6046 lines
164 KiB
JSON
6046 lines
164 KiB
JSON
|
{
|
||
|
|
"best_global_step": null,
|
||
|
|
"best_metric": null,
|
||
|
|
"best_model_checkpoint": null,
|
||
|
|
"epoch": 0.2334176230305388,
|
||
|
|
"eval_steps": 3000,
|
||
|
|
"global_step": 3000,
|
||
|
|
"is_hyper_param_search": false,
|
||
|
|
"is_local_process_zero": true,
|
||
|
|
"is_world_process_zero": true,
|
||
|
|
"log_history": [
|
||
|
|
{
|
||
|
|
"entropy": 4.822155237197876,
|
||
|
|
"epoch": 0.00038902937171756465,
|
||
|
|
"grad_norm": 13.625,
|
||
|
|
"learning_rate": 2e-06,
|
||
|
|
"loss": 14.2815,
|
||
|
|
"mean_token_accuracy": 0.0,
|
||
|
|
"num_tokens": 8755.0,
|
||
|
|
"step": 5
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 4.850994205474853,
|
||
|
|
"epoch": 0.0007780587434351293,
|
||
|
|
"grad_norm": 12.8125,
|
||
|
|
"learning_rate": 4.5e-06,
|
||
|
|
"loss": 14.2765,
|
||
|
|
"mean_token_accuracy": 0.0,
|
||
|
|
"num_tokens": 17641.0,
|
||
|
|
"step": 10
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 4.890376091003418,
|
||
|
|
"epoch": 0.001167088115152694,
|
||
|
|
"grad_norm": 14.125,
|
||
|
|
"learning_rate": 7e-06,
|
||
|
|
"loss": 14.0648,
|
||
|
|
"mean_token_accuracy": 0.0,
|
||
|
|
"num_tokens": 26293.0,
|
||
|
|
"step": 15
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.021843671798706,
|
||
|
|
"epoch": 0.0015561174868702586,
|
||
|
|
"grad_norm": 24.25,
|
||
|
|
"learning_rate": 9.5e-06,
|
||
|
|
"loss": 13.6631,
|
||
|
|
"mean_token_accuracy": 0.0,
|
||
|
|
"num_tokens": 35627.0,
|
||
|
|
"step": 20
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.008373975753784,
|
||
|
|
"epoch": 0.0019451468585878235,
|
||
|
|
"grad_norm": 22.625,
|
||
|
|
"learning_rate": 1.2e-05,
|
||
|
|
"loss": 12.5376,
|
||
|
|
"mean_token_accuracy": 0.0,
|
||
|
|
"num_tokens": 43861.0,
|
||
|
|
"step": 25
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.86599760055542,
|
||
|
|
"epoch": 0.002334176230305388,
|
||
|
|
"grad_norm": 5.5625,
|
||
|
|
"learning_rate": 1.4500000000000002e-05,
|
||
|
|
"loss": 11.2709,
|
||
|
|
"mean_token_accuracy": 0.0,
|
||
|
|
"num_tokens": 52816.0,
|
||
|
|
"step": 30
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.603609943389893,
|
||
|
|
"epoch": 0.0027232056020229526,
|
||
|
|
"grad_norm": 2.90625,
|
||
|
|
"learning_rate": 1.7000000000000003e-05,
|
||
|
|
"loss": 10.7418,
|
||
|
|
"mean_token_accuracy": 0.0,
|
||
|
|
"num_tokens": 61370.0,
|
||
|
|
"step": 35
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.707041549682618,
|
||
|
|
"epoch": 0.0031122349737405172,
|
||
|
|
"grad_norm": 2.734375,
|
||
|
|
"learning_rate": 1.95e-05,
|
||
|
|
"loss": 10.5031,
|
||
|
|
"mean_token_accuracy": 0.024387366394512354,
|
||
|
|
"num_tokens": 69444.0,
|
||
|
|
"step": 40
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.700100994110107,
|
||
|
|
"epoch": 0.003501264345458082,
|
||
|
|
"grad_norm": 2.59375,
|
||
|
|
"learning_rate": 2.2e-05,
|
||
|
|
"loss": 10.1892,
|
||
|
|
"mean_token_accuracy": 0.04717930629849434,
|
||
|
|
"num_tokens": 77892.0,
|
||
|
|
"step": 45
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.646122360229493,
|
||
|
|
"epoch": 0.003890293717175647,
|
||
|
|
"grad_norm": 2.1875,
|
||
|
|
"learning_rate": 2.4500000000000003e-05,
|
||
|
|
"loss": 9.9187,
|
||
|
|
"mean_token_accuracy": 0.04567050337791443,
|
||
|
|
"num_tokens": 86154.0,
|
||
|
|
"step": 50
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.534105396270752,
|
||
|
|
"epoch": 0.004279323088893211,
|
||
|
|
"grad_norm": 2.046875,
|
||
|
|
"learning_rate": 2.7e-05,
|
||
|
|
"loss": 9.7477,
|
||
|
|
"mean_token_accuracy": 0.04727716967463493,
|
||
|
|
"num_tokens": 95589.0,
|
||
|
|
"step": 55
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.492498683929444,
|
||
|
|
"epoch": 0.004668352460610776,
|
||
|
|
"grad_norm": 1.8984375,
|
||
|
|
"learning_rate": 2.95e-05,
|
||
|
|
"loss": 9.6445,
|
||
|
|
"mean_token_accuracy": 0.05069234669208526,
|
||
|
|
"num_tokens": 105268.0,
|
||
|
|
"step": 60
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.49142427444458,
|
||
|
|
"epoch": 0.0050573818323283405,
|
||
|
|
"grad_norm": 1.7890625,
|
||
|
|
"learning_rate": 3.2e-05,
|
||
|
|
"loss": 9.4976,
|
||
|
|
"mean_token_accuracy": 0.049440599605441095,
|
||
|
|
"num_tokens": 113347.0,
|
||
|
|
"step": 65
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.467069816589355,
|
||
|
|
"epoch": 0.005446411204045905,
|
||
|
|
"grad_norm": 1.8359375,
|
||
|
|
"learning_rate": 3.4500000000000005e-05,
|
||
|
|
"loss": 9.4401,
|
||
|
|
"mean_token_accuracy": 0.04667307287454605,
|
||
|
|
"num_tokens": 121235.0,
|
||
|
|
"step": 70
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.470718002319336,
|
||
|
|
"epoch": 0.00583544057576347,
|
||
|
|
"grad_norm": 1.734375,
|
||
|
|
"learning_rate": 3.7e-05,
|
||
|
|
"loss": 9.3426,
|
||
|
|
"mean_token_accuracy": 0.04654357880353928,
|
||
|
|
"num_tokens": 129529.0,
|
||
|
|
"step": 75
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.457951641082763,
|
||
|
|
"epoch": 0.0062244699474810344,
|
||
|
|
"grad_norm": 1.6875,
|
||
|
|
"learning_rate": 3.95e-05,
|
||
|
|
"loss": 9.272,
|
||
|
|
"mean_token_accuracy": 0.046728644892573355,
|
||
|
|
"num_tokens": 137918.0,
|
||
|
|
"step": 80
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.396386432647706,
|
||
|
|
"epoch": 0.006613499319198599,
|
||
|
|
"grad_norm": 1.7421875,
|
||
|
|
"learning_rate": 4.2000000000000004e-05,
|
||
|
|
"loss": 9.1338,
|
||
|
|
"mean_token_accuracy": 0.04958013892173767,
|
||
|
|
"num_tokens": 146445.0,
|
||
|
|
"step": 85
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.327083683013916,
|
||
|
|
"epoch": 0.007002528690916164,
|
||
|
|
"grad_norm": 1.6171875,
|
||
|
|
"learning_rate": 4.45e-05,
|
||
|
|
"loss": 9.1232,
|
||
|
|
"mean_token_accuracy": 0.04555690307170153,
|
||
|
|
"num_tokens": 155904.0,
|
||
|
|
"step": 90
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.330926036834716,
|
||
|
|
"epoch": 0.007391558062633729,
|
||
|
|
"grad_norm": 1.65625,
|
||
|
|
"learning_rate": 4.7000000000000004e-05,
|
||
|
|
"loss": 8.9882,
|
||
|
|
"mean_token_accuracy": 0.05696064569056034,
|
||
|
|
"num_tokens": 164436.0,
|
||
|
|
"step": 95
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.282738304138183,
|
||
|
|
"epoch": 0.007780587434351294,
|
||
|
|
"grad_norm": 1.5,
|
||
|
|
"learning_rate": 4.9500000000000004e-05,
|
||
|
|
"loss": 8.8612,
|
||
|
|
"mean_token_accuracy": 0.06417469121515751,
|
||
|
|
"num_tokens": 172985.0,
|
||
|
|
"step": 100
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.166734981536866,
|
||
|
|
"epoch": 0.008169616806068859,
|
||
|
|
"grad_norm": 1.4453125,
|
||
|
|
"learning_rate": 5.2e-05,
|
||
|
|
"loss": 8.7107,
|
||
|
|
"mean_token_accuracy": 0.06344903856515885,
|
||
|
|
"num_tokens": 182084.0,
|
||
|
|
"step": 105
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.032082462310791,
|
||
|
|
"epoch": 0.008558646177786422,
|
||
|
|
"grad_norm": 1.4453125,
|
||
|
|
"learning_rate": 5.45e-05,
|
||
|
|
"loss": 8.5665,
|
||
|
|
"mean_token_accuracy": 0.06556271649897098,
|
||
|
|
"num_tokens": 190742.0,
|
||
|
|
"step": 110
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 9.869285392761231,
|
||
|
|
"epoch": 0.008947675549503988,
|
||
|
|
"grad_norm": 1.5,
|
||
|
|
"learning_rate": 5.7e-05,
|
||
|
|
"loss": 8.4757,
|
||
|
|
"mean_token_accuracy": 0.06190440617501736,
|
||
|
|
"num_tokens": 199600.0,
|
||
|
|
"step": 115
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 9.778227043151855,
|
||
|
|
"epoch": 0.009336704921221552,
|
||
|
|
"grad_norm": 1.4140625,
|
||
|
|
"learning_rate": 5.9499999999999996e-05,
|
||
|
|
"loss": 8.3857,
|
||
|
|
"mean_token_accuracy": 0.06300465390086174,
|
||
|
|
"num_tokens": 207883.0,
|
||
|
|
"step": 120
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 9.670316696166992,
|
||
|
|
"epoch": 0.009725734292939117,
|
||
|
|
"grad_norm": 1.1875,
|
||
|
|
"learning_rate": 6.2e-05,
|
||
|
|
"loss": 8.3105,
|
||
|
|
"mean_token_accuracy": 0.06091714054346085,
|
||
|
|
"num_tokens": 216216.0,
|
||
|
|
"step": 125
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 9.542773723602295,
|
||
|
|
"epoch": 0.010114763664656681,
|
||
|
|
"grad_norm": 1.140625,
|
||
|
|
"learning_rate": 6.450000000000001e-05,
|
||
|
|
"loss": 8.1616,
|
||
|
|
"mean_token_accuracy": 0.060033614933490756,
|
||
|
|
"num_tokens": 225250.0,
|
||
|
|
"step": 130
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 9.252435779571533,
|
||
|
|
"epoch": 0.010503793036374246,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 6.7e-05,
|
||
|
|
"loss": 8.0742,
|
||
|
|
"mean_token_accuracy": 0.060005930438637736,
|
||
|
|
"num_tokens": 233748.0,
|
||
|
|
"step": 135
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 9.096595191955567,
|
||
|
|
"epoch": 0.01089282240809181,
|
||
|
|
"grad_norm": 0.89453125,
|
||
|
|
"learning_rate": 6.950000000000001e-05,
|
||
|
|
"loss": 7.9959,
|
||
|
|
"mean_token_accuracy": 0.06127222627401352,
|
||
|
|
"num_tokens": 242629.0,
|
||
|
|
"step": 140
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.962436199188232,
|
||
|
|
"epoch": 0.011281851779809376,
|
||
|
|
"grad_norm": 1.234375,
|
||
|
|
"learning_rate": 7.2e-05,
|
||
|
|
"loss": 7.909,
|
||
|
|
"mean_token_accuracy": 0.05921337716281414,
|
||
|
|
"num_tokens": 251458.0,
|
||
|
|
"step": 145
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.643758296966553,
|
||
|
|
"epoch": 0.01167088115152694,
|
||
|
|
"grad_norm": 0.97265625,
|
||
|
|
"learning_rate": 7.45e-05,
|
||
|
|
"loss": 7.8293,
|
||
|
|
"mean_token_accuracy": 0.06760686710476875,
|
||
|
|
"num_tokens": 260557.0,
|
||
|
|
"step": 150
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.623544311523437,
|
||
|
|
"epoch": 0.012059910523244505,
|
||
|
|
"grad_norm": 0.9375,
|
||
|
|
"learning_rate": 7.7e-05,
|
||
|
|
"loss": 7.8373,
|
||
|
|
"mean_token_accuracy": 0.0637216754257679,
|
||
|
|
"num_tokens": 269262.0,
|
||
|
|
"step": 155
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.43661003112793,
|
||
|
|
"epoch": 0.012448939894962069,
|
||
|
|
"grad_norm": 0.8671875,
|
||
|
|
"learning_rate": 7.950000000000001e-05,
|
||
|
|
"loss": 7.7627,
|
||
|
|
"mean_token_accuracy": 0.06424607634544373,
|
||
|
|
"num_tokens": 277804.0,
|
||
|
|
"step": 160
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.36682481765747,
|
||
|
|
"epoch": 0.012837969266679634,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 8.2e-05,
|
||
|
|
"loss": 7.7312,
|
||
|
|
"mean_token_accuracy": 0.06261771470308304,
|
||
|
|
"num_tokens": 287450.0,
|
||
|
|
"step": 165
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.331795120239258,
|
||
|
|
"epoch": 0.013226998638397198,
|
||
|
|
"grad_norm": 0.96484375,
|
||
|
|
"learning_rate": 8.450000000000001e-05,
|
||
|
|
"loss": 7.7411,
|
||
|
|
"mean_token_accuracy": 0.060985132306814197,
|
||
|
|
"num_tokens": 296497.0,
|
||
|
|
"step": 170
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.14490041732788,
|
||
|
|
"epoch": 0.013616028010114764,
|
||
|
|
"grad_norm": 0.9765625,
|
||
|
|
"learning_rate": 8.7e-05,
|
||
|
|
"loss": 7.6481,
|
||
|
|
"mean_token_accuracy": 0.06689309664070606,
|
||
|
|
"num_tokens": 305414.0,
|
||
|
|
"step": 175
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.198940753936768,
|
||
|
|
"epoch": 0.014005057381832327,
|
||
|
|
"grad_norm": 0.81640625,
|
||
|
|
"learning_rate": 8.95e-05,
|
||
|
|
"loss": 7.6672,
|
||
|
|
"mean_token_accuracy": 0.06457812413573265,
|
||
|
|
"num_tokens": 313639.0,
|
||
|
|
"step": 180
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.073842096328736,
|
||
|
|
"epoch": 0.014394086753549893,
|
||
|
|
"grad_norm": 1.28125,
|
||
|
|
"learning_rate": 9.2e-05,
|
||
|
|
"loss": 7.6674,
|
||
|
|
"mean_token_accuracy": 0.06364725269377232,
|
||
|
|
"num_tokens": 322855.0,
|
||
|
|
"step": 185
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.109543991088866,
|
||
|
|
"epoch": 0.014783116125267459,
|
||
|
|
"grad_norm": 1.3125,
|
||
|
|
"learning_rate": 9.45e-05,
|
||
|
|
"loss": 7.7752,
|
||
|
|
"mean_token_accuracy": 0.06727200374007225,
|
||
|
|
"num_tokens": 332071.0,
|
||
|
|
"step": 190
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.057977771759033,
|
||
|
|
"epoch": 0.015172145496985022,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 9.7e-05,
|
||
|
|
"loss": 7.566,
|
||
|
|
"mean_token_accuracy": 0.06908895485103131,
|
||
|
|
"num_tokens": 339990.0,
|
||
|
|
"step": 195
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.997255945205689,
|
||
|
|
"epoch": 0.015561174868702588,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 9.95e-05,
|
||
|
|
"loss": 7.6125,
|
||
|
|
"mean_token_accuracy": 0.06956774480640888,
|
||
|
|
"num_tokens": 348581.0,
|
||
|
|
"step": 200
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.994923257827759,
|
||
|
|
"epoch": 0.01595020424042015,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.000102,
|
||
|
|
"loss": 7.6167,
|
||
|
|
"mean_token_accuracy": 0.0684602677822113,
|
||
|
|
"num_tokens": 357032.0,
|
||
|
|
"step": 205
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.967700386047364,
|
||
|
|
"epoch": 0.016339233612137717,
|
||
|
|
"grad_norm": 1.171875,
|
||
|
|
"learning_rate": 0.00010449999999999999,
|
||
|
|
"loss": 7.5867,
|
||
|
|
"mean_token_accuracy": 0.06691787987947465,
|
||
|
|
"num_tokens": 366562.0,
|
||
|
|
"step": 210
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.971745204925537,
|
||
|
|
"epoch": 0.016728262983855283,
|
||
|
|
"grad_norm": 1.203125,
|
||
|
|
"learning_rate": 0.000107,
|
||
|
|
"loss": 7.5795,
|
||
|
|
"mean_token_accuracy": 0.06968615017831326,
|
||
|
|
"num_tokens": 374555.0,
|
||
|
|
"step": 215
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.965626382827759,
|
||
|
|
"epoch": 0.017117292355572845,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.0001095,
|
||
|
|
"loss": 7.6079,
|
||
|
|
"mean_token_accuracy": 0.0643578365445137,
|
||
|
|
"num_tokens": 383583.0,
|
||
|
|
"step": 220
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.928164482116699,
|
||
|
|
"epoch": 0.01750632172729041,
|
||
|
|
"grad_norm": 0.94140625,
|
||
|
|
"learning_rate": 0.000112,
|
||
|
|
"loss": 7.6282,
|
||
|
|
"mean_token_accuracy": 0.06437015496194362,
|
||
|
|
"num_tokens": 392932.0,
|
||
|
|
"step": 225
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.909833192825317,
|
||
|
|
"epoch": 0.017895351099007976,
|
||
|
|
"grad_norm": 0.9765625,
|
||
|
|
"learning_rate": 0.0001145,
|
||
|
|
"loss": 7.4691,
|
||
|
|
"mean_token_accuracy": 0.07002470232546329,
|
||
|
|
"num_tokens": 401653.0,
|
||
|
|
"step": 230
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.861414289474487,
|
||
|
|
"epoch": 0.01828438047072554,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.00011700000000000001,
|
||
|
|
"loss": 7.5637,
|
||
|
|
"mean_token_accuracy": 0.07073870301246643,
|
||
|
|
"num_tokens": 410432.0,
|
||
|
|
"step": 235
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.856981992721558,
|
||
|
|
"epoch": 0.018673409842443103,
|
||
|
|
"grad_norm": 1.1953125,
|
||
|
|
"learning_rate": 0.00011949999999999999,
|
||
|
|
"loss": 7.5329,
|
||
|
|
"mean_token_accuracy": 0.06801014207303524,
|
||
|
|
"num_tokens": 419380.0,
|
||
|
|
"step": 240
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.891967344284057,
|
||
|
|
"epoch": 0.01906243921416067,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.000122,
|
||
|
|
"loss": 7.4564,
|
||
|
|
"mean_token_accuracy": 0.06902936287224293,
|
||
|
|
"num_tokens": 427682.0,
|
||
|
|
"step": 245
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.861574316024781,
|
||
|
|
"epoch": 0.019451468585878234,
|
||
|
|
"grad_norm": 0.96875,
|
||
|
|
"learning_rate": 0.0001245,
|
||
|
|
"loss": 7.5409,
|
||
|
|
"mean_token_accuracy": 0.0647453736513853,
|
||
|
|
"num_tokens": 437708.0,
|
||
|
|
"step": 250
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.8262309551239015,
|
||
|
|
"epoch": 0.0198404979575958,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.000127,
|
||
|
|
"loss": 7.5126,
|
||
|
|
"mean_token_accuracy": 0.07395943552255631,
|
||
|
|
"num_tokens": 446480.0,
|
||
|
|
"step": 255
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.851358556747437,
|
||
|
|
"epoch": 0.020229527329313362,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.0001295,
|
||
|
|
"loss": 7.5359,
|
||
|
|
"mean_token_accuracy": 0.06948852837085724,
|
||
|
|
"num_tokens": 455273.0,
|
||
|
|
"step": 260
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.842593669891357,
|
||
|
|
"epoch": 0.020618556701030927,
|
||
|
|
"grad_norm": 0.9453125,
|
||
|
|
"learning_rate": 0.000132,
|
||
|
|
"loss": 7.465,
|
||
|
|
"mean_token_accuracy": 0.07136857807636261,
|
||
|
|
"num_tokens": 464306.0,
|
||
|
|
"step": 265
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.763935899734497,
|
||
|
|
"epoch": 0.021007586072748493,
|
||
|
|
"grad_norm": 0.984375,
|
||
|
|
"learning_rate": 0.00013450000000000002,
|
||
|
|
"loss": 7.465,
|
||
|
|
"mean_token_accuracy": 0.06971037797629834,
|
||
|
|
"num_tokens": 472812.0,
|
||
|
|
"step": 270
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.8695519924163815,
|
||
|
|
"epoch": 0.02139661544446606,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.00013700000000000002,
|
||
|
|
"loss": 7.4372,
|
||
|
|
"mean_token_accuracy": 0.07087112925946712,
|
||
|
|
"num_tokens": 481326.0,
|
||
|
|
"step": 275
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.783837080001831,
|
||
|
|
"epoch": 0.02178564481618362,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.0001395,
|
||
|
|
"loss": 7.386,
|
||
|
|
"mean_token_accuracy": 0.07493826448917389,
|
||
|
|
"num_tokens": 489147.0,
|
||
|
|
"step": 280
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.839688062667847,
|
||
|
|
"epoch": 0.022174674187901186,
|
||
|
|
"grad_norm": 1.15625,
|
||
|
|
"learning_rate": 0.00014199999999999998,
|
||
|
|
"loss": 7.3969,
|
||
|
|
"mean_token_accuracy": 0.07674465849995613,
|
||
|
|
"num_tokens": 497455.0,
|
||
|
|
"step": 285
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.756985473632812,
|
||
|
|
"epoch": 0.02256370355961875,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.0001445,
|
||
|
|
"loss": 7.3386,
|
||
|
|
"mean_token_accuracy": 0.07174206636846066,
|
||
|
|
"num_tokens": 506735.0,
|
||
|
|
"step": 290
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.69587721824646,
|
||
|
|
"epoch": 0.022952732931336317,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.000147,
|
||
|
|
"loss": 7.4096,
|
||
|
|
"mean_token_accuracy": 0.07052636668086051,
|
||
|
|
"num_tokens": 515976.0,
|
||
|
|
"step": 295
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.748194456100464,
|
||
|
|
"epoch": 0.02334176230305388,
|
||
|
|
"grad_norm": 1.4375,
|
||
|
|
"learning_rate": 0.0001495,
|
||
|
|
"loss": 7.4103,
|
||
|
|
"mean_token_accuracy": 0.07094176150858403,
|
||
|
|
"num_tokens": 524986.0,
|
||
|
|
"step": 300
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.740332698822021,
|
||
|
|
"epoch": 0.023730791674771445,
|
||
|
|
"grad_norm": 1.203125,
|
||
|
|
"learning_rate": 0.000152,
|
||
|
|
"loss": 7.4071,
|
||
|
|
"mean_token_accuracy": 0.07837972790002823,
|
||
|
|
"num_tokens": 533146.0,
|
||
|
|
"step": 305
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.687754583358765,
|
||
|
|
"epoch": 0.02411982104648901,
|
||
|
|
"grad_norm": 0.9921875,
|
||
|
|
"learning_rate": 0.00015450000000000001,
|
||
|
|
"loss": 7.3068,
|
||
|
|
"mean_token_accuracy": 0.07906603664159775,
|
||
|
|
"num_tokens": 541704.0,
|
||
|
|
"step": 310
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.6879466533660885,
|
||
|
|
"epoch": 0.024508850418206576,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 0.000157,
|
||
|
|
"loss": 7.2855,
|
||
|
|
"mean_token_accuracy": 0.07894096970558166,
|
||
|
|
"num_tokens": 550088.0,
|
||
|
|
"step": 315
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.648388147354126,
|
||
|
|
"epoch": 0.024897879789924138,
|
||
|
|
"grad_norm": 1.1796875,
|
||
|
|
"learning_rate": 0.0001595,
|
||
|
|
"loss": 7.2823,
|
||
|
|
"mean_token_accuracy": 0.0771455705165863,
|
||
|
|
"num_tokens": 558763.0,
|
||
|
|
"step": 320
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.7199187755584715,
|
||
|
|
"epoch": 0.025286909161641703,
|
||
|
|
"grad_norm": 1.34375,
|
||
|
|
"learning_rate": 0.000162,
|
||
|
|
"loss": 7.3686,
|
||
|
|
"mean_token_accuracy": 0.07701200395822524,
|
||
|
|
"num_tokens": 567538.0,
|
||
|
|
"step": 325
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.674441337585449,
|
||
|
|
"epoch": 0.02567593853335927,
|
||
|
|
"grad_norm": 1.15625,
|
||
|
|
"learning_rate": 0.00016450000000000001,
|
||
|
|
"loss": 7.392,
|
||
|
|
"mean_token_accuracy": 0.07433984279632569,
|
||
|
|
"num_tokens": 577626.0,
|
||
|
|
"step": 330
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.577795839309692,
|
||
|
|
"epoch": 0.026064967905076834,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.00016700000000000002,
|
||
|
|
"loss": 7.3307,
|
||
|
|
"mean_token_accuracy": 0.0771209366619587,
|
||
|
|
"num_tokens": 587163.0,
|
||
|
|
"step": 335
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.641181945800781,
|
||
|
|
"epoch": 0.026453997276794396,
|
||
|
|
"grad_norm": 0.98828125,
|
||
|
|
"learning_rate": 0.00016950000000000003,
|
||
|
|
"loss": 7.2974,
|
||
|
|
"mean_token_accuracy": 0.07834560088813305,
|
||
|
|
"num_tokens": 595896.0,
|
||
|
|
"step": 340
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.7260040760040285,
|
||
|
|
"epoch": 0.026843026648511962,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.00017199999999999998,
|
||
|
|
"loss": 7.3103,
|
||
|
|
"mean_token_accuracy": 0.07935898192226887,
|
||
|
|
"num_tokens": 603815.0,
|
||
|
|
"step": 345
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.639403676986694,
|
||
|
|
"epoch": 0.027232056020229527,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.00017449999999999999,
|
||
|
|
"loss": 7.3426,
|
||
|
|
"mean_token_accuracy": 0.07771432399749756,
|
||
|
|
"num_tokens": 612208.0,
|
||
|
|
"step": 350
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.6438861846923825,
|
||
|
|
"epoch": 0.027621085391947093,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.000177,
|
||
|
|
"loss": 7.3047,
|
||
|
|
"mean_token_accuracy": 0.08054265901446342,
|
||
|
|
"num_tokens": 621840.0,
|
||
|
|
"step": 355
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.623253965377808,
|
||
|
|
"epoch": 0.028010114763664655,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.0001795,
|
||
|
|
"loss": 7.302,
|
||
|
|
"mean_token_accuracy": 0.07845958769321441,
|
||
|
|
"num_tokens": 630770.0,
|
||
|
|
"step": 360
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.586232614517212,
|
||
|
|
"epoch": 0.02839914413538222,
|
||
|
|
"grad_norm": 1.375,
|
||
|
|
"learning_rate": 0.000182,
|
||
|
|
"loss": 7.3025,
|
||
|
|
"mean_token_accuracy": 0.07674148865044117,
|
||
|
|
"num_tokens": 640313.0,
|
||
|
|
"step": 365
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.703115844726563,
|
||
|
|
"epoch": 0.028788173507099786,
|
||
|
|
"grad_norm": 1.3515625,
|
||
|
|
"learning_rate": 0.0001845,
|
||
|
|
"loss": 7.3352,
|
||
|
|
"mean_token_accuracy": 0.08353722617030143,
|
||
|
|
"num_tokens": 648594.0,
|
||
|
|
"step": 370
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.667205572128296,
|
||
|
|
"epoch": 0.02917720287881735,
|
||
|
|
"grad_norm": 1.4765625,
|
||
|
|
"learning_rate": 0.000187,
|
||
|
|
"loss": 7.3262,
|
||
|
|
"mean_token_accuracy": 0.0825626440346241,
|
||
|
|
"num_tokens": 656478.0,
|
||
|
|
"step": 375
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.610483121871948,
|
||
|
|
"epoch": 0.029566232250534917,
|
||
|
|
"grad_norm": 1.3203125,
|
||
|
|
