6046 lines
164 KiB
JSON
6046 lines
164 KiB
JSON
|
{
|
||
|
|
"best_global_step": null,
|
||
|
|
"best_metric": null,
|
||
|
|
"best_model_checkpoint": null,
|
||
|
|
"epoch": 0.2334176230305388,
|
||
|
|
"eval_steps": 3000,
|
||
|
|
"global_step": 3000,
|
||
|
|
"is_hyper_param_search": false,
|
||
|
|
"is_local_process_zero": true,
|
||
|
|
"is_world_process_zero": true,
|
||
|
|
"log_history": [
|
||
|
|
{
|
||
|
|
"entropy": 10.742576789855956,
|
||
|
|
"epoch": 0.00038902937171756465,
|
||
|
|
"grad_norm": 5.21875,
|
||
|
|
"learning_rate": 2e-06,
|
||
|
|
"loss": 10.7444,
|
||
|
|
"mean_token_accuracy": 0.0,
|
||
|
|
"num_tokens": 8755.0,
|
||
|
|
"step": 5
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.742605495452882,
|
||
|
|
"epoch": 0.0007780587434351293,
|
||
|
|
"grad_norm": 5.375,
|
||
|
|
"learning_rate": 4.5e-06,
|
||
|
|
"loss": 10.7346,
|
||
|
|
"mean_token_accuracy": 0.0,
|
||
|
|
"num_tokens": 17641.0,
|
||
|
|
"step": 10
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.742611026763916,
|
||
|
|
"epoch": 0.001167088115152694,
|
||
|
|
"grad_norm": 5.46875,
|
||
|
|
"learning_rate": 7e-06,
|
||
|
|
"loss": 10.6932,
|
||
|
|
"mean_token_accuracy": 0.0,
|
||
|
|
"num_tokens": 26293.0,
|
||
|
|
"step": 15
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.742596912384034,
|
||
|
|
"epoch": 0.0015561174868702586,
|
||
|
|
"grad_norm": 5.03125,
|
||
|
|
"learning_rate": 9.5e-06,
|
||
|
|
"loss": 10.6732,
|
||
|
|
"mean_token_accuracy": 0.0003551477799192071,
|
||
|
|
"num_tokens": 35627.0,
|
||
|
|
"step": 20
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.742521381378173,
|
||
|
|
"epoch": 0.0019451468585878235,
|
||
|
|
"grad_norm": 4.71875,
|
||
|
|
"learning_rate": 1.2e-05,
|
||
|
|
"loss": 10.5441,
|
||
|
|
"mean_token_accuracy": 0.009159033582545818,
|
||
|
|
"num_tokens": 43861.0,
|
||
|
|
"step": 25
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.742165279388427,
|
||
|
|
"epoch": 0.002334176230305388,
|
||
|
|
"grad_norm": 4.1875,
|
||
|
|
"learning_rate": 1.4500000000000002e-05,
|
||
|
|
"loss": 10.4398,
|
||
|
|
"mean_token_accuracy": 0.03247077781707049,
|
||
|
|
"num_tokens": 52816.0,
|
||
|
|
"step": 30
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.740872764587403,
|
||
|
|
"epoch": 0.0027232056020229526,
|
||
|
|
"grad_norm": 3.375,
|
||
|
|
"learning_rate": 1.7000000000000003e-05,
|
||
|
|
"loss": 10.3142,
|
||
|
|
"mean_token_accuracy": 0.03825325649231672,
|
||
|
|
"num_tokens": 61370.0,
|
||
|
|
"step": 35
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.737211132049561,
|
||
|
|
"epoch": 0.0031122349737405172,
|
||
|
|
"grad_norm": 2.765625,
|
||
|
|
"learning_rate": 1.95e-05,
|
||
|
|
"loss": 10.1536,
|
||
|
|
"mean_token_accuracy": 0.044245490059256556,
|
||
|
|
"num_tokens": 69444.0,
|
||
|
|
"step": 40
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.730943870544433,
|
||
|
|
"epoch": 0.003501264345458082,
|
||
|
|
"grad_norm": 2.40625,
|
||
|
|
"learning_rate": 2.2e-05,
|
||
|
|
"loss": 10.0549,
|
||
|
|
"mean_token_accuracy": 0.044146507233381274,
|
||
|
|
"num_tokens": 77892.0,
|
||
|
|
"step": 45
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.725597763061524,
|
||
|
|
"epoch": 0.003890293717175647,
|
||
|
|
"grad_norm": 2.078125,
|
||
|
|
"learning_rate": 2.4500000000000003e-05,
|
||
|
|
"loss": 9.9865,
|
||
|
|
"mean_token_accuracy": 0.04212083183228969,
|
||
|
|
"num_tokens": 86154.0,
|
||
|
|
"step": 50
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.72157793045044,
|
||
|
|
"epoch": 0.004279323088893211,
|
||
|
|
"grad_norm": 2.0625,
|
||
|
|
"learning_rate": 2.7e-05,
|
||
|
|
"loss": 9.9514,
|
||
|
|
"mean_token_accuracy": 0.04536668732762337,
|
||
|
|
"num_tokens": 95589.0,
|
||
|
|
"step": 55
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.716520404815673,
|
||
|
|
"epoch": 0.004668352460610776,
|
||
|
|
"grad_norm": 1.984375,
|
||
|
|
"learning_rate": 2.95e-05,
|
||
|
|
"loss": 9.898,
|
||
|
|
"mean_token_accuracy": 0.04543796852231026,
|
||
|
|
"num_tokens": 105268.0,
|
||
|
|
"step": 60
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.711576366424561,
|
||
|
|
"epoch": 0.0050573818323283405,
|
||
|
|
"grad_norm": 1.890625,
|
||
|
|
"learning_rate": 3.2e-05,
|
||
|
|
"loss": 9.7831,
|
||
|
|
"mean_token_accuracy": 0.04743263386189937,
|
||
|
|
"num_tokens": 113347.0,
|
||
|
|
"step": 65
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.705528163909912,
|
||
|
|
"epoch": 0.005446411204045905,
|
||
|
|
"grad_norm": 1.9609375,
|
||
|
|
"learning_rate": 3.4500000000000005e-05,
|
||
|
|
"loss": 9.7233,
|
||
|
|
"mean_token_accuracy": 0.04614104889333248,
|
||
|
|
"num_tokens": 121235.0,
|
||
|
|
"step": 70
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.699932765960693,
|
||
|
|
"epoch": 0.00583544057576347,
|
||
|
|
"grad_norm": 1.828125,
|
||
|
|
"learning_rate": 3.7e-05,
|
||
|
|
"loss": 9.674,
|
||
|
|
"mean_token_accuracy": 0.045549771189689635,
|
||
|
|
"num_tokens": 129529.0,
|
||
|
|
"step": 75
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.695240116119384,
|
||
|
|
"epoch": 0.0062244699474810344,
|
||
|
|
"grad_norm": 1.84375,
|
||
|
|
"learning_rate": 3.95e-05,
|
||
|
|
"loss": 9.6104,
|
||
|
|
"mean_token_accuracy": 0.046765000373125074,
|
||
|
|
"num_tokens": 137918.0,
|
||
|
|
"step": 80
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.686996364593506,
|
||
|
|
"epoch": 0.006613499319198599,
|
||
|
|
"grad_norm": 1.921875,
|
||
|
|
"learning_rate": 4.2000000000000004e-05,
|
||
|
|
"loss": 9.5017,
|
||
|
|
"mean_token_accuracy": 0.05623045340180397,
|
||
|
|
"num_tokens": 146445.0,
|
||
|
|
"step": 85
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.671263790130615,
|
||
|
|
"epoch": 0.007002528690916164,
|
||
|
|
"grad_norm": 1.84375,
|
||
|
|
"learning_rate": 4.45e-05,
|
||
|
|
"loss": 9.4967,
|
||
|
|
"mean_token_accuracy": 0.057636797428131104,
|
||
|
|
"num_tokens": 155904.0,
|
||
|
|
"step": 90
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.655223369598389,
|
||
|
|
"epoch": 0.007391558062633729,
|
||
|
|
"grad_norm": 1.8125,
|
||
|
|
"learning_rate": 4.7000000000000004e-05,
|
||
|
|
"loss": 9.4006,
|
||
|
|
"mean_token_accuracy": 0.05863568969070911,
|
||
|
|
"num_tokens": 164436.0,
|
||
|
|
"step": 95
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.634439468383789,
|
||
|
|
"epoch": 0.007780587434351294,
|
||
|
|
"grad_norm": 1.7421875,
|
||
|
|
"learning_rate": 4.9500000000000004e-05,
|
||
|
|
"loss": 9.3022,
|
||
|
|
"mean_token_accuracy": 0.06445249132812023,
|
||
|
|
"num_tokens": 172985.0,
|
||
|
|
"step": 100
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.591667461395264,
|
||
|
|
"epoch": 0.008169616806068859,
|
||
|
|
"grad_norm": 1.6953125,
|
||
|
|
"learning_rate": 5.2e-05,
|
||
|
|
"loss": 9.1936,
|
||
|
|
"mean_token_accuracy": 0.06430471092462539,
|
||
|
|
"num_tokens": 182084.0,
|
||
|
|
"step": 105
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.53823823928833,
|
||
|
|
"epoch": 0.008558646177786422,
|
||
|
|
"grad_norm": 1.640625,
|
||
|
|
"learning_rate": 5.45e-05,
|
||
|
|
"loss": 9.0792,
|
||
|
|
"mean_token_accuracy": 0.0625245351344347,
|
||
|
|
"num_tokens": 190742.0,
|
||
|
|
"step": 110
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.481583213806152,
|
||
|
|
"epoch": 0.008947675549503988,
|
||
|
|
"grad_norm": 1.7109375,
|
||
|
|
"learning_rate": 5.7e-05,
|
||
|
|
"loss": 8.9948,
|
||
|
|
"mean_token_accuracy": 0.06432581804692745,
|
||
|
|
"num_tokens": 199600.0,
|
||
|
|
"step": 115
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.431952953338623,
|
||
|
|
"epoch": 0.009336704921221552,
|
||
|
|
"grad_norm": 1.671875,
|
||
|
|
"learning_rate": 5.9499999999999996e-05,
|
||
|
|
"loss": 8.8995,
|
||
|
|
"mean_token_accuracy": 0.06441468745470047,
|
||
|
|
"num_tokens": 207883.0,
|
||
|
|
"step": 120
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.365525436401366,
|
||
|
|
"epoch": 0.009725734292939117,
|
||
|
|
"grad_norm": 1.5,
|
||
|
|
"learning_rate": 6.2e-05,
|
||
|
|
"loss": 8.8018,
|
||
|
|
"mean_token_accuracy": 0.06325564533472061,
|
||
|
|
"num_tokens": 216216.0,
|
||
|
|
"step": 125
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.309541988372803,
|
||
|
|
"epoch": 0.010114763664656681,
|
||
|
|
"grad_norm": 1.46875,
|
||
|
|
"learning_rate": 6.450000000000001e-05,
|
||
|
|
"loss": 8.6768,
|
||
|
|
"mean_token_accuracy": 0.06168311797082424,
|
||
|
|
"num_tokens": 225250.0,
|
||
|
|
"step": 130
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.241107082366943,
|
||
|
|
"epoch": 0.010503793036374246,
|
||
|
|
"grad_norm": 1.3515625,
|
||
|
|
"learning_rate": 6.7e-05,
|
||
|
|
"loss": 8.5623,
|
||
|
|
"mean_token_accuracy": 0.059869692847132686,
|
||
|
|
"num_tokens": 233748.0,
|
||
|
|
"step": 135
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.114632701873779,
|
||
|
|
"epoch": 0.01089282240809181,
|
||
|
|
"grad_norm": 1.2265625,
|
||
|
|
"learning_rate": 6.950000000000001e-05,
|
||
|
|
"loss": 8.4505,
|
||
|
|
"mean_token_accuracy": 0.06234452910721302,
|
||
|
|
"num_tokens": 242629.0,
|
||
|
|
"step": 140
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.001305103302002,
|
||
|
|
"epoch": 0.011281851779809376,
|
||
|
|
"grad_norm": 1.46875,
|
||
|
|
"learning_rate": 7.2e-05,
|
||
|
|
"loss": 8.3258,
|
||
|
|
"mean_token_accuracy": 0.05941925346851349,
|
||
|
|
"num_tokens": 251458.0,
|
||
|
|
"step": 145
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 9.833595371246338,
|
||
|
|
"epoch": 0.01167088115152694,
|
||
|
|
"grad_norm": 1.203125,
|
||
|
|
"learning_rate": 7.45e-05,
|
||
|
|
"loss": 8.2078,
|
||
|
|
"mean_token_accuracy": 0.06866976507008075,
|
||
|
|
"num_tokens": 260557.0,
|
||
|
|
"step": 150
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 9.655412101745606,
|
||
|
|
"epoch": 0.012059910523244505,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 7.7e-05,
|
||
|
|
"loss": 8.1497,
|
||
|
|
"mean_token_accuracy": 0.06398723609745502,
|
||
|
|
"num_tokens": 269262.0,
|
||
|
|
"step": 155
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 9.519824028015137,
|
||
|
|
"epoch": 0.012448939894962069,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 7.950000000000001e-05,
|
||
|
|
"loss": 8.0264,
|
||
|
|
"mean_token_accuracy": 0.06563923060894013,
|
||
|
|
"num_tokens": 277804.0,
|
||
|
|
"step": 160
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 9.293780612945557,
|
||
|
|
"epoch": 0.012837969266679634,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 8.2e-05,
|
||
|
|
"loss": 7.9388,
|
||
|
|
"mean_token_accuracy": 0.0646277904510498,
|
||
|
|
"num_tokens": 287450.0,
|
||
|
|
"step": 165
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 9.156445980072021,
|
||
|
|
"epoch": 0.013226998638397198,
|
||
|
|
"grad_norm": 0.96875,
|
||
|
|
"learning_rate": 8.450000000000001e-05,
|
||
|
|
"loss": 7.9051,
|
||
|
|
"mean_token_accuracy": 0.06273124553263187,
|
||
|
|
"num_tokens": 296497.0,
|
||
|
|
"step": 170
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.887872219085693,
|
||
|
|
"epoch": 0.013616028010114764,
|
||
|
|
"grad_norm": 0.93359375,
|
||
|
|
"learning_rate": 8.7e-05,
|
||
|
|
"loss": 7.7677,
|
||
|
|
"mean_token_accuracy": 0.06659091413021087,
|
||
|
|
"num_tokens": 305414.0,
|
||
|
|
"step": 175
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.771506786346436,
|
||
|
|
"epoch": 0.014005057381832327,
|
||
|
|
"grad_norm": 0.78125,
|
||
|
|
"learning_rate": 8.95e-05,
|
||
|
|
"loss": 7.7563,
|
||
|
|
"mean_token_accuracy": 0.06347964778542518,
|
||
|
|
"num_tokens": 313639.0,
|
||
|
|
"step": 180
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.585464668273925,
|
||
|
|
"epoch": 0.014394086753549893,
|
||
|
|
"grad_norm": 0.8125,
|
||
|
|
"learning_rate": 9.2e-05,
|
||
|
|
"loss": 7.7352,
|
||
|
|
"mean_token_accuracy": 0.06393053829669952,
|
||
|
|
"num_tokens": 322855.0,
|
||
|
|
"step": 185
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.50670690536499,
|
||
|
|
"epoch": 0.014783116125267459,
|
||
|
|
"grad_norm": 0.85546875,
|
||
|
|
"learning_rate": 9.45e-05,
|
||
|
|
"loss": 7.8169,
|
||
|
|
"mean_token_accuracy": 0.06778145208954811,
|
||
|
|
"num_tokens": 332071.0,
|
||
|
|
"step": 190
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.431924152374268,
|
||
|
|
"epoch": 0.015172145496985022,
|
||
|
|
"grad_norm": 0.8984375,
|
||
|
|
"learning_rate": 9.7e-05,
|
||
|
|
"loss": 7.6122,
|
||
|
|
"mean_token_accuracy": 0.07193873748183251,
|
||
|
|
"num_tokens": 339990.0,
|
||
|
|
"step": 195
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.313230800628663,
|
||
|
|
"epoch": 0.015561174868702588,
|
||
|
|
"grad_norm": 0.8515625,
|
||
|
|
"learning_rate": 9.95e-05,
|
||
|
|
"loss": 7.6533,
|
||
|
|
"mean_token_accuracy": 0.06932461187243462,
|
||
|
|
"num_tokens": 348581.0,
|
||
|
|
"step": 200
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.288263511657714,
|
||
|
|
"epoch": 0.01595020424042015,
|
||
|
|
"grad_norm": 0.91015625,
|
||
|
|
"learning_rate": 0.000102,
|
||
|
|
"loss": 7.6415,
|
||
|
|
"mean_token_accuracy": 0.07069163881242276,
|
||
|
|
"num_tokens": 357032.0,
|
||
|
|
"step": 205
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.254517364501954,
|
||
|
|
"epoch": 0.016339233612137717,
|
||
|
|
"grad_norm": 0.84765625,
|
||
|
|
"learning_rate": 0.00010449999999999999,
|
||
|
|
"loss": 7.607,
|
||
|
|
"mean_token_accuracy": 0.06844000443816185,
|
||
|
|
"num_tokens": 366562.0,
|
||
|
|
"step": 210
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.228306484222411,
|
||
|
|
"epoch": 0.016728262983855283,
|
||
|
|
"grad_norm": 0.98828125,
|
||
|
|
"learning_rate": 0.000107,
|
||
|
|
"loss": 7.5965,
|
||
|
|
"mean_token_accuracy": 0.07050794810056686,
|
||
|
|
"num_tokens": 374555.0,
|
||
|
|
"step": 215
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.206252288818359,
|
||
|
|
"epoch": 0.017117292355572845,
|
||
|
|
"grad_norm": 1.203125,
|
||
|
|
"learning_rate": 0.0001095,
|
||
|
|
"loss": 7.6274,
|
||
|
|
"mean_token_accuracy": 0.06776856631040573,
|
||
|
|
"num_tokens": 383583.0,
|
||
|
|
"step": 220
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.121715068817139,
|
||
|
|
"epoch": 0.01750632172729041,
|
||
|
|
"grad_norm": 0.78125,
|
||
|
|
"learning_rate": 0.000112,
|
||
|
|
"loss": 7.6405,
|
||
|
|
"mean_token_accuracy": 0.06792488619685173,
|
||
|
|
"num_tokens": 392932.0,
|
||
|
|
"step": 225
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.169992160797118,
|
||
|
|
"epoch": 0.017895351099007976,
|
||
|
|
"grad_norm": 0.89453125,
|
||
|
|
"learning_rate": 0.0001145,
|
||
|
|
"loss": 7.4836,
|
||
|
|
"mean_token_accuracy": 0.07281714007258415,
|
||
|
|
"num_tokens": 401653.0,
|
||
|
|
"step": 230
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.105243301391601,
|
||
|
|
"epoch": 0.01828438047072554,
|
||
|
|
"grad_norm": 0.87890625,
|
||
|
|
"learning_rate": 0.00011700000000000001,
|
||
|
|
"loss": 7.5741,
|
||
|
|
"mean_token_accuracy": 0.07232600301504136,
|
||
|
|
"num_tokens": 410432.0,
|
||
|
|
"step": 235
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.124885082244873,
|
||
|
|
"epoch": 0.018673409842443103,
|
||
|
|
"grad_norm": 0.83203125,
|
||
|
|
"learning_rate": 0.00011949999999999999,
|
||
|
|
"loss": 7.5359,
|
||
|
|
"mean_token_accuracy": 0.07120791971683502,
|
||
|
|
"num_tokens": 419380.0,
|
||
|
|
"step": 240
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.092760372161866,
|
||
|
|
"epoch": 0.01906243921416067,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.000122,
|
||
|
|
"loss": 7.4537,
|
||
|
|
"mean_token_accuracy": 0.07131325155496597,
|
||
|
|
"num_tokens": 427682.0,
|
||
|
|
"step": 245
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.064310121536256,
|
||
|
|
"epoch": 0.019451468585878234,
|
||
|
|
"grad_norm": 0.9140625,
|
||
|
|
"learning_rate": 0.0001245,
|
||
|
|
"loss": 7.5297,
|
||
|
|
"mean_token_accuracy": 0.06986031346023083,
|
||
|
|
"num_tokens": 437708.0,
|
||
|
|
"step": 250
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.066622257232666,
|
||
|
|
"epoch": 0.0198404979575958,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.000127,
|
||
|
|
"loss": 7.49,
|
||
|
|
"mean_token_accuracy": 0.07588860243558884,
|
||
|
|
"num_tokens": 446480.0,
|
||
|
|
"step": 255
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.031266736984254,
|
||
|
|
"epoch": 0.020229527329313362,
|
||
|
|
"grad_norm": 0.953125,
|
||
|
|
"learning_rate": 0.0001295,
|
||
|
|
"loss": 7.524,
|
||
|
|
"mean_token_accuracy": 0.06815474294126034,
|
||
|
|
"num_tokens": 455273.0,
|
||
|
|
"step": 260
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.06600604057312,
|
||
|
|
"epoch": 0.020618556701030927,
|
||
|
|
"grad_norm": 1.1953125,
|
||
|
|
"learning_rate": 0.000132,
|
||
|
|
"loss": 7.4511,
|
||
|
|
"mean_token_accuracy": 0.07497221603989601,
|
||
|
|
"num_tokens": 464306.0,
|
||
|
|
"step": 265
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.944579219818115,
|
||
|
|
"epoch": 0.021007586072748493,
|
||
|
|
"grad_norm": 0.984375,
|
||
|
|
"learning_rate": 0.00013450000000000002,
|
||
|
|
"loss": 7.4544,
|
||
|
|
"mean_token_accuracy": 0.07208218537271023,
|
||
|
|
"num_tokens": 472812.0,
|
||
|
|
"step": 270
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.977314424514771,
|
||
|
|
"epoch": 0.02139661544446606,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.00013700000000000002,
|
||
|
|
"loss": 7.437,
|
||
|
|
"mean_token_accuracy": 0.07208085916936398,
|
||
|
|
"num_tokens": 481326.0,
|
||
|
|
"step": 275
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.039547538757324,
|
||
|
|
"epoch": 0.02178564481618362,
|
||
|
|
"grad_norm": 0.921875,
|
||
|
|
"learning_rate": 0.0001395,
|
||
|
|
"loss": 7.377,
|
||
|
|
"mean_token_accuracy": 0.0771931130439043,
|
||
|
|
"num_tokens": 489147.0,
|
||
|
|
"step": 280
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.921053743362426,
|
||
|
|
"epoch": 0.022174674187901186,
|
||
|
|
"grad_norm": 0.98828125,
|
||
|
|
"learning_rate": 0.00014199999999999998,
|
||
|
|
"loss": 7.3711,
|
||
|
|
"mean_token_accuracy": 0.08139716684818268,
|
||
|
|
"num_tokens": 497455.0,
|
||
|
|
"step": 285
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.94639024734497,
|
||
|
|
"epoch": 0.02256370355961875,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.0001445,
|
||
|
|
"loss": 7.3084,
|
||
|
|
"mean_token_accuracy": 0.08105910569429398,
|
||
|
|
"num_tokens": 506735.0,
|
||
|
|
"step": 290
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.939362382888794,
|
||
|
|
"epoch": 0.022952732931336317,
|
||
|
|
"grad_norm": 0.953125,
|
||
|
|
"learning_rate": 0.000147,
|
||
|
|
"loss": 7.3807,
|
||
|
|
"mean_token_accuracy": 0.07725862711668015,
|
||
|
|
"num_tokens": 515976.0,
|
||
|
|
"step": 295
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.8592973232269285,
|
||
|
|
"epoch": 0.02334176230305388,
|
||
|
|
"grad_norm": 1.2578125,
|
||
|
|
"learning_rate": 0.0001495,
|
||
|
|
"loss": 7.3728,
|
||
|
|
"mean_token_accuracy": 0.0786518905311823,
|
||
|
|
"num_tokens": 524986.0,
|
||
|
|
"step": 300
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.871623373031616,
|
||
|
|
"epoch": 0.023730791674771445,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.000152,
|
||
|
|
"loss": 7.3857,
|
||
|
|
"mean_token_accuracy": 0.08207501620054244,
|
||
|
|
"num_tokens": 533146.0,
|
||
|
|
"step": 305
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.966270780563354,
|
||
|
|
"epoch": 0.02411982104648901,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.00015450000000000001,
|
||
|
|
"loss": 7.2788,
|
||
|
|
"mean_token_accuracy": 0.08436923623085021,
|
||
|
|
"num_tokens": 541704.0,
|
||
|
|
"step": 310
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.803447914123535,
|
||
|
|
"epoch": 0.024508850418206576,
|
||
|
|
"grad_norm": 1.1953125,
|
||
|
|
"learning_rate": 0.000157,
|
||
|
|
"loss": 7.2596,
|
||
|
|
"mean_token_accuracy": 0.08413073793053627,
|
||
|
|
"num_tokens": 550088.0,
|
||
|
|
"step": 315
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.808595514297485,
|
||
|
|
"epoch": 0.024897879789924138,
|
||
|
|
"grad_norm": 1.15625,
|
||
|
|
"learning_rate": 0.0001595,
|
||
|
|
"loss": 7.2537,
|
||
|
|
"mean_token_accuracy": 0.0833888128399849,
|
||
|
|
"num_tokens": 558763.0,
|
||
|
|
"step": 320
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.894071006774903,
|
||
|
|
"epoch": 0.025286909161641703,
|
||
|
|
"grad_norm": 0.96875,
|
||
|
|
"learning_rate": 0.000162,
|
||
|
|
"loss": 7.3379,
|
||
|
|
"mean_token_accuracy": 0.08004550337791443,
|
||
|
|
"num_tokens": 567538.0,
|
||
|
|
"step": 325
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.824001407623291,
|
||
|
|
"epoch": 0.02567593853335927,
|
||
|
|
"grad_norm": 1.2421875,
|
||
|
|
"learning_rate": 0.00016450000000000001,
|
||
|
|
"loss": 7.3535,
|
||
|
|
"mean_token_accuracy": 0.07598577216267585,
|
||
|
|
"num_tokens": 577626.0,
|
||
|
|
"step": 330
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.784535598754883,
|
||
|
|
"epoch": 0.026064967905076834,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.00016700000000000002,
|
||
|
|
"loss": 7.299,
|
||
|
|
"mean_token_accuracy": 0.07876510173082352,
|
||
|
|
"num_tokens": 587163.0,
|
||
|
|
"step": 335
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.756780767440796,
|
||
|
|
"epoch": 0.026453997276794396,
|
||
|
|
"grad_norm": 0.94921875,
|
||
|
|
"learning_rate": 0.00016950000000000003,
|
||
|
|
"loss": 7.2511,
|
||
|
|
"mean_token_accuracy": 0.08080902062356472,
|
||
|
|
"num_tokens": 595896.0,
|
||
|
|
"step": 340
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.8993690490722654,
|
||
|
|
"epoch": 0.026843026648511962,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.00017199999999999998,
|
||
|
|
"loss": 7.2821,
|
||
|
|
"mean_token_accuracy": 0.08391863107681274,
|
||
|
|
"num_tokens": 603815.0,
|
||
|
|
"step": 345
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.769748687744141,
|
||
|
|
"epoch": 0.027232056020229527,
|
||
|
|
"grad_norm": 0.99609375,
|
||
|
|
"learning_rate": 0.00017449999999999999,
|
||
|
|
"loss": 7.3017,
|
||
|
|
"mean_token_accuracy": 0.08513520881533623,
|
||
|
|
"num_tokens": 612208.0,
|
||
|
|
"step": 350
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.818035459518432,
|
||
|
|
"epoch": 0.027621085391947093,
|
||
|
|
"grad_norm": 0.984375,
|
||
|
|
"learning_rate": 0.000177,
|
||
|
|
"loss": 7.2697,
|
||
|
|
"mean_token_accuracy": 0.08533527255058289,
|
||
|
|
"num_tokens": 621840.0,
|
||
|
|
"step": 355
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.816836357116699,
|
||
|
|
"epoch": 0.028010114763664655,
|
||
|
|
"grad_norm": 0.984375,
|
||
|
|
"learning_rate": 0.0001795,
|
||
|
|
"loss": 7.2659,
|
||
|
|
"mean_token_accuracy": 0.08314265757799148,
|
||
|
|
"num_tokens": 630770.0,
|
||
|
|
"step": 360
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.714138650894165,
|
||
|
|
"epoch": 0.02839914413538222,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.000182,
|
||
|
|
"loss": 7.2661,
|
||
|
|
"mean_token_accuracy": 0.08392885178327561,
|
||
|
|
"num_tokens": 640313.0,
|
||
|
|
"step": 365
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.856315994262696,
|
||
|
|
"epoch": 0.028788173507099786,
|
||
|
|
"grad_norm": 0.99609375,
|
||
|
|
"learning_rate": 0.0001845,
|
||
|
|
"loss": 7.2949,
|
||
|
|
"mean_token_accuracy": 0.08515013977885247,
|
||
|
|
"num_tokens": 648594.0,
|
||
|
|
"step": 370
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.847173547744751,
|
||
|
|
"epoch": 0.02917720287881735,
|
||
|
|
"grad_norm": 1.3125,
|
||
|
|
"learning_rate": 0.000187,
|
||
|
|
"loss": 7.2775,
|
||
|
|
"mean_token_accuracy": 0.08574092835187912,
|
||
|
|
"num_tokens": 656478.0,
|
