54134 lines
1.5 MiB
54134 lines
1.5 MiB
{
|
|
"best_global_step": null,
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 2.1006808014005056,
|
|
"eval_steps": 3000,
|
|
"global_step": 27000,
|
|
"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
|
|
},
|
|
{
|
|
"entropy": 5.914532804489136,
|
|
"epoch": 0.23380665240225637,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000499725840766324,
|
|
"loss": 5.7209,
|
|
"mean_token_accuracy": 0.15771688520908356,
|
|
"num_tokens": 5227310.0,
|
|
"step": 3005
|
|
},
|
|
{
|
|
"entropy": 6.004350805282593,
|
|
"epoch": 0.23419568177397393,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004997244712792453,
|
|
"loss": 5.8185,
|
|
"mean_token_accuracy": 0.1469304844737053,
|
|
"num_tokens": 5235882.0,
|
|
"step": 3010
|
|
},
|
|
{
|
|
"entropy": 5.97558012008667,
|
|
"epoch": 0.2345847111456915,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004997230983823305,
|
|
"loss": 5.733,
|
|
"mean_token_accuracy": 0.1464428722858429,
|
|
"num_tokens": 5244149.0,
|
|
"step": 3015
|
|
},
|
|
{
|
|
"entropy": 5.811860370635986,
|
|
"epoch": 0.23497374051740907,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004997217220756003,
|
|
"loss": 5.5949,
|
|
"mean_token_accuracy": 0.1532672643661499,
|
|
"num_tokens": 5252473.0,
|
|
"step": 3020
|
|
},
|
|
{
|
|
"entropy": 5.928388214111328,
|
|
"epoch": 0.23536276988912663,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004997203423590757,
|
|
"loss": 5.7517,
|
|
"mean_token_accuracy": 0.15568342953920364,
|
|
"num_tokens": 5260972.0,
|
|
"step": 3025
|
|
},
|
|
{
|
|
"entropy": 5.972634315490723,
|
|
"epoch": 0.2357517992608442,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004997189592327775,
|
|
"loss": 5.7873,
|
|
"mean_token_accuracy": 0.13899434357881546,
|
|
"num_tokens": 5270513.0,
|
|
"step": 3030
|
|
},
|
|
{
|
|
"entropy": 5.970373249053955,
|
|
"epoch": 0.23614082863256175,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004997175726967268,
|
|
"loss": 5.7495,
|
|
"mean_token_accuracy": 0.1445789471268654,
|
|
"num_tokens": 5278433.0,
|
|
"step": 3035
|
|
},
|
|
{
|
|
"entropy": 5.905675411224365,
|
|
"epoch": 0.23652985800427934,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004997161827509447,
|
|
"loss": 5.7585,
|
|
"mean_token_accuracy": 0.14649613872170447,
|
|
"num_tokens": 5287389.0,
|
|
"step": 3040
|
|
},
|
|
{
|
|
"entropy": 5.956258916854859,
|
|
"epoch": 0.2369188873759969,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004997147893954521,
|
|
"loss": 5.8565,
|
|
"mean_token_accuracy": 0.14266041815280914,
|
|
"num_tokens": 5296220.0,
|
|
"step": 3045
|
|
},
|
|
{
|
|
"entropy": 5.96304931640625,
|
|
"epoch": 0.23730791674771445,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004997133926302702,
|
|
"loss": 5.7852,
|
|
"mean_token_accuracy": 0.14856525361537934,
|
|
"num_tokens": 5304152.0,
|
|
"step": 3050
|
|
},
|
|
{
|
|
"entropy": 6.020824432373047,
|
|
"epoch": 0.237696946119432,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004997119924554204,
|
|
"loss": 5.8112,
|
|
"mean_token_accuracy": 0.14321792423725127,
|
|
"num_tokens": 5312374.0,
|
|
"step": 3055
|
|
},
|
|
{
|
|
"entropy": 5.898687171936035,
|
|
"epoch": 0.23808597549114957,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004997105888709236,
|
|
"loss": 5.7338,
|
|
"mean_token_accuracy": 0.1488700330257416,
|
|
"num_tokens": 5320696.0,
|
|
"step": 3060
|
|
},
|
|
{
|
|
"entropy": 5.996364736557007,
|
|
"epoch": 0.23847500486286716,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004997091818768015,
|
|
"loss": 5.8581,
|
|
"mean_token_accuracy": 0.14631845131516458,
|
|
"num_tokens": 5328754.0,
|
|
"step": 3065
|
|
},
|
|
{
|
|
"entropy": 6.014861583709717,
|
|
"epoch": 0.23886403423458472,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000499707771473075,
|
|
"loss": 5.8258,
|
|
"mean_token_accuracy": 0.14964541494846345,
|
|
"num_tokens": 5337553.0,
|
|
"step": 3070
|
|
},
|
|
{
|
|
"entropy": 5.994286060333252,
|
|
"epoch": 0.23925306360630227,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004997063576597659,
|
|
"loss": 5.7521,
|
|
"mean_token_accuracy": 0.15279997289180755,
|
|
"num_tokens": 5346063.0,
|
|
"step": 3075
|
|
},
|
|
{
|
|
"entropy": 5.946002388000489,
|
|
"epoch": 0.23964209297801983,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004997049404368954,
|
|
"loss": 5.8209,
|
|
"mean_token_accuracy": 0.14650205597281457,
|
|
"num_tokens": 5354187.0,
|
|
"step": 3080
|
|
},
|
|
{
|
|
"entropy": 5.965845775604248,
|
|
"epoch": 0.2400311223497374,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000499703519804485,
|
|
"loss": 5.8657,
|
|
"mean_token_accuracy": 0.1399562805891037,
|
|
"num_tokens": 5362819.0,
|
|
"step": 3085
|
|
},
|
|
{
|
|
"entropy": 5.967871189117432,
|
|
"epoch": 0.24042015172145498,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004997020957625564,
|
|
"loss": 5.7274,
|
|
"mean_token_accuracy": 0.15995107144117354,
|
|
"num_tokens": 5371249.0,
|
|
"step": 3090
|
|
},
|
|
{
|
|
"entropy": 5.9214027404785154,
|
|
"epoch": 0.24080918109317254,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004997006683111312,
|
|
"loss": 5.7441,
|
|
"mean_token_accuracy": 0.14917703121900558,
|
|
"num_tokens": 5379284.0,
|
|
"step": 3095
|
|
},
|
|
{
|
|
"entropy": 5.997532606124878,
|
|
"epoch": 0.2411982104648901,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.000499699237450231,
|
|
"loss": 5.8315,
|
|
"mean_token_accuracy": 0.1462565302848816,
|
|
"num_tokens": 5388541.0,
|
|
"step": 3100
|
|
},
|
|
{
|
|
"entropy": 6.00367169380188,
|
|
"epoch": 0.24158723983660765,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004996978031798774,
|
|
"loss": 5.9068,
|
|
"mean_token_accuracy": 0.14637081027030946,
|
|
"num_tokens": 5397226.0,
|
|
"step": 3105
|
|
},
|
|
{
|
|
"entropy": 5.973370695114136,
|
|
"epoch": 0.24197626920832524,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004996963655000924,
|
|
"loss": 5.8089,
|
|
"mean_token_accuracy": 0.14054676070809363,
|
|
"num_tokens": 5405579.0,
|
|
"step": 3110
|
|
},
|
|
{
|
|
"entropy": 6.009214591979981,
|
|
"epoch": 0.2423652985800428,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004996949244108977,
|
|
"loss": 5.9245,
|
|
"mean_token_accuracy": 0.13549011573195457,
|
|
"num_tokens": 5414529.0,
|
|
"step": 3115
|
|
},
|
|
{
|
|
"entropy": 6.035836887359619,
|
|
"epoch": 0.24275432795176036,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000499693479912315,
|
|
"loss": 5.8796,
|
|
"mean_token_accuracy": 0.14944745674729348,
|
|
"num_tokens": 5423641.0,
|
|
"step": 3120
|
|
},
|
|
{
|
|
"entropy": 5.9449841499328615,
|
|
"epoch": 0.24314335732347792,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004996920320043666,
|
|
"loss": 5.7772,
|
|
"mean_token_accuracy": 0.14886331856250762,
|
|
"num_tokens": 5432558.0,
|
|
"step": 3125
|
|
},
|
|
{
|
|
"entropy": 5.950368738174438,
|
|
"epoch": 0.24353238669519547,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004996905806870742,
|
|
"loss": 5.7315,
|
|
"mean_token_accuracy": 0.14748364686965942,
|
|
"num_tokens": 5441449.0,
|
|
"step": 3130
|
|
},
|
|
{
|
|
"entropy": 5.87958459854126,
|
|
"epoch": 0.24392141606691306,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004996891259604598,
|
|
"loss": 5.7568,
|
|
"mean_token_accuracy": 0.1489865630865097,
|
|
"num_tokens": 5451142.0,
|
|
"step": 3135
|
|
},
|
|
{
|
|
"entropy": 5.970316457748413,
|
|
"epoch": 0.24431044543863062,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004996876678245455,
|
|
"loss": 5.6999,
|
|
"mean_token_accuracy": 0.14703621417284013,
|
|
"num_tokens": 5459290.0,
|
|
"step": 3140
|
|
},
|
|
{
|
|
"entropy": 5.939565229415893,
|
|
"epoch": 0.24469947481034818,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004996862062793536,
|
|
"loss": 5.7295,
|
|
"mean_token_accuracy": 0.1500839561223984,
|
|
"num_tokens": 5467776.0,
|
|
"step": 3145
|
|
},
|
|
{
|
|
"entropy": 5.856816625595092,
|
|
"epoch": 0.24508850418206574,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004996847413249061,
|
|
"loss": 5.6092,
|
|
"mean_token_accuracy": 0.15638387948274612,
|
|
"num_tokens": 5476005.0,
|
|
"step": 3150
|
|
},
|
|
{
|
|
"entropy": 5.990639543533325,
|
|
"epoch": 0.24547753355378332,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004996832729612252,
|
|
"loss": 5.7943,
|
|
"mean_token_accuracy": 0.1473146602511406,
|
|
"num_tokens": 5484225.0,
|
|
"step": 3155
|
|
},
|
|
{
|
|
"entropy": 5.839318799972534,
|
|
"epoch": 0.24586656292550088,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004996818011883333,
|
|
"loss": 5.7023,
|
|
"mean_token_accuracy": 0.15613459944725036,
|
|
"num_tokens": 5493111.0,
|
|
"step": 3160
|
|
},
|
|
{
|
|
"entropy": 5.878914022445679,
|
|
"epoch": 0.24625559229721844,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004996803260062527,
|
|
"loss": 5.7295,
|
|
"mean_token_accuracy": 0.15031494274735452,
|
|
"num_tokens": 5501574.0,
|
|
"step": 3165
|
|
},
|
|
{
|
|
"entropy": 5.983736276626587,
|
|
"epoch": 0.246644621668936,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004996788474150057,
|
|
"loss": 5.7602,
|
|
"mean_token_accuracy": 0.14838263839483262,
|
|
"num_tokens": 5511136.0,
|
|
"step": 3170
|
|
},
|
|
{
|
|
"entropy": 5.882587671279907,
|
|
"epoch": 0.24703365104065356,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004996773654146149,
|
|
"loss": 5.7409,
|
|
"mean_token_accuracy": 0.15212823152542115,
|
|
"num_tokens": 5520324.0,
|
|
"step": 3175
|
|
},
|
|
{
|
|
"entropy": 5.967652320861816,
|
|
"epoch": 0.24742268041237114,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004996758800051026,
|
|
"loss": 5.7024,
|
|
"mean_token_accuracy": 0.15401688665151597,
|
|
"num_tokens": 5528960.0,
|
|
"step": 3180
|
|
},
|
|
{
|
|
"entropy": 5.9393322467803955,
|
|
"epoch": 0.2478117097840887,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004996743911864916,
|
|
"loss": 5.8557,
|
|
"mean_token_accuracy": 0.1460486263036728,
|
|
"num_tokens": 5537391.0,
|
|
"step": 3185
|
|
},
|
|
{
|
|
"entropy": 5.9707262992858885,
|
|
"epoch": 0.24820073915580626,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004996728989588041,
|
|
"loss": 5.7953,
|
|
"mean_token_accuracy": 0.14829789772629737,
|
|
"num_tokens": 5546577.0,
|
|
"step": 3190
|
|
},
|
|
{
|
|
"entropy": 6.049851703643799,
|
|
"epoch": 0.24858976852752382,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004996714033220632,
|
|
"loss": 5.742,
|
|
"mean_token_accuracy": 0.14722291827201844,
|
|
"num_tokens": 5555247.0,
|
|
"step": 3195
|
|
},
|
|
{
|
|
"entropy": 5.890546751022339,
|
|
"epoch": 0.2489787978992414,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004996699042762911,
|
|
"loss": 5.6942,
|
|
"mean_token_accuracy": 0.15134429037570954,
|
|
"num_tokens": 5563598.0,
|
|
"step": 3200
|
|
},
|
|
{
|
|
"entropy": 5.940383005142212,
|
|
"epoch": 0.24936782727095896,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004996684018215111,
|
|
"loss": 5.725,
|
|
"mean_token_accuracy": 0.14869000166654586,
|
|
"num_tokens": 5572734.0,
|
|
"step": 3205
|
|
},
|
|
{
|
|
"entropy": 5.9394947528839115,
|
|
"epoch": 0.24975685664267652,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004996668959577453,
|
|
"loss": 5.8488,
|
|
"mean_token_accuracy": 0.1437419608235359,
|
|
"num_tokens": 5581224.0,
|
|
"step": 3210
|
|
},
|
|
{
|
|
"entropy": 6.008606481552124,
|
|
"epoch": 0.2501458860143941,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004996653866850173,
|
|
"loss": 5.8409,
|
|
"mean_token_accuracy": 0.14231252372264863,
|
|
"num_tokens": 5590138.0,
|
|
"step": 3215
|
|
},
|
|
{
|
|
"entropy": 5.949661636352539,
|
|
"epoch": 0.25053491538611167,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004996638740033495,
|
|
"loss": 5.7713,
|
|
"mean_token_accuracy": 0.15526752471923827,
|
|
"num_tokens": 5598654.0,
|
|
"step": 3220
|
|
},
|
|
{
|
|
"entropy": 5.846512508392334,
|
|
"epoch": 0.2509239447578292,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004996623579127651,
|
|
"loss": 5.7136,
|
|
"mean_token_accuracy": 0.1543463483452797,
|
|
"num_tokens": 5607404.0,
|
|
"step": 3225
|
|
},
|
|
{
|
|
"entropy": 5.943040132522583,
|
|
"epoch": 0.2513129741295468,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004996608384132868,
|
|
"loss": 5.7429,
|
|
"mean_token_accuracy": 0.14950166493654252,
|
|
"num_tokens": 5617133.0,
|
|
"step": 3230
|
|
},
|
|
{
|
|
"entropy": 5.90880651473999,
|
|
"epoch": 0.25170200350126437,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000499659315504938,
|
|
"loss": 5.7707,
|
|
"mean_token_accuracy": 0.1484447628259659,
|
|
"num_tokens": 5625389.0,
|
|
"step": 3235
|
|
},
|
|
{
|
|
"entropy": 5.857119131088257,
|
|
"epoch": 0.2520910328729819,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004996577891877417,
|
|
"loss": 5.6411,
|
|
"mean_token_accuracy": 0.16271414309740068,
|
|
"num_tokens": 5633985.0,
|
|
"step": 3240
|
|
},
|
|
{
|
|
"entropy": 5.973174619674682,
|
|
"epoch": 0.2524800622446995,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004996562594617209,
|
|
"loss": 5.7649,
|
|
"mean_token_accuracy": 0.14711527973413469,
|
|
"num_tokens": 5642524.0,
|
|
"step": 3245
|
|
},
|
|
{
|
|
"entropy": 5.936709356307984,
|
|
"epoch": 0.252869091616417,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004996547263268991,
|
|
"loss": 5.7178,
|
|
"mean_token_accuracy": 0.14921012967824937,
|
|
"num_tokens": 5651788.0,
|
|
"step": 3250
|
|
},
|
|
{
|
|
"entropy": 5.888123035430908,
|
|
"epoch": 0.2532581209881346,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004996531897832993,
|
|
"loss": 5.7602,
|
|
"mean_token_accuracy": 0.14676389396190642,
|
|
"num_tokens": 5660757.0,
|
|
"step": 3255
|
|
},
|
|
{
|
|
"entropy": 6.043964958190918,
|
|
"epoch": 0.2536471503598522,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000499651649830945,
|
|
"loss": 5.8528,
|
|
"mean_token_accuracy": 0.1506285548210144,
|
|
"num_tokens": 5669760.0,
|
|
"step": 3260
|
|
},
|
|
{
|
|
"entropy": 5.922834873199463,
|
|
"epoch": 0.2540361797315697,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004996501064698593,
|
|
"loss": 5.7811,
|
|
"mean_token_accuracy": 0.15074339210987092,
|
|
"num_tokens": 5678313.0,
|
|
"step": 3265
|
|
},
|
|
{
|
|
"entropy": 5.939870929718017,
|
|
"epoch": 0.2544252091032873,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000499648559700066,
|
|
"loss": 5.6956,
|
|
"mean_token_accuracy": 0.15352511703968047,
|
|
"num_tokens": 5686942.0,
|
|
"step": 3270
|
|
},
|
|
{
|
|
"entropy": 5.876242780685425,
|
|
"epoch": 0.25481423847500484,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004996470095215884,
|
|
"loss": 5.6997,
|
|
"mean_token_accuracy": 0.15511421784758567,
|
|
"num_tokens": 5695612.0,
|
|
"step": 3275
|
|
},
|
|
{
|
|
"entropy": 5.961434316635132,
|
|
"epoch": 0.2552032678467224,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004996454559344498,
|
|
"loss": 5.8798,
|
|
"mean_token_accuracy": 0.1368470698595047,
|
|
"num_tokens": 5705067.0,
|
|
"step": 3280
|
|
},
|
|
{
|
|
"entropy": 5.967849016189575,
|
|
"epoch": 0.25559229721844,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004996438989386741,
|
|
"loss": 5.7754,
|
|
"mean_token_accuracy": 0.15305520966649055,
|
|
"num_tokens": 5714092.0,
|
|
"step": 3285
|
|
},
|
|
{
|
|
"entropy": 5.969217824935913,
|
|
"epoch": 0.25598132659015754,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004996423385342847,
|
|
"loss": 5.7351,
|
|
"mean_token_accuracy": 0.15343412458896638,
|
|
"num_tokens": 5722638.0,
|
|
"step": 3290
|
|
},
|
|
{
|
|
"entropy": 5.878257513046265,
|
|
"epoch": 0.25637035596187513,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004996407747213055,
|
|
"loss": 5.7449,
|
|
"mean_token_accuracy": 0.14493217319250107,
|
|
"num_tokens": 5731511.0,
|
|
"step": 3295
|
|
},
|
|
{
|
|
"entropy": 5.914233160018921,
|
|
"epoch": 0.25675938533359266,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00049963920749976,
|
|
"loss": 5.7517,
|
|
"mean_token_accuracy": 0.15331401228904723,
|
|
"num_tokens": 5740950.0,
|
|
"step": 3300
|
|
},
|
|
{
|
|
"entropy": 5.908319330215454,
|
|
"epoch": 0.25714841470531025,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004996376368696721,
|
|
"loss": 5.705,
|
|
"mean_token_accuracy": 0.14798064678907394,
|
|
"num_tokens": 5749163.0,
|
|
"step": 3305
|
|
},
|
|
{
|
|
"entropy": 5.932552862167358,
|
|
"epoch": 0.25753744407702783,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004996360628310656,
|
|
"loss": 5.7536,
|
|
"mean_token_accuracy": 0.14659023731946946,
|
|
"num_tokens": 5758321.0,
|
|
"step": 3310
|
|
},
|
|
{
|
|
"entropy": 5.938609218597412,
|
|
"epoch": 0.25792647344874536,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004996344853839644,
|
|
"loss": 5.8042,
|
|
"mean_token_accuracy": 0.14989116787910461,
|
|
"num_tokens": 5767277.0,
|
|
"step": 3315
|
|
},
|
|
{
|
|
"entropy": 5.8936632633209225,
|
|
"epoch": 0.25831550282046295,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004996329045283924,
|
|
"loss": 5.7001,
|
|
"mean_token_accuracy": 0.15724189579486847,
|
|
"num_tokens": 5775694.0,
|
|
"step": 3320
|
|
},
|
|
{
|
|
"entropy": 5.810319709777832,
|
|
"epoch": 0.25870453219218054,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004996313202643737,
|
|
"loss": 5.6225,
|
|
"mean_token_accuracy": 0.15532325357198715,
|
|
"num_tokens": 5783932.0,
|
|
"step": 3325
|
|
},
|
|
{
|
|
"entropy": 5.897975730895996,
|
|
"epoch": 0.25909356156389807,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004996297325919321,
|
|
"loss": 5.7529,
|
|
"mean_token_accuracy": 0.15493739545345306,
|
|
"num_tokens": 5792100.0,
|
|
"step": 3330
|
|
},
|
|
{
|
|
"entropy": 5.90851583480835,
|
|
"epoch": 0.25948259093561565,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004996281415110919,
|
|
"loss": 5.7307,
|
|
"mean_token_accuracy": 0.14977378994226456,
|
|
"num_tokens": 5801481.0,
|
|
"step": 3335
|
|
},
|
|
{
|
|
"entropy": 5.9347193241119385,
|
|
"epoch": 0.2598716203073332,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004996265470218773,
|
|
"loss": 5.8223,
|
|
"mean_token_accuracy": 0.14538975059986115,
|
|
"num_tokens": 5810053.0,
|
|
"step": 3340
|
|
},
|
|
{
|
|
"entropy": 5.880348157882691,
|
|
"epoch": 0.26026064967905077,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004996249491243122,
|
|
"loss": 5.6137,
|
|
"mean_token_accuracy": 0.16179749518632888,
|
|
"num_tokens": 5818454.0,
|
|
"step": 3345
|
|
},
|
|
{
|
|
"entropy": 5.8937677383422855,
|
|
"epoch": 0.26064967905076836,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004996233478184211,
|
|
"loss": 5.7778,
|
|
"mean_token_accuracy": 0.14190399944782256,
|
|
"num_tokens": 5827013.0,
|
|
"step": 3350
|
|
},
|
|
{
|
|
"entropy": 5.825893449783325,
|
|
"epoch": 0.2610387084224859,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004996217431042282,
|
|
"loss": 5.7808,
|
|
"mean_token_accuracy": 0.1439354784786701,
|
|
"num_tokens": 5835862.0,
|
|
"step": 3355
|
|
},
|
|
{
|
|
"entropy": 5.8302641868591305,
|
|
"epoch": 0.2614277377942035,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000499620134981758,
|
|
"loss": 5.5539,
|
|
"mean_token_accuracy": 0.15147414058446884,
|
|
"num_tokens": 5843827.0,
|
|
"step": 3360
|
|
},
|
|
{
|
|
"entropy": 5.872374200820923,
|
|
"epoch": 0.261816767165921,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004996185234510346,
|
|
"loss": 5.7502,
|
|
"mean_token_accuracy": 0.14820392578840255,
|
|
"num_tokens": 5852677.0,
|
|
"step": 3365
|
|
},
|
|
{
|
|
"entropy": 5.92858190536499,
|
|
"epoch": 0.2622057965376386,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004996169085120828,
|
|
"loss": 5.7093,
|
|
"mean_token_accuracy": 0.15133587270975113,
|
|
"num_tokens": 5861686.0,
|
|
"step": 3370
|
|
},
|
|
{
|
|
"entropy": 5.819103622436524,
|
|
"epoch": 0.2625948259093562,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004996152901649268,
|
|
"loss": 5.669,
|
|
"mean_token_accuracy": 0.14954098016023637,
|
|
"num_tokens": 5870690.0,
|
|
"step": 3375
|
|
},
|
|
{
|
|
"entropy": 5.902088308334351,
|
|
"epoch": 0.2629838552810737,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004996136684095913,
|
|
"loss": 5.7409,
|
|
"mean_token_accuracy": 0.14959589689970015,
|
|
"num_tokens": 5879804.0,
|
|
"step": 3380
|
|
},
|
|
{
|
|
"entropy": 5.966397905349732,
|
|
"epoch": 0.2633728846527913,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004996120432461009,
|
|
"loss": 5.8384,
|
|
"mean_token_accuracy": 0.14443578869104384,
|
|
"num_tokens": 5888781.0,
|
|
"step": 3385
|
|
},
|
|
{
|
|
"entropy": 5.987284231185913,
|
|
"epoch": 0.2637619140245088,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004996104146744804,
|
|
"loss": 5.7414,
|
|
"mean_token_accuracy": 0.14745590537786485,
|
|
"num_tokens": 5897439.0,
|
|
"step": 3390
|
|
},
|
|
{
|
|
"entropy": 5.88730821609497,
|
|
"epoch": 0.2641509433962264,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004996087826947541,
|
|
"loss": 5.7026,
|
|
"mean_token_accuracy": 0.161055551469326,
|
|
"num_tokens": 5905471.0,
|
|
"step": 3395
|
|
},
|
|
{
|
|
"entropy": 5.804925203323364,
|
|
"epoch": 0.264539972767944,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004996071473069471,
|
|
"loss": 5.7367,
|
|
"mean_token_accuracy": 0.15316548198461533,
|
|
"num_tokens": 5913795.0,
|
|
"step": 3400
|
|
},
|
|
{
|
|
"entropy": 6.04078631401062,
|
|
"epoch": 0.26492900213966153,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004996055085110842,
|
|
"loss": 5.7997,
|
|
"mean_token_accuracy": 0.15046787038445472,
|
|
"num_tokens": 5922119.0,
|
|
"step": 3405
|
|
},
|
|
{
|
|
"entropy": 5.822887897491455,
|
|
"epoch": 0.2653180315113791,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004996038663071902,
|
|
"loss": 5.6847,
|
|
"mean_token_accuracy": 0.1509345754981041,
|
|
"num_tokens": 5930759.0,
|
|
"step": 3410
|
|
},
|
|
{
|
|
"entropy": 5.903107595443726,
|
|
"epoch": 0.26570706088309665,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004996022206952901,
|
|
"loss": 5.7198,
|
|
"mean_token_accuracy": 0.15288078486919404,
|
|
"num_tokens": 5939830.0,
|
|
"step": 3415
|
|
},
|
|
{
|
|
"entropy": 5.929271078109741,
|
|
"epoch": 0.26609609025481423,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004996005716754086,
|
|
"loss": 5.7181,
|
|
"mean_token_accuracy": 0.15389925241470337,
|
|
"num_tokens": 5947737.0,
|
|
"step": 3420
|
|
},
|
|
{
|
|
"entropy": 5.778887224197388,
|
|
"epoch": 0.2664851196265318,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000499598919247571,
|
|
"loss": 5.6762,
|
|
"mean_token_accuracy": 0.15809207260608674,
|
|
"num_tokens": 5955905.0,
|
|
"step": 3425
|
|
},
|
|
{
|
|
"entropy": 5.849305629730225,
|
|
"epoch": 0.26687414899824935,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004995972634118023,
|
|
"loss": 5.7386,
|
|
"mean_token_accuracy": 0.15352326929569243,
|
|
"num_tokens": 5965223.0,
|
|
"step": 3430
|
|
},
|
|
{
|
|
"entropy": 5.93175745010376,
|
|
"epoch": 0.26726317836996694,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004995956041681277,
|
|
"loss": 5.7526,
|
|
"mean_token_accuracy": 0.15678024291992188,
|
|
"num_tokens": 5973615.0,
|
|
"step": 3435
|
|
},
|
|
{
|
|
"entropy": 5.861295080184936,
|
|
"epoch": 0.2676522077416845,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004995939415165722,
|
|
"loss": 5.669,
|
|
"mean_token_accuracy": 0.15896339267492293,
|
|
"num_tokens": 5981600.0,
|
|
"step": 3440
|
|
},
|
|
{
|
|
"entropy": 5.877530956268311,
|
|
"epoch": 0.26804123711340205,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004995922754571611,
|
|
"loss": 5.683,
|
|
"mean_token_accuracy": 0.15407007783651352,
|
|
"num_tokens": 5989928.0,
|
|
"step": 3445
|
|
},
|
|
{
|
|
"entropy": 5.829905796051025,
|
|
"epoch": 0.26843026648511964,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004995906059899197,
|
|
"loss": 5.7397,
|
|
"mean_token_accuracy": 0.15136908739805222,
|
|
"num_tokens": 5998704.0,
|
|
"step": 3450
|
|
},
|
|
{
|
|
"entropy": 5.886248350143433,
|
|
"epoch": 0.26881929585683717,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004995889331148733,
|
|
"loss": 5.7208,
|
|
"mean_token_accuracy": 0.1513502597808838,
|
|
"num_tokens": 6007476.0,
|
|
"step": 3455
|
|
},
|
|
{
|
|
"entropy": 5.973094367980957,
|
|
"epoch": 0.26920832522855476,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004995872568320474,
|
|
"loss": 5.7813,
|
|
"mean_token_accuracy": 0.14543018639087676,
|
|
"num_tokens": 6016324.0,
|
|
"step": 3460
|
|
},
|
|
{
|
|
"entropy": 5.911590433120727,
|
|
"epoch": 0.26959735460027234,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004995855771414673,
|
|
"loss": 5.7337,
|
|
"mean_token_accuracy": 0.15289803743362426,
|
|
"num_tokens": 6024709.0,
|
|
"step": 3465
|
|
},
|
|
{
|
|
"entropy": 5.858439874649048,
|
|
"epoch": 0.2699863839719899,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004995838940431585,
|
|
"loss": 5.5745,
|
|
"mean_token_accuracy": 0.15924426466226577,
|
|
"num_tokens": 6033131.0,
|
|
"step": 3470
|
|
},
|
|
{
|
|
"entropy": 5.817553472518921,
|
|
"epoch": 0.27037541334370746,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004995822075371466,
|
|
"loss": 5.7783,
|
|
"mean_token_accuracy": 0.14763862043619155,
|
|
"num_tokens": 6042310.0,
|
|
"step": 3475
|
|
},
|
|
{
|
|
"entropy": 5.891201305389404,
|
|
"epoch": 0.270764442715425,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004995805176234571,
|
|
"loss": 5.5947,
|
|
"mean_token_accuracy": 0.15696365535259246,
|
|
"num_tokens": 6050617.0,
|
|
"step": 3480
|
|
},
|
|
{
|
|
"entropy": 5.897118473052979,
|
|
"epoch": 0.2711534720871426,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004995788243021158,
|
|
"loss": 5.7699,
|
|
"mean_token_accuracy": 0.14828943312168122,
|
|
"num_tokens": 6060090.0,
|
|
"step": 3485
|
|
},
|
|
{
|
|
"entropy": 5.909312772750854,
|
|
"epoch": 0.27154250145886016,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004995771275731483,
|
|
"loss": 5.7084,
|
|
"mean_token_accuracy": 0.15499398112297058,
|
|
"num_tokens": 6068646.0,
|
|
"step": 3490
|
|
},
|
|
{
|
|
"entropy": 5.904059219360351,
|
|
"epoch": 0.2719315308305777,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004995754274365802,
|
|
"loss": 5.769,
|
|
"mean_token_accuracy": 0.15764224529266357,
|
|
"num_tokens": 6077896.0,
|
|
"step": 3495
|
|
},
|
|
{
|
|
"entropy": 5.8887194156646725,
|
|
"epoch": 0.2723205602022953,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004995737238924376,
|
|
"loss": 5.691,
|
|
"mean_token_accuracy": 0.15045809149742126,
|
|
"num_tokens": 6087189.0,
|
|
"step": 3500
|
|
},
|
|
{
|
|
"entropy": 5.8543816089630125,
|
|
"epoch": 0.2727095895740128,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004995720169407461,
|
|
"loss": 5.6928,
|
|
"mean_token_accuracy": 0.15313887149095534,
|
|
"num_tokens": 6095394.0,
|
|
"step": 3505
|
|
},
|
|
{
|
|
"entropy": 5.90059175491333,
|
|
"epoch": 0.2730986189457304,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004995703065815317,
|
|
"loss": 5.6558,
|
|
"mean_token_accuracy": 0.15778090357780455,
|
|
"num_tokens": 6104135.0,
|
|
"step": 3510
|
|
},
|
|
{
|
|
"entropy": 5.874152612686157,
|
|
"epoch": 0.273487648317448,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004995685928148203,
|
|
"loss": 5.774,
|
|
"mean_token_accuracy": 0.14561692923307418,
|
|
"num_tokens": 6112160.0,
|
|
"step": 3515
|
|
},
|
|
{
|
|
"entropy": 5.9434703350067135,
|
|
"epoch": 0.2738766776891655,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000499566875640638,
|
|
"loss": 5.775,
|
|
"mean_token_accuracy": 0.15645800679922103,
|
|
"num_tokens": 6120575.0,
|
|
"step": 3520
|
|
},
|
|
{
|
|
"entropy": 5.929290294647217,
|
|
"epoch": 0.2742657070608831,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004995651550590108,
|
|
"loss": 5.7745,
|
|
"mean_token_accuracy": 0.15056986957788468,
|
|
"num_tokens": 6129367.0,
|
|
"step": 3525
|
|
},
|
|
{
|
|
"entropy": 5.876437711715698,
|
|
"epoch": 0.2746547364326007,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004995634310699647,
|
|
"loss": 5.744,
|
|
"mean_token_accuracy": 0.15265202671289443,
|
|
"num_tokens": 6137440.0,
|
|
"step": 3530
|
|
},
|
|
{
|
|
"entropy": 5.872723627090454,
|
|
"epoch": 0.2750437658043182,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004995617036735261,
|
|
"loss": 5.673,
|
|
"mean_token_accuracy": 0.154018035531044,
|
|
"num_tokens": 6146770.0,
|
|
"step": 3535
|
|
},
|
|
{
|
|
"entropy": 6.0044420719146725,
|
|
"epoch": 0.2754327951760358,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004995599728697211,
|
|
"loss": 5.7703,
|
|
"mean_token_accuracy": 0.1499793127179146,
|
|
"num_tokens": 6155994.0,
|
|
"step": 3540
|
|
},
|
|
{
|
|
"entropy": 5.789418649673462,
|
|
"epoch": 0.27582182454775334,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004995582386585759,
|
|
"loss": 5.6619,
|
|
"mean_token_accuracy": 0.14758216962218285,
|
|
"num_tokens": 6163941.0,
|
|
"step": 3545
|
|
},
|
|
{
|
|
"entropy": 5.8281224250793455,
|
|
"epoch": 0.2762108539194709,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004995565010401167,
|
|
"loss": 5.7346,
|
|
"mean_token_accuracy": 0.14870691299438477,
|
|
"num_tokens": 6172681.0,
|
|
"step": 3550
|
|
},
|
|
{
|
|
"entropy": 5.9554907321929935,
|
|
"epoch": 0.2765998832911885,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004995547600143702,
|
|
"loss": 5.7072,
|
|
"mean_token_accuracy": 0.14850514829158784,
|
|
"num_tokens": 6181449.0,
|
|
"step": 3555
|
|
},
|
|
{
|
|
"entropy": 5.873755407333374,
|
|
"epoch": 0.27698891266290604,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004995530155813625,
|
|
"loss": 5.6887,
|
|
"mean_token_accuracy": 0.15598696768283843,
|
|
"num_tokens": 6190275.0,
|
|
"step": 3560
|
|
},
|
|
{
|
|
"entropy": 5.884641075134278,
|
|
"epoch": 0.2773779420346236,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004995512677411203,
|
|
"loss": 5.7351,
|
|
"mean_token_accuracy": 0.1550119176506996,
|
|
"num_tokens": 6198521.0,
|
|
"step": 3565
|
|
},
|
|
{
|
|
"entropy": 5.901494312286377,
|
|
"epoch": 0.27776697140634116,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004995495164936698,
|
|
"loss": 5.7628,
|
|
"mean_token_accuracy": 0.1469577133655548,
|
|
"num_tokens": 6207318.0,
|
|
"step": 3570
|
|
},
|
|
{
|
|
"entropy": 5.902689838409424,
|
|
"epoch": 0.27815600077805874,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004995477618390381,
|
|
"loss": 5.651,
|
|
"mean_token_accuracy": 0.15427243560552598,
|
|
"num_tokens": 6216693.0,
|
|
"step": 3575
|
|
},
|
|
{
|
|
"entropy": 5.85602765083313,
|
|
"epoch": 0.27854503014977633,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004995460037772513,
|
|
"loss": 5.7077,
|
|
"mean_token_accuracy": 0.14970823526382446,
|
|
"num_tokens": 6225207.0,
|
|
"step": 3580
|
|
},
|
|
{
|
|
"entropy": 5.885422992706299,
|
|
"epoch": 0.27893405952149386,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004995442423083365,
|
|
"loss": 5.6551,
|
|
"mean_token_accuracy": 0.16121675074100494,
|
|
"num_tokens": 6232653.0,
|
|
"step": 3585
|
|
},
|
|
{
|
|
"entropy": 5.828827238082885,
|
|
"epoch": 0.27932308889321145,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004995424774323201,
|
|
"loss": 5.6419,
|
|
"mean_token_accuracy": 0.15972325801849366,
|
|
"num_tokens": 6241093.0,
|
|
"step": 3590
|
|
},
|
|
{
|
|
"entropy": 5.789525175094605,
|
|
"epoch": 0.279712118264929,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000499540709149229,
|
|
"loss": 5.564,
|
|
"mean_token_accuracy": 0.16275173425674438,
|
|
"num_tokens": 6249144.0,
|
|
"step": 3595
|
|
},
|
|
{
|
|
"entropy": 5.865627717971802,
|
|
"epoch": 0.28010114763664656,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004995389374590901,
|
|
"loss": 5.6389,
|
|
"mean_token_accuracy": 0.15749034732580186,
|
|
"num_tokens": 6257622.0,
|
|
"step": 3600
|
|
},
|
|
{
|
|
"entropy": 5.882948589324951,
|
|
"epoch": 0.28049017700836415,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004995371623619301,
|
|
"loss": 5.6636,
|
|
"mean_token_accuracy": 0.15338655188679695,
|
|
"num_tokens": 6266435.0,
|
|
"step": 3605
|
|
},
|
|
{
|
|
"entropy": 5.8372331142425535,
|
|
"epoch": 0.2808792063800817,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000499535383857776,
|
|
"loss": 5.7877,
|
|
"mean_token_accuracy": 0.149023699760437,
|
|
"num_tokens": 6275053.0,
|
|
"step": 3610
|
|
},
|
|
{
|
|
"entropy": 5.8476598262786865,
|
|
"epoch": 0.28126823575179927,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000499533601946655,
|
|
"loss": 5.6726,
|
|
"mean_token_accuracy": 0.1459781378507614,
|
|
"num_tokens": 6283240.0,
|
|
"step": 3615
|
|
},
|
|
{
|
|
"entropy": 5.800600624084472,
|
|
"epoch": 0.2816572651235168,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004995318166285938,
|
|
"loss": 5.6236,
|
|
"mean_token_accuracy": 0.1582282230257988,
|
|
"num_tokens": 6292133.0,
|
|
"step": 3620
|
|
},
|
|
{
|
|
"entropy": 5.931145143508911,
|
|
"epoch": 0.2820462944952344,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004995300279036199,
|
|
"loss": 5.7512,
|
|
"mean_token_accuracy": 0.15329633504152299,
|
|
"num_tokens": 6300954.0,
|
|
"step": 3625
|
|
},
|
|
{
|
|
"entropy": 5.803219652175903,
|
|
"epoch": 0.28243532386695197,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00049952823577176,
|
|
"loss": 5.623,
|
|
"mean_token_accuracy": 0.16018344163894654,
|
|
"num_tokens": 6309637.0,
|
|
"step": 3630
|
|
},
|
|
{
|
|
"entropy": 5.870447778701783,
|
|
"epoch": 0.2828243532386695,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004995264402330416,
|
|
"loss": 5.6889,
|
|
"mean_token_accuracy": 0.153514064848423,
|
|
"num_tokens": 6318539.0,
|
|
"step": 3635
|
|
},
|
|
{
|
|
"entropy": 5.877357006072998,
|
|
"epoch": 0.2832133826103871,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004995246412874919,
|
|
"loss": 5.6063,
|
|
"mean_token_accuracy": 0.15626251548528672,
|
|
"num_tokens": 6327109.0,
|
|
"step": 3640
|
|
},
|
|
{
|
|
"entropy": 5.796565914154053,
|
|
"epoch": 0.2836024119821047,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000499522838935138,
|
|
"loss": 5.6188,
|
|
"mean_token_accuracy": 0.1544191963970661,
|
|
"num_tokens": 6335555.0,
|
|
"step": 3645
|
|
},
|
|
{
|
|
"entropy": 5.89104151725769,
|
|
"epoch": 0.2839914413538222,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004995210331760074,
|
|
"loss": 5.7761,
|
|
"mean_token_accuracy": 0.15136173665523528,
|
|
"num_tokens": 6344716.0,
|
|
"step": 3650
|
|
},
|
|
{
|
|
"entropy": 5.848493671417236,
|
|
"epoch": 0.2843804707255398,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004995192240101275,
|
|
"loss": 5.6321,
|
|
"mean_token_accuracy": 0.16200316846370696,
|
|
"num_tokens": 6353618.0,
|
|
"step": 3655
|
|
},
|
|
{
|
|
"entropy": 5.9154908657073975,
|
|
"epoch": 0.2847695000972573,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004995174114375258,
|
|
"loss": 5.7482,
|
|
"mean_token_accuracy": 0.14789825528860093,
|
|
"num_tokens": 6362039.0,
|
|
"step": 3660
|
|
},
|
|
{
|
|
"entropy": 5.913218307495117,
|
|
"epoch": 0.2851585294689749,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004995155954582297,
|
|
"loss": 5.6811,
|
|
"mean_token_accuracy": 0.15068026036024093,
|
|
"num_tokens": 6370331.0,
|
|
"step": 3665
|
|
},
|
|
{
|
|
"entropy": 5.845167112350464,
|
|
"epoch": 0.2855475588406925,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004995137760722668,
|
|
"loss": 5.6551,
|
|
"mean_token_accuracy": 0.15810975283384324,
|
|
"num_tokens": 6378943.0,
|
|
"step": 3670
|
|
},
|
|
{
|
|
"entropy": 5.879886245727539,
|
|
"epoch": 0.28593658821241,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004995119532796646,
|
|
"loss": 5.7192,
|
|
"mean_token_accuracy": 0.1432995818555355,
|
|
"num_tokens": 6387745.0,
|
|
"step": 3675
|
|
},
|
|
{
|
|
"entropy": 5.7256762981414795,
|
|
"epoch": 0.2863256175841276,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000499510127080451,
|
|
"loss": 5.5589,
|
|
"mean_token_accuracy": 0.1562187597155571,
|
|
"num_tokens": 6396915.0,
|
|
"step": 3680
|
|
},
|
|
{
|
|
"entropy": 5.798629856109619,
|
|
"epoch": 0.28671464695584514,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004995082974746535,
|
|
"loss": 5.6084,
|
|
"mean_token_accuracy": 0.15959389954805375,
|
|
"num_tokens": 6405453.0,
|
|
"step": 3685
|
|
},
|
|
{
|
|
"entropy": 5.9083412170410154,
|
|
"epoch": 0.28710367632756273,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004995064644622999,
|
|
"loss": 5.6961,
|
|
"mean_token_accuracy": 0.15132231414318084,
|
|
"num_tokens": 6413693.0,
|
|
"step": 3690
|
|
},
|
|
{
|
|
"entropy": 5.764428520202637,
|
|
"epoch": 0.2874927056992803,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004995046280434181,
|
|
"loss": 5.682,
|
|
"mean_token_accuracy": 0.14993201121687888,
|
|
"num_tokens": 6422738.0,
|
|
"step": 3695
|
|
},
|
|
{
|
|
"entropy": 5.837015295028687,
|
|
"epoch": 0.28788173507099785,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004995027882180358,
|
|
"loss": 5.6273,
|
|
"mean_token_accuracy": 0.15370226055383682,
|
|
"num_tokens": 6431743.0,
|
|
"step": 3700
|
|
},
|
|
{
|
|
"entropy": 5.881600713729858,
|
|
"epoch": 0.28827076444271543,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004995009449861812,
|
|
"loss": 5.6616,
|
|
"mean_token_accuracy": 0.15563700199127198,
|
|
"num_tokens": 6440586.0,
|
|
"step": 3705
|
|
},
|
|
{
|
|
"entropy": 5.804992055892944,
|
|
"epoch": 0.28865979381443296,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000499499098347882,
|
|
"loss": 5.7168,
|
|
"mean_token_accuracy": 0.1542726181447506,
|
|
"num_tokens": 6449644.0,
|
|
"step": 3710
|
|
},
|
|
{
|
|
"entropy": 5.833136034011841,
|
|
"epoch": 0.28904882318615055,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004994972483031662,
|
|
"loss": 5.6053,
|
|
"mean_token_accuracy": 0.16261792182922363,
|
|
"num_tokens": 6458752.0,
|
|
"step": 3715
|
|
},
|
|
{
|
|
"entropy": 5.797244644165039,
|
|
"epoch": 0.28943785255786814,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.000499495394852062,
|
|
"loss": 5.6716,
|
|
"mean_token_accuracy": 0.15677656084299088,
|
|
"num_tokens": 6468333.0,
|
|
"step": 3720
|
|
},
|
|
{
|
|
"entropy": 5.707669687271118,
|
|
"epoch": 0.28982688192958567,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004994935379945977,
|
|
"loss": 5.5339,
|
|
"mean_token_accuracy": 0.15437540858983995,
|
|
"num_tokens": 6477406.0,
|
|
"step": 3725
|
|
},
|
|
{
|
|
"entropy": 5.859027671813965,
|
|
"epoch": 0.29021591130130325,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004994916777308012,
|
|
"loss": 5.6851,
|
|
"mean_token_accuracy": 0.1511788085103035,
|
|
"num_tokens": 6486399.0,
|
|
"step": 3730
|
|
},
|
|
{
|
|
"entropy": 5.791624116897583,
|
|
"epoch": 0.29060494067302084,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004994898140607007,
|
|
"loss": 5.5922,
|
|
"mean_token_accuracy": 0.15610771924257277,
|
|
"num_tokens": 6494853.0,
|
|
"step": 3735
|
|
},
|
|
{
|
|
"entropy": 5.872024250030518,
|
|
"epoch": 0.29099397004473837,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004994879469843247,
|
|
"loss": 5.7565,
|
|
"mean_token_accuracy": 0.1508682370185852,
|
|
"num_tokens": 6503301.0,
|
|
"step": 3740
|
|
},
|
|
{
|
|
"entropy": 5.838651132583618,
|
|
"epoch": 0.29138299941645596,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004994860765017013,
|
|
"loss": 5.6465,
|
|
"mean_token_accuracy": 0.15341054350137712,
|
|
"num_tokens": 6512685.0,
|
|
"step": 3745
|
|
},
|
|
{
|
|
"entropy": 5.834665298461914,
|
|
"epoch": 0.2917720287881735,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000499484202612859,
|
|
"loss": 5.7428,
|
|
"mean_token_accuracy": 0.1516564279794693,
|
|
"num_tokens": 6520673.0,
|
|
"step": 3750
|
|
},
|
|
{
|
|
"entropy": 5.879530334472657,
|
|
"epoch": 0.2921610581598911,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004994823253178264,
|
|
"loss": 5.657,
|
|
"mean_token_accuracy": 0.15068983137607575,
|
|
"num_tokens": 6529039.0,
|
|
"step": 3755
|
|
},
|
|
{
|
|
"entropy": 5.832844400405884,
|
|
"epoch": 0.29255008753160866,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004994804446166317,
|
|
"loss": 5.7447,
|
|
"mean_token_accuracy": 0.1464340180158615,
|
|
"num_tokens": 6537932.0,
|
|
"step": 3760
|
|
},
|
|
{
|
|
"entropy": 5.897266864776611,
|
|
"epoch": 0.2929391169033262,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004994785605093035,
|
|
"loss": 5.6243,
|
|
"mean_token_accuracy": 0.15435930714011192,
|
|
"num_tokens": 6546278.0,
|
|
"step": 3765
|
|
},
|
|
{
|
|
"entropy": 5.840794086456299,
|
|
"epoch": 0.2933281462750438,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004994766729958705,
|
|
"loss": 5.6752,
|
|
"mean_token_accuracy": 0.16036221235990525,
|
|
"num_tokens": 6554449.0,
|
|
"step": 3770
|
|
},
|
|
{
|
|
"entropy": 5.830932760238648,
|
|
"epoch": 0.2937171756467613,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004994747820763612,
|
|
"loss": 5.6631,
|
|
"mean_token_accuracy": 0.15727959871292113,
|
|
"num_tokens": 6563272.0,
|
|
"step": 3775
|
|
},
|
|
{
|
|
"entropy": 5.917678117752075,
|
|
"epoch": 0.2941062050184789,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004994728877508046,
|
|
"loss": 5.6737,
|
|
"mean_token_accuracy": 0.15500990450382232,
|
|
"num_tokens": 6571864.0,
|
|
"step": 3780
|
|
},
|
|
{
|
|
"entropy": 5.834184646606445,
|
|
"epoch": 0.2944952343901965,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004994709900192289,
|
|
"loss": 5.6644,
|
|
"mean_token_accuracy": 0.15712282955646514,
|
|
"num_tokens": 6580435.0,
|
|
"step": 3785
|
|
},
|
|
{
|
|
"entropy": 5.909469509124756,
|
|
"epoch": 0.294884263761914,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004994690888816635,
|
|
"loss": 5.6642,
|
|
"mean_token_accuracy": 0.15690299719572068,
|
|
"num_tokens": 6589261.0,
|
|
"step": 3790
|
|
},
|
|
{
|
|
"entropy": 5.864827394485474,
|
|
"epoch": 0.2952732931336316,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004994671843381367,
|
|
"loss": 5.7462,
|
|
"mean_token_accuracy": 0.15970321893692016,
|
|
"num_tokens": 6598057.0,
|
|
"step": 3795
|
|
},
|
|
{
|
|
"entropy": 5.95170750617981,
|
|
"epoch": 0.29566232250534913,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004994652763886778,
|
|
"loss": 5.7119,
|
|
"mean_token_accuracy": 0.14755399972200395,
|
|
"num_tokens": 6606439.0,
|
|
"step": 3800
|
|
},
|
|
{
|
|
"entropy": 5.879061555862426,
|
|
"epoch": 0.2960513518770667,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004994633650333155,
|
|
"loss": 5.714,
|
|
"mean_token_accuracy": 0.15110620558261872,
|
|
"num_tokens": 6615350.0,
|
|
"step": 3805
|
|
},
|
|
{
|
|
"entropy": 5.87994384765625,
|
|
"epoch": 0.2964403812487843,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004994614502720792,
|
|
"loss": 5.769,
|
|
"mean_token_accuracy": 0.15212479382753372,
|
|
"num_tokens": 6624258.0,
|
|
"step": 3810
|
|
},
|
|
{
|
|
"entropy": 5.970225715637207,
|
|
"epoch": 0.29682941062050183,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004994595321049974,
|
|
"loss": 5.748,
|
|
"mean_token_accuracy": 0.1487318679690361,
|
|
"num_tokens": 6632382.0,
|
|
"step": 3815
|
|
},
|
|
{
|
|
"entropy": 5.829820251464843,
|
|
"epoch": 0.2972184399922194,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004994576105320994,
|
|
"loss": 5.6629,
|
|
"mean_token_accuracy": 0.15289796888828278,
|
|
"num_tokens": 6640482.0,
|
|
"step": 3820
|
|
},
|
|
{
|
|
"entropy": 5.817120790481567,
|
|
"epoch": 0.29760746936393695,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004994556855534146,
|
|
"loss": 5.6476,
|
|
"mean_token_accuracy": 0.15640270859003066,
|
|
"num_tokens": 6648912.0,
|
|
"step": 3825
|
|
},
|
|
{
|
|
"entropy": 5.801205730438232,
|
|
"epoch": 0.29799649873565454,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004994537571689719,
|
|
"loss": 5.6288,
|
|
"mean_token_accuracy": 0.15806550532579422,
|
|
"num_tokens": 6656912.0,
|
|
"step": 3830
|
|
},
|
|
{
|
|
"entropy": 5.728374814987182,
|
|
"epoch": 0.2983855281073721,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004994518253788007,
|
|
"loss": 5.6519,
|
|
"mean_token_accuracy": 0.15597154051065446,
|
|
"num_tokens": 6665900.0,
|
|
"step": 3835
|
|
},
|
|
{
|
|
"entropy": 5.88460373878479,
|
|
"epoch": 0.29877455747908965,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004994498901829304,
|
|
"loss": 5.6988,
|
|
"mean_token_accuracy": 0.15435834527015685,
|
|
"num_tokens": 6674426.0,
|
|
"step": 3840
|
|
},
|
|
{
|
|
"entropy": 5.884772253036499,
|
|
"epoch": 0.29916358685080724,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004994479515813903,
|
|
"loss": 5.6541,
|
|
"mean_token_accuracy": 0.15605763345956802,
|
|
"num_tokens": 6683566.0,
|
|
"step": 3845
|
|
},
|
|
{
|
|
"entropy": 5.798302364349365,
|
|
"epoch": 0.2995526162225248,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004994460095742096,
|
|
"loss": 5.6867,
|
|
"mean_token_accuracy": 0.1584527686238289,
|
|
"num_tokens": 6693341.0,
|
|
"step": 3850
|
|
},
|
|
{
|
|
"entropy": 5.827801609039307,
|
|
"epoch": 0.29994164559424236,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000499444064161418,
|
|
"loss": 5.5855,
|
|
"mean_token_accuracy": 0.15363955348730088,
|
|
"num_tokens": 6701734.0,
|
|
"step": 3855
|
|
},
|
|
{
|
|
"entropy": 5.810207843780518,
|
|
"epoch": 0.30033067496595994,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000499442115343045,
|
|
"loss": 5.6245,
|
|
"mean_token_accuracy": 0.1571832537651062,
|
|
"num_tokens": 6710572.0,
|
|
"step": 3860
|
|
},
|
|
{
|
|
"entropy": 5.891124248504639,
|
|
"epoch": 0.3007197043376775,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004994401631191202,
|
|
"loss": 5.7396,
|
|
"mean_token_accuracy": 0.14851216599345207,
|
|
"num_tokens": 6719355.0,
|
|
"step": 3865
|
|
},
|
|
{
|
|
"entropy": 5.982782506942749,
|
|
"epoch": 0.30110873370939506,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004994382074896731,
|
|
"loss": 5.7702,
|
|
"mean_token_accuracy": 0.14574634730815889,
|
|
"num_tokens": 6729279.0,
|
|
"step": 3870
|
|
},
|
|
{
|
|
"entropy": 5.794736433029175,
|
|
"epoch": 0.30149776308111265,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004994362484547335,
|
|
"loss": 5.5907,
|
|
"mean_token_accuracy": 0.15171013325452803,
|
|
"num_tokens": 6737318.0,
|
|
"step": 3875
|
|
},
|
|
{
|
|
"entropy": 5.8127483367919925,
|
|
"epoch": 0.3018867924528302,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004994342860143309,
|
|
"loss": 5.6749,
|
|
"mean_token_accuracy": 0.1597735196352005,
|
|
"num_tokens": 6746520.0,
|
|
"step": 3880
|
|
},
|
|
{
|
|
"entropy": 5.835038423538208,
|
|
"epoch": 0.30227582182454776,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004994323201684953,
|
|
"loss": 5.5972,
|
|
"mean_token_accuracy": 0.1554494395852089,
|
|
"num_tokens": 6755685.0,
|
|
"step": 3885
|
|
},
|
|
{
|
|
"entropy": 5.8171398639678955,
|
|
"epoch": 0.3026648511962653,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004994303509172566,
|
|
"loss": 5.7417,
|
|
"mean_token_accuracy": 0.15470685362815856,
|
|
"num_tokens": 6764347.0,
|
|
"step": 3890
|
|
},
|
|
{
|
|
"entropy": 5.926692819595337,
|
|
"epoch": 0.3030538805679829,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004994283782606444,
|
|
"loss": 5.7076,
|
|
"mean_token_accuracy": 0.15835860669612883,
|
|
"num_tokens": 6772887.0,
|
|
"step": 3895
|
|
},
|
|
{
|
|
"entropy": 5.7954470157623295,
|
|
"epoch": 0.30344290993970047,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004994264021986888,
|
|
"loss": 5.6726,
|
|
"mean_token_accuracy": 0.14857605174183847,
|
|
"num_tokens": 6780860.0,
|
|
"step": 3900
|
|
},
|
|
{
|
|
"entropy": 5.790612697601318,
|
|
"epoch": 0.303831939311418,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004994244227314197,
|
|
"loss": 5.6931,
|
|
"mean_token_accuracy": 0.15410419106483458,
|
|
"num_tokens": 6789491.0,
|
|
"step": 3905
|
|
},
|
|
{
|
|
"entropy": 5.917981243133545,
|
|
"epoch": 0.3042209686831356,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004994224398588672,
|
|
"loss": 5.6175,
|
|
"mean_token_accuracy": 0.15719443410634995,
|
|
"num_tokens": 6797128.0,
|
|
"step": 3910
|
|
},
|
|
{
|
|
"entropy": 5.842257022857666,
|
|
"epoch": 0.3046099980548531,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004994204535810615,
|
|
"loss": 5.6526,
|
|
"mean_token_accuracy": 0.15690061897039415,
|
|
"num_tokens": 6805235.0,
|
|
"step": 3915
|
|
},
|
|
{
|
|
"entropy": 5.784561395645142,
|
|
"epoch": 0.3049990274265707,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004994184638980326,
|
|
"loss": 5.577,
|
|
"mean_token_accuracy": 0.1572084903717041,
|
|
"num_tokens": 6813863.0,
|
|
"step": 3920
|
|
},
|
|
{
|
|
"entropy": 5.830573415756225,
|
|
"epoch": 0.3053880567982883,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004994164708098107,
|
|
"loss": 5.6372,
|
|
"mean_token_accuracy": 0.15513723939657212,
|
|
"num_tokens": 6822015.0,
|
|
"step": 3925
|
|
},
|
|
{
|
|
"entropy": 5.889108514785766,
|
|
"epoch": 0.3057770861700058,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000499414474316426,
|
|
"loss": 5.6945,
|
|
"mean_token_accuracy": 0.15233523547649383,
|
|
"num_tokens": 6830598.0,
|
|
"step": 3930
|
|
},
|
|
{
|
|
"entropy": 5.857270097732544,
|
|
"epoch": 0.3061661155417234,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004994124744179088,
|
|
"loss": 5.6859,
|
|
"mean_token_accuracy": 0.16359390765428544,
|
|
"num_tokens": 6839129.0,
|
|
"step": 3935
|
|
},
|
|
{
|
|
"entropy": 5.8585127830505375,
|
|
"epoch": 0.306555144913441,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004994104711142896,
|
|
"loss": 5.6445,
|
|
"mean_token_accuracy": 0.15050655901432036,
|
|
"num_tokens": 6848199.0,
|
|
"step": 3940
|
|
},
|
|
{
|
|
"entropy": 5.837422466278076,
|
|
"epoch": 0.3069441742851585,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004994084644055986,
|
|
"loss": 5.6615,
|
|
"mean_token_accuracy": 0.15743141025304794,
|
|
"num_tokens": 6857340.0,
|
|
"step": 3945
|
|
},
|
|
{
|
|
"entropy": 5.805282306671143,
|
|
"epoch": 0.3073332036568761,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004994064542918664,
|
|
"loss": 5.6911,
|
|
"mean_token_accuracy": 0.1498067356646061,
|
|
"num_tokens": 6865830.0,
|
|
"step": 3950
|
|
},
|
|
{
|
|
"entropy": 5.843528699874878,
|
|
"epoch": 0.30772223302859364,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004994044407731235,
|
|
"loss": 5.7512,
|
|
"mean_token_accuracy": 0.1488284096121788,
|
|
"num_tokens": 6874318.0,
|
|
"step": 3955
|
|
},
|
|
{
|
|
"entropy": 6.015487432479858,
|
|
"epoch": 0.3081112624003112,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004994024238494002,
|
|
"loss": 5.7414,
|
|
"mean_token_accuracy": 0.15100244730710982,
|
|
"num_tokens": 6882008.0,
|
|
"step": 3960
|
|
},
|
|
{
|
|
"entropy": 5.84633150100708,
|
|
"epoch": 0.3085002917720288,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004994004035207274,
|
|
"loss": 5.595,
|
|
"mean_token_accuracy": 0.1584687501192093,
|
|
"num_tokens": 6890411.0,
|
|
"step": 3965
|
|
},
|
|
{
|
|
"entropy": 5.800809621810913,
|
|
"epoch": 0.30888932114374634,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004993983797871356,
|
|
"loss": 5.6356,
|
|
"mean_token_accuracy": 0.152000392973423,
|
|
"num_tokens": 6899201.0,
|
|
"step": 3970
|
|
},
|
|
{
|
|
"entropy": 5.80447564125061,
|
|
"epoch": 0.30927835051546393,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004993963526486555,
|
|
"loss": 5.6534,
|
|
"mean_token_accuracy": 0.15221117436885834,
|
|
"num_tokens": 6907470.0,
|
|
"step": 3975
|
|
},
|
|
{
|
|
"entropy": 5.788397216796875,
|
|
"epoch": 0.30966737988718146,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000499394322105318,
|
|
"loss": 5.6828,
|
|
"mean_token_accuracy": 0.15586572289466857,
|
|
"num_tokens": 6916542.0,
|
|
"step": 3980
|
|
},
|
|
{
|
|
"entropy": 5.851479148864746,
|
|
"epoch": 0.31005640925889905,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004993922881571538,
|
|
"loss": 5.6814,
|
|
"mean_token_accuracy": 0.15342268645763396,
|
|
"num_tokens": 6925974.0,
|
|
"step": 3985
|
|
},
|
|
{
|
|
"entropy": 5.911538314819336,
|
|
"epoch": 0.31044543863061663,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004993902508041939,
|
|
"loss": 5.703,
|
|
"mean_token_accuracy": 0.14747922271490096,
|
|
"num_tokens": 6934987.0,
|
|
"step": 3990
|
|
},
|
|
{
|
|
"entropy": 5.766879081726074,
|
|
"epoch": 0.31083446800233416,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000499388210046469,
|
|
"loss": 5.5871,
|
|
"mean_token_accuracy": 0.15272050797939302,
|
|
"num_tokens": 6944497.0,
|
|
"step": 3995
|
|
},
|
|
{
|
|
"entropy": 5.847130870819091,
|
|
"epoch": 0.31122349737405175,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004993861658840102,
|
|
"loss": 5.7243,
|
|
"mean_token_accuracy": 0.14793727397918702,
|
|
"num_tokens": 6953394.0,
|
|
"step": 4000
|
|
},
|
|
{
|
|
"entropy": 5.84558367729187,
|
|
"epoch": 0.3116125267457693,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004993841183168484,
|
|
"loss": 5.6365,
|
|
"mean_token_accuracy": 0.15578553080558777,
|
|
"num_tokens": 6961715.0,
|
|
"step": 4005
|
|
},
|
|
{
|
|
"entropy": 5.784832239151001,
|
|
"epoch": 0.31200155611748687,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004993820673450148,
|
|
"loss": 5.6423,
|
|
"mean_token_accuracy": 0.15401849076151847,
|
|
"num_tokens": 6970041.0,
|
|
"step": 4010
|
|
},
|
|
{
|
|
"entropy": 5.887779331207275,
|
|
"epoch": 0.31239058548920445,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004993800129685404,
|
|
"loss": 5.7804,
|
|
"mean_token_accuracy": 0.14733504951000215,
|
|
"num_tokens": 6979522.0,
|
|
"step": 4015
|
|
},
|
|
{
|
|
"entropy": 5.884895706176758,
|
|
"epoch": 0.312779614860922,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004993779551874565,
|
|
"loss": 5.7401,
|
|
"mean_token_accuracy": 0.14512501955032348,
|
|
"num_tokens": 6988470.0,
|
|
"step": 4020
|
|
},
|
|
{
|
|
"entropy": 5.913160419464111,
|
|
"epoch": 0.31316864423263957,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004993758940017943,
|
|
"loss": 5.745,
|
|
"mean_token_accuracy": 0.15878498256206514,
|
|
"num_tokens": 6996696.0,
|
|
"step": 4025
|
|
},
|
|
{
|
|
"entropy": 5.890307474136352,
|
|
"epoch": 0.31355767360435716,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000499373829411585,
|
|
"loss": 5.6215,
|
|
"mean_token_accuracy": 0.15232147574424743,
|
|
"num_tokens": 7005297.0,
|
|
"step": 4030
|
|
},
|
|
{
|
|
"entropy": 5.814219665527344,
|
|
"epoch": 0.3139467029760747,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00049937176141686,
|
|
"loss": 5.6209,
|
|
"mean_token_accuracy": 0.15302640944719315,
|
|
"num_tokens": 7013569.0,
|
|
"step": 4035
|
|
},
|
|
{
|
|
"entropy": 5.770711660385132,
|
|
"epoch": 0.3143357323477923,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004993696900176506,
|
|
"loss": 5.5739,
|
|
"mean_token_accuracy": 0.15835325047373772,
|
|
"num_tokens": 7021449.0,
|
|
"step": 4040
|
|
},
|
|
{
|
|
"entropy": 5.825836849212647,
|
|
"epoch": 0.3147247617195098,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004993676152139883,
|
|
"loss": 5.6855,
|
|
"mean_token_accuracy": 0.1571549579501152,
|
|
"num_tokens": 7029663.0,
|
|
"step": 4045
|
|
},
|
|
{
|
|
"entropy": 5.803576135635376,
|
|
"epoch": 0.3151137910912274,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004993655370059046,
|
|
"loss": 5.6877,
|
|
"mean_token_accuracy": 0.154311640560627,
|
|
"num_tokens": 7039038.0,
|
|
"step": 4050
|
|
},
|
|
{
|
|
"entropy": 5.823104667663574,
|
|
"epoch": 0.315502820462945,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004993634553934309,
|
|
"loss": 5.645,
|
|
"mean_token_accuracy": 0.15580660626292228,
|
|
"num_tokens": 7047595.0,
|
|
"step": 4055
|
|
},
|
|
{
|
|
"entropy": 5.835638093948364,
|
|
"epoch": 0.3158918498346625,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004993613703765989,
|
|
"loss": 5.6582,
|
|
"mean_token_accuracy": 0.15214158296585084,
|
|
"num_tokens": 7055711.0,
|
|
"step": 4060
|
|
},
|
|
{
|
|
"entropy": 5.870501375198364,
|
|
"epoch": 0.3162808792063801,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004993592819554402,
|
|
"loss": 5.6272,
|
|
"mean_token_accuracy": 0.15837595313787461,
|
|
"num_tokens": 7064100.0,
|
|
"step": 4065
|
|
},
|
|
{
|
|
"entropy": 5.80830135345459,
|
|
"epoch": 0.3166699085780976,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004993571901299866,
|
|
"loss": 5.5916,
|
|
"mean_token_accuracy": 0.15826652497053145,
|
|
"num_tokens": 7073040.0,
|
|
"step": 4070
|
|
},
|
|
{
|
|
"entropy": 5.811197662353516,
|
|
"epoch": 0.3170589379498152,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004993550949002697,
|
|
"loss": 5.6968,
|
|
"mean_token_accuracy": 0.1517757922410965,
|
|
"num_tokens": 7081513.0,
|
|
"step": 4075
|
|
},
|
|
{
|
|
"entropy": 5.772473526000977,
|
|
"epoch": 0.3174479673215328,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004993529962663213,
|
|
"loss": 5.595,
|
|
"mean_token_accuracy": 0.1613408699631691,
|
|
"num_tokens": 7090704.0,
|
|
"step": 4080
|
|
},
|
|
{
|
|
"entropy": 5.818785381317139,
|
|
"epoch": 0.31783699669325033,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004993508942281732,
|
|
"loss": 5.7533,
|
|
"mean_token_accuracy": 0.14853261411190033,
|
|
"num_tokens": 7099692.0,
|
|
"step": 4085
|
|
},
|
|
{
|
|
"entropy": 5.7818577766418455,
|
|
"epoch": 0.3182260260649679,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004993487887858575,
|
|
"loss": 5.5793,
|
|
"mean_token_accuracy": 0.15307215079665185,
|
|
"num_tokens": 7108021.0,
|
|
"step": 4090
|
|
},
|
|
{
|
|
"entropy": 5.80325174331665,
|
|
"epoch": 0.31861505543668545,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000499346679939406,
|
|
"loss": 5.6545,
|
|
"mean_token_accuracy": 0.1577788397669792,
|
|
"num_tokens": 7116689.0,
|
|
"step": 4095
|
|
},
|
|
{
|
|
"entropy": 5.832878112792969,
|
|
"epoch": 0.31900408480840303,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004993445676888507,
|
|
"loss": 5.7519,
|
|
"mean_token_accuracy": 0.1521778553724289,
|
|
"num_tokens": 7125453.0,
|
|
"step": 4100
|
|
},
|
|
{
|
|
"entropy": 5.942759323120117,
|
|
"epoch": 0.3193931141801206,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004993424520342236,
|
|
"loss": 5.7843,
|
|
"mean_token_accuracy": 0.15119208842515947,
|
|
"num_tokens": 7133692.0,
|
|
"step": 4105
|
|
},
|
|
{
|
|
"entropy": 5.860222673416137,
|
|
"epoch": 0.31978214355183815,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004993403329755569,
|
|
"loss": 5.5968,
|
|
"mean_token_accuracy": 0.15934908539056777,
|
|
"num_tokens": 7142362.0,
|
|
"step": 4110
|
|
},
|
|
{
|
|
"entropy": 5.746327972412109,
|
|
"epoch": 0.32017117292355574,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004993382105128828,
|
|
"loss": 5.6226,
|
|
"mean_token_accuracy": 0.15567729622125626,
|
|
"num_tokens": 7151020.0,
|
|
"step": 4115
|
|
},
|
|
{
|
|
"entropy": 5.768520021438599,
|
|
"epoch": 0.32056020229527327,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004993360846462333,
|
|
"loss": 5.5285,
|
|
"mean_token_accuracy": 0.16255829334259034,
|
|
"num_tokens": 7159453.0,
|
|
"step": 4120
|
|
},
|
|
{
|
|
"entropy": 5.889703607559204,
|
|
"epoch": 0.32094923166699085,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004993339553756408,
|
|
"loss": 5.7937,
|
|
"mean_token_accuracy": 0.1460296593606472,
|
|
"num_tokens": 7168758.0,
|
|
"step": 4125
|
|
},
|
|
{
|
|
"entropy": 5.824968242645264,
|
|
"epoch": 0.32133826103870844,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004993318227011378,
|
|
"loss": 5.6026,
|
|
"mean_token_accuracy": 0.15972633063793182,
|
|
"num_tokens": 7177835.0,
|
|
"step": 4130
|
|
},
|
|
{
|
|
"entropy": 5.817380714416504,
|
|
"epoch": 0.32172729041042597,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004993296866227562,
|
|
"loss": 5.6396,
|
|
"mean_token_accuracy": 0.16363780200481415,
|
|
"num_tokens": 7186424.0,
|
|
"step": 4135
|
|
},
|
|
{
|
|
"entropy": 5.817440557479858,
|
|
"epoch": 0.32211631978214356,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004993275471405288,
|
|
"loss": 5.6284,
|
|
"mean_token_accuracy": 0.16064855307340623,
|
|
"num_tokens": 7194800.0,
|
|
"step": 4140
|
|
},
|
|
{
|
|
"entropy": 5.759157609939575,
|
|
"epoch": 0.32250534915386114,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004993254042544879,
|
|
"loss": 5.5543,
|
|
"mean_token_accuracy": 0.16035097762942313,
|
|
"num_tokens": 7203820.0,
|
|
"step": 4145
|
|
},
|
|
{
|
|
"entropy": 5.781700611114502,
|
|
"epoch": 0.3228943785255787,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000499323257964666,
|
|
"loss": 5.5454,
|
|
"mean_token_accuracy": 0.1592766359448433,
|
|
"num_tokens": 7211793.0,
|
|
"step": 4150
|
|
},
|
|
{
|
|
"entropy": 5.802039670944214,
|
|
"epoch": 0.32328340789729626,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004993211082710957,
|
|
"loss": 5.6027,
|
|
"mean_token_accuracy": 0.1580141991376877,
|
|
"num_tokens": 7220471.0,
|
|
"step": 4155
|
|
},
|
|
{
|
|
"entropy": 5.803948020935058,
|
|
"epoch": 0.3236724372690138,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004993189551738097,
|
|
"loss": 5.6609,
|
|
"mean_token_accuracy": 0.1602739378809929,
|
|
"num_tokens": 7228788.0,
|
|
"step": 4160
|
|
},
|
|
{
|
|
"entropy": 5.875597524642944,
|
|
"epoch": 0.3240614666407314,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004993167986728405,
|
|
"loss": 5.8232,
|
|
"mean_token_accuracy": 0.15174989998340607,
|
|
"num_tokens": 7237707.0,
|
|
"step": 4165
|
|
},
|
|
{
|
|
"entropy": 5.858319091796875,
|
|
"epoch": 0.32445049601244896,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000499314638768221,
|
|
"loss": 5.5789,
|
|
"mean_token_accuracy": 0.1572333574295044,
|
|
"num_tokens": 7246296.0,
|
|
"step": 4170
|
|
},
|
|
{
|
|
"entropy": 5.758087635040283,
|
|
"epoch": 0.3248395253841665,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004993124754599839,
|
|
"loss": 5.5103,
|
|
"mean_token_accuracy": 0.16214703321456908,
|
|
"num_tokens": 7255076.0,
|
|
"step": 4175
|
|
},
|
|
{
|
|
"entropy": 5.6478697776794435,
|
|
"epoch": 0.3252285547558841,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004993103087481619,
|
|
"loss": 5.599,
|
|
"mean_token_accuracy": 0.15897218883037567,
|
|
"num_tokens": 7263169.0,
|
|
"step": 4180
|
|
},
|
|
{
|
|
"entropy": 5.875939607620239,
|
|
"epoch": 0.3256175841276016,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004993081386327881,
|
|
"loss": 5.6549,
|
|
"mean_token_accuracy": 0.1627318650484085,
|
|
"num_tokens": 7271748.0,
|
|
"step": 4185
|
|
},
|
|
{
|
|
"entropy": 5.7767092227935795,
|
|
"epoch": 0.3260066134993192,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004993059651138953,
|
|
"loss": 5.4638,
|
|
"mean_token_accuracy": 0.1650639668107033,
|
|
"num_tokens": 7280291.0,
|
|
"step": 4190
|
|
},
|
|
{
|
|
"entropy": 5.714006567001343,
|
|
"epoch": 0.3263956428710368,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004993037881915165,
|
|
"loss": 5.6706,
|
|
"mean_token_accuracy": 0.15370635092258453,
|
|
"num_tokens": 7290307.0,
|
|
"step": 4195
|
|
},
|
|
{
|
|
"entropy": 5.853940105438232,
|
|
"epoch": 0.3267846722427543,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004993016078656847,
|
|
"loss": 5.754,
|
|
"mean_token_accuracy": 0.1487473540008068,
|
|
"num_tokens": 7297942.0,
|
|
"step": 4200
|
|
},
|
|
{
|
|
"entropy": 5.7838770866394045,
|
|
"epoch": 0.3271737016144719,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000499299424136433,
|
|
"loss": 5.6306,
|
|
"mean_token_accuracy": 0.15384245216846465,
|
|
"num_tokens": 7307378.0,
|
|
"step": 4205
|
|
},
|
|
{
|
|
"entropy": 5.778017473220825,
|
|
"epoch": 0.32756273098618943,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004992972370037946,
|
|
"loss": 5.5811,
|
|
"mean_token_accuracy": 0.1592706561088562,
|
|
"num_tokens": 7315985.0,
|
|
"step": 4210
|
|
},
|
|
{
|
|
"entropy": 5.843814849853516,
|
|
"epoch": 0.327951760357907,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004992950464678026,
|
|
"loss": 5.691,
|
|
"mean_token_accuracy": 0.1587142139673233,
|
|
"num_tokens": 7324142.0,
|
|
"step": 4215
|
|
},
|
|
{
|
|
"entropy": 5.740630483627319,
|
|
"epoch": 0.3283407897296246,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004992928525284903,
|
|
"loss": 5.5362,
|
|
"mean_token_accuracy": 0.16127856969833373,
|
|
"num_tokens": 7333012.0,
|
|
"step": 4220
|
|
},
|
|
{
|
|
"entropy": 5.765237712860108,
|
|
"epoch": 0.32872981910134214,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000499290655185891,
|
|
"loss": 5.5906,
|
|
"mean_token_accuracy": 0.160532608628273,
|
|
"num_tokens": 7341838.0,
|
|
"step": 4225
|
|
},
|
|
{
|
|
"entropy": 5.7777024269104,
|
|
"epoch": 0.3291188484730597,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000499288454440038,
|
|
"loss": 5.5255,
|
|
"mean_token_accuracy": 0.17211012840270995,
|
|
"num_tokens": 7349986.0,
|
|
"step": 4230
|
|
},
|
|
{
|
|
"entropy": 5.856859874725342,
|
|
"epoch": 0.3295078778447773,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004992862502909645,
|
|
"loss": 5.7791,
|
|
"mean_token_accuracy": 0.14971803575754167,
|
|
"num_tokens": 7359428.0,
|
|
"step": 4235
|
|
},
|
|
{
|
|
"entropy": 5.868747282028198,
|
|
"epoch": 0.32989690721649484,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004992840427387043,
|
|
"loss": 5.6902,
|
|
"mean_token_accuracy": 0.15117943584918975,
|
|
"num_tokens": 7368524.0,
|
|
"step": 4240
|
|
},
|
|
{
|
|
"entropy": 5.838213348388672,
|
|
"epoch": 0.3302859365882124,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004992818317832908,
|
|
"loss": 5.5728,
|
|
"mean_token_accuracy": 0.1599339485168457,
|
|
"num_tokens": 7377979.0,
|
|
"step": 4245
|
|
},
|
|
{
|
|
"entropy": 5.684649276733398,
|
|
"epoch": 0.33067496595992996,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004992796174247574,
|
|
"loss": 5.4922,
|
|
"mean_token_accuracy": 0.15754138231277465,
|
|
"num_tokens": 7386283.0,
|
|
"step": 4250
|
|
},
|
|
{
|
|
"entropy": 5.7293774604797365,
|
|
"epoch": 0.33106399533164754,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004992773996631378,
|
|
"loss": 5.6276,
|
|
"mean_token_accuracy": 0.15059794411063193,
|
|
"num_tokens": 7395409.0,
|
|
"step": 4255
|
|
},
|
|
{
|
|
"entropy": 5.841209554672242,
|
|
"epoch": 0.33145302470336513,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004992751784984656,
|
|
"loss": 5.705,
|
|
"mean_token_accuracy": 0.1574711725115776,
|
|
"num_tokens": 7403389.0,
|
|
"step": 4260
|
|
},
|
|
{
|
|
"entropy": 5.814565706253052,
|
|
"epoch": 0.33184205407508266,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004992729539307745,
|
|
"loss": 5.6165,
|
|
"mean_token_accuracy": 0.15815107226371766,
|
|
"num_tokens": 7411506.0,
|
|
"step": 4265
|
|
},
|
|
{
|
|
"entropy": 5.849872016906739,
|
|
"epoch": 0.33223108344680025,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004992707259600984,
|
|
"loss": 5.7025,
|
|
"mean_token_accuracy": 0.15787684619426728,
|
|
"num_tokens": 7420219.0,
|
|
"step": 4270
|
|
},
|
|
{
|
|
"entropy": 5.829010963439941,
|
|
"epoch": 0.3326201128185178,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004992684945864709,
|
|
"loss": 5.6124,
|
|
"mean_token_accuracy": 0.16116924285888673,
|
|
"num_tokens": 7428442.0,
|
|
"step": 4275
|
|
},
|
|
{
|
|
"entropy": 5.769632053375244,
|
|
"epoch": 0.33300914219023536,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004992662598099261,
|
|
"loss": 5.5713,
|
|
"mean_token_accuracy": 0.1633827120065689,
|
|
"num_tokens": 7436364.0,
|
|
"step": 4280
|
|
},
|
|
{
|
|
"entropy": 5.811918067932129,
|
|
"epoch": 0.33339817156195295,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004992640216304975,
|
|
"loss": 5.6446,
|
|
"mean_token_accuracy": 0.14872778430581093,
|
|
"num_tokens": 7444122.0,
|
|
"step": 4285
|
|
},
|
|
{
|
|
"entropy": 5.867029237747192,
|
|
"epoch": 0.3337872009336705,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004992617800482196,
|
|
"loss": 5.6601,
|
|
"mean_token_accuracy": 0.15238194465637206,
|
|
"num_tokens": 7454122.0,
|
|
"step": 4290
|
|
},
|
|
{
|
|
"entropy": 5.827371215820312,
|
|
"epoch": 0.33417623030538807,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000499259535063126,
|
|
"loss": 5.6652,
|
|
"mean_token_accuracy": 0.16036169081926346,
|
|
"num_tokens": 7463057.0,
|
|
"step": 4295
|
|
},
|
|
{
|
|
"entropy": 5.80002613067627,
|
|
"epoch": 0.3345652596771056,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000499257286675251,
|
|
"loss": 5.6295,
|
|
"mean_token_accuracy": 0.1520880788564682,
|
|
"num_tokens": 7471675.0,
|
|
"step": 4300
|
|
},
|
|
{
|
|
"entropy": 5.708404207229615,
|
|
"epoch": 0.3349542890488232,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004992550348846285,
|
|
"loss": 5.5731,
|
|
"mean_token_accuracy": 0.15868975967168808,
|
|
"num_tokens": 7479870.0,
|
|
"step": 4305
|
|
},
|
|
{
|
|
"entropy": 5.807326030731201,
|
|
"epoch": 0.33534331842054077,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004992527796912928,
|
|
"loss": 5.6442,
|
|
"mean_token_accuracy": 0.1565382771193981,
|
|
"num_tokens": 7489830.0,
|
|
"step": 4310
|
|
},
|
|
{
|
|
"entropy": 5.791453504562378,
|
|
"epoch": 0.3357323477922583,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004992505210952782,
|
|
"loss": 5.5757,
|
|
"mean_token_accuracy": 0.1656323567032814,
|
|
"num_tokens": 7497852.0,
|
|
"step": 4315
|
|
},
|
|
{
|
|
"entropy": 5.785038661956787,
|
|
"epoch": 0.3361213771639759,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004992482590966188,
|
|
"loss": 5.7069,
|
|
"mean_token_accuracy": 0.1559569127857685,
|
|
"num_tokens": 7506419.0,
|
|
"step": 4320
|
|
},
|
|
{
|
|
"entropy": 5.837784051895142,
|
|
"epoch": 0.3365104065356934,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004992459936953489,
|
|
"loss": 5.5972,
|
|
"mean_token_accuracy": 0.16566000878810883,
|
|
"num_tokens": 7514757.0,
|
|
"step": 4325
|
|
},
|
|
{
|
|
"entropy": 5.790379810333252,
|
|
"epoch": 0.336899435907411,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004992437248915032,
|
|
"loss": 5.664,
|
|
"mean_token_accuracy": 0.15615198463201524,
|
|
"num_tokens": 7523912.0,
|
|
"step": 4330
|
|
},
|
|
{
|
|
"entropy": 5.751581430435181,
|
|
"epoch": 0.3372884652791286,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004992414526851157,
|
|
"loss": 5.5474,
|
|
"mean_token_accuracy": 0.16585139334201812,
|
|
"num_tokens": 7532401.0,
|
|
"step": 4335
|
|
},
|
|
{
|
|
"entropy": 5.669851446151734,
|
|
"epoch": 0.3376774946508461,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004992391770762212,
|
|
"loss": 5.5144,
|
|
"mean_token_accuracy": 0.16344813257455826,
|
|
"num_tokens": 7541257.0,
|
|
"step": 4340
|
|
},
|
|
{
|
|
"entropy": 5.706036615371704,
|
|
"epoch": 0.3380665240225637,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000499236898064854,
|
|
"loss": 5.4562,
|
|
"mean_token_accuracy": 0.15973441749811174,
|
|
"num_tokens": 7549812.0,
|
|
"step": 4345
|
|
},
|
|
{
|
|
"entropy": 5.743966579437256,
|
|
"epoch": 0.3384555533942813,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004992346156510488,
|
|
"loss": 5.5513,
|
|
"mean_token_accuracy": 0.15965283364057542,
|
|
"num_tokens": 7559319.0,
|
|
"step": 4350
|
|
},
|
|
{
|
|
"entropy": 5.813631963729859,
|
|
"epoch": 0.3388445827659988,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004992323298348403,
|
|
"loss": 5.6947,
|
|
"mean_token_accuracy": 0.1522468313574791,
|
|
"num_tokens": 7567900.0,
|
|
"step": 4355
|
|
},
|
|
{
|
|
"entropy": 5.833976316452026,
|
|
"epoch": 0.3392336121377164,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000499230040616263,
|
|
"loss": 5.6194,
|
|
"mean_token_accuracy": 0.1545071080327034,
|
|
"num_tokens": 7576163.0,
|
|
"step": 4360
|
|
},
|
|
{
|
|
"entropy": 5.769789743423462,
|
|
"epoch": 0.33962264150943394,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004992277479953518,
|
|
"loss": 5.5671,
|
|
"mean_token_accuracy": 0.15694677829742432,
|
|
"num_tokens": 7584221.0,
|
|
"step": 4365
|
|
},
|
|
{
|
|
"entropy": 5.700899267196656,
|
|
"epoch": 0.34001167088115153,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004992254519721414,
|
|
"loss": 5.5473,
|
|
"mean_token_accuracy": 0.15996042490005494,
|
|
"num_tokens": 7593569.0,
|
|
"step": 4370
|
|
},
|
|
{
|
|
"entropy": 5.7665114402771,
|
|
"epoch": 0.3404007002528691,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004992231525466666,
|
|
"loss": 5.6089,
|
|
"mean_token_accuracy": 0.16032602339982988,
|
|
"num_tokens": 7602666.0,
|
|
"step": 4375
|
|
},
|
|
{
|
|
"entropy": 5.74814510345459,
|
|
"epoch": 0.34078972962458665,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004992208497189624,
|
|
"loss": 5.6791,
|
|
"mean_token_accuracy": 0.15110585689544678,
|
|
"num_tokens": 7611874.0,
|
|
"step": 4380
|
|
},
|
|
{
|
|
"entropy": 5.841089820861816,
|
|
"epoch": 0.34117875899630423,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004992185434890637,
|
|
"loss": 5.6336,
|
|
"mean_token_accuracy": 0.15836991518735885,
|
|
"num_tokens": 7620385.0,
|
|
"step": 4385
|
|
},
|
|
{
|
|
"entropy": 5.894673633575439,
|
|
"epoch": 0.34156778836802176,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004992162338570055,
|
|
"loss": 5.6854,
|
|
"mean_token_accuracy": 0.148434978723526,
|
|
"num_tokens": 7628786.0,
|
|
"step": 4390
|
|
},
|
|
{
|
|
"entropy": 5.769052648544312,
|
|
"epoch": 0.34195681773973935,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004992139208228227,
|
|
"loss": 5.5032,
|
|
"mean_token_accuracy": 0.16336381584405898,
|
|
"num_tokens": 7637389.0,
|
|
"step": 4395
|
|
},
|
|
{
|
|
"entropy": 5.750074100494385,
|
|
"epoch": 0.34234584711145694,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004992116043865506,
|
|
"loss": 5.6689,
|
|
"mean_token_accuracy": 0.15916045010089874,
|
|
"num_tokens": 7645793.0,
|
|
"step": 4400
|
|
},
|
|
{
|
|
"entropy": 5.878291654586792,
|
|
"epoch": 0.34273487648317447,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004992092845482244,
|
|
"loss": 5.6357,
|
|
"mean_token_accuracy": 0.16118928492069245,
|
|
"num_tokens": 7653951.0,
|
|
"step": 4405
|
|
},
|
|
{
|
|
"entropy": 5.724064445495605,
|
|
"epoch": 0.34312390585489205,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004992069613078791,
|
|
"loss": 5.4944,
|
|
"mean_token_accuracy": 0.16808485239744186,
|
|
"num_tokens": 7662753.0,
|
|
"step": 4410
|
|
},
|
|
{
|
|
"entropy": 5.686445617675782,
|
|
"epoch": 0.3435129352266096,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004992046346655499,
|
|
"loss": 5.4727,
|
|
"mean_token_accuracy": 0.16301707774400712,
|
|
"num_tokens": 7671832.0,
|
|
"step": 4415
|
|
},
|
|
{
|
|
"entropy": 5.801256561279297,
|
|
"epoch": 0.34390196459832717,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004992023046212723,
|
|
"loss": 5.6282,
|
|
"mean_token_accuracy": 0.1588641732931137,
|
|
"num_tokens": 7680969.0,
|
|
"step": 4420
|
|
},
|
|
{
|
|
"entropy": 5.8781603336334225,
|
|
"epoch": 0.34429099397004476,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004991999711750816,
|
|
"loss": 5.6316,
|
|
"mean_token_accuracy": 0.15277016907930374,
|
|
"num_tokens": 7689277.0,
|
|
"step": 4425
|
|
},
|
|
{
|
|
"entropy": 5.728748893737793,
|
|
"epoch": 0.3446800233417623,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004991976343270133,
|
|
"loss": 5.5592,
|
|
"mean_token_accuracy": 0.1625969737768173,
|
|
"num_tokens": 7697373.0,
|
|
"step": 4430
|
|
},
|
|
{
|
|
"entropy": 5.857252168655395,
|
|
"epoch": 0.3450690527134799,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004991952940771026,
|
|
"loss": 5.6249,
|
|
"mean_token_accuracy": 0.15589040964841844,
|
|
"num_tokens": 7705767.0,
|
|
"step": 4435
|
|
},
|
|
{
|
|
"entropy": 5.715005779266358,
|
|
"epoch": 0.34545808208519746,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004991929504253852,
|
|
"loss": 5.5207,
|
|
"mean_token_accuracy": 0.1657451167702675,
|
|
"num_tokens": 7713746.0,
|
|
"step": 4440
|
|
},
|
|
{
|
|
"entropy": 5.747983598709107,
|
|
"epoch": 0.345847111456915,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004991906033718966,
|
|
"loss": 5.66,
|
|
"mean_token_accuracy": 0.15185474902391433,
|
|
"num_tokens": 7721829.0,
|
|
"step": 4445
|
|
},
|
|
{
|
|
"entropy": 5.7072593688964846,
|
|
"epoch": 0.3462361408286326,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004991882529166724,
|
|
"loss": 5.5254,
|
|
"mean_token_accuracy": 0.1630813479423523,
|
|
"num_tokens": 7730479.0,
|
|
"step": 4450
|
|
},
|
|
{
|
|
"entropy": 5.768003606796265,
|
|
"epoch": 0.3466251702003501,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004991858990597483,
|
|
"loss": 5.4953,
|
|
"mean_token_accuracy": 0.16315876841545104,
|
|
"num_tokens": 7738659.0,
|
|
"step": 4455
|
|
},
|
|
{
|
|
"entropy": 5.835393476486206,
|
|
"epoch": 0.3470141995720677,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004991835418011601,
|
|
"loss": 5.7726,
|
|
"mean_token_accuracy": 0.15530015379190446,
|
|
"num_tokens": 7747597.0,
|
|
"step": 4460
|
|
},
|
|
{
|
|
"entropy": 5.778534841537476,
|
|
"epoch": 0.3474032289437853,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004991811811409434,
|
|
"loss": 5.6145,
|
|
"mean_token_accuracy": 0.1572774849832058,
|
|
"num_tokens": 7756666.0,
|
|
"step": 4465
|
|
},
|
|
{
|
|
"entropy": 5.8093178272247314,
|
|
"epoch": 0.3477922583155028,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004991788170791341,
|
|
"loss": 5.6412,
|
|
"mean_token_accuracy": 0.15569517463445665,
|
|
"num_tokens": 7765621.0,
|
|
"step": 4470
|
|
},
|
|
{
|
|
"entropy": 5.762197351455688,
|
|
"epoch": 0.3481812876872204,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004991764496157682,
|
|
"loss": 5.5449,
|
|
"mean_token_accuracy": 0.15648710131645202,
|
|
"num_tokens": 7774137.0,
|
|
"step": 4475
|
|
},
|
|
{
|
|
"entropy": 5.828894186019897,
|
|
"epoch": 0.34857031705893793,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004991740787508814,
|
|
"loss": 5.6492,
|
|
"mean_token_accuracy": 0.15211960375308992,
|
|
"num_tokens": 7783144.0,
|
|
"step": 4480
|
|
},
|
|
{
|
|
"entropy": 5.78465690612793,
|
|
"epoch": 0.3489593464306555,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004991717044845097,
|
|
"loss": 5.6866,
|
|
"mean_token_accuracy": 0.14937788471579552,
|
|
"num_tokens": 7791530.0,
|
|
"step": 4485
|
|
},
|
|
{
|
|
"entropy": 5.761826896667481,
|
|
"epoch": 0.3493483758023731,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004991693268166892,
|
|
"loss": 5.5461,
|
|
"mean_token_accuracy": 0.1595842033624649,
|
|
"num_tokens": 7800869.0,
|
|
"step": 4490
|
|
},
|
|
{
|
|
"entropy": 5.781609058380127,
|
|
"epoch": 0.34973740517409063,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004991669457474559,
|
|
"loss": 5.6224,
|
|
"mean_token_accuracy": 0.15640588253736495,
|
|
"num_tokens": 7810201.0,
|
|
"step": 4495
|
|
},
|
|
{
|
|
"entropy": 5.749261569976807,
|
|
"epoch": 0.3501264345458082,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004991645612768461,
|
|
"loss": 5.5152,
|
|
"mean_token_accuracy": 0.1649569660425186,
|
|
"num_tokens": 7818529.0,
|
|
"step": 4500
|
|
},
|
|
{
|
|
"entropy": 5.7531813621521,
|
|
"epoch": 0.35051546391752575,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004991621734048958,
|
|
"loss": 5.5601,
|
|
"mean_token_accuracy": 0.16200138330459596,
|
|
"num_tokens": 7827254.0,
|
|
"step": 4505
|
|
},
|
|
{
|
|
"entropy": 5.77031102180481,
|
|
"epoch": 0.35090449328924334,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004991597821316415,
|
|
"loss": 5.5726,
|
|
"mean_token_accuracy": 0.16260626912117004,
|
|
"num_tokens": 7836437.0,
|
|
"step": 4510
|
|
},
|
|
{
|
|
"entropy": 5.717511510848999,
|
|
"epoch": 0.3512935226609609,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004991573874571192,
|
|
"loss": 5.5881,
|
|
"mean_token_accuracy": 0.16121748238801956,
|
|
"num_tokens": 7844939.0,
|
|
"step": 4515
|
|
},
|
|
{
|
|
"entropy": 5.755042934417725,
|
|
"epoch": 0.35168255203267845,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004991549893813653,
|
|
"loss": 5.5594,
|
|
"mean_token_accuracy": 0.1579587161540985,
|
|
"num_tokens": 7852889.0,
|
|
"step": 4520
|
|
},
|
|
{
|
|
"entropy": 5.809964561462403,
|
|
"epoch": 0.35207158140439604,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004991525879044162,
|
|
"loss": 5.7009,
|
|
"mean_token_accuracy": 0.1521313928067684,
|
|
"num_tokens": 7861867.0,
|
|
"step": 4525
|
|
},
|
|
{
|
|
"entropy": 5.759050130844116,
|
|
"epoch": 0.35246061077611357,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004991501830263084,
|
|
"loss": 5.4925,
|
|
"mean_token_accuracy": 0.16492490023374556,
|
|
"num_tokens": 7869343.0,
|
|
"step": 4530
|
|
},
|
|
{
|
|
"entropy": 5.743049049377442,
|
|
"epoch": 0.35284964014783116,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004991477747470783,
|
|
"loss": 5.5496,
|
|
"mean_token_accuracy": 0.16336526572704316,
|
|
"num_tokens": 7877142.0,
|
|
"step": 4535
|
|
},
|
|
{
|
|
"entropy": 5.715654516220093,
|
|
"epoch": 0.35323866951954874,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004991453630667625,
|
|
"loss": 5.5718,
|
|
"mean_token_accuracy": 0.1644924059510231,
|
|
"num_tokens": 7885183.0,
|
|
"step": 4540
|
|
},
|
|
{
|
|
"entropy": 5.660160732269287,
|
|
"epoch": 0.3536276988912663,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004991429479853976,
|
|
"loss": 5.4073,
|
|
"mean_token_accuracy": 0.17003071159124375,
|
|
"num_tokens": 7893848.0,
|
|
"step": 4545
|
|
},
|
|
{
|
|
"entropy": 5.752790403366089,
|
|
"epoch": 0.35401672826298386,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004991405295030202,
|
|
"loss": 5.5774,
|
|
"mean_token_accuracy": 0.15930684059858322,
|
|
"num_tokens": 7902438.0,
|
|
"step": 4550
|
|
},
|
|
{
|
|
"entropy": 5.7751688957214355,
|
|
"epoch": 0.35440575763470145,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004991381076196671,
|
|
"loss": 5.543,
|
|
"mean_token_accuracy": 0.15595637112855912,
|
|
"num_tokens": 7910951.0,
|
|
"step": 4555
|
|
},
|
|
{
|
|
"entropy": 5.748727226257325,
|
|
"epoch": 0.354794787006419,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004991356823353748,
|
|
"loss": 5.6526,
|
|
"mean_token_accuracy": 0.1568855568766594,
|
|
"num_tokens": 7920375.0,
|
|
"step": 4560
|
|
},
|
|
{
|
|
"entropy": 5.702395009994507,
|
|
"epoch": 0.35518381637813656,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004991332536501804,
|
|
"loss": 5.5248,
|
|
"mean_token_accuracy": 0.1637159138917923,
|
|
"num_tokens": 7928656.0,
|
|
"step": 4565
|
|
},
|
|
{
|
|
"entropy": 5.88414044380188,
|
|
"epoch": 0.3555728457498541,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004991308215641205,
|
|
"loss": 5.7693,
|
|
"mean_token_accuracy": 0.15237502455711366,
|
|
"num_tokens": 7936929.0,
|
|
"step": 4570
|
|
},
|
|
{
|
|
"entropy": 5.835222911834717,
|
|
"epoch": 0.3559618751215717,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004991283860772323,
|
|
"loss": 5.5781,
|
|
"mean_token_accuracy": 0.16577111184597015,
|
|
"num_tokens": 7945592.0,
|
|
"step": 4575
|
|
},
|
|
{
|
|
"entropy": 5.725835466384888,
|
|
"epoch": 0.35635090449328927,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004991259471895525,
|
|
"loss": 5.5138,
|
|
"mean_token_accuracy": 0.16628557145595552,
|
|
"num_tokens": 7953656.0,
|
|
"step": 4580
|
|
},
|
|
{
|
|
"entropy": 5.777119445800781,
|
|
"epoch": 0.3567399338650068,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004991235049011182,
|
|
"loss": 5.5921,
|
|
"mean_token_accuracy": 0.16313516050577165,
|
|
"num_tokens": 7962038.0,
|
|
"step": 4585
|
|
},
|
|
{
|
|
"entropy": 5.779297161102295,
|
|
"epoch": 0.3571289632367244,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004991210592119663,
|
|
"loss": 5.673,
|
|
"mean_token_accuracy": 0.1561742752790451,
|
|
"num_tokens": 7970338.0,
|
|
"step": 4590
|
|
},
|
|
{
|
|
"entropy": 5.824539995193481,
|
|
"epoch": 0.3575179926084419,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004991186101221342,
|
|
"loss": 5.5993,
|
|
"mean_token_accuracy": 0.16285818666219712,
|
|
"num_tokens": 7979173.0,
|
|
"step": 4595
|
|
},
|
|
{
|
|
"entropy": 5.753220415115356,
|
|
"epoch": 0.3579070219801595,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000499116157631659,
|
|
"loss": 5.4754,
|
|
"mean_token_accuracy": 0.16968862116336822,
|
|
"num_tokens": 7987245.0,
|
|
"step": 4600
|
|
},
|
|
{
|
|
"entropy": 5.782096433639526,
|
|
"epoch": 0.3582960513518771,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004991137017405777,
|
|
"loss": 5.6827,
|
|
"mean_token_accuracy": 0.15123804807662963,
|
|
"num_tokens": 7995551.0,
|
|
"step": 4605
|
|
},
|
|
{
|
|
"entropy": 5.699934291839599,
|
|
"epoch": 0.3586850807235946,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004991112424489277,
|
|
"loss": 5.4975,
|
|
"mean_token_accuracy": 0.16038129031658171,
|
|
"num_tokens": 8004069.0,
|
|
"step": 4610
|
|
},
|
|
{
|
|
"entropy": 5.725274276733399,
|
|
"epoch": 0.3590741100953122,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004991087797567462,
|
|
"loss": 5.5675,
|
|
"mean_token_accuracy": 0.16466078162193298,
|
|
"num_tokens": 8012537.0,
|
|
"step": 4615
|
|
},
|
|
{
|
|
"entropy": 5.838127136230469,
|
|
"epoch": 0.35946313946702974,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004991063136640709,
|
|
"loss": 5.5434,
|
|
"mean_token_accuracy": 0.15995005071163176,
|
|
"num_tokens": 8021387.0,
|
|
"step": 4620
|
|
},
|
|
{
|
|
"entropy": 5.732734203338623,
|
|
"epoch": 0.3598521688387473,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004991038441709388,
|
|
"loss": 5.499,
|
|
"mean_token_accuracy": 0.1588419958949089,
|
|
"num_tokens": 8030261.0,
|
|
"step": 4625
|
|
},
|
|
{
|
|
"entropy": 5.771962738037109,
|
|
"epoch": 0.3602411982104649,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004991013712773877,
|
|
"loss": 5.581,
|
|
"mean_token_accuracy": 0.15491561591625214,
|
|
"num_tokens": 8038161.0,
|
|
"step": 4630
|
|
},
|
|
{
|
|
"entropy": 5.7120036602020265,
|
|
"epoch": 0.36063022758218244,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004990988949834549,
|
|
"loss": 5.6502,
|
|
"mean_token_accuracy": 0.16104790568351746,
|
|
"num_tokens": 8046340.0,
|
|
"step": 4635
|
|
},
|
|
{
|
|
"entropy": 5.80100302696228,
|
|
"epoch": 0.3610192569539,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000499096415289178,
|
|
"loss": 5.5868,
|
|
"mean_token_accuracy": 0.1563143476843834,
|
|
"num_tokens": 8054997.0,
|
|
"step": 4640
|
|
},
|
|
{
|
|
"entropy": 5.75185375213623,
|
|
"epoch": 0.3614082863256176,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004990939321945948,
|
|
"loss": 5.5207,
|
|
"mean_token_accuracy": 0.16830721646547317,
|
|
"num_tokens": 8063686.0,
|
|
"step": 4645
|
|
},
|
|
{
|
|
"entropy": 5.738094854354858,
|
|
"epoch": 0.36179731569733514,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004990914456997427,
|
|
"loss": 5.6455,
|
|
"mean_token_accuracy": 0.15778837502002716,
|
|
"num_tokens": 8072999.0,
|
|
"step": 4650
|
|
},
|
|
{
|
|
"entropy": 5.734006452560425,
|
|
"epoch": 0.36218634506905273,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004990889558046598,
|
|
"loss": 5.4954,
|
|
"mean_token_accuracy": 0.1635401204228401,
|
|
"num_tokens": 8081596.0,
|
|
"step": 4655
|
|
},
|
|
{
|
|
"entropy": 5.792643308639526,
|
|
"epoch": 0.36257537444077026,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004990864625093836,
|
|
"loss": 5.7211,
|
|
"mean_token_accuracy": 0.1504440724849701,
|
|
"num_tokens": 8090948.0,
|
|
"step": 4660
|
|
},
|
|
{
|
|
"entropy": 5.738381576538086,
|
|
"epoch": 0.36296440381248785,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004990839658139519,
|
|
"loss": 5.7118,
|
|
"mean_token_accuracy": 0.15039844661951066,
|
|
"num_tokens": 8099445.0,
|
|
"step": 4665
|
|
},
|
|
{
|
|
"entropy": 5.817491865158081,
|
|
"epoch": 0.36335343318420543,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004990814657184028,
|
|
"loss": 5.5696,
|
|
"mean_token_accuracy": 0.15574323982000352,
|
|
"num_tokens": 8108119.0,
|
|
"step": 4670
|
|
},
|
|
{
|
|
"entropy": 5.782070636749268,
|
|
"epoch": 0.36374246255592296,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004990789622227741,
|
|
"loss": 5.5735,
|
|
"mean_token_accuracy": 0.15753818452358245,
|
|
"num_tokens": 8117060.0,
|
|
"step": 4675
|
|
},
|
|
{
|
|
"entropy": 5.714137172698974,
|
|
"epoch": 0.36413149192764055,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004990764553271038,
|
|
"loss": 5.5652,
|
|
"mean_token_accuracy": 0.15798794180154802,
|
|
"num_tokens": 8126229.0,
|
|
"step": 4680
|
|
},
|
|
{
|
|
"entropy": 5.788286256790161,
|
|
"epoch": 0.3645205212993581,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004990739450314299,
|
|
"loss": 5.5223,
|
|
"mean_token_accuracy": 0.16824372112751007,
|
|
"num_tokens": 8134694.0,
|
|
"step": 4685
|
|
},
|
|
{
|
|
"entropy": 5.772018814086914,
|
|
"epoch": 0.36490955067107567,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004990714313357906,
|
|
"loss": 5.5969,
|
|
"mean_token_accuracy": 0.1634421780705452,
|
|
"num_tokens": 8143329.0,
|
|
"step": 4690
|
|
},
|
|
{
|
|
"entropy": 5.750579977035523,
|
|
"epoch": 0.36529858004279325,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000499068914240224,
|
|
"loss": 5.5701,
|
|
"mean_token_accuracy": 0.16435180157423018,
|
|
"num_tokens": 8151432.0,
|
|
"step": 4695
|
|
},
|
|
{
|
|
"entropy": 5.76611328125,
|
|
"epoch": 0.3656876094145108,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004990663937447682,
|
|
"loss": 5.5442,
|
|
"mean_token_accuracy": 0.16045622676610946,
|
|
"num_tokens": 8159677.0,
|
|
"step": 4700
|
|
},
|
|
{
|
|
"entropy": 5.727065992355347,
|
|
"epoch": 0.36607663878622837,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004990638698494615,
|
|
"loss": 5.6065,
|
|
"mean_token_accuracy": 0.15686380863189697,
|
|
"num_tokens": 8168710.0,
|
|
"step": 4705
|
|
},
|
|
{
|
|
"entropy": 5.742712450027466,
|
|
"epoch": 0.3664656681579459,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004990613425543423,
|
|
"loss": 5.5955,
|
|
"mean_token_accuracy": 0.1621291607618332,
|
|
"num_tokens": 8177501.0,
|
|
"step": 4710
|
|
},
|
|
{
|
|
"entropy": 5.843996238708496,
|
|
"epoch": 0.3668546975296635,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004990588118594487,
|
|
"loss": 5.6682,
|
|
"mean_token_accuracy": 0.15319716781377793,
|
|
"num_tokens": 8185791.0,
|
|
"step": 4715
|
|
},
|
|
{
|
|
"entropy": 5.831458473205567,
|
|
"epoch": 0.3672437269013811,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004990562777648194,
|
|
"loss": 5.6938,
|
|
"mean_token_accuracy": 0.15462879985570907,
|
|
"num_tokens": 8195020.0,
|
|
"step": 4720
|
|
},
|
|
{
|
|
"entropy": 5.756261014938355,
|
|
"epoch": 0.3676327562730986,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004990537402704928,
|
|
"loss": 5.5623,
|
|
"mean_token_accuracy": 0.15908532589673996,
|
|
"num_tokens": 8203540.0,
|
|
"step": 4725
|
|
},
|
|
{
|
|
"entropy": 5.799097156524658,
|
|
"epoch": 0.3680217856448162,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004990511993765071,
|
|
"loss": 5.5506,
|
|
"mean_token_accuracy": 0.15895125716924668,
|
|
"num_tokens": 8211985.0,
|
|
"step": 4730
|
|
},
|
|
{
|
|
"entropy": 5.733615446090698,
|
|
"epoch": 0.3684108150165337,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004990486550829011,
|
|
"loss": 5.6262,
|
|
"mean_token_accuracy": 0.1645650178194046,
|
|
"num_tokens": 8220289.0,
|
|
"step": 4735
|
|
},
|
|
{
|
|
"entropy": 5.8451371669769285,
|
|
"epoch": 0.3687998443882513,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004990461073897134,
|
|
"loss": 5.6569,
|
|
"mean_token_accuracy": 0.14948247075080873,
|
|
"num_tokens": 8229652.0,
|
|
"step": 4740
|
|
},
|
|
{
|
|
"entropy": 5.806291913986206,
|
|
"epoch": 0.3691888737599689,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004990435562969827,
|
|
"loss": 5.6478,
|
|
"mean_token_accuracy": 0.15665459036827087,
|
|
"num_tokens": 8237728.0,
|
|
"step": 4745
|
|
},
|
|
{
|
|
"entropy": 5.7270866394042965,
|
|
"epoch": 0.3695779031316864,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004990410018047475,
|
|
"loss": 5.5425,
|
|
"mean_token_accuracy": 0.16309150755405427,
|
|
"num_tokens": 8246393.0,
|
|
"step": 4750
|
|
},
|
|
{
|
|
"entropy": 5.695544958114624,
|
|
"epoch": 0.369966932503404,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004990384439130467,
|
|
"loss": 5.4984,
|
|
"mean_token_accuracy": 0.16200296729803085,
|
|
"num_tokens": 8256736.0,
|
|
"step": 4755
|
|
},
|
|
{
|
|
"entropy": 5.77980260848999,
|
|
"epoch": 0.3703559618751216,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004990358826219192,
|
|
"loss": 5.5975,
|
|
"mean_token_accuracy": 0.16518477648496627,
|
|
"num_tokens": 8265126.0,
|
|
"step": 4760
|
|
},
|
|
{
|
|
"entropy": 5.778947877883911,
|
|
"epoch": 0.37074499124683913,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004990333179314038,
|
|
"loss": 5.4984,
|
|
"mean_token_accuracy": 0.16346690207719802,
|
|
"num_tokens": 8273136.0,
|
|
"step": 4765
|
|
},
|
|
{
|
|
"entropy": 5.620182704925537,
|
|
"epoch": 0.3711340206185567,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004990307498415393,
|
|
"loss": 5.4276,
|
|
"mean_token_accuracy": 0.16780980080366134,
|
|
"num_tokens": 8281697.0,
|
|
"step": 4770
|
|
},
|
|
{
|
|
"entropy": 5.665127325057983,
|
|
"epoch": 0.37152304999027425,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004990281783523648,
|
|
"loss": 5.5628,
|
|
"mean_token_accuracy": 0.16574217826128007,
|
|
"num_tokens": 8290765.0,
|
|
"step": 4775
|
|
},
|
|
{
|
|
"entropy": 5.823178434371949,
|
|
"epoch": 0.37191207936199183,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004990256034639192,
|
|
"loss": 5.6786,
|
|
"mean_token_accuracy": 0.15433327853679657,
|
|
"num_tokens": 8299875.0,
|
|
"step": 4780
|
|
},
|
|
{
|
|
"entropy": 5.750207090377808,
|
|
"epoch": 0.3723011087337094,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004990230251762418,
|
|
"loss": 5.5241,
|
|
"mean_token_accuracy": 0.16539545208215714,
|
|
"num_tokens": 8308515.0,
|
|
"step": 4785
|
|
},
|
|
{
|
|
"entropy": 5.682763338088989,
|
|
"epoch": 0.37269013810542695,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004990204434893713,
|
|
"loss": 5.4468,
|
|
"mean_token_accuracy": 0.16895510554313659,
|
|
"num_tokens": 8317260.0,
|
|
"step": 4790
|
|
},
|
|
{
|
|
"entropy": 5.7800510883331295,
|
|
"epoch": 0.37307916747714454,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004990178584033474,
|
|
"loss": 5.6156,
|
|
"mean_token_accuracy": 0.1566510796546936,
|
|
"num_tokens": 8325887.0,
|
|
"step": 4795
|
|
},
|
|
{
|
|
"entropy": 5.842481851577759,
|
|
"epoch": 0.37346819684886207,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004990152699182089,
|
|
"loss": 5.6152,
|
|
"mean_token_accuracy": 0.15425875931978225,
|
|
"num_tokens": 8333974.0,
|
|
"step": 4800
|
|
},
|
|
{
|
|
"entropy": 5.722154998779297,
|
|
"epoch": 0.37385722622057965,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004990126780339953,
|
|
"loss": 5.5918,
|
|
"mean_token_accuracy": 0.15548155158758165,
|
|
"num_tokens": 8343199.0,
|
|
"step": 4805
|
|
},
|
|
{
|
|
"entropy": 5.685928583145142,
|
|
"epoch": 0.37424625559229724,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004990100827507459,
|
|
"loss": 5.3899,
|
|
"mean_token_accuracy": 0.16845352202653885,
|
|
"num_tokens": 8351202.0,
|
|
"step": 4810
|
|
},
|
|
{
|
|
"entropy": 5.811168527603149,
|
|
"epoch": 0.37463528496401477,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004990074840684999,
|
|
"loss": 5.7413,
|
|
"mean_token_accuracy": 0.14929891377687454,
|
|
"num_tokens": 8360011.0,
|
|
"step": 4815
|
|
},
|
|
{
|
|
"entropy": 5.75562105178833,
|
|
"epoch": 0.37502431433573236,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004990048819872969,
|
|
"loss": 5.6051,
|
|
"mean_token_accuracy": 0.16131770461797715,
|
|
"num_tokens": 8367874.0,
|
|
"step": 4820
|
|
},
|
|
{
|
|
"entropy": 5.723214483261108,
|
|
"epoch": 0.3754133437074499,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004990022765071765,
|
|
"loss": 5.57,
|
|
"mean_token_accuracy": 0.15871281325817108,
|
|
"num_tokens": 8376708.0,
|
|
"step": 4825
|
|
},
|
|
{
|
|
"entropy": 5.7772377014160154,
|
|
"epoch": 0.3758023730791675,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000498999667628178,
|
|
"loss": 5.5918,
|
|
"mean_token_accuracy": 0.16533441841602325,
|
|
"num_tokens": 8385467.0,
|
|
"step": 4830
|
|
},
|
|
{
|
|
"entropy": 5.749735116958618,
|
|
"epoch": 0.37619140245088506,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004989970553503411,
|
|
"loss": 5.5598,
|
|
"mean_token_accuracy": 0.15902363508939743,
|
|
"num_tokens": 8393574.0,
|
|
"step": 4835
|
|
},
|
|
{
|
|
"entropy": 5.69984188079834,
|
|
"epoch": 0.3765804318226026,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004989944396737054,
|
|
"loss": 5.6006,
|
|
"mean_token_accuracy": 0.16227839142084122,
|
|
"num_tokens": 8402857.0,
|
|
"step": 4840
|
|
},
|
|
{
|
|
"entropy": 5.737270069122315,
|
|
"epoch": 0.3769694611943202,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004989918205983106,
|
|
"loss": 5.599,
|
|
"mean_token_accuracy": 0.16925140619277954,
|
|
"num_tokens": 8411728.0,
|
|
"step": 4845
|
|
},
|
|
{
|
|
"entropy": 5.779333019256592,
|
|
"epoch": 0.37735849056603776,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004989891981241964,
|
|
"loss": 5.5787,
|
|
"mean_token_accuracy": 0.1665400505065918,
|
|
"num_tokens": 8420307.0,
|
|
"step": 4850
|
|
},
|
|
{
|
|
"entropy": 5.787651681900025,
|
|
"epoch": 0.3777475199377553,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004989865722514027,
|
|
"loss": 5.5925,
|
|
"mean_token_accuracy": 0.15569850653409958,
|
|
"num_tokens": 8429442.0,
|
|
"step": 4855
|
|
},
|
|
{
|
|
"entropy": 5.721146774291992,
|
|
"epoch": 0.3781365493094729,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004989839429799692,
|
|
"loss": 5.4756,
|
|
"mean_token_accuracy": 0.17139440774917603,
|
|
"num_tokens": 8437945.0,
|
|
"step": 4860
|
|
},
|
|
{
|
|
"entropy": 5.701009464263916,
|
|
"epoch": 0.3785255786811904,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000498981310309936,
|
|
"loss": 5.468,
|
|
"mean_token_accuracy": 0.1617519348859787,
|
|
"num_tokens": 8445743.0,
|
|
"step": 4865
|
|
},
|
|
{
|
|
"entropy": 5.6702821254730225,
|
|
"epoch": 0.378914608052908,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004989786742413428,
|
|
"loss": 5.5636,
|
|
"mean_token_accuracy": 0.15807968527078628,
|
|
"num_tokens": 8454091.0,
|
|
"step": 4870
|
|
},
|
|
{
|
|
"entropy": 5.8274698734283445,
|
|
"epoch": 0.3793036374246256,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004989760347742298,
|
|
"loss": 5.5638,
|
|
"mean_token_accuracy": 0.1589045539498329,
|
|
"num_tokens": 8461992.0,
|
|
"step": 4875
|
|
},
|
|
{
|
|
"entropy": 5.684429550170899,
|
|
"epoch": 0.3796926667963431,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004989733919086369,
|
|
"loss": 5.5048,
|
|
"mean_token_accuracy": 0.16163448840379716,
|
|
"num_tokens": 8470730.0,
|
|
"step": 4880
|
|
},
|
|
{
|
|
"entropy": 5.702088356018066,
|
|
"epoch": 0.3800816961680607,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004989707456446043,
|
|
"loss": 5.5565,
|
|
"mean_token_accuracy": 0.16036150306463243,
|
|
"num_tokens": 8479947.0,
|
|
"step": 4885
|
|
},
|
|
{
|
|
"entropy": 5.825870656967163,
|
|
"epoch": 0.38047072553977823,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004989680959821721,
|
|
"loss": 5.6376,
|
|
"mean_token_accuracy": 0.15936389118432998,
|
|
"num_tokens": 8488237.0,
|
|
"step": 4890
|
|
},
|
|
{
|
|
"entropy": 5.738702583312988,
|
|
"epoch": 0.3808597549114958,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004989654429213805,
|
|
"loss": 5.5045,
|
|
"mean_token_accuracy": 0.1659325733780861,
|
|
"num_tokens": 8497146.0,
|
|
"step": 4895
|
|
},
|
|
{
|
|
"entropy": 5.747964525222779,
|
|
"epoch": 0.3812487842832134,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004989627864622699,
|
|
"loss": 5.5789,
|
|
"mean_token_accuracy": 0.16467523127794265,
|
|
"num_tokens": 8505736.0,
|
|
"step": 4900
|
|
},
|
|
{
|
|
"entropy": 5.765132761001587,
|
|
"epoch": 0.38163781365493094,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004989601266048804,
|
|
"loss": 5.5924,
|
|
"mean_token_accuracy": 0.1583853229880333,
|
|
"num_tokens": 8515368.0,
|
|
"step": 4905
|
|
},
|
|
{
|
|
"entropy": 5.72173228263855,
|
|
"epoch": 0.3820268430266485,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004989574633492525,
|
|
"loss": 5.5642,
|
|
"mean_token_accuracy": 0.1621312364935875,
|
|
"num_tokens": 8524141.0,
|
|
"step": 4910
|
|
},
|
|
{
|
|
"entropy": 5.718557834625244,
|
|
"epoch": 0.38241587239836605,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004989547966954266,
|
|
"loss": 5.4734,
|
|
"mean_token_accuracy": 0.16636828035116197,
|
|
"num_tokens": 8533116.0,
|
|
"step": 4915
|
|
},
|
|
{
|
|
"entropy": 5.712999486923218,
|
|
"epoch": 0.38280490177008364,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000498952126643443,
|
|
"loss": 5.6072,
|
|
"mean_token_accuracy": 0.16635651737451554,
|
|
"num_tokens": 8541919.0,
|
|
"step": 4920
|
|
},
|
|
{
|
|
"entropy": 5.7109620571136475,
|
|
"epoch": 0.3831939311418012,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004989494531933424,
|
|
"loss": 5.4876,
|
|
"mean_token_accuracy": 0.17107266783714295,
|
|
"num_tokens": 8550372.0,
|
|
"step": 4925
|
|
},
|
|
{
|
|
"entropy": 5.757292413711548,
|
|
"epoch": 0.38358296051351876,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004989467763451652,
|
|
"loss": 5.5827,
|
|
"mean_token_accuracy": 0.15917742997407913,
|
|
"num_tokens": 8559246.0,
|
|
"step": 4930
|
|
},
|
|
{
|
|
"entropy": 5.6922876834869385,
|
|
"epoch": 0.38397198988523634,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004989440960989523,
|
|
"loss": 5.3482,
|
|
"mean_token_accuracy": 0.16702754199504852,
|
|
"num_tokens": 8567005.0,
|
|
"step": 4935
|
|
},
|
|
{
|
|
"entropy": 5.64597373008728,
|
|
"epoch": 0.3843610192569539,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000498941412454744,
|
|
"loss": 5.5681,
|
|
"mean_token_accuracy": 0.1547877758741379,
|
|
"num_tokens": 8575399.0,
|
|
"step": 4940
|
|
},
|
|
{
|
|
"entropy": 5.817316627502441,
|
|
"epoch": 0.38475004862867146,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004989387254125813,
|
|
"loss": 5.6216,
|
|
"mean_token_accuracy": 0.15826431214809417,
|
|
"num_tokens": 8583994.0,
|
|
"step": 4945
|
|
},
|
|
{
|
|
"entropy": 5.731871128082275,
|
|
"epoch": 0.38513907800038905,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004989360349725049,
|
|
"loss": 5.5533,
|
|
"mean_token_accuracy": 0.16471867114305497,
|
|
"num_tokens": 8593446.0,
|
|
"step": 4950
|
|
},
|
|
{
|
|
"entropy": 5.743245267868042,
|
|
"epoch": 0.3855281073721066,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004989333411345555,
|
|
"loss": 5.5482,
|
|
"mean_token_accuracy": 0.16647694557905196,
|
|
"num_tokens": 8602821.0,
|
|
"step": 4955
|
|
},
|
|
{
|
|
"entropy": 5.751190042495727,
|
|
"epoch": 0.38591713674382416,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004989306438987742,
|
|
"loss": 5.6471,
|
|
"mean_token_accuracy": 0.15571539402008056,
|
|
"num_tokens": 8611831.0,
|
|
"step": 4960
|
|
},
|
|
{
|
|
"entropy": 5.795993375778198,
|
|
"epoch": 0.38630616611554175,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004989279432652018,
|
|
"loss": 5.5403,
|
|
"mean_token_accuracy": 0.16009591668844222,
|
|
"num_tokens": 8620986.0,
|
|
"step": 4965
|
|
},
|
|
{
|
|
"entropy": 5.733548927307129,
|
|
"epoch": 0.3866951954872593,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004989252392338791,
|
|
"loss": 5.4854,
|
|
"mean_token_accuracy": 0.1636480860412121,
|
|
"num_tokens": 8629822.0,
|
|
"step": 4970
|
|
},
|
|
{
|
|
"entropy": 5.724105978012085,
|
|
"epoch": 0.38708422485897687,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004989225318048475,
|
|
"loss": 5.6001,
|
|
"mean_token_accuracy": 0.15980519205331803,
|
|
"num_tokens": 8637679.0,
|
|
"step": 4975
|
|
},
|
|
{
|
|
"entropy": 5.76774034500122,
|
|
"epoch": 0.3874732542306944,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004989198209781478,
|
|
"loss": 5.6142,
|
|
"mean_token_accuracy": 0.1648936003446579,
|
|
"num_tokens": 8646705.0,
|
|
"step": 4980
|
|
},
|
|
{
|
|
"entropy": 5.794110631942749,
|
|
"epoch": 0.387862283602412,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004989171067538211,
|
|
"loss": 5.5435,
|
|
"mean_token_accuracy": 0.16352889388799668,
|
|
"num_tokens": 8655599.0,
|
|
"step": 4985
|
|
},
|
|
{
|
|
"entropy": 5.69699764251709,
|
|
"epoch": 0.38825131297412957,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.000498914389131909,
|
|
"loss": 5.5651,
|
|
"mean_token_accuracy": 0.15984487384557725,
|
|
"num_tokens": 8665025.0,
|
|
"step": 4990
|
|
},
|
|
{
|
|
"entropy": 5.715613317489624,
|
|
"epoch": 0.3886403423458471,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004989116681124523,
|
|
"loss": 5.4493,
|
|
"mean_token_accuracy": 0.1684253543615341,
|
|
"num_tokens": 8672994.0,
|
|
"step": 4995
|
|
},
|
|
{
|
|
"entropy": 5.686432600021362,
|
|
"epoch": 0.3890293717175647,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004989089436954924,
|
|
"loss": 5.5803,
|
|
"mean_token_accuracy": 0.15855107009410857,
|
|
"num_tokens": 8682457.0,
|
|
"step": 5000
|
|
},
|
|
{
|
|
"entropy": 5.764044570922851,
|
|
"epoch": 0.3894184010892822,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004989062158810706,
|
|
"loss": 5.5553,
|
|
"mean_token_accuracy": 0.16128483563661575,
|
|
"num_tokens": 8690888.0,
|
|
"step": 5005
|
|
},
|
|
{
|
|
"entropy": 5.811047554016113,
|
|
"epoch": 0.3898074304609998,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004989034846692284,
|
|
"loss": 5.656,
|
|
"mean_token_accuracy": 0.15784021466970444,
|
|
"num_tokens": 8699632.0,
|
|
"step": 5010
|
|
},
|
|
{
|
|
"entropy": 5.699138116836548,
|
|
"epoch": 0.3901964598327174,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004989007500600073,
|
|
"loss": 5.4907,
|
|
"mean_token_accuracy": 0.16482501178979875,
|
|
"num_tokens": 8707955.0,
|
|
"step": 5015
|
|
},
|
|
{
|
|
"entropy": 5.753307962417603,
|
|
"epoch": 0.3905854892044349,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004988980120534486,
|
|
"loss": 5.6395,
|
|
"mean_token_accuracy": 0.16032529175281524,
|
|
"num_tokens": 8716103.0,
|
|
"step": 5020
|
|
},
|
|
{
|
|
"entropy": 5.694552755355835,
|
|
"epoch": 0.3909745185761525,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000498895270649594,
|
|
"loss": 5.495,
|
|
"mean_token_accuracy": 0.1711027666926384,
|
|
"num_tokens": 8724499.0,
|
|
"step": 5025
|
|
},
|
|
{
|
|
"entropy": 5.667240476608276,
|
|
"epoch": 0.39136354794787004,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000498892525848485,
|
|
"loss": 5.515,
|
|
"mean_token_accuracy": 0.1710180327296257,
|
|
"num_tokens": 8732829.0,
|
|
"step": 5030
|
|
},
|
|
{
|
|
"entropy": 5.62990984916687,
|
|
"epoch": 0.3917525773195876,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004988897776501633,
|
|
"loss": 5.3801,
|
|
"mean_token_accuracy": 0.17283668592572213,
|
|
"num_tokens": 8741617.0,
|
|
"step": 5035
|
|
},
|
|
{
|
|
"entropy": 5.655297517776489,
|
|
"epoch": 0.3921416066913052,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004988870260546705,
|
|
"loss": 5.369,
|
|
"mean_token_accuracy": 0.17152581065893174,
|
|
"num_tokens": 8750146.0,
|
|
"step": 5040
|
|
},
|
|
{
|
|
"entropy": 5.684403562545777,
|
|
"epoch": 0.39253063606302274,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004988842710620486,
|
|
"loss": 5.5443,
|
|
"mean_token_accuracy": 0.16621591448783873,
|
|
"num_tokens": 8758744.0,
|
|
"step": 5045
|
|
},
|
|
{
|
|
"entropy": 5.667189884185791,
|
|
"epoch": 0.39291966543474033,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004988815126723391,
|
|
"loss": 5.5707,
|
|
"mean_token_accuracy": 0.1603170469403267,
|
|
"num_tokens": 8768219.0,
|
|
"step": 5050
|
|
},
|
|
{
|
|
"entropy": 5.7467005252838135,
|
|
"epoch": 0.3933086948064579,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004988787508855841,
|
|
"loss": 5.5639,
|
|
"mean_token_accuracy": 0.15709830820560455,
|
|
"num_tokens": 8777047.0,
|
|
"step": 5055
|
|
},
|
|
{
|
|
"entropy": 5.678100967407227,
|
|
"epoch": 0.39369772417817545,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004988759857018253,
|
|
"loss": 5.4517,
|
|
"mean_token_accuracy": 0.16117836385965348,
|
|
"num_tokens": 8785918.0,
|
|
"step": 5060
|
|
},
|
|
{
|
|
"entropy": 5.648393821716309,
|
|
"epoch": 0.39408675354989303,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004988732171211048,
|
|
"loss": 5.5265,
|
|
"mean_token_accuracy": 0.15852733552455903,
|
|
"num_tokens": 8794253.0,
|
|
"step": 5065
|
|
},
|
|
{
|
|
"entropy": 5.688629388809204,
|
|
"epoch": 0.39447578292161056,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004988704451434644,
|
|
"loss": 5.5785,
|
|
"mean_token_accuracy": 0.16885487884283065,
|
|
"num_tokens": 8802352.0,
|
|
"step": 5070
|
|
},
|
|
{
|
|
"entropy": 5.782166004180908,
|
|
"epoch": 0.39486481229332815,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004988676697689465,
|
|
"loss": 5.5381,
|
|
"mean_token_accuracy": 0.15879994332790376,
|
|
"num_tokens": 8810956.0,
|
|
"step": 5075
|
|
},
|
|
{
|
|
"entropy": 5.6235700130462645,
|
|
"epoch": 0.39525384166504574,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000498864890997593,
|
|
"loss": 5.4612,
|
|
"mean_token_accuracy": 0.16021384447813034,
|
|
"num_tokens": 8819062.0,
|
|
"step": 5080
|
|
},
|
|
{
|
|
"entropy": 5.668540382385254,
|
|
"epoch": 0.39564287103676327,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004988621088294461,
|
|
"loss": 5.5664,
|
|
"mean_token_accuracy": 0.1544269561767578,
|
|
"num_tokens": 8827470.0,
|
|
"step": 5085
|
|
},
|
|
{
|
|
"entropy": 5.756826543807984,
|
|
"epoch": 0.39603190040848085,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000498859323264548,
|
|
"loss": 5.5979,
|
|
"mean_token_accuracy": 0.1592550739645958,
|
|
"num_tokens": 8837003.0,
|
|
"step": 5090
|
|
},
|
|
{
|
|
"entropy": 5.724267387390137,
|
|
"epoch": 0.3964209297801984,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.000498856534302941,
|
|
"loss": 5.5996,
|
|
"mean_token_accuracy": 0.15522586405277253,
|
|
"num_tokens": 8846605.0,
|
|
"step": 5095
|
|
},
|
|
{
|
|
"entropy": 5.802182674407959,
|
|
"epoch": 0.39680995915191597,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004988537419446673,
|
|
"loss": 5.6184,
|
|
"mean_token_accuracy": 0.15980854481458664,
|
|
"num_tokens": 8855232.0,
|
|
"step": 5100
|
|
},
|
|
{
|
|
"entropy": 5.745633840560913,
|
|
"epoch": 0.39719898852363356,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004988509461897694,
|
|
"loss": 5.5063,
|
|
"mean_token_accuracy": 0.1694345474243164,
|
|
"num_tokens": 8864176.0,
|
|
"step": 5105
|
|
},
|
|
{
|
|
"entropy": 5.700151252746582,
|
|
"epoch": 0.3975880178953511,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004988481470382897,
|
|
"loss": 5.581,
|
|
"mean_token_accuracy": 0.16570933312177658,
|
|
"num_tokens": 8872671.0,
|
|
"step": 5110
|
|
},
|
|
{
|
|
"entropy": 5.633589887619019,
|
|
"epoch": 0.3979770472670687,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004988453444902708,
|
|
"loss": 5.4773,
|
|
"mean_token_accuracy": 0.1687018722295761,
|
|
"num_tokens": 8881316.0,
|
|
"step": 5115
|
|
},
|
|
{
|
|
"entropy": 5.768270206451416,
|
|
"epoch": 0.3983660766387862,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004988425385457549,
|
|
"loss": 5.6128,
|
|
"mean_token_accuracy": 0.16246161833405495,
|
|
"num_tokens": 8890114.0,
|
|
"step": 5120
|
|
},
|
|
{
|
|
"entropy": 5.7693624019622805,
|
|
"epoch": 0.3987551060105038,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004988397292047848,
|
|
"loss": 5.5367,
|
|
"mean_token_accuracy": 0.16662347167730332,
|
|
"num_tokens": 8899598.0,
|
|
"step": 5125
|
|
},
|
|
{
|
|
"entropy": 5.5953779220581055,
|
|
"epoch": 0.3991441353822214,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004988369164674032,
|
|
"loss": 5.3957,
|
|
"mean_token_accuracy": 0.16895558983087539,
|
|
"num_tokens": 8908244.0,
|
|
"step": 5130
|
|
},
|
|
{
|
|
"entropy": 5.67269926071167,
|
|
"epoch": 0.3995331647539389,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004988341003336526,
|
|
"loss": 5.4557,
|
|
"mean_token_accuracy": 0.16561708748340606,
|
|
"num_tokens": 8916280.0,
|
|
"step": 5135
|
|
},
|
|
{
|
|
"entropy": 5.776008939743042,
|
|
"epoch": 0.3999221941256565,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004988312808035757,
|
|
"loss": 5.5072,
|
|
"mean_token_accuracy": 0.1566791757941246,
|
|
"num_tokens": 8923947.0,
|
|
"step": 5140
|
|
},
|
|
{
|
|
"entropy": 5.646599531173706,
|
|
"epoch": 0.400311223497374,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004988284578772155,
|
|
"loss": 5.5424,
|
|
"mean_token_accuracy": 0.15635721981525422,
|
|
"num_tokens": 8933374.0,
|
|
"step": 5145
|
|
},
|
|
{
|
|
"entropy": 5.6722198009490965,
|
|
"epoch": 0.4007002528690916,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004988256315546146,
|
|
"loss": 5.4755,
|
|
"mean_token_accuracy": 0.1645133301615715,
|
|
"num_tokens": 8941757.0,
|
|
"step": 5150
|
|
},
|
|
{
|
|
"entropy": 5.66157374382019,
|
|
"epoch": 0.4010892822408092,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004988228018358161,
|
|
"loss": 5.3833,
|
|
"mean_token_accuracy": 0.16919830590486526,
|
|
"num_tokens": 8950128.0,
|
|
"step": 5155
|
|
},
|
|
{
|
|
"entropy": 5.734227657318115,
|
|
"epoch": 0.40147831161252673,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004988199687208628,
|
|
"loss": 5.5318,
|
|
"mean_token_accuracy": 0.15678182244300842,
|
|
"num_tokens": 8958939.0,
|
|
"step": 5160
|
|
},
|
|
{
|
|
"entropy": 5.7235174655914305,
|
|
"epoch": 0.4018673409842443,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004988171322097977,
|
|
"loss": 5.4884,
|
|
"mean_token_accuracy": 0.166029854118824,
|
|
"num_tokens": 8967519.0,
|
|
"step": 5165
|
|
},
|
|
{
|
|
"entropy": 5.623489952087402,
|
|
"epoch": 0.4022563703559619,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004988142923026638,
|
|
"loss": 5.3649,
|
|
"mean_token_accuracy": 0.17290344089269638,
|
|
"num_tokens": 8976215.0,
|
|
"step": 5170
|
|
},
|
|
{
|
|
"entropy": 5.739109516143799,
|
|
"epoch": 0.40264539972767943,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004988114489995044,
|
|
"loss": 5.5925,
|
|
"mean_token_accuracy": 0.15214981213212014,
|
|
"num_tokens": 8984060.0,
|
|
"step": 5175
|
|
},
|
|
{
|
|
"entropy": 5.726056623458862,
|
|
"epoch": 0.403034429099397,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004988086023003624,
|
|
"loss": 5.5359,
|
|
"mean_token_accuracy": 0.15775070786476136,
|
|
"num_tokens": 8992301.0,
|
|
"step": 5180
|
|
},
|
|
{
|
|
"entropy": 5.763833379745483,
|
|
"epoch": 0.40342345847111455,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004988057522052811,
|
|
"loss": 5.5542,
|
|
"mean_token_accuracy": 0.16253505051136016,
|
|
"num_tokens": 9000517.0,
|
|
"step": 5185
|
|
},
|
|
{
|
|
"entropy": 5.663650035858154,
|
|
"epoch": 0.40381248784283214,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004988028987143037,
|
|
"loss": 5.5185,
|
|
"mean_token_accuracy": 0.15818402916193008,
|
|
"num_tokens": 9008826.0,
|
|
"step": 5190
|
|
},
|
|
{
|
|
"entropy": 5.710343217849731,
|
|
"epoch": 0.4042015172145497,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004988000418274736,
|
|
"loss": 5.5037,
|
|
"mean_token_accuracy": 0.15956878066062927,
|
|
"num_tokens": 9017952.0,
|
|
"step": 5195
|
|
},
|
|
{
|
|
"entropy": 5.698844003677368,
|
|
"epoch": 0.40459054658626725,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004987971815448341,
|
|
"loss": 5.5108,
|
|
"mean_token_accuracy": 0.16802990138530732,
|
|
"num_tokens": 9026688.0,
|
|
"step": 5200
|
|
},
|
|
{
|
|
"entropy": 5.6753887176513675,
|
|
"epoch": 0.40497957595798484,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004987943178664285,
|
|
"loss": 5.4604,
|
|
"mean_token_accuracy": 0.16948893219232558,
|
|
"num_tokens": 9035761.0,
|
|
"step": 5205
|
|
},
|
|
{
|
|
"entropy": 5.711546516418457,
|
|
"epoch": 0.40536860532970237,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004987914507923004,
|
|
"loss": 5.6052,
|
|
"mean_token_accuracy": 0.15351177304983138,
|
|
"num_tokens": 9044510.0,
|
|
"step": 5210
|
|
},
|
|
{
|
|
"entropy": 5.688313055038452,
|
|
"epoch": 0.40575763470141996,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004987885803224931,
|
|
"loss": 5.4623,
|
|
"mean_token_accuracy": 0.16280150562524795,
|
|
"num_tokens": 9053031.0,
|
|
"step": 5215
|
|
},
|
|
{
|
|
"entropy": 5.616592454910278,
|
|
"epoch": 0.40614666407313754,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004987857064570505,
|
|
"loss": 5.4429,
|
|
"mean_token_accuracy": 0.1689184382557869,
|
|
"num_tokens": 9061580.0,
|
|
"step": 5220
|
|
},
|
|
{
|
|
"entropy": 5.711910200119019,
|
|
"epoch": 0.4065356934448551,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004987828291960158,
|
|
"loss": 5.5666,
|
|
"mean_token_accuracy": 0.16402611136436462,
|
|
"num_tokens": 9069741.0,
|
|
"step": 5225
|
|
},
|
|
{
|
|
"entropy": 5.8263026714324955,
|
|
"epoch": 0.40692472281657266,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000498779948539433,
|
|
"loss": 5.5922,
|
|
"mean_token_accuracy": 0.15314422994852067,
|
|
"num_tokens": 9079214.0,
|
|
"step": 5230
|
|
},
|
|
{
|
|
"entropy": 5.779076194763183,
|
|
"epoch": 0.4073137521882902,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004987770644873455,
|
|
"loss": 5.5444,
|
|
"mean_token_accuracy": 0.16699129492044448,
|
|
"num_tokens": 9088201.0,
|
|
"step": 5235
|
|
},
|
|
{
|
|
"entropy": 5.714314365386963,
|
|
"epoch": 0.4077027815600078,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004987741770397974,
|
|
"loss": 5.5828,
|
|
"mean_token_accuracy": 0.15950050503015517,
|
|
"num_tokens": 9096829.0,
|
|
"step": 5240
|
|
},
|
|
{
|
|
"entropy": 5.693706512451172,
|
|
"epoch": 0.40809181093172536,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004987712861968323,
|
|
"loss": 5.5217,
|
|
"mean_token_accuracy": 0.16581078618764877,
|
|
"num_tokens": 9105515.0,
|
|
"step": 5245
|
|
},
|
|
{
|
|
"entropy": 5.708260154724121,
|
|
"epoch": 0.4084808403034429,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000498768391958494,
|
|
"loss": 5.4997,
|
|
"mean_token_accuracy": 0.16316778659820558,
|
|
"num_tokens": 9113614.0,
|
|
"step": 5250
|
|
},
|
|
{
|
|
"entropy": 5.705586671829224,
|
|
"epoch": 0.4088698696751605,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004987654943248266,
|
|
"loss": 5.5814,
|
|
"mean_token_accuracy": 0.15525239408016206,
|
|
"num_tokens": 9122337.0,
|
|
"step": 5255
|
|
},
|
|
{
|
|
"entropy": 5.752633762359619,
|
|
"epoch": 0.40925889904687807,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004987625932958739,
|
|
"loss": 5.4856,
|
|
"mean_token_accuracy": 0.16904787570238114,
|
|
"num_tokens": 9130417.0,
|
|
"step": 5260
|
|
},
|
|
{
|
|
"entropy": 5.7156274795532225,
|
|
"epoch": 0.4096479284185956,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004987596888716801,
|
|
"loss": 5.5429,
|
|
"mean_token_accuracy": 0.15976496934890747,
|
|
"num_tokens": 9139317.0,
|
|
"step": 5265
|
|
},
|
|
{
|
|
"entropy": 5.701608371734619,
|
|
"epoch": 0.4100369577903132,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004987567810522892,
|
|
"loss": 5.5256,
|
|
"mean_token_accuracy": 0.16300612986087798,
|
|
"num_tokens": 9147808.0,
|
|
"step": 5270
|
|
},
|
|
{
|
|
"entropy": 5.785950708389282,
|
|
"epoch": 0.4104259871620307,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004987538698377451,
|
|
"loss": 5.6164,
|
|
"mean_token_accuracy": 0.1566879279911518,
|
|
"num_tokens": 9157117.0,
|
|
"step": 5275
|
|
},
|
|
{
|
|
"entropy": 5.738699245452881,
|
|
"epoch": 0.4108150165337483,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004987509552280924,
|
|
"loss": 5.4742,
|
|
"mean_token_accuracy": 0.15899330377578735,
|
|
"num_tokens": 9165297.0,
|
|
"step": 5280
|
|
},
|
|
{
|
|
"entropy": 5.749457693099975,
|
|
"epoch": 0.4112040459054659,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000498748037223375,
|
|
"loss": 5.605,
|
|
"mean_token_accuracy": 0.16066010892391205,
|
|
"num_tokens": 9172945.0,
|
|
"step": 5285
|
|
},
|
|
{
|
|
"entropy": 5.722745656967163,
|
|
"epoch": 0.4115930752771834,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004987451158236372,
|
|
"loss": 5.5321,
|
|
"mean_token_accuracy": 0.16613929271697997,
|
|
"num_tokens": 9181445.0,
|
|
"step": 5290
|
|
},
|
|
{
|
|
"entropy": 5.635143423080445,
|
|
"epoch": 0.411982104648901,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004987421910289234,
|
|
"loss": 5.3782,
|
|
"mean_token_accuracy": 0.17040496617555617,
|
|
"num_tokens": 9189535.0,
|
|
"step": 5295
|
|
},
|
|
{
|
|
"entropy": 5.684240674972534,
|
|
"epoch": 0.41237113402061853,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004987392628392781,
|
|
"loss": 5.6002,
|
|
"mean_token_accuracy": 0.14962754249572754,
|
|
"num_tokens": 9198328.0,
|
|
"step": 5300
|
|
},
|
|
{
|
|
"entropy": 5.749529075622559,
|
|
"epoch": 0.4127601633923361,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004987363312547456,
|
|
"loss": 5.486,
|
|
"mean_token_accuracy": 0.16676264256238937,
|
|
"num_tokens": 9206840.0,
|
|
"step": 5305
|
|
},
|
|
{
|
|
"entropy": 5.644282436370849,
|
|
"epoch": 0.4131491927640537,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004987333962753703,
|
|
"loss": 5.3891,
|
|
"mean_token_accuracy": 0.1677182286977768,
|
|
"num_tokens": 9215155.0,
|
|
"step": 5310
|
|
},
|
|
{
|
|
"entropy": 5.636444759368897,
|
|
"epoch": 0.41353822213577124,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004987304579011967,
|
|
"loss": 5.5709,
|
|
"mean_token_accuracy": 0.16278092861175536,
|
|
"num_tokens": 9224426.0,
|
|
"step": 5315
|
|
},
|
|
{
|
|
"entropy": 5.75674786567688,
|
|
"epoch": 0.4139272515074888,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004987275161322697,
|
|
"loss": 5.5879,
|
|
"mean_token_accuracy": 0.16320908665657044,
|
|
"num_tokens": 9233785.0,
|
|
"step": 5320
|
|
},
|
|
{
|
|
"entropy": 5.726920557022095,
|
|
"epoch": 0.41431628087920636,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004987245709686337,
|
|
"loss": 5.5433,
|
|
"mean_token_accuracy": 0.1654205784201622,
|
|
"num_tokens": 9242168.0,
|
|
"step": 5325
|
|
},
|
|
{
|
|
"entropy": 5.675925016403198,
|
|
"epoch": 0.41470531025092394,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004987216224103334,
|
|
"loss": 5.5575,
|
|
"mean_token_accuracy": 0.165568046271801,
|
|
"num_tokens": 9250862.0,
|
|
"step": 5330
|
|
},
|
|
{
|
|
"entropy": 5.745130348205566,
|
|
"epoch": 0.41509433962264153,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004987186704574136,
|
|
"loss": 5.5718,
|
|
"mean_token_accuracy": 0.1554880768060684,
|
|
"num_tokens": 9259957.0,
|
|
"step": 5335
|
|
},
|
|
{
|
|
"entropy": 5.6644360542297365,
|
|
"epoch": 0.41548336899435906,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004987157151099189,
|
|
"loss": 5.4438,
|
|
"mean_token_accuracy": 0.1625848740339279,
|
|
"num_tokens": 9268590.0,
|
|
"step": 5340
|
|
},
|
|
{
|
|
"entropy": 5.731019973754883,
|
|
"epoch": 0.41587239836607665,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004987127563678945,
|
|
"loss": 5.5041,
|
|
"mean_token_accuracy": 0.16602175831794738,
|
|
"num_tokens": 9276872.0,
|
|
"step": 5345
|
|
},
|
|
{
|
|
"entropy": 5.660704183578491,
|
|
"epoch": 0.4162614277377942,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004987097942313852,
|
|
"loss": 5.3897,
|
|
"mean_token_accuracy": 0.16859978586435317,
|
|
"num_tokens": 9284556.0,
|
|
"step": 5350
|
|
},
|
|
{
|
|
"entropy": 5.658067750930786,
|
|
"epoch": 0.41665045710951176,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004987068287004355,
|
|
"loss": 5.5496,
|
|
"mean_token_accuracy": 0.16045835316181184,
|
|
"num_tokens": 9293315.0,
|
|
"step": 5355
|
|
},
|
|
{
|
|
"entropy": 5.743117427825927,
|
|
"epoch": 0.41703948648122935,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004987038597750909,
|
|
"loss": 5.5163,
|
|
"mean_token_accuracy": 0.16282073706388472,
|
|
"num_tokens": 9302923.0,
|
|
"step": 5360
|
|
},
|
|
{
|
|
"entropy": 5.745809125900268,
|
|
"epoch": 0.4174285158529469,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004987008874553964,
|
|
"loss": 5.4611,
|
|
"mean_token_accuracy": 0.16524637937545777,
|
|
"num_tokens": 9311388.0,
|
|
"step": 5365
|
|
},
|
|
{
|
|
"entropy": 5.652669095993042,
|
|
"epoch": 0.41781754522466447,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004986979117413969,
|
|
"loss": 5.4161,
|
|
"mean_token_accuracy": 0.16866108775138855,
|
|
"num_tokens": 9319880.0,
|
|
"step": 5370
|
|
},
|
|
{
|
|
"entropy": 5.64964451789856,
|
|
"epoch": 0.41820657459638205,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004986949326331376,
|
|
"loss": 5.5533,
|
|
"mean_token_accuracy": 0.16394897997379304,
|
|
"num_tokens": 9328374.0,
|
|
"step": 5375
|
|
},
|
|
{
|
|
"entropy": 5.802340698242188,
|
|
"epoch": 0.4185956039680996,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004986919501306638,
|
|
"loss": 5.5123,
|
|
"mean_token_accuracy": 0.1731323316693306,
|
|
"num_tokens": 9336428.0,
|
|
"step": 5380
|
|
},
|
|
{
|
|
"entropy": 5.649902200698852,
|
|
"epoch": 0.41898463333981717,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004986889642340207,
|
|
"loss": 5.5978,
|
|
"mean_token_accuracy": 0.16033813655376433,
|
|
"num_tokens": 9345794.0,
|
|
"step": 5385
|
|
},
|
|
{
|
|
"entropy": 5.750280857086182,
|
|
"epoch": 0.4193736627115347,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004986859749432536,
|
|
"loss": 5.5594,
|
|
"mean_token_accuracy": 0.16315516829490662,
|
|
"num_tokens": 9354724.0,
|
|
"step": 5390
|
|
},
|
|
{
|
|
"entropy": 5.756238889694214,
|
|
"epoch": 0.4197626920832523,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004986829822584078,
|
|
"loss": 5.5656,
|
|
"mean_token_accuracy": 0.15743476301431655,
|
|
"num_tokens": 9364008.0,
|
|
"step": 5395
|
|
},
|
|
{
|
|
"entropy": 5.707322835922241,
|
|
"epoch": 0.4201517214549699,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004986799861795289,
|
|
"loss": 5.5339,
|
|
"mean_token_accuracy": 0.1696193978190422,
|
|
"num_tokens": 9372409.0,
|
|
"step": 5400
|
|
},
|
|
{
|
|
"entropy": 5.7119945049285885,
|
|
"epoch": 0.4205407508266874,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004986769867066622,
|
|
"loss": 5.4935,
|
|
"mean_token_accuracy": 0.15928569734096526,
|
|
"num_tokens": 9381172.0,
|
|
"step": 5405
|
|
},
|
|
{
|
|
"entropy": 5.687317514419556,
|
|
"epoch": 0.420929780198405,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004986739838398532,
|
|
"loss": 5.498,
|
|
"mean_token_accuracy": 0.16979421973228453,
|
|
"num_tokens": 9389245.0,
|
|
"step": 5410
|
|
},
|
|
{
|
|
"entropy": 5.674244928359985,
|
|
"epoch": 0.4213188095701225,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004986709775791475,
|
|
"loss": 5.5252,
|
|
"mean_token_accuracy": 0.1654878482222557,
|
|
"num_tokens": 9397954.0,
|
|
"step": 5415
|
|
},
|
|
{
|
|
"entropy": 5.690672397613525,
|
|
"epoch": 0.4217078389418401,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004986679679245907,
|
|
"loss": 5.6287,
|
|
"mean_token_accuracy": 0.16026378571987152,
|
|
"num_tokens": 9406986.0,
|
|
"step": 5420
|
|
},
|
|
{
|
|
"entropy": 5.717019557952881,
|
|
"epoch": 0.4220968683135577,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004986649548762286,
|
|
"loss": 5.5742,
|
|
"mean_token_accuracy": 0.1631506010890007,
|
|
"num_tokens": 9415163.0,
|
|
"step": 5425
|
|
},
|
|
{
|
|
"entropy": 5.661070251464844,
|
|
"epoch": 0.4224858976852752,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004986619384341066,
|
|
"loss": 5.4088,
|
|
"mean_token_accuracy": 0.1779765322804451,
|
|
"num_tokens": 9423422.0,
|
|
"step": 5430
|
|
},
|
|
{
|
|
"entropy": 5.645610094070435,
|
|
"epoch": 0.4228749270569928,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004986589185982708,
|
|
"loss": 5.4398,
|
|
"mean_token_accuracy": 0.1771764948964119,
|
|
"num_tokens": 9431349.0,
|
|
"step": 5435
|
|
},
|
|
{
|
|
"entropy": 5.688213777542114,
|
|
"epoch": 0.42326395642871034,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004986558953687671,
|
|
"loss": 5.5416,
|
|
"mean_token_accuracy": 0.1582077220082283,
|
|
"num_tokens": 9439715.0,
|
|
"step": 5440
|
|
},
|
|
{
|
|
"entropy": 5.704529523849487,
|
|
"epoch": 0.42365298580042793,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004986528687456409,
|
|
"loss": 5.5438,
|
|
"mean_token_accuracy": 0.16103184521198272,
|
|
"num_tokens": 9448216.0,
|
|
"step": 5445
|
|
},
|
|
{
|
|
"entropy": 5.721759462356568,
|
|
"epoch": 0.4240420151721455,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004986498387289384,
|
|
"loss": 5.4833,
|
|
"mean_token_accuracy": 0.16496723741292954,
|
|
"num_tokens": 9456346.0,
|
|
"step": 5450
|
|
},
|
|
{
|
|
"entropy": 5.695312547683716,
|
|
"epoch": 0.42443104454386305,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004986468053187058,
|
|
"loss": 5.5504,
|
|
"mean_token_accuracy": 0.16503108739852906,
|
|
"num_tokens": 9465476.0,
|
|
"step": 5455
|
|
},
|
|
{
|
|
"entropy": 5.706718254089355,
|
|
"epoch": 0.42482007391558063,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004986437685149887,
|
|
"loss": 5.612,
|
|
"mean_token_accuracy": 0.15952038690447806,
|
|
"num_tokens": 9474582.0,
|
|
"step": 5460
|
|
},
|
|
{
|
|
"entropy": 5.746453380584716,
|
|
"epoch": 0.4252091032872982,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004986407283178334,
|
|
"loss": 5.4859,
|
|
"mean_token_accuracy": 0.1622675821185112,
|
|
"num_tokens": 9482801.0,
|
|
"step": 5465
|
|
},
|
|
{
|
|
"entropy": 5.641479969024658,
|
|
"epoch": 0.42559813265901575,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004986376847272861,
|
|
"loss": 5.5206,
|
|
"mean_token_accuracy": 0.16077911108732224,
|
|
"num_tokens": 9490894.0,
|
|
"step": 5470
|
|
},
|
|
{
|
|
"entropy": 5.651269340515137,
|
|
"epoch": 0.42598716203073334,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004986346377433929,
|
|
"loss": 5.4734,
|
|
"mean_token_accuracy": 0.16265116333961488,
|
|
"num_tokens": 9499414.0,
|
|
"step": 5475
|
|
},
|
|
{
|
|
"entropy": 5.661998271942139,
|
|
"epoch": 0.42637619140245087,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004986315873661999,
|
|
"loss": 5.442,
|
|
"mean_token_accuracy": 0.16423789411783218,
|
|
"num_tokens": 9508945.0,
|
|
"step": 5480
|
|
},
|
|
{
|
|
"entropy": 5.670542764663696,
|
|
"epoch": 0.42676522077416845,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004986285335957536,
|
|
"loss": 5.5177,
|
|
"mean_token_accuracy": 0.16872450709342957,
|
|
"num_tokens": 9517833.0,
|
|
"step": 5485
|
|
},
|
|
{
|
|
"entropy": 5.726272010803223,
|
|
"epoch": 0.42715425014588604,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004986254764321002,
|
|
"loss": 5.6532,
|
|
"mean_token_accuracy": 0.15438937693834304,
|
|
"num_tokens": 9526551.0,
|
|
"step": 5490
|
|
},
|
|
{
|
|
"entropy": 5.655402517318725,
|
|
"epoch": 0.42754327951760357,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004986224158752861,
|
|
"loss": 5.4257,
|
|
"mean_token_accuracy": 0.16619780510663987,
|
|
"num_tokens": 9535224.0,
|
|
"step": 5495
|
|
},
|
|
{
|
|
"entropy": 5.705122661590576,
|
|
"epoch": 0.42793230888932116,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004986193519253578,
|
|
"loss": 5.5366,
|
|
"mean_token_accuracy": 0.154195199906826,
|
|
"num_tokens": 9544466.0,
|
|
"step": 5500
|
|
},
|
|
{
|
|
"entropy": 5.6616448879241945,
|
|
"epoch": 0.4283213382610387,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004986162845823618,
|
|
"loss": 5.5371,
|
|
"mean_token_accuracy": 0.16176573187112808,
|
|
"num_tokens": 9553520.0,
|
|
"step": 5505
|
|
},
|
|
{
|
|
"entropy": 5.68340654373169,
|
|
"epoch": 0.4287103676327563,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004986132138463446,
|
|
"loss": 5.4413,
|
|
"mean_token_accuracy": 0.17152554541826248,
|
|
"num_tokens": 9562053.0,
|
|
"step": 5510
|
|
},
|
|
{
|
|
"entropy": 5.66190538406372,
|
|
"epoch": 0.42909939700447386,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004986101397173528,
|
|
"loss": 5.4353,
|
|
"mean_token_accuracy": 0.16798286885023117,
|
|
"num_tokens": 9570632.0,
|
|
"step": 5515
|
|
},
|
|
{
|
|
"entropy": 5.724105596542358,
|
|
"epoch": 0.4294884263761914,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000498607062195433,
|
|
"loss": 5.4348,
|
|
"mean_token_accuracy": 0.17020454853773118,
|
|
"num_tokens": 9578739.0,
|
|
"step": 5520
|
|
},
|
|
{
|
|
"entropy": 5.612820720672607,
|
|
"epoch": 0.429877455747909,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.000498603981280632,
|
|
"loss": 5.4649,
|
|
"mean_token_accuracy": 0.16295552998781204,
|
|
"num_tokens": 9587314.0,
|
|
"step": 5525
|
|
},
|
|
{
|
|
"entropy": 5.702166795730591,
|
|
"epoch": 0.4302664851196265,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004986008969729964,
|
|
"loss": 5.5272,
|
|
"mean_token_accuracy": 0.16558773517608644,
|
|
"num_tokens": 9595954.0,
|
|
"step": 5530
|
|
},
|
|
{
|
|
"entropy": 5.751034450531006,
|
|
"epoch": 0.4306555144913441,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004985978092725731,
|
|
"loss": 5.5447,
|
|
"mean_token_accuracy": 0.15605991929769517,
|
|
"num_tokens": 9604767.0,
|
|
"step": 5535
|
|
},
|
|
{
|
|
"entropy": 5.632840204238891,
|
|
"epoch": 0.4310445438630617,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000498594718179409,
|
|
"loss": 5.4079,
|
|
"mean_token_accuracy": 0.16811801493167877,
|
|
"num_tokens": 9613173.0,
|
|
"step": 5540
|
|
},
|
|
{
|
|
"entropy": 5.7372047901153564,
|
|
"epoch": 0.4314335732347792,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004985916236935508,
|
|
"loss": 5.5031,
|
|
"mean_token_accuracy": 0.16015706434845925,
|
|
"num_tokens": 9622777.0,
|
|
"step": 5545
|
|
},
|
|
{
|
|
"entropy": 5.673089981079102,
|
|
"epoch": 0.4318226026064968,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004985885258150458,
|
|
"loss": 5.4563,
|
|
"mean_token_accuracy": 0.16085392683744432,
|
|
"num_tokens": 9631019.0,
|
|
"step": 5550
|
|
},
|
|
{
|
|
"entropy": 5.653888320922851,
|
|
"epoch": 0.43221163197821433,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004985854245439408,
|
|
"loss": 5.5169,
|
|
"mean_token_accuracy": 0.15890958905220032,
|
|
"num_tokens": 9639797.0,
|
|
"step": 5555
|
|
},
|
|
{
|
|
"entropy": 5.694570541381836,
|
|
"epoch": 0.4326006613499319,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004985823198802827,
|
|
"loss": 5.4995,
|
|
"mean_token_accuracy": 0.16874769777059556,
|
|
"num_tokens": 9648393.0,
|
|
"step": 5560
|
|
},
|
|
{
|
|
"entropy": 5.712398386001587,
|
|
"epoch": 0.4329896907216495,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004985792118241188,
|
|
"loss": 5.4821,
|
|
"mean_token_accuracy": 0.1667462021112442,
|
|
"num_tokens": 9657260.0,
|
|
"step": 5565
|
|
},
|
|
{
|
|
"entropy": 5.654960584640503,
|
|
"epoch": 0.43337872009336703,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004985761003754961,
|
|
"loss": 5.5491,
|
|
"mean_token_accuracy": 0.16649328768253327,
|
|
"num_tokens": 9665883.0,
|
|
"step": 5570
|
|
},
|
|
{
|
|
"entropy": 5.7316896438598635,
|
|
"epoch": 0.4337677494650846,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004985729855344622,
|
|
"loss": 5.5645,
|
|
"mean_token_accuracy": 0.1632181152701378,
|
|
"num_tokens": 9674100.0,
|
|
"step": 5575
|
|
},
|
|
{
|
|
"entropy": 5.70767560005188,
|
|
"epoch": 0.4341567788368022,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000498569867301064,
|
|
"loss": 5.5275,
|
|
"mean_token_accuracy": 0.1664811134338379,
|
|
"num_tokens": 9683236.0,
|
|
"step": 5580
|
|
},
|
|
{
|
|
"entropy": 5.661159086227417,
|
|
"epoch": 0.43454580820851973,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004985667456753489,
|
|
"loss": 5.4882,
|
|
"mean_token_accuracy": 0.1633784294128418,
|
|
"num_tokens": 9692076.0,
|
|
"step": 5585
|
|
},
|
|
{
|
|
"entropy": 5.708376789093018,
|
|
"epoch": 0.4349348375802373,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004985636206573642,
|
|
"loss": 5.5367,
|
|
"mean_token_accuracy": 0.16655746847391129,
|
|
"num_tokens": 9700266.0,
|
|
"step": 5590
|
|
},
|
|
{
|
|
"entropy": 5.7091821193695065,
|
|
"epoch": 0.43532386695195485,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004985604922471575,
|
|
"loss": 5.4921,
|
|
"mean_token_accuracy": 0.16823821514844894,
|
|
"num_tokens": 9708643.0,
|
|
"step": 5595
|
|
},
|
|
{
|
|
"entropy": 5.710525894165039,
|
|
"epoch": 0.43571289632367244,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004985573604447761,
|
|
"loss": 5.5321,
|
|
"mean_token_accuracy": 0.16186349242925643,
|
|
"num_tokens": 9717459.0,
|
|
"step": 5600
|
|
},
|
|
{
|
|
"entropy": 5.641446352005005,
|
|
"epoch": 0.43610192569539,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004985542252502676,
|
|
"loss": 5.4471,
|
|
"mean_token_accuracy": 0.16886800825595855,
|
|
"num_tokens": 9726251.0,
|
|
"step": 5605
|
|
},
|
|
{
|
|
"entropy": 5.5887237071990965,
|
|
"epoch": 0.43649095506710756,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004985510866636796,
|
|
"loss": 5.4351,
|
|
"mean_token_accuracy": 0.16684530675411224,
|
|
"num_tokens": 9735327.0,
|
|
"step": 5610
|
|
},
|
|
{
|
|
"entropy": 5.692466068267822,
|
|
"epoch": 0.43687998443882514,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004985479446850596,
|
|
"loss": 5.5955,
|
|
"mean_token_accuracy": 0.1570721372961998,
|
|
"num_tokens": 9743642.0,
|
|
"step": 5615
|
|
},
|
|
{
|
|
"entropy": 5.708640003204346,
|
|
"epoch": 0.4372690138105427,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004985447993144554,
|
|
"loss": 5.4528,
|
|
"mean_token_accuracy": 0.16921658664941788,
|
|
"num_tokens": 9752235.0,
|
|
"step": 5620
|
|
},
|
|
{
|
|
"entropy": 5.721048498153687,
|
|
"epoch": 0.43765804318226026,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004985416505519147,
|
|
"loss": 5.5436,
|
|
"mean_token_accuracy": 0.15602369606494904,
|
|
"num_tokens": 9761012.0,
|
|
"step": 5625
|
|
},
|
|
{
|
|
"entropy": 5.660058546066284,
|
|
"epoch": 0.43804707255397785,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004985384983974853,
|
|
"loss": 5.4967,
|
|
"mean_token_accuracy": 0.16976085305213928,
|
|
"num_tokens": 9769810.0,
|
|
"step": 5630
|
|
},
|
|
{
|
|
"entropy": 5.696043157577515,
|
|
"epoch": 0.4384361019256954,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004985353428512148,
|
|
"loss": 5.4427,
|
|
"mean_token_accuracy": 0.16465951800346373,
|
|
"num_tokens": 9778186.0,
|
|
"step": 5635
|
|
},
|
|
{
|
|
"entropy": 5.6428123950958256,
|
|
"epoch": 0.43882513129741296,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004985321839131514,
|
|
"loss": 5.5107,
|
|
"mean_token_accuracy": 0.1715571776032448,
|
|
"num_tokens": 9786456.0,
|
|
"step": 5640
|
|
},
|
|
{
|
|
"entropy": 5.6313409328460695,
|
|
"epoch": 0.4392141606691305,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004985290215833428,
|
|
"loss": 5.5105,
|
|
"mean_token_accuracy": 0.16007644087076187,
|
|
"num_tokens": 9794613.0,
|
|
"step": 5645
|
|
},
|
|
{
|
|
"entropy": 5.772847032546997,
|
|
"epoch": 0.4396031900408481,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004985258558618372,
|
|
"loss": 5.4253,
|
|
"mean_token_accuracy": 0.16906558126211166,
|
|
"num_tokens": 9803388.0,
|
|
"step": 5650
|
|
},
|
|
{
|
|
"entropy": 5.686429882049561,
|
|
"epoch": 0.43999221941256567,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004985226867486825,
|
|
"loss": 5.4927,
|
|
"mean_token_accuracy": 0.16778526455163956,
|
|
"num_tokens": 9812450.0,
|
|
"step": 5655
|
|
},
|
|
{
|
|
"entropy": 5.697888708114624,
|
|
"epoch": 0.4403812487842832,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004985195142439267,
|
|
"loss": 5.5822,
|
|
"mean_token_accuracy": 0.15718315094709395,
|
|
"num_tokens": 9821377.0,
|
|
"step": 5660
|
|
},
|
|
{
|
|
"entropy": 5.705540800094605,
|
|
"epoch": 0.4407702781560008,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004985163383476181,
|
|
"loss": 5.4875,
|
|
"mean_token_accuracy": 0.1577681854367256,
|
|
"num_tokens": 9829761.0,
|
|
"step": 5665
|
|
},
|
|
{
|
|
"entropy": 5.733972978591919,
|
|
"epoch": 0.44115930752771837,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004985131590598048,
|
|
"loss": 5.5511,
|
|
"mean_token_accuracy": 0.1609368309378624,
|
|
"num_tokens": 9838921.0,
|
|
"step": 5670
|
|
},
|
|
{
|
|
"entropy": 5.6359227180480955,
|
|
"epoch": 0.4415483368994359,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004985099763805352,
|
|
"loss": 5.3777,
|
|
"mean_token_accuracy": 0.17368233948946,
|
|
"num_tokens": 9846822.0,
|
|
"step": 5675
|
|
},
|
|
{
|
|
"entropy": 5.72635440826416,
|
|
"epoch": 0.4419373662711535,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004985067903098574,
|
|
"loss": 5.5993,
|
|
"mean_token_accuracy": 0.16365385204553604,
|
|
"num_tokens": 9855951.0,
|
|
"step": 5680
|
|
},
|
|
{
|
|
"entropy": 5.744476556777954,
|
|
"epoch": 0.442326395642871,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004985036008478197,
|
|
"loss": 5.5551,
|
|
"mean_token_accuracy": 0.1636480838060379,
|
|
"num_tokens": 9864875.0,
|
|
"step": 5685
|
|
},
|
|
{
|
|
"entropy": 5.712133169174194,
|
|
"epoch": 0.4427154250145886,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004985004079944707,
|
|
"loss": 5.5163,
|
|
"mean_token_accuracy": 0.16914052963256837,
|
|
"num_tokens": 9873785.0,
|
|
"step": 5690
|
|
},
|
|
{
|
|
"entropy": 5.688980293273926,
|
|
"epoch": 0.4431044543863062,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004984972117498587,
|
|
"loss": 5.5177,
|
|
"mean_token_accuracy": 0.16533356308937072,
|
|
"num_tokens": 9883214.0,
|
|
"step": 5695
|
|
},
|
|
{
|
|
"entropy": 5.645994234085083,
|
|
"epoch": 0.4434934837580237,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004984940121140323,
|
|
"loss": 5.479,
|
|
"mean_token_accuracy": 0.16787913143634797,
|
|
"num_tokens": 9891346.0,
|
|
"step": 5700
|
|
},
|
|
{
|
|
"entropy": 5.633553791046142,
|
|
"epoch": 0.4438825131297413,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00049849080908704,
|
|
"loss": 5.4031,
|
|
"mean_token_accuracy": 0.16850567013025283,
|
|
"num_tokens": 9900646.0,
|
|
"step": 5705
|
|
},
|
|
{
|
|
"entropy": 5.717324352264404,
|
|
"epoch": 0.44427154250145884,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004984876026689302,
|
|
"loss": 5.5555,
|
|
"mean_token_accuracy": 0.16231814920902252,
|
|
"num_tokens": 9910851.0,
|
|
"step": 5710
|
|
},
|
|
{
|
|
"entropy": 5.761937665939331,
|
|
"epoch": 0.4446605718731764,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000498484392859752,
|
|
"loss": 5.5562,
|
|
"mean_token_accuracy": 0.16021174788475037,
|
|
"num_tokens": 9919919.0,
|
|
"step": 5715
|
|
},
|
|
{
|
|
"entropy": 5.69112377166748,
|
|
"epoch": 0.445049601244894,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004984811796595538,
|
|
"loss": 5.4923,
|
|
"mean_token_accuracy": 0.16262091994285582,
|
|
"num_tokens": 9928831.0,
|
|
"step": 5720
|
|
},
|
|
{
|
|
"entropy": 5.654398727416992,
|
|
"epoch": 0.44543863061661154,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004984779630683843,
|
|
"loss": 5.4547,
|
|
"mean_token_accuracy": 0.1687433198094368,
|
|
"num_tokens": 9936840.0,
|
|
"step": 5725
|
|
},
|
|
{
|
|
"entropy": 5.6957135677337645,
|
|
"epoch": 0.44582765998832913,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004984747430862924,
|
|
"loss": 5.5298,
|
|
"mean_token_accuracy": 0.16438896656036378,
|
|
"num_tokens": 9945845.0,
|
|
"step": 5730
|
|
},
|
|
{
|
|
"entropy": 5.732899951934814,
|
|
"epoch": 0.44621668936004666,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004984715197133271,
|
|
"loss": 5.5126,
|
|
"mean_token_accuracy": 0.16476755142211913,
|
|
"num_tokens": 9955176.0,
|
|
"step": 5735
|
|
},
|
|
{
|
|
"entropy": 5.601716375350952,
|
|
"epoch": 0.44660571873176425,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004984682929495371,
|
|
"loss": 5.4027,
|
|
"mean_token_accuracy": 0.16928163319826126,
|
|
"num_tokens": 9963182.0,
|
|
"step": 5740
|
|
},
|
|
{
|
|
"entropy": 5.685400867462159,
|
|
"epoch": 0.44699474810348183,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004984650627949715,
|
|
"loss": 5.5542,
|
|
"mean_token_accuracy": 0.16373046189546586,
|
|
"num_tokens": 9971239.0,
|
|
"step": 5745
|
|
},
|
|
{
|
|
"entropy": 5.712329864501953,
|
|
"epoch": 0.44738377747519936,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004984618292496792,
|
|
"loss": 5.5029,
|
|
"mean_token_accuracy": 0.16495627909898758,
|
|
"num_tokens": 9980285.0,
|
|
"step": 5750
|
|
},
|
|
{
|
|
"entropy": 5.7070457458496096,
|
|
"epoch": 0.44777280684691695,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004984585923137093,
|
|
"loss": 5.516,
|
|
"mean_token_accuracy": 0.16542391180992128,
|
|
"num_tokens": 9988922.0,
|
|
"step": 5755
|
|
},
|
|
{
|
|
"entropy": 5.711098575592041,
|
|
"epoch": 0.4481618362186345,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000498455351987111,
|
|
"loss": 5.5938,
|
|
"mean_token_accuracy": 0.1608327105641365,
|
|
"num_tokens": 9998538.0,
|
|
"step": 5760
|
|
},
|
|
{
|
|
"entropy": 5.81380786895752,
|
|
"epoch": 0.44855086559035207,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004984521082699333,
|
|
"loss": 5.4965,
|
|
"mean_token_accuracy": 0.16169293075799943,
|
|
"num_tokens": 10006646.0,
|
|
"step": 5765
|
|
},
|
|
{
|
|
"entropy": 5.657651472091675,
|
|
"epoch": 0.44893989496206965,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004984488611622256,
|
|
"loss": 5.4764,
|
|
"mean_token_accuracy": 0.1706524446606636,
|
|
"num_tokens": 10016511.0,
|
|
"step": 5770
|
|
},
|
|
{
|
|
"entropy": 5.626505661010742,
|
|
"epoch": 0.4493289243337872,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000498445610664037,
|
|
"loss": 5.3888,
|
|
"mean_token_accuracy": 0.16900736689567566,
|
|
"num_tokens": 10025223.0,
|
|
"step": 5775
|
|
},
|
|
{
|
|
"entropy": 5.618741846084594,
|
|
"epoch": 0.44971795370550477,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000498442356775417,
|
|
"loss": 5.4751,
|
|
"mean_token_accuracy": 0.16690605729818345,
|
|
"num_tokens": 10033678.0,
|
|
"step": 5780
|
|
},
|
|
{
|
|
"entropy": 5.664579105377197,
|
|
"epoch": 0.45010698307722236,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004984390994964148,
|
|
"loss": 5.3964,
|
|
"mean_token_accuracy": 0.16832560449838638,
|
|
"num_tokens": 10042028.0,
|
|
"step": 5785
|
|
},
|
|
{
|
|
"entropy": 5.711661767959595,
|
|
"epoch": 0.4504960124489399,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00049843583882708,
|
|
"loss": 5.5481,
|
|
"mean_token_accuracy": 0.16350454241037368,
|
|
"num_tokens": 10050758.0,
|
|
"step": 5790
|
|
},
|
|
{
|
|
"entropy": 5.591366386413574,
|
|
"epoch": 0.4508850418206575,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000498432574767462,
|
|
"loss": 5.3269,
|
|
"mean_token_accuracy": 0.17831166684627534,
|
|
"num_tokens": 10058688.0,
|
|
"step": 5795
|
|
},
|
|
{
|
|
"entropy": 5.621751403808593,
|
|
"epoch": 0.451274071192375,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004984293073176103,
|
|
"loss": 5.4197,
|
|
"mean_token_accuracy": 0.17680519819259644,
|
|
"num_tokens": 10067302.0,
|
|
"step": 5800
|
|
},
|
|
{
|
|
"entropy": 5.620537376403808,
|
|
"epoch": 0.4516631005640926,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004984260364775744,
|
|
"loss": 5.4157,
|
|
"mean_token_accuracy": 0.1698002278804779,
|
|
"num_tokens": 10076424.0,
|
|
"step": 5805
|
|
},
|
|
{
|
|
"entropy": 5.689474725723267,
|
|
"epoch": 0.4520521299358102,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.000498422762247404,
|
|
"loss": 5.5609,
|
|
"mean_token_accuracy": 0.16164169758558272,
|
|
"num_tokens": 10086307.0,
|
|
"step": 5810
|
|
},
|
|
{
|
|
"entropy": 5.6550195693969725,
|
|
"epoch": 0.4524411593075277,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004984194846271489,
|
|
"loss": 5.4124,
|
|
"mean_token_accuracy": 0.16617335975170136,
|
|
"num_tokens": 10094954.0,
|
|
"step": 5815
|
|
},
|
|
{
|
|
"entropy": 5.625373649597168,
|
|
"epoch": 0.4528301886792453,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004984162036168586,
|
|
"loss": 5.5063,
|
|
"mean_token_accuracy": 0.1653664916753769,
|
|
"num_tokens": 10104401.0,
|
|
"step": 5820
|
|
},
|
|
{
|
|
"entropy": 5.585896444320679,
|
|
"epoch": 0.4532192180509628,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004984129192165831,
|
|
"loss": 5.5119,
|
|
"mean_token_accuracy": 0.16613335609436036,
|
|
"num_tokens": 10112596.0,
|
|
"step": 5825
|
|
},
|
|
{
|
|
"entropy": 5.704642724990845,
|
|
"epoch": 0.4536082474226804,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004984096314263722,
|
|
"loss": 5.5643,
|
|
"mean_token_accuracy": 0.16454292684793473,
|
|
"num_tokens": 10121311.0,
|
|
"step": 5830
|
|
},
|
|
{
|
|
"entropy": 5.630156230926514,
|
|
"epoch": 0.453997276794398,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004984063402462757,
|
|
"loss": 5.3555,
|
|
"mean_token_accuracy": 0.17521204501390458,
|
|
"num_tokens": 10130010.0,
|
|
"step": 5835
|
|
},
|
|
{
|
|
"entropy": 5.6026153564453125,
|
|
"epoch": 0.45438630616611553,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004984030456763435,
|
|
"loss": 5.4706,
|
|
"mean_token_accuracy": 0.1734953925013542,
|
|
"num_tokens": 10138473.0,
|
|
"step": 5840
|
|
},
|
|
{
|
|
"entropy": 5.762540626525879,
|
|
"epoch": 0.4547753355378331,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004983997477166257,
|
|
"loss": 5.54,
|
|
"mean_token_accuracy": 0.16557761579751967,
|
|
"num_tokens": 10146843.0,
|
|
"step": 5845
|
|
},
|
|
{
|
|
"entropy": 5.585455226898193,
|
|
"epoch": 0.45516436490955064,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004983964463671723,
|
|
"loss": 5.4082,
|
|
"mean_token_accuracy": 0.17130711823701858,
|
|
"num_tokens": 10155319.0,
|
|
"step": 5850
|
|
},
|
|
{
|
|
"entropy": 5.660451078414917,
|
|
"epoch": 0.45555339428126823,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004983931416280334,
|
|
"loss": 5.5784,
|
|
"mean_token_accuracy": 0.15584017261862754,
|
|
"num_tokens": 10164308.0,
|
|
"step": 5855
|
|
},
|
|
{
|
|
"entropy": 5.755096054077148,
|
|
"epoch": 0.4559424236529858,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004983898334992591,
|
|
"loss": 5.5853,
|
|
"mean_token_accuracy": 0.16000744700431824,
|
|
"num_tokens": 10173173.0,
|
|
"step": 5860
|
|
},
|
|
{
|
|
"entropy": 5.678262710571289,
|
|
"epoch": 0.45633145302470335,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004983865219808998,
|
|
"loss": 5.489,
|
|
"mean_token_accuracy": 0.16422337144613267,
|
|
"num_tokens": 10181376.0,
|
|
"step": 5865
|
|
},
|
|
{
|
|
"entropy": 5.746049976348877,
|
|
"epoch": 0.45672048239642093,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004983832070730055,
|
|
"loss": 5.5995,
|
|
"mean_token_accuracy": 0.16115534156560898,
|
|
"num_tokens": 10189701.0,
|
|
"step": 5870
|
|
},
|
|
{
|
|
"entropy": 5.6774920463562015,
|
|
"epoch": 0.4571095117681385,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004983798887756265,
|
|
"loss": 5.4579,
|
|
"mean_token_accuracy": 0.1671434983611107,
|
|
"num_tokens": 10198721.0,
|
|
"step": 5875
|
|
},
|
|
{
|
|
"entropy": 5.598591899871826,
|
|
"epoch": 0.45749854113985605,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004983765670888133,
|
|
"loss": 5.3462,
|
|
"mean_token_accuracy": 0.17291613519191742,
|
|
"num_tokens": 10206428.0,
|
|
"step": 5880
|
|
},
|
|
{
|
|
"entropy": 5.562051773071289,
|
|
"epoch": 0.45788757051157364,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004983732420126163,
|
|
"loss": 5.4937,
|
|
"mean_token_accuracy": 0.16735068559646607,
|
|
"num_tokens": 10214941.0,
|
|
"step": 5885
|
|
},
|
|
{
|
|
"entropy": 5.686462688446045,
|
|
"epoch": 0.45827659988329117,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004983699135470858,
|
|
"loss": 5.4916,
|
|
"mean_token_accuracy": 0.16933013796806334,
|
|
"num_tokens": 10223491.0,
|
|
"step": 5890
|
|
},
|
|
{
|
|
"entropy": 5.685241460800171,
|
|
"epoch": 0.45866562925500876,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004983665816922723,
|
|
"loss": 5.4304,
|
|
"mean_token_accuracy": 0.16738610714673996,
|
|
"num_tokens": 10231820.0,
|
|
"step": 5895
|
|
},
|
|
{
|
|
"entropy": 5.642031812667847,
|
|
"epoch": 0.45905465862672634,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004983632464482267,
|
|
"loss": 5.4196,
|
|
"mean_token_accuracy": 0.17414960265159607,
|
|
"num_tokens": 10239781.0,
|
|
"step": 5900
|
|
},
|
|
{
|
|
"entropy": 5.657448434829712,
|
|
"epoch": 0.4594436879984439,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004983599078149991,
|
|
"loss": 5.4475,
|
|
"mean_token_accuracy": 0.1785872086882591,
|
|
"num_tokens": 10248093.0,
|
|
"step": 5905
|
|
},
|
|
{
|
|
"entropy": 5.702689075469971,
|
|
"epoch": 0.45983271737016146,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004983565657926405,
|
|
"loss": 5.4636,
|
|
"mean_token_accuracy": 0.16945738792419435,
|
|
"num_tokens": 10256370.0,
|
|
"step": 5910
|
|
},
|
|
{
|
|
"entropy": 5.615186977386474,
|
|
"epoch": 0.460221746741879,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004983532203812017,
|
|
"loss": 5.4399,
|
|
"mean_token_accuracy": 0.16275497525930405,
|
|
"num_tokens": 10264924.0,
|
|
"step": 5915
|
|
},
|
|
{
|
|
"entropy": 5.643068838119507,
|
|
"epoch": 0.4606107761135966,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004983498715807331,
|
|
"loss": 5.3804,
|
|
"mean_token_accuracy": 0.1671242117881775,
|
|
"num_tokens": 10273488.0,
|
|
"step": 5920
|
|
},
|
|
{
|
|
"entropy": 5.668789386749268,
|
|
"epoch": 0.46099980548531416,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004983465193912857,
|
|
"loss": 5.4632,
|
|
"mean_token_accuracy": 0.16634155362844466,
|
|
"num_tokens": 10281534.0,
|
|
"step": 5925
|
|
},
|
|
{
|
|
"entropy": 5.668724584579468,
|
|
"epoch": 0.4613888348570317,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004983431638129104,
|
|
"loss": 5.5026,
|
|
"mean_token_accuracy": 0.16119295507669448,
|
|
"num_tokens": 10289613.0,
|
|
"step": 5930
|
|
},
|
|
{
|
|
"entropy": 5.717075490951538,
|
|
"epoch": 0.4617778642287493,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004983398048456581,
|
|
"loss": 5.5491,
|
|
"mean_token_accuracy": 0.1646980419754982,
|
|
"num_tokens": 10299027.0,
|
|
"step": 5935
|
|
},
|
|
{
|
|
"entropy": 5.717835378646851,
|
|
"epoch": 0.4621668936004668,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004983364424895796,
|
|
"loss": 5.5061,
|
|
"mean_token_accuracy": 0.16248458176851271,
|
|
"num_tokens": 10308727.0,
|
|
"step": 5940
|
|
},
|
|
{
|
|
"entropy": 5.725033092498779,
|
|
"epoch": 0.4625559229721844,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004983330767447262,
|
|
"loss": 5.5373,
|
|
"mean_token_accuracy": 0.16755590587854385,
|
|
"num_tokens": 10318129.0,
|
|
"step": 5945
|
|
},
|
|
{
|
|
"entropy": 5.624452114105225,
|
|
"epoch": 0.462944952343902,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004983297076111489,
|
|
"loss": 5.3765,
|
|
"mean_token_accuracy": 0.17445236146450044,
|
|
"num_tokens": 10326504.0,
|
|
"step": 5950
|
|
},
|
|
{
|
|
"entropy": 5.594799041748047,
|
|
"epoch": 0.4633339817156195,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004983263350888987,
|
|
"loss": 5.4356,
|
|
"mean_token_accuracy": 0.17249158918857574,
|
|
"num_tokens": 10334585.0,
|
|
"step": 5955
|
|
},
|
|
{
|
|
"entropy": 5.618805265426635,
|
|
"epoch": 0.4637230110873371,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004983229591780268,
|
|
"loss": 5.4586,
|
|
"mean_token_accuracy": 0.1713235542178154,
|
|
"num_tokens": 10343328.0,
|
|
"step": 5960
|
|
},
|
|
{
|
|
"entropy": 5.618730592727661,
|
|
"epoch": 0.46411204045905463,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004983195798785844,
|
|
"loss": 5.4736,
|
|
"mean_token_accuracy": 0.1642005518078804,
|
|
"num_tokens": 10352289.0,
|
|
"step": 5965
|
|
},
|
|
{
|
|
"entropy": 5.745180225372314,
|
|
"epoch": 0.4645010698307722,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004983161971906228,
|
|
"loss": 5.5841,
|
|
"mean_token_accuracy": 0.15788466483354568,
|
|
"num_tokens": 10360847.0,
|
|
"step": 5970
|
|
},
|
|
{
|
|
"entropy": 5.670765161514282,
|
|
"epoch": 0.4648900992024898,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004983128111141935,
|
|
"loss": 5.4975,
|
|
"mean_token_accuracy": 0.16726861894130707,
|
|
"num_tokens": 10368911.0,
|
|
"step": 5975
|
|
},
|
|
{
|
|
"entropy": 5.621411466598511,
|
|
"epoch": 0.46527912857420733,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004983094216493475,
|
|
"loss": 5.4432,
|
|
"mean_token_accuracy": 0.17352777272462844,
|
|
"num_tokens": 10377257.0,
|
|
"step": 5980
|
|
},
|
|
{
|
|
"entropy": 5.66666350364685,
|
|
"epoch": 0.4656681579459249,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004983060287961367,
|
|
"loss": 5.4989,
|
|
"mean_token_accuracy": 0.1640869066119194,
|
|
"num_tokens": 10386167.0,
|
|
"step": 5985
|
|
},
|
|
{
|
|
"entropy": 5.660472679138183,
|
|
"epoch": 0.4660571873176425,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004983026325546123,
|
|
"loss": 5.3912,
|
|
"mean_token_accuracy": 0.164736832678318,
|
|
"num_tokens": 10395802.0,
|
|
"step": 5990
|
|
},
|
|
{
|
|
"entropy": 5.6535501956939695,
|
|
"epoch": 0.46644621668936004,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004982992329248257,
|
|
"loss": 5.5194,
|
|
"mean_token_accuracy": 0.16232506781816483,
|
|
"num_tokens": 10404836.0,
|
|
"step": 5995
|
|
},
|
|
{
|
|
"entropy": 5.737968635559082,
|
|
"epoch": 0.4668352460610776,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004982958299068289,
|
|
"loss": 5.493,
|
|
"mean_token_accuracy": 0.16429309397935868,
|
|
"num_tokens": 10413394.0,
|
|
"step": 6000
|
|
},
|
|
{
|
|
"epoch": 0.4668352460610776,
|
|
"eval_entropy": 5.495044304110662,
|
|
"eval_loss": 5.507410049438477,
|
|
"eval_mean_token_accuracy": 0.17327504654821005,
|
|
"eval_num_tokens": 10413394.0,
|
|
"eval_runtime": 21.5979,
|
|
"eval_samples_per_second": 1924.173,
|
|
"eval_steps_per_second": 240.533,
|
|
"step": 6000
|
|
},
|
|
{
|
|
"entropy": 5.611471319198609,
|
|
"epoch": 0.46722427543279516,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000498292423500673,
|
|
"loss": 5.3977,
|
|
"mean_token_accuracy": 0.17447368502616883,
|
|
"num_tokens": 10421916.0,
|
|
"step": 6005
|
|
},
|
|
{
|
|
"entropy": 5.626347494125366,
|
|
"epoch": 0.46761330480451274,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004982890137064102,
|
|
"loss": 5.4753,
|
|
"mean_token_accuracy": 0.16418679058551788,
|
|
"num_tokens": 10430703.0,
|
|
"step": 6010
|
|
},
|
|
{
|
|
"entropy": 5.704648208618164,
|
|
"epoch": 0.46800233417623033,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000498285600524092,