"learning_rate": 0.0001895,
|
||
|
|
"loss": 7.2807,
|
||
|
|
"mean_token_accuracy": 0.08631925098598003,
|
||
|
|
"num_tokens": 665405.0,
|
||
|
|
"step": 380
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.60249695777893,
|
||
|
|
"epoch": 0.02995526162225248,
|
||
|
|
"grad_norm": 1.53125,
|
||
|
|
"learning_rate": 0.000192,
|
||
|
|
"loss": 7.298,
|
||
|
|
"mean_token_accuracy": 0.08242034763097764,
|
||
|
|
"num_tokens": 674301.0,
|
||
|
|
"step": 385
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.5917730808258055,
|
||
|
|
"epoch": 0.030344290993970045,
|
||
|
|
"grad_norm": 1.359375,
|
||
|
|
"learning_rate": 0.0001945,
|
||
|
|
"loss": 7.3025,
|
||
|
|
"mean_token_accuracy": 0.08338480368256569,
|
||
|
|
"num_tokens": 683159.0,
|
||
|
|
"step": 390
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.459813356399536,
|
||
|
|
"epoch": 0.03073332036568761,
|
||
|
|
"grad_norm": 1.2265625,
|
||
|
|
"learning_rate": 0.00019700000000000002,
|
||
|
|
"loss": 7.1421,
|
||
|
|
"mean_token_accuracy": 0.08484522178769112,
|
||
|
|
"num_tokens": 690992.0,
|
||
|
|
"step": 395
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.521260738372803,
|
||
|
|
"epoch": 0.031122349737405176,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.00019950000000000002,
|
||
|
|
"loss": 7.2325,
|
||
|
|
"mean_token_accuracy": 0.0865586407482624,
|
||
|
|
"num_tokens": 699934.0,
|
||
|
|
"step": 400
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.689074850082397,
|
||
|
|
"epoch": 0.03151137910912274,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.000202,
|
||
|
|
"loss": 7.2634,
|
||
|
|
"mean_token_accuracy": 0.08598847389221191,
|
||
|
|
"num_tokens": 708844.0,
|
||
|
|
"step": 405
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.583835411071777,
|
||
|
|
"epoch": 0.0319004084808403,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.00020449999999999998,
|
||
|
|
"loss": 7.3307,
|
||
|
|
"mean_token_accuracy": 0.07737800255417823,
|
||
|
|
"num_tokens": 718148.0,
|
||
|
|
"step": 410
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.633756828308106,
|
||
|
|
"epoch": 0.03228943785255787,
|
||
|
|
"grad_norm": 1.46875,
|
||
|
|
"learning_rate": 0.000207,
|
||
|
|
"loss": 7.2544,
|
||
|
|
"mean_token_accuracy": 0.07819749228656292,
|
||
|
|
"num_tokens": 726859.0,
|
||
|
|
"step": 415
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.554245710372925,
|
||
|
|
"epoch": 0.032678467224275434,
|
||
|
|
"grad_norm": 1.2109375,
|
||
|
|
"learning_rate": 0.0002095,
|
||
|
|
"loss": 7.246,
|
||
|
|
"mean_token_accuracy": 0.08443724215030671,
|
||
|
|
"num_tokens": 735045.0,
|
||
|
|
"step": 420
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.451032447814941,
|
||
|
|
"epoch": 0.033067496595993,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.000212,
|
||
|
|
"loss": 7.1407,
|
||
|
|
"mean_token_accuracy": 0.08672306761145591,
|
||
|
|
"num_tokens": 743538.0,
|
||
|
|
"step": 425
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.555552005767822,
|
||
|
|
"epoch": 0.033456525967710565,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.0002145,
|
||
|
|
"loss": 7.1863,
|
||
|
|
"mean_token_accuracy": 0.08307315856218338,
|
||
|
|
"num_tokens": 752518.0,
|
||
|
|
"step": 430
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.4741191387176515,
|
||
|
|
"epoch": 0.033845555339428124,
|
||
|
|
"grad_norm": 1.1796875,
|
||
|
|
"learning_rate": 0.00021700000000000002,
|
||
|
|
"loss": 7.2221,
|
||
|
|
"mean_token_accuracy": 0.0827447958290577,
|
||
|
|
"num_tokens": 760354.0,
|
||
|
|
"step": 435
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.546918106079102,
|
||
|
|
"epoch": 0.03423458471114569,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.0002195,
|
||
|
|
"loss": 7.2616,
|
||
|
|
"mean_token_accuracy": 0.08273635283112526,
|
||
|
|
"num_tokens": 769522.0,
|
||
|
|
"step": 440
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.495674991607666,
|
||
|
|
"epoch": 0.034623614082863255,
|
||
|
|
"grad_norm": 1.4609375,
|
||
|
|
"learning_rate": 0.000222,
|
||
|
|
"loss": 7.2017,
|
||
|
|
"mean_token_accuracy": 0.08487647026777267,
|
||
|
|
"num_tokens": 778548.0,
|
||
|
|
"step": 445
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.38130784034729,
|
||
|
|
"epoch": 0.03501264345458082,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 0.0002245,
|
||
|
|
"loss": 7.2101,
|
||
|
|
"mean_token_accuracy": 0.0793451689183712,
|
||
|
|
"num_tokens": 787666.0,
|
||
|
|
"step": 450
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.549726963043213,
|
||
|
|
"epoch": 0.035401672826298386,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.00022700000000000002,
|
||
|
|
"loss": 7.1139,
|
||
|
|
"mean_token_accuracy": 0.08504968136548996,
|
||
|
|
"num_tokens": 796550.0,
|
||
|
|
"step": 455
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.504650354385376,
|
||
|
|
"epoch": 0.03579070219801595,
|
||
|
|
"grad_norm": 1.796875,
|
||
|
|
"learning_rate": 0.00022950000000000002,
|
||
|
|
"loss": 7.1867,
|
||
|
|
"mean_token_accuracy": 0.08266782015562057,
|
||
|
|
"num_tokens": 804549.0,
|
||
|
|
"step": 460
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.351037645339966,
|
||
|
|
"epoch": 0.03617973156973352,
|
||
|
|
"grad_norm": 1.8125,
|
||
|
|
"learning_rate": 0.00023200000000000003,
|
||
|
|
"loss": 7.1745,
|
||
|
|
"mean_token_accuracy": 0.0821124792098999,
|
||
|
|
"num_tokens": 813328.0,
|
||
|
|
"step": 465
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.462553834915161,
|
||
|
|
"epoch": 0.03656876094145108,
|
||
|
|
"grad_norm": 1.15625,
|
||
|
|
"learning_rate": 0.00023449999999999998,
|
||
|
|
"loss": 7.1959,
|
||
|
|
"mean_token_accuracy": 0.08460092917084694,
|
||
|
|
"num_tokens": 821733.0,
|
||
|
|
"step": 470
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.480328607559204,
|
||
|
|
"epoch": 0.03695779031316864,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.000237,
|
||
|
|
"loss": 7.1285,
|
||
|
|
"mean_token_accuracy": 0.09022513628005982,
|
||
|
|
"num_tokens": 830243.0,
|
||
|
|
"step": 475
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.4883809089660645,
|
||
|
|
"epoch": 0.03734681968488621,
|
||
|
|
"grad_norm": 1.359375,
|
||
|
|
"learning_rate": 0.0002395,
|
||
|
|
"loss": 7.1151,
|
||
|
|
"mean_token_accuracy": 0.08559876456856727,
|
||
|
|
"num_tokens": 839059.0,
|
||
|
|
"step": 480
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.358342885971069,
|
||
|
|
"epoch": 0.03773584905660377,
|
||
|
|
"grad_norm": 1.1640625,
|
||
|
|
"learning_rate": 0.000242,
|
||
|
|
"loss": 7.0025,
|
||
|
|
"mean_token_accuracy": 0.09025049507617951,
|
||
|
|
"num_tokens": 846932.0,
|
||
|
|
"step": 485
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.452124309539795,
|
||
|
|
"epoch": 0.03812487842832134,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.0002445,
|
||
|
|
"loss": 7.189,
|
||
|
|
"mean_token_accuracy": 0.08558763191103935,
|
||
|
|
"num_tokens": 855333.0,
|
||
|
|
"step": 490
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.272187662124634,
|
||
|
|
"epoch": 0.0385139078000389,
|
||
|
|
"grad_norm": 1.171875,
|
||
|
|
"learning_rate": 0.000247,
|
||
|
|
"loss": 6.9548,
|
||
|
|
"mean_token_accuracy": 0.08893074840307236,
|
||
|
|
"num_tokens": 863571.0,
|
||
|
|
"step": 495
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.292969179153443,
|
||
|
|
"epoch": 0.03890293717175647,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0002495,
|
||
|
|
"loss": 7.0493,
|
||
|
|
"mean_token_accuracy": 0.09270301833748817,
|
||
|
|
"num_tokens": 872145.0,
|
||
|
|
"step": 500
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.372188377380371,
|
||
|
|
"epoch": 0.039291966543474034,
|
||
|
|
"grad_norm": 1.1640625,
|
||
|
|
"learning_rate": 0.000252,
|
||
|
|
"loss": 7.0977,
|
||
|
|
"mean_token_accuracy": 0.09041493535041809,
|
||
|
|
"num_tokens": 880634.0,
|
||
|
|
"step": 505
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.319440698623657,
|
||
|
|
"epoch": 0.0396809959151916,
|
||
|
|
"grad_norm": 1.25,
|
||
|
|
"learning_rate": 0.0002545,
|
||
|
|
"loss": 7.0217,
|
||
|
|
"mean_token_accuracy": 0.09262948110699654,
|
||
|
|
"num_tokens": 889178.0,
|
||
|
|
"step": 510
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.348286437988281,
|
||
|
|
"epoch": 0.04007002528690916,
|
||
|
|
"grad_norm": 1.234375,
|
||
|
|
"learning_rate": 0.000257,
|
||
|
|
"loss": 7.0317,
|
||
|
|
"mean_token_accuracy": 0.0870862402021885,
|
||
|
|
"num_tokens": 898255.0,
|
||
|
|
"step": 515
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.30951418876648,
|
||
|
|
"epoch": 0.040459054658626724,
|
||
|
|
"grad_norm": 1.390625,
|
||
|
|
"learning_rate": 0.0002595,
|
||
|
|
"loss": 7.0797,
|
||
|
|
"mean_token_accuracy": 0.08530072048306465,
|
||
|
|
"num_tokens": 907369.0,
|
||
|
|
"step": 520
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.279186010360718,
|
||
|
|
"epoch": 0.04084808403034429,
|
||
|
|
"grad_norm": 1.3046875,
|
||
|
|
"learning_rate": 0.000262,
|
||
|
|
"loss": 6.9894,
|
||
|
|
"mean_token_accuracy": 0.08949219137430191,
|
||
|
|
"num_tokens": 915946.0,
|
||
|
|
"step": 525
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.312940263748169,
|
||
|
|
"epoch": 0.041237113402061855,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.00026450000000000003,
|
||
|
|
"loss": 7.0555,
|
||
|
|
"mean_token_accuracy": 0.08699819520115852,
|
||
|
|
"num_tokens": 925579.0,
|
||
|
|
"step": 530
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.287747240066528,
|
||
|
|
"epoch": 0.04162614277377942,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.00026700000000000004,
|
||
|
|
"loss": 7.051,
|
||
|
|
"mean_token_accuracy": 0.08002875968813897,
|
||
|
|
"num_tokens": 934732.0,
|
||
|
|
"step": 535
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.365451860427856,
|
||
|
|
"epoch": 0.042015172145496986,
|
||
|
|
"grad_norm": 1.25,
|
||
|
|
"learning_rate": 0.00026950000000000005,
|
||
|
|
"loss": 7.093,
|
||
|
|
"mean_token_accuracy": 0.08397311195731164,
|
||
|
|
"num_tokens": 943371.0,
|
||
|
|
"step": 540
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.219664525985718,
|
||
|
|
"epoch": 0.04240420151721455,
|
||
|
|
"grad_norm": 1.203125,
|
||
|
|
"learning_rate": 0.00027200000000000005,
|
||
|
|
"loss": 6.9402,
|
||
|
|
"mean_token_accuracy": 0.0904044933617115,
|
||
|
|
"num_tokens": 951977.0,
|
||
|
|
"step": 545
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.254467868804932,
|
||
|
|
"epoch": 0.04279323088893212,
|
||
|
|
"grad_norm": 1.1640625,
|
||
|
|
"learning_rate": 0.0002745,
|
||
|
|
"loss": 6.9391,
|
||
|
|
"mean_token_accuracy": 0.0922541782259941,
|
||
|
|
"num_tokens": 960474.0,
|
||
|
|
"step": 550
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.333742237091064,
|
||
|
|
"epoch": 0.04318226026064968,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.000277,
|
||
|
|
"loss": 7.0511,
|
||
|
|
"mean_token_accuracy": 0.09165818765759468,
|
||
|
|
"num_tokens": 969823.0,
|
||
|
|
"step": 555
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.292873668670654,
|
||
|
|
"epoch": 0.04357128963236724,
|
||
|
|
"grad_norm": 1.2890625,
|
||
|
|
"learning_rate": 0.0002795,
|
||
|
|
"loss": 6.986,
|
||
|
|
"mean_token_accuracy": 0.09415137693285942,
|
||
|
|
"num_tokens": 977417.0,
|
||
|
|
"step": 560
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.079999351501465,
|
||
|
|
"epoch": 0.04396031900408481,
|
||
|
|
"grad_norm": 1.2109375,
|
||
|
|
"learning_rate": 0.00028199999999999997,
|
||
|
|
"loss": 6.9884,
|
||
|
|
"mean_token_accuracy": 0.10306930914521217,
|
||
|
|
"num_tokens": 985519.0,
|
||
|
|
"step": 565
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.27137303352356,
|
||
|
|
"epoch": 0.04434934837580237,
|
||
|
|
"grad_norm": 1.2578125,
|
||
|
|
"learning_rate": 0.0002845,
|
||
|
|
"loss": 6.9794,
|
||
|
|
"mean_token_accuracy": 0.09349554628133774,
|
||
|
|
"num_tokens": 994136.0,
|
||
|
|
"step": 570
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.154263257980347,
|
||
|
|
"epoch": 0.04473837774751994,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.000287,
|
||
|
|
"loss": 6.9517,
|
||
|
|
"mean_token_accuracy": 0.09410769864916801,
|
||
|
|
"num_tokens": 1002896.0,
|
||
|
|
"step": 575
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.334334993362427,
|
||
|
|
"epoch": 0.0451274071192375,
|
||
|
|
"grad_norm": 1.21875,
|
||
|
|
"learning_rate": 0.0002895,
|
||
|
|
"loss": 7.0187,
|
||
|
|
"mean_token_accuracy": 0.09660950601100922,
|
||
|
|
"num_tokens": 1011032.0,
|
||
|
|
"step": 580
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.145978736877441,
|
||
|
|
"epoch": 0.04551643649095507,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.000292,
|
||
|
|
"loss": 6.9924,
|
||
|
|
"mean_token_accuracy": 0.0898567907512188,
|
||
|
|
"num_tokens": 1019901.0,
|
||
|
|
"step": 585
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.253001117706299,
|
||
|
|
"epoch": 0.045905465862672634,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.0002945,
|
||
|
|
"loss": 6.9853,
|
||
|
|
"mean_token_accuracy": 0.09278224185109138,
|
||
|
|
"num_tokens": 1029049.0,
|
||
|
|
"step": 590
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.109061622619629,
|
||
|
|
"epoch": 0.0462944952343902,
|
||
|
|
"grad_norm": 1.140625,
|
||
|
|
"learning_rate": 0.000297,
|
||
|
|
"loss": 6.9351,
|
||
|
|
"mean_token_accuracy": 0.10167267620563507,
|
||
|
|
"num_tokens": 1037580.0,
|
||
|
|
"step": 595
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.2255167961120605,
|
||
|
|
"epoch": 0.04668352460610776,
|
||
|
|
"grad_norm": 1.3203125,
|
||
|
|
"learning_rate": 0.0002995,
|
||
|
|
"loss": 7.0098,
|
||
|
|
"mean_token_accuracy": 0.0949100524187088,
|
||
|
|
"num_tokens": 1045804.0,
|
||
|
|
"step": 600
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.198540210723877,
|
||
|
|
"epoch": 0.047072553977825324,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.000302,
|
||
|
|
"loss": 6.9746,
|
||
|
|
"mean_token_accuracy": 0.08983623161911965,
|
||
|
|
"num_tokens": 1054719.0,
|
||
|
|
"step": 605
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.234898900985717,
|
||
|
|
"epoch": 0.04746158334954289,
|
||
|
|
"grad_norm": 1.1953125,
|
||
|
|
"learning_rate": 0.0003045,
|
||
|
|
"loss": 6.9403,
|
||
|
|
"mean_token_accuracy": 0.09563231095671654,
|
||
|
|
"num_tokens": 1063373.0,
|
||
|
|
"step": 610
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.065098714828491,
|
||
|
|
"epoch": 0.047850612721260455,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.000307,
|
||
|
|
"loss": 6.9348,
|
||
|
|
"mean_token_accuracy": 0.09286908954381942,
|
||
|
|
"num_tokens": 1073021.0,
|
||
|
|
"step": 615
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.1705584049224855,
|
||
|
|
"epoch": 0.04823964209297802,
|
||
|
|
"grad_norm": 1.234375,
|
||
|
|
"learning_rate": 0.0003095,
|
||
|
|
"loss": 6.9828,
|
||
|
|
"mean_token_accuracy": 0.0865123376250267,
|
||
|
|
"num_tokens": 1081547.0,
|
||
|
|
"step": 620
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.136169195175171,
|
||
|
|
"epoch": 0.048628671464695586,
|
||
|
|
"grad_norm": 1.2421875,
|
||
|
|
"learning_rate": 0.000312,
|
||
|
|
"loss": 6.9483,
|
||
|
|
"mean_token_accuracy": 0.08919977843761444,
|
||
|
|
"num_tokens": 1090695.0,
|
||
|
|
"step": 625
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.059012079238892,
|
||
|
|
"epoch": 0.04901770083641315,
|
||
|
|
"grad_norm": 1.15625,
|
||
|
|
"learning_rate": 0.0003145,
|
||
|
|
"loss": 6.8458,
|
||
|
|
"mean_token_accuracy": 0.09551393389701843,
|
||
|
|
"num_tokens": 1099563.0,
|
||
|
|
"step": 630
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.09900312423706,
|
||
|
|
"epoch": 0.04940673020813072,
|
||
|
|
"grad_norm": 1.140625,
|
||
|
|
"learning_rate": 0.000317,
|
||
|
|
"loss": 6.9189,
|
||
|
|
"mean_token_accuracy": 0.09224364534020424,
|
||
|
|
"num_tokens": 1109021.0,
|
||
|
|
"step": 635
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.17626314163208,
|
||
|
|
"epoch": 0.049795759579848276,
|
||
|
|
"grad_norm": 1.1953125,
|
||
|
|
"learning_rate": 0.0003195,
|
||
|
|
"loss": 6.9065,
|
||
|
|
"mean_token_accuracy": 0.09903016537427903,
|
||
|
|
"num_tokens": 1118281.0,
|
||
|
|
"step": 640
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.107364559173584,
|
||
|
|
"epoch": 0.05018478895156584,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.000322,
|
||
|
|
"loss": 6.964,
|
||
|
|
"mean_token_accuracy": 0.08841050490736961,
|
||
|
|
"num_tokens": 1127513.0,
|
||
|
|
"step": 645
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.992545318603516,
|
||
|
|
"epoch": 0.05057381832328341,
|
||
|
|
"grad_norm": 1.2265625,
|
||
|
|
"learning_rate": 0.00032450000000000003,
|
||
|
|
"loss": 6.8344,
|
||
|
|
"mean_token_accuracy": 0.09609550759196281,
|
||
|
|
"num_tokens": 1136140.0,
|
||
|
|
"step": 650
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.074442529678345,
|
||
|
|
"epoch": 0.05096284769500097,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.00032700000000000003,
|
||
|
|
"loss": 6.8501,
|
||
|
|
"mean_token_accuracy": 0.09899003729224205,
|
||
|
|
"num_tokens": 1144297.0,
|
||
|
|
"step": 655
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.111178350448609,
|
||
|
|
"epoch": 0.05135187706671854,
|
||
|
|
"grad_norm": 1.21875,
|
||
|
|
"learning_rate": 0.00032950000000000004,
|
||
|
|
"loss": 6.9436,
|
||
|
|
"mean_token_accuracy": 0.09194107502698898,
|
||
|
|
"num_tokens": 1153639.0,
|
||
|
|
"step": 660
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.128814029693603,
|
||
|
|
"epoch": 0.0517409064384361,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.00033200000000000005,
|
||
|
|
"loss": 6.9222,
|
||
|
|
"mean_token_accuracy": 0.0915698304772377,
|
||
|
|
"num_tokens": 1162825.0,
|
||
|
|
"step": 665
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.055984973907471,
|
||
|
|
"epoch": 0.05212993581015367,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 0.00033450000000000005,
|
||
|
|
"loss": 6.9361,
|
||
|
|
"mean_token_accuracy": 0.09659557938575744,
|
||
|
|
"num_tokens": 1171887.0,
|
||
|
|
"step": 670
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.070049524307251,
|
||
|
|
"epoch": 0.052518965181871234,
|
||
|
|
"grad_norm": 1.171875,
|
||
|
|
"learning_rate": 0.000337,
|
||
|
|
"loss": 6.8421,
|
||
|
|
"mean_token_accuracy": 0.09676870629191399,
|
||
|
|
"num_tokens": 1179963.0,
|
||
|
|
"step": 675
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.01722412109375,
|
||
|
|
"epoch": 0.05290799455358879,
|
||
|
|
"grad_norm": 1.1640625,
|
||
|
|
"learning_rate": 0.0003395,
|
||
|
|
"loss": 6.8121,
|
||
|
|
"mean_token_accuracy": 0.1057270735502243,
|
||
|
|
"num_tokens": 1188408.0,
|
||
|
|
"step": 680
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.035515451431275,
|
||
|
|
"epoch": 0.05329702392530636,
|
||
|
|
"grad_norm": 1.1875,
|
||
|
|
"learning_rate": 0.000342,
|
||
|
|
"loss": 6.8597,
|
||
|
|
"mean_token_accuracy": 0.09449592679738998,
|
||
|
|
"num_tokens": 1197751.0,
|
||
|
|
"step": 685
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.0010096549987795,
|
||
|
|
"epoch": 0.053686053297023924,
|
||
|
|
"grad_norm": 1.25,
|
||
|
|
"learning_rate": 0.00034449999999999997,
|
||
|
|
"loss": 6.906,
|
||
|
|
"mean_token_accuracy": 0.09311776012182235,
|
||
|
|
"num_tokens": 1207101.0,
|
||
|
|
"step": 690
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.023842525482178,
|
||
|
|
"epoch": 0.05407508266874149,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.000347,
|
||
|
|
"loss": 6.8788,
|
||
|
|
"mean_token_accuracy": 0.0990625761449337,
|
||
|
|
"num_tokens": 1216395.0,
|
||
|
|
"step": 695
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.073128890991211,
|
||
|
|
"epoch": 0.054464112040459055,
|
||
|
|
"grad_norm": 1.1640625,
|
||
|
|
"learning_rate": 0.0003495,
|
||
|
|
"loss": 6.8717,
|
||
|
|
"mean_token_accuracy": 0.09589955136179924,
|
||
|
|
"num_tokens": 1225496.0,
|
||
|
|
"step": 700
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.041469240188599,
|
||
|
|
"epoch": 0.05485314141217662,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.000352,
|
||
|
|
"loss": 6.9301,
|
||
|
|
"mean_token_accuracy": 0.09590573534369469,
|
||
|
|
"num_tokens": 1233934.0,
|
||
|
|
"step": 705
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.04399471282959,
|
||
|
|
"epoch": 0.055242170783894186,
|
||
|
|
"grad_norm": 1.265625,
|
||
|
|
"learning_rate": 0.0003545,
|
||
|
|
"loss": 6.7922,
|
||
|
|
"mean_token_accuracy": 0.10261676609516143,
|
||
|
|
"num_tokens": 1242165.0,
|
||
|
|
"step": 710
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.965677070617676,
|
||
|
|
"epoch": 0.05563120015561175,
|
||
|
|
"grad_norm": 1.3046875,
|
||
|
|
"learning_rate": 0.000357,
|
||
|
|
"loss": 6.852,
|
||
|
|
"mean_token_accuracy": 0.10717706456780433,
|
||
|
|
"num_tokens": 1250021.0,
|
||
|
|
"step": 715
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.072294569015503,
|
||
|
|
"epoch": 0.05602022952732931,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.0003595,
|
||
|
|
"loss": 6.8828,
|
||
|
|
"mean_token_accuracy": 0.09521595239639283,
|
||
|
|
"num_tokens": 1258397.0,
|
||
|
|
"step": 720
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.938068056106568,
|
||
|
|
"epoch": 0.056409258899046875,
|
||
|
|
"grad_norm": 1.265625,
|
||
|
|
"learning_rate": 0.000362,
|
||
|
|
"loss": 6.8759,
|
||
|
|
"mean_token_accuracy": 0.09533992037177086,
|
||
|
|
"num_tokens": 1266764.0,
|
||
|
|
"step": 725
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.03787579536438,
|
||
|
|
"epoch": 0.05679828827076444,
|
||
|
|
"grad_norm": 1.28125,
|
||
|
|
"learning_rate": 0.0003645,
|
||
|
|
"loss": 6.871,
|
||
|
|
"mean_token_accuracy": 0.09679570645093918,
|
||
|
|
"num_tokens": 1275643.0,
|
||
|
|
"step": 730
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.005536794662476,
|
||
|
|
"epoch": 0.057187317642482006,
|
||
|
|
"grad_norm": 1.171875,
|
||
|
|
"learning_rate": 0.000367,
|
||
|
|
"loss": 6.8628,
|
||
|
|
"mean_token_accuracy": 0.09435820877552033,
|
||
|
|
"num_tokens": 1284379.0,
|
||
|
|
"step": 735
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.9134307384490965,
|
||
|
|
"epoch": 0.05757634701419957,
|
||
|
|
"grad_norm": 1.1953125,
|
||
|
|
"learning_rate": 0.0003695,
|
||
|
|
"loss": 6.7031,
|
||
|
|
"mean_token_accuracy": 0.10279496237635613,
|
||
|
|
"num_tokens": 1293115.0,
|
||
|
|
"step": 740
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.002116298675537,
|
||
|
|
"epoch": 0.05796537638591714,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.000372,
|
||
|
|
"loss": 6.8861,
|
||
|
|
"mean_token_accuracy": 0.09175937101244927,
|
||
|
|
"num_tokens": 1301583.0,
|
||
|
|
"step": 745
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.992090654373169,
|
||
|
|
"epoch": 0.0583544057576347,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.0003745,
|
||
|
|
"loss": 6.7932,
|
||
|
|
"mean_token_accuracy": 0.10047848448157311,
|
||
|
|
"num_tokens": 1310721.0,
|
||
|
|
"step": 750
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.046376800537109,
|
||
|
|
"epoch": 0.05874343512935227,
|
||
|
|
"grad_norm": 1.4296875,
|
||
|
|
"learning_rate": 0.000377,
|
||
|
|
"loss": 6.9584,
|
||
|
|
"mean_token_accuracy": 0.09057950675487518,
|
||
|
|
"num_tokens": 1319056.0,
|
||
|
|
"step": 755
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.978992366790772,
|
||
|
|
"epoch": 0.059132464501069834,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.0003795,
|
||
|
|
"loss": 6.8188,
|
||
|
|
"mean_token_accuracy": 0.09845160394906997,
|
||
|
|
"num_tokens": 1327259.0,
|
||
|
|
"step": 760
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.802176570892334,
