8035 lines
219 KiB
JSON
8035 lines
219 KiB
JSON
{
|
|
"best_global_step": null,
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 0.264366676580417,
|
|
"eval_steps": 500,
|
|
"global_step": 4000,
|
|
"is_hyper_param_search": false,
|
|
"is_local_process_zero": true,
|
|
"is_world_process_zero": true,
|
|
"log_history": [
|
|
{
|
|
"entropy": 10.69155969619751,
|
|
"epoch": 0.0003304583457255213,
|
|
"grad_norm": 12.8125,
|
|
"learning_rate": 2e-06,
|
|
"loss": 10.8103,
|
|
"mean_token_accuracy": 0.0,
|
|
"num_tokens": 10836.0,
|
|
"step": 5
|
|
},
|
|
{
|
|
"entropy": 10.69160442352295,
|
|
"epoch": 0.0006609166914510426,
|
|
"grad_norm": 10.9375,
|
|
"learning_rate": 4.5e-06,
|
|
"loss": 10.7287,
|
|
"mean_token_accuracy": 0.00010266940807923675,
|
|
"num_tokens": 20708.0,
|
|
"step": 10
|
|
},
|
|
{
|
|
"entropy": 10.691381645202636,
|
|
"epoch": 0.000991375037176564,
|
|
"grad_norm": 9.375,
|
|
"learning_rate": 7e-06,
|
|
"loss": 10.556,
|
|
"mean_token_accuracy": 0.012630514975171536,
|
|
"num_tokens": 32651.0,
|
|
"step": 15
|
|
},
|
|
{
|
|
"entropy": 10.685187435150146,
|
|
"epoch": 0.0013218333829020852,
|
|
"grad_norm": 6.25,
|
|
"learning_rate": 9.5e-06,
|
|
"loss": 10.2559,
|
|
"mean_token_accuracy": 0.04093300513923168,
|
|
"num_tokens": 43844.0,
|
|
"step": 20
|
|
},
|
|
{
|
|
"entropy": 10.628204250335694,
|
|
"epoch": 0.0016522917286276066,
|
|
"grad_norm": 3.9375,
|
|
"learning_rate": 1.2e-05,
|
|
"loss": 10.0415,
|
|
"mean_token_accuracy": 0.038726492412388326,
|
|
"num_tokens": 55019.0,
|
|
"step": 25
|
|
},
|
|
{
|
|
"entropy": 10.554113483428955,
|
|
"epoch": 0.001982750074353128,
|
|
"grad_norm": 3.140625,
|
|
"learning_rate": 1.4500000000000002e-05,
|
|
"loss": 9.8257,
|
|
"mean_token_accuracy": 0.048476964607834815,
|
|
"num_tokens": 66746.0,
|
|
"step": 30
|
|
},
|
|
{
|
|
"entropy": 10.590810203552246,
|
|
"epoch": 0.002313208420078649,
|
|
"grad_norm": 2.765625,
|
|
"learning_rate": 1.7000000000000003e-05,
|
|
"loss": 9.8306,
|
|
"mean_token_accuracy": 0.03930025473237038,
|
|
"num_tokens": 78821.0,
|
|
"step": 35
|
|
},
|
|
{
|
|
"entropy": 10.605837535858154,
|
|
"epoch": 0.0026436667658041703,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 1.95e-05,
|
|
"loss": 9.7593,
|
|
"mean_token_accuracy": 0.037112961150705816,
|
|
"num_tokens": 89051.0,
|
|
"step": 40
|
|
},
|
|
{
|
|
"entropy": 10.587123107910156,
|
|
"epoch": 0.0029741251115296915,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 2.2e-05,
|
|
"loss": 9.6663,
|
|
"mean_token_accuracy": 0.040811435878276826,
|
|
"num_tokens": 99691.0,
|
|
"step": 45
|
|
},
|
|
{
|
|
"entropy": 10.559133148193359,
|
|
"epoch": 0.003304583457255213,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 2.4500000000000003e-05,
|
|
"loss": 9.7075,
|
|
"mean_token_accuracy": 0.03913131728768349,
|
|
"num_tokens": 110614.0,
|
|
"step": 50
|
|
},
|
|
{
|
|
"entropy": 10.571648788452148,
|
|
"epoch": 0.0036350418029807343,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 2.7e-05,
|
|
"loss": 9.7135,
|
|
"mean_token_accuracy": 0.03680916838347912,
|
|
"num_tokens": 122915.0,
|
|
"step": 55
|
|
},
|
|
{
|
|
"entropy": 10.579666042327881,
|
|
"epoch": 0.003965500148706256,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 2.95e-05,
|
|
"loss": 9.5367,
|
|
"mean_token_accuracy": 0.040818646922707556,
|
|
"num_tokens": 132627.0,
|
|
"step": 60
|
|
},
|
|
{
|
|
"entropy": 10.55205478668213,
|
|
"epoch": 0.004295958494431777,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 3.2e-05,
|
|
"loss": 9.5003,
|
|
"mean_token_accuracy": 0.044149795174598695,
|
|
"num_tokens": 144317.0,
|
|
"step": 65
|
|
},
|
|
{
|
|
"entropy": 10.516563987731933,
|
|
"epoch": 0.004626416840157298,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 3.4500000000000005e-05,
|
|
"loss": 9.3204,
|
|
"mean_token_accuracy": 0.04889754429459572,
|
|
"num_tokens": 152798.0,
|
|
"step": 70
|
|
},
|
|
{
|
|
"entropy": 10.421174716949462,
|
|
"epoch": 0.00495687518588282,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 3.7e-05,
|
|
"loss": 9.2668,
|
|
"mean_token_accuracy": 0.04544033259153366,
|
|
"num_tokens": 162656.0,
|
|
"step": 75
|
|
},
|
|
{
|
|
"entropy": 10.396770095825195,
|
|
"epoch": 0.005287333531608341,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 3.95e-05,
|
|
"loss": 9.226,
|
|
"mean_token_accuracy": 0.050432728976011275,
|
|
"num_tokens": 173784.0,
|
|
"step": 80
|
|
},
|
|
{
|
|
"entropy": 10.419888401031494,
|
|
"epoch": 0.005617791877333862,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 4.2000000000000004e-05,
|
|
"loss": 9.1258,
|
|
"mean_token_accuracy": 0.0568363256752491,
|
|
"num_tokens": 184681.0,
|
|
"step": 85
|
|
},
|
|
{
|
|
"entropy": 10.358776760101318,
|
|
"epoch": 0.005948250223059383,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 4.45e-05,
|
|
"loss": 9.0169,
|
|
"mean_token_accuracy": 0.053509436920285224,
|
|
"num_tokens": 195307.0,
|
|
"step": 90
|
|
},
|
|
{
|
|
"entropy": 10.326674938201904,
|
|
"epoch": 0.006278708568784905,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 4.7000000000000004e-05,
|
|
"loss": 8.8921,
|
|
"mean_token_accuracy": 0.060885720700025556,
|
|
"num_tokens": 206857.0,
|
|
"step": 95
|
|
},
|
|
{
|
|
"entropy": 10.2583758354187,
|
|
"epoch": 0.006609166914510426,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 4.9500000000000004e-05,
|
|
"loss": 8.8016,
|
|
"mean_token_accuracy": 0.05900029614567757,
|
|
"num_tokens": 217291.0,
|
|
"step": 100
|
|
},
|
|
{
|
|
"entropy": 10.172372817993164,
|
|
"epoch": 0.006939625260235947,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 5.2e-05,
|
|
"loss": 8.6847,
|
|
"mean_token_accuracy": 0.0601776622235775,
|
|
"num_tokens": 227184.0,
|
|
"step": 105
|
|
},
|
|
{
|
|
"entropy": 10.142582893371582,
|
|
"epoch": 0.007270083605961469,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 5.45e-05,
|
|
"loss": 8.5856,
|
|
"mean_token_accuracy": 0.062167299538850786,
|
|
"num_tokens": 237928.0,
|
|
"step": 110
|
|
},
|
|
{
|
|
"entropy": 9.992514324188232,
|
|
"epoch": 0.00760054195168699,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 5.7e-05,
|
|
"loss": 8.4541,
|
|
"mean_token_accuracy": 0.07033347450196743,
|
|
"num_tokens": 250073.0,
|
|
"step": 115
|
|
},
|
|
{
|
|
"entropy": 9.925767707824708,
|
|
"epoch": 0.007931000297412512,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 5.9499999999999996e-05,
|
|
"loss": 8.3133,
|
|
"mean_token_accuracy": 0.07063820958137512,
|
|
"num_tokens": 261191.0,
|
|
"step": 120
|
|
},
|
|
{
|
|
"entropy": 9.826898574829102,
|
|
"epoch": 0.008261458643138032,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 6.2e-05,
|
|
"loss": 8.2501,
|
|
"mean_token_accuracy": 0.0650045171380043,
|
|
"num_tokens": 271226.0,
|
|
"step": 125
|
|
},
|
|
{
|
|
"entropy": 9.688051795959472,
|
|
"epoch": 0.008591916988863553,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 6.450000000000001e-05,
|
|
"loss": 8.1108,
|
|
"mean_token_accuracy": 0.07041079625487327,
|
|
"num_tokens": 282632.0,
|
|
"step": 130
|
|
},
|
|
{
|
|
"entropy": 9.554755210876465,
|
|
"epoch": 0.008922375334589075,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 6.7e-05,
|
|
"loss": 8.0812,
|
|
"mean_token_accuracy": 0.06935585699975491,
|
|
"num_tokens": 294119.0,
|
|
"step": 135
|
|
},
|
|
{
|
|
"entropy": 9.3393235206604,
|
|
"epoch": 0.009252833680314597,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 6.950000000000001e-05,
|
|
"loss": 7.9154,
|
|
"mean_token_accuracy": 0.06800433918833733,
|
|
"num_tokens": 304725.0,
|
|
"step": 140
|
|
},
|
|
{
|
|
"entropy": 9.183171463012695,
|
|
"epoch": 0.009583292026040118,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 7.2e-05,
|
|
"loss": 7.8272,
|
|
"mean_token_accuracy": 0.06738981902599335,
|
|
"num_tokens": 315260.0,
|
|
"step": 145
|
|
},
|
|
{
|
|
"entropy": 9.023473262786865,
|
|
"epoch": 0.00991375037176564,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 7.45e-05,
|
|
"loss": 7.816,
|
|
"mean_token_accuracy": 0.0658723335713148,
|
|
"num_tokens": 326228.0,
|
|
"step": 150
|
|
},
|
|
{
|
|
"entropy": 8.789591312408447,
|
|
"epoch": 0.01024420871749116,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 7.7e-05,
|
|
"loss": 7.6682,
|
|
"mean_token_accuracy": 0.07138085626065731,
|
|
"num_tokens": 336974.0,
|
|
"step": 155
|
|
},
|
|
{
|
|
"entropy": 8.713123226165772,
|
|
"epoch": 0.010574667063216681,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 7.950000000000001e-05,
|
|
"loss": 7.6937,
|
|
"mean_token_accuracy": 0.06671310998499394,
|
|
"num_tokens": 347380.0,
|
|
"step": 160
|
|
},
|
|
{
|
|
"entropy": 8.564159774780274,
|
|
"epoch": 0.010905125408942203,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 8.2e-05,
|
|
"loss": 7.5414,
|
|
"mean_token_accuracy": 0.06911698617041111,
|
|
"num_tokens": 358159.0,
|
|
"step": 165
|
|
},
|
|
{
|
|
"entropy": 8.391338634490968,
|
|
"epoch": 0.011235583754667725,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 8.450000000000001e-05,
|
|
"loss": 7.6154,
|
|
"mean_token_accuracy": 0.06779548972845077,
|
|
"num_tokens": 369224.0,
|
|
"step": 170
|
|
},
|
|
{
|
|
"entropy": 8.317761039733886,
|
|
"epoch": 0.011566042100393246,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 8.7e-05,
|
|
"loss": 7.5342,
|
|
"mean_token_accuracy": 0.0646525926887989,
|
|
"num_tokens": 380973.0,
|
|
"step": 175
|
|
},
|
|
{
|
|
"entropy": 8.257954692840576,
|
|
"epoch": 0.011896500446118766,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 8.95e-05,
|
|
"loss": 7.6128,
|
|
"mean_token_accuracy": 0.06305343359708786,
|
|
"num_tokens": 393367.0,
|
|
"step": 180
|
|
},
|
|
{
|
|
"entropy": 8.156609535217285,
|
|
"epoch": 0.012226958791844288,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 9.2e-05,
|
|
"loss": 7.5075,
|
|
"mean_token_accuracy": 0.07255993783473969,
|
|
"num_tokens": 405104.0,
|
|
"step": 185
|
|
},
|
|
{
|
|
"entropy": 8.167465686798096,
|
|
"epoch": 0.01255741713756981,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 9.45e-05,
|
|
"loss": 7.5335,
|
|
"mean_token_accuracy": 0.06890368461608887,
|
|
"num_tokens": 415734.0,
|
|
"step": 190
|
|
},
|
|
{
|
|
"entropy": 8.079139995574952,
|
|
"epoch": 0.01288787548329533,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 9.7e-05,
|
|
"loss": 7.5476,
|
|
"mean_token_accuracy": 0.06830249056220054,
|
|
"num_tokens": 425949.0,
|
|
"step": 195
|
|
},
|
|
{
|
|
"entropy": 8.103539848327637,
|
|
"epoch": 0.013218333829020852,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 9.95e-05,
|
|
"loss": 7.3962,
|
|
"mean_token_accuracy": 0.06818307042121888,
|
|
"num_tokens": 436083.0,
|
|
"step": 200
|
|
},
|
|
{
|
|
"entropy": 7.987107515335083,
|
|
"epoch": 0.013548792174746372,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.000102,
|
|
"loss": 7.4,
|
|
"mean_token_accuracy": 0.0744843065738678,
|
|
"num_tokens": 446731.0,
|
|
"step": 205
|
|
},
|
|
{
|
|
"entropy": 7.954383039474488,
|
|
"epoch": 0.013879250520471894,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00010449999999999999,
|
|
"loss": 7.392,
|
|
"mean_token_accuracy": 0.0729294192045927,
|
|
"num_tokens": 456630.0,
|
|
"step": 210
|
|
},
|
|
{
|
|
"entropy": 7.964882946014404,
|
|
"epoch": 0.014209708866197416,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.000107,
|
|
"loss": 7.406,
|
|
"mean_token_accuracy": 0.06909749209880829,
|
|
"num_tokens": 468804.0,
|
|
"step": 215
|
|
},
|
|
{
|
|
"entropy": 7.789395570755005,
|
|
"epoch": 0.014540167211922937,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0001095,
|
|
"loss": 7.3496,
|
|
"mean_token_accuracy": 0.07542757764458656,
|
|
"num_tokens": 479321.0,
|
|
"step": 220
|
|
},
|
|
{
|
|
"entropy": 7.850273847579956,
|
|
"epoch": 0.014870625557648459,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000112,
|
|
"loss": 7.3846,
|
|
"mean_token_accuracy": 0.0726801447570324,
|
|
"num_tokens": 490788.0,
|
|
"step": 225
|
|
},
|
|
{
|
|
"entropy": 7.854997777938843,
|
|
"epoch": 0.01520108390337398,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0001145,
|
|
"loss": 7.3583,
|
|
"mean_token_accuracy": 0.07561610527336597,
|
|
"num_tokens": 501992.0,
|
|
"step": 230
|
|
},
|
|
{
|
|
"entropy": 7.8472926139831545,
|
|
"epoch": 0.0155315422490995,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00011700000000000001,
|
|
"loss": 7.2768,
|
|
"mean_token_accuracy": 0.08250004723668099,
|
|
"num_tokens": 511927.0,
|
|
"step": 235
|
|
},
|
|
{
|
|
"entropy": 7.760110378265381,
|
|
"epoch": 0.015862000594825024,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00011949999999999999,
|
|
"loss": 7.2478,
|
|
"mean_token_accuracy": 0.08096232078969479,
|
|
"num_tokens": 521874.0,
|
|
"step": 240
|
|
},
|
|
{
|
|
"entropy": 7.749714708328247,
|
|
"epoch": 0.016192458940550544,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000122,
|
|
"loss": 7.3405,
|
|
"mean_token_accuracy": 0.07609539777040482,
|
|
"num_tokens": 532913.0,
|
|
"step": 245
|
|
},
|
|
{
|
|
"entropy": 7.832424545288086,
|
|
"epoch": 0.016522917286276063,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0001245,
|
|
"loss": 7.2888,
|
|
"mean_token_accuracy": 0.07482444941997528,
|
|
"num_tokens": 544195.0,
|
|
"step": 250
|
|
},
|
|
{
|
|
"entropy": 7.710200643539428,
|
|
"epoch": 0.016853375632001587,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000127,
|
|
"loss": 7.2822,
|
|
"mean_token_accuracy": 0.07511841356754304,
|
|
"num_tokens": 555555.0,
|
|
"step": 255
|
|
},
|
|
{
|
|
"entropy": 7.723060989379883,
|
|
"epoch": 0.017183833977727107,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0001295,
|
|
"loss": 7.3017,
|
|
"mean_token_accuracy": 0.06918322369456291,
|
|
"num_tokens": 566446.0,
|
|
"step": 260
|
|
},
|
|
{
|
|
"entropy": 7.735864305496216,
|
|
"epoch": 0.01751429232345263,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000132,
|
|
"loss": 7.1435,
|
|
"mean_token_accuracy": 0.08523371145129204,
|
|
"num_tokens": 576138.0,
|
|
"step": 265
|
|
},
|
|
{
|
|
"entropy": 7.7571961879730225,
|
|
"epoch": 0.01784475066917815,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.00013450000000000002,
|
|
"loss": 7.4068,
|
|
"mean_token_accuracy": 0.07323086895048618,
|
|
"num_tokens": 587559.0,
|
|
"step": 270
|
|
},
|
|
{
|
|
"entropy": 7.637564659118652,
|
|
"epoch": 0.01817520901490367,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00013700000000000002,
|
|
"loss": 7.2492,
|
|
"mean_token_accuracy": 0.07899717763066291,
|
|
"num_tokens": 598704.0,
|
|
"step": 275
|
|
},
|
|
{
|
|
"entropy": 7.6305924415588375,
|
|
"epoch": 0.018505667360629193,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0001395,
|
|
"loss": 7.2202,
|
|
"mean_token_accuracy": 0.08230236917734146,
|
|
"num_tokens": 609992.0,
|
|
"step": 280
|
|
},
|
|
{
|
|
"entropy": 7.777820110321045,
|
|
"epoch": 0.018836125706354713,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00014199999999999998,
|
|
"loss": 7.2906,
|
|
"mean_token_accuracy": 0.0766009196639061,
|
|
"num_tokens": 620756.0,
|
|
"step": 285
|
|
},
|
|
{
|
|
"entropy": 7.612432479858398,
|
|
"epoch": 0.019166584052080236,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0001445,
|
|
"loss": 7.1494,
|
|
"mean_token_accuracy": 0.08179529085755348,
|
|
"num_tokens": 630335.0,
|
|
"step": 290
|
|
},
|
|
{
|
|
"entropy": 7.54581618309021,
|
|
"epoch": 0.019497042397805756,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000147,
|
|
"loss": 7.2277,
|
|
"mean_token_accuracy": 0.07613298408687115,
|
|
"num_tokens": 641176.0,
|
|
"step": 295
|
|
},
|
|
{
|
|
"entropy": 7.677836608886719,
|
|
"epoch": 0.01982750074353128,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0001495,
|
|
"loss": 7.1341,
|
|
"mean_token_accuracy": 0.0822694730013609,
|
|
"num_tokens": 652144.0,
|
|
"step": 300
|
|
},
|
|
{
|
|
"entropy": 7.5951337814331055,
|
|
"epoch": 0.0201579590892568,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.000152,
|
|
"loss": 7.1135,
|
|
"mean_token_accuracy": 0.07866659983992577,
|
|
"num_tokens": 663040.0,
|
|
"step": 305
|
|
},
|
|
{
|
|
"entropy": 7.540827846527099,
|
|
"epoch": 0.02048841743498232,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00015450000000000001,
|
|
"loss": 7.1588,
|
|
"mean_token_accuracy": 0.08099368289113044,
|
|
"num_tokens": 674407.0,
|
|
"step": 310
|
|
},
|
|
{
|
|
"entropy": 7.606076622009278,
|
|
"epoch": 0.020818875780707843,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000157,
|
|
"loss": 7.1684,
|
|
"mean_token_accuracy": 0.07814301066100597,
|
|
"num_tokens": 686575.0,
|
|
"step": 315
|
|
},
|
|
{
|
|
"entropy": 7.528010988235474,
|
|
"epoch": 0.021149334126433363,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0001595,
|
|
"loss": 7.1044,
|
|
"mean_token_accuracy": 0.08741299659013749,
|
|
"num_tokens": 697404.0,
|
|
"step": 320
|
|
},
|
|
{
|
|
"entropy": 7.685597991943359,
|
|
"epoch": 0.021479792472158886,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000162,
|
|
"loss": 7.2433,
|
|
"mean_token_accuracy": 0.07762166783213616,
|
|
"num_tokens": 708462.0,
|
|
"step": 325
|
|
},
|
|
{
|
|
"entropy": 7.546236228942871,
|
|
"epoch": 0.021810250817884406,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00016450000000000001,
|
|
"loss": 7.1297,
|
|
"mean_token_accuracy": 0.08397110104560852,
|
|
"num_tokens": 719485.0,
|
|
"step": 330
|
|
},
|
|
{
|
|
"entropy": 7.449752140045166,
|
|
"epoch": 0.022140709163609926,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00016700000000000002,
|
|
"loss": 7.1155,
|
|
"mean_token_accuracy": 0.08090364784002305,
|
|
"num_tokens": 730417.0,
|
|
"step": 335
|
|
},
|
|
{
|
|
"entropy": 7.544217443466186,
|
|
"epoch": 0.02247116750933545,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00016950000000000003,
|
|
"loss": 7.0674,
|
|
"mean_token_accuracy": 0.08530745506286622,
|
|
"num_tokens": 740644.0,
|
|
"step": 340
|
|
},
|
|
{
|
|
"entropy": 7.413099479675293,
|
|
"epoch": 0.02280162585506097,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00017199999999999998,
|
|
"loss": 7.0263,
|
|
"mean_token_accuracy": 0.0855514369904995,
|
|
"num_tokens": 751843.0,
|
|
"step": 345
|
|
},
|
|
{
|
|
"entropy": 7.519398832321167,
|
|
"epoch": 0.023132084200786492,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00017449999999999999,
|
|
"loss": 7.0071,
|
|
"mean_token_accuracy": 0.08101744726300239,
|
|
"num_tokens": 763193.0,
|
|
"step": 350
|
|
},
|
|
{
|
|
"entropy": 7.416529798507691,
|
|
"epoch": 0.023462542546512012,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000177,
|
|
"loss": 7.088,
|
|
"mean_token_accuracy": 0.07980120629072189,
|
|
"num_tokens": 775393.0,
|
|
"step": 355
|
|
},
|
|
{
|
|
"entropy": 7.473480892181397,
|
|
"epoch": 0.023793000892237532,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0001795,