|
|
"loss": 5.5136,
|
|
"mean_token_accuracy": 0.16784841120243071,
|
|
"num_tokens": 10439523.0,
|
|
"step": 6015
|
|
},
|
|
{
|
|
"entropy": 5.648009967803955,
|
|
"epoch": 0.46839136354794786,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004982821839537701,
|
|
"loss": 5.4241,
|
|
"mean_token_accuracy": 0.17214948534965516,
|
|
"num_tokens": 10447777.0,
|
|
"step": 6020
|
|
},
|
|
{
|
|
"entropy": 5.638533878326416,
|
|
"epoch": 0.46878039291966545,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004982787639954966,
|
|
"loss": 5.3972,
|
|
"mean_token_accuracy": 0.1707349255681038,
|
|
"num_tokens": 10456105.0,
|
|
"step": 6025
|
|
},
|
|
{
|
|
"entropy": 5.68563323020935,
|
|
"epoch": 0.469169422291383,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004982753406493232,
|
|
"loss": 5.4491,
|
|
"mean_token_accuracy": 0.1683100551366806,
|
|
"num_tokens": 10464590.0,
|
|
"step": 6030
|
|
},
|
|
{
|
|
"entropy": 5.686050891876221,
|
|
"epoch": 0.46955845166310056,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004982719139153018,
|
|
"loss": 5.4714,
|
|
"mean_token_accuracy": 0.1673478290438652,
|
|
"num_tokens": 10472702.0,
|
|
"step": 6035
|
|
},
|
|
{
|
|
"entropy": 5.570622825622559,
|
|
"epoch": 0.46994748103481815,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004982684837934845,
|
|
"loss": 5.4005,
|
|
"mean_token_accuracy": 0.1666673019528389,
|
|
"num_tokens": 10480682.0,
|
|
"step": 6040
|
|
},
|
|
{
|
|
"entropy": 5.721953248977661,
|
|
"epoch": 0.4703365104065357,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004982650502839234,
|
|
"loss": 5.4953,
|
|
"mean_token_accuracy": 0.1655719682574272,
|
|
"num_tokens": 10488873.0,
|
|
"step": 6045
|
|
},
|
|
{
|
|
"entropy": 5.685389995574951,
|
|
"epoch": 0.47072553977825327,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004982616133866705,
|
|
"loss": 5.4602,
|
|
"mean_token_accuracy": 0.1705882355570793,
|
|
"num_tokens": 10497077.0,
|
|
"step": 6050
|
|
},
|
|
{
|
|
"entropy": 5.664164638519287,
|
|
"epoch": 0.4711145691499708,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004982581731017779,
|
|
"loss": 5.4511,
|
|
"mean_token_accuracy": 0.16683453023433686,
|
|
"num_tokens": 10506072.0,
|
|
"step": 6055
|
|
},
|
|
{
|
|
"entropy": 5.685359239578247,
|
|
"epoch": 0.4715035985216884,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004982547294292979,
|
|
"loss": 5.5081,
|
|
"mean_token_accuracy": 0.16408928632736205,
|
|
"num_tokens": 10515175.0,
|
|
"step": 6060
|
|
},
|
|
{
|
|
"entropy": 5.6141149520874025,
|
|
"epoch": 0.47189262789340597,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004982512823692828,
|
|
"loss": 5.4006,
|
|
"mean_token_accuracy": 0.16687188446521758,
|
|
"num_tokens": 10524800.0,
|
|
"step": 6065
|
|
},
|
|
{
|
|
"entropy": 5.649979209899902,
|
|
"epoch": 0.4722816572651235,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004982478319217848,
|
|
"loss": 5.5852,
|
|
"mean_token_accuracy": 0.15808211714029313,
|
|
"num_tokens": 10534608.0,
|
|
"step": 6070
|
|
},
|
|
{
|
|
"entropy": 5.745941495895385,
|
|
"epoch": 0.4726706866368411,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004982443780868562,
|
|
"loss": 5.4897,
|
|
"mean_token_accuracy": 0.16620081812143325,
|
|
"num_tokens": 10542992.0,
|
|
"step": 6075
|
|
},
|
|
{
|
|
"entropy": 5.67744812965393,
|
|
"epoch": 0.4730597160085587,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004982409208645496,
|
|
"loss": 5.4874,
|
|
"mean_token_accuracy": 0.16672162860631942,
|
|
"num_tokens": 10551682.0,
|
|
"step": 6080
|
|
},
|
|
{
|
|
"entropy": 5.611584854125977,
|
|
"epoch": 0.4734487453802762,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004982374602549173,
|
|
"loss": 5.4447,
|
|
"mean_token_accuracy": 0.16964718252420424,
|
|
"num_tokens": 10560556.0,
|
|
"step": 6085
|
|
},
|
|
{
|
|
"entropy": 5.694293689727783,
|
|
"epoch": 0.4738377747519938,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004982339962580119,
|
|
"loss": 5.6142,
|
|
"mean_token_accuracy": 0.15800638645887374,
|
|
"num_tokens": 10569361.0,
|
|
"step": 6090
|
|
},
|
|
{
|
|
"entropy": 5.607173299789428,
|
|
"epoch": 0.4742268041237113,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004982305288738859,
|
|
"loss": 5.4209,
|
|
"mean_token_accuracy": 0.17520027309656144,
|
|
"num_tokens": 10577997.0,
|
|
"step": 6095
|
|
},
|
|
{
|
|
"entropy": 5.687979412078858,
|
|
"epoch": 0.4746158334954289,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004982270581025919,
|
|
"loss": 5.5251,
|
|
"mean_token_accuracy": 0.17112909853458405,
|
|
"num_tokens": 10587005.0,
|
|
"step": 6100
|
|
},
|
|
{
|
|
"entropy": 5.672091341018676,
|
|
"epoch": 0.4750048628671465,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004982235839441826,
|
|
"loss": 5.3696,
|
|
"mean_token_accuracy": 0.17774538993835448,
|
|
"num_tokens": 10595196.0,
|
|
"step": 6105
|
|
},
|
|
{
|
|
"entropy": 5.69416036605835,
|
|
"epoch": 0.475393892238864,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004982201063987108,
|
|
"loss": 5.5435,
|
|
"mean_token_accuracy": 0.1597681984305382,
|
|
"num_tokens": 10603796.0,
|
|
"step": 6110
|
|
},
|
|
{
|
|
"entropy": 5.689189910888672,
|
|
"epoch": 0.4757829216105816,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004982166254662292,
|
|
"loss": 5.5103,
|
|
"mean_token_accuracy": 0.1657646656036377,
|
|
"num_tokens": 10612895.0,
|
|
"step": 6115
|
|
},
|
|
{
|
|
"entropy": 5.6923877716064455,
|
|
"epoch": 0.47617195098229914,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004982131411467904,
|
|
"loss": 5.5651,
|
|
"mean_token_accuracy": 0.16675678938627242,
|
|
"num_tokens": 10621310.0,
|
|
"step": 6120
|
|
},
|
|
{
|
|
"entropy": 5.605409955978393,
|
|
"epoch": 0.4765609803540167,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004982096534404476,
|
|
"loss": 5.3864,
|
|
"mean_token_accuracy": 0.16726448982954026,
|
|
"num_tokens": 10629598.0,
|
|
"step": 6125
|
|
},
|
|
{
|
|
"entropy": 5.692520093917847,
|
|
"epoch": 0.4769500097257343,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004982061623472535,
|
|
"loss": 5.4087,
|
|
"mean_token_accuracy": 0.17069395780563354,
|
|
"num_tokens": 10638218.0,
|
|
"step": 6130
|
|
},
|
|
{
|
|
"entropy": 5.691115808486939,
|
|
"epoch": 0.47733903909745184,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004982026678672612,
|
|
"loss": 5.516,
|
|
"mean_token_accuracy": 0.16282628774642943,
|
|
"num_tokens": 10647215.0,
|
|
"step": 6135
|
|
},
|
|
{
|
|
"entropy": 5.677426338195801,
|
|
"epoch": 0.47772806846916943,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004981991700005238,
|
|
"loss": 5.6324,
|
|
"mean_token_accuracy": 0.15961235165596008,
|
|
"num_tokens": 10655755.0,
|
|
"step": 6140
|
|
},
|
|
{
|
|
"entropy": 5.759636735916137,
|
|
"epoch": 0.47811709784088696,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000498195668747094,
|
|
"loss": 5.5084,
|
|
"mean_token_accuracy": 0.16573580950498581,
|
|
"num_tokens": 10663969.0,
|
|
"step": 6145
|
|
},
|
|
{
|
|
"entropy": 5.6918775081634525,
|
|
"epoch": 0.47850612721260455,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004981921641070254,
|
|
"loss": 5.3825,
|
|
"mean_token_accuracy": 0.16804722398519517,
|
|
"num_tokens": 10672048.0,
|
|
"step": 6150
|
|
},
|
|
{
|
|
"entropy": 5.608302307128906,
|
|
"epoch": 0.47889515658432213,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004981886560803708,
|
|
"loss": 5.4828,
|
|
"mean_token_accuracy": 0.16609022319316863,
|
|
"num_tokens": 10681802.0,
|
|
"step": 6155
|
|
},
|
|
{
|
|
"entropy": 5.6948483943939205,
|
|
"epoch": 0.47928418595603967,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004981851446671838,
|
|
"loss": 5.545,
|
|
"mean_token_accuracy": 0.15990679562091828,
|
|
"num_tokens": 10690618.0,
|
|
"step": 6160
|
|
},
|
|
{
|
|
"entropy": 5.67942967414856,
|
|
"epoch": 0.47967321532775725,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004981816298675173,
|
|
"loss": 5.4514,
|
|
"mean_token_accuracy": 0.17377543151378633,
|
|
"num_tokens": 10699080.0,
|
|
"step": 6165
|
|
},
|
|
{
|
|
"entropy": 5.647350740432739,
|
|
"epoch": 0.4800622446994748,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004981781116814248,
|
|
"loss": 5.4539,
|
|
"mean_token_accuracy": 0.16524712294340133,
|
|
"num_tokens": 10708939.0,
|
|
"step": 6170
|
|
},
|
|
{
|
|
"entropy": 5.69949164390564,
|
|
"epoch": 0.48045127407119237,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004981745901089596,
|
|
"loss": 5.3711,
|
|
"mean_token_accuracy": 0.1681235522031784,
|
|
"num_tokens": 10717356.0,
|
|
"step": 6175
|
|
},
|
|
{
|
|
"entropy": 5.69394736289978,
|
|
"epoch": 0.48084030344290996,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004981710651501753,
|
|
"loss": 5.4605,
|
|
"mean_token_accuracy": 0.16272638440132142,
|
|
"num_tokens": 10725616.0,
|
|
"step": 6180
|
|
},
|
|
{
|
|
"entropy": 5.620643281936646,
|
|
"epoch": 0.4812293328146275,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004981675368051254,
|
|
"loss": 5.4527,
|
|
"mean_token_accuracy": 0.16980734765529631,
|
|
"num_tokens": 10734337.0,
|
|
"step": 6185
|
|
},
|
|
{
|
|
"entropy": 5.645343685150147,
|
|
"epoch": 0.4816183621863451,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004981640050738633,
|
|
"loss": 5.4907,
|
|
"mean_token_accuracy": 0.16745964735746383,
|
|
"num_tokens": 10742720.0,
|
|
"step": 6190
|
|
},
|
|
{
|
|
"entropy": 5.713866233825684,
|
|
"epoch": 0.48200739155806266,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004981604699564426,
|
|
"loss": 5.5143,
|
|
"mean_token_accuracy": 0.16125882863998414,
|
|
"num_tokens": 10751809.0,
|
|
"step": 6195
|
|
},
|
|
{
|
|
"entropy": 5.643674039840699,
|
|
"epoch": 0.4823964209297802,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004981569314529169,
|
|
"loss": 5.3826,
|
|
"mean_token_accuracy": 0.17199781239032746,
|
|
"num_tokens": 10759879.0,
|
|
"step": 6200
|
|
},
|
|
{
|
|
"entropy": 5.555496120452881,
|
|
"epoch": 0.4827854503014978,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00049815338956334,
|
|
"loss": 5.4444,
|
|
"mean_token_accuracy": 0.16761718839406967,
|
|
"num_tokens": 10769309.0,
|
|
"step": 6205
|
|
},
|
|
{
|
|
"entropy": 5.637994718551636,
|
|
"epoch": 0.4831744796732153,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004981498442877656,
|
|
"loss": 5.3933,
|
|
"mean_token_accuracy": 0.17291852235794067,
|
|
"num_tokens": 10777676.0,
|
|
"step": 6210
|
|
},
|
|
{
|
|
"entropy": 5.648993921279907,
|
|
"epoch": 0.4835635090449329,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004981462956262474,
|
|
"loss": 5.5845,
|
|
"mean_token_accuracy": 0.16300415694713594,
|
|
"num_tokens": 10786278.0,
|
|
"step": 6215
|
|
},
|
|
{
|
|
"entropy": 5.711193609237671,
|
|
"epoch": 0.4839525384166505,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004981427435788396,
|
|
"loss": 5.5147,
|
|
"mean_token_accuracy": 0.1662832885980606,
|
|
"num_tokens": 10795323.0,
|
|
"step": 6220
|
|
},
|
|
{
|
|
"entropy": 5.695321989059448,
|
|
"epoch": 0.484341567788368,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004981391881455957,
|
|
"loss": 5.3936,
|
|
"mean_token_accuracy": 0.1736224412918091,
|
|
"num_tokens": 10803978.0,
|
|
"step": 6225
|
|
},
|
|
{
|
|
"entropy": 5.671928787231446,
|
|
"epoch": 0.4847305971600856,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004981356293265696,
|
|
"loss": 5.4905,
|
|
"mean_token_accuracy": 0.16860363334417344,
|
|
"num_tokens": 10812488.0,
|
|
"step": 6230
|
|
},
|
|
{
|
|
"entropy": 5.690825319290161,
|
|
"epoch": 0.4851196265318031,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004981320671218157,
|
|
"loss": 5.4825,
|
|
"mean_token_accuracy": 0.16431137025356293,
|
|
"num_tokens": 10821076.0,
|
|
"step": 6235
|
|
},
|
|
{
|
|
"entropy": 5.602234601974487,
|
|
"epoch": 0.4855086559035207,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004981285015313877,
|
|
"loss": 5.31,
|
|
"mean_token_accuracy": 0.18187370002269745,
|
|
"num_tokens": 10828634.0,
|
|
"step": 6240
|
|
},
|
|
{
|
|
"entropy": 5.634187126159668,
|
|
"epoch": 0.4858976852752383,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004981249325553399,
|
|
"loss": 5.4464,
|
|
"mean_token_accuracy": 0.17350577116012572,
|
|
"num_tokens": 10837481.0,
|
|
"step": 6245
|
|
},
|
|
{
|
|
"entropy": 5.625172281265259,
|
|
"epoch": 0.48628671464695583,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004981213601937264,
|
|
"loss": 5.5051,
|
|
"mean_token_accuracy": 0.15857475399971008,
|
|
"num_tokens": 10846729.0,
|
|
"step": 6250
|
|
},
|
|
{
|
|
"entropy": 5.709941816329956,
|
|
"epoch": 0.4866757440186734,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004981177844466013,
|
|
"loss": 5.4911,
|
|
"mean_token_accuracy": 0.16200155019760132,
|
|
"num_tokens": 10855344.0,
|
|
"step": 6255
|
|
},
|
|
{
|
|
"entropy": 5.695097494125366,
|
|
"epoch": 0.48706477339039095,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004981142053140192,
|
|
"loss": 5.5255,
|
|
"mean_token_accuracy": 0.1674111381173134,
|
|
"num_tokens": 10863934.0,
|
|
"step": 6260
|
|
},
|
|
{
|
|
"entropy": 5.626110935211182,
|
|
"epoch": 0.48745380276210853,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004981106227960339,
|
|
"loss": 5.5045,
|
|
"mean_token_accuracy": 0.16477670669555664,
|
|
"num_tokens": 10872031.0,
|
|
"step": 6265
|
|
},
|
|
{
|
|
"entropy": 5.718598461151123,
|
|
"epoch": 0.4878428321338261,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004981070368927001,
|
|
"loss": 5.5731,
|
|
"mean_token_accuracy": 0.16409001350402833,
|
|
"num_tokens": 10881385.0,
|
|
"step": 6270
|
|
},
|
|
{
|
|
"entropy": 5.678594493865967,
|
|
"epoch": 0.48823186150554365,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000498103447604072,
|
|
"loss": 5.4697,
|
|
"mean_token_accuracy": 0.1685481011867523,
|
|
"num_tokens": 10890483.0,
|
|
"step": 6275
|
|
},
|
|
{
|
|
"entropy": 5.630790519714355,
|
|
"epoch": 0.48862089087726124,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004980998549302044,
|
|
"loss": 5.5031,
|
|
"mean_token_accuracy": 0.17031818777322769,
|
|
"num_tokens": 10898338.0,
|
|
"step": 6280
|
|
},
|
|
{
|
|
"entropy": 5.6111741065979,
|
|
"epoch": 0.4890099202489788,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004980962588711516,
|
|
"loss": 5.4897,
|
|
"mean_token_accuracy": 0.1661595106124878,
|
|
"num_tokens": 10908087.0,
|
|
"step": 6285
|
|
},
|
|
{
|
|
"entropy": 5.747820568084717,
|
|
"epoch": 0.48939894962069636,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000498092659426968,
|
|
"loss": 5.4743,
|
|
"mean_token_accuracy": 0.16227587312459946,
|
|
"num_tokens": 10916704.0,
|
|
"step": 6290
|
|
},
|
|
{
|
|
"entropy": 5.674692535400391,
|
|
"epoch": 0.48978797899241394,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004980890565977085,
|
|
"loss": 5.439,
|
|
"mean_token_accuracy": 0.1698486715555191,
|
|
"num_tokens": 10925186.0,
|
|
"step": 6295
|
|
},
|
|
{
|
|
"entropy": 5.616642427444458,
|
|
"epoch": 0.4901770083641315,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004980854503834276,
|
|
"loss": 5.4967,
|
|
"mean_token_accuracy": 0.16892740577459336,
|
|
"num_tokens": 10934247.0,
|
|
"step": 6300
|
|
},
|
|
{
|
|
"entropy": 5.74802975654602,
|
|
"epoch": 0.49056603773584906,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004980818407841802,
|
|
"loss": 5.5229,
|
|
"mean_token_accuracy": 0.16045583933591842,
|
|
"num_tokens": 10944260.0,
|
|
"step": 6305
|
|
},
|
|
{
|
|
"entropy": 5.697029542922974,
|
|
"epoch": 0.49095506710756665,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004980782278000207,
|
|
"loss": 5.4731,
|
|
"mean_token_accuracy": 0.16220095604658127,
|
|
"num_tokens": 10954065.0,
|
|
"step": 6310
|
|
},
|
|
{
|
|
"entropy": 5.6517290592193605,
|
|
"epoch": 0.4913440964792842,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004980746114310043,
|
|
"loss": 5.5439,
|
|
"mean_token_accuracy": 0.1659497171640396,
|
|
"num_tokens": 10962918.0,
|
|
"step": 6315
|
|
},
|
|
{
|
|
"entropy": 5.617909145355225,
|
|
"epoch": 0.49173312585100176,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004980709916771858,
|
|
"loss": 5.4076,
|
|
"mean_token_accuracy": 0.1703692078590393,
|
|
"num_tokens": 10972356.0,
|
|
"step": 6320
|
|
},
|
|
{
|
|
"entropy": 5.616169452667236,
|
|
"epoch": 0.4921221552227193,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004980673685386198,
|
|
"loss": 5.4644,
|
|
"mean_token_accuracy": 0.1629459321498871,
|
|
"num_tokens": 10980984.0,
|
|
"step": 6325
|
|
},
|
|
{
|
|
"entropy": 5.617296028137207,
|
|
"epoch": 0.4925111845944369,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004980637420153618,
|
|
"loss": 5.4052,
|
|
"mean_token_accuracy": 0.1666889727115631,
|
|
"num_tokens": 10989809.0,
|
|
"step": 6330
|
|
},
|
|
{
|
|
"entropy": 5.63802056312561,
|
|
"epoch": 0.49290021396615447,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004980601121074664,
|
|
"loss": 5.453,
|
|
"mean_token_accuracy": 0.1644183024764061,
|
|
"num_tokens": 10998824.0,
|
|
"step": 6335
|
|
},
|
|
{
|
|
"entropy": 5.722669553756714,
|
|
"epoch": 0.493289243337872,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004980564788149889,
|
|
"loss": 5.5222,
|
|
"mean_token_accuracy": 0.16973644942045213,
|
|
"num_tokens": 11006755.0,
|
|
"step": 6340
|
|
},
|
|
{
|
|
"entropy": 5.619312381744384,
|
|
"epoch": 0.4936782727095896,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004980528421379844,
|
|
"loss": 5.4179,
|
|
"mean_token_accuracy": 0.17462491989135742,
|
|
"num_tokens": 11015337.0,
|
|
"step": 6345
|
|
},
|
|
{
|
|
"entropy": 5.562566661834717,
|
|
"epoch": 0.4940673020813071,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000498049202076508,
|
|
"loss": 5.3348,
|
|
"mean_token_accuracy": 0.17756202816963196,
|
|
"num_tokens": 11024186.0,
|
|
"step": 6350
|
|
},
|
|
{
|
|
"entropy": 5.6552270412445065,
|
|
"epoch": 0.4944563314530247,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004980455586306149,
|
|
"loss": 5.4615,
|
|
"mean_token_accuracy": 0.1687190517783165,
|
|
"num_tokens": 11032504.0,
|
|
"step": 6355
|
|
},
|
|
{
|
|
"entropy": 5.723153495788575,
|
|
"epoch": 0.4948453608247423,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004980419118003605,
|
|
"loss": 5.3969,
|
|
"mean_token_accuracy": 0.16880524754524232,
|
|
"num_tokens": 11042252.0,
|
|
"step": 6360
|
|
},
|
|
{
|
|
"entropy": 5.703668785095215,
|
|
"epoch": 0.4952343901964598,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004980382615858001,
|
|
"loss": 5.4826,
|
|
"mean_token_accuracy": 0.16379437744617462,
|
|
"num_tokens": 11051361.0,
|
|
"step": 6365
|
|
},
|
|
{
|
|
"entropy": 5.6041374683380125,
|
|
"epoch": 0.4956234195681774,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004980346079869892,
|
|
"loss": 5.4484,
|
|
"mean_token_accuracy": 0.16445529013872145,
|
|
"num_tokens": 11060822.0,
|
|
"step": 6370
|
|
},
|
|
{
|
|
"entropy": 5.6370484828948975,
|
|
"epoch": 0.49601244893989493,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000498030951003983,
|
|
"loss": 5.5271,
|
|
"mean_token_accuracy": 0.16127680093050004,
|
|
"num_tokens": 11069528.0,
|
|
"step": 6375
|
|
},
|
|
{
|
|
"entropy": 5.634170007705689,
|
|
"epoch": 0.4964014783116125,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004980272906368371,
|
|
"loss": 5.361,
|
|
"mean_token_accuracy": 0.174397711455822,
|
|
"num_tokens": 11077917.0,
|
|
"step": 6380
|
|
},
|
|
{
|
|
"entropy": 5.5964888572692875,
|
|
"epoch": 0.4967905076833301,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004980236268856071,
|
|
"loss": 5.4408,
|
|
"mean_token_accuracy": 0.16141705960035324,
|
|
"num_tokens": 11085938.0,
|
|
"step": 6385
|
|
},
|
|
{
|
|
"entropy": 5.60595817565918,
|
|
"epoch": 0.49717953705504764,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004980199597503487,
|
|
"loss": 5.5015,
|
|
"mean_token_accuracy": 0.16092778593301774,
|
|
"num_tokens": 11094898.0,
|
|
"step": 6390
|
|
},
|
|
{
|
|
"entropy": 5.640070581436158,
|
|
"epoch": 0.4975685664267652,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004980162892311171,
|
|
"loss": 5.3664,
|
|
"mean_token_accuracy": 0.1711999848484993,
|
|
"num_tokens": 11103038.0,
|
|
"step": 6395
|
|
},
|
|
{
|
|
"entropy": 5.675674295425415,
|
|
"epoch": 0.4979575957984828,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004980126153279684,
|
|
"loss": 5.4478,
|
|
"mean_token_accuracy": 0.16367504447698594,
|
|
"num_tokens": 11111965.0,
|
|
"step": 6400
|
|
},
|
|
{
|
|
"entropy": 5.636992788314819,
|
|
"epoch": 0.49834662517020034,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004980089380409583,
|
|
"loss": 5.4701,
|
|
"mean_token_accuracy": 0.16154250949621202,
|
|
"num_tokens": 11121482.0,
|
|
"step": 6405
|
|
},
|
|
{
|
|
"entropy": 5.66742844581604,
|
|
"epoch": 0.4987356545419179,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004980052573701424,
|
|
"loss": 5.4534,
|
|
"mean_token_accuracy": 0.1701739862561226,
|
|
"num_tokens": 11129742.0,
|
|
"step": 6410
|
|
},
|
|
{
|
|
"entropy": 5.656267976760864,
|
|
"epoch": 0.49912468391363546,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004980015733155767,
|
|
"loss": 5.4676,
|
|
"mean_token_accuracy": 0.16760584563016892,
|
|
"num_tokens": 11138388.0,
|
|
"step": 6415
|
|
},
|
|
{
|
|
"entropy": 5.474362707138061,
|
|
"epoch": 0.49951371328535304,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004979978858773171,
|
|
"loss": 5.2006,
|
|
"mean_token_accuracy": 0.18340540081262588,
|
|
"num_tokens": 11146967.0,
|
|
"step": 6420
|
|
},
|
|
{
|
|
"entropy": 5.641241121292114,
|
|
"epoch": 0.49990274265707063,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004979941950554195,
|
|
"loss": 5.5672,
|
|
"mean_token_accuracy": 0.16281252056360246,
|
|
"num_tokens": 11155888.0,
|
|
"step": 6425
|
|
},
|
|
{
|
|
"entropy": 5.7240630149841305,
|
|
"epoch": 0.5002917720287882,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004979905008499399,
|
|
"loss": 5.4083,
|
|
"mean_token_accuracy": 0.17032212167978286,
|
|
"num_tokens": 11164358.0,
|
|
"step": 6430
|
|
},
|
|
{
|
|
"entropy": 5.611014366149902,
|
|
"epoch": 0.5006808014005057,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004979868032609344,
|
|
"loss": 5.2753,
|
|
"mean_token_accuracy": 0.18071538507938384,
|
|
"num_tokens": 11172416.0,
|
|
"step": 6435
|
|
},
|
|
{
|
|
"entropy": 5.640211296081543,
|
|
"epoch": 0.5010698307722233,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004979831022884591,
|
|
"loss": 5.4608,
|
|
"mean_token_accuracy": 0.16421267986297608,
|
|
"num_tokens": 11181159.0,
|
|
"step": 6440
|
|
},
|
|
{
|
|
"entropy": 5.663838481903076,
|
|
"epoch": 0.5014588601439409,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004979793979325701,
|
|
"loss": 5.4998,
|
|
"mean_token_accuracy": 0.16421327739953995,
|
|
"num_tokens": 11189725.0,
|
|
"step": 6445
|
|
},
|
|
{
|
|
"entropy": 5.672861528396607,
|
|
"epoch": 0.5018478895156584,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004979756901933236,
|
|
"loss": 5.4741,
|
|
"mean_token_accuracy": 0.16618643403053285,
|
|
"num_tokens": 11197795.0,
|
|
"step": 6450
|
|
},
|
|
{
|
|
"entropy": 5.684984397888184,
|
|
"epoch": 0.502236918887376,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000497971979070776,
|
|
"loss": 5.439,
|
|
"mean_token_accuracy": 0.17090869694948196,
|
|
"num_tokens": 11205352.0,
|
|
"step": 6455
|
|
},
|
|
{
|
|
"entropy": 5.633697748184204,
|
|
"epoch": 0.5026259482590936,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004979682645649834,
|
|
"loss": 5.4625,
|
|
"mean_token_accuracy": 0.16927655562758445,
|
|
"num_tokens": 11214142.0,
|
|
"step": 6460
|
|
},
|
|
{
|
|
"entropy": 5.6249748229980465,
|
|
"epoch": 0.5030149776308112,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004979645466760025,
|
|
"loss": 5.3582,
|
|
"mean_token_accuracy": 0.17228575199842452,
|
|
"num_tokens": 11222565.0,
|
|
"step": 6465
|
|
},
|
|
{
|
|
"entropy": 5.6179883003234865,
|
|
"epoch": 0.5034040070025287,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004979608254038892,
|
|
"loss": 5.4671,
|
|
"mean_token_accuracy": 0.1600498229265213,
|
|
"num_tokens": 11231829.0,
|
|
"step": 6470
|
|
},
|
|
{
|
|
"entropy": 5.623617362976074,
|
|
"epoch": 0.5037930363742462,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004979571007487003,
|
|
"loss": 5.4731,
|
|
"mean_token_accuracy": 0.1706765592098236,
|
|
"num_tokens": 11240302.0,
|
|
"step": 6475
|
|
},
|
|
{
|
|
"entropy": 5.727696180343628,
|
|
"epoch": 0.5041820657459638,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004979533727104924,
|
|
"loss": 5.5714,
|
|
"mean_token_accuracy": 0.15697085857391357,
|
|
"num_tokens": 11248610.0,
|
|
"step": 6480
|
|
},
|
|
{
|
|
"entropy": 5.652313756942749,
|
|
"epoch": 0.5045710951176814,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000497949641289322,
|
|
"loss": 5.4685,
|
|
"mean_token_accuracy": 0.17022727876901628,
|
|
"num_tokens": 11257441.0,
|
|
"step": 6485
|
|
},
|
|
{
|
|
"entropy": 5.590007686614991,
|
|
"epoch": 0.504960124489399,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004979459064852456,
|
|
"loss": 5.3465,
|
|
"mean_token_accuracy": 0.16538669615983964,
|
|
"num_tokens": 11265915.0,
|
|
"step": 6490
|
|
},
|
|
{
|
|
"entropy": 5.670529985427857,
|
|
"epoch": 0.5053491538611166,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004979421682983197,
|
|
"loss": 5.4751,
|
|
"mean_token_accuracy": 0.16173707395792009,
|
|
"num_tokens": 11274165.0,
|
|
"step": 6495
|
|
},
|
|
{
|
|
"entropy": 5.689936256408691,
|
|
"epoch": 0.505738183232834,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004979384267286015,
|
|
"loss": 5.4048,
|
|
"mean_token_accuracy": 0.17155286222696303,
|
|
"num_tokens": 11283316.0,
|
|
"step": 6500
|
|
},
|
|
{
|
|
"entropy": 5.648772954940796,
|
|
"epoch": 0.5061272126045516,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004979346817761475,
|
|
"loss": 5.5451,
|
|
"mean_token_accuracy": 0.16382537186145782,
|
|
"num_tokens": 11292289.0,
|
|
"step": 6505
|
|
},
|
|
{
|
|
"entropy": 5.662769746780396,
|
|
"epoch": 0.5065162419762692,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004979309334410144,
|
|
"loss": 5.4601,
|
|
"mean_token_accuracy": 0.16324011385440826,
|
|
"num_tokens": 11301192.0,
|
|
"step": 6510
|
|
},
|
|
{
|
|
"entropy": 5.7098266124725345,
|
|
"epoch": 0.5069052713479868,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004979271817232594,
|
|
"loss": 5.4808,
|
|
"mean_token_accuracy": 0.17188810110092162,
|
|
"num_tokens": 11309906.0,
|
|
"step": 6515
|
|
},
|
|
{
|
|
"entropy": 5.6908995628356935,
|
|
"epoch": 0.5072943007197044,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004979234266229391,
|
|
"loss": 5.4609,
|
|
"mean_token_accuracy": 0.16591265350580214,
|
|
"num_tokens": 11318227.0,
|
|
"step": 6520
|
|
},
|
|
{
|
|
"entropy": 5.543266248703003,
|
|
"epoch": 0.5076833300914219,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004979196681401106,
|
|
"loss": 5.4885,
|
|
"mean_token_accuracy": 0.16181913167238235,
|
|
"num_tokens": 11327524.0,
|
|
"step": 6525
|
|
},
|
|
{
|
|
"entropy": 5.656088352203369,
|
|
"epoch": 0.5080723594631394,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000497915906274831,
|
|
"loss": 5.4004,
|
|
"mean_token_accuracy": 0.17116282731294633,
|
|
"num_tokens": 11336214.0,
|
|
"step": 6530
|
|
},
|
|
{
|
|
"entropy": 5.681649684906006,
|
|
"epoch": 0.508461388834857,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004979121410271574,
|
|
"loss": 5.2699,
|
|
"mean_token_accuracy": 0.18444954007863998,
|
|
"num_tokens": 11344551.0,
|
|
"step": 6535
|
|
},
|
|
{
|
|
"entropy": 5.509459018707275,
|
|
"epoch": 0.5088504182065746,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004979083723971468,
|
|
"loss": 5.3258,
|
|
"mean_token_accuracy": 0.1782999262213707,
|
|
"num_tokens": 11353180.0,
|
|
"step": 6540
|
|
},
|
|
{
|
|
"entropy": 5.462130117416382,
|
|
"epoch": 0.5092394475782922,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004979046003848564,
|
|
"loss": 5.3146,
|
|
"mean_token_accuracy": 0.17773108780384064,
|
|
"num_tokens": 11361343.0,
|
|
"step": 6545
|
|
},
|
|
{
|
|
"entropy": 5.581699991226197,
|
|
"epoch": 0.5096284769500097,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004979008249903435,
|
|
"loss": 5.4102,
|
|
"mean_token_accuracy": 0.17800912261009216,
|
|
"num_tokens": 11369915.0,
|
|
"step": 6550
|
|
},
|
|
{
|
|
"entropy": 5.63182520866394,
|
|
"epoch": 0.5100175063217273,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004978970462136655,
|
|
"loss": 5.4432,
|
|
"mean_token_accuracy": 0.16393458247184753,
|
|
"num_tokens": 11379813.0,
|
|
"step": 6555
|
|
},
|
|
{
|
|
"entropy": 5.6643470287322994,
|
|
"epoch": 0.5104065356934449,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004978932640548794,
|
|
"loss": 5.3959,
|
|
"mean_token_accuracy": 0.1692471981048584,
|
|
"num_tokens": 11388029.0,
|
|
"step": 6560
|
|
},
|
|
{
|
|
"entropy": 5.615650320053101,
|
|
"epoch": 0.5107955650651624,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004978894785140429,
|
|
"loss": 5.3138,
|
|
"mean_token_accuracy": 0.17617870420217513,
|
|
"num_tokens": 11395852.0,
|
|
"step": 6565
|
|
},
|
|
{
|
|
"entropy": 5.594472980499267,
|
|
"epoch": 0.51118459443688,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004978856895912132,
|
|
"loss": 5.424,
|
|
"mean_token_accuracy": 0.1696908950805664,
|
|
"num_tokens": 11404756.0,
|
|
"step": 6570
|
|
},
|
|
{
|
|
"entropy": 5.736187171936035,
|
|
"epoch": 0.5115736238085975,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004978818972864481,
|
|
"loss": 5.5854,
|
|
"mean_token_accuracy": 0.16184193193912505,
|
|
"num_tokens": 11413301.0,
|
|
"step": 6575
|
|
},
|
|
{
|
|
"entropy": 5.711348819732666,
|
|
"epoch": 0.5119626531803151,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004978781015998048,
|
|
"loss": 5.3515,
|
|
"mean_token_accuracy": 0.1738321989774704,
|
|
"num_tokens": 11421034.0,
|
|
"step": 6580
|
|
},
|
|
{
|
|
"entropy": 5.609139537811279,
|
|
"epoch": 0.5123516825520327,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004978743025313413,
|
|
"loss": 5.3942,
|
|
"mean_token_accuracy": 0.17445635795593262,
|
|
"num_tokens": 11429066.0,
|
|
"step": 6585
|
|
},
|
|
{
|
|
"entropy": 5.498823261260986,
|
|
"epoch": 0.5127407119237503,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004978705000811148,
|
|
"loss": 5.4094,
|
|
"mean_token_accuracy": 0.16928456127643585,
|
|
"num_tokens": 11438109.0,
|
|
"step": 6590
|
|
},
|
|
{
|
|
"entropy": 5.658320903778076,
|
|
"epoch": 0.5131297412954678,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004978666942491832,
|
|
"loss": 5.4287,
|
|
"mean_token_accuracy": 0.1691526874899864,
|
|
"num_tokens": 11446787.0,
|
|
"step": 6595
|
|
},
|
|
{
|
|
"entropy": 5.59825587272644,
|
|
"epoch": 0.5135187706671853,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004978628850356043,
|
|
"loss": 5.3867,
|
|
"mean_token_accuracy": 0.16849370002746583,
|
|
"num_tokens": 11456262.0,
|
|
"step": 6600
|
|
},
|
|
{
|
|
"entropy": 5.638675928115845,
|
|
"epoch": 0.5139078000389029,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004978590724404358,
|
|
"loss": 5.3882,
|
|
"mean_token_accuracy": 0.17555086463689804,
|
|
"num_tokens": 11464297.0,
|
|
"step": 6605
|
|
},
|
|
{
|
|
"entropy": 5.6504510879516605,
|
|
"epoch": 0.5142968294106205,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004978552564637356,
|
|
"loss": 5.4598,
|
|
"mean_token_accuracy": 0.16988648921251298,
|
|
"num_tokens": 11473519.0,
|
|
"step": 6610
|
|
},
|
|
{
|
|
"entropy": 5.662782049179077,
|
|
"epoch": 0.5146858587823381,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004978514371055616,
|
|
"loss": 5.4553,
|
|
"mean_token_accuracy": 0.16260288804769515,
|
|
"num_tokens": 11482249.0,
|
|
"step": 6615
|
|
},
|
|
{
|
|
"entropy": 5.5754162788391115,
|
|
"epoch": 0.5150748881540557,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004978476143659718,
|
|
"loss": 5.4179,
|
|
"mean_token_accuracy": 0.1698406532406807,
|
|
"num_tokens": 11490687.0,
|
|
"step": 6620
|
|
},
|
|
{
|
|
"entropy": 5.561270093917846,
|
|
"epoch": 0.5154639175257731,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004978437882450241,
|
|
"loss": 5.4276,
|
|
"mean_token_accuracy": 0.1648566707968712,
|
|
"num_tokens": 11500225.0,
|
|
"step": 6625
|
|
},
|
|
{
|
|
"entropy": 5.6289667129516605,
|
|
"epoch": 0.5158529468974907,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004978399587427766,
|
|
"loss": 5.3552,
|
|
"mean_token_accuracy": 0.1658610612154007,
|
|
"num_tokens": 11508116.0,
|
|
"step": 6630
|
|
},
|
|
{
|
|
"entropy": 5.542283058166504,
|
|
"epoch": 0.5162419762692083,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004978361258592874,
|
|
"loss": 5.4362,
|
|
"mean_token_accuracy": 0.16429463773965836,
|
|
"num_tokens": 11516525.0,
|
|
"step": 6635
|
|
},
|
|
{
|
|
"entropy": 5.606814956665039,
|
|
"epoch": 0.5166310056409259,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004978322895946147,
|
|
"loss": 5.4068,
|
|
"mean_token_accuracy": 0.17431761771440507,
|
|
"num_tokens": 11525434.0,
|
|
"step": 6640
|
|
},
|
|
{
|
|
"entropy": 5.676286029815674,
|
|
"epoch": 0.5170200350126435,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004978284499488167,
|
|
"loss": 5.4635,
|
|
"mean_token_accuracy": 0.16793732196092606,
|
|
"num_tokens": 11534318.0,
|
|
"step": 6645
|
|
},
|
|
{
|
|
"entropy": 5.6349205493927,
|
|
"epoch": 0.5174090643843611,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004978246069219516,
|
|
"loss": 5.3908,
|
|
"mean_token_accuracy": 0.1799973353743553,
|
|
"num_tokens": 11542777.0,
|
|
"step": 6650
|
|
},
|
|
{
|
|
"entropy": 5.625831985473633,
|
|
"epoch": 0.5177980937560785,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004978207605140777,
|
|
"loss": 5.3896,
|
|
"mean_token_accuracy": 0.17461561858654023,
|
|
"num_tokens": 11550888.0,
|
|
"step": 6655
|
|
},
|
|
{
|
|
"entropy": 5.626785707473755,
|
|
"epoch": 0.5181871231277961,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004978169107252534,
|
|
"loss": 5.4318,
|
|
"mean_token_accuracy": 0.1628247007727623,
|
|
"num_tokens": 11560047.0,
|
|
"step": 6660
|
|
},
|
|
{
|
|
"entropy": 5.671987104415893,
|
|
"epoch": 0.5185761524995137,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004978130575555373,
|
|
"loss": 5.4189,
|
|
"mean_token_accuracy": 0.1725052371621132,
|
|
"num_tokens": 11568862.0,
|
|
"step": 6665
|
|
},
|
|
{
|
|
"entropy": 5.550399494171143,
|
|
"epoch": 0.5189651818712313,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004978092010049877,
|
|
"loss": 5.3735,
|
|
"mean_token_accuracy": 0.1731133446097374,
|
|
"num_tokens": 11577509.0,
|
|
"step": 6670
|
|
},
|
|
{
|
|
"entropy": 5.743370056152344,
|
|
"epoch": 0.5193542112429489,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000497805341073663,
|
|
"loss": 5.4857,
|
|
"mean_token_accuracy": 0.17034248411655425,
|
|
"num_tokens": 11585902.0,
|
|
"step": 6675
|
|
},
|
|
{
|
|
"entropy": 5.667796611785889,
|
|
"epoch": 0.5197432406146664,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004978014777616219,
|
|
"loss": 5.4979,
|
|
"mean_token_accuracy": 0.17023638486862183,
|
|
"num_tokens": 11594895.0,
|
|
"step": 6680
|
|
},
|
|
{
|
|
"entropy": 5.5753960609436035,
|
|
"epoch": 0.520132269986384,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004977976110689229,
|
|
"loss": 5.3123,
|
|
"mean_token_accuracy": 0.1708584502339363,
|
|
"num_tokens": 11604080.0,
|
|
"step": 6685
|
|
},
|
|
{
|
|
"entropy": 5.665987968444824,
|
|
"epoch": 0.5205212993581015,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.000497793740995625,
|
|
"loss": 5.4386,
|
|
"mean_token_accuracy": 0.16633949279785157,
|
|
"num_tokens": 11613370.0,
|
|
"step": 6690
|
|
},
|
|
{
|
|
"entropy": 5.585418844223023,
|
|
"epoch": 0.5209103287298191,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004977898675417866,
|
|
"loss": 5.4211,
|
|
"mean_token_accuracy": 0.16649907678365708,
|
|
"num_tokens": 11621913.0,
|
|
"step": 6695
|
|
},
|
|
{
|
|
"entropy": 5.642942237854004,
|
|
"epoch": 0.5212993581015367,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004977859907074664,
|
|
"loss": 5.5436,
|
|
"mean_token_accuracy": 0.16430994272232055,
|
|
"num_tokens": 11630393.0,
|
|
"step": 6700
|
|
},
|
|
{
|
|
"entropy": 5.720639753341675,
|
|
"epoch": 0.5216883874732542,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004977821104927236,
|
|
"loss": 5.4928,
|
|
"mean_token_accuracy": 0.1631960764527321,
|
|
"num_tokens": 11639038.0,
|
|
"step": 6705
|
|
},
|
|
{
|
|
"entropy": 5.618670892715454,
|
|
"epoch": 0.5220774168449718,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004977782268976167,
|
|
"loss": 5.406,
|
|
"mean_token_accuracy": 0.16851633042097092,
|
|
"num_tokens": 11647355.0,
|
|
"step": 6710
|
|
},
|
|
{
|
|
"entropy": 5.596138334274292,
|
|
"epoch": 0.5224664462166894,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004977743399222048,
|
|
"loss": 5.3802,
|
|
"mean_token_accuracy": 0.1682727590203285,
|
|
"num_tokens": 11655899.0,
|
|
"step": 6715
|
|
},
|
|
{
|
|
"entropy": 5.725822591781617,
|
|
"epoch": 0.522855475588407,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004977704495665471,
|
|
"loss": 5.5674,
|
|
"mean_token_accuracy": 0.15976732969284058,
|
|
"num_tokens": 11664602.0,
|
|
"step": 6720
|
|
},
|
|
{
|
|
"entropy": 5.6776047706604,
|
|
"epoch": 0.5232445049601245,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004977665558307023,
|
|
"loss": 5.3917,
|
|
"mean_token_accuracy": 0.17342305481433867,
|
|
"num_tokens": 11673011.0,
|
|
"step": 6725
|
|
},
|
|
{
|
|
"entropy": 5.750084304809571,
|
|
"epoch": 0.523633534331842,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004977626587147295,
|
|
"loss": 5.5673,
|
|
"mean_token_accuracy": 0.1633073076605797,
|
|
"num_tokens": 11681989.0,
|
|
"step": 6730
|
|
},
|
|
{
|
|
"entropy": 5.703148746490479,
|
|
"epoch": 0.5240225637035596,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000497758758218688,
|
|
"loss": 5.4916,
|
|
"mean_token_accuracy": 0.16183123290538787,
|
|
"num_tokens": 11690502.0,
|
|
"step": 6735
|
|
},
|
|
{
|
|
"entropy": 5.641050243377686,
|
|
"epoch": 0.5244115930752772,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004977548543426368,
|
|
"loss": 5.4935,
|
|
"mean_token_accuracy": 0.166514340788126,
|
|
"num_tokens": 11699594.0,
|
|
"step": 6740
|
|
},
|
|
{
|
|
"entropy": 5.584754896163941,
|
|
"epoch": 0.5248006224469948,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004977509470866353,
|
|
"loss": 5.3668,
|
|
"mean_token_accuracy": 0.16964129209518433,
|
|
"num_tokens": 11708009.0,
|
|
"step": 6745
|
|
},
|
|
{
|
|
"entropy": 5.702879905700684,
|
|
"epoch": 0.5251896518187124,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004977470364507427,
|
|
"loss": 5.5323,
|
|
"mean_token_accuracy": 0.16005744338035582,
|
|
"num_tokens": 11716592.0,
|
|
"step": 6750
|
|
},
|
|
{
|
|
"entropy": 5.688350057601928,
|
|
"epoch": 0.5255786811904298,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004977431224350184,
|
|
"loss": 5.559,
|
|
"mean_token_accuracy": 0.15319210886955262,
|
|
"num_tokens": 11725894.0,
|
|
"step": 6755
|
|
},
|
|
{
|
|
"entropy": 5.726099252700806,
|
|
"epoch": 0.5259677105621474,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004977392050395217,
|
|
"loss": 5.4079,
|
|
"mean_token_accuracy": 0.16904182434082032,
|
|
"num_tokens": 11734141.0,
|
|
"step": 6760
|
|
},
|
|
{
|
|
"entropy": 5.658994817733765,
|
|
"epoch": 0.526356739933865,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004977352842643121,
|
|
"loss": 5.5067,
|
|
"mean_token_accuracy": 0.164360873401165,
|
|
"num_tokens": 11742539.0,
|
|
"step": 6765
|
|
},
|
|
{
|
|
"entropy": 5.661802816390991,
|
|
"epoch": 0.5267457693055826,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000497731360109449,
|
|
"loss": 5.4757,
|
|
"mean_token_accuracy": 0.16561661511659623,
|
|
"num_tokens": 11751649.0,
|
|
"step": 6770
|
|
},
|
|
{
|
|
"entropy": 5.689319801330567,
|
|
"epoch": 0.5271347986773002,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004977274325749922,
|
|
"loss": 5.4887,
|
|
"mean_token_accuracy": 0.16493163704872132,
|
|
"num_tokens": 11760376.0,
|
|
"step": 6775
|
|
},
|
|
{
|
|
"entropy": 5.683128690719604,
|
|
"epoch": 0.5275238280490177,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004977235016610011,
|
|
"loss": 5.4508,
|
|
"mean_token_accuracy": 0.16838639378547668,
|
|
"num_tokens": 11768644.0,
|
|
"step": 6780
|
|
},
|
|
{
|
|
"entropy": 5.702654647827148,
|
|
"epoch": 0.5279128574207352,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004977195673675353,
|
|
"loss": 5.521,
|
|
"mean_token_accuracy": 0.16457068622112275,
|
|
"num_tokens": 11777282.0,
|
|
"step": 6785
|
|
},
|
|
{
|
|
"entropy": 5.630511379241943,
|
|
"epoch": 0.5283018867924528,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004977156296946545,
|
|
"loss": 5.4285,
|
|
"mean_token_accuracy": 0.16902912259101868,
|
|
"num_tokens": 11786108.0,
|
|
"step": 6790
|
|
},
|
|
{
|
|
"entropy": 5.619226408004761,
|
|
"epoch": 0.5286909161641704,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004977116886424187,
|
|
"loss": 5.4717,
|
|
"mean_token_accuracy": 0.1616060495376587,
|
|
"num_tokens": 11795151.0,
|
|
"step": 6795
|
|
},
|
|
{
|
|
"entropy": 5.745349264144897,
|
|
"epoch": 0.529079945535888,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004977077442108873,
|
|
"loss": 5.4159,
|
|
"mean_token_accuracy": 0.17375196963548661,
|
|
"num_tokens": 11803971.0,
|
|
"step": 6800
|
|
},
|
|
{
|
|
"entropy": 5.609159469604492,
|
|
"epoch": 0.5294689749076055,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004977037964001204,
|
|
"loss": 5.4662,
|
|
"mean_token_accuracy": 0.17144315242767333,
|
|
"num_tokens": 11812483.0,
|
|
"step": 6805
|
|
},
|
|
{
|
|
"entropy": 5.580070114135742,
|
|
"epoch": 0.5298580042793231,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000497699845210178,
|
|
"loss": 5.3558,
|
|
"mean_token_accuracy": 0.17689975798130037,
|
|
"num_tokens": 11821144.0,
|
|
"step": 6810
|
|
},
|
|
{
|
|
"entropy": 5.630408430099488,
|
|
"epoch": 0.5302470336510406,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004976958906411197,
|
|
"loss": 5.3189,
|
|
"mean_token_accuracy": 0.17868188321590422,
|
|
"num_tokens": 11829298.0,
|
|
"step": 6815
|
|
},
|
|
{
|
|
"entropy": 5.668645286560059,
|
|
"epoch": 0.5306360630227582,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004976919326930059,
|
|
"loss": 5.4219,
|
|
"mean_token_accuracy": 0.17015438079833983,
|
|
"num_tokens": 11837558.0,
|
|
"step": 6820
|
|
},
|
|
{
|
|
"entropy": 5.546228361129761,
|
|
"epoch": 0.5310250923944758,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004976879713658964,
|
|
"loss": 5.3114,
|
|
"mean_token_accuracy": 0.17407533675432205,
|
|
"num_tokens": 11845770.0,
|
|
"step": 6825
|
|
},
|
|
{
|
|
"entropy": 5.677445554733277,
|
|
"epoch": 0.5314141217661933,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004976840066598514,
|
|
"loss": 5.4971,
|
|
"mean_token_accuracy": 0.15888483226299285,
|
|
"num_tokens": 11854351.0,
|
|
"step": 6830
|
|
},
|
|
{
|
|
"entropy": 5.77203950881958,
|
|
"epoch": 0.5318031511379109,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004976800385749309,
|
|
"loss": 5.4912,
|
|
"mean_token_accuracy": 0.17434257715940477,
|
|
"num_tokens": 11862610.0,
|
|
"step": 6835
|
|
},
|
|
{
|
|
"entropy": 5.652606201171875,
|
|
"epoch": 0.5321921805096285,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004976760671111954,
|
|
"loss": 5.4788,
|
|
"mean_token_accuracy": 0.17035529613494874,
|
|
"num_tokens": 11871078.0,
|
|
"step": 6840
|
|
},
|
|
{
|
|
"entropy": 5.609366941452026,
|
|
"epoch": 0.532581209881346,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000497672092268705,
|
|
"loss": 5.3485,
|
|
"mean_token_accuracy": 0.17742927223443986,
|
|
"num_tokens": 11879303.0,
|
|
"step": 6845
|
|
},
|
|
{
|
|
"entropy": 5.624922180175782,
|
|
"epoch": 0.5329702392530636,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00049766811404752,
|
|
"loss": 5.3957,
|
|
"mean_token_accuracy": 0.17183460891246796,
|
|
"num_tokens": 11887855.0,
|
|
"step": 6850
|
|
},
|
|
{
|
|
"entropy": 5.701442718505859,
|
|
"epoch": 0.5333592686247812,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004976641324477008,
|
|
"loss": 5.3599,
|
|
"mean_token_accuracy": 0.17164410650730133,
|
|
"num_tokens": 11896262.0,
|
|
"step": 6855
|
|
},
|
|
{
|
|
"entropy": 5.511118984222412,
|
|
"epoch": 0.5337482979964987,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004976601474693077,
|
|
"loss": 5.2781,
|
|
"mean_token_accuracy": 0.1787315785884857,
|
|
"num_tokens": 11905140.0,
|
|
"step": 6860
|
|
},
|
|
{
|
|
"entropy": 5.542644214630127,
|
|
"epoch": 0.5341373273682163,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004976561591124014,
|
|
"loss": 5.3198,
|
|
"mean_token_accuracy": 0.17594115883111955,
|
|
"num_tokens": 11913177.0,
|
|
"step": 6865
|
|
},
|
|
{
|
|
"entropy": 5.453828239440918,
|
|
"epoch": 0.5345263567399339,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004976521673770421,
|
|
"loss": 5.3571,
|
|
"mean_token_accuracy": 0.17943618297576905,
|
|
"num_tokens": 11921955.0,
|
|
"step": 6870
|
|
},
|
|
{
|
|
"entropy": 5.603758478164673,
|
|
"epoch": 0.5349153861116515,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004976481722632907,
|
|
"loss": 5.3558,
|
|
"mean_token_accuracy": 0.1703154921531677,
|
|
"num_tokens": 11930976.0,
|
|
"step": 6875
|
|
},
|
|
{
|
|
"entropy": 5.619595861434936,
|
|
"epoch": 0.535304415483369,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004976441737712076,
|
|
"loss": 5.2819,
|
|
"mean_token_accuracy": 0.17539516985416412,
|
|
"num_tokens": 11939708.0,
|
|
"step": 6880
|
|
},
|
|
{
|
|
"entropy": 5.6227837085723875,
|
|
"epoch": 0.5356934448550865,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004976401719008536,
|
|
"loss": 5.4718,
|
|
"mean_token_accuracy": 0.16340460404753684,
|
|
"num_tokens": 11949176.0,
|
|
"step": 6885
|
|
},
|
|
{
|
|
"entropy": 5.623278713226318,
|
|
"epoch": 0.5360824742268041,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004976361666522893,
|
|
"loss": 5.3277,
|
|
"mean_token_accuracy": 0.17831586450338363,
|
|
"num_tokens": 11958089.0,
|
|
"step": 6890
|
|
},
|
|
{
|
|
"entropy": 5.647400808334351,
|
|
"epoch": 0.5364715035985217,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004976321580255755,
|
|
"loss": 5.4209,
|
|
"mean_token_accuracy": 0.17419404089450835,
|
|
"num_tokens": 11966719.0,
|
|
"step": 6895
|
|
},
|
|
{
|
|
"entropy": 5.651475811004639,
|
|
"epoch": 0.5368605329702393,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004976281460207731,
|
|
"loss": 5.4901,
|
|
"mean_token_accuracy": 0.1658528283238411,
|
|
"num_tokens": 11975959.0,
|
|
"step": 6900
|
|
},
|
|
{
|
|
"entropy": 5.63256721496582,
|
|
"epoch": 0.5372495623419569,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000497624130637943,
|
|
"loss": 5.4354,
|
|
"mean_token_accuracy": 0.1661873921751976,
|
|
"num_tokens": 11984282.0,
|
|
"step": 6905
|
|
},
|
|
{
|
|
"entropy": 5.659536361694336,
|
|
"epoch": 0.5376385917136743,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000497620111877146,
|
|
"loss": 5.4367,
|
|
"mean_token_accuracy": 0.1674356371164322,
|
|
"num_tokens": 11993289.0,
|
|
"step": 6910
|
|
},
|
|
{
|
|
"entropy": 5.584860134124756,
|
|
"epoch": 0.5380276210853919,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004976160897384431,
|
|
"loss": 5.3668,
|
|
"mean_token_accuracy": 0.17173303812742233,
|
|
"num_tokens": 12002425.0,
|
|
"step": 6915
|
|
},
|
|
{
|
|
"entropy": 5.628754281997681,
|
|
"epoch": 0.5384166504571095,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004976120642218955,
|
|
"loss": 5.3784,
|
|
"mean_token_accuracy": 0.17149677276611328,
|
|
"num_tokens": 12010435.0,
|
|
"step": 6920
|
|
},
|
|
{
|
|
"entropy": 5.562549209594726,
|
|
"epoch": 0.5388056798288271,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000497608035327564,
|
|
"loss": 5.4306,
|
|
"mean_token_accuracy": 0.1634228304028511,
|
|
"num_tokens": 12018768.0,
|
|
"step": 6925
|
|
},
|
|
{
|
|
"entropy": 5.64377384185791,
|
|
"epoch": 0.5391947092005447,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00049760400305551,
|
|
"loss": 5.4494,
|
|
"mean_token_accuracy": 0.17214796990156173,
|
|
"num_tokens": 12027617.0,
|
|
"step": 6930
|
|
},
|
|
{
|
|
"entropy": 5.663191556930542,
|
|
"epoch": 0.5395837385722622,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004975999674057944,
|
|
"loss": 5.4171,
|
|
"mean_token_accuracy": 0.16715274453163148,
|
|
"num_tokens": 12036024.0,
|
|
"step": 6935
|
|
},
|
|
{
|
|
"entropy": 5.671573257446289,
|
|
"epoch": 0.5399727679439797,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004975959283784787,
|
|
"loss": 5.4519,
|
|
"mean_token_accuracy": 0.16841286569833755,
|
|
"num_tokens": 12044206.0,
|
|
"step": 6940
|
|
},
|
|
{
|
|
"entropy": 5.598822069168091,
|
|
"epoch": 0.5403617973156973,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004975918859736241,
|
|
"loss": 5.3335,
|
|
"mean_token_accuracy": 0.17251801639795303,
|
|
"num_tokens": 12052294.0,
|
|
"step": 6945
|
|
},
|
|
{
|
|
"entropy": 5.585722303390503,
|
|
"epoch": 0.5407508266874149,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004975878401912919,
|
|
"loss": 5.453,
|
|
"mean_token_accuracy": 0.16552573442459106,
|
|
"num_tokens": 12060446.0,
|
|
"step": 6950
|
|
},
|
|
{
|
|
"entropy": 5.657906723022461,
|
|
"epoch": 0.5411398560591325,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004975837910315436,
|
|
"loss": 5.5333,
|
|
"mean_token_accuracy": 0.1649618551135063,
|
|
"num_tokens": 12069267.0,
|
|
"step": 6955
|
|
},
|
|
{
|
|
"entropy": 5.696007919311524,
|
|
"epoch": 0.54152888543085,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004975797384944405,
|
|
"loss": 5.4524,
|
|
"mean_token_accuracy": 0.1656179204583168,
|
|
"num_tokens": 12077808.0,
|
|
"step": 6960
|
|
},
|
|
{
|
|
"entropy": 5.620603752136231,
|
|
"epoch": 0.5419179148025676,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000497575682580044,
|
|
"loss": 5.4231,
|
|
"mean_token_accuracy": 0.16909924298524856,
|
|
"num_tokens": 12086893.0,
|
|
"step": 6965
|
|
},
|
|
{
|
|
"entropy": 5.599455213546753,
|
|
"epoch": 0.5423069441742852,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000497571623288416,
|
|
"loss": 5.3045,
|
|
"mean_token_accuracy": 0.1750321552157402,
|
|
"num_tokens": 12095462.0,
|
|
"step": 6970
|
|
},
|
|
{
|
|
"entropy": 5.646379852294922,
|
|
"epoch": 0.5426959735460027,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004975675606196177,
|
|
"loss": 5.4068,
|
|
"mean_token_accuracy": 0.1716737598180771,
|
|
"num_tokens": 12103477.0,
|
|
"step": 6975
|
|
},
|
|
{
|
|
"entropy": 5.693296003341675,
|
|
"epoch": 0.5430850029177203,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000497563494573711,
|
|
"loss": 5.5203,
|
|
"mean_token_accuracy": 0.1662907287478447,
|
|
"num_tokens": 12112752.0,
|
|
"step": 6980
|
|
},
|
|
{
|
|
"entropy": 5.695676946640015,
|
|
"epoch": 0.5434740322894378,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004975594251507575,
|
|
"loss": 5.4567,
|
|
"mean_token_accuracy": 0.1623358443379402,
|
|
"num_tokens": 12121883.0,
|
|
"step": 6985
|
|
},
|
|
{
|
|
"entropy": 5.662042140960693,
|
|
"epoch": 0.5438630616611554,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000497555352350819,
|
|
"loss": 5.3843,
|
|
"mean_token_accuracy": 0.1695976585149765,
|
|
"num_tokens": 12130316.0,
|
|
"step": 6990
|
|
},
|
|
{
|
|
"entropy": 5.607014846801758,
|
|
"epoch": 0.544252091032873,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004975512761739572,
|
|
"loss": 5.3817,
|
|
"mean_token_accuracy": 0.1685868486762047,
|
|
"num_tokens": 12138856.0,
|
|
"step": 6995
|
|
},
|
|
{
|
|
"entropy": 5.5710813999176025,
|
|
"epoch": 0.5446411204045906,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000497547196620234,
|
|
"loss": 5.449,
|
|
"mean_token_accuracy": 0.1645628333091736,
|
|
"num_tokens": 12147933.0,
|
|
"step": 7000
|
|
},
|
|
{
|
|
"entropy": 5.600865125656128,
|
|
"epoch": 0.5450301497763081,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004975431136897114,
|
|
"loss": 5.3418,
|
|
"mean_token_accuracy": 0.17403218895196915,
|
|
"num_tokens": 12156529.0,
|
|
"step": 7005
|
|
},
|
|
{
|
|
"entropy": 5.6149626731872555,
|
|
"epoch": 0.5454191791480256,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004975390273824512,
|
|
"loss": 5.2957,
|
|
"mean_token_accuracy": 0.17711113393306732,
|
|
"num_tokens": 12165233.0,
|
|
"step": 7010
|
|
},
|
|
{
|
|
"entropy": 5.656652784347534,
|
|
"epoch": 0.5458082085197432,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004975349376985155,
|
|
"loss": 5.4905,
|
|
"mean_token_accuracy": 0.16208152174949647,
|
|
"num_tokens": 12173260.0,
|
|
"step": 7015
|
|
},
|
|
{
|
|
"entropy": 5.633213138580322,
|
|
"epoch": 0.5461972378914608,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004975308446379663,
|
|
"loss": 5.4872,
|
|
"mean_token_accuracy": 0.1661377176642418,
|
|
"num_tokens": 12181676.0,
|
|
"step": 7020
|
|
},
|
|
{
|
|
"entropy": 5.663449764251709,
|
|
"epoch": 0.5465862672631784,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004975267482008657,
|
|
"loss": 5.3998,
|
|
"mean_token_accuracy": 0.16634807139635086,
|
|
"num_tokens": 12189485.0,
|
|
"step": 7025
|
|
},
|
|
{
|
|
"entropy": 5.61206283569336,
|
|
"epoch": 0.546975296634896,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.000497522648387276,
|
|
"loss": 5.318,
|
|
"mean_token_accuracy": 0.17358834743499757,
|
|
"num_tokens": 12198429.0,
|
|
"step": 7030
|
|
},
|
|
{
|
|
"entropy": 5.6052594661712645,
|
|
"epoch": 0.5473643260066134,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004975185451972592,
|
|
"loss": 5.4449,
|
|
"mean_token_accuracy": 0.17202031910419463,
|
|
"num_tokens": 12207404.0,
|
|
"step": 7035
|
|
},
|
|
{
|
|
"entropy": 5.670430994033813,
|
|
"epoch": 0.547753355378331,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004975144386308776,
|
|
"loss": 5.4222,
|
|
"mean_token_accuracy": 0.1661749705672264,
|
|
"num_tokens": 12216301.0,
|
|
"step": 7040
|
|
},
|
|
{
|
|
"entropy": 5.589423131942749,
|
|
"epoch": 0.5481423847500486,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004975103286881936,
|
|
"loss": 5.4065,
|
|
"mean_token_accuracy": 0.17458733767271042,
|
|
"num_tokens": 12224873.0,
|
|
"step": 7045
|
|
},
|
|
{
|
|
"entropy": 5.603284597396851,
|
|
"epoch": 0.5485314141217662,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004975062153692696,
|
|
"loss": 5.3784,
|
|
"mean_token_accuracy": 0.17105503529310226,
|
|
"num_tokens": 12233439.0,
|
|
"step": 7050
|
|
},
|
|
{
|
|
"entropy": 5.656129550933838,
|
|
"epoch": 0.5489204434934838,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004975020986741678,
|
|
"loss": 5.4493,
|
|
"mean_token_accuracy": 0.16752919703722,
|
|
"num_tokens": 12242235.0,
|
|
"step": 7055
|
|
},
|
|
{
|
|
"entropy": 5.597258377075195,
|
|
"epoch": 0.5493094728652014,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004974979786029509,
|
|
"loss": 5.388,
|
|
"mean_token_accuracy": 0.17538175135850906,
|
|
"num_tokens": 12251295.0,
|
|
"step": 7060
|
|
},
|
|
{
|
|
"entropy": 5.629272842407227,
|
|
"epoch": 0.5496985022369189,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004974938551556814,
|
|
"loss": 5.3133,
|
|
"mean_token_accuracy": 0.17724365890026092,
|
|
"num_tokens": 12260130.0,
|
|
"step": 7065
|
|
},
|
|
{
|
|
"entropy": 5.5907104969024655,
|
|
"epoch": 0.5500875316086364,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004974897283324217,
|
|
"loss": 5.393,
|
|
"mean_token_accuracy": 0.16955282539129257,
|
|
"num_tokens": 12269542.0,
|
|
"step": 7070
|
|
},
|
|
{
|
|
"entropy": 5.630454397201538,
|
|
"epoch": 0.550476560980354,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004974855981332343,
|
|
"loss": 5.4673,
|
|
"mean_token_accuracy": 0.17138559967279435,
|
|
"num_tokens": 12278174.0,
|
|
"step": 7075
|
|
},
|
|
{
|
|
"entropy": 5.663634777069092,
|
|
"epoch": 0.5508655903520716,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004974814645581823,
|
|
"loss": 5.5483,
|
|
"mean_token_accuracy": 0.16026232093572618,
|
|
"num_tokens": 12287651.0,
|
|
"step": 7080
|
|
},
|
|
{
|
|
"entropy": 5.76173586845398,
|
|
"epoch": 0.5512546197237892,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004974773276073282,
|
|
"loss": 5.5228,
|
|
"mean_token_accuracy": 0.1664297416806221,
|
|
"num_tokens": 12296009.0,
|
|
"step": 7085
|
|
},
|
|
{
|
|
"entropy": 5.6218091487884525,
|
|
"epoch": 0.5516436490955067,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004974731872807347,
|
|
"loss": 5.3927,
|
|
"mean_token_accuracy": 0.16824719458818435,
|
|
"num_tokens": 12305406.0,
|
|
"step": 7090
|
|
},
|
|
{
|
|
"entropy": 5.65089635848999,
|
|
"epoch": 0.5520326784672243,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004974690435784647,
|
|
"loss": 5.45,
|
|
"mean_token_accuracy": 0.1661311000585556,
|
|
"num_tokens": 12314169.0,
|
|
"step": 7095
|
|
},
|
|
{
|
|
"entropy": 5.569345140457154,
|
|
"epoch": 0.5524217078389418,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004974648965005811,
|
|
"loss": 5.331,
|
|
"mean_token_accuracy": 0.17652279734611512,
|
|
"num_tokens": 12323019.0,
|
|
"step": 7100
|
|
},
|
|
{
|
|
"entropy": 5.595728015899658,
|
|
"epoch": 0.5528107372106594,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004974607460471466,
|
|
"loss": 5.435,
|
|
"mean_token_accuracy": 0.16858349591493607,
|
|
"num_tokens": 12331491.0,
|
|
"step": 7105
|
|
},
|
|
{
|
|
"entropy": 5.6596444606781,
|
|
"epoch": 0.553199766582377,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004974565922182246,
|
|
"loss": 5.398,
|
|
"mean_token_accuracy": 0.1735352173447609,
|
|
"num_tokens": 12339647.0,
|
|
"step": 7110
|
|
},
|
|
{
|
|
"entropy": 5.648700618743897,
|
|
"epoch": 0.5535887959540945,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004974524350138777,
|
|
"loss": 5.4002,
|
|
"mean_token_accuracy": 0.1696406900882721,
|
|
"num_tokens": 12348469.0,
|
|
"step": 7115
|
|
},
|
|
{
|
|
"entropy": 5.645704698562622,
|
|
"epoch": 0.5539778253258121,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004974482744341693,
|
|
"loss": 5.3714,
|
|
"mean_token_accuracy": 0.17332192361354828,
|
|
"num_tokens": 12357168.0,
|
|
"step": 7120
|
|
},
|
|
{
|
|
"entropy": 5.5719810962677006,
|
|
"epoch": 0.5543668546975297,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004974441104791624,
|
|
"loss": 5.3745,
|
|
"mean_token_accuracy": 0.17122909426689148,
|
|
"num_tokens": 12365750.0,
|
|
"step": 7125
|
|
},
|
|
{
|
|
"entropy": 5.639922761917115,
|
|
"epoch": 0.5547558840692473,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004974399431489201,
|
|
"loss": 5.4018,
|
|
"mean_token_accuracy": 0.17219276428222657,
|
|
"num_tokens": 12374086.0,
|
|
"step": 7130
|
|
},
|
|
{
|
|
"entropy": 5.663942813873291,
|
|
"epoch": 0.5551449134409648,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004974357724435057,
|
|
"loss": 5.3642,
|
|
"mean_token_accuracy": 0.1792665883898735,
|
|
"num_tokens": 12381997.0,
|
|
"step": 7135
|
|
},
|
|
{
|
|
"entropy": 5.646653938293457,
|
|
"epoch": 0.5555339428126823,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004974315983629825,
|
|
"loss": 5.4462,
|
|
"mean_token_accuracy": 0.17241283059120177,
|
|
"num_tokens": 12391083.0,
|
|
"step": 7140
|
|
},
|
|
{
|
|
"entropy": 5.634599733352661,
|
|
"epoch": 0.5559229721843999,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004974274209074139,
|
|
"loss": 5.371,
|
|
"mean_token_accuracy": 0.17252092063426971,
|
|
"num_tokens": 12400016.0,
|
|
"step": 7145
|
|
},
|
|
{
|
|
"entropy": 5.685489320755005,
|
|
"epoch": 0.5563120015561175,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004974232400768632,
|
|
"loss": 5.4818,
|
|
"mean_token_accuracy": 0.16982473880052568,
|
|
"num_tokens": 12409255.0,
|
|
"step": 7150
|
|
},
|
|
{
|
|
"entropy": 5.641375494003296,
|
|
"epoch": 0.5567010309278351,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004974190558713939,
|
|
"loss": 5.3884,
|
|
"mean_token_accuracy": 0.17358123064041137,
|
|
"num_tokens": 12417765.0,
|
|
"step": 7155
|
|
},
|
|
{
|
|
"entropy": 5.669316005706787,
|
|
"epoch": 0.5570900602995527,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004974148682910694,
|
|
"loss": 5.6177,
|
|
"mean_token_accuracy": 0.15360698252916336,
|
|
"num_tokens": 12427588.0,
|
|
"step": 7160
|
|
},
|
|
{
|
|
"entropy": 5.59427547454834,
|
|
"epoch": 0.5574790896712701,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004974106773359533,
|
|
"loss": 5.289,
|
|
"mean_token_accuracy": 0.17874647974967955,
|
|
"num_tokens": 12435773.0,
|
|
"step": 7165
|
|
},
|
|
{
|
|
"entropy": 5.605812740325928,
|
|
"epoch": 0.5578681190429877,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004974064830061091,
|
|
"loss": 5.4123,
|
|
"mean_token_accuracy": 0.17299440503120422,
|
|
"num_tokens": 12443837.0,
|
|
"step": 7170
|
|
},
|
|
{
|
|
"entropy": 5.572979688644409,
|
|
"epoch": 0.5582571484147053,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004974022853016006,
|
|
"loss": 5.4106,
|
|
"mean_token_accuracy": 0.17499408423900603,
|
|
"num_tokens": 12452945.0,
|
|
"step": 7175
|
|
},
|
|
{
|
|
"entropy": 5.595126533508301,
|
|
"epoch": 0.5586461777864229,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004973980842224913,
|
|
"loss": 5.3213,
|
|
"mean_token_accuracy": 0.18019433468580245,
|
|
"num_tokens": 12461008.0,
|
|
"step": 7180
|
|
},
|
|
{
|
|
"entropy": 5.541195869445801,
|
|
"epoch": 0.5590352071581405,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004973938797688452,
|
|
"loss": 5.3315,
|
|
"mean_token_accuracy": 0.16913951933383942,
|
|
"num_tokens": 12469314.0,
|
|
"step": 7185
|
|
},
|
|
{
|
|
"entropy": 5.607437181472778,
|
|
"epoch": 0.559424236529858,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004973896719407259,
|
|
"loss": 5.3747,
|
|
"mean_token_accuracy": 0.16569244116544724,
|
|
"num_tokens": 12477540.0,
|
|
"step": 7190
|
|
},
|
|
{
|
|
"entropy": 5.611822509765625,
|
|
"epoch": 0.5598132659015755,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004973854607381972,
|
|
"loss": 5.4272,
|
|
"mean_token_accuracy": 0.17706743329763414,
|
|
"num_tokens": 12486894.0,
|
|
"step": 7195
|
|
},
|
|
{
|
|
"entropy": 5.660370969772339,
|
|
"epoch": 0.5602022952732931,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004973812461613232,
|
|
"loss": 5.4215,
|
|
"mean_token_accuracy": 0.16543299257755278,
|
|
"num_tokens": 12496213.0,
|
|
"step": 7200
|
|
},
|
|
{
|
|
"entropy": 5.621604681015015,
|
|
"epoch": 0.5605913246450107,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004973770282101677,
|
|
"loss": 5.3941,
|
|
"mean_token_accuracy": 0.17001705318689347,
|
|
"num_tokens": 12504160.0,
|
|
"step": 7205
|
|
},
|
|
{
|
|
"entropy": 5.5064887523651125,
|
|
"epoch": 0.5609803540167283,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004973728068847947,
|
|
"loss": 5.3406,
|
|
"mean_token_accuracy": 0.17627592831850053,
|
|
"num_tokens": 12511915.0,
|
|
"step": 7210
|
|
},
|
|
{
|
|
"entropy": 5.633753728866577,
|
|
"epoch": 0.5613693833884458,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004973685821852684,
|
|
"loss": 5.3721,
|
|
"mean_token_accuracy": 0.17439102977514268,
|
|
"num_tokens": 12520400.0,
|
|
"step": 7215
|
|
},
|
|
{
|
|
"entropy": 5.592429780960083,
|
|
"epoch": 0.5617584127601634,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004973643541116528,
|
|
"loss": 5.295,
|
|
"mean_token_accuracy": 0.1770132914185524,
|
|
"num_tokens": 12528724.0,
|
|
"step": 7220
|
|
},
|
|
{
|
|
"entropy": 5.6063238143920895,
|
|
"epoch": 0.562147442131881,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000497360122664012,
|
|
"loss": 5.4863,
|
|
"mean_token_accuracy": 0.17149095386266708,
|
|
"num_tokens": 12537378.0,
|
|
"step": 7225
|
|
},
|
|
{
|
|
"entropy": 5.597244024276733,
|
|
"epoch": 0.5625364715035985,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004973558878424104,
|
|
"loss": 5.3994,
|
|
"mean_token_accuracy": 0.17489453703165053,
|
|
"num_tokens": 12546080.0,
|
|
"step": 7230
|
|
},
|
|
{
|
|
"entropy": 5.684036159515381,
|
|
"epoch": 0.5629255008753161,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004973516496469119,
|
|
"loss": 5.4159,
|
|
"mean_token_accuracy": 0.1706525832414627,
|
|
"num_tokens": 12554526.0,
|
|
"step": 7235
|
|
},
|
|
{
|
|
"entropy": 5.616761255264282,
|
|
"epoch": 0.5633145302470336,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004973474080775811,
|
|
"loss": 5.3895,
|
|
"mean_token_accuracy": 0.17201378792524338,
|
|
"num_tokens": 12563018.0,
|
|
"step": 7240
|
|
},
|
|
{
|
|
"entropy": 5.597792434692383,
|
|
"epoch": 0.5637035596187512,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004973431631344824,
|
|
"loss": 5.4425,
|
|
"mean_token_accuracy": 0.1725260868668556,
|
|
"num_tokens": 12571611.0,
|
|
"step": 7245
|
|
},
|
|
{
|
|
"entropy": 5.68755464553833,
|
|
"epoch": 0.5640925889904688,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00049733891481768,
|
|
"loss": 5.5059,
|
|
"mean_token_accuracy": 0.1666056454181671,
|
|
"num_tokens": 12580168.0,
|
|
"step": 7250
|
|
},
|
|
{
|
|
"entropy": 5.59826512336731,
|
|
"epoch": 0.5644816183621864,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004973346631272384,
|
|
"loss": 5.4141,
|
|
"mean_token_accuracy": 0.17382865399122238,
|
|
"num_tokens": 12589843.0,
|
|
"step": 7255
|
|
},
|
|
{
|
|
"entropy": 5.685404348373413,
|
|
"epoch": 0.5648706477339039,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004973304080632222,
|
|
"loss": 5.4488,
|
|
"mean_token_accuracy": 0.16553327292203904,
|
|
"num_tokens": 12598219.0,
|
|
"step": 7260
|
|
},
|
|
{
|
|
"entropy": 5.603097867965698,
|
|
"epoch": 0.5652596771056215,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000497326149625696,
|
|
"loss": 5.4304,
|
|
"mean_token_accuracy": 0.16851159632205964,
|
|
"num_tokens": 12606665.0,
|
|
"step": 7265
|
|
},
|
|
{
|
|
"entropy": 5.603170919418335,
|
|
"epoch": 0.565648706477339,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004973218878147244,
|
|
"loss": 5.3684,
|
|
"mean_token_accuracy": 0.17258040308952333,
|
|
"num_tokens": 12615062.0,
|
|
"step": 7270
|
|
},
|
|
{
|
|
"entropy": 5.682673454284668,
|
|
"epoch": 0.5660377358490566,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004973176226303719,
|
|
"loss": 5.4455,
|
|
"mean_token_accuracy": 0.1684245362877846,
|
|
"num_tokens": 12623923.0,
|
|
"step": 7275
|
|
},
|
|
{
|
|
"entropy": 5.619794845581055,
|
|
"epoch": 0.5664267652207742,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004973133540727033,
|
|
"loss": 5.3834,
|
|
"mean_token_accuracy": 0.16963649094104766,
|
|
"num_tokens": 12632579.0,
|
|
"step": 7280
|
|
},
|
|
{
|
|
"entropy": 5.571510648727417,
|
|
"epoch": 0.5668157945924918,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004973090821417835,
|
|
"loss": 5.3358,
|
|
"mean_token_accuracy": 0.17332665473222733,
|
|
"num_tokens": 12640847.0,
|
|
"step": 7285
|
|
},
|
|
{
|
|
"entropy": 5.655331659317016,
|
|
"epoch": 0.5672048239642093,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004973048068376772,
|
|
"loss": 5.3288,
|
|
"mean_token_accuracy": 0.17651396989822388,
|
|
"num_tokens": 12649020.0,
|
|
"step": 7290
|
|
},
|
|
{
|
|
"entropy": 5.5143170833587645,
|
|
"epoch": 0.5675938533359268,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004973005281604492,
|
|
"loss": 5.2662,
|
|
"mean_token_accuracy": 0.17431186586618425,
|
|
"num_tokens": 12657569.0,
|
|
"step": 7295
|
|
},
|
|
{
|
|
"entropy": 5.692615413665772,
|
|
"epoch": 0.5679828827076444,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004972962461101646,
|
|
"loss": 5.5137,
|
|
"mean_token_accuracy": 0.16529098376631737,
|
|
"num_tokens": 12666681.0,
|
|
"step": 7300
|
|
},
|
|
{
|
|
"entropy": 5.616756820678711,
|
|
"epoch": 0.568371912079362,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004972919606868883,
|
|
"loss": 5.3323,
|
|
"mean_token_accuracy": 0.17070917636156083,
|
|
"num_tokens": 12675210.0,
|
|
"step": 7305
|
|
},
|
|
{
|
|
"entropy": 5.661812496185303,
|
|
"epoch": 0.5687609414510796,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004972876718906852,
|
|
"loss": 5.3856,
|
|
"mean_token_accuracy": 0.17086227983236313,
|
|
"num_tokens": 12684019.0,
|
|
"step": 7310
|
|
},
|
|
{
|
|
"entropy": 5.607829952239991,
|
|
"epoch": 0.5691499708227972,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004972833797216206,
|
|
"loss": 5.4218,
|
|
"mean_token_accuracy": 0.1609044313430786,
|
|
"num_tokens": 12692891.0,
|
|
"step": 7315
|
|
},
|
|
{
|
|
"entropy": 5.591648054122925,
|
|
"epoch": 0.5695390001945146,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004972790841797595,
|
|
"loss": 5.3389,
|
|
"mean_token_accuracy": 0.1735210597515106,
|
|
"num_tokens": 12700606.0,
|
|
"step": 7320
|
|
},
|
|
{
|
|
"entropy": 5.58307032585144,
|
|
"epoch": 0.5699280295662322,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000497274785265167,
|
|
"loss": 5.4367,
|
|
"mean_token_accuracy": 0.16894268244504929,
|
|
"num_tokens": 12709116.0,
|
|
"step": 7325
|
|
},
|
|
{
|
|
"entropy": 5.636340570449829,
|
|
"epoch": 0.5703170589379498,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004972704829779086,
|
|
"loss": 5.3984,
|
|
"mean_token_accuracy": 0.170769339799881,
|
|
"num_tokens": 12717484.0,
|
|
"step": 7330
|
|
},
|
|
{
|
|
"entropy": 5.540655183792114,
|
|
"epoch": 0.5707060883096674,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004972661773180492,
|
|
"loss": 5.3223,
|
|
"mean_token_accuracy": 0.17410922795534134,
|
|
"num_tokens": 12726216.0,
|
|
"step": 7335
|
|
},
|
|
{
|
|
"entropy": 5.556302165985107,
|
|
"epoch": 0.571095117681385,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004972618682856545,
|
|
"loss": 5.3093,
|
|
"mean_token_accuracy": 0.17505342066287993,
|
|
"num_tokens": 12735312.0,
|
|
"step": 7340
|
|
},
|
|
{
|
|
"entropy": 5.59719409942627,
|
|
"epoch": 0.5714841470531025,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004972575558807896,
|
|
"loss": 5.4374,
|
|
"mean_token_accuracy": 0.16841867715120315,
|
|
"num_tokens": 12744641.0,
|
|
"step": 7345
|
|
},
|
|
{
|
|
"entropy": 5.6559624671936035,
|
|
"epoch": 0.57187317642482,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004972532401035201,
|
|
"loss": 5.4043,
|
|
"mean_token_accuracy": 0.1704619497060776,
|
|
"num_tokens": 12753951.0,
|
|
"step": 7350
|
|
},
|
|
{
|
|
"entropy": 5.688356494903564,
|
|
"epoch": 0.5722622057965376,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004972489209539114,
|
|
"loss": 5.418,
|
|
"mean_token_accuracy": 0.16977932006120683,
|
|
"num_tokens": 12762571.0,
|
|
"step": 7355
|
|
},
|
|
{
|
|
"entropy": 5.673377943038941,
|
|
"epoch": 0.5726512351682552,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004972445984320292,
|
|
"loss": 5.484,
|
|
"mean_token_accuracy": 0.16849375218153,
|
|
"num_tokens": 12771275.0,
|
|
"step": 7360
|
|
},
|
|
{
|
|
"entropy": 5.620267629623413,
|
|
"epoch": 0.5730402645399728,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004972402725379388,
|
|
"loss": 5.3931,
|
|
"mean_token_accuracy": 0.17000342756509781,
|
|
"num_tokens": 12780488.0,
|
|
"step": 7365
|
|
},
|
|
{
|
|
"entropy": 5.646515369415283,
|
|
"epoch": 0.5734292939116903,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000497235943271706,
|
|
"loss": 5.408,
|
|
"mean_token_accuracy": 0.17405337244272232,
|
|
"num_tokens": 12788588.0,
|
|
"step": 7370
|
|
},
|
|
{
|
|
"entropy": 5.5791943073272705,
|
|
"epoch": 0.5738183232834079,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004972316106333966,
|
|
"loss": 5.3517,
|
|
"mean_token_accuracy": 0.16888998448848724,
|
|
"num_tokens": 12797010.0,
|
|
"step": 7375
|
|
},
|
|
{
|
|
"entropy": 5.655337905883789,
|
|
"epoch": 0.5742073526551255,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004972272746230761,
|
|
"loss": 5.442,
|
|
"mean_token_accuracy": 0.17081831395626068,
|
|
"num_tokens": 12805430.0,
|
|
"step": 7380
|
|
},
|
|
{
|
|
"entropy": 5.704648160934449,
|
|
"epoch": 0.574596382026843,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004972229352408104,
|
|
"loss": 5.4147,
|
|
"mean_token_accuracy": 0.17035266011953354,
|
|
"num_tokens": 12813912.0,
|
|
"step": 7385
|
|
},
|
|
{
|
|
"entropy": 5.688452529907226,
|
|
"epoch": 0.5749854113985606,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004972185924866655,
|
|
"loss": 5.4272,
|
|
"mean_token_accuracy": 0.1671118125319481,
|
|
"num_tokens": 12822421.0,
|
|
"step": 7390
|
|
},
|
|
{
|
|
"entropy": 5.53705153465271,
|
|
"epoch": 0.5753744407702781,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004972142463607071,
|
|
"loss": 5.3079,
|
|
"mean_token_accuracy": 0.1757025510072708,
|
|
"num_tokens": 12830670.0,
|
|
"step": 7395
|
|
},
|
|
{
|
|
"entropy": 5.633034515380859,
|
|
"epoch": 0.5757634701419957,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004972098968630012,
|
|
"loss": 5.431,
|
|
"mean_token_accuracy": 0.16999536752700806,
|
|
"num_tokens": 12839887.0,
|
|
"step": 7400
|
|
},
|
|
{
|
|
"entropy": 5.541968441009521,
|
|
"epoch": 0.5761524995137133,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004972055439936137,
|
|
"loss": 5.3334,
|
|
"mean_token_accuracy": 0.1776442050933838,
|
|
"num_tokens": 12848028.0,
|
|
"step": 7405
|
|
},
|
|
{
|
|
"entropy": 5.519324254989624,
|
|
"epoch": 0.5765415288854309,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004972011877526109,
|
|
"loss": 5.3389,
|
|
"mean_token_accuracy": 0.17134140133857728,
|
|
"num_tokens": 12857248.0,
|
|
"step": 7410
|
|
},
|
|
{
|
|
"entropy": 5.639415216445923,
|
|
"epoch": 0.5769305582571485,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004971968281400587,
|
|
"loss": 5.3294,
|
|
"mean_token_accuracy": 0.17492977529764175,
|
|
"num_tokens": 12866352.0,
|
|
"step": 7415
|
|
},
|
|
{
|
|
"entropy": 5.6588198184967045,
|
|
"epoch": 0.5773195876288659,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004971924651560233,
|
|
"loss": 5.4357,
|
|
"mean_token_accuracy": 0.16394705325365067,
|
|
"num_tokens": 12874548.0,
|
|
"step": 7420
|
|
},
|
|
{
|
|
"entropy": 5.5939655780792235,
|
|
"epoch": 0.5777086170005835,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004971880988005709,
|
|
"loss": 5.2928,
|
|
"mean_token_accuracy": 0.17573003321886063,
|
|
"num_tokens": 12883172.0,
|
|
"step": 7425
|
|
},
|
|
{
|
|
"entropy": 5.526439380645752,
|
|
"epoch": 0.5780976463723011,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004971837290737677,
|
|
"loss": 5.3223,
|
|
"mean_token_accuracy": 0.1796867400407791,
|
|
"num_tokens": 12891776.0,
|
|
"step": 7430
|
|
},
|
|
{
|
|
"entropy": 5.583204650878907,
|
|
"epoch": 0.5784866757440187,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004971793559756801,
|
|
"loss": 5.2974,
|
|
"mean_token_accuracy": 0.17945968955755234,
|
|
"num_tokens": 12900530.0,
|
|
"step": 7435
|
|
},
|
|
{
|
|
"entropy": 5.538809108734131,
|
|
"epoch": 0.5788757051157363,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004971749795063744,
|
|
"loss": 5.3276,
|
|
"mean_token_accuracy": 0.17095972299575807,
|
|
"num_tokens": 12909260.0,
|
|
"step": 7440
|
|
},
|
|
{
|
|
"entropy": 5.569579696655273,
|
|
"epoch": 0.5792647344874537,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.000497170599665917,
|
|
"loss": 5.3305,
|
|
"mean_token_accuracy": 0.16970742046833037,
|
|
"num_tokens": 12918143.0,
|
|
"step": 7445
|
|
},
|
|
{
|
|
"entropy": 5.609571313858032,
|
|
"epoch": 0.5796537638591713,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004971662164543743,
|
|
"loss": 5.3917,
|
|
"mean_token_accuracy": 0.1706962466239929,
|
|
"num_tokens": 12926361.0,
|
|
"step": 7450
|
|
},
|
|
{
|
|
"entropy": 5.564591646194458,
|
|
"epoch": 0.5800427932308889,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004971618298718131,
|
|
"loss": 5.3313,
|
|
"mean_token_accuracy": 0.17570846676826476,
|
|
"num_tokens": 12935080.0,
|
|
"step": 7455
|
|
},
|
|
{
|
|
"entropy": 5.648508977890015,
|
|
"epoch": 0.5804318226026065,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004971574399182995,
|
|
"loss": 5.4895,
|
|
"mean_token_accuracy": 0.16634377092123032,
|
|
"num_tokens": 12944078.0,
|
|
"step": 7460
|
|
},
|
|
{
|
|
"entropy": 5.659052038192749,
|
|
"epoch": 0.5808208519743241,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004971530465939005,
|
|
"loss": 5.3972,
|
|
"mean_token_accuracy": 0.16960996389389038,
|
|
"num_tokens": 12952800.0,
|
|
"step": 7465
|
|
},
|
|
{
|
|
"entropy": 5.715012264251709,
|
|
"epoch": 0.5812098813460417,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004971486498986825,
|
|
"loss": 5.4961,
|
|
"mean_token_accuracy": 0.16457866877317429,
|
|
"num_tokens": 12962402.0,
|
|
"step": 7470
|
|
},
|
|
{
|
|
"entropy": 5.568425273895263,
|
|
"epoch": 0.5815989107177592,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004971442498327124,
|
|
"loss": 5.2584,
|
|
"mean_token_accuracy": 0.17899834513664245,
|
|
"num_tokens": 12971116.0,
|
|
"step": 7475
|
|
},
|
|
{
|
|
"entropy": 5.5052838802337645,
|
|
"epoch": 0.5819879400894767,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004971398463960568,
|
|
"loss": 5.3686,
|
|
"mean_token_accuracy": 0.1670986607670784,
|
|
"num_tokens": 12979570.0,
|
|
"step": 7480
|
|
},
|
|
{
|
|
"entropy": 5.640371656417846,
|
|
"epoch": 0.5823769694611943,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004971354395887827,
|
|
"loss": 5.3951,
|
|
"mean_token_accuracy": 0.17526982724666595,
|
|
"num_tokens": 12987942.0,
|
|
"step": 7485
|
|
},
|
|
{
|
|
"entropy": 5.622890377044678,
|
|
"epoch": 0.5827659988329119,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004971310294109569,
|
|
"loss": 5.4293,
|
|
"mean_token_accuracy": 0.17028453648090364,
|
|
"num_tokens": 12996499.0,
|
|
"step": 7490
|
|
},
|
|
{
|
|
"entropy": 5.529724359512329,
|
|
"epoch": 0.5831550282046295,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004971266158626461,
|
|
"loss": 5.3675,
|
|
"mean_token_accuracy": 0.17635761350393295,
|
|
"num_tokens": 13005622.0,
|
|
"step": 7495
|
|
},
|
|
{
|
|
"entropy": 5.594239330291748,
|
|
"epoch": 0.583544057576347,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004971221989439177,
|
|
"loss": 5.4032,
|
|
"mean_token_accuracy": 0.16471988409757615,
|
|
"num_tokens": 13014417.0,
|
|
"step": 7500
|
|
},
|
|
{
|
|
"entropy": 5.586181688308716,
|
|
"epoch": 0.5839330869480646,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004971177786548384,
|
|
"loss": 5.3209,
|
|
"mean_token_accuracy": 0.17067594975233077,
|
|
"num_tokens": 13022887.0,
|
|
"step": 7505
|
|
},
|
|
{
|
|
"entropy": 5.564024019241333,
|
|
"epoch": 0.5843221163197821,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004971133549954753,
|
|
"loss": 5.4208,
|
|
"mean_token_accuracy": 0.1676742047071457,
|
|
"num_tokens": 13031676.0,
|
|
"step": 7510
|
|
},
|
|
{
|
|
"entropy": 5.591061210632324,
|
|
"epoch": 0.5847111456914997,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004971089279658954,
|
|
"loss": 5.3809,
|
|
"mean_token_accuracy": 0.17073456943035126,
|
|
"num_tokens": 13040489.0,
|
|
"step": 7515
|
|
},
|
|
{
|
|
"entropy": 5.645109987258911,
|
|
"epoch": 0.5851001750632173,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004971044975661663,
|
|
"loss": 5.298,
|
|
"mean_token_accuracy": 0.17565406411886214,
|
|
"num_tokens": 13048280.0,
|
|
"step": 7520
|
|
},
|
|
{
|
|
"entropy": 5.553524398803711,
|
|
"epoch": 0.5854892044349348,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004971000637963549,
|
|
"loss": 5.2769,
|
|
"mean_token_accuracy": 0.18950254768133162,
|
|
"num_tokens": 13056471.0,
|
|
"step": 7525
|
|
},
|
|
{
|
|
"entropy": 5.616096782684326,
|
|
"epoch": 0.5858782338066524,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004970956266565285,
|
|
"loss": 5.4636,
|
|
"mean_token_accuracy": 0.168794621527195,
|
|
"num_tokens": 13065289.0,
|
|
"step": 7530
|
|
},
|
|
{
|
|
"entropy": 5.677121305465699,
|
|
"epoch": 0.58626726317837,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004970911861467544,
|
|
"loss": 5.4795,
|
|
"mean_token_accuracy": 0.17004801630973815,
|
|
"num_tokens": 13073648.0,
|
|
"step": 7535
|
|
},
|
|
{
|
|
"entropy": 5.6547130107879635,
|
|
"epoch": 0.5866562925500876,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004970867422671002,
|
|
"loss": 5.4862,
|
|
"mean_token_accuracy": 0.17260521799325942,
|
|
"num_tokens": 13082205.0,
|
|
"step": 7540
|
|
},
|
|
{
|
|
"entropy": 5.654366731643677,
|
|
"epoch": 0.5870453219218051,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000497082295017633,
|
|
"loss": 5.3632,
|
|
"mean_token_accuracy": 0.169638891518116,
|
|
"num_tokens": 13090970.0,
|
|
"step": 7545
|
|
},
|
|
{
|
|
"entropy": 5.633034324645996,
|
|
"epoch": 0.5874343512935226,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004970778443984206,
|
|
"loss": 5.2772,
|
|
"mean_token_accuracy": 0.18007944971323014,
|
|
"num_tokens": 13098290.0,
|
|
"step": 7550
|
|
},
|
|
{
|
|
"entropy": 5.531872987747192,
|
|
"epoch": 0.5878233806652402,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004970733904095303,
|
|
"loss": 5.2325,
|
|
"mean_token_accuracy": 0.18482622057199477,
|
|
"num_tokens": 13106971.0,
|
|
"step": 7555
|
|
},
|
|
{
|
|
"entropy": 5.663135814666748,
|
|
"epoch": 0.5882124100369578,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004970689330510298,
|
|
"loss": 5.5028,
|
|
"mean_token_accuracy": 0.16574273109436036,
|
|
"num_tokens": 13115742.0,
|
|
"step": 7560
|
|
},
|
|
{
|
|
"entropy": 5.635857486724854,
|
|
"epoch": 0.5886014394086754,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004970644723229868,
|
|
"loss": 5.4773,
|
|
"mean_token_accuracy": 0.1727609857916832,
|
|
"num_tokens": 13124192.0,
|
|
"step": 7565
|
|
},
|
|
{
|
|
"entropy": 5.580559301376343,
|
|
"epoch": 0.588990468780393,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004970600082254687,
|
|
"loss": 5.3013,
|
|
"mean_token_accuracy": 0.17216529250144957,
|
|
"num_tokens": 13133510.0,
|
|
"step": 7570
|
|
},
|
|
{
|
|
"entropy": 5.604172897338867,
|
|
"epoch": 0.5893794981521104,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004970555407585436,
|
|
"loss": 5.4111,
|
|
"mean_token_accuracy": 0.17594430446624756,
|
|
"num_tokens": 13141704.0,
|
|
"step": 7575
|
|
},
|
|
{
|
|
"entropy": 5.523994970321655,
|
|
"epoch": 0.589768527523828,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000497051069922279,
|
|
"loss": 5.2853,
|
|
"mean_token_accuracy": 0.16935604214668273,
|
|
"num_tokens": 13150559.0,
|
|
"step": 7580
|
|
},
|
|
{
|
|
"entropy": 5.558675527572632,
|
|
"epoch": 0.5901575568955456,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004970465957167429,
|
|
"loss": 5.3639,
|
|
"mean_token_accuracy": 0.17506027966737747,
|
|
"num_tokens": 13159428.0,
|
|
"step": 7585
|
|
},
|
|
{
|
|
"entropy": 5.58739275932312,
|
|
"epoch": 0.5905465862672632,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000497042118142003,
|
|
"loss": 5.5061,
|
|
"mean_token_accuracy": 0.16214175373315812,
|
|
"num_tokens": 13168299.0,
|
|
"step": 7590
|
|
},
|
|
{
|
|
"entropy": 5.6119704246521,
|
|
"epoch": 0.5909356156389808,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004970376371981275,
|
|
"loss": 5.3608,
|
|
"mean_token_accuracy": 0.17236538380384445,
|
|
"num_tokens": 13176906.0,
|
|
"step": 7595
|
|
},
|
|
{
|
|
"entropy": 5.6741773128509525,
|
|
"epoch": 0.5913246450106983,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004970331528851842,
|
|
"loss": 5.4567,
|
|
"mean_token_accuracy": 0.16617743521928788,
|
|
"num_tokens": 13186180.0,
|
|
"step": 7600
|
|
},
|
|
{
|
|
"entropy": 5.561134624481201,
|
|
"epoch": 0.5917136743824158,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004970286652032412,
|
|
"loss": 5.2933,
|
|
"mean_token_accuracy": 0.1796172395348549,
|
|
"num_tokens": 13195111.0,
|
|
"step": 7605
|
|
},
|
|
{
|
|
"entropy": 5.601275491714477,
|
|
"epoch": 0.5921027037541334,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004970241741523667,
|
|
"loss": 5.3604,
|
|
"mean_token_accuracy": 0.17476796954870225,
|
|
"num_tokens": 13204170.0,
|
|
"step": 7610
|
|
},
|
|
{
|
|
"entropy": 5.5979756832122805,
|
|
"epoch": 0.592491733125851,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004970196797326286,
|
|
"loss": 5.364,
|
|
"mean_token_accuracy": 0.17164454609155655,
|
|
"num_tokens": 13213479.0,
|
|
"step": 7615
|
|
},
|
|
{
|
|
"entropy": 5.593438625335693,
|
|
"epoch": 0.5928807624975686,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004970151819440955,
|
|
"loss": 5.3883,
|
|
"mean_token_accuracy": 0.17189265340566634,
|
|
"num_tokens": 13222182.0,
|
|
"step": 7620
|
|
},
|
|
{
|
|
"entropy": 5.526077461242676,
|
|
"epoch": 0.5932697918692861,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004970106807868351,
|
|
"loss": 5.2641,
|
|
"mean_token_accuracy": 0.17490562349557875,
|
|
"num_tokens": 13230681.0,
|
|
"step": 7625
|
|
},
|
|
{
|
|
"entropy": 5.697098302841186,
|
|
"epoch": 0.5936588212410037,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.000497006176260916,
|
|
"loss": 5.446,
|
|
"mean_token_accuracy": 0.1732114225625992,
|
|
"num_tokens": 13239254.0,
|
|
"step": 7630
|
|
},
|
|
{
|
|
"entropy": 5.534705781936646,
|
|
"epoch": 0.5940478506127213,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004970016683664068,
|
|
"loss": 5.3178,
|
|
"mean_token_accuracy": 0.1772586613893509,
|
|
"num_tokens": 13248317.0,
|
|
"step": 7635
|
|
},
|
|
{
|
|
"entropy": 5.653423500061035,
|
|
"epoch": 0.5944368799844388,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004969971571033754,
|
|
"loss": 5.3687,
|
|
"mean_token_accuracy": 0.17507459074258805,
|
|
"num_tokens": 13256977.0,
|
|
"step": 7640
|
|
},
|
|
{
|
|
"entropy": 5.635997629165649,
|
|
"epoch": 0.5948259093561564,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004969926424718906,
|
|
"loss": 5.4371,
|
|
"mean_token_accuracy": 0.17063387334346772,
|
|
"num_tokens": 13266012.0,
|
|
"step": 7645
|
|
},
|
|
{
|
|
"entropy": 5.618613338470459,
|
|
"epoch": 0.5952149387278739,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004969881244720207,
|
|
"loss": 5.4522,
|
|
"mean_token_accuracy": 0.17322476655244828,
|
|
"num_tokens": 13275248.0,
|
|
"step": 7650
|
|
},
|
|
{
|
|
"entropy": 5.6184052467346195,
|
|
"epoch": 0.5956039680995915,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004969836031038343,
|
|
"loss": 5.3183,
|
|
"mean_token_accuracy": 0.16789155900478364,
|
|
"num_tokens": 13284235.0,
|
|
"step": 7655
|
|
},
|
|
{
|
|
"entropy": 5.635403156280518,
|
|
"epoch": 0.5959929974713091,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004969790783674002,
|
|
"loss": 5.4,
|
|
"mean_token_accuracy": 0.1698325291275978,
|
|
"num_tokens": 13292423.0,
|
|
"step": 7660
|
|
},
|
|
{
|
|
"entropy": 5.590408039093018,
|
|
"epoch": 0.5963820268430267,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004969745502627868,
|
|
"loss": 5.4235,
|
|
"mean_token_accuracy": 0.167571958899498,
|
|
"num_tokens": 13300936.0,
|
|
"step": 7665
|
|
},
|
|
{
|
|
"entropy": 5.5580121040344235,
|
|
"epoch": 0.5967710562147442,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004969700187900629,
|
|
"loss": 5.2224,
|
|
"mean_token_accuracy": 0.18108144104480745,
|
|
"num_tokens": 13308881.0,
|
|
"step": 7670
|
|
},
|
|
{
|
|
"entropy": 5.607459640502929,
|
|
"epoch": 0.5971600855864618,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004969654839492973,
|
|
"loss": 5.4123,
|
|
"mean_token_accuracy": 0.17161239981651305,
|
|
"num_tokens": 13317864.0,
|
|
"step": 7675
|
|
},
|
|
{
|
|
"entropy": 5.620231771469117,
|
|
"epoch": 0.5975491149581793,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004969609457405588,
|
|
"loss": 5.3725,
|
|
"mean_token_accuracy": 0.1709914728999138,
|
|
"num_tokens": 13326990.0,
|
|
"step": 7680
|
|
},
|
|
{
|
|
"entropy": 5.692099857330322,
|
|
"epoch": 0.5979381443298969,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004969564041639163,
|
|
"loss": 5.5486,
|
|
"mean_token_accuracy": 0.16365605890750884,
|
|
"num_tokens": 13336437.0,
|
|
"step": 7685
|
|
},
|
|
{
|
|
"entropy": 5.628011226654053,
|
|
"epoch": 0.5983271737016145,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004969518592194386,
|
|
"loss": 5.383,
|
|
"mean_token_accuracy": 0.16583366096019744,
|
|
"num_tokens": 13345368.0,
|
|
"step": 7690
|
|
},
|
|
{
|
|
"entropy": 5.559656143188477,
|
|
"epoch": 0.5987162030733321,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004969473109071946,
|
|
"loss": 5.4253,
|
|
"mean_token_accuracy": 0.1732177883386612,
|
|
"num_tokens": 13354171.0,
|
|
"step": 7695
|
|
},
|
|
{
|
|
"entropy": 5.661171102523804,
|
|
"epoch": 0.5991052324450497,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004969427592272535,
|
|
"loss": 5.4133,
|
|
"mean_token_accuracy": 0.16940583735704423,
|
|
"num_tokens": 13362912.0,
|
|
"step": 7700
|
|
},
|
|
{
|
|
"entropy": 5.636720609664917,
|
|
"epoch": 0.5994942618167671,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004969382041796843,
|
|
"loss": 5.3092,
|
|
"mean_token_accuracy": 0.17516656816005707,
|
|
"num_tokens": 13370913.0,
|
|
"step": 7705
|
|
},
|
|
{
|
|
"entropy": 5.62378077507019,
|
|
"epoch": 0.5998832911884847,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000496933645764556,
|
|
"loss": 5.4739,
|
|
"mean_token_accuracy": 0.16723166555166244,
|
|
"num_tokens": 13379557.0,
|
|
"step": 7710
|
|
},
|
|
{
|
|
"entropy": 5.5516557693481445,
|
|
"epoch": 0.6002723205602023,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004969290839819381,
|
|
"loss": 5.3666,
|
|
"mean_token_accuracy": 0.1747287005186081,
|
|
"num_tokens": 13388129.0,
|
|
"step": 7715
|
|
},
|
|
{
|
|
"entropy": 5.645891332626343,
|
|
"epoch": 0.6006613499319199,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004969245188318994,
|
|
"loss": 5.4869,
|
|
"mean_token_accuracy": 0.17049409300088883,
|
|
"num_tokens": 13396713.0,
|
|
"step": 7720
|
|
},
|
|
{
|
|
"entropy": 5.645609188079834,
|
|
"epoch": 0.6010503793036375,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004969199503145093,
|
|
"loss": 5.4195,
|
|
"mean_token_accuracy": 0.17086775004863738,
|
|
"num_tokens": 13406171.0,
|
|
"step": 7725
|
|
},
|
|
{
|
|
"entropy": 5.566971063613892,
|
|
"epoch": 0.601439408675355,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004969153784298374,
|
|
"loss": 5.3476,
|
|
"mean_token_accuracy": 0.17182642966508865,
|
|
"num_tokens": 13415107.0,
|
|
"step": 7730
|
|
},
|
|
{
|
|
"entropy": 5.60140700340271,
|
|
"epoch": 0.6018284380470725,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004969108031779527,
|
|
"loss": 5.4544,
|
|
"mean_token_accuracy": 0.1706515446305275,
|
|
"num_tokens": 13423533.0,
|
|
"step": 7735
|
|
},
|
|
{
|
|
"entropy": 5.673208951950073,
|
|
"epoch": 0.6022174674187901,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004969062245589247,
|
|
"loss": 5.4364,
|
|
"mean_token_accuracy": 0.16617097109556198,
|
|
"num_tokens": 13432798.0,
|
|
"step": 7740
|
|
},
|
|
{
|
|
"entropy": 5.657231378555298,
|
|
"epoch": 0.6026064967905077,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004969016425728231,
|
|
"loss": 5.3837,
|
|
"mean_token_accuracy": 0.17782800644636154,
|
|
"num_tokens": 13441123.0,
|
|
"step": 7745
|
|
},
|
|
{
|
|
"entropy": 5.566253709793091,
|
|
"epoch": 0.6029955261622253,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004968970572197172,
|
|
"loss": 5.304,
|
|
"mean_token_accuracy": 0.17716853320598602,
|
|
"num_tokens": 13449548.0,
|
|
"step": 7750
|
|
},
|
|
{
|
|
"entropy": 5.599495124816895,
|
|
"epoch": 0.6033845555339428,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004968924684996765,
|
|
"loss": 5.3814,
|
|
"mean_token_accuracy": 0.1734702154994011,
|
|
"num_tokens": 13458022.0,
|
|
"step": 7755
|
|
},
|
|
{
|
|
"entropy": 5.591137886047363,
|
|
"epoch": 0.6037735849056604,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.000496887876412771,
|
|
"loss": 5.352,
|
|
"mean_token_accuracy": 0.1717812716960907,
|
|
"num_tokens": 13466871.0,
|
|
"step": 7760
|
|
},
|
|
{
|
|
"entropy": 5.614107513427735,
|
|
"epoch": 0.6041626142773779,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004968832809590701,
|
|
"loss": 5.3703,
|
|
"mean_token_accuracy": 0.17414651662111283,
|
|
"num_tokens": 13475659.0,
|
|
"step": 7765
|
|
},
|
|
{
|
|
"entropy": 5.625330400466919,
|
|
"epoch": 0.6045516436490955,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004968786821386435,
|
|
"loss": 5.3962,
|
|
"mean_token_accuracy": 0.16906533837318422,
|
|
"num_tokens": 13484146.0,
|
|
"step": 7770
|
|
},
|
|
{
|
|
"entropy": 5.612520551681518,
|
|
"epoch": 0.6049406730208131,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004968740799515611,
|
|
"loss": 5.3949,
|
|
"mean_token_accuracy": 0.17522106766700746,
|
|
"num_tokens": 13492831.0,
|
|
"step": 7775
|
|
},
|
|
{
|
|
"entropy": 5.607007646560669,
|
|
"epoch": 0.6053297023925306,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004968694743978926,
|
|
"loss": 5.3678,
|
|
"mean_token_accuracy": 0.17839196920394898,
|
|
"num_tokens": 13501640.0,
|
|
"step": 7780
|
|
},
|
|
{
|
|
"entropy": 5.655982160568238,
|
|
"epoch": 0.6057187317642482,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004968648654777081,
|
|
"loss": 5.3845,
|
|
"mean_token_accuracy": 0.1761223405599594,
|
|
"num_tokens": 13509816.0,
|
|
"step": 7785
|
|
},
|
|
{
|
|
"entropy": 5.650158643722534,
|
|
"epoch": 0.6061077611359658,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004968602531910773,
|
|
"loss": 5.4491,
|
|
"mean_token_accuracy": 0.17165745943784713,
|
|
"num_tokens": 13518384.0,
|
|
"step": 7790
|
|
},
|
|
{
|
|
"entropy": 5.587653398513794,
|
|
"epoch": 0.6064967905076833,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004968556375380704,
|
|
"loss": 5.3126,
|
|
"mean_token_accuracy": 0.17027076035737992,
|
|
"num_tokens": 13527115.0,
|
|
"step": 7795
|
|
},
|
|
{
|
|
"entropy": 5.6321692943573,
|
|
"epoch": 0.6068858198794009,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004968510185187571,
|
|
"loss": 5.5346,
|
|
"mean_token_accuracy": 0.16949589401483536,
|
|
"num_tokens": 13535743.0,
|
|
"step": 7800
|
|
},
|
|
{
|
|
"entropy": 5.591909599304199,
|
|
"epoch": 0.6072748492511184,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000496846396133208,
|
|
"loss": 5.3394,
|
|
"mean_token_accuracy": 0.1780050903558731,
|
|
"num_tokens": 13544167.0,
|
|
"step": 7805
|
|
},
|
|
{
|
|
"entropy": 5.585002040863037,
|
|
"epoch": 0.607663878622836,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004968417703814928,
|
|
"loss": 5.4004,
|
|
"mean_token_accuracy": 0.1679321452975273,
|
|
"num_tokens": 13552291.0,
|
|
"step": 7810
|
|
},
|
|
{
|
|
"entropy": 5.6585938930511475,
|
|
"epoch": 0.6080529079945536,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004968371412636818,
|
|
"loss": 5.4355,
|
|
"mean_token_accuracy": 0.17032116800546646,
|
|
"num_tokens": 13561185.0,
|
|
"step": 7815
|
|
},
|
|
{
|
|
"entropy": 5.682382202148437,
|
|
"epoch": 0.6084419373662712,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004968325087798453,
|
|
"loss": 5.3238,
|
|
"mean_token_accuracy": 0.18022632747888565,
|
|
"num_tokens": 13569815.0,
|
|
"step": 7820
|
|
},
|
|
{
|
|
"entropy": 5.588699150085449,
|
|
"epoch": 0.6088309667379888,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004968278729300536,
|
|
"loss": 5.4331,
|
|
"mean_token_accuracy": 0.16961714923381804,
|
|
"num_tokens": 13578882.0,
|
|
"step": 7825
|
|
},
|
|
{
|
|
"entropy": 5.57780966758728,
|
|
"epoch": 0.6092199961097062,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004968232337143769,
|
|
"loss": 5.3144,
|
|
"mean_token_accuracy": 0.17948854118585586,
|
|
"num_tokens": 13587479.0,
|
|
"step": 7830
|
|
},
|
|
{
|
|
"entropy": 5.515082788467407,
|
|
"epoch": 0.6096090254814238,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004968185911328858,
|
|
"loss": 5.2152,
|
|
"mean_token_accuracy": 0.17272976338863372,
|
|
"num_tokens": 13596049.0,
|
|
"step": 7835
|
|
},
|
|
{
|
|
"entropy": 5.643992233276367,
|
|
"epoch": 0.6099980548531414,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004968139451856506,
|
|
"loss": 5.4925,
|
|
"mean_token_accuracy": 0.1680475354194641,
|
|
"num_tokens": 13604766.0,
|
|
"step": 7840
|
|
},
|
|
{
|
|
"entropy": 5.6659993648529055,
|
|
"epoch": 0.610387084224859,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004968092958727419,
|
|
"loss": 5.4614,
|
|
"mean_token_accuracy": 0.1690959021449089,
|
|
"num_tokens": 13614051.0,
|
|
"step": 7845
|
|
},
|
|
{
|
|
"entropy": 5.634029293060303,
|
|
"epoch": 0.6107761135965766,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00049680464319423,
|
|
"loss": 5.4037,
|
|
"mean_token_accuracy": 0.17126537561416627,
|
|
"num_tokens": 13623100.0,
|
|
"step": 7850
|
|
},
|
|
{
|
|
"entropy": 5.656065464019775,
|
|
"epoch": 0.6111651429682942,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004967999871501858,
|
|
"loss": 5.4086,
|
|
"mean_token_accuracy": 0.17563506215810776,
|
|
"num_tokens": 13631732.0,
|
|
"step": 7855
|
|
},
|
|
{
|
|
"entropy": 5.617393684387207,
|
|
"epoch": 0.6115541723400116,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004967953277406798,
|
|
"loss": 5.3901,
|
|
"mean_token_accuracy": 0.1730097770690918,
|
|
"num_tokens": 13640355.0,
|
|
"step": 7860
|
|
},
|
|
{
|
|
"entropy": 5.635977268218994,
|
|
"epoch": 0.6119432017117292,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004967906649657828,
|
|
"loss": 5.4603,
|
|
"mean_token_accuracy": 0.1736888751387596,
|
|
"num_tokens": 13649108.0,
|
|
"step": 7865
|
|
},
|
|
{
|
|
"entropy": 5.610578441619873,
|
|
"epoch": 0.6123322310834468,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004967859988255655,
|
|
"loss": 5.3027,
|
|
"mean_token_accuracy": 0.1875598818063736,
|
|
"num_tokens": 13656765.0,
|
|
"step": 7870
|
|
},
|
|
{
|
|
"entropy": 5.5898693084716795,
|
|
"epoch": 0.6127212604551644,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004967813293200985,
|
|
"loss": 5.3808,
|
|
"mean_token_accuracy": 0.17080039381980897,
|
|
"num_tokens": 13664692.0,
|
|
"step": 7875
|
|
},
|
|
{
|
|
"entropy": 5.491356992721558,
|
|
"epoch": 0.613110289826882,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004967766564494529,
|
|
"loss": 5.2597,
|
|
"mean_token_accuracy": 0.17703975439071656,
|
|
"num_tokens": 13672913.0,
|
|
"step": 7880
|
|
},
|
|
{
|
|
"entropy": 5.547981834411621,
|
|
"epoch": 0.6134993191985995,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004967719802136996,
|
|
"loss": 5.2479,
|
|
"mean_token_accuracy": 0.1814624547958374,
|
|
"num_tokens": 13682427.0,
|
|
"step": 7885
|
|
},
|
|
{
|
|
"entropy": 5.589805030822754,
|
|
"epoch": 0.613888348570317,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004967673006129094,
|
|
"loss": 5.352,
|
|
"mean_token_accuracy": 0.17558028995990754,
|
|
"num_tokens": 13690815.0,
|
|
"step": 7890
|
|
},
|
|
{
|
|
"entropy": 5.6545045375823975,
|
|
"epoch": 0.6142773779420346,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004967626176471536,
|
|
"loss": 5.4793,
|
|
"mean_token_accuracy": 0.16500618010759355,
|
|
"num_tokens": 13699522.0,
|
|
"step": 7895
|
|
},
|
|
{
|
|
"entropy": 5.731170749664306,
|
|
"epoch": 0.6146664073137522,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004967579313165028,
|
|
"loss": 5.4809,
|
|
"mean_token_accuracy": 0.16668136566877365,
|
|
"num_tokens": 13708075.0,
|
|
"step": 7900
|
|
},
|
|
{
|
|
"entropy": 5.629131746292114,
|
|
"epoch": 0.6150554366854698,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004967532416210284,
|
|
"loss": 5.3669,
|
|
"mean_token_accuracy": 0.17131840139627458,
|
|
"num_tokens": 13716397.0,
|
|
"step": 7905
|
|
},
|
|
{
|
|
"entropy": 5.569436693191529,
|
|
"epoch": 0.6154444660571873,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004967485485608016,
|
|
"loss": 5.3618,
|
|
"mean_token_accuracy": 0.17754382640123367,
|
|
"num_tokens": 13724724.0,
|
|
"step": 7910
|
|
},
|
|
{
|
|
"entropy": 5.581193113327027,
|
|
"epoch": 0.6158334954289049,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004967438521358934,
|
|
"loss": 5.3233,
|
|
"mean_token_accuracy": 0.183150814473629,
|
|
"num_tokens": 13733389.0,
|
|
"step": 7915
|
|
},
|
|
{
|
|
"entropy": 5.581504392623901,
|
|
"epoch": 0.6162225248006225,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004967391523463754,
|
|
"loss": 5.2795,
|
|
"mean_token_accuracy": 0.17858623266220092,
|
|
"num_tokens": 13742569.0,
|
|
"step": 7920
|
|
},
|
|
{
|
|
"entropy": 5.526614665985107,
|
|
"epoch": 0.61661155417234,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004967344491923185,
|
|
"loss": 5.272,
|
|
"mean_token_accuracy": 0.17839372754096985,
|
|
"num_tokens": 13750975.0,
|
|
"step": 7925
|
|
},
|
|
{
|
|
"entropy": 5.558490228652954,
|
|
"epoch": 0.6170005835440576,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004967297426737943,
|
|
"loss": 5.3336,
|
|
"mean_token_accuracy": 0.18053995072841644,
|
|
"num_tokens": 13758782.0,
|
|
"step": 7930
|
|
},
|
|
{
|
|
"entropy": 5.655747127532959,
|
|
"epoch": 0.6173896129157751,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004967250327908742,
|
|
"loss": 5.4636,
|
|
"mean_token_accuracy": 0.16564081460237504,
|
|
"num_tokens": 13767321.0,
|
|
"step": 7935
|
|
},
|
|
{
|
|
"entropy": 5.6967109680175785,
|
|
"epoch": 0.6177786422874927,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004967203195436297,
|
|
"loss": 5.4465,
|
|
"mean_token_accuracy": 0.1746225267648697,
|
|
"num_tokens": 13775992.0,
|
|
"step": 7940
|
|
},
|
|
{
|
|
"entropy": 5.58898811340332,
|
|
"epoch": 0.6181676716592103,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004967156029321322,
|
|
"loss": 5.2813,
|
|
"mean_token_accuracy": 0.18081785142421722,
|
|
"num_tokens": 13784358.0,
|
|
"step": 7945
|
|
},
|
|
{
|
|
"entropy": 5.495432949066162,
|
|
"epoch": 0.6185567010309279,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004967108829564532,
|
|
"loss": 5.2837,
|
|
"mean_token_accuracy": 0.18145979791879654,
|
|
"num_tokens": 13792834.0,
|
|
"step": 7950
|
|
},
|
|
{
|
|
"entropy": 5.627613973617554,
|
|
"epoch": 0.6189457304026454,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004967061596166646,
|
|
"loss": 5.3854,
|
|
"mean_token_accuracy": 0.17125617116689681,
|
|
"num_tokens": 13801414.0,
|
|
"step": 7955
|
|
},
|
|
{
|
|
"entropy": 5.628814077377319,
|
|
"epoch": 0.6193347597743629,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004967014329128378,
|
|
"loss": 5.4099,
|
|
"mean_token_accuracy": 0.17231540232896805,
|
|
"num_tokens": 13810459.0,
|
|
"step": 7960
|
|
},
|
|
{
|
|
"entropy": 5.581355810165405,
|
|
"epoch": 0.6197237891460805,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004966967028450448,
|
|
"loss": 5.2502,
|
|
"mean_token_accuracy": 0.17979186326265334,
|
|
"num_tokens": 13818460.0,
|
|
"step": 7965
|
|
},
|
|
{
|
|
"entropy": 5.602181911468506,
|
|
"epoch": 0.6201128185177981,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000496691969413357,
|
|
"loss": 5.3718,
|
|
"mean_token_accuracy": 0.17108058035373688,
|
|
"num_tokens": 13827693.0,
|
|
"step": 7970
|
|
},
|
|
{
|
|
"entropy": 5.610408926010132,
|
|
"epoch": 0.6205018478895157,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004966872326178466,
|
|
"loss": 5.3649,
|
|
"mean_token_accuracy": 0.1674000144004822,
|
|
"num_tokens": 13836506.0,
|
|
"step": 7975
|
|
},
|
|
{
|
|
"entropy": 5.558001708984375,
|
|
"epoch": 0.6208908772612333,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004966824924585851,
|
|
"loss": 5.4006,
|
|
"mean_token_accuracy": 0.17037640810012816,
|
|
"num_tokens": 13844977.0,
|
|
"step": 7980
|
|
},
|
|
{
|
|
"entropy": 5.588616037368775,
|
|
"epoch": 0.6212799066329507,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004966777489356448,
|
|
"loss": 5.3664,
|
|
"mean_token_accuracy": 0.17286057770252228,
|
|
"num_tokens": 13854514.0,
|
|
"step": 7985
|
|
},
|
|
{
|
|
"entropy": 5.607264375686645,
|
|
"epoch": 0.6216689360046683,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004966730020490975,
|
|
"loss": 5.3567,
|
|
"mean_token_accuracy": 0.17180452793836593,
|
|
"num_tokens": 13863037.0,
|
|
"step": 7990
|
|
},
|
|
{
|
|
"entropy": 5.52875657081604,
|
|
"epoch": 0.6220579653763859,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000496668251799015,
|
|
"loss": 5.3316,
|
|
"mean_token_accuracy": 0.18510827124118806,
|
|
"num_tokens": 13871720.0,
|
|
"step": 7995
|
|
},
|
|
{
|
|
"entropy": 5.5923436164855955,
|
|
"epoch": 0.6224469947481035,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004966634981854699,
|
|
"loss": 5.3831,
|
|
"mean_token_accuracy": 0.1798848181962967,
|
|
"num_tokens": 13880214.0,
|
|
"step": 8000
|
|
},
|
|
{
|
|
"entropy": 5.608328056335449,
|
|
"epoch": 0.6228360241198211,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004966587412085339,
|
|
"loss": 5.4798,
|
|
"mean_token_accuracy": 0.16268185526132584,
|
|
"num_tokens": 13888784.0,
|
|
"step": 8005
|
|
},
|
|
{
|
|
"entropy": 5.62626895904541,
|
|
"epoch": 0.6232250534915386,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004966539808682793,
|
|
"loss": 5.3488,
|
|
"mean_token_accuracy": 0.17655370533466339,
|
|
"num_tokens": 13897466.0,
|
|
"step": 8010
|
|
},
|
|
{
|
|
"entropy": 5.555896949768067,
|
|
"epoch": 0.6236140828632561,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004966492171647783,
|
|
"loss": 5.3722,
|
|
"mean_token_accuracy": 0.1709124967455864,
|
|
"num_tokens": 13906556.0,
|
|
"step": 8015
|
|
},
|
|
{
|
|
"entropy": 5.5468177318573,
|
|
"epoch": 0.6240031122349737,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004966444500981032,
|
|
"loss": 5.316,
|
|
"mean_token_accuracy": 0.17478737235069275,
|
|
"num_tokens": 13915473.0,
|
|
"step": 8020
|
|
},
|
|
{
|
|
"entropy": 5.603696870803833,
|
|
"epoch": 0.6243921416066913,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004966396796683265,
|
|
"loss": 5.4901,
|
|
"mean_token_accuracy": 0.16448316276073455,
|
|
"num_tokens": 13924775.0,
|
|
"step": 8025
|
|
},
|
|
{
|
|
"entropy": 5.635816383361816,
|
|
"epoch": 0.6247811709784089,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004966349058755204,
|
|
"loss": 5.3678,
|
|
"mean_token_accuracy": 0.16653134822845458,
|
|
"num_tokens": 13933992.0,
|
|
"step": 8030
|
|
},
|
|
{
|
|
"entropy": 5.6757204055786135,
|
|
"epoch": 0.6251702003501264,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004966301287197573,
|
|
"loss": 5.4984,
|
|
"mean_token_accuracy": 0.17714831978082657,
|
|
"num_tokens": 13942877.0,
|
|
"step": 8035
|
|
},
|
|
{
|
|
"entropy": 5.570053243637085,
|
|
"epoch": 0.625559229721844,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004966253482011098,
|
|
"loss": 5.3822,
|
|
"mean_token_accuracy": 0.17082124948501587,
|
|
"num_tokens": 13952003.0,
|
|
"step": 8040
|
|
},
|
|
{
|
|
"entropy": 5.638340044021606,
|
|
"epoch": 0.6259482590935616,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004966205643196503,
|
|
"loss": 5.3317,
|
|
"mean_token_accuracy": 0.1808565765619278,
|
|
"num_tokens": 13959801.0,
|
|
"step": 8045
|
|
},
|
|
{
|
|
"entropy": 5.574903726577759,
|
|
"epoch": 0.6263372884652791,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004966157770754516,
|
|
"loss": 5.3307,
|
|
"mean_token_accuracy": 0.16821729838848115,
|
|
"num_tokens": 13968535.0,
|
|
"step": 8050
|
|
},
|
|
{
|
|
"entropy": 5.579510879516602,
|
|
"epoch": 0.6267263178369967,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000496610986468586,
|
|
"loss": 5.3052,
|
|
"mean_token_accuracy": 0.1752540349960327,
|
|
"num_tokens": 13977079.0,
|
|
"step": 8055
|
|
},
|
|
{
|
|
"entropy": 5.544235515594482,
|
|
"epoch": 0.6271153472087143,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004966061924991267,
|
|
"loss": 5.313,
|
|
"mean_token_accuracy": 0.1814327582716942,
|
|
"num_tokens": 13985118.0,
|
|
"step": 8060
|
|
},
|
|
{
|
|
"entropy": 5.574939870834351,
|
|
"epoch": 0.6275043765804318,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000496601395167146,
|
|
"loss": 5.2674,
|
|
"mean_token_accuracy": 0.175836481153965,
|
|
"num_tokens": 13994061.0,
|
|
"step": 8065
|
|
},
|
|
{
|
|
"entropy": 5.588698101043701,
|
|
"epoch": 0.6278934059521494,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004965965944727168,
|
|
"loss": 5.4225,
|
|
"mean_token_accuracy": 0.16943728923797607,
|
|
"num_tokens": 14002879.0,
|
|
"step": 8070
|
|
},
|
|
{
|
|
"entropy": 5.6054764747619625,
|
|
"epoch": 0.628282435323867,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004965917904159121,
|
|
"loss": 5.3928,
|
|
"mean_token_accuracy": 0.17182569801807404,
|
|
"num_tokens": 14011570.0,
|
|
"step": 8075
|
|
},
|
|
{
|
|
"entropy": 5.540693473815918,
|
|
"epoch": 0.6286714646955845,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004965869829968046,
|
|
"loss": 5.2401,
|
|
"mean_token_accuracy": 0.17718469053506852,
|
|
"num_tokens": 14019282.0,
|
|
"step": 8080
|
|
},
|
|
{
|
|
"entropy": 5.535258197784424,
|
|
"epoch": 0.6290604940673021,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004965821722154674,
|
|
"loss": 5.2634,
|
|
"mean_token_accuracy": 0.18298577517271042,
|
|
"num_tokens": 14027774.0,
|
|
"step": 8085
|
|
},
|
|
{
|
|
"entropy": 5.539744234085083,
|
|
"epoch": 0.6294495234390196,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004965773580719734,
|
|
"loss": 5.2434,
|
|
"mean_token_accuracy": 0.17935188710689545,
|
|
"num_tokens": 14036754.0,
|
|
"step": 8090
|
|
},
|
|
{
|
|
"entropy": 5.625921058654785,
|
|
"epoch": 0.6298385528107372,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004965725405663957,
|
|
"loss": 5.4197,
|
|
"mean_token_accuracy": 0.17523077130317688,
|
|
"num_tokens": 14045714.0,
|
|
"step": 8095
|
|
},
|
|
{
|
|
"entropy": 5.662188243865967,
|
|
"epoch": 0.6302275821824548,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004965677196988073,
|
|
"loss": 5.4539,
|
|
"mean_token_accuracy": 0.16636739373207093,
|
|
"num_tokens": 14054973.0,
|
|
"step": 8100
|
|
},
|
|
{
|
|
"entropy": 5.639545726776123,
|
|
"epoch": 0.6306166115541724,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004965628954692815,
|
|
"loss": 5.3587,
|
|
"mean_token_accuracy": 0.1728656142950058,
|
|
"num_tokens": 14064037.0,
|
|
"step": 8105
|
|
},
|
|
{
|
|
"entropy": 5.64419846534729,
|
|
"epoch": 0.63100564092589,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004965580678778913,
|
|
"loss": 5.3895,
|
|
"mean_token_accuracy": 0.17385393232107163,
|
|
"num_tokens": 14072269.0,
|
|
"step": 8110
|
|
},
|
|
{
|
|
"entropy": 5.581698369979859,
|
|
"epoch": 0.6313946702976074,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004965532369247102,
|
|
"loss": 5.34,
|
|
"mean_token_accuracy": 0.17125858664512633,
|
|
"num_tokens": 14080595.0,
|
|
"step": 8115
|
|
},
|
|
{
|
|
"entropy": 5.579161024093628,
|
|
"epoch": 0.631783699669325,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004965484026098111,
|
|
"loss": 5.3099,
|
|
"mean_token_accuracy": 0.17416503578424453,
|
|
"num_tokens": 14089159.0,
|
|
"step": 8120
|
|
},
|
|
{
|
|
"entropy": 5.63450517654419,
|
|
"epoch": 0.6321727290410426,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004965435649332679,
|
|
"loss": 5.4103,
|
|
"mean_token_accuracy": 0.17195792496204376,
|
|
"num_tokens": 14098192.0,
|
|
"step": 8125
|
|
},
|
|
{
|
|
"entropy": 5.590230131149292,
|
|
"epoch": 0.6325617584127602,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004965387238951536,
|
|
"loss": 5.2306,
|
|
"mean_token_accuracy": 0.1833092600107193,
|
|
"num_tokens": 14106552.0,
|
|
"step": 8130
|
|
},
|
|
{
|
|
"entropy": 5.554232931137085,
|
|
"epoch": 0.6329507877844778,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004965338794955418,
|
|
"loss": 5.2961,
|
|
"mean_token_accuracy": 0.17610278874635696,
|
|
"num_tokens": 14114783.0,
|
|
"step": 8135
|
|
},
|
|
{
|
|
"entropy": 5.547451019287109,
|
|
"epoch": 0.6333398171561953,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004965290317345061,
|
|
"loss": 5.3602,
|
|
"mean_token_accuracy": 0.16638550609350206,
|
|
"num_tokens": 14124182.0,
|
|
"step": 8140
|
|
},
|
|
{
|
|
"entropy": 5.656743097305298,
|
|
"epoch": 0.6337288465279128,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004965241806121198,
|
|
"loss": 5.3824,
|
|
"mean_token_accuracy": 0.16936965882778168,
|
|
"num_tokens": 14133037.0,
|
|
"step": 8145
|
|
},
|
|
{
|
|
"entropy": 5.612976551055908,
|
|
"epoch": 0.6341178758996304,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004965193261284567,
|
|
"loss": 5.364,
|
|
"mean_token_accuracy": 0.17326362580060958,
|
|
"num_tokens": 14141677.0,
|
|
"step": 8150
|
|
},
|
|
{
|
|
"entropy": 5.518466806411743,
|
|
"epoch": 0.634506905271348,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004965144682835904,
|
|
"loss": 5.3133,
|
|
"mean_token_accuracy": 0.17942651063203813,
|
|
"num_tokens": 14149980.0,
|
|
"step": 8155
|
|
},
|
|
{
|
|
"entropy": 5.577079343795776,
|
|
"epoch": 0.6348959346430656,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004965096070775946,
|
|
"loss": 5.3674,
|
|
"mean_token_accuracy": 0.18032984137535096,
|
|
"num_tokens": 14158298.0,
|
|
"step": 8160
|
|
},
|
|
{
|
|
"entropy": 5.589863634109497,
|
|
"epoch": 0.6352849640147831,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004965047425105431,
|
|
"loss": 5.3223,
|
|
"mean_token_accuracy": 0.18497874438762665,
|
|
"num_tokens": 14166321.0,
|
|
"step": 8165
|
|
},
|
|
{
|
|
"entropy": 5.48642930984497,
|
|
"epoch": 0.6356739933865007,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004964998745825097,
|
|
"loss": 5.3027,
|
|
"mean_token_accuracy": 0.18269782811403273,
|
|
"num_tokens": 14174619.0,
|
|
"step": 8170
|
|
},
|
|
{
|
|
"entropy": 5.537335062026978,
|
|
"epoch": 0.6360630227582182,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004964950032935682,
|
|
"loss": 5.2955,
|
|
"mean_token_accuracy": 0.17796382308006287,
|
|
"num_tokens": 14183548.0,
|
|
"step": 8175
|
|
},
|
|
{
|
|
"entropy": 5.7116475105285645,
|
|
"epoch": 0.6364520521299358,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004964901286437927,
|
|
"loss": 5.494,
|
|
"mean_token_accuracy": 0.17413605600595475,
|
|
"num_tokens": 14192306.0,
|
|
"step": 8180
|
|
},
|
|
{
|
|
"entropy": 5.5339843273162845,
|
|
"epoch": 0.6368410815016534,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004964852506332568,
|
|
"loss": 5.1908,
|
|
"mean_token_accuracy": 0.18867799490690232,
|
|
"num_tokens": 14200280.0,
|
|
"step": 8185
|
|
},
|
|
{
|
|
"entropy": 5.540139293670654,
|
|
"epoch": 0.6372301108733709,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000496480369262035,
|
|
"loss": 5.4294,
|
|
"mean_token_accuracy": 0.1720765322446823,
|
|
"num_tokens": 14208484.0,
|
|
"step": 8190
|
|
},
|
|
{
|
|
"entropy": 5.579662942886353,
|
|
"epoch": 0.6376191402450885,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000496475484530201,
|
|
"loss": 5.4106,
|
|
"mean_token_accuracy": 0.17133046686649323,
|
|
"num_tokens": 14217368.0,
|
|
"step": 8195
|
|
},
|
|
{
|
|
"entropy": 5.689886903762817,
|
|
"epoch": 0.6380081696168061,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004964705964378292,
|
|
"loss": 5.438,
|
|
"mean_token_accuracy": 0.166541887819767,
|
|
"num_tokens": 14226663.0,
|
|
"step": 8200
|
|
},
|
|
{
|
|
"entropy": 5.6033202648162845,
|
|
"epoch": 0.6383971989885237,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004964657049849934,
|
|
"loss": 5.2964,
|
|
"mean_token_accuracy": 0.17614648044109343,
|
|
"num_tokens": 14235153.0,
|
|
"step": 8205
|
|
},
|
|
{
|
|
"entropy": 5.556395196914673,
|
|
"epoch": 0.6387862283602412,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004964608101717681,
|
|
"loss": 5.4151,
|
|
"mean_token_accuracy": 0.1731547698378563,
|
|
"num_tokens": 14244245.0,
|
|
"step": 8210
|
|
},
|
|
{
|
|
"entropy": 5.605984258651733,
|
|
"epoch": 0.6391752577319587,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004964559119982275,
|
|
"loss": 5.3254,
|
|
"mean_token_accuracy": 0.17295570224523543,
|
|
"num_tokens": 14252666.0,
|
|
"step": 8215
|
|
},
|
|
{
|
|
"entropy": 5.631249046325683,
|
|
"epoch": 0.6395642871036763,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000496451010464446,
|
|
"loss": 5.4016,
|
|
"mean_token_accuracy": 0.17393245548009872,
|
|
"num_tokens": 14262232.0,
|
|
"step": 8220
|
|
},
|
|
{
|
|
"entropy": 5.62627592086792,
|
|
"epoch": 0.6399533164753939,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004964461055704978,
|
|
"loss": 5.3398,
|
|
"mean_token_accuracy": 0.17456934452056885,
|
|
"num_tokens": 14270496.0,
|
|
"step": 8225
|
|
},
|
|
{
|
|
"entropy": 5.5464574813842775,
|
|
"epoch": 0.6403423458471115,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004964411973164574,
|
|
"loss": 5.2623,
|
|
"mean_token_accuracy": 0.18351061046123504,
|
|
"num_tokens": 14278597.0,
|
|
"step": 8230
|
|
},
|
|
{
|
|
"entropy": 5.544543647766114,
|
|
"epoch": 0.6407313752188291,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004964362857023993,
|
|
"loss": 5.3248,
|
|
"mean_token_accuracy": 0.17445123195648193,
|
|
"num_tokens": 14287444.0,
|
|
"step": 8235
|
|
},
|
|
{
|
|
"entropy": 5.535120153427124,
|
|
"epoch": 0.6411204045905465,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000496431370728398,
|
|
"loss": 5.2631,
|
|
"mean_token_accuracy": 0.17866938263177873,
|
|
"num_tokens": 14296041.0,
|
|
"step": 8240
|
|
},
|
|
{
|
|
"entropy": 5.575885438919068,
|
|
"epoch": 0.6415094339622641,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004964264523945281,
|
|
"loss": 5.2654,
|
|
"mean_token_accuracy": 0.17801269739866257,
|
|
"num_tokens": 14304700.0,
|
|
"step": 8245
|
|
},
|
|
{
|
|
"entropy": 5.615669870376587,
|
|
"epoch": 0.6418984633339817,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004964215307008643,
|
|
"loss": 5.3976,
|
|
"mean_token_accuracy": 0.17064619660377503,
|
|
"num_tokens": 14312873.0,
|
|
"step": 8250
|
|
},
|
|
{
|
|
"entropy": 5.623337507247925,
|
|
"epoch": 0.6422874927056993,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004964166056474811,
|
|
"loss": 5.3849,
|
|
"mean_token_accuracy": 0.1692052811384201,
|
|
"num_tokens": 14321697.0,
|
|
"step": 8255
|
|
},
|
|
{
|
|
"entropy": 5.58499116897583,
|
|
"epoch": 0.6426765220774169,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004964116772344534,
|
|
"loss": 5.3774,
|
|
"mean_token_accuracy": 0.16862674802541733,
|
|
"num_tokens": 14330074.0,
|
|
"step": 8260
|
|
},
|
|
{
|
|
"entropy": 5.659800958633423,
|
|
"epoch": 0.6430655514491345,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004964067454618559,
|
|
"loss": 5.4435,
|
|
"mean_token_accuracy": 0.16576170325279235,
|
|
"num_tokens": 14339485.0,
|
|
"step": 8265
|
|
},
|
|
{
|
|
"entropy": 5.680325651168824,
|
|
"epoch": 0.6434545808208519,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004964018103297634,
|
|
"loss": 5.4143,
|
|
"mean_token_accuracy": 0.1698738992214203,
|
|
"num_tokens": 14348182.0,
|
|
"step": 8270
|
|
},
|
|
{
|
|
"entropy": 5.692117309570312,
|
|
"epoch": 0.6438436101925695,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004963968718382509,
|
|
"loss": 5.4582,
|
|
"mean_token_accuracy": 0.1681407019495964,
|
|
"num_tokens": 14357202.0,
|
|
"step": 8275
|
|
},
|
|
{
|
|
"entropy": 5.604986333847046,
|
|
"epoch": 0.6442326395642871,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004963919299873931,
|
|
"loss": 5.3812,
|
|
"mean_token_accuracy": 0.1657526060938835,
|
|
"num_tokens": 14366001.0,
|
|
"step": 8280
|
|
},
|
|
{
|
|
"entropy": 5.664509963989258,
|
|
"epoch": 0.6446216689360047,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004963869847772653,
|
|
"loss": 5.4065,
|
|
"mean_token_accuracy": 0.16915652602910997,
|
|
"num_tokens": 14374894.0,
|
|
"step": 8285
|
|
},
|
|
{
|
|
"entropy": 5.562790155410767,
|
|
"epoch": 0.6450106983077223,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004963820362079423,
|
|
"loss": 5.3809,
|
|
"mean_token_accuracy": 0.17515988796949386,
|
|
"num_tokens": 14383396.0,
|
|
"step": 8290
|
|
},
|
|
{
|
|
"entropy": 5.58872127532959,
|
|
"epoch": 0.6453997276794398,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004963770842794994,
|
|
"loss": 5.2961,
|
|
"mean_token_accuracy": 0.18302446156740187,
|
|
"num_tokens": 14392514.0,
|
|
"step": 8295
|
|
},
|
|
{
|
|
"entropy": 5.607506370544433,
|
|
"epoch": 0.6457887570511573,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004963721289920115,
|
|
"loss": 5.3395,
|
|
"mean_token_accuracy": 0.1733679324388504,
|
|
"num_tokens": 14401916.0,
|
|
"step": 8300
|
|
},
|
|
{
|
|
"entropy": 5.592385196685791,
|
|
"epoch": 0.6461777864228749,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004963671703455538,
|
|
"loss": 5.406,
|
|
"mean_token_accuracy": 0.17042556703090667,
|
|
"num_tokens": 14410476.0,
|
|
"step": 8305
|
|
},
|
|
{
|
|
"entropy": 5.610119152069092,
|
|
"epoch": 0.6465668157945925,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004963622083402018,
|
|
"loss": 5.3981,
|
|
"mean_token_accuracy": 0.17096285223960878,
|
|
"num_tokens": 14418437.0,
|
|
"step": 8310
|
|
},
|
|
{
|
|
"entropy": 5.557107162475586,
|
|
"epoch": 0.6469558451663101,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004963572429760305,
|
|
"loss": 5.3384,
|
|
"mean_token_accuracy": 0.17626968324184417,
|
|
"num_tokens": 14426978.0,
|
|
"step": 8315
|
|
},
|
|
{
|
|
"entropy": 5.637966680526733,
|
|
"epoch": 0.6473448745380276,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004963522742531155,
|
|
"loss": 5.3646,
|
|
"mean_token_accuracy": 0.17541678845882416,
|
|
"num_tokens": 14435043.0,
|
|
"step": 8320
|
|
},
|
|
{
|
|
"entropy": 5.583234119415283,
|
|
"epoch": 0.6477339039097452,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000496347302171532,
|
|
"loss": 5.2759,
|
|
"mean_token_accuracy": 0.18421368151903153,
|
|
"num_tokens": 14443397.0,
|
|
"step": 8325
|
|
},
|
|
{
|
|
"entropy": 5.574254941940308,
|
|
"epoch": 0.6481229332814628,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004963423267313554,
|
|
"loss": 5.3712,
|
|
"mean_token_accuracy": 0.17410993427038193,
|
|
"num_tokens": 14452536.0,
|
|
"step": 8330
|
|
},
|
|
{
|
|
"entropy": 5.595439624786377,
|
|
"epoch": 0.6485119626531803,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004963373479326614,
|
|
"loss": 5.4407,
|
|
"mean_token_accuracy": 0.16464628130197526,
|
|
"num_tokens": 14461901.0,
|
|
"step": 8335
|
|
},
|
|
{
|
|
"entropy": 5.591050386428833,
|
|
"epoch": 0.6489009920248979,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004963323657755255,
|
|
"loss": 5.3376,
|
|
"mean_token_accuracy": 0.17729219943284988,
|
|
"num_tokens": 14470547.0,
|
|
"step": 8340
|
|
},
|
|
{
|
|
"entropy": 5.528455781936645,
|
|
"epoch": 0.6492900213966154,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004963273802600231,
|
|
"loss": 5.2297,
|
|
"mean_token_accuracy": 0.17649297267198563,
|
|
"num_tokens": 14478439.0,
|
|
"step": 8345
|
|
},
|
|
{
|
|
"entropy": 5.617388200759888,
|
|
"epoch": 0.649679050768333,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00049632239138623,
|
|
"loss": 5.2801,
|
|
"mean_token_accuracy": 0.18349619209766388,
|
|
"num_tokens": 14486621.0,
|
|
"step": 8350
|
|
},
|
|
{
|
|
"entropy": 5.562037467956543,
|
|
"epoch": 0.6500680801400506,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004963173991542219,
|
|
"loss": 5.2874,
|
|
"mean_token_accuracy": 0.17734003514051438,
|
|
"num_tokens": 14495313.0,
|
|
"step": 8355
|
|
},
|
|
{
|
|
"entropy": 5.617541790008545,
|
|
"epoch": 0.6504571095117682,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004963124035640746,
|
|
"loss": 5.3475,
|
|
"mean_token_accuracy": 0.1766296923160553,
|
|
"num_tokens": 14503647.0,
|
|
"step": 8360
|
|
},
|
|
{
|
|
"entropy": 5.613102531433105,
|
|
"epoch": 0.6508461388834857,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004963074046158637,
|
|
"loss": 5.2805,
|
|
"mean_token_accuracy": 0.1789421707391739,
|
|
"num_tokens": 14512350.0,
|
|
"step": 8365
|
|
},
|
|
{
|
|
"entropy": 5.6533385753631595,
|
|
"epoch": 0.6512351682552032,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004963024023096652,
|
|
"loss": 5.4291,
|
|
"mean_token_accuracy": 0.1655445083975792,
|
|
"num_tokens": 14521801.0,
|
|
"step": 8370
|
|
},
|
|
{
|
|
"entropy": 5.554292678833008,
|
|
"epoch": 0.6516241976269208,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004962973966455551,
|
|
"loss": 5.259,
|
|
"mean_token_accuracy": 0.1753644213080406,
|
|
"num_tokens": 14530045.0,
|
|
"step": 8375
|
|
},
|
|
{
|
|
"entropy": 5.60089373588562,
|
|
"epoch": 0.6520132269986384,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004962923876236092,
|
|
"loss": 5.3808,
|
|
"mean_token_accuracy": 0.1721917897462845,
|
|
"num_tokens": 14538944.0,
|
|
"step": 8380
|
|
},
|
|
{
|
|
"entropy": 5.680092430114746,
|
|
"epoch": 0.652402256370356,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004962873752439035,
|
|
"loss": 5.3918,
|
|
"mean_token_accuracy": 0.17222664952278138,
|
|
"num_tokens": 14548180.0,
|
|
"step": 8385
|
|
},
|
|
{
|
|
"entropy": 5.645467519760132,
|
|
"epoch": 0.6527912857420736,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004962823595065141,
|
|
"loss": 5.4098,
|
|
"mean_token_accuracy": 0.17034562826156616,
|
|
"num_tokens": 14556907.0,
|
|
"step": 8390
|
|
},
|
|
{
|
|
"entropy": 5.578256464004516,
|
|
"epoch": 0.653180315113791,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004962773404115172,
|
|
"loss": 5.3816,
|
|
"mean_token_accuracy": 0.17010515034198762,
|
|
"num_tokens": 14565317.0,
|
|
"step": 8395
|
|
},
|
|
{
|
|
"entropy": 5.6273193359375,
|
|
"epoch": 0.6535693444855086,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004962723179589886,
|
|
"loss": 5.4375,
|
|
"mean_token_accuracy": 0.17320182919502258,
|
|
"num_tokens": 14574485.0,
|
|
"step": 8400
|
|
},
|
|
{
|
|
"entropy": 5.6831926822662355,
|
|
"epoch": 0.6539583738572262,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000496267292149005,
|
|
"loss": 5.3366,
|
|
"mean_token_accuracy": 0.17173146307468415,
|
|
"num_tokens": 14584002.0,
|
|
"step": 8405
|
|
},
|
|
{
|
|
"entropy": 5.620897436141968,
|
|
"epoch": 0.6543474032289438,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004962622629816423,
|
|
"loss": 5.2866,
|
|
"mean_token_accuracy": 0.17372749596834183,
|
|
"num_tokens": 14592033.0,
|
|
"step": 8410
|
|
},
|
|
{
|
|
"entropy": 5.575413608551026,
|
|
"epoch": 0.6547364326006614,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000496257230456977,
|
|
"loss": 5.4229,
|
|
"mean_token_accuracy": 0.16647793501615524,
|
|
"num_tokens": 14600084.0,
|
|
"step": 8415
|
|
},
|
|
{
|
|
"entropy": 5.549050331115723,
|
|
"epoch": 0.6551254619723789,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004962521945750855,
|
|
"loss": 5.3345,
|
|
"mean_token_accuracy": 0.18473218381404877,
|
|
"num_tokens": 14608380.0,
|
|
"step": 8420
|
|
},
|
|
{
|
|
"entropy": 5.601489877700805,
|
|
"epoch": 0.6555144913440965,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000496247155336044,
|
|
"loss": 5.3939,
|
|
"mean_token_accuracy": 0.17354901134967804,
|
|
"num_tokens": 14616864.0,
|
|
"step": 8425
|
|
},
|
|
{
|
|
"entropy": 5.623040390014649,
|
|
"epoch": 0.655903520715814,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004962421127399291,
|
|
"loss": 5.4296,
|
|
"mean_token_accuracy": 0.1710478574037552,
|
|
"num_tokens": 14627054.0,
|
|
"step": 8430
|
|
},
|
|
{
|
|
"entropy": 5.670633983612061,
|
|
"epoch": 0.6562925500875316,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004962370667868172,
|
|
"loss": 5.3229,
|
|
"mean_token_accuracy": 0.17703424990177155,
|
|
"num_tokens": 14634985.0,
|
|
"step": 8435
|
|
},
|
|
{
|
|
"entropy": 5.643927383422851,
|
|
"epoch": 0.6566815794592492,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004962320174767851,
|
|
"loss": 5.3916,
|
|
"mean_token_accuracy": 0.18009753823280333,
|
|
"num_tokens": 14644135.0,
|
|
"step": 8440
|
|
},
|
|
{
|
|
"entropy": 5.552023220062256,
|
|
"epoch": 0.6570706088309667,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000496226964809909,
|
|
"loss": 5.3505,
|
|
"mean_token_accuracy": 0.17871672064065933,
|
|
"num_tokens": 14652997.0,
|
|
"step": 8445
|
|
},
|
|
{
|
|
"entropy": 5.575016212463379,
|
|
"epoch": 0.6574596382026843,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000496221908786266,
|
|
"loss": 5.4318,
|
|
"mean_token_accuracy": 0.1723785251379013,
|
|
"num_tokens": 14661961.0,
|
|
"step": 8450
|
|
},
|
|
{
|
|
"entropy": 5.677073335647583,
|
|
"epoch": 0.6578486675744019,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004962168494059327,
|
|
"loss": 5.5334,
|
|
"mean_token_accuracy": 0.1619396537542343,
|
|
"num_tokens": 14671407.0,
|
|
"step": 8455
|
|
},
|
|
{
|
|
"entropy": 5.653186559677124,
|
|
"epoch": 0.6582376969461194,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004962117866689857,
|
|
"loss": 5.3801,
|
|
"mean_token_accuracy": 0.17210789620876313,
|
|
"num_tokens": 14680015.0,
|
|
"step": 8460
|
|
},
|
|
{
|
|
"entropy": 5.530022239685058,
|
|
"epoch": 0.658626726317837,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000496206720575502,
|
|
"loss": 5.2363,
|
|
"mean_token_accuracy": 0.17737187445163727,
|
|
"num_tokens": 14688444.0,
|
|
"step": 8465
|
|
},
|
|
{
|
|
"entropy": 5.562881183624268,
|
|
"epoch": 0.6590157556895546,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004962016511255584,
|
|
"loss": 5.3704,
|
|
"mean_token_accuracy": 0.1729799672961235,
|
|
"num_tokens": 14697246.0,
|
|
"step": 8470
|
|
},
|
|
{
|
|
"entropy": 5.561779022216797,
|
|
"epoch": 0.6594047850612721,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004961965783192318,
|
|
"loss": 5.2517,
|
|
"mean_token_accuracy": 0.18331620693206788,
|
|
"num_tokens": 14706066.0,
|
|
"step": 8475
|
|
},
|
|
{
|
|
"entropy": 5.601294326782226,
|
|
"epoch": 0.6597938144329897,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004961915021565992,
|
|
"loss": 5.3758,
|
|
"mean_token_accuracy": 0.16975661367177963,
|
|
"num_tokens": 14714327.0,
|
|
"step": 8480
|
|
},
|
|
{
|
|
"entropy": 5.552827501296997,
|
|
"epoch": 0.6601828438047073,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004961864226377377,
|
|
"loss": 5.2382,
|
|
"mean_token_accuracy": 0.17383477240800857,
|
|
"num_tokens": 14723053.0,
|
|
"step": 8485
|
|
},
|
|
{
|
|
"entropy": 5.542729759216309,
|
|
"epoch": 0.6605718731764249,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004961813397627241,
|
|
"loss": 5.2263,
|
|
"mean_token_accuracy": 0.1823290318250656,
|
|
"num_tokens": 14731825.0,
|
|
"step": 8490
|
|
},
|
|
{
|
|
"entropy": 5.584241247177124,
|
|
"epoch": 0.6609609025481424,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004961762535316358,
|
|
"loss": 5.4327,
|
|
"mean_token_accuracy": 0.16857006251811982,
|
|
"num_tokens": 14740751.0,
|
|
"step": 8495
|
|
},
|
|
{
|
|
"entropy": 5.608772897720337,
|
|
"epoch": 0.6613499319198599,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004961711639445499,
|
|
"loss": 5.3014,
|
|
"mean_token_accuracy": 0.1776784747838974,
|
|
"num_tokens": 14748994.0,
|
|
"step": 8500
|
|
},
|
|
{
|
|
"entropy": 5.606518363952636,
|
|
"epoch": 0.6617389612915775,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004961660710015435,
|
|
"loss": 5.2935,
|
|
"mean_token_accuracy": 0.17489899098873138,
|
|
"num_tokens": 14757388.0,
|
|
"step": 8505
|
|
},
|
|
{
|
|
"entropy": 5.676743650436402,
|
|
"epoch": 0.6621279906632951,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004961609747026943,
|
|
"loss": 5.4395,
|
|
"mean_token_accuracy": 0.16976004093885422,
|
|
"num_tokens": 14766654.0,
|
|
"step": 8510
|
|
},
|
|
{
|
|
"entropy": 5.580006885528564,
|
|
"epoch": 0.6625170200350127,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004961558750480791,
|
|
"loss": 5.3578,
|
|
"mean_token_accuracy": 0.17017442137002944,
|
|
"num_tokens": 14775561.0,
|
|
"step": 8515
|
|
},
|
|
{
|
|
"entropy": 5.593653726577759,
|
|
"epoch": 0.6629060494067303,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004961507720377756,
|
|
"loss": 5.4202,
|
|
"mean_token_accuracy": 0.16423940807580947,
|
|
"num_tokens": 14783596.0,
|
|
"step": 8520
|
|
},
|
|
{
|
|
"entropy": 5.634108591079712,
|
|
"epoch": 0.6632950787784477,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004961456656718611,
|
|
"loss": 5.4294,
|
|
"mean_token_accuracy": 0.16964395791292192,
|
|
"num_tokens": 14791932.0,
|
|
"step": 8525
|
|
},
|
|
{
|
|
"entropy": 5.652415704727173,
|
|
"epoch": 0.6636841081501653,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000496140555950413,
|
|
"loss": 5.4536,
|
|
"mean_token_accuracy": 0.16912026405334474,
|
|
"num_tokens": 14801261.0,
|
|
"step": 8530
|
|
},
|
|
{
|
|
"entropy": 5.6047392845153805,
|
|
"epoch": 0.6640731375218829,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004961354428735091,
|
|
"loss": 5.3357,
|
|
"mean_token_accuracy": 0.17305805534124374,
|
|
"num_tokens": 14809788.0,
|
|
"step": 8535
|
|
},
|
|
{
|
|
"entropy": 5.545555257797242,
|
|
"epoch": 0.6644621668936005,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004961303264412267,
|
|
"loss": 5.3274,
|
|
"mean_token_accuracy": 0.17021722495555877,
|
|
"num_tokens": 14818324.0,
|
|
"step": 8540
|
|
},
|
|
{
|
|
"entropy": 5.526040124893188,
|
|
"epoch": 0.6648511962653181,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004961252066536437,
|
|
"loss": 5.2805,
|
|
"mean_token_accuracy": 0.17774665653705596,
|
|
"num_tokens": 14827020.0,
|
|
"step": 8545
|
|
},
|
|
{
|
|
"entropy": 5.564234209060669,
|
|
"epoch": 0.6652402256370356,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004961200835108375,
|
|
"loss": 5.3871,
|
|
"mean_token_accuracy": 0.1685611218214035,
|
|
"num_tokens": 14835522.0,
|
|
"step": 8550
|
|
},
|
|
{
|
|
"entropy": 5.63460865020752,
|
|
"epoch": 0.6656292550087531,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000496114957012886,
|
|
"loss": 5.3465,
|
|
"mean_token_accuracy": 0.17625492215156555,
|
|
"num_tokens": 14844676.0,
|
|
"step": 8555
|
|
},
|
|
{
|
|
"entropy": 5.653724718093872,
|
|
"epoch": 0.6660182843804707,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004961098271598671,
|
|
"loss": 5.3852,
|
|
"mean_token_accuracy": 0.17274842262268067,
|
|
"num_tokens": 14853996.0,
|
|
"step": 8560
|
|
},
|
|
{
|
|
"entropy": 5.612109565734864,
|
|
"epoch": 0.6664073137521883,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004961046939518585,
|
|
"loss": 5.3729,
|
|
"mean_token_accuracy": 0.17253222763538362,
|
|
"num_tokens": 14862981.0,
|
|
"step": 8565
|
|
},
|
|
{
|
|
"entropy": 5.613665246963501,
|
|
"epoch": 0.6667963431239059,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004960995573889379,
|
|
"loss": 5.4015,
|
|
"mean_token_accuracy": 0.16996358931064606,
|
|
"num_tokens": 14872378.0,
|
|
"step": 8570
|
|
},
|
|
{
|
|
"entropy": 5.558696269989014,
|
|
"epoch": 0.6671853724956234,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004960944174711836,
|
|
"loss": 5.3487,
|
|
"mean_token_accuracy": 0.1734008237719536,
|
|
"num_tokens": 14881662.0,
|
|
"step": 8575
|
|
},
|
|
{
|
|
"entropy": 5.628997802734375,
|
|
"epoch": 0.667574401867341,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004960892741986734,
|
|
"loss": 5.2375,
|
|
"mean_token_accuracy": 0.17901071906089783,
|
|
"num_tokens": 14890211.0,
|
|
"step": 8580
|
|
},
|
|
{
|
|
"entropy": 5.663716506958008,
|
|
"epoch": 0.6679634312390585,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004960841275714853,
|
|
"loss": 5.4768,
|
|
"mean_token_accuracy": 0.165939624607563,
|
|
"num_tokens": 14899865.0,
|
|
"step": 8585
|
|
},
|
|
{
|
|
"entropy": 5.59187388420105,
|
|
"epoch": 0.6683524606107761,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004960789775896975,
|
|
"loss": 5.375,
|
|
"mean_token_accuracy": 0.1709680363535881,
|
|
"num_tokens": 14908334.0,
|
|
"step": 8590
|
|
},
|
|
{
|
|
"entropy": 5.546440458297729,
|
|
"epoch": 0.6687414899824937,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004960738242533881,
|
|
"loss": 5.3263,
|
|
"mean_token_accuracy": 0.17018923163414001,
|
|
"num_tokens": 14916477.0,
|
|
"step": 8595
|
|
},
|
|
{
|
|
"entropy": 5.534609317779541,
|
|
"epoch": 0.6691305193542112,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004960686675626353,
|
|
"loss": 5.2612,
|
|
"mean_token_accuracy": 0.18023026138544082,
|
|
"num_tokens": 14925223.0,
|
|
"step": 8600
|
|
},
|
|
{
|
|
"entropy": 5.615374946594239,
|
|
"epoch": 0.6695195487259288,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004960635075175173,
|
|
"loss": 5.4224,
|
|
"mean_token_accuracy": 0.1766976684331894,
|
|
"num_tokens": 14934427.0,
|
|
"step": 8605
|
|
},
|
|
{
|
|
"entropy": 5.660296106338501,
|
|
"epoch": 0.6699085780976464,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004960583441181124,
|
|
"loss": 5.3294,
|
|
"mean_token_accuracy": 0.17061750888824462,
|
|
"num_tokens": 14943175.0,
|
|
"step": 8610
|
|
},
|
|
{
|
|
"entropy": 5.641629028320312,
|
|
"epoch": 0.670297607469364,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004960531773644992,
|
|
"loss": 5.3658,
|
|
"mean_token_accuracy": 0.17371981889009475,
|
|
"num_tokens": 14951933.0,
|
|
"step": 8615
|
|
},
|
|
{
|
|
"entropy": 5.539992618560791,
|
|
"epoch": 0.6706866368410815,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004960480072567557,
|
|
"loss": 5.3346,
|
|
"mean_token_accuracy": 0.17478349655866623,
|
|
"num_tokens": 14960735.0,
|
|
"step": 8620
|
|
},
|
|
{
|
|
"entropy": 5.596373748779297,
|
|
"epoch": 0.671075666212799,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004960428337949604,
|
|
"loss": 5.4398,
|
|
"mean_token_accuracy": 0.16128688901662827,
|
|
"num_tokens": 14970326.0,
|
|
"step": 8625
|
|
},
|
|
{
|
|
"entropy": 5.629201078414917,
|
|
"epoch": 0.6714646955845166,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004960376569791921,
|
|
"loss": 5.2938,
|
|
"mean_token_accuracy": 0.17815542072057725,
|
|
"num_tokens": 14979822.0,
|
|
"step": 8630
|
|
},
|
|
{
|
|
"entropy": 5.6754405975341795,
|
|
"epoch": 0.6718537249562342,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004960324768095291,
|
|
"loss": 5.4085,
|
|
"mean_token_accuracy": 0.1730176329612732,
|
|
"num_tokens": 14989350.0,
|
|
"step": 8635
|
|
},
|
|
{
|
|
"entropy": 5.6606629371643065,
|
|
"epoch": 0.6722427543279518,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004960272932860502,
|
|
"loss": 5.4147,
|
|
"mean_token_accuracy": 0.16840969920158386,
|
|
"num_tokens": 14998763.0,
|
|
"step": 8640
|
|
},
|
|
{
|
|
"entropy": 5.59739351272583,
|
|
"epoch": 0.6726317836996694,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004960221064088338,
|
|
"loss": 5.2809,
|
|
"mean_token_accuracy": 0.17504533380270004,
|
|
"num_tokens": 15006497.0,
|
|
"step": 8645
|
|
},
|
|
{
|
|
"entropy": 5.513886976242065,
|
|
"epoch": 0.6730208130713868,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004960169161779588,
|
|
"loss": 5.2495,
|
|
"mean_token_accuracy": 0.17931035459041594,
|
|
"num_tokens": 15014397.0,
|
|
"step": 8650
|
|
},
|
|
{
|
|
"entropy": 5.548941230773925,
|
|
"epoch": 0.6734098424431044,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004960117225935038,
|
|
"loss": 5.2764,
|
|
"mean_token_accuracy": 0.18180057406425476,
|
|
"num_tokens": 15022726.0,
|
|
"step": 8655
|
|
},
|
|
{
|
|
"entropy": 5.680811405181885,
|
|
"epoch": 0.673798871814822,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004960065256555477,
|
|
"loss": 5.4944,
|
|
"mean_token_accuracy": 0.1663055121898651,
|
|
"num_tokens": 15032317.0,
|
|
"step": 8660
|
|
},
|
|
{
|
|
"entropy": 5.596422576904297,
|
|
"epoch": 0.6741879011865396,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004960013253641695,
|
|
"loss": 5.3526,
|
|
"mean_token_accuracy": 0.17427897900342942,
|
|
"num_tokens": 15041091.0,
|
|
"step": 8665
|
|
},
|
|
{
|
|
"entropy": 5.630930995941162,
|
|
"epoch": 0.6745769305582572,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004959961217194477,
|
|
"loss": 5.495,
|
|
"mean_token_accuracy": 0.16269925981760025,
|
|
"num_tokens": 15049797.0,
|
|
"step": 8670
|
|
},
|
|
{
|
|
"entropy": 5.549777984619141,
|
|
"epoch": 0.6749659599299748,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004959909147214615,
|
|
"loss": 5.1909,
|
|
"mean_token_accuracy": 0.18470783829689025,
|
|
"num_tokens": 15057736.0,
|
|
"step": 8675
|
|
},
|
|
{
|
|
"entropy": 5.5708211898803714,
|
|
"epoch": 0.6753549893016922,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004959857043702902,
|
|
"loss": 5.362,
|
|
"mean_token_accuracy": 0.1793429061770439,
|
|
"num_tokens": 15066072.0,
|
|
"step": 8680
|
|
},
|
|
{
|
|
"entropy": 5.529650020599365,
|
|
"epoch": 0.6757440186734098,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004959804906660124,
|
|
"loss": 5.2662,
|
|
"mean_token_accuracy": 0.1785495787858963,
|
|
"num_tokens": 15073918.0,
|
|
"step": 8685
|
|
},
|
|
{
|
|
"entropy": 5.613301610946655,
|
|
"epoch": 0.6761330480451274,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004959752736087073,
|
|
"loss": 5.3614,
|
|
"mean_token_accuracy": 0.1788905903697014,
|
|
"num_tokens": 15082937.0,
|
|
"step": 8690
|
|
},
|
|
{
|
|
"entropy": 5.559736108779907,
|
|
"epoch": 0.676522077416845,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004959700531984543,
|
|
"loss": 5.3177,
|
|
"mean_token_accuracy": 0.18061764240264894,
|
|
"num_tokens": 15091218.0,
|
|
"step": 8695
|
|
},
|
|
{
|
|
"entropy": 5.553287220001221,
|
|
"epoch": 0.6769111067885626,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004959648294353324,
|
|
"loss": 5.2474,
|
|
"mean_token_accuracy": 0.18204528391361235,
|
|
"num_tokens": 15099640.0,
|
|
"step": 8700
|
|
},
|
|
{
|
|
"entropy": 5.599412107467652,
|
|
"epoch": 0.6773001361602801,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004959596023194208,
|
|
"loss": 5.3279,
|
|
"mean_token_accuracy": 0.17507115006446838,
|
|
"num_tokens": 15108710.0,
|
|
"step": 8705
|
|
},
|
|
{
|
|
"entropy": 5.5698775291442875,
|
|
"epoch": 0.6776891655319977,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000495954371850799,
|
|
"loss": 5.2904,
|
|
"mean_token_accuracy": 0.17398254275321962,
|
|
"num_tokens": 15117074.0,
|
|
"step": 8710
|
|
},
|
|
{
|
|
"entropy": 5.6180814743042,
|
|
"epoch": 0.6780781949037152,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004959491380295463,
|
|
"loss": 5.2742,
|
|
"mean_token_accuracy": 0.17939819693565368,
|
|
"num_tokens": 15124714.0,
|
|
"step": 8715
|
|
},
|
|
{
|
|
"entropy": 5.544650268554688,
|
|
"epoch": 0.6784672242754328,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004959439008557422,
|
|
"loss": 5.3062,
|
|
"mean_token_accuracy": 0.1737214908003807,
|
|
"num_tokens": 15134177.0,
|
|
"step": 8720
|
|
},
|
|
{
|
|
"entropy": 5.614916658401489,
|
|
"epoch": 0.6788562536471504,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000495938660329466,
|
|
"loss": 5.3171,
|
|
"mean_token_accuracy": 0.17673608660697937,
|
|
"num_tokens": 15142659.0,
|
|
"step": 8725
|
|
},
|
|
{
|
|
"entropy": 5.581689453125,
|
|
"epoch": 0.6792452830188679,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004959334164507973,
|
|
"loss": 5.4753,
|
|
"mean_token_accuracy": 0.1690713033080101,
|
|
"num_tokens": 15151423.0,
|
|
"step": 8730
|
|
},
|
|
{
|
|
"entropy": 5.582829475402832,
|
|
"epoch": 0.6796343123905855,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004959281692198155,
|
|
"loss": 5.2525,
|
|
"mean_token_accuracy": 0.17850179523229598,
|
|
"num_tokens": 15159986.0,
|
|
"step": 8735
|
|
},
|
|
{
|
|
"entropy": 5.616036605834961,
|
|
"epoch": 0.6800233417623031,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004959229186366007,
|
|
"loss": 5.3328,
|
|
"mean_token_accuracy": 0.17353588789701463,
|
|
"num_tokens": 15168183.0,
|
|
"step": 8740
|
|
},
|
|
{
|
|
"entropy": 5.525445938110352,
|
|
"epoch": 0.6804123711340206,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000495917664701232,
|
|
"loss": 5.243,
|
|
"mean_token_accuracy": 0.18078750669956206,
|
|
"num_tokens": 15176476.0,
|
|
"step": 8745
|
|
},
|
|
{
|
|
"entropy": 5.673672342300415,
|
|
"epoch": 0.6808014005057382,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004959124074137894,
|
|
"loss": 5.5157,
|
|
"mean_token_accuracy": 0.16620651483535767,
|
|
"num_tokens": 15186873.0,
|
|
"step": 8750
|
|
},
|
|
{
|
|
"entropy": 5.639481735229492,
|
|
"epoch": 0.6811904298774557,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004959071467743526,
|
|
"loss": 5.309,
|
|
"mean_token_accuracy": 0.16986880004405974,
|
|
"num_tokens": 15194965.0,
|
|
"step": 8755
|
|
},
|
|
{
|
|
"entropy": 5.551694726943969,
|
|
"epoch": 0.6815794592491733,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004959018827830016,
|
|
"loss": 5.1768,
|
|
"mean_token_accuracy": 0.18066548109054564,
|
|
"num_tokens": 15204028.0,
|
|
"step": 8760
|
|
},
|
|
{
|
|
"entropy": 5.494821929931641,
|
|
"epoch": 0.6819684886208909,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000495896615439816,
|
|
"loss": 5.2047,
|
|
"mean_token_accuracy": 0.1873243436217308,
|
|
"num_tokens": 15212011.0,
|
|
"step": 8765
|
|
},
|
|
{
|
|
"entropy": 5.519406366348266,
|
|
"epoch": 0.6823575179926085,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004958913447448759,
|
|
"loss": 5.288,
|
|
"mean_token_accuracy": 0.17712078392505645,
|
|
"num_tokens": 15220088.0,
|
|
"step": 8770
|
|
},
|
|
{
|
|
"entropy": 5.612569952011109,
|
|
"epoch": 0.682746547364326,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004958860706982613,
|
|
"loss": 5.2461,
|
|
"mean_token_accuracy": 0.1817832812666893,
|
|
"num_tokens": 15228676.0,
|
|
"step": 8775
|
|
},
|
|
{
|
|
"entropy": 5.540105104446411,
|
|
"epoch": 0.6831355767360435,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000495880793300052,
|
|
"loss": 5.2864,
|
|
"mean_token_accuracy": 0.1815814346075058,
|
|
"num_tokens": 15237392.0,
|
|
"step": 8780
|
|
},
|
|
{
|
|
"entropy": 5.54796781539917,
|
|
"epoch": 0.6835246061077611,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004958755125503284,
|
|
"loss": 5.4185,
|
|
"mean_token_accuracy": 0.1767105430364609,
|
|
"num_tokens": 15246738.0,
|
|
"step": 8785
|
|
},
|
|
{
|
|
"entropy": 5.647914218902588,
|
|
"epoch": 0.6839136354794787,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004958702284491703,
|
|
"loss": 5.3897,
|
|
"mean_token_accuracy": 0.1756160721182823,
|
|
"num_tokens": 15255154.0,
|
|
"step": 8790
|
|
},
|
|
{
|
|
"entropy": 5.57085337638855,
|
|
"epoch": 0.6843026648511963,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004958649409966581,
|
|
"loss": 5.2768,
|
|
"mean_token_accuracy": 0.18078256845474244,
|
|
"num_tokens": 15264178.0,
|
|
"step": 8795
|
|
},
|
|
{
|
|
"entropy": 5.605639028549194,
|
|
"epoch": 0.6846916942229139,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000495859650192872,
|
|
"loss": 5.3878,
|
|
"mean_token_accuracy": 0.17433761656284333,
|
|
"num_tokens": 15272591.0,
|
|
"step": 8800
|
|
},
|
|
{
|
|
"entropy": 5.59878191947937,
|
|
"epoch": 0.6850807235946313,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004958543560378922,
|
|
"loss": 5.2939,
|
|
"mean_token_accuracy": 0.16908714026212693,
|
|
"num_tokens": 15281280.0,
|
|
"step": 8805
|
|
},
|
|
{
|
|
"entropy": 5.593587160110474,
|
|
"epoch": 0.6854697529663489,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004958490585317991,
|
|
"loss": 5.2382,
|
|
"mean_token_accuracy": 0.1843152090907097,
|
|
"num_tokens": 15290639.0,
|
|
"step": 8810
|
|
},
|
|
{
|
|
"entropy": 5.52235860824585,
|
|
"epoch": 0.6858587823380665,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000495843757674673,
|
|
"loss": 5.2296,
|
|
"mean_token_accuracy": 0.1753144696354866,
|
|
"num_tokens": 15298877.0,
|
|
"step": 8815
|
|
},
|
|
{
|
|
"entropy": 5.596991682052613,
|
|
"epoch": 0.6862478117097841,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004958384534665945,
|
|
"loss": 5.3783,
|
|
"mean_token_accuracy": 0.17458462715148926,
|
|
"num_tokens": 15307710.0,
|
|
"step": 8820
|
|
},
|
|
{
|
|
"entropy": 5.633730268478393,
|
|
"epoch": 0.6866368410815017,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004958331459076438,
|
|
"loss": 5.3891,
|
|
"mean_token_accuracy": 0.17663782089948654,
|
|
"num_tokens": 15315749.0,
|
|
"step": 8825
|
|
},
|
|
{
|
|
"entropy": 5.661491775512696,
|
|
"epoch": 0.6870258704532192,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004958278349979018,
|
|
"loss": 5.3432,
|
|
"mean_token_accuracy": 0.16726212650537492,
|
|
"num_tokens": 15324161.0,
|
|
"step": 8830
|
|
},
|
|
{
|
|
"entropy": 5.476969242095947,
|
|
"epoch": 0.6874148998249368,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004958225207374488,
|
|
"loss": 5.2393,
|
|
"mean_token_accuracy": 0.17856181263923646,
|
|
"num_tokens": 15333414.0,
|
|
"step": 8835
|
|
},
|
|
{
|
|
"entropy": 5.547606134414673,
|
|
"epoch": 0.6878039291966543,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004958172031263655,
|
|
"loss": 5.3028,
|
|
"mean_token_accuracy": 0.17507703602313995,
|
|
"num_tokens": 15342369.0,
|
|
"step": 8840
|
|
},
|
|
{
|
|
"entropy": 5.619305086135864,
|
|
"epoch": 0.6881929585683719,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004958118821647326,
|
|
"loss": 5.3836,
|
|
"mean_token_accuracy": 0.17099674493074418,
|
|
"num_tokens": 15351109.0,
|
|
"step": 8845
|
|
},
|
|
{
|
|
"entropy": 5.574743413925171,
|
|
"epoch": 0.6885819879400895,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004958065578526308,
|
|
"loss": 5.2711,
|
|
"mean_token_accuracy": 0.1795060008764267,
|
|
"num_tokens": 15359837.0,
|
|
"step": 8850
|
|
},
|
|
{
|
|
"entropy": 5.53717565536499,
|
|
"epoch": 0.688971017311807,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000495801230190141,
|
|
"loss": 5.3116,
|
|
"mean_token_accuracy": 0.18208779990673066,
|
|
"num_tokens": 15368776.0,
|
|
"step": 8855
|
|
},
|
|
{
|
|
"entropy": 5.568300533294678,
|
|
"epoch": 0.6893600466835246,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004957958991773441,
|
|
"loss": 5.3055,
|
|
"mean_token_accuracy": 0.17928243428468704,
|
|
"num_tokens": 15378127.0,
|
|
"step": 8860
|
|
},
|
|
{
|
|
"entropy": 5.579755067825317,
|
|
"epoch": 0.6897490760552422,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004957905648143206,
|
|
"loss": 5.2787,
|
|
"mean_token_accuracy": 0.17940096259117128,
|
|
"num_tokens": 15386580.0,
|
|
"step": 8865
|
|
},
|
|
{
|
|
"entropy": 5.584767055511475,
|
|
"epoch": 0.6901381054269597,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004957852271011519,
|
|
"loss": 5.405,
|
|
"mean_token_accuracy": 0.17330296337604523,
|
|
"num_tokens": 15395973.0,
|
|
"step": 8870
|
|
},
|
|
{
|
|
"entropy": 5.606221294403076,
|
|
"epoch": 0.6905271347986773,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004957798860379187,
|
|
"loss": 5.3118,
|
|
"mean_token_accuracy": 0.1782598003745079,
|
|
"num_tokens": 15404738.0,
|
|
"step": 8875
|
|
},
|
|
{
|
|
"entropy": 5.622283554077148,
|
|
"epoch": 0.6909161641703949,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004957745416247022,
|
|
"loss": 5.4441,
|
|
"mean_token_accuracy": 0.1751920148730278,
|
|
"num_tokens": 15413530.0,
|
|
"step": 8880
|
|
},
|
|
{
|
|
"entropy": 5.633462619781494,
|
|
"epoch": 0.6913051935421124,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004957691938615833,
|
|
"loss": 5.4183,
|
|
"mean_token_accuracy": 0.1715339332818985,
|
|
"num_tokens": 15423268.0,
|
|
"step": 8885
|
|
},
|
|
{
|
|
"entropy": 5.574162769317627,
|
|
"epoch": 0.69169422291383,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004957638427486434,
|
|
"loss": 5.2495,
|
|
"mean_token_accuracy": 0.18264658004045486,
|
|
"num_tokens": 15431690.0,
|
|
"step": 8890
|
|
},
|
|
{
|
|
"entropy": 5.598479509353638,
|
|
"epoch": 0.6920832522855476,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004957584882859636,
|
|
"loss": 5.3982,
|
|
"mean_token_accuracy": 0.16933944076299667,
|
|
"num_tokens": 15440110.0,
|
|
"step": 8895
|
|
},
|
|
{
|
|
"entropy": 5.663942480087281,
|
|
"epoch": 0.6924722816572652,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004957531304736251,
|
|
"loss": 5.4078,
|
|
"mean_token_accuracy": 0.17168613970279695,
|
|
"num_tokens": 15449022.0,
|
|
"step": 8900
|
|
},
|
|
{
|
|
"entropy": 5.677679395675659,
|
|
"epoch": 0.6928613110289827,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004957477693117091,
|
|
"loss": 5.4359,
|
|
"mean_token_accuracy": 0.16897011548280716,
|
|
"num_tokens": 15457826.0,
|
|
"step": 8905
|
|
},
|
|
{
|
|
"entropy": 5.600473356246948,
|
|
"epoch": 0.6932503404007002,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004957424048002971,
|
|
"loss": 5.3552,
|
|
"mean_token_accuracy": 0.17295342981815337,
|
|
"num_tokens": 15466631.0,
|
|
"step": 8910
|
|
},
|
|
{
|
|
"entropy": 5.5296543598175045,
|
|
"epoch": 0.6936393697724178,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004957370369394706,
|
|
"loss": 5.2514,
|
|
"mean_token_accuracy": 0.17798096388578416,
|
|
"num_tokens": 15474666.0,
|
|
"step": 8915
|
|
},
|
|
{
|
|
"entropy": 5.53621883392334,
|
|
"epoch": 0.6940283991441354,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004957316657293107,
|
|
"loss": 5.2409,
|
|
"mean_token_accuracy": 0.1825147047638893,
|
|
"num_tokens": 15483576.0,
|
|
"step": 8920
|
|
},
|
|
{
|
|
"entropy": 5.751343250274658,
|
|
"epoch": 0.694417428515853,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004957262911698992,
|
|
"loss": 5.3941,
|
|
"mean_token_accuracy": 0.17334622144699097,
|
|
"num_tokens": 15491313.0,
|
|
"step": 8925
|
|
},
|
|
{
|
|
"entropy": 5.640914344787598,
|
|
"epoch": 0.6948064578875706,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004957209132613175,
|
|
"loss": 5.3363,
|
|
"mean_token_accuracy": 0.17856969833374023,
|
|
"num_tokens": 15500638.0,
|
|
"step": 8930
|
|
},
|
|
{
|
|
"entropy": 5.565763854980469,
|
|
"epoch": 0.695195487259288,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004957155320036473,
|
|
"loss": 5.3285,
|
|
"mean_token_accuracy": 0.17599815875291824,
|
|
"num_tokens": 15509170.0,
|
|
"step": 8935
|
|
},
|
|
{
|
|
"entropy": 5.678889417648316,
|
|
"epoch": 0.6955845166310056,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004957101473969702,
|
|
"loss": 5.4244,
|
|
"mean_token_accuracy": 0.16916741132736207,
|
|
"num_tokens": 15518108.0,
|
|
"step": 8940
|
|
},
|
|
{
|
|
"entropy": 5.578175735473633,
|
|
"epoch": 0.6959735460027232,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000495704759441368,
|
|
"loss": 5.29,
|
|
"mean_token_accuracy": 0.1825377270579338,
|
|
"num_tokens": 15526558.0,
|
|
"step": 8945
|
|
},
|
|
{
|
|
"entropy": 5.577849960327148,
|
|
"epoch": 0.6963625753744408,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004956993681369221,
|
|
"loss": 5.2647,
|
|
"mean_token_accuracy": 0.17751545161008836,
|
|
"num_tokens": 15535685.0,
|
|
"step": 8950
|
|
},
|
|
{
|
|
"entropy": 5.555082225799561,
|
|
"epoch": 0.6967516047461584,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004956939734837148,
|
|
"loss": 5.3069,
|
|
"mean_token_accuracy": 0.18180457949638368,
|
|
"num_tokens": 15544072.0,
|
|
"step": 8955
|
|
},
|
|
{
|
|
"entropy": 5.575622272491455,
|
|
"epoch": 0.6971406341178759,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004956885754818277,
|
|
"loss": 5.4028,
|
|
"mean_token_accuracy": 0.1679277539253235,
|
|
"num_tokens": 15553303.0,
|
|
"step": 8960
|
|
},
|
|
{
|
|
"entropy": 5.61887001991272,
|
|
"epoch": 0.6975296634895934,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004956831741313427,
|
|
"loss": 5.3316,
|
|
"mean_token_accuracy": 0.17559644281864167,
|
|
"num_tokens": 15561942.0,
|
|
"step": 8965
|
|
},
|
|
{
|
|
"entropy": 5.5660655975341795,
|
|
"epoch": 0.697918692861311,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004956777694323418,
|
|
"loss": 5.1906,
|
|
"mean_token_accuracy": 0.18667613863945007,
|
|
"num_tokens": 15569988.0,
|
|
"step": 8970
|
|
},
|
|
{
|
|
"entropy": 5.58125638961792,
|
|
"epoch": 0.6983077222330286,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000495672361384907,
|
|
"loss": 5.3878,
|
|
"mean_token_accuracy": 0.1742572844028473,
|
|
"num_tokens": 15579816.0,
|
|
"step": 8975
|
|
},
|
|
{
|
|
"entropy": 5.611002349853516,
|
|
"epoch": 0.6986967516047462,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004956669499891202,
|
|
"loss": 5.2717,
|
|
"mean_token_accuracy": 0.17696754336357118,
|
|
"num_tokens": 15587843.0,
|
|
"step": 8980
|
|
},
|
|
{
|
|
"entropy": 5.579117298126221,
|
|
"epoch": 0.6990857809764637,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004956615352450639,
|
|
"loss": 5.3207,
|
|
"mean_token_accuracy": 0.17747793793678285,
|
|
"num_tokens": 15596798.0,
|
|
"step": 8985
|
|
},
|
|
{
|
|
"entropy": 5.588120603561402,
|
|
"epoch": 0.6994748103481813,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004956561171528198,
|
|
"loss": 5.4235,
|
|
"mean_token_accuracy": 0.1786605969071388,
|
|
"num_tokens": 15605360.0,
|
|
"step": 8990
|
|
},
|
|
{
|
|
"entropy": 5.573551416397095,
|
|
"epoch": 0.6998638397198989,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004956506957124704,
|
|
"loss": 5.2779,
|
|
"mean_token_accuracy": 0.18233997970819474,
|
|
"num_tokens": 15613557.0,
|
|
"step": 8995
|
|
},
|
|
{
|
|
"entropy": 5.566599798202515,
|
|
"epoch": 0.7002528690916164,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000495645270924098,
|
|
"loss": 5.3547,
|
|
"mean_token_accuracy": 0.17617263793945312,
|
|
"num_tokens": 15622144.0,
|
|
"step": 9000
|
|
},
|
|
{
|
|
"epoch": 0.7002528690916164,
|
|
"eval_entropy": 5.384195727218907,
|
|
"eval_loss": 5.35413932800293,
|
|
"eval_mean_token_accuracy": 0.18322673444568938,
|
|
"eval_num_tokens": 15622144.0,
|
|
"eval_runtime": 21.6228,
|
|
"eval_samples_per_second": 1921.957,
|
|
"eval_steps_per_second": 240.256,
|
|
"step": 9000
|
|
},
|
|
{
|
|
"entropy": 5.5418754577636715,
|
|
"epoch": 0.700641898463334,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004956398427877847,
|
|
"loss": 5.2871,
|
|
"mean_token_accuracy": 0.17854682952165604,
|
|
"num_tokens": 15631119.0,
|
|
"step": 9005
|
|
},
|
|
{
|
|
"entropy": 5.5199097156524655,
|
|
"epoch": 0.7010309278350515,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000495634411303613,
|
|
"loss": 5.204,
|
|
"mean_token_accuracy": 0.18505824506282806,
|
|
"num_tokens": 15639969.0,
|
|
"step": 9010
|
|
},
|
|
{
|
|
"entropy": 5.551648426055908,
|
|
"epoch": 0.7014199572067691,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004956289764716654,
|
|
"loss": 5.3377,
|
|
"mean_token_accuracy": 0.17793741226196289,
|
|
"num_tokens": 15648522.0,
|
|
"step": 9015
|
|
},
|
|
{
|
|
"entropy": 5.524827766418457,
|
|
"epoch": 0.7018089865784867,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004956235382920241,
|
|
"loss": 5.2618,
|
|
"mean_token_accuracy": 0.17254749685525894,
|
|
"num_tokens": 15656834.0,
|
|
"step": 9020
|
|
},
|
|
{
|
|
"entropy": 5.66479754447937,
|
|
"epoch": 0.7021980159502043,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004956180967647717,
|
|
"loss": 5.4573,
|
|
"mean_token_accuracy": 0.1677004277706146,
|
|
"num_tokens": 15665066.0,
|
|
"step": 9025