||
|
|
"step": 375
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.662766361236573,
|
||
|
|
"epoch": 0.029566232250534917,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.0001895,
|
||
|
|
"loss": 7.2441,
|
||
|
|
"mean_token_accuracy": 0.08885113224387169,
|
||
|
|
"num_tokens": 665405.0,
|
||
|
|
"step": 380
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.820247316360474,
|
||
|
|
"epoch": 0.02995526162225248,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.000192,
|
||
|
|
"loss": 7.2536,
|
||
|
|
"mean_token_accuracy": 0.08792344853281975,
|
||
|
|
"num_tokens": 674301.0,
|
||
|
|
"step": 385
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.737472772598267,
|
||
|
|
"epoch": 0.030344290993970045,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.0001945,
|
||
|
|
"loss": 7.2531,
|
||
|
|
"mean_token_accuracy": 0.09053674265742302,
|
||
|
|
"num_tokens": 683159.0,
|
||
|
|
"step": 390
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.638981580734253,
|
||
|
|
"epoch": 0.03073332036568761,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.00019700000000000002,
|
||
|
|
"loss": 7.0875,
|
||
|
|
"mean_token_accuracy": 0.09513727799057961,
|
||
|
|
"num_tokens": 690992.0,
|
||
|
|
"step": 395
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.6433281898498535,
|
||
|
|
"epoch": 0.031122349737405176,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.00019950000000000002,
|
||
|
|
"loss": 7.1734,
|
||
|
|
"mean_token_accuracy": 0.09246476516127586,
|
||
|
|
"num_tokens": 699934.0,
|
||
|
|
"step": 400
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.765408372879028,
|
||
|
|
"epoch": 0.03151137910912274,
|
||
|
|
"grad_norm": 1.2890625,
|
||
|
|
"learning_rate": 0.000202,
|
||
|
|
"loss": 7.2187,
|
||
|
|
"mean_token_accuracy": 0.08869696706533432,
|
||
|
|
"num_tokens": 708844.0,
|
||
|
|
"step": 405
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.719944286346435,
|
||
|
|
"epoch": 0.0319004084808403,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.00020449999999999998,
|
||
|
|
"loss": 7.2784,
|
||
|
|
"mean_token_accuracy": 0.08538637533783913,
|
||
|
|
"num_tokens": 718148.0,
|
||
|
|
"step": 410
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.750207042694091,
|
||
|
|
"epoch": 0.03228943785255787,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.000207,
|
||
|
|
"loss": 7.2089,
|
||
|
|
"mean_token_accuracy": 0.08420872502028942,
|
||
|
|
"num_tokens": 726859.0,
|
||
|
|
"step": 415
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.683270502090454,
|
||
|
|
"epoch": 0.032678467224275434,
|
||
|
|
"grad_norm": 1.34375,
|
||
|
|
"learning_rate": 0.0002095,
|
||
|
|
"loss": 7.2145,
|
||
|
|
"mean_token_accuracy": 0.09039615541696548,
|
||
|
|
"num_tokens": 735045.0,
|
||
|
|
"step": 420
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.59128589630127,
|
||
|
|
"epoch": 0.033067496595993,
|
||
|
|
"grad_norm": 0.8828125,
|
||
|
|
"learning_rate": 0.000212,
|
||
|
|
"loss": 7.0827,
|
||
|
|
"mean_token_accuracy": 0.09434614479541778,
|
||
|
|
"num_tokens": 743538.0,
|
||
|
|
"step": 425
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.6708005428314205,
|
||
|
|
"epoch": 0.033456525967710565,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.0002145,
|
||
|
|
"loss": 7.1281,
|
||
|
|
"mean_token_accuracy": 0.0933873251080513,
|
||
|
|
"num_tokens": 752518.0,
|
||
|
|
"step": 430
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.578746604919433,
|
||
|
|
"epoch": 0.033845555339428124,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.00021700000000000002,
|
||
|
|
"loss": 7.1528,
|
||
|
|
"mean_token_accuracy": 0.08902024403214455,
|
||
|
|
"num_tokens": 760354.0,
|
||
|
|
"step": 435
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.675575685501099,
|
||
|
|
"epoch": 0.03423458471114569,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0002195,
|
||
|
|
"loss": 7.2022,
|
||
|
|
"mean_token_accuracy": 0.0862238198518753,
|
||
|
|
"num_tokens": 769522.0,
|
||
|
|
"step": 440
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.607626724243164,
|
||
|
|
"epoch": 0.034623614082863255,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 0.000222,
|
||
|
|
"loss": 7.1284,
|
||
|
|
"mean_token_accuracy": 0.09797925055027008,
|
||
|
|
"num_tokens": 778548.0,
|
||
|
|
"step": 445
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.591102743148804,
|
||
|
|
"epoch": 0.03501264345458082,
|
||
|
|
"grad_norm": 1.140625,
|
||
|
|
"learning_rate": 0.0002245,
|
||
|
|
"loss": 7.143,
|
||
|
|
"mean_token_accuracy": 0.09332999736070632,
|
||
|
|
"num_tokens": 787666.0,
|
||
|
|
"step": 450
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.638665723800659,
|
||
|
|
"epoch": 0.035401672826298386,
|
||
|
|
"grad_norm": 1.1796875,
|
||
|
|
"learning_rate": 0.00022700000000000002,
|
||
|
|
"loss": 7.0542,
|
||
|
|
"mean_token_accuracy": 0.09499929621815681,
|
||
|
|
"num_tokens": 796550.0,
|
||
|
|
"step": 455
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.587637615203858,
|
||
|
|
"epoch": 0.03579070219801595,
|
||
|
|
"grad_norm": 1.40625,
|
||
|
|
"learning_rate": 0.00022950000000000002,
|
||
|
|
"loss": 7.1221,
|
||
|
|
"mean_token_accuracy": 0.09292486310005188,
|
||
|
|
"num_tokens": 804549.0,
|
||
|
|
"step": 460
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.547951364517212,
|
||
|
|
"epoch": 0.03617973156973352,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.00023200000000000003,
|
||
|
|
"loss": 7.0937,
|
||
|
|
"mean_token_accuracy": 0.09402075335383415,
|
||
|
|
"num_tokens": 813328.0,
|
||
|
|
"step": 465
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.606256341934204,
|
||
|
|
"epoch": 0.03656876094145108,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.00023449999999999998,
|
||
|
|
"loss": 7.1404,
|
||
|
|
"mean_token_accuracy": 0.0924923688173294,
|
||
|
|
"num_tokens": 821733.0,
|
||
|
|
"step": 470
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.556232976913452,
|
||
|
|
"epoch": 0.03695779031316864,
|
||
|
|
"grad_norm": 1.1875,
|
||
|
|
"learning_rate": 0.000237,
|
||
|
|
"loss": 7.0732,
|
||
|
|
"mean_token_accuracy": 0.09500073790550231,
|
||
|
|
"num_tokens": 830243.0,
|
||
|
|
"step": 475
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.638236665725708,
|
||
|
|
"epoch": 0.03734681968488621,
|
||
|
|
"grad_norm": 1.2890625,
|
||
|
|
"learning_rate": 0.0002395,
|
||
|
|
"loss": 7.0519,
|
||
|
|
"mean_token_accuracy": 0.09168064296245575,
|
||
|
|
"num_tokens": 839059.0,
|
||
|
|
"step": 480
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.385732889175415,
|
||
|
|
"epoch": 0.03773584905660377,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.000242,
|
||
|
|
"loss": 6.9442,
|
||
|
|
"mean_token_accuracy": 0.09834211766719818,
|
||
|
|
"num_tokens": 846932.0,
|
||
|
|
"step": 485
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.602040719985962,
|
||
|
|
"epoch": 0.03812487842832134,
|
||
|
|
"grad_norm": 1.203125,
|
||
|
|
"learning_rate": 0.0002445,
|
||
|
|
"loss": 7.1423,
|
||
|
|
"mean_token_accuracy": 0.08770201802253723,
|
||
|
|
"num_tokens": 855333.0,
|
||
|
|
"step": 490
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.395545721054077,
|
||
|
|
"epoch": 0.0385139078000389,
|
||
|
|
"grad_norm": 1.3203125,
|
||
|
|
"learning_rate": 0.000247,
|
||
|
|
"loss": 6.9209,
|
||
|
|
"mean_token_accuracy": 0.09375111684203148,
|
||
|
|
"num_tokens": 863571.0,
|
||
|
|
"step": 495
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.454263353347779,
|
||
|
|
"epoch": 0.03890293717175647,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.0002495,
|
||
|
|
"loss": 6.992,
|
||
|
|
"mean_token_accuracy": 0.10193705037236214,
|
||
|
|
"num_tokens": 872145.0,
|
||
|
|
"step": 500
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.494772291183471,
|
||
|
|
"epoch": 0.039291966543474034,
|
||
|
|
"grad_norm": 1.171875,
|
||
|
|
"learning_rate": 0.000252,
|
||
|
|
"loss": 7.0283,
|
||
|
|
"mean_token_accuracy": 0.09722969233989716,
|
||
|
|
"num_tokens": 880634.0,
|
||
|
|
"step": 505
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.492091417312622,
|
||
|
|
"epoch": 0.0396809959151916,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0002545,
|
||
|
|
"loss": 6.9729,
|
||
|
|
"mean_token_accuracy": 0.09642753973603249,
|
||
|
|
"num_tokens": 889178.0,
|
||
|
|
"step": 510
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.418828535079956,
|
||
|
|
"epoch": 0.04007002528690916,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.000257,
|
||
|
|
"loss": 6.9655,
|
||
|
|
"mean_token_accuracy": 0.09765015915036201,
|
||
|
|
"num_tokens": 898255.0,
|
||
|
|
"step": 515
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.432187509536743,
|
||
|
|
"epoch": 0.040459054658626724,
|
||
|
|
"grad_norm": 1.203125,
|
||
|
|
"learning_rate": 0.0002595,
|
||
|
|
"loss": 7.0224,
|
||
|
|
"mean_token_accuracy": 0.09072192162275314,
|
||
|
|
"num_tokens": 907369.0,
|
||
|
|
"step": 520
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.4239561557769775,
|
||
|
|
"epoch": 0.04084808403034429,
|
||
|
|
"grad_norm": 1.15625,
|
||
|
|
"learning_rate": 0.000262,
|
||
|
|
"loss": 6.9475,
|
||
|
|
"mean_token_accuracy": 0.0962302841246128,
|
||
|
|
"num_tokens": 915946.0,
|
||
|
|
"step": 525
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.447218513488769,
|
||
|
|
"epoch": 0.041237113402061855,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.00026450000000000003,
|
||
|
|
"loss": 6.9879,
|
||
|
|
"mean_token_accuracy": 0.09441638067364692,
|
||
|
|
"num_tokens": 925579.0,
|
||
|
|
"step": 530
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.409813165664673,
|
||
|
|
"epoch": 0.04162614277377942,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.00026700000000000004,
|
||
|
|
"loss": 6.977,
|
||
|
|
"mean_token_accuracy": 0.09423855319619179,
|
||
|
|
"num_tokens": 934732.0,
|
||
|
|
"step": 535
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.454560852050781,
|
||
|
|
"epoch": 0.042015172145496986,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.00026950000000000005,
|
||
|
|
"loss": 7.0283,
|
||
|
|
"mean_token_accuracy": 0.09172707796096802,
|
||
|
|
"num_tokens": 943371.0,
|
||
|
|
"step": 540
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.407678842544556,
|
||
|
|
"epoch": 0.04240420151721455,
|
||
|
|
"grad_norm": 1.1875,
|
||
|
|
"learning_rate": 0.00027200000000000005,
|
||
|
|
"loss": 6.8926,
|
||
|
|
"mean_token_accuracy": 0.09576850831508636,
|
||
|
|
"num_tokens": 951977.0,
|
||
|
|
"step": 545
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.412649726867675,
|
||
|
|
"epoch": 0.04279323088893212,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.0002745,
|
||
|
|
"loss": 6.886,
|
||
|
|
"mean_token_accuracy": 0.10018825083971024,
|
||
|
|
"num_tokens": 960474.0,
|
||
|
|
"step": 550
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.447184467315674,
|
||
|
|
"epoch": 0.04318226026064968,
|
||
|
|
"grad_norm": 0.97265625,
|
||
|
|
"learning_rate": 0.000277,
|
||
|
|
"loss": 6.9998,
|
||
|
|
"mean_token_accuracy": 0.09603087753057479,
|
||
|
|
"num_tokens": 969823.0,
|
||
|
|
"step": 555
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.450275087356568,
|
||
|
|
"epoch": 0.04357128963236724,
|
||
|
|
"grad_norm": 1.1796875,
|
||
|
|
"learning_rate": 0.0002795,
|
||
|
|
"loss": 6.9175,
|
||
|
|
"mean_token_accuracy": 0.10505582615733147,
|
||
|
|
"num_tokens": 977417.0,
|
||
|
|
"step": 560
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.354970455169678,
|
||
|
|
"epoch": 0.04396031900408481,
|
||
|
|
"grad_norm": 1.203125,
|
||
|
|
"learning_rate": 0.00028199999999999997,
|
||
|
|
"loss": 6.9189,
|
||
|
|
"mean_token_accuracy": 0.11012696176767349,
|
||
|
|
"num_tokens": 985519.0,
|
||
|
|
"step": 565
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.33652982711792,
|
||
|
|
"epoch": 0.04434934837580237,
|
||
|
|
"grad_norm": 1.3046875,
|
||
|
|
"learning_rate": 0.0002845,
|
||
|
|
"loss": 6.9209,
|
||
|
|
"mean_token_accuracy": 0.10035700276494026,
|
||
|
|
"num_tokens": 994136.0,
|
||
|
|
"step": 570
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.332489347457885,
|
||
|
|
"epoch": 0.04473837774751994,
|
||
|
|
"grad_norm": 1.2421875,
|
||
|
|
"learning_rate": 0.000287,
|
||
|
|
"loss": 6.8909,
|
||
|
|
"mean_token_accuracy": 0.09913867935538292,
|
||
|
|
"num_tokens": 1002896.0,
|
||
|
|
"step": 575
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.440053081512451,
|
||
|
|
"epoch": 0.0451274071192375,
|
||
|
|
"grad_norm": 1.2109375,
|
||
|
|
"learning_rate": 0.0002895,
|
||
|
|
"loss": 6.968,
|
||
|
|
"mean_token_accuracy": 0.10127009153366089,
|
||
|
|
"num_tokens": 1011032.0,
|
||
|
|
"step": 580
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.2483752250671385,
|
||
|
|
"epoch": 0.04551643649095507,
|
||
|
|
"grad_norm": 1.140625,
|
||
|
|
"learning_rate": 0.000292,
|
||
|
|
"loss": 6.9354,
|
||
|
|
"mean_token_accuracy": 0.09478853791952133,
|
||
|
|
"num_tokens": 1019901.0,
|
||
|
|
"step": 585
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.367902326583862,
|
||
|
|
"epoch": 0.045905465862672634,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.0002945,
|
||
|
|
"loss": 6.9199,
|
||
|
|
"mean_token_accuracy": 0.09609107375144958,
|
||
|
|
"num_tokens": 1029049.0,
|
||
|
|
"step": 590
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.297397232055664,
|
||
|
|
"epoch": 0.0462944952343902,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.000297,
|
||
|
|
"loss": 6.88,
|
||
|
|
"mean_token_accuracy": 0.11009425967931748,
|
||
|
|
"num_tokens": 1037580.0,
|
||
|
|
"step": 595
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.358423042297363,
|
||
|
|
"epoch": 0.04668352460610776,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 0.0002995,
|
||
|
|
"loss": 6.9401,
|
||
|
|
"mean_token_accuracy": 0.10255178958177566,
|
||
|
|
"num_tokens": 1045804.0,
|
||
|
|
"step": 600
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.327436733245849,
|
||
|
|
"epoch": 0.047072553977825324,
|
||
|
|
"grad_norm": 1.15625,
|
||
|
|
"learning_rate": 0.000302,
|
||
|
|
"loss": 6.8943,
|
||
|
|
"mean_token_accuracy": 0.0945185400545597,
|
||
|
|
"num_tokens": 1054719.0,
|
||
|
|
"step": 605
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.400276851654053,
|
||
|
|
"epoch": 0.04746158334954289,
|
||
|
|
"grad_norm": 1.1796875,
|
||
|
|
"learning_rate": 0.0003045,
|
||
|
|
"loss": 6.8877,
|
||
|
|
"mean_token_accuracy": 0.10351422131061554,
|
||
|
|
"num_tokens": 1063373.0,
|
||
|
|
"step": 610
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.205434131622314,
|
||
|
|
"epoch": 0.047850612721260455,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.000307,
|
||
|
|
"loss": 6.8601,
|
||
|
|
"mean_token_accuracy": 0.1029354140162468,
|
||
|
|
"num_tokens": 1073021.0,
|
||
|
|
"step": 615
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.366950464248657,
|
||
|
|
"epoch": 0.04823964209297802,
|
||
|
|
"grad_norm": 1.34375,
|
||
|
|
"learning_rate": 0.0003095,
|
||
|
|
"loss": 6.9232,
|
||
|
|
"mean_token_accuracy": 0.09619447886943817,
|
||
|
|
"num_tokens": 1081547.0,
|
||
|
|
"step": 620
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.274023580551147,
|
||
|
|
"epoch": 0.048628671464695586,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.000312,
|
||
|
|
"loss": 6.8907,
|
||
|
|
"mean_token_accuracy": 0.09834453091025352,
|
||
|
|
"num_tokens": 1090695.0,
|
||
|
|
"step": 625
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.250863170623779,
|
||
|
|
"epoch": 0.04901770083641315,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.0003145,
|
||
|
|
"loss": 6.7816,
|
||
|
|
"mean_token_accuracy": 0.10651093125343322,
|
||
|
|
"num_tokens": 1099563.0,
|
||
|
|
"step": 630
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.316005992889404,
|
||
|
|
"epoch": 0.04940673020813072,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.000317,
|
||
|
|
"loss": 6.8534,
|
||
|
|
"mean_token_accuracy": 0.1008830115199089,
|
||
|
|
"num_tokens": 1109021.0,
|
||
|
|
"step": 635
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.2779614448547365,
|
||
|
|
"epoch": 0.049795759579848276,
|
||
|
|
"grad_norm": 1.21875,
|
||
|
|
"learning_rate": 0.0003195,
|
||
|
|
"loss": 6.8518,
|
||
|
|
"mean_token_accuracy": 0.10254788249731064,
|
||
|
|
"num_tokens": 1118281.0,
|
||
|
|
"step": 640
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.271533203125,
|
||
|
|
"epoch": 0.05018478895156584,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.000322,
|
||
|
|
"loss": 6.8932,
|
||
|
|
"mean_token_accuracy": 0.09681643918156624,
|
||
|
|
"num_tokens": 1127513.0,
|
||
|
|
"step": 645
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.177491044998169,
|
||
|
|
"epoch": 0.05057381832328341,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 0.00032450000000000003,
|
||
|
|
"loss": 6.766,
|
||
|
|
"mean_token_accuracy": 0.10509725958108902,
|
||
|
|
"num_tokens": 1136140.0,
|
||
|
|
"step": 650
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.26359543800354,
|
||
|
|
"epoch": 0.05096284769500097,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 0.00032700000000000003,
|
||
|
|
"loss": 6.7939,
|
||
|
|
"mean_token_accuracy": 0.10301651507616043,
|
||
|
|
"num_tokens": 1144297.0,
|
||
|
|
"step": 655
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.281031465530395,
|
||
|
|
"epoch": 0.05135187706671854,
|
||
|
|
"grad_norm": 1.2578125,
|
||
|
|
"learning_rate": 0.00032950000000000004,
|
||
|
|
"loss": 6.8864,
|
||
|
|
"mean_token_accuracy": 0.09698515310883522,
|
||
|
|
"num_tokens": 1153639.0,
|
||
|
|
"step": 660
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.245992708206177,
|
||
|
|
"epoch": 0.0517409064384361,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.00033200000000000005,
|
||
|
|
"loss": 6.8538,
|
||
|
|
"mean_token_accuracy": 0.09941518083214759,
|
||
|
|
"num_tokens": 1162825.0,
|
||
|
|
"step": 665
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.20550389289856,
|
||
|
|
"epoch": 0.05212993581015367,
|
||
|
|
"grad_norm": 1.1796875,
|
||
|
|
"learning_rate": 0.00033450000000000005,
|
||
|
|
"loss": 6.8767,
|
||
|
|
"mean_token_accuracy": 0.10294063836336136,
|
||
|
|
"num_tokens": 1171887.0,
|
||
|
|
"step": 670
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.228694581985474,
|
||
|
|
"epoch": 0.052518965181871234,
|
||
|
|
"grad_norm": 1.171875,
|
||
|
|
"learning_rate": 0.000337,
|
||
|
|
"loss": 6.7878,
|
||
|
|
"mean_token_accuracy": 0.10553507208824157,
|
||
|
|
"num_tokens": 1179963.0,
|
||
|
|
"step": 675
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.170407724380493,
|
||
|
|
"epoch": 0.05290799455358879,
|
||
|
|
"grad_norm": 1.1796875,
|
||
|
|
"learning_rate": 0.0003395,
|
||
|
|
"loss": 6.7633,
|
||
|
|
"mean_token_accuracy": 0.10891782119870186,
|
||
|
|
"num_tokens": 1188408.0,
|
||
|
|
"step": 680
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.168772220611572,
|
||
|
|
"epoch": 0.05329702392530636,
|
||
|
|
"grad_norm": 1.1640625,
|
||
|
|
"learning_rate": 0.000342,
|
||
|
|
"loss": 6.7986,
|
||
|
|
"mean_token_accuracy": 0.09899375736713409,
|
||
|
|
"num_tokens": 1197751.0,
|
||
|
|
"step": 685
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.197608995437622,
|
||
|
|
"epoch": 0.053686053297023924,
|
||
|
|
"grad_norm": 1.171875,
|
||
|
|
"learning_rate": 0.00034449999999999997,
|
||
|
|
"loss": 6.8312,
|
||
|
|
"mean_token_accuracy": 0.1030447706580162,
|
||
|
|
"num_tokens": 1207101.0,
|
||
|
|
"step": 690
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.218799304962158,
|
||
|
|
"epoch": 0.05407508266874149,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.000347,
|
||
|
|
"loss": 6.829,
|
||
|
|
"mean_token_accuracy": 0.10361301824450493,
|
||
|
|
"num_tokens": 1216395.0,
|
||
|
|
"step": 695
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.224749946594239,
|
||
|
|
"epoch": 0.054464112040459055,
|
||
|
|
"grad_norm": 1.2265625,
|
||
|
|
"learning_rate": 0.0003495,
|
||
|
|
"loss": 6.8108,
|
||
|
|
"mean_token_accuracy": 0.10502151176333427,
|
||
|
|
"num_tokens": 1225496.0,
|
||
|
|
"step": 700
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.232848119735718,
|
||
|
|
"epoch": 0.05485314141217662,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.000352,
|
||
|
|
"loss": 6.8746,
|
||
|
|
"mean_token_accuracy": 0.10201601535081864,
|
||
|
|
"num_tokens": 1233934.0,
|
||
|
|
"step": 705
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.18028507232666,
|
||
|
|
"epoch": 0.055242170783894186,
|
||
|
|
"grad_norm": 1.2578125,
|
||
|
|
"learning_rate": 0.0003545,
|
||
|
|
"loss": 6.7279,
|
||
|
|
"mean_token_accuracy": 0.1090910330414772,
|
||
|
|
"num_tokens": 1242165.0,
|
||
|
|
"step": 710
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.153624200820923,
|
||
|
|
"epoch": 0.05563120015561175,
|
||
|
|
"grad_norm": 1.296875,
|
||
|
|
"learning_rate": 0.000357,
|
||
|
|
"loss": 6.7967,
|
||
|
|
"mean_token_accuracy": 0.1042649894952774,
|
||
|
|
"num_tokens": 1250021.0,
|
||
|
|
"step": 715
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.190495872497559,
|
||
|
|
"epoch": 0.05602022952732931,
|
||
|
|
"grad_norm": 1.140625,
|
||
|
|
"learning_rate": 0.0003595,
|
||
|
|
"loss": 6.8155,
|
||
|
|
"mean_token_accuracy": 0.10334040820598603,
|
||
|
|
"num_tokens": 1258397.0,
|
||
|
|
"step": 720
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.170076513290406,
|
||
|
|
"epoch": 0.056409258899046875,
|
||
|
|
"grad_norm": 1.3046875,
|
||
|
|
"learning_rate": 0.000362,
|
||
|
|
"loss": 6.8121,
|
||
|
|
"mean_token_accuracy": 0.10407566651701927,
|
||
|
|
"num_tokens": 1266764.0,
|
||
|
|
"step": 725
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.1744321346282955,
|
||
|
|
"epoch": 0.05679828827076444,
|
||
|
|
"grad_norm": 1.2265625,
|
||
|
|
"learning_rate": 0.0003645,
|
||
|
|
"loss": 6.8094,
|
||
|
|
"mean_token_accuracy": 0.09987704753875733,
|
||
|
|
"num_tokens": 1275643.0,
|
||
|
|
"step": 730
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.19658842086792,
|
||
|
|
"epoch": 0.057187317642482006,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.000367,
|
||
|
|
"loss": 6.7852,
|
||
|
|
"mean_token_accuracy": 0.10181980207562447,
|
||
|
|
"num_tokens": 1284379.0,
|
||
|
|
"step": 735
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.100433397293091,
|
||
|
|
"epoch": 0.05757634701419957,
|
||
|
|
"grad_norm": 1.1640625,
|
||
|
|
"learning_rate": 0.0003695,
|
||
|
|
"loss": 6.6451,
|
||
|
|
"mean_token_accuracy": 0.11134169921278954,
|
||
|
|
"num_tokens": 1293115.0,
|
||
|
|
"step": 740
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.243102264404297,
|
||
|
|
"epoch": 0.05796537638591714,
|
||
|
|
"grad_norm": 1.1953125,
|
||
|
|
"learning_rate": 0.000372,
|
||
|
|
"loss": 6.8351,
|
||
|
|
"mean_token_accuracy": 0.09663488790392875,
|
||
|
|
"num_tokens": 1301583.0,
|
||
|
|
"step": 745
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.155255460739136,
|
||
|
|
"epoch": 0.0583544057576347,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0003745,
|
||
|
|
"loss": 6.7361,
|
||
|
|
"mean_token_accuracy": 0.10636070072650909,
|
||
|
|
"num_tokens": 1310721.0,
|
||
|
|
"step": 750
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.158748054504395,
|
||
|
|
"epoch": 0.05874343512935227,
|
||
|
|
"grad_norm": 1.234375,
|
||
|
|
"learning_rate": 0.000377,
|
||
|
|
"loss": 6.8794,
|
||
|
|
"mean_token_accuracy": 0.09966575875878333,
|
||
|
|
"num_tokens": 1319056.0,
|
||
|
|
"step": 755
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.131784152984619,
|
||
|
|
"epoch": 0.059132464501069834,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.0003795,
|
||
|
|