|
||
|
|
"epoch": 0.05952149387278739,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.000382,
|
||
|
|
"loss": 6.7344,
|
||
|
|
"mean_token_accuracy": 0.10277749001979827,
|
||
|
|
"num_tokens": 1335906.0,
|
||
|
|
"step": 765
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.969279003143311,
|
||
|
|
"epoch": 0.05991052324450496,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0003845,
|
||
|
|
"loss": 6.7815,
|
||
|
|
"mean_token_accuracy": 0.09497542083263397,
|
||
|
|
"num_tokens": 1344743.0,
|
||
|
|
"step": 770
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.937004804611206,
|
||
|
|
"epoch": 0.060299552616222524,
|
||
|
|
"grad_norm": 1.1640625,
|
||
|
|
"learning_rate": 0.00038700000000000003,
|
||
|
|
"loss": 6.7824,
|
||
|
|
"mean_token_accuracy": 0.10425732806324958,
|
||
|
|
"num_tokens": 1353211.0,
|
||
|
|
"step": 775
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.98970251083374,
|
||
|
|
"epoch": 0.06068858198794009,
|
||
|
|
"grad_norm": 1.140625,
|
||
|
|
"learning_rate": 0.00038950000000000003,
|
||
|
|
"loss": 6.8914,
|
||
|
|
"mean_token_accuracy": 0.09508336558938027,
|
||
|
|
"num_tokens": 1361849.0,
|
||
|
|
"step": 780
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.0657209873199465,
|
||
|
|
"epoch": 0.061077611359657655,
|
||
|
|
"grad_norm": 1.2109375,
|
||
|
|
"learning_rate": 0.00039200000000000004,
|
||
|
|
"loss": 6.8692,
|
||
|
|
"mean_token_accuracy": 0.09809008985757828,
|
||
|
|
"num_tokens": 1369804.0,
|
||
|
|
"step": 785
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.779054069519043,
|
||
|
|
"epoch": 0.06146664073137522,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.00039450000000000005,
|
||
|
|
"loss": 6.6693,
|
||
|
|
"mean_token_accuracy": 0.10079652965068817,
|
||
|
|
"num_tokens": 1378478.0,
|
||
|
|
"step": 790
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.980751800537109,
|
||
|
|
"epoch": 0.061855670103092786,
|
||
|
|
"grad_norm": 1.2734375,
|
||
|
|
"learning_rate": 0.00039700000000000005,
|
||
|
|
"loss": 6.7786,
|
||
|
|
"mean_token_accuracy": 0.10327165126800537,
|
||
|
|
"num_tokens": 1387225.0,
|
||
|
|
"step": 795
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.81693058013916,
|
||
|
|
"epoch": 0.06224469947481035,
|
||
|
|
"grad_norm": 1.171875,
|
||
|
|
"learning_rate": 0.0003995,
|
||
|
|
"loss": 6.7366,
|
||
|
|
"mean_token_accuracy": 0.10770381912589073,
|
||
|
|
"num_tokens": 1395338.0,
|
||
|
|
"step": 800
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.881891345977783,
|
||
|
|
"epoch": 0.06263372884652792,
|
||
|
|
"grad_norm": 1.1640625,
|
||
|
|
"learning_rate": 0.000402,
|
||
|
|
"loss": 6.7277,
|
||
|
|
"mean_token_accuracy": 0.10118440762162209,
|
||
|
|
"num_tokens": 1403794.0,
|
||
|
|
"step": 805
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.83382511138916,
|
||
|
|
"epoch": 0.06302275821824548,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0004045,
|
||
|
|
"loss": 6.8108,
|
||
|
|
"mean_token_accuracy": 0.09670943543314933,
|
||
|
|
"num_tokens": 1412522.0,
|
||
|
|
"step": 810
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.897907876968384,
|
||
|
|
"epoch": 0.06341178758996305,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.00040699999999999997,
|
||
|
|
"loss": 6.77,
|
||
|
|
"mean_token_accuracy": 0.10105407387018203,
|
||
|
|
"num_tokens": 1421347.0,
|
||
|
|
"step": 815
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.901159429550171,
|
||
|
|
"epoch": 0.0638008169616806,
|
||
|
|
"grad_norm": 1.2890625,
|
||
|
|
"learning_rate": 0.0004095,
|
||
|
|
"loss": 6.764,
|
||
|
|
"mean_token_accuracy": 0.10549613162875175,
|
||
|
|
"num_tokens": 1429788.0,
|
||
|
|
"step": 820
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.920616817474365,
|
||
|
|
"epoch": 0.06418984633339817,
|
||
|
|
"grad_norm": 1.234375,
|
||
|
|
"learning_rate": 0.000412,
|
||
|
|
"loss": 6.7755,
|
||
|
|
"mean_token_accuracy": 0.1008368693292141,
|
||
|
|
"num_tokens": 1437442.0,
|
||
|
|
"step": 825
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.839075517654419,
|
||
|
|
"epoch": 0.06457887570511574,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.0004145,
|
||
|
|
"loss": 6.6952,
|
||
|
|
"mean_token_accuracy": 0.10623135343194008,
|
||
|
|
"num_tokens": 1445604.0,
|
||
|
|
"step": 830
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.784990549087524,
|
||
|
|
"epoch": 0.0649679050768333,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.000417,
|
||
|
|
"loss": 6.7381,
|
||
|
|
"mean_token_accuracy": 0.10426093637943268,
|
||
|
|
"num_tokens": 1454342.0,
|
||
|
|
"step": 835
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.8920652866363525,
|
||
|
|
"epoch": 0.06535693444855087,
|
||
|
|
"grad_norm": 1.1640625,
|
||
|
|
"learning_rate": 0.0004195,
|
||
|
|
"loss": 6.7367,
|
||
|
|
"mean_token_accuracy": 0.10608365461230278,
|
||
|
|
"num_tokens": 1463189.0,
|
||
|
|
"step": 840
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.890959739685059,
|
||
|
|
"epoch": 0.06574596382026843,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.000422,
|
||
|
|
"loss": 6.7978,
|
||
|
|
"mean_token_accuracy": 0.10302787348628044,
|
||
|
|
"num_tokens": 1471608.0,
|
||
|
|
"step": 845
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.851788759231567,
|
||
|
|
"epoch": 0.066134993191986,
|
||
|
|
"grad_norm": 1.171875,
|
||
|
|
"learning_rate": 0.0004245,
|
||
|
|
"loss": 6.8147,
|
||
|
|
"mean_token_accuracy": 0.09880862534046173,
|
||
|
|
"num_tokens": 1480452.0,
|
||
|
|
"step": 850
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.886212015151978,
|
||
|
|
"epoch": 0.06652402256370356,
|
||
|
|
"grad_norm": 1.15625,
|
||
|
|
"learning_rate": 0.000427,
|
||
|
|
"loss": 6.731,
|
||
|
|
"mean_token_accuracy": 0.10134131312370301,
|
||
|
|
"num_tokens": 1489118.0,
|
||
|
|
"step": 855
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.777446126937866,
|
||
|
|
"epoch": 0.06691305193542113,
|
||
|
|
"grad_norm": 1.28125,
|
||
|
|
"learning_rate": 0.0004295,
|
||
|
|
"loss": 6.7396,
|
||
|
|
"mean_token_accuracy": 0.10189275071024895,
|
||
|
|
"num_tokens": 1498961.0,
|
||
|
|
"step": 860
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.961002397537231,
|
||
|
|
"epoch": 0.06730208130713869,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.000432,
|
||
|
|
"loss": 6.7346,
|
||
|
|
"mean_token_accuracy": 0.10392786636948585,
|
||
|
|
"num_tokens": 1506772.0,
|
||
|
|
"step": 865
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.684235572814941,
|
||
|
|
"epoch": 0.06769111067885625,
|
||
|
|
"grad_norm": 1.1796875,
|
||
|
|
"learning_rate": 0.0004345,
|
||
|
|
"loss": 6.6058,
|
||
|
|
"mean_token_accuracy": 0.11117016151547432,
|
||
|
|
"num_tokens": 1515095.0,
|
||
|
|
"step": 870
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.75773983001709,
|
||
|
|
"epoch": 0.06808014005057382,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.000437,
|
||
|
|
"loss": 6.6385,
|
||
|
|
"mean_token_accuracy": 0.10891954004764556,
|
||
|
|
"num_tokens": 1523477.0,
|
||
|
|
"step": 875
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.817113065719605,
|
||
|
|
"epoch": 0.06846916942229138,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 0.0004395,
|
||
|
|
"loss": 6.685,
|
||
|
|
"mean_token_accuracy": 0.1045746587216854,
|
||
|
|
"num_tokens": 1531786.0,
|
||
|
|
"step": 880
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.726958084106445,
|
||
|
|
"epoch": 0.06885819879400895,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 0.000442,
|
||
|
|
"loss": 6.7751,
|
||
|
|
"mean_token_accuracy": 0.09731194078922271,
|
||
|
|
"num_tokens": 1540737.0,
|
||
|
|
"step": 885
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.791330051422119,
|
||
|
|
"epoch": 0.06924722816572651,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.0004445,
|
||
|
|
"loss": 6.6346,
|
||
|
|
"mean_token_accuracy": 0.10614737197756767,
|
||
|
|
"num_tokens": 1548923.0,
|
||
|
|
"step": 890
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.754159545898437,
|
||
|
|
"epoch": 0.06963625753744408,
|
||
|
|
"grad_norm": 1.2734375,
|
||
|
|
"learning_rate": 0.000447,
|
||
|
|
"loss": 6.5903,
|
||
|
|
"mean_token_accuracy": 0.11033120304346085,
|
||
|
|
"num_tokens": 1557043.0,
|
||
|
|
"step": 895
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.731679964065552,
|
||
|
|
"epoch": 0.07002528690916164,
|
||
|
|
"grad_norm": 1.28125,
|
||
|
|
"learning_rate": 0.00044950000000000003,
|
||
|
|
"loss": 6.6426,
|
||
|
|
"mean_token_accuracy": 0.11067456901073455,
|
||
|
|
"num_tokens": 1564994.0,
|
||
|
|
"step": 900
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.702912616729736,
|
||
|
|
"epoch": 0.0704143162808792,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.00045200000000000004,
|
||
|
|
"loss": 6.6416,
|
||
|
|
"mean_token_accuracy": 0.10571441873908043,
|
||
|
|
"num_tokens": 1573859.0,
|
||
|
|
"step": 905
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.7874678611755375,
|
||
|
|
"epoch": 0.07080334565259677,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.00045450000000000004,
|
||
|
|
"loss": 6.6015,
|
||
|
|
"mean_token_accuracy": 0.10410746335983276,
|
||
|
|
"num_tokens": 1581947.0,
|
||
|
|
"step": 910
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.733553743362426,
|
||
|
|
"epoch": 0.07119237502431433,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.00045700000000000005,
|
||
|
|
"loss": 6.5969,
|
||
|
|
"mean_token_accuracy": 0.1054476335644722,
|
||
|
|
"num_tokens": 1589971.0,
|
||
|
|
"step": 915
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.662263441085815,
|
||
|
|
"epoch": 0.0715814043960319,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 0.00045950000000000006,
|
||
|
|
"loss": 6.5353,
|
||
|
|
"mean_token_accuracy": 0.10906143486499786,
|
||
|
|
"num_tokens": 1598612.0,
|
||
|
|
"step": 920
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.747431993484497,
|
||
|
|
"epoch": 0.07197043376774946,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.000462,
|
||
|
|
"loss": 6.6744,
|
||
|
|
"mean_token_accuracy": 0.10410971119999886,
|
||
|
|
"num_tokens": 1607378.0,
|
||
|
|
"step": 925
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.722044801712036,
|
||
|
|
"epoch": 0.07235946313946703,
|
||
|
|
"grad_norm": 1.140625,
|
||
|
|
"learning_rate": 0.0004645,
|
||
|
|
"loss": 6.6808,
|
||
|
|
"mean_token_accuracy": 0.10857486054301262,
|
||
|
|
"num_tokens": 1615987.0,
|
||
|
|
"step": 930
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.60372314453125,
|
||
|
|
"epoch": 0.07274849251118459,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.000467,
|
||
|
|
"loss": 6.4755,
|
||
|
|
"mean_token_accuracy": 0.11410957649350166,
|
||
|
|
"num_tokens": 1625366.0,
|
||
|
|
"step": 935
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.74839038848877,
|
||
|
|
"epoch": 0.07313752188290217,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.0004695,
|
||
|
|
"loss": 6.6503,
|
||
|
|
"mean_token_accuracy": 0.11121466904878616,
|
||
|
|
"num_tokens": 1633020.0,
|
||
|
|
"step": 940
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.660103130340576,
|
||
|
|
"epoch": 0.07352655125461972,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.000472,
|
||
|
|
"loss": 6.5628,
|
||
|
|
"mean_token_accuracy": 0.10735638439655304,
|
||
|
|
"num_tokens": 1641518.0,
|
||
|
|
"step": 945
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.626758766174317,
|
||
|
|
"epoch": 0.07391558062633728,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.0004745,
|
||
|
|
"loss": 6.6274,
|
||
|
|
"mean_token_accuracy": 0.10905742049217224,
|
||
|
|
"num_tokens": 1650472.0,
|
||
|
|
"step": 950
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.731736516952514,
|
||
|
|
"epoch": 0.07430460999805485,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.000477,
|
||
|
|
"loss": 6.6641,
|
||
|
|
"mean_token_accuracy": 0.10684092938899994,
|
||
|
|
"num_tokens": 1659037.0,
|
||
|
|
"step": 955
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.7984882354736325,
|
||
|
|
"epoch": 0.07469363936977241,
|
||
|
|
"grad_norm": 1.1875,
|
||
|
|
"learning_rate": 0.0004795,
|
||
|
|
"loss": 6.7402,
|
||
|
|
"mean_token_accuracy": 0.11028921380639076,
|
||
|
|
"num_tokens": 1667897.0,
|
||
|
|
"step": 960
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.646100997924805,
|
||
|
|
"epoch": 0.07508266874148999,
|
||
|
|
"grad_norm": 1.1640625,
|
||
|
|
"learning_rate": 0.000482,
|
||
|
|
"loss": 6.6023,
|
||
|
|
"mean_token_accuracy": 0.10662103071808815,
|
||
|
|
"num_tokens": 1676535.0,
|
||
|
|
"step": 965
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.676787853240967,
|
||
|
|
"epoch": 0.07547169811320754,
|
||
|
|
"grad_norm": 1.1796875,
|
||
|
|
"learning_rate": 0.0004845,
|
||
|
|
"loss": 6.6142,
|
||
|
|
"mean_token_accuracy": 0.112273221462965,
|
||
|
|
"num_tokens": 1684415.0,
|
||
|
|
"step": 970
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.774458551406861,
|
||
|
|
"epoch": 0.07586072748492512,
|
||
|
|
"grad_norm": 1.140625,
|
||
|
|
"learning_rate": 0.000487,
|
||
|
|
"loss": 6.5561,
|
||
|
|
"mean_token_accuracy": 0.116531490534544,
|
||
|
|
"num_tokens": 1692443.0,
|
||
|
|
"step": 975
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.536187648773193,
|
||
|
|
"epoch": 0.07624975685664268,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0004895,
|
||
|
|
"loss": 6.5712,
|
||
|
|
"mean_token_accuracy": 0.11104042083024979,
|
||
|
|
"num_tokens": 1700814.0,
|
||
|
|
"step": 980
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.613480758666992,
|
||
|
|
"epoch": 0.07663878622836025,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.000492,
|
||
|
|
"loss": 6.4202,
|
||
|
|
"mean_token_accuracy": 0.11706303432583809,
|
||
|
|
"num_tokens": 1709591.0,
|
||
|
|
"step": 985
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.604351425170899,
|
||
|
|
"epoch": 0.0770278156000778,
|
||
|
|
"grad_norm": 0.96875,
|
||
|
|
"learning_rate": 0.0004945,
|
||
|
|
"loss": 6.649,
|
||
|
|
"mean_token_accuracy": 0.10275007560849189,
|
||
|
|
"num_tokens": 1718951.0,
|
||
|
|
"step": 990
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.788380146026611,
|
||
|
|
"epoch": 0.07741684497179536,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.000497,
|
||
|
|
"loss": 6.6033,
|
||
|
|
"mean_token_accuracy": 0.10998706892132759,
|
||
|
|
"num_tokens": 1727481.0,
|
||
|
|
"step": 995
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.614393281936645,
|
||
|
|
"epoch": 0.07780587434351294,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.0004995,
|
||
|
|
"loss": 6.6159,
|
||
|
|
"mean_token_accuracy": 0.11028658896684647,
|
||
|
|
"num_tokens": 1736985.0,
|
||
|
|
"step": 1000
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.725703430175781,
|
||
|
|
"epoch": 0.0781949037152305,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.0004999999989075146,
|
||
|
|
"loss": 6.6662,
|
||
|
|
"mean_token_accuracy": 0.10597634539008141,
|
||
|
|
"num_tokens": 1745470.0,
|
||
|
|
"step": 1005
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.6766214847564695,
|
||
|
|
"epoch": 0.07858393308694807,
|
||
|
|
"grad_norm": 1.2890625,
|
||
|
|
"learning_rate": 0.0004999999944692927,
|
||
|
|
"loss": 6.6027,
|
||
|
|
"mean_token_accuracy": 0.10940899178385735,
|
||
|
|
"num_tokens": 1754185.0,
|
||
|
|
"step": 1010
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.623138475418091,
|
||
|
|
"epoch": 0.07897296245866563,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.000499999986617054,
|
||
|
|
"loss": 6.6002,
|
||
|
|
"mean_token_accuracy": 0.10764588713645935,
|
||
|
|
"num_tokens": 1762100.0,
|
||
|
|
"step": 1015
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.748181295394898,
|
||
|
|
"epoch": 0.0793619918303832,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0004999999753507986,
|
||
|
|
"loss": 6.611,
|
||
|
|
"mean_token_accuracy": 0.11316110268235206,
|
||
|
|
"num_tokens": 1771070.0,
|
||
|
|
"step": 1020
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.6043675422668455,
|
||
|
|
"epoch": 0.07975102120210076,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.0004999999606705267,
|
||
|
|
"loss": 6.6079,
|
||
|
|
"mean_token_accuracy": 0.1110180787742138,
|
||
|
|
"num_tokens": 1780085.0,
|
||
|
|
"step": 1025
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.726189851760864,
|
||
|
|
"epoch": 0.08014005057381832,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004999999425762385,
|
||
|
|
"loss": 6.593,
|
||
|
|
"mean_token_accuracy": 0.11032602861523629,
|
||
|
|
"num_tokens": 1789316.0,
|
||
|
|
"step": 1030
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.535479640960693,
|
||
|
|
"epoch": 0.08052907994553589,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004999999210679344,
|
||
|
|
"loss": 6.5229,
|
||
|
|
"mean_token_accuracy": 0.11178331673145295,
|
||
|
|
"num_tokens": 1797975.0,
|
||
|
|
"step": 1035
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.64363055229187,
|
||
|
|
"epoch": 0.08091810931725345,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.0004999998961456145,
|
||
|
|
"loss": 6.6213,
|
||
|
|
"mean_token_accuracy": 0.1123659923672676,
|
||
|
|
"num_tokens": 1806129.0,
|
||
|
|
"step": 1040
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.674095535278321,
|
||
|
|
"epoch": 0.08130713868897102,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.0004999998678092794,
|
||
|
|
"loss": 6.614,
|
||
|
|
"mean_token_accuracy": 0.11390430778265,
|
||
|
|
"num_tokens": 1813956.0,
|
||
|
|
"step": 1045
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.638593435287476,
|
||
|
|
"epoch": 0.08169616806068858,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.0004999998360589293,
|
||
|
|
"loss": 6.6301,
|
||
|
|
"mean_token_accuracy": 0.1099810428917408,
|
||
|
|
"num_tokens": 1822572.0,
|
||
|
|
"step": 1050
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.633063173294067,
|
||
|
|
"epoch": 0.08208519743240615,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.000499999800894565,
|
||
|
|
"loss": 6.5446,
|
||
|
|
"mean_token_accuracy": 0.10445918366312981,
|
||
|
|
"num_tokens": 1831870.0,
|
||
|
|
"step": 1055
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.541274070739746,
|
||
|
|
"epoch": 0.08247422680412371,
|
||
|
|
"grad_norm": 1.296875,
|
||
|
|
"learning_rate": 0.0004999997623161866,
|
||
|
|
"loss": 6.5895,
|
||
|
|
"mean_token_accuracy": 0.10464150458574295,
|
||
|
|
"num_tokens": 1840414.0,
|
||
|
|
"step": 1060
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.682097768783569,
|
||
|
|
"epoch": 0.08286325617584128,
|
||
|
|
"grad_norm": 1.171875,
|
||
|
|
"learning_rate": 0.0004999997203237951,
|
||
|
|
"loss": 6.5946,
|
||
|
|
"mean_token_accuracy": 0.10805075541138649,
|
||
|
|
"num_tokens": 1850385.0,
|
||
|
|
"step": 1065
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.531861686706543,
|
||
|
|
"epoch": 0.08325228554755884,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.000499999674917391,
|
||
|
|
"loss": 6.5024,
|
||
|
|
"mean_token_accuracy": 0.1158783845603466,
|
||
|
|
"num_tokens": 1858479.0,
|
||
|
|
"step": 1070
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.57890043258667,
|
||
|
|
"epoch": 0.0836413149192764,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004999996260969748,
|
||
|
|
"loss": 6.5797,
|
||
|
|
"mean_token_accuracy": 0.10807743966579438,
|
||
|
|
"num_tokens": 1867357.0,
|
||
|
|
"step": 1075
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.5686417579650875,
|
||
|
|
"epoch": 0.08403034429099397,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.0004999995738625475,
|
||
|
|
"loss": 6.5273,
|
||
|
|
"mean_token_accuracy": 0.10552098453044892,
|
||
|
|
"num_tokens": 1876211.0,
|
||
|
|
"step": 1080
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.5786802768707275,
|
||
|
|
"epoch": 0.08441937366271153,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.0004999995182141099,
|
||
|
|
"loss": 6.442,
|
||
|
|
"mean_token_accuracy": 0.11163912862539291,
|
||
|
|
"num_tokens": 1884301.0,
|
||
|
|
"step": 1085
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.694643640518189,
|
||
|
|
"epoch": 0.0848084030344291,
|
||
|
|
"grad_norm": 1.140625,
|
||
|
|
"learning_rate": 0.0004999994591516626,
|
||
|
|
"loss": 6.6044,
|
||
|
|
"mean_token_accuracy": 0.11439522057771682,
|
||
|
|
"num_tokens": 1893191.0,
|
||
|
|
"step": 1090
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.425136470794678,
|
||
|
|
"epoch": 0.08519743240614666,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.0004999993966752066,
|
||
|
|
"loss": 6.4612,
|
||
|
|
"mean_token_accuracy": 0.11129482239484786,
|
||
|
|
"num_tokens": 1901434.0,
|
||
|
|
"step": 1095
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.548592042922974,
|
||
|
|
"epoch": 0.08558646177786423,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.000499999330784743,
|
||
|
|
"loss": 6.4515,
|
||
|
|
"mean_token_accuracy": 0.11943399086594582,
|
||
|
|
"num_tokens": 1910054.0,
|
||
|
|
"step": 1100
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.629737424850464,
|
||
|
|
"epoch": 0.08597549114958179,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.0004999992614802725,
|
||
|
|
"loss": 6.5999,
|
||
|
|
"mean_token_accuracy": 0.111067134141922,
|
||
|
|
"num_tokens": 1918607.0,
|
||
|
|
"step": 1105
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.568958854675293,
|
||
|
|
"epoch": 0.08636452052129936,
|
||
|
|
"grad_norm": 0.99609375,
|
||
|
|
"learning_rate": 0.0004999991887617966,
|
||
|
|
"loss": 6.5401,
|
||
|
|
"mean_token_accuracy": 0.11289476603269577,
|
||
|
|
"num_tokens": 1927610.0,
|
||
|
|
"step": 1110
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.529994678497315,
|
||
|
|
"epoch": 0.08675354989301692,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.0004999991126293158,
|
||
|
|
"loss": 6.4982,
|
||
|
|
"mean_token_accuracy": 0.11338723674416543,
|
||
|
|
"num_tokens": 1936174.0,
|
||
|
|
"step": 1115
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.547743463516236,
|
||
|
|
"epoch": 0.08714257926473448,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.0004999990330828318,
|
||
|
|
"loss": 6.4164,
|
||
|
|
"mean_token_accuracy": 0.12166852355003357,
|
||
|
|
"num_tokens": 1944228.0,
|
||
|
|
"step": 1120
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.585451459884643,
|
||
|
|
"epoch": 0.08753160863645205,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.0004999989501223456,
|
||
|
|
"loss": 6.5128,
|
||
|
|
"mean_token_accuracy": 0.1150627963244915,
|
||
|
|
"num_tokens": 1953144.0,
|
||
|
|
"step": 1125
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.561717414855957,
|
||
|
|
"epoch": 0.08792063800816961,
|
||
|
|
"grad_norm": 1.140625,
|
||
|
|
"learning_rate": 0.0004999988637478584,
|
||
|
|
"loss": 6.5849,
|
||
|
|
"mean_token_accuracy": 0.11227734759449959,
|
||
|
|
"num_tokens": 1961947.0,
|
||
|
|
"step": 1130
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.619640874862671,
|
||
|
|
"epoch": 0.08830966737988719,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004999987739593716,
|
||
|
|
"loss": 6.533,
|
||
|
|
"mean_token_accuracy": 0.11325131580233574,
|
||
|
|
"num_tokens": 1970674.0,
|
||
|
|
"step": 1135
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.5710524559021,
|
||
|
|
"epoch": 0.08869869675160474,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.0004999986807568865,
|
||
|
|
"loss": 6.5262,
|
||
|
|
"mean_token_accuracy": 0.11231668442487716,
|
||
|
|
"num_tokens": 1979173.0,
|
||
|
|
"step": 1140
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.571699047088623,
|
||
|
|
"epoch": 0.08908772612332232,
|
||
|
|
"grad_norm": 1.15625,
|
