713909f277
Model: fpadovani/ind-latn-10mb-after-ppt-shuff-dyck-100mb-ckpt500_seed3407 Source: Original Platform
6046 lines
164 KiB
JSON
6046 lines
164 KiB
JSON
{
|
|
"best_global_step": null,
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 0.2334176230305388,
|
|
"eval_steps": 3000,
|
|
"global_step": 3000,
|
|
"is_hyper_param_search": false,
|
|
"is_local_process_zero": true,
|
|
"is_world_process_zero": true,
|
|
"log_history": [
|
|
{
|
|
"entropy": 4.92353572845459,
|
|
"epoch": 0.00038902937171756465,
|
|
"grad_norm": 13.375,
|
|
"learning_rate": 2e-06,
|
|
"loss": 14.2513,
|
|
"mean_token_accuracy": 0.0001277139177545905,
|
|
"num_tokens": 8755.0,
|
|
"step": 5
|
|
},
|
|
{
|
|
"entropy": 4.934064674377441,
|
|
"epoch": 0.0007780587434351293,
|
|
"grad_norm": 13.875,
|
|
"learning_rate": 4.5e-06,
|
|
"loss": 14.2685,
|
|
"mean_token_accuracy": 0.0,
|
|
"num_tokens": 17641.0,
|
|
"step": 10
|
|
},
|
|
{
|
|
"entropy": 4.950730228424073,
|
|
"epoch": 0.001167088115152694,
|
|
"grad_norm": 15.1875,
|
|
"learning_rate": 7e-06,
|
|
"loss": 14.1845,
|
|
"mean_token_accuracy": 0.0,
|
|
"num_tokens": 26293.0,
|
|
"step": 15
|
|
},
|
|
{
|
|
"entropy": 4.978141450881958,
|
|
"epoch": 0.0015561174868702586,
|
|
"grad_norm": 16.875,
|
|
"learning_rate": 9.5e-06,
|
|
"loss": 14.0758,
|
|
"mean_token_accuracy": 0.0,
|
|
"num_tokens": 35627.0,
|
|
"step": 20
|
|
},
|
|
{
|
|
"entropy": 5.09318265914917,
|
|
"epoch": 0.0019451468585878235,
|
|
"grad_norm": 20.25,
|
|
"learning_rate": 1.2e-05,
|
|
"loss": 13.6416,
|
|
"mean_token_accuracy": 0.0,
|
|
"num_tokens": 43861.0,
|
|
"step": 25
|
|
},
|
|
{
|
|
"entropy": 5.357007932662964,
|
|
"epoch": 0.002334176230305388,
|
|
"grad_norm": 26.375,
|
|
"learning_rate": 1.4500000000000002e-05,
|
|
"loss": 13.1478,
|
|
"mean_token_accuracy": 0.0,
|
|
"num_tokens": 52816.0,
|
|
"step": 30
|
|
},
|
|
{
|
|
"entropy": 6.636251544952392,
|
|
"epoch": 0.0027232056020229526,
|
|
"grad_norm": 25.375,
|
|
"learning_rate": 1.7000000000000003e-05,
|
|
"loss": 12.0885,
|
|
"mean_token_accuracy": 0.0,
|
|
"num_tokens": 61370.0,
|
|
"step": 35
|
|
},
|
|
{
|
|
"entropy": 9.923179340362548,
|
|
"epoch": 0.0031122349737405172,
|
|
"grad_norm": 3.578125,
|
|
"learning_rate": 1.95e-05,
|
|
"loss": 10.9048,
|
|
"mean_token_accuracy": 0.0001186239649541676,
|
|
"num_tokens": 69444.0,
|
|
"step": 40
|
|
},
|
|
{
|
|
"entropy": 10.702562427520752,
|
|
"epoch": 0.003501264345458082,
|
|
"grad_norm": 3.28125,
|
|
"learning_rate": 2.2e-05,
|
|
"loss": 10.6653,
|
|
"mean_token_accuracy": 0.011188959912396967,
|
|
"num_tokens": 77892.0,
|
|
"step": 45
|
|
},
|
|
{
|
|
"entropy": 10.734418773651123,
|
|
"epoch": 0.003890293717175647,
|
|
"grad_norm": 2.75,
|
|
"learning_rate": 2.4500000000000003e-05,
|
|
"loss": 10.5129,
|
|
"mean_token_accuracy": 0.020575371105223894,
|
|
"num_tokens": 86154.0,
|
|
"step": 50
|
|
},
|
|
{
|
|
"entropy": 10.707633876800537,
|
|
"epoch": 0.004279323088893211,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 2.7e-05,
|
|
"loss": 10.3484,
|
|
"mean_token_accuracy": 0.01765873283147812,
|
|
"num_tokens": 95589.0,
|
|
"step": 55
|
|
},
|
|
{
|
|
"entropy": 10.638573741912841,
|
|
"epoch": 0.004668352460610776,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 2.95e-05,
|
|
"loss": 10.1852,
|
|
"mean_token_accuracy": 0.017188905738294125,
|
|
"num_tokens": 105268.0,
|
|
"step": 60
|
|
},
|
|
{
|
|
"entropy": 10.698107624053955,
|
|
"epoch": 0.0050573818323283405,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 3.2e-05,
|
|
"loss": 9.9755,
|
|
"mean_token_accuracy": 0.020746274664998055,
|
|
"num_tokens": 113347.0,
|
|
"step": 65
|
|
},
|
|
{
|
|
"entropy": 10.710992527008056,
|
|
"epoch": 0.005446411204045905,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 3.4500000000000005e-05,
|
|
"loss": 9.8539,
|
|
"mean_token_accuracy": 0.029131441563367843,
|
|
"num_tokens": 121235.0,
|
|
"step": 70
|
|
},
|
|
{
|
|
"entropy": 10.693155670166016,
|
|
"epoch": 0.00583544057576347,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 3.7e-05,
|
|
"loss": 9.8016,
|
|
"mean_token_accuracy": 0.03198963850736618,
|
|
"num_tokens": 129529.0,
|
|
"step": 75
|
|
},
|
|
{
|
|
"entropy": 10.6787428855896,
|
|
"epoch": 0.0062244699474810344,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 3.95e-05,
|
|
"loss": 9.719,
|
|
"mean_token_accuracy": 0.026658685877919197,
|
|
"num_tokens": 137918.0,
|
|
"step": 80
|
|
},
|
|
{
|
|
"entropy": 10.677947998046875,
|
|
"epoch": 0.006613499319198599,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 4.2000000000000004e-05,
|
|
"loss": 9.5968,
|
|
"mean_token_accuracy": 0.03781393375247717,
|
|
"num_tokens": 146445.0,
|
|
"step": 85
|
|
},
|
|
{
|
|
"entropy": 10.670944595336914,
|
|
"epoch": 0.007002528690916164,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 4.45e-05,
|
|
"loss": 9.5696,
|
|
"mean_token_accuracy": 0.0504709430038929,
|
|
"num_tokens": 155904.0,
|
|
"step": 90
|
|
},
|
|
{
|
|
"entropy": 10.652875709533692,
|
|
"epoch": 0.007391558062633729,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 4.7000000000000004e-05,
|
|
"loss": 9.45,
|
|
"mean_token_accuracy": 0.050913235172629356,
|
|
"num_tokens": 164436.0,
|
|
"step": 95
|
|
},
|
|
{
|
|
"entropy": 10.624427032470702,
|
|
"epoch": 0.007780587434351294,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 4.9500000000000004e-05,
|
|
"loss": 9.3318,
|
|
"mean_token_accuracy": 0.048470248281955716,
|
|
"num_tokens": 172985.0,
|
|
"step": 100
|
|
},
|
|
{
|
|
"entropy": 10.590660285949706,
|
|
"epoch": 0.008169616806068859,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 5.2e-05,
|
|
"loss": 9.2226,
|
|
"mean_token_accuracy": 0.04833147563040256,
|
|
"num_tokens": 182084.0,
|
|
"step": 105
|
|
},
|
|
{
|
|
"entropy": 10.561868572235108,
|
|
"epoch": 0.008558646177786422,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 5.45e-05,
|
|
"loss": 9.0932,
|
|
"mean_token_accuracy": 0.05851382501423359,
|
|
"num_tokens": 190742.0,
|
|
"step": 110
|
|
},
|
|
{
|
|
"entropy": 10.509655570983886,
|
|
"epoch": 0.008947675549503988,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 5.7e-05,
|
|
"loss": 8.9979,
|
|
"mean_token_accuracy": 0.057733524963259696,
|
|
"num_tokens": 199600.0,
|
|
"step": 115
|
|
},
|
|
{
|
|
"entropy": 10.445792770385742,
|
|
"epoch": 0.009336704921221552,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 5.9499999999999996e-05,
|
|
"loss": 8.9087,
|
|
"mean_token_accuracy": 0.05567027330398559,
|
|
"num_tokens": 207883.0,
|
|
"step": 120
|
|
},
|
|
{
|
|
"entropy": 10.376938629150391,
|
|
"epoch": 0.009725734292939117,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 6.2e-05,
|
|
"loss": 8.8037,
|
|
"mean_token_accuracy": 0.05684689395129681,
|
|
"num_tokens": 216216.0,
|
|
"step": 125
|
|
},
|
|
{
|
|
"entropy": 10.31500473022461,
|
|
"epoch": 0.010114763664656681,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 6.450000000000001e-05,
|
|
"loss": 8.6827,
|
|
"mean_token_accuracy": 0.05753975734114647,
|
|
"num_tokens": 225250.0,
|
|
"step": 130
|
|
},
|
|
{
|
|
"entropy": 10.194760513305663,
|
|
"epoch": 0.010503793036374246,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 6.7e-05,
|
|
"loss": 8.5671,
|
|
"mean_token_accuracy": 0.054637744277715686,
|
|
"num_tokens": 233748.0,
|
|
"step": 135
|
|
},
|
|
{
|
|
"entropy": 10.12427225112915,
|
|
"epoch": 0.01089282240809181,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 6.950000000000001e-05,
|
|
"loss": 8.4612,
|
|
"mean_token_accuracy": 0.0579361479729414,
|
|
"num_tokens": 242629.0,
|
|
"step": 140
|
|
},
|
|
{
|
|
"entropy": 9.959631061553955,
|
|
"epoch": 0.011281851779809376,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 7.2e-05,
|
|
"loss": 8.3515,
|
|
"mean_token_accuracy": 0.054840120300650594,
|
|
"num_tokens": 251458.0,
|
|
"step": 145
|
|
},
|
|
{
|
|
"entropy": 9.83036823272705,
|
|
"epoch": 0.01167088115152694,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 7.45e-05,
|
|
"loss": 8.2394,
|
|
"mean_token_accuracy": 0.06350252479314804,
|
|
"num_tokens": 260557.0,
|
|
"step": 150
|
|
},
|
|
{
|
|
"entropy": 9.662144470214844,
|
|
"epoch": 0.012059910523244505,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 7.7e-05,
|
|
"loss": 8.1841,
|
|
"mean_token_accuracy": 0.061289533600211145,
|
|
"num_tokens": 269262.0,
|
|
"step": 155
|
|
},
|
|
{
|
|
"entropy": 9.52525873184204,
|
|
"epoch": 0.012448939894962069,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 7.950000000000001e-05,
|
|
"loss": 8.0687,
|
|
"mean_token_accuracy": 0.06112904436886311,
|
|
"num_tokens": 277804.0,
|
|
"step": 160
|
|
},
|
|
{
|
|
"entropy": 9.351448822021485,
|
|
"epoch": 0.012837969266679634,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 8.2e-05,
|
|
"loss": 7.9878,
|
|
"mean_token_accuracy": 0.06238803043961525,
|
|
"num_tokens": 287450.0,
|
|
"step": 165
|
|
},
|
|
{
|
|
"entropy": 9.164531326293945,
|
|
"epoch": 0.013226998638397198,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 8.450000000000001e-05,
|
|
"loss": 7.947,
|
|
"mean_token_accuracy": 0.05899545960128307,
|
|
"num_tokens": 296497.0,
|
|
"step": 170
|
|
},
|
|
{
|
|
"entropy": 8.984291362762452,
|
|
"epoch": 0.013616028010114764,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 8.7e-05,
|
|
"loss": 7.8233,
|
|
"mean_token_accuracy": 0.06463964357972145,
|
|
"num_tokens": 305414.0,
|
|
"step": 175
|
|
},
|
|
{
|
|
"entropy": 8.76324167251587,
|
|
"epoch": 0.014005057381832327,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 8.95e-05,
|
|
"loss": 7.8054,
|
|
"mean_token_accuracy": 0.05876799784600735,
|
|
"num_tokens": 313639.0,
|
|
"step": 180
|
|
},
|
|
{
|
|
"entropy": 8.647741985321044,
|
|
"epoch": 0.014394086753549893,
|
|
"grad_norm": 0.73828125,
|
|
"learning_rate": 9.2e-05,
|
|
"loss": 7.7893,
|
|
"mean_token_accuracy": 0.06448987349867821,
|
|
"num_tokens": 322855.0,
|
|
"step": 185
|
|
},
|
|
{
|
|
"entropy": 8.506945037841797,
|
|
"epoch": 0.014783116125267459,
|
|
"grad_norm": 0.7265625,
|
|
"learning_rate": 9.45e-05,
|
|
"loss": 7.8651,
|
|
"mean_token_accuracy": 0.06298348568379879,
|
|
"num_tokens": 332071.0,
|
|
"step": 190
|
|
},
|
|
{
|
|
"entropy": 8.408401393890381,
|
|
"epoch": 0.015172145496985022,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 9.7e-05,
|
|
"loss": 7.668,
|
|
"mean_token_accuracy": 0.06562523804605007,
|
|
"num_tokens": 339990.0,
|
|
"step": 195
|
|
},
|
|
{
|
|
"entropy": 8.309197616577148,
|
|
"epoch": 0.015561174868702588,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 9.95e-05,
|
|
"loss": 7.7209,
|
|
"mean_token_accuracy": 0.0656034205108881,
|
|
"num_tokens": 348581.0,
|
|
"step": 200
|
|
},
|
|
{
|
|
"entropy": 8.265014839172363,
|
|
"epoch": 0.01595020424042015,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.000102,
|
|
"loss": 7.709,
|
|
"mean_token_accuracy": 0.06688988246023655,
|
|
"num_tokens": 357032.0,
|
|
"step": 205
|
|
},
|
|
{
|
|
"entropy": 8.248595333099365,
|
|
"epoch": 0.016339233612137717,
|
|
"grad_norm": 0.7109375,
|
|
"learning_rate": 0.00010449999999999999,
|
|
"loss": 7.6737,
|
|
"mean_token_accuracy": 0.06308167651295662,
|
|
"num_tokens": 366562.0,
|
|
"step": 210
|
|
},
|
|
{
|
|
"entropy": 8.197728157043457,
|
|
"epoch": 0.016728262983855283,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.000107,
|
|
"loss": 7.6647,
|
|
"mean_token_accuracy": 0.06641935594379902,
|
|
"num_tokens": 374555.0,
|
|
"step": 215
|
|
},
|
|
{
|
|
"entropy": 8.081507778167724,
|
|
"epoch": 0.017117292355572845,
|
|
"grad_norm": 0.76953125,
|
|
"learning_rate": 0.0001095,
|
|
"loss": 7.702,
|
|
"mean_token_accuracy": 0.060842974483966826,
|
|
"num_tokens": 383583.0,
|
|
"step": 220
|
|
},
|
|
{
|
|
"entropy": 8.141448211669921,
|
|
"epoch": 0.01750632172729041,
|
|
"grad_norm": 0.6484375,
|
|
"learning_rate": 0.000112,
|
|
"loss": 7.719,
|
|
"mean_token_accuracy": 0.06294353380799293,
|
|
"num_tokens": 392932.0,
|
|
"step": 225
|
|
},
|
|
{
|
|
"entropy": 8.129082298278808,
|
|
"epoch": 0.017895351099007976,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0001145,
|
|
"loss": 7.572,
|
|
"mean_token_accuracy": 0.06622617989778519,
|
|
"num_tokens": 401653.0,
|
|
"step": 230
|
|
},
|
|
{
|
|
"entropy": 8.068495750427246,
|
|
"epoch": 0.01828438047072554,
|
|
"grad_norm": 0.74609375,
|
|
"learning_rate": 0.00011700000000000001,
|
|
"loss": 7.6611,
|
|
"mean_token_accuracy": 0.06250618062913418,
|
|
"num_tokens": 410432.0,
|
|
"step": 235
|
|
},
|
|
{
|
|
"entropy": 8.076781940460204,
|
|
"epoch": 0.018673409842443103,
|
|
"grad_norm": 0.71875,
|
|
"learning_rate": 0.00011949999999999999,
|
|
"loss": 7.6261,
|
|
"mean_token_accuracy": 0.06318732835352421,
|
|
"num_tokens": 419380.0,
|
|
"step": 240
|
|
},
|
|
{
|
|
"entropy": 8.065077304840088,
|
|
"epoch": 0.01906243921416067,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000122,
|
|
"loss": 7.5564,
|
|
"mean_token_accuracy": 0.0642390213906765,
|
|
"num_tokens": 427682.0,
|
|
"step": 245
|
|
},
|
|
{
|
|
"entropy": 8.04588441848755,
|
|
"epoch": 0.019451468585878234,
|
|
"grad_norm": 0.7265625,
|
|
"learning_rate": 0.0001245,
|
|
"loss": 7.6214,
|
|
"mean_token_accuracy": 0.062338390946388246,
|
|
"num_tokens": 437708.0,
|
|
"step": 250
|
|
},
|
|
{
|
|
"entropy": 8.039131164550781,
|
|
"epoch": 0.0198404979575958,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.000127,
|
|
"loss": 7.6017,
|
|
"mean_token_accuracy": 0.067028983309865,
|
|
"num_tokens": 446480.0,
|
|
"step": 255
|
|
},
|
|
{
|
|
"entropy": 8.057591438293457,
|
|
"epoch": 0.020229527329313362,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0001295,
|
|
"loss": 7.6213,
|
|
"mean_token_accuracy": 0.06589528843760491,
|
|
"num_tokens": 455273.0,
|
|
"step": 260
|
|
},
|
|
{
|
|
"entropy": 8.022430849075317,
|
|
"epoch": 0.020618556701030927,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.000132,
|
|
"loss": 7.5587,
|
|
"mean_token_accuracy": 0.06589296795427799,
|
|
"num_tokens": 464306.0,
|
|
"step": 265
|
|
},
|
|
{
|
|
"entropy": 8.003626775741576,
|
|
"epoch": 0.021007586072748493,
|
|
"grad_norm": 0.7109375,
|
|
"learning_rate": 0.00013450000000000002,
|
|
"loss": 7.5562,
|
|
"mean_token_accuracy": 0.06347908154129982,
|
|
"num_tokens": 472812.0,
|
|
"step": 270
|
|
},
|
|
{
|
|
"entropy": 7.978896903991699,
|
|
"epoch": 0.02139661544446606,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.00013700000000000002,
|
|
"loss": 7.5405,
|
|
"mean_token_accuracy": 0.06544829607009887,
|
|
"num_tokens": 481326.0,
|
|
"step": 275
|
|
},
|
|
{
|
|
"entropy": 7.993354463577271,
|
|
"epoch": 0.02178564481618362,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0001395,
|
|
"loss": 7.4823,
|
|
"mean_token_accuracy": 0.06848083920776844,
|
|
"num_tokens": 489147.0,
|
|
"step": 280
|
|
},
|
|
{
|
|
"entropy": 7.981906986236572,
|
|
"epoch": 0.022174674187901186,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.00014199999999999998,
|
|
"loss": 7.4842,
|
|
"mean_token_accuracy": 0.07221479900181293,
|
|
"num_tokens": 497455.0,
|
|
"step": 285
|
|
},
|
|
{
|
|
"entropy": 7.967179822921753,
|
|
"epoch": 0.02256370355961875,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0001445,
|
|
"loss": 7.4328,
|
|
"mean_token_accuracy": 0.0648717537522316,
|
|
"num_tokens": 506735.0,
|
|
"step": 290
|
|
},
|
|
{
|
|
"entropy": 7.938949966430664,
|
|
"epoch": 0.022952732931336317,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.000147,
|
|
"loss": 7.489,
|
|
"mean_token_accuracy": 0.06714184954762459,
|
|
"num_tokens": 515976.0,
|
|
"step": 295
|
|
},
|
|
{
|
|
"entropy": 7.8373462677001955,
|
|
"epoch": 0.02334176230305388,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0001495,
|
|
"loss": 7.4997,
|
|
"mean_token_accuracy": 0.06925978623330593,
|
|
"num_tokens": 524986.0,
|
|
"step": 300
|
|
},
|
|
{
|
|
"entropy": 7.921111154556274,
|
|
"epoch": 0.023730791674771445,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000152,
|
|
"loss": 7.4968,
|
|
"mean_token_accuracy": 0.07236363515257835,
|
|
"num_tokens": 533146.0,
|
|
"step": 305
|
|
},
|
|
{
|
|
"entropy": 7.893795490264893,
|
|
"epoch": 0.02411982104648901,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.00015450000000000001,
|
|
"loss": 7.4158,
|
|
"mean_token_accuracy": 0.06991111040115357,
|
|
"num_tokens": 541704.0,
|
|
"step": 310
|
|
},
|
|
{
|
|
"entropy": 7.880386638641357,
|
|
"epoch": 0.024508850418206576,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000157,
|
|
"loss": 7.3869,
|
|
"mean_token_accuracy": 0.0700387105345726,
|
|
"num_tokens": 550088.0,
|
|
"step": 315
|
|
},
|
|
{
|
|
"entropy": 7.82145209312439,
|
|
"epoch": 0.024897879789924138,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0001595,
|
|
"loss": 7.3733,
|
|
"mean_token_accuracy": 0.07134931497275829,
|
|
"num_tokens": 558763.0,
|
|
"step": 320
|
|
},
|
|
{
|
|
"entropy": 7.873892116546631,
|
|
"epoch": 0.025286909161641703,
|
|
"grad_norm": 0.6953125,
|
|
"learning_rate": 0.000162,
|
|
"loss": 7.4578,
|
|
"mean_token_accuracy": 0.06747227981686592,
|
|
"num_tokens": 567538.0,
|
|
"step": 325
|
|
},
|
|
{
|
|
"entropy": 7.873815393447876,
|
|
"epoch": 0.02567593853335927,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00016450000000000001,
|
|
"loss": 7.4837,
|
|
"mean_token_accuracy": 0.0674517210572958,
|
|
"num_tokens": 577626.0,
|
|
"step": 330
|
|
},
|
|
{
|
|
"entropy": 7.768797588348389,
|
|
"epoch": 0.026064967905076834,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.00016700000000000002,
|
|
"loss": 7.4164,
|
|
"mean_token_accuracy": 0.06899687238037586,
|
|
"num_tokens": 587163.0,
|
|
"step": 335
|
|
},
|
|
{
|
|
"entropy": 7.8342077255249025,
|
|
"epoch": 0.026453997276794396,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00016950000000000003,
|
|
"loss": 7.3806,
|
|
"mean_token_accuracy": 0.07264294996857643,
|
|
"num_tokens": 595896.0,
|
|
"step": 340
|
|
},
|
|
{
|
|
"entropy": 7.910291004180908,
|
|
"epoch": 0.026843026648511962,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00017199999999999998,
|
|
"loss": 7.409,
|
|
"mean_token_accuracy": 0.07169737853109837,
|
|
"num_tokens": 603815.0,
|
|
"step": 345
|
|
},
|
|
{
|
|
"entropy": 7.82722544670105,
|
|
"epoch": 0.027232056020229527,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.00017449999999999999,
|
|
"loss": 7.4483,
|
|
"mean_token_accuracy": 0.07086139768362046,
|
|
"num_tokens": 612208.0,
|
|
"step": 350
|
|
},
|
|
{
|
|
"entropy": 7.742429780960083,
|
|
"epoch": 0.027621085391947093,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000177,
|
|
"loss": 7.4119,
|
|
"mean_token_accuracy": 0.07163332626223565,
|
|
"num_tokens": 621840.0,
|
|
"step": 355
|
|
},
|
|
{
|
|
"entropy": 7.883988571166992,
|
|
"epoch": 0.028010114763664655,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0001795,
|
|
"loss": 7.4061,
|
|
"mean_token_accuracy": 0.07186231873929501,
|
|
"num_tokens": 630770.0,
|
|
"step": 360
|
|
},
|
|
{
|
|
"entropy": 7.773575687408448,
|
|
"epoch": 0.02839914413538222,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000182,
|
|
"loss": 7.4064,
|
|
"mean_token_accuracy": 0.07286142185330391,
|
|
"num_tokens": 640313.0,
|
|
"step": 365
|
|
},
|
|
{
|
|
"entropy": 7.860558700561524,
|
|
"epoch": 0.028788173507099786,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0001845,
|
|
"loss": 7.4376,
|
|
"mean_token_accuracy": 0.07616207674145699,
|
|
"num_tokens": 648594.0,
|
|
"step": 370
|
|
},
|
|
{
|
|
"entropy": 7.8611939430236815,
|
|
"epoch": 0.02917720287881735,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000187,
|
|
"loss": 7.4204,
|
|
"mean_token_accuracy": 0.07530638352036476,
|
|
"num_tokens": 656478.0,
|
|
"step": 375
|
|
},
|
|
{
|
|
"entropy": 7.69996657371521,
|
|