"loss": 6.7662,
|
||
|
|
"mean_token_accuracy": 0.1062756285071373,
|
||
|
|
"num_tokens": 1327259.0,
|
||
|
|
"step": 760
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.098258781433105,
|
||
|
|
"epoch": 0.05952149387278739,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 0.000382,
|
||
|
|
"loss": 6.6695,
|
||
|
|
"mean_token_accuracy": 0.10549260452389717,
|
||
|
|
"num_tokens": 1335906.0,
|
||
|
|
"step": 765
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.124299383163452,
|
||
|
|
"epoch": 0.05991052324450496,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.0003845,
|
||
|
|
"loss": 6.7193,
|
||
|
|
"mean_token_accuracy": 0.10388574972748757,
|
||
|
|
"num_tokens": 1344743.0,
|
||
|
|
"step": 770
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.124751281738281,
|
||
|
|
"epoch": 0.060299552616222524,
|
||
|
|
"grad_norm": 1.28125,
|
||
|
|
"learning_rate": 0.00038700000000000003,
|
||
|
|
"loss": 6.732,
|
||
|
|
"mean_token_accuracy": 0.10936428904533387,
|
||
|
|
"num_tokens": 1353211.0,
|
||
|
|
"step": 775
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.119222116470337,
|
||
|
|
"epoch": 0.06068858198794009,
|
||
|
|
"grad_norm": 1.15625,
|
||
|
|
"learning_rate": 0.00038950000000000003,
|
||
|
|
"loss": 6.8463,
|
||
|
|
"mean_token_accuracy": 0.09924818351864814,
|
||
|
|
"num_tokens": 1361849.0,
|
||
|
|
"step": 780
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.19121618270874,
|
||
|
|
"epoch": 0.061077611359657655,
|
||
|
|
"grad_norm": 1.1953125,
|
||
|
|
"learning_rate": 0.00039200000000000004,
|
||
|
|
"loss": 6.8264,
|
||
|
|
"mean_token_accuracy": 0.10749334692955018,
|
||
|
|
"num_tokens": 1369804.0,
|
||
|
|
"step": 785
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.045189571380615,
|
||
|
|
"epoch": 0.06146664073137522,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.00039450000000000005,
|
||
|
|
"loss": 6.6156,
|
||
|
|
"mean_token_accuracy": 0.10870056599378586,
|
||
|
|
"num_tokens": 1378478.0,
|
||
|
|
"step": 790
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.11121244430542,
|
||
|
|
"epoch": 0.061855670103092786,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.00039700000000000005,
|
||
|
|
"loss": 6.7107,
|
||
|
|
"mean_token_accuracy": 0.10817317888140679,
|
||
|
|
"num_tokens": 1387225.0,
|
||
|
|
"step": 795
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.035085678100586,
|
||
|
|
"epoch": 0.06224469947481035,
|
||
|
|
"grad_norm": 1.25,
|
||
|
|
"learning_rate": 0.0003995,
|
||
|
|
"loss": 6.6882,
|
||
|
|
"mean_token_accuracy": 0.10929678976535798,
|
||
|
|
"num_tokens": 1395338.0,
|
||
|
|
"step": 800
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.0744215965271,
|
||
|
|
"epoch": 0.06263372884652792,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.000402,
|
||
|
|
"loss": 6.6625,
|
||
|
|
"mean_token_accuracy": 0.10991387590765953,
|
||
|
|
"num_tokens": 1403794.0,
|
||
|
|
"step": 805
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.982004165649414,
|
||
|
|
"epoch": 0.06302275821824548,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004045,
|
||
|
|
"loss": 6.738,
|
||
|
|
"mean_token_accuracy": 0.10092620700597763,
|
||
|
|
"num_tokens": 1412522.0,
|
||
|
|
"step": 810
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.081152534484863,
|
||
|
|
"epoch": 0.06341178758996305,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.00040699999999999997,
|
||
|
|
"loss": 6.7227,
|
||
|
|
"mean_token_accuracy": 0.10850374028086662,
|
||
|
|
"num_tokens": 1421347.0,
|
||
|
|
"step": 815
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.046439456939697,
|
||
|
|
"epoch": 0.0638008169616806,
|
||
|
|
"grad_norm": 1.1953125,
|
||
|
|
"learning_rate": 0.0004095,
|
||
|
|
"loss": 6.7041,
|
||
|
|
"mean_token_accuracy": 0.11018050685524941,
|
||
|
|
"num_tokens": 1429788.0,
|
||
|
|
"step": 820
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.077642393112183,
|
||
|
|
"epoch": 0.06418984633339817,
|
||
|
|
"grad_norm": 1.2265625,
|
||
|
|
"learning_rate": 0.000412,
|
||
|
|
"loss": 6.6955,
|
||
|
|
"mean_token_accuracy": 0.1097219817340374,
|
||
|
|
"num_tokens": 1437442.0,
|
||
|
|
"step": 825
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.984000587463379,
|
||
|
|
"epoch": 0.06457887570511574,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.0004145,
|
||
|
|
"loss": 6.6325,
|
||
|
|
"mean_token_accuracy": 0.10700507164001465,
|
||
|
|
"num_tokens": 1445604.0,
|
||
|
|
"step": 830
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.009225702285766,
|
||
|
|
"epoch": 0.0649679050768333,
|
||
|
|
"grad_norm": 1.140625,
|
||
|
|
"learning_rate": 0.000417,
|
||
|
|
"loss": 6.6963,
|
||
|
|
"mean_token_accuracy": 0.10920493751764297,
|
||
|
|
"num_tokens": 1454342.0,
|
||
|
|
"step": 835
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.046473693847656,
|
||
|
|
"epoch": 0.06535693444855087,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.0004195,
|
||
|
|
"loss": 6.6777,
|
||
|
|
"mean_token_accuracy": 0.11271065473556519,
|
||
|
|
"num_tokens": 1463189.0,
|
||
|
|
"step": 840
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.0349955558776855,
|
||
|
|
"epoch": 0.06574596382026843,
|
||
|
|
"grad_norm": 1.1875,
|
||
|
|
"learning_rate": 0.000422,
|
||
|
|
"loss": 6.751,
|
||
|
|
"mean_token_accuracy": 0.1046958401799202,
|
||
|
|
"num_tokens": 1471608.0,
|
||
|
|
"step": 845
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.108201360702514,
|
||
|
|
"epoch": 0.066134993191986,
|
||
|
|
"grad_norm": 1.1953125,
|
||
|
|
"learning_rate": 0.0004245,
|
||
|
|
"loss": 6.7468,
|
||
|
|
"mean_token_accuracy": 0.10504127219319344,
|
||
|
|
"num_tokens": 1480452.0,
|
||
|
|
"step": 850
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.051074695587158,
|
||
|
|
"epoch": 0.06652402256370356,
|
||
|
|
"grad_norm": 1.2734375,
|
||
|
|
"learning_rate": 0.000427,
|
||
|
|
"loss": 6.6688,
|
||
|
|
"mean_token_accuracy": 0.10868829116225243,
|
||
|
|
"num_tokens": 1489118.0,
|
||
|
|
"step": 855
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.962509250640869,
|
||
|
|
"epoch": 0.06691305193542113,
|
||
|
|
"grad_norm": 1.171875,
|
||
|
|
"learning_rate": 0.0004295,
|
||
|
|
"loss": 6.6703,
|
||
|
|
"mean_token_accuracy": 0.10638387426733971,
|
||
|
|
"num_tokens": 1498961.0,
|
||
|
|
"step": 860
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.081515598297119,
|
||
|
|
"epoch": 0.06730208130713869,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.000432,
|
||
|
|
"loss": 6.6661,
|
||
|
|
"mean_token_accuracy": 0.10934964269399643,
|
||
|
|
"num_tokens": 1506772.0,
|
||
|
|
"step": 865
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.947929859161377,
|
||
|
|
"epoch": 0.06769111067885625,
|
||
|
|
"grad_norm": 1.1796875,
|
||
|
|
"learning_rate": 0.0004345,
|
||
|
|
"loss": 6.5534,
|
||
|
|
"mean_token_accuracy": 0.11734423041343689,
|
||
|
|
"num_tokens": 1515095.0,
|
||
|
|
"step": 870
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.930423736572266,
|
||
|
|
"epoch": 0.06808014005057382,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.000437,
|
||
|
|
"loss": 6.593,
|
||
|
|
"mean_token_accuracy": 0.11688333824276924,
|
||
|
|
"num_tokens": 1523477.0,
|
||
|
|
"step": 875
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.0028105735778805,
|
||
|
|
"epoch": 0.06846916942229138,
|
||
|
|
"grad_norm": 1.171875,
|
||
|
|
"learning_rate": 0.0004395,
|
||
|
|
"loss": 6.6287,
|
||
|
|
"mean_token_accuracy": 0.10662296116352081,
|
||
|
|
"num_tokens": 1531786.0,
|
||
|
|
"step": 880
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.932631206512451,
|
||
|
|
"epoch": 0.06885819879400895,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.000442,
|
||
|
|
"loss": 6.7189,
|
||
|
|
"mean_token_accuracy": 0.10187280923128128,
|
||
|
|
"num_tokens": 1540737.0,
|
||
|
|
"step": 885
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.950942516326904,
|
||
|
|
"epoch": 0.06924722816572651,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0004445,
|
||
|
|
"loss": 6.5705,
|
||
|
|
"mean_token_accuracy": 0.11004639267921448,
|
||
|
|
"num_tokens": 1548923.0,
|
||
|
|
"step": 890
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.921659803390503,
|
||
|
|
"epoch": 0.06963625753744408,
|
||
|
|
"grad_norm": 1.2578125,
|
||
|
|
"learning_rate": 0.000447,
|
||
|
|
"loss": 6.5273,
|
||
|
|
"mean_token_accuracy": 0.11898597478866577,
|
||
|
|
"num_tokens": 1557043.0,
|
||
|
|
"step": 895
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.893300342559814,
|
||
|
|
"epoch": 0.07002528690916164,
|
||
|
|
"grad_norm": 1.171875,
|
||
|
|
"learning_rate": 0.00044950000000000003,
|
||
|
|
"loss": 6.5837,
|
||
|
|
"mean_token_accuracy": 0.11473687514662742,
|
||
|
|
"num_tokens": 1564994.0,
|
||
|
|
"step": 900
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.921711587905884,
|
||
|
|
"epoch": 0.0704143162808792,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.00045200000000000004,
|
||
|
|
"loss": 6.5688,
|
||
|
|
"mean_token_accuracy": 0.11160103157162667,
|
||
|
|
"num_tokens": 1573859.0,
|
||
|
|
"step": 905
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.986482381820679,
|
||
|
|
"epoch": 0.07080334565259677,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.00045450000000000004,
|
||
|
|
"loss": 6.5448,
|
||
|
|
"mean_token_accuracy": 0.1087655171751976,
|
||
|
|
"num_tokens": 1581947.0,
|
||
|
|
"step": 910
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.883696842193603,
|
||
|
|
"epoch": 0.07119237502431433,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.00045700000000000005,
|
||
|
|
"loss": 6.5205,
|
||
|
|
"mean_token_accuracy": 0.11201854199171066,
|
||
|
|
"num_tokens": 1589971.0,
|
||
|
|
"step": 915
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.8449201583862305,
|
||
|
|
"epoch": 0.0715814043960319,
|
||
|
|
"grad_norm": 1.171875,
|
||
|
|
"learning_rate": 0.00045950000000000006,
|
||
|
|
"loss": 6.4817,
|
||
|
|
"mean_token_accuracy": 0.11529209017753601,
|
||
|
|
"num_tokens": 1598612.0,
|
||
|
|
"step": 920
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.935947418212891,
|
||
|
|
"epoch": 0.07197043376774946,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.000462,
|
||
|
|
"loss": 6.621,
|
||
|
|
"mean_token_accuracy": 0.10783407837152481,
|
||
|
|
"num_tokens": 1607378.0,
|
||
|
|
"step": 925
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.844717597961425,
|
||
|
|
"epoch": 0.07235946313946703,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0004645,
|
||
|
|
"loss": 6.617,
|
||
|
|
"mean_token_accuracy": 0.1145533099770546,
|
||
|
|
"num_tokens": 1615987.0,
|
||
|
|
"step": 930
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.833771276473999,
|
||
|
|
"epoch": 0.07274849251118459,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.000467,
|
||
|
|
"loss": 6.4242,
|
||
|
|
"mean_token_accuracy": 0.11947599574923515,
|
||
|
|
"num_tokens": 1625366.0,
|
||
|
|
"step": 935
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.898650407791138,
|
||
|
|
"epoch": 0.07313752188290217,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0004695,
|
||
|
|
"loss": 6.6015,
|
||
|
|
"mean_token_accuracy": 0.11430608332157136,
|
||
|
|
"num_tokens": 1633020.0,
|
||
|
|
"step": 940
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.870701551437378,
|
||
|
|
"epoch": 0.07352655125461972,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.000472,
|
||
|
|
"loss": 6.5056,
|
||
|
|
"mean_token_accuracy": 0.11246326416730881,
|
||
|
|
"num_tokens": 1641518.0,
|
||
|
|
"step": 945
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.800650787353516,
|
||
|
|
"epoch": 0.07391558062633728,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.0004745,
|
||
|
|
"loss": 6.5851,
|
||
|
|
"mean_token_accuracy": 0.10907077416777611,
|
||
|
|
"num_tokens": 1650472.0,
|
||
|
|
"step": 950
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.919282150268555,
|
||
|
|
"epoch": 0.07430460999805485,
|
||
|
|
"grad_norm": 1.1796875,
|
||
|
|
"learning_rate": 0.000477,
|
||
|
|
"loss": 6.6162,
|
||
|
|
"mean_token_accuracy": 0.10955818668007851,
|
||
|
|
"num_tokens": 1659037.0,
|
||
|
|
"step": 955
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.930318880081177,
|
||
|
|
"epoch": 0.07469363936977241,
|
||
|
|
"grad_norm": 1.15625,
|
||
|
|
"learning_rate": 0.0004795,
|
||
|
|
"loss": 6.6848,
|
||
|
|
"mean_token_accuracy": 0.1120296597480774,
|
||
|
|
"num_tokens": 1667897.0,
|
||
|
|
"step": 960
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.849212980270385,
|
||
|
|
"epoch": 0.07508266874148999,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.000482,
|
||
|
|
"loss": 6.5291,
|
||
|
|
"mean_token_accuracy": 0.1111655130982399,
|
||
|
|
"num_tokens": 1676535.0,
|
||
|
|
"step": 965
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.944094228744507,
|
||
|
|
"epoch": 0.07547169811320754,
|
||
|
|
"grad_norm": 1.2109375,
|
||
|
|
"learning_rate": 0.0004845,
|
||
|
|
"loss": 6.5692,
|
||
|
|
"mean_token_accuracy": 0.11485065668821334,
|
||
|
|
"num_tokens": 1684415.0,
|
||
|
|
"step": 970
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.882363891601562,
|
||
|
|
"epoch": 0.07586072748492512,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.000487,
|
||
|
|
"loss": 6.5195,
|
||
|
|
"mean_token_accuracy": 0.1194272443652153,
|
||
|
|
"num_tokens": 1692443.0,
|
||
|
|
"step": 975
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.744445562362671,
|
||
|
|
"epoch": 0.07624975685664268,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004895,
|
||
|
|
"loss": 6.5166,
|
||
|
|
"mean_token_accuracy": 0.11746397837996483,
|
||
|
|
"num_tokens": 1700814.0,
|
||
|
|
"step": 980
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.767728662490844,
|
||
|
|
"epoch": 0.07663878622836025,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.000492,
|
||
|
|
"loss": 6.3699,
|
||
|
|
"mean_token_accuracy": 0.11762674301862716,
|
||
|
|
"num_tokens": 1709591.0,
|
||
|
|
"step": 985
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.861118412017822,
|
||
|
|
"epoch": 0.0770278156000778,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.0004945,
|
||
|
|
"loss": 6.6015,
|
||
|
|
"mean_token_accuracy": 0.10945382416248321,
|
||
|
|
"num_tokens": 1718951.0,
|
||
|
|
"step": 990
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.884693145751953,
|
||
|
|
"epoch": 0.07741684497179536,
|
||
|
|
"grad_norm": 1.265625,
|
||
|
|
"learning_rate": 0.000497,
|
||
|
|
"loss": 6.566,
|
||
|
|
"mean_token_accuracy": 0.11041911020874977,
|
||
|
|
"num_tokens": 1727481.0,
|
||
|
|
"step": 995
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.846743249893189,
|
||
|
|
"epoch": 0.07780587434351294,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.0004995,
|
||
|
|
"loss": 6.5609,
|
||
|
|
"mean_token_accuracy": 0.11417475417256355,
|
||
|
|
"num_tokens": 1736985.0,
|
||
|
|
"step": 1000
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.892654371261597,
|
||
|
|
"epoch": 0.0781949037152305,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0004999999989075146,
|
||
|
|
"loss": 6.6256,
|
||
|
|
"mean_token_accuracy": 0.11123185381293296,
|
||
|
|
"num_tokens": 1745470.0,
|
||
|
|
"step": 1005
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.851777601242065,
|
||
|
|
"epoch": 0.07858393308694807,
|
||
|
|
"grad_norm": 1.2109375,
|
||
|
|
"learning_rate": 0.0004999999944692927,
|
||
|
|
"loss": 6.5357,
|
||
|
|
"mean_token_accuracy": 0.10865053832530976,
|
||
|
|
"num_tokens": 1754185.0,
|
||
|
|
"step": 1010
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.776595211029052,
|
||
|
|
"epoch": 0.07897296245866563,
|
||
|
|
"grad_norm": 1.171875,
|
||
|
|
"learning_rate": 0.000499999986617054,
|
||
|
|
"loss": 6.546,
|
||
|
|
"mean_token_accuracy": 0.11072391048073768,
|
||
|
|
"num_tokens": 1762100.0,
|
||
|
|
"step": 1015
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.961122608184814,
|
||
|
|
"epoch": 0.0793619918303832,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.0004999999753507986,
|
||
|
|
"loss": 6.5689,
|
||
|
|
"mean_token_accuracy": 0.10964735001325607,
|
||
|
|
"num_tokens": 1771070.0,
|
||
|
|
"step": 1020
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.746126365661621,
|
||
|
|
"epoch": 0.07975102120210076,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.0004999999606705267,
|
||
|
|
"loss": 6.5597,
|
||
|
|
"mean_token_accuracy": 0.1127906545996666,
|
||
|
|
"num_tokens": 1780085.0,
|
||
|
|
"step": 1025
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.842060327529907,
|
||
|
|
"epoch": 0.08014005057381832,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0004999999425762385,
|
||
|
|
"loss": 6.5404,
|
||
|
|
"mean_token_accuracy": 0.11701353117823601,
|
||
|
|
"num_tokens": 1789316.0,
|
||
|
|
"step": 1030
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.778835821151733,
|
||
|
|
"epoch": 0.08052907994553589,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.0004999999210679344,
|
||
|
|
"loss": 6.475,
|
||
|
|
"mean_token_accuracy": 0.11409812644124032,
|
||
|
|
"num_tokens": 1797975.0,
|
||
|
|
"step": 1035
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.787038946151734,
|
||
|
|
"epoch": 0.08091810931725345,
|
||
|
|
"grad_norm": 1.15625,
|
||
|
|
"learning_rate": 0.0004999998961456145,
|
||
|
|
"loss": 6.5602,
|
||
|
|
"mean_token_accuracy": 0.11720341742038727,
|
||
|
|
"num_tokens": 1806129.0,
|
||
|
|
"step": 1040
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.956608533859253,
|
||
|
|
"epoch": 0.08130713868897102,
|
||
|
|
"grad_norm": 1.140625,
|
||
|
|
"learning_rate": 0.0004999998678092794,
|
||
|
|
"loss": 6.5564,
|
||
|
|
"mean_token_accuracy": 0.1117042988538742,
|
||
|
|
"num_tokens": 1813956.0,
|
||
|
|
"step": 1045
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.857865571975708,
|
||
|
|
"epoch": 0.08169616806068858,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0004999998360589293,
|
||
|
|
"loss": 6.5845,
|
||
|
|
"mean_token_accuracy": 0.11212223619222642,
|
||
|
|
"num_tokens": 1822572.0,
|
||
|
|
"step": 1050
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.7688240051269535,
|
||
|
|
"epoch": 0.08208519743240615,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.000499999800894565,
|
||
|
|
"loss": 6.4791,
|
||
|
|
"mean_token_accuracy": 0.11256719455122947,
|
||
|
|
"num_tokens": 1831870.0,
|
||
|
|
"step": 1055
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.68245153427124,
|
||
|
|
"epoch": 0.08247422680412371,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.0004999997623161866,
|
||
|
|
"loss": 6.5135,
|
||
|
|
"mean_token_accuracy": 0.1109384387731552,
|
||
|
|
"num_tokens": 1840414.0,
|
||
|
|
"step": 1060
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.897469997406006,
|
||
|
|
"epoch": 0.08286325617584128,
|
||
|
|
"grad_norm": 0.984375,
|
||
|
|
"learning_rate": 0.0004999997203237951,
|
||
|
|
"loss": 6.5357,
|
||
|
|
"mean_token_accuracy": 0.1112027607858181,
|
||
|
|
"num_tokens": 1850385.0,
|
||
|
|
"step": 1065
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.6467287063598635,
|
||
|
|
"epoch": 0.08325228554755884,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.000499999674917391,
|
||
|
|
"loss": 6.4407,
|
||
|
|
"mean_token_accuracy": 0.12009736895561218,
|
||
|
|
"num_tokens": 1858479.0,
|
||
|
|
"step": 1070
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.7970844268798825,
|
||
|
|
"epoch": 0.0836413149192764,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004999996260969748,
|
||
|
|
"loss": 6.5109,
|
||
|
|
"mean_token_accuracy": 0.11019074022769929,
|
||
|
|
"num_tokens": 1867357.0,
|
||
|
|
"step": 1075
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.754551267623901,
|
||
|
|
"epoch": 0.08403034429099397,
|
||
|
|
"grad_norm": 1.171875,
|
||
|
|
"learning_rate": 0.0004999995738625475,
|
||
|
|
"loss": 6.4736,
|
||
|
|
"mean_token_accuracy": 0.11016227900981904,
|
||
|
|
"num_tokens": 1876211.0,
|
||
|
|
"step": 1080
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.769411373138428,
|
||
|
|
"epoch": 0.08441937366271153,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004999995182141099,
|
||
|
|
"loss": 6.3942,
|
||
|
|
"mean_token_accuracy": 0.11268195807933808,
|
||
|
|
"num_tokens": 1884301.0,
|
||
|
|
"step": 1085
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.7784522533416744,
|
||
|
|
"epoch": 0.0848084030344291,
|
||
|
|
"grad_norm": 1.1796875,
|
||
|
|
"learning_rate": 0.0004999994591516626,
|
||
|
|
"loss": 6.5555,
|
||
|
|
"mean_token_accuracy": 0.11373023912310601,
|
||
|
|
"num_tokens": 1893191.0,
|
||
|
|
"step": 1090
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.673826599121094,
|
||
|
|
"epoch": 0.08519743240614666,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.0004999993966752066,
|
||
|
|
"loss": 6.4283,
|
||
|
|
"mean_token_accuracy": 0.11703478917479515,
|
||
|
|
"num_tokens": 1901434.0,
|
||
|
|
"step": 1095
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.760957384109497,
|
||
|
|
"epoch": 0.08558646177786423,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.000499999330784743,
|
||
|
|
"loss": 6.4054,
|
||
|
|
"mean_token_accuracy": 0.12261063754558563,
|
||
|
|
"num_tokens": 1910054.0,
|
||
|
|
"step": 1100
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.764858293533325,
|
||
|
|
"epoch": 0.08597549114958179,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.0004999992614802725,
|
||
|
|
"loss": 6.5472,
|
||
|
|
"mean_token_accuracy": 0.11576480343937874,
|
||
|
|
"num_tokens": 1918607.0,
|
||
|
|
"step": 1105
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.76983675956726,
|
||
|
|
"epoch": 0.08636452052129936,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.0004999991887617966,
|
||
|
|
"loss": 6.4969,
|
||
|
|
"mean_token_accuracy": 0.11678617969155311,
|
||
|
|
"num_tokens": 1927610.0,
|
||
|
|
"step": 1110
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.654897880554199,
|
||
|
|
"epoch": 0.08675354989301692,
|
||
|
|
"grad_norm": 1.1953125,
|
||
|
|
"learning_rate": 0.0004999991126293158,
|
||
|
|
"loss": 6.4455,
|
||
|
|
"mean_token_accuracy": 0.11631680354475975,
|
||
|
|
"num_tokens": 1936174.0,
|
||
|
|
"step": 1115
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.732142686843872,
|
||
|
|
"epoch": 0.08714257926473448,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.0004999990330828318,
|
||
|
|
"loss": 6.3693,
|
||
|
|
"mean_token_accuracy": 0.12286917939782142,
|
||
|
|
"num_tokens": 1944228.0,
|
||
|
|
"step": 1120
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.709880685806274,
|
||
|
|
"epoch": 0.08753160863645205,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.0004999989501223456,
|
||
|
|
"loss": 6.4821,
|
||
|
|
"mean_token_accuracy": 0.11934061720967293,
|
||
|
|
"num_tokens": 1953144.0,
|
||
|
|
"step": 1125
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.783202028274536,
|
||
|
|
"epoch": 0.08792063800816961,
|
||
|
|
"grad_norm": 1.1953125,
|
||
|
|
"learning_rate": 0.0004999988637478584,
|
||
|
|
"loss": 6.5277,
|
||
|
|
"mean_token_accuracy": 0.11476651057600976,
|
||
|
|
"num_tokens": 1961947.0,
|
||
|
|
"step": 1130
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.779601001739502,
|
||
|
|
"epoch": 0.08830966737988719,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.0004999987739593716,
|
||
|
|
"loss": 6.5028,
|
||
|
|
"mean_token_accuracy": 0.1122349627315998,
|
||
|
|
"num_tokens": 1970674.0,
|
||
|
|
"step": 1135
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.816339492797852,
|
||
|
|
"epoch": 0.08869869675160474,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.0004999986807568865,
|
||
|
|
"loss": 6.4793,
|
||
|
|
