoch": 0.8792063800816962,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004927963163921343,
|
|
"loss": 5.2182,
|
|
"mean_token_accuracy": 0.1877909481525421,
|
|
"num_tokens": 19605904.0,
|
|
"step": 11300
|
|
},
|
|
{
|
|
"entropy": 5.585718584060669,
|
|
"epoch": 0.8795954094534137,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004927893577576685,
|
|
"loss": 5.2041,
|
|
"mean_token_accuracy": 0.17550091743469237,
|
|
"num_tokens": 19614660.0,
|
|
"step": 11305
|
|
},
|
|
{
|
|
"entropy": 5.533907270431518,
|
|
"epoch": 0.8799844388251313,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004927823958185959,
|
|
"loss": 5.1828,
|
|
"mean_token_accuracy": 0.19499629586935044,
|
|
"num_tokens": 19623210.0,
|
|
"step": 11310
|
|
},
|
|
{
|
|
"entropy": 5.558951330184937,
|
|
"epoch": 0.8803734681968488,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000492775430575022,
|
|
"loss": 5.2722,
|
|
"mean_token_accuracy": 0.17748644202947617,
|
|
"num_tokens": 19631747.0,
|
|
"step": 11315
|
|
},
|
|
{
|
|
"entropy": 5.6451085090637205,
|
|
"epoch": 0.8807624975685664,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004927684620270527,
|
|
"loss": 5.3576,
|
|
"mean_token_accuracy": 0.1731577232480049,
|
|
"num_tokens": 19639902.0,
|
|
"step": 11320
|
|
},
|
|
{
|
|
"entropy": 5.6624321937561035,
|
|
"epoch": 0.881151526940284,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004927614901747935,
|
|
"loss": 5.3697,
|
|
"mean_token_accuracy": 0.17460268884897232,
|
|
"num_tokens": 19648478.0,
|
|
"step": 11325
|
|
},
|
|
{
|
|
"entropy": 5.690453720092774,
|
|
"epoch": 0.8815405563120016,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004927545150183503,
|
|
"loss": 5.389,
|
|
"mean_token_accuracy": 0.17978238314390182,
|
|
"num_tokens": 19657467.0,
|
|
"step": 11330
|
|
},
|
|
{
|
|
"entropy": 5.718032169342041,
|
|
"epoch": 0.8819295856837192,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000492747536557829,
|
|
"loss": 5.3469,
|
|
"mean_token_accuracy": 0.16780038177967072,
|
|
"num_tokens": 19665382.0,
|
|
"step": 11335
|
|
},
|
|
{
|
|
"entropy": 5.562109756469726,
|
|
"epoch": 0.8823186150554367,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004927405547933353,
|
|
"loss": 5.1483,
|
|
"mean_token_accuracy": 0.1870612844824791,
|
|
"num_tokens": 19674486.0,
|
|
"step": 11340
|
|
},
|
|
{
|
|
"entropy": 5.597084808349609,
|
|
"epoch": 0.8827076444271542,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004927335697249753,
|
|
"loss": 5.1849,
|
|
"mean_token_accuracy": 0.18209384381771088,
|
|
"num_tokens": 19683060.0,
|
|
"step": 11345
|
|
},
|
|
{
|
|
"entropy": 5.4729695320129395,
|
|
"epoch": 0.8830966737988718,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004927265813528549,
|
|
"loss": 5.1536,
|
|
"mean_token_accuracy": 0.19034045487642287,
|
|
"num_tokens": 19691634.0,
|
|
"step": 11350
|
|
},
|
|
{
|
|
"entropy": 5.54167742729187,
|
|
"epoch": 0.8834857031705894,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004927195896770804,
|
|
"loss": 5.2583,
|
|
"mean_token_accuracy": 0.17653674483299256,
|
|
"num_tokens": 19699975.0,
|
|
"step": 11355
|
|
},
|
|
{
|
|
"entropy": 5.5695860385894775,
|
|
"epoch": 0.883874732542307,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004927125946977574,
|
|
"loss": 5.2123,
|
|
"mean_token_accuracy": 0.18081354349851608,
|
|
"num_tokens": 19708431.0,
|
|
"step": 11360
|
|
},
|
|
{
|
|
"entropy": 5.548543310165405,
|
|
"epoch": 0.8842637619140246,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004927055964149923,
|
|
"loss": 5.2326,
|
|
"mean_token_accuracy": 0.1743628427386284,
|
|
"num_tokens": 19717189.0,
|
|
"step": 11365
|
|
},
|
|
{
|
|
"entropy": 5.59026985168457,
|
|
"epoch": 0.884652791285742,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004926985948288914,
|
|
"loss": 5.2754,
|
|
"mean_token_accuracy": 0.18580946773290635,
|
|
"num_tokens": 19725855.0,
|
|
"step": 11370
|
|
},
|
|
{
|
|
"entropy": 5.547528028488159,
|
|
"epoch": 0.8850418206574596,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004926915899395608,
|
|
"loss": 5.204,
|
|
"mean_token_accuracy": 0.18512689471244811,
|
|
"num_tokens": 19734617.0,
|
|
"step": 11375
|
|
},
|
|
{
|
|
"entropy": 5.642363119125366,
|
|
"epoch": 0.8854308500291772,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004926845817471068,
|
|
"loss": 5.3033,
|
|
"mean_token_accuracy": 0.17751339375972747,
|
|
"num_tokens": 19743731.0,
|
|
"step": 11380
|
|
},
|
|
{
|
|
"entropy": 5.5991583347320555,
|
|
"epoch": 0.8858198794008948,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004926775702516358,
|
|
"loss": 5.2551,
|
|
"mean_token_accuracy": 0.18061378598213196,
|
|
"num_tokens": 19752336.0,
|
|
"step": 11385
|
|
},