|
|
"loss": 6.9638,
|
|
"mean_token_accuracy": 0.08316674306988717,
|
|
"num_tokens": 786292.0,
|
|
"step": 360
|
|
},
|
|
{
|
|
"entropy": 7.4191234588623045,
|
|
"epoch": 0.024123459237963055,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000182,
|
|
"loss": 7.0293,
|
|
"mean_token_accuracy": 0.07673819884657859,
|
|
"num_tokens": 798344.0,
|
|
"step": 365
|
|
},
|
|
{
|
|
"entropy": 7.390763473510742,
|
|
"epoch": 0.024453917583688575,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0001845,
|
|
"loss": 7.0266,
|
|
"mean_token_accuracy": 0.08823682218790055,
|
|
"num_tokens": 809058.0,
|
|
"step": 370
|
|
},
|
|
{
|
|
"entropy": 7.3451203346252445,
|
|
"epoch": 0.0247843759294141,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000187,
|
|
"loss": 6.9562,
|
|
"mean_token_accuracy": 0.08663681447505951,
|
|
"num_tokens": 820848.0,
|
|
"step": 375
|
|
},
|
|
{
|
|
"entropy": 7.416850471496582,
|
|
"epoch": 0.02511483427513962,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0001895,
|
|
"loss": 7.0447,
|
|
"mean_token_accuracy": 0.08994424119591712,
|
|
"num_tokens": 833361.0,
|
|
"step": 380
|
|
},
|
|
{
|
|
"entropy": 7.370834159851074,
|
|
"epoch": 0.02544529262086514,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000192,
|
|
"loss": 6.9881,
|
|
"mean_token_accuracy": 0.08523149564862251,
|
|
"num_tokens": 843801.0,
|
|
"step": 385
|
|
},
|
|
{
|
|
"entropy": 7.4036249160766605,
|
|
"epoch": 0.02577575096659066,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0001945,
|
|
"loss": 6.9772,
|
|
"mean_token_accuracy": 0.08082735612988472,
|
|
"num_tokens": 854477.0,
|
|
"step": 390
|
|
},
|
|
{
|
|
"entropy": 7.330833148956299,
|
|
"epoch": 0.02610620931231618,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00019700000000000002,
|
|
"loss": 7.0413,
|
|
"mean_token_accuracy": 0.08312294557690621,
|
|
"num_tokens": 863380.0,
|
|
"step": 395
|
|
},
|
|
{
|
|
"entropy": 7.37300477027893,
|
|
"epoch": 0.026436667658041705,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00019950000000000002,
|
|
"loss": 6.9635,
|
|
"mean_token_accuracy": 0.08273139744997024,
|
|
"num_tokens": 874215.0,
|
|
"step": 400
|
|
},
|
|
{
|
|
"entropy": 7.265693616867066,
|
|
"epoch": 0.026767126003767225,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.000202,
|
|
"loss": 7.0215,
|
|
"mean_token_accuracy": 0.09335545673966408,
|
|
"num_tokens": 885928.0,
|
|
"step": 405
|
|
},
|
|
{
|
|
"entropy": 7.470329475402832,
|
|
"epoch": 0.027097584349492745,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00020449999999999998,
|
|
"loss": 7.036,
|
|
"mean_token_accuracy": 0.08615454584360123,
|
|
"num_tokens": 896349.0,
|
|
"step": 410
|
|
},
|
|
{
|
|
"entropy": 7.282833099365234,
|
|
"epoch": 0.027428042695218268,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000207,
|
|
"loss": 6.9012,
|
|
"mean_token_accuracy": 0.0931041918694973,
|
|
"num_tokens": 907126.0,
|
|
"step": 415
|
|
},
|
|
{
|
|
"entropy": 7.305163431167602,
|
|
"epoch": 0.027758501040943788,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0002095,
|
|
"loss": 7.0214,
|
|
"mean_token_accuracy": 0.08308781683444977,
|
|
"num_tokens": 918021.0,
|
|
"step": 420
|
|
},
|
|
{
|
|
"entropy": 7.268058013916016,
|
|
"epoch": 0.02808895938666931,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000212,
|
|
"loss": 6.8958,
|
|
"mean_token_accuracy": 0.08962870463728904,
|
|
"num_tokens": 929321.0,
|
|
"step": 425
|
|
},
|
|
{
|
|
"entropy": 7.27590012550354,
|
|
"epoch": 0.02841941773239483,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0002145,
|
|
"loss": 6.9289,
|
|
"mean_token_accuracy": 0.08679753243923187,
|
|
"num_tokens": 940196.0,
|
|
"step": 430
|
|
},
|
|
{
|
|
"entropy": 7.284714984893799,
|
|
"epoch": 0.028749876078120355,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00021700000000000002,
|
|
"loss": 6.9195,
|
|
"mean_token_accuracy": 0.09327666312456132,
|
|
"num_tokens": 950600.0,
|
|
"step": 435
|
|
},
|
|
{
|
|
"entropy": 7.263758373260498,
|
|
"epoch": 0.029080334423845874,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0002195,
|
|
"loss": 6.9498,
|
|
"mean_token_accuracy": 0.08754595220088959,
|
|
"num_tokens": 961447.0,
|
|
"step": 440
|
|
},
|
|
{
|
|
"entropy": 7.194220161437988,
|
|
"epoch": 0.029410792769571394,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000222,
|
|
"loss": 6.8597,
|
|
"mean_token_accuracy": 0.08954929485917092,
|
|
"num_tokens": 973264.0,
|
|
"step": 445
|
|
},
|
|
{
|
|
"entropy": 7.355491304397583,
|
|
"epoch": 0.029741251115296918,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0002245,
|
|
"loss": 7.0987,
|
|
"mean_token_accuracy": 0.07984722442924977,
|
|
"num_tokens": 985123.0,
|
|
"step": 450
|
|
},
|
|
{
|
|
"entropy": 7.258900594711304,
|
|
"epoch": 0.030071709461022438,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00022700000000000002,
|
|
"loss": 6.935,
|
|
"mean_token_accuracy": 0.08211459219455719,
|
|
"num_tokens": 996037.0,
|
|
"step": 455
|
|
},
|
|
{
|
|
"entropy": 7.292104005813599,
|
|
"epoch": 0.03040216780674796,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00022950000000000002,
|
|
"loss": 6.9936,
|
|
"mean_token_accuracy": 0.0812192477285862,
|
|
"num_tokens": 1006940.0,
|
|
"step": 460
|
|
},
|
|
{
|
|
"entropy": 7.212660837173462,
|
|
"epoch": 0.03073262615247348,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00023200000000000003,
|
|
"loss": 6.8055,
|
|
"mean_token_accuracy": 0.08365916460752487,
|
|
"num_tokens": 1017259.0,
|
|
"step": 465
|
|
},
|
|
{
|
|
"entropy": 7.161711931228638,
|
|
"epoch": 0.031063084498199,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00023449999999999998,
|
|
"loss": 6.8381,
|
|
"mean_token_accuracy": 0.08933527991175652,
|
|
"num_tokens": 1028477.0,
|
|
"step": 470
|
|
},
|
|
{
|
|
"entropy": 7.197433996200561,
|
|
"epoch": 0.031393542843924524,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000237,
|
|
"loss": 6.8515,
|
|
"mean_token_accuracy": 0.0891186311841011,
|
|
"num_tokens": 1039812.0,
|
|
"step": 475
|
|
},
|
|
{
|
|
"entropy": 7.1398866176605225,
|
|
"epoch": 0.03172400118965005,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0002395,
|
|
"loss": 6.8207,
|
|
"mean_token_accuracy": 0.09132780060172081,
|
|
"num_tokens": 1050856.0,
|
|
"step": 480
|
|
},
|
|
{
|
|
"entropy": 7.054386281967163,
|
|
"epoch": 0.032054459535375564,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000242,
|
|
"loss": 6.6937,
|
|
"mean_token_accuracy": 0.09542593285441399,
|
|
"num_tokens": 1061491.0,
|
|
"step": 485
|
|
},
|
|
{
|
|
"entropy": 7.081818532943726,
|
|
"epoch": 0.03238491788110109,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0002445,
|
|
"loss": 6.7775,
|
|
"mean_token_accuracy": 0.08975680768489838,
|
|
"num_tokens": 1071986.0,
|
|
"step": 490
|
|
},
|
|
{
|
|
"entropy": 7.154221773147583,
|
|
"epoch": 0.03271537622682661,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000247,
|
|
"loss": 6.8332,
|
|
"mean_token_accuracy": 0.08331749886274338,
|
|
"num_tokens": 1084174.0,
|
|
"step": 495
|
|
},
|
|
{
|
|
"entropy": 7.191654109954834,
|
|
"epoch": 0.03304583457255213,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0002495,
|
|
"loss": 6.8399,
|
|
"mean_token_accuracy": 0.08998439535498619,
|
|
"num_tokens": 1094267.0,
|
|
"step": 500
|
|
},
|
|
{
|
|
"entropy": 7.129807043075561,
|
|
"epoch": 0.03337629291827765,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000252,
|
|
"loss": 6.8272,
|
|
"mean_token_accuracy": 0.09337387830018998,
|
|
"num_tokens": 1105421.0,
|
|
"step": 505
|
|
},
|
|
{
|
|
"entropy": 7.136587476730346,
|
|
"epoch": 0.033706751264003174,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0002545,
|
|
"loss": 6.9057,
|
|
"mean_token_accuracy": 0.08978310525417328,
|
|
"num_tokens": 1117574.0,
|
|
"step": 510
|
|
},
|
|
{
|
|
"entropy": 7.068832921981811,
|
|
"epoch": 0.0340372096097287,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000257,
|
|
"loss": 6.7841,
|
|
"mean_token_accuracy": 0.09897544533014298,
|
|
"num_tokens": 1129666.0,
|
|
"step": 515
|
|
},
|
|
{
|
|
"entropy": 7.095613145828247,
|
|
"epoch": 0.03436766795545421,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0002595,
|
|
"loss": 6.8098,
|
|
"mean_token_accuracy": 0.09167956337332725,
|
|
"num_tokens": 1140936.0,
|
|
"step": 520
|
|
},
|
|
{
|
|
"entropy": 7.066299915313721,
|
|
"epoch": 0.03469812630117974,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000262,
|
|
"loss": 6.8261,
|
|
"mean_token_accuracy": 0.09235902950167656,
|
|
"num_tokens": 1152239.0,
|
|
"step": 525
|
|
},
|
|
{
|
|
"entropy": 7.073812246322632,
|
|
"epoch": 0.03502858464690526,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00026450000000000003,
|
|
"loss": 6.7493,
|
|
"mean_token_accuracy": 0.09044400379061698,
|
|
"num_tokens": 1162680.0,
|
|
"step": 530
|
|
},
|
|
{
|
|
"entropy": 7.036542844772339,
|
|
"epoch": 0.035359042992630776,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00026700000000000004,
|
|
"loss": 6.8029,
|
|
"mean_token_accuracy": 0.09098404496908188,
|
|
"num_tokens": 1173155.0,
|
|
"step": 535
|
|
},
|
|
{
|
|
"entropy": 7.014681577682495,
|
|
"epoch": 0.0356895013383563,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00026950000000000005,
|
|
"loss": 6.7485,
|
|
"mean_token_accuracy": 0.09319498017430305,
|
|
"num_tokens": 1183042.0,
|
|
"step": 540
|
|
},
|
|
{
|
|
"entropy": 7.069463157653809,
|
|
"epoch": 0.03601995968408182,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00027200000000000005,
|
|
"loss": 6.8447,
|
|
"mean_token_accuracy": 0.08397522196173668,
|
|
"num_tokens": 1194512.0,
|
|
"step": 545
|
|
},
|
|
{
|
|
"entropy": 7.06383261680603,
|
|
"epoch": 0.03635041802980734,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0002745,
|
|
"loss": 6.7105,
|
|
"mean_token_accuracy": 0.09679808020591736,
|
|
"num_tokens": 1205063.0,
|
|
"step": 550
|
|
},
|
|
{
|
|
"entropy": 6.9953466892242435,
|
|
"epoch": 0.03668087637553286,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.000277,
|
|
"loss": 6.7437,
|
|
"mean_token_accuracy": 0.0971693828701973,
|
|
"num_tokens": 1215967.0,
|
|
"step": 555
|
|
},
|
|
{
|
|
"entropy": 7.036475419998169,
|
|
"epoch": 0.037011334721258386,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0002795,
|
|
"loss": 6.7225,
|
|
"mean_token_accuracy": 0.09566427320241928,
|
|
"num_tokens": 1226712.0,
|
|
"step": 560
|
|
},
|
|
{
|
|
"entropy": 7.018493223190307,
|
|
"epoch": 0.03734179306698391,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00028199999999999997,
|
|
"loss": 6.7553,
|
|
"mean_token_accuracy": 0.09875442162156105,
|
|
"num_tokens": 1238058.0,
|
|
"step": 565
|
|
},
|
|
{
|
|
"entropy": 6.883628988265992,
|
|
"epoch": 0.037672251412709426,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0002845,
|
|
"loss": 6.6518,
|
|
"mean_token_accuracy": 0.09676829054951668,
|
|
"num_tokens": 1248199.0,
|
|
"step": 570
|
|
},
|
|
{
|
|
"entropy": 6.979853677749634,
|
|
"epoch": 0.03800270975843495,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000287,
|
|
"loss": 6.7898,
|
|
"mean_token_accuracy": 0.08489116355776787,
|
|
"num_tokens": 1260755.0,
|
|
"step": 575
|
|
},
|
|
{
|
|
"entropy": 7.026479578018188,
|
|
"epoch": 0.03833316810416047,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0002895,
|
|
"loss": 6.7464,
|
|
"mean_token_accuracy": 0.0949298694729805,
|
|
"num_tokens": 1270395.0,
|
|
"step": 580
|
|
},
|
|
{
|
|
"entropy": 6.907937526702881,
|
|
"epoch": 0.03866362644988599,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000292,
|
|
"loss": 6.7393,
|
|
"mean_token_accuracy": 0.09430743306875229,
|
|
"num_tokens": 1282735.0,
|
|
"step": 585
|
|
},
|
|
{
|
|
"entropy": 6.929727029800415,
|
|
"epoch": 0.03899408479561151,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0002945,
|
|
"loss": 6.6946,
|
|
"mean_token_accuracy": 0.09773564413189888,
|
|
"num_tokens": 1292991.0,
|
|
"step": 590
|
|
},
|
|
{
|
|
"entropy": 6.953424596786499,
|
|
"epoch": 0.039324543141337036,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000297,
|
|
"loss": 6.7259,
|
|
"mean_token_accuracy": 0.09127573445439338,
|
|
"num_tokens": 1303361.0,
|
|
"step": 595
|
|
},
|
|
{
|
|
"entropy": 6.939087438583374,
|
|
"epoch": 0.03965500148706256,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0002995,
|
|
"loss": 6.6299,
|
|
"mean_token_accuracy": 0.09687030985951424,
|
|
"num_tokens": 1314099.0,
|
|
"step": 600
|
|
},
|
|
{
|
|
"entropy": 6.892501449584961,
|
|
"epoch": 0.039985459832788076,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000302,
|
|
"loss": 6.6377,
|
|
"mean_token_accuracy": 0.09915548786520959,
|
|
"num_tokens": 1324059.0,
|
|
"step": 605
|
|
},
|
|
{
|
|
"entropy": 6.982302951812744,
|
|
"epoch": 0.0403159181785136,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0003045,
|
|
"loss": 6.7706,
|
|
"mean_token_accuracy": 0.09124096035957337,
|
|
"num_tokens": 1334208.0,
|
|
"step": 610
|
|
},
|
|
{
|
|
"entropy": 7.0098623752594,
|
|
"epoch": 0.04064637652423912,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.000307,
|
|
"loss": 6.7337,
|
|
"mean_token_accuracy": 0.09305815249681473,
|
|
"num_tokens": 1345633.0,
|
|
"step": 615
|
|
},
|
|
{
|
|
"entropy": 6.876529264450073,
|
|
"epoch": 0.04097683486996464,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0003095,
|
|
"loss": 6.5852,
|
|
"mean_token_accuracy": 0.09691078439354897,
|
|
"num_tokens": 1356478.0,
|
|
"step": 620
|
|
},
|
|
{
|
|
"entropy": 6.807394647598267,
|
|
"epoch": 0.04130729321569016,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000312,
|
|
"loss": 6.6882,
|
|
"mean_token_accuracy": 0.09402298852801323,
|
|
"num_tokens": 1368925.0,
|
|
"step": 625
|
|
},
|
|
{
|
|
"entropy": 6.940099287033081,
|
|
"epoch": 0.041637751561415685,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0003145,
|
|
"loss": 6.7044,
|
|
"mean_token_accuracy": 0.09032920226454735,
|
|
"num_tokens": 1379150.0,
|
|
"step": 630
|
|
},
|
|
{
|
|
"entropy": 6.922402429580688,
|
|
"epoch": 0.0419682099071412,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000317,
|
|
"loss": 6.6115,
|
|
"mean_token_accuracy": 0.10022713616490364,
|
|
"num_tokens": 1388993.0,
|
|
"step": 635
|
|
},
|
|
{
|
|
"entropy": 6.887875175476074,
|
|
"epoch": 0.042298668252866725,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0003195,
|
|
"loss": 6.6978,
|
|
"mean_token_accuracy": 0.09888584762811661,
|
|
"num_tokens": 1399906.0,
|
|
"step": 640
|
|
},
|
|
{
|
|
"entropy": 6.799718141555786,
|
|
"epoch": 0.04262912659859225,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000322,
|
|
"loss": 6.6084,
|
|
"mean_token_accuracy": 0.09428260773420334,
|
|
"num_tokens": 1411494.0,
|
|
"step": 645
|
|
},
|
|
{
|
|
"entropy": 6.889655542373657,
|
|
"epoch": 0.04295958494431777,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00032450000000000003,
|
|
"loss": 6.6969,
|
|
"mean_token_accuracy": 0.0979191929101944,
|
|
"num_tokens": 1423298.0,
|
|
"step": 650
|
|
},
|
|
{
|
|
"entropy": 6.769257879257202,
|
|
"epoch": 0.04329004329004329,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00032700000000000003,
|
|
"loss": 6.5803,
|
|
"mean_token_accuracy": 0.09798824638128281,
|
|
"num_tokens": 1433892.0,
|
|
"step": 655
|
|
},
|
|
{
|
|
"entropy": 6.887624311447143,
|
|
"epoch": 0.04362050163576881,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00032950000000000004,
|
|
"loss": 6.6894,
|
|
"mean_token_accuracy": 0.09577311277389526,
|
|
"num_tokens": 1443778.0,
|
|
"step": 660
|
|
},
|
|
{
|
|
"entropy": 6.862514400482178,
|
|
"epoch": 0.043950959981494335,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00033200000000000005,
|
|
"loss": 6.6303,
|
|
"mean_token_accuracy": 0.09138552024960518,
|
|
"num_tokens": 1454990.0,
|
|
"step": 665
|
|
},
|
|
{
|
|
"entropy": 6.814253664016723,
|
|
"epoch": 0.04428141832721985,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00033450000000000005,
|
|
"loss": 6.6097,
|
|
"mean_token_accuracy": 0.09931056052446366,
|
|
"num_tokens": 1466678.0,
|
|
"step": 670
|
|
},
|
|
{
|
|
"entropy": 6.9184776782989506,
|
|
"epoch": 0.044611876672945375,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000337,
|
|
"loss": 6.6926,
|
|
"mean_token_accuracy": 0.10091055706143379,
|
|
"num_tokens": 1477011.0,
|
|
"step": 675
|
|
},
|
|
{
|
|
"entropy": 6.720648336410522,
|
|
"epoch": 0.0449423350186709,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0003395,
|
|
"loss": 6.5383,
|
|
"mean_token_accuracy": 0.0934677354991436,
|
|
"num_tokens": 1487519.0,
|
|
"step": 680
|
|
},
|
|
{
|
|
"entropy": 6.770115756988526,
|
|
"epoch": 0.045272793364396414,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000342,
|
|
"loss": 6.6625,
|
|
"mean_token_accuracy": 0.09488041177392006,
|
|
"num_tokens": 1499831.0,
|
|
"step": 685
|
|
},
|
|
{
|
|
"entropy": 6.773311138153076,
|
|
"epoch": 0.04560325171012194,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00034449999999999997,
|
|
"loss": 6.5623,
|
|
"mean_token_accuracy": 0.09586277455091477,
|
|
"num_tokens": 1509884.0,
|
|
"step": 690
|
|
},
|
|
{
|
|
"entropy": 6.797134351730347,
|
|
"epoch": 0.04593371005584746,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000347,
|
|
"loss": 6.566,
|
|
"mean_token_accuracy": 0.09943261742591858,
|
|
"num_tokens": 1519693.0,
|
|
"step": 695
|
|
},
|
|
{
|
|
"entropy": 6.701273775100708,
|
|
"epoch": 0.046264168401572985,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0003495,
|
|
"loss": 6.5545,
|
|
"mean_token_accuracy": 0.09949971362948418,
|
|
"num_tokens": 1530649.0,
|
|
"step": 700
|
|
},
|
|
{
|
|
"entropy": 6.817782831192017,
|
|
"epoch": 0.0465946267472985,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000352,
|
|
"loss": 6.6569,
|
|
"mean_token_accuracy": 0.1008459135890007,
|
|
"num_tokens": 1541285.0,
|
|
"step": 705
|
|
},
|
|
{
|
|
"entropy": 6.7360601902008055,
|
|
"epoch": 0.046925085093024024,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0003545,
|
|
"loss": 6.5629,
|
|
"mean_token_accuracy": 0.10334613248705864,
|
|
"num_tokens": 1552405.0,
|
|
"step": 710
|
|
},
|
|
{
|
|
"entropy": 6.708620166778564,
|
|
"epoch": 0.04725554343874955,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.000357,
|
|
"loss": 6.5703,
|
|
"mean_token_accuracy": 0.09885218217968941,
|
|
"num_tokens": 1563471.0,
|
|
"step": 715
|
|
},
|
|
{
|
|
"entropy": 6.694813919067383,
|
|
"epoch": 0.047586001784475064,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0003595,
|
|
"loss": 6.6496,
|
|
"mean_token_accuracy": 0.09043260738253593,
|
|
"num_tokens": 1573499.0,
|
|
"step": 720
|
|
},
|
|
{
|
|
"entropy": 6.73417477607727,
|
|
