4032fffd3d
Model: fpadovani/eus-latn-10mb-after-ppt-shuff-dyck-100mb-ckpt500_seed10 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": 0.26492405510420347,
|
|
"eval_steps": 3000,
|
|
"global_step": 3000,
|
|
"is_hyper_param_search": false,
|
|
"is_local_process_zero": true,
|
|
"is_world_process_zero": true,
|
|
"log_history": [
|
|
{
|
|
"entropy": 4.937930107116699,
|
|
"epoch": 0.0004415400918403391,
|
|
"grad_norm": 16.25,
|
|
"learning_rate": 2e-06,
|
|
"loss": 14.1689,
|
|
"mean_token_accuracy": 0.0,
|
|
"num_tokens": 9295.0,
|
|
"step": 5
|
|
},
|
|
{
|
|
"entropy": 4.9478801727294925,
|
|
"epoch": 0.0008830801836806782,
|
|
"grad_norm": 16.75,
|
|
"learning_rate": 4.5e-06,
|
|
"loss": 14.0804,
|
|
"mean_token_accuracy": 0.0,
|
|
"num_tokens": 17694.0,
|
|
"step": 10
|
|
},
|
|
{
|
|
"entropy": 4.970736074447632,
|
|
"epoch": 0.0013246202755210173,
|
|
"grad_norm": 17.875,
|
|
"learning_rate": 7e-06,
|
|
"loss": 14.0763,
|
|
"mean_token_accuracy": 0.0,
|
|
"num_tokens": 26875.0,
|
|
"step": 15
|
|
},
|
|
{
|
|
"entropy": 5.00352029800415,
|
|
"epoch": 0.0017661603673613563,
|
|
"grad_norm": 20.625,
|
|
"learning_rate": 9.5e-06,
|
|
"loss": 13.9684,
|
|
"mean_token_accuracy": 9.208103292621673e-05,
|
|
"num_tokens": 38072.0,
|
|
"step": 20
|
|
},
|
|
{
|
|
"entropy": 5.193281745910644,
|
|
"epoch": 0.0022077004592016957,
|
|
"grad_norm": 25.875,
|
|
"learning_rate": 1.2e-05,
|
|
"loss": 13.4895,
|
|
"mean_token_accuracy": 0.00010976948542520403,
|
|
"num_tokens": 48899.0,
|
|
"step": 25
|
|
},
|
|
{
|
|
"entropy": 5.656161642074585,
|
|
"epoch": 0.0026492405510420347,
|
|
"grad_norm": 31.0,
|
|
"learning_rate": 1.4500000000000002e-05,
|
|
"loss": 12.7498,
|
|
"mean_token_accuracy": 0.0,
|
|
"num_tokens": 57994.0,
|
|
"step": 30
|
|
},
|
|
{
|
|
"entropy": 7.820593309402466,
|
|
"epoch": 0.0030907806428823736,
|
|
"grad_norm": 14.5625,
|
|
"learning_rate": 1.7000000000000003e-05,
|
|
"loss": 11.581,
|
|
"mean_token_accuracy": 0.0,
|
|
"num_tokens": 67252.0,
|
|
"step": 35
|
|
},
|
|
{
|
|
"entropy": 10.46483039855957,
|
|
"epoch": 0.0035323207347227126,
|
|
"grad_norm": 3.5625,
|
|
"learning_rate": 1.95e-05,
|
|
"loss": 10.7728,
|
|
"mean_token_accuracy": 0.00608623722800985,
|
|
"num_tokens": 76787.0,
|
|
"step": 40
|
|
},
|
|
{
|
|
"entropy": 10.734039402008056,
|
|
"epoch": 0.003973860826563052,
|
|
"grad_norm": 3.15625,
|
|
"learning_rate": 2.2e-05,
|
|
"loss": 10.6475,
|
|
"mean_token_accuracy": 0.016124986205250026,
|
|
"num_tokens": 86718.0,
|
|
"step": 45
|
|
},
|
|
{
|
|
"entropy": 10.734684371948243,
|
|
"epoch": 0.004415400918403391,
|
|
"grad_norm": 2.96875,
|
|
"learning_rate": 2.4500000000000003e-05,
|
|
"loss": 10.444,
|
|
"mean_token_accuracy": 0.017893549520522356,
|
|
"num_tokens": 96136.0,
|
|
"step": 50
|
|
},
|
|
{
|
|
"entropy": 10.690448665618897,
|
|
"epoch": 0.00485694101024373,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 2.7e-05,
|
|
"loss": 10.2836,
|
|
"mean_token_accuracy": 0.016107181273400783,
|
|
"num_tokens": 106579.0,
|
|
"step": 55
|
|
},
|
|
{
|
|
"entropy": 10.6747314453125,
|
|
"epoch": 0.005298481102084069,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 2.95e-05,
|
|
"loss": 10.0794,
|
|
"mean_token_accuracy": 0.01910884603857994,
|
|
"num_tokens": 115698.0,
|
|
"step": 60
|
|
},
|
|
{
|
|
"entropy": 10.712893676757812,
|
|
"epoch": 0.005740021193924408,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 3.2e-05,
|
|
"loss": 9.987,
|
|
"mean_token_accuracy": 0.04295358825474978,
|
|
"num_tokens": 125141.0,
|
|
"step": 65
|
|
},
|
|
{
|
|
"entropy": 10.70653076171875,
|
|
"epoch": 0.006181561285764747,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 3.4500000000000005e-05,
|
|
"loss": 9.8323,
|
|
"mean_token_accuracy": 0.06280341930687428,
|
|
"num_tokens": 134148.0,
|
|
"step": 70
|
|
},
|
|
{
|
|
"entropy": 10.686304759979247,
|
|
"epoch": 0.006623101377605086,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 3.7e-05,
|
|
"loss": 9.8022,
|
|
"mean_token_accuracy": 0.05989494659006596,
|
|
"num_tokens": 143032.0,
|
|
"step": 75
|
|
},
|
|
{
|
|
"entropy": 10.672717380523682,
|
|
"epoch": 0.007064641469445425,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 3.95e-05,
|
|
"loss": 9.7113,
|
|
"mean_token_accuracy": 0.06549292616546154,
|
|
"num_tokens": 151477.0,
|
|
"step": 80
|
|
},
|
|
{
|
|
"entropy": 10.66338300704956,
|
|
"epoch": 0.007506181561285765,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 4.2000000000000004e-05,
|
|
"loss": 9.6711,
|
|
"mean_token_accuracy": 0.06344555392861366,
|
|
"num_tokens": 161364.0,
|
|
"step": 85
|
|
},
|
|
{
|
|
"entropy": 10.649686336517334,
|
|
"epoch": 0.007947721653126103,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 4.45e-05,
|
|
"loss": 9.5988,
|
|
"mean_token_accuracy": 0.059225669503211974,
|
|
"num_tokens": 171771.0,
|
|
"step": 90
|
|
},
|
|
{
|
|
"entropy": 10.630746650695801,
|
|
"epoch": 0.008389261744966443,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 4.7000000000000004e-05,
|
|
"loss": 9.4381,
|
|
"mean_token_accuracy": 0.06350292377173901,
|
|
"num_tokens": 180461.0,
|
|
"step": 95
|
|
},
|
|
{
|
|
"entropy": 10.59743824005127,
|
|
"epoch": 0.008830801836806783,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 4.9500000000000004e-05,
|
|
"loss": 9.4588,
|
|
"mean_token_accuracy": 0.06274225264787674,
|
|
"num_tokens": 190873.0,
|
|
"step": 100
|
|
},
|
|
{
|
|
"entropy": 10.572507667541505,
|
|
"epoch": 0.009272341928647121,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 5.2e-05,
|
|
"loss": 9.2659,
|
|
"mean_token_accuracy": 0.06957426071166992,
|
|
"num_tokens": 199146.0,
|
|
"step": 105
|
|
},
|
|
{
|
|
"entropy": 10.532439994812012,
|
|
"epoch": 0.00971388202048746,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 5.45e-05,
|
|
"loss": 9.2169,
|
|
"mean_token_accuracy": 0.07027090489864349,
|
|
"num_tokens": 208218.0,
|
|
"step": 110
|
|
},
|
|
{
|
|
"entropy": 10.482099723815917,
|
|
"epoch": 0.010155422112327799,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 5.7e-05,
|
|
"loss": 9.1174,
|
|
"mean_token_accuracy": 0.0710879024118185,
|
|
"num_tokens": 217548.0,
|
|
"step": 115
|
|
},
|
|
{
|
|
"entropy": 10.431210136413574,
|
|
"epoch": 0.010596962204168139,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 5.9499999999999996e-05,
|
|
"loss": 9.0402,
|
|
"mean_token_accuracy": 0.06714637242257596,
|
|
"num_tokens": 226157.0,
|
|
"step": 120
|
|
},
|
|
{
|
|
"entropy": 10.364525890350341,
|
|
"epoch": 0.011038502296008477,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 6.2e-05,
|
|
"loss": 8.957,
|
|
"mean_token_accuracy": 0.07038320675492286,
|
|
"num_tokens": 235879.0,
|
|
"step": 125
|
|
},
|
|
{
|
|
"entropy": 10.272084522247315,
|
|
"epoch": 0.011480042387848817,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 6.450000000000001e-05,
|
|
"loss": 8.8401,
|
|
"mean_token_accuracy": 0.07076714783906937,
|
|
"num_tokens": 244532.0,
|
|
"step": 130
|
|
},
|
|
{
|
|
"entropy": 10.150115776062012,
|
|
"epoch": 0.011921582479689156,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 6.7e-05,
|
|
"loss": 8.7849,
|
|
"mean_token_accuracy": 0.07159631326794624,
|
|
"num_tokens": 254037.0,
|
|
"step": 135
|
|
},
|
|
{
|
|
"entropy": 10.064141464233398,
|
|
"epoch": 0.012363122571529495,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 6.950000000000001e-05,
|
|
"loss": 8.7124,
|
|
"mean_token_accuracy": 0.06714138388633728,
|
|
"num_tokens": 264162.0,
|
|
"step": 140
|
|
},
|
|
{
|
|
"entropy": 9.97827501296997,
|
|
"epoch": 0.012804662663369834,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 7.2e-05,
|
|
"loss": 8.6055,
|
|
"mean_token_accuracy": 0.07109769769012927,
|
|
"num_tokens": 273644.0,
|
|
"step": 145
|
|
},
|
|
{
|
|
"entropy": 9.83043041229248,
|
|
"epoch": 0.013246202755210172,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 7.45e-05,
|
|
"loss": 8.4902,
|
|
"mean_token_accuracy": 0.07540867626667022,
|
|
"num_tokens": 283643.0,
|
|
"step": 150
|
|
},
|
|
{
|
|
"entropy": 9.671627426147461,
|
|
"epoch": 0.013687742847050512,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 7.7e-05,
|
|
"loss": 8.3939,
|
|
"mean_token_accuracy": 0.0741175465285778,
|
|
"num_tokens": 292636.0,
|
|
"step": 155
|
|
},
|
|
{
|
|
"entropy": 9.572625064849854,
|
|
"epoch": 0.01412928293889085,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 7.950000000000001e-05,
|
|
"loss": 8.2828,
|
|
"mean_token_accuracy": 0.07567049115896225,
|
|
"num_tokens": 302059.0,
|
|
"step": 160
|
|
},
|
|
{
|
|
"entropy": 9.38239164352417,
|
|
"epoch": 0.01457082303073119,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 8.2e-05,
|
|
"loss": 8.3316,
|
|
"mean_token_accuracy": 0.07153738178312778,
|
|
"num_tokens": 311995.0,
|
|
"step": 165
|
|
},
|
|
{
|
|
"entropy": 9.255543613433838,
|
|
"epoch": 0.01501236312257153,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 8.450000000000001e-05,
|
|
"loss": 8.2309,
|
|
"mean_token_accuracy": 0.07089664451777936,
|
|
"num_tokens": 322035.0,
|
|
"step": 170
|
|
},
|
|
{
|
|
"entropy": 9.142601108551025,
|
|
"epoch": 0.015453903214411868,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 8.7e-05,
|
|
"loss": 8.1473,
|
|
"mean_token_accuracy": 0.07471434287726879,
|
|
"num_tokens": 330746.0,
|
|
"step": 175
|
|
},
|
|
{
|
|
"entropy": 8.977528285980224,
|
|
"epoch": 0.015895443306252206,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 8.95e-05,
|
|
"loss": 8.1055,
|
|
"mean_token_accuracy": 0.07090946286916733,
|
|
"num_tokens": 339445.0,
|
|
"step": 180
|
|
},
|
|
{
|
|
"entropy": 8.824779510498047,
|
|
"epoch": 0.016336983398092548,
|
|
"grad_norm": 0.76171875,
|
|
"learning_rate": 9.2e-05,
|
|
"loss": 8.1189,
|
|
"mean_token_accuracy": 0.06805617697536945,
|
|
"num_tokens": 349171.0,
|
|
"step": 185
|
|
},
|
|
{
|
|
"entropy": 8.705509662628174,
|
|
"epoch": 0.016778523489932886,
|
|
"grad_norm": 0.68359375,
|
|
"learning_rate": 9.45e-05,
|
|
"loss": 8.0342,
|
|
"mean_token_accuracy": 0.07489757090806962,
|
|
"num_tokens": 358146.0,
|
|
"step": 190
|
|
},
|
|
{
|
|
"entropy": 8.5638991355896,
|
|
"epoch": 0.017220063581773224,
|
|
"grad_norm": 0.7421875,
|
|
"learning_rate": 9.7e-05,
|
|
"loss": 7.9875,
|
|
"mean_token_accuracy": 0.07784983068704605,
|
|
"num_tokens": 366921.0,
|
|
"step": 195
|
|
},
|
|
{
|
|
"entropy": 8.432452964782716,
|
|
"epoch": 0.017661603673613566,
|
|
"grad_norm": 0.7109375,
|
|
"learning_rate": 9.95e-05,
|
|
"loss": 8.01,
|
|
"mean_token_accuracy": 0.07490835711359978,
|
|
"num_tokens": 375993.0,
|
|
"step": 200
|
|
},
|
|
{
|
|
"entropy": 8.46620798110962,
|
|
"epoch": 0.018103143765453904,
|
|
"grad_norm": 0.67578125,
|
|
"learning_rate": 0.000102,
|
|
"loss": 8.1292,
|
|
"mean_token_accuracy": 0.06469435021281242,
|
|
"num_tokens": 385072.0,
|
|
"step": 205
|
|
},
|
|
{
|
|
"entropy": 8.469141292572022,
|
|
"epoch": 0.018544683857294242,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.00010449999999999999,
|
|
"loss": 7.9661,
|
|
"mean_token_accuracy": 0.07081307880580426,
|
|
"num_tokens": 393928.0,
|
|
"step": 210
|
|
},
|
|
{
|
|
"entropy": 8.398229122161865,
|
|
"epoch": 0.01898622394913458,
|
|
"grad_norm": 0.64453125,
|
|
"learning_rate": 0.000107,
|
|
"loss": 8.0343,
|
|
"mean_token_accuracy": 0.07047690935432911,
|
|
"num_tokens": 403245.0,
|
|
"step": 215
|
|
},
|
|
{
|
|
"entropy": 8.3765549659729,
|
|
"epoch": 0.01942776404097492,
|
|
"grad_norm": 0.625,
|
|
"learning_rate": 0.0001095,
|
|
"loss": 7.9137,
|
|
"mean_token_accuracy": 0.08345218449831009,
|
|
"num_tokens": 413192.0,
|
|
"step": 220
|
|
},
|
|
{
|
|
"entropy": 8.40019121170044,
|
|
"epoch": 0.01986930413281526,
|
|
"grad_norm": 0.76953125,
|
|
"learning_rate": 0.000112,
|
|
"loss": 7.9652,
|
|
"mean_token_accuracy": 0.07346240207552909,
|
|
"num_tokens": 422219.0,
|
|
"step": 225
|
|
},
|
|
{
|
|
"entropy": 8.349788379669189,
|
|
"epoch": 0.020310844224655598,
|
|
"grad_norm": 0.7734375,
|
|
"learning_rate": 0.0001145,
|
|
"loss": 7.9015,
|
|
"mean_token_accuracy": 0.08022939898073674,
|
|
"num_tokens": 431654.0,
|
|
"step": 230
|
|
},
|
|
{
|
|
"entropy": 8.380678462982178,
|
|
"epoch": 0.02075238431649594,
|
|
"grad_norm": 0.6328125,
|
|
"learning_rate": 0.00011700000000000001,
|
|
"loss": 7.9143,
|
|
"mean_token_accuracy": 0.08441097363829612,
|
|
"num_tokens": 441817.0,
|
|
"step": 235
|
|
},
|
|
{
|
|
"entropy": 8.25525884628296,
|
|
"epoch": 0.021193924408336277,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.00011949999999999999,
|
|
"loss": 7.8807,
|
|
"mean_token_accuracy": 0.08318600244820118,
|
|
"num_tokens": 450285.0,
|
|
"step": 240
|
|
},
|
|
{
|
|
"entropy": 8.265483093261718,
|
|
"epoch": 0.021635464500176615,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.000122,
|
|
"loss": 7.9189,
|
|
"mean_token_accuracy": 0.07491880282759666,
|
|
"num_tokens": 459726.0,
|
|
"step": 245
|
|
},
|
|
{
|
|
"entropy": 8.335671520233154,
|
|
"epoch": 0.022077004592016954,
|
|
"grad_norm": 0.74609375,
|
|
"learning_rate": 0.0001245,
|
|
"loss": 7.8952,
|
|
"mean_token_accuracy": 0.07705423757433891,
|
|
"num_tokens": 469236.0,
|
|
"step": 250
|
|
},
|
|
{
|
|
"entropy": 8.266505146026612,
|
|
"epoch": 0.022518544683857295,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.000127,
|
|
"loss": 7.9973,
|
|
"mean_token_accuracy": 0.07031807117164135,
|
|
"num_tokens": 478835.0,
|
|
"step": 255
|
|
},
|
|
{
|
|
"entropy": 8.278965950012207,
|
|
"epoch": 0.022960084775697633,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0001295,
|
|
"loss": 7.8611,
|
|
"mean_token_accuracy": 0.07837036736309529,
|
|
"num_tokens": 487748.0,
|
|
"step": 260
|
|
},
|
|
{
|
|
"entropy": 8.250927925109863,
|
|
"epoch": 0.02340162486753797,
|
|
"grad_norm": 0.69140625,
|
|
"learning_rate": 0.000132,
|
|
"loss": 7.976,
|
|
"mean_token_accuracy": 0.07374264337122441,
|
|
"num_tokens": 497733.0,
|
|
"step": 265
|
|
},
|
|
{
|
|
"entropy": 8.279707717895509,
|
|
"epoch": 0.023843164959378313,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00013450000000000002,
|
|
"loss": 7.8168,
|
|
"mean_token_accuracy": 0.0817179311066866,
|
|
"num_tokens": 506351.0,
|
|
"step": 270
|
|
},
|
|
{
|
|
"entropy": 8.150735473632812,
|
|
"epoch": 0.02428470505121865,
|
|
"grad_norm": 0.68359375,
|
|
"learning_rate": 0.00013700000000000002,
|
|
"loss": 7.8459,
|
|
"mean_token_accuracy": 0.08556010201573372,
|
|
"num_tokens": 515865.0,
|
|
"step": 275
|
|
},
|
|
{
|
|
"entropy": 8.268842601776123,
|
|
"epoch": 0.02472624514305899,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0001395,
|
|
"loss": 7.8569,
|
|
"mean_token_accuracy": 0.0806879721581936,
|
|
"num_tokens": 524695.0,
|
|
"step": 280
|
|
},
|
|
{
|
|
"entropy": 8.203614711761475,
|
|
"epoch": 0.025167785234899327,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.00014199999999999998,
|
|
"loss": 7.8531,
|
|
"mean_token_accuracy": 0.07765759006142617,
|
|
"num_tokens": 533896.0,
|
|
"step": 285
|
|
},
|
|
{
|
|
"entropy": 8.160596179962159,
|
|
"epoch": 0.02560932532673967,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0001445,
|
|
"loss": 7.9379,
|
|
"mean_token_accuracy": 0.072020772844553,
|
|
"num_tokens": 543260.0,
|
|
"step": 290
|
|
},
|
|
{
|
|
"entropy": 8.251058101654053,
|
|
"epoch": 0.026050865418580007,
|
|
"grad_norm": 0.7421875,
|
|
"learning_rate": 0.000147,
|
|
"loss": 7.8555,
|
|
"mean_token_accuracy": 0.0810875877737999,
|
|
"num_tokens": 553857.0,
|
|
"step": 295
|
|
},
|
|
{
|
|
"entropy": 8.141295623779296,
|
|
"epoch": 0.026492405510420345,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.0001495,
|
|
"loss": 7.821,
|
|
"mean_token_accuracy": 0.0825580857694149,
|
|
"num_tokens": 562461.0,
|
|
"step": 300
|
|
},
|
|
{
|
|
"entropy": 8.181407356262207,
|
|
"epoch": 0.026933945602260687,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.000152,
|
|
"loss": 7.8487,
|
|
"mean_token_accuracy": 0.07985757477581501,
|
|
"num_tokens": 571863.0,
|
|
"step": 305
|
|
},
|
|
{
|
|
"entropy": 8.115688610076905,
|
|
"epoch": 0.027375485694101025,
|
|
"grad_norm": 0.65234375,
|
|
"learning_rate": 0.00015450000000000001,
|
|
"loss": 7.8567,
|
|
"mean_token_accuracy": 0.07967338487505912,
|
|
"num_tokens": 581063.0,
|
|
"step": 310
|
|
},
|
|
{
|
|
"entropy": 8.166765213012695,
|
|
"epoch": 0.027817025785941363,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.000157,
|
|
"loss": 7.7804,
|
|
"mean_token_accuracy": 0.08055768013000489,
|
|
"num_tokens": 590821.0,
|
|
"step": 315
|
|
},
|
|
{
|
|
"entropy": 8.144050884246827,
|
|
"epoch": 0.0282585658777817,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0001595,
|
|
"loss": 7.754,
|
|
"mean_token_accuracy": 0.0802922174334526,
|
|
"num_tokens": 599701.0,
|
|
"step": 320
|
|
},
|
|
{
|
|
"entropy": 8.107472562789917,
|
|
"epoch": 0.028700105969622042,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000162,
|
|
"loss": 7.7741,
|
|
"mean_token_accuracy": 0.07862499617040157,
|
|
"num_tokens": 608071.0,
|
|
"step": 325
|
|
},
|
|
{
|
|
"entropy": 8.11353440284729,
|
|
"epoch": 0.02914164606146238,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00016450000000000001,
|
|
"loss": 7.8263,
|
|
"mean_token_accuracy": 0.07856386005878449,
|
|
"num_tokens": 616643.0,
|
|
"step": 330
|
|
},
|
|
{
|
|
"entropy": 8.142715454101562,
|
|
"epoch": 0.02958318615330272,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00016700000000000002,
|
|
"loss": 7.8415,
|
|
"mean_token_accuracy": 0.08129560798406602,
|
|
"num_tokens": 626002.0,
|
|
"step": 335
|
|
},
|
|
{
|
|
"entropy": 8.08275752067566,
|
|
"epoch": 0.03002472624514306,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00016950000000000003,
|
|
"loss": 7.7904,
|
|
"mean_token_accuracy": 0.08131296187639236,
|
|
"num_tokens": 636100.0,
|
|
"step": 340
|
|
},
|
|
{
|
|
"entropy": 8.157522010803223,
|
|
"epoch": 0.0304662663369834,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00017199999999999998,
|
|
"loss": 7.8174,
|
|
"mean_token_accuracy": 0.07889350652694702,
|
|
"num_tokens": 645142.0,
|
|
"step": 345
|
|
},
|
|
{
|
|
"entropy": 8.096787357330323,
|
|
"epoch": 0.030907806428823736,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00017449999999999999,
|
|
"loss": 7.7584,
|
|
"mean_token_accuracy": 0.0830284185707569,
|
|
"num_tokens": 654482.0,
|
|
"step": 350
|
|
},
|
|
{
|
|
"entropy": 8.052792024612426,
|
|
"epoch": 0.031349346520664075,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000177,
|
|
"loss": 7.7812,
|
|
"mean_token_accuracy": 0.07971454188227653,
|
|
"num_tokens": 663167.0,
|
|
"step": 355
|
|
},
|
|
{
|
|
"entropy": 8.085110521316528,
|
|
"epoch": 0.03179088661250441,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0001795,
|
|
"loss": 7.8482,
|
|
"mean_token_accuracy": 0.0779881864786148,
|
|
"num_tokens": 672996.0,
|
|
"step": 360
|
|
},
|
|
{
|
|
"entropy": 8.109179019927979,
|
|
"epoch": 0.03223242670434476,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000182,
|
|
"loss": 7.778,
|
|
"mean_token_accuracy": 0.0821885697543621,
|
|
"num_tokens": 681479.0,
|
|
"step": 365
|
|
},
|
|
{
|
|
"entropy": 8.096177530288696,
|
|
"epoch": 0.032673966796185096,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0001845,
|
|
"loss": 7.699,
|
|
"mean_token_accuracy": 0.08528197333216667,
|
|
"num_tokens": 690222.0,
|
|
"step": 370
|
|
},
|
|
{
|
|
"entropy": 8.048606014251709,
|
|
"epoch": 0.033115506888025434,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000187,
|
|
"loss": 7.7136,
|
|
"mean_token_accuracy": 0.08710152879357339,
|
|
"num_tokens": 699143.0,
|
|
"step": 375
|
|
},
|
|
{
|
|
"entropy": 7.981799745559693,
|
|
"epoch": 0.03355704697986577,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0001895,
|
|
"loss": 7.6844,
|
|
"mean_token_accuracy": 0.08963175565004348,