|
|
{
|
|
"entropy": 5.555872297286987,
|
|
"epoch": 0.8862089087726124,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004926705554532541,
|
|
"loss": 5.2787,
|
|
"mean_token_accuracy": 0.1789202481508255,
|
|
"num_tokens": 19761488.0,
|
|
"step": 11390
|
|
},
|
|
{
|
|
"entropy": 5.5467212200164795,
|
|
"epoch": 0.8865979381443299,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004926635373520682,
|
|
"loss": 5.1844,
|
|
"mean_token_accuracy": 0.18448866307735443,
|
|
"num_tokens": 19770330.0,
|
|
"step": 11395
|
|
},
|
|
{
|
|
"entropy": 5.56444525718689,
|
|
"epoch": 0.8869869675160474,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004926565159481845,
|
|
"loss": 5.2244,
|
|
"mean_token_accuracy": 0.18237495124340058,
|
|
"num_tokens": 19779037.0,
|
|
"step": 11400
|
|
},
|
|
{
|
|
"entropy": 5.583184480667114,
|
|
"epoch": 0.887375996887765,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004926494912417097,
|
|
"loss": 5.3047,
|
|
"mean_token_accuracy": 0.17376061528921127,
|
|
"num_tokens": 19787661.0,
|
|
"step": 11405
|
|
},
|
|
{
|
|
"entropy": 5.556111907958984,
|
|
"epoch": 0.8877650262594826,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004926424632327503,
|
|
"loss": 5.2078,
|
|
"mean_token_accuracy": 0.18178965747356415,
|
|
"num_tokens": 19796421.0,
|
|
"step": 11410
|
|
},
|
|
{
|
|
"entropy": 5.535477924346924,
|
|
"epoch": 0.8881540556312002,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004926354319214129,
|
|
"loss": 5.2206,
|
|
"mean_token_accuracy": 0.18311661928892137,
|
|
"num_tokens": 19805842.0,
|
|
"step": 11415
|
|
},
|
|
{
|
|
"entropy": 5.5428627014160154,
|
|
"epoch": 0.8885430850029177,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004926283973078041,
|
|
"loss": 5.2476,
|
|
"mean_token_accuracy": 0.18432259261608125,
|
|
"num_tokens": 19814179.0,
|
|
"step": 11420
|
|
},
|
|
{
|
|
"entropy": 5.540349626541138,
|
|
"epoch": 0.8889321143746353,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004926213593920309,
|
|
"loss": 5.3165,
|
|
"mean_token_accuracy": 0.17773068845272064,
|
|
"num_tokens": 19822435.0,
|
|
"step": 11425
|
|
},
|
|
{
|
|
"entropy": 5.614234161376953,
|
|
"epoch": 0.8893211437463528,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004926143181742,
|
|
"loss": 5.2146,
|
|
"mean_token_accuracy": 0.18455283790826799,
|
|
"num_tokens": 19830300.0,
|
|
"step": 11430
|
|
},
|
|
{
|
|
"entropy": 5.556007957458496,
|
|
"epoch": 0.8897101731180704,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004926072736544181,
|
|
"loss": 5.3444,
|
|
"mean_token_accuracy": 0.17781427651643752,
|
|
"num_tokens": 19839264.0,
|
|
"step": 11435
|
|
},
|
|
{
|
|
"entropy": 5.5439025402069095,
|
|
"epoch": 0.890099202489788,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004926002258327922,
|
|
"loss": 5.2694,
|
|
"mean_token_accuracy": 0.18135368525981904,
|
|
"num_tokens": 19848086.0,
|
|
"step": 11440
|
|
},
|
|
{
|
|
"entropy": 5.610151863098144,
|
|
"epoch": 0.8904882318615055,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004925931747094292,
|
|
"loss": 5.2579,
|
|
"mean_token_accuracy": 0.1756952151656151,
|
|
"num_tokens": 19856571.0,
|
|
"step": 11445
|
|
},
|
|
{
|
|
"entropy": 5.570679187774658,
|
|
"epoch": 0.8908772612332231,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004925861202844361,
|
|
"loss": 5.277,
|
|
"mean_token_accuracy": 0.1755858764052391,
|
|
"num_tokens": 19865272.0,
|
|
"step": 11450
|
|
},
|
|
{
|
|
"entropy": 5.539387464523315,
|
|
"epoch": 0.8912662906049407,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00049257906255792,
|
|
"loss": 5.1969,
|
|
"mean_token_accuracy": 0.1824360743165016,
|
|
"num_tokens": 19874307.0,
|
|
"step": 11455
|
|
},
|
|
{
|
|
"entropy": 5.558570623397827,
|
|
"epoch": 0.8916553199766583,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000492572001529988,
|
|
"loss": 5.2803,
|
|
"mean_token_accuracy": 0.17733534574508666,
|
|
"num_tokens": 19882851.0,
|
|
"step": 11460
|
|
},
|
|
{
|
|
"entropy": 5.556431293487549,
|
|
"epoch": 0.8920443493483758,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004925649372007469,
|
|
"loss": 5.1565,
|
|
"mean_token_accuracy": 0.19295447170734406,
|
|
"num_tokens": 19891276.0,
|
|
"step": 11465
|
|
},
|
|
{
|
|
"entropy": 5.616119909286499,
|
|
"epoch": 0.8924333787200933,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004925578695703045,
|
|
"loss": 5.3134,
|
|
"mean_token_accuracy": 0.1715076133608818,
|
|
"num_tokens": 19900551.0,
|
|
"step": 11470
|
|
},
|
|
{
|
|
"entropy": 5.639095497131348,
|
|
"epoch": 0.8928224080918109,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004925507986387676,
|
|
"loss": 5.33,
|
|
"mean_token_accuracy": 0.17884072959423064,
|
|