||
|
|
"learning_rate": 0.0004999985841404045,
|
||
|
|
"loss": 6.5119,
|
||
|
|
"mean_token_accuracy": 0.11496285647153855,
|
||
|
|
"num_tokens": 1988134.0,
|
||
|
|
"step": 1145
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.590276622772217,
|
||
|
|
"epoch": 0.08947675549503988,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.0004999984841099271,
|
||
|
|
"loss": 6.4446,
|
||
|
|
"mean_token_accuracy": 0.11542503014206887,
|
||
|
|
"num_tokens": 1996977.0,
|
||
|
|
"step": 1150
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.562020540237427,
|
||
|
|
"epoch": 0.08986578486675743,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.000499998380665456,
|
||
|
|
"loss": 6.5304,
|
||
|
|
"mean_token_accuracy": 0.11315923407673836,
|
||
|
|
"num_tokens": 2005946.0,
|
||
|
|
"step": 1155
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.455333232879639,
|
||
|
|
"epoch": 0.090254814238475,
|
||
|
|
"grad_norm": 1.21875,
|
||
|
|
"learning_rate": 0.0004999982738069924,
|
||
|
|
"loss": 6.3473,
|
||
|
|
"mean_token_accuracy": 0.1175466775894165,
|
||
|
|
"num_tokens": 2014882.0,
|
||
|
|
"step": 1160
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.515373849868775,
|
||
|
|
"epoch": 0.09064384361019256,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.0004999981635345382,
|
||
|
|
"loss": 6.5179,
|
||
|
|
"mean_token_accuracy": 0.10954774022102357,
|
||
|
|
"num_tokens": 2024858.0,
|
||
|
|
"step": 1165
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.458465433120727,
|
||
|
|
"epoch": 0.09103287298191014,
|
||
|
|
"grad_norm": 1.21875,
|
||
|
|
"learning_rate": 0.0004999980498480949,
|
||
|
|
"loss": 6.4391,
|
||
|
|
"mean_token_accuracy": 0.11511781737208367,
|
||
|
|
"num_tokens": 2034072.0,
|
||
|
|
"step": 1170
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.5074522495269775,
|
||
|
|
"epoch": 0.0914219023536277,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.0004999979327476644,
|
||
|
|
"loss": 6.4671,
|
||
|
|
"mean_token_accuracy": 0.11546923145651818,
|
||
|
|
"num_tokens": 2042649.0,
|
||
|
|
"step": 1175
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.587860155105591,
|
||
|
|
"epoch": 0.09181093172534527,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 0.0004999978122332485,
|
||
|
|
"loss": 6.4992,
|
||
|
|
"mean_token_accuracy": 0.11586807146668435,
|
||
|
|
"num_tokens": 2050866.0,
|
||
|
|
"step": 1180
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.52506422996521,
|
||
|
|
"epoch": 0.09219996109706283,
|
||
|
|
"grad_norm": 1.15625,
|
||
|
|
"learning_rate": 0.0004999976883048487,
|
||
|
|
"loss": 6.4864,
|
||
|
|
"mean_token_accuracy": 0.11557217240333557,
|
||
|
|
"num_tokens": 2058914.0,
|
||
|
|
"step": 1185
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.44358549118042,
|
||
|
|
"epoch": 0.0925889904687804,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.0004999975609624673,
|
||
|
|
"loss": 6.4263,
|
||
|
|
"mean_token_accuracy": 0.11425086855888367,
|
||
|
|
"num_tokens": 2068098.0,
|
||
|
|
"step": 1190
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.557921361923218,
|
||
|
|
"epoch": 0.09297801984049796,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.0004999974302061059,
|
||
|
|
"loss": 6.4396,
|
||
|
|
"mean_token_accuracy": 0.11065051257610321,
|
||
|
|
"num_tokens": 2077299.0,
|
||
|
|
"step": 1195
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.459573030471802,
|
||
|
|
"epoch": 0.09336704921221552,
|
||
|
|
"grad_norm": 1.2265625,
|
||
|
|
"learning_rate": 0.0004999972960357666,
|
||
|
|
"loss": 6.5447,
|
||
|
|
"mean_token_accuracy": 0.10892835408449172,
|
||
|
|
"num_tokens": 2087868.0,
|
||
|
|
"step": 1200
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.489337158203125,
|
||
|
|
"epoch": 0.09375607858393309,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0004999971584514516,
|
||
|
|
"loss": 6.4566,
|
||
|
|
"mean_token_accuracy": 0.1227202832698822,
|
||
|
|
"num_tokens": 2096553.0,
|
||
|
|
"step": 1205
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.578389406204224,
|
||
|
|
"epoch": 0.09414510795565065,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.0004999970174531627,
|
||
|
|
"loss": 6.4195,
|
||
|
|
"mean_token_accuracy": 0.11719959750771522,
|
||
|
|
"num_tokens": 2104809.0,
|
||
|
|
"step": 1210
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.33401346206665,
|
||
|
|
"epoch": 0.09453413732736822,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0004999968730409022,
|
||
|
|
"loss": 6.3881,
|
||
|
|
"mean_token_accuracy": 0.11444653123617173,
|
||
|
|
"num_tokens": 2113869.0,
|
||
|
|
"step": 1215
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.419023704528809,
|
||
|
|
"epoch": 0.09492316669908578,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.0004999967252146723,
|
||
|
|
"loss": 6.2354,
|
||
|
|
"mean_token_accuracy": 0.11691547855734825,
|
||
|
|
"num_tokens": 2121749.0,
|
||
|
|
"step": 1220
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.44911470413208,
|
||
|
|
"epoch": 0.09531219607080335,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0004999965739744752,
|
||
|
|
"loss": 6.4501,
|
||
|
|
"mean_token_accuracy": 0.11253133341670037,
|
||
|
|
"num_tokens": 2130828.0,
|
||
|
|
"step": 1225
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.503531265258789,
|
||
|
|
"epoch": 0.09570122544252091,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.0004999964193203132,
|
||
|
|
"loss": 6.4259,
|
||
|
|
"mean_token_accuracy": 0.11821354776620865,
|
||
|
|
"num_tokens": 2138928.0,
|
||
|
|
"step": 1230
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.505114889144897,
|
||
|
|
"epoch": 0.09609025481423847,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004999962612521888,
|
||
|
|
"loss": 6.4558,
|
||
|
|
"mean_token_accuracy": 0.11319027468562126,
|
||
|
|
"num_tokens": 2147643.0,
|
||
|
|
"step": 1235
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.468291425704956,
|
||
|
|
"epoch": 0.09647928418595604,
|
||
|
|
"grad_norm": 0.94140625,
|
||
|
|
"learning_rate": 0.0004999960997701041,
|
||
|
|
"loss": 6.3764,
|
||
|
|
"mean_token_accuracy": 0.11834514439105988,
|
||
|
|
"num_tokens": 2156766.0,
|
||
|
|
"step": 1240
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.5396839618682865,
|
||
|
|
"epoch": 0.0968683135576736,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0004999959348740618,
|
||
|
|
"loss": 6.4326,
|
||
|
|
"mean_token_accuracy": 0.11484687998890877,
|
||
|
|
"num_tokens": 2165517.0,
|
||
|
|
"step": 1245
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.355327892303467,
|
||
|
|
"epoch": 0.09725734292939117,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.0004999957665640641,
|
||
|
|
"loss": 6.3062,
|
||
|
|
"mean_token_accuracy": 0.12052496299147605,
|
||
|
|
"num_tokens": 2174812.0,
|
||
|
|
"step": 1250
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.483971643447876,
|
||
|
|
"epoch": 0.09764637230110873,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.000499995594840114,
|
||
|
|
"loss": 6.4579,
|
||
|
|
"mean_token_accuracy": 0.11715996637940407,
|
||
|
|
"num_tokens": 2183968.0,
|
||
|
|
"step": 1255
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.429156923294068,
|
||
|
|
"epoch": 0.0980354016728263,
|
||
|
|
"grad_norm": 1.1796875,
|
||
|
|
"learning_rate": 0.0004999954197022138,
|
||
|
|
"loss": 6.4806,
|
||
|
|
"mean_token_accuracy": 0.11790231317281723,
|
||
|
|
"num_tokens": 2191947.0,
|
||
|
|
"step": 1260
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.465476655960083,
|
||
|
|
"epoch": 0.09842443104454386,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.0004999952411503661,
|
||
|
|
"loss": 6.3135,
|
||
|
|
"mean_token_accuracy": 0.12436129152774811,
|
||
|
|
"num_tokens": 2199951.0,
|
||
|
|
"step": 1265
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.426665306091309,
|
||
|
|
"epoch": 0.09881346041626143,
|
||
|
|
"grad_norm": 1.15625,
|
||
|
|
"learning_rate": 0.0004999950591845738,
|
||
|
|
"loss": 6.4638,
|
||
|
|
"mean_token_accuracy": 0.11671050637960434,
|
||
|
|
"num_tokens": 2208714.0,
|
||
|
|
"step": 1270
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.443587970733643,
|
||
|
|
"epoch": 0.09920248978797899,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.0004999948738048397,
|
||
|
|
"loss": 6.3192,
|
||
|
|
"mean_token_accuracy": 0.11797064170241356,
|
||
|
|
"num_tokens": 2217250.0,
|
||
|
|
"step": 1275
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.448610448837281,
|
||
|
|
"epoch": 0.09959151915969655,
|
||
|
|
"grad_norm": 1.1875,
|
||
|
|
"learning_rate": 0.0004999946850111663,
|
||
|
|
"loss": 6.3792,
|
||
|
|
"mean_token_accuracy": 0.11981845200061798,
|
||
|
|
"num_tokens": 2225468.0,
|
||
|
|
"step": 1280
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.333937406539917,
|
||
|
|
"epoch": 0.09998054853141412,
|
||
|
|
"grad_norm": 1.203125,
|
||
|
|
"learning_rate": 0.0004999944928035569,
|
||
|
|
"loss": 6.3276,
|
||
|
|
"mean_token_accuracy": 0.12700017243623735,
|
||
|
|
"num_tokens": 2233893.0,
|
||
|
|
"step": 1285
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.566837978363037,
|
||
|
|
"epoch": 0.10036957790313168,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.000499994297182014,
|
||
|
|
"loss": 6.4126,
|
||
|
|
"mean_token_accuracy": 0.12005007639527321,
|
||
|
|
"num_tokens": 2242487.0,
|
||
|
|
"step": 1290
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.329822826385498,
|
||
|
|
"epoch": 0.10075860727484925,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.0004999940981465408,
|
||
|
|
"loss": 6.232,
|
||
|
|
"mean_token_accuracy": 0.1259617954492569,
|
||
|
|
"num_tokens": 2250518.0,
|
||
|
|
"step": 1295
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.410264587402343,
|
||
|
|
"epoch": 0.10114763664656681,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.0004999938956971404,
|
||
|
|
"loss": 6.4075,
|
||
|
|
"mean_token_accuracy": 0.11481295600533485,
|
||
|
|
"num_tokens": 2259024.0,
|
||
|
|
"step": 1300
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.495929098129272,
|
||
|
|
"epoch": 0.10153666601828439,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004999936898338156,
|
||
|
|
"loss": 6.4544,
|
||
|
|
"mean_token_accuracy": 0.10940589010715485,
|
||
|
|
"num_tokens": 2267832.0,
|
||
|
|
"step": 1305
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.447009181976318,
|
||
|
|
"epoch": 0.10192569539000194,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.0004999934805565698,
|
||
|
|
"loss": 6.5092,
|
||
|
|
"mean_token_accuracy": 0.110442166775465,
|
||
|
|
"num_tokens": 2276834.0,
|
||
|
|
"step": 1310
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.569683933258057,
|
||
|
|
"epoch": 0.10231472476171952,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.000499993267865406,
|
||
|
|
"loss": 6.4354,
|
||
|
|
"mean_token_accuracy": 0.11660119816660881,
|
||
|
|
"num_tokens": 2285736.0,
|
||
|
|
"step": 1315
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.479250431060791,
|
||
|
|
"epoch": 0.10270375413343708,
|
||
|
|
"grad_norm": 0.9765625,
|
||
|
|
"learning_rate": 0.0004999930517603275,
|
||
|
|
"loss": 6.3938,
|
||
|
|
"mean_token_accuracy": 0.12768669724464415,
|
||
|
|
"num_tokens": 2294177.0,
|
||
|
|
"step": 1320
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.3529052734375,
|
||
|
|
"epoch": 0.10309278350515463,
|
||
|
|
"grad_norm": 1.140625,
|
||
|
|
"learning_rate": 0.0004999928322413374,
|
||
|
|
"loss": 6.1691,
|
||
|
|
"mean_token_accuracy": 0.12876419499516487,
|
||
|
|
"num_tokens": 2302784.0,
|
||
|
|
"step": 1325
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.26311182975769,
|
||
|
|
"epoch": 0.1034818128768722,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.0004999926093084394,
|
||
|
|
"loss": 6.2909,
|
||
|
|
"mean_token_accuracy": 0.11930396482348442,
|
||
|
|
"num_tokens": 2311650.0,
|
||
|
|
"step": 1330
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.529369115829468,
|
||
|
|
"epoch": 0.10387084224858976,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.0004999923829616365,
|
||
|
|
"loss": 6.4039,
|
||
|
|
"mean_token_accuracy": 0.11483718827366829,
|
||
|
|
"num_tokens": 2319828.0,
|
||
|
|
"step": 1335
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.323467636108399,
|
||
|
|
"epoch": 0.10425987162030734,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.0004999921532009323,
|
||
|
|
"loss": 6.4176,
|
||
|
|
"mean_token_accuracy": 0.11197080835700035,
|
||
|
|
"num_tokens": 2328636.0,
|
||
|
|
"step": 1340
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.486206817626953,
|
||
|
|
"epoch": 0.1046489009920249,
|
||
|
|
"grad_norm": 1.15625,
|
||
|
|
"learning_rate": 0.0004999919200263304,
|
||
|
|
"loss": 6.3007,
|
||
|
|
"mean_token_accuracy": 0.12107961252331734,
|
||
|
|
"num_tokens": 2336771.0,
|
||
|
|
"step": 1345
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.383418703079224,
|
||
|
|
"epoch": 0.10503793036374247,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.0004999916834378342,
|
||
|
|
"loss": 6.4489,
|
||
|
|
"mean_token_accuracy": 0.1177673652768135,
|
||
|
|
"num_tokens": 2346106.0,
|
||
|
|
"step": 1350
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.498797035217285,
|
||
|
|
"epoch": 0.10542695973546003,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.0004999914434354472,
|
||
|
|
"loss": 6.4394,
|
||
|
|
"mean_token_accuracy": 0.11363381147384644,
|
||
|
|
"num_tokens": 2354943.0,
|
||
|
|
"step": 1355
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.306008958816529,
|
||
|
|
"epoch": 0.10581598910717759,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004999912000191733,
|
||
|
|
"loss": 6.3262,
|
||
|
|
"mean_token_accuracy": 0.12337140962481499,
|
||
|
|
"num_tokens": 2363699.0,
|
||
|
|
"step": 1360
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.407146310806274,
|
||
|
|
"epoch": 0.10620501847889516,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.000499990953189016,
|
||
|
|
"loss": 6.4561,
|
||
|
|
"mean_token_accuracy": 0.11349867284297943,
|
||
|
|
"num_tokens": 2373316.0,
|
||
|
|
"step": 1365
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.638979101181031,
|
||
|
|
"epoch": 0.10659404785061272,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0004999907029449791,
|
||
|
|
"loss": 6.5114,
|
||
|
|
"mean_token_accuracy": 0.11165152713656426,
|
||
|
|
"num_tokens": 2381550.0,
|
||
|
|
"step": 1370
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.372858619689941,
|
||
|
|
"epoch": 0.10698307722233029,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0004999904492870663,
|
||
|
|
"loss": 6.3452,
|
||
|
|
"mean_token_accuracy": 0.12479593753814697,
|
||
|
|
"num_tokens": 2389546.0,
|
||
|
|
"step": 1375
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.456328392028809,
|
||
|
|
"epoch": 0.10737210659404785,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.0004999901922152816,
|
||
|
|
"loss": 6.3064,
|
||
|
|
"mean_token_accuracy": 0.1262669622898102,
|
||
|
|
"num_tokens": 2398852.0,
|
||
|
|
"step": 1380
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.367328929901123,
|
||
|
|
"epoch": 0.10776113596576542,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.0004999899317296288,
|
||
|
|
"loss": 6.3803,
|
||
|
|
"mean_token_accuracy": 0.11952286437153817,
|
||
|
|
"num_tokens": 2407815.0,
|
||
|
|
"step": 1385
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.42546501159668,
|
||
|
|
"epoch": 0.10815016533748298,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004999896678301121,
|
||
|
|
"loss": 6.2467,
|
||
|
|
"mean_token_accuracy": 0.12261220291256905,
|
||
|
|
"num_tokens": 2417300.0,
|
||
|
|
"step": 1390
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.408157634735107,
|
||
|
|
"epoch": 0.10853919470920055,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.0004999894005167352,
|
||
|
|
"loss": 6.4055,
|
||
|
|
"mean_token_accuracy": 0.11997133195400238,
|
||
|
|
"num_tokens": 2426257.0,
|
||
|
|
"step": 1395
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.538053035736084,
|
||
|
|
"epoch": 0.10892822408091811,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.000499989129789502,
|
||
|
|
"loss": 6.4231,
|
||
|
|
"mean_token_accuracy": 0.12112721130251884,
|
||
|
|
"num_tokens": 2434595.0,
|
||
|
|
"step": 1400
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.45562744140625,
|
||
|
|
"epoch": 0.10931725345263567,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.0004999888556484172,
|
||
|
|
"loss": 6.4582,
|
||
|
|
"mean_token_accuracy": 0.11823535412549972,
|
||
|
|
"num_tokens": 2443945.0,
|
||
|
|
"step": 1405
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.332750463485718,
|
||
|
|
"epoch": 0.10970628282435324,
|
||
|
|
"grad_norm": 1.140625,
|
||
|
|
"learning_rate": 0.0004999885780934845,
|
||
|
|
"loss": 6.3009,
|
||
|
|
"mean_token_accuracy": 0.11995220556855202,
|
||
|
|
"num_tokens": 2453141.0,
|
||
|
|
"step": 1410
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.403821897506714,
|
||
|
|
"epoch": 0.1100953121960708,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0004999882971247081,
|
||
|
|
"loss": 6.3884,
|
||
|
|
"mean_token_accuracy": 0.11859115436673165,
|
||
|
|
"num_tokens": 2461873.0,
|
||
|
|
"step": 1415
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.377913141250611,
|
||
|
|
"epoch": 0.11048434156778837,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 0.0004999880127420926,
|
||
|
|
"loss": 6.4231,
|
||
|
|
"mean_token_accuracy": 0.11527122929692268,
|
||
|
|
"num_tokens": 2471238.0,
|
||
|
|
"step": 1420
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.386839056015015,
|
||
|
|
"epoch": 0.11087337093950593,
|
||
|
|
"grad_norm": 1.15625,
|
||
|
|
"learning_rate": 0.0004999877249456421,
|
||
|
|
"loss": 6.307,
|
||
|
|
"mean_token_accuracy": 0.12340098172426224,
|
||
|
|
"num_tokens": 2479412.0,
|
||
|
|
"step": 1425
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.303452777862549,
|
||
|
|
"epoch": 0.1112624003112235,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.0004999874337353609,
|
||
|
|
"loss": 6.18,
|
||
|
|
"mean_token_accuracy": 0.12517158687114716,
|
||
|
|
"num_tokens": 2488150.0,
|
||
|
|
"step": 1430
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.356554985046387,
|
||
|
|
"epoch": 0.11165142968294106,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004999871391112535,
|
||
|
|
"loss": 6.361,
|
||
|
|
"mean_token_accuracy": 0.12490880936384201,
|
||
|
|
"num_tokens": 2498103.0,
|
||
|
|
"step": 1435
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.340976142883301,
|
||
|
|
"epoch": 0.11204045905465862,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.0004999868410733244,
|
||
|
|
"loss": 6.2139,
|
||
|
|
"mean_token_accuracy": 0.12381952628493309,
|
||
|
|
"num_tokens": 2506211.0,
|
||
|
|
"step": 1440
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.205969381332397,
|
||
|
|
"epoch": 0.11242948842637619,
|
||
|
|
"grad_norm": 1.15625,
|
||
|
|
"learning_rate": 0.000499986539621578,
|
||
|
|
"loss": 6.2657,
|
||
|
|
"mean_token_accuracy": 0.12168120294809341,
|
||
|
|
"num_tokens": 2514743.0,
|
||
|
|
"step": 1445
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.263538980484009,
|
||
|
|
"epoch": 0.11281851779809375,
|
||
|
|
"grad_norm": 0.984375,
|
||
|
|
"learning_rate": 0.0004999862347560191,
|
||
|
|
"loss": 6.2461,
|
||
|
|
"mean_token_accuracy": 0.12048678621649742,
|
||
|
|
"num_tokens": 2523824.0,
|
||
|
|
"step": 1450
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.411288928985596,
|
||
|
|
"epoch": 0.11320754716981132,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.0004999859264766521,
|
||
|
|
"loss": 6.3292,
|
||
|
|
"mean_token_accuracy": 0.11649304181337357,
|
||
|
|
"num_tokens": 2532360.0,
|
||
|
|
"step": 1455
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.369462871551514,
|
||
|
|
"epoch": 0.11359657654152888,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.0004999856147834817,
|
||
|
|
"loss": 6.2934,
|
||
|
|
"mean_token_accuracy": 0.1242024652659893,
|
||
|
|
"num_tokens": 2540547.0,
|
||
|
|
"step": 1460
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.267951345443725,
|
||
|
|
"epoch": 0.11398560591324645,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.0004999852996765129,
|
||
|
|
"loss": 6.2993,
|
||
|
|
"mean_token_accuracy": 0.12303554266691208,
|
||
|
|
"num_tokens": 2549193.0,
|
||
|
|
"step": 1465
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.381441640853882,
|
||
|
|
"epoch": 0.11437463528496401,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.0004999849811557502,
|
||
|
|
"loss": 6.315,
|
||
|
|
"mean_token_accuracy": 0.11787554398179054,
|
||
|
|
"num_tokens": 2557553.0,
|
||
|
|
"step": 1470
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.47734432220459,
|
||
|
|
"epoch": 0.11476366465668159,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004999846592211984,
|
||
|
|
"loss": 6.4155,
|
||
|
|
"mean_token_accuracy": 0.11765160784125328,
|
||
|
|
"num_tokens": 2565945.0,
|
||
|
|
"step": 1475
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.43158483505249,
|
||
|
|
"epoch": 0.11515269402839914,
|
||
|
|
"grad_norm": 1.1640625,
|
||
|
|
"learning_rate": 0.0004999843338728626,
|
||
|
|
"loss": 6.2817,
|
||
|
|
"mean_token_accuracy": 0.11672718673944474,
|
||
|
|
"num_tokens": 2574364.0,
|
||
|
|
"step": 1480
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.202181673049926,
|
||
|
|
"epoch": 0.1155417234001167,
|
||
|
|
"grad_norm": 0.98046875,
|
||
|
|
"learning_rate": 0.0004999840051107476,
|
||
|
|
"loss": 6.206,
|
||
|
|
"mean_token_accuracy": 0.1248119167983532,
|
||
|
|
"num_tokens": 2582825.0,
|
||
|
|
"step": 1485
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.488698577880859,
|
||
|
|
"epoch": 0.11593075277183428,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.0004999836729348584,
|
||
|
|
"loss": 6.3568,
|
||
|
|
"mean_token_accuracy": 0.12094219103455543,
|
||
|
|
"num_tokens": 2591628.0,
|
||
|
|
"step": 1490
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.31714186668396,
|
||
|
|
"epoch": 0.11631978214355183,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.0004999833373452,
|
||
|
|
"loss": 6.3628,
|
||
|
|
"mean_token_accuracy": 0.11592670232057571,
|
||
|
|
"num_tokens": 2600436.0,
|
||
|
|
"step": 1495
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.338783550262451,
|
||
|
|
"epoch": 0.1167088115152694,
|
||
|
|
"grad_norm": 1.171875,
|
||
|
|
"learning_rate": 0.0004999829983417778,
|
||
|
|
"loss": 6.3026,
|
||
|
|
"mean_token_accuracy": 0.12240928933024406,
|
||
|
|
"num_tokens": 2609709.0,
|
||
|
|
"step": 1500
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.433617877960205,
|
||
|
|
"epoch": 0.11709784088698696,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.0004999826559245965,
|
||
|
|
"loss": 6.3332,
|
||
|
|
"mean_token_accuracy": 0.11754970774054527,
|
||
|
|
"num_tokens": 2617992.0,
|
||
|
|
"step": 1505
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.219531154632568,
|
||
|
|
"epoch": 0.11748687025870454,
|
||
|
|
"grad_norm": 0.9921875,
|
||
|
|
"learning_rate": 0.0004999823100936615,
|
||
|
|
"loss": 6.234,
|
||
|
|
"mean_token_accuracy": 0.12196057289838791,
|
||
|
|
"num_tokens": 2626706.0,
|
||
|
|
"step": 1510
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.436577415466308,
|
||
|
|
"epoch": 0.1178758996304221,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.0004999819608489781,
|
||
|
|
"loss": 6.2957,
|
||
|
|
"mean_token_accuracy": 0.12622082754969596,
|
||
|
|
"num_tokens": 2634642.0,
|
||
|
|
"step": 1515
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.392754316329956,
|
||
|
|