|
|
"num_tokens": 708416.0,
|
|
"step": 380
|
|
},
|
|
{
|
|
"entropy": 8.0686354637146,
|
|
"epoch": 0.03399858707170611,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000192,
|
|
"loss": 7.7816,
|
|
"mean_token_accuracy": 0.08127610832452774,
|
|
"num_tokens": 718140.0,
|
|
"step": 385
|
|
},
|
|
{
|
|
"entropy": 8.01650652885437,
|
|
"epoch": 0.03444012716354645,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0001945,
|
|
"loss": 7.7234,
|
|
"mean_token_accuracy": 0.08251546621322632,
|
|
"num_tokens": 727100.0,
|
|
"step": 390
|
|
},
|
|
{
|
|
"entropy": 7.99934663772583,
|
|
"epoch": 0.034881667255386786,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.00019700000000000002,
|
|
"loss": 7.6959,
|
|
"mean_token_accuracy": 0.0842419758439064,
|
|
"num_tokens": 736383.0,
|
|
"step": 395
|
|
},
|
|
{
|
|
"entropy": 8.089943981170654,
|
|
"epoch": 0.03532320734722713,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00019950000000000002,
|
|
"loss": 7.755,
|
|
"mean_token_accuracy": 0.08859959691762924,
|
|
"num_tokens": 745746.0,
|
|
"step": 400
|
|
},
|
|
{
|
|
"entropy": 8.041479778289794,
|
|
"epoch": 0.03576474743906747,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000202,
|
|
"loss": 7.7302,
|
|
"mean_token_accuracy": 0.08785694614052772,
|
|
"num_tokens": 754276.0,
|
|
"step": 405
|
|
},
|
|
{
|
|
"entropy": 8.044493007659913,
|
|
"epoch": 0.03620628753090781,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00020449999999999998,
|
|
"loss": 7.6459,
|
|
"mean_token_accuracy": 0.08876177445054054,
|
|
"num_tokens": 763044.0,
|
|
"step": 410
|
|
},
|
|
{
|
|
"entropy": 8.00500979423523,
|
|
"epoch": 0.036647827622748146,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.000207,
|
|
"loss": 7.6932,
|
|
"mean_token_accuracy": 0.08604336977005005,
|
|
"num_tokens": 771727.0,
|
|
"step": 415
|
|
},
|
|
{
|
|
"entropy": 8.017408561706542,
|
|
"epoch": 0.037089367714588484,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0002095,
|
|
"loss": 7.6466,
|
|
"mean_token_accuracy": 0.08596126586198807,
|
|
"num_tokens": 781430.0,
|
|
"step": 420
|
|
},
|
|
{
|
|
"entropy": 7.938171768188477,
|
|
"epoch": 0.03753090780642882,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000212,
|
|
"loss": 7.6106,
|
|
"mean_token_accuracy": 0.09112684056162834,
|
|
"num_tokens": 790619.0,
|
|
"step": 425
|
|
},
|
|
{
|
|
"entropy": 8.108117580413818,
|
|
"epoch": 0.03797244789826916,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0002145,
|
|
"loss": 7.7037,
|
|
"mean_token_accuracy": 0.08285126835107803,
|
|
"num_tokens": 800264.0,
|
|
"step": 430
|
|
},
|
|
{
|
|
"entropy": 8.017135334014892,
|
|
"epoch": 0.038413987990109505,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00021700000000000002,
|
|
"loss": 7.6698,
|
|
"mean_token_accuracy": 0.08375026062130927,
|
|
"num_tokens": 810522.0,
|
|
"step": 435
|
|
},
|
|
{
|
|
"entropy": 7.982311105728149,
|
|
"epoch": 0.03885552808194984,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0002195,
|
|
"loss": 7.6376,
|
|
"mean_token_accuracy": 0.08961728811264039,
|
|
"num_tokens": 819361.0,
|
|
"step": 440
|
|
},
|
|
{
|
|
"entropy": 7.917629718780518,
|
|
"epoch": 0.03929706817379018,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.000222,
|
|
"loss": 7.681,
|
|
"mean_token_accuracy": 0.08837661817669869,
|
|
"num_tokens": 829146.0,
|
|
"step": 445
|
|
},
|
|
{
|
|
"entropy": 7.935456418991089,
|
|
"epoch": 0.03973860826563052,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0002245,
|
|
"loss": 7.5834,
|
|
"mean_token_accuracy": 0.09174824506044388,
|
|
"num_tokens": 837315.0,
|
|
"step": 450
|
|
},
|
|
{
|
|
"entropy": 7.988494825363159,
|
|
"epoch": 0.04018014835747086,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00022700000000000002,
|
|
"loss": 7.599,
|
|
"mean_token_accuracy": 0.08744515627622604,
|
|
"num_tokens": 845757.0,
|
|
"step": 455
|
|
},
|
|
{
|
|
"entropy": 7.945766162872315,
|
|
"epoch": 0.040621688449311195,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00022950000000000002,
|
|
"loss": 7.6764,
|
|
"mean_token_accuracy": 0.08117738515138626,
|
|
"num_tokens": 854899.0,
|
|
"step": 460
|
|
},
|
|
{
|
|
"entropy": 7.949225807189942,
|
|
"epoch": 0.041063228541151534,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.00023200000000000003,
|
|
"loss": 7.5731,
|
|
"mean_token_accuracy": 0.09045649319887161,
|
|
"num_tokens": 863839.0,
|
|
"step": 465
|
|
},
|
|
{
|
|
"entropy": 7.848576593399048,
|
|
"epoch": 0.04150476863299188,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00023449999999999998,
|
|
"loss": 7.4955,
|
|
"mean_token_accuracy": 0.09183765053749085,
|
|
"num_tokens": 872249.0,
|
|
"step": 470
|
|
},
|
|
{
|
|
"entropy": 7.883409404754639,
|
|
"epoch": 0.04194630872483222,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000237,
|
|
"loss": 7.6401,
|
|
"mean_token_accuracy": 0.08584671169519424,
|
|
"num_tokens": 881839.0,
|
|
"step": 475
|
|
},
|
|
{
|
|
"entropy": 8.046848773956299,
|
|
"epoch": 0.042387848816672555,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0002395,
|
|
"loss": 7.66,
|
|
"mean_token_accuracy": 0.08414728939533234,
|
|
"num_tokens": 890865.0,
|
|
"step": 480
|
|
},
|
|
{
|
|
"entropy": 7.87333869934082,
|
|
"epoch": 0.04282938890851289,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000242,
|
|
"loss": 7.6421,
|
|
"mean_token_accuracy": 0.08928802534937859,
|
|
"num_tokens": 900858.0,
|
|
"step": 485
|
|
},
|
|
{
|
|
"entropy": 7.997522354125977,
|
|
"epoch": 0.04327092900035323,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0002445,
|
|
"loss": 7.6155,
|
|
"mean_token_accuracy": 0.08748602122068405,
|
|
"num_tokens": 910396.0,
|
|
"step": 490
|
|
},
|
|
{
|
|
"entropy": 7.981202268600464,
|
|
"epoch": 0.04371246909219357,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000247,
|
|
"loss": 7.5676,
|
|
"mean_token_accuracy": 0.09339846298098564,
|
|
"num_tokens": 919532.0,
|
|
"step": 495
|
|
},
|
|
{
|
|
"entropy": 7.883893203735352,
|
|
"epoch": 0.04415400918403391,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0002495,
|
|
"loss": 7.5701,
|
|
"mean_token_accuracy": 0.09045918881893159,
|
|
"num_tokens": 928204.0,
|
|
"step": 500
|
|
},
|
|
{
|
|
"entropy": 7.865892791748047,
|
|
"epoch": 0.04459554927587425,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000252,
|
|
"loss": 7.5447,
|
|
"mean_token_accuracy": 0.09523545205593109,
|
|
"num_tokens": 937457.0,
|
|
"step": 505
|
|
},
|
|
{
|
|
"entropy": 7.911080026626587,
|
|
"epoch": 0.04503708936771459,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0002545,
|
|
"loss": 7.6263,
|
|
"mean_token_accuracy": 0.08180606141686439,
|
|
"num_tokens": 946680.0,
|
|
"step": 510
|
|
},
|
|
{
|
|
"entropy": 7.8668982028961185,
|
|
"epoch": 0.04547862945955493,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.000257,
|
|
"loss": 7.6101,
|
|
"mean_token_accuracy": 0.08870264962315559,
|
|
"num_tokens": 957088.0,
|
|
"step": 515
|
|
},
|
|
{
|
|
"entropy": 7.863427400588989,
|
|
"epoch": 0.045920169551395267,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0002595,
|
|
"loss": 7.5106,
|
|
"mean_token_accuracy": 0.08896929919719695,
|
|
"num_tokens": 966171.0,
|
|
"step": 520
|
|
},
|
|
{
|
|
"entropy": 7.8639161586761475,
|
|
"epoch": 0.046361709643235605,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000262,
|
|
"loss": 7.4888,
|
|
"mean_token_accuracy": 0.09330687001347542,
|
|
"num_tokens": 975038.0,
|
|
"step": 525
|
|
},
|
|
{
|
|
"entropy": 7.818875646591186,
|
|
"epoch": 0.04680324973507594,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.00026450000000000003,
|
|
"loss": 7.5302,
|
|
"mean_token_accuracy": 0.08389112651348114,
|
|
"num_tokens": 985559.0,
|
|
"step": 530
|
|
},
|
|
{
|
|
"entropy": 7.823013496398926,
|
|
"epoch": 0.04724478982691628,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00026700000000000004,
|
|
"loss": 7.5115,
|
|
"mean_token_accuracy": 0.08914603590965271,
|
|
"num_tokens": 994342.0,
|
|
"step": 535
|
|
},
|
|
{
|
|
"entropy": 7.819721317291259,
|
|
"epoch": 0.047686329918756626,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00026950000000000005,
|
|
"loss": 7.4312,
|
|
"mean_token_accuracy": 0.09510840475559235,
|
|
"num_tokens": 1003246.0,
|
|
"step": 540
|
|
},
|
|
{
|
|
"entropy": 7.761527013778687,
|
|
"epoch": 0.048127870010596964,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00027200000000000005,
|
|
"loss": 7.4377,
|
|
"mean_token_accuracy": 0.09536420628428459,
|
|
"num_tokens": 1011949.0,
|
|
"step": 545
|
|
},
|
|
{
|
|
"entropy": 7.710439205169678,
|
|
"epoch": 0.0485694101024373,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0002745,
|
|
"loss": 7.4041,
|
|
"mean_token_accuracy": 0.09840207025408745,
|
|
"num_tokens": 1020117.0,
|
|
"step": 550
|
|
},
|
|
{
|
|
"entropy": 7.790178346633911,
|
|
"epoch": 0.04901095019427764,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000277,
|
|
"loss": 7.5068,
|
|
"mean_token_accuracy": 0.09245016798377037,
|
|
"num_tokens": 1028917.0,
|
|
"step": 555
|
|
},
|
|
{
|
|
"entropy": 7.74592957496643,
|
|
"epoch": 0.04945249028611798,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0002795,
|
|
"loss": 7.4332,
|
|
"mean_token_accuracy": 0.098258488625288,
|
|
"num_tokens": 1037542.0,
|
|
"step": 560
|
|
},
|
|
{
|
|
"entropy": 7.822019767761231,
|
|
"epoch": 0.049894030377958316,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00028199999999999997,
|
|
"loss": 7.4483,
|
|
"mean_token_accuracy": 0.09288977608084678,
|
|
"num_tokens": 1046735.0,
|
|
"step": 565
|
|
},
|
|
{
|
|
"entropy": 7.696895027160645,
|
|
"epoch": 0.050335570469798654,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0002845,
|
|
"loss": 7.4109,
|
|
"mean_token_accuracy": 0.09220683723688125,
|
|
"num_tokens": 1055306.0,
|
|
"step": 570
|
|
},
|
|
{
|
|
"entropy": 7.7618858337402346,
|
|
"epoch": 0.050777110561639,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000287,
|
|
"loss": 7.4532,
|
|
"mean_token_accuracy": 0.10119536891579628,
|
|
"num_tokens": 1064340.0,
|
|
"step": 575
|
|
},
|
|
{
|
|
"entropy": 7.708547353744507,
|
|
"epoch": 0.05121865065347934,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0002895,
|
|
"loss": 7.4029,
|
|
"mean_token_accuracy": 0.09979302212595939,
|
|
"num_tokens": 1074235.0,
|
|
"step": 580
|
|
},
|
|
{
|
|
"entropy": 7.783248233795166,
|
|
"epoch": 0.051660190745319676,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.000292,
|
|
"loss": 7.5004,
|
|
"mean_token_accuracy": 0.09268677458167077,
|
|
"num_tokens": 1083858.0,
|
|
"step": 585
|
|
},
|
|
{
|
|
"entropy": 7.698816013336182,
|
|
"epoch": 0.052101730837160014,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0002945,
|
|
"loss": 7.4726,
|
|
"mean_token_accuracy": 0.09486816674470902,
|
|
"num_tokens": 1093674.0,
|
|
"step": 590
|
|
},
|
|
{
|
|
"entropy": 7.755134534835816,
|
|
"epoch": 0.05254327092900035,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000297,
|
|
"loss": 7.4248,
|
|
"mean_token_accuracy": 0.09409366473555565,
|
|
"num_tokens": 1103166.0,
|
|
"step": 595
|
|
},
|
|
{
|
|
"entropy": 7.736843490600586,
|
|
"epoch": 0.05298481102084069,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0002995,
|
|
"loss": 7.3856,
|
|
"mean_token_accuracy": 0.0958656646311283,
|
|
"num_tokens": 1111458.0,
|
|
"step": 600
|
|
},
|
|
{
|
|
"entropy": 7.718952560424805,
|
|
"epoch": 0.05342635111268103,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000302,
|
|
"loss": 7.408,
|
|
"mean_token_accuracy": 0.09764600619673729,
|
|
"num_tokens": 1120844.0,
|
|
"step": 605
|
|
},
|
|
{
|
|
"entropy": 7.711683893203736,
|
|
"epoch": 0.05386789120452137,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0003045,
|
|
"loss": 7.468,
|
|
"mean_token_accuracy": 0.09388890862464905,
|
|
"num_tokens": 1129948.0,
|
|
"step": 610
|
|
},
|
|
{
|
|
"entropy": 7.6961164474487305,
|
|
"epoch": 0.05430943129636171,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000307,
|
|
"loss": 7.4152,
|
|
"mean_token_accuracy": 0.09394951239228248,
|
|
"num_tokens": 1140142.0,
|
|
"step": 615
|
|
},
|
|
{
|
|
"entropy": 7.727436828613281,
|
|
"epoch": 0.05475097138820205,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0003095,
|
|
"loss": 7.4145,
|
|
"mean_token_accuracy": 0.09343566671013832,
|
|
"num_tokens": 1148428.0,
|
|
"step": 620
|
|
},
|
|
{
|
|
"entropy": 7.692458534240723,
|
|
"epoch": 0.05519251148004239,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000312,
|
|
"loss": 7.4136,
|
|
"mean_token_accuracy": 0.10091176852583886,
|
|
"num_tokens": 1157949.0,
|
|
"step": 625
|
|
},
|
|
{
|
|
"entropy": 7.679105138778686,
|
|
"epoch": 0.055634051571882726,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0003145,
|
|
"loss": 7.3581,
|
|
"mean_token_accuracy": 0.09939868301153183,
|
|
"num_tokens": 1166492.0,
|
|
"step": 630
|
|
},
|
|
{
|
|
"entropy": 7.625578594207764,
|
|
"epoch": 0.056075591663723064,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000317,
|
|
"loss": 7.3769,
|
|
"mean_token_accuracy": 0.09818158000707626,
|
|
"num_tokens": 1176212.0,
|
|
"step": 635
|
|
},
|
|
{
|
|
"entropy": 7.703707695007324,
|
|
"epoch": 0.0565171317555634,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0003195,
|
|
"loss": 7.3927,
|
|
"mean_token_accuracy": 0.09552990198135376,
|
|
"num_tokens": 1185909.0,
|
|
"step": 640
|
|
},
|
|
{
|
|
"entropy": 7.680257797241211,
|
|
"epoch": 0.05695867184740375,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000322,
|
|
"loss": 7.3432,
|
|
"mean_token_accuracy": 0.10017694756388665,
|
|
"num_tokens": 1196370.0,
|
|
"step": 645
|
|
},
|
|
{
|
|
"entropy": 7.708677196502686,
|
|
"epoch": 0.057400211939244085,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00032450000000000003,
|
|
"loss": 7.3425,
|
|
"mean_token_accuracy": 0.09847476780414581,
|
|
"num_tokens": 1205581.0,
|
|
"step": 650
|
|
},
|
|
{
|
|
"entropy": 7.593413877487182,
|
|
"epoch": 0.05784175203108442,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00032700000000000003,
|
|
"loss": 7.354,
|
|
"mean_token_accuracy": 0.0941406324505806,
|
|
"num_tokens": 1214437.0,
|
|
"step": 655
|
|
},
|
|
{
|
|
"entropy": 7.702506065368652,
|
|
"epoch": 0.05828329212292476,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00032950000000000004,
|
|
"loss": 7.411,
|
|
"mean_token_accuracy": 0.095302315056324,
|
|
"num_tokens": 1224690.0,
|
|
"step": 660
|
|
},
|
|
{
|
|
"entropy": 7.615428924560547,
|
|
"epoch": 0.0587248322147651,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00033200000000000005,
|
|
"loss": 7.2941,
|
|
"mean_token_accuracy": 0.09989068508148194,
|
|
"num_tokens": 1234370.0,
|
|
"step": 665
|
|
},
|
|
{
|
|
"entropy": 7.657983112335205,
|
|
"epoch": 0.05916637230660544,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00033450000000000005,
|
|
"loss": 7.3656,
|
|
"mean_token_accuracy": 0.10043076574802398,
|
|
"num_tokens": 1243801.0,
|
|
"step": 670
|
|
},
|
|
{
|
|
"entropy": 7.7026012420654295,
|
|
"epoch": 0.05960791239844578,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000337,
|
|
"loss": 7.4161,
|
|
"mean_token_accuracy": 0.09777282178401947,
|
|
"num_tokens": 1253750.0,
|
|
"step": 675
|
|
},
|
|
{
|
|
"entropy": 7.55789999961853,
|
|
"epoch": 0.06004945249028612,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0003395,
|
|
"loss": 7.3337,
|
|
"mean_token_accuracy": 0.09737052693963051,
|
|
"num_tokens": 1262593.0,
|
|
"step": 680
|
|
},
|
|
{
|
|
"entropy": 7.5179671287536625,
|
|
"epoch": 0.06049099258212646,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000342,
|
|
"loss": 7.2582,
|
|
"mean_token_accuracy": 0.10692062303423881,
|
|
"num_tokens": 1271919.0,
|
|
"step": 685
|
|
},
|
|
{
|
|
"entropy": 7.656077432632446,
|
|
"epoch": 0.0609325326739668,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00034449999999999997,
|
|
"loss": 7.2333,
|
|
"mean_token_accuracy": 0.09819802343845367,
|
|
"num_tokens": 1281211.0,
|
|
"step": 690
|
|
},
|
|
{
|
|
"entropy": 7.640378093719482,
|
|
"epoch": 0.061374072765807135,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000347,
|
|
"loss": 7.266,
|
|
"mean_token_accuracy": 0.1042046993970871,
|
|
"num_tokens": 1290030.0,
|
|
"step": 695
|
|
},
|
|
{
|
|
"entropy": 7.5324629783630375,
|
|
"epoch": 0.06181561285764747,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0003495,
|
|
"loss": 7.3256,
|
|
"mean_token_accuracy": 0.09880118295550347,
|
|
"num_tokens": 1299182.0,
|
|
"step": 700
|
|
},
|
|
{
|
|
"entropy": 7.511147689819336,
|
|
"epoch": 0.06225715294948781,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000352,
|
|
"loss": 7.1888,
|
|
"mean_token_accuracy": 0.11093291938304901,
|
|
"num_tokens": 1307807.0,
|
|
"step": 705
|
|
},
|
|
{
|
|
"entropy": 7.603596162796021,
|
|
"epoch": 0.06269869304132815,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0003545,
|
|
"loss": 7.2998,
|
|
"mean_token_accuracy": 0.09913515821099281,
|
|
"num_tokens": 1317213.0,
|
|
"step": 710
|
|
},
|
|
{
|
|
"entropy": 7.583738040924072,
|
|
"epoch": 0.0631402331331685,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000357,
|
|
"loss": 7.2939,
|
|
"mean_token_accuracy": 0.10248328670859337,
|
|
"num_tokens": 1326712.0,
|
|
"step": 715
|
|
},
|
|
{
|
|
"entropy": 7.438777256011963,
|
|
"epoch": 0.06358177322500883,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0003595,
|
|
"loss": 7.1652,
|
|
"mean_token_accuracy": 0.10802278816699981,
|
|
"num_tokens": 1335197.0,
|
|
"step": 720
|
|
},
|
|
{
|
|
"entropy": 7.493983316421509,
|
|
"epoch": 0.06402331331684917,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000362,
|
|
"loss": 7.2128,
|
|
"mean_token_accuracy": 0.10637593865394593,
|
|
"num_tokens": 1345184.0,
|
|
"step": 725
|
|
},
|
|
{
|
|
"entropy": 7.524926710128784,
|
|
"epoch": 0.06446485340868952,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0003645,
|
|
"loss": 7.1743,
|
|
"mean_token_accuracy": 0.10707266703248024,
|
|
"num_tokens": 1354035.0,
|
|
"step": 730
|
|
},
|
|
{
|
|
"entropy": 7.510273838043213,
|
|
"epoch": 0.06490639350052985,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000367,
|
|
"loss": 7.2745,
|
|
"mean_token_accuracy": 0.10252953544259072,
|
|
"num_tokens": 1363694.0,
|
|
"step": 735
|
|
},
|
|
{
|
|
"entropy": 7.540264368057251,
|
|
"epoch": 0.06534793359237019,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0003695,
|
|
"loss": 7.2861,
|
|
"mean_token_accuracy": 0.10127113163471221,
|
|
"num_tokens": 1373213.0,
|
|
"step": 740
|
|
},
|
|
{
|
|
"entropy": 7.644721269607544,
|
|
"epoch": 0.06578947368421052,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000372,
|
|
"loss": 7.3536,
|
|
"mean_token_accuracy": 0.09904789999127388,
|
|
"num_tokens": 1382583.0,
|
|
"step": 745
|
|
},
|
|
{
|
|
"entropy": 7.567507886886597,
|
|
"epoch": 0.06623101377605087,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0003745,
|
|
"loss": 7.2901,
|
|
"mean_token_accuracy": 0.10179097279906273,
|
|
"num_tokens": 1393179.0,
|
|
"step": 750
|
|
},
|
|
{
|
|
"entropy": 7.4339879035949705,
|
|
"epoch": 0.0666725538678912,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000377,
|
|
"loss": 7.2578,
|
|
"mean_token_accuracy": 0.10336068943142891,
|
|
"num_tokens": 1402710.0,
|
|
"step": 755
|
|
},
|
|
{
|
|
"entropy": 7.391937112808227,
|
|
"epoch": 0.06711409395973154,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0003795,
|
|
"loss": 7.1319,
|
|
"mean_token_accuracy": 0.10740135014057159,
|
|
"num_tokens": 1411951.0,
|
|
"step": 760
|
|
},
|
|
{
|
|
"entropy": 7.566329479217529,
|
|
"epoch": 0.06755563405157189,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000382,
|
|
"loss": 7.228,
|
|
"mean_token_accuracy": 0.10449767932295799,