|
|
},
|
|
{
|
|
"entropy": 5.605295324325562,
|
|
"epoch": 0.7025870453219218,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004956126518899911,
|
|
"loss": 5.3422,
|
|
"mean_token_accuracy": 0.17819261848926543,
|
|
"num_tokens": 15673733.0,
|
|
"step": 9030
|
|
},
|
|
{
|
|
"entropy": 5.6864011764526365,
|
|
"epoch": 0.7029760746936393,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004956072036677644,
|
|
"loss": 5.3775,
|
|
"mean_token_accuracy": 0.1767784833908081,
|
|
"num_tokens": 15682212.0,
|
|
"step": 9035
|
|
},
|
|
{
|
|
"entropy": 5.5967779636383055,
|
|
"epoch": 0.7033651040653569,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004956017520981746,
|
|
"loss": 5.3616,
|
|
"mean_token_accuracy": 0.1693396046757698,
|
|
"num_tokens": 15690518.0,
|
|
"step": 9040
|
|
},
|
|
{
|
|
"entropy": 5.656971168518067,
|
|
"epoch": 0.7037541334370745,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004955962971813044,
|
|
"loss": 5.41,
|
|
"mean_token_accuracy": 0.1654631972312927,
|
|
"num_tokens": 15699474.0,
|
|
"step": 9045
|
|
},
|
|
{
|
|
"entropy": 5.683543634414673,
|
|
"epoch": 0.7041431628087921,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004955908389172364,
|
|
"loss": 5.4212,
|
|
"mean_token_accuracy": 0.17195746153593064,
|
|
"num_tokens": 15708571.0,
|
|
"step": 9050
|
|
},
|
|
{
|
|
"entropy": 5.708956527709961,
|
|
"epoch": 0.7045321921805097,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004955853773060536,
|
|
"loss": 5.4089,
|
|
"mean_token_accuracy": 0.1737460657954216,
|
|
"num_tokens": 15717307.0,
|
|
"step": 9055
|
|
},
|
|
{
|
|
"entropy": 5.600407600402832,
|
|
"epoch": 0.7049212215522271,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004955799123478388,
|
|
"loss": 5.1901,
|
|
"mean_token_accuracy": 0.18662470281124116,
|
|
"num_tokens": 15725502.0,
|
|
"step": 9060
|
|
},
|
|
{
|
|
"entropy": 5.536356353759766,
|
|
"epoch": 0.7053102509239447,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004955744440426748,
|
|
"loss": 5.4074,
|
|
"mean_token_accuracy": 0.1703765869140625,
|
|
"num_tokens": 15734805.0,
|
|
"step": 9065
|
|
},
|
|
{
|
|
"entropy": 5.601238012313843,
|
|
"epoch": 0.7056992802956623,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004955689723906448,
|
|
"loss": 5.258,
|
|
"mean_token_accuracy": 0.1776318818330765,
|
|
"num_tokens": 15743313.0,
|
|
"step": 9070
|
|
},
|
|
{
|
|
"entropy": 5.553364896774292,
|
|
"epoch": 0.7060883096673799,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004955634973918318,
|
|
"loss": 5.2177,
|
|
"mean_token_accuracy": 0.18231946974992752,
|
|
"num_tokens": 15752552.0,
|
|
"step": 9075
|
|
},
|
|
{
|
|
"entropy": 5.623722982406616,
|
|
"epoch": 0.7064773390390975,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004955580190463186,
|
|
"loss": 5.3135,
|
|
"mean_token_accuracy": 0.1862163260579109,
|
|
"num_tokens": 15761404.0,
|
|
"step": 9080
|
|
},
|
|
{
|
|
"entropy": 5.648780250549317,
|
|
"epoch": 0.7068663684108151,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004955525373541886,
|
|
"loss": 5.3778,
|
|
"mean_token_accuracy": 0.17349406629800795,
|
|
"num_tokens": 15770605.0,
|
|
"step": 9085
|
|
},
|
|
{
|
|
"entropy": 5.516891813278198,
|
|
"epoch": 0.7072553977825325,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004955470523155249,
|
|
"loss": 5.268,
|
|
"mean_token_accuracy": 0.17934121787548066,
|
|
"num_tokens": 15778047.0,
|
|
"step": 9090
|
|
},
|
|
{
|
|
"entropy": 5.537967300415039,
|
|
"epoch": 0.7076444271542501,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004955415639304107,
|
|
"loss": 5.3323,
|
|
"mean_token_accuracy": 0.17830815613269807,
|
|
"num_tokens": 15788304.0,
|
|
"step": 9095
|
|
},
|
|
{
|
|
"entropy": 5.617676544189453,
|
|
"epoch": 0.7080334565259677,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004955360721989292,
|
|
"loss": 5.3359,
|
|
"mean_token_accuracy": 0.17249158769845963,
|
|
"num_tokens": 15796448.0,
|
|
"step": 9100
|
|
},
|
|
{
|
|
"entropy": 5.555719661712646,
|
|
"epoch": 0.7084224858976853,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004955305771211641,
|
|
"loss": 5.2904,
|
|
"mean_token_accuracy": 0.17670710235834122,
|
|
"num_tokens": 15805072.0,
|
|
"step": 9105
|
|
},
|
|
{
|
|
"entropy": 5.572696495056152,
|
|
"epoch": 0.7088115152694029,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004955250786971982,
|
|
"loss": 5.3442,
|
|
"mean_token_accuracy": 0.1760936662554741,
|
|
"num_tokens": 15813918.0,
|
|
"step": 9110
|
|
},
|
|
{
|
|
"entropy": 5.7184289455413815,
|
|
"epoch": 0.7092005446411204,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004955195769271154,
|
|
"loss": 5.4707,
|
|
"mean_token_accuracy": 0.17003964632749557,
|
|
"num_tokens": 15822675.0,
|
|
"step": 9115
|
|
},
|
|
{
|
|
"entropy": 5.6127406597137455,
|
|
"epoch": 0.709589574012838,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004955140718109991,
|
|
"loss": 5.356,
|
|
"mean_token_accuracy": 0.17116720974445343,
|
|
"num_tokens": 15831056.0,
|
|
"step": 9120
|
|
},
|
|
{
|
|
"entropy": 5.630828237533569,
|
|
"epoch": 0.7099786033845555,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004955085633489326,
|
|
"loss": 5.4178,
|
|
"mean_token_accuracy": 0.16970840990543365,
|
|
"num_tokens": 15839948.0,
|
|
"step": 9125
|
|
},
|
|
{
|
|
"entropy": 5.632455205917358,
|
|
"epoch": 0.7103676327562731,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004955030515409997,
|
|
"loss": 5.316,
|
|
"mean_token_accuracy": 0.1776179775595665,
|
|
"num_tokens": 15848738.0,
|
|
"step": 9130
|
|
},
|
|
{
|
|
"entropy": 5.609870433807373,
|
|
"epoch": 0.7107566621279907,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004954975363872838,
|
|
"loss": 5.3776,
|
|
"mean_token_accuracy": 0.1716231659054756,
|
|
"num_tokens": 15859073.0,
|
|
"step": 9135
|
|
},
|
|
{
|
|
"entropy": 5.601574182510376,
|
|
"epoch": 0.7111456914997082,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004954920178878689,
|
|
"loss": 5.2674,
|
|
"mean_token_accuracy": 0.18010449558496475,
|
|
"num_tokens": 15868146.0,
|
|
"step": 9140
|
|
},
|
|
{
|
|
"entropy": 5.528825283050537,
|
|
"epoch": 0.7115347208714258,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004954864960428385,
|
|
"loss": 5.2252,
|
|
"mean_token_accuracy": 0.1761257156729698,
|
|
"num_tokens": 15876915.0,
|
|
"step": 9145
|
|
},
|
|
{
|
|
"entropy": 5.556982183456421,
|
|
"epoch": 0.7119237502431434,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004954809708522765,
|
|
"loss": 5.309,
|
|
"mean_token_accuracy": 0.17798453122377395,
|
|
"num_tokens": 15884947.0,
|
|
"step": 9150
|
|
},
|
|
{
|
|
"entropy": 5.611155080795288,
|
|
"epoch": 0.712312779614861,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004954754423162667,
|
|
"loss": 5.3015,
|
|
"mean_token_accuracy": 0.1726186603307724,
|
|
"num_tokens": 15894595.0,
|
|
"step": 9155
|
|
},
|
|
{
|
|
"entropy": 5.616395807266235,
|
|
"epoch": 0.7127018089865785,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000495469910434893,
|
|
"loss": 5.2993,
|
|
"mean_token_accuracy": 0.18139362037181855,
|
|
"num_tokens": 15902920.0,
|
|
"step": 9160
|
|
},
|
|
{
|
|
"entropy": 5.5656671047210695,
|
|
"epoch": 0.713090838358296,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004954643752082392,
|
|
"loss": 5.2935,
|
|
"mean_token_accuracy": 0.1780125841498375,
|
|
"num_tokens": 15911414.0,
|
|
"step": 9165
|
|
},
|
|
{
|
|
"entropy": 5.6202209949493405,
|
|
"epoch": 0.7134798677300136,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004954588366363896,
|
|
"loss": 5.3907,
|
|
"mean_token_accuracy": 0.1711605429649353,
|
|
"num_tokens": 15919855.0,
|
|
"step": 9170
|
|
},
|
|
{
|
|
"entropy": 5.557894134521485,
|
|
"epoch": 0.7138688971017312,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004954532947194279,
|
|
"loss": 5.3023,
|
|
"mean_token_accuracy": 0.17727120369672775,
|
|
"num_tokens": 15928932.0,
|
|
"step": 9175
|
|
},
|
|
{
|
|
"entropy": 5.638629388809204,
|
|
"epoch": 0.7142579264734488,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004954477494574384,
|
|
"loss": 5.3705,
|
|
"mean_token_accuracy": 0.17425462752580642,
|
|
"num_tokens": 15938266.0,
|
|
"step": 9180
|
|
},
|
|
{
|
|
"entropy": 5.692516899108886,
|
|
"epoch": 0.7146469558451664,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004954422008505052,
|
|
"loss": 5.3944,
|
|
"mean_token_accuracy": 0.16764615774154662,
|
|
"num_tokens": 15947100.0,
|
|
"step": 9185
|
|
},
|
|
{
|
|
"entropy": 5.611473178863525,
|
|
"epoch": 0.7150359852168838,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004954366488987125,
|
|
"loss": 5.3783,
|
|
"mean_token_accuracy": 0.1700735718011856,
|
|
"num_tokens": 15955544.0,
|
|
"step": 9190
|
|
},
|
|
{
|
|
"entropy": 5.652182483673096,
|
|
"epoch": 0.7154250145886014,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004954310936021444,
|
|
"loss": 5.4001,
|
|
"mean_token_accuracy": 0.17192965745925903,
|
|
"num_tokens": 15963372.0,
|
|
"step": 9195
|
|
},
|
|
{
|
|
"entropy": 5.644375038146973,
|
|
"epoch": 0.715814043960319,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004954255349608853,
|
|
"loss": 5.3771,
|
|
"mean_token_accuracy": 0.16869236081838607,
|
|
"num_tokens": 15972940.0,
|
|
"step": 9200
|
|
},
|
|
{
|
|
"entropy": 5.633125686645508,
|
|
"epoch": 0.7162030733320366,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004954199729750198,
|
|
"loss": 5.3375,
|
|
"mean_token_accuracy": 0.16978246420621873,
|
|
"num_tokens": 15982238.0,
|
|
"step": 9205
|
|
},
|
|
{
|
|
"entropy": 5.624726867675781,
|
|
"epoch": 0.7165921027037542,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004954144076446318,
|
|
"loss": 5.3454,
|
|
"mean_token_accuracy": 0.17483690232038498,
|
|
"num_tokens": 15990835.0,
|
|
"step": 9210
|
|
},
|
|
{
|
|
"entropy": 5.633648681640625,
|
|
"epoch": 0.7169811320754716,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004954088389698061,
|
|
"loss": 5.4455,
|
|
"mean_token_accuracy": 0.17005229145288467,
|
|
"num_tokens": 16000649.0,
|
|
"step": 9215
|
|
},
|
|
{
|
|
"entropy": 5.612905120849609,
|
|
"epoch": 0.7173701614471892,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000495403266950627,
|
|
"loss": 5.3601,
|
|
"mean_token_accuracy": 0.17579613029956817,
|
|
"num_tokens": 16009214.0,
|
|
"step": 9220
|
|
},
|
|
{
|
|
"entropy": 5.648853302001953,
|
|
"epoch": 0.7177591908189068,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004953976915871792,
|
|
"loss": 5.3409,
|
|
"mean_token_accuracy": 0.1749788999557495,
|
|
"num_tokens": 16018173.0,
|
|
"step": 9225
|
|
},
|
|
{
|
|
"entropy": 5.549958801269531,
|
|
"epoch": 0.7181482201906244,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004953921128795472,
|
|
"loss": 5.2362,
|
|
"mean_token_accuracy": 0.18928415328264236,
|
|
"num_tokens": 16026857.0,
|
|
"step": 9230
|
|
},
|
|
{
|
|
"entropy": 5.589247131347657,
|
|
"epoch": 0.718537249562342,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004953865308278156,
|
|
"loss": 5.4026,
|
|
"mean_token_accuracy": 0.16704169660806656,
|
|
"num_tokens": 16035792.0,
|
|
"step": 9235
|
|
},
|
|
{
|
|
"entropy": 5.623420095443725,
|
|
"epoch": 0.7189262789340595,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004953809454320693,
|
|
"loss": 5.3325,
|
|
"mean_token_accuracy": 0.1779796898365021,
|
|
"num_tokens": 16044874.0,
|
|
"step": 9240
|
|
},
|
|
{
|
|
"entropy": 5.614606761932373,
|
|
"epoch": 0.7193153083057771,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004953753566923929,
|
|
"loss": 5.3004,
|
|
"mean_token_accuracy": 0.17517977058887482,
|
|
"num_tokens": 16053705.0,
|
|
"step": 9245
|
|
},
|
|
{
|
|
"entropy": 5.5654683113098145,
|
|
"epoch": 0.7197043376774946,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004953697646088712,
|
|
"loss": 5.3101,
|
|
"mean_token_accuracy": 0.1744338884949684,
|
|
"num_tokens": 16062987.0,
|
|
"step": 9250
|
|
},
|
|
{
|
|
"entropy": 5.558124971389771,
|
|
"epoch": 0.7200933670492122,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004953641691815891,
|
|
"loss": 5.2853,
|
|
"mean_token_accuracy": 0.1788240686058998,
|
|
"num_tokens": 16071247.0,
|
|
"step": 9255
|
|
},
|
|
{
|
|
"entropy": 5.530323934555054,
|
|
"epoch": 0.7204823964209298,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004953585704106315,
|
|
"loss": 5.2264,
|
|
"mean_token_accuracy": 0.1773939922451973,
|
|
"num_tokens": 16080190.0,
|
|
"step": 9260
|
|
},
|
|
{
|
|
"entropy": 5.575647354125977,
|
|
"epoch": 0.7208714257926473,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004953529682960832,
|
|
"loss": 5.3155,
|
|
"mean_token_accuracy": 0.17726240903139115,
|
|
"num_tokens": 16088885.0,
|
|
"step": 9265
|
|
},
|
|
{
|
|
"entropy": 5.561666536331177,
|
|
"epoch": 0.7212604551643649,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004953473628380295,
|
|
"loss": 5.2756,
|
|
"mean_token_accuracy": 0.17821484357118605,
|
|
"num_tokens": 16097202.0,
|
|
"step": 9270
|
|
},
|
|
{
|
|
"entropy": 5.588506174087525,
|
|
"epoch": 0.7216494845360825,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004953417540365553,
|
|
"loss": 5.2431,
|
|
"mean_token_accuracy": 0.18142793625593184,
|
|
"num_tokens": 16105468.0,
|
|
"step": 9275
|
|
},
|
|
{
|
|
"entropy": 5.64068570137024,
|
|
"epoch": 0.7220385139078,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004953361418917455,
|
|
"loss": 5.3979,
|
|
"mean_token_accuracy": 0.1801755577325821,
|
|
"num_tokens": 16114624.0,
|
|
"step": 9280
|
|
},
|
|
{
|
|
"entropy": 5.530179595947265,
|
|
"epoch": 0.7224275432795176,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004953305264036856,
|
|
"loss": 5.2353,
|
|
"mean_token_accuracy": 0.17767134457826614,
|
|
"num_tokens": 16123983.0,
|
|
"step": 9285
|
|
},
|
|
{
|
|
"entropy": 5.638651132583618,
|
|
"epoch": 0.7228165726512352,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004953249075724607,
|
|
"loss": 5.3471,
|
|
"mean_token_accuracy": 0.17877227663993836,
|
|
"num_tokens": 16132886.0,
|
|
"step": 9290
|
|
},
|
|
{
|
|
"entropy": 5.554377841949463,
|
|
"epoch": 0.7232056020229527,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004953192853981559,
|
|
"loss": 5.1984,
|
|
"mean_token_accuracy": 0.1873273730278015,
|
|
"num_tokens": 16141526.0,
|
|
"step": 9295
|
|
},
|
|
{
|
|
"entropy": 5.576457214355469,
|
|
"epoch": 0.7235946313946703,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004953136598808566,
|
|
"loss": 5.3813,
|
|
"mean_token_accuracy": 0.18493103832006455,
|
|
"num_tokens": 16149949.0,
|
|
"step": 9300
|
|
},
|
|
{
|
|
"entropy": 5.608815240859985,
|
|
"epoch": 0.7239836607663879,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004953080310206481,
|
|
"loss": 5.3449,
|
|
"mean_token_accuracy": 0.17716638147830963,
|
|
"num_tokens": 16158131.0,
|
|
"step": 9305
|
|
},
|
|
{
|
|
"entropy": 5.501528787612915,
|
|
"epoch": 0.7243726901381055,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004953023988176162,
|
|
"loss": 5.2499,
|
|
"mean_token_accuracy": 0.17929585576057433,
|
|
"num_tokens": 16167131.0,
|
|
"step": 9310
|
|
},
|
|
{
|
|
"entropy": 5.6442553997039795,
|
|
"epoch": 0.724761719509823,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004952967632718458,
|
|
"loss": 5.4633,
|
|
"mean_token_accuracy": 0.1731911689043045,
|
|
"num_tokens": 16176198.0,
|
|
"step": 9315
|
|
},
|
|
{
|
|
"entropy": 5.592202043533325,
|
|
"epoch": 0.7251507488815405,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004952911243834227,
|
|
"loss": 5.3427,
|
|
"mean_token_accuracy": 0.17611104547977446,
|
|
"num_tokens": 16184860.0,
|
|
"step": 9320
|
|
},
|
|
{
|
|
"entropy": 5.593503427505493,
|
|
"epoch": 0.7255397782532581,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004952854821524324,
|
|
"loss": 5.328,
|
|
"mean_token_accuracy": 0.17426833510398865,
|
|
"num_tokens": 16193126.0,
|
|
"step": 9325
|
|
},
|
|
{
|
|
"entropy": 5.5762348651885985,
|
|
"epoch": 0.7259288076249757,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004952798365789606,
|
|
"loss": 5.3067,
|
|
"mean_token_accuracy": 0.17548383623361588,
|
|
"num_tokens": 16201763.0,
|
|
"step": 9330
|
|
},
|
|
{
|
|
"entropy": 5.575831174850464,
|
|
"epoch": 0.7263178369966933,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004952741876630928,
|
|
"loss": 5.2582,
|
|
"mean_token_accuracy": 0.18297910690307617,
|
|
"num_tokens": 16210947.0,
|
|
"step": 9335
|
|
},
|
|
{
|
|
"entropy": 5.614086771011353,
|
|
"epoch": 0.7267068663684109,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004952685354049148,
|
|
"loss": 5.3308,
|
|
"mean_token_accuracy": 0.17360346168279647,
|
|
"num_tokens": 16219772.0,
|
|
"step": 9340
|
|
},
|
|
{
|
|
"entropy": 5.637112236022949,
|
|
"epoch": 0.7270958957401283,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004952628798045124,
|
|
"loss": 5.3211,
|
|
"mean_token_accuracy": 0.18236895203590392,
|
|
"num_tokens": 16227759.0,
|
|
"step": 9345
|
|
},
|
|
{
|
|
"entropy": 5.549534940719605,
|
|
"epoch": 0.7274849251118459,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004952572208619714,
|
|
"loss": 5.2177,
|
|
"mean_token_accuracy": 0.17939460426568984,
|
|
"num_tokens": 16236913.0,
|
|
"step": 9350
|
|
},
|
|
{
|
|
"entropy": 5.581374168395996,
|
|
"epoch": 0.7278739544835635,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004952515585773778,
|
|
"loss": 5.3427,
|
|
"mean_token_accuracy": 0.17206512838602067,
|
|
"num_tokens": 16246190.0,
|
|
"step": 9355
|
|
},
|
|
{
|
|
"entropy": 5.5773841381073,
|
|
"epoch": 0.7282629838552811,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004952458929508171,
|
|
"loss": 5.3031,
|
|
"mean_token_accuracy": 0.1751967504620552,
|
|
"num_tokens": 16255476.0,
|
|
"step": 9360
|
|
},
|
|
{
|
|
"entropy": 5.584682369232178,
|
|
"epoch": 0.7286520132269987,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004952402239823757,
|
|
"loss": 5.331,
|
|
"mean_token_accuracy": 0.1706559732556343,
|
|
"num_tokens": 16264701.0,
|
|
"step": 9365
|
|
},
|
|
{
|
|
"entropy": 5.441281652450561,
|
|
"epoch": 0.7290410425987162,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004952345516721393,
|
|
"loss": 5.1648,
|
|
"mean_token_accuracy": 0.18849799335002898,
|
|
"num_tokens": 16272999.0,
|
|
"step": 9370
|
|
},
|
|
{
|
|
"entropy": 5.66496958732605,
|
|
"epoch": 0.7294300719704337,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004952288760201942,
|
|
"loss": 5.4418,
|
|
"mean_token_accuracy": 0.17025233134627343,
|
|
"num_tokens": 16282537.0,
|
|
"step": 9375
|
|
},
|
|
{
|
|
"entropy": 5.633242988586426,
|
|
"epoch": 0.7298191013421513,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004952231970266265,
|
|
"loss": 5.3001,
|
|
"mean_token_accuracy": 0.17955290973186494,
|
|
"num_tokens": 16291155.0,
|
|
"step": 9380
|
|
},
|
|
{
|
|
"entropy": 5.643191957473755,
|
|
"epoch": 0.7302081307138689,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004952175146915223,
|
|
"loss": 5.3829,
|
|
"mean_token_accuracy": 0.1692135140299797,
|
|
"num_tokens": 16300466.0,
|
|
"step": 9385
|
|
},
|
|
{
|
|
"entropy": 5.596168661117554,
|
|
"epoch": 0.7305971600855865,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004952118290149679,
|
|
"loss": 5.2849,
|
|
"mean_token_accuracy": 0.1738765999674797,
|
|
"num_tokens": 16309250.0,
|
|
"step": 9390
|
|
},
|
|
{
|
|
"entropy": 5.647305631637574,
|
|
"epoch": 0.730986189457304,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004952061399970492,
|
|
"loss": 5.3829,
|
|
"mean_token_accuracy": 0.17449599206447602,
|
|
"num_tokens": 16318056.0,
|
|
"step": 9395
|
|
},
|
|
{
|
|
"entropy": 5.538020944595337,
|
|
"epoch": 0.7313752188290216,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000495200447637853,
|
|
"loss": 5.2386,
|
|
"mean_token_accuracy": 0.17811905592679977,
|
|
"num_tokens": 16326455.0,
|
|
"step": 9400
|
|
},
|
|
{
|
|
"entropy": 5.510137224197388,
|
|
"epoch": 0.7317642482007392,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004951947519374655,
|
|
"loss": 5.227,
|
|
"mean_token_accuracy": 0.18160680383443834,
|
|
"num_tokens": 16334584.0,
|
|
"step": 9405
|
|
},
|
|
{
|
|
"entropy": 5.5503466606140135,
|
|
"epoch": 0.7321532775724567,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004951890528959731,
|
|
"loss": 5.2573,
|
|
"mean_token_accuracy": 0.18433501571416855,
|
|
"num_tokens": 16342361.0,
|
|
"step": 9410
|
|
},
|
|
{
|
|
"entropy": 5.635887479782104,
|
|
"epoch": 0.7325423069441743,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004951833505134623,
|
|
"loss": 5.3919,
|
|
"mean_token_accuracy": 0.17290140837430953,
|
|
"num_tokens": 16350414.0,
|
|
"step": 9415
|
|
},
|
|
{
|
|
"entropy": 5.500445413589477,
|
|
"epoch": 0.7329313363158918,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004951776447900196,
|
|
"loss": 5.2269,
|
|
"mean_token_accuracy": 0.18617474734783174,
|
|
"num_tokens": 16359266.0,
|
|
"step": 9420
|
|
},
|
|
{
|
|
"entropy": 5.4902732372283936,
|
|
"epoch": 0.7333203656876094,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004951719357257317,
|
|
"loss": 5.2058,
|
|
"mean_token_accuracy": 0.1826066866517067,
|
|
"num_tokens": 16367558.0,
|
|
"step": 9425
|
|
},
|
|
{
|
|
"entropy": 5.451519298553467,
|
|
"epoch": 0.733709395059327,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000495166223320685,
|
|
"loss": 5.1901,
|
|
"mean_token_accuracy": 0.184382164478302,
|
|
"num_tokens": 16375690.0,
|
|
"step": 9430
|
|
},
|
|
{
|
|
"entropy": 5.5959672927856445,
|
|
"epoch": 0.7340984244310446,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004951605075749662,
|
|
"loss": 5.3103,
|
|
"mean_token_accuracy": 0.17972762435674666,
|
|
"num_tokens": 16384157.0,
|
|
"step": 9435
|
|
},
|
|
{
|
|
"entropy": 5.613910102844239,
|
|
"epoch": 0.7344874538027621,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004951547884886623,
|
|
"loss": 5.3572,
|
|
"mean_token_accuracy": 0.18060232400894166,
|
|
"num_tokens": 16392153.0,
|
|
"step": 9440
|
|
},
|
|
{
|
|
"entropy": 5.457367038726806,
|
|
"epoch": 0.7348764831744796,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004951490660618598,
|
|
"loss": 5.1221,
|
|
"mean_token_accuracy": 0.1908814549446106,
|
|
"num_tokens": 16400132.0,
|
|
"step": 9445
|
|
},
|
|
{
|
|
"entropy": 5.553274536132813,
|
|
"epoch": 0.7352655125461972,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004951433402946457,
|
|
"loss": 5.2937,
|
|
"mean_token_accuracy": 0.18400580137968064,
|
|
"num_tokens": 16408297.0,
|
|
"step": 9450
|
|
},
|
|
{
|
|
"entropy": 5.5737401962280275,
|
|
"epoch": 0.7356545419179148,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004951376111871068,
|
|
"loss": 5.3443,
|
|
"mean_token_accuracy": 0.17686122059822082,
|
|
"num_tokens": 16417977.0,
|
|
"step": 9455
|
|
},
|
|
{
|
|
"entropy": 5.58512773513794,
|
|
"epoch": 0.7360435712896324,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004951318787393299,
|
|
"loss": 5.2265,
|
|
"mean_token_accuracy": 0.18320877254009246,
|
|
"num_tokens": 16427156.0,
|
|
"step": 9460
|
|
},
|
|
{
|
|
"entropy": 5.64531135559082,
|
|
"epoch": 0.73643260066135,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004951261429514023,
|
|
"loss": 5.4389,
|
|
"mean_token_accuracy": 0.16900589615106582,
|
|
"num_tokens": 16435845.0,
|
|
"step": 9465
|
|
},
|
|
{
|
|
"entropy": 5.6111023902893065,
|
|
"epoch": 0.7368216300330674,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004951204038234106,
|
|
"loss": 5.3945,
|
|
"mean_token_accuracy": 0.17545305341482162,
|
|
"num_tokens": 16445876.0,
|
|
"step": 9470
|
|
},
|
|
{
|
|
"entropy": 5.601052713394165,
|
|
"epoch": 0.737210659404785,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004951146613554424,
|
|
"loss": 5.3357,
|
|
"mean_token_accuracy": 0.18090222775936127,
|
|
"num_tokens": 16454688.0,
|
|
"step": 9475
|
|
},
|
|
{
|
|
"entropy": 5.642931413650513,
|
|
"epoch": 0.7375996887765026,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004951089155475843,
|
|
"loss": 5.4152,
|
|
"mean_token_accuracy": 0.16919267326593398,
|
|
"num_tokens": 16463932.0,
|
|
"step": 9480
|
|
},
|
|
{
|
|
"entropy": 5.616369152069092,
|
|
"epoch": 0.7379887181482202,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000495103166399924,
|
|
"loss": 5.3242,
|
|
"mean_token_accuracy": 0.17350419461727143,
|
|
"num_tokens": 16472627.0,
|
|
"step": 9485
|
|
},
|
|
{
|
|
"entropy": 5.644665336608886,
|
|
"epoch": 0.7383777475199378,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004950974139125484,
|
|
"loss": 5.3634,
|
|
"mean_token_accuracy": 0.17660223096609115,
|
|
"num_tokens": 16480819.0,
|
|
"step": 9490
|
|
},
|
|
{
|
|
"entropy": 5.600194644927979,
|
|
"epoch": 0.7387667768916554,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004950916580855448,
|
|
"loss": 5.3286,
|
|
"mean_token_accuracy": 0.17571170181035994,
|
|
"num_tokens": 16489055.0,
|
|
"step": 9495
|
|
},
|
|
{
|
|
"entropy": 5.548560953140258,
|
|
"epoch": 0.7391558062633728,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004950858989190007,
|
|
"loss": 5.3297,
|
|
"mean_token_accuracy": 0.1835804373025894,
|
|
"num_tokens": 16497375.0,
|
|
"step": 9500
|
|
},
|
|
{
|
|
"entropy": 5.493134450912476,
|
|
"epoch": 0.7395448356350904,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004950801364130032,
|
|
"loss": 5.1607,
|
|
"mean_token_accuracy": 0.18572535663843154,
|
|
"num_tokens": 16505183.0,
|
|
"step": 9505
|
|
},
|
|
{
|
|
"entropy": 5.597559452056885,
|
|
"epoch": 0.739933865006808,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004950743705676401,
|
|
"loss": 5.4381,
|
|
"mean_token_accuracy": 0.16902757957577705,
|
|
"num_tokens": 16514018.0,
|
|
"step": 9510
|
|
},
|
|
{
|
|
"entropy": 5.615971994400025,
|
|
"epoch": 0.7403228943785256,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004950686013829987,
|
|
"loss": 5.3076,
|
|
"mean_token_accuracy": 0.18013171702623368,
|
|
"num_tokens": 16522954.0,
|
|
"step": 9515
|
|
},
|
|
{
|
|
"entropy": 5.71082763671875,
|
|
"epoch": 0.7407119237502432,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004950628288591665,
|
|
"loss": 5.3547,
|
|
"mean_token_accuracy": 0.17512065768241883,
|
|
"num_tokens": 16530845.0,
|
|
"step": 9520
|
|
},
|
|
{
|
|
"entropy": 5.565211915969849,
|
|
"epoch": 0.7411009531219607,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004950570529962311,
|
|
"loss": 5.3313,
|
|
"mean_token_accuracy": 0.1752915546298027,
|
|
"num_tokens": 16540464.0,
|
|
"step": 9525
|
|
},
|
|
{
|
|
"entropy": 5.473846054077148,
|
|
"epoch": 0.7414899824936783,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004950512737942803,
|
|
"loss": 5.2103,
|
|
"mean_token_accuracy": 0.18890926241874695,
|
|
"num_tokens": 16549485.0,
|
|
"step": 9530
|
|
},
|
|
{
|
|
"entropy": 5.6329456806182865,
|
|
"epoch": 0.7418790118653958,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004950454912534015,
|
|
"loss": 5.3656,
|
|
"mean_token_accuracy": 0.17809097170829774,
|
|
"num_tokens": 16557854.0,
|
|
"step": 9535
|
|
},
|
|
{
|
|
"entropy": 5.635037088394165,
|
|
"epoch": 0.7422680412371134,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004950397053736827,
|
|
"loss": 5.3982,
|
|
"mean_token_accuracy": 0.17356866598129272,
|
|
"num_tokens": 16565975.0,
|
|
"step": 9540
|
|
},
|
|
{
|
|
"entropy": 5.603233718872071,
|
|
"epoch": 0.742657070608831,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004950339161552117,
|
|
"loss": 5.366,
|
|
"mean_token_accuracy": 0.17709572613239288,
|
|
"num_tokens": 16575038.0,
|
|
"step": 9545
|
|
},
|
|
{
|
|
"entropy": 5.536765909194946,
|
|
"epoch": 0.7430460999805485,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004950281235980761,
|
|
"loss": 5.2234,
|
|
"mean_token_accuracy": 0.18227089196443558,
|
|
"num_tokens": 16584292.0,
|
|
"step": 9550
|
|
},
|
|
{
|
|
"entropy": 5.583617877960205,
|
|
"epoch": 0.7434351293522661,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000495022327702364,
|
|
"loss": 5.3176,
|
|
"mean_token_accuracy": 0.1783987820148468,
|
|
"num_tokens": 16592331.0,
|
|
"step": 9555
|
|
},
|
|
{
|
|
"entropy": 5.557074785232544,
|
|
"epoch": 0.7438241587239837,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004950165284681631,
|
|
"loss": 5.2694,
|
|
"mean_token_accuracy": 0.17992899864912032,
|
|
"num_tokens": 16601845.0,
|
|
"step": 9560
|
|
},
|
|
{
|
|
"entropy": 5.584936475753784,
|
|
"epoch": 0.7442131880957013,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004950107258955618,
|
|
"loss": 5.3511,
|
|
"mean_token_accuracy": 0.17872835099697112,
|
|
"num_tokens": 16610438.0,
|
|
"step": 9565
|
|
},
|
|
{
|
|
"entropy": 5.540927791595459,
|
|
"epoch": 0.7446022174674188,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004950049199846479,
|
|
"loss": 5.2705,
|
|
"mean_token_accuracy": 0.18069363981485367,
|
|
"num_tokens": 16618892.0,
|
|
"step": 9570
|
|
},
|
|
{
|
|
"entropy": 5.639248418807983,
|
|
"epoch": 0.7449912468391363,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004949991107355095,
|
|
"loss": 5.3096,
|
|
"mean_token_accuracy": 0.17804142832756042,
|
|
"num_tokens": 16627702.0,
|
|
"step": 9575
|
|
},
|
|
{
|
|
"entropy": 5.51157283782959,
|
|
"epoch": 0.7453802762108539,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004949932981482347,
|
|
"loss": 5.2218,
|
|
"mean_token_accuracy": 0.18788692057132722,
|
|
"num_tokens": 16635653.0,
|
|
"step": 9580
|
|
},
|
|
{
|
|
"entropy": 5.5664544105529785,
|
|
"epoch": 0.7457693055825715,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004949874822229118,
|
|
"loss": 5.3531,
|
|
"mean_token_accuracy": 0.18009264767169952,
|
|
"num_tokens": 16643898.0,
|
|
"step": 9585
|
|
},
|
|
{
|
|
"entropy": 5.596207046508789,
|
|
"epoch": 0.7461583349542891,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004949816629596288,
|
|
"loss": 5.2252,
|
|
"mean_token_accuracy": 0.18270762860774994,
|
|
"num_tokens": 16653126.0,
|
|
"step": 9590
|
|
},
|
|
{
|
|
"entropy": 5.656696367263794,
|
|
"epoch": 0.7465473643260067,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004949758403584746,
|
|
"loss": 5.3469,
|
|
"mean_token_accuracy": 0.1753896027803421,
|
|
"num_tokens": 16661561.0,
|
|
"step": 9595
|
|
},
|
|
{
|
|
"entropy": 5.544621753692627,
|
|
"epoch": 0.7469363936977241,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004949700144195368,
|
|
"loss": 5.3028,
|
|
"mean_token_accuracy": 0.17755116224288942,
|
|
"num_tokens": 16669657.0,
|
|
"step": 9600
|
|
},
|
|
{
|
|
"entropy": 5.519941425323486,
|
|
"epoch": 0.7473254230694417,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004949641851429043,
|
|
"loss": 5.3038,
|
|
"mean_token_accuracy": 0.1791791334748268,
|
|
"num_tokens": 16678486.0,
|
|
"step": 9605
|
|
},
|
|
{
|
|
"entropy": 5.595032501220703,
|
|
"epoch": 0.7477144524411593,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004949583525286654,
|
|
"loss": 5.2735,
|
|
"mean_token_accuracy": 0.177974633872509,
|
|
"num_tokens": 16686638.0,
|
|
"step": 9610
|
|
},
|
|
{
|
|
"entropy": 5.594528484344482,
|
|
"epoch": 0.7481034818128769,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004949525165769085,
|
|
"loss": 5.2215,
|
|
"mean_token_accuracy": 0.17921450287103652,
|
|
"num_tokens": 16694393.0,
|
|
"step": 9615
|
|
},
|
|
{
|
|
"entropy": 5.568652772903443,
|
|
"epoch": 0.7484925111845945,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004949466772877224,
|
|
"loss": 5.2646,
|
|
"mean_token_accuracy": 0.18511301875114441,
|
|
"num_tokens": 16702613.0,
|
|
"step": 9620
|
|
},
|
|
{
|
|
"entropy": 5.561077070236206,
|
|
"epoch": 0.748881540556312,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004949408346611955,
|
|
"loss": 5.2364,
|
|
"mean_token_accuracy": 0.18199257850646972,
|
|
"num_tokens": 16711210.0,
|
|
"step": 9625
|
|
},
|
|
{
|
|
"entropy": 5.564145612716675,
|
|
"epoch": 0.7492705699280295,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004949349886974165,
|
|
"loss": 5.2972,
|
|
"mean_token_accuracy": 0.1834089621901512,
|
|
"num_tokens": 16719124.0,
|
|
"step": 9630
|
|
},
|
|
{
|
|
"entropy": 5.600499248504638,
|
|
"epoch": 0.7496595992997471,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004949291393964741,
|
|
"loss": 5.2676,
|
|
"mean_token_accuracy": 0.17806679606437684,
|
|
"num_tokens": 16727240.0,
|
|
"step": 9635
|
|
},
|
|
{
|
|
"entropy": 5.576705551147461,
|
|
"epoch": 0.7500486286714647,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000494923286758457,
|
|
"loss": 5.38,
|
|
"mean_token_accuracy": 0.17818381488323212,
|
|
"num_tokens": 16736524.0,
|
|
"step": 9640
|
|
},
|
|
{
|
|
"entropy": 5.704974842071533,
|
|
"epoch": 0.7504376580431823,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004949174307834541,
|
|
"loss": 5.4922,
|
|
"mean_token_accuracy": 0.16476022750139235,
|
|
"num_tokens": 16745798.0,
|
|
"step": 9645
|
|
},
|
|
{
|
|
"entropy": 5.589550638198853,
|
|
"epoch": 0.7508266874148998,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004949115714715543,
|
|
"loss": 5.2774,
|
|
"mean_token_accuracy": 0.18031025826931,
|
|
"num_tokens": 16754263.0,
|
|
"step": 9650
|
|
},
|
|
{
|
|
"entropy": 5.509631538391114,
|
|
"epoch": 0.7512157167866174,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004949057088228465,
|
|
"loss": 5.1671,
|
|
"mean_token_accuracy": 0.18788377642631532,
|
|
"num_tokens": 16762610.0,
|
|
"step": 9655
|
|
},
|
|
{
|
|
"entropy": 5.587539911270142,
|
|
"epoch": 0.751604746158335,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004948998428374194,
|
|
"loss": 5.3813,
|
|
"mean_token_accuracy": 0.17164374738931656,
|
|
"num_tokens": 16771436.0,
|
|
"step": 9660
|
|
},
|
|
{
|
|
"entropy": 5.6791328430175785,
|
|
"epoch": 0.7519937755300525,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004948939735153622,
|
|
"loss": 5.3954,
|
|
"mean_token_accuracy": 0.17684406042099,
|
|
"num_tokens": 16779647.0,
|
|
"step": 9665
|
|
},
|
|
{
|
|
"entropy": 5.666022825241089,
|
|
"epoch": 0.7523828049017701,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004948881008567641,
|
|
"loss": 5.352,
|
|
"mean_token_accuracy": 0.1790418267250061,
|
|
"num_tokens": 16788116.0,
|
|
"step": 9670
|
|
},
|
|
{
|
|
"entropy": 5.549437808990478,
|
|
"epoch": 0.7527718342734876,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004948822248617139,
|
|
"loss": 5.2878,
|
|
"mean_token_accuracy": 0.18091578632593155,
|
|
"num_tokens": 16796518.0,
|
|
"step": 9675
|
|
},
|
|
{
|
|
"entropy": 5.55680022239685,
|
|
"epoch": 0.7531608636452052,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000494876345530301,
|
|
"loss": 5.2654,
|
|
"mean_token_accuracy": 0.1813149034976959,
|
|
"num_tokens": 16805511.0,
|
|
"step": 9680
|
|
},
|
|
{
|
|
"entropy": 5.583335542678833,
|
|
"epoch": 0.7535498930169228,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004948704628626145,
|
|
"loss": 5.282,
|
|
"mean_token_accuracy": 0.17796677052974702,
|
|
"num_tokens": 16813173.0,
|
|
"step": 9685
|
|
},
|
|
{
|
|
"entropy": 5.627739143371582,
|
|
"epoch": 0.7539389223886404,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004948645768587437,
|
|
"loss": 5.3799,
|
|
"mean_token_accuracy": 0.17010469883680343,
|
|
"num_tokens": 16822193.0,
|
|
"step": 9690
|
|
},
|
|
{
|
|
"entropy": 5.518557786941528,
|
|
"epoch": 0.7543279517603579,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004948586875187778,
|
|
"loss": 5.1055,
|
|
"mean_token_accuracy": 0.1896416053175926,
|
|
"num_tokens": 16830421.0,
|
|
"step": 9695
|
|
},
|
|
{
|
|
"entropy": 5.56982102394104,
|
|
"epoch": 0.7547169811320755,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004948527948428064,
|
|
"loss": 5.2132,
|
|
"mean_token_accuracy": 0.18295853286981584,
|
|
"num_tokens": 16838988.0,
|
|
"step": 9700
|
|
},
|
|
{
|
|
"entropy": 5.534185743331909,
|
|
"epoch": 0.755106010503793,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004948468988309187,
|
|
"loss": 5.35,
|
|
"mean_token_accuracy": 0.17599449008703233,
|
|
"num_tokens": 16847980.0,
|
|
"step": 9705
|
|
},
|
|
{
|
|
"entropy": 5.496274757385254,
|
|
"epoch": 0.7554950398755106,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004948409994832043,
|
|
"loss": 5.2328,
|
|
"mean_token_accuracy": 0.18318645805120468,
|
|
"num_tokens": 16857263.0,
|
|
"step": 9710
|
|
},
|
|
{
|
|
"entropy": 5.592087888717652,
|
|
"epoch": 0.7558840692472282,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004948350967997526,
|
|
"loss": 5.2375,
|
|
"mean_token_accuracy": 0.1804831087589264,
|
|
"num_tokens": 16865314.0,
|
|
"step": 9715
|
|
},
|
|
{
|
|
"entropy": 5.618679857254028,
|
|
"epoch": 0.7562730986189458,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004948291907806532,
|
|
"loss": 5.3287,
|
|
"mean_token_accuracy": 0.18105187863111497,
|
|
"num_tokens": 16875359.0,
|
|
"step": 9720
|
|
},
|
|
{
|
|
"entropy": 5.626615762710571,
|
|
"epoch": 0.7566621279906633,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004948232814259957,
|
|
"loss": 5.4465,
|
|
"mean_token_accuracy": 0.16737451404333115,
|
|
"num_tokens": 16885279.0,
|
|
"step": 9725
|
|
},
|
|
{
|
|
"entropy": 5.67550139427185,
|
|
"epoch": 0.7570511573623808,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004948173687358699,
|
|
"loss": 5.3648,
|
|
"mean_token_accuracy": 0.17636879682540893,
|
|
"num_tokens": 16894463.0,
|
|
"step": 9730
|
|
},
|
|
{
|
|
"entropy": 5.615520334243774,
|
|
"epoch": 0.7574401867340984,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004948114527103652,
|
|
"loss": 5.3019,
|
|
"mean_token_accuracy": 0.16981316953897477,
|
|
"num_tokens": 16903378.0,
|
|
"step": 9735
|
|
},
|
|
{
|
|
"entropy": 5.568920230865478,
|
|
"epoch": 0.757829216105816,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004948055333495717,
|
|
"loss": 5.3493,
|
|
"mean_token_accuracy": 0.17093088179826738,
|
|
"num_tokens": 16912039.0,
|
|
"step": 9740
|
|
},
|
|
{
|
|
"entropy": 5.553165483474731,
|
|
"epoch": 0.7582182454775336,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004947996106535791,
|
|
"loss": 5.2949,
|
|
"mean_token_accuracy": 0.17178265303373336,
|
|
"num_tokens": 16920516.0,
|
|
"step": 9745
|
|
},
|
|
{
|
|
"entropy": 5.661890935897827,
|
|
"epoch": 0.7586072748492512,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004947936846224773,
|
|
"loss": 5.3096,
|
|
"mean_token_accuracy": 0.17241132408380508,
|
|
"num_tokens": 16929131.0,
|
|
"step": 9750
|
|
},
|
|
{
|
|
"entropy": 5.539224529266358,
|
|
"epoch": 0.7589963042209686,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004947877552563562,
|
|
"loss": 5.3331,
|
|
"mean_token_accuracy": 0.18203827887773513,
|
|
"num_tokens": 16937352.0,
|
|
"step": 9755
|
|
},
|
|
{
|
|
"entropy": 5.593630933761597,
|
|
"epoch": 0.7593853335926862,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004947818225553056,
|
|
"loss": 5.4071,
|
|
"mean_token_accuracy": 0.17220403701066972,
|
|
"num_tokens": 16946439.0,
|
|
"step": 9760
|
|
},
|
|
{
|
|
"entropy": 5.6424661636352536,
|
|
"epoch": 0.7597743629644038,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004947758865194156,
|
|
"loss": 5.2918,
|
|
"mean_token_accuracy": 0.17695994526147843,
|
|
"num_tokens": 16955402.0,
|
|
"step": 9765
|
|
},
|
|
{
|
|
"entropy": 5.495573997497559,
|
|
"epoch": 0.7601633923361214,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004947699471487766,
|
|
"loss": 5.2244,
|
|
"mean_token_accuracy": 0.18328388929367065,
|
|
"num_tokens": 16964299.0,
|
|
"step": 9770
|
|
},
|
|
{
|
|
"entropy": 5.50468430519104,
|
|
"epoch": 0.760552421707839,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004947640044434782,
|
|
"loss": 5.2758,
|
|
"mean_token_accuracy": 0.17400199323892593,
|
|
"num_tokens": 16973483.0,
|
|
"step": 9775
|
|
},
|
|
{
|
|
"entropy": 5.590785169601441,
|
|
"epoch": 0.7609414510795565,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004947580584036109,
|
|
"loss": 5.3239,
|
|
"mean_token_accuracy": 0.18279939740896226,
|
|
"num_tokens": 16982234.0,
|
|
"step": 9780
|
|
},
|
|
{
|
|
"entropy": 5.581445789337158,
|
|
"epoch": 0.761330480451274,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004947521090292649,
|
|
"loss": 5.2892,
|
|
"mean_token_accuracy": 0.1782561406493187,
|
|
"num_tokens": 16990669.0,
|
|
"step": 9785
|
|
},
|
|
{
|
|
"entropy": 5.648339176177979,
|
|
"epoch": 0.7617195098229916,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004947461563205304,
|
|
"loss": 5.3507,
|
|
"mean_token_accuracy": 0.17734525352716446,
|
|
"num_tokens": 16999998.0,
|
|
"step": 9790
|
|
},
|
|
{
|
|
"entropy": 5.661034297943115,
|
|
"epoch": 0.7621085391947092,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004947402002774977,
|
|
"loss": 5.3529,
|
|
"mean_token_accuracy": 0.1741270527243614,
|
|
"num_tokens": 17008518.0,
|
|
"step": 9795
|
|
},
|
|
{
|
|
"entropy": 5.543142318725586,
|
|
"epoch": 0.7624975685664268,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004947342409002572,
|
|
"loss": 5.2809,
|
|
"mean_token_accuracy": 0.17424834668636321,
|
|
"num_tokens": 17017182.0,
|
|
"step": 9800
|
|
},
|
|
{
|
|
"entropy": 5.565796613693237,
|
|
"epoch": 0.7628865979381443,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004947282781888994,
|
|
"loss": 5.2961,
|
|
"mean_token_accuracy": 0.17821226865053177,
|
|
"num_tokens": 17026186.0,
|
|
"step": 9805
|
|
},
|
|
{
|
|
"entropy": 5.473713350296021,
|
|
"epoch": 0.7632756273098619,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004947223121435147,
|
|
"loss": 5.175,
|
|
"mean_token_accuracy": 0.19047538787126542,
|
|
"num_tokens": 17034295.0,
|
|
"step": 9810
|
|
},
|
|
{
|
|
"entropy": 5.44863224029541,
|
|
"epoch": 0.7636646566815795,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004947163427641936,
|
|
"loss": 5.252,
|
|
"mean_token_accuracy": 0.17861233055591583,
|
|
"num_tokens": 17043195.0,
|
|
"step": 9815
|
|
},
|
|
{
|
|
"entropy": 5.518514013290405,
|
|
"epoch": 0.764053686053297,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004947103700510268,
|
|
"loss": 5.1959,
|
|
"mean_token_accuracy": 0.17903678566217424,
|
|
"num_tokens": 17051903.0,
|
|
"step": 9820
|
|
},
|
|
{
|
|
"entropy": 5.539800930023193,
|
|
"epoch": 0.7644427154250146,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004947043940041047,
|
|
"loss": 5.2636,
|
|
"mean_token_accuracy": 0.1832680806517601,
|
|
"num_tokens": 17060495.0,
|
|
"step": 9825
|
|
},
|
|
{
|
|
"entropy": 5.601056957244873,
|
|
"epoch": 0.7648317447967321,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004946984146235183,
|
|
"loss": 5.3227,
|
|
"mean_token_accuracy": 0.17461752742528916,
|
|
"num_tokens": 17069254.0,
|
|
"step": 9830
|
|
},
|
|
{
|
|
"entropy": 5.6530539989471436,
|
|
"epoch": 0.7652207741684497,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004946924319093579,
|
|
"loss": 5.2799,
|
|
"mean_token_accuracy": 0.17788524329662322,
|
|
"num_tokens": 17077323.0,
|
|
"step": 9835
|
|
},
|
|
{
|
|
"entropy": 5.529206657409668,
|
|
"epoch": 0.7656098035401673,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004946864458617148,
|
|
"loss": 5.169,
|
|
"mean_token_accuracy": 0.18858975172042847,
|
|
"num_tokens": 17085377.0,
|
|
"step": 9840
|
|
},
|
|
{
|
|
"entropy": 5.500270652770996,
|
|
"epoch": 0.7659988329118849,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004946804564806793,
|
|
"loss": 5.242,
|
|
"mean_token_accuracy": 0.17937949299812317,
|
|
"num_tokens": 17094288.0,
|
|
"step": 9845
|
|
},
|
|
{
|
|
"entropy": 5.571313285827637,
|
|
"epoch": 0.7663878622836025,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004946744637663427,
|
|
"loss": 5.1776,
|
|
"mean_token_accuracy": 0.18991186916828157,
|
|
"num_tokens": 17101572.0,
|
|
"step": 9850
|
|
},
|
|
{
|
|
"entropy": 5.549397754669189,
|
|
"epoch": 0.7667768916553199,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004946684677187956,
|
|
"loss": 5.315,
|
|
"mean_token_accuracy": 0.1745953306555748,
|
|
"num_tokens": 17110151.0,
|
|
"step": 9855
|
|
},
|
|
{
|
|
"entropy": 5.60110821723938,
|
|
"epoch": 0.7671659210270375,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004946624683381292,
|
|
"loss": 5.3045,
|
|
"mean_token_accuracy": 0.17201686799526214,
|
|
"num_tokens": 17118172.0,
|
|
"step": 9860
|
|
},
|
|
{
|
|
"entropy": 5.522176218032837,
|
|
"epoch": 0.7675549503987551,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004946564656244345,
|
|
"loss": 5.1812,
|
|
"mean_token_accuracy": 0.18621729910373688,
|
|
"num_tokens": 17126855.0,
|
|
"step": 9865
|
|
},
|
|
{
|
|
"entropy": 5.602323389053344,
|
|
"epoch": 0.7679439797704727,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004946504595778026,
|
|
"loss": 5.3748,
|
|
"mean_token_accuracy": 0.17457078397274017,
|
|
"num_tokens": 17135737.0,
|
|
"step": 9870
|
|
},
|
|
{
|
|
"entropy": 5.64451322555542,
|
|
"epoch": 0.7683330091421903,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004946444501983246,
|
|
"loss": 5.3098,
|
|
"mean_token_accuracy": 0.17592848539352418,
|
|
"num_tokens": 17144521.0,
|
|
"step": 9875
|
|
},
|
|
{
|
|
"entropy": 5.6431746006011965,
|
|
"epoch": 0.7687220385139077,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004946384374860916,
|
|
"loss": 5.3946,
|
|
"mean_token_accuracy": 0.1757023736834526,
|
|
"num_tokens": 17153534.0,
|
|
"step": 9880
|
|
},
|
|
{
|
|
"entropy": 5.52467942237854,
|
|
"epoch": 0.7691110678856253,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004946324214411949,
|
|
"loss": 5.2258,
|
|
"mean_token_accuracy": 0.1848434701561928,
|
|
"num_tokens": 17162600.0,
|
|
"step": 9885
|
|
},
|
|
{
|
|
"entropy": 5.569587516784668,
|
|
"epoch": 0.7695000972573429,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004946264020637259,
|
|
"loss": 5.3193,
|
|
"mean_token_accuracy": 0.17557533234357833,
|
|
"num_tokens": 17171373.0,
|
|
"step": 9890
|
|
},
|
|
{
|
|
"entropy": 5.632002305984497,
|
|
"epoch": 0.7698891266290605,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004946203793537757,
|
|
"loss": 5.3351,
|
|
"mean_token_accuracy": 0.17728708386421205,
|
|
"num_tokens": 17180090.0,
|
|
"step": 9895
|
|
},
|
|
{
|
|
"entropy": 5.60519757270813,
|
|
"epoch": 0.7702781560007781,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004946143533114358,
|
|
"loss": 5.2577,
|
|
"mean_token_accuracy": 0.1822723478078842,
|
|
"num_tokens": 17189592.0,
|
|
"step": 9900
|
|
},
|
|
{
|
|
"entropy": 5.519287204742431,
|
|
"epoch": 0.7706671853724957,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004946083239367976,
|
|
"loss": 5.1972,
|
|
"mean_token_accuracy": 0.18773100078105925,
|
|
"num_tokens": 17198287.0,
|
|
"step": 9905
|
|
},
|
|
{
|
|
"entropy": 5.593173360824585,
|
|
"epoch": 0.7710562147442132,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004946022912299527,
|
|
"loss": 5.3013,
|
|
"mean_token_accuracy": 0.17522221207618713,
|
|
"num_tokens": 17206349.0,
|
|
"step": 9910
|
|
},
|
|
{
|
|
"entropy": 5.614915943145752,
|
|
"epoch": 0.7714452441159307,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004945962551909926,
|
|
"loss": 5.4031,
|
|
"mean_token_accuracy": 0.1742765948176384,
|
|
"num_tokens": 17215408.0,
|
|
"step": 9915
|
|
},
|
|
{
|
|
"entropy": 5.684574699401855,
|
|
"epoch": 0.7718342734876483,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004945902158200089,
|
|
"loss": 5.3549,
|
|
"mean_token_accuracy": 0.17250179797410964,
|
|
"num_tokens": 17224342.0,
|
|
"step": 9920
|
|
},
|
|
{
|
|
"entropy": 5.59126558303833,
|
|
"epoch": 0.7722233028593659,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004945841731170931,
|
|
"loss": 5.2355,
|
|
"mean_token_accuracy": 0.1765318751335144,
|
|
"num_tokens": 17232532.0,
|
|
"step": 9925
|
|
},
|
|
{
|
|
"entropy": 5.51690354347229,
|
|
"epoch": 0.7726123322310835,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004945781270823369,
|
|
"loss": 5.2437,
|
|
"mean_token_accuracy": 0.18184578269720078,
|
|
"num_tokens": 17240786.0,
|
|
"step": 9930
|
|
},
|
|
{
|
|
"entropy": 5.513026142120362,
|
|
"epoch": 0.773001361602801,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004945720777158323,
|
|
"loss": 5.2295,
|
|
"mean_token_accuracy": 0.18555503934621811,
|
|
"num_tokens": 17248515.0,
|
|
"step": 9935
|
|
},
|
|
{
|
|
"entropy": 5.591573333740234,
|
|
"epoch": 0.7733903909745186,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004945660250176708,
|
|
"loss": 5.276,
|
|
"mean_token_accuracy": 0.18310922980308533,
|
|
"num_tokens": 17257098.0,
|
|
"step": 9940
|
|
},
|
|
{
|
|
"entropy": 5.561489295959473,
|
|
"epoch": 0.7737794203462361,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004945599689879443,
|
|
"loss": 5.2754,
|
|
"mean_token_accuracy": 0.17605521529912949,
|
|
"num_tokens": 17266851.0,
|
|
"step": 9945
|
|
},
|
|
{
|
|
"entropy": 5.5478973388671875,
|
|
"epoch": 0.7741684497179537,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004945539096267448,
|
|
"loss": 5.2233,
|
|
"mean_token_accuracy": 0.17532940953969955,
|
|
"num_tokens": 17275568.0,
|
|
"step": 9950
|
|
},
|
|
{
|
|
"entropy": 5.525739049911499,
|
|
"epoch": 0.7745574790896713,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004945478469341642,
|
|
"loss": 5.1988,
|
|
"mean_token_accuracy": 0.18495745062828065,
|
|
"num_tokens": 17284528.0,
|
|
"step": 9955
|
|
},
|
|
{
|
|
"entropy": 5.606883478164673,
|
|
"epoch": 0.7749465084613888,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004945417809102944,
|
|
"loss": 5.3396,
|
|
"mean_token_accuracy": 0.1755354180932045,
|
|
"num_tokens": 17293973.0,
|
|
"step": 9960
|
|
},
|
|
{
|
|
"entropy": 5.524585103988647,
|
|
"epoch": 0.7753355378331064,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004945357115552275,
|
|
"loss": 5.2319,
|
|
"mean_token_accuracy": 0.17984241396188735,
|
|
"num_tokens": 17302321.0,
|
|
"step": 9965
|
|
},
|
|
{
|
|
"entropy": 5.580976581573486,
|
|
"epoch": 0.775724567204824,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004945296388690557,
|
|
"loss": 5.3504,
|
|
"mean_token_accuracy": 0.17670010775327682,
|
|
"num_tokens": 17311226.0,
|
|
"step": 9970
|
|
},
|
|
{
|
|
"entropy": 5.609677982330322,
|
|
"epoch": 0.7761135965765416,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000494523562851871,
|
|
"loss": 5.3277,
|
|
"mean_token_accuracy": 0.17759332209825515,
|
|
"num_tokens": 17319818.0,
|
|
"step": 9975
|
|
},
|
|
{
|
|
"entropy": 5.6251226425170895,
|
|
"epoch": 0.7765026259482591,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004945174835037655,
|
|
"loss": 5.3474,
|
|
"mean_token_accuracy": 0.17106997072696686,
|
|
"num_tokens": 17329195.0,
|
|
"step": 9980
|
|
},
|
|
{
|
|
"entropy": 5.650672054290771,
|
|
"epoch": 0.7768916553199766,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004945114008248319,
|
|
"loss": 5.4327,
|
|
"mean_token_accuracy": 0.17871665358543395,
|
|
"num_tokens": 17337689.0,
|
|
"step": 9985
|
|
},
|
|
{
|
|
"entropy": 5.582010173797608,
|
|
"epoch": 0.7772806846916942,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004945053148151619,
|
|
"loss": 5.1884,
|
|
"mean_token_accuracy": 0.18419857025146485,
|
|
"num_tokens": 17345467.0,
|
|
"step": 9990
|
|
},
|
|
{
|
|
"entropy": 5.548644399642944,
|
|
"epoch": 0.7776697140634118,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004944992254748482,
|
|
"loss": 5.3342,
|
|
"mean_token_accuracy": 0.1798410654067993,
|
|
"num_tokens": 17353651.0,
|
|
"step": 9995
|
|
},
|
|
{
|
|
"entropy": 5.608665990829468,
|
|
"epoch": 0.7780587434351294,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004944931328039832,
|
|
"loss": 5.3904,
|
|
"mean_token_accuracy": 0.17302385866641998,
|
|
"num_tokens": 17362777.0,
|
|
"step": 10000
|
|
},
|
|
{
|
|
"entropy": 5.664591360092163,
|
|
"epoch": 0.778447772806847,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004944870368026592,
|
|
"loss": 5.3237,
|
|
"mean_token_accuracy": 0.17910516113042832,
|
|
"num_tokens": 17371562.0,
|
|
"step": 10005
|
|
},
|
|
{
|
|
"entropy": 5.633160924911499,
|
|
"epoch": 0.7788368021785644,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004944809374709689,
|
|
"loss": 5.3136,
|
|
"mean_token_accuracy": 0.17074411660432814,
|
|
"num_tokens": 17381185.0,
|
|
"step": 10010
|
|
},
|
|
{
|
|
"entropy": 5.597475528717041,
|
|
"epoch": 0.779225831550282,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004944748348090045,
|
|
"loss": 5.279,
|
|
"mean_token_accuracy": 0.18732508569955825,
|
|
"num_tokens": 17390658.0,
|
|
"step": 10015
|
|
},
|
|
{
|
|
"entropy": 5.5473918437957765,
|
|
"epoch": 0.7796148609219996,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004944687288168589,
|
|
"loss": 5.2168,
|
|
"mean_token_accuracy": 0.17947004586458207,
|
|
"num_tokens": 17399968.0,
|
|
"step": 10020
|
|
},
|
|
{
|
|
"entropy": 5.587859106063843,
|
|
"epoch": 0.7800038902937172,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004944626194946246,
|
|
"loss": 5.3441,
|
|
"mean_token_accuracy": 0.1738036096096039,
|
|
"num_tokens": 17408727.0,
|
|
"step": 10025
|
|
},
|
|
{
|
|
"entropy": 5.583702516555786,
|
|
"epoch": 0.7803929196654348,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004944565068423945,
|
|
"loss": 5.3554,
|
|
"mean_token_accuracy": 0.17960301786661148,
|
|
"num_tokens": 17417517.0,
|
|
"step": 10030
|
|
},
|
|
{
|
|
"entropy": 5.6376337051391605,
|
|
"epoch": 0.7807819490371523,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004944503908602612,
|
|
"loss": 5.3434,
|
|
"mean_token_accuracy": 0.17666764408349991,
|
|
"num_tokens": 17427035.0,
|
|
"step": 10035
|
|
},
|
|
{
|
|
"entropy": 5.641467332839966,
|
|
"epoch": 0.7811709784088698,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004944442715483174,
|
|
"loss": 5.248,
|
|
"mean_token_accuracy": 0.1828450620174408,
|
|
"num_tokens": 17435585.0,
|
|
"step": 10040
|
|
},
|
|
{
|
|
"entropy": 5.551241016387939,
|
|
"epoch": 0.7815600077805874,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004944381489066561,
|
|
"loss": 5.2636,
|
|
"mean_token_accuracy": 0.18091956228017808,
|
|
"num_tokens": 17444317.0,
|
|
"step": 10045
|
|
},
|
|
{
|
|
"entropy": 5.620751953125,
|
|
"epoch": 0.781949037152305,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004944320229353702,
|
|
"loss": 5.4727,
|
|
"mean_token_accuracy": 0.17515989094972612,
|
|
"num_tokens": 17453585.0,
|
|
"step": 10050
|
|
},
|
|
{
|
|
"entropy": 5.586199188232422,
|
|
"epoch": 0.7823380665240226,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004944258936345526,
|
|
"loss": 5.2588,
|
|
"mean_token_accuracy": 0.18479428440332413,
|
|
"num_tokens": 17462233.0,
|
|
"step": 10055
|
|
},
|
|
{
|
|
"entropy": 5.549157810211182,
|
|
"epoch": 0.7827270958957401,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004944197610042963,
|
|
"loss": 5.1583,
|
|
"mean_token_accuracy": 0.1919889599084854,
|
|
"num_tokens": 17470566.0,
|
|
"step": 10060
|
|
},
|
|
{
|
|
"entropy": 5.556268930435181,
|
|
"epoch": 0.7831161252674577,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004944136250446944,
|
|
"loss": 5.2804,
|
|
"mean_token_accuracy": 0.1742836907505989,
|
|
"num_tokens": 17479267.0,
|
|
"step": 10065
|
|
},
|
|
{
|
|
"entropy": 5.4754805088043215,
|
|
"epoch": 0.7835051546391752,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004944074857558399,
|
|
"loss": 5.1722,
|
|
"mean_token_accuracy": 0.18835856914520263,
|
|
"num_tokens": 17488060.0,
|
|
"step": 10070
|
|
},
|
|
{
|
|
"entropy": 5.676930952072143,
|
|
"epoch": 0.7838941840108928,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004944013431378261,
|
|
"loss": 5.4177,
|
|
"mean_token_accuracy": 0.17947075963020326,
|
|
"num_tokens": 17497240.0,
|
|
"step": 10075
|
|
},
|
|
{
|
|
"entropy": 5.641529941558838,
|
|
"epoch": 0.7842832133826104,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004943951971907461,
|
|
"loss": 5.3746,
|
|
"mean_token_accuracy": 0.17811400294303895,
|
|
"num_tokens": 17506017.0,
|
|
"step": 10080
|
|
},
|
|
{
|
|
"entropy": 5.625462532043457,
|
|
"epoch": 0.7846722427543279,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004943890479146933,
|
|
"loss": 5.3175,
|
|
"mean_token_accuracy": 0.178188057243824,
|
|
"num_tokens": 17514764.0,
|
|
"step": 10085
|
|
},
|
|
{
|
|
"entropy": 5.547196388244629,
|
|
"epoch": 0.7850612721260455,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004943828953097607,
|
|
"loss": 5.2942,
|
|
"mean_token_accuracy": 0.1766573965549469,
|
|
"num_tokens": 17524183.0,
|
|
"step": 10090
|
|
},
|
|
{
|
|
"entropy": 5.552852392196655,
|
|
"epoch": 0.7854503014977631,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.000494376739376042,
|
|
"loss": 5.241,
|
|
"mean_token_accuracy": 0.18242752254009248,
|
|
"num_tokens": 17533426.0,
|
|
"step": 10095
|
|
},
|
|
{
|
|
"entropy": 5.61579270362854,
|
|
"epoch": 0.7858393308694807,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004943705801136304,
|
|
"loss": 5.1873,
|
|
"mean_token_accuracy": 0.1837708830833435,
|
|
"num_tokens": 17541966.0,
|
|
"step": 10100
|
|
},
|
|
{
|
|
"entropy": 5.587601232528686,
|
|
"epoch": 0.7862283602411982,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004943644175226193,
|
|
"loss": 5.2882,
|
|
"mean_token_accuracy": 0.1829829156398773,
|
|
"num_tokens": 17551157.0,
|
|
"step": 10105
|
|
},
|
|
{
|
|
"entropy": 5.52039270401001,
|
|
"epoch": 0.7866173896129158,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004943582516031025,
|
|
"loss": 5.2057,
|
|
"mean_token_accuracy": 0.1859710082411766,
|
|
"num_tokens": 17559999.0,
|
|
"step": 10110
|
|
},
|
|
{
|
|
"entropy": 5.581799268722534,
|
|
"epoch": 0.7870064189846333,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004943520823551732,
|
|
"loss": 5.2531,
|
|
"mean_token_accuracy": 0.18347948640584946,
|
|
"num_tokens": 17568873.0,
|
|
"step": 10115
|
|
},
|
|
{
|
|
"entropy": 5.5961323261260985,
|
|
"epoch": 0.7873954483563509,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004943459097789252,
|
|
"loss": 5.328,
|
|
"mean_token_accuracy": 0.1859396740794182,
|
|
"num_tokens": 17577807.0,
|
|
"step": 10120
|
|
},
|
|
{
|
|
"entropy": 5.599230861663818,
|
|
"epoch": 0.7877844777280685,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004943397338744523,
|
|
"loss": 5.3442,
|
|
"mean_token_accuracy": 0.17688045501708985,
|
|
"num_tokens": 17586646.0,
|
|
"step": 10125
|
|
},
|
|
{
|
|
"entropy": 5.650975227355957,
|
|
"epoch": 0.7881735070997861,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000494333554641848,
|
|
"loss": 5.406,
|
|
"mean_token_accuracy": 0.17036691009998323,
|
|
"num_tokens": 17595458.0,
|
|
"step": 10130
|
|
},
|
|
{
|
|
"entropy": 5.611591577529907,
|
|
"epoch": 0.7885625364715037,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000494327372081206,
|
|
"loss": 5.3205,
|
|
"mean_token_accuracy": 0.178653784096241,
|
|
"num_tokens": 17603997.0,
|
|
"step": 10135
|
|
},
|
|
{
|
|
"entropy": 5.636513948440552,
|
|
"epoch": 0.7889515658432211,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004943211861926204,
|
|
"loss": 5.3409,
|
|
"mean_token_accuracy": 0.17546274811029433,
|
|
"num_tokens": 17612347.0,
|
|
"step": 10140
|
|
},
|
|
{
|
|
"entropy": 5.563936233520508,
|
|
"epoch": 0.7893405952149387,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004943149969761848,
|
|
"loss": 5.1964,
|
|
"mean_token_accuracy": 0.1862559735774994,
|
|
"num_tokens": 17620618.0,
|
|
"step": 10145
|
|
},
|
|
{
|
|
"entropy": 5.495310258865357,
|
|
"epoch": 0.7897296245866563,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004943088044319932,
|
|
"loss": 5.2127,
|
|
"mean_token_accuracy": 0.18083256781101226,
|
|
"num_tokens": 17629164.0,
|
|
"step": 10150
|
|
},
|
|
{
|
|
"entropy": 5.642545223236084,
|
|
"epoch": 0.7901186539583739,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004943026085601395,
|
|
"loss": 5.388,
|
|
"mean_token_accuracy": 0.17380305081605912,
|
|
"num_tokens": 17638454.0,
|
|
"step": 10155
|
|
},
|
|
{
|
|
"entropy": 5.58918867111206,
|
|
"epoch": 0.7905076833300915,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004942964093607178,
|
|
"loss": 5.3049,
|
|
"mean_token_accuracy": 0.17752310484647751,
|
|
"num_tokens": 17647099.0,
|
|
"step": 10160
|
|
},
|
|
{
|
|
"entropy": 5.594116115570069,
|
|
"epoch": 0.790896712701809,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004942902068338222,
|
|
"loss": 5.2704,
|
|
"mean_token_accuracy": 0.18279317766427994,
|
|
"num_tokens": 17655214.0,
|
|
"step": 10165
|
|
},
|
|
{
|
|
"entropy": 5.562254953384399,
|
|
"epoch": 0.7912857420735265,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004942840009795466,
|
|
"loss": 5.236,
|
|
"mean_token_accuracy": 0.1806568518280983,
|
|
"num_tokens": 17663342.0,
|
|
"step": 10170
|
|
},
|
|
{
|
|
"entropy": 5.704637908935547,
|
|
"epoch": 0.7916747714452441,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004942777917979855,
|
|
"loss": 5.4433,
|
|
"mean_token_accuracy": 0.16575012654066085,
|
|
"num_tokens": 17671725.0,
|
|
"step": 10175
|
|
},
|
|
{
|
|
"entropy": 5.567132616043091,
|
|
"epoch": 0.7920638008169617,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004942715792892328,
|
|
"loss": 5.3392,
|
|
"mean_token_accuracy": 0.1732524037361145,
|
|
"num_tokens": 17680627.0,
|
|
"step": 10180
|
|
},
|
|
{
|
|
"entropy": 5.618295097351075,
|
|
"epoch": 0.7924528301886793,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000494265363453383,
|
|
"loss": 5.2998,
|
|
"mean_token_accuracy": 0.18326802551746368,
|
|
"num_tokens": 17688392.0,
|
|
"step": 10185
|
|
},
|
|
{
|
|
"entropy": 5.50335283279419,
|
|
"epoch": 0.7928418595603968,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004942591442905302,
|
|
"loss": 5.2558,
|
|
"mean_token_accuracy": 0.18379608690738677,
|
|
"num_tokens": 17697546.0,
|
|
"step": 10190
|
|
},
|
|
{
|
|
"entropy": 5.508504199981689,
|
|
"epoch": 0.7932308889321144,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004942529218007689,
|
|
"loss": 5.2165,
|
|
"mean_token_accuracy": 0.18102292269468306,
|
|
"num_tokens": 17705555.0,
|
|
"step": 10195
|
|
},
|
|
{
|
|
"entropy": 5.581924962997436,
|
|
"epoch": 0.7936199183038319,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004942466959841936,
|
|
"loss": 5.3836,
|
|
"mean_token_accuracy": 0.16984927654266357,
|
|
"num_tokens": 17715652.0,
|
|
"step": 10200
|
|
},
|
|
{
|
|
"entropy": 5.512160062789917,
|
|
"epoch": 0.7940089476755495,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004942404668408985,
|
|
"loss": 5.124,
|
|
"mean_token_accuracy": 0.18311595916748047,
|
|
"num_tokens": 17724111.0,
|
|
"step": 10205
|
|
},
|
|
{
|
|
"entropy": 5.461303615570069,
|
|
"epoch": 0.7943979770472671,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004942342343709783,
|
|
"loss": 5.1396,
|
|
"mean_token_accuracy": 0.18451044708490372,
|
|
"num_tokens": 17732732.0,
|
|
"step": 10210
|
|
},
|
|
{
|
|
"entropy": 5.558248853683471,
|
|
"epoch": 0.7947870064189846,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004942279985745275,
|
|
"loss": 5.2399,
|
|
"mean_token_accuracy": 0.18044923096895218,
|
|
"num_tokens": 17741338.0,
|
|
"step": 10215
|
|
},
|
|
{
|
|
"entropy": 5.6359869003295895,
|
|
"epoch": 0.7951760357907022,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004942217594516409,
|
|
"loss": 5.4489,
|
|
"mean_token_accuracy": 0.1734004020690918,
|
|
"num_tokens": 17750651.0,
|
|
"step": 10220
|
|
},
|
|
{
|
|
"entropy": 5.604165887832641,
|
|
"epoch": 0.7955650651624198,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000494215517002413,
|
|
"loss": 5.2573,
|
|
"mean_token_accuracy": 0.18303716629743577,
|
|
"num_tokens": 17759052.0,
|
|
"step": 10225
|
|
},
|
|
{
|
|
"entropy": 5.621202278137207,
|
|
"epoch": 0.7959540945341373,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004942092712269384,
|
|
"loss": 5.3162,
|
|
"mean_token_accuracy": 0.1753840208053589,
|
|
"num_tokens": 17767246.0,
|
|
"step": 10230
|
|
},
|
|
{
|
|
"entropy": 5.646518230438232,
|
|
"epoch": 0.7963431239058549,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004942030221253122,
|
|
"loss": 5.3416,
|
|
"mean_token_accuracy": 0.17957145124673843,
|
|
"num_tokens": 17777022.0,
|
|
"step": 10235
|
|
},
|
|
{
|
|
"entropy": 5.57313551902771,
|
|
"epoch": 0.7967321532775724,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004941967696976289,
|
|
"loss": 5.3091,
|
|
"mean_token_accuracy": 0.17263340651988984,
|
|
"num_tokens": 17785586.0,
|
|
"step": 10240
|
|
},
|
|
{
|
|
"entropy": 5.538752698898316,
|
|
"epoch": 0.79712118264929,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004941905139439835,
|
|
"loss": 5.3038,
|
|
"mean_token_accuracy": 0.17859912812709808,
|
|
"num_tokens": 17794320.0,
|
|
"step": 10245
|
|
},
|
|
{
|
|
"entropy": 5.632735300064087,
|
|
"epoch": 0.7975102120210076,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004941842548644712,
|
|
"loss": 5.3097,
|
|
"mean_token_accuracy": 0.18384564220905303,
|
|
"num_tokens": 17803384.0,
|
|
"step": 10250
|
|
},
|
|
{
|
|
"entropy": 5.605423831939698,
|
|
"epoch": 0.7978992413927252,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004941779924591864,
|
|
"loss": 5.2807,
|
|
"mean_token_accuracy": 0.17626046687364577,
|
|
"num_tokens": 17811955.0,
|
|
"step": 10255
|
|
},
|
|
{
|
|
"entropy": 5.567848348617554,
|
|
"epoch": 0.7982882707644428,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004941717267282244,
|
|
"loss": 5.3242,
|
|
"mean_token_accuracy": 0.17602663338184357,
|
|
"num_tokens": 17820582.0,
|
|
"step": 10260
|
|
},
|
|
{
|
|
"entropy": 5.643657493591308,
|
|
"epoch": 0.7986773001361602,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004941654576716806,
|
|
"loss": 5.245,
|
|
"mean_token_accuracy": 0.18023714274168015,
|
|
"num_tokens": 17828465.0,
|
|
"step": 10265
|
|
},
|
|
{
|
|
"entropy": 5.5508965969085695,
|
|
"epoch": 0.7990663295078778,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004941591852896495,
|
|
"loss": 5.2445,
|
|
"mean_token_accuracy": 0.18421650677919388,
|
|
"num_tokens": 17836931.0,
|
|
"step": 10270
|
|
},
|
|
{
|
|
"entropy": 5.572287082672119,
|
|
"epoch": 0.7994553588795954,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004941529095822268,
|
|
"loss": 5.3278,
|
|
"mean_token_accuracy": 0.17869895994663237,
|
|
"num_tokens": 17845192.0,
|
|
"step": 10275
|
|
},
|
|
{
|
|
"entropy": 5.554533910751343,
|
|
"epoch": 0.799844388251313,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004941466305495074,
|
|
"loss": 5.3059,
|
|
"mean_token_accuracy": 0.17677113115787507,
|
|
"num_tokens": 17854121.0,
|
|
"step": 10280
|
|
},
|
|
{
|
|
"entropy": 5.603392553329468,
|
|
"epoch": 0.8002334176230306,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004941403481915867,
|
|
"loss": 5.2917,
|
|
"mean_token_accuracy": 0.17675098776817322,
|
|
"num_tokens": 17862931.0,
|
|
"step": 10285
|
|
},
|
|
{
|
|
"entropy": 5.649144268035888,
|
|
"epoch": 0.800622446994748,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004941340625085601,
|
|
"loss": 5.3176,
|
|
"mean_token_accuracy": 0.17665561735630037,
|
|
"num_tokens": 17871909.0,
|
|
"step": 10290
|
|
},
|
|
{
|
|
"entropy": 5.547114706039428,
|
|
"epoch": 0.8010114763664656,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004941277735005228,
|
|
"loss": 5.231,
|
|
"mean_token_accuracy": 0.18726652562618257,
|
|
"num_tokens": 17880487.0,
|
|
"step": 10295
|
|
},
|
|
{
|
|
"entropy": 5.544336891174316,
|
|
"epoch": 0.8014005057381832,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004941214811675702,
|
|
"loss": 5.301,
|
|
"mean_token_accuracy": 0.17943531274795532,
|
|
"num_tokens": 17888712.0,
|
|
"step": 10300
|
|
},
|
|
{
|
|
"entropy": 5.628103160858155,
|
|
"epoch": 0.8017895351099008,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004941151855097982,
|
|
"loss": 5.3364,
|
|
"mean_token_accuracy": 0.16981505006551742,
|
|
"num_tokens": 17898163.0,
|
|
"step": 10305
|
|
},
|
|
{
|
|
"entropy": 5.551942348480225,
|
|
"epoch": 0.8021785644816184,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004941088865273018,
|
|
"loss": 5.227,
|
|
"mean_token_accuracy": 0.18352603912353516,
|
|
"num_tokens": 17906849.0,
|
|
"step": 10310
|
|
},
|
|
{
|
|
"entropy": 5.574260997772217,
|
|
"epoch": 0.802567593853336,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004941025842201769,
|
|
"loss": 5.2549,
|
|
"mean_token_accuracy": 0.1780119240283966,
|
|
"num_tokens": 17915695.0,
|
|
"step": 10315
|
|
},
|
|
{
|
|
"entropy": 5.64654860496521,
|
|
"epoch": 0.8029566232250535,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004940962785885189,
|
|
"loss": 5.3543,
|
|
"mean_token_accuracy": 0.17598017901182175,
|
|
"num_tokens": 17924706.0,
|
|
"step": 10320
|
|
},
|
|
{
|
|
"entropy": 5.561926555633545,
|
|
"epoch": 0.803345652596771,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004940899696324237,
|
|
"loss": 5.3287,
|
|
"mean_token_accuracy": 0.18102977126836778,
|
|
"num_tokens": 17934061.0,
|
|
"step": 10325
|
|
},
|
|
{
|
|
"entropy": 5.536122751235962,
|
|
"epoch": 0.8037346819684886,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004940836573519868,
|
|
"loss": 5.2054,
|
|
"mean_token_accuracy": 0.17839139550924302,
|
|
"num_tokens": 17942580.0,
|
|
"step": 10330
|
|
},
|
|
{
|
|
"entropy": 5.525859594345093,
|
|
"epoch": 0.8041237113402062,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004940773417473043,
|
|
"loss": 5.1004,
|
|
"mean_token_accuracy": 0.18802183270454406,
|
|
"num_tokens": 17951171.0,
|
|
"step": 10335
|
|
},
|
|
{
|
|
"entropy": 5.512113428115844,
|
|
"epoch": 0.8045127407119238,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004940710228184717,
|
|
"loss": 5.1789,
|
|
"mean_token_accuracy": 0.19142742902040483,
|
|
"num_tokens": 17959674.0,
|
|
"step": 10340
|
|
},
|
|
{
|
|
"entropy": 5.538492822647095,
|
|
"epoch": 0.8049017700836413,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000494064700565585,
|
|
"loss": 5.2434,
|
|
"mean_token_accuracy": 0.18216741681098939,
|
|
"num_tokens": 17969036.0,
|
|
"step": 10345
|
|
},
|
|
{
|
|
"entropy": 5.547858619689942,
|
|
"epoch": 0.8052907994553589,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004940583749887403,
|
|
"loss": 5.2602,
|
|
"mean_token_accuracy": 0.18307285904884338,
|
|
"num_tokens": 17977406.0,
|
|
"step": 10350
|
|
},
|
|
{
|
|
"entropy": 5.557126045227051,
|
|
"epoch": 0.8056798288270764,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004940520460880333,
|
|
"loss": 5.2322,
|
|
"mean_token_accuracy": 0.18356891870498657,
|
|
"num_tokens": 17985981.0,
|
|
"step": 10355
|
|
},
|
|
{
|
|
"entropy": 5.637621688842773,
|
|
"epoch": 0.806068858198794,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004940457138635601,
|
|
"loss": 5.4217,
|
|
"mean_token_accuracy": 0.17267650961875916,
|
|
"num_tokens": 17994246.0,
|
|
"step": 10360
|
|
},
|
|
{
|
|
"entropy": 5.581584882736206,
|
|
"epoch": 0.8064578875705116,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004940393783154169,
|
|
"loss": 5.2593,
|
|
"mean_token_accuracy": 0.17970990985631943,
|
|
"num_tokens": 18002444.0,
|
|
"step": 10365
|
|
},
|
|
{
|
|
"entropy": 5.532887077331543,
|
|
"epoch": 0.8068469169422291,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004940330394436999,
|
|
"loss": 5.1834,
|
|
"mean_token_accuracy": 0.18363454490900039,
|
|
"num_tokens": 18011076.0,
|
|
"step": 10370
|
|
},
|
|
{
|
|
"entropy": 5.64114203453064,
|
|
"epoch": 0.8072359463139467,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000494026697248505,
|
|
"loss": 5.4665,
|
|
"mean_token_accuracy": 0.1663346603512764,
|
|
"num_tokens": 18020232.0,
|
|
"step": 10375
|
|
},
|
|
{
|
|
"entropy": 5.636241626739502,
|
|
"epoch": 0.8076249756856643,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004940203517299287,
|
|
"loss": 5.2743,
|
|
"mean_token_accuracy": 0.1763804465532303,
|
|
"num_tokens": 18029055.0,
|
|
"step": 10380
|
|
},
|
|
{
|
|
"entropy": 5.642540788650512,
|
|
"epoch": 0.8080140050573819,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000494014002888067,
|
|
"loss": 5.4172,
|
|
"mean_token_accuracy": 0.1637917563319206,
|
|
"num_tokens": 18037827.0,
|
|
"step": 10385
|
|
},
|
|
{
|
|
"entropy": 5.536993980407715,
|
|
"epoch": 0.8084030344290994,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004940076507230166,
|
|
"loss": 5.2474,
|
|
"mean_token_accuracy": 0.17653342634439467,
|
|
"num_tokens": 18047017.0,
|
|
"step": 10390
|
|
},
|
|
{
|
|
"entropy": 5.619476079940796,
|
|
"epoch": 0.8087920638008169,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004940012952348735,
|
|
"loss": 5.354,
|
|
"mean_token_accuracy": 0.17621037364006042,
|
|
"num_tokens": 18056256.0,
|
|
"step": 10395
|
|
},
|
|
{
|
|
"entropy": 5.568868350982666,
|
|
"epoch": 0.8091810931725345,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004939949364237345,
|
|
"loss": 5.1129,
|
|
"mean_token_accuracy": 0.19875151962041854,
|
|
"num_tokens": 18064127.0,
|
|
"step": 10400
|
|
},
|
|
{
|
|
"entropy": 5.507281875610351,
|
|
"epoch": 0.8095701225442521,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004939885742896958,
|
|
"loss": 5.2757,
|
|
"mean_token_accuracy": 0.1827508956193924,
|
|
"num_tokens": 18072766.0,
|
|
"step": 10405
|
|
},
|
|
{
|
|
"entropy": 5.5320202827453615,
|
|
"epoch": 0.8099591519159697,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000493982208832854,
|
|
"loss": 5.2401,
|
|
"mean_token_accuracy": 0.17939431816339493,
|
|
"num_tokens": 18080685.0,
|
|
"step": 10410
|
|
},
|
|
{
|
|
"entropy": 5.613889408111572,
|
|
"epoch": 0.8103481812876873,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004939758400533058,
|
|
"loss": 5.3109,
|
|
"mean_token_accuracy": 0.1760113373398781,
|
|
"num_tokens": 18090026.0,
|
|
"step": 10415
|
|
},
|
|
{
|
|
"entropy": 5.591238641738892,
|
|
"epoch": 0.8107372106594047,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004939694679511478,
|
|
"loss": 5.2274,
|
|
"mean_token_accuracy": 0.18148638010025026,
|
|
"num_tokens": 18098638.0,
|
|
"step": 10420
|
|
},
|
|
{
|
|
"entropy": 5.526708889007568,
|
|
"epoch": 0.8111262400311223,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004939630925264765,
|
|
"loss": 5.2639,
|
|
"mean_token_accuracy": 0.18288784623146057,
|
|
"num_tokens": 18106844.0,
|
|
"step": 10425
|
|
},
|
|
{
|
|
"entropy": 5.581420755386352,
|
|
"epoch": 0.8115152694028399,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000493956713779389,
|
|
"loss": 5.2536,
|
|
"mean_token_accuracy": 0.17701498419046402,
|
|
"num_tokens": 18114758.0,
|
|
"step": 10430
|
|
},
|
|
{
|
|
"entropy": 5.5890758514404295,
|
|
"epoch": 0.8119042987745575,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004939503317099817,
|
|
"loss": 5.2254,
|
|
"mean_token_accuracy": 0.18185850977897644,
|
|
"num_tokens": 18122839.0,
|
|
"step": 10435
|
|
},
|
|
{
|
|
"entropy": 5.5715070247650145,
|
|
"epoch": 0.8122933281462751,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004939439463183517,
|
|
"loss": 5.3198,
|
|
"mean_token_accuracy": 0.18264523893594742,
|
|
"num_tokens": 18131709.0,
|
|
"step": 10440
|
|
},
|
|
{
|
|
"entropy": 5.580619525909424,
|
|
"epoch": 0.8126823575179926,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004939375576045958,
|
|
"loss": 5.2965,
|
|
"mean_token_accuracy": 0.17366210371255875,
|
|
"num_tokens": 18140334.0,
|
|
"step": 10445
|
|
},
|
|
{
|
|
"entropy": 5.531055545806884,
|
|
"epoch": 0.8130713868897101,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004939311655688109,
|
|
"loss": 5.293,
|
|
"mean_token_accuracy": 0.1767920583486557,
|
|
"num_tokens": 18148648.0,
|
|
"step": 10450
|
|
},
|
|
{
|
|
"entropy": 5.560915088653564,
|
|
"epoch": 0.8134604162614277,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004939247702110941,
|
|
"loss": 5.296,
|
|
"mean_token_accuracy": 0.18004312962293625,
|
|
"num_tokens": 18156891.0,
|
|
"step": 10455
|
|
},
|
|
{
|
|
"entropy": 5.569944620132446,
|
|
"epoch": 0.8138494456331453,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004939183715315423,
|
|
"loss": 5.2408,
|
|
"mean_token_accuracy": 0.18391807228326798,
|
|
"num_tokens": 18166512.0,
|
|
"step": 10460
|
|
},
|
|
{
|
|
"entropy": 5.591281080245972,
|
|
"epoch": 0.8142384750048629,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004939119695302526,
|
|
"loss": 5.1994,
|
|
"mean_token_accuracy": 0.18591028600931167,
|
|
"num_tokens": 18175064.0,
|
|
"step": 10465
|
|
},
|
|
{
|
|
"entropy": 5.552697563171387,
|
|
"epoch": 0.8146275043765804,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004939055642073224,
|
|
"loss": 5.3331,
|
|
"mean_token_accuracy": 0.17966595739126207,
|
|
"num_tokens": 18184251.0,
|
|
"step": 10470
|
|
},
|
|
{
|
|
"entropy": 5.516888427734375,
|
|
"epoch": 0.815016533748298,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004938991555628484,
|
|
"loss": 5.167,
|
|
"mean_token_accuracy": 0.18957981765270232,
|
|
"num_tokens": 18193274.0,
|
|
"step": 10475
|
|
},
|
|
{
|
|
"entropy": 5.532575511932373,
|
|
"epoch": 0.8154055631200156,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004938927435969283,
|
|
"loss": 5.2303,
|
|
"mean_token_accuracy": 0.18930566757917405,
|
|
"num_tokens": 18201878.0,
|
|
"step": 10480
|
|
},
|
|
{
|
|
"entropy": 5.51650972366333,
|
|
"epoch": 0.8157945924917331,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004938863283096592,
|
|
"loss": 5.1984,
|
|
"mean_token_accuracy": 0.18496177345514297,
|
|
"num_tokens": 18210343.0,
|
|
"step": 10485
|
|
},
|
|
{
|
|
"entropy": 5.641515016555786,
|
|
"epoch": 0.8161836218634507,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004938799097011384,
|
|
"loss": 5.3281,
|
|
"mean_token_accuracy": 0.18384619504213334,
|
|
"num_tokens": 18218599.0,
|
|
"step": 10490
|
|
},
|
|
{
|
|
"entropy": 5.550069665908813,
|
|
"epoch": 0.8165726512351682,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004938734877714634,
|
|
"loss": 5.2091,
|
|
"mean_token_accuracy": 0.18761346638202667,
|
|
"num_tokens": 18226384.0,
|
|
"step": 10495
|
|
},
|
|
{
|
|
"entropy": 5.519427156448364,
|
|
"epoch": 0.8169616806068858,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004938670625207317,
|
|
"loss": 5.2014,
|
|
"mean_token_accuracy": 0.1802952140569687,
|
|
"num_tokens": 18234894.0,
|
|
"step": 10500
|
|
},
|
|
{
|
|
"entropy": 5.565952444076538,
|
|
"epoch": 0.8173507099786034,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004938606339490406,
|
|
"loss": 5.2414,
|
|
"mean_token_accuracy": 0.18535373508930206,
|
|
"num_tokens": 18243768.0,
|
|
"step": 10505
|
|
},
|
|
{
|
|
"entropy": 5.584456729888916,
|
|
"epoch": 0.817739739350321,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004938542020564877,
|
|
"loss": 5.2782,
|
|
"mean_token_accuracy": 0.18248629719018936,
|
|
"num_tokens": 18252364.0,
|
|
"step": 10510
|
|
},
|
|
{
|
|
"entropy": 5.53111891746521,
|
|
"epoch": 0.8181287687220385,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004938477668431706,
|
|
"loss": 5.2278,
|
|
"mean_token_accuracy": 0.18297127038240432,
|
|
"num_tokens": 18260997.0,
|
|
"step": 10515
|
|
},
|
|
{
|
|
"entropy": 5.672461938858032,
|
|
"epoch": 0.8185177980937561,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004938413283091871,
|
|
"loss": 5.413,
|
|
"mean_token_accuracy": 0.17652716487646103,
|
|
"num_tokens": 18270171.0,
|
|
"step": 10520
|
|
},
|
|
{
|
|
"entropy": 5.643474149703979,
|
|
"epoch": 0.8189068274654736,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004938348864546347,
|
|
"loss": 5.2559,
|
|
"mean_token_accuracy": 0.18688322007656097,
|
|
"num_tokens": 18278772.0,
|
|
"step": 10525
|
|
},
|
|
{
|
|
"entropy": 5.486976099014282,
|
|
"epoch": 0.8192958568371912,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004938284412796111,
|
|
"loss": 5.0895,
|
|
"mean_token_accuracy": 0.18835799694061278,
|
|
"num_tokens": 18287305.0,
|
|
"step": 10530
|
|
},
|
|
{
|
|
"entropy": 5.470224809646607,
|
|
"epoch": 0.8196848862089088,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004938219927842144,
|
|
"loss": 5.3277,
|
|
"mean_token_accuracy": 0.1742580935359001,
|
|
"num_tokens": 18296532.0,
|
|
"step": 10535
|
|
},
|
|
{
|
|
"entropy": 5.55927472114563,
|
|
"epoch": 0.8200739155806264,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004938155409685422,
|
|
"loss": 5.1859,
|
|
"mean_token_accuracy": 0.18895601928234101,
|
|
"num_tokens": 18304612.0,
|
|
"step": 10540
|
|
},
|
|
{
|
|
"entropy": 5.555217218399048,
|
|
"epoch": 0.820462944952344,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004938090858326923,
|
|
"loss": 5.2545,
|
|
"mean_token_accuracy": 0.18999724090099335,
|
|
"num_tokens": 18312970.0,
|
|
"step": 10545
|
|
},
|
|
{
|
|
"entropy": 5.578555965423584,
|
|
"epoch": 0.8208519743240614,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000493802627376763,
|
|
"loss": 5.2793,
|
|
"mean_token_accuracy": 0.181522336602211,
|
|
"num_tokens": 18321073.0,
|
|
"step": 10550
|
|
},
|
|
{
|
|
"entropy": 5.5834558486938475,
|
|
"epoch": 0.821241003695779,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004937961656008518,
|
|
"loss": 5.2667,
|
|
"mean_token_accuracy": 0.18040078282356262,
|
|
"num_tokens": 18329960.0,
|
|
"step": 10555
|
|
},
|
|
{
|
|
"entropy": 5.514997577667236,
|
|
"epoch": 0.8216300330674966,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004937897005050573,
|
|
"loss": 5.2308,
|
|
"mean_token_accuracy": 0.18348744064569472,
|
|
"num_tokens": 18337935.0,
|
|
"step": 10560
|
|
},
|
|
{
|
|
"entropy": 5.541813945770263,
|
|
"epoch": 0.8220190624392142,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004937832320894772,
|
|
"loss": 5.2233,
|
|
"mean_token_accuracy": 0.18325609117746353,
|
|
"num_tokens": 18347445.0,
|
|
"step": 10565
|
|
},
|
|
{
|
|
"entropy": 5.586518907546997,
|
|
"epoch": 0.8224080918109318,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004937767603542098,
|
|
"loss": 5.2327,
|
|
"mean_token_accuracy": 0.18263234943151474,
|
|
"num_tokens": 18355817.0,
|
|
"step": 10570
|
|
},
|
|
{
|
|
"entropy": 5.571928024291992,
|
|
"epoch": 0.8227971211826492,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004937702852993534,
|
|
"loss": 5.2282,
|
|
"mean_token_accuracy": 0.18538487404584886,
|
|
"num_tokens": 18363478.0,
|
|
"step": 10575
|
|
},
|
|
{
|
|
"entropy": 5.531855154037475,
|
|
"epoch": 0.8231861505543668,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000493763806925006,
|
|
"loss": 5.2108,
|
|
"mean_token_accuracy": 0.18181927502155304,
|
|
"num_tokens": 18371788.0,
|
|
"step": 10580
|
|
},
|
|
{
|
|
"entropy": 5.53119592666626,
|
|
"epoch": 0.8235751799260844,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004937573252312661,
|
|
"loss": 5.2477,
|
|
"mean_token_accuracy": 0.18195367455482483,
|
|
"num_tokens": 18380361.0,
|
|
"step": 10585
|
|
},
|
|
{
|
|
"entropy": 5.575139045715332,
|
|
"epoch": 0.823964209297802,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000493750840218232,
|
|
"loss": 5.3032,
|
|
"mean_token_accuracy": 0.18456340879201888,
|
|
"num_tokens": 18389396.0,
|
|
"step": 10590
|
|
},
|
|
{
|
|
"entropy": 5.549172067642212,
|
|
"epoch": 0.8243532386695196,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004937443518860021,
|
|
"loss": 5.3634,
|
|
"mean_token_accuracy": 0.16981100738048555,
|
|
"num_tokens": 18398517.0,
|
|
"step": 10595
|
|
},
|
|
{
|
|
"entropy": 5.645396184921265,
|
|
"epoch": 0.8247422680412371,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004937378602346747,
|
|
"loss": 5.2937,
|
|
"mean_token_accuracy": 0.18099551200866698,
|
|
"num_tokens": 18406620.0,
|
|
"step": 10600
|
|
},
|
|
{
|
|
"entropy": 5.5864983081817625,
|
|
"epoch": 0.8251312974129547,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004937313652643485,
|
|
"loss": 5.3128,
|
|
"mean_token_accuracy": 0.17442767173051835,
|
|
"num_tokens": 18414849.0,
|
|
"step": 10605
|
|
},
|
|
{
|
|
"entropy": 5.521216821670532,
|
|
"epoch": 0.8255203267846722,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000493724866975122,
|
|
"loss": 5.2769,
|
|
"mean_token_accuracy": 0.18221895694732665,
|
|
"num_tokens": 18423675.0,
|
|
"step": 10610
|
|
},
|
|
{
|
|
"entropy": 5.66914439201355,
|
|
"epoch": 0.8259093561563898,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004937183653670937,
|
|
"loss": 5.3275,
|
|
"mean_token_accuracy": 0.17973185926675797,
|
|
"num_tokens": 18432848.0,
|
|
"step": 10615
|
|
},
|
|
{
|
|
"entropy": 5.662630844116211,
|
|
"epoch": 0.8262983855281074,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004937118604403623,
|
|
"loss": 5.3713,
|
|
"mean_token_accuracy": 0.17663578391075135,
|
|
"num_tokens": 18441210.0,
|
|
"step": 10620
|
|
},
|
|
{
|
|
"entropy": 5.59189510345459,
|
|
"epoch": 0.8266874148998249,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004937053521950266,
|
|
"loss": 5.2786,
|
|
"mean_token_accuracy": 0.17604520916938782,
|
|
"num_tokens": 18450084.0,
|
|
"step": 10625
|
|
},
|
|
{
|
|
"entropy": 5.486194515228272,
|
|
"epoch": 0.8270764442715425,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004936988406311854,
|
|
"loss": 5.1548,
|
|
"mean_token_accuracy": 0.18131692260503768,
|
|
"num_tokens": 18458329.0,
|
|
"step": 10630
|
|
},
|
|
{
|
|
"entropy": 5.525796365737915,
|
|
"epoch": 0.8274654736432601,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004936923257489373,
|
|
"loss": 5.2683,
|
|
"mean_token_accuracy": 0.17761918902397156,
|
|
"num_tokens": 18467518.0,
|
|
"step": 10635
|
|
},
|
|
{
|
|
"entropy": 5.520053434371948,
|
|
"epoch": 0.8278545030149776,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004936858075483811,
|
|
"loss": 5.1578,
|
|
"mean_token_accuracy": 0.1974279910326004,
|
|
"num_tokens": 18476051.0,
|
|
"step": 10640
|
|
},
|
|
{
|
|
"entropy": 5.584073686599732,
|
|
"epoch": 0.8282435323866952,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000493679286029616,
|
|
"loss": 5.2558,
|
|
"mean_token_accuracy": 0.18164041340351106,
|
|
"num_tokens": 18484492.0,
|
|
"step": 10645
|
|
},
|
|
{
|
|
"entropy": 5.581503963470459,
|
|
"epoch": 0.8286325617584127,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004936727611927407,
|
|
"loss": 5.3281,
|
|
"mean_token_accuracy": 0.1709176108241081,
|
|
"num_tokens": 18493759.0,
|
|
"step": 10650
|
|
},
|
|
{
|
|
"entropy": 5.606781721115112,
|
|
"epoch": 0.8290215911301303,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004936662330378546,
|
|
"loss": 5.1846,
|
|
"mean_token_accuracy": 0.18201837837696075,
|
|
"num_tokens": 18501750.0,
|
|
"step": 10655
|
|
},
|
|
{
|
|
"entropy": 5.490160417556763,
|
|
"epoch": 0.8294106205018479,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004936597015650561,
|
|
"loss": 5.1917,
|
|
"mean_token_accuracy": 0.18296556621789933,
|
|
"num_tokens": 18511003.0,
|
|
"step": 10660
|
|
},
|
|
{
|
|
"entropy": 5.513647127151489,
|
|
"epoch": 0.8297996498735655,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004936531667744448,
|
|
"loss": 5.2433,
|
|
"mean_token_accuracy": 0.18767827302217482,
|
|
"num_tokens": 18519544.0,
|
|
"step": 10665
|
|
},
|
|
{
|
|
"entropy": 5.686276054382324,
|
|
"epoch": 0.8301886792452831,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004936466286661197,
|
|
"loss": 5.3324,
|
|
"mean_token_accuracy": 0.17959838956594468,
|
|
"num_tokens": 18528766.0,
|
|
"step": 10670
|
|
},
|
|
{
|
|
"entropy": 5.601961088180542,
|
|
"epoch": 0.8305777086170005,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00049364008724018,
|
|
"loss": 5.3349,
|
|
"mean_token_accuracy": 0.1756493031978607,
|
|
"num_tokens": 18538243.0,
|
|
"step": 10675
|
|
},
|
|
{
|
|
"entropy": 5.592152118682861,
|
|
"epoch": 0.8309667379887181,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000493633542496725,
|
|
"loss": 5.3425,
|
|
"mean_token_accuracy": 0.1781254753470421,
|
|
"num_tokens": 18547028.0,
|
|
"step": 10680
|
|
},
|
|
{
|
|
"entropy": 5.618417549133301,
|
|
"epoch": 0.8313557673604357,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004936269944358539,
|
|
"loss": 5.3546,
|
|
"mean_token_accuracy": 0.17658570408821106,
|
|
"num_tokens": 18555821.0,
|
|
"step": 10685
|
|
},
|
|
{
|
|
"entropy": 5.542150449752808,
|
|
"epoch": 0.8317447967321533,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004936204430576664,
|
|
"loss": 5.322,
|
|
"mean_token_accuracy": 0.17941897213459015,
|
|
"num_tokens": 18564213.0,
|
|
"step": 10690
|
|
},
|
|
{
|
|
"entropy": 5.60770435333252,
|
|
"epoch": 0.8321338261038709,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004936138883622614,
|
|
"loss": 5.2899,
|
|
"mean_token_accuracy": 0.17497958540916442,
|
|
"num_tokens": 18573132.0,
|
|
"step": 10695
|
|
},
|
|
{
|
|
"entropy": 5.606252002716064,
|
|
"epoch": 0.8325228554755884,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004936073303497387,
|
|
"loss": 5.1981,
|
|
"mean_token_accuracy": 0.18049157559871673,
|
|
"num_tokens": 18581131.0,
|
|
"step": 10700
|
|
},
|
|
{
|
|
"entropy": 5.564637136459351,
|
|
"epoch": 0.8329118848473059,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004936007690201976,
|
|
"loss": 5.2805,
|
|
"mean_token_accuracy": 0.1784028634428978,
|
|
"num_tokens": 18589602.0,
|
|
"step": 10705
|
|
},
|
|
{
|
|
"entropy": 5.548305988311768,
|
|
"epoch": 0.8333009142190235,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000493594204373738,
|
|
"loss": 5.2647,
|
|
"mean_token_accuracy": 0.1764623209834099,
|
|
"num_tokens": 18598263.0,
|
|
"step": 10710
|
|
},
|
|
{
|
|
"entropy": 5.606611728668213,
|
|
"epoch": 0.8336899435907411,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004935876364104591,
|
|
"loss": 5.1725,
|
|
"mean_token_accuracy": 0.189447121322155,
|
|
"num_tokens": 18606432.0,
|
|
"step": 10715
|
|
},
|
|
{
|
|
"entropy": 5.573548603057861,
|
|
"epoch": 0.8340789729624587,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004935810651304608,
|
|
"loss": 5.3071,
|
|
"mean_token_accuracy": 0.17638261318206788,
|
|
"num_tokens": 18614769.0,
|
|
"step": 10720
|
|
},
|
|
{
|
|
"entropy": 5.607085561752319,
|
|
"epoch": 0.8344680023341763,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004935744905338427,
|
|
"loss": 5.271,
|
|
"mean_token_accuracy": 0.17813154458999633,
|
|
"num_tokens": 18623505.0,
|
|
"step": 10725
|
|
},
|
|
{
|
|
"entropy": 5.621091651916504,
|
|
"epoch": 0.8348570317058938,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004935679126207046,
|
|
"loss": 5.2392,
|
|
"mean_token_accuracy": 0.19103155732154847,
|
|
"num_tokens": 18632072.0,
|
|
"step": 10730
|
|
},
|
|
{
|
|
"entropy": 5.650973272323609,
|
|
"epoch": 0.8352460610776113,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004935613313911463,
|
|
"loss": 5.3168,
|
|
"mean_token_accuracy": 0.17635270208120346,
|
|
"num_tokens": 18640439.0,
|
|
"step": 10735
|
|
},
|
|
{
|
|
"entropy": 5.56662220954895,
|
|
"epoch": 0.8356350904493289,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004935547468452678,
|
|
"loss": 5.3091,
|
|
"mean_token_accuracy": 0.16891513168811798,
|
|
"num_tokens": 18649554.0,
|
|
"step": 10740
|
|
},
|
|
{
|
|
"entropy": 5.607131433486939,
|
|
"epoch": 0.8360241198210465,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004935481589831688,
|
|
"loss": 5.1742,
|
|
"mean_token_accuracy": 0.1841895952820778,
|
|
"num_tokens": 18657918.0,
|
|
"step": 10745
|
|
},
|
|
{
|
|
"entropy": 5.629995822906494,
|
|
"epoch": 0.8364131491927641,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004935415678049492,
|
|
"loss": 5.288,
|
|
"mean_token_accuracy": 0.17434722632169725,
|
|
"num_tokens": 18666735.0,
|
|
"step": 10750
|
|
},
|
|
{
|
|
"entropy": 5.569375228881836,
|
|
"epoch": 0.8368021785644816,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004935349733107094,
|
|
"loss": 5.1825,
|
|
"mean_token_accuracy": 0.1853045254945755,
|
|
"num_tokens": 18674977.0,
|
|
"step": 10755
|
|
},
|
|
{
|
|
"entropy": 5.5684432029724125,
|
|
"epoch": 0.8371912079361992,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000493528375500549,
|
|
"loss": 5.3288,
|
|
"mean_token_accuracy": 0.17748333066701888,
|
|
"num_tokens": 18683624.0,
|
|
"step": 10760
|
|
},
|
|
{
|
|
"entropy": 5.524935007095337,
|
|
"epoch": 0.8375802373079168,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004935217743745685,
|
|
"loss": 5.2199,
|
|
"mean_token_accuracy": 0.18397823274135588,
|
|
"num_tokens": 18692183.0,
|
|
"step": 10765
|
|
},
|
|
{
|
|
"entropy": 5.604568290710449,
|
|
"epoch": 0.8379692666796343,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004935151699328677,
|
|
"loss": 5.3085,
|
|
"mean_token_accuracy": 0.17603420168161393,
|
|
"num_tokens": 18700989.0,
|
|
"step": 10770
|
|
},
|
|
{
|
|
"entropy": 5.545925712585449,
|
|
"epoch": 0.8383582960513519,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004935085621755471,
|
|
"loss": 5.1773,
|
|
"mean_token_accuracy": 0.18596030175685882,
|
|
"num_tokens": 18709126.0,
|
|
"step": 10775
|
|
},
|
|
{
|
|
"entropy": 5.587519264221191,
|
|
"epoch": 0.8387473254230694,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000493501951102707,
|
|
"loss": 5.2801,
|
|
"mean_token_accuracy": 0.17877295315265657,
|
|
"num_tokens": 18717378.0,
|
|
"step": 10780
|
|
},
|
|
{
|
|
"entropy": 5.650118827819824,
|
|
"epoch": 0.839136354794787,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004934953367144474,
|
|
"loss": 5.3387,
|
|
"mean_token_accuracy": 0.17719743847846986,
|
|
"num_tokens": 18725694.0,
|
|
"step": 10785
|
|
},
|
|
{
|
|
"entropy": 5.557237815856934,
|
|
"epoch": 0.8395253841665046,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004934887190108688,
|
|
"loss": 5.2483,
|
|
"mean_token_accuracy": 0.1862121567130089,
|
|
"num_tokens": 18734737.0,
|
|
"step": 10790
|
|
},
|
|
{
|
|
"entropy": 5.691574382781982,
|
|
"epoch": 0.8399144135382222,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004934820979920719,
|
|
"loss": 5.4604,
|
|
"mean_token_accuracy": 0.1678543671965599,
|
|
"num_tokens": 18743895.0,
|
|
"step": 10795
|
|
},
|
|
{
|
|
"entropy": 5.637724208831787,
|
|
"epoch": 0.8403034429099397,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004934754736581567,
|
|
"loss": 5.3261,
|
|
"mean_token_accuracy": 0.17763975709676744,
|
|
"num_tokens": 18753105.0,
|
|
"step": 10800
|
|
},
|
|
{
|
|
"entropy": 5.481872081756592,
|
|
"epoch": 0.8406924722816572,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000493468846009224,
|
|
"loss": 5.186,
|
|
"mean_token_accuracy": 0.18352127373218535,
|
|
"num_tokens": 18761593.0,
|
|
"step": 10805
|
|
},
|
|
{
|
|
"entropy": 5.628566932678223,
|
|
"epoch": 0.8410815016533748,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004934622150453742,
|
|
"loss": 5.2388,
|
|
"mean_token_accuracy": 0.18627728074789046,
|
|
"num_tokens": 18770105.0,
|
|
"step": 10810
|
|
},
|
|
{
|
|
"entropy": 5.605173635482788,
|
|
"epoch": 0.8414705310250924,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.000493455580766708,
|
|
"loss": 5.2866,
|
|
"mean_token_accuracy": 0.17801288664340972,
|
|
"num_tokens": 18778429.0,
|
|
"step": 10815
|
|
},
|
|
{
|
|
"entropy": 5.651268720626831,
|
|
"epoch": 0.84185956039681,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004934489431733262,
|
|
"loss": 5.327,
|
|
"mean_token_accuracy": 0.17554858028888704,
|
|
"num_tokens": 18787072.0,
|
|
"step": 10820
|
|
},
|
|
{
|
|
"entropy": 5.529681539535522,
|
|
"epoch": 0.8422485897685276,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004934423022653293,
|
|
"loss": 5.1998,
|
|
"mean_token_accuracy": 0.18770936578512193,
|
|
"num_tokens": 18795628.0,
|
|
"step": 10825
|
|
},
|
|
{
|
|
"entropy": 5.560863208770752,
|
|
"epoch": 0.842637619140245,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004934356580428182,
|
|
"loss": 5.2882,
|
|
"mean_token_accuracy": 0.17767442017793655,
|
|
"num_tokens": 18804313.0,
|
|
"step": 10830
|
|
},
|
|
{
|
|
"entropy": 5.613304376602173,
|
|
"epoch": 0.8430266485119626,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004934290105058937,
|
|
"loss": 5.3149,
|
|
"mean_token_accuracy": 0.1774200201034546,
|
|
"num_tokens": 18813170.0,
|
|
"step": 10835
|
|
},
|
|
{
|
|
"entropy": 5.5797830581665036,
|
|
"epoch": 0.8434156778836802,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004934223596546565,
|
|
"loss": 5.2632,
|
|
"mean_token_accuracy": 0.1828976258635521,
|
|
"num_tokens": 18823009.0,
|
|
"step": 10840
|
|
},
|
|
{
|
|
"entropy": 5.589580345153808,
|
|
"epoch": 0.8438047072553978,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004934157054892077,
|
|
"loss": 5.3109,
|
|
"mean_token_accuracy": 0.17641228437423706,
|
|
"num_tokens": 18831272.0,
|
|
"step": 10845
|
|
},
|
|
{
|
|
"entropy": 5.562094211578369,
|
|
"epoch": 0.8441937366271154,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004934090480096482,
|
|
"loss": 5.299,
|
|
"mean_token_accuracy": 0.17283533960580827,
|
|
"num_tokens": 18839481.0,
|
|
"step": 10850
|
|
},
|
|
{
|
|
"entropy": 5.531780529022217,
|
|
"epoch": 0.8445827659988329,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004934023872160791,
|
|
"loss": 5.26,
|
|
"mean_token_accuracy": 0.18713913410902022,
|
|
"num_tokens": 18848586.0,
|
|
"step": 10855
|
|
},
|
|
{
|
|
"entropy": 5.568729019165039,
|
|
"epoch": 0.8449717953705504,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004933957231086014,
|
|
"loss": 5.1588,
|
|
"mean_token_accuracy": 0.18601678311824799,
|
|
"num_tokens": 18856948.0,
|
|
"step": 10860
|
|
},
|
|
{
|
|
"entropy": 5.581716871261596,
|
|
"epoch": 0.845360824742268,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004933890556873161,
|
|
"loss": 5.2363,
|
|
"mean_token_accuracy": 0.1828387498855591,
|
|
"num_tokens": 18864741.0,
|
|
"step": 10865
|
|
},
|
|
{
|
|
"entropy": 5.566734266281128,
|
|
"epoch": 0.8457498541139856,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004933823849523246,
|
|
"loss": 5.2831,
|
|
"mean_token_accuracy": 0.17859045118093492,
|
|
"num_tokens": 18873373.0,
|
|
"step": 10870
|
|
},
|
|
{
|
|
"entropy": 5.621180152893066,
|
|
"epoch": 0.8461388834857032,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004933757109037279,
|
|
"loss": 5.1734,
|
|
"mean_token_accuracy": 0.18435244262218475,
|
|
"num_tokens": 18881590.0,
|
|
"step": 10875
|
|
},
|
|
{
|
|
"entropy": 5.598472595214844,
|
|
"epoch": 0.8465279128574207,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004933690335416274,
|
|
"loss": 5.2838,
|
|
"mean_token_accuracy": 0.1795947551727295,
|
|
"num_tokens": 18889838.0,
|
|
"step": 10880
|
|
},
|
|
{
|
|
"entropy": 5.509574937820434,
|
|
"epoch": 0.8469169422291383,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004933623528661245,
|
|
"loss": 5.1859,
|
|
"mean_token_accuracy": 0.18743556141853332,
|
|
"num_tokens": 18898577.0,
|
|
"step": 10885
|
|
},
|
|
{
|
|
"entropy": 5.6272741794586185,
|
|
"epoch": 0.8473059716008559,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004933556688773203,
|
|
"loss": 5.3269,
|
|
"mean_token_accuracy": 0.1822746753692627,
|
|
"num_tokens": 18907309.0,
|
|
"step": 10890
|
|
},
|
|
{
|
|
"entropy": 5.579664325714111,
|
|
"epoch": 0.8476950009725734,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004933489815753165,
|
|
"loss": 5.259,
|
|
"mean_token_accuracy": 0.1802939161658287,
|
|
"num_tokens": 18915956.0,
|
|
"step": 10895
|
|
},
|
|
{
|
|
"entropy": 5.562767219543457,
|
|
"epoch": 0.848084030344291,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004933422909602143,
|
|
"loss": 5.3698,
|
|
"mean_token_accuracy": 0.17607285976409912,
|
|
"num_tokens": 18924603.0,
|
|
"step": 10900
|
|
},
|
|
{
|
|
"entropy": 5.6034938335418705,
|
|
"epoch": 0.8484730597160085,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004933355970321155,
|
|
"loss": 5.2233,
|
|
"mean_token_accuracy": 0.19376989603042602,
|
|
"num_tokens": 18933231.0,
|
|
"step": 10905
|
|
},
|
|
{
|
|
"entropy": 5.643422651290893,
|
|
"epoch": 0.8488620890877261,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004933288997911215,
|
|
"loss": 5.3461,
|
|
"mean_token_accuracy": 0.17191843837499618,
|
|
"num_tokens": 18942172.0,
|
|
"step": 10910
|
|
},
|
|
{
|
|
"entropy": 5.601671886444092,
|
|
"epoch": 0.8492511184594437,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004933221992373338,
|
|
"loss": 5.3014,
|
|
"mean_token_accuracy": 0.18420382738113403,
|
|
"num_tokens": 18951440.0,
|
|
"step": 10915
|
|
},
|
|
{
|
|
"entropy": 5.595506048202514,
|
|
"epoch": 0.8496401478311613,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004933154953708544,
|
|
"loss": 5.2545,
|
|
"mean_token_accuracy": 0.17833930402994155,
|
|
"num_tokens": 18959797.0,
|
|
"step": 10920
|
|
},
|
|
{
|
|
"entropy": 5.569685554504394,
|
|
"epoch": 0.8500291772028788,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004933087881917848,
|
|
"loss": 5.2557,
|
|
"mean_token_accuracy": 0.18182741552591325,
|
|
"num_tokens": 18968811.0,
|
|
"step": 10925
|
|
},
|
|
{
|
|
"entropy": 5.647049331665039,
|
|
"epoch": 0.8504182065745964,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004933020777002268,
|
|
"loss": 5.3944,
|
|
"mean_token_accuracy": 0.1689011871814728,
|
|
"num_tokens": 18977467.0,
|
|
"step": 10930
|
|
},
|
|
{
|
|
"entropy": 5.63600492477417,
|
|
"epoch": 0.8508072359463139,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004932953638962823,
|
|
"loss": 5.2903,
|
|
"mean_token_accuracy": 0.17715788632631302,
|
|
"num_tokens": 18985760.0,
|
|
"step": 10935
|
|
},
|
|
{
|
|
"entropy": 5.675756120681763,
|
|
"epoch": 0.8511962653180315,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000493288646780053,
|
|
"loss": 5.3285,
|
|
"mean_token_accuracy": 0.17073256522417068,
|
|
"num_tokens": 18993812.0,
|
|
"step": 10940
|
|
},
|
|
{
|
|
"entropy": 5.579043006896972,
|
|
"epoch": 0.8515852946897491,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004932819263516409,
|
|
"loss": 5.3169,
|
|
"mean_token_accuracy": 0.17365503907203675,
|
|
"num_tokens": 19003056.0,
|
|
"step": 10945
|
|
},
|
|
{
|
|
"entropy": 5.640437602996826,
|
|
"epoch": 0.8519743240614667,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004932752026111481,
|
|
"loss": 5.326,
|
|
"mean_token_accuracy": 0.18457741886377335,
|
|
"num_tokens": 19011533.0,
|
|
"step": 10950
|
|
},
|
|
{
|
|
"entropy": 5.589516830444336,
|
|
"epoch": 0.8523633534331843,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004932684755586765,
|
|
"loss": 5.2553,
|
|
"mean_token_accuracy": 0.18523511439561843,
|
|
"num_tokens": 19020773.0,
|
|
"step": 10955
|
|
},
|
|
{
|
|
"entropy": 5.556193828582764,
|
|
"epoch": 0.8527523828049017,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004932617451943282,
|
|
"loss": 5.2692,
|
|
"mean_token_accuracy": 0.1786767065525055,
|
|
"num_tokens": 19029809.0,
|
|
"step": 10960
|
|
},
|
|
{
|
|
"entropy": 5.588405799865723,
|
|
"epoch": 0.8531414121766193,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004932550115182053,
|
|
"loss": 5.1919,
|
|
"mean_token_accuracy": 0.18426750153303145,
|
|
"num_tokens": 19038875.0,
|
|
"step": 10965
|
|
},
|
|
{
|
|
"entropy": 5.668352508544922,
|
|
"epoch": 0.8535304415483369,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00049324827453041,
|
|
"loss": 5.2954,
|
|
"mean_token_accuracy": 0.1859284058213234,
|
|
"num_tokens": 19047273.0,
|
|
"step": 10970
|
|
},
|
|
{
|
|
"entropy": 5.5029138088226315,
|
|
"epoch": 0.8539194709200545,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004932415342310446,
|
|
"loss": 5.226,
|
|
"mean_token_accuracy": 0.18578009456396102,
|
|
"num_tokens": 19056309.0,
|
|
"step": 10975
|
|
},
|
|
{
|
|
"entropy": 5.576099920272827,
|
|
"epoch": 0.8543085002917721,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004932347906202111,
|
|
"loss": 5.1929,
|
|
"mean_token_accuracy": 0.18371533304452897,
|
|
"num_tokens": 19064487.0,
|
|
"step": 10980
|
|
},
|
|
{
|
|
"entropy": 5.629020071029663,
|
|
"epoch": 0.8546975296634896,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000493228043698012,
|
|
"loss": 5.4229,
|
|
"mean_token_accuracy": 0.1786932975053787,
|
|
"num_tokens": 19073431.0,
|
|
"step": 10985
|
|
},
|
|
{
|
|
"entropy": 5.579223012924194,
|
|
"epoch": 0.8550865590352071,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004932212934645498,
|
|
"loss": 5.2955,
|
|
"mean_token_accuracy": 0.1799983873963356,
|
|
"num_tokens": 19081648.0,
|
|
"step": 10990
|
|
},
|
|
{
|
|
"entropy": 5.494553661346435,
|
|
"epoch": 0.8554755884069247,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004932145399199268,
|
|
"loss": 5.2156,
|
|
"mean_token_accuracy": 0.18520181775093078,
|
|
"num_tokens": 19090581.0,
|
|
"step": 10995
|
|
},
|
|
{
|
|
"entropy": 5.652668523788452,
|
|
"epoch": 0.8558646177786423,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004932077830642455,
|
|
"loss": 5.291,
|
|
"mean_token_accuracy": 0.17706617563962937,
|
|
"num_tokens": 19098924.0,
|
|
"step": 11000
|
|
},
|
|
{
|
|
"entropy": 5.634372806549072,
|
|
"epoch": 0.8562536471503599,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004932010228976084,
|
|
"loss": 5.2951,
|
|
"mean_token_accuracy": 0.18166774958372117,
|
|
"num_tokens": 19108267.0,
|
|
"step": 11005
|
|
},
|
|
{
|
|
"entropy": 5.644163608551025,
|
|
"epoch": 0.8566426765220774,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000493194259420118,
|
|
"loss": 5.3173,
|
|
"mean_token_accuracy": 0.1759129285812378,
|
|
"num_tokens": 19117158.0,
|
|
"step": 11010
|
|
},
|
|
{
|
|
"entropy": 5.562337493896484,
|
|
"epoch": 0.857031705893795,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000493187492631877,
|
|
"loss": 5.2836,
|
|
"mean_token_accuracy": 0.18314954042434692,
|
|
"num_tokens": 19126013.0,
|
|
"step": 11015
|
|
},
|
|
{
|
|
"entropy": 5.554191589355469,
|
|
"epoch": 0.8574207352655125,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004931807225329882,
|
|
"loss": 5.2311,
|
|
"mean_token_accuracy": 0.18219724297523499,
|
|
"num_tokens": 19134655.0,
|
|
"step": 11020
|
|
},
|
|
{
|
|
"entropy": 5.543011665344238,
|
|
"epoch": 0.8578097646372301,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004931739491235541,
|
|
"loss": 5.1314,
|
|
"mean_token_accuracy": 0.18265994936227797,
|
|
"num_tokens": 19143311.0,
|
|
"step": 11025
|
|
},
|
|
{
|
|
"entropy": 5.607172536849975,
|
|
"epoch": 0.8581987940089477,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004931671724036777,
|
|
"loss": 5.2656,
|
|
"mean_token_accuracy": 0.18656713962554933,
|
|
"num_tokens": 19152422.0,
|
|
"step": 11030
|
|
},
|
|
{
|
|
"entropy": 5.608309650421143,
|
|
"epoch": 0.8585878233806652,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004931603923734616,
|
|
"loss": 5.3731,
|
|
"mean_token_accuracy": 0.17477262318134307,
|
|
"num_tokens": 19161510.0,
|
|
"step": 11035
|
|
},
|
|
{
|
|
"entropy": 5.52988109588623,
|
|
"epoch": 0.8589768527523828,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004931536090330088,
|
|
"loss": 5.1933,
|
|
"mean_token_accuracy": 0.18769892752170564,
|
|
"num_tokens": 19170097.0,
|
|
"step": 11040
|
|
},
|
|
{
|
|
"entropy": 5.5798032760620115,
|
|
"epoch": 0.8593658821241004,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004931468223824222,
|
|
"loss": 5.2359,
|
|
"mean_token_accuracy": 0.18533996045589446,
|
|
"num_tokens": 19179131.0,
|
|
"step": 11045
|
|
},
|
|
{
|
|
"entropy": 5.510780191421508,
|
|
"epoch": 0.859754911495818,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004931400324218048,
|
|
"loss": 5.1521,
|
|
"mean_token_accuracy": 0.18891196697950363,
|
|
"num_tokens": 19187289.0,
|
|
"step": 11050
|
|
},
|
|
{
|
|
"entropy": 5.5318817615509035,
|
|
"epoch": 0.8601439408675355,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004931332391512597,
|
|
"loss": 5.2588,
|
|
"mean_token_accuracy": 0.18268831372261046,
|
|
"num_tokens": 19195746.0,
|
|
"step": 11055
|
|
},
|
|
{
|
|
"entropy": 5.657726907730103,
|
|
"epoch": 0.860532970239253,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004931264425708897,
|
|
"loss": 5.2772,
|
|
"mean_token_accuracy": 0.17957644909620285,
|
|
"num_tokens": 19204683.0,
|
|
"step": 11060
|
|
},
|
|
{
|
|
"entropy": 5.565079832077027,
|
|
"epoch": 0.8609219996109706,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004931196426807983,
|
|
"loss": 5.1942,
|
|
"mean_token_accuracy": 0.1739495277404785,
|
|
"num_tokens": 19213405.0,
|
|
"step": 11065
|
|
},
|
|
{
|
|
"entropy": 5.558668422698974,
|
|
"epoch": 0.8613110289826882,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004931128394810884,
|
|
"loss": 5.2932,
|
|
"mean_token_accuracy": 0.1813378795981407,
|
|
"num_tokens": 19222717.0,
|
|
"step": 11070
|
|
},
|
|
{
|
|
"entropy": 5.656969976425171,
|
|
"epoch": 0.8617000583544058,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004931060329718634,
|
|
"loss": 5.2941,
|
|
"mean_token_accuracy": 0.17425547689199447,
|
|
"num_tokens": 19230688.0,
|
|
"step": 11075
|
|
},
|
|
{
|
|
"entropy": 5.613022518157959,
|
|
"epoch": 0.8620890877261234,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004930992231532265,
|
|
"loss": 5.3514,
|
|
"mean_token_accuracy": 0.1688617140054703,
|
|
"num_tokens": 19239192.0,
|
|
"step": 11080
|
|
},
|
|
{
|
|
"entropy": 5.621093082427978,
|
|
"epoch": 0.8624781170978408,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000493092410025281,
|
|
"loss": 5.3322,
|
|
"mean_token_accuracy": 0.17372597455978395,
|
|
"num_tokens": 19247903.0,
|
|
"step": 11085
|
|
},
|
|
{
|
|
"entropy": 5.603265428543091,
|
|
"epoch": 0.8628671464695584,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004930855935881302,
|
|
"loss": 5.2803,
|
|
"mean_token_accuracy": 0.17990875244140625,
|
|
"num_tokens": 19256127.0,
|
|
"step": 11090
|
|
},
|
|
{
|
|
"entropy": 5.596434783935547,
|
|
"epoch": 0.863256175841276,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004930787738418777,
|
|
"loss": 5.2475,
|
|
"mean_token_accuracy": 0.18377451449632645,
|
|
"num_tokens": 19264742.0,
|
|
"step": 11095
|
|
},
|
|
{
|
|
"entropy": 5.573207521438599,
|
|
"epoch": 0.8636452052129936,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004930719507866269,
|
|
"loss": 5.213,
|
|
"mean_token_accuracy": 0.18178284168243408,
|
|
"num_tokens": 19273618.0,
|
|
"step": 11100
|
|
},
|
|
{
|
|
"entropy": 5.607818603515625,
|
|
"epoch": 0.8640342345847112,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004930651244224814,
|
|
"loss": 5.2712,
|
|
"mean_token_accuracy": 0.18519938588142396,
|
|
"num_tokens": 19281792.0,
|
|
"step": 11105
|
|
},
|
|
{
|
|
"entropy": 5.511165904998779,
|
|
"epoch": 0.8644232639564287,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004930582947495448,
|
|
"loss": 5.2364,
|
|
"mean_token_accuracy": 0.17781448662281035,
|
|
"num_tokens": 19289738.0,
|
|
"step": 11110
|
|
},
|
|
{
|
|
"entropy": 5.619218063354492,
|
|
"epoch": 0.8648122933281462,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004930514617679206,
|
|
"loss": 5.225,
|
|
"mean_token_accuracy": 0.18328847289085387,
|
|
"num_tokens": 19298711.0,
|
|
"step": 11115
|
|
},
|
|
{
|
|
"entropy": 5.670982360839844,
|
|
"epoch": 0.8652013226998638,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004930446254777125,
|
|
"loss": 5.3287,
|
|
"mean_token_accuracy": 0.18125866651535033,
|
|
"num_tokens": 19307435.0,
|
|
"step": 11120
|
|
},
|
|
{
|
|
"entropy": 5.551834154129028,
|
|
"epoch": 0.8655903520715814,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004930377858790242,
|
|
"loss": 5.2042,
|
|
"mean_token_accuracy": 0.18154563158750534,
|
|
"num_tokens": 19315327.0,
|
|
"step": 11125
|
|
},
|
|
{
|
|
"entropy": 5.545620679855347,
|
|
"epoch": 0.865979381443299,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004930309429719595,
|
|
"loss": 5.1551,
|
|
"mean_token_accuracy": 0.1891895890235901,
|
|
"num_tokens": 19323261.0,
|
|
"step": 11130
|
|
},
|
|
{
|
|
"entropy": 5.4682965755462645,
|
|
"epoch": 0.8663684108150166,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004930240967566224,
|
|
"loss": 5.1283,
|
|
"mean_token_accuracy": 0.18640220314264297,
|
|
"num_tokens": 19332297.0,
|
|
"step": 11135
|
|
},
|
|
{
|
|
"entropy": 5.541049814224243,
|
|
"epoch": 0.8667574401867341,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004930172472331167,
|
|
"loss": 5.1663,
|
|
"mean_token_accuracy": 0.18291076570749282,
|
|
"num_tokens": 19340848.0,
|
|
"step": 11140
|
|
},
|
|
{
|
|
"entropy": 5.5286298274993895,
|
|
"epoch": 0.8671464695584516,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004930103944015463,
|
|
"loss": 5.2089,
|
|
"mean_token_accuracy": 0.18289046585559846,
|
|
"num_tokens": 19349072.0,
|
|
"step": 11145
|
|
},
|
|
{
|
|
"entropy": 5.621784114837647,
|
|
"epoch": 0.8675354989301692,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004930035382620149,
|
|
"loss": 5.2659,
|
|
"mean_token_accuracy": 0.18448480367660522,
|
|
"num_tokens": 19357723.0,
|
|
"step": 11150
|
|
},
|
|
{
|
|
"entropy": 5.515363550186157,
|
|
"epoch": 0.8679245283018868,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000492996678814627,
|
|
"loss": 5.2027,
|
|
"mean_token_accuracy": 0.1899164915084839,
|
|
"num_tokens": 19365925.0,
|
|
"step": 11155
|
|
},
|
|
{
|
|
"entropy": 5.50625205039978,
|
|
"epoch": 0.8683135576736044,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004929898160594865,
|
|
"loss": 5.2557,
|
|
"mean_token_accuracy": 0.1823277398943901,
|
|
"num_tokens": 19374190.0,
|
|
"step": 11160
|
|
},
|
|
{
|
|
"entropy": 5.544011402130127,
|
|
"epoch": 0.8687025870453219,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004929829499966974,
|
|
"loss": 5.244,
|
|
"mean_token_accuracy": 0.18081277012825012,
|
|
"num_tokens": 19382375.0,
|
|
"step": 11165
|
|
},
|
|
{
|
|
"entropy": 5.645644044876098,
|
|
"epoch": 0.8690916164170395,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004929760806263641,
|
|
"loss": 5.2952,
|
|
"mean_token_accuracy": 0.18304144740104675,
|
|
"num_tokens": 19390191.0,
|
|
"step": 11170
|
|
},
|
|
{
|
|
"entropy": 5.537923336029053,
|
|
"epoch": 0.8694806457887571,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004929692079485906,
|
|
"loss": 5.0954,
|
|
"mean_token_accuracy": 0.19233231097459794,
|
|
"num_tokens": 19399401.0,
|
|
"step": 11175
|
|
},
|
|
{
|
|
"entropy": 5.514873600006103,
|
|
"epoch": 0.8698696751604746,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004929623319634814,
|
|
"loss": 5.1988,
|
|
"mean_token_accuracy": 0.1855992019176483,
|
|
"num_tokens": 19407956.0,
|
|
"step": 11180
|
|
},
|
|
{
|
|
"entropy": 5.560956764221191,
|
|
"epoch": 0.8702587045321922,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004929554526711407,
|
|
"loss": 5.3478,
|
|
"mean_token_accuracy": 0.180048431456089,
|
|
"num_tokens": 19416432.0,
|
|
"step": 11185
|
|
},
|
|
{
|
|
"entropy": 5.546083641052246,
|
|
"epoch": 0.8706477339039097,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004929485700716729,
|
|
"loss": 5.2248,
|
|
"mean_token_accuracy": 0.18299429714679719,
|
|
"num_tokens": 19425208.0,
|
|
"step": 11190
|
|
},
|
|
{
|
|
"entropy": 5.644758796691894,
|
|
"epoch": 0.8710367632756273,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004929416841651824,
|
|
"loss": 5.3298,
|
|
"mean_token_accuracy": 0.18089791685342788,
|
|
"num_tokens": 19434169.0,
|
|
"step": 11195
|
|
},
|
|
{
|
|
"entropy": 5.550636720657349,
|
|
"epoch": 0.8714257926473449,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004929347949517739,
|
|
"loss": 5.1011,
|
|
"mean_token_accuracy": 0.19305706769227982,
|
|
"num_tokens": 19443484.0,
|
|
"step": 11200
|
|
},
|
|
{
|
|
"entropy": 5.513714361190796,
|
|
"epoch": 0.8718148220190625,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004929279024315516,
|
|
"loss": 5.2667,
|
|
"mean_token_accuracy": 0.18305621594190596,
|
|
"num_tokens": 19452193.0,
|
|
"step": 11205
|
|
},
|
|
{
|
|
"entropy": 5.679654121398926,
|
|
"epoch": 0.87220385139078,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004929210066046204,
|
|
"loss": 5.3846,
|
|
"mean_token_accuracy": 0.17571600824594497,
|
|
"num_tokens": 19460684.0,
|
|
"step": 11210
|
|
},
|
|
{
|
|
"entropy": 5.62515287399292,
|
|
"epoch": 0.8725928807624975,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004929141074710847,
|
|
"loss": 5.2333,
|
|
"mean_token_accuracy": 0.18159908354282378,
|
|
"num_tokens": 19469206.0,
|
|
"step": 11215
|
|
},
|
|
{
|
|
"entropy": 5.55255913734436,
|
|
"epoch": 0.8729819101342151,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004929072050310491,
|
|
"loss": 5.2785,
|
|
"mean_token_accuracy": 0.17789066433906556,
|
|
"num_tokens": 19477514.0,
|
|
"step": 11220
|
|
},
|
|
{
|
|
"entropy": 5.546413421630859,
|
|
"epoch": 0.8733709395059327,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004929002992846188,
|
|
"loss": 5.3287,
|
|
"mean_token_accuracy": 0.17711522430181503,
|
|
"num_tokens": 19486792.0,
|
|
"step": 11225
|
|
},
|
|
{
|
|
"entropy": 5.614936256408692,
|
|
"epoch": 0.8737599688776503,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004928933902318981,
|
|
"loss": 5.2662,
|
|
"mean_token_accuracy": 0.1872934803366661,
|
|
"num_tokens": 19495708.0,
|
|
"step": 11230
|
|
},
|
|
{
|
|
"entropy": 5.656894969940185,
|
|
"epoch": 0.8741489982493679,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000492886477872992,
|
|
"loss": 5.4256,
|
|
"mean_token_accuracy": 0.1650377556681633,
|
|
"num_tokens": 19505063.0,
|
|
"step": 11235
|
|
},
|
|
{
|
|
"entropy": 5.657841396331787,
|
|
"epoch": 0.8745380276210853,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004928795622080054,
|
|
"loss": 5.3524,
|
|
"mean_token_accuracy": 0.17346434891223908,
|
|
"num_tokens": 19514641.0,
|
|
"step": 11240
|
|
},
|
|
{
|
|
"entropy": 5.57841305732727,
|
|
"epoch": 0.8749270569928029,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004928726432370434,
|
|
"loss": 5.2196,
|
|
"mean_token_accuracy": 0.18648359775543213,
|
|
"num_tokens": 19523136.0,
|
|
"step": 11245
|
|
},
|
|
{
|
|
"entropy": 5.529555797576904,
|
|
"epoch": 0.8753160863645205,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004928657209602107,
|
|
"loss": 5.1199,
|
|
"mean_token_accuracy": 0.1928300753235817,
|
|
"num_tokens": 19532258.0,
|
|
"step": 11250
|
|
},
|
|
{
|
|
"entropy": 5.586338853836059,
|
|
"epoch": 0.8757051157362381,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004928587953776125,
|
|
"loss": 5.3626,
|
|
"mean_token_accuracy": 0.17475418597459794,
|
|
"num_tokens": 19541235.0,
|
|
"step": 11255
|
|
},
|
|
{
|
|
"entropy": 5.591464805603027,
|
|
"epoch": 0.8760941451079557,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004928518664893538,
|
|
"loss": 5.2969,
|
|
"mean_token_accuracy": 0.17780354842543603,
|
|
"num_tokens": 19550259.0,
|
|
"step": 11260
|
|
},
|
|
{
|
|
"entropy": 5.645087766647339,
|
|
"epoch": 0.8764831744796732,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004928449342955397,
|
|
"loss": 5.2585,
|
|
"mean_token_accuracy": 0.18799372911453247,
|
|
"num_tokens": 19558500.0,
|
|
"step": 11265
|
|
},
|
|
{
|
|
"entropy": 5.588253593444824,
|
|
"epoch": 0.8768722038513908,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004928379987962756,
|
|
"loss": 5.2056,
|
|
"mean_token_accuracy": 0.18315169215202332,
|
|
"num_tokens": 19566562.0,
|
|
"step": 11270
|
|
},
|
|
{
|
|
"entropy": 5.54454984664917,
|
|
"epoch": 0.8772612332231083,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004928310599916666,
|
|
"loss": 5.23,
|
|
"mean_token_accuracy": 0.1823637768626213,
|
|
"num_tokens": 19575219.0,
|
|
"step": 11275
|
|
},
|
|
{
|
|
"entropy": 5.516556358337402,
|
|
"epoch": 0.8776502625948259,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004928241178818178,
|
|
"loss": 5.1663,
|
|
"mean_token_accuracy": 0.18708829283714296,
|
|
"num_tokens": 19584311.0,
|
|
"step": 11280
|
|
},
|
|
{
|
|
"entropy": 5.5517336368560795,
|
|
"epoch": 0.8780392919665435,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004928171724668349,
|
|
"loss": 5.3106,
|
|
"mean_token_accuracy": 0.1739381805062294,
|
|
"num_tokens": 19593802.0,
|
|
"step": 11285
|
|
},
|
|
{
|
|
"entropy": 5.596087551116943,
|
|
"epoch": 0.878428321338261,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004928102237468229,
|
|
"loss": 5.2712,
|
|
"mean_token_accuracy": 0.18105054050683975,
|
|
"num_tokens": 19603046.0,
|
|
"step": 11290
|
|
},
|
|
{
|
|
"entropy": 5.492772626876831,
|
|
"epoch": 0.8788173507099786,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004928032717218876,
|
|
"loss": 5.154,
|
|
"mean_token_accuracy": 0.1845415100455284,
|
|
"num_tokens": 19611609.0,
|
|
"step": 11295
|
|
},
|
|
{
|
|
"entropy": 5.5506798267364506,
|
|
"epoch": 0.8792063800816962,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004927963163921343,
|
|
"loss": 5.183,
|
|
"mean_token_accuracy": 0.18141555041074753,
|
|
"num_tokens": 19619380.0,
|
|
"step": 11300
|
|
},
|
|
{
|
|
"entropy": 5.6594970703125,
|
|
"epoch": 0.8795954094534137,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004927893577576685,
|
|
"loss": 5.3483,
|
|
"mean_token_accuracy": 0.17350445538759232,
|
|
"num_tokens": 19628336.0,
|
|
"step": 11305
|
|
},
|
|
{
|
|
"entropy": 5.58415036201477,
|
|
"epoch": 0.8799844388251313,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004927823958185959,
|
|
"loss": 5.3135,
|
|
"mean_token_accuracy": 0.18502842932939528,
|
|
"num_tokens": 19637888.0,
|
|
"step": 11310
|
|
},
|
|
{
|
|
"entropy": 5.542030572891235,
|
|
"epoch": 0.8803734681968488,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000492775430575022,
|
|
"loss": 5.2315,
|
|
"mean_token_accuracy": 0.17773975431919098,
|
|
"num_tokens": 19646123.0,
|
|
"step": 11315
|
|
},
|
|
{
|
|
"entropy": 5.550410032272339,
|
|
"epoch": 0.8807624975685664,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004927684620270527,
|
|
"loss": 5.1987,
|
|
"mean_token_accuracy": 0.18863066732883454,
|
|
"num_tokens": 19655264.0,
|
|
"step": 11320
|
|
},
|
|
{
|
|
"entropy": 5.672732877731323,
|
|
"epoch": 0.881151526940284,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004927614901747935,
|
|
"loss": 5.3354,
|
|
"mean_token_accuracy": 0.17010691314935683,
|
|
"num_tokens": 19663594.0,
|
|
"step": 11325
|
|
},
|
|
{
|
|
"entropy": 5.629295063018799,
|
|
"epoch": 0.8815405563120016,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004927545150183503,
|
|
"loss": 5.2882,
|
|
"mean_token_accuracy": 0.17685989290475845,
|
|
"num_tokens": 19671515.0,
|
|
"step": 11330
|
|
},
|
|
{
|
|
"entropy": 5.561790657043457,
|
|
"epoch": 0.8819295856837192,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000492747536557829,
|
|
"loss": 5.1631,
|
|
"mean_token_accuracy": 0.18699969053268434,
|
|
"num_tokens": 19680288.0,
|
|
"step": 11335
|
|
},
|
|
{
|
|
"entropy": 5.577661752700806,
|
|
"epoch": 0.8823186150554367,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004927405547933353,
|
|
"loss": 5.1824,
|
|
"mean_token_accuracy": 0.18766162991523744,
|
|
"num_tokens": 19688717.0,
|
|
"step": 11340
|
|
},
|
|
{
|
|
"entropy": 5.499565696716308,
|
|
"epoch": 0.8827076444271542,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004927335697249753,
|
|
"loss": 5.1276,
|
|
"mean_token_accuracy": 0.19210835099220275,
|
|
"num_tokens": 19697412.0,
|
|
"step": 11345
|
|
},
|
|
{
|
|
"entropy": 5.540387344360352,
|
|
"epoch": 0.8830966737988718,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004927265813528549,
|
|
"loss": 5.2759,
|
|
"mean_token_accuracy": 0.17797500044107437,
|
|
"num_tokens": 19706127.0,
|
|
"step": 11350
|
|
},
|
|
{
|
|
"entropy": 5.658319091796875,
|
|
"epoch": 0.8834857031705894,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004927195896770804,
|
|
"loss": 5.3498,
|
|
"mean_token_accuracy": 0.17664047032594682,
|
|
"num_tokens": 19715178.0,
|
|
"step": 11355
|
|
},
|
|
{
|
|
"entropy": 5.6233717918396,
|
|
"epoch": 0.883874732542307,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004927125946977574,
|
|
"loss": 5.2247,
|
|
"mean_token_accuracy": 0.18304519653320311,
|
|
"num_tokens": 19723814.0,
|
|
"step": 11360
|
|
},
|
|
{
|
|
"entropy": 5.64864411354065,
|
|
"epoch": 0.8842637619140246,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004927055964149923,
|
|
"loss": 5.3606,
|
|
"mean_token_accuracy": 0.17506654262542726,
|
|
"num_tokens": 19732153.0,
|
|
"step": 11365
|
|
},
|
|
{
|
|
"entropy": 5.611151599884034,
|
|
"epoch": 0.884652791285742,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004926985948288914,
|
|
"loss": 5.2671,
|
|
"mean_token_accuracy": 0.18468063473701476,
|
|
"num_tokens": 19740251.0,
|
|
"step": 11370
|
|
},
|
|
{
|
|
"entropy": 5.501591968536377,
|
|
"epoch": 0.8850418206574596,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004926915899395608,
|
|
"loss": 5.1897,
|
|
"mean_token_accuracy": 0.19013190865516663,
|
|
"num_tokens": 19748695.0,
|
|
"step": 11375
|
|
},
|
|
{
|
|
"entropy": 5.552240657806396,
|
|
"epoch": 0.8854308500291772,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004926845817471068,
|
|
"loss": 5.2068,
|
|
"mean_token_accuracy": 0.17810254842042922,
|
|
"num_tokens": 19757674.0,
|
|
"step": 11380
|
|
},
|
|
{
|
|
"entropy": 5.509834671020508,
|
|
"epoch": 0.8858198794008948,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004926775702516358,
|
|
"loss": 5.0912,
|
|
"mean_token_accuracy": 0.18988971710205077,
|
|
"num_tokens": 19765555.0,
|
|
"step": 11385
|
|
},
|
|
{
|
|
"entropy": 5.489891624450683,
|
|
"epoch": 0.8862089087726124,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004926705554532541,
|
|
"loss": 5.2398,
|
|
"mean_token_accuracy": 0.18355209976434708,
|
|
"num_tokens": 19773986.0,
|
|
"step": 11390
|
|
},
|
|
{
|
|
"entropy": 5.598408555984497,
|
|
"epoch": 0.8865979381443299,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004926635373520682,
|
|
"loss": 5.2618,
|
|
"mean_token_accuracy": 0.185488785803318,
|
|
"num_tokens": 19782308.0,
|
|
"step": 11395
|
|
},
|
|
{
|
|
"entropy": 5.5852643013000485,
|
|
"epoch": 0.8869869675160474,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004926565159481845,
|
|
"loss": 5.2103,
|
|
"mean_token_accuracy": 0.17813374549150468,
|
|
"num_tokens": 19790447.0,
|
|
"step": 11400
|
|
},
|
|
{
|
|
"entropy": 5.586507368087768,
|
|
"epoch": 0.887375996887765,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004926494912417097,
|
|
"loss": 5.3312,
|
|
"mean_token_accuracy": 0.1808769389986992,
|
|
"num_tokens": 19798889.0,
|
|
"step": 11405
|
|
},
|
|
{
|
|
"entropy": 5.540809535980225,
|
|
"epoch": 0.8877650262594826,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004926424632327503,
|
|
"loss": 5.1603,
|
|
"mean_token_accuracy": 0.18644642382860183,
|
|
"num_tokens": 19807192.0,
|
|
"step": 11410
|
|
},
|
|
{
|
|
"entropy": 5.607935762405395,
|
|
"epoch": 0.8881540556312002,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004926354319214129,
|
|
"loss": 5.2886,
|
|
"mean_token_accuracy": 0.18072779178619386,
|
|
"num_tokens": 19815864.0,
|
|
"step": 11415
|
|
},
|
|
{
|
|
"entropy": 5.609080839157104,
|
|
"epoch": 0.8885430850029177,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004926283973078041,
|
|
"loss": 5.2193,
|
|
"mean_token_accuracy": 0.17907162606716157,
|
|
"num_tokens": 19823218.0,
|
|
"step": 11420
|
|
},
|
|
{
|
|
"entropy": 5.563449764251709,
|
|
"epoch": 0.8889321143746353,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004926213593920309,
|
|
"loss": 5.2678,
|
|
"mean_token_accuracy": 0.18048640489578247,
|
|
"num_tokens": 19832098.0,
|
|
"step": 11425
|
|
},
|
|
{
|
|
"entropy": 5.553020858764649,
|
|
"epoch": 0.8893211437463528,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004926143181742,
|
|
"loss": 5.1955,
|
|
"mean_token_accuracy": 0.18601744025945663,
|
|
"num_tokens": 19840180.0,
|
|
"step": 11430
|
|
},
|
|
{
|
|
"entropy": 5.574113178253174,
|
|
"epoch": 0.8897101731180704,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004926072736544181,
|
|
"loss": 5.2475,
|
|
"mean_token_accuracy": 0.17808691263198853,
|
|
"num_tokens": 19849016.0,
|
|
"step": 11435
|
|
},
|
|
{
|
|
"entropy": 5.4969141483306885,
|
|
"epoch": 0.890099202489788,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004926002258327922,
|
|
"loss": 5.1901,
|
|
"mean_token_accuracy": 0.18305204212665557,
|
|
"num_tokens": 19858044.0,
|
|
"step": 11440
|
|
},
|
|
{
|
|
"entropy": 5.507494163513184,
|
|
"epoch": 0.8904882318615055,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004925931747094292,
|
|
"loss": 5.1242,
|
|
"mean_token_accuracy": 0.1915612429380417,
|
|
"num_tokens": 19867557.0,
|
|
"step": 11445
|
|
},
|
|
{
|
|
"entropy": 5.559364366531372,
|
|
"epoch": 0.8908772612332231,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004925861202844361,
|
|
"loss": 5.2385,
|
|
"mean_token_accuracy": 0.18321475982666016,
|
|
"num_tokens": 19876009.0,
|
|
"step": 11450
|
|
},
|
|
{
|
|
"entropy": 5.592780590057373,
|
|
"epoch": 0.8912662906049407,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00049257906255792,
|
|
"loss": 5.3242,
|
|
"mean_token_accuracy": 0.177417029440403,
|
|
"num_tokens": 19885085.0,
|
|
"step": 11455
|
|
},
|
|
{
|
|
"entropy": 5.660267639160156,
|
|
"epoch": 0.8916553199766583,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000492572001529988,
|
|
"loss": 5.2678,
|
|
"mean_token_accuracy": 0.1806852012872696,
|
|
"num_tokens": 19893877.0,
|
|
"step": 11460
|
|
},
|
|
{
|
|
"entropy": 5.664147233963012,
|
|
"epoch": 0.8920443493483758,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004925649372007469,
|
|
"loss": 5.3886,
|
|
"mean_token_accuracy": 0.17875148504972457,
|
|
"num_tokens": 19902480.0,
|
|
"step": 11465
|
|
},
|
|
{
|
|
"entropy": 5.562815952301025,
|
|
"epoch": 0.8924333787200933,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004925578695703045,
|
|
"loss": 5.1605,
|
|
"mean_token_accuracy": 0.1883439913392067,
|
|
"num_tokens": 19910981.0,
|
|
"step": 11470
|
|
},
|
|
{
|
|
"entropy": 5.591741371154785,
|
|
"epoch": 0.8928224080918109,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004925507986387676,
|
|
"loss": 5.2847,
|
|
"mean_token_accuracy": 0.1760623872280121,
|
|
"num_tokens": 19920055.0,
|
|
"step": 11475
|
|
},
|
|
{
|
|
"entropy": 5.62313141822815,
|
|
"epoch": 0.8932114374635285,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004925437244062436,
|
|
"loss": 5.3377,
|
|
"mean_token_accuracy": 0.18255451917648316,
|
|
"num_tokens": 19928010.0,
|
|
"step": 11480
|
|
},
|
|
{
|
|
"entropy": 5.62455415725708,
|
|
"epoch": 0.8936004668352461,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004925366468728397,
|
|
"loss": 5.2213,
|
|
"mean_token_accuracy": 0.1811926007270813,
|
|
"num_tokens": 19935992.0,
|
|
"step": 11485
|
|
},
|
|
{
|
|
"entropy": 5.6355571269989015,
|
|
"epoch": 0.8939894962069637,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004925295660386635,
|
|
"loss": 5.3433,
|
|
"mean_token_accuracy": 0.17380679547786712,
|
|
"num_tokens": 19944522.0,
|
|
"step": 11490
|
|
},
|
|
{
|
|
"entropy": 5.688939332962036,
|
|
"epoch": 0.8943785255786811,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004925224819038224,
|
|
"loss": 5.2745,
|
|
"mean_token_accuracy": 0.18633388429880143,
|
|
"num_tokens": 19952991.0,
|
|
"step": 11495
|
|
},
|
|
{
|
|
"entropy": 5.544963312149048,
|
|
"epoch": 0.8947675549503987,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004925153944684239,
|
|
"loss": 5.2916,
|
|
"mean_token_accuracy": 0.1772780016064644,
|
|
"num_tokens": 19962301.0,
|
|
"step": 11500
|
|
},
|
|
{
|
|
"entropy": 5.602243041992187,
|
|
"epoch": 0.8951565843221163,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004925083037325754,
|
|
"loss": 5.3624,
|
|
"mean_token_accuracy": 0.1738313317298889,
|
|
"num_tokens": 19971159.0,
|
|
"step": 11505
|
|
},
|
|
{
|
|
"entropy": 5.633229351043701,
|
|
"epoch": 0.8955456136938339,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004925012096963847,
|
|
"loss": 5.2399,
|
|
"mean_token_accuracy": 0.17955626994371415,
|
|
"num_tokens": 19979608.0,
|
|
"step": 11510
|
|
},
|
|
{
|
|
"entropy": 5.585269641876221,
|
|
"epoch": 0.8959346430655515,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004924941123599593,
|
|
"loss": 5.2266,
|
|
"mean_token_accuracy": 0.18074027001857756,
|
|
"num_tokens": 19988348.0,
|
|
"step": 11515
|
|
},
|
|
{
|
|
"entropy": 5.546251201629639,
|
|
"epoch": 0.896323672437269,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004924870117234069,
|
|
"loss": 5.2439,
|
|
"mean_token_accuracy": 0.17923223376274108,
|
|
"num_tokens": 19996970.0,
|
|
"step": 11520
|
|
},
|
|
{
|
|
"entropy": 5.660845375061035,
|
|
"epoch": 0.8967127018089865,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004924799077868353,
|
|
"loss": 5.3695,
|
|
"mean_token_accuracy": 0.18099111020565034,
|
|
"num_tokens": 20005297.0,
|
|
"step": 11525
|
|
},
|
|
{
|
|
"entropy": 5.6322602272033695,
|
|
"epoch": 0.8971017311807041,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004924728005503522,
|
|
"loss": 5.2969,
|
|
"mean_token_accuracy": 0.1728695034980774,
|
|
"num_tokens": 20013971.0,
|
|
"step": 11530
|
|
},
|
|
{
|
|
"entropy": 5.596248197555542,
|
|
"epoch": 0.8974907605524217,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004924656900140655,
|
|
"loss": 5.2611,
|
|
"mean_token_accuracy": 0.17985946238040923,
|
|
"num_tokens": 20022536.0,
|
|
"step": 11535
|
|
},
|
|
{
|
|
"entropy": 5.545647048950196,
|
|
"epoch": 0.8978797899241393,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004924585761780831,
|
|
"loss": 5.184,
|
|
"mean_token_accuracy": 0.1842767894268036,
|
|
"num_tokens": 20031676.0,
|
|
"step": 11540
|
|
},
|
|
{
|
|
"entropy": 5.617026472091675,
|
|
"epoch": 0.8982688192958569,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000492451459042513,
|
|
"loss": 5.2615,
|
|
"mean_token_accuracy": 0.17981941103935242,
|
|
"num_tokens": 20039783.0,
|
|
"step": 11545
|
|
},
|
|
{
|
|
"entropy": 5.565978336334228,
|
|
"epoch": 0.8986578486675744,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000492444338607463,
|
|
"loss": 5.3078,
|
|
"mean_token_accuracy": 0.17649320214986802,
|
|
"num_tokens": 20047859.0,
|
|
"step": 11550
|
|
},
|
|
{
|
|
"entropy": 5.628445768356324,
|
|
"epoch": 0.899046878039292,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004924372148730413,
|
|
"loss": 5.3464,
|
|
"mean_token_accuracy": 0.17112823724746704,
|
|
"num_tokens": 20056711.0,
|
|
"step": 11555
|
|
},
|
|
{
|
|
"entropy": 5.5603772640228275,
|
|
"epoch": 0.8994359074110095,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000492430087839356,
|
|
"loss": 5.1817,
|
|
"mean_token_accuracy": 0.18270686715841294,
|
|
"num_tokens": 20065715.0,
|
|
"step": 11560
|
|
},
|
|
{
|
|
"entropy": 5.559036779403686,
|
|
"epoch": 0.8998249367827271,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004924229575065152,
|
|
"loss": 5.2834,
|
|
"mean_token_accuracy": 0.18429706245660782,
|
|
"num_tokens": 20073815.0,
|
|
"step": 11565
|
|
},
|
|
{
|
|
"entropy": 5.615834140777588,
|
|
"epoch": 0.9002139661544447,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000492415823874627,
|
|
"loss": 5.2647,
|
|
"mean_token_accuracy": 0.18063076734542846,
|
|
"num_tokens": 20082331.0,
|
|
"step": 11570
|
|
},
|
|
{
|
|
"entropy": 5.588377904891968,
|
|
"epoch": 0.9006029955261622,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004924086869437998,
|
|
"loss": 5.336,
|
|
"mean_token_accuracy": 0.180070897936821,
|
|
"num_tokens": 20091095.0,
|
|
"step": 11575
|
|
},
|
|
{
|
|
"entropy": 5.589910840988159,
|
|
"epoch": 0.9009920248978798,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004924015467141417,
|
|
"loss": 5.2478,
|
|
"mean_token_accuracy": 0.18325827717781068,
|
|
"num_tokens": 20100111.0,
|
|
"step": 11580
|
|
},
|
|
{
|
|
"entropy": 5.6593669891357425,
|
|
"epoch": 0.9013810542695974,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004923944031857613,
|
|
"loss": 5.3149,
|
|
"mean_token_accuracy": 0.183930803835392,
|
|
"num_tokens": 20108542.0,
|
|
"step": 11585
|
|
},
|
|
{
|
|
"entropy": 5.56063814163208,
|
|
"epoch": 0.901770083641315,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004923872563587668,
|
|
"loss": 5.2359,
|
|
"mean_token_accuracy": 0.18408215492963792,
|
|
"num_tokens": 20117831.0,
|
|
"step": 11590
|
|
},
|
|
{
|
|
"entropy": 5.555573034286499,
|
|
"epoch": 0.9021591130130325,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004923801062332666,
|
|
"loss": 5.1851,
|
|
"mean_token_accuracy": 0.18191388994455338,
|
|
"num_tokens": 20127322.0,
|
|
"step": 11595
|
|
},
|
|
{
|
|
"entropy": 5.639308929443359,
|
|
"epoch": 0.90254814238475,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004923729528093694,
|
|
"loss": 5.2383,
|
|
"mean_token_accuracy": 0.18221660554409028,
|
|
"num_tokens": 20135772.0,
|
|
"step": 11600
|
|
},
|
|
{
|
|
"entropy": 5.572954702377319,
|
|
"epoch": 0.9029371717564676,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004923657960871836,
|
|
"loss": 5.2528,
|
|
"mean_token_accuracy": 0.18276721090078354,
|
|
"num_tokens": 20144110.0,
|
|
"step": 11605
|
|
},
|
|
{
|
|
"entropy": 5.613551473617553,
|
|
"epoch": 0.9033262011281852,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004923586360668178,
|
|
"loss": 5.3595,
|
|
"mean_token_accuracy": 0.17548990547657012,
|
|
"num_tokens": 20153391.0,
|
|
"step": 11610
|
|
},
|
|
{
|
|
"entropy": 5.531225395202637,
|
|
"epoch": 0.9037152304999028,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004923514727483807,
|
|
"loss": 5.1895,
|
|
"mean_token_accuracy": 0.1855894073843956,
|
|
"num_tokens": 20161877.0,
|
|
"step": 11615
|
|
},
|
|
{
|
|
"entropy": 5.497713804244995,
|
|
"epoch": 0.9041042598716204,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000492344306131981,
|
|
"loss": 5.1516,
|
|
"mean_token_accuracy": 0.18799446523189545,
|
|
"num_tokens": 20169922.0,
|
|
"step": 11620
|
|
},
|
|
{
|
|
"entropy": 5.488319158554077,
|
|
"epoch": 0.9044932892433378,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004923371362177272,
|
|
"loss": 5.2081,
|
|
"mean_token_accuracy": 0.18522389382123947,
|
|
"num_tokens": 20177780.0,
|
|
"step": 11625
|
|
},
|
|
{
|
|
"entropy": 5.560370588302613,
|
|
"epoch": 0.9048823186150554,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004923299630057284,
|
|
"loss": 5.1973,
|
|
"mean_token_accuracy": 0.18629174381494523,
|
|
"num_tokens": 20186303.0,
|
|
"step": 11630
|
|
},
|
|
{
|
|
"entropy": 5.5183638572692875,
|
|
"epoch": 0.905271347986773,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004923227864960934,
|
|
"loss": 5.1837,
|
|
"mean_token_accuracy": 0.18678800463676454,
|
|
"num_tokens": 20194042.0,
|
|
"step": 11635
|
|
},
|
|
{
|
|
"entropy": 5.456225490570068,
|
|
"epoch": 0.9056603773584906,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000492315606688931,
|
|
"loss": 5.1875,
|
|
"mean_token_accuracy": 0.1878139778971672,
|
|
"num_tokens": 20202929.0,
|
|
"step": 11640
|
|
},
|
|
{
|
|
"entropy": 5.558633136749267,
|
|
"epoch": 0.9060494067302082,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004923084235843501,
|
|
"loss": 5.2404,
|
|
"mean_token_accuracy": 0.17828413993120193,
|
|
"num_tokens": 20210864.0,
|
|
"step": 11645
|
|
},
|
|
{
|
|
"entropy": 5.628408622741699,
|
|
"epoch": 0.9064384361019256,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004923012371824598,
|
|
"loss": 5.2621,
|
|
"mean_token_accuracy": 0.18141427040100097,
|
|
"num_tokens": 20219390.0,
|
|
"step": 11650
|
|
},
|
|
{
|
|
"entropy": 5.574519968032837,
|
|
"epoch": 0.9068274654736432,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000492294047483369,
|
|
"loss": 5.2039,
|
|
"mean_token_accuracy": 0.19042831808328628,
|
|
"num_tokens": 20227241.0,
|
|
"step": 11655
|
|
},
|
|
{
|
|
"entropy": 5.537701225280761,
|
|
"epoch": 0.9072164948453608,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004922868544871869,
|
|
"loss": 5.357,
|
|
"mean_token_accuracy": 0.176102514564991,
|
|
"num_tokens": 20236001.0,
|
|
"step": 11660
|
|
},
|
|
{
|
|
"entropy": 5.62885308265686,
|
|
"epoch": 0.9076055242170784,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004922796581940227,
|
|
"loss": 5.2372,
|
|
"mean_token_accuracy": 0.18050403892993927,
|
|
"num_tokens": 20244316.0,
|
|
"step": 11665
|
|
},
|
|
{
|
|
"entropy": 5.531038522720337,
|
|
"epoch": 0.907994553588796,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004922724586039855,
|
|
"loss": 5.2143,
|
|
"mean_token_accuracy": 0.1854308769106865,
|
|
"num_tokens": 20252693.0,
|
|
"step": 11670
|
|
},
|
|
{
|
|
"entropy": 5.507435750961304,
|
|
"epoch": 0.9083835829605135,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004922652557171846,
|
|
"loss": 5.2566,
|
|
"mean_token_accuracy": 0.1850678652524948,
|
|
"num_tokens": 20262252.0,
|
|
"step": 11675
|
|
},
|
|
{
|
|
"entropy": 5.552498912811279,
|
|
"epoch": 0.9087726123322311,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004922580495337292,
|
|
"loss": 5.0966,
|
|
"mean_token_accuracy": 0.1937366932630539,
|
|
"num_tokens": 20270755.0,
|
|
"step": 11680
|
|
},
|
|
{
|
|
"entropy": 5.562260913848877,
|
|
"epoch": 0.9091616417039486,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004922508400537288,
|
|
"loss": 5.1804,
|
|
"mean_token_accuracy": 0.18096505105495453,
|
|
"num_tokens": 20278739.0,
|
|
"step": 11685
|
|
},
|
|
{
|
|
"entropy": 5.556400442123413,
|
|
"epoch": 0.9095506710756662,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004922436272772926,
|
|
"loss": 5.3292,
|
|
"mean_token_accuracy": 0.1719320610165596,
|
|
"num_tokens": 20288160.0,
|
|
"step": 11690
|
|
},
|
|
{
|
|
"entropy": 5.566889762878418,
|
|
"epoch": 0.9099397004473838,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004922364112045301,
|
|
"loss": 5.2625,
|
|
"mean_token_accuracy": 0.18204254359006883,
|
|
"num_tokens": 20296730.0,
|
|
"step": 11695
|
|
},
|
|
{
|
|
"entropy": 5.574968862533569,
|
|
"epoch": 0.9103287298191013,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000492229191835551,
|
|
"loss": 5.2072,
|
|
"mean_token_accuracy": 0.18102122992277145,
|
|
"num_tokens": 20305941.0,
|
|
"step": 11700
|
|
},
|
|
{
|
|
"entropy": 5.555197858810425,
|
|
"epoch": 0.9107177591908189,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004922219691704645,
|
|
"loss": 5.2278,
|
|
"mean_token_accuracy": 0.18434746861457824,
|
|
"num_tokens": 20314081.0,
|
|
"step": 11705
|
|
},
|
|
{
|
|
"entropy": 5.618513488769532,
|
|
"epoch": 0.9111067885625365,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004922147432093805,
|
|
"loss": 5.2905,
|
|
"mean_token_accuracy": 0.17522201985120772,
|
|
"num_tokens": 20323004.0,
|
|
"step": 11710
|
|
},
|
|
{
|
|
"entropy": 5.584374189376831,
|
|
"epoch": 0.911495817934254,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004922075139524083,
|
|
"loss": 5.1905,
|
|
"mean_token_accuracy": 0.18178245425224304,
|
|
"num_tokens": 20331122.0,
|
|
"step": 11715
|
|
},
|
|
{
|
|
"entropy": 5.551940536499023,
|
|
"epoch": 0.9118848473059716,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000492200281399658,
|
|
"loss": 5.2733,
|
|
"mean_token_accuracy": 0.17392054200172424,
|
|
"num_tokens": 20339602.0,
|
|
"step": 11720
|
|
},
|
|
{
|
|
"entropy": 5.56371488571167,
|
|
"epoch": 0.9122738766776891,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000492193045551239,
|
|
"loss": 5.1372,
|
|
"mean_token_accuracy": 0.1840537041425705,
|
|
"num_tokens": 20348431.0,
|
|
"step": 11725
|
|
},
|
|
{
|
|
"entropy": 5.523512554168701,
|
|
"epoch": 0.9126629060494067,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004921858064072612,
|
|
"loss": 5.1864,
|
|
"mean_token_accuracy": 0.1874503806233406,
|
|
"num_tokens": 20357235.0,
|
|
"step": 11730
|
|
},
|
|
{
|
|
"entropy": 5.556927728652954,
|
|
"epoch": 0.9130519354211243,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004921785639678347,
|
|
"loss": 5.1602,
|
|
"mean_token_accuracy": 0.1839824616909027,
|
|
"num_tokens": 20366169.0,
|
|
"step": 11735
|
|
},
|
|
{
|
|
"entropy": 5.5867105484008786,
|
|
"epoch": 0.9134409647928419,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000492171318233069,
|
|
"loss": 5.2393,
|
|
"mean_token_accuracy": 0.18073418438434602,
|
|
"num_tokens": 20375213.0,
|
|
"step": 11740
|
|
},
|
|
{
|
|
"entropy": 5.527808046340942,
|
|
"epoch": 0.9138299941645595,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004921640692030742,
|
|
"loss": 5.2407,
|
|
"mean_token_accuracy": 0.17796168327331544,
|
|
"num_tokens": 20383992.0,
|
|
"step": 11745
|
|
},
|
|
{
|
|
"entropy": 5.578649473190308,
|
|
"epoch": 0.914219023536277,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004921568168779603,
|
|
"loss": 5.2133,
|
|
"mean_token_accuracy": 0.1853245973587036,
|
|
"num_tokens": 20392318.0,
|
|
"step": 11750
|
|
},
|
|
{
|
|
"entropy": 5.641834449768067,
|
|
"epoch": 0.9146080529079945,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004921495612578374,
|
|
"loss": 5.3316,
|
|
"mean_token_accuracy": 0.1788714274764061,
|
|
"num_tokens": 20401556.0,
|
|
"step": 11755
|
|
},
|
|
{
|
|
"entropy": 5.55460295677185,
|
|
"epoch": 0.9149970822797121,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004921423023428156,
|
|
"loss": 5.2237,
|
|
"mean_token_accuracy": 0.18192702680826187,
|
|
"num_tokens": 20410480.0,
|
|
"step": 11760
|
|
},
|
|
{
|
|
"entropy": 5.535108041763306,
|
|
"epoch": 0.9153861116514297,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004921350401330049,
|
|
"loss": 5.175,
|
|
"mean_token_accuracy": 0.18815360516309737,
|
|
"num_tokens": 20419748.0,
|
|
"step": 11765
|
|
},
|
|
{
|
|
"entropy": 5.574000644683838,
|
|
"epoch": 0.9157751410231473,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004921277746285155,
|
|
"loss": 5.2429,
|
|
"mean_token_accuracy": 0.18199095427989959,
|
|
"num_tokens": 20429552.0,
|
|
"step": 11770
|
|
},
|
|
{
|
|
"entropy": 5.713226652145385,
|
|
"epoch": 0.9161641703948649,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004921205058294579,
|
|
"loss": 5.3085,
|
|
"mean_token_accuracy": 0.1789688929915428,
|
|
"num_tokens": 20438476.0,
|
|
"step": 11775
|
|
},
|
|
{
|
|
"entropy": 5.5220348834991455,
|
|
"epoch": 0.9165531997665823,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000492113233735942,
|
|
"loss": 5.1148,
|
|
"mean_token_accuracy": 0.18550708293914794,
|
|
"num_tokens": 20447035.0,
|
|
"step": 11780
|
|
},
|
|
{
|
|
"entropy": 5.5483856201171875,
|
|
"epoch": 0.9169422291382999,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004921059583480785,
|
|
"loss": 5.2711,
|
|
"mean_token_accuracy": 0.18236800283193588,
|
|
"num_tokens": 20456200.0,
|
|
"step": 11785
|
|
},
|
|
{
|
|
"entropy": 5.585720109939575,
|
|
"epoch": 0.9173312585100175,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004920986796659775,
|
|
"loss": 5.26,
|
|
"mean_token_accuracy": 0.1862987145781517,
|
|
"num_tokens": 20465444.0,
|
|
"step": 11790
|
|
},
|
|
{
|
|
"entropy": 5.536608648300171,
|
|
"epoch": 0.9177202878817351,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004920913976897498,
|
|
"loss": 5.1567,
|
|
"mean_token_accuracy": 0.1878991261124611,
|
|
"num_tokens": 20473851.0,
|
|
"step": 11795
|
|
},
|
|
{
|
|
"entropy": 5.518877983093262,
|
|
"epoch": 0.9181093172534527,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004920841124195055,
|
|
"loss": 5.2428,
|
|
"mean_token_accuracy": 0.18687252402305604,
|
|
"num_tokens": 20482232.0,
|
|
"step": 11800
|
|
},
|
|
{
|
|
"entropy": 5.495103645324707,
|
|
"epoch": 0.9184983466251702,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004920768238553554,
|
|
"loss": 5.1363,
|
|
"mean_token_accuracy": 0.19422158151865004,
|
|
"num_tokens": 20490498.0,
|
|
"step": 11805
|
|
},
|
|
{
|
|
"entropy": 5.533331823348999,
|
|
"epoch": 0.9188873759968877,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004920695319974099,
|
|
"loss": 5.2071,
|
|
"mean_token_accuracy": 0.18390069752931595,
|
|
"num_tokens": 20499125.0,
|
|
"step": 11810
|
|
},
|
|
{
|
|
"entropy": 5.585284805297851,
|
|
"epoch": 0.9192764053686053,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004920622368457798,
|
|
"loss": 5.3503,
|
|
"mean_token_accuracy": 0.18015943318605424,
|
|
"num_tokens": 20507665.0,
|
|
"step": 11815
|
|
},
|
|
{
|
|
"entropy": 5.595728492736816,
|
|
"epoch": 0.9196654347403229,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004920549384005759,
|
|
"loss": 5.2787,
|
|
"mean_token_accuracy": 0.18034791201353073,
|
|
"num_tokens": 20516509.0,
|
|
"step": 11820
|
|
},
|
|
{
|
|
"entropy": 5.597612285614014,
|
|
"epoch": 0.9200544641120405,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004920476366619086,
|
|
"loss": 5.3042,
|
|
"mean_token_accuracy": 0.1835848107933998,
|
|
"num_tokens": 20524830.0,
|
|
"step": 11825
|
|
},
|
|
{
|
|
"entropy": 5.581564140319824,
|
|
"epoch": 0.920443493483758,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000492040331629889,
|
|
"loss": 5.2012,
|
|
"mean_token_accuracy": 0.17886543720960618,
|
|
"num_tokens": 20533746.0,
|
|
"step": 11830
|
|
},
|
|
{
|
|
"entropy": 5.539874839782715,
|
|
"epoch": 0.9208325228554756,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004920330233046277,
|
|
"loss": 5.1779,
|
|
"mean_token_accuracy": 0.1898143023252487,
|
|
"num_tokens": 20542350.0,
|
|
"step": 11835
|
|
},
|
|
{
|
|
"entropy": 5.5576598167419435,
|
|
"epoch": 0.9212215522271932,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004920257116862359,
|
|
"loss": 5.3021,
|
|
"mean_token_accuracy": 0.18487888127565383,
|
|
"num_tokens": 20551670.0,
|
|
"step": 11840
|
|
},
|
|
{
|
|
"entropy": 5.608811140060425,
|
|
"epoch": 0.9216105815989107,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004920183967748241,
|
|
"loss": 5.2466,
|
|
"mean_token_accuracy": 0.17925604432821274,
|
|
"num_tokens": 20560692.0,
|
|
"step": 11845
|
|
},
|
|
{
|
|
"entropy": 5.589293432235718,
|
|
"epoch": 0.9219996109706283,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004920110785705037,
|
|
"loss": 5.1998,
|
|
"mean_token_accuracy": 0.18300125300884246,
|
|
"num_tokens": 20569262.0,
|
|
"step": 11850
|
|
},
|
|
{
|
|
"entropy": 5.537121105194092,
|
|
"epoch": 0.9223886403423458,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004920037570733857,
|
|
"loss": 5.1988,
|
|
"mean_token_accuracy": 0.1828903526067734,
|
|
"num_tokens": 20577850.0,
|
|
"step": 11855
|
|
},
|
|
{
|
|
"entropy": 5.579100322723389,
|
|
"epoch": 0.9227776697140634,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004919964322835809,
|
|
"loss": 5.2813,
|
|
"mean_token_accuracy": 0.17564146369695663,
|
|
"num_tokens": 20587021.0,
|
|
"step": 11860
|
|
},
|
|
{
|
|
"entropy": 5.5887792110443115,
|
|
"epoch": 0.923166699085781,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004919891042012006,
|
|
"loss": 5.2035,
|
|
"mean_token_accuracy": 0.1853077918291092,
|
|
"num_tokens": 20594631.0,
|
|
"step": 11865
|
|
},
|
|
{
|
|
"entropy": 5.519110488891601,
|
|
"epoch": 0.9235557284574986,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004919817728263562,
|
|
"loss": 5.1377,
|
|
"mean_token_accuracy": 0.18740917146205902,
|
|
"num_tokens": 20602765.0,
|
|
"step": 11870
|
|
},
|
|
{
|
|
"entropy": 5.637236833572388,
|
|
"epoch": 0.9239447578292161,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004919744381591586,
|
|
"loss": 5.2648,
|
|
"mean_token_accuracy": 0.19036677181720735,
|
|
"num_tokens": 20611350.0,
|
|
"step": 11875
|
|
},
|
|
{
|
|
"entropy": 5.563019943237305,
|
|
"epoch": 0.9243337872009336,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004919671001997193,
|
|
"loss": 5.192,
|
|
"mean_token_accuracy": 0.18654754161834716,
|
|
"num_tokens": 20620201.0,
|
|
"step": 11880
|
|
},
|
|
{
|
|
"entropy": 5.603507232666016,
|
|
"epoch": 0.9247228165726512,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004919597589481497,
|
|
"loss": 5.2478,
|
|
"mean_token_accuracy": 0.1864937126636505,
|
|
"num_tokens": 20627870.0,
|
|
"step": 11885
|
|
},
|
|
{
|
|
"entropy": 5.5766901016235355,
|
|
"epoch": 0.9251118459443688,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000491952414404561,
|
|
"loss": 5.2431,
|
|
"mean_token_accuracy": 0.18415390998125075,
|
|
"num_tokens": 20635894.0,
|
|
"step": 11890
|
|
},
|
|
{
|
|
"entropy": 5.59851861000061,
|
|
"epoch": 0.9255008753160864,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004919450665690646,
|
|
"loss": 5.2941,
|
|
"mean_token_accuracy": 0.18335267305374145,
|
|
"num_tokens": 20644091.0,
|
|
"step": 11895
|
|
},
|
|
{
|
|
"entropy": 5.58082594871521,
|
|
"epoch": 0.925889904687804,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004919377154417724,
|
|
"loss": 5.1567,
|
|
"mean_token_accuracy": 0.18717770129442216,
|
|
"num_tokens": 20651994.0,
|
|
"step": 11900
|
|
},
|
|
{
|
|
"entropy": 5.537593746185303,
|
|
"epoch": 0.9262789340595214,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004919303610227954,
|
|
"loss": 5.1806,
|
|
"mean_token_accuracy": 0.18851915895938873,
|
|
"num_tokens": 20660192.0,
|
|
"step": 11905
|
|
},
|
|
{
|
|
"entropy": 5.65830979347229,
|
|
"epoch": 0.926667963431239,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004919230033122457,
|
|
"loss": 5.2585,
|
|
"mean_token_accuracy": 0.1791141539812088,
|
|
"num_tokens": 20668275.0,
|
|
"step": 11910
|
|
},
|
|
{
|
|
"entropy": 5.521208429336548,
|
|
"epoch": 0.9270569928029566,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004919156423102345,
|
|
"loss": 5.2391,
|
|
"mean_token_accuracy": 0.18416546583175658,
|
|
"num_tokens": 20676936.0,
|
|
"step": 11915
|
|
},
|
|
{
|
|
"entropy": 5.591800546646118,
|
|
"epoch": 0.9274460221746742,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004919082780168736,
|
|
"loss": 5.3476,
|
|
"mean_token_accuracy": 0.17247433364391326,
|
|
"num_tokens": 20685600.0,
|
|
"step": 11920
|
|
},
|
|
{
|
|
"entropy": 5.603094625473022,
|
|
"epoch": 0.9278350515463918,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004919009104322751,
|
|
"loss": 5.2913,
|
|
"mean_token_accuracy": 0.18120404779911042,
|
|
"num_tokens": 20693714.0,
|
|
"step": 11925
|
|
},
|
|
{
|
|
"entropy": 5.575480985641479,
|
|
"epoch": 0.9282240809181093,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004918935395565503,
|
|
"loss": 5.2368,
|
|
"mean_token_accuracy": 0.1812037318944931,
|
|
"num_tokens": 20702529.0,
|
|
"step": 11930
|
|
},
|
|
{
|
|
"entropy": 5.541878509521484,
|
|
"epoch": 0.9286131102898268,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004918861653898113,
|
|
"loss": 5.1647,
|
|
"mean_token_accuracy": 0.1846123978495598,
|
|
"num_tokens": 20711775.0,
|
|
"step": 11935
|
|
},
|
|
{
|
|
"entropy": 5.582861375808716,
|
|
"epoch": 0.9290021396615444,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004918787879321701,
|
|
"loss": 5.2248,
|
|
"mean_token_accuracy": 0.18018672317266465,
|
|
"num_tokens": 20720653.0,
|
|
"step": 11940
|
|
},
|
|
{
|
|
"entropy": 5.6048431396484375,
|
|
"epoch": 0.929391169033262,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004918714071837384,
|
|
"loss": 5.2494,
|
|
"mean_token_accuracy": 0.18456124812364577,
|
|
"num_tokens": 20729208.0,
|
|
"step": 11945
|
|
},
|
|
{
|
|
"entropy": 5.589124155044556,
|
|
"epoch": 0.9297801984049796,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004918640231446282,
|
|
"loss": 5.3006,
|
|
"mean_token_accuracy": 0.1827417090535164,
|
|
"num_tokens": 20738670.0,
|
|
"step": 11950
|
|
},
|
|
{
|
|
"entropy": 5.562734603881836,
|
|
"epoch": 0.9301692277766972,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004918566358149517,
|
|
"loss": 5.3508,
|
|
"mean_token_accuracy": 0.17917992323637008,
|
|
"num_tokens": 20748315.0,
|
|
"step": 11955
|
|
},
|
|
{
|
|
"entropy": 5.656414747238159,
|
|
"epoch": 0.9305582571484147,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000491849245194821,
|
|
"loss": 5.3902,
|
|
"mean_token_accuracy": 0.17061794102191924,
|
|
"num_tokens": 20757623.0,
|
|
"step": 11960
|
|
},
|
|
{
|
|
"entropy": 5.608323287963867,
|
|
"epoch": 0.9309472865201323,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004918418512843479,
|
|
"loss": 5.2138,
|
|
"mean_token_accuracy": 0.18692825585603715,
|
|
"num_tokens": 20765817.0,
|
|
"step": 11965
|
|
},
|
|
{
|
|
"entropy": 5.521482181549072,
|
|
"epoch": 0.9313363158918498,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004918344540836451,
|
|
"loss": 5.1088,
|
|
"mean_token_accuracy": 0.19574368596076966,
|
|
"num_tokens": 20773931.0,
|
|
"step": 11970
|
|
},
|
|
{
|
|
"entropy": 5.625129652023316,
|
|
"epoch": 0.9317253452635674,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004918270535928244,
|
|
"loss": 5.2492,
|
|
"mean_token_accuracy": 0.17974198013544082,
|
|
"num_tokens": 20782652.0,
|
|
"step": 11975
|
|
},
|
|
{
|
|
"entropy": 5.567449998855591,
|
|
"epoch": 0.932114374635285,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004918196498119984,
|
|
"loss": 5.146,
|
|
"mean_token_accuracy": 0.19232137799263,
|
|
"num_tokens": 20791293.0,
|
|
"step": 11980
|
|
},
|
|
{
|
|
"entropy": 5.533898782730103,
|
|
"epoch": 0.9325034040070025,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004918122427412793,
|
|
"loss": 5.2505,
|
|
"mean_token_accuracy": 0.17886458784341813,
|
|
"num_tokens": 20800317.0,
|
|
"step": 11985
|
|
},
|
|
{
|
|
"entropy": 5.54930272102356,
|
|
"epoch": 0.9328924333787201,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004918048323807795,
|
|
"loss": 5.2269,
|
|
"mean_token_accuracy": 0.19041681736707688,
|
|
"num_tokens": 20809231.0,
|
|
"step": 11990
|
|
},
|
|
{
|
|
"entropy": 5.571619272232056,
|
|
"epoch": 0.9332814627504377,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004917974187306114,
|
|
"loss": 5.1505,
|
|
"mean_token_accuracy": 0.1843850404024124,
|
|
"num_tokens": 20818327.0,
|
|
"step": 11995
|
|
},
|
|
{
|
|
"entropy": 5.614779090881347,
|
|
"epoch": 0.9336704921221552,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004917900017908875,
|
|
"loss": 5.3149,
|
|
"mean_token_accuracy": 0.17424997091293334,
|
|
"num_tokens": 20826995.0,
|
|
"step": 12000
|
|
},
|
|
{
|
|
"epoch": 0.9336704921221552,
|
|
"eval_entropy": 5.3652247088361635,
|
|
"eval_loss": 5.260458469390869,
|
|
"eval_mean_token_accuracy": 0.19026692330234893,
|
|
"eval_num_tokens": 20826995.0,
|
|
"eval_runtime": 21.5957,
|
|
"eval_samples_per_second": 1924.368,
|
|
"eval_steps_per_second": 240.558,
|
|
"step": 12000
|
|
},
|
|
{
|
|
"entropy": 5.476382541656494,
|
|
"epoch": 0.9340595214938728,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004917825815617205,
|
|
"loss": 5.0362,
|
|
"mean_token_accuracy": 0.1938027784228325,
|
|
"num_tokens": 20835641.0,
|
|
"step": 12005
|
|
},
|
|
{
|
|
"entropy": 5.586126899719238,
|
|
"epoch": 0.9344485508655903,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004917751580432229,
|
|
"loss": 5.1696,
|
|
"mean_token_accuracy": 0.18758552074432372,
|
|
"num_tokens": 20844728.0,
|
|
"step": 12010
|
|
},
|
|
{
|
|
"entropy": 5.511921501159668,
|
|
"epoch": 0.9348375802373079,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004917677312355072,
|
|
"loss": 5.1688,
|
|
"mean_token_accuracy": 0.18927164226770402,
|
|
"num_tokens": 20853013.0,
|
|
"step": 12015
|
|
},
|
|
{
|
|
"entropy": 5.629630088806152,
|
|
"epoch": 0.9352266096090255,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004917603011386863,
|
|
"loss": 5.24,
|
|
"mean_token_accuracy": 0.18145138621330262,
|
|
"num_tokens": 20861592.0,
|
|
"step": 12020
|
|
},
|
|
{
|
|
"entropy": 5.552721214294434,
|
|
"epoch": 0.9356156389807431,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004917528677528727,
|
|
"loss": 5.2046,
|
|
"mean_token_accuracy": 0.18107561618089676,
|
|
"num_tokens": 20869645.0,
|
|
"step": 12025
|
|
},
|
|
{
|
|
"entropy": 5.590920114517212,
|
|
"epoch": 0.9360046683524607,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004917454310781795,
|
|
"loss": 5.2526,
|
|
"mean_token_accuracy": 0.18239778727293016,
|
|
"num_tokens": 20878154.0,
|
|
"step": 12030
|
|
},
|
|
{
|
|
"entropy": 5.593302011489868,