"epoch": 0.04791646013020059,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000362,
|
|
"loss": 6.4942,
|
|
"mean_token_accuracy": 0.09848063513636589,
|
|
"num_tokens": 1583827.0,
|
|
"step": 725
|
|
},
|
|
{
|
|
"entropy": 6.88015398979187,
|
|
"epoch": 0.04824691847592611,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0003645,
|
|
"loss": 6.6481,
|
|
"mean_token_accuracy": 0.0926512323319912,
|
|
"num_tokens": 1594525.0,
|
|
"step": 730
|
|
},
|
|
{
|
|
"entropy": 6.7281975746154785,
|
|
"epoch": 0.048577376821651634,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000367,
|
|
"loss": 6.6375,
|
|
"mean_token_accuracy": 0.09198551625013351,
|
|
"num_tokens": 1605263.0,
|
|
"step": 735
|
|
},
|
|
{
|
|
"entropy": 6.725015354156494,
|
|
"epoch": 0.04890783516737715,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0003695,
|
|
"loss": 6.5674,
|
|
"mean_token_accuracy": 0.09970696419477462,
|
|
"num_tokens": 1616232.0,
|
|
"step": 740
|
|
},
|
|
{
|
|
"entropy": 6.655939340591431,
|
|
"epoch": 0.049238293513102674,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000372,
|
|
"loss": 6.5418,
|
|
"mean_token_accuracy": 0.10249985605478287,
|
|
"num_tokens": 1627370.0,
|
|
"step": 745
|
|
},
|
|
{
|
|
"entropy": 6.780833673477173,
|
|
"epoch": 0.0495687518588282,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0003745,
|
|
"loss": 6.6559,
|
|
"mean_token_accuracy": 0.09198240488767624,
|
|
"num_tokens": 1639328.0,
|
|
"step": 750
|
|
},
|
|
{
|
|
"entropy": 6.692653226852417,
|
|
"epoch": 0.049899210204553714,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000377,
|
|
"loss": 6.5224,
|
|
"mean_token_accuracy": 0.09956051632761956,
|
|
"num_tokens": 1649910.0,
|
|
"step": 755
|
|
},
|
|
{
|
|
"entropy": 6.702142667770386,
|
|
"epoch": 0.05022966855027924,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0003795,
|
|
"loss": 6.5548,
|
|
"mean_token_accuracy": 0.09980311691761017,
|
|
"num_tokens": 1661429.0,
|
|
"step": 760
|
|
},
|
|
{
|
|
"entropy": 6.625659704208374,
|
|
"epoch": 0.05056012689600476,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000382,
|
|
"loss": 6.4848,
|
|
"mean_token_accuracy": 0.10349942594766617,
|
|
"num_tokens": 1672169.0,
|
|
"step": 765
|
|
},
|
|
{
|
|
"entropy": 6.666405963897705,
|
|
"epoch": 0.05089058524173028,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0003845,
|
|
"loss": 6.5629,
|
|
"mean_token_accuracy": 0.09543908089399337,
|
|
"num_tokens": 1683860.0,
|
|
"step": 770
|
|
},
|
|
{
|
|
"entropy": 6.645580005645752,
|
|
"epoch": 0.0512210435874558,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00038700000000000003,
|
|
"loss": 6.4625,
|
|
"mean_token_accuracy": 0.10984127521514893,
|
|
"num_tokens": 1694348.0,
|
|
"step": 775
|
|
},
|
|
{
|
|
"entropy": 6.645284843444824,
|
|
"epoch": 0.05155150193318132,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00038950000000000003,
|
|
"loss": 6.5667,
|
|
"mean_token_accuracy": 0.09349910616874695,
|
|
"num_tokens": 1704673.0,
|
|
"step": 780
|
|
},
|
|
{
|
|
"entropy": 6.770039892196655,
|
|
"epoch": 0.05188196027890685,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00039200000000000004,
|
|
"loss": 6.6103,
|
|
"mean_token_accuracy": 0.09760363474488258,
|
|
"num_tokens": 1714887.0,
|
|
"step": 785
|
|
},
|
|
{
|
|
"entropy": 6.663259124755859,
|
|
"epoch": 0.05221241862463236,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00039450000000000005,
|
|
"loss": 6.5466,
|
|
"mean_token_accuracy": 0.09423963278532028,
|
|
"num_tokens": 1725630.0,
|
|
"step": 790
|
|
},
|
|
{
|
|
"entropy": 6.584082794189453,
|
|
"epoch": 0.05254287697035789,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00039700000000000005,
|
|
"loss": 6.5141,
|
|
"mean_token_accuracy": 0.10037482157349586,
|
|
"num_tokens": 1736526.0,
|
|
"step": 795
|
|
},
|
|
{
|
|
"entropy": 6.771090745925903,
|
|
"epoch": 0.05287333531608341,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0003995,
|
|
"loss": 6.6545,
|
|
"mean_token_accuracy": 0.09194476455450058,
|
|
"num_tokens": 1748138.0,
|
|
"step": 800
|
|
},
|
|
{
|
|
"entropy": 6.5120241165161135,
|
|
"epoch": 0.053203793661808926,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000402,
|
|
"loss": 6.442,
|
|
"mean_token_accuracy": 0.10061683282256126,
|
|
"num_tokens": 1758691.0,
|
|
"step": 805
|
|
},
|
|
{
|
|
"entropy": 6.637072944641114,
|
|
"epoch": 0.05353425200753445,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004045,
|
|
"loss": 6.5277,
|
|
"mean_token_accuracy": 0.0915706716477871,
|
|
"num_tokens": 1770004.0,
|
|
"step": 810
|
|
},
|
|
{
|
|
"entropy": 6.73297963142395,
|
|
"epoch": 0.05386471035325997,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00040699999999999997,
|
|
"loss": 6.5924,
|
|
"mean_token_accuracy": 0.09404471218585968,
|
|
"num_tokens": 1780269.0,
|
|
"step": 815
|
|
},
|
|
{
|
|
"entropy": 6.589795207977295,
|
|
"epoch": 0.05419516869898549,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004095,
|
|
"loss": 6.5231,
|
|
"mean_token_accuracy": 0.10108774527907372,
|
|
"num_tokens": 1790581.0,
|
|
"step": 820
|
|
},
|
|
{
|
|
"entropy": 6.64861421585083,
|
|
"epoch": 0.05452562704471101,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000412,
|
|
"loss": 6.4919,
|
|
"mean_token_accuracy": 0.10306402817368507,
|
|
"num_tokens": 1801930.0,
|
|
"step": 825
|
|
},
|
|
{
|
|
"entropy": 6.569200468063355,
|
|
"epoch": 0.054856085390436536,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004145,
|
|
"loss": 6.4747,
|
|
"mean_token_accuracy": 0.10015810206532479,
|
|
"num_tokens": 1812876.0,
|
|
"step": 830
|
|
},
|
|
{
|
|
"entropy": 6.593674230575561,
|
|
"epoch": 0.05518654373616206,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000417,
|
|
"loss": 6.5424,
|
|
"mean_token_accuracy": 0.09639053866267204,
|
|
"num_tokens": 1825521.0,
|
|
"step": 835
|
|
},
|
|
{
|
|
"entropy": 6.617445182800293,
|
|
"epoch": 0.055517002081887576,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004195,
|
|
"loss": 6.5164,
|
|
"mean_token_accuracy": 0.09912106320261956,
|
|
"num_tokens": 1835268.0,
|
|
"step": 840
|
|
},
|
|
{
|
|
"entropy": 6.559435272216797,
|
|
"epoch": 0.0558474604276131,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000422,
|
|
"loss": 6.4468,
|
|
"mean_token_accuracy": 0.10214125663042069,
|
|
"num_tokens": 1846269.0,
|
|
"step": 845
|
|
},
|
|
{
|
|
"entropy": 6.57283730506897,
|
|
"epoch": 0.05617791877333862,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004245,
|
|
"loss": 6.5153,
|
|
"mean_token_accuracy": 0.10395664349198341,
|
|
"num_tokens": 1857710.0,
|
|
"step": 850
|
|
},
|
|
{
|
|
"entropy": 6.483006477355957,
|
|
"epoch": 0.05650837711906414,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000427,
|
|
"loss": 6.5148,
|
|
"mean_token_accuracy": 0.10404823273420334,
|
|
"num_tokens": 1868569.0,
|
|
"step": 855
|
|
},
|
|
{
|
|
"entropy": 6.575480699539185,
|
|
"epoch": 0.05683883546478966,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004295,
|
|
"loss": 6.4747,
|
|
"mean_token_accuracy": 0.10771524235606193,
|
|
"num_tokens": 1878580.0,
|
|
"step": 860
|
|
},
|
|
{
|
|
"entropy": 6.6114942073822025,
|
|
"epoch": 0.057169293810515186,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000432,
|
|
"loss": 6.4172,
|
|
"mean_token_accuracy": 0.10425916984677315,
|
|
"num_tokens": 1888963.0,
|
|
"step": 865
|
|
},
|
|
{
|
|
"entropy": 6.547268295288086,
|
|
"epoch": 0.05749975215624071,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004345,
|
|
"loss": 6.598,
|
|
"mean_token_accuracy": 0.09941022247076034,
|
|
"num_tokens": 1900085.0,
|
|
"step": 870
|
|
},
|
|
{
|
|
"entropy": 6.600188589096069,
|
|
"epoch": 0.057830210501966225,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000437,
|
|
"loss": 6.4176,
|
|
"mean_token_accuracy": 0.10359677523374558,
|
|
"num_tokens": 1911447.0,
|
|
"step": 875
|
|
},
|
|
{
|
|
"entropy": 6.464424467086792,
|
|
"epoch": 0.05816066884769175,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004395,
|
|
"loss": 6.448,
|
|
"mean_token_accuracy": 0.09791496470570564,
|
|
"num_tokens": 1922194.0,
|
|
"step": 880
|
|
},
|
|
{
|
|
"entropy": 6.561442136764526,
|
|
"epoch": 0.05849112719341727,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000442,
|
|
"loss": 6.481,
|
|
"mean_token_accuracy": 0.10386462211608886,
|
|
"num_tokens": 1932829.0,
|
|
"step": 885
|
|
},
|
|
{
|
|
"entropy": 6.573152256011963,
|
|
"epoch": 0.05882158553914279,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004445,
|
|
"loss": 6.5259,
|
|
"mean_token_accuracy": 0.10657603517174721,
|
|
"num_tokens": 1942504.0,
|
|
"step": 890
|
|
},
|
|
{
|
|
"entropy": 6.475641679763794,
|
|
"epoch": 0.05915204388486831,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.000447,
|
|
"loss": 6.5123,
|
|
"mean_token_accuracy": 0.10546292960643769,
|
|
"num_tokens": 1954934.0,
|
|
"step": 895
|
|
},
|
|
{
|
|
"entropy": 6.5593757152557375,
|
|
"epoch": 0.059482502230593835,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00044950000000000003,
|
|
"loss": 6.4601,
|
|
"mean_token_accuracy": 0.10120314806699753,
|
|
"num_tokens": 1968005.0,
|
|
"step": 900
|
|
},
|
|
{
|
|
"entropy": 6.476503992080689,
|
|
"epoch": 0.05981296057631935,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00045200000000000004,
|
|
"loss": 6.4575,
|
|
"mean_token_accuracy": 0.1004819169640541,
|
|
"num_tokens": 1978532.0,
|
|
"step": 905
|
|
},
|
|
{
|
|
"entropy": 6.53993706703186,
|
|
"epoch": 0.060143418922044875,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00045450000000000004,
|
|
"loss": 6.5338,
|
|
"mean_token_accuracy": 0.10164398774504661,
|
|
"num_tokens": 1989051.0,
|
|
"step": 910
|
|
},
|
|
{
|
|
"entropy": 6.523714780807495,
|
|
"epoch": 0.0604738772677704,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00045700000000000005,
|
|
"loss": 6.406,
|
|
"mean_token_accuracy": 0.1086203046143055,
|
|
"num_tokens": 2001245.0,
|
|
"step": 915
|
|
},
|
|
{
|
|
"entropy": 6.457377147674561,
|
|
"epoch": 0.06080433561349592,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00045950000000000006,
|
|
"loss": 6.4188,
|
|
"mean_token_accuracy": 0.10521991178393364,
|
|
"num_tokens": 2011840.0,
|
|
"step": 920
|
|
},
|
|
{
|
|
"entropy": 6.440218067169189,
|
|
"epoch": 0.06113479395922144,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000462,
|
|
"loss": 6.369,
|
|
"mean_token_accuracy": 0.10432081371545791,
|
|
"num_tokens": 2022454.0,
|
|
"step": 925
|
|
},
|
|
{
|
|
"entropy": 6.510140705108642,
|
|
"epoch": 0.06146525230494696,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004645,
|
|
"loss": 6.5518,
|
|
"mean_token_accuracy": 0.0980154186487198,
|
|
"num_tokens": 2032745.0,
|
|
"step": 930
|
|
},
|
|
{
|
|
"entropy": 6.4728662967681885,
|
|
"epoch": 0.061795710650672485,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000467,
|
|
"loss": 6.4647,
|
|
"mean_token_accuracy": 0.09817253425717354,
|
|
"num_tokens": 2043020.0,
|
|
"step": 935
|
|
},
|
|
{
|
|
"entropy": 6.616012287139893,
|
|
"epoch": 0.062126168996398,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004695,
|
|
"loss": 6.5055,
|
|
"mean_token_accuracy": 0.09617855548858642,
|
|
"num_tokens": 2055288.0,
|
|
"step": 940
|
|
},
|
|
{
|
|
"entropy": 6.403015899658203,
|
|
"epoch": 0.062456627342123525,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000472,
|
|
"loss": 6.4289,
|
|
"mean_token_accuracy": 0.10303806513547897,
|
|
"num_tokens": 2066252.0,
|
|
"step": 945
|
|
},
|
|
{
|
|
"entropy": 6.583564329147339,
|
|
"epoch": 0.06278708568784905,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004745,
|
|
"loss": 6.5182,
|
|
"mean_token_accuracy": 0.09759321138262748,
|
|
"num_tokens": 2079404.0,
|
|
"step": 950
|
|
},
|
|
{
|
|
"entropy": 6.481687831878662,
|
|
"epoch": 0.06311754403357457,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000477,
|
|
"loss": 6.3989,
|
|
"mean_token_accuracy": 0.1046754002571106,
|
|
"num_tokens": 2091420.0,
|
|
"step": 955
|
|
},
|
|
{
|
|
"entropy": 6.471569585800171,
|
|
"epoch": 0.0634480023793001,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004795,
|
|
"loss": 6.4209,
|
|
"mean_token_accuracy": 0.09959583207964898,
|
|
"num_tokens": 2101825.0,
|
|
"step": 960
|
|
},
|
|
{
|
|
"entropy": 6.467436027526856,
|
|
"epoch": 0.0637784607250256,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000482,
|
|
"loss": 6.3872,
|
|
"mean_token_accuracy": 0.1006256528198719,
|
|
"num_tokens": 2113847.0,
|
|
"step": 965
|
|
},
|
|
{
|
|
"entropy": 6.3760229587554935,
|
|
"epoch": 0.06410891907075113,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004845,
|
|
"loss": 6.3764,
|
|
"mean_token_accuracy": 0.10424125492572785,
|
|
"num_tokens": 2124855.0,
|
|
"step": 970
|
|
},
|
|
{
|
|
"entropy": 6.363870906829834,
|
|
"epoch": 0.06443937741647665,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000487,
|
|
"loss": 6.3566,
|
|
"mean_token_accuracy": 0.10852005258202553,
|
|
"num_tokens": 2135164.0,
|
|
"step": 975
|
|
},
|
|
{
|
|
"entropy": 6.540998125076294,
|
|
"epoch": 0.06476983576220217,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004895,
|
|
"loss": 6.471,
|
|
"mean_token_accuracy": 0.09465332999825478,
|
|
"num_tokens": 2146458.0,
|
|
"step": 980
|
|
},
|
|
{
|
|
"entropy": 6.4124726295471195,
|
|
"epoch": 0.0651002941079277,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000492,
|
|
"loss": 6.4226,
|
|
"mean_token_accuracy": 0.10414307788014412,
|
|
"num_tokens": 2159184.0,
|
|
"step": 985
|
|
},
|
|
{
|
|
"entropy": 6.3850232601165775,
|
|
"epoch": 0.06543075245365322,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004945,
|
|
"loss": 6.3661,
|
|
"mean_token_accuracy": 0.10461859554052352,
|
|
"num_tokens": 2170424.0,
|
|
"step": 990
|
|
},
|
|
{
|
|
"entropy": 6.399285221099854,
|
|
"epoch": 0.06576121079937874,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000497,
|
|
"loss": 6.3683,
|
|
"mean_token_accuracy": 0.1082889124751091,
|
|
"num_tokens": 2181193.0,
|
|
"step": 995
|
|
},
|
|
{
|
|
"entropy": 6.315083360671997,
|
|
"epoch": 0.06609166914510425,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004995,
|
|
"loss": 6.3219,
|
|
"mean_token_accuracy": 0.10567663609981537,
|
|
"num_tokens": 2191963.0,
|
|
"step": 1000
|
|
},
|
|
{
|
|
"entropy": 6.397964954376221,
|
|
"epoch": 0.06642212749082978,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000499998026082006,
|
|
"loss": 6.3973,
|
|
"mean_token_accuracy": 0.10832930952310563,
|
|
"num_tokens": 2202620.0,
|
|
"step": 1005
|
|
},
|
|
{
|
|
"entropy": 6.533894824981689,
|
|
"epoch": 0.0667525858365553,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004999900070995136,
|
|
"loss": 6.4228,
|
|
"mean_token_accuracy": 0.10299602895975113,
|
|
"num_tokens": 2213271.0,
|
|
"step": 1010
|
|
},
|
|
{
|
|
"entropy": 6.368393087387085,
|
|
"epoch": 0.06708304418228082,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999758199023239,
|
|
"loss": 6.4129,
|
|
"mean_token_accuracy": 0.09798410907387733,
|
|
"num_tokens": 2223556.0,
|
|
"step": 1015
|
|
},
|
|
{
|
|
"entropy": 6.429405403137207,
|
|
"epoch": 0.06741350252800635,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999554648793858,
|
|
"loss": 6.4296,
|
|
"mean_token_accuracy": 0.10144790187478066,
|
|
"num_tokens": 2233866.0,
|
|
"step": 1020
|
|
},
|
|
{
|
|
"entropy": 6.420916748046875,
|
|
"epoch": 0.06774396087373187,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004999289425887425,
|
|
"loss": 6.442,
|
|
"mean_token_accuracy": 0.10680803060531616,
|
|
"num_tokens": 2246388.0,
|
|
"step": 1025
|
|
},
|
|
{
|
|
"entropy": 6.485070371627808,
|
|
"epoch": 0.0680744192194574,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998962537575161,
|
|
"loss": 6.4173,
|
|
"mean_token_accuracy": 0.11337929293513298,
|
|
"num_tokens": 2257799.0,
|
|
"step": 1030
|
|
},
|
|
{
|
|
"entropy": 6.429631853103638,
|
|
"epoch": 0.0684048775651829,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998573992818874,
|
|
"loss": 6.4513,
|
|
"mean_token_accuracy": 0.09858574867248535,
|
|
"num_tokens": 2269320.0,
|
|
"step": 1035
|
|
},
|
|
{
|
|
"entropy": 6.250541496276855,
|
|
"epoch": 0.06873533591090843,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004998123802270715,
|
|
"loss": 6.299,
|
|
"mean_token_accuracy": 0.10207094028592109,
|
|
"num_tokens": 2280002.0,
|
|
"step": 1040
|
|
},
|
|
{
|
|
"entropy": 6.494193410873413,
|
|
"epoch": 0.06906579425663395,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004997611978272886,
|
|
"loss": 6.491,
|
|
"mean_token_accuracy": 0.1080724485218525,
|
|
"num_tokens": 2291698.0,
|
|
"step": 1045
|
|
},
|
|
{
|
|
"entropy": 6.4392985820770265,
|
|
"epoch": 0.06939625260235947,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004997038534857298,
|
|
"loss": 6.4857,
|
|
"mean_token_accuracy": 0.10086370706558227,
|
|
"num_tokens": 2302946.0,
|
|
"step": 1050
|
|
},
|
|
{
|
|
"entropy": 6.394264602661133,
|
|
"epoch": 0.069726710948085,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004996403487745194,
|
|
"loss": 6.4254,
|
|
"mean_token_accuracy": 0.10714520588517189,
|
|
"num_tokens": 2312556.0,
|
|
"step": 1055
|
|
},
|
|
{
|
|
"entropy": 6.5946221351623535,
|
|
"epoch": 0.07005716929381052,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000499570685434671,
|
|
"loss": 6.5625,
|
|
"mean_token_accuracy": 0.10093791782855988,
|
|
"num_tokens": 2325099.0,
|
|
"step": 1060
|
|
},
|
|
{
|
|
"entropy": 6.45420503616333,
|
|
"epoch": 0.07038762763953604,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004994948653760405,
|
|
"loss": 6.451,
|
|
"mean_token_accuracy": 0.10265908166766166,
|
|
"num_tokens": 2336561.0,
|
|
"step": 1065
|
|
},
|
|
{
|
|
"entropy": 6.294920635223389,
|
|
"epoch": 0.07071808598526155,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004994128906772729,
|
|
"loss": 6.3643,
|
|
"mean_token_accuracy": 0.1072157271206379,
|
|
"num_tokens": 2346264.0,
|
|
"step": 1070
|
|
},
|
|
{
|
|
"entropy": 6.44938645362854,
|
|
"epoch": 0.07104854433098708,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000499324763585746,
|
|
"loss": 6.3667,
|
|
"mean_token_accuracy": 0.1099700540304184,
|
|
"num_tokens": 2355627.0,
|
|
"step": 1075
|
|
},
|
|
{
|
|
"entropy": 6.320340871810913,
|
|
"epoch": 0.0713790026767126,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004992304865175085,
|
|
"loss": 6.3115,
|
|
"mean_token_accuracy": 0.10740844681859016,
|
|
"num_tokens": 2366693.0,
|
|
"step": 1080
|
|
},
|
|
{
|
|
"entropy": 6.422510385513306,
|
|
"epoch": 0.07170946102243812,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004991300620572138,
|
|
"loss": 6.3416,
|
|
"mean_token_accuracy": 0.10623999536037446,
|
|
"num_tokens": 2376954.0,
|
|
"step": 1085
|
|
},
|
|