"epoch": 0.029566232250534917,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0001895,
|
|
"loss": 7.3901,
|
|
"mean_token_accuracy": 0.07715101987123489,
|
|
"num_tokens": 665405.0,
|
|
"step": 380
|
|
},
|
|
{
|
|
"entropy": 7.884545755386353,
|
|
"epoch": 0.02995526162225248,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000192,
|
|
"loss": 7.4072,
|
|
"mean_token_accuracy": 0.07346850857138634,
|
|
"num_tokens": 674301.0,
|
|
"step": 385
|
|
},
|
|
{
|
|
"entropy": 7.79351954460144,
|
|
"epoch": 0.030344290993970045,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0001945,
|
|
"loss": 7.4109,
|
|
"mean_token_accuracy": 0.08006449043750763,
|
|
"num_tokens": 683159.0,
|
|
"step": 390
|
|
},
|
|
{
|
|
"entropy": 7.635227489471435,
|
|
"epoch": 0.03073332036568761,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00019700000000000002,
|
|
"loss": 7.253,
|
|
"mean_token_accuracy": 0.08206554427742958,
|
|
"num_tokens": 690992.0,
|
|
"step": 395
|
|
},
|
|
{
|
|
"entropy": 7.689710521697998,
|
|
"epoch": 0.031122349737405176,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.00019950000000000002,
|
|
"loss": 7.3351,
|
|
"mean_token_accuracy": 0.08058228120207786,
|
|
"num_tokens": 699934.0,
|
|
"step": 400
|
|
},
|
|
{
|
|
"entropy": 7.84839277267456,
|
|
"epoch": 0.03151137910912274,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000202,
|
|
"loss": 7.3736,
|
|
"mean_token_accuracy": 0.07575208507478237,
|
|
"num_tokens": 708844.0,
|
|
"step": 405
|
|
},
|
|
{
|
|
"entropy": 7.728482341766357,
|
|
"epoch": 0.0319004084808403,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00020449999999999998,
|
|
"loss": 7.4388,
|
|
"mean_token_accuracy": 0.07045924849808216,
|
|
"num_tokens": 718148.0,
|
|
"step": 410
|
|
},
|
|
{
|
|
"entropy": 7.762258625030517,
|
|
"epoch": 0.03228943785255787,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000207,
|
|
"loss": 7.3623,
|
|
"mean_token_accuracy": 0.0722539782524109,
|
|
"num_tokens": 726859.0,
|
|
"step": 415
|
|
},
|
|
{
|
|
"entropy": 7.745457887649536,
|
|
"epoch": 0.032678467224275434,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0002095,
|
|
"loss": 7.3553,
|
|
"mean_token_accuracy": 0.07971226572990417,
|
|
"num_tokens": 735045.0,
|
|
"step": 420
|
|
},
|
|
{
|
|
"entropy": 7.745830869674682,
|
|
"epoch": 0.033067496595993,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000212,
|
|
"loss": 7.2402,
|
|
"mean_token_accuracy": 0.08178875669836998,
|
|
"num_tokens": 743538.0,
|
|
"step": 425
|
|
},
|
|
{
|
|
"entropy": 7.6178747653961185,
|
|
"epoch": 0.033456525967710565,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0002145,
|
|
"loss": 7.2988,
|
|
"mean_token_accuracy": 0.0807783305644989,
|
|
"num_tokens": 752518.0,
|
|
"step": 430
|
|
},
|
|
{
|
|
"entropy": 7.715822649002075,
|
|
"epoch": 0.033845555339428124,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00021700000000000002,
|
|
"loss": 7.3213,
|
|
"mean_token_accuracy": 0.07773758620023727,
|
|
"num_tokens": 760354.0,
|
|
"step": 435
|
|
},
|
|
{
|
|
"entropy": 7.711114501953125,
|
|
"epoch": 0.03423458471114569,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0002195,
|
|
"loss": 7.3633,
|
|
"mean_token_accuracy": 0.07912566363811493,
|
|
"num_tokens": 769522.0,
|
|
"step": 440
|
|
},
|
|
{
|
|
"entropy": 7.787883377075195,
|
|
"epoch": 0.034623614082863255,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000222,
|
|
"loss": 7.3054,
|
|
"mean_token_accuracy": 0.08274181857705117,
|
|
"num_tokens": 778548.0,
|
|
"step": 445
|
|
},
|
|
{
|
|
"entropy": 7.620460271835327,
|
|
"epoch": 0.03501264345458082,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0002245,
|
|
"loss": 7.318,
|
|
"mean_token_accuracy": 0.07461104467511177,
|
|
"num_tokens": 787666.0,
|
|
"step": 450
|
|
},
|
|
{
|
|
"entropy": 7.71654577255249,
|
|
"epoch": 0.035401672826298386,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00022700000000000002,
|
|
"loss": 7.2207,
|
|
"mean_token_accuracy": 0.07886159271001816,
|
|
"num_tokens": 796550.0,
|
|
"step": 455
|
|
},
|
|
{
|
|
"entropy": 7.6406464099884035,
|
|
"epoch": 0.03579070219801595,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.00022950000000000002,
|
|
"loss": 7.275,
|
|
"mean_token_accuracy": 0.083228849619627,
|
|
"num_tokens": 804549.0,
|
|
"step": 460
|
|
},
|
|
{
|
|
"entropy": 7.61014609336853,
|
|
"epoch": 0.03617973156973352,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00023200000000000003,
|
|
"loss": 7.2721,
|
|
"mean_token_accuracy": 0.08080526292324067,
|
|
"num_tokens": 813328.0,
|
|
"step": 465
|
|
},
|
|
{
|
|
"entropy": 7.666672468185425,
|
|
"epoch": 0.03656876094145108,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00023449999999999998,
|
|
"loss": 7.2935,
|
|
"mean_token_accuracy": 0.08522161021828652,
|
|
"num_tokens": 821733.0,
|
|
"step": 470
|
|
},
|
|
{
|
|
"entropy": 7.678701782226563,
|
|
"epoch": 0.03695779031316864,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.000237,
|
|
"loss": 7.2352,
|
|
"mean_token_accuracy": 0.08546577319502831,
|
|
"num_tokens": 830243.0,
|
|
"step": 475
|
|
},
|
|
{
|
|
"entropy": 7.726054334640503,
|
|
"epoch": 0.03734681968488621,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0002395,
|
|
"loss": 7.2069,
|
|
"mean_token_accuracy": 0.08190477639436722,
|
|
"num_tokens": 839059.0,
|
|
"step": 480
|
|
},
|
|
{
|
|
"entropy": 7.506451272964478,
|
|
"epoch": 0.03773584905660377,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.000242,
|
|
"loss": 7.1162,
|
|
"mean_token_accuracy": 0.08447866290807723,
|
|
"num_tokens": 846932.0,
|
|
"step": 485
|
|
},
|
|
{
|
|
"entropy": 7.670350217819214,
|
|
"epoch": 0.03812487842832134,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0002445,
|
|
"loss": 7.2847,
|
|
"mean_token_accuracy": 0.07881609201431275,
|
|
"num_tokens": 855333.0,
|
|
"step": 490
|
|
},
|
|
{
|
|
"entropy": 7.547208404541015,
|
|
"epoch": 0.0385139078000389,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000247,
|
|
"loss": 7.0816,
|
|
"mean_token_accuracy": 0.08268252983689309,
|
|
"num_tokens": 863571.0,
|
|
"step": 495
|
|
},
|
|
{
|
|
"entropy": 7.472938203811646,
|
|
"epoch": 0.03890293717175647,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0002495,
|
|
"loss": 7.1508,
|
|
"mean_token_accuracy": 0.0897403359413147,
|
|
"num_tokens": 872145.0,
|
|
"step": 500
|
|
},
|
|
{
|
|
"entropy": 7.586430358886719,
|
|
"epoch": 0.039291966543474034,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000252,
|
|
"loss": 7.1937,
|
|
"mean_token_accuracy": 0.08515456318855286,
|
|
"num_tokens": 880634.0,
|
|
"step": 505
|
|
},
|
|
{
|
|
"entropy": 7.575957155227661,
|
|
"epoch": 0.0396809959151916,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0002545,
|
|
"loss": 7.1256,
|
|
"mean_token_accuracy": 0.08602449670433998,
|
|
"num_tokens": 889178.0,
|
|
"step": 510
|
|
},
|
|
{
|
|
"entropy": 7.5376099109649655,
|
|
"epoch": 0.04007002528690916,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.000257,
|
|
"loss": 7.1261,
|
|
"mean_token_accuracy": 0.08836784139275551,
|
|
"num_tokens": 898255.0,
|
|
"step": 515
|
|
},
|
|
{
|
|
"entropy": 7.452177858352661,
|
|
"epoch": 0.040459054658626724,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0002595,
|
|
"loss": 7.1758,
|
|
"mean_token_accuracy": 0.08208275288343429,
|
|
"num_tokens": 907369.0,
|
|
"step": 520
|
|
},
|
|
{
|
|
"entropy": 7.568976831436157,
|
|
"epoch": 0.04084808403034429,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000262,
|
|
"loss": 7.0939,
|
|
"mean_token_accuracy": 0.08972274139523506,
|
|
"num_tokens": 915946.0,
|
|
"step": 525
|
|
},
|
|
{
|
|
"entropy": 7.516032934188843,
|
|
"epoch": 0.041237113402061855,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00026450000000000003,
|
|
"loss": 7.1498,
|
|
"mean_token_accuracy": 0.084378083050251,
|
|
"num_tokens": 925579.0,
|
|
"step": 530
|
|
},
|
|
{
|
|
"entropy": 7.533543968200684,
|
|
"epoch": 0.04162614277377942,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00026700000000000004,
|
|
"loss": 7.1322,
|
|
"mean_token_accuracy": 0.07946365103125572,
|
|
"num_tokens": 934732.0,
|
|
"step": 535
|
|
},
|
|
{
|
|
"entropy": 7.449686288833618,
|
|
"epoch": 0.042015172145496986,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00026950000000000005,
|
|
"loss": 7.1725,
|
|
"mean_token_accuracy": 0.08084325268864631,
|
|
"num_tokens": 943371.0,
|
|
"step": 540
|
|
},
|
|
{
|
|
"entropy": 7.500879001617432,
|
|
"epoch": 0.04240420151721455,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00027200000000000005,
|
|
"loss": 7.0484,
|
|
"mean_token_accuracy": 0.0895972803235054,
|
|
"num_tokens": 951977.0,
|
|
"step": 545
|
|
},
|
|
{
|
|
"entropy": 7.4533003807067875,
|
|
"epoch": 0.04279323088893212,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0002745,
|
|
"loss": 7.0355,
|
|
"mean_token_accuracy": 0.08960011452436448,
|
|
"num_tokens": 960474.0,
|
|
"step": 550
|
|
},
|
|
{
|
|
"entropy": 7.598705387115478,
|
|
"epoch": 0.04318226026064968,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000277,
|
|
"loss": 7.1391,
|
|
"mean_token_accuracy": 0.0912420243024826,
|
|
"num_tokens": 969823.0,
|
|
"step": 555
|
|
},
|
|
{
|
|
"entropy": 7.485738754272461,
|
|
"epoch": 0.04357128963236724,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0002795,
|
|
"loss": 7.0609,
|
|
"mean_token_accuracy": 0.09367068633437156,
|
|
"num_tokens": 977417.0,
|
|
"step": 560
|
|
},
|
|
{
|
|
"entropy": 7.455179023742676,
|
|
"epoch": 0.04396031900408481,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00028199999999999997,
|
|
"loss": 7.0682,
|
|
"mean_token_accuracy": 0.0958904579281807,
|
|
"num_tokens": 985519.0,
|
|
"step": 565
|
|
},
|
|
{
|
|
"entropy": 7.482391786575318,
|
|
"epoch": 0.04434934837580237,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0002845,
|
|
"loss": 7.0641,
|
|
"mean_token_accuracy": 0.08767548501491547,
|
|
"num_tokens": 994136.0,
|
|
"step": 570
|
|
},
|
|
{
|
|
"entropy": 7.325763988494873,
|
|
"epoch": 0.04473837774751994,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000287,
|
|
"loss": 7.0354,
|
|
"mean_token_accuracy": 0.08815001025795936,
|
|
"num_tokens": 1002896.0,
|
|
"step": 575
|
|
},
|
|
{
|
|
"entropy": 7.49589991569519,
|
|
"epoch": 0.0451274071192375,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0002895,
|
|
"loss": 7.1115,
|
|
"mean_token_accuracy": 0.08954815194010735,
|
|
"num_tokens": 1011032.0,
|
|
"step": 580
|
|
},
|
|
{
|
|
"entropy": 7.365485429763794,
|
|
"epoch": 0.04551643649095507,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000292,
|
|
"loss": 7.0774,
|
|
"mean_token_accuracy": 0.08928431719541549,
|
|
"num_tokens": 1019901.0,
|
|
"step": 585
|
|
},
|
|
{
|
|
"entropy": 7.4467432498931885,
|
|
"epoch": 0.045905465862672634,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0002945,
|
|
"loss": 7.0539,
|
|
"mean_token_accuracy": 0.0877431645989418,
|
|
"num_tokens": 1029049.0,
|
|
"step": 590
|
|
},
|
|
{
|
|
"entropy": 7.367093896865844,
|
|
"epoch": 0.0462944952343902,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.000297,
|
|
"loss": 7.0025,
|
|
"mean_token_accuracy": 0.09999658241868019,
|
|
"num_tokens": 1037580.0,
|
|
"step": 595
|
|
},
|
|
{
|
|
"entropy": 7.53356819152832,
|
|
"epoch": 0.04668352460610776,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0002995,
|
|
"loss": 7.0789,
|
|
"mean_token_accuracy": 0.09073482006788254,
|
|
"num_tokens": 1045804.0,
|
|
"step": 600
|
|
},
|
|
{
|
|
"entropy": 7.356887912750244,
|
|
"epoch": 0.047072553977825324,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000302,
|
|
"loss": 7.0293,
|
|
"mean_token_accuracy": 0.08818676322698593,
|
|
"num_tokens": 1054719.0,
|
|
"step": 605
|
|
},
|
|
{
|
|
"entropy": 7.446684646606445,
|
|
"epoch": 0.04746158334954289,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0003045,
|
|
"loss": 7.013,
|
|
"mean_token_accuracy": 0.08933027312159539,
|
|
"num_tokens": 1063373.0,
|
|
"step": 610
|
|
},
|
|
{
|
|
"entropy": 7.305212068557739,
|
|
"epoch": 0.047850612721260455,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000307,
|
|
"loss": 6.9932,
|
|
"mean_token_accuracy": 0.09075823351740837,
|
|
"num_tokens": 1073021.0,
|
|
"step": 615
|
|
},
|
|
{
|
|
"entropy": 7.409698390960694,
|
|
"epoch": 0.04823964209297802,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0003095,
|
|
"loss": 7.0495,
|
|
"mean_token_accuracy": 0.08623504415154457,
|
|
"num_tokens": 1081547.0,
|
|
"step": 620
|
|
},
|
|
{
|
|
"entropy": 7.397112703323364,
|
|
"epoch": 0.048628671464695586,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000312,
|
|
"loss": 7.0104,
|
|
"mean_token_accuracy": 0.08981771692633629,
|
|
"num_tokens": 1090695.0,
|
|
"step": 625
|
|
},
|
|
{
|
|
"entropy": 7.31109766960144,
|
|
"epoch": 0.04901770083641315,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0003145,
|
|
"loss": 6.9118,
|
|
"mean_token_accuracy": 0.0954255647957325,
|
|
"num_tokens": 1099563.0,
|
|
"step": 630
|
|
},
|
|
{
|
|
"entropy": 7.338528490066528,
|
|
"epoch": 0.04940673020813072,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.000317,
|
|
"loss": 6.9835,
|
|
"mean_token_accuracy": 0.09025626108050347,
|
|
"num_tokens": 1109021.0,
|
|
"step": 635
|
|
},
|
|
{
|
|
"entropy": 7.372527933120727,
|
|
"epoch": 0.049795759579848276,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0003195,
|
|
"loss": 6.9745,
|
|
"mean_token_accuracy": 0.09381573870778084,
|
|
"num_tokens": 1118281.0,
|
|
"step": 640
|
|
},
|
|
{
|
|
"entropy": 7.344166088104248,
|
|
"epoch": 0.05018478895156584,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000322,
|
|
"loss": 7.0264,
|
|
"mean_token_accuracy": 0.08852934762835503,
|
|
"num_tokens": 1127513.0,
|
|
"step": 645
|
|
},
|
|
{
|
|
"entropy": 7.236174535751343,
|
|
"epoch": 0.05057381832328341,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00032450000000000003,
|
|
"loss": 6.8914,
|
|
"mean_token_accuracy": 0.09319968894124031,
|
|
"num_tokens": 1136140.0,
|
|
"step": 650
|
|
},
|
|
{
|
|
"entropy": 7.3045234203338625,
|
|
"epoch": 0.05096284769500097,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00032700000000000003,
|
|
"loss": 6.9159,
|
|
"mean_token_accuracy": 0.09398315250873565,
|
|
"num_tokens": 1144297.0,
|
|
"step": 655
|
|
},
|
|
{
|
|
"entropy": 7.339838361740112,
|
|
"epoch": 0.05135187706671854,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00032950000000000004,
|
|
"loss": 7.0013,
|
|
"mean_token_accuracy": 0.0909078523516655,
|
|
"num_tokens": 1153639.0,
|
|
"step": 660
|
|
},
|
|
{
|
|
"entropy": 7.2977570533752445,
|
|
"epoch": 0.0517409064384361,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00033200000000000005,
|
|
"loss": 6.9892,
|
|
"mean_token_accuracy": 0.09121011421084405,
|
|
"num_tokens": 1162825.0,
|
|
"step": 665
|
|
},
|
|
{
|
|
"entropy": 7.272716379165649,
|
|
"epoch": 0.05212993581015367,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00033450000000000005,
|
|
"loss": 7.0,
|
|
"mean_token_accuracy": 0.0927580676972866,
|
|
"num_tokens": 1171887.0,
|
|
"step": 670
|
|
},
|
|
{
|
|
"entropy": 7.289681434631348,
|
|
"epoch": 0.052518965181871234,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000337,
|
|
"loss": 6.9128,
|
|
"mean_token_accuracy": 0.09554491266608238,
|
|
"num_tokens": 1179963.0,
|
|
"step": 675
|
|
},
|
|
{
|
|
"entropy": 7.24162278175354,
|
|
"epoch": 0.05290799455358879,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0003395,
|
|
"loss": 6.8815,
|
|
"mean_token_accuracy": 0.09879456236958503,
|
|
"num_tokens": 1188408.0,
|
|
"step": 680
|
|
},
|
|
{
|
|
"entropy": 7.2835136413574215,
|
|
"epoch": 0.05329702392530636,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000342,
|
|
"loss": 6.9133,
|
|
"mean_token_accuracy": 0.0909463919699192,
|
|
"num_tokens": 1197751.0,
|
|
"step": 685
|
|
},
|
|
{
|
|
"entropy": 7.258634185791015,
|
|
"epoch": 0.053686053297023924,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00034449999999999997,
|
|
"loss": 6.9544,
|
|
"mean_token_accuracy": 0.09061150550842285,
|
|
"num_tokens": 1207101.0,
|
|
"step": 690
|
|
},
|
|
{
|
|
"entropy": 7.253326082229615,
|
|
"epoch": 0.05407508266874149,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000347,
|
|
"loss": 6.9457,
|
|
"mean_token_accuracy": 0.09488306194543839,
|
|
"num_tokens": 1216395.0,
|
|
"step": 695
|
|
},
|
|
{
|
|
"entropy": 7.289101219177246,
|
|
"epoch": 0.054464112040459055,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0003495,
|
|
"loss": 6.9216,
|
|
"mean_token_accuracy": 0.09484536051750184,
|
|
"num_tokens": 1225496.0,
|
|
"step": 700
|
|
},
|
|
{
|
|
"entropy": 7.246467351913452,
|
|
"epoch": 0.05485314141217662,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000352,
|
|
"loss": 6.9826,
|
|
"mean_token_accuracy": 0.09187191799283027,
|
|
"num_tokens": 1233934.0,
|
|
"step": 705
|
|
},
|
|
{
|
|
"entropy": 7.28291802406311,
|
|
"epoch": 0.055242170783894186,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0003545,
|
|
"loss": 6.8526,
|
|
"mean_token_accuracy": 0.10444689691066741,
|
|
"num_tokens": 1242165.0,
|
|
"step": 710
|
|
},
|
|
{
|
|
"entropy": 7.235671281814575,
|
|
"epoch": 0.05563120015561175,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.000357,
|
|
"loss": 6.9106,
|
|
"mean_token_accuracy": 0.09974046424031258,
|
|
"num_tokens": 1250021.0,
|
|
"step": 715
|
|
},
|
|
{
|
|
"entropy": 7.2171196937561035,
|
|
"epoch": 0.05602022952732931,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0003595,
|
|
"loss": 6.9197,
|
|
"mean_token_accuracy": 0.09527276083827019,
|
|
"num_tokens": 1258397.0,
|
|
"step": 720
|
|
},
|
|
{
|
|
"entropy": 7.222966718673706,
|
|
"epoch": 0.056409258899046875,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000362,
|
|
"loss": 6.9115,
|
|
"mean_token_accuracy": 0.09537832140922546,
|
|
"num_tokens": 1266764.0,
|
|
"step": 725
|
|
},
|
|
{
|
|
"entropy": 7.289536237716675,
|
|
"epoch": 0.05679828827076444,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0003645,
|
|
"loss": 6.9214,
|
|
"mean_token_accuracy": 0.09203095957636834,
|
|
"num_tokens": 1275643.0,
|
|
"step": 730
|
|
},
|
|
{
|
|
"entropy": 7.227653741836548,
|
|
"epoch": 0.057187317642482006,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000367,
|
|
"loss": 6.9059,
|
|
"mean_token_accuracy": 0.0964889533817768,
|
|
"num_tokens": 1284379.0,
|
|
"step": 735
|
|
},
|
|
{
|
|
"entropy": 7.118802309036255,
|
|
"epoch": 0.05757634701419957,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0003695,
|
|
"loss": 6.7643,
|
|
"mean_token_accuracy": 0.10291910842061043,
|
|
"num_tokens": 1293115.0,
|
|
"step": 740
|
|
},
|
|
{
|
|
"entropy": 7.243952751159668,
|
|
"epoch": 0.05796537638591714,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000372,
|
|
"loss": 6.9463,
|
|
"mean_token_accuracy": 0.09045971632003784,
|
|
"num_tokens": 1301583.0,
|
|
"step": 745
|
|
},
|
|
{
|
|
"entropy": 7.1956870555877686,
|
|
"epoch": 0.0583544057576347,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0003745,
|
|
"loss": 6.8552,
|
|
"mean_token_accuracy": 0.09680608436465263,
|
|
"num_tokens": 1310721.0,
|
|
"step": 750
|
|
},
|
|
{
|
|
"entropy": 7.304637289047241,
|
|
"epoch": 0.05874343512935227,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.000377,
|
|
"loss": 6.9913,
|
|
"mean_token_accuracy": 0.0911169946193695,
|
|
"num_tokens": 1319056.0,
|
|
"step": 755
|
|
},
|
|
{
|
|
"entropy": 7.180689954757691,
|
|
"epoch": 0.059132464501069834,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0003795,
|
|
"loss": 6.8737,
|
|
"mean_token_accuracy": 0.09462213069200516,
|
|
"num_tokens": 1327259.0,
|
|
"step": 760
|
|
},
|
|
{
|
|
"entropy": 7.10323920249939,
|
|
"epoch": 0.05952149387278739,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000382,