|
|
"epoch": 0.9363936977241781,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004917379911147193,
|
|
"loss": 5.1964,
|
|
"mean_token_accuracy": 0.19307635277509688,
|
|
"num_tokens": 20886260.0,
|
|
"step": 12035
|
|
},
|
|
{
|
|
"entropy": 5.5298034191131595,
|
|
"epoch": 0.9367827270958957,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004917305478626049,
|
|
"loss": 5.1609,
|
|
"mean_token_accuracy": 0.1862980455160141,
|
|
"num_tokens": 20895688.0,
|
|
"step": 12040
|
|
},
|
|
{
|
|
"entropy": 5.5384777069091795,
|
|
"epoch": 0.9371717564676133,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004917231013219495,
|
|
"loss": 5.2756,
|
|
"mean_token_accuracy": 0.1831613928079605,
|
|
"num_tokens": 20903904.0,
|
|
"step": 12045
|
|
},
|
|
{
|
|
"entropy": 5.602621603012085,
|
|
"epoch": 0.9375607858393309,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000491715651492866,
|
|
"loss": 5.2673,
|
|
"mean_token_accuracy": 0.18519030660390853,
|
|
"num_tokens": 20913411.0,
|
|
"step": 12050
|
|
},
|
|
{
|
|
"entropy": 5.581089019775391,
|
|
"epoch": 0.9379498152110485,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004917081983754675,
|
|
"loss": 5.2303,
|
|
"mean_token_accuracy": 0.18019794374704362,
|
|
"num_tokens": 20922088.0,
|
|
"step": 12055
|
|
},
|
|
{
|
|
"entropy": 5.4662697315216064,
|
|
"epoch": 0.938338844582766,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004917007419698669,
|
|
"loss": 5.2267,
|
|
"mean_token_accuracy": 0.18475015014410018,
|
|
"num_tokens": 20930879.0,
|
|
"step": 12060
|
|
},
|
|
{
|
|
"entropy": 5.519509220123291,
|
|
"epoch": 0.9387278739544835,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004916932822761776,
|
|
"loss": 5.192,
|
|
"mean_token_accuracy": 0.18773053586483002,
|
|
"num_tokens": 20939092.0,
|
|
"step": 12065
|
|
},
|
|
{
|
|
"entropy": 5.567389726638794,
|
|
"epoch": 0.9391169033262011,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004916858192945126,
|
|
"loss": 5.2424,
|
|
"mean_token_accuracy": 0.1826593279838562,
|
|
"num_tokens": 20947599.0,
|
|
"step": 12070
|
|
},
|
|
{
|
|
"entropy": 5.617564725875854,
|
|
"epoch": 0.9395059326979187,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004916783530249852,
|
|
"loss": 5.297,
|
|
"mean_token_accuracy": 0.17814621776342393,
|
|
"num_tokens": 20955725.0,
|
|
"step": 12075
|
|
},
|
|
{
|
|
"entropy": 5.498813343048096,
|
|
"epoch": 0.9398949620696363,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004916708834677086,
|
|
"loss": 5.105,
|
|
"mean_token_accuracy": 0.19145222306251525,
|
|
"num_tokens": 20965040.0,
|
|
"step": 12080
|
|
},
|
|
{
|
|
"entropy": 5.581015491485596,
|
|
"epoch": 0.9402839914413538,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004916634106227962,
|
|
"loss": 5.2505,
|
|
"mean_token_accuracy": 0.1820598751306534,
|
|
"num_tokens": 20974204.0,
|
|
"step": 12085
|
|
},
|
|
{
|
|
"entropy": 5.6329758644104,
|
|
"epoch": 0.9406730208130714,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004916559344903614,
|
|
"loss": 5.2536,
|
|
"mean_token_accuracy": 0.18456069827079774,
|
|
"num_tokens": 20982109.0,
|
|
"step": 12090
|
|
},
|
|
{
|
|
"entropy": 5.579155397415161,
|
|
"epoch": 0.941062050184789,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004916484550705176,
|
|
"loss": 5.2732,
|
|
"mean_token_accuracy": 0.1756502389907837,
|
|
"num_tokens": 20990375.0,
|
|
"step": 12095
|
|
},
|
|
{
|
|
"entropy": 5.571983337402344,
|
|
"epoch": 0.9414510795565065,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004916409723633785,
|
|
"loss": 5.2959,
|
|
"mean_token_accuracy": 0.18447652012109755,
|
|
"num_tokens": 20998535.0,
|
|
"step": 12100
|
|
},
|
|
{
|
|
"entropy": 5.517458200454712,
|
|
"epoch": 0.9418401089282241,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004916334863690573,
|
|
"loss": 5.1476,
|
|
"mean_token_accuracy": 0.18308708369731902,
|
|
"num_tokens": 21006597.0,
|
|
"step": 12105
|
|
},
|
|
{
|
|
"entropy": 5.572100687026977,
|
|
"epoch": 0.9422291382999416,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004916259970876678,
|
|
"loss": 5.2134,
|
|
"mean_token_accuracy": 0.18781745731830596,
|
|
"num_tokens": 21015498.0,
|
|
"step": 12110
|
|
},
|
|
{
|
|
"entropy": 5.6254716396331785,
|
|
"epoch": 0.9426181676716592,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004916185045193237,
|
|
"loss": 5.2534,
|
|
"mean_token_accuracy": 0.17619127333164214,
|
|
"num_tokens": 21024090.0,
|
|
"step": 12115
|
|
},
|
|
{
|
|
"entropy": 5.594352388381958,
|
|
"epoch": 0.9430071970433768,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004916110086641384,
|
|
"loss": 5.2696,
|
|
"mean_token_accuracy": 0.17645178884267806,
|
|
"num_tokens": 21032928.0,
|
|
"step": 12120
|
|
},
|
|
{
|
|
"entropy": 5.620367193222046,
|
|
"epoch": 0.9433962264150944,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004916035095222259,
|
|
"loss": 5.3366,
|
|
"mean_token_accuracy": 0.17488097101449968,
|
|
"num_tokens": 21041467.0,
|
|
"step": 12125
|
|
},
|
|
{
|
|
"entropy": 5.601778411865235,
|
|
"epoch": 0.9437852557868119,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004915960070936999,
|
|
"loss": 5.2584,
|
|
"mean_token_accuracy": 0.1897648349404335,
|
|
"num_tokens": 21049325.0,
|
|
"step": 12130
|
|
},
|
|
{
|
|
"entropy": 5.568003797531128,
|
|
"epoch": 0.9441742851585294,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004915885013786742,
|
|
"loss": 5.3149,
|
|
"mean_token_accuracy": 0.17808953821659088,
|
|
"num_tokens": 21057911.0,
|
|
"step": 12135
|
|
},
|
|
{
|
|
"entropy": 5.611033773422241,
|
|
"epoch": 0.944563314530247,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004915809923772628,
|
|
"loss": 5.298,
|
|
"mean_token_accuracy": 0.17284227013587952,
|
|
"num_tokens": 21066974.0,
|
|
"step": 12140
|
|
},
|
|
{
|
|
"entropy": 5.602640533447266,
|
|
"epoch": 0.9449523439019646,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004915734800895796,
|
|
"loss": 5.2294,
|
|
"mean_token_accuracy": 0.1814958468079567,
|
|
"num_tokens": 21075591.0,
|
|
"step": 12145
|
|
},
|
|
{
|
|
"entropy": 5.572117328643799,
|
|
"epoch": 0.9453413732736822,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004915659645157383,
|
|
"loss": 5.2703,
|
|
"mean_token_accuracy": 0.18109863251447678,
|
|
"num_tokens": 21084496.0,
|
|
"step": 12150
|
|
},
|
|
{
|
|
"entropy": 5.6210774898529055,
|
|
"epoch": 0.9457304026453998,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004915584456558535,
|
|
"loss": 5.1573,
|
|
"mean_token_accuracy": 0.18336624652147293,
|
|
"num_tokens": 21092811.0,
|
|
"step": 12155
|
|
},
|
|
{
|
|
"entropy": 5.612228155136108,
|
|
"epoch": 0.9461194320171173,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004915509235100388,
|
|
"loss": 5.2221,
|
|
"mean_token_accuracy": 0.18512363731861115,
|
|
"num_tokens": 21101449.0,
|
|
"step": 12160
|
|
},
|
|
{
|
|
"entropy": 5.67351598739624,
|
|
"epoch": 0.9465084613888348,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004915433980784086,
|
|
"loss": 5.3351,
|
|
"mean_token_accuracy": 0.17369821220636367,
|
|
"num_tokens": 21109476.0,
|
|
"step": 12165
|
|
},
|
|
{
|
|
"entropy": 5.556552505493164,
|
|
"epoch": 0.9468974907605524,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004915358693610769,
|
|
"loss": 5.2253,
|
|
"mean_token_accuracy": 0.18115261644124986,
|
|
"num_tokens": 21118431.0,
|
|
"step": 12170
|
|
},
|
|
{
|
|
"entropy": 5.540670347213745,
|
|
"epoch": 0.94728652013227,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004915283373581581,
|
|
"loss": 5.2133,
|
|
"mean_token_accuracy": 0.18355928510427474,
|
|
"num_tokens": 21127390.0,
|
|
"step": 12175
|
|
},
|
|
{
|
|
"entropy": 5.659769105911255,
|
|
"epoch": 0.9476755495039876,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004915208020697664,
|
|
"loss": 5.3076,
|
|
"mean_token_accuracy": 0.17318570911884307,
|
|
"num_tokens": 21136323.0,
|
|
"step": 12180
|
|
},
|
|
{
|
|
"entropy": 5.5947404384613035,
|
|
"epoch": 0.9480645788757052,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004915132634960162,
|
|
"loss": 5.2529,
|
|
"mean_token_accuracy": 0.1843479171395302,
|
|
"num_tokens": 21145228.0,
|
|
"step": 12185
|
|
},
|
|
{
|
|
"entropy": 5.575587368011474,
|
|
"epoch": 0.9484536082474226,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004915057216370218,
|
|
"loss": 5.1696,
|
|
"mean_token_accuracy": 0.18563294559717178,
|
|
"num_tokens": 21153288.0,
|
|
"step": 12190
|
|
},
|
|
{
|
|
"entropy": 5.552964353561402,
|
|
"epoch": 0.9488426376191402,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004914981764928977,
|
|
"loss": 5.215,
|
|
"mean_token_accuracy": 0.1865030899643898,
|
|
"num_tokens": 21161802.0,
|
|
"step": 12195
|
|
},
|
|
{
|
|
"entropy": 5.504632616043091,
|
|
"epoch": 0.9492316669908578,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004914906280637584,
|
|
"loss": 5.1629,
|
|
"mean_token_accuracy": 0.18965061008930206,
|
|
"num_tokens": 21170018.0,
|
|
"step": 12200
|
|
},
|
|
{
|
|
"entropy": 5.659635448455811,
|
|
"epoch": 0.9496206963625754,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004914830763497183,
|
|
"loss": 5.3583,
|
|
"mean_token_accuracy": 0.16727759540081025,
|
|
"num_tokens": 21179128.0,
|
|
"step": 12205
|
|
},
|
|
{
|
|
"entropy": 5.635401105880737,
|
|
"epoch": 0.950009725734293,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004914755213508922,
|
|
"loss": 5.2064,
|
|
"mean_token_accuracy": 0.18544783741235732,
|
|
"num_tokens": 21188138.0,
|
|
"step": 12210
|
|
},
|
|
{
|
|
"entropy": 5.600381088256836,
|
|
"epoch": 0.9503987551060105,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004914679630673945,
|
|
"loss": 5.2836,
|
|
"mean_token_accuracy": 0.18301821649074554,
|
|
"num_tokens": 21196465.0,
|
|
"step": 12215
|
|
},
|
|
{
|
|
"entropy": 5.557601499557495,
|
|
"epoch": 0.950787784477728,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004914604014993401,
|
|
"loss": 5.1828,
|
|
"mean_token_accuracy": 0.1813039004802704,
|
|
"num_tokens": 21205309.0,
|
|
"step": 12220
|
|
},
|
|
{
|
|
"entropy": 5.536256980895996,
|
|
"epoch": 0.9511768138494456,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004914528366468436,
|
|
"loss": 5.148,
|
|
"mean_token_accuracy": 0.19110174030065535,
|
|
"num_tokens": 21214216.0,
|
|
"step": 12225
|
|
},
|
|
{
|
|
"entropy": 5.52139630317688,
|
|
"epoch": 0.9515658432211632,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004914452685100199,
|
|
"loss": 5.1673,
|
|
"mean_token_accuracy": 0.18793029487133026,
|
|
"num_tokens": 21222246.0,
|
|
"step": 12230
|
|
},
|
|
{
|
|
"entropy": 5.547867727279663,
|
|
"epoch": 0.9519548725928808,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004914376970889836,
|
|
"loss": 5.2197,
|
|
"mean_token_accuracy": 0.18555752485990523,
|
|
"num_tokens": 21230696.0,
|
|
"step": 12235
|
|
},
|
|
{
|
|
"entropy": 5.6180586338043215,
|
|
"epoch": 0.9523439019645983,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004914301223838497,
|
|
"loss": 5.3321,
|
|
"mean_token_accuracy": 0.18029067367315293,
|
|
"num_tokens": 21239909.0,
|
|
"step": 12240
|
|
},
|
|
{
|
|
"entropy": 5.555740070343018,
|
|
"epoch": 0.9527329313363159,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004914225443947334,
|
|
"loss": 5.1897,
|
|
"mean_token_accuracy": 0.1832535222172737,
|
|
"num_tokens": 21248124.0,
|
|
"step": 12245
|
|
},
|
|
{
|
|
"entropy": 5.688931512832641,
|
|
"epoch": 0.9531219607080335,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004914149631217494,
|
|
"loss": 5.3857,
|
|
"mean_token_accuracy": 0.1684218630194664,
|
|
"num_tokens": 21257042.0,
|
|
"step": 12250
|
|
},
|
|
{
|
|
"entropy": 5.659134578704834,
|
|
"epoch": 0.953510990079751,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004914073785650127,
|
|
"loss": 5.319,
|
|
"mean_token_accuracy": 0.17946300953626632,
|
|
"num_tokens": 21265627.0,
|
|
"step": 12255
|
|
},
|
|
{
|
|
"entropy": 5.622348594665527,
|
|
"epoch": 0.9539000194514686,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004913997907246385,
|
|
"loss": 5.2302,
|
|
"mean_token_accuracy": 0.1794123485684395,
|
|
"num_tokens": 21273688.0,
|
|
"step": 12260
|
|
},
|
|
{
|
|
"entropy": 5.573261499404907,
|
|
"epoch": 0.9542890488231861,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.000491392199600742,
|
|
"loss": 5.2167,
|
|
"mean_token_accuracy": 0.1829856112599373,
|
|
"num_tokens": 21283432.0,
|
|
"step": 12265
|
|
},
|
|
{
|
|
"entropy": 5.601358890533447,
|
|
"epoch": 0.9546780781949037,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004913846051934382,
|
|
"loss": 5.257,
|
|
"mean_token_accuracy": 0.1796272873878479,
|
|
"num_tokens": 21292003.0,
|
|
"step": 12270
|
|
},
|
|
{
|
|
"entropy": 5.541041088104248,
|
|
"epoch": 0.9550671075666213,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004913770075028425,
|
|
"loss": 5.1712,
|
|
"mean_token_accuracy": 0.18643339425325395,
|
|
"num_tokens": 21299914.0,
|
|
"step": 12275
|
|
},
|
|
{
|
|
"entropy": 5.59332242012024,
|
|
"epoch": 0.9554561369383389,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004913694065290701,
|
|
"loss": 5.3817,
|
|
"mean_token_accuracy": 0.16797806769609452,
|
|
"num_tokens": 21309398.0,
|
|
"step": 12280
|
|
},
|
|
{
|
|
"entropy": 5.588516473770142,
|
|
"epoch": 0.9558451663100564,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004913618022722363,
|
|
"loss": 5.2111,
|
|
"mean_token_accuracy": 0.18153220415115356,
|
|
"num_tokens": 21317828.0,
|
|
"step": 12285
|
|
},
|
|
{
|
|
"entropy": 5.65195107460022,
|
|
"epoch": 0.9562341956817739,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004913541947324566,
|
|
"loss": 5.3281,
|
|
"mean_token_accuracy": 0.1786283001303673,
|
|
"num_tokens": 21326266.0,
|
|
"step": 12290
|
|
},
|
|
{
|
|
"entropy": 5.663617181777954,
|
|
"epoch": 0.9566232250534915,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004913465839098463,
|
|
"loss": 5.2539,
|
|
"mean_token_accuracy": 0.17708837538957595,
|
|
"num_tokens": 21335476.0,
|
|
"step": 12295
|
|
},
|
|
{
|
|
"entropy": 5.6138804912567135,
|
|
"epoch": 0.9570122544252091,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004913389698045209,
|
|
"loss": 5.187,
|
|
"mean_token_accuracy": 0.18348243534564973,
|
|
"num_tokens": 21344045.0,
|
|
"step": 12300
|
|
},
|
|
{
|
|
"entropy": 5.578237009048462,
|
|
"epoch": 0.9574012837969267,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000491331352416596,
|
|
"loss": 5.2092,
|
|
"mean_token_accuracy": 0.1864698812365532,
|
|
"num_tokens": 21352309.0,
|
|
"step": 12305
|
|
},
|
|
{
|
|
"entropy": 5.512121343612671,
|
|
"epoch": 0.9577903131686443,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004913237317461872,
|
|
"loss": 5.2582,
|
|
"mean_token_accuracy": 0.18393941223621368,
|
|
"num_tokens": 21362164.0,
|
|
"step": 12310
|
|
},
|
|
{
|
|
"entropy": 5.687423753738403,
|
|
"epoch": 0.9581793425403617,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00049131610779341,
|
|
"loss": 5.218,
|
|
"mean_token_accuracy": 0.18826501369476317,
|
|
"num_tokens": 21372817.0,
|
|
"step": 12315
|
|
},
|
|
{
|
|
"entropy": 5.599769735336304,
|
|
"epoch": 0.9585683719120793,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004913084805583803,
|
|
"loss": 5.2089,
|
|
"mean_token_accuracy": 0.18398718237876893,
|
|
"num_tokens": 21381035.0,
|
|
"step": 12320
|
|
},
|
|
{
|
|
"entropy": 5.522907781600952,
|
|
"epoch": 0.9589574012837969,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004913008500412136,
|
|
"loss": 5.1759,
|
|
"mean_token_accuracy": 0.19183382838964463,
|
|
"num_tokens": 21390074.0,
|
|
"step": 12325
|
|
},
|
|
{
|
|
"entropy": 5.576920461654663,
|
|
"epoch": 0.9593464306555145,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004912932162420259,
|
|
"loss": 5.2284,
|
|
"mean_token_accuracy": 0.17680705487728118,
|
|
"num_tokens": 21398726.0,
|
|
"step": 12330
|
|
},
|
|
{
|
|
"entropy": 5.612211561203003,
|
|
"epoch": 0.9597354600272321,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004912855791609327,
|
|
"loss": 5.2216,
|
|
"mean_token_accuracy": 0.17984077483415603,
|
|
"num_tokens": 21407225.0,
|
|
"step": 12335
|
|
},
|
|
{
|
|
"entropy": 5.5571564674377445,
|
|
"epoch": 0.9601244893989496,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004912779387980502,
|
|
"loss": 5.2014,
|
|
"mean_token_accuracy": 0.18145482540130614,
|
|
"num_tokens": 21416746.0,
|
|
"step": 12340
|
|
},
|
|
{
|
|
"entropy": 5.579716920852661,
|
|
"epoch": 0.9605135187706672,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004912702951534942,
|
|
"loss": 5.2703,
|
|
"mean_token_accuracy": 0.17398476898670195,
|
|
"num_tokens": 21425621.0,
|
|
"step": 12345
|
|
},
|
|
{
|
|
"entropy": 5.5823915004730225,
|
|
"epoch": 0.9609025481423847,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004912626482273809,
|
|
"loss": 5.1622,
|
|
"mean_token_accuracy": 0.19778977781534196,
|
|
"num_tokens": 21433674.0,
|
|
"step": 12350
|
|
},
|
|
{
|
|
"entropy": 5.59567699432373,
|
|
"epoch": 0.9612915775141023,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004912549980198258,
|
|
"loss": 5.263,
|
|
"mean_token_accuracy": 0.18211924731731416,
|
|
"num_tokens": 21442285.0,
|
|
"step": 12355
|
|
},
|
|
{
|
|
"entropy": 5.591646671295166,
|
|
"epoch": 0.9616806068858199,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004912473445309455,
|
|
"loss": 5.2198,
|
|
"mean_token_accuracy": 0.1867017537355423,
|
|
"num_tokens": 21450345.0,
|
|
"step": 12360
|
|
},
|
|
{
|
|
"entropy": 5.490157270431519,
|
|
"epoch": 0.9620696362575375,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000491239687760856,
|
|
"loss": 5.1355,
|
|
"mean_token_accuracy": 0.19054339826107025,
|
|
"num_tokens": 21458618.0,
|
|
"step": 12365
|
|
},
|
|
{
|
|
"entropy": 5.485005903244018,
|
|
"epoch": 0.962458665629255,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004912320277096732,
|
|
"loss": 5.1701,
|
|
"mean_token_accuracy": 0.18405425697565078,
|
|
"num_tokens": 21467410.0,
|
|
"step": 12370
|
|
},
|
|
{
|
|
"entropy": 5.5545494556427,
|
|
"epoch": 0.9628476950009726,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004912243643775137,
|
|
"loss": 5.2239,
|
|
"mean_token_accuracy": 0.17915583848953248,
|
|
"num_tokens": 21475454.0,
|
|
"step": 12375
|
|
},
|
|
{
|
|
"entropy": 5.539155912399292,
|
|
"epoch": 0.9632367243726901,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004912166977644936,
|
|
"loss": 5.1399,
|
|
"mean_token_accuracy": 0.18764171302318572,
|
|
"num_tokens": 21483431.0,
|
|
"step": 12380
|
|
},
|
|
{
|
|
"entropy": 5.560909032821655,
|
|
"epoch": 0.9636257537444077,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004912090278707293,
|
|
"loss": 5.2157,
|
|
"mean_token_accuracy": 0.18055916875600814,
|
|
"num_tokens": 21491199.0,
|
|
"step": 12385
|
|
},
|
|
{
|
|
"entropy": 5.563940858840942,
|
|
"epoch": 0.9640147831161253,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000491201354696337,
|
|
"loss": 5.3014,
|
|
"mean_token_accuracy": 0.17994246184825896,
|
|
"num_tokens": 21500339.0,
|
|
"step": 12390
|
|
},
|
|
{
|
|
"entropy": 5.576026535034179,
|
|
"epoch": 0.9644038124878428,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004911936782414334,
|
|
"loss": 5.2521,
|
|
"mean_token_accuracy": 0.18026733994483948,
|
|
"num_tokens": 21508945.0,
|
|
"step": 12395
|
|
},
|
|
{
|
|
"entropy": 5.604353952407837,
|
|
"epoch": 0.9647928418595604,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004911859985061348,
|
|
"loss": 5.214,
|
|
"mean_token_accuracy": 0.1814992293715477,
|
|
"num_tokens": 21517649.0,
|
|
"step": 12400
|
|
},
|
|
{
|
|
"entropy": 5.590505218505859,
|
|
"epoch": 0.965181871231278,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004911783154905577,
|
|
"loss": 5.2124,
|
|
"mean_token_accuracy": 0.1816068634390831,
|
|
"num_tokens": 21526650.0,
|
|
"step": 12405
|
|
},
|
|
{
|
|
"entropy": 5.612040615081787,
|
|
"epoch": 0.9655709006029956,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004911706291948188,
|
|
"loss": 5.2318,
|
|
"mean_token_accuracy": 0.18331041932106018,
|
|
"num_tokens": 21535401.0,
|
|
"step": 12410
|
|
},
|
|
{
|
|
"entropy": 5.647918748855591,
|
|
"epoch": 0.9659599299747131,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004911629396190348,
|
|
"loss": 5.2607,
|
|
"mean_token_accuracy": 0.17844109684228898,
|
|
"num_tokens": 21543973.0,
|
|
"step": 12415
|
|
},
|
|
{
|
|
"entropy": 5.522848224639892,
|
|
"epoch": 0.9663489593464306,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004911552467633221,
|
|
"loss": 5.2032,
|
|
"mean_token_accuracy": 0.18064285814762115,
|
|
"num_tokens": 21552875.0,
|
|
"step": 12420
|
|
},
|
|
{
|
|
"entropy": 5.484639310836792,
|
|
"epoch": 0.9667379887181482,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004911475506277976,
|
|
"loss": 5.1251,
|
|
"mean_token_accuracy": 0.1943623512983322,
|
|
"num_tokens": 21561469.0,
|
|
"step": 12425
|
|
},
|
|
{
|
|
"entropy": 5.5896384716033936,
|
|
"epoch": 0.9671270180898658,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000491139851212578,
|
|
"loss": 5.1998,
|
|
"mean_token_accuracy": 0.19158778935670853,
|
|
"num_tokens": 21569523.0,
|
|
"step": 12430
|
|
},
|
|
{
|
|
"entropy": 5.535619258880615,
|
|
"epoch": 0.9675160474615834,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004911321485177802,
|
|
"loss": 5.1592,
|
|
"mean_token_accuracy": 0.18858758807182313,
|
|
"num_tokens": 21577700.0,
|
|
"step": 12435
|
|
},
|
|
{
|
|
"entropy": 5.593519830703736,
|
|
"epoch": 0.967905076833301,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004911244425435212,
|
|
"loss": 5.2029,
|
|
"mean_token_accuracy": 0.18343724608421325,
|
|
"num_tokens": 21586233.0,
|
|
"step": 12440
|
|
},
|
|
{
|
|
"entropy": 5.572824001312256,
|
|
"epoch": 0.9682941062050184,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004911167332899176,
|
|
"loss": 5.2521,
|
|
"mean_token_accuracy": 0.18704710602760316,
|
|
"num_tokens": 21595330.0,
|
|
"step": 12445
|
|
},
|
|
{
|
|
"entropy": 5.528388977050781,
|
|
"epoch": 0.968683135576736,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004911090207570867,
|
|
"loss": 5.1758,
|
|
"mean_token_accuracy": 0.19266084283590318,
|
|
"num_tokens": 21604522.0,
|
|
"step": 12450
|
|
},
|
|
{
|
|
"entropy": 5.607219982147217,
|
|
"epoch": 0.9690721649484536,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004911013049451453,
|
|
"loss": 5.1593,
|
|
"mean_token_accuracy": 0.18465932756662368,
|
|
"num_tokens": 21613599.0,
|
|
"step": 12455
|
|
},
|
|
{
|
|
"entropy": 5.546594190597534,
|
|
"epoch": 0.9694611943201712,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004910935858542106,
|
|
"loss": 5.2375,
|
|
"mean_token_accuracy": 0.17949807196855544,
|
|
"num_tokens": 21622587.0,
|
|
"step": 12460
|
|
},
|
|
{
|
|
"entropy": 5.554617023468017,
|
|
"epoch": 0.9698502236918888,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004910858634843997,
|
|
"loss": 5.2538,
|
|
"mean_token_accuracy": 0.17767165154218673,
|
|
"num_tokens": 21630782.0,
|
|
"step": 12465
|
|
},
|
|
{
|
|
"entropy": 5.584745407104492,
|
|
"epoch": 0.9702392530636063,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004910781378358297,
|
|
"loss": 5.1233,
|
|
"mean_token_accuracy": 0.191708105802536,
|
|
"num_tokens": 21639354.0,
|
|
"step": 12470
|
|
},
|
|
{
|
|
"entropy": 5.5527793884277346,
|
|
"epoch": 0.9706282824353238,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004910704089086178,
|
|
"loss": 5.2856,
|
|
"mean_token_accuracy": 0.18243273645639418,
|
|
"num_tokens": 21648292.0,
|
|
"step": 12475
|
|
},
|
|
{
|
|
"entropy": 5.603460311889648,
|
|
"epoch": 0.9710173118070414,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004910626767028815,
|
|
"loss": 5.2205,
|
|
"mean_token_accuracy": 0.19073559641838073,
|
|
"num_tokens": 21657382.0,
|
|
"step": 12480
|
|
},
|
|
{
|
|
"entropy": 5.598748397827149,
|
|
"epoch": 0.971406341178759,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004910549412187379,
|
|
"loss": 5.2136,
|
|
"mean_token_accuracy": 0.17809648513793946,
|
|
"num_tokens": 21666327.0,
|
|
"step": 12485
|
|
},
|
|
{
|
|
"entropy": 5.567792081832886,
|
|
"epoch": 0.9717953705504766,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004910472024563045,
|
|
"loss": 5.2357,
|
|
"mean_token_accuracy": 0.18883391767740249,
|
|
"num_tokens": 21674882.0,
|
|
"step": 12490
|
|
},
|
|
{
|
|
"entropy": 5.679027414321899,
|
|
"epoch": 0.9721843999221941,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004910394604156987,
|
|
"loss": 5.3274,
|
|
"mean_token_accuracy": 0.1758040115237236,
|
|
"num_tokens": 21683255.0,
|
|
"step": 12495
|
|
},
|
|
{
|
|
"entropy": 5.648699760437012,
|
|
"epoch": 0.9725734292939117,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004910317150970379,
|
|
"loss": 5.1908,
|
|
"mean_token_accuracy": 0.1852326661348343,
|
|
"num_tokens": 21692274.0,
|
|
"step": 12500
|
|
},
|
|
{
|
|
"entropy": 5.4729467868804935,
|
|
"epoch": 0.9729624586656292,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004910239665004397,
|
|
"loss": 5.1105,
|
|
"mean_token_accuracy": 0.19836493879556655,
|
|
"num_tokens": 21700767.0,
|
|
"step": 12505
|
|
},
|
|
{
|
|
"entropy": 5.53968825340271,
|
|
"epoch": 0.9733514880373468,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004910162146260216,
|
|
"loss": 5.2643,
|
|
"mean_token_accuracy": 0.18542049676179886,
|
|
"num_tokens": 21709430.0,
|
|
"step": 12510
|
|
},
|
|
{
|
|
"entropy": 5.546899795532227,
|
|
"epoch": 0.9737405174090644,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004910084594739013,
|
|
"loss": 5.1657,
|
|
"mean_token_accuracy": 0.1877752274274826,
|
|
"num_tokens": 21717978.0,
|
|
"step": 12515
|
|
},
|
|
{
|
|
"entropy": 5.43008942604065,
|
|
"epoch": 0.9741295467807819,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004910007010441964,
|
|
"loss": 5.0367,
|
|
"mean_token_accuracy": 0.19908907860517502,
|
|
"num_tokens": 21726608.0,
|
|
"step": 12520
|
|
},
|
|
{
|
|
"entropy": 5.491342258453369,
|
|
"epoch": 0.9745185761524995,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004909929393370248,
|
|
"loss": 5.1987,
|
|
"mean_token_accuracy": 0.18284936547279357,
|
|
"num_tokens": 21735402.0,
|
|
"step": 12525
|
|
},
|
|
{
|
|
"entropy": 5.523431444168091,
|
|
"epoch": 0.9749076055242171,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004909851743525041,
|
|
"loss": 5.1633,
|
|
"mean_token_accuracy": 0.18822280317544937,
|
|
"num_tokens": 21744620.0,
|
|
"step": 12530
|
|
},
|
|
{
|
|
"entropy": 5.5951985836029055,
|
|
"epoch": 0.9752966348959347,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000490977406090752,
|
|
"loss": 5.2426,
|
|
"mean_token_accuracy": 0.1834847956895828,
|
|
"num_tokens": 21753270.0,
|
|
"step": 12535
|
|
},
|
|
{
|
|
"entropy": 5.623544311523437,
|
|
"epoch": 0.9756856642676522,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004909696345518867,
|
|
"loss": 5.2587,
|
|
"mean_token_accuracy": 0.1800254002213478,
|
|
"num_tokens": 21761477.0,
|
|
"step": 12540
|
|
},
|
|
{
|
|
"entropy": 5.48270354270935,
|
|
"epoch": 0.9760746936393697,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004909618597360258,
|
|
"loss": 5.1723,
|
|
"mean_token_accuracy": 0.1867610439658165,
|
|
"num_tokens": 21769925.0,
|
|
"step": 12545
|
|
},
|
|
{
|
|
"entropy": 5.573631429672242,
|
|
"epoch": 0.9764637230110873,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004909540816432876,
|
|
"loss": 5.2373,
|
|
"mean_token_accuracy": 0.1894602969288826,
|
|
"num_tokens": 21778850.0,
|
|
"step": 12550
|
|
},
|
|
{
|
|
"entropy": 5.593955755233765,
|
|
"epoch": 0.9768527523828049,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004909463002737897,
|
|
"loss": 5.2941,
|
|
"mean_token_accuracy": 0.17965374290943145,
|
|
"num_tokens": 21787408.0,
|
|
"step": 12555
|
|
},
|
|
{
|
|
"entropy": 5.635477209091187,
|
|
"epoch": 0.9772417817545225,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004909385156276506,
|
|
"loss": 5.2508,
|
|
"mean_token_accuracy": 0.1876464918255806,
|
|
"num_tokens": 21795967.0,
|
|
"step": 12560
|
|
},
|
|
{
|
|
"entropy": 5.592546081542968,
|
|
"epoch": 0.9776308111262401,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004909307277049881,
|
|
"loss": 5.2039,
|
|
"mean_token_accuracy": 0.1853122130036354,
|
|
"num_tokens": 21804472.0,
|
|
"step": 12565
|
|
},
|
|
{
|
|
"entropy": 5.489376401901245,
|
|
"epoch": 0.9780198404979576,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004909229365059205,
|
|
"loss": 5.2057,
|
|
"mean_token_accuracy": 0.18564027696847915,
|
|
"num_tokens": 21813233.0,
|
|
"step": 12570
|
|
},
|
|
{
|
|
"entropy": 5.490174007415772,
|
|
"epoch": 0.9784088698696751,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004909151420305661,
|
|
"loss": 5.0931,
|
|
"mean_token_accuracy": 0.19649251252412797,
|
|
"num_tokens": 21821413.0,
|
|
"step": 12575
|
|
},
|
|
{
|
|
"entropy": 5.563841390609741,
|
|
"epoch": 0.9787978992413927,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000490907344279043,
|
|
"loss": 5.1751,
|
|
"mean_token_accuracy": 0.1877642899751663,
|
|
"num_tokens": 21829222.0,
|
|
"step": 12580
|
|
},
|
|
{
|
|
"entropy": 5.5319915294647215,
|
|
"epoch": 0.9791869286131103,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004908995432514698,
|
|
"loss": 5.194,
|
|
"mean_token_accuracy": 0.1828892335295677,
|
|
"num_tokens": 21837033.0,
|
|
"step": 12585
|
|
},
|
|
{
|
|
"entropy": 5.637091732025146,
|
|
"epoch": 0.9795759579848279,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004908917389479645,
|
|
"loss": 5.2439,
|
|
"mean_token_accuracy": 0.18043948113918304,
|
|
"num_tokens": 21845464.0,
|
|
"step": 12590
|
|
},
|
|
{
|
|
"entropy": 5.51136360168457,
|
|
"epoch": 0.9799649873565455,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004908839313686456,
|
|
"loss": 5.1854,
|
|
"mean_token_accuracy": 0.18375110179185866,
|
|
"num_tokens": 21853497.0,
|
|
"step": 12595
|
|
},
|
|
{
|
|
"entropy": 5.593607711791992,
|
|
"epoch": 0.980354016728263,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004908761205136319,
|
|
"loss": 5.2689,
|
|
"mean_token_accuracy": 0.18147289454936982,
|
|
"num_tokens": 21861710.0,
|
|
"step": 12600
|
|
},
|
|
{
|
|
"entropy": 5.645310544967652,
|
|
"epoch": 0.9807430460999805,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004908683063830414,
|
|
"loss": 5.1995,
|
|
"mean_token_accuracy": 0.17797971218824388,
|
|
"num_tokens": 21870472.0,
|
|
"step": 12605
|
|
},
|
|
{
|
|
"entropy": 5.6198813915252686,
|
|
"epoch": 0.9811320754716981,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004908604889769932,
|
|
"loss": 5.2964,
|
|
"mean_token_accuracy": 0.17758426517248155,
|
|
"num_tokens": 21878287.0,
|
|
"step": 12610
|
|
},
|
|
{
|
|
"entropy": 5.634679317474365,
|
|
"epoch": 0.9815211048434157,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004908526682956054,
|
|
"loss": 5.3133,
|
|
"mean_token_accuracy": 0.17233989685773848,
|
|
"num_tokens": 21887587.0,
|
|
"step": 12615
|
|
},
|
|
{
|
|
"entropy": 5.562415647506714,
|
|
"epoch": 0.9819101342151333,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004908448443389972,
|
|
"loss": 5.1428,
|
|
"mean_token_accuracy": 0.19184593260288238,
|
|
"num_tokens": 21895923.0,
|
|
"step": 12620
|
|
},
|
|
{
|
|
"entropy": 5.562763929367065,
|
|
"epoch": 0.9822991635868508,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004908370171072869,
|
|
"loss": 5.18,
|
|
"mean_token_accuracy": 0.19212259501218795,
|
|
"num_tokens": 21904439.0,
|
|
"step": 12625
|
|
},
|
|
{
|
|
"entropy": 5.540858364105224,
|
|
"epoch": 0.9826881929585684,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004908291866005933,
|
|
"loss": 5.1488,
|
|
"mean_token_accuracy": 0.18386462330818176,
|
|
"num_tokens": 21912473.0,
|
|
"step": 12630
|
|
},
|
|
{
|
|
"entropy": 5.486727380752564,
|
|
"epoch": 0.9830772223302859,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004908213528190355,
|
|
"loss": 5.2317,
|
|
"mean_token_accuracy": 0.17889027893543244,
|
|
"num_tokens": 21921631.0,
|
|
"step": 12635
|
|
},
|
|
{
|
|
"entropy": 5.492412996292114,
|
|
"epoch": 0.9834662517020035,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004908135157627321,
|
|
"loss": 5.1311,
|
|
"mean_token_accuracy": 0.19090985506772995,
|
|
"num_tokens": 21929984.0,
|
|
"step": 12640
|
|
},
|
|
{
|
|
"entropy": 5.536947298049927,
|
|
"epoch": 0.9838552810737211,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004908056754318022,
|
|
"loss": 5.0891,
|
|
"mean_token_accuracy": 0.19027605503797532,
|
|
"num_tokens": 21937349.0,
|
|
"step": 12645
|
|
},
|
|
{
|
|
"entropy": 5.503980445861816,
|
|
"epoch": 0.9842443104454386,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004907978318263646,
|
|
"loss": 5.2024,
|
|
"mean_token_accuracy": 0.1863625630736351,
|
|
"num_tokens": 21946176.0,
|
|
"step": 12650
|
|
},
|
|
{
|
|
"entropy": 5.584465789794922,
|
|
"epoch": 0.9846333398171562,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004907899849465383,
|
|
"loss": 5.1879,
|
|
"mean_token_accuracy": 0.18762608766555786,
|
|
"num_tokens": 21954645.0,
|
|
"step": 12655
|
|
},
|
|
{
|
|
"entropy": 5.578148937225341,
|
|
"epoch": 0.9850223691888738,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004907821347924424,
|
|
"loss": 5.2262,
|
|
"mean_token_accuracy": 0.17646457105875016,
|
|
"num_tokens": 21963290.0,
|
|
"step": 12660
|
|
},
|
|
{
|
|
"entropy": 5.574510526657105,
|
|
"epoch": 0.9854113985605913,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004907742813641963,
|
|
"loss": 5.242,
|
|
"mean_token_accuracy": 0.18453686386346818,
|
|
"num_tokens": 21971005.0,
|
|
"step": 12665
|
|
},
|
|
{
|
|
"entropy": 5.538446092605591,
|
|
"epoch": 0.9858004279323089,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004907664246619187,
|
|
"loss": 5.1549,
|
|
"mean_token_accuracy": 0.1910643011331558,
|
|
"num_tokens": 21980067.0,
|
|
"step": 12670
|
|
},
|
|
{
|
|
"entropy": 5.566548156738281,
|
|
"epoch": 0.9861894573040264,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004907585646857293,
|
|
"loss": 5.1899,
|
|
"mean_token_accuracy": 0.18357451856136323,
|
|
"num_tokens": 21988511.0,
|
|
"step": 12675
|
|
},
|
|
{
|
|
"entropy": 5.535651922225952,
|
|
"epoch": 0.986578486675744,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004907507014357467,
|
|
"loss": 5.1687,
|
|
"mean_token_accuracy": 0.18767756074666977,
|
|
"num_tokens": 21997074.0,
|
|
"step": 12680
|
|
},
|
|
{
|
|
"entropy": 5.59835262298584,
|
|
"epoch": 0.9869675160474616,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004907428349120909,
|
|
"loss": 5.2995,
|
|
"mean_token_accuracy": 0.1809012398123741,
|
|
"num_tokens": 22005412.0,
|
|
"step": 12685
|
|
},
|
|
{
|
|
"entropy": 5.521641683578491,
|
|
"epoch": 0.9873565454191792,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004907349651148809,
|
|
"loss": 5.1009,
|
|
"mean_token_accuracy": 0.19311340302228927,
|
|
"num_tokens": 22013588.0,
|
|
"step": 12690
|
|
},
|
|
{
|
|
"entropy": 5.560098314285279,
|
|
"epoch": 0.9877455747908968,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004907270920442361,
|
|
"loss": 5.2467,
|
|
"mean_token_accuracy": 0.18230018764734268,
|
|
"num_tokens": 22021669.0,
|
|
"step": 12695
|
|
},
|
|
{
|
|
"entropy": 5.50910496711731,
|
|
"epoch": 0.9881346041626142,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004907192157002762,
|
|
"loss": 5.1106,
|
|
"mean_token_accuracy": 0.19061779975891113,
|
|
"num_tokens": 22030295.0,
|
|
"step": 12700
|
|
},
|
|
{
|
|
"entropy": 5.589793014526367,
|
|
"epoch": 0.9885236335343318,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004907113360831204,
|
|
"loss": 5.2625,
|
|
"mean_token_accuracy": 0.18287634551525117,
|
|
"num_tokens": 22038924.0,
|
|
"step": 12705
|
|
},
|
|
{
|
|
"entropy": 5.5686742782592775,
|
|
"epoch": 0.9889126629060494,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004907034531928886,
|
|
"loss": 5.1742,
|
|
"mean_token_accuracy": 0.19149626344442366,
|
|
"num_tokens": 22047586.0,
|
|
"step": 12710
|
|
},
|
|
{
|
|
"entropy": 5.523001956939697,
|
|
"epoch": 0.989301692277767,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004906955670297001,
|
|
"loss": 5.1547,
|
|
"mean_token_accuracy": 0.1865146890282631,
|
|
"num_tokens": 22055695.0,
|
|
"step": 12715
|
|
},
|
|
{
|
|
"entropy": 5.614638900756836,
|
|
"epoch": 0.9896907216494846,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004906876775936746,
|
|
"loss": 5.3082,
|
|
"mean_token_accuracy": 0.17966843992471696,
|
|
"num_tokens": 22064472.0,
|
|
"step": 12720
|
|
},
|
|
{
|
|
"entropy": 5.631753921508789,
|
|
"epoch": 0.990079751021202,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004906797848849321,
|
|
"loss": 5.2373,
|
|
"mean_token_accuracy": 0.1752263605594635,
|
|
"num_tokens": 22072726.0,
|
|
"step": 12725
|
|
},
|
|
{
|
|
"entropy": 5.581534147262573,
|
|
"epoch": 0.9904687803929196,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000490671888903592,
|
|
"loss": 5.1329,
|
|
"mean_token_accuracy": 0.18759203255176543,
|
|
"num_tokens": 22081074.0,
|
|
"step": 12730
|
|
},
|
|
{
|
|
"entropy": 5.500444126129151,
|
|
"epoch": 0.9908578097646372,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004906639896497744,
|
|
"loss": 5.1214,
|
|
"mean_token_accuracy": 0.19771044552326203,
|
|
"num_tokens": 22089924.0,
|
|
"step": 12735
|
|
},
|
|
{
|
|
"entropy": 5.588295030593872,
|
|
"epoch": 0.9912468391363548,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004906560871235988,
|
|
"loss": 5.1378,
|
|
"mean_token_accuracy": 0.18912340700626373,
|
|
"num_tokens": 22099088.0,
|
|
"step": 12740
|
|
},
|
|
{
|
|
"entropy": 5.651731348037719,
|
|
"epoch": 0.9916358685080724,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004906481813251854,
|
|
"loss": 5.2843,
|
|
"mean_token_accuracy": 0.1810019001364708,
|
|
"num_tokens": 22108344.0,
|
|
"step": 12745
|
|
},
|
|
{
|
|
"entropy": 5.563349723815918,
|
|
"epoch": 0.9920248978797899,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004906402722546542,
|
|
"loss": 5.197,
|
|
"mean_token_accuracy": 0.18123072236776352,
|
|
"num_tokens": 22116476.0,
|
|
"step": 12750
|
|
},
|
|
{
|
|
"entropy": 5.621095132827759,
|
|
"epoch": 0.9924139272515075,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000490632359912125,
|
|
"loss": 5.2968,
|
|
"mean_token_accuracy": 0.1742379203438759,
|
|
"num_tokens": 22125445.0,
|
|
"step": 12755
|
|
},
|
|
{
|
|
"entropy": 5.602992916107178,
|
|
"epoch": 0.992802956623225,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000490624444297718,
|
|
"loss": 5.3181,
|
|
"mean_token_accuracy": 0.18033766895532607,
|
|
"num_tokens": 22134886.0,
|
|
"step": 12760
|
|
},
|
|
{
|
|
"entropy": 5.525603151321411,
|
|
"epoch": 0.9931919859949426,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004906165254115533,
|
|
"loss": 5.1782,
|
|
"mean_token_accuracy": 0.18814245462417603,
|
|
"num_tokens": 22144521.0,
|
|
"step": 12765
|
|
},
|
|
{
|
|
"entropy": 5.496958541870117,
|
|
"epoch": 0.9935810153666602,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000490608603253751,
|
|
"loss": 5.1939,
|
|
"mean_token_accuracy": 0.1895970657467842,
|
|
"num_tokens": 22152754.0,
|
|
"step": 12770
|
|
},
|
|
{
|
|
"entropy": 5.548004865646362,
|
|
"epoch": 0.9939700447383778,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004906006778244312,
|
|
"loss": 5.1773,
|
|
"mean_token_accuracy": 0.1882224589586258,
|
|
"num_tokens": 22161711.0,
|
|
"step": 12775
|
|
},
|
|
{
|
|
"entropy": 5.605820941925049,
|
|
"epoch": 0.9943590741100953,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004905927491237145,
|
|
"loss": 5.3014,
|
|
"mean_token_accuracy": 0.18251292556524276,
|
|
"num_tokens": 22169762.0,
|
|
"step": 12780
|
|
},
|
|
{
|
|
"entropy": 5.568092966079712,
|
|
"epoch": 0.9947481034818129,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004905848171517208,
|
|
"loss": 5.1474,
|
|
"mean_token_accuracy": 0.18988931626081468,
|
|
"num_tokens": 22178415.0,
|
|
"step": 12785
|
|
},
|
|
{
|
|
"entropy": 5.499771595001221,
|
|
"epoch": 0.9951371328535304,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004905768819085706,
|
|
"loss": 5.0934,
|
|
"mean_token_accuracy": 0.19471519887447358,
|
|
"num_tokens": 22187643.0,
|
|
"step": 12790
|
|
},
|
|
{
|
|
"entropy": 5.4495015144348145,
|
|
"epoch": 0.995526162225248,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004905689433943846,
|
|
"loss": 5.1344,
|
|
"mean_token_accuracy": 0.189376999437809,
|
|
"num_tokens": 22196355.0,
|
|
"step": 12795
|
|
},
|
|
{
|
|
"entropy": 5.576473808288574,
|
|
"epoch": 0.9959151915969656,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004905610016092828,
|
|
"loss": 5.2524,
|
|
"mean_token_accuracy": 0.18064917623996735,
|
|
"num_tokens": 22204648.0,
|
|
"step": 12800
|
|
},
|
|
{
|
|
"entropy": 5.555432415008545,
|
|
"epoch": 0.9963042209686831,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004905530565533859,
|
|
"loss": 5.2268,
|
|
"mean_token_accuracy": 0.18231253921985627,
|
|
"num_tokens": 22212811.0,
|
|
"step": 12805
|
|
},
|
|
{
|
|
"entropy": 5.482769107818603,
|
|
"epoch": 0.9966932503404007,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004905451082268146,
|
|
"loss": 5.1944,
|
|
"mean_token_accuracy": 0.18336111754179002,
|
|
"num_tokens": 22220611.0,
|
|
"step": 12810
|
|
},
|
|
{
|
|
"entropy": 5.578828048706055,
|
|
"epoch": 0.9970822797121183,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004905371566296891,
|
|
"loss": 5.2084,
|
|
"mean_token_accuracy": 0.18011167496442795,
|
|
"num_tokens": 22229606.0,
|
|
"step": 12815
|
|
},
|
|
{
|
|
"entropy": 5.642096424102784,
|
|
"epoch": 0.9974713090838359,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004905292017621305,
|
|
"loss": 5.1853,
|
|
"mean_token_accuracy": 0.18634316176176072,
|
|
"num_tokens": 22238157.0,
|
|
"step": 12820
|
|
},
|
|
{
|
|
"entropy": 5.547455549240112,
|
|
"epoch": 0.9978603384555534,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004905212436242593,
|
|
"loss": 5.2221,
|
|
"mean_token_accuracy": 0.18357642143964767,
|
|
"num_tokens": 22246696.0,
|
|
"step": 12825
|
|
},
|
|
{
|
|
"entropy": 5.544768905639648,
|
|
"epoch": 0.9982493678272709,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004905132822161962,
|
|
"loss": 5.2526,
|
|
"mean_token_accuracy": 0.18186190873384475,
|
|
"num_tokens": 22255028.0,
|
|
"step": 12830
|
|
},
|
|
{
|
|
"entropy": 5.6687843799591064,
|
|
"epoch": 0.9986383971989885,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004905053175380621,
|
|
"loss": 5.3011,
|
|
"mean_token_accuracy": 0.18592547625303268,
|
|
"num_tokens": 22263198.0,
|
|
"step": 12835
|
|
},
|
|
{
|
|
"entropy": 5.623014688491821,
|
|
"epoch": 0.9990274265707061,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004904973495899778,
|
|
"loss": 5.2992,
|
|
"mean_token_accuracy": 0.18507118821144103,
|
|
"num_tokens": 22273780.0,
|
|
"step": 12840
|
|
},
|
|
{
|
|
"entropy": 5.659826850891113,
|
|
"epoch": 0.9994164559424237,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004904893783720642,
|
|
"loss": 5.3248,
|
|
"mean_token_accuracy": 0.17507429122924806,
|
|
"num_tokens": 22281545.0,
|
|
"step": 12845
|
|
},
|
|
{
|
|
"entropy": 5.550436544418335,
|
|
"epoch": 0.9998054853141413,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004904814038844424,
|
|
"loss": 5.2104,
|
|
"mean_token_accuracy": 0.17978432923555374,
|
|
"num_tokens": 22290426.0,
|
|
"step": 12850
|
|
},
|
|
{
|
|
"entropy": 5.602494610680474,
|
|
"epoch": 1.000155611748687,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004904734261272332,
|
|
"loss": 5.2511,
|
|
"mean_token_accuracy": 0.1884353756904602,
|
|
"num_tokens": 22297475.0,
|
|
"step": 12855
|
|
},
|
|
{
|
|
"entropy": 5.497782230377197,
|
|
"epoch": 1.0005446411204046,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004904654451005576,
|
|
"loss": 4.9866,
|
|
"mean_token_accuracy": 0.1947847932577133,
|
|
"num_tokens": 22305784.0,
|
|
"step": 12860
|
|
},
|
|
{
|
|
"entropy": 5.526057243347168,
|
|
"epoch": 1.0009336704921221,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004904574608045369,
|
|
"loss": 5.0917,
|
|
"mean_token_accuracy": 0.18853476494550706,
|
|
"num_tokens": 22313951.0,
|
|
"step": 12865
|
|
},
|
|
{
|
|
"entropy": 5.63850769996643,
|
|
"epoch": 1.0013226998638398,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004904494732392923,
|
|
"loss": 5.1972,
|
|
"mean_token_accuracy": 0.18424230217933654,
|
|
"num_tokens": 22322509.0,
|
|
"step": 12870
|
|
},
|
|
{
|
|
"entropy": 5.545155191421509,
|
|
"epoch": 1.0017117292355573,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004904414824049448,
|
|
"loss": 5.1513,
|
|
"mean_token_accuracy": 0.18539026528596877,
|
|
"num_tokens": 22331475.0,
|
|
"step": 12875
|
|
},
|
|
{
|
|
"entropy": 5.533708000183106,
|
|
"epoch": 1.0021007586072748,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004904334883016156,
|
|
"loss": 5.0775,
|
|
"mean_token_accuracy": 0.19584077447652817,
|
|
"num_tokens": 22341114.0,
|
|
"step": 12880
|
|
},
|
|
{
|
|
"entropy": 5.581373596191407,
|
|
"epoch": 1.0024897879789925,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004904254909294261,
|
|
"loss": 5.1495,
|
|
"mean_token_accuracy": 0.190461228787899,
|
|
"num_tokens": 22349199.0,
|
|
"step": 12885
|
|
},
|
|
{
|
|
"entropy": 5.566561937332153,
|
|
"epoch": 1.00287881735071,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004904174902884978,
|
|
"loss": 5.121,
|
|
"mean_token_accuracy": 0.18924966603517532,
|
|
"num_tokens": 22358485.0,
|
|
"step": 12890
|
|
},
|
|
{
|
|
"entropy": 5.634268808364868,
|
|
"epoch": 1.0032678467224276,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004904094863789519,
|
|
"loss": 5.1754,
|
|
"mean_token_accuracy": 0.1821126490831375,
|
|
"num_tokens": 22366936.0,
|
|
"step": 12895
|
|
},
|
|
{
|
|
"entropy": 5.652461814880371,
|
|
"epoch": 1.0036568760941451,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00049040147920091,
|
|
"loss": 5.1534,
|
|
"mean_token_accuracy": 0.18067814260721207,
|
|
"num_tokens": 22376007.0,
|
|
"step": 12900
|
|
},
|
|
{
|
|
"entropy": 5.512387371063232,
|
|
"epoch": 1.0040459054658626,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004903934687544933,
|
|
"loss": 5.0686,
|
|
"mean_token_accuracy": 0.2005569815635681,
|
|
"num_tokens": 22384747.0,
|
|
"step": 12905
|
|
},
|
|
{
|
|
"entropy": 5.56094217300415,
|
|
"epoch": 1.0044349348375803,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004903854550398237,
|
|
"loss": 5.0965,
|
|
"mean_token_accuracy": 0.19653735160827637,
|
|
"num_tokens": 22393730.0,
|
|
"step": 12910
|
|
},
|
|
{
|
|
"entropy": 5.604393053054809,
|
|
"epoch": 1.0048239642092978,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004903774380570226,
|
|
"loss": 5.1229,
|
|
"mean_token_accuracy": 0.18444818258285522,
|
|
"num_tokens": 22402121.0,
|
|
"step": 12915
|
|
},
|
|
{
|
|
"entropy": 5.559228849411011,
|
|
"epoch": 1.0052129935810155,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004903694178062117,
|
|
"loss": 5.1351,
|
|
"mean_token_accuracy": 0.18738230615854262,
|
|
"num_tokens": 22410943.0,
|
|
"step": 12920
|
|
},
|
|
{
|
|
"entropy": 5.606460475921631,
|
|
"epoch": 1.005602022952733,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004903613942875126,
|
|
"loss": 5.2004,
|
|
"mean_token_accuracy": 0.18455881029367446,
|
|
"num_tokens": 22420137.0,
|
|
"step": 12925
|
|
},
|
|
{
|
|
"entropy": 5.575601530075073,
|
|
"epoch": 1.0059910523244504,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004903533675010472,
|
|
"loss": 5.1336,
|
|
"mean_token_accuracy": 0.18333719819784164,
|
|
"num_tokens": 22429031.0,
|
|
"step": 12930
|
|
},
|
|
{
|
|
"entropy": 5.526545190811158,
|
|
"epoch": 1.006380081696168,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004903453374469373,
|
|
"loss": 5.1805,
|
|
"mean_token_accuracy": 0.18613078743219375,
|
|
"num_tokens": 22438735.0,
|
|
"step": 12935
|
|
},
|
|
{
|
|
"entropy": 5.603658199310303,
|
|
"epoch": 1.0067691110678856,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004903373041253045,
|
|
"loss": 5.172,
|
|
"mean_token_accuracy": 0.18485343158245088,
|
|
"num_tokens": 22447374.0,
|
|
"step": 12940
|
|
},
|
|
{
|
|
"entropy": 5.6252185821533205,
|
|
"epoch": 1.0071581404396033,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004903292675362709,
|
|
"loss": 5.108,
|
|
"mean_token_accuracy": 0.18936037570238112,
|
|
"num_tokens": 22455542.0,
|
|
"step": 12945
|
|
},
|
|
{
|
|
"entropy": 5.505251741409301,
|
|
"epoch": 1.0075471698113208,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004903212276799584,
|
|
"loss": 5.1622,
|
|
"mean_token_accuracy": 0.18490004986524583,
|
|
"num_tokens": 22464591.0,
|
|
"step": 12950
|
|
},
|
|
{
|
|
"entropy": 5.559835195541382,
|
|
"epoch": 1.0079361991830382,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004903131845564889,
|
|
"loss": 5.0936,
|
|
"mean_token_accuracy": 0.19423397928476333,
|
|
"num_tokens": 22472315.0,
|
|
"step": 12955
|
|
},
|
|
{
|
|
"entropy": 5.580622291564941,
|
|
"epoch": 1.008325228554756,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004903051381659847,
|
|
"loss": 5.2402,
|
|
"mean_token_accuracy": 0.17842978835105897,
|
|
"num_tokens": 22480662.0,
|
|
"step": 12960
|
|
},
|
|
{
|
|
"entropy": 5.4951142311096195,
|
|
"epoch": 1.0087142579264734,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004902970885085677,
|
|
"loss": 5.1334,
|
|
"mean_token_accuracy": 0.18665957897901536,
|
|
"num_tokens": 22489600.0,
|
|
"step": 12965
|
|
},
|
|
{
|
|
"entropy": 5.615678405761718,
|
|
"epoch": 1.009103287298191,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00049028903558436,
|
|
"loss": 5.1742,
|
|
"mean_token_accuracy": 0.1867367744445801,
|
|
"num_tokens": 22498114.0,
|
|
"step": 12970
|
|
},
|
|
{
|
|
"entropy": 5.534137105941772,
|
|
"epoch": 1.0094923166699086,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004902809793934838,
|
|
"loss": 5.009,
|
|
"mean_token_accuracy": 0.20099946856498718,
|
|
"num_tokens": 22506349.0,
|
|
"step": 12975
|
|
},
|
|
{
|
|
"entropy": 5.538618516921997,
|
|
"epoch": 1.009881346041626,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004902729199360615,
|
|
"loss": 5.0936,
|
|
"mean_token_accuracy": 0.1934603363275528,
|
|
"num_tokens": 22514878.0,
|
|
"step": 12980
|
|
},
|
|
{
|
|
"entropy": 5.550827550888061,
|
|
"epoch": 1.0102703754133437,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004902648572122153,
|
|
"loss": 5.1364,
|
|
"mean_token_accuracy": 0.17829016596078873,
|
|
"num_tokens": 22522992.0,
|
|
"step": 12985
|
|
},
|
|
{
|
|
"entropy": 5.64747986793518,
|
|
"epoch": 1.0106594047850612,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004902567912220674,
|
|
"loss": 5.1871,
|
|
"mean_token_accuracy": 0.18084194958209993,
|
|
"num_tokens": 22531407.0,
|
|
"step": 12990
|
|
},
|
|
{
|
|
"entropy": 5.508750486373901,
|
|
"epoch": 1.011048434156779,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004902487219657404,
|
|
"loss": 5.0794,
|
|
"mean_token_accuracy": 0.18966627568006517,
|
|
"num_tokens": 22540255.0,
|
|
"step": 12995
|
|
},
|
|
{
|
|
"entropy": 5.533417701721191,
|
|
"epoch": 1.0114374635284964,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004902406494433566,
|
|
"loss": 5.1183,
|
|
"mean_token_accuracy": 0.18966990560293198,
|
|
"num_tokens": 22549139.0,
|
|
"step": 13000
|
|
},
|
|
{
|
|
"entropy": 5.5960956573486325,
|
|
"epoch": 1.0118264929002139,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004902325736550386,
|
|
"loss": 5.1184,
|
|
"mean_token_accuracy": 0.1921576127409935,
|
|
"num_tokens": 22557746.0,
|
|
"step": 13005
|
|
},
|
|
{
|
|
"entropy": 5.578761196136474,
|
|
"epoch": 1.0122155222719316,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004902244946009088,
|
|
"loss": 5.1094,
|
|
"mean_token_accuracy": 0.18693674057722093,
|
|
"num_tokens": 22566695.0,
|
|
"step": 13010
|
|
},
|
|
{
|
|
"entropy": 5.564864826202393,
|
|
"epoch": 1.012604551643649,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004902164122810899,
|
|
"loss": 5.1119,
|
|
"mean_token_accuracy": 0.1888263612985611,
|
|
"num_tokens": 22575196.0,
|
|
"step": 13015
|
|
},
|
|
{
|
|
"entropy": 5.566193246841431,
|
|
"epoch": 1.0129935810153667,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004902083266957045,
|
|
"loss": 5.1133,
|
|
"mean_token_accuracy": 0.1898096725344658,
|
|
"num_tokens": 22583520.0,
|
|
"step": 13020
|
|
},
|
|
{
|
|
"entropy": 5.558519744873047,
|
|
"epoch": 1.0133826103870842,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004902002378448753,
|
|
"loss": 5.1734,
|
|
"mean_token_accuracy": 0.18409187942743302,
|
|
"num_tokens": 22591896.0,
|
|
"step": 13025
|
|
},
|
|
{
|
|
"entropy": 5.55157585144043,
|
|
"epoch": 1.0137716397588017,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000490192145728725,
|
|
"loss": 5.0948,
|
|
"mean_token_accuracy": 0.19964988231658937,
|
|
"num_tokens": 22600097.0,
|
|
"step": 13030
|
|
},
|
|
{
|
|
"entropy": 5.540172433853149,
|
|
"epoch": 1.0141606691305194,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004901840503473764,
|
|
"loss": 5.0375,
|
|
"mean_token_accuracy": 0.18559068590402603,
|
|
"num_tokens": 22607956.0,
|
|
"step": 13035
|
|
},
|
|
{
|
|
"entropy": 5.540137910842896,
|
|
"epoch": 1.0145496985022369,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004901759517009522,
|
|
"loss": 5.1338,
|
|
"mean_token_accuracy": 0.17898587733507157,
|
|
"num_tokens": 22616549.0,
|
|
"step": 13040
|
|
},
|
|
{
|
|
"entropy": 5.55298810005188,
|
|
"epoch": 1.0149387278739546,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004901678497895755,
|
|
"loss": 5.0563,
|
|
"mean_token_accuracy": 0.1862951323390007,
|
|
"num_tokens": 22625138.0,
|
|
"step": 13045
|
|
},
|
|
{
|
|
"entropy": 5.566691541671753,
|
|
"epoch": 1.015327757245672,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004901597446133692,
|
|
"loss": 5.1496,
|
|
"mean_token_accuracy": 0.18422176837921142,
|
|
"num_tokens": 22633808.0,
|
|
"step": 13050
|
|
},
|
|
{
|
|
"entropy": 5.528288269042969,
|
|
"epoch": 1.0157167866173895,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004901516361724564,
|
|
"loss": 5.0905,
|
|
"mean_token_accuracy": 0.19693392962217332,
|
|
"num_tokens": 22642517.0,
|
|
"step": 13055
|
|
},
|
|
{
|
|
"entropy": 5.581601953506469,
|
|
"epoch": 1.0161058159891072,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004901435244669597,
|
|
"loss": 5.1511,
|
|
"mean_token_accuracy": 0.1824340358376503,
|
|
"num_tokens": 22651822.0,
|
|
"step": 13060
|
|
},
|
|
{
|
|
"entropy": 5.583770418167115,
|
|
"epoch": 1.0164948453608247,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004901354094970025,
|
|
"loss": 5.1236,
|
|
"mean_token_accuracy": 0.19076863974332808,
|
|
"num_tokens": 22660763.0,
|
|
"step": 13065
|
|
},
|
|
{
|
|
"entropy": 5.521487760543823,
|
|
"epoch": 1.0168838747325424,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004901272912627081,
|
|
"loss": 5.1253,
|
|
"mean_token_accuracy": 0.18654322177171706,
|
|
"num_tokens": 22669449.0,
|
|
"step": 13070
|
|
},
|
|
{
|
|
"entropy": 5.5992106914520265,
|
|
"epoch": 1.0172729041042599,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004901191697641992,
|
|
"loss": 5.1501,
|
|
"mean_token_accuracy": 0.18977264761924745,
|
|
"num_tokens": 22678212.0,
|
|
"step": 13075
|
|
},
|
|
{
|
|
"entropy": 5.553779935836792,
|
|
"epoch": 1.0176619334759773,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004901110450015994,
|
|
"loss": 5.0905,
|
|
"mean_token_accuracy": 0.19180919378995895,
|
|
"num_tokens": 22686509.0,
|
|
"step": 13080
|
|
},
|
|
{
|
|
"entropy": 5.5005475044250485,
|
|
"epoch": 1.018050962847695,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004901029169750319,
|
|
"loss": 5.1146,
|
|
"mean_token_accuracy": 0.18717952966690063,
|
|
"num_tokens": 22695473.0,
|
|
"step": 13085
|
|
},
|
|
{
|
|
"entropy": 5.57834529876709,
|
|
"epoch": 1.0184399922194125,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004900947856846201,
|
|
"loss": 5.1808,
|
|
"mean_token_accuracy": 0.18466604948043824,
|
|
"num_tokens": 22704567.0,
|
|
"step": 13090
|
|
},
|
|
{
|
|
"entropy": 5.540963172912598,
|
|
"epoch": 1.0188290215911302,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000490086651130487,
|
|
"loss": 5.0544,
|
|
"mean_token_accuracy": 0.19342739433050155,
|
|
"num_tokens": 22713981.0,
|
|
"step": 13095
|
|
},
|
|
{
|
|
"entropy": 5.477065086364746,
|
|
"epoch": 1.0192180509628477,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004900785133127566,
|
|
"loss": 4.9968,
|
|
"mean_token_accuracy": 0.20526853054761887,
|
|
"num_tokens": 22722855.0,
|
|
"step": 13100
|
|
},
|
|
{
|
|
"entropy": 5.523031425476074,
|
|
"epoch": 1.0196070803345652,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.000490070372231552,
|
|
"loss": 5.1184,
|
|
"mean_token_accuracy": 0.18693454563617706,
|
|
"num_tokens": 22732454.0,
|
|
"step": 13105
|
|
},
|
|
{
|
|
"entropy": 5.524135732650757,
|
|
"epoch": 1.0199961097062828,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004900622278869968,
|
|
"loss": 4.9761,
|
|
"mean_token_accuracy": 0.20482657998800277,
|
|
"num_tokens": 22741331.0,
|
|
"step": 13110
|
|
},
|
|
{
|
|
"entropy": 5.584689283370972,
|
|
"epoch": 1.0203851390780003,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004900540802792146,
|
|
"loss": 5.1816,
|
|
"mean_token_accuracy": 0.1842080235481262,
|
|
"num_tokens": 22749983.0,
|
|
"step": 13115
|
|
},
|
|
{
|
|
"entropy": 5.501961898803711,
|
|
"epoch": 1.020774168449718,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000490045929408329,
|
|
"loss": 5.1246,
|
|
"mean_token_accuracy": 0.19006228744983672,
|
|
"num_tokens": 22759112.0,
|
|
"step": 13120
|
|
},
|
|
{
|
|
"entropy": 5.560851001739502,
|
|
"epoch": 1.0211631978214355,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004900377752744637,
|
|
"loss": 5.1706,
|
|
"mean_token_accuracy": 0.18927655816078187,
|
|
"num_tokens": 22768456.0,
|
|
"step": 13125
|
|
},
|
|
{
|
|
"entropy": 5.56893401145935,
|
|
"epoch": 1.021552227193153,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004900296178777426,
|
|
"loss": 5.0771,
|
|
"mean_token_accuracy": 0.19508728981018067,
|
|
"num_tokens": 22777450.0,
|
|
"step": 13130
|
|
},
|
|
{
|
|
"entropy": 5.584453201293945,
|
|
"epoch": 1.0219412565648707,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000490021457218289,
|
|
"loss": 5.1347,
|
|
"mean_token_accuracy": 0.19422568678855895,
|
|
"num_tokens": 22785704.0,
|
|
"step": 13135
|
|
},
|
|
{
|
|
"entropy": 5.484196329116822,
|
|
"epoch": 1.0223302859365881,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004900132932962272,
|
|
"loss": 5.1152,
|
|
"mean_token_accuracy": 0.18883706331253053,
|
|
"num_tokens": 22794649.0,
|
|
"step": 13140
|
|
},
|
|
{
|
|
"entropy": 5.600627803802491,
|
|
"epoch": 1.0227193153083058,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000490005126111681,
|
|
"loss": 5.2152,
|
|
"mean_token_accuracy": 0.1855715736746788,
|
|
"num_tokens": 22803501.0,
|
|
"step": 13145
|
|
},
|
|
{
|
|
"entropy": 5.671587705612183,
|
|
"epoch": 1.0231083446800233,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000489996955664774,
|
|
"loss": 5.1421,
|
|
"mean_token_accuracy": 0.18789013475179672,
|
|
"num_tokens": 22811779.0,
|
|
"step": 13150
|
|
},
|
|
{
|
|
"entropy": 5.528184700012207,
|
|
"epoch": 1.023497374051741,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004899887819556306,
|
|
"loss": 5.1439,
|
|
"mean_token_accuracy": 0.18700369745492934,
|
|
"num_tokens": 22821108.0,
|
|
"step": 13155
|
|
},
|
|
{
|
|
"entropy": 5.5858643531799315,
|
|
"epoch": 1.0238864034234585,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004899806049843745,
|
|
"loss": 5.1645,
|
|
"mean_token_accuracy": 0.1873817428946495,
|
|
"num_tokens": 22829369.0,
|
|
"step": 13160
|
|
},
|
|
{
|
|
"entropy": 5.567682218551636,
|
|
"epoch": 1.024275432795176,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004899724247511299,
|
|
"loss": 5.1211,
|
|
"mean_token_accuracy": 0.1896756872534752,
|
|
"num_tokens": 22838441.0,
|
|
"step": 13165
|
|
},
|
|
{
|
|
"entropy": 5.580206680297851,
|
|
"epoch": 1.0246644621668937,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000489964241256021,
|
|
"loss": 5.0986,
|
|
"mean_token_accuracy": 0.18903386741876602,
|
|
"num_tokens": 22847587.0,
|
|
"step": 13170
|
|
},
|
|
{
|
|
"entropy": 5.494615125656128,
|
|
"epoch": 1.0250534915386111,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004899560544991718,
|
|
"loss": 5.0652,
|
|
"mean_token_accuracy": 0.19684161096811295,
|
|
"num_tokens": 22856051.0,
|
|
"step": 13175
|
|
},
|
|
{
|
|
"entropy": 5.556175231933594,
|
|
"epoch": 1.0254425209103288,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004899478644807068,
|
|
"loss": 5.1392,
|
|
"mean_token_accuracy": 0.18752205967903138,
|
|
"num_tokens": 22864822.0,
|
|
"step": 13180
|
|
},
|
|
{
|
|
"entropy": 5.568244171142578,
|
|
"epoch": 1.0258315502820463,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004899396712007498,
|
|
"loss": 5.111,
|
|
"mean_token_accuracy": 0.18785069435834884,
|
|
"num_tokens": 22873199.0,
|
|
"step": 13185
|
|
},
|
|
{
|
|
"entropy": 5.540246438980103,
|
|
"epoch": 1.0262205796537638,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004899314746594256,
|
|
"loss": 5.1798,
|
|
"mean_token_accuracy": 0.18196630626916885,
|
|
"num_tokens": 22881184.0,
|
|
"step": 13190
|
|
},
|
|
{
|
|
"entropy": 5.590057373046875,
|
|
"epoch": 1.0266096090254815,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004899232748568584,
|
|
"loss": 5.0867,
|
|
"mean_token_accuracy": 0.19181957691907883,
|
|
"num_tokens": 22890087.0,
|
|
"step": 13195
|
|
},
|
|
{
|
|
"entropy": 5.570810317993164,
|
|
"epoch": 1.026998638397199,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004899150717931724,
|
|
"loss": 5.1042,
|
|
"mean_token_accuracy": 0.19140806347131728,
|
|
"num_tokens": 22899013.0,
|
|
"step": 13200
|
|
},
|
|
{
|
|
"entropy": 5.522170639038086,
|
|
"epoch": 1.0273876677689167,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004899068654684924,
|
|
"loss": 5.2531,
|
|
"mean_token_accuracy": 0.18083969503641129,
|
|
"num_tokens": 22908740.0,
|
|
"step": 13205
|
|
},
|
|
{
|
|
"entropy": 5.623792028427124,
|
|
"epoch": 1.0277766971406341,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004898986558829428,
|
|
"loss": 5.1725,
|
|
"mean_token_accuracy": 0.18605524599552153,
|
|
"num_tokens": 22917502.0,
|
|
"step": 13210
|
|
},
|
|
{
|
|
"entropy": 5.571014165878296,
|
|
"epoch": 1.0281657265123516,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004898904430366479,
|
|
"loss": 5.0847,
|
|
"mean_token_accuracy": 0.18972016572952272,
|
|
"num_tokens": 22927076.0,
|
|
"step": 13215
|
|
},
|
|
{
|
|
"entropy": 5.582257509231567,
|
|
"epoch": 1.0285547558840693,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004898822269297328,
|
|
"loss": 5.1514,
|
|
"mean_token_accuracy": 0.1842966914176941,
|
|
"num_tokens": 22936111.0,
|
|
"step": 13220
|
|
},
|
|
{
|
|
"entropy": 5.503234243392944,
|
|
"epoch": 1.0289437852557868,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004898740075623218,
|
|
"loss": 5.0257,
|
|
"mean_token_accuracy": 0.1970045030117035,
|
|
"num_tokens": 22944752.0,
|
|
"step": 13225
|
|
},
|
|
{
|
|
"entropy": 5.614857482910156,
|
|
"epoch": 1.0293328146275045,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004898657849345399,
|
|
"loss": 5.2587,
|
|
"mean_token_accuracy": 0.18242369294166566,
|
|
"num_tokens": 22952971.0,
|
|
"step": 13230
|
|
},
|
|
{
|
|
"entropy": 5.598722982406616,
|
|
"epoch": 1.029721843999222,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004898575590465116,
|
|
"loss": 5.1625,
|
|
"mean_token_accuracy": 0.19350814819335938,
|
|
"num_tokens": 22961257.0,
|
|
"step": 13235
|
|
},
|
|
{
|
|
"entropy": 5.54152193069458,
|
|
"epoch": 1.0301108733709394,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004898493298983619,
|
|
"loss": 5.2078,
|
|
"mean_token_accuracy": 0.1872486114501953,
|
|
"num_tokens": 22970659.0,
|
|
"step": 13240
|
|
},
|
|
{
|
|
"entropy": 5.5529930114746096,
|
|
"epoch": 1.0304999027426571,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004898410974902155,
|
|
"loss": 5.1463,
|
|
"mean_token_accuracy": 0.19037771075963975,
|
|
"num_tokens": 22978830.0,
|
|
"step": 13245
|
|
},
|
|
{
|
|
"entropy": 5.623561668395996,
|
|
"epoch": 1.0308889321143746,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004898328618221974,
|
|
"loss": 5.116,
|
|
"mean_token_accuracy": 0.19342898428440095,
|
|
"num_tokens": 22987100.0,
|
|
"step": 13250
|
|
},
|
|
{
|
|
"entropy": 5.573216152191162,
|
|
"epoch": 1.0312779614860923,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004898246228944327,
|
|
"loss": 5.1436,
|
|
"mean_token_accuracy": 0.187310791015625,
|
|
"num_tokens": 22995749.0,
|
|
"step": 13255
|
|
},
|
|
{
|
|
"entropy": 5.646274137496948,
|
|
"epoch": 1.0316669908578098,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004898163807070461,
|
|
"loss": 5.1989,
|
|
"mean_token_accuracy": 0.19106748849153518,
|
|
"num_tokens": 23004410.0,
|
|
"step": 13260
|
|
},
|
|
{
|
|
"entropy": 5.5814062595367435,
|
|
"epoch": 1.0320560202295272,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004898081352601629,
|
|
"loss": 5.0764,
|
|
"mean_token_accuracy": 0.18742465525865554,
|
|
"num_tokens": 23012935.0,
|
|
"step": 13265
|
|
},
|
|
{
|
|
"entropy": 5.515347146987915,
|
|
"epoch": 1.032445049601245,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004897998865539082,
|
|
"loss": 5.0627,
|
|
"mean_token_accuracy": 0.19089292585849763,
|
|
"num_tokens": 23021769.0,
|
|
"step": 13270
|
|
},
|
|
{
|
|
"entropy": 5.5167755603790285,
|
|
"epoch": 1.0328340789729624,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004897916345884069,
|
|
"loss": 5.0689,
|
|
"mean_token_accuracy": 0.18745699375867844,
|
|
"num_tokens": 23030915.0,
|
|
"step": 13275
|
|
},
|
|
{
|
|
"entropy": 5.565987968444825,
|
|
"epoch": 1.0332231083446801,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004897833793637847,
|
|
"loss": 5.184,
|
|
"mean_token_accuracy": 0.18107736855745316,
|
|
"num_tokens": 23039422.0,
|
|
"step": 13280
|
|
},
|
|
{
|
|
"entropy": 5.5884381294250485,
|
|
"epoch": 1.0336121377163976,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004897751208801665,
|
|
"loss": 5.2361,
|
|
"mean_token_accuracy": 0.17725082188844682,
|
|
"num_tokens": 23048485.0,
|
|
"step": 13285
|
|
},
|
|
{
|
|
"entropy": 5.524944734573364,
|
|
"epoch": 1.034001167088115,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004897668591376777,
|
|
"loss": 5.1014,
|
|
"mean_token_accuracy": 0.19463111460208893,
|
|
"num_tokens": 23057506.0,
|
|
"step": 13290
|
|
},
|
|
{
|
|
"entropy": 5.522286653518677,
|
|
"epoch": 1.0343901964598328,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004897585941364436,
|
|
"loss": 4.9591,
|
|
"mean_token_accuracy": 0.20029387921094893,
|
|
"num_tokens": 23065430.0,
|
|
"step": 13295
|
|
},
|
|
{
|
|
"entropy": 5.489220762252808,
|
|
"epoch": 1.0347792258315502,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004897503258765896,
|
|
"loss": 5.0845,
|
|
"mean_token_accuracy": 0.18796505630016327,
|
|
"num_tokens": 23074533.0,
|
|
"step": 13300
|
|
},
|
|
{
|
|
"entropy": 5.55793137550354,
|
|
"epoch": 1.035168255203268,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004897420543582413,
|
|
"loss": 5.0892,
|
|
"mean_token_accuracy": 0.19122830927371978,
|
|
"num_tokens": 23083020.0,
|
|
"step": 13305
|
|
},
|
|
{
|
|
"entropy": 5.533450269699097,
|
|
"epoch": 1.0355572845749854,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000489733779581524,
|
|
"loss": 5.1358,
|
|
"mean_token_accuracy": 0.1904940977692604,
|
|
"num_tokens": 23091992.0,
|
|
"step": 13310
|
|
},
|
|
{
|
|
"entropy": 5.49093861579895,
|
|
"epoch": 1.035946313946703,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004897255015465635,
|
|
"loss": 5.1079,
|
|
"mean_token_accuracy": 0.18566958904266356,
|
|
"num_tokens": 23100411.0,
|
|
"step": 13315
|
|
},
|
|
{
|
|
"entropy": 5.536679458618164,
|
|
"epoch": 1.0363353433184206,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004897172202534853,
|
|
"loss": 5.2,
|
|
"mean_token_accuracy": 0.19183483123779296,
|
|
"num_tokens": 23108867.0,
|
|
"step": 13320
|
|
},
|
|
{
|
|
"entropy": 5.553509473800659,
|
|
"epoch": 1.036724372690138,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000489708935702415,
|
|
"loss": 5.0427,
|
|
"mean_token_accuracy": 0.19434165507555007,
|
|
"num_tokens": 23116692.0,
|
|
"step": 13325
|
|
},
|
|
{
|
|
"entropy": 5.567583990097046,
|
|
"epoch": 1.0371134020618558,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004897006478934784,
|
|
"loss": 5.1178,
|
|
"mean_token_accuracy": 0.19184658229351043,
|
|
"num_tokens": 23125138.0,
|
|
"step": 13330
|
|
},
|
|
{
|
|
"entropy": 5.523353481292725,
|
|
"epoch": 1.0375024314335732,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004896923568268011,
|
|
"loss": 5.1292,
|
|
"mean_token_accuracy": 0.1848578304052353,
|
|
"num_tokens": 23133263.0,
|
|
"step": 13335
|
|
},
|
|
{
|
|
"entropy": 5.570543670654297,
|
|
"epoch": 1.0378914608052907,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000489684062502509,
|
|
"loss": 5.1076,
|
|
"mean_token_accuracy": 0.18882636576890946,
|
|
"num_tokens": 23141984.0,
|
|
"step": 13340
|
|
},
|
|
{
|
|
"entropy": 5.54804482460022,
|
|
"epoch": 1.0382804901770084,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004896757649207281,
|
|
"loss": 5.0817,
|
|
"mean_token_accuracy": 0.19435103237628937,
|
|
"num_tokens": 23151598.0,
|
|
"step": 13345
|
|
},
|
|
{
|
|
"entropy": 5.589086961746216,
|
|
"epoch": 1.0386695195487259,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000489667464081584,
|
|
"loss": 5.2228,
|
|
"mean_token_accuracy": 0.18364229947328567,
|
|
"num_tokens": 23159737.0,
|
|
"step": 13350
|
|
},
|
|
{
|
|
"entropy": 5.554082155227661,
|
|
"epoch": 1.0390585489204436,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004896591599852029,
|
|
"loss": 5.0743,
|
|
"mean_token_accuracy": 0.19256037026643752,
|
|
"num_tokens": 23168852.0,
|
|
"step": 13355
|
|
},
|
|
{
|
|
"entropy": 5.624046325683594,
|
|
"epoch": 1.039447578292161,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004896508526317107,
|
|
"loss": 5.1585,
|
|
"mean_token_accuracy": 0.18748216480016708,
|
|
"num_tokens": 23178227.0,
|
|
"step": 13360
|
|
},
|
|
{
|
|
"entropy": 5.567367076873779,
|
|
"epoch": 1.0398366076638785,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004896425420212334,
|
|
"loss": 5.0713,
|
|
"mean_token_accuracy": 0.19270658642053604,
|
|
"num_tokens": 23187286.0,
|
|
"step": 13365
|
|
},
|
|
{
|
|
"entropy": 5.575743103027344,
|
|
"epoch": 1.0402256370355962,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004896342281538973,
|
|
"loss": 5.1224,
|
|
"mean_token_accuracy": 0.19453513473272324,
|
|
"num_tokens": 23196163.0,
|
|
"step": 13370
|
|
},
|
|
{
|
|
"entropy": 5.56591157913208,
|
|
"epoch": 1.0406146664073137,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004896259110298283,
|
|
"loss": 5.0689,
|
|
"mean_token_accuracy": 0.19389081746339798,
|
|
"num_tokens": 23203742.0,
|
|
"step": 13375
|
|
},
|
|
{
|
|
"entropy": 5.644067621231079,
|
|
"epoch": 1.0410036957790314,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004896175906491528,
|
|
"loss": 5.2359,
|
|
"mean_token_accuracy": 0.18386470526456833,
|
|
"num_tokens": 23212860.0,
|
|
"step": 13380
|
|
},
|
|
{
|
|
"entropy": 5.61379861831665,
|
|
"epoch": 1.0413927251507489,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004896092670119968,
|
|
"loss": 5.1104,
|
|
"mean_token_accuracy": 0.1852978527545929,
|
|
"num_tokens": 23222558.0,
|
|
"step": 13385
|
|
},
|
|
{
|
|
"entropy": 5.571009683609009,
|
|
"epoch": 1.0417817545224664,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004896009401184869,
|
|
"loss": 5.1585,
|
|
"mean_token_accuracy": 0.18610741943120956,
|
|
"num_tokens": 23231413.0,
|
|
"step": 13390
|
|
},
|
|
{
|
|
"entropy": 5.546082162857056,
|
|
"epoch": 1.042170783894184,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004895926099687493,
|
|
"loss": 5.1014,
|
|
"mean_token_accuracy": 0.19446830302476883,
|
|
"num_tokens": 23240783.0,
|
|
"step": 13395
|
|
},
|
|
{
|
|
"entropy": 5.5714925765991214,
|
|
"epoch": 1.0425598132659015,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004895842765629104,
|
|
"loss": 5.2161,
|
|
"mean_token_accuracy": 0.1871562495827675,
|
|
"num_tokens": 23249125.0,
|
|
"step": 13400
|
|
},
|
|
{
|
|
"entropy": 5.57609338760376,
|
|
"epoch": 1.0429488426376192,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004895759399010966,
|
|
"loss": 5.0759,
|
|
"mean_token_accuracy": 0.18885018080472946,
|
|
"num_tokens": 23257793.0,
|
|
"step": 13405
|
|
},
|
|
{
|
|
"entropy": 5.483095693588257,
|
|
"epoch": 1.0433378720093367,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004895675999834345,
|
|
"loss": 5.046,
|
|
"mean_token_accuracy": 0.19669701755046845,
|
|
"num_tokens": 23266361.0,
|
|
"step": 13410
|
|
},
|
|
{
|
|
"entropy": 5.5332506656646725,
|
|
"epoch": 1.0437269013810542,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004895592568100505,
|
|
"loss": 5.0144,
|
|
"mean_token_accuracy": 0.19876361936330794,
|
|
"num_tokens": 23274914.0,
|
|
"step": 13415
|
|
},
|
|
{
|
|
"entropy": 5.540232467651367,
|
|
"epoch": 1.0441159307527719,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004895509103810714,
|
|
"loss": 5.1125,
|
|
"mean_token_accuracy": 0.1861565440893173,
|
|
"num_tokens": 23283067.0,
|
|
"step": 13420
|
|
},
|
|
{
|
|
"entropy": 5.55697603225708,
|
|
"epoch": 1.0445049601244893,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004895425606966237,
|
|
"loss": 5.1262,
|
|
"mean_token_accuracy": 0.18422970175743103,
|
|
"num_tokens": 23291114.0,
|
|
"step": 13425
|
|
},
|
|
{
|
|
"entropy": 5.493901014328003,
|
|
"epoch": 1.044893989496207,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000489534207756834,
|
|
"loss": 4.9969,
|
|
"mean_token_accuracy": 0.19421214163303374,
|
|
"num_tokens": 23300525.0,
|
|
"step": 13430
|
|
},
|
|
{
|
|
"entropy": 5.550111293792725,
|
|
"epoch": 1.0452830188679245,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004895258515618293,
|
|
"loss": 5.092,
|
|
"mean_token_accuracy": 0.19004881232976914,
|
|
"num_tokens": 23308984.0,
|
|
"step": 13435
|
|
},
|
|
{
|
|
"entropy": 5.575098037719727,
|
|
"epoch": 1.045672048239642,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004895174921117362,
|
|
"loss": 5.1936,
|
|
"mean_token_accuracy": 0.17996650338172912,
|
|
"num_tokens": 23318137.0,
|
|
"step": 13440
|
|
},
|
|
{
|
|
"entropy": 5.6501775741577145,
|
|
"epoch": 1.0460610776113597,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004895091294066816,
|
|
"loss": 5.2549,
|
|
"mean_token_accuracy": 0.17623160183429717,
|
|
"num_tokens": 23326276.0,
|
|
"step": 13445
|
|
},
|
|
{
|
|
"entropy": 5.569949579238892,
|
|
"epoch": 1.0464501069830772,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004895007634467924,
|
|
"loss": 5.1273,
|
|
"mean_token_accuracy": 0.18646959215402603,
|
|
"num_tokens": 23334578.0,
|
|
"step": 13450
|
|
},
|
|
{
|
|
"entropy": 5.541098260879517,
|
|
"epoch": 1.0468391363547949,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004894923942321955,
|
|
"loss": 5.1495,
|
|
"mean_token_accuracy": 0.1853663593530655,
|
|
"num_tokens": 23344173.0,
|
|
"step": 13455
|
|
},
|
|
{
|
|
"entropy": 5.519333457946777,
|
|
"epoch": 1.0472281657265123,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004894840217630179,
|
|
"loss": 5.0135,
|
|
"mean_token_accuracy": 0.1950036659836769,
|
|
"num_tokens": 23353098.0,
|
|
"step": 13460
|
|
},
|
|
{
|
|
"entropy": 5.616471624374389,
|
|
"epoch": 1.0476171950982298,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004894756460393868,
|
|
"loss": 5.1416,
|
|
"mean_token_accuracy": 0.18826956450939178,
|
|
"num_tokens": 23362364.0,
|
|
"step": 13465
|
|
},
|
|
{
|
|
"entropy": 5.59700984954834,
|
|
"epoch": 1.0480062244699475,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000489467267061429,
|
|
"loss": 5.1801,
|
|
"mean_token_accuracy": 0.180839404463768,
|
|
"num_tokens": 23371903.0,
|
|
"step": 13470
|
|
},
|
|
{
|
|
"entropy": 5.537702465057373,
|
|
"epoch": 1.048395253841665,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004894588848292718,
|
|
"loss": 5.0958,
|
|
"mean_token_accuracy": 0.19802405536174775,
|
|
"num_tokens": 23381711.0,
|
|
"step": 13475
|
|
},
|
|
{
|
|
"entropy": 5.548175239562989,
|
|
"epoch": 1.0487842832133827,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004894504993430425,
|
|
"loss": 5.0529,
|
|
"mean_token_accuracy": 0.18945176750421525,
|
|
"num_tokens": 23389812.0,
|
|
"step": 13480
|
|
},
|
|
{
|
|
"entropy": 5.565440273284912,
|
|
"epoch": 1.0491733125851002,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000489442110602868,
|
|
"loss": 5.0834,
|
|
"mean_token_accuracy": 0.20017406791448594,
|
|
"num_tokens": 23399231.0,
|
|
"step": 13485
|
|
},
|
|
{
|
|
"entropy": 5.53766565322876,
|
|
"epoch": 1.0495623419568176,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004894337186088759,
|
|
"loss": 5.0657,
|
|
"mean_token_accuracy": 0.18777775764465332,
|
|
"num_tokens": 23407764.0,
|
|
"step": 13490
|
|
},
|
|
{
|
|
"entropy": 5.541928052902222,
|
|
"epoch": 1.0499513713285353,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004894253233611934,
|
|
"loss": 5.024,
|
|
"mean_token_accuracy": 0.19526999145746232,
|
|
"num_tokens": 23416368.0,
|
|
"step": 13495
|
|
},
|
|
{
|
|
"entropy": 5.633498764038086,
|
|
"epoch": 1.0503404007002528,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000489416924859948,
|
|
"loss": 5.2654,
|
|
"mean_token_accuracy": 0.18364062011241913,
|
|
"num_tokens": 23425415.0,
|
|
"step": 13500
|
|
},
|
|
{
|
|
"entropy": 5.5485481262207035,
|
|
"epoch": 1.0507294300719705,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000489408523105267,
|
|
"loss": 5.0778,
|
|
"mean_token_accuracy": 0.18930239826440812,
|
|
"num_tokens": 23433435.0,
|
|
"step": 13505
|
|
},
|
|
{
|
|
"entropy": 5.591840982437134,
|
|
"epoch": 1.051118459443688,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004894001180972779,
|
|
"loss": 5.1359,
|
|
"mean_token_accuracy": 0.18588989675045015,
|
|
"num_tokens": 23442002.0,
|
|
"step": 13510
|
|
},
|
|
{
|
|
"entropy": 5.486305904388428,
|
|
"epoch": 1.0515074888154055,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004893917098361082,
|
|
"loss": 4.929,
|
|
"mean_token_accuracy": 0.19889771640300752,
|
|
"num_tokens": 23450437.0,
|
|
"step": 13515
|
|
},
|
|
{
|
|
"entropy": 5.476190757751465,
|
|
"epoch": 1.0518965181871232,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004893832983218856,
|
|
"loss": 5.0278,
|
|
"mean_token_accuracy": 0.19660004675388337,
|
|
"num_tokens": 23458755.0,
|
|
"step": 13520
|
|
},
|
|
{
|
|
"entropy": 5.580454349517822,
|
|
"epoch": 1.0522855475588406,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004893748835547377,
|
|
"loss": 5.1623,
|
|
"mean_token_accuracy": 0.18904335498809816,
|
|
"num_tokens": 23467138.0,
|
|
"step": 13525
|
|
},
|
|
{
|
|
"entropy": 5.533040857315063,
|
|
"epoch": 1.0526745769305583,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004893664655347921,
|
|
"loss": 5.0258,
|
|
"mean_token_accuracy": 0.19522487968206406,
|
|
"num_tokens": 23475494.0,
|
|
"step": 13530
|
|
},
|
|
{
|
|
"entropy": 5.481938695907592,
|
|
"epoch": 1.0530636063022758,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004893580442621767,
|
|
"loss": 4.9874,
|
|
"mean_token_accuracy": 0.19702944606542588,
|
|
"num_tokens": 23484215.0,
|
|
"step": 13535
|
|
},
|
|
{
|
|
"entropy": 5.486063432693482,
|
|
"epoch": 1.0534526356739935,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000489349619737019,
|
|
"loss": 5.0709,
|
|
"mean_token_accuracy": 0.1844639077782631,
|
|
"num_tokens": 23492604.0,
|
|
"step": 13540
|
|
},
|
|
{
|
|
"entropy": 5.644566297531128,
|
|
"epoch": 1.053841665045711,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000489341191959447,
|
|
"loss": 5.2725,
|
|
"mean_token_accuracy": 0.18335204273462297,
|
|
"num_tokens": 23501817.0,
|
|
"step": 13545
|
|
},
|
|
{
|
|
"entropy": 5.647152423858643,
|
|
"epoch": 1.0542306944174284,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004893327609295887,
|
|
"loss": 5.1743,
|
|
"mean_token_accuracy": 0.1869557186961174,
|
|
"num_tokens": 23509996.0,
|
|
"step": 13550
|
|
},
|
|
{
|
|
"entropy": 5.493410587310791,
|
|
"epoch": 1.0546197237891461,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004893243266475719,
|
|
"loss": 4.9317,
|
|
"mean_token_accuracy": 0.20967918485403061,
|
|
"num_tokens": 23518316.0,
|
|
"step": 13555
|
|
},
|
|
{
|
|
"entropy": 5.500581550598144,
|
|
"epoch": 1.0550087531608636,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004893158891135245,
|
|
"loss": 5.1489,
|
|
"mean_token_accuracy": 0.18843015730381013,
|
|
"num_tokens": 23526851.0,
|
|
"step": 13560
|
|
},
|
|
{
|
|
"entropy": 5.575391435623169,
|
|
"epoch": 1.055397782532581,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004893074483275746,
|
|
"loss": 5.0565,
|
|
"mean_token_accuracy": 0.19761413782835008,
|
|
"num_tokens": 23534757.0,
|
|
"step": 13565
|
|
},
|
|
{
|
|
"entropy": 5.55781044960022,
|
|
"epoch": 1.0557868119042988,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004892990042898503,
|
|
"loss": 5.1213,
|
|
"mean_token_accuracy": 0.1814389169216156,
|
|
"num_tokens": 23544102.0,
|
|
"step": 13570
|
|
},
|
|
{
|
|
"entropy": 5.526807880401611,
|
|
"epoch": 1.0561758412760163,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004892905570004798,
|
|
"loss": 5.1574,
|
|
"mean_token_accuracy": 0.17815360724925994,
|
|
"num_tokens": 23552663.0,
|
|
"step": 13575
|
|
},
|
|
{
|
|
"entropy": 5.540577507019043,
|
|
"epoch": 1.056564870647734,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000489282106459591,
|
|
"loss": 5.0421,
|
|
"mean_token_accuracy": 0.19477053433656694,
|
|
"num_tokens": 23561144.0,
|
|
"step": 13580
|
|
},
|
|
{
|
|
"entropy": 5.485770654678345,
|
|
"epoch": 1.0569539000194514,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004892736526673124,
|
|
"loss": 5.0383,
|
|
"mean_token_accuracy": 0.19195435792207718,
|
|
"num_tokens": 23569833.0,
|
|
"step": 13585
|
|
},
|
|
{
|
|
"entropy": 5.5496666431427,
|
|
"epoch": 1.0573429293911691,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004892651956237721,
|
|
"loss": 5.1038,
|
|
"mean_token_accuracy": 0.1859749212861061,
|
|
"num_tokens": 23578643.0,
|
|
"step": 13590
|
|
},
|
|
{
|
|
"entropy": 5.611403131484986,
|
|
"epoch": 1.0577319587628866,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004892567353290986,
|
|
"loss": 5.171,
|
|
"mean_token_accuracy": 0.18489499092102052,
|
|
"num_tokens": 23587324.0,
|
|
"step": 13595
|
|
},
|
|
{
|
|
"entropy": 5.515933990478516,
|
|
"epoch": 1.058120988134604,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004892482717834201,
|
|
"loss": 5.1094,
|
|
"mean_token_accuracy": 0.18617239743471145,
|
|
"num_tokens": 23595670.0,
|
|
"step": 13600
|
|
},
|
|
{
|
|
"entropy": 5.52309217453003,
|
|
"epoch": 1.0585100175063218,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004892398049868651,
|
|
"loss": 5.0229,
|
|
"mean_token_accuracy": 0.2074963331222534,
|
|
"num_tokens": 23603833.0,
|
|
"step": 13605
|
|
},
|
|
{
|
|
"entropy": 5.542495965957642,
|
|
"epoch": 1.0588990468780393,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000489231334939562,
|
|
"loss": 5.1126,
|
|
"mean_token_accuracy": 0.18682459890842437,
|
|
"num_tokens": 23612815.0,
|
|
"step": 13610
|
|
},
|
|
{
|
|
"entropy": 5.570399570465088,
|
|
"epoch": 1.059288076249757,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004892228616416395,
|
|
"loss": 5.1166,
|
|
"mean_token_accuracy": 0.18690780103206633,
|
|
"num_tokens": 23621178.0,
|
|
"step": 13615
|
|
},
|
|
{
|
|
"entropy": 5.559569931030273,
|
|
"epoch": 1.0596771056214744,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004892143850932259,
|
|
"loss": 5.3037,
|
|
"mean_token_accuracy": 0.18021937012672423,
|
|
"num_tokens": 23630681.0,
|
|
"step": 13620
|
|
},
|
|
{
|
|
"entropy": 5.570667314529419,
|
|
"epoch": 1.060066134993192,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00048920590529445,
|
|
"loss": 5.0976,
|
|
"mean_token_accuracy": 0.19716931283473968,
|
|
"num_tokens": 23639374.0,
|
|
"step": 13625
|
|
},
|
|
{
|
|
"entropy": 5.550150299072266,
|
|
"epoch": 1.0604551643649096,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004891974222454406,
|
|
"loss": 5.1074,
|
|
"mean_token_accuracy": 0.19388217777013778,
|
|
"num_tokens": 23648217.0,
|
|
"step": 13630
|
|
},
|
|
{
|
|
"entropy": 5.576891994476318,
|
|
"epoch": 1.060844193736627,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004891889359463261,
|
|
"loss": 5.0819,
|
|
"mean_token_accuracy": 0.1954309433698654,
|
|
"num_tokens": 23656688.0,
|
|
"step": 13635
|
|
},
|
|
{
|
|
"entropy": 5.533861351013184,
|
|
"epoch": 1.0612332231083448,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004891804463972354,
|
|
"loss": 5.152,
|
|
"mean_token_accuracy": 0.191353702545166,
|
|
"num_tokens": 23666646.0,
|
|
"step": 13640
|
|
},
|
|
{
|
|
"entropy": 5.5231880187988285,
|
|
"epoch": 1.0616222524800623,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004891719535982974,
|
|
"loss": 5.0516,
|
|
"mean_token_accuracy": 0.19825712740421295,
|
|
"num_tokens": 23675278.0,
|
|
"step": 13645
|
|
},
|
|
{
|
|
"entropy": 5.559094047546386,
|
|
"epoch": 1.0620112818517797,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004891634575496408,
|
|
"loss": 5.169,
|
|
"mean_token_accuracy": 0.1882852330803871,
|
|
"num_tokens": 23684263.0,
|
|
"step": 13650
|
|
},
|
|
{
|
|
"entropy": 5.542915916442871,
|
|
"epoch": 1.0624003112234974,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004891549582513946,
|
|
"loss": 4.9945,
|
|
"mean_token_accuracy": 0.19987936913967133,
|
|
"num_tokens": 23692249.0,
|
|
"step": 13655
|
|
},
|
|
{
|
|
"entropy": 5.5894450664520265,
|
|
"epoch": 1.062789340595215,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000489146455703688,
|
|
"loss": 5.2109,
|
|
"mean_token_accuracy": 0.18558669835329056,
|
|
"num_tokens": 23701082.0,
|
|
"step": 13660
|
|
},
|
|
{
|
|
"entropy": 5.557166004180909,
|
|
"epoch": 1.0631783699669326,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004891379499066495,
|
|
"loss": 5.1697,
|
|
"mean_token_accuracy": 0.17952576279640198,
|
|
"num_tokens": 23710277.0,
|
|
"step": 13665
|
|
},
|
|
{
|
|
"entropy": 5.542935180664062,
|
|
"epoch": 1.06356739933865,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004891294408604087,
|
|
"loss": 5.1395,
|
|
"mean_token_accuracy": 0.18682847768068314,
|
|
"num_tokens": 23719131.0,
|
|
"step": 13670
|
|
},
|
|
{
|
|
"entropy": 5.5245277881622314,
|
|
"epoch": 1.0639564287103676,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004891209285650942,
|
|
"loss": 5.0844,
|
|
"mean_token_accuracy": 0.18916123509407043,
|
|
"num_tokens": 23727674.0,
|
|
"step": 13675
|
|
},
|
|
{
|
|
"entropy": 5.5888899803161625,
|
|
"epoch": 1.0643454580820852,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004891124130208355,
|
|
"loss": 5.2052,
|
|
"mean_token_accuracy": 0.18104732632637024,
|
|
"num_tokens": 23736181.0,
|
|
"step": 13680
|
|
},
|
|
{
|
|
"entropy": 5.561683225631714,
|
|
"epoch": 1.0647344874538027,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004891038942277618,
|
|
"loss": 5.0908,
|
|
"mean_token_accuracy": 0.19476557672023773,
|
|
"num_tokens": 23744552.0,
|
|
"step": 13685
|
|
},
|
|
{
|
|
"entropy": 5.640599250793457,
|
|
"epoch": 1.0651235168255204,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004890953721860022,
|
|
"loss": 5.2097,
|
|
"mean_token_accuracy": 0.18445058166980743,
|
|
"num_tokens": 23753755.0,
|
|
"step": 13690
|
|
},
|
|
{
|
|
"entropy": 5.5744880676269535,
|
|
"epoch": 1.065512546197238,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004890868468956862,
|
|
"loss": 5.1122,
|
|
"mean_token_accuracy": 0.19210155457258224,
|
|
"num_tokens": 23761759.0,
|
|
"step": 13695
|
|
},
|
|
{
|
|
"entropy": 5.5430450439453125,
|
|
"epoch": 1.0659015755689554,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000489078318356943,
|
|
"loss": 5.096,
|
|
"mean_token_accuracy": 0.19025285840034484,
|
|
"num_tokens": 23769952.0,
|
|
"step": 13700
|
|
},
|
|
{
|
|
"entropy": 5.516364002227784,
|
|
"epoch": 1.066290604940673,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004890697865699021,
|
|
"loss": 5.1414,
|
|
"mean_token_accuracy": 0.18873618841171264,
|
|
"num_tokens": 23778045.0,
|
|
"step": 13705
|
|
},
|
|
{
|
|
"entropy": 5.560581254959106,
|
|
"epoch": 1.0666796343123905,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004890612515346929,
|
|
"loss": 5.0779,
|
|
"mean_token_accuracy": 0.18887751549482346,
|
|
"num_tokens": 23787477.0,
|
|
"step": 13710
|
|
},
|
|
{
|
|
"entropy": 5.555035829544067,
|
|
"epoch": 1.0670686636841082,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004890527132514448,
|
|
"loss": 5.0814,
|
|
"mean_token_accuracy": 0.20074543058872224,
|
|
"num_tokens": 23795905.0,
|
|
"step": 13715
|
|
},
|
|
{
|
|
"entropy": 5.627185678482055,
|
|
"epoch": 1.0674576930558257,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004890441717202876,
|
|
"loss": 5.1546,
|
|
"mean_token_accuracy": 0.1903741791844368,
|
|
"num_tokens": 23804339.0,
|
|
"step": 13720
|
|
},
|
|
{
|
|
"entropy": 5.582160139083863,
|
|
"epoch": 1.0678467224275432,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004890356269413507,
|
|
"loss": 5.1562,
|
|
"mean_token_accuracy": 0.185725799202919,
|
|
"num_tokens": 23813032.0,
|
|
"step": 13725
|
|
},
|
|
{
|
|
"entropy": 5.56419734954834,
|
|
"epoch": 1.068235751799261,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000489027078914764,
|
|
"loss": 5.0371,
|
|
"mean_token_accuracy": 0.2049105256795883,
|
|
"num_tokens": 23822047.0,
|
|
"step": 13730
|
|
},
|
|
{
|
|
"entropy": 5.462968206405639,
|
|
"epoch": 1.0686247811709784,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004890185276406569,
|
|
"loss": 5.011,
|
|
"mean_token_accuracy": 0.1926239013671875,
|
|
"num_tokens": 23831220.0,
|
|
"step": 13735
|
|
},
|
|
{
|
|
"entropy": 5.540319967269897,
|
|
"epoch": 1.069013810542696,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004890099731191592,
|
|
"loss": 5.17,
|
|
"mean_token_accuracy": 0.18684637397527695,
|
|
"num_tokens": 23840118.0,
|
|
"step": 13740
|
|
},
|
|
{
|
|
"entropy": 5.587307167053223,
|
|
"epoch": 1.0694028399144135,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000489001415350401,
|
|
"loss": 5.1306,
|
|
"mean_token_accuracy": 0.19016505479812623,
|
|
"num_tokens": 23848826.0,
|
|
"step": 13745
|
|
},
|
|
{
|
|
"entropy": 5.62038516998291,
|
|
"epoch": 1.069791869286131,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004889928543345118,
|
|
"loss": 5.2569,
|
|
"mean_token_accuracy": 0.184573432803154,
|
|
"num_tokens": 23857462.0,
|
|
"step": 13750
|
|
},
|
|
{
|
|
"entropy": 5.540248727798462,
|
|
"epoch": 1.0701808986578487,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004889842900716217,
|
|
"loss": 5.1117,
|
|
"mean_token_accuracy": 0.19019486606121064,
|
|
"num_tokens": 23866842.0,
|
|
"step": 13755
|
|
},
|
|
{
|
|
"entropy": 5.574837350845337,
|
|
"epoch": 1.0705699280295662,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004889757225618606,
|
|
"loss": 5.1394,
|
|
"mean_token_accuracy": 0.18294884860515595,
|
|
"num_tokens": 23875079.0,
|
|
"step": 13760
|
|
},
|
|
{
|
|
"entropy": 5.615604066848755,
|
|
"epoch": 1.0709589574012839,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004889671518053584,
|
|
"loss": 5.1147,
|
|
"mean_token_accuracy": 0.1861308217048645,
|
|
"num_tokens": 23883963.0,
|
|
"step": 13765
|
|
},
|
|
{
|
|
"entropy": 5.589229679107666,
|
|
"epoch": 1.0713479867730014,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004889585778022453,
|
|
"loss": 5.0853,
|
|
"mean_token_accuracy": 0.20030197203159333,
|
|
"num_tokens": 23892709.0,
|
|
"step": 13770
|
|
},
|
|
{
|
|
"entropy": 5.57830696105957,
|
|
"epoch": 1.0717370161447188,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004889500005526514,
|
|
"loss": 5.2215,
|
|
"mean_token_accuracy": 0.1834134966135025,
|
|
"num_tokens": 23901124.0,
|
|
"step": 13775
|
|
},
|
|
{
|
|
"entropy": 5.6007640838623045,
|
|
"epoch": 1.0721260455164365,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004889414200567067,
|
|
"loss": 5.1574,
|
|
"mean_token_accuracy": 0.1839173659682274,
|
|
"num_tokens": 23909442.0,
|
|
"step": 13780
|
|
},
|
|
{
|
|
"entropy": 5.5681853771209715,
|
|
"epoch": 1.072515074888154,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004889328363145415,
|
|
"loss": 5.1293,
|
|
"mean_token_accuracy": 0.19386406540870665,
|
|
"num_tokens": 23918143.0,
|
|
"step": 13785
|
|
},
|
|
{
|
|
"entropy": 5.580930900573731,
|
|
"epoch": 1.0729041042598717,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004889242493262859,
|
|
"loss": 5.0733,
|
|
"mean_token_accuracy": 0.1941058561205864,
|
|
"num_tokens": 23926432.0,
|
|
"step": 13790
|
|
},
|
|
{
|
|
"entropy": 5.6241645336151125,
|
|
"epoch": 1.0732931336315892,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004889156590920704,
|
|
"loss": 5.2217,
|
|
"mean_token_accuracy": 0.17931180894374849,
|
|
"num_tokens": 23935362.0,
|
|
"step": 13795
|
|
},
|
|
{
|
|
"entropy": 5.488368797302246,
|
|
"epoch": 1.0736821630033067,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004889070656120253,
|
|
"loss": 4.9684,
|
|
"mean_token_accuracy": 0.198727485537529,
|
|
"num_tokens": 23943926.0,
|
|
"step": 13800
|
|
},
|
|
{
|
|
"entropy": 5.5760266304016115,
|
|
"epoch": 1.0740711923750244,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004888984688862809,
|
|
"loss": 5.135,
|
|
"mean_token_accuracy": 0.1842544123530388,
|
|
"num_tokens": 23952513.0,
|
|
"step": 13805
|
|
},
|
|
{
|
|
"entropy": 5.537561082839966,
|
|
"epoch": 1.0744602217467418,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004888898689149677,
|
|
"loss": 5.1714,
|
|
"mean_token_accuracy": 0.18406044393777848,
|
|
"num_tokens": 23961529.0,
|
|
"step": 13810
|
|
},
|
|
{
|
|
"entropy": 5.676672124862671,
|
|
"epoch": 1.0748492511184595,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004888812656982162,
|
|
"loss": 5.19,
|
|
"mean_token_accuracy": 0.18808944076299666,
|
|
"num_tokens": 23971156.0,
|
|
"step": 13815
|
|
},
|
|
{
|
|
"entropy": 5.6050958156585695,
|
|
"epoch": 1.075238280490177,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004888726592361569,
|
|
"loss": 5.1075,
|
|
"mean_token_accuracy": 0.18496610671281816,
|
|
"num_tokens": 23979676.0,
|
|
"step": 13820
|
|
},
|
|
{
|
|
"entropy": 5.5462747573852536,
|
|
"epoch": 1.0756273098618945,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004888640495289204,
|
|
"loss": 5.0621,
|
|
"mean_token_accuracy": 0.19622142910957335,
|
|
"num_tokens": 23987764.0,
|
|
"step": 13825
|
|
},
|
|
{
|
|
"entropy": 5.562421226501465,
|
|
"epoch": 1.0760163392336122,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004888554365766374,
|
|
"loss": 5.108,
|
|
"mean_token_accuracy": 0.18574558049440384,
|
|
"num_tokens": 23995844.0,
|
|
"step": 13830
|
|
},
|
|
{
|
|
"entropy": 5.608630514144897,
|
|
"epoch": 1.0764053686053296,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004888468203794385,
|
|
"loss": 5.1845,
|
|
"mean_token_accuracy": 0.18551842570304872,
|
|
"num_tokens": 24003824.0,
|
|
"step": 13835
|
|
},
|
|
{
|
|
"entropy": 5.561627149581909,
|
|
"epoch": 1.0767943979770473,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004888382009374545,
|
|
"loss": 5.1338,
|
|
"mean_token_accuracy": 0.1885688602924347,
|
|
"num_tokens": 24012471.0,
|
|
"step": 13840
|
|
},
|
|
{
|
|
"entropy": 5.571304273605347,
|
|
"epoch": 1.0771834273487648,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004888295782508161,
|
|
"loss": 5.0982,
|
|
"mean_token_accuracy": 0.1925314575433731,
|
|
"num_tokens": 24021344.0,
|
|
"step": 13845
|
|
},
|
|
{
|
|
"entropy": 5.529728031158447,
|
|
"epoch": 1.0775724567204823,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004888209523196542,
|
|
"loss": 5.0805,
|
|
"mean_token_accuracy": 0.19462160766124725,
|
|
"num_tokens": 24029598.0,
|
|
"step": 13850
|
|
},
|
|
{
|
|
"entropy": 5.506401872634887,
|
|
"epoch": 1.0779614860922,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004888123231440997,
|
|
"loss": 5.1042,
|
|
"mean_token_accuracy": 0.19367956668138503,
|
|
"num_tokens": 24038097.0,
|
|
"step": 13855
|
|
},
|
|
{
|
|
"entropy": 5.55786166191101,
|
|
"epoch": 1.0783505154639175,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004888036907242834,
|
|
"loss": 5.1556,
|
|
"mean_token_accuracy": 0.19234763830900192,
|
|
"num_tokens": 24046812.0,
|
|
"step": 13860
|
|
},
|
|
{
|
|
"entropy": 5.597179555892945,
|
|
"epoch": 1.0787395448356352,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004887950550603366,
|
|
"loss": 5.1237,
|
|
"mean_token_accuracy": 0.18817501217126847,
|
|
"num_tokens": 24054908.0,
|
|
"step": 13865
|
|
},
|
|
{
|
|
"entropy": 5.503034448623657,
|
|
"epoch": 1.0791285742073526,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004887864161523901,
|
|
"loss": 5.1082,
|
|
"mean_token_accuracy": 0.19433763027191162,
|
|
"num_tokens": 24063695.0,
|
|
"step": 13870
|
|
},
|
|
{
|
|
"entropy": 5.530128383636475,
|
|
"epoch": 1.0795176035790701,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004887777740005749,
|
|
"loss": 5.1087,
|
|
"mean_token_accuracy": 0.19398031383752823,
|
|
"num_tokens": 24072481.0,
|
|
"step": 13875
|
|
},
|
|
{
|
|
"entropy": 5.5003636360168455,
|
|
"epoch": 1.0799066329507878,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004887691286050224,
|
|
"loss": 5.1208,
|
|
"mean_token_accuracy": 0.194350366294384,
|
|
"num_tokens": 24080751.0,
|
|
"step": 13880
|
|
},
|
|
{
|
|
"entropy": 5.544689130783081,
|
|
"epoch": 1.0802956623225053,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004887604799658635,
|
|
"loss": 5.0922,
|
|
"mean_token_accuracy": 0.19087753295898438,
|
|
"num_tokens": 24088618.0,
|
|
"step": 13885
|
|
},
|
|
{
|
|
"entropy": 5.578266620635986,
|
|
"epoch": 1.080684691694223,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004887518280832295,
|
|
"loss": 5.1842,
|
|
"mean_token_accuracy": 0.1857525885105133,
|
|
"num_tokens": 24096754.0,
|
|
"step": 13890
|
|
},
|
|
{
|
|
"entropy": 5.551661491394043,
|
|
"epoch": 1.0810737210659405,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004887431729572519,
|
|
"loss": 5.1186,
|
|
"mean_token_accuracy": 0.1966030180454254,
|
|
"num_tokens": 24104793.0,
|
|
"step": 13895
|
|
},
|
|
{
|
|
"entropy": 5.707340955734253,
|
|
"epoch": 1.081462750437658,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004887345145880617,
|
|
"loss": 5.2533,
|
|
"mean_token_accuracy": 0.17408431321382523,
|
|
"num_tokens": 24113816.0,
|
|
"step": 13900
|
|
},
|
|
{
|
|
"entropy": 5.557224750518799,
|
|
"epoch": 1.0818517798093756,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004887258529757904,
|
|
"loss": 5.0394,
|
|
"mean_token_accuracy": 0.19136426597833633,
|
|
"num_tokens": 24123002.0,
|
|
"step": 13905
|
|
},
|
|
{
|
|
"entropy": 5.581175184249878,
|
|
"epoch": 1.082240809181093,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004887171881205696,
|
|
"loss": 5.0965,
|
|
"mean_token_accuracy": 0.1916172832250595,
|
|
"num_tokens": 24130841.0,
|
|
"step": 13910
|
|
},
|
|
{
|
|
"entropy": 5.579694938659668,
|
|
"epoch": 1.0826298385528108,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004887085200225306,
|
|
"loss": 5.1689,
|
|
"mean_token_accuracy": 0.1794822633266449,
|
|
"num_tokens": 24139236.0,
|
|
"step": 13915
|
|
},
|
|
{
|
|
"entropy": 5.5275708675384525,
|
|
"epoch": 1.0830188679245283,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004886998486818049,
|
|
"loss": 5.027,
|
|
"mean_token_accuracy": 0.19782494753599167,
|
|
"num_tokens": 24147824.0,
|
|
"step": 13920
|
|
},
|
|
{
|
|
"entropy": 5.553222513198852,
|
|
"epoch": 1.083407897296246,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004886911740985242,
|
|
"loss": 5.1548,
|
|
"mean_token_accuracy": 0.1861773267388344,
|
|
"num_tokens": 24156555.0,
|
|
"step": 13925
|
|
},
|
|
{
|
|
"entropy": 5.620675897598266,
|
|
"epoch": 1.0837969266679635,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00048868249627282,
|
|
"loss": 5.0816,
|
|
"mean_token_accuracy": 0.19274846464395523,
|
|
"num_tokens": 24164424.0,
|
|
"step": 13930
|
|
},
|
|
{
|
|
"entropy": 5.591138029098511,
|
|
"epoch": 1.084185956039681,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000488673815204824,
|
|
"loss": 5.1033,
|
|
"mean_token_accuracy": 0.19383617043495177,
|
|
"num_tokens": 24173325.0,
|
|
"step": 13935
|
|
},
|
|
{
|
|
"entropy": 5.611918878555298,
|
|
"epoch": 1.0845749854113986,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004886651308946681,
|
|
"loss": 5.2591,
|
|
"mean_token_accuracy": 0.18532256484031678,
|
|
"num_tokens": 24181781.0,
|
|
"step": 13940
|
|
},
|
|
{
|
|
"entropy": 5.58632264137268,
|
|
"epoch": 1.084964014783116,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004886564433424839,
|
|
"loss": 5.0742,
|
|
"mean_token_accuracy": 0.18997456282377242,
|
|
"num_tokens": 24190065.0,
|
|
"step": 13945
|
|
},
|
|
{
|
|
"entropy": 5.585769128799439,
|
|
"epoch": 1.0853530441548336,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004886477525484032,
|
|
"loss": 5.212,
|
|
"mean_token_accuracy": 0.17957908660173416,
|
|
"num_tokens": 24198814.0,
|
|
"step": 13950
|
|
},
|
|
{
|
|
"entropy": 5.560888624191284,
|
|
"epoch": 1.0857420735265513,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004886390585125579,
|
|
"loss": 5.0894,
|
|
"mean_token_accuracy": 0.18675375282764434,
|
|
"num_tokens": 24208008.0,
|
|
"step": 13955
|
|
},
|
|
{
|
|
"entropy": 5.625029468536377,
|
|
"epoch": 1.0861311028982688,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004886303612350799,
|
|
"loss": 5.0937,
|
|
"mean_token_accuracy": 0.1943022146821022,
|
|
"num_tokens": 24216098.0,
|
|
"step": 13960
|
|
},
|
|
{
|
|
"entropy": 5.485174608230591,
|
|
"epoch": 1.0865201322699864,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004886216607161013,
|
|
"loss": 5.0299,
|
|
"mean_token_accuracy": 0.19588403701782225,
|
|
"num_tokens": 24224943.0,
|
|
"step": 13965
|
|
},
|
|
{
|
|
"entropy": 5.528639411926269,
|
|
"epoch": 1.086909161641704,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004886129569557538,
|
|
"loss": 5.0989,
|
|
"mean_token_accuracy": 0.18515908420085908,
|
|
"num_tokens": 24232950.0,
|
|
"step": 13970
|
|
},
|
|
{
|
|
"entropy": 5.625828123092651,
|
|
"epoch": 1.0872981910134216,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004886042499541699,
|
|
"loss": 5.2439,
|
|
"mean_token_accuracy": 0.1840382382273674,
|
|
"num_tokens": 24242355.0,
|
|
"step": 13975
|
|
},
|
|
{
|
|
"entropy": 5.56804723739624,
|
|
"epoch": 1.087687220385139,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004885955397114813,
|
|
"loss": 5.0947,
|
|
"mean_token_accuracy": 0.1971299722790718,
|
|
"num_tokens": 24251247.0,
|
|
"step": 13980
|
|
},
|
|
{
|
|
"entropy": 5.551373243331909,
|
|
"epoch": 1.0880762497568566,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004885868262278205,
|
|
"loss": 5.1746,
|
|
"mean_token_accuracy": 0.18218241333961488,
|
|
"num_tokens": 24260281.0,
|
|
"step": 13985
|
|
},
|
|
{
|
|
"entropy": 5.621750020980835,
|
|
"epoch": 1.0884652791285743,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004885781095033195,
|
|
"loss": 5.1733,
|
|
"mean_token_accuracy": 0.18397517502307892,
|
|
"num_tokens": 24268474.0,
|
|
"step": 13990
|
|
},
|
|
{
|
|
"entropy": 5.635916090011596,
|
|
"epoch": 1.0888543085002917,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004885693895381108,
|
|
"loss": 5.1351,
|
|
"mean_token_accuracy": 0.19216557443141938,
|
|
"num_tokens": 24276897.0,
|
|
"step": 13995
|
|
},
|
|
{
|
|
"entropy": 5.551297521591186,
|
|
"epoch": 1.0892433378720092,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004885606663323263,
|
|
"loss": 5.122,
|
|
"mean_token_accuracy": 0.1863850697875023,
|
|
"num_tokens": 24285892.0,
|
|
"step": 14000
|
|
},
|
|
{
|
|
"entropy": 5.537345504760742,
|
|
"epoch": 1.089632367243727,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004885519398860987,
|
|
"loss": 5.1681,
|
|
"mean_token_accuracy": 0.18805530667304993,
|
|
"num_tokens": 24294141.0,
|
|
"step": 14005
|
|
},
|
|
{
|
|
"entropy": 5.517060804367065,
|
|
"epoch": 1.0900213966154444,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004885432101995604,
|
|
"loss": 5.062,
|
|
"mean_token_accuracy": 0.19237542003393174,
|
|
"num_tokens": 24302803.0,
|
|
"step": 14010
|
|
},
|
|
{
|
|
"entropy": 5.67067322731018,
|
|
"epoch": 1.090410425987162,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004885344772728436,
|
|
"loss": 5.2398,
|
|
"mean_token_accuracy": 0.18113906681537628,
|
|
"num_tokens": 24311755.0,
|
|
"step": 14015
|
|
},
|
|
{
|
|
"entropy": 5.579156446456909,
|
|
"epoch": 1.0907994553588796,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004885257411060812,
|
|
"loss": 5.0567,
|
|
"mean_token_accuracy": 0.1981242999434471,
|
|
"num_tokens": 24320913.0,
|
|
"step": 14020
|
|
},
|
|
{
|
|
"entropy": 5.614050960540771,
|
|
"epoch": 1.0911884847305973,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004885170016994053,
|
|
"loss": 5.2668,
|
|
"mean_token_accuracy": 0.17813585549592972,
|
|
"num_tokens": 24331112.0,
|
|
"step": 14025
|
|
},
|
|
{
|
|
"entropy": 5.5172981262207035,
|
|
"epoch": 1.0915775141023147,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004885082590529489,
|
|
"loss": 5.0573,
|
|
"mean_token_accuracy": 0.19136620163917542,
|
|
"num_tokens": 24339286.0,
|
|
"step": 14030
|
|
},
|
|
{
|
|
"entropy": 5.529982995986939,
|
|
"epoch": 1.0919665434740322,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004884995131668445,
|
|
"loss": 5.074,
|
|
"mean_token_accuracy": 0.18799741417169571,
|
|
"num_tokens": 24347787.0,
|
|
"step": 14035
|
|
},
|
|
{
|
|
"entropy": 5.553857660293579,
|
|
"epoch": 1.09235557284575,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004884907640412248,
|
|
"loss": 5.0428,
|
|
"mean_token_accuracy": 0.195489402115345,
|
|
"num_tokens": 24356340.0,
|
|
"step": 14040
|
|
},
|
|
{
|
|
"entropy": 5.5461619853973385,
|
|
"epoch": 1.0927446022174674,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004884820116762225,
|
|
"loss": 5.1257,
|
|
"mean_token_accuracy": 0.18353502899408342,
|
|
"num_tokens": 24365182.0,
|
|
"step": 14045
|
|
},
|
|
{
|
|
"entropy": 5.62374062538147,
|
|
"epoch": 1.093133631589185,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004884732560719706,
|
|
"loss": 5.1581,
|
|
"mean_token_accuracy": 0.1798996075987816,
|
|
"num_tokens": 24373455.0,
|
|
"step": 14050
|
|
},
|
|
{
|
|
"entropy": 5.601822280883789,
|
|
"epoch": 1.0935226609609026,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004884644972286017,
|
|
"loss": 5.2276,
|
|
"mean_token_accuracy": 0.18316431790590287,
|
|
"num_tokens": 24382433.0,
|
|
"step": 14055
|
|
},
|
|
{
|
|
"entropy": 5.547022914886474,
|
|
"epoch": 1.09391169033262,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004884557351462488,
|
|
"loss": 5.0565,
|
|
"mean_token_accuracy": 0.19143435209989548,
|
|
"num_tokens": 24390971.0,
|
|
"step": 14060
|
|
},
|
|
{
|
|
"entropy": 5.612474679946899,
|
|
"epoch": 1.0943007197043377,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004884469698250449,
|
|
"loss": 5.1079,
|
|
"mean_token_accuracy": 0.18284114748239516,
|
|
"num_tokens": 24399508.0,
|
|
"step": 14065
|
|
},
|
|
{
|
|
"entropy": 5.532827472686767,
|
|
"epoch": 1.0946897490760552,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000488438201265123,
|
|
"loss": 5.051,
|
|
"mean_token_accuracy": 0.19327640384435654,
|
|
"num_tokens": 24408424.0,
|
|
"step": 14070
|
|
},
|
|
{
|
|
"entropy": 5.491205787658691,
|
|
"epoch": 1.095078778447773,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004884294294666161,
|
|
"loss": 5.1679,
|
|
"mean_token_accuracy": 0.18431971073150635,
|
|
"num_tokens": 24416918.0,
|
|
"step": 14075
|
|
},
|
|
{
|
|
"entropy": 5.537044429779053,
|
|
"epoch": 1.0954678078194904,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004884206544296573,
|
|
"loss": 5.0223,
|
|
"mean_token_accuracy": 0.19488463699817657,
|
|
"num_tokens": 24425779.0,
|
|
"step": 14080
|
|
},
|
|
{
|
|
"entropy": 5.506648254394531,
|
|
"epoch": 1.0958568371912079,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004884118761543797,
|
|
"loss": 5.0387,
|
|
"mean_token_accuracy": 0.18994079381227494,
|
|
"num_tokens": 24434567.0,
|
|
"step": 14085
|
|
},
|
|
{
|
|
"entropy": 5.549871635437012,
|
|
"epoch": 1.0962458665629256,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004884030946409167,
|
|
"loss": 5.1301,
|
|
"mean_token_accuracy": 0.18966175019741058,
|
|
"num_tokens": 24442980.0,
|
|
"step": 14090
|
|
},
|
|
{
|
|
"entropy": 5.537383699417115,
|
|
"epoch": 1.096634895934643,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004883943098894013,
|
|
"loss": 5.059,
|
|
"mean_token_accuracy": 0.18882790356874465,
|
|
"num_tokens": 24452273.0,
|
|
"step": 14095
|
|
},
|
|
{
|
|
"entropy": 5.616352272033692,
|
|
"epoch": 1.0970239253063607,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000488385521899967,
|
|
"loss": 5.1594,
|
|
"mean_token_accuracy": 0.19060663729906083,
|
|
"num_tokens": 24461854.0,
|
|
"step": 14100
|
|
},
|
|
{
|
|
"entropy": 5.616894388198853,
|
|
"epoch": 1.0974129546780782,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000488376730672747,
|
|
"loss": 5.2052,
|
|
"mean_token_accuracy": 0.1858152389526367,
|
|
"num_tokens": 24470468.0,
|
|
"step": 14105
|
|
},
|
|
{
|
|
"entropy": 5.534484910964966,
|
|
"epoch": 1.0978019840497957,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004883679362078746,
|
|
"loss": 5.0745,
|
|
"mean_token_accuracy": 0.19345633685588837,
|
|
"num_tokens": 24479282.0,
|
|
"step": 14110
|
|
},
|
|
{
|
|
"entropy": 5.629233884811401,
|
|
"epoch": 1.0981910134215134,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004883591385054836,
|
|
"loss": 5.1488,
|
|
"mean_token_accuracy": 0.19297229498624802,
|
|
"num_tokens": 24487331.0,
|
|
"step": 14115
|
|
},
|
|
{
|
|
"entropy": 5.605197095870972,
|
|
"epoch": 1.0985800427932308,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004883503375657072,
|
|
"loss": 5.0553,
|
|
"mean_token_accuracy": 0.19714493453502654,
|
|
"num_tokens": 24496101.0,
|
|
"step": 14120
|
|
},
|
|
{
|
|
"entropy": 5.623606109619141,
|
|
"epoch": 1.0989690721649485,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004883415333886789,
|
|
"loss": 5.154,
|
|
"mean_token_accuracy": 0.1851455107331276,
|
|
"num_tokens": 24504321.0,
|
|
"step": 14125
|
|
},
|
|
{
|
|
"entropy": 5.566852378845215,
|
|
"epoch": 1.099358101536666,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004883327259745325,
|
|
"loss": 5.054,
|
|
"mean_token_accuracy": 0.19597918838262557,
|
|
"num_tokens": 24511887.0,
|
|
"step": 14130
|
|
},
|
|
{
|
|
"entropy": 5.549468278884888,
|
|
"epoch": 1.0997471309083835,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004883239153234015,
|
|
"loss": 5.0602,
|
|
"mean_token_accuracy": 0.1902603030204773,
|
|
"num_tokens": 24521188.0,
|
|
"step": 14135
|
|
},
|
|
{
|
|
"entropy": 5.576074504852295,
|
|
"epoch": 1.1001361602801012,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004883151014354197,
|
|
"loss": 5.0593,
|
|
"mean_token_accuracy": 0.19443640857934952,
|
|
"num_tokens": 24530656.0,
|
|
"step": 14140
|
|
},
|
|
{
|
|
"entropy": 5.494708251953125,
|
|
"epoch": 1.1005251896518187,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004883062843107207,
|
|
"loss": 5.0538,
|
|
"mean_token_accuracy": 0.18540543913841248,
|
|
"num_tokens": 24539438.0,
|
|
"step": 14145
|
|
},
|
|
{
|
|
"entropy": 5.562297916412353,
|
|
"epoch": 1.1009142190235364,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004882974639494383,
|
|
"loss": 5.1366,
|
|
"mean_token_accuracy": 0.1859801784157753,
|
|
"num_tokens": 24548005.0,
|
|
"step": 14150
|
|
},
|
|
{
|
|
"entropy": 5.628852224349975,
|
|
"epoch": 1.1013032483952538,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004882886403517065,
|
|
"loss": 5.1877,
|
|
"mean_token_accuracy": 0.18561447858810426,
|
|
"num_tokens": 24556507.0,
|
|
"step": 14155
|
|
},
|
|
{
|
|
"entropy": 5.534324502944946,
|
|
"epoch": 1.1016922777669713,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004882798135176589,
|
|
"loss": 5.1231,
|
|
"mean_token_accuracy": 0.19144049137830735,
|
|
"num_tokens": 24565228.0,
|
|
"step": 14160
|
|
},
|
|
{
|
|
"entropy": 5.533432674407959,
|
|
"epoch": 1.102081307138689,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00048827098344742973,
|
|
"loss": 5.0794,
|
|
"mean_token_accuracy": 0.1909134492278099,
|
|
"num_tokens": 24573977.0,
|
|
"step": 14165
|
|
},
|
|
{
|
|
"entropy": 5.512648105621338,
|
|
"epoch": 1.1024703365104065,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004882621501411528,
|
|
"loss": 5.02,
|
|
"mean_token_accuracy": 0.1979286938905716,
|
|
"num_tokens": 24582897.0,
|
|
"step": 14170
|
|
},
|
|
{
|
|
"entropy": 5.532407331466675,
|
|
"epoch": 1.1028593658821242,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004882533135989622,
|
|
"loss": 5.031,
|
|
"mean_token_accuracy": 0.19007385969161988,
|
|
"num_tokens": 24591132.0,
|
|
"step": 14175
|
|
},
|
|
{
|
|
"entropy": 5.494268703460693,
|
|
"epoch": 1.1032483952538417,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000488244473820992,
|
|
"loss": 5.0741,
|
|
"mean_token_accuracy": 0.19256412535905837,
|
|
"num_tokens": 24600111.0,
|
|
"step": 14180
|
|
},
|
|
{
|
|
"entropy": 5.511301851272583,
|
|
"epoch": 1.1036374246255591,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00048823563080737634,
|
|
"loss": 5.1113,
|
|
"mean_token_accuracy": 0.19070682376623155,
|
|
"num_tokens": 24609229.0,
|
|
"step": 14185
|
|
},
|
|
{
|
|
"entropy": 5.547101640701294,
|
|
"epoch": 1.1040264539972768,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004882267845582493,
|
|
"loss": 5.0289,
|
|
"mean_token_accuracy": 0.19263579696416855,
|
|
"num_tokens": 24618012.0,
|
|
"step": 14190
|
|
},
|
|
{
|
|
"entropy": 5.555389785766602,
|
|
"epoch": 1.1044154833689943,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00048821793507374526,
|
|
"loss": 5.0968,
|
|
"mean_token_accuracy": 0.1878509536385536,
|
|
"num_tokens": 24626801.0,
|
|
"step": 14195
|
|
},
|
|
{
|
|
"entropy": 5.610468816757202,
|
|
"epoch": 1.104804512740712,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004882090823539984,
|
|
"loss": 5.1662,
|
|
"mean_token_accuracy": 0.1899107202887535,
|
|
"num_tokens": 24635365.0,
|
|
"step": 14200
|
|
},
|
|
{
|
|
"entropy": 5.546853160858154,
|
|
"epoch": 1.1051935421124295,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004882002263991431,
|
|
"loss": 5.0937,
|
|
"mean_token_accuracy": 0.1900238573551178,
|
|
"num_tokens": 24643745.0,
|
|
"step": 14205
|
|
},
|
|
{
|
|
"entropy": 5.497986125946045,
|
|
"epoch": 1.105582571484147,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00048819136720931364,
|
|
"loss": 5.0049,
|
|
"mean_token_accuracy": 0.18967562168836594,
|
|
"num_tokens": 24652760.0,
|
|
"step": 14210
|
|
},
|
|
{
|
|
"entropy": 5.535041666030883,
|
|
"epoch": 1.1059716008558647,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00048818250478464457,
|
|
"loss": 5.1166,
|
|
"mean_token_accuracy": 0.19113752394914627,
|
|
"num_tokens": 24661326.0,
|
|
"step": 14215
|
|
},
|
|
{
|
|
"entropy": 5.569070148468017,
|
|
"epoch": 1.1063606302275821,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004881736391252703,
|
|
"loss": 5.0152,
|
|
"mean_token_accuracy": 0.2029775857925415,
|
|
"num_tokens": 24669611.0,
|
|
"step": 14220
|
|
},
|
|
{
|
|
"entropy": 5.584267473220825,
|
|
"epoch": 1.1067496595992998,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004881647702313253,
|
|
"loss": 5.1536,
|
|
"mean_token_accuracy": 0.1834797292947769,
|
|
"num_tokens": 24677780.0,
|
|
"step": 14225
|
|
},
|
|
{
|
|
"entropy": 5.50883297920227,
|
|
"epoch": 1.1071386889710173,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00048815589810294427,
|
|
"loss": 5.0188,
|
|
"mean_token_accuracy": 0.1955699771642685,
|
|
"num_tokens": 24685807.0,
|
|
"step": 14230
|
|
},
|
|
{
|
|
"entropy": 5.543837785720825,
|
|
"epoch": 1.1075277183427348,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00048814702274026174,
|
|
"loss": 5.0901,
|
|
"mean_token_accuracy": 0.1868273437023163,
|
|
"num_tokens": 24694383.0,
|
|
"step": 14235
|
|
},
|
|
{
|
|
"entropy": 5.51952052116394,
|
|
"epoch": 1.1079167477144525,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004881381441434124,
|
|
"loss": 5.0359,
|
|
"mean_token_accuracy": 0.19846682846546174,
|
|
"num_tokens": 24702325.0,
|
|
"step": 14240
|
|
},
|
|
{
|
|
"entropy": 5.617363166809082,
|
|
"epoch": 1.10830577708617,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000488129262312531,
|
|
"loss": 5.0643,
|
|
"mean_token_accuracy": 0.19092031121253966,
|
|
"num_tokens": 24710725.0,
|
|
"step": 14245
|
|
},
|
|
{
|
|
"entropy": 5.570712566375732,
|
|
"epoch": 1.1086948064578876,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00048812037724775217,
|
|
"loss": 5.1146,
|
|
"mean_token_accuracy": 0.19066088199615477,
|
|
"num_tokens": 24720230.0,
|
|
"step": 14250
|
|
},
|
|
{
|
|
"entropy": 5.540719270706177,
|
|
"epoch": 1.1090838358296051,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004881114889492109,
|
|
"loss": 5.0723,
|
|
"mean_token_accuracy": 0.19068222045898436,
|
|
"num_tokens": 24728896.0,
|
|
"step": 14255
|
|
},
|
|
{
|
|
"entropy": 5.617240476608276,
|
|
"epoch": 1.1094728652013226,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00048810259741704197,
|
|
"loss": 5.1538,
|
|
"mean_token_accuracy": 0.1849449783563614,
|
|
"num_tokens": 24737731.0,
|
|
"step": 14260
|
|
},
|
|
{
|
|
"entropy": 5.559365606307983,
|
|
"epoch": 1.1098618945730403,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004880937026513803,
|
|
"loss": 5.0182,
|
|
"mean_token_accuracy": 0.2024766504764557,
|
|
"num_tokens": 24746335.0,
|
|
"step": 14265
|
|
},
|
|
{
|
|
"entropy": 5.525782108306885,
|
|
"epoch": 1.1102509239447578,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004880848046523609,
|
|
"loss": 5.0314,
|
|
"mean_token_accuracy": 0.19644611775875093,
|
|
"num_tokens": 24755917.0,
|
|
"step": 14270
|
|
},
|
|
{
|
|
"entropy": 5.5859959602355955,
|
|
"epoch": 1.1106399533164755,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00048807590342011875,
|
|
"loss": 5.1782,
|
|
"mean_token_accuracy": 0.18299742490053178,
|
|
"num_tokens": 24764713.0,
|
|
"step": 14275
|
|
},
|
|
{
|
|
"entropy": 5.661219358444214,
|
|
"epoch": 1.111028982688193,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00048806699895478895,
|
|
"loss": 5.2017,
|
|
"mean_token_accuracy": 0.18422999680042268,
|
|
"num_tokens": 24773464.0,
|
|
"step": 14280
|
|
},
|
|
{
|
|
"entropy": 5.59569935798645,
|
|
"epoch": 1.1114180120599104,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004880580912565065,
|
|
"loss": 5.1056,
|
|
"mean_token_accuracy": 0.19189320802688598,
|
|
"num_tokens": 24781437.0,
|
|
"step": 14285
|
|
},
|
|
{
|
|
"entropy": 5.471013593673706,
|
|
"epoch": 1.1118070414316281,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004880491803254067,
|
|
"loss": 4.9623,
|
|
"mean_token_accuracy": 0.20401892960071563,
|
|
"num_tokens": 24789505.0,
|
|
"step": 14290
|
|
},
|
|
{
|
|
"entropy": 5.582314920425415,
|
|
"epoch": 1.1121960708033456,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004880402661616246,
|
|
"loss": 5.1777,
|
|
"mean_token_accuracy": 0.18516246229410172,
|
|
"num_tokens": 24798492.0,
|
|
"step": 14295
|
|
},
|
|
{
|
|
"entropy": 5.582237386703492,
|
|
"epoch": 1.1125851001750633,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004880313487652956,
|
|
"loss": 5.1427,
|
|
"mean_token_accuracy": 0.18301793336868286,
|
|
"num_tokens": 24807472.0,
|
|
"step": 14300
|
|
},
|
|
{
|
|
"entropy": 5.621257877349853,
|
|
"epoch": 1.1129741295467808,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00048802242813655503,
|
|
"loss": 5.1447,
|
|
"mean_token_accuracy": 0.1889468625187874,
|
|
"num_tokens": 24815838.0,
|
|
"step": 14305
|
|
},
|
|
{
|
|
"entropy": 5.535931158065796,
|
|
"epoch": 1.1133631589184985,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000488013504275538,
|
|
"loss": 5.0308,
|
|
"mean_token_accuracy": 0.20103780925273895,
|
|
"num_tokens": 24823953.0,
|
|
"step": 14310
|
|
},
|
|
{
|
|
"entropy": 5.493774938583374,
|
|
"epoch": 1.113752188290216,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004880045771823802,
|
|
"loss": 4.9757,
|
|
"mean_token_accuracy": 0.20277907103300094,
|
|
"num_tokens": 24832414.0,
|
|
"step": 14315
|
|
},
|
|
{
|
|
"entropy": 5.5106306076049805,
|
|
"epoch": 1.1141412176619334,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00048799564685721695,
|
|
"loss": 5.105,
|
|
"mean_token_accuracy": 0.19672067314386368,
|
|
"num_tokens": 24840503.0,
|
|
"step": 14320
|
|
},
|
|
{
|
|
"entropy": 5.58501615524292,
|
|
"epoch": 1.1145302470336511,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004879867133001837,
|
|
"loss": 5.2269,
|
|
"mean_token_accuracy": 0.1800301879644394,
|
|
"num_tokens": 24849272.0,
|
|
"step": 14325
|
|
},
|
|
{
|
|
"entropy": 5.645293569564819,
|
|
"epoch": 1.1149192764053686,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004879777765114162,
|
|
"loss": 5.1811,
|
|
"mean_token_accuracy": 0.18523346483707429,
|
|
"num_tokens": 24858565.0,
|
|
"step": 14330
|
|
},
|
|
{
|
|
"entropy": 5.595496988296508,
|
|
"epoch": 1.115308305777086,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00048796883649104996,
|
|
"loss": 5.1225,
|
|
"mean_token_accuracy": 0.19080182015895844,
|
|
"num_tokens": 24867811.0,
|
|
"step": 14335
|
|
},
|
|
{
|
|
"entropy": 5.551525211334228,
|
|
"epoch": 1.1156973351488038,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004879598932392206,
|
|
"loss": 5.1684,
|
|
"mean_token_accuracy": 0.18083980083465576,
|
|
"num_tokens": 24876776.0,
|
|
"step": 14340
|
|
},
|
|
{
|
|
"entropy": 5.563112735748291,
|
|
"epoch": 1.1160863645205212,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00048795094675606364,
|
|
"loss": 5.0618,
|
|
"mean_token_accuracy": 0.19113542437553405,
|
|
"num_tokens": 24885030.0,
|
|
"step": 14345
|
|
},
|
|
{
|
|
"entropy": 5.628605318069458,
|
|
"epoch": 1.116475393892239,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004879419970417152,
|
|
"loss": 5.2177,
|
|
"mean_token_accuracy": 0.18255677670240403,
|
|
"num_tokens": 24894336.0,
|
|
"step": 14350
|
|
},
|
|
{
|
|
"entropy": 5.632161855697632,
|
|
"epoch": 1.1168644232639564,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00048793304409631077,
|
|
"loss": 5.1768,
|
|
"mean_token_accuracy": 0.1853221356868744,
|
|
"num_tokens": 24903107.0,
|
|
"step": 14355
|
|
},
|
|
{
|
|
"entropy": 5.688526201248169,
|
|
"epoch": 1.117253452635674,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004879240879199863,
|
|
"loss": 5.2455,
|
|
"mean_token_accuracy": 0.18908555656671525,
|
|
"num_tokens": 24912727.0,
|
|
"step": 14360
|
|
},
|
|
{
|
|
"entropy": 5.521405267715454,
|
|
"epoch": 1.1176424820073916,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00048791512851287786,
|
|
"loss": 5.0194,
|
|
"mean_token_accuracy": 0.192735193669796,
|
|
"num_tokens": 24921534.0,
|
|
"step": 14365
|
|
},
|
|
{
|
|
"entropy": 5.5539459705352785,
|
|
"epoch": 1.118031511379109,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00048790616587512107,
|
|
"loss": 5.1014,
|
|
"mean_token_accuracy": 0.18986730128526688,
|
|
"num_tokens": 24930093.0,
|
|
"step": 14370
|
|
},
|
|
{
|
|
"entropy": 5.610888242721558,
|
|
"epoch": 1.1184205407508268,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004878972000068521,
|
|
"loss": 5.1886,
|
|
"mean_token_accuracy": 0.19122879803180695,
|
|
"num_tokens": 24939230.0,
|
|
"step": 14375
|
|
},
|
|
{
|
|
"entropy": 5.621839952468872,
|
|
"epoch": 1.1188095701225442,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00048788823090820707,
|
|
"loss": 5.2321,
|
|
"mean_token_accuracy": 0.19314769208431243,
|
|
"num_tokens": 24947595.0,
|
|
"step": 14380
|
|
},
|
|
{
|
|
"entropy": 5.619896697998047,
|
|
"epoch": 1.1191985994942617,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00048787925857932194,
|
|
"loss": 5.1861,
|
|
"mean_token_accuracy": 0.18565509021282195,
|
|
"num_tokens": 24957099.0,
|
|
"step": 14385
|
|
},
|
|
{
|
|
"entropy": 5.55630464553833,
|
|
"epoch": 1.1195876288659794,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00048787028302033287,
|
|
"loss": 5.0709,
|
|
"mean_token_accuracy": 0.18945772796869279,
|
|
"num_tokens": 24965701.0,
|
|
"step": 14390
|
|
},
|
|
{
|
|
"entropy": 5.638362216949463,
|
|
"epoch": 1.1199766582376969,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00048786130423137606,
|
|
"loss": 5.1916,
|
|
"mean_token_accuracy": 0.1828547954559326,
|
|
"num_tokens": 24974025.0,
|
|
"step": 14395
|
|
},
|
|
{
|
|
"entropy": 5.664219856262207,
|
|
"epoch": 1.1203656876094146,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004878523222125879,
|
|
"loss": 5.2263,
|
|
"mean_token_accuracy": 0.18391305655241014,
|
|
"num_tokens": 24982930.0,
|
|
"step": 14400
|
|
},
|
|
{
|
|
"entropy": 5.615021991729736,
|
|
"epoch": 1.120754716981132,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004878433369641044,
|
|
"loss": 5.0937,
|
|
"mean_token_accuracy": 0.1945231392979622,
|
|
"num_tokens": 24991332.0,
|
|
"step": 14405
|
|
},
|
|
{
|
|
"entropy": 5.56526026725769,
|
|
"epoch": 1.1211437463528497,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004878343484860621,
|
|
"loss": 5.0918,
|
|
"mean_token_accuracy": 0.19387697875499726,
|
|
"num_tokens": 25000130.0,
|
|
"step": 14410
|
|
},
|
|
{
|
|
"entropy": 5.546545886993409,
|
|
"epoch": 1.1215327757245672,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004878253567785972,
|
|
"loss": 5.108,
|
|
"mean_token_accuracy": 0.19131711423397063,
|
|
"num_tokens": 25008423.0,
|
|
"step": 14415
|
|
},
|
|
{
|
|
"entropy": 5.634926509857178,
|
|
"epoch": 1.1219218050962847,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00048781636184184644,
|
|
"loss": 5.1681,
|
|
"mean_token_accuracy": 0.18848209381103515,
|
|
"num_tokens": 25017399.0,
|
|
"step": 14420
|
|
},
|
|
{
|
|
"entropy": 5.649090909957886,
|
|
"epoch": 1.1223108344680024,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000487807363675946,
|
|
"loss": 5.1544,
|
|
"mean_token_accuracy": 0.1925899416208267,
|
|
"num_tokens": 25025957.0,
|
|
"step": 14425
|
|
},
|
|
{
|
|
"entropy": 5.600171184539795,
|
|
"epoch": 1.1226998638397199,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004877983622810326,
|
|
"loss": 5.0783,
|
|
"mean_token_accuracy": 0.19370086640119552,
|
|
"num_tokens": 25034246.0,
|
|
"step": 14430
|
|
},
|
|
{
|
|
"entropy": 5.523709964752197,
|
|
"epoch": 1.1230888932114376,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004877893576572427,
|
|
"loss": 5.083,
|
|
"mean_token_accuracy": 0.19385031163692473,
|
|
"num_tokens": 25042461.0,
|
|
"step": 14435
|
|
},
|
|
{
|
|
"entropy": 5.569584846496582,
|
|
"epoch": 1.123477922583155,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000487780349804713,
|
|
"loss": 5.0519,
|
|
"mean_token_accuracy": 0.19904048144817352,
|
|
"num_tokens": 25051291.0,
|
|
"step": 14440
|
|
},
|
|
{
|
|
"entropy": 5.587459659576416,
|
|
"epoch": 1.1238669519548725,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004877713387235802,
|
|
"loss": 5.1772,
|
|
"mean_token_accuracy": 0.18640127629041672,
|
|
"num_tokens": 25060538.0,
|
|
"step": 14445
|
|
},
|
|
{
|
|
"entropy": 5.608622407913208,
|
|
"epoch": 1.1242559813265902,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000487762324413981,
|
|
"loss": 5.1562,
|
|
"mean_token_accuracy": 0.18106972724199294,
|
|
"num_tokens": 25068965.0,
|
|
"step": 14450
|
|
},
|
|
{
|
|
"entropy": 5.610302543640136,
|
|
"epoch": 1.1246450106983077,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00048775330687605213,
|
|
"loss": 5.1423,
|
|
"mean_token_accuracy": 0.18641403913497925,
|
|
"num_tokens": 25077021.0,
|
|
"step": 14455
|
|
},
|
|
{
|
|
"entropy": 5.569644498825073,
|
|
"epoch": 1.1250340400700254,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004877442861099305,
|
|
"loss": 5.1383,
|
|
"mean_token_accuracy": 0.19138455837965013,
|
|
"num_tokens": 25086009.0,
|
|
"step": 14460
|
|
},
|
|
{
|
|
"entropy": 5.501922464370727,
|
|
"epoch": 1.1254230694417429,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004877352621157529,
|
|
"loss": 5.06,
|
|
"mean_token_accuracy": 0.1943339228630066,
|
|
"num_tokens": 25094745.0,
|
|
"step": 14465
|
|
},
|
|
{
|
|
"entropy": 5.564437532424927,
|
|
"epoch": 1.1258120988134603,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00048772623489365635,
|
|
"loss": 5.0715,
|
|
"mean_token_accuracy": 0.18664079457521437,
|
|
"num_tokens": 25103087.0,
|
|
"step": 14470
|
|
},
|
|
{
|
|
"entropy": 5.6123435497283936,
|
|
"epoch": 1.126201128185178,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004877172044437777,
|
|
"loss": 5.1098,
|
|
"mean_token_accuracy": 0.18710518032312393,
|
|
"num_tokens": 25111822.0,
|
|
"step": 14475
|
|
},
|
|
{
|
|
"entropy": 5.572814893722534,
|
|
"epoch": 1.1265901575568955,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00048770817076625416,
|
|
"loss": 5.0947,
|
|
"mean_token_accuracy": 0.19054839611053467,
|
|
"num_tokens": 25119975.0,
|
|
"step": 14480
|
|
},
|
|
{
|
|
"entropy": 5.5661180973052975,
|
|
"epoch": 1.126979186928613,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00048769913386122253,
|
|
"loss": 5.1575,
|
|
"mean_token_accuracy": 0.18483465164899826,
|
|
"num_tokens": 25129031.0,
|
|
"step": 14485
|
|
},
|
|
{
|
|
"entropy": 5.5998358726501465,
|
|
"epoch": 1.1273682163003307,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004876900937288202,
|
|
"loss": 5.0812,
|
|
"mean_token_accuracy": 0.1930053025484085,
|
|
"num_tokens": 25138230.0,
|
|
"step": 14490
|
|
},
|
|
{
|
|
"entropy": 5.630468511581421,
|
|
"epoch": 1.1277572456720482,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00048768105036918426,
|
|
"loss": 5.1217,
|
|
"mean_token_accuracy": 0.18948798328638078,
|
|
"num_tokens": 25147120.0,
|
|
"step": 14495
|
|
},
|
|
{
|
|
"entropy": 5.574945020675659,
|
|
"epoch": 1.1281462750437659,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00048767200378245187,
|
|
"loss": 5.1208,
|
|
"mean_token_accuracy": 0.1898228719830513,
|
|
"num_tokens": 25155623.0,
|
|
"step": 14500
|
|
},
|
|
{
|
|
"entropy": 5.4905647277832035,
|
|
"epoch": 1.1285353044154833,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00048766295396876025,
|
|
"loss": 5.0076,
|
|
"mean_token_accuracy": 0.19737488478422166,
|
|
"num_tokens": 25163867.0,
|
|
"step": 14505
|
|
},
|
|
{
|
|
"entropy": 5.560219097137451,
|
|
"epoch": 1.128924333787201,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00048765390092824683,
|
|
"loss": 5.1268,
|
|
"mean_token_accuracy": 0.19247578084468842,
|
|
"num_tokens": 25172838.0,
|
|
"step": 14510
|
|
},
|
|
{
|
|
"entropy": 5.551562786102295,
|
|
"epoch": 1.1293133631589185,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000487644844661049,
|
|
"loss": 5.0555,
|
|
"mean_token_accuracy": 0.19907177835702897,
|
|
"num_tokens": 25181168.0,
|
|
"step": 14515
|
|
},
|
|
{
|
|
"entropy": 5.569566059112549,
|
|
"epoch": 1.129702392530636,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000487635785167304,
|
|
"loss": 5.1521,
|
|
"mean_token_accuracy": 0.1940109983086586,
|
|
"num_tokens": 25190115.0,
|
|
"step": 14520
|
|
},
|
|
{
|
|
"entropy": 5.578721714019776,
|
|
"epoch": 1.1300914219023537,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00048762672244714953,
|
|
"loss": 5.1406,
|
|
"mean_token_accuracy": 0.19143279492855073,
|
|
"num_tokens": 25199594.0,
|
|
"step": 14525
|
|
},
|
|
{
|
|
"entropy": 5.60958251953125,
|
|
"epoch": 1.1304804512740712,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004876176565007229,
|
|
"loss": 5.1136,
|
|
"mean_token_accuracy": 0.1821112722158432,
|
|
"num_tokens": 25208060.0,
|
|
"step": 14530
|
|
},
|
|
{
|
|
"entropy": 5.574132633209229,
|
|
"epoch": 1.1308694806457888,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00048760858732816174,
|
|
"loss": 5.0652,
|
|
"mean_token_accuracy": 0.18881643563508987,
|
|
"num_tokens": 25216257.0,
|
|
"step": 14535
|
|
},
|
|
{
|
|
"entropy": 5.541465616226196,
|
|
"epoch": 1.1312585100175063,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004875995149296037,
|
|
"loss": 5.087,
|
|
"mean_token_accuracy": 0.18855876475572586,
|
|
"num_tokens": 25225032.0,
|
|
"step": 14540
|
|
},
|
|
{
|
|
"entropy": 5.584880208969116,
|
|
"epoch": 1.1316475393892238,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004875904393051864,
|
|
"loss": 5.1337,
|
|
"mean_token_accuracy": 0.19188373386859894,
|
|
"num_tokens": 25233624.0,
|
|
"step": 14545
|
|
},
|
|
{
|
|
"entropy": 5.533587455749512,
|
|
"epoch": 1.1320365687609415,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004875813604550476,
|
|
"loss": 5.1012,
|
|
"mean_token_accuracy": 0.18869900852441787,
|
|
"num_tokens": 25242132.0,
|
|
"step": 14550
|
|
},
|
|
{
|
|
"entropy": 5.584107303619385,
|
|
"epoch": 1.132425598132659,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00048757227837932494,
|
|
"loss": 5.0851,
|
|
"mean_token_accuracy": 0.19440909922122956,
|
|
"num_tokens": 25250923.0,
|
|
"step": 14555
|
|
},
|
|
{
|
|
"entropy": 5.575410795211792,
|
|
"epoch": 1.1328146275043767,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004875631930781563,
|
|
"loss": 5.098,
|
|
"mean_token_accuracy": 0.18965144455432892,
|
|
"num_tokens": 25259783.0,
|
|
"step": 14560
|
|
},
|
|
{
|
|
"entropy": 5.655840301513672,
|
|
"epoch": 1.1332036568760941,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00048755410455167967,
|
|
"loss": 5.286,
|
|
"mean_token_accuracy": 0.1829624816775322,
|
|
"num_tokens": 25268801.0,
|
|
"step": 14565
|
|
},
|
|
{
|
|
"entropy": 5.567112684249878,
|
|
"epoch": 1.1335926862478116,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004875450128000326,
|
|
"loss": 5.0975,
|
|
"mean_token_accuracy": 0.20123474895954133,
|
|
"num_tokens": 25277226.0,
|
|
"step": 14570
|
|
},
|
|
{
|
|
"entropy": 5.580487775802612,
|
|
"epoch": 1.1339817156195293,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004875359178233534,
|
|
"loss": 5.1523,
|
|
"mean_token_accuracy": 0.182919679582119,
|
|
"num_tokens": 25285887.0,
|
|
"step": 14575
|
|
},
|
|
{
|
|
"entropy": 5.517343759536743,
|
|
"epoch": 1.1343707449912468,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00048752681962177985,
|
|
"loss": 5.0093,
|
|
"mean_token_accuracy": 0.19050014466047288,
|
|
"num_tokens": 25294025.0,
|
|
"step": 14580
|
|
},
|
|
{
|
|
"entropy": 5.6035301208496096,
|
|
"epoch": 1.1347597743629645,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00048751771819545013,
|
|
"loss": 5.2135,
|
|
"mean_token_accuracy": 0.18079658150672911,
|
|
"num_tokens": 25303016.0,
|
|
"step": 14585
|
|
},
|
|
{
|
|
"entropy": 5.54065465927124,
|
|
"epoch": 1.135148803734682,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00048750861354450236,
|
|
"loss": 5.0172,
|
|
"mean_token_accuracy": 0.19706076085567475,
|
|
"num_tokens": 25311193.0,
|
|
"step": 14590
|
|
},
|
|
{
|
|
"entropy": 5.550218296051026,
|
|
"epoch": 1.1355378331063994,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004874995056690746,
|
|
"loss": 5.0666,
|
|
"mean_token_accuracy": 0.19193121343851088,
|
|
"num_tokens": 25319380.0,
|
|
"step": 14595
|
|
},
|
|
{
|
|
"entropy": 5.535642480850219,
|
|
"epoch": 1.1359268624781171,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000487490394569305,
|
|
"loss": 5.08,
|
|
"mean_token_accuracy": 0.19244492948055267,
|
|
"num_tokens": 25327854.0,
|
|
"step": 14600
|
|
},
|
|
{
|
|
"entropy": 5.582655620574951,
|
|
"epoch": 1.1363158918498346,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004874812802453319,
|
|
"loss": 5.1514,
|
|
"mean_token_accuracy": 0.18457458466291427,
|
|
"num_tokens": 25335912.0,
|
|
"step": 14605
|
|
},
|
|
{
|
|
"entropy": 5.563676929473877,
|
|
"epoch": 1.1367049212215523,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004874721626972936,
|
|
"loss": 5.1668,
|
|
"mean_token_accuracy": 0.19149231761693955,
|
|
"num_tokens": 25344104.0,
|
|
"step": 14610
|
|
},
|
|
{
|
|
"entropy": 5.452754831314087,
|
|
"epoch": 1.1370939505932698,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004874630419253284,
|
|
"loss": 4.9252,
|
|
"mean_token_accuracy": 0.20484225004911422,
|
|
"num_tokens": 25352583.0,
|
|
"step": 14615
|
|
},
|
|
{
|
|
"entropy": 5.541375732421875,
|
|
"epoch": 1.1374829799649873,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00048745391792957474,
|
|
"loss": 5.0434,
|
|
"mean_token_accuracy": 0.19370035380125045,
|
|
"num_tokens": 25361035.0,
|
|
"step": 14620
|
|
},
|
|
{
|
|
"entropy": 5.563179588317871,
|
|
"epoch": 1.137872009336705,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00048744479071017097,
|
|
"loss": 5.0871,
|
|
"mean_token_accuracy": 0.18786347210407256,
|
|
"num_tokens": 25369511.0,
|
|
"step": 14625
|
|
},
|
|
{
|
|
"entropy": 5.586024761199951,
|
|
"epoch": 1.1382610387084224,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004874356602672556,
|
|
"loss": 5.0854,
|
|
"mean_token_accuracy": 0.1938834547996521,
|
|
"num_tokens": 25378023.0,
|
|
"step": 14630
|
|
},
|
|
{
|
|
"entropy": 5.580712842941284,
|
|
"epoch": 1.1386500680801401,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004874265266009673,
|
|
"loss": 5.117,
|
|
"mean_token_accuracy": 0.19111802577972412,
|
|
"num_tokens": 25386791.0,
|
|
"step": 14635
|
|
},
|
|
{
|
|
"entropy": 5.606944227218628,
|
|
"epoch": 1.1390390974518576,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004874173897114445,
|
|
"loss": 5.1464,
|
|
"mean_token_accuracy": 0.18752903640270233,
|
|
"num_tokens": 25395401.0,
|
|
"step": 14640
|
|
},
|
|
{
|
|
"entropy": 5.575720643997192,
|
|
"epoch": 1.1394281268235753,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00048740824959882603,
|
|
"loss": 5.1135,
|
|
"mean_token_accuracy": 0.18792559206485748,
|
|
"num_tokens": 25404193.0,
|
|
"step": 14645
|
|
},
|
|
{
|
|
"entropy": 5.639514636993408,
|
|
"epoch": 1.1398171561952928,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004873991062632504,
|
|
"loss": 5.1714,
|
|
"mean_token_accuracy": 0.18551381379365922,
|
|
"num_tokens": 25413073.0,
|
|
"step": 14650
|
|
},
|
|
{
|
|
"entropy": 5.546651935577392,
|
|
"epoch": 1.1402061855670103,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00048738995970485635,
|
|
"loss": 5.0803,
|
|
"mean_token_accuracy": 0.19260105192661287,
|
|
"num_tokens": 25422064.0,
|
|
"step": 14655
|
|
},
|
|
{
|
|
"entropy": 5.52317624092102,
|
|
"epoch": 1.140595214938728,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004873808099237827,
|
|
"loss": 5.0614,
|
|
"mean_token_accuracy": 0.19399910420179367,
|
|
"num_tokens": 25430711.0,
|
|
"step": 14660
|
|
},
|
|
{
|
|
"entropy": 5.608675146102906,
|
|
"epoch": 1.1409842443104454,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004873716569201684,
|
|
"loss": 5.1719,
|
|
"mean_token_accuracy": 0.1873139202594757,
|
|
"num_tokens": 25439527.0,
|
|
"step": 14665
|
|
},
|
|
{
|
|
"entropy": 5.634265327453614,
|
|
"epoch": 1.141373273682163,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00048736250069415213,
|
|
"loss": 5.1565,
|
|
"mean_token_accuracy": 0.18710326701402663,
|
|
"num_tokens": 25448633.0,
|
|
"step": 14670
|
|
},
|
|
{
|
|
"entropy": 5.564380216598511,
|
|
"epoch": 1.1417623030538806,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004873533412458729,
|
|
"loss": 5.1007,
|
|
"mean_token_accuracy": 0.19030878245830535,
|
|
"num_tokens": 25457657.0,
|
|
"step": 14675
|
|
},
|
|
{
|
|
"entropy": 5.5843555450439455,
|
|
"epoch": 1.142151332425598,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00048734417857546986,
|
|
"loss": 5.1574,
|
|
"mean_token_accuracy": 0.18433075696229934,
|
|
"num_tokens": 25466698.0,
|
|
"step": 14680
|
|
},
|
|
{
|
|
"entropy": 5.59642915725708,
|
|
"epoch": 1.1425403617973158,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004873350126830818,
|
|
"loss": 5.1226,
|
|
"mean_token_accuracy": 0.18787850588560104,
|
|
"num_tokens": 25474921.0,
|
|
"step": 14685
|
|
},
|
|
{
|
|
"entropy": 5.551491212844849,
|
|
"epoch": 1.1429293911690332,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004873258435688479,
|
|
"loss": 5.02,
|
|
"mean_token_accuracy": 0.19826652556657792,
|
|
"num_tokens": 25483553.0,
|
|
"step": 14690
|
|
},
|
|
{
|
|
"entropy": 5.591440629959107,
|
|
"epoch": 1.143318420540751,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004873166712329073,
|
|
"loss": 5.0939,
|
|
"mean_token_accuracy": 0.19593354761600495,
|
|
"num_tokens": 25492408.0,
|
|
"step": 14695
|
|
},
|
|
{
|
|
"entropy": 5.541330003738404,
|
|
"epoch": 1.1437074499124684,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00048730749567539914,
|
|
"loss": 5.1244,
|
|
"mean_token_accuracy": 0.18857344835996628,
|
|
"num_tokens": 25501404.0,
|
|
"step": 14700
|
|
},
|
|
{
|
|
"entropy": 5.667981386184692,
|
|
"epoch": 1.144096479284186,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00048729831689646257,
|
|
"loss": 5.1248,
|
|
"mean_token_accuracy": 0.18747548907995223,
|
|
"num_tokens": 25510176.0,
|
|
"step": 14705
|
|
},
|
|
{
|
|
"entropy": 5.521900749206543,
|
|
"epoch": 1.1444855086559036,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00048728913489623705,
|
|
"loss": 5.041,
|
|
"mean_token_accuracy": 0.19366063326597213,
|
|
"num_tokens": 25518809.0,
|
|
"step": 14710
|
|
},
|
|
{
|
|
"entropy": 5.551668262481689,
|
|
"epoch": 1.144874538027621,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004872799496748618,
|
|
"loss": 5.1532,
|
|
"mean_token_accuracy": 0.19095004498958587,
|
|
"num_tokens": 25527415.0,
|
|
"step": 14715
|
|
},
|
|
{
|
|
"entropy": 5.5533545970916744,
|
|
"epoch": 1.1452635673993385,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004872707612324761,
|
|
"loss": 5.1018,
|
|
"mean_token_accuracy": 0.18428247421979904,
|
|
"num_tokens": 25535618.0,
|
|
"step": 14720
|
|
},
|
|
{
|
|
"entropy": 5.580552387237549,
|
|
"epoch": 1.1456525967710562,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004872615695692196,
|
|
"loss": 5.0831,
|
|
"mean_token_accuracy": 0.19384828060865403,
|
|
"num_tokens": 25544228.0,
|
|
"step": 14725
|
|
},
|
|
{
|
|
"entropy": 5.616612195968628,
|
|
"epoch": 1.1460416261427737,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004872523746852315,
|
|
"loss": 5.1458,
|
|
"mean_token_accuracy": 0.1881529062986374,
|
|
"num_tokens": 25553557.0,
|
|
"step": 14730
|
|
},
|
|
{
|
|
"entropy": 5.554841327667236,
|
|
"epoch": 1.1464306555144914,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00048724317658065146,
|
|
"loss": 5.0768,
|
|
"mean_token_accuracy": 0.1937004417181015,
|
|
"num_tokens": 25562018.0,
|
|
"step": 14735
|
|
},
|
|
{
|
|
"entropy": 5.597393321990967,
|
|
"epoch": 1.146819684886209,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00048723397525561916,
|
|
"loss": 5.1132,
|
|
"mean_token_accuracy": 0.19164858311414718,
|
|
"num_tokens": 25569382.0,
|
|
"step": 14740
|
|
},
|
|
{
|
|
"entropy": 5.48429045677185,
|
|
"epoch": 1.1472087142579266,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00048722477071027394,
|
|
"loss": 5.0543,
|
|
"mean_token_accuracy": 0.1927467867732048,
|
|
"num_tokens": 25578172.0,
|
|
"step": 14745
|
|
},
|
|
{
|
|
"entropy": 5.522347116470337,
|
|
"epoch": 1.147597743629644,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00048721556294475574,
|
|
"loss": 5.0996,
|
|
"mean_token_accuracy": 0.18739671856164933,
|
|
"num_tokens": 25587572.0,
|
|
"step": 14750
|
|
},
|
|
{
|
|
"entropy": 5.575719165802002,
|
|
"epoch": 1.1479867730013615,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00048720635195920403,
|
|
"loss": 5.1471,
|
|
"mean_token_accuracy": 0.19230797588825227,
|
|
"num_tokens": 25596609.0,
|
|
"step": 14755
|
|
},
|
|
{
|
|
"entropy": 5.567278146743774,
|
|
"epoch": 1.1483758023730792,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004871971377537588,
|
|
"loss": 5.1423,
|
|
"mean_token_accuracy": 0.18543420732021332,
|
|
"num_tokens": 25605707.0,
|
|
"step": 14760
|
|
},
|
|
{
|
|
"entropy": 5.57260684967041,
|
|
"epoch": 1.1487648317447967,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004871879203285597,
|
|
"loss": 5.1156,
|
|
"mean_token_accuracy": 0.19459976702928544,
|
|
"num_tokens": 25614218.0,
|
|
"step": 14765
|
|
},
|
|
{
|
|
"entropy": 5.5321691036224365,
|
|
"epoch": 1.1491538611165142,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00048717869968374655,
|
|
"loss": 5.0297,
|
|
"mean_token_accuracy": 0.1946216568350792,
|
|
"num_tokens": 25622613.0,
|
|
"step": 14770
|
|
},
|
|
{
|
|
"entropy": 5.664019012451172,
|
|
"epoch": 1.1495428904882319,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00048716947581945954,
|
|
"loss": 5.1729,
|
|
"mean_token_accuracy": 0.19284721463918686,
|
|
"num_tokens": 25631396.0,
|
|
"step": 14775
|
|
},
|
|
{
|
|
"entropy": 5.569239282608033,
|
|
"epoch": 1.1499319198599494,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004871602487358383,
|
|
"loss": 5.0749,
|
|
"mean_token_accuracy": 0.1919866144657135,
|
|
"num_tokens": 25640870.0,
|
|
"step": 14780
|
|
},
|
|
{
|
|
"entropy": 5.560152864456176,
|
|
"epoch": 1.150320949231667,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000487151018433023,
|
|
"loss": 5.1432,
|
|
"mean_token_accuracy": 0.18698510825634002,
|
|
"num_tokens": 25649395.0,
|
|
"step": 14785
|
|
},
|
|
{
|
|
"entropy": 5.61124620437622,
|
|
"epoch": 1.1507099786033845,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00048714178491115367,
|
|
"loss": 5.2358,
|
|
"mean_token_accuracy": 0.1810119032859802,
|
|
"num_tokens": 25659087.0,
|
|
"step": 14790
|
|
},
|
|
{
|
|
"entropy": 5.641227674484253,
|
|
"epoch": 1.1510990079751022,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00048713254817037046,
|
|
"loss": 5.1564,
|
|
"mean_token_accuracy": 0.1962727501988411,
|
|
"num_tokens": 25667847.0,
|
|
"step": 14795
|
|
},
|
|
{
|
|
"entropy": 5.6062705516815186,
|
|
"epoch": 1.1514880373468197,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004871233082108135,
|
|
"loss": 5.106,
|
|
"mean_token_accuracy": 0.19782232046127318,
|
|
"num_tokens": 25676786.0,
|
|
"step": 14800
|
|
},
|
|
{
|
|
"entropy": 5.605106401443481,
|
|
"epoch": 1.1518770667185372,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004871140650326228,
|
|
"loss": 5.1476,
|
|
"mean_token_accuracy": 0.1856660410761833,
|
|
"num_tokens": 25685223.0,
|
|
"step": 14805
|
|
},
|
|
{
|
|
"entropy": 5.559368562698364,
|
|
"epoch": 1.1522660960902549,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004871048186359389,
|
|
"loss": 5.1032,
|
|
"mean_token_accuracy": 0.18552485704421998,
|
|
"num_tokens": 25694243.0,
|
|
"step": 14810
|
|
},
|
|
{
|
|
"entropy": 5.5484109878540036,
|
|
"epoch": 1.1526551254619724,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000487095569020902,
|
|
"loss": 4.9898,
|
|
"mean_token_accuracy": 0.19948240220546723,
|
|
"num_tokens": 25702735.0,
|
|
"step": 14815
|
|
},
|
|
{
|
|
"entropy": 5.526841926574707,
|
|
"epoch": 1.1530441548336898,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004870863161876524,
|
|
"loss": 5.0639,
|
|
"mean_token_accuracy": 0.19685641378164292,
|
|
"num_tokens": 25711577.0,
|
|
"step": 14820
|
|
},
|
|
{
|
|
"entropy": 5.489689493179322,
|
|
"epoch": 1.1534331842054075,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004870770601363305,
|
|
"loss": 4.9949,
|
|
"mean_token_accuracy": 0.20101726055145264,
|
|
"num_tokens": 25719927.0,
|
|
"step": 14825
|
|
},
|
|
{
|
|
"entropy": 5.541572952270508,
|
|
"epoch": 1.153822213577125,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00048706780086707675,
|
|
"loss": 5.0797,
|
|
"mean_token_accuracy": 0.19204696416854858,
|
|
"num_tokens": 25728144.0,
|
|
"step": 14830
|
|
},
|
|
{
|
|
"entropy": 5.552884578704834,
|
|
"epoch": 1.1542112429488427,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004870585383800317,
|
|
"loss": 5.0184,
|
|
"mean_token_accuracy": 0.19972701370716095,
|
|
"num_tokens": 25736736.0,
|
|
"step": 14835
|
|
},
|
|
{
|
|
"entropy": 5.6133159637451175,
|
|
"epoch": 1.1546002723205602,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00048704927267533585,
|
|
"loss": 5.1934,
|
|
"mean_token_accuracy": 0.19172807186841964,
|
|
"num_tokens": 25745031.0,
|
|
"step": 14840
|
|
},
|
|
{
|
|
"entropy": 5.633868312835693,
|
|
"epoch": 1.1549893016922779,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00048704000375312975,
|
|
"loss": 5.1924,
|
|
"mean_token_accuracy": 0.19258706420660018,
|
|
"num_tokens": 25754265.0,
|
|
"step": 14845
|
|
},
|
|
{
|
|
"entropy": 5.642695093154908,
|
|
"epoch": 1.1553783310639953,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00048703073161355414,
|
|
"loss": 5.177,
|
|
"mean_token_accuracy": 0.17840857654809952,
|
|
"num_tokens": 25763084.0,
|
|
"step": 14850
|
|
},
|
|
{
|
|
"entropy": 5.656079578399658,
|
|
"epoch": 1.1557673604357128,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004870214562567497,
|
|
"loss": 5.1534,
|
|
"mean_token_accuracy": 0.18367359340190886,
|
|
"num_tokens": 25771626.0,
|
|
"step": 14855
|
|
},
|
|
{
|
|
"entropy": 5.564869213104248,
|
|
"epoch": 1.1561563898074305,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000487012177682857,
|
|
"loss": 5.1143,
|
|
"mean_token_accuracy": 0.18735800236463546,
|
|
"num_tokens": 25780326.0,
|
|
"step": 14860
|
|
},
|
|
{
|
|
"entropy": 5.624983549118042,
|
|
"epoch": 1.156545419179148,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004870028958920171,
|
|
"loss": 5.2342,
|
|
"mean_token_accuracy": 0.1776147499680519,
|
|
"num_tokens": 25789318.0,
|
|
"step": 14865
|
|
},
|
|
{
|
|
"entropy": 5.592816352844238,
|
|
"epoch": 1.1569344485508655,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004869936108843706,
|
|
"loss": 5.1929,
|
|
"mean_token_accuracy": 0.18489024490118028,
|
|
"num_tokens": 25798025.0,
|
|
"step": 14870
|
|
},
|
|
{
|
|
"entropy": 5.615821504592896,
|
|
"epoch": 1.1573234779225832,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00048698432266005854,
|
|
"loss": 5.1002,
|
|
"mean_token_accuracy": 0.19362777918577195,
|
|
"num_tokens": 25806669.0,
|
|
"step": 14875
|
|
},
|
|
{
|
|
"entropy": 5.618700551986694,
|
|
"epoch": 1.1577125072943006,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004869750312192217,
|
|
"loss": 5.0887,
|
|
"mean_token_accuracy": 0.19141381680965425,
|
|
"num_tokens": 25815938.0,
|
|
"step": 14880
|
|
},
|
|
{
|
|
"entropy": 5.552509355545044,
|
|
"epoch": 1.1581015366660183,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00048696573656200123,
|
|
"loss": 5.0467,
|
|
"mean_token_accuracy": 0.19463123083114625,
|
|
"num_tokens": 25824293.0,
|
|
"step": 14885
|
|
},
|
|
{
|
|
"entropy": 5.640071105957031,
|
|
"epoch": 1.1584905660377358,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00048695643868853806,
|
|
"loss": 5.1488,
|
|
"mean_token_accuracy": 0.18800119161605836,
|
|
"num_tokens": 25833081.0,
|
|
"step": 14890
|
|
},
|
|
{
|
|
"entropy": 5.630659198760986,
|
|
"epoch": 1.1588795954094535,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004869471375989733,
|
|
"loss": 5.1858,
|
|
"mean_token_accuracy": 0.18351871520280838,
|
|
"num_tokens": 25841344.0,
|
|
"step": 14895
|
|
},
|
|
{
|
|
"entropy": 5.59793872833252,
|
|
"epoch": 1.159268624781171,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004869378332934481,
|
|
"loss": 5.1557,
|
|
"mean_token_accuracy": 0.18592580854892732,
|
|
"num_tokens": 25850617.0,
|
|
"step": 14900
|
|
},
|
|
{
|
|
"entropy": 5.564720201492309,
|
|
"epoch": 1.1596576541528885,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00048692852577210356,
|
|
"loss": 5.1403,
|
|
"mean_token_accuracy": 0.1918509930372238,
|
|
"num_tokens": 25858569.0,
|
|
"step": 14905
|
|
},
|
|
{
|
|
"entropy": 5.53714919090271,
|
|
"epoch": 1.1600466835246062,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000486919215035081,
|
|
"loss": 5.1155,
|
|
"mean_token_accuracy": 0.19092709422111512,
|
|
"num_tokens": 25866892.0,
|
|
"step": 14910
|
|
},
|
|
{
|
|
"entropy": 5.631830263137817,
|
|
"epoch": 1.1604357128963236,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004869099010825217,
|
|
"loss": 5.1942,
|
|
"mean_token_accuracy": 0.18311539739370347,
|
|
"num_tokens": 25875661.0,
|
|
"step": 14915
|
|
},
|
|
{
|
|
"entropy": 5.524275255203247,
|
|
"epoch": 1.1608247422680413,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00048690058391456684,
|
|
"loss": 5.0049,
|
|
"mean_token_accuracy": 0.20060795843601226,
|
|
"num_tokens": 25884951.0,
|
|
"step": 14920
|
|
},
|
|
{
|
|
"entropy": 5.635675573348999,
|
|
"epoch": 1.1612137716397588,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004868912635313579,
|
|
"loss": 5.2372,
|
|
"mean_token_accuracy": 0.18609603941440583,
|
|
"num_tokens": 25893652.0,
|
|
"step": 14925
|
|
},
|
|
{
|
|
"entropy": 5.639912080764771,
|
|
"epoch": 1.1616028010114763,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004868819399330364,
|
|
"loss": 5.0547,
|
|
"mean_token_accuracy": 0.19008962363004683,
|
|
"num_tokens": 25902375.0,
|
|
"step": 14930
|
|
},
|
|
{
|
|
"entropy": 5.61219596862793,
|
|
"epoch": 1.161991830383194,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004868726131197436,
|
|
"loss": 5.0558,
|
|
"mean_token_accuracy": 0.1957837834954262,
|
|
"num_tokens": 25911322.0,
|
|
"step": 14935
|
|
},
|
|
{
|
|
"entropy": 5.620619106292724,
|
|
"epoch": 1.1623808597549115,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004868632830916212,
|
|
"loss": 5.1609,
|
|
"mean_token_accuracy": 0.19244829267263414,
|
|
"num_tokens": 25920444.0,
|
|
"step": 14940
|
|
},
|
|
{
|
|
"entropy": 5.567115926742554,
|
|
"epoch": 1.1627698891266292,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004868539498488106,
|
|
"loss": 5.1674,
|
|
"mean_token_accuracy": 0.18978559076786042,
|
|
"num_tokens": 25928986.0,
|
|
"step": 14945
|
|
},
|
|
{
|
|
"entropy": 5.591844654083252,
|
|
"epoch": 1.1631589184983466,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004868446133914536,
|
|
"loss": 5.1573,
|
|
"mean_token_accuracy": 0.18468926697969437,
|
|
"num_tokens": 25938209.0,
|
|
"step": 14950
|
|
},
|
|
{
|
|
"entropy": 5.637552547454834,
|
|
"epoch": 1.163547947870064,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00048683527371969185,
|
|
"loss": 5.1772,
|
|
"mean_token_accuracy": 0.1779983326792717,
|
|
"num_tokens": 25946909.0,
|
|
"step": 14955
|
|
},
|
|
{
|
|
"entropy": 5.591159296035767,
|
|
"epoch": 1.1639369772417818,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00048682593083366685,
|
|
"loss": 5.2094,
|
|
"mean_token_accuracy": 0.1895134285092354,
|
|
"num_tokens": 25956154.0,
|
|
"step": 14960
|
|
},
|
|
{
|
|
"entropy": 5.592004442214966,
|
|
"epoch": 1.1643260066134993,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00048681658473352055,
|
|
"loss": 5.1077,
|
|
"mean_token_accuracy": 0.19457264244556427,
|
|
"num_tokens": 25964478.0,
|
|
"step": 14965
|
|
},
|
|
{
|
|
"entropy": 5.553935861587524,
|
|
"epoch": 1.164715035985217,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004868072354193947,
|
|
"loss": 5.1047,
|
|
"mean_token_accuracy": 0.18316972255706787,
|
|
"num_tokens": 25973162.0,
|
|
"step": 14970
|
|
},
|
|
{
|
|
"entropy": 5.5709902286529545,
|
|
"epoch": 1.1651040653569344,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004867978828914312,
|
|
"loss": 5.0624,
|
|
"mean_token_accuracy": 0.1913768991827965,
|
|
"num_tokens": 25982790.0,
|
|
"step": 14975
|
|
},
|
|
{
|
|
"entropy": 5.5766767978668215,
|
|
"epoch": 1.165493094728652,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004867885271497719,
|
|
"loss": 5.0162,
|
|
"mean_token_accuracy": 0.1961001604795456,
|
|
"num_tokens": 25992111.0,
|
|
"step": 14980
|
|
},
|
|
{
|
|
"entropy": 5.630577659606933,
|
|
"epoch": 1.1658821241003696,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004867791681945588,
|
|
"loss": 5.1463,
|
|
"mean_token_accuracy": 0.18628059178590775,
|
|
"num_tokens": 26000803.0,
|
|
"step": 14985
|
|
},
|
|
{
|
|
"entropy": 5.654449033737182,
|
|
"epoch": 1.166271153472087,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00048676980602593395,
|
|
"loss": 5.2573,
|
|
"mean_token_accuracy": 0.18055839836597443,
|
|
"num_tokens": 26010152.0,
|
|
"step": 14990
|
|
},
|
|
{
|
|
"entropy": 5.589032411575317,
|
|
"epoch": 1.1666601828438048,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00048676044064403936,
|
|
"loss": 5.1552,
|
|
"mean_token_accuracy": 0.18115283101797103,
|
|
"num_tokens": 26019183.0,
|
|
"step": 14995
|
|
},
|
|
{
|
|
"entropy": 5.618133401870727,
|
|
"epoch": 1.1670492122155223,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004867510720490171,
|
|
"loss": 5.084,
|
|
"mean_token_accuracy": 0.19277227520942689,
|
|
"num_tokens": 26027459.0,
|
|
"step": 15000
|
|
},
|
|
{
|
|
"epoch": 1.1670492122155223,
|
|
"eval_entropy": 5.38063917646509,
|
|
"eval_loss": 5.199825763702393,
|
|
"eval_mean_token_accuracy": 0.19610792320146367,
|
|
"eval_num_tokens": 26027459.0,
|
|
"eval_runtime": 21.6837,
|
|
"eval_samples_per_second": 1916.558,
|
|
"eval_steps_per_second": 239.581,
|
|
"step": 15000
|
|
},
|
|
{
|
|
"entropy": 5.6070170402526855,
|
|
"epoch": 1.1674382415872397,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004867417002410094,
|
|
"loss": 5.153,
|
|
"mean_token_accuracy": 0.18308807909488678,
|
|
"num_tokens": 26036421.0,
|
|
"step": 15005
|
|
},
|
|
{
|
|
"entropy": 5.571762180328369,
|
|
"epoch": 1.1678272709589574,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00048673232522015845,
|
|
"loss": 5.1572,
|
|
"mean_token_accuracy": 0.1901620551943779,
|
|
"num_tokens": 26044971.0,
|
|
"step": 15010
|
|
},
|
|
{
|
|
"entropy": 5.558289480209351,
|
|
"epoch": 1.168216300330675,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004867229469866064,
|
|
"loss": 5.1052,
|
|
"mean_token_accuracy": 0.18862562179565429,
|
|
"num_tokens": 26053597.0,
|
|
"step": 15015
|
|
},
|
|
{
|
|
"entropy": 5.6364421367645265,
|
|
"epoch": 1.1686053297023926,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004867135655404956,
|
|
"loss": 5.1571,
|
|
"mean_token_accuracy": 0.1851444274187088,
|
|
"num_tokens": 26061928.0,
|
|
"step": 15020
|
|
},
|
|
{
|
|
"entropy": 5.576354598999023,
|
|
"epoch": 1.16899435907411,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00048670418088196844,
|
|
"loss": 5.1127,
|
|
"mean_token_accuracy": 0.19274311810731887,
|
|
"num_tokens": 26070917.0,
|
|
"step": 15025
|
|
},
|
|
{
|
|
"entropy": 5.500616121292114,
|
|
"epoch": 1.1693833884458276,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004866947930111674,
|
|
"loss": 5.0449,
|
|
"mean_token_accuracy": 0.19592256247997283,
|
|
"num_tokens": 26079556.0,
|
|
"step": 15030
|
|
},
|
|
{
|
|
"entropy": 5.5612077713012695,