{
|
|
"entropy": 6.327064418792725,
|
|
"epoch": 0.07203991936816365,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004990234929580494,
|
|
"loss": 6.4336,
|
|
"mean_token_accuracy": 0.09785263687372207,
|
|
"num_tokens": 2388023.0,
|
|
"step": 1090
|
|
},
|
|
{
|
|
"entropy": 6.400377702713013,
|
|
"epoch": 0.07237037771388917,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004989107821416609,
|
|
"loss": 6.3651,
|
|
"mean_token_accuracy": 0.1035020537674427,
|
|
"num_tokens": 2397683.0,
|
|
"step": 1095
|
|
},
|
|
{
|
|
"entropy": 6.3421402931213375,
|
|
"epoch": 0.07270083605961468,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004987919326980723,
|
|
"loss": 6.3374,
|
|
"mean_token_accuracy": 0.10992366895079612,
|
|
"num_tokens": 2408077.0,
|
|
"step": 1100
|
|
},
|
|
{
|
|
"entropy": 6.337559461593628,
|
|
"epoch": 0.0730312944053402,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004986669478856011,
|
|
"loss": 6.3712,
|
|
"mean_token_accuracy": 0.10661208927631378,
|
|
"num_tokens": 2418938.0,
|
|
"step": 1105
|
|
},
|
|
{
|
|
"entropy": 6.382309675216675,
|
|
"epoch": 0.07336175275106573,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004985358311307688,
|
|
"loss": 6.3715,
|
|
"mean_token_accuracy": 0.1041027471423149,
|
|
"num_tokens": 2430562.0,
|
|
"step": 1110
|
|
},
|
|
{
|
|
"entropy": 6.327745485305786,
|
|
"epoch": 0.07369221109679125,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004983985860282081,
|
|
"loss": 6.4583,
|
|
"mean_token_accuracy": 0.10101124793291091,
|
|
"num_tokens": 2442734.0,
|
|
"step": 1115
|
|
},
|
|
{
|
|
"entropy": 6.42706789970398,
|
|
"epoch": 0.07402266944251677,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004982552163405623,
|
|
"loss": 6.3024,
|
|
"mean_token_accuracy": 0.11131583824753762,
|
|
"num_tokens": 2454265.0,
|
|
"step": 1120
|
|
},
|
|
{
|
|
"entropy": 6.202260732650757,
|
|
"epoch": 0.0743531277882423,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004981057259983839,
|
|
"loss": 6.2635,
|
|
"mean_token_accuracy": 0.10871926620602608,
|
|
"num_tokens": 2464545.0,
|
|
"step": 1125
|
|
},
|
|
{
|
|
"entropy": 6.418315887451172,
|
|
"epoch": 0.07468358613396782,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004979501191000262,
|
|
"loss": 6.5126,
|
|
"mean_token_accuracy": 0.09977985322475433,
|
|
"num_tokens": 2476342.0,
|
|
"step": 1130
|
|
},
|
|
{
|
|
"entropy": 6.423433876037597,
|
|
"epoch": 0.07501404447969333,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004977883999115311,
|
|
"loss": 6.4156,
|
|
"mean_token_accuracy": 0.10508456379175186,
|
|
"num_tokens": 2487279.0,
|
|
"step": 1135
|
|
},
|
|
{
|
|
"entropy": 6.342500114440918,
|
|
"epoch": 0.07534450282541885,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004976205728665113,
|
|
"loss": 6.2813,
|
|
"mean_token_accuracy": 0.10875830128788948,
|
|
"num_tokens": 2497503.0,
|
|
"step": 1140
|
|
},
|
|
{
|
|
"entropy": 6.346517181396484,
|
|
"epoch": 0.07567496117114438,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004974466425660307,
|
|
"loss": 6.3795,
|
|
"mean_token_accuracy": 0.10393059179186821,
|
|
"num_tokens": 2507990.0,
|
|
"step": 1145
|
|
},
|
|
{
|
|
"entropy": 6.343197631835937,
|
|
"epoch": 0.0760054195168699,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004972666137784759,
|
|
"loss": 6.3247,
|
|
"mean_token_accuracy": 0.10598115846514702,
|
|
"num_tokens": 2520699.0,
|
|
"step": 1150
|
|
},
|
|
{
|
|
"entropy": 6.326574993133545,
|
|
"epoch": 0.07633587786259542,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004970804914394271,
|
|
"loss": 6.3057,
|
|
"mean_token_accuracy": 0.11388499960303307,
|
|
"num_tokens": 2531027.0,
|
|
"step": 1155
|
|
},
|
|
{
|
|
"entropy": 6.389388084411621,
|
|
"epoch": 0.07666633620832095,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004968882806515225,
|
|
"loss": 6.4589,
|
|
"mean_token_accuracy": 0.10438870191574097,
|
|
"num_tokens": 2543939.0,
|
|
"step": 1160
|
|
},
|
|
{
|
|
"entropy": 6.4396069049835205,
|
|
"epoch": 0.07699679455404647,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004966899866843177,
|
|
"loss": 6.4023,
|
|
"mean_token_accuracy": 0.1009863406419754,
|
|
"num_tokens": 2555721.0,
|
|
"step": 1165
|
|
},
|
|
{
|
|
"entropy": 6.384159183502197,
|
|
"epoch": 0.07732725289977198,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000496485614974142,
|
|
"loss": 6.4926,
|
|
"mean_token_accuracy": 0.10290684588253499,
|
|
"num_tokens": 2567312.0,
|
|
"step": 1170
|
|
},
|
|
{
|
|
"entropy": 6.239294576644897,
|
|
"epoch": 0.0776577112454975,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004962751711239492,
|
|
"loss": 6.238,
|
|
"mean_token_accuracy": 0.10982146114110947,
|
|
"num_tokens": 2577992.0,
|
|
"step": 1175
|
|
},
|
|
{
|
|
"entropy": 6.390829038619995,
|
|
"epoch": 0.07798816959122302,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004960586609031636,
|
|
"loss": 6.4177,
|
|
"mean_token_accuracy": 0.10007556304335594,
|
|
"num_tokens": 2588866.0,
|
|
"step": 1180
|
|
},
|
|
{
|
|
"entropy": 6.311258459091187,
|
|
"epoch": 0.07831862793694855,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004958360902475224,
|
|
"loss": 6.4175,
|
|
"mean_token_accuracy": 0.10478579625487328,
|
|
"num_tokens": 2600053.0,
|
|
"step": 1185
|
|
},
|
|
{
|
|
"entropy": 6.347922992706299,
|
|
"epoch": 0.07864908628267407,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004956074652589125,
|
|
"loss": 6.2668,
|
|
"mean_token_accuracy": 0.10886808261275291,
|
|
"num_tokens": 2610251.0,
|
|
"step": 1190
|
|
},
|
|
{
|
|
"entropy": 6.273433685302734,
|
|
"epoch": 0.0789795446283996,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004953727922052035,
|
|
"loss": 6.3048,
|
|
"mean_token_accuracy": 0.10753131210803986,
|
|
"num_tokens": 2621316.0,
|
|
"step": 1195
|
|
},
|
|
{
|
|
"entropy": 6.365851497650146,
|
|
"epoch": 0.07931000297412512,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004951320775200756,
|
|
"loss": 6.3617,
|
|
"mean_token_accuracy": 0.11127811819314956,
|
|
"num_tokens": 2632439.0,
|
|
"step": 1200
|
|
},
|
|
{
|
|
"entropy": 6.370825147628784,
|
|
"epoch": 0.07964046131985063,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004948853278028436,
|
|
"loss": 6.3267,
|
|
"mean_token_accuracy": 0.10939299240708351,
|
|
"num_tokens": 2644006.0,
|
|
"step": 1205
|
|
},
|
|
{
|
|
"entropy": 6.228281831741333,
|
|
"epoch": 0.07997091966557615,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004946325498182755,
|
|
"loss": 6.304,
|
|
"mean_token_accuracy": 0.10606826171278953,
|
|
"num_tokens": 2655434.0,
|
|
"step": 1210
|
|
},
|
|
{
|
|
"entropy": 6.371251440048217,
|
|
"epoch": 0.08030137801130167,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004943737504964076,
|
|
"loss": 6.3195,
|
|
"mean_token_accuracy": 0.11309513822197914,
|
|
"num_tokens": 2666521.0,
|
|
"step": 1215
|
|
},
|
|
{
|
|
"entropy": 6.23853235244751,
|
|
"epoch": 0.0806318363570272,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.000494108936932354,
|
|
"loss": 6.3228,
|
|
"mean_token_accuracy": 0.10499642714858055,
|
|
"num_tokens": 2678334.0,
|
|
"step": 1220
|
|
},
|
|
{
|
|
"entropy": 6.331731510162354,
|
|
"epoch": 0.08096229470275272,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004938381163861124,
|
|
"loss": 6.361,
|
|
"mean_token_accuracy": 0.10780482292175293,
|
|
"num_tokens": 2690261.0,
|
|
"step": 1225
|
|
},
|
|
{
|
|
"entropy": 6.356092739105224,
|
|
"epoch": 0.08129275304847824,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004935612962823645,
|
|
"loss": 6.2904,
|
|
"mean_token_accuracy": 0.11208009794354439,
|
|
"num_tokens": 2702579.0,
|
|
"step": 1230
|
|
},
|
|
{
|
|
"entropy": 6.319092178344727,
|
|
"epoch": 0.08162321139420375,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004932784842102739,
|
|
"loss": 6.2844,
|
|
"mean_token_accuracy": 0.11137590855360031,
|
|
"num_tokens": 2713336.0,
|
|
"step": 1235
|
|
},
|
|
{
|
|
"entropy": 6.241940927505493,
|
|
"epoch": 0.08195366973992928,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004929896879232758,
|
|
"loss": 6.2338,
|
|
"mean_token_accuracy": 0.11121944114565849,
|
|
"num_tokens": 2724578.0,
|
|
"step": 1240
|
|
},
|
|
{
|
|
"entropy": 6.193857049942016,
|
|
"epoch": 0.0822841280856548,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004926949153388668,
|
|
"loss": 6.2239,
|
|
"mean_token_accuracy": 0.11443476602435113,
|
|
"num_tokens": 2736160.0,
|
|
"step": 1245
|
|
},
|
|
{
|
|
"entropy": 6.269001722335815,
|
|
"epoch": 0.08261458643138032,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004923941745383859,
|
|
"loss": 6.2598,
|
|
"mean_token_accuracy": 0.1093744695186615,
|
|
"num_tokens": 2748370.0,
|
|
"step": 1250
|
|
},
|
|
{
|
|
"entropy": 6.245749282836914,
|
|
"epoch": 0.08294504477710585,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000492087473766794,
|
|
"loss": 6.2235,
|
|
"mean_token_accuracy": 0.11153279915452004,
|
|
"num_tokens": 2758556.0,
|
|
"step": 1255
|
|
},
|
|
{
|
|
"entropy": 6.228459167480469,
|
|
"epoch": 0.08327550312283137,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.000491774821432448,
|
|
"loss": 6.2554,
|
|
"mean_token_accuracy": 0.10969504565000535,
|
|
"num_tokens": 2770110.0,
|
|
"step": 1260
|
|
},
|
|
{
|
|
"entropy": 6.314351272583008,
|
|
"epoch": 0.0836059614685569,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004914562261068693,
|
|
"loss": 6.3025,
|
|
"mean_token_accuracy": 0.10905899181962013,
|
|
"num_tokens": 2782226.0,
|
|
"step": 1265
|
|
},
|
|
{
|
|
"entropy": 6.236157655715942,
|
|
"epoch": 0.0839364198142824,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004911316965245098,
|
|
"loss": 6.1767,
|
|
"mean_token_accuracy": 0.11525296643376351,
|
|
"num_tokens": 2791815.0,
|
|
"step": 1270
|
|
},
|
|
{
|
|
"entropy": 6.145106315612793,
|
|
"epoch": 0.08426687816000793,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.000490801241582512,
|
|
"loss": 6.2014,
|
|
"mean_token_accuracy": 0.11409328505396843,
|
|
"num_tokens": 2802472.0,
|
|
"step": 1275
|
|
},
|
|
{
|
|
"entropy": 6.254790163040161,
|
|
"epoch": 0.08459733650573345,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000490464870340465,
|
|
"loss": 6.1966,
|
|
"mean_token_accuracy": 0.1131843589246273,
|
|
"num_tokens": 2812262.0,
|
|
"step": 1280
|
|
},
|
|
{
|
|
"entropy": 6.218746042251587,
|
|
"epoch": 0.08492779485145897,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004901225920201563,
|
|
"loss": 6.1711,
|
|
"mean_token_accuracy": 0.11364943832159043,
|
|
"num_tokens": 2821806.0,
|
|
"step": 1285
|
|
},
|
|
{
|
|
"entropy": 6.2752289295196535,
|
|
"epoch": 0.0852582531971845,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.000489774416005319,
|
|
"loss": 6.292,
|
|
"mean_token_accuracy": 0.10570647865533829,
|
|
"num_tokens": 2832544.0,
|
|
"step": 1290
|
|
},
|
|
{
|
|
"entropy": 6.2815282344818115,
|
|
"epoch": 0.08558871154291002,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004894203518413742,
|
|
"loss": 6.3097,
|
|
"mean_token_accuracy": 0.10787594094872474,
|
|
"num_tokens": 2843347.0,
|
|
"step": 1295
|
|
},
|
|
{
|
|
"entropy": 6.27464919090271,
|
|
"epoch": 0.08591916988863554,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004890604092351701,
|
|
"loss": 6.2873,
|
|
"mean_token_accuracy": 0.11007290184497834,
|
|
"num_tokens": 2854361.0,
|
|
"step": 1300
|
|
},
|
|
{
|
|
"entropy": 6.28824667930603,
|
|
"epoch": 0.08624962823436105,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.000488694598054715,
|
|
"loss": 6.2942,
|
|
"mean_token_accuracy": 0.11148815751075744,
|
|
"num_tokens": 2865716.0,
|
|
"step": 1305
|
|
},
|
|
{
|
|
"entropy": 6.313663482666016,
|
|
"epoch": 0.08658008658008658,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004883229283289071,
|
|
"loss": 6.2973,
|
|
"mean_token_accuracy": 0.11001308336853981,
|
|
"num_tokens": 2876409.0,
|
|
"step": 1310
|
|
},
|
|
{
|
|
"entropy": 6.236247873306274,
|
|
"epoch": 0.0869105449258121,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00048794541024725993,
|
|
"loss": 6.1624,
|
|
"mean_token_accuracy": 0.11299015209078789,
|
|
"num_tokens": 2885964.0,
|
|
"step": 1315
|
|
},
|
|
{
|
|
"entropy": 6.212308168411255,
|
|
"epoch": 0.08724100327153762,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004875620541596221,
|
|
"loss": 6.2009,
|
|
"mean_token_accuracy": 0.11274494603276253,
|
|
"num_tokens": 2896486.0,
|
|
"step": 1320
|
|
},
|
|
{
|
|
"entropy": 6.227869939804077,
|
|
"epoch": 0.08757146161726315,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.00048717287057589454,
|
|
"loss": 6.3043,
|
|
"mean_token_accuracy": 0.10914059206843377,
|
|
"num_tokens": 2907216.0,
|
|
"step": 1325
|
|
},
|
|
{
|
|
"entropy": 6.188024950027466,
|
|
"epoch": 0.08790191996298867,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004867778701657417,
|
|
"loss": 6.223,
|
|
"mean_token_accuracy": 0.10957143902778625,
|
|
"num_tokens": 2916975.0,
|
|
"step": 1330
|
|
},
|
|
{
|
|
"entropy": 6.274955558776855,
|
|
"epoch": 0.0882323783087142,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00048637706375829955,
|
|
"loss": 6.2648,
|
|
"mean_token_accuracy": 0.1095338560640812,
|
|
"num_tokens": 2927824.0,
|
|
"step": 1335
|
|
},
|
|
{
|
|
"entropy": 6.2339982986450195,
|
|
"epoch": 0.0885628366544397,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000485970462341878,
|
|
"loss": 6.2159,
|
|
"mean_token_accuracy": 0.11319034472107888,
|
|
"num_tokens": 2938311.0,
|
|
"step": 1340
|
|
},
|
|
{
|
|
"entropy": 6.248281240463257,
|
|
"epoch": 0.08889329500016523,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00048555807706366044,
|
|
"loss": 6.2644,
|
|
"mean_token_accuracy": 0.11580364927649497,
|
|
"num_tokens": 2948504.0,
|
|
"step": 1345
|
|
},
|
|
{
|
|
"entropy": 6.243304252624512,
|
|
"epoch": 0.08922375334589075,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.00048513991922939756,
|
|
"loss": 6.2667,
|
|
"mean_token_accuracy": 0.10695719793438911,
|
|
"num_tokens": 2959414.0,
|
|
"step": 1350
|
|
},
|
|
{
|
|
"entropy": 6.278574228286743,
|
|
"epoch": 0.08955421169161627,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00048471600030309744,
|
|
"loss": 6.2457,
|
|
"mean_token_accuracy": 0.11053696125745774,
|
|
"num_tokens": 2969739.0,
|
|
"step": 1355
|
|
},
|
|
{
|
|
"entropy": 6.252624797821045,
|
|
"epoch": 0.0898846700373418,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00048428633190671186,
|
|
"loss": 6.2745,
|
|
"mean_token_accuracy": 0.10981930121779442,
|
|
"num_tokens": 2980618.0,
|
|
"step": 1360
|
|
},
|
|
{
|
|
"entropy": 6.179713249206543,
|
|
"epoch": 0.09021512838306732,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004838509258198167,
|
|
"loss": 6.2588,
|
|
"mean_token_accuracy": 0.11370926424860954,
|
|
"num_tokens": 2993005.0,
|
|
"step": 1365
|
|
},
|
|
{
|
|
"entropy": 6.325649785995483,
|
|
"epoch": 0.09054558672879283,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00048340979397929,
|
|
"loss": 6.2234,
|
|
"mean_token_accuracy": 0.1116867408156395,
|
|
"num_tokens": 3003951.0,
|
|
"step": 1370
|
|
},
|
|
{
|
|
"entropy": 6.122556161880493,
|
|
"epoch": 0.09087604507451835,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.00048296294847898386,
|
|
"loss": 6.1785,
|
|
"mean_token_accuracy": 0.1196735866367817,
|
|
"num_tokens": 3014347.0,
|
|
"step": 1375
|
|
},
|
|
{
|
|
"entropy": 6.27095890045166,
|
|
"epoch": 0.09120650342024388,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004825104015693934,
|
|
"loss": 6.2813,
|
|
"mean_token_accuracy": 0.11019450649619103,
|
|
"num_tokens": 3025938.0,
|
|
"step": 1380
|
|
},
|
|
{
|
|
"entropy": 6.216333627700806,
|
|
"epoch": 0.0915369617659694,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004820521656573208,
|
|
"loss": 6.23,
|
|
"mean_token_accuracy": 0.11627952679991722,
|
|
"num_tokens": 3036774.0,
|
|
"step": 1385
|
|
},
|
|
{
|
|
"entropy": 6.2260870933532715,
|
|
"epoch": 0.09186742011169492,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.00048158825330553505,
|
|
"loss": 6.2357,
|
|
"mean_token_accuracy": 0.1122400440275669,
|
|
"num_tokens": 3048767.0,
|
|
"step": 1390
|
|
},
|
|
{
|
|
"entropy": 6.2184850692749025,
|
|
"epoch": 0.09219787845742045,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00048111867723242763,
|
|
"loss": 6.1944,
|
|
"mean_token_accuracy": 0.10921861827373505,
|
|
"num_tokens": 3058632.0,
|
|
"step": 1395
|
|
},
|
|
{
|
|
"entropy": 6.121122741699219,
|
|
"epoch": 0.09252833680314597,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004806434503116637,
|
|
"loss": 6.0642,
|
|
"mean_token_accuracy": 0.12121142446994781,
|
|
"num_tokens": 3069288.0,
|
|
"step": 1400
|
|
},
|
|
{
|
|
"entropy": 6.113697719573975,
|
|
"epoch": 0.09285879514887148,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004801625855718296,
|
|
"loss": 6.1353,
|
|
"mean_token_accuracy": 0.10769173875451088,
|
|
"num_tokens": 3079060.0,
|
|
"step": 1405
|
|
},
|
|
{
|
|
"entropy": 6.21345329284668,
|
|
"epoch": 0.093189253494597,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00047967609619607477,
|
|
"loss": 6.2299,
|
|
"mean_token_accuracy": 0.10818874016404152,
|
|
"num_tokens": 3089864.0,
|
|
"step": 1410
|
|
},
|
|
{
|
|
"entropy": 6.25667405128479,
|
|
"epoch": 0.09351971184032253,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004791839955217513,
|
|
"loss": 6.2142,
|
|
"mean_token_accuracy": 0.10830713286995888,
|
|
"num_tokens": 3099968.0,
|
|
"step": 1415
|
|
},
|
|
{
|
|
"entropy": 6.209473514556885,
|
|
"epoch": 0.09385017018604805,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00047868629704004786,
|
|
"loss": 6.1982,
|
|
"mean_token_accuracy": 0.10743900611996651,
|
|
"num_tokens": 3110354.0,
|
|
"step": 1420
|
|
},
|
|
{
|
|
"entropy": 6.180089139938355,
|
|
"epoch": 0.09418062853177357,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00047818301439561965,
|
|
"loss": 6.1477,
|
|
"mean_token_accuracy": 0.11282439082860947,
|
|
"num_tokens": 3121638.0,
|
|
"step": 1425
|
|
},
|
|
{
|
|
"entropy": 6.140780687332153,
|
|
"epoch": 0.0945110868774991,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00047767416138621454,
|
|
"loss": 6.1543,
|
|
"mean_token_accuracy": 0.11213898211717606,
|
|
"num_tokens": 3132609.0,
|
|
"step": 1430
|
|
},
|
|
{
|
|
"entropy": 6.257613754272461,
|
|
"epoch": 0.09484154522322462,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.000477159751962295,
|
|
"loss": 6.2194,
|
|
"mean_token_accuracy": 0.11128115206956864,
|
|
"num_tokens": 3144445.0,
|
|
"step": 1435
|
|
},
|
|
{
|
|
"entropy": 6.14837908744812,
|
|
"epoch": 0.09517200356895013,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00047663980022665507,