"mean_token_accuracy": 0.11963360384106636,
|
||
|
|
"num_tokens": 1979173.0,
|
||
|
|
"step": 1140
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.641682291030884,
|
||
|
|
"epoch": 0.08908772612332232,
|
||
|
|
"grad_norm": 1.203125,
|
||
|
|
"learning_rate": 0.0004999985841404045,
|
||
|
|
"loss": 6.4536,
|
||
|
|
"mean_token_accuracy": 0.11661232337355613,
|
||
|
|
"num_tokens": 1988134.0,
|
||
|
|
"step": 1145
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.796137905120849,
|
||
|
|
"epoch": 0.08947675549503988,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.0004999984841099271,
|
||
|
|
"loss": 6.4027,
|
||
|
|
"mean_token_accuracy": 0.11723847314715385,
|
||
|
|
"num_tokens": 1996977.0,
|
||
|
|
"step": 1150
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.740950250625611,
|
||
|
|
"epoch": 0.08986578486675743,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.000499998380665456,
|
||
|
|
"loss": 6.4805,
|
||
|
|
"mean_token_accuracy": 0.11753954589366913,
|
||
|
|
"num_tokens": 2005946.0,
|
||
|
|
"step": 1155
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.676974439620972,
|
||
|
|
"epoch": 0.090254814238475,
|
||
|
|
"grad_norm": 1.234375,
|
||
|
|
"learning_rate": 0.0004999982738069924,
|
||
|
|
"loss": 6.2987,
|
||
|
|
"mean_token_accuracy": 0.12011792436242104,
|
||
|
|
"num_tokens": 2014882.0,
|
||
|
|
"step": 1160
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.609836864471435,
|
||
|
|
"epoch": 0.09064384361019256,
|
||
|
|
"grad_norm": 1.1953125,
|
||
|
|
"learning_rate": 0.0004999981635345382,
|
||
|
|
"loss": 6.4888,
|
||
|
|
"mean_token_accuracy": 0.11186635941267013,
|
||
|
|
"num_tokens": 2024858.0,
|
||
|
|
"step": 1165
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.676596641540527,
|
||
|
|
"epoch": 0.09103287298191014,
|
||
|
|
"grad_norm": 1.203125,
|
||
|
|
"learning_rate": 0.0004999980498480949,
|
||
|
|
"loss": 6.4003,
|
||
|
|
"mean_token_accuracy": 0.11673102378845215,
|
||
|
|
"num_tokens": 2034072.0,
|
||
|
|
"step": 1170
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.680279922485352,
|
||
|
|
"epoch": 0.0914219023536277,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.0004999979327476644,
|
||
|
|
"loss": 6.4054,
|
||
|
|
"mean_token_accuracy": 0.11940634250640869,
|
||
|
|
"num_tokens": 2042649.0,
|
||
|
|
"step": 1175
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.699150514602661,
|
||
|
|
"epoch": 0.09181093172534527,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.0004999978122332485,
|
||
|
|
"loss": 6.4254,
|
||
|
|
"mean_token_accuracy": 0.12093920707702636,
|
||
|
|
"num_tokens": 2050866.0,
|
||
|
|
"step": 1180
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.7128864288330075,
|
||
|
|
"epoch": 0.09219996109706283,
|
||
|
|
"grad_norm": 1.1796875,
|
||
|
|
"learning_rate": 0.0004999976883048487,
|
||
|
|
"loss": 6.4421,
|
||
|
|
"mean_token_accuracy": 0.11782675310969352,
|
||
|
|
"num_tokens": 2058914.0,
|
||
|
|
"step": 1185
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.6109076023101805,
|
||
|
|
"epoch": 0.0925889904687804,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.0004999975609624673,
|
||
|
|
"loss": 6.3777,
|
||
|
|
"mean_token_accuracy": 0.11382007896900177,
|
||
|
|
"num_tokens": 2068098.0,
|
||
|
|
"step": 1190
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.656971406936646,
|
||
|
|
"epoch": 0.09297801984049796,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.0004999974302061059,
|
||
|
|
"loss": 6.3773,
|
||
|
|
"mean_token_accuracy": 0.11357153728604316,
|
||
|
|
"num_tokens": 2077299.0,
|
||
|
|
"step": 1195
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.678202056884766,
|
||
|
|
"epoch": 0.09336704921221552,
|
||
|
|
"grad_norm": 1.21875,
|
||
|
|
"learning_rate": 0.0004999972960357666,
|
||
|
|
"loss": 6.4757,
|
||
|
|
"mean_token_accuracy": 0.11248122900724411,
|
||
|
|
"num_tokens": 2087868.0,
|
||
|
|
"step": 1200
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.6500016212463375,
|
||
|
|
"epoch": 0.09375607858393309,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.0004999971584514516,
|
||
|
|
"loss": 6.3967,
|
||
|
|
"mean_token_accuracy": 0.12456627488136292,
|
||
|
|
"num_tokens": 2096553.0,
|
||
|
|
"step": 1205
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.7588951110839846,
|
||
|
|
"epoch": 0.09414510795565065,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.0004999970174531627,
|
||
|
|
"loss": 6.3727,
|
||
|
|
"mean_token_accuracy": 0.11930682808160782,
|
||
|
|
"num_tokens": 2104809.0,
|
||
|
|
"step": 1210
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.5227766036987305,
|
||
|
|
"epoch": 0.09453413732736822,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.0004999968730409022,
|
||
|
|
"loss": 6.3513,
|
||
|
|
"mean_token_accuracy": 0.11753158569335938,
|
||
|
|
"num_tokens": 2113869.0,
|
||
|
|
"step": 1215
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.59004921913147,
|
||
|
|
"epoch": 0.09492316669908578,
|
||
|
|
"grad_norm": 1.140625,
|
||
|
|
"learning_rate": 0.0004999967252146723,
|
||
|
|
"loss": 6.1845,
|
||
|
|
"mean_token_accuracy": 0.11563206911087036,
|
||
|
|
"num_tokens": 2121749.0,
|
||
|
|
"step": 1220
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.602604007720947,
|
||
|
|
"epoch": 0.09531219607080335,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.0004999965739744752,
|
||
|
|
"loss": 6.3919,
|
||
|
|
"mean_token_accuracy": 0.11459906175732612,
|
||
|
|
"num_tokens": 2130828.0,
|
||
|
|
"step": 1225
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.719199275970459,
|
||
|
|
"epoch": 0.09570122544252091,
|
||
|
|
"grad_norm": 1.1640625,
|
||
|
|
"learning_rate": 0.0004999964193203132,
|
||
|
|
"loss": 6.3664,
|
||
|
|
"mean_token_accuracy": 0.12008291706442834,
|
||
|
|
"num_tokens": 2138928.0,
|
||
|
|
"step": 1230
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.622300052642823,
|
||
|
|
"epoch": 0.09609025481423847,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.0004999962612521888,
|
||
|
|
"loss": 6.4103,
|
||
|
|
"mean_token_accuracy": 0.11864980831742286,
|
||
|
|
"num_tokens": 2147643.0,
|
||
|
|
"step": 1235
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.690579223632812,
|
||
|
|
"epoch": 0.09647928418595604,
|
||
|
|
"grad_norm": 0.98046875,
|
||
|
|
"learning_rate": 0.0004999960997701041,
|
||
|
|
"loss": 6.3286,
|
||
|
|
"mean_token_accuracy": 0.12595243826508523,
|
||
|
|
"num_tokens": 2156766.0,
|
||
|
|
"step": 1240
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.594869613647461,
|
||
|
|
"epoch": 0.0968683135576736,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004999959348740618,
|
||
|
|
"loss": 6.3937,
|
||
|
|
"mean_token_accuracy": 0.11976057812571525,
|
||
|
|
"num_tokens": 2165517.0,
|
||
|
|
"step": 1245
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.534668731689453,
|
||
|
|
"epoch": 0.09725734292939117,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.0004999957665640641,
|
||
|
|
"loss": 6.2614,
|
||
|
|
"mean_token_accuracy": 0.12245074957609177,
|
||
|
|
"num_tokens": 2174812.0,
|
||
|
|
"step": 1250
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.62302975654602,
|
||
|
|
"epoch": 0.09764637230110873,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.000499995594840114,
|
||
|
|
"loss": 6.3965,
|
||
|
|
"mean_token_accuracy": 0.11696946769952773,
|
||
|
|
"num_tokens": 2183968.0,
|
||
|
|
"step": 1255
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.6896251201629635,
|
||
|
|
"epoch": 0.0980354016728263,
|
||
|
|
"grad_norm": 1.171875,
|
||
|
|
"learning_rate": 0.0004999954197022138,
|
||
|
|
"loss": 6.4257,
|
||
|
|
"mean_token_accuracy": 0.12401301488280296,
|
||
|
|
"num_tokens": 2191947.0,
|
||
|
|
"step": 1260
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.606826972961426,
|
||
|
|
"epoch": 0.09842443104454386,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.0004999952411503661,
|
||
|
|
"loss": 6.271,
|
||
|
|
"mean_token_accuracy": 0.12751914858818053,
|
||
|
|
"num_tokens": 2199951.0,
|
||
|
|
"step": 1265
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.564306163787842,
|
||
|
|
"epoch": 0.09881346041626143,
|
||
|
|
"grad_norm": 1.1953125,
|
||
|
|
"learning_rate": 0.0004999950591845738,
|
||
|
|
"loss": 6.4197,
|
||
|
|
"mean_token_accuracy": 0.12145831063389778,
|
||
|
|
"num_tokens": 2208714.0,
|
||
|
|
"step": 1270
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.571636629104614,
|
||
|
|
"epoch": 0.09920248978797899,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004999948738048397,
|
||
|
|
"loss": 6.2797,
|
||
|
|
"mean_token_accuracy": 0.12155360877513885,
|
||
|
|
"num_tokens": 2217250.0,
|
||
|
|
"step": 1275
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.634035968780518,
|
||
|
|
"epoch": 0.09959151915969655,
|
||
|
|
"grad_norm": 1.2265625,
|
||
|
|
"learning_rate": 0.0004999946850111663,
|
||
|
|
"loss": 6.3297,
|
||
|
|
"mean_token_accuracy": 0.12339223623275757,
|
||
|
|
"num_tokens": 2225468.0,
|
||
|
|
"step": 1280
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.528422164916992,
|
||
|
|
"epoch": 0.09998054853141412,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.0004999944928035569,
|
||
|
|
"loss": 6.2904,
|
||
|
|
"mean_token_accuracy": 0.12815140709280967,
|
||
|
|
"num_tokens": 2233893.0,
|
||
|
|
"step": 1285
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.6666259765625,
|
||
|
|
"epoch": 0.10036957790313168,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 0.000499994297182014,
|
||
|
|
"loss": 6.3539,
|
||
|
|
"mean_token_accuracy": 0.12206242978572845,
|
||
|
|
"num_tokens": 2242487.0,
|
||
|
|
"step": 1290
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.534954357147217,
|
||
|
|
"epoch": 0.10075860727484925,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.0004999940981465408,
|
||
|
|
"loss": 6.1874,
|
||
|
|
"mean_token_accuracy": 0.12534248530864717,
|
||
|
|
"num_tokens": 2250518.0,
|
||
|
|
"step": 1295
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.555987071990967,
|
||
|
|
"epoch": 0.10114763664656681,
|
||
|
|
"grad_norm": 1.2109375,
|
||
|
|
"learning_rate": 0.0004999938956971404,
|
||
|
|
"loss": 6.3579,
|
||
|
|
"mean_token_accuracy": 0.11568900793790818,
|
||
|
|
"num_tokens": 2259024.0,
|
||
|
|
"step": 1300
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.613235092163086,
|
||
|
|
"epoch": 0.10153666601828439,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004999936898338156,
|
||
|
|
"loss": 6.4011,
|
||
|
|
"mean_token_accuracy": 0.11064468100666999,
|
||
|
|
"num_tokens": 2267832.0,
|
||
|
|
"step": 1305
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.580302953720093,
|
||
|
|
"epoch": 0.10192569539000194,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0004999934805565698,
|
||
|
|
"loss": 6.4644,
|
||
|
|
"mean_token_accuracy": 0.11155277863144875,
|
||
|
|
"num_tokens": 2276834.0,
|
||
|
|
"step": 1310
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.698448944091797,
|
||
|
|
"epoch": 0.10231472476171952,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.000499993267865406,
|
||
|
|
"loss": 6.3886,
|
||
|
|
"mean_token_accuracy": 0.11738630458712578,
|
||
|
|
"num_tokens": 2285736.0,
|
||
|
|
"step": 1315
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.663760614395142,
|
||
|
|
"epoch": 0.10270375413343708,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0004999930517603275,
|
||
|
|
"loss": 6.3469,
|
||
|
|
"mean_token_accuracy": 0.12696315422654153,
|
||
|
|
"num_tokens": 2294177.0,
|
||
|
|
"step": 1320
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.5038152694702145,
|
||
|
|
"epoch": 0.10309278350515463,
|
||
|
|
"grad_norm": 1.203125,
|
||
|
|
"learning_rate": 0.0004999928322413374,
|
||
|
|
"loss": 6.1338,
|
||
|
|
"mean_token_accuracy": 0.13216883465647697,
|
||
|
|
"num_tokens": 2302784.0,
|
||
|
|
"step": 1325
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.468310213088989,
|
||
|
|
"epoch": 0.1034818128768722,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.0004999926093084394,
|
||
|
|
"loss": 6.2448,
|
||
|
|
"mean_token_accuracy": 0.12271884679794312,
|
||
|
|
"num_tokens": 2311650.0,
|
||
|
|
"step": 1330
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.5902739524841305,
|
||
|
|
"epoch": 0.10387084224858976,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.0004999923829616365,
|
||
|
|
"loss": 6.3573,
|
||
|
|
"mean_token_accuracy": 0.12029535993933678,
|
||
|
|
"num_tokens": 2319828.0,
|
||
|
|
"step": 1335
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.606714200973511,
|
||
|
|
"epoch": 0.10425987162030734,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.0004999921532009323,
|
||
|
|
"loss": 6.3635,
|
||
|
|
"mean_token_accuracy": 0.1170631617307663,
|
||
|
|
"num_tokens": 2328636.0,
|
||
|
|
"step": 1340
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.487597703933716,
|
||
|
|
"epoch": 0.1046489009920249,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 0.0004999919200263304,
|
||
|
|
"loss": 6.2424,
|
||
|
|
"mean_token_accuracy": 0.12811223715543746,
|
||
|
|
"num_tokens": 2336771.0,
|
||
|
|
"step": 1345
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.611960554122925,
|
||
|
|
"epoch": 0.10503793036374247,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004999916834378342,
|
||
|
|
"loss": 6.388,
|
||
|
|
"mean_token_accuracy": 0.11745835095643997,
|
||
|
|
"num_tokens": 2346106.0,
|
||
|
|
"step": 1350
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.6681524276733395,
|
||
|
|
"epoch": 0.10542695973546003,
|
||
|
|
"grad_norm": 1.15625,
|
||
|
|
"learning_rate": 0.0004999914434354472,
|
||
|
|
"loss": 6.3915,
|
||
|
|
"mean_token_accuracy": 0.11755762621760368,
|
||
|
|
"num_tokens": 2354943.0,
|
||
|
|
"step": 1355
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.3937695026397705,
|
||
|
|
"epoch": 0.10581598910717759,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0004999912000191733,
|
||
|
|
"loss": 6.2812,
|
||
|
|
"mean_token_accuracy": 0.12295414507389069,
|
||
|
|
"num_tokens": 2363699.0,
|
||
|
|
"step": 1360
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.576402616500855,
|
||
|
|
"epoch": 0.10620501847889516,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.000499990953189016,
|
||
|
|
"loss": 6.4118,
|
||
|
|
"mean_token_accuracy": 0.11689253002405167,
|
||
|
|
"num_tokens": 2373316.0,
|
||
|
|
"step": 1365
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.740978050231933,
|
||
|
|
"epoch": 0.10659404785061272,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0004999907029449791,
|
||
|
|
"loss": 6.4907,
|
||
|
|
"mean_token_accuracy": 0.11326492577791214,
|
||
|
|
"num_tokens": 2381550.0,
|
||
|
|
"step": 1370
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.545381116867065,
|
||
|
|
"epoch": 0.10698307722233029,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004999904492870663,
|
||
|
|
"loss": 6.3081,
|
||
|
|
"mean_token_accuracy": 0.12226687595248223,
|
||
|
|
"num_tokens": 2389546.0,
|
||
|
|
"step": 1375
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.559665966033935,
|
||
|
|
"epoch": 0.10737210659404785,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.0004999901922152816,
|
||
|
|
"loss": 6.2522,
|
||
|
|
"mean_token_accuracy": 0.13022437021136285,
|
||
|
|
"num_tokens": 2398852.0,
|
||
|
|
"step": 1380
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.537785530090332,
|
||
|
|
"epoch": 0.10776113596576542,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0004999899317296288,
|
||
|
|
"loss": 6.341,
|
||
|
|
"mean_token_accuracy": 0.11776238903403283,
|
||
|
|
"num_tokens": 2407815.0,
|
||
|
|
"step": 1385
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.536812734603882,
|
||
|
|
"epoch": 0.10815016533748298,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004999896678301121,
|
||
|
|
"loss": 6.2117,
|
||
|
|
"mean_token_accuracy": 0.12601763755083084,
|
||
|
|
"num_tokens": 2417300.0,
|
||
|
|
"step": 1390
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.544566440582275,
|
||
|
|
"epoch": 0.10853919470920055,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.0004999894005167352,
|
||
|
|
"loss": 6.3687,
|
||
|
|
"mean_token_accuracy": 0.12166865617036819,
|
||
|
|
"num_tokens": 2426257.0,
|
||
|
|
"step": 1395
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.673711729049683,
|
||
|
|
"epoch": 0.10892822408091811,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.000499989129789502,
|
||
|
|
"loss": 6.3822,
|
||
|
|
"mean_token_accuracy": 0.12371926084160804,
|
||
|
|
"num_tokens": 2434595.0,
|
||
|
|
"step": 1400
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.637689447402954,
|
||
|
|
"epoch": 0.10931725345263567,
|
||
|
|
"grad_norm": 0.99609375,
|
||
|
|
"learning_rate": 0.0004999888556484172,
|
||
|
|
"loss": 6.3857,
|
||
|
|
"mean_token_accuracy": 0.12067539989948273,
|
||
|
|
"num_tokens": 2443945.0,
|
||
|
|
"step": 1405
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.449913835525512,
|
||
|
|
"epoch": 0.10970628282435324,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 0.0004999885780934845,
|
||
|
|
"loss": 6.2578,
|
||
|
|
"mean_token_accuracy": 0.12468339428305626,
|
||
|
|
"num_tokens": 2453141.0,
|
||
|
|
"step": 1410
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.639901494979858,
|
||
|
|
"epoch": 0.1100953121960708,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.0004999882971247081,
|
||
|
|
"loss": 6.3439,
|
||
|
|
"mean_token_accuracy": 0.11852156817913055,
|
||
|
|
"num_tokens": 2461873.0,
|
||
|
|
"step": 1415
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.518063354492187,
|
||
|
|
"epoch": 0.11048434156778837,
|
||
|
|
"grad_norm": 1.140625,
|
||
|
|
"learning_rate": 0.0004999880127420926,
|
||
|
|
"loss": 6.361,
|
||
|
|
"mean_token_accuracy": 0.1180450290441513,
|
||
|
|
"num_tokens": 2471238.0,
|
||
|
|
"step": 1420
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.570301914215088,
|
||
|
|
"epoch": 0.11087337093950593,
|
||
|
|
"grad_norm": 1.140625,
|
||
|
|
"learning_rate": 0.0004999877249456421,
|
||
|
|
"loss": 6.2637,
|
||
|
|
"mean_token_accuracy": 0.12611638382077217,
|
||
|
|
"num_tokens": 2479412.0,
|
||
|
|
"step": 1425
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.350358390808106,
|
||
|
|
"epoch": 0.1112624003112235,
|
||
|
|
"grad_norm": 1.171875,
|
||
|
|
"learning_rate": 0.0004999874337353609,
|
||
|
|
"loss": 6.1379,
|
||
|
|
"mean_token_accuracy": 0.1284614808857441,
|
||
|
|
"num_tokens": 2488150.0,
|
||
|
|
"step": 1430
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.525825834274292,
|
||
|
|
"epoch": 0.11165142968294106,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004999871391112535,
|
||
|
|
"loss": 6.3105,
|
||
|
|
"mean_token_accuracy": 0.12847553417086602,
|
||
|
|
"num_tokens": 2498103.0,
|
||
|
|
"step": 1435
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.43725700378418,
|
||
|
|
"epoch": 0.11204045905465862,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0004999868410733244,
|
||
|
|
"loss": 6.1815,
|
||
|
|
"mean_token_accuracy": 0.12891680896282195,
|
||
|
|
"num_tokens": 2506211.0,
|
||
|
|
"step": 1440
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.403781414031982,
|
||
|
|
"epoch": 0.11242948842637619,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.000499986539621578,
|
||
|
|
"loss": 6.2016,
|
||
|
|
"mean_token_accuracy": 0.12844212278723716,
|
||
|
|
"num_tokens": 2514743.0,
|
||
|
|
"step": 1445
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.451426029205322,
|
||
|
|
"epoch": 0.11281851779809375,
|
||
|
|
"grad_norm": 0.98046875,
|
||
|
|
"learning_rate": 0.0004999862347560191,
|
||
|
|
"loss": 6.2131,
|
||
|
|
"mean_token_accuracy": 0.11876050010323524,
|
||
|
|
"num_tokens": 2523824.0,
|
||
|
|
"step": 1450
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.63544545173645,
|
||
|
|
"epoch": 0.11320754716981132,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.0004999859264766521,
|
||
|
|
"loss": 6.2911,
|
||
|
|
"mean_token_accuracy": 0.11931056976318359,
|
||
|
|
"num_tokens": 2532360.0,
|
||
|
|
"step": 1455
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.430943727493286,
|
||
|
|
"epoch": 0.11359657654152888,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.0004999856147834817,
|
||
|
|
"loss": 6.2346,
|
||
|
|
"mean_token_accuracy": 0.12711054608225822,
|
||
|
|
"num_tokens": 2540547.0,
|
||
|
|
"step": 1460
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.486865091323852,
|
||
|
|
"epoch": 0.11398560591324645,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.0004999852996765129,
|
||
|
|
"loss": 6.2473,
|
||
|
|
"mean_token_accuracy": 0.12674545124173164,
|
||
|
|
"num_tokens": 2549193.0,
|
||
|
|
"step": 1465
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.464196062088012,
|
||
|
|
"epoch": 0.11437463528496401,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.0004999849811557502,
|
||
|
|
"loss": 6.2622,
|
||
|
|
"mean_token_accuracy": 0.12100255340337754,
|
||
|
|
"num_tokens": 2557553.0,
|
||
|
|
"step": 1470
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.629219913482666,
|
||
|
|
"epoch": 0.11476366465668159,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.0004999846592211984,
|
||
|
|
"loss": 6.3607,
|
||
|
|
"mean_token_accuracy": 0.12177548781037331,
|
||
|
|
"num_tokens": 2565945.0,
|
||
|
|
"step": 1475
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.536821985244751,
|
||
|
|
"epoch": 0.11515269402839914,
|
||
|
|
"grad_norm": 1.1953125,
|
||
|
|
"learning_rate": 0.0004999843338728626,
|
||
|
|
"loss": 6.2246,
|
||
|
|
"mean_token_accuracy": 0.12030538022518159,
|
||
|
|
"num_tokens": 2574364.0,
|
||
|
|
"step": 1480
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.438568162918091,
|
||
|
|
"epoch": 0.1155417234001167,
|
||
|
|
"grad_norm": 0.984375,
|
||
|
|
"learning_rate": 0.0004999840051107476,
|
||
|
|
"loss": 6.1639,
|
||
|
|
"mean_token_accuracy": 0.12257452458143234,
|
||
|
|
"num_tokens": 2582825.0,
|
||
|
|
"step": 1485
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.53958911895752,
|
||
|
|
"epoch": 0.11593075277183428,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.0004999836729348584,
|
||
|
|
"loss": 6.2992,
|
||
|
|
"mean_token_accuracy": 0.12617669850587845,
|
||
|
|
"num_tokens": 2591628.0,
|
||
|
|
"step": 1490
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.568798446655274,
|
||
|
|
"epoch": 0.11631978214355183,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0004999833373452,
|
||
|
|
"loss": 6.3072,
|
||
|
|
"mean_token_accuracy": 0.11595111265778542,
|
||
|
|
"num_tokens": 2600436.0,
|
||
|
|
"step": 1495
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.432466316223144,
|
||
|
|
"epoch": 0.1167088115152694,
|
||
|
|
"grad_norm": 1.15625,
|
||
|
|
"learning_rate": 0.0004999829983417778,
|
||
|
|
"loss": 6.2444,
|
||
|
|
"mean_token_accuracy": 0.1281425453722477,
|
||
|
|
"num_tokens": 2609709.0,
|
||
|
|
"step": 1500
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.624283027648926,
|
||
|
|
"epoch": 0.11709784088698696,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.0004999826559245965,
|
||
|
|
"loss": 6.2546,
|
||
|
|
"mean_token_accuracy": 0.12523326128721238,
|
||
|
|
"num_tokens": 2617992.0,
|
||
|
|
"step": 1505
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.3710126876831055,
|
||
|
|
"epoch": 0.11748687025870454,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004999823100936615,
|
||
|
|
"loss": 6.1762,
|
||
|
|
"mean_token_accuracy": 0.12328904047608376,
|
||
|
|
"num_tokens": 2626706.0,
|
||
|
|
"step": 1510
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.600048542022705,
|
||
|
|