|
|
"epoch": 1.1697724178175453,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00048668540192823467,
|
|
"loss": 5.1433,
|
|
"mean_token_accuracy": 0.1903790056705475,
|
|
"num_tokens": 26087963.0,
|
|
"step": 15035
|
|
},
|
|
{
|
|
"entropy": 5.6055991649627686,
|
|
"epoch": 1.1701614471892627,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000486676007633313,
|
|
"loss": 5.084,
|
|
"mean_token_accuracy": 0.19391100704669953,
|
|
"num_tokens": 26096208.0,
|
|
"step": 15040
|
|
},
|
|
{
|
|
"entropy": 5.6063727855682375,
|
|
"epoch": 1.1705504765609804,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004866666101265448,
|
|
"loss": 5.1093,
|
|
"mean_token_accuracy": 0.18813618272542953,
|
|
"num_tokens": 26104961.0,
|
|
"step": 15045
|
|
},
|
|
{
|
|
"entropy": 5.5672554016113285,
|
|
"epoch": 1.170939505932698,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00048665720940807274,
|
|
"loss": 5.1264,
|
|
"mean_token_accuracy": 0.18212450444698333,
|
|
"num_tokens": 26113889.0,
|
|
"step": 15050
|
|
},
|
|
{
|
|
"entropy": 5.521347856521606,
|
|
"epoch": 1.1713285353044154,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00048664780547803935,
|
|
"loss": 5.0879,
|
|
"mean_token_accuracy": 0.19350726306438445,
|
|
"num_tokens": 26122139.0,
|
|
"step": 15055
|
|
},
|
|
{
|
|
"entropy": 5.633164596557617,
|
|
"epoch": 1.171717564676133,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004866383983365873,
|
|
"loss": 5.1458,
|
|
"mean_token_accuracy": 0.19945055693387986,
|
|
"num_tokens": 26130817.0,
|
|
"step": 15060
|
|
},
|
|
{
|
|
"entropy": 5.600032997131348,
|
|
"epoch": 1.1721065940478506,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00048662898798385956,
|
|
"loss": 5.1501,
|
|
"mean_token_accuracy": 0.19003477841615676,
|
|
"num_tokens": 26140035.0,
|
|
"step": 15065
|
|
},
|
|
{
|
|
"entropy": 5.669366121292114,
|
|
"epoch": 1.1724956234195683,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00048661957441999875,
|
|
"loss": 5.2063,
|
|
"mean_token_accuracy": 0.18841926008462906,
|
|
"num_tokens": 26149575.0,
|
|
"step": 15070
|
|
},
|
|
{
|
|
"entropy": 5.637383031845093,
|
|
"epoch": 1.1728846527912857,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00048661015764514765,
|
|
"loss": 5.1419,
|
|
"mean_token_accuracy": 0.19596780240535736,
|
|
"num_tokens": 26158743.0,
|
|
"step": 15075
|
|
},
|
|
{
|
|
"entropy": 5.611569261550903,
|
|
"epoch": 1.1732736821630034,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00048660073765944927,
|
|
"loss": 5.1557,
|
|
"mean_token_accuracy": 0.18850169628858565,
|
|
"num_tokens": 26167380.0,
|
|
"step": 15080
|
|
},
|
|
{
|
|
"entropy": 5.4767015933990475,
|
|
"epoch": 1.173662711534721,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004865913144630465,
|
|
"loss": 5.071,
|
|
"mean_token_accuracy": 0.19493190497159957,
|
|
"num_tokens": 26175613.0,
|
|
"step": 15085
|
|
},
|
|
{
|
|
"entropy": 5.618897724151611,
|
|
"epoch": 1.1740517409064384,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00048658188805608227,
|
|
"loss": 5.1873,
|
|
"mean_token_accuracy": 0.18750355243682862,
|
|
"num_tokens": 26184347.0,
|
|
"step": 15090
|
|
},
|
|
{
|
|
"entropy": 5.597576522827149,
|
|
"epoch": 1.174440770278156,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004865724584386998,
|
|
"loss": 5.1111,
|
|
"mean_token_accuracy": 0.19106998145580292,
|
|
"num_tokens": 26193513.0,
|
|
"step": 15095
|
|
},
|
|
{
|
|
"entropy": 5.611871528625488,
|
|
"epoch": 1.1748297996498736,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004865630256110418,
|
|
"loss": 5.1127,
|
|
"mean_token_accuracy": 0.18844806253910065,
|
|
"num_tokens": 26202790.0,
|
|
"step": 15100
|
|
},
|
|
{
|
|
"entropy": 5.544135904312133,
|
|
"epoch": 1.175218829021591,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00048655358957325174,
|
|
"loss": 5.0763,
|
|
"mean_token_accuracy": 0.19279582798480988,
|
|
"num_tokens": 26211032.0,
|
|
"step": 15105
|
|
},
|
|
{
|
|
"entropy": 5.50651330947876,
|
|
"epoch": 1.1756078583933087,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00048654415032547277,
|
|
"loss": 5.0169,
|
|
"mean_token_accuracy": 0.19430835843086242,
|
|
"num_tokens": 26219963.0,
|
|
"step": 15110
|
|
},
|
|
{
|
|
"entropy": 5.617864322662354,
|
|
"epoch": 1.1759968877650262,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00048653470786784794,
|
|
"loss": 5.0614,
|
|
"mean_token_accuracy": 0.1897891029715538,
|
|
"num_tokens": 26228164.0,
|
|
"step": 15115
|
|
},
|
|
{
|
|
"entropy": 5.569379043579102,
|
|
"epoch": 1.176385917136744,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004865252622005206,
|
|
"loss": 5.0896,
|
|
"mean_token_accuracy": 0.19182399213314055,
|
|
"num_tokens": 26236294.0,
|
|
"step": 15120
|
|
},
|
|
{
|
|
"entropy": 5.516499376296997,
|
|
"epoch": 1.1767749465084614,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00048651581332363405,
|
|
"loss": 5.0441,
|
|
"mean_token_accuracy": 0.19946387708187102,
|
|
"num_tokens": 26244955.0,
|
|
"step": 15125
|
|
},
|
|
{
|
|
"entropy": 5.5880265712738035,
|
|
"epoch": 1.177163975880179,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00048650636123733176,
|
|
"loss": 5.1306,
|
|
"mean_token_accuracy": 0.18992896676063536,
|
|
"num_tokens": 26253221.0,
|
|
"step": 15130
|
|
},
|
|
{
|
|
"entropy": 5.627907800674438,
|
|
"epoch": 1.1775530052518965,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004864969059417571,
|
|
"loss": 5.2193,
|
|
"mean_token_accuracy": 0.17644216865301132,
|
|
"num_tokens": 26262544.0,
|
|
"step": 15135
|
|
},
|
|
{
|
|
"entropy": 5.611646747589111,
|
|
"epoch": 1.177942034623614,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004864874474370534,
|
|
"loss": 5.1093,
|
|
"mean_token_accuracy": 0.19003526717424393,
|
|
"num_tokens": 26271864.0,
|
|
"step": 15140
|
|
},
|
|
{
|
|
"entropy": 5.655444192886352,
|
|
"epoch": 1.1783310639953317,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00048647798572336445,
|
|
"loss": 5.1658,
|
|
"mean_token_accuracy": 0.18868221789598466,
|
|
"num_tokens": 26279713.0,
|
|
"step": 15145
|
|
},
|
|
{
|
|
"entropy": 5.545048809051513,
|
|
"epoch": 1.1787200933670492,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00048646852080083355,
|
|
"loss": 4.9951,
|
|
"mean_token_accuracy": 0.20163817703723907,
|
|
"num_tokens": 26288654.0,
|
|
"step": 15150
|
|
},
|
|
{
|
|
"entropy": 5.581171369552612,
|
|
"epoch": 1.1791091227387667,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004864590526696045,
|
|
"loss": 5.1769,
|
|
"mean_token_accuracy": 0.18162493258714676,
|
|
"num_tokens": 26297007.0,
|
|
"step": 15155
|
|
},
|
|
{
|
|
"entropy": 5.5863746166229244,
|
|
"epoch": 1.1794981521104844,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00048644958132982094,
|
|
"loss": 5.1028,
|
|
"mean_token_accuracy": 0.19216720908880233,
|
|
"num_tokens": 26305601.0,
|
|
"step": 15160
|
|
},
|
|
{
|
|
"entropy": 5.618317174911499,
|
|
"epoch": 1.1798871814822018,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00048644010678162644,
|
|
"loss": 5.1424,
|
|
"mean_token_accuracy": 0.1963210791349411,
|
|
"num_tokens": 26313455.0,
|
|
"step": 15165
|
|
},
|
|
{
|
|
"entropy": 5.6111854076385494,
|
|
"epoch": 1.1802762108539195,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004864306290251649,
|
|
"loss": 5.1522,
|
|
"mean_token_accuracy": 0.188117116689682,
|
|
"num_tokens": 26322450.0,
|
|
"step": 15170
|
|
},
|
|
{
|
|
"entropy": 5.63731575012207,
|
|
"epoch": 1.180665240225637,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00048642114806058014,
|
|
"loss": 5.1653,
|
|
"mean_token_accuracy": 0.1797630086541176,
|
|
"num_tokens": 26331301.0,
|
|
"step": 15175
|
|
},
|
|
{
|
|
"entropy": 5.722377347946167,
|
|
"epoch": 1.1810542695973547,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004864116638880159,
|
|
"loss": 5.248,
|
|
"mean_token_accuracy": 0.18856421262025833,
|
|
"num_tokens": 26339937.0,
|
|
"step": 15180
|
|
},
|
|
{
|
|
"entropy": 5.626636075973511,
|
|
"epoch": 1.1814432989690722,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004864021765076162,
|
|
"loss": 5.1145,
|
|
"mean_token_accuracy": 0.19093227237462998,
|
|
"num_tokens": 26348541.0,
|
|
"step": 15185
|
|
},
|
|
{
|
|
"entropy": 5.558046579360962,
|
|
"epoch": 1.1818323283407897,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00048639268591952494,
|
|
"loss": 5.0793,
|
|
"mean_token_accuracy": 0.19542826861143112,
|
|
"num_tokens": 26356621.0,
|
|
"step": 15190
|
|
},
|
|
{
|
|
"entropy": 5.613065147399903,
|
|
"epoch": 1.1822213577125074,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00048638319212388614,
|
|
"loss": 5.1801,
|
|
"mean_token_accuracy": 0.18269234746694565,
|
|
"num_tokens": 26366112.0,
|
|
"step": 15195
|
|
},
|
|
{
|
|
"entropy": 5.665078783035279,
|
|
"epoch": 1.1826103870842248,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004863736951208438,
|
|
"loss": 5.1534,
|
|
"mean_token_accuracy": 0.18836449235677719,
|
|
"num_tokens": 26374768.0,
|
|
"step": 15200
|
|
},
|
|
{
|
|
"entropy": 5.597625112533569,
|
|
"epoch": 1.1829994164559423,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00048636419491054217,
|
|
"loss": 5.1359,
|
|
"mean_token_accuracy": 0.1941370978951454,
|
|
"num_tokens": 26383097.0,
|
|
"step": 15205
|
|
},
|
|
{
|
|
"entropy": 5.6053431034088135,
|
|
"epoch": 1.18338844582766,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004863546914931252,
|
|
"loss": 5.1141,
|
|
"mean_token_accuracy": 0.1876509353518486,
|
|
"num_tokens": 26391361.0,
|
|
"step": 15210
|
|
},
|
|
{
|
|
"entropy": 5.5784852504730225,
|
|
"epoch": 1.1837774751993775,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004863451848687373,
|
|
"loss": 5.0642,
|
|
"mean_token_accuracy": 0.1935330033302307,
|
|
"num_tokens": 26400818.0,
|
|
"step": 15215
|
|
},
|
|
{
|
|
"entropy": 5.60666708946228,
|
|
"epoch": 1.1841665045710952,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00048633567503752253,
|
|
"loss": 5.1392,
|
|
"mean_token_accuracy": 0.1896408572793007,
|
|
"num_tokens": 26409650.0,
|
|
"step": 15220
|
|
},
|
|
{
|
|
"entropy": 5.5267926216125485,
|
|
"epoch": 1.1845555339428127,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004863261619996253,
|
|
"loss": 5.0136,
|
|
"mean_token_accuracy": 0.19559521079063416,
|
|
"num_tokens": 26418237.0,
|
|
"step": 15225
|
|
},
|
|
{
|
|
"entropy": 5.470397090911865,
|
|
"epoch": 1.1849445633145304,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004863166457551899,
|
|
"loss": 4.9812,
|
|
"mean_token_accuracy": 0.20518125891685485,
|
|
"num_tokens": 26426366.0,
|
|
"step": 15230
|
|
},
|
|
{
|
|
"entropy": 5.4904931545257565,
|
|
"epoch": 1.1853335926862478,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004863071263043608,
|
|
"loss": 5.0764,
|
|
"mean_token_accuracy": 0.18565648496150972,
|
|
"num_tokens": 26435603.0,
|
|
"step": 15235
|
|
},
|
|
{
|
|
"entropy": 5.609816455841065,
|
|
"epoch": 1.1857226220579653,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004862976036472823,
|
|
"loss": 5.1902,
|
|
"mean_token_accuracy": 0.18635938614606856,
|
|
"num_tokens": 26444230.0,
|
|
"step": 15240
|
|
},
|
|
{
|
|
"entropy": 5.592506742477417,
|
|
"epoch": 1.186111651429683,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00048628807778409907,
|
|
"loss": 5.0532,
|
|
"mean_token_accuracy": 0.18922004848718643,
|
|
"num_tokens": 26452779.0,
|
|
"step": 15245
|
|
},
|
|
{
|
|
"entropy": 5.605657768249512,
|
|
"epoch": 1.1865006808014005,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004862785487149555,
|
|
"loss": 5.2057,
|
|
"mean_token_accuracy": 0.18610675036907195,
|
|
"num_tokens": 26461977.0,
|
|
"step": 15250
|
|
},
|
|
{
|
|
"entropy": 5.576980113983154,
|
|
"epoch": 1.186889710173118,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004862690164399963,
|
|
"loss": 5.0114,
|
|
"mean_token_accuracy": 0.19747587144374848,
|
|
"num_tokens": 26470182.0,
|
|
"step": 15255
|
|
},
|
|
{
|
|
"entropy": 5.629970455169678,
|
|
"epoch": 1.1872787395448356,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00048625948095936593,
|
|
"loss": 5.2197,
|
|
"mean_token_accuracy": 0.18533240109682084,
|
|
"num_tokens": 26479445.0,
|
|
"step": 15260
|
|
},
|
|
{
|
|
"entropy": 5.594922065734863,
|
|
"epoch": 1.1876677689165531,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00048624994227320923,
|
|
"loss": 5.0857,
|
|
"mean_token_accuracy": 0.19384056627750396,
|
|
"num_tokens": 26488085.0,
|
|
"step": 15265
|
|
},
|
|
{
|
|
"entropy": 5.6941886901855465,
|
|
"epoch": 1.1880567982882708,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00048624040038167094,
|
|
"loss": 5.2301,
|
|
"mean_token_accuracy": 0.18443275094032288,
|
|
"num_tokens": 26496849.0,
|
|
"step": 15270
|
|
},
|
|
{
|
|
"entropy": 5.56822657585144,
|
|
"epoch": 1.1884458276599883,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00048623085528489584,
|
|
"loss": 5.0957,
|
|
"mean_token_accuracy": 0.19489249885082244,
|
|
"num_tokens": 26505412.0,
|
|
"step": 15275
|
|
},
|
|
{
|
|
"entropy": 5.5129741668701175,
|
|
"epoch": 1.188834857031706,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00048622130698302863,
|
|
"loss": 5.0667,
|
|
"mean_token_accuracy": 0.1912377417087555,
|
|
"num_tokens": 26513564.0,
|
|
"step": 15280
|
|
},
|
|
{
|
|
"entropy": 5.533912181854248,
|
|
"epoch": 1.1892238864034235,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00048621175547621426,
|
|
"loss": 5.0909,
|
|
"mean_token_accuracy": 0.18857007175683976,
|
|
"num_tokens": 26522230.0,
|
|
"step": 15285
|
|
},
|
|
{
|
|
"entropy": 5.56089072227478,
|
|
"epoch": 1.189612915775141,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004862022007645978,
|
|
"loss": 5.0803,
|
|
"mean_token_accuracy": 0.19006049931049346,
|
|
"num_tokens": 26531719.0,
|
|
"step": 15290
|
|
},
|
|
{
|
|
"entropy": 5.511069583892822,
|
|
"epoch": 1.1900019451468586,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00048619264284832403,
|
|
"loss": 5.0378,
|
|
"mean_token_accuracy": 0.20560531914234162,
|
|
"num_tokens": 26540352.0,
|
|
"step": 15295
|
|
},
|
|
{
|
|
"entropy": 5.583624649047851,
|
|
"epoch": 1.1903909745185761,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00048618308172753804,
|
|
"loss": 5.0254,
|
|
"mean_token_accuracy": 0.1968090355396271,
|
|
"num_tokens": 26548252.0,
|
|
"step": 15300
|
|
},
|
|
{
|
|
"entropy": 5.596045255661011,
|
|
"epoch": 1.1907800038902936,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004861735174023849,
|
|
"loss": 5.0925,
|
|
"mean_token_accuracy": 0.1928489938378334,
|
|
"num_tokens": 26557267.0,
|
|
"step": 15305
|
|
},
|
|
{
|
|
"entropy": 5.607676887512207,
|
|
"epoch": 1.1911690332620113,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00048616394987300985,
|
|
"loss": 5.2073,
|
|
"mean_token_accuracy": 0.18672688454389572,
|
|
"num_tokens": 26566221.0,
|
|
"step": 15310
|
|
},
|
|
{
|
|
"entropy": 5.597143888473511,
|
|
"epoch": 1.1915580626337288,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004861543791395579,
|
|
"loss": 5.2152,
|
|
"mean_token_accuracy": 0.18726943284273148,
|
|
"num_tokens": 26574826.0,
|
|
"step": 15315
|
|
},
|
|
{
|
|
"entropy": 5.59898796081543,
|
|
"epoch": 1.1919470920054465,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004861448052021743,
|
|
"loss": 5.1869,
|
|
"mean_token_accuracy": 0.179260778427124,
|
|
"num_tokens": 26583442.0,
|
|
"step": 15320
|
|
},
|
|
{
|
|
"entropy": 5.639116430282593,
|
|
"epoch": 1.192336121377164,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004861352280610044,
|
|
"loss": 5.127,
|
|
"mean_token_accuracy": 0.19415039718151092,
|
|
"num_tokens": 26592106.0,
|
|
"step": 15325
|
|
},
|
|
{
|
|
"entropy": 5.587483024597168,
|
|
"epoch": 1.1927251507488816,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00048612564771619346,
|
|
"loss": 5.0137,
|
|
"mean_token_accuracy": 0.19882869422435762,
|
|
"num_tokens": 26601275.0,
|
|
"step": 15330
|
|
},
|
|
{
|
|
"entropy": 5.475168609619141,
|
|
"epoch": 1.193114180120599,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00048611606416788686,
|
|
"loss": 4.9694,
|
|
"mean_token_accuracy": 0.19517303258180618,
|
|
"num_tokens": 26610179.0,
|
|
"step": 15335
|
|
},
|
|
{
|
|
"entropy": 5.545497083663941,
|
|
"epoch": 1.1935032094923166,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00048610647741622996,
|
|
"loss": 5.1411,
|
|
"mean_token_accuracy": 0.18698107302188874,
|
|
"num_tokens": 26619463.0,
|
|
"step": 15340
|
|
},
|
|
{
|
|
"entropy": 5.551906251907349,
|
|
"epoch": 1.1938922388640343,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004860968874613683,
|
|
"loss": 4.985,
|
|
"mean_token_accuracy": 0.20008267164230348,
|
|
"num_tokens": 26627597.0,
|
|
"step": 15345
|
|
},
|
|
{
|
|
"entropy": 5.566534519195557,
|
|
"epoch": 1.1942812682357518,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004860872943034474,
|
|
"loss": 5.0884,
|
|
"mean_token_accuracy": 0.19655673056840897,
|
|
"num_tokens": 26636180.0,
|
|
"step": 15350
|
|
},
|
|
{
|
|
"entropy": 5.571224308013916,
|
|
"epoch": 1.1946702976074695,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004860776979426128,
|
|
"loss": 5.0286,
|
|
"mean_token_accuracy": 0.19708898961544036,
|
|
"num_tokens": 26644803.0,
|
|
"step": 15355
|
|
},
|
|
{
|
|
"entropy": 5.5151488304138185,
|
|
"epoch": 1.195059326979187,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004860680983790101,
|
|
"loss": 5.0747,
|
|
"mean_token_accuracy": 0.18061135560274125,
|
|
"num_tokens": 26653619.0,
|
|
"step": 15360
|
|
},
|
|
{
|
|
"entropy": 5.598951387405395,
|
|
"epoch": 1.1954483563509044,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004860584956127849,
|
|
"loss": 5.0944,
|
|
"mean_token_accuracy": 0.1840843752026558,
|
|
"num_tokens": 26662291.0,
|
|
"step": 15365
|
|
},
|
|
{
|
|
"entropy": 5.610071134567261,
|
|
"epoch": 1.195837385722622,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00048604888964408306,
|
|
"loss": 5.0501,
|
|
"mean_token_accuracy": 0.20193059146404266,
|
|
"num_tokens": 26670592.0,
|
|
"step": 15370
|
|
},
|
|
{
|
|
"entropy": 5.564420509338379,
|
|
"epoch": 1.1962264150943396,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004860392804730502,
|
|
"loss": 5.1194,
|
|
"mean_token_accuracy": 0.19373519122600555,
|
|
"num_tokens": 26679816.0,
|
|
"step": 15375
|
|
},
|
|
{
|
|
"entropy": 5.608189535140991,
|
|
"epoch": 1.1966154444660573,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00048602966809983204,
|
|
"loss": 5.0841,
|
|
"mean_token_accuracy": 0.1990629717707634,
|
|
"num_tokens": 26688185.0,
|
|
"step": 15380
|
|
},
|
|
{
|
|
"entropy": 5.628693962097168,
|
|
"epoch": 1.1970044738377748,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004860200525245746,
|
|
"loss": 5.1441,
|
|
"mean_token_accuracy": 0.19673731327056884,
|
|
"num_tokens": 26697157.0,
|
|
"step": 15385
|
|
},
|
|
{
|
|
"entropy": 5.575571823120117,
|
|
"epoch": 1.1973935032094922,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004860104337474239,
|
|
"loss": 5.09,
|
|
"mean_token_accuracy": 0.18258867263793946,
|
|
"num_tokens": 26705868.0,
|
|
"step": 15390
|
|
},
|
|
{
|
|
"entropy": 5.5600487232208256,
|
|
"epoch": 1.19778253258121,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00048600081176852555,
|
|
"loss": 5.1417,
|
|
"mean_token_accuracy": 0.18435254096984863,
|
|
"num_tokens": 26714364.0,
|
|
"step": 15395
|
|
},
|
|
{
|
|
"entropy": 5.573964262008667,
|
|
"epoch": 1.1981715619529274,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00048599118658802575,
|
|
"loss": 5.1365,
|
|
"mean_token_accuracy": 0.18718570321798325,
|
|
"num_tokens": 26722866.0,
|
|
"step": 15400
|
|
},
|
|
{
|
|
"entropy": 5.631946086883545,
|
|
"epoch": 1.198560591324645,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004859815582060706,
|
|
"loss": 5.0898,
|
|
"mean_token_accuracy": 0.1913563922047615,
|
|
"num_tokens": 26731305.0,
|
|
"step": 15405
|
|
},
|
|
{
|
|
"entropy": 5.62173490524292,
|
|
"epoch": 1.1989496206963626,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004859719266228061,
|
|
"loss": 5.0882,
|
|
"mean_token_accuracy": 0.19028402119874954,
|
|
"num_tokens": 26740807.0,
|
|
"step": 15410
|
|
},
|
|
{
|
|
"entropy": 5.558030414581299,
|
|
"epoch": 1.19933865006808,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004859622918383784,
|
|
"loss": 5.0828,
|
|
"mean_token_accuracy": 0.19723034054040908,
|
|
"num_tokens": 26749748.0,
|
|
"step": 15415
|
|
},
|
|
{
|
|
"entropy": 5.599880599975586,
|
|
"epoch": 1.1997276794397977,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004859526538529337,
|
|
"loss": 5.1279,
|
|
"mean_token_accuracy": 0.19151920974254608,
|
|
"num_tokens": 26758597.0,
|
|
"step": 15420
|
|
},
|
|
{
|
|
"entropy": 5.590807342529297,
|
|
"epoch": 1.2001167088115152,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004859430126666182,
|
|
"loss": 5.1801,
|
|
"mean_token_accuracy": 0.1843524843454361,
|
|
"num_tokens": 26766772.0,
|
|
"step": 15425
|
|
},
|
|
{
|
|
"entropy": 5.476952457427979,
|
|
"epoch": 1.200505738183233,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00048593336827957824,
|
|
"loss": 4.9198,
|
|
"mean_token_accuracy": 0.2183031901717186,
|
|
"num_tokens": 26775229.0,
|
|
"step": 15430
|
|
},
|
|
{
|
|
"entropy": 5.520895195007324,
|
|
"epoch": 1.2008947675549504,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00048592372069196024,
|
|
"loss": 5.0846,
|
|
"mean_token_accuracy": 0.18325729370117189,
|
|
"num_tokens": 26784188.0,
|
|
"step": 15435
|
|
},
|
|
{
|
|
"entropy": 5.460034704208374,
|
|
"epoch": 1.2012837969266679,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004859140699039104,
|
|
"loss": 5.0273,
|
|
"mean_token_accuracy": 0.19336565285921098,
|
|
"num_tokens": 26792687.0,
|
|
"step": 15440
|
|
},
|
|
{
|
|
"entropy": 5.5107306957244875,
|
|
"epoch": 1.2016728262983856,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00048590441591557526,
|
|
"loss": 5.0786,
|
|
"mean_token_accuracy": 0.19534944593906403,
|
|
"num_tokens": 26801931.0,
|
|
"step": 15445
|
|
},
|
|
{
|
|
"entropy": 5.600342416763306,
|
|
"epoch": 1.202061855670103,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00048589475872710134,
|
|
"loss": 5.2971,
|
|
"mean_token_accuracy": 0.182644072920084,
|
|
"num_tokens": 26810689.0,
|
|
"step": 15450
|
|
},
|
|
{
|
|
"entropy": 5.60272331237793,
|
|
"epoch": 1.2024508850418207,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004858850983386351,
|
|
"loss": 5.111,
|
|
"mean_token_accuracy": 0.18917934447526932,
|
|
"num_tokens": 26819038.0,
|
|
"step": 15455
|
|
},
|
|
{
|
|
"entropy": 5.579953956604004,
|
|
"epoch": 1.2028399144135382,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004858754347503231,
|
|
"loss": 5.0171,
|
|
"mean_token_accuracy": 0.20105472803115845,
|
|
"num_tokens": 26827443.0,
|
|
"step": 15460
|
|
},
|
|
{
|
|
"entropy": 5.565564441680908,
|
|
"epoch": 1.203228943785256,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00048586576796231216,
|
|
"loss": 5.0161,
|
|
"mean_token_accuracy": 0.19953968226909638,
|
|
"num_tokens": 26836306.0,
|
|
"step": 15465
|
|
},
|
|
{
|
|
"entropy": 5.584036779403687,
|
|
"epoch": 1.2036179731569734,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004858560979747487,
|
|
"loss": 5.1187,
|
|
"mean_token_accuracy": 0.19076377153396606,
|
|
"num_tokens": 26845043.0,
|
|
"step": 15470
|
|
},
|
|
{
|
|
"entropy": 5.587303256988525,
|
|
"epoch": 1.2040070025286909,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00048584642478777967,
|
|
"loss": 5.0504,
|
|
"mean_token_accuracy": 0.19465643614530564,
|
|
"num_tokens": 26853978.0,
|
|
"step": 15475
|
|
},
|
|
{
|
|
"entropy": 5.553425025939942,
|
|
"epoch": 1.2043960319004086,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004858367484015517,
|
|
"loss": 4.9753,
|
|
"mean_token_accuracy": 0.1934100016951561,
|
|
"num_tokens": 26862487.0,
|
|
"step": 15480
|
|
},
|
|
{
|
|
"entropy": 5.534739875793457,
|
|
"epoch": 1.204785061272126,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00048582706881621166,
|
|
"loss": 5.1476,
|
|
"mean_token_accuracy": 0.190867018699646,
|
|
"num_tokens": 26871137.0,
|
|
"step": 15485
|
|
},
|
|
{
|
|
"entropy": 5.539325904846192,
|
|
"epoch": 1.2051740906438435,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004858173860319063,
|
|
"loss": 5.0504,
|
|
"mean_token_accuracy": 0.19186416566371917,
|
|
"num_tokens": 26880091.0,
|
|
"step": 15490
|
|
},
|
|
{
|
|
"entropy": 5.566355228424072,
|
|
"epoch": 1.2055631200155612,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00048580770004878277,
|
|
"loss": 5.0923,
|
|
"mean_token_accuracy": 0.19103320837020873,
|
|
"num_tokens": 26888777.0,
|
|
"step": 15495
|
|
},
|
|
{
|
|
"entropy": 5.552337503433227,
|
|
"epoch": 1.2059521493872787,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004857980108669879,
|
|
"loss": 5.049,
|
|
"mean_token_accuracy": 0.19066378921270372,
|
|
"num_tokens": 26897689.0,
|
|
"step": 15500
|
|
},
|
|
{
|
|
"entropy": 5.637480401992798,
|
|
"epoch": 1.2063411787589964,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00048578831848666875,
|
|
"loss": 5.0968,
|
|
"mean_token_accuracy": 0.18980053514242173,
|
|
"num_tokens": 26906209.0,
|
|
"step": 15505
|
|
},
|
|
{
|
|
"entropy": 5.627501392364502,
|
|
"epoch": 1.2067302081307139,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00048577862290797235,
|
|
"loss": 5.242,
|
|
"mean_token_accuracy": 0.18738613426685333,
|
|
"num_tokens": 26916340.0,
|
|
"step": 15510
|
|
},
|
|
{
|
|
"entropy": 5.617512178421021,
|
|
"epoch": 1.2071192375024316,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00048576892413104586,
|
|
"loss": 5.1177,
|
|
"mean_token_accuracy": 0.19289989918470382,
|
|
"num_tokens": 26924482.0,
|
|
"step": 15515
|
|
},
|
|
{
|
|
"entropy": 5.549185800552368,
|
|
"epoch": 1.207508266874149,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004857592221560364,
|
|
"loss": 5.0774,
|
|
"mean_token_accuracy": 0.18911547362804412,
|
|
"num_tokens": 26932844.0,
|
|
"step": 15520
|
|
},
|
|
{
|
|
"entropy": 5.451512193679809,
|
|
"epoch": 1.2078972962458665,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004857495169830912,
|
|
"loss": 4.9645,
|
|
"mean_token_accuracy": 0.1984395354986191,
|
|
"num_tokens": 26940916.0,
|
|
"step": 15525
|
|
},
|
|
{
|
|
"entropy": 5.590522146224975,
|
|
"epoch": 1.2082863256175842,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004857398086123575,
|
|
"loss": 5.1085,
|
|
"mean_token_accuracy": 0.19080109745264054,
|
|
"num_tokens": 26949182.0,
|
|
"step": 15530
|
|
},
|
|
{
|
|
"entropy": 5.591371726989746,
|
|
"epoch": 1.2086753549893017,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004857300970439827,
|
|
"loss": 5.0546,
|
|
"mean_token_accuracy": 0.19957173317670823,
|
|
"num_tokens": 26957531.0,
|
|
"step": 15535
|
|
},
|
|
{
|
|
"entropy": 5.589437866210938,
|
|
"epoch": 1.2090643843610192,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00048572038227811404,
|
|
"loss": 5.1522,
|
|
"mean_token_accuracy": 0.19046340137720108,
|
|
"num_tokens": 26965430.0,
|
|
"step": 15540
|
|
},
|
|
{
|
|
"entropy": 5.615444135665894,
|
|
"epoch": 1.2094534137327368,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000485710664314899,
|
|
"loss": 5.1805,
|
|
"mean_token_accuracy": 0.1888631597161293,
|
|
"num_tokens": 26974132.0,
|
|
"step": 15545
|
|
},
|
|
{
|
|
"entropy": 5.57098274230957,
|
|
"epoch": 1.2098424431044543,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000485700943154485,
|
|
"loss": 5.0712,
|
|
"mean_token_accuracy": 0.1968693792819977,
|
|
"num_tokens": 26982277.0,
|
|
"step": 15550
|
|
},
|
|
{
|
|
"entropy": 5.4820122718811035,
|
|
"epoch": 1.210231472476172,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004856912187970195,
|
|
"loss": 5.0301,
|
|
"mean_token_accuracy": 0.1910757064819336,
|
|
"num_tokens": 26991827.0,
|
|
"step": 15555
|
|
},
|
|
{
|
|
"entropy": 5.625962591171264,
|
|
"epoch": 1.2106205018478895,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004856814912426502,
|
|
"loss": 5.1834,
|
|
"mean_token_accuracy": 0.18780433088541032,
|
|
"num_tokens": 27000697.0,
|
|
"step": 15560
|
|
},
|
|
{
|
|
"entropy": 5.576309251785278,
|
|
"epoch": 1.2110095312196072,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004856717604915245,
|
|
"loss": 5.1232,
|
|
"mean_token_accuracy": 0.19405819326639176,
|
|
"num_tokens": 27009461.0,
|
|
"step": 15565
|
|
},
|
|
{
|
|
"entropy": 5.516828155517578,
|
|
"epoch": 1.2113985605913247,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004856620265437902,
|
|
"loss": 5.0538,
|
|
"mean_token_accuracy": 0.19772937297821044,
|
|
"num_tokens": 27017970.0,
|
|
"step": 15570
|
|
},
|
|
{
|
|
"entropy": 5.588766288757324,
|
|
"epoch": 1.2117875899630421,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000485652289399595,
|
|
"loss": 5.1133,
|
|
"mean_token_accuracy": 0.19586780816316604,
|
|
"num_tokens": 27026439.0,
|
|
"step": 15575
|
|
},
|
|
{
|
|
"entropy": 5.580862903594971,
|
|
"epoch": 1.2121766193347598,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00048564254905908655,
|
|
"loss": 5.0592,
|
|
"mean_token_accuracy": 0.19007128924131395,
|
|
"num_tokens": 27034985.0,
|
|
"step": 15580
|
|
},
|
|
{
|
|
"entropy": 5.638749790191651,
|
|
"epoch": 1.2125656487064773,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00048563280552241266,
|
|
"loss": 5.2045,
|
|
"mean_token_accuracy": 0.18281891345977783,
|
|
"num_tokens": 27044171.0,
|
|
"step": 15585
|
|
},
|
|
{
|
|
"entropy": 5.635423803329468,
|
|
"epoch": 1.2129546780781948,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004856230587897212,
|
|
"loss": 5.1648,
|
|
"mean_token_accuracy": 0.18812349885702134,
|
|
"num_tokens": 27053219.0,
|
|
"step": 15590
|
|
},
|
|
{
|
|
"entropy": 5.518210744857788,
|
|
"epoch": 1.2133437074499125,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004856133088611602,
|
|
"loss": 5.0267,
|
|
"mean_token_accuracy": 0.20125340521335602,
|
|
"num_tokens": 27062012.0,
|
|
"step": 15595
|
|
},
|
|
{
|
|
"entropy": 5.556315279006958,
|
|
"epoch": 1.21373273682163,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004856035557368773,
|
|
"loss": 5.1216,
|
|
"mean_token_accuracy": 0.18618103116750717,
|
|
"num_tokens": 27070854.0,
|
|
"step": 15600
|
|
},
|
|
{
|
|
"entropy": 5.640985441207886,
|
|
"epoch": 1.2141217661933477,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00048559379941702074,
|
|
"loss": 5.1629,
|
|
"mean_token_accuracy": 0.19010813981294633,
|
|
"num_tokens": 27079295.0,
|
|
"step": 15605
|
|
},
|
|
{
|
|
"entropy": 5.572699546813965,
|
|
"epoch": 1.2145107955650651,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00048558403990173844,
|
|
"loss": 5.0501,
|
|
"mean_token_accuracy": 0.19180653244256973,
|
|
"num_tokens": 27087909.0,
|
|
"step": 15610
|
|
},
|
|
{
|
|
"entropy": 5.512327384948731,
|
|
"epoch": 1.2148998249367828,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00048557427719117855,
|
|
"loss": 5.0837,
|
|
"mean_token_accuracy": 0.1947572946548462,
|
|
"num_tokens": 27096461.0,
|
|
"step": 15615
|
|
},
|
|
{
|
|
"entropy": 5.608134174346924,
|
|
"epoch": 1.2152888543085003,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004855645112854891,
|
|
"loss": 5.214,
|
|
"mean_token_accuracy": 0.18693210631608964,
|
|
"num_tokens": 27104846.0,
|
|
"step": 15620
|
|
},
|
|
{
|
|
"entropy": 5.619349527359009,
|
|
"epoch": 1.2156778836802178,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004855547421848184,
|
|
"loss": 5.0074,
|
|
"mean_token_accuracy": 0.20129285305738448,
|
|
"num_tokens": 27112623.0,
|
|
"step": 15625
|
|
},
|
|
{
|
|
"entropy": 5.5897434711456295,
|
|
"epoch": 1.2160669130519355,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00048554496988931456,
|
|
"loss": 5.0528,
|
|
"mean_token_accuracy": 0.1938340410590172,
|
|
"num_tokens": 27120752.0,
|
|
"step": 15630
|
|
},
|
|
{
|
|
"entropy": 5.640067768096924,
|
|
"epoch": 1.216455942423653,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00048553519439912597,
|
|
"loss": 5.2194,
|
|
"mean_token_accuracy": 0.1824770301580429,
|
|
"num_tokens": 27129583.0,
|
|
"step": 15635
|
|
},
|
|
{
|
|
"entropy": 5.614911413192749,
|
|
"epoch": 1.2168449717953704,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004855254157144009,
|
|
"loss": 5.1265,
|
|
"mean_token_accuracy": 0.19445567578077316,
|
|
"num_tokens": 27137807.0,
|
|
"step": 15640
|
|
},
|
|
{
|
|
"entropy": 5.541811513900757,
|
|
"epoch": 1.2172340011670881,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004855156338352877,
|
|
"loss": 4.9878,
|
|
"mean_token_accuracy": 0.19631571918725968,
|
|
"num_tokens": 27146246.0,
|
|
"step": 15645
|
|
},
|
|
{
|
|
"entropy": 5.572632741928101,
|
|
"epoch": 1.2176230305388056,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00048550584876193493,
|
|
"loss": 5.0661,
|
|
"mean_token_accuracy": 0.19595494270324706,
|
|
"num_tokens": 27154811.0,
|
|
"step": 15650
|
|
},
|
|
{
|
|
"entropy": 5.608317852020264,
|
|
"epoch": 1.2180120599105233,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00048549606049449085,
|
|
"loss": 5.0746,
|
|
"mean_token_accuracy": 0.20396005660295485,
|
|
"num_tokens": 27162849.0,
|
|
"step": 15655
|
|
},
|
|
{
|
|
"entropy": 5.552761554718018,
|
|
"epoch": 1.2184010892822408,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004854862690331041,
|
|
"loss": 5.1461,
|
|
"mean_token_accuracy": 0.18890870958566666,
|
|
"num_tokens": 27171268.0,
|
|
"step": 15660
|
|
},
|
|
{
|
|
"entropy": 5.582083988189697,
|
|
"epoch": 1.2187901186539585,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00048547647437792327,
|
|
"loss": 5.0932,
|
|
"mean_token_accuracy": 0.19241475462913513,
|
|
"num_tokens": 27179571.0,
|
|
"step": 15665
|
|
},
|
|
{
|
|
"entropy": 5.561008262634277,
|
|
"epoch": 1.219179148025676,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000485466676529097,
|
|
"loss": 5.0763,
|
|
"mean_token_accuracy": 0.1964916095137596,
|
|
"num_tokens": 27188441.0,
|
|
"step": 15670
|
|
},
|
|
{
|
|
"entropy": 5.629905891418457,
|
|
"epoch": 1.2195681773973934,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00048545687548677373,
|
|
"loss": 5.0965,
|
|
"mean_token_accuracy": 0.18833362311124802,
|
|
"num_tokens": 27196960.0,
|
|
"step": 15675
|
|
},
|
|
{
|
|
"entropy": 5.569472551345825,
|
|
"epoch": 1.2199572067691111,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004854470712511025,
|
|
"loss": 5.0958,
|
|
"mean_token_accuracy": 0.194248528778553,
|
|
"num_tokens": 27205129.0,
|
|
"step": 15680
|
|
},
|
|
{
|
|
"entropy": 5.5625584602355955,
|
|
"epoch": 1.2203462361408286,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00048543726382223193,
|
|
"loss": 5.0546,
|
|
"mean_token_accuracy": 0.19435477405786514,
|
|
"num_tokens": 27214213.0,
|
|
"step": 15685
|
|
},
|
|
{
|
|
"entropy": 5.556509065628052,
|
|
"epoch": 1.220735265512546,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00048542745320031075,
|
|
"loss": 5.1004,
|
|
"mean_token_accuracy": 0.18486985117197036,
|
|
"num_tokens": 27222447.0,
|
|
"step": 15690
|
|
},
|
|
{
|
|
"entropy": 5.584448385238647,
|
|
"epoch": 1.2211242948842638,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00048541763938548795,
|
|
"loss": 5.0802,
|
|
"mean_token_accuracy": 0.19131069481372834,
|
|
"num_tokens": 27230872.0,
|
|
"step": 15695
|
|
},
|
|
{
|
|
"entropy": 5.589754295349121,
|
|
"epoch": 1.2215133242559812,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00048540782237791244,
|
|
"loss": 5.1528,
|
|
"mean_token_accuracy": 0.18907450288534164,
|
|
"num_tokens": 27239171.0,
|
|
"step": 15700
|
|
},
|
|
{
|
|
"entropy": 5.532102870941162,
|
|
"epoch": 1.221902353627699,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00048539800217773293,
|
|
"loss": 5.0568,
|
|
"mean_token_accuracy": 0.18893016129732132,
|
|
"num_tokens": 27247530.0,
|
|
"step": 15705
|
|
},
|
|
{
|
|
"entropy": 5.595793914794922,
|
|
"epoch": 1.2222913829994164,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004853881787850988,
|
|
"loss": 5.1411,
|
|
"mean_token_accuracy": 0.18888894766569136,
|
|
"num_tokens": 27255579.0,
|
|
"step": 15710
|
|
},
|
|
{
|
|
"entropy": 5.534402656555176,
|
|
"epoch": 1.2226804123711341,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00048537835220015886,
|
|
"loss": 5.0785,
|
|
"mean_token_accuracy": 0.19326250106096268,
|
|
"num_tokens": 27264209.0,
|
|
"step": 15715
|
|
},
|
|
{
|
|
"entropy": 5.625450134277344,
|
|
"epoch": 1.2230694417428516,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004853685224230623,
|
|
"loss": 5.1456,
|
|
"mean_token_accuracy": 0.18266841471195222,
|
|
"num_tokens": 27272424.0,
|
|
"step": 15720
|
|
},
|
|
{
|
|
"entropy": 5.530358362197876,
|
|
"epoch": 1.223458471114569,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00048535868945395825,
|
|
"loss": 4.9674,
|
|
"mean_token_accuracy": 0.201402847468853,
|
|
"num_tokens": 27281265.0,
|
|
"step": 15725
|
|
},
|
|
{
|
|
"entropy": 5.625441598892212,
|
|
"epoch": 1.2238475004862868,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00048534885329299586,
|
|
"loss": 5.2232,
|
|
"mean_token_accuracy": 0.19027862846851348,
|
|
"num_tokens": 27290026.0,
|
|
"step": 15730
|
|
},
|
|
{
|
|
"entropy": 5.608558654785156,
|
|
"epoch": 1.2242365298580042,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004853390139403245,
|
|
"loss": 5.1688,
|
|
"mean_token_accuracy": 0.18795347958803177,
|
|
"num_tokens": 27298597.0,
|
|
"step": 15735
|
|
},
|
|
{
|
|
"entropy": 5.633943796157837,
|
|
"epoch": 1.224625559229722,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00048532917139609334,
|
|
"loss": 5.1335,
|
|
"mean_token_accuracy": 0.18765166252851487,
|
|
"num_tokens": 27306763.0,
|
|
"step": 15740
|
|
},
|
|
{
|
|
"entropy": 5.580550622940064,
|
|
"epoch": 1.2250145886014394,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004853193256604518,
|
|
"loss": 5.1385,
|
|
"mean_token_accuracy": 0.18764326423406602,
|
|
"num_tokens": 27315782.0,
|
|
"step": 15745
|
|
},
|
|
{
|
|
"entropy": 5.681466007232666,
|
|
"epoch": 1.2254036179731569,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00048530947673354924,
|
|
"loss": 5.1861,
|
|
"mean_token_accuracy": 0.18378168642520903,
|
|
"num_tokens": 27324487.0,
|
|
"step": 15750
|
|
},
|
|
{
|
|
"entropy": 5.61579475402832,
|
|
"epoch": 1.2257926473448746,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004852996246155351,
|
|
"loss": 5.1106,
|
|
"mean_token_accuracy": 0.18874807208776473,
|
|
"num_tokens": 27333099.0,
|
|
"step": 15755
|
|
},
|
|
{
|
|
"entropy": 5.582251024246216,
|
|
"epoch": 1.226181676716592,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00048528976930655896,
|
|
"loss": 5.1176,
|
|
"mean_token_accuracy": 0.18901627659797668,
|
|
"num_tokens": 27341697.0,
|
|
"step": 15760
|
|
},
|
|
{
|
|
"entropy": 5.618842029571534,
|
|
"epoch": 1.2265707060883098,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00048527991080677015,
|
|
"loss": 5.0962,
|
|
"mean_token_accuracy": 0.1931592270731926,
|
|
"num_tokens": 27349811.0,
|
|
"step": 15765
|
|
},
|
|
{
|
|
"entropy": 5.562830066680908,
|
|
"epoch": 1.2269597354600272,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00048527004911631843,
|
|
"loss": 5.1045,
|
|
"mean_token_accuracy": 0.19176326990127562,
|
|
"num_tokens": 27358257.0,
|
|
"step": 15770
|
|
},
|
|
{
|
|
"entropy": 5.616780614852905,
|
|
"epoch": 1.2273487648317447,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004852601842353534,
|
|
"loss": 5.07,
|
|
"mean_token_accuracy": 0.19709960520267486,
|
|
"num_tokens": 27366993.0,
|
|
"step": 15775
|
|
},
|
|
{
|
|
"entropy": 5.610050439834595,
|
|
"epoch": 1.2277377942034624,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00048525031616402476,
|
|
"loss": 5.1003,
|
|
"mean_token_accuracy": 0.1969912141561508,
|
|
"num_tokens": 27375780.0,
|
|
"step": 15780
|
|
},
|
|
{
|
|
"entropy": 5.576451301574707,
|
|
"epoch": 1.2281268235751799,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00048524044490248227,
|
|
"loss": 5.1585,
|
|
"mean_token_accuracy": 0.18969890773296355,
|
|
"num_tokens": 27384641.0,
|
|
"step": 15785
|
|
},
|
|
{
|
|
"entropy": 5.638945150375366,
|
|
"epoch": 1.2285158529468976,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00048523057045087557,
|
|
"loss": 5.1405,
|
|
"mean_token_accuracy": 0.19688313007354735,
|
|
"num_tokens": 27392990.0,
|
|
"step": 15790
|
|
},
|
|
{
|
|
"entropy": 5.650594854354859,
|
|
"epoch": 1.228904882318615,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00048522069280935466,
|
|
"loss": 5.285,
|
|
"mean_token_accuracy": 0.18183117657899855,
|
|
"num_tokens": 27401012.0,
|
|
"step": 15795
|
|
},
|
|
{
|
|
"entropy": 5.54598650932312,
|
|
"epoch": 1.2292939116903325,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004852108119780693,
|
|
"loss": 5.0812,
|
|
"mean_token_accuracy": 0.19106172472238542,
|
|
"num_tokens": 27409758.0,
|
|
"step": 15800
|
|
},
|
|
{
|
|
"entropy": 5.614936780929566,
|
|
"epoch": 1.2296829410620502,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004852009279571694,
|
|
"loss": 5.0934,
|
|
"mean_token_accuracy": 0.19357936829328537,
|
|
"num_tokens": 27417592.0,
|
|
"step": 15805
|
|
},
|
|
{
|
|
"entropy": 5.570390510559082,
|
|
"epoch": 1.2300719704337677,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000485191040746805,
|
|
"loss": 5.058,
|
|
"mean_token_accuracy": 0.19234727174043656,
|
|
"num_tokens": 27426822.0,
|
|
"step": 15810
|
|
},
|
|
{
|
|
"entropy": 5.536443281173706,
|
|
"epoch": 1.2304609998054854,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004851811503471262,
|
|
"loss": 5.0443,
|
|
"mean_token_accuracy": 0.20273693054914474,
|
|
"num_tokens": 27435446.0,
|
|
"step": 15815
|
|
},
|
|
{
|
|
"entropy": 5.585339832305908,
|
|
"epoch": 1.2308500291772029,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00048517125675828294,
|
|
"loss": 5.0434,
|
|
"mean_token_accuracy": 0.19286508113145828,
|
|
"num_tokens": 27443156.0,
|
|
"step": 15820
|
|
},
|
|
{
|
|
"entropy": 5.659043884277343,
|
|
"epoch": 1.2312390585489204,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00048516135998042536,
|
|
"loss": 5.1712,
|
|
"mean_token_accuracy": 0.19028818011283874,
|
|
"num_tokens": 27451500.0,
|
|
"step": 15825
|
|
},
|
|
{
|
|
"entropy": 5.6254126071929935,
|
|
"epoch": 1.231628087920638,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004851514600137037,
|
|
"loss": 5.1307,
|
|
"mean_token_accuracy": 0.19801352322101592,
|
|
"num_tokens": 27460237.0,
|
|
"step": 15830
|
|
},
|
|
{
|
|
"entropy": 5.588210487365723,
|
|
"epoch": 1.2320171172923555,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00048514155685826807,
|
|
"loss": 5.0884,
|
|
"mean_token_accuracy": 0.19894171953201295,
|
|
"num_tokens": 27468434.0,
|
|
"step": 15835
|
|
},
|
|
{
|
|
"entropy": 5.6366798877716064,
|
|
"epoch": 1.2324061466640732,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004851316505142688,
|
|
"loss": 5.1157,
|
|
"mean_token_accuracy": 0.19308706521987914,
|
|
"num_tokens": 27477667.0,
|
|
"step": 15840
|
|
},
|
|
{
|
|
"entropy": 5.618930673599243,
|
|
"epoch": 1.2327951760357907,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00048512174098185615,
|
|
"loss": 5.0811,
|
|
"mean_token_accuracy": 0.18397969752550125,
|
|
"num_tokens": 27486365.0,
|
|
"step": 15845
|
|
},
|
|
{
|
|
"entropy": 5.530434226989746,
|
|
"epoch": 1.2331842054075082,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00048511182826118055,
|
|
"loss": 5.0673,
|
|
"mean_token_accuracy": 0.19726494401693345,
|
|
"num_tokens": 27495310.0,
|
|
"step": 15850
|
|
},
|
|
{
|
|
"entropy": 5.4918054103851315,
|
|
"epoch": 1.2335732347792259,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00048510191235239246,
|
|
"loss": 5.0325,
|
|
"mean_token_accuracy": 0.19891120940446855,
|
|
"num_tokens": 27504175.0,
|
|
"step": 15855
|
|
},
|
|
{
|
|
"entropy": 5.657974195480347,
|
|
"epoch": 1.2339622641509433,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00048509199325564217,
|
|
"loss": 5.0955,
|
|
"mean_token_accuracy": 0.18868385255336761,
|
|
"num_tokens": 27512042.0,
|
|
"step": 15860
|
|
},
|
|
{
|
|
"entropy": 5.62535662651062,
|
|
"epoch": 1.234351293522661,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004850820709710803,
|
|
"loss": 5.1832,
|
|
"mean_token_accuracy": 0.19400513917207718,
|
|
"num_tokens": 27520721.0,
|
|
"step": 15865
|
|
},
|
|
{
|
|
"entropy": 5.512140846252441,
|
|
"epoch": 1.2347403228943785,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004850721454988574,
|
|
"loss": 5.0726,
|
|
"mean_token_accuracy": 0.18600696921348572,
|
|
"num_tokens": 27529431.0,
|
|
"step": 15870
|
|
},
|
|
{
|
|
"entropy": 5.520215559005737,
|
|
"epoch": 1.235129352266096,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00048506221683912405,
|
|
"loss": 4.9983,
|
|
"mean_token_accuracy": 0.20258515030145646,
|
|
"num_tokens": 27537380.0,
|
|
"step": 15875
|
|
},
|
|
{
|
|
"entropy": 5.509256362915039,
|
|
"epoch": 1.2355183816378137,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004850522849920309,
|
|
"loss": 5.0145,
|
|
"mean_token_accuracy": 0.1896832525730133,
|
|
"num_tokens": 27547487.0,
|
|
"step": 15880
|
|
},
|
|
{
|
|
"entropy": 5.645970439910888,
|
|
"epoch": 1.2359074110095312,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00048504234995772863,
|
|
"loss": 5.0863,
|
|
"mean_token_accuracy": 0.19388291388750076,
|
|
"num_tokens": 27556813.0,
|
|
"step": 15885
|
|
},
|
|
{
|
|
"entropy": 5.626342058181763,
|
|
"epoch": 1.2362964403812489,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004850324117363681,
|
|
"loss": 5.2079,
|
|
"mean_token_accuracy": 0.18508358299732208,
|
|
"num_tokens": 27566602.0,
|
|
"step": 15890
|
|
},
|
|
{
|
|
"entropy": 5.575374269485474,
|
|
"epoch": 1.2366854697529663,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00048502247032809997,
|
|
"loss": 5.1123,
|
|
"mean_token_accuracy": 0.19680604785680772,
|
|
"num_tokens": 27574577.0,
|
|
"step": 15895
|
|
},
|
|
{
|
|
"entropy": 5.685038471221924,
|
|
"epoch": 1.237074499124684,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004850125257330751,
|
|
"loss": 5.2692,
|
|
"mean_token_accuracy": 0.17783930599689485,
|
|
"num_tokens": 27582702.0,
|
|
"step": 15900
|
|
},
|
|
{
|
|
"entropy": 5.592756843566894,
|
|
"epoch": 1.2374635284964015,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00048500257795144446,
|
|
"loss": 5.1617,
|
|
"mean_token_accuracy": 0.18681564629077912,
|
|
"num_tokens": 27591457.0,
|
|
"step": 15905
|
|
},
|
|
{
|
|
"entropy": 5.553035497665405,
|
|
"epoch": 1.237852557868119,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000484992626983359,
|
|
"loss": 5.0212,
|
|
"mean_token_accuracy": 0.19970177859067917,
|
|
"num_tokens": 27600643.0,
|
|
"step": 15910
|
|
},
|
|
{
|
|
"entropy": 5.587669134140015,
|
|
"epoch": 1.2382415872398367,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004849826728289696,
|
|
"loss": 5.0241,
|
|
"mean_token_accuracy": 0.19343722462654114,
|
|
"num_tokens": 27608438.0,
|
|
"step": 15915
|
|
},
|
|
{
|
|
"entropy": 5.614461994171142,
|
|
"epoch": 1.2386306166115542,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00048497271548842737,
|
|
"loss": 5.1477,
|
|
"mean_token_accuracy": 0.19096991866827012,
|
|
"num_tokens": 27617149.0,
|
|
"step": 15920
|
|
},
|
|
{
|
|
"entropy": 5.523227977752685,
|
|
"epoch": 1.2390196459832716,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004849627549618834,
|
|
"loss": 5.0878,
|
|
"mean_token_accuracy": 0.1934687003493309,
|
|
"num_tokens": 27625188.0,
|
|
"step": 15925
|
|
},
|
|
{
|
|
"entropy": 5.523476934432983,
|
|
"epoch": 1.2394086753549893,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00048495279124948886,
|
|
"loss": 5.1571,
|
|
"mean_token_accuracy": 0.19009485989809036,
|
|
"num_tokens": 27633865.0,
|
|
"step": 15930
|
|
},
|
|
{
|
|
"entropy": 5.57327356338501,
|
|
"epoch": 1.2397977047267068,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004849428243513948,
|
|
"loss": 5.1101,
|
|
"mean_token_accuracy": 0.19219367057085038,
|
|
"num_tokens": 27642528.0,
|
|
"step": 15935
|
|
},
|
|
{
|
|
"entropy": 5.608651161193848,
|
|
"epoch": 1.2401867340984245,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00048493285426775255,
|
|
"loss": 5.1983,
|
|
"mean_token_accuracy": 0.17797445505857468,
|
|
"num_tokens": 27651291.0,
|
|
"step": 15940
|
|
},
|
|
{
|
|
"entropy": 5.641522073745728,
|
|
"epoch": 1.240575763470142,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004849228809987135,
|
|
"loss": 5.194,
|
|
"mean_token_accuracy": 0.1832926467061043,
|
|
"num_tokens": 27660725.0,
|
|
"step": 15945
|
|
},
|
|
{
|
|
"entropy": 5.6311310768127445,
|
|
"epoch": 1.2409647928418597,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004849129045444288,
|
|
"loss": 5.0392,
|
|
"mean_token_accuracy": 0.19656172543764114,
|
|
"num_tokens": 27669282.0,
|
|
"step": 15950
|
|
},
|
|
{
|
|
"entropy": 5.563568258285523,
|
|
"epoch": 1.2413538222135772,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004849029249050498,
|
|
"loss": 5.0433,
|
|
"mean_token_accuracy": 0.2009149357676506,
|
|
"num_tokens": 27677987.0,
|
|
"step": 15955
|
|
},
|
|
{
|
|
"entropy": 5.500935697555542,
|
|
"epoch": 1.2417428515852946,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00048489294208072805,
|
|
"loss": 5.0502,
|
|
"mean_token_accuracy": 0.19451956152915956,
|
|
"num_tokens": 27686409.0,
|
|
"step": 15960
|
|
},
|
|
{
|
|
"entropy": 5.554556941986084,
|
|
"epoch": 1.2421318809570123,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00048488295607161495,
|
|
"loss": 5.0513,
|
|
"mean_token_accuracy": 0.19104095846414565,
|
|
"num_tokens": 27695485.0,
|
|
"step": 15965
|
|
},
|
|
{
|
|
"entropy": 5.547342348098755,
|
|
"epoch": 1.2425209103287298,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004848729668778621,
|
|
"loss": 4.9517,
|
|
"mean_token_accuracy": 0.19947921484708786,
|
|
"num_tokens": 27703962.0,
|
|
"step": 15970
|
|
},
|
|
{
|
|
"entropy": 5.5795379161834715,
|
|
"epoch": 1.2429099397004473,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004848629744996211,
|
|
"loss": 5.0794,
|
|
"mean_token_accuracy": 0.1934753343462944,
|
|
"num_tokens": 27713632.0,
|
|
"step": 15975
|
|
},
|
|
{
|
|
"entropy": 5.557565307617187,
|
|
"epoch": 1.243298969072165,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004848529789370434,
|
|
"loss": 5.1575,
|
|
"mean_token_accuracy": 0.19070208668708802,
|
|
"num_tokens": 27722890.0,
|
|
"step": 15980
|
|
},
|
|
{
|
|
"entropy": 5.58310489654541,
|
|
"epoch": 1.2436879984438824,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004848429801902808,
|
|
"loss": 5.0829,
|
|
"mean_token_accuracy": 0.19657804667949677,
|
|
"num_tokens": 27731325.0,
|
|
"step": 15985
|
|
},
|
|
{
|
|
"entropy": 5.600124549865723,
|
|
"epoch": 1.2440770278156001,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00048483297825948485,
|
|
"loss": 5.163,
|
|
"mean_token_accuracy": 0.18975530713796615,
|
|
"num_tokens": 27739600.0,
|
|
"step": 15990
|
|
},
|
|
{
|
|
"entropy": 5.583254814147949,
|
|
"epoch": 1.2444660571873176,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00048482297314480756,
|
|
"loss": 5.145,
|
|
"mean_token_accuracy": 0.1875674992799759,
|
|
"num_tokens": 27747860.0,
|
|
"step": 15995
|
|
},
|
|
{
|
|
"entropy": 5.552810192108154,
|
|
"epoch": 1.2448550865590353,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004848129648464006,
|
|
"loss": 5.0608,
|
|
"mean_token_accuracy": 0.1939297452569008,
|
|
"num_tokens": 27757141.0,
|
|
"step": 16000
|
|
},
|
|
{
|
|
"entropy": 5.619099903106689,
|
|
"epoch": 1.2452441159307528,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004848029533644159,
|
|
"loss": 5.2286,
|
|
"mean_token_accuracy": 0.1821589231491089,
|
|
"num_tokens": 27766832.0,
|
|
"step": 16005
|
|
},
|
|
{
|
|
"entropy": 5.600907993316651,
|
|
"epoch": 1.2456331453024703,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004847929386990052,
|
|
"loss": 5.0999,
|
|
"mean_token_accuracy": 0.18735098242759704,
|
|
"num_tokens": 27775487.0,
|
|
"step": 16010
|
|
},
|
|
{
|
|
"entropy": 5.578440952301025,
|
|
"epoch": 1.246022174674188,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00048478292085032065,
|
|
"loss": 5.0388,
|
|
"mean_token_accuracy": 0.19397705793380737,
|
|
"num_tokens": 27783601.0,
|
|
"step": 16015
|
|
},
|
|
{
|
|
"entropy": 5.626968955993652,
|
|
"epoch": 1.2464112040459054,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004847728998185142,
|
|
"loss": 5.1514,
|
|
"mean_token_accuracy": 0.18919097930192946,
|
|
"num_tokens": 27792931.0,
|
|
"step": 16020
|
|
},
|
|
{
|
|
"entropy": 5.642937469482422,
|
|
"epoch": 1.246800233417623,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00048476287560373786,
|
|
"loss": 5.1112,
|
|
"mean_token_accuracy": 0.1907007873058319,
|
|
"num_tokens": 27801388.0,
|
|
"step": 16025
|
|
},
|
|
{
|
|
"entropy": 5.5731464385986325,
|
|
"epoch": 1.2471892627893406,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00048475284820614375,
|
|
"loss": 5.0878,
|
|
"mean_token_accuracy": 0.1909249857068062,
|
|
"num_tokens": 27810047.0,
|
|
"step": 16030
|
|
},
|
|
{
|
|
"entropy": 5.588643646240234,
|
|
"epoch": 1.247578292161058,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00048474281762588407,
|
|
"loss": 5.0863,
|
|
"mean_token_accuracy": 0.1944271668791771,
|
|
"num_tokens": 27818800.0,
|
|
"step": 16035
|
|
},
|
|
{
|
|
"entropy": 5.53579363822937,
|
|
"epoch": 1.2479673215327758,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004847327838631109,
|
|
"loss": 5.0497,
|
|
"mean_token_accuracy": 0.19037897288799285,
|
|
"num_tokens": 27827623.0,
|
|
"step": 16040
|
|
},
|
|
{
|
|
"entropy": 5.5154825210571286,
|
|
"epoch": 1.2483563509044933,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004847227469179766,
|
|
"loss": 5.0194,
|
|
"mean_token_accuracy": 0.20358068197965623,
|
|
"num_tokens": 27836491.0,
|
|
"step": 16045
|
|
},
|
|
{
|
|
"entropy": 5.57544322013855,
|
|
"epoch": 1.248745380276211,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004847127067906334,
|
|
"loss": 5.0835,
|
|
"mean_token_accuracy": 0.19623470604419707,
|
|
"num_tokens": 27845563.0,
|
|
"step": 16050
|
|
},
|
|
{
|
|
"entropy": 5.570050191879273,
|
|
"epoch": 1.2491344096479284,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00048470266348123365,
|
|
"loss": 5.0424,
|
|
"mean_token_accuracy": 0.19259732961654663,
|
|
"num_tokens": 27854263.0,
|
|
"step": 16055
|
|
},
|
|
{
|
|
"entropy": 5.595818948745728,
|
|
"epoch": 1.249523439019646,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004846926169899298,
|
|
"loss": 5.0712,
|
|
"mean_token_accuracy": 0.19274725317955016,
|
|
"num_tokens": 27862868.0,
|
|
"step": 16060
|
|
},
|
|
{
|
|
"entropy": 5.605850887298584,
|
|
"epoch": 1.2499124683913636,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00048468256731687426,
|
|
"loss": 5.1862,
|
|
"mean_token_accuracy": 0.18923528492450714,
|
|
"num_tokens": 27872053.0,
|
|
"step": 16065
|
|
},
|
|
{
|
|
"entropy": 5.554771852493286,
|
|
"epoch": 1.250301497763081,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004846725144622194,
|
|
"loss": 4.9908,
|
|
"mean_token_accuracy": 0.20081694722175597,
|
|
"num_tokens": 27880953.0,
|
|
"step": 16070
|
|
},
|
|
{
|
|
"entropy": 5.5996613025665285,
|
|
"epoch": 1.2506905271347986,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000484662458426118,
|
|
"loss": 5.0799,
|
|
"mean_token_accuracy": 0.19625876247882842,
|
|
"num_tokens": 27890102.0,
|
|
"step": 16075
|
|
},
|
|
{
|
|
"entropy": 5.630896520614624,
|
|
"epoch": 1.2510795565065163,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00048465239920872247,
|
|
"loss": 5.17,
|
|
"mean_token_accuracy": 0.1895263284444809,
|
|
"num_tokens": 27899305.0,
|
|
"step": 16080
|
|
},
|
|
{
|
|
"entropy": 5.643464756011963,
|
|
"epoch": 1.2514685858782337,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00048464233681018545,
|
|
"loss": 5.1111,
|
|
"mean_token_accuracy": 0.19226248264312745,
|
|
"num_tokens": 27907476.0,
|
|
"step": 16085
|
|
},
|
|
{
|
|
"entropy": 5.620686769485474,
|
|
"epoch": 1.2518576152499514,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004846322712306596,
|
|
"loss": 5.1852,
|
|
"mean_token_accuracy": 0.1901336207985878,
|
|
"num_tokens": 27915353.0,
|
|
"step": 16090
|
|
},
|
|
{
|
|
"entropy": 5.546068525314331,
|
|
"epoch": 1.252246644621669,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00048462220247029783,
|
|
"loss": 5.1022,
|
|
"mean_token_accuracy": 0.1912755399942398,
|
|
"num_tokens": 27923980.0,
|
|
"step": 16095
|
|
},
|
|
{
|
|
"entropy": 5.583468008041382,
|
|
"epoch": 1.2526356739933866,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00048461213052925265,
|
|
"loss": 5.1839,
|
|
"mean_token_accuracy": 0.18978094011545182,
|
|
"num_tokens": 27932760.0,
|
|
"step": 16100
|
|
},
|
|
{
|
|
"entropy": 5.566206312179565,
|
|
"epoch": 1.253024703365104,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004846020554076771,
|
|
"loss": 5.0548,
|
|
"mean_token_accuracy": 0.1946013256907463,
|
|
"num_tokens": 27941328.0,
|
|
"step": 16105
|
|
},
|
|
{
|
|
"entropy": 5.618392658233643,
|
|
"epoch": 1.2534137327368216,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004845919771057239,
|
|
"loss": 5.2321,
|
|
"mean_token_accuracy": 0.18288879096508026,
|
|
"num_tokens": 27949597.0,
|
|
"step": 16110
|
|
},
|
|
{
|
|
"entropy": 5.626197052001953,
|
|
"epoch": 1.2538027621085392,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004845818956235462,
|
|
"loss": 5.1073,
|
|
"mean_token_accuracy": 0.19146668463945388,
|
|
"num_tokens": 27958798.0,
|
|
"step": 16115
|
|
},
|
|
{
|
|
"entropy": 5.615036678314209,
|
|
"epoch": 1.2541917914802567,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00048457181096129664,
|
|
"loss": 5.0582,
|
|
"mean_token_accuracy": 0.19657903015613556,
|
|
"num_tokens": 27967582.0,
|
|
"step": 16120
|
|
},
|
|
{
|
|
"entropy": 5.565688276290894,
|
|
"epoch": 1.2545808208519742,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004845617231191285,
|
|
"loss": 5.0449,
|
|
"mean_token_accuracy": 0.18856090158224106,
|
|
"num_tokens": 27975959.0,
|
|
"step": 16125
|
|
},
|
|
{
|
|
"entropy": 5.560848379135132,
|
|
"epoch": 1.254969850223692,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004845516320971948,
|
|
"loss": 5.0679,
|
|
"mean_token_accuracy": 0.1995279684662819,
|
|
"num_tokens": 27983980.0,
|
|
"step": 16130
|
|
},
|
|
{
|
|
"entropy": 5.565843915939331,
|
|
"epoch": 1.2553588795954094,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004845415378956486,
|
|
"loss": 4.9683,
|
|
"mean_token_accuracy": 0.1910046696662903,
|
|
"num_tokens": 27992563.0,
|
|
"step": 16135
|
|
},
|
|
{
|
|
"entropy": 5.548493051528931,
|
|
"epoch": 1.255747908967127,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000484531440514643,
|
|
"loss": 4.97,
|
|
"mean_token_accuracy": 0.20675093978643416,
|
|
"num_tokens": 28001457.0,
|
|
"step": 16140
|
|
},
|
|
{
|
|
"entropy": 5.664248275756836,
|
|
"epoch": 1.2561369383388445,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00048452133995433136,
|
|
"loss": 5.1392,
|
|
"mean_token_accuracy": 0.18932852298021316,
|
|
"num_tokens": 28009507.0,
|
|
"step": 16145
|
|
},
|
|
{
|
|
"entropy": 5.508557224273682,
|
|
"epoch": 1.2565259677105622,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004845112362148668,
|
|
"loss": 5.0821,
|
|
"mean_token_accuracy": 0.18782061338424683,
|
|
"num_tokens": 28017858.0,
|
|
"step": 16150
|
|
},
|
|
{
|
|
"entropy": 5.619452667236328,
|
|
"epoch": 1.2569149970822797,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004845011292964028,
|
|
"loss": 5.147,
|
|
"mean_token_accuracy": 0.19194145649671554,
|
|
"num_tokens": 28026832.0,
|
|
"step": 16155
|
|
},
|
|
{
|
|
"entropy": 5.63121919631958,
|
|
"epoch": 1.2573040264539972,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00048449101919909265,
|
|
"loss": 5.0282,
|
|
"mean_token_accuracy": 0.19895150065422057,
|
|
"num_tokens": 28034546.0,
|
|
"step": 16160
|
|
},
|
|
{
|
|
"entropy": 5.547819375991821,
|
|
"epoch": 1.257693055825715,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00048448090592308955,
|
|
"loss": 5.102,
|
|
"mean_token_accuracy": 0.18822899013757705,
|
|
"num_tokens": 28043400.0,
|
|
"step": 16165
|
|
},
|
|
{
|
|
"entropy": 5.516633176803589,
|
|
"epoch": 1.2580820851974324,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004844707894685473,
|
|
"loss": 5.0692,
|
|
"mean_token_accuracy": 0.19954805225133895,
|
|
"num_tokens": 28052764.0,
|
|
"step": 16170
|
|
},
|
|
{
|
|
"entropy": 5.6272422790527346,
|
|
"epoch": 1.2584711145691498,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004844606698356192,
|
|
"loss": 5.148,
|
|
"mean_token_accuracy": 0.1852506160736084,
|
|
"num_tokens": 28061859.0,
|
|
"step": 16175
|
|
},
|
|
{
|
|
"entropy": 5.596032905578613,
|
|
"epoch": 1.2588601439408675,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004844505470244588,
|
|
"loss": 5.0273,
|
|
"mean_token_accuracy": 0.1958564728498459,
|
|
"num_tokens": 28070935.0,
|
|
"step": 16180
|
|
},
|
|
{
|
|
"entropy": 5.6125835418701175,
|
|
"epoch": 1.2592491733125852,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004844404210352197,
|
|
"loss": 5.0962,
|
|
"mean_token_accuracy": 0.18744837492704391,
|
|
"num_tokens": 28079864.0,
|
|
"step": 16185
|
|
},
|
|
{
|
|
"entropy": 5.515648889541626,
|
|
"epoch": 1.2596382026843027,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00048443029186805554,
|
|
"loss": 4.9706,
|
|
"mean_token_accuracy": 0.1960033118724823,
|
|
"num_tokens": 28088938.0,
|
|
"step": 16190
|
|
},
|
|
{
|
|
"entropy": 5.558675241470337,
|
|
"epoch": 1.2600272320560202,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004844201595231201,
|
|
"loss": 5.0844,
|
|
"mean_token_accuracy": 0.19341787099838256,
|
|
"num_tokens": 28097213.0,
|
|
"step": 16195
|
|
},
|
|
{
|
|
"entropy": 5.5612386703491214,
|
|
"epoch": 1.2604162614277379,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00048441002400056706,
|
|
"loss": 5.1093,
|
|
"mean_token_accuracy": 0.19028161615133285,
|
|
"num_tokens": 28105187.0,
|
|
"step": 16200
|
|
},
|
|
{
|
|
"entropy": 5.584390592575073,
|
|
"epoch": 1.2608052907994554,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004843998853005502,
|
|
"loss": 5.0666,
|
|
"mean_token_accuracy": 0.19468899965286254,
|
|
"num_tokens": 28113238.0,
|
|
"step": 16205
|
|
},
|
|
{
|
|
"entropy": 5.540847206115723,
|
|
"epoch": 1.2611943201711728,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004843897434232233,
|
|
"loss": 5.0032,
|
|
"mean_token_accuracy": 0.19913533926010132,
|
|
"num_tokens": 28121502.0,
|
|
"step": 16210
|
|
},
|
|
{
|
|
"entropy": 5.5665552616119385,
|
|
"epoch": 1.2615833495428905,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00048437959836874047,
|
|
"loss": 5.088,
|
|
"mean_token_accuracy": 0.19445707499980927,
|
|
"num_tokens": 28130269.0,
|
|
"step": 16215
|
|
},
|
|
{
|
|
"entropy": 5.601376152038574,
|
|
"epoch": 1.261972378914608,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00048436945013725544,
|
|
"loss": 5.2229,
|
|
"mean_token_accuracy": 0.18307623118162156,
|
|
"num_tokens": 28139482.0,
|
|
"step": 16220
|
|
},
|
|
{
|
|
"entropy": 5.602341842651367,
|
|
"epoch": 1.2623614082863255,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00048435929872892226,
|
|
"loss": 5.175,
|
|
"mean_token_accuracy": 0.19212170094251632,
|
|
"num_tokens": 28148443.0,
|
|
"step": 16225
|
|
},
|
|
{
|
|
"entropy": 5.628897380828858,
|
|
"epoch": 1.2627504376580432,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004843491441438949,
|
|
"loss": 5.031,
|
|
"mean_token_accuracy": 0.19913185238838196,
|
|
"num_tokens": 28156807.0,
|
|
"step": 16230
|
|
},
|
|
{
|
|
"entropy": 5.567248439788818,
|
|
"epoch": 1.2631394670297609,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00048433898638232755,
|
|
"loss": 5.0874,
|
|
"mean_token_accuracy": 0.19673034697771072,
|
|
"num_tokens": 28165019.0,
|
|
"step": 16235
|
|
},
|
|
{
|
|
"entropy": 5.561327791213989,
|
|
"epoch": 1.2635284964014784,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004843288254443742,
|
|
"loss": 5.1295,
|
|
"mean_token_accuracy": 0.1899797186255455,
|
|
"num_tokens": 28173505.0,
|
|
"step": 16240
|
|
},
|
|
{
|
|
"entropy": 5.6576591491699215,
|
|
"epoch": 1.2639175257731958,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004843186613301892,
|
|
"loss": 5.1607,
|
|
"mean_token_accuracy": 0.18639736324548722,
|
|
"num_tokens": 28182524.0,
|
|
"step": 16245
|
|
},
|
|
{
|
|
"entropy": 5.662319087982178,
|
|
"epoch": 1.2643065551449135,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004843084940399266,
|
|
"loss": 5.207,
|
|
"mean_token_accuracy": 0.18318491876125337,
|
|
"num_tokens": 28191093.0,
|
|
"step": 16250
|
|
},
|
|
{
|
|
"entropy": 5.591050243377685,
|
|
"epoch": 1.264695584516631,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004842983235737408,
|
|
"loss": 5.0964,
|
|
"mean_token_accuracy": 0.18838854879140854,
|
|
"num_tokens": 28199092.0,
|
|
"step": 16255
|
|
},
|
|
{
|
|
"entropy": 5.657285737991333,
|
|
"epoch": 1.2650846138883485,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004842881499317861,
|
|
"loss": 5.1784,
|
|
"mean_token_accuracy": 0.1909079894423485,
|
|
"num_tokens": 28207341.0,
|
|
"step": 16260
|
|
},
|
|
{
|
|
"entropy": 5.6056070804595945,
|
|
"epoch": 1.2654736432600662,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004842779731142168,
|
|
"loss": 5.0872,
|
|
"mean_token_accuracy": 0.1917978510260582,
|
|
"num_tokens": 28216370.0,
|
|
"step": 16265
|
|
},
|
|
{
|
|
"entropy": 5.605053567886353,
|
|
"epoch": 1.2658626726317836,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00048426779312118735,
|
|
"loss": 5.1234,
|
|
"mean_token_accuracy": 0.19039810448884964,
|
|
"num_tokens": 28224554.0,
|
|
"step": 16270
|
|
},
|
|
{
|
|
"entropy": 5.663516330718994,
|
|
"epoch": 1.2662517020035013,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004842576099528522,
|
|
"loss": 5.1525,
|
|
"mean_token_accuracy": 0.18665037900209427,
|
|
"num_tokens": 28232672.0,
|
|
"step": 16275
|
|
},
|
|
{
|
|
"entropy": 5.551630687713623,
|
|
"epoch": 1.2666407313752188,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004842474236093659,
|
|
"loss": 4.9758,
|
|
"mean_token_accuracy": 0.19758483916521072,
|
|
"num_tokens": 28240730.0,
|
|
"step": 16280
|
|
},
|
|
{
|
|
"entropy": 5.5807586193084715,
|
|
"epoch": 1.2670297607469365,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00048423723409088306,
|
|
"loss": 5.0974,
|
|
"mean_token_accuracy": 0.1906809017062187,
|
|
"num_tokens": 28248989.0,
|
|
"step": 16285
|
|
},
|
|
{
|
|
"entropy": 5.6339654445648195,
|
|
"epoch": 1.267418790118654,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004842270413975582,
|
|
"loss": 5.177,
|
|
"mean_token_accuracy": 0.1912175014615059,
|
|
"num_tokens": 28256900.0,
|
|
"step": 16290
|
|
},
|
|
{
|
|
"entropy": 5.648556184768677,
|
|
"epoch": 1.2678078194903715,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000484216845529546,
|
|
"loss": 5.1246,
|
|
"mean_token_accuracy": 0.18360855877399446,
|
|
"num_tokens": 28265832.0,
|
|
"step": 16295
|
|
},
|
|
{
|
|
"entropy": 5.56776704788208,
|
|
"epoch": 1.2681968488620892,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00048420664648700113,
|
|
"loss": 5.0134,
|
|
"mean_token_accuracy": 0.19365309178829193,
|
|
"num_tokens": 28274661.0,
|
|
"step": 16300
|
|
},
|
|
{
|
|
"entropy": 5.614473009109497,
|
|
"epoch": 1.2685858782338066,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004841964442700784,
|
|
"loss": 5.0773,
|
|
"mean_token_accuracy": 0.19184325635433197,
|
|
"num_tokens": 28283303.0,
|
|
"step": 16305
|
|
},
|
|
{
|
|
"entropy": 5.57660059928894,
|
|
"epoch": 1.2689749076055241,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00048418623887893264,
|
|
"loss": 4.9794,
|
|
"mean_token_accuracy": 0.19630232751369475,
|
|
"num_tokens": 28291660.0,
|
|
"step": 16310
|
|
},
|
|
{
|
|
"entropy": 5.5983765602111815,
|
|
"epoch": 1.2693639369772418,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00048417603031371867,
|
|
"loss": 5.1414,
|
|
"mean_token_accuracy": 0.18618385791778563,
|
|
"num_tokens": 28301314.0,
|
|
"step": 16315
|
|
},
|
|
{
|
|
"entropy": 5.598386764526367,
|
|
"epoch": 1.2697529663489593,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004841658185745913,
|
|
"loss": 5.0897,
|
|
"mean_token_accuracy": 0.19332052618265153,
|
|
"num_tokens": 28310044.0,
|
|
"step": 16320
|
|
},
|
|
{
|
|
"entropy": 5.720161008834839,
|
|
"epoch": 1.270141995720677,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00048415560366170564,
|
|
"loss": 5.1888,
|
|
"mean_token_accuracy": 0.19506587237119674,
|
|
"num_tokens": 28319773.0,
|
|
"step": 16325
|
|
},
|
|
{
|
|
"entropy": 5.586122369766235,
|
|
"epoch": 1.2705310250923945,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004841453855752165,
|
|
"loss": 4.9882,
|
|
"mean_token_accuracy": 0.19530003964900972,
|
|
"num_tokens": 28328070.0,
|
|
"step": 16330
|
|
},
|
|
{
|
|
"entropy": 5.587516784667969,
|
|
"epoch": 1.2709200544641122,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004841351643152791,
|
|
"loss": 5.0815,
|
|
"mean_token_accuracy": 0.1963294342160225,
|
|
"num_tokens": 28337636.0,
|
|
"step": 16335
|
|
},
|
|
{
|
|
"entropy": 5.4862799644470215,
|
|
"epoch": 1.2713090838358296,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004841249398820485,
|
|
"loss": 5.0875,
|
|
"mean_token_accuracy": 0.19166263937950134,
|
|
"num_tokens": 28346609.0,
|
|
"step": 16340
|
|
},
|
|
{
|
|
"entropy": 5.587266969680786,
|
|
"epoch": 1.271698113207547,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004841147122756797,
|
|
"loss": 5.1128,
|
|
"mean_token_accuracy": 0.19189873486757278,
|
|
"num_tokens": 28355395.0,
|
|
"step": 16345
|
|
},
|
|
{
|
|
"entropy": 5.569062089920044,
|
|
"epoch": 1.2720871425792648,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000484104481496328,
|
|
"loss": 5.1861,
|
|
"mean_token_accuracy": 0.1872741088271141,
|
|
"num_tokens": 28364447.0,
|
|
"step": 16350
|
|
},
|
|
{
|
|
"entropy": 5.62692928314209,
|
|
"epoch": 1.2724761719509823,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004840942475441486,
|
|
"loss": 5.1193,
|
|
"mean_token_accuracy": 0.19126724004745482,
|
|
"num_tokens": 28372872.0,
|
|
"step": 16355
|
|
},
|
|
{
|
|
"entropy": 5.608555316925049,
|
|
"epoch": 1.2728652013226998,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004840840104192969,
|
|
"loss": 4.9748,
|
|
"mean_token_accuracy": 0.19754622876644135,
|
|
"num_tokens": 28380840.0,
|
|
"step": 16360
|
|
},
|
|
{
|
|
"entropy": 5.5594652652740475,
|
|
"epoch": 1.2732542306944175,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.000484073770121928,
|
|
"loss": 5.0421,
|
|
"mean_token_accuracy": 0.19092322736978531,
|
|
"num_tokens": 28390417.0,
|
|
"step": 16365
|
|
},
|
|
{
|
|
"entropy": 5.574447917938232,
|
|
"epoch": 1.273643260066135,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004840635266521975,
|
|
"loss": 5.0974,
|
|
"mean_token_accuracy": 0.18769218474626542,
|
|
"num_tokens": 28400101.0,
|
|
"step": 16370
|
|
},
|
|
{
|
|
"entropy": 5.525232982635498,
|
|
"epoch": 1.2740322894378526,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004840532800102607,
|
|
"loss": 5.0204,
|
|
"mean_token_accuracy": 0.19470336884260178,
|
|
"num_tokens": 28408336.0,
|
|
"step": 16375
|
|
},
|
|
{
|
|
"entropy": 5.551790523529053,
|
|
"epoch": 1.27442131880957,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00048404303019627314,
|
|
"loss": 5.044,
|
|
"mean_token_accuracy": 0.19560120701789857,
|
|
"num_tokens": 28416985.0,
|
|
"step": 16380
|
|
},
|
|
{
|
|
"entropy": 5.593158912658692,
|
|
"epoch": 1.2748103481812878,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00048403277721039036,
|
|
"loss": 5.2012,
|
|
"mean_token_accuracy": 0.18230695575475692,
|
|
"num_tokens": 28425543.0,
|
|
"step": 16385
|
|
},
|
|
{
|
|
"entropy": 5.609423542022705,
|
|
"epoch": 1.2751993775530053,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004840225210527679,
|
|
"loss": 5.135,
|
|
"mean_token_accuracy": 0.187672358751297,
|
|
"num_tokens": 28435151.0,
|
|
"step": 16390
|
|
},
|
|
{
|
|
"entropy": 5.618977832794189,
|
|
"epoch": 1.2755884069247228,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004840122617235613,
|
|
"loss": 5.1311,
|
|
"mean_token_accuracy": 0.18690426051616668,
|
|
"num_tokens": 28444535.0,
|
|
"step": 16395
|
|
},
|
|
{
|
|
"entropy": 5.647767162322998,
|
|
"epoch": 1.2759774362964404,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004840019992229263,
|
|
"loss": 5.0739,
|
|
"mean_token_accuracy": 0.19250009953975677,
|
|
"num_tokens": 28452852.0,
|
|
"step": 16400
|
|
},
|
|
{
|
|
"entropy": 5.61885347366333,
|
|
"epoch": 1.276366465668158,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00048399173355101867,
|
|
"loss": 5.1149,
|
|
"mean_token_accuracy": 0.18428053855895996,
|
|
"num_tokens": 28462573.0,
|
|
"step": 16405
|
|
},
|
|
{
|
|
"entropy": 5.649799156188965,
|
|
"epoch": 1.2767554950398754,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00048398146470799417,
|
|
"loss": 5.1763,
|
|
"mean_token_accuracy": 0.18333609849214555,
|
|
"num_tokens": 28471714.0,
|
|
"step": 16410
|
|
},
|
|
{
|
|
"entropy": 5.566230726242066,
|
|
"epoch": 1.277144524411593,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00048397119269400846,
|
|
"loss": 5.0476,
|
|
"mean_token_accuracy": 0.20105839818716048,
|
|
"num_tokens": 28479989.0,
|
|
"step": 16415
|
|
},
|
|
{
|
|
"entropy": 5.571966981887817,
|
|
"epoch": 1.2775335537833106,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00048396091750921766,
|
|
"loss": 5.0956,
|
|
"mean_token_accuracy": 0.1905428558588028,
|
|
"num_tokens": 28488707.0,
|
|
"step": 16420
|
|
},
|
|
{
|
|
"entropy": 5.672205829620362,
|
|
"epoch": 1.2779225831550283,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004839506391537774,
|
|
"loss": 5.2359,
|
|
"mean_token_accuracy": 0.18538480401039123,
|
|
"num_tokens": 28497228.0,
|
|
"step": 16425
|
|
},
|
|
{
|
|
"entropy": 5.660464096069336,
|
|
"epoch": 1.2783116125267457,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004839403576278438,
|
|
"loss": 5.0881,
|
|
"mean_token_accuracy": 0.1925577163696289,
|
|
"num_tokens": 28505604.0,
|
|
"step": 16430
|
|
},
|
|
{
|
|
"entropy": 5.5633667469024655,
|
|
"epoch": 1.2787006418984634,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004839300729315729,
|
|
"loss": 5.1376,
|
|
"mean_token_accuracy": 0.18924558013677598,
|
|
"num_tokens": 28514798.0,
|
|
"step": 16435
|
|
},
|
|
{
|
|
"entropy": 5.6681187629699705,
|
|
"epoch": 1.279089671270181,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004839197850651206,
|
|
"loss": 5.1366,
|
|
"mean_token_accuracy": 0.1956767573952675,
|
|
"num_tokens": 28523883.0,
|
|
"step": 16440
|
|
},
|
|
{
|
|
"entropy": 5.626384449005127,
|
|
"epoch": 1.2794787006418984,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00048390949402864317,
|
|
"loss": 5.1232,
|
|
"mean_token_accuracy": 0.18650213479995728,
|
|
"num_tokens": 28532290.0,
|
|
"step": 16445
|
|
},
|
|
{
|
|
"entropy": 5.53694715499878,
|
|
"epoch": 1.279867730013616,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00048389919982229666,
|
|
"loss": 5.0439,
|
|
"mean_token_accuracy": 0.19717105180025102,
|
|
"num_tokens": 28540775.0,
|
|
"step": 16450
|
|
},
|
|
{
|
|
"entropy": 5.570633745193481,
|
|
"epoch": 1.2802567593853336,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00048388890244623723,
|
|
"loss": 5.1526,
|
|
"mean_token_accuracy": 0.187069371342659,
|
|
"num_tokens": 28549517.0,
|
|
"step": 16455
|
|
},
|
|
{
|
|
"entropy": 5.612607765197754,
|
|
"epoch": 1.280645788757051,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004838786019006213,
|
|
"loss": 5.1072,
|
|
"mean_token_accuracy": 0.19305062144994736,
|
|
"num_tokens": 28557708.0,
|
|
"step": 16460
|
|
},
|
|
{
|
|
"entropy": 5.638970041275025,
|
|
"epoch": 1.2810348181287687,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00048386829818560493,
|
|
"loss": 5.118,
|
|
"mean_token_accuracy": 0.18778360188007354,
|
|
"num_tokens": 28566912.0,
|
|
"step": 16465
|
|
},
|
|
{
|
|
"entropy": 5.556902313232422,
|
|
"epoch": 1.2814238475004862,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00048385799130134464,
|
|
"loss": 5.1253,
|
|
"mean_token_accuracy": 0.18722086399793625,
|
|
"num_tokens": 28577104.0,
|
|
"step": 16470
|
|
},
|
|
{
|
|
"entropy": 5.558637285232544,
|
|
"epoch": 1.281812876872204,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004838476812479968,
|
|
"loss": 5.1151,
|
|
"mean_token_accuracy": 0.18765891641378402,
|
|
"num_tokens": 28585984.0,
|
|
"step": 16475
|
|
},
|
|
{
|
|
"entropy": 5.636599922180176,
|
|
"epoch": 1.2822019062439214,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00048383736802571774,
|
|
"loss": 5.1455,
|
|
"mean_token_accuracy": 0.18856384754180908,
|
|
"num_tokens": 28594945.0,
|
|
"step": 16480
|
|
},
|
|
{
|
|
"entropy": 5.701941633224488,
|
|
"epoch": 1.282590935615639,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000483827051634664,
|
|
"loss": 5.1687,
|
|
"mean_token_accuracy": 0.186891108751297,
|
|
"num_tokens": 28603546.0,
|
|
"step": 16485
|
|
},
|
|
{
|
|
"entropy": 5.6071686267852785,
|
|
"epoch": 1.2829799649873566,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00048381673207499224,
|
|
"loss": 5.1071,
|
|
"mean_token_accuracy": 0.19561906456947326,
|
|
"num_tokens": 28612057.0,
|
|
"step": 16490
|
|
},
|
|
{
|
|
"entropy": 5.540022325515747,
|
|
"epoch": 1.283368994359074,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004838064093468588,
|
|
"loss": 5.063,
|
|
"mean_token_accuracy": 0.18930589854717256,
|
|
"num_tokens": 28620945.0,
|
|
"step": 16495
|
|
},
|
|
{
|
|
"entropy": 5.525605964660644,
|
|
"epoch": 1.2837580237307917,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004837960834504206,
|
|
"loss": 4.9635,
|
|
"mean_token_accuracy": 0.2052335560321808,
|
|
"num_tokens": 28629028.0,
|
|
"step": 16500
|
|
},
|
|
{
|
|
"entropy": 5.527144479751587,
|
|
"epoch": 1.2841470531025092,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004837857543858341,
|
|
"loss": 5.0221,
|
|
"mean_token_accuracy": 0.19998676031827928,
|
|
"num_tokens": 28637533.0,
|
|
"step": 16505
|
|
},
|
|
{
|
|
"entropy": 5.626755571365356,
|
|
"epoch": 1.2845360824742267,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004837754221532561,
|
|
"loss": 5.1699,
|
|
"mean_token_accuracy": 0.18968948125839233,
|
|
"num_tokens": 28646906.0,
|
|
"step": 16510
|
|
},
|
|
{
|
|
"entropy": 5.558996725082397,
|
|
"epoch": 1.2849251118459444,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00048376508675284334,
|
|
"loss": 5.0473,
|
|
"mean_token_accuracy": 0.199790096282959,
|
|
"num_tokens": 28655597.0,
|
|
"step": 16515
|
|
},
|
|
{
|
|
"entropy": 5.644053602218628,
|
|
"epoch": 1.2853141412176619,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00048375474818475274,
|
|
"loss": 5.1807,
|
|
"mean_token_accuracy": 0.18855624198913573,
|
|
"num_tokens": 28664806.0,
|
|
"step": 16520
|
|
},
|
|
{
|
|
"entropy": 5.5634369373321535,
|
|
"epoch": 1.2857031705893796,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00048374440644914104,
|
|
"loss": 5.0241,
|
|
"mean_token_accuracy": 0.20249858498573303,
|
|
"num_tokens": 28673610.0,
|
|
"step": 16525
|
|
},
|
|
{
|
|
"entropy": 5.611365222930909,
|
|
"epoch": 1.286092199961097,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00048373406154616523,
|
|
"loss": 5.0798,
|
|
"mean_token_accuracy": 0.19193932712078093,
|
|
"num_tokens": 28681726.0,
|
|
"step": 16530
|
|
},
|
|
{
|
|
"entropy": 5.653905534744263,
|
|
"epoch": 1.2864812293328147,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00048372371347598226,
|
|
"loss": 5.2393,
|
|
"mean_token_accuracy": 0.17713529914617537,
|
|
"num_tokens": 28691014.0,
|
|
"step": 16535
|
|
},
|
|
{
|
|
"entropy": 5.632786226272583,
|
|
"epoch": 1.2868702587045322,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00048371336223874923,
|
|
"loss": 5.1223,
|
|
"mean_token_accuracy": 0.18437448889017105,
|
|
"num_tokens": 28699304.0,
|
|
"step": 16540
|
|
},
|
|
{
|
|
"entropy": 5.633014917373657,
|
|
"epoch": 1.2872592880762497,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000483703007834623,
|
|
"loss": 5.0416,
|
|
"mean_token_accuracy": 0.19493970274925232,
|
|
"num_tokens": 28707950.0,
|
|
"step": 16545
|
|
},
|
|
{
|
|
"entropy": 5.540950584411621,
|
|
"epoch": 1.2876483174479674,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004836926502637609,
|
|
"loss": 5.0564,
|
|
"mean_token_accuracy": 0.19928259402513504,
|
|
"num_tokens": 28716678.0,
|
|
"step": 16550
|
|
},
|
|
{
|
|
"entropy": 5.5410106658935545,
|
|
"epoch": 1.2880373468196848,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00048368228952632005,
|
|
"loss": 5.0783,
|
|
"mean_token_accuracy": 0.20132799297571183,
|
|
"num_tokens": 28725658.0,
|
|
"step": 16555
|
|
},
|
|
{
|
|
"entropy": 5.645573425292969,
|
|
"epoch": 1.2884263761914023,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00048367192562245756,
|
|
"loss": 5.1198,
|
|
"mean_token_accuracy": 0.19349722415208817,
|
|
"num_tokens": 28733859.0,
|
|
"step": 16560
|
|
},
|
|
{
|
|
"entropy": 5.52505316734314,
|
|
"epoch": 1.28881540556312,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00048366155855233067,
|
|
"loss": 5.0158,
|
|
"mean_token_accuracy": 0.19758519530296326,
|
|
"num_tokens": 28741941.0,
|
|
"step": 16565
|
|
},
|
|
{
|
|
"entropy": 5.5179039478302006,
|
|
"epoch": 1.2892044349348377,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004836511883160968,
|
|
"loss": 4.9459,
|
|
"mean_token_accuracy": 0.20259023755788802,
|
|
"num_tokens": 28750296.0,
|
|
"step": 16570
|
|
},
|
|
{
|
|
"entropy": 5.4994813919067385,
|
|
"epoch": 1.2895934643065552,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004836408149139133,
|
|
"loss": 4.9406,
|
|
"mean_token_accuracy": 0.2073293909430504,
|
|
"num_tokens": 28758359.0,
|
|
"step": 16575
|
|
},
|
|
{
|
|
"entropy": 5.61463098526001,
|
|
"epoch": 1.2899824936782727,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00048363043834593743,
|
|
"loss": 5.14,
|
|
"mean_token_accuracy": 0.1906037822365761,
|
|
"num_tokens": 28766944.0,
|
|
"step": 16580
|
|
},
|
|
{
|
|
"entropy": 5.593300628662109,
|
|
"epoch": 1.2903715230499904,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004836200586123268,
|
|
"loss": 5.1483,
|
|
"mean_token_accuracy": 0.1891775071620941,
|
|
"num_tokens": 28775897.0,
|
|
"step": 16585
|
|
},
|
|
{
|
|
"entropy": 5.550483894348145,
|
|
"epoch": 1.2907605524217078,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00048360967571323875,
|
|
"loss": 5.0644,
|
|
"mean_token_accuracy": 0.19618291705846785,
|
|
"num_tokens": 28784509.0,
|
|
"step": 16590
|
|
},
|
|
{
|
|
"entropy": 5.515319347381592,
|
|
"epoch": 1.2911495817934253,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00048359928964883094,
|
|
"loss": 4.9466,
|
|
"mean_token_accuracy": 0.20244549214839935,
|
|
"num_tokens": 28793347.0,
|
|
"step": 16595
|
|
},
|
|
{
|
|
"entropy": 5.5574531078338625,
|
|
"epoch": 1.291538611165143,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000483588900419261,
|
|
"loss": 5.0429,
|
|
"mean_token_accuracy": 0.19651865363121032,
|
|
"num_tokens": 28801100.0,
|
|
"step": 16600
|
|
},
|
|
{
|
|
"entropy": 5.504043054580689,
|
|
"epoch": 1.2919276405368605,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004835785080246864,
|
|
"loss": 5.0202,
|
|
"mean_token_accuracy": 0.19907681792974471,
|
|
"num_tokens": 28809508.0,
|
|
"step": 16605
|
|
},
|
|
{
|
|
"entropy": 5.556125164031982,
|
|
"epoch": 1.292316669908578,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000483568112465265,
|
|
"loss": 5.1015,
|
|
"mean_token_accuracy": 0.1911289930343628,
|
|
"num_tokens": 28819263.0,
|
|
"step": 16610
|
|
},
|
|
{
|
|
"entropy": 5.6806353569030765,
|
|
"epoch": 1.2927056992802957,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00048355771374115436,
|
|
"loss": 5.188,
|
|
"mean_token_accuracy": 0.1793963521718979,
|
|
"num_tokens": 28827316.0,
|
|
"step": 16615
|
|
},
|
|
{
|
|
"entropy": 5.634837627410889,
|
|
"epoch": 1.2930947286520134,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004835473118525125,
|
|
"loss": 5.1937,
|
|
"mean_token_accuracy": 0.18826982378959656,
|
|
"num_tokens": 28836272.0,
|
|
"step": 16620
|
|
},
|
|
{
|
|
"entropy": 5.567659711837768,
|
|
"epoch": 1.2934837580237308,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004835369067994971,
|
|
"loss": 5.0773,
|
|
"mean_token_accuracy": 0.19229266941547393,
|
|
"num_tokens": 28845180.0,
|
|
"step": 16625
|
|
},
|
|
{
|
|
"entropy": 5.560893630981445,
|
|
"epoch": 1.2938727873954483,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000483526498582266,
|
|
"loss": 5.0406,
|
|
"mean_token_accuracy": 0.1899822846055031,
|
|
"num_tokens": 28853903.0,
|
|
"step": 16630
|
|
},
|
|
{
|
|
"entropy": 5.557149267196655,
|
|
"epoch": 1.294261816767166,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00048351608720097715,
|
|
"loss": 5.0591,
|
|
"mean_token_accuracy": 0.1918584644794464,
|
|
"num_tokens": 28863071.0,
|
|
"step": 16635
|
|
},
|
|
{
|
|
"entropy": 5.6259753704071045,
|
|
"epoch": 1.2946508461388835,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00048350567265578867,
|
|
"loss": 5.1436,
|
|
"mean_token_accuracy": 0.18397480845451356,
|
|
"num_tokens": 28871620.0,
|
|
"step": 16640
|
|
},
|
|
{
|
|
"entropy": 5.669278907775879,
|
|
"epoch": 1.295039875510601,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004834952549468584,
|
|
"loss": 5.1861,
|
|
"mean_token_accuracy": 0.18329119980335234,
|
|
"num_tokens": 28879940.0,
|
|
"step": 16645
|
|
},
|
|
{
|
|
"entropy": 5.663364696502685,
|
|
"epoch": 1.2954289048823187,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004834848340743446,
|
|
"loss": 5.188,
|
|
"mean_token_accuracy": 0.18708661198616028,
|
|
"num_tokens": 28889012.0,
|
|
"step": 16650
|
|
},
|
|
{
|
|
"entropy": 5.593817567825317,
|
|
"epoch": 1.2958179342540361,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004834744100384052,
|
|
"loss": 5.0649,
|
|
"mean_token_accuracy": 0.19851250797510148,
|
|
"num_tokens": 28897312.0,
|
|
"step": 16655
|
|
},
|
|
{
|
|
"entropy": 5.596896457672119,
|
|
"epoch": 1.2962069636257538,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004834639828391984,
|
|
"loss": 5.0228,
|
|
"mean_token_accuracy": 0.20130644738674164,
|
|
"num_tokens": 28905977.0,
|
|
"step": 16660
|
|
},
|
|
{
|
|
"entropy": 5.5150003910064695,
|
|
"epoch": 1.2965959929974713,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00048345355247688256,
|
|
"loss": 5.0315,
|
|
"mean_token_accuracy": 0.19771711081266402,
|
|
"num_tokens": 28913979.0,
|
|
"step": 16665
|
|
},
|
|
{
|
|
"entropy": 5.565609741210937,
|
|
"epoch": 1.296985022369189,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004834431189516158,
|
|
"loss": 5.0589,
|
|
"mean_token_accuracy": 0.19748270362615586,
|
|
"num_tokens": 28922090.0,
|
|
"step": 16670
|
|
},
|
|
{
|
|
"entropy": 5.644658708572388,
|
|
"epoch": 1.2973740517409065,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004834326822635565,
|
|
"loss": 5.196,
|
|
"mean_token_accuracy": 0.1837651640176773,
|
|
"num_tokens": 28930816.0,
|
|
"step": 16675
|
|
},
|
|
{
|
|
"entropy": 5.634592819213867,
|
|
"epoch": 1.297763081112624,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00048342224241286296,
|
|
"loss": 5.1681,
|
|
"mean_token_accuracy": 0.18510053902864457,
|
|
"num_tokens": 28939125.0,
|
|
"step": 16680
|
|
},
|
|
{
|
|
"entropy": 5.5525157928466795,
|
|
"epoch": 1.2981521104843416,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004834117993996937,
|
|
"loss": 5.0497,
|
|
"mean_token_accuracy": 0.19919029921293258,
|
|
"num_tokens": 28947783.0,
|
|
"step": 16685
|
|
},
|
|
{
|
|
"entropy": 5.677631807327271,
|
|
"epoch": 1.2985411398560591,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004834013532242071,
|
|
"loss": 5.1768,
|
|
"mean_token_accuracy": 0.19040046632289886,
|
|
"num_tokens": 28957305.0,
|
|
"step": 16690
|
|
},
|
|
{
|
|
"entropy": 5.6526202201843265,
|
|
"epoch": 1.2989301692277766,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004833909038865616,
|
|
"loss": 5.1309,
|
|
"mean_token_accuracy": 0.18405349999666215,
|
|
"num_tokens": 28965757.0,
|
|
"step": 16695
|
|
},
|
|
{
|
|
"entropy": 5.632620620727539,
|
|
"epoch": 1.2993191985994943,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004833804513869159,
|
|
"loss": 5.1242,
|
|
"mean_token_accuracy": 0.19095647931098939,
|
|
"num_tokens": 28974846.0,
|
|
"step": 16700
|
|
},
|
|
{
|
|
"entropy": 5.501182699203492,
|
|
"epoch": 1.2997082279712118,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004833699957254284,
|
|
"loss": 4.9758,
|
|
"mean_token_accuracy": 0.19298425763845445,
|
|
"num_tokens": 28984060.0,
|
|
"step": 16705
|
|
},
|
|
{
|
|
"entropy": 5.580200910568237,
|
|
"epoch": 1.3000972573429295,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000483359536902258,
|
|
"loss": 5.0239,
|
|
"mean_token_accuracy": 0.19201190173625945,
|
|
"num_tokens": 28992705.0,
|
|
"step": 16710
|
|
},
|
|
{
|
|
"entropy": 5.635155057907104,
|
|
"epoch": 1.300486286714647,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004833490749175632,
|
|
"loss": 5.1393,
|
|
"mean_token_accuracy": 0.19078140705823898,
|
|
"num_tokens": 29001306.0,
|
|
"step": 16715
|
|
},
|
|
{
|
|
"entropy": 5.588790416717529,
|
|
"epoch": 1.3008753160863646,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00048333860977150286,
|
|
"loss": 5.143,
|
|
"mean_token_accuracy": 0.19001102298498154,
|
|
"num_tokens": 29010371.0,
|
|
"step": 16720
|
|
},
|
|
{
|
|
"entropy": 5.6419358253479,
|
|
"epoch": 1.3012643454580821,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00048332814146423566,
|
|
"loss": 5.1004,
|
|
"mean_token_accuracy": 0.19558511972427367,
|
|
"num_tokens": 29019940.0,
|
|
"step": 16725
|
|
},
|
|
{
|
|
"entropy": 5.660441589355469,
|
|
"epoch": 1.3016533748297996,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004833176699959206,
|
|
"loss": 5.1284,
|
|
"mean_token_accuracy": 0.19217051714658737,
|
|
"num_tokens": 29027644.0,
|
|
"step": 16730
|
|
},
|
|
{
|
|
"entropy": 5.57693076133728,
|
|
"epoch": 1.3020424042015173,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00048330719536671633,
|
|
"loss": 5.0715,
|
|
"mean_token_accuracy": 0.19291132539510727,
|
|
"num_tokens": 29035166.0,
|
|
"step": 16735
|
|
},
|
|
{
|
|
"entropy": 5.517680549621582,
|
|
"epoch": 1.3024314335732348,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000483296717576782,
|
|
"loss": 5.0236,
|
|
"mean_token_accuracy": 0.19569295942783355,
|
|
"num_tokens": 29044539.0,
|
|
"step": 16740
|
|
},
|
|
{
|
|
"entropy": 5.588887453079224,
|
|
"epoch": 1.3028204629449522,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004832862366262765,
|
|
"loss": 5.0743,
|
|
"mean_token_accuracy": 0.2067807838320732,
|
|
"num_tokens": 29052849.0,
|
|
"step": 16745
|
|
},
|
|
{
|
|
"entropy": 5.552817726135254,
|
|
"epoch": 1.30320949231667,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00048327575251535886,
|
|
"loss": 5.0801,
|
|
"mean_token_accuracy": 0.18806463479995728,
|
|
"num_tokens": 29061881.0,
|
|
"step": 16750
|
|
},
|
|
{
|
|
"entropy": 5.706825923919678,
|
|
"epoch": 1.3035985216883874,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004832652652441883,
|
|
"loss": 5.1506,
|
|
"mean_token_accuracy": 0.1846309334039688,
|
|
"num_tokens": 29070460.0,
|
|
"step": 16755
|
|
},
|
|
{
|
|
"entropy": 5.688552808761597,
|
|
"epoch": 1.303987551060105,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00048325477481292375,
|
|
"loss": 5.1726,
|
|
"mean_token_accuracy": 0.1844995841383934,
|
|
"num_tokens": 29079061.0,
|
|
"step": 16760
|
|
},
|
|
{
|
|
"entropy": 5.5268206119537355,
|
|
"epoch": 1.3043765804318226,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004832442812217244,
|
|
"loss": 5.0562,
|
|
"mean_token_accuracy": 0.19239771664142608,
|
|
"num_tokens": 29087525.0,
|
|
"step": 16765
|
|
},
|
|
{
|
|
"entropy": 5.56028995513916,
|
|
"epoch": 1.3047656098035403,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004832337844707496,
|
|
"loss": 5.0332,
|
|
"mean_token_accuracy": 0.19624444991350173,
|
|
"num_tokens": 29096206.0,
|
|
"step": 16770
|
|
},
|
|
{
|
|
"entropy": 5.653877019882202,
|
|
"epoch": 1.3051546391752578,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00048322328456015855,
|
|
"loss": 5.2253,
|
|
"mean_token_accuracy": 0.19010618031024934,
|
|
"num_tokens": 29105025.0,
|
|
"step": 16775
|
|
},
|
|
{
|
|
"entropy": 5.6057463645935055,
|
|
"epoch": 1.3055436685469752,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00048321278149011053,
|
|
"loss": 5.1835,
|
|
"mean_token_accuracy": 0.18936053216457366,
|
|
"num_tokens": 29113468.0,
|
|
"step": 16780
|
|
},
|
|
{
|
|
"entropy": 5.5992865562438965,
|
|
"epoch": 1.305932697918693,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00048320227526076504,
|
|
"loss": 5.0798,
|
|
"mean_token_accuracy": 0.19523320645093917,
|
|
"num_tokens": 29122904.0,
|
|
"step": 16785
|
|
},
|
|
{
|
|
"entropy": 5.607943916320801,
|
|
"epoch": 1.3063217272904104,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004831917658722814,
|
|
"loss": 5.0633,
|
|
"mean_token_accuracy": 0.20157826095819473,
|
|
"num_tokens": 29132408.0,
|
|
"step": 16790
|
|
},
|
|
{
|
|
"entropy": 5.648335695266724,
|
|
"epoch": 1.3067107566621279,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00048318125332481903,
|
|
"loss": 5.2157,
|
|
"mean_token_accuracy": 0.18695988208055497,
|
|
"num_tokens": 29141840.0,
|
|
"step": 16795
|
|
},
|
|
{
|
|
"entropy": 5.718431091308593,
|
|
"epoch": 1.3070997860338456,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00048317073761853764,
|
|
"loss": 5.1752,
|
|
"mean_token_accuracy": 0.18881198167800903,
|
|
"num_tokens": 29150759.0,
|
|
"step": 16800
|
|
},
|
|
{
|
|
"entropy": 5.544278478622436,
|
|
"epoch": 1.307488815405563,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004831602187535965,
|
|
"loss": 4.9853,
|
|
"mean_token_accuracy": 0.2031836599111557,
|
|
"num_tokens": 29159489.0,
|
|
"step": 16805
|
|
},
|
|
{
|
|
"entropy": 5.56814866065979,
|
|
"epoch": 1.3078778447772808,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004831496967301554,
|
|
"loss": 5.0213,
|
|
"mean_token_accuracy": 0.1931745857000351,
|
|
"num_tokens": 29168160.0,
|
|
"step": 16810
|
|
},
|
|
{
|
|
"entropy": 5.628138732910156,
|
|
"epoch": 1.3082668741489982,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00048313917154837386,
|
|
"loss": 5.1058,
|
|
"mean_token_accuracy": 0.19329580068588256,
|
|
"num_tokens": 29176534.0,
|
|
"step": 16815
|
|
},
|
|
{
|
|
"entropy": 5.542742204666138,
|
|
"epoch": 1.308655903520716,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004831286432084118,
|
|
"loss": 5.0077,
|
|
"mean_token_accuracy": 0.203941248357296,
|
|
"num_tokens": 29185461.0,
|
|
"step": 16820
|
|
},
|
|
{
|
|
"entropy": 5.604961585998535,
|
|
"epoch": 1.3090449328924334,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004831181117104289,
|
|
"loss": 5.144,
|
|
"mean_token_accuracy": 0.18596413284540175,
|
|
"num_tokens": 29194218.0,
|
|
"step": 16825
|
|
},
|
|
{
|
|
"entropy": 5.577546691894531,
|
|
"epoch": 1.3094339622641509,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00048310757705458476,
|
|
"loss": 5.1079,
|
|
"mean_token_accuracy": 0.19188106060028076,
|
|
"num_tokens": 29203720.0,
|
|
"step": 16830
|
|
},
|
|
{
|
|
"entropy": 5.613342523574829,
|
|
"epoch": 1.3098229916358686,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00048309703924103944,
|
|
"loss": 5.1674,
|
|
"mean_token_accuracy": 0.1892984539270401,
|
|
"num_tokens": 29212588.0,
|
|
"step": 16835
|
|
},
|
|
{
|
|
"entropy": 5.6453112125396725,
|
|
"epoch": 1.310212021007586,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00048308649826995283,
|
|
"loss": 5.169,
|
|
"mean_token_accuracy": 0.1883926883339882,
|
|
"num_tokens": 29220718.0,
|
|
"step": 16840
|
|
},
|
|
{
|
|
"entropy": 5.6234375,
|
|
"epoch": 1.3106010503793035,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00048307595414148475,
|
|
"loss": 5.0402,
|
|
"mean_token_accuracy": 0.19771301746368408,
|
|
"num_tokens": 29229386.0,
|
|
"step": 16845
|
|
},
|
|
{
|
|
"entropy": 5.604703712463379,
|
|
"epoch": 1.3109900797510212,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004830654068557952,
|
|
"loss": 5.0924,
|
|
"mean_token_accuracy": 0.19491372704505922,
|
|
"num_tokens": 29238390.0,
|
|
"step": 16850
|
|
},
|
|
{
|
|
"entropy": 5.643201112747192,
|
|
"epoch": 1.3113791091227387,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004830548564130444,
|
|
"loss": 5.183,
|
|
"mean_token_accuracy": 0.18927546441555024,
|
|
"num_tokens": 29246502.0,
|
|
"step": 16855
|
|
},
|
|
{
|
|
"entropy": 5.582104253768921,
|
|
"epoch": 1.3117681384944564,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00048304430281339216,
|
|
"loss": 5.1069,
|
|
"mean_token_accuracy": 0.1855737254023552,
|
|
"num_tokens": 29254954.0,
|
|
"step": 16860
|
|
},
|
|
{
|
|
"entropy": 5.606703567504883,
|
|
"epoch": 1.3121571678661739,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004830337460569989,
|
|
"loss": 5.0788,
|
|
"mean_token_accuracy": 0.2005214884877205,
|
|
"num_tokens": 29263294.0,
|
|
"step": 16865
|
|
},
|
|
{
|
|
"entropy": 5.584879732131958,
|
|
"epoch": 1.3125461972378916,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004830231861440246,
|
|
"loss": 5.0548,
|
|
"mean_token_accuracy": 0.19693197309970856,
|
|
"num_tokens": 29271737.0,
|
|
"step": 16870
|
|
},
|
|
{
|
|
"entropy": 5.69629430770874,
|
|
"epoch": 1.312935226609609,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004830126230746295,
|
|
"loss": 5.1933,
|
|
"mean_token_accuracy": 0.18574800491333007,
|
|
"num_tokens": 29279473.0,
|
|
"step": 16875
|
|
},
|
|
{
|
|
"entropy": 5.60352578163147,
|
|
"epoch": 1.3133242559813265,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00048300205684897405,
|
|
"loss": 5.1038,
|
|
"mean_token_accuracy": 0.20338490307331086,
|
|
"num_tokens": 29287650.0,
|
|
"step": 16880
|
|
},
|
|
{
|
|
"entropy": 5.600238370895386,
|
|
"epoch": 1.3137132853530442,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004829914874672184,
|
|
"loss": 5.1287,
|
|
"mean_token_accuracy": 0.18724319487810134,
|
|
"num_tokens": 29296914.0,
|
|
"step": 16885
|
|
},
|
|
{
|
|
"entropy": 5.666216325759888,
|
|
"epoch": 1.3141023147247617,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00048298091492952297,
|
|
"loss": 5.1136,
|
|
"mean_token_accuracy": 0.18820077627897264,
|
|
"num_tokens": 29305409.0,
|
|
"step": 16890
|
|
},
|
|
{
|
|
"entropy": 5.69935245513916,
|
|
"epoch": 1.3144913440964792,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004829703392360482,
|
|
"loss": 5.135,
|
|
"mean_token_accuracy": 0.18850217014551163,
|
|
"num_tokens": 29314333.0,
|
|
"step": 16895
|
|
},
|
|
{
|
|
"entropy": 5.510940837860107,
|
|
"epoch": 1.3148803734681969,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00048295976038695455,
|
|
"loss": 4.9864,
|
|
"mean_token_accuracy": 0.19643135219812394,
|
|
"num_tokens": 29323764.0,
|
|
"step": 16900
|
|
},
|
|
{
|
|
"entropy": 5.571589994430542,
|
|
"epoch": 1.3152694028399143,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004829491783824025,
|
|
"loss": 5.0723,
|
|
"mean_token_accuracy": 0.19625774621963502,
|
|
"num_tokens": 29331734.0,
|
|
"step": 16905
|
|
},
|
|
{
|
|
"entropy": 5.523209047317505,
|
|
"epoch": 1.315658432211632,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00048293859322255276,
|
|
"loss": 4.9797,
|
|
"mean_token_accuracy": 0.20637786090373994,
|
|
"num_tokens": 29339791.0,
|
|
"step": 16910
|
|
},
|
|
{
|
|
"entropy": 5.538656234741211,
|
|
"epoch": 1.3160474615833495,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004829280049075657,
|
|
"loss": 5.1159,
|
|
"mean_token_accuracy": 0.1856507495045662,
|
|
"num_tokens": 29348548.0,
|
|
"step": 16915
|
|
},
|
|
{
|
|
"entropy": 5.570025873184204,
|
|
"epoch": 1.3164364909550672,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00048291741343760216,
|
|
"loss": 5.0421,
|
|
"mean_token_accuracy": 0.19357602000236512,
|
|
"num_tokens": 29357151.0,
|
|
"step": 16920
|
|
},
|
|
{
|
|
"entropy": 5.672178745269775,
|
|
"epoch": 1.3168255203267847,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004829068188128229,
|
|
"loss": 5.0379,
|
|
"mean_token_accuracy": 0.20119286328554153,
|
|
"num_tokens": 29365643.0,
|
|
"step": 16925
|
|
},
|
|
{
|
|
"entropy": 5.581224250793457,
|
|
"epoch": 1.3172145496985022,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004828962210333885,
|
|
"loss": 5.1326,
|
|
"mean_token_accuracy": 0.18838583528995514,
|
|
"num_tokens": 29374215.0,
|
|
"step": 16930
|
|
},
|
|
{
|
|
"entropy": 5.569288730621338,
|
|
"epoch": 1.3176035790702199,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004828856200994598,
|
|
"loss": 5.0447,
|
|
"mean_token_accuracy": 0.19315528720617295,
|
|
"num_tokens": 29382586.0,
|
|
"step": 16935
|
|
},
|
|
{
|
|
"entropy": 5.535900545120239,
|
|
"epoch": 1.3179926084419373,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004828750160111978,
|
|
"loss": 5.1007,
|
|
"mean_token_accuracy": 0.18802523463964463,
|
|
"num_tokens": 29391922.0,
|
|
"step": 16940
|
|
},
|
|
{
|
|
"entropy": 5.609203863143921,
|
|
"epoch": 1.3183816378136548,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00048286440876876325,
|
|
"loss": 5.0571,
|
|
"mean_token_accuracy": 0.19533028900623323,
|
|
"num_tokens": 29400408.0,
|
|
"step": 16945
|
|
},
|
|
{
|
|
"entropy": 5.56855616569519,
|
|
"epoch": 1.3187706671853725,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00048285379837231714,
|
|
"loss": 4.9909,
|
|
"mean_token_accuracy": 0.20062803030014037,
|
|
"num_tokens": 29408130.0,
|
|
"step": 16950
|
|
},
|
|
{
|
|
"entropy": 5.617013835906983,
|
|
"epoch": 1.31915969655709,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004828431848220205,
|
|
"loss": 5.0769,
|
|
"mean_token_accuracy": 0.19123691767454148,
|
|
"num_tokens": 29417446.0,
|
|
"step": 16955
|
|
},
|
|
{
|
|
"entropy": 5.649213027954102,
|
|
"epoch": 1.3195487259288077,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004828325681180343,
|
|
"loss": 5.1492,
|
|
"mean_token_accuracy": 0.19348373264074326,
|
|
"num_tokens": 29426023.0,
|
|
"step": 16960
|
|
},
|
|
{
|
|
"entropy": 5.621719026565552,
|
|
"epoch": 1.3199377553005252,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004828219482605197,
|
|
"loss": 5.0658,
|
|
"mean_token_accuracy": 0.194810451567173,
|
|
"num_tokens": 29434737.0,
|
|
"step": 16965
|
|
},
|
|
{
|
|
"entropy": 5.554741144180298,
|
|
"epoch": 1.3203267846722428,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00048281132524963786,
|
|
"loss": 5.0852,
|
|
"mean_token_accuracy": 0.18866194933652877,
|
|
"num_tokens": 29443926.0,
|
|
"step": 16970
|
|
},
|
|
{
|
|
"entropy": 5.5818909168243405,
|
|
"epoch": 1.3207158140439603,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004828006990855499,
|
|
"loss": 5.082,
|
|
"mean_token_accuracy": 0.19597212225198746,
|
|
"num_tokens": 29452495.0,
|
|
"step": 16975
|
|
},
|
|
{
|
|
"entropy": 5.557660484313965,
|
|
"epoch": 1.3211048434156778,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00048279006976841704,
|
|
"loss": 5.0463,
|
|
"mean_token_accuracy": 0.19332642257213592,
|
|
"num_tokens": 29460661.0,
|
|
"step": 16980
|
|
},
|
|
{
|
|
"entropy": 5.584459733963013,
|
|
"epoch": 1.3214938727873955,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004827794372984007,
|
|
"loss": 5.0413,
|
|
"mean_token_accuracy": 0.19895520955324172,
|
|
"num_tokens": 29469155.0,
|
|
"step": 16985
|
|
},
|
|
{
|
|
"entropy": 5.636346054077149,
|
|
"epoch": 1.321882902159113,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000482768801675662,
|
|
"loss": 5.1516,
|
|
"mean_token_accuracy": 0.19496320486068724,
|
|
"num_tokens": 29478220.0,
|
|
"step": 16990
|
|
},
|
|
{
|
|
"entropy": 5.606045913696289,
|
|
"epoch": 1.3222719315308304,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004827581629003625,
|
|
"loss": 5.1037,
|
|
"mean_token_accuracy": 0.19156274050474167,
|
|
"num_tokens": 29486336.0,
|
|
"step": 16995
|
|
},
|
|
{
|
|
"entropy": 5.654403591156006,
|
|
"epoch": 1.3226609609025481,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00048274752097266356,
|
|
"loss": 5.2119,
|
|
"mean_token_accuracy": 0.18937937766313553,
|
|
"num_tokens": 29495150.0,
|
|
"step": 17000
|
|
},
|
|
{
|
|
"entropy": 5.626471328735351,
|
|
"epoch": 1.3230499902742658,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004827368758927266,
|
|
"loss": 5.0915,
|
|
"mean_token_accuracy": 0.1930074691772461,
|
|
"num_tokens": 29503508.0,
|
|
"step": 17005
|
|
},
|
|
{
|
|
"entropy": 5.571884632110596,
|
|
"epoch": 1.3234390196459833,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004827262276607132,
|
|
"loss": 5.0703,
|
|
"mean_token_accuracy": 0.19201896339654922,
|
|
"num_tokens": 29513038.0,
|
|
"step": 17010
|
|
},
|
|
{
|
|
"entropy": 5.560047960281372,
|
|
"epoch": 1.3238280490177008,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000482715576276785,
|
|
"loss": 5.0374,
|
|
"mean_token_accuracy": 0.19725186377763748,
|
|
"num_tokens": 29521344.0,
|
|
"step": 17015
|
|
},
|
|
{
|
|
"entropy": 5.5897095680236815,
|
|
"epoch": 1.3242170783894185,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004827049217411035,
|
|
"loss": 5.1529,
|
|
"mean_token_accuracy": 0.18654258400201798,
|
|
"num_tokens": 29530109.0,
|
|
"step": 17020
|
|
},
|
|
{
|
|
"entropy": 5.615104150772095,
|
|
"epoch": 1.324606107761136,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00048269426405383043,
|
|
"loss": 5.0741,
|
|
"mean_token_accuracy": 0.18548837006092073,
|
|
"num_tokens": 29539114.0,
|
|
"step": 17025
|
|
},
|
|
{
|
|
"entropy": 5.609760284423828,
|
|
"epoch": 1.3249951371328534,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00048268360321512745,
|
|
"loss": 5.1188,
|
|
"mean_token_accuracy": 0.19076967090368271,
|
|
"num_tokens": 29548746.0,
|
|
"step": 17030
|
|
},
|
|
{
|
|
"entropy": 5.63235182762146,
|
|
"epoch": 1.3253841665045711,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004826729392251564,
|
|
"loss": 5.1562,
|
|
"mean_token_accuracy": 0.18577359467744828,
|
|
"num_tokens": 29557681.0,
|
|
"step": 17035
|
|
},
|
|
{
|
|
"entropy": 5.6283042430877686,
|
|
"epoch": 1.3257731958762886,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000482662272084079,
|
|
"loss": 5.1407,
|
|
"mean_token_accuracy": 0.19394930452108383,
|
|
"num_tokens": 29566151.0,
|
|
"step": 17040
|
|
},
|
|
{
|
|
"entropy": 5.558325672149659,
|
|
"epoch": 1.326162225248006,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004826516017920571,
|
|
"loss": 4.9518,
|
|
"mean_token_accuracy": 0.20908219814300538,
|
|
"num_tokens": 29574853.0,
|
|
"step": 17045
|
|
},
|
|
{
|
|
"entropy": 5.56689190864563,
|
|
"epoch": 1.3265512546197238,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004826409283492528,
|
|
"loss": 5.0598,
|
|
"mean_token_accuracy": 0.19533458203077317,
|
|
"num_tokens": 29583319.0,
|
|
"step": 17050
|
|
},
|
|
{
|
|
"entropy": 5.5869800567626955,
|
|
"epoch": 1.3269402839914415,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00048263025175582783,
|
|
"loss": 5.1499,
|
|
"mean_token_accuracy": 0.1880865439772606,
|
|
"num_tokens": 29591949.0,
|
|
"step": 17055
|
|
},
|
|
{
|
|
"entropy": 5.6449895858764645,
|
|
"epoch": 1.327329313363159,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004826195720119442,
|
|
"loss": 5.1545,
|
|
"mean_token_accuracy": 0.18147476613521576,
|
|
"num_tokens": 29600293.0,
|
|
"step": 17060
|
|
},
|
|
{
|
|
"entropy": 5.657760190963745,
|
|
"epoch": 1.3277183427348764,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004826088891177641,
|
|
"loss": 5.1738,
|
|
"mean_token_accuracy": 0.1958606019616127,
|
|
"num_tokens": 29608602.0,
|
|
"step": 17065
|
|
},
|
|
{
|
|
"entropy": 5.581202125549316,
|
|
"epoch": 1.3281073721065941,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00048259820307344954,
|
|
"loss": 5.134,
|
|
"mean_token_accuracy": 0.19184042662382125,
|
|
"num_tokens": 29617464.0,
|
|
"step": 17070
|
|
},
|
|
{
|
|
"entropy": 5.619830656051636,
|
|
"epoch": 1.3284964014783116,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00048258751387916267,
|
|
"loss": 5.0386,
|
|
"mean_token_accuracy": 0.20158812552690505,
|
|
"num_tokens": 29626297.0,
|
|
"step": 17075
|
|
},
|
|
{
|
|
"entropy": 5.554988861083984,
|
|
"epoch": 1.328885430850029,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00048257682153506564,
|
|
"loss": 5.0658,
|
|
"mean_token_accuracy": 0.19179969131946564,
|
|
"num_tokens": 29635085.0,
|
|
"step": 17080
|
|
},
|
|
{
|
|
"entropy": 5.552317905426025,
|
|
"epoch": 1.3292744602217468,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004825661260413208,
|
|
"loss": 5.051,
|
|
"mean_token_accuracy": 0.1966339558362961,
|
|
"num_tokens": 29643528.0,
|
|
"step": 17085
|
|
},
|
|
{
|
|
"entropy": 5.560385084152221,
|
|
"epoch": 1.3296634895934643,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00048255542739809035,
|
|
"loss": 5.1091,
|
|
"mean_token_accuracy": 0.1915844276547432,
|
|
"num_tokens": 29651883.0,
|
|
"step": 17090
|
|
},
|
|
{
|
|
"entropy": 5.554691791534424,
|
|
"epoch": 1.330052518965182,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00048254472560553665,
|
|
"loss": 5.0973,
|
|
"mean_token_accuracy": 0.18957026898860932,
|
|
"num_tokens": 29661092.0,
|
|
"step": 17095
|
|
},
|
|
{
|
|
"entropy": 5.601039552688599,
|
|
"epoch": 1.3304415483368994,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00048253402066382207,
|
|
"loss": 5.1307,
|
|
"mean_token_accuracy": 0.1981351912021637,
|
|
"num_tokens": 29670285.0,
|
|
"step": 17100
|
|
},
|
|
{
|
|
"entropy": 5.637584638595581,
|
|
"epoch": 1.3308305777086171,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004825233125731091,
|
|
"loss": 5.1747,
|
|
"mean_token_accuracy": 0.18887474089860917,
|
|
"num_tokens": 29679249.0,
|
|
"step": 17105
|
|
},
|
|
{
|
|
"entropy": 5.6272870063781735,
|
|
"epoch": 1.3312196070803346,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00048251260133356014,
|
|
"loss": 5.1446,
|
|
"mean_token_accuracy": 0.1861952617764473,
|
|
"num_tokens": 29687978.0,
|
|
"step": 17110
|
|
},
|
|
{
|
|
"entropy": 5.59926118850708,
|
|
"epoch": 1.331608636452052,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00048250188694533774,
|
|
"loss": 5.162,
|
|
"mean_token_accuracy": 0.18740419149398804,
|
|
"num_tokens": 29695972.0,
|
|
"step": 17115
|
|
},
|
|
{
|
|
"entropy": 5.626380062103271,
|
|
"epoch": 1.3319976658237698,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004824911694086044,
|
|
"loss": 4.9934,
|
|
"mean_token_accuracy": 0.1966044545173645,
|
|
"num_tokens": 29704997.0,
|
|
"step": 17120
|
|
},
|
|
{
|
|
"entropy": 5.707925271987915,
|
|
"epoch": 1.3323866951954872,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000482480448723523,
|
|
"loss": 5.2219,
|
|
"mean_token_accuracy": 0.19110133349895478,
|
|
"num_tokens": 29713957.0,
|
|
"step": 17125
|
|
},
|
|
{
|
|
"entropy": 5.640682506561279,
|
|
"epoch": 1.3327757245672047,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00048246972489025586,
|
|
"loss": 5.115,
|
|
"mean_token_accuracy": 0.19240255206823348,
|
|
"num_tokens": 29721989.0,
|
|
"step": 17130
|
|
},
|
|
{
|
|
"entropy": 5.591029119491577,
|
|
"epoch": 1.3331647539389224,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00048245899790896597,
|
|
"loss": 5.0425,
|
|
"mean_token_accuracy": 0.19880155175924302,
|
|
"num_tokens": 29730032.0,
|
|
"step": 17135
|
|
},
|
|
{
|
|
"entropy": 5.581392478942871,
|
|
"epoch": 1.33355378331064,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004824482677798159,
|
|
"loss": 5.0597,
|
|
"mean_token_accuracy": 0.19574938714504242,
|
|
"num_tokens": 29738545.0,
|
|
"step": 17140
|
|
},
|
|
{
|
|
"entropy": 5.626249551773071,
|
|
"epoch": 1.3339428126823576,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00048243753450296863,
|
|
"loss": 5.0789,
|
|
"mean_token_accuracy": 0.1984911873936653,
|
|
"num_tokens": 29747371.0,
|
|
"step": 17145
|
|
},
|
|
{
|
|
"entropy": 5.592475748062133,
|
|
"epoch": 1.334331842054075,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00048242679807858693,
|
|
"loss": 5.0233,
|
|
"mean_token_accuracy": 0.19690910279750823,
|
|
"num_tokens": 29756565.0,
|
|
"step": 17150
|
|
},
|
|
{
|
|
"entropy": 5.540616273880005,
|
|
"epoch": 1.3347208714257928,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00048241605850683365,
|
|
"loss": 5.0405,
|
|
"mean_token_accuracy": 0.1935047596693039,
|
|
"num_tokens": 29765846.0,
|
|
"step": 17155
|
|
},
|
|
{
|
|
"entropy": 5.601731586456299,
|
|
"epoch": 1.3351099007975102,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00048240531578787197,
|
|
"loss": 5.0869,
|
|
"mean_token_accuracy": 0.19569143950939177,
|
|
"num_tokens": 29774222.0,
|
|
"step": 17160
|
|
},
|
|
{
|
|
"entropy": 5.565546274185181,
|
|
"epoch": 1.3354989301692277,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004823945699218647,
|
|
"loss": 4.9861,
|
|
"mean_token_accuracy": 0.20037296116352082,
|
|
"num_tokens": 29782366.0,
|
|
"step": 17165
|
|
},
|
|
{
|
|
"entropy": 5.6020973205566404,
|
|
"epoch": 1.3358879595409454,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004823838209089749,
|
|
"loss": 5.1308,
|
|
"mean_token_accuracy": 0.18899450004100798,
|
|
"num_tokens": 29792147.0,
|
|
"step": 17170
|
|
},
|
|
{
|
|
"entropy": 5.615554237365723,
|
|
"epoch": 1.3362769889126629,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00048237306874936565,
|
|
"loss": 5.0882,
|
|
"mean_token_accuracy": 0.19848169833421708,
|
|
"num_tokens": 29801325.0,
|
|
"step": 17175
|
|
},
|
|
{
|
|
"entropy": 5.579449605941773,
|
|
"epoch": 1.3366660182843804,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004823623134432001,
|
|
"loss": 5.0531,
|
|
"mean_token_accuracy": 0.19223212003707885,
|
|
"num_tokens": 29809353.0,
|
|
"step": 17180
|
|
},
|
|
{
|
|
"entropy": 5.566813325881958,
|
|
"epoch": 1.337055047656098,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00048235155499064166,
|
|
"loss": 5.0997,
|
|
"mean_token_accuracy": 0.19648808240890503,
|
|
"num_tokens": 29817746.0,
|
|
"step": 17185
|
|
},
|
|
{
|
|
"entropy": 5.562612056732178,
|
|
"epoch": 1.3374440770278155,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00048234079339185335,
|
|
"loss": 5.118,
|
|
"mean_token_accuracy": 0.19193292707204818,
|
|
"num_tokens": 29826468.0,
|
|
"step": 17190
|
|
},
|
|
{
|
|
"entropy": 5.651003646850586,
|
|
"epoch": 1.3378331063995332,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00048233002864699856,
|
|
"loss": 5.1846,
|
|
"mean_token_accuracy": 0.18184355199337005,
|
|
"num_tokens": 29835051.0,
|
|
"step": 17195
|
|
},
|
|
{
|
|
"entropy": 5.632854032516479,
|
|
"epoch": 1.3382221357712507,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004823192607562405,
|
|
"loss": 5.081,
|
|
"mean_token_accuracy": 0.19087070524692534,
|
|
"num_tokens": 29843514.0,
|
|
"step": 17200
|
|
},
|
|
{
|
|
"entropy": 5.591190910339355,
|
|
"epoch": 1.3386111651429684,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00048230848971974265,
|
|
"loss": 5.01,
|
|
"mean_token_accuracy": 0.19248565584421157,
|
|
"num_tokens": 29851861.0,
|
|
"step": 17205
|
|
},
|
|
{
|
|
"entropy": 5.5409363269805905,
|
|
"epoch": 1.3390001945146859,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004822977155376684,
|
|
"loss": 5.0213,
|
|
"mean_token_accuracy": 0.19842875599861146,
|
|
"num_tokens": 29860639.0,
|
|
"step": 17210
|
|
},
|
|
{
|
|
"entropy": 5.550060033798218,
|
|
"epoch": 1.3393892238864034,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004822869382101814,
|
|
"loss": 5.1883,
|
|
"mean_token_accuracy": 0.18755810260772704,
|
|
"num_tokens": 29869931.0,
|
|
"step": 17215
|
|
},
|
|
{
|
|
"entropy": 5.63261775970459,
|
|
"epoch": 1.339778253258121,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004822761577374449,
|
|
"loss": 5.1042,
|
|
"mean_token_accuracy": 0.19078442007303237,
|
|
"num_tokens": 29878933.0,
|
|
"step": 17220
|
|
},
|
|
{
|
|
"entropy": 5.607994461059571,
|
|
"epoch": 1.3401672826298385,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004822653741196227,
|
|
"loss": 5.0956,
|
|
"mean_token_accuracy": 0.1942954868078232,
|
|
"num_tokens": 29888031.0,
|
|
"step": 17225
|
|
},
|
|
{
|
|
"entropy": 5.574734401702881,
|
|
"epoch": 1.340556312001556,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004822545873568783,
|
|
"loss": 5.0562,
|
|
"mean_token_accuracy": 0.19396908581256866,
|
|
"num_tokens": 29896792.0,
|
|
"step": 17230
|
|
},
|
|
{
|
|
"entropy": 5.551525640487671,
|
|
"epoch": 1.3409453413732737,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00048224379744937545,
|
|
"loss": 5.0441,
|
|
"mean_token_accuracy": 0.19622675478458404,
|
|
"num_tokens": 29905185.0,
|
|
"step": 17235
|
|
},
|
|
{
|
|
"entropy": 5.652295637130737,
|
|
"epoch": 1.3413343707449912,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00048223300439727783,
|
|
"loss": 5.1544,
|
|
"mean_token_accuracy": 0.18267314434051513,
|
|
"num_tokens": 29913289.0,
|
|
"step": 17240
|
|
},
|
|
{
|
|
"entropy": 5.583216190338135,
|
|
"epoch": 1.3417234001167089,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00048222220820074926,
|
|
"loss": 5.1015,
|
|
"mean_token_accuracy": 0.1957106590270996,
|
|
"num_tokens": 29922112.0,
|
|
"step": 17245
|
|
},
|
|
{
|
|
"entropy": 5.626125860214233,
|
|
"epoch": 1.3421124294884264,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00048221140885995346,
|
|
"loss": 5.0849,
|
|
"mean_token_accuracy": 0.1889687806367874,
|
|
"num_tokens": 29930944.0,
|
|
"step": 17250
|
|
},
|
|
{
|
|
"entropy": 5.665236186981201,
|
|
"epoch": 1.342501458860144,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004822006063750543,
|
|
"loss": 5.1933,
|
|
"mean_token_accuracy": 0.18412038832902908,
|
|
"num_tokens": 29938576.0,
|
|
"step": 17255
|
|
},
|
|
{
|
|
"entropy": 5.588354682922363,
|
|
"epoch": 1.3428904882318615,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00048218980074621575,
|
|
"loss": 5.0862,
|
|
"mean_token_accuracy": 0.19173820912837983,
|
|
"num_tokens": 29946771.0,
|
|
"step": 17260
|
|
},
|
|
{
|
|
"entropy": 5.6391833305358885,
|
|
"epoch": 1.343279517603579,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00048217899197360183,
|
|
"loss": 5.1065,
|
|
"mean_token_accuracy": 0.19124213308095933,
|
|
"num_tokens": 29955098.0,
|
|
"step": 17265
|
|
},
|
|
{
|
|
"entropy": 5.576250219345093,
|
|
"epoch": 1.3436685469752967,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004821681800573764,
|
|
"loss": 5.1183,
|
|
"mean_token_accuracy": 0.18985211104154587,
|
|
"num_tokens": 29964538.0,
|
|
"step": 17270
|
|
},
|
|
{
|
|
"entropy": 5.586406278610229,
|
|
"epoch": 1.3440575763470142,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004821573649977036,
|
|
"loss": 5.0529,
|
|
"mean_token_accuracy": 0.19566859155893326,
|
|
"num_tokens": 29973965.0,
|
|
"step": 17275
|
|
},
|
|
{
|
|
"entropy": 5.5091344833374025,
|
|
"epoch": 1.3444466057187316,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00048214654679474753,
|
|
"loss": 4.9762,
|
|
"mean_token_accuracy": 0.19796336591243743,
|
|
"num_tokens": 29982742.0,
|
|
"step": 17280
|
|
},
|
|
{
|
|
"entropy": 5.527531623840332,
|
|
"epoch": 1.3448356350904493,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00048213572544867224,
|
|
"loss": 5.0483,
|
|
"mean_token_accuracy": 0.19206763654947281,
|
|
"num_tokens": 29991846.0,
|
|
"step": 17285
|
|
},
|
|
{
|
|
"entropy": 5.631241130828857,
|
|
"epoch": 1.3452246644621668,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00048212490095964213,
|
|
"loss": 5.0025,
|
|
"mean_token_accuracy": 0.20127080231904984,
|
|
"num_tokens": 29999784.0,
|
|
"step": 17290
|
|
},
|
|
{
|
|
"entropy": 5.573941898345947,
|
|
"epoch": 1.3456136938338845,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004821140733278212,
|
|
"loss": 5.1206,
|
|
"mean_token_accuracy": 0.192512209713459,
|
|
"num_tokens": 30008139.0,
|
|
"step": 17295
|
|
},
|
|
{
|
|
"entropy": 5.596026515960693,
|
|
"epoch": 1.346002723205602,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004821032425533739,
|
|
"loss": 5.1149,
|
|
"mean_token_accuracy": 0.1973307266831398,
|
|
"num_tokens": 30016891.0,
|
|
"step": 17300
|
|
},
|
|
{
|
|
"entropy": 5.5896257877349855,
|
|
"epoch": 1.3463917525773197,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004820924086364646,
|
|
"loss": 5.0976,
|
|
"mean_token_accuracy": 0.1946762517094612,
|
|
"num_tokens": 30025472.0,
|
|
"step": 17305
|
|
},
|
|
{
|
|
"entropy": 5.624167728424072,
|
|
"epoch": 1.3467807819490372,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00048208157157725756,
|
|
"loss": 5.0983,
|
|
"mean_token_accuracy": 0.19798196107149124,
|
|
"num_tokens": 30034088.0,
|
|
"step": 17310
|
|
},
|
|
{
|
|
"entropy": 5.5352325439453125,
|
|
"epoch": 1.3471698113207546,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00048207073137591726,
|
|
"loss": 5.0417,
|
|
"mean_token_accuracy": 0.192068450152874,
|
|
"num_tokens": 30042651.0,
|
|
"step": 17315
|
|
},
|
|
{
|
|
"entropy": 5.580952596664429,
|
|
"epoch": 1.3475588406924723,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00048205988803260824,
|
|
"loss": 5.0011,
|
|
"mean_token_accuracy": 0.2002151608467102,
|
|
"num_tokens": 30050898.0,
|
|
"step": 17320
|
|
},
|
|
{
|
|
"entropy": 5.677296829223633,
|
|
"epoch": 1.3479478700641898,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00048204904154749496,
|
|
"loss": 5.1725,
|
|
"mean_token_accuracy": 0.1894117623567581,
|
|
"num_tokens": 30059357.0,
|
|
"step": 17325
|
|
},
|
|
{
|
|
"entropy": 5.60735297203064,
|
|
"epoch": 1.3483368994359073,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00048203819192074206,
|
|
"loss": 5.0754,
|
|
"mean_token_accuracy": 0.1892850935459137,
|
|
"num_tokens": 30068137.0,
|
|
"step": 17330
|
|
},
|
|
{
|
|
"entropy": 5.600775814056396,
|
|
"epoch": 1.348725928807625,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00048202733915251407,
|
|
"loss": 5.1299,
|
|
"mean_token_accuracy": 0.195503132045269,
|
|
"num_tokens": 30077139.0,
|
|
"step": 17335
|
|
},
|
|
{
|
|
"entropy": 5.633728885650635,
|
|
"epoch": 1.3491149581793425,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00048201648324297573,
|
|
"loss": 5.1307,
|
|
"mean_token_accuracy": 0.20009224861860275,
|
|
"num_tokens": 30085267.0,
|
|
"step": 17340
|
|
},
|
|
{
|
|
"entropy": 5.570550918579102,
|
|
"epoch": 1.3495039875510602,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00048200562419229185,
|
|
"loss": 5.0517,
|
|
"mean_token_accuracy": 0.20046866983175277,
|
|
"num_tokens": 30093804.0,
|
|
"step": 17345
|
|
},
|
|
{
|
|
"entropy": 5.5981920719146725,
|
|
"epoch": 1.3498930169227776,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000481994762000627,
|
|
"loss": 5.0327,
|
|
"mean_token_accuracy": 0.20512161552906036,
|
|
"num_tokens": 30102653.0,
|
|
"step": 17350
|
|
},
|
|
{
|
|
"entropy": 5.534904336929321,
|
|
"epoch": 1.3502820462944953,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00048198389666814616,
|
|
"loss": 5.0145,
|
|
"mean_token_accuracy": 0.19998365193605422,
|
|
"num_tokens": 30111978.0,
|
|
"step": 17355
|
|
},
|
|
{
|
|
"entropy": 5.623388576507568,
|
|
"epoch": 1.3506710756662128,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00048197302819501416,
|
|
"loss": 5.2542,
|
|
"mean_token_accuracy": 0.18305663168430328,
|
|
"num_tokens": 30120387.0,
|
|
"step": 17360
|
|
},
|
|
{
|
|
"entropy": 5.601443147659301,
|
|
"epoch": 1.3510601050379303,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00048196215658139586,
|
|
"loss": 5.0984,
|
|
"mean_token_accuracy": 0.19018661379814147,
|
|
"num_tokens": 30129069.0,
|
|
"step": 17365
|
|
},
|
|
{
|
|
"entropy": 5.5916832447052,
|
|
"epoch": 1.351449134409648,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004819512818274562,
|
|
"loss": 5.0703,
|
|
"mean_token_accuracy": 0.19169774949550628,
|
|
"num_tokens": 30138077.0,
|
|
"step": 17370
|
|
},
|
|
{
|
|
"entropy": 5.554825639724731,
|
|
"epoch": 1.3518381637813655,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004819404039333603,
|
|
"loss": 5.0164,
|
|
"mean_token_accuracy": 0.19625434875488282,
|
|
"num_tokens": 30146189.0,
|
|
"step": 17375
|
|
},
|
|
{
|
|
"entropy": 5.596820497512818,
|
|
"epoch": 1.352227193153083,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004819295228992731,
|
|
"loss": 5.1441,
|
|
"mean_token_accuracy": 0.18551240712404252,
|
|
"num_tokens": 30155664.0,
|
|
"step": 17380
|
|
},
|
|
{
|
|
"entropy": 5.621693563461304,
|
|
"epoch": 1.3526162225248006,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00048191863872535984,
|
|
"loss": 5.0982,
|
|
"mean_token_accuracy": 0.19399722069501876,
|
|
"num_tokens": 30164701.0,
|
|
"step": 17385
|
|
},
|
|
{
|
|
"entropy": 5.6402098655700685,
|
|
"epoch": 1.3530052518965183,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004819077514117855,
|
|
"loss": 5.1395,
|
|
"mean_token_accuracy": 0.19072800129652023,
|
|
"num_tokens": 30173916.0,
|
|
"step": 17390
|
|
},
|
|
{
|
|
"entropy": 5.588237047195435,
|
|
"epoch": 1.3533942812682358,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00048189686095871545,
|
|
"loss": 5.0708,
|
|
"mean_token_accuracy": 0.19412756562232972,
|
|
"num_tokens": 30182803.0,
|
|
"step": 17395
|
|
},
|
|
{
|
|
"entropy": 5.5683369636535645,
|
|
"epoch": 1.3537833106399533,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00048188596736631475,
|
|
"loss": 5.0786,
|
|
"mean_token_accuracy": 0.20161097794771193,
|
|
"num_tokens": 30191589.0,
|
|
"step": 17400
|
|
},
|
|
{
|
|
"entropy": 5.605751371383667,
|
|
"epoch": 1.354172340011671,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00048187507063474885,
|
|
"loss": 5.1785,
|
|
"mean_token_accuracy": 0.1880600258708,
|
|
"num_tokens": 30200170.0,
|
|
"step": 17405
|
|
},
|
|
{
|
|
"entropy": 5.626162481307984,
|
|
"epoch": 1.3545613693833884,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00048186417076418294,
|
|
"loss": 5.0419,
|
|
"mean_token_accuracy": 0.19382455348968505,
|
|
"num_tokens": 30208683.0,
|
|
"step": 17410
|
|
},
|
|
{
|
|
"entropy": 5.589068412780762,
|
|
"epoch": 1.354950398755106,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00048185326775478256,
|
|
"loss": 5.0985,
|
|
"mean_token_accuracy": 0.1832721158862114,
|
|
"num_tokens": 30217141.0,
|
|
"step": 17415
|
|
},
|
|
{
|
|
"entropy": 5.582963228225708,
|
|
"epoch": 1.3553394281268236,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00048184236160671306,
|
|
"loss": 5.0901,
|
|
"mean_token_accuracy": 0.18514712750911713,
|
|
"num_tokens": 30226759.0,
|
|
"step": 17420
|
|
},
|
|
{
|
|
"entropy": 5.616628122329712,
|
|
"epoch": 1.355728457498541,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00048183145232013995,
|
|
"loss": 5.1576,
|
|
"mean_token_accuracy": 0.19223590493202208,
|
|
"num_tokens": 30235945.0,
|
|
"step": 17425
|
|
},
|
|
{
|
|
"entropy": 5.620598363876343,
|
|
"epoch": 1.3561174868702586,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00048182053989522883,
|
|
"loss": 5.1247,
|
|
"mean_token_accuracy": 0.18232114762067794,
|
|
"num_tokens": 30244912.0,
|
|
"step": 17430
|
|
},
|
|
{
|
|
"entropy": 5.6058262348175045,
|
|
"epoch": 1.3565065162419763,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00048180962433214515,
|
|
"loss": 5.0715,
|
|
"mean_token_accuracy": 0.19382267892360688,
|
|
"num_tokens": 30253807.0,
|
|
"step": 17435
|
|
},
|
|
{
|
|
"entropy": 5.615492296218872,
|
|
"epoch": 1.356895545613694,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00048179870563105453,
|
|
"loss": 5.172,
|
|
"mean_token_accuracy": 0.1914404660463333,
|
|
"num_tokens": 30262380.0,
|
|
"step": 17440
|
|
},
|
|
{
|
|
"entropy": 5.655902481079101,
|
|
"epoch": 1.3572845749854114,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004817877837921228,
|
|
"loss": 5.1003,
|
|
"mean_token_accuracy": 0.19246790558099747,
|
|
"num_tokens": 30271374.0,
|
|
"step": 17445
|
|
},
|
|
{
|
|
"entropy": 5.601302671432495,
|
|
"epoch": 1.357673604357129,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004817768588155155,
|
|
"loss": 5.1328,
|
|
"mean_token_accuracy": 0.19475583285093306,
|
|
"num_tokens": 30280037.0,
|
|
"step": 17450
|
|
},
|
|
{
|
|
"entropy": 5.531799364089966,
|
|
"epoch": 1.3580626337288466,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00048176593070139865,
|
|
"loss": 4.9348,
|
|
"mean_token_accuracy": 0.21244002878665924,
|
|
"num_tokens": 30288335.0,
|
|
"step": 17455
|
|
},
|
|
{
|
|
"entropy": 5.519866943359375,
|
|
"epoch": 1.358451663100564,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00048175499944993767,
|
|
"loss": 5.0368,
|
|
"mean_token_accuracy": 0.19410879909992218,
|
|
"num_tokens": 30297109.0,
|
|
"step": 17460
|
|
},
|
|
{
|
|
"entropy": 5.580335521697998,
|
|
"epoch": 1.3588406924722816,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00048174406506129884,
|
|
"loss": 5.0509,
|
|
"mean_token_accuracy": 0.19508031755685806,
|
|
"num_tokens": 30305594.0,
|
|
"step": 17465
|
|
},
|
|
{
|
|
"entropy": 5.542119836807251,
|
|
"epoch": 1.3592297218439993,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00048173312753564787,
|
|
"loss": 4.9816,
|
|
"mean_token_accuracy": 0.20457783639431,
|
|
"num_tokens": 30313106.0,
|
|
"step": 17470
|
|
},
|
|
{
|
|
"entropy": 5.576837539672852,
|
|
"epoch": 1.3596187512157167,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004817221868731506,
|
|
"loss": 5.17,
|
|
"mean_token_accuracy": 0.1869833990931511,
|
|
"num_tokens": 30322194.0,
|
|
"step": 17475
|
|
},
|
|
{
|
|
"entropy": 5.53590497970581,
|
|
"epoch": 1.3600077805874344,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00048171124307397334,
|
|
"loss": 5.0174,
|
|
"mean_token_accuracy": 0.19708539694547653,
|
|
"num_tokens": 30330247.0,
|
|
"step": 17480
|
|
},
|
|
{
|
|
"entropy": 5.619177913665771,
|
|
"epoch": 1.360396809959152,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004817002961382819,
|
|
"loss": 5.1134,
|
|
"mean_token_accuracy": 0.19212924540042878,
|
|
"num_tokens": 30338738.0,
|
|
"step": 17485
|
|
},
|
|
{
|
|
"entropy": 5.576988649368286,
|
|
"epoch": 1.3607858393308696,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00048168934606624255,
|
|
"loss": 5.0908,
|
|
"mean_token_accuracy": 0.19094870686531068,
|
|
"num_tokens": 30347729.0,
|
|
"step": 17490
|
|
},
|
|
{
|
|
"entropy": 5.62130708694458,
|
|
"epoch": 1.361174868702587,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00048167839285802116,
|
|
"loss": 5.1002,
|
|
"mean_token_accuracy": 0.1885942116379738,
|
|
"num_tokens": 30356408.0,
|
|
"step": 17495
|
|
},
|
|
{
|
|
"entropy": 5.5848783493042,
|
|
"epoch": 1.3615638980743046,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004816674365137843,
|
|
"loss": 5.0646,
|
|
"mean_token_accuracy": 0.19244394302368165,
|
|
"num_tokens": 30364910.0,
|
|
"step": 17500
|
|
},
|
|
{
|
|
"entropy": 5.557191944122314,
|
|
"epoch": 1.3619529274460223,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000481656477033698,
|
|
"loss": 5.0823,
|
|
"mean_token_accuracy": 0.1955784320831299,
|
|
"num_tokens": 30373882.0,
|
|
"step": 17505
|
|
},
|
|
{
|
|
"entropy": 5.643977117538452,
|
|
"epoch": 1.3623419568177397,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004816455144179286,
|
|
"loss": 5.1402,
|
|
"mean_token_accuracy": 0.1846423327922821,
|
|
"num_tokens": 30382884.0,
|
|
"step": 17510
|
|
},
|
|
{
|
|
"entropy": 5.592962169647217,
|
|
"epoch": 1.3627309861894572,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004816345486666424,
|
|
"loss": 5.0437,
|
|
"mean_token_accuracy": 0.1940524697303772,
|
|
"num_tokens": 30391798.0,
|
|
"step": 17515
|
|
},
|
|
{
|
|
"entropy": 5.583971691131592,
|
|
"epoch": 1.363120015561175,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004816235797800058,
|
|
"loss": 5.0603,
|
|
"mean_token_accuracy": 0.19570833891630174,
|
|
"num_tokens": 30400194.0,
|
|
"step": 17520
|
|
},
|
|
{
|
|
"entropy": 5.569255828857422,
|
|
"epoch": 1.3635090449328924,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004816126077581852,
|
|
"loss": 4.9913,
|
|
"mean_token_accuracy": 0.19892526268959046,
|
|
"num_tokens": 30408653.0,
|
|
"step": 17525
|
|
},
|
|
{
|
|
"entropy": 5.550200891494751,
|
|
"epoch": 1.36389807430461,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00048160163260134724,
|
|
"loss": 5.1267,
|
|
"mean_token_accuracy": 0.19007736295461655,
|
|
"num_tokens": 30417467.0,
|
|
"step": 17530
|
|
},
|
|
{
|
|
"entropy": 5.5903106212615965,
|
|
"epoch": 1.3642871036763276,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004815906543096583,
|
|
"loss": 5.0976,
|
|
"mean_token_accuracy": 0.18592511117458344,
|
|
"num_tokens": 30425993.0,
|
|
"step": 17535
|
|
},
|
|
{
|
|
"entropy": 5.634143924713134,
|
|
"epoch": 1.3646761330480452,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000481579672883285,
|
|
"loss": 5.0976,
|
|
"mean_token_accuracy": 0.19496258944272996,
|
|
"num_tokens": 30434809.0,
|
|
"step": 17540
|
|
},
|
|
{
|
|
"entropy": 5.601830720901489,
|
|
"epoch": 1.3650651624197627,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00048156868832239396,
|
|
"loss": 5.0998,
|
|
"mean_token_accuracy": 0.1941066637635231,
|
|
"num_tokens": 30443536.0,
|
|
"step": 17545
|
|
},
|
|
{
|
|
"entropy": 5.518461418151856,
|
|
"epoch": 1.3654541917914802,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004815577006271519,
|
|
"loss": 5.0835,
|
|
"mean_token_accuracy": 0.19164232313632965,
|
|
"num_tokens": 30452163.0,
|
|
"step": 17550
|
|
},
|
|
{
|
|
"entropy": 5.563957834243775,
|
|
"epoch": 1.365843221163198,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00048154670979772555,
|
|
"loss": 5.0576,
|
|
"mean_token_accuracy": 0.19976511895656585,
|
|
"num_tokens": 30461234.0,
|
|
"step": 17555
|
|
},
|
|
{
|
|
"entropy": 5.725088453292846,
|
|
"epoch": 1.3662322505349154,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004815357158342815,
|
|
"loss": 5.2178,
|
|
"mean_token_accuracy": 0.17882028073072434,
|
|
"num_tokens": 30470438.0,
|
|
"step": 17560
|
|
},
|
|
{
|
|
"entropy": 5.639098882675171,
|
|
"epoch": 1.3666212799066328,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004815247187369868,
|
|
"loss": 5.0081,
|
|
"mean_token_accuracy": 0.19483415633440018,
|
|
"num_tokens": 30479454.0,
|
|
"step": 17565
|
|
},
|
|
{
|
|
"entropy": 5.632966947555542,
|
|
"epoch": 1.3670103092783505,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00048151371850600814,
|
|
"loss": 5.1187,
|
|
"mean_token_accuracy": 0.189105848968029,
|
|
"num_tokens": 30487968.0,
|
|
"step": 17570
|
|
},
|
|
{
|
|
"entropy": 5.595620012283325,
|
|
"epoch": 1.367399338650068,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00048150271514151255,
|
|
"loss": 5.0474,
|
|
"mean_token_accuracy": 0.1967533975839615,
|
|
"num_tokens": 30495712.0,
|
|
"step": 17575
|
|
},
|
|
{
|
|
"entropy": 5.605516576766968,
|
|
"epoch": 1.3677883680217857,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00048149170864366693,
|
|
"loss": 5.1447,
|
|
"mean_token_accuracy": 0.18511847406625748,
|
|
"num_tokens": 30505008.0,
|
|
"step": 17580
|
|
},
|
|
{
|
|
"entropy": 5.612831735610962,
|
|
"epoch": 1.3681773973935032,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00048148069901263836,
|
|
"loss": 5.0421,
|
|
"mean_token_accuracy": 0.19839342981576918,
|
|
"num_tokens": 30514496.0,
|
|
"step": 17585
|
|
},
|
|
{
|
|
"entropy": 5.590772294998169,
|
|
"epoch": 1.368566426765221,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00048146968624859375,
|
|
"loss": 5.0267,
|
|
"mean_token_accuracy": 0.19972210973501206,
|
|
"num_tokens": 30522942.0,
|
|
"step": 17590
|
|
},
|
|
{
|
|
"entropy": 5.658151483535766,
|
|
"epoch": 1.3689554561369384,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004814586703517003,
|
|
"loss": 5.1894,
|
|
"mean_token_accuracy": 0.18800529688596726,
|
|
"num_tokens": 30532124.0,
|
|
"step": 17595
|
|
},
|
|
{
|
|
"entropy": 5.671984100341797,
|
|
"epoch": 1.3693444855086558,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004814476513221251,
|
|
"loss": 5.2975,
|
|
"mean_token_accuracy": 0.17737707495689392,
|
|
"num_tokens": 30541063.0,
|
|
"step": 17600
|
|
},
|
|
{
|
|
"entropy": 5.664184284210205,
|
|
"epoch": 1.3697335148803735,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00048143662916003545,
|
|
"loss": 5.0155,
|
|
"mean_token_accuracy": 0.19651644676923752,
|
|
"num_tokens": 30549062.0,
|
|
"step": 17605
|
|
},
|
|
{
|
|
"entropy": 5.65010347366333,
|
|
"epoch": 1.370122544252091,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004814256038655985,
|
|
"loss": 5.1154,
|
|
"mean_token_accuracy": 0.18934282064437866,
|
|
"num_tokens": 30557211.0,
|
|
"step": 17610
|
|
},
|
|
{
|
|
"entropy": 5.613674211502075,
|
|
"epoch": 1.3705115736238085,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004814145754389816,
|
|
"loss": 5.1701,
|
|
"mean_token_accuracy": 0.18557561188936234,
|
|
"num_tokens": 30566603.0,
|
|
"step": 17615
|
|
},
|
|
{
|
|
"entropy": 5.574848222732544,
|
|
"epoch": 1.3709006029955262,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00048140354388035204,
|
|
"loss": 5.0494,
|
|
"mean_token_accuracy": 0.1934528112411499,
|
|
"num_tokens": 30574903.0,
|
|
"step": 17620
|
|
},
|
|
{
|
|
"entropy": 5.661852407455444,
|
|
"epoch": 1.3712896323672437,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004813925091898772,
|
|
"loss": 5.1385,
|
|
"mean_token_accuracy": 0.18710356801748276,
|
|
"num_tokens": 30584925.0,
|
|
"step": 17625
|
|
},
|
|
{
|
|
"entropy": 5.688584709167481,
|
|
"epoch": 1.3716786617389614,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004813814713677246,
|
|
"loss": 5.1887,
|
|
"mean_token_accuracy": 0.1886507675051689,
|
|
"num_tokens": 30593376.0,
|
|
"step": 17630
|
|
},
|
|
{
|
|
"entropy": 5.611472225189209,
|
|
"epoch": 1.3720676911106788,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004813704304140616,
|
|
"loss": 5.1142,
|
|
"mean_token_accuracy": 0.19458251148462297,
|
|
"num_tokens": 30602306.0,
|
|
"step": 17635
|
|
},
|
|
{
|
|
"entropy": 5.556731748580932,
|
|
"epoch": 1.3724567204823965,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004813593863290559,
|
|
"loss": 5.0566,
|
|
"mean_token_accuracy": 0.1932797759771347,
|
|
"num_tokens": 30611340.0,
|
|
"step": 17640
|
|
},
|
|
{
|
|
"entropy": 5.617712688446045,
|
|
"epoch": 1.372845749854114,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004813483391128748,
|
|
"loss": 5.1591,
|
|
"mean_token_accuracy": 0.19261574894189834,
|
|
"num_tokens": 30619507.0,
|
|
"step": 17645
|
|
},
|
|
{
|
|
"entropy": 5.639880228042602,
|
|
"epoch": 1.3732347792258315,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004813372887656862,
|
|
"loss": 5.1521,
|
|
"mean_token_accuracy": 0.1923792615532875,
|
|
"num_tokens": 30629897.0,
|
|
"step": 17650
|
|
},
|
|
{
|
|
"entropy": 5.6188194274902346,
|
|
"epoch": 1.3736238085975492,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004813262352876576,
|
|
"loss": 5.0936,
|
|
"mean_token_accuracy": 0.19418303966522216,
|
|
"num_tokens": 30638517.0,
|
|
"step": 17655
|
|
},
|
|
{
|
|
"entropy": 5.646220588684082,
|
|
"epoch": 1.3740128379692667,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00048131517867895684,
|
|
"loss": 5.1397,
|
|
"mean_token_accuracy": 0.19555290937423705,
|
|
"num_tokens": 30646816.0,
|
|
"step": 17660
|
|
},
|
|
{
|
|
"entropy": 5.628312063217163,
|
|
"epoch": 1.3744018673409841,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00048130411893975155,
|
|
"loss": 5.0978,
|
|
"mean_token_accuracy": 0.19647861868143082,
|
|
"num_tokens": 30655199.0,
|
|
"step": 17665
|
|
},
|
|
{
|
|
"entropy": 5.557996082305908,
|
|
"epoch": 1.3747908967127018,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004812930560702097,
|
|
"loss": 4.9805,
|
|
"mean_token_accuracy": 0.19906099885702133,
|
|
"num_tokens": 30663562.0,
|
|
"step": 17670
|
|
},
|
|
{
|
|
"entropy": 5.60725769996643,
|
|
"epoch": 1.3751799260844193,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00048128199007049907,
|
|
"loss": 5.1464,
|
|
"mean_token_accuracy": 0.18604770302772522,
|
|
"num_tokens": 30672611.0,
|
|
"step": 17675
|
|
},
|
|
{
|
|
"entropy": 5.591836309432983,
|
|
"epoch": 1.375568955456137,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00048127092094078756,
|
|
"loss": 5.0758,
|
|
"mean_token_accuracy": 0.19608640819787979,
|
|
"num_tokens": 30680766.0,
|
|
"step": 17680
|
|
},
|
|
{
|
|
"entropy": 5.544107103347779,
|
|
"epoch": 1.3759579848278545,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00048125984868124317,
|
|
"loss": 4.9433,
|
|
"mean_token_accuracy": 0.19995449334383011,
|
|
"num_tokens": 30689192.0,
|
|
"step": 17685
|
|
},
|
|
{
|
|
"entropy": 5.576938152313232,
|
|
"epoch": 1.3763470141995722,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004812487732920338,
|
|
"loss": 5.0601,
|
|
"mean_token_accuracy": 0.1913628935813904,
|
|
"num_tokens": 30697889.0,
|
|
"step": 17690
|
|
},
|
|
{
|
|
"entropy": 5.656646203994751,
|
|
"epoch": 1.3767360435712896,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004812376947733277,
|
|
"loss": 5.1042,
|
|
"mean_token_accuracy": 0.19301426857709886,
|
|
"num_tokens": 30706285.0,
|
|
"step": 17695
|
|
},
|
|
{
|
|
"entropy": 5.59697995185852,
|
|
"epoch": 1.3771250729430071,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00048122661312529263,
|
|
"loss": 5.0701,
|
|
"mean_token_accuracy": 0.1972261354327202,
|
|
"num_tokens": 30715159.0,
|
|
"step": 17700
|
|
},
|
|
{
|
|
"entropy": 5.544631671905518,
|
|
"epoch": 1.3775141023147248,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004812155283480971,
|
|
"loss": 4.9839,
|
|
"mean_token_accuracy": 0.19768782705068588,
|
|
"num_tokens": 30723133.0,
|
|
"step": 17705
|
|
},
|
|
{
|
|
"entropy": 5.658510971069336,
|
|
"epoch": 1.3779031316864423,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004812044404419091,
|
|
"loss": 5.1674,
|
|
"mean_token_accuracy": 0.19228937476873398,
|
|
"num_tokens": 30732272.0,
|
|
"step": 17710
|
|
},
|
|
{
|
|
"entropy": 5.620146799087524,
|
|
"epoch": 1.3782921610581598,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000481193349406897,
|
|
"loss": 5.0317,
|
|
"mean_token_accuracy": 0.19477264136075972,
|
|
"num_tokens": 30740439.0,
|
|
"step": 17715
|
|
},
|
|
{
|
|
"entropy": 5.56381368637085,
|
|
"epoch": 1.3786811904298775,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000481182255243229,
|
|
"loss": 5.0931,
|
|
"mean_token_accuracy": 0.19626167863607408,
|
|
"num_tokens": 30749722.0,
|
|
"step": 17720
|
|
},
|
|
{
|
|
"entropy": 5.718609285354614,
|
|
"epoch": 1.379070219801595,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00048117115795107335,
|
|
"loss": 5.292,
|
|
"mean_token_accuracy": 0.18305347114801407,
|
|
"num_tokens": 30759261.0,
|
|
"step": 17725
|
|
},
|
|
{
|
|
"entropy": 5.693091630935669,
|
|
"epoch": 1.3794592491733126,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004811600575305987,
|
|
"loss": 5.1203,
|
|
"mean_token_accuracy": 0.1956807032227516,
|
|
"num_tokens": 30769133.0,
|
|
"step": 17730
|
|
},
|
|
{
|
|
"entropy": 5.615317535400391,
|
|
"epoch": 1.3798482785450301,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004811489539819731,
|
|
"loss": 5.0459,
|
|
"mean_token_accuracy": 0.19954855144023895,
|
|
"num_tokens": 30777879.0,
|
|
"step": 17735
|
|
},
|
|
{
|
|
"entropy": 5.6220598220825195,
|
|
"epoch": 1.3802373079167478,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00048113784730536544,
|
|
"loss": 5.1674,
|
|
"mean_token_accuracy": 0.19754636138677598,
|
|
"num_tokens": 30786307.0,
|
|
"step": 17740
|
|
},
|
|
{
|
|
"entropy": 5.6582808017730715,
|
|
"epoch": 1.3806263372884653,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00048112673750094396,
|
|
"loss": 5.1837,
|
|
"mean_token_accuracy": 0.18878302574157715,
|
|
"num_tokens": 30796153.0,
|
|
"step": 17745
|
|
},
|
|
{
|
|
"entropy": 5.608172369003296,
|
|
"epoch": 1.3810153666601828,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004811156245688773,
|
|
"loss": 4.9604,
|
|
"mean_token_accuracy": 0.19866713136434555,
|
|
"num_tokens": 30805441.0,
|
|
"step": 17750
|
|
},
|
|
{
|
|
"entropy": 5.56573076248169,
|
|
"epoch": 1.3814043960319005,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004811045085093342,
|
|
"loss": 5.1187,
|
|
"mean_token_accuracy": 0.18319412022829057,
|
|
"num_tokens": 30814898.0,
|
|
"step": 17755
|
|
},
|
|
{
|
|
"entropy": 5.681590938568116,
|
|
"epoch": 1.381793425403618,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004810933893224831,
|
|
"loss": 5.2924,
|
|
"mean_token_accuracy": 0.18218099623918532,
|
|
"num_tokens": 30823995.0,
|
|
"step": 17760
|
|
},
|
|
{
|
|
"entropy": 5.655806541442871,
|
|
"epoch": 1.3821824547753354,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00048108226700849287,
|
|
"loss": 5.1243,
|
|
"mean_token_accuracy": 0.19118371307849885,
|
|
"num_tokens": 30832963.0,
|
|
"step": 17765
|
|
},
|
|
{
|
|
"entropy": 5.640542078018188,
|
|
"epoch": 1.382571484147053,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004810711415675323,
|
|
"loss": 5.1283,
|
|
"mean_token_accuracy": 0.18644823580980302,
|
|
"num_tokens": 30841559.0,
|
|
"step": 17770
|
|
},
|
|
{
|
|
"entropy": 5.6816521167755125,
|
|
"epoch": 1.3829605135187706,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004810600129997702,
|
|
"loss": 5.1765,
|
|
"mean_token_accuracy": 0.18798786252737046,
|
|
"num_tokens": 30850481.0,
|
|
"step": 17775
|
|
},
|
|
{
|
|
"entropy": 5.63182635307312,
|
|
"epoch": 1.3833495428904883,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00048104888130537534,
|
|
"loss": 5.0154,
|
|
"mean_token_accuracy": 0.19417383372783661,
|
|
"num_tokens": 30859632.0,
|
|
"step": 17780
|
|
},
|
|
{
|
|
"entropy": 5.654698419570923,
|
|
"epoch": 1.3837385722622058,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00048103774648451664,
|
|
"loss": 5.0895,
|
|
"mean_token_accuracy": 0.19187875539064408,
|
|
"num_tokens": 30867909.0,
|
|
"step": 17785
|
|
},
|
|
{
|
|
"entropy": 5.6158520698547365,
|
|
"epoch": 1.3841276016339235,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00048102660853736314,
|
|
"loss": 5.1031,
|
|
"mean_token_accuracy": 0.19536942839622498,
|
|
"num_tokens": 30876339.0,
|
|
"step": 17790
|
|
},
|
|
{
|
|
"entropy": 5.624637222290039,
|
|
"epoch": 1.384516631005641,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004810154674640837,
|
|
"loss": 5.0804,
|
|
"mean_token_accuracy": 0.19113468378782272,
|
|
"num_tokens": 30884998.0,
|
|
"step": 17795
|
|
},
|
|
{
|
|
"entropy": 5.649057626724243,
|
|
"epoch": 1.3849056603773584,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00048100432326484744,
|
|
"loss": 5.1144,
|
|
"mean_token_accuracy": 0.18475880324840546,
|
|
"num_tokens": 30893554.0,
|
|
"step": 17800
|
|
},
|
|
{
|
|
"entropy": 5.5887950420379635,
|
|
"epoch": 1.385294689749076,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004809931759398235,
|
|
"loss": 5.1169,
|
|
"mean_token_accuracy": 0.19248030930757523,
|
|
"num_tokens": 30901954.0,
|
|
"step": 17805
|
|
},
|
|
{
|
|
"entropy": 5.607624244689942,
|
|
"epoch": 1.3856837191207936,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00048098202548918094,
|
|
"loss": 5.0737,
|
|
"mean_token_accuracy": 0.19664642661809922,
|
|
"num_tokens": 30911145.0,
|
|
"step": 17810
|
|
},
|
|
{
|
|
"entropy": 5.5625138759613035,
|
|
"epoch": 1.386072748492511,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00048097087191308914,
|
|
"loss": 4.9676,
|
|
"mean_token_accuracy": 0.2015418902039528,
|
|
"num_tokens": 30918924.0,
|
|
"step": 17815
|
|
},
|
|
{
|
|
"entropy": 5.591161823272705,
|
|
"epoch": 1.3864617778642288,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004809597152117171,
|
|
"loss": 5.1286,
|
|
"mean_token_accuracy": 0.19008181989192963,
|
|
"num_tokens": 30927620.0,
|
|
"step": 17820
|
|
},
|
|
{
|
|
"entropy": 5.593923854827881,
|
|
"epoch": 1.3868508072359464,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004809485553852342,
|
|
"loss": 5.0181,
|
|
"mean_token_accuracy": 0.19180162400007247,
|
|
"num_tokens": 30936140.0,
|
|
"step": 17825
|
|
},
|
|
{
|
|
"entropy": 5.700794744491577,
|
|
"epoch": 1.387239836607664,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004809373924338098,
|
|
"loss": 5.2234,
|
|
"mean_token_accuracy": 0.18718539029359818,
|
|
"num_tokens": 30944450.0,
|
|
"step": 17830
|
|
},
|
|
{
|
|
"entropy": 5.572172403335571,
|
|
"epoch": 1.3876288659793814,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00048092622635761316,
|
|
"loss": 5.0533,
|
|
"mean_token_accuracy": 0.1959550365805626,
|
|
"num_tokens": 30953536.0,
|
|
"step": 17835
|
|
},
|
|
{
|
|
"entropy": 5.6090741634368895,
|
|
"epoch": 1.388017895351099,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00048091505715681395,
|
|
"loss": 5.071,
|
|
"mean_token_accuracy": 0.19303107261657715,
|
|
"num_tokens": 30962556.0,
|
|
"step": 17840
|
|
},
|
|
{
|
|
"entropy": 5.589877653121948,
|
|
"epoch": 1.3884069247228166,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004809038848315814,
|
|
"loss": 5.0184,
|
|
"mean_token_accuracy": 0.20263680517673494,
|
|
"num_tokens": 30970476.0,
|
|
"step": 17845
|
|
},
|
|
{
|
|
"entropy": 5.664753007888794,
|
|
"epoch": 1.388795954094534,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004808927093820851,
|
|
"loss": 5.0633,
|
|
"mean_token_accuracy": 0.18840179443359376,
|
|
"num_tokens": 30978945.0,
|
|
"step": 17850
|
|
},
|
|
{
|
|
"entropy": 5.552944183349609,
|
|
"epoch": 1.3891849834662517,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004808815308084947,
|
|
"loss": 5.0265,
|
|
"mean_token_accuracy": 0.19097656458616258,
|
|
"num_tokens": 30988135.0,
|
|
"step": 17855
|
|
},
|
|
{
|
|
"entropy": 5.656019258499145,
|
|
"epoch": 1.3895740128379692,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004808703491109798,
|
|
"loss": 5.11,
|
|
"mean_token_accuracy": 0.1987979531288147,
|
|
"num_tokens": 30996408.0,
|
|
"step": 17860
|
|
},
|
|
{
|
|
"entropy": 5.594230604171753,
|
|
"epoch": 1.3899630422096867,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004808591642897099,
|
|
"loss": 5.1335,
|
|
"mean_token_accuracy": 0.19308444410562514,
|
|
"num_tokens": 31004156.0,
|
|
"step": 17865
|
|
},
|
|
{
|
|
"entropy": 5.575358629226685,
|
|
"epoch": 1.3903520715814044,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000480847976344855,
|
|
"loss": 5.0647,
|
|
"mean_token_accuracy": 0.19762326776981354,
|
|
"num_tokens": 31013518.0,
|
|
"step": 17870
|
|
},
|
|
{
|
|
"entropy": 5.555838012695313,
|
|
"epoch": 1.390741100953122,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00048083678527658465,
|
|
"loss": 4.9586,
|
|
"mean_token_accuracy": 0.20326709598302842,
|
|
"num_tokens": 31022116.0,
|
|
"step": 17875
|
|
},
|
|
{
|
|
"entropy": 5.635913276672364,
|
|
"epoch": 1.3911301303248396,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004808255910850687,
|
|
"loss": 5.1227,
|
|
"mean_token_accuracy": 0.19242368191480635,
|
|
"num_tokens": 31030320.0,
|
|
"step": 17880
|
|
},
|
|
{
|
|
"entropy": 5.63309416770935,
|
|
"epoch": 1.391519159696557,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004808143937704769,
|
|
"loss": 5.0846,
|
|
"mean_token_accuracy": 0.1992114245891571,
|
|
"num_tokens": 31038410.0,
|
|
"step": 17885
|
|
},
|
|
{
|
|
"entropy": 5.582927322387695,
|
|
"epoch": 1.3919081890682747,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00048080319333297937,
|
|
"loss": 5.0019,
|
|
"mean_token_accuracy": 0.19571396857500076,
|
|
"num_tokens": 31047719.0,
|
|
"step": 17890
|
|
},
|
|
{
|
|
"entropy": 5.588042974472046,
|
|
"epoch": 1.3922972184399922,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00048079198977274597,
|
|
"loss": 5.138,
|
|
"mean_token_accuracy": 0.19519376158714294,
|
|
"num_tokens": 31057536.0,
|
|
"step": 17895
|
|
},
|
|
{
|
|
"entropy": 5.6246764183044435,
|
|
"epoch": 1.3926862478117097,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00048078078308994666,
|
|
"loss": 5.0877,
|
|
"mean_token_accuracy": 0.19471651166677476,
|
|
"num_tokens": 31066975.0,
|
|
"step": 17900
|
|
},
|
|
{
|
|
"entropy": 5.617932558059692,
|
|
"epoch": 1.3930752771834274,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004807695732847515,
|
|
"loss": 5.0789,
|
|
"mean_token_accuracy": 0.20295270383358002,
|
|
"num_tokens": 31075573.0,
|
|
"step": 17905
|
|
},
|
|
{
|
|
"entropy": 5.56302843093872,
|
|
"epoch": 1.3934643065551449,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00048075836035733053,
|
|
"loss": 5.0057,
|
|
"mean_token_accuracy": 0.20600516051054002,
|
|
"num_tokens": 31084486.0,
|
|
"step": 17910
|
|
},
|
|
{
|
|
"entropy": 5.588654088973999,
|
|
"epoch": 1.3938533359268626,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000480747144307854,
|
|
"loss": 5.0568,
|
|
"mean_token_accuracy": 0.1980026915669441,
|
|
"num_tokens": 31093045.0,
|
|
"step": 17915
|
|
},
|
|
{
|
|
"entropy": 5.6169164180755615,
|
|
"epoch": 1.39424236529858,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00048073592513649203,
|
|
"loss": 5.0863,
|
|
"mean_token_accuracy": 0.20203913152217864,
|
|
"num_tokens": 31102024.0,
|
|
"step": 17920
|
|
},
|
|
{
|
|
"entropy": 5.603633403778076,
|
|
"epoch": 1.3946313946702977,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004807247028434148,
|
|
"loss": 5.1737,
|
|
"mean_token_accuracy": 0.18329787105321885,
|
|
"num_tokens": 31110656.0,
|
|
"step": 17925
|
|
},
|
|
{
|
|
"entropy": 5.626287126541138,
|
|
"epoch": 1.3950204240420152,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004807134774287927,
|
|
"loss": 5.0325,
|
|
"mean_token_accuracy": 0.20022621005773544,
|
|
"num_tokens": 31119199.0,
|
|
"step": 17930
|
|
},
|
|
{
|
|
"entropy": 5.59880633354187,
|
|
"epoch": 1.3954094534137327,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00048070224889279603,
|
|
"loss": 5.0341,
|
|
"mean_token_accuracy": 0.20225781351327896,
|
|
"num_tokens": 31127301.0,
|
|
"step": 17935
|
|
},
|
|
{
|
|
"entropy": 5.591383457183838,
|
|
"epoch": 1.3957984827854504,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00048069101723559505,
|
|
"loss": 5.1173,
|
|
"mean_token_accuracy": 0.19614229649305343,
|
|
"num_tokens": 31136714.0,
|
|
"step": 17940
|
|
},
|
|
{
|
|
"entropy": 5.635069084167481,
|
|
"epoch": 1.3961875121571679,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004806797824573603,
|
|
"loss": 5.1176,
|
|
"mean_token_accuracy": 0.18883515149354935,
|
|
"num_tokens": 31145663.0,
|
|
"step": 17945
|
|
},
|
|
{
|
|
"entropy": 5.516148710250855,
|
|
"epoch": 1.3965765415288853,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004806685445582624,
|
|
"loss": 4.8749,
|
|
"mean_token_accuracy": 0.20871867388486862,
|
|
"num_tokens": 31154335.0,
|
|
"step": 17950
|
|
},
|
|
{
|
|
"entropy": 5.572521686553955,
|
|
"epoch": 1.396965570900603,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00048065730353847143,
|
|
"loss": 5.0792,
|
|
"mean_token_accuracy": 0.19308810383081437,
|
|
"num_tokens": 31163683.0,
|
|
"step": 17955
|
|
},
|
|
{
|
|
"entropy": 5.6317041397094725,
|
|
"epoch": 1.3973546002723205,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00048064605939815837,
|
|
"loss": 5.1616,
|
|
"mean_token_accuracy": 0.19347446858882905,
|
|
"num_tokens": 31172361.0,
|
|
"step": 17960
|
|
},
|
|
{
|
|
"entropy": 5.602168416976928,
|
|
"epoch": 1.3977436296440382,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004806348121374936,
|
|
"loss": 5.0034,
|
|
"mean_token_accuracy": 0.20054301917552947,
|
|
"num_tokens": 31180572.0,
|
|
"step": 17965
|
|
},
|
|
{
|
|
"entropy": 5.522147560119629,
|
|
"epoch": 1.3981326590157557,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004806235617566479,
|
|
"loss": 5.0134,
|
|
"mean_token_accuracy": 0.19778368771076202,
|
|
"num_tokens": 31188751.0,
|
|
"step": 17970
|
|
},
|
|
{
|
|
"entropy": 5.653079319000244,
|
|
"epoch": 1.3985216883874734,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000480612308255792,
|
|
"loss": 5.2122,
|
|
"mean_token_accuracy": 0.18623577207326888,
|
|
"num_tokens": 31197762.0,
|
|
"step": 17975
|
|
},
|
|
{
|
|
"entropy": 5.67055115699768,
|
|
"epoch": 1.3989107177591908,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00048060105163509647,
|
|
"loss": 5.1405,
|
|
"mean_token_accuracy": 0.19143532663583757,
|
|
"num_tokens": 31207203.0,
|
|
"step": 17980
|
|
},
|
|
{
|
|
"entropy": 5.684044122695923,
|
|
"epoch": 1.3992997471309083,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004805897918947323,
|
|
"loss": 5.1061,
|
|
"mean_token_accuracy": 0.1947082608938217,
|
|
"num_tokens": 31215711.0,
|
|
"step": 17985
|
|
},
|
|
{
|
|
"entropy": 5.602418899536133,
|
|
"epoch": 1.399688776502626,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004805785290348702,
|
|
"loss": 5.0652,
|
|
"mean_token_accuracy": 0.19409611374139785,
|
|
"num_tokens": 31224564.0,
|
|
"step": 17990
|
|
},
|
|
{
|
|
"entropy": 5.5717569351196286,
|
|
"epoch": 1.4000778058743435,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00048056726305568124,
|
|
"loss": 5.043,
|
|
"mean_token_accuracy": 0.1928005561232567,
|
|
"num_tokens": 31233252.0,
|
|
"step": 17995
|
|
},
|
|
{
|
|
"entropy": 5.622393369674683,
|
|
"epoch": 1.400466835246061,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00048055599395733617,
|
|
"loss": 5.1404,
|
|
"mean_token_accuracy": 0.1910122126340866,
|
|
"num_tokens": 31242539.0,
|
|
"step": 18000
|
|
},
|
|
{
|
|
"epoch": 1.400466835246061,
|
|
"eval_entropy": 5.429286362553469,
|
|
"eval_loss": 5.153907775878906,
|
|
"eval_mean_token_accuracy": 0.19979570700900845,
|
|
"eval_num_tokens": 31242539.0,
|
|
"eval_runtime": 21.6061,
|
|
"eval_samples_per_second": 1923.435,
|
|
"eval_steps_per_second": 240.441,
|
|
"step": 18000
|
|
},
|
|
{
|
|
"entropy": 5.65056209564209,
|
|
"epoch": 1.4008558646177787,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00048054472174000615,
|
|
"loss": 5.1001,
|
|
"mean_token_accuracy": 0.1949731782078743,
|
|
"num_tokens": 31250770.0,
|
|
"step": 18005
|
|
},
|
|
{
|
|
"entropy": 5.578313302993775,
|
|
"epoch": 1.4012448939894961,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00048053344640386207,
|
|
"loss": 5.0429,
|
|
"mean_token_accuracy": 0.20055692493915558,
|
|
"num_tokens": 31259507.0,
|
|
"step": 18010
|
|
},
|
|
{
|
|
"entropy": 5.611670923233032,
|
|
"epoch": 1.4016339233612138,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00048052216794907505,
|
|
"loss": 5.144,
|
|
"mean_token_accuracy": 0.19261469095945358,
|
|
"num_tokens": 31268106.0,
|
|
"step": 18015
|
|
},
|
|
{
|
|
"entropy": 5.507248783111573,
|
|
"epoch": 1.4020229527329313,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00048051088637581624,
|
|
"loss": 5.0425,
|
|
"mean_token_accuracy": 0.19696250557899475,
|
|
"num_tokens": 31276495.0,
|
|
"step": 18020
|
|
},
|
|
{
|
|
"entropy": 5.639213037490845,
|
|
"epoch": 1.402411982104649,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000480499601684257,