|
|
"loss": 6.1785,
|
|
"mean_token_accuracy": 0.10812792181968689,
|
|
"num_tokens": 3154942.0,
|
|
"step": 1440
|
|
},
|
|
{
|
|
"entropy": 6.268062877655029,
|
|
"epoch": 0.09550246191467565,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00047611432043403437,
|
|
"loss": 6.1964,
|
|
"mean_token_accuracy": 0.11239229813218117,
|
|
"num_tokens": 3165444.0,
|
|
"step": 1445
|
|
},
|
|
{
|
|
"entropy": 6.080770492553711,
|
|
"epoch": 0.09583292026040117,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004755833269907267,
|
|
"loss": 6.1447,
|
|
"mean_token_accuracy": 0.10863324329257011,
|
|
"num_tokens": 3175228.0,
|
|
"step": 1450
|
|
},
|
|
{
|
|
"entropy": 6.161494970321655,
|
|
"epoch": 0.0961633786061267,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004750468344541857,
|
|
"loss": 6.1406,
|
|
"mean_token_accuracy": 0.11648099794983864,
|
|
"num_tokens": 3186028.0,
|
|
"step": 1455
|
|
},
|
|
{
|
|
"entropy": 6.114691972732544,
|
|
"epoch": 0.09649383695185222,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00047450485753262525,
|
|
"loss": 6.1006,
|
|
"mean_token_accuracy": 0.12160674259066581,
|
|
"num_tokens": 3196351.0,
|
|
"step": 1460
|
|
},
|
|
{
|
|
"entropy": 6.209639406204223,
|
|
"epoch": 0.09682429529757774,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.00047395741108461633,
|
|
"loss": 6.1886,
|
|
"mean_token_accuracy": 0.11488557681441307,
|
|
"num_tokens": 3207788.0,
|
|
"step": 1465
|
|
},
|
|
{
|
|
"entropy": 6.155808544158935,
|
|
"epoch": 0.09715475364330327,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00047340451011867985,
|
|
"loss": 6.2009,
|
|
"mean_token_accuracy": 0.11256440505385398,
|
|
"num_tokens": 3219941.0,
|
|
"step": 1470
|
|
},
|
|
{
|
|
"entropy": 6.30653486251831,
|
|
"epoch": 0.09748521198902878,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00047284616979287515,
|
|
"loss": 6.1727,
|
|
"mean_token_accuracy": 0.11391912326216698,
|
|
"num_tokens": 3229199.0,
|
|
"step": 1475
|
|
},
|
|
{
|
|
"entropy": 6.140384721755981,
|
|
"epoch": 0.0978156703347543,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00047228240541438433,
|
|
"loss": 6.267,
|
|
"mean_token_accuracy": 0.11459414213895798,
|
|
"num_tokens": 3239414.0,
|
|
"step": 1480
|
|
},
|
|
{
|
|
"entropy": 6.296479082107544,
|
|
"epoch": 0.09814612868047982,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00047171323243909257,
|
|
"loss": 6.2115,
|
|
"mean_token_accuracy": 0.10864720344543458,
|
|
"num_tokens": 3250403.0,
|
|
"step": 1485
|
|
},
|
|
{
|
|
"entropy": 6.155523252487183,
|
|
"epoch": 0.09847658702620535,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.00047113866647116457,
|
|
"loss": 6.2497,
|
|
"mean_token_accuracy": 0.11157322898507119,
|
|
"num_tokens": 3262579.0,
|
|
"step": 1490
|
|
},
|
|
{
|
|
"entropy": 6.1816212177276615,
|
|
"epoch": 0.09880704537193087,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004705587232626164,
|
|
"loss": 6.1422,
|
|
"mean_token_accuracy": 0.11603116244077682,
|
|
"num_tokens": 3273750.0,
|
|
"step": 1495
|
|
},
|
|
{
|
|
"entropy": 6.107717561721802,
|
|
"epoch": 0.0991375037176564,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00046997341871288424,
|
|
"loss": 6.1289,
|
|
"mean_token_accuracy": 0.12265687435865402,
|
|
"num_tokens": 3283996.0,
|
|
"step": 1500
|
|
},
|
|
{
|
|
"entropy": 6.131625509262085,
|
|
"epoch": 0.0994679620633819,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004693827688683879,
|
|
"loss": 6.0187,
|
|
"mean_token_accuracy": 0.11918074786663055,
|
|
"num_tokens": 3292943.0,
|
|
"step": 1505
|
|
},
|
|
{
|
|
"entropy": 6.132188510894776,
|
|
"epoch": 0.09979842040910743,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004687867899220914,
|
|
"loss": 6.1835,
|
|
"mean_token_accuracy": 0.10584012866020202,
|
|
"num_tokens": 3304191.0,
|
|
"step": 1510
|
|
},
|
|
{
|
|
"entropy": 6.163652515411377,
|
|
"epoch": 0.10012887875483295,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.00046818549821305846,
|
|
"loss": 6.2052,
|
|
"mean_token_accuracy": 0.11709263175725937,
|
|
"num_tokens": 3315975.0,
|
|
"step": 1515
|
|
},
|
|
{
|
|
"entropy": 6.178392648696899,
|
|
"epoch": 0.10045933710055847,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00046757891022600494,
|
|
"loss": 6.1128,
|
|
"mean_token_accuracy": 0.11773563474416733,
|
|
"num_tokens": 3325791.0,
|
|
"step": 1520
|
|
},
|
|
{
|
|
"entropy": 6.118534708023072,
|
|
"epoch": 0.100789795446284,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004669670425908471,
|
|
"loss": 6.0265,
|
|
"mean_token_accuracy": 0.12415608391165733,
|
|
"num_tokens": 3337084.0,
|
|
"step": 1525
|
|
},
|
|
{
|
|
"entropy": 6.131903266906738,
|
|
"epoch": 0.10112025379200952,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004663499120822451,
|
|
"loss": 6.188,
|
|
"mean_token_accuracy": 0.1162960797548294,
|
|
"num_tokens": 3347656.0,
|
|
"step": 1530
|
|
},
|
|
{
|
|
"entropy": 6.111458349227905,
|
|
"epoch": 0.10145071213773504,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004657275356191437,
|
|
"loss": 6.1446,
|
|
"mean_token_accuracy": 0.11285249292850494,
|
|
"num_tokens": 3358470.0,
|
|
"step": 1535
|
|
},
|
|
{
|
|
"entropy": 6.132451152801513,
|
|
"epoch": 0.10178117048346055,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00046509993026430804,
|
|
"loss": 6.1516,
|
|
"mean_token_accuracy": 0.11467810049653053,
|
|
"num_tokens": 3369785.0,
|
|
"step": 1540
|
|
},
|
|
{
|
|
"entropy": 6.037471771240234,
|
|
"epoch": 0.10211162882918608,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004644671132238558,
|
|
"loss": 6.0066,
|
|
"mean_token_accuracy": 0.11747827231884003,
|
|
"num_tokens": 3380184.0,
|
|
"step": 1545
|
|
},
|
|
{
|
|
"entropy": 6.223239707946777,
|
|
"epoch": 0.1024420871749116,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00046382910184678585,
|
|
"loss": 6.2372,
|
|
"mean_token_accuracy": 0.10368058383464814,
|
|
"num_tokens": 3392318.0,
|
|
"step": 1550
|
|
},
|
|
{
|
|
"entropy": 6.05759105682373,
|
|
"epoch": 0.10277254552063712,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004631859136245025,
|
|
"loss": 6.1011,
|
|
"mean_token_accuracy": 0.12060254365205765,
|
|
"num_tokens": 3404172.0,
|
|
"step": 1555
|
|
},
|
|
{
|
|
"entropy": 6.165526008605957,
|
|
"epoch": 0.10310300386636265,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004625375661903357,
|
|
"loss": 6.1491,
|
|
"mean_token_accuracy": 0.113789352029562,
|
|
"num_tokens": 3415094.0,
|
|
"step": 1560
|
|
},
|
|
{
|
|
"entropy": 6.157840156555176,
|
|
"epoch": 0.10343346221208817,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00046188407731905787,
|
|
"loss": 6.1138,
|
|
"mean_token_accuracy": 0.11692992597818375,
|
|
"num_tokens": 3425112.0,
|
|
"step": 1565
|
|
},
|
|
{
|
|
"entropy": 6.133219766616821,
|
|
"epoch": 0.1037639205578137,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00046122546492639643,
|
|
"loss": 6.1412,
|
|
"mean_token_accuracy": 0.11253001466393471,
|
|
"num_tokens": 3436291.0,
|
|
"step": 1570
|
|
},
|
|
{
|
|
"entropy": 6.157659387588501,
|
|
"epoch": 0.1040943789035392,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000460561747068543,
|
|
"loss": 6.0943,
|
|
"mean_token_accuracy": 0.11375325843691826,
|
|
"num_tokens": 3446272.0,
|
|
"step": 1575
|
|
},
|
|
{
|
|
"entropy": 6.066218566894531,
|
|
"epoch": 0.10442483724926473,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004598929419416578,
|
|
"loss": 6.0472,
|
|
"mean_token_accuracy": 0.11564663499593734,
|
|
"num_tokens": 3456480.0,
|
|
"step": 1580
|
|
},
|
|
{
|
|
"entropy": 6.1905122756958,
|
|
"epoch": 0.10475529559499025,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.00045921906788137123,
|
|
"loss": 6.2008,
|
|
"mean_token_accuracy": 0.11073072105646134,
|
|
"num_tokens": 3466802.0,
|
|
"step": 1585
|
|
},
|
|
{
|
|
"entropy": 6.0846182346344,
|
|
"epoch": 0.10508575394071577,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00045854014336228115,
|
|
"loss": 6.1406,
|
|
"mean_token_accuracy": 0.11512378677725792,
|
|
"num_tokens": 3477953.0,
|
|
"step": 1590
|
|
},
|
|
{
|
|
"entropy": 6.2287193775177006,
|
|
"epoch": 0.1054162122864413,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00045785618699744615,
|
|
"loss": 6.1636,
|
|
"mean_token_accuracy": 0.11149707362055779,
|
|
"num_tokens": 3489344.0,
|
|
"step": 1595
|
|
},
|
|
{
|
|
"entropy": 6.164507913589477,
|
|
"epoch": 0.10574667063216682,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00045716721753787543,
|
|
"loss": 6.163,
|
|
"mean_token_accuracy": 0.11218822970986367,
|
|
"num_tokens": 3499510.0,
|
|
"step": 1600
|
|
},
|
|
{
|
|
"entropy": 6.060268688201904,
|
|
"epoch": 0.10607712897789234,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004564732538720148,
|
|
"loss": 6.1065,
|
|
"mean_token_accuracy": 0.11604890152812004,
|
|
"num_tokens": 3511063.0,
|
|
"step": 1605
|
|
},
|
|
{
|
|
"entropy": 6.095123767852783,
|
|
"epoch": 0.10640758732361785,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.00045577431502522877,
|
|
"loss": 6.077,
|
|
"mean_token_accuracy": 0.11458933204412461,
|
|
"num_tokens": 3522439.0,
|
|
"step": 1610
|
|
},
|
|
{
|
|
"entropy": 6.216342306137085,
|
|
"epoch": 0.10673804566934338,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004550704201592787,
|
|
"loss": 6.1707,
|
|
"mean_token_accuracy": 0.1091039940714836,
|
|
"num_tokens": 3534565.0,
|
|
"step": 1615
|
|
},
|
|
{
|
|
"entropy": 6.075492000579834,
|
|
"epoch": 0.1070685040150689,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004543615885717981,
|
|
"loss": 6.1302,
|
|
"mean_token_accuracy": 0.11420867219567299,
|
|
"num_tokens": 3545181.0,
|
|
"step": 1620
|
|
},
|
|
{
|
|
"entropy": 6.105979251861572,
|
|
"epoch": 0.10739896236079442,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.00045364783969576296,
|
|
"loss": 6.061,
|
|
"mean_token_accuracy": 0.1188174806535244,
|
|
"num_tokens": 3555564.0,
|
|
"step": 1625
|
|
},
|
|
{
|
|
"entropy": 6.116254472732544,
|
|
"epoch": 0.10772942070651995,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004529291930989592,
|
|
"loss": 5.9994,
|
|
"mean_token_accuracy": 0.11808712556958198,
|
|
"num_tokens": 3566399.0,
|
|
"step": 1630
|
|
},
|
|
{
|
|
"entropy": 6.0679151058197025,
|
|
"epoch": 0.10805987905224547,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004522056684834464,
|
|
"loss": 6.1487,
|
|
"mean_token_accuracy": 0.11982507184147835,
|
|
"num_tokens": 3578976.0,
|
|
"step": 1635
|
|
},
|
|
{
|
|
"entropy": 6.144264173507691,
|
|
"epoch": 0.10839033739797098,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004514772856850173,
|
|
"loss": 6.1001,
|
|
"mean_token_accuracy": 0.11587735712528228,
|
|
"num_tokens": 3589008.0,
|
|
"step": 1640
|
|
},
|
|
{
|
|
"entropy": 6.153319311141968,
|
|
"epoch": 0.1087207957436965,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004507440646726542,
|
|
"loss": 6.2382,
|
|
"mean_token_accuracy": 0.11306579560041427,
|
|
"num_tokens": 3600143.0,
|
|
"step": 1645
|
|
},
|
|
{
|
|
"entropy": 6.108720445632935,
|
|
"epoch": 0.10905125408942203,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004500060255479818,
|
|
"loss": 6.0044,
|
|
"mean_token_accuracy": 0.12236109375953674,
|
|
"num_tokens": 3611284.0,
|
|
"step": 1650
|
|
},
|
|
{
|
|
"entropy": 6.1106945991516115,
|
|
"epoch": 0.10938171243514755,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004492631885447151,
|
|
"loss": 6.2384,
|
|
"mean_token_accuracy": 0.10738296657800675,
|
|
"num_tokens": 3623183.0,
|
|
"step": 1655
|
|
},
|
|
{
|
|
"entropy": 6.135138416290284,
|
|
"epoch": 0.10971217078087307,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.00044851557402810616,
|
|
"loss": 6.0543,
|
|
"mean_token_accuracy": 0.11862583830952644,
|
|
"num_tokens": 3633839.0,
|
|
"step": 1660
|
|
},
|
|
{
|
|
"entropy": 6.106761360168457,
|
|
"epoch": 0.1100426291265986,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00044776320249438444,
|
|
"loss": 6.0467,
|
|
"mean_token_accuracy": 0.1231298141181469,
|
|
"num_tokens": 3643711.0,
|
|
"step": 1665
|
|
},
|
|
{
|
|
"entropy": 6.166563224792481,
|
|
"epoch": 0.11037308747232412,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00044700609457019565,
|
|
"loss": 6.0615,
|
|
"mean_token_accuracy": 0.1154701866209507,
|
|
"num_tokens": 3654057.0,
|
|
"step": 1670
|
|
},
|
|
{
|
|
"entropy": 6.06359372138977,
|
|
"epoch": 0.11070354581804963,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004462442710120359,
|
|
"loss": 6.1166,
|
|
"mean_token_accuracy": 0.12230326756834983,
|
|
"num_tokens": 3666331.0,
|
|
"step": 1675
|
|
},
|
|
{
|
|
"entropy": 6.062233209609985,
|
|
"epoch": 0.11103400416377515,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.000445477752705683,
|
|
"loss": 6.1061,
|
|
"mean_token_accuracy": 0.11978174075484276,
|
|
"num_tokens": 3677348.0,
|
|
"step": 1680
|
|
},
|
|
{
|
|
"entropy": 6.206814098358154,
|
|
"epoch": 0.11136446250950068,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.00044470656066562336,
|
|
"loss": 6.1584,
|
|
"mean_token_accuracy": 0.11494633331894874,
|
|
"num_tokens": 3689437.0,
|
|
"step": 1685
|
|
},
|
|
{
|
|
"entropy": 6.122125577926636,
|
|
"epoch": 0.1116949208552262,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004439307160344765,
|
|
"loss": 6.0263,
|
|
"mean_token_accuracy": 0.11857278496026993,
|
|
"num_tokens": 3699777.0,
|
|
"step": 1690
|
|
},
|
|
{
|
|
"entropy": 6.01873550415039,
|
|
"epoch": 0.11202537920095172,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00044315024008241473,
|
|
"loss": 6.0816,
|
|
"mean_token_accuracy": 0.1186749741435051,
|
|
"num_tokens": 3709884.0,
|
|
"step": 1695
|
|
},
|
|
{
|
|
"entropy": 6.2084437847137455,
|
|
"epoch": 0.11235583754667725,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004423651542065806,
|
|
"loss": 6.1635,
|
|
"mean_token_accuracy": 0.11090115904808044,
|
|
"num_tokens": 3720108.0,
|
|
"step": 1700
|
|
},
|
|
{
|
|
"entropy": 6.058039855957031,
|
|
"epoch": 0.11268629589240277,
|
|
"grad_norm": 0.78125,
|
|
"learning_rate": 0.00044157547993050006,
|
|
"loss": 5.9818,
|
|
"mean_token_accuracy": 0.11920696869492531,
|
|
"num_tokens": 3730451.0,
|
|
"step": 1705
|
|
},
|
|
{
|
|
"entropy": 6.046294832229615,
|
|
"epoch": 0.11301675423812828,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00044078123890349227,
|
|
"loss": 6.097,
|
|
"mean_token_accuracy": 0.1181908592581749,
|
|
"num_tokens": 3741096.0,
|
|
"step": 1710
|
|
},
|
|
{
|
|
"entropy": 6.084577226638794,
|
|
"epoch": 0.1133472125838538,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00043998245290007606,
|
|
"loss": 6.0648,
|
|
"mean_token_accuracy": 0.1169357568025589,
|
|
"num_tokens": 3752315.0,
|
|
"step": 1715
|
|
},
|
|
{
|
|
"entropy": 6.056306409835815,
|
|
"epoch": 0.11367767092957932,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00043917914381937323,
|
|
"loss": 5.9981,
|
|
"mean_token_accuracy": 0.12442444041371345,
|
|
"num_tokens": 3762928.0,
|
|
"step": 1720
|
|
},
|
|
{
|
|
"entropy": 6.081887865066529,
|
|
"epoch": 0.11400812927530485,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00043837133368450815,
|
|
"loss": 6.0561,
|
|
"mean_token_accuracy": 0.12079024240374565,
|
|
"num_tokens": 3773913.0,
|
|
"step": 1725
|
|
},
|
|
{
|
|
"entropy": 6.00506706237793,
|
|
"epoch": 0.11433858762103037,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004375590446420037,
|
|
"loss": 6.0037,
|
|
"mean_token_accuracy": 0.12071179449558259,
|
|
"num_tokens": 3784118.0,
|
|
"step": 1730
|
|
},
|
|
{
|
|
"entropy": 6.0816583156585695,
|
|
"epoch": 0.1146690459667559,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004367422989611743,
|
|
"loss": 6.0532,
|
|
"mean_token_accuracy": 0.12486425340175629,
|
|
"num_tokens": 3795127.0,
|
|
"step": 1735
|
|
},
|
|
{
|
|
"entropy": 6.187271451950073,
|
|
"epoch": 0.11499950431248142,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004359211190335153,
|
|
"loss": 6.1544,
|
|
"mean_token_accuracy": 0.1165512628853321,
|
|
"num_tokens": 3806749.0,
|
|
"step": 1740
|
|
},
|
|
{
|
|
"entropy": 5.995714712142944,
|
|
"epoch": 0.11532996265820693,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00043509552737208923,
|
|
"loss": 6.0622,
|
|
"mean_token_accuracy": 0.11765437126159668,
|
|
"num_tokens": 3819638.0,
|
|
"step": 1745
|
|
},
|
|
{
|
|
"entropy": 6.09981598854065,
|
|
"epoch": 0.11566042100393245,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00043426554661090853,
|
|
"loss": 6.075,
|
|
"mean_token_accuracy": 0.1119348719716072,
|
|
"num_tokens": 3829910.0,
|
|
"step": 1750
|
|
},
|
|
{
|
|
"entropy": 6.0744712352752686,
|
|
"epoch": 0.11599087934965797,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00043343119950431516,
|
|
"loss": 6.1298,
|
|
"mean_token_accuracy": 0.1234098456799984,
|
|
"num_tokens": 3840951.0,
|
|
"step": 1755
|
|
},
|
|
{
|
|
"entropy": 6.13551893234253,
|
|
"epoch": 0.1163213376953835,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00043259250892635644,
|
|
"loss": 6.053,
|
|
"mean_token_accuracy": 0.13278661146759987,
|
|
"num_tokens": 3851925.0,
|
|
"step": 1760
|
|
},
|
|
{
|
|
"entropy": 6.041951465606689,
|
|
"epoch": 0.11665179604110902,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004317494978701582,
|
|
"loss": 6.0414,
|
|
"mean_token_accuracy": 0.11928681805729865,
|
|
"num_tokens": 3864428.0,
|
|
"step": 1765
|
|
},
|
|
{
|
|
"entropy": 6.14216046333313,
|
|
"epoch": 0.11698225438683454,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004309021894472943,
|
|
"loss": 6.0768,
|
|
"mean_token_accuracy": 0.11839759200811387,
|
|
"num_tokens": 3874973.0,
|
|
"step": 1770
|
|
},
|
|
{
|
|
"entropy": 6.017182064056397,
|
|
"epoch": 0.11731271273256007,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004300506068871534,
|
|
"loss": 6.0086,
|
|
"mean_token_accuracy": 0.1203161895275116,
|
|
"num_tokens": 3884322.0,
|
|
"step": 1775
|
|
},
|
|
{
|
|
"entropy": 6.060783767700196,
|
|
"epoch": 0.11764317107828558,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.00042919477353630135,
|
|
"loss": 6.0014,
|
|
"mean_token_accuracy": 0.12610603570938111,
|
|
"num_tokens": 3895788.0,
|
|
"step": 1780
|
|
},
|
|
{
|
|
"entropy": 6.017779397964477,
|
|
"epoch": 0.1179736294240111,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.000428334712857842,
|
|
"loss": 5.9566,
|
|
"mean_token_accuracy": 0.11848487928509713,
|
|
"num_tokens": 3906290.0,
|
|
"step": 1785
|
|
},
|
|
{
|
|
"entropy": 6.014243078231812,
|
|
"epoch": 0.11830408776973662,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00042747044843077304,
|
|
"loss": 6.019,
|
|
"mean_token_accuracy": 0.1230869933962822,