"epoch": 0.11826492900213967,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004999816081905515,
|
||
|
|
"loss": 6.32,
|
||
|
|
"mean_token_accuracy": 0.11421801522374153,
|
||
|
|
"num_tokens": 2644160.0,
|
||
|
|
"step": 1520
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.293839359283448,
|
||
|
|
"epoch": 0.11865395837385723,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004999812521183872,
|
||
|
|
"loss": 6.2894,
|
||
|
|
"mean_token_accuracy": 0.11762222573161125,
|
||
|
|
"num_tokens": 2653390.0,
|
||
|
|
"step": 1525
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.410764217376709,
|
||
|
|
"epoch": 0.11904298774557479,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.0004999808926324903,
|
||
|
|
"loss": 6.3436,
|
||
|
|
"mean_token_accuracy": 0.12275402769446372,
|
||
|
|
"num_tokens": 2662561.0,
|
||
|
|
"step": 1530
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.3587933540344235,
|
||
|
|
"epoch": 0.11943201711729236,
|
||
|
|
"grad_norm": 1.2109375,
|
||
|
|
"learning_rate": 0.0004999805297328665,
|
||
|
|
"loss": 6.3074,
|
||
|
|
"mean_token_accuracy": 0.1183415673673153,
|
||
|
|
"num_tokens": 2670694.0,
|
||
|
|
"step": 1535
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.311541795730591,
|
||
|
|
"epoch": 0.11982104648900992,
|
||
|
|
"grad_norm": 1.15625,
|
||
|
|
"learning_rate": 0.0004999801634195214,
|
||
|
|
"loss": 6.1963,
|
||
|
|
"mean_token_accuracy": 0.1258288785815239,
|
||
|
|
"num_tokens": 2679583.0,
|
||
|
|
"step": 1540
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.238374280929565,
|
||
|
|
"epoch": 0.12021007586072749,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.0004999797936924603,
|
||
|
|
"loss": 6.18,
|
||
|
|
"mean_token_accuracy": 0.1266369491815567,
|
||
|
|
"num_tokens": 2688429.0,
|
||
|
|
"step": 1545
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.39892201423645,
|
||
|
|
"epoch": 0.12059910523244505,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.000499979420551689,
|
||
|
|
"loss": 6.2598,
|
||
|
|
"mean_token_accuracy": 0.12087157368659973,
|
||
|
|
"num_tokens": 2697134.0,
|
||
|
|
"step": 1550
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.295349359512329,
|
||
|
|
"epoch": 0.12098813460416262,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.000499979043997213,
|
||
|
|
"loss": 6.4089,
|
||
|
|
"mean_token_accuracy": 0.11821548864245415,
|
||
|
|
"num_tokens": 2705641.0,
|
||
|
|
"step": 1555
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.431625747680664,
|
||
|
|
"epoch": 0.12137716397588018,
|
||
|
|
"grad_norm": 0.99609375,
|
||
|
|
"learning_rate": 0.0004999786640290381,
|
||
|
|
"loss": 6.3464,
|
||
|
|
"mean_token_accuracy": 0.12412570863962173,
|
||
|
|
"num_tokens": 2714977.0,
|
||
|
|
"step": 1560
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.363233518600464,
|
||
|
|
"epoch": 0.12176619334759774,
|
||
|
|
"grad_norm": 1.171875,
|
||
|
|
"learning_rate": 0.0004999782806471701,
|
||
|
|
"loss": 6.1914,
|
||
|
|
"mean_token_accuracy": 0.13308344036340714,
|
||
|
|
"num_tokens": 2723120.0,
|
||
|
|
"step": 1565
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.120411777496338,
|
||
|
|
"epoch": 0.12215522271931531,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.0004999778938516147,
|
||
|
|
"loss": 6.1757,
|
||
|
|
"mean_token_accuracy": 0.12850490733981132,
|
||
|
|
"num_tokens": 2731964.0,
|
||
|
|
"step": 1570
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.417637777328491,
|
||
|
|
"epoch": 0.12254425209103287,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.000499977503642378,
|
||
|
|
"loss": 6.2551,
|
||
|
|
"mean_token_accuracy": 0.1218321792781353,
|
||
|
|
"num_tokens": 2741537.0,
|
||
|
|
"step": 1575
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.3168291568756105,
|
||
|
|
"epoch": 0.12293328146275044,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004999771100194656,
|
||
|
|
"loss": 6.3696,
|
||
|
|
"mean_token_accuracy": 0.11779501438140869,
|
||
|
|
"num_tokens": 2751522.0,
|
||
|
|
"step": 1580
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.4047736644744875,
|
||
|
|
"epoch": 0.123322310834468,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.0004999767129828837,
|
||
|
|
"loss": 6.3764,
|
||
|
|
"mean_token_accuracy": 0.1190227821469307,
|
||
|
|
"num_tokens": 2761100.0,
|
||
|
|
"step": 1585
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.328610754013061,
|
||
|
|
"epoch": 0.12371134020618557,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.0004999763125326383,
|
||
|
|
"loss": 6.3118,
|
||
|
|
"mean_token_accuracy": 0.12152700573205948,
|
||
|
|
"num_tokens": 2769171.0,
|
||
|
|
"step": 1590
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.314954519271851,
|
||
|
|
"epoch": 0.12410036957790313,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0004999759086687355,
|
||
|
|
"loss": 6.2403,
|
||
|
|
"mean_token_accuracy": 0.12723048627376557,
|
||
|
|
"num_tokens": 2778021.0,
|
||
|
|
"step": 1595
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.23314094543457,
|
||
|
|
"epoch": 0.1244893989496207,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0004999755013911813,
|
||
|
|
"loss": 6.1759,
|
||
|
|
"mean_token_accuracy": 0.12251143753528596,
|
||
|
|
"num_tokens": 2787206.0,
|
||
|
|
"step": 1600
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.26002311706543,
|
||
|
|
"epoch": 0.12487842832133826,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.000499975090699982,
|
||
|
|
"loss": 6.2446,
|
||
|
|
"mean_token_accuracy": 0.12474475502967834,
|
||
|
|
"num_tokens": 2796051.0,
|
||
|
|
"step": 1605
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.323851251602173,
|
||
|
|
"epoch": 0.12526745769305583,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004999746765951438,
|
||
|
|
"loss": 6.2139,
|
||
|
|
"mean_token_accuracy": 0.12785117849707603,
|
||
|
|
"num_tokens": 2804961.0,
|
||
|
|
"step": 1610
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.220086097717285,
|
||
|
|
"epoch": 0.1256564870647734,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.0004999742590766729,
|
||
|
|
"loss": 6.162,
|
||
|
|
"mean_token_accuracy": 0.13089769557118416,
|
||
|
|
"num_tokens": 2813691.0,
|
||
|
|
"step": 1615
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.348862361907959,
|
||
|
|
"epoch": 0.12604551643649095,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.0004999738381445757,
|
||
|
|
"loss": 6.3027,
|
||
|
|
"mean_token_accuracy": 0.12603299766778947,
|
||
|
|
"num_tokens": 2822248.0,
|
||
|
|
"step": 1620
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.300800323486328,
|
||
|
|
"epoch": 0.1264345458082085,
|
||
|
|
"grad_norm": 0.98046875,
|
||
|
|
"learning_rate": 0.0004999734137988586,
|
||
|
|
"loss": 6.2652,
|
||
|
|
"mean_token_accuracy": 0.12721927613019943,
|
||
|
|
"num_tokens": 2830826.0,
|
||
|
|
"step": 1625
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.349361848831177,
|
||
|
|
"epoch": 0.1268235751799261,
|
||
|
|
"grad_norm": 1.140625,
|
||
|
|
"learning_rate": 0.000499972986039528,
|
||
|
|
"loss": 6.2394,
|
||
|
|
"mean_token_accuracy": 0.12500909343361855,
|
||
|
|
"num_tokens": 2839766.0,
|
||
|
|
"step": 1630
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.150761938095092,
|
||
|
|
"epoch": 0.12721260455164365,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0004999725548665904,
|
||
|
|
"loss": 6.1824,
|
||
|
|
"mean_token_accuracy": 0.1287871330976486,
|
||
|
|
"num_tokens": 2848728.0,
|
||
|
|
"step": 1635
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.2481162548065186,
|
||
|
|
"epoch": 0.1276016339233612,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0004999721202800524,
|
||
|
|
"loss": 6.2047,
|
||
|
|
"mean_token_accuracy": 0.12618736550211906,
|
||
|
|
"num_tokens": 2857221.0,
|
||
|
|
"step": 1640
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.356158924102783,
|
||
|
|
"epoch": 0.12799066329507877,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.0004999716822799206,
|
||
|
|
"loss": 6.2587,
|
||
|
|
"mean_token_accuracy": 0.12475384697318077,
|
||
|
|
"num_tokens": 2865314.0,
|
||
|
|
"step": 1645
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.177302742004395,
|
||
|
|
"epoch": 0.12837969266679633,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.0004999712408662016,
|
||
|
|
"loss": 6.1601,
|
||
|
|
"mean_token_accuracy": 0.12740891054272652,
|
||
|
|
"num_tokens": 2873654.0,
|
||
|
|
"step": 1650
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.293839740753174,
|
||
|
|
"epoch": 0.12876872203851392,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0004999707960389021,
|
||
|
|
"loss": 6.0531,
|
||
|
|
"mean_token_accuracy": 0.1375553861260414,
|
||
|
|
"num_tokens": 2881604.0,
|
||
|
|
"step": 1655
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.180183172225952,
|
||
|
|
"epoch": 0.12915775141023147,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.0004999703477980288,
|
||
|
|
"loss": 6.2284,
|
||
|
|
"mean_token_accuracy": 0.12667952552437783,
|
||
|
|
"num_tokens": 2890427.0,
|
||
|
|
"step": 1660
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.2946490287780765,
|
||
|
|
"epoch": 0.12954678078194903,
|
||
|
|
"grad_norm": 1.140625,
|
||
|
|
"learning_rate": 0.0004999698961435885,
|
||
|
|
"loss": 6.2166,
|
||
|
|
"mean_token_accuracy": 0.12776827216148376,
|
||
|
|
"num_tokens": 2899206.0,
|
||
|
|
"step": 1665
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.22862982749939,
|
||
|
|
"epoch": 0.1299358101536666,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.0004999694410755882,
|
||
|
|
"loss": 6.1441,
|
||
|
|
"mean_token_accuracy": 0.13045118749141693,
|
||
|
|
"num_tokens": 2907738.0,
|
||
|
|
"step": 1670
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.36701512336731,
|
||
|
|
"epoch": 0.13032483952538418,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0004999689825940347,
|
||
|
|
"loss": 6.3546,
|
||
|
|
"mean_token_accuracy": 0.12260913178324699,
|
||
|
|
"num_tokens": 2916881.0,
|
||
|
|
"step": 1675
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.307208681106568,
|
||
|
|
"epoch": 0.13071386889710174,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.0004999685206989349,
|
||
|
|
"loss": 6.2985,
|
||
|
|
"mean_token_accuracy": 0.12256755828857421,
|
||
|
|
"num_tokens": 2926467.0,
|
||
|
|
"step": 1680
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.328924751281738,
|
||
|
|
"epoch": 0.1311028982688193,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004999680553902959,
|
||
|
|
"loss": 6.2203,
|
||
|
|
"mean_token_accuracy": 0.12661089450120927,
|
||
|
|
"num_tokens": 2934671.0,
|
||
|
|
"step": 1685
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.2300127983093265,
|
||
|
|
"epoch": 0.13149192764053685,
|
||
|
|
"grad_norm": 0.99609375,
|
||
|
|
"learning_rate": 0.0004999675866681247,
|
||
|
|
"loss": 6.2477,
|
||
|
|
"mean_token_accuracy": 0.12255840674042702,
|
||
|
|
"num_tokens": 2943925.0,
|
||
|
|
"step": 1690
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.3268860340118405,
|
||
|
|
"epoch": 0.1318809570122544,
|
||
|
|
"grad_norm": 1.1640625,
|
||
|
|
"learning_rate": 0.0004999671145324286,
|
||
|
|
"loss": 6.2737,
|
||
|
|
"mean_token_accuracy": 0.12354717627167702,
|
||
|
|
"num_tokens": 2952118.0,
|
||
|
|
"step": 1695
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.198916673660278,
|
||
|
|
"epoch": 0.132269986383972,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004999666389832144,
|
||
|
|
"loss": 6.2565,
|
||
|
|
"mean_token_accuracy": 0.12337172478437423,
|
||
|
|
"num_tokens": 2961110.0,
|
||
|
|
"step": 1700
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.370461797714233,
|
||
|
|
"epoch": 0.13265901575568956,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.0004999661600204897,
|
||
|
|
"loss": 6.2018,
|
||
|
|
"mean_token_accuracy": 0.1303697146475315,
|
||
|
|
"num_tokens": 2968877.0,
|
||
|
|
"step": 1705
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.274533605575561,
|
||
|
|
"epoch": 0.13304804512740712,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.0004999656776442615,
|
||
|
|
"loss": 6.2517,
|
||
|
|
"mean_token_accuracy": 0.12431417629122735,
|
||
|
|
"num_tokens": 2977346.0,
|
||
|
|
"step": 1710
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.382883358001709,
|
||
|
|
"epoch": 0.13343707449912467,
|
||
|
|
"grad_norm": 1.1796875,
|
||
|
|
"learning_rate": 0.0004999651918545372,
|
||
|
|
"loss": 6.3048,
|
||
|
|
"mean_token_accuracy": 0.12000608816742897,
|
||
|
|
"num_tokens": 2987494.0,
|
||
|
|
"step": 1715
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.174839067459106,
|
||
|
|
"epoch": 0.13382610387084226,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0004999647026513243,
|
||
|
|
"loss": 6.2205,
|
||
|
|
"mean_token_accuracy": 0.12753525152802467,
|
||
|
|
"num_tokens": 2996728.0,
|
||
|
|
"step": 1720
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.326526355743408,
|
||
|
|
"epoch": 0.13421513324255982,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.00049996421003463,
|
||
|
|
"loss": 6.246,
|
||
|
|
"mean_token_accuracy": 0.1228347972035408,
|
||
|
|
"num_tokens": 3005810.0,
|
||
|
|
"step": 1725
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.330873584747314,
|
||
|
|
"epoch": 0.13460416261427738,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.0004999637140044619,
|
||
|
|
"loss": 6.2459,
|
||
|
|
"mean_token_accuracy": 0.126748938113451,
|
||
|
|
"num_tokens": 3014603.0,
|
||
|
|
"step": 1730
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.344876098632812,
|
||
|
|
"epoch": 0.13499319198599494,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.0004999632145608275,
|
||
|
|
"loss": 6.2485,
|
||
|
|
"mean_token_accuracy": 0.1315198339521885,
|
||
|
|
"num_tokens": 3023170.0,
|
||
|
|
"step": 1735
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.176899099349976,
|
||
|
|
"epoch": 0.1353822213577125,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.0004999627117037343,
|
||
|
|
"loss": 6.0139,
|
||
|
|
"mean_token_accuracy": 0.1374137058854103,
|
||
|
|
"num_tokens": 3030565.0,
|
||
|
|
"step": 1740
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.213472747802735,
|
||
|
|
"epoch": 0.13577125072943008,
|
||
|
|
"grad_norm": 0.98828125,
|
||
|
|
"learning_rate": 0.00049996220543319,
|
||
|
|
"loss": 6.2668,
|
||
|
|
"mean_token_accuracy": 0.12655473724007607,
|
||
|
|
"num_tokens": 3040124.0,
|
||
|
|
"step": 1745
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.248841428756714,
|
||
|
|
"epoch": 0.13616028010114764,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.0004999616957492025,
|
||
|
|
"loss": 6.1425,
|
||
|
|
"mean_token_accuracy": 0.13515366464853287,
|
||
|
|
"num_tokens": 3048458.0,
|
||
|
|
"step": 1750
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.153084564208984,
|
||
|
|
"epoch": 0.1365493094728652,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.0004999611826517793,
|
||
|
|
"loss": 6.0994,
|
||
|
|
"mean_token_accuracy": 0.12315743416547775,
|
||
|
|
"num_tokens": 3057926.0,
|
||
|
|
"step": 1755
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.198520135879517,
|
||
|
|
"epoch": 0.13693833884458276,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0004999606661409281,
|
||
|
|
"loss": 6.1478,
|
||
|
|
"mean_token_accuracy": 0.12459316626191139,
|
||
|
|
"num_tokens": 3066683.0,
|
||
|
|
"step": 1760
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.209071207046509,
|
||
|
|
"epoch": 0.13732736821630034,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.0004999601462166569,
|
||
|
|
"loss": 6.2232,
|
||
|
|
"mean_token_accuracy": 0.1232085220515728,
|
||
|
|
"num_tokens": 3075117.0,
|
||
|
|
"step": 1765
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.387924146652222,
|
||
|
|
"epoch": 0.1377163975880179,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0004999596228789736,
|
||
|
|
"loss": 6.2893,
|
||
|
|
"mean_token_accuracy": 0.11906761825084686,
|
||
|
|
"num_tokens": 3084399.0,
|
||
|
|
"step": 1770
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.153161096572876,
|
||
|
|
"epoch": 0.13810542695973546,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0004999590961278859,
|
||
|
|
"loss": 6.0684,
|
||
|
|
"mean_token_accuracy": 0.1295698270201683,
|
||
|
|
"num_tokens": 3093030.0,
|
||
|
|
"step": 1775
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.248177433013916,
|
||
|
|
"epoch": 0.13849445633145302,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.0004999585659634021,
|
||
|
|
"loss": 6.1324,
|
||
|
|
"mean_token_accuracy": 0.12821952775120735,
|
||
|
|
"num_tokens": 3101670.0,
|
||
|
|
"step": 1780
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.1346358299255375,
|
||
|
|
"epoch": 0.13888348570317058,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.0004999580323855301,
|
||
|
|
"loss": 6.1046,
|
||
|
|
"mean_token_accuracy": 0.13306863680481912,
|
||
|
|
"num_tokens": 3109703.0,
|
||
|
|
"step": 1785
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.173340606689453,
|
||
|
|
"epoch": 0.13927251507488816,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.0004999574953942781,
|
||
|
|
"loss": 6.0857,
|
||
|
|
"mean_token_accuracy": 0.13532105088233948,
|
||
|
|
"num_tokens": 3118388.0,
|
||
|
|
"step": 1790
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.211510944366455,
|
||
|
|
"epoch": 0.13966154444660572,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.0004999569549896541,
|
||
|
|
"loss": 6.0999,
|
||
|
|
"mean_token_accuracy": 0.12918610870838165,
|
||
|
|
"num_tokens": 3126466.0,
|
||
|
|
"step": 1795
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.148796653747558,
|
||
|
|
"epoch": 0.14005057381832328,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0004999564111716665,
|
||
|
|
"loss": 6.1445,
|
||
|
|
"mean_token_accuracy": 0.1295869193971157,
|
||
|
|
"num_tokens": 3135322.0,
|
||
|
|
"step": 1800
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.213176441192627,
|
||
|
|
"epoch": 0.14043960319004084,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.0004999558639403232,
|
||
|
|
"loss": 6.1362,
|
||
|
|
"mean_token_accuracy": 0.13269315287470818,
|
||
|
|
"num_tokens": 3144498.0,
|
||
|
|
"step": 1805
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.154889154434204,
|
||
|
|
"epoch": 0.1408286325617584,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004999553132956328,
|
||
|
|
"loss": 6.0918,
|
||
|
|
"mean_token_accuracy": 0.1243074245750904,
|
||
|
|
"num_tokens": 3153573.0,
|
||
|
|
"step": 1810
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.111627864837646,
|
||
|
|
"epoch": 0.14121766193347599,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.0004999547592376035,
|
||
|
|
"loss": 6.0367,
|
||
|
|
"mean_token_accuracy": 0.13732606172561646,
|
||
|
|
"num_tokens": 3161705.0,
|
||
|
|
"step": 1815
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.186681270599365,
|
||
|
|
"epoch": 0.14160669130519354,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.0004999542017662438,
|
||
|
|
"loss": 6.2095,
|
||
|
|
"mean_token_accuracy": 0.1262743815779686,
|
||
|
|
"num_tokens": 3170068.0,
|
||
|
|
"step": 1820
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.2195604801177975,
|
||
|
|
"epoch": 0.1419957206769111,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.0004999536408815623,
|
||
|
|
"loss": 6.2049,
|
||
|
|
"mean_token_accuracy": 0.1259988561272621,
|
||
|
|
"num_tokens": 3178140.0,
|
||
|
|
"step": 1825
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.24831223487854,
|
||
|
|
"epoch": 0.14238475004862866,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.0004999530765835672,
|
||
|
|
"loss": 6.1748,
|
||
|
|
"mean_token_accuracy": 0.12702307850122452,
|
||
|
|
"num_tokens": 3186518.0,
|
||
|
|
"step": 1830
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.132204341888428,
|
||
|
|
"epoch": 0.14277377942034625,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0004999525088722673,
|
||
|
|
"loss": 6.1701,
|
||
|
|
"mean_token_accuracy": 0.12800654545426368,
|
||
|
|
"num_tokens": 3195246.0,
|
||
|
|
"step": 1835
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.260305500030517,
|
||
|
|
"epoch": 0.1431628087920638,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.0004999519377476711,
|
||
|
|
"loss": 6.1879,
|
||
|
|
"mean_token_accuracy": 0.12606484889984132,
|
||
|
|
"num_tokens": 3203946.0,
|
||
|
|
"step": 1840
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.296053028106689,
|
||
|
|
"epoch": 0.14355183816378136,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0004999513632097872,
|
||
|
|
"loss": 6.1966,
|
||
|
|
"mean_token_accuracy": 0.12585848867893218,
|
||
|
|
"num_tokens": 3212208.0,
|
||
|
|
"step": 1845
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.150812864303589,
|
||
|
|
"epoch": 0.14394086753549892,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.0004999507852586245,
|
||
|
|
"loss": 6.1283,
|
||
|
|
"mean_token_accuracy": 0.1285582311451435,
|
||
|
|
"num_tokens": 3221572.0,
|
||
|
|
"step": 1850
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.348111915588379,
|
||
|
|
"epoch": 0.14432989690721648,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004999502038941917,
|
||
|
|
"loss": 6.2547,
|
||
|
|
"mean_token_accuracy": 0.12246640846133232,
|
||
|
|
"num_tokens": 3230898.0,
|
||
|
|
"step": 1855
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.1041018009185795,
|
||
|
|
"epoch": 0.14471892627893407,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.0004999496191164975,
|
||
|
|
"loss": 6.2237,
|
||
|
|
"mean_token_accuracy": 0.12463869079947472,
|
||
|
|
"num_tokens": 3240524.0,
|
||
|
|
"step": 1860
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.230608510971069,
|
||
|
|
"epoch": 0.14510795565065163,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.000499949030925551,
|
||
|
|
"loss": 5.983,
|
||
|
|
"mean_token_accuracy": 0.13494621962308884,
|
||
|
|
"num_tokens": 3248864.0,
|
||
|
|
"step": 1865
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.146592664718628,
|
||
|
|
"epoch": 0.14549698502236919,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.0004999484393213609,
|
||
|
|
"loss": 6.1843,
|
||
|
|
"mean_token_accuracy": 0.13349625766277312,
|
||
|
|
"num_tokens": 3256823.0,
|
||
|
|
"step": 1870
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.205172920227051,
|
||
|
|
"epoch": 0.14588601439408674,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004999478443039363,
|
||
|
|
"loss": 6.081,
|
||
|
|
"mean_token_accuracy": 0.13374736532568932,
|
||
|
|
"num_tokens": 3265621.0,
|
||
|
|
"step": 1875
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.102890062332153,
|
||
|
|
"epoch": 0.14627504376580433,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.0004999472458732862,
|
||
|
|
"loss": 6.1181,
|
||
|
|
"mean_token_accuracy": 0.13089252263307571,
|
||
|
|
"num_tokens": 3273515.0,
|
||
|
|
"step": 1880
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.302053070068359,
|
||
|
|
"epoch": 0.1466640731375219,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.0004999466440294198,
|
||
|
|
"loss": 6.1777,
|
||
|
|
"mean_token_accuracy": 0.1274590365588665,
|
||
|
|
"num_tokens": 3282283.0,
|
||
|
|
"step": 1885
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.190755081176758,
|
||
|
|
"epoch": 0.14705310250923945,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.000499946038772346,
|
||
|
|
"loss": 6.1776,
|
||
|
|
"mean_token_accuracy": 0.13259075209498405,
|
||
|
|
"num_tokens": 3290792.0,
|
||
|
|
"step": 1890
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.0863714694976805,
|
||
|
|
"epoch": 0.147442131880957,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.0004999454301020741,