|
|
"loss": 5.1316,
|
|
"mean_token_accuracy": 0.18737502992153168,
|
|
"num_tokens": 31284962.0,
|
|
"step": 18025
|
|
},
|
|
{
|
|
"entropy": 5.6458573818206785,
|
|
"epoch": 1.4028010114763665,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004804883138745682,
|
|
"loss": 5.1704,
|
|
"mean_token_accuracy": 0.18758513033390045,
|
|
"num_tokens": 31294497.0,
|
|
"step": 18030
|
|
},
|
|
{
|
|
"entropy": 5.593687057495117,
|
|
"epoch": 1.403190040848084,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004804770229469214,
|
|
"loss": 5.0873,
|
|
"mean_token_accuracy": 0.1968716114759445,
|
|
"num_tokens": 31302607.0,
|
|
"step": 18035
|
|
},
|
|
{
|
|
"entropy": 5.661804866790772,
|
|
"epoch": 1.4035790702198017,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004804657289014878,
|
|
"loss": 5.1457,
|
|
"mean_token_accuracy": 0.19137624949216842,
|
|
"num_tokens": 31311989.0,
|
|
"step": 18040
|
|
},
|
|
{
|
|
"entropy": 5.676852560043335,
|
|
"epoch": 1.4039680995915191,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00048045443173843884,
|
|
"loss": 5.0587,
|
|
"mean_token_accuracy": 0.19819005131721495,
|
|
"num_tokens": 31320681.0,
|
|
"step": 18045
|
|
},
|
|
{
|
|
"entropy": 5.6062075138092045,
|
|
"epoch": 1.4043571289632366,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00048044313145794587,
|
|
"loss": 5.0871,
|
|
"mean_token_accuracy": 0.19399428516626357,
|
|
"num_tokens": 31328985.0,
|
|
"step": 18050
|
|
},
|
|
{
|
|
"entropy": 5.583251905441284,
|
|
"epoch": 1.4047461583349543,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00048043182806018034,
|
|
"loss": 5.0359,
|
|
"mean_token_accuracy": 0.19411151856184006,
|
|
"num_tokens": 31337486.0,
|
|
"step": 18055
|
|
},
|
|
{
|
|
"entropy": 5.608684492111206,
|
|
"epoch": 1.4051351877066718,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00048042052154531384,
|
|
"loss": 5.1453,
|
|
"mean_token_accuracy": 0.1958534985780716,
|
|
"num_tokens": 31345831.0,
|
|
"step": 18060
|
|
},
|
|
{
|
|
"entropy": 5.571682929992676,
|
|
"epoch": 1.4055242170783895,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004804092119135179,
|
|
"loss": 5.0368,
|
|
"mean_token_accuracy": 0.20379883348941802,
|
|
"num_tokens": 31354791.0,
|
|
"step": 18065
|
|
},
|
|
{
|
|
"entropy": 5.566554880142212,
|
|
"epoch": 1.405913246450107,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004803978991649641,
|
|
"loss": 4.9957,
|
|
"mean_token_accuracy": 0.20051505863666536,
|
|
"num_tokens": 31362652.0,
|
|
"step": 18070
|
|
},
|
|
{
|
|
"entropy": 5.559219646453857,
|
|
"epoch": 1.4063022758218247,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00048038658329982404,
|
|
"loss": 5.0968,
|
|
"mean_token_accuracy": 0.19080246835947037,
|
|
"num_tokens": 31371439.0,
|
|
"step": 18075
|
|
},
|
|
{
|
|
"entropy": 5.701272916793823,
|
|
"epoch": 1.4066913051935421,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004803752643182695,
|
|
"loss": 5.106,
|
|
"mean_token_accuracy": 0.1903628170490265,
|
|
"num_tokens": 31380039.0,
|
|
"step": 18080
|
|
},
|
|
{
|
|
"entropy": 5.662473726272583,
|
|
"epoch": 1.4070803345652596,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004803639422204723,
|
|
"loss": 5.2068,
|
|
"mean_token_accuracy": 0.18122496753931044,
|
|
"num_tokens": 31389318.0,
|
|
"step": 18085
|
|
},
|
|
{
|
|
"entropy": 5.623923587799072,
|
|
"epoch": 1.4074693639369773,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004803526170066041,
|
|
"loss": 5.0892,
|
|
"mean_token_accuracy": 0.19313371181488037,
|
|
"num_tokens": 31398442.0,
|
|
"step": 18090
|
|
},
|
|
{
|
|
"entropy": 5.623306941986084,
|
|
"epoch": 1.4078583933086948,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00048034128867683674,
|
|
"loss": 5.0897,
|
|
"mean_token_accuracy": 0.19325269460678102,
|
|
"num_tokens": 31406566.0,
|
|
"step": 18095
|
|
},
|
|
{
|
|
"entropy": 5.607749891281128,
|
|
"epoch": 1.4082474226804123,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004803299572313422,
|
|
"loss": 5.1523,
|
|
"mean_token_accuracy": 0.18824519217014313,
|
|
"num_tokens": 31415207.0,
|
|
"step": 18100
|
|
},
|
|
{
|
|
"entropy": 5.692129611968994,
|
|
"epoch": 1.40863645205213,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004803186226702924,
|
|
"loss": 5.1372,
|
|
"mean_token_accuracy": 0.18130026161670684,
|
|
"num_tokens": 31424175.0,
|
|
"step": 18105
|
|
},
|
|
{
|
|
"entropy": 5.656840801239014,
|
|
"epoch": 1.4090254814238474,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004803072849938592,
|
|
"loss": 5.1649,
|
|
"mean_token_accuracy": 0.18290869295597076,
|
|
"num_tokens": 31434022.0,
|
|
"step": 18110
|
|
},
|
|
{
|
|
"entropy": 5.665083551406861,
|
|
"epoch": 1.4094145107955651,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004802959442022149,
|
|
"loss": 5.0415,
|
|
"mean_token_accuracy": 0.19713061600923537,
|
|
"num_tokens": 31442838.0,
|
|
"step": 18115
|
|
},
|
|
{
|
|
"entropy": 5.638256502151489,
|
|
"epoch": 1.4098035401672826,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00048028460029553126,
|
|
"loss": 5.0545,
|
|
"mean_token_accuracy": 0.1910913735628128,
|
|
"num_tokens": 31451482.0,
|
|
"step": 18120
|
|
},
|
|
{
|
|
"entropy": 5.612159204483032,
|
|
"epoch": 1.4101925695390003,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00048027325327398065,
|
|
"loss": 5.0966,
|
|
"mean_token_accuracy": 0.19379920065402984,
|
|
"num_tokens": 31460234.0,
|
|
"step": 18125
|
|
},
|
|
{
|
|
"entropy": 5.603456258773804,
|
|
"epoch": 1.4105815989107178,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004802619031377351,
|
|
"loss": 5.046,
|
|
"mean_token_accuracy": 0.20101485550403594,
|
|
"num_tokens": 31470466.0,
|
|
"step": 18130
|
|
},
|
|
{
|
|
"entropy": 5.54808406829834,
|
|
"epoch": 1.4109706282824352,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00048025054988696684,
|
|
"loss": 5.1508,
|
|
"mean_token_accuracy": 0.19007025063037872,
|
|
"num_tokens": 31480901.0,
|
|
"step": 18135
|
|
},
|
|
{
|
|
"entropy": 5.616864156723023,
|
|
"epoch": 1.411359657654153,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00048023919352184827,
|
|
"loss": 5.0591,
|
|
"mean_token_accuracy": 0.18969772458076478,
|
|
"num_tokens": 31490329.0,
|
|
"step": 18140
|
|
},
|
|
{
|
|
"entropy": 5.579936361312866,
|
|
"epoch": 1.4117486870258704,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00048022783404255156,
|
|
"loss": 5.1002,
|
|
"mean_token_accuracy": 0.1935671091079712,
|
|
"num_tokens": 31499519.0,
|
|
"step": 18145
|
|
},
|
|
{
|
|
"entropy": 5.624794054031372,
|
|
"epoch": 1.412137716397588,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004802164714492491,
|
|
"loss": 5.1373,
|
|
"mean_token_accuracy": 0.19408158510923385,
|
|
"num_tokens": 31507899.0,
|
|
"step": 18150
|
|
},
|
|
{
|
|
"entropy": 5.700310182571411,
|
|
"epoch": 1.4125267457693056,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00048020510574211335,
|
|
"loss": 5.2804,
|
|
"mean_token_accuracy": 0.179886831343174,
|
|
"num_tokens": 31517861.0,
|
|
"step": 18155
|
|
},
|
|
{
|
|
"entropy": 5.656043863296508,
|
|
"epoch": 1.412915775141023,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00048019373692131674,
|
|
"loss": 5.1562,
|
|
"mean_token_accuracy": 0.18432103246450424,
|
|
"num_tokens": 31527273.0,
|
|
"step": 18160
|
|
},
|
|
{
|
|
"entropy": 5.660457563400269,
|
|
"epoch": 1.4133048045127408,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00048018236498703176,
|
|
"loss": 5.0776,
|
|
"mean_token_accuracy": 0.19688465148210527,
|
|
"num_tokens": 31536221.0,
|
|
"step": 18165
|
|
},
|
|
{
|
|
"entropy": 5.589381694793701,
|
|
"epoch": 1.4136938338844582,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00048017098993943097,
|
|
"loss": 5.0384,
|
|
"mean_token_accuracy": 0.19620970338582994,
|
|
"num_tokens": 31544329.0,
|
|
"step": 18170
|
|
},
|
|
{
|
|
"entropy": 5.6423393249511715,
|
|
"epoch": 1.414082863256176,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000480159611778687,
|
|
"loss": 5.1152,
|
|
"mean_token_accuracy": 0.19195820093154908,
|
|
"num_tokens": 31552323.0,
|
|
"step": 18175
|
|
},
|
|
{
|
|
"entropy": 5.620124769210816,
|
|
"epoch": 1.4144718926278934,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00048014823050497243,
|
|
"loss": 5.0736,
|
|
"mean_token_accuracy": 0.19446938186883928,
|
|
"num_tokens": 31560432.0,
|
|
"step": 18180
|
|
},
|
|
{
|
|
"entropy": 5.5212007522583,
|
|
"epoch": 1.4148609219996109,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00048013684611846,
|
|
"loss": 5.0513,
|
|
"mean_token_accuracy": 0.19666382521390915,
|
|
"num_tokens": 31569294.0,
|
|
"step": 18185
|
|
},
|
|
{
|
|
"entropy": 5.59936637878418,
|
|
"epoch": 1.4152499513713286,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00048012545861932245,
|
|
"loss": 5.0672,
|
|
"mean_token_accuracy": 0.19645187854766846,
|
|
"num_tokens": 31577860.0,
|
|
"step": 18190
|
|
},
|
|
{
|
|
"entropy": 5.582728719711303,
|
|
"epoch": 1.415638980743046,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004801140680077325,
|
|
"loss": 5.0185,
|
|
"mean_token_accuracy": 0.19730323255062104,
|
|
"num_tokens": 31586034.0,
|
|
"step": 18195
|
|
},
|
|
{
|
|
"entropy": 5.606848239898682,
|
|
"epoch": 1.4160280101147635,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004801026742838631,
|
|
"loss": 5.0575,
|
|
"mean_token_accuracy": 0.19499358236789704,
|
|
"num_tokens": 31594911.0,
|
|
"step": 18200
|
|
},
|
|
{
|
|
"entropy": 5.622370338439941,
|
|
"epoch": 1.4164170394864812,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004800912774478871,
|
|
"loss": 5.1377,
|
|
"mean_token_accuracy": 0.18979110568761826,
|
|
"num_tokens": 31603477.0,
|
|
"step": 18205
|
|
},
|
|
{
|
|
"entropy": 5.669853544235229,
|
|
"epoch": 1.416806068858199,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004800798774999773,
|
|
"loss": 5.1092,
|
|
"mean_token_accuracy": 0.1946551099419594,
|
|
"num_tokens": 31612288.0,
|
|
"step": 18210
|
|
},
|
|
{
|
|
"entropy": 5.617135381698608,
|
|
"epoch": 1.4171950982299164,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00048006847444030686,
|
|
"loss": 5.0374,
|
|
"mean_token_accuracy": 0.20270806401968003,
|
|
"num_tokens": 31621580.0,
|
|
"step": 18215
|
|
},
|
|
{
|
|
"entropy": 5.555125713348389,
|
|
"epoch": 1.4175841276016339,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004800570682690487,
|
|
"loss": 5.0428,
|
|
"mean_token_accuracy": 0.18795739561319352,
|
|
"num_tokens": 31629860.0,
|
|
"step": 18220
|
|
},
|
|
{
|
|
"entropy": 5.686068058013916,
|
|
"epoch": 1.4179731569733516,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004800456589863759,
|
|
"loss": 5.1157,
|
|
"mean_token_accuracy": 0.1867443472146988,
|
|
"num_tokens": 31639012.0,
|
|
"step": 18225
|
|
},
|
|
{
|
|
"entropy": 5.632424545288086,
|
|
"epoch": 1.418362186345069,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004800342465924616,
|
|
"loss": 5.1263,
|
|
"mean_token_accuracy": 0.19317781180143356,
|
|
"num_tokens": 31648675.0,
|
|
"step": 18230
|
|
},
|
|
{
|
|
"entropy": 5.636453104019165,
|
|
"epoch": 1.4187512157167865,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000480022831087479,
|
|
"loss": 5.0783,
|
|
"mean_token_accuracy": 0.204926760494709,
|
|
"num_tokens": 31656570.0,
|
|
"step": 18235
|
|
},
|
|
{
|
|
"entropy": 5.5677026271820065,
|
|
"epoch": 1.4191402450885042,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004800114124716012,
|
|
"loss": 5.021,
|
|
"mean_token_accuracy": 0.1986503854393959,
|
|
"num_tokens": 31665636.0,
|
|
"step": 18240
|
|
},
|
|
{
|
|
"entropy": 5.652220916748047,
|
|
"epoch": 1.4195292744602217,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004799999907450015,
|
|
"loss": 5.1445,
|
|
"mean_token_accuracy": 0.18698307126760483,
|
|
"num_tokens": 31673638.0,
|
|
"step": 18245
|
|
},
|
|
{
|
|
"entropy": 5.647220087051392,
|
|
"epoch": 1.4199183038319392,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004799885659078533,
|
|
"loss": 5.1086,
|
|
"mean_token_accuracy": 0.19938829094171523,
|
|
"num_tokens": 31681886.0,
|
|
"step": 18250
|
|
},
|
|
{
|
|
"entropy": 5.696392822265625,
|
|
"epoch": 1.4203073332036569,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004799771379603299,
|
|
"loss": 5.2431,
|
|
"mean_token_accuracy": 0.18172856718301772,
|
|
"num_tokens": 31690349.0,
|
|
"step": 18255
|
|
},
|
|
{
|
|
"entropy": 5.596795272827149,
|
|
"epoch": 1.4206963625753746,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004799657069026046,
|
|
"loss": 5.0932,
|
|
"mean_token_accuracy": 0.18580224364995956,
|
|
"num_tokens": 31699183.0,
|
|
"step": 18260
|
|
},
|
|
{
|
|
"entropy": 5.589864921569824,
|
|
"epoch": 1.421085391947092,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00047995427273485097,
|
|
"loss": 5.0729,
|
|
"mean_token_accuracy": 0.19426646828651428,
|
|
"num_tokens": 31707759.0,
|
|
"step": 18265
|
|
},
|
|
{
|
|
"entropy": 5.68631796836853,
|
|
"epoch": 1.4214744213188095,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00047994283545724247,
|
|
"loss": 5.1959,
|
|
"mean_token_accuracy": 0.1878586396574974,
|
|
"num_tokens": 31716383.0,
|
|
"step": 18270
|
|
},
|
|
{
|
|
"entropy": 5.6335736274719235,
|
|
"epoch": 1.4218634506905272,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00047993139506995273,
|
|
"loss": 5.1149,
|
|
"mean_token_accuracy": 0.18795016705989837,
|
|
"num_tokens": 31724617.0,
|
|
"step": 18275
|
|
},
|
|
{
|
|
"entropy": 5.6211004734039305,
|
|
"epoch": 1.4222524800622447,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004799199515731551,
|
|
"loss": 5.0447,
|
|
"mean_token_accuracy": 0.19736108928918839,
|
|
"num_tokens": 31732027.0,
|
|
"step": 18280
|
|
},
|
|
{
|
|
"entropy": 5.556650590896607,
|
|
"epoch": 1.4226415094339622,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00047990850496702346,
|
|
"loss": 5.0165,
|
|
"mean_token_accuracy": 0.19981116205453872,
|
|
"num_tokens": 31740707.0,
|
|
"step": 18285
|
|
},
|
|
{
|
|
"entropy": 5.614840316772461,
|
|
"epoch": 1.4230305388056799,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004798970552517314,
|
|
"loss": 5.0466,
|
|
"mean_token_accuracy": 0.19524014443159105,
|
|
"num_tokens": 31748864.0,
|
|
"step": 18290
|
|
},
|
|
{
|
|
"entropy": 5.67936749458313,
|
|
"epoch": 1.4234195681773973,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00047988560242745264,
|
|
"loss": 5.2248,
|
|
"mean_token_accuracy": 0.18662955462932587,
|
|
"num_tokens": 31758356.0,
|
|
"step": 18295
|
|
},
|
|
{
|
|
"entropy": 5.652460098266602,
|
|
"epoch": 1.423808597549115,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000479874146494361,
|
|
"loss": 5.0928,
|
|
"mean_token_accuracy": 0.20081959068775176,
|
|
"num_tokens": 31766911.0,
|
|
"step": 18300
|
|
},
|
|
{
|
|
"entropy": 5.628424596786499,
|
|
"epoch": 1.4241976269208325,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004798626874526302,
|
|
"loss": 5.1094,
|
|
"mean_token_accuracy": 0.1921548694372177,
|
|
"num_tokens": 31775551.0,
|
|
"step": 18305
|
|
},
|
|
{
|
|
"entropy": 5.655199813842773,
|
|
"epoch": 1.4245866562925502,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00047985122530243426,
|
|
"loss": 5.2528,
|
|
"mean_token_accuracy": 0.18085827976465224,
|
|
"num_tokens": 31784064.0,
|
|
"step": 18310
|
|
},
|
|
{
|
|
"entropy": 5.674431228637696,
|
|
"epoch": 1.4249756856642677,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000479839760043947,
|
|
"loss": 5.1177,
|
|
"mean_token_accuracy": 0.19235825836658477,
|
|
"num_tokens": 31792574.0,
|
|
"step": 18315
|
|
},
|
|
{
|
|
"entropy": 5.617513179779053,
|
|
"epoch": 1.4253647150359852,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00047982829167734245,
|
|
"loss": 4.9516,
|
|
"mean_token_accuracy": 0.20302326679229737,
|
|
"num_tokens": 31800331.0,
|
|
"step": 18320
|
|
},
|
|
{
|
|
"entropy": 5.56688084602356,
|
|
"epoch": 1.4257537444077029,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00047981682020279456,
|
|
"loss": 5.0276,
|
|
"mean_token_accuracy": 0.19550492763519287,
|
|
"num_tokens": 31808474.0,
|
|
"step": 18325
|
|
},
|
|
{
|
|
"entropy": 5.634739637374878,
|
|
"epoch": 1.4261427737794203,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004798053456204775,
|
|
"loss": 5.1295,
|
|
"mean_token_accuracy": 0.18659272640943528,
|
|
"num_tokens": 31817026.0,
|
|
"step": 18330
|
|
},
|
|
{
|
|
"entropy": 5.552191543579101,
|
|
"epoch": 1.4265318031511378,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004797938679305651,
|
|
"loss": 4.9773,
|
|
"mean_token_accuracy": 0.1975885584950447,
|
|
"num_tokens": 31825096.0,
|
|
"step": 18335
|
|
},
|
|
{
|
|
"entropy": 5.586865663528442,
|
|
"epoch": 1.4269208325228555,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00047978238713323193,
|
|
"loss": 5.1363,
|
|
"mean_token_accuracy": 0.19227559268474578,
|
|
"num_tokens": 31833650.0,
|
|
"step": 18340
|
|
},
|
|
{
|
|
"entropy": 5.621965312957764,
|
|
"epoch": 1.427309861894573,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00047977090322865183,
|
|
"loss": 5.0668,
|
|
"mean_token_accuracy": 0.19526671022176742,
|
|
"num_tokens": 31841803.0,
|
|
"step": 18345
|
|
},
|
|
{
|
|
"entropy": 5.662142753601074,
|
|
"epoch": 1.4276988912662907,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004797594162169993,
|
|
"loss": 5.1272,
|
|
"mean_token_accuracy": 0.19729547053575516,
|
|
"num_tokens": 31850121.0,
|
|
"step": 18350
|
|
},
|
|
{
|
|
"entropy": 5.619376516342163,
|
|
"epoch": 1.4280879206380082,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004797479260984485,
|
|
"loss": 5.0872,
|
|
"mean_token_accuracy": 0.192670339345932,
|
|
"num_tokens": 31858585.0,
|
|
"step": 18355
|
|
},
|
|
{
|
|
"entropy": 5.587238359451294,
|
|
"epoch": 1.4284769500097259,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00047973643287317386,
|
|
"loss": 5.0725,
|
|
"mean_token_accuracy": 0.19097839891910554,
|
|
"num_tokens": 31866199.0,
|
|
"step": 18360
|
|
},
|
|
{
|
|
"entropy": 5.58135027885437,
|
|
"epoch": 1.4288659793814433,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00047972493654134963,
|
|
"loss": 5.0787,
|
|
"mean_token_accuracy": 0.1959703803062439,
|
|
"num_tokens": 31875423.0,
|
|
"step": 18365
|
|
},
|
|
{
|
|
"entropy": 5.576603269577026,
|
|
"epoch": 1.4292550087531608,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00047971343710315043,
|
|
"loss": 4.9822,
|
|
"mean_token_accuracy": 0.19986646622419357,
|
|
"num_tokens": 31883110.0,
|
|
"step": 18370
|
|
},
|
|
{
|
|
"entropy": 5.550352907180786,
|
|
"epoch": 1.4296440381248785,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004797019345587506,
|
|
"loss": 5.1004,
|
|
"mean_token_accuracy": 0.19365949779748917,
|
|
"num_tokens": 31891588.0,
|
|
"step": 18375
|
|
},
|
|
{
|
|
"entropy": 5.580299806594849,
|
|
"epoch": 1.430033067496596,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004796904289083248,
|
|
"loss": 5.0493,
|
|
"mean_token_accuracy": 0.19603380858898162,
|
|
"num_tokens": 31900671.0,
|
|
"step": 18380
|
|
},
|
|
{
|
|
"entropy": 5.645295524597168,
|
|
"epoch": 1.4304220968683135,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004796789201520474,
|
|
"loss": 5.1061,
|
|
"mean_token_accuracy": 0.1948881193995476,
|
|
"num_tokens": 31909188.0,
|
|
"step": 18385
|
|
},
|
|
{
|
|
"entropy": 5.615600442886352,
|
|
"epoch": 1.4308111262400312,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00047966740829009333,
|
|
"loss": 5.0601,
|
|
"mean_token_accuracy": 0.20297318696975708,
|
|
"num_tokens": 31917607.0,
|
|
"step": 18390
|
|
},
|
|
{
|
|
"entropy": 5.626970720291138,
|
|
"epoch": 1.4312001556117486,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000479655893322637,
|
|
"loss": 5.1179,
|
|
"mean_token_accuracy": 0.18798398226499557,
|
|
"num_tokens": 31926510.0,
|
|
"step": 18395
|
|
},
|
|
{
|
|
"entropy": 5.62557282447815,
|
|
"epoch": 1.4315891849834663,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004796443752498532,
|
|
"loss": 5.1973,
|
|
"mean_token_accuracy": 0.18588899672031403,
|
|
"num_tokens": 31935550.0,
|
|
"step": 18400
|
|
},
|
|
{
|
|
"entropy": 5.697294759750366,
|
|
"epoch": 1.4319782143551838,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004796328540719169,
|
|
"loss": 5.245,
|
|
"mean_token_accuracy": 0.1828196555376053,
|
|
"num_tokens": 31944499.0,
|
|
"step": 18405
|
|
},
|
|
{
|
|
"entropy": 5.682896375656128,
|
|
"epoch": 1.4323672437269015,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004796213297890026,
|
|
"loss": 4.9934,
|
|
"mean_token_accuracy": 0.20257802605628966,
|
|
"num_tokens": 31952622.0,
|
|
"step": 18410
|
|
},
|
|
{
|
|
"entropy": 5.576907920837402,
|
|
"epoch": 1.432756273098619,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004796098024012853,
|
|
"loss": 5.0463,
|
|
"mean_token_accuracy": 0.19152364432811736,
|
|
"num_tokens": 31961606.0,
|
|
"step": 18415
|
|
},
|
|
{
|
|
"entropy": 5.591465282440185,
|
|
"epoch": 1.4331453024703364,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00047959827190894,
|
|
"loss": 5.1588,
|
|
"mean_token_accuracy": 0.1911668822169304,
|
|
"num_tokens": 31970312.0,
|
|
"step": 18420
|
|
},
|
|
{
|
|
"entropy": 5.638664960861206,
|
|
"epoch": 1.4335343318420541,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00047958673831214157,
|
|
"loss": 5.1088,
|
|
"mean_token_accuracy": 0.1924675703048706,
|
|
"num_tokens": 31978718.0,
|
|
"step": 18425
|
|
},
|
|
{
|
|
"entropy": 5.6605628490447994,
|
|
"epoch": 1.4339233612137716,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00047957520161106496,
|
|
"loss": 5.129,
|
|
"mean_token_accuracy": 0.19112288504838942,
|
|
"num_tokens": 31987451.0,
|
|
"step": 18430
|
|
},
|
|
{
|
|
"entropy": 5.630765008926391,
|
|
"epoch": 1.434312390585489,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004795636618058853,
|
|
"loss": 4.9444,
|
|
"mean_token_accuracy": 0.20537668615579605,
|
|
"num_tokens": 31994977.0,
|
|
"step": 18435
|
|
},
|
|
{
|
|
"entropy": 5.562106609344482,
|
|
"epoch": 1.4347014199572068,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004795521188967777,
|
|
"loss": 5.0107,
|
|
"mean_token_accuracy": 0.205131596326828,
|
|
"num_tokens": 32003804.0,
|
|
"step": 18440
|
|
},
|
|
{
|
|
"entropy": 5.65944094657898,
|
|
"epoch": 1.4350904493289243,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004795405728839172,
|
|
"loss": 5.157,
|
|
"mean_token_accuracy": 0.186469466984272,
|
|
"num_tokens": 32012090.0,
|
|
"step": 18445
|
|
},
|
|
{
|
|
"entropy": 5.625867509841919,
|
|
"epoch": 1.435479478700642,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004795290237674792,
|
|
"loss": 5.1,
|
|
"mean_token_accuracy": 0.19061363786458968,
|
|
"num_tokens": 32019664.0,
|
|
"step": 18450
|
|
},
|
|
{
|
|
"entropy": 5.639222145080566,
|
|
"epoch": 1.4358685080723594,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00047951747154763866,
|
|
"loss": 5.1472,
|
|
"mean_token_accuracy": 0.1914323627948761,
|
|
"num_tokens": 32028457.0,
|
|
"step": 18455
|
|
},
|
|
{
|
|
"entropy": 5.5980840682983395,
|
|
"epoch": 1.4362575374440771,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00047950591622457106,
|
|
"loss": 4.9769,
|
|
"mean_token_accuracy": 0.19838547110557556,
|
|
"num_tokens": 32036730.0,
|
|
"step": 18460
|
|
},
|
|
{
|
|
"entropy": 5.667256832122803,
|
|
"epoch": 1.4366465668157946,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00047949435779845174,
|
|
"loss": 5.157,
|
|
"mean_token_accuracy": 0.19142668843269348,
|
|
"num_tokens": 32045657.0,
|
|
"step": 18465
|
|
},
|
|
{
|
|
"entropy": 5.598685789108276,
|
|
"epoch": 1.437035596187512,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00047948279626945596,
|
|
"loss": 5.0746,
|
|
"mean_token_accuracy": 0.19695494174957276,
|
|
"num_tokens": 32053973.0,
|
|
"step": 18470
|
|
},
|
|
{
|
|
"entropy": 5.700230741500855,
|
|
"epoch": 1.4374246255592298,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00047947123163775924,
|
|
"loss": 5.1867,
|
|
"mean_token_accuracy": 0.18649926781654358,
|
|
"num_tokens": 32062833.0,
|
|
"step": 18475
|
|
},
|
|
{
|
|
"entropy": 5.58428692817688,
|
|
"epoch": 1.4378136549309473,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000479459663903537,
|
|
"loss": 5.0426,
|
|
"mean_token_accuracy": 0.20397589355707169,
|
|
"num_tokens": 32071578.0,
|
|
"step": 18480
|
|
},
|
|
{
|
|
"entropy": 5.573904037475586,
|
|
"epoch": 1.4382026843026647,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004794480930669649,
|
|
"loss": 4.9845,
|
|
"mean_token_accuracy": 0.19611933082342148,
|
|
"num_tokens": 32079847.0,
|
|
"step": 18485
|
|
},
|
|
{
|
|
"entropy": 5.596569156646728,
|
|
"epoch": 1.4385917136743824,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004794365191282183,
|
|
"loss": 5.0594,
|
|
"mean_token_accuracy": 0.1885624721646309,
|
|
"num_tokens": 32089751.0,
|
|
"step": 18490
|
|
},
|
|
{
|
|
"entropy": 5.676380157470703,
|
|
"epoch": 1.4389807430461,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00047942494208747297,
|
|
"loss": 5.2091,
|
|
"mean_token_accuracy": 0.18499039858579636,
|
|
"num_tokens": 32097791.0,
|
|
"step": 18495
|
|
},
|
|
{
|
|
"entropy": 5.6378261089324955,
|
|
"epoch": 1.4393697724178176,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004794133619449045,
|
|
"loss": 5.0123,
|
|
"mean_token_accuracy": 0.20201625674962997,
|
|
"num_tokens": 32106417.0,
|
|
"step": 18500
|
|
},
|
|
{
|
|
"entropy": 5.586153173446656,
|
|
"epoch": 1.439758801789535,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004794017787006886,
|
|
"loss": 5.1074,
|
|
"mean_token_accuracy": 0.18926345109939574,
|
|
"num_tokens": 32115035.0,
|
|
"step": 18505
|
|
},
|
|
{
|
|
"entropy": 5.579412221908569,
|
|
"epoch": 1.4401478311612528,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000479390192355001,
|
|
"loss": 5.0476,
|
|
"mean_token_accuracy": 0.19102127999067306,
|
|
"num_tokens": 32123704.0,
|
|
"step": 18510
|
|
},
|
|
{
|
|
"entropy": 5.6527947902679445,
|
|
"epoch": 1.4405368605329703,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004793786029080176,
|
|
"loss": 5.1396,
|
|
"mean_token_accuracy": 0.1928951308131218,
|
|
"num_tokens": 32132672.0,
|
|
"step": 18515
|
|
},
|
|
{
|
|
"entropy": 5.603618097305298,
|
|
"epoch": 1.4409258899046877,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004793670103599143,
|
|
"loss": 5.0526,
|
|
"mean_token_accuracy": 0.196324722468853,
|
|
"num_tokens": 32142135.0,
|
|
"step": 18520
|
|
},
|
|
{
|
|
"entropy": 5.656747150421142,
|
|
"epoch": 1.4413149192764054,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00047935541471086677,
|
|
"loss": 5.1518,
|
|
"mean_token_accuracy": 0.17748203575611116,
|
|
"num_tokens": 32151261.0,
|
|
"step": 18525
|
|
},
|
|
{
|
|
"entropy": 5.587941455841064,
|
|
"epoch": 1.441703948648123,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004793438159610511,
|
|
"loss": 5.0467,
|
|
"mean_token_accuracy": 0.1954227790236473,
|
|
"num_tokens": 32159454.0,
|
|
"step": 18530
|
|
},
|
|
{
|
|
"entropy": 5.678868389129638,
|
|
"epoch": 1.4420929780198404,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00047933221411064334,
|
|
"loss": 5.1374,
|
|
"mean_token_accuracy": 0.18622193336486817,
|
|
"num_tokens": 32168706.0,
|
|
"step": 18535
|
|
},
|
|
{
|
|
"entropy": 5.732566022872925,
|
|
"epoch": 1.442482007391558,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004793206091598194,
|
|
"loss": 5.1976,
|
|
"mean_token_accuracy": 0.1847882091999054,
|
|
"num_tokens": 32177892.0,
|
|
"step": 18540
|
|
},
|
|
{
|
|
"entropy": 5.631687307357788,
|
|
"epoch": 1.4428710367632755,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004793090011087554,
|
|
"loss": 5.0835,
|
|
"mean_token_accuracy": 0.19265912622213363,
|
|
"num_tokens": 32186081.0,
|
|
"step": 18545
|
|
},
|
|
{
|
|
"entropy": 5.631122875213623,
|
|
"epoch": 1.4432600661349932,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00047929738995762755,
|
|
"loss": 5.0564,
|
|
"mean_token_accuracy": 0.1973811626434326,
|
|
"num_tokens": 32193778.0,
|
|
"step": 18550
|
|
},
|
|
{
|
|
"entropy": 5.5404986381530765,
|
|
"epoch": 1.4436490955067107,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000479285775706612,
|
|
"loss": 5.0342,
|
|
"mean_token_accuracy": 0.20107520520687103,
|
|
"num_tokens": 32202773.0,
|
|
"step": 18555
|
|
},
|
|
{
|
|
"entropy": 5.617558765411377,
|
|
"epoch": 1.4440381248784284,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00047927415835588496,
|
|
"loss": 5.0676,
|
|
"mean_token_accuracy": 0.19942388385534288,
|
|
"num_tokens": 32212105.0,
|
|
"step": 18560
|
|
},
|
|
{
|
|
"entropy": 5.570112943649292,
|
|
"epoch": 1.444427154250146,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00047926253790562265,
|
|
"loss": 4.9492,
|
|
"mean_token_accuracy": 0.20351517498493193,
|
|
"num_tokens": 32220550.0,
|
|
"step": 18565
|
|
},
|
|
{
|
|
"entropy": 5.567720031738281,
|
|
"epoch": 1.4448161836218634,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00047925091435600147,
|
|
"loss": 4.9395,
|
|
"mean_token_accuracy": 0.19839542508125305,
|
|
"num_tokens": 32228562.0,
|
|
"step": 18570
|
|
},
|
|
{
|
|
"entropy": 5.606336688995361,
|
|
"epoch": 1.445205212993581,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00047923928770719776,
|
|
"loss": 5.1077,
|
|
"mean_token_accuracy": 0.19797687083482743,
|
|
"num_tokens": 32237172.0,
|
|
"step": 18575
|
|
},
|
|
{
|
|
"entropy": 5.594252729415894,
|
|
"epoch": 1.4455942423652985,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00047922765795938797,
|
|
"loss": 5.0936,
|
|
"mean_token_accuracy": 0.19104631394147872,
|
|
"num_tokens": 32246211.0,
|
|
"step": 18580
|
|
},
|
|
{
|
|
"entropy": 5.534573268890381,
|
|
"epoch": 1.445983271737016,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004792160251127485,
|
|
"loss": 5.0193,
|
|
"mean_token_accuracy": 0.20064648985862732,
|
|
"num_tokens": 32255366.0,
|
|
"step": 18585
|
|
},
|
|
{
|
|
"entropy": 5.708288764953613,
|
|
"epoch": 1.4463723011087337,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00047920438916745586,
|
|
"loss": 5.1926,
|
|
"mean_token_accuracy": 0.18635097593069078,
|
|
"num_tokens": 32264342.0,
|
|
"step": 18590
|
|
},
|
|
{
|
|
"entropy": 5.649402761459351,
|
|
"epoch": 1.4467613304804512,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004791927501236866,
|
|
"loss": 5.1161,
|
|
"mean_token_accuracy": 0.19162465631961823,
|
|
"num_tokens": 32273184.0,
|
|
"step": 18595
|
|
},
|
|
{
|
|
"entropy": 5.640807628631592,
|
|
"epoch": 1.4471503598521689,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00047918110798161754,
|
|
"loss": 5.1552,
|
|
"mean_token_accuracy": 0.1887485519051552,
|
|
"num_tokens": 32282303.0,
|
|
"step": 18600
|
|
},
|
|
{
|
|
"entropy": 5.624294090270996,
|
|
"epoch": 1.4475393892238864,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00047916946274142503,
|
|
"loss": 5.0258,
|
|
"mean_token_accuracy": 0.20135403722524642,
|
|
"num_tokens": 32291118.0,
|
|
"step": 18605
|
|
},
|
|
{
|
|
"entropy": 5.660922336578369,
|
|
"epoch": 1.447928418595604,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00047915781440328593,
|
|
"loss": 5.0852,
|
|
"mean_token_accuracy": 0.18727379739284516,
|
|
"num_tokens": 32299746.0,
|
|
"step": 18610
|
|
},
|
|
{
|
|
"entropy": 5.605949115753174,
|
|
"epoch": 1.4483174479673215,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004791461629673769,
|
|
"loss": 5.0953,
|
|
"mean_token_accuracy": 0.19682133048772812,
|
|
"num_tokens": 32308515.0,
|
|
"step": 18615
|
|
},
|
|
{
|
|
"entropy": 5.65838851928711,
|
|
"epoch": 1.448706477339039,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004791345084338748,
|
|
"loss": 5.199,
|
|
"mean_token_accuracy": 0.1900344505906105,
|
|
"num_tokens": 32317607.0,
|
|
"step": 18620
|
|
},
|
|
{
|
|
"entropy": 5.669473266601562,
|
|
"epoch": 1.4490955067107567,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004791228508029565,
|
|
"loss": 5.1046,
|
|
"mean_token_accuracy": 0.19572567492723464,
|
|
"num_tokens": 32325822.0,
|
|
"step": 18625
|
|
},
|
|
{
|
|
"entropy": 5.672076082229614,
|
|
"epoch": 1.4494845360824742,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00047911119007479873,
|
|
"loss": 5.1921,
|
|
"mean_token_accuracy": 0.1872390791773796,
|
|
"num_tokens": 32336297.0,
|
|
"step": 18630
|
|
},
|
|
{
|
|
"entropy": 5.614063358306884,
|
|
"epoch": 1.4498735654541917,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00047909952624957866,
|
|
"loss": 5.0673,
|
|
"mean_token_accuracy": 0.19189515411853791,
|
|
"num_tokens": 32344306.0,
|
|
"step": 18635
|
|
},
|
|
{
|
|
"entropy": 5.6910542964935305,
|
|
"epoch": 1.4502625948259094,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000479087859327473,
|
|
"loss": 5.182,
|
|
"mean_token_accuracy": 0.1891653671860695,
|
|
"num_tokens": 32353668.0,
|
|
"step": 18640
|
|
},
|
|
{
|
|
"entropy": 5.66265377998352,
|
|
"epoch": 1.450651624197627,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000479076189308659,
|
|
"loss": 5.0744,
|
|
"mean_token_accuracy": 0.19263841062784196,
|
|
"num_tokens": 32361563.0,
|
|
"step": 18645
|
|
},
|
|
{
|
|
"entropy": 5.682370519638061,
|
|
"epoch": 1.4510406535693445,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00047906451619331364,
|
|
"loss": 5.1791,
|
|
"mean_token_accuracy": 0.18816327899694443,
|
|
"num_tokens": 32369612.0,
|
|
"step": 18650
|
|
},
|
|
{
|
|
"entropy": 5.604054594039917,
|
|
"epoch": 1.451429682941062,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00047905283998161404,
|
|
"loss": 4.9846,
|
|
"mean_token_accuracy": 0.2052964448928833,
|
|
"num_tokens": 32379013.0,
|
|
"step": 18655
|
|
},
|
|
{
|
|
"entropy": 5.587451457977295,
|
|
"epoch": 1.4518187123127797,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00047904116067373743,
|
|
"loss": 5.0885,
|
|
"mean_token_accuracy": 0.19270721971988677,
|
|
"num_tokens": 32387933.0,
|
|
"step": 18660
|
|
},
|
|
{
|
|
"entropy": 5.644082641601562,
|
|
"epoch": 1.4522077416844972,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004790294782698609,
|
|
"loss": 5.1323,
|
|
"mean_token_accuracy": 0.19549304395914077,
|
|
"num_tokens": 32395669.0,
|
|
"step": 18665
|
|
},
|
|
{
|
|
"entropy": 5.5467259883880615,
|
|
"epoch": 1.4525967710562147,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004790177927701618,
|
|
"loss": 4.9841,
|
|
"mean_token_accuracy": 0.20273464620113374,
|
|
"num_tokens": 32403676.0,
|
|
"step": 18670
|
|
},
|
|
{
|
|
"entropy": 5.637514305114746,
|
|
"epoch": 1.4529858004279324,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004790061041748174,
|
|
"loss": 5.064,
|
|
"mean_token_accuracy": 0.19444344639778138,
|
|
"num_tokens": 32412089.0,
|
|
"step": 18675
|
|
},
|
|
{
|
|
"entropy": 5.637416219711303,
|
|
"epoch": 1.4533748297996498,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004789944124840051,
|
|
"loss": 5.0345,
|
|
"mean_token_accuracy": 0.20215693414211272,
|
|
"num_tokens": 32420357.0,
|
|
"step": 18680
|
|
},
|
|
{
|
|
"entropy": 5.641674947738648,
|
|
"epoch": 1.4537638591713673,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004789827176979022,
|
|
"loss": 5.124,
|
|
"mean_token_accuracy": 0.1940718859434128,
|
|
"num_tokens": 32429118.0,
|
|
"step": 18685
|
|
},
|
|
{
|
|
"entropy": 5.666227865219116,
|
|
"epoch": 1.454152888543085,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004789710198166864,
|
|
"loss": 5.0413,
|
|
"mean_token_accuracy": 0.19791026115417482,
|
|
"num_tokens": 32437266.0,
|
|
"step": 18690
|
|
},
|
|
{
|
|
"entropy": 5.650438737869263,
|
|
"epoch": 1.4545419179148027,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00047895931884053497,
|
|
"loss": 5.1451,
|
|
"mean_token_accuracy": 0.18620180040597917,
|
|
"num_tokens": 32446014.0,
|
|
"step": 18695
|
|
},
|
|
{
|
|
"entropy": 5.608058643341065,
|
|
"epoch": 1.4549309472865202,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00047894761476962547,
|
|
"loss": 5.1222,
|
|
"mean_token_accuracy": 0.19133968651294708,
|
|
"num_tokens": 32454591.0,
|
|
"step": 18700
|
|
},
|
|
{
|
|
"entropy": 5.6327752590179445,
|
|
"epoch": 1.4553199766582376,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00047893590760413545,
|
|
"loss": 5.0818,
|
|
"mean_token_accuracy": 0.19855124056339263,
|
|
"num_tokens": 32462748.0,
|
|
"step": 18705
|
|
},
|
|
{
|
|
"entropy": 5.619998121261597,
|
|
"epoch": 1.4557090060299553,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00047892419734424276,
|
|
"loss": 5.0514,
|
|
"mean_token_accuracy": 0.19774118363857268,
|
|
"num_tokens": 32471792.0,
|
|
"step": 18710
|
|
},
|
|
{
|
|
"entropy": 5.629866409301758,
|
|
"epoch": 1.4560980354016728,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00047891248399012495,
|
|
"loss": 5.1246,
|
|
"mean_token_accuracy": 0.19463704377412797,
|
|
"num_tokens": 32480804.0,
|
|
"step": 18715
|
|
},
|
|
{
|
|
"entropy": 5.662797212600708,
|
|
"epoch": 1.4564870647733903,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004789007675419597,
|
|
"loss": 5.0797,
|
|
"mean_token_accuracy": 0.190041483938694,
|
|
"num_tokens": 32489591.0,
|
|
"step": 18720
|
|
},
|
|
{
|
|
"entropy": 5.6002167701721195,
|
|
"epoch": 1.456876094145108,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00047888904799992486,
|
|
"loss": 5.0887,
|
|
"mean_token_accuracy": 0.19588097780942917,
|
|
"num_tokens": 32498164.0,
|
|
"step": 18725
|
|
},
|
|
{
|
|
"entropy": 5.572938251495361,
|
|
"epoch": 1.4572651235168255,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00047887732536419826,
|
|
"loss": 4.9163,
|
|
"mean_token_accuracy": 0.20508276373147966,
|
|
"num_tokens": 32505909.0,
|
|
"step": 18730
|
|
},
|
|
{
|
|
"entropy": 5.56914005279541,
|
|
"epoch": 1.4576541528885432,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004788655996349577,
|
|
"loss": 5.0507,
|
|
"mean_token_accuracy": 0.19836744666099548,
|
|
"num_tokens": 32513990.0,
|
|
"step": 18735
|
|
},
|
|
{
|
|
"entropy": 5.54734354019165,
|
|
"epoch": 1.4580431822602606,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00047885387081238125,
|
|
"loss": 5.0935,
|
|
"mean_token_accuracy": 0.1966705337166786,
|
|
"num_tokens": 32522932.0,
|
|
"step": 18740
|
|
},
|
|
{
|
|
"entropy": 5.586341333389282,
|
|
"epoch": 1.4584322116319783,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004788421388966467,
|
|
"loss": 5.1631,
|
|
"mean_token_accuracy": 0.18542364984750748,
|
|
"num_tokens": 32530953.0,
|
|
"step": 18745
|
|
},
|
|
{
|
|
"entropy": 5.598444080352783,
|
|
"epoch": 1.4588212410036958,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00047883040388793207,
|
|
"loss": 5.0249,
|
|
"mean_token_accuracy": 0.1909759059548378,
|
|
"num_tokens": 32539812.0,
|
|
"step": 18750
|
|
},
|
|
{
|
|
"entropy": 5.590904426574707,
|
|
"epoch": 1.4592102703754133,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00047881866578641563,
|
|
"loss": 5.004,
|
|
"mean_token_accuracy": 0.19597628116607665,
|
|
"num_tokens": 32548425.0,
|
|
"step": 18755
|
|
},
|
|
{
|
|
"entropy": 5.572804641723633,
|
|
"epoch": 1.459599299747131,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004788069245922753,
|
|
"loss": 5.0602,
|
|
"mean_token_accuracy": 0.196938718855381,
|
|
"num_tokens": 32557619.0,
|
|
"step": 18760
|
|
},
|
|
{
|
|
"entropy": 5.631060171127319,
|
|
"epoch": 1.4599883291188485,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004787951803056893,
|
|
"loss": 5.0974,
|
|
"mean_token_accuracy": 0.1899582639336586,
|
|
"num_tokens": 32565602.0,
|
|
"step": 18765
|
|
},
|
|
{
|
|
"entropy": 5.640539216995239,
|
|
"epoch": 1.460377358490566,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004787834329268358,
|
|
"loss": 5.0929,
|
|
"mean_token_accuracy": 0.190221931040287,
|
|
"num_tokens": 32573691.0,
|
|
"step": 18770
|
|
},
|
|
{
|
|
"entropy": 5.6178418636322025,
|
|
"epoch": 1.4607663878622836,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000478771682455893,
|
|
"loss": 5.1855,
|
|
"mean_token_accuracy": 0.18590253591537476,
|
|
"num_tokens": 32582642.0,
|
|
"step": 18775
|
|
},
|
|
{
|
|
"entropy": 5.6502768993377686,
|
|
"epoch": 1.461155417234001,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004787599288930393,
|
|
"loss": 5.0887,
|
|
"mean_token_accuracy": 0.193520687520504,
|
|
"num_tokens": 32591328.0,
|
|
"step": 18780
|
|
},
|
|
{
|
|
"entropy": 5.607243824005127,
|
|
"epoch": 1.4615444466057188,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000478748172238453,
|
|
"loss": 5.0334,
|
|
"mean_token_accuracy": 0.1931418925523758,
|
|
"num_tokens": 32599286.0,
|
|
"step": 18785
|
|
},
|
|
{
|
|
"entropy": 5.660870933532715,
|
|
"epoch": 1.4619334759774363,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004787364124923125,
|
|
"loss": 5.2085,
|
|
"mean_token_accuracy": 0.18378716260194777,
|
|
"num_tokens": 32608156.0,
|
|
"step": 18790
|
|
},
|
|
{
|
|
"entropy": 5.627944231033325,
|
|
"epoch": 1.462322505349154,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00047872464965479625,
|
|
"loss": 5.0326,
|
|
"mean_token_accuracy": 0.1981569692492485,
|
|
"num_tokens": 32616134.0,
|
|
"step": 18795
|
|
},
|
|
{
|
|
"entropy": 5.623494815826416,
|
|
"epoch": 1.4627115347208715,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004787128837260826,
|
|
"loss": 5.0649,
|
|
"mean_token_accuracy": 0.19462388902902603,
|
|
"num_tokens": 32624711.0,
|
|
"step": 18800
|
|
},
|
|
{
|
|
"entropy": 5.609109354019165,
|
|
"epoch": 1.463100564092589,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004787011147063503,
|
|
"loss": 5.0845,
|
|
"mean_token_accuracy": 0.1947449803352356,
|
|
"num_tokens": 32633049.0,
|
|
"step": 18805
|
|
},
|
|
{
|
|
"entropy": 5.604067325592041,
|
|
"epoch": 1.4634895934643066,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004786893425957777,
|
|
"loss": 5.0366,
|
|
"mean_token_accuracy": 0.19538322240114211,
|
|
"num_tokens": 32641173.0,
|
|
"step": 18810
|
|
},
|
|
{
|
|
"entropy": 5.611535978317261,
|
|
"epoch": 1.463878622836024,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004786775673945436,
|
|
"loss": 5.0265,
|
|
"mean_token_accuracy": 0.19927253425121308,
|
|
"num_tokens": 32650275.0,
|
|
"step": 18815
|
|
},
|
|
{
|
|
"entropy": 5.623269271850586,
|
|
"epoch": 1.4642676522077416,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00047866578910282656,
|
|
"loss": 5.0394,
|
|
"mean_token_accuracy": 0.20161254853010177,
|
|
"num_tokens": 32658675.0,
|
|
"step": 18820
|
|
},
|
|
{
|
|
"entropy": 5.5783905506134035,
|
|
"epoch": 1.4646566815794593,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00047865400772080535,
|
|
"loss": 5.0478,
|
|
"mean_token_accuracy": 0.1950514480471611,
|
|
"num_tokens": 32666643.0,
|
|
"step": 18825
|
|
},
|
|
{
|
|
"entropy": 5.569488525390625,
|
|
"epoch": 1.4650457109511767,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00047864222324865875,
|
|
"loss": 4.964,
|
|
"mean_token_accuracy": 0.1971247375011444,
|
|
"num_tokens": 32674791.0,
|
|
"step": 18830
|
|
},
|
|
{
|
|
"entropy": 5.621426916122436,
|
|
"epoch": 1.4654347403228944,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004786304356865655,
|
|
"loss": 5.0667,
|
|
"mean_token_accuracy": 0.20350729823112487,
|
|
"num_tokens": 32682790.0,
|
|
"step": 18835
|
|
},
|
|
{
|
|
"entropy": 5.63403549194336,
|
|
"epoch": 1.465823769694612,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00047861864503470457,
|
|
"loss": 5.1752,
|
|
"mean_token_accuracy": 0.18855532109737397,
|
|
"num_tokens": 32692701.0,
|
|
"step": 18840
|
|
},
|
|
{
|
|
"entropy": 5.666257238388061,
|
|
"epoch": 1.4662127990663296,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004786068512932547,
|
|
"loss": 5.1192,
|
|
"mean_token_accuracy": 0.1941573441028595,
|
|
"num_tokens": 32701297.0,
|
|
"step": 18845
|
|
},
|
|
{
|
|
"entropy": 5.622356748580932,
|
|
"epoch": 1.466601828438047,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000478595054462395,
|
|
"loss": 5.0296,
|
|
"mean_token_accuracy": 0.19540116786956788,
|
|
"num_tokens": 32710188.0,
|
|
"step": 18850
|
|
},
|
|
{
|
|
"entropy": 5.568635272979736,
|
|
"epoch": 1.4669908578097646,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00047858325454230437,
|
|
"loss": 5.0799,
|
|
"mean_token_accuracy": 0.19875933676958085,
|
|
"num_tokens": 32719255.0,
|
|
"step": 18855
|
|
},
|
|
{
|
|
"entropy": 5.635839128494263,
|
|
"epoch": 1.4673798871814823,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004785714515331619,
|
|
"loss": 5.1147,
|
|
"mean_token_accuracy": 0.19851367622613908,
|
|
"num_tokens": 32728133.0,
|
|
"step": 18860
|
|
},
|
|
{
|
|
"entropy": 5.679207706451416,
|
|
"epoch": 1.4677689165531997,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00047855964543514666,
|
|
"loss": 5.1398,
|
|
"mean_token_accuracy": 0.19351682662963868,
|
|
"num_tokens": 32736333.0,
|
|
"step": 18865
|
|
},
|
|
{
|
|
"entropy": 5.54669885635376,
|
|
"epoch": 1.4681579459249172,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00047854783624843786,
|
|
"loss": 5.0482,
|
|
"mean_token_accuracy": 0.20009141862392427,
|
|
"num_tokens": 32744954.0,
|
|
"step": 18870
|
|
},
|
|
{
|
|
"entropy": 5.565046787261963,
|
|
"epoch": 1.468546975296635,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00047853602397321453,
|
|
"loss": 5.1133,
|
|
"mean_token_accuracy": 0.18978338241577147,
|
|
"num_tokens": 32753720.0,
|
|
"step": 18875
|
|
},
|
|
{
|
|
"entropy": 5.6289421081542965,
|
|
"epoch": 1.4689360046683524,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00047852420860965605,
|
|
"loss": 5.0025,
|
|
"mean_token_accuracy": 0.20046208798885345,
|
|
"num_tokens": 32762903.0,
|
|
"step": 18880
|
|
},
|
|
{
|
|
"entropy": 5.704815912246704,
|
|
"epoch": 1.46932503404007,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00047851239015794166,
|
|
"loss": 5.1908,
|
|
"mean_token_accuracy": 0.19168568253517151,
|
|
"num_tokens": 32771367.0,
|
|
"step": 18885
|
|
},
|
|
{
|
|
"entropy": 5.6372082233428955,
|
|
"epoch": 1.4697140634117876,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00047850056861825066,
|
|
"loss": 5.1001,
|
|
"mean_token_accuracy": 0.19459104984998704,
|
|
"num_tokens": 32779782.0,
|
|
"step": 18890
|
|
},
|
|
{
|
|
"entropy": 5.512723922729492,
|
|
"epoch": 1.4701030927835053,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00047848874399076245,
|
|
"loss": 5.0027,
|
|
"mean_token_accuracy": 0.19342736452817916,
|
|
"num_tokens": 32788157.0,
|
|
"step": 18895
|
|
},
|
|
{
|
|
"entropy": 5.506467819213867,
|
|
"epoch": 1.4704921221552227,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004784769162756563,
|
|
"loss": 4.9677,
|
|
"mean_token_accuracy": 0.20290024280548097,
|
|
"num_tokens": 32796590.0,
|
|
"step": 18900
|
|
},
|
|
{
|
|
"entropy": 5.705487871170044,
|
|
"epoch": 1.4708811515269402,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000478465085473112,
|
|
"loss": 5.1989,
|
|
"mean_token_accuracy": 0.1869395539164543,
|
|
"num_tokens": 32806297.0,
|
|
"step": 18905
|
|
},
|
|
{
|
|
"entropy": 5.66557354927063,
|
|
"epoch": 1.471270180898658,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004784532515833088,
|
|
"loss": 5.0504,
|
|
"mean_token_accuracy": 0.2005374625325203,
|
|
"num_tokens": 32815370.0,
|
|
"step": 18910
|
|
},
|
|
{
|
|
"entropy": 5.544957304000855,
|
|
"epoch": 1.4716592102703754,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00047844141460642636,
|
|
"loss": 5.0886,
|
|
"mean_token_accuracy": 0.1905941218137741,
|
|
"num_tokens": 32824678.0,
|
|
"step": 18915
|
|
},
|
|
{
|
|
"entropy": 5.671629762649536,
|
|
"epoch": 1.4720482396420929,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00047842957454264425,
|
|
"loss": 5.1525,
|
|
"mean_token_accuracy": 0.18905438631772994,
|
|
"num_tokens": 32834759.0,
|
|
"step": 18920
|
|
},
|
|
{
|
|
"entropy": 5.7063267707824705,
|
|
"epoch": 1.4724372690138106,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00047841773139214213,
|
|
"loss": 5.1098,
|
|
"mean_token_accuracy": 0.19695671796798705,
|
|
"num_tokens": 32843152.0,
|
|
"step": 18925
|
|
},
|
|
{
|
|
"entropy": 5.69730920791626,
|
|
"epoch": 1.472826298385528,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004784058851550997,
|
|
"loss": 5.2789,
|
|
"mean_token_accuracy": 0.17807060182094575,
|
|
"num_tokens": 32852702.0,
|
|
"step": 18930
|
|
},
|
|
{
|
|
"entropy": 5.602971839904785,
|
|
"epoch": 1.4732153277572457,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004783940358316967,
|
|
"loss": 4.9783,
|
|
"mean_token_accuracy": 0.20461677014827728,
|
|
"num_tokens": 32860201.0,
|
|
"step": 18935
|
|
},
|
|
{
|
|
"entropy": 5.533371257781982,
|
|
"epoch": 1.4736043571289632,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00047838218342211296,
|
|
"loss": 4.9526,
|
|
"mean_token_accuracy": 0.20545047670602798,
|
|
"num_tokens": 32868731.0,
|
|
"step": 18940
|
|
},
|
|
{
|
|
"entropy": 5.633207559585571,
|
|
"epoch": 1.473993386500681,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00047837032792652837,
|
|
"loss": 5.1665,
|
|
"mean_token_accuracy": 0.19108043164014815,
|
|
"num_tokens": 32876960.0,
|
|
"step": 18945
|
|
},
|
|
{
|
|
"entropy": 5.64943528175354,
|
|
"epoch": 1.4743824158723984,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004783584693451226,
|
|
"loss": 5.1162,
|
|
"mean_token_accuracy": 0.19863019585609437,
|
|
"num_tokens": 32886446.0,
|
|
"step": 18950
|
|
},
|
|
{
|
|
"entropy": 5.683539390563965,
|
|
"epoch": 1.4747714452441159,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004783466076780759,
|
|
"loss": 5.1883,
|
|
"mean_token_accuracy": 0.18699711412191392,
|
|
"num_tokens": 32895141.0,
|
|
"step": 18955
|
|
},
|
|
{
|
|
"entropy": 5.632814931869507,
|
|
"epoch": 1.4751604746158336,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004783347429255679,
|
|
"loss": 5.0937,
|
|
"mean_token_accuracy": 0.18989978581666947,
|
|
"num_tokens": 32904191.0,
|
|
"step": 18960
|
|
},
|
|
{
|
|
"entropy": 5.643506288528442,
|
|
"epoch": 1.475549503987551,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000478322875087779,
|
|
"loss": 5.0869,
|
|
"mean_token_accuracy": 0.19535375386476517,
|
|
"num_tokens": 32912805.0,
|
|
"step": 18965
|
|
},
|
|
{
|
|
"entropy": 5.596161842346191,
|
|
"epoch": 1.4759385333592685,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00047831100416488906,
|
|
"loss": 5.0408,
|
|
"mean_token_accuracy": 0.19759644120931624,
|
|
"num_tokens": 32921275.0,
|
|
"step": 18970
|
|
},
|
|
{
|
|
"entropy": 5.654126787185669,
|
|
"epoch": 1.4763275627309862,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00047829913015707816,
|
|
"loss": 5.1255,
|
|
"mean_token_accuracy": 0.19490253031253815,
|
|
"num_tokens": 32929472.0,
|
|
"step": 18975
|
|
},
|
|
{
|
|
"entropy": 5.602848482131958,
|
|
"epoch": 1.4767165921027037,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00047828725306452657,
|
|
"loss": 5.1017,
|
|
"mean_token_accuracy": 0.1915998175740242,
|
|
"num_tokens": 32937697.0,
|
|
"step": 18980
|
|
},
|
|
{
|
|
"entropy": 5.6230028629302975,
|
|
"epoch": 1.4771056214744214,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00047827537288741453,
|
|
"loss": 5.0871,
|
|
"mean_token_accuracy": 0.19737082123756408,
|
|
"num_tokens": 32946516.0,
|
|
"step": 18985
|
|
},
|
|
{
|
|
"entropy": 5.602562999725341,
|
|
"epoch": 1.4774946508461388,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004782634896259222,
|
|
"loss": 4.9725,
|
|
"mean_token_accuracy": 0.20284359455108641,
|
|
"num_tokens": 32954841.0,
|
|
"step": 18990
|
|
},
|
|
{
|
|
"entropy": 5.624081468582153,
|
|
"epoch": 1.4778836802178565,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00047825160328023,
|
|
"loss": 5.1223,
|
|
"mean_token_accuracy": 0.19007060378789903,
|
|
"num_tokens": 32963678.0,
|
|
"step": 18995
|
|
},
|
|
{
|
|
"entropy": 5.547390031814575,
|
|
"epoch": 1.478272709589574,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004782397138505181,
|
|
"loss": 4.9276,
|
|
"mean_token_accuracy": 0.20106931030750275,
|
|
"num_tokens": 32973163.0,
|
|
"step": 19000
|
|
},
|
|
{
|
|
"entropy": 5.6826231479644775,
|
|
"epoch": 1.4786617389612915,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00047822782133696715,
|
|
"loss": 5.1306,
|
|
"mean_token_accuracy": 0.19287146031856536,
|
|
"num_tokens": 32982473.0,
|
|
"step": 19005
|
|
},
|
|
{
|
|
"entropy": 5.630597114562988,
|
|
"epoch": 1.4790507683330092,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004782159257397574,
|
|
"loss": 4.9863,
|
|
"mean_token_accuracy": 0.21068858057260514,
|
|
"num_tokens": 32990328.0,
|
|
"step": 19010
|
|
},
|
|
{
|
|
"entropy": 5.523217296600341,
|
|
"epoch": 1.4794397977047267,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00047820402705906953,
|
|
"loss": 5.0562,
|
|
"mean_token_accuracy": 0.19401719570159912,
|
|
"num_tokens": 32998432.0,
|
|
"step": 19015
|
|
},
|
|
{
|
|
"entropy": 5.607138776779175,
|
|
"epoch": 1.4798288270764441,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00047819212529508394,
|
|
"loss": 5.1349,
|
|
"mean_token_accuracy": 0.19625232517719268,
|
|
"num_tokens": 33007017.0,
|
|
"step": 19020
|
|
},
|
|
{
|
|
"entropy": 5.678186655044556,
|
|
"epoch": 1.4802178564481618,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004781802204479812,
|
|
"loss": 5.0574,
|
|
"mean_token_accuracy": 0.2002095714211464,
|
|
"num_tokens": 33015212.0,
|
|
"step": 19025
|
|
},
|
|
{
|
|
"entropy": 5.641040325164795,
|
|
"epoch": 1.4806068858198795,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004781683125179421,
|
|
"loss": 5.0957,
|
|
"mean_token_accuracy": 0.19393496215343475,
|
|
"num_tokens": 33023555.0,
|
|
"step": 19030
|
|
},
|
|
{
|
|
"entropy": 5.5690813064575195,
|
|
"epoch": 1.480995915191597,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004781564015051472,
|
|
"loss": 5.0908,
|
|
"mean_token_accuracy": 0.1918323427438736,
|
|
"num_tokens": 33033048.0,
|
|
"step": 19035
|
|
},
|
|
{
|
|
"entropy": 5.520502042770386,
|
|
"epoch": 1.4813849445633145,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004781444874097772,
|
|
"loss": 4.9688,
|
|
"mean_token_accuracy": 0.19712026715278624,
|
|
"num_tokens": 33041553.0,
|
|
"step": 19040
|
|
},
|
|
{
|
|
"entropy": 5.557957410812378,
|
|
"epoch": 1.4817739739350322,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00047813257023201307,
|
|
"loss": 5.077,
|
|
"mean_token_accuracy": 0.1975543677806854,
|
|
"num_tokens": 33050864.0,
|
|
"step": 19045
|
|
},
|
|
{
|
|
"entropy": 5.562325382232666,
|
|
"epoch": 1.4821630033067497,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004781206499720354,
|
|
"loss": 4.9698,
|
|
"mean_token_accuracy": 0.20305258631706238,
|
|
"num_tokens": 33059700.0,
|
|
"step": 19050
|
|
},
|
|
{
|
|
"entropy": 5.51577582359314,
|
|
"epoch": 1.4825520326784671,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00047810872663002523,
|
|
"loss": 4.9413,
|
|
"mean_token_accuracy": 0.2056463822722435,
|
|
"num_tokens": 33067784.0,
|
|
"step": 19055
|
|
},
|
|
{
|
|
"entropy": 5.6162621021270756,
|
|
"epoch": 1.4829410620501848,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00047809680020616333,
|
|
"loss": 5.0959,
|
|
"mean_token_accuracy": 0.18692475110292434,
|
|
"num_tokens": 33077174.0,
|
|
"step": 19060
|
|
},
|
|
{
|
|
"entropy": 5.665803718566894,
|
|
"epoch": 1.4833300914219023,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00047808487070063083,
|
|
"loss": 5.1253,
|
|
"mean_token_accuracy": 0.19567935317754745,
|
|
"num_tokens": 33085492.0,
|
|
"step": 19065
|
|
},
|
|
{
|
|
"entropy": 5.622681045532227,
|
|
"epoch": 1.4837191207936198,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004780729381136086,
|
|
"loss": 5.0582,
|
|
"mean_token_accuracy": 0.19979335218667985,
|
|
"num_tokens": 33094388.0,
|
|
"step": 19070
|
|
},
|
|
{
|
|
"entropy": 5.511441659927368,
|
|
"epoch": 1.4841081501653375,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004780610024452778,
|
|
"loss": 4.907,
|
|
"mean_token_accuracy": 0.20075707733631135,
|
|
"num_tokens": 33101996.0,
|
|
"step": 19075
|
|
},
|
|
{
|
|
"entropy": 5.577497148513794,
|
|
"epoch": 1.4844971795370552,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00047804906369581954,
|
|
"loss": 5.1478,
|
|
"mean_token_accuracy": 0.19141252636909484,
|
|
"num_tokens": 33111139.0,
|
|
"step": 19080
|
|
},
|
|
{
|
|
"entropy": 5.589953374862671,
|
|
"epoch": 1.4848862089087727,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004780371218654148,
|
|
"loss": 4.9715,
|
|
"mean_token_accuracy": 0.198114213347435,
|
|
"num_tokens": 33119159.0,
|
|
"step": 19085
|
|
},
|
|
{
|
|
"entropy": 5.6928643703460695,
|
|
"epoch": 1.4852752382804901,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00047802517695424496,
|
|
"loss": 5.1371,
|
|
"mean_token_accuracy": 0.1929064154624939,
|
|
"num_tokens": 33128317.0,
|
|
"step": 19090
|
|
},
|
|
{
|
|
"entropy": 5.583741903305054,
|
|
"epoch": 1.4856642676522078,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004780132289624913,
|
|
"loss": 5.0555,
|
|
"mean_token_accuracy": 0.20420397222042083,
|
|
"num_tokens": 33136936.0,
|
|
"step": 19095
|
|
},
|
|
{
|
|
"entropy": 5.670713901519775,
|
|
"epoch": 1.4860532970239253,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004780012778903349,
|
|
"loss": 5.1239,
|
|
"mean_token_accuracy": 0.19669472724199294,
|
|
"num_tokens": 33145059.0,
|
|
"step": 19100
|
|
},
|
|
{
|
|
"entropy": 5.5884113788604735,
|
|
"epoch": 1.4864423263956428,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00047798932373795724,
|
|
"loss": 5.0171,
|
|
"mean_token_accuracy": 0.18887748420238495,
|
|
"num_tokens": 33153683.0,
|
|
"step": 19105
|
|
},
|
|
{
|
|
"entropy": 5.699123859405518,
|
|
"epoch": 1.4868313557673605,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00047797736650553977,
|
|
"loss": 5.129,
|
|
"mean_token_accuracy": 0.1959105670452118,
|
|
"num_tokens": 33163179.0,
|
|
"step": 19110
|
|
},
|
|
{
|
|
"entropy": 5.607194423675537,
|
|
"epoch": 1.487220385139078,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00047796540619326366,
|
|
"loss": 4.954,
|
|
"mean_token_accuracy": 0.20326871126890184,
|
|
"num_tokens": 33172029.0,
|
|
"step": 19115
|
|
},
|
|
{
|
|
"entropy": 5.655848169326783,
|
|
"epoch": 1.4876094145107956,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004779534428013107,
|
|
"loss": 5.1421,
|
|
"mean_token_accuracy": 0.19332901984453202,
|
|
"num_tokens": 33181168.0,
|
|
"step": 19120
|
|
},
|
|
{
|
|
"entropy": 5.642968559265137,
|
|
"epoch": 1.4879984438825131,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00047794147632986223,
|
|
"loss": 5.1437,
|
|
"mean_token_accuracy": 0.18727092891931535,
|
|
"num_tokens": 33191320.0,
|
|
"step": 19125
|
|
},
|
|
{
|
|
"entropy": 5.556647300720215,
|
|
"epoch": 1.4883874732542308,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004779295067790999,
|
|
"loss": 5.0604,
|
|
"mean_token_accuracy": 0.1952892005443573,
|
|
"num_tokens": 33199625.0,
|
|
"step": 19130
|
|
},
|
|
{
|
|
"entropy": 5.62584342956543,
|
|
"epoch": 1.4887765026259483,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004779175341492053,
|
|
"loss": 5.0401,
|
|
"mean_token_accuracy": 0.19846860468387603,
|
|
"num_tokens": 33208145.0,
|
|
"step": 19135
|
|
},
|
|
{
|
|
"entropy": 5.664146137237549,
|
|
"epoch": 1.4891655319976658,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004779055584403601,
|
|
"loss": 5.0557,
|
|
"mean_token_accuracy": 0.19516253471374512,
|
|
"num_tokens": 33216441.0,
|
|
"step": 19140
|
|
},
|
|
{
|
|
"entropy": 5.667415475845337,
|
|
"epoch": 1.4895545613693835,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000477893579652746,
|
|
"loss": 5.0574,
|
|
"mean_token_accuracy": 0.18994946032762527,
|
|
"num_tokens": 33225612.0,
|
|
"step": 19145
|
|
},
|
|
{
|
|
"entropy": 5.591235065460205,
|
|
"epoch": 1.489943590741101,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00047788159778654475,
|
|
"loss": 5.0459,
|
|
"mean_token_accuracy": 0.19451239705085754,
|
|
"num_tokens": 33234410.0,
|
|
"step": 19150
|
|
},
|
|
{
|
|
"entropy": 5.633623933792114,
|
|
"epoch": 1.4903326201128184,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00047786961284193813,
|
|
"loss": 4.9892,
|
|
"mean_token_accuracy": 0.2010344535112381,
|
|
"num_tokens": 33242838.0,
|
|
"step": 19155
|
|
},
|
|
{
|
|
"entropy": 5.616855478286743,
|
|
"epoch": 1.4907216494845361,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004778576248191081,
|
|
"loss": 5.1354,
|
|
"mean_token_accuracy": 0.1909354954957962,
|
|
"num_tokens": 33251266.0,
|
|
"step": 19160
|
|
},
|
|
{
|
|
"entropy": 5.6047464370727536,
|
|
"epoch": 1.4911106788562536,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004778456337182365,
|
|
"loss": 5.0411,
|
|
"mean_token_accuracy": 0.19840567260980607,
|
|
"num_tokens": 33259644.0,
|
|
"step": 19165
|
|
},
|
|
{
|
|
"entropy": 5.662776708602905,
|
|
"epoch": 1.4914997082279713,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004778336395395052,
|
|
"loss": 5.0414,
|
|
"mean_token_accuracy": 0.1946261316537857,
|
|
"num_tokens": 33267547.0,
|
|
"step": 19170
|
|
},
|
|
{
|
|
"entropy": 5.63383264541626,
|
|
"epoch": 1.4918887375996888,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00047782164228309636,
|
|
"loss": 5.0746,
|
|
"mean_token_accuracy": 0.19716629683971404,
|
|
"num_tokens": 33276808.0,
|
|
"step": 19175
|
|
},
|
|
{
|
|
"entropy": 5.614906454086304,
|
|
"epoch": 1.4922777669714065,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00047780964194919193,
|
|
"loss": 5.1141,
|
|
"mean_token_accuracy": 0.19483509808778762,
|
|
"num_tokens": 33285569.0,
|
|
"step": 19180
|
|
},
|
|
{
|
|
"entropy": 5.6178529262542725,
|
|
"epoch": 1.492666796343124,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00047779763853797387,
|
|
"loss": 5.0976,
|
|
"mean_token_accuracy": 0.1935784101486206,
|
|
"num_tokens": 33295214.0,
|
|
"step": 19185
|
|
},
|
|
{
|
|
"entropy": 5.658003234863282,
|
|
"epoch": 1.4930558257148414,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004777856320496245,
|
|
"loss": 5.0181,
|
|
"mean_token_accuracy": 0.20267871022224426,
|
|
"num_tokens": 33304140.0,
|
|
"step": 19190
|
|
},
|
|
{
|
|
"entropy": 5.6380421161651615,
|
|
"epoch": 1.493444855086559,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000477773622484326,
|
|
"loss": 5.1314,
|
|
"mean_token_accuracy": 0.19123824387788774,
|
|
"num_tokens": 33312879.0,
|
|
"step": 19195
|
|
},
|
|
{
|
|
"entropy": 5.594028568267822,
|
|
"epoch": 1.4938338844582766,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004777616098422604,
|
|
"loss": 5.0691,
|
|
"mean_token_accuracy": 0.19961473047733308,
|
|
"num_tokens": 33320769.0,
|
|
"step": 19200
|
|
},
|
|
{
|
|
"entropy": 5.551181507110596,
|
|
"epoch": 1.494222913829994,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00047774959412361014,
|
|
"loss": 4.9382,
|
|
"mean_token_accuracy": 0.2064416453242302,
|
|
"num_tokens": 33328911.0,
|
|
"step": 19205
|
|
},
|
|
{
|
|
"entropy": 5.606557941436767,
|
|
"epoch": 1.4946119432017118,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004777375753285575,
|
|
"loss": 5.0251,
|
|
"mean_token_accuracy": 0.20039540082216262,
|
|
"num_tokens": 33337607.0,
|
|
"step": 19210
|
|
},
|
|
{
|
|
"entropy": 5.620619678497315,
|
|
"epoch": 1.4950009725734292,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00047772555345728486,
|
|
"loss": 5.0865,
|
|
"mean_token_accuracy": 0.19120642244815828,
|
|
"num_tokens": 33346663.0,
|
|
"step": 19215
|
|
},
|
|
{
|
|
"entropy": 5.726786136627197,
|
|
"epoch": 1.495390001945147,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004777135285099746,
|
|
"loss": 5.137,
|
|
"mean_token_accuracy": 0.18543317168951035,
|
|
"num_tokens": 33355501.0,
|
|
"step": 19220
|
|
},
|
|
{
|
|
"entropy": 5.636517143249511,
|
|
"epoch": 1.4957790313168644,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004777015004868092,
|
|
"loss": 5.0061,
|
|
"mean_token_accuracy": 0.19206279516220093,
|
|
"num_tokens": 33363497.0,
|
|
"step": 19225
|
|
},
|
|
{
|
|
"entropy": 5.575192832946778,
|
|
"epoch": 1.496168060688582,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004776894693879712,
|
|
"loss": 4.9634,
|
|
"mean_token_accuracy": 0.20535971820354462,
|
|
"num_tokens": 33371349.0,
|
|
"step": 19230
|
|
},
|
|
{
|
|
"entropy": 5.583275985717774,
|
|
"epoch": 1.4965570900602996,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004776774352136431,
|
|
"loss": 4.9334,
|
|
"mean_token_accuracy": 0.2051143616437912,
|
|
"num_tokens": 33379889.0,
|
|
"step": 19235
|
|
},
|
|
{
|
|
"entropy": 5.647780275344848,
|
|
"epoch": 1.496946119432017,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00047766539796400756,
|
|
"loss": 5.091,
|
|
"mean_token_accuracy": 0.19515041410923004,
|
|
"num_tokens": 33388452.0,
|
|
"step": 19240
|
|
},
|
|
{
|
|
"entropy": 5.561920404434204,
|
|
"epoch": 1.4973351488037348,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004776533576392471,
|
|
"loss": 5.0111,
|
|
"mean_token_accuracy": 0.19974779337644577,
|
|
"num_tokens": 33397598.0,
|
|
"step": 19245
|
|
},
|
|
{
|
|
"entropy": 5.650741195678711,
|
|
"epoch": 1.4977241781754522,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004776413142395445,
|
|
"loss": 5.077,
|
|
"mean_token_accuracy": 0.19172862768173218,
|
|
"num_tokens": 33406509.0,
|
|
"step": 19250
|
|
},
|
|
{
|
|
"entropy": 5.622381639480591,
|
|
"epoch": 1.4981132075471697,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00047762926776508244,
|
|
"loss": 5.0578,
|
|
"mean_token_accuracy": 0.19003280997276306,
|
|
"num_tokens": 33415129.0,
|
|
"step": 19255
|
|
},
|
|
{
|
|
"entropy": 5.52165002822876,
|
|
"epoch": 1.4985022369188874,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00047761721821604387,
|
|
"loss": 4.9222,
|
|
"mean_token_accuracy": 0.1996190145611763,
|
|
"num_tokens": 33423588.0,
|
|
"step": 19260
|
|
},
|
|
{
|
|
"entropy": 5.638728618621826,
|
|
"epoch": 1.4988912662906049,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004776051655926115,
|
|
"loss": 5.1293,
|
|
"mean_token_accuracy": 0.19162203520536422,
|
|
"num_tokens": 33431598.0,
|
|
"step": 19265
|
|
},
|
|
{
|
|
"entropy": 5.71886305809021,
|
|
"epoch": 1.4992802956623226,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00047759310989496813,
|
|
"loss": 5.1785,
|
|
"mean_token_accuracy": 0.1957082450389862,
|
|
"num_tokens": 33441139.0,
|
|
"step": 19270
|
|
},
|
|
{
|
|
"entropy": 5.673923015594482,
|
|
"epoch": 1.49966932503404,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004775810511232969,
|
|
"loss": 5.035,
|
|
"mean_token_accuracy": 0.19134389609098434,
|
|
"num_tokens": 33449558.0,
|
|
"step": 19275
|
|
},
|
|
{
|
|
"entropy": 5.641165494918823,
|
|
"epoch": 1.5000583544057577,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00047756898927778056,
|
|
"loss": 5.1119,
|
|
"mean_token_accuracy": 0.1928480863571167,
|
|
"num_tokens": 33457429.0,
|
|
"step": 19280
|
|
},
|
|
{
|
|
"entropy": 5.558756589889526,
|
|
"epoch": 1.5004473837774752,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00047755692435860227,
|
|
"loss": 4.9724,
|
|
"mean_token_accuracy": 0.20363960266113282,
|
|
"num_tokens": 33465781.0,
|
|
"step": 19285
|
|
},
|
|
{
|
|
"entropy": 5.66274676322937,
|
|
"epoch": 1.5008364131491927,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000477544856365945,
|
|
"loss": 5.0351,
|
|
"mean_token_accuracy": 0.19682733565568925,
|
|
"num_tokens": 33473865.0,
|
|
"step": 19290
|
|
},
|
|
{
|
|
"entropy": 5.622910451889038,
|
|
"epoch": 1.5012254425209104,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00047753278529999205,
|
|
"loss": 5.0924,
|
|
"mean_token_accuracy": 0.1950071409344673,
|
|
"num_tokens": 33482497.0,
|
|
"step": 19295
|
|
},
|
|
{
|
|
"entropy": 5.607402276992798,
|
|
"epoch": 1.5016144718926279,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00047752071116092637,
|
|
"loss": 5.0988,
|
|
"mean_token_accuracy": 0.19350376576185227,
|
|
"num_tokens": 33490933.0,
|
|
"step": 19300
|
|
},
|
|
{
|
|
"entropy": 5.6274772644042965,
|
|
"epoch": 1.5020035012643453,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004775086339489312,
|
|
"loss": 5.1078,
|
|
"mean_token_accuracy": 0.19557205885648726,
|
|
"num_tokens": 33500192.0,
|
|
"step": 19305
|
|
},
|
|
{
|
|
"entropy": 5.633109998703003,
|
|
"epoch": 1.502392530636063,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004774965536641899,
|
|
"loss": 5.0701,
|
|
"mean_token_accuracy": 0.19493254274129868,
|
|
"num_tokens": 33508543.0,
|
|
"step": 19310
|
|
},
|
|
{
|
|
"entropy": 5.5880790710449215,
|
|
"epoch": 1.5027815600077807,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00047748447030688575,
|
|
"loss": 5.0978,
|
|
"mean_token_accuracy": 0.19160389602184297,
|
|
"num_tokens": 33517310.0,
|
|
"step": 19315
|
|
},
|
|
{
|
|
"entropy": 5.650627994537354,
|
|
"epoch": 1.503170589379498,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00047747238387720194,
|
|
"loss": 5.1335,
|
|
"mean_token_accuracy": 0.18930622488260268,
|
|
"num_tokens": 33526274.0,
|
|
"step": 19320
|
|
},
|
|
{
|
|
"entropy": 5.7084485530853275,
|
|
"epoch": 1.5035596187512157,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000477460294375322,
|
|
"loss": 5.1364,
|
|
"mean_token_accuracy": 0.19404075145721436,
|
|
"num_tokens": 33534438.0,
|
|
"step": 19325
|
|
},
|
|
{
|
|
"entropy": 5.611669588088989,
|
|
"epoch": 1.5039486481229334,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00047744820180142935,
|
|
"loss": 5.0547,
|
|
"mean_token_accuracy": 0.19025860577821732,
|
|
"num_tokens": 33542943.0,
|
|
"step": 19330
|
|
},
|
|
{
|
|
"entropy": 5.599581575393676,
|
|
"epoch": 1.5043376774946509,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00047743610615570746,
|
|
"loss": 5.0614,
|
|
"mean_token_accuracy": 0.19358940422534943,
|
|
"num_tokens": 33550567.0,
|
|
"step": 19335
|
|
},
|
|
{
|
|
"entropy": 5.6271261215209964,
|
|
"epoch": 1.5047267068663683,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00047742400743833993,
|
|
"loss": 5.1604,
|
|
"mean_token_accuracy": 0.19190303087234498,
|
|
"num_tokens": 33559851.0,
|
|
"step": 19340
|
|
},
|
|
{
|
|
"entropy": 5.669795417785645,
|
|
"epoch": 1.505115736238086,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004774119056495102,
|
|
"loss": 5.0715,
|
|
"mean_token_accuracy": 0.1915639564394951,
|
|
"num_tokens": 33568645.0,
|
|
"step": 19345
|
|
},
|
|
{
|
|
"entropy": 5.628902387619019,
|
|
"epoch": 1.5055047656098035,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00047739980078940206,
|
|
"loss": 5.0424,
|
|
"mean_token_accuracy": 0.2036150723695755,
|
|
"num_tokens": 33577331.0,
|
|
"step": 19350
|
|
},
|
|
{
|
|
"entropy": 5.540964078903198,
|
|
"epoch": 1.505893794981521,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00047738769285819894,
|
|
"loss": 4.9036,
|
|
"mean_token_accuracy": 0.20337747782468796,
|
|
"num_tokens": 33586196.0,
|
|
"step": 19355
|
|
},
|
|
{
|
|
"entropy": 5.588247871398925,
|
|
"epoch": 1.5062828243532387,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004773755818560849,
|
|
"loss": 5.1326,
|
|
"mean_token_accuracy": 0.19261325299739837,
|
|
"num_tokens": 33595200.0,
|
|
"step": 19360
|
|
},
|
|
{
|
|
"entropy": 5.60738172531128,
|
|
"epoch": 1.5066718537249564,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004773634677832434,
|
|
"loss": 5.013,
|
|
"mean_token_accuracy": 0.20040953606367112,
|
|
"num_tokens": 33604130.0,
|
|
"step": 19365
|
|
},
|
|
{
|
|
"entropy": 5.648499774932861,
|
|
"epoch": 1.5070608830966739,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004773513506398584,
|
|
"loss": 5.1968,
|
|
"mean_token_accuracy": 0.18189657330513,
|
|
"num_tokens": 33613254.0,
|
|
"step": 19370
|
|
},
|
|
{
|
|
"entropy": 5.6190064430236815,
|
|
"epoch": 1.5074499124683913,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004773392304261137,
|
|
"loss": 5.0537,
|
|
"mean_token_accuracy": 0.20282718390226365,
|
|
"num_tokens": 33621395.0,
|
|
"step": 19375
|
|
},
|
|
{
|
|
"entropy": 5.616506671905517,
|
|
"epoch": 1.507838941840109,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004773271071421933,
|
|
"loss": 5.0036,
|
|
"mean_token_accuracy": 0.196007376909256,
|
|
"num_tokens": 33630293.0,
|
|
"step": 19380
|
|
},
|
|
{
|
|
"entropy": 5.66860065460205,
|
|
"epoch": 1.5082279712118265,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00047731498078828105,
|
|
"loss": 5.1109,
|
|
"mean_token_accuracy": 0.19406146705150604,
|
|
"num_tokens": 33638224.0,
|
|
"step": 19385
|
|
},
|
|
{
|
|
"entropy": 5.68125729560852,
|
|
"epoch": 1.508617000583544,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000477302851364561,
|
|
"loss": 5.1554,
|
|
"mean_token_accuracy": 0.18304163515567778,
|
|
"num_tokens": 33646974.0,
|
|
"step": 19390
|
|
},
|
|
{
|
|
"entropy": 5.640812683105469,
|
|
"epoch": 1.5090060299552617,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00047729071887121717,
|
|
"loss": 5.1323,
|
|
"mean_token_accuracy": 0.18878572136163713,
|
|
"num_tokens": 33656171.0,
|
|
"step": 19395
|
|
},
|
|
{
|
|
"entropy": 5.622091245651245,
|
|
"epoch": 1.5093950593269791,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004772785833084337,
|
|
"loss": 5.1228,
|
|
"mean_token_accuracy": 0.18826854079961777,
|
|
"num_tokens": 33664605.0,
|
|
"step": 19400
|
|
},
|
|
{
|
|
"entropy": 5.652630090713501,
|
|
"epoch": 1.5097840886986966,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004772664446763946,
|
|
"loss": 5.1083,
|
|
"mean_token_accuracy": 0.19310170710086821,
|
|
"num_tokens": 33673128.0,
|
|
"step": 19405
|
|
},
|
|
{
|
|
"entropy": 5.594411039352417,
|
|
"epoch": 1.5101731180704143,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004772543029752842,
|
|
"loss": 5.0499,
|
|
"mean_token_accuracy": 0.19972462952136993,
|
|
"num_tokens": 33681358.0,
|
|
"step": 19410
|
|
},
|
|
{
|
|
"entropy": 5.556503772735596,
|
|
"epoch": 1.510562147442132,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00047724215820528666,
|
|
"loss": 4.939,
|
|
"mean_token_accuracy": 0.2080944821238518,
|
|
"num_tokens": 33690282.0,
|
|
"step": 19415
|
|
},
|
|
{
|
|
"entropy": 5.549698352813721,
|
|
"epoch": 1.5109511768138495,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004772300103665863,
|
|
"loss": 5.0076,
|
|
"mean_token_accuracy": 0.1941213235259056,
|
|
"num_tokens": 33698294.0,
|
|
"step": 19420
|
|
},
|
|
{
|
|
"entropy": 5.5501477241516115,
|
|
"epoch": 1.511340206185567,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00047721785945936733,
|
|
"loss": 4.9793,
|
|
"mean_token_accuracy": 0.20674926787614822,
|
|
"num_tokens": 33706552.0,
|
|
"step": 19425
|
|
},
|
|
{
|
|
"entropy": 5.619852876663208,
|
|
"epoch": 1.5117292355572847,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004772057054838143,
|
|
"loss": 5.0335,
|
|
"mean_token_accuracy": 0.19712848514318465,
|
|
"num_tokens": 33714704.0,
|
|
"step": 19430
|
|
},
|
|
{
|
|
"entropy": 5.642540121078492,
|
|
"epoch": 1.5121182649290021,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00047719354844011146,
|
|
"loss": 5.094,
|
|
"mean_token_accuracy": 0.19931830912828447,
|
|
"num_tokens": 33723823.0,
|
|
"step": 19435
|
|
},
|
|
{
|
|
"entropy": 5.718218851089477,
|
|
"epoch": 1.5125072943007196,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004771813883284434,
|
|
"loss": 5.1549,
|
|
"mean_token_accuracy": 0.19305465519428253,
|
|
"num_tokens": 33732616.0,
|
|
"step": 19440
|
|
},
|
|
{
|
|
"entropy": 5.577765274047851,
|
|
"epoch": 1.5128963236724373,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00047716922514899455,
|
|
"loss": 5.0202,
|
|
"mean_token_accuracy": 0.20044719725847243,
|
|
"num_tokens": 33741542.0,
|
|
"step": 19445
|
|
},
|
|
{
|
|
"entropy": 5.593866348266602,
|
|
"epoch": 1.5132853530441548,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00047715705890194953,
|
|
"loss": 5.0813,
|
|
"mean_token_accuracy": 0.1991390824317932,
|
|
"num_tokens": 33750651.0,
|
|
"step": 19450
|
|
},
|
|
{
|
|
"entropy": 5.537260627746582,
|
|
"epoch": 1.5136743824158723,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00047714488958749285,
|
|
"loss": 5.1175,
|
|
"mean_token_accuracy": 0.19317656010389328,
|
|
"num_tokens": 33760741.0,
|
|
"step": 19455
|
|
},
|
|
{
|
|
"entropy": 5.701646995544434,
|
|
"epoch": 1.51406341178759,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00047713271720580924,
|
|
"loss": 5.1173,
|
|
"mean_token_accuracy": 0.19490543603897095,
|
|
"num_tokens": 33769541.0,
|
|
"step": 19460
|
|
},
|
|
{
|
|
"entropy": 5.644590234756469,
|
|
"epoch": 1.5144524411593077,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004771205417570834,
|
|
"loss": 5.1174,
|
|
"mean_token_accuracy": 0.19758770763874053,
|
|
"num_tokens": 33778684.0,
|
|
"step": 19465
|
|
},
|
|
{
|
|
"entropy": 5.656781387329102,
|
|
"epoch": 1.5148414705310251,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00047710836324150004,
|
|
"loss": 5.0996,
|
|
"mean_token_accuracy": 0.1960084393620491,
|
|
"num_tokens": 33787782.0,
|
|
"step": 19470
|
|
},
|
|
{
|
|
"entropy": 5.638566589355468,
|
|
"epoch": 1.5152304999027426,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000477096181659244,
|
|
"loss": 5.054,
|
|
"mean_token_accuracy": 0.19813997447490692,
|
|
"num_tokens": 33796194.0,
|
|
"step": 19475
|
|
},
|
|
{
|
|
"entropy": 5.652682542800903,
|
|
"epoch": 1.5156195292744603,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004770839970105,
|
|
"loss": 5.0524,
|
|
"mean_token_accuracy": 0.1946710765361786,
|
|
"num_tokens": 33804615.0,
|
|
"step": 19480
|
|
},
|
|
{
|
|
"entropy": 5.653340196609497,
|
|
"epoch": 1.5160085586461778,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00047707180929545295,
|
|
"loss": 5.1486,
|
|
"mean_token_accuracy": 0.1954011395573616,
|
|
"num_tokens": 33812937.0,
|
|
"step": 19485
|
|
},
|
|
{
|
|
"entropy": 5.601870775222778,
|
|
"epoch": 1.5163975880178953,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00047705961851428786,
|
|
"loss": 5.0152,
|
|
"mean_token_accuracy": 0.19929749220609666,
|
|
"num_tokens": 33821454.0,
|
|
"step": 19490
|
|
},
|
|
{
|
|
"entropy": 5.665795755386353,
|
|
"epoch": 1.516786617389613,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00047704742466718973,
|
|
"loss": 5.1156,
|
|
"mean_token_accuracy": 0.19531653821468353,
|
|
"num_tokens": 33829736.0,
|
|
"step": 19495
|
|
},
|
|
{
|
|
"entropy": 5.660660028457642,
|
|
"epoch": 1.5171756467613304,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00047703522775434354,
|
|
"loss": 5.1024,
|
|
"mean_token_accuracy": 0.19056737571954727,
|
|
"num_tokens": 33838403.0,
|
|
"step": 19500
|
|
},
|
|
{
|
|
"entropy": 5.609117317199707,
|
|
"epoch": 1.517564676133048,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00047702302777593425,
|
|
"loss": 5.0817,
|
|
"mean_token_accuracy": 0.19499066323041916,
|
|
"num_tokens": 33847149.0,
|
|
"step": 19505
|
|
},
|
|
{
|
|
"entropy": 5.630152463912964,
|
|
"epoch": 1.5179537055047656,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00047701082473214715,
|
|
"loss": 5.0539,
|
|
"mean_token_accuracy": 0.19630080610513687,
|
|
"num_tokens": 33855924.0,
|
|
"step": 19510
|
|
},
|
|
{
|
|
"entropy": 5.605315256118774,
|
|
"epoch": 1.5183427348764833,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00047699861862316725,
|
|
"loss": 5.0619,
|
|
"mean_token_accuracy": 0.1962066501379013,
|
|
"num_tokens": 33864314.0,
|
|
"step": 19515
|
|
},
|
|
{
|
|
"entropy": 5.6441854476928714,
|
|
"epoch": 1.5187317642482008,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004769864094491798,
|
|
"loss": 5.0128,
|
|
"mean_token_accuracy": 0.20023605078458787,
|
|
"num_tokens": 33873468.0,
|
|
"step": 19520
|
|
},
|
|
{
|
|
"entropy": 5.620679759979248,
|
|
"epoch": 1.5191207936199183,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004769741972103702,
|
|
"loss": 5.0722,
|
|
"mean_token_accuracy": 0.19524154663085938,
|
|
"num_tokens": 33881627.0,
|
|
"step": 19525
|
|
},
|
|
{
|
|
"entropy": 5.5914106369018555,
|
|
"epoch": 1.519509822991636,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00047696198190692353,
|
|
"loss": 5.0683,
|
|
"mean_token_accuracy": 0.1924902081489563,
|
|
"num_tokens": 33889839.0,
|
|
"step": 19530
|
|
},
|
|
{
|
|
"entropy": 5.603225946426392,
|
|
"epoch": 1.5198988523633534,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004769497635390253,
|
|
"loss": 5.0035,
|
|
"mean_token_accuracy": 0.1945620968937874,
|
|
"num_tokens": 33898370.0,
|
|
"step": 19535
|
|
},
|
|
{
|
|
"entropy": 5.651098203659058,
|
|
"epoch": 1.520287881735071,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004769375421068608,
|
|
"loss": 5.1051,
|
|
"mean_token_accuracy": 0.19593175649642944,
|
|
"num_tokens": 33907419.0,
|
|
"step": 19540
|
|
},
|
|
{
|
|
"entropy": 5.646708917617798,
|
|
"epoch": 1.5206769111067886,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00047692531761061555,
|
|
"loss": 5.0836,
|
|
"mean_token_accuracy": 0.190091510117054,
|
|
"num_tokens": 33915957.0,
|
|
"step": 19545
|
|
},
|
|
{
|
|
"entropy": 5.650356245040894,
|
|
"epoch": 1.521065940478506,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000476913090050475,
|
|
"loss": 5.0468,
|
|
"mean_token_accuracy": 0.19721494615077972,
|
|
"num_tokens": 33924012.0,
|
|
"step": 19550
|
|
},
|
|
{
|
|
"entropy": 5.590018177032471,
|
|
"epoch": 1.5214549698502235,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00047690085942662464,
|
|
"loss": 5.1079,
|
|
"mean_token_accuracy": 0.18801727145910263,
|
|
"num_tokens": 33932652.0,
|
|
"step": 19555
|
|
},
|
|
{
|
|
"entropy": 5.611227369308471,
|
|
"epoch": 1.5218439992219412,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00047688862573925015,
|
|
"loss": 5.0231,
|
|
"mean_token_accuracy": 0.1991322085261345,
|
|
"num_tokens": 33941208.0,
|
|
"step": 19560
|
|
},
|
|
{
|
|
"entropy": 5.608739757537842,
|
|
"epoch": 1.522233028593659,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00047687638898853707,
|
|
"loss": 5.0247,
|
|
"mean_token_accuracy": 0.19637274295091628,
|
|
"num_tokens": 33950435.0,
|
|
"step": 19565
|
|
},
|
|
{
|
|
"entropy": 5.60824146270752,
|
|
"epoch": 1.5226220579653764,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004768641491746711,
|
|
"loss": 5.03,
|
|
"mean_token_accuracy": 0.2013051465153694,
|
|
"num_tokens": 33959659.0,
|
|
"step": 19570
|
|
},
|
|
{
|
|
"entropy": 5.624347448348999,
|
|
"epoch": 1.523011087337094,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000476851906297838,
|
|
"loss": 5.0471,
|
|
"mean_token_accuracy": 0.191919207572937,
|
|
"num_tokens": 33969105.0,
|
|
"step": 19575
|
|
},
|
|
{
|
|
"entropy": 5.621804475784302,
|
|
"epoch": 1.5234001167088116,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00047683966035822346,
|
|
"loss": 5.1487,
|
|
"mean_token_accuracy": 0.1893953189253807,
|
|
"num_tokens": 33977314.0,
|
|
"step": 19580
|
|
},
|
|
{
|
|
"entropy": 5.603160047531128,
|
|
"epoch": 1.523789146080529,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00047682741135601336,
|
|
"loss": 5.0751,
|
|
"mean_token_accuracy": 0.1930656224489212,
|
|
"num_tokens": 33985696.0,
|
|
"step": 19585
|
|
},
|
|
{
|
|
"entropy": 5.506903409957886,
|
|
"epoch": 1.5241781754522465,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00047681515929139356,
|
|
"loss": 4.847,
|
|
"mean_token_accuracy": 0.21282618194818498,
|
|
"num_tokens": 33994539.0,
|
|
"step": 19590
|
|
},
|
|
{
|
|
"entropy": 5.578264808654785,
|
|
"epoch": 1.5245672048239642,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00047680290416454995,
|
|
"loss": 5.1177,
|
|
"mean_token_accuracy": 0.18260177969932556,
|
|
"num_tokens": 34003101.0,
|
|
"step": 19595
|
|
},
|
|
{
|
|
"entropy": 5.65296368598938,
|
|
"epoch": 1.524956234195682,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004767906459756684,
|
|
"loss": 5.0614,
|
|
"mean_token_accuracy": 0.19860363900661468,
|
|
"num_tokens": 34011344.0,
|
|
"step": 19600
|
|
},
|
|
{
|
|
"entropy": 5.6451750755310055,
|
|
"epoch": 1.5253452635673992,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00047677838472493504,
|
|
"loss": 5.0775,
|
|
"mean_token_accuracy": 0.19790596812963485,
|
|
"num_tokens": 34019628.0,
|
|
"step": 19605
|
|
},
|
|
{
|
|
"entropy": 5.634744930267334,
|
|
"epoch": 1.5257342929391169,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004767661204125358,
|
|
"loss": 5.0498,
|
|
"mean_token_accuracy": 0.19294812083244323,
|
|
"num_tokens": 34027709.0,
|
|
"step": 19610
|
|
},
|
|
{
|
|
"entropy": 5.5801502704620365,
|
|
"epoch": 1.5261233223108346,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004767538530386569,
|
|
"loss": 5.1021,
|
|
"mean_token_accuracy": 0.19398279637098312,
|
|
"num_tokens": 34036412.0,
|
|
"step": 19615
|
|
},
|
|
{
|
|
"entropy": 5.618213891983032,
|
|
"epoch": 1.526512351682552,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00047674158260348437,
|
|
"loss": 5.0417,
|
|
"mean_token_accuracy": 0.20025135278701783,
|
|
"num_tokens": 34044842.0,
|
|
"step": 19620
|
|
},
|
|
{
|
|
"entropy": 5.548794889450074,
|
|
"epoch": 1.5269013810542695,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00047672930910720436,
|
|
"loss": 5.0051,
|
|
"mean_token_accuracy": 0.19667597711086274,
|
|
"num_tokens": 34053286.0,
|
|
"step": 19625
|
|
},
|
|
{
|
|
"entropy": 5.565608263015747,
|
|
"epoch": 1.5272904104259872,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00047671703255000326,
|
|
"loss": 5.0255,
|
|
"mean_token_accuracy": 0.2006692573428154,
|
|
"num_tokens": 34062059.0,
|
|
"step": 19630
|
|
},
|
|
{
|
|
"entropy": 5.634258222579956,
|
|
"epoch": 1.5276794397977047,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004767047529320673,
|
|
"loss": 5.1078,
|
|
"mean_token_accuracy": 0.1846057280898094,
|
|
"num_tokens": 34070800.0,
|
|
"step": 19635
|
|
},
|
|
{
|
|
"entropy": 5.644186735153198,
|
|
"epoch": 1.5280684691694222,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00047669247025358257,
|
|
"loss": 5.1418,
|
|
"mean_token_accuracy": 0.19050773978233337,
|
|
"num_tokens": 34079935.0,
|
|
"step": 19640
|
|
},
|
|
{
|
|
"entropy": 5.595399713516235,
|
|
"epoch": 1.5284574985411399,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00047668018451473584,
|
|
"loss": 5.0139,
|
|
"mean_token_accuracy": 0.19541258960962296,
|
|
"num_tokens": 34088614.0,
|
|
"step": 19645
|
|
},
|
|
{
|
|
"entropy": 5.651969385147095,
|
|
"epoch": 1.5288465279128576,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004766678957157132,
|
|
"loss": 5.0385,
|
|
"mean_token_accuracy": 0.20503697097301482,
|
|
"num_tokens": 34096899.0,
|
|
"step": 19650
|
|
},
|
|
{
|
|
"entropy": 5.656499862670898,
|
|
"epoch": 1.5292355572845748,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004766556038567013,
|
|
"loss": 5.1438,
|
|
"mean_token_accuracy": 0.18763657212257384,
|
|
"num_tokens": 34105936.0,
|
|
"step": 19655
|
|
},
|
|
{
|
|
"entropy": 5.592771768569946,
|
|
"epoch": 1.5296245866562925,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004766433089378865,
|
|
"loss": 5.0109,
|
|
"mean_token_accuracy": 0.19464890658855438,
|
|
"num_tokens": 34113675.0,
|
|
"step": 19660
|
|
},
|
|
{
|
|
"entropy": 5.600823307037354,
|
|
"epoch": 1.5300136160280102,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00047663101095945544,
|
|
"loss": 4.9224,
|
|
"mean_token_accuracy": 0.20701434314250947,
|
|
"num_tokens": 34121944.0,
|
|
"step": 19665
|
|
},
|
|
{
|
|
"entropy": 5.530815601348877,
|
|
"epoch": 1.5304026453997277,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00047661870992159476,
|
|
"loss": 5.0292,
|
|
"mean_token_accuracy": 0.20334934294223786,
|
|
"num_tokens": 34130403.0,
|
|
"step": 19670
|
|
},
|
|
{
|
|
"entropy": 5.6039036273956295,
|
|
"epoch": 1.5307916747714452,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00047660640582449106,
|
|
"loss": 5.1219,
|
|
"mean_token_accuracy": 0.20233838856220246,
|
|
"num_tokens": 34139853.0,
|
|
"step": 19675
|
|
},
|
|
{
|
|
"entropy": 5.705723476409912,
|
|
"epoch": 1.5311807041431629,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00047659409866833104,
|
|
"loss": 5.1529,
|
|
"mean_token_accuracy": 0.20370273292064667,
|
|
"num_tokens": 34147833.0,
|
|
"step": 19680
|
|
},
|
|
{
|
|
"entropy": 5.65820894241333,
|
|
"epoch": 1.5315697335148803,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004765817884533014,
|
|
"loss": 5.0617,
|
|
"mean_token_accuracy": 0.2025201916694641,
|
|
"num_tokens": 34156248.0,
|
|
"step": 19685
|
|
},
|
|
{
|
|
"entropy": 5.482030534744263,
|
|
"epoch": 1.5319587628865978,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000476569475179589,
|
|
"loss": 4.9385,
|
|
"mean_token_accuracy": 0.20380509942770003,
|
|
"num_tokens": 34164523.0,
|
|
"step": 19690
|
|
},
|
|
{
|
|
"entropy": 5.626768398284912,
|
|
"epoch": 1.5323477922583155,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00047655715884738074,
|
|
"loss": 5.1945,
|
|
"mean_token_accuracy": 0.19471436738967896,
|
|
"num_tokens": 34174084.0,
|
|
"step": 19695
|
|
},
|
|
{
|
|
"entropy": 5.690047740936279,
|
|
"epoch": 1.5327368216300332,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004765448394568632,
|
|
"loss": 5.0932,
|
|
"mean_token_accuracy": 0.19534295201301574,
|
|
"num_tokens": 34182551.0,
|
|
"step": 19700
|
|
},
|
|
{
|
|
"entropy": 5.582829809188842,
|
|
"epoch": 1.5331258510017505,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004765325170082237,
|
|
"loss": 4.9426,
|
|
"mean_token_accuracy": 0.20883558243513106,
|
|
"num_tokens": 34190899.0,
|
|
"step": 19705
|
|
},
|
|
{
|
|
"entropy": 5.602930355072021,
|
|
"epoch": 1.5335148803734682,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000476520191501649,
|
|
"loss": 5.1503,
|
|
"mean_token_accuracy": 0.1931648448109627,
|
|
"num_tokens": 34200394.0,
|
|
"step": 19710
|
|
},
|
|
{
|
|
"entropy": 5.669780588150024,
|
|
"epoch": 1.5339039097451859,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00047650786293732607,
|
|
"loss": 5.1346,
|
|
"mean_token_accuracy": 0.1856587454676628,
|
|
"num_tokens": 34209773.0,
|
|
"step": 19715
|
|
},
|
|
{
|
|
"entropy": 5.660230350494385,
|
|
"epoch": 1.5342929391169033,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004764955313154421,
|
|
"loss": 5.0693,
|
|
"mean_token_accuracy": 0.1954827845096588,
|
|
"num_tokens": 34218487.0,
|
|
"step": 19720
|
|
},
|
|
{
|
|
"entropy": 5.644893312454224,
|
|
"epoch": 1.5346819684886208,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00047648319663618415,
|
|
"loss": 5.1257,
|
|
"mean_token_accuracy": 0.20266671031713485,
|
|
"num_tokens": 34227309.0,
|
|
"step": 19725
|
|
},
|
|
{
|
|
"entropy": 5.6277666091918945,
|
|
"epoch": 1.5350709978603385,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00047647085889973936,
|
|
"loss": 5.0757,
|
|
"mean_token_accuracy": 0.1967098072171211,
|
|
"num_tokens": 34235877.0,
|
|
"step": 19730
|
|
},
|
|
{
|
|
"entropy": 5.627515888214111,
|
|
"epoch": 1.535460027232056,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00047645851810629503,
|
|
"loss": 5.0395,
|
|
"mean_token_accuracy": 0.19868775606155395,
|
|
"num_tokens": 34244073.0,
|
|
"step": 19735
|
|
},
|
|
{
|
|
"entropy": 5.6074498176574705,
|
|
"epoch": 1.5358490566037735,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00047644617425603825,
|
|
"loss": 5.0788,
|
|
"mean_token_accuracy": 0.19275624603033065,
|
|
"num_tokens": 34252255.0,
|
|
"step": 19740
|
|
},
|
|
{
|
|
"entropy": 5.6151293277740475,
|
|
"epoch": 1.5362380859754912,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004764338273491565,
|
|
"loss": 5.0686,
|
|
"mean_token_accuracy": 0.1988752841949463,
|
|
"num_tokens": 34261063.0,
|
|
"step": 19745
|
|
},
|
|
{
|
|
"entropy": 5.6376872062683105,
|
|
"epoch": 1.5366271153472089,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00047642147738583695,
|
|
"loss": 5.1095,
|
|
"mean_token_accuracy": 0.1929849550127983,
|
|
"num_tokens": 34269072.0,
|
|
"step": 19750
|
|
},
|
|
{
|
|
"entropy": 5.6929536819458,
|
|
"epoch": 1.5370161447189261,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004764091243662671,
|
|
"loss": 5.0951,
|
|
"mean_token_accuracy": 0.1925562933087349,
|
|
"num_tokens": 34277845.0,
|
|
"step": 19755
|
|
},
|
|
{
|
|
"entropy": 5.50715217590332,
|
|
"epoch": 1.5374051740906438,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00047639676829063437,
|
|
"loss": 4.9282,
|
|
"mean_token_accuracy": 0.20247926861047744,
|
|
"num_tokens": 34285831.0,
|
|
"step": 19760
|
|
},
|
|
{
|
|
"entropy": 5.65914740562439,
|
|
"epoch": 1.5377942034623615,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00047638440915912623,
|
|
"loss": 5.1262,
|
|
"mean_token_accuracy": 0.1922749936580658,
|
|
"num_tokens": 34294095.0,
|
|
"step": 19765
|
|
},
|
|
{
|
|
"entropy": 5.686305522918701,
|
|
"epoch": 1.538183232834079,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004763720469719303,
|
|
"loss": 5.0746,
|
|
"mean_token_accuracy": 0.19617477506399156,
|
|
"num_tokens": 34301570.0,
|
|
"step": 19770
|
|
},
|
|
{
|
|
"entropy": 5.622435522079468,
|
|
"epoch": 1.5385722622057965,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000476359681729234,
|
|
"loss": 5.1067,
|
|
"mean_token_accuracy": 0.19251677691936492,
|
|
"num_tokens": 34310119.0,
|
|
"step": 19775
|
|
},
|
|
{
|
|
"entropy": 5.62856912612915,
|
|
"epoch": 1.5389612915775142,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000476347313431225,
|
|
"loss": 5.0238,
|
|
"mean_token_accuracy": 0.2005590945482254,
|
|
"num_tokens": 34319622.0,
|
|
"step": 19780
|
|
},
|
|
{
|
|
"entropy": 5.586194849014282,
|
|
"epoch": 1.5393503209492316,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00047633494207809096,
|
|
"loss": 5.0356,
|
|
"mean_token_accuracy": 0.19964371919631957,
|
|
"num_tokens": 34328376.0,
|
|
"step": 19785
|
|
},
|
|
{
|
|
"entropy": 5.5850992679595945,
|
|
"epoch": 1.539739350320949,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00047632256767001977,
|
|
"loss": 5.0821,
|
|
"mean_token_accuracy": 0.19479367434978484,
|
|
"num_tokens": 34337430.0,
|
|
"step": 19790
|
|
},
|
|
{
|
|
"entropy": 5.660489177703857,
|
|
"epoch": 1.5401283796926668,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000476310190207199,
|
|
"loss": 5.0811,
|
|
"mean_token_accuracy": 0.19488630294799805,
|
|
"num_tokens": 34345639.0,
|
|
"step": 19795
|
|
},
|
|
{
|
|
"entropy": 5.6912225723266605,
|
|
"epoch": 1.5405174090643845,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00047629780968981653,
|
|
"loss": 5.0813,
|
|
"mean_token_accuracy": 0.19781474620103837,
|
|
"num_tokens": 34354083.0,
|
|
"step": 19800
|
|
},
|
|
{
|
|
"entropy": 5.585956335067749,
|
|
"epoch": 1.540906438436102,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00047628542611806007,
|
|
"loss": 5.0535,
|
|
"mean_token_accuracy": 0.19291966706514357,
|
|
"num_tokens": 34363882.0,
|
|
"step": 19805
|
|
},
|
|
{
|
|
"entropy": 5.554418420791626,
|
|
"epoch": 1.5412954678078195,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00047627303949211773,
|
|
"loss": 5.0023,
|
|
"mean_token_accuracy": 0.19834552109241485,
|
|
"num_tokens": 34372487.0,
|
|
"step": 19810
|
|
},
|
|
{
|
|
"entropy": 5.59479603767395,
|
|
"epoch": 1.5416844971795371,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004762606498121774,
|
|
"loss": 5.0322,
|
|
"mean_token_accuracy": 0.19938748180866242,
|
|
"num_tokens": 34380729.0,
|
|
"step": 19815
|
|
},
|
|
{
|
|
"entropy": 5.6450221061706545,
|
|
"epoch": 1.5420735265512546,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000476248257078427,
|
|
"loss": 5.0817,
|
|
"mean_token_accuracy": 0.19415965676307678,
|
|
"num_tokens": 34390121.0,
|
|
"step": 19820
|
|
},
|
|
{
|
|
"entropy": 5.60985803604126,
|
|
"epoch": 1.542462555922972,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004762358612910547,
|
|
"loss": 5.041,
|
|
"mean_token_accuracy": 0.1984054520726204,
|
|
"num_tokens": 34398460.0,
|
|
"step": 19825
|
|
},
|
|
{
|
|
"entropy": 5.607812738418579,
|
|
"epoch": 1.5428515852946898,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004762234624502484,
|
|
"loss": 5.0415,
|
|
"mean_token_accuracy": 0.19524168968200684,
|
|
"num_tokens": 34407406.0,
|
|
"step": 19830
|
|
},
|
|
{
|
|
"entropy": 5.6053698539733885,
|
|
"epoch": 1.5432406146664073,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00047621106055619644,
|
|
"loss": 5.0016,
|
|
"mean_token_accuracy": 0.20045041888952256,
|
|
"num_tokens": 34416588.0,
|
|
"step": 19835
|
|
},
|
|
{
|
|
"entropy": 5.624873542785645,
|
|
"epoch": 1.5436296440381247,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00047619865560908687,
|
|
"loss": 5.0621,
|
|
"mean_token_accuracy": 0.1941896751523018,
|
|
"num_tokens": 34425266.0,
|
|
"step": 19840
|
|
},
|
|
{
|
|
"entropy": 5.627095174789429,
|
|
"epoch": 1.5440186734098424,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004761862476091079,
|
|
"loss": 5.031,
|
|
"mean_token_accuracy": 0.1932322636246681,
|
|
"num_tokens": 34433790.0,
|
|
"step": 19845
|
|
},
|
|
{
|
|
"entropy": 5.685766983032226,
|
|
"epoch": 1.5444077027815601,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00047617383655644785,
|
|
"loss": 5.1525,
|
|
"mean_token_accuracy": 0.18489960730075836,
|
|
"num_tokens": 34442733.0,
|
|
"step": 19850
|
|
},
|
|
{
|
|
"entropy": 5.693801641464233,
|
|
"epoch": 1.5447967321532776,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004761614224512951,
|
|
"loss": 5.0434,
|
|
"mean_token_accuracy": 0.19998459666967391,
|
|
"num_tokens": 34451756.0,
|
|
"step": 19855
|
|
},
|
|
{
|
|
"entropy": 5.616048765182495,
|
|
"epoch": 1.545185761524995,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004761490052938379,
|
|
"loss": 5.0738,
|
|
"mean_token_accuracy": 0.19717212170362472,
|
|
"num_tokens": 34460003.0,
|
|
"step": 19860
|
|
},
|
|
{
|
|
"entropy": 5.606335687637329,
|
|
"epoch": 1.5455747908967128,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004761365850842646,
|
|
"loss": 5.0699,
|
|
"mean_token_accuracy": 0.19799195677042009,
|
|
"num_tokens": 34468485.0,
|
|
"step": 19865
|
|
},
|
|
{
|
|
"entropy": 5.6451362609863285,
|
|
"epoch": 1.5459638202684303,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004761241618227639,
|
|
"loss": 5.0012,
|
|
"mean_token_accuracy": 0.19553233534097672,
|
|
"num_tokens": 34477221.0,
|
|
"step": 19870
|
|
},
|
|
{
|
|
"entropy": 5.65382604598999,
|
|
"epoch": 1.5463528496401477,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00047611173550952414,
|
|
"loss": 5.1529,
|
|
"mean_token_accuracy": 0.19217605739831925,
|
|
"num_tokens": 34486339.0,
|
|
"step": 19875
|
|
},
|
|
{
|
|
"entropy": 5.635845947265625,
|
|
"epoch": 1.5467418790118654,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00047609930614473387,
|
|
"loss": 5.0197,
|
|
"mean_token_accuracy": 0.19935112446546555,
|
|
"num_tokens": 34494595.0,
|
|
"step": 19880
|
|
},
|
|
{
|
|
"entropy": 5.58845887184143,
|
|
"epoch": 1.547130908383583,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00047608687372858175,
|
|
"loss": 4.9813,
|
|
"mean_token_accuracy": 0.19906204342842101,
|
|
"num_tokens": 34502702.0,
|
|
"step": 19885
|
|
},
|
|
{
|
|
"entropy": 5.647160196304322,
|
|
"epoch": 1.5475199377553004,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00047607443826125633,
|
|
"loss": 5.1251,
|
|
"mean_token_accuracy": 0.19534933269023896,
|
|
"num_tokens": 34510828.0,
|
|
"step": 19890
|
|
},
|
|
{
|
|
"entropy": 5.709363412857056,
|
|
"epoch": 1.547908967127018,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00047606199974294637,
|
|
"loss": 5.1891,
|
|
"mean_token_accuracy": 0.19509582072496415,
|
|
"num_tokens": 34520288.0,
|
|
"step": 19895
|
|
},
|
|
{
|
|
"entropy": 5.6825488090515135,
|
|
"epoch": 1.5482979964987358,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004760495581738406,
|
|
"loss": 5.0566,
|
|
"mean_token_accuracy": 0.20270530879497528,
|
|
"num_tokens": 34528178.0,
|
|
"step": 19900
|
|
},
|
|
{
|
|
"entropy": 5.636096239089966,
|
|
"epoch": 1.5486870258704533,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004760371135541278,
|
|
"loss": 5.1029,
|
|
"mean_token_accuracy": 0.18809671252965926,
|
|
"num_tokens": 34536915.0,
|
|
"step": 19905
|
|
},
|
|
{
|
|
"entropy": 5.66641206741333,
|
|
"epoch": 1.5490760552421707,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004760246658839967,
|
|
"loss": 5.0548,
|
|
"mean_token_accuracy": 0.19265463203191757,
|
|
"num_tokens": 34545009.0,
|
|
"step": 19910
|
|
},
|
|
{
|
|
"entropy": 5.669793939590454,
|
|
"epoch": 1.5494650846138884,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004760122151636364,
|
|
"loss": 5.1462,
|
|
"mean_token_accuracy": 0.1940530702471733,
|
|
"num_tokens": 34553936.0,
|
|
"step": 19915
|
|
},
|
|
{
|
|
"entropy": 5.661856174468994,
|
|
"epoch": 1.549854113985606,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004759997613932356,
|
|
"loss": 5.0243,
|
|
"mean_token_accuracy": 0.2001774340867996,
|
|
"num_tokens": 34563068.0,
|
|
"step": 19920
|
|
},
|
|
{
|
|
"entropy": 5.665142250061035,
|
|
"epoch": 1.5502431433573234,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00047598730457298335,
|
|
"loss": 5.1666,
|
|
"mean_token_accuracy": 0.18391934782266617,
|
|
"num_tokens": 34571787.0,
|
|
"step": 19925
|
|
},
|
|
{
|
|
"entropy": 5.695776271820068,
|
|
"epoch": 1.550632172729041,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00047597484470306866,
|
|
"loss": 5.0654,
|
|
"mean_token_accuracy": 0.19397427886724472,
|
|
"num_tokens": 34580375.0,
|
|
"step": 19930
|
|
},
|
|
{
|
|
"entropy": 5.688618230819702,
|
|
"epoch": 1.5510212021007586,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004759623817836806,
|
|
"loss": 5.1049,
|
|
"mean_token_accuracy": 0.19783754348754884,
|
|
"num_tokens": 34588762.0,
|
|
"step": 19935
|
|
},
|
|
{
|
|
"entropy": 5.59483494758606,
|
|
"epoch": 1.551410231472476,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004759499158150082,
|
|
"loss": 4.9973,
|
|
"mean_token_accuracy": 0.2052197962999344,
|
|
"num_tokens": 34596986.0,
|
|
"step": 19940
|
|
},
|
|
{
|
|
"entropy": 5.709632158279419,
|
|
"epoch": 1.5517992608441937,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00047593744679724076,
|
|
"loss": 5.1209,
|
|
"mean_token_accuracy": 0.19396817684173584,
|
|
"num_tokens": 34605445.0,
|
|
"step": 19945
|
|
},
|
|
{
|
|
"entropy": 5.618798112869262,
|
|
"epoch": 1.5521882902159114,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00047592497473056733,
|
|
"loss": 5.1045,
|
|
"mean_token_accuracy": 0.1942835971713066,
|
|
"num_tokens": 34614793.0,
|
|
"step": 19950
|
|
},
|
|
{
|
|
"entropy": 5.7228367805480955,
|
|
"epoch": 1.552577319587629,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00047591249961517724,
|
|
"loss": 5.2085,
|
|
"mean_token_accuracy": 0.1784688040614128,
|
|
"num_tokens": 34623790.0,
|
|
"step": 19955
|
|
},
|
|
{
|
|
"entropy": 5.611024665832519,
|
|
"epoch": 1.5529663489593464,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004759000214512598,
|
|
"loss": 5.0571,
|
|
"mean_token_accuracy": 0.196479195356369,
|
|
"num_tokens": 34632387.0,
|
|
"step": 19960
|
|
},
|
|
{
|
|
"entropy": 5.569279050827026,
|
|
"epoch": 1.553355378331064,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004758875402390042,
|
|
"loss": 5.0507,
|
|
"mean_token_accuracy": 0.20331077873706818,
|
|
"num_tokens": 34640097.0,
|
|
"step": 19965
|
|
},
|
|
{
|
|
"entropy": 5.607867193222046,
|
|
"epoch": 1.5537444077027815,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00047587505597859996,
|
|
"loss": 5.0559,
|
|
"mean_token_accuracy": 0.19027096182107925,
|
|
"num_tokens": 34649525.0,
|
|
"step": 19970
|
|
},
|
|
{
|
|
"entropy": 5.591685009002686,
|
|
"epoch": 1.554133437074499,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00047586256867023646,
|
|
"loss": 5.0012,
|
|
"mean_token_accuracy": 0.2034752756357193,
|
|
"num_tokens": 34658467.0,
|
|
"step": 19975
|
|
},
|
|
{
|
|
"entropy": 5.694282150268554,
|
|
"epoch": 1.5545224664462167,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004758500783141032,
|
|
"loss": 5.1483,
|
|
"mean_token_accuracy": 0.1910340443253517,
|
|
"num_tokens": 34666926.0,
|
|
"step": 19980
|
|
},
|
|
{
|
|
"entropy": 5.679008960723877,
|
|
"epoch": 1.5549114958179344,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004758375849103897,
|
|
"loss": 5.0726,
|
|
"mean_token_accuracy": 0.19341611564159394,
|
|
"num_tokens": 34675023.0,
|
|
"step": 19985
|
|
},
|
|
{
|
|
"entropy": 5.6026839256286625,
|
|
"epoch": 1.5553005251896517,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004758250884592855,
|
|
"loss": 5.0181,
|
|
"mean_token_accuracy": 0.20133753567934037,
|
|
"num_tokens": 34683191.0,
|
|
"step": 19990
|
|
},
|
|
{
|
|
"entropy": 5.616697645187378,
|
|
"epoch": 1.5556895545613694,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00047581258896098024,
|
|
"loss": 5.0416,
|
|
"mean_token_accuracy": 0.20284320861101152,
|
|
"num_tokens": 34691899.0,
|
|
"step": 19995
|
|
},
|
|
{
|
|
"entropy": 5.645014047622681,
|
|
"epoch": 1.556078583933087,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004758000864156636,
|
|
"loss": 5.1262,
|
|
"mean_token_accuracy": 0.19397966414690018,
|
|
"num_tokens": 34700942.0,
|
|
"step": 20000
|
|
},
|
|
{
|
|
"entropy": 5.665093231201172,
|
|
"epoch": 1.5564676133048045,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00047578758082352527,
|
|
"loss": 5.1599,
|
|
"mean_token_accuracy": 0.19051943570375443,
|
|
"num_tokens": 34710780.0,
|
|
"step": 20005
|
|
},
|
|
{
|
|
"entropy": 5.657600784301758,
|
|
"epoch": 1.556856642676522,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00047577507218475487,
|
|
"loss": 5.0605,
|
|
"mean_token_accuracy": 0.1937171623110771,
|
|
"num_tokens": 34719332.0,
|
|
"step": 20010
|
|
},
|
|
{
|
|
"entropy": 5.676499223709106,
|
|
"epoch": 1.5572456720482397,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00047576256049954236,
|
|
"loss": 5.1172,
|
|
"mean_token_accuracy": 0.18435289561748505,
|
|
"num_tokens": 34727890.0,
|
|
"step": 20015
|
|
},
|
|
{
|
|
"entropy": 5.643419790267944,
|
|
"epoch": 1.5576347014199572,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004757500457680776,
|
|
"loss": 5.099,
|
|
"mean_token_accuracy": 0.19545732885599137,
|
|
"num_tokens": 34736942.0,
|
|
"step": 20020
|
|
},
|
|
{
|
|
"entropy": 5.610087060928345,
|
|
"epoch": 1.5580237307916747,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004757375279905504,
|
|
"loss": 4.9548,
|
|
"mean_token_accuracy": 0.20365367084741592,
|
|
"num_tokens": 34745612.0,
|
|
"step": 20025
|
|
},
|
|
{
|
|
"entropy": 5.634346199035645,
|
|
"epoch": 1.5584127601633924,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00047572500716715075,
|
|
"loss": 5.0568,
|
|
"mean_token_accuracy": 0.19421056658029556,
|
|
"num_tokens": 34754276.0,
|
|
"step": 20030
|
|
},
|
|
{
|
|
"entropy": 5.603091382980347,
|
|
"epoch": 1.55880178953511,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00047571248329806855,
|
|
"loss": 4.9568,
|
|
"mean_token_accuracy": 0.2041890576481819,
|
|
"num_tokens": 34762042.0,
|
|
"step": 20035
|
|
},
|
|
{
|
|
"entropy": 5.564679431915283,
|
|
"epoch": 1.5591908189068273,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00047569995638349383,
|
|
"loss": 4.9987,
|
|
"mean_token_accuracy": 0.19739745259284974,
|
|
"num_tokens": 34770172.0,
|
|
"step": 20040
|
|
},
|
|
{
|
|
"entropy": 5.593704557418823,
|
|
"epoch": 1.559579848278545,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004756874264236168,
|
|
"loss": 5.0106,
|
|
"mean_token_accuracy": 0.20030488669872284,
|
|
"num_tokens": 34778647.0,
|
|
"step": 20045
|
|
},
|
|
{
|
|
"entropy": 5.610961294174194,
|
|
"epoch": 1.5599688776502627,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00047567489341862753,
|
|
"loss": 5.0453,
|
|
"mean_token_accuracy": 0.1973257318139076,
|
|
"num_tokens": 34787409.0,
|
|
"step": 20050
|
|
},
|
|
{
|
|
"entropy": 5.6935631275177006,
|
|
"epoch": 1.5603579070219802,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00047566235736871607,
|
|
"loss": 5.1361,
|
|
"mean_token_accuracy": 0.19000124782323838,
|
|
"num_tokens": 34795634.0,
|
|
"step": 20055
|
|
},
|
|
{
|
|
"entropy": 5.627721214294434,
|
|
"epoch": 1.5607469363936977,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00047564981827407277,
|
|
"loss": 4.9943,
|
|
"mean_token_accuracy": 0.2055493637919426,
|
|
"num_tokens": 34803803.0,
|
|
"step": 20060
|
|
},
|
|
{
|
|
"entropy": 5.611069202423096,
|
|
"epoch": 1.5611359657654154,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00047563727613488785,
|
|
"loss": 5.0003,
|
|
"mean_token_accuracy": 0.19775864779949187,
|
|
"num_tokens": 34813202.0,
|
|
"step": 20065
|
|
},
|
|
{
|
|
"entropy": 5.627691268920898,
|
|
"epoch": 1.5615249951371328,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00047562473095135154,
|
|
"loss": 5.107,
|
|
"mean_token_accuracy": 0.19250735640525818,
|
|
"num_tokens": 34821717.0,
|
|
"step": 20070
|
|
},
|
|
{
|
|
"entropy": 5.628086185455322,
|
|
"epoch": 1.5619140245088503,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004756121827236544,
|
|
"loss": 5.0173,
|
|
"mean_token_accuracy": 0.19739003777503966,
|
|
"num_tokens": 34830366.0,
|
|
"step": 20075
|
|
},
|
|
{
|
|
"entropy": 5.632188558578491,
|
|
"epoch": 1.562303053880568,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004755996314519866,
|
|
"loss": 5.0864,
|
|
"mean_token_accuracy": 0.1988873600959778,
|
|
"num_tokens": 34838734.0,
|
|
"step": 20080
|
|
},
|
|
{
|
|
"entropy": 5.562366199493408,
|
|
"epoch": 1.5626920832522857,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004755870771365387,
|
|
"loss": 5.001,
|
|
"mean_token_accuracy": 0.20255364328622819,
|
|
"num_tokens": 34846873.0,
|
|
"step": 20085
|
|
},
|
|
{
|
|
"entropy": 5.661673831939697,
|
|
"epoch": 1.563081112624003,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00047557451977750113,
|
|
"loss": 5.0522,
|
|
"mean_token_accuracy": 0.1934480294585228,
|
|
"num_tokens": 34855542.0,
|
|
"step": 20090
|
|
},
|
|
{
|
|
"entropy": 5.614608907699585,
|
|
"epoch": 1.5634701419957207,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004755619593750645,
|
|
"loss": 4.9968,
|
|
"mean_token_accuracy": 0.20677870661020278,
|
|
"num_tokens": 34864656.0,
|
|
"step": 20095
|
|
},
|
|
{
|
|
"entropy": 5.64049072265625,
|
|
"epoch": 1.5638591713674383,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004755493959294194,
|
|
"loss": 5.0992,
|
|
"mean_token_accuracy": 0.19462711811065675,
|
|
"num_tokens": 34873891.0,
|
|
"step": 20100
|
|
},
|
|
{
|
|
"entropy": 5.636171960830689,
|
|
"epoch": 1.5642482007391558,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004755368294407564,
|
|
"loss": 5.0955,
|
|
"mean_token_accuracy": 0.19437652975320815,
|
|
"num_tokens": 34883278.0,
|
|
"step": 20105
|
|
},
|
|
{
|
|
"entropy": 5.567042493820191,
|
|
"epoch": 1.5646372301108733,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004755242599092662,
|
|
"loss": 5.0096,
|
|
"mean_token_accuracy": 0.20047936588525772,
|
|
"num_tokens": 34892323.0,
|
|
"step": 20110
|
|
},
|
|
{
|
|
"entropy": 5.661008501052857,
|
|
"epoch": 1.565026259482591,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00047551168733513956,
|
|
"loss": 5.0619,
|
|
"mean_token_accuracy": 0.19229132384061814,
|
|
"num_tokens": 34901774.0,
|
|
"step": 20115
|
|
},
|
|
{
|
|
"entropy": 5.717881345748902,
|
|
"epoch": 1.5654152888543085,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00047549911171856717,
|
|
"loss": 5.0733,
|
|
"mean_token_accuracy": 0.19608502089977264,
|
|
"num_tokens": 34911082.0,
|
|
"step": 20120
|
|
},
|
|
{
|
|
"entropy": 5.655798101425171,
|
|
"epoch": 1.565804318226026,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004754865330597398,
|
|
"loss": 5.0725,
|
|
"mean_token_accuracy": 0.1976458489894867,
|
|
"num_tokens": 34919631.0,
|
|
"step": 20125
|
|
},
|
|
{
|
|
"entropy": 5.6539222240448,
|
|
"epoch": 1.5661933475977436,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00047547395135884854,
|
|
"loss": 5.075,
|
|
"mean_token_accuracy": 0.19253887832164765,
|
|
"num_tokens": 34928258.0,
|
|
"step": 20130
|
|
},
|
|
{
|
|
"entropy": 5.629160833358765,
|
|
"epoch": 1.5665823769694613,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004754613666160841,
|
|
"loss": 5.0655,
|
|
"mean_token_accuracy": 0.19675603806972503,
|
|
"num_tokens": 34936590.0,
|
|
"step": 20135
|
|
},
|
|
{
|
|
"entropy": 5.582829284667969,
|
|
"epoch": 1.5669714063411786,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00047544877883163753,
|
|
"loss": 5.0901,
|
|
"mean_token_accuracy": 0.18784206956624985,
|
|
"num_tokens": 34945468.0,
|
|
"step": 20140
|
|
},
|
|
{
|
|
"entropy": 5.588636589050293,
|
|
"epoch": 1.5673604357128963,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00047543618800569975,
|
|
"loss": 5.0063,
|
|
"mean_token_accuracy": 0.20052008628845214,
|
|
"num_tokens": 34954005.0,
|
|
"step": 20145
|
|
},
|
|
{
|
|
"entropy": 5.568189287185669,
|
|
"epoch": 1.567749465084614,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00047542359413846184,
|
|
"loss": 5.0066,
|
|
"mean_token_accuracy": 0.19526299387216567,
|
|
"num_tokens": 34962852.0,
|
|
"step": 20150
|
|
},
|
|
{
|
|
"entropy": 5.640872955322266,
|
|
"epoch": 1.5681384944563315,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004754109972301149,
|
|
"loss": 5.0869,
|
|
"mean_token_accuracy": 0.18892480283975602,
|
|
"num_tokens": 34971718.0,
|
|
"step": 20155
|
|
},
|
|
{
|
|
"entropy": 5.669030952453613,
|
|
"epoch": 1.568527523828049,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00047539839728085007,
|
|
"loss": 5.017,
|
|
"mean_token_accuracy": 0.2027488976716995,
|
|
"num_tokens": 34980155.0,
|
|
"step": 20160
|
|
},
|
|
{
|
|
"entropy": 5.698576593399048,
|
|
"epoch": 1.5689165531997666,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004753857942908585,
|
|
"loss": 5.2282,
|
|
"mean_token_accuracy": 0.18437210470438004,
|
|
"num_tokens": 34989971.0,
|
|
"step": 20165
|
|
},
|
|
{
|
|
"entropy": 5.598672199249267,
|
|
"epoch": 1.5693055825714841,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004753731882603315,
|
|
"loss": 5.0293,
|
|
"mean_token_accuracy": 0.1893721714615822,
|
|
"num_tokens": 34998760.0,
|
|
"step": 20170
|
|
},
|
|
{
|
|
"entropy": 5.630321455001831,
|
|
"epoch": 1.5696946119432016,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00047536057918946026,
|
|
"loss": 5.0792,
|
|
"mean_token_accuracy": 0.19391676783561707,
|
|
"num_tokens": 35008020.0,
|
|
"step": 20175
|
|
},
|
|
{
|
|
"entropy": 5.556445217132568,
|
|
"epoch": 1.5700836413149193,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004753479670784361,
|
|
"loss": 4.9488,
|
|
"mean_token_accuracy": 0.20516219288110732,
|
|
"num_tokens": 35016357.0,
|
|
"step": 20180
|
|
},
|
|
{
|
|
"entropy": 5.586726331710816,
|
|
"epoch": 1.570472670686637,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004753353519274505,
|
|
"loss": 5.0611,
|
|
"mean_token_accuracy": 0.19814965426921843,
|
|
"num_tokens": 35025312.0,
|
|
"step": 20185
|
|
},
|
|
{
|
|
"entropy": 5.635017347335816,
|
|
"epoch": 1.5708617000583545,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004753227337366948,
|
|
"loss": 5.1322,
|
|
"mean_token_accuracy": 0.1941147953271866,
|
|
"num_tokens": 35033781.0,
|
|
"step": 20190
|
|
},
|
|
{
|
|
"entropy": 5.697467374801636,
|
|
"epoch": 1.571250729430072,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00047531011250636046,
|
|
"loss": 5.1446,
|
|
"mean_token_accuracy": 0.19301952570676803,
|
|
"num_tokens": 35042884.0,
|
|
"step": 20195
|
|
},
|
|
{
|
|
"entropy": 5.628695440292359,
|
|
"epoch": 1.5716397588017896,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00047529748823663896,
|
|
"loss": 4.9863,
|
|
"mean_token_accuracy": 0.20543665885925294,
|
|
"num_tokens": 35051789.0,
|
|
"step": 20200
|
|
},
|
|
{
|
|
"entropy": 5.6485589981079105,
|
|
"epoch": 1.572028788173507,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004752848609277219,
|
|
"loss": 5.0795,
|
|
"mean_token_accuracy": 0.1973910391330719,
|
|
"num_tokens": 35059958.0,
|
|
"step": 20205
|
|
},
|
|
{
|
|
"entropy": 5.632623386383057,
|
|
"epoch": 1.5724178175452246,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00047527223057980086,
|
|
"loss": 5.0444,
|
|
"mean_token_accuracy": 0.20189540088176727,
|
|
"num_tokens": 35068384.0,
|
|
"step": 20210
|
|
},
|
|
{
|
|
"entropy": 5.685867166519165,
|
|
"epoch": 1.5728068469169423,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00047525959719306736,
|
|
"loss": 5.114,
|
|
"mean_token_accuracy": 0.18957228511571883,
|
|
"num_tokens": 35076660.0,
|
|
"step": 20215
|
|
},
|
|
{
|
|
"entropy": 5.657887744903564,
|
|
"epoch": 1.5731958762886598,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004752469607677134,
|
|
"loss": 5.0324,
|
|
"mean_token_accuracy": 0.20160100013017654,
|
|
"num_tokens": 35085527.0,
|
|
"step": 20220
|
|
},
|
|
{
|
|
"entropy": 5.615867233276367,
|
|
"epoch": 1.5735849056603772,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004752343213039305,
|
|
"loss": 5.0224,
|
|
"mean_token_accuracy": 0.1970536783337593,
|
|
"num_tokens": 35094066.0,
|
|
"step": 20225
|
|
},
|
|
{
|
|
"entropy": 5.670680189132691,
|
|
"epoch": 1.573973935032095,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004752216788019104,
|
|
"loss": 5.1801,
|
|
"mean_token_accuracy": 0.18883613646030425,
|
|
"num_tokens": 35103219.0,
|
|
"step": 20230
|
|
},
|
|
{
|
|
"entropy": 5.684045076370239,
|
|
"epoch": 1.5743629644038126,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004752090332618451,
|
|
"loss": 5.0873,
|
|
"mean_token_accuracy": 0.19407470673322677,
|
|
"num_tokens": 35111336.0,
|
|
"step": 20235
|
|
},
|
|
{
|
|
"entropy": 5.662780809402466,
|
|
"epoch": 1.57475199377553,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004751963846839263,
|
|
"loss": 5.0485,
|
|
"mean_token_accuracy": 0.20413943082094194,
|
|
"num_tokens": 35119758.0,
|
|
"step": 20240
|
|
},
|
|
{
|
|
"entropy": 5.560201740264892,
|
|
"epoch": 1.5751410231472476,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00047518373306834605,
|
|
"loss": 4.983,
|
|
"mean_token_accuracy": 0.20027344226837157,
|
|
"num_tokens": 35128535.0,
|
|
"step": 20245
|
|
},
|
|
{
|
|
"entropy": 5.625986528396607,
|
|
"epoch": 1.5755300525189653,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00047517107841529626,
|
|
"loss": 5.134,
|
|
"mean_token_accuracy": 0.189190836250782,
|
|
"num_tokens": 35137443.0,
|
|
"step": 20250
|
|
},
|
|
{
|
|
"entropy": 5.561290884017945,
|
|
"epoch": 1.5759190818906827,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000475158420724969,
|
|
"loss": 4.9266,
|
|
"mean_token_accuracy": 0.20940395146608354,
|
|
"num_tokens": 35145801.0,
|
|
"step": 20255
|
|
},
|
|
{
|
|
"entropy": 5.694694566726684,
|
|
"epoch": 1.5763081112624002,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00047514575999755627,
|
|
"loss": 5.1562,
|
|
"mean_token_accuracy": 0.18767069578170775,
|
|
"num_tokens": 35154661.0,
|
|
"step": 20260
|
|
},
|
|
{
|
|
"entropy": 5.66506061553955,
|
|
"epoch": 1.576697140634118,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00047513309623325024,
|
|
"loss": 5.1608,
|
|
"mean_token_accuracy": 0.18657090067863463,
|
|
"num_tokens": 35163762.0,
|
|
"step": 20265
|
|
},
|
|
{
|
|
"entropy": 5.64682354927063,
|
|
"epoch": 1.5770861700058354,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004751204294322429,
|
|
"loss": 5.0665,
|
|
"mean_token_accuracy": 0.19244659096002578,
|
|
"num_tokens": 35172059.0,
|
|
"step": 20270
|
|
},
|
|
{
|
|
"entropy": 5.642732095718384,
|
|
"epoch": 1.5774751993775529,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00047510775959472675,
|
|
"loss": 5.1283,
|
|
"mean_token_accuracy": 0.1892454966902733,
|
|
"num_tokens": 35179805.0,
|
|
"step": 20275
|
|
},
|
|
{
|
|
"entropy": 5.585176944732666,
|
|
"epoch": 1.5778642287492706,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004750950867208937,
|
|
"loss": 5.0817,
|
|
"mean_token_accuracy": 0.19841177761554718,
|
|
"num_tokens": 35188136.0,
|
|
"step": 20280
|
|
},
|
|
{
|
|
"entropy": 5.736662435531616,
|
|
"epoch": 1.5782532581209883,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004750824108109362,
|
|
"loss": 5.1645,
|
|
"mean_token_accuracy": 0.1901683747768402,
|
|
"num_tokens": 35196577.0,
|
|
"step": 20285
|
|
},
|
|
{
|
|
"entropy": 5.61679253578186,
|
|
"epoch": 1.5786422874927057,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004750697318650466,
|
|
"loss": 5.0736,
|
|
"mean_token_accuracy": 0.19375281482934953,
|
|
"num_tokens": 35205223.0,
|
|
"step": 20290
|
|
},
|
|
{
|
|
"entropy": 5.69085545539856,
|
|
"epoch": 1.5790313168644232,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004750570498834173,
|
|
"loss": 5.1416,
|
|
"mean_token_accuracy": 0.187985922396183,
|
|
"num_tokens": 35213776.0,
|
|
"step": 20295
|
|
},
|
|
{
|
|
"entropy": 5.618429803848267,
|
|
"epoch": 1.579420346236141,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004750443648662407,
|
|
"loss": 5.0696,
|
|
"mean_token_accuracy": 0.19948683083057403,
|
|
"num_tokens": 35222596.0,
|
|
"step": 20300
|
|
},
|
|
{
|
|
"entropy": 5.7082775115966795,
|
|
"epoch": 1.5798093756078584,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00047503167681370924,
|
|
"loss": 5.2039,
|
|
"mean_token_accuracy": 0.18726951330900193,
|
|
"num_tokens": 35232402.0,
|
|
"step": 20305
|
|
},
|
|
{
|
|
"entropy": 5.639067220687866,
|
|
"epoch": 1.5801984049795759,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004750189857260154,
|
|
"loss": 4.9905,
|
|
"mean_token_accuracy": 0.20895290076732637,
|
|
"num_tokens": 35240651.0,
|
|
"step": 20310
|
|
},
|
|
{
|
|
"entropy": 5.581398582458496,
|
|
"epoch": 1.5805874343512936,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004750062916033519,
|
|
"loss": 5.027,
|
|
"mean_token_accuracy": 0.19455200731754302,
|
|
"num_tokens": 35249101.0,
|
|
"step": 20315
|
|
},
|
|
{
|
|
"entropy": 5.647253561019897,
|
|
"epoch": 1.580976463723011,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004749935944459113,
|
|
"loss": 5.1305,
|
|
"mean_token_accuracy": 0.18680695444345474,
|
|
"num_tokens": 35257909.0,
|
|
"step": 20320
|
|
},
|
|
{
|
|
"entropy": 5.706323909759521,
|
|
"epoch": 1.5813654930947285,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004749808942538862,
|
|
"loss": 5.1865,
|
|
"mean_token_accuracy": 0.18164627701044084,
|
|
"num_tokens": 35267128.0,
|
|
"step": 20325
|
|
},
|
|
{
|
|
"entropy": 5.670701122283935,
|
|
"epoch": 1.5817545224664462,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004749681910274693,
|
|
"loss": 5.0713,
|
|
"mean_token_accuracy": 0.19438831955194474,
|
|
"num_tokens": 35275751.0,
|
|
"step": 20330
|
|
},
|
|
{
|
|
"entropy": 5.604038524627685,
|
|
"epoch": 1.582143551838164,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00047495548476685334,
|
|
"loss": 4.9836,
|
|
"mean_token_accuracy": 0.20060366541147232,
|
|
"num_tokens": 35285359.0,
|
|
"step": 20335
|
|
},
|
|
{
|
|
"entropy": 5.577478981018066,
|
|
"epoch": 1.5825325812098814,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00047494277547223125,
|
|
"loss": 4.9781,
|
|
"mean_token_accuracy": 0.19926492124795914,
|
|
"num_tokens": 35293691.0,
|
|
"step": 20340
|
|
},
|
|
{
|
|
"entropy": 5.582086610794067,
|
|
"epoch": 1.5829216105815989,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00047493006314379573,
|
|
"loss": 5.0148,
|
|
"mean_token_accuracy": 0.2020304471254349,
|
|
"num_tokens": 35302751.0,
|
|
"step": 20345
|
|
},
|
|
{
|
|
"entropy": 5.70212755203247,
|
|
"epoch": 1.5833106399533166,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00047491734778173976,
|
|
"loss": 5.093,
|
|
"mean_token_accuracy": 0.19042124450206757,
|
|
"num_tokens": 35311849.0,
|
|
"step": 20350
|
|
},
|
|
{
|
|
"entropy": 5.606876611709595,
|
|
"epoch": 1.583699669325034,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00047490462938625617,
|
|
"loss": 5.0321,
|
|
"mean_token_accuracy": 0.198320609331131,
|
|
"num_tokens": 35320248.0,
|
|
"step": 20355
|
|
},
|
|
{
|
|
"entropy": 5.651252222061157,
|
|
"epoch": 1.5840886986967515,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00047489190795753806,
|
|
"loss": 5.0366,
|
|
"mean_token_accuracy": 0.20442617684602737,
|
|
"num_tokens": 35328565.0,
|
|
"step": 20360
|
|
},
|
|
{
|
|
"entropy": 5.604735374450684,
|
|
"epoch": 1.5844777280684692,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004748791834957784,
|
|
"loss": 5.0352,
|
|
"mean_token_accuracy": 0.20153813660144806,
|
|
"num_tokens": 35337828.0,
|
|
"step": 20365
|
|
},
|
|
{
|
|
"entropy": 5.640591764450074,
|
|
"epoch": 1.5848667574401867,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00047486645600117037,
|
|
"loss": 5.1281,
|
|
"mean_token_accuracy": 0.18953794836997986,
|
|
"num_tokens": 35347107.0,
|
|
"step": 20370
|
|
},
|
|
{
|
|
"entropy": 5.6811388492584225,
|
|
"epoch": 1.5852557868119042,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004748537254739068,
|
|
"loss": 5.0515,
|
|
"mean_token_accuracy": 0.1988525688648224,
|
|
"num_tokens": 35355925.0,
|
|
"step": 20375
|
|
},
|
|
{
|
|
"entropy": 5.623303079605103,
|
|
"epoch": 1.5856448161836219,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004748409919141812,
|
|
"loss": 5.0239,
|
|
"mean_token_accuracy": 0.19985021501779557,
|
|
"num_tokens": 35364319.0,
|
|
"step": 20380
|
|
},
|
|
{
|
|
"entropy": 5.546020793914795,
|
|
"epoch": 1.5860338455553395,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004748282553221865,
|
|
"loss": 4.9642,
|
|
"mean_token_accuracy": 0.20473470389842988,
|
|
"num_tokens": 35372358.0,
|
|
"step": 20385
|
|
},
|
|
{
|
|
"entropy": 5.639964818954468,
|
|
"epoch": 1.586422874927057,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004748155156981162,
|
|
"loss": 5.2054,
|
|
"mean_token_accuracy": 0.18248383104801177,
|
|
"num_tokens": 35381301.0,
|
|
"step": 20390
|
|
},
|
|
{
|
|
"entropy": 5.651611757278443,
|
|
"epoch": 1.5868119042987745,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00047480277304216346,
|
|
"loss": 5.0181,
|
|
"mean_token_accuracy": 0.19694725126028062,
|
|
"num_tokens": 35389778.0,
|
|
"step": 20395
|
|
},
|
|
{
|
|
"entropy": 5.6118851661682125,
|
|
"epoch": 1.5872009336704922,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00047479002735452164,
|
|
"loss": 4.9859,
|
|
"mean_token_accuracy": 0.19889788329601288,
|
|
"num_tokens": 35397926.0,
|
|
"step": 20400
|
|
},
|
|
{
|
|
"entropy": 5.5962324142456055,
|
|
"epoch": 1.5875899630422097,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00047477727863538415,
|
|
"loss": 5.0185,
|
|
"mean_token_accuracy": 0.20125045776367187,
|
|
"num_tokens": 35406462.0,
|
|
"step": 20405
|
|
},
|
|
{
|
|
"entropy": 5.679141616821289,
|
|
"epoch": 1.5879789924139271,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00047476452688494444,
|
|
"loss": 5.0256,
|
|
"mean_token_accuracy": 0.19560559540987016,
|
|
"num_tokens": 35414989.0,
|
|
"step": 20410
|
|
},
|
|
{
|
|
"entropy": 5.667212677001953,
|
|
"epoch": 1.5883680217856448,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000474751772103396,
|
|
"loss": 5.0136,
|
|
"mean_token_accuracy": 0.20355913341045379,
|
|
"num_tokens": 35423738.0,
|
|
"step": 20415
|
|
},
|
|
{
|
|
"entropy": 5.67338376045227,
|
|
"epoch": 1.5887570511573625,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004747390142909323,
|
|
"loss": 5.0561,
|
|
"mean_token_accuracy": 0.19209839254617692,
|
|
"num_tokens": 35432377.0,
|
|
"step": 20420
|
|
},
|
|
{
|
|
"entropy": 5.589076089859009,
|
|
"epoch": 1.5891460805290798,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00047472625344774713,
|
|
"loss": 5.0438,
|
|
"mean_token_accuracy": 0.20113733559846877,
|
|
"num_tokens": 35441188.0,
|
|
"step": 20425
|
|
},
|
|
{
|
|
"entropy": 5.6141499996185305,
|
|
"epoch": 1.5895351099007975,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00047471348957403374,
|
|
"loss": 5.1025,
|
|
"mean_token_accuracy": 0.1982101321220398,
|
|
"num_tokens": 35449715.0,
|
|
"step": 20430
|
|
},
|
|
{
|
|
"entropy": 5.627524709701538,
|
|
"epoch": 1.5899241392725152,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004747007226699862,
|
|
"loss": 5.0656,
|
|
"mean_token_accuracy": 0.1978027567267418,
|
|
"num_tokens": 35458420.0,
|
|
"step": 20435
|
|
},
|
|
{
|
|
"entropy": 5.6718086242675785,
|
|
"epoch": 1.5903131686442327,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00047468795273579803,
|
|
"loss": 4.9883,
|
|
"mean_token_accuracy": 0.19835505038499832,
|
|
"num_tokens": 35467072.0,
|
|
"step": 20440
|
|
},
|
|
{
|
|
"entropy": 5.638486337661743,
|
|
"epoch": 1.5907021980159501,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004746751797716629,
|
|
"loss": 5.0537,
|
|
"mean_token_accuracy": 0.19619325697422027,
|
|
"num_tokens": 35475539.0,
|
|
"step": 20445
|
|
},
|
|
{
|
|
"entropy": 5.636385822296143,
|
|
"epoch": 1.5910912273876678,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004746624037777748,
|
|
"loss": 5.0582,
|
|
"mean_token_accuracy": 0.20286996513605118,
|
|
"num_tokens": 35484260.0,
|
|
"step": 20450
|
|
},
|
|
{
|
|
"entropy": 5.665251350402832,
|
|
"epoch": 1.5914802567593853,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00047464962475432754,
|
|
"loss": 4.9885,
|
|
"mean_token_accuracy": 0.20174664109945298,
|
|
"num_tokens": 35492539.0,
|
|
"step": 20455
|
|
},
|
|
{
|
|
"entropy": 5.718202590942383,
|
|
"epoch": 1.5918692861311028,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000474636842701515,
|
|
"loss": 5.1516,
|
|
"mean_token_accuracy": 0.19236619174480438,
|
|
"num_tokens": 35502008.0,
|
|
"step": 20460
|
|
},
|
|
{
|
|
"entropy": 5.6056407451629635,
|
|
"epoch": 1.5922583155028205,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004746240576195311,
|
|
"loss": 5.0198,
|
|
"mean_token_accuracy": 0.19924120903015136,
|
|
"num_tokens": 35510677.0,
|
|
"step": 20465
|
|
},
|
|
{
|
|
"entropy": 5.60391092300415,
|
|
"epoch": 1.5926473448745382,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00047461126950856987,
|
|
"loss": 5.0622,
|
|
"mean_token_accuracy": 0.19693288952112198,
|
|
"num_tokens": 35519368.0,
|
|
"step": 20470
|
|
},
|
|
{
|
|
"entropy": 5.701827716827393,
|
|
"epoch": 1.5930363742462554,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004745984783688253,
|
|
"loss": 5.1815,
|
|
"mean_token_accuracy": 0.1867993012070656,
|
|
"num_tokens": 35527952.0,
|
|
"step": 20475
|
|
},
|
|
{
|
|
"entropy": 5.706687116622925,
|
|
"epoch": 1.5934254036179731,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00047458568420049153,
|
|
"loss": 5.1105,
|
|
"mean_token_accuracy": 0.1935567080974579,
|
|
"num_tokens": 35537806.0,
|
|
"step": 20480
|
|
},
|
|
{
|
|
"entropy": 5.578287982940674,
|
|
"epoch": 1.5938144329896908,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00047457288700376274,
|
|
"loss": 4.9572,
|
|
"mean_token_accuracy": 0.1940494492650032,
|
|
"num_tokens": 35546135.0,
|
|
"step": 20485
|
|
},
|
|
{
|
|
"entropy": 5.551790428161621,
|
|
"epoch": 1.5942034623614083,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00047456008677883304,
|
|
"loss": 5.0313,
|
|
"mean_token_accuracy": 0.19893161803483964,
|
|
"num_tokens": 35555065.0,
|
|
"step": 20490
|
|
},
|
|
{
|
|
"entropy": 5.657136487960815,
|
|
"epoch": 1.5945924917331258,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004745472835258966,
|
|
"loss": 5.1352,
|
|
"mean_token_accuracy": 0.19141838401556016,
|
|
"num_tokens": 35564222.0,
|
|
"step": 20495
|
|
},
|
|
{
|
|
"entropy": 5.6803154945373535,
|
|
"epoch": 1.5949815211048435,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00047453447724514773,
|
|
"loss": 5.099,
|
|
"mean_token_accuracy": 0.1897246018052101,
|
|
"num_tokens": 35573021.0,
|
|
"step": 20500
|
|
},
|
|
{
|
|
"entropy": 5.676893854141236,
|
|
"epoch": 1.595370550476561,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004745216679367808,
|
|
"loss": 5.1332,
|
|
"mean_token_accuracy": 0.1959197148680687,
|
|
"num_tokens": 35581105.0,
|
|
"step": 20505
|
|
},
|
|
{
|
|
"entropy": 5.692387914657592,
|
|
"epoch": 1.5957595798482784,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004745088556009901,
|
|
"loss": 5.1767,
|
|
"mean_token_accuracy": 0.18537239879369735,
|
|
"num_tokens": 35590169.0,
|
|
"step": 20510
|
|
},
|
|
{
|
|
"entropy": 5.643527221679688,
|
|
"epoch": 1.5961486092199961,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004744960402379701,
|
|
"loss": 5.0617,
|
|
"mean_token_accuracy": 0.20321208089590073,
|
|
"num_tokens": 35598760.0,
|
|
"step": 20515
|
|
},
|
|
{
|
|
"entropy": 5.690423107147216,
|
|
"epoch": 1.5965376385917138,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00047448322184791525,
|
|
"loss": 5.1003,
|
|
"mean_token_accuracy": 0.19415076971054077,
|
|
"num_tokens": 35607014.0,
|
|
"step": 20520
|
|
},
|
|
{
|
|
"entropy": 5.689444875717163,
|
|
"epoch": 1.596926667963431,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00047447040043101994,
|
|
"loss": 5.0687,
|
|
"mean_token_accuracy": 0.19446302056312562,
|
|
"num_tokens": 35615319.0,
|
|
"step": 20525
|
|
},
|
|
{
|
|
"entropy": 5.621392011642456,
|
|
"epoch": 1.5973156973351488,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00047445757598747886,
|
|
"loss": 5.0904,
|
|
"mean_token_accuracy": 0.1962117910385132,
|
|
"num_tokens": 35623836.0,
|
|
"step": 20530
|
|
},
|
|
{
|
|
"entropy": 5.585716772079468,
|
|
"epoch": 1.5977047267068665,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004744447485174864,
|
|
"loss": 4.981,
|
|
"mean_token_accuracy": 0.1976259395480156,
|
|
"num_tokens": 35632601.0,
|
|
"step": 20535
|
|
},
|
|
{
|
|
"entropy": 5.734390735626221,
|
|
"epoch": 1.598093756078584,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00047443191802123746,
|
|
"loss": 5.1334,
|
|
"mean_token_accuracy": 0.19487304538488387,
|
|
"num_tokens": 35642035.0,
|
|
"step": 20540
|
|
},
|
|
{
|
|
"entropy": 5.639154052734375,
|
|
"epoch": 1.5984827854503014,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00047441908449892664,
|
|
"loss": 5.0538,
|
|
"mean_token_accuracy": 0.20130744874477385,
|
|
"num_tokens": 35650454.0,
|
|
"step": 20545
|
|
},
|
|
{
|
|
"entropy": 5.6871569633483885,
|
|
"epoch": 1.5988718148220191,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00047440624795074855,
|
|
"loss": 5.0974,
|
|
"mean_token_accuracy": 0.1976846382021904,
|
|
"num_tokens": 35658945.0,
|
|
"step": 20550
|
|
},
|
|
{
|
|
"entropy": 5.674994468688965,
|
|
"epoch": 1.5992608441937366,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00047439340837689804,
|
|
"loss": 5.0921,
|
|
"mean_token_accuracy": 0.19574213027954102,
|
|
"num_tokens": 35667193.0,
|
|
"step": 20555
|
|
},
|
|
{
|
|
"entropy": 5.605404663085937,
|
|
"epoch": 1.599649873565454,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00047438056577756986,
|
|
"loss": 4.943,
|
|
"mean_token_accuracy": 0.2057245135307312,
|
|
"num_tokens": 35676100.0,
|
|
"step": 20560
|
|
},
|
|
{
|
|
"entropy": 5.647966051101685,
|
|
"epoch": 1.6000389029371718,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00047436772015295903,
|
|
"loss": 5.0667,
|
|
"mean_token_accuracy": 0.19314984381198883,
|
|
"num_tokens": 35684352.0,
|
|
"step": 20565
|
|
},
|
|
{
|
|
"entropy": 5.673441696166992,
|
|
"epoch": 1.6004279323088895,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00047435487150326036,
|
|
"loss": 5.0147,
|
|
"mean_token_accuracy": 0.20399393886327744,
|
|
"num_tokens": 35693044.0,
|
|
"step": 20570
|
|
},
|
|
{
|
|
"entropy": 5.591395711898803,
|
|
"epoch": 1.6008169616806067,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004743420198286688,
|
|
"loss": 5.0088,
|
|
"mean_token_accuracy": 0.20347841084003448,
|
|
"num_tokens": 35701172.0,
|
|
"step": 20575
|
|
},
|
|
{
|
|
"entropy": 5.62863564491272,
|
|
"epoch": 1.6012059910523244,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00047432916512937936,
|
|
"loss": 5.1096,
|
|
"mean_token_accuracy": 0.1904487982392311,
|
|
"num_tokens": 35709905.0,
|
|
"step": 20580
|
|
},
|
|
{
|
|
"entropy": 5.622174978256226,
|
|
"epoch": 1.6015950204240421,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004743163074055871,
|
|
"loss": 5.0712,
|
|
"mean_token_accuracy": 0.19702855348587037,
|
|
"num_tokens": 35718404.0,
|
|
"step": 20585
|
|
},
|
|
{
|
|
"entropy": 5.677816534042359,
|
|
"epoch": 1.6019840497957596,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004743034466574871,
|
|
"loss": 5.0889,
|
|
"mean_token_accuracy": 0.19194709211587907,
|
|
"num_tokens": 35726475.0,
|
|
"step": 20590
|
|
},
|
|
{
|
|
"entropy": 5.654997396469116,
|
|
"epoch": 1.602373079167477,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004742905828852746,
|
|
"loss": 5.1117,
|
|
"mean_token_accuracy": 0.1939750149846077,
|
|
"num_tokens": 35734819.0,
|
|
"step": 20595
|
|
},
|
|
{
|
|
"entropy": 5.58772087097168,
|
|
"epoch": 1.6027621085391948,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004742777160891447,
|
|
"loss": 4.9955,
|
|
"mean_token_accuracy": 0.200380939245224,
|
|
"num_tokens": 35743098.0,
|
|
"step": 20600
|
|
},
|
|
{
|
|
"entropy": 5.66486496925354,
|
|
"epoch": 1.6031511379109122,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004742648462692926,
|
|
"loss": 5.1079,
|
|
"mean_token_accuracy": 0.19390379041433334,
|
|
"num_tokens": 35752502.0,
|
|
"step": 20605
|
|
},
|
|
{
|
|
"entropy": 5.675458478927612,
|
|
"epoch": 1.6035401672826297,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00047425197342591363,
|
|
"loss": 5.0381,
|
|
"mean_token_accuracy": 0.20833075493574144,
|
|
"num_tokens": 35761293.0,
|
|
"step": 20610
|
|
},
|
|
{
|
|
"entropy": 5.647287654876709,
|
|
"epoch": 1.6039291966543474,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004742390975592031,
|
|
"loss": 5.1622,
|
|
"mean_token_accuracy": 0.1827400729060173,
|
|
"num_tokens": 35771031.0,
|
|
"step": 20615
|
|
},
|
|
{
|
|
"entropy": 5.675501918792724,
|
|
"epoch": 1.604318226026065,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00047422621866935645,
|
|
"loss": 5.0616,
|
|
"mean_token_accuracy": 0.19546449929475784,
|
|
"num_tokens": 35778894.0,
|
|
"step": 20620
|
|
},
|
|
{
|
|
"entropy": 5.735651063919067,
|
|
"epoch": 1.6047072553977826,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000474213336756569,
|
|
"loss": 5.1229,
|
|
"mean_token_accuracy": 0.19083805829286576,
|
|
"num_tokens": 35787159.0,
|
|
"step": 20625
|
|
},
|
|
{
|
|
"entropy": 5.60609540939331,
|
|
"epoch": 1.6050962847695,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004742004518210362,
|
|
"loss": 5.04,
|
|
"mean_token_accuracy": 0.2049606204032898,
|
|
"num_tokens": 35795858.0,
|
|
"step": 20630
|
|
},
|
|
{
|
|
"entropy": 5.604734611511231,
|
|
"epoch": 1.6054853141412178,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004741875638629536,
|
|
"loss": 5.0508,
|
|
"mean_token_accuracy": 0.2021583303809166,
|
|
"num_tokens": 35804754.0,
|
|
"step": 20635
|
|
},
|
|
{
|
|
"entropy": 5.707863759994507,
|
|
"epoch": 1.6058743435129352,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004741746728825168,
|
|
"loss": 5.1498,
|
|
"mean_token_accuracy": 0.1861529216170311,
|
|
"num_tokens": 35813622.0,
|
|
"step": 20640
|
|
},
|
|
{
|
|
"entropy": 5.638468790054321,
|
|
"epoch": 1.6062633728846527,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004741617788799213,
|
|
"loss": 5.0428,
|
|
"mean_token_accuracy": 0.19861431419849396,
|
|
"num_tokens": 35821345.0,
|
|
"step": 20645
|
|
},
|
|
{
|
|
"entropy": 5.608671092987061,
|
|
"epoch": 1.6066524022563704,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00047414888185536285,
|
|
"loss": 5.0527,
|
|
"mean_token_accuracy": 0.20123450756072997,
|
|
"num_tokens": 35830058.0,
|
|
"step": 20650
|
|
},
|
|
{
|
|
"entropy": 5.674367952346802,
|
|
"epoch": 1.6070414316280879,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004741359818090371,
|
|
"loss": 5.0754,
|
|
"mean_token_accuracy": 0.19666314125061035,
|
|
"num_tokens": 35838951.0,
|
|
"step": 20655
|
|
},
|
|
{
|
|
"entropy": 5.6696014404296875,
|
|
"epoch": 1.6074304609998054,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00047412307874113976,
|
|
"loss": 5.039,
|
|
"mean_token_accuracy": 0.2006827637553215,
|
|
"num_tokens": 35847245.0,
|
|
"step": 20660
|
|
},
|
|
{
|
|
"entropy": 5.678802108764648,
|
|
"epoch": 1.607819490371523,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004741101726518667,
|
|
"loss": 5.1442,
|
|
"mean_token_accuracy": 0.1897593155503273,
|
|
"num_tokens": 35856037.0,
|
|
"step": 20665
|
|
},
|
|
{
|
|
"entropy": 5.600672960281372,
|
|
"epoch": 1.6082085197432407,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004740972635414136,
|
|
"loss": 4.9946,
|
|
"mean_token_accuracy": 0.20069389194250106,
|
|
"num_tokens": 35864881.0,
|
|
"step": 20670
|
|
},
|
|
{
|
|
"entropy": 5.734729290008545,
|
|
"epoch": 1.6085975491149582,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004740843514099765,
|
|
"loss": 5.1038,
|
|
"mean_token_accuracy": 0.19034747034311295,
|
|
"num_tokens": 35872941.0,
|
|
"step": 20675
|
|
},
|
|
{
|
|
"entropy": 5.600311899185181,
|
|
"epoch": 1.6089865784866757,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004740714362577512,
|
|
"loss": 5.0818,
|
|
"mean_token_accuracy": 0.19161975085735322,
|
|
"num_tokens": 35882068.0,
|
|
"step": 20680
|
|
},
|
|
{
|
|
"entropy": 5.595686388015747,
|
|
"epoch": 1.6093756078583934,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00047405851808493364,
|
|
"loss": 5.0161,
|
|
"mean_token_accuracy": 0.19953440874814987,
|
|
"num_tokens": 35890306.0,
|
|
"step": 20685
|
|
},
|
|
{
|
|
"entropy": 5.6738725185394285,
|
|
"epoch": 1.6097646372301109,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00047404559689172006,
|
|
"loss": 5.0854,
|
|
"mean_token_accuracy": 0.20426378399133682,
|
|
"num_tokens": 35899311.0,
|
|
"step": 20690
|
|
},
|
|
{
|
|
"entropy": 5.660208320617675,
|
|
"epoch": 1.6101536666018283,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00047403267267830617,
|
|
"loss": 5.139,
|
|
"mean_token_accuracy": 0.1853990823030472,
|
|
"num_tokens": 35908599.0,
|
|
"step": 20695
|
|
},
|
|
{
|
|
"entropy": 5.656005811691284,
|
|
"epoch": 1.610542695973546,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00047401974544488844,
|
|
"loss": 5.0885,
|
|
"mean_token_accuracy": 0.194300676882267,
|
|
"num_tokens": 35917318.0,
|
|
"step": 20700
|
|
},
|
|
{
|
|
"entropy": 5.686577224731446,
|
|
"epoch": 1.6109317253452635,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004740068151916628,
|
|
"loss": 5.0472,
|
|
"mean_token_accuracy": 0.20165519118309022,
|
|
"num_tokens": 35926179.0,
|
|
"step": 20705
|
|
},
|
|
{
|
|
"entropy": 5.579198503494263,
|
|
"epoch": 1.611320754716981,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004739938819188255,
|
|
"loss": 4.9406,
|
|
"mean_token_accuracy": 0.21100088357925414,
|
|
"num_tokens": 35934155.0,
|
|
"step": 20710
|
|
},
|
|
{
|
|
"entropy": 5.5677179336547855,
|
|
"epoch": 1.6117097840886987,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004739809456265727,
|
|
"loss": 5.0009,
|
|
"mean_token_accuracy": 0.20057405531406403,
|
|
"num_tokens": 35942301.0,
|
|
"step": 20715
|
|
},
|
|
{
|
|
"entropy": 5.572567415237427,
|
|
"epoch": 1.6120988134604164,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004739680063151008,
|
|
"loss": 4.9897,
|
|
"mean_token_accuracy": 0.20024237930774688,
|
|
"num_tokens": 35951005.0,
|
|
"step": 20720
|
|
},
|
|
{
|
|
"entropy": 5.603487777709961,
|
|
"epoch": 1.6124878428321339,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004739550639846061,
|
|
"loss": 5.1029,
|
|
"mean_token_accuracy": 0.19691314101219176,
|
|
"num_tokens": 35959425.0,
|
|
"step": 20725
|
|
},
|
|
{
|
|
"entropy": 5.644115734100342,
|
|
"epoch": 1.6128768722038513,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00047394211863528496,
|
|
"loss": 5.0507,
|
|
"mean_token_accuracy": 0.20300205945968627,
|
|
"num_tokens": 35967803.0,
|
|
"step": 20730
|
|
},
|
|
{
|
|
"entropy": 5.65472149848938,
|
|
"epoch": 1.613265901575569,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004739291702673338,
|
|
"loss": 5.1508,
|
|
"mean_token_accuracy": 0.19188271313905716,
|
|
"num_tokens": 35977313.0,
|
|
"step": 20735
|
|
},
|
|
{
|
|
"entropy": 5.754576921463013,
|
|
"epoch": 1.6136549309472865,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004739162188809492,
|
|
"loss": 5.1301,
|
|
"mean_token_accuracy": 0.19150076657533646,
|
|
"num_tokens": 35986404.0,
|
|
"step": 20740
|
|
},
|
|
{
|
|
"entropy": 5.693943977355957,
|
|
"epoch": 1.614043960319004,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00047390326447632747,
|
|
"loss": 5.1136,
|
|
"mean_token_accuracy": 0.1960122987627983,
|
|
"num_tokens": 35995865.0,
|
|
"step": 20745
|
|
},
|
|
{
|
|
"entropy": 5.606211805343628,
|
|
"epoch": 1.6144329896907217,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004738903070536654,
|
|
"loss": 5.0028,
|
|
"mean_token_accuracy": 0.2009105697274208,
|
|
"num_tokens": 36005098.0,
|
|
"step": 20750
|
|
},
|
|
{
|
|
"entropy": 5.585506772994995,
|
|
"epoch": 1.6148220190624392,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004738773466131594,
|
|
"loss": 5.0468,
|
|
"mean_token_accuracy": 0.19974856525659562,
|
|
"num_tokens": 36013642.0,
|
|
"step": 20755
|
|
},
|
|
{
|
|
"entropy": 5.663722085952759,
|
|
"epoch": 1.6152110484341566,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004738643831550063,
|
|
"loss": 5.1496,
|
|
"mean_token_accuracy": 0.19051231145858766,
|
|
"num_tokens": 36022565.0,
|
|
"step": 20760
|
|
},
|
|
{
|
|
"entropy": 5.688801622390747,
|
|
"epoch": 1.6156000778058743,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004738514166794026,
|
|
"loss": 5.105,
|
|
"mean_token_accuracy": 0.19139495342969895,
|
|
"num_tokens": 36031406.0,
|
|
"step": 20765
|
|
},
|
|
{
|
|
"entropy": 5.672761058807373,
|
|
"epoch": 1.615989107177592,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00047383844718654525,
|
|
"loss": 5.1122,
|
|
"mean_token_accuracy": 0.19586308896541596,
|
|
"num_tokens": 36040282.0,
|
|
"step": 20770
|
|
},
|
|
{
|
|
"entropy": 5.731324529647827,
|
|
"epoch": 1.6163781365493095,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004738254746766309,
|
|
"loss": 5.1755,
|
|
"mean_token_accuracy": 0.19230180233716965,
|
|
"num_tokens": 36049647.0,
|
|
"step": 20775
|
|
},
|
|
{
|
|
"entropy": 5.612593412399292,
|
|
"epoch": 1.616767165921027,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004738124991498565,
|
|
"loss": 4.997,
|
|
"mean_token_accuracy": 0.20100639760494232,
|
|
"num_tokens": 36057992.0,
|
|
"step": 20780
|
|
},
|
|
{
|
|
"entropy": 5.637743711471558,
|
|
"epoch": 1.6171561952927447,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00047379952060641866,
|
|
"loss": 5.0465,
|
|
"mean_token_accuracy": 0.19832704663276673,
|
|
"num_tokens": 36066145.0,
|
|
"step": 20785
|
|
},
|
|
{
|
|
"entropy": 5.610766649246216,
|
|
"epoch": 1.6175452246644622,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00047378653904651475,
|
|
"loss": 5.0538,
|
|
"mean_token_accuracy": 0.1973472848534584,
|
|
"num_tokens": 36074596.0,
|
|
"step": 20790
|
|
},
|
|
{
|
|
"entropy": 5.680673980712891,
|
|
"epoch": 1.6179342540361796,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00047377355447034136,
|
|
"loss": 4.9744,
|
|
"mean_token_accuracy": 0.20498497039079666,
|
|
"num_tokens": 36083499.0,
|
|
"step": 20795
|
|
},
|
|
{
|
|
"entropy": 5.675352239608765,
|
|
"epoch": 1.6183232834078973,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004737605668780958,
|
|
"loss": 5.0828,
|
|
"mean_token_accuracy": 0.19587368816137313,
|
|
"num_tokens": 36092293.0,
|
|
"step": 20800
|
|
},
|
|
{
|
|
"entropy": 5.603817415237427,
|
|
"epoch": 1.618712312779615,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00047374757626997494,
|
|
"loss": 5.0672,
|
|
"mean_token_accuracy": 0.19137837141752242,
|
|
"num_tokens": 36100926.0,
|
|
"step": 20805
|
|
},
|
|
{
|
|
"entropy": 5.71808557510376,
|
|
"epoch": 1.6191013421513323,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004737345826461759,
|
|
"loss": 5.117,
|
|
"mean_token_accuracy": 0.1947830930352211,
|
|
"num_tokens": 36109831.0,
|
|
"step": 20810
|
|
},
|
|
{
|
|
"entropy": 5.720207166671753,
|
|
"epoch": 1.61949037152305,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004737215860068959,
|
|
"loss": 5.1604,
|
|
"mean_token_accuracy": 0.19615888744592666,
|
|
"num_tokens": 36118759.0,
|
|
"step": 20815
|
|
},
|
|
{
|
|
"entropy": 5.680451774597168,
|
|
"epoch": 1.6198794008947677,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00047370858635233223,
|
|
"loss": 5.1996,
|
|
"mean_token_accuracy": 0.18841734826564788,
|
|
"num_tokens": 36127854.0,
|
|
"step": 20820
|
|
},
|
|
{
|
|
"entropy": 5.649180889129639,
|
|
"epoch": 1.6202684302664851,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00047369558368268194,
|
|
"loss": 5.1098,
|
|
"mean_token_accuracy": 0.19646184742450715,
|
|
"num_tokens": 36137686.0,
|
|
"step": 20825
|
|
},
|
|
{
|
|
"entropy": 5.7078650951385494,
|
|
"epoch": 1.6206574596382026,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004736825779981424,
|
|
"loss": 5.0943,
|
|
"mean_token_accuracy": 0.19082683622837066,
|
|
"num_tokens": 36146352.0,
|
|
"step": 20830
|
|
},
|
|
{
|
|
"entropy": 5.636092805862427,
|
|
"epoch": 1.6210464890099203,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004736695692989111,
|
|
"loss": 5.0235,
|
|
"mean_token_accuracy": 0.19839919209480286,
|
|
"num_tokens": 36156106.0,
|
|
"step": 20835
|
|
},
|
|
{
|
|
"entropy": 5.604526233673096,
|
|
"epoch": 1.6214355183816378,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004736565575851852,
|
|
"loss": 4.9353,
|
|
"mean_token_accuracy": 0.20191120654344558,
|
|
"num_tokens": 36164169.0,
|
|
"step": 20840
|
|
},
|
|
{
|
|
"entropy": 5.657121229171753,
|
|
"epoch": 1.6218245477533553,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004736435428571622,
|
|
"loss": 5.0836,
|
|
"mean_token_accuracy": 0.19656098037958145,
|
|
"num_tokens": 36173368.0,
|
|
"step": 20845
|
|
},
|
|
{
|
|
"entropy": 5.669279909133911,
|
|
"epoch": 1.622213577125073,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004736305251150397,
|
|
"loss": 5.0564,
|
|
"mean_token_accuracy": 0.19547295570373535,
|
|
"num_tokens": 36182405.0,
|
|
"step": 20850
|
|
},
|
|
{
|
|
"entropy": 5.653002834320068,
|
|
"epoch": 1.6226026064967907,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004736175043590151,
|
|
"loss": 5.1261,
|
|
"mean_token_accuracy": 0.19115351438522338,
|
|
"num_tokens": 36191683.0,
|
|
"step": 20855
|
|
},
|
|
{
|
|
"entropy": 5.658615255355835,
|
|
"epoch": 1.622991635868508,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000473604480589286,
|
|
"loss": 5.0142,
|
|
"mean_token_accuracy": 0.1963836133480072,
|
|
"num_tokens": 36200173.0,
|
|
"step": 20860
|
|
},
|
|
{
|
|
"entropy": 5.559234714508056,
|
|
"epoch": 1.6233806652402256,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00047359145380605007,
|
|
"loss": 5.0341,
|
|
"mean_token_accuracy": 0.1956578016281128,
|
|
"num_tokens": 36209057.0,
|
|
"step": 20865
|
|
},
|
|
{
|
|
"entropy": 5.611531209945679,
|
|
"epoch": 1.6237696946119433,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004735784240095049,
|
|
"loss": 5.0414,
|
|
"mean_token_accuracy": 0.1999165654182434,
|
|
"num_tokens": 36217645.0,
|
|
"step": 20870
|
|
},
|
|
{
|
|
"entropy": 5.714205408096314,
|
|
"epoch": 1.6241587239836608,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00047356539119984813,
|
|
"loss": 5.1148,
|
|
"mean_token_accuracy": 0.19280873239040375,
|
|
"num_tokens": 36226282.0,
|
|
"step": 20875
|
|
},
|
|
{
|
|
"entropy": 5.635988759994507,
|
|
"epoch": 1.6245477533553783,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004735523553772777,
|
|
"loss": 5.1034,
|
|
"mean_token_accuracy": 0.19602324962615966,
|
|
"num_tokens": 36235322.0,
|
|
"step": 20880
|
|
},
|
|
{
|
|
"entropy": 5.6181481838226315,
|
|
"epoch": 1.624936782727096,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004735393165419912,
|
|
"loss": 5.0222,
|
|
"mean_token_accuracy": 0.20810025185346603,
|
|
"num_tokens": 36244212.0,
|
|
"step": 20885
|
|
},
|
|
{
|
|
"entropy": 5.6242388725280765,
|
|
"epoch": 1.6253258120988134,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00047352627469418666,
|
|
"loss": 5.0505,
|
|
"mean_token_accuracy": 0.19684476107358934,
|
|
"num_tokens": 36252837.0,
|
|
"step": 20890
|
|
},
|
|
{
|
|
"entropy": 5.70183482170105,
|
|
"epoch": 1.625714841470531,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004735132298340619,
|
|
"loss": 5.0918,
|
|
"mean_token_accuracy": 0.188697150349617,
|
|
"num_tokens": 36261492.0,
|
|
"step": 20895
|
|
},
|
|
{
|
|
"entropy": 5.670249605178833,
|
|
"epoch": 1.6261038708422486,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004735001819618148,
|
|
"loss": 5.0639,
|
|
"mean_token_accuracy": 0.1967158392071724,
|
|
"num_tokens": 36270195.0,
|
|
"step": 20900
|
|
},
|
|
{
|
|
"entropy": 5.6828728199005125,
|
|
"epoch": 1.6264929002139663,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004734871310776434,
|
|
"loss": 5.0073,
|
|
"mean_token_accuracy": 0.21293383240699768,
|
|
"num_tokens": 36278546.0,
|
|
"step": 20905
|
|
},
|
|
{
|
|
"entropy": 5.668334245681763,
|
|
"epoch": 1.6268819295856836,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004734740771817457,
|
|
"loss": 5.1361,
|
|
"mean_token_accuracy": 0.18799256533384323,
|
|
"num_tokens": 36287433.0,
|
|
"step": 20910
|
|
},
|
|
{
|
|
"entropy": 5.582912302017212,
|
|
"epoch": 1.6272709589574013,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004734610202743198,
|
|
"loss": 4.9889,
|
|
"mean_token_accuracy": 0.18900973051786424,
|
|
"num_tokens": 36296213.0,
|
|
"step": 20915
|
|
},
|
|
{
|
|
"entropy": 5.5907923698425295,
|
|
"epoch": 1.627659988329119,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004734479603555638,
|
|
"loss": 4.9535,
|
|
"mean_token_accuracy": 0.2138149544596672,
|
|
"num_tokens": 36303989.0,
|
|
"step": 20920
|
|
},
|
|
{
|
|
"entropy": 5.713953113555908,
|
|
"epoch": 1.6280490177008364,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00047343489742567593,
|
|
"loss": 5.2562,
|
|
"mean_token_accuracy": 0.18459749966859818,
|
|
"num_tokens": 36312939.0,
|
|
"step": 20925
|
|
},
|
|
{
|
|
"entropy": 5.702159643173218,
|
|
"epoch": 1.628438047072554,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00047342183148485424,
|
|
"loss": 5.0351,
|
|
"mean_token_accuracy": 0.20019447952508926,
|
|
"num_tokens": 36322130.0,
|
|
"step": 20930
|
|
},
|
|
{
|
|
"entropy": 5.649999284744263,
|
|
"epoch": 1.6288270764442716,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00047340876253329706,
|
|
"loss": 4.9951,
|
|
"mean_token_accuracy": 0.19987224489450456,
|
|
"num_tokens": 36330376.0,
|
|
"step": 20935
|
|
},
|
|
{
|
|
"entropy": 5.579406833648681,
|
|
"epoch": 1.629216105815989,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00047339569057120275,
|
|
"loss": 5.004,
|
|
"mean_token_accuracy": 0.20319799184799195,
|
|
"num_tokens": 36339614.0,
|
|
"step": 20940
|
|
},
|
|
{
|
|
"entropy": 5.659418344497681,
|
|
"epoch": 1.6296051351877066,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00047338261559876966,
|
|
"loss": 5.1035,
|
|
"mean_token_accuracy": 0.19244890213012694,
|
|
"num_tokens": 36349561.0,
|
|
"step": 20945
|
|
},
|
|
{
|
|
"entropy": 5.707289171218872,
|
|
"epoch": 1.6299941645594243,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00047336953761619604,
|
|
"loss": 5.1455,
|
|
"mean_token_accuracy": 0.189005284011364,
|
|
"num_tokens": 36358277.0,
|
|
"step": 20950
|
|
},
|
|
{
|
|
"entropy": 5.719502544403076,
|
|
"epoch": 1.630383193931142,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00047335645662368046,
|
|
"loss": 5.1167,
|
|
"mean_token_accuracy": 0.19907114356756211,
|
|
"num_tokens": 36366736.0,
|
|
"step": 20955
|
|
},
|
|
{
|
|
"entropy": 5.663247871398926,
|
|
"epoch": 1.6307722233028592,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004733433726214214,
|
|
"loss": 5.0661,
|
|
"mean_token_accuracy": 0.20213507413864135,
|
|
"num_tokens": 36374802.0,
|
|
"step": 20960
|
|
},
|
|
{
|
|
"entropy": 5.646998643875122,
|
|
"epoch": 1.631161252674577,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00047333028560961733,
|
|
"loss": 5.0854,
|
|
"mean_token_accuracy": 0.19363243728876114,
|
|
"num_tokens": 36384195.0,
|
|
"step": 20965
|
|
},
|
|
{
|
|
"entropy": 5.631627368927002,
|
|
"epoch": 1.6315502820462946,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00047331719558846687,
|
|
"loss": 5.0988,
|
|
"mean_token_accuracy": 0.19158527851104737,
|
|
"num_tokens": 36393001.0,
|
|
"step": 20970
|
|
},
|
|
{
|
|
"entropy": 5.679379653930664,
|
|
"epoch": 1.631939311418012,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00047330410255816863,
|
|
"loss": 5.0502,
|
|
"mean_token_accuracy": 0.18936222791671753,
|
|
"num_tokens": 36401674.0,
|
|
"step": 20975
|
|
},
|
|
{
|
|
"entropy": 5.610768032073975,
|
|
"epoch": 1.6323283407897295,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00047329100651892123,
|
|
"loss": 5.0255,
|
|
"mean_token_accuracy": 0.20752585530281067,
|
|
"num_tokens": 36409817.0,
|
|
"step": 20980
|
|
},
|
|
{
|
|
"entropy": 5.630240964889526,
|
|
"epoch": 1.6327173701614472,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004732779074709234,
|
|
"loss": 4.9905,
|
|
"mean_token_accuracy": 0.20000280290842057,
|
|
"num_tokens": 36417541.0,
|
|
"step": 20985
|
|
},
|
|
{
|
|
"entropy": 5.6237305164337155,
|
|
"epoch": 1.6331063995331647,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000473264805414374,
|
|
"loss": 5.1055,
|
|
"mean_token_accuracy": 0.18834645599126815,
|
|
"num_tokens": 36426613.0,
|
|
"step": 20990
|
|
},
|
|
{
|
|
"entropy": 5.651272487640381,
|
|
"epoch": 1.6334954289048822,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00047325170034947167,
|
|
"loss": 5.0966,
|
|
"mean_token_accuracy": 0.19901169538497926,
|
|
"num_tokens": 36436052.0,
|
|
"step": 20995
|
|
},
|
|
{
|
|
"entropy": 5.612300539016724,
|
|
"epoch": 1.6338844582766,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00047323859227641537,
|
|
"loss": 5.0048,
|
|
"mean_token_accuracy": 0.20065058767795563,
|
|
"num_tokens": 36444386.0,
|
|
"step": 21000
|
|
},
|
|
{
|
|
"epoch": 1.6338844582766,
|
|
"eval_entropy": 5.425801253846566,
|
|
"eval_loss": 5.124657154083252,
|
|
"eval_mean_token_accuracy": 0.20376745658757253,
|
|
"eval_num_tokens": 36444386.0,
|
|
"eval_runtime": 21.8112,
|
|
"eval_samples_per_second": 1905.353,
|
|
"eval_steps_per_second": 238.181,
|
|
"step": 21000
|
|
},
|
|
{
|
|
"entropy": 5.685236263275146,
|
|
"epoch": 1.6342734876483176,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00047322548119540397,
|
|
"loss": 5.0627,
|
|
"mean_token_accuracy": 0.1946759581565857,
|
|
"num_tokens": 36452759.0,
|
|
"step": 21005
|
|
},
|
|
{
|
|
"entropy": 5.650661134719849,
|
|
"epoch": 1.634662517020035,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00047321236710663636,
|
|
"loss": 5.024,
|
|
"mean_token_accuracy": 0.20091758370399476,
|
|
"num_tokens": 36460581.0,
|
|
"step": 21010
|
|
},
|
|
{
|
|
"entropy": 5.629543972015381,
|
|
"epoch": 1.6350515463917525,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00047319925001031165,
|
|
"loss": 5.0451,
|
|
"mean_token_accuracy": 0.20526855140924455,
|
|
"num_tokens": 36468995.0,
|
|
"step": 21015
|
|
},
|
|
{
|
|