|
|
"num_tokens": 1420987.0,
|
|
"step": 765
|
|
},
|
|
{
|
|
"entropy": 7.435188674926758,
|
|
"epoch": 0.06799717414341222,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0003845,
|
|
"loss": 7.2097,
|
|
"mean_token_accuracy": 0.10870371311903,
|
|
"num_tokens": 1429816.0,
|
|
"step": 770
|
|
},
|
|
{
|
|
"entropy": 7.429537582397461,
|
|
"epoch": 0.06843871423525257,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00038700000000000003,
|
|
"loss": 7.2684,
|
|
"mean_token_accuracy": 0.10217438042163848,
|
|
"num_tokens": 1439734.0,
|
|
"step": 775
|
|
},
|
|
{
|
|
"entropy": 7.496665811538696,
|
|
"epoch": 0.0688802543270929,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00038950000000000003,
|
|
"loss": 7.1856,
|
|
"mean_token_accuracy": 0.10607536807656288,
|
|
"num_tokens": 1448666.0,
|
|
"step": 780
|
|
},
|
|
{
|
|
"entropy": 7.520268392562866,
|
|
"epoch": 0.06932179441893324,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00039200000000000004,
|
|
"loss": 7.2336,
|
|
"mean_token_accuracy": 0.10618305131793022,
|
|
"num_tokens": 1458754.0,
|
|
"step": 785
|
|
},
|
|
{
|
|
"entropy": 7.4070884704589846,
|
|
"epoch": 0.06976333451077357,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.00039450000000000005,
|
|
"loss": 7.0997,
|
|
"mean_token_accuracy": 0.11265210434794426,
|
|
"num_tokens": 1468409.0,
|
|
"step": 790
|
|
},
|
|
{
|
|
"entropy": 7.468406248092651,
|
|
"epoch": 0.07020487460261392,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00039700000000000005,
|
|
"loss": 7.1527,
|
|
"mean_token_accuracy": 0.10318700969219208,
|
|
"num_tokens": 1477133.0,
|
|
"step": 795
|
|
},
|
|
{
|
|
"entropy": 7.417441082000733,
|
|
"epoch": 0.07064641469445426,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0003995,
|
|
"loss": 7.2323,
|
|
"mean_token_accuracy": 0.1052546851336956,
|
|
"num_tokens": 1487215.0,
|
|
"step": 800
|
|
},
|
|
{
|
|
"entropy": 7.510851049423218,
|
|
"epoch": 0.0710879547862946,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000402,
|
|
"loss": 7.2308,
|
|
"mean_token_accuracy": 0.10290714055299759,
|
|
"num_tokens": 1496545.0,
|
|
"step": 805
|
|
},
|
|
{
|
|
"entropy": 7.4078692436218265,
|
|
"epoch": 0.07152949487813494,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004045,
|
|
"loss": 7.1474,
|
|
"mean_token_accuracy": 0.11182119399309158,
|
|
"num_tokens": 1505189.0,
|
|
"step": 810
|
|
},
|
|
{
|
|
"entropy": 7.373153114318848,
|
|
"epoch": 0.07197103496997527,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00040699999999999997,
|
|
"loss": 7.1244,
|
|
"mean_token_accuracy": 0.11001503765583039,
|
|
"num_tokens": 1513398.0,
|
|
"step": 815
|
|
},
|
|
{
|
|
"entropy": 7.427165269851685,
|
|
"epoch": 0.07241257506181561,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004095,
|
|
"loss": 7.1308,
|
|
"mean_token_accuracy": 0.10737015083432197,
|
|
"num_tokens": 1522712.0,
|
|
"step": 820
|
|
},
|
|
{
|
|
"entropy": 7.457416105270386,
|
|
"epoch": 0.07285411515365595,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000412,
|
|
"loss": 7.1819,
|
|
"mean_token_accuracy": 0.10398382544517518,
|
|
"num_tokens": 1532487.0,
|
|
"step": 825
|
|
},
|
|
{
|
|
"entropy": 7.382591438293457,
|
|
"epoch": 0.07329565524549629,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004145,
|
|
"loss": 7.1938,
|
|
"mean_token_accuracy": 0.10898119583725929,
|
|
"num_tokens": 1541888.0,
|
|
"step": 830
|
|
},
|
|
{
|
|
"entropy": 7.489791011810302,
|
|
"epoch": 0.07373719533733664,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000417,
|
|
"loss": 7.2249,
|
|
"mean_token_accuracy": 0.10024029538035392,
|
|
"num_tokens": 1552170.0,
|
|
"step": 835
|
|
},
|
|
{
|
|
"entropy": 7.418872737884522,
|
|
"epoch": 0.07417873542917697,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004195,
|
|
"loss": 7.1548,
|
|
"mean_token_accuracy": 0.10629647746682166,
|
|
"num_tokens": 1562012.0,
|
|
"step": 840
|
|
},
|
|
{
|
|
"entropy": 7.322513008117676,
|
|
"epoch": 0.07462027552101731,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000422,
|
|
"loss": 7.0843,
|
|
"mean_token_accuracy": 0.10927556678652764,
|
|
"num_tokens": 1570150.0,
|
|
"step": 845
|
|
},
|
|
{
|
|
"entropy": 7.437068700790405,
|
|
"epoch": 0.07506181561285764,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004245,
|
|
"loss": 7.1004,
|
|
"mean_token_accuracy": 0.11221965476870537,
|
|
"num_tokens": 1579627.0,
|
|
"step": 850
|
|
},
|
|
{
|
|
"entropy": 7.385348701477051,
|
|
"epoch": 0.07550335570469799,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000427,
|
|
"loss": 7.2112,
|
|
"mean_token_accuracy": 0.1068318523466587,
|
|
"num_tokens": 1590059.0,
|
|
"step": 855
|
|
},
|
|
{
|
|
"entropy": 7.306034994125366,
|
|
"epoch": 0.07594489579653832,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004295,
|
|
"loss": 7.0794,
|
|
"mean_token_accuracy": 0.10881896913051606,
|
|
"num_tokens": 1599656.0,
|
|
"step": 860
|
|
},
|
|
{
|
|
"entropy": 7.4415796279907225,
|
|
"epoch": 0.07638643588837866,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000432,
|
|
"loss": 7.0527,
|
|
"mean_token_accuracy": 0.10823039263486862,
|
|
"num_tokens": 1608708.0,
|
|
"step": 865
|
|
},
|
|
{
|
|
"entropy": 7.342567300796508,
|
|
"epoch": 0.07682797598021901,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004345,
|
|
"loss": 7.1278,
|
|
"mean_token_accuracy": 0.10357554033398628,
|
|
"num_tokens": 1617467.0,
|
|
"step": 870
|
|
},
|
|
{
|
|
"entropy": 7.296669960021973,
|
|
"epoch": 0.07726951607205934,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000437,
|
|
"loss": 7.0572,
|
|
"mean_token_accuracy": 0.10800771564245223,
|
|
"num_tokens": 1626656.0,
|
|
"step": 875
|
|
},
|
|
{
|
|
"entropy": 7.441175413131714,
|
|
"epoch": 0.07771105616389969,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004395,
|
|
"loss": 7.1039,
|
|
"mean_token_accuracy": 0.10841156914830208,
|
|
"num_tokens": 1635769.0,
|
|
"step": 880
|
|
},
|
|
{
|
|
"entropy": 7.383777809143067,
|
|
"epoch": 0.07815259625574002,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000442,
|
|
"loss": 7.2128,
|
|
"mean_token_accuracy": 0.10014851167798042,
|
|
"num_tokens": 1645237.0,
|
|
"step": 885
|
|
},
|
|
{
|
|
"entropy": 7.236069011688232,
|
|
"epoch": 0.07859413634758036,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004445,
|
|
"loss": 7.0403,
|
|
"mean_token_accuracy": 0.11353820711374282,
|
|
"num_tokens": 1654266.0,
|
|
"step": 890
|
|
},
|
|
{
|
|
"entropy": 7.362179565429687,
|
|
"epoch": 0.0790356764394207,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000447,
|
|
"loss": 7.1451,
|
|
"mean_token_accuracy": 0.1029183603823185,
|
|
"num_tokens": 1663409.0,
|
|
"step": 895
|
|
},
|
|
{
|
|
"entropy": 7.379905128479004,
|
|
"epoch": 0.07947721653126104,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00044950000000000003,
|
|
"loss": 7.092,
|
|
"mean_token_accuracy": 0.10835795775055886,
|
|
"num_tokens": 1672664.0,
|
|
"step": 900
|
|
},
|
|
{
|
|
"entropy": 7.292973804473877,
|
|
"epoch": 0.07991875662310138,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00045200000000000004,
|
|
"loss": 7.2004,
|
|
"mean_token_accuracy": 0.10515450984239579,
|
|
"num_tokens": 1682656.0,
|
|
"step": 905
|
|
},
|
|
{
|
|
"entropy": 7.3837714195251465,
|
|
"epoch": 0.08036029671494171,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00045450000000000004,
|
|
"loss": 7.0557,
|
|
"mean_token_accuracy": 0.10702643021941186,
|
|
"num_tokens": 1692155.0,
|
|
"step": 910
|
|
},
|
|
{
|
|
"entropy": 7.325821781158448,
|
|
"epoch": 0.08080183680678206,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00045700000000000005,
|
|
"loss": 7.0631,
|
|
"mean_token_accuracy": 0.11022284105420113,
|
|
"num_tokens": 1701347.0,
|
|
"step": 915
|
|
},
|
|
{
|
|
"entropy": 7.298824167251587,
|
|
"epoch": 0.08124337689862239,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00045950000000000006,
|
|
"loss": 7.0693,
|
|
"mean_token_accuracy": 0.11432591453194618,
|
|
"num_tokens": 1710110.0,
|
|
"step": 920
|
|
},
|
|
{
|
|
"entropy": 7.375689554214477,
|
|
"epoch": 0.08168491699046274,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.000462,
|
|
"loss": 7.0914,
|
|
"mean_token_accuracy": 0.10915563106536866,
|
|
"num_tokens": 1718880.0,
|
|
"step": 925
|
|
},
|
|
{
|
|
"entropy": 7.270999765396118,
|
|
"epoch": 0.08212645708230307,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004645,
|
|
"loss": 7.0282,
|
|
"mean_token_accuracy": 0.11133510172367096,
|
|
"num_tokens": 1729164.0,
|
|
"step": 930
|
|
},
|
|
{
|
|
"entropy": 7.216585683822632,
|
|
"epoch": 0.08256799717414341,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000467,
|
|
"loss": 7.0806,
|
|
"mean_token_accuracy": 0.11017340123653412,
|
|
"num_tokens": 1738407.0,
|
|
"step": 935
|
|
},
|
|
{
|
|
"entropy": 7.264530849456787,
|
|
"epoch": 0.08300953726598376,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004695,
|
|
"loss": 7.0866,
|
|
"mean_token_accuracy": 0.11002494916319847,
|
|
"num_tokens": 1747972.0,
|
|
"step": 940
|
|
},
|
|
{
|
|
"entropy": 7.352582788467407,
|
|
"epoch": 0.08345107735782409,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000472,
|
|
"loss": 7.0913,
|
|
"mean_token_accuracy": 0.1055463895201683,
|
|
"num_tokens": 1757597.0,
|
|
"step": 945
|
|
},
|
|
{
|
|
"entropy": 7.296703195571899,
|
|
"epoch": 0.08389261744966443,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004745,
|
|
"loss": 7.0832,
|
|
"mean_token_accuracy": 0.10835389271378518,
|
|
"num_tokens": 1766905.0,
|
|
"step": 950
|
|
},
|
|
{
|
|
"entropy": 7.316994667053223,
|
|
"epoch": 0.08433415754150476,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.000477,
|
|
"loss": 7.0214,
|
|
"mean_token_accuracy": 0.11587357893586159,
|
|
"num_tokens": 1776483.0,
|
|
"step": 955
|
|
},
|
|
{
|
|
"entropy": 7.267442893981934,
|
|
"epoch": 0.08477569763334511,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004795,
|
|
"loss": 7.1195,
|
|
"mean_token_accuracy": 0.10487466976046562,
|
|
"num_tokens": 1787050.0,
|
|
"step": 960
|
|
},
|
|
{
|
|
"entropy": 7.335643339157104,
|
|
"epoch": 0.08521723772518544,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000482,
|
|
"loss": 7.0617,
|
|
"mean_token_accuracy": 0.11197662577033043,
|
|
"num_tokens": 1796972.0,
|
|
"step": 965
|
|
},
|
|
{
|
|
"entropy": 7.191023874282837,
|
|
"epoch": 0.08565877781702579,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004845,
|
|
"loss": 6.9551,
|
|
"mean_token_accuracy": 0.1202144518494606,
|
|
"num_tokens": 1804779.0,
|
|
"step": 970
|
|
},
|
|
{
|
|
"entropy": 7.229815483093262,
|
|
"epoch": 0.08610031790886613,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000487,
|
|
"loss": 7.001,
|
|
"mean_token_accuracy": 0.1176213040947914,
|
|
"num_tokens": 1813373.0,
|
|
"step": 975
|
|
},
|
|
{
|
|
"entropy": 7.1644312858581545,
|
|
"epoch": 0.08654185800070646,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004895,
|
|
"loss": 6.8935,
|
|
"mean_token_accuracy": 0.12180616855621337,
|
|
"num_tokens": 1822042.0,
|
|
"step": 980
|
|
},
|
|
{
|
|
"entropy": 7.214623975753784,
|
|
"epoch": 0.08698339809254681,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000492,
|
|
"loss": 7.0036,
|
|
"mean_token_accuracy": 0.11261652708053589,
|
|
"num_tokens": 1831695.0,
|
|
"step": 985
|
|
},
|
|
{
|
|
"entropy": 7.246127367019653,
|
|
"epoch": 0.08742493818438714,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004945,
|
|
"loss": 7.0218,
|
|
"mean_token_accuracy": 0.11053162068128586,
|
|
"num_tokens": 1841035.0,
|
|
"step": 990
|
|
},
|
|
{
|
|
"entropy": 7.273807048797607,
|
|
"epoch": 0.08786647827622748,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000497,
|
|
"loss": 7.0012,
|
|
"mean_token_accuracy": 0.11223224252462387,
|
|
"num_tokens": 1849808.0,
|
|
"step": 995
|
|
},
|
|
{
|
|
"entropy": 7.180046844482422,
|
|
"epoch": 0.08830801836806781,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004995,
|
|
"loss": 7.0557,
|
|
"mean_token_accuracy": 0.11089910492300988,
|
|
"num_tokens": 1859583.0,
|
|
"step": 1000
|
|
},
|
|
{
|
|
"entropy": 7.183477878570557,
|
|
"epoch": 0.08874955845990816,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.000499999998589561,
|
|
"loss": 6.9748,
|
|
"mean_token_accuracy": 0.11256436705589294,
|
|
"num_tokens": 1869060.0,
|
|
"step": 1005
|
|
},
|
|
{
|
|
"entropy": 7.321033000946045,
|
|
"epoch": 0.0891910985517485,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999999928596523,
|
|
"loss": 7.0264,
|
|
"mean_token_accuracy": 0.11636429131031037,
|
|
"num_tokens": 1878963.0,
|
|
"step": 1010
|
|
},
|
|
{
|
|
"entropy": 7.146453619003296,
|
|
"epoch": 0.08963263864358884,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999999827221219,
|
|
"loss": 6.9548,
|
|
"mean_token_accuracy": 0.11412466391921043,
|
|
"num_tokens": 1888681.0,
|
|
"step": 1015
|
|
},
|
|
{
|
|
"entropy": 7.116451168060303,
|
|
"epoch": 0.09007417873542918,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999999681769696,
|
|
"loss": 6.9771,
|
|
"mean_token_accuracy": 0.11544483378529549,
|
|
"num_tokens": 1897293.0,
|
|
"step": 1020
|
|
},
|
|
{
|
|
"entropy": 7.188655519485474,
|
|
"epoch": 0.09051571882726951,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000499999949224196,
|
|
"loss": 7.0143,
|
|
"mean_token_accuracy": 0.11129978001117706,
|
|
"num_tokens": 1907243.0,
|
|
"step": 1025
|
|
},
|
|
{
|
|
"entropy": 7.212197875976562,
|
|
"epoch": 0.09095725891910986,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999999258638013,
|
|
"loss": 6.9686,
|
|
"mean_token_accuracy": 0.1180865965783596,
|
|
"num_tokens": 1916979.0,
|
|
"step": 1030
|
|
},
|
|
{
|
|
"entropy": 7.376511192321777,
|
|
"epoch": 0.09139879901095019,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004999998980957861,
|
|
"loss": 7.0302,
|
|
"mean_token_accuracy": 0.1100818432867527,
|
|
"num_tokens": 1926151.0,
|
|
"step": 1035
|
|
},
|
|
{
|
|
"entropy": 7.1434496402740475,
|
|
"epoch": 0.09184033910279053,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999998659201508,
|
|
"loss": 7.0049,
|
|
"mean_token_accuracy": 0.11358301714062691,
|
|
"num_tokens": 1935847.0,
|
|
"step": 1040
|
|
},
|
|
{
|
|
"entropy": 7.185492038726807,
|
|
"epoch": 0.09228187919463088,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999998293368961,
|
|
"loss": 6.9572,
|
|
"mean_token_accuracy": 0.12387590035796166,
|
|
"num_tokens": 1945114.0,
|
|
"step": 1045
|
|
},
|
|
{
|
|
"entropy": 7.154706048965454,
|
|
"epoch": 0.09272341928647121,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004999997883460227,
|
|
"loss": 6.9569,
|
|
"mean_token_accuracy": 0.11779660508036613,
|
|
"num_tokens": 1954924.0,
|
|
"step": 1050
|
|
},
|
|
{
|
|
"entropy": 7.140568017959595,
|
|
"epoch": 0.09316495937831155,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999997429475314,
|
|
"loss": 6.9131,
|
|
"mean_token_accuracy": 0.11738472655415536,
|
|
"num_tokens": 1963946.0,
|
|
"step": 1055
|
|
},
|
|
{
|
|
"entropy": 7.117366647720337,
|
|
"epoch": 0.09360649947015189,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999996931414232,
|
|
"loss": 6.927,
|
|
"mean_token_accuracy": 0.12068335115909576,
|
|
"num_tokens": 1973780.0,
|
|
"step": 1060
|
|
},
|
|
{
|
|
"entropy": 7.151812124252319,
|
|
"epoch": 0.09404803956199223,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999996389276988,
|
|
"loss": 6.9555,
|
|
"mean_token_accuracy": 0.11808405518531799,
|
|
"num_tokens": 1983561.0,
|
|
"step": 1065
|
|
},
|
|
{
|
|
"entropy": 7.215504932403564,
|
|
"epoch": 0.09448957965383256,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999995803063596,
|
|
"loss": 6.9481,
|
|
"mean_token_accuracy": 0.11382859721779823,
|
|
"num_tokens": 1993257.0,
|
|
"step": 1070
|
|
},
|
|
{
|
|
"entropy": 6.997649192810059,
|
|
"epoch": 0.0949311197456729,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004999995172774065,
|
|
"loss": 6.8483,
|
|
"mean_token_accuracy": 0.12370764091610909,
|
|
"num_tokens": 2003391.0,
|
|
"step": 1075
|
|
},
|
|
{
|
|
"entropy": 7.239151048660278,
|
|
"epoch": 0.09537265983751325,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999994498408408,
|
|
"loss": 6.9732,
|
|
"mean_token_accuracy": 0.11102722734212875,
|
|
"num_tokens": 2012004.0,
|
|
"step": 1080
|
|
},
|
|
{
|
|
"entropy": 7.1418920993804935,
|
|
"epoch": 0.09581419992935358,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004999993779966639,
|
|
"loss": 6.9566,
|
|
"mean_token_accuracy": 0.11490248888731003,
|
|
"num_tokens": 2022033.0,
|
|
"step": 1085
|
|
},
|
|
{
|
|
"entropy": 7.171054220199585,
|
|
"epoch": 0.09625574002119393,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999993017448771,
|
|
"loss": 6.9893,
|
|
"mean_token_accuracy": 0.11266493499279022,
|
|
"num_tokens": 2031628.0,
|
|
"step": 1090
|
|
},
|
|
{
|
|
"entropy": 7.1874267578125,
|
|
"epoch": 0.09669728011303426,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004999992210854821,
|
|
"loss": 6.9058,
|
|
"mean_token_accuracy": 0.1091111071407795,
|
|
"num_tokens": 2040339.0,
|
|
"step": 1095
|
|
},
|
|
{
|
|
"entropy": 7.08800573348999,
|
|
"epoch": 0.0971388202048746,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999991360184801,
|
|
"loss": 6.9265,
|
|
"mean_token_accuracy": 0.11344177350401878,
|
|
"num_tokens": 2050099.0,
|
|
"step": 1100
|
|
},
|
|
{
|
|
"entropy": 7.174203872680664,
|
|
"epoch": 0.09758036029671494,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999990465438731,
|
|
"loss": 6.9676,
|
|
"mean_token_accuracy": 0.11609438061714172,
|
|
"num_tokens": 2059572.0,
|
|
"step": 1105
|
|
},
|
|
{
|
|
"entropy": 7.087515354156494,
|
|
"epoch": 0.09802190038855528,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999989526616628,
|
|
"loss": 6.9018,
|
|
"mean_token_accuracy": 0.12604590877890587,
|
|
"num_tokens": 2068449.0,
|
|
"step": 1110
|
|
},
|
|
{
|
|
"entropy": 7.112388658523559,
|
|
"epoch": 0.09846344048039563,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999988543718509,
|
|
"loss": 6.8388,
|
|
"mean_token_accuracy": 0.11249179318547249,
|
|
"num_tokens": 2077508.0,
|
|
"step": 1115
|
|
},
|
|
{
|
|
"entropy": 7.071923446655274,
|
|
"epoch": 0.09890498057223596,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004999987516744394,
|
|
"loss": 6.8896,
|
|
"mean_token_accuracy": 0.12044401988387107,
|
|
"num_tokens": 2087458.0,
|
|
"step": 1120
|
|
},
|
|
{
|
|
"entropy": 7.085772848129272,
|
|
"epoch": 0.0993465206640763,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999986445694303,
|
|
"loss": 7.0003,
|
|
"mean_token_accuracy": 0.11157744228839875,
|
|
"num_tokens": 2096966.0,
|
|
"step": 1125
|
|
},
|
|
{
|
|
"entropy": 7.1603165626525875,
|
|
"epoch": 0.09978806075591663,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999985330568258,
|
|
"loss": 6.984,
|
|
"mean_token_accuracy": 0.11366051360964775,
|
|
"num_tokens": 2106528.0,
|
|
"step": 1130
|
|
},
|
|
{
|
|
"entropy": 7.182817792892456,
|
|
"epoch": 0.10022960084775698,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999984171366278,
|
|
"loss": 6.9151,
|
|
"mean_token_accuracy": 0.12007406130433082,
|
|
"num_tokens": 2114582.0,
|
|
"step": 1135
|
|
},
|
|
{
|
|
"entropy": 7.036507177352905,
|
|
"epoch": 0.10067114093959731,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.000499998296808839,
|
|
"loss": 6.9229,
|
|
"mean_token_accuracy": 0.11831944435834885,
|
|
"num_tokens": 2125675.0,
|
|
"step": 1140
|
|
},
|
|
{
|
|
"entropy": 7.13743371963501,
|
|
"epoch": 0.10111268103143765,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999981720734615,
|
|
"loss": 6.9518,
|
|
"mean_token_accuracy": 0.11637505069375038,
|
|
"num_tokens": 2134696.0,
|
|