"num_tokens": 19909412.0,
|
|
"step": 11475
|
|
},
|
|
{
|
|
"entropy": 5.569097280502319,
|
|
"epoch": 0.8932114374635285,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004925437244062436,
|
|
"loss": 5.1774,
|
|
"mean_token_accuracy": 0.18880049884319305,
|
|
"num_tokens": 19918073.0,
|
|
"step": 11480
|
|
},
|
|
{
|
|
"entropy": 5.445699977874756,
|
|
"epoch": 0.8936004668352461,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004925366468728397,
|
|
"loss": 5.134,
|
|
"mean_token_accuracy": 0.19442103207111358,
|
|
"num_tokens": 19926040.0,
|
|
"step": 11485
|
|
},
|
|
{
|
|
"entropy": 5.560358476638794,
|
|
"epoch": 0.8939894962069637,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004925295660386635,
|
|
"loss": 5.2952,
|
|
"mean_token_accuracy": 0.18159547597169876,
|
|
"num_tokens": 19934543.0,
|
|
"step": 11490
|
|
},
|
|
{
|
|
"entropy": 5.584822463989258,
|
|
"epoch": 0.8943785255786811,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004925224819038224,
|
|
"loss": 5.2261,
|
|
"mean_token_accuracy": 0.1877506196498871,
|
|
"num_tokens": 19943198.0,
|
|
"step": 11495
|
|
},
|
|
{
|
|
"entropy": 5.501182699203492,
|
|
"epoch": 0.8947675549503987,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004925153944684239,
|
|
"loss": 5.1606,
|
|
"mean_token_accuracy": 0.19049780517816545,
|
|
"num_tokens": 19952319.0,
|
|
"step": 11500
|
|
},
|
|
{
|
|
"entropy": 5.500726127624512,
|
|
"epoch": 0.8951565843221163,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004925083037325754,
|
|
"loss": 5.1564,
|
|
"mean_token_accuracy": 0.18824374675750732,
|
|
"num_tokens": 19961982.0,
|
|
"step": 11505
|
|
},
|
|
{
|
|
"entropy": 5.541096115112305,
|
|
"epoch": 0.8955456136938339,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004925012096963847,
|
|
"loss": 5.1747,
|
|
"mean_token_accuracy": 0.18422329127788545,
|
|
"num_tokens": 19971055.0,
|
|
"step": 11510
|
|
},
|
|
{
|
|
"entropy": 5.46767144203186,
|
|
"epoch": 0.8959346430655515,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004924941123599593,
|
|
"loss": 5.0646,
|
|
"mean_token_accuracy": 0.1973741590976715,
|
|
"num_tokens": 19979850.0,
|
|
"step": 11515
|
|
},
|
|
{
|
|
"entropy": 5.563228511810303,
|
|
"epoch": 0.896323672437269,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004924870117234069,
|
|
"loss": 5.2763,
|
|
"mean_token_accuracy": 0.18018045723438264,
|
|
"num_tokens": 19989261.0,
|
|
"step": 11520
|
|
},
|
|
{
|
|
"entropy": 5.5026203155517575,
|
|
"epoch": 0.8967127018089865,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004924799077868353,
|
|
"loss": 5.1871,
|
|
"mean_token_accuracy": 0.17769325226545335,
|
|
"num_tokens": 19998321.0,
|
|
"step": 11525
|
|
},
|
|
{
|
|
"entropy": 5.500790166854858,
|
|
"epoch": 0.8971017311807041,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004924728005503522,
|
|
"loss": 5.2668,
|
|
"mean_token_accuracy": 0.17981211543083192,
|
|
"num_tokens": 20007191.0,
|
|
"step": 11530
|
|
},
|
|
{
|
|
"entropy": 5.615214252471924,
|
|
"epoch": 0.8974907605524217,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004924656900140655,
|
|
"loss": 5.2881,
|
|
"mean_token_accuracy": 0.17898485511541368,
|
|
"num_tokens": 20015805.0,
|
|
"step": 11535
|
|
},
|
|
{
|
|
"entropy": 5.587937355041504,
|
|
"epoch": 0.8978797899241393,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004924585761780831,
|
|
"loss": 5.2651,
|
|
"mean_token_accuracy": 0.1849955752491951,
|
|
"num_tokens": 20024861.0,
|
|
"step": 11540
|
|
},
|
|
{
|
|
"entropy": 5.652350950241089,
|
|
"epoch": 0.8982688192958569,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000492451459042513,
|
|
"loss": 5.3174,
|
|
"mean_token_accuracy": 0.17797672301530837,
|
|
"num_tokens": 20034208.0,
|
|
"step": 11545
|
|
},
|
|
{
|
|
"entropy": 5.544576501846313,
|
|
"epoch": 0.8986578486675744,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000492444338607463,
|
|
"loss": 5.2727,
|
|
"mean_token_accuracy": 0.1784976452589035,
|
|
"num_tokens": 20042786.0,
|
|
"step": 11550
|
|
},
|
|
{
|
|
"entropy": 5.639313840866089,
|
|
"epoch": 0.899046878039292,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004924372148730413,
|
|
"loss": 5.322,
|
|
"mean_token_accuracy": 0.17717861235141755,
|
|
"num_tokens": 20051697.0,
|
|
"step": 11555
|
|
},
|
|
{
|
|
"entropy": 5.622322702407837,
|
|
"epoch": 0.8994359074110095,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000492430087839356,
|
|
"loss": 5.2756,
|
|
"mean_token_accuracy": 0.18705434650182723,
|
|
"num_tokens": 20059814.0,
|
|
"step": 11560
|
|
},
|
|
{
|
|
"entropy": 5.555255651473999,
|
|
"epoch": 0.8998249367827271,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004924229575065152,
|
|
"loss": 5.2892,
|
|