|
|
"loss": 6.7893,
|
|
"mean_token_accuracy": 0.09687989726662635,
|
|
"num_tokens": 1335906.0,
|
|
"step": 765
|
|
},
|
|
{
|
|
"entropy": 7.191504859924317,
|
|
"epoch": 0.05991052324450496,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0003845,
|
|
"loss": 6.832,
|
|
"mean_token_accuracy": 0.09174941778182984,
|
|
"num_tokens": 1344743.0,
|
|
"step": 770
|
|
},
|
|
{
|
|
"entropy": 7.170624208450318,
|
|
"epoch": 0.060299552616222524,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00038700000000000003,
|
|
"loss": 6.8469,
|
|
"mean_token_accuracy": 0.09922058656811714,
|
|
"num_tokens": 1353211.0,
|
|
"step": 775
|
|
},
|
|
{
|
|
"entropy": 7.190778684616089,
|
|
"epoch": 0.06068858198794009,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00038950000000000003,
|
|
"loss": 6.954,
|
|
"mean_token_accuracy": 0.0928943283855915,
|
|
"num_tokens": 1361849.0,
|
|
"step": 780
|
|
},
|
|
{
|
|
"entropy": 7.262214231491089,
|
|
"epoch": 0.061077611359657655,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00039200000000000004,
|
|
"loss": 6.9363,
|
|
"mean_token_accuracy": 0.09803319126367568,
|
|
"num_tokens": 1369804.0,
|
|
"step": 785
|
|
},
|
|
{
|
|
"entropy": 7.06411600112915,
|
|
"epoch": 0.06146664073137522,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00039450000000000005,
|
|
"loss": 6.7328,
|
|
"mean_token_accuracy": 0.09864451736211777,
|
|
"num_tokens": 1378478.0,
|
|
"step": 790
|
|
},
|
|
{
|
|
"entropy": 7.197555208206177,
|
|
"epoch": 0.061855670103092786,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00039700000000000005,
|
|
"loss": 6.8123,
|
|
"mean_token_accuracy": 0.10194888114929199,
|
|
"num_tokens": 1387225.0,
|
|
"step": 795
|
|
},
|
|
{
|
|
"entropy": 7.082095813751221,
|
|
"epoch": 0.06224469947481035,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0003995,
|
|
"loss": 6.7738,
|
|
"mean_token_accuracy": 0.10356510728597641,
|
|
"num_tokens": 1395338.0,
|
|
"step": 800
|
|
},
|
|
{
|
|
"entropy": 7.111552381515503,
|
|
"epoch": 0.06263372884652792,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000402,
|
|
"loss": 6.7695,
|
|
"mean_token_accuracy": 0.10290253907442093,
|
|
"num_tokens": 1403794.0,
|
|
"step": 805
|
|
},
|
|
{
|
|
"entropy": 7.024047470092773,
|
|
"epoch": 0.06302275821824548,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004045,
|
|
"loss": 6.8432,
|
|
"mean_token_accuracy": 0.09563084170222283,
|
|
"num_tokens": 1412522.0,
|
|
"step": 810
|
|
},
|
|
{
|
|
"entropy": 7.1450153350830075,
|
|
"epoch": 0.06341178758996305,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00040699999999999997,
|
|
"loss": 6.8187,
|
|
"mean_token_accuracy": 0.09947089925408363,
|
|
"num_tokens": 1421347.0,
|
|
"step": 815
|
|
},
|
|
{
|
|
"entropy": 7.098122262954712,
|
|
"epoch": 0.0638008169616806,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004095,
|
|
"loss": 6.8049,
|
|
"mean_token_accuracy": 0.10245971083641052,
|
|
"num_tokens": 1429788.0,
|
|
"step": 820
|
|
},
|
|
{
|
|
"entropy": 7.155891752243042,
|
|
"epoch": 0.06418984633339817,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000412,
|
|
"loss": 6.8032,
|
|
"mean_token_accuracy": 0.09958769977092743,
|
|
"num_tokens": 1437442.0,
|
|
"step": 825
|
|
},
|
|
{
|
|
"entropy": 7.052066421508789,
|
|
"epoch": 0.06457887570511574,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004145,
|
|
"loss": 6.7311,
|
|
"mean_token_accuracy": 0.1029736690223217,
|
|
"num_tokens": 1445604.0,
|
|
"step": 830
|
|
},
|
|
{
|
|
"entropy": 7.043609714508056,
|
|
"epoch": 0.0649679050768333,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000417,
|
|
"loss": 6.7971,
|
|
"mean_token_accuracy": 0.10040144473314286,
|
|
"num_tokens": 1454342.0,
|
|
"step": 835
|
|
},
|
|
{
|
|
"entropy": 7.063785266876221,
|
|
"epoch": 0.06535693444855087,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004195,
|
|
"loss": 6.783,
|
|
"mean_token_accuracy": 0.10244178175926208,
|
|
"num_tokens": 1463189.0,
|
|
"step": 840
|
|
},
|
|
{
|
|
"entropy": 7.155404758453369,
|
|
"epoch": 0.06574596382026843,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000422,
|
|
"loss": 6.8392,
|
|
"mean_token_accuracy": 0.10035181567072868,
|
|
"num_tokens": 1471608.0,
|
|
"step": 845
|
|
},
|
|
{
|
|
"entropy": 7.050847911834717,
|
|
"epoch": 0.066134993191986,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004245,
|
|
"loss": 6.8413,
|
|
"mean_token_accuracy": 0.09997277483344078,
|
|
"num_tokens": 1480452.0,
|
|
"step": 850
|
|
},
|
|
{
|
|
"entropy": 7.136737203598022,
|
|
"epoch": 0.06652402256370356,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000427,
|
|
"loss": 6.7728,
|
|
"mean_token_accuracy": 0.1025382250547409,
|
|
"num_tokens": 1489118.0,
|
|
"step": 855
|
|
},
|
|
{
|
|
"entropy": 7.027253580093384,
|
|
"epoch": 0.06691305193542113,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004295,
|
|
"loss": 6.7729,
|
|
"mean_token_accuracy": 0.10166823267936706,
|
|
"num_tokens": 1498961.0,
|
|
"step": 860
|
|
},
|
|
{
|
|
"entropy": 7.135442447662354,
|
|
"epoch": 0.06730208130713869,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000432,
|
|
"loss": 6.7701,
|
|
"mean_token_accuracy": 0.10654019340872764,
|
|
"num_tokens": 1506772.0,
|
|
"step": 865
|
|
},
|
|
{
|
|
"entropy": 6.916374588012696,
|
|
"epoch": 0.06769111067885625,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004345,
|
|
"loss": 6.6407,
|
|
"mean_token_accuracy": 0.11762609407305717,
|
|
"num_tokens": 1515095.0,
|
|
"step": 870
|
|
},
|
|
{
|
|
"entropy": 6.9736268520355225,
|
|
"epoch": 0.06808014005057382,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000437,
|
|
"loss": 6.683,
|
|
"mean_token_accuracy": 0.1091225765645504,
|
|
"num_tokens": 1523477.0,
|
|
"step": 875
|
|
},
|
|
{
|
|
"entropy": 7.0554869174957275,
|
|
"epoch": 0.06846916942229138,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004395,
|
|
"loss": 6.7139,
|
|
"mean_token_accuracy": 0.10232555940747261,
|
|
"num_tokens": 1531786.0,
|
|
"step": 880
|
|
},
|
|
{
|
|
"entropy": 6.96433653831482,
|
|
"epoch": 0.06885819879400895,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000442,
|
|
"loss": 6.8101,
|
|
"mean_token_accuracy": 0.09944222122430801,
|
|
"num_tokens": 1540737.0,
|
|
"step": 885
|
|
},
|
|
{
|
|
"entropy": 6.9922035217285154,
|
|
"epoch": 0.06924722816572651,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004445,
|
|
"loss": 6.6588,
|
|
"mean_token_accuracy": 0.11068925410509109,
|
|
"num_tokens": 1548923.0,
|
|
"step": 890
|
|
},
|
|
{
|
|
"entropy": 6.973821449279785,
|
|
"epoch": 0.06963625753744408,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.000447,
|
|
"loss": 6.6204,
|
|
"mean_token_accuracy": 0.11367354318499565,
|
|
"num_tokens": 1557043.0,
|
|
"step": 895
|
|
},
|
|
{
|
|
"entropy": 6.884301996231079,
|
|
"epoch": 0.07002528690916164,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00044950000000000003,
|
|
"loss": 6.676,
|
|
"mean_token_accuracy": 0.11100396364927292,
|
|
"num_tokens": 1564994.0,
|
|
"step": 900
|
|
},
|
|
{
|
|
"entropy": 6.9740638256073,
|
|
"epoch": 0.0704143162808792,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00045200000000000004,
|
|
"loss": 6.6743,
|
|
"mean_token_accuracy": 0.10693940743803979,
|
|
"num_tokens": 1573859.0,
|
|
"step": 905
|
|
},
|
|
{
|
|
"entropy": 6.9993712425231935,
|
|
"epoch": 0.07080334565259677,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00045450000000000004,
|
|
"loss": 6.6378,
|
|
"mean_token_accuracy": 0.1043596014380455,
|
|
"num_tokens": 1581947.0,
|
|
"step": 910
|
|
},
|
|
{
|
|
"entropy": 6.931872034072876,
|
|
"epoch": 0.07119237502431433,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00045700000000000005,
|
|
"loss": 6.6297,
|
|
"mean_token_accuracy": 0.10515054538846016,
|
|
"num_tokens": 1589971.0,
|
|
"step": 915
|
|
},
|
|
{
|
|
"entropy": 6.943262052536011,
|
|
"epoch": 0.0715814043960319,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00045950000000000006,
|
|
"loss": 6.5682,
|
|
"mean_token_accuracy": 0.112590941041708,
|
|
"num_tokens": 1598612.0,
|
|
"step": 920
|
|
},
|
|
{
|
|
"entropy": 6.923539781570435,
|
|
"epoch": 0.07197043376774946,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000462,
|
|
"loss": 6.7038,
|
|
"mean_token_accuracy": 0.10295232012867928,
|
|
"num_tokens": 1607378.0,
|
|
"step": 925
|
|
},
|
|
{
|
|
"entropy": 6.933366394042968,
|
|
"epoch": 0.07235946313946703,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004645,
|
|
"loss": 6.7097,
|
|
"mean_token_accuracy": 0.10812588483095169,
|
|
"num_tokens": 1615987.0,
|
|
"step": 930
|
|
},
|
|
{
|
|
"entropy": 6.845373868942261,
|
|
"epoch": 0.07274849251118459,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000467,
|
|
"loss": 6.5179,
|
|
"mean_token_accuracy": 0.11268422231078148,
|
|
"num_tokens": 1625366.0,
|
|
"step": 935
|
|
},
|
|
{
|
|
"entropy": 6.906345510482788,
|
|
"epoch": 0.07313752188290217,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004695,
|
|
"loss": 6.684,
|
|
"mean_token_accuracy": 0.10814397260546685,
|
|
"num_tokens": 1633020.0,
|
|
"step": 940
|
|
},
|
|
{
|
|
"entropy": 6.9255390644073485,
|
|
"epoch": 0.07352655125461972,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000472,
|
|
"loss": 6.6024,
|
|
"mean_token_accuracy": 0.10560433045029641,
|
|
"num_tokens": 1641518.0,
|
|
"step": 945
|
|
},
|
|
{
|
|
"entropy": 6.891413450241089,
|
|
"epoch": 0.07391558062633728,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004745,
|
|
"loss": 6.665,
|
|
"mean_token_accuracy": 0.10579808205366134,
|
|
"num_tokens": 1650472.0,
|
|
"step": 950
|
|
},
|
|
{
|
|
"entropy": 6.896768856048584,
|
|
"epoch": 0.07430460999805485,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000477,
|
|
"loss": 6.6856,
|
|
"mean_token_accuracy": 0.10723391622304916,
|
|
"num_tokens": 1659037.0,
|
|
"step": 955
|
|
},
|
|
{
|
|
"entropy": 7.026918506622314,
|
|
"epoch": 0.07469363936977241,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004795,
|
|
"loss": 6.7696,
|
|
"mean_token_accuracy": 0.10622313320636749,
|
|
"num_tokens": 1667897.0,
|
|
"step": 960
|
|
},
|
|
{
|
|
"entropy": 6.8374017715454105,
|
|
"epoch": 0.07508266874148999,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000482,
|
|
"loss": 6.6141,
|
|
"mean_token_accuracy": 0.1083839975297451,
|
|
"num_tokens": 1676535.0,
|
|
"step": 965
|
|
},
|
|
{
|
|
"entropy": 6.900466632843018,
|
|
"epoch": 0.07547169811320754,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004845,
|
|
"loss": 6.6481,
|
|
"mean_token_accuracy": 0.10983363538980484,
|
|
"num_tokens": 1684415.0,
|
|
"step": 970
|
|
},
|
|
{
|
|
"entropy": 6.9876219749450685,
|
|
"epoch": 0.07586072748492512,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000487,
|
|
"loss": 6.6023,
|
|
"mean_token_accuracy": 0.11541447341442108,
|
|
"num_tokens": 1692443.0,
|
|
"step": 975
|
|
},
|
|
{
|
|
"entropy": 6.73767499923706,
|
|
"epoch": 0.07624975685664268,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004895,
|
|
"loss": 6.6032,
|
|
"mean_token_accuracy": 0.1102523811161518,
|
|
"num_tokens": 1700814.0,
|
|
"step": 980
|
|
},
|
|
{
|
|
"entropy": 6.8459278583526615,
|
|
"epoch": 0.07663878622836025,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000492,
|
|
"loss": 6.4589,
|
|
"mean_token_accuracy": 0.11454312652349471,
|
|
"num_tokens": 1709591.0,
|
|
"step": 985
|
|
},
|
|
{
|
|
"entropy": 6.855618333816528,
|
|
"epoch": 0.0770278156000778,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004945,
|
|
"loss": 6.6899,
|
|
"mean_token_accuracy": 0.10243948996067047,
|
|
"num_tokens": 1718951.0,
|
|
"step": 990
|
|
},
|
|
{
|
|
"entropy": 7.0016392230987545,
|
|
"epoch": 0.07741684497179536,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000497,
|
|
"loss": 6.6382,
|
|
"mean_token_accuracy": 0.10815301239490509,
|
|
"num_tokens": 1727481.0,
|
|
"step": 995
|
|
},
|
|
{
|
|
"entropy": 6.801933670043946,
|
|
"epoch": 0.07780587434351294,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004995,
|
|
"loss": 6.6336,
|
|
"mean_token_accuracy": 0.10878749638795852,
|
|
"num_tokens": 1736985.0,
|
|
"step": 1000
|
|
},
|
|
{
|
|
"entropy": 6.949926328659058,
|
|
"epoch": 0.0781949037152305,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999999989075146,
|
|
"loss": 6.6868,
|
|
"mean_token_accuracy": 0.10359607338905334,
|
|
"num_tokens": 1745470.0,
|
|
"step": 1005
|
|
},
|
|
{
|
|
"entropy": 6.897040796279907,
|
|
"epoch": 0.07858393308694807,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004999999944692927,
|
|
"loss": 6.629,
|
|
"mean_token_accuracy": 0.10731491297483445,
|
|
"num_tokens": 1754185.0,
|
|
"step": 1010
|
|
},
|
|
{
|
|
"entropy": 6.833609628677368,
|
|
"epoch": 0.07897296245866563,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000499999986617054,
|
|
"loss": 6.6342,
|
|
"mean_token_accuracy": 0.10663639605045319,
|
|
"num_tokens": 1762100.0,
|
|
"step": 1015
|
|
},
|
|
{
|
|
"entropy": 6.971498203277588,
|
|
"epoch": 0.0793619918303832,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999999753507986,
|
|
"loss": 6.6379,
|
|
"mean_token_accuracy": 0.10761738270521164,
|
|
"num_tokens": 1771070.0,
|
|
"step": 1020
|
|
},
|
|
{
|
|
"entropy": 6.819230461120606,
|
|
"epoch": 0.07975102120210076,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999999606705267,
|
|
"loss": 6.6338,
|
|
"mean_token_accuracy": 0.10975765809416771,
|
|
"num_tokens": 1780085.0,
|
|
"step": 1025
|
|
},
|
|
{
|
|
"entropy": 6.906311321258545,
|
|
"epoch": 0.08014005057381832,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999999425762385,
|
|
"loss": 6.6172,
|
|
"mean_token_accuracy": 0.113339963555336,
|
|
"num_tokens": 1789316.0,
|
|
"step": 1030
|
|
},
|
|
{
|
|
"entropy": 6.783714866638183,
|
|
"epoch": 0.08052907994553589,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999999210679344,
|
|
"loss": 6.5369,
|
|
"mean_token_accuracy": 0.112546556442976,
|
|
"num_tokens": 1797975.0,
|
|
"step": 1035
|
|
},
|
|
{
|
|
"entropy": 6.838487339019776,
|
|
"epoch": 0.08091810931725345,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999998961456145,
|
|
"loss": 6.6393,
|
|
"mean_token_accuracy": 0.11156408786773682,
|
|
"num_tokens": 1806129.0,
|
|
"step": 1040
|
|
},
|
|
{
|
|
"entropy": 6.908475303649903,
|
|
"epoch": 0.08130713868897102,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999998678092794,
|
|
"loss": 6.6392,
|
|
"mean_token_accuracy": 0.11067313626408577,
|
|
"num_tokens": 1813956.0,
|
|
"step": 1045
|
|
},
|
|
{
|
|
"entropy": 6.9355841159820555,
|
|
"epoch": 0.08169616806068858,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999998360589293,
|
|
"loss": 6.6473,
|
|
"mean_token_accuracy": 0.11026927605271339,
|
|
"num_tokens": 1822572.0,
|
|
"step": 1050
|
|
},
|
|
{
|
|
"entropy": 6.757045555114746,
|
|
"epoch": 0.08208519743240615,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000499999800894565,
|
|
"loss": 6.5619,
|
|
"mean_token_accuracy": 0.11012868583202362,
|
|
"num_tokens": 1831870.0,
|
|
"step": 1055
|
|
},
|
|
{
|
|
"entropy": 6.749943971633911,
|
|
"epoch": 0.08247422680412371,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999997623161866,
|
|
"loss": 6.593,
|
|
"mean_token_accuracy": 0.10753906518220901,
|
|
"num_tokens": 1840414.0,
|
|
"step": 1060
|
|
},
|
|
{
|
|
"entropy": 6.898047304153442,
|
|
"epoch": 0.08286325617584128,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999997203237951,
|
|
"loss": 6.6142,
|
|
"mean_token_accuracy": 0.10993773117661476,
|
|
"num_tokens": 1850385.0,
|
|
"step": 1065
|
|
},
|
|
{
|
|
"entropy": 6.692205476760864,
|
|
"epoch": 0.08325228554755884,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000499999674917391,
|
|
"loss": 6.5192,
|
|
"mean_token_accuracy": 0.12006976082921028,
|
|
"num_tokens": 1858479.0,
|
|
"step": 1070
|
|
},
|
|
{
|
|
"entropy": 6.8471941471099855,
|
|
"epoch": 0.0836413149192764,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999996260969748,
|
|
"loss": 6.5988,
|
|
"mean_token_accuracy": 0.10776122882962227,
|
|
"num_tokens": 1867357.0,
|
|
"step": 1075
|
|
},
|
|
{
|
|
"entropy": 6.78913459777832,
|
|
"epoch": 0.08403034429099397,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999995738625475,
|
|
"loss": 6.5436,
|
|
"mean_token_accuracy": 0.10430336892604827,
|
|
"num_tokens": 1876211.0,
|
|
"step": 1080
|
|
},
|
|
{
|
|
"entropy": 6.690899896621704,
|
|
"epoch": 0.08441937366271153,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999995182141099,
|
|
"loss": 6.4663,
|
|
"mean_token_accuracy": 0.10824713706970215,
|
|
"num_tokens": 1884301.0,
|
|
"step": 1085
|
|
},
|
|
{
|
|
"entropy": 6.911795234680175,
|
|
"epoch": 0.0848084030344291,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999994591516626,
|
|
"loss": 6.622,
|
|
"mean_token_accuracy": 0.11672904044389724,
|
|
"num_tokens": 1893191.0,
|
|
"step": 1090
|
|
},
|
|
{
|
|
"entropy": 6.69744906425476,
|
|
"epoch": 0.08519743240614666,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999993966752066,
|
|
"loss": 6.4871,
|
|
"mean_token_accuracy": 0.11046854481101036,
|
|
"num_tokens": 1901434.0,
|
|
"step": 1095
|
|
},
|
|
{
|
|
"entropy": 6.7617669105529785,
|
|
"epoch": 0.08558646177786423,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000499999330784743,
|
|
"loss": 6.4873,
|
|
"mean_token_accuracy": 0.1202208161354065,
|
|
"num_tokens": 1910054.0,
|
|
"step": 1100
|
|
},
|
|
{
|
|
"entropy": 6.82279953956604,
|
|
"epoch": 0.08597549114958179,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999992614802725,
|
|
"loss": 6.6178,
|
|
"mean_token_accuracy": 0.11331576108932495,
|
|
"num_tokens": 1918607.0,
|
|
"step": 1105
|
|
},
|
|
{
|
|
"entropy": 6.74808177947998,
|
|
"epoch": 0.08636452052129936,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004999991887617966,
|
|
"loss": 6.5604,
|
|
"mean_token_accuracy": 0.11329781040549278,
|
|
"num_tokens": 1927610.0,
|
|
"step": 1110
|
|
},
|
|
{
|
|
"entropy": 6.721193456649781,
|
|
"epoch": 0.08675354989301692,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004999991126293158,
|
|
"loss": 6.5076,
|
|
"mean_token_accuracy": 0.11460185199975967,
|
|
"num_tokens": 1936174.0,
|
|
"step": 1115
|
|
},
|
|
{
|
|
"entropy": 6.726939487457275,
|
|
"epoch": 0.08714257926473448,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999990330828318,
|
|
"loss": 6.437,
|
|
"mean_token_accuracy": 0.12100310698151588,
|
|
"num_tokens": 1944228.0,
|
|
"step": 1120
|
|
},
|
|
{
|
|
"entropy": 6.830557537078858,
|
|
"epoch": 0.08753160863645205,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999989501223456,
|
|
"loss": 6.5437,
|
|
"mean_token_accuracy": 0.11512776464223862,
|
|
"num_tokens": 1953144.0,
|
|
"step": 1125
|
|
},
|
|
{
|
|
"entropy": 6.717128944396973,
|
|
"epoch": 0.08792063800816961,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999988637478584,
|
|
"loss": 6.5947,
|
|
"mean_token_accuracy": 0.11105897948145867,
|
|
"num_tokens": 1961947.0,
|
|
"step": 1130
|
|
},
|
|
{
|
|
"entropy": 6.843059253692627,
|
|
"epoch": 0.08830966737988719,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999987739593716,
|
|
"loss": 6.5708,
|
|
"mean_token_accuracy": 0.11229311525821686,
|
|
"num_tokens": 1970674.0,
|
|
"step": 1135
|
|
},
|
|
{
|
|
"entropy": 6.781560564041138,
|
|
"epoch": 0.08869869675160474,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999986807568865,
|
|
"loss": 6.5356,
|
|
"mean_token_accuracy": 0.11566499695181846,
|
|
"num_tokens": 1979173.0,
|
|
"step": 1140
|
|
},
|
|
{
|
|
"entropy": 6.708818435668945,
|
|
"epoch": 0.08908772612332232,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999985841404045,
|
|
"loss": 6.5334,
|
|