"step": 1145
|
|
},
|
|
{
|
|
"entropy": 7.1318199157714846,
|
|
"epoch": 0.101554221123278,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004999980429304977,
|
|
"loss": 6.8227,
|
|
"mean_token_accuracy": 0.11497059166431427,
|
|
"num_tokens": 2144110.0,
|
|
"step": 1150
|
|
},
|
|
{
|
|
"entropy": 7.095803737640381,
|
|
"epoch": 0.10199576121511833,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004999979093799502,
|
|
"loss": 6.8998,
|
|
"mean_token_accuracy": 0.11766083538532257,
|
|
"num_tokens": 2153059.0,
|
|
"step": 1155
|
|
},
|
|
{
|
|
"entropy": 7.164034080505371,
|
|
"epoch": 0.10243730130695868,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999977714218217,
|
|
"loss": 6.9923,
|
|
"mean_token_accuracy": 0.11412862613797188,
|
|
"num_tokens": 2162322.0,
|
|
"step": 1160
|
|
},
|
|
{
|
|
"entropy": 7.045686197280884,
|
|
"epoch": 0.102878841398799,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999976290561147,
|
|
"loss": 6.8552,
|
|
"mean_token_accuracy": 0.11943022832274437,
|
|
"num_tokens": 2170707.0,
|
|
"step": 1165
|
|
},
|
|
{
|
|
"entropy": 7.092855930328369,
|
|
"epoch": 0.10332038149063935,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999974822828322,
|
|
"loss": 6.8983,
|
|
"mean_token_accuracy": 0.11820499077439309,
|
|
"num_tokens": 2180134.0,
|
|
"step": 1170
|
|
},
|
|
{
|
|
"entropy": 7.0811927318573,
|
|
"epoch": 0.10376192158247968,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000499997331101977,
|
|
"loss": 6.8482,
|
|
"mean_token_accuracy": 0.11699439510703087,
|
|
"num_tokens": 2188277.0,
|
|
"step": 1175
|
|
},
|
|
{
|
|
"entropy": 7.0605254650115965,
|
|
"epoch": 0.10420346167432003,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000499997175513552,
|
|
"loss": 6.8229,
|
|
"mean_token_accuracy": 0.12035220712423325,
|
|
"num_tokens": 2197380.0,
|
|
"step": 1180
|
|
},
|
|
{
|
|
"entropy": 7.096225452423096,
|
|
"epoch": 0.10464500176616037,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004999970155175603,
|
|
"loss": 6.9042,
|
|
"mean_token_accuracy": 0.1133291132748127,
|
|
"num_tokens": 2207183.0,
|
|
"step": 1185
|
|
},
|
|
{
|
|
"entropy": 7.040783309936524,
|
|
"epoch": 0.1050865418580007,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.000499996851114005,
|
|
"loss": 6.8536,
|
|
"mean_token_accuracy": 0.11778900921344757,
|
|
"num_tokens": 2216686.0,
|
|
"step": 1190
|
|
},
|
|
{
|
|
"entropy": 7.115582895278931,
|
|
"epoch": 0.10552808194984105,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999966823028894,
|
|
"loss": 6.9219,
|
|
"mean_token_accuracy": 0.11533070355653763,
|
|
"num_tokens": 2226060.0,
|
|
"step": 1195
|
|
},
|
|
{
|
|
"entropy": 7.038763046264648,
|
|
"epoch": 0.10596962204168138,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999965090842168,
|
|
"loss": 6.8396,
|
|
"mean_token_accuracy": 0.12296478524804115,
|
|
"num_tokens": 2235941.0,
|
|
"step": 1200
|
|
},
|
|
{
|
|
"entropy": 6.94191164970398,
|
|
"epoch": 0.10641116213352173,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004999963314579905,
|
|
"loss": 6.8194,
|
|
"mean_token_accuracy": 0.12413551509380341,
|
|
"num_tokens": 2245026.0,
|
|
"step": 1205
|
|
},
|
|
{
|
|
"entropy": 7.188455581665039,
|
|
"epoch": 0.10685270222536206,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999961494242139,
|
|
"loss": 6.9298,
|
|
"mean_token_accuracy": 0.11509394273161888,
|
|
"num_tokens": 2254261.0,
|
|
"step": 1210
|
|
},
|
|
{
|
|
"entropy": 7.011233329772949,
|
|
"epoch": 0.1072942423172024,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999959629828908,
|
|
"loss": 6.8824,
|
|
"mean_token_accuracy": 0.11670115143060684,
|
|
"num_tokens": 2263025.0,
|
|
"step": 1215
|
|
},
|
|
{
|
|
"entropy": 7.086313724517822,
|
|
"epoch": 0.10773578240904275,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004999957721340248,
|
|
"loss": 6.8529,
|
|
"mean_token_accuracy": 0.1207992248237133,
|
|
"num_tokens": 2271970.0,
|
|
"step": 1220
|
|
},
|
|
{
|
|
"entropy": 7.134052801132202,
|
|
"epoch": 0.10817732250088308,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004999955768776195,
|
|
"loss": 6.8253,
|
|
"mean_token_accuracy": 0.12035808637738228,
|
|
"num_tokens": 2281624.0,
|
|
"step": 1225
|
|
},
|
|
{
|
|
"entropy": 6.951407861709595,
|
|
"epoch": 0.10861886259272342,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999953772136788,
|
|
"loss": 6.8166,
|
|
"mean_token_accuracy": 0.1174696959555149,
|
|
"num_tokens": 2290151.0,
|
|
"step": 1230
|
|
},
|
|
{
|
|
"entropy": 7.069948720932007,
|
|
"epoch": 0.10906040268456375,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999951731422068,
|
|
"loss": 6.8155,
|
|
"mean_token_accuracy": 0.12470634207129479,
|
|
"num_tokens": 2299143.0,
|
|
"step": 1235
|
|
},
|
|
{
|
|
"entropy": 7.0021812438964846,
|
|
"epoch": 0.1095019427764041,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999949646632072,
|
|
"loss": 6.8169,
|
|
"mean_token_accuracy": 0.11980563923716545,
|
|
"num_tokens": 2308257.0,
|
|
"step": 1240
|
|
},
|
|
{
|
|
"entropy": 7.0178139209747314,
|
|
"epoch": 0.10994348286824443,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004999947517766842,
|
|
"loss": 6.8092,
|
|
"mean_token_accuracy": 0.12045684233307838,
|
|
"num_tokens": 2318192.0,
|
|
"step": 1245
|
|
},
|
|
{
|
|
"entropy": 7.048533487319946,
|
|
"epoch": 0.11038502296008477,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000499994534482642,
|
|
"loss": 6.8642,
|
|
"mean_token_accuracy": 0.11663642451167107,
|
|
"num_tokens": 2327015.0,
|
|
"step": 1250
|
|
},
|
|
{
|
|
"entropy": 7.001744413375855,
|
|
"epoch": 0.11082656305192512,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999943127810847,
|
|
"loss": 6.8725,
|
|
"mean_token_accuracy": 0.11562840417027473,
|
|
"num_tokens": 2336873.0,
|
|
"step": 1255
|
|
},
|
|
{
|
|
"entropy": 7.011013555526733,
|
|
"epoch": 0.11126810314376545,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999940866720169,
|
|
"loss": 6.821,
|
|
"mean_token_accuracy": 0.12255764603614808,
|
|
"num_tokens": 2345193.0,
|
|
"step": 1260
|
|
},
|
|
{
|
|
"entropy": 7.060343503952026,
|
|
"epoch": 0.1117096432356058,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004999938561554429,
|
|
"loss": 6.732,
|
|
"mean_token_accuracy": 0.12168303355574608,
|
|
"num_tokens": 2355368.0,
|
|
"step": 1265
|
|
},
|
|
{
|
|
"entropy": 6.952377223968506,
|
|
"epoch": 0.11215118332744613,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004999936212313672,
|
|
"loss": 6.8565,
|
|
"mean_token_accuracy": 0.11511669009923935,
|
|
"num_tokens": 2365480.0,
|
|
"step": 1270
|
|
},
|
|
{
|
|
"entropy": 7.023001718521118,
|
|
"epoch": 0.11259272341928647,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999933818997943,
|
|
"loss": 6.8131,
|
|
"mean_token_accuracy": 0.1278669573366642,
|
|
"num_tokens": 2373655.0,
|
|
"step": 1275
|
|
},
|
|
{
|
|
"entropy": 7.012344169616699,
|
|
"epoch": 0.1130342635111268,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004999931381607292,
|
|
"loss": 6.8204,
|
|
"mean_token_accuracy": 0.12402483075857162,
|
|
"num_tokens": 2383283.0,
|
|
"step": 1280
|
|
},
|
|
{
|
|
"entropy": 7.009754276275634,
|
|
"epoch": 0.11347580360296715,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004999928900141764,
|
|
"loss": 6.8781,
|
|
"mean_token_accuracy": 0.11701322942972184,
|
|
"num_tokens": 2392970.0,
|
|
"step": 1285
|
|
},
|
|
{
|
|
"entropy": 7.004397630691528,
|
|
"epoch": 0.1139173436948075,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000499992637460141,
|
|
"loss": 6.7458,
|
|
"mean_token_accuracy": 0.1333714246749878,
|
|
"num_tokens": 2402594.0,
|
|
"step": 1290
|
|
},
|
|
{
|
|
"entropy": 6.943610906600952,
|
|
"epoch": 0.11435888378664782,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004999923804986275,
|
|
"loss": 6.7477,
|
|
"mean_token_accuracy": 0.12496615052223206,
|
|
"num_tokens": 2411718.0,
|
|
"step": 1295
|
|
},
|
|
{
|
|
"entropy": 6.986547565460205,
|
|
"epoch": 0.11480042387848817,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004999921191296415,
|
|
"loss": 6.8248,
|
|
"mean_token_accuracy": 0.11757947653532028,
|
|
"num_tokens": 2421285.0,
|
|
"step": 1300
|
|
},
|
|
{
|
|
"entropy": 7.024937295913697,
|
|
"epoch": 0.1152419639703285,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999918533531877,
|
|
"loss": 6.877,
|
|
"mean_token_accuracy": 0.12012948319315911,
|
|
"num_tokens": 2431070.0,
|
|
"step": 1305
|
|
},
|
|
{
|
|
"entropy": 6.981199169158936,
|
|
"epoch": 0.11568350406216885,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999915831692714,
|
|
"loss": 6.7876,
|
|
"mean_token_accuracy": 0.1231262855231762,
|
|
"num_tokens": 2440572.0,
|
|
"step": 1310
|
|
},
|
|
{
|
|
"entropy": 6.893063688278199,
|
|
"epoch": 0.11612504415400918,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999913085778981,
|
|
"loss": 6.6922,
|
|
"mean_token_accuracy": 0.12878676727414132,
|
|
"num_tokens": 2449451.0,
|
|
"step": 1315
|
|
},
|
|
{
|
|
"entropy": 6.9775279521942135,
|
|
"epoch": 0.11656658424584952,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999910295790729,
|
|
"loss": 6.8187,
|
|
"mean_token_accuracy": 0.11927035376429558,
|
|
"num_tokens": 2458803.0,
|
|
"step": 1320
|
|
},
|
|
{
|
|
"entropy": 7.028124904632568,
|
|
"epoch": 0.11700812433768987,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004999907461728014,
|
|
"loss": 6.7396,
|
|
"mean_token_accuracy": 0.12259037122130394,
|
|
"num_tokens": 2467838.0,
|
|
"step": 1325
|
|
},
|
|
{
|
|
"entropy": 6.956664562225342,
|
|
"epoch": 0.1174496644295302,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999904583590893,
|
|
"loss": 6.708,
|
|
"mean_token_accuracy": 0.1303823284804821,
|
|
"num_tokens": 2476726.0,
|
|
"step": 1330
|
|
},
|
|
{
|
|
"entropy": 6.849405431747437,
|
|
"epoch": 0.11789120452137054,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999901661379418,
|
|
"loss": 6.6171,
|
|
"mean_token_accuracy": 0.13071923553943635,
|
|
"num_tokens": 2485249.0,
|
|
"step": 1335
|
|
},
|
|
{
|
|
"entropy": 6.931700134277344,
|
|
"epoch": 0.11833274461321087,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004999898695093652,
|
|
"loss": 6.7519,
|
|
"mean_token_accuracy": 0.12411127239465714,
|
|
"num_tokens": 2494136.0,
|
|
"step": 1340
|
|
},
|
|
{
|
|
"entropy": 6.999692344665528,
|
|
"epoch": 0.11877428470505122,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004999895684733648,
|
|
"loss": 6.7524,
|
|
"mean_token_accuracy": 0.12757925391197206,
|
|
"num_tokens": 2504282.0,
|
|
"step": 1345
|
|
},
|
|
{
|
|
"entropy": 6.92269287109375,
|
|
"epoch": 0.11921582479689156,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004999892630299467,
|
|
"loss": 6.7272,
|
|
"mean_token_accuracy": 0.1256536178290844,
|
|
"num_tokens": 2513313.0,
|
|
"step": 1350
|
|
},
|
|
{
|
|
"entropy": 6.8869856834411625,
|
|
"epoch": 0.1196573648887319,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004999889531791171,
|
|
"loss": 6.7139,
|
|
"mean_token_accuracy": 0.12457521334290504,
|
|
"num_tokens": 2522824.0,
|
|
"step": 1355
|
|
},
|
|
{
|
|
"entropy": 6.899789142608642,
|
|
"epoch": 0.12009890498057224,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004999886389208817,
|
|
"loss": 6.7113,
|
|
"mean_token_accuracy": 0.12446566447615623,
|
|
"num_tokens": 2531362.0,
|
|
"step": 1360
|
|
},
|
|
{
|
|
"entropy": 6.9725359916687015,
|
|
"epoch": 0.12054044507241257,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004999883202552468,
|
|
"loss": 6.8036,
|
|
"mean_token_accuracy": 0.11904620304703713,
|
|
"num_tokens": 2540389.0,
|
|
"step": 1365
|
|
},
|
|
{
|
|
"entropy": 6.9280036926269535,
|
|
"epoch": 0.12098198516425292,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004999879971822189,
|
|
"loss": 6.7275,
|
|
"mean_token_accuracy": 0.12448851019144058,
|
|
"num_tokens": 2550468.0,
|
|
"step": 1370
|
|
},
|
|
{
|
|
"entropy": 6.879989242553711,
|
|
"epoch": 0.12142352525609325,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999876697018038,
|
|
"loss": 6.7523,
|
|
"mean_token_accuracy": 0.12376532703638077,
|
|
"num_tokens": 2559998.0,
|
|
"step": 1375
|
|
},
|
|
{
|
|
"entropy": 6.906263637542724,
|
|
"epoch": 0.1218650653479336,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999873378140085,
|
|
"loss": 6.6884,
|
|
"mean_token_accuracy": 0.12875040695071222,
|
|
"num_tokens": 2570058.0,
|
|
"step": 1380
|
|
},
|
|
{
|
|
"entropy": 6.964244222640991,
|
|
"epoch": 0.12230660543977394,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999870015188389,
|
|
"loss": 6.693,
|
|
"mean_token_accuracy": 0.12742569595575332,
|
|
"num_tokens": 2578859.0,
|
|
"step": 1385
|
|
},
|
|
{
|
|
"entropy": 6.930225372314453,
|
|
"epoch": 0.12274814553161427,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999866608163021,
|
|
"loss": 6.7472,
|
|
"mean_token_accuracy": 0.12182884812355041,
|
|
"num_tokens": 2588639.0,
|
|
"step": 1390
|
|
},
|
|
{
|
|
"entropy": 6.946022987365723,
|
|
"epoch": 0.12318968562345461,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999863157064045,
|
|
"loss": 6.6954,
|
|
"mean_token_accuracy": 0.13521388545632362,
|
|
"num_tokens": 2597679.0,
|
|
"step": 1395
|
|
},
|
|
{
|
|
"entropy": 6.886091995239258,
|
|
"epoch": 0.12363122571529495,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999859661891529,
|
|
"loss": 6.7843,
|
|
"mean_token_accuracy": 0.12181777730584145,
|
|
"num_tokens": 2607841.0,
|
|
"step": 1400
|
|
},
|
|
{
|
|
"entropy": 6.958340835571289,
|
|
"epoch": 0.12407276580713529,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999856122645543,
|
|
"loss": 6.7371,
|
|
"mean_token_accuracy": 0.12391316443681717,
|
|
"num_tokens": 2618023.0,
|
|
"step": 1405
|
|
},
|
|
{
|
|
"entropy": 6.9667067527771,
|
|
"epoch": 0.12451430589897562,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999852539326154,
|
|
"loss": 6.7222,
|
|
"mean_token_accuracy": 0.12619368433952333,
|
|
"num_tokens": 2627174.0,
|
|
"step": 1410
|
|
},
|
|
{
|
|
"entropy": 6.849303531646728,
|
|
"epoch": 0.12495584599081597,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999848911933434,
|
|
"loss": 6.673,
|
|
"mean_token_accuracy": 0.12527169808745384,
|
|
"num_tokens": 2636485.0,
|
|
"step": 1415
|
|
},
|
|
{
|
|
"entropy": 6.840041828155518,
|
|
"epoch": 0.1253973860826563,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999845240467453,
|
|
"loss": 6.7288,
|
|
"mean_token_accuracy": 0.12444792836904525,
|
|
"num_tokens": 2645484.0,
|
|
"step": 1420
|
|
},
|
|
{
|
|
"entropy": 6.993687105178833,
|
|
"epoch": 0.12583892617449666,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004999841524928282,
|
|
"loss": 6.6797,
|
|
"mean_token_accuracy": 0.12360677868127823,
|
|
"num_tokens": 2654753.0,
|
|
"step": 1425
|
|
},
|
|
{
|
|
"entropy": 6.829198551177979,
|
|
"epoch": 0.126280466266337,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004999837765315997,
|
|
"loss": 6.749,
|
|
"mean_token_accuracy": 0.12858281508088112,
|
|
"num_tokens": 2663861.0,
|
|
"step": 1430
|
|
},
|
|
{
|
|
"entropy": 6.992751169204712,
|
|
"epoch": 0.12672200635817732,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999833961630669,
|
|
"loss": 6.7325,
|
|
"mean_token_accuracy": 0.12685227245092393,
|
|
"num_tokens": 2673426.0,
|
|
"step": 1435
|
|
},
|
|
{
|
|
"entropy": 6.908594751358033,
|
|
"epoch": 0.12716354645001765,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999830113872374,
|
|
"loss": 6.7442,
|
|
"mean_token_accuracy": 0.12368026599287987,
|
|
"num_tokens": 2682597.0,
|
|
"step": 1440
|
|
},
|
|
{
|
|
"entropy": 6.829099655151367,
|
|
"epoch": 0.127605086541858,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999826222041186,
|
|
"loss": 6.6518,
|
|
"mean_token_accuracy": 0.12994373813271523,
|
|
"num_tokens": 2691299.0,
|
|
"step": 1445
|
|
},
|
|
{
|
|
"entropy": 6.969326400756836,
|
|
"epoch": 0.12804662663369834,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004999822286137182,
|
|
"loss": 6.7546,
|
|
"mean_token_accuracy": 0.12233989536762238,
|
|
"num_tokens": 2701133.0,
|
|
"step": 1450
|
|
},
|
|
{
|
|
"entropy": 6.840322494506836,
|
|
"epoch": 0.12848816672553867,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004999818306160439,
|
|
"loss": 6.7135,
|
|
"mean_token_accuracy": 0.12351029440760612,
|
|
"num_tokens": 2710704.0,
|
|
"step": 1455
|
|
},
|
|
{
|
|
"entropy": 6.927147150039673,
|
|
"epoch": 0.12892970681737903,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999814282111034,
|
|
"loss": 6.6843,
|
|
"mean_token_accuracy": 0.12635136246681214,
|
|
"num_tokens": 2719220.0,
|
|
"step": 1460
|
|
},
|
|
{
|
|
"entropy": 6.858917474746704,
|
|
"epoch": 0.12937124690921936,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999810213989047,
|
|
"loss": 6.7173,
|
|
"mean_token_accuracy": 0.1293303906917572,
|
|
"num_tokens": 2728931.0,
|
|
"step": 1465
|
|
},
|
|
{
|
|
"entropy": 6.898620748519898,
|
|
"epoch": 0.1298127870010597,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999806101794558,
|
|
"loss": 6.739,
|
|
"mean_token_accuracy": 0.12490534409880638,
|
|
"num_tokens": 2738933.0,
|
|
"step": 1470
|
|
},
|
|
{
|
|
"entropy": 6.900324058532715,
|
|
"epoch": 0.13025432709290002,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004999801945527648,
|
|
"loss": 6.6992,
|
|
"mean_token_accuracy": 0.12481218501925469,
|
|
"num_tokens": 2748807.0,
|
|
"step": 1475
|
|
},
|
|
{
|
|
"entropy": 6.84165096282959,
|
|
"epoch": 0.13069586718474038,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999797745188395,
|
|
"loss": 6.6427,
|
|
"mean_token_accuracy": 0.12684471234679223,
|
|
"num_tokens": 2757377.0,
|
|
"step": 1480
|
|
},
|
|
{
|
|
"entropy": 6.855244731903076,
|
|
"epoch": 0.13113740727658071,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004999793500776886,
|
|
"loss": 6.7431,
|
|
"mean_token_accuracy": 0.1237080566585064,
|
|
"num_tokens": 2767621.0,
|
|
"step": 1485
|
|
},
|
|
{
|
|
"entropy": 6.912423419952392,
|
|
"epoch": 0.13157894736842105,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999789212293201,
|
|
"loss": 6.6604,
|
|
"mean_token_accuracy": 0.12734709233045577,
|
|
"num_tokens": 2776946.0,
|
|
"step": 1490
|
|
},
|
|
{
|
|
"entropy": 6.797172594070434,
|
|
"epoch": 0.1320204874602614,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004999784879737423,
|
|
"loss": 6.6914,
|
|
"mean_token_accuracy": 0.12315848618745803,
|
|
"num_tokens": 2786027.0,
|
|
"step": 1495
|
|
},
|
|
{
|
|
"entropy": 6.886532497406006,
|
|
"epoch": 0.13246202755210174,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999780503109642,
|
|
"loss": 6.6162,
|
|
"mean_token_accuracy": 0.13158534690737725,
|
|
"num_tokens": 2794131.0,
|
|
"step": 1500
|
|
},
|
|
{
|
|
"entropy": 6.920978593826294,
|
|
"epoch": 0.13290356764394207,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004999776082409939,
|
|
"loss": 6.6941,
|
|
"mean_token_accuracy": 0.12774772495031356,
|
|
"num_tokens": 2803066.0,
|
|
"step": 1505
|
|
},
|
|
{
|
|
"entropy": 6.776230764389038,
|
|
"epoch": 0.1333451077357824,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999771617638401,
|
|
"loss": 6.5783,
|
|
"mean_token_accuracy": 0.13168612942099572,
|
|
"num_tokens": 2813321.0,
|
|
"step": 1510
|
|
},
|
|
{
|
|
"entropy": 6.877940082550049,
|
|
"epoch": 0.13378664782762276,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999767108795118,
|
|
"loss": 6.7411,
|
|
"mean_token_accuracy": 0.12401887774467468,
|
|
"num_tokens": 2822770.0,
|
|
"step": 1515
|
|
},
|
|
{
|
|
"entropy": 6.8076917171478275,
|
|
"epoch": 0.1342281879194631,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999762555880176,
|
|
"loss": 6.5542,
|
|
"mean_token_accuracy": 0.1320797972381115,
