6046 lines
164 KiB
JSON
6046 lines
164 KiB
JSON
|
{
|
||
|
|
"best_global_step": null,
|
||
|
|
"best_metric": null,
|
||
|
|
"best_model_checkpoint": null,
|
||
|
|
"epoch": 0.2334176230305388,
|
||
|
|
"eval_steps": 3000,
|
||
|
|
"global_step": 3000,
|
||
|
|
"is_hyper_param_search": false,
|
||
|
|
"is_local_process_zero": true,
|
||
|
|
"is_world_process_zero": true,
|
||
|
|
"log_history": [
|
||
|
|
{
|
||
|
|
"entropy": 10.742087173461915,
|
||
|
|
"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
|
||
|
|
}
|
||
|
|
],
|
||
|
|
"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": 1050172329000960.0,
|
||
|
|
"train_batch_size": 16,
|
||
|
|
"trial_name": null,
|
||
|
|
"trial_params": null
|
||
|
|
}
|