"mean_token_accuracy": 0.11458146646618843,
|
|
"num_tokens": 1988134.0,
|
|
"step": 1145
|
|
},
|
|
{
|
|
"entropy": 6.784994983673096,
|
|
"epoch": 0.08947675549503988,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999984841099271,
|
|
"loss": 6.4755,
|
|
"mean_token_accuracy": 0.11356236785650253,
|
|
"num_tokens": 1996977.0,
|
|
"step": 1150
|
|
},
|
|
{
|
|
"entropy": 6.741352796554565,
|
|
"epoch": 0.08986578486675743,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000499998380665456,
|
|
"loss": 6.5366,
|
|
"mean_token_accuracy": 0.11298326328396797,
|
|
"num_tokens": 2005946.0,
|
|
"step": 1155
|
|
},
|
|
{
|
|
"entropy": 6.695943164825439,
|
|
"epoch": 0.090254814238475,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999982738069924,
|
|
"loss": 6.3749,
|
|
"mean_token_accuracy": 0.11534976065158845,
|
|
"num_tokens": 2014882.0,
|
|
"step": 1160
|
|
},
|
|
{
|
|
"entropy": 6.682829093933106,
|
|
"epoch": 0.09064384361019256,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999981635345382,
|
|
"loss": 6.5476,
|
|
"mean_token_accuracy": 0.11290719136595725,
|
|
"num_tokens": 2024858.0,
|
|
"step": 1165
|
|
},
|
|
{
|
|
"entropy": 6.672901630401611,
|
|
"epoch": 0.09103287298191014,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004999980498480949,
|
|
"loss": 6.466,
|
|
"mean_token_accuracy": 0.11438599750399589,
|
|
"num_tokens": 2034072.0,
|
|
"step": 1170
|
|
},
|
|
{
|
|
"entropy": 6.712941026687622,
|
|
"epoch": 0.0914219023536277,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999979327476644,
|
|
"loss": 6.4753,
|
|
"mean_token_accuracy": 0.11522193774580955,
|
|
"num_tokens": 2042649.0,
|
|
"step": 1175
|
|
},
|
|
{
|
|
"entropy": 6.714944648742676,
|
|
"epoch": 0.09181093172534527,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999978122332485,
|
|
"loss": 6.4979,
|
|
"mean_token_accuracy": 0.11657196953892708,
|
|
"num_tokens": 2050866.0,
|
|
"step": 1180
|
|
},
|
|
{
|
|
"entropy": 6.751889419555664,
|
|
"epoch": 0.09219996109706283,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999976883048487,
|
|
"loss": 6.4984,
|
|
"mean_token_accuracy": 0.1147743172943592,
|
|
"num_tokens": 2058914.0,
|
|
"step": 1185
|
|
},
|
|
{
|
|
"entropy": 6.674278974533081,
|
|
"epoch": 0.0925889904687804,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999975609624673,
|
|
"loss": 6.4469,
|
|
"mean_token_accuracy": 0.11601505503058433,
|
|
"num_tokens": 2068098.0,
|
|
"step": 1190
|
|
},
|
|
{
|
|
"entropy": 6.666662788391113,
|
|
"epoch": 0.09297801984049796,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999974302061059,
|
|
"loss": 6.4465,
|
|
"mean_token_accuracy": 0.11012001484632492,
|
|
"num_tokens": 2077299.0,
|
|
"step": 1195
|
|
},
|
|
{
|
|
"entropy": 6.718023204803467,
|
|
"epoch": 0.09336704921221552,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999972960357666,
|
|
"loss": 6.5418,
|
|
"mean_token_accuracy": 0.11328572109341621,
|
|
"num_tokens": 2087868.0,
|
|
"step": 1200
|
|
},
|
|
{
|
|
"entropy": 6.68776216506958,
|
|
"epoch": 0.09375607858393309,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999971584514516,
|
|
"loss": 6.4704,
|
|
"mean_token_accuracy": 0.12280796691775323,
|
|
"num_tokens": 2096553.0,
|
|
"step": 1205
|
|
},
|
|
{
|
|
"entropy": 6.763374853134155,
|
|
"epoch": 0.09414510795565065,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999970174531627,
|
|
"loss": 6.4254,
|
|
"mean_token_accuracy": 0.11939279362559319,
|
|
"num_tokens": 2104809.0,
|
|
"step": 1210
|
|
},
|
|
{
|
|
"entropy": 6.544530963897705,
|
|
"epoch": 0.09453413732736822,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999968730409022,
|
|
"loss": 6.4114,
|
|
"mean_token_accuracy": 0.11297131180763245,
|
|
"num_tokens": 2113869.0,
|
|
"step": 1215
|
|
},
|
|
{
|
|
"entropy": 6.637964534759521,
|
|
"epoch": 0.09492316669908578,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999967252146723,
|
|
"loss": 6.245,
|
|
"mean_token_accuracy": 0.1171722136437893,
|
|
"num_tokens": 2121749.0,
|
|
"step": 1220
|
|
},
|
|
{
|
|
"entropy": 6.630059051513672,
|
|
"epoch": 0.09531219607080335,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999965739744752,
|
|
"loss": 6.4551,
|
|
"mean_token_accuracy": 0.11625204831361771,
|
|
"num_tokens": 2130828.0,
|
|
"step": 1225
|
|
},
|
|
{
|
|
"entropy": 6.729389619827271,
|
|
"epoch": 0.09570122544252091,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999964193203132,
|
|
"loss": 6.4343,
|
|
"mean_token_accuracy": 0.11840956956148148,
|
|
"num_tokens": 2138928.0,
|
|
"step": 1230
|
|
},
|
|
{
|
|
"entropy": 6.677809381484986,
|
|
"epoch": 0.09609025481423847,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999962612521888,
|
|
"loss": 6.4553,
|
|
"mean_token_accuracy": 0.11565364599227905,
|
|
"num_tokens": 2147643.0,
|
|
"step": 1235
|
|
},
|
|
{
|
|
"entropy": 6.696507167816162,
|
|
"epoch": 0.09647928418595604,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004999960997701041,
|
|
"loss": 6.3968,
|
|
"mean_token_accuracy": 0.1201579064130783,
|
|
"num_tokens": 2156766.0,
|
|
"step": 1240
|
|
},
|
|
{
|
|
"entropy": 6.621823453903199,
|
|
"epoch": 0.0968683135576736,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999959348740618,
|
|
"loss": 6.4417,
|
|
"mean_token_accuracy": 0.11661816611886025,
|
|
"num_tokens": 2165517.0,
|
|
"step": 1245
|
|
},
|
|
{
|
|
"entropy": 6.576675033569336,
|
|
"epoch": 0.09725734292939117,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999957665640641,
|
|
"loss": 6.3206,
|
|
"mean_token_accuracy": 0.12200571298599243,
|
|
"num_tokens": 2174812.0,
|
|
"step": 1250
|
|
},
|
|
{
|
|
"entropy": 6.646194124221802,
|
|
"epoch": 0.09764637230110873,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000499995594840114,
|
|
"loss": 6.4638,
|
|
"mean_token_accuracy": 0.12040529623627663,
|
|
"num_tokens": 2183968.0,
|
|
"step": 1255
|
|
},
|
|
{
|
|
"entropy": 6.681028127670288,
|
|
"epoch": 0.0980354016728263,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004999954197022138,
|
|
"loss": 6.4909,
|
|
"mean_token_accuracy": 0.1184639185667038,
|
|
"num_tokens": 2191947.0,
|
|
"step": 1260
|
|
},
|
|
{
|
|
"entropy": 6.642876625061035,
|
|
"epoch": 0.09842443104454386,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999952411503661,
|
|
"loss": 6.3293,
|
|
"mean_token_accuracy": 0.12336919456720352,
|
|
"num_tokens": 2199951.0,
|
|
"step": 1265
|
|
},
|
|
{
|
|
"entropy": 6.591861581802368,
|
|
"epoch": 0.09881346041626143,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999950591845738,
|
|
"loss": 6.4673,
|
|
"mean_token_accuracy": 0.11935944855213165,
|
|
"num_tokens": 2208714.0,
|
|
"step": 1270
|
|
},
|
|
{
|
|
"entropy": 6.581157541275024,
|
|
"epoch": 0.09920248978797899,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999948738048397,
|
|
"loss": 6.3282,
|
|
"mean_token_accuracy": 0.11878729537129402,
|
|
"num_tokens": 2217250.0,
|
|
"step": 1275
|
|
},
|
|
{
|
|
"entropy": 6.7235880374908445,
|
|
"epoch": 0.09959151915969655,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999946850111663,
|
|
"loss": 6.3894,
|
|
"mean_token_accuracy": 0.12055943980813026,
|
|
"num_tokens": 2225468.0,
|
|
"step": 1280
|
|
},
|
|
{
|
|
"entropy": 6.508683109283448,
|
|
"epoch": 0.09998054853141412,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999944928035569,
|
|
"loss": 6.3437,
|
|
"mean_token_accuracy": 0.12606204822659492,
|
|
"num_tokens": 2233893.0,
|
|
"step": 1285
|
|
},
|
|
{
|
|
"entropy": 6.760361814498902,
|
|
"epoch": 0.10036957790313168,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000499994297182014,
|
|
"loss": 6.4239,
|
|
"mean_token_accuracy": 0.11900506541132927,
|
|
"num_tokens": 2242487.0,
|
|
"step": 1290
|
|
},
|
|
{
|
|
"entropy": 6.464075803756714,
|
|
"epoch": 0.10075860727484925,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999940981465408,
|
|
"loss": 6.2418,
|
|
"mean_token_accuracy": 0.12773674577474595,
|
|
"num_tokens": 2250518.0,
|
|
"step": 1295
|
|
},
|
|
{
|
|
"entropy": 6.635386562347412,
|
|
"epoch": 0.10114763664656681,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999938956971404,
|
|
"loss": 6.4266,
|
|
"mean_token_accuracy": 0.11632013618946076,
|
|
"num_tokens": 2259024.0,
|
|
"step": 1300
|
|
},
|
|
{
|
|
"entropy": 6.615658807754516,
|
|
"epoch": 0.10153666601828439,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999936898338156,
|
|
"loss": 6.4632,
|
|
"mean_token_accuracy": 0.11199147924780846,
|
|
"num_tokens": 2267832.0,
|
|
"step": 1305
|
|
},
|
|
{
|
|
"entropy": 6.635924625396728,
|
|
"epoch": 0.10192569539000194,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999934805565698,
|
|
"loss": 6.5261,
|
|
"mean_token_accuracy": 0.11091560125350952,
|
|
"num_tokens": 2276834.0,
|
|
"step": 1310
|
|
},
|
|
{
|
|
"entropy": 6.73242449760437,
|
|
"epoch": 0.10231472476171952,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000499993267865406,
|
|
"loss": 6.4461,
|
|
"mean_token_accuracy": 0.11519345194101334,
|
|
"num_tokens": 2285736.0,
|
|
"step": 1315
|
|
},
|
|
{
|
|
"entropy": 6.697244501113891,
|
|
"epoch": 0.10270375413343708,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999930517603275,
|
|
"loss": 6.4108,
|
|
"mean_token_accuracy": 0.1263464353978634,
|
|
"num_tokens": 2294177.0,
|
|
"step": 1320
|
|
},
|
|
{
|
|
"entropy": 6.468812894821167,
|
|
"epoch": 0.10309278350515463,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999928322413374,
|
|
"loss": 6.1839,
|
|
"mean_token_accuracy": 0.12833936586976052,
|
|
"num_tokens": 2302784.0,
|
|
"step": 1325
|
|
},
|
|
{
|
|
"entropy": 6.505994129180908,
|
|
"epoch": 0.1034818128768722,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999926093084394,
|
|
"loss": 6.2968,
|
|
"mean_token_accuracy": 0.12245660051703453,
|
|
"num_tokens": 2311650.0,
|
|
"step": 1330
|
|
},
|
|
{
|
|
"entropy": 6.66971116065979,
|
|
"epoch": 0.10387084224858976,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999923829616365,
|
|
"loss": 6.3996,
|
|
"mean_token_accuracy": 0.11883401051163674,
|
|
"num_tokens": 2319828.0,
|
|
"step": 1335
|
|
},
|
|
{
|
|
"entropy": 6.553110504150391,
|
|
"epoch": 0.10425987162030734,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999921532009323,
|
|
"loss": 6.416,
|
|
"mean_token_accuracy": 0.11476577743887902,
|
|
"num_tokens": 2328636.0,
|
|
"step": 1340
|
|
},
|
|
{
|
|
"entropy": 6.5455653190612795,
|
|
"epoch": 0.1046489009920249,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999919200263304,
|
|
"loss": 6.2977,
|
|
"mean_token_accuracy": 0.12469864264130592,
|
|
"num_tokens": 2336771.0,
|
|
"step": 1345
|
|
},
|
|
{
|
|
"entropy": 6.624483728408814,
|
|
"epoch": 0.10503793036374247,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999916834378342,
|
|
"loss": 6.4529,
|
|
"mean_token_accuracy": 0.11439902409911155,
|
|
"num_tokens": 2346106.0,
|
|
"step": 1350
|
|
},
|
|
{
|
|
"entropy": 6.588077735900879,
|
|
"epoch": 0.10542695973546003,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999914434354472,
|
|
"loss": 6.4435,
|
|
"mean_token_accuracy": 0.11157507598400115,
|
|
"num_tokens": 2354943.0,
|
|
"step": 1355
|
|
},
|
|
{
|
|
"entropy": 6.484687662124633,
|
|
"epoch": 0.10581598910717759,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999912000191733,
|
|
"loss": 6.3291,
|
|
"mean_token_accuracy": 0.12155802845954895,
|
|
"num_tokens": 2363699.0,
|
|
"step": 1360
|
|
},
|
|
{
|
|
"entropy": 6.56774754524231,
|
|
"epoch": 0.10620501847889516,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000499990953189016,
|
|
"loss": 6.4607,
|
|
"mean_token_accuracy": 0.11734867691993714,
|
|
"num_tokens": 2373316.0,
|
|
"step": 1365
|
|
},
|
|
{
|
|
"entropy": 6.792719316482544,
|
|
"epoch": 0.10659404785061272,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999907029449791,
|
|
"loss": 6.5466,
|
|
"mean_token_accuracy": 0.1130414329469204,
|
|
"num_tokens": 2381550.0,
|
|
"step": 1370
|
|
},
|
|
{
|
|
"entropy": 6.568495798110962,
|
|
"epoch": 0.10698307722233029,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999904492870663,
|
|
"loss": 6.3407,
|
|
"mean_token_accuracy": 0.12280402705073357,
|
|
"num_tokens": 2389546.0,
|
|
"step": 1375
|
|
},
|
|
{
|
|
"entropy": 6.602413702011108,
|
|
"epoch": 0.10737210659404785,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999901922152816,
|
|
"loss": 6.3119,
|
|
"mean_token_accuracy": 0.12875628471374512,
|
|
"num_tokens": 2398852.0,
|
|
"step": 1380
|
|
},
|
|
{
|
|
"entropy": 6.514067602157593,
|
|
"epoch": 0.10776113596576542,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999899317296288,
|
|
"loss": 6.4055,
|
|
"mean_token_accuracy": 0.11861231550574303,
|
|
"num_tokens": 2407815.0,
|
|
"step": 1385
|
|
},
|
|
{
|
|
"entropy": 6.577896213531494,
|
|
"epoch": 0.10815016533748298,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004999896678301121,
|
|
"loss": 6.2648,
|
|
"mean_token_accuracy": 0.12172571048140526,
|
|
"num_tokens": 2417300.0,
|
|
"step": 1390
|
|
},
|
|
{
|
|
"entropy": 6.5998763084411625,
|
|
"epoch": 0.10853919470920055,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999894005167352,
|
|
"loss": 6.4098,
|
|
"mean_token_accuracy": 0.12156257852911949,
|
|
"num_tokens": 2426257.0,
|
|
"step": 1395
|
|
},
|
|
{
|
|
"entropy": 6.676355028152466,
|
|
"epoch": 0.10892822408091811,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000499989129789502,
|
|
"loss": 6.4257,
|
|
"mean_token_accuracy": 0.1204957626760006,
|
|
"num_tokens": 2434595.0,
|
|
"step": 1400
|
|
},
|
|
{
|
|
"entropy": 6.654974126815796,
|
|
"epoch": 0.10931725345263567,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004999888556484172,
|
|
"loss": 6.4462,
|
|
"mean_token_accuracy": 0.11929797455668449,
|
|
"num_tokens": 2443945.0,
|
|
"step": 1405
|
|
},
|
|
{
|
|
"entropy": 6.505768489837647,
|
|
"epoch": 0.10970628282435324,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999885780934845,
|
|
"loss": 6.3098,
|
|
"mean_token_accuracy": 0.12298460751771927,
|
|
"num_tokens": 2453141.0,
|
|
"step": 1410
|
|
},
|
|
{
|
|
"entropy": 6.586579370498657,
|
|
"epoch": 0.1100953121960708,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999882971247081,
|
|
"loss": 6.3959,
|
|
"mean_token_accuracy": 0.11581015586853027,
|
|
"num_tokens": 2461873.0,
|
|
"step": 1415
|
|
},
|
|
{
|
|
"entropy": 6.595294094085693,
|
|
"epoch": 0.11048434156778837,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999880127420926,
|
|
"loss": 6.4179,
|
|
"mean_token_accuracy": 0.11764904409646988,
|
|
"num_tokens": 2471238.0,
|
|
"step": 1420
|
|
},
|
|
{
|
|
"entropy": 6.5501360416412355,
|
|
"epoch": 0.11087337093950593,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999877249456421,
|
|
"loss": 6.2916,
|
|
"mean_token_accuracy": 0.1313754253089428,
|
|
"num_tokens": 2479412.0,
|
|
"step": 1425
|
|
},
|
|
{
|
|
"entropy": 6.429438781738281,
|
|
"epoch": 0.1112624003112235,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999874337353609,
|
|
"loss": 6.2078,
|
|
"mean_token_accuracy": 0.1259915679693222,
|
|
"num_tokens": 2488150.0,
|
|
"step": 1430
|
|
},
|
|
{
|
|
"entropy": 6.529017305374145,
|
|
"epoch": 0.11165142968294106,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004999871391112535,
|
|
"loss": 6.3654,
|
|
"mean_token_accuracy": 0.1272561579942703,
|
|
"num_tokens": 2498103.0,
|
|
"step": 1435
|
|
},
|
|
{
|
|
"entropy": 6.49380464553833,
|
|
"epoch": 0.11204045905465862,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999868410733244,
|
|
"loss": 6.2319,
|
|
"mean_token_accuracy": 0.1280946686863899,
|
|
"num_tokens": 2506211.0,
|
|
"step": 1440
|
|
},
|
|
{
|
|
"entropy": 6.4133141994476315,
|
|
"epoch": 0.11242948842637619,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000499986539621578,
|
|
"loss": 6.2552,
|
|
"mean_token_accuracy": 0.1278551071882248,
|
|
"num_tokens": 2514743.0,
|
|
"step": 1445
|
|
},
|
|
{
|
|
"entropy": 6.430079650878906,
|
|
"epoch": 0.11281851779809375,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004999862347560191,
|
|
"loss": 6.2533,
|
|
"mean_token_accuracy": 0.12282558158040047,
|
|
"num_tokens": 2523824.0,
|
|
"step": 1450
|
|
},
|
|
{
|
|
"entropy": 6.598657894134521,
|
|
"epoch": 0.11320754716981132,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004999859264766521,
|
|
"loss": 6.3219,
|
|
"mean_token_accuracy": 0.12097884491086006,
|
|
"num_tokens": 2532360.0,
|
|
"step": 1455
|
|
},
|
|
{
|
|
"entropy": 6.540658664703369,
|
|
"epoch": 0.11359657654152888,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999856147834817,
|
|
"loss": 6.2807,
|
|
"mean_token_accuracy": 0.13108301162719727,
|
|
"num_tokens": 2540547.0,
|
|
"step": 1460
|
|
},
|
|
{
|
|
"entropy": 6.4696839332580565,
|
|
"epoch": 0.11398560591324645,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999852996765129,
|
|
"loss": 6.3052,
|
|
"mean_token_accuracy": 0.12217096462845803,
|
|
"num_tokens": 2549193.0,
|
|
"step": 1465
|
|
},
|
|
{
|
|
"entropy": 6.500145196914673,
|
|
"epoch": 0.11437463528496401,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999849811557502,
|
|
"loss": 6.3173,
|
|
"mean_token_accuracy": 0.11922707110643387,
|
|
"num_tokens": 2557553.0,
|
|
"step": 1470
|
|
},
|
|
{
|
|
"entropy": 6.638996171951294,
|
|
"epoch": 0.11476366465668159,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999846592211984,
|
|
"loss": 6.4043,
|
|
"mean_token_accuracy": 0.1211747631430626,
|
|
"num_tokens": 2565945.0,
|
|
"step": 1475
|
|
},
|
|
{
|
|
"entropy": 6.573302364349365,
|
|
"epoch": 0.11515269402839914,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999843338728626,
|
|
"loss": 6.2786,
|
|
"mean_token_accuracy": 0.11536813229322433,
|
|
"num_tokens": 2574364.0,
|
|
"step": 1480
|
|
},
|
|
{
|
|
"entropy": 6.438839960098266,
|
|
"epoch": 0.1155417234001167,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004999840051107476,
|
|
"loss": 6.2133,
|
|
"mean_token_accuracy": 0.12060227617621422,
|
|
"num_tokens": 2582825.0,
|
|
"step": 1485
|
|
},
|
|
{
|
|
"entropy": 6.600337505340576,
|
|
"epoch": 0.11593075277183428,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999836729348584,
|
|
"loss": 6.3589,
|
|
"mean_token_accuracy": 0.12052287831902504,
|
|
"num_tokens": 2591628.0,
|
|
"step": 1490
|
|
},
|
|
{
|
|
"entropy": 6.495076751708984,
|
|
"epoch": 0.11631978214355183,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999833373452,
|
|
"loss": 6.3561,
|
|
"mean_token_accuracy": 0.1171538695693016,
|
|
"num_tokens": 2600436.0,
|
|
"step": 1495
|
|
},
|
|
{
|
|
"entropy": 6.521013927459717,
|
|
"epoch": 0.1167088115152694,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999829983417778,
|
|
"loss": 6.299,
|
|
"mean_token_accuracy": 0.12321334183216096,
|
|
"num_tokens": 2609709.0,
|
|
"step": 1500
|
|
},
|
|
{
|
|
"entropy": 6.610712099075317,
|
|
"epoch": 0.11709784088698696,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999826559245965,
|
|
"loss": 6.3006,
|
|
"mean_token_accuracy": 0.12215944081544876,
|
|
"num_tokens": 2617992.0,
|
|
"step": 1505
|
|
},
|
|
{
|
|
"entropy": 6.396210336685181,
|
|
"epoch": 0.11748687025870454,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004999823100936615,
|
|
"loss": 6.2158,
|
|
"mean_token_accuracy": 0.12474563270807267,
|
|
"num_tokens": 2626706.0,
|
|
"step": 1510
|
|
},
|
|
{
|
|
"entropy": 6.615616989135742,
|
|
"epoch": 0.1178758996304221,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999819608489781,
|
|
"loss": 6.287,
|
|
"mean_token_accuracy": 0.12880871593952178,
|
|
"num_tokens": 2634642.0,
|
|
"step": 1515
|
|
},
|
|
{
|
|
"entropy": 6.544697713851929,
|
|
"epoch": 0.11826492900213967,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999816081905515,
|
|
"loss": 6.3346,
|
|
"mean_token_accuracy": 0.11531090214848519,