|
|
"num_tokens": 3918307.0,
|
|
"step": 1790
|
|
},
|
|
{
|
|
"entropy": 6.131927728652954,
|
|
"epoch": 0.11863454611546215,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00042660200394934047,
|
|
"loss": 5.9494,
|
|
"mean_token_accuracy": 0.12833101823925971,
|
|
"num_tokens": 3927961.0,
|
|
"step": 1795
|
|
},
|
|
{
|
|
"entropy": 6.007832765579224,
|
|
"epoch": 0.11896500446118767,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.00042572940322238844,
|
|
"loss": 6.0721,
|
|
"mean_token_accuracy": 0.12216415703296661,
|
|
"num_tokens": 3938856.0,
|
|
"step": 1800
|
|
},
|
|
{
|
|
"entropy": 6.142443132400513,
|
|
"epoch": 0.1192954628069132,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00042485267017270664,
|
|
"loss": 6.0204,
|
|
"mean_token_accuracy": 0.11401933133602142,
|
|
"num_tokens": 3949130.0,
|
|
"step": 1805
|
|
},
|
|
{
|
|
"entropy": 6.046123409271241,
|
|
"epoch": 0.1196259211526387,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004239718288363745,
|
|
"loss": 6.0282,
|
|
"mean_token_accuracy": 0.12689696326851846,
|
|
"num_tokens": 3959608.0,
|
|
"step": 1810
|
|
},
|
|
{
|
|
"entropy": 6.030874300003052,
|
|
"epoch": 0.11995637949836423,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004230869033621023,
|
|
"loss": 6.0297,
|
|
"mean_token_accuracy": 0.12190217599272728,
|
|
"num_tokens": 3970568.0,
|
|
"step": 1815
|
|
},
|
|
{
|
|
"entropy": 6.054608011245728,
|
|
"epoch": 0.12028683784408975,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004221979180105688,
|
|
"loss": 6.0547,
|
|
"mean_token_accuracy": 0.12139095738530159,
|
|
"num_tokens": 3981331.0,
|
|
"step": 1820
|
|
},
|
|
{
|
|
"entropy": 6.106698703765869,
|
|
"epoch": 0.12061729618981527,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00042130489715375645,
|
|
"loss": 6.0647,
|
|
"mean_token_accuracy": 0.12319901958107948,
|
|
"num_tokens": 3991308.0,
|
|
"step": 1825
|
|
},
|
|
{
|
|
"entropy": 6.052343559265137,
|
|
"epoch": 0.1209477545355408,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.00042040786527428335,
|
|
"loss": 6.0923,
|
|
"mean_token_accuracy": 0.11331535801291466,
|
|
"num_tokens": 4002845.0,
|
|
"step": 1830
|
|
},
|
|
{
|
|
"entropy": 6.076606750488281,
|
|
"epoch": 0.12127821288126632,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004195068469647315,
|
|
"loss": 5.9403,
|
|
"mean_token_accuracy": 0.11846193000674247,
|
|
"num_tokens": 4013965.0,
|
|
"step": 1835
|
|
},
|
|
{
|
|
"entropy": 6.006163883209228,
|
|
"epoch": 0.12160867122699184,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00041860186692697297,
|
|
"loss": 6.0103,
|
|
"mean_token_accuracy": 0.11975394338369369,
|
|
"num_tokens": 4025147.0,
|
|
"step": 1840
|
|
},
|
|
{
|
|
"entropy": 5.987787866592408,
|
|
"epoch": 0.12193912957271735,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.00041769294997149264,
|
|
"loss": 5.9685,
|
|
"mean_token_accuracy": 0.11788635551929474,
|
|
"num_tokens": 4036211.0,
|
|
"step": 1845
|
|
},
|
|
{
|
|
"entropy": 5.983676433563232,
|
|
"epoch": 0.12226958791844288,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004167801210167081,
|
|
"loss": 5.9681,
|
|
"mean_token_accuracy": 0.11938774883747101,
|
|
"num_tokens": 4047334.0,
|
|
"step": 1850
|
|
},
|
|
{
|
|
"entropy": 5.979567909240723,
|
|
"epoch": 0.1226000462641684,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004158634050882861,
|
|
"loss": 5.9698,
|
|
"mean_token_accuracy": 0.1232984036207199,
|
|
"num_tokens": 4057721.0,
|
|
"step": 1855
|
|
},
|
|
{
|
|
"entropy": 6.002678442001343,
|
|
"epoch": 0.12293050460989392,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004149428273184569,
|
|
"loss": 5.9766,
|
|
"mean_token_accuracy": 0.12730967849493027,
|
|
"num_tokens": 4068706.0,
|
|
"step": 1860
|
|
},
|
|
{
|
|
"entropy": 6.153607749938965,
|
|
"epoch": 0.12326096295561945,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004140184129453253,
|
|
"loss": 6.1081,
|
|
"mean_token_accuracy": 0.11698444038629532,
|
|
"num_tokens": 4080665.0,
|
|
"step": 1865
|
|
},
|
|
{
|
|
"entropy": 5.997483539581299,
|
|
"epoch": 0.12359142130134497,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.000413090187312178,
|
|
"loss": 5.974,
|
|
"mean_token_accuracy": 0.12393559291958808,
|
|
"num_tokens": 4090416.0,
|
|
"step": 1870
|
|
},
|
|
{
|
|
"entropy": 6.084975814819336,
|
|
"epoch": 0.1239218796470705,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004121581758667898,
|
|
"loss": 6.1249,
|
|
"mean_token_accuracy": 0.11143699139356614,
|
|
"num_tokens": 4103654.0,
|
|
"step": 1875
|
|
},
|
|
{
|
|
"entropy": 6.13955283164978,
|
|
"epoch": 0.124252337992796,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.00041122240416072533,
|
|
"loss": 6.0661,
|
|
"mean_token_accuracy": 0.11829451844096184,
|
|
"num_tokens": 4115379.0,
|
|
"step": 1880
|
|
},
|
|
{
|
|
"entropy": 6.022474384307861,
|
|
"epoch": 0.12458279633852153,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004102828978486385,
|
|
"loss": 6.005,
|
|
"mean_token_accuracy": 0.12134672105312347,
|
|
"num_tokens": 4126484.0,
|
|
"step": 1885
|
|
},
|
|
{
|
|
"entropy": 6.000612592697143,
|
|
"epoch": 0.12491325468424705,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004093396826875695,
|
|
"loss": 5.9166,
|
|
"mean_token_accuracy": 0.12053108140826226,
|
|
"num_tokens": 4136688.0,
|
|
"step": 1890
|
|
},
|
|
{
|
|
"entropy": 6.110885763168335,
|
|
"epoch": 0.12524371302997256,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.00040839278453623837,
|
|
"loss": 6.0484,
|
|
"mean_token_accuracy": 0.11308068186044692,
|
|
"num_tokens": 4148494.0,
|
|
"step": 1895
|
|
},
|
|
{
|
|
"entropy": 6.037317228317261,
|
|
"epoch": 0.1255741713756981,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004074422293543363,
|
|
"loss": 5.9727,
|
|
"mean_token_accuracy": 0.12479877322912217,
|
|
"num_tokens": 4158972.0,
|
|
"step": 1900
|
|
},
|
|
{
|
|
"entropy": 6.032406187057495,
|
|
"epoch": 0.1259046297214236,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004064880432018137,
|
|
"loss": 6.0411,
|
|
"mean_token_accuracy": 0.123694559186697,
|
|
"num_tokens": 4169272.0,
|
|
"step": 1905
|
|
},
|
|
{
|
|
"entropy": 6.020960426330566,
|
|
"epoch": 0.12623508806714914,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00040553025223816615,
|
|
"loss": 6.1126,
|
|
"mean_token_accuracy": 0.12069303393363953,
|
|
"num_tokens": 4179784.0,
|
|
"step": 1910
|
|
},
|
|
{
|
|
"entropy": 6.117973661422729,
|
|
"epoch": 0.12656554641287465,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00040456888272171653,
|
|
"loss": 6.0102,
|
|
"mean_token_accuracy": 0.1250431977212429,
|
|
"num_tokens": 4191107.0,
|
|
"step": 1915
|
|
},
|
|
{
|
|
"entropy": 5.99821195602417,
|
|
"epoch": 0.1268960047586002,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.00040360396100889577,
|
|
"loss": 5.9856,
|
|
"mean_token_accuracy": 0.1198937714099884,
|
|
"num_tokens": 4202514.0,
|
|
"step": 1920
|
|
},
|
|
{
|
|
"entropy": 6.058861970901489,
|
|
"epoch": 0.1272264631043257,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004026355135535202,
|
|
"loss": 6.0176,
|
|
"mean_token_accuracy": 0.12005358338356018,
|
|
"num_tokens": 4212774.0,
|
|
"step": 1925
|
|
},
|
|
{
|
|
"entropy": 6.005505657196045,
|
|
"epoch": 0.1275569214500512,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.000401663566906066,
|
|
"loss": 5.9843,
|
|
"mean_token_accuracy": 0.12146756052970886,
|
|
"num_tokens": 4223916.0,
|
|
"step": 1930
|
|
},
|
|
{
|
|
"entropy": 6.047685766220093,
|
|
"epoch": 0.12788737979577675,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00040068814771294134,
|
|
"loss": 5.9946,
|
|
"mean_token_accuracy": 0.12256797626614571,
|
|
"num_tokens": 4234797.0,
|
|
"step": 1935
|
|
},
|
|
{
|
|
"entropy": 6.033254909515381,
|
|
"epoch": 0.12821783814150226,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0003997092827157562,
|
|
"loss": 5.9465,
|
|
"mean_token_accuracy": 0.12523586601018905,
|
|
"num_tokens": 4244570.0,
|
|
"step": 1940
|
|
},
|
|
{
|
|
"entropy": 6.036639642715454,
|
|
"epoch": 0.1285482964872278,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.000398726998750589,
|
|
"loss": 5.9332,
|
|
"mean_token_accuracy": 0.12222968190908431,
|
|
"num_tokens": 4255886.0,
|
|
"step": 1945
|
|
},
|
|
{
|
|
"entropy": 6.083045816421508,
|
|
"epoch": 0.1288787548329533,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00039774132274725076,
|
|
"loss": 6.0507,
|
|
"mean_token_accuracy": 0.11652255430817604,
|
|
"num_tokens": 4265481.0,
|
|
"step": 1950
|
|
},
|
|
{
|
|
"entropy": 5.989598989486694,
|
|
"epoch": 0.12920921317867884,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00039675228172854707,
|
|
"loss": 5.9689,
|
|
"mean_token_accuracy": 0.135612603276968,
|
|
"num_tokens": 4276796.0,
|
|
"step": 1955
|
|
},
|
|
{
|
|
"entropy": 5.987274599075318,
|
|
"epoch": 0.12953967152440435,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0003957599028095371,
|
|
"loss": 5.9608,
|
|
"mean_token_accuracy": 0.1197905033826828,
|
|
"num_tokens": 4286545.0,
|
|
"step": 1960
|
|
},
|
|
{
|
|
"entropy": 6.03082594871521,
|
|
"epoch": 0.12987012987012986,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00039476421319679017,
|
|
"loss": 5.9624,
|
|
"mean_token_accuracy": 0.11818473339080811,
|
|
"num_tokens": 4296760.0,
|
|
"step": 1965
|
|
},
|
|
{
|
|
"entropy": 6.0703412055969235,
|
|
"epoch": 0.1302005882158554,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00039376524018764,
|
|
"loss": 6.0485,
|
|
"mean_token_accuracy": 0.11644991636276245,
|
|
"num_tokens": 4307875.0,
|
|
"step": 1970
|
|
},
|
|
{
|
|
"entropy": 6.081045722961425,
|
|
"epoch": 0.1305310465615809,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00039276301116943616,
|
|
"loss": 5.966,
|
|
"mean_token_accuracy": 0.1219286009669304,
|
|
"num_tokens": 4318112.0,
|
|
"step": 1975
|
|
},
|
|
{
|
|
"entropy": 6.0375096797943115,
|
|
"epoch": 0.13086150490730644,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0003917575536187936,
|
|
"loss": 6.0307,
|
|
"mean_token_accuracy": 0.12071197330951691,
|
|
"num_tokens": 4329160.0,
|
|
"step": 1980
|
|
},
|
|
{
|
|
"entropy": 6.029511308670044,
|
|
"epoch": 0.13119196325303195,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.00039074889510083894,
|
|
"loss": 6.0124,
|
|
"mean_token_accuracy": 0.11219448745250701,
|
|
"num_tokens": 4340679.0,
|
|
"step": 1985
|
|
},
|
|
{
|
|
"entropy": 5.994394207000733,
|
|
"epoch": 0.1315224215987575,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00038973706326845495,
|
|
"loss": 5.9142,
|
|
"mean_token_accuracy": 0.12976134046912194,
|
|
"num_tokens": 4351469.0,
|
|
"step": 1990
|
|
},
|
|
{
|
|
"entropy": 6.054664421081543,
|
|
"epoch": 0.131852879944483,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0003887220858615225,
|
|
"loss": 5.9382,
|
|
"mean_token_accuracy": 0.1238166332244873,
|
|
"num_tokens": 4362402.0,
|
|
"step": 1995
|
|
},
|
|
{
|
|
"entropy": 5.9494719982147215,
|
|
"epoch": 0.1321833382902085,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0003877039907061597,
|
|
"loss": 5.9134,
|
|
"mean_token_accuracy": 0.12591730579733848,
|
|
"num_tokens": 4373416.0,
|
|
"step": 2000
|
|
},
|
|
{
|
|
"entropy": 6.025772285461426,
|
|
"epoch": 0.13251379663593404,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0003866828057139598,
|
|
"loss": 5.9365,
|
|
"mean_token_accuracy": 0.12159456014633178,
|
|
"num_tokens": 4384088.0,
|
|
"step": 2005
|
|
},
|
|
{
|
|
"entropy": 5.989640712738037,
|
|
"epoch": 0.13284425498165955,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.00038565855888122503,
|
|
"loss": 5.969,
|
|
"mean_token_accuracy": 0.12716591879725456,
|
|
"num_tokens": 4394437.0,
|
|
"step": 2010
|
|
},
|
|
{
|
|
"entropy": 6.024784994125366,
|
|
"epoch": 0.1331747133273851,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.00038463127828819975,
|
|
"loss": 5.9863,
|
|
"mean_token_accuracy": 0.1208786502480507,
|
|
"num_tokens": 4406380.0,
|
|
"step": 2015
|
|
},
|
|
{
|
|
"entropy": 6.031035280227661,
|
|
"epoch": 0.1335051716731106,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.00038360099209830043,
|
|
"loss": 5.923,
|
|
"mean_token_accuracy": 0.11903775483369827,
|
|
"num_tokens": 4416722.0,
|
|
"step": 2020
|
|
},
|
|
{
|
|
"entropy": 5.908541202545166,
|
|
"epoch": 0.13383563001883614,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0003825677285573433,
|
|
"loss": 5.9234,
|
|
"mean_token_accuracy": 0.12334291711449623,
|
|
"num_tokens": 4428952.0,
|
|
"step": 2025
|
|
},
|
|
{
|
|
"entropy": 5.99616322517395,
|
|
"epoch": 0.13416608836456165,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00038153151599277027,
|
|
"loss": 5.9841,
|
|
"mean_token_accuracy": 0.13151775747537614,
|
|
"num_tokens": 4440708.0,
|
|
"step": 2030
|
|
},
|
|
{
|
|
"entropy": 6.00049467086792,
|
|
"epoch": 0.13449654671028716,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0003804923828128723,
|
|
"loss": 5.9187,
|
|
"mean_token_accuracy": 0.11983594074845313,
|
|
"num_tokens": 4450011.0,
|
|
"step": 2035
|
|
},
|
|
{
|
|
"entropy": 5.985984849929809,
|
|
"epoch": 0.1348270050560127,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0003794503575060104,
|
|
"loss": 5.9808,
|
|
"mean_token_accuracy": 0.11849164143204689,
|
|
"num_tokens": 4459819.0,
|
|
"step": 2040
|
|
},
|
|
{
|
|
"entropy": 6.125252723693848,
|
|
"epoch": 0.1351574634017382,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00037840546863983484,
|
|
"loss": 6.0483,
|
|
"mean_token_accuracy": 0.11972128003835678,
|
|
"num_tokens": 4471387.0,
|
|
"step": 2045
|
|
},
|
|
{
|
|
"entropy": 5.977398490905761,
|
|
"epoch": 0.13548792174746374,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0003773577448605015,
|
|
"loss": 5.9753,
|
|
"mean_token_accuracy": 0.11840699166059494,
|
|
"num_tokens": 4482656.0,
|
|
"step": 2050
|
|
},
|
|
{
|
|
"entropy": 6.073825645446777,
|
|
"epoch": 0.13581838009318925,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0003763072148918872,
|
|
"loss": 5.9501,
|
|
"mean_token_accuracy": 0.11884443014860153,
|
|
"num_tokens": 4493743.0,
|
|
"step": 2055
|
|
},
|
|
{
|
|
"entropy": 5.98469033241272,
|
|
"epoch": 0.1361488384389148,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0003752539075348017,
|
|
"loss": 5.9921,
|
|
"mean_token_accuracy": 0.12724643871188163,
|
|
"num_tokens": 4504458.0,
|
|
"step": 2060
|
|
},
|
|
{
|
|
"entropy": 6.0669393062591555,
|
|
"epoch": 0.1364792967846403,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00037419785166619817,
|
|
"loss": 5.9405,
|
|
"mean_token_accuracy": 0.12355776950716972,
|
|
"num_tokens": 4515252.0,
|
|
"step": 2065
|
|
},
|
|
{
|
|
"entropy": 5.976189231872558,
|
|
"epoch": 0.1368097551303658,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0003731390762383818,
|
|
"loss": 5.9996,
|
|
"mean_token_accuracy": 0.11911048516631126,
|
|
"num_tokens": 4525897.0,
|
|
"step": 2070
|
|
},
|
|
{
|
|
"entropy": 5.995615148544312,
|
|
"epoch": 0.13714021347609134,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0003720776102782158,
|
|
"loss": 5.9157,
|
|
"mean_token_accuracy": 0.12931742668151855,
|
|
"num_tokens": 4536880.0,
|
|
"step": 2075
|
|
},
|
|
{
|
|
"entropy": 6.001523160934449,
|
|
"epoch": 0.13747067182181685,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00037101348288632555,
|
|
"loss": 5.9563,
|
|
"mean_token_accuracy": 0.12963717803359032,
|
|
"num_tokens": 4548393.0,
|
|
"step": 2080
|
|
},
|
|
{
|
|
"entropy": 6.018896532058716,
|
|
"epoch": 0.1378011301675424,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0003699467232363012,
|
|
"loss": 5.9081,
|
|
"mean_token_accuracy": 0.12658436149358748,
|
|
"num_tokens": 4558815.0,
|
|
"step": 2085
|
|
},
|
|
{
|
|
"entropy": 5.919460487365723,
|
|
"epoch": 0.1381315885132679,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0003688773605738973,
|
|
"loss": 5.8264,
|
|
"mean_token_accuracy": 0.13002557456493377,
|
|
"num_tokens": 4569635.0,
|
|
"step": 2090
|
|
},
|
|
{
|
|
"entropy": 6.057313346862793,
|
|
"epoch": 0.13846204685899344,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00036780542421623134,
|
|
"loss": 6.0051,
|
|
"mean_token_accuracy": 0.11859628185629845,
|
|
"num_tokens": 4580530.0,
|
|
"step": 2095
|
|
},
|
|
{
|
|
"entropy": 6.086062860488892,
|
|
"epoch": 0.13879250520471895,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0003667309435509802,
|
|
"loss": 5.9005,
|
|
"mean_token_accuracy": 0.12926798388361932,
|
|
"num_tokens": 4590571.0,
|
|
"step": 2100
|
|
},
|
|
{
|
|
"entropy": 5.9572924137115475,
|
|
"epoch": 0.13912296355044446,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0003656539480355741,
|
|
"loss": 6.011,
|
|
"mean_token_accuracy": 0.11958485841751099,
|
|
"num_tokens": 4601815.0,
|
|
"step": 2105
|
|
},
|
|
{
|
|
"entropy": 5.969584894180298,
|
|
"epoch": 0.13945342189617,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0003645744671963891,
|
|
"loss": 5.9562,
|
|
"mean_token_accuracy": 0.12423629984259606,
|
|
"num_tokens": 4612178.0,
|
|
"step": 2110
|
|
},
|
|
{
|
|
"entropy": 6.156944608688354,
|
|
"epoch": 0.1397838802418955,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0003634925306279376,
|
|
"loss": 6.0497,
|
|
"mean_token_accuracy": 0.11549849137663841,
|
|
"num_tokens": 4623633.0,
|
|
"step": 2115
|
|
},
|
|
{
|
|
"entropy": 5.993225145339966,
|
|
"epoch": 0.14011433858762104,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0003624081679920574,
|
|
"loss": 5.8725,
|
|
"mean_token_accuracy": 0.1219449669122696,
|
|
"num_tokens": 4633906.0,
|
|
"step": 2120
|
|
},
|
|
{
|
|
"entropy": 5.977391147613526,
|
|
"epoch": 0.14044479693334655,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0003613214090170977,
|
|
"loss": 6.0342,
|
|
"mean_token_accuracy": 0.12138277366757393,
|
|
"num_tokens": 4645456.0,
|
|
"step": 2125
|
|
},
|
|
{
|
|
"entropy": 6.09858512878418,
|
|
"epoch": 0.1407752552790721,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0003602322834971048,
|
|
"loss": 6.0141,
|
|
"mean_token_accuracy": 0.12055039256811143,
|
|
"num_tokens": 4657179.0,
|
|
"step": 2130
|
|
},
|
|
{
|
|
"entropy": 6.032768058776855,
|
|
"epoch": 0.1411057136247976,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0003591408212910051,
|
|
"loss": 5.92,
|
|
"mean_token_accuracy": 0.12781096920371054,
|
|
"num_tokens": 4667537.0,
|
|
"step": 2135
|
|
},
|
|
{
|
|
"entropy": 5.939779472351074,
|
|
"epoch": 0.1414361719705231,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0003580470523217863,
|
|
"loss": 5.8569,
|
|
"mean_token_accuracy": 0.13010146841406822,
|
|
"num_tokens": 4677928.0,
|
|
"step": 2140
|
|
},
|
|
{
|
|
"entropy": 6.003098058700561,