"mean_token_accuracy": 0.18103350102901458,
|
|
"num_tokens": 20068329.0,
|
|
"step": 11565
|
|
},
|
|
{
|
|
"entropy": 5.581609153747559,
|
|
"epoch": 0.9002139661544447,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000492415823874627,
|
|
"loss": 5.2698,
|
|
"mean_token_accuracy": 0.18550906479358673,
|
|
"num_tokens": 20076925.0,
|
|
"step": 11570
|
|
},
|
|
{
|
|
"entropy": 5.56740369796753,
|
|
"epoch": 0.9006029955261622,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004924086869437998,
|
|
"loss": 5.2909,
|
|
"mean_token_accuracy": 0.17394916862249374,
|
|
"num_tokens": 20085248.0,
|
|
"step": 11575
|
|
},
|
|
{
|
|
"entropy": 5.590228033065796,
|
|
"epoch": 0.9009920248978798,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004924015467141417,
|
|
"loss": 5.2863,
|
|
"mean_token_accuracy": 0.17664130926132202,
|
|
"num_tokens": 20093929.0,
|
|
"step": 11580
|
|
},
|
|
{
|
|
"entropy": 5.58238582611084,
|
|
"epoch": 0.9013810542695974,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004923944031857613,
|
|
"loss": 5.3472,
|
|
"mean_token_accuracy": 0.17677741944789888,
|
|
"num_tokens": 20103141.0,
|
|
"step": 11585
|
|
},
|
|
{
|
|
"entropy": 5.54950180053711,
|
|
"epoch": 0.901770083641315,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004923872563587668,
|
|
"loss": 5.1753,
|
|
"mean_token_accuracy": 0.19261873364448548,
|
|
"num_tokens": 20111938.0,
|
|
"step": 11590
|
|
},
|
|
{
|
|
"entropy": 5.52837119102478,
|
|
"epoch": 0.9021591130130325,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004923801062332666,
|
|
"loss": 5.167,
|
|
"mean_token_accuracy": 0.1935260236263275,
|
|
"num_tokens": 20120795.0,
|
|
"step": 11595
|
|
},
|
|
{
|
|
"entropy": 5.56316065788269,
|
|
"epoch": 0.90254814238475,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004923729528093694,
|
|
"loss": 5.2534,
|
|
"mean_token_accuracy": 0.18112141489982606,
|
|
"num_tokens": 20129816.0,
|
|
"step": 11600
|
|
},
|
|
{
|
|
"entropy": 5.610924768447876,
|
|
"epoch": 0.9029371717564676,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004923657960871836,
|
|
"loss": 5.38,
|
|
"mean_token_accuracy": 0.17450439035892487,
|
|
"num_tokens": 20138380.0,
|
|
"step": 11605
|
|
},
|
|
{
|
|
"entropy": 5.656967687606811,
|
|
"epoch": 0.9033262011281852,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004923586360668178,
|
|
"loss": 5.3778,
|
|
"mean_token_accuracy": 0.1771547645330429,
|
|
"num_tokens": 20147201.0,
|
|
"step": 11610
|
|
},
|
|
{
|
|
"entropy": 5.56103835105896,
|
|
"epoch": 0.9037152304999028,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004923514727483807,
|
|
"loss": 5.1967,
|
|
"mean_token_accuracy": 0.18787529468536376,
|
|
"num_tokens": 20156744.0,
|
|
"step": 11615
|
|
},
|
|
{
|
|
"entropy": 5.582573461532593,
|
|
"epoch": 0.9041042598716204,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000492344306131981,
|
|
"loss": 5.2335,
|
|
"mean_token_accuracy": 0.17903553545475007,
|
|
"num_tokens": 20165081.0,
|
|
"step": 11620
|
|
},
|
|
{
|
|
"entropy": 5.592436456680298,
|
|
"epoch": 0.9044932892433378,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004923371362177272,
|
|
"loss": 5.2368,
|
|
"mean_token_accuracy": 0.17818743586540223,
|
|
"num_tokens": 20172893.0,
|
|
"step": 11625
|
|
},
|
|
{
|
|
"entropy": 5.575743532180786,
|
|
"epoch": 0.9048823186150554,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004923299630057284,
|
|
"loss": 5.2937,
|
|
"mean_token_accuracy": 0.17944218814373017,
|
|
"num_tokens": 20181351.0,
|
|
"step": 11630
|
|
},
|
|
{
|
|
"entropy": 5.594365119934082,
|
|
"epoch": 0.905271347986773,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004923227864960934,
|
|
"loss": 5.3206,
|
|
"mean_token_accuracy": 0.17152225077152253,
|
|
"num_tokens": 20189650.0,
|
|
"step": 11635
|
|
},
|
|
{
|
|
"entropy": 5.6272036075592045,
|
|
"epoch": 0.9056603773584906,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.000492315606688931,
|
|
"loss": 5.2667,
|
|
"mean_token_accuracy": 0.17608900666236876,
|
|
"num_tokens": 20198184.0,
|
|
"step": 11640
|
|
},
|
|
{
|
|
"entropy": 5.6504967212677,
|
|
"epoch": 0.9060494067302082,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004923084235843501,
|
|
"loss": 5.1974,
|
|
"mean_token_accuracy": 0.1882951557636261,
|
|
"num_tokens": 20206357.0,
|
|
"step": 11645
|
|
},
|
|
{
|
|
"entropy": 5.51787371635437,
|
|
"epoch": 0.9064384361019256,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004923012371824598,
|
|
"loss": 5.3138,
|
|
"mean_token_accuracy": 0.1831569939851761,
|
|
"num_tokens": 20214384.0,
|
|
"step": 11650
|
|
},
|
|
{
|
|
"entropy": 5.569528341293335,
|
|
"epoch": 0.9068274654736432,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000492294047483369,