|
|
"num_tokens": 2644160.0,
|
|
"step": 1520
|
|
},
|
|
{
|
|
"entropy": 6.434164953231812,
|
|
"epoch": 0.11865395837385723,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999812521183872,
|
|
"loss": 6.2948,
|
|
"mean_token_accuracy": 0.11871815845370293,
|
|
"num_tokens": 2653390.0,
|
|
"step": 1525
|
|
},
|
|
{
|
|
"entropy": 6.589237403869629,
|
|
"epoch": 0.11904298774557479,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999808926324903,
|
|
"loss": 6.3435,
|
|
"mean_token_accuracy": 0.12100820019841194,
|
|
"num_tokens": 2662561.0,
|
|
"step": 1530
|
|
},
|
|
{
|
|
"entropy": 6.478472805023193,
|
|
"epoch": 0.11943201711729236,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999805297328665,
|
|
"loss": 6.3086,
|
|
"mean_token_accuracy": 0.11910761371254922,
|
|
"num_tokens": 2670694.0,
|
|
"step": 1535
|
|
},
|
|
{
|
|
"entropy": 6.46109447479248,
|
|
"epoch": 0.11982104648900992,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999801634195214,
|
|
"loss": 6.1965,
|
|
"mean_token_accuracy": 0.12499032095074654,
|
|
"num_tokens": 2679583.0,
|
|
"step": 1540
|
|
},
|
|
{
|
|
"entropy": 6.4330726146698,
|
|
"epoch": 0.12021007586072749,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999797936924603,
|
|
"loss": 6.1847,
|
|
"mean_token_accuracy": 0.13039473071694374,
|
|
"num_tokens": 2688429.0,
|
|
"step": 1545
|
|
},
|
|
{
|
|
"entropy": 6.5682470321655275,
|
|
"epoch": 0.12059910523244505,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000499979420551689,
|
|
"loss": 6.258,
|
|
"mean_token_accuracy": 0.12565399780869485,
|
|
"num_tokens": 2697134.0,
|
|
"step": 1550
|
|
},
|
|
{
|
|
"entropy": 6.446918916702271,
|
|
"epoch": 0.12098813460416262,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.000499979043997213,
|
|
"loss": 6.4093,
|
|
"mean_token_accuracy": 0.11900994554162025,
|
|
"num_tokens": 2705641.0,
|
|
"step": 1555
|
|
},
|
|
{
|
|
"entropy": 6.5380446434021,
|
|
"epoch": 0.12137716397588018,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004999786640290381,
|
|
"loss": 6.333,
|
|
"mean_token_accuracy": 0.1262545704841614,
|
|
"num_tokens": 2714977.0,
|
|
"step": 1560
|
|
},
|
|
{
|
|
"entropy": 6.517403984069825,
|
|
"epoch": 0.12176619334759774,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999782806471701,
|
|
"loss": 6.1801,
|
|
"mean_token_accuracy": 0.13938897997140884,
|
|
"num_tokens": 2723120.0,
|
|
"step": 1565
|
|
},
|
|
{
|
|
"entropy": 6.311800098419189,
|
|
"epoch": 0.12215522271931531,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999778938516147,
|
|
"loss": 6.1791,
|
|
"mean_token_accuracy": 0.1359429642558098,
|
|
"num_tokens": 2731964.0,
|
|
"step": 1570
|
|
},
|
|
{
|
|
"entropy": 6.646980047225952,
|
|
"epoch": 0.12254425209103287,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000499977503642378,
|
|
"loss": 6.2559,
|
|
"mean_token_accuracy": 0.1213235966861248,
|
|
"num_tokens": 2741537.0,
|
|
"step": 1575
|
|
},
|
|
{
|
|
"entropy": 6.3805046558380125,
|
|
"epoch": 0.12293328146275044,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999771100194656,
|
|
"loss": 6.3638,
|
|
"mean_token_accuracy": 0.12285436391830444,
|
|
"num_tokens": 2751522.0,
|
|
"step": 1580
|
|
},
|
|
{
|
|
"entropy": 6.59956202507019,
|
|
"epoch": 0.123322310834468,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999767129828837,
|
|
"loss": 6.3669,
|
|
"mean_token_accuracy": 0.11640789434313774,
|
|
"num_tokens": 2761100.0,
|
|
"step": 1585
|
|
},
|
|
{
|
|
"entropy": 6.441359281539917,
|
|
"epoch": 0.12371134020618557,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999763125326383,
|
|
"loss": 6.2932,
|
|
"mean_token_accuracy": 0.1239714004099369,
|
|
"num_tokens": 2769171.0,
|
|
"step": 1590
|
|
},
|
|
{
|
|
"entropy": 6.480400943756104,
|
|
"epoch": 0.12410036957790313,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999759086687355,
|
|
"loss": 6.2306,
|
|
"mean_token_accuracy": 0.12737515345215797,
|
|
"num_tokens": 2778021.0,
|
|
"step": 1595
|
|
},
|
|
{
|
|
"entropy": 6.3953241348266605,
|
|
"epoch": 0.1244893989496207,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999755013911813,
|
|
"loss": 6.1706,
|
|
"mean_token_accuracy": 0.12780368328094482,
|
|
"num_tokens": 2787206.0,
|
|
"step": 1600
|
|
},
|
|
{
|
|
"entropy": 6.448420667648316,
|
|
"epoch": 0.12487842832133826,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.000499975090699982,
|
|
"loss": 6.2372,
|
|
"mean_token_accuracy": 0.12469636872410775,
|
|
"num_tokens": 2796051.0,
|
|
"step": 1605
|
|
},
|
|
{
|
|
"entropy": 6.501862096786499,
|
|
"epoch": 0.12526745769305583,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004999746765951438,
|
|
"loss": 6.1934,
|
|
"mean_token_accuracy": 0.12748273462057114,
|
|
"num_tokens": 2804961.0,
|
|
"step": 1610
|
|
},
|
|
{
|
|
"entropy": 6.395801019668579,
|
|
"epoch": 0.1256564870647734,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999742590766729,
|
|
"loss": 6.1504,
|
|
"mean_token_accuracy": 0.12995274290442466,
|
|
"num_tokens": 2813691.0,
|
|
"step": 1615
|
|
},
|
|
{
|
|
"entropy": 6.438721466064453,
|
|
"epoch": 0.12604551643649095,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999738381445757,
|
|
"loss": 6.2961,
|
|
"mean_token_accuracy": 0.12733198031783105,
|
|
"num_tokens": 2822248.0,
|
|
"step": 1620
|
|
},
|
|
{
|
|
"entropy": 6.4921409606933596,
|
|
"epoch": 0.1264345458082085,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999734137988586,
|
|
"loss": 6.2473,
|
|
"mean_token_accuracy": 0.12927133068442345,
|
|
"num_tokens": 2830826.0,
|
|
"step": 1625
|
|
},
|
|
{
|
|
"entropy": 6.472244501113892,
|
|
"epoch": 0.1268235751799261,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000499972986039528,
|
|
"loss": 6.2285,
|
|
"mean_token_accuracy": 0.1285054236650467,
|
|
"num_tokens": 2839766.0,
|
|
"step": 1630
|
|
},
|
|
{
|
|
"entropy": 6.295017290115356,
|
|
"epoch": 0.12721260455164365,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004999725548665904,
|
|
"loss": 6.1702,
|
|
"mean_token_accuracy": 0.13327566310763359,
|
|
"num_tokens": 2848728.0,
|
|
"step": 1635
|
|
},
|
|
{
|
|
"entropy": 6.369825220108032,
|
|
"epoch": 0.1276016339233612,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999721202800524,
|
|
"loss": 6.1868,
|
|
"mean_token_accuracy": 0.13074957728385925,
|
|
"num_tokens": 2857221.0,
|
|
"step": 1640
|
|
},
|
|
{
|
|
"entropy": 6.546764755249024,
|
|
"epoch": 0.12799066329507877,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999716822799206,
|
|
"loss": 6.2481,
|
|
"mean_token_accuracy": 0.13030916303396226,
|
|
"num_tokens": 2865314.0,
|
|
"step": 1645
|
|
},
|
|
{
|
|
"entropy": 6.320151281356812,
|
|
"epoch": 0.12837969266679633,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999712408662016,
|
|
"loss": 6.1424,
|
|
"mean_token_accuracy": 0.12682838290929793,
|
|
"num_tokens": 2873654.0,
|
|
"step": 1650
|
|
},
|
|
{
|
|
"entropy": 6.379095506668091,
|
|
"epoch": 0.12876872203851392,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999707960389021,
|
|
"loss": 6.0377,
|
|
"mean_token_accuracy": 0.13998508602380752,
|
|
"num_tokens": 2881604.0,
|
|
"step": 1655
|
|
},
|
|
{
|
|
"entropy": 6.374504232406617,
|
|
"epoch": 0.12915775141023147,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999703477980288,
|
|
"loss": 6.2388,
|
|
"mean_token_accuracy": 0.12339747697114944,
|
|
"num_tokens": 2890427.0,
|
|
"step": 1660
|
|
},
|
|
{
|
|
"entropy": 6.471899557113647,
|
|
"epoch": 0.12954678078194903,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999698961435885,
|
|
"loss": 6.2024,
|
|
"mean_token_accuracy": 0.12862686440348625,
|
|
"num_tokens": 2899206.0,
|
|
"step": 1665
|
|
},
|
|
{
|
|
"entropy": 6.3578918933868405,
|
|
"epoch": 0.1299358101536666,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999694410755882,
|
|
"loss": 6.1251,
|
|
"mean_token_accuracy": 0.13412127643823624,
|
|
"num_tokens": 2907738.0,
|
|
"step": 1670
|
|
},
|
|
{
|
|
"entropy": 6.475336980819702,
|
|
"epoch": 0.13032483952538418,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999689825940347,
|
|
"loss": 6.3526,
|
|
"mean_token_accuracy": 0.12458359599113464,
|
|
"num_tokens": 2916881.0,
|
|
"step": 1675
|
|
},
|
|
{
|
|
"entropy": 6.48715295791626,
|
|
"epoch": 0.13071386889710174,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004999685206989349,
|
|
"loss": 6.2833,
|
|
"mean_token_accuracy": 0.12076244428753853,
|
|
"num_tokens": 2926467.0,
|
|
"step": 1680
|
|
},
|
|
{
|
|
"entropy": 6.485057735443116,
|
|
"epoch": 0.1311028982688193,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999680553902959,
|
|
"loss": 6.2095,
|
|
"mean_token_accuracy": 0.12537256702780725,
|
|
"num_tokens": 2934671.0,
|
|
"step": 1685
|
|
},
|
|
{
|
|
"entropy": 6.374607038497925,
|
|
"epoch": 0.13149192764053685,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004999675866681247,
|
|
"loss": 6.2382,
|
|
"mean_token_accuracy": 0.12314836755394935,
|
|
"num_tokens": 2943925.0,
|
|
"step": 1690
|
|
},
|
|
{
|
|
"entropy": 6.529426240921021,
|
|
"epoch": 0.1318809570122544,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999671145324286,
|
|
"loss": 6.2839,
|
|
"mean_token_accuracy": 0.12293665111064911,
|
|
"num_tokens": 2952118.0,
|
|
"step": 1695
|
|
},
|
|
{
|
|
"entropy": 6.332964897155762,
|
|
"epoch": 0.132269986383972,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999666389832144,
|
|
"loss": 6.246,
|
|
"mean_token_accuracy": 0.12483881637454033,
|
|
"num_tokens": 2961110.0,
|
|
"step": 1700
|
|
},
|
|
{
|
|
"entropy": 6.501490259170533,
|
|
"epoch": 0.13265901575568956,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999661600204897,
|
|
"loss": 6.1969,
|
|
"mean_token_accuracy": 0.1331293873488903,
|
|
"num_tokens": 2968877.0,
|
|
"step": 1705
|
|
},
|
|
{
|
|
"entropy": 6.432631254196167,
|
|
"epoch": 0.13304804512740712,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999656776442615,
|
|
"loss": 6.2441,
|
|
"mean_token_accuracy": 0.12796934992074965,
|
|
"num_tokens": 2977346.0,
|
|
"step": 1710
|
|
},
|
|
{
|
|
"entropy": 6.520103311538696,
|
|
"epoch": 0.13343707449912467,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999651918545372,
|
|
"loss": 6.2982,
|
|
"mean_token_accuracy": 0.12270353958010674,
|
|
"num_tokens": 2987494.0,
|
|
"step": 1715
|
|
},
|
|
{
|
|
"entropy": 6.414762353897094,
|
|
"epoch": 0.13382610387084226,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999647026513243,
|
|
"loss": 6.2018,
|
|
"mean_token_accuracy": 0.12620207220315932,
|
|
"num_tokens": 2996728.0,
|
|
"step": 1720
|
|
},
|
|
{
|
|
"entropy": 6.426468324661255,
|
|
"epoch": 0.13421513324255982,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00049996421003463,
|
|
"loss": 6.2245,
|
|
"mean_token_accuracy": 0.12518492266535758,
|
|
"num_tokens": 3005810.0,
|
|
"step": 1725
|
|
},
|
|
{
|
|
"entropy": 6.418255186080932,
|
|
"epoch": 0.13460416261427738,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999637140044619,
|
|
"loss": 6.2506,
|
|
"mean_token_accuracy": 0.12523002028465272,
|
|
"num_tokens": 3014603.0,
|
|
"step": 1730
|
|
},
|
|
{
|
|
"entropy": 6.536535358428955,
|
|
"epoch": 0.13499319198599494,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999632145608275,
|
|
"loss": 6.2372,
|
|
"mean_token_accuracy": 0.13129105269908906,
|
|
"num_tokens": 3023170.0,
|
|
"step": 1735
|
|
},
|
|
{
|
|
"entropy": 6.278478670120239,
|
|
"epoch": 0.1353822213577125,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999627117037343,
|
|
"loss": 5.9949,
|
|
"mean_token_accuracy": 0.13947482481598855,
|
|
"num_tokens": 3030565.0,
|
|
"step": 1740
|
|
},
|
|
{
|
|
"entropy": 6.4359362602233885,
|
|
"epoch": 0.13577125072943008,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00049996220543319,
|
|
"loss": 6.2643,
|
|
"mean_token_accuracy": 0.12935592159628867,
|
|
"num_tokens": 3040124.0,
|
|
"step": 1745
|
|
},
|
|
{
|
|
"entropy": 6.372562122344971,
|
|
"epoch": 0.13616028010114764,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999616957492025,
|
|
"loss": 6.1289,
|
|
"mean_token_accuracy": 0.13145363405346872,
|
|
"num_tokens": 3048458.0,
|
|
"step": 1750
|
|
},
|
|
{
|
|
"entropy": 6.290291500091553,
|
|
"epoch": 0.1365493094728652,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004999611826517793,
|
|
"loss": 6.103,
|
|
"mean_token_accuracy": 0.1282423861324787,
|
|
"num_tokens": 3057926.0,
|
|
"step": 1755
|
|
},
|
|
{
|
|
"entropy": 6.379631900787354,
|
|
"epoch": 0.13693833884458276,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004999606661409281,
|
|
"loss": 6.1366,
|
|
"mean_token_accuracy": 0.12733863443136215,
|
|
"num_tokens": 3066683.0,
|
|
"step": 1760
|
|
},
|
|
{
|
|
"entropy": 6.335511159896851,
|
|
"epoch": 0.13732736821630034,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999601462166569,
|
|
"loss": 6.2076,
|
|
"mean_token_accuracy": 0.1272580251097679,
|
|
"num_tokens": 3075117.0,
|
|
"step": 1765
|
|
},
|
|
{
|
|
"entropy": 6.486139631271362,
|
|
"epoch": 0.1377163975880179,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004999596228789736,
|
|
"loss": 6.2551,
|
|
"mean_token_accuracy": 0.12465462982654571,
|
|
"num_tokens": 3084399.0,
|
|
"step": 1770
|
|
},
|
|
{
|
|
"entropy": 6.3006826877594,
|
|
"epoch": 0.13810542695973546,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999590961278859,
|
|
"loss": 6.0508,
|
|
"mean_token_accuracy": 0.13070713505148887,
|
|
"num_tokens": 3093030.0,
|
|
"step": 1775
|
|
},
|
|
{
|
|
"entropy": 6.385556221008301,
|
|
"epoch": 0.13849445633145302,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999585659634021,
|
|
"loss": 6.1168,
|
|
"mean_token_accuracy": 0.12877569422125817,
|
|
"num_tokens": 3101670.0,
|
|
"step": 1780
|
|
},
|
|
{
|
|
"entropy": 6.281736993789673,
|
|
"epoch": 0.13888348570317058,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999580323855301,
|
|
"loss": 6.0969,
|
|
"mean_token_accuracy": 0.1332916021347046,
|
|
"num_tokens": 3109703.0,
|
|
"step": 1785
|
|
},
|
|
{
|
|
"entropy": 6.332530498504639,
|
|
"epoch": 0.13927251507488816,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999574953942781,
|
|
"loss": 6.0721,
|
|
"mean_token_accuracy": 0.1361841931939125,
|
|
"num_tokens": 3118388.0,
|
|
"step": 1790
|
|
},
|
|
{
|
|
"entropy": 6.350433826446533,
|
|
"epoch": 0.13966154444660572,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999569549896541,
|
|
"loss": 6.0765,
|
|
"mean_token_accuracy": 0.13128025978803634,
|
|
"num_tokens": 3126466.0,
|
|
"step": 1795
|
|
},
|
|
{
|
|
"entropy": 6.373475027084351,
|
|
"epoch": 0.14005057381832328,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999564111716665,
|
|
"loss": 6.1227,
|
|
"mean_token_accuracy": 0.13267524316906928,
|
|
"num_tokens": 3135322.0,
|
|
"step": 1800
|
|
},
|
|
{
|
|
"entropy": 6.354067659378051,
|
|
"epoch": 0.14043960319004084,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004999558639403232,
|
|
"loss": 6.1047,
|
|
"mean_token_accuracy": 0.1384847082197666,
|
|
"num_tokens": 3144498.0,
|
|
"step": 1805
|
|
},
|
|
{
|
|
"entropy": 6.28254337310791,
|
|
"epoch": 0.1408286325617584,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004999553132956328,
|
|
"loss": 6.0917,
|
|
"mean_token_accuracy": 0.12457187175750732,
|
|
"num_tokens": 3153573.0,
|
|
"step": 1810
|
|
},
|
|
{
|
|
"entropy": 6.256527614593506,
|
|
"epoch": 0.14121766193347599,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999547592376035,
|
|
"loss": 6.0228,
|
|
"mean_token_accuracy": 0.13926569893956184,
|
|
"num_tokens": 3161705.0,
|
|
"step": 1815
|
|
},
|
|
{
|
|
"entropy": 6.382395887374878,
|
|
"epoch": 0.14160669130519354,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999542017662438,
|
|
"loss": 6.1838,
|
|
"mean_token_accuracy": 0.1349948912858963,
|
|
"num_tokens": 3170068.0,
|
|
"step": 1820
|
|
},
|
|
{
|
|
"entropy": 6.34617772102356,
|
|
"epoch": 0.1419957206769111,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999536408815623,
|
|
"loss": 6.1935,
|
|
"mean_token_accuracy": 0.12690433263778686,
|
|
"num_tokens": 3178140.0,
|
|
"step": 1825
|
|
},
|
|
{
|
|
"entropy": 6.422201013565063,
|
|
"epoch": 0.14238475004862866,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999530765835672,
|
|
"loss": 6.1579,
|
|
"mean_token_accuracy": 0.1325029954314232,
|
|
"num_tokens": 3186518.0,
|
|
"step": 1830
|
|
},
|
|
{
|
|
"entropy": 6.289926528930664,
|
|
"epoch": 0.14277377942034625,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999525088722673,
|
|
"loss": 6.1548,
|
|
"mean_token_accuracy": 0.1283407174050808,
|
|
"num_tokens": 3195246.0,
|
|
"step": 1835
|
|
},
|
|
{
|
|
"entropy": 6.444282150268554,
|
|
"epoch": 0.1431628087920638,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999519377476711,
|
|
"loss": 6.1779,
|
|
"mean_token_accuracy": 0.12667956873774527,
|
|
"num_tokens": 3203946.0,
|
|
"step": 1840
|
|
},
|
|
{
|
|
"entropy": 6.306654262542724,
|
|
"epoch": 0.14355183816378136,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999513632097872,
|
|
"loss": 6.1739,
|
|
"mean_token_accuracy": 0.13087522089481354,
|
|
"num_tokens": 3212208.0,
|
|
"step": 1845
|
|
},
|
|
{
|
|
"entropy": 6.336764192581176,
|
|
"epoch": 0.14394086753549892,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999507852586245,
|
|
"loss": 6.1172,
|
|
"mean_token_accuracy": 0.1314890868961811,
|
|
"num_tokens": 3221572.0,
|
|
"step": 1850
|
|
},
|
|
{
|
|
"entropy": 6.424954843521118,
|
|
"epoch": 0.14432989690721648,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004999502038941917,
|
|
"loss": 6.2263,
|
|
"mean_token_accuracy": 0.12041985988616943,
|
|
"num_tokens": 3230898.0,
|
|
"step": 1855
|
|
},
|
|
{
|
|
"entropy": 6.333400774002075,
|
|
"epoch": 0.14471892627893407,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004999496191164975,
|
|
"loss": 6.2051,
|
|
"mean_token_accuracy": 0.12520071864128113,
|
|
"num_tokens": 3240524.0,
|
|
"step": 1860
|
|
},
|
|
{
|
|
"entropy": 6.29474139213562,
|
|
"epoch": 0.14510795565065163,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000499949030925551,
|
|
"loss": 5.9728,
|
|
"mean_token_accuracy": 0.13799916058778763,
|
|
"num_tokens": 3248864.0,
|
|
"step": 1865
|
|
},
|
|
{
|
|
"entropy": 6.325572156906128,
|
|
"epoch": 0.14549698502236919,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999484393213609,
|
|
"loss": 6.1491,
|
|
"mean_token_accuracy": 0.13214721530675888,
|
|
"num_tokens": 3256823.0,
|
|
"step": 1870
|
|
},
|
|
{
|
|
"entropy": 6.3230939388275145,
|
|
"epoch": 0.14588601439408674,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004999478443039363,
|
|
"loss": 6.0723,
|
|
"mean_token_accuracy": 0.13165922313928605,
|
|
"num_tokens": 3265621.0,
|
|
"step": 1875
|
|
},
|
|
{
|
|
"entropy": 6.260721683502197,
|
|
"epoch": 0.14627504376580433,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999472458732862,
|
|
"loss": 6.0962,
|
|
"mean_token_accuracy": 0.13295478150248527,
|
|
"num_tokens": 3273515.0,
|
|
"step": 1880
|
|
},
|
|
{
|
|
"entropy": 6.414492464065551,
|
|
"epoch": 0.1466640731375219,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999466440294198,
|
|
"loss": 6.1689,
|
|
"mean_token_accuracy": 0.12950320392847062,
|
|
"num_tokens": 3282283.0,
|
|
"step": 1885
|
|
},
|
|
{
|
|
"entropy": 6.302510833740234,
|
|
"epoch": 0.14705310250923945,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000499946038772346,
|
|
"loss": 6.1611,
|
|
"mean_token_accuracy": 0.13020878359675409,
|
|
"num_tokens": 3290792.0,
|
|
"step": 1890
|
|
},
|
|
{
|
|
"entropy": 6.255168008804321,
|
|
"epoch": 0.147442131880957,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999454301020741,
|
|
"loss": 6.0204,
|
|
"mean_token_accuracy": 0.13267397582530976,