|
|
"epoch": 0.14176663031624864,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0003569510065756771,
|
|
"loss": 5.9134,
|
|
"mean_token_accuracy": 0.12065098583698272,
|
|
"num_tokens": 4689008.0,
|
|
"step": 2145
|
|
},
|
|
{
|
|
"entropy": 5.916090440750122,
|
|
"epoch": 0.14209708866197415,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0003558527141013254,
|
|
"loss": 5.8429,
|
|
"mean_token_accuracy": 0.12585493326187133,
|
|
"num_tokens": 4699298.0,
|
|
"step": 2150
|
|
},
|
|
{
|
|
"entropy": 5.947958374023438,
|
|
"epoch": 0.1424275470076997,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0003547522050089742,
|
|
"loss": 5.8352,
|
|
"mean_token_accuracy": 0.13155150935053825,
|
|
"num_tokens": 4710676.0,
|
|
"step": 2155
|
|
},
|
|
{
|
|
"entropy": 6.014295148849487,
|
|
"epoch": 0.1427580053534252,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00035364950946963606,
|
|
"loss": 5.9319,
|
|
"mean_token_accuracy": 0.1239827185869217,
|
|
"num_tokens": 4721449.0,
|
|
"step": 2160
|
|
},
|
|
{
|
|
"entropy": 5.884983682632447,
|
|
"epoch": 0.1430884636991507,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0003525446577142663,
|
|
"loss": 5.921,
|
|
"mean_token_accuracy": 0.12243939265608787,
|
|
"num_tokens": 4732782.0,
|
|
"step": 2165
|
|
},
|
|
{
|
|
"entropy": 6.044854259490966,
|
|
"epoch": 0.14341892204487625,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00035143768003293395,
|
|
"loss": 5.9436,
|
|
"mean_token_accuracy": 0.12090348973870277,
|
|
"num_tokens": 4743803.0,
|
|
"step": 2170
|
|
},
|
|
{
|
|
"entropy": 6.011450004577637,
|
|
"epoch": 0.14374938039060176,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0003503286067739913,
|
|
"loss": 5.8529,
|
|
"mean_token_accuracy": 0.12691977992653847,
|
|
"num_tokens": 4753956.0,
|
|
"step": 2175
|
|
},
|
|
{
|
|
"entropy": 5.913992214202881,
|
|
"epoch": 0.1440798387363273,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00034921746834324193,
|
|
"loss": 5.8976,
|
|
"mean_token_accuracy": 0.12181725725531578,
|
|
"num_tokens": 4764107.0,
|
|
"step": 2180
|
|
},
|
|
{
|
|
"entropy": 5.936023950576782,
|
|
"epoch": 0.1444102970820528,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0003481042952031072,
|
|
"loss": 5.9791,
|
|
"mean_token_accuracy": 0.11868964433670044,
|
|
"num_tokens": 4777517.0,
|
|
"step": 2185
|
|
},
|
|
{
|
|
"entropy": 6.088853359222412,
|
|
"epoch": 0.14474075542777834,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0003469891178717911,
|
|
"loss": 5.9548,
|
|
"mean_token_accuracy": 0.12576491236686707,
|
|
"num_tokens": 4788646.0,
|
|
"step": 2190
|
|
},
|
|
{
|
|
"entropy": 5.935952997207641,
|
|
"epoch": 0.14507121377350385,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0003458719669224436,
|
|
"loss": 5.8414,
|
|
"mean_token_accuracy": 0.12711916491389275,
|
|
"num_tokens": 4800056.0,
|
|
"step": 2195
|
|
},
|
|
{
|
|
"entropy": 5.994973230361938,
|
|
"epoch": 0.14540167211922936,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0003447528729823221,
|
|
"loss": 5.9134,
|
|
"mean_token_accuracy": 0.12803838774561882,
|
|
"num_tokens": 4811750.0,
|
|
"step": 2200
|
|
},
|
|
{
|
|
"entropy": 5.972018241882324,
|
|
"epoch": 0.1457321304649549,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0003436318667319525,
|
|
"loss": 5.7915,
|
|
"mean_token_accuracy": 0.13188241943717002,
|
|
"num_tokens": 4821246.0,
|
|
"step": 2205
|
|
},
|
|
{
|
|
"entropy": 5.945446491241455,
|
|
"epoch": 0.1460625888106804,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00034250897890428716,
|
|
"loss": 5.9351,
|
|
"mean_token_accuracy": 0.12208826020359993,
|
|
"num_tokens": 4830997.0,
|
|
"step": 2210
|
|
},
|
|
{
|
|
"entropy": 5.980181550979614,
|
|
"epoch": 0.14639304715640594,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0003413842402838633,
|
|
"loss": 5.9413,
|
|
"mean_token_accuracy": 0.12774869054555893,
|
|
"num_tokens": 4841832.0,
|
|
"step": 2215
|
|
},
|
|
{
|
|
"entropy": 6.013609981536865,
|
|
"epoch": 0.14672350550213145,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00034025768170595834,
|
|
"loss": 5.9338,
|
|
"mean_token_accuracy": 0.1231840044260025,
|
|
"num_tokens": 4853019.0,
|
|
"step": 2220
|
|
},
|
|
{
|
|
"entropy": 5.919531583786011,
|
|
"epoch": 0.147053963847857,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0003391293340557446,
|
|
"loss": 5.8076,
|
|
"mean_token_accuracy": 0.13418867141008378,
|
|
"num_tokens": 4863154.0,
|
|
"step": 2225
|
|
},
|
|
{
|
|
"entropy": 5.950919771194458,
|
|
"epoch": 0.1473844221935825,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0003379992282674431,
|
|
"loss": 5.8671,
|
|
"mean_token_accuracy": 0.12605979815125465,
|
|
"num_tokens": 4874417.0,
|
|
"step": 2230
|
|
},
|
|
{
|
|
"entropy": 5.9616920948028564,
|
|
"epoch": 0.147714880539308,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0003368673953234749,
|
|
"loss": 5.8532,
|
|
"mean_token_accuracy": 0.12495729625225067,
|
|
"num_tokens": 4884938.0,
|
|
"step": 2235
|
|
},
|
|
{
|
|
"entropy": 5.936260986328125,
|
|
"epoch": 0.14804533888503354,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00033573386625361176,
|
|
"loss": 5.915,
|
|
"mean_token_accuracy": 0.13103888630867006,
|
|
"num_tokens": 4896924.0,
|
|
"step": 2240
|
|
},
|
|
{
|
|
"entropy": 5.940017747879028,
|
|
"epoch": 0.14837579723075905,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00033459867213412567,
|
|
"loss": 5.8129,
|
|
"mean_token_accuracy": 0.12942383736371993,
|
|
"num_tokens": 4907832.0,
|
|
"step": 2245
|
|
},
|
|
{
|
|
"entropy": 5.957295179367065,
|
|
"epoch": 0.1487062555764846,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.000333461844086937,
|
|
"loss": 5.8806,
|
|
"mean_token_accuracy": 0.12414975464344025,
|
|
"num_tokens": 4918540.0,
|
|
"step": 2250
|
|
},
|
|
{
|
|
"entropy": 5.988948202133178,
|
|
"epoch": 0.1490367139222101,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00033232341327876097,
|
|
"loss": 5.9191,
|
|
"mean_token_accuracy": 0.12228220328688622,
|
|
"num_tokens": 4928554.0,
|
|
"step": 2255
|
|
},
|
|
{
|
|
"entropy": 5.9447300910949705,
|
|
"epoch": 0.14936717226793564,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0003311834109202531,
|
|
"loss": 5.8314,
|
|
"mean_token_accuracy": 0.1241962768137455,
|
|
"num_tokens": 4938940.0,
|
|
"step": 2260
|
|
},
|
|
{
|
|
"entropy": 5.9421549320220945,
|
|
"epoch": 0.14969763061366115,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00033004186826515416,
|
|
"loss": 5.8816,
|
|
"mean_token_accuracy": 0.13139158338308335,
|
|
"num_tokens": 4948891.0,
|
|
"step": 2265
|
|
},
|
|
{
|
|
"entropy": 5.893658065795899,
|
|
"epoch": 0.15002808895938666,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0003288988166094324,
|
|
"loss": 5.8451,
|
|
"mean_token_accuracy": 0.13356359601020812,
|
|
"num_tokens": 4959621.0,
|
|
"step": 2270
|
|
},
|
|
{
|
|
"entropy": 5.96704134941101,
|
|
"epoch": 0.1503585473051122,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.00032775428729042656,
|
|
"loss": 5.8639,
|
|
"mean_token_accuracy": 0.13060243502259256,
|
|
"num_tokens": 4971229.0,
|
|
"step": 2275
|
|
},
|
|
{
|
|
"entropy": 5.943797588348389,
|
|
"epoch": 0.1506890056508377,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000326608311685986,
|
|
"loss": 5.9113,
|
|
"mean_token_accuracy": 0.12553274035453796,
|
|
"num_tokens": 4983412.0,
|
|
"step": 2280
|
|
},
|
|
{
|
|
"entropy": 5.976533365249634,
|
|
"epoch": 0.15101946399656324,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0003254609212136108,
|
|
"loss": 5.8601,
|
|
"mean_token_accuracy": 0.12690886855125427,
|
|
"num_tokens": 4995402.0,
|
|
"step": 2285
|
|
},
|
|
{
|
|
"entropy": 5.937811088562012,
|
|
"epoch": 0.15134992234228875,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.00032431214732959036,
|
|
"loss": 5.8095,
|
|
"mean_token_accuracy": 0.13060305640101433,
|
|
"num_tokens": 5005278.0,
|
|
"step": 2290
|
|
},
|
|
{
|
|
"entropy": 5.977418279647827,
|
|
"epoch": 0.1516803806880143,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.000323162021528141,
|
|
"loss": 5.8761,
|
|
"mean_token_accuracy": 0.13133179917931556,
|
|
"num_tokens": 5018083.0,
|
|
"step": 2295
|
|
},
|
|
{
|
|
"entropy": 5.836956930160523,
|
|
"epoch": 0.1520108390337398,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.00032201057534054264,
|
|
"loss": 5.8377,
|
|
"mean_token_accuracy": 0.12924288734793662,
|
|
"num_tokens": 5029504.0,
|
|
"step": 2300
|
|
},
|
|
{
|
|
"entropy": 5.890814781188965,
|
|
"epoch": 0.1523412973794653,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00032085784033427414,
|
|
"loss": 5.9018,
|
|
"mean_token_accuracy": 0.12763333171606064,
|
|
"num_tokens": 5041073.0,
|
|
"step": 2305
|
|
},
|
|
{
|
|
"entropy": 6.015343284606933,
|
|
"epoch": 0.15267175572519084,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0003197038481121478,
|
|
"loss": 5.8492,
|
|
"mean_token_accuracy": 0.13010832741856576,
|
|
"num_tokens": 5052963.0,
|
|
"step": 2310
|
|
},
|
|
{
|
|
"entropy": 6.014020347595215,
|
|
"epoch": 0.15300221407091635,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0003185486303114436,
|
|
"loss": 5.8873,
|
|
"mean_token_accuracy": 0.12328246384859085,
|
|
"num_tokens": 5064520.0,
|
|
"step": 2315
|
|
},
|
|
{
|
|
"entropy": 6.012540864944458,
|
|
"epoch": 0.1533326724166419,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0003173922186030409,
|
|
"loss": 5.8938,
|
|
"mean_token_accuracy": 0.12742167711257935,
|
|
"num_tokens": 5076140.0,
|
|
"step": 2320
|
|
},
|
|
{
|
|
"entropy": 5.897510766983032,
|
|
"epoch": 0.1536631307623674,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000316234644690551,
|
|
"loss": 5.8764,
|
|
"mean_token_accuracy": 0.1323993869125843,
|
|
"num_tokens": 5087142.0,
|
|
"step": 2325
|
|
},
|
|
{
|
|
"entropy": 5.892305326461792,
|
|
"epoch": 0.15399358910809294,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0003150759403094473,
|
|
"loss": 5.8275,
|
|
"mean_token_accuracy": 0.13164777159690857,
|
|
"num_tokens": 5098329.0,
|
|
"step": 2330
|
|
},
|
|
{
|
|
"entropy": 5.98356556892395,
|
|
"epoch": 0.15432404745381845,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00031391613722619587,
|
|
"loss": 5.8734,
|
|
"mean_token_accuracy": 0.13292605727910994,
|
|
"num_tokens": 5109687.0,
|
|
"step": 2335
|
|
},
|
|
{
|
|
"entropy": 5.978481483459473,
|
|
"epoch": 0.15465450579954396,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.000312755267237384,
|
|
"loss": 5.9023,
|
|
"mean_token_accuracy": 0.128876506537199,
|
|
"num_tokens": 5121768.0,
|
|
"step": 2340
|
|
},
|
|
{
|
|
"entropy": 5.973013591766358,
|
|
"epoch": 0.1549849641452695,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0003115933621688488,
|
|
"loss": 5.8901,
|
|
"mean_token_accuracy": 0.12832141369581224,
|
|
"num_tokens": 5132374.0,
|
|
"step": 2345
|
|
},
|
|
{
|
|
"entropy": 5.955020380020142,
|
|
"epoch": 0.155315422490995,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00031043045387480487,
|
|
"loss": 5.8451,
|
|
"mean_token_accuracy": 0.13495676666498185,
|
|
"num_tokens": 5142565.0,
|
|
"step": 2350
|
|
},
|
|
{
|
|
"entropy": 5.96494197845459,
|
|
"epoch": 0.15564588083672054,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0003092665742369703,
|
|
"loss": 5.9332,
|
|
"mean_token_accuracy": 0.12575956508517266,
|
|
"num_tokens": 5154055.0,
|
|
"step": 2355
|
|
},
|
|
{
|
|
"entropy": 5.87860517501831,
|
|
"epoch": 0.15597633918244605,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00030810175516369343,
|
|
"loss": 5.8013,
|
|
"mean_token_accuracy": 0.13395209535956382,
|
|
"num_tokens": 5164963.0,
|
|
"step": 2360
|
|
},
|
|
{
|
|
"entropy": 5.975199365615845,
|
|
"epoch": 0.1563067975281716,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0003069360285890775,
|
|
"loss": 5.9413,
|
|
"mean_token_accuracy": 0.1292440749704838,
|
|
"num_tokens": 5174920.0,
|
|
"step": 2365
|
|
},
|
|
{
|
|
"entropy": 6.061293601989746,
|
|
"epoch": 0.1566372558738971,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00030576942647210547,
|
|
"loss": 5.9112,
|
|
"mean_token_accuracy": 0.11963123232126235,
|
|
"num_tokens": 5186104.0,
|
|
"step": 2370
|
|
},
|
|
{
|
|
"entropy": 5.9678411960601805,
|
|
"epoch": 0.1569677142196226,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.00030460198079576355,
|
|
"loss": 5.9312,
|
|
"mean_token_accuracy": 0.12077434957027436,
|
|
"num_tokens": 5198829.0,
|
|
"step": 2375
|
|
},
|
|
{
|
|
"entropy": 6.038298273086548,
|
|
"epoch": 0.15729817256534814,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0003034337235661648,
|
|
"loss": 5.9309,
|
|
"mean_token_accuracy": 0.12781475856900215,
|
|
"num_tokens": 5210431.0,
|
|
"step": 2380
|
|
},
|
|
{
|
|
"entropy": 5.869541358947754,
|
|
"epoch": 0.15762863091107365,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0003022646868116714,
|
|
"loss": 5.7086,
|
|
"mean_token_accuracy": 0.1334770664572716,
|
|
"num_tokens": 5221121.0,
|
|
"step": 2385
|
|
},
|
|
{
|
|
"entropy": 5.917714691162109,
|
|
"epoch": 0.1579590892567992,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0003010949025820163,
|
|
"loss": 5.9248,
|
|
"mean_token_accuracy": 0.12324604168534278,
|
|
"num_tokens": 5230990.0,
|
|
"step": 2390
|
|
},
|
|
{
|
|
"entropy": 5.957208156585693,
|
|
"epoch": 0.1582895476025247,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0002999244029474252,
|
|
"loss": 5.8019,
|
|
"mean_token_accuracy": 0.13554456755518912,
|
|
"num_tokens": 5242034.0,
|
|
"step": 2395
|
|
},
|
|
{
|
|
"entropy": 5.934989070892334,
|
|
"epoch": 0.15862000594825024,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.00029875321999773684,
|
|
"loss": 5.881,
|
|
"mean_token_accuracy": 0.1278662919998169,
|
|
"num_tokens": 5253494.0,
|
|
"step": 2400
|
|
},
|
|
{
|
|
"entropy": 5.949424695968628,
|
|
"epoch": 0.15895046429397575,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00029758138584152333,
|
|
"loss": 5.8742,
|
|
"mean_token_accuracy": 0.12536027953028678,
|
|
"num_tokens": 5264396.0,
|
|
"step": 2405
|
|
},
|
|
{
|
|
"entropy": 5.925760316848755,
|
|
"epoch": 0.15928092263970126,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0002964089326052102,
|
|
"loss": 5.8736,
|
|
"mean_token_accuracy": 0.1293839246034622,
|
|
"num_tokens": 5275083.0,
|
|
"step": 2410
|
|
},
|
|
{
|
|
"entropy": 5.990449142456055,
|
|
"epoch": 0.1596113809854268,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0002952358924321949,
|
|
"loss": 5.8648,
|
|
"mean_token_accuracy": 0.12962149679660798,
|
|
"num_tokens": 5285477.0,
|
|
"step": 2415
|
|
},
|
|
{
|
|
"entropy": 5.997568845748901,
|
|
"epoch": 0.1599418393311523,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00029406229748196657,
|
|
"loss": 5.8329,
|
|
"mean_token_accuracy": 0.12890177071094513,
|
|
"num_tokens": 5295389.0,
|
|
"step": 2420
|
|
},
|
|
{
|
|
"entropy": 5.866568946838379,
|
|
"epoch": 0.16027229767687784,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0002928881799292235,
|
|
"loss": 5.8157,
|
|
"mean_token_accuracy": 0.12456537410616875,
|
|
"num_tokens": 5307484.0,
|
|
"step": 2425
|
|
},
|
|
{
|
|
"entropy": 5.983704900741577,
|
|
"epoch": 0.16060275602260335,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.00029171357196299154,
|
|
"loss": 5.8461,
|
|
"mean_token_accuracy": 0.13300153613090515,
|
|
"num_tokens": 5319383.0,
|
|
"step": 2430
|
|
},
|
|
{
|
|
"entropy": 5.903039598464966,
|
|
"epoch": 0.16093321436832886,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0002905385057857414,
|
|
"loss": 5.8502,
|
|
"mean_token_accuracy": 0.12382182031869889,
|
|
"num_tokens": 5330496.0,
|
|
"step": 2435
|
|
},
|
|
{
|
|
"entropy": 5.988858985900879,
|
|
"epoch": 0.1612636727140544,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0002893630136125058,
|
|
"loss": 5.9193,
|
|
"mean_token_accuracy": 0.13424939885735512,
|
|
"num_tokens": 5341887.0,
|
|
"step": 2440
|
|
},
|
|
{
|
|
"entropy": 5.8920307636260985,
|
|
"epoch": 0.1615941310597799,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0002881871276699967,
|
|
"loss": 5.738,
|
|
"mean_token_accuracy": 0.13925896286964418,
|
|
"num_tokens": 5351538.0,
|
|
"step": 2445
|
|
},
|
|
{
|
|
"entropy": 5.914970064163208,
|
|
"epoch": 0.16192458940550544,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00028701088019572114,
|
|
"loss": 5.7943,
|
|
"mean_token_accuracy": 0.12924092561006545,
|
|
"num_tokens": 5361267.0,
|
|
"step": 2450
|
|
},
|
|
{
|
|
"entropy": 5.912482833862304,
|
|
"epoch": 0.16225504775123095,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0002858343034370977,
|
|
"loss": 5.8752,
|
|
"mean_token_accuracy": 0.1289635866880417,
|
|
"num_tokens": 5371682.0,
|
|
"step": 2455
|
|
},
|
|
{
|
|
"entropy": 5.985330057144165,
|
|
"epoch": 0.1625855060969565,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00028465742965057267,
|
|
"loss": 5.8044,
|
|
"mean_token_accuracy": 0.1314018689095974,
|
|
"num_tokens": 5382775.0,
|
|
"step": 2460
|
|
},
|
|
{
|
|
"entropy": 5.882676124572754,
|
|
"epoch": 0.162915964442682,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00028348029110073533,
|
|
"loss": 5.782,
|
|
"mean_token_accuracy": 0.13026854917407035,
|
|
"num_tokens": 5392568.0,
|
|
"step": 2465
|
|
},
|
|
{
|
|
"entropy": 5.962293863296509,
|
|
"epoch": 0.1632464227884075,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00028230292005943365,
|
|
"loss": 5.8695,
|
|
"mean_token_accuracy": 0.1239129975438118,
|
|
"num_tokens": 5403804.0,
|
|
"step": 2470
|
|
},
|
|
{
|
|
"entropy": 5.960084342956543,
|
|
"epoch": 0.16357688113413305,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00028112534880488945,
|
|
"loss": 5.8436,
|
|
"mean_token_accuracy": 0.12335392981767654,
|
|
"num_tokens": 5415545.0,
|
|
"step": 2475
|
|
},
|
|
{
|
|
"entropy": 5.905651330947876,
|
|
"epoch": 0.16390733947985855,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0002799476096208137,
|
|
"loss": 5.7466,
|
|
"mean_token_accuracy": 0.13702406510710716,
|
|
"num_tokens": 5427130.0,
|
|
"step": 2480
|
|
},
|
|
{
|
|
"entropy": 5.876770496368408,
|
|
"epoch": 0.1642377978255841,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00027876973479552087,
|
|
"loss": 5.8771,
|
|
"mean_token_accuracy": 0.12868581116199493,
|
|
"num_tokens": 5437960.0,
|
|
"step": 2485
|
|
},
|
|
{
|
|
"entropy": 5.961537265777588,
|
|
"epoch": 0.1645682561713096,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00027759175662104424,
|
|
"loss": 5.8355,
|
|
"mean_token_accuracy": 0.13011333495378494,
|
|
"num_tokens": 5449061.0,
|
|
"step": 2490
|
|
},
|
|
{
|
|
"entropy": 5.842987108230591,
|
|
"epoch": 0.16489871451703514,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0002764137073922508,