|
|
"num_tokens": 2830986.0,
|
|
"step": 1520
|
|
},
|
|
{
|
|
"entropy": 6.787933206558227,
|
|
"epoch": 0.13466972801130342,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999757958893666,
|
|
"loss": 6.7605,
|
|
"mean_token_accuracy": 0.12231313586235046,
|
|
"num_tokens": 2840808.0,
|
|
"step": 1525
|
|
},
|
|
{
|
|
"entropy": 6.998130750656128,
|
|
"epoch": 0.13511126810314378,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004999753317835677,
|
|
"loss": 6.6455,
|
|
"mean_token_accuracy": 0.12353885173797607,
|
|
"num_tokens": 2850043.0,
|
|
"step": 1530
|
|
},
|
|
{
|
|
"entropy": 6.652038717269898,
|
|
"epoch": 0.1355528081949841,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999748632706299,
|
|
"loss": 6.6144,
|
|
"mean_token_accuracy": 0.12928197756409646,
|
|
"num_tokens": 2860088.0,
|
|
"step": 1535
|
|
},
|
|
{
|
|
"entropy": 6.91050090789795,
|
|
"epoch": 0.13599434828682444,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004999743903505626,
|
|
"loss": 6.6809,
|
|
"mean_token_accuracy": 0.12998059689998626,
|
|
"num_tokens": 2869564.0,
|
|
"step": 1540
|
|
},
|
|
{
|
|
"entropy": 6.814730072021485,
|
|
"epoch": 0.13643588837866477,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999739130233749,
|
|
"loss": 6.6792,
|
|
"mean_token_accuracy": 0.12127165272831916,
|
|
"num_tokens": 2878511.0,
|
|
"step": 1545
|
|
},
|
|
{
|
|
"entropy": 6.931462144851684,
|
|
"epoch": 0.13687742847050513,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999734312890761,
|
|
"loss": 6.6895,
|
|
"mean_token_accuracy": 0.12624901607632638,
|
|
"num_tokens": 2888424.0,
|
|
"step": 1550
|
|
},
|
|
{
|
|
"entropy": 6.782437467575074,
|
|
"epoch": 0.13731896856234546,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999729451476757,
|
|
"loss": 6.6543,
|
|
"mean_token_accuracy": 0.12920576557517052,
|
|
"num_tokens": 2897636.0,
|
|
"step": 1555
|
|
},
|
|
{
|
|
"entropy": 6.844197607040405,
|
|
"epoch": 0.1377605086541858,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004999724545991835,
|
|
"loss": 6.563,
|
|
"mean_token_accuracy": 0.13266987800598146,
|
|
"num_tokens": 2907132.0,
|
|
"step": 1560
|
|
},
|
|
{
|
|
"entropy": 6.810891151428223,
|
|
"epoch": 0.13820204874602615,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004999719596436086,
|
|
"loss": 6.6234,
|
|
"mean_token_accuracy": 0.12518846914172171,
|
|
"num_tokens": 2916491.0,
|
|
"step": 1565
|
|
},
|
|
{
|
|
"entropy": 6.79849009513855,
|
|
"epoch": 0.13864358883786648,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999714602809611,
|
|
"loss": 6.5621,
|
|
"mean_token_accuracy": 0.1363304764032364,
|
|
"num_tokens": 2925656.0,
|
|
"step": 1570
|
|
},
|
|
{
|
|
"entropy": 6.793143224716187,
|
|
"epoch": 0.1390851289297068,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999709565112506,
|
|
"loss": 6.6186,
|
|
"mean_token_accuracy": 0.13135875687003135,
|
|
"num_tokens": 2934748.0,
|
|
"step": 1575
|
|
},
|
|
{
|
|
"entropy": 6.717667436599731,
|
|
"epoch": 0.13952666902154715,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000499970448334487,
|
|
"loss": 6.6221,
|
|
"mean_token_accuracy": 0.12501492649316787,
|
|
"num_tokens": 2943606.0,
|
|
"step": 1580
|
|
},
|
|
{
|
|
"entropy": 6.882297611236572,
|
|
"epoch": 0.1399682091133875,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999699357506803,
|
|
"loss": 6.6275,
|
|
"mean_token_accuracy": 0.126065044850111,
|
|
"num_tokens": 2952756.0,
|
|
"step": 1585
|
|
},
|
|
{
|
|
"entropy": 6.776244974136352,
|
|
"epoch": 0.14040974920522784,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004999694187598406,
|
|
"loss": 6.5767,
|
|
"mean_token_accuracy": 0.12857100814580918,
|
|
"num_tokens": 2961790.0,
|
|
"step": 1590
|
|
},
|
|
{
|
|
"entropy": 6.833420181274414,
|
|
"epoch": 0.14085128929706817,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004999688973619777,
|
|
"loss": 6.5744,
|
|
"mean_token_accuracy": 0.12646075263619422,
|
|
"num_tokens": 2970939.0,
|
|
"step": 1595
|
|
},
|
|
{
|
|
"entropy": 6.802111101150513,
|
|
"epoch": 0.14129282938890853,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004999683715571022,
|
|
"loss": 6.6249,
|
|
"mean_token_accuracy": 0.12900373488664627,
|
|
"num_tokens": 2980182.0,
|
|
"step": 1600
|
|
},
|
|
{
|
|
"entropy": 6.9092512130737305,
|
|
"epoch": 0.14173436948074886,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999678413452242,
|
|
"loss": 6.6787,
|
|
"mean_token_accuracy": 0.12571411207318306,
|
|
"num_tokens": 2990119.0,
|
|
"step": 1605
|
|
},
|
|
{
|
|
"entropy": 6.721599006652832,
|
|
"epoch": 0.1421759095725892,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004999673067263542,
|
|
"loss": 6.6058,
|
|
"mean_token_accuracy": 0.13111452385783195,
|
|
"num_tokens": 2999889.0,
|
|
"step": 1610
|
|
},
|
|
{
|
|
"entropy": 6.784647035598755,
|
|
"epoch": 0.14261744966442952,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004999667677005026,
|
|
"loss": 6.5981,
|
|
"mean_token_accuracy": 0.13359114453196524,
|
|
"num_tokens": 3009204.0,
|
|
"step": 1615
|
|
},
|
|
{
|
|
"entropy": 6.784178304672241,
|
|
"epoch": 0.14305898975626988,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999662242676799,
|
|
"loss": 6.6844,
|
|
"mean_token_accuracy": 0.1268974155187607,
|
|
"num_tokens": 3018491.0,
|
|
"step": 1620
|
|
},
|
|
{
|
|
"entropy": 6.795537805557251,
|
|
"epoch": 0.1435005298481102,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004999656764278968,
|
|
"loss": 6.6208,
|
|
"mean_token_accuracy": 0.13830544129014016,
|
|
"num_tokens": 3028330.0,
|
|
"step": 1625
|
|
},
|
|
{
|
|
"entropy": 6.7406950950622555,
|
|
"epoch": 0.14394206993995054,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004999651241811642,
|
|
"loss": 6.5979,
|
|
"mean_token_accuracy": 0.12952237874269484,
|
|
"num_tokens": 3038035.0,
|
|
"step": 1630
|
|
},
|
|
{
|
|
"entropy": 6.8958698272705075,
|
|
"epoch": 0.1443836100317909,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999645675274925,
|
|
"loss": 6.6833,
|
|
"mean_token_accuracy": 0.12506106793880462,
|
|
"num_tokens": 3047270.0,
|
|
"step": 1635
|
|
},
|
|
{
|
|
"entropy": 6.712257814407349,
|
|
"epoch": 0.14482515012363123,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999640064668931,
|
|
"loss": 6.5277,
|
|
"mean_token_accuracy": 0.1350895307958126,
|
|
"num_tokens": 3056540.0,
|
|
"step": 1640
|
|
},
|
|
{
|
|
"entropy": 6.760552787780762,
|
|
"epoch": 0.14526669021547156,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004999634409993766,
|
|
"loss": 6.631,
|
|
"mean_token_accuracy": 0.12776513770222664,
|
|
"num_tokens": 3065800.0,
|
|
"step": 1645
|
|
},
|
|
{
|
|
"entropy": 6.860488700866699,
|
|
"epoch": 0.1457082303073119,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004999628711249544,
|
|
"loss": 6.5654,
|
|
"mean_token_accuracy": 0.13428230658173562,
|
|
"num_tokens": 3075339.0,
|
|
"step": 1650
|
|
},
|
|
{
|
|
"entropy": 6.753561735153198,
|
|
"epoch": 0.14614977039915225,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004999622968436373,
|
|
"loss": 6.6494,
|
|
"mean_token_accuracy": 0.12430301308631897,
|
|
"num_tokens": 3084798.0,
|
|
"step": 1655
|
|
},
|
|
{
|
|
"entropy": 6.865996789932251,
|
|
"epoch": 0.14659131049099258,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999617181554369,
|
|
"loss": 6.6611,
|
|
"mean_token_accuracy": 0.13118176385760308,
|
|
"num_tokens": 3093437.0,
|
|
"step": 1660
|
|
},
|
|
{
|
|
"entropy": 6.732730865478516,
|
|
"epoch": 0.1470328505828329,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004999611350603643,
|
|
"loss": 6.6614,
|
|
"mean_token_accuracy": 0.125968486815691,
|
|
"num_tokens": 3102588.0,
|
|
"step": 1665
|
|
},
|
|
{
|
|
"entropy": 6.854873085021973,
|
|
"epoch": 0.14747439067467327,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.000499960547558431,
|
|
"loss": 6.546,
|
|
"mean_token_accuracy": 0.13650740087032318,
|
|
"num_tokens": 3112448.0,
|
|
"step": 1670
|
|
},
|
|
{
|
|
"entropy": 6.792056465148926,
|
|
"epoch": 0.1479159307665136,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999599556496486,
|
|
"loss": 6.6032,
|
|
"mean_token_accuracy": 0.13347120061516762,
|
|
"num_tokens": 3121760.0,
|
|
"step": 1675
|
|
},
|
|
{
|
|
"entropy": 6.710882043838501,
|
|
"epoch": 0.14835747085835393,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999593593340286,
|
|
"loss": 6.5476,
|
|
"mean_token_accuracy": 0.13694098070263863,
|
|
"num_tokens": 3130585.0,
|
|
"step": 1680
|
|
},
|
|
{
|
|
"entropy": 6.756034183502197,
|
|
"epoch": 0.14879901095019427,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999587586115826,
|
|
"loss": 6.5101,
|
|
"mean_token_accuracy": 0.1322891369462013,
|
|
"num_tokens": 3139811.0,
|
|
"step": 1685
|
|
},
|
|
{
|
|
"entropy": 6.741791248321533,
|
|
"epoch": 0.14924055104203462,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999581534823226,
|
|
"loss": 6.5782,
|
|
"mean_token_accuracy": 0.13344234824180604,
|
|
"num_tokens": 3148601.0,
|
|
"step": 1690
|
|
},
|
|
{
|
|
"entropy": 6.74654541015625,
|
|
"epoch": 0.14968209113387496,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004999575439462601,
|
|
"loss": 6.5475,
|
|
"mean_token_accuracy": 0.13243092596530914,
|
|
"num_tokens": 3157639.0,
|
|
"step": 1695
|
|
},
|
|
{
|
|
"entropy": 6.863055038452148,
|
|
"epoch": 0.1501236312257153,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999569300034075,
|
|
"loss": 6.6686,
|
|
"mean_token_accuracy": 0.12570775672793388,
|
|
"num_tokens": 3168161.0,
|
|
"step": 1700
|
|
},
|
|
{
|
|
"entropy": 6.697668886184692,
|
|
"epoch": 0.15056517131755565,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004999563116537764,
|
|
"loss": 6.5863,
|
|
"mean_token_accuracy": 0.13283494636416435,
|
|
"num_tokens": 3177388.0,
|
|
"step": 1705
|
|
},
|
|
{
|
|
"entropy": 6.749922609329223,
|
|
"epoch": 0.15100671140939598,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004999556888973792,
|
|
"loss": 6.5652,
|
|
"mean_token_accuracy": 0.13535942062735556,
|
|
"num_tokens": 3187166.0,
|
|
"step": 1710
|
|
},
|
|
{
|
|
"entropy": 6.7436247825622555,
|
|
"epoch": 0.1514482515012363,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004999550617342279,
|
|
"loss": 6.5117,
|
|
"mean_token_accuracy": 0.13675145283341408,
|
|
"num_tokens": 3197325.0,
|
|
"step": 1715
|
|
},
|
|
{
|
|
"entropy": 6.722959423065186,
|
|
"epoch": 0.15188979159307664,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000499954430164335,
|
|
"loss": 6.5838,
|
|
"mean_token_accuracy": 0.13445114344358444,
|
|
"num_tokens": 3207348.0,
|
|
"step": 1720
|
|
},
|
|
{
|
|
"entropy": 6.767676830291748,
|
|
"epoch": 0.152331331684917,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004999537941877127,
|
|
"loss": 6.5839,
|
|
"mean_token_accuracy": 0.13400614261627197,
|
|
"num_tokens": 3217291.0,
|
|
"step": 1725
|
|
},
|
|
{
|
|
"entropy": 6.651678419113159,
|
|
"epoch": 0.15277287177675733,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999531538043735,
|
|
"loss": 6.4987,
|
|
"mean_token_accuracy": 0.1366315647959709,
|
|
"num_tokens": 3225427.0,
|
|
"step": 1730
|
|
},
|
|
{
|
|
"entropy": 6.813160705566406,
|
|
"epoch": 0.15321441186859766,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999525090143298,
|
|
"loss": 6.6344,
|
|
"mean_token_accuracy": 0.13224097862839698,
|
|
"num_tokens": 3235037.0,
|
|
"step": 1735
|
|
},
|
|
{
|
|
"entropy": 6.71365065574646,
|
|
"epoch": 0.15365595196043802,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999518598175946,
|
|
"loss": 6.4877,
|
|
"mean_token_accuracy": 0.14198092222213746,
|
|
"num_tokens": 3244318.0,
|
|
"step": 1740
|
|
},
|
|
{
|
|
"entropy": 6.645174169540406,
|
|
"epoch": 0.15409749205227835,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999512062141805,
|
|
"loss": 6.5706,
|
|
"mean_token_accuracy": 0.13333735913038253,
|
|
"num_tokens": 3253753.0,
|
|
"step": 1745
|
|
},
|
|
{
|
|
"entropy": 6.7497145652771,
|
|
"epoch": 0.15453903214411868,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999505482040999,
|
|
"loss": 6.4393,
|
|
"mean_token_accuracy": 0.14499711841344834,
|
|
"num_tokens": 3263081.0,
|
|
"step": 1750
|
|
},
|
|
{
|
|
"entropy": 6.651862573623657,
|
|
"epoch": 0.154980572235959,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999498857873662,
|
|
"loss": 6.5053,
|
|
"mean_token_accuracy": 0.13713117241859435,
|
|
"num_tokens": 3271091.0,
|
|
"step": 1755
|
|
},
|
|
{
|
|
"entropy": 6.762651491165161,
|
|
"epoch": 0.15542211232779937,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999492189639921,
|
|
"loss": 6.5627,
|
|
"mean_token_accuracy": 0.13147899731993676,
|
|
"num_tokens": 3280149.0,
|
|
"step": 1760
|
|
},
|
|
{
|
|
"entropy": 6.781657361984253,
|
|
"epoch": 0.1558636524196397,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999485477339907,
|
|
"loss": 6.4859,
|
|
"mean_token_accuracy": 0.13011387065052987,
|
|
"num_tokens": 3288644.0,
|
|
"step": 1765
|
|
},
|
|
{
|
|
"entropy": 6.6499279022216795,
|
|
"epoch": 0.15630519251148003,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999478720973753,
|
|
"loss": 6.5944,
|
|
"mean_token_accuracy": 0.12865517288446426,
|
|
"num_tokens": 3298756.0,
|
|
"step": 1770
|
|
},
|
|
{
|
|
"entropy": 6.82049560546875,
|
|
"epoch": 0.1567467326033204,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000499947192054159,
|
|
"loss": 6.572,
|
|
"mean_token_accuracy": 0.12759956419467927,
|
|
"num_tokens": 3307004.0,
|
|
"step": 1775
|
|
},
|
|
{
|
|
"entropy": 6.729887390136719,
|
|
"epoch": 0.15718827269516072,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000499946507604355,
|
|
"loss": 6.525,
|
|
"mean_token_accuracy": 0.13568256571888923,
|
|
"num_tokens": 3316341.0,
|
|
"step": 1780
|
|
},
|
|
{
|
|
"entropy": 6.621280479431152,
|
|
"epoch": 0.15762981278700106,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000499945818747977,
|
|
"loss": 6.4272,
|
|
"mean_token_accuracy": 0.14301357716321944,
|
|
"num_tokens": 3324837.0,
|
|
"step": 1785
|
|
},
|
|
{
|
|
"entropy": 6.751738595962524,
|
|
"epoch": 0.1580713528788414,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004999451254850383,
|
|
"loss": 6.632,
|
|
"mean_token_accuracy": 0.1333488866686821,
|
|
"num_tokens": 3334029.0,
|
|
"step": 1790
|
|
},
|
|
{
|
|
"entropy": 6.715813636779785,
|
|
"epoch": 0.15851289297068175,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004999444278155525,
|
|
"loss": 6.4757,
|
|
"mean_token_accuracy": 0.13364549726247787,
|
|
"num_tokens": 3343566.0,
|
|
"step": 1795
|
|
},
|
|
{
|
|
"entropy": 6.723165607452392,
|
|
"epoch": 0.15895443306252208,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999437257395333,
|
|
"loss": 6.5602,
|
|
"mean_token_accuracy": 0.12862215787172318,
|
|
"num_tokens": 3352428.0,
|
|
"step": 1800
|
|
},
|
|
{
|
|
"entropy": 6.686942768096924,
|
|
"epoch": 0.1593959731543624,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004999430192569944,
|
|
"loss": 6.4482,
|
|
"mean_token_accuracy": 0.13607168048620225,
|
|
"num_tokens": 3361404.0,
|
|
"step": 1805
|
|
},
|
|
{
|
|
"entropy": 6.660811424255371,
|
|
"epoch": 0.15983751324620277,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004999423083679498,
|
|
"loss": 6.5889,
|
|
"mean_token_accuracy": 0.13365302309393884,
|
|
"num_tokens": 3370341.0,
|
|
"step": 1810
|
|
},
|
|
{
|
|
"entropy": 6.763469409942627,
|
|
"epoch": 0.1602790533380431,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004999415930724133,
|
|
"loss": 6.5229,
|
|
"mean_token_accuracy": 0.1372690588235855,
|
|
"num_tokens": 3379441.0,
|
|
"step": 1815
|
|
},
|
|
{
|
|
"entropy": 6.6314574718475345,
|
|
"epoch": 0.16072059342988343,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999408733703988,
|
|
"loss": 6.5031,
|
|
"mean_token_accuracy": 0.1369751662015915,
|
|
"num_tokens": 3389000.0,
|
|
"step": 1820
|
|
},
|
|
{
|
|
"entropy": 6.7453086376190186,
|
|
"epoch": 0.16116213352172376,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004999401492619207,
|
|
"loss": 6.558,
|
|
"mean_token_accuracy": 0.13744618371129036,
|
|
"num_tokens": 3398897.0,
|
|
"step": 1825
|
|
},
|
|
{
|
|
"entropy": 6.6991571426391605,
|
|
"epoch": 0.16160367361356412,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999394207469928,
|
|
"loss": 6.5246,
|
|
"mean_token_accuracy": 0.13513347804546355,
|
|
"num_tokens": 3408234.0,
|
|
"step": 1830
|
|
},
|
|
{
|
|
"entropy": 6.602311992645264,
|
|
"epoch": 0.16204521370540445,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004999386878256297,
|
|
"loss": 6.5632,
|
|
"mean_token_accuracy": 0.1290775217115879,
|
|
"num_tokens": 3417966.0,
|
|
"step": 1835
|
|
},
|
|
{
|
|
"entropy": 6.755477428436279,
|
|
"epoch": 0.16248675379724478,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999379504978457,
|
|
"loss": 6.5486,
|
|
"mean_token_accuracy": 0.13179300874471664,
|
|
"num_tokens": 3426689.0,
|
|
"step": 1840
|
|
},
|
|
{
|
|
"entropy": 6.736843299865723,
|
|
"epoch": 0.16292829388908514,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.000499937208763655,
|
|
"loss": 6.5904,
|
|
"mean_token_accuracy": 0.13453762903809546,
|
|
"num_tokens": 3437066.0,
|
|
"step": 1845
|
|
},
|
|
{
|
|
"entropy": 6.701791572570801,
|
|
"epoch": 0.16336983398092547,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999364626230724,
|
|
"loss": 6.5238,
|
|
"mean_token_accuracy": 0.1287774458527565,
|
|
"num_tokens": 3446215.0,
|
|
"step": 1850
|
|
},
|
|
{
|
|
"entropy": 6.76169638633728,
|
|
"epoch": 0.1638113740727658,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999357120761124,
|
|
"loss": 6.4623,
|
|
"mean_token_accuracy": 0.1368204079568386,
|
|
"num_tokens": 3456173.0,
|
|
"step": 1855
|
|
},
|
|
{
|
|
"entropy": 6.623220682144165,
|
|
"epoch": 0.16425291416460613,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004999349571227898,
|
|
"loss": 6.5465,
|
|
"mean_token_accuracy": 0.1315374918282032,
|
|
"num_tokens": 3465815.0,
|
|
"step": 1860
|
|
},
|
|
{
|
|
"entropy": 6.729666709899902,
|
|
"epoch": 0.1646944542564465,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999341977631193,
|
|
"loss": 6.473,
|
|
"mean_token_accuracy": 0.13990226536989211,
|
|
"num_tokens": 3474396.0,
|
|
"step": 1865
|
|
},
|
|
{
|
|
"entropy": 6.622664070129394,
|
|
"epoch": 0.16513599434828682,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004999334339971157,
|
|
"loss": 6.5267,
|
|
"mean_token_accuracy": 0.1300884112715721,
|
|
"num_tokens": 3484240.0,
|
|
"step": 1870
|
|
},
|
|
{
|
|
"entropy": 6.753061437606812,
|
|
"epoch": 0.16557753444012716,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004999326658247942,
|
|
"loss": 6.4985,
|
|
"mean_token_accuracy": 0.1349583201110363,
|
|
"num_tokens": 3493569.0,
|
|
"step": 1875
|
|
},
|
|
{
|
|
"entropy": 6.659213352203369,
|
|
"epoch": 0.16601907453196751,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999318932461696,
|
|
"loss": 6.4129,
|
|
"mean_token_accuracy": 0.12922252491116523,
|
|
"num_tokens": 3501947.0,
|
|
"step": 1880
|
|
},
|
|
{
|
|
"entropy": 6.578718376159668,
|
|
"epoch": 0.16646061462380785,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004999311162612571,
|
|
"loss": 6.4492,
|
|
"mean_token_accuracy": 0.14246295243501664,
|
|
"num_tokens": 3511817.0,
|
|
"step": 1885
|
|
},
|
|
{
|
|
"entropy": 6.711222791671753,
|
|
"epoch": 0.16690215471564818,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000499930334870072,
|
|
"loss": 6.5397,
|
|
"mean_token_accuracy": 0.1377376690506935,
|
|
"num_tokens": 3521581.0,
|
|
"step": 1890
|
|
},
|
|
{
|
|
"entropy": 6.6527848720550535,
|
|
"epoch": 0.1673436948074885,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999295490726296,