|
|
"num_tokens": 3299430.0,
|
|
"step": 1895
|
|
},
|
|
{
|
|
"entropy": 6.261677408218384,
|
|
"epoch": 0.14783116125267456,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999448180186133,
|
|
"loss": 6.0808,
|
|
"mean_token_accuracy": 0.13431849405169488,
|
|
"num_tokens": 3307949.0,
|
|
"step": 1900
|
|
},
|
|
{
|
|
"entropy": 6.340135097503662,
|
|
"epoch": 0.14822019062439215,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000499944202521973,
|
|
"loss": 6.1246,
|
|
"mean_token_accuracy": 0.13576969206333162,
|
|
"num_tokens": 3316900.0,
|
|
"step": 1905
|
|
},
|
|
{
|
|
"entropy": 6.295166778564453,
|
|
"epoch": 0.1486092199961097,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999435836121624,
|
|
"loss": 6.0446,
|
|
"mean_token_accuracy": 0.13577630817890168,
|
|
"num_tokens": 3325656.0,
|
|
"step": 1910
|
|
},
|
|
{
|
|
"entropy": 6.309445333480835,
|
|
"epoch": 0.14899824936782727,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000499942961289191,
|
|
"loss": 6.2644,
|
|
"mean_token_accuracy": 0.12280140817165375,
|
|
"num_tokens": 3334219.0,
|
|
"step": 1915
|
|
},
|
|
{
|
|
"entropy": 6.317688608169556,
|
|
"epoch": 0.14938727873954483,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004999423355530683,
|
|
"loss": 6.0314,
|
|
"mean_token_accuracy": 0.13022207394242286,
|
|
"num_tokens": 3343637.0,
|
|
"step": 1920
|
|
},
|
|
{
|
|
"entropy": 6.314282560348511,
|
|
"epoch": 0.1497763081112624,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999417064038035,
|
|
"loss": 6.1686,
|
|
"mean_token_accuracy": 0.13118190541863442,
|
|
"num_tokens": 3352624.0,
|
|
"step": 1925
|
|
},
|
|
{
|
|
"entropy": 6.262926197052002,
|
|
"epoch": 0.15016533748297997,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999410738414065,
|
|
"loss": 6.0802,
|
|
"mean_token_accuracy": 0.1389567419886589,
|
|
"num_tokens": 3361394.0,
|
|
"step": 1930
|
|
},
|
|
{
|
|
"entropy": 6.377456378936768,
|
|
"epoch": 0.15055436685469753,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999404378658866,
|
|
"loss": 6.1348,
|
|
"mean_token_accuracy": 0.13395721539855004,
|
|
"num_tokens": 3369406.0,
|
|
"step": 1935
|
|
},
|
|
{
|
|
"entropy": 6.3417693138122555,
|
|
"epoch": 0.1509433962264151,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999397984772536,
|
|
"loss": 6.0852,
|
|
"mean_token_accuracy": 0.13622010201215745,
|
|
"num_tokens": 3377737.0,
|
|
"step": 1940
|
|
},
|
|
{
|
|
"entropy": 6.2485908508300785,
|
|
"epoch": 0.15133242559813265,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999391556755172,
|
|
"loss": 6.1389,
|
|
"mean_token_accuracy": 0.12751591503620147,
|
|
"num_tokens": 3385514.0,
|
|
"step": 1945
|
|
},
|
|
{
|
|
"entropy": 6.394997596740723,
|
|
"epoch": 0.15172145496985023,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999385094606872,
|
|
"loss": 6.0537,
|
|
"mean_token_accuracy": 0.13509045764803887,
|
|
"num_tokens": 3394500.0,
|
|
"step": 1950
|
|
},
|
|
{
|
|
"entropy": 6.220421218872071,
|
|
"epoch": 0.1521104843415678,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999378598327733,
|
|
"loss": 6.0306,
|
|
"mean_token_accuracy": 0.13421875312924386,
|
|
"num_tokens": 3403289.0,
|
|
"step": 1955
|
|
},
|
|
{
|
|
"entropy": 6.218709182739258,
|
|
"epoch": 0.15249951371328535,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999372067917854,
|
|
"loss": 5.9569,
|
|
"mean_token_accuracy": 0.14868551939725877,
|
|
"num_tokens": 3410892.0,
|
|
"step": 1960
|
|
},
|
|
{
|
|
"entropy": 6.162004232406616,
|
|
"epoch": 0.1528885430850029,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999365503377335,
|
|
"loss": 6.061,
|
|
"mean_token_accuracy": 0.13821410536766052,
|
|
"num_tokens": 3420329.0,
|
|
"step": 1965
|
|
},
|
|
{
|
|
"entropy": 6.333985614776611,
|
|
"epoch": 0.1532775724567205,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999358904706273,
|
|
"loss": 6.0505,
|
|
"mean_token_accuracy": 0.1318977616727352,
|
|
"num_tokens": 3429429.0,
|
|
"step": 1970
|
|
},
|
|
{
|
|
"entropy": 6.335431814193726,
|
|
"epoch": 0.15366660182843805,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999352271904771,
|
|
"loss": 6.1639,
|
|
"mean_token_accuracy": 0.1311632439494133,
|
|
"num_tokens": 3438198.0,
|
|
"step": 1975
|
|
},
|
|
{
|
|
"entropy": 6.457853221893311,
|
|
"epoch": 0.1540556312001556,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999345604972928,
|
|
"loss": 6.2972,
|
|
"mean_token_accuracy": 0.1280217707157135,
|
|
"num_tokens": 3447732.0,
|
|
"step": 1980
|
|
},
|
|
{
|
|
"entropy": 6.3014496803283695,
|
|
"epoch": 0.15444466057187317,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999338903910846,
|
|
"loss": 6.0717,
|
|
"mean_token_accuracy": 0.13846041038632392,
|
|
"num_tokens": 3456392.0,
|
|
"step": 1985
|
|
},
|
|
{
|
|
"entropy": 6.261079359054565,
|
|
"epoch": 0.15483368994359073,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999332168718626,
|
|
"loss": 6.1141,
|
|
"mean_token_accuracy": 0.13328127637505532,
|
|
"num_tokens": 3464473.0,
|
|
"step": 1990
|
|
},
|
|
{
|
|
"entropy": 6.2995849609375,
|
|
"epoch": 0.15522271931530832,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004999325399396371,
|
|
"loss": 6.0817,
|
|
"mean_token_accuracy": 0.13139236569404603,
|
|
"num_tokens": 3473740.0,
|
|
"step": 1995
|
|
},
|
|
{
|
|
"entropy": 6.162753677368164,
|
|
"epoch": 0.15561174868702587,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999318595944183,
|
|
"loss": 5.985,
|
|
"mean_token_accuracy": 0.1351643517613411,
|
|
"num_tokens": 3482249.0,
|
|
"step": 2000
|
|
},
|
|
{
|
|
"entropy": 6.419935607910157,
|
|
"epoch": 0.15600077805874343,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999311758362166,
|
|
"loss": 6.2085,
|
|
"mean_token_accuracy": 0.12761779576539994,
|
|
"num_tokens": 3490753.0,
|
|
"step": 2005
|
|
},
|
|
{
|
|
"entropy": 6.390731334686279,
|
|
"epoch": 0.156389807430461,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999304886650422,
|
|
"loss": 6.1566,
|
|
"mean_token_accuracy": 0.13517940416932106,
|
|
"num_tokens": 3499373.0,
|
|
"step": 2010
|
|
},
|
|
{
|
|
"entropy": 6.3211747169494625,
|
|
"epoch": 0.15677883680217858,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999297980809058,
|
|
"loss": 6.1308,
|
|
"mean_token_accuracy": 0.12607129365205766,
|
|
"num_tokens": 3508344.0,
|
|
"step": 2015
|
|
},
|
|
{
|
|
"entropy": 6.359952831268311,
|
|
"epoch": 0.15716786617389614,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004999291040838176,
|
|
"loss": 6.0979,
|
|
"mean_token_accuracy": 0.1342169925570488,
|
|
"num_tokens": 3517009.0,
|
|
"step": 2020
|
|
},
|
|
{
|
|
"entropy": 6.2388135433197025,
|
|
"epoch": 0.1575568955456137,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999284066737884,
|
|
"loss": 6.1366,
|
|
"mean_token_accuracy": 0.13406251445412637,
|
|
"num_tokens": 3525989.0,
|
|
"step": 2025
|
|
},
|
|
{
|
|
"entropy": 6.306530141830445,
|
|
"epoch": 0.15794592491733125,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999277058508285,
|
|
"loss": 6.0173,
|
|
"mean_token_accuracy": 0.13108256459236145,
|
|
"num_tokens": 3533947.0,
|
|
"step": 2030
|
|
},
|
|
{
|
|
"entropy": 6.262210369110107,
|
|
"epoch": 0.1583349542890488,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999270016149486,
|
|
"loss": 6.0749,
|
|
"mean_token_accuracy": 0.1352415882050991,
|
|
"num_tokens": 3541974.0,
|
|
"step": 2035
|
|
},
|
|
{
|
|
"entropy": 6.268887376785278,
|
|
"epoch": 0.1587239836607664,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999262939661596,
|
|
"loss": 6.0026,
|
|
"mean_token_accuracy": 0.1375070445239544,
|
|
"num_tokens": 3550436.0,
|
|
"step": 2040
|
|
},
|
|
{
|
|
"entropy": 6.26065878868103,
|
|
"epoch": 0.15911301303248396,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999255829044721,
|
|
"loss": 6.0238,
|
|
"mean_token_accuracy": 0.13955531716346742,
|
|
"num_tokens": 3558283.0,
|
|
"step": 2045
|
|
},
|
|
{
|
|
"entropy": 6.194809818267823,
|
|
"epoch": 0.15950204240420152,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004999248684298968,
|
|
"loss": 5.939,
|
|
"mean_token_accuracy": 0.1412186801433563,
|
|
"num_tokens": 3566968.0,
|
|
"step": 2050
|
|
},
|
|
{
|
|
"entropy": 6.244066286087036,
|
|
"epoch": 0.15989107177591907,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999241505424447,
|
|
"loss": 6.0625,
|
|
"mean_token_accuracy": 0.12982572838664055,
|
|
"num_tokens": 3575580.0,
|
|
"step": 2055
|
|
},
|
|
{
|
|
"entropy": 6.259646034240722,
|
|
"epoch": 0.16028010114763663,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004999234292421265,
|
|
"loss": 6.1312,
|
|
"mean_token_accuracy": 0.13408922925591468,
|
|
"num_tokens": 3584389.0,
|
|
"step": 2060
|
|
},
|
|
{
|
|
"entropy": 6.286141872406006,
|
|
"epoch": 0.16066913051935422,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999227045289535,
|
|
"loss": 5.9685,
|
|
"mean_token_accuracy": 0.13707195296883584,
|
|
"num_tokens": 3593009.0,
|
|
"step": 2065
|
|
},
|
|
{
|
|
"entropy": 6.142366409301758,
|
|
"epoch": 0.16105815989107178,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999219764029363,
|
|
"loss": 6.0046,
|
|
"mean_token_accuracy": 0.13540613800287246,
|
|
"num_tokens": 3601914.0,
|
|
"step": 2070
|
|
},
|
|
{
|
|
"entropy": 6.207937431335449,
|
|
"epoch": 0.16144718926278934,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999212448640861,
|
|
"loss": 5.9673,
|
|
"mean_token_accuracy": 0.13867463171482086,
|
|
"num_tokens": 3609883.0,
|
|
"step": 2075
|
|
},
|
|
{
|
|
"entropy": 6.189123487472534,
|
|
"epoch": 0.1618362186345069,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999205099124141,
|
|
"loss": 5.9265,
|
|
"mean_token_accuracy": 0.1397370256483555,
|
|
"num_tokens": 3618103.0,
|
|
"step": 2080
|
|
},
|
|
{
|
|
"entropy": 6.399334859848023,
|
|
"epoch": 0.16222524800622448,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999197715479313,
|
|
"loss": 6.1937,
|
|
"mean_token_accuracy": 0.1316985122859478,
|
|
"num_tokens": 3625861.0,
|
|
"step": 2085
|
|
},
|
|
{
|
|
"entropy": 6.1656725883483885,
|
|
"epoch": 0.16261427737794204,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999190297706489,
|
|
"loss": 5.9726,
|
|
"mean_token_accuracy": 0.13532934188842774,
|
|
"num_tokens": 3634498.0,
|
|
"step": 2090
|
|
},
|
|
{
|
|
"entropy": 6.1408239841461185,
|
|
"epoch": 0.1630033067496596,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999182845805783,
|
|
"loss": 5.9117,
|
|
"mean_token_accuracy": 0.13378374204039573,
|
|
"num_tokens": 3644186.0,
|
|
"step": 2095
|
|
},
|
|
{
|
|
"entropy": 6.151297092437744,
|
|
"epoch": 0.16339233612137716,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999175359777306,
|
|
"loss": 6.0603,
|
|
"mean_token_accuracy": 0.13409929126501083,
|
|
"num_tokens": 3652831.0,
|
|
"step": 2100
|
|
},
|
|
{
|
|
"entropy": 6.346699666976929,
|
|
"epoch": 0.16378136549309472,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999167839621174,
|
|
"loss": 5.9205,
|
|
"mean_token_accuracy": 0.14053727090358734,
|
|
"num_tokens": 3661230.0,
|
|
"step": 2105
|
|
},
|
|
{
|
|
"entropy": 6.19318904876709,
|
|
"epoch": 0.1641703948648123,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999160285337501,
|
|
"loss": 6.0607,
|
|
"mean_token_accuracy": 0.1370956338942051,
|
|
"num_tokens": 3669250.0,
|
|
"step": 2110
|
|
},
|
|
{
|
|
"entropy": 6.26489109992981,
|
|
"epoch": 0.16455942423652986,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999152696926399,
|
|
"loss": 6.0286,
|
|
"mean_token_accuracy": 0.138458015024662,
|
|
"num_tokens": 3677568.0,
|
|
"step": 2115
|
|
},
|
|
{
|
|
"entropy": 6.253146648406982,
|
|
"epoch": 0.16494845360824742,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004999145074387985,
|
|
"loss": 6.0233,
|
|
"mean_token_accuracy": 0.1416604608297348,
|
|
"num_tokens": 3685488.0,
|
|
"step": 2120
|
|
},
|
|
{
|
|
"entropy": 6.180020809173584,
|
|
"epoch": 0.16533748297996498,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999137417722374,
|
|
"loss": 6.002,
|
|
"mean_token_accuracy": 0.13473087772727013,
|
|
"num_tokens": 3694357.0,
|
|
"step": 2125
|
|
},
|
|
{
|
|
"entropy": 6.316441535949707,
|
|
"epoch": 0.16572651235168256,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999129726929684,
|
|
"loss": 6.0723,
|
|
"mean_token_accuracy": 0.1360612131655216,
|
|
"num_tokens": 3703173.0,
|
|
"step": 2130
|
|
},
|
|
{
|
|
"entropy": 6.205403232574463,
|
|
"epoch": 0.16611554172340012,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999122002010029,
|
|
"loss": 6.0431,
|
|
"mean_token_accuracy": 0.14090028777718544,
|
|
"num_tokens": 3712070.0,
|
|
"step": 2135
|
|
},
|
|
{
|
|
"entropy": 6.206867980957031,
|
|
"epoch": 0.16650457109511768,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999114242963527,
|
|
"loss": 5.9404,
|
|
"mean_token_accuracy": 0.14348391592502593,
|
|
"num_tokens": 3720245.0,
|
|
"step": 2140
|
|
},
|
|
{
|
|
"entropy": 6.18376841545105,
|
|
"epoch": 0.16689360046683524,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999106449790298,
|
|
"loss": 6.0492,
|
|
"mean_token_accuracy": 0.137314972281456,
|
|
"num_tokens": 3730064.0,
|
|
"step": 2145
|
|
},
|
|
{
|
|
"entropy": 6.136141538619995,
|
|
"epoch": 0.1672826298385528,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999098622490458,
|
|
"loss": 5.9864,
|
|
"mean_token_accuracy": 0.14003208428621292,
|
|
"num_tokens": 3738741.0,
|
|
"step": 2150
|
|
},
|
|
{
|
|
"entropy": 6.289495420455933,
|
|
"epoch": 0.16767165921027039,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999090761064125,
|
|
"loss": 6.0533,
|
|
"mean_token_accuracy": 0.13532209545373916,
|
|
"num_tokens": 3747472.0,
|
|
"step": 2155
|
|
},
|
|
{
|
|
"entropy": 6.240089464187622,
|
|
"epoch": 0.16806068858198794,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000499908286551142,
|
|
"loss": 6.0641,
|
|
"mean_token_accuracy": 0.13511611968278886,
|
|
"num_tokens": 3756643.0,
|
|
"step": 2160
|
|
},
|
|
{
|
|
"entropy": 6.315414953231811,
|
|
"epoch": 0.1684497179537055,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999074935832463,
|
|
"loss": 6.1853,
|
|
"mean_token_accuracy": 0.12947507873177527,
|
|
"num_tokens": 3765490.0,
|
|
"step": 2165
|
|
},
|
|
{
|
|
"entropy": 6.2349205493927,
|
|
"epoch": 0.16883874732542306,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999066972027373,
|
|
"loss": 5.938,
|
|
"mean_token_accuracy": 0.1387890338897705,
|
|
"num_tokens": 3773063.0,
|
|
"step": 2170
|
|
},
|
|
{
|
|
"entropy": 6.261452722549438,
|
|
"epoch": 0.16922777669714065,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999058974096271,
|
|
"loss": 6.1062,
|
|
"mean_token_accuracy": 0.1365394599735737,
|
|
"num_tokens": 3781763.0,
|
|
"step": 2175
|
|
},
|
|
{
|
|
"entropy": 6.2590172290802,
|
|
"epoch": 0.1696168060688582,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000499905094203928,
|
|
"loss": 6.0982,
|
|
"mean_token_accuracy": 0.1321517176926136,
|
|
"num_tokens": 3790582.0,
|
|
"step": 2180
|
|
},
|
|
{
|
|
"entropy": 6.202856731414795,
|
|
"epoch": 0.17000583544057576,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000499904287585652,
|
|
"loss": 5.9206,
|
|
"mean_token_accuracy": 0.13618794158101083,
|
|
"num_tokens": 3798745.0,
|
|
"step": 2185
|
|
},
|
|
{
|
|
"entropy": 6.172497653961182,
|
|
"epoch": 0.17039486481229332,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999034775548113,
|
|
"loss": 6.0095,
|
|
"mean_token_accuracy": 0.1356318287551403,
|
|
"num_tokens": 3806901.0,
|
|
"step": 2190
|
|
},
|
|
{
|
|
"entropy": 6.2153675079345705,
|
|
"epoch": 0.17078389418401088,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999026641114185,
|
|
"loss": 5.9479,
|
|
"mean_token_accuracy": 0.14665559828281402,
|
|
"num_tokens": 3815742.0,
|
|
"step": 2195
|
|
},
|
|
{
|
|
"entropy": 6.144705820083618,
|
|
"epoch": 0.17117292355572847,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999018472554857,
|
|
"loss": 6.0388,
|
|
"mean_token_accuracy": 0.13324448689818383,
|
|
"num_tokens": 3824468.0,
|
|
"step": 2200
|
|
},
|
|
{
|
|
"entropy": 6.208492565155029,
|
|
"epoch": 0.17156195292744603,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999010269870253,
|
|
"loss": 5.9937,
|
|
"mean_token_accuracy": 0.13999679386615754,
|
|
"num_tokens": 3832834.0,
|
|
"step": 2205
|
|
},
|
|
{
|
|
"entropy": 6.242017364501953,
|
|
"epoch": 0.17195098229916359,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999002033060498,
|
|
"loss": 6.0525,
|
|
"mean_token_accuracy": 0.13752312287688256,
|
|
"num_tokens": 3841780.0,
|
|
"step": 2210
|
|
},
|
|
{
|
|
"entropy": 6.24888129234314,
|
|
"epoch": 0.17234001167088114,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004998993762125716,
|
|
"loss": 6.1355,
|
|
"mean_token_accuracy": 0.12495578080415726,
|
|
"num_tokens": 3849840.0,
|
|
"step": 2215
|
|
},
|
|
{
|
|
"entropy": 6.293956756591797,
|
|
"epoch": 0.17272904104259873,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998985457066034,
|
|
"loss": 6.079,
|
|
"mean_token_accuracy": 0.13282646834850312,
|
|
"num_tokens": 3858204.0,
|
|
"step": 2220
|
|
},
|
|
{
|
|
"entropy": 6.2079095363616945,
|
|
"epoch": 0.1731180704143163,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004998977117881576,
|
|
"loss": 6.0237,
|
|
"mean_token_accuracy": 0.14005702137947082,
|
|
"num_tokens": 3866615.0,
|
|
"step": 2225
|
|
},
|
|
{
|
|
"entropy": 6.221766662597656,
|
|
"epoch": 0.17350709978603385,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004998968744572472,
|
|
"loss": 6.0559,
|
|
"mean_token_accuracy": 0.14006396681070327,
|
|
"num_tokens": 3876003.0,
|
|
"step": 2230
|
|
},
|
|
{
|
|
"entropy": 6.193023920059204,
|
|
"epoch": 0.1738961291577514,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004998960337138845,
|
|
"loss": 5.9727,
|
|
"mean_token_accuracy": 0.13838636204600335,
|
|
"num_tokens": 3884362.0,
|
|
"step": 2235
|
|
},
|
|
{
|
|
"entropy": 6.160814571380615,
|
|
"epoch": 0.17428515852946896,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004998951895580826,
|
|
"loss": 5.9274,
|
|
"mean_token_accuracy": 0.13808080181479454,
|
|
"num_tokens": 3893177.0,
|
|
"step": 2240
|
|
},
|
|
{
|
|
"entropy": 6.1626489639282225,
|
|
"epoch": 0.17467418790118655,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998943419898542,
|
|
"loss": 5.9864,
|
|
"mean_token_accuracy": 0.14280490577220917,
|
|
"num_tokens": 3903006.0,
|
|
"step": 2245
|
|
},
|
|
{
|
|
"entropy": 6.204087400436402,
|
|
"epoch": 0.1750632172729041,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004998934910092119,
|
|
"loss": 5.8424,
|
|
"mean_token_accuracy": 0.1409443661570549,
|
|
"num_tokens": 3912256.0,
|
|
"step": 2250
|
|
},
|
|
{
|
|
"entropy": 6.134327507019043,
|
|
"epoch": 0.17545224664462167,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998926366161689,
|
|
"loss": 6.0321,
|
|
"mean_token_accuracy": 0.13451322615146638,
|
|
"num_tokens": 3921121.0,
|
|
"step": 2255
|
|
},
|
|
{
|
|
"entropy": 6.185262537002563,
|
|
"epoch": 0.17584127601633923,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004998917788107383,
|
|
"loss": 5.9843,
|
|
"mean_token_accuracy": 0.13937503695487977,
|
|
"num_tokens": 3929348.0,
|
|
"step": 2260
|
|
},
|
|
{
|
|
"entropy": 6.260100173950195,
|
|
"epoch": 0.17623030538805678,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998909175929326,
|
|
"loss": 6.1355,
|
|
"mean_token_accuracy": 0.13460659310221673,
|
|
"num_tokens": 3938073.0,
|
|
"step": 2265
|
|
},
|
|
{
|
|
"entropy": 6.28374981880188,
|
|
"epoch": 0.17661933475977437,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004998900529627653,
|
|
"loss": 6.1158,
|
|
"mean_token_accuracy": 0.13738646805286409,
|
|