"entropy": 5.718970918655396,
|
|
"epoch": 1.6354405757634702,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004731861299066287,
|
|
"loss": 5.1196,
|
|
"mean_token_accuracy": 0.19818554818630219,
|
|
"num_tokens": 36477901.0,
|
|
"step": 21020
|
|
},
|
|
{
|
|
"entropy": 5.68755407333374,
|
|
"epoch": 1.6358296051351877,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004731730067957867,
|
|
"loss": 5.1119,
|
|
"mean_token_accuracy": 0.19964181035757064,
|
|
"num_tokens": 36486500.0,
|
|
"step": 21025
|
|
},
|
|
{
|
|
"entropy": 5.626431035995483,
|
|
"epoch": 1.6362186345069052,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00047315988067798476,
|
|
"loss": 5.053,
|
|
"mean_token_accuracy": 0.19768139570951462,
|
|
"num_tokens": 36495247.0,
|
|
"step": 21030
|
|
},
|
|
{
|
|
"entropy": 5.626111078262329,
|
|
"epoch": 1.6366076638786229,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000473146751553422,
|
|
"loss": 5.0111,
|
|
"mean_token_accuracy": 0.206063412129879,
|
|
"num_tokens": 36503633.0,
|
|
"step": 21035
|
|
},
|
|
{
|
|
"entropy": 5.65632381439209,
|
|
"epoch": 1.6369966932503404,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004731336194222978,
|
|
"loss": 5.0788,
|
|
"mean_token_accuracy": 0.1980946645140648,
|
|
"num_tokens": 36512138.0,
|
|
"step": 21040
|
|
},
|
|
{
|
|
"entropy": 5.6815392017364506,
|
|
"epoch": 1.6373857226220578,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00047312048428481114,
|
|
"loss": 5.061,
|
|
"mean_token_accuracy": 0.20013161301612853,
|
|
"num_tokens": 36521029.0,
|
|
"step": 21045
|
|
},
|
|
{
|
|
"entropy": 5.608483123779297,
|
|
"epoch": 1.6377747519937755,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00047310734614116153,
|
|
"loss": 4.9886,
|
|
"mean_token_accuracy": 0.20001065731048584,
|
|
"num_tokens": 36530658.0,
|
|
"step": 21050
|
|
},
|
|
{
|
|
"entropy": 5.618550252914429,
|
|
"epoch": 1.6381637813654932,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004730942049915483,
|
|
"loss": 4.9898,
|
|
"mean_token_accuracy": 0.1970773383975029,
|
|
"num_tokens": 36539037.0,
|
|
"step": 21055
|
|
},
|
|
{
|
|
"entropy": 5.646327257156372,
|
|
"epoch": 1.6385528107372107,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004730810608361707,
|
|
"loss": 5.0826,
|
|
"mean_token_accuracy": 0.1998617023229599,
|
|
"num_tokens": 36547863.0,
|
|
"step": 21060
|
|
},
|
|
{
|
|
"entropy": 5.684886646270752,
|
|
"epoch": 1.6389418401089282,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00047306791367522833,
|
|
"loss": 5.1045,
|
|
"mean_token_accuracy": 0.19899885803461076,
|
|
"num_tokens": 36555896.0,
|
|
"step": 21065
|
|
},
|
|
{
|
|
"entropy": 5.595557403564453,
|
|
"epoch": 1.6393308694806459,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004730547635089206,
|
|
"loss": 5.0367,
|
|
"mean_token_accuracy": 0.20867674499750138,
|
|
"num_tokens": 36564088.0,
|
|
"step": 21070
|
|
},
|
|
{
|
|
"entropy": 5.656909227371216,
|
|
"epoch": 1.6397198988523634,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00047304161033744714,
|
|
"loss": 4.9992,
|
|
"mean_token_accuracy": 0.2010756775736809,
|
|
"num_tokens": 36572490.0,
|
|
"step": 21075
|
|
},
|
|
{
|
|
"entropy": 5.686183261871338,
|
|
"epoch": 1.6401089282240808,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004730284541610075,
|
|
"loss": 5.0703,
|
|
"mean_token_accuracy": 0.1874392732977867,
|
|
"num_tokens": 36580834.0,
|
|
"step": 21080
|
|
},
|
|
{
|
|
"entropy": 5.637238359451294,
|
|
"epoch": 1.6404979575957985,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004730152949798012,
|
|
"loss": 5.0346,
|
|
"mean_token_accuracy": 0.20410232841968537,
|
|
"num_tokens": 36589420.0,
|
|
"step": 21085
|
|
},
|
|
{
|
|
"entropy": 5.579383277893067,
|
|
"epoch": 1.640886986967516,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00047300213279402787,
|
|
"loss": 5.0534,
|
|
"mean_token_accuracy": 0.19768901467323302,
|
|
"num_tokens": 36598419.0,
|
|
"step": 21090
|
|
},
|
|
{
|
|
"entropy": 5.614743328094482,
|
|
"epoch": 1.6412760163392335,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00047298896760388745,
|
|
"loss": 5.0776,
|
|
"mean_token_accuracy": 0.19908344149589538,
|
|
"num_tokens": 36607367.0,
|
|
"step": 21095
|
|
},
|
|
{
|
|
"entropy": 5.709177398681641,
|
|
"epoch": 1.6416650457109512,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004729757994095796,
|
|
"loss": 5.1625,
|
|
"mean_token_accuracy": 0.19179748445749284,
|
|
"num_tokens": 36616197.0,
|
|
"step": 21100
|
|
},
|
|
{
|
|
"entropy": 5.733490371704102,
|
|
"epoch": 1.6420540750826689,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00047296262821130405,
|
|
"loss": 5.1889,
|
|
"mean_token_accuracy": 0.1905401736497879,
|
|
"num_tokens": 36625452.0,
|
|
"step": 21105
|
|
},
|
|
{
|
|
"entropy": 5.6510701179504395,
|
|
"epoch": 1.6424431044543863,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00047294945400926065,
|
|
"loss": 5.1163,
|
|
"mean_token_accuracy": 0.19272997081279755,
|
|
"num_tokens": 36634356.0,
|
|
"step": 21110
|
|
},
|
|
{
|
|
"entropy": 5.66380820274353,
|
|
"epoch": 1.6428321338261038,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004729362768036494,
|
|
"loss": 5.0771,
|
|
"mean_token_accuracy": 0.19462316185235978,
|
|
"num_tokens": 36642548.0,
|
|
"step": 21115
|
|
},
|
|
{
|
|
"entropy": 5.640546560287476,
|
|
"epoch": 1.6432211631978215,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00047292309659467024,
|
|
"loss": 4.9804,
|
|
"mean_token_accuracy": 0.20825111716985703,
|
|
"num_tokens": 36650548.0,
|
|
"step": 21120
|
|
},
|
|
{
|
|
"entropy": 5.604476976394653,
|
|
"epoch": 1.643610192569539,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004729099133825231,
|
|
"loss": 5.0202,
|
|
"mean_token_accuracy": 0.19761257469654084,
|
|
"num_tokens": 36659322.0,
|
|
"step": 21125
|
|
},
|
|
{
|
|
"entropy": 5.616048955917359,
|
|
"epoch": 1.6439992219412565,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000472896727167408,
|
|
"loss": 5.0039,
|
|
"mean_token_accuracy": 0.20036645233631134,
|
|
"num_tokens": 36667699.0,
|
|
"step": 21130
|
|
},
|
|
{
|
|
"entropy": 5.715201282501221,
|
|
"epoch": 1.6443882513129742,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00047288353794952505,
|
|
"loss": 5.13,
|
|
"mean_token_accuracy": 0.1948148638010025,
|
|
"num_tokens": 36677842.0,
|
|
"step": 21135
|
|
},
|
|
{
|
|
"entropy": 5.608692312240601,
|
|
"epoch": 1.6447772806846916,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004728703457290744,
|
|
"loss": 4.9294,
|
|
"mean_token_accuracy": 0.21180818676948548,
|
|
"num_tokens": 36686488.0,
|
|
"step": 21140
|
|
},
|
|
{
|
|
"entropy": 5.652051067352295,
|
|
"epoch": 1.6451663100564091,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004728571505062562,
|
|
"loss": 5.1088,
|
|
"mean_token_accuracy": 0.19624157398939132,
|
|
"num_tokens": 36694955.0,
|
|
"step": 21145
|
|
},
|
|
{
|
|
"entropy": 5.557367324829102,
|
|
"epoch": 1.6455553394281268,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004728439522812707,
|
|
"loss": 4.9874,
|
|
"mean_token_accuracy": 0.2034481644630432,
|
|
"num_tokens": 36703481.0,
|
|
"step": 21150
|
|
},
|
|
{
|
|
"entropy": 5.686665010452271,
|
|
"epoch": 1.6459443687998445,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00047283075105431806,
|
|
"loss": 5.1937,
|
|
"mean_token_accuracy": 0.19371117651462555,
|
|
"num_tokens": 36711812.0,
|
|
"step": 21155
|
|
},
|
|
{
|
|
"entropy": 5.668038415908813,
|
|
"epoch": 1.646333398171562,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004728175468255987,
|
|
"loss": 5.0522,
|
|
"mean_token_accuracy": 0.20208872854709625,
|
|
"num_tokens": 36720496.0,
|
|
"step": 21160
|
|
},
|
|
{
|
|
"entropy": 5.6225639343261715,
|
|
"epoch": 1.6467224275432795,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00047280433959531287,
|
|
"loss": 4.9297,
|
|
"mean_token_accuracy": 0.20318156331777573,
|
|
"num_tokens": 36728959.0,
|
|
"step": 21165
|
|
},
|
|
{
|
|
"entropy": 5.585181140899659,
|
|
"epoch": 1.6471114569149972,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000472791129363661,
|
|
"loss": 5.0361,
|
|
"mean_token_accuracy": 0.19560608118772507,
|
|
"num_tokens": 36737492.0,
|
|
"step": 21170
|
|
},
|
|
{
|
|
"entropy": 5.640459728240967,
|
|
"epoch": 1.6475004862867146,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004727779161308436,
|
|
"loss": 4.9933,
|
|
"mean_token_accuracy": 0.2004745975136757,
|
|
"num_tokens": 36745852.0,
|
|
"step": 21175
|
|
},
|
|
{
|
|
"entropy": 5.680353593826294,
|
|
"epoch": 1.6478895156584321,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004727646998970612,
|
|
"loss": 5.0735,
|
|
"mean_token_accuracy": 0.19790082424879074,
|
|
"num_tokens": 36753897.0,
|
|
"step": 21180
|
|
},
|
|
{
|
|
"entropy": 5.634651851654053,
|
|
"epoch": 1.6482785450301498,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00047275148066251417,
|
|
"loss": 5.0246,
|
|
"mean_token_accuracy": 0.19867342561483384,
|
|
"num_tokens": 36762737.0,
|
|
"step": 21185
|
|
},
|
|
{
|
|
"entropy": 5.704489469528198,
|
|
"epoch": 1.6486675744018673,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004727382584274032,
|
|
"loss": 5.1112,
|
|
"mean_token_accuracy": 0.19380357414484023,
|
|
"num_tokens": 36770742.0,
|
|
"step": 21190
|
|
},
|
|
{
|
|
"entropy": 5.739238977432251,
|
|
"epoch": 1.6490566037735848,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00047272503319192887,
|
|
"loss": 5.1698,
|
|
"mean_token_accuracy": 0.1844904363155365,
|
|
"num_tokens": 36779420.0,
|
|
"step": 21195
|
|
},
|
|
{
|
|
"entropy": 5.5963489532470705,
|
|
"epoch": 1.6494456331453025,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004727118049562919,
|
|
"loss": 5.0016,
|
|
"mean_token_accuracy": 0.19979230910539628,
|
|
"num_tokens": 36787888.0,
|
|
"step": 21200
|
|
},
|
|
{
|
|
"entropy": 5.57241997718811,
|
|
"epoch": 1.6498346625170202,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000472698573720693,
|
|
"loss": 4.9328,
|
|
"mean_token_accuracy": 0.2079233855009079,
|
|
"num_tokens": 36797131.0,
|
|
"step": 21205
|
|
},
|
|
{
|
|
"entropy": 5.616825723648072,
|
|
"epoch": 1.6502236918887376,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004726853394853329,
|
|
"loss": 5.1078,
|
|
"mean_token_accuracy": 0.19077519625425338,
|
|
"num_tokens": 36805429.0,
|
|
"step": 21210
|
|
},
|
|
{
|
|
"entropy": 5.645532846450806,
|
|
"epoch": 1.650612721260455,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00047267210225041234,
|
|
"loss": 5.1497,
|
|
"mean_token_accuracy": 0.18943463861942292,
|
|
"num_tokens": 36814204.0,
|
|
"step": 21215
|
|
},
|
|
{
|
|
"entropy": 5.757275390625,
|
|
"epoch": 1.6510017506321728,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00047265886201613234,
|
|
"loss": 5.1125,
|
|
"mean_token_accuracy": 0.19360610097646713,
|
|
"num_tokens": 36823229.0,
|
|
"step": 21220
|
|
},
|
|
{
|
|
"entropy": 5.729987573623657,
|
|
"epoch": 1.6513907800038903,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00047264561878269365,
|
|
"loss": 5.18,
|
|
"mean_token_accuracy": 0.18842648416757585,
|
|
"num_tokens": 36832252.0,
|
|
"step": 21225
|
|
},
|
|
{
|
|
"entropy": 5.614921617507934,
|
|
"epoch": 1.6517798093756078,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004726323725502973,
|
|
"loss": 5.0472,
|
|
"mean_token_accuracy": 0.19894642531871795,
|
|
"num_tokens": 36841456.0,
|
|
"step": 21230
|
|
},
|
|
{
|
|
"entropy": 5.6571146011352536,
|
|
"epoch": 1.6521688387473255,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004726191233191443,
|
|
"loss": 5.0228,
|
|
"mean_token_accuracy": 0.2042941778898239,
|
|
"num_tokens": 36849717.0,
|
|
"step": 21235
|
|
},
|
|
{
|
|
"entropy": 5.650038576126098,
|
|
"epoch": 1.6525578681190431,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004726058710894357,
|
|
"loss": 5.1076,
|
|
"mean_token_accuracy": 0.1954307049512863,
|
|
"num_tokens": 36858222.0,
|
|
"step": 21240
|
|
},
|
|
{
|
|
"entropy": 5.592621326446533,
|
|
"epoch": 1.6529468974907604,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004725926158613724,
|
|
"loss": 5.0881,
|
|
"mean_token_accuracy": 0.1922290101647377,
|
|
"num_tokens": 36866899.0,
|
|
"step": 21245
|
|
},
|
|
{
|
|
"entropy": 5.658283805847168,
|
|
"epoch": 1.653335926862478,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004725793576351557,
|
|
"loss": 5.0491,
|
|
"mean_token_accuracy": 0.20789932161569596,
|
|
"num_tokens": 36876124.0,
|
|
"step": 21250
|
|
},
|
|
{
|
|
"entropy": 5.691045713424683,
|
|
"epoch": 1.6537249562341958,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004725660964109867,
|
|
"loss": 5.1068,
|
|
"mean_token_accuracy": 0.19472858160734177,
|
|
"num_tokens": 36884689.0,
|
|
"step": 21255
|
|
},
|
|
{
|
|
"entropy": 5.6766516208648685,
|
|
"epoch": 1.6541139856059133,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00047255283218906673,
|
|
"loss": 5.0806,
|
|
"mean_token_accuracy": 0.1931871712207794,
|
|
"num_tokens": 36893073.0,
|
|
"step": 21260
|
|
},
|
|
{
|
|
"entropy": 5.670859432220459,
|
|
"epoch": 1.6545030149776307,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000472539564969597,
|
|
"loss": 5.0887,
|
|
"mean_token_accuracy": 0.19451346546411513,
|
|
"num_tokens": 36902428.0,
|
|
"step": 21265
|
|
},
|
|
{
|
|
"entropy": 5.69565224647522,
|
|
"epoch": 1.6548920443493484,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00047252629475277863,
|
|
"loss": 5.1098,
|
|
"mean_token_accuracy": 0.19970912784337996,
|
|
"num_tokens": 36910297.0,
|
|
"step": 21270
|
|
},
|
|
{
|
|
"entropy": 5.641442012786865,
|
|
"epoch": 1.655281073721066,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004725130215388132,
|
|
"loss": 5.0534,
|
|
"mean_token_accuracy": 0.19424191415309905,
|
|
"num_tokens": 36919115.0,
|
|
"step": 21275
|
|
},
|
|
{
|
|
"entropy": 5.6860127449035645,
|
|
"epoch": 1.6556701030927834,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004724997453279021,
|
|
"loss": 5.0811,
|
|
"mean_token_accuracy": 0.19655924141407013,
|
|
"num_tokens": 36928419.0,
|
|
"step": 21280
|
|
},
|
|
{
|
|
"entropy": 5.6646819591522215,
|
|
"epoch": 1.656059132464501,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004724864661202467,
|
|
"loss": 5.0378,
|
|
"mean_token_accuracy": 0.20006120949983597,
|
|
"num_tokens": 36936511.0,
|
|
"step": 21285
|
|
},
|
|
{
|
|
"entropy": 5.672817659378052,
|
|
"epoch": 1.6564481618362188,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00047247318391604846,
|
|
"loss": 5.1035,
|
|
"mean_token_accuracy": 0.1965818926692009,
|
|
"num_tokens": 36945316.0,
|
|
"step": 21290
|
|
},
|
|
{
|
|
"entropy": 5.634977912902832,
|
|
"epoch": 1.656837191207936,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00047245989871550897,
|
|
"loss": 5.1275,
|
|
"mean_token_accuracy": 0.18893318325281144,
|
|
"num_tokens": 36954140.0,
|
|
"step": 21295
|
|
},
|
|
{
|
|
"entropy": 5.628003311157227,
|
|
"epoch": 1.6572262205796537,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004724466105188299,
|
|
"loss": 5.0776,
|
|
"mean_token_accuracy": 0.1945530191063881,
|
|
"num_tokens": 36962852.0,
|
|
"step": 21300
|
|
},
|
|
{
|
|
"entropy": 5.7002171039581295,
|
|
"epoch": 1.6576152499513714,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00047243331932621263,
|
|
"loss": 5.0906,
|
|
"mean_token_accuracy": 0.19977089613676072,
|
|
"num_tokens": 36971617.0,
|
|
"step": 21305
|
|
},
|
|
{
|
|
"entropy": 5.641374588012695,
|
|
"epoch": 1.658004279323089,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004724200251378591,
|
|
"loss": 5.1099,
|
|
"mean_token_accuracy": 0.19899785071611403,
|
|
"num_tokens": 36981078.0,
|
|
"step": 21310
|
|
},
|
|
{
|
|
"entropy": 5.644744968414306,
|
|
"epoch": 1.6583933086948064,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004724067279539709,
|
|
"loss": 5.0131,
|
|
"mean_token_accuracy": 0.19661311954259872,
|
|
"num_tokens": 36989860.0,
|
|
"step": 21315
|
|
},
|
|
{
|
|
"entropy": 5.652134370803833,
|
|
"epoch": 1.658782338066524,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00047239342777474975,
|
|
"loss": 5.0463,
|
|
"mean_token_accuracy": 0.2002684146165848,
|
|
"num_tokens": 36998037.0,
|
|
"step": 21320
|
|
},
|
|
{
|
|
"entropy": 5.707924842834473,
|
|
"epoch": 1.6591713674382416,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00047238012460039765,
|
|
"loss": 5.0732,
|
|
"mean_token_accuracy": 0.19763096421957016,
|
|
"num_tokens": 37006375.0,
|
|
"step": 21325
|
|
},
|
|
{
|
|
"entropy": 5.6436220645904545,
|
|
"epoch": 1.659560396809959,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004723668184311162,
|
|
"loss": 5.141,
|
|
"mean_token_accuracy": 0.18975942879915236,
|
|
"num_tokens": 37014650.0,
|
|
"step": 21330
|
|
},
|
|
{
|
|
"entropy": 5.637217855453491,
|
|
"epoch": 1.6599494261816767,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004723535092671074,
|
|
"loss": 5.1053,
|
|
"mean_token_accuracy": 0.18916617184877396,
|
|
"num_tokens": 37023147.0,
|
|
"step": 21335
|
|
},
|
|
{
|
|
"entropy": 5.749104070663452,
|
|
"epoch": 1.6603384555533944,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00047234019710857335,
|
|
"loss": 5.1037,
|
|
"mean_token_accuracy": 0.1955679774284363,
|
|
"num_tokens": 37031461.0,
|
|
"step": 21340
|
|
},
|
|
{
|
|
"entropy": 5.726814270019531,
|
|
"epoch": 1.6607274849251117,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004723268819557158,
|
|
"loss": 5.1414,
|
|
"mean_token_accuracy": 0.19410899430513381,
|
|
"num_tokens": 37039924.0,
|
|
"step": 21345
|
|
},
|
|
{
|
|
"entropy": 5.630940341949463,
|
|
"epoch": 1.6611165142968294,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00047231356380873687,
|
|
"loss": 5.038,
|
|
"mean_token_accuracy": 0.20254645347595215,
|
|
"num_tokens": 37048631.0,
|
|
"step": 21350
|
|
},
|
|
{
|
|
"entropy": 5.637073755264282,
|
|
"epoch": 1.661505543668547,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004723002426678388,
|
|
"loss": 5.0486,
|
|
"mean_token_accuracy": 0.2034415289759636,
|
|
"num_tokens": 37057018.0,
|
|
"step": 21355
|
|
},
|
|
{
|
|
"entropy": 5.666430187225342,
|
|
"epoch": 1.6618945730402646,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004722869185332235,
|
|
"loss": 5.083,
|
|
"mean_token_accuracy": 0.19698277115821838,
|
|
"num_tokens": 37065762.0,
|
|
"step": 21360
|
|
},
|
|
{
|
|
"entropy": 5.638964700698852,
|
|
"epoch": 1.662283602411982,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00047227359140509324,
|
|
"loss": 5.0778,
|
|
"mean_token_accuracy": 0.19166834354400636,
|
|
"num_tokens": 37073836.0,
|
|
"step": 21365
|
|
},
|
|
{
|
|
"entropy": 5.654311800003052,
|
|
"epoch": 1.6626726317836997,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004722602612836501,
|
|
"loss": 5.127,
|
|
"mean_token_accuracy": 0.19017945677042009,
|
|
"num_tokens": 37082788.0,
|
|
"step": 21370
|
|
},
|
|
{
|
|
"entropy": 5.716874313354492,
|
|
"epoch": 1.6630616611554172,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00047224692816909665,
|
|
"loss": 5.1524,
|
|
"mean_token_accuracy": 0.18403398394584655,
|
|
"num_tokens": 37091228.0,
|
|
"step": 21375
|
|
},
|
|
{
|
|
"entropy": 5.668335390090943,
|
|
"epoch": 1.6634506905271347,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004722335920616349,
|
|
"loss": 5.0562,
|
|
"mean_token_accuracy": 0.19864943325519563,
|
|
"num_tokens": 37099819.0,
|
|
"step": 21380
|
|
},
|
|
{
|
|
"entropy": 5.638710927963257,
|
|
"epoch": 1.6638397198988524,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00047222025296146745,
|
|
"loss": 5.0927,
|
|
"mean_token_accuracy": 0.1881011739373207,
|
|
"num_tokens": 37108129.0,
|
|
"step": 21385
|
|
},
|
|
{
|
|
"entropy": 5.591794013977051,
|
|
"epoch": 1.66422874927057,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00047220691086879643,
|
|
"loss": 4.994,
|
|
"mean_token_accuracy": 0.2084198921918869,
|
|
"num_tokens": 37116093.0,
|
|
"step": 21390
|
|
},
|
|
{
|
|
"entropy": 5.622945880889892,
|
|
"epoch": 1.6646177786422873,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004721935657838245,
|
|
"loss": 5.0458,
|
|
"mean_token_accuracy": 0.1923132747411728,
|
|
"num_tokens": 37124098.0,
|
|
"step": 21395
|
|
},
|
|
{
|
|
"entropy": 5.719037961959839,
|
|
"epoch": 1.665006808014005,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000472180217706754,
|
|
"loss": 5.1232,
|
|
"mean_token_accuracy": 0.18765225410461425,
|
|
"num_tokens": 37132608.0,
|
|
"step": 21400
|
|
},
|
|
{
|
|
"entropy": 5.701768589019776,
|
|
"epoch": 1.6653958373857227,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004721668666377876,
|
|
"loss": 5.127,
|
|
"mean_token_accuracy": 0.19519110321998595,
|
|
"num_tokens": 37141365.0,
|
|
"step": 21405
|
|
},
|
|
{
|
|
"entropy": 5.592532682418823,
|
|
"epoch": 1.6657848667574402,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00047215351257712783,
|
|
"loss": 5.0091,
|
|
"mean_token_accuracy": 0.20509780645370485,
|
|
"num_tokens": 37150146.0,
|
|
"step": 21410
|
|
},
|
|
{
|
|
"entropy": 5.720004463195801,
|
|
"epoch": 1.6661738961291577,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00047214015552497735,
|
|
"loss": 5.1887,
|
|
"mean_token_accuracy": 0.1878465473651886,
|
|
"num_tokens": 37158887.0,
|
|
"step": 21415
|
|
},
|
|
{
|
|
"entropy": 5.709566068649292,
|
|
"epoch": 1.6665629255008754,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00047212679548153867,
|
|
"loss": 5.0286,
|
|
"mean_token_accuracy": 0.1976467952132225,
|
|
"num_tokens": 37167902.0,
|
|
"step": 21420
|
|
},
|
|
{
|
|
"entropy": 5.7032022953033445,
|
|
"epoch": 1.6669519548725928,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00047211343244701475,
|
|
"loss": 5.1605,
|
|
"mean_token_accuracy": 0.19156619608402253,
|
|
"num_tokens": 37175853.0,
|
|
"step": 21425
|
|
},
|
|
{
|
|
"entropy": 5.619184303283691,
|
|
"epoch": 1.6673409842443103,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004721000664216081,
|
|
"loss": 5.0397,
|
|
"mean_token_accuracy": 0.19947168380022048,
|
|
"num_tokens": 37184036.0,
|
|
"step": 21430
|
|
},
|
|
{
|
|
"entropy": 5.685922431945801,
|
|
"epoch": 1.667730013616028,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004720866974055219,
|
|
"loss": 5.1022,
|
|
"mean_token_accuracy": 0.19761382937431335,
|
|
"num_tokens": 37193277.0,
|
|
"step": 21435
|
|
},
|
|
{
|
|
"entropy": 5.701192426681518,
|
|
"epoch": 1.6681190429877457,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004720733253989585,
|
|
"loss": 5.0644,
|
|
"mean_token_accuracy": 0.2003820925951004,
|
|
"num_tokens": 37201925.0,
|
|
"step": 21440
|
|
},
|
|
{
|
|
"entropy": 5.6847645282745365,
|
|
"epoch": 1.6685080723594632,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00047205995040212114,
|
|
"loss": 5.1555,
|
|
"mean_token_accuracy": 0.1892498627305031,
|
|
"num_tokens": 37210552.0,
|
|
"step": 21445
|
|
},
|
|
{
|
|
"entropy": 5.6613525390625,
|
|
"epoch": 1.6688971017311807,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004720465724152127,
|
|
"loss": 5.0784,
|
|
"mean_token_accuracy": 0.1969710037112236,
|
|
"num_tokens": 37219001.0,
|
|
"step": 21450
|
|
},
|
|
{
|
|
"entropy": 5.64767861366272,
|
|
"epoch": 1.6692861311028984,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00047203319143843613,
|
|
"loss": 5.0381,
|
|
"mean_token_accuracy": 0.20369212180376053,
|
|
"num_tokens": 37227635.0,
|
|
"step": 21455
|
|
},
|
|
{
|
|
"entropy": 5.615681934356689,
|
|
"epoch": 1.6696751604746158,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004720198074719946,
|
|
"loss": 5.0596,
|
|
"mean_token_accuracy": 0.19911978095769883,
|
|
"num_tokens": 37236872.0,
|
|
"step": 21460
|
|
},
|
|
{
|
|
"entropy": 5.706751585006714,
|
|
"epoch": 1.6700641898463333,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00047200642051609094,
|
|
"loss": 5.1304,
|
|
"mean_token_accuracy": 0.1907180964946747,
|
|
"num_tokens": 37245026.0,
|
|
"step": 21465
|
|
},
|
|
{
|
|
"entropy": 5.680355262756348,
|
|
"epoch": 1.670453219218051,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004719930305709285,
|
|
"loss": 5.0714,
|
|
"mean_token_accuracy": 0.19570827186107637,
|
|
"num_tokens": 37253295.0,
|
|
"step": 21470
|
|
},
|
|
{
|
|
"entropy": 5.651104497909546,
|
|
"epoch": 1.6708422485897685,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00047197963763671033,
|
|
"loss": 5.0467,
|
|
"mean_token_accuracy": 0.2063677117228508,
|
|
"num_tokens": 37262785.0,
|
|
"step": 21475
|
|
},
|
|
{
|
|
"entropy": 5.642996978759766,
|
|
"epoch": 1.671231277961486,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004719662417136397,
|
|
"loss": 5.1256,
|
|
"mean_token_accuracy": 0.2006133183836937,
|
|
"num_tokens": 37271937.0,
|
|
"step": 21480
|
|
},
|
|
{
|
|
"entropy": 5.6505739212036135,
|
|
"epoch": 1.6716203073332037,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00047195284280191987,
|
|
"loss": 5.0212,
|
|
"mean_token_accuracy": 0.20324522256851196,
|
|
"num_tokens": 37280861.0,
|
|
"step": 21485
|
|
},
|
|
{
|
|
"entropy": 5.671285104751587,
|
|
"epoch": 1.6720093367049214,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004719394409017541,
|
|
"loss": 5.0643,
|
|
"mean_token_accuracy": 0.19922929108142853,
|
|
"num_tokens": 37289235.0,
|
|
"step": 21490
|
|
},
|
|
{
|
|
"entropy": 5.64128360748291,
|
|
"epoch": 1.6723983660766388,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00047192603601334585,
|
|
"loss": 5.0703,
|
|
"mean_token_accuracy": 0.19294965714216233,
|
|
"num_tokens": 37297778.0,
|
|
"step": 21495
|
|
},
|
|
{
|
|
"entropy": 5.645361471176147,
|
|
"epoch": 1.6727873954483563,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00047191262813689835,
|
|
"loss": 5.0826,
|
|
"mean_token_accuracy": 0.19001952558755875,
|
|
"num_tokens": 37306960.0,
|
|
"step": 21500
|
|
},
|
|
{
|
|
"entropy": 5.659552669525146,
|
|
"epoch": 1.673176424820074,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004718992172726152,
|
|
"loss": 5.1064,
|
|
"mean_token_accuracy": 0.19469638764858246,
|
|
"num_tokens": 37316050.0,
|
|
"step": 21505
|
|
},
|
|
{
|
|
"entropy": 5.586802673339844,
|
|
"epoch": 1.6735654541917915,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00047188580342069983,
|
|
"loss": 5.0591,
|
|
"mean_token_accuracy": 0.19923404604196548,
|
|
"num_tokens": 37325058.0,
|
|
"step": 21510
|
|
},
|
|
{
|
|
"entropy": 5.712506818771362,
|
|
"epoch": 1.673954483563509,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004718723865813557,
|
|
"loss": 5.1592,
|
|
"mean_token_accuracy": 0.18860733211040498,
|
|
"num_tokens": 37333512.0,
|
|
"step": 21515
|
|
},
|
|
{
|
|
"entropy": 5.677211666107178,
|
|
"epoch": 1.6743435129352267,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004718589667547865,
|
|
"loss": 5.0552,
|
|
"mean_token_accuracy": 0.20085858553647995,
|
|
"num_tokens": 37341695.0,
|
|
"step": 21520
|
|
},
|
|
{
|
|
"entropy": 5.693460464477539,
|
|
"epoch": 1.6747325423069441,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004718455439411958,
|
|
"loss": 5.2198,
|
|
"mean_token_accuracy": 0.18530402928590775,
|
|
"num_tokens": 37350917.0,
|
|
"step": 21525
|
|
},
|
|
{
|
|
"entropy": 5.735363435745239,
|
|
"epoch": 1.6751215716786616,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004718321181407873,
|
|
"loss": 5.1697,
|
|
"mean_token_accuracy": 0.1849642351269722,
|
|
"num_tokens": 37360206.0,
|
|
"step": 21530
|
|
},
|
|
{
|
|
"entropy": 5.744312524795532,
|
|
"epoch": 1.6755106010503793,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004718186893537647,
|
|
"loss": 5.1339,
|
|
"mean_token_accuracy": 0.19340480268001556,
|
|
"num_tokens": 37369378.0,
|
|
"step": 21535
|
|
},
|
|
{
|
|
"entropy": 5.660828876495361,
|
|
"epoch": 1.675899630422097,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004718052575803318,
|
|
"loss": 5.0524,
|
|
"mean_token_accuracy": 0.20309800207614898,
|
|
"num_tokens": 37377744.0,
|
|
"step": 21540
|
|
},
|
|
{
|
|
"entropy": 5.667059135437012,
|
|
"epoch": 1.6762886597938145,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004717918228206923,
|
|
"loss": 5.0565,
|
|
"mean_token_accuracy": 0.19197254925966262,
|
|
"num_tokens": 37387097.0,
|
|
"step": 21545
|
|
},
|
|
{
|
|
"entropy": 5.713493490219117,
|
|
"epoch": 1.676677689165532,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004717783850750501,
|
|
"loss": 5.1459,
|
|
"mean_token_accuracy": 0.1895543411374092,
|
|
"num_tokens": 37395551.0,
|
|
"step": 21550
|
|
},
|
|
{
|
|
"entropy": 5.630736780166626,
|
|
"epoch": 1.6770667185372496,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004717649443436091,
|
|
"loss": 4.9281,
|
|
"mean_token_accuracy": 0.20800315886735915,
|
|
"num_tokens": 37403876.0,
|
|
"step": 21555
|
|
},
|
|
{
|
|
"entropy": 5.658391809463501,
|
|
"epoch": 1.6774557479089671,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00047175150062657336,
|
|
"loss": 5.0505,
|
|
"mean_token_accuracy": 0.1969800129532814,
|
|
"num_tokens": 37412658.0,
|
|
"step": 21560
|
|
},
|
|
{
|
|
"entropy": 5.656177282333374,
|
|
"epoch": 1.6778447772806846,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00047173805392414664,
|
|
"loss": 5.0293,
|
|
"mean_token_accuracy": 0.19987383335828782,
|
|
"num_tokens": 37420790.0,
|
|
"step": 21565
|
|
},
|
|
{
|
|
"entropy": 5.639275074005127,
|
|
"epoch": 1.6782338066524023,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004717246042365332,
|
|
"loss": 5.098,
|
|
"mean_token_accuracy": 0.19355754554271698,
|
|
"num_tokens": 37428866.0,
|
|
"step": 21570
|
|
},
|
|
{
|
|
"entropy": 5.6372967720031735,
|
|
"epoch": 1.6786228360241198,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00047171115156393695,
|
|
"loss": 5.032,
|
|
"mean_token_accuracy": 0.2024747237563133,
|
|
"num_tokens": 37437636.0,
|
|
"step": 21575
|
|
},
|
|
{
|
|
"entropy": 5.6486818313598635,
|
|
"epoch": 1.6790118653958372,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00047169769590656207,
|
|
"loss": 5.0879,
|
|
"mean_token_accuracy": 0.19749243259429933,
|
|
"num_tokens": 37446455.0,
|
|
"step": 21580
|
|
},
|
|
{
|
|
"entropy": 5.641884803771973,
|
|
"epoch": 1.679400894767555,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00047168423726461273,
|
|
"loss": 5.1577,
|
|
"mean_token_accuracy": 0.1887023076415062,
|
|
"num_tokens": 37454997.0,
|
|
"step": 21585
|
|
},
|
|
{
|
|
"entropy": 5.637234306335449,
|
|
"epoch": 1.6797899241392726,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004716707756382931,
|
|
"loss": 4.9943,
|
|
"mean_token_accuracy": 0.20316977947950363,
|
|
"num_tokens": 37463701.0,
|
|
"step": 21590
|
|
},
|
|
{
|
|
"entropy": 5.703650093078613,
|
|
"epoch": 1.6801789535109901,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00047165731102780757,
|
|
"loss": 5.1235,
|
|
"mean_token_accuracy": 0.18962299823760986,
|
|
"num_tokens": 37472460.0,
|
|
"step": 21595
|
|
},
|
|
{
|
|
"entropy": 5.677802467346192,
|
|
"epoch": 1.6805679828827076,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00047164384343336037,
|
|
"loss": 5.0337,
|
|
"mean_token_accuracy": 0.19802031815052032,
|
|
"num_tokens": 37481114.0,
|
|
"step": 21600
|
|
},
|
|
{
|
|
"entropy": 5.6594819068908695,
|
|
"epoch": 1.6809570122544253,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00047163037285515583,
|
|
"loss": 5.1129,
|
|
"mean_token_accuracy": 0.19172435253858566,
|
|
"num_tokens": 37489593.0,
|
|
"step": 21605
|
|
},
|
|
{
|
|
"entropy": 5.726067781448364,
|
|
"epoch": 1.6813460416261428,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004716168992933982,
|
|
"loss": 5.1599,
|
|
"mean_token_accuracy": 0.19118998050689698,
|
|
"num_tokens": 37498044.0,
|
|
"step": 21610
|
|
},
|
|
{
|
|
"entropy": 5.741387605667114,
|
|
"epoch": 1.6817350709978602,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00047160342274829234,
|
|
"loss": 5.0648,
|
|
"mean_token_accuracy": 0.19408333748579026,
|
|
"num_tokens": 37507339.0,
|
|
"step": 21615
|
|
},
|
|
{
|
|
"entropy": 5.608314943313599,
|
|
"epoch": 1.682124100369578,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00047158994322004223,
|
|
"loss": 4.9657,
|
|
"mean_token_accuracy": 0.20372917652130126,
|
|
"num_tokens": 37515919.0,
|
|
"step": 21620
|
|
},
|
|
{
|
|
"entropy": 5.628144121170044,
|
|
"epoch": 1.6825131297412956,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004715764607088527,
|
|
"loss": 4.9686,
|
|
"mean_token_accuracy": 0.20786874294281005,
|
|
"num_tokens": 37524990.0,
|
|
"step": 21625
|
|
},
|
|
{
|
|
"entropy": 5.628019189834594,
|
|
"epoch": 1.6829021591130129,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004715629752149283,
|
|
"loss": 5.1045,
|
|
"mean_token_accuracy": 0.19200923144817353,
|
|
"num_tokens": 37534125.0,
|
|
"step": 21630
|
|
},
|
|
{
|
|
"entropy": 5.648524332046509,
|
|
"epoch": 1.6832911884847306,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00047154948673847356,
|
|
"loss": 5.0221,
|
|
"mean_token_accuracy": 0.1976946175098419,
|
|
"num_tokens": 37541715.0,
|
|
"step": 21635
|
|
},
|
|
{
|
|
"entropy": 5.7356569290161135,
|
|
"epoch": 1.6836802178564483,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004715359952796933,
|
|
"loss": 5.156,
|
|
"mean_token_accuracy": 0.20350012481212615,
|
|
"num_tokens": 37550097.0,
|
|
"step": 21640
|
|
},
|
|
{
|
|
"entropy": 5.585136222839355,
|
|
"epoch": 1.6840692472281658,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00047152250083879203,
|
|
"loss": 5.0188,
|
|
"mean_token_accuracy": 0.19679685980081557,
|
|
"num_tokens": 37558950.0,
|
|
"step": 21645
|
|
},
|
|
{
|
|
"entropy": 5.675404357910156,
|
|
"epoch": 1.6844582765998832,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00047150900341597464,
|
|
"loss": 5.034,
|
|
"mean_token_accuracy": 0.20156317204236984,
|
|
"num_tokens": 37567737.0,
|
|
"step": 21650
|
|
},
|
|
{
|
|
"entropy": 5.700136137008667,
|
|
"epoch": 1.684847305971601,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004714955030114459,
|
|
"loss": 5.0773,
|
|
"mean_token_accuracy": 0.19584817737340926,
|
|
"num_tokens": 37576649.0,
|
|
"step": 21655
|
|
},
|
|
{
|
|
"entropy": 5.655124568939209,
|
|
"epoch": 1.6852363353433184,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00047148199962541065,
|
|
"loss": 5.0558,
|
|
"mean_token_accuracy": 0.20388414412736894,
|
|
"num_tokens": 37584455.0,
|
|
"step": 21660
|
|
},
|
|
{
|
|
"entropy": 5.659012794494629,
|
|
"epoch": 1.6856253647150359,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004714684932580738,
|
|
"loss": 5.1272,
|
|
"mean_token_accuracy": 0.18838134557008743,
|
|
"num_tokens": 37593653.0,
|
|
"step": 21665
|
|
},
|
|
{
|
|
"entropy": 5.693011713027954,
|
|
"epoch": 1.6860143940867536,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004714549839096403,
|
|
"loss": 5.1093,
|
|
"mean_token_accuracy": 0.1929284319281578,
|
|
"num_tokens": 37603212.0,
|
|
"step": 21670
|
|
},
|
|
{
|
|
"entropy": 5.686216735839844,
|
|
"epoch": 1.6864034234584713,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00047144147158031507,
|
|
"loss": 5.0331,
|
|
"mean_token_accuracy": 0.19574832767248154,
|
|
"num_tokens": 37611871.0,
|
|
"step": 21675
|
|
},
|
|
{
|
|
"entropy": 5.7182615280151365,
|
|
"epoch": 1.6867924528301885,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004714279562703032,
|
|
"loss": 5.2188,
|
|
"mean_token_accuracy": 0.18723901510238647,
|
|
"num_tokens": 37621410.0,
|
|
"step": 21680
|
|
},
|
|
{
|
|
"entropy": 5.664160490036011,
|
|
"epoch": 1.6871814822019062,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004714144379798098,
|
|
"loss": 5.0297,
|
|
"mean_token_accuracy": 0.19567696303129195,
|
|
"num_tokens": 37629525.0,
|
|
"step": 21685
|
|
},
|
|
{
|
|
"entropy": 5.723068618774414,
|
|
"epoch": 1.687570511573624,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00047140091670903986,
|
|
"loss": 5.0854,
|
|
"mean_token_accuracy": 0.19774255752563477,
|
|
"num_tokens": 37638183.0,
|
|
"step": 21690
|
|
},
|
|
{
|
|
"entropy": 5.686976766586303,
|
|
"epoch": 1.6879595409453414,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00047138739245819857,
|
|
"loss": 5.0693,
|
|
"mean_token_accuracy": 0.19803808480501175,
|
|
"num_tokens": 37646884.0,
|
|
"step": 21695
|
|
},
|
|
{
|
|
"entropy": 5.738629531860352,
|
|
"epoch": 1.6883485703170589,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00047137386522749124,
|
|
"loss": 5.1196,
|
|
"mean_token_accuracy": 0.18730611950159073,
|
|
"num_tokens": 37655482.0,
|
|
"step": 21700
|
|
},
|
|
{
|
|
"entropy": 5.612303066253662,
|
|
"epoch": 1.6887375996887766,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004713603350171231,
|
|
"loss": 4.9336,
|
|
"mean_token_accuracy": 0.2021462708711624,
|
|
"num_tokens": 37664056.0,
|
|
"step": 21705
|
|
},
|
|
{
|
|
"entropy": 5.669025564193726,
|
|
"epoch": 1.689126629060494,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00047134680182729926,
|
|
"loss": 5.2382,
|
|
"mean_token_accuracy": 0.19384651780128478,
|
|
"num_tokens": 37673198.0,
|
|
"step": 21710
|
|
},
|
|
{
|
|
"entropy": 5.664942216873169,
|
|
"epoch": 1.6895156584322115,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004713332656582254,
|
|
"loss": 5.0697,
|
|
"mean_token_accuracy": 0.19532050788402558,
|
|
"num_tokens": 37682660.0,
|
|
"step": 21715
|
|
},
|
|
{
|
|
"entropy": 5.633370590209961,
|
|
"epoch": 1.6899046878039292,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004713197265101066,
|
|
"loss": 5.0389,
|
|
"mean_token_accuracy": 0.202335362136364,
|
|
"num_tokens": 37691232.0,
|
|
"step": 21720
|
|
},
|
|
{
|
|
"entropy": 5.61824893951416,
|
|
"epoch": 1.690293717175647,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00047130618438314856,
|
|
"loss": 5.0005,
|
|
"mean_token_accuracy": 0.20015470683574677,
|
|
"num_tokens": 37699734.0,
|
|
"step": 21725
|
|
},
|
|
{
|
|
"entropy": 5.700785541534424,
|
|
"epoch": 1.6906827465473642,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004712926392775565,
|
|
"loss": 5.0839,
|
|
"mean_token_accuracy": 0.1999967008829117,
|
|
"num_tokens": 37708529.0,
|
|
"step": 21730
|
|
},
|
|
{
|
|
"entropy": 5.63576717376709,
|
|
"epoch": 1.6910717759190819,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004712790911935362,
|
|
"loss": 4.9562,
|
|
"mean_token_accuracy": 0.2098645582795143,
|
|
"num_tokens": 37717197.0,
|
|
"step": 21735
|
|
},
|
|
{
|
|
"entropy": 5.618352890014648,
|
|
"epoch": 1.6914608052907996,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000471265540131293,
|
|
"loss": 5.0982,
|
|
"mean_token_accuracy": 0.19188545197248458,
|
|
"num_tokens": 37726276.0,
|
|
"step": 21740
|
|
},
|
|
{
|
|
"entropy": 5.72824912071228,
|
|
"epoch": 1.691849834662517,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00047125198609103267,
|
|
"loss": 5.137,
|
|
"mean_token_accuracy": 0.19199802875518798,
|
|
"num_tokens": 37735016.0,
|
|
"step": 21745
|
|
},
|
|
{
|
|
"entropy": 5.729806423187256,
|
|
"epoch": 1.6922388640342345,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004712384290729607,
|
|
"loss": 5.104,
|
|
"mean_token_accuracy": 0.20036841332912445,
|
|
"num_tokens": 37744332.0,
|
|
"step": 21750
|
|
},
|
|
{
|
|
"entropy": 5.7336780548095705,
|
|
"epoch": 1.6926278934059522,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000471224869077283,
|
|
"loss": 5.164,
|
|
"mean_token_accuracy": 0.1810240551829338,
|
|
"num_tokens": 37752805.0,
|
|
"step": 21755
|
|
},
|
|
{
|
|
"entropy": 5.708140134811401,
|
|
"epoch": 1.6930169227776697,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00047121130610420527,
|
|
"loss": 5.0816,
|
|
"mean_token_accuracy": 0.19440166354179383,
|
|
"num_tokens": 37760979.0,
|
|
"step": 21760
|
|
},
|
|
{
|
|
"entropy": 5.588563919067383,
|
|
"epoch": 1.6934059521493872,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00047119774015393323,
|
|
"loss": 5.0224,
|
|
"mean_token_accuracy": 0.19733347296714782,
|
|
"num_tokens": 37769096.0,
|
|
"step": 21765
|
|
},
|
|
{
|
|
"entropy": 5.656375885009766,
|
|
"epoch": 1.6937949815211049,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00047118417122667285,
|
|
"loss": 5.0283,
|
|
"mean_token_accuracy": 0.19535085558891296,
|
|
"num_tokens": 37776998.0,
|
|
"step": 21770
|
|
},
|
|
{
|
|
"entropy": 5.7147716045379635,
|
|
"epoch": 1.6941840108928226,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004711705993226298,
|
|
"loss": 5.1449,
|
|
"mean_token_accuracy": 0.19495135098695754,
|
|
"num_tokens": 37785547.0,
|
|
"step": 21775
|
|
},
|
|
{
|
|
"entropy": 5.667989873886109,
|
|
"epoch": 1.6945730402645398,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004711570244420102,
|
|
"loss": 5.0958,
|
|
"mean_token_accuracy": 0.1913059949874878,
|
|
"num_tokens": 37793659.0,
|
|
"step": 21780
|
|
},
|
|
{
|
|
"entropy": 5.6489544868469235,
|
|
"epoch": 1.6949620696362575,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004711434465850199,
|
|
"loss": 5.0083,
|
|
"mean_token_accuracy": 0.19947948008775712,
|
|
"num_tokens": 37802282.0,
|
|
"step": 21785
|
|
},
|
|
{
|
|
"entropy": 5.69829363822937,
|
|
"epoch": 1.6953510990079752,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004711298657518651,
|
|
"loss": 5.0728,
|
|
"mean_token_accuracy": 0.19906374365091323,
|
|
"num_tokens": 37810692.0,
|
|
"step": 21790
|
|
},
|
|
{
|
|
"entropy": 5.606528997421265,
|
|
"epoch": 1.6957401283796927,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004711162819427518,
|
|
"loss": 5.0343,
|
|
"mean_token_accuracy": 0.20089835524559022,
|
|
"num_tokens": 37819264.0,
|
|
"step": 21795
|
|
},
|
|
{
|
|
"entropy": 5.662407445907593,
|
|
"epoch": 1.6961291577514102,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000471102695157886,
|
|
"loss": 5.0801,
|
|
"mean_token_accuracy": 0.20163782984018325,
|
|
"num_tokens": 37827650.0,
|
|
"step": 21800
|
|
},
|
|
{
|
|
"entropy": 5.565398263931274,
|
|
"epoch": 1.6965181871231279,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004710891053974739,
|
|
"loss": 5.0159,
|
|
"mean_token_accuracy": 0.2013427272439003,
|
|
"num_tokens": 37835683.0,
|
|
"step": 21805
|
|
},
|
|
{
|
|
"entropy": 5.652868175506592,
|
|
"epoch": 1.6969072164948453,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004710755126617217,
|
|
"loss": 5.0309,
|
|
"mean_token_accuracy": 0.1954900309443474,
|
|
"num_tokens": 37844334.0,
|
|
"step": 21810
|
|
},
|
|
{
|
|
"entropy": 5.617059993743896,
|
|
"epoch": 1.6972962458665628,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004710619169508358,
|
|
"loss": 5.0088,
|
|
"mean_token_accuracy": 0.19692396521568298,
|
|
"num_tokens": 37853609.0,
|
|
"step": 21815
|
|
},
|
|
{
|
|
"entropy": 5.665457820892334,
|
|
"epoch": 1.6976852752382805,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004710483182650223,
|
|
"loss": 5.0612,
|
|
"mean_token_accuracy": 0.19669616967439651,
|
|
"num_tokens": 37862817.0,
|
|
"step": 21820
|
|
},
|
|
{
|
|
"entropy": 5.589251852035522,
|
|
"epoch": 1.6980743046099982,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00047103471660448767,
|
|
"loss": 5.0005,
|
|
"mean_token_accuracy": 0.2045843094587326,
|
|
"num_tokens": 37871630.0,
|
|
"step": 21825
|
|
},
|
|
{
|
|
"entropy": 5.552453231811524,
|
|
"epoch": 1.6984633339817157,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00047102111196943813,
|
|
"loss": 5.0202,
|
|
"mean_token_accuracy": 0.20275750160217285,
|
|
"num_tokens": 37881098.0,
|
|
"step": 21830
|
|
},
|
|
{
|
|
"entropy": 5.659877634048462,
|
|
"epoch": 1.6988523633534331,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00047100750436008035,
|
|
"loss": 5.024,
|
|
"mean_token_accuracy": 0.2032433718442917,
|
|
"num_tokens": 37889760.0,
|
|
"step": 21835
|
|
},
|
|
{
|
|
"entropy": 5.740854406356812,
|
|
"epoch": 1.6992413927251508,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00047099389377662054,
|
|
"loss": 5.132,
|
|
"mean_token_accuracy": 0.19285643249750137,
|
|
"num_tokens": 37898417.0,
|
|
"step": 21840
|
|
},
|
|
{
|
|
"entropy": 5.639759302139282,
|
|
"epoch": 1.6996304220968683,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004709802802192654,
|
|
"loss": 5.0801,
|
|
"mean_token_accuracy": 0.2006111890077591,
|
|
"num_tokens": 37907117.0,
|
|
"step": 21845
|
|
},
|
|
{
|
|
"entropy": 5.614550828933716,
|
|
"epoch": 1.7000194514685858,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00047096666368822153,
|
|
"loss": 5.0148,
|
|
"mean_token_accuracy": 0.1985253646969795,
|
|
"num_tokens": 37915781.0,
|
|
"step": 21850
|
|
},
|
|
{
|
|
"entropy": 5.650159883499145,
|
|
"epoch": 1.7004084808403035,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00047095304418369536,
|
|
"loss": 5.1034,
|
|
"mean_token_accuracy": 0.19175428450107573,
|
|
"num_tokens": 37924770.0,
|
|
"step": 21855
|
|
},
|
|
{
|
|
"entropy": 5.657611083984375,
|
|
"epoch": 1.700797510212021,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004709394217058936,
|
|
"loss": 5.1124,
|
|
"mean_token_accuracy": 0.19348921179771422,
|
|
"num_tokens": 37933512.0,
|
|
"step": 21860
|
|
},
|
|
{
|
|
"entropy": 5.612676429748535,
|
|
"epoch": 1.7011865395837384,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004709257962550231,
|
|
"loss": 4.935,
|
|
"mean_token_accuracy": 0.20104921907186507,
|
|
"num_tokens": 37942439.0,
|
|
"step": 21865
|
|
},
|
|
{
|
|
"entropy": 5.672794818878174,
|
|
"epoch": 1.7015755689554561,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00047091216783129035,
|
|
"loss": 5.1241,
|
|
"mean_token_accuracy": 0.19222945719957352,
|
|
"num_tokens": 37951388.0,
|
|
"step": 21870
|
|
},
|
|
{
|
|
"entropy": 5.689729785919189,
|
|
"epoch": 1.7019645983271738,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004708985364349024,
|
|
"loss": 5.116,
|
|
"mean_token_accuracy": 0.19365573674440384,
|
|
"num_tokens": 37960372.0,
|
|
"step": 21875
|
|
},
|
|
{
|
|
"entropy": 5.71558632850647,
|
|
"epoch": 1.7023536276988913,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00047088490206606586,
|
|
"loss": 5.2004,
|
|
"mean_token_accuracy": 0.17831635028123854,
|
|
"num_tokens": 37969472.0,
|
|
"step": 21880
|
|
},
|
|
{
|
|
"entropy": 5.616215753555298,
|
|
"epoch": 1.7027426570706088,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00047087126472498785,
|
|
"loss": 4.9312,
|
|
"mean_token_accuracy": 0.2066580057144165,
|
|
"num_tokens": 37977422.0,
|
|
"step": 21885
|
|
},
|
|
{
|
|
"entropy": 5.596018838882446,
|
|
"epoch": 1.7031316864423265,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.000470857624411875,
|
|
"loss": 4.9122,
|
|
"mean_token_accuracy": 0.20602083951234818,
|
|
"num_tokens": 37985861.0,
|
|
"step": 21890
|
|
},
|
|
{
|
|
"entropy": 5.690075063705445,
|
|
"epoch": 1.703520715814044,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00047084398112693456,
|
|
"loss": 5.0423,
|
|
"mean_token_accuracy": 0.20235230773687363,
|
|
"num_tokens": 37994535.0,
|
|
"step": 21895
|
|
},
|
|
{
|
|
"entropy": 5.6552125930786135,
|
|
"epoch": 1.7039097451857614,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004708303348703734,
|
|
"loss": 5.0822,
|
|
"mean_token_accuracy": 0.19286412000656128,
|
|
"num_tokens": 38003351.0,
|
|
"step": 21900
|
|
},
|
|
{
|
|
"entropy": 5.678764867782593,
|
|
"epoch": 1.7042987745574791,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004708166856423986,
|
|
"loss": 5.0784,
|
|
"mean_token_accuracy": 0.19291504323482514,
|
|
"num_tokens": 38012210.0,
|
|
"step": 21905
|
|
},
|
|
{
|
|
"entropy": 5.696633291244507,
|
|
"epoch": 1.7046878039291966,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00047080303344321727,
|
|
"loss": 5.0751,
|
|
"mean_token_accuracy": 0.19998956620693206,
|
|
"num_tokens": 38020548.0,
|
|
"step": 21910
|
|
},
|
|
{
|
|
"entropy": 5.687703037261963,
|
|
"epoch": 1.705076833300914,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00047078937827303653,
|
|
"loss": 5.0388,
|
|
"mean_token_accuracy": 0.19409146904945374,
|
|
"num_tokens": 38029451.0,
|
|
"step": 21915
|
|
},
|
|
{
|
|
"entropy": 5.656308364868164,
|
|
"epoch": 1.7054658626726318,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004707757201320636,
|
|
"loss": 5.0799,
|
|
"mean_token_accuracy": 0.1945350632071495,
|
|
"num_tokens": 38037821.0,
|
|
"step": 21920
|
|
},
|
|
{
|
|
"entropy": 5.615873718261719,
|
|
"epoch": 1.7058548920443495,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00047076205902050577,
|
|
"loss": 5.1307,
|
|
"mean_token_accuracy": 0.19154444336891174,
|
|
"num_tokens": 38046188.0,
|
|
"step": 21925
|
|
},
|
|
{
|
|
"entropy": 5.679753208160401,
|
|
"epoch": 1.706243921416067,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00047074839493857024,
|
|
"loss": 5.1302,
|
|
"mean_token_accuracy": 0.1952909231185913,
|
|
"num_tokens": 38054821.0,
|
|
"step": 21930
|
|
},
|
|
{
|
|
"entropy": 5.672739744186401,
|
|
"epoch": 1.7066329507877844,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004707347278864644,
|
|
"loss": 5.0532,
|
|
"mean_token_accuracy": 0.19533757120370865,
|
|
"num_tokens": 38063057.0,
|
|
"step": 21935
|
|
},
|
|
{
|
|
"entropy": 5.706013154983521,
|
|
"epoch": 1.7070219801595021,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00047072105786439563,
|
|
"loss": 5.2027,
|
|
"mean_token_accuracy": 0.1914782240986824,
|
|
"num_tokens": 38071694.0,
|
|
"step": 21940
|
|
},
|
|
{
|
|
"entropy": 5.691050481796265,
|
|
"epoch": 1.7074110095312196,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00047070738487257137,
|
|
"loss": 5.0219,
|
|
"mean_token_accuracy": 0.1982439175248146,
|
|
"num_tokens": 38080965.0,
|
|
"step": 21945
|
|
},
|
|
{
|
|
"entropy": 5.667789697647095,
|
|
"epoch": 1.707800038902937,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00047069370891119895,
|
|
"loss": 5.0521,
|
|
"mean_token_accuracy": 0.19038837552070617,
|
|
"num_tokens": 38089786.0,
|
|
"step": 21950
|
|
},
|
|
{
|
|
"entropy": 5.6412077903747555,
|
|
"epoch": 1.7081890682746548,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000470680029980486,
|
|
"loss": 5.0622,
|
|
"mean_token_accuracy": 0.19882871955633163,
|
|
"num_tokens": 38097994.0,
|
|
"step": 21955
|
|
},
|
|
{
|
|
"entropy": 5.690302467346191,
|
|
"epoch": 1.7085780976463723,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00047066634808064006,
|
|
"loss": 5.1178,
|
|
"mean_token_accuracy": 0.19154055416584015,
|
|
"num_tokens": 38106910.0,
|
|
"step": 21960
|
|
},
|
|
{
|
|
"entropy": 5.646644115447998,
|
|
"epoch": 1.7089671270180897,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00047065266321186873,
|
|
"loss": 5.0332,
|
|
"mean_token_accuracy": 0.2043434962630272,
|
|
"num_tokens": 38115162.0,
|
|
"step": 21965
|
|
},
|
|
{
|
|
"entropy": 5.705600547790527,
|
|
"epoch": 1.7093561563898074,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004706389753743797,
|
|
"loss": 5.083,
|
|
"mean_token_accuracy": 0.20416899919509887,
|
|
"num_tokens": 38123776.0,
|
|
"step": 21970
|
|
},
|
|
{
|
|
"entropy": 5.705074787139893,
|
|
"epoch": 1.7097451857615251,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004706252845683805,
|
|
"loss": 5.1659,
|
|
"mean_token_accuracy": 0.19011609256267548,
|
|
"num_tokens": 38132591.0,
|
|
"step": 21975
|
|
},
|
|
{
|
|
"entropy": 5.6537495136260985,
|
|
"epoch": 1.7101342151332426,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00047061159079407903,
|
|
"loss": 5.027,
|
|
"mean_token_accuracy": 0.2028370201587677,
|
|
"num_tokens": 38141092.0,
|
|
"step": 21980
|
|
},
|
|
{
|
|
"entropy": 5.633610391616822,
|
|
"epoch": 1.71052324450496,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000470597894051683,
|
|
"loss": 5.0078,
|
|
"mean_token_accuracy": 0.1986740291118622,
|
|
"num_tokens": 38149315.0,
|
|
"step": 21985
|
|
},
|
|
{
|
|
"entropy": 5.604947948455811,
|
|
"epoch": 1.7109122738766778,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004705841943414003,
|
|
"loss": 4.9733,
|
|
"mean_token_accuracy": 0.19915590435266495,
|
|
"num_tokens": 38158208.0,
|
|
"step": 21990
|
|
},
|
|
{
|
|
"entropy": 5.74879937171936,
|
|
"epoch": 1.7113013032483952,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00047057049166343876,
|
|
"loss": 5.126,
|
|
"mean_token_accuracy": 0.19257869869470595,
|
|
"num_tokens": 38166339.0,
|
|
"step": 21995
|
|
},
|
|
{
|
|
"entropy": 5.717361402511597,
|
|
"epoch": 1.7116903326201127,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00047055678601800623,
|
|
"loss": 5.084,
|
|
"mean_token_accuracy": 0.19625718891620636,
|
|
"num_tokens": 38174813.0,
|
|
"step": 22000
|
|
},
|
|
{
|
|
"entropy": 5.656217098236084,
|
|
"epoch": 1.7120793619918304,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00047054307740531076,
|
|
"loss": 4.9596,
|
|
"mean_token_accuracy": 0.20155562162399293,
|
|
"num_tokens": 38183440.0,
|
|
"step": 22005
|
|
},
|
|
{
|
|
"entropy": 5.596694850921631,
|
|
"epoch": 1.712468391363548,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00047052936582556035,
|
|
"loss": 5.0202,
|
|
"mean_token_accuracy": 0.19960058182477952,
|
|
"num_tokens": 38192510.0,
|
|
"step": 22010
|
|
},
|
|
{
|
|
"entropy": 5.650761985778809,
|
|
"epoch": 1.7128574207352654,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00047051565127896307,
|
|
"loss": 5.0144,
|
|
"mean_token_accuracy": 0.20671189874410628,
|
|
"num_tokens": 38200854.0,
|
|
"step": 22015
|
|
},
|
|
{
|
|
"entropy": 5.6916844844818115,
|
|
"epoch": 1.713246450106983,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00047050193376572686,
|
|
"loss": 5.0717,
|
|
"mean_token_accuracy": 0.1918088510632515,
|
|
"num_tokens": 38209632.0,
|
|
"step": 22020
|
|
},
|
|
{
|
|
"entropy": 5.615683746337891,
|
|
"epoch": 1.7136354794787008,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00047048821328606,
|
|
"loss": 4.9976,
|
|
"mean_token_accuracy": 0.20116380751132965,
|
|
"num_tokens": 38218657.0,
|
|
"step": 22025
|
|
},
|
|
{
|
|
"entropy": 5.7197511196136475,
|
|
"epoch": 1.7140245088504182,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004704744898401708,
|
|
"loss": 5.0643,
|
|
"mean_token_accuracy": 0.19772231131792067,
|
|
"num_tokens": 38227507.0,
|
|
"step": 22030
|
|
},
|
|
{
|
|
"entropy": 5.6676534652709964,
|
|
"epoch": 1.7144135382221357,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004704607634282672,
|
|
"loss": 5.0377,
|
|
"mean_token_accuracy": 0.1997448906302452,
|
|
"num_tokens": 38236822.0,
|
|
"step": 22035
|
|
},
|
|
{
|
|
"entropy": 5.563470411300659,
|
|
"epoch": 1.7148025675938534,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00047044703405055765,
|
|
"loss": 4.9497,
|
|
"mean_token_accuracy": 0.2040942892432213,
|
|
"num_tokens": 38245144.0,
|
|
"step": 22040
|
|
},
|
|
{
|
|
"entropy": 5.621599626541138,
|
|
"epoch": 1.7151915969655709,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00047043330170725046,
|
|
"loss": 5.0516,
|
|
"mean_token_accuracy": 0.1953385666012764,
|
|
"num_tokens": 38254363.0,
|
|
"step": 22045
|
|
},
|
|
{
|
|
"entropy": 5.634972953796387,
|
|
"epoch": 1.7155806263372884,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00047041956639855406,
|
|
"loss": 5.051,
|
|
"mean_token_accuracy": 0.19931643605232238,
|
|
"num_tokens": 38263117.0,
|
|
"step": 22050
|
|
},
|
|
{
|
|
"entropy": 5.632564926147461,
|
|
"epoch": 1.715969655709006,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004704058281246766,
|
|
"loss": 5.0341,
|
|
"mean_token_accuracy": 0.1971964493393898,
|
|
"num_tokens": 38271217.0,
|
|
"step": 22055
|
|
},
|
|
{
|
|
"entropy": 5.716578531265259,
|
|
"epoch": 1.7163586850807238,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004703920868858268,
|
|
"loss": 5.1623,
|
|
"mean_token_accuracy": 0.19212710112333298,
|
|
"num_tokens": 38279789.0,
|
|
"step": 22060
|
|
},
|
|
{
|
|
"entropy": 5.626923418045044,
|
|
"epoch": 1.716747714452441,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00047037834268221315,
|
|
"loss": 4.9823,
|
|
"mean_token_accuracy": 0.20163310319185257,
|
|
"num_tokens": 38288845.0,
|
|
"step": 22065
|
|
},
|
|
{
|
|
"entropy": 5.656175184249878,
|
|
"epoch": 1.7171367438241587,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004703645955140441,
|
|
"loss": 5.0493,
|
|
"mean_token_accuracy": 0.1967256933450699,
|
|
"num_tokens": 38297237.0,
|
|
"step": 22070
|
|
},
|
|
{
|
|
"entropy": 5.745203351974487,
|
|
"epoch": 1.7175257731958764,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00047035084538152815,
|
|
"loss": 5.1585,
|
|
"mean_token_accuracy": 0.18956682980060577,
|
|
"num_tokens": 38306582.0,
|
|
"step": 22075
|
|
},
|
|
{
|
|
"entropy": 5.658037710189819,
|
|
"epoch": 1.7179148025675939,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004703370922848742,
|
|
"loss": 4.9744,
|
|
"mean_token_accuracy": 0.21153550297021867,
|
|
"num_tokens": 38315406.0,
|
|
"step": 22080
|
|
},
|
|
{
|
|
"entropy": 5.62490701675415,
|
|
"epoch": 1.7183038319393114,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00047032333622429074,
|
|
"loss": 4.9744,
|
|
"mean_token_accuracy": 0.20097845196723937,
|
|
"num_tokens": 38324271.0,
|
|
"step": 22085
|
|
},
|
|
{
|
|
"entropy": 5.664039182662964,
|
|
"epoch": 1.718692861311029,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00047030957719998656,
|
|
"loss": 5.0756,
|
|
"mean_token_accuracy": 0.19401168525218965,
|
|
"num_tokens": 38332831.0,
|
|
"step": 22090
|
|
},
|
|
{
|
|
"entropy": 5.632407712936401,
|
|
"epoch": 1.7190818906827465,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004702958152121704,
|
|
"loss": 4.9909,
|
|
"mean_token_accuracy": 0.20227778404951097,
|
|
"num_tokens": 38341263.0,
|
|
"step": 22095
|
|
},
|
|
{
|
|
"entropy": 5.648492622375488,
|
|
"epoch": 1.719470920054464,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004702820502610511,
|
|
"loss": 5.1847,
|
|
"mean_token_accuracy": 0.18876439929008484,
|
|
"num_tokens": 38349890.0,
|
|
"step": 22100
|
|
},
|
|
{
|
|
"entropy": 5.610504007339477,
|
|
"epoch": 1.7198599494261817,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004702682823468375,
|
|
"loss": 4.9655,
|
|
"mean_token_accuracy": 0.20201875567436217,
|
|
"num_tokens": 38358071.0,
|
|
"step": 22105
|
|
},
|
|
{
|
|
"entropy": 5.711025524139404,
|
|
"epoch": 1.7202489787978994,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00047025451146973844,
|
|
"loss": 5.1283,
|
|
"mean_token_accuracy": 0.19127406924962997,
|
|
"num_tokens": 38366859.0,
|
|
"step": 22110
|
|
},
|
|
{
|
|
"entropy": 5.770093822479248,
|
|
"epoch": 1.7206380081696167,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00047024073762996305,
|
|
"loss": 5.2786,
|
|
"mean_token_accuracy": 0.180878247320652,
|
|
"num_tokens": 38375897.0,
|
|
"step": 22115
|
|
},
|
|
{
|
|
"entropy": 5.6647388458251955,
|
|
"epoch": 1.7210270375413343,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004702269608277202,
|
|
"loss": 5.0572,
|
|
"mean_token_accuracy": 0.20210765302181244,
|
|
"num_tokens": 38384700.0,
|
|
"step": 22120
|
|
},
|
|
{
|
|
"entropy": 5.698626279830933,
|
|
"epoch": 1.721416066913052,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004702131810632189,
|
|
"loss": 5.1123,
|
|
"mean_token_accuracy": 0.19869651645421982,
|
|
"num_tokens": 38393212.0,
|
|
"step": 22125
|
|
},
|
|
{
|
|
"entropy": 5.620493793487549,
|
|
"epoch": 1.7218050962847695,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00047019939833666837,
|
|
"loss": 5.0233,
|
|
"mean_token_accuracy": 0.20437860637903213,
|
|
"num_tokens": 38401572.0,
|
|
"step": 22130
|
|
},
|
|
{
|
|
"entropy": 5.618623733520508,
|
|
"epoch": 1.722194125656487,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004701856126482776,
|
|
"loss": 5.0555,
|
|
"mean_token_accuracy": 0.19549354761838914,
|
|
"num_tokens": 38410669.0,
|
|
"step": 22135
|
|
},
|
|
{
|
|
"entropy": 5.661244440078735,
|
|
"epoch": 1.7225831550282047,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004701718239982559,
|
|
"loss": 5.0658,
|
|
"mean_token_accuracy": 0.1931559458374977,
|
|
"num_tokens": 38419038.0,
|
|
"step": 22140
|
|
},
|
|
{
|
|
"entropy": 5.6170848369598385,
|
|
"epoch": 1.7229721843999222,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00047015803238681234,
|
|
"loss": 5.0027,
|
|
"mean_token_accuracy": 0.2055936947464943,
|
|
"num_tokens": 38427314.0,
|
|
"step": 22145
|
|
},
|
|
{
|
|
"entropy": 5.608303117752075,
|
|
"epoch": 1.7233612137716396,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004701442378141563,
|
|
"loss": 4.9995,
|
|
"mean_token_accuracy": 0.19678326845169067,
|
|
"num_tokens": 38435373.0,
|
|
"step": 22150
|
|
},
|
|
{
|
|
"entropy": 5.613267707824707,
|
|
"epoch": 1.7237502431433573,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000470130440280497,
|
|
"loss": 5.0228,
|
|
"mean_token_accuracy": 0.20060820132493973,
|
|
"num_tokens": 38444448.0,
|
|
"step": 22155
|
|
},
|
|
{
|
|
"entropy": 5.6791112422943115,
|
|
"epoch": 1.724139272515075,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004701166397860439,
|
|
"loss": 4.9721,
|
|
"mean_token_accuracy": 0.20241123139858247,
|
|
"num_tokens": 38453576.0,
|
|
"step": 22160
|
|
},
|
|
{
|
|
"entropy": 5.686106252670288,
|
|
"epoch": 1.7245283018867923,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004701028363310064,
|
|
"loss": 5.0127,
|
|
"mean_token_accuracy": 0.20553840398788453,
|
|
"num_tokens": 38462848.0,
|
|
"step": 22165
|
|
},
|
|
{
|
|
"entropy": 5.6319732666015625,
|
|
"epoch": 1.72491733125851,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00047008902991559385,
|
|
"loss": 5.0021,
|
|
"mean_token_accuracy": 0.20384716987609863,
|
|
"num_tokens": 38470953.0,
|
|
"step": 22170
|
|
},
|
|
{
|
|
"entropy": 5.687946414947509,
|
|
"epoch": 1.7253063606302277,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004700752205400158,
|
|
"loss": 5.1323,
|
|
"mean_token_accuracy": 0.19119604974985122,
|
|
"num_tokens": 38479835.0,
|
|
"step": 22175
|
|
},
|
|
{
|
|
"entropy": 5.679265928268433,
|
|
"epoch": 1.7256953900019452,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00047006140820448174,
|
|
"loss": 5.0515,
|
|
"mean_token_accuracy": 0.19489602446556092,
|
|
"num_tokens": 38488342.0,
|
|
"step": 22180
|
|
},
|
|
{
|
|
"entropy": 5.664249897003174,
|
|
"epoch": 1.7260844193736626,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00047004759290920136,
|
|
"loss": 5.0676,
|
|
"mean_token_accuracy": 0.1976734146475792,
|
|
"num_tokens": 38496716.0,
|
|
"step": 22185
|
|
},
|
|
{
|
|
"entropy": 5.658633279800415,
|
|
"epoch": 1.7264734487453803,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004700337746543841,
|
|
"loss": 5.0953,
|
|
"mean_token_accuracy": 0.19553611129522325,
|
|
"num_tokens": 38506615.0,
|
|
"step": 22190
|
|
},
|
|
{
|
|
"entropy": 5.609146404266357,
|
|
"epoch": 1.7268624781170978,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004700199534402398,
|
|
"loss": 4.9031,
|
|
"mean_token_accuracy": 0.20573283582925797,
|
|
"num_tokens": 38515936.0,
|
|
"step": 22195
|
|
},
|
|
{
|
|
"entropy": 5.622857475280762,
|
|
"epoch": 1.7272515074888153,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004700061292669781,
|
|
"loss": 5.0328,
|
|
"mean_token_accuracy": 0.19693392515182495,
|
|
"num_tokens": 38524829.0,
|
|
"step": 22200
|
|
},
|
|
{
|
|
"entropy": 5.681061124801635,
|
|
"epoch": 1.727640536860533,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004699923021348088,
|
|
"loss": 5.1863,
|
|
"mean_token_accuracy": 0.18945951163768768,
|
|
"num_tokens": 38533686.0,
|
|
"step": 22205
|
|
},
|
|
{
|
|
"entropy": 5.704560089111328,
|
|
"epoch": 1.7280295662322507,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00046997847204394166,
|
|
"loss": 5.0564,
|
|
"mean_token_accuracy": 0.19742194563150406,
|
|
"num_tokens": 38542449.0,
|
|
"step": 22210
|
|
},
|
|
{
|
|
"entropy": 5.679417324066162,
|
|
"epoch": 1.728418595603968,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00046996463899458653,
|
|
"loss": 5.0275,
|
|
"mean_token_accuracy": 0.20108308494091034,
|
|
"num_tokens": 38550888.0,
|
|
"step": 22215
|
|
},
|
|
{
|
|
"entropy": 5.5916379451751705,
|
|
"epoch": 1.7288076249756856,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004699508029869533,
|
|
"loss": 5.0696,
|
|
"mean_token_accuracy": 0.19759927093982696,
|
|
"num_tokens": 38559366.0,
|
|
"step": 22220
|
|
},
|
|
{
|
|
"entropy": 5.692618656158447,
|
|
"epoch": 1.7291966543474033,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00046993696402125205,
|
|
"loss": 5.0914,
|
|
"mean_token_accuracy": 0.20067006051540376,
|
|
"num_tokens": 38567080.0,
|
|
"step": 22225
|
|
},
|
|
{
|
|
"entropy": 5.657074213027954,
|
|
"epoch": 1.7295856837191208,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004699231220976925,
|
|
"loss": 5.0689,
|
|
"mean_token_accuracy": 0.2045196369290352,
|
|
"num_tokens": 38575520.0,
|
|
"step": 22230
|
|
},
|
|
{
|
|
"entropy": 5.7178449630737305,
|
|
"epoch": 1.7299747130908383,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004699092772164849,
|
|
"loss": 5.1606,
|
|
"mean_token_accuracy": 0.1892016500234604,
|
|
"num_tokens": 38583974.0,
|
|
"step": 22235
|
|
},
|
|
{
|
|
"entropy": 5.6052460193634035,
|
|
"epoch": 1.730363742462556,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004698954293778392,
|
|
"loss": 5.0696,
|
|
"mean_token_accuracy": 0.19698223024606704,
|
|
"num_tokens": 38592677.0,
|
|
"step": 22240
|
|
},
|
|
{
|
|
"entropy": 5.621514415740966,
|
|
"epoch": 1.7307527718342735,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00046988157858196555,
|
|
"loss": 4.9104,
|
|
"mean_token_accuracy": 0.201981620490551,
|
|
"num_tokens": 38601342.0,
|
|
"step": 22245
|
|
},
|
|
{
|
|
"entropy": 5.712474775314331,
|
|
"epoch": 1.731141801205991,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00046986772482907426,
|
|
"loss": 5.1634,
|
|
"mean_token_accuracy": 0.18830789625644684,
|
|
"num_tokens": 38610895.0,
|
|
"step": 22250
|
|
},
|
|
{
|
|
"entropy": 5.668631267547608,
|
|
"epoch": 1.7315308305777086,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004698538681193754,
|
|
"loss": 5.1195,
|
|
"mean_token_accuracy": 0.1954927295446396,
|
|
"num_tokens": 38619059.0,
|
|
"step": 22255
|
|
},
|
|
{
|
|
"entropy": 5.679808139801025,
|
|
"epoch": 1.7319198599494263,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00046984000845307907,
|
|
"loss": 5.0718,
|
|
"mean_token_accuracy": 0.1958228886127472,
|
|
"num_tokens": 38628084.0,
|
|
"step": 22260
|
|
},
|
|
{
|
|
"entropy": 5.6559711456298825,
|
|
"epoch": 1.7323088893211438,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00046982614583039584,
|
|
"loss": 5.0758,
|
|
"mean_token_accuracy": 0.19177769422531127,
|
|
"num_tokens": 38636205.0,
|
|
"step": 22265
|
|
},
|
|
{
|
|
"entropy": 5.6353994846344,
|
|
"epoch": 1.7326979186928613,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004698122802515359,
|
|
"loss": 5.0316,
|
|
"mean_token_accuracy": 0.19626931250095367,
|
|
"num_tokens": 38644583.0,
|
|
"step": 22270
|
|
},
|
|
{
|
|
"entropy": 5.642191600799561,
|
|
"epoch": 1.733086948064579,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004697984117167097,
|
|
"loss": 5.0163,
|
|
"mean_token_accuracy": 0.20118715465068818,
|
|
"num_tokens": 38653517.0,
|
|
"step": 22275
|
|
},
|
|
{
|
|
"entropy": 5.6460182666778564,
|
|
"epoch": 1.7334759774362964,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00046978454022612767,
|
|
"loss": 5.0765,
|
|
"mean_token_accuracy": 0.1928579553961754,
|
|
"num_tokens": 38661926.0,
|
|
"step": 22280
|
|
},
|
|
{
|
|
"entropy": 5.753850650787354,
|
|
"epoch": 1.733865006808014,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00046977066578000025,
|
|
"loss": 5.1241,
|
|
"mean_token_accuracy": 0.19831566363573075,
|
|
"num_tokens": 38671567.0,
|
|
"step": 22285
|
|
},
|
|
{
|
|
"entropy": 5.679229211807251,
|
|
"epoch": 1.7342540361797316,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00046975678837853806,
|
|
"loss": 5.0494,
|
|
"mean_token_accuracy": 0.20398346036672593,
|
|
"num_tokens": 38680439.0,
|
|
"step": 22290
|
|
},
|
|
{
|
|
"entropy": 5.642826557159424,
|
|
"epoch": 1.734643065551449,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00046974290802195156,
|
|
"loss": 5.0976,
|
|
"mean_token_accuracy": 0.19669349044561385,
|
|
"num_tokens": 38689168.0,
|
|
"step": 22295
|
|
},
|
|
{
|
|
"entropy": 5.689180564880371,
|
|
"epoch": 1.7350320949231666,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004697290247104513,
|
|
"loss": 5.0323,
|
|
"mean_token_accuracy": 0.19757416248321533,
|
|
"num_tokens": 38697592.0,
|
|
"step": 22300
|
|
},
|
|
{
|
|
"entropy": 5.649882888793945,
|
|
"epoch": 1.7354211242948843,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00046971513844424814,
|
|
"loss": 5.0798,
|
|
"mean_token_accuracy": 0.19310355484485625,
|
|
"num_tokens": 38705561.0,
|
|
"step": 22305
|
|
},
|
|
{
|
|
"entropy": 5.614341115951538,
|
|
"epoch": 1.735810153666602,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00046970124922355265,
|
|
"loss": 5.0392,
|
|
"mean_token_accuracy": 0.2010719284415245,
|
|
"num_tokens": 38714694.0,
|
|
"step": 22310
|
|
},
|
|
{
|
|
"entropy": 5.679735565185547,
|
|
"epoch": 1.7361991830383194,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004696873570485756,
|
|
"loss": 5.0254,
|
|
"mean_token_accuracy": 0.20323633998632432,
|
|
"num_tokens": 38722797.0,
|
|
"step": 22315
|
|
},
|
|
{
|
|
"entropy": 5.682542705535889,
|
|
"epoch": 1.736588212410037,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004696734619195278,
|
|
"loss": 5.0992,
|
|
"mean_token_accuracy": 0.1997784748673439,
|
|
"num_tokens": 38732076.0,
|
|
"step": 22320
|
|
},
|
|
{
|
|
"entropy": 5.699263191223144,
|
|
"epoch": 1.7369772417817546,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00046965956383662,
|
|
"loss": 5.1075,
|
|
"mean_token_accuracy": 0.20008494555950165,
|
|
"num_tokens": 38740992.0,
|
|
"step": 22325
|
|
},
|
|
{
|
|
"entropy": 5.6915748596191404,
|
|
"epoch": 1.737366271153472,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004696456628000632,
|
|
"loss": 5.0761,
|
|
"mean_token_accuracy": 0.19764744490385056,
|
|
"num_tokens": 38749266.0,
|
|
"step": 22330
|
|
},
|
|
{
|
|
"entropy": 5.677693510055542,
|
|
"epoch": 1.7377553005251896,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00046963175881006825,
|
|
"loss": 5.1521,
|
|
"mean_token_accuracy": 0.19179669469594957,
|
|
"num_tokens": 38757983.0,
|
|
"step": 22335
|
|
},
|
|
{
|
|
"entropy": 5.6361168384552,
|
|
"epoch": 1.7381443298969073,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004696178518668462,
|
|
"loss": 4.9896,
|
|
"mean_token_accuracy": 0.20907741338014602,
|
|
"num_tokens": 38766258.0,
|
|
"step": 22340
|
|
},
|
|
{
|
|
"entropy": 5.68007230758667,
|
|
"epoch": 1.7385333592686247,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00046960394197060804,
|
|
"loss": 5.1095,
|
|
"mean_token_accuracy": 0.19478160440921782,
|
|
"num_tokens": 38775105.0,
|
|
"step": 22345
|
|
},
|
|
{
|
|
"entropy": 5.695080280303955,
|
|
"epoch": 1.7389223886403422,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00046959002912156473,
|
|
"loss": 5.1197,
|
|
"mean_token_accuracy": 0.1957464560866356,
|
|
"num_tokens": 38783415.0,
|
|
"step": 22350
|
|
},
|
|
{
|
|
"entropy": 5.6615049839019775,
|
|
"epoch": 1.73931141801206,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004695761133199275,
|
|
"loss": 5.1281,
|
|
"mean_token_accuracy": 0.1939013972878456,
|
|
"num_tokens": 38791703.0,
|
|
"step": 22355
|
|
},
|
|
{
|
|
"entropy": 5.666936206817627,
|
|
"epoch": 1.7397004473837776,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004695621945659074,
|
|
"loss": 5.1025,
|
|
"mean_token_accuracy": 0.19301100075244904,
|
|
"num_tokens": 38800823.0,
|
|
"step": 22360
|
|
},
|
|
{
|
|
"entropy": 5.674952459335327,
|
|
"epoch": 1.740089476755495,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004695482728597157,
|
|
"loss": 5.0987,
|
|
"mean_token_accuracy": 0.18985410928726196,
|
|
"num_tokens": 38810607.0,
|
|
"step": 22365
|
|
},
|
|
{
|
|
"entropy": 5.652855157852173,
|
|
"epoch": 1.7404785061272126,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00046953434820156363,
|
|
"loss": 5.0429,
|
|
"mean_token_accuracy": 0.19221502989530564,
|
|
"num_tokens": 38819288.0,
|
|
"step": 22370
|
|
},
|
|
{
|
|
"entropy": 5.639925289154053,
|
|
"epoch": 1.7408675354989303,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004695204205916624,
|
|
"loss": 4.9931,
|
|
"mean_token_accuracy": 0.2042757272720337,
|
|
"num_tokens": 38827791.0,
|
|
"step": 22375
|
|
},
|
|
{
|
|
"entropy": 5.689849328994751,
|
|
"epoch": 1.7412565648706477,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004695064900302235,
|
|
"loss": 5.0529,
|
|
"mean_token_accuracy": 0.19893163293600083,
|
|
"num_tokens": 38836338.0,
|
|
"step": 22380
|
|
},
|
|
{
|
|
"entropy": 5.7244312286376955,
|
|
"epoch": 1.7416455942423652,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004694925565174581,
|
|
"loss": 5.0148,
|
|
"mean_token_accuracy": 0.1985758975148201,
|
|
"num_tokens": 38844768.0,
|
|
"step": 22385
|
|
},
|
|
{
|
|
"entropy": 5.75396466255188,
|
|
"epoch": 1.742034623614083,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00046947862005357777,
|
|
"loss": 5.1498,
|
|
"mean_token_accuracy": 0.19053892642259598,
|
|
"num_tokens": 38854022.0,
|
|
"step": 22390
|
|
},
|
|
{
|
|
"entropy": 5.655837488174439,
|
|
"epoch": 1.7424236529858004,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004694646806387939,
|
|
"loss": 5.0215,
|
|
"mean_token_accuracy": 0.2034000650048256,
|
|
"num_tokens": 38862035.0,
|
|
"step": 22395
|
|
},
|
|
{
|
|
"entropy": 5.659757041931153,
|
|
"epoch": 1.7428126823575179,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004694507382733181,
|
|
"loss": 5.0617,
|
|
"mean_token_accuracy": 0.2006596252322197,
|
|
"num_tokens": 38870762.0,
|
|
"step": 22400
|
|
},
|
|
{
|
|
"entropy": 5.655742597579956,
|
|
"epoch": 1.7432017117292355,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004694367929573618,
|
|
"loss": 5.0009,
|
|
"mean_token_accuracy": 0.2085031747817993,
|
|
"num_tokens": 38879791.0,
|
|
"step": 22405
|
|
},
|
|
{
|
|
"entropy": 5.789531087875366,
|
|
"epoch": 1.7435907411009532,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004694228446911367,
|
|
"loss": 5.1339,
|
|
"mean_token_accuracy": 0.19194365888834,
|
|
"num_tokens": 38889926.0,
|
|
"step": 22410
|
|
},
|
|
{
|
|
"entropy": 5.698483085632324,
|
|
"epoch": 1.7439797704726707,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004694088934748542,
|
|
"loss": 5.0695,
|
|
"mean_token_accuracy": 0.19272553473711013,
|
|
"num_tokens": 38898428.0,
|
|
"step": 22415
|
|
},
|
|
{
|
|
"entropy": 5.623120498657227,
|
|
"epoch": 1.7443687998443882,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004693949393087263,
|
|
"loss": 5.1,
|
|
"mean_token_accuracy": 0.19020944982767105,
|
|
"num_tokens": 38906800.0,
|
|
"step": 22420
|
|
},
|
|
{
|
|
"entropy": 5.66190276145935,
|
|
"epoch": 1.744757829216106,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004693809821929647,
|
|
"loss": 5.0619,
|
|
"mean_token_accuracy": 0.18886170089244841,
|
|
"num_tokens": 38915947.0,
|
|
"step": 22425
|
|
},
|
|
{
|
|
"entropy": 5.74968729019165,
|
|
"epoch": 1.7451468585878234,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000469367022127781,
|
|
"loss": 5.1052,
|
|
"mean_token_accuracy": 0.1926722154021263,
|
|
"num_tokens": 38924895.0,
|
|
"step": 22430
|
|
},
|
|
{
|
|
"entropy": 5.715599250793457,
|
|
"epoch": 1.7455358879595408,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00046935305911338703,
|
|
"loss": 5.086,
|
|
"mean_token_accuracy": 0.18825379759073257,
|
|
"num_tokens": 38933393.0,
|
|
"step": 22435
|
|
},
|
|
{
|
|
"entropy": 5.702757740020752,
|
|
"epoch": 1.7459249173312585,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004693390931499948,
|
|
"loss": 5.0827,
|
|
"mean_token_accuracy": 0.2023254230618477,
|
|
"num_tokens": 38942219.0,
|
|
"step": 22440
|
|
},
|
|
{
|
|
"entropy": 5.676919794082641,
|
|
"epoch": 1.7463139467029762,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004693251242378162,
|
|
"loss": 5.0381,
|
|
"mean_token_accuracy": 0.1928280547261238,
|
|
"num_tokens": 38950938.0,
|
|
"step": 22445
|
|
},
|
|
{
|
|
"entropy": 5.643939352035522,
|
|
"epoch": 1.7467029760746935,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00046931115237706304,
|
|
"loss": 5.0497,
|
|
"mean_token_accuracy": 0.197927089035511,
|
|
"num_tokens": 38959805.0,
|
|
"step": 22450
|
|
},
|
|
{
|
|
"entropy": 5.6327300548553465,
|
|
"epoch": 1.7470920054464112,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004692971775679475,
|
|
"loss": 4.9843,
|
|
"mean_token_accuracy": 0.2004704847931862,
|
|
"num_tokens": 38968308.0,
|
|
"step": 22455
|
|
},
|
|
{
|
|
"entropy": 5.784936761856079,
|
|
"epoch": 1.7474810348181289,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00046928319981068154,
|
|
"loss": 5.1239,
|
|
"mean_token_accuracy": 0.19116262793540956,
|
|
"num_tokens": 38976409.0,
|
|
"step": 22460
|
|
},
|
|
{
|
|
"entropy": 5.636967039108276,
|
|
"epoch": 1.7478700641898464,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004692692191054773,
|
|
"loss": 5.0552,
|
|
"mean_token_accuracy": 0.19898292571306228,
|
|
"num_tokens": 38985193.0,
|
|
"step": 22465
|
|
},
|
|
{
|
|
"entropy": 5.633849000930786,
|
|
"epoch": 1.7482590935615638,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004692552354525468,
|
|
"loss": 5.0477,
|
|
"mean_token_accuracy": 0.20176565051078796,
|
|
"num_tokens": 38994141.0,
|
|
"step": 22470
|
|
},
|
|
{
|
|
"entropy": 5.696846437454224,
|
|
"epoch": 1.7486481229332815,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004692412488521023,
|
|
"loss": 5.1808,
|
|
"mean_token_accuracy": 0.19120857119560242,
|
|
"num_tokens": 39002953.0,
|
|
"step": 22475
|
|
},
|
|
{
|
|
"entropy": 5.722127914428711,
|
|
"epoch": 1.749037152304999,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.000469227259304356,
|
|
"loss": 5.0954,
|
|
"mean_token_accuracy": 0.20289715826511384,
|
|
"num_tokens": 39010672.0,
|
|
"step": 22480
|
|
},
|
|
{
|
|
"entropy": 5.66537618637085,
|
|
"epoch": 1.7494261816767165,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00046921326680952023,
|
|
"loss": 5.1277,
|
|
"mean_token_accuracy": 0.1905087947845459,
|
|
"num_tokens": 39019677.0,
|
|
"step": 22485
|
|
},
|
|
{
|
|
"entropy": 5.680766582489014,
|
|
"epoch": 1.7498152110484342,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004691992713678072,
|
|
"loss": 5.0727,
|
|
"mean_token_accuracy": 0.1929251730442047,
|
|
"num_tokens": 39028165.0,
|
|
"step": 22490
|
|
},
|
|
{
|
|
"entropy": 5.621655464172363,
|
|
"epoch": 1.7502042404201519,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004691852729794293,
|
|
"loss": 5.0054,
|
|
"mean_token_accuracy": 0.19845127910375596,
|
|
"num_tokens": 39037537.0,
|
|
"step": 22495
|
|
},
|
|
{
|
|
"entropy": 5.6673445224761965,
|
|
"epoch": 1.7505932697918691,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004691712716445991,
|
|
"loss": 5.035,
|
|
"mean_token_accuracy": 0.19844138622283936,
|
|
"num_tokens": 39045861.0,
|
|
"step": 22500
|
|
},
|
|
{
|
|
"entropy": 5.709296083450317,
|
|
"epoch": 1.7509822991635868,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004691572673635288,
|
|
"loss": 5.0493,
|
|
"mean_token_accuracy": 0.19929910451173782,
|
|
"num_tokens": 39054526.0,
|
|
"step": 22505
|
|
},
|
|
{
|
|
"entropy": 5.66934986114502,
|
|
"epoch": 1.7513713285353045,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000469143260136431,
|
|
"loss": 5.063,
|
|
"mean_token_accuracy": 0.19108586758375168,
|
|
"num_tokens": 39063296.0,
|
|
"step": 22510
|
|
},
|
|
{
|
|
"entropy": 5.674559259414673,
|
|
"epoch": 1.751760357907022,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004691292499635183,
|
|
"loss": 4.9905,
|
|
"mean_token_accuracy": 0.19899203181266784,
|
|
"num_tokens": 39071570.0,
|
|
"step": 22515
|
|
},
|
|
{
|
|
"entropy": 5.643053960800171,
|
|
"epoch": 1.7521493872787395,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004691152368450032,
|
|
"loss": 5.0791,
|
|
"mean_token_accuracy": 0.19975041300058366,
|
|
"num_tokens": 39080798.0,
|
|
"step": 22520
|
|
},
|
|
{
|
|
"entropy": 5.658553981781006,
|
|
"epoch": 1.7525384166504572,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00046910122078109835,
|
|
"loss": 5.0581,
|
|
"mean_token_accuracy": 0.19790079891681672,
|
|
"num_tokens": 39089572.0,
|
|
"step": 22525
|
|
},
|
|
{
|
|
"entropy": 5.7552674293518065,
|
|
"epoch": 1.7529274460221747,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004690872017720163,
|
|
"loss": 5.1612,
|
|
"mean_token_accuracy": 0.19588136970996856,
|
|
"num_tokens": 39098391.0,
|
|
"step": 22530
|
|
},
|
|
{
|
|
"entropy": 5.6929107189178465,
|
|
"epoch": 1.7533164753938921,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00046907317981797006,
|
|
"loss": 5.1215,
|
|
"mean_token_accuracy": 0.1927901938557625,
|
|
"num_tokens": 39106892.0,
|
|
"step": 22535
|
|
},
|
|
{
|
|
"entropy": 5.680017471313477,
|
|
"epoch": 1.7537055047656098,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00046905915491917213,
|
|
"loss": 5.0546,
|
|
"mean_token_accuracy": 0.19367746710777284,
|
|
"num_tokens": 39115635.0,
|
|
"step": 22540
|
|
},
|
|
{
|
|
"entropy": 5.704803323745727,
|
|
"epoch": 1.7540945341373275,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004690451270758354,
|
|
"loss": 5.0492,
|
|
"mean_token_accuracy": 0.19545793235301973,
|
|
"num_tokens": 39123665.0,
|
|
"step": 22545
|
|
},
|
|
{
|
|
"entropy": 5.704788017272949,
|
|
"epoch": 1.7544835635090448,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00046903109628817276,
|
|
"loss": 5.1127,
|
|
"mean_token_accuracy": 0.19106509834527968,
|
|
"num_tokens": 39132727.0,
|
|
"step": 22550
|
|
},
|
|
{
|
|
"entropy": 5.669383955001831,
|
|
"epoch": 1.7548725928807625,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00046901706255639703,
|
|
"loss": 5.0842,
|
|
"mean_token_accuracy": 0.1927453249692917,
|
|
"num_tokens": 39140814.0,
|
|
"step": 22555
|
|
},
|
|
{
|
|
"entropy": 5.762030696868896,
|
|
"epoch": 1.7552616222524802,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004690030258807212,
|
|
"loss": 5.1575,
|
|
"mean_token_accuracy": 0.18692436665296555,
|
|
"num_tokens": 39149877.0,
|
|
"step": 22560
|
|
},
|
|
{
|
|
"entropy": 5.675040626525879,
|
|
"epoch": 1.7556506516241976,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00046898898626135827,
|
|
"loss": 5.0909,
|
|
"mean_token_accuracy": 0.19413626044988633,
|
|
"num_tokens": 39158698.0,
|
|
"step": 22565
|
|
},
|
|
{
|
|
"entropy": 5.603366994857788,
|
|
"epoch": 1.7560396809959151,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004689749436985211,
|
|
"loss": 5.003,
|
|
"mean_token_accuracy": 0.20513325482606887,
|
|
"num_tokens": 39167546.0,
|
|
"step": 22570
|
|
},
|
|
{
|
|
"entropy": 5.669141006469727,
|
|
"epoch": 1.7564287103676328,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00046896089819242304,
|
|
"loss": 5.0588,
|
|
"mean_token_accuracy": 0.1938392236828804,
|
|
"num_tokens": 39176547.0,
|
|
"step": 22575
|
|
},
|
|
{
|
|
"entropy": 5.745855236053467,
|
|
"epoch": 1.7568177397393503,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004689468497432771,
|
|
"loss": 5.0725,
|
|
"mean_token_accuracy": 0.198039710521698,
|
|
"num_tokens": 39185273.0,
|
|
"step": 22580
|
|
},
|
|
{
|
|
"entropy": 5.703879451751709,
|
|
"epoch": 1.7572067691110678,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004689327983512963,
|
|
"loss": 5.0321,
|
|
"mean_token_accuracy": 0.20252016484737395,
|
|
"num_tokens": 39194204.0,
|
|
"step": 22585
|
|
},
|
|
{
|
|
"entropy": 5.667798328399658,
|
|
"epoch": 1.7575957984827855,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00046891874401669404,
|
|
"loss": 4.9768,
|
|
"mean_token_accuracy": 0.20301975756883622,
|
|
"num_tokens": 39202951.0,
|
|
"step": 22590
|
|
},
|
|
{
|
|
"entropy": 5.588111639022827,
|
|
"epoch": 1.7579848278545032,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004689046867396834,
|
|
"loss": 5.0512,
|
|
"mean_token_accuracy": 0.19673458784818648,
|
|
"num_tokens": 39211508.0,
|
|
"step": 22595
|
|
},
|
|
{
|
|
"entropy": 5.7373357772827145,
|
|
"epoch": 1.7583738572262204,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004688906265204779,
|
|
"loss": 5.113,
|
|
"mean_token_accuracy": 0.19004614800214767,
|
|
"num_tokens": 39219804.0,
|
|
"step": 22600
|
|
},
|
|
{
|
|
"entropy": 5.753034400939941,
|
|
"epoch": 1.7587628865979381,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004688765633592907,
|
|
"loss": 5.142,
|
|
"mean_token_accuracy": 0.1904366448521614,
|
|
"num_tokens": 39228204.0,
|
|
"step": 22605
|
|
},
|
|
{
|
|
"entropy": 5.6577208042144775,
|
|
"epoch": 1.7591519159696558,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004688624972563352,
|
|
"loss": 5.0685,
|
|
"mean_token_accuracy": 0.19090791046619415,
|
|
"num_tokens": 39237003.0,
|
|
"step": 22610
|
|
},
|
|
{
|
|
"entropy": 5.621747016906738,
|
|
"epoch": 1.7595409453413733,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004688484282118249,
|
|
"loss": 5.0332,
|
|
"mean_token_accuracy": 0.19215899407863618,
|
|
"num_tokens": 39245636.0,
|
|
"step": 22615
|
|
},
|
|
{
|
|
"entropy": 5.5834471702575685,
|
|
"epoch": 1.7599299747130908,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004688343562259732,
|
|
"loss": 4.9189,
|
|
"mean_token_accuracy": 0.2004231721162796,
|
|
"num_tokens": 39254288.0,
|
|
"step": 22620
|
|
},
|
|
{
|
|
"entropy": 5.679382562637329,
|
|
"epoch": 1.7603190040848085,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004688202812989937,
|
|
"loss": 5.1094,
|
|
"mean_token_accuracy": 0.1992802456021309,
|
|
"num_tokens": 39263217.0,
|
|
"step": 22625
|
|
},
|
|
{
|
|
"entropy": 5.604801511764526,
|
|
"epoch": 1.760708033456526,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004688062034311,
|
|
"loss": 5.0664,
|
|
"mean_token_accuracy": 0.19958146810531616,
|
|
"num_tokens": 39271240.0,
|
|
"step": 22630
|
|
},
|
|
{
|
|
"entropy": 5.609039688110352,
|
|
"epoch": 1.7610970628282434,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00046879212262250546,
|
|
"loss": 4.9922,
|
|
"mean_token_accuracy": 0.20655782222747804,
|
|
"num_tokens": 39279665.0,
|
|
"step": 22635
|
|
},
|
|
{
|
|
"entropy": 5.699652242660522,
|
|
"epoch": 1.761486092199961,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00046877803887342406,
|
|
"loss": 5.175,
|
|
"mean_token_accuracy": 0.192455293238163,
|
|
"num_tokens": 39287975.0,
|
|
"step": 22640
|
|
},
|
|
{
|
|
"entropy": 5.716793346405029,
|
|
"epoch": 1.7618751215716788,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004687639521840693,
|
|
"loss": 5.1186,
|
|
"mean_token_accuracy": 0.19389519840478897,
|
|
"num_tokens": 39296541.0,
|
|
"step": 22645
|
|
},
|
|
{
|
|
"entropy": 5.695902109146118,
|
|
"epoch": 1.7622641509433963,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00046874986255465495,
|
|
"loss": 5.0083,
|
|
"mean_token_accuracy": 0.20217987298965454,
|
|
"num_tokens": 39304710.0,
|
|
"step": 22650
|
|
},
|
|
{
|
|
"entropy": 5.657218360900879,
|
|
"epoch": 1.7626531803151138,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00046873576998539485,
|
|
"loss": 4.9624,
|
|
"mean_token_accuracy": 0.20321538746356965,
|
|
"num_tokens": 39313236.0,
|
|
"step": 22655
|
|
},
|
|
{
|
|
"entropy": 5.607696008682251,
|
|
"epoch": 1.7630422096868315,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004687216744765028,
|
|
"loss": 4.9099,
|
|
"mean_token_accuracy": 0.20135416239500045,
|
|
"num_tokens": 39322656.0,
|
|
"step": 22660
|
|
},
|
|
{
|
|
"entropy": 5.656253337860107,
|
|
"epoch": 1.763431239058549,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004687075760281927,
|
|
"loss": 4.9794,
|
|
"mean_token_accuracy": 0.2120069906115532,
|
|
"num_tokens": 39331074.0,
|
|
"step": 22665
|
|
},
|
|
{
|
|
"entropy": 5.643962144851685,
|
|
"epoch": 1.7638202684302664,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004686934746406784,
|
|
"loss": 5.0419,
|
|
"mean_token_accuracy": 0.1975744664669037,
|
|
"num_tokens": 39339450.0,
|
|
"step": 22670
|
|
},
|
|
{
|
|
"entropy": 5.678130435943603,
|
|
"epoch": 1.764209297801984,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00046867937031417397,
|
|
"loss": 5.1565,
|
|
"mean_token_accuracy": 0.19002707600593566,
|
|
"num_tokens": 39347270.0,
|
|
"step": 22675
|
|
},
|
|
{
|
|
"entropy": 5.656103849411011,
|
|
"epoch": 1.7645983271737016,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004686652630488933,
|
|
"loss": 5.0679,
|
|
"mean_token_accuracy": 0.1878320664167404,
|
|
"num_tokens": 39355853.0,
|
|
"step": 22680
|
|
},
|
|
{
|
|
"entropy": 5.580417728424072,
|
|
"epoch": 1.764987356545419,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00046865115284505063,
|
|
"loss": 4.9699,
|
|
"mean_token_accuracy": 0.20845221728086472,
|
|
"num_tokens": 39364160.0,
|
|
"step": 22685
|
|
},
|
|
{
|
|
"entropy": 5.622933101654053,
|
|
"epoch": 1.7653763859171367,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00046863703970285986,
|
|
"loss": 5.0646,
|
|
"mean_token_accuracy": 0.19981067329645158,
|
|
"num_tokens": 39372504.0,
|
|
"step": 22690
|
|
},
|
|
{
|
|
"entropy": 5.663434171676636,
|
|
"epoch": 1.7657654152888544,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004686229236225352,
|
|
"loss": 5.056,
|
|
"mean_token_accuracy": 0.2035764843225479,
|
|
"num_tokens": 39380883.0,
|
|
"step": 22695
|
|
},
|
|
{
|
|
"entropy": 5.7430390357971195,
|
|
"epoch": 1.766154444660572,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004686088046042909,
|
|
"loss": 5.1099,
|
|
"mean_token_accuracy": 0.1917836457490921,
|
|
"num_tokens": 39389943.0,
|
|
"step": 22700
|
|
},
|
|
{
|
|
"entropy": 5.596102619171143,
|
|
"epoch": 1.7665434740322894,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00046859468264834114,
|
|
"loss": 5.0603,
|
|
"mean_token_accuracy": 0.20420622676610947,
|
|
"num_tokens": 39398919.0,
|
|
"step": 22705
|
|
},
|
|
{
|
|
"entropy": 5.67539701461792,
|
|
"epoch": 1.766932503404007,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00046858055775490017,
|
|
"loss": 5.1429,
|
|
"mean_token_accuracy": 0.1941673770546913,
|
|
"num_tokens": 39407547.0,
|
|
"step": 22710
|
|
},
|
|
{
|
|
"entropy": 5.648145771026611,
|
|
"epoch": 1.7673215327757246,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004685664299241825,
|
|
"loss": 4.9771,
|
|
"mean_token_accuracy": 0.20077628642320633,
|
|
"num_tokens": 39416264.0,
|
|
"step": 22715
|
|
},
|
|
{
|
|
"entropy": 5.62908411026001,
|
|
"epoch": 1.767710562147442,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004685522991564022,
|
|
"loss": 5.0399,
|
|
"mean_token_accuracy": 0.19342577159404756,
|
|
"num_tokens": 39424104.0,
|
|
"step": 22720
|
|
},
|
|
{
|
|
"entropy": 5.693596601486206,
|
|
"epoch": 1.7680995915191597,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004685381654517738,
|
|
"loss": 5.0853,
|
|
"mean_token_accuracy": 0.19596892595291138,
|
|
"num_tokens": 39432443.0,
|
|
"step": 22725
|
|
},
|
|
{
|
|
"entropy": 5.620149850845337,
|
|
"epoch": 1.7684886208908772,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004685240288105119,
|
|
"loss": 5.0557,
|
|
"mean_token_accuracy": 0.19603675305843354,
|
|
"num_tokens": 39441620.0,
|
|
"step": 22730
|
|
},
|
|
{
|
|
"entropy": 5.628264617919922,
|
|
"epoch": 1.7688776502625947,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00046850988923283085,
|
|
"loss": 5.0249,
|
|
"mean_token_accuracy": 0.2046712026000023,
|
|
"num_tokens": 39449854.0,
|
|
"step": 22735
|
|
},
|
|
{
|
|
"entropy": 5.644801044464112,
|
|
"epoch": 1.7692666796343124,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00046849574671894523,
|
|
"loss": 5.0969,
|
|
"mean_token_accuracy": 0.19389274567365647,
|
|
"num_tokens": 39458496.0,
|
|
"step": 22740
|
|
},
|
|
{
|
|
"entropy": 5.695472192764282,
|
|
"epoch": 1.76965570900603,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00046848160126906956,
|
|
"loss": 5.1113,
|
|
"mean_token_accuracy": 0.19473907947540284,
|
|
"num_tokens": 39466545.0,
|
|
"step": 22745
|
|
},
|
|
{
|
|
"entropy": 5.68575439453125,
|
|
"epoch": 1.7700447383777476,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004684674528834186,
|
|
"loss": 5.0967,
|
|
"mean_token_accuracy": 0.19515854269266128,
|
|
"num_tokens": 39475771.0,
|
|
"step": 22750
|
|
},
|
|
{
|
|
"entropy": 5.6835036277771,
|
|
"epoch": 1.770433767749465,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00046845330156220703,
|
|
"loss": 5.1075,
|
|
"mean_token_accuracy": 0.19743928909301758,
|
|
"num_tokens": 39484244.0,
|
|
"step": 22755
|
|
},
|
|
{
|
|
"entropy": 5.718806219100952,
|
|
"epoch": 1.7708227971211827,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004684391473056495,
|
|
"loss": 5.1383,
|
|
"mean_token_accuracy": 0.19019536375999452,
|
|
"num_tokens": 39493138.0,
|
|
"step": 22760
|
|
},
|
|
{
|
|
"entropy": 5.737482309341431,
|
|
"epoch": 1.7712118264929002,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00046842499011396076,
|
|
"loss": 5.0948,
|
|
"mean_token_accuracy": 0.1941129133105278,
|
|
"num_tokens": 39502065.0,
|
|
"step": 22765
|
|
},
|
|
{
|
|
"entropy": 5.697163152694702,
|
|
"epoch": 1.7716008558646177,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00046841082998735575,
|
|
"loss": 5.0726,
|
|
"mean_token_accuracy": 0.20459358245134354,
|
|
"num_tokens": 39510095.0,
|
|
"step": 22770
|
|
},
|
|
{
|
|
"entropy": 5.635035753250122,
|
|
"epoch": 1.7719898852363354,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00046839666692604916,
|
|
"loss": 5.1274,
|
|
"mean_token_accuracy": 0.19442155808210373,
|
|
"num_tokens": 39518104.0,
|
|
"step": 22775
|
|
},
|
|
{
|
|
"entropy": 5.716279029846191,
|
|
"epoch": 1.7723789146080529,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.000468382500930256,
|
|
"loss": 5.086,
|
|
"mean_token_accuracy": 0.1993977263569832,
|
|
"num_tokens": 39526768.0,
|
|
"step": 22780
|
|
},
|
|
{
|
|
"entropy": 5.673862409591675,
|
|
"epoch": 1.7727679439797703,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00046836833200019116,
|
|
"loss": 5.0487,
|
|
"mean_token_accuracy": 0.19186717867851258,
|
|
"num_tokens": 39535847.0,
|
|
"step": 22785
|
|
},
|
|
{
|
|
"entropy": 5.734010219573975,
|
|
"epoch": 1.773156973351488,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004683541601360697,
|
|
"loss": 5.1132,
|
|
"mean_token_accuracy": 0.20216183960437775,
|
|
"num_tokens": 39544364.0,
|
|
"step": 22790
|
|
},
|
|
{
|
|
"entropy": 5.702363157272339,
|
|
"epoch": 1.7735460027232057,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00046833998533810653,
|
|
"loss": 5.1274,
|
|
"mean_token_accuracy": 0.18689947426319123,
|
|
"num_tokens": 39552733.0,
|
|
"step": 22795
|
|
},
|
|
{
|
|
"entropy": 5.695834112167359,
|
|
"epoch": 1.7739350320949232,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004683258076065169,
|
|
"loss": 5.0619,
|
|
"mean_token_accuracy": 0.19932250082492828,
|
|
"num_tokens": 39561580.0,
|
|
"step": 22800
|
|
},
|
|
{
|
|
"entropy": 5.625617504119873,
|
|
"epoch": 1.7743240614666407,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00046831162694151586,
|
|
"loss": 5.0517,
|
|
"mean_token_accuracy": 0.19228088706731797,
|
|
"num_tokens": 39570283.0,
|
|
"step": 22805
|
|
},
|
|
{
|
|
"entropy": 5.668644189834595,
|
|
"epoch": 1.7747130908383584,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00046829744334331855,
|
|
"loss": 5.0251,
|
|
"mean_token_accuracy": 0.19798846840858458,
|
|
"num_tokens": 39578835.0,
|
|
"step": 22810
|
|
},
|
|
{
|
|
"entropy": 5.684339761734009,
|
|
"epoch": 1.7751021202100759,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00046828325681214013,
|
|
"loss": 5.0779,
|
|
"mean_token_accuracy": 0.20166678726673126,
|
|
"num_tokens": 39587053.0,
|
|
"step": 22815
|
|
},
|
|
{
|
|
"entropy": 5.676909780502319,
|
|
"epoch": 1.7754911495817933,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000468269067348196,
|
|
"loss": 5.1579,
|
|
"mean_token_accuracy": 0.18229772597551347,
|
|
"num_tokens": 39595799.0,
|
|
"step": 22820
|
|
},
|
|
{
|
|
"entropy": 5.707350969314575,
|
|
"epoch": 1.775880178953511,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004682548749517014,
|
|
"loss": 5.0331,
|
|
"mean_token_accuracy": 0.1991925686597824,
|
|
"num_tokens": 39604248.0,
|
|
"step": 22825
|
|
},
|
|
{
|
|
"entropy": 5.624576568603516,
|
|
"epoch": 1.7762692083252287,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00046824067962287163,
|
|
"loss": 5.0319,
|
|
"mean_token_accuracy": 0.19990004897117614,
|
|
"num_tokens": 39612690.0,
|
|
"step": 22830
|
|
},
|
|
{
|
|
"entropy": 5.666665887832641,
|
|
"epoch": 1.776658237696946,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004682264813619221,
|
|
"loss": 5.0725,
|
|
"mean_token_accuracy": 0.19386529922485352,
|
|
"num_tokens": 39621784.0,
|
|
"step": 22835
|
|
},
|
|
{
|
|
"entropy": 5.658817148208618,
|
|
"epoch": 1.7770472670686637,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00046821228016906836,
|
|
"loss": 5.0013,
|
|
"mean_token_accuracy": 0.2040756016969681,
|
|
"num_tokens": 39630455.0,
|
|
"step": 22840
|
|
},
|
|
{
|
|
"entropy": 5.635995864868164,
|
|
"epoch": 1.7774362964403814,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004681980760445257,
|
|
"loss": 5.0147,
|
|
"mean_token_accuracy": 0.19693631827831268,
|
|
"num_tokens": 39639017.0,
|
|
"step": 22845
|
|
},
|
|
{
|
|
"entropy": 5.642162275314331,
|
|
"epoch": 1.7778253258120988,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004681838689885098,
|
|
"loss": 4.9665,
|
|
"mean_token_accuracy": 0.2065414234995842,
|
|
"num_tokens": 39648083.0,
|
|
"step": 22850
|
|
},
|
|
{
|
|
"entropy": 5.661451816558838,
|
|
"epoch": 1.7782143551838163,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004681696590012362,
|
|
"loss": 5.0582,
|
|
"mean_token_accuracy": 0.20174534022808074,
|
|
"num_tokens": 39656887.0,
|
|
"step": 22855
|
|
},
|
|
{
|
|
"entropy": 5.6726624965667725,
|
|
"epoch": 1.778603384555534,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00046815544608292043,
|
|
"loss": 5.089,
|
|
"mean_token_accuracy": 0.1949265718460083,
|
|
"num_tokens": 39665658.0,
|
|
"step": 22860
|
|
},
|
|
{
|
|
"entropy": 5.6686193466186525,
|
|
"epoch": 1.7789924139272515,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004681412302337782,
|
|
"loss": 5.0508,
|
|
"mean_token_accuracy": 0.19710324704647064,
|
|
"num_tokens": 39673423.0,
|
|
"step": 22865
|
|
},
|
|
{
|
|
"entropy": 5.691291570663452,
|
|
"epoch": 1.779381443298969,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004681270114540252,
|
|
"loss": 5.0719,
|
|
"mean_token_accuracy": 0.20220151543617249,
|
|
"num_tokens": 39682382.0,
|
|
"step": 22870
|
|
},
|
|
{
|
|
"entropy": 5.700251150131225,
|
|
"epoch": 1.7797704726706867,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004681127897438772,
|
|
"loss": 5.1107,
|
|
"mean_token_accuracy": 0.19690333157777787,
|
|
"num_tokens": 39691089.0,
|
|
"step": 22875
|
|
},
|
|
{
|
|
"entropy": 5.729765319824219,
|
|
"epoch": 1.7801595020424044,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00046809856510355007,
|
|
"loss": 5.1577,
|
|
"mean_token_accuracy": 0.19188273549079896,
|
|
"num_tokens": 39700888.0,
|
|
"step": 22880
|
|
},
|
|
{
|
|
"entropy": 5.723038196563721,
|
|
"epoch": 1.7805485314141216,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004680843375332595,
|
|
"loss": 5.1142,
|
|
"mean_token_accuracy": 0.20196729749441147,
|
|
"num_tokens": 39708515.0,
|
|
"step": 22885
|
|
},
|
|
{
|
|
"entropy": 5.619906806945801,
|
|
"epoch": 1.7809375607858393,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00046807010703322143,
|
|
"loss": 4.9656,
|
|
"mean_token_accuracy": 0.2009779006242752,
|
|
"num_tokens": 39716790.0,
|
|
"step": 22890
|
|
},
|
|
{
|
|
"entropy": 5.72461314201355,
|
|
"epoch": 1.781326590157557,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004680558736036518,
|
|
"loss": 5.0329,
|
|
"mean_token_accuracy": 0.19692874401807786,
|
|
"num_tokens": 39726292.0,
|
|
"step": 22895
|
|
},
|
|
{
|
|
"entropy": 5.641946840286255,
|
|
"epoch": 1.7817156195292745,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004680416372447666,
|
|
"loss": 5.0403,
|
|
"mean_token_accuracy": 0.20342497080564498,
|
|
"num_tokens": 39735222.0,
|
|
"step": 22900
|
|
},
|
|
{
|
|
"entropy": 5.627364683151245,
|
|
"epoch": 1.782104648900992,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00046802739795678177,
|
|
"loss": 5.0891,
|
|
"mean_token_accuracy": 0.1946094438433647,
|
|
"num_tokens": 39744619.0,
|
|
"step": 22905
|
|
},
|
|
{
|
|
"entropy": 5.673235034942627,
|
|
"epoch": 1.7824936782727097,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00046801315573991346,
|
|
"loss": 5.0901,
|
|
"mean_token_accuracy": 0.19993328750133516,
|
|
"num_tokens": 39752394.0,
|
|
"step": 22910
|
|
},
|
|
{
|
|
"entropy": 5.633034992218017,
|
|
"epoch": 1.7828827076444271,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00046799891059437764,
|
|
"loss": 4.991,
|
|
"mean_token_accuracy": 0.20043096244335173,
|
|
"num_tokens": 39760529.0,
|
|
"step": 22915
|
|
},
|
|
{
|
|
"entropy": 5.720476579666138,
|
|
"epoch": 1.7832717370161446,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00046798466252039056,
|
|
"loss": 5.1383,
|
|
"mean_token_accuracy": 0.19344329684972764,
|
|
"num_tokens": 39768231.0,
|
|
"step": 22920
|
|
},
|
|
{
|
|
"entropy": 5.75451340675354,
|
|
"epoch": 1.7836607663878623,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00046797041151816845,
|
|
"loss": 5.1984,
|
|
"mean_token_accuracy": 0.19174774885177612,
|
|
"num_tokens": 39776773.0,
|
|
"step": 22925
|
|
},
|
|
{
|
|
"entropy": 5.7062615871429445,
|
|
"epoch": 1.78404979575958,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00046795615758792747,
|
|
"loss": 5.0567,
|
|
"mean_token_accuracy": 0.1905716598033905,
|
|
"num_tokens": 39785248.0,
|
|
"step": 22930
|
|
},
|
|
{
|
|
"entropy": 5.632964611053467,
|
|
"epoch": 1.7844388251312973,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004679419007298839,
|
|
"loss": 5.0575,
|
|
"mean_token_accuracy": 0.19742142856121064,
|
|
"num_tokens": 39794794.0,
|
|
"step": 22935
|
|
},
|
|
{
|
|
"entropy": 5.6968883037567135,
|
|
"epoch": 1.784827854503015,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004679276409442541,
|
|
"loss": 5.0396,
|
|
"mean_token_accuracy": 0.1929635375738144,
|
|
"num_tokens": 39803662.0,
|
|
"step": 22940
|
|
},
|
|
{
|
|
"entropy": 5.7244353771209715,
|
|
"epoch": 1.7852168838747327,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004679133782312544,
|
|
"loss": 5.0432,
|
|
"mean_token_accuracy": 0.19755503684282302,
|
|
"num_tokens": 39812189.0,
|
|
"step": 22945
|
|
},
|
|
{
|
|
"entropy": 5.679898691177368,
|
|
"epoch": 1.7856059132464501,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004678991125911013,
|
|
"loss": 5.0813,
|
|
"mean_token_accuracy": 0.19720999300479888,
|
|
"num_tokens": 39820831.0,
|
|
"step": 22950
|
|
},
|
|
{
|
|
"entropy": 5.571303224563598,
|
|
"epoch": 1.7859949426181676,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004678848440240111,
|
|
"loss": 4.9429,
|
|
"mean_token_accuracy": 0.2035401001572609,
|
|
"num_tokens": 39829380.0,
|
|
"step": 22955
|
|
},
|
|
{
|
|
"entropy": 5.631348943710327,
|
|
"epoch": 1.7863839719898853,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004678705725302005,
|
|
"loss": 5.0633,
|
|
"mean_token_accuracy": 0.20108917355537415,
|
|
"num_tokens": 39838243.0,
|
|
"step": 22960
|
|
},
|
|
{
|
|
"entropy": 5.689360809326172,
|
|
"epoch": 1.7867730013616028,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004678562981098859,
|
|
"loss": 5.0397,
|
|
"mean_token_accuracy": 0.20027730166912078,
|
|
"num_tokens": 39846885.0,
|
|
"step": 22965
|
|
},
|
|
{
|
|
"entropy": 5.665248441696167,
|
|
"epoch": 1.7871620307333203,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00046784202076328394,
|
|
"loss": 5.0054,
|
|
"mean_token_accuracy": 0.20157646387815475,
|
|
"num_tokens": 39855337.0,
|
|
"step": 22970
|
|
},
|
|
{
|
|
"entropy": 5.590274238586426,
|
|
"epoch": 1.787551060105038,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00046782774049061124,
|
|
"loss": 5.0752,
|
|
"mean_token_accuracy": 0.20414217114448546,
|
|
"num_tokens": 39864606.0,
|
|
"step": 22975
|
|
},
|
|
{
|
|
"entropy": 5.74508376121521,
|
|
"epoch": 1.7879400894767556,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004678134572920845,
|
|
"loss": 5.0775,
|
|
"mean_token_accuracy": 0.19494454711675643,
|
|
"num_tokens": 39872621.0,
|
|
"step": 22980
|
|
},
|
|
{
|
|
"entropy": 5.710721445083618,
|
|
"epoch": 1.788329118848473,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004677991711679204,
|
|
"loss": 5.0525,
|
|
"mean_token_accuracy": 0.20031729489564895,
|
|
"num_tokens": 39880525.0,
|
|
"step": 22985
|
|
},
|
|
{
|
|
"entropy": 5.645658349990844,
|
|
"epoch": 1.7887181482201906,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00046778488211833585,
|
|
"loss": 4.9711,
|
|
"mean_token_accuracy": 0.20704260915517808,
|
|
"num_tokens": 39889541.0,
|
|
"step": 22990
|
|
},
|
|
{
|
|
"entropy": 5.672270727157593,
|
|
"epoch": 1.7891071775919083,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004677705901435475,
|
|
"loss": 5.0438,
|
|
"mean_token_accuracy": 0.1979015737771988,
|
|
"num_tokens": 39897682.0,
|
|
"step": 22995
|
|
},
|
|
{
|
|
"entropy": 5.703026056289673,
|
|
"epoch": 1.7894962069636258,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004677562952437723,
|
|
"loss": 5.0597,
|
|
"mean_token_accuracy": 0.19432690292596816,
|
|
"num_tokens": 39906656.0,
|
|
"step": 23000
|
|
},
|
|
{
|
|
"entropy": 5.723121500015258,
|
|
"epoch": 1.7898852363353432,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00046774199741922705,
|
|
"loss": 5.1327,
|
|
"mean_token_accuracy": 0.19010985791683196,
|
|
"num_tokens": 39915202.0,
|
|
"step": 23005
|
|
},
|
|
{
|
|
"entropy": 5.621491575241089,
|
|
"epoch": 1.790274265707061,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00046772769667012884,
|
|
"loss": 4.978,
|
|
"mean_token_accuracy": 0.20201105028390884,
|
|
"num_tokens": 39923510.0,
|
|
"step": 23010
|
|
},
|
|
{
|
|
"entropy": 5.5676689624786375,
|
|
"epoch": 1.7906632950787784,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004677133929966946,
|
|
"loss": 5.0231,
|
|
"mean_token_accuracy": 0.2080300882458687,
|
|
"num_tokens": 39932468.0,
|
|
"step": 23015
|
|
},
|
|
{
|
|
"entropy": 5.71773247718811,
|
|
"epoch": 1.791052324450496,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00046769908639914134,
|
|
"loss": 5.1256,
|
|
"mean_token_accuracy": 0.19488838613033294,
|
|
"num_tokens": 39942758.0,
|
|
"step": 23020
|
|
},
|
|
{
|
|
"entropy": 5.7325835704803465,
|
|
"epoch": 1.7914413538222136,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004676847768776861,
|
|
"loss": 5.1069,
|
|
"mean_token_accuracy": 0.19283661395311355,
|
|
"num_tokens": 39950829.0,
|
|
"step": 23025
|
|
},
|
|
{
|
|
"entropy": 5.620270252227783,
|
|
"epoch": 1.7918303831939313,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004676704644325462,
|
|
"loss": 5.0978,
|
|
"mean_token_accuracy": 0.19478842318058015,
|
|
"num_tokens": 39960204.0,
|
|
"step": 23030
|
|
},
|
|
{
|
|
"entropy": 5.662912130355835,
|
|
"epoch": 1.7922194125656488,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004676561490639385,
|
|
"loss": 5.0521,
|
|
"mean_token_accuracy": 0.19848431050777435,
|
|
"num_tokens": 39968513.0,
|
|
"step": 23035
|
|
},
|
|
{
|
|
"entropy": 5.654798793792724,
|
|
"epoch": 1.7926084419373662,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004676418307720805,
|
|
"loss": 5.0886,
|
|
"mean_token_accuracy": 0.19719878286123277,
|
|
"num_tokens": 39977181.0,
|
|
"step": 23040
|
|
},
|
|
{
|
|
"entropy": 5.558326864242554,
|
|
"epoch": 1.792997471309084,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004676275095571892,
|
|
"loss": 4.9012,
|
|
"mean_token_accuracy": 0.2106527015566826,
|
|
"num_tokens": 39986760.0,
|
|
"step": 23045
|
|
},
|
|
{
|
|
"entropy": 5.6533793926239015,
|
|
"epoch": 1.7933865006808014,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00046761318541948215,
|
|
"loss": 5.1154,
|
|
"mean_token_accuracy": 0.18526081889867782,
|
|
"num_tokens": 39995203.0,
|
|
"step": 23050
|
|
},
|
|
{
|
|
"entropy": 5.643955230712891,
|
|
"epoch": 1.7937755300525189,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004675988583591766,
|
|
"loss": 4.9996,
|
|
"mean_token_accuracy": 0.20396423041820527,
|
|
"num_tokens": 40003526.0,
|
|
"step": 23055
|
|
},
|
|
{
|
|
"entropy": 5.681190490722656,
|
|
"epoch": 1.7941645594242366,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00046758452837648997,
|
|
"loss": 5.0547,
|
|
"mean_token_accuracy": 0.19564736485481263,
|
|
"num_tokens": 40012036.0,
|
|
"step": 23060
|
|
},
|
|
{
|
|
"entropy": 5.635527181625366,
|
|
"epoch": 1.794553588795954,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004675701954716395,
|
|
"loss": 5.0653,
|
|
"mean_token_accuracy": 0.19711072444915773,
|
|
"num_tokens": 40020237.0,
|
|
"step": 23065
|
|
},
|
|
{
|
|
"entropy": 5.611155700683594,
|
|
"epoch": 1.7949426181676715,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00046755585964484286,
|
|
"loss": 4.9757,
|
|
"mean_token_accuracy": 0.20652034133672714,
|
|
"num_tokens": 40028749.0,
|
|
"step": 23070
|
|
},
|
|
{
|
|
"entropy": 5.6394758224487305,
|
|
"epoch": 1.7953316475393892,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004675415208963177,
|
|
"loss": 4.9477,
|
|
"mean_token_accuracy": 0.20087110251188278,
|
|
"num_tokens": 40036799.0,
|
|
"step": 23075
|
|
},
|
|
{
|
|
"entropy": 5.629435968399048,
|
|
"epoch": 1.795720676911107,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00046752717922628125,
|
|
"loss": 5.0887,
|
|
"mean_token_accuracy": 0.19493671059608458,
|
|
"num_tokens": 40045416.0,
|
|
"step": 23080
|
|
},
|
|
{
|
|
"entropy": 5.7006933212280275,
|
|
"epoch": 1.7961097062828244,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004675128346349514,
|
|
"loss": 5.1208,
|
|
"mean_token_accuracy": 0.1985117867588997,
|
|
"num_tokens": 40054128.0,
|
|
"step": 23085
|
|
},
|
|
{
|
|
"entropy": 5.775534915924072,
|
|
"epoch": 1.7964987356545419,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00046749848712254554,
|
|
"loss": 5.1354,
|
|
"mean_token_accuracy": 0.19225320518016814,
|
|
"num_tokens": 40062765.0,
|
|
"step": 23090
|
|
},
|
|
{
|
|
"entropy": 5.642290782928467,
|
|
"epoch": 1.7968877650262596,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00046748413668928164,
|
|
"loss": 5.0555,
|
|
"mean_token_accuracy": 0.20141281187534332,
|
|
"num_tokens": 40071190.0,
|
|
"step": 23095
|
|
},
|
|
{
|
|
"entropy": 5.654160833358764,
|
|
"epoch": 1.797276794397977,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004674697833353774,
|
|
"loss": 5.0654,
|
|
"mean_token_accuracy": 0.1998469427227974,
|
|
"num_tokens": 40080552.0,
|
|
"step": 23100
|
|
},
|
|
{
|
|
"entropy": 5.67447862625122,
|
|
"epoch": 1.7976658237696945,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00046745542706105045,
|
|
"loss": 5.0817,
|
|
"mean_token_accuracy": 0.20118483752012253,
|
|
"num_tokens": 40089407.0,
|
|
"step": 23105
|
|
},
|
|
{
|
|
"entropy": 5.794737243652344,
|
|
"epoch": 1.7980548531414122,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00046744106786651875,
|
|
"loss": 5.2701,
|
|
"mean_token_accuracy": 0.18606453239917756,
|
|
"num_tokens": 40097946.0,
|
|
"step": 23110
|
|
},
|
|
{
|
|
"entropy": 5.655776882171631,
|
|
"epoch": 1.7984438825131297,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004674267057520001,
|
|
"loss": 5.0128,
|
|
"mean_token_accuracy": 0.20463781356811522,
|
|
"num_tokens": 40105901.0,
|
|
"step": 23115
|
|
},
|
|
{
|
|
"entropy": 5.61436710357666,
|
|
"epoch": 1.7988329118848472,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004674123407177125,
|
|
"loss": 4.9325,
|
|
"mean_token_accuracy": 0.2023484319448471,
|
|
"num_tokens": 40114481.0,
|
|
"step": 23120
|
|
},
|
|
{
|
|
"entropy": 5.646229028701782,
|
|
"epoch": 1.7992219412565649,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00046739797276387394,
|
|
"loss": 5.0051,
|
|
"mean_token_accuracy": 0.20337729305028915,
|
|
"num_tokens": 40123086.0,
|
|
"step": 23125
|
|
},
|
|
{
|
|
"entropy": 5.654345750808716,
|
|
"epoch": 1.7996109706282826,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00046738360189070235,
|
|
"loss": 5.0062,
|
|
"mean_token_accuracy": 0.20031450390815736,
|
|
"num_tokens": 40131497.0,
|
|
"step": 23130
|
|
},
|
|
{
|
|
"entropy": 5.619352340698242,
|
|
"epoch": 1.8,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004673692280984157,
|
|
"loss": 5.0442,
|
|
"mean_token_accuracy": 0.19908270388841628,
|
|
"num_tokens": 40139632.0,
|
|
"step": 23135
|
|
},
|
|
{
|
|
"entropy": 5.62560658454895,
|
|
"epoch": 1.8003890293717175,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004673548513872324,
|
|
"loss": 5.0156,
|
|
"mean_token_accuracy": 0.2011853873729706,
|
|
"num_tokens": 40148312.0,
|
|
"step": 23140
|
|
},
|
|
{
|
|
"entropy": 5.677383899688721,
|
|
"epoch": 1.8007780587434352,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00046734047175737026,
|
|
"loss": 5.089,
|
|
"mean_token_accuracy": 0.1920654758810997,
|
|
"num_tokens": 40156750.0,
|
|
"step": 23145
|
|
},
|
|
{
|
|
"entropy": 5.630202770233154,
|
|
"epoch": 1.8011670881151527,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00046732608920904754,
|
|
"loss": 5.0582,
|
|
"mean_token_accuracy": 0.19776277244091034,
|
|
"num_tokens": 40165334.0,
|
|
"step": 23150
|
|
},
|
|
{
|
|
"entropy": 5.642322587966919,
|
|
"epoch": 1.8015561174868702,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004673117037424827,
|
|
"loss": 5.0427,
|
|
"mean_token_accuracy": 0.20004768669605255,
|
|
"num_tokens": 40174217.0,
|
|
"step": 23155
|
|
},
|
|
{
|
|
"entropy": 5.602140998840332,
|
|
"epoch": 1.8019451468585879,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00046729731535789375,
|
|
"loss": 5.012,
|
|
"mean_token_accuracy": 0.20319269448518754,
|
|
"num_tokens": 40182889.0,
|
|
"step": 23160
|
|
},
|
|
{
|
|
"entropy": 5.66202449798584,
|
|
"epoch": 1.8023341762303053,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00046728292405549913,
|
|
"loss": 5.069,
|
|
"mean_token_accuracy": 0.19812913239002228,
|
|
"num_tokens": 40191428.0,
|
|
"step": 23165
|
|
},
|
|
{
|
|
"entropy": 5.659556674957275,
|
|
"epoch": 1.8027232056020228,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004672685298355172,
|
|
"loss": 5.0341,
|
|
"mean_token_accuracy": 0.20688219219446183,
|
|
"num_tokens": 40200204.0,
|
|
"step": 23170
|
|
},
|
|
{
|
|
"entropy": 5.641662454605102,
|
|
"epoch": 1.8031122349737405,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004672541326981664,
|
|
"loss": 4.9308,
|
|
"mean_token_accuracy": 0.21110827773809432,
|
|
"num_tokens": 40208326.0,
|
|
"step": 23175
|
|
},
|
|
{
|
|
"entropy": 5.569920396804809,
|
|
"epoch": 1.8035012643454582,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000467239732643665,
|
|
"loss": 5.0495,
|
|
"mean_token_accuracy": 0.20019952654838563,
|
|
"num_tokens": 40217300.0,
|
|
"step": 23180
|
|
},
|
|
{
|
|
"entropy": 5.642634057998658,
|
|
"epoch": 1.8038902937171757,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00046722532967223183,
|
|
"loss": 5.1421,
|
|
"mean_token_accuracy": 0.19416471868753432,
|
|
"num_tokens": 40226695.0,
|
|
"step": 23185
|
|
},
|
|
{
|
|
"entropy": 5.692462491989136,
|
|
"epoch": 1.8042793230888932,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004672109237840851,
|
|
"loss": 5.0292,
|
|
"mean_token_accuracy": 0.19761148393154143,
|
|
"num_tokens": 40235286.0,
|
|
"step": 23190
|
|
},
|
|
{
|
|
"entropy": 5.609381532669067,
|
|
"epoch": 1.8046683524606109,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00046719651497944355,
|
|
"loss": 4.9935,
|
|
"mean_token_accuracy": 0.20100178122520446,
|
|
"num_tokens": 40244065.0,
|
|
"step": 23195
|
|
},
|
|
{
|
|
"entropy": 5.70858244895935,
|
|
"epoch": 1.8050573818323283,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004671821032585259,
|
|
"loss": 5.1978,
|
|
"mean_token_accuracy": 0.18573150485754014,
|
|
"num_tokens": 40253058.0,
|
|
"step": 23200
|
|
},
|
|
{
|
|
"entropy": 5.712513828277588,
|
|
"epoch": 1.8054464112040458,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004671676886215506,
|
|
"loss": 5.0845,
|
|
"mean_token_accuracy": 0.19421554058790208,
|
|
"num_tokens": 40261797.0,
|
|
"step": 23205
|
|
},
|
|
{
|
|
"entropy": 5.646021223068237,
|
|
"epoch": 1.8058354405757635,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004671532710687365,
|
|
"loss": 5.0395,
|
|
"mean_token_accuracy": 0.20096675753593446,
|
|
"num_tokens": 40270003.0,
|
|
"step": 23210
|
|
},
|
|
{
|
|
"entropy": 5.638779211044311,
|
|
"epoch": 1.806224469947481,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004671388506003024,
|
|
"loss": 5.0679,
|
|
"mean_token_accuracy": 0.19866203665733337,
|
|
"num_tokens": 40278241.0,
|
|
"step": 23215
|
|
},
|
|
{
|
|
"entropy": 5.677653694152832,
|
|
"epoch": 1.8066134993191985,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004671244272164671,
|
|
"loss": 5.1198,
|
|
"mean_token_accuracy": 0.19523296654224395,
|
|
"num_tokens": 40286316.0,
|
|
"step": 23220
|
|
},
|
|
{
|
|
"entropy": 5.667910099029541,
|
|
"epoch": 1.8070025286909162,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00046711000091744935,
|
|
"loss": 5.0748,
|
|
"mean_token_accuracy": 0.19464613497257233,
|
|
"num_tokens": 40295378.0,
|
|
"step": 23225
|
|
},
|
|
{
|
|
"entropy": 5.717720699310303,
|
|
"epoch": 1.8073915580626339,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004670955717034681,
|
|
"loss": 5.0814,
|
|
"mean_token_accuracy": 0.19408326596021652,
|
|
"num_tokens": 40305379.0,
|
|
"step": 23230
|
|
},
|
|
{
|
|
"entropy": 5.710579967498779,
|
|
"epoch": 1.8077805874343513,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00046708113957474233,
|
|
"loss": 5.1186,
|
|
"mean_token_accuracy": 0.1927325263619423,
|
|
"num_tokens": 40314174.0,
|
|
"step": 23235
|
|
},
|
|
{
|
|
"entropy": 5.71313853263855,
|
|
"epoch": 1.8081696168060688,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000467066704531491,
|
|
"loss": 5.1042,
|
|
"mean_token_accuracy": 0.20000478625297546,
|
|
"num_tokens": 40323708.0,
|
|
"step": 23240
|
|
},
|
|
{
|
|
"entropy": 5.647215175628662,
|
|
"epoch": 1.8085586461777865,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004670522665739332,
|
|
"loss": 5.0004,
|
|
"mean_token_accuracy": 0.20029812306165695,
|
|
"num_tokens": 40333664.0,
|
|
"step": 23245
|
|
},
|
|
{
|
|
"entropy": 5.663864660263061,
|
|
"epoch": 1.808947675549504,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004670378257022878,
|
|
"loss": 5.0542,
|
|
"mean_token_accuracy": 0.20027079284191132,
|
|
"num_tokens": 40342037.0,
|
|
"step": 23250
|
|
},
|
|
{
|
|
"entropy": 5.657285118103028,
|
|
"epoch": 1.8093367049212215,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00046702338191677414,
|
|
"loss": 4.9995,
|
|
"mean_token_accuracy": 0.20434896498918534,
|
|
"num_tokens": 40350472.0,
|
|
"step": 23255
|
|
},
|
|
{
|
|
"entropy": 5.667795658111572,
|
|
"epoch": 1.8097257342929391,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004670089352176113,
|
|
"loss": 5.0727,
|
|
"mean_token_accuracy": 0.19985506683588028,
|
|
"num_tokens": 40358829.0,
|
|
"step": 23260
|
|
},
|
|
{
|
|
"entropy": 5.629911088943482,
|
|
"epoch": 1.8101147636646568,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00046699448560501847,
|
|
"loss": 5.0737,
|
|
"mean_token_accuracy": 0.19637651294469832,
|
|
"num_tokens": 40367414.0,
|
|
"step": 23265
|
|
},
|
|
{
|
|
"entropy": 5.667527914047241,
|
|
"epoch": 1.810503793036374,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004669800330792149,
|
|
"loss": 5.1191,
|
|
"mean_token_accuracy": 0.1909766376018524,
|
|
"num_tokens": 40375969.0,
|
|
"step": 23270
|
|
},
|
|
{
|
|
"entropy": 5.722210788726807,
|
|
"epoch": 1.8108928224080918,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00046696557764041994,
|
|
"loss": 5.0594,
|
|
"mean_token_accuracy": 0.19282193928956987,
|
|
"num_tokens": 40384200.0,
|
|
"step": 23275
|
|
},
|
|
{
|
|
"entropy": 5.741775274276733,
|
|
"epoch": 1.8112818517798095,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004669511192888528,
|
|
"loss": 5.1682,
|
|
"mean_token_accuracy": 0.19382085800170898,
|
|
"num_tokens": 40392891.0,
|
|
"step": 23280
|
|
},
|
|
{
|
|
"entropy": 5.717968320846557,
|
|
"epoch": 1.811670881151527,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00046693665802473294,
|
|
"loss": 5.1208,
|
|
"mean_token_accuracy": 0.19663182497024537,
|
|
"num_tokens": 40402009.0,
|
|
"step": 23285
|
|
},
|
|
{
|
|
"entropy": 5.72480263710022,
|
|
"epoch": 1.8120599105232444,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00046692219384827986,
|
|
"loss": 5.1051,
|
|
"mean_token_accuracy": 0.1851302906870842,
|
|
"num_tokens": 40410756.0,
|
|
"step": 23290
|
|
},
|
|
{
|
|
"entropy": 5.706399059295654,
|
|
"epoch": 1.8124489398949621,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004669077267597129,
|
|
"loss": 5.1325,
|
|
"mean_token_accuracy": 0.19384849965572357,
|
|
"num_tokens": 40420087.0,
|
|
"step": 23295
|
|
},
|
|
{
|
|
"entropy": 5.619845056533814,
|
|
"epoch": 1.8128379692666796,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00046689325675925174,
|
|
"loss": 4.9897,
|
|
"mean_token_accuracy": 0.20281611680984496,
|
|
"num_tokens": 40428741.0,
|
|
"step": 23300
|
|
},
|
|
{
|
|
"entropy": 5.759622097015381,
|
|
"epoch": 1.813226998638397,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00046687878384711574,
|
|
"loss": 5.198,
|
|
"mean_token_accuracy": 0.18550204932689668,
|
|
"num_tokens": 40438128.0,
|
|
"step": 23305
|
|
},
|
|
{
|
|
"entropy": 5.712845325469971,
|
|
"epoch": 1.8136160280101148,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00046686430802352476,
|
|
"loss": 5.1376,
|
|
"mean_token_accuracy": 0.19512750059366227,
|
|
"num_tokens": 40446990.0,
|
|
"step": 23310
|
|
},
|
|
{
|
|
"entropy": 5.647995328903198,
|
|
"epoch": 1.8140050573818325,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004668498292886982,
|
|
"loss": 5.0422,
|
|
"mean_token_accuracy": 0.19947749823331834,
|
|
"num_tokens": 40454627.0,
|
|
"step": 23315
|
|
},
|
|
{
|
|
"entropy": 5.634478950500489,
|
|
"epoch": 1.8143940867535497,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00046683534764285577,
|
|
"loss": 5.0716,
|
|
"mean_token_accuracy": 0.2054267942905426,
|
|
"num_tokens": 40463321.0,
|
|
"step": 23320
|
|
},
|
|
{
|
|
"entropy": 5.609573316574097,
|
|
"epoch": 1.8147831161252674,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00046682086308621725,
|
|
"loss": 4.9214,
|
|
"mean_token_accuracy": 0.2108432486653328,
|
|
"num_tokens": 40472156.0,
|
|
"step": 23325
|
|
},
|
|
{
|
|
"entropy": 5.643345928192138,
|
|
"epoch": 1.8151721454969851,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004668063756190026,
|
|
"loss": 5.0675,
|
|
"mean_token_accuracy": 0.1969673976302147,
|
|
"num_tokens": 40480938.0,
|
|
"step": 23330
|
|
},
|
|
{
|
|
"entropy": 5.632159280776977,
|
|
"epoch": 1.8155611748687026,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00046679188524143136,
|
|
"loss": 5.0114,
|
|
"mean_token_accuracy": 0.20527398139238356,
|
|
"num_tokens": 40489740.0,
|
|
"step": 23335
|
|
},
|
|
{
|
|
"entropy": 5.705085706710816,
|
|
"epoch": 1.81595020424042,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004667773919537235,
|
|
"loss": 5.0025,
|
|
"mean_token_accuracy": 0.2028025820851326,
|
|
"num_tokens": 40498420.0,
|
|
"step": 23340
|
|
},
|
|
{
|
|
"entropy": 5.634736204147339,
|
|
"epoch": 1.8163392336121378,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00046676289575609914,
|
|
"loss": 4.9234,
|
|
"mean_token_accuracy": 0.20825934708118438,
|
|
"num_tokens": 40506634.0,
|
|
"step": 23345
|
|
},
|
|
{
|
|
"entropy": 5.678823232650757,
|
|
"epoch": 1.8167282629838553,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00046674839664877796,
|
|
"loss": 5.1488,
|
|
"mean_token_accuracy": 0.19508560448884965,
|
|
"num_tokens": 40515310.0,
|
|
"step": 23350
|
|
},
|
|
{
|
|
"entropy": 5.676866865158081,
|
|
"epoch": 1.8171172923555727,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004667338946319801,
|
|
"loss": 5.0091,
|
|
"mean_token_accuracy": 0.20593808293342591,
|
|
"num_tokens": 40523739.0,
|
|
"step": 23355
|
|
},
|
|
{
|
|
"entropy": 5.721298503875732,
|
|
"epoch": 1.8175063217272904,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004667193897059255,
|
|
"loss": 5.1639,
|
|
"mean_token_accuracy": 0.19017911404371263,
|
|
"num_tokens": 40533070.0,
|
|
"step": 23360
|
|
},
|
|
{
|
|
"entropy": 5.731092691421509,
|
|
"epoch": 1.8178953510990081,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00046670488187083436,
|
|
"loss": 5.0058,
|
|
"mean_token_accuracy": 0.20166377425193788,
|
|
"num_tokens": 40541975.0,
|
|
"step": 23365
|
|
},
|
|
{
|
|
"entropy": 5.725260829925537,
|
|
"epoch": 1.8182843804707254,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004666903711269267,
|
|
"loss": 5.141,
|
|
"mean_token_accuracy": 0.19650277644395828,
|
|
"num_tokens": 40550896.0,
|
|
"step": 23370
|
|
},
|
|
{
|
|
"entropy": 5.635598659515381,
|
|
"epoch": 1.818673409842443,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004666758574744228,
|
|
"loss": 5.1201,
|
|
"mean_token_accuracy": 0.19900337010622024,
|
|
"num_tokens": 40559719.0,
|
|
"step": 23375
|
|
},
|
|
{
|
|
"entropy": 5.709807014465332,
|
|
"epoch": 1.8190624392141608,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004666613409135429,
|
|
"loss": 5.1162,
|
|
"mean_token_accuracy": 0.19977762550115585,
|
|
"num_tokens": 40568448.0,
|
|
"step": 23380
|
|
},
|
|
{
|
|
"entropy": 5.785470867156983,
|
|
"epoch": 1.8194514685858783,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004666468214445072,
|
|
"loss": 5.1308,
|
|
"mean_token_accuracy": 0.19481135606765748,
|
|
"num_tokens": 40576443.0,
|
|
"step": 23385
|
|
},
|
|
{
|
|
"entropy": 5.645090579986572,
|
|
"epoch": 1.8198404979575957,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00046663229906753595,
|
|
"loss": 4.9142,
|
|
"mean_token_accuracy": 0.21064617484807968,
|
|
"num_tokens": 40584440.0,
|
|
"step": 23390
|
|
},
|
|
{
|
|
"entropy": 5.655154848098755,
|
|
"epoch": 1.8202295273293134,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00046661777378284965,
|
|
"loss": 5.172,
|
|
"mean_token_accuracy": 0.19538187235593796,
|
|
"num_tokens": 40593696.0,
|
|
"step": 23395
|
|
},
|
|
{
|
|
"entropy": 5.65268874168396,
|
|
"epoch": 1.820618556701031,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004666032455906685,
|
|
"loss": 5.0023,
|
|
"mean_token_accuracy": 0.2076433554291725,
|
|
"num_tokens": 40601368.0,
|
|
"step": 23400
|
|
},
|
|
{
|
|
"entropy": 5.7503540992736815,
|
|
"epoch": 1.8210075860727484,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00046658871449121325,
|
|
"loss": 5.086,
|
|
"mean_token_accuracy": 0.2028270110487938,
|
|
"num_tokens": 40609143.0,
|
|
"step": 23405
|
|
},
|
|
{
|
|
"entropy": 5.696317195892334,
|
|
"epoch": 1.821396615444466,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004665741804847041,
|
|
"loss": 5.0632,
|
|
"mean_token_accuracy": 0.2003426656126976,
|
|
"num_tokens": 40617602.0,
|
|
"step": 23410
|
|
},
|
|
{
|
|
"entropy": 5.612908935546875,
|
|
"epoch": 1.8217856448161838,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00046655964357136164,
|
|
"loss": 4.9612,
|
|
"mean_token_accuracy": 0.20739205926656723,
|
|
"num_tokens": 40626412.0,
|
|
"step": 23415
|
|
},
|
|
{
|
|
"entropy": 5.652625846862793,
|
|
"epoch": 1.822174674187901,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00046654510375140657,
|
|
"loss": 5.0202,
|
|
"mean_token_accuracy": 0.206109456717968,
|
|
"num_tokens": 40635095.0,
|
|
"step": 23420
|
|
},
|
|
{
|
|
"entropy": 5.678670167922974,
|
|
"epoch": 1.8225637035596187,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004665305610250594,
|
|
"loss": 5.0384,
|
|
"mean_token_accuracy": 0.20043517649173737,
|
|
"num_tokens": 40643421.0,
|
|
"step": 23425
|
|
},
|
|
{
|
|
"entropy": 5.647865676879883,
|
|
"epoch": 1.8229527329313364,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004665160153925408,
|
|
"loss": 5.0729,
|
|
"mean_token_accuracy": 0.20355336666107177,
|
|
"num_tokens": 40652180.0,
|
|
"step": 23430
|
|
},
|
|
{
|
|
"entropy": 5.735098266601563,
|
|
"epoch": 1.823341762303054,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00046650146685407154,
|
|
"loss": 5.1481,
|
|
"mean_token_accuracy": 0.18693066388368607,
|
|
"num_tokens": 40660398.0,
|
|
"step": 23435
|
|
},
|
|
{
|
|
"entropy": 5.714107656478882,
|
|
"epoch": 1.8237307916747714,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00046648691540987226,
|
|
"loss": 5.1676,
|
|
"mean_token_accuracy": 0.1879961296916008,
|
|
"num_tokens": 40668827.0,
|
|
"step": 23440
|
|
},
|
|
{
|
|
"entropy": 5.688480520248413,
|
|
"epoch": 1.824119821046489,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00046647236106016387,
|
|
"loss": 5.0699,
|
|
"mean_token_accuracy": 0.1986662283539772,
|
|
"num_tokens": 40676920.0,
|
|
"step": 23445
|
|
},
|
|
{
|
|
"entropy": 5.670010995864868,
|
|
"epoch": 1.8245088504182065,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004664578038051672,
|
|
"loss": 5.0114,
|
|
"mean_token_accuracy": 0.20432327389717103,
|
|
"num_tokens": 40685115.0,
|
|
"step": 23450
|
|
},
|
|
{
|
|
"entropy": 5.676260232925415,
|
|
"epoch": 1.824897879789924,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000466443243645103,
|
|
"loss": 5.039,
|
|
"mean_token_accuracy": 0.1987512916326523,
|
|
"num_tokens": 40693870.0,
|
|
"step": 23455
|
|
},
|
|
{
|
|
"entropy": 5.718591928482056,
|
|
"epoch": 1.8252869091616417,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004664286805801923,
|
|
"loss": 5.022,
|
|
"mean_token_accuracy": 0.194333516061306,
|
|
"num_tokens": 40703031.0,
|
|
"step": 23460
|
|
},
|
|
{
|
|
"entropy": 5.622937917709351,
|
|
"epoch": 1.8256759385333594,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004664141146106562,
|
|
"loss": 4.985,
|
|
"mean_token_accuracy": 0.20394688844680786,
|
|
"num_tokens": 40711690.0,
|
|
"step": 23465
|
|
},
|
|
{
|
|
"entropy": 5.668556261062622,
|
|
"epoch": 1.8260649679050769,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00046639954573671547,
|
|
"loss": 5.0804,
|
|
"mean_token_accuracy": 0.1969800263643265,
|
|
"num_tokens": 40720086.0,
|
|
"step": 23470
|
|
},
|
|
{
|
|
"entropy": 5.764101028442383,
|
|
"epoch": 1.8264539972767944,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00046638497395859127,
|
|
"loss": 5.1254,
|
|
"mean_token_accuracy": 0.1944834589958191,
|
|
"num_tokens": 40728117.0,
|
|
"step": 23475
|
|
},
|
|
{
|
|
"entropy": 5.727489233016968,
|
|
"epoch": 1.826843026648512,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004663703992765047,
|
|
"loss": 5.1156,
|
|
"mean_token_accuracy": 0.1994257539510727,
|
|
"num_tokens": 40736761.0,
|
|
"step": 23480
|
|
},
|
|
{
|
|
"entropy": 5.659313726425171,
|
|
"epoch": 1.8272320560202295,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00046635582169067693,
|
|
"loss": 5.0645,
|
|
"mean_token_accuracy": 0.19522079676389695,
|
|
"num_tokens": 40745291.0,
|
|
"step": 23485
|
|
},
|
|
{
|
|
"entropy": 5.743591356277466,
|
|
"epoch": 1.827621085391947,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00046634124120132915,
|
|
"loss": 5.0786,
|
|
"mean_token_accuracy": 0.20272588282823562,
|
|
"num_tokens": 40754308.0,
|
|
"step": 23490
|
|
},
|
|
{
|
|
"entropy": 5.633688020706177,
|
|
"epoch": 1.8280101147636647,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004663266578086826,
|
|
"loss": 4.9807,
|
|
"mean_token_accuracy": 0.19849610179662705,
|
|
"num_tokens": 40763046.0,
|
|
"step": 23495
|
|
},
|
|
{
|
|
"entropy": 5.5965883255004885,
|
|
"epoch": 1.8283991441353822,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004663120715129585,
|
|
"loss": 5.0297,
|
|
"mean_token_accuracy": 0.19359540343284606,
|
|
"num_tokens": 40770912.0,
|
|
"step": 23500
|
|
},
|
|
{
|
|
"entropy": 5.704968357086182,
|
|
"epoch": 1.8287881735070997,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004662974823143783,
|
|
"loss": 5.1235,
|
|
"mean_token_accuracy": 0.1852446749806404,
|
|
"num_tokens": 40779748.0,
|
|
"step": 23505
|
|
},
|
|
{
|
|
"entropy": 5.742366933822632,
|
|
"epoch": 1.8291772028788174,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004662828902131632,
|
|
"loss": 5.1075,
|
|
"mean_token_accuracy": 0.195328725874424,
|
|
"num_tokens": 40787732.0,
|
|
"step": 23510
|
|
},
|
|
{
|
|
"entropy": 5.6843358993530275,
|
|
"epoch": 1.829566232250535,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004662682952095348,
|
|
"loss": 5.0101,
|
|
"mean_token_accuracy": 0.20013401806354522,
|
|
"num_tokens": 40796521.0,
|
|
"step": 23515
|
|
},
|
|
{
|
|
"entropy": 5.713075876235962,
|
|
"epoch": 1.8299552616222525,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00046625369730371436,
|
|
"loss": 5.1469,
|
|
"mean_token_accuracy": 0.19386830925941467,
|
|
"num_tokens": 40805479.0,
|
|
"step": 23520
|
|
},
|
|
{
|
|
"entropy": 5.654767990112305,
|
|
"epoch": 1.83034429099397,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004662390964959235,
|
|
"loss": 4.9644,
|
|
"mean_token_accuracy": 0.20261916816234588,
|
|
"num_tokens": 40813647.0,
|
|
"step": 23525
|
|
},
|
|
{
|
|
"entropy": 5.60133318901062,
|
|
"epoch": 1.8307333203656877,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00046622449278638375,
|
|
"loss": 4.9544,
|
|
"mean_token_accuracy": 0.20324818044900894,
|
|
"num_tokens": 40821753.0,
|
|
"step": 23530
|
|
},
|
|
{
|
|
"entropy": 5.660799503326416,
|
|
"epoch": 1.8311223497374052,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004662098861753167,
|
|
"loss": 5.1023,
|
|
"mean_token_accuracy": 0.20108500570058824,
|
|
"num_tokens": 40830391.0,
|
|
"step": 23535
|
|
},
|
|
{
|
|
"entropy": 5.656362628936767,
|
|
"epoch": 1.8315113791091227,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00046619527666294394,
|
|
"loss": 5.0444,
|
|
"mean_token_accuracy": 0.20144785940647125,
|
|
"num_tokens": 40839372.0,
|
|
"step": 23540
|
|
},
|
|
{
|
|
"entropy": 5.70982518196106,
|
|
"epoch": 1.8319004084808403,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004661806642494872,
|
|
"loss": 5.1384,
|
|
"mean_token_accuracy": 0.1974942773580551,
|
|
"num_tokens": 40847945.0,
|
|
"step": 23545
|
|
},
|
|
{
|
|
"entropy": 5.786671686172485,
|
|
"epoch": 1.8322894378525578,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004661660489351681,
|
|
"loss": 5.1726,
|
|
"mean_token_accuracy": 0.19213981181383133,
|
|
"num_tokens": 40857600.0,
|
|
"step": 23550
|
|
},
|
|
{
|
|
"entropy": 5.670353746414184,
|
|
"epoch": 1.8326784672242753,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004661514307202086,
|
|
"loss": 5.0074,
|
|
"mean_token_accuracy": 0.2023478180170059,
|
|
"num_tokens": 40866672.0,
|
|
"step": 23555
|
|
},
|
|
{
|
|
"entropy": 5.6903105735778805,
|
|
"epoch": 1.833067496595993,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00046613680960483036,
|
|
"loss": 5.0503,
|
|
"mean_token_accuracy": 0.1918072909116745,
|
|
"num_tokens": 40875240.0,
|
|
"step": 23560
|
|
},
|
|
{
|
|
"entropy": 5.62783727645874,
|
|
"epoch": 1.8334565259677107,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004661221855892552,
|
|
"loss": 5.0031,
|
|
"mean_token_accuracy": 0.19587404429912567,
|
|
"num_tokens": 40883731.0,
|
|
"step": 23565
|
|
},
|
|
{
|
|
"entropy": 5.625275087356568,
|
|
"epoch": 1.8338455553394282,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00046610755867370506,
|
|
"loss": 4.9792,
|
|
"mean_token_accuracy": 0.202235047519207,
|
|
"num_tokens": 40892572.0,
|
|
"step": 23570
|
|
},
|
|
{
|
|
"entropy": 5.6437853336334225,
|
|
"epoch": 1.8342345847111456,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000466092928858402,
|
|
"loss": 5.0611,
|
|
"mean_token_accuracy": 0.20040431171655654,
|
|
"num_tokens": 40901603.0,
|
|
"step": 23575
|
|
},
|
|
{
|
|
"entropy": 5.6633320331573485,
|
|
"epoch": 1.8346236140828633,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00046607829614356787,
|
|
"loss": 5.0458,
|
|
"mean_token_accuracy": 0.20046085715293885,
|
|
"num_tokens": 40910502.0,
|
|
"step": 23580
|
|
},
|
|
{
|
|
"entropy": 5.680140495300293,
|
|
"epoch": 1.8350126434545808,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004660636605294247,
|
|
"loss": 5.0009,
|
|
"mean_token_accuracy": 0.2056643158197403,
|
|
"num_tokens": 40919858.0,
|
|
"step": 23585
|
|
},
|
|
{
|
|
"entropy": 5.726168966293335,
|
|
"epoch": 1.8354016728262983,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004660490220161946,
|
|
"loss": 5.0369,
|
|
"mean_token_accuracy": 0.201455157995224,
|
|
"num_tokens": 40928795.0,
|
|
"step": 23590
|
|
},
|
|
{
|
|
"entropy": 5.6757513046264645,
|
|
"epoch": 1.835790702198016,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00046603438060409966,
|
|
"loss": 5.0282,
|
|
"mean_token_accuracy": 0.20020510405302047,
|
|
"num_tokens": 40937240.0,
|
|
"step": 23595
|
|
},
|
|
{
|
|
"entropy": 5.668379831314087,
|
|
"epoch": 1.8361797315697335,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000466019736293362,
|
|
"loss": 5.0757,
|
|
"mean_token_accuracy": 0.1974781259894371,
|
|
"num_tokens": 40945974.0,
|
|
"step": 23600
|
|
},
|
|
{
|
|
"entropy": 5.644535923004151,
|
|
"epoch": 1.836568760941451,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00046600508908420396,
|
|
"loss": 4.9809,
|
|
"mean_token_accuracy": 0.21096906661987305,
|
|
"num_tokens": 40953553.0,
|
|
"step": 23605
|
|
},
|
|
{
|
|
"entropy": 5.6556085586547855,
|
|
"epoch": 1.8369577903131686,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00046599043897684766,
|
|
"loss": 5.0216,
|
|
"mean_token_accuracy": 0.20918246656656264,
|
|
"num_tokens": 40961287.0,
|
|
"step": 23610
|
|
},
|
|
{
|
|
"entropy": 5.617972469329834,
|
|
"epoch": 1.8373468196848863,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004659757859715155,
|
|
"loss": 4.9763,
|
|
"mean_token_accuracy": 0.20169522911310195,
|
|
"num_tokens": 40970266.0,
|
|
"step": 23615
|
|
},
|
|
{
|
|
"entropy": 5.691685390472412,
|
|
"epoch": 1.8377358490566038,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00046596113006842975,
|
|
"loss": 5.0141,
|
|
"mean_token_accuracy": 0.20533781200647355,
|
|
"num_tokens": 40978303.0,
|
|
"step": 23620
|
|
},
|
|
{
|
|
"entropy": 5.759164428710937,
|
|
"epoch": 1.8381248784283213,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004659464712678128,
|
|
"loss": 5.0657,
|
|
"mean_token_accuracy": 0.1988115653395653,
|
|
"num_tokens": 40986360.0,
|
|
"step": 23625
|
|
},
|
|
{
|
|
"entropy": 5.641524171829223,
|
|
"epoch": 1.838513907800039,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004659318095698871,
|
|
"loss": 5.1188,
|
|
"mean_token_accuracy": 0.19440290480852127,
|
|
"num_tokens": 40995323.0,
|
|
"step": 23630
|
|
},
|
|
{
|
|
"entropy": 5.668115949630737,
|
|
"epoch": 1.8389029371717565,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000465917144974875,
|
|
"loss": 5.0173,
|
|
"mean_token_accuracy": 0.20526110827922822,
|
|
"num_tokens": 41004032.0,
|
|
"step": 23635
|
|
},
|
|
{
|
|
"entropy": 5.694147968292237,
|
|
"epoch": 1.839291966543474,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004659024774829992,
|
|
"loss": 5.049,
|
|
"mean_token_accuracy": 0.19918417781591416,
|
|
"num_tokens": 41011992.0,
|
|
"step": 23640
|
|
},
|
|
{
|
|
"entropy": 5.699076128005982,
|
|
"epoch": 1.8396809959151916,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000465887807094482,
|
|
"loss": 5.0863,
|
|
"mean_token_accuracy": 0.1953320950269699,
|
|
"num_tokens": 41020252.0,
|
|
"step": 23645
|
|
},
|
|
{
|
|
"entropy": 5.683829641342163,
|
|
"epoch": 1.8400700252869093,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00046587313380954635,
|
|
"loss": 4.9953,
|
|
"mean_token_accuracy": 0.19899878799915313,
|
|
"num_tokens": 41028858.0,
|
|
"step": 23650
|
|
},
|
|
{
|
|
"entropy": 5.691145896911621,
|
|
"epoch": 1.8404590546586266,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00046585845762841453,
|
|
"loss": 4.973,
|
|
"mean_token_accuracy": 0.20388407856225968,
|
|
"num_tokens": 41037539.0,
|
|
"step": 23655
|
|
},
|
|
{
|
|
"entropy": 5.663805770874023,
|
|
"epoch": 1.8408480840303443,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004658437785513095,
|
|
"loss": 5.081,
|
|
"mean_token_accuracy": 0.19854643791913987,
|
|
"num_tokens": 41045809.0,
|
|
"step": 23660
|
|
},
|
|
{
|
|
"entropy": 5.607454776763916,
|
|
"epoch": 1.841237113402062,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004658290965784539,
|
|
"loss": 4.9958,
|
|
"mean_token_accuracy": 0.2029963865876198,
|
|
"num_tokens": 41054675.0,
|
|
"step": 23665
|
|
},
|
|
{
|
|
"entropy": 5.711282205581665,
|
|
"epoch": 1.8416261427737795,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004658144117100704,
|
|
"loss": 5.1612,
|
|
"mean_token_accuracy": 0.19147171080112457,
|
|
"num_tokens": 41063493.0,
|
|
"step": 23670
|
|
},
|
|
{
|
|
"entropy": 5.699791812896729,
|
|
"epoch": 1.842015172145497,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00046579972394638204,
|
|
"loss": 5.0894,
|
|
"mean_token_accuracy": 0.1946207493543625,
|
|
"num_tokens": 41072985.0,
|
|
"step": 23675
|
|
},
|
|
{
|
|
"entropy": 5.691910934448242,
|
|
"epoch": 1.8424042015172146,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00046578503328761146,
|
|
"loss": 5.0647,
|
|
"mean_token_accuracy": 0.20021508634090424,
|
|
"num_tokens": 41080926.0,
|
|
"step": 23680
|
|
},
|
|
{
|
|
"entropy": 5.601751804351807,
|
|
"epoch": 1.842793230888932,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00046577033973398173,
|
|
"loss": 5.0031,
|
|
"mean_token_accuracy": 0.20392018258571626,
|
|
"num_tokens": 41090251.0,
|
|
"step": 23685
|
|
},
|
|
{
|
|
"entropy": 5.62412109375,
|
|
"epoch": 1.8431822602606496,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004657556432857157,
|
|
"loss": 4.9653,
|
|
"mean_token_accuracy": 0.20614240914583207,
|
|
"num_tokens": 41098681.0,
|
|
"step": 23690
|
|
},
|
|
{
|
|
"entropy": 5.670771551132202,
|
|
"epoch": 1.8435712896323673,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004657409439430364,
|
|
"loss": 5.0977,
|
|
"mean_token_accuracy": 0.2012905165553093,
|
|
"num_tokens": 41107399.0,
|
|
"step": 23695
|
|
},
|
|
{
|
|
"entropy": 5.712767457962036,
|
|
"epoch": 1.843960319004085,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004657262417061669,
|
|
"loss": 5.048,
|
|
"mean_token_accuracy": 0.19650247246026992,
|
|
"num_tokens": 41116476.0,
|
|
"step": 23700
|
|
},
|
|
{
|
|
"entropy": 5.627057886123657,
|
|
"epoch": 1.8443493483758022,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004657115365753302,
|
|
"loss": 4.9791,
|
|
"mean_token_accuracy": 0.19985273480415344,
|
|
"num_tokens": 41125191.0,
|
|
"step": 23705
|
|
},
|
|
{
|
|
"entropy": 5.624863481521606,
|
|
"epoch": 1.84473837774752,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00046569682855074953,
|
|
"loss": 4.9925,
|
|
"mean_token_accuracy": 0.2109066978096962,
|
|
"num_tokens": 41133811.0,
|
|
"step": 23710
|
|
},
|
|
{
|
|
"entropy": 5.6927660465240475,
|
|
"epoch": 1.8451274071192376,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00046568211763264796,
|
|
"loss": 5.1323,
|
|
"mean_token_accuracy": 0.19276395440101624,
|
|
"num_tokens": 41143093.0,
|
|
"step": 23715
|
|
},
|
|
{
|
|
"entropy": 5.762273597717285,
|
|
"epoch": 1.845516436490955,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004656674038212488,
|
|
"loss": 5.1412,
|
|
"mean_token_accuracy": 0.19303966015577317,
|
|
"num_tokens": 41152106.0,
|
|
"step": 23720
|
|
},
|
|
{
|
|
"entropy": 5.684381103515625,
|
|
"epoch": 1.8459054658626726,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00046565268711677525,
|
|
"loss": 5.0205,
|
|
"mean_token_accuracy": 0.19906811267137528,
|
|
"num_tokens": 41161100.0,
|
|
"step": 23725
|
|
},
|
|
{
|
|
"entropy": 5.6614970684051515,
|
|
"epoch": 1.8462944952343903,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00046563796751945065,
|
|
"loss": 5.057,
|
|
"mean_token_accuracy": 0.19930259585380555,
|
|
"num_tokens": 41170339.0,
|
|
"step": 23730
|
|
},
|
|
{
|
|
"entropy": 5.714292240142822,
|
|
"epoch": 1.8466835246061077,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00046562324502949834,
|
|
"loss": 5.0549,
|
|
"mean_token_accuracy": 0.19824913889169693,
|
|
"num_tokens": 41178821.0,
|
|
"step": 23735
|
|
},
|
|
{
|
|
"entropy": 5.719708728790283,
|
|
"epoch": 1.8470725539778252,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004656085196471416,
|
|
"loss": 5.0648,
|
|
"mean_token_accuracy": 0.19827462434768678,
|
|
"num_tokens": 41187578.0,
|
|
"step": 23740
|
|
},
|
|
{
|
|
"entropy": 5.545157957077026,
|
|
"epoch": 1.847461583349543,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00046559379137260404,
|
|
"loss": 4.9357,
|
|
"mean_token_accuracy": 0.20713798701763153,
|
|
"num_tokens": 41196799.0,
|
|
"step": 23745
|
|
},
|
|
{
|
|
"entropy": 5.650405645370483,
|
|
"epoch": 1.8478506127212606,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000465579060206109,
|
|
"loss": 5.1154,
|
|
"mean_token_accuracy": 0.19511368423700332,
|
|
"num_tokens": 41206300.0,
|
|
"step": 23750
|
|
},
|
|
{
|
|
"entropy": 5.766040182113647,
|
|
"epoch": 1.8482396420929779,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00046556432614788015,
|
|
"loss": 5.1069,
|
|
"mean_token_accuracy": 0.19853024184703827,
|
|
"num_tokens": 41214377.0,
|
|
"step": 23755
|
|
},
|
|
{
|
|
"entropy": 5.676653671264648,
|
|
"epoch": 1.8486286714646956,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004655495891981409,
|
|
"loss": 5.0063,
|
|
"mean_token_accuracy": 0.19895326644182204,
|
|
"num_tokens": 41223303.0,
|
|
"step": 23760
|
|
},
|
|
{
|
|
"entropy": 5.687079858779907,
|
|
"epoch": 1.8490177008364133,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000465534849357115,
|
|
"loss": 5.1443,
|
|
"mean_token_accuracy": 0.19204787611961366,
|
|
"num_tokens": 41232323.0,
|
|
"step": 23765
|
|
},
|
|
{
|
|
"entropy": 5.726064872741699,
|
|
"epoch": 1.8494067302081307,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00046552010662502595,
|
|
"loss": 5.1038,
|
|
"mean_token_accuracy": 0.1950084537267685,
|
|
"num_tokens": 41241605.0,
|
|
"step": 23770
|
|
},
|
|
{
|
|
"entropy": 5.756454133987427,
|
|
"epoch": 1.8497957595798482,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004655053610020976,
|
|
"loss": 5.174,
|
|
"mean_token_accuracy": 0.18778659105300904,
|
|
"num_tokens": 41250604.0,
|
|
"step": 23775
|
|
},
|
|
{
|
|
"entropy": 5.65646448135376,
|
|
"epoch": 1.850184788951566,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004654906124885535,
|
|
"loss": 4.9695,
|
|
"mean_token_accuracy": 0.20573434829711915,
|
|
"num_tokens": 41258640.0,
|
|
"step": 23780
|
|
},
|
|
{
|
|
"entropy": 5.657597780227661,
|
|
"epoch": 1.8505738183232834,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004654758610846176,
|
|
"loss": 5.1129,
|
|
"mean_token_accuracy": 0.20204756408929825,
|
|
"num_tokens": 41268104.0,
|
|
"step": 23785
|
|
},
|
|
{
|
|
"entropy": 5.690503025054932,
|
|
"epoch": 1.8509628476950009,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004654611067905137,
|
|
"loss": 5.1337,
|
|
"mean_token_accuracy": 0.1977001339197159,
|
|
"num_tokens": 41276276.0,
|
|
"step": 23790
|
|
},
|
|
{
|
|
"entropy": 5.688591146469117,
|
|
"epoch": 1.8513518770667186,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00046544634960646563,
|
|
"loss": 4.9828,
|
|
"mean_token_accuracy": 0.2058488130569458,
|
|
"num_tokens": 41284464.0,
|
|
"step": 23795
|
|
},
|
|
{
|
|
"entropy": 5.679538917541504,
|
|
"epoch": 1.8517409064384363,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004654315895326974,
|
|
"loss": 4.9948,
|
|
"mean_token_accuracy": 0.1992371916770935,
|
|
"num_tokens": 41293108.0,
|
|
"step": 23800
|
|
},
|
|
{
|
|
"entropy": 5.658460426330566,
|
|
"epoch": 1.8521299358101535,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004654168265694328,
|
|
"loss": 5.0377,
|
|
"mean_token_accuracy": 0.19509689807891845,
|
|
"num_tokens": 41301830.0,
|
|
"step": 23805
|
|
},
|
|
{
|
|
"entropy": 5.7098856449127195,
|
|
"epoch": 1.8525189651818712,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000465402060716896,
|
|
"loss": 5.0706,
|
|
"mean_token_accuracy": 0.19837660789489747,
|
|
"num_tokens": 41310487.0,
|
|
"step": 23810
|
|
},
|
|
{
|
|
"entropy": 5.735160303115845,
|
|
"epoch": 1.852907994553589,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000465387291975311,
|
|
"loss": 5.1457,
|
|
"mean_token_accuracy": 0.19527142941951753,
|
|
"num_tokens": 41319730.0,
|
|
"step": 23815
|
|
},
|
|
{
|
|
"entropy": 5.6724484920501705,
|
|
"epoch": 1.8532970239253064,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00046537252034490185,
|
|
"loss": 5.0451,
|
|
"mean_token_accuracy": 0.20284042954444886,
|
|
"num_tokens": 41328914.0,
|
|
"step": 23820
|
|
},
|
|
{
|
|
"entropy": 5.647346448898316,
|
|
"epoch": 1.8536860532970239,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00046535774582589275,
|
|
"loss": 5.0819,
|
|
"mean_token_accuracy": 0.19659153819084169,
|
|
"num_tokens": 41337060.0,
|
|
"step": 23825
|
|
},
|
|
{
|
|
"entropy": 5.684302282333374,
|
|
"epoch": 1.8540750826687415,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00046534296841850776,
|
|
"loss": 5.0051,
|
|
"mean_token_accuracy": 0.20757822394371034,
|
|
"num_tokens": 41344966.0,
|
|
"step": 23830
|
|
},
|
|
{
|
|
"entropy": 5.608697366714478,
|
|
"epoch": 1.854464112040459,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00046532818812297124,
|
|
"loss": 4.926,
|
|
"mean_token_accuracy": 0.20916413962841035,
|
|
"num_tokens": 41353678.0,
|
|
"step": 23835
|
|
},
|
|
{
|
|
"entropy": 5.745792627334595,
|
|
"epoch": 1.8548531414121765,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004653134049395074,
|
|
"loss": 5.1785,
|
|
"mean_token_accuracy": 0.20162003636360168,
|
|
"num_tokens": 41362782.0,
|
|
"step": 23840
|
|
},
|
|
{
|
|
"entropy": 5.646778774261475,
|
|
"epoch": 1.8552421707838942,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004652986188683406,
|
|
"loss": 5.0171,
|
|
"mean_token_accuracy": 0.20401924699544907,
|
|
"num_tokens": 41370668.0,
|
|
"step": 23845
|
|
},
|
|
{
|
|
"entropy": 5.611280870437622,
|
|
"epoch": 1.855631200155612,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00046528382990969504,
|
|
"loss": 4.9994,
|
|
"mean_token_accuracy": 0.2035282790660858,
|
|
"num_tokens": 41378945.0,
|
|
"step": 23850
|
|
},
|
|
{
|
|
"entropy": 5.7154212474823,
|
|
"epoch": 1.8560202295273294,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004652690380637953,
|
|
"loss": 5.0693,
|
|
"mean_token_accuracy": 0.1947337046265602,
|
|
"num_tokens": 41387579.0,
|
|
"step": 23855
|
|
},
|
|
{
|
|
"entropy": 5.696177768707275,
|
|
"epoch": 1.8564092588990468,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004652542433308657,
|
|
"loss": 5.0718,
|
|
"mean_token_accuracy": 0.2017604887485504,
|
|
"num_tokens": 41396472.0,
|
|
"step": 23860
|
|
},
|
|
{
|
|
"entropy": 5.7154511451721195,
|
|
"epoch": 1.8567982882707645,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004652394457111309,
|
|
"loss": 5.1161,
|
|
"mean_token_accuracy": 0.19253923296928405,
|
|
"num_tokens": 41404599.0,
|
|
"step": 23865
|
|
},
|
|
{
|
|
"entropy": 5.739647674560547,
|
|
"epoch": 1.857187317642482,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00046522464520481517,
|
|
"loss": 5.1399,
|
|
"mean_token_accuracy": 0.18762982040643691,
|
|
"num_tokens": 41412799.0,
|
|
"step": 23870
|
|
},
|
|
{
|
|
"entropy": 5.64436707496643,
|
|
"epoch": 1.8575763470141995,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00046520984181214333,
|
|
"loss": 4.9524,
|
|
"mean_token_accuracy": 0.20920240730047227,
|
|
"num_tokens": 41421193.0,
|
|
"step": 23875
|
|
},
|
|
{
|
|
"entropy": 5.665311288833618,
|
|
"epoch": 1.8579653763859172,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004651950355333398,
|
|
"loss": 5.0175,
|
|
"mean_token_accuracy": 0.19525519758462906,
|
|
"num_tokens": 41430201.0,
|
|
"step": 23880
|
|
},
|
|
{
|
|
"entropy": 5.605517768859864,
|
|
"epoch": 1.8583544057576347,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004651802263686294,
|
|
"loss": 4.9876,
|
|
"mean_token_accuracy": 0.19989306330680848,
|
|
"num_tokens": 41439122.0,
|
|
"step": 23885
|
|
},
|
|
{
|
|
"entropy": 5.671520757675171,
|
|
"epoch": 1.8587434351293521,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004651654143182367,
|
|
"loss": 5.05,
|
|
"mean_token_accuracy": 0.19741638153791427,
|
|
"num_tokens": 41448553.0,
|
|
"step": 23890
|
|
},
|
|
{
|
|
"entropy": 5.651991558074951,
|
|
"epoch": 1.8591324645010698,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004651505993823866,
|
|
"loss": 5.0183,
|
|
"mean_token_accuracy": 0.2022734746336937,
|
|
"num_tokens": 41457098.0,
|
|
"step": 23895
|
|
},
|
|
{
|
|
"entropy": 5.669555187225342,
|
|
"epoch": 1.8595214938727875,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00046513578156130383,
|
|
"loss": 5.075,
|
|
"mean_token_accuracy": 0.19775795042514802,
|
|
"num_tokens": 41465714.0,
|
|
"step": 23900
|
|
},
|
|
{
|
|
"entropy": 5.747840929031372,
|
|
"epoch": 1.859910523244505,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004651209608552131,
|
|
"loss": 5.0953,
|
|
"mean_token_accuracy": 0.1980939269065857,
|
|
"num_tokens": 41474418.0,
|
|
"step": 23905
|
|
},
|
|
{
|
|
"entropy": 5.645845603942871,
|
|
"epoch": 1.8602995526162225,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00046510613726433945,
|
|
"loss": 4.9773,
|
|
"mean_token_accuracy": 0.2044762283563614,
|
|
"num_tokens": 41482430.0,
|
|
"step": 23910
|
|
},
|
|
{
|
|
"entropy": 5.711126470565796,
|
|
"epoch": 1.8606885819879402,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004650913107889078,
|
|
"loss": 5.1362,
|
|
"mean_token_accuracy": 0.19826145470142365,
|
|
"num_tokens": 41490759.0,
|
|
"step": 23915
|
|
},
|
|
{
|
|
"entropy": 5.594354343414307,
|
|
"epoch": 1.8610776113596577,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000465076481429143,
|
|
"loss": 4.9887,
|
|
"mean_token_accuracy": 0.20265743881464005,
|
|
"num_tokens": 41499660.0,
|
|
"step": 23920
|
|
},
|
|
{
|
|
"entropy": 5.68090500831604,
|
|
"epoch": 1.8614666407313751,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004650616491852701,
|
|
"loss": 5.0168,
|
|
"mean_token_accuracy": 0.20643742382526398,
|
|
"num_tokens": 41507515.0,
|
|
"step": 23925
|
|
},
|
|
{
|
|
"entropy": 5.722912311553955,
|
|
"epoch": 1.8618556701030928,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00046504681405751426,
|
|
"loss": 5.08,
|
|
"mean_token_accuracy": 0.19374623000621796,
|
|
"num_tokens": 41515859.0,
|
|
"step": 23930
|
|
},
|
|
{
|
|
"entropy": 5.685977268218994,
|
|
"epoch": 1.8622446994748103,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00046503197604610047,
|
|
"loss": 5.1096,
|
|
"mean_token_accuracy": 0.20370736271142958,
|
|
"num_tokens": 41524776.0,
|
|
"step": 23935
|
|
},
|
|
{
|
|
"entropy": 5.701795148849487,
|
|
"epoch": 1.8626337288465278,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00046501713515125393,
|
|
"loss": 5.0243,
|
|
"mean_token_accuracy": 0.20092787891626357,
|
|
"num_tokens": 41532854.0,
|
|
"step": 23940
|
|
},
|
|
{
|
|
"entropy": 5.72903528213501,
|
|
"epoch": 1.8630227582182455,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004650022913731998,
|
|
"loss": 5.0099,
|
|
"mean_token_accuracy": 0.21019555926322936,
|
|
"num_tokens": 41542038.0,
|
|
"step": 23945
|
|
},
|
|
{
|
|
"entropy": 5.686867141723633,
|
|
"epoch": 1.8634117875899632,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00046498744471216335,
|
|
"loss": 5.022,
|
|
"mean_token_accuracy": 0.20487914979457855,
|
|
"num_tokens": 41550428.0,
|
|
"step": 23950
|
|
},
|
|
{
|
|
"entropy": 5.635628890991211,
|
|
"epoch": 1.8638008169616807,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00046497259516836974,
|
|
"loss": 4.9958,
|
|
"mean_token_accuracy": 0.20121567100286483,
|
|
"num_tokens": 41559289.0,
|
|
"step": 23955
|
|
},
|
|
{
|
|
"entropy": 5.691625165939331,
|
|
"epoch": 1.8641898463333981,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00046495774274204446,
|
|
"loss": 5.0109,
|
|
"mean_token_accuracy": 0.20548161417245864,
|
|
"num_tokens": 41567901.0,
|
|
"step": 23960
|
|
},
|
|
{
|
|
"entropy": 5.760720205307007,
|
|
"epoch": 1.8645788757051158,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004649428874334127,
|
|
"loss": 5.1296,
|
|
"mean_token_accuracy": 0.1914092168211937,
|
|
"num_tokens": 41577589.0,
|
|
"step": 23965
|
|
},
|
|
{
|
|
"entropy": 5.736770391464233,
|
|
"epoch": 1.8649679050768333,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004649280292427,
|
|
"loss": 5.1248,
|
|
"mean_token_accuracy": 0.19287013858556748,
|
|
"num_tokens": 41586319.0,
|
|
"step": 23970
|
|
},
|
|
{
|
|
"entropy": 5.736889457702636,
|
|
"epoch": 1.8653569344485508,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004649131681701318,
|
|
"loss": 5.1106,
|
|
"mean_token_accuracy": 0.19541349709033967,
|
|
"num_tokens": 41594316.0,
|
|
"step": 23975
|
|
},
|
|
{
|
|
"entropy": 5.660229873657227,
|
|
"epoch": 1.8657459638202685,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00046489830421593347,
|
|
"loss": 5.0369,
|
|
"mean_token_accuracy": 0.19791144132614136,
|
|
"num_tokens": 41603221.0,
|
|
"step": 23980
|
|
},
|
|
{
|
|
"entropy": 5.64997034072876,
|
|
"epoch": 1.866134993191986,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004648834373803307,
|
|
"loss": 5.0503,
|
|
"mean_token_accuracy": 0.19683537185192107,
|
|
"num_tokens": 41612082.0,
|
|
"step": 23985
|
|
},
|
|
{
|
|
"entropy": 5.710425853729248,
|
|
"epoch": 1.8665240225637034,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00046486856766354893,
|
|
"loss": 5.0065,
|
|
"mean_token_accuracy": 0.2030527263879776,
|
|
"num_tokens": 41619762.0,
|
|
"step": 23990
|
|
},
|
|
{
|
|
"entropy": 5.636745882034302,
|
|
"epoch": 1.8669130519354211,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00046485369506581387,
|
|
"loss": 5.0095,
|
|
"mean_token_accuracy": 0.19832469820976256,
|
|
"num_tokens": 41627968.0,
|
|
"step": 23995
|
|
},
|
|
{
|
|
"entropy": 5.69230694770813,
|
|
"epoch": 1.8673020813071388,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00046483881958735124,
|
|
"loss": 5.0917,
|
|
"mean_token_accuracy": 0.19699103087186814,
|
|
"num_tokens": 41636841.0,
|
|
"step": 24000
|
|
},
|
|
{
|
|
"epoch": 1.8673020813071388,
|
|
"eval_entropy": 5.483582375758651,
|
|
"eval_loss": 5.10653018951416,
|
|
"eval_mean_token_accuracy": 0.20658851980273832,
|
|
"eval_num_tokens": 41636841.0,
|
|
"eval_runtime": 21.8321,
|
|
"eval_samples_per_second": 1903.529,
|
|
"eval_steps_per_second": 237.953,
|
|
"step": 24000
|
|
},
|
|
{
|
|
"entropy": 5.741102457046509,
|
|
"epoch": 1.8676911106788563,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00046482394122838663,
|
|
"loss": 5.0506,
|
|
"mean_token_accuracy": 0.2047205686569214,
|
|
"num_tokens": 41645352.0,
|
|
"step": 24005
|
|
},
|
|
{
|
|
"entropy": 5.660536670684815,
|
|
"epoch": 1.8680801400505738,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00046480905998914587,
|
|
"loss": 4.9577,
|
|
"mean_token_accuracy": 0.20603823363780976,