|
|
"loss": 6.5204,
|
|
"mean_token_accuracy": 0.13453154340386392,
|
|
"num_tokens": 3531659.0,
|
|
"step": 1895
|
|
},
|
|
{
|
|
"entropy": 6.594851064682007,
|
|
"epoch": 0.16778523489932887,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999287588689453,
|
|
"loss": 6.3853,
|
|
"mean_token_accuracy": 0.14152303338050842,
|
|
"num_tokens": 3540919.0,
|
|
"step": 1900
|
|
},
|
|
{
|
|
"entropy": 6.660305786132812,
|
|
"epoch": 0.1682267749911692,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004999279642590344,
|
|
"loss": 6.3887,
|
|
"mean_token_accuracy": 0.13910981193184851,
|
|
"num_tokens": 3549756.0,
|
|
"step": 1905
|
|
},
|
|
{
|
|
"entropy": 6.607125902175904,
|
|
"epoch": 0.16866831508300953,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004999271652429127,
|
|
"loss": 6.454,
|
|
"mean_token_accuracy": 0.13921822756528854,
|
|
"num_tokens": 3559686.0,
|
|
"step": 1910
|
|
},
|
|
{
|
|
"entropy": 6.609749174118042,
|
|
"epoch": 0.1691098551748499,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999263618205958,
|
|
"loss": 6.4051,
|
|
"mean_token_accuracy": 0.13996847197413445,
|
|
"num_tokens": 3568558.0,
|
|
"step": 1915
|
|
},
|
|
{
|
|
"entropy": 6.624215602874756,
|
|
"epoch": 0.16955139526669022,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004999255539920993,
|
|
"loss": 6.484,
|
|
"mean_token_accuracy": 0.1342615231871605,
|
|
"num_tokens": 3578297.0,
|
|
"step": 1920
|
|
},
|
|
{
|
|
"entropy": 6.698274326324463,
|
|
"epoch": 0.16999293535853055,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004999247417574391,
|
|
"loss": 6.5244,
|
|
"mean_token_accuracy": 0.13907946199178695,
|
|
"num_tokens": 3588372.0,
|
|
"step": 1925
|
|
},
|
|
{
|
|
"entropy": 6.692286682128906,
|
|
"epoch": 0.17043447545037088,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999239251166312,
|
|
"loss": 6.4649,
|
|
"mean_token_accuracy": 0.14157049655914306,
|
|
"num_tokens": 3597728.0,
|
|
"step": 1930
|
|
},
|
|
{
|
|
"entropy": 6.6316468715667725,
|
|
"epoch": 0.17087601554221124,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999231040696914,
|
|
"loss": 6.454,
|
|
"mean_token_accuracy": 0.14170244634151458,
|
|
"num_tokens": 3606886.0,
|
|
"step": 1935
|
|
},
|
|
{
|
|
"entropy": 6.678344964981079,
|
|
"epoch": 0.17131755563405157,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999222786166361,
|
|
"loss": 6.4845,
|
|
"mean_token_accuracy": 0.13350907787680627,
|
|
"num_tokens": 3615795.0,
|
|
"step": 1940
|
|
},
|
|
{
|
|
"entropy": 6.665940523147583,
|
|
"epoch": 0.1717590957258919,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999214487574812,
|
|
"loss": 6.4825,
|
|
"mean_token_accuracy": 0.13486144170165063,
|
|
"num_tokens": 3624360.0,
|
|
"step": 1945
|
|
},
|
|
{
|
|
"entropy": 6.654449462890625,
|
|
"epoch": 0.17220063581773226,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004999206144922431,
|
|
"loss": 6.4428,
|
|
"mean_token_accuracy": 0.1393147215247154,
|
|
"num_tokens": 3633822.0,
|
|
"step": 1950
|
|
},
|
|
{
|
|
"entropy": 6.6238181591033936,
|
|
"epoch": 0.1726421759095726,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.000499919775820938,
|
|
"loss": 6.5075,
|
|
"mean_token_accuracy": 0.13793846368789672,
|
|
"num_tokens": 3643667.0,
|
|
"step": 1955
|
|
},
|
|
{
|
|
"entropy": 6.619096565246582,
|
|
"epoch": 0.17308371600141292,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004999189327435825,
|
|
"loss": 6.4087,
|
|
"mean_token_accuracy": 0.13899273052811623,
|
|
"num_tokens": 3652596.0,
|
|
"step": 1960
|
|
},
|
|
{
|
|
"entropy": 6.695830154418945,
|
|
"epoch": 0.17352525609325326,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999180852601929,
|
|
"loss": 6.5268,
|
|
"mean_token_accuracy": 0.13822980970144272,
|
|
"num_tokens": 3661362.0,
|
|
"step": 1965
|
|
},
|
|
{
|
|
"entropy": 6.632474565505982,
|
|
"epoch": 0.17396679618509361,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000499917233370786,
|
|
"loss": 6.4865,
|
|
"mean_token_accuracy": 0.1420795053243637,
|
|
"num_tokens": 3671573.0,
|
|
"step": 1970
|
|
},
|
|
{
|
|
"entropy": 6.656900548934937,
|
|
"epoch": 0.17440833627693395,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999163770753784,
|
|
"loss": 6.5884,
|
|
"mean_token_accuracy": 0.1283446244895458,
|
|
"num_tokens": 3681183.0,
|
|
"step": 1975
|
|
},
|
|
{
|
|
"entropy": 6.667371845245361,
|
|
"epoch": 0.17484987636877428,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999155163739869,
|
|
"loss": 6.4293,
|
|
"mean_token_accuracy": 0.13852844312787055,
|
|
"num_tokens": 3689768.0,
|
|
"step": 1980
|
|
},
|
|
{
|
|
"entropy": 6.64871244430542,
|
|
"epoch": 0.17529141646061464,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004999146512666284,
|
|
"loss": 6.4866,
|
|
"mean_token_accuracy": 0.13745958730578423,
|
|
"num_tokens": 3699291.0,
|
|
"step": 1985
|
|
},
|
|
{
|
|
"entropy": 6.74596848487854,
|
|
"epoch": 0.17573295655245497,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004999137817533197,
|
|
"loss": 6.4329,
|
|
"mean_token_accuracy": 0.13396958485245705,
|
|
"num_tokens": 3708551.0,
|
|
"step": 1990
|
|
},
|
|
{
|
|
"entropy": 6.543181896209717,
|
|
"epoch": 0.1761744966442953,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004999129078340779,
|
|
"loss": 6.4554,
|
|
"mean_token_accuracy": 0.13674973249435424,
|
|
"num_tokens": 3717617.0,
|
|
"step": 1995
|
|
},
|
|
{
|
|
"entropy": 6.594240331649781,
|
|
"epoch": 0.17661603673613563,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004999120295089202,
|
|
"loss": 6.4395,
|
|
"mean_token_accuracy": 0.14458404257893562,
|
|
"num_tokens": 3728457.0,
|
|
"step": 2000
|
|
},
|
|
{
|
|
"entropy": 6.636260986328125,
|
|
"epoch": 0.177057576827976,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004999111467778639,
|
|
"loss": 6.5277,
|
|
"mean_token_accuracy": 0.13387356027960778,
|
|
"num_tokens": 3738467.0,
|
|
"step": 2005
|
|
},
|
|
{
|
|
"entropy": 6.71912145614624,
|
|
"epoch": 0.17749911691981632,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000499910259640926,
|
|
"loss": 6.532,
|
|
"mean_token_accuracy": 0.13334558084607123,
|
|
"num_tokens": 3747482.0,
|
|
"step": 2010
|
|
},
|
|
{
|
|
"entropy": 6.6471014499664305,
|
|
"epoch": 0.17794065701165665,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.000499909368098124,
|
|
"loss": 6.5043,
|
|
"mean_token_accuracy": 0.1343577802181244,
|
|
"num_tokens": 3756227.0,
|
|
"step": 2015
|
|
},
|
|
{
|
|
"entropy": 6.543698358535766,
|
|
"epoch": 0.178382197103497,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004999084721494754,
|
|
"loss": 6.4101,
|
|
"mean_token_accuracy": 0.13692991584539413,
|
|
"num_tokens": 3765481.0,
|
|
"step": 2020
|
|
},
|
|
{
|
|
"entropy": 6.616260051727295,
|
|
"epoch": 0.17882373719533734,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999075717949978,
|
|
"loss": 6.4347,
|
|
"mean_token_accuracy": 0.13827534690499305,
|
|
"num_tokens": 3774261.0,
|
|
"step": 2025
|
|
},
|
|
{
|
|
"entropy": 6.604419136047364,
|
|
"epoch": 0.17926527728717767,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999066670347089,
|
|
"loss": 6.4235,
|
|
"mean_token_accuracy": 0.14103795886039733,
|
|
"num_tokens": 3783725.0,
|
|
"step": 2030
|
|
},
|
|
{
|
|
"entropy": 6.695284843444824,
|
|
"epoch": 0.179706817379018,
|
|
"grad_norm": 0.734375,
|
|
"learning_rate": 0.0004999057578686261,
|
|
"loss": 6.5538,
|
|
"mean_token_accuracy": 0.13175728917121887,
|
|
"num_tokens": 3794129.0,
|
|
"step": 2035
|
|
},
|
|
{
|
|
"entropy": 6.723241186141967,
|
|
"epoch": 0.18014835747085836,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999048442967675,
|
|
"loss": 6.5037,
|
|
"mean_token_accuracy": 0.13313911259174346,
|
|
"num_tokens": 3803954.0,
|
|
"step": 2040
|
|
},
|
|
{
|
|
"entropy": 6.576015520095825,
|
|
"epoch": 0.1805898975626987,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004999039263191508,
|
|
"loss": 6.4143,
|
|
"mean_token_accuracy": 0.13729096055030823,
|
|
"num_tokens": 3812220.0,
|
|
"step": 2045
|
|
},
|
|
{
|
|
"entropy": 6.613183689117432,
|
|
"epoch": 0.18103143765453902,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004999030039357943,
|
|
"loss": 6.4089,
|
|
"mean_token_accuracy": 0.1392333209514618,
|
|
"num_tokens": 3821595.0,
|
|
"step": 2050
|
|
},
|
|
{
|
|
"entropy": 6.618626260757447,
|
|
"epoch": 0.18147297774637938,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004999020771467158,
|
|
"loss": 6.4898,
|
|
"mean_token_accuracy": 0.13633593022823334,
|
|
"num_tokens": 3831020.0,
|
|
"step": 2055
|
|
},
|
|
{
|
|
"entropy": 6.593099689483642,
|
|
"epoch": 0.1819145178382197,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004999011459519335,
|
|
"loss": 6.4288,
|
|
"mean_token_accuracy": 0.13460941165685653,
|
|
"num_tokens": 3839735.0,
|
|
"step": 2060
|
|
},
|
|
{
|
|
"entropy": 6.643797731399536,
|
|
"epoch": 0.18235605793006004,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999002103514655,
|
|
"loss": 6.5236,
|
|
"mean_token_accuracy": 0.13866995573043822,
|
|
"num_tokens": 3849095.0,
|
|
"step": 2065
|
|
},
|
|
{
|
|
"entropy": 6.676905632019043,
|
|
"epoch": 0.18279759802190038,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998992703453304,
|
|
"loss": 6.5015,
|
|
"mean_token_accuracy": 0.14171259924769403,
|
|
"num_tokens": 3859063.0,
|
|
"step": 2070
|
|
},
|
|
{
|
|
"entropy": 6.639267778396606,
|
|
"epoch": 0.18323913811374073,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004998983259335466,
|
|
"loss": 6.5092,
|
|
"mean_token_accuracy": 0.13027978986501693,
|
|
"num_tokens": 3868626.0,
|
|
"step": 2075
|
|
},
|
|
{
|
|
"entropy": 6.607439041137695,
|
|
"epoch": 0.18368067820558107,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004998973771161324,
|
|
"loss": 6.4954,
|
|
"mean_token_accuracy": 0.139207723736763,
|
|
"num_tokens": 3878477.0,
|
|
"step": 2080
|
|
},
|
|
{
|
|
"entropy": 6.611793661117554,
|
|
"epoch": 0.1841222182974214,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004998964238931065,
|
|
"loss": 6.3776,
|
|
"mean_token_accuracy": 0.14397683441638948,
|
|
"num_tokens": 3887166.0,
|
|
"step": 2085
|
|
},
|
|
{
|
|
"entropy": 6.496103525161743,
|
|
"epoch": 0.18456375838926176,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004998954662644876,
|
|
"loss": 6.3283,
|
|
"mean_token_accuracy": 0.1425325997173786,
|
|
"num_tokens": 3896431.0,
|
|
"step": 2090
|
|
},
|
|
{
|
|
"entropy": 6.614110946655273,
|
|
"epoch": 0.1850052984811021,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998945042302943,
|
|
"loss": 6.402,
|
|
"mean_token_accuracy": 0.1468320146203041,
|
|
"num_tokens": 3904937.0,
|
|
"step": 2095
|
|
},
|
|
{
|
|
"entropy": 6.649114370346069,
|
|
"epoch": 0.18544683857294242,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004998935377905457,
|
|
"loss": 6.4103,
|
|
"mean_token_accuracy": 0.14189980030059815,
|
|
"num_tokens": 3913905.0,
|
|
"step": 2100
|
|
},
|
|
{
|
|
"entropy": 6.551333093643189,
|
|
"epoch": 0.18588837866478275,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004998925669452605,
|
|
"loss": 6.4386,
|
|
"mean_token_accuracy": 0.1394965521991253,
|
|
"num_tokens": 3923894.0,
|
|
"step": 2105
|
|
},
|
|
{
|
|
"entropy": 6.607130718231201,
|
|
"epoch": 0.1863299187566231,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004998915916944579,
|
|
"loss": 6.4454,
|
|
"mean_token_accuracy": 0.1338847316801548,
|
|
"num_tokens": 3932124.0,
|
|
"step": 2110
|
|
},
|
|
{
|
|
"entropy": 6.626301956176758,
|
|
"epoch": 0.18677145884846344,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004998906120381568,
|
|
"loss": 6.4752,
|
|
"mean_token_accuracy": 0.1314583897590637,
|
|
"num_tokens": 3942462.0,
|
|
"step": 2115
|
|
},
|
|
{
|
|
"entropy": 6.55535740852356,
|
|
"epoch": 0.18721299894030377,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004998896279763766,
|
|
"loss": 6.4285,
|
|
"mean_token_accuracy": 0.143652606010437,
|
|
"num_tokens": 3951361.0,
|
|
"step": 2120
|
|
},
|
|
{
|
|
"entropy": 6.699276733398437,
|
|
"epoch": 0.18765453903214413,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004998886395091365,
|
|
"loss": 6.5322,
|
|
"mean_token_accuracy": 0.13593855649232864,
|
|
"num_tokens": 3961486.0,
|
|
"step": 2125
|
|
},
|
|
{
|
|
"entropy": 6.510635089874268,
|
|
"epoch": 0.18809607912398446,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998876466364559,
|
|
"loss": 6.329,
|
|
"mean_token_accuracy": 0.14105381667613984,
|
|
"num_tokens": 3970019.0,
|
|
"step": 2130
|
|
},
|
|
{
|
|
"entropy": 6.581699275970459,
|
|
"epoch": 0.1885376192158248,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004998866493583541,
|
|
"loss": 6.3318,
|
|
"mean_token_accuracy": 0.1405398890376091,
|
|
"num_tokens": 3978625.0,
|
|
"step": 2135
|
|
},
|
|
{
|
|
"entropy": 6.564266300201416,
|
|
"epoch": 0.18897915930766512,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998856476748509,
|
|
"loss": 6.4541,
|
|
"mean_token_accuracy": 0.13665426075458526,
|
|
"num_tokens": 3989191.0,
|
|
"step": 2140
|
|
},
|
|
{
|
|
"entropy": 6.618397665023804,
|
|
"epoch": 0.18942069939950548,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004998846415859656,
|
|
"loss": 6.431,
|
|
"mean_token_accuracy": 0.13899025768041612,
|
|
"num_tokens": 3998558.0,
|
|
"step": 2145
|
|
},
|
|
{
|
|
"entropy": 6.506017112731934,
|
|
"epoch": 0.1898622394913458,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004998836310917182,
|
|
"loss": 6.3985,
|
|
"mean_token_accuracy": 0.14203351140022277,
|
|
"num_tokens": 4008318.0,
|
|
"step": 2150
|
|
},
|
|
{
|
|
"entropy": 6.643159866333008,
|
|
"epoch": 0.19030377958318614,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004998826161921282,
|
|
"loss": 6.3839,
|
|
"mean_token_accuracy": 0.1404844231903553,
|
|
"num_tokens": 4017133.0,
|
|
"step": 2155
|
|
},
|
|
{
|
|
"entropy": 6.56635799407959,
|
|
"epoch": 0.1907453196750265,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004998815968872157,
|
|
"loss": 6.3718,
|
|
"mean_token_accuracy": 0.14540308713912964,
|
|
"num_tokens": 4026289.0,
|
|
"step": 2160
|
|
},
|
|
{
|
|
"entropy": 6.529609298706054,
|
|
"epoch": 0.19118685976686683,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004998805731770007,
|
|
"loss": 6.3744,
|
|
"mean_token_accuracy": 0.14073018357157707,
|
|
"num_tokens": 4035209.0,
|
|
"step": 2165
|
|
},
|
|
{
|
|
"entropy": 6.62944221496582,
|
|
"epoch": 0.19162839985870717,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.000499879545061503,
|
|
"loss": 6.5068,
|
|
"mean_token_accuracy": 0.12898163348436356,
|
|
"num_tokens": 4044498.0,
|
|
"step": 2170
|
|
},
|
|
{
|
|
"entropy": 6.6656512260437015,
|
|
"epoch": 0.1920699399505475,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004998785125407432,
|
|
"loss": 6.4006,
|
|
"mean_token_accuracy": 0.14504364654421806,
|
|
"num_tokens": 4054211.0,
|
|
"step": 2175
|
|
},
|
|
{
|
|
"entropy": 6.602165699005127,
|
|
"epoch": 0.19251148004238786,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.000499877475614741,
|
|
"loss": 6.4231,
|
|
"mean_token_accuracy": 0.13061779513955116,
|
|
"num_tokens": 4064089.0,
|
|
"step": 2180
|
|
},
|
|
{
|
|
"entropy": 6.533041334152221,
|
|
"epoch": 0.1929530201342282,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004998764342835169,
|
|
"loss": 6.3658,
|
|
"mean_token_accuracy": 0.14450084567070007,
|
|
"num_tokens": 4073042.0,
|
|
"step": 2185
|
|
},
|
|
{
|
|
"entropy": 6.503344345092773,
|
|
"epoch": 0.19339456022606852,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998753885470915,
|
|
"loss": 6.4349,
|
|
"mean_token_accuracy": 0.13570086807012557,
|
|
"num_tokens": 4081667.0,
|
|
"step": 2190
|
|
},
|
|
{
|
|
"entropy": 6.554050397872925,
|
|
"epoch": 0.19383610031790888,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004998743384054851,
|
|
"loss": 6.4315,
|
|
"mean_token_accuracy": 0.14233472645282746,
|
|
"num_tokens": 4090598.0,
|
|
"step": 2195
|
|
},
|
|
{
|
|
"entropy": 6.641329669952393,
|
|
"epoch": 0.1942776404097492,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004998732838587183,
|
|
"loss": 6.3621,
|
|
"mean_token_accuracy": 0.14019383788108825,
|
|
"num_tokens": 4100113.0,
|
|
"step": 2200
|
|
},
|
|
{
|
|
"entropy": 6.567934036254883,
|
|
"epoch": 0.19471918050158954,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004998722249068118,
|
|
"loss": 6.3488,
|
|
"mean_token_accuracy": 0.14066357761621476,
|
|
"num_tokens": 4108473.0,
|
|
"step": 2205
|
|
},
|
|
{
|
|
"entropy": 6.440048599243164,
|
|
"epoch": 0.19516072059342987,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004998711615497863,
|
|
"loss": 6.3735,
|
|
"mean_token_accuracy": 0.14175349250435829,
|
|
"num_tokens": 4118479.0,
|
|
"step": 2210
|
|
},
|
|
{
|
|
"entropy": 6.5755712509155275,
|
|
"epoch": 0.19560226068527023,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998700937876626,
|
|
"loss": 6.326,
|
|
"mean_token_accuracy": 0.1472289428114891,
|
|
"num_tokens": 4127458.0,
|
|
"step": 2215
|
|
},
|
|
{
|
|
"entropy": 6.598430156707764,
|
|
"epoch": 0.19604380077711056,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004998690216204615,
|
|
"loss": 6.4709,
|
|
"mean_token_accuracy": 0.13767264410853386,
|
|
"num_tokens": 4138099.0,
|
|
"step": 2220
|
|
},
|
|
{
|
|
"entropy": 6.552243328094482,
|
|
"epoch": 0.1964853408689509,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004998679450482043,
|
|
"loss": 6.335,
|
|
"mean_token_accuracy": 0.14231890067458153,
|
|
"num_tokens": 4147991.0,
|
|
"step": 2225
|
|
},
|
|
{
|
|
"entropy": 6.487472057342529,
|
|
"epoch": 0.19692688096079125,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000499866864070912,
|
|
"loss": 6.4582,
|
|
"mean_token_accuracy": 0.1360939234495163,
|
|
"num_tokens": 4157128.0,
|
|
"step": 2230
|
|
},
|
|
{
|
|
"entropy": 6.669093990325928,
|
|
"epoch": 0.19736842105263158,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004998657786886056,
|
|
"loss": 6.4883,
|
|
"mean_token_accuracy": 0.13292337208986282,
|
|
"num_tokens": 4168339.0,
|
|
"step": 2235
|
|
},
|
|
{
|
|
"entropy": 6.5326982021331785,
|
|
"epoch": 0.1978099611444719,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004998646889013066,
|
|
"loss": 6.3211,
|
|
"mean_token_accuracy": 0.14647760689258577,
|
|
"num_tokens": 4177476.0,
|
|
"step": 2240
|
|
},
|
|
{
|
|
"entropy": 6.605254316329956,
|
|
"epoch": 0.19825150123631224,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998635947090362,
|
|
"loss": 6.4406,
|
|
"mean_token_accuracy": 0.1364073134958744,
|
|
"num_tokens": 4187578.0,
|
|
"step": 2245
|
|
},
|
|
{
|
|
"entropy": 6.487747430801392,
|
|
"epoch": 0.1986930413281526,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004998624961118158,
|
|
"loss": 6.3272,
|
|
"mean_token_accuracy": 0.14302509576082229,
|
|
"num_tokens": 4196826.0,
|
|
"step": 2250
|
|
},
|
|
{
|
|
"entropy": 6.587798023223877,
|
|
"epoch": 0.19913458141999293,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000499861393109667,
|
|
"loss": 6.301,
|
|
"mean_token_accuracy": 0.14366807490587236,
|
|
"num_tokens": 4206085.0,
|
|
"step": 2255
|
|
},
|
|
{
|
|
"entropy": 6.432883596420288,
|
|
"epoch": 0.19957612151183327,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004998602857026114,
|
|
"loss": 6.3367,
|
|
"mean_token_accuracy": 0.1540941886603832,
|
|
"num_tokens": 4215375.0,
|
|
"step": 2260
|
|
},
|
|
{
|
|
"entropy": 6.59939227104187,
|
|
"epoch": 0.20001766160367362,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004998591738906708,
|
|
"loss": 6.3942,
|
|
"mean_token_accuracy": 0.13624251410365104,
|
|
"num_tokens": 4224809.0,
|
|
"step": 2265
|
|
},
|
|
{
|
|
"entropy": 6.535125207901001,
|
|