"num_tokens": 3946641.0,
|
|
"step": 2270
|
|
},
|
|
{
|
|
"entropy": 6.256800127029419,
|
|
"epoch": 0.17700836413149193,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998891849202495,
|
|
"loss": 5.9659,
|
|
"mean_token_accuracy": 0.1371592253446579,
|
|
"num_tokens": 3954586.0,
|
|
"step": 2275
|
|
},
|
|
{
|
|
"entropy": 6.119969654083252,
|
|
"epoch": 0.1773973935032095,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000499888313465398,
|
|
"loss": 6.0389,
|
|
"mean_token_accuracy": 0.14258864596486093,
|
|
"num_tokens": 3963745.0,
|
|
"step": 2280
|
|
},
|
|
{
|
|
"entropy": 6.1104155540466305,
|
|
"epoch": 0.17778642287492705,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004998874385982247,
|
|
"loss": 5.8596,
|
|
"mean_token_accuracy": 0.1476686991751194,
|
|
"num_tokens": 3972452.0,
|
|
"step": 2285
|
|
},
|
|
{
|
|
"entropy": 6.156691980361939,
|
|
"epoch": 0.17817545224664463,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004998865603187421,
|
|
"loss": 5.9683,
|
|
"mean_token_accuracy": 0.13907164037227632,
|
|
"num_tokens": 3980770.0,
|
|
"step": 2290
|
|
},
|
|
{
|
|
"entropy": 6.192203378677368,
|
|
"epoch": 0.1785644816183622,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000499885678626964,
|
|
"loss": 5.9986,
|
|
"mean_token_accuracy": 0.13721442893147467,
|
|
"num_tokens": 3989545.0,
|
|
"step": 2295
|
|
},
|
|
{
|
|
"entropy": 6.25260329246521,
|
|
"epoch": 0.17895351099007975,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004998847935229038,
|
|
"loss": 5.9638,
|
|
"mean_token_accuracy": 0.13558776378631593,
|
|
"num_tokens": 3998034.0,
|
|
"step": 2300
|
|
},
|
|
{
|
|
"entropy": 6.122658395767212,
|
|
"epoch": 0.1793425403617973,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004998839050065746,
|
|
"loss": 5.9926,
|
|
"mean_token_accuracy": 0.1411259353160858,
|
|
"num_tokens": 4007110.0,
|
|
"step": 2305
|
|
},
|
|
{
|
|
"entropy": 6.245479536056519,
|
|
"epoch": 0.17973156973351487,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998830130779902,
|
|
"loss": 6.0628,
|
|
"mean_token_accuracy": 0.13011873438954352,
|
|
"num_tokens": 4015930.0,
|
|
"step": 2310
|
|
},
|
|
{
|
|
"entropy": 6.104860258102417,
|
|
"epoch": 0.18012059910523245,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.000499882117737164,
|
|
"loss": 5.8558,
|
|
"mean_token_accuracy": 0.1457628294825554,
|
|
"num_tokens": 4024510.0,
|
|
"step": 2315
|
|
},
|
|
{
|
|
"entropy": 6.106551742553711,
|
|
"epoch": 0.18050962847695,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004998812189841096,
|
|
"loss": 5.9437,
|
|
"mean_token_accuracy": 0.14204365611076356,
|
|
"num_tokens": 4033714.0,
|
|
"step": 2320
|
|
},
|
|
{
|
|
"entropy": 6.316892910003662,
|
|
"epoch": 0.18089865784866757,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998803168188407,
|
|
"loss": 6.1612,
|
|
"mean_token_accuracy": 0.13279995173215867,
|
|
"num_tokens": 4042376.0,
|
|
"step": 2325
|
|
},
|
|
{
|
|
"entropy": 6.147280216217041,
|
|
"epoch": 0.18128768722038513,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998794112413708,
|
|
"loss": 5.925,
|
|
"mean_token_accuracy": 0.13952778577804564,
|
|
"num_tokens": 4050521.0,
|
|
"step": 2330
|
|
},
|
|
{
|
|
"entropy": 6.251437854766846,
|
|
"epoch": 0.18167671659210272,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004998785022517137,
|
|
"loss": 6.0965,
|
|
"mean_token_accuracy": 0.13085465058684348,
|
|
"num_tokens": 4059384.0,
|
|
"step": 2335
|
|
},
|
|
{
|
|
"entropy": 6.1695960521697994,
|
|
"epoch": 0.18206574596382027,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998775898498835,
|
|
"loss": 5.9663,
|
|
"mean_token_accuracy": 0.14308709353208543,
|
|
"num_tokens": 4067655.0,
|
|
"step": 2340
|
|
},
|
|
{
|
|
"entropy": 6.172775983810425,
|
|
"epoch": 0.18245477533553783,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998766740358936,
|
|
"loss": 5.9634,
|
|
"mean_token_accuracy": 0.14366720467805863,
|
|
"num_tokens": 4075828.0,
|
|
"step": 2345
|
|
},
|
|
{
|
|
"entropy": 6.232926893234253,
|
|
"epoch": 0.1828438047072554,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998757548097582,
|
|
"loss": 5.9226,
|
|
"mean_token_accuracy": 0.1397922396659851,
|
|
"num_tokens": 4083796.0,
|
|
"step": 2350
|
|
},
|
|
{
|
|
"entropy": 6.120053386688232,
|
|
"epoch": 0.18323283407897295,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004998748321714911,
|
|
"loss": 6.0329,
|
|
"mean_token_accuracy": 0.14252227693796157,
|
|
"num_tokens": 4092981.0,
|
|
"step": 2355
|
|
},
|
|
{
|
|
"entropy": 6.174644327163696,
|
|
"epoch": 0.18362186345069054,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998739061211065,
|
|
"loss": 5.879,
|
|
"mean_token_accuracy": 0.13968045711517335,
|
|
"num_tokens": 4101363.0,
|
|
"step": 2360
|
|
},
|
|
{
|
|
"entropy": 6.13595757484436,
|
|
"epoch": 0.1840108928224081,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004998729766586181,
|
|
"loss": 5.9492,
|
|
"mean_token_accuracy": 0.1380427822470665,
|
|
"num_tokens": 4110164.0,
|
|
"step": 2365
|
|
},
|
|
{
|
|
"entropy": 6.248952150344849,
|
|
"epoch": 0.18439992219412565,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998720437840403,
|
|
"loss": 6.0636,
|
|
"mean_token_accuracy": 0.1388567715883255,
|
|
"num_tokens": 4119098.0,
|
|
"step": 2370
|
|
},
|
|
{
|
|
"entropy": 6.176186418533325,
|
|
"epoch": 0.1847889515658432,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998711074973871,
|
|
"loss": 5.9613,
|
|
"mean_token_accuracy": 0.14075352251529694,
|
|
"num_tokens": 4127522.0,
|
|
"step": 2375
|
|
},
|
|
{
|
|
"entropy": 6.1555253028869625,
|
|
"epoch": 0.1851779809375608,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004998701677986728,
|
|
"loss": 5.9933,
|
|
"mean_token_accuracy": 0.1459673412144184,
|
|
"num_tokens": 4136311.0,
|
|
"step": 2380
|
|
},
|
|
{
|
|
"entropy": 6.152952861785889,
|
|
"epoch": 0.18556701030927836,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004998692246879116,
|
|
"loss": 5.9173,
|
|
"mean_token_accuracy": 0.14190907552838325,
|
|
"num_tokens": 4145160.0,
|
|
"step": 2385
|
|
},
|
|
{
|
|
"entropy": 6.123033618927002,
|
|
"epoch": 0.18595603968099592,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998682781651178,
|
|
"loss": 5.8841,
|
|
"mean_token_accuracy": 0.1437641464173794,
|
|
"num_tokens": 4153921.0,
|
|
"step": 2390
|
|
},
|
|
{
|
|
"entropy": 6.115445232391357,
|
|
"epoch": 0.18634506905271347,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004998673282303059,
|
|
"loss": 5.9681,
|
|
"mean_token_accuracy": 0.1352468617260456,
|
|
"num_tokens": 4162580.0,
|
|
"step": 2395
|
|
},
|
|
{
|
|
"entropy": 6.182539653778076,
|
|
"epoch": 0.18673409842443103,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004998663748834901,
|
|
"loss": 5.9663,
|
|
"mean_token_accuracy": 0.14548829048871995,
|
|
"num_tokens": 4170623.0,
|
|
"step": 2400
|
|
},
|
|
{
|
|
"entropy": 6.110377979278565,
|
|
"epoch": 0.18712312779614862,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004998654181246851,
|
|
"loss": 5.9514,
|
|
"mean_token_accuracy": 0.14497750550508498,
|
|
"num_tokens": 4178724.0,
|
|
"step": 2405
|
|
},
|
|
{
|
|
"entropy": 6.137342739105224,
|
|
"epoch": 0.18751215716786618,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998644579539052,
|
|
"loss": 5.9613,
|
|
"mean_token_accuracy": 0.1416378900408745,
|
|
"num_tokens": 4187773.0,
|
|
"step": 2410
|
|
},
|
|
{
|
|
"entropy": 6.170235538482666,
|
|
"epoch": 0.18790118653958374,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000499863494371165,
|
|
"loss": 5.9529,
|
|
"mean_token_accuracy": 0.13757317140698433,
|
|
"num_tokens": 4196628.0,
|
|
"step": 2415
|
|
},
|
|
{
|
|
"entropy": 6.15802321434021,
|
|
"epoch": 0.1882902159113013,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998625273764793,
|
|
"loss": 5.9779,
|
|
"mean_token_accuracy": 0.1390997901558876,
|
|
"num_tokens": 4205090.0,
|
|
"step": 2420
|
|
},
|
|
{
|
|
"entropy": 6.209850788116455,
|
|
"epoch": 0.18867924528301888,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004998615569698626,
|
|
"loss": 5.8944,
|
|
"mean_token_accuracy": 0.1414852797985077,
|
|
"num_tokens": 4212757.0,
|
|
"step": 2425
|
|
},
|
|
{
|
|
"entropy": 6.018552446365357,
|
|
"epoch": 0.18906827465473644,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998605831513296,
|
|
"loss": 5.9541,
|
|
"mean_token_accuracy": 0.14190278872847556,
|
|
"num_tokens": 4221556.0,
|
|
"step": 2430
|
|
},
|
|
{
|
|
"entropy": 6.107316589355468,
|
|
"epoch": 0.189457304026454,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004998596059208953,
|
|
"loss": 5.9427,
|
|
"mean_token_accuracy": 0.13826509863138198,
|
|
"num_tokens": 4231524.0,
|
|
"step": 2435
|
|
},
|
|
{
|
|
"entropy": 6.196195983886719,
|
|
"epoch": 0.18984633339817156,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998586252785743,
|
|
"loss": 5.9895,
|
|
"mean_token_accuracy": 0.1437416195869446,
|
|
"num_tokens": 4240229.0,
|
|
"step": 2440
|
|
},
|
|
{
|
|
"entropy": 6.146422052383423,
|
|
"epoch": 0.19023536276988912,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004998576412243816,
|
|
"loss": 5.8743,
|
|
"mean_token_accuracy": 0.14444278329610824,
|
|
"num_tokens": 4248053.0,
|
|
"step": 2445
|
|
},
|
|
{
|
|
"entropy": 6.164689350128174,
|
|
"epoch": 0.1906243921416067,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004998566537583321,
|
|
"loss": 5.9185,
|
|
"mean_token_accuracy": 0.14325421303510666,
|
|
"num_tokens": 4256019.0,
|
|
"step": 2450
|
|
},
|
|
{
|
|
"entropy": 6.0683635711669925,
|
|
"epoch": 0.19101342151332426,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998556628804408,
|
|
"loss": 5.9053,
|
|
"mean_token_accuracy": 0.14163314551115036,
|
|
"num_tokens": 4263805.0,
|
|
"step": 2455
|
|
},
|
|
{
|
|
"entropy": 6.10060682296753,
|
|
"epoch": 0.19140245088504182,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998546685907225,
|
|
"loss": 5.9544,
|
|
"mean_token_accuracy": 0.13736186251044274,
|
|
"num_tokens": 4272712.0,
|
|
"step": 2460
|
|
},
|
|
{
|
|
"entropy": 6.20326189994812,
|
|
"epoch": 0.19179148025675938,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998536708891927,
|
|
"loss": 5.8959,
|
|
"mean_token_accuracy": 0.1452920749783516,
|
|
"num_tokens": 4281222.0,
|
|
"step": 2465
|
|
},
|
|
{
|
|
"entropy": 6.094033193588257,
|
|
"epoch": 0.19218050962847694,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998526697758663,
|
|
"loss": 6.0001,
|
|
"mean_token_accuracy": 0.13505400642752646,
|
|
"num_tokens": 4290558.0,
|
|
"step": 2470
|
|
},
|
|
{
|
|
"entropy": 6.264354085922241,
|
|
"epoch": 0.19256953900019452,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998516652507585,
|
|
"loss": 6.0245,
|
|
"mean_token_accuracy": 0.13424147367477418,
|
|
"num_tokens": 4299684.0,
|
|
"step": 2475
|
|
},
|
|
{
|
|
"entropy": 6.101936912536621,
|
|
"epoch": 0.19295856837191208,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004998506573138846,
|
|
"loss": 5.9608,
|
|
"mean_token_accuracy": 0.14035997539758682,
|
|
"num_tokens": 4308938.0,
|
|
"step": 2480
|
|
},
|
|
{
|
|
"entropy": 6.069972848892212,
|
|
"epoch": 0.19334759774362964,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004998496459652598,
|
|
"loss": 5.828,
|
|
"mean_token_accuracy": 0.147909976541996,
|
|
"num_tokens": 4317646.0,
|
|
"step": 2485
|
|
},
|
|
{
|
|
"entropy": 6.097158575057984,
|
|
"epoch": 0.1937366271153472,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004998486312048995,
|
|
"loss": 5.9509,
|
|
"mean_token_accuracy": 0.14012686312198638,
|
|
"num_tokens": 4326876.0,
|
|
"step": 2490
|
|
},
|
|
{
|
|
"entropy": 6.119687271118164,
|
|
"epoch": 0.19412565648706478,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004998476130328193,
|
|
"loss": 5.9374,
|
|
"mean_token_accuracy": 0.14259177893400193,
|
|
"num_tokens": 4335391.0,
|
|
"step": 2495
|
|
},
|
|
{
|
|
"entropy": 6.211879730224609,
|
|
"epoch": 0.19451468585878234,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004998465914490343,
|
|
"loss": 5.9104,
|
|
"mean_token_accuracy": 0.1425481393933296,
|
|
"num_tokens": 4343253.0,
|
|
"step": 2500
|
|
},
|
|
{
|
|
"entropy": 5.971693420410157,
|
|
"epoch": 0.1949037152304999,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00049984556645356,
|
|
"loss": 5.8904,
|
|
"mean_token_accuracy": 0.13843516409397125,
|
|
"num_tokens": 4352161.0,
|
|
"step": 2505
|
|
},
|
|
{
|
|
"entropy": 6.155507898330688,
|
|
"epoch": 0.19529274460221746,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004998445380464124,
|
|
"loss": 5.853,
|
|
"mean_token_accuracy": 0.1473579704761505,
|
|
"num_tokens": 4360414.0,
|
|
"step": 2510
|
|
},
|
|
{
|
|
"entropy": 6.0863183498382565,
|
|
"epoch": 0.19568177397393502,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004998435062276066,
|
|
"loss": 5.8366,
|
|
"mean_token_accuracy": 0.15001533925533295,
|
|
"num_tokens": 4369375.0,
|
|
"step": 2515
|
|
},
|
|
{
|
|
"entropy": 5.990550470352173,
|
|
"epoch": 0.1960708033456526,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998424709971586,
|
|
"loss": 5.8722,
|
|
"mean_token_accuracy": 0.14208223000168801,
|
|
"num_tokens": 4378638.0,
|
|
"step": 2520
|
|
},
|
|
{
|
|
"entropy": 6.178989458084106,
|
|
"epoch": 0.19645983271737016,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004998414323550839,
|
|
"loss": 5.8595,
|
|
"mean_token_accuracy": 0.14671409651637077,
|
|
"num_tokens": 4388262.0,
|
|
"step": 2525
|
|
},
|
|
{
|
|
"entropy": 6.066281509399414,
|
|
"epoch": 0.19684886208908772,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004998403903013984,
|
|
"loss": 5.864,
|
|
"mean_token_accuracy": 0.14327401518821717,
|
|
"num_tokens": 4396894.0,
|
|
"step": 2530
|
|
},
|
|
{
|
|
"entropy": 6.139949607849121,
|
|
"epoch": 0.19723789146080528,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004998393448361179,
|
|
"loss": 5.9885,
|
|
"mean_token_accuracy": 0.14116159975528716,
|
|
"num_tokens": 4405455.0,
|
|
"step": 2535
|
|
},
|
|
{
|
|
"entropy": 6.167979383468628,
|
|
"epoch": 0.19762692083252287,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000499838295959258,
|
|
"loss": 5.8999,
|
|
"mean_token_accuracy": 0.1390222877264023,
|
|
"num_tokens": 4414355.0,
|
|
"step": 2540
|
|
},
|
|
{
|
|
"entropy": 5.997927045822143,
|
|
"epoch": 0.19801595020424043,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000499837243670835,
|
|
"loss": 5.7913,
|
|
"mean_token_accuracy": 0.15371408313512802,
|
|
"num_tokens": 4422305.0,
|
|
"step": 2545
|
|
},
|
|
{
|
|
"entropy": 6.17957763671875,
|
|
"epoch": 0.19840497957595798,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004998361879708646,
|
|
"loss": 5.9198,
|
|
"mean_token_accuracy": 0.1427523523569107,
|
|
"num_tokens": 4430813.0,
|
|
"step": 2550
|
|
},
|
|
{
|
|
"entropy": 6.099480628967285,
|
|
"epoch": 0.19879400894767554,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000499835128859363,
|
|
"loss": 5.8828,
|
|
"mean_token_accuracy": 0.1461223766207695,
|
|
"num_tokens": 4440229.0,
|
|
"step": 2555
|
|
},
|
|
{
|
|
"entropy": 6.00967698097229,
|
|
"epoch": 0.1991830383193931,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004998340663363461,
|
|
"loss": 5.8994,
|
|
"mean_token_accuracy": 0.14125050902366637,
|
|
"num_tokens": 4449417.0,
|
|
"step": 2560
|
|
},
|
|
{
|
|
"entropy": 6.186902904510498,
|
|
"epoch": 0.1995720676911107,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998330004018301,
|
|
"loss": 5.9456,
|
|
"mean_token_accuracy": 0.13707190454006196,
|
|
"num_tokens": 4457377.0,
|
|
"step": 2565
|
|
},
|
|
{
|
|
"entropy": 6.101526355743408,
|
|
"epoch": 0.19996109706282825,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004998319310558312,
|
|
"loss": 5.8663,
|
|
"mean_token_accuracy": 0.14043352231383324,
|
|
"num_tokens": 4466839.0,
|
|
"step": 2570
|
|
},
|
|
{
|
|
"entropy": 6.076670742034912,
|
|
"epoch": 0.2003501264345458,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004998308582983657,
|
|
"loss": 5.8854,
|
|
"mean_token_accuracy": 0.14421407207846643,
|
|
"num_tokens": 4476369.0,
|
|
"step": 2575
|
|
},
|
|
{
|
|
"entropy": 6.072381830215454,
|
|
"epoch": 0.20073915580626336,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004998297821294497,
|
|
"loss": 5.9561,
|
|
"mean_token_accuracy": 0.14137691259384155,
|
|
"num_tokens": 4485609.0,
|
|
"step": 2580
|
|
},
|
|
{
|
|
"entropy": 6.131612968444824,
|
|
"epoch": 0.20112818517798095,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998287025490995,
|
|
"loss": 5.9162,
|
|
"mean_token_accuracy": 0.14042819067835807,
|
|
"num_tokens": 4494535.0,
|
|
"step": 2585
|
|
},
|
|
{
|
|
"entropy": 6.1383223056793215,
|
|
"epoch": 0.2015172145496985,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004998276195573317,
|
|
"loss": 5.8955,
|
|
"mean_token_accuracy": 0.13853249028325082,
|
|
"num_tokens": 4503133.0,
|
|
"step": 2590
|
|
},
|
|
{
|
|
"entropy": 6.049847364425659,
|
|
"epoch": 0.20190624392141607,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004998265331541627,
|
|
"loss": 5.7882,
|
|
"mean_token_accuracy": 0.149039888381958,
|
|
"num_tokens": 4511465.0,
|
|
"step": 2595
|
|
},
|
|
{
|
|
"entropy": 6.050959205627441,
|
|
"epoch": 0.20229527329313363,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998254433396088,
|
|
"loss": 5.8551,
|
|
"mean_token_accuracy": 0.14632439315319062,
|
|
"num_tokens": 4520177.0,
|
|
"step": 2600
|
|
},
|
|
{
|
|
"entropy": 6.156892967224121,
|
|
"epoch": 0.20268430266485118,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004998243501136867,
|
|
"loss": 6.0153,
|
|
"mean_token_accuracy": 0.14031418338418006,
|
|
"num_tokens": 4528370.0,
|
|
"step": 2605
|
|
},
|
|
{
|
|
"entropy": 6.219958877563476,
|
|
"epoch": 0.20307333203656877,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004998232534764129,
|
|
"loss": 6.0333,
|
|
"mean_token_accuracy": 0.13372237458825112,
|
|
"num_tokens": 4538258.0,
|
|
"step": 2610
|
|
},
|
|
{
|
|
"entropy": 6.0912260055542,
|
|
"epoch": 0.20346236140828633,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998221534278041,
|
|
"loss": 5.9243,
|
|
"mean_token_accuracy": 0.14148016050457954,
|
|
"num_tokens": 4547300.0,
|
|
"step": 2615
|
|
},
|
|
{
|
|
"entropy": 6.163697814941406,
|
|
"epoch": 0.2038513907800039,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004998210499678769,
|
|
"loss": 5.9894,
|
|
"mean_token_accuracy": 0.13505751192569732,
|
|
"num_tokens": 4556877.0,
|
|
"step": 2620
|
|
},
|
|
{
|
|
"entropy": 6.094733190536499,
|
|
"epoch": 0.20424042015172145,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998199430966481,
|
|
"loss": 5.8389,
|
|
"mean_token_accuracy": 0.1471896141767502,
|
|
"num_tokens": 4565999.0,
|
|
"step": 2625
|
|
},
|
|
{
|
|
"entropy": 6.09189739227295,
|
|
"epoch": 0.20462944952343903,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998188328141346,
|
|
"loss": 5.8909,
|
|
"mean_token_accuracy": 0.13818741962313652,
|
|
"num_tokens": 4574027.0,
|
|
"step": 2630
|
|
},
|
|
{
|
|
"entropy": 6.029260110855103,
|
|
"epoch": 0.2050184788951566,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004998177191203531,
|
|
"loss": 5.8962,
|
|
"mean_token_accuracy": 0.1333038367331028,
|
|
"num_tokens": 4582402.0,
|
|
"step": 2635
|
|
},
|
|
{
|
|
"entropy": 6.102605962753296,
|
|
"epoch": 0.20540750826687415,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998166020153204,
|
|
"loss": 5.8411,
|
|
"mean_token_accuracy": 0.14166108146309853,
|
|
"num_tokens": 4590381.0,
|
|
"step": 2640
|
|
},
|
|
{
|
|
"entropy": 6.096075630187988,
|
|
"epoch": 0.2057965376385917,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998154814990538,
|
|
"loss": 5.9002,
|
|