"epoch": 0.1178758996304221,
|
||
|
|
"grad_norm": 1.1640625,
|
||
|
|
"learning_rate": 0.0004999819608489781,
|
||
|
|
"loss": 6.2453,
|
||
|
|
"mean_token_accuracy": 0.12911369353532792,
|
||
|
|
"num_tokens": 2634642.0,
|
||
|
|
"step": 1515
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.53199143409729,
|
||
|
|
"epoch": 0.11826492900213967,
|
||
|
|
"grad_norm": 0.98828125,
|
||
|
|
"learning_rate": 0.0004999816081905515,
|
||
|
|
"loss": 6.2789,
|
||
|
|
"mean_token_accuracy": 0.11790527626872063,
|
||
|
|
"num_tokens": 2644160.0,
|
||
|
|
"step": 1520
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.3495841979980465,
|
||
|
|
"epoch": 0.11865395837385723,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0004999812521183872,
|
||
|
|
"loss": 6.2528,
|
||
|
|
"mean_token_accuracy": 0.11885925233364106,
|
||
|
|
"num_tokens": 2653390.0,
|
||
|
|
"step": 1525
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.5672304153442385,
|
||
|
|
"epoch": 0.11904298774557479,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0004999808926324903,
|
||
|
|
"loss": 6.2957,
|
||
|
|
"mean_token_accuracy": 0.12170536145567894,
|
||
|
|
"num_tokens": 2662561.0,
|
||
|
|
"step": 1530
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.494124794006348,
|
||
|
|
"epoch": 0.11943201711729236,
|
||
|
|
"grad_norm": 1.1953125,
|
||
|
|
"learning_rate": 0.0004999805297328665,
|
||
|
|
"loss": 6.2467,
|
||
|
|
"mean_token_accuracy": 0.12452413216233253,
|
||
|
|
"num_tokens": 2670694.0,
|
||
|
|
"step": 1535
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.401147556304932,
|
||
|
|
"epoch": 0.11982104648900992,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.0004999801634195214,
|
||
|
|
"loss": 6.1463,
|
||
|
|
"mean_token_accuracy": 0.12829762995243071,
|
||
|
|
"num_tokens": 2679583.0,
|
||
|
|
"step": 1540
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.418363094329834,
|
||
|
|
"epoch": 0.12021007586072749,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.0004999797936924603,
|
||
|
|
"loss": 6.1377,
|
||
|
|
"mean_token_accuracy": 0.13158272877335547,
|
||
|
|
"num_tokens": 2688429.0,
|
||
|
|
"step": 1545
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.529831981658935,
|
||
|
|
"epoch": 0.12059910523244505,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.000499979420551689,
|
||
|
|
"loss": 6.2132,
|
||
|
|
"mean_token_accuracy": 0.12612780630588533,
|
||
|
|
"num_tokens": 2697134.0,
|
||
|
|
"step": 1550
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.446161222457886,
|
||
|
|
"epoch": 0.12098813460416262,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.000499979043997213,
|
||
|
|
"loss": 6.3499,
|
||
|
|
"mean_token_accuracy": 0.12430260628461838,
|
||
|
|
"num_tokens": 2705641.0,
|
||
|
|
"step": 1555
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.519960689544678,
|
||
|
|
"epoch": 0.12137716397588018,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0004999786640290381,
|
||
|
|
"loss": 6.2822,
|
||
|
|
"mean_token_accuracy": 0.13202693238854407,
|
||
|
|
"num_tokens": 2714977.0,
|
||
|
|
"step": 1560
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.495924043655395,
|
||
|
|
"epoch": 0.12176619334759774,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.0004999782806471701,
|
||
|
|
"loss": 6.1374,
|
||
|
|
"mean_token_accuracy": 0.13872739523649216,
|
||
|
|
"num_tokens": 2723120.0,
|
||
|
|
"step": 1565
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.295685195922852,
|
||
|
|
"epoch": 0.12215522271931531,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.0004999778938516147,
|
||
|
|
"loss": 6.1402,
|
||
|
|
"mean_token_accuracy": 0.13263760954141618,
|
||
|
|
"num_tokens": 2731964.0,
|
||
|
|
"step": 1570
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.6035463333129885,
|
||
|
|
"epoch": 0.12254425209103287,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.000499977503642378,
|
||
|
|
"loss": 6.1997,
|
||
|
|
"mean_token_accuracy": 0.12307174578309059,
|
||
|
|
"num_tokens": 2741537.0,
|
||
|
|
"step": 1575
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.387080717086792,
|
||
|
|
"epoch": 0.12293328146275044,
|
||
|
|
"grad_norm": 0.99609375,
|
||
|
|
"learning_rate": 0.0004999771100194656,
|
||
|
|
"loss": 6.313,
|
||
|
|
"mean_token_accuracy": 0.12455416470766068,
|
||
|
|
"num_tokens": 2751522.0,
|
||
|
|
"step": 1580
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.577677011489868,
|
||
|
|
"epoch": 0.123322310834468,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0004999767129828837,
|
||
|
|
"loss": 6.3166,
|
||
|
|
"mean_token_accuracy": 0.11798776909708977,
|
||
|
|
"num_tokens": 2761100.0,
|
||
|
|
"step": 1585
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.441084480285644,
|
||
|
|
"epoch": 0.12371134020618557,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.0004999763125326383,
|
||
|
|
"loss": 6.2427,
|
||
|
|
"mean_token_accuracy": 0.12579894289374352,
|
||
|
|
"num_tokens": 2769171.0,
|
||
|
|
"step": 1590
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.440652084350586,
|
||
|
|
"epoch": 0.12410036957790313,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0004999759086687355,
|
||
|
|
"loss": 6.1895,
|
||
|
|
"mean_token_accuracy": 0.12780183404684067,
|
||
|
|
"num_tokens": 2778021.0,
|
||
|
|
"step": 1595
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.3568809032440186,
|
||
|
|
"epoch": 0.1244893989496207,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0004999755013911813,
|
||
|
|
"loss": 6.1279,
|
||
|
|
"mean_token_accuracy": 0.12737615406513214,
|
||
|
|
"num_tokens": 2787206.0,
|
||
|
|
"step": 1600
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.398793506622314,
|
||
|
|
"epoch": 0.12487842832133826,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.000499975090699982,
|
||
|
|
"loss": 6.1907,
|
||
|
|
"mean_token_accuracy": 0.12401381433010102,
|
||
|
|
"num_tokens": 2796051.0,
|
||
|
|
"step": 1605
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.447634220123291,
|
||
|
|
"epoch": 0.12526745769305583,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004999746765951438,
|
||
|
|
"loss": 6.1438,
|
||
|
|
"mean_token_accuracy": 0.12876681834459305,
|
||
|
|
"num_tokens": 2804961.0,
|
||
|
|
"step": 1610
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.419821071624756,
|
||
|
|
"epoch": 0.1256564870647734,
|
||
|
|
"grad_norm": 1.1640625,
|
||
|
|
"learning_rate": 0.0004999742590766729,
|
||
|
|
"loss": 6.1004,
|
||
|
|
"mean_token_accuracy": 0.1357290342450142,
|
||
|
|
"num_tokens": 2813691.0,
|
||
|
|
"step": 1615
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.391876268386841,
|
||
|
|
"epoch": 0.12604551643649095,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.0004999738381445757,
|
||
|
|
"loss": 6.2317,
|
||
|
|
"mean_token_accuracy": 0.12731038108468057,
|
||
|
|
"num_tokens": 2822248.0,
|
||
|
|
"step": 1620
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.477704286575317,
|
||
|
|
"epoch": 0.1264345458082085,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004999734137988586,
|
||
|
|
"loss": 6.1942,
|
||
|
|
"mean_token_accuracy": 0.12995147630572318,
|
||
|
|
"num_tokens": 2830826.0,
|
||
|
|
"step": 1625
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.421813488006592,
|
||
|
|
"epoch": 0.1268235751799261,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.000499972986039528,
|
||
|
|
"loss": 6.1865,
|
||
|
|
"mean_token_accuracy": 0.12956878170371056,
|
||
|
|
"num_tokens": 2839766.0,
|
||
|
|
"step": 1630
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.311213779449463,
|
||
|
|
"epoch": 0.12721260455164365,
|
||
|
|
"grad_norm": 0.9765625,
|
||
|
|
"learning_rate": 0.0004999725548665904,
|
||
|
|
"loss": 6.1189,
|
||
|
|
"mean_token_accuracy": 0.1319350078701973,
|
||
|
|
"num_tokens": 2848728.0,
|
||
|
|
"step": 1635
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.348865556716919,
|
||
|
|
"epoch": 0.1276016339233612,
|
||
|
|
"grad_norm": 1.1640625,
|
||
|
|
"learning_rate": 0.0004999721202800524,
|
||
|
|
"loss": 6.1481,
|
||
|
|
"mean_token_accuracy": 0.12775396332144737,
|
||
|
|
"num_tokens": 2857221.0,
|
||
|
|
"step": 1640
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.470174407958984,
|
||
|
|
"epoch": 0.12799066329507877,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0004999716822799206,
|
||
|
|
"loss": 6.2085,
|
||
|
|
"mean_token_accuracy": 0.13055417835712432,
|
||
|
|
"num_tokens": 2865314.0,
|
||
|
|
"step": 1645
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.300682735443115,
|
||
|
|
"epoch": 0.12837969266679633,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 0.0004999712408662016,
|
||
|
|
"loss": 6.0805,
|
||
|
|
"mean_token_accuracy": 0.13145830407738684,
|
||
|
|
"num_tokens": 2873654.0,
|
||
|
|
"step": 1650
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.335351085662841,
|
||
|
|
"epoch": 0.12876872203851392,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.0004999707960389021,
|
||
|
|
"loss": 5.9957,
|
||
|
|
"mean_token_accuracy": 0.13766974061727524,
|
||
|
|
"num_tokens": 2881604.0,
|
||
|
|
"step": 1655
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.3854491233825685,
|
||
|
|
"epoch": 0.12915775141023147,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0004999703477980288,
|
||
|
|
"loss": 6.1897,
|
||
|
|
"mean_token_accuracy": 0.12948238775134085,
|
||
|
|
"num_tokens": 2890427.0,
|
||
|
|
"step": 1660
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.4016913890838625,
|
||
|
|
"epoch": 0.12954678078194903,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.0004999698961435885,
|
||
|
|
"loss": 6.1487,
|
||
|
|
"mean_token_accuracy": 0.12871672213077545,
|
||
|
|
"num_tokens": 2899206.0,
|
||
|
|
"step": 1665
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.379415559768677,
|
||
|
|
"epoch": 0.1299358101536666,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004999694410755882,
|
||
|
|
"loss": 6.0845,
|
||
|
|
"mean_token_accuracy": 0.13119084686040877,
|
||
|
|
"num_tokens": 2907738.0,
|
||
|
|
"step": 1670
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.384844398498535,
|
||
|
|
"epoch": 0.13032483952538418,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004999689825940347,
|
||
|
|
"loss": 6.2902,
|
||
|
|
"mean_token_accuracy": 0.12188465967774391,
|
||
|
|
"num_tokens": 2916881.0,
|
||
|
|
"step": 1675
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.461624526977539,
|
||
|
|
"epoch": 0.13071386889710174,
|
||
|
|
"grad_norm": 0.9765625,
|
||
|
|
"learning_rate": 0.0004999685206989349,
|
||
|
|
"loss": 6.2395,
|
||
|
|
"mean_token_accuracy": 0.1223972775042057,
|
||
|
|
"num_tokens": 2926467.0,
|
||
|
|
"step": 1680
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.4319689750671385,
|
||
|
|
"epoch": 0.1311028982688193,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.0004999680553902959,
|
||
|
|
"loss": 6.1786,
|
||
|
|
"mean_token_accuracy": 0.12664306312799453,
|
||
|
|
"num_tokens": 2934671.0,
|
||
|
|
"step": 1685
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.371197986602783,
|
||
|
|
"epoch": 0.13149192764053685,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.0004999675866681247,
|
||
|
|
"loss": 6.2,
|
||
|
|
"mean_token_accuracy": 0.12353175431489945,
|
||
|
|
"num_tokens": 2943925.0,
|
||
|
|
"step": 1690
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.441555547714233,
|
||
|
|
"epoch": 0.1318809570122544,
|
||
|
|
"grad_norm": 1.1875,
|
||
|
|
"learning_rate": 0.0004999671145324286,
|
||
|
|
"loss": 6.2338,
|
||
|
|
"mean_token_accuracy": 0.12637216970324516,
|
||
|
|
"num_tokens": 2952118.0,
|
||
|
|
"step": 1695
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.3267382144927975,
|
||
|
|
"epoch": 0.132269986383972,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0004999666389832144,
|
||
|
|
"loss": 6.2113,
|
||
|
|
"mean_token_accuracy": 0.12672000229358674,
|
||
|
|
"num_tokens": 2961110.0,
|
||
|
|
"step": 1700
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.460357189178467,
|
||
|
|
"epoch": 0.13265901575568956,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.0004999661600204897,
|
||
|
|
"loss": 6.1454,
|
||
|
|
"mean_token_accuracy": 0.13502151966094972,
|
||
|
|
"num_tokens": 2968877.0,
|
||
|
|
"step": 1705
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.44069094657898,
|
||
|
|
"epoch": 0.13304804512740712,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0004999656776442615,
|
||
|
|
"loss": 6.1976,
|
||
|
|
"mean_token_accuracy": 0.13004121631383897,
|
||
|
|
"num_tokens": 2977346.0,
|
||
|
|
"step": 1710
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.449344873428345,
|
||
|
|
"epoch": 0.13343707449912467,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.0004999651918545372,
|
||
|
|
"loss": 6.2464,
|
||
|
|
"mean_token_accuracy": 0.12166893184185028,
|
||
|
|
"num_tokens": 2987494.0,
|
||
|
|
"step": 1715
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.389680957794189,
|
||
|
|
"epoch": 0.13382610387084226,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.0004999647026513243,
|
||
|
|
"loss": 6.1548,
|
||
|
|
"mean_token_accuracy": 0.12699257507920264,
|
||
|
|
"num_tokens": 2996728.0,
|
||
|
|
"step": 1720
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.319113826751709,
|
||
|
|
"epoch": 0.13421513324255982,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.00049996421003463,
|
||
|
|
"loss": 6.1861,
|
||
|
|
"mean_token_accuracy": 0.12468351423740387,
|
||
|
|
"num_tokens": 3005810.0,
|
||
|
|
"step": 1725
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.385270690917968,
|
||
|
|
"epoch": 0.13460416261427738,
|
||
|
|
"grad_norm": 1.15625,
|
||
|
|
"learning_rate": 0.0004999637140044619,
|
||
|
|
"loss": 6.2053,
|
||
|
|
"mean_token_accuracy": 0.12655822560191154,
|
||
|
|
"num_tokens": 3014603.0,
|
||
|
|
"step": 1730
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.544794750213623,
|
||
|
|
"epoch": 0.13499319198599494,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.0004999632145608275,
|
||
|
|
"loss": 6.1965,
|
||
|
|
"mean_token_accuracy": 0.13691407367587088,
|
||
|
|
"num_tokens": 3023170.0,
|
||
|
|
"step": 1735
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.259229373931885,
|
||
|
|
"epoch": 0.1353822213577125,
|
||
|
|
"grad_norm": 1.140625,
|
||
|
|
"learning_rate": 0.0004999627117037343,
|
||
|
|
"loss": 5.9459,
|
||
|
|
"mean_token_accuracy": 0.13729629442095756,
|
||
|
|
"num_tokens": 3030565.0,
|
||
|
|
"step": 1740
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.357711887359619,
|
||
|
|
"epoch": 0.13577125072943008,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.00049996220543319,
|
||
|
|
"loss": 6.2181,
|
||
|
|
"mean_token_accuracy": 0.1307998225092888,
|
||
|
|
"num_tokens": 3040124.0,
|
||
|
|
"step": 1745
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.373897314071655,
|
||
|
|
"epoch": 0.13616028010114764,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0004999616957492025,
|
||
|
|
"loss": 6.0817,
|
||
|
|
"mean_token_accuracy": 0.13463346734642984,
|
||
|
|
"num_tokens": 3048458.0,
|
||
|
|
"step": 1750
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.304511833190918,
|
||
|
|
"epoch": 0.1365493094728652,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.0004999611826517793,
|
||
|
|
"loss": 6.0558,
|
||
|
|
"mean_token_accuracy": 0.12701260522007943,
|
||
|
|
"num_tokens": 3057926.0,
|
||
|
|
"step": 1755
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.371023035049438,
|
||
|
|
"epoch": 0.13693833884458276,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0004999606661409281,
|
||
|
|
"loss": 6.0875,
|
||
|
|
"mean_token_accuracy": 0.12731098383665085,
|
||
|
|
"num_tokens": 3066683.0,
|
||
|
|
"step": 1760
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.228750848770142,
|
||
|
|
"epoch": 0.13732736821630034,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.0004999601462166569,
|
||
|
|
"loss": 6.1605,
|
||
|
|
"mean_token_accuracy": 0.12849701195955276,
|
||
|
|
"num_tokens": 3075117.0,
|
||
|
|
"step": 1765
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.453361701965332,
|
||
|
|
"epoch": 0.1377163975880179,
|
||
|
|
"grad_norm": 0.9921875,
|
||
|
|
"learning_rate": 0.0004999596228789736,
|
||
|
|
"loss": 6.2112,
|
||
|
|
"mean_token_accuracy": 0.12286571562290191,
|
||
|
|
"num_tokens": 3084399.0,
|
||
|
|
"step": 1770
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.295282793045044,
|
||
|
|
"epoch": 0.13810542695973546,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.0004999590961278859,
|
||
|
|
"loss": 6.0036,
|
||
|
|
"mean_token_accuracy": 0.13310012146830558,
|
||
|
|
"num_tokens": 3093030.0,
|
||
|
|
"step": 1775
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.348547077178955,
|
||
|
|
"epoch": 0.13849445633145302,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004999585659634021,
|
||
|
|
"loss": 6.052,
|
||
|
|
"mean_token_accuracy": 0.13083661049604417,
|
||
|
|
"num_tokens": 3101670.0,
|
||
|
|
"step": 1780
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.234915637969971,
|
||
|
|
"epoch": 0.13888348570317058,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.0004999580323855301,
|
||
|
|
"loss": 6.0479,
|
||
|
|
"mean_token_accuracy": 0.13650041073560715,
|
||
|
|
"num_tokens": 3109703.0,
|
||
|
|
"step": 1785
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.281410074234008,
|
||
|
|
"epoch": 0.13927251507488816,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.0004999574953942781,
|
||
|
|
"loss": 6.0274,
|
||
|
|
"mean_token_accuracy": 0.13567775562405587,
|
||
|
|
"num_tokens": 3118388.0,
|
||
|
|
"step": 1790
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.353200960159302,
|
||
|
|
"epoch": 0.13966154444660572,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.0004999569549896541,
|
||
|
|
"loss": 6.0302,
|
||
|
|
"mean_token_accuracy": 0.13202294185757638,
|
||
|
|
"num_tokens": 3126466.0,
|
||
|
|
"step": 1795
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.298340797424316,
|
||
|
|
"epoch": 0.14005057381832328,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.0004999564111716665,
|
||
|
|
"loss": 6.0839,
|
||
|
|
"mean_token_accuracy": 0.1356653556227684,
|
||
|
|
"num_tokens": 3135322.0,
|
||
|
|
"step": 1800
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.337237930297851,
|
||
|
|
"epoch": 0.14043960319004084,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.0004999558639403232,
|
||
|
|
"loss": 6.0588,
|
||
|
|
"mean_token_accuracy": 0.1421361118555069,
|
||
|
|
"num_tokens": 3144498.0,
|
||
|
|
"step": 1805
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.217201280593872,
|
||
|
|
"epoch": 0.1408286325617584,
|
||
|
|
"grad_norm": 0.97265625,
|
||
|
|
"learning_rate": 0.0004999553132956328,
|
||
|
|
"loss": 6.0453,
|
||
|
|
"mean_token_accuracy": 0.1293400026857853,
|
||
|
|
"num_tokens": 3153573.0,
|
||
|
|
"step": 1810
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.2849945545196535,
|
||
|
|
"epoch": 0.14121766193347599,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.0004999547592376035,
|
||
|
|
"loss": 5.9778,
|
||
|
|
"mean_token_accuracy": 0.1387234814465046,
|
||
|
|
"num_tokens": 3161705.0,
|
||
|
|
"step": 1815
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.3220963954925535,
|
||
|
|
"epoch": 0.14160669130519354,
|
||
|
|
"grad_norm": 1.15625,
|
||
|
|
"learning_rate": 0.0004999542017662438,
|
||
|
|
"loss": 6.1431,
|
||
|
|
"mean_token_accuracy": 0.1342538885772228,
|
||
|
|
"num_tokens": 3170068.0,
|
||
|
|
"step": 1820
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.324667310714721,
|
||
|
|
"epoch": 0.1419957206769111,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004999536408815623,
|
||
|
|
"loss": 6.1425,
|
||
|
|
"mean_token_accuracy": 0.12565823644399643,
|
||
|
|
"num_tokens": 3178140.0,
|
||
|
|
"step": 1825
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.320392513275147,
|
||
|
|
"epoch": 0.14238475004862866,
|
||
|
|
"grad_norm": 1.15625,
|
||
|
|
"learning_rate": 0.0004999530765835672,
|
||
|
|
"loss": 6.1249,
|
||
|
|
"mean_token_accuracy": 0.13419567197561263,
|
||
|
|
"num_tokens": 3186518.0,
|
||
|
|
"step": 1830
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.2921764850616455,
|
||
|
|
"epoch": 0.14277377942034625,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.0004999525088722673,
|
||
|
|
"loss": 6.1074,
|
||
|
|
"mean_token_accuracy": 0.13023580014705657,
|
||
|
|
"num_tokens": 3195246.0,
|
||
|
|
"step": 1835
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.419817972183227,
|
||
|
|
"epoch": 0.1431628087920638,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.0004999519377476711,
|
||
|
|
"loss": 6.1211,
|
||
|
|
"mean_token_accuracy": 0.12776365801692008,
|
||
|
|
"num_tokens": 3203946.0,
|
||
|
|
"step": 1840
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.292534494400025,
|
||
|
|
"epoch": 0.14355183816378136,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.0004999513632097872,
|
||
|
|
"loss": 6.1428,
|
||
|
|
"mean_token_accuracy": 0.13157911524176596,
|
||
|
|
"num_tokens": 3212208.0,
|
||
|
|
"step": 1845
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.2916301727294925,
|
||
|
|
"epoch": 0.14394086753549892,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004999507852586245,
|
||
|
|
"loss": 6.0611,
|
||
|
|
"mean_token_accuracy": 0.1329232007265091,
|
||
|
|
"num_tokens": 3221572.0,
|
||
|
|
"step": 1850
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.4152443408966064,
|
||
|
|
"epoch": 0.14432989690721648,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.0004999502038941917,
|
||
|
|
"loss": 6.1794,
|
||
|
|
"mean_token_accuracy": 0.12200985550880432,
|
||
|
|
"num_tokens": 3230898.0,
|
||
|
|
"step": 1855
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.27156891822815,
|
||
|
|
"epoch": 0.14471892627893407,
|
||
|
|
"grad_norm": 0.9765625,
|
||
|
|
"learning_rate": 0.0004999496191164975,
|
||
|
|
"loss": 6.1572,
|
||
|
|
"mean_token_accuracy": 0.12799620404839515,
|
||
|
|
"num_tokens": 3240524.0,
|
||
|
|
"step": 1860
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.280993509292602,
|
||
|
|
"epoch": 0.14510795565065163,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.000499949030925551,
|
||
|
|
"loss": 5.926,
|
||
|
|
"mean_token_accuracy": 0.13632097840309143,
|
||
|
|
"num_tokens": 3248864.0,
|
||
|
|
"step": 1865
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.335269403457642,
|
||
|
|
"epoch": 0.14549698502236919,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.0004999484393213609,
|
||
|
|
"loss": 6.1133,
|
||
|
|
"mean_token_accuracy": 0.1336534596979618,
|
||
|
|
"num_tokens": 3256823.0,
|
||
|
|
"step": 1870
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.222145652770996,
|
||
|
|
"epoch": 0.14588601439408674,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004999478443039363,
|
||
|
|
"loss": 6.0304,
|
||
|
|
"mean_token_accuracy": 0.1363625131547451,
|
||
|
|
"num_tokens": 3265621.0,
|
||
|
|
"step": 1875
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.254001569747925,
|
||
|
|
"epoch": 0.14627504376580433,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.0004999472458732862,
|
||
|
|
"loss": 6.0469,
|
||
|
|
"mean_token_accuracy": 0.13533957973122596,
|
||
|
|
"num_tokens": 3273515.0,
|
||
|
|
"step": 1880
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.403596448898315,
|
||
|
|
"epoch": 0.1466640731375219,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.0004999466440294198,
|
||
|
|
"loss": 6.127,
|
||
|
|
"mean_token_accuracy": 0.13045344352722169,
|
||
|
|
"num_tokens": 3282283.0,
|
||
|
|
"step": 1885
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.232098484039307,
