24079 lines
661 KiB
JSON
24079 lines
661 KiB
JSON
{
|
|
"best_global_step": null,
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 0.9336704921221552,
|
|
"eval_steps": 3000,
|
|
"global_step": 12000,
|
|
"is_hyper_param_search": false,
|
|
"is_local_process_zero": true,
|
|
"is_world_process_zero": true,
|
|
"log_history": [
|
|
{
|
|
"entropy": 10.742576789855956,
|
|
"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
|
|
}
|
|
],
|
|
"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": 4199832201461760.0,
|
|
"train_batch_size": 16,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|