|
|
"loss": 5.2594,
|
|
"mean_token_accuracy": 0.17942496240139008,
|
|
"num_tokens": 20224103.0,
|
|
"step": 11655
|
|
},
|
|
{
|
|
"entropy": 5.611847877502441,
|
|
"epoch": 0.9072164948453608,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004922868544871869,
|
|
"loss": 5.2911,
|
|
"mean_token_accuracy": 0.18178559690713883,
|
|
"num_tokens": 20233414.0,
|
|
"step": 11660
|
|
},
|
|
{
|
|
"entropy": 5.593952655792236,
|
|
"epoch": 0.9076055242170784,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004922796581940227,
|
|
"loss": 5.1803,
|
|
"mean_token_accuracy": 0.19224899709224702,
|
|
"num_tokens": 20240988.0,
|
|
"step": 11665
|
|
},
|
|
{
|
|
"entropy": 5.481856918334961,
|
|
"epoch": 0.907994553588796,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004922724586039855,
|
|
"loss": 5.1899,
|
|
"mean_token_accuracy": 0.18444481790065764,
|
|
"num_tokens": 20250066.0,
|
|
"step": 11670
|
|
},
|
|
{
|
|
"entropy": 5.5165046691894535,
|
|
"epoch": 0.9083835829605135,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004922652557171846,
|
|
"loss": 5.1441,
|
|
"mean_token_accuracy": 0.18613797426223755,
|
|
"num_tokens": 20258435.0,
|
|
"step": 11675
|
|
},
|
|
{
|
|
"entropy": 5.574391174316406,
|
|
"epoch": 0.9087726123322311,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004922580495337292,
|
|
"loss": 5.2908,
|
|
"mean_token_accuracy": 0.18753574043512344,
|
|
"num_tokens": 20267345.0,
|
|
"step": 11680
|
|
},
|
|
{
|
|
"entropy": 5.622555875778199,
|
|
"epoch": 0.9091616417039486,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004922508400537288,
|
|
"loss": 5.3052,
|
|
"mean_token_accuracy": 0.18619502782821656,
|
|
"num_tokens": 20275644.0,
|
|
"step": 11685
|
|
},
|
|
{
|
|
"entropy": 5.602553844451904,
|
|
"epoch": 0.9095506710756662,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004922436272772926,
|
|
"loss": 5.3039,
|
|
"mean_token_accuracy": 0.18190854787826538,
|
|
"num_tokens": 20284459.0,
|
|
"step": 11690
|
|
},
|
|
{
|
|
"entropy": 5.574173355102539,
|
|
"epoch": 0.9099397004473838,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004922364112045301,
|
|
"loss": 5.1817,
|
|
"mean_token_accuracy": 0.18159767091274262,
|
|
"num_tokens": 20293088.0,
|
|
"step": 11695
|
|
},
|
|
{
|
|
"entropy": 5.509349203109741,
|
|
"epoch": 0.9103287298191013,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000492229191835551,
|
|
"loss": 5.216,
|
|
"mean_token_accuracy": 0.18721252381801606,
|
|
"num_tokens": 20301811.0,
|
|
"step": 11700
|
|
},
|
|
{
|
|
"entropy": 5.6459808349609375,
|
|
"epoch": 0.9107177591908189,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004922219691704645,
|
|
"loss": 5.3606,
|
|
"mean_token_accuracy": 0.1744689628481865,
|
|
"num_tokens": 20310365.0,
|
|
"step": 11705
|
|
},
|
|
{
|
|
"entropy": 5.652016544342041,
|
|
"epoch": 0.9111067885625365,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004922147432093805,
|
|
"loss": 5.2731,
|
|
"mean_token_accuracy": 0.18861508071422578,
|
|
"num_tokens": 20318891.0,
|
|
"step": 11710
|
|
},
|
|
{
|
|
"entropy": 5.527889442443848,
|
|
"epoch": 0.911495817934254,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004922075139524083,
|
|
"loss": 5.1479,
|
|
"mean_token_accuracy": 0.19287789911031722,
|
|
"num_tokens": 20327313.0,
|
|
"step": 11715
|
|
},
|
|
{
|
|
"entropy": 5.514367198944091,
|
|
"epoch": 0.9118848473059716,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000492200281399658,
|
|
"loss": 5.1379,
|
|
"mean_token_accuracy": 0.1912658095359802,
|
|
"num_tokens": 20335511.0,
|
|
"step": 11720
|
|
},
|
|
{
|
|
"entropy": 5.530355930328369,
|
|
"epoch": 0.9122738766776891,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000492193045551239,
|
|
"loss": 5.1654,
|
|
"mean_token_accuracy": 0.19051099866628646,
|
|
"num_tokens": 20343588.0,
|
|
"step": 11725
|
|
},
|
|
{
|
|
"entropy": 5.557232236862182,
|
|
"epoch": 0.9126629060494067,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004921858064072612,
|
|
"loss": 5.2391,
|
|
"mean_token_accuracy": 0.1865159258246422,
|
|
"num_tokens": 20352793.0,
|
|
"step": 11730
|
|
},
|
|
{
|
|
"entropy": 5.573578262329102,
|
|
"epoch": 0.9130519354211243,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004921785639678347,
|
|
"loss": 5.3133,
|
|
"mean_token_accuracy": 0.182097165286541,
|
|
"num_tokens": 20362480.0,
|
|
"step": 11735
|
|
},
|
|
{
|
|
"entropy": 5.5420506477355955,
|
|
"epoch": 0.9134409647928419,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000492171318233069,
|
|
"loss": 5.1714,
|
|
"mean_token_accuracy": 0.18888458162546157,
|
|
"num_tokens": 20371192.0,
|
|
"step": 11740
|
|
},
|
|
{
|
|
"entropy": 5.638186502456665,
|
|