|
||
|
|
"epoch": 0.14705310250923945,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.000499946038772346,
|
||
|
|
"loss": 6.1111,
|
||
|
|
"mean_token_accuracy": 0.1315282925963402,
|
||
|
|
"num_tokens": 3290792.0,
|
||
|
|
"step": 1890
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.209755945205688,
|
||
|
|
"epoch": 0.147442131880957,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.0004999454301020741,
|
||
|
|
"loss": 5.9861,
|
||
|
|
"mean_token_accuracy": 0.13717192485928537,
|
||
|
|
"num_tokens": 3299430.0,
|
||
|
|
"step": 1895
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.237886095046997,
|
||
|
|
"epoch": 0.14783116125267456,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.0004999448180186133,
|
||
|
|
"loss": 6.0308,
|
||
|
|
"mean_token_accuracy": 0.13776149302721025,
|
||
|
|
"num_tokens": 3307949.0,
|
||
|
|
"step": 1900
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.336954259872437,
|
||
|
|
"epoch": 0.14822019062439215,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.000499944202521973,
|
||
|
|
"loss": 6.0864,
|
||
|
|
"mean_token_accuracy": 0.13430200293660163,
|
||
|
|
"num_tokens": 3316900.0,
|
||
|
|
"step": 1905
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.256044054031372,
|
||
|
|
"epoch": 0.1486092199961097,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004999435836121624,
|
||
|
|
"loss": 6.011,
|
||
|
|
"mean_token_accuracy": 0.14276451393961906,
|
||
|
|
"num_tokens": 3325656.0,
|
||
|
|
"step": 1910
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.280759811401367,
|
||
|
|
"epoch": 0.14899824936782727,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.000499942961289191,
|
||
|
|
"loss": 6.2337,
|
||
|
|
"mean_token_accuracy": 0.12067875787615776,
|
||
|
|
"num_tokens": 3334219.0,
|
||
|
|
"step": 1915
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.266615104675293,
|
||
|
|
"epoch": 0.14938727873954483,
|
||
|
|
"grad_norm": 0.96484375,
|
||
|
|
"learning_rate": 0.0004999423355530683,
|
||
|
|
"loss": 5.9838,
|
||
|
|
"mean_token_accuracy": 0.13729652389883995,
|
||
|
|
"num_tokens": 3343637.0,
|
||
|
|
"step": 1920
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.2604649543762205,
|
||
|
|
"epoch": 0.1497763081112624,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004999417064038035,
|
||
|
|
"loss": 6.1361,
|
||
|
|
"mean_token_accuracy": 0.13217737153172493,
|
||
|
|
"num_tokens": 3352624.0,
|
||
|
|
"step": 1925
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.27165207862854,
|
||
|
|
"epoch": 0.15016533748297997,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0004999410738414065,
|
||
|
|
"loss": 6.0498,
|
||
|
|
"mean_token_accuracy": 0.13848454281687736,
|
||
|
|
"num_tokens": 3361394.0,
|
||
|
|
"step": 1930
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.322489500045776,
|
||
|
|
"epoch": 0.15055436685469753,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.0004999404378658866,
|
||
|
|
"loss": 6.0933,
|
||
|
|
"mean_token_accuracy": 0.13730501234531403,
|
||
|
|
"num_tokens": 3369406.0,
|
||
|
|
"step": 1935
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.297638177871704,
|
||
|
|
"epoch": 0.1509433962264151,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0004999397984772536,
|
||
|
|
"loss": 6.0326,
|
||
|
|
"mean_token_accuracy": 0.1359100379049778,
|
||
|
|
"num_tokens": 3377737.0,
|
||
|
|
"step": 1940
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.2445666790008545,
|
||
|
|
"epoch": 0.15133242559813265,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004999391556755172,
|
||
|
|
"loss": 6.0976,
|
||
|
|
"mean_token_accuracy": 0.1317235164344311,
|
||
|
|
"num_tokens": 3385514.0,
|
||
|
|
"step": 1945
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.3746106147766115,
|
||
|
|
"epoch": 0.15172145496985023,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0004999385094606872,
|
||
|
|
"loss": 6.0018,
|
||
|
|
"mean_token_accuracy": 0.13859265744686128,
|
||
|
|
"num_tokens": 3394500.0,
|
||
|
|
"step": 1950
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.192457056045532,
|
||
|
|
"epoch": 0.1521104843415678,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.0004999378598327733,
|
||
|
|
"loss": 5.9877,
|
||
|
|
"mean_token_accuracy": 0.13467359468340873,
|
||
|
|
"num_tokens": 3403289.0,
|
||
|
|
"step": 1955
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.171674203872681,
|
||
|
|
"epoch": 0.15249951371328535,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0004999372067917854,
|
||
|
|
"loss": 5.9218,
|
||
|
|
"mean_token_accuracy": 0.1461538165807724,
|
||
|
|
"num_tokens": 3410892.0,
|
||
|
|
"step": 1960
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.118824768066406,
|
||
|
|
"epoch": 0.1528885430850029,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004999365503377335,
|
||
|
|
"loss": 6.0113,
|
||
|
|
"mean_token_accuracy": 0.1375325731933117,
|
||
|
|
"num_tokens": 3420329.0,
|
||
|
|
"step": 1965
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.259453964233399,
|
||
|
|
"epoch": 0.1532775724567205,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.0004999358904706273,
|
||
|
|
"loss": 6.0045,
|
||
|
|
"mean_token_accuracy": 0.13776946887373925,
|
||
|
|
"num_tokens": 3429429.0,
|
||
|
|
"step": 1970
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.2952652931213375,
|
||
|
|
"epoch": 0.15366660182843805,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.0004999352271904771,
|
||
|
|
"loss": 6.1282,
|
||
|
|
"mean_token_accuracy": 0.1321935884654522,
|
||
|
|
"num_tokens": 3438198.0,
|
||
|
|
"step": 1975
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.369889831542968,
|
||
|
|
"epoch": 0.1540556312001556,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.0004999345604972928,
|
||
|
|
"loss": 6.262,
|
||
|
|
"mean_token_accuracy": 0.13315195590257645,
|
||
|
|
"num_tokens": 3447732.0,
|
||
|
|
"step": 1980
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.301447629928589,
|
||
|
|
"epoch": 0.15444466057187317,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.0004999338903910846,
|
||
|
|
"loss": 6.027,
|
||
|
|
"mean_token_accuracy": 0.13421724662184714,
|
||
|
|
"num_tokens": 3456392.0,
|
||
|
|
"step": 1985
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.218537998199463,
|
||
|
|
"epoch": 0.15483368994359073,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.0004999332168718626,
|
||
|
|
"loss": 6.0684,
|
||
|
|
"mean_token_accuracy": 0.13393645808100701,
|
||
|
|
"num_tokens": 3464473.0,
|
||
|
|
"step": 1990
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.275947332382202,
|
||
|
|
"epoch": 0.15522271931530832,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.0004999325399396371,
|
||
|
|
"loss": 6.0328,
|
||
|
|
"mean_token_accuracy": 0.13263694792985917,
|
||
|
|
"num_tokens": 3473740.0,
|
||
|
|
"step": 1995
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.1024096488952635,
|
||
|
|
"epoch": 0.15561174868702587,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.0004999318595944183,
|
||
|
|
"loss": 5.9452,
|
||
|
|
"mean_token_accuracy": 0.13779015839099884,
|
||
|
|
"num_tokens": 3482249.0,
|
||
|
|
"step": 2000
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.3668300151824955,
|
||
|
|
"epoch": 0.15600077805874343,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.0004999311758362166,
|
||
|
|
"loss": 6.1654,
|
||
|
|
"mean_token_accuracy": 0.13282385990023612,
|
||
|
|
"num_tokens": 3490753.0,
|
||
|
|
"step": 2005
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.333145952224731,
|
||
|
|
"epoch": 0.156389807430461,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004999304886650422,
|
||
|
|
"loss": 6.1167,
|
||
|
|
"mean_token_accuracy": 0.13160909786820413,
|
||
|
|
"num_tokens": 3499373.0,
|
||
|
|
"step": 2010
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.249400472640991,
|
||
|
|
"epoch": 0.15677883680217858,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.0004999297980809058,
|
||
|
|
"loss": 6.0791,
|
||
|
|
"mean_token_accuracy": 0.12948477640748024,
|
||
|
|
"num_tokens": 3508344.0,
|
||
|
|
"step": 2015
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.3681032180786135,
|
||
|
|
"epoch": 0.15716786617389614,
|
||
|
|
"grad_norm": 0.9921875,
|
||
|
|
"learning_rate": 0.0004999291040838176,
|
||
|
|
"loss": 6.0576,
|
||
|
|
"mean_token_accuracy": 0.13269878849387168,
|
||
|
|
"num_tokens": 3517009.0,
|
||
|
|
"step": 2020
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.21099362373352,
|
||
|
|
"epoch": 0.1575568955456137,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.0004999284066737884,
|
||
|
|
"loss": 6.0727,
|
||
|
|
"mean_token_accuracy": 0.1345763050019741,
|
||
|
|
"num_tokens": 3525989.0,
|
||
|
|
"step": 2025
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.309366989135742,
|
||
|
|
"epoch": 0.15794592491733125,
|
||
|
|
"grad_norm": 1.15625,
|
||
|
|
"learning_rate": 0.0004999277058508285,
|
||
|
|
"loss": 5.96,
|
||
|
|
"mean_token_accuracy": 0.1353427805006504,
|
||
|
|
"num_tokens": 3533947.0,
|
||
|
|
"step": 2030
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.186928176879883,
|
||
|
|
"epoch": 0.1583349542890488,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.0004999270016149486,
|
||
|
|
"loss": 6.0351,
|
||
|
|
"mean_token_accuracy": 0.1369633160531521,
|
||
|
|
"num_tokens": 3541974.0,
|
||
|
|
"step": 2035
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.187212657928467,
|
||
|
|
"epoch": 0.1587239836607664,
|
||
|
|
"grad_norm": 1.203125,
|
||
|
|
"learning_rate": 0.0004999262939661596,
|
||
|
|
"loss": 5.9727,
|
||
|
|
"mean_token_accuracy": 0.14454701095819472,
|
||
|
|
"num_tokens": 3550436.0,
|
||
|
|
"step": 2040
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.289414739608764,
|
||
|
|
"epoch": 0.15911301303248396,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.0004999255829044721,
|
||
|
|
"loss": 5.9739,
|
||
|
|
"mean_token_accuracy": 0.13857920691370965,
|
||
|
|
"num_tokens": 3558283.0,
|
||
|
|
"step": 2045
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.116622686386108,
|
||
|
|
"epoch": 0.15950204240420152,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.0004999248684298968,
|
||
|
|
"loss": 5.8858,
|
||
|
|
"mean_token_accuracy": 0.144998886436224,
|
||
|
|
"num_tokens": 3566968.0,
|
||
|
|
"step": 2050
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.24771900177002,
|
||
|
|
"epoch": 0.15989107177591907,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0004999241505424447,
|
||
|
|
"loss": 6.0221,
|
||
|
|
"mean_token_accuracy": 0.13150276690721513,
|
||
|
|
"num_tokens": 3575580.0,
|
||
|
|
"step": 2055
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.248853874206543,
|
||
|
|
"epoch": 0.16028010114763663,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004999234292421265,
|
||
|
|
"loss": 6.101,
|
||
|
|
"mean_token_accuracy": 0.1321192666888237,
|
||
|
|
"num_tokens": 3584389.0,
|
||
|
|
"step": 2060
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.242433500289917,
|
||
|
|
"epoch": 0.16066913051935422,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004999227045289535,
|
||
|
|
"loss": 5.9212,
|
||
|
|
"mean_token_accuracy": 0.13805124387145043,
|
||
|
|
"num_tokens": 3593009.0,
|
||
|
|
"step": 2065
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.113874626159668,
|
||
|
|
"epoch": 0.16105815989107178,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.0004999219764029363,
|
||
|
|
"loss": 5.9619,
|
||
|
|
"mean_token_accuracy": 0.14041583985090256,
|
||
|
|
"num_tokens": 3601914.0,
|
||
|
|
"step": 2070
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.152489185333252,
|
||
|
|
"epoch": 0.16144718926278934,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.0004999212448640861,
|
||
|
|
"loss": 5.9363,
|
||
|
|
"mean_token_accuracy": 0.13822590857744216,
|
||
|
|
"num_tokens": 3609883.0,
|
||
|
|
"step": 2075
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.18636155128479,
|
||
|
|
"epoch": 0.1618362186345069,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.0004999205099124141,
|
||
|
|
"loss": 5.8719,
|
||
|
|
"mean_token_accuracy": 0.14322010651230813,
|
||
|
|
"num_tokens": 3618103.0,
|
||
|
|
"step": 2080
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.312455940246582,
|
||
|
|
"epoch": 0.16222524800622448,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.0004999197715479313,
|
||
|
|
"loss": 6.144,
|
||
|
|
"mean_token_accuracy": 0.13272519782185555,
|
||
|
|
"num_tokens": 3625861.0,
|
||
|
|
"step": 2085
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.127534246444702,
|
||
|
|
"epoch": 0.16261427737794204,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.0004999190297706489,
|
||
|
|
"loss": 5.9282,
|
||
|
|
"mean_token_accuracy": 0.13653620779514314,
|
||
|
|
"num_tokens": 3634498.0,
|
||
|
|
"step": 2090
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.104422616958618,
|
||
|
|
"epoch": 0.1630033067496596,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0004999182845805783,
|
||
|
|
"loss": 5.8667,
|
||
|
|
"mean_token_accuracy": 0.136298568546772,
|
||
|
|
"num_tokens": 3644186.0,
|
||
|
|
"step": 2095
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.148884201049805,
|
||
|
|
"epoch": 0.16339233612137716,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.0004999175359777306,
|
||
|
|
"loss": 6.0077,
|
||
|
|
"mean_token_accuracy": 0.13732302114367484,
|
||
|
|
"num_tokens": 3652831.0,
|
||
|
|
"step": 2100
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.29127516746521,
|
||
|
|
"epoch": 0.16378136549309472,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.0004999167839621174,
|
||
|
|
"loss": 5.8715,
|
||
|
|
"mean_token_accuracy": 0.14166171625256538,
|
||
|
|
"num_tokens": 3661230.0,
|
||
|
|
"step": 2105
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.123455286026001,
|
||
|
|
"epoch": 0.1641703948648123,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.0004999160285337501,
|
||
|
|
"loss": 6.0161,
|
||
|
|
"mean_token_accuracy": 0.13657576814293862,
|
||
|
|
"num_tokens": 3669250.0,
|
||
|
|
"step": 2110
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.189156150817871,
|
||
|
|
"epoch": 0.16455942423652986,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.0004999152696926399,
|
||
|
|
"loss": 5.9946,
|
||
|
|
"mean_token_accuracy": 0.13579504638910295,
|
||
|
|
"num_tokens": 3677568.0,
|
||
|
|
"step": 2115
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.241203927993775,
|
||
|
|
"epoch": 0.16494845360824742,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004999145074387985,
|
||
|
|
"loss": 5.9924,
|
||
|
|
"mean_token_accuracy": 0.1418316200375557,
|
||
|
|
"num_tokens": 3685488.0,
|
||
|
|
"step": 2120
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.1650886058807375,
|
||
|
|
"epoch": 0.16533748297996498,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004999137417722374,
|
||
|
|
"loss": 5.9612,
|
||
|
|
"mean_token_accuracy": 0.13932890743017196,
|
||
|
|
"num_tokens": 3694357.0,
|
||
|
|
"step": 2125
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.243571758270264,
|
||
|
|
"epoch": 0.16572651235168256,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.0004999129726929684,
|
||
|
|
"loss": 6.025,
|
||
|
|
"mean_token_accuracy": 0.13471606448292733,
|
||
|
|
"num_tokens": 3703173.0,
|
||
|
|
"step": 2130
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.174264240264892,
|
||
|
|
"epoch": 0.16611554172340012,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.0004999122002010029,
|
||
|
|
"loss": 6.0072,
|
||
|
|
"mean_token_accuracy": 0.13919395282864572,
|
||
|
|
"num_tokens": 3712070.0,
|
||
|
|
"step": 2135
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.181047868728638,
|
||
|
|
"epoch": 0.16650457109511768,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.0004999114242963527,
|
||
|
|
"loss": 5.9059,
|
||
|
|
"mean_token_accuracy": 0.14334050118923186,
|
||
|
|
"num_tokens": 3720245.0,
|
||
|
|
"step": 2140
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.130413055419922,
|
||
|
|
"epoch": 0.16689360046683524,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004999106449790298,
|
||
|
|
"loss": 5.9891,
|
||
|
|
"mean_token_accuracy": 0.13500823676586152,
|
||
|
|
"num_tokens": 3730064.0,
|
||
|
|
"step": 2145
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.13914041519165,
|
||
|
|
"epoch": 0.1672826298385528,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.0004999098622490458,
|
||
|
|
"loss": 5.9473,
|
||
|
|
"mean_token_accuracy": 0.1373259760439396,
|
||
|
|
"num_tokens": 3738741.0,
|
||
|
|
"step": 2150
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.230259609222412,
|
||
|
|
"epoch": 0.16767165921027039,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004999090761064125,
|
||
|
|
"loss": 6.0108,
|
||
|
|
"mean_token_accuracy": 0.13627254143357276,
|
||
|
|
"num_tokens": 3747472.0,
|
||
|
|
"step": 2155
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.231689691543579,
|
||
|
|
"epoch": 0.16806068858198794,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.000499908286551142,
|
||
|
|
"loss": 6.0384,
|
||
|
|
"mean_token_accuracy": 0.1343052066862583,
|
||
|
|
"num_tokens": 3756643.0,
|
||
|
|
"step": 2160
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.230075120925903,
|
||
|
|
"epoch": 0.1684497179537055,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.0004999074935832463,
|
||
|
|
"loss": 6.1358,
|
||
|
|
"mean_token_accuracy": 0.12708577439188956,
|
||
|
|
"num_tokens": 3765490.0,
|
||
|
|
"step": 2165
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.219008159637451,
|
||
|
|
"epoch": 0.16883874732542306,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.0004999066972027373,
|
||
|
|
"loss": 5.8962,
|
||
|
|
"mean_token_accuracy": 0.13918948471546172,
|
||
|
|
"num_tokens": 3773063.0,
|
||
|
|
"step": 2170
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.2020885944366455,
|
||
|
|
"epoch": 0.16922777669714065,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0004999058974096271,
|
||
|
|
"loss": 6.0591,
|
||
|
|
"mean_token_accuracy": 0.13676124885678292,
|
||
|
|
"num_tokens": 3781763.0,
|
||
|
|
"step": 2175
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.239950656890869,
|
||
|
|
"epoch": 0.1696168060688582,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.000499905094203928,
|
||
|
|
"loss": 6.0534,
|
||
|
|
"mean_token_accuracy": 0.13679237961769103,
|
||
|
|
"num_tokens": 3790582.0,
|
||
|
|
"step": 2180
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.150587844848633,
|
||
|
|
"epoch": 0.17000583544057576,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.000499904287585652,
|
||
|
|
"loss": 5.867,
|
||
|
|
"mean_token_accuracy": 0.1422402709722519,
|
||
|
|
"num_tokens": 3798745.0,
|
||
|
|
"step": 2185
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.110662794113159,
|
||
|
|
"epoch": 0.17039486481229332,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.0004999034775548113,
|
||
|
|
"loss": 5.9639,
|
||
|
|
"mean_token_accuracy": 0.1360377162694931,
|
||
|
|
"num_tokens": 3806901.0,
|
||
|
|
"step": 2190
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.1845409870147705,
|
||
|
|
"epoch": 0.17078389418401088,
|
||
|
|
"grad_norm": 1.3359375,
|
||
|
|
"learning_rate": 0.0004999026641114185,
|
||
|
|
"loss": 5.9155,
|
||
|
|
"mean_token_accuracy": 0.14578790441155434,
|
||
|
|
"num_tokens": 3815742.0,
|
||
|
|
"step": 2195
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.143110513687134,
|
||
|
|
"epoch": 0.17117292355572847,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004999018472554857,
|
||
|
|
"loss": 5.9944,
|
||
|
|
"mean_token_accuracy": 0.13587727323174476,
|
||
|
|
"num_tokens": 3824468.0,
|
||
|
|
"step": 2200
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.135712718963623,
|
||
|
|
"epoch": 0.17156195292744603,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0004999010269870253,
|
||
|
|
"loss": 5.9584,
|
||
|
|
"mean_token_accuracy": 0.143868188560009,
|
||
|
|
"num_tokens": 3832834.0,
|
||
|
|
"step": 2205
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.166628980636597,
|
||
|
|
"epoch": 0.17195098229916359,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0004999002033060498,
|
||
|
|
"loss": 5.9977,
|
||
|
|
"mean_token_accuracy": 0.14069228172302245,
|
||
|
|
"num_tokens": 3841780.0,
|
||
|
|
"step": 2210
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.188239908218383,
|
||
|
|
"epoch": 0.17234001167088114,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.0004998993762125716,
|
||
|
|
"loss": 6.1029,
|
||
|
|
"mean_token_accuracy": 0.13046709224581718,
|
||
|
|
"num_tokens": 3849840.0,
|
||
|
|
"step": 2215
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.256720972061157,
|
||
|
|
"epoch": 0.17272904104259873,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.0004998985457066034,
|
||
|
|
"loss": 6.0247,
|
||
|
|
"mean_token_accuracy": 0.13210274502635003,
|
||
|
|
"num_tokens": 3858204.0,
|
||
|
|
"step": 2220
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.179963779449463,
|
||
|
|
"epoch": 0.1731180704143163,
|
||
|
|
"grad_norm": 0.9375,
|
||
|
|
"learning_rate": 0.0004998977117881576,
|
||
|
|
"loss": 5.9783,
|
||
|
|
"mean_token_accuracy": 0.1354764722287655,
|
||
|
|
"num_tokens": 3866615.0,
|
||
|
|
"step": 2225
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.147153520584107,
|
||
|
|
"epoch": 0.17350709978603385,
|
||
|
|
"grad_norm": 0.921875,
|
||
|
|
"learning_rate": 0.0004998968744572472,
|
||
|
|
"loss": 6.0107,
|
||
|
|
"mean_token_accuracy": 0.14103505611419678,
|
||
|
|
"num_tokens": 3876003.0,
|
||
|
|
"step": 2230
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.217945766448975,
|
||
|
|
"epoch": 0.1738961291577514,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.0004998960337138845,
|
||
|
|
"loss": 5.9371,
|
||
|
|
"mean_token_accuracy": 0.14079653322696686,
|
||
|
|
"num_tokens": 3884362.0,
|
||
|
|
"step": 2235
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.073576307296753,
|
||
|
|
"epoch": 0.17428515852946896,
|
||
|
|
"grad_norm": 0.9609375,
|
||
|
|
"learning_rate": 0.0004998951895580826,
|
||
|
|
"loss": 5.897,
|
||
|
|
"mean_token_accuracy": 0.14070344492793083,
|
||
|
|
"num_tokens": 3893177.0,
|
||
|
|
"step": 2240
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.157261037826538,
|
||
|
|
"epoch": 0.17467418790118655,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.0004998943419898542,
|
||
|
|
"loss": 5.9474,
|
||
|
|
"mean_token_accuracy": 0.1386074975132942,
|
||
|
|
"num_tokens": 3903006.0,
|
||
|
|
"step": 2245
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.155741262435913,
|
||
|
|
"epoch": 0.1750632172729041,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.0004998934910092119,
|
||
|
|
"loss": 5.8105,
|
||
|
|
"mean_token_accuracy": 0.14036383107304573,
|
||
|
|
"num_tokens": 3912256.0,
|
||
|
|
"step": 2250
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.107159423828125,
|
||
|
|
"epoch": 0.17545224664462167,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0004998926366161689,
|
||
|
|
"loss": 5.9881,
|
||
|
|
"mean_token_accuracy": 0.13784814327955247,
|
||
|
|
"num_tokens": 3921121.0,
|
||
|
|
"step": 2255
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.162649297714234,
|
||
|
|
"epoch": 0.17584127601633923,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004998917788107383,
|
||
|
|
"loss": 5.936,
|
||
|
|
"mean_token_accuracy": 0.14180586934089662,
|
||
|
|
"num_tokens": 3929348.0,
|
||
|
|
"step": 2260
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.186119127273559,
|
||
|