|
|
"num_tokens": 41654296.0,
|
|
"step": 24010
|
|
},
|
|
{
|
|
"entropy": 5.590140914916992,
|
|
"epoch": 1.8684691694222915,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004647941758698547,
|
|
"loss": 5.0156,
|
|
"mean_token_accuracy": 0.1979769691824913,
|
|
"num_tokens": 41662008.0,
|
|
"step": 24015
|
|
},
|
|
{
|
|
"entropy": 5.7127727508544925,
|
|
"epoch": 1.868858198794009,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000464779288870739,
|
|
"loss": 5.1653,
|
|
"mean_token_accuracy": 0.1959889277815819,
|
|
"num_tokens": 41671765.0,
|
|
"step": 24020
|
|
},
|
|
{
|
|
"entropy": 5.760813999176025,
|
|
"epoch": 1.8692472281657264,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00046476439899202464,
|
|
"loss": 5.1483,
|
|
"mean_token_accuracy": 0.1913057327270508,
|
|
"num_tokens": 41681035.0,
|
|
"step": 24025
|
|
},
|
|
{
|
|
"entropy": 5.700266933441162,
|
|
"epoch": 1.8696362575374441,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00046474950623393756,
|
|
"loss": 5.0134,
|
|
"mean_token_accuracy": 0.20269862115383147,
|
|
"num_tokens": 41689974.0,
|
|
"step": 24030
|
|
},
|
|
{
|
|
"entropy": 5.692906045913697,
|
|
"epoch": 1.8700252869091616,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004647346105967038,
|
|
"loss": 5.0764,
|
|
"mean_token_accuracy": 0.19065997898578643,
|
|
"num_tokens": 41698560.0,
|
|
"step": 24035
|
|
},
|
|
{
|
|
"entropy": 5.697722101211548,
|
|
"epoch": 1.870414316280879,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004647197120805493,
|
|
"loss": 5.0303,
|
|
"mean_token_accuracy": 0.20352455228567123,
|
|
"num_tokens": 41706741.0,
|
|
"step": 24040
|
|
},
|
|
{
|
|
"entropy": 5.6599808692932125,
|
|
"epoch": 1.8708033456525968,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00046470481068570013,
|
|
"loss": 5.0118,
|
|
"mean_token_accuracy": 0.19611548781394958,
|
|
"num_tokens": 41715685.0,
|
|
"step": 24045
|
|
},
|
|
{
|
|
"entropy": 5.648841094970703,
|
|
"epoch": 1.8711923750243145,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004646899064123824,
|
|
"loss": 5.0843,
|
|
"mean_token_accuracy": 0.2012360453605652,
|
|
"num_tokens": 41724123.0,
|
|
"step": 24050
|
|
},
|
|
{
|
|
"entropy": 5.7200220108032225,
|
|
"epoch": 1.871581404396032,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004646749992608223,
|
|
"loss": 5.0574,
|
|
"mean_token_accuracy": 0.20124853700399398,
|
|
"num_tokens": 41732604.0,
|
|
"step": 24055
|
|
},
|
|
{
|
|
"entropy": 5.630925798416138,
|
|
"epoch": 1.8719704337677494,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004646600892312459,
|
|
"loss": 5.016,
|
|
"mean_token_accuracy": 0.2035152032971382,
|
|
"num_tokens": 41740444.0,
|
|
"step": 24060
|
|
},
|
|
{
|
|
"entropy": 5.654859256744385,
|
|
"epoch": 1.872359463139467,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004646451763238796,
|
|
"loss": 5.0105,
|
|
"mean_token_accuracy": 0.19737775027751922,
|
|
"num_tokens": 41748800.0,
|
|
"step": 24065
|
|
},
|
|
{
|
|
"entropy": 5.648532152175903,
|
|
"epoch": 1.8727484925111846,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004646302605389496,
|
|
"loss": 5.0589,
|
|
"mean_token_accuracy": 0.19410253912210465,
|
|
"num_tokens": 41757402.0,
|
|
"step": 24070
|
|
},
|
|
{
|
|
"entropy": 5.699870777130127,
|
|
"epoch": 1.873137521882902,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004646153418766822,
|
|
"loss": 5.0262,
|
|
"mean_token_accuracy": 0.20737480372190475,
|
|
"num_tokens": 41766604.0,
|
|
"step": 24075
|
|
},
|
|
{
|
|
"entropy": 5.756013679504394,
|
|
"epoch": 1.8735265512546198,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00046460042033730377,
|
|
"loss": 5.2053,
|
|
"mean_token_accuracy": 0.19025604277849198,
|
|
"num_tokens": 41775450.0,
|
|
"step": 24080
|
|
},
|
|
{
|
|
"entropy": 5.7421306610107425,
|
|
"epoch": 1.8739155806263375,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004645854959210408,
|
|
"loss": 5.1726,
|
|
"mean_token_accuracy": 0.19606088250875472,
|
|
"num_tokens": 41784355.0,
|
|
"step": 24085
|
|
},
|
|
{
|
|
"entropy": 5.655627822875976,
|
|
"epoch": 1.8743046099980547,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00046457056862811956,
|
|
"loss": 4.999,
|
|
"mean_token_accuracy": 0.19285477101802825,
|
|
"num_tokens": 41793441.0,
|
|
"step": 24090
|
|
},
|
|
{
|
|
"entropy": 5.672564315795898,
|
|
"epoch": 1.8746936393697724,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004645556384587668,
|
|
"loss": 4.9977,
|
|
"mean_token_accuracy": 0.19842258393764495,
|
|
"num_tokens": 41802407.0,
|
|
"step": 24095
|
|
},
|
|
{
|
|
"entropy": 5.700974321365356,
|
|
"epoch": 1.87508266874149,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004645407054132089,
|
|
"loss": 5.0544,
|
|
"mean_token_accuracy": 0.1979052484035492,
|
|
"num_tokens": 41810362.0,
|
|
"step": 24100
|
|
},
|
|
{
|
|
"entropy": 5.676897716522217,
|
|
"epoch": 1.8754716981132076,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004645257694916725,
|
|
"loss": 5.1575,
|
|
"mean_token_accuracy": 0.19177428483963013,
|
|
"num_tokens": 41819332.0,
|
|
"step": 24105
|
|
},
|
|
{
|
|
"entropy": 5.698676872253418,
|
|
"epoch": 1.875860727484925,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004645108306943842,
|
|
"loss": 5.0183,
|
|
"mean_token_accuracy": 0.20641182065010072,
|
|
"num_tokens": 41828048.0,
|
|
"step": 24110
|
|
},
|
|
{
|
|
"entropy": 5.636488342285157,
|
|
"epoch": 1.8762497568566427,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004644958890215707,
|
|
"loss": 4.9914,
|
|
"mean_token_accuracy": 0.20486603081226348,
|
|
"num_tokens": 41836583.0,
|
|
"step": 24115
|
|
},
|
|
{
|
|
"entropy": 5.660585546493531,
|
|
"epoch": 1.8766387862283602,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004644809444734586,
|
|
"loss": 5.0557,
|
|
"mean_token_accuracy": 0.19707500636577607,
|
|
"num_tokens": 41845454.0,
|
|
"step": 24120
|
|
},
|
|
{
|
|
"entropy": 5.700658845901489,
|
|
"epoch": 1.8770278156000777,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00046446599705027487,
|
|
"loss": 5.0334,
|
|
"mean_token_accuracy": 0.19468516558408738,
|
|
"num_tokens": 41854481.0,
|
|
"step": 24125
|
|
},
|
|
{
|
|
"entropy": 5.730928039550781,
|
|
"epoch": 1.8774168449717954,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00046445104675224607,
|
|
"loss": 5.0904,
|
|
"mean_token_accuracy": 0.2011136829853058,
|
|
"num_tokens": 41863015.0,
|
|
"step": 24130
|
|
},
|
|
{
|
|
"entropy": 5.723241806030273,
|
|
"epoch": 1.877805874343513,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004644360935795993,
|
|
"loss": 5.0601,
|
|
"mean_token_accuracy": 0.19522613734006883,
|
|
"num_tokens": 41871703.0,
|
|
"step": 24135
|
|
},
|
|
{
|
|
"entropy": 5.7228978157043455,
|
|
"epoch": 1.8781949037152303,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00046442113753256126,
|
|
"loss": 5.0013,
|
|
"mean_token_accuracy": 0.19627539813518524,
|
|
"num_tokens": 41880136.0,
|
|
"step": 24140
|
|
},
|
|
{
|
|
"entropy": 5.722740173339844,
|
|
"epoch": 1.878583933086948,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00046440617861135905,
|
|
"loss": 5.1315,
|
|
"mean_token_accuracy": 0.19552311301231384,
|
|
"num_tokens": 41889065.0,
|
|
"step": 24145
|
|
},
|
|
{
|
|
"entropy": 5.618831777572632,
|
|
"epoch": 1.8789729624586657,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004643912168162194,
|
|
"loss": 4.9717,
|
|
"mean_token_accuracy": 0.20740085244178771,
|
|
"num_tokens": 41898160.0,
|
|
"step": 24150
|
|
},
|
|
{
|
|
"entropy": 5.725120782852173,
|
|
"epoch": 1.8793619918303832,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004643762521473696,
|
|
"loss": 5.0554,
|
|
"mean_token_accuracy": 0.2016186848282814,
|
|
"num_tokens": 41907037.0,
|
|
"step": 24155
|
|
},
|
|
{
|
|
"entropy": 5.724745416641236,
|
|
"epoch": 1.8797510212021007,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004643612846050366,
|
|
"loss": 5.1157,
|
|
"mean_token_accuracy": 0.1896385058760643,
|
|
"num_tokens": 41915176.0,
|
|
"step": 24160
|
|
},
|
|
{
|
|
"entropy": 5.728715610504151,
|
|
"epoch": 1.8801400505738184,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00046434631418944744,
|
|
"loss": 5.1057,
|
|
"mean_token_accuracy": 0.19158462584018707,
|
|
"num_tokens": 41923586.0,
|
|
"step": 24165
|
|
},
|
|
{
|
|
"entropy": 5.703259468078613,
|
|
"epoch": 1.8805290799455359,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004643313409008294,
|
|
"loss": 5.1898,
|
|
"mean_token_accuracy": 0.18386437743902206,
|
|
"num_tokens": 41932803.0,
|
|
"step": 24170
|
|
},
|
|
{
|
|
"entropy": 5.718877363204956,
|
|
"epoch": 1.8809181093172533,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00046431636473940956,
|
|
"loss": 5.0844,
|
|
"mean_token_accuracy": 0.19435103833675385,
|
|
"num_tokens": 41941737.0,
|
|
"step": 24175
|
|
},
|
|
{
|
|
"entropy": 5.6895629405975345,
|
|
"epoch": 1.881307138688971,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004643013857054152,
|
|
"loss": 4.999,
|
|
"mean_token_accuracy": 0.2022035926580429,
|
|
"num_tokens": 41950099.0,
|
|
"step": 24180
|
|
},
|
|
{
|
|
"entropy": 5.658486413955688,
|
|
"epoch": 1.8816961680606887,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00046428640379907367,
|
|
"loss": 5.0662,
|
|
"mean_token_accuracy": 0.19750165045261384,
|
|
"num_tokens": 41959091.0,
|
|
"step": 24185
|
|
},
|
|
{
|
|
"entropy": 5.728923988342285,
|
|
"epoch": 1.882085197432406,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00046427141902061225,
|
|
"loss": 4.9813,
|
|
"mean_token_accuracy": 0.20358682423830032,
|
|
"num_tokens": 41968462.0,
|
|
"step": 24190
|
|
},
|
|
{
|
|
"entropy": 5.680650281906128,
|
|
"epoch": 1.8824742268041237,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004642564313702582,
|
|
"loss": 5.0571,
|
|
"mean_token_accuracy": 0.19784417897462844,
|
|
"num_tokens": 41976514.0,
|
|
"step": 24195
|
|
},
|
|
{
|
|
"entropy": 5.626406717300415,
|
|
"epoch": 1.8828632561758414,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00046424144084823916,
|
|
"loss": 4.9735,
|
|
"mean_token_accuracy": 0.2012020990252495,
|
|
"num_tokens": 41985583.0,
|
|
"step": 24200
|
|
},
|
|
{
|
|
"entropy": 5.643293714523315,
|
|
"epoch": 1.8832522855475589,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004642264474547824,
|
|
"loss": 4.9842,
|
|
"mean_token_accuracy": 0.20644300431013107,
|
|
"num_tokens": 41993684.0,
|
|
"step": 24205
|
|
},
|
|
{
|
|
"entropy": 5.641506958007812,
|
|
"epoch": 1.8836413149192763,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00046421145119011556,
|
|
"loss": 4.9498,
|
|
"mean_token_accuracy": 0.20412273854017257,
|
|
"num_tokens": 42002239.0,
|
|
"step": 24210
|
|
},
|
|
{
|
|
"entropy": 5.5814532279968265,
|
|
"epoch": 1.884030344290994,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000464196452054466,
|
|
"loss": 4.9239,
|
|
"mean_token_accuracy": 0.20882173329591752,
|
|
"num_tokens": 42010886.0,
|
|
"step": 24215
|
|
},
|
|
{
|
|
"entropy": 5.678795433044433,
|
|
"epoch": 1.8844193736627115,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004641814500480615,
|
|
"loss": 5.1051,
|
|
"mean_token_accuracy": 0.1926621153950691,
|
|
"num_tokens": 42019703.0,
|
|
"step": 24220
|
|
},
|
|
{
|
|
"entropy": 5.7432952404022215,
|
|
"epoch": 1.884808403034429,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004641664451711296,
|
|
"loss": 5.158,
|
|
"mean_token_accuracy": 0.19239576607942582,
|
|
"num_tokens": 42028467.0,
|
|
"step": 24225
|
|
},
|
|
{
|
|
"entropy": 5.684470176696777,
|
|
"epoch": 1.8851974324061467,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00046415143742389793,
|
|
"loss": 5.0396,
|
|
"mean_token_accuracy": 0.1998426377773285,
|
|
"num_tokens": 42037220.0,
|
|
"step": 24230
|
|
},
|
|
{
|
|
"entropy": 5.706933927536011,
|
|
"epoch": 1.8855864617778644,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004641364268065943,
|
|
"loss": 5.0975,
|
|
"mean_token_accuracy": 0.1953598141670227,
|
|
"num_tokens": 42046034.0,
|
|
"step": 24235
|
|
},
|
|
{
|
|
"entropy": 5.654673051834107,
|
|
"epoch": 1.8859754911495816,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00046412141331944644,
|
|
"loss": 5.0442,
|
|
"mean_token_accuracy": 0.1991073340177536,
|
|
"num_tokens": 42054659.0,
|
|
"step": 24240
|
|
},
|
|
{
|
|
"entropy": 5.709597110748291,
|
|
"epoch": 1.8863645205212993,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00046410639696268206,
|
|
"loss": 5.0999,
|
|
"mean_token_accuracy": 0.1921329081058502,
|
|
"num_tokens": 42063130.0,
|
|
"step": 24245
|
|
},
|
|
{
|
|
"entropy": 5.702262830734253,
|
|
"epoch": 1.886753549893017,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004640913777365292,
|
|
"loss": 5.1088,
|
|
"mean_token_accuracy": 0.19227679818868637,
|
|
"num_tokens": 42071162.0,
|
|
"step": 24250
|
|
},
|
|
{
|
|
"entropy": 5.678764772415161,
|
|
"epoch": 1.8871425792647345,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00046407635564121565,
|
|
"loss": 5.1064,
|
|
"mean_token_accuracy": 0.19842315167188646,
|
|
"num_tokens": 42079948.0,
|
|
"step": 24255
|
|
},
|
|
{
|
|
"entropy": 5.7053149223327635,
|
|
"epoch": 1.887531608636452,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00046406133067696936,
|
|
"loss": 5.0567,
|
|
"mean_token_accuracy": 0.19605812579393386,
|
|
"num_tokens": 42089010.0,
|
|
"step": 24260
|
|
},
|
|
{
|
|
"entropy": 5.759976196289062,
|
|
"epoch": 1.8879206380081697,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004640463028440182,
|
|
"loss": 5.0605,
|
|
"mean_token_accuracy": 0.19377840757369996,
|
|
"num_tokens": 42097096.0,
|
|
"step": 24265
|
|
},
|
|
{
|
|
"entropy": 5.616702318191528,
|
|
"epoch": 1.8883096673798871,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004640312721425904,
|
|
"loss": 4.9776,
|
|
"mean_token_accuracy": 0.19980015903711318,
|
|
"num_tokens": 42105870.0,
|
|
"step": 24270
|
|
},
|
|
{
|
|
"entropy": 5.638563919067383,
|
|
"epoch": 1.8886986967516046,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004640162385729139,
|
|
"loss": 4.9755,
|
|
"mean_token_accuracy": 0.21114583760499955,
|
|
"num_tokens": 42114246.0,
|
|
"step": 24275
|
|
},
|
|
{
|
|
"entropy": 5.624612712860108,
|
|
"epoch": 1.8890877261233223,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004640012021352168,
|
|
"loss": 4.9844,
|
|
"mean_token_accuracy": 0.19922612458467484,
|
|
"num_tokens": 42122163.0,
|
|
"step": 24280
|
|
},
|
|
{
|
|
"entropy": 5.659454774856568,
|
|
"epoch": 1.88947675549504,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004639861628297273,
|
|
"loss": 5.0182,
|
|
"mean_token_accuracy": 0.2026349723339081,
|
|
"num_tokens": 42130255.0,
|
|
"step": 24285
|
|
},
|
|
{
|
|
"entropy": 5.734159326553344,
|
|
"epoch": 1.8898657848667575,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00046397112065667354,
|
|
"loss": 5.0919,
|
|
"mean_token_accuracy": 0.19065866768360137,
|
|
"num_tokens": 42138615.0,
|
|
"step": 24290
|
|
},
|
|
{
|
|
"entropy": 5.68282380104065,
|
|
"epoch": 1.890254814238475,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00046395607561628387,
|
|
"loss": 4.9794,
|
|
"mean_token_accuracy": 0.20117951631546022,
|
|
"num_tokens": 42146502.0,
|
|
"step": 24295
|
|
},
|
|
{
|
|
"entropy": 5.668199634552002,
|
|
"epoch": 1.8906438436101927,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00046394102770878643,
|
|
"loss": 5.0517,
|
|
"mean_token_accuracy": 0.2024393394589424,
|
|
"num_tokens": 42155548.0,
|
|
"step": 24300
|
|
},
|
|
{
|
|
"entropy": 5.560957574844361,
|
|
"epoch": 1.8910328729819101,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00046392597693440974,
|
|
"loss": 4.8722,
|
|
"mean_token_accuracy": 0.20830923765897752,
|
|
"num_tokens": 42163813.0,
|
|
"step": 24305
|
|
},
|
|
{
|
|
"entropy": 5.743336915969849,
|
|
"epoch": 1.8914219023536276,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004639109232933819,
|
|
"loss": 5.0829,
|
|
"mean_token_accuracy": 0.1985733166337013,
|
|
"num_tokens": 42172702.0,
|
|
"step": 24310
|
|
},
|
|
{
|
|
"entropy": 5.735151672363282,
|
|
"epoch": 1.8918109317253453,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004638958667859316,
|
|
"loss": 5.1321,
|
|
"mean_token_accuracy": 0.20116187632083893,
|
|
"num_tokens": 42180776.0,
|
|
"step": 24315
|
|
},
|
|
{
|
|
"entropy": 5.71647367477417,
|
|
"epoch": 1.8921999610970628,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004638808074122872,
|
|
"loss": 5.0649,
|
|
"mean_token_accuracy": 0.19686400294303893,
|
|
"num_tokens": 42189695.0,
|
|
"step": 24320
|
|
},
|
|
{
|
|
"entropy": 5.66493821144104,
|
|
"epoch": 1.8925889904687803,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004638657451726771,
|
|
"loss": 5.0428,
|
|
"mean_token_accuracy": 0.19719133228063584,
|
|
"num_tokens": 42197884.0,
|
|
"step": 24325
|
|
},
|
|
{
|
|
"entropy": 5.744034194946289,
|
|
"epoch": 1.892978019840498,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00046385068006732995,
|
|
"loss": 5.1461,
|
|
"mean_token_accuracy": 0.1902386024594307,
|
|
"num_tokens": 42206800.0,
|
|
"step": 24330
|
|
},
|
|
{
|
|
"entropy": 5.702206563949585,
|
|
"epoch": 1.8933670492122157,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00046383561209647437,
|
|
"loss": 5.0202,
|
|
"mean_token_accuracy": 0.21366167962551116,
|
|
"num_tokens": 42216091.0,
|
|
"step": 24335
|
|
},
|
|
{
|
|
"entropy": 5.629003572463989,
|
|
"epoch": 1.8937560785839331,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00046382054126033884,
|
|
"loss": 5.0525,
|
|
"mean_token_accuracy": 0.19962407499551774,
|
|
"num_tokens": 42224675.0,
|
|
"step": 24340
|
|
},
|
|
{
|
|
"entropy": 5.709082508087159,
|
|
"epoch": 1.8941451079556506,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004638054675591523,
|
|
"loss": 5.079,
|
|
"mean_token_accuracy": 0.19774367809295654,
|
|
"num_tokens": 42232964.0,
|
|
"step": 24345
|
|
},
|
|
{
|
|
"entropy": 5.733403730392456,
|
|
"epoch": 1.8945341373273683,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004637903909931432,
|
|
"loss": 5.0788,
|
|
"mean_token_accuracy": 0.19271970093250274,
|
|
"num_tokens": 42241932.0,
|
|
"step": 24350
|
|
},
|
|
{
|
|
"entropy": 5.645138120651245,
|
|
"epoch": 1.8949231666990858,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004637753115625404,
|
|
"loss": 4.8912,
|
|
"mean_token_accuracy": 0.20349908322095872,
|
|
"num_tokens": 42250146.0,
|
|
"step": 24355
|
|
},
|
|
{
|
|
"entropy": 5.656929779052734,
|
|
"epoch": 1.8953121960708033,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004637602292675726,
|
|
"loss": 5.1267,
|
|
"mean_token_accuracy": 0.19452781826257706,
|
|
"num_tokens": 42259183.0,
|
|
"step": 24360
|
|
},
|
|
{
|
|
"entropy": 5.732398843765258,
|
|
"epoch": 1.895701225442521,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004637451441084689,
|
|
"loss": 5.1551,
|
|
"mean_token_accuracy": 0.189733025431633,
|
|
"num_tokens": 42268436.0,
|
|
"step": 24365
|
|
},
|
|
{
|
|
"entropy": 5.777950572967529,
|
|
"epoch": 1.8960902548142384,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004637300560854581,
|
|
"loss": 5.1021,
|
|
"mean_token_accuracy": 0.19860146641731263,
|
|
"num_tokens": 42277146.0,
|
|
"step": 24370
|
|
},
|
|
{
|
|
"entropy": 5.742022466659546,
|
|
"epoch": 1.896479284185956,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000463714965198769,
|
|
"loss": 5.0604,
|
|
"mean_token_accuracy": 0.1950198993086815,
|
|
"num_tokens": 42286571.0,
|
|
"step": 24375
|
|
},
|
|
{
|
|
"entropy": 5.6356847286224365,
|
|
"epoch": 1.8968683135576736,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004636998714486307,
|
|
"loss": 5.0013,
|
|
"mean_token_accuracy": 0.20521741807460786,
|
|
"num_tokens": 42295415.0,
|
|
"step": 24380
|
|
},
|
|
{
|
|
"entropy": 5.676912832260132,
|
|
"epoch": 1.8972573429293913,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00046368477483527224,
|
|
"loss": 5.0648,
|
|
"mean_token_accuracy": 0.19570236802101135,
|
|
"num_tokens": 42305105.0,
|
|
"step": 24385
|
|
},
|
|
{
|
|
"entropy": 5.688040494918823,
|
|
"epoch": 1.8976463723011088,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004636696753589226,
|
|
"loss": 4.981,
|
|
"mean_token_accuracy": 0.20344528555870056,
|
|
"num_tokens": 42313034.0,
|
|
"step": 24390
|
|
},
|
|
{
|
|
"entropy": 5.638887643814087,
|
|
"epoch": 1.8980354016728263,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004636545730198109,
|
|
"loss": 5.0353,
|
|
"mean_token_accuracy": 0.19749893993139267,
|
|
"num_tokens": 42321249.0,
|
|
"step": 24395
|
|
},
|
|
{
|
|
"entropy": 5.641788816452026,
|
|
"epoch": 1.898424431044544,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00046363946781816643,
|
|
"loss": 5.0568,
|
|
"mean_token_accuracy": 0.19804082810878754,
|
|
"num_tokens": 42329519.0,
|
|
"step": 24400
|
|
},
|
|
{
|
|
"entropy": 5.742695283889771,
|
|
"epoch": 1.8988134604162614,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00046362435975421816,
|
|
"loss": 5.1187,
|
|
"mean_token_accuracy": 0.19449923038482667,
|
|
"num_tokens": 42338318.0,
|
|
"step": 24405
|
|
},
|
|
{
|
|
"entropy": 5.689006710052491,
|
|
"epoch": 1.899202489787979,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00046360924882819554,
|
|
"loss": 5.0372,
|
|
"mean_token_accuracy": 0.19813034534454346,
|
|
"num_tokens": 42346038.0,
|
|
"step": 24410
|
|
},
|
|
{
|
|
"entropy": 5.672586250305176,
|
|
"epoch": 1.8995915191596966,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004635941350403277,
|
|
"loss": 5.0187,
|
|
"mean_token_accuracy": 0.20174821764230727,
|
|
"num_tokens": 42356280.0,
|
|
"step": 24415
|
|
},
|
|
{
|
|
"entropy": 5.644523429870605,
|
|
"epoch": 1.899980548531414,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004635790183908442,
|
|
"loss": 4.9686,
|
|
"mean_token_accuracy": 0.21053633987903594,
|
|
"num_tokens": 42364716.0,
|
|
"step": 24420
|
|
},
|
|
{
|
|
"entropy": 5.6797035217285154,
|
|
"epoch": 1.9003695779031315,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00046356389887997415,
|
|
"loss": 5.1051,
|
|
"mean_token_accuracy": 0.19301884472370148,
|
|
"num_tokens": 42373137.0,
|
|
"step": 24425
|
|
},
|
|
{
|
|
"entropy": 5.683261728286743,
|
|
"epoch": 1.9007586072748492,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00046354877650794707,
|
|
"loss": 5.0089,
|
|
"mean_token_accuracy": 0.19646963328123093,
|
|
"num_tokens": 42382054.0,
|
|
"step": 24430
|
|
},
|
|
{
|
|
"entropy": 5.6304632186889645,
|
|
"epoch": 1.901147636646567,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00046353365127499235,
|
|
"loss": 5.0157,
|
|
"mean_token_accuracy": 0.1978391870856285,
|
|
"num_tokens": 42391228.0,
|
|
"step": 24435
|
|
},
|
|
{
|
|
"entropy": 5.706356716156006,
|
|
"epoch": 1.9015366660182844,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004635185231813396,
|
|
"loss": 4.9921,
|
|
"mean_token_accuracy": 0.20484830290079117,
|
|
"num_tokens": 42400178.0,
|
|
"step": 24440
|
|
},
|
|
{
|
|
"entropy": 5.693290185928345,
|
|
"epoch": 1.901925695390002,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004635033922272183,
|
|
"loss": 5.0457,
|
|
"mean_token_accuracy": 0.20605269819498062,
|
|
"num_tokens": 42408515.0,
|
|
"step": 24445
|
|
},
|
|
{
|
|
"entropy": 5.738110303878784,
|
|
"epoch": 1.9023147247617196,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00046348825841285813,
|
|
"loss": 5.0815,
|
|
"mean_token_accuracy": 0.19458684772253038,
|
|
"num_tokens": 42417291.0,
|
|
"step": 24450
|
|
},
|
|
{
|
|
"entropy": 5.811046600341797,
|
|
"epoch": 1.902703754133437,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004634731217384886,
|
|
"loss": 5.2364,
|
|
"mean_token_accuracy": 0.1796120062470436,
|
|
"num_tokens": 42426371.0,
|
|
"step": 24455
|
|
},
|
|
{
|
|
"entropy": 5.768460845947265,
|
|
"epoch": 1.9030927835051545,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004634579822043394,
|
|
"loss": 5.1909,
|
|
"mean_token_accuracy": 0.19514919221401214,
|
|
"num_tokens": 42434767.0,
|
|
"step": 24460
|
|
},
|
|
{
|
|
"entropy": 5.685267496109009,
|
|
"epoch": 1.9034818128768722,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00046344283981064035,
|
|
"loss": 5.0596,
|
|
"mean_token_accuracy": 0.2002108722925186,
|
|
"num_tokens": 42443618.0,
|
|
"step": 24465
|
|
},
|
|
{
|
|
"entropy": 5.6775439262390135,
|
|
"epoch": 1.90387084224859,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00046342769455762114,
|
|
"loss": 5.0287,
|
|
"mean_token_accuracy": 0.1962940812110901,
|
|
"num_tokens": 42453134.0,
|
|
"step": 24470
|
|
},
|
|
{
|
|
"entropy": 5.713677597045899,
|
|
"epoch": 1.9042598716203072,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004634125464455116,
|
|
"loss": 5.0482,
|
|
"mean_token_accuracy": 0.19347914606332778,
|
|
"num_tokens": 42462037.0,
|
|
"step": 24475
|
|
},
|
|
{
|
|
"entropy": 5.6461576461792,
|
|
"epoch": 1.9046489009920249,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00046339739547454146,
|
|
"loss": 4.9839,
|
|
"mean_token_accuracy": 0.20335804373025895,
|
|
"num_tokens": 42471318.0,
|
|
"step": 24480
|
|
},
|
|
{
|
|
"entropy": 5.675210475921631,
|
|
"epoch": 1.9050379303637426,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00046338224164494074,
|
|
"loss": 5.0822,
|
|
"mean_token_accuracy": 0.19868521839380265,
|
|
"num_tokens": 42478851.0,
|
|
"step": 24485
|
|
},
|
|
{
|
|
"entropy": 5.618244314193726,
|
|
"epoch": 1.90542695973546,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00046336708495693933,
|
|
"loss": 4.998,
|
|
"mean_token_accuracy": 0.20081014335155487,
|
|
"num_tokens": 42488406.0,
|
|
"step": 24490
|
|
},
|
|
{
|
|
"entropy": 5.691645097732544,
|
|
"epoch": 1.9058159891071775,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00046335192541076725,
|
|
"loss": 4.9317,
|
|
"mean_token_accuracy": 0.20910554379224777,
|
|
"num_tokens": 42496001.0,
|
|
"step": 24495
|
|
},
|
|
{
|
|
"entropy": 5.675712966918946,
|
|
"epoch": 1.9062050184788952,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004633367630066545,
|
|
"loss": 5.093,
|
|
"mean_token_accuracy": 0.192819344997406,
|
|
"num_tokens": 42504808.0,
|
|
"step": 24500
|
|
},
|
|
{
|
|
"entropy": 5.6577520847320555,
|
|
"epoch": 1.9065940478506127,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00046332159774483116,
|
|
"loss": 5.0329,
|
|
"mean_token_accuracy": 0.201383475959301,
|
|
"num_tokens": 42512885.0,
|
|
"step": 24505
|
|
},
|
|
{
|
|
"entropy": 5.660343360900879,
|
|
"epoch": 1.9069830772223302,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004633064296255273,
|
|
"loss": 5.0083,
|
|
"mean_token_accuracy": 0.19845706075429917,
|
|
"num_tokens": 42521481.0,
|
|
"step": 24510
|
|
},
|
|
{
|
|
"entropy": 5.714602041244507,
|
|
"epoch": 1.9073721065940479,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00046329125864897307,
|
|
"loss": 5.0662,
|
|
"mean_token_accuracy": 0.19484372437000275,
|
|
"num_tokens": 42529784.0,
|
|
"step": 24515
|
|
},
|
|
{
|
|
"entropy": 5.656867122650146,
|
|
"epoch": 1.9077611359657656,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004632760848153987,
|
|
"loss": 4.9426,
|
|
"mean_token_accuracy": 0.2061595305800438,
|
|
"num_tokens": 42538802.0,
|
|
"step": 24520
|
|
},
|
|
{
|
|
"entropy": 5.672155904769897,
|
|
"epoch": 1.9081501653374828,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004632609081250345,
|
|
"loss": 4.985,
|
|
"mean_token_accuracy": 0.19744465947151185,
|
|
"num_tokens": 42547699.0,
|
|
"step": 24525
|
|
},
|
|
{
|
|
"entropy": 5.688351774215699,
|
|
"epoch": 1.9085391947092005,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00046324572857811054,
|
|
"loss": 5.0452,
|
|
"mean_token_accuracy": 0.19838589280843735,
|
|
"num_tokens": 42556583.0,
|
|
"step": 24530
|
|
},
|
|
{
|
|
"entropy": 5.611498403549194,
|
|
"epoch": 1.9089282240809182,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004632305461748573,
|
|
"loss": 4.9469,
|
|
"mean_token_accuracy": 0.21325928270816802,
|
|
"num_tokens": 42565025.0,
|
|
"step": 24535
|
|
},
|
|
{
|
|
"entropy": 5.6442724704742435,
|
|
"epoch": 1.9093172534526357,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00046321536091550517,
|
|
"loss": 5.0483,
|
|
"mean_token_accuracy": 0.1989640474319458,
|
|
"num_tokens": 42573798.0,
|
|
"step": 24540
|
|
},
|
|
{
|
|
"entropy": 5.718202304840088,
|
|
"epoch": 1.9097062828243532,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004632001728002845,
|
|
"loss": 5.0257,
|
|
"mean_token_accuracy": 0.20260567516088485,
|
|
"num_tokens": 42582002.0,
|
|
"step": 24545
|
|
},
|
|
{
|
|
"entropy": 5.777220106124878,
|
|
"epoch": 1.9100953121960709,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004631849818294257,
|
|
"loss": 5.0461,
|
|
"mean_token_accuracy": 0.1970430076122284,
|
|
"num_tokens": 42591387.0,
|
|
"step": 24550
|
|
},
|
|
{
|
|
"entropy": 5.741730785369873,
|
|
"epoch": 1.9104843415677883,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00046316978800315934,
|
|
"loss": 5.1143,
|
|
"mean_token_accuracy": 0.20090012401342391,
|
|
"num_tokens": 42599769.0,
|
|
"step": 24555
|
|
},
|
|
{
|
|
"entropy": 5.60371618270874,
|
|
"epoch": 1.9108733709395058,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000463154591321716,
|
|
"loss": 4.9644,
|
|
"mean_token_accuracy": 0.2052150085568428,
|
|
"num_tokens": 42608279.0,
|
|
"step": 24560
|
|
},
|
|
{
|
|
"entropy": 5.641292524337769,
|
|
"epoch": 1.9112624003112235,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00046313939178532624,
|
|
"loss": 5.0369,
|
|
"mean_token_accuracy": 0.19688843190670013,
|
|
"num_tokens": 42616652.0,
|
|
"step": 24565
|
|
},
|
|
{
|
|
"entropy": 5.638890123367309,
|
|
"epoch": 1.9116514296829412,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004631241893942206,
|
|
"loss": 5.0016,
|
|
"mean_token_accuracy": 0.19857836067676543,
|
|
"num_tokens": 42625629.0,
|
|
"step": 24570
|
|
},
|
|
{
|
|
"entropy": 5.677545595169067,
|
|
"epoch": 1.9120404590546585,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00046310898414862983,
|
|
"loss": 5.0823,
|
|
"mean_token_accuracy": 0.20221803337335587,
|
|
"num_tokens": 42634159.0,
|
|
"step": 24575
|
|
},
|
|
{
|
|
"entropy": 5.743991088867188,
|
|
"epoch": 1.9124294884263762,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004630937760487847,
|
|
"loss": 5.1482,
|
|
"mean_token_accuracy": 0.1890771880745888,
|
|
"num_tokens": 42642880.0,
|
|
"step": 24580
|
|
},
|
|
{
|
|
"entropy": 5.697179937362671,
|
|
"epoch": 1.9128185177980939,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004630785650949158,
|
|
"loss": 5.0869,
|
|
"mean_token_accuracy": 0.1961984694004059,
|
|
"num_tokens": 42651481.0,
|
|
"step": 24585
|
|
},
|
|
{
|
|
"entropy": 5.7100200176239015,
|
|
"epoch": 1.9132075471698113,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004630633512872541,
|
|
"loss": 5.0566,
|
|
"mean_token_accuracy": 0.20454505532979966,
|
|
"num_tokens": 42660131.0,
|
|
"step": 24590
|
|
},
|
|
{
|
|
"entropy": 5.664259052276611,
|
|
"epoch": 1.9135965765415288,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00046304813462603035,
|
|
"loss": 5.0797,
|
|
"mean_token_accuracy": 0.20387784540653228,
|
|
"num_tokens": 42669094.0,
|
|
"step": 24595
|
|
},
|
|
{
|
|
"entropy": 5.676291418075562,
|
|
"epoch": 1.9139856059132465,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004630329151114754,
|
|
"loss": 5.0123,
|
|
"mean_token_accuracy": 0.20979381799697877,
|
|
"num_tokens": 42677792.0,
|
|
"step": 24600
|
|
},
|
|
{
|
|
"entropy": 5.725220823287964,
|
|
"epoch": 1.914374635284964,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00046301769274382034,
|
|
"loss": 5.0953,
|
|
"mean_token_accuracy": 0.19348185509443283,
|
|
"num_tokens": 42686397.0,
|
|
"step": 24605
|
|
},
|
|
{
|
|
"entropy": 5.697055244445801,
|
|
"epoch": 1.9147636646566815,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004630024675232961,
|
|
"loss": 5.0259,
|
|
"mean_token_accuracy": 0.20506162643432618,
|
|
"num_tokens": 42695832.0,
|
|
"step": 24610
|
|
},
|
|
{
|
|
"entropy": 5.674222087860107,
|
|
"epoch": 1.9151526940283992,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00046298723945013354,
|
|
"loss": 5.0458,
|
|
"mean_token_accuracy": 0.19670222103595733,
|
|
"num_tokens": 42704378.0,
|
|
"step": 24615
|
|
},
|
|
{
|
|
"entropy": 5.6558003425598145,
|
|
"epoch": 1.9155417234001169,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004629720085245639,
|
|
"loss": 5.0032,
|
|
"mean_token_accuracy": 0.19691879600286483,
|
|
"num_tokens": 42713926.0,
|
|
"step": 24620
|
|
},
|
|
{
|
|
"entropy": 5.726751518249512,
|
|
"epoch": 1.9159307527718341,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004629567747468182,
|
|
"loss": 4.9749,
|
|
"mean_token_accuracy": 0.20231074392795562,
|
|
"num_tokens": 42722779.0,
|
|
"step": 24625
|
|
},
|
|
{
|
|
"entropy": 5.689429044723511,
|
|
"epoch": 1.9163197821435518,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004629415381171276,
|
|
"loss": 4.9647,
|
|
"mean_token_accuracy": 0.2019610345363617,
|
|
"num_tokens": 42731460.0,
|
|
"step": 24630
|
|
},
|
|
{
|
|
"entropy": 5.6924498081207275,
|
|
"epoch": 1.9167088115152695,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00046292629863572325,
|
|
"loss": 5.0535,
|
|
"mean_token_accuracy": 0.19991564005613327,
|
|
"num_tokens": 42739733.0,
|
|
"step": 24635
|
|
},
|
|
{
|
|
"entropy": 5.753908491134643,
|
|
"epoch": 1.917097840886987,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004629110563028365,
|
|
"loss": 5.0719,
|
|
"mean_token_accuracy": 0.19914218932390212,
|
|
"num_tokens": 42748330.0,
|
|
"step": 24640
|
|
},
|
|
{
|
|
"entropy": 5.695810317993164,
|
|
"epoch": 1.9174868702587045,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004628958111186985,
|
|
"loss": 5.0751,
|
|
"mean_token_accuracy": 0.19527909755706788,
|
|
"num_tokens": 42757423.0,
|
|
"step": 24645
|
|
},
|
|
{
|
|
"entropy": 5.668301963806153,
|
|
"epoch": 1.9178758996304222,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004628805630835407,
|
|
"loss": 5.0847,
|
|
"mean_token_accuracy": 0.192294117808342,
|
|
"num_tokens": 42766213.0,
|
|
"step": 24650
|
|
},
|
|
{
|
|
"entropy": 5.748909664154053,
|
|
"epoch": 1.9182649290021396,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004628653121975944,
|
|
"loss": 5.0907,
|
|
"mean_token_accuracy": 0.20167043358087539,
|
|
"num_tokens": 42774037.0,
|
|
"step": 24655
|
|
},
|
|
{
|
|
"entropy": 5.688054895401001,
|
|
"epoch": 1.918653958373857,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000462850058461091,
|
|
"loss": 5.1383,
|
|
"mean_token_accuracy": 0.1927604928612709,
|
|
"num_tokens": 42782806.0,
|
|
"step": 24660
|
|
},
|
|
{
|
|
"entropy": 5.599278163909912,
|
|
"epoch": 1.9190429877455748,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004628348018742619,
|
|
"loss": 4.9692,
|
|
"mean_token_accuracy": 0.19859009683132173,
|
|
"num_tokens": 42791790.0,
|
|
"step": 24665
|
|
},
|
|
{
|
|
"entropy": 5.725513744354248,
|
|
"epoch": 1.9194320171172925,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004628195424373387,
|
|
"loss": 5.1401,
|
|
"mean_token_accuracy": 0.18950953036546708,
|
|
"num_tokens": 42799966.0,
|
|
"step": 24670
|
|
},
|
|
{
|
|
"entropy": 5.696822452545166,
|
|
"epoch": 1.91982104648901,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00046280428015055286,
|
|
"loss": 5.0379,
|
|
"mean_token_accuracy": 0.20477413833141328,
|
|
"num_tokens": 42808022.0,
|
|
"step": 24675
|
|
},
|
|
{
|
|
"entropy": 5.681642007827759,
|
|
"epoch": 1.9202100758607274,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00046278901501413606,
|
|
"loss": 4.957,
|
|
"mean_token_accuracy": 0.21134666502475738,
|
|
"num_tokens": 42816191.0,
|
|
"step": 24680
|
|
},
|
|
{
|
|
"entropy": 5.693042469024658,
|
|
"epoch": 1.9205991052324451,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00046277374702831983,
|
|
"loss": 5.0534,
|
|
"mean_token_accuracy": 0.19525159299373626,
|
|
"num_tokens": 42824840.0,
|
|
"step": 24685
|
|
},
|
|
{
|
|
"entropy": 5.672334671020508,
|
|
"epoch": 1.9209881346041626,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00046275847619333576,
|
|
"loss": 5.0396,
|
|
"mean_token_accuracy": 0.1973715215921402,
|
|
"num_tokens": 42833788.0,
|
|
"step": 24690
|
|
},
|
|
{
|
|
"entropy": 5.734400939941406,
|
|
"epoch": 1.92137716397588,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00046274320250941576,
|
|
"loss": 5.0836,
|
|
"mean_token_accuracy": 0.19542493373155595,
|
|
"num_tokens": 42842666.0,
|
|
"step": 24695
|
|
},
|
|
{
|
|
"entropy": 5.775894498825073,
|
|
"epoch": 1.9217661933475978,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00046272792597679146,
|
|
"loss": 5.1169,
|
|
"mean_token_accuracy": 0.1904724881052971,
|
|
"num_tokens": 42850725.0,
|
|
"step": 24700
|
|
},
|
|
{
|
|
"entropy": 5.680692195892334,
|
|
"epoch": 1.9221552227193153,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00046271264659569474,
|
|
"loss": 5.0681,
|
|
"mean_token_accuracy": 0.19184989780187606,
|
|
"num_tokens": 42859732.0,
|
|
"step": 24705
|
|
},
|
|
{
|
|
"entropy": 5.715995359420776,
|
|
"epoch": 1.9225442520910327,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004626973643663573,
|
|
"loss": 5.0564,
|
|
"mean_token_accuracy": 0.19708100259304046,
|
|
"num_tokens": 42868858.0,
|
|
"step": 24710
|
|
},
|
|
{
|
|
"entropy": 5.722647571563721,
|
|
"epoch": 1.9229332814627504,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004626820792890112,
|
|
"loss": 5.0865,
|
|
"mean_token_accuracy": 0.19535237103700637,
|
|
"num_tokens": 42877483.0,
|
|
"step": 24715
|
|
},
|
|
{
|
|
"entropy": 5.680809354782104,
|
|
"epoch": 1.9233223108344681,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004626667913638882,
|
|
"loss": 4.9326,
|
|
"mean_token_accuracy": 0.21316238939762117,
|
|
"num_tokens": 42885156.0,
|
|
"step": 24720
|
|
},
|
|
{
|
|
"entropy": 5.730360412597657,
|
|
"epoch": 1.9237113402061856,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004626515005912203,
|
|
"loss": 5.1225,
|
|
"mean_token_accuracy": 0.19758251160383225,
|
|
"num_tokens": 42893599.0,
|
|
"step": 24725
|
|
},
|
|
{
|
|
"entropy": 5.679024171829224,
|
|
"epoch": 1.924100369577903,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004626362069712397,
|
|
"loss": 4.9986,
|
|
"mean_token_accuracy": 0.2093589186668396,
|
|
"num_tokens": 42902861.0,
|
|
"step": 24730
|
|
},
|
|
{
|
|
"entropy": 5.689429044723511,
|
|
"epoch": 1.9244893989496208,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004626209105041782,
|
|
"loss": 5.0547,
|
|
"mean_token_accuracy": 0.19889709502458572,
|
|
"num_tokens": 42911246.0,
|
|
"step": 24735
|
|
},
|
|
{
|
|
"entropy": 5.670091724395752,
|
|
"epoch": 1.9248784283213383,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000462605611190268,
|
|
"loss": 5.1332,
|
|
"mean_token_accuracy": 0.194108085334301,
|
|
"num_tokens": 42919526.0,
|
|
"step": 24740
|
|
},
|
|
{
|
|
"entropy": 5.666739797592163,
|
|
"epoch": 1.9252674576930557,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00046259030902974133,
|
|
"loss": 4.952,
|
|
"mean_token_accuracy": 0.20560158789157867,
|
|
"num_tokens": 42927473.0,
|
|
"step": 24745
|
|
},
|
|
{
|
|
"entropy": 5.644410848617554,
|
|
"epoch": 1.9256564870647734,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004625750040228302,
|
|
"loss": 5.0159,
|
|
"mean_token_accuracy": 0.20053688436746597,
|
|
"num_tokens": 42936108.0,
|
|
"step": 24750
|
|
},
|
|
{
|
|
"entropy": 5.629378366470337,
|
|
"epoch": 1.926045516436491,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00046255969616976704,
|
|
"loss": 4.9465,
|
|
"mean_token_accuracy": 0.20834380388259888,
|
|
"num_tokens": 42944147.0,
|
|
"step": 24755
|
|
},
|
|
{
|
|
"entropy": 5.665427732467651,
|
|
"epoch": 1.9264345458082084,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000462544385470784,
|
|
"loss": 5.1342,
|
|
"mean_token_accuracy": 0.1902235969901085,
|
|
"num_tokens": 42952674.0,
|
|
"step": 24760
|
|
},
|
|
{
|
|
"entropy": 5.665197038650513,
|
|
"epoch": 1.926823575179926,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004625290719261134,
|
|
"loss": 5.0126,
|
|
"mean_token_accuracy": 0.20286975353956221,
|
|
"num_tokens": 42960907.0,
|
|
"step": 24765
|
|
},
|
|
{
|
|
"entropy": 5.685473823547364,
|
|
"epoch": 1.9272126045516438,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004625137555359876,
|
|
"loss": 5.0076,
|
|
"mean_token_accuracy": 0.194828163087368,
|
|
"num_tokens": 42968875.0,
|
|
"step": 24770
|
|
},
|
|
{
|
|
"entropy": 5.692585468292236,
|
|
"epoch": 1.9276016339233613,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00046249843630063905,
|
|
"loss": 5.0266,
|
|
"mean_token_accuracy": 0.20408463180065156,
|
|
"num_tokens": 42977062.0,
|
|
"step": 24775
|
|
},
|
|
{
|
|
"entropy": 5.668549203872681,
|
|
"epoch": 1.9279906632950787,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004624831142203001,
|
|
"loss": 5.0032,
|
|
"mean_token_accuracy": 0.20419415533542634,
|
|
"num_tokens": 42985346.0,
|
|
"step": 24780
|
|
},
|
|
{
|
|
"entropy": 5.656054210662842,
|
|
"epoch": 1.9283796926667964,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00046246778929520346,
|
|
"loss": 5.0654,
|
|
"mean_token_accuracy": 0.18509457260370255,
|
|
"num_tokens": 42993529.0,
|
|
"step": 24785
|
|
},
|
|
{
|
|
"entropy": 5.7392017364501955,
|
|
"epoch": 1.928768722038514,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004624524615255814,
|
|
"loss": 5.068,
|
|
"mean_token_accuracy": 0.1970072254538536,
|
|
"num_tokens": 43002254.0,
|
|
"step": 24790
|
|
},
|
|
{
|
|
"entropy": 5.679862833023071,
|
|
"epoch": 1.9291577514102314,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00046243713091166655,
|
|
"loss": 5.0453,
|
|
"mean_token_accuracy": 0.20193109959363936,
|
|
"num_tokens": 43011130.0,
|
|
"step": 24795
|
|
},
|
|
{
|
|
"entropy": 5.642696666717529,
|
|
"epoch": 1.929546780781949,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004624217974536916,
|
|
"loss": 4.9932,
|
|
"mean_token_accuracy": 0.20740202218294143,
|
|
"num_tokens": 43019185.0,
|
|
"step": 24800
|
|
},
|
|
{
|
|
"entropy": 5.737049150466919,
|
|
"epoch": 1.9299358101536666,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00046240646115188925,
|
|
"loss": 5.1968,
|
|
"mean_token_accuracy": 0.18931230902671814,
|
|
"num_tokens": 43028817.0,
|
|
"step": 24805
|
|
},
|
|
{
|
|
"entropy": 5.688579940795899,
|
|
"epoch": 1.930324839525384,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004623911220064921,
|
|
"loss": 5.0191,
|
|
"mean_token_accuracy": 0.20310221016407012,
|
|
"num_tokens": 43038205.0,
|
|
"step": 24810
|
|
},
|
|
{
|
|
"entropy": 5.654299974441528,
|
|
"epoch": 1.9307138688971017,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00046237578001773297,
|
|
"loss": 5.0434,
|
|
"mean_token_accuracy": 0.19733235687017442,
|
|
"num_tokens": 43046844.0,
|
|
"step": 24815
|
|
},
|
|
{
|
|
"entropy": 5.680369710922241,
|
|
"epoch": 1.9311028982688194,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00046236043518584454,
|
|
"loss": 5.1311,
|
|
"mean_token_accuracy": 0.193811796605587,
|
|
"num_tokens": 43055928.0,
|
|
"step": 24820
|
|
},
|
|
{
|
|
"entropy": 5.735134601593018,
|
|
"epoch": 1.931491927640537,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004623450875110597,
|
|
"loss": 5.0654,
|
|
"mean_token_accuracy": 0.1998404085636139,
|
|
"num_tokens": 43065371.0,
|
|
"step": 24825
|
|
},
|
|
{
|
|
"entropy": 5.732225799560547,
|
|
"epoch": 1.9318809570122544,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00046232973699361147,
|
|
"loss": 5.0069,
|
|
"mean_token_accuracy": 0.19985468536615372,
|
|
"num_tokens": 43073486.0,
|
|
"step": 24830
|
|
},
|
|
{
|
|
"entropy": 5.636778211593628,
|
|
"epoch": 1.932269986383972,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004623143836337326,
|
|
"loss": 5.0505,
|
|
"mean_token_accuracy": 0.20184364765882493,
|
|
"num_tokens": 43083028.0,
|
|
"step": 24835
|
|
},
|
|
{
|
|
"entropy": 5.636121416091919,
|
|
"epoch": 1.9326590157556895,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00046229902743165607,
|
|
"loss": 5.0425,
|
|
"mean_token_accuracy": 0.19869482964277269,
|
|
"num_tokens": 43091134.0,
|
|
"step": 24840
|
|
},
|
|
{
|
|
"entropy": 5.708029317855835,
|
|
"epoch": 1.933048045127407,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004622836683876149,
|
|
"loss": 5.0848,
|
|
"mean_token_accuracy": 0.19872661232948302,
|
|
"num_tokens": 43099849.0,
|
|
"step": 24845
|
|
},
|
|
{
|
|
"entropy": 5.71333065032959,
|
|
"epoch": 1.9334370744991247,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004622683065018422,
|
|
"loss": 5.0355,
|
|
"mean_token_accuracy": 0.1981332778930664,
|
|
"num_tokens": 43108311.0,
|
|
"step": 24850
|
|
},
|
|
{
|
|
"entropy": 5.674883460998535,
|
|
"epoch": 1.9338261038708422,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00046225294177457105,
|
|
"loss": 4.9317,
|
|
"mean_token_accuracy": 0.20503869354724885,
|
|
"num_tokens": 43116179.0,
|
|
"step": 24855
|
|
},
|
|
{
|
|
"entropy": 5.600819826126099,
|
|
"epoch": 1.9342151332425597,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00046223757420603445,
|
|
"loss": 4.9646,
|
|
"mean_token_accuracy": 0.20399170368909836,
|
|
"num_tokens": 43125728.0,
|
|
"step": 24860
|
|
},
|
|
{
|
|
"entropy": 5.598449850082398,
|
|
"epoch": 1.9346041626142774,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004622222037964658,
|
|
"loss": 4.9376,
|
|
"mean_token_accuracy": 0.20348993241786956,
|
|
"num_tokens": 43134512.0,
|
|
"step": 24865
|
|
},
|
|
{
|
|
"entropy": 5.622919511795044,
|
|
"epoch": 1.934993191985995,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00046220683054609815,
|
|
"loss": 4.9999,
|
|
"mean_token_accuracy": 0.20116004347801208,
|
|
"num_tokens": 43144831.0,
|
|
"step": 24870
|
|
},
|
|
{
|
|
"entropy": 5.68464150428772,
|
|
"epoch": 1.9353822213577125,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00046219145445516483,
|
|
"loss": 5.0808,
|
|
"mean_token_accuracy": 0.1960323229432106,
|
|
"num_tokens": 43153614.0,
|
|
"step": 24875
|
|
},
|
|
{
|
|
"entropy": 5.69285020828247,
|
|
"epoch": 1.93577125072943,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00046217607552389905,
|
|
"loss": 5.0655,
|
|
"mean_token_accuracy": 0.19818117022514342,
|
|
"num_tokens": 43162004.0,
|
|
"step": 24880
|
|
},
|
|
{
|
|
"entropy": 5.670533895492554,
|
|
"epoch": 1.9361602801011477,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00046216069375253435,
|
|
"loss": 4.9883,
|
|
"mean_token_accuracy": 0.20691214203834535,
|
|
"num_tokens": 43170255.0,
|
|
"step": 24885
|
|
},
|
|
{
|
|
"entropy": 5.633712339401245,
|
|
"epoch": 1.9365493094728652,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000462145309141304,
|
|
"loss": 5.0684,
|
|
"mean_token_accuracy": 0.1982306033372879,
|
|
"num_tokens": 43179036.0,
|
|
"step": 24890
|
|
},
|
|
{
|
|
"entropy": 5.723203325271607,
|
|
"epoch": 1.9369383388445827,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004621299216904414,
|
|
"loss": 5.0823,
|
|
"mean_token_accuracy": 0.1950405389070511,
|
|
"num_tokens": 43187207.0,
|
|
"step": 24895
|
|
},
|
|
{
|
|
"entropy": 5.6816870212554935,
|
|
"epoch": 1.9373273682163004,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00046211453140018006,
|
|
"loss": 5.0717,
|
|
"mean_token_accuracy": 0.19018362015485762,
|
|
"num_tokens": 43195600.0,
|
|
"step": 24900
|
|
},
|
|
{
|
|
"entropy": 5.709857368469239,
|
|
"epoch": 1.937716397588018,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004620991382707537,
|
|
"loss": 5.0779,
|
|
"mean_token_accuracy": 0.2035515621304512,
|
|
"num_tokens": 43204069.0,
|
|
"step": 24905
|
|
},
|
|
{
|
|
"entropy": 5.692591142654419,
|
|
"epoch": 1.9381054269597353,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00046208374230239556,
|
|
"loss": 5.1354,
|
|
"mean_token_accuracy": 0.19016434848308564,
|
|
"num_tokens": 43212998.0,
|
|
"step": 24910
|
|
},
|
|
{
|
|
"entropy": 5.737407112121582,
|
|
"epoch": 1.938494456331453,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004620683434953394,
|
|
"loss": 5.086,
|
|
"mean_token_accuracy": 0.1937735676765442,
|
|
"num_tokens": 43222411.0,
|
|
"step": 24915
|
|
},
|
|
{
|
|
"entropy": 5.699862766265869,
|
|
"epoch": 1.9388834857031707,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00046205294184981896,
|
|
"loss": 5.0396,
|
|
"mean_token_accuracy": 0.19747995287179948,
|
|
"num_tokens": 43231265.0,
|
|
"step": 24920
|
|
},
|
|
{
|
|
"entropy": 5.7016222953796385,
|
|
"epoch": 1.9392725150748882,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00046203753736606787,
|
|
"loss": 5.0394,
|
|
"mean_token_accuracy": 0.19650323390960694,
|
|
"num_tokens": 43240609.0,
|
|
"step": 24925
|
|
},
|
|
{
|
|
"entropy": 5.713491201400757,
|
|
"epoch": 1.9396615444466057,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004620221300443197,
|
|
"loss": 5.0544,
|
|
"mean_token_accuracy": 0.20287737548351287,
|
|
"num_tokens": 43249381.0,
|
|
"step": 24930
|
|
},
|
|
{
|
|
"entropy": 5.702598142623901,
|
|
"epoch": 1.9400505738183234,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004620067198848086,
|
|
"loss": 5.0275,
|
|
"mean_token_accuracy": 0.1996012806892395,
|
|
"num_tokens": 43257653.0,
|
|
"step": 24935
|
|
},
|
|
{
|
|
"entropy": 5.71220326423645,
|
|
"epoch": 1.9404396031900408,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00046199130688776805,
|
|
"loss": 5.1243,
|
|
"mean_token_accuracy": 0.19815213978290558,
|
|
"num_tokens": 43267111.0,
|
|
"step": 24940
|
|
},
|
|
{
|
|
"entropy": 5.661815547943116,
|
|
"epoch": 1.9408286325617583,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00046197589105343204,
|
|
"loss": 4.9933,
|
|
"mean_token_accuracy": 0.20314147025346757,
|
|
"num_tokens": 43276207.0,
|
|
"step": 24945
|
|
},
|
|
{
|
|
"entropy": 5.737192058563233,
|
|
"epoch": 1.941217661933476,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004619604723820345,
|
|
"loss": 5.0419,
|
|
"mean_token_accuracy": 0.20260156095027923,
|
|
"num_tokens": 43285031.0,
|
|
"step": 24950
|
|
},
|
|
{
|
|
"entropy": 5.72438268661499,
|
|
"epoch": 1.9416066913051937,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004619450508738094,
|
|
"loss": 5.0738,
|
|
"mean_token_accuracy": 0.19643659442663192,
|
|
"num_tokens": 43292802.0,
|
|
"step": 24955
|
|
},
|
|
{
|
|
"entropy": 5.721855974197387,
|
|
"epoch": 1.941995720676911,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00046192962652899056,
|
|
"loss": 5.0207,
|
|
"mean_token_accuracy": 0.20338866114616394,
|
|
"num_tokens": 43302349.0,
|
|
"step": 24960
|
|
},
|
|
{
|
|
"entropy": 5.661811447143554,
|
|
"epoch": 1.9423847500486286,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00046191419934781236,
|
|
"loss": 4.9956,
|
|
"mean_token_accuracy": 0.20217992961406708,
|
|
"num_tokens": 43311455.0,
|
|
"step": 24965
|
|
},
|
|
{
|
|
"entropy": 5.671417093276977,
|
|
"epoch": 1.9427737794203463,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004618987693305086,
|
|
"loss": 5.0214,
|
|
"mean_token_accuracy": 0.20294463485479355,
|
|
"num_tokens": 43319924.0,
|
|
"step": 24970
|
|
},
|
|
{
|
|
"entropy": 5.708370018005371,
|
|
"epoch": 1.9431628087920638,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004618833364773135,
|
|
"loss": 5.1489,
|
|
"mean_token_accuracy": 0.19678598195314406,
|
|
"num_tokens": 43328772.0,
|
|
"step": 24975
|
|
},
|
|
{
|
|
"entropy": 5.66936502456665,
|
|
"epoch": 1.9435518381637813,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00046186790078846127,
|
|
"loss": 5.0229,
|
|
"mean_token_accuracy": 0.20237229019403458,
|
|
"num_tokens": 43338862.0,
|
|
"step": 24980
|
|
},
|
|
{
|
|
"entropy": 5.696899843215943,
|
|
"epoch": 1.943940867535499,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00046185246226418603,
|
|
"loss": 5.0565,
|
|
"mean_token_accuracy": 0.19844810962677,
|
|
"num_tokens": 43347292.0,
|
|
"step": 24985
|
|
},
|
|
{
|
|
"entropy": 5.616959047317505,
|
|
"epoch": 1.9443298969072165,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00046183702090472206,
|
|
"loss": 4.9908,
|
|
"mean_token_accuracy": 0.2068087115883827,
|
|
"num_tokens": 43356676.0,
|
|
"step": 24990
|
|
},
|
|
{
|
|
"entropy": 5.723744297027588,
|
|
"epoch": 1.944718926278934,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004618215767103037,
|
|
"loss": 5.1452,
|
|
"mean_token_accuracy": 0.19212857335805894,
|
|
"num_tokens": 43364746.0,
|
|
"step": 24995
|
|
},
|
|
{
|
|
"entropy": 5.699723911285401,
|
|
"epoch": 1.9451079556506516,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004618061296811653,
|
|
"loss": 4.9689,
|
|
"mean_token_accuracy": 0.20378757268190384,
|
|
"num_tokens": 43373541.0,
|
|
"step": 25000
|
|
},
|
|
{
|
|
"entropy": 5.688391780853271,
|
|
"epoch": 1.9454969850223693,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00046179067981754124,
|
|
"loss": 4.9814,
|
|
"mean_token_accuracy": 0.19692103266716005,
|
|
"num_tokens": 43382524.0,
|
|
"step": 25005
|
|
},
|
|
{
|
|
"entropy": 5.605011510848999,
|
|
"epoch": 1.9458860143940866,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00046177522711966584,
|
|
"loss": 5.0189,
|
|
"mean_token_accuracy": 0.20577212423086166,
|
|
"num_tokens": 43391875.0,
|
|
"step": 25010
|
|
},
|
|
{
|
|
"entropy": 5.709514570236206,
|
|
"epoch": 1.9462750437658043,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00046175977158777377,
|
|
"loss": 5.1163,
|
|
"mean_token_accuracy": 0.193670791387558,
|
|
"num_tokens": 43399942.0,
|
|
"step": 25015
|
|
},
|
|
{
|
|
"entropy": 5.727441740036011,
|
|
"epoch": 1.946664073137522,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004617443132220993,
|
|
"loss": 5.0863,
|
|
"mean_token_accuracy": 0.19419944584369658,
|
|
"num_tokens": 43409371.0,
|
|
"step": 25020
|
|
},
|
|
{
|
|
"entropy": 5.68810133934021,
|
|
"epoch": 1.9470531025092395,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00046172885202287717,
|
|
"loss": 5.068,
|
|
"mean_token_accuracy": 0.2046906530857086,
|
|
"num_tokens": 43418181.0,
|
|
"step": 25025
|
|
},
|
|
{
|
|
"entropy": 5.623637390136719,
|
|
"epoch": 1.947442131880957,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00046171338799034194,
|
|
"loss": 5.0198,
|
|
"mean_token_accuracy": 0.20464629977941512,
|
|
"num_tokens": 43426004.0,
|
|
"step": 25030
|
|
},
|
|
{
|
|
"entropy": 5.652096462249756,
|
|
"epoch": 1.9478311612526746,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004616979211247282,
|
|
"loss": 4.9283,
|
|
"mean_token_accuracy": 0.20263815373182298,
|
|
"num_tokens": 43433732.0,
|
|
"step": 25035
|
|
},
|
|
{
|
|
"entropy": 5.694263124465943,
|
|
"epoch": 1.9482201906243921,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00046168245142627065,
|
|
"loss": 5.0665,
|
|
"mean_token_accuracy": 0.2010141909122467,
|
|
"num_tokens": 43442374.0,
|
|
"step": 25040
|
|
},
|
|
{
|
|
"entropy": 5.723499917984009,
|
|
"epoch": 1.9486092199961096,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004616669788952041,
|
|
"loss": 5.1035,
|
|
"mean_token_accuracy": 0.19832152575254441,
|
|
"num_tokens": 43451335.0,
|
|
"step": 25045
|
|
},
|
|
{
|
|
"entropy": 5.728225612640381,
|
|
"epoch": 1.9489982493678273,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00046165150353176315,
|
|
"loss": 5.1091,
|
|
"mean_token_accuracy": 0.1952285036444664,
|
|
"num_tokens": 43459520.0,
|
|
"step": 25050
|
|
},
|
|
{
|
|
"entropy": 5.669061183929443,
|
|
"epoch": 1.949387278739545,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004616360253361828,
|
|
"loss": 5.0269,
|
|
"mean_token_accuracy": 0.19924459159374236,
|
|
"num_tokens": 43467695.0,
|
|
"step": 25055
|
|
},
|
|
{
|
|
"entropy": 5.6503904342651365,
|
|
"epoch": 1.9497763081112622,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00046162054430869777,
|
|
"loss": 5.0821,
|
|
"mean_token_accuracy": 0.19960678070783616,
|
|
"num_tokens": 43476161.0,
|
|
"step": 25060
|
|
},
|
|
{
|
|
"entropy": 5.6617834091186525,
|
|
"epoch": 1.95016533748298,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000461605060449543,
|
|
"loss": 4.9942,
|
|
"mean_token_accuracy": 0.19702244251966478,
|
|
"num_tokens": 43485106.0,
|
|
"step": 25065
|
|
},
|
|
{
|
|
"entropy": 5.719282722473144,
|
|
"epoch": 1.9505543668546976,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00046158957375895353,
|
|
"loss": 5.0888,
|
|
"mean_token_accuracy": 0.1899719089269638,
|
|
"num_tokens": 43494232.0,
|
|
"step": 25070
|
|
},
|
|
{
|
|
"entropy": 5.7387049198150635,
|
|
"epoch": 1.950943396226415,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004615740842371643,
|
|
"loss": 4.9995,
|
|
"mean_token_accuracy": 0.2024102047085762,
|
|
"num_tokens": 43502556.0,
|
|
"step": 25075
|
|
},
|
|
{
|
|
"entropy": 5.633154964447021,
|
|
"epoch": 1.9513324255981326,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00046155859188441023,
|
|
"loss": 4.9591,
|
|
"mean_token_accuracy": 0.2012600228190422,
|
|
"num_tokens": 43511594.0,
|
|
"step": 25080
|
|
},
|
|
{
|
|
"entropy": 5.637977743148804,
|
|
"epoch": 1.9517214549698503,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004615430967009265,
|
|
"loss": 5.093,
|
|
"mean_token_accuracy": 0.19673862755298616,
|
|
"num_tokens": 43520532.0,
|
|
"step": 25085
|
|
},
|
|
{
|
|
"entropy": 5.700028991699218,
|
|
"epoch": 1.9521104843415678,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00046152759868694815,
|
|
"loss": 5.1048,
|
|
"mean_token_accuracy": 0.19827057868242265,
|
|
"num_tokens": 43529286.0,
|
|
"step": 25090
|
|
},
|
|
{
|
|
"entropy": 5.72367844581604,
|
|
"epoch": 1.9524995137132852,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004615120978427104,
|
|
"loss": 5.0569,
|
|
"mean_token_accuracy": 0.19502451717853547,
|
|
"num_tokens": 43537983.0,
|
|
"step": 25095
|
|
},
|
|
{
|
|
"entropy": 5.682291316986084,
|
|
"epoch": 1.952888543085003,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004614965941684485,
|
|
"loss": 5.007,
|
|
"mean_token_accuracy": 0.20533406883478164,
|
|
"num_tokens": 43546550.0,
|
|
"step": 25100
|
|
},
|
|
{
|
|
"entropy": 5.7151782512664795,
|
|
"epoch": 1.9532775724567206,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004614810876643975,
|
|
"loss": 5.0969,
|
|
"mean_token_accuracy": 0.2019813746213913,
|
|
"num_tokens": 43555006.0,
|
|
"step": 25105
|
|
},
|
|
{
|
|
"entropy": 5.7196849346160885,
|
|
"epoch": 1.953666601828438,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00046146557833079286,
|
|
"loss": 5.1581,
|
|
"mean_token_accuracy": 0.19339825510978698,
|
|
"num_tokens": 43563925.0,
|
|
"step": 25110
|
|
},
|
|
{
|
|
"entropy": 5.740710496902466,
|
|
"epoch": 1.9540556312001556,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004614500661678698,
|
|
"loss": 5.0532,
|
|
"mean_token_accuracy": 0.19742967337369918,
|
|
"num_tokens": 43572269.0,
|
|
"step": 25115
|
|
},
|
|
{
|
|
"entropy": 5.706193733215332,
|
|
"epoch": 1.9544446605718733,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004614345511758639,
|
|
"loss": 5.0691,
|
|
"mean_token_accuracy": 0.19874023497104645,
|
|
"num_tokens": 43579908.0,
|
|
"step": 25120
|
|
},
|
|
{
|
|
"entropy": 5.659958171844482,
|
|
"epoch": 1.9548336899435907,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00046141903335501034,
|
|
"loss": 5.015,
|
|
"mean_token_accuracy": 0.19763632863759995,
|
|
"num_tokens": 43589328.0,
|
|
"step": 25125
|
|
},
|
|
{
|
|
"entropy": 5.683829927444458,
|
|
"epoch": 1.9552227193153082,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004614035127055447,
|
|
"loss": 5.0596,
|
|
"mean_token_accuracy": 0.20008797943592072,
|
|
"num_tokens": 43597840.0,
|
|
"step": 25130
|
|
},
|
|
{
|
|
"entropy": 5.664583683013916,
|
|
"epoch": 1.955611748687026,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004613879892277024,
|
|
"loss": 5.0113,
|
|
"mean_token_accuracy": 0.20468807816505433,
|
|
"num_tokens": 43606496.0,
|
|
"step": 25135
|
|
},
|
|
{
|
|
"entropy": 5.727624893188477,
|
|
"epoch": 1.9560007780587434,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000461372462921719,
|
|
"loss": 5.0211,
|
|
"mean_token_accuracy": 0.20284863114356994,
|
|
"num_tokens": 43614411.0,
|
|
"step": 25140
|
|
},
|
|
{
|
|
"entropy": 5.612778854370117,
|
|
"epoch": 1.9563898074304609,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004613569337878302,
|
|
"loss": 4.9732,
|
|
"mean_token_accuracy": 0.2039729431271553,
|
|
"num_tokens": 43622842.0,
|
|
"step": 25145
|
|
},
|
|
{
|
|
"entropy": 5.680815315246582,
|
|
"epoch": 1.9567788368021786,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004613414018262715,
|
|
"loss": 5.081,
|
|
"mean_token_accuracy": 0.19264834970235825,
|
|
"num_tokens": 43631535.0,
|
|
"step": 25150
|
|
},
|
|
{
|
|
"entropy": 5.724313402175904,
|
|
"epoch": 1.9571678661738963,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004613258670372786,
|
|
"loss": 5.075,
|
|
"mean_token_accuracy": 0.19988464266061784,
|
|
"num_tokens": 43640197.0,
|
|
"step": 25155
|
|
},
|
|
{
|
|
"entropy": 5.632492113113403,
|
|
"epoch": 1.9575568955456137,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004613103294210873,
|
|
"loss": 5.0124,
|
|
"mean_token_accuracy": 0.2055905982851982,
|
|
"num_tokens": 43648685.0,
|
|
"step": 25160
|
|
},
|
|
{
|
|
"entropy": 5.63893690109253,
|
|
"epoch": 1.9579459249173312,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00046129478897793323,
|
|
"loss": 5.0327,
|
|
"mean_token_accuracy": 0.19616321921348573,
|
|
"num_tokens": 43657526.0,
|
|
"step": 25165
|
|
},
|
|
{
|
|
"entropy": 5.733870220184326,
|
|
"epoch": 1.958334954289049,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00046127924570805236,
|
|
"loss": 5.0521,
|
|
"mean_token_accuracy": 0.20517999231815337,
|
|
"num_tokens": 43666119.0,
|
|
"step": 25170
|
|
},
|
|
{
|
|
"entropy": 5.7572027206420895,
|
|
"epoch": 1.9587239836607664,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004612636996116803,
|
|
"loss": 5.0335,
|
|
"mean_token_accuracy": 0.19316034466028215,
|
|
"num_tokens": 43674634.0,
|
|
"step": 25175
|
|
},
|
|
{
|
|
"entropy": 5.587348175048828,
|
|
"epoch": 1.9591130130324839,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004612481506890532,
|
|
"loss": 4.9749,
|
|
"mean_token_accuracy": 0.2059198796749115,
|
|
"num_tokens": 43683329.0,
|
|
"step": 25180
|
|
},
|
|
{
|
|
"entropy": 5.652428865432739,
|
|
"epoch": 1.9595020424042016,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00046123259894040677,
|
|
"loss": 4.997,
|
|
"mean_token_accuracy": 0.20335134565830232,
|
|
"num_tokens": 43692598.0,
|
|
"step": 25185
|
|
},
|
|
{
|
|
"entropy": 5.6406090259552,
|
|
"epoch": 1.959891071775919,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000461217044365977,
|
|
"loss": 4.9794,
|
|
"mean_token_accuracy": 0.19794338643550874,
|
|
"num_tokens": 43702260.0,
|
|
"step": 25190
|
|
},
|
|
{
|
|
"entropy": 5.741105222702027,
|
|
"epoch": 1.9602801011476365,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004612014869660002,
|
|
"loss": 5.0847,
|
|
"mean_token_accuracy": 0.19749262034893036,
|
|
"num_tokens": 43710003.0,
|
|
"step": 25195
|
|
},
|
|
{
|
|
"entropy": 5.699049425125122,
|
|
"epoch": 1.9606691305193542,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00046118592674071197,
|
|
"loss": 4.9994,
|
|
"mean_token_accuracy": 0.2033785253763199,
|
|
"num_tokens": 43718687.0,
|
|
"step": 25200
|
|
},
|
|
{
|
|
"entropy": 5.628763008117676,
|
|
"epoch": 1.961058159891072,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004611703636903488,
|
|
"loss": 4.9408,
|
|
"mean_token_accuracy": 0.21014311909675598,
|
|
"num_tokens": 43727051.0,
|
|
"step": 25205
|
|
},
|
|
{
|
|
"entropy": 5.652144813537598,
|
|
"epoch": 1.9614471892627894,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004611547978151466,
|
|
"loss": 4.9824,
|
|
"mean_token_accuracy": 0.20597678273916245,
|
|
"num_tokens": 43735572.0,
|
|
"step": 25210
|
|
},
|
|
{
|
|
"entropy": 5.69415807723999,
|
|
"epoch": 1.9618362186345069,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00046113922911534167,
|
|
"loss": 5.0378,
|
|
"mean_token_accuracy": 0.20135923326015473,
|
|
"num_tokens": 43744286.0,
|
|
"step": 25215
|
|
},
|
|
{
|
|
"entropy": 5.683207893371582,
|
|
"epoch": 1.9622252480062246,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004611236575911702,
|
|
"loss": 5.1179,
|
|
"mean_token_accuracy": 0.19950320273637773,
|
|
"num_tokens": 43754042.0,
|
|
"step": 25220
|
|
},
|
|
{
|
|
"entropy": 5.661234331130982,
|
|
"epoch": 1.962614277377942,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00046110808324286844,
|
|
"loss": 4.918,
|
|
"mean_token_accuracy": 0.20831528156995774,
|
|
"num_tokens": 43762031.0,
|
|
"step": 25225
|
|
},
|
|
{
|
|
"entropy": 5.694571018218994,
|
|
"epoch": 1.9630033067496595,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00046109250607067275,
|
|
"loss": 5.0853,
|
|
"mean_token_accuracy": 0.20041561126708984,
|
|
"num_tokens": 43770546.0,
|
|
"step": 25230
|
|
},
|
|
{
|
|
"entropy": 5.674601268768311,
|
|
"epoch": 1.9633923361213772,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004610769260748196,
|
|
"loss": 5.0659,
|
|
"mean_token_accuracy": 0.2015522912144661,
|
|
"num_tokens": 43779918.0,
|
|
"step": 25235
|
|
},
|
|
{
|
|
"entropy": 5.712134981155396,
|
|
"epoch": 1.9637813654930947,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004610613432555451,
|
|
"loss": 5.0424,
|
|
"mean_token_accuracy": 0.19891495406627654,
|
|
"num_tokens": 43788425.0,
|
|
"step": 25240
|
|
},
|
|
{
|
|
"entropy": 5.687092208862305,
|
|
"epoch": 1.9641703948648122,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00046104575761308597,
|
|
"loss": 5.081,
|
|
"mean_token_accuracy": 0.1917901709675789,
|
|
"num_tokens": 43797080.0,
|
|
"step": 25245
|
|
},
|
|
{
|
|
"entropy": 5.659074115753174,
|
|
"epoch": 1.9645594242365298,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004610301691476786,
|
|
"loss": 5.0305,
|
|
"mean_token_accuracy": 0.20866090804338455,
|
|
"num_tokens": 43806026.0,
|
|
"step": 25250
|
|
},
|
|
{
|
|
"entropy": 5.742336416244507,
|
|
"epoch": 1.9649484536082475,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004610145778595594,
|
|
"loss": 5.0714,
|
|
"mean_token_accuracy": 0.20536938160657883,
|
|
"num_tokens": 43814333.0,
|
|
"step": 25255
|
|
},
|
|
{
|
|
"entropy": 5.67303056716919,
|
|
"epoch": 1.965337482979965,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004609989837489651,
|
|
"loss": 4.9999,
|
|
"mean_token_accuracy": 0.20021286457777024,
|
|
"num_tokens": 43823235.0,
|
|
"step": 25260
|
|
},
|
|
{
|
|
"entropy": 5.7027748107910154,
|
|
"epoch": 1.9657265123516825,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00046098338681613234,
|
|
"loss": 5.0472,
|
|
"mean_token_accuracy": 0.2012014254927635,
|
|
"num_tokens": 43832257.0,
|
|
"step": 25265
|
|
},
|
|
{
|
|
"entropy": 5.693505144119262,
|
|
"epoch": 1.9661155417234002,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004609677870612976,
|
|
"loss": 4.9915,
|
|
"mean_token_accuracy": 0.20833290070295335,
|
|
"num_tokens": 43840359.0,
|
|
"step": 25270
|
|
},
|
|
{
|
|
"entropy": 5.621105766296386,
|
|
"epoch": 1.9665045710951177,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004609521844846978,
|
|
"loss": 5.0995,
|
|
"mean_token_accuracy": 0.19711009413003922,
|
|
"num_tokens": 43849374.0,
|
|
"step": 25275
|
|
},
|
|
{
|
|
"entropy": 5.679486989974976,
|
|
"epoch": 1.9668936004668351,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004609365790865695,
|
|
"loss": 5.0904,
|
|
"mean_token_accuracy": 0.19939954429864884,
|
|
"num_tokens": 43857861.0,
|
|
"step": 25280
|
|
},
|
|
{
|
|
"entropy": 5.728759860992431,
|
|
"epoch": 1.9672826298385528,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00046092097086714956,
|
|
"loss": 5.0783,
|
|
"mean_token_accuracy": 0.19538939893245696,
|
|
"num_tokens": 43865964.0,
|
|
"step": 25285
|
|
},
|
|
{
|
|
"entropy": 5.6879819393157955,
|
|
"epoch": 1.9676716592102705,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00046090535982667486,
|
|
"loss": 4.9977,
|
|
"mean_token_accuracy": 0.21127932667732238,
|
|
"num_tokens": 43874434.0,
|
|
"step": 25290
|
|
},
|
|
{
|
|
"entropy": 5.68955807685852,
|
|
"epoch": 1.9680606885819878,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00046088974596538216,
|
|
"loss": 5.0581,
|
|
"mean_token_accuracy": 0.2008354365825653,
|
|
"num_tokens": 43882691.0,
|
|
"step": 25295
|
|
},
|
|
{
|
|
"entropy": 5.7535323143005375,
|
|
"epoch": 1.9684497179537055,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004608741292835085,
|
|
"loss": 5.0778,
|
|
"mean_token_accuracy": 0.19867088049650192,
|
|
"num_tokens": 43890589.0,
|
|
"step": 25300
|
|
},
|
|
{
|
|
"entropy": 5.736508893966675,
|
|
"epoch": 1.9688387473254232,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004608585097812907,
|
|
"loss": 5.0641,
|
|
"mean_token_accuracy": 0.2058962658047676,
|
|
"num_tokens": 43898908.0,
|
|
"step": 25305
|
|
},
|
|
{
|
|
"entropy": 5.715743064880371,
|
|
"epoch": 1.9692277766971407,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004608428874589659,
|
|
"loss": 5.1035,
|
|
"mean_token_accuracy": 0.20044049620628357,
|
|
"num_tokens": 43907640.0,
|
|
"step": 25310
|
|
},
|
|
{
|
|
"entropy": 5.66007809638977,
|
|
"epoch": 1.9696168060688581,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004608272623167711,
|
|
"loss": 4.9666,
|
|
"mean_token_accuracy": 0.20785339325666427,
|
|
"num_tokens": 43915757.0,
|
|
"step": 25315
|
|
},
|
|
{
|
|
"entropy": 5.745566463470459,
|
|
"epoch": 1.9700058354405758,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00046081163435494335,
|
|
"loss": 5.1183,
|
|
"mean_token_accuracy": 0.19631423503160478,
|
|
"num_tokens": 43924910.0,
|
|
"step": 25320
|
|
},
|
|
{
|
|
"entropy": 5.70884256362915,
|
|
"epoch": 1.9703948648122933,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004607960035737198,
|
|
"loss": 5.068,
|
|
"mean_token_accuracy": 0.20402657389640808,
|
|
"num_tokens": 43933122.0,
|
|
"step": 25325
|
|
},
|
|
{
|
|
"entropy": 5.6227329730987545,
|
|
"epoch": 1.9707838941840108,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004607803699733376,
|
|
"loss": 5.03,
|
|
"mean_token_accuracy": 0.20439278334379196,
|
|
"num_tokens": 43941996.0,
|
|
"step": 25330
|
|
},
|
|
{
|
|
"entropy": 5.66074948310852,
|
|
"epoch": 1.9711729235557285,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000460764733554034,
|
|
"loss": 4.9705,
|
|
"mean_token_accuracy": 0.21043404787778855,
|
|
"num_tokens": 43950637.0,
|
|
"step": 25335
|
|
},
|
|
{
|
|
"entropy": 5.715720176696777,
|
|
"epoch": 1.9715619529274462,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00046074909431604623,
|
|
"loss": 5.0595,
|
|
"mean_token_accuracy": 0.1962682917714119,
|
|
"num_tokens": 43959252.0,
|
|
"step": 25340
|
|
},
|
|
{
|
|
"entropy": 5.685758447647094,
|
|
"epoch": 1.9719509822991634,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004607334522596116,
|
|
"loss": 5.0253,
|
|
"mean_token_accuracy": 0.1940817043185234,
|
|
"num_tokens": 43968391.0,
|
|
"step": 25345
|
|
},
|
|
{
|
|
"entropy": 5.683940839767456,
|
|
"epoch": 1.9723400116708811,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004607178073849675,
|
|
"loss": 4.9678,
|
|
"mean_token_accuracy": 0.20793296098709108,
|
|
"num_tokens": 43977066.0,
|
|
"step": 25350
|
|
},
|
|
{
|
|
"entropy": 5.701573896408081,
|
|
"epoch": 1.9727290410425988,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004607021596923512,
|
|
"loss": 5.0307,
|
|
"mean_token_accuracy": 0.2119439348578453,
|
|
"num_tokens": 43985072.0,
|
|
"step": 25355
|
|
},
|
|
{
|
|
"entropy": 5.7974132061004635,
|
|
"epoch": 1.9731180704143163,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004606865091820003,
|
|
"loss": 5.2184,
|
|
"mean_token_accuracy": 0.18994032144546508,
|
|
"num_tokens": 43993321.0,
|
|
"step": 25360
|
|
},
|
|
{
|
|
"entropy": 5.607664346694946,
|
|
"epoch": 1.9735070997860338,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004606708558541521,
|
|
"loss": 4.9082,
|
|
"mean_token_accuracy": 0.21403990387916566,
|
|
"num_tokens": 44002476.0,
|
|
"step": 25365
|
|
},
|
|
{
|
|
"entropy": 5.690027379989624,
|
|
"epoch": 1.9738961291577515,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004606551997090442,
|
|
"loss": 5.1128,
|
|
"mean_token_accuracy": 0.19725189507007598,
|
|
"num_tokens": 44011790.0,
|
|
"step": 25370
|
|
},
|
|
{
|
|
"entropy": 5.662188100814819,
|
|
"epoch": 1.974285158529469,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004606395407469141,
|
|
"loss": 5.0115,
|
|
"mean_token_accuracy": 0.1975963830947876,
|
|
"num_tokens": 44021086.0,
|
|
"step": 25375
|
|
},
|
|
{
|
|
"entropy": 5.64773006439209,
|
|
"epoch": 1.9746741879011864,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004606238789679995,
|
|
"loss": 4.9785,
|
|
"mean_token_accuracy": 0.20605355650186538,
|
|
"num_tokens": 44029789.0,
|
|
"step": 25380
|
|
},
|
|
{
|
|
"entropy": 5.6224274158477785,
|
|
"epoch": 1.9750632172729041,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004606082143725381,
|
|
"loss": 5.0156,
|
|
"mean_token_accuracy": 0.19660866856575013,
|
|
"num_tokens": 44039508.0,
|
|
"step": 25385
|
|
},
|
|
{
|
|
"entropy": 5.671589279174805,
|
|
"epoch": 1.9754522466446218,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004605925469607673,
|
|
"loss": 5.0206,
|
|
"mean_token_accuracy": 0.2061230480670929,
|
|
"num_tokens": 44048464.0,
|
|
"step": 25390
|
|
},
|
|
{
|
|
"entropy": 5.790804386138916,
|
|
"epoch": 1.975841276016339,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00046057687673292506,
|
|
"loss": 5.1257,
|
|
"mean_token_accuracy": 0.19666651785373687,
|
|
"num_tokens": 44057613.0,
|
|
"step": 25395
|
|
},
|
|
{
|
|
"entropy": 5.652014827728271,
|
|
"epoch": 1.9762303053880568,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00046056120368924907,
|
|
"loss": 4.9155,
|
|
"mean_token_accuracy": 0.2143044278025627,
|
|
"num_tokens": 44066334.0,
|
|
"step": 25400
|
|
},
|
|
{
|
|
"entropy": 5.678717136383057,
|
|
"epoch": 1.9766193347597745,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004605455278299772,
|
|
"loss": 5.1578,
|
|
"mean_token_accuracy": 0.19586342126131057,
|
|
"num_tokens": 44076355.0,
|
|
"step": 25405
|
|
},
|
|
{
|
|
"entropy": 5.734120035171509,
|
|
"epoch": 1.977008364131492,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004605298491553472,
|
|
"loss": 5.0873,
|
|
"mean_token_accuracy": 0.19350172579288483,
|
|
"num_tokens": 44084445.0,
|
|
"step": 25410
|
|
},
|
|
{
|
|
"entropy": 5.709806442260742,
|
|
"epoch": 1.9773973935032094,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004605141676655971,
|
|
"loss": 5.0202,
|
|
"mean_token_accuracy": 0.2078096255660057,
|
|
"num_tokens": 44093711.0,
|
|
"step": 25415
|
|
},
|
|
{
|
|
"entropy": 5.675356197357178,
|
|
"epoch": 1.9777864228749271,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00046049848336096485,
|
|
"loss": 5.0339,
|
|
"mean_token_accuracy": 0.1947970747947693,
|
|
"num_tokens": 44102647.0,
|
|
"step": 25420
|
|
},
|
|
{
|
|
"entropy": 5.694596862792968,
|
|
"epoch": 1.9781754522466446,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004604827962416883,
|
|
"loss": 4.9447,
|
|
"mean_token_accuracy": 0.20636706054210663,
|
|
"num_tokens": 44110661.0,
|
|
"step": 25425
|
|
},
|
|
{
|
|
"entropy": 5.759284353256225,
|
|
"epoch": 1.978564481618362,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004604671063080055,
|
|
"loss": 5.1851,
|
|
"mean_token_accuracy": 0.18675361275672914,
|
|
"num_tokens": 44119441.0,
|
|
"step": 25430
|
|
},
|
|
{
|
|
"entropy": 5.672123956680298,
|
|
"epoch": 1.9789535109900798,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004604514135601546,
|
|
"loss": 4.9747,
|
|
"mean_token_accuracy": 0.20359019935131073,
|
|
"num_tokens": 44127774.0,
|
|
"step": 25435
|
|
},
|
|
{
|
|
"entropy": 5.746460390090943,
|
|
"epoch": 1.9793425403617975,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004604357179983736,
|
|
"loss": 5.2082,
|
|
"mean_token_accuracy": 0.1801075428724289,
|
|
"num_tokens": 44137075.0,
|
|
"step": 25440
|
|
},
|
|
{
|
|
"entropy": 5.638615465164184,
|
|
"epoch": 1.9797315697335147,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004604200196229009,
|
|
"loss": 4.9598,
|
|
"mean_token_accuracy": 0.20288174152374266,
|
|
"num_tokens": 44145647.0,
|
|
"step": 25445
|
|
},
|
|
{
|
|
"entropy": 5.658754348754883,
|
|
"epoch": 1.9801205991052324,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004604043184339744,
|
|
"loss": 4.9156,
|
|
"mean_token_accuracy": 0.20674976706504822,
|
|
"num_tokens": 44154267.0,
|
|
"step": 25450
|
|
},
|
|
{
|
|
"entropy": 5.6858209609985355,
|
|
"epoch": 1.9805096284769501,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004603886144318325,
|
|
"loss": 5.0673,
|
|
"mean_token_accuracy": 0.1997123286128044,
|
|
"num_tokens": 44162532.0,
|
|
"step": 25455
|
|
},
|
|
{
|
|
"entropy": 5.721542549133301,
|
|
"epoch": 1.9808986578486676,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00046037290761671346,
|
|
"loss": 5.0591,
|
|
"mean_token_accuracy": 0.20254214704036713,
|
|
"num_tokens": 44171218.0,
|
|
"step": 25460
|
|
},
|
|
{
|
|
"entropy": 5.6671037673950195,
|
|
"epoch": 1.981287687220385,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004603571979888556,
|
|
"loss": 5.1139,
|
|
"mean_token_accuracy": 0.1940985918045044,
|
|
"num_tokens": 44180189.0,
|
|
"step": 25465
|
|
},
|
|
{
|
|
"entropy": 5.688149785995483,
|
|
"epoch": 1.9816767165921028,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004603414855484973,
|
|
"loss": 4.9742,
|
|
"mean_token_accuracy": 0.20860636681318284,
|
|
"num_tokens": 44189048.0,
|
|
"step": 25470
|
|
},
|
|
{
|
|
"entropy": 5.699688911437988,
|
|
"epoch": 1.9820657459638202,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000460325770295877,
|
|
"loss": 5.0603,
|
|
"mean_token_accuracy": 0.19870493412017823,
|
|
"num_tokens": 44197995.0,
|
|
"step": 25475
|
|
},
|
|
{
|
|
"entropy": 5.722847890853882,
|
|
"epoch": 1.9824547753355377,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00046031005223123297,
|
|
"loss": 5.166,
|
|
"mean_token_accuracy": 0.18669108152389527,
|
|
"num_tokens": 44207042.0,
|
|
"step": 25480
|
|
},
|
|
{
|
|
"entropy": 5.6642577171325685,
|
|
"epoch": 1.9828438047072554,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000460294331354804,
|
|
"loss": 4.9599,
|
|
"mean_token_accuracy": 0.21300921142101287,
|
|
"num_tokens": 44214678.0,
|
|
"step": 25485
|
|
},
|
|
{
|
|
"entropy": 5.617475605010986,
|
|
"epoch": 1.983232834078973,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004602786076668283,
|
|
"loss": 4.9891,
|
|
"mean_token_accuracy": 0.20738008320331575,
|
|
"num_tokens": 44223752.0,
|
|
"step": 25490
|
|
},
|
|
{
|
|
"entropy": 5.706676864624024,
|
|
"epoch": 1.9836218634506906,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00046026288116754477,
|
|
"loss": 5.0557,
|
|
"mean_token_accuracy": 0.19884685426950455,
|
|
"num_tokens": 44232109.0,
|
|
"step": 25495
|
|
},
|
|
{
|
|
"entropy": 5.778555107116699,
|
|
"epoch": 1.984010892822408,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004602471518571919,
|
|
"loss": 5.1791,
|
|
"mean_token_accuracy": 0.187676078081131,
|
|
"num_tokens": 44239957.0,
|
|
"step": 25500
|
|
},
|
|
{
|
|
"entropy": 5.767152786254883,
|
|
"epoch": 1.9843999221941258,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004602314197360083,
|
|
"loss": 5.0474,
|
|
"mean_token_accuracy": 0.20314751118421553,
|
|
"num_tokens": 44248582.0,
|
|
"step": 25505
|
|
},
|
|
{
|
|
"entropy": 5.757918500900269,
|
|
"epoch": 1.9847889515658432,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004602156848042328,
|
|
"loss": 5.0455,
|
|
"mean_token_accuracy": 0.19783039391040802,
|
|
"num_tokens": 44256711.0,
|
|
"step": 25510
|
|
},
|
|
{
|
|
"entropy": 5.6873878002166744,
|
|
"epoch": 1.9851779809375607,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000460199947062104,
|
|
"loss": 5.0179,
|
|
"mean_token_accuracy": 0.20318072140216828,
|
|
"num_tokens": 44265140.0,
|
|
"step": 25515
|
|
},
|
|
{
|
|
"entropy": 5.737044477462769,
|
|
"epoch": 1.9855670103092784,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00046018420650986074,
|
|
"loss": 5.0187,
|
|
"mean_token_accuracy": 0.19934685230255128,
|
|
"num_tokens": 44273560.0,
|
|
"step": 25520
|
|
},
|
|
{
|
|
"entropy": 5.635279893875122,
|
|
"epoch": 1.9859560396809959,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000460168463147742,
|
|
"loss": 4.9339,
|
|
"mean_token_accuracy": 0.20691336840391159,
|
|
"num_tokens": 44282155.0,
|
|
"step": 25525
|
|
},
|
|
{
|
|
"entropy": 5.690180063247681,
|
|
"epoch": 1.9863450690527134,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004601527169759865,
|
|
"loss": 4.9728,
|
|
"mean_token_accuracy": 0.20464201271533966,
|
|
"num_tokens": 44291237.0,
|
|
"step": 25530
|
|
},
|
|
{
|
|
"entropy": 5.681266117095947,
|
|
"epoch": 1.986734098424431,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004601369679948333,
|
|
"loss": 5.0057,
|
|
"mean_token_accuracy": 0.19905872792005538,
|
|
"num_tokens": 44299886.0,
|
|
"step": 25535
|
|
},
|
|
{
|
|
"entropy": 5.692330741882325,
|
|
"epoch": 1.9871231277961487,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00046012121620452127,
|
|
"loss": 5.1277,
|
|
"mean_token_accuracy": 0.20163533538579942,
|
|
"num_tokens": 44308247.0,
|
|
"step": 25540
|
|
},
|
|
{
|
|
"entropy": 5.717720460891724,
|
|
"epoch": 1.9875121571678662,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004601054616052893,
|
|
"loss": 5.0096,
|
|
"mean_token_accuracy": 0.2031998246908188,
|
|
"num_tokens": 44316301.0,
|
|
"step": 25545
|
|
},
|
|
{
|
|
"entropy": 5.810669040679931,
|
|
"epoch": 1.9879011865395837,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00046008970419737674,
|
|
"loss": 5.1456,
|
|
"mean_token_accuracy": 0.18856994509696962,
|
|
"num_tokens": 44324758.0,
|
|
"step": 25550
|
|
},
|
|
{
|
|
"entropy": 5.75964126586914,
|
|
"epoch": 1.9882902159113014,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004600739439810225,
|
|
"loss": 5.1349,
|
|
"mean_token_accuracy": 0.1874127745628357,
|
|
"num_tokens": 44333139.0,
|
|
"step": 25555
|
|
},
|
|
{
|
|
"entropy": 5.744812822341919,
|
|
"epoch": 1.9886792452830189,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00046005818095646564,
|
|
"loss": 5.0819,
|
|
"mean_token_accuracy": 0.2012840449810028,
|
|
"num_tokens": 44341992.0,
|
|
"step": 25560
|
|
},
|
|
{
|
|
"entropy": 5.684985208511352,
|
|
"epoch": 1.9890682746547363,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00046004241512394544,
|
|
"loss": 5.051,
|
|
"mean_token_accuracy": 0.19588932543992996,
|
|
"num_tokens": 44350947.0,
|
|
"step": 25565
|
|
},
|
|
{
|
|
"entropy": 5.678867483139038,
|
|
"epoch": 1.989457304026454,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004600266464837012,
|
|
"loss": 5.0154,
|
|
"mean_token_accuracy": 0.2034503012895584,
|
|
"num_tokens": 44358934.0,
|
|
"step": 25570
|
|
},
|
|
{
|
|
"entropy": 5.663506078720093,
|
|
"epoch": 1.9898463333981715,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004600108750359721,
|
|
"loss": 4.9743,
|
|
"mean_token_accuracy": 0.20285267978906632,
|
|
"num_tokens": 44367117.0,
|
|
"step": 25575
|
|
},
|
|
{
|
|
"entropy": 5.7010821342468265,
|
|
"epoch": 1.990235362769889,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00045999510078099736,
|
|
"loss": 5.0393,
|
|
"mean_token_accuracy": 0.19596458971500397,
|
|
"num_tokens": 44375591.0,
|
|
"step": 25580
|
|
},
|
|
{
|
|
"entropy": 5.6329389095306395,
|
|
"epoch": 1.9906243921416067,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00045997932371901645,
|
|
"loss": 4.9312,
|
|
"mean_token_accuracy": 0.21049901992082595,
|
|
"num_tokens": 44384602.0,
|
|
"step": 25585
|
|
},
|
|
{
|
|
"entropy": 5.609166431427002,
|
|
"epoch": 1.9910134215133244,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004599635438502687,
|
|
"loss": 4.9271,
|
|
"mean_token_accuracy": 0.21531407684087753,
|
|
"num_tokens": 44393451.0,
|
|
"step": 25590
|
|
},
|
|
{
|
|
"entropy": 5.630014276504516,
|
|
"epoch": 1.9914024508850419,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00045994776117499363,
|
|
"loss": 4.9728,
|
|
"mean_token_accuracy": 0.2018023505806923,
|
|
"num_tokens": 44401638.0,
|
|
"step": 25595
|
|
},
|
|
{
|
|
"entropy": 5.661988639831543,
|
|
"epoch": 1.9917914802567593,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00045993197569343063,
|
|
"loss": 5.001,
|
|
"mean_token_accuracy": 0.20364686995744705,
|
|
"num_tokens": 44410337.0,
|
|
"step": 25600
|
|
},
|
|
{
|
|
"entropy": 5.681255960464478,
|
|
"epoch": 1.992180509628477,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00045991618740581926,
|
|
"loss": 5.0636,
|
|
"mean_token_accuracy": 0.2019265279173851,
|
|
"num_tokens": 44418178.0,
|
|
"step": 25605
|
|
},
|
|
{
|
|
"entropy": 5.740093803405761,
|
|
"epoch": 1.9925695390001945,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004599003963123991,
|
|
"loss": 5.0764,
|
|
"mean_token_accuracy": 0.19247499257326126,
|
|
"num_tokens": 44427056.0,
|
|
"step": 25610
|
|
},
|
|
{
|
|
"entropy": 5.769051361083984,
|
|
"epoch": 1.992958568371912,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00045988460241340966,
|
|
"loss": 5.0381,
|
|
"mean_token_accuracy": 0.20148291140794755,
|
|
"num_tokens": 44434687.0,
|
|
"step": 25615
|
|
},
|
|
{
|
|
"entropy": 5.699707174301148,
|
|
"epoch": 1.9933475977436297,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00045986880570909075,
|
|
"loss": 5.0328,
|
|
"mean_token_accuracy": 0.20362118631601334,
|
|
"num_tokens": 44442763.0,
|
|
"step": 25620
|
|
},
|
|
{
|
|
"entropy": 5.558286046981811,
|
|
"epoch": 1.9937366271153472,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00045985300619968186,
|
|
"loss": 4.9175,
|
|
"mean_token_accuracy": 0.2075865775346756,
|
|
"num_tokens": 44451850.0,
|
|
"step": 25625
|
|
},
|
|
{
|
|
"entropy": 5.602642250061035,
|
|
"epoch": 1.9941256564870646,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00045983720388542286,
|
|
"loss": 4.9737,
|
|
"mean_token_accuracy": 0.21108553558588028,
|
|
"num_tokens": 44459915.0,
|
|
"step": 25630
|
|
},
|
|
{
|
|
"entropy": 5.606112337112426,
|
|
"epoch": 1.9945146858587823,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004598213987665535,
|
|
"loss": 5.036,
|
|
"mean_token_accuracy": 0.20402218252420426,
|
|
"num_tokens": 44469252.0,
|
|
"step": 25635
|
|
},
|
|
{
|
|
"entropy": 5.778771114349365,
|
|
"epoch": 1.9949037152305,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00045980559084331354,
|
|
"loss": 5.1011,
|
|
"mean_token_accuracy": 0.19799538552761078,
|
|
"num_tokens": 44477748.0,
|
|
"step": 25640
|
|
},
|
|
{
|
|
"entropy": 5.662566614151001,
|
|
"epoch": 1.9952927446022175,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000459789780115943,
|
|
"loss": 5.0422,
|
|
"mean_token_accuracy": 0.19278250634670258,
|
|
"num_tokens": 44485796.0,
|
|
"step": 25645
|
|
},
|
|
{
|
|
"entropy": 5.611935758590699,
|
|
"epoch": 1.995681773973935,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00045977396658468156,
|
|
"loss": 5.0482,
|
|
"mean_token_accuracy": 0.19376108795404434,
|
|
"num_tokens": 44494604.0,
|
|
"step": 25650
|
|
},
|
|
{
|
|
"entropy": 5.655222320556641,
|
|
"epoch": 1.9960708033456527,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004597581502497693,
|
|
"loss": 5.0303,
|
|
"mean_token_accuracy": 0.19579687863588333,
|
|
"num_tokens": 44503728.0,
|
|
"step": 25655
|
|
},
|
|
{
|
|
"entropy": 5.707696533203125,
|
|
"epoch": 1.9964598327173702,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004597423311114462,
|
|
"loss": 5.0072,
|
|
"mean_token_accuracy": 0.20464685261249543,
|
|
"num_tokens": 44512201.0,
|
|
"step": 25660
|
|
},
|
|
{
|
|
"entropy": 5.715597152709961,
|
|
"epoch": 1.9968488620890876,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004597265091699522,
|
|
"loss": 5.036,
|
|
"mean_token_accuracy": 0.19904591143131256,
|
|
"num_tokens": 44520122.0,
|
|
"step": 25665
|
|
},
|
|
{
|
|
"entropy": 5.605073499679565,
|
|
"epoch": 1.9972378914608053,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004597106844255276,
|
|
"loss": 5.038,
|
|
"mean_token_accuracy": 0.19938948899507522,
|
|
"num_tokens": 44528928.0,
|
|
"step": 25670
|
|
},
|
|
{
|
|
"entropy": 5.731636619567871,
|
|
"epoch": 1.9976269208325228,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00045969485687841227,
|
|
"loss": 5.1668,
|
|
"mean_token_accuracy": 0.19572292417287826,
|
|
"num_tokens": 44537330.0,
|
|
"step": 25675
|
|
},
|
|
{
|
|
"entropy": 5.720711374282837,
|
|
"epoch": 1.9980159502042403,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00045967902652884645,
|
|
"loss": 5.0309,
|
|
"mean_token_accuracy": 0.20138122886419296,
|
|
"num_tokens": 44545748.0,
|
|
"step": 25680
|
|
},
|
|
{
|
|
"entropy": 5.6698570728302,
|
|
"epoch": 1.998404979575958,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004596631933770704,
|
|
"loss": 5.1346,
|
|
"mean_token_accuracy": 0.19554666429758072,
|
|
"num_tokens": 44554562.0,
|
|
"step": 25685
|
|
},
|
|
{
|
|
"entropy": 5.651662397384643,
|
|
"epoch": 1.9987940089476757,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00045964735742332427,
|
|
"loss": 4.9729,
|
|
"mean_token_accuracy": 0.20400928407907487,
|
|
"num_tokens": 44563544.0,
|
|
"step": 25690
|
|
},
|
|
{
|
|
"entropy": 5.717379760742188,
|
|
"epoch": 1.9991830383193931,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004596315186678484,
|
|
"loss": 5.0522,
|
|
"mean_token_accuracy": 0.1999122068285942,
|
|
"num_tokens": 44571179.0,
|
|
"step": 25695
|
|
},
|
|
{
|
|
"entropy": 5.720243692398071,
|
|
"epoch": 1.9995720676911106,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00045961567711088307,
|
|
"loss": 5.0894,
|
|
"mean_token_accuracy": 0.20062737315893173,
|
|
"num_tokens": 44580237.0,
|
|
"step": 25700
|
|
},
|
|
{
|
|
"entropy": 5.675827741622925,
|
|
"epoch": 1.9999610970628283,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00045959983275266873,
|
|
"loss": 5.0272,
|
|
"mean_token_accuracy": 0.20159684717655182,
|
|
"num_tokens": 44588362.0,
|
|
"step": 25705
|
|
},
|
|
{
|
|
"entropy": 5.671978367699517,
|
|
"epoch": 2.000311223497374,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00045958398559344573,
|
|
"loss": 4.9589,
|
|
"mean_token_accuracy": 0.20681650274329716,
|
|
"num_tokens": 44596037.0,
|
|
"step": 25710
|
|
},
|
|
{
|
|
"entropy": 5.734713172912597,
|
|
"epoch": 2.0007002528690916,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00045956813563345454,
|
|
"loss": 5.0188,
|
|
"mean_token_accuracy": 0.20624375194311143,
|
|
"num_tokens": 44604913.0,
|
|
"step": 25715
|
|
},
|
|
{
|
|
"entropy": 5.71753339767456,
|
|
"epoch": 2.0010892822408093,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004595522828729357,
|
|
"loss": 5.0555,
|
|
"mean_token_accuracy": 0.20264316648244857,
|
|
"num_tokens": 44613523.0,
|
|
"step": 25720
|
|
},
|
|
{
|
|
"entropy": 5.654740905761718,
|
|
"epoch": 2.0014783116125265,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004595364273121296,
|
|
"loss": 4.8569,
|
|
"mean_token_accuracy": 0.21545921862125397,
|
|
"num_tokens": 44622259.0,
|
|
"step": 25725
|
|
},
|
|
{
|
|
"entropy": 5.616589832305908,
|
|
"epoch": 2.0018673409842442,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004595205689512771,
|
|
"loss": 4.9408,
|
|
"mean_token_accuracy": 0.2076679602265358,
|
|
"num_tokens": 44630793.0,
|
|
"step": 25730
|
|
},
|
|
{
|
|
"entropy": 5.678444528579712,
|
|
"epoch": 2.002256370355962,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00045950470779061855,
|
|
"loss": 4.9575,
|
|
"mean_token_accuracy": 0.20859505981206894,
|
|
"num_tokens": 44638986.0,
|
|
"step": 25735
|
|
},
|
|
{
|
|
"entropy": 5.705001640319824,
|
|
"epoch": 2.0026453997276796,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00045948884383039475,
|
|
"loss": 5.0253,
|
|
"mean_token_accuracy": 0.19875845611095427,
|
|
"num_tokens": 44647491.0,
|
|
"step": 25740
|
|
},
|
|
{
|
|
"entropy": 5.613849735260009,
|
|
"epoch": 2.003034429099397,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00045947297707084637,
|
|
"loss": 4.9496,
|
|
"mean_token_accuracy": 0.2067682147026062,
|
|
"num_tokens": 44655431.0,
|
|
"step": 25745
|
|
},
|
|
{
|
|
"entropy": 5.634070634841919,
|
|
"epoch": 2.0034234584711146,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004594571075122142,
|
|
"loss": 4.9621,
|
|
"mean_token_accuracy": 0.20248010754585266,
|
|
"num_tokens": 44664398.0,
|
|
"step": 25750
|
|
},
|
|
{
|
|
"entropy": 5.693981504440307,
|
|
"epoch": 2.0038124878428323,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00045944123515473905,
|
|
"loss": 4.9518,
|
|
"mean_token_accuracy": 0.2038433238863945,
|
|
"num_tokens": 44673372.0,
|
|
"step": 25755
|
|
},
|
|
{
|
|
"entropy": 5.611620903015137,
|
|
"epoch": 2.0042015172145495,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00045942535999866175,
|
|
"loss": 4.8688,
|
|
"mean_token_accuracy": 0.21319093853235244,
|
|
"num_tokens": 44681736.0,
|
|
"step": 25760
|
|
},
|
|
{
|
|
"entropy": 5.6853429794311525,
|
|
"epoch": 2.0045905465862672,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004594094820442231,
|
|
"loss": 5.0136,
|
|
"mean_token_accuracy": 0.20086731463670732,
|
|
"num_tokens": 44691858.0,
|
|
"step": 25765
|
|
},
|
|
{
|
|
"entropy": 5.746147680282593,
|
|
"epoch": 2.004979575957985,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.000459393601291664,
|
|
"loss": 5.0466,
|
|
"mean_token_accuracy": 0.19366568475961685,
|
|
"num_tokens": 44701002.0,
|
|
"step": 25770
|
|
},
|
|
{
|
|
"entropy": 5.686776065826416,
|
|
"epoch": 2.005368605329702,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00045937771774122563,
|
|
"loss": 4.9282,
|
|
"mean_token_accuracy": 0.21595702320337296,
|
|
"num_tokens": 44709158.0,
|
|
"step": 25775
|
|
},
|
|
{
|
|
"entropy": 5.638172149658203,
|
|
"epoch": 2.00575763470142,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004593618313931488,
|
|
"loss": 4.9622,
|
|
"mean_token_accuracy": 0.20781536400318146,
|
|
"num_tokens": 44717495.0,
|
|
"step": 25780
|
|
},
|
|
{
|
|
"entropy": 5.687889480590821,
|
|
"epoch": 2.0061466640731376,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00045934594224767463,
|
|
"loss": 4.9503,
|
|
"mean_token_accuracy": 0.20594877898693084,
|
|
"num_tokens": 44726040.0,
|
|
"step": 25785
|
|
},
|
|
{
|
|
"entropy": 5.675553703308106,
|
|
"epoch": 2.0065356934448553,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00045933005030504424,
|
|
"loss": 4.9884,
|
|
"mean_token_accuracy": 0.1997014030814171,
|
|
"num_tokens": 44735098.0,
|
|
"step": 25790
|
|
},
|
|
{
|
|
"entropy": 5.649155521392823,
|
|
"epoch": 2.0069247228165725,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00045931415556549863,
|
|
"loss": 4.9724,
|
|
"mean_token_accuracy": 0.20108432918787003,
|
|
"num_tokens": 44743764.0,
|
|
"step": 25795
|
|
},
|
|
{
|
|
"entropy": 5.643327617645264,
|
|
"epoch": 2.0073137521882902,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004592982580292792,
|
|
"loss": 4.8748,
|
|
"mean_token_accuracy": 0.20692960619926454,
|
|
"num_tokens": 44751554.0,
|
|
"step": 25800
|
|
},
|
|
{
|
|
"entropy": 5.734205865859986,
|
|
"epoch": 2.007702781560008,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00045928235769662697,
|
|
"loss": 5.0574,
|
|
"mean_token_accuracy": 0.19601832032203675,
|
|
"num_tokens": 44760158.0,
|
|
"step": 25805
|
|
},
|
|
{
|
|
"entropy": 5.66917781829834,
|
|
"epoch": 2.008091810931725,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00045926645456778327,
|
|
"loss": 4.9414,
|
|
"mean_token_accuracy": 0.20913155674934386,
|
|
"num_tokens": 44769209.0,
|
|
"step": 25810
|
|
},
|
|
{
|
|
"entropy": 5.6618571281433105,
|
|
"epoch": 2.008480840303443,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00045925054864298946,
|
|
"loss": 4.9889,
|
|
"mean_token_accuracy": 0.20589143335819243,
|
|
"num_tokens": 44777991.0,
|
|
"step": 25815
|
|
},
|
|
{
|
|
"entropy": 5.707407665252686,
|
|
"epoch": 2.0088698696751606,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00045923463992248684,
|
|
"loss": 5.0302,
|
|
"mean_token_accuracy": 0.19930059015750884,
|
|
"num_tokens": 44786492.0,
|
|
"step": 25820
|
|
},
|
|
{
|
|
"entropy": 5.710167074203492,
|
|
"epoch": 2.009258899046878,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00045921872840651675,
|
|
"loss": 5.0604,
|
|
"mean_token_accuracy": 0.20184142887592316,
|
|
"num_tokens": 44795021.0,
|
|
"step": 25825
|
|
},
|
|
{
|
|
"entropy": 5.6584185600280765,
|
|
"epoch": 2.0096479284185955,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00045920281409532064,
|
|
"loss": 4.9671,
|
|
"mean_token_accuracy": 0.20276207625865936,
|
|
"num_tokens": 44803267.0,
|
|
"step": 25830
|
|
},
|
|
{
|
|
"entropy": 5.714813375473023,
|
|
"epoch": 2.010036957790313,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004591868969891401,
|
|
"loss": 5.0269,
|
|
"mean_token_accuracy": 0.20033709108829498,
|
|
"num_tokens": 44811954.0,
|
|
"step": 25835
|
|
},
|
|
{
|
|
"entropy": 5.643784618377685,
|
|
"epoch": 2.010425987162031,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004591709770882165,
|
|
"loss": 4.8838,
|
|
"mean_token_accuracy": 0.2096843644976616,
|
|
"num_tokens": 44820748.0,
|
|
"step": 25840
|
|
},
|
|
{
|
|
"entropy": 5.6935258388519285,
|
|
"epoch": 2.010815016533748,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004591550543927915,
|
|
"loss": 5.0806,
|
|
"mean_token_accuracy": 0.19925837367773055,
|
|
"num_tokens": 44829400.0,
|
|
"step": 25845
|
|
},
|
|
{
|
|
"entropy": 5.733881187438965,
|
|
"epoch": 2.011204045905466,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004591391289031067,
|
|
"loss": 4.997,
|
|
"mean_token_accuracy": 0.2024434193968773,
|
|
"num_tokens": 44838663.0,
|
|
"step": 25850
|
|
},
|
|
{
|
|
"entropy": 5.700822496414185,
|
|
"epoch": 2.0115930752771836,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004591232006194036,
|
|
"loss": 4.9219,
|
|
"mean_token_accuracy": 0.21281079053878785,
|
|
"num_tokens": 44847365.0,
|
|
"step": 25855
|
|
},
|
|
{
|
|
"entropy": 5.696553325653076,
|
|
"epoch": 2.011982104648901,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00045910726954192404,
|
|
"loss": 4.9795,
|
|
"mean_token_accuracy": 0.20659883618354796,
|
|
"num_tokens": 44856093.0,
|
|
"step": 25860
|
|
},
|
|
{
|
|
"entropy": 5.61371603012085,
|
|
"epoch": 2.0123711340206185,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004590913356709097,
|
|
"loss": 4.9443,
|
|
"mean_token_accuracy": 0.20985369086265565,
|
|
"num_tokens": 44865116.0,
|
|
"step": 25865
|
|
},
|
|
{
|
|
"entropy": 5.654669570922851,
|
|
"epoch": 2.012760163392336,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00045907539900660237,
|
|
"loss": 5.0218,
|
|
"mean_token_accuracy": 0.20194179862737655,
|
|
"num_tokens": 44874037.0,
|
|
"step": 25870
|
|
},
|
|
{
|
|
"entropy": 5.649487161636353,
|
|
"epoch": 2.013149192764054,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004590594595492438,
|
|
"loss": 4.8503,
|
|
"mean_token_accuracy": 0.21097995042800904,
|
|
"num_tokens": 44882603.0,
|
|
"step": 25875
|
|
},
|
|
{
|
|
"entropy": 5.667109632492066,
|
|
"epoch": 2.013538222135771,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00045904351729907593,
|
|
"loss": 4.8998,
|
|
"mean_token_accuracy": 0.21082854717969896,
|
|
"num_tokens": 44890645.0,
|
|
"step": 25880
|
|
},
|
|
{
|
|
"entropy": 5.732386732101441,
|
|
"epoch": 2.013927251507489,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00045902757225634066,
|
|
"loss": 5.0209,
|
|
"mean_token_accuracy": 0.20473106652498246,
|
|
"num_tokens": 44898972.0,
|
|
"step": 25885
|
|
},
|
|
{
|
|
"entropy": 5.632081985473633,
|
|
"epoch": 2.0143162808792066,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004590116244212799,
|
|
"loss": 5.0007,
|
|
"mean_token_accuracy": 0.21055980771780014,
|
|
"num_tokens": 44907427.0,
|
|
"step": 25890
|
|
},
|
|
{
|
|
"entropy": 5.697575187683105,
|
|
"epoch": 2.014705310250924,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004589956737941355,
|
|
"loss": 5.0422,
|
|
"mean_token_accuracy": 0.19956227391958237,
|
|
"num_tokens": 44916465.0,
|
|
"step": 25895
|
|
},
|
|
{
|
|
"entropy": 5.7018509864807125,
|
|
"epoch": 2.0150943396226415,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004589797203751497,
|
|
"loss": 4.959,
|
|
"mean_token_accuracy": 0.21271492838859557,
|
|
"num_tokens": 44925102.0,
|
|
"step": 25900
|
|
},
|
|
{
|
|
"entropy": 5.651805591583252,
|
|
"epoch": 2.015483368994359,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004589637641645645,
|
|
"loss": 4.9309,
|
|
"mean_token_accuracy": 0.21065156310796737,
|
|
"num_tokens": 44933061.0,
|
|
"step": 25905
|
|
},
|
|
{
|
|
"entropy": 5.5902876377105715,
|
|
"epoch": 2.0158723983660765,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00045894780516262193,
|
|
"loss": 4.9805,
|
|
"mean_token_accuracy": 0.20562071949243546,
|
|
"num_tokens": 44942342.0,
|
|
"step": 25910
|
|
},
|
|
{
|
|
"entropy": 5.677871322631836,
|
|
"epoch": 2.016261427737794,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004589318433695642,
|
|
"loss": 4.9725,
|
|
"mean_token_accuracy": 0.2132783353328705,
|
|
"num_tokens": 44951163.0,
|
|
"step": 25915
|
|
},
|
|
{
|
|
"entropy": 5.632634162902832,
|
|
"epoch": 2.016650457109512,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004589158787856336,
|
|
"loss": 4.9429,
|
|
"mean_token_accuracy": 0.20722294002771377,
|
|
"num_tokens": 44960208.0,
|
|
"step": 25920
|
|
},
|
|
{
|
|
"entropy": 5.613522672653199,
|
|
"epoch": 2.0170394864812295,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004588999114110721,
|
|
"loss": 4.8495,
|
|
"mean_token_accuracy": 0.21180173009634018,
|
|
"num_tokens": 44969051.0,
|
|
"step": 25925
|
|
},
|
|
{
|
|
"entropy": 5.619331979751587,
|
|
"epoch": 2.017428515852947,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004588839412461223,
|
|
"loss": 4.895,
|
|
"mean_token_accuracy": 0.21775769293308259,
|
|
"num_tokens": 44977980.0,
|
|
"step": 25930
|
|
},
|
|
{
|
|
"entropy": 5.628773593902588,
|
|
"epoch": 2.0178175452246645,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004588679682910264,
|
|
"loss": 4.9702,
|
|
"mean_token_accuracy": 0.20029470175504685,
|
|
"num_tokens": 44986520.0,
|
|
"step": 25935
|
|
},
|
|
{
|
|
"entropy": 5.675970983505249,
|
|
"epoch": 2.018206574596382,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004588519925460266,
|
|
"loss": 4.9658,
|
|
"mean_token_accuracy": 0.20854251384735106,
|
|
"num_tokens": 44995011.0,
|
|
"step": 25940
|
|
},
|
|
{
|
|
"entropy": 5.600999116897583,
|
|
"epoch": 2.0185956039680995,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004588360140113655,
|
|
"loss": 4.9519,
|
|
"mean_token_accuracy": 0.21334500908851622,
|
|
"num_tokens": 45004611.0,
|
|
"step": 25945
|
|
},
|
|
{
|
|
"entropy": 5.694470453262329,
|
|
"epoch": 2.018984633339817,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004588200326872855,
|
|
"loss": 4.9996,
|
|
"mean_token_accuracy": 0.19941993951797485,
|
|
"num_tokens": 45013832.0,
|
|
"step": 25950
|
|
},
|
|
{
|
|
"entropy": 5.692751932144165,
|
|
"epoch": 2.019373662711535,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004588040485740291,
|
|
"loss": 4.938,
|
|
"mean_token_accuracy": 0.20973325073719024,
|
|
"num_tokens": 45022751.0,
|
|
"step": 25955
|
|
},
|
|
{
|
|
"entropy": 5.710015678405762,
|
|
"epoch": 2.019762692083252,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004587880616718387,
|
|
"loss": 5.0067,
|
|
"mean_token_accuracy": 0.20685900747776031,
|
|
"num_tokens": 45030826.0,
|
|
"step": 25960
|
|
},
|
|
{
|
|
"entropy": 5.694577550888061,
|
|
"epoch": 2.02015172145497,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004587720719809572,
|
|
"loss": 4.9807,
|
|
"mean_token_accuracy": 0.20188210159540176,
|
|
"num_tokens": 45039625.0,
|
|
"step": 25965
|
|
},
|
|
{
|
|
"entropy": 5.645271158218383,
|
|
"epoch": 2.0205407508266875,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004587560795016269,
|
|
"loss": 4.9577,
|
|
"mean_token_accuracy": 0.21033827662467958,
|
|
"num_tokens": 45048229.0,
|
|
"step": 25970
|
|
},
|
|
{
|
|
"entropy": 5.710571336746216,
|
|
"epoch": 2.020929780198405,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004587400842340905,
|
|
"loss": 5.0424,
|
|
"mean_token_accuracy": 0.19907742440700532,
|
|
"num_tokens": 45057414.0,
|
|
"step": 25975
|
|
},
|
|
{
|
|
"entropy": 5.616314888000488,
|
|
"epoch": 2.0213188095701224,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00045872408617859083,
|
|
"loss": 4.8948,
|
|
"mean_token_accuracy": 0.206028513610363,
|
|
"num_tokens": 45065785.0,
|
|
"step": 25980
|
|
},
|
|
{
|
|
"entropy": 5.604463863372803,
|
|
"epoch": 2.02170783894184,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00045870808533537066,
|
|
"loss": 4.9172,
|
|
"mean_token_accuracy": 0.20810531228780746,
|
|
"num_tokens": 45074896.0,
|
|
"step": 25985
|
|
},
|
|
{
|
|
"entropy": 5.593366909027099,
|
|
"epoch": 2.022096868313558,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00045869208170467256,
|
|
"loss": 4.9534,
|
|
"mean_token_accuracy": 0.20079635828733444,
|
|
"num_tokens": 45083554.0,
|
|
"step": 25990
|
|
},
|
|
{
|
|
"entropy": 5.705989122390747,
|
|
"epoch": 2.022485897685275,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004586760752867396,
|
|
"loss": 4.9613,
|
|
"mean_token_accuracy": 0.2041795775294304,
|
|
"num_tokens": 45092204.0,
|
|
"step": 25995
|
|
},
|
|
{
|
|
"entropy": 5.691451597213745,
|
|
"epoch": 2.022874927056993,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00045866006608181456,
|
|
"loss": 4.9848,
|
|
"mean_token_accuracy": 0.19816917479038237,
|
|
"num_tokens": 45101665.0,
|
|
"step": 26000
|
|
},
|
|
{
|
|
"entropy": 5.663026142120361,
|
|
"epoch": 2.0232639564287105,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004586440540901403,
|
|
"loss": 5.0325,
|
|
"mean_token_accuracy": 0.19990342557430268,
|
|
"num_tokens": 45111093.0,
|
|
"step": 26005
|
|
},
|
|
{
|
|
"entropy": 5.673209238052368,
|
|
"epoch": 2.0236529858004277,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00045862803931195976,
|
|
"loss": 4.9594,
|
|
"mean_token_accuracy": 0.20590735971927643,
|
|
"num_tokens": 45118826.0,
|
|
"step": 26010
|
|
},
|
|
{
|
|
"entropy": 5.697975730895996,
|
|
"epoch": 2.0240420151721454,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004586120217475161,
|
|
"loss": 4.9947,
|
|
"mean_token_accuracy": 0.20848352313041688,
|
|
"num_tokens": 45128265.0,
|
|
"step": 26015
|
|
},
|
|
{
|
|
"entropy": 5.714987516403198,
|
|
"epoch": 2.024431044543863,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004585960013970522,
|
|
"loss": 5.0309,
|
|
"mean_token_accuracy": 0.19488996118307114,
|
|
"num_tokens": 45137922.0,
|
|
"step": 26020
|
|
},
|
|
{
|
|
"entropy": 5.611620473861694,
|
|
"epoch": 2.024820073915581,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004585799782608112,
|
|
"loss": 4.8571,
|
|
"mean_token_accuracy": 0.21922712475061418,
|
|
"num_tokens": 45146242.0,
|
|
"step": 26025
|
|
},
|
|
{
|
|
"entropy": 5.692760896682739,
|
|
"epoch": 2.025209103287298,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00045856395233903624,
|
|
"loss": 5.0341,
|
|
"mean_token_accuracy": 0.19816716462373735,
|
|
"num_tokens": 45154897.0,
|
|
"step": 26030
|
|
},
|
|
{
|
|
"entropy": 5.678602266311645,
|
|
"epoch": 2.025598132659016,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004585479236319705,
|
|
"loss": 4.9918,
|
|
"mean_token_accuracy": 0.2063049018383026,
|
|
"num_tokens": 45164786.0,
|
|
"step": 26035
|
|
},
|
|
{
|
|
"entropy": 5.702360534667969,
|
|
"epoch": 2.0259871620307335,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00045853189213985714,
|
|
"loss": 5.0272,
|
|
"mean_token_accuracy": 0.19565706849098205,
|
|
"num_tokens": 45173652.0,
|
|
"step": 26040
|
|
},
|
|
{
|
|
"entropy": 5.672584581375122,
|
|
"epoch": 2.0263761914024507,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00045851585786293943,
|
|
"loss": 4.902,
|
|
"mean_token_accuracy": 0.21253832131624223,
|
|
"num_tokens": 45182399.0,
|
|
"step": 26045
|
|
},
|
|
{
|
|
"entropy": 5.6637773513793945,
|
|
"epoch": 2.0267652207741684,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00045849982080146067,
|
|
"loss": 4.9684,
|
|
"mean_token_accuracy": 0.20364944636821747,
|
|
"num_tokens": 45191587.0,
|
|
"step": 26050
|
|
},
|
|
{
|
|
"entropy": 5.638995122909546,
|
|
"epoch": 2.027154250145886,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004584837809556642,
|
|
"loss": 4.944,
|
|
"mean_token_accuracy": 0.20783798694610595,
|
|
"num_tokens": 45200032.0,
|
|
"step": 26055
|
|
},
|
|
{
|
|
"entropy": 5.634393167495728,
|
|
"epoch": 2.0275432795176034,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00045846773832579346,
|
|
"loss": 4.9616,
|
|
"mean_token_accuracy": 0.2055723026394844,
|
|
"num_tokens": 45209205.0,
|
|
"step": 26060
|
|
},
|
|
{
|
|
"entropy": 5.721559238433838,
|
|
"epoch": 2.027932308889321,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00045845169291209176,
|
|
"loss": 4.9728,
|
|
"mean_token_accuracy": 0.20819129943847656,
|
|
"num_tokens": 45217603.0,
|
|
"step": 26065
|
|
},
|
|
{
|
|
"entropy": 5.669111919403076,
|
|
"epoch": 2.0283213382610388,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00045843564471480263,
|
|
"loss": 4.9232,
|
|
"mean_token_accuracy": 0.2025085687637329,
|
|
"num_tokens": 45225971.0,
|
|
"step": 26070
|
|
},
|
|
{
|
|
"entropy": 5.698772192001343,
|
|
"epoch": 2.0287103676327565,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004584195937341695,
|
|
"loss": 4.9969,
|
|
"mean_token_accuracy": 0.20161072462797164,
|
|
"num_tokens": 45234494.0,
|
|
"step": 26075
|
|
},
|
|
{
|
|
"entropy": 5.617690944671631,
|
|
"epoch": 2.0290993970044737,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00045840353997043606,
|
|
"loss": 4.8215,
|
|
"mean_token_accuracy": 0.2159263789653778,
|
|
"num_tokens": 45242685.0,
|
|
"step": 26080
|
|
},
|
|
{
|
|
"entropy": 5.650600004196167,
|
|
"epoch": 2.0294884263761914,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004583874834238458,
|
|
"loss": 4.9071,
|
|
"mean_token_accuracy": 0.2079970806837082,
|
|
"num_tokens": 45252282.0,
|
|
"step": 26085
|
|
},
|
|
{
|
|
"entropy": 5.685449504852295,
|
|
"epoch": 2.029877455747909,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004583714240946423,
|
|
"loss": 5.0674,
|
|
"mean_token_accuracy": 0.19315167367458344,
|
|
"num_tokens": 45261390.0,
|
|
"step": 26090
|
|
},
|
|
{
|
|
"entropy": 5.718031501770019,
|
|
"epoch": 2.0302664851196264,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00045835536198306936,
|
|
"loss": 5.078,
|
|
"mean_token_accuracy": 0.19824135452508926,
|
|
"num_tokens": 45270244.0,
|
|
"step": 26095
|
|
},
|
|
{
|
|
"entropy": 5.705060958862305,
|
|
"epoch": 2.030655514491344,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00045833929708937067,
|
|
"loss": 4.99,
|
|
"mean_token_accuracy": 0.1969300001859665,
|
|
"num_tokens": 45279404.0,
|
|
"step": 26100
|
|
},
|
|
{
|
|
"entropy": 5.692380475997925,
|
|
"epoch": 2.0310445438630618,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004583232294137899,
|
|
"loss": 4.957,
|
|
"mean_token_accuracy": 0.21014004945755005,
|
|
"num_tokens": 45288064.0,
|
|
"step": 26105
|
|
},
|
|
{
|
|
"entropy": 5.68449559211731,
|
|
"epoch": 2.031433573234779,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004583071589565709,
|
|
"loss": 4.9963,
|
|
"mean_token_accuracy": 0.20225270539522172,
|
|
"num_tokens": 45296528.0,
|
|
"step": 26110
|
|
},
|
|
{
|
|
"entropy": 5.6436333656311035,
|
|
"epoch": 2.0318226026064967,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004582910857179576,
|
|
"loss": 4.9103,
|
|
"mean_token_accuracy": 0.20844800472259523,
|
|
"num_tokens": 45305524.0,
|
|
"step": 26115
|
|
},
|
|
{
|
|
"entropy": 5.7331455707550045,
|
|
"epoch": 2.0322116319782144,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004582750096981938,
|
|
"loss": 5.0968,
|
|
"mean_token_accuracy": 0.19437944144010544,
|
|
"num_tokens": 45314386.0,
|
|
"step": 26120
|
|
},
|
|
{
|
|
"entropy": 5.68181471824646,
|
|
"epoch": 2.032600661349932,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004582589308975234,
|
|
"loss": 4.9866,
|
|
"mean_token_accuracy": 0.20569924265146255,
|
|
"num_tokens": 45322901.0,
|
|
"step": 26125
|
|
},
|
|
{
|
|
"entropy": 5.6107419490814205,
|
|
"epoch": 2.0329896907216494,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00045824284931619044,
|
|
"loss": 4.92,
|
|
"mean_token_accuracy": 0.20761809945106507,
|
|
"num_tokens": 45331509.0,
|
|
"step": 26130
|
|
},
|
|
{
|
|
"entropy": 5.6627459049224855,
|
|
"epoch": 2.033378720093367,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00045822676495443893,
|
|
"loss": 4.9699,
|
|
"mean_token_accuracy": 0.2066069394350052,
|
|
"num_tokens": 45340356.0,
|
|
"step": 26135
|
|
},
|
|
{
|
|
"entropy": 5.753885221481323,
|
|
"epoch": 2.0337677494650848,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00045821067781251284,
|
|
"loss": 5.0075,
|
|
"mean_token_accuracy": 0.20187541842460632,
|
|
"num_tokens": 45349890.0,
|
|
"step": 26140
|
|
},
|
|
{
|
|
"entropy": 5.671606969833374,
|
|
"epoch": 2.034156778836802,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00045819458789065633,
|
|
"loss": 4.9676,
|
|
"mean_token_accuracy": 0.20906978994607925,
|
|
"num_tokens": 45359249.0,
|
|
"step": 26145
|
|
},
|
|
{
|
|
"entropy": 5.65541410446167,
|
|
"epoch": 2.0345458082085197,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004581784951891135,
|
|
"loss": 4.9479,
|
|
"mean_token_accuracy": 0.21289274096488953,
|
|
"num_tokens": 45367832.0,
|
|
"step": 26150
|
|
},
|
|
{
|
|
"entropy": 5.662096929550171,
|
|
"epoch": 2.0349348375802374,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004581623997081286,
|
|
"loss": 4.9549,
|
|
"mean_token_accuracy": 0.20920063853263854,
|
|
"num_tokens": 45376316.0,
|
|
"step": 26155
|
|
},
|
|
{
|
|
"entropy": 5.710555791854858,
|
|
"epoch": 2.0353238669519547,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004581463014479459,
|
|
"loss": 5.0221,
|
|
"mean_token_accuracy": 0.19455120116472244,
|
|
"num_tokens": 45385801.0,
|
|
"step": 26160
|
|
},
|
|
{
|
|
"entropy": 5.6823070526123045,
|
|
"epoch": 2.0357128963236724,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004581302004088095,
|
|
"loss": 4.984,
|
|
"mean_token_accuracy": 0.20982643812894822,
|
|
"num_tokens": 45394669.0,
|
|
"step": 26165
|
|
},
|
|
{
|
|
"entropy": 5.644961738586426,
|
|
"epoch": 2.03610192569539,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004581140965909638,
|
|
"loss": 4.945,
|
|
"mean_token_accuracy": 0.2074610635638237,
|
|
"num_tokens": 45402896.0,
|
|
"step": 26170
|
|
},
|
|
{
|
|
"entropy": 5.637491273880005,
|
|
"epoch": 2.0364909550671078,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004580979899946531,
|
|
"loss": 4.9811,
|
|
"mean_token_accuracy": 0.20109013319015503,
|
|
"num_tokens": 45411047.0,
|
|
"step": 26175
|
|
},
|
|
{
|
|
"entropy": 5.71692385673523,
|
|
"epoch": 2.036879984438825,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004580818806201219,
|
|
"loss": 5.0923,
|
|
"mean_token_accuracy": 0.19554199278354645,
|
|
"num_tokens": 45420661.0,
|
|
"step": 26180
|
|
},
|
|
{
|
|
"entropy": 5.729820346832275,
|
|
"epoch": 2.0372690138105427,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00045806576846761453,
|
|
"loss": 4.9335,
|
|
"mean_token_accuracy": 0.21313071995973587,
|
|
"num_tokens": 45429199.0,
|
|
"step": 26185
|
|
},
|
|
{
|
|
"entropy": 5.69167308807373,
|
|
"epoch": 2.0376580431822604,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00045804965353737556,
|
|
"loss": 4.9362,
|
|
"mean_token_accuracy": 0.20775840878486634,
|
|
"num_tokens": 45437504.0,
|
|
"step": 26190
|
|
},
|
|
{
|
|
"entropy": 5.589030981063843,
|
|
"epoch": 2.0380470725539777,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004580335358296494,
|
|
"loss": 4.8991,
|
|
"mean_token_accuracy": 0.20800567418336868,
|
|
"num_tokens": 45445696.0,
|
|
"step": 26195
|
|
},
|
|
{
|
|
"entropy": 5.662701892852783,
|
|
"epoch": 2.0384361019256954,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00045801741534468065,
|
|
"loss": 5.0082,
|
|
"mean_token_accuracy": 0.20205149352550505,
|
|
"num_tokens": 45455058.0,
|
|
"step": 26200
|
|
},
|
|
{
|
|
"entropy": 5.829818964004517,
|
|
"epoch": 2.038825131297413,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004580012920827139,
|
|
"loss": 5.072,
|
|
"mean_token_accuracy": 0.20382075756788254,
|
|
"num_tokens": 45464193.0,
|
|
"step": 26205
|
|
},
|
|
{
|
|
"entropy": 5.601741695404053,
|
|
"epoch": 2.0392141606691303,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004579851660439939,
|
|
"loss": 4.8451,
|
|
"mean_token_accuracy": 0.2141188085079193,
|
|
"num_tokens": 45471922.0,
|
|
"step": 26210
|
|
},
|
|
{
|
|
"entropy": 5.674674701690674,
|
|
"epoch": 2.039603190040848,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00045796903722876523,
|
|
"loss": 5.0304,
|
|
"mean_token_accuracy": 0.19680144488811493,
|
|
"num_tokens": 45480181.0,
|
|
"step": 26215
|
|
},
|
|
{
|
|
"entropy": 5.8024567604064945,
|
|
"epoch": 2.0399922194125657,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004579529056372726,
|
|
"loss": 5.0355,
|
|
"mean_token_accuracy": 0.20499414950609207,
|
|
"num_tokens": 45488970.0,
|
|
"step": 26220
|
|
},
|
|
{
|
|
"entropy": 5.793949937820434,
|
|
"epoch": 2.0403812487842834,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004579367712697609,
|
|
"loss": 4.9593,
|
|
"mean_token_accuracy": 0.20311334282159804,
|
|
"num_tokens": 45497066.0,
|
|
"step": 26225
|
|
},
|
|
{
|
|
"entropy": 5.6367613792419435,
|
|
"epoch": 2.0407702781560006,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00045792063412647475,
|
|
"loss": 4.9373,
|
|
"mean_token_accuracy": 0.2043283000588417,
|
|
"num_tokens": 45506399.0,
|
|
"step": 26230
|
|
},
|
|
{
|
|
"entropy": 5.648182439804077,
|
|
"epoch": 2.0411593075277183,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00045790449420765925,
|
|
"loss": 4.9665,
|
|
"mean_token_accuracy": 0.20089273899793625,
|
|
"num_tokens": 45516625.0,
|
|
"step": 26235
|
|
},
|
|
{
|
|
"entropy": 5.75351128578186,
|
|
"epoch": 2.041548336899436,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00045788835151355914,
|
|
"loss": 5.0613,
|
|
"mean_token_accuracy": 0.19787285923957826,
|
|
"num_tokens": 45525539.0,
|
|
"step": 26240
|
|
},
|
|
{
|
|
"entropy": 5.7503454208374025,
|
|
"epoch": 2.0419373662711533,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00045787220604441933,
|
|
"loss": 4.9804,
|
|
"mean_token_accuracy": 0.2094811752438545,
|
|
"num_tokens": 45535388.0,
|
|
"step": 26245
|
|
},
|
|
{
|
|
"entropy": 5.701186466217041,
|
|
"epoch": 2.042326395642871,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00045785605780048497,
|
|
"loss": 5.0224,
|
|
"mean_token_accuracy": 0.2008216053247452,
|
|
"num_tokens": 45543729.0,
|
|
"step": 26250
|
|
},
|
|
{
|
|
"entropy": 5.702984809875488,
|
|
"epoch": 2.0427154250145887,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00045783990678200086,
|
|
"loss": 5.0288,
|
|
"mean_token_accuracy": 0.2026811271905899,
|
|
"num_tokens": 45551887.0,
|
|
"step": 26255
|
|
},
|
|
{
|
|
"entropy": 5.783022403717041,
|
|
"epoch": 2.043104454386306,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00045782375298921227,
|
|
"loss": 5.0823,
|
|
"mean_token_accuracy": 0.19830229729413987,
|
|
"num_tokens": 45560267.0,
|
|
"step": 26260
|
|
},
|
|
{
|
|
"entropy": 5.711447811126709,
|
|
"epoch": 2.0434934837580236,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004578075964223642,
|
|
"loss": 4.9902,
|
|
"mean_token_accuracy": 0.1970672056078911,
|
|
"num_tokens": 45569459.0,
|
|
"step": 26265
|
|
},
|
|
{
|
|
"entropy": 5.770064115524292,
|
|
"epoch": 2.0438825131297413,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004577914370817018,
|
|
"loss": 4.9751,
|
|
"mean_token_accuracy": 0.1991291642189026,
|
|
"num_tokens": 45577713.0,
|
|
"step": 26270
|
|
},
|
|
{
|
|
"entropy": 5.645679521560669,
|
|
"epoch": 2.044271542501459,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00045777527496747034,
|
|
"loss": 4.9147,
|
|
"mean_token_accuracy": 0.2066315308213234,
|
|
"num_tokens": 45586521.0,
|
|
"step": 26275
|
|
},
|
|
{
|
|
"entropy": 5.677498483657837,
|
|
"epoch": 2.0446605718731763,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00045775911007991493,
|
|
"loss": 4.9637,
|
|
"mean_token_accuracy": 0.20217486321926117,
|
|
"num_tokens": 45595210.0,
|
|
"step": 26280
|
|
},
|
|
{
|
|
"entropy": 5.689458227157592,
|
|
"epoch": 2.045049601244894,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00045774294241928093,
|
|
"loss": 5.0127,
|
|
"mean_token_accuracy": 0.2055308476090431,
|
|
"num_tokens": 45603472.0,
|
|
"step": 26285
|
|
},
|
|
{
|
|
"entropy": 5.681685447692871,
|
|
"epoch": 2.0454386306166117,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004577267719858137,
|
|
"loss": 5.0598,
|
|
"mean_token_accuracy": 0.19471936970949172,
|
|
"num_tokens": 45612149.0,
|
|
"step": 26290
|
|
},
|
|
{
|
|
"entropy": 5.779747676849365,
|
|
"epoch": 2.045827659988329,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00045771059877975853,
|
|
"loss": 5.0731,
|
|
"mean_token_accuracy": 0.19781418293714523,
|
|
"num_tokens": 45619903.0,
|
|
"step": 26295
|
|
},
|
|
{
|
|
"entropy": 5.692175817489624,
|
|
"epoch": 2.0462166893600466,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004576944228013608,
|
|
"loss": 4.9637,
|
|
"mean_token_accuracy": 0.21066200584173203,
|
|
"num_tokens": 45628012.0,
|
|
"step": 26300
|
|
},
|
|
{
|
|
"entropy": 5.642592239379883,
|
|
"epoch": 2.0466057187317643,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000457678244050866,
|
|
"loss": 4.9939,
|
|
"mean_token_accuracy": 0.20328520089387894,
|
|
"num_tokens": 45636587.0,
|
|
"step": 26305
|
|
},
|
|
{
|
|
"entropy": 5.67674036026001,
|
|
"epoch": 2.046994748103482,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004576620625285196,
|
|
"loss": 4.9494,
|
|
"mean_token_accuracy": 0.20184803009033203,
|
|
"num_tokens": 45645189.0,
|
|
"step": 26310
|
|
},
|
|
{
|
|
"entropy": 5.750026893615723,
|
|
"epoch": 2.0473837774751993,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00045764587823456717,
|
|
"loss": 5.0311,
|
|
"mean_token_accuracy": 0.2033383622765541,
|
|
"num_tokens": 45654059.0,
|
|
"step": 26315
|
|
},
|
|
{
|
|
"entropy": 5.695265674591065,
|
|
"epoch": 2.047772806846917,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00045762969116925424,
|
|
"loss": 4.9006,
|
|
"mean_token_accuracy": 0.21536493450403213,
|
|
"num_tokens": 45662125.0,
|
|
"step": 26320
|
|
},
|
|
{
|
|
"entropy": 5.7020679950714115,
|
|
"epoch": 2.0481618362186347,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00045761350133282643,
|
|
"loss": 4.9797,
|
|
"mean_token_accuracy": 0.20785591900348663,
|
|
"num_tokens": 45670068.0,
|
|
"step": 26325
|
|
},
|
|
{
|
|
"entropy": 5.656160736083985,
|
|
"epoch": 2.048550865590352,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00045759730872552937,
|
|
"loss": 4.8675,
|
|
"mean_token_accuracy": 0.21632105708122254,
|
|
"num_tokens": 45678717.0,
|
|
"step": 26330
|
|
},
|
|
{
|
|
"entropy": 5.645941638946534,
|
|
"epoch": 2.0489398949620696,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004575811133476088,
|
|
"loss": 4.9587,
|
|
"mean_token_accuracy": 0.20723410546779633,
|
|
"num_tokens": 45686882.0,
|
|
"step": 26335
|
|
},
|
|
{
|
|
"entropy": 5.601016664505005,
|
|
"epoch": 2.0493289243337873,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00045756491519931047,
|
|
"loss": 4.8898,
|
|
"mean_token_accuracy": 0.20890021324157715,
|
|
"num_tokens": 45695460.0,
|
|
"step": 26340
|
|
},
|
|
{
|
|
"entropy": 5.756913805007935,
|
|
"epoch": 2.0497179537055046,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004575487142808801,
|
|
"loss": 5.0525,
|
|
"mean_token_accuracy": 0.19704596996307372,
|
|
"num_tokens": 45703287.0,
|
|
"step": 26345
|
|
},
|
|
{
|
|
"entropy": 5.727641439437866,
|
|
"epoch": 2.0501069830772223,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004575325105925636,
|
|
"loss": 5.0713,
|
|
"mean_token_accuracy": 0.19566494226455688,
|
|
"num_tokens": 45712830.0,
|
|
"step": 26350
|
|
},
|
|
{
|
|
"entropy": 5.6460315704345705,
|
|
"epoch": 2.05049601244894,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00045751630413460665,
|
|
"loss": 5.0651,
|
|
"mean_token_accuracy": 0.19860530644655228,
|
|
"num_tokens": 45720701.0,
|
|
"step": 26355
|
|
},
|
|
{
|
|
"entropy": 5.6865331649780275,
|
|
"epoch": 2.0508850418206577,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004575000949072554,
|
|
"loss": 4.9264,
|
|
"mean_token_accuracy": 0.2069900169968605,
|
|
"num_tokens": 45728663.0,
|
|
"step": 26360
|
|
},
|
|
{
|
|
"entropy": 5.6829897403717045,
|
|
"epoch": 2.051274071192375,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004574838829107557,
|
|
"loss": 4.9779,
|
|
"mean_token_accuracy": 0.2015938863158226,
|
|
"num_tokens": 45737661.0,
|
|
"step": 26365
|
|
},
|
|
{
|
|
"entropy": 5.599342250823975,
|
|
"epoch": 2.0516631005640926,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004574676681453535,
|
|
"loss": 4.9297,
|
|
"mean_token_accuracy": 0.2127887412905693,
|
|
"num_tokens": 45746343.0,
|
|
"step": 26370
|
|
},
|
|
{
|
|
"entropy": 5.622148895263672,
|
|
"epoch": 2.0520521299358103,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00045745145061129485,
|
|
"loss": 4.9654,
|
|
"mean_token_accuracy": 0.2032032698392868,
|
|
"num_tokens": 45755025.0,
|
|
"step": 26375
|
|
},
|
|
{
|
|
"entropy": 5.705486536026001,
|
|
"epoch": 2.0524411593075276,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00045743523030882584,
|
|
"loss": 5.0355,
|
|
"mean_token_accuracy": 0.20282019525766373,
|
|
"num_tokens": 45763107.0,
|
|
"step": 26380
|
|
},
|
|
{
|
|
"entropy": 5.6822922706604,
|
|
"epoch": 2.0528301886792453,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004574190072381926,
|
|
"loss": 4.9203,
|
|
"mean_token_accuracy": 0.21141140460968016,
|
|
"num_tokens": 45771754.0,
|
|
"step": 26385
|
|
},
|
|
{
|
|
"entropy": 5.688706350326538,
|
|
"epoch": 2.053219218050963,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004574027813996413,
|
|
"loss": 5.0893,
|
|
"mean_token_accuracy": 0.20015982836484908,
|
|
"num_tokens": 45779282.0,
|
|
"step": 26390
|
|
},
|
|
{
|
|
"entropy": 5.707024145126343,
|
|
"epoch": 2.05360824742268,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004573865527934181,
|
|
"loss": 5.0427,
|
|
"mean_token_accuracy": 0.19662826657295226,
|
|
"num_tokens": 45788002.0,
|
|
"step": 26395
|
|
},
|
|
{
|
|
"entropy": 5.763675212860107,
|
|
"epoch": 2.053997276794398,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004573703214197692,
|
|
"loss": 5.0319,
|
|
"mean_token_accuracy": 0.1990533947944641,
|
|
"num_tokens": 45796563.0,
|
|
"step": 26400
|
|
},
|
|
{
|
|
"entropy": 5.687012004852295,
|
|
"epoch": 2.0543863061661156,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00045735408727894095,
|
|
"loss": 4.9572,
|
|
"mean_token_accuracy": 0.20754703283309936,
|
|
"num_tokens": 45806311.0,
|
|
"step": 26405
|
|
},
|
|
{
|
|
"entropy": 5.682385015487671,
|
|
"epoch": 2.0547753355378333,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00045733785037117977,
|
|
"loss": 4.9483,
|
|
"mean_token_accuracy": 0.20658033937215806,
|
|
"num_tokens": 45814007.0,
|
|
"step": 26410
|
|
},
|
|
{
|
|
"entropy": 5.670385646820068,
|
|
"epoch": 2.0551643649095506,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004573216106967319,
|
|
"loss": 4.9801,
|
|
"mean_token_accuracy": 0.19763838350772858,
|
|
"num_tokens": 45822492.0,
|
|
"step": 26415
|
|
},
|
|
{
|
|
"entropy": 5.641687440872192,
|
|
"epoch": 2.0555533942812683,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00045730536825584365,
|
|
"loss": 4.918,
|
|
"mean_token_accuracy": 0.20933483242988588,
|
|
"num_tokens": 45830853.0,
|
|
"step": 26420
|
|
},
|
|
{
|
|
"entropy": 5.739394187927246,
|
|
"epoch": 2.055942423652986,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00045728912304876176,
|
|
"loss": 5.0138,
|
|
"mean_token_accuracy": 0.20124027729034424,
|
|
"num_tokens": 45839948.0,
|
|
"step": 26425
|
|
},
|
|
{
|
|
"entropy": 5.793256711959839,
|
|
"epoch": 2.056331453024703,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004572728750757326,
|
|
"loss": 5.1247,
|
|
"mean_token_accuracy": 0.1831857144832611,
|
|
"num_tokens": 45848264.0,
|
|
"step": 26430
|
|
},
|
|
{
|
|
"entropy": 5.611777877807617,
|
|
"epoch": 2.056720482396421,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004572566243370025,
|
|
"loss": 4.892,
|
|
"mean_token_accuracy": 0.21454827040433883,
|
|
"num_tokens": 45856523.0,
|
|
"step": 26435
|
|
},
|
|
{
|
|
"entropy": 5.642489337921143,
|
|
"epoch": 2.0571095117681386,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004572403708328183,
|
|
"loss": 5.0056,
|
|
"mean_token_accuracy": 0.20898969769477843,
|
|
"num_tokens": 45864736.0,
|
|
"step": 26440
|
|
},
|
|
{
|
|
"entropy": 5.671368217468261,
|
|
"epoch": 2.057498541139856,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004572241145634266,
|
|
"loss": 5.0037,
|
|
"mean_token_accuracy": 0.2016543686389923,
|
|
"num_tokens": 45873979.0,
|
|
"step": 26445
|
|
},
|
|
{
|
|
"entropy": 5.643639373779297,
|
|
"epoch": 2.0578875705115736,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000457207855529074,
|
|
"loss": 4.959,
|
|
"mean_token_accuracy": 0.20861584991216658,
|
|
"num_tokens": 45882545.0,
|
|
"step": 26450
|
|
},
|
|
{
|
|
"entropy": 5.669561815261841,
|
|
"epoch": 2.0582765998832913,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00045719159373000713,
|
|
"loss": 5.0473,
|
|
"mean_token_accuracy": 0.19620343595743178,
|
|
"num_tokens": 45890830.0,
|
|
"step": 26455
|
|
},
|
|
{
|
|
"entropy": 5.773867225646972,
|
|
"epoch": 2.058665629255009,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004571753291664729,
|
|
"loss": 4.9935,
|
|
"mean_token_accuracy": 0.20281164348125458,
|
|
"num_tokens": 45899457.0,
|
|
"step": 26460
|
|
},
|
|
{
|
|
"entropy": 5.685356998443604,
|
|
"epoch": 2.059054658626726,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004571590618387179,
|
|
"loss": 4.9994,
|
|
"mean_token_accuracy": 0.20380024760961532,
|
|
"num_tokens": 45907998.0,
|
|
"step": 26465
|
|
},
|
|
{
|
|
"entropy": 5.645242547988891,
|
|
"epoch": 2.059443687998444,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004571427917469892,
|
|
"loss": 4.928,
|
|
"mean_token_accuracy": 0.2026064619421959,
|
|
"num_tokens": 45916102.0,
|
|
"step": 26470
|
|
},
|
|
{
|
|
"entropy": 5.657299900054932,
|
|
"epoch": 2.0598327173701616,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00045712651889153345,
|
|
"loss": 4.9613,
|
|
"mean_token_accuracy": 0.20668953508138657,
|
|
"num_tokens": 45924347.0,
|
|
"step": 26475
|
|
},
|
|
{
|
|
"entropy": 5.7314183712005615,
|
|
"epoch": 2.060221746741879,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00045711024327259764,
|
|
"loss": 4.9837,
|
|
"mean_token_accuracy": 0.2074410766363144,
|
|
"num_tokens": 45932702.0,
|
|
"step": 26480
|
|
},
|
|
{
|
|
"entropy": 5.61371865272522,
|
|
"epoch": 2.0606107761135966,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00045709396489042884,
|
|
"loss": 4.9459,
|
|
"mean_token_accuracy": 0.20138026028871536,
|
|
"num_tokens": 45941235.0,
|
|
"step": 26485
|
|
},
|
|
{
|
|
"entropy": 5.681282043457031,
|
|
"epoch": 2.0609998054853143,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00045707768374527385,
|
|
"loss": 4.94,
|
|
"mean_token_accuracy": 0.21190550923347473,
|
|
"num_tokens": 45949582.0,
|
|
"step": 26490
|
|
},
|
|
{
|
|
"entropy": 5.695214796066284,
|
|
"epoch": 2.0613888348570315,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004570613998373799,
|
|
"loss": 5.0095,
|
|
"mean_token_accuracy": 0.20235701650381088,
|
|
"num_tokens": 45957920.0,
|
|
"step": 26495
|
|
},
|
|
{
|
|
"entropy": 5.6700811862945555,
|
|
"epoch": 2.061777864228749,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00045704511316699395,
|
|
"loss": 5.0506,
|
|
"mean_token_accuracy": 0.20360081791877746,
|
|
"num_tokens": 45966302.0,
|
|
"step": 26500
|
|
},
|
|
{
|
|
"entropy": 5.733704376220703,
|
|
"epoch": 2.062166893600467,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00045702882373436317,
|
|
"loss": 5.0719,
|
|
"mean_token_accuracy": 0.19766143411397935,
|
|
"num_tokens": 45975481.0,
|
|
"step": 26505
|
|
},
|
|
{
|
|
"entropy": 5.816517686843872,
|
|
"epoch": 2.0625559229721846,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004570125315397347,
|
|
"loss": 5.062,
|
|
"mean_token_accuracy": 0.20263160914182662,
|
|
"num_tokens": 45984466.0,
|
|
"step": 26510
|
|
},
|
|
{
|
|
"entropy": 5.662425756454468,
|
|
"epoch": 2.062944952343902,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004569962365833558,
|
|
"loss": 4.8943,
|
|
"mean_token_accuracy": 0.20768968611955643,
|
|
"num_tokens": 45992862.0,
|
|
"step": 26515
|
|
},
|
|
{
|
|
"entropy": 5.63205771446228,
|
|
"epoch": 2.0633339817156195,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00045697993886547374,
|
|
"loss": 4.9946,
|
|
"mean_token_accuracy": 0.19968704879283905,
|
|
"num_tokens": 46001211.0,
|
|
"step": 26520
|
|
},
|
|
{
|
|
"entropy": 5.721051979064941,
|
|
"epoch": 2.0637230110873372,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00045696363838633566,
|
|
"loss": 5.0073,
|
|
"mean_token_accuracy": 0.19828609973192216,
|
|
"num_tokens": 46009574.0,
|
|
"step": 26525
|
|
},
|
|
{
|
|
"entropy": 5.71382737159729,
|
|
"epoch": 2.0641120404590545,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00045694733514618904,
|
|
"loss": 4.9422,
|
|
"mean_token_accuracy": 0.20257085859775542,
|
|
"num_tokens": 46017686.0,
|
|
"step": 26530
|
|
},
|
|
{
|
|
"entropy": 5.688066673278809,
|
|
"epoch": 2.064501069830772,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004569310291452812,
|
|
"loss": 4.9663,
|
|
"mean_token_accuracy": 0.2029442995786667,
|
|
"num_tokens": 46026842.0,
|
|
"step": 26535
|
|
},
|
|
{
|
|
"entropy": 5.644578695297241,
|
|
"epoch": 2.06489009920249,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004569147203838595,
|
|
"loss": 4.9604,
|
|
"mean_token_accuracy": 0.20868255496025084,
|
|
"num_tokens": 46036308.0,
|
|
"step": 26540
|
|
},
|
|
{
|
|
"entropy": 5.702411651611328,
|
|
"epoch": 2.065279128574207,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00045689840886217157,
|
|
"loss": 4.9733,
|
|
"mean_token_accuracy": 0.20491039454936982,
|
|
"num_tokens": 46045424.0,
|
|
"step": 26545
|
|
},
|
|
{
|
|
"entropy": 5.667631721496582,
|
|
"epoch": 2.065668157945925,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00045688209458046475,
|
|
"loss": 4.9508,
|
|
"mean_token_accuracy": 0.20506266504526138,
|
|
"num_tokens": 46054386.0,
|
|
"step": 26550
|
|
},
|
|
{
|
|
"entropy": 5.633437442779541,
|
|
"epoch": 2.0660571873176425,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00045686577753898663,
|
|
"loss": 4.8846,
|
|
"mean_token_accuracy": 0.214173524081707,
|
|
"num_tokens": 46063617.0,
|
|
"step": 26555
|
|
},
|
|
{
|
|
"entropy": 5.702445220947266,
|
|
"epoch": 2.0664462166893602,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00045684945773798483,
|
|
"loss": 5.0766,
|
|
"mean_token_accuracy": 0.20049827843904494,
|
|
"num_tokens": 46072915.0,
|
|
"step": 26560
|
|
},
|
|
{
|
|
"entropy": 5.725633859634399,
|
|
"epoch": 2.0668352460610775,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000456833135177707,
|
|
"loss": 5.101,
|
|
"mean_token_accuracy": 0.19491964280605317,
|
|
"num_tokens": 46081890.0,
|
|
"step": 26565
|
|
},
|
|
{
|
|
"entropy": 5.770382881164551,
|
|
"epoch": 2.067224275432795,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004568168098584007,
|
|
"loss": 5.0652,
|
|
"mean_token_accuracy": 0.19314909130334854,
|
|
"num_tokens": 46090445.0,
|
|
"step": 26570
|
|
},
|
|
{
|
|
"entropy": 5.76362042427063,
|
|
"epoch": 2.067613304804513,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004568004817803137,
|
|
"loss": 5.0252,
|
|
"mean_token_accuracy": 0.20208129584789275,
|
|
"num_tokens": 46099866.0,
|
|
"step": 26575
|
|
},
|
|
{
|
|
"entropy": 5.674625205993652,
|
|
"epoch": 2.06800233417623,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004567841509436937,
|
|
"loss": 4.9287,
|
|
"mean_token_accuracy": 0.20954311192035674,
|
|
"num_tokens": 46108036.0,
|
|
"step": 26580
|
|
},
|
|
{
|
|
"entropy": 5.678498792648315,
|
|
"epoch": 2.068391363547948,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004567678173487887,
|
|
"loss": 4.8992,
|
|
"mean_token_accuracy": 0.21291859298944474,
|
|
"num_tokens": 46116087.0,
|
|
"step": 26585
|
|
},
|
|
{
|
|
"entropy": 5.643871879577636,
|
|
"epoch": 2.0687803929196655,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004567514809958462,
|
|
"loss": 4.9825,
|
|
"mean_token_accuracy": 0.21221491247415541,
|
|
"num_tokens": 46124934.0,
|
|
"step": 26590
|
|
},
|
|
{
|
|
"entropy": 5.700538682937622,
|
|
"epoch": 2.069169422291383,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004567351418851144,
|
|
"loss": 4.9921,
|
|
"mean_token_accuracy": 0.2074885591864586,
|
|
"num_tokens": 46133691.0,
|
|
"step": 26595
|
|
},
|
|
{
|
|
"entropy": 5.729164123535156,
|
|
"epoch": 2.0695584516631005,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00045671880001684113,
|
|
"loss": 5.0537,
|
|
"mean_token_accuracy": 0.19493894577026366,
|
|
"num_tokens": 46141933.0,
|
|
"step": 26600
|
|
},
|
|
{
|
|
"entropy": 5.672248888015747,
|
|
"epoch": 2.069947481034818,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00045670245539127413,
|
|
"loss": 4.9336,
|
|
"mean_token_accuracy": 0.20921938270330429,
|
|
"num_tokens": 46150656.0,
|
|
"step": 26605
|
|
},
|
|
{
|
|
"entropy": 5.620133686065674,
|
|
"epoch": 2.070336510406536,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00045668610800866173,
|
|
"loss": 4.9543,
|
|
"mean_token_accuracy": 0.2051005929708481,
|
|
"num_tokens": 46160353.0,
|
|
"step": 26610
|
|
},
|
|
{
|
|
"entropy": 5.684297752380371,
|
|
"epoch": 2.070725539778253,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00045666975786925177,
|
|
"loss": 4.9904,
|
|
"mean_token_accuracy": 0.2084883764386177,
|
|
"num_tokens": 46168810.0,
|
|
"step": 26615
|
|
},
|
|
{
|
|
"entropy": 5.699772834777832,
|
|
"epoch": 2.071114569149971,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004566534049732923,
|
|
"loss": 4.9695,
|
|
"mean_token_accuracy": 0.20911960750818254,
|
|
"num_tokens": 46177593.0,
|
|
"step": 26620
|
|
},
|
|
{
|
|
"entropy": 5.688872289657593,
|
|
"epoch": 2.0715035985216885,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00045663704932103166,
|
|
"loss": 4.9698,
|
|
"mean_token_accuracy": 0.21247036904096603,
|
|
"num_tokens": 46186027.0,
|
|
"step": 26625
|
|
},
|
|
{
|
|
"entropy": 5.7123737812042235,
|
|
"epoch": 2.071892627893406,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00045662069091271785,
|
|
"loss": 5.0808,
|
|
"mean_token_accuracy": 0.19122884124517442,
|
|
"num_tokens": 46194705.0,
|
|
"step": 26630
|
|
},
|
|
{
|
|
"entropy": 5.698910570144653,
|
|
"epoch": 2.0722816572651235,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00045660432974859924,
|
|
"loss": 4.9227,
|
|
"mean_token_accuracy": 0.20927760750055313,
|
|
"num_tokens": 46203498.0,
|
|
"step": 26635
|
|
},
|
|
{
|
|
"entropy": 5.721298789978027,
|
|
"epoch": 2.072670686636841,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00045658796582892383,
|
|
"loss": 4.9745,
|
|
"mean_token_accuracy": 0.21304211765527725,
|
|
"num_tokens": 46211918.0,
|
|
"step": 26640
|
|
},
|
|
{
|
|
"entropy": 5.742507600784302,
|
|
"epoch": 2.073059716008559,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00045657159915394013,
|
|
"loss": 5.0695,
|
|
"mean_token_accuracy": 0.20158637464046478,
|
|
"num_tokens": 46220689.0,
|
|
"step": 26645
|
|
},
|
|
{
|
|
"entropy": 5.711783456802368,
|
|
"epoch": 2.073448745380276,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004565552297238964,
|
|
"loss": 5.0406,
|
|
"mean_token_accuracy": 0.1979992210865021,
|
|
"num_tokens": 46229645.0,
|
|
"step": 26650
|
|
},
|
|
{
|
|
"entropy": 5.754027795791626,
|
|
"epoch": 2.073837774751994,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.000456538857539041,
|
|
"loss": 5.0118,
|
|
"mean_token_accuracy": 0.1969640538096428,
|
|
"num_tokens": 46237691.0,
|
|
"step": 26655
|
|
},
|
|
{
|
|
"entropy": 5.702052974700928,
|
|
"epoch": 2.0742268041237115,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00045652248259962254,
|
|
"loss": 4.9701,
|
|
"mean_token_accuracy": 0.20612976849079132,
|
|
"num_tokens": 46245756.0,
|
|
"step": 26660
|
|
},
|
|
{
|
|
"entropy": 5.753409910202026,
|
|
"epoch": 2.0746158334954288,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004565061049058892,
|
|
"loss": 5.0689,
|
|
"mean_token_accuracy": 0.19615186154842376,
|
|
"num_tokens": 46255233.0,
|
|
"step": 26665
|
|
},
|
|
{
|
|
"entropy": 5.705156421661377,
|
|
"epoch": 2.0750048628671465,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00045648972445808963,
|
|
"loss": 5.0111,
|
|
"mean_token_accuracy": 0.19983147978782653,
|
|
"num_tokens": 46263569.0,
|
|
"step": 26670
|
|
},
|
|
{
|
|
"entropy": 5.616665649414062,
|
|
"epoch": 2.075393892238864,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00045647334125647235,
|
|
"loss": 4.8987,
|
|
"mean_token_accuracy": 0.20818208903074265,
|
|
"num_tokens": 46273010.0,
|
|
"step": 26675
|
|
},
|
|
{
|
|
"entropy": 5.754445362091064,
|
|
"epoch": 2.0757829216105814,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000456456955301286,
|
|
"loss": 4.9747,
|
|
"mean_token_accuracy": 0.21063933074474334,
|
|
"num_tokens": 46281566.0,
|
|
"step": 26680
|
|
},
|
|
{
|
|
"entropy": 5.602251291275024,
|
|
"epoch": 2.076171950982299,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004564405665927791,
|
|
"loss": 4.8693,
|
|
"mean_token_accuracy": 0.21099644154310226,
|
|
"num_tokens": 46290267.0,
|
|
"step": 26685
|
|
},
|
|
{
|
|
"entropy": 5.634386110305786,
|
|
"epoch": 2.076560980354017,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00045642417513120043,
|
|
"loss": 4.8995,
|
|
"mean_token_accuracy": 0.21202029436826705,
|
|
"num_tokens": 46298694.0,
|
|
"step": 26690
|
|
},
|
|
{
|
|
"entropy": 5.680882310867309,
|
|
"epoch": 2.076950009725734,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00045640778091679876,
|
|
"loss": 4.8625,
|
|
"mean_token_accuracy": 0.21378698199987411,
|
|
"num_tokens": 46307358.0,
|
|
"step": 26695
|
|
},
|
|
{
|
|
"entropy": 5.6812952041625975,
|
|
"epoch": 2.0773390390974518,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004563913839498226,
|
|
"loss": 4.9164,
|
|
"mean_token_accuracy": 0.2135591298341751,
|
|
"num_tokens": 46316351.0,
|
|
"step": 26700
|
|
},
|
|
{
|
|
"entropy": 5.6801787376403805,
|
|
"epoch": 2.0777280684691695,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000456374984230521,
|
|
"loss": 4.9746,
|
|
"mean_token_accuracy": 0.20548408180475236,
|
|
"num_tokens": 46325591.0,
|
|
"step": 26705
|
|
},
|
|
{
|
|
"entropy": 5.690999555587768,
|
|
"epoch": 2.078117097840887,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004563585817591427,
|
|
"loss": 4.9555,
|
|
"mean_token_accuracy": 0.20443084537982942,
|
|
"num_tokens": 46334595.0,
|
|
"step": 26710
|
|
},
|
|
{
|
|
"entropy": 5.771510267257691,
|
|
"epoch": 2.0785061272126044,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004563421765359365,
|
|
"loss": 5.0369,
|
|
"mean_token_accuracy": 0.19937919825315475,
|
|
"num_tokens": 46343587.0,
|
|
"step": 26715
|
|
},
|
|
{
|
|
"entropy": 5.8022724151611325,
|
|
"epoch": 2.078895156584322,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00045632576856115156,
|
|
"loss": 5.0261,
|
|
"mean_token_accuracy": 0.20182194858789443,
|
|
"num_tokens": 46351900.0,
|
|
"step": 26720
|
|
},
|
|
{
|
|
"entropy": 5.722235107421875,
|
|
"epoch": 2.07928418595604,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00045630935783503657,
|
|
"loss": 5.0231,
|
|
"mean_token_accuracy": 0.2011237323284149,
|
|
"num_tokens": 46359854.0,
|
|
"step": 26725
|
|
},
|
|
{
|
|
"entropy": 5.712496328353882,
|
|
"epoch": 2.079673215327757,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004562929443578407,
|
|
"loss": 5.1116,
|
|
"mean_token_accuracy": 0.19846736788749694,
|
|
"num_tokens": 46368930.0,
|
|
"step": 26730
|
|
},
|
|
{
|
|
"entropy": 5.6774827003479,
|
|
"epoch": 2.0800622446994748,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004562765281298129,
|
|
"loss": 4.8986,
|
|
"mean_token_accuracy": 0.20788912922143937,
|
|
"num_tokens": 46377522.0,
|
|
"step": 26735
|
|
},
|
|
{
|
|
"entropy": 5.669716310501099,
|
|
"epoch": 2.0804512740711925,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004562601091512024,
|
|
"loss": 4.9971,
|
|
"mean_token_accuracy": 0.19960644990205764,
|
|
"num_tokens": 46386368.0,
|
|
"step": 26740
|
|
},
|
|
{
|
|
"entropy": 5.695429706573487,
|
|
"epoch": 2.08084030344291,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004562436874222582,
|
|
"loss": 4.9553,
|
|
"mean_token_accuracy": 0.2035237267613411,
|
|
"num_tokens": 46395363.0,
|
|
"step": 26745
|
|
},
|
|
{
|
|
"entropy": 5.748808670043945,
|
|
"epoch": 2.0812293328146274,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00045622726294322955,
|
|
"loss": 5.0225,
|
|
"mean_token_accuracy": 0.19950494766235352,
|
|
"num_tokens": 46403998.0,
|
|
"step": 26750
|
|
},
|
|
{
|
|
"entropy": 5.576841592788696,
|
|
"epoch": 2.081618362186345,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00045621083571436563,
|
|
"loss": 4.8201,
|
|
"mean_token_accuracy": 0.222538498044014,
|
|
"num_tokens": 46412138.0,
|
|
"step": 26755
|
|
},
|
|
{
|
|
"entropy": 5.631717395782471,
|
|
"epoch": 2.082007391558063,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004561944057359157,
|
|
"loss": 4.9819,
|
|
"mean_token_accuracy": 0.20640279799699784,
|
|
"num_tokens": 46420761.0,
|
|
"step": 26760
|
|
},
|
|
{
|
|
"entropy": 5.601476192474365,
|
|
"epoch": 2.08239642092978,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004561779730081291,
|
|
"loss": 4.9488,
|
|
"mean_token_accuracy": 0.21046752184629441,
|
|
"num_tokens": 46428938.0,
|
|
"step": 26765
|
|
},
|
|
{
|
|
"entropy": 5.7185474872589115,
|
|
"epoch": 2.0827854503014978,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004561615375312551,
|
|
"loss": 4.9554,
|
|
"mean_token_accuracy": 0.21121462434530258,
|
|
"num_tokens": 46436552.0,
|
|
"step": 26770
|
|
},
|
|
{
|
|
"entropy": 5.633351278305054,
|
|
"epoch": 2.0831744796732155,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00045614509930554304,
|
|
"loss": 4.9118,
|
|
"mean_token_accuracy": 0.2094930127263069,
|
|
"num_tokens": 46445223.0,
|
|
"step": 26775
|
|
},
|
|
{
|
|
"entropy": 5.680253314971924,
|
|
"epoch": 2.0835635090449327,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00045612865833124253,
|
|
"loss": 5.0323,
|
|
"mean_token_accuracy": 0.20136726796627044,
|
|
"num_tokens": 46453232.0,
|
|
"step": 26780
|
|
},
|
|
{
|
|
"entropy": 5.559950256347657,
|
|
"epoch": 2.0839525384166504,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004561122146086029,
|
|
"loss": 4.8388,
|
|
"mean_token_accuracy": 0.21345621794462205,
|
|
"num_tokens": 46462562.0,
|
|
"step": 26785
|
|
},
|
|
{
|
|
"entropy": 5.675860929489136,
|
|
"epoch": 2.084341567788368,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004560957681378737,
|
|
"loss": 5.0317,
|
|
"mean_token_accuracy": 0.1949341729283333,
|
|
"num_tokens": 46470599.0,
|
|
"step": 26790
|
|
},
|
|
{
|
|
"entropy": 5.745585489273071,
|
|
"epoch": 2.084730597160086,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00045607931891930445,
|
|
"loss": 4.9897,
|
|
"mean_token_accuracy": 0.2033182993531227,
|
|
"num_tokens": 46478707.0,
|
|
"step": 26795
|
|
},
|
|
{
|
|
"entropy": 5.657948923110962,
|
|
"epoch": 2.085119626531803,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004560628669531447,
|
|
"loss": 4.9773,
|
|
"mean_token_accuracy": 0.2046966314315796,
|
|
"num_tokens": 46487044.0,
|
|
"step": 26800
|
|
},
|
|
{
|
|
"entropy": 5.686334657669067,
|
|
"epoch": 2.0855086559035207,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00045604641223964416,
|
|
"loss": 4.985,
|
|
"mean_token_accuracy": 0.19873972088098527,
|
|
"num_tokens": 46495278.0,
|
|
"step": 26805
|
|
},
|
|
{
|
|
"entropy": 5.644309186935425,
|
|
"epoch": 2.0858976852752384,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00045602995477905247,
|
|
"loss": 4.9989,
|
|
"mean_token_accuracy": 0.2050021097064018,
|
|
"num_tokens": 46503545.0,
|
|
"step": 26810
|
|
},
|
|
{
|
|
"entropy": 5.654935693740844,
|
|
"epoch": 2.0862867146469557,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004560134945716194,
|
|
"loss": 5.0312,
|
|
"mean_token_accuracy": 0.21401808112859727,
|
|
"num_tokens": 46513058.0,
|
|
"step": 26815
|
|
},
|
|
{
|
|
"entropy": 5.708903217315674,
|
|
"epoch": 2.0866757440186734,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00045599703161759464,
|
|
"loss": 4.9381,
|
|
"mean_token_accuracy": 0.20220120400190353,
|
|
"num_tokens": 46520651.0,
|
|
"step": 26820
|
|
},
|
|
{
|
|
"entropy": 5.651180028915405,
|
|
"epoch": 2.087064773390391,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00045598056591722805,
|
|
"loss": 4.92,
|
|
"mean_token_accuracy": 0.20638586580753326,
|
|
"num_tokens": 46528899.0,
|
|
"step": 26825
|
|
},
|
|
{
|
|
"entropy": 5.731946802139282,
|
|
"epoch": 2.0874538027621083,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00045596409747076936,
|
|
"loss": 5.1213,
|
|
"mean_token_accuracy": 0.18965098559856414,
|
|
"num_tokens": 46537921.0,
|
|
"step": 26830
|
|
},
|
|
{
|
|
"entropy": 5.713159465789795,
|
|
"epoch": 2.087842832133826,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004559476262784686,
|
|
"loss": 4.9551,
|
|
"mean_token_accuracy": 0.20966471135616302,
|
|
"num_tokens": 46547432.0,
|
|
"step": 26835
|
|
},
|
|
{
|
|
"entropy": 5.694389772415161,
|
|
"epoch": 2.0882318615055437,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004559311523405755,
|
|
"loss": 5.0058,
|
|
"mean_token_accuracy": 0.20187440067529677,
|
|
"num_tokens": 46555406.0,
|
|
"step": 26840
|
|
},
|
|
{
|
|
"entropy": 5.727861070632935,
|
|
"epoch": 2.0886208908772614,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004559146756573402,
|
|
"loss": 5.0013,
|
|
"mean_token_accuracy": 0.2088017523288727,
|
|
"num_tokens": 46564428.0,
|
|
"step": 26845
|
|
},
|
|
{
|
|
"entropy": 5.704367351531983,
|
|
"epoch": 2.0890099202489787,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00045589819622901274,
|
|
"loss": 4.9285,
|
|
"mean_token_accuracy": 0.2126939758658409,
|
|
"num_tokens": 46573222.0,
|
|
"step": 26850
|
|
},
|
|
{
|
|
"entropy": 5.666756296157837,
|
|
"epoch": 2.0893989496206964,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000455881714055843,
|
|
"loss": 4.9345,
|
|
"mean_token_accuracy": 0.2110202580690384,
|
|
"num_tokens": 46581951.0,
|
|
"step": 26855
|
|
},
|
|
{
|
|
"entropy": 5.728613185882568,
|
|
"epoch": 2.089787978992414,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00045586522913808114,
|
|
"loss": 5.0557,
|
|
"mean_token_accuracy": 0.21197190880775452,
|
|
"num_tokens": 46590658.0,
|
|
"step": 26860
|
|
},
|
|
{
|
|
"entropy": 5.694840002059936,
|
|
"epoch": 2.0901770083641313,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004558487414759773,
|
|
"loss": 4.9027,
|
|
"mean_token_accuracy": 0.21503257155418395,
|
|
"num_tokens": 46599068.0,
|
|
"step": 26865
|
|
},
|
|
{
|
|
"entropy": 5.655412244796753,
|
|
"epoch": 2.090566037735849,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00045583225106978175,
|
|
"loss": 4.9914,
|
|
"mean_token_accuracy": 0.20396257936954498,
|
|
"num_tokens": 46608024.0,
|
|
"step": 26870
|
|
},
|
|
{
|
|
"entropy": 5.643037366867065,
|
|
"epoch": 2.0909550671075667,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004558157579197446,
|
|
"loss": 4.9302,
|
|
"mean_token_accuracy": 0.20895154327154158,
|
|
"num_tokens": 46616558.0,
|
|
"step": 26875
|
|
},
|
|
{
|
|
"entropy": 5.7506249904632565,
|
|
"epoch": 2.091344096479284,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00045579926202611603,
|
|
"loss": 5.1379,
|
|
"mean_token_accuracy": 0.19193762093782424,
|
|
"num_tokens": 46624943.0,
|
|
"step": 26880
|
|
},
|
|
{
|
|
"entropy": 5.673505687713623,
|
|
"epoch": 2.0917331258510017,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004557827633891465,
|
|
"loss": 4.9833,
|
|
"mean_token_accuracy": 0.19999424517154693,
|
|
"num_tokens": 46633753.0,
|
|
"step": 26885
|
|
},
|
|
{
|
|
"entropy": 5.711205911636353,
|
|
"epoch": 2.0921221552227194,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004557662620090863,
|
|
"loss": 4.9935,
|
|
"mean_token_accuracy": 0.20564150661230088,
|
|
"num_tokens": 46642210.0,
|
|
"step": 26890
|
|
},
|
|
{
|
|
"entropy": 5.691160678863525,
|
|
"epoch": 2.092511184594437,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00045574975788618564,
|
|
"loss": 4.9513,
|
|
"mean_token_accuracy": 0.20996245741844177,
|
|
"num_tokens": 46650327.0,
|
|
"step": 26895
|
|
},
|
|
{
|
|
"entropy": 5.6484599113464355,
|
|
"epoch": 2.0929002139661543,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004557332510206953,
|
|
"loss": 4.8833,
|
|
"mean_token_accuracy": 0.21219709515571594,
|
|
"num_tokens": 46659453.0,
|
|
"step": 26900
|
|
},
|
|
{
|
|
"entropy": 5.736992979049683,
|
|
"epoch": 2.093289243337872,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004557167414128654,
|
|
"loss": 4.9679,
|
|
"mean_token_accuracy": 0.20799987614154816,
|
|
"num_tokens": 46667378.0,
|
|
"step": 26905
|
|
},
|
|
{
|
|
"entropy": 5.725967359542847,
|
|
"epoch": 2.0936782727095897,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004557002290629467,
|
|
"loss": 5.1324,
|
|
"mean_token_accuracy": 0.1900894433259964,
|
|
"num_tokens": 46675949.0,
|
|
"step": 26910
|
|
},
|
|
{
|
|
"entropy": 5.770013904571533,
|
|
"epoch": 2.094067302081307,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00045568371397118954,
|
|
"loss": 5.1541,
|
|
"mean_token_accuracy": 0.19959221333265303,
|
|
"num_tokens": 46684808.0,
|
|
"step": 26915
|
|
},
|
|
{
|
|
"entropy": 5.716790723800659,
|
|
"epoch": 2.0944563314530247,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004556671961378446,
|
|
"loss": 4.9666,
|
|
"mean_token_accuracy": 0.2076625183224678,
|
|
"num_tokens": 46693209.0,
|
|
"step": 26920
|
|
},
|
|
{
|
|
"entropy": 5.633689975738525,
|
|
"epoch": 2.0948453608247424,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00045565067556316264,
|
|
"loss": 4.943,
|
|
"mean_token_accuracy": 0.2135712593793869,
|
|
"num_tokens": 46702405.0,
|
|
"step": 26925
|
|
},
|
|
{
|
|
"entropy": 5.5798985958099365,
|
|
"epoch": 2.0952343901964596,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004556341522473941,
|
|
"loss": 4.9592,
|
|
"mean_token_accuracy": 0.2059960275888443,
|
|
"num_tokens": 46711568.0,
|
|
"step": 26930
|
|
},
|
|
{
|
|
"entropy": 5.655941534042358,
|
|
"epoch": 2.0956234195681773,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004556176261907899,
|
|
"loss": 4.98,
|
|
"mean_token_accuracy": 0.20742260813713073,
|
|
"num_tokens": 46719886.0,
|
|
"step": 26935
|
|
},
|
|
{
|
|
"entropy": 5.6564287662506105,
|
|
"epoch": 2.096012448939895,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004556010973936006,
|
|
"loss": 4.8356,
|
|
"mean_token_accuracy": 0.21430304795503616,
|
|
"num_tokens": 46728293.0,
|
|
"step": 26940
|
|
},
|
|
{
|
|
"entropy": 5.683703279495239,
|
|
"epoch": 2.0964014783116127,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004555845658560772,
|
|
"loss": 4.9879,
|
|
"mean_token_accuracy": 0.2014298677444458,
|
|
"num_tokens": 46736730.0,
|
|
"step": 26945
|
|
},
|
|
{
|
|
"entropy": 5.687503290176392,
|
|
"epoch": 2.09679050768333,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00045556803157847036,
|
|
"loss": 5.0408,
|
|
"mean_token_accuracy": 0.1930103436112404,
|
|
"num_tokens": 46745563.0,
|
|
"step": 26950
|
|
},
|
|
{
|
|
"entropy": 5.722416162490845,
|
|
"epoch": 2.0971795370550477,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00045555149456103113,
|
|
"loss": 4.988,
|
|
"mean_token_accuracy": 0.20209750384092331,
|
|
"num_tokens": 46754285.0,
|
|
"step": 26955
|
|
},
|
|
{
|
|
"entropy": 5.706587600708008,
|
|
"epoch": 2.0975685664267654,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004555349548040102,
|
|
"loss": 4.9867,
|
|
"mean_token_accuracy": 0.21139516979455947,
|
|
"num_tokens": 46763114.0,
|
|
"step": 26960
|
|
},
|
|
{
|
|
"entropy": 5.704325723648071,
|
|
"epoch": 2.0979575957984826,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004555184123076589,
|
|
"loss": 4.9986,
|
|
"mean_token_accuracy": 0.2040882334113121,
|
|
"num_tokens": 46771150.0,
|
|
"step": 26965
|
|
},
|
|
{
|
|
"entropy": 5.6477532386779785,
|
|
"epoch": 2.0983466251702003,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00045550186707222785,
|
|
"loss": 4.8857,
|
|
"mean_token_accuracy": 0.21533036679029466,
|
|
"num_tokens": 46779955.0,
|
|
"step": 26970
|
|
},
|
|
{
|
|
"entropy": 5.678753089904785,
|
|
"epoch": 2.098735654541918,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004554853190979683,
|
|
"loss": 5.0204,
|
|
"mean_token_accuracy": 0.19841573685407637,
|
|
"num_tokens": 46788769.0,
|
|
"step": 26975
|
|
},
|
|
{
|
|
"entropy": 5.72996416091919,
|
|
"epoch": 2.0991246839136353,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.00045546876838513134,
|
|
"loss": 5.0257,
|
|
"mean_token_accuracy": 0.20052011162042618,
|
|
"num_tokens": 46797649.0,
|
|
"step": 26980
|
|
},
|
|
{
|
|
"entropy": 5.693415212631225,
|
|
"epoch": 2.099513713285353,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00045545221493396805,
|
|
"loss": 4.9371,
|
|
"mean_token_accuracy": 0.20562161654233932,
|
|
"num_tokens": 46806140.0,
|
|
"step": 26985
|
|
},
|
|
{
|
|
"entropy": 5.697494268417358,
|
|
"epoch": 2.0999027426570707,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00045543565874472963,
|
|
"loss": 4.8799,
|
|
"mean_token_accuracy": 0.2161271169781685,
|
|
"num_tokens": 46815476.0,
|
|
"step": 26990
|
|
},
|
|
{
|
|
"entropy": 5.6711503028869625,
|
|
"epoch": 2.1002917720287884,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00045541909981766725,
|
|
"loss": 5.0351,
|
|
"mean_token_accuracy": 0.20086161494255067,
|
|
"num_tokens": 46824171.0,
|
|
"step": 26995
|
|
},
|
|
{
|
|
"entropy": 5.609083890914917,
|
|
"epoch": 2.1006808014005056,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004554025381530322,
|
|
"loss": 4.8806,
|
|
"mean_token_accuracy": 0.2124312177300453,
|
|
"num_tokens": 46832474.0,
|
|
"step": 27000
|
|
},
|
|
{
|
|
"epoch": 2.1006808014005056,
|
|
"eval_entropy": 5.377945898861927,
|
|
"eval_loss": 5.092503070831299,
|
|
"eval_mean_token_accuracy": 0.209100198200738,
|
|
"eval_num_tokens": 46832474.0,
|
|
"eval_runtime": 21.5964,
|
|
"eval_samples_per_second": 1924.304,
|
|
"eval_steps_per_second": 240.55,
|
|
"step": 27000
|
|
}
|
|
],
|
|
"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": 9426381468641280.0,
|
|
"train_batch_size": 16,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|