"epoch": 0.9138299941645595,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004921640692030742,
|
|
"loss": 5.3085,
|
|
"mean_token_accuracy": 0.18450805842876433,
|
|
"num_tokens": 20379322.0,
|
|
"step": 11745
|
|
},
|
|
{
|
|
"entropy": 5.622485828399658,
|
|
"epoch": 0.914219023536277,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004921568168779603,
|
|
"loss": 5.2604,
|
|
"mean_token_accuracy": 0.17219553589820863,
|
|
"num_tokens": 20387976.0,
|
|
"step": 11750
|
|
},
|
|
{
|
|
"entropy": 5.5516157150268555,
|
|
"epoch": 0.9146080529079945,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004921495612578374,
|
|
"loss": 5.325,
|
|
"mean_token_accuracy": 0.17372918725013733,
|
|
"num_tokens": 20397398.0,
|
|
"step": 11755
|
|
},
|
|
{
|
|
"entropy": 5.529106760025025,
|
|
"epoch": 0.9149970822797121,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004921423023428156,
|
|
"loss": 5.2339,
|
|
"mean_token_accuracy": 0.1838798388838768,
|
|
"num_tokens": 20406503.0,
|
|
"step": 11760
|
|
},
|
|
{
|
|
"entropy": 5.541811323165893,
|
|
"epoch": 0.9153861116514297,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004921350401330049,
|
|
"loss": 5.1691,
|
|
"mean_token_accuracy": 0.18593801259994508,
|
|
"num_tokens": 20415117.0,
|
|
"step": 11765
|
|
},
|
|
{
|
|
"entropy": 5.5522106170654295,
|
|
"epoch": 0.9157751410231473,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004921277746285155,
|
|
"loss": 5.254,
|
|
"mean_token_accuracy": 0.18175882548093797,
|
|
"num_tokens": 20423519.0,
|
|
"step": 11770
|
|
},
|
|
{
|
|
"entropy": 5.561598682403565,
|
|
"epoch": 0.9161641703948649,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004921205058294579,
|
|
"loss": 5.1807,
|
|
"mean_token_accuracy": 0.1842939481139183,
|
|
"num_tokens": 20431831.0,
|
|
"step": 11775
|
|
},
|
|
{
|
|
"entropy": 5.619694757461548,
|
|
"epoch": 0.9165531997665823,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000492113233735942,
|
|
"loss": 5.3216,
|
|
"mean_token_accuracy": 0.17371482849121095,
|
|
"num_tokens": 20440927.0,
|
|
"step": 11780
|
|
},
|
|
{
|
|
"entropy": 5.524583244323731,
|
|
"epoch": 0.9169422291382999,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004921059583480785,
|
|
"loss": 5.1934,
|
|
"mean_token_accuracy": 0.19074779599905015,
|
|
"num_tokens": 20448974.0,
|
|
"step": 11785
|
|
},
|
|
{
|
|
"entropy": 5.50584135055542,
|
|
"epoch": 0.9173312585100175,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004920986796659775,
|
|
"loss": 5.1245,
|
|
"mean_token_accuracy": 0.191385318338871,
|
|
"num_tokens": 20457955.0,
|
|
"step": 11790
|
|
},
|
|
{
|
|
"entropy": 5.507561826705933,
|
|
"epoch": 0.9177202878817351,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004920913976897498,
|
|
"loss": 5.2366,
|
|
"mean_token_accuracy": 0.18471247851848602,
|
|
"num_tokens": 20465942.0,
|
|
"step": 11795
|
|
},
|
|
{
|
|
"entropy": 5.541639804840088,
|
|
"epoch": 0.9181093172534527,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004920841124195055,
|
|
"loss": 5.2782,
|
|
"mean_token_accuracy": 0.1835801288485527,
|
|
"num_tokens": 20474726.0,
|
|
"step": 11800
|
|
},
|
|
{
|
|
"entropy": 5.513240098953247,
|
|
"epoch": 0.9184983466251702,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004920768238553554,
|
|
"loss": 5.225,
|
|
"mean_token_accuracy": 0.184701868891716,
|
|
"num_tokens": 20483442.0,
|
|
"step": 11805
|
|
},
|
|
{
|
|
"entropy": 5.509365367889404,
|
|
"epoch": 0.9188873759968877,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004920695319974099,
|
|
"loss": 5.1861,
|
|
"mean_token_accuracy": 0.18636468350887297,
|
|
"num_tokens": 20492950.0,
|
|
"step": 11810
|
|
},
|
|
{
|
|
"entropy": 5.607105827331543,
|
|
"epoch": 0.9192764053686053,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004920622368457798,
|
|
"loss": 5.2863,
|
|
"mean_token_accuracy": 0.1794748067855835,
|
|
"num_tokens": 20502035.0,
|
|
"step": 11815
|
|
},
|
|
{
|
|
"entropy": 5.601960372924805,
|
|
"epoch": 0.9196654347403229,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004920549384005759,
|
|
"loss": 5.1661,
|
|
"mean_token_accuracy": 0.19141081124544143,
|
|
"num_tokens": 20510140.0,
|
|
"step": 11820
|
|
},
|
|
{
|
|
"entropy": 5.587213468551636,
|
|
"epoch": 0.9200544641120405,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004920476366619086,
|
|
"loss": 5.2799,
|
|
"mean_token_accuracy": 0.17743276059627533,
|
|
"num_tokens": 20519391.0,
|
|
"step": 11825
|
|
},
|
|
{
|
|
"entropy": 5.6275735855102536,
|
|
"epoch": 0.920443493483758,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000492040331629889,
|
|
"loss": 5.2717,
|
|
"mean_token_accuracy": 0.1765116959810257,
|
|
"num_tokens": 20527635.0,
|
|
"step": 11830
|
|
},
|
|
{
|
|
"entropy": 5.6019606590271,
|
|