|
"epoch": 0.17623030538805678,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.0004998909175929326,
|
||
|
|
"loss": 6.1057,
|
||
|
|
"mean_token_accuracy": 0.13549725115299224,
|
||
|
|
"num_tokens": 3938073.0,
|
||
|
|
"step": 2265
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.232157850265503,
|
||
|
|
"epoch": 0.17661933475977437,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0004998900529627653,
|
||
|
|
"loss": 6.0756,
|
||
|
|
"mean_token_accuracy": 0.13264880701899529,
|
||
|
|
"num_tokens": 3946641.0,
|
||
|
|
"step": 2270
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.23204550743103,
|
||
|
|
"epoch": 0.17700836413149193,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.0004998891849202495,
|
||
|
|
"loss": 5.9243,
|
||
|
|
"mean_token_accuracy": 0.14050190299749374,
|
||
|
|
"num_tokens": 3954586.0,
|
||
|
|
"step": 2275
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.094369125366211,
|
||
|
|
"epoch": 0.1773973935032095,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.000499888313465398,
|
||
|
|
"loss": 5.9946,
|
||
|
|
"mean_token_accuracy": 0.13950968906283379,
|
||
|
|
"num_tokens": 3963745.0,
|
||
|
|
"step": 2280
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.103000974655151,
|
||
|
|
"epoch": 0.17778642287492705,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.0004998874385982247,
|
||
|
|
"loss": 5.8128,
|
||
|
|
"mean_token_accuracy": 0.14982413798570632,
|
||
|
|
"num_tokens": 3972452.0,
|
||
|
|
"step": 2285
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.083374404907227,
|
||
|
|
"epoch": 0.17817545224664463,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.0004998865603187421,
|
||
|
|
"loss": 5.9248,
|
||
|
|
"mean_token_accuracy": 0.14283788874745368,
|
||
|
|
"num_tokens": 3980770.0,
|
||
|
|
"step": 2290
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.199732637405395,
|
||
|
|
"epoch": 0.1785644816183622,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.000499885678626964,
|
||
|
|
"loss": 5.9604,
|
||
|
|
"mean_token_accuracy": 0.13827717006206514,
|
||
|
|
"num_tokens": 3989545.0,
|
||
|
|
"step": 2295
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.1625518798828125,
|
||
|
|
"epoch": 0.17895351099007975,
|
||
|
|
"grad_norm": 0.98046875,
|
||
|
|
"learning_rate": 0.0004998847935229038,
|
||
|
|
"loss": 5.9269,
|
||
|
|
"mean_token_accuracy": 0.13749036863446235,
|
||
|
|
"num_tokens": 3998034.0,
|
||
|
|
"step": 2300
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.0795563697814945,
|
||
|
|
"epoch": 0.1793425403617973,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004998839050065746,
|
||
|
|
"loss": 5.9428,
|
||
|
|
"mean_token_accuracy": 0.1421938106417656,
|
||
|
|
"num_tokens": 4007110.0,
|
||
|
|
"step": 2305
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.205491638183593,
|
||
|
|
"epoch": 0.17973156973351487,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.0004998830130779902,
|
||
|
|
"loss": 6.0211,
|
||
|
|
"mean_token_accuracy": 0.1329338550567627,
|
||
|
|
"num_tokens": 4015930.0,
|
||
|
|
"step": 2310
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.017514371871949,
|
||
|
|
"epoch": 0.18012059910523245,
|
||
|
|
"grad_norm": 0.99609375,
|
||
|
|
"learning_rate": 0.000499882117737164,
|
||
|
|
"loss": 5.8263,
|
||
|
|
"mean_token_accuracy": 0.1466153845191002,
|
||
|
|
"num_tokens": 4024510.0,
|
||
|
|
"step": 2315
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.066116762161255,
|
||
|
|
"epoch": 0.18050962847695,
|
||
|
|
"grad_norm": 0.98046875,
|
||
|
|
"learning_rate": 0.0004998812189841096,
|
||
|
|
"loss": 5.9342,
|
||
|
|
"mean_token_accuracy": 0.13980292826890944,
|
||
|
|
"num_tokens": 4033714.0,
|
||
|
|
"step": 2320
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.282118463516236,
|
||
|
|
"epoch": 0.18089865784866757,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.0004998803168188407,
|
||
|
|
"loss": 6.1212,
|
||
|
|
"mean_token_accuracy": 0.1319077990949154,
|
||
|
|
"num_tokens": 4042376.0,
|
||
|
|
"step": 2325
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.0946657180786135,
|
||
|
|
"epoch": 0.18128768722038513,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.0004998794112413708,
|
||
|
|
"loss": 5.8755,
|
||
|
|
"mean_token_accuracy": 0.1430434338748455,
|
||
|
|
"num_tokens": 4050521.0,
|
||
|
|
"step": 2330
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.216298198699951,
|
||
|
|
"epoch": 0.18167671659210272,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.0004998785022517137,
|
||
|
|
"loss": 6.0448,
|
||
|
|
"mean_token_accuracy": 0.13777603581547737,
|
||
|
|
"num_tokens": 4059384.0,
|
||
|
|
"step": 2335
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.148222923278809,
|
||
|
|
"epoch": 0.18206574596382027,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.0004998775898498835,
|
||
|
|
"loss": 5.9296,
|
||
|
|
"mean_token_accuracy": 0.13958509340882302,
|
||
|
|
"num_tokens": 4067655.0,
|
||
|
|
"step": 2340
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.157079124450684,
|
||
|
|
"epoch": 0.18245477533553783,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.0004998766740358936,
|
||
|
|
"loss": 5.9141,
|
||
|
|
"mean_token_accuracy": 0.1455913409590721,
|
||
|
|
"num_tokens": 4075828.0,
|
||
|
|
"step": 2345
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.141853141784668,
|
||
|
|
"epoch": 0.1828438047072554,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.0004998757548097582,
|
||
|
|
"loss": 5.8682,
|
||
|
|
"mean_token_accuracy": 0.1426569327712059,
|
||
|
|
"num_tokens": 4083796.0,
|
||
|
|
"step": 2350
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.067271041870117,
|
||
|
|
"epoch": 0.18323283407897295,
|
||
|
|
"grad_norm": 0.98046875,
|
||
|
|
"learning_rate": 0.0004998748321714911,
|
||
|
|
"loss": 6.0011,
|
||
|
|
"mean_token_accuracy": 0.14092514365911485,
|
||
|
|
"num_tokens": 4092981.0,
|
||
|
|
"step": 2355
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.112659883499146,
|
||
|
|
"epoch": 0.18362186345069054,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.0004998739061211065,
|
||
|
|
"loss": 5.827,
|
||
|
|
"mean_token_accuracy": 0.14185563325881959,
|
||
|
|
"num_tokens": 4101363.0,
|
||
|
|
"step": 2360
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.115339231491089,
|
||
|
|
"epoch": 0.1840108928224081,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.0004998729766586181,
|
||
|
|
"loss": 5.9131,
|
||
|
|
"mean_token_accuracy": 0.14075915217399598,
|
||
|
|
"num_tokens": 4110164.0,
|
||
|
|
"step": 2365
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.212285280227661,
|
||
|
|
"epoch": 0.18439992219412565,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.0004998720437840403,
|
||
|
|
"loss": 6.0276,
|
||
|
|
"mean_token_accuracy": 0.13580502569675446,
|
||
|
|
"num_tokens": 4119098.0,
|
||
|
|
"step": 2370
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.153889179229736,
|
||
|
|
"epoch": 0.1847889515658432,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.0004998711074973871,
|
||
|
|
"loss": 5.9253,
|
||
|
|
"mean_token_accuracy": 0.14312097132205964,
|
||
|
|
"num_tokens": 4127522.0,
|
||
|
|
"step": 2375
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.095731449127197,
|
||
|
|
"epoch": 0.1851779809375608,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.0004998701677986728,
|
||
|
|
"loss": 5.9557,
|
||
|
|
"mean_token_accuracy": 0.1446719117462635,
|
||
|
|
"num_tokens": 4136311.0,
|
||
|
|
"step": 2380
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.094022607803344,
|
||
|
|
"epoch": 0.18556701030927836,
|
||
|
|
"grad_norm": 0.9765625,
|
||
|
|
"learning_rate": 0.0004998692246879116,
|
||
|
|
"loss": 5.8754,
|
||
|
|
"mean_token_accuracy": 0.14761602729558945,
|
||
|
|
"num_tokens": 4145160.0,
|
||
|
|
"step": 2385
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.067728042602539,
|
||
|
|
"epoch": 0.18595603968099592,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.0004998682781651178,
|
||
|
|
"loss": 5.8564,
|
||
|
|
"mean_token_accuracy": 0.14451601579785348,
|
||
|
|
"num_tokens": 4153921.0,
|
||
|
|
"step": 2390
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.078082847595215,
|
||
|
|
"epoch": 0.18634506905271347,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0004998673282303059,
|
||
|
|
"loss": 5.9202,
|
||
|
|
"mean_token_accuracy": 0.13949069231748581,
|
||
|
|
"num_tokens": 4162580.0,
|
||
|
|
"step": 2395
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.101584386825562,
|
||
|
|
"epoch": 0.18673409842443103,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004998663748834901,
|
||
|
|
"loss": 5.9162,
|
||
|
|
"mean_token_accuracy": 0.1455289751291275,
|
||
|
|
"num_tokens": 4170623.0,
|
||
|
|
"step": 2400
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.083553886413574,
|
||
|
|
"epoch": 0.18712312779614862,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.0004998654181246851,
|
||
|
|
"loss": 5.9049,
|
||
|
|
"mean_token_accuracy": 0.1480133354663849,
|
||
|
|
"num_tokens": 4178724.0,
|
||
|
|
"step": 2405
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.097364902496338,
|
||
|
|
"epoch": 0.18751215716786618,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.0004998644579539052,
|
||
|
|
"loss": 5.9147,
|
||
|
|
"mean_token_accuracy": 0.1468910664319992,
|
||
|
|
"num_tokens": 4187773.0,
|
||
|
|
"step": 2410
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.116354370117188,
|
||
|
|
"epoch": 0.18790118653958374,
|
||
|
|
"grad_norm": 0.9921875,
|
||
|
|
"learning_rate": 0.000499863494371165,
|
||
|
|
"loss": 5.9139,
|
||
|
|
"mean_token_accuracy": 0.13767781779170035,
|
||
|
|
"num_tokens": 4196628.0,
|
||
|
|
"step": 2415
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.088314533233643,
|
||
|
|
"epoch": 0.1882902159113013,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.0004998625273764793,
|
||
|
|
"loss": 5.9477,
|
||
|
|
"mean_token_accuracy": 0.13856262788176538,
|
||
|
|
"num_tokens": 4205090.0,
|
||
|
|
"step": 2420
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.103470802307129,
|
||
|
|
"epoch": 0.18867924528301888,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0004998615569698626,
|
||
|
|
"loss": 5.8589,
|
||
|
|
"mean_token_accuracy": 0.143842813372612,
|
||
|
|
"num_tokens": 4212757.0,
|
||
|
|
"step": 2425
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.075373220443725,
|
||
|
|
"epoch": 0.18906827465473644,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.0004998605831513296,
|
||
|
|
"loss": 5.9298,
|
||
|
|
"mean_token_accuracy": 0.14338203594088555,
|
||
|
|
"num_tokens": 4221556.0,
|
||
|
|
"step": 2430
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.053972434997559,
|
||
|
|
"epoch": 0.189457304026454,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004998596059208953,
|
||
|
|
"loss": 5.9098,
|
||
|
|
"mean_token_accuracy": 0.14371097087860107,
|
||
|
|
"num_tokens": 4231524.0,
|
||
|
|
"step": 2435
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.094544792175293,
|
||
|
|
"epoch": 0.18984633339817156,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.0004998586252785743,
|
||
|
|
"loss": 5.9522,
|
||
|
|
"mean_token_accuracy": 0.14406583532691003,
|
||
|
|
"num_tokens": 4240229.0,
|
||
|
|
"step": 2440
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.133808565139771,
|
||
|
|
"epoch": 0.19023536276988912,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004998576412243816,
|
||
|
|
"loss": 5.8211,
|
||
|
|
"mean_token_accuracy": 0.14667747020721436,
|
||
|
|
"num_tokens": 4248053.0,
|
||
|
|
"step": 2445
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.111063623428345,
|
||
|
|
"epoch": 0.1906243921416067,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004998566537583321,
|
||
|
|
"loss": 5.8754,
|
||
|
|
"mean_token_accuracy": 0.14372672364115716,
|
||
|
|
"num_tokens": 4256019.0,
|
||
|
|
"step": 2450
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.058719348907471,
|
||
|
|
"epoch": 0.19101342151332426,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.0004998556628804408,
|
||
|
|
"loss": 5.8515,
|
||
|
|
"mean_token_accuracy": 0.14850348010659217,
|
||
|
|
"num_tokens": 4263805.0,
|
||
|
|
"step": 2455
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.0601448059082035,
|
||
|
|
"epoch": 0.19140245088504182,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.0004998546685907225,
|
||
|
|
"loss": 5.9217,
|
||
|
|
"mean_token_accuracy": 0.14053093194961547,
|
||
|
|
"num_tokens": 4272712.0,
|
||
|
|
"step": 2460
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.184451723098755,
|
||
|
|
"epoch": 0.19179148025675938,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004998536708891927,
|
||
|
|
"loss": 5.8494,
|
||
|
|
"mean_token_accuracy": 0.14523410499095918,
|
||
|
|
"num_tokens": 4281222.0,
|
||
|
|
"step": 2465
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.039083003997803,
|
||
|
|
"epoch": 0.19218050962847694,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.0004998526697758663,
|
||
|
|
"loss": 5.9574,
|
||
|
|
"mean_token_accuracy": 0.1356569655239582,
|
||
|
|
"num_tokens": 4290558.0,
|
||
|
|
"step": 2470
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.214207363128662,
|
||
|
|
"epoch": 0.19256953900019452,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0004998516652507585,
|
||
|
|
"loss": 5.992,
|
||
|
|
"mean_token_accuracy": 0.1386689119040966,
|
||
|
|
"num_tokens": 4299684.0,
|
||
|
|
"step": 2475
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.056800842285156,
|
||
|
|
"epoch": 0.19295856837191208,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.0004998506573138846,
|
||
|
|
"loss": 5.9337,
|
||
|
|
"mean_token_accuracy": 0.14160904437303543,
|
||
|
|
"num_tokens": 4308938.0,
|
||
|
|
"step": 2480
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.002795457839966,
|
||
|
|
"epoch": 0.19334759774362964,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.0004998496459652598,
|
||
|
|
"loss": 5.7948,
|
||
|
|
"mean_token_accuracy": 0.1451106436550617,
|
||
|
|
"num_tokens": 4317646.0,
|
||
|
|
"step": 2485
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.065030527114868,
|
||
|
|
"epoch": 0.1937366271153472,
|
||
|
|
"grad_norm": 0.99609375,
|
||
|
|
"learning_rate": 0.0004998486312048995,
|
||
|
|
"loss": 5.9336,
|
||
|
|
"mean_token_accuracy": 0.13834921047091484,
|
||
|
|
"num_tokens": 4326876.0,
|
||
|
|
"step": 2490
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.060744047164917,
|
||
|
|
"epoch": 0.19412565648706478,
|
||
|
|
"grad_norm": 0.96484375,
|
||
|
|
"learning_rate": 0.0004998476130328193,
|
||
|
|
"loss": 5.8946,
|
||
|
|
"mean_token_accuracy": 0.1431366868317127,
|
||
|
|
"num_tokens": 4335391.0,
|
||
|
|
"step": 2495
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.179794597625732,
|
||
|
|
"epoch": 0.19451468585878234,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004998465914490343,
|
||
|
|
"loss": 5.876,
|
||
|
|
"mean_token_accuracy": 0.1446529857814312,
|
||
|
|
"num_tokens": 4343253.0,
|
||
|
|
"step": 2500
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.931164121627807,
|
||
|
|
"epoch": 0.1949037152304999,
|
||
|
|
"grad_norm": 0.97265625,
|
||
|
|
"learning_rate": 0.00049984556645356,
|
||
|
|
"loss": 5.8497,
|
||
|
|
"mean_token_accuracy": 0.14115574061870576,
|
||
|
|
"num_tokens": 4352161.0,
|
||
|
|
"step": 2505
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.055073976516724,
|
||
|
|
"epoch": 0.19529274460221746,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004998445380464124,
|
||
|
|
"loss": 5.8066,
|
||
|
|
"mean_token_accuracy": 0.15022924542427063,
|
||
|
|
"num_tokens": 4360414.0,
|
||
|
|
"step": 2510
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.062896585464477,
|
||
|
|
"epoch": 0.19568177397393502,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.0004998435062276066,
|
||
|
|
"loss": 5.7918,
|
||
|
|
"mean_token_accuracy": 0.1486874118447304,
|
||
|
|
"num_tokens": 4369375.0,
|
||
|
|
"step": 2515
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.977962446212769,
|
||
|
|
"epoch": 0.1960708033456526,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.0004998424709971586,
|
||
|
|
"loss": 5.8276,
|
||
|
|
"mean_token_accuracy": 0.14558200165629387,
|
||
|
|
"num_tokens": 4378638.0,
|
||
|
|
"step": 2520
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.117749452590942,
|
||
|
|
"epoch": 0.19645983271737016,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004998414323550839,
|
||
|
|
"loss": 5.8265,
|
||
|
|
"mean_token_accuracy": 0.1476297803223133,
|
||
|
|
"num_tokens": 4388262.0,
|
||
|
|
"step": 2525
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.057101821899414,
|
||
|
|
"epoch": 0.19684886208908772,
|
||
|
|
"grad_norm": 0.98828125,
|
||
|
|
"learning_rate": 0.0004998403903013984,
|
||
|
|
"loss": 5.8196,
|
||
|
|
"mean_token_accuracy": 0.14260421246290206,
|
||
|
|
"num_tokens": 4396894.0,
|
||
|
|
"step": 2530
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.098726224899292,
|
||
|
|
"epoch": 0.19723789146080528,
|
||
|
|
"grad_norm": 0.9375,
|
||
|
|
"learning_rate": 0.0004998393448361179,
|
||
|
|
"loss": 5.9515,
|
||
|
|
"mean_token_accuracy": 0.14099942818284034,
|
||
|
|
"num_tokens": 4405455.0,
|
||
|
|
"step": 2535
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.090051698684692,
|
||
|
|
"epoch": 0.19762692083252287,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 0.000499838295959258,
|
||
|
|
"loss": 5.8408,
|
||
|
|
"mean_token_accuracy": 0.14691002145409585,
|
||
|
|
"num_tokens": 4414355.0,
|
||
|
|
"step": 2540
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.944388818740845,
|
||
|
|
"epoch": 0.19801595020424043,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.000499837243670835,
|
||
|
|
"loss": 5.7418,
|
||
|
|
"mean_token_accuracy": 0.15249036699533464,
|
||
|
|
"num_tokens": 4422305.0,
|
||
|
|
"step": 2545
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.083198404312133,
|
||
|
|
"epoch": 0.19840497957595798,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.0004998361879708646,
|
||
|
|
"loss": 5.8824,
|
||
|
|
"mean_token_accuracy": 0.14111227691173553,
|
||
|
|
"num_tokens": 4430813.0,
|
||
|
|
"step": 2550
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.062122344970703,
|
||
|
|
"epoch": 0.19879400894767554,
|
||
|
|
"grad_norm": 0.9765625,
|
||
|
|
"learning_rate": 0.000499835128859363,
|
||
|
|
"loss": 5.845,
|
||
|
|
"mean_token_accuracy": 0.1449693761765957,
|
||
|
|
"num_tokens": 4440229.0,
|
||
|
|
"step": 2555
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.969413232803345,
|
||
|
|
"epoch": 0.1991830383193931,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.0004998340663363461,
|
||
|
|
"loss": 5.8636,
|
||
|
|
"mean_token_accuracy": 0.14286035373806955,
|
||
|
|
"num_tokens": 4449417.0,
|
||
|
|
"step": 2560
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.115420150756836,
|
||
|
|
"epoch": 0.1995720676911107,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0004998330004018301,
|
||
|
|
"loss": 5.9049,
|
||
|
|
"mean_token_accuracy": 0.14032256752252578,
|
||
|
|
"num_tokens": 4457377.0,
|
||
|
|
"step": 2565
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.076362800598145,
|
||
|
|
"epoch": 0.19996109706282825,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004998319310558312,
|
||
|
|
"loss": 5.8205,
|
||
|
|
"mean_token_accuracy": 0.14231560602784157,
|
||
|
|
"num_tokens": 4466839.0,
|
||
|
|
"step": 2570
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.02218279838562,
|
||
|
|
"epoch": 0.2003501264345458,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.0004998308582983657,
|
||
|
|
"loss": 5.8572,
|
||
|
|
"mean_token_accuracy": 0.14494595527648926,
|
||
|
|
"num_tokens": 4476369.0,
|
||
|
|
"step": 2575
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.032584857940674,
|
||
|
|
"epoch": 0.20073915580626336,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.0004998297821294497,
|
||
|
|
"loss": 5.921,
|
||
|
|
"mean_token_accuracy": 0.14298095181584358,
|
||
|
|
"num_tokens": 4485609.0,
|
||
|
|
"step": 2580
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.070321846008301,
|
||
|
|
"epoch": 0.20112818517798095,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.0004998287025490995,
|
||
|
|
"loss": 5.873,
|
||
|
|
"mean_token_accuracy": 0.14022249430418016,
|
||
|
|
"num_tokens": 4494535.0,
|
||
|
|
"step": 2585
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.069472455978394,
|
||
|
|
"epoch": 0.2015172145496985,
|
||
|
|
"grad_norm": 0.95703125,
|
||
|
|
"learning_rate": 0.0004998276195573317,
|
||
|
|
"loss": 5.8392,
|
||
|
|
"mean_token_accuracy": 0.1400721177458763,
|
||
|
|
"num_tokens": 4503133.0,
|
||
|
|
"step": 2590
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.981370306015014,
|
||
|
|
"epoch": 0.20190624392141607,
|
||
|
|
"grad_norm": 0.94140625,
|
||
|
|
"learning_rate": 0.0004998265331541627,
|
||
|
|
"loss": 5.7476,
|
||
|
|
"mean_token_accuracy": 0.15337812453508376,
|
||
|
|
"num_tokens": 4511465.0,
|
||
|
|
"step": 2595
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.02926983833313,
|
||
|
|
"epoch": 0.20229527329313363,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0004998254433396088,
|
||
|
|
"loss": 5.8029,
|
||
|
|
"mean_token_accuracy": 0.14853528290987014,
|
||
|
|
"num_tokens": 4520177.0,
|
||
|
|
"step": 2600
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.066452360153198,
|
||
|
|
"epoch": 0.20268430266485118,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0004998243501136867,
|
||
|
|
"loss": 5.9622,
|
||
|
|
"mean_token_accuracy": 0.14383991807699203,
|
||
|
|
"num_tokens": 4528370.0,
|
||
|
|
"step": 2605
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.163117504119873,
|
||
|
|
"epoch": 0.20307333203656877,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0004998232534764129,
|
||
|
|
"loss": 5.99,
|
||
|
|
"mean_token_accuracy": 0.13582537844777107,
|
||
|
|
"num_tokens": 4538258.0,
|
||
|
|
"step": 2610
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.0580810546875,
|
||
|
|
"epoch": 0.20346236140828633,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004998221534278041,
|
||
|
|
"loss": 5.8843,
|
||
|
|
"mean_token_accuracy": 0.14223846048116684,
|
||
|
|
"num_tokens": 4547300.0,
|
||
|
|
"step": 2615
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.087620735168457,
|
||
|
|
"epoch": 0.2038513907800039,
|
||
|
|
"grad_norm": 0.9453125,
|
||
|
|
"learning_rate": 0.0004998210499678769,
|
||
|
|
"loss": 5.9576,
|
||
|
|
"mean_token_accuracy": 0.13359709531068803,
|
||
|
|
"num_tokens": 4556877.0,
|
||
|
|
"step": 2620
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.031925868988037,
|
||
|
|
"epoch": 0.20424042015172145,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.0004998199430966481,
|
||
|
|
"loss": 5.8074,
|
||
|
|
"mean_token_accuracy": 0.1435726575553417,
|
||
|
|
"num_tokens": 4565999.0,
|
||
|
|
"step": 2625
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.016840887069702,
|
||
|
|
"epoch": 0.20462944952343903,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.0004998188328141346,
|
||
|
|
"loss": 5.8493,
|
||
|
|
"mean_token_accuracy": 0.13968632593750954,
|
||
|
|
"num_tokens": 4574027.0,
|
||
|
|
"step": 2630
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.995946645736694,
|
||
|
|
"epoch": 0.2050184788951566,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0004998177191203531,
|
||
|
|
"loss": 5.8536,
|
||
|
|
"mean_token_accuracy": 0.13539135009050368,
|
||
|
|
"num_tokens": 4582402.0,
|
||
|
|
"step": 2635
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.051613092422485,