|
||
|
|
"loss": 6.0339,
|
||
|
|
"mean_token_accuracy": 0.13120581805706025,
|
||
|
|
"num_tokens": 3299430.0,
|
||
|
|
"step": 1895
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.0903504371643065,
|
||
|
|
"epoch": 0.14783116125267456,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0004999448180186133,
|
||
|
|
"loss": 6.0903,
|
||
|
|
"mean_token_accuracy": 0.13683573827147483,
|
||
|
|
"num_tokens": 3307949.0,
|
||
|
|
"step": 1900
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.229368877410889,
|
||
|
|
"epoch": 0.14822019062439215,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.000499944202521973,
|
||
|
|
"loss": 6.1406,
|
||
|
|
"mean_token_accuracy": 0.132175462692976,
|
||
|
|
"num_tokens": 3316900.0,
|
||
|
|
"step": 1905
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.17071123123169,
|
||
|
|
"epoch": 0.1486092199961097,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.0004999435836121624,
|
||
|
|
"loss": 6.0652,
|
||
|
|
"mean_token_accuracy": 0.1382671631872654,
|
||
|
|
"num_tokens": 3325656.0,
|
||
|
|
"step": 1910
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.12831974029541,
|
||
|
|
"epoch": 0.14899824936782727,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.000499942961289191,
|
||
|
|
"loss": 6.2872,
|
||
|
|
"mean_token_accuracy": 0.1173948660492897,
|
||
|
|
"num_tokens": 3334219.0,
|
||
|
|
"step": 1915
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.157317447662353,
|
||
|
|
"epoch": 0.14938727873954483,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0004999423355530683,
|
||
|
|
"loss": 6.0383,
|
||
|
|
"mean_token_accuracy": 0.13165762796998023,
|
||
|
|
"num_tokens": 3343637.0,
|
||
|
|
"step": 1920
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.206801414489746,
|
||
|
|
"epoch": 0.1497763081112624,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.0004999417064038035,
|
||
|
|
"loss": 6.1862,
|
||
|
|
"mean_token_accuracy": 0.12926548048853875,
|
||
|
|
"num_tokens": 3352624.0,
|
||
|
|
"step": 1925
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.149757146835327,
|
||
|
|
"epoch": 0.15016533748297997,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.0004999410738414065,
|
||
|
|
"loss": 6.1082,
|
||
|
|
"mean_token_accuracy": 0.13714757189154625,
|
||
|
|
"num_tokens": 3361394.0,
|
||
|
|
"step": 1930
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.227800416946411,
|
||
|
|
"epoch": 0.15055436685469753,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0004999404378658866,
|
||
|
|
"loss": 6.1733,
|
||
|
|
"mean_token_accuracy": 0.12909363806247712,
|
||
|
|
"num_tokens": 3369406.0,
|
||
|
|
"step": 1935
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.210609102249146,
|
||
|
|
"epoch": 0.1509433962264151,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.0004999397984772536,
|
||
|
|
"loss": 6.118,
|
||
|
|
"mean_token_accuracy": 0.13228227570652962,
|
||
|
|
"num_tokens": 3377737.0,
|
||
|
|
"step": 1940
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.14217209815979,
|
||
|
|
"epoch": 0.15133242559813265,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.0004999391556755172,
|
||
|
|
"loss": 6.1793,
|
||
|
|
"mean_token_accuracy": 0.12301846668124199,
|
||
|
|
"num_tokens": 3385514.0,
|
||
|
|
"step": 1945
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.25277943611145,
|
||
|
|
"epoch": 0.15172145496985023,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.0004999385094606872,
|
||
|
|
"loss": 6.0841,
|
||
|
|
"mean_token_accuracy": 0.12941004782915116,
|
||
|
|
"num_tokens": 3394500.0,
|
||
|
|
"step": 1950
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.072525215148926,
|
||
|
|
"epoch": 0.1521104843415678,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.0004999378598327733,
|
||
|
|
"loss": 6.0482,
|
||
|
|
"mean_token_accuracy": 0.13268509283661842,
|
||
|
|
"num_tokens": 3403289.0,
|
||
|
|
"step": 1955
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.129705810546875,
|
||
|
|
"epoch": 0.15249951371328535,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.0004999372067917854,
|
||
|
|
"loss": 5.9779,
|
||
|
|
"mean_token_accuracy": 0.14540664553642274,
|
||
|
|
"num_tokens": 3410892.0,
|
||
|
|
"step": 1960
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.94409441947937,
|
||
|
|
"epoch": 0.1528885430850029,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.0004999365503377335,
|
||
|
|
"loss": 6.0923,
|
||
|
|
"mean_token_accuracy": 0.1343274734914303,
|
||
|
|
"num_tokens": 3420329.0,
|
||
|
|
"step": 1965
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.1848186492919925,
|
||
|
|
"epoch": 0.1532775724567205,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 0.0004999358904706273,
|
||
|
|
"loss": 6.0757,
|
||
|
|
"mean_token_accuracy": 0.13067501410841942,
|
||
|
|
"num_tokens": 3429429.0,
|
||
|
|
"step": 1970
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.242197704315186,
|
||
|
|
"epoch": 0.15366660182843805,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.0004999352271904771,
|
||
|
|
"loss": 6.1883,
|
||
|
|
"mean_token_accuracy": 0.13034674525260925,
|
||
|
|
"num_tokens": 3438198.0,
|
||
|
|
"step": 1975
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.305315351486206,
|
||
|
|
"epoch": 0.1540556312001556,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.0004999345604972928,
|
||
|
|
"loss": 6.3239,
|
||
|
|
"mean_token_accuracy": 0.12621623277664185,
|
||
|
|
"num_tokens": 3447732.0,
|
||
|
|
"step": 1980
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.164562368392945,
|
||
|
|
"epoch": 0.15444466057187317,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.0004999338903910846,
|
||
|
|
"loss": 6.1061,
|
||
|
|
"mean_token_accuracy": 0.13278778791427612,
|
||
|
|
"num_tokens": 3456392.0,
|
||
|
|
"step": 1985
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.115700435638428,
|
||
|
|
"epoch": 0.15483368994359073,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.0004999332168718626,
|
||
|
|
"loss": 6.1287,
|
||
|
|
"mean_token_accuracy": 0.12967223972082137,
|
||
|
|
"num_tokens": 3464473.0,
|
||
|
|
"step": 1990
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.218503189086914,
|
||
|
|
"epoch": 0.15522271931530832,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004999325399396371,
|
||
|
|
"loss": 6.1162,
|
||
|
|
"mean_token_accuracy": 0.1300376333296299,
|
||
|
|
"num_tokens": 3473740.0,
|
||
|
|
"step": 1995
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.042573642730713,
|
||
|
|
"epoch": 0.15561174868702587,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.0004999318595944183,
|
||
|
|
"loss": 5.9931,
|
||
|
|
"mean_token_accuracy": 0.13783685192465783,
|
||
|
|
"num_tokens": 3482249.0,
|
||
|
|
"step": 2000
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.1918027877807615,
|
||
|
|
"epoch": 0.15600077805874343,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.0004999311758362166,
|
||
|
|
"loss": 6.232,
|
||
|
|
"mean_token_accuracy": 0.12764381915330886,
|
||
|
|
"num_tokens": 3490753.0,
|
||
|
|
"step": 2005
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.289742422103882,
|
||
|
|
"epoch": 0.156389807430461,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.0004999304886650422,
|
||
|
|
"loss": 6.1855,
|
||
|
|
"mean_token_accuracy": 0.13486020341515542,
|
||
|
|
"num_tokens": 3499373.0,
|
||
|
|
"step": 2010
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.184504985809326,
|
||
|
|
"epoch": 0.15677883680217858,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.0004999297980809058,
|
||
|
|
"loss": 6.1424,
|
||
|
|
"mean_token_accuracy": 0.1249059982597828,
|
||
|
|
"num_tokens": 3508344.0,
|
||
|
|
"step": 2015
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.184778118133545,
|
||
|
|
"epoch": 0.15716786617389614,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.0004999291040838176,
|
||
|
|
"loss": 6.1248,
|
||
|
|
"mean_token_accuracy": 0.12921407744288443,
|
||
|
|
"num_tokens": 3517009.0,
|
||
|
|
"step": 2020
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.145992374420166,
|
||
|
|
"epoch": 0.1575568955456137,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.0004999284066737884,
|
||
|
|
"loss": 6.1738,
|
||
|
|
"mean_token_accuracy": 0.12950941175222397,
|
||
|
|
"num_tokens": 3525989.0,
|
||
|
|
"step": 2025
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.1984889030456545,
|
||
|
|
"epoch": 0.15794592491733125,
|
||
|
|
"grad_norm": 1.2421875,
|
||
|
|
"learning_rate": 0.0004999277058508285,
|
||
|
|
"loss": 6.0545,
|
||
|
|
"mean_token_accuracy": 0.131241425126791,
|
||
|
|
"num_tokens": 3533947.0,
|
||
|
|
"step": 2030
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.107672691345215,
|
||
|
|
"epoch": 0.1583349542890488,
|
||
|
|
"grad_norm": 1.15625,
|
||
|
|
"learning_rate": 0.0004999270016149486,
|
||
|
|
"loss": 6.1038,
|
||
|
|
"mean_token_accuracy": 0.13247671499848365,
|
||
|
|
"num_tokens": 3541974.0,
|
||
|
|
"step": 2035
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.177549695968628,
|
||
|
|
"epoch": 0.1587239836607664,
|
||
|
|
"grad_norm": 1.2265625,
|
||
|
|
"learning_rate": 0.0004999262939661596,
|
||
|
|
"loss": 6.0491,
|
||
|
|
"mean_token_accuracy": 0.13692999854683877,
|
||
|
|
"num_tokens": 3550436.0,
|
||
|
|
"step": 2040
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.074217414855957,
|
||
|
|
"epoch": 0.15911301303248396,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.0004999255829044721,
|
||
|
|
"loss": 6.0395,
|
||
|
|
"mean_token_accuracy": 0.1331242173910141,
|
||
|
|
"num_tokens": 3558283.0,
|
||
|
|
"step": 2045
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.054254388809204,
|
||
|
|
"epoch": 0.15950204240420152,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004999248684298968,
|
||
|
|
"loss": 5.9622,
|
||
|
|
"mean_token_accuracy": 0.13776934295892715,
|
||
|
|
"num_tokens": 3566968.0,
|
||
|
|
"step": 2050
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.1414141178131105,
|
||
|
|
"epoch": 0.15989107177591907,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.0004999241505424447,
|
||
|
|
"loss": 6.09,
|
||
|
|
"mean_token_accuracy": 0.1294178307056427,
|
||
|
|
"num_tokens": 3575580.0,
|
||
|
|
"step": 2055
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.134491062164306,
|
||
|
|
"epoch": 0.16028010114763663,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.0004999234292421265,
|
||
|
|
"loss": 6.1488,
|
||
|
|
"mean_token_accuracy": 0.1253335177898407,
|
||
|
|
"num_tokens": 3584389.0,
|
||
|
|
"step": 2060
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.124525165557861,
|
||
|
|
"epoch": 0.16066913051935422,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004999227045289535,
|
||
|
|
"loss": 5.9953,
|
||
|
|
"mean_token_accuracy": 0.13211522698402406,
|
||
|
|
"num_tokens": 3593009.0,
|
||
|
|
"step": 2065
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.005406618118286,
|
||
|
|
"epoch": 0.16105815989107178,
|
||
|
|
"grad_norm": 1.140625,
|
||
|
|
"learning_rate": 0.0004999219764029363,
|
||
|
|
"loss": 6.0273,
|
||
|
|
"mean_token_accuracy": 0.13406043648719787,
|
||
|
|
"num_tokens": 3601914.0,
|
||
|
|
"step": 2070
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.083451604843139,
|
||
|
|
"epoch": 0.16144718926278934,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.0004999212448640861,
|
||
|
|
"loss": 6.0017,
|
||
|
|
"mean_token_accuracy": 0.1371099457144737,
|
||
|
|
"num_tokens": 3609883.0,
|
||
|
|
"step": 2075
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.041997861862183,
|
||
|
|
"epoch": 0.1618362186345069,
|
||
|
|
"grad_norm": 1.1796875,
|
||
|
|
"learning_rate": 0.0004999205099124141,
|
||
|
|
"loss": 5.9485,
|
||
|
|
"mean_token_accuracy": 0.1380833439528942,
|
||
|
|
"num_tokens": 3618103.0,
|
||
|
|
"step": 2080
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.211324644088745,
|
||
|
|
"epoch": 0.16222524800622448,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.0004999197715479313,
|
||
|
|
"loss": 6.2004,
|
||
|
|
"mean_token_accuracy": 0.12658180743455888,
|
||
|
|
"num_tokens": 3625861.0,
|
||
|
|
"step": 2085
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.0661292552948,
|
||
|
|
"epoch": 0.16261427737794204,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.0004999190297706489,
|
||
|
|
"loss": 5.9956,
|
||
|
|
"mean_token_accuracy": 0.13370829075574875,
|
||
|
|
"num_tokens": 3634498.0,
|
||
|
|
"step": 2090
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.9809905052185055,
|
||
|
|
"epoch": 0.1630033067496596,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0004999182845805783,
|
||
|
|
"loss": 5.9366,
|
||
|
|
"mean_token_accuracy": 0.1317710854113102,
|
||
|
|
"num_tokens": 3644186.0,
|
||
|
|
"step": 2095
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.073202466964721,
|
||
|
|
"epoch": 0.16339233612137716,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0004999175359777306,
|
||
|
|
"loss": 6.0839,
|
||
|
|
"mean_token_accuracy": 0.1325150176882744,
|
||
|
|
"num_tokens": 3652831.0,
|
||
|
|
"step": 2100
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.146014595031739,
|
||
|
|
"epoch": 0.16378136549309472,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.0004999167839621174,
|
||
|
|
"loss": 5.9266,
|
||
|
|
"mean_token_accuracy": 0.13688404113054276,
|
||
|
|
"num_tokens": 3661230.0,
|
||
|
|
"step": 2105
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.052286386489868,
|
||
|
|
"epoch": 0.1641703948648123,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.0004999160285337501,
|
||
|
|
"loss": 6.0939,
|
||
|
|
"mean_token_accuracy": 0.13448251336812972,
|
||
|
|
"num_tokens": 3669250.0,
|
||
|
|
"step": 2110
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.162040853500367,
|
||
|
|
"epoch": 0.16455942423652986,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 0.0004999152696926399,
|
||
|
|
"loss": 6.0641,
|
||
|
|
"mean_token_accuracy": 0.13017964810132981,
|
||
|
|
"num_tokens": 3677568.0,
|
||
|
|
"step": 2115
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.074533367156983,
|
||
|
|
"epoch": 0.16494845360824742,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.0004999145074387985,
|
||
|
|
"loss": 6.0569,
|
||
|
|
"mean_token_accuracy": 0.13938968032598495,
|
||
|
|
"num_tokens": 3685488.0,
|
||
|
|
"step": 2120
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.06183180809021,
|
||
|
|
"epoch": 0.16533748297996498,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.0004999137417722374,
|
||
|
|
"loss": 6.0211,
|
||
|
|
"mean_token_accuracy": 0.1328076884150505,
|
||
|
|
"num_tokens": 3694357.0,
|
||
|
|
"step": 2125
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.185010480880737,
|
||
|
|
"epoch": 0.16572651235168256,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0004999129726929684,
|
||
|
|
"loss": 6.0988,
|
||
|
|
"mean_token_accuracy": 0.12953946217894555,
|
||
|
|
"num_tokens": 3703173.0,
|
||
|
|
"step": 2130
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.085592031478882,
|
||
|
|
"epoch": 0.16611554172340012,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.0004999122002010029,
|
||
|
|
"loss": 6.0802,
|
||
|
|
"mean_token_accuracy": 0.1351713642477989,
|
||
|
|
"num_tokens": 3712070.0,
|
||
|
|
"step": 2135
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.08102331161499,
|
||
|
|
"epoch": 0.16650457109511768,
|
||
|
|
"grad_norm": 1.171875,
|
||
|
|
"learning_rate": 0.0004999114242963527,
|
||
|
|
"loss": 5.9542,
|
||
|
|
"mean_token_accuracy": 0.13849778547883035,
|
||
|
|
"num_tokens": 3720245.0,
|
||
|
|
"step": 2140
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.093478488922119,
|
||
|
|
"epoch": 0.16689360046683524,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.0004999106449790298,
|
||
|
|
"loss": 6.0675,
|
||
|
|
"mean_token_accuracy": 0.1316705711185932,
|
||
|
|
"num_tokens": 3730064.0,
|
||
|
|
"step": 2145
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.04008116722107,
|
||
|
|
"epoch": 0.1672826298385528,
|
||
|
|
"grad_norm": 1.15625,
|
||
|
|
"learning_rate": 0.0004999098622490458,
|
||
|
|
"loss": 6.0144,
|
||
|
|
"mean_token_accuracy": 0.13639871776103973,
|
||
|
|
"num_tokens": 3738741.0,
|
||
|
|
"step": 2150
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.110120344161987,
|
||
|
|
"epoch": 0.16767165921027039,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.0004999090761064125,
|
||
|
|
"loss": 6.082,
|
||
|
|
"mean_token_accuracy": 0.1319386325776577,
|
||
|
|
"num_tokens": 3747472.0,
|
||
|
|
"step": 2155
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.128765726089478,
|
||
|
|
"epoch": 0.16806068858198794,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.000499908286551142,
|
||
|
|
"loss": 6.1113,
|
||
|
|
"mean_token_accuracy": 0.12933499738574028,
|
||
|
|
"num_tokens": 3756643.0,
|
||
|
|
"step": 2160
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.174497509002686,
|
||
|
|
"epoch": 0.1684497179537055,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.0004999074935832463,
|
||
|
|
"loss": 6.2028,
|
||
|
|
"mean_token_accuracy": 0.12676079869270324,
|
||
|
|
"num_tokens": 3765490.0,
|
||
|
|
"step": 2165
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.175439405441284,
|
||
|
|
"epoch": 0.16883874732542306,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.0004999066972027373,
|
||
|
|
"loss": 5.982,
|
||
|
|
"mean_token_accuracy": 0.1337745077908039,
|
||
|
|
"num_tokens": 3773063.0,
|
||
|
|
"step": 2170
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.086578416824341,
|
||
|
|
"epoch": 0.16922777669714065,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.0004999058974096271,
|
||
|
|
"loss": 6.1422,
|
||
|
|
"mean_token_accuracy": 0.13035047948360443,
|
||
|
|
"num_tokens": 3781763.0,
|
||
|
|
"step": 2175
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.155812501907349,
|
||
|
|
"epoch": 0.1696168060688582,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.000499905094203928,
|
||
|
|
"loss": 6.1166,
|
||
|
|
"mean_token_accuracy": 0.13063591718673706,
|
||
|
|
"num_tokens": 3790582.0,
|
||
|
|
"step": 2180
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.049755430221557,
|
||
|
|
"epoch": 0.17000583544057576,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.000499904287585652,
|
||
|
|
"loss": 5.9385,
|
||
|
|
"mean_token_accuracy": 0.13590469360351562,
|
||
|
|
"num_tokens": 3798745.0,
|
||
|
|
"step": 2185
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.070274925231933,
|
||
|
|
"epoch": 0.17039486481229332,
|
||
|
|
"grad_norm": 1.15625,
|
||
|
|
"learning_rate": 0.0004999034775548113,
|
||
|
|
"loss": 6.0465,
|
||
|
|
"mean_token_accuracy": 0.13319867253303527,
|
||
|
|
"num_tokens": 3806901.0,
|
||
|
|
"step": 2190
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.097325992584229,
|
||
|
|
"epoch": 0.17078389418401088,
|
||
|
|
"grad_norm": 1.3359375,
|
||
|
|
"learning_rate": 0.0004999026641114185,
|
||
|
|
"loss": 5.9886,
|
||
|
|
"mean_token_accuracy": 0.14209552258253097,
|
||
|
|
"num_tokens": 3815742.0,
|
||
|
|
"step": 2195
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.061678075790406,
|
||
|
|
"epoch": 0.17117292355572847,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.0004999018472554857,
|
||
|
|
"loss": 6.0584,
|
||
|
|
"mean_token_accuracy": 0.13574853166937828,
|
||
|
|
"num_tokens": 3824468.0,
|
||
|
|
"step": 2200
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.073797559738159,
|
||
|
|
"epoch": 0.17156195292744603,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0004999010269870253,
|
||
|
|
"loss": 6.0104,
|
||
|
|
"mean_token_accuracy": 0.14009651392698289,
|
||
|
|
"num_tokens": 3832834.0,
|
||
|
|
"step": 2205
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.0712377548217775,
|
||
|
|
"epoch": 0.17195098229916359,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.0004999002033060498,
|
||
|
|
"loss": 6.0698,
|
||
|
|
"mean_token_accuracy": 0.13802544698119162,
|
||
|
|
"num_tokens": 3841780.0,
|
||
|
|
"step": 2210
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.18810019493103,
|
||
|
|
"epoch": 0.17234001167088114,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.0004998993762125716,
|
||
|
|
"loss": 6.1724,
|
||
|
|
"mean_token_accuracy": 0.12603602111339568,
|
||
|
|
"num_tokens": 3849840.0,
|
||
|
|
"step": 2215
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.1790083885192875,
|
||
|
|
"epoch": 0.17272904104259873,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.0004998985457066034,
|
||
|
|
"loss": 6.1032,
|
||
|
|
"mean_token_accuracy": 0.12879095897078513,
|
||
|
|
"num_tokens": 3858204.0,
|
||
|
|
"step": 2220
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.101538562774659,
|
||
|
|
"epoch": 0.1731180704143163,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004998977117881576,
|
||
|
|
"loss": 6.064,
|
||
|
|
"mean_token_accuracy": 0.13742057457566262,
|
||
|
|
"num_tokens": 3866615.0,
|
||
|
|
"step": 2225
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.113582420349121,
|
||
|
|
"epoch": 0.17350709978603385,
|
||
|
|
"grad_norm": 0.953125,
|
||
|
|
"learning_rate": 0.0004998968744572472,
|
||
|
|
"loss": 6.0757,
|
||
|
|
"mean_token_accuracy": 0.1406781442463398,
|
||
|
|
"num_tokens": 3876003.0,
|
||
|
|
"step": 2230
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.089564180374145,
|
||
|
|
"epoch": 0.1738961291577514,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.0004998960337138845,
|
||
|
|
"loss": 5.9898,
|
||
|
|
"mean_token_accuracy": 0.13798459023237228,
|
||
|
|
"num_tokens": 3884362.0,
|
||
|
|
"step": 2235
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.070445728302002,
|
||
|
|
"epoch": 0.17428515852946896,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.0004998951895580826,
|
||
|
|
"loss": 5.9656,
|
||
|
|
"mean_token_accuracy": 0.13325194045901298,
|
||
|
|
"num_tokens": 3893177.0,
|
||
|
|
"step": 2240
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.066017198562622,
|
||
|
|
"epoch": 0.17467418790118655,
|
||
|
|
"grad_norm": 1.15625,
|
||
|
|
"learning_rate": 0.0004998943419898542,
|
||
|
|
"loss": 6.0105,
|
||
|
|
"mean_token_accuracy": 0.1373025618493557,
|
||
|
|
"num_tokens": 3903006.0,
|
||
|
|
"step": 2245
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.062432098388672,
|
||
|
|
"epoch": 0.1750632172729041,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0004998934910092119,
|
||
|
|
"loss": 5.8835,
|
||
|
|
"mean_token_accuracy": 0.13740511238574982,
|
||
|
|
"num_tokens": 3912256.0,
|
||
|
|
"step": 2250
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.976859426498413,
|
||
|
|
"epoch": 0.17545224664462167,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.0004998926366161689,
|
||
|
|
"loss": 6.0611,
|
||
|
|
"mean_token_accuracy": 0.13139487579464912,
|
||
|
|
"num_tokens": 3921121.0,
|
||
|
|
"step": 2255
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.122124671936035,
|
||
|
|
"epoch": 0.17584127601633923,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.0004998917788107383,
|
||
|
|
"loss": 6.0115,
|
||
|
|
"mean_token_accuracy": 0.136553792655468,
|
||
|
|
"num_tokens": 3929348.0,
|
||
|
|
"step": 2260
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.115105676651001,
|
||
|
|
"epoch": 0.17623030538805678,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.0004998909175929326,
|
||
|
|
"loss": 6.1648,
|
||
|
|
"mean_token_accuracy": 0.1333843521773815,
|
||
|
|
"num_tokens": 3938073.0,
|
||
|
|
"step": 2265
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.180411100387573,
|
||
|
|
"epoch": 0.17661933475977437,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.0004998900529627653,
|
||
|
|
"loss": 6.1517,