"mean_token_accuracy": 0.13965460956096648,
|
|
"num_tokens": 4598910.0,
|
|
"step": 2645
|
|
},
|
|
{
|
|
"entropy": 6.230145454406738,
|
|
"epoch": 0.20618556701030927,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00049981435757157,
|
|
"loss": 6.0215,
|
|
"mean_token_accuracy": 0.13467366695404054,
|
|
"num_tokens": 4607400.0,
|
|
"step": 2650
|
|
},
|
|
{
|
|
"entropy": 6.057853126525879,
|
|
"epoch": 0.20657459638202685,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004998132302328862,
|
|
"loss": 5.9545,
|
|
"mean_token_accuracy": 0.14162048250436782,
|
|
"num_tokens": 4616510.0,
|
|
"step": 2655
|
|
},
|
|
{
|
|
"entropy": 6.152973604202271,
|
|
"epoch": 0.2069636257537444,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004998120994830195,
|
|
"loss": 5.9042,
|
|
"mean_token_accuracy": 0.14345652610063553,
|
|
"num_tokens": 4624529.0,
|
|
"step": 2660
|
|
},
|
|
{
|
|
"entropy": 6.153080034255981,
|
|
"epoch": 0.20735265512546197,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000499810965321987,
|
|
"loss": 5.8473,
|
|
"mean_token_accuracy": 0.144081724435091,
|
|
"num_tokens": 4632141.0,
|
|
"step": 2665
|
|
},
|
|
{
|
|
"entropy": 6.135512018203736,
|
|
"epoch": 0.20774168449717953,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998098277498059,
|
|
"loss": 6.0399,
|
|
"mean_token_accuracy": 0.13816287219524384,
|
|
"num_tokens": 4640378.0,
|
|
"step": 2670
|
|
},
|
|
{
|
|
"entropy": 6.064649534225464,
|
|
"epoch": 0.2081307138688971,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004998086867664934,
|
|
"loss": 5.8117,
|
|
"mean_token_accuracy": 0.1414397269487381,
|
|
"num_tokens": 4649313.0,
|
|
"step": 2675
|
|
},
|
|
{
|
|
"entropy": 6.121465873718262,
|
|
"epoch": 0.20851974324061467,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000499807542372067,
|
|
"loss": 5.9071,
|
|
"mean_token_accuracy": 0.14331126660108567,
|
|
"num_tokens": 4658272.0,
|
|
"step": 2680
|
|
},
|
|
{
|
|
"entropy": 6.036688280105591,
|
|
"epoch": 0.20890877261233223,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004998063945665439,
|
|
"loss": 5.7901,
|
|
"mean_token_accuracy": 0.1520828664302826,
|
|
"num_tokens": 4665970.0,
|
|
"step": 2685
|
|
},
|
|
{
|
|
"entropy": 6.189170980453492,
|
|
"epoch": 0.2092978019840498,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004998052433499416,
|
|
"loss": 6.0293,
|
|
"mean_token_accuracy": 0.13662858083844184,
|
|
"num_tokens": 4675308.0,
|
|
"step": 2690
|
|
},
|
|
{
|
|
"entropy": 6.077781295776367,
|
|
"epoch": 0.20968683135576735,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998040887222776,
|
|
"loss": 5.8742,
|
|
"mean_token_accuracy": 0.14358604997396468,
|
|
"num_tokens": 4684316.0,
|
|
"step": 2695
|
|
},
|
|
{
|
|
"entropy": 6.031701469421387,
|
|
"epoch": 0.21007586072748494,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998029306835693,
|
|
"loss": 5.7824,
|
|
"mean_token_accuracy": 0.14697564840316774,
|
|
"num_tokens": 4693029.0,
|
|
"step": 2700
|
|
},
|
|
{
|
|
"entropy": 6.0618767738342285,
|
|
"epoch": 0.2104648900992025,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998017692338344,
|
|
"loss": 5.9842,
|
|
"mean_token_accuracy": 0.13347845301032066,
|
|
"num_tokens": 4702404.0,
|
|
"step": 2705
|
|
},
|
|
{
|
|
"entropy": 6.141680812835693,
|
|
"epoch": 0.21085391947092005,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004998006043730905,
|
|
"loss": 5.9526,
|
|
"mean_token_accuracy": 0.13373763784766196,
|
|
"num_tokens": 4711126.0,
|
|
"step": 2710
|
|
},
|
|
{
|
|
"entropy": 6.116554880142212,
|
|
"epoch": 0.2112429488426376,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004997994361013551,
|
|
"loss": 5.9516,
|
|
"mean_token_accuracy": 0.1492009460926056,
|
|
"num_tokens": 4719816.0,
|
|
"step": 2715
|
|
},
|
|
{
|
|
"entropy": 6.174014472961426,
|
|
"epoch": 0.21163197821435517,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004997982644186461,
|
|
"loss": 5.8835,
|
|
"mean_token_accuracy": 0.14039621651172637,
|
|
"num_tokens": 4728294.0,
|
|
"step": 2720
|
|
},
|
|
{
|
|
"entropy": 6.0613030910491945,
|
|
"epoch": 0.21202100758607276,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004997970893249813,
|
|
"loss": 5.815,
|
|
"mean_token_accuracy": 0.1434742122888565,
|
|
"num_tokens": 4736708.0,
|
|
"step": 2725
|
|
},
|
|
{
|
|
"entropy": 6.044667100906372,
|
|
"epoch": 0.21241003695779032,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004997959108203785,
|
|
"loss": 5.9964,
|
|
"mean_token_accuracy": 0.1296418972313404,
|
|
"num_tokens": 4744893.0,
|
|
"step": 2730
|
|
},
|
|
{
|
|
"entropy": 6.243737983703613,
|
|
"epoch": 0.21279906632950787,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004997947289048554,
|
|
"loss": 5.9463,
|
|
"mean_token_accuracy": 0.1440265618264675,
|
|
"num_tokens": 4753246.0,
|
|
"step": 2735
|
|
},
|
|
{
|
|
"entropy": 6.026007032394409,
|
|
"epoch": 0.21318809570122543,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004997935435784302,
|
|
"loss": 5.875,
|
|
"mean_token_accuracy": 0.14041776210069656,
|
|
"num_tokens": 4762229.0,
|
|
"step": 2740
|
|
},
|
|
{
|
|
"entropy": 5.99229941368103,
|
|
"epoch": 0.21357712507294302,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004997923548411208,
|
|
"loss": 5.8139,
|
|
"mean_token_accuracy": 0.148726749420166,
|
|
"num_tokens": 4771315.0,
|
|
"step": 2745
|
|
},
|
|
{
|
|
"entropy": 5.956744146347046,
|
|
"epoch": 0.21396615444466058,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000499791162692945,
|
|
"loss": 5.7628,
|
|
"mean_token_accuracy": 0.15489397719502448,
|
|
"num_tokens": 4779848.0,
|
|
"step": 2750
|
|
},
|
|
{
|
|
"entropy": 6.160625457763672,
|
|
"epoch": 0.21435518381637814,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004997899671339214,
|
|
"loss": 5.999,
|
|
"mean_token_accuracy": 0.13992350101470946,
|
|
"num_tokens": 4788939.0,
|
|
"step": 2755
|
|
},
|
|
{
|
|
"entropy": 6.131371355056762,
|
|
"epoch": 0.2147442131880957,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004997887681640675,
|
|
"loss": 5.9017,
|
|
"mean_token_accuracy": 0.14416032284498215,
|
|
"num_tokens": 4797719.0,
|
|
"step": 2760
|
|
},
|
|
{
|
|
"entropy": 6.09780068397522,
|
|
"epoch": 0.21513324255981325,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004997875657834021,
|
|
"loss": 5.9332,
|
|
"mean_token_accuracy": 0.13998101651668549,
|
|
"num_tokens": 4805601.0,
|
|
"step": 2765
|
|
},
|
|
{
|
|
"entropy": 6.137105464935303,
|
|
"epoch": 0.21552227193153084,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004997863599919432,
|
|
"loss": 5.8913,
|
|
"mean_token_accuracy": 0.1408081702888012,
|
|
"num_tokens": 4814993.0,
|
|
"step": 2770
|
|
},
|
|
{
|
|
"entropy": 6.115447616577148,
|
|
"epoch": 0.2159113013032484,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004997851507897089,
|
|
"loss": 5.8477,
|
|
"mean_token_accuracy": 0.1397731989622116,
|
|
"num_tokens": 4824156.0,
|
|
"step": 2775
|
|
},
|
|
{
|
|
"entropy": 5.991670274734497,
|
|
"epoch": 0.21630033067496596,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004997839381767178,
|
|
"loss": 5.9414,
|
|
"mean_token_accuracy": 0.14050936251878737,
|
|
"num_tokens": 4833827.0,
|
|
"step": 2780
|
|
},
|
|
{
|
|
"entropy": 6.081092882156372,
|
|
"epoch": 0.21668936004668352,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004997827221529882,
|
|
"loss": 5.8829,
|
|
"mean_token_accuracy": 0.1428877130150795,
|
|
"num_tokens": 4842801.0,
|
|
"step": 2785
|
|
},
|
|
{
|
|
"entropy": 6.08880844116211,
|
|
"epoch": 0.2170783894184011,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004997815027185386,
|
|
"loss": 5.7536,
|
|
"mean_token_accuracy": 0.14653713181614875,
|
|
"num_tokens": 4850928.0,
|
|
"step": 2790
|
|
},
|
|
{
|
|
"entropy": 5.995206022262574,
|
|
"epoch": 0.21746741879011866,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004997802798733874,
|
|
"loss": 5.8637,
|
|
"mean_token_accuracy": 0.1513894386589527,
|
|
"num_tokens": 4859510.0,
|
|
"step": 2795
|
|
},
|
|
{
|
|
"entropy": 6.10595588684082,
|
|
"epoch": 0.21785644816183622,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004997790536175534,
|
|
"loss": 5.8902,
|
|
"mean_token_accuracy": 0.1465415373444557,
|
|
"num_tokens": 4868201.0,
|
|
"step": 2800
|
|
},
|
|
{
|
|
"entropy": 6.035786819458008,
|
|
"epoch": 0.21824547753355378,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004997778239510548,
|
|
"loss": 5.816,
|
|
"mean_token_accuracy": 0.15248959213495256,
|
|
"num_tokens": 4876896.0,
|
|
"step": 2805
|
|
},
|
|
{
|
|
"entropy": 6.001589441299439,
|
|
"epoch": 0.21863450690527134,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004997765908739106,
|
|
"loss": 5.7908,
|
|
"mean_token_accuracy": 0.1534420743584633,
|
|
"num_tokens": 4885136.0,
|
|
"step": 2810
|
|
},
|
|
{
|
|
"entropy": 6.0229329586029055,
|
|
"epoch": 0.21902353627698892,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004997753543861395,
|
|
"loss": 5.7893,
|
|
"mean_token_accuracy": 0.14993626177310942,
|
|
"num_tokens": 4893277.0,
|
|
"step": 2815
|
|
},
|
|
{
|
|
"entropy": 6.036485242843628,
|
|
"epoch": 0.21941256564870648,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00049977411448776,
|
|
"loss": 5.9514,
|
|
"mean_token_accuracy": 0.1361225239932537,
|
|
"num_tokens": 4901977.0,
|
|
"step": 2820
|
|
},
|
|
{
|
|
"entropy": 6.142391729354858,
|
|
"epoch": 0.21980159502042404,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004997728711787912,
|
|
"loss": 5.9431,
|
|
"mean_token_accuracy": 0.1336057133972645,
|
|
"num_tokens": 4910888.0,
|
|
"step": 2825
|
|
},
|
|
{
|
|
"entropy": 6.031327724456787,
|
|
"epoch": 0.2201906243921416,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004997716244592518,
|
|
"loss": 5.9456,
|
|
"mean_token_accuracy": 0.13697238340973855,
|
|
"num_tokens": 4920369.0,
|
|
"step": 2830
|
|
},
|
|
{
|
|
"entropy": 6.1665221691131595,
|
|
"epoch": 0.22057965376385918,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004997703743291607,
|
|
"loss": 5.9347,
|
|
"mean_token_accuracy": 0.13784253150224685,
|
|
"num_tokens": 4928799.0,
|
|
"step": 2835
|
|
},
|
|
{
|
|
"entropy": 6.118892431259155,
|
|
"epoch": 0.22096868313557674,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000499769120788537,
|
|
"loss": 5.8422,
|
|
"mean_token_accuracy": 0.15058550387620925,
|
|
"num_tokens": 4937194.0,
|
|
"step": 2840
|
|
},
|
|
{
|
|
"entropy": 6.045169401168823,
|
|
"epoch": 0.2213577125072943,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004997678638373995,
|
|
"loss": 5.9202,
|
|
"mean_token_accuracy": 0.13822367861866952,
|
|
"num_tokens": 4946174.0,
|
|
"step": 2845
|
|
},
|
|
{
|
|
"entropy": 6.097653436660766,
|
|
"epoch": 0.22174674187901186,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004997666034757676,
|
|
"loss": 5.8543,
|
|
"mean_token_accuracy": 0.13650616109371186,
|
|
"num_tokens": 4955376.0,
|
|
"step": 2850
|
|
},
|
|
{
|
|
"entropy": 6.003319025039673,
|
|
"epoch": 0.22213577125072942,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004997653397036603,
|
|
"loss": 5.8545,
|
|
"mean_token_accuracy": 0.14963753297924995,
|
|
"num_tokens": 4964138.0,
|
|
"step": 2855
|
|
},
|
|
{
|
|
"entropy": 6.087133550643921,
|
|
"epoch": 0.222524800622447,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004997640725210965,
|
|
"loss": 5.945,
|
|
"mean_token_accuracy": 0.13923729509115218,
|
|
"num_tokens": 4973868.0,
|
|
"step": 2860
|
|
},
|
|
{
|
|
"entropy": 6.072530794143677,
|
|
"epoch": 0.22291382999416456,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004997628019280958,
|
|
"loss": 5.8158,
|
|
"mean_token_accuracy": 0.14615875333547593,
|
|
"num_tokens": 4982687.0,
|
|
"step": 2865
|
|
},
|
|
{
|
|
"entropy": 6.07082724571228,
|
|
"epoch": 0.22330285936588212,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004997615279246773,
|
|
"loss": 5.8724,
|
|
"mean_token_accuracy": 0.13691072314977645,
|
|
"num_tokens": 4992072.0,
|
|
"step": 2870
|
|
},
|
|
{
|
|
"entropy": 6.080668687820435,
|
|
"epoch": 0.22369188873759968,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004997602505108603,
|
|
"loss": 5.8261,
|
|
"mean_token_accuracy": 0.14304942935705184,
|
|
"num_tokens": 5000551.0,
|
|
"step": 2875
|
|
},
|
|
{
|
|
"entropy": 6.073841190338134,
|
|
"epoch": 0.22408091810931724,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004997589696866644,
|
|
"loss": 5.9859,
|
|
"mean_token_accuracy": 0.13843553885817528,
|
|
"num_tokens": 5009292.0,
|
|
"step": 2880
|
|
},
|
|
{
|
|
"entropy": 6.066045570373535,
|
|
"epoch": 0.22446994748103483,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004997576854521088,
|
|
"loss": 5.8342,
|
|
"mean_token_accuracy": 0.1451627016067505,
|
|
"num_tokens": 5018407.0,
|
|
"step": 2885
|
|
},
|
|
{
|
|
"entropy": 5.999263858795166,
|
|
"epoch": 0.22485897685275238,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000499756397807213,
|
|
"loss": 5.8877,
|
|
"mean_token_accuracy": 0.14157619029283525,
|
|
"num_tokens": 5027353.0,
|
|
"step": 2890
|
|
},
|
|
{
|
|
"entropy": 6.1293292999267575,
|
|
"epoch": 0.22524800622446994,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004997551067519966,
|
|
"loss": 5.8898,
|
|
"mean_token_accuracy": 0.14480420351028442,
|
|
"num_tokens": 5036476.0,
|
|
"step": 2895
|
|
},
|
|
{
|
|
"entropy": 6.099696016311645,
|
|
"epoch": 0.2256370355961875,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004997538122864792,
|
|
"loss": 5.8458,
|
|
"mean_token_accuracy": 0.1427316889166832,
|
|
"num_tokens": 5045132.0,
|
|
"step": 2900
|
|
},
|
|
{
|
|
"entropy": 6.082901287078857,
|
|
"epoch": 0.2260260649679051,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004997525144106804,
|
|
"loss": 5.8717,
|
|
"mean_token_accuracy": 0.1474373534321785,
|
|
"num_tokens": 5053665.0,
|
|
"step": 2905
|
|
},
|
|
{
|
|
"entropy": 6.110235738754272,
|
|
"epoch": 0.22641509433962265,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00049975121312462,
|
|
"loss": 5.8163,
|
|
"mean_token_accuracy": 0.1529403179883957,
|
|
"num_tokens": 5062516.0,
|
|
"step": 2910
|
|
},
|
|
{
|
|
"entropy": 6.043049669265747,
|
|
"epoch": 0.2268041237113402,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004997499084283177,
|
|
"loss": 5.8536,
|
|
"mean_token_accuracy": 0.14332823008298873,
|
|
"num_tokens": 5071260.0,
|
|
"step": 2915
|
|
},
|
|
{
|
|
"entropy": 5.952953195571899,
|
|
"epoch": 0.22719315308305776,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004997486003217932,
|
|
"loss": 5.8082,
|
|
"mean_token_accuracy": 0.15106913149356843,
|
|
"num_tokens": 5079215.0,
|
|
"step": 2920
|
|
},
|
|
{
|
|
"entropy": 6.071919727325439,
|
|
"epoch": 0.22758218245477532,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004997472888050664,
|
|
"loss": 5.8879,
|
|
"mean_token_accuracy": 0.1414925940334797,
|
|
"num_tokens": 5088404.0,
|
|
"step": 2925
|
|
},
|
|
{
|
|
"entropy": 6.055942630767822,
|
|
"epoch": 0.2279712118264929,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004997459738781573,
|
|
"loss": 5.803,
|
|
"mean_token_accuracy": 0.147076266258955,
|
|
"num_tokens": 5096756.0,
|
|
"step": 2930
|
|
},
|
|
{
|
|
"entropy": 6.042949390411377,
|
|
"epoch": 0.22836024119821047,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004997446555410857,
|
|
"loss": 5.967,
|
|
"mean_token_accuracy": 0.14154459834098815,
|
|
"num_tokens": 5106160.0,
|
|
"step": 2935
|
|
},
|
|
{
|
|
"entropy": 5.963182592391968,
|
|
"epoch": 0.22874927056992803,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004997433337938716,
|
|
"loss": 5.899,
|
|
"mean_token_accuracy": 0.14055694192647933,
|
|
"num_tokens": 5114915.0,
|
|
"step": 2940
|
|
},
|
|
{
|
|
"entropy": 6.1321821212768555,
|
|
"epoch": 0.22913829994164558,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004997420086365351,
|
|
"loss": 5.8087,
|
|
"mean_token_accuracy": 0.14655397981405258,
|
|
"num_tokens": 5123249.0,
|
|
"step": 2945
|
|
},
|
|
{
|
|
"entropy": 5.994801664352417,
|
|
"epoch": 0.22952732931336317,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004997406800690966,
|
|
"loss": 5.7989,
|
|
"mean_token_accuracy": 0.14508022367954254,
|
|
"num_tokens": 5131906.0,
|
|
"step": 2950
|
|
},
|
|
{
|
|
"entropy": 6.047790002822876,
|
|
"epoch": 0.22991635868508073,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004997393480915758,
|
|
"loss": 5.795,
|
|
"mean_token_accuracy": 0.1496501974761486,
|
|
"num_tokens": 5140740.0,
|
|
"step": 2955
|
|
},
|
|
{
|
|
"entropy": 6.069603347778321,
|
|
"epoch": 0.2303053880567983,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004997380127039931,
|
|
"loss": 5.9802,
|
|
"mean_token_accuracy": 0.14554987102746964,
|
|
"num_tokens": 5149748.0,
|
|
"step": 2960
|
|
},
|
|
{
|
|
"entropy": 5.9712036609649655,
|
|
"epoch": 0.23069441742851585,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004997366739063688,
|
|
"loss": 5.7259,
|
|
"mean_token_accuracy": 0.15179628431797026,
|
|
"num_tokens": 5158475.0,
|
|
"step": 2965
|
|
},
|
|
{
|
|
"entropy": 6.014142608642578,
|
|
"epoch": 0.2310834468002334,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004997353316987231,
|
|
"loss": 5.9024,
|
|
"mean_token_accuracy": 0.1394285723567009,
|
|
"num_tokens": 5166593.0,
|
|
"step": 2970
|
|
},
|
|
{
|
|
"entropy": 6.108148241043091,
|
|
"epoch": 0.231472476171951,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004997339860810765,
|
|
"loss": 5.8795,
|
|
"mean_token_accuracy": 0.1452465608716011,
|
|
"num_tokens": 5175557.0,
|
|
"step": 2975
|
|
},
|
|
{
|
|
"entropy": 6.0830058574676515,
|
|
"epoch": 0.23186150554366855,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004997326370534495,
|
|
"loss": 5.7837,
|
|
"mean_token_accuracy": 0.14554769918322563,
|
|
"num_tokens": 5184140.0,
|
|
"step": 2980
|
|
},
|
|
{
|
|
"entropy": 6.019090270996093,
|
|
"epoch": 0.2322505349153861,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004997312846158622,
|
|
"loss": 5.8684,
|
|
"mean_token_accuracy": 0.14349435344338418,
|
|
"num_tokens": 5192347.0,
|
|
"step": 2985
|
|
},
|
|
{
|
|
"entropy": 6.08717942237854,
|
|
"epoch": 0.23263956428710367,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004997299287683355,
|
|
"loss": 5.8239,
|
|
"mean_token_accuracy": 0.14950033277273178,
|
|
"num_tokens": 5201327.0,
|
|
"step": 2990
|
|
},
|
|
{
|
|
"entropy": 6.0416545391082765,
|
|
"epoch": 0.23302859365882125,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004997285695108898,
|
|
"loss": 5.9213,
|
|
"mean_token_accuracy": 0.14163968116044998,
|
|
"num_tokens": 5209873.0,
|
|
"step": 2995
|
|
},
|
|
{
|
|
"entropy": 6.0891759395599365,
|
|
"epoch": 0.2334176230305388,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004997272068435458,
|
|
"loss": 5.8338,
|
|
"mean_token_accuracy": 0.14707664102315904,
|
|
"num_tokens": 5219176.0,
|
|
"step": 3000
|
|
},
|
|
{
|
|
"epoch": 0.2334176230305388,
|
|
"eval_entropy": 5.810826111115207,
|
|
"eval_loss": 5.8746232986450195,
|
|
"eval_mean_token_accuracy": 0.15242935873360103,
|
|
"eval_num_tokens": 5219176.0,
|
|
"eval_runtime": 21.8651,
|
|
"eval_samples_per_second": 1900.651,
|
|
"eval_steps_per_second": 237.593,
|
|
"step": 3000
|
|
}
|
|
],
|
|
"logging_steps": 5,
|
|
"max_steps": 128520,
|
|
"num_input_tokens_seen": 0,
|
|
"num_train_epochs": 10,
|
|
"save_steps": 3000,
|
|
"stateful_callbacks": {
|
|
"TrainerControl": {
|
|
"args": {
|
|
"should_epoch_stop": false,
|
|
"should_evaluate": false,
|
|
"should_log": false,
|
|
"should_save": true,
|
|
"should_training_stop": false
|
|
},
|
|
"attributes": {}
|
|
}
|
|
},
|
|
"total_flos": 1052336906403840.0,
|
|
"train_batch_size": 16,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|