|
||
|
|
"epoch": 0.20540750826687415,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.0004998166020153204,
|
||
|
|
"loss": 5.8055,
|
||
|
|
"mean_token_accuracy": 0.14385574758052827,
|
||
|
|
"num_tokens": 4590381.0,
|
||
|
|
"step": 2640
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.0391960620880125,
|
||
|
|
"epoch": 0.2057965376385917,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.0004998154814990538,
|
||
|
|
"loss": 5.8637,
|
||
|
|
"mean_token_accuracy": 0.14247775822877884,
|
||
|
|
"num_tokens": 4598910.0,
|
||
|
|
"step": 2645
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.170034503936767,
|
||
|
|
"epoch": 0.20618556701030927,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.00049981435757157,
|
||
|
|
"loss": 5.9733,
|
||
|
|
"mean_token_accuracy": 0.13756560906767845,
|
||
|
|
"num_tokens": 4607400.0,
|
||
|
|
"step": 2650
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.0044433116912845,
|
||
|
|
"epoch": 0.20657459638202685,
|
||
|
|
"grad_norm": 0.88671875,
|
||
|
|
"learning_rate": 0.0004998132302328862,
|
||
|
|
"loss": 5.9158,
|
||
|
|
"mean_token_accuracy": 0.14620504081249236,
|
||
|
|
"num_tokens": 4616510.0,
|
||
|
|
"step": 2655
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.089318561553955,
|
||
|
|
"epoch": 0.2069636257537444,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.0004998120994830195,
|
||
|
|
"loss": 5.8585,
|
||
|
|
"mean_token_accuracy": 0.15085278004407882,
|
||
|
|
"num_tokens": 4624529.0,
|
||
|
|
"step": 2660
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.052582168579102,
|
||
|
|
"epoch": 0.20735265512546197,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.000499810965321987,
|
||
|
|
"loss": 5.7948,
|
||
|
|
"mean_token_accuracy": 0.1443331226706505,
|
||
|
|
"num_tokens": 4632141.0,
|
||
|
|
"step": 2665
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.077098178863525,
|
||
|
|
"epoch": 0.20774168449717953,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.0004998098277498059,
|
||
|
|
"loss": 6.0011,
|
||
|
|
"mean_token_accuracy": 0.14341832026839257,
|
||
|
|
"num_tokens": 4640378.0,
|
||
|
|
"step": 2670
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.038132619857788,
|
||
|
|
"epoch": 0.2081307138688971,
|
||
|
|
"grad_norm": 0.94140625,
|
||
|
|
"learning_rate": 0.0004998086867664934,
|
||
|
|
"loss": 5.7666,
|
||
|
|
"mean_token_accuracy": 0.14619476199150086,
|
||
|
|
"num_tokens": 4649313.0,
|
||
|
|
"step": 2675
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.0627112865448,
|
||
|
|
"epoch": 0.20851974324061467,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.000499807542372067,
|
||
|
|
"loss": 5.8704,
|
||
|
|
"mean_token_accuracy": 0.14677273184061052,
|
||
|
|
"num_tokens": 4658272.0,
|
||
|
|
"step": 2680
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.999119997024536,
|
||
|
|
"epoch": 0.20890877261233223,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004998063945665439,
|
||
|
|
"loss": 5.7272,
|
||
|
|
"mean_token_accuracy": 0.1503640040755272,
|
||
|
|
"num_tokens": 4665970.0,
|
||
|
|
"step": 2685
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.0891471862792965,
|
||
|
|
"epoch": 0.2092978019840498,
|
||
|
|
"grad_norm": 0.953125,
|
||
|
|
"learning_rate": 0.0004998052433499416,
|
||
|
|
"loss": 5.9918,
|
||
|
|
"mean_token_accuracy": 0.1369311533868313,
|
||
|
|
"num_tokens": 4675308.0,
|
||
|
|
"step": 2690
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.027482986450195,
|
||
|
|
"epoch": 0.20968683135576735,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004998040887222776,
|
||
|
|
"loss": 5.8264,
|
||
|
|
"mean_token_accuracy": 0.14104743599891661,
|
||
|
|
"num_tokens": 4684316.0,
|
||
|
|
"step": 2695
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.0261436939239506,
|
||
|
|
"epoch": 0.21007586072748494,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.0004998029306835693,
|
||
|
|
"loss": 5.7484,
|
||
|
|
"mean_token_accuracy": 0.1449325144290924,
|
||
|
|
"num_tokens": 4693029.0,
|
||
|
|
"step": 2700
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.008954334259033,
|
||
|
|
"epoch": 0.2104648900992025,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004998017692338344,
|
||
|
|
"loss": 5.9501,
|
||
|
|
"mean_token_accuracy": 0.1345457024872303,
|
||
|
|
"num_tokens": 4702404.0,
|
||
|
|
"step": 2705
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.1038126945495605,
|
||
|
|
"epoch": 0.21085391947092005,
|
||
|
|
"grad_norm": 0.95703125,
|
||
|
|
"learning_rate": 0.0004998006043730905,
|
||
|
|
"loss": 5.9081,
|
||
|
|
"mean_token_accuracy": 0.1360231891274452,
|
||
|
|
"num_tokens": 4711126.0,
|
||
|
|
"step": 2710
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.061972713470459,
|
||
|
|
"epoch": 0.2112429488426376,
|
||
|
|
"grad_norm": 0.96484375,
|
||
|
|
"learning_rate": 0.0004997994361013551,
|
||
|
|
"loss": 5.9103,
|
||
|
|
"mean_token_accuracy": 0.1473036840558052,
|
||
|
|
"num_tokens": 4719816.0,
|
||
|
|
"step": 2715
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.112641429901123,
|
||
|
|
"epoch": 0.21163197821435517,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.0004997982644186461,
|
||
|
|
"loss": 5.8544,
|
||
|
|
"mean_token_accuracy": 0.14111861065030099,
|
||
|
|
"num_tokens": 4728294.0,
|
||
|
|
"step": 2720
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.039841270446777,
|
||
|
|
"epoch": 0.21202100758607276,
|
||
|
|
"grad_norm": 0.9609375,
|
||
|
|
"learning_rate": 0.0004997970893249813,
|
||
|
|
"loss": 5.781,
|
||
|
|
"mean_token_accuracy": 0.14560880810022353,
|
||
|
|
"num_tokens": 4736708.0,
|
||
|
|
"step": 2725
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.011950349807739,
|
||
|
|
"epoch": 0.21241003695779032,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004997959108203785,
|
||
|
|
"loss": 5.9664,
|
||
|
|
"mean_token_accuracy": 0.13347356244921685,
|
||
|
|
"num_tokens": 4744893.0,
|
||
|
|
"step": 2730
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.164001941680908,
|
||
|
|
"epoch": 0.21279906632950787,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.0004997947289048554,
|
||
|
|
"loss": 5.909,
|
||
|
|
"mean_token_accuracy": 0.14289160668849946,
|
||
|
|
"num_tokens": 4753246.0,
|
||
|
|
"step": 2735
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.004565238952637,
|
||
|
|
"epoch": 0.21318809570122543,
|
||
|
|
"grad_norm": 0.99609375,
|
||
|
|
"learning_rate": 0.0004997935435784302,
|
||
|
|
"loss": 5.8313,
|
||
|
|
"mean_token_accuracy": 0.13941832184791564,
|
||
|
|
"num_tokens": 4762229.0,
|
||
|
|
"step": 2740
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.904656267166137,
|
||
|
|
"epoch": 0.21357712507294302,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004997923548411208,
|
||
|
|
"loss": 5.788,
|
||
|
|
"mean_token_accuracy": 0.1491306185722351,
|
||
|
|
"num_tokens": 4771315.0,
|
||
|
|
"step": 2745
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.89280514717102,
|
||
|
|
"epoch": 0.21396615444466058,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.000499791162692945,
|
||
|
|
"loss": 5.7262,
|
||
|
|
"mean_token_accuracy": 0.15562662929296495,
|
||
|
|
"num_tokens": 4779848.0,
|
||
|
|
"step": 2750
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.105467939376831,
|
||
|
|
"epoch": 0.21435518381637814,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004997899671339214,
|
||
|
|
"loss": 5.953,
|
||
|
|
"mean_token_accuracy": 0.13940655589103698,
|
||
|
|
"num_tokens": 4788939.0,
|
||
|
|
"step": 2755
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.0590917587280275,
|
||
|
|
"epoch": 0.2147442131880957,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004997887681640675,
|
||
|
|
"loss": 5.8526,
|
||
|
|
"mean_token_accuracy": 0.14215253964066504,
|
||
|
|
"num_tokens": 4797719.0,
|
||
|
|
"step": 2760
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.048555850982666,
|
||
|
|
"epoch": 0.21513324255981325,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.0004997875657834021,
|
||
|
|
"loss": 5.9096,
|
||
|
|
"mean_token_accuracy": 0.14236008748412132,
|
||
|
|
"num_tokens": 4805601.0,
|
||
|
|
"step": 2765
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.133038139343261,
|
||
|
|
"epoch": 0.21552227193153084,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.0004997863599919432,
|
||
|
|
"loss": 5.8669,
|
||
|
|
"mean_token_accuracy": 0.14362844973802566,
|
||
|
|
"num_tokens": 4814993.0,
|
||
|
|
"step": 2770
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.037166595458984,
|
||
|
|
"epoch": 0.2159113013032484,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004997851507897089,
|
||
|
|
"loss": 5.8201,
|
||
|
|
"mean_token_accuracy": 0.1418660469353199,
|
||
|
|
"num_tokens": 4824156.0,
|
||
|
|
"step": 2775
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.9804931640625,
|
||
|
|
"epoch": 0.21630033067496596,
|
||
|
|
"grad_norm": 0.96484375,
|
||
|
|
"learning_rate": 0.0004997839381767178,
|
||
|
|
"loss": 5.914,
|
||
|
|
"mean_token_accuracy": 0.13883057311177255,
|
||
|
|
"num_tokens": 4833827.0,
|
||
|
|
"step": 2780
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.000218725204467,
|
||
|
|
"epoch": 0.21668936004668352,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0004997827221529882,
|
||
|
|
"loss": 5.8457,
|
||
|
|
"mean_token_accuracy": 0.14448366090655326,
|
||
|
|
"num_tokens": 4842801.0,
|
||
|
|
"step": 2785
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.977024841308594,
|
||
|
|
"epoch": 0.2170783894184011,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0004997815027185386,
|
||
|
|
"loss": 5.7228,
|
||
|
|
"mean_token_accuracy": 0.1479553274810314,
|
||
|
|
"num_tokens": 4850928.0,
|
||
|
|
"step": 2790
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.019153690338134,
|
||
|
|
"epoch": 0.21746741879011866,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004997802798733874,
|
||
|
|
"loss": 5.8354,
|
||
|
|
"mean_token_accuracy": 0.14865680709481238,
|
||
|
|
"num_tokens": 4859510.0,
|
||
|
|
"step": 2795
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.055089998245239,
|
||
|
|
"epoch": 0.21785644816183622,
|
||
|
|
"grad_norm": 0.921875,
|
||
|
|
"learning_rate": 0.0004997790536175534,
|
||
|
|
"loss": 5.8612,
|
||
|
|
"mean_token_accuracy": 0.14595925584435462,
|
||
|
|
"num_tokens": 4868201.0,
|
||
|
|
"step": 2800
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.951241731643677,
|
||
|
|
"epoch": 0.21824547753355378,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0004997778239510548,
|
||
|
|
"loss": 5.7896,
|
||
|
|
"mean_token_accuracy": 0.1492677852511406,
|
||
|
|
"num_tokens": 4876896.0,
|
||
|
|
"step": 2805
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.933494901657104,
|
||
|
|
"epoch": 0.21863450690527134,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0004997765908739106,
|
||
|
|
"loss": 5.7462,
|
||
|
|
"mean_token_accuracy": 0.1509405829012394,
|
||
|
|
"num_tokens": 4885136.0,
|
||
|
|
"step": 2810
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.998682165145874,
|
||
|
|
"epoch": 0.21902353627698892,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.0004997753543861395,
|
||
|
|
"loss": 5.7656,
|
||
|
|
"mean_token_accuracy": 0.14779986441135406,
|
||
|
|
"num_tokens": 4893277.0,
|
||
|
|
"step": 2815
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.959256601333618,
|
||
|
|
"epoch": 0.21941256564870648,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.00049977411448776,
|
||
|
|
"loss": 5.9097,
|
||
|
|
"mean_token_accuracy": 0.14146498516201972,
|
||
|
|
"num_tokens": 4901977.0,
|
||
|
|
"step": 2820
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.075650453567505,
|
||
|
|
"epoch": 0.21980159502042404,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0004997728711787912,
|
||
|
|
"loss": 5.9125,
|
||
|
|
"mean_token_accuracy": 0.13340190574526786,
|
||
|
|
"num_tokens": 4910888.0,
|
||
|
|
"step": 2825
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.026413440704346,
|
||
|
|
"epoch": 0.2201906243921416,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.0004997716244592518,
|
||
|
|
"loss": 5.9052,
|
||
|
|
"mean_token_accuracy": 0.13878937885165216,
|
||
|
|
"num_tokens": 4920369.0,
|
||
|
|
"step": 2830
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.093588161468506,
|
||
|
|
"epoch": 0.22057965376385918,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.0004997703743291607,
|
||
|
|
"loss": 5.8955,
|
||
|
|
"mean_token_accuracy": 0.14121510535478593,
|
||
|
|
"num_tokens": 4928799.0,
|
||
|
|
"step": 2835
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.091677141189575,
|
||
|
|
"epoch": 0.22096868313557674,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.000499769120788537,
|
||
|
|
"loss": 5.7852,
|
||
|
|
"mean_token_accuracy": 0.15266166031360626,
|
||
|
|
"num_tokens": 4937194.0,
|
||
|
|
"step": 2840
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.987790822982788,
|
||
|
|
"epoch": 0.2213577125072943,
|
||
|
|
"grad_norm": 0.99609375,
|
||
|
|
"learning_rate": 0.0004997678638373995,
|
||
|
|
"loss": 5.8642,
|
||
|
|
"mean_token_accuracy": 0.14156924486160277,
|
||
|
|
"num_tokens": 4946174.0,
|
||
|
|
"step": 2845
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.006899881362915,
|
||
|
|
"epoch": 0.22174674187901186,
|
||
|
|
"grad_norm": 0.94921875,
|
||
|
|
"learning_rate": 0.0004997666034757676,
|
||
|
|
"loss": 5.8244,
|
||
|
|
"mean_token_accuracy": 0.13754797130823135,
|
||
|
|
"num_tokens": 4955376.0,
|
||
|
|
"step": 2850
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.980024337768555,
|
||
|
|
"epoch": 0.22213577125072942,
|
||
|
|
"grad_norm": 0.9140625,
|
||
|
|
"learning_rate": 0.0004997653397036603,
|
||
|
|
"loss": 5.8092,
|
||
|
|
"mean_token_accuracy": 0.15121594890952111,
|
||
|
|
"num_tokens": 4964138.0,
|
||
|
|
"step": 2855
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.042385482788086,
|
||
|
|
"epoch": 0.222524800622447,
|
||
|
|
"grad_norm": 0.953125,
|
||
|
|
"learning_rate": 0.0004997640725210965,
|
||
|
|
"loss": 5.9065,
|
||
|
|
"mean_token_accuracy": 0.14113098457455636,
|
||
|
|
"num_tokens": 4973868.0,
|
||
|
|
"step": 2860
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.009365510940552,
|
||
|
|
"epoch": 0.22291382999416456,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.0004997628019280958,
|
||
|
|
"loss": 5.7881,
|
||
|
|
"mean_token_accuracy": 0.1450905978679657,
|
||
|
|
"num_tokens": 4982687.0,
|
||
|
|
"step": 2865
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.019914531707764,
|
||
|
|
"epoch": 0.22330285936588212,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004997615279246773,
|
||
|
|
"loss": 5.8441,
|
||
|
|
"mean_token_accuracy": 0.14207333847880363,
|
||
|
|
"num_tokens": 4992072.0,
|
||
|
|
"step": 2870
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.99617919921875,
|
||
|
|
"epoch": 0.22369188873759968,
|
||
|
|
"grad_norm": 0.99609375,
|
||
|
|
"learning_rate": 0.0004997602505108603,
|
||
|
|
"loss": 5.7744,
|
||
|
|
"mean_token_accuracy": 0.14771850109100343,
|
||
|
|
"num_tokens": 5000551.0,
|
||
|
|
"step": 2875
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.006196022033691,
|
||
|
|
"epoch": 0.22408091810931724,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004997589696866644,
|
||
|
|
"loss": 5.9401,
|
||
|
|
"mean_token_accuracy": 0.14075398147106172,
|
||
|
|
"num_tokens": 5009292.0,
|
||
|
|
"step": 2880
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.030385875701905,
|
||
|
|
"epoch": 0.22446994748103483,
|
||
|
|
"grad_norm": 0.984375,
|
||
|
|
"learning_rate": 0.0004997576854521088,
|
||
|
|
"loss": 5.7943,
|
||
|
|
"mean_token_accuracy": 0.14536833316087722,
|
||
|
|
"num_tokens": 5018407.0,
|
||
|
|
"step": 2885
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.986768054962158,
|
||
|
|
"epoch": 0.22485897685275238,
|
||
|
|
"grad_norm": 0.984375,
|
||
|
|
"learning_rate": 0.000499756397807213,
|
||
|
|
"loss": 5.8587,
|
||
|
|
"mean_token_accuracy": 0.14210979640483856,
|
||
|
|
"num_tokens": 5027353.0,
|
||
|
|
"step": 2890
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.054828786849976,
|
||
|
|
"epoch": 0.22524800622446994,
|
||
|
|
"grad_norm": 0.98828125,
|
||
|
|
"learning_rate": 0.0004997551067519966,
|
||
|
|
"loss": 5.8523,
|
||
|
|
"mean_token_accuracy": 0.14193106740713118,
|
||
|
|
"num_tokens": 5036476.0,
|
||
|
|
"step": 2895
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.0023867130279545,
|
||
|
|
"epoch": 0.2256370355961875,
|
||
|
|
"grad_norm": 0.98046875,
|
||
|
|
"learning_rate": 0.0004997538122864792,
|
||
|
|
"loss": 5.808,
|
||
|
|
"mean_token_accuracy": 0.14258752316236495,
|
||
|
|
"num_tokens": 5045132.0,
|
||
|
|
"step": 2900
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.03665246963501,
|
||
|
|
"epoch": 0.2260260649679051,
|
||
|
|
"grad_norm": 0.99609375,
|
||
|
|
"learning_rate": 0.0004997525144106804,
|
||
|
|
"loss": 5.8281,
|
||
|
|
"mean_token_accuracy": 0.14626746699213983,
|
||
|
|
"num_tokens": 5053665.0,
|
||
|
|
"step": 2905
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.007569980621338,
|
||
|
|
"epoch": 0.22641509433962265,
|
||
|
|
"grad_norm": 0.9609375,
|
||
|
|
"learning_rate": 0.00049975121312462,
|
||
|
|
"loss": 5.7764,
|
||
|
|
"mean_token_accuracy": 0.15300558432936667,
|
||
|
|
"num_tokens": 5062516.0,
|
||
|
|
"step": 2910
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.989815378189087,
|
||
|
|
"epoch": 0.2268041237113402,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.0004997499084283177,
|
||
|
|
"loss": 5.8238,
|
||
|
|
"mean_token_accuracy": 0.14331282824277877,
|
||
|
|
"num_tokens": 5071260.0,
|
||
|
|
"step": 2915
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.912539625167847,
|
||
|
|
"epoch": 0.22719315308305776,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0004997486003217932,
|
||
|
|
"loss": 5.7846,
|
||
|
|
"mean_token_accuracy": 0.15056708306074143,
|
||
|
|
"num_tokens": 5079215.0,
|
||
|
|
"step": 2920
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.9982171058654785,
|
||
|
|
"epoch": 0.22758218245477532,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.0004997472888050664,
|
||
|
|
"loss": 5.8364,
|
||
|
|
"mean_token_accuracy": 0.14199614971876146,
|
||
|
|
"num_tokens": 5088404.0,
|
||
|
|
"step": 2925
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.948773670196533,
|
||
|
|
"epoch": 0.2279712118264929,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0004997459738781573,
|
||
|
|
"loss": 5.7779,
|
||
|
|
"mean_token_accuracy": 0.14737778007984162,
|
||
|
|
"num_tokens": 5096756.0,
|
||
|
|
"step": 2930
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.046881580352784,
|
||
|
|
"epoch": 0.22836024119821047,
|
||
|
|
"grad_norm": 0.921875,
|
||
|
|
"learning_rate": 0.0004997446555410857,
|
||
|
|
"loss": 5.9382,
|
||
|
|
"mean_token_accuracy": 0.14340072497725487,
|
||
|
|
"num_tokens": 5106160.0,
|
||
|
|
"step": 2935
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.882016944885254,
|
||
|
|
"epoch": 0.22874927056992803,
|
||
|
|
"grad_norm": 0.96875,
|
||
|
|
"learning_rate": 0.0004997433337938716,
|
||
|
|
"loss": 5.8607,
|
||
|
|
"mean_token_accuracy": 0.14600483030080796,
|
||
|
|
"num_tokens": 5114915.0,
|
||
|
|
"step": 2940
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.0260986328125,
|
||
|
|
"epoch": 0.22913829994164558,
|
||
|
|
"grad_norm": 0.984375,
|
||
|
|
"learning_rate": 0.0004997420086365351,
|
||
|
|
"loss": 5.7735,
|
||
|
|
"mean_token_accuracy": 0.1435887724161148,
|
||
|
|
"num_tokens": 5123249.0,
|
||
|
|
"step": 2945
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.994471597671509,
|
||
|
|
"epoch": 0.22952732931336317,
|
||
|
|
"grad_norm": 0.953125,
|
||
|
|
"learning_rate": 0.0004997406800690966,
|
||
|
|
"loss": 5.7702,
|
||
|
|
"mean_token_accuracy": 0.14430145174264908,
|
||
|
|
"num_tokens": 5131906.0,
|
||
|
|
"step": 2950
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.992271280288696,
|
||
|
|
"epoch": 0.22991635868508073,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.0004997393480915758,
|
||
|
|
"loss": 5.7451,
|
||
|
|
"mean_token_accuracy": 0.15099966078996657,
|
||
|
|
"num_tokens": 5140740.0,
|
||
|
|
"step": 2955
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.006669330596924,
|
||
|
|
"epoch": 0.2303053880567983,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.0004997380127039931,
|
||
|
|
"loss": 5.9405,
|
||
|
|
"mean_token_accuracy": 0.14362909346818925,
|
||
|
|
"num_tokens": 5149748.0,
|
||
|
|
"step": 2960
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.904706525802612,
|
||
|
|
"epoch": 0.23069441742851585,
|
||
|
|
"grad_norm": 0.97265625,
|
||
|
|
"learning_rate": 0.0004997366739063688,
|
||
|
|
"loss": 5.6624,
|
||
|
|
"mean_token_accuracy": 0.15620378851890565,
|
||
|
|
"num_tokens": 5158475.0,
|
||
|
|
"step": 2965
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.965284395217895,
|
||
|
|
"epoch": 0.2310834468002334,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.0004997353316987231,
|
||
|
|
"loss": 5.8742,
|
||
|
|
"mean_token_accuracy": 0.13686980605125426,
|
||
|
|
"num_tokens": 5166593.0,
|
||
|
|
"step": 2970
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.072088766098022,
|
||
|
|
"epoch": 0.231472476171951,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0004997339860810765,
|
||
|
|
"loss": 5.8417,
|
||
|
|
"mean_token_accuracy": 0.14505124390125274,
|
||
|
|
"num_tokens": 5175557.0,
|
||
|
|
"step": 2975
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.97886700630188,
|
||
|
|
"epoch": 0.23186150554366855,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004997326370534495,
|
||
|
|
"loss": 5.7418,
|
||
|
|
"mean_token_accuracy": 0.14757711663842202,
|
||
|
|
"num_tokens": 5184140.0,
|
||
|
|
"step": 2980
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.984816789627075,
|
||
|
|
"epoch": 0.2322505349153861,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004997312846158622,
|
||
|
|
"loss": 5.8323,
|
||
|
|
"mean_token_accuracy": 0.14205295890569686,
|
||
|
|
"num_tokens": 5192347.0,
|
||
|
|
"step": 2985
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.038908290863037,
|
||
|
|
"epoch": 0.23263956428710367,
|
||
|
|
"grad_norm": 0.9921875,
|
||
|
|
"learning_rate": 0.0004997299287683355,
|
||
|
|
"loss": 5.7938,
|
||
|
|
"mean_token_accuracy": 0.15015682727098464,
|
||
|
|
"num_tokens": 5201327.0,
|
||
|
|
"step": 2990
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.9845648288726805,
|
||
|
|
"epoch": 0.23302859365882125,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0004997285695108898,
|
||
|
|
"loss": 5.8845,
|
||
|
|
"mean_token_accuracy": 0.1420726865530014,
|
||
|
|
"num_tokens": 5209873.0,
|
||
|
|
"step": 2995
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.02182092666626,
|
||
|
|
"epoch": 0.2334176230305388,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0004997272068435458,
|
||
|
|
"loss": 5.7891,
|
||
|
|
"mean_token_accuracy": 0.14845749586820603,
|
||
|
|
"num_tokens": 5219176.0,
|
||
|
|
"step": 3000
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.2334176230305388,
|
||
|
|
"eval_entropy": 5.766755393746957,
|
||
|
|
"eval_loss": 5.836002349853516,
|
||
|
|
"eval_mean_token_accuracy": 0.15392624230282712,
|
||
|
|
"eval_num_tokens": 5219176.0,
|
||
|
|
"eval_runtime": 21.8281,
|
||
|
|
"eval_samples_per_second": 1903.876,
|
||
|
|
"eval_steps_per_second": 237.996,
|
||
|
|
"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": 1052336906403840.0,
|
||
|
|
"train_batch_size": 16,
|
||
|
|
"trial_name": null,
|
||
|
|
"trial_params": null
|
||
|
|
}
|