"epoch": 0.20045920169551396,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004998580576738668,
|
|
"loss": 6.3869,
|
|
"mean_token_accuracy": 0.1412413999438286,
|
|
"num_tokens": 4234048.0,
|
|
"step": 2270
|
|
},
|
|
{
|
|
"entropy": 6.533976364135742,
|
|
"epoch": 0.2009007417873543,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004998569370522213,
|
|
"loss": 6.4072,
|
|
"mean_token_accuracy": 0.14488251730799676,
|
|
"num_tokens": 4242622.0,
|
|
"step": 2275
|
|
},
|
|
{
|
|
"entropy": 6.589724588394165,
|
|
"epoch": 0.20134228187919462,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004998558120257563,
|
|
"loss": 6.3473,
|
|
"mean_token_accuracy": 0.14969526827335358,
|
|
"num_tokens": 4251833.0,
|
|
"step": 2280
|
|
},
|
|
{
|
|
"entropy": 6.640519809722901,
|
|
"epoch": 0.20178382197103498,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004998546825944938,
|
|
"loss": 6.4479,
|
|
"mean_token_accuracy": 0.13527315109968185,
|
|
"num_tokens": 4260769.0,
|
|
"step": 2285
|
|
},
|
|
{
|
|
"entropy": 6.484637928009033,
|
|
"epoch": 0.2022253620628753,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.000499853548758456,
|
|
"loss": 6.4441,
|
|
"mean_token_accuracy": 0.14147843569517135,
|
|
"num_tokens": 4270805.0,
|
|
"step": 2290
|
|
},
|
|
{
|
|
"entropy": 6.580462312698364,
|
|
"epoch": 0.20266690215471564,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.000499852410517665,
|
|
"loss": 6.4282,
|
|
"mean_token_accuracy": 0.13979952931404113,
|
|
"num_tokens": 4280860.0,
|
|
"step": 2295
|
|
},
|
|
{
|
|
"entropy": 6.549244785308838,
|
|
"epoch": 0.203108442246556,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004998512678721431,
|
|
"loss": 6.4135,
|
|
"mean_token_accuracy": 0.14154525697231293,
|
|
"num_tokens": 4291283.0,
|
|
"step": 2300
|
|
},
|
|
{
|
|
"entropy": 6.6056934833526615,
|
|
"epoch": 0.20354998233839633,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000499850120821913,
|
|
"loss": 6.3769,
|
|
"mean_token_accuracy": 0.13967125117778778,
|
|
"num_tokens": 4300920.0,
|
|
"step": 2305
|
|
},
|
|
{
|
|
"entropy": 6.631320190429688,
|
|
"epoch": 0.20399152243023666,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004998489693669967,
|
|
"loss": 6.3364,
|
|
"mean_token_accuracy": 0.1530125007033348,
|
|
"num_tokens": 4311056.0,
|
|
"step": 2310
|
|
},
|
|
{
|
|
"entropy": 6.41552734375,
|
|
"epoch": 0.204433062522077,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.000499847813507417,
|
|
"loss": 6.2605,
|
|
"mean_token_accuracy": 0.14134440571069717,
|
|
"num_tokens": 4320013.0,
|
|
"step": 2315
|
|
},
|
|
{
|
|
"entropy": 6.52802586555481,
|
|
"epoch": 0.20487460261391735,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004998466532431966,
|
|
"loss": 6.2845,
|
|
"mean_token_accuracy": 0.1438765361905098,
|
|
"num_tokens": 4328243.0,
|
|
"step": 2320
|
|
},
|
|
{
|
|
"entropy": 6.505352210998535,
|
|
"epoch": 0.20531614270575768,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004998454885743581,
|
|
"loss": 6.3987,
|
|
"mean_token_accuracy": 0.1398943543434143,
|
|
"num_tokens": 4337126.0,
|
|
"step": 2325
|
|
},
|
|
{
|
|
"entropy": 6.534863376617432,
|
|
"epoch": 0.205757682797598,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004998443195009242,
|
|
"loss": 6.3298,
|
|
"mean_token_accuracy": 0.14415593892335893,
|
|
"num_tokens": 4347008.0,
|
|
"step": 2330
|
|
},
|
|
{
|
|
"entropy": 6.526832628250122,
|
|
"epoch": 0.20619922288943837,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004998431460229182,
|
|
"loss": 6.3074,
|
|
"mean_token_accuracy": 0.14151543527841567,
|
|
"num_tokens": 4355979.0,
|
|
"step": 2335
|
|
},
|
|
{
|
|
"entropy": 6.50370044708252,
|
|
"epoch": 0.2066407629812787,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004998419681403627,
|
|
"loss": 6.3397,
|
|
"mean_token_accuracy": 0.13715255707502366,
|
|
"num_tokens": 4364843.0,
|
|
"step": 2340
|
|
},
|
|
{
|
|
"entropy": 6.5381780624389645,
|
|
"epoch": 0.20708230307311903,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998407858532809,
|
|
"loss": 6.399,
|
|
"mean_token_accuracy": 0.1404947891831398,
|
|
"num_tokens": 4373951.0,
|
|
"step": 2345
|
|
},
|
|
{
|
|
"entropy": 6.539831066131592,
|
|
"epoch": 0.20752384316495937,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000499839599161696,
|
|
"loss": 6.3743,
|
|
"mean_token_accuracy": 0.1348615162074566,
|
|
"num_tokens": 4382672.0,
|
|
"step": 2350
|
|
},
|
|
{
|
|
"entropy": 6.503879594802856,
|
|
"epoch": 0.20796538325679972,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004998384080656314,
|
|
"loss": 6.323,
|
|
"mean_token_accuracy": 0.1376982130110264,
|
|
"num_tokens": 4392113.0,
|
|
"step": 2355
|
|
},
|
|
{
|
|
"entropy": 6.495373058319092,
|
|
"epoch": 0.20840692334864006,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00049983721256511,
|
|
"loss": 6.3301,
|
|
"mean_token_accuracy": 0.14757516384124755,
|
|
"num_tokens": 4401587.0,
|
|
"step": 2360
|
|
},
|
|
{
|
|
"entropy": 6.432989120483398,
|
|
"epoch": 0.2088484634404804,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004998360126601556,
|
|
"loss": 6.2641,
|
|
"mean_token_accuracy": 0.14713913276791574,
|
|
"num_tokens": 4410304.0,
|
|
"step": 2365
|
|
},
|
|
{
|
|
"entropy": 6.4272682666778564,
|
|
"epoch": 0.20929000353232075,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004998348083507916,
|
|
"loss": 6.386,
|
|
"mean_token_accuracy": 0.1397126257419586,
|
|
"num_tokens": 4419832.0,
|
|
"step": 2370
|
|
},
|
|
{
|
|
"entropy": 6.525888919830322,
|
|
"epoch": 0.20973154362416108,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004998335996370416,
|
|
"loss": 6.2407,
|
|
"mean_token_accuracy": 0.15095002949237823,
|
|
"num_tokens": 4428237.0,
|
|
"step": 2375
|
|
},
|
|
{
|
|
"entropy": 6.497446823120117,
|
|
"epoch": 0.2101730837160014,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004998323865189291,
|
|
"loss": 6.3849,
|
|
"mean_token_accuracy": 0.13744312450289725,
|
|
"num_tokens": 4437325.0,
|
|
"step": 2380
|
|
},
|
|
{
|
|
"entropy": 6.524771118164063,
|
|
"epoch": 0.21061462380784174,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004998311689964781,
|
|
"loss": 6.2568,
|
|
"mean_token_accuracy": 0.15043262839317323,
|
|
"num_tokens": 4446745.0,
|
|
"step": 2385
|
|
},
|
|
{
|
|
"entropy": 6.476553869247437,
|
|
"epoch": 0.2110561638996821,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004998299470697125,
|
|
"loss": 6.3391,
|
|
"mean_token_accuracy": 0.14306224137544632,
|
|
"num_tokens": 4455947.0,
|
|
"step": 2390
|
|
},
|
|
{
|
|
"entropy": 6.497906303405761,
|
|
"epoch": 0.21149770399152243,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004998287207386559,
|
|
"loss": 6.3061,
|
|
"mean_token_accuracy": 0.1393039345741272,
|
|
"num_tokens": 4465300.0,
|
|
"step": 2395
|
|
},
|
|
{
|
|
"entropy": 6.564029312133789,
|
|
"epoch": 0.21193924408336276,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004998274900033326,
|
|
"loss": 6.3067,
|
|
"mean_token_accuracy": 0.1415036529302597,
|
|
"num_tokens": 4474470.0,
|
|
"step": 2400
|
|
},
|
|
{
|
|
"entropy": 6.402004289627075,
|
|
"epoch": 0.21238078417520312,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004998262548637667,
|
|
"loss": 6.3252,
|
|
"mean_token_accuracy": 0.14604315310716628,
|
|
"num_tokens": 4483991.0,
|
|
"step": 2405
|
|
},
|
|
{
|
|
"entropy": 6.517073488235473,
|
|
"epoch": 0.21282232426704345,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004998250153199822,
|
|
"loss": 6.3753,
|
|
"mean_token_accuracy": 0.14476549327373506,
|
|
"num_tokens": 4493963.0,
|
|
"step": 2410
|
|
},
|
|
{
|
|
"entropy": 6.551792812347412,
|
|
"epoch": 0.21326386435888378,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004998237713720036,
|
|
"loss": 6.3964,
|
|
"mean_token_accuracy": 0.14275107234716417,
|
|
"num_tokens": 4504310.0,
|
|
"step": 2415
|
|
},
|
|
{
|
|
"entropy": 6.4785685539245605,
|
|
"epoch": 0.2137054044507241,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998225230198552,
|
|
"loss": 6.2939,
|
|
"mean_token_accuracy": 0.1452530562877655,
|
|
"num_tokens": 4513217.0,
|
|
"step": 2420
|
|
},
|
|
{
|
|
"entropy": 6.5528992176055905,
|
|
"epoch": 0.21414694454256447,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998212702635614,
|
|
"loss": 6.365,
|
|
"mean_token_accuracy": 0.13781265765428544,
|
|
"num_tokens": 4521746.0,
|
|
"step": 2425
|
|
},
|
|
{
|
|
"entropy": 6.4305943012237545,
|
|
"epoch": 0.2145884846344048,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004998200131031469,
|
|
"loss": 6.2658,
|
|
"mean_token_accuracy": 0.14664409756660463,
|
|
"num_tokens": 4531244.0,
|
|
"step": 2430
|
|
},
|
|
{
|
|
"entropy": 6.574305582046509,
|
|
"epoch": 0.21503002472624513,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998187515386361,
|
|
"loss": 6.2638,
|
|
"mean_token_accuracy": 0.14604247286915778,
|
|
"num_tokens": 4540065.0,
|
|
"step": 2435
|
|
},
|
|
{
|
|
"entropy": 6.408740425109864,
|
|
"epoch": 0.2154715648180855,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004998174855700538,
|
|
"loss": 6.344,
|
|
"mean_token_accuracy": 0.1382213518023491,
|
|
"num_tokens": 4549691.0,
|
|
"step": 2440
|
|
},
|
|
{
|
|
"entropy": 6.517018890380859,
|
|
"epoch": 0.21591310490992582,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004998162151974248,
|
|
"loss": 6.2199,
|
|
"mean_token_accuracy": 0.14915743321180344,
|
|
"num_tokens": 4559311.0,
|
|
"step": 2445
|
|
},
|
|
{
|
|
"entropy": 6.559193229675293,
|
|
"epoch": 0.21635464500176615,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000499814940420774,
|
|
"loss": 6.3878,
|
|
"mean_token_accuracy": 0.14189895316958429,
|
|
"num_tokens": 4569243.0,
|
|
"step": 2450
|
|
},
|
|
{
|
|
"entropy": 6.393787431716919,
|
|
"epoch": 0.21679618509360649,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004998136612401266,
|
|
"loss": 6.326,
|
|
"mean_token_accuracy": 0.1409069925546646,
|
|
"num_tokens": 4578898.0,
|
|
"step": 2455
|
|
},
|
|
{
|
|
"entropy": 6.48945894241333,
|
|
"epoch": 0.21723772518544684,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004998123776555071,
|
|
"loss": 6.3673,
|
|
"mean_token_accuracy": 0.143455608189106,
|
|
"num_tokens": 4588443.0,
|
|
"step": 2460
|
|
},
|
|
{
|
|
"entropy": 6.497863721847534,
|
|
"epoch": 0.21767926527728718,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004998110896669412,
|
|
"loss": 6.3381,
|
|
"mean_token_accuracy": 0.13771693482995034,
|
|
"num_tokens": 4599333.0,
|
|
"step": 2465
|
|
},
|
|
{
|
|
"entropy": 6.558657217025757,
|
|
"epoch": 0.2181208053691275,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004998097972744539,
|
|
"loss": 6.3569,
|
|
"mean_token_accuracy": 0.14392640367150306,
|
|
"num_tokens": 4608287.0,
|
|
"step": 2470
|
|
},
|
|
{
|
|
"entropy": 6.453986263275146,
|
|
"epoch": 0.21856234546096787,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998085004780705,
|
|
"loss": 6.2777,
|
|
"mean_token_accuracy": 0.14240417033433914,
|
|
"num_tokens": 4616849.0,
|
|
"step": 2475
|
|
},
|
|
{
|
|
"entropy": 6.480883169174194,
|
|
"epoch": 0.2190038855528082,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004998071992778164,
|
|
"loss": 6.2876,
|
|
"mean_token_accuracy": 0.14548520371317863,
|
|
"num_tokens": 4625830.0,
|
|
"step": 2480
|
|
},
|
|
{
|
|
"entropy": 6.467753934860229,
|
|
"epoch": 0.21944542564464853,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.000499805893673717,
|
|
"loss": 6.3282,
|
|
"mean_token_accuracy": 0.14801275581121445,
|
|
"num_tokens": 4635404.0,
|
|
"step": 2485
|
|
},
|
|
{
|
|
"entropy": 6.565742492675781,
|
|
"epoch": 0.21988696573648886,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004998045836657982,
|
|
"loss": 6.3555,
|
|
"mean_token_accuracy": 0.14250202104449272,
|
|
"num_tokens": 4644422.0,
|
|
"step": 2490
|
|
},
|
|
{
|
|
"entropy": 6.506637191772461,
|
|
"epoch": 0.22032850582832922,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004998032692540853,
|
|
"loss": 6.3906,
|
|
"mean_token_accuracy": 0.13982019126415252,
|
|
"num_tokens": 4653641.0,
|
|
"step": 2495
|
|
},
|
|
{
|
|
"entropy": 6.542034721374511,
|
|
"epoch": 0.22077004592016955,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004998019504386044,
|
|
"loss": 6.3289,
|
|
"mean_token_accuracy": 0.143229641020298,
|
|
"num_tokens": 4662999.0,
|
|
"step": 2500
|
|
},
|
|
{
|
|
"entropy": 6.514064455032349,
|
|
"epoch": 0.22121158601200988,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004998006272193809,
|
|
"loss": 6.3434,
|
|
"mean_token_accuracy": 0.1452925592660904,
|
|
"num_tokens": 4672587.0,
|
|
"step": 2505
|
|
},
|
|
{
|
|
"entropy": 6.424850225448608,
|
|
"epoch": 0.22165312610385024,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004997992995964412,
|
|
"loss": 6.2687,
|
|
"mean_token_accuracy": 0.14280916899442672,
|
|
"num_tokens": 4682504.0,
|
|
"step": 2510
|
|
},
|
|
{
|
|
"entropy": 6.46969838142395,
|
|
"epoch": 0.22209466619569057,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004997979675698109,
|
|
"loss": 6.3981,
|
|
"mean_token_accuracy": 0.14228205978870392,
|
|
"num_tokens": 4691728.0,
|
|
"step": 2515
|
|
},
|
|
{
|
|
"entropy": 6.499358606338501,
|
|
"epoch": 0.2225362062875309,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004997966311395164,
|
|
"loss": 6.2038,
|
|
"mean_token_accuracy": 0.15347035229206085,
|
|
"num_tokens": 4701169.0,
|
|
"step": 2520
|
|
},
|
|
{
|
|
"entropy": 6.416709661483765,
|
|
"epoch": 0.22297774637937123,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004997952903055836,
|
|
"loss": 6.225,
|
|
"mean_token_accuracy": 0.1492363281548023,
|
|
"num_tokens": 4711050.0,
|
|
"step": 2525
|
|
},
|
|
{
|
|
"entropy": 6.540422153472901,
|
|
"epoch": 0.2234192864712116,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000499793945068039,
|
|
"loss": 6.3515,
|
|
"mean_token_accuracy": 0.14371454566717148,
|
|
"num_tokens": 4720520.0,
|
|
"step": 2530
|
|
},
|
|
{
|
|
"entropy": 6.360270595550537,
|
|
"epoch": 0.22386082656305192,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004997925954269088,
|
|
"loss": 6.2195,
|
|
"mean_token_accuracy": 0.1561760887503624,
|
|
"num_tokens": 4729446.0,
|
|
"step": 2535
|
|
},
|
|
{
|
|
"entropy": 6.379441928863526,
|
|
"epoch": 0.22430236665489225,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004997912413822196,
|
|
"loss": 6.3196,
|
|
"mean_token_accuracy": 0.14638870134949683,
|
|
"num_tokens": 4739294.0,
|
|
"step": 2540
|
|
},
|
|
{
|
|
"entropy": 6.594422245025635,
|
|
"epoch": 0.2247439067467326,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004997898829339979,
|
|
"loss": 6.2911,
|
|
"mean_token_accuracy": 0.14837272465229034,
|
|
"num_tokens": 4747764.0,
|
|
"step": 2545
|
|
},
|
|
{
|
|
"entropy": 6.369044256210327,
|
|
"epoch": 0.22518544683857294,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00049978852008227,
|
|
"loss": 6.2216,
|
|
"mean_token_accuracy": 0.1513258472084999,
|
|
"num_tokens": 4756647.0,
|
|
"step": 2550
|
|
},
|
|
{
|
|
"entropy": 6.45693073272705,
|
|
"epoch": 0.22562698693041328,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.000499787152827063,
|
|
"loss": 6.2796,
|
|
"mean_token_accuracy": 0.14629189819097518,
|
|
"num_tokens": 4765907.0,
|
|
"step": 2555
|
|
},
|
|
{
|
|
"entropy": 6.52665147781372,
|
|
"epoch": 0.2260685270222536,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004997857811684035,
|
|
"loss": 6.3609,
|
|
"mean_token_accuracy": 0.14549251645803452,
|
|
"num_tokens": 4774670.0,
|
|
"step": 2560
|
|
},
|
|
{
|
|
"entropy": 6.445423984527588,
|
|
"epoch": 0.22651006711409397,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004997844051063183,
|
|
"loss": 6.2632,
|
|
"mean_token_accuracy": 0.15502836257219316,
|
|
"num_tokens": 4783662.0,
|
|
"step": 2565
|
|
},
|
|
{
|
|
"entropy": 6.455739736557007,
|
|
"epoch": 0.2269516072059343,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004997830246408346,
|
|
"loss": 6.2772,
|
|
"mean_token_accuracy": 0.14837741404771804,
|
|
"num_tokens": 4794352.0,
|
|
"step": 2570
|
|
},
|
|
{
|
|
"entropy": 6.368543529510498,
|
|
"epoch": 0.22739314729777463,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004997816397719791,
|
|
"loss": 6.2842,
|
|
"mean_token_accuracy": 0.14470751956105232,
|
|
"num_tokens": 4805185.0,
|
|
"step": 2575
|
|
},
|
|
{
|
|
"entropy": 6.49798994064331,
|
|
"epoch": 0.227834687389615,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004997802504997792,
|
|
"loss": 6.2227,
|
|
"mean_token_accuracy": 0.1516940973699093,
|
|
"num_tokens": 4814178.0,
|
|
"step": 2580
|
|
},
|
|
{
|
|
"entropy": 6.3884289264678955,
|
|
"epoch": 0.22827622748145532,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004997788568242621,
|
|
"loss": 6.2732,
|
|
"mean_token_accuracy": 0.15293048024177552,
|
|
"num_tokens": 4822634.0,
|
|
"step": 2585
|
|
},
|
|
{
|
|
"entropy": 6.4718101024627686,
|
|
"epoch": 0.22871776757329565,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000499777458745455,
|
|
"loss": 6.2981,
|
|
"mean_token_accuracy": 0.14538061991333961,
|
|
"num_tokens": 4831892.0,
|
|
"step": 2590
|
|
},
|
|
{
|
|
"entropy": 6.53868556022644,
|
|
"epoch": 0.22915930766513598,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004997760562633853,
|
|
"loss": 6.2461,
|
|
"mean_token_accuracy": 0.14104571789503098,
|
|
"num_tokens": 4840585.0,
|
|
"step": 2595
|
|
},
|
|
{
|
|
"entropy": 6.3369544506072994,
|
|
"epoch": 0.22960084775697634,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004997746493780804,
|
|
"loss": 6.2662,
|
|
"mean_token_accuracy": 0.14956960678100586,
|
|
"num_tokens": 4849680.0,
|
|
"step": 2600
|
|
},
|
|
{
|
|
"entropy": 6.402548980712891,
|
|
"epoch": 0.23004238784881667,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000499773238089568,
|
|
"loss": 6.1946,
|
|
"mean_token_accuracy": 0.15193643122911454,
|
|
"num_tokens": 4858935.0,
|
|
"step": 2605
|
|
},
|
|
{
|
|
"entropy": 6.451043272018433,
|
|
"epoch": 0.230483927940657,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004997718223978758,
|
|
"loss": 6.2793,
|
|
"mean_token_accuracy": 0.15012711733579637,
|
|
"num_tokens": 4868612.0,
|
|
"step": 2610
|
|
},
|
|
{
|
|
"entropy": 6.471085453033448,
|
|
"epoch": 0.23092546803249736,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004997704023030315,
|
|
"loss": 6.3092,
|
|
"mean_token_accuracy": 0.14472778290510177,
|
|
"num_tokens": 4876923.0,
|
|
"step": 2615
|
|
},
|
|
{
|
|
"entropy": 6.488173103332519,
|
|
"epoch": 0.2313670081243377,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004997689778050627,
|
|
"loss": 6.3912,
|
|
"mean_token_accuracy": 0.1424463249742985,
|
|
"num_tokens": 4886683.0,
|
|
"step": 2620
|
|
},
|
|
{
|
|
"entropy": 6.476648426055908,
|
|
"epoch": 0.23180854821617802,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004997675489039975,
|
|
"loss": 6.2493,
|
|
"mean_token_accuracy": 0.14954889714717864,
|
|
"num_tokens": 4895877.0,
|
|
"step": 2625
|
|
},
|
|
{
|
|
"entropy": 6.476872062683105,
|
|
"epoch": 0.23225008830801835,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004997661155998638,
|
|
"loss": 6.3645,
|
|
"mean_token_accuracy": 0.1469063326716423,
|
|
"num_tokens": 4904929.0,
|
|
"step": 2630
|
|
},
|
|
{
|
|
"entropy": 6.5085193634033205,
|
|
"epoch": 0.2326916283998587,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004997646778926898,
|
|
"loss": 6.2951,
|
|
"mean_token_accuracy": 0.14097197651863097,
|
|
"num_tokens": 4913157.0,
|
|
"step": 2635
|
|
},
|
|
{
|
|
"entropy": 6.490143060684204,
|
|
"epoch": 0.23313316849169904,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004997632357825035,
|
|
"loss": 6.3681,
|
|