"epoch": 0.9208325228554756,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004920330233046277,
|
|
"loss": 5.2326,
|
|
"mean_token_accuracy": 0.18538276851177216,
|
|
"num_tokens": 20536455.0,
|
|
"step": 11835
|
|
},
|
|
{
|
|
"entropy": 5.637334966659546,
|
|
"epoch": 0.9212215522271932,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004920257116862359,
|
|
"loss": 5.3601,
|
|
"mean_token_accuracy": 0.17379544377326966,
|
|
"num_tokens": 20545887.0,
|
|
"step": 11840
|
|
},
|
|
{
|
|
"entropy": 5.527892971038819,
|
|
"epoch": 0.9216105815989107,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004920183967748241,
|
|
"loss": 5.2338,
|
|
"mean_token_accuracy": 0.18469038903713225,
|
|
"num_tokens": 20554415.0,
|
|
"step": 11845
|
|
},
|
|
{
|
|
"entropy": 5.608368301391602,
|
|
"epoch": 0.9219996109706283,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004920110785705037,
|
|
"loss": 5.3044,
|
|
"mean_token_accuracy": 0.1792415663599968,
|
|
"num_tokens": 20563081.0,
|
|
"step": 11850
|
|
},
|
|
{
|
|
"entropy": 5.5365087509155275,
|
|
"epoch": 0.9223886403423458,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004920037570733857,
|
|
"loss": 5.1588,
|
|
"mean_token_accuracy": 0.1892438307404518,
|
|
"num_tokens": 20571800.0,
|
|
"step": 11855
|
|
},
|
|
{
|
|
"entropy": 5.579374027252197,
|
|
"epoch": 0.9227776697140634,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004919964322835809,
|
|
"loss": 5.2944,
|
|
"mean_token_accuracy": 0.18046103715896605,
|
|
"num_tokens": 20580481.0,
|
|
"step": 11860
|
|
},
|
|
{
|
|
"entropy": 5.530831289291382,
|
|
"epoch": 0.923166699085781,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004919891042012006,
|
|
"loss": 5.1701,
|
|
"mean_token_accuracy": 0.18944658488035201,
|
|
"num_tokens": 20589575.0,
|
|
"step": 11865
|
|
},
|
|
{
|
|
"entropy": 5.531797075271607,
|
|
"epoch": 0.9235557284574986,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004919817728263562,
|
|
"loss": 5.2465,
|
|
"mean_token_accuracy": 0.18160925060510635,
|
|
"num_tokens": 20598277.0,
|
|
"step": 11870
|
|
},
|
|
{
|
|
"entropy": 5.634156799316406,
|
|
"epoch": 0.9239447578292161,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004919744381591586,
|
|
"loss": 5.3722,
|
|
"mean_token_accuracy": 0.18001783341169358,
|
|
"num_tokens": 20607013.0,
|
|
"step": 11875
|
|
},
|
|
{
|
|
"entropy": 5.574320554733276,
|
|
"epoch": 0.9243337872009336,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004919671001997193,
|
|
"loss": 5.278,
|
|
"mean_token_accuracy": 0.17825234234333037,
|
|
"num_tokens": 20615605.0,
|
|
"step": 11880
|
|
},
|
|
{
|
|
"entropy": 5.6079527854919435,
|
|
"epoch": 0.9247228165726512,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004919597589481497,
|
|
"loss": 5.2612,
|
|
"mean_token_accuracy": 0.1799523875117302,
|
|
"num_tokens": 20624275.0,
|
|
"step": 11885
|
|
},
|
|
{
|
|
"entropy": 5.57183518409729,
|
|
"epoch": 0.9251118459443688,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000491952414404561,
|
|
"loss": 5.2162,
|
|
"mean_token_accuracy": 0.1849514827132225,
|
|
"num_tokens": 20632681.0,
|
|
"step": 11890
|
|
},
|
|
{
|
|
"entropy": 5.66807599067688,
|
|
"epoch": 0.9255008753160864,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004919450665690646,
|
|
"loss": 5.2688,
|
|
"mean_token_accuracy": 0.18525569140911102,
|
|
"num_tokens": 20641432.0,
|
|
"step": 11895
|
|
},
|
|
{
|
|
"entropy": 5.583403253555298,
|
|
"epoch": 0.925889904687804,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004919377154417724,
|
|
"loss": 5.2715,
|
|
"mean_token_accuracy": 0.18098506182432175,
|
|
"num_tokens": 20650120.0,
|
|
"step": 11900
|
|
},
|
|
{
|
|
"entropy": 5.529873466491699,
|
|
"epoch": 0.9262789340595214,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004919303610227954,
|
|
"loss": 5.1948,
|
|
"mean_token_accuracy": 0.18440381437540054,
|
|
"num_tokens": 20658188.0,
|
|
"step": 11905
|
|
},
|
|
{
|
|
"entropy": 5.492690134048462,
|
|
"epoch": 0.926667963431239,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004919230033122457,
|
|
"loss": 5.1105,
|
|
"mean_token_accuracy": 0.19484479129314422,
|
|
"num_tokens": 20666157.0,
|
|
"step": 11910
|
|
},
|
|
{
|
|
"entropy": 5.544192504882813,
|
|
"epoch": 0.9270569928029566,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004919156423102345,
|
|
"loss": 5.3112,
|
|
"mean_token_accuracy": 0.18255216404795646,
|
|
"num_tokens": 20674995.0,
|
|
"step": 11915
|
|
},
|
|
{
|
|
"entropy": 5.630472421646118,
|
|
"epoch": 0.9274460221746742,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004919082780168736,
|
|
"loss": 5.2452,
|
|
"mean_token_accuracy": 0.17868777960538865,
|
|
"num_tokens": 20683786.0,
|
|
"step": 11920
|
|
},
|
|
{
|