|
||
|
|
"mean_token_accuracy": 0.13141252994537353,
|
||
|
|
"num_tokens": 3946641.0,
|
||
|
|
"step": 2270
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.104985952377319,
|
||
|
|
"epoch": 0.17700836413149193,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0004998891849202495,
|
||
|
|
"loss": 5.9903,
|
||
|
|
"mean_token_accuracy": 0.14097551256418228,
|
||
|
|
"num_tokens": 3954586.0,
|
||
|
|
"step": 2275
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.104686546325683,
|
||
|
|
"epoch": 0.1773973935032095,
|
||
|
|
"grad_norm": 1.1640625,
|
||
|
|
"learning_rate": 0.000499888313465398,
|
||
|
|
"loss": 6.07,
|
||
|
|
"mean_token_accuracy": 0.13397311642766,
|
||
|
|
"num_tokens": 3963745.0,
|
||
|
|
"step": 2280
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.96400728225708,
|
||
|
|
"epoch": 0.17778642287492705,
|
||
|
|
"grad_norm": 1.140625,
|
||
|
|
"learning_rate": 0.0004998874385982247,
|
||
|
|
"loss": 5.9027,
|
||
|
|
"mean_token_accuracy": 0.14004776999354362,
|
||
|
|
"num_tokens": 3972452.0,
|
||
|
|
"step": 2285
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.05688362121582,
|
||
|
|
"epoch": 0.17817545224664463,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.0004998865603187421,
|
||
|
|
"loss": 5.9988,
|
||
|
|
"mean_token_accuracy": 0.1436510995030403,
|
||
|
|
"num_tokens": 3980770.0,
|
||
|
|
"step": 2290
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.075594854354859,
|
||
|
|
"epoch": 0.1785644816183622,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.000499885678626964,
|
||
|
|
"loss": 6.0332,
|
||
|
|
"mean_token_accuracy": 0.1328875847160816,
|
||
|
|
"num_tokens": 3989545.0,
|
||
|
|
"step": 2295
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.132068157196045,
|
||
|
|
"epoch": 0.17895351099007975,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0004998847935229038,
|
||
|
|
"loss": 5.9967,
|
||
|
|
"mean_token_accuracy": 0.13653107732534409,
|
||
|
|
"num_tokens": 3998034.0,
|
||
|
|
"step": 2300
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.996809244155884,
|
||
|
|
"epoch": 0.1793425403617973,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.0004998839050065746,
|
||
|
|
"loss": 6.0155,
|
||
|
|
"mean_token_accuracy": 0.13644992858171462,
|
||
|
|
"num_tokens": 4007110.0,
|
||
|
|
"step": 2305
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.1447912693023685,
|
||
|
|
"epoch": 0.17973156973351487,
|
||
|
|
"grad_norm": 1.1640625,
|
||
|
|
"learning_rate": 0.0004998830130779902,
|
||
|
|
"loss": 6.081,
|
||
|
|
"mean_token_accuracy": 0.1253010168671608,
|
||
|
|
"num_tokens": 4015930.0,
|
||
|
|
"step": 2310
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.943305206298828,
|
||
|
|
"epoch": 0.18012059910523245,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.000499882117737164,
|
||
|
|
"loss": 5.9002,
|
||
|
|
"mean_token_accuracy": 0.1380581721663475,
|
||
|
|
"num_tokens": 4024510.0,
|
||
|
|
"step": 2315
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.021866035461426,
|
||
|
|
"epoch": 0.18050962847695,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.0004998812189841096,
|
||
|
|
"loss": 6.0017,
|
||
|
|
"mean_token_accuracy": 0.13569412529468536,
|
||
|
|
"num_tokens": 4033714.0,
|
||
|
|
"step": 2320
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.267440891265869,
|
||
|
|
"epoch": 0.18089865784866757,
|
||
|
|
"grad_norm": 1.1953125,
|
||
|
|
"learning_rate": 0.0004998803168188407,
|
||
|
|
"loss": 6.1894,
|
||
|
|
"mean_token_accuracy": 0.12759222686290742,
|
||
|
|
"num_tokens": 4042376.0,
|
||
|
|
"step": 2325
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.987464523315429,
|
||
|
|
"epoch": 0.18128768722038513,
|
||
|
|
"grad_norm": 1.15625,
|
||
|
|
"learning_rate": 0.0004998794112413708,
|
||
|
|
"loss": 5.9676,
|
||
|
|
"mean_token_accuracy": 0.13705897852778434,
|
||
|
|
"num_tokens": 4050521.0,
|
||
|
|
"step": 2330
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.129739475250244,
|
||
|
|
"epoch": 0.18167671659210272,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.0004998785022517137,
|
||
|
|
"loss": 6.1285,
|
||
|
|
"mean_token_accuracy": 0.13060672208666801,
|
||
|
|
"num_tokens": 4059384.0,
|
||
|
|
"step": 2335
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.096893787384033,
|
||
|
|
"epoch": 0.18206574596382027,
|
||
|
|
"grad_norm": 1.171875,
|
||
|
|
"learning_rate": 0.0004998775898498835,
|
||
|
|
"loss": 5.9993,
|
||
|
|
"mean_token_accuracy": 0.14007975906133652,
|
||
|
|
"num_tokens": 4067655.0,
|
||
|
|
"step": 2340
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.091242122650146,
|
||
|
|
"epoch": 0.18245477533553783,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0004998766740358936,
|
||
|
|
"loss": 6.0002,
|
||
|
|
"mean_token_accuracy": 0.13961011469364165,
|
||
|
|
"num_tokens": 4075828.0,
|
||
|
|
"step": 2345
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.064389991760254,
|
||
|
|
"epoch": 0.1828438047072554,
|
||
|
|
"grad_norm": 1.140625,
|
||
|
|
"learning_rate": 0.0004998757548097582,
|
||
|
|
"loss": 5.9544,
|
||
|
|
"mean_token_accuracy": 0.1372029885649681,
|
||
|
|
"num_tokens": 4083796.0,
|
||
|
|
"step": 2350
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.049620866775513,
|
||
|
|
"epoch": 0.18323283407897295,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004998748321714911,
|
||
|
|
"loss": 6.0694,
|
||
|
|
"mean_token_accuracy": 0.1378914788365364,
|
||
|
|
"num_tokens": 4092981.0,
|
||
|
|
"step": 2355
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.1165852546691895,
|
||
|
|
"epoch": 0.18362186345069054,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.0004998739061211065,
|
||
|
|
"loss": 5.9022,
|
||
|
|
"mean_token_accuracy": 0.13754450157284737,
|
||
|
|
"num_tokens": 4101363.0,
|
||
|
|
"step": 2360
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.994014501571655,
|
||
|
|
"epoch": 0.1840108928224081,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.0004998729766586181,
|
||
|
|
"loss": 5.9818,
|
||
|
|
"mean_token_accuracy": 0.13217142075300217,
|
||
|
|
"num_tokens": 4110164.0,
|
||
|
|
"step": 2365
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.155200433731079,
|
||
|
|
"epoch": 0.18439992219412565,
|
||
|
|
"grad_norm": 1.171875,
|
||
|
|
"learning_rate": 0.0004998720437840403,
|
||
|
|
"loss": 6.0914,
|
||
|
|
"mean_token_accuracy": 0.13508604243397712,
|
||
|
|
"num_tokens": 4119098.0,
|
||
|
|
"step": 2370
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.0071946144104,
|
||
|
|
"epoch": 0.1847889515658432,
|
||
|
|
"grad_norm": 1.234375,
|
||
|
|
"learning_rate": 0.0004998711074973871,
|
||
|
|
"loss": 6.0049,
|
||
|
|
"mean_token_accuracy": 0.13795318752527236,
|
||
|
|
"num_tokens": 4127522.0,
|
||
|
|
"step": 2375
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.070244169235229,
|
||
|
|
"epoch": 0.1851779809375608,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.0004998701677986728,
|
||
|
|
"loss": 6.0077,
|
||
|
|
"mean_token_accuracy": 0.1410178415477276,
|
||
|
|
"num_tokens": 4136311.0,
|
||
|
|
"step": 2380
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.038260412216187,
|
||
|
|
"epoch": 0.18556701030927836,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.0004998692246879116,
|
||
|
|
"loss": 5.9512,
|
||
|
|
"mean_token_accuracy": 0.13766373842954635,
|
||
|
|
"num_tokens": 4145160.0,
|
||
|
|
"step": 2385
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.024521255493164,
|
||
|
|
"epoch": 0.18595603968099592,
|
||
|
|
"grad_norm": 1.140625,
|
||
|
|
"learning_rate": 0.0004998682781651178,
|
||
|
|
"loss": 5.9199,
|
||
|
|
"mean_token_accuracy": 0.1416017644107342,
|
||
|
|
"num_tokens": 4153921.0,
|
||
|
|
"step": 2390
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.976970195770264,
|
||
|
|
"epoch": 0.18634506905271347,
|
||
|
|
"grad_norm": 1.15625,
|
||
|
|
"learning_rate": 0.0004998673282303059,
|
||
|
|
"loss": 6.0103,
|
||
|
|
"mean_token_accuracy": 0.13148440048098564,
|
||
|
|
"num_tokens": 4162580.0,
|
||
|
|
"step": 2395
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.058378648757935,
|
||
|
|
"epoch": 0.18673409842443103,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0004998663748834901,
|
||
|
|
"loss": 5.9925,
|
||
|
|
"mean_token_accuracy": 0.14528287947177887,
|
||
|
|
"num_tokens": 4170623.0,
|
||
|
|
"step": 2400
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.958464670181274,
|
||
|
|
"epoch": 0.18712312779614862,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.0004998654181246851,
|
||
|
|
"loss": 5.9829,
|
||
|
|
"mean_token_accuracy": 0.14436606466770172,
|
||
|
|
"num_tokens": 4178724.0,
|
||
|
|
"step": 2405
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.100484609603882,
|
||
|
|
"epoch": 0.18751215716786618,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 0.0004998644579539052,
|
||
|
|
"loss": 6.0043,
|
||
|
|
"mean_token_accuracy": 0.1338537909090519,
|
||
|
|
"num_tokens": 4187773.0,
|
||
|
|
"step": 2410
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.042976903915405,
|
||
|
|
"epoch": 0.18790118653958374,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.000499863494371165,
|
||
|
|
"loss": 5.9943,
|
||
|
|
"mean_token_accuracy": 0.13325006514787674,
|
||
|
|
"num_tokens": 4196628.0,
|
||
|
|
"step": 2415
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.010223531723023,
|
||
|
|
"epoch": 0.1882902159113013,
|
||
|
|
"grad_norm": 1.1953125,
|
||
|
|
"learning_rate": 0.0004998625273764793,
|
||
|
|
"loss": 6.0131,
|
||
|
|
"mean_token_accuracy": 0.13294664397835732,
|
||
|
|
"num_tokens": 4205090.0,
|
||
|
|
"step": 2420
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.092058897018433,
|
||
|
|
"epoch": 0.18867924528301888,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.0004998615569698626,
|
||
|
|
"loss": 5.9354,
|
||
|
|
"mean_token_accuracy": 0.13965011090040208,
|
||
|
|
"num_tokens": 4212757.0,
|
||
|
|
"step": 2425
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.937941074371338,
|
||
|
|
"epoch": 0.18906827465473644,
|
||
|
|
"grad_norm": 1.15625,
|
||
|
|
"learning_rate": 0.0004998605831513296,
|
||
|
|
"loss": 6.0061,
|
||
|
|
"mean_token_accuracy": 0.13672970831394196,
|
||
|
|
"num_tokens": 4221556.0,
|
||
|
|
"step": 2430
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.04915041923523,
|
||
|
|
"epoch": 0.189457304026454,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.0004998596059208953,
|
||
|
|
"loss": 5.9845,
|
||
|
|
"mean_token_accuracy": 0.1367019921541214,
|
||
|
|
"num_tokens": 4231524.0,
|
||
|
|
"step": 2435
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.068562269210815,
|
||
|
|
"epoch": 0.18984633339817156,
|
||
|
|
"grad_norm": 1.203125,
|
||
|
|
"learning_rate": 0.0004998586252785743,
|
||
|
|
"loss": 6.033,
|
||
|
|
"mean_token_accuracy": 0.13946653604507447,
|
||
|
|
"num_tokens": 4240229.0,
|
||
|
|
"step": 2440
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.0727231979370115,
|
||
|
|
"epoch": 0.19023536276988912,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.0004998576412243816,
|
||
|
|
"loss": 5.8959,
|
||
|
|
"mean_token_accuracy": 0.1430160492658615,
|
||
|
|
"num_tokens": 4248053.0,
|
||
|
|
"step": 2445
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.979983377456665,
|
||
|
|
"epoch": 0.1906243921416067,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.0004998566537583321,
|
||
|
|
"loss": 5.9445,
|
||
|
|
"mean_token_accuracy": 0.13744831085205078,
|
||
|
|
"num_tokens": 4256019.0,
|
||
|
|
"step": 2450
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.966663980484009,
|
||
|
|
"epoch": 0.19101342151332426,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 0.0004998556628804408,
|
||
|
|
"loss": 5.9374,
|
||
|
|
"mean_token_accuracy": 0.14200827106833458,
|
||
|
|
"num_tokens": 4263805.0,
|
||
|
|
"step": 2455
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.009949111938477,
|
||
|
|
"epoch": 0.19140245088504182,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 0.0004998546685907225,
|
||
|
|
"loss": 6.0064,
|
||
|
|
"mean_token_accuracy": 0.13264923617243768,
|
||
|
|
"num_tokens": 4272712.0,
|
||
|
|
"step": 2460
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.149252986907959,
|
||
|
|
"epoch": 0.19179148025675938,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.0004998536708891927,
|
||
|
|
"loss": 5.925,
|
||
|
|
"mean_token_accuracy": 0.13811769112944602,
|
||
|
|
"num_tokens": 4281222.0,
|
||
|
|
"step": 2465
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.9671777248382565,
|
||
|
|
"epoch": 0.19218050962847694,
|
||
|
|
"grad_norm": 1.1796875,
|
||
|
|
"learning_rate": 0.0004998526697758663,
|
||
|
|
"loss": 6.0407,
|
||
|
|
"mean_token_accuracy": 0.13144374191761016,
|
||
|
|
"num_tokens": 4290558.0,
|
||
|
|
"step": 2470
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.1793351650238035,
|
||
|
|
"epoch": 0.19256953900019452,
|
||
|
|
"grad_norm": 1.15625,
|
||
|
|
"learning_rate": 0.0004998516652507585,
|
||
|
|
"loss": 6.0627,
|
||
|
|
"mean_token_accuracy": 0.13413436934351922,
|
||
|
|
"num_tokens": 4299684.0,
|
||
|
|
"step": 2475
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.021236515045166,
|
||
|
|
"epoch": 0.19295856837191208,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 0.0004998506573138846,
|
||
|
|
"loss": 5.9912,
|
||
|
|
"mean_token_accuracy": 0.13706500977277755,
|
||
|
|
"num_tokens": 4308938.0,
|
||
|
|
"step": 2480
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.901808786392212,
|
||
|
|
"epoch": 0.19334759774362964,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.0004998496459652598,
|
||
|
|
"loss": 5.8451,
|
||
|
|
"mean_token_accuracy": 0.14526244178414344,
|
||
|
|
"num_tokens": 4317646.0,
|
||
|
|
"step": 2485
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.038481521606445,
|
||
|
|
"epoch": 0.1937366271153472,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.0004998486312048995,
|
||
|
|
"loss": 6.0126,
|
||
|
|
"mean_token_accuracy": 0.13267346024513244,
|
||
|
|
"num_tokens": 4326876.0,
|
||
|
|
"step": 2490
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.011993885040283,
|
||
|
|
"epoch": 0.19412565648706478,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004998476130328193,
|
||
|
|
"loss": 5.9727,
|
||
|
|
"mean_token_accuracy": 0.13389160186052323,
|
||
|
|
"num_tokens": 4335391.0,
|
||
|
|
"step": 2495
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.093814420700073,
|
||
|
|
"epoch": 0.19451468585878234,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.0004998465914490343,
|
||
|
|
"loss": 5.9477,
|
||
|
|
"mean_token_accuracy": 0.1392389416694641,
|
||
|
|
"num_tokens": 4343253.0,
|
||
|
|
"step": 2500
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.857272100448609,
|
||
|
|
"epoch": 0.1949037152304999,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.00049984556645356,
|
||
|
|
"loss": 5.9121,
|
||
|
|
"mean_token_accuracy": 0.13694104179739952,
|
||
|
|
"num_tokens": 4352161.0,
|
||
|
|
"step": 2505
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.038425636291504,
|
||
|
|
"epoch": 0.19529274460221746,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.0004998445380464124,
|
||
|
|
"loss": 5.8884,
|
||
|
|
"mean_token_accuracy": 0.14439246132969857,
|
||
|
|
"num_tokens": 4360414.0,
|
||
|
|
"step": 2510
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.939995336532593,
|
||
|
|
"epoch": 0.19568177397393502,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.0004998435062276066,
|
||
|
|
"loss": 5.8708,
|
||
|
|
"mean_token_accuracy": 0.14280477836728095,
|
||
|
|
"num_tokens": 4369375.0,
|
||
|
|
"step": 2515
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.956083202362061,
|
||
|
|
"epoch": 0.1960708033456526,
|
||
|
|
"grad_norm": 1.1796875,
|
||
|
|
"learning_rate": 0.0004998424709971586,
|
||
|
|
"loss": 5.8909,
|
||
|
|
"mean_token_accuracy": 0.14073455035686494,
|
||
|
|
"num_tokens": 4378638.0,
|
||
|
|
"step": 2520
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.053691482543945,
|
||
|
|
"epoch": 0.19645983271737016,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.0004998414323550839,
|
||
|
|
"loss": 5.9011,
|
||
|
|
"mean_token_accuracy": 0.14022955894470215,
|
||
|
|
"num_tokens": 4388262.0,
|
||
|
|
"step": 2525
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.941793966293335,
|
||
|
|
"epoch": 0.19684886208908772,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.0004998403903013984,
|
||
|
|
"loss": 5.8905,
|
||
|
|
"mean_token_accuracy": 0.14416835457086563,
|
||
|
|
"num_tokens": 4396894.0,
|
||
|
|
"step": 2530
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.041631984710693,
|
||
|
|
"epoch": 0.19723789146080528,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.0004998393448361179,
|
||
|
|
"loss": 6.0315,
|
||
|
|
"mean_token_accuracy": 0.13690985292196273,
|
||
|
|
"num_tokens": 4405455.0,
|
||
|
|
"step": 2535
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.992990112304687,
|
||
|
|
"epoch": 0.19762692083252287,
|
||
|
|
"grad_norm": 1.2890625,
|
||
|
|
"learning_rate": 0.000499838295959258,
|
||
|
|
"loss": 5.928,
|
||
|
|
"mean_token_accuracy": 0.14115260988473893,
|
||
|
|
"num_tokens": 4414355.0,
|
||
|
|
"step": 2540
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.914900016784668,
|
||
|
|
"epoch": 0.19801595020424043,
|
||
|
|
"grad_norm": 1.1640625,
|
||
|
|
"learning_rate": 0.000499837243670835,
|
||
|
|
"loss": 5.8179,
|
||
|
|
"mean_token_accuracy": 0.1473945528268814,
|
||
|
|
"num_tokens": 4422305.0,
|
||
|
|
"step": 2545
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.036011266708374,
|
||
|
|
"epoch": 0.19840497957595798,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.0004998361879708646,
|
||
|
|
"loss": 5.9657,
|
||
|
|
"mean_token_accuracy": 0.13633855655789376,
|
||
|
|
"num_tokens": 4430813.0,
|
||
|
|
"step": 2550
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.001768779754639,
|
||
|
|
"epoch": 0.19879400894767554,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.000499835128859363,
|
||
|
|
"loss": 5.912,
|
||
|
|
"mean_token_accuracy": 0.1366153724491596,
|
||
|
|
"num_tokens": 4440229.0,
|
||
|
|
"step": 2555
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.897327852249146,
|
||
|
|
"epoch": 0.1991830383193931,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.0004998340663363461,
|
||
|
|
"loss": 5.9416,
|
||
|
|
"mean_token_accuracy": 0.1395571157336235,
|
||
|
|
"num_tokens": 4449417.0,
|
||
|
|
"step": 2560
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.056894111633301,
|
||
|
|
"epoch": 0.1995720676911107,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.0004998330004018301,
|
||
|
|
"loss": 5.9896,
|
||
|
|
"mean_token_accuracy": 0.1364094316959381,
|
||
|
|
"num_tokens": 4457377.0,
|
||
|
|
"step": 2565
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.001095819473266,
|
||
|
|
"epoch": 0.19996109706282825,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.0004998319310558312,
|
||
|
|
"loss": 5.9002,
|
||
|
|
"mean_token_accuracy": 0.13426558971405028,
|
||
|
|
"num_tokens": 4466839.0,
|
||
|
|
"step": 2570
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.00073275566101,
|
||
|
|
"epoch": 0.2003501264345458,
|
||
|
|
"grad_norm": 1.2421875,
|
||
|
|
"learning_rate": 0.0004998308582983657,
|
||
|
|
"loss": 5.939,
|
||
|
|
"mean_token_accuracy": 0.13854092359542847,
|
||
|
|
"num_tokens": 4476369.0,
|
||
|
|
"step": 2575
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.930768013000488,
|
||
|
|
"epoch": 0.20073915580626336,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.0004998297821294497,
|
||
|
|
"loss": 5.9983,
|
||
|
|
"mean_token_accuracy": 0.1397320196032524,
|
||
|
|
"num_tokens": 4485609.0,
|
||
|
|
"step": 2580
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.091860771179199,
|
||
|
|
"epoch": 0.20112818517798095,
|
||
|
|
"grad_norm": 1.171875,
|
||
|
|
"learning_rate": 0.0004998287025490995,
|
||
|
|
"loss": 5.9507,
|
||
|
|
"mean_token_accuracy": 0.13778043463826178,
|
||
|
|
"num_tokens": 4494535.0,
|
||
|
|
"step": 2585
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.033001947402954,
|
||
|
|
"epoch": 0.2015172145496985,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004998276195573317,
|
||
|
|
"loss": 5.9397,
|
||
|
|
"mean_token_accuracy": 0.13595538437366486,
|
||
|
|
"num_tokens": 4503133.0,
|
||
|
|
"step": 2590
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.909776592254639,
|
||
|
|
"epoch": 0.20190624392141607,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.0004998265331541627,
|
||
|
|
"loss": 5.823,
|
||
|
|
"mean_token_accuracy": 0.14806269705295563,
|
||
|
|
"num_tokens": 4511465.0,
|
||
|
|
"step": 2595
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.000340795516967,
|
||
|
|
"epoch": 0.20229527329313363,
|
||
|
|
"grad_norm": 1.171875,
|
||
|
|
"learning_rate": 0.0004998254433396088,
|
||
|
|
"loss": 5.8801,
|
||
|
|
"mean_token_accuracy": 0.14329356104135513,
|
||
|
|
"num_tokens": 4520177.0,
|
||
|
|
"step": 2600
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.028240633010864,
|
||
|
|
"epoch": 0.20268430266485118,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 0.0004998243501136867,
|
||
|
|
"loss": 6.0412,
|
||
|
|
"mean_token_accuracy": 0.14004021510481834,
|
||
|
|
"num_tokens": 4528370.0,
|
||
|
|
"step": 2605
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.139981508255005,
|
||
|
|
"epoch": 0.20307333203656877,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.0004998232534764129,
|
||
|
|
"loss": 6.0734,
|
||
|
|
"mean_token_accuracy": 0.12724738717079162,
|
||
|
|
"num_tokens": 4538258.0,
|
||
|
|
"step": 2610
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.979653692245483,
|
||
|
|
"epoch": 0.20346236140828633,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0004998221534278041,
|
||
|
|
"loss": 5.9563,
|
||
|
|
"mean_token_accuracy": 0.13595332875847815,
|
||
|
|
"num_tokens": 4547300.0,
|
||
|
|
"step": 2615
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.005828428268432,
|
||
|
|
"epoch": 0.2038513907800039,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.0004998210499678769,
|
||
|
|
"loss": 6.0261,
|
||
|
|
"mean_token_accuracy": 0.1293840527534485,
|
||
|
|
"num_tokens": 4556877.0,
|
||
|
|
"step": 2620
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.971534633636475,
|
||
|
|
"epoch": 0.20424042015172145,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.0004998199430966481,
|
||
|
|
"loss": 5.8685,
|
||
|
|
"mean_token_accuracy": 0.14265082031488419,
|
||
|
|
"num_tokens": 4565999.0,
|
||
|
|
"step": 2625
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.986526393890381,
|
||
|
|
"epoch": 0.20462944952343903,
|
||
|
|
"grad_norm": 1.1796875,
|
||
|
|
"learning_rate": 0.0004998188328141346,
|
||
|
|
"loss": 5.9325,
|
||
|
|
"mean_token_accuracy": 0.13216623142361641,
|
||
|
|
"num_tokens": 4574027.0,
|
||
|
|
"step": 2630
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.968379497528076,
|
||
|
|
"epoch": 0.2050184788951566,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.0004998177191203531,
|
||
|
|
"loss": 5.9367,
|
||
|
|
"mean_token_accuracy": 0.12880696952342988,
|
||
|
|
"num_tokens": 4582402.0,
|
||
|
|
"step": 2635
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.008789730072022,
|
||
|
|
"epoch": 0.20540750826687415,
|
||
|
|
"grad_norm": 1.2109375,
|
||
|
|
"learning_rate": 0.0004998166020153204,
|
||
|
|
"loss": 5.8792,
|
||
|
|
"mean_token_accuracy": 0.13846833407878875,
|
||
|
|
"num_tokens": 4590381.0,
|
||
|
|
"step": 2640
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.974490213394165,
|
||
|
|
"epoch": 0.2057965376385917,
|
||
|
|
"grad_norm": 1.1796875,
|