"mean_token_accuracy": 0.13852858543395996,
|
|
"num_tokens": 4923791.0,
|
|
"step": 2640
|
|
},
|
|
{
|
|
"entropy": 6.4098340511322025,
|
|
"epoch": 0.23357470858353938,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004997617892693333,
|
|
"loss": 6.2606,
|
|
"mean_token_accuracy": 0.1469244882464409,
|
|
"num_tokens": 4933184.0,
|
|
"step": 2645
|
|
},
|
|
{
|
|
"entropy": 6.462233257293701,
|
|
"epoch": 0.23401624867537973,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004997603383532075,
|
|
"loss": 6.2178,
|
|
"mean_token_accuracy": 0.15098182260990142,
|
|
"num_tokens": 4941833.0,
|
|
"step": 2650
|
|
},
|
|
{
|
|
"entropy": 6.405755138397216,
|
|
"epoch": 0.23445778876722007,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004997588830341545,
|
|
"loss": 6.1816,
|
|
"mean_token_accuracy": 0.15357830375432968,
|
|
"num_tokens": 4950942.0,
|
|
"step": 2655
|
|
},
|
|
{
|
|
"entropy": 6.4815491199493405,
|
|
"epoch": 0.2348993288590604,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004997574233122028,
|
|
"loss": 6.3526,
|
|
"mean_token_accuracy": 0.1432811886072159,
|
|
"num_tokens": 4962005.0,
|
|
"step": 2660
|
|
},
|
|
{
|
|
"entropy": 6.4480256080627445,
|
|
"epoch": 0.23534086895090076,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004997559591873809,
|
|
"loss": 6.2118,
|
|
"mean_token_accuracy": 0.15217095017433166,
|
|
"num_tokens": 4970965.0,
|
|
"step": 2665
|
|
},
|
|
{
|
|
"entropy": 6.428168153762817,
|
|
"epoch": 0.2357824090427411,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004997544906597178,
|
|
"loss": 6.2401,
|
|
"mean_token_accuracy": 0.14764407500624657,
|
|
"num_tokens": 4980460.0,
|
|
"step": 2670
|
|
},
|
|
{
|
|
"entropy": 6.38992223739624,
|
|
"epoch": 0.23622394913458142,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004997530177292418,
|
|
"loss": 6.1835,
|
|
"mean_token_accuracy": 0.1445123538374901,
|
|
"num_tokens": 4989343.0,
|
|
"step": 2675
|
|
},
|
|
{
|
|
"entropy": 6.2847757816314695,
|
|
"epoch": 0.23666548922642175,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004997515403959823,
|
|
"loss": 6.2281,
|
|
"mean_token_accuracy": 0.14587305262684822,
|
|
"num_tokens": 4998881.0,
|
|
"step": 2680
|
|
},
|
|
{
|
|
"entropy": 6.461613607406616,
|
|
"epoch": 0.2371070293182621,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004997500586599677,
|
|
"loss": 6.292,
|
|
"mean_token_accuracy": 0.14370835274457933,
|
|
"num_tokens": 5008368.0,
|
|
"step": 2685
|
|
},
|
|
{
|
|
"entropy": 6.479917383193969,
|
|
"epoch": 0.23754856941010244,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004997485725212274,
|
|
"loss": 6.3201,
|
|
"mean_token_accuracy": 0.15082732439041138,
|
|
"num_tokens": 5017904.0,
|
|
"step": 2690
|
|
},
|
|
{
|
|
"entropy": 6.5032206058502195,
|
|
"epoch": 0.23799010950194277,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004997470819797903,
|
|
"loss": 6.2612,
|
|
"mean_token_accuracy": 0.15601224899291993,
|
|
"num_tokens": 5026836.0,
|
|
"step": 2695
|
|
},
|
|
{
|
|
"entropy": 6.387510490417481,
|
|
"epoch": 0.23843164959378313,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004997455870356857,
|
|
"loss": 6.2253,
|
|
"mean_token_accuracy": 0.14688334614038467,
|
|
"num_tokens": 5035621.0,
|
|
"step": 2700
|
|
},
|
|
{
|
|
"entropy": 6.4787116050720215,
|
|
"epoch": 0.23887318968562346,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004997440876889429,
|
|
"loss": 6.2895,
|
|
"mean_token_accuracy": 0.1482943207025528,
|
|
"num_tokens": 5044076.0,
|
|
"step": 2705
|
|
},
|
|
{
|
|
"entropy": 6.492949533462524,
|
|
"epoch": 0.2393147297774638,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004997425839395913,
|
|
"loss": 6.3029,
|
|
"mean_token_accuracy": 0.14274363666772844,
|
|
"num_tokens": 5053931.0,
|
|
"step": 2710
|
|
},
|
|
{
|
|
"entropy": 6.3609747886657715,
|
|
"epoch": 0.23975626986930412,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004997410757876602,
|
|
"loss": 6.2358,
|
|
"mean_token_accuracy": 0.15066074430942536,
|
|
"num_tokens": 5063969.0,
|
|
"step": 2715
|
|
},
|
|
{
|
|
"entropy": 6.469989538192749,
|
|
"epoch": 0.24019780996114448,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004997395632331793,
|
|
"loss": 6.3041,
|
|
"mean_token_accuracy": 0.1426872693002224,
|
|
"num_tokens": 5073253.0,
|
|
"step": 2720
|
|
},
|
|
{
|
|
"entropy": 6.411794424057007,
|
|
"epoch": 0.2406393500529848,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004997380462761781,
|
|
"loss": 6.2456,
|
|
"mean_token_accuracy": 0.1446852631866932,
|
|
"num_tokens": 5082673.0,
|
|
"step": 2725
|
|
},
|
|
{
|
|
"entropy": 6.405149459838867,
|
|
"epoch": 0.24108089014482514,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004997365249166864,
|
|
"loss": 6.2601,
|
|
"mean_token_accuracy": 0.15146871134638787,
|
|
"num_tokens": 5092040.0,
|
|
"step": 2730
|
|
},
|
|
{
|
|
"entropy": 6.448270606994629,
|
|
"epoch": 0.2415224302366655,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004997349991547342,
|
|
"loss": 6.2359,
|
|
"mean_token_accuracy": 0.14747195094823837,
|
|
"num_tokens": 5101942.0,
|
|
"step": 2735
|
|
},
|
|
{
|
|
"entropy": 6.3382261276245115,
|
|
"epoch": 0.24196397032850583,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004997334689903509,
|
|
"loss": 6.2302,
|
|
"mean_token_accuracy": 0.15405145585536956,
|
|
"num_tokens": 5111081.0,
|
|
"step": 2740
|
|
},
|
|
{
|
|
"entropy": 6.4858105182647705,
|
|
"epoch": 0.24240551042034617,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004997319344235668,
|
|
"loss": 6.2757,
|
|
"mean_token_accuracy": 0.1433402493596077,
|
|
"num_tokens": 5120250.0,
|
|
"step": 2745
|
|
},
|
|
{
|
|
"entropy": 6.476590394973755,
|
|
"epoch": 0.2428470505121865,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.000499730395454412,
|
|
"loss": 6.3262,
|
|
"mean_token_accuracy": 0.13439106568694115,
|
|
"num_tokens": 5130090.0,
|
|
"step": 2750
|
|
},
|
|
{
|
|
"entropy": 6.378527879714966,
|
|
"epoch": 0.24328859060402686,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004997288520829166,
|
|
"loss": 6.2372,
|
|
"mean_token_accuracy": 0.14988442063331603,
|
|
"num_tokens": 5138680.0,
|
|
"step": 2755
|
|
},
|
|
{
|
|
"entropy": 6.441170692443848,
|
|
"epoch": 0.2437301306958672,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004997273043091107,
|
|
"loss": 6.304,
|
|
"mean_token_accuracy": 0.1427198089659214,
|
|
"num_tokens": 5150025.0,
|
|
"step": 2760
|
|
},
|
|
{
|
|
"entropy": 6.356282091140747,
|
|
"epoch": 0.24417167078770752,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004997257521330248,
|
|
"loss": 6.1376,
|
|
"mean_token_accuracy": 0.15772749930620195,
|
|
"num_tokens": 5159159.0,
|
|
"step": 2765
|
|
},
|
|
{
|
|
"entropy": 6.350546789169312,
|
|
"epoch": 0.24461321087954788,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004997241955546892,
|
|
"loss": 6.3025,
|
|
"mean_token_accuracy": 0.1383981317281723,
|
|
"num_tokens": 5168584.0,
|
|
"step": 2770
|
|
},
|
|
{
|
|
"entropy": 6.4935712814331055,
|
|
"epoch": 0.2450547509713882,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004997226345741343,
|
|
"loss": 6.2395,
|
|
"mean_token_accuracy": 0.14813449531793593,
|
|
"num_tokens": 5177804.0,
|
|
"step": 2775
|
|
},
|
|
{
|
|
"entropy": 6.330422210693359,
|
|
"epoch": 0.24549629106322854,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000499721069191391,
|
|
"loss": 6.1723,
|
|
"mean_token_accuracy": 0.15173402577638626,
|
|
"num_tokens": 5187022.0,
|
|
"step": 2780
|
|
},
|
|
{
|
|
"entropy": 6.383345079421997,
|
|
"epoch": 0.24593783115506887,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004997194994064896,
|
|
"loss": 6.1975,
|
|
"mean_token_accuracy": 0.15482074320316314,
|
|
"num_tokens": 5195882.0,
|
|
"step": 2785
|
|
},
|
|
{
|
|
"entropy": 6.353169202804565,
|
|
"epoch": 0.24637937124690923,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000499717925219461,
|
|
"loss": 6.1664,
|
|
"mean_token_accuracy": 0.14942888617515565,
|
|
"num_tokens": 5204401.0,
|
|
"step": 2790
|
|
},
|
|
{
|
|
"entropy": 6.470758771896362,
|
|
"epoch": 0.24682091133874956,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004997163466303362,
|
|
"loss": 6.1492,
|
|
"mean_token_accuracy": 0.15647954791784285,
|
|
"num_tokens": 5214262.0,
|
|
"step": 2795
|
|
},
|
|
{
|
|
"entropy": 6.308819770812988,
|
|
"epoch": 0.2472624514305899,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000499714763639146,
|
|
"loss": 6.2008,
|
|
"mean_token_accuracy": 0.14968698844313622,
|
|
"num_tokens": 5223871.0,
|
|
"step": 2800
|
|
},
|
|
{
|
|
"entropy": 6.387062311172485,
|
|
"epoch": 0.24770399152243025,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004997131762459211,
|
|
"loss": 6.2141,
|
|
"mean_token_accuracy": 0.15620359778404236,
|
|
"num_tokens": 5233395.0,
|
|
"step": 2805
|
|
},
|
|
{
|
|
"entropy": 6.389224910736084,
|
|
"epoch": 0.24814553161427058,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004997115844506932,
|
|
"loss": 6.1637,
|
|
"mean_token_accuracy": 0.15392670035362244,
|
|
"num_tokens": 5243184.0,
|
|
"step": 2810
|
|
},
|
|
{
|
|
"entropy": 6.247744512557984,
|
|
"epoch": 0.2485870717061109,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004997099882534929,
|
|
"loss": 6.0597,
|
|
"mean_token_accuracy": 0.16176963746547698,
|
|
"num_tokens": 5252851.0,
|
|
"step": 2815
|
|
},
|
|
{
|
|
"entropy": 6.453801250457763,
|
|
"epoch": 0.24902861179795124,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004997083876543519,
|
|
"loss": 6.2417,
|
|
"mean_token_accuracy": 0.14792601466178895,
|
|
"num_tokens": 5261870.0,
|
|
"step": 2820
|
|
},
|
|
{
|
|
"entropy": 6.370384979248047,
|
|
"epoch": 0.2494701518897916,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004997067826533014,
|
|
"loss": 6.1957,
|
|
"mean_token_accuracy": 0.1431150496006012,
|
|
"num_tokens": 5271639.0,
|
|
"step": 2825
|
|
},
|
|
{
|
|
"entropy": 6.440698575973511,
|
|
"epoch": 0.24991169198163193,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004997051732503726,
|
|
"loss": 6.2035,
|
|
"mean_token_accuracy": 0.14459088742733,
|
|
"num_tokens": 5280746.0,
|
|
"step": 2830
|
|
},
|
|
{
|
|
"entropy": 6.372076845169067,
|
|
"epoch": 0.25035323207347226,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004997035594455975,
|
|
"loss": 6.2268,
|
|
"mean_token_accuracy": 0.14702461585402488,
|
|
"num_tokens": 5290201.0,
|
|
"step": 2835
|
|
},
|
|
{
|
|
"entropy": 6.380630159378052,
|
|
"epoch": 0.2507947721653126,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004997019412390074,
|
|
"loss": 6.2107,
|
|
"mean_token_accuracy": 0.15259625762701035,
|
|
"num_tokens": 5300336.0,
|
|
"step": 2840
|
|
},
|
|
{
|
|
"entropy": 6.392699670791626,
|
|
"epoch": 0.2512363122571529,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000499700318630634,
|
|
"loss": 6.2537,
|
|
"mean_token_accuracy": 0.14918554574251175,
|
|
"num_tokens": 5309174.0,
|
|
"step": 2845
|
|
},
|
|
{
|
|
"entropy": 6.462964773178101,
|
|
"epoch": 0.2516778523489933,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004996986916205092,
|
|
"loss": 6.3122,
|
|
"mean_token_accuracy": 0.14475011378526687,
|
|
"num_tokens": 5317702.0,
|
|
"step": 2850
|
|
},
|
|
{
|
|
"entropy": 6.428555202484131,
|
|
"epoch": 0.25211939244083365,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004996970602086648,
|
|
"loss": 6.2571,
|
|
"mean_token_accuracy": 0.1455409847199917,
|
|
"num_tokens": 5326838.0,
|
|
"step": 2855
|
|
},
|
|
{
|
|
"entropy": 6.358886051177978,
|
|
"epoch": 0.252560932532674,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004996954243951327,
|
|
"loss": 6.1463,
|
|
"mean_token_accuracy": 0.15396089106798172,
|
|
"num_tokens": 5335679.0,
|
|
"step": 2860
|
|
},
|
|
{
|
|
"entropy": 6.4643134593963625,
|
|
"epoch": 0.2530024726245143,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004996937841799451,
|
|
"loss": 6.2858,
|
|
"mean_token_accuracy": 0.15384045615792274,
|
|
"num_tokens": 5344670.0,
|
|
"step": 2865
|
|
},
|
|
{
|
|
"entropy": 6.345240116119385,
|
|
"epoch": 0.25344401271635464,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004996921395631342,
|
|
"loss": 6.1141,
|
|
"mean_token_accuracy": 0.15072092190384864,
|
|
"num_tokens": 5353501.0,
|
|
"step": 2870
|
|
},
|
|
{
|
|
"entropy": 6.391109418869019,
|
|
"epoch": 0.25388555280819497,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.000499690490544732,
|
|
"loss": 6.2151,
|
|
"mean_token_accuracy": 0.15420024394989013,
|
|
"num_tokens": 5362778.0,
|
|
"step": 2875
|
|
},
|
|
{
|
|
"entropy": 6.355072355270385,
|
|
"epoch": 0.2543270929000353,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004996888371247707,
|
|
"loss": 6.187,
|
|
"mean_token_accuracy": 0.15069863200187683,
|
|
"num_tokens": 5371231.0,
|
|
"step": 2880
|
|
},
|
|
{
|
|
"entropy": 6.396897888183593,
|
|
"epoch": 0.2547686329918757,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.000499687179303283,
|
|
"loss": 6.2352,
|
|
"mean_token_accuracy": 0.14393327459692956,
|
|
"num_tokens": 5380655.0,
|
|
"step": 2885
|
|
},
|
|
{
|
|
"entropy": 6.39494571685791,
|
|
"epoch": 0.255210173083716,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004996855170803012,
|
|
"loss": 6.2326,
|
|
"mean_token_accuracy": 0.14647915214300156,
|
|
"num_tokens": 5390269.0,
|
|
"step": 2890
|
|
},
|
|
{
|
|
"entropy": 6.329206228256226,
|
|
"epoch": 0.25565171317555635,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004996838504558581,
|
|
"loss": 6.0774,
|
|
"mean_token_accuracy": 0.1588391736149788,
|
|
"num_tokens": 5398348.0,
|
|
"step": 2895
|
|
},
|
|
{
|
|
"entropy": 6.267703342437744,
|
|
"epoch": 0.2560932532673967,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.000499682179429986,
|
|
"loss": 6.2315,
|
|
"mean_token_accuracy": 0.15087486952543258,
|
|
"num_tokens": 5408294.0,
|
|
"step": 2900
|
|
},
|
|
{
|
|
"entropy": 6.416153049468994,
|
|
"epoch": 0.256534793359237,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004996805040027178,
|
|
"loss": 6.2348,
|
|
"mean_token_accuracy": 0.15022216588258744,
|
|
"num_tokens": 5418301.0,
|
|
"step": 2905
|
|
},
|
|
{
|
|
"entropy": 6.394410037994385,
|
|
"epoch": 0.25697633345107734,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004996788241740863,
|
|
"loss": 6.3045,
|
|
"mean_token_accuracy": 0.1489267498254776,
|
|
"num_tokens": 5427990.0,
|
|
"step": 2910
|
|
},
|
|
{
|
|
"entropy": 6.474830102920532,
|
|
"epoch": 0.2574178735429177,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004996771399441243,
|
|
"loss": 6.2283,
|
|
"mean_token_accuracy": 0.1464369684457779,
|
|
"num_tokens": 5437140.0,
|
|
"step": 2915
|
|
},
|
|
{
|
|
"entropy": 6.340023994445801,
|
|
"epoch": 0.25785941363475806,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004996754513128652,
|
|
"loss": 6.1935,
|
|
"mean_token_accuracy": 0.15139320865273476,
|
|
"num_tokens": 5445832.0,
|
|
"step": 2920
|
|
},
|
|
{
|
|
"entropy": 6.317194700241089,
|
|
"epoch": 0.2583009537265984,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004996737582803416,
|
|
"loss": 6.2144,
|
|
"mean_token_accuracy": 0.1541209414601326,
|
|
"num_tokens": 5455359.0,
|
|
"step": 2925
|
|
},
|
|
{
|
|
"entropy": 6.433325910568238,
|
|
"epoch": 0.2587424938184387,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004996720608465868,
|
|
"loss": 6.2866,
|
|
"mean_token_accuracy": 0.1430448040366173,
|
|
"num_tokens": 5465055.0,
|
|
"step": 2930
|
|
},
|
|
{
|
|
"entropy": 6.408900499343872,
|
|
"epoch": 0.25918403391027905,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004996703590116342,
|
|
"loss": 6.2059,
|
|
"mean_token_accuracy": 0.15415119379758835,
|
|
"num_tokens": 5474048.0,
|
|
"step": 2935
|
|
},
|
|
{
|
|
"entropy": 6.290044689178467,
|
|
"epoch": 0.2596255740021194,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004996686527755171,
|
|
"loss": 6.0412,
|
|
"mean_token_accuracy": 0.1648414745926857,
|
|
"num_tokens": 5483025.0,
|
|
"step": 2940
|
|
},
|
|
{
|
|
"entropy": 6.291623878479004,
|
|
"epoch": 0.2600671140939597,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004996669421382687,
|
|
"loss": 6.1957,
|
|
"mean_token_accuracy": 0.15358467102050782,
|
|
"num_tokens": 5492001.0,
|
|
"step": 2945
|
|
},
|
|
{
|
|
"entropy": 6.4285280227661135,
|
|
"epoch": 0.26050865418580005,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004996652270999228,
|
|
"loss": 6.2239,
|
|
"mean_token_accuracy": 0.14998335987329484,
|
|
"num_tokens": 5502524.0,
|
|
"step": 2950
|
|
},
|
|
{
|
|
"entropy": 6.320462036132812,
|
|
"epoch": 0.26095019427764043,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004996635076605128,
|
|
"loss": 6.1768,
|
|
"mean_token_accuracy": 0.1475066915154457,
|
|
"num_tokens": 5511526.0,
|
|
"step": 2955
|
|
},
|
|
{
|
|
"entropy": 6.406644201278686,
|
|
"epoch": 0.26139173436948077,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004996617838200725,
|
|
"loss": 6.2645,
|
|
"mean_token_accuracy": 0.14729123413562775,
|
|
"num_tokens": 5520577.0,
|
|
"step": 2960
|
|
},
|
|
{
|
|
"entropy": 6.391732931137085,
|
|
"epoch": 0.2618332744613211,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004996600555786357,
|
|
"loss": 6.155,
|
|
"mean_token_accuracy": 0.15534588098526,
|
|
"num_tokens": 5529681.0,
|
|
"step": 2965
|
|
},
|
|
{
|
|
"entropy": 6.326655769348145,
|
|
"epoch": 0.26227481455316143,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004996583229362362,
|
|
"loss": 6.2055,
|
|
"mean_token_accuracy": 0.14942387789487838,
|
|
"num_tokens": 5538984.0,
|
|
"step": 2970
|
|
},
|
|
{
|
|
"entropy": 6.3987696170806885,
|
|
"epoch": 0.26271635464500176,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004996565858929078,
|
|
"loss": 6.2258,
|
|
"mean_token_accuracy": 0.1435547314584255,
|
|
"num_tokens": 5548593.0,
|
|
"step": 2975
|
|
},
|
|
{
|
|
"entropy": 6.368779802322388,
|
|
"epoch": 0.2631578947368421,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004996548444486847,
|
|
"loss": 6.1997,
|
|
"mean_token_accuracy": 0.15220200568437575,
|
|
"num_tokens": 5557584.0,
|
|
"step": 2980
|
|
},
|
|
{
|
|
"entropy": 6.44010329246521,
|
|
"epoch": 0.2635994348286824,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004996530986036008,
|
|
"loss": 6.2569,
|
|
"mean_token_accuracy": 0.14837291613221168,
|
|
"num_tokens": 5567438.0,
|
|
"step": 2985
|
|
},
|
|
{
|
|
"entropy": 6.328577947616577,
|
|
"epoch": 0.2640409749205228,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004996513483576907,
|
|
"loss": 6.2752,
|
|
"mean_token_accuracy": 0.1468944802880287,
|
|
"num_tokens": 5577138.0,
|
|
"step": 2990
|
|
},
|
|
{
|
|
"entropy": 6.488377714157105,
|
|
"epoch": 0.26448251501236314,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004996495937109884,
|
|
"loss": 6.2327,
|
|
"mean_token_accuracy": 0.1452515721321106,
|
|
"num_tokens": 5586086.0,
|
|
"step": 2995
|
|
},
|
|
{
|
|
"entropy": 6.347766876220703,
|
|
"epoch": 0.26492405510420347,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004996478346635283,
|
|
"loss": 6.2034,
|
|
"mean_token_accuracy": 0.1538815215229988,
|
|
"num_tokens": 5594991.0,
|
|
"step": 3000
|
|
},
|
|
{
|
|
"epoch": 0.26492405510420347,
|
|
"eval_entropy": 6.11064261509905,
|
|
"eval_loss": 6.222682952880859,
|
|
"eval_mean_token_accuracy": 0.15619063689225773,
|
|
"eval_num_tokens": 5594991.0,
|
|
"eval_runtime": 20.7082,
|
|
"eval_samples_per_second": 1705.363,
|
|
"eval_steps_per_second": 213.201,
|
|
"step": 3000
|
|
}
|
|
],
|
|
"logging_steps": 5,
|
|
"max_steps": 113230,
|
|
"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": 1225184707215360.0,
|
|
"train_batch_size": 16,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|