|
"entropy": 5.580710172653198,
|
|
"epoch": 0.9278350515463918,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004919009104322751,
|
|
"loss": 5.2721,
|
|
"mean_token_accuracy": 0.17575779557228088,
|
|
"num_tokens": 20692582.0,
|
|
"step": 11925
|
|
},
|
|
{
|
|
"entropy": 5.596516084671021,
|
|
"epoch": 0.9282240809181093,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004918935395565503,
|
|
"loss": 5.32,
|
|
"mean_token_accuracy": 0.17592122703790664,
|
|
"num_tokens": 20700892.0,
|
|
"step": 11930
|
|
},
|
|
{
|
|
"entropy": 5.51577353477478,
|
|
"epoch": 0.9286131102898268,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004918861653898113,
|
|
"loss": 5.137,
|
|
"mean_token_accuracy": 0.196639546751976,
|
|
"num_tokens": 20709521.0,
|
|
"step": 11935
|
|
},
|
|
{
|
|
"entropy": 5.532233953475952,
|
|
"epoch": 0.9290021396615444,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004918787879321701,
|
|
"loss": 5.2632,
|
|
"mean_token_accuracy": 0.17572422772645951,
|
|
"num_tokens": 20717614.0,
|
|
"step": 11940
|
|
},
|
|
{
|
|
"entropy": 5.560285663604736,
|
|
"epoch": 0.929391169033262,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004918714071837384,
|
|
"loss": 5.1965,
|
|
"mean_token_accuracy": 0.18053747564554215,
|
|
"num_tokens": 20726624.0,
|
|
"step": 11945
|
|
},
|
|
{
|
|
"entropy": 5.6247334480285645,
|
|
"epoch": 0.9297801984049796,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004918640231446282,
|
|
"loss": 5.2943,
|
|
"mean_token_accuracy": 0.1780096933245659,
|
|
"num_tokens": 20734738.0,
|
|
"step": 11950
|
|
},
|
|
{
|
|
"entropy": 5.582316732406616,
|
|
"epoch": 0.9301692277766972,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004918566358149517,
|
|
"loss": 5.2306,
|
|
"mean_token_accuracy": 0.1833841785788536,
|
|
"num_tokens": 20742825.0,
|
|
"step": 11955
|
|
},
|
|
{
|
|
"entropy": 5.552599716186523,
|
|
"epoch": 0.9305582571484147,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000491849245194821,
|
|
"loss": 5.1919,
|
|
"mean_token_accuracy": 0.1891092151403427,
|
|
"num_tokens": 20752132.0,
|
|
"step": 11960
|
|
},
|
|
{
|
|
"entropy": 5.628361988067627,
|
|
"epoch": 0.9309472865201323,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004918418512843479,
|
|
"loss": 5.3183,
|
|
"mean_token_accuracy": 0.1766253247857094,
|
|
"num_tokens": 20761838.0,
|
|
"step": 11965
|
|
},
|
|
{
|
|
"entropy": 5.599145078659058,
|
|
"epoch": 0.9313363158918498,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004918344540836451,
|
|
"loss": 5.2227,
|
|
"mean_token_accuracy": 0.1821851596236229,
|
|
"num_tokens": 20770405.0,
|
|
"step": 11970
|
|
},
|
|
{
|
|
"entropy": 5.711616325378418,
|
|
"epoch": 0.9317253452635674,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004918270535928244,
|
|
"loss": 5.3912,
|
|
"mean_token_accuracy": 0.17361809313297272,
|
|
"num_tokens": 20780130.0,
|
|
"step": 11975
|
|
},
|
|
{
|
|
"entropy": 5.53233323097229,
|
|
"epoch": 0.932114374635285,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004918196498119984,
|
|
"loss": 5.2735,
|
|
"mean_token_accuracy": 0.18742605298757553,
|
|
"num_tokens": 20788852.0,
|
|
"step": 11980
|
|
},
|
|
{
|
|
"entropy": 5.545420932769775,
|
|
"epoch": 0.9325034040070025,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004918122427412793,
|
|
"loss": 5.2168,
|
|
"mean_token_accuracy": 0.18332792818546295,
|
|
"num_tokens": 20796944.0,
|
|
"step": 11985
|
|
},
|
|
{
|
|
"entropy": 5.549014568328857,
|
|
"epoch": 0.9328924333787201,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004918048323807795,
|
|
"loss": 5.3128,
|
|
"mean_token_accuracy": 0.18216352313756942,
|
|
"num_tokens": 20806118.0,
|
|
"step": 11990
|
|
},
|
|
{
|
|
"entropy": 5.609514474868774,
|
|
"epoch": 0.9332814627504377,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004917974187306114,
|
|
"loss": 5.1055,
|
|
"mean_token_accuracy": 0.1885119527578354,
|
|
"num_tokens": 20814643.0,
|
|
"step": 11995
|
|
},
|
|
{
|
|
"entropy": 5.583715391159058,
|
|
"epoch": 0.9336704921221552,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004917900017908875,
|
|
"loss": 5.1952,
|
|
"mean_token_accuracy": 0.18639011681079865,
|
|
"num_tokens": 20823315.0,
|
|
"step": 12000
|
|
},
|
|
{
|
|
"epoch": 0.9336704921221552,
|
|
"eval_entropy": 5.316801309631465,
|
|
"eval_loss": 5.258728981018066,
|
|
"eval_mean_token_accuracy": 0.19031005386725655,
|
|
"eval_num_tokens": 20823315.0,
|
|
"eval_runtime": 21.8591,
|
|
"eval_samples_per_second": 1901.173,
|
|
"eval_steps_per_second": 237.658,
|
|
"step": 12000
|
|
}
|
|
],
|
|
"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": 4196454589071360.0,
|
|
"train_batch_size": 16,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|