||
|
|
"learning_rate": 0.0004998154814990538,
|
||
|
|
"loss": 5.9537,
|
||
|
|
"mean_token_accuracy": 0.1356106296181679,
|
||
|
|
"num_tokens": 4598910.0,
|
||
|
|
"step": 2645
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.088257789611816,
|
||
|
|
"epoch": 0.20618556701030927,
|
||
|
|
"grad_norm": 1.15625,
|
||
|
|
"learning_rate": 0.00049981435757157,
|
||
|
|
"loss": 6.0635,
|
||
|
|
"mean_token_accuracy": 0.13483888730406762,
|
||
|
|
"num_tokens": 4607400.0,
|
||
|
|
"step": 2650
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.0065418720245365,
|
||
|
|
"epoch": 0.20657459638202685,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004998132302328862,
|
||
|
|
"loss": 5.9841,
|
||
|
|
"mean_token_accuracy": 0.13869831562042237,
|
||
|
|
"num_tokens": 4616510.0,
|
||
|
|
"step": 2655
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.0361473083496096,
|
||
|
|
"epoch": 0.2069636257537444,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.0004998120994830195,
|
||
|
|
"loss": 5.9252,
|
||
|
|
"mean_token_accuracy": 0.13956483379006385,
|
||
|
|
"num_tokens": 4624529.0,
|
||
|
|
"step": 2660
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.988192987442017,
|
||
|
|
"epoch": 0.20735265512546197,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.000499810965321987,
|
||
|
|
"loss": 5.878,
|
||
|
|
"mean_token_accuracy": 0.14122434854507446,
|
||
|
|
"num_tokens": 4632141.0,
|
||
|
|
"step": 2665
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.0770069599151615,
|
||
|
|
"epoch": 0.20774168449717953,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.0004998098277498059,
|
||
|
|
"loss": 6.0879,
|
||
|
|
"mean_token_accuracy": 0.13708560466766356,
|
||
|
|
"num_tokens": 4640378.0,
|
||
|
|
"step": 2670
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.992913913726807,
|
||
|
|
"epoch": 0.2081307138688971,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.0004998086867664934,
|
||
|
|
"loss": 5.8624,
|
||
|
|
"mean_token_accuracy": 0.1408246174454689,
|
||
|
|
"num_tokens": 4649313.0,
|
||
|
|
"step": 2675
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.023945999145508,
|
||
|
|
"epoch": 0.20851974324061467,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 0.000499807542372067,
|
||
|
|
"loss": 5.9354,
|
||
|
|
"mean_token_accuracy": 0.13988457173109053,
|
||
|
|
"num_tokens": 4658272.0,
|
||
|
|
"step": 2680
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.9485689163208,
|
||
|
|
"epoch": 0.20890877261233223,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.0004998063945665439,
|
||
|
|
"loss": 5.8129,
|
||
|
|
"mean_token_accuracy": 0.14626293927431105,
|
||
|
|
"num_tokens": 4665970.0,
|
||
|
|
"step": 2685
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.054908418655396,
|
||
|
|
"epoch": 0.2092978019840498,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.0004998052433499416,
|
||
|
|
"loss": 6.0729,
|
||
|
|
"mean_token_accuracy": 0.13403074070811272,
|
||
|
|
"num_tokens": 4675308.0,
|
||
|
|
"step": 2690
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.953923273086548,
|
||
|
|
"epoch": 0.20968683135576735,
|
||
|
|
"grad_norm": 1.15625,
|
||
|
|
"learning_rate": 0.0004998040887222776,
|
||
|
|
"loss": 5.9252,
|
||
|
|
"mean_token_accuracy": 0.14064669460058213,
|
||
|
|
"num_tokens": 4684316.0,
|
||
|
|
"step": 2695
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.935117626190186,
|
||
|
|
"epoch": 0.21007586072748494,
|
||
|
|
"grad_norm": 1.1640625,
|
||
|
|
"learning_rate": 0.0004998029306835693,
|
||
|
|
"loss": 5.8302,
|
||
|
|
"mean_token_accuracy": 0.14040096402168273,
|
||
|
|
"num_tokens": 4693029.0,
|
||
|
|
"step": 2700
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.969882678985596,
|
||
|
|
"epoch": 0.2104648900992025,
|
||
|
|
"grad_norm": 1.140625,
|
||
|
|
"learning_rate": 0.0004998017692338344,
|
||
|
|
"loss": 6.0223,
|
||
|
|
"mean_token_accuracy": 0.12936139851808548,
|
||
|
|
"num_tokens": 4702404.0,
|
||
|
|
"step": 2705
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.073090076446533,
|
||
|
|
"epoch": 0.21085391947092005,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.0004998006043730905,
|
||
|
|
"loss": 6.0099,
|
||
|
|
"mean_token_accuracy": 0.1324215866625309,
|
||
|
|
"num_tokens": 4711126.0,
|
||
|
|
"step": 2710
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.01806755065918,
|
||
|
|
"epoch": 0.2112429488426376,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.0004997994361013551,
|
||
|
|
"loss": 5.9836,
|
||
|
|
"mean_token_accuracy": 0.14106897115707398,
|
||
|
|
"num_tokens": 4719816.0,
|
||
|
|
"step": 2715
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.064080381393433,
|
||
|
|
"epoch": 0.21163197821435517,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.0004997982644186461,
|
||
|
|
"loss": 5.9379,
|
||
|
|
"mean_token_accuracy": 0.13593154698610305,
|
||
|
|
"num_tokens": 4728294.0,
|
||
|
|
"step": 2720
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.94310736656189,
|
||
|
|
"epoch": 0.21202100758607276,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.0004997970893249813,
|
||
|
|
"loss": 5.854,
|
||
|
|
"mean_token_accuracy": 0.13800680860877038,
|
||
|
|
"num_tokens": 4736708.0,
|
||
|
|
"step": 2725
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.933603143692016,
|
||
|
|
"epoch": 0.21241003695779032,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.0004997959108203785,
|
||
|
|
"loss": 6.0458,
|
||
|
|
"mean_token_accuracy": 0.12775178700685502,
|
||
|
|
"num_tokens": 4744893.0,
|
||
|
|
"step": 2730
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.176341199874878,
|
||
|
|
"epoch": 0.21279906632950787,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 0.0004997947289048554,
|
||
|
|
"loss": 5.999,
|
||
|
|
"mean_token_accuracy": 0.1405559279024601,
|
||
|
|
"num_tokens": 4753246.0,
|
||
|
|
"step": 2735
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.897936725616455,
|
||
|
|
"epoch": 0.21318809570122543,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.0004997935435784302,
|
||
|
|
"loss": 5.9414,
|
||
|
|
"mean_token_accuracy": 0.13054090812802316,
|
||
|
|
"num_tokens": 4762229.0,
|
||
|
|
"step": 2740
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.909042406082153,
|
||
|
|
"epoch": 0.21357712507294302,
|
||
|
|
"grad_norm": 1.140625,
|
||
|
|
"learning_rate": 0.0004997923548411208,
|
||
|
|
"loss": 5.8621,
|
||
|
|
"mean_token_accuracy": 0.142558104544878,
|
||
|
|
"num_tokens": 4771315.0,
|
||
|
|
"step": 2745
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.853223991394043,
|
||
|
|
"epoch": 0.21396615444466058,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 0.000499791162692945,
|
||
|
|
"loss": 5.8006,
|
||
|
|
"mean_token_accuracy": 0.15525677800178528,
|
||
|
|
"num_tokens": 4779848.0,
|
||
|
|
"step": 2750
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.055026388168335,
|
||
|
|
"epoch": 0.21435518381637814,
|
||
|
|
"grad_norm": 1.140625,
|
||
|
|
"learning_rate": 0.0004997899671339214,
|
||
|
|
"loss": 6.0451,
|
||
|
|
"mean_token_accuracy": 0.13737379312515258,
|
||
|
|
"num_tokens": 4788939.0,
|
||
|
|
"step": 2755
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.061662101745606,
|
||
|
|
"epoch": 0.2147442131880957,
|
||
|
|
"grad_norm": 1.140625,
|
||
|
|
"learning_rate": 0.0004997887681640675,
|
||
|
|
"loss": 5.9461,
|
||
|
|
"mean_token_accuracy": 0.13985273018479347,
|
||
|
|
"num_tokens": 4797719.0,
|
||
|
|
"step": 2760
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.999246883392334,
|
||
|
|
"epoch": 0.21513324255981325,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 0.0004997875657834021,
|
||
|
|
"loss": 5.9969,
|
||
|
|
"mean_token_accuracy": 0.13766290992498398,
|
||
|
|
"num_tokens": 4805601.0,
|
||
|
|
"step": 2765
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.081051206588745,
|
||
|
|
"epoch": 0.21552227193153084,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.0004997863599919432,
|
||
|
|
"loss": 5.9449,
|
||
|
|
"mean_token_accuracy": 0.1343104846775532,
|
||
|
|
"num_tokens": 4814993.0,
|
||
|
|
"step": 2770
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.954710197448731,
|
||
|
|
"epoch": 0.2159113013032484,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 0.0004997851507897089,
|
||
|
|
"loss": 5.8984,
|
||
|
|
"mean_token_accuracy": 0.13721237406134607,
|
||
|
|
"num_tokens": 4824156.0,
|
||
|
|
"step": 2775
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.996489238739014,
|
||
|
|
"epoch": 0.21630033067496596,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.0004997839381767178,
|
||
|
|
"loss": 5.9783,
|
||
|
|
"mean_token_accuracy": 0.13451813906431198,
|
||
|
|
"num_tokens": 4833827.0,
|
||
|
|
"step": 2780
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.017173147201538,
|
||
|
|
"epoch": 0.21668936004668352,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.0004997827221529882,
|
||
|
|
"loss": 5.933,
|
||
|
|
"mean_token_accuracy": 0.1363959453999996,
|
||
|
|
"num_tokens": 4842801.0,
|
||
|
|
"step": 2785
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.913520240783692,
|
||
|
|
"epoch": 0.2170783894184011,
|
||
|
|
"grad_norm": 1.2109375,
|
||
|
|
"learning_rate": 0.0004997815027185386,
|
||
|
|
"loss": 5.8,
|
||
|
|
"mean_token_accuracy": 0.14078494608402253,
|
||
|
|
"num_tokens": 4850928.0,
|
||
|
|
"step": 2790
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.954702281951905,
|
||
|
|
"epoch": 0.21746741879011866,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.0004997802798733874,
|
||
|
|
"loss": 5.9126,
|
||
|
|
"mean_token_accuracy": 0.14376682043075562,
|
||
|
|
"num_tokens": 4859510.0,
|
||
|
|
"step": 2795
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.984350776672363,
|
||
|
|
"epoch": 0.21785644816183622,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004997790536175534,
|
||
|
|
"loss": 5.9476,
|
||
|
|
"mean_token_accuracy": 0.142086473852396,
|
||
|
|
"num_tokens": 4868201.0,
|
||
|
|
"step": 2800
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.916833448410034,
|
||
|
|
"epoch": 0.21824547753355378,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.0004997778239510548,
|
||
|
|
"loss": 5.8629,
|
||
|
|
"mean_token_accuracy": 0.14448021799325944,
|
||
|
|
"num_tokens": 4876896.0,
|
||
|
|
"step": 2805
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.956957864761352,
|
||
|
|
"epoch": 0.21863450690527134,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 0.0004997765908739106,
|
||
|
|
"loss": 5.8441,
|
||
|
|
"mean_token_accuracy": 0.1507068805396557,
|
||
|
|
"num_tokens": 4885136.0,
|
||
|
|
"step": 2810
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.890355157852173,
|
||
|
|
"epoch": 0.21902353627698892,
|
||
|
|
"grad_norm": 1.2109375,
|
||
|
|
"learning_rate": 0.0004997753543861395,
|
||
|
|
"loss": 5.8366,
|
||
|
|
"mean_token_accuracy": 0.14202951788902282,
|
||
|
|
"num_tokens": 4893277.0,
|
||
|
|
"step": 2815
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.901514625549316,
|
||
|
|
"epoch": 0.21941256564870648,
|
||
|
|
"grad_norm": 1.140625,
|
||
|
|
"learning_rate": 0.00049977411448776,
|
||
|
|
"loss": 5.9996,
|
||
|
|
"mean_token_accuracy": 0.1315869204699993,
|
||
|
|
"num_tokens": 4901977.0,
|
||
|
|
"step": 2820
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.111964225769043,
|
||
|
|
"epoch": 0.21980159502042404,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 0.0004997728711787912,
|
||
|
|
"loss": 5.9792,
|
||
|
|
"mean_token_accuracy": 0.13206361159682273,
|
||
|
|
"num_tokens": 4910888.0,
|
||
|
|
"step": 2825
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.006693887710571,
|
||
|
|
"epoch": 0.2201906243921416,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.0004997716244592518,
|
||
|
|
"loss": 5.9925,
|
||
|
|
"mean_token_accuracy": 0.13072279542684556,
|
||
|
|
"num_tokens": 4920369.0,
|
||
|
|
"step": 2830
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.057053852081299,
|
||
|
|
"epoch": 0.22057965376385918,
|
||
|
|
"grad_norm": 1.234375,
|
||
|
|
"learning_rate": 0.0004997703743291607,
|
||
|
|
"loss": 5.9848,
|
||
|
|
"mean_token_accuracy": 0.13089529797434807,
|
||
|
|
"num_tokens": 4928799.0,
|
||
|
|
"step": 2835
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.970766544342041,
|
||
|
|
"epoch": 0.22096868313557674,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.000499769120788537,
|
||
|
|
"loss": 5.8758,
|
||
|
|
"mean_token_accuracy": 0.1434700906276703,
|
||
|
|
"num_tokens": 4937194.0,
|
||
|
|
"step": 2840
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.957070255279541,
|
||
|
|
"epoch": 0.2213577125072943,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.0004997678638373995,
|
||
|
|
"loss": 5.9522,
|
||
|
|
"mean_token_accuracy": 0.13605077415704728,
|
||
|
|
"num_tokens": 4946174.0,
|
||
|
|
"step": 2845
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.955007648468017,
|
||
|
|
"epoch": 0.22174674187901186,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.0004997666034757676,
|
||
|
|
"loss": 5.9156,
|
||
|
|
"mean_token_accuracy": 0.12960682660341263,
|
||
|
|
"num_tokens": 4955376.0,
|
||
|
|
"step": 2850
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.967183685302734,
|
||
|
|
"epoch": 0.22213577125072942,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004997653397036603,
|
||
|
|
"loss": 5.8994,
|
||
|
|
"mean_token_accuracy": 0.1478715233504772,
|
||
|
|
"num_tokens": 4964138.0,
|
||
|
|
"step": 2855
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.938944244384766,
|
||
|
|
"epoch": 0.222524800622447,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.0004997640725210965,
|
||
|
|
"loss": 6.0018,
|
||
|
|
"mean_token_accuracy": 0.1362317405641079,
|
||
|
|
"num_tokens": 4973868.0,
|
||
|
|
"step": 2860
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.965620470046997,
|
||
|
|
"epoch": 0.22291382999416456,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.0004997628019280958,
|
||
|
|
"loss": 5.8569,
|
||
|
|
"mean_token_accuracy": 0.14108419343829154,
|
||
|
|
"num_tokens": 4982687.0,
|
||
|
|
"step": 2865
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.985421180725098,
|
||
|
|
"epoch": 0.22330285936588212,
|
||
|
|
"grad_norm": 1.140625,
|
||
|
|
"learning_rate": 0.0004997615279246773,
|
||
|
|
"loss": 5.9236,
|
||
|
|
"mean_token_accuracy": 0.13613910377025604,
|
||
|
|
"num_tokens": 4992072.0,
|
||
|
|
"step": 2870
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.967291831970215,
|
||
|
|
"epoch": 0.22369188873759968,
|
||
|
|
"grad_norm": 1.140625,
|
||
|
|
"learning_rate": 0.0004997602505108603,
|
||
|
|
"loss": 5.8763,
|
||
|
|
"mean_token_accuracy": 0.13791223987936974,
|
||
|
|
"num_tokens": 5000551.0,
|
||
|
|
"step": 2875
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.991910934448242,
|
||
|
|
"epoch": 0.22408091810931724,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.0004997589696866644,
|
||
|
|
"loss": 6.029,
|
||
|
|
"mean_token_accuracy": 0.13684648349881173,
|
||
|
|
"num_tokens": 5009292.0,
|
||
|
|
"step": 2880
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.043682527542114,
|
||
|
|
"epoch": 0.22446994748103483,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.0004997576854521088,
|
||
|
|
"loss": 5.8801,
|
||
|
|
"mean_token_accuracy": 0.1401052340865135,
|
||
|
|
"num_tokens": 5018407.0,
|
||
|
|
"step": 2885
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.913548946380615,
|
||
|
|
"epoch": 0.22485897685275238,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.000499756397807213,
|
||
|
|
"loss": 5.9256,
|
||
|
|
"mean_token_accuracy": 0.13805932700634002,
|
||
|
|
"num_tokens": 5027353.0,
|
||
|
|
"step": 2890
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.067233896255493,
|
||
|
|
"epoch": 0.22524800622446994,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.0004997551067519966,
|
||
|
|
"loss": 5.9562,
|
||
|
|
"mean_token_accuracy": 0.1377393364906311,
|
||
|
|
"num_tokens": 5036476.0,
|
||
|
|
"step": 2895
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.9502188205719,
|
||
|
|
"epoch": 0.2256370355961875,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.0004997538122864792,
|
||
|
|
"loss": 5.8845,
|
||
|
|
"mean_token_accuracy": 0.139453986287117,
|
||
|
|
"num_tokens": 5045132.0,
|
||
|
|
"step": 2900
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.971363878250122,
|
||
|
|
"epoch": 0.2260260649679051,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.0004997525144106804,
|
||
|
|
"loss": 5.9125,
|
||
|
|
"mean_token_accuracy": 0.13996420204639434,
|
||
|
|
"num_tokens": 5053665.0,
|
||
|
|
"step": 2905
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.960469675064087,
|
||
|
|
"epoch": 0.22641509433962265,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.00049975121312462,
|
||
|
|
"loss": 5.862,
|
||
|
|
"mean_token_accuracy": 0.14218528047204018,
|
||
|
|
"num_tokens": 5062516.0,
|
||
|
|
"step": 2910
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.987781763076782,
|
||
|
|
"epoch": 0.2268041237113402,
|
||
|
|
"grad_norm": 1.171875,
|
||
|
|
"learning_rate": 0.0004997499084283177,
|
||
|
|
"loss": 5.9022,
|
||
|
|
"mean_token_accuracy": 0.13738748133182527,
|
||
|
|
"num_tokens": 5071260.0,
|
||
|
|
"step": 2915
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.856913328170776,
|
||
|
|
"epoch": 0.22719315308305776,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.0004997486003217932,
|
||
|
|
"loss": 5.8443,
|
||
|
|
"mean_token_accuracy": 0.14911826103925704,
|
||
|
|
"num_tokens": 5079215.0,
|
||
|
|
"step": 2920
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.894352054595947,
|
||
|
|
"epoch": 0.22758218245477532,
|
||
|
|
"grad_norm": 1.1875,
|
||
|
|
"learning_rate": 0.0004997472888050664,
|
||
|
|
"loss": 5.9278,
|
||
|
|
"mean_token_accuracy": 0.13858695551753045,
|
||
|
|
"num_tokens": 5088404.0,
|
||
|
|
"step": 2925
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.946014642715454,
|
||
|
|
"epoch": 0.2279712118264929,
|
||
|
|
"grad_norm": 1.2265625,
|
||
|
|
"learning_rate": 0.0004997459738781573,
|
||
|
|
"loss": 5.85,
|
||
|
|
"mean_token_accuracy": 0.14364279732108115,
|
||
|
|
"num_tokens": 5096756.0,
|
||
|
|
"step": 2930
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.026473569869995,
|
||
|
|
"epoch": 0.22836024119821047,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0004997446555410857,
|
||
|
|
"loss": 6.0139,
|
||
|
|
"mean_token_accuracy": 0.1368228353559971,
|
||
|
|
"num_tokens": 5106160.0,
|
||
|
|
"step": 2935
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.9237579822540285,
|
||
|
|
"epoch": 0.22874927056992803,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.0004997433337938716,
|
||
|
|
"loss": 5.9492,
|
||
|
|
"mean_token_accuracy": 0.14053435251116753,
|
||
|
|
"num_tokens": 5114915.0,
|
||
|
|
"step": 2940
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.031959056854248,
|
||
|
|
"epoch": 0.22913829994164558,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.0004997420086365351,
|
||
|
|
"loss": 5.8661,
|
||
|
|
"mean_token_accuracy": 0.13943756744265556,
|
||
|
|
"num_tokens": 5123249.0,
|
||
|
|
"step": 2945
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.872917175292969,
|
||
|
|
"epoch": 0.22952732931336317,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0004997406800690966,
|
||
|
|
"loss": 5.8562,
|
||
|
|
"mean_token_accuracy": 0.13768355622887612,
|
||
|
|
"num_tokens": 5131906.0,
|
||
|
|
"step": 2950
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.946727228164673,
|
||
|
|
"epoch": 0.22991635868508073,
|
||
|
|
"grad_norm": 1.140625,
|
||
|
|
"learning_rate": 0.0004997393480915758,
|
||
|
|
"loss": 5.8604,
|
||
|
|
"mean_token_accuracy": 0.14464073702692987,
|
||
|
|
"num_tokens": 5140740.0,
|
||
|
|
"step": 2955
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.008235311508178,
|
||
|
|
"epoch": 0.2303053880567983,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.0004997380127039931,
|
||
|
|
"loss": 6.0233,
|
||
|
|
"mean_token_accuracy": 0.1408081255853176,
|
||
|
|
"num_tokens": 5149748.0,
|
||
|
|
"step": 2960
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.929762601852417,
|
||
|
|
"epoch": 0.23069441742851585,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.0004997366739063688,
|
||
|
|
"loss": 5.7618,
|
||
|
|
"mean_token_accuracy": 0.1476716160774231,
|
||
|
|
"num_tokens": 5158475.0,
|
||
|
|
"step": 2965
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.9083868026733395,
|
||
|
|
"epoch": 0.2310834468002334,
|
||
|
|
"grad_norm": 1.1796875,
|
||
|
|
"learning_rate": 0.0004997353316987231,
|
||
|
|
"loss": 5.9642,
|
||
|
|
"mean_token_accuracy": 0.13468277528882028,
|
||
|
|
"num_tokens": 5166593.0,
|
||
|
|
"step": 2970
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.0169929504394535,
|
||
|
|
"epoch": 0.231472476171951,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.0004997339860810765,
|
||
|
|
"loss": 5.9261,
|
||
|
|
"mean_token_accuracy": 0.13820526376366615,
|
||
|
|
"num_tokens": 5175557.0,
|
||
|
|
"step": 2975
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.977094888687134,
|
||
|
|
"epoch": 0.23186150554366855,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.0004997326370534495,
|
||
|
|
"loss": 5.823,
|
||
|
|
"mean_token_accuracy": 0.14529850631952285,
|
||
|
|
"num_tokens": 5184140.0,
|
||
|
|
"step": 2980
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.931415271759033,
|
||
|
|
"epoch": 0.2322505349153861,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.0004997312846158622,
|
||
|
|
"loss": 5.9268,
|
||
|
|
"mean_token_accuracy": 0.1361088216304779,
|
||
|
|
"num_tokens": 5192347.0,
|
||
|
|
"step": 2985
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.982898855209351,
|
||
|
|
"epoch": 0.23263956428710367,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.0004997299287683355,
|
||
|
|
"loss": 5.8816,
|
||
|
|
"mean_token_accuracy": 0.14375673681497575,
|
||
|
|
"num_tokens": 5201327.0,
|
||
|
|
"step": 2990
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.978207778930664,
|
||
|
|
"epoch": 0.23302859365882125,
|
||
|
|
"grad_norm": 1.171875,
|
||
|
|
"learning_rate": 0.0004997285695108898,
|
||
|
|
"loss": 5.9732,
|
||
|
|
"mean_token_accuracy": 0.14029283672571183,
|
||
|
|
"num_tokens": 5209873.0,
|
||
|
|
"step": 2995
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.967278957366943,
|
||
|
|
"epoch": 0.2334176230305388,
|
||
|
|
"grad_norm": 1.171875,
|
||
|
|
"learning_rate": 0.0004997272068435458,
|
||
|
|
"loss": 5.8719,
|
||
|
|
"mean_token_accuracy": 0.14271339401602745,
|
||
|
|
"num_tokens": 5219176.0,
|
||
|
|
"step": 3000
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.2334176230305388,
|
||
|
|
"eval_entropy": 5.769374112467908,
|
||
|
|
"eval_loss": 5.937982082366943,
|
||
|
|
"eval_mean_token_accuracy": 0.1473742507426812,
|
||
|
|
"eval_num_tokens": 5219176.0,
|
||
|
|
"eval_runtime": 28.5735,
|
||
|
|
"eval_samples_per_second": 1454.427,
|
||
|
|
"eval_steps_per_second": 181.812,
|
||
|
|
"step": 3000
|
||
|
|
}
|
||
|
|
],
|
||
|
|
"logging_steps": 5,
|
||
|
|
"max_steps": 128520,
|
||
|
|
"num_input_tokens_seen": 0,
|
||
|
|
"num_train_epochs": 10,
|
||
|
|
"save_steps": 3000,
|
||
|
|
"stateful_callbacks": {
|
||
|
|
"TrainerControl": {
|
||
|
|
"args": {
|
||
|
|
"should_epoch_stop": false,
|
||
|
|
"should_evaluate": false,
|
||
|
|
"should_log": false,
|
||
|
|
"should_save": true,
|
||
|
|
"should_training_stop": false
|
||
|
|
},
|
||
|
|
"attributes": {}
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"total_flos": 7097826576384000.0,
|
||
|
|
"train_batch_size": 16,
|
||
|
|
"trial_name": null,
|
||
|
|
"trial_params": null
|
||
|
|
}
|