|
|
"loss": 5.6949,
|
|
"mean_token_accuracy": 0.1325258806347847,
|
|
"num_tokens": 5458866.0,
|
|
"step": 2495
|
|
},
|
|
{
|
|
"entropy": 5.897944831848145,
|
|
"epoch": 0.16522917286276065,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00027523561940595505,
|
|
"loss": 5.9088,
|
|
"mean_token_accuracy": 0.12777996808290482,
|
|
"num_tokens": 5471099.0,
|
|
"step": 2500
|
|
},
|
|
{
|
|
"entropy": 6.014475917816162,
|
|
"epoch": 0.16555963120848616,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0002740575249600342,
|
|
"loss": 5.831,
|
|
"mean_token_accuracy": 0.12404372617602348,
|
|
"num_tokens": 5481398.0,
|
|
"step": 2505
|
|
},
|
|
{
|
|
"entropy": 5.975114393234253,
|
|
"epoch": 0.1658900895542117,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00027287945635254263,
|
|
"loss": 5.8654,
|
|
"mean_token_accuracy": 0.13046190962195398,
|
|
"num_tokens": 5492367.0,
|
|
"step": 2510
|
|
},
|
|
{
|
|
"entropy": 5.951542139053345,
|
|
"epoch": 0.1662205478999372,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00027170144588082635,
|
|
"loss": 5.8262,
|
|
"mean_token_accuracy": 0.1304252676665783,
|
|
"num_tokens": 5502417.0,
|
|
"step": 2515
|
|
},
|
|
{
|
|
"entropy": 5.929127836227417,
|
|
"epoch": 0.16655100624566274,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00027052352584063763,
|
|
"loss": 5.8495,
|
|
"mean_token_accuracy": 0.12919385284185408,
|
|
"num_tokens": 5512717.0,
|
|
"step": 2520
|
|
},
|
|
{
|
|
"entropy": 5.943115282058716,
|
|
"epoch": 0.16688146459138825,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.00026934572852524907,
|
|
"loss": 5.7424,
|
|
"mean_token_accuracy": 0.13604939505457878,
|
|
"num_tokens": 5524291.0,
|
|
"step": 2525
|
|
},
|
|
{
|
|
"entropy": 5.891250038146973,
|
|
"epoch": 0.1672119229371138,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00026816808622456937,
|
|
"loss": 5.7918,
|
|
"mean_token_accuracy": 0.12903665602207184,
|
|
"num_tokens": 5535553.0,
|
|
"step": 2530
|
|
},
|
|
{
|
|
"entropy": 5.9290930271148685,
|
|
"epoch": 0.1675423812828393,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0002669906312242569,
|
|
"loss": 5.8758,
|
|
"mean_token_accuracy": 0.12555921077728271,
|
|
"num_tokens": 5547971.0,
|
|
"step": 2535
|
|
},
|
|
{
|
|
"entropy": 5.954944801330567,
|
|
"epoch": 0.1678728396285648,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00026581339580483525,
|
|
"loss": 5.7922,
|
|
"mean_token_accuracy": 0.1261722080409527,
|
|
"num_tokens": 5558518.0,
|
|
"step": 2540
|
|
},
|
|
{
|
|
"entropy": 5.827763509750366,
|
|
"epoch": 0.16820329797429034,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0002646364122408082,
|
|
"loss": 5.6695,
|
|
"mean_token_accuracy": 0.139225035905838,
|
|
"num_tokens": 5567204.0,
|
|
"step": 2545
|
|
},
|
|
{
|
|
"entropy": 5.867939090728759,
|
|
"epoch": 0.16853375632001585,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0002634597127997749,
|
|
"loss": 5.7419,
|
|
"mean_token_accuracy": 0.1334774114191532,
|
|
"num_tokens": 5577186.0,
|
|
"step": 2550
|
|
},
|
|
{
|
|
"entropy": 5.912454652786255,
|
|
"epoch": 0.1688642146657414,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0002622833297415445,
|
|
"loss": 5.7996,
|
|
"mean_token_accuracy": 0.12685954943299294,
|
|
"num_tokens": 5588457.0,
|
|
"step": 2555
|
|
},
|
|
{
|
|
"entropy": 5.844043445587158,
|
|
"epoch": 0.1691946730114669,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0002611072953172531,
|
|
"loss": 5.7617,
|
|
"mean_token_accuracy": 0.1334838829934597,
|
|
"num_tokens": 5598791.0,
|
|
"step": 2560
|
|
},
|
|
{
|
|
"entropy": 5.923829889297485,
|
|
"epoch": 0.16952513135719244,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00025993164176847845,
|
|
"loss": 5.8387,
|
|
"mean_token_accuracy": 0.1282860592007637,
|
|
"num_tokens": 5609665.0,
|
|
"step": 2565
|
|
},
|
|
{
|
|
"entropy": 5.855816650390625,
|
|
"epoch": 0.16985558970291795,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0002587564013263564,
|
|
"loss": 5.69,
|
|
"mean_token_accuracy": 0.1412699244916439,
|
|
"num_tokens": 5619734.0,
|
|
"step": 2570
|
|
},
|
|
{
|
|
"entropy": 5.9366308689117435,
|
|
"epoch": 0.17018604804864346,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0002575816062106974,
|
|
"loss": 5.8547,
|
|
"mean_token_accuracy": 0.13018670603632926,
|
|
"num_tokens": 5629725.0,
|
|
"step": 2575
|
|
},
|
|
{
|
|
"entropy": 5.9805704116821286,
|
|
"epoch": 0.170516506394369,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.00025640728862910293,
|
|
"loss": 5.8872,
|
|
"mean_token_accuracy": 0.13128093257546425,
|
|
"num_tokens": 5639475.0,
|
|
"step": 2580
|
|
},
|
|
{
|
|
"entropy": 5.950761508941651,
|
|
"epoch": 0.1708469647400945,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00025523348077608285,
|
|
"loss": 5.7133,
|
|
"mean_token_accuracy": 0.1365797609090805,
|
|
"num_tokens": 5649723.0,
|
|
"step": 2585
|
|
},
|
|
{
|
|
"entropy": 5.988879823684693,
|
|
"epoch": 0.17117742308582004,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00025406021483217225,
|
|
"loss": 5.9388,
|
|
"mean_token_accuracy": 0.1212875485420227,
|
|
"num_tokens": 5660925.0,
|
|
"step": 2590
|
|
},
|
|
{
|
|
"entropy": 5.984985208511352,
|
|
"epoch": 0.17150788143154555,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00025288752296304963,
|
|
"loss": 5.8473,
|
|
"mean_token_accuracy": 0.12533353492617608,
|
|
"num_tokens": 5671503.0,
|
|
"step": 2595
|
|
},
|
|
{
|
|
"entropy": 5.902792978286743,
|
|
"epoch": 0.1718383397772711,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.000251715437318655,
|
|
"loss": 5.8002,
|
|
"mean_token_accuracy": 0.13392459228634834,
|
|
"num_tokens": 5682776.0,
|
|
"step": 2600
|
|
},
|
|
{
|
|
"entropy": 5.950735378265381,
|
|
"epoch": 0.1721687981229966,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0002505439900323084,
|
|
"loss": 5.8327,
|
|
"mean_token_accuracy": 0.12548649236559867,
|
|
"num_tokens": 5693963.0,
|
|
"step": 2605
|
|
},
|
|
{
|
|
"entropy": 5.90710334777832,
|
|
"epoch": 0.1724992564687221,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00024937321321982894,
|
|
"loss": 5.7798,
|
|
"mean_token_accuracy": 0.12447368055582046,
|
|
"num_tokens": 5704130.0,
|
|
"step": 2610
|
|
},
|
|
{
|
|
"entropy": 5.921608257293701,
|
|
"epoch": 0.17282971481444764,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.00024820313897865433,
|
|
"loss": 5.8603,
|
|
"mean_token_accuracy": 0.12968271523714064,
|
|
"num_tokens": 5716178.0,
|
|
"step": 2615
|
|
},
|
|
{
|
|
"entropy": 5.922191047668457,
|
|
"epoch": 0.17316017316017315,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.00024703379938696105,
|
|
"loss": 5.7965,
|
|
"mean_token_accuracy": 0.13129083663225175,
|
|
"num_tokens": 5726725.0,
|
|
"step": 2620
|
|
},
|
|
{
|
|
"entropy": 5.91840181350708,
|
|
"epoch": 0.1734906315058987,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00024586522650278447,
|
|
"loss": 5.8084,
|
|
"mean_token_accuracy": 0.13205453306436538,
|
|
"num_tokens": 5738671.0,
|
|
"step": 2625
|
|
},
|
|
{
|
|
"entropy": 5.869366073608399,
|
|
"epoch": 0.1738210898516242,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.00024469745236314064,
|
|
"loss": 5.7797,
|
|
"mean_token_accuracy": 0.13480837419629096,
|
|
"num_tokens": 5749482.0,
|
|
"step": 2630
|
|
},
|
|
{
|
|
"entropy": 5.903876256942749,
|
|
"epoch": 0.17415154819734974,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00024353050898314767,
|
|
"loss": 5.7654,
|
|
"mean_token_accuracy": 0.13303880915045738,
|
|
"num_tokens": 5759437.0,
|
|
"step": 2635
|
|
},
|
|
{
|
|
"entropy": 5.942639255523682,
|
|
"epoch": 0.17448200654307525,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.00024236442835514743,
|
|
"loss": 5.8103,
|
|
"mean_token_accuracy": 0.1287062108516693,
|
|
"num_tokens": 5770774.0,
|
|
"step": 2640
|
|
},
|
|
{
|
|
"entropy": 5.976558542251587,
|
|
"epoch": 0.17481246488880076,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.00024119924244782965,
|
|
"loss": 5.8485,
|
|
"mean_token_accuracy": 0.13130325227975845,
|
|
"num_tokens": 5783850.0,
|
|
"step": 2645
|
|
},
|
|
{
|
|
"entropy": 5.845825290679931,
|
|
"epoch": 0.1751429232345263,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00024003498320535462,
|
|
"loss": 5.7937,
|
|
"mean_token_accuracy": 0.1281990922987461,
|
|
"num_tokens": 5794851.0,
|
|
"step": 2650
|
|
},
|
|
{
|
|
"entropy": 5.939936208724975,
|
|
"epoch": 0.1754733815802518,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00023887168254647727,
|
|
"loss": 5.8163,
|
|
"mean_token_accuracy": 0.1292009711265564,
|
|
"num_tokens": 5807334.0,
|
|
"step": 2655
|
|
},
|
|
{
|
|
"entropy": 6.002299976348877,
|
|
"epoch": 0.17580383992597734,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00023770937236367308,
|
|
"loss": 5.7822,
|
|
"mean_token_accuracy": 0.1305939793586731,
|
|
"num_tokens": 5818659.0,
|
|
"step": 2660
|
|
},
|
|
{
|
|
"entropy": 5.903382349014282,
|
|
"epoch": 0.17613429827170285,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00023654808452226278,
|
|
"loss": 5.7846,
|
|
"mean_token_accuracy": 0.13801127225160598,
|
|
"num_tokens": 5830039.0,
|
|
"step": 2665
|
|
},
|
|
{
|
|
"entropy": 5.858245086669922,
|
|
"epoch": 0.1764647566174284,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00023538785085953912,
|
|
"loss": 5.7266,
|
|
"mean_token_accuracy": 0.13197551816701888,
|
|
"num_tokens": 5840993.0,
|
|
"step": 2670
|
|
},
|
|
{
|
|
"entropy": 5.846403694152832,
|
|
"epoch": 0.1767952149631539,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00023422870318389404,
|
|
"loss": 5.7011,
|
|
"mean_token_accuracy": 0.13837847262620925,
|
|
"num_tokens": 5851990.0,
|
|
"step": 2675
|
|
},
|
|
{
|
|
"entropy": 5.860212516784668,
|
|
"epoch": 0.1771256733088794,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0002330706732739468,
|
|
"loss": 5.7122,
|
|
"mean_token_accuracy": 0.13180145919322966,
|
|
"num_tokens": 5862531.0,
|
|
"step": 2680
|
|
},
|
|
{
|
|
"entropy": 5.9052369594573975,
|
|
"epoch": 0.17745613165460494,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00023191379287767211,
|
|
"loss": 5.6858,
|
|
"mean_token_accuracy": 0.1392284169793129,
|
|
"num_tokens": 5873123.0,
|
|
"step": 2685
|
|
},
|
|
{
|
|
"entropy": 5.847132778167724,
|
|
"epoch": 0.17778659000033045,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0002307580937115305,
|
|
"loss": 5.7788,
|
|
"mean_token_accuracy": 0.13311546444892883,
|
|
"num_tokens": 5883673.0,
|
|
"step": 2690
|
|
},
|
|
{
|
|
"entropy": 5.864989423751831,
|
|
"epoch": 0.178117048346056,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00022960360745959846,
|
|
"loss": 5.763,
|
|
"mean_token_accuracy": 0.13155393823981285,
|
|
"num_tokens": 5894014.0,
|
|
"step": 2695
|
|
},
|
|
{
|
|
"entropy": 5.964633464813232,
|
|
"epoch": 0.1784475066917815,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.00022845036577269972,
|
|
"loss": 5.8579,
|
|
"mean_token_accuracy": 0.1255391702055931,
|
|
"num_tokens": 5906684.0,
|
|
"step": 2700
|
|
},
|
|
{
|
|
"entropy": 5.990382289886474,
|
|
"epoch": 0.178777965037507,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00022729840026753777,
|
|
"loss": 5.7619,
|
|
"mean_token_accuracy": 0.128306782245636,
|
|
"num_tokens": 5916529.0,
|
|
"step": 2705
|
|
},
|
|
{
|
|
"entropy": 5.930219936370849,
|
|
"epoch": 0.17910842338323255,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0002261477425258287,
|
|
"loss": 5.8118,
|
|
"mean_token_accuracy": 0.12666352838277817,
|
|
"num_tokens": 5927407.0,
|
|
"step": 2710
|
|
},
|
|
{
|
|
"entropy": 5.922336196899414,
|
|
"epoch": 0.17943888172895806,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0002249984240934358,
|
|
"loss": 5.7796,
|
|
"mean_token_accuracy": 0.13263439387083054,
|
|
"num_tokens": 5938117.0,
|
|
"step": 2715
|
|
},
|
|
{
|
|
"entropy": 5.934243535995483,
|
|
"epoch": 0.1797693400746836,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.00022385047647950464,
|
|
"loss": 5.7557,
|
|
"mean_token_accuracy": 0.13183477893471718,
|
|
"num_tokens": 5948921.0,
|
|
"step": 2720
|
|
},
|
|
{
|
|
"entropy": 5.888190841674804,
|
|
"epoch": 0.1800997984204091,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0002227039311555986,
|
|
"loss": 5.7077,
|
|
"mean_token_accuracy": 0.13072834238409997,
|
|
"num_tokens": 5959130.0,
|
|
"step": 2725
|
|
},
|
|
{
|
|
"entropy": 5.8759246349334715,
|
|
"epoch": 0.18043025676613464,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0002215588195548372,
|
|
"loss": 5.7533,
|
|
"mean_token_accuracy": 0.13456925004720688,
|
|
"num_tokens": 5969798.0,
|
|
"step": 2730
|
|
},
|
|
{
|
|
"entropy": 5.917500019073486,
|
|
"epoch": 0.18076071511186015,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00022041517307103337,
|
|
"loss": 5.9105,
|
|
"mean_token_accuracy": 0.1230971023440361,
|
|
"num_tokens": 5980525.0,
|
|
"step": 2735
|
|
},
|
|
{
|
|
"entropy": 5.917275476455688,
|
|
"epoch": 0.18109117345758566,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0002192730230578331,
|
|
"loss": 5.7334,
|
|
"mean_token_accuracy": 0.13198483362793922,
|
|
"num_tokens": 5991145.0,
|
|
"step": 2740
|
|
},
|
|
{
|
|
"entropy": 5.911556673049927,
|
|
"epoch": 0.1814216318033112,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0002181324008278559,
|
|
"loss": 5.7212,
|
|
"mean_token_accuracy": 0.1307394452393055,
|
|
"num_tokens": 6002077.0,
|
|
"step": 2745
|
|
},
|
|
{
|
|
"entropy": 5.916306829452514,
|
|
"epoch": 0.1817520901490367,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.00021699333765183655,
|
|
"loss": 5.849,
|
|
"mean_token_accuracy": 0.12679824531078338,
|
|
"num_tokens": 6014543.0,
|
|
"step": 2750
|
|
},
|
|
{
|
|
"entropy": 5.989484453201294,
|
|
"epoch": 0.18208254849476224,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0002158558647577673,
|
|
"loss": 5.8111,
|
|
"mean_token_accuracy": 0.1315327599644661,
|
|
"num_tokens": 6025282.0,
|
|
"step": 2755
|
|
},
|
|
{
|
|
"entropy": 5.9353189945220945,
|
|
"epoch": 0.18241300684048775,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00021472001333004215,
|
|
"loss": 5.7334,
|
|
"mean_token_accuracy": 0.12867416590452194,
|
|
"num_tokens": 6035517.0,
|
|
"step": 2760
|
|
},
|
|
{
|
|
"entropy": 5.891751956939697,
|
|
"epoch": 0.1827434651862133,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00021358581450860186,
|
|
"loss": 5.7786,
|
|
"mean_token_accuracy": 0.13786315619945527,
|
|
"num_tokens": 6045907.0,
|
|
"step": 2765
|
|
},
|
|
{
|
|
"entropy": 5.895381212234497,
|
|
"epoch": 0.1830739235319388,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0002124532993880799,
|
|
"loss": 5.737,
|
|
"mean_token_accuracy": 0.1349709689617157,
|
|
"num_tokens": 6057111.0,
|
|
"step": 2770
|
|
},
|
|
{
|
|
"entropy": 5.9264609813690186,
|
|
"epoch": 0.1834043818776643,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00021132249901695044,
|
|
"loss": 5.7479,
|
|
"mean_token_accuracy": 0.13150662034749985,
|
|
"num_tokens": 6068336.0,
|
|
"step": 2775
|
|
},
|
|
{
|
|
"entropy": 5.85119481086731,
|
|
"epoch": 0.18373484022338984,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00021019344439667705,
|
|
"loss": 5.67,
|
|
"mean_token_accuracy": 0.14122786223888398,
|
|
"num_tokens": 6077717.0,
|
|
"step": 2780
|
|
},
|
|
{
|
|
"entropy": 5.854406833648682,
|
|
"epoch": 0.18406529856911535,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00020906616648086213,
|
|
"loss": 5.7897,
|
|
"mean_token_accuracy": 0.135731852799654,
|
|
"num_tokens": 6088430.0,
|
|
"step": 2785
|
|
},
|
|
{
|
|
"entropy": 5.9320056438446045,
|
|
"epoch": 0.1843957569148409,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00020794069617439942,
|
|
"loss": 5.7681,
|
|
"mean_token_accuracy": 0.12851391807198526,
|
|
"num_tokens": 6100283.0,
|
|
"step": 2790
|
|
},
|
|
{
|
|
"entropy": 5.902456188201905,
|
|
"epoch": 0.1847262152605664,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00020681706433262593,
|
|
"loss": 5.728,
|
|
"mean_token_accuracy": 0.13515040427446365,
|
|
"num_tokens": 6110924.0,
|
|
"step": 2795
|
|
},
|
|
{
|
|
"entropy": 5.852253580093384,
|
|
"epoch": 0.18505667360629194,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00020569530176047602,
|
|
"loss": 5.6641,
|
|
"mean_token_accuracy": 0.13833696842193605,
|
|
"num_tokens": 6121080.0,
|
|
"step": 2800
|
|
},
|
|
{
|
|
"entropy": 5.927852582931519,
|
|
"epoch": 0.18538713195201745,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0002045754392116374,
|
|
"loss": 5.7782,
|
|
"mean_token_accuracy": 0.13148573264479638,
|
|
"num_tokens": 6132090.0,
|
|
"step": 2805
|
|
},
|
|
{
|
|
"entropy": 5.861389207839966,
|
|
"epoch": 0.18571759029774296,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00020345750738770757,
|
|
"loss": 5.708,
|
|
"mean_token_accuracy": 0.1311952218413353,
|
|
"num_tokens": 6142446.0,
|
|
"step": 2810
|
|
},
|
|
{
|
|
"entropy": 5.8359503746032715,
|
|
"epoch": 0.1860480486434685,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00020234153693735214,
|
|
"loss": 5.6944,
|
|
"mean_token_accuracy": 0.135716512799263,
|
|
"num_tokens": 6153570.0,
|
|
"step": 2815
|
|
},
|
|
{
|
|
"entropy": 5.888143253326416,
|
|
"epoch": 0.186378506989194,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0002012275584554647,
|
|
"loss": 5.829,
|
|
"mean_token_accuracy": 0.127596814930439,
|
|
"num_tokens": 6164424.0,
|
|
"step": 2820
|
|
},
|
|
{
|
|
"entropy": 5.9717817306518555,
|
|
"epoch": 0.18670896533491954,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00020011560248232803,
|
|
"loss": 5.77,
|
|
"mean_token_accuracy": 0.1353263109922409,
|
|
"num_tokens": 6175238.0,
|
|
"step": 2825
|
|
},
|
|
{
|
|
"entropy": 5.873361539840698,
|
|
"epoch": 0.18703942368064505,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00019900569950277692,
|
|
"loss": 5.6935,
|
|
"mean_token_accuracy": 0.13210524693131448,
|
|
"num_tokens": 6186196.0,
|
|
"step": 2830
|
|
},
|
|
{
|
|
"entropy": 5.873475360870361,
|
|
"epoch": 0.1873698820263706,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00019789787994536228,
|
|
"loss": 5.7214,
|
|
"mean_token_accuracy": 0.1349502272903919,
|
|
"num_tokens": 6196835.0,
|
|
"step": 2835
|
|
},
|
|
{
|
|
"entropy": 5.915193939208985,
|
|
"epoch": 0.1877003403720961,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00019679217418151667,
|
|
"loss": 5.7597,
|
|
"mean_token_accuracy": 0.13205045983195304,
|
|
"num_tokens": 6207917.0,
|
|
"step": 2840
|
|
},
|
|
{
|
|
"entropy": 5.822631883621216,
|
|
"epoch": 0.1880307987178216,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00019568861252472236,
|
|
"loss": 5.6925,
|
|
"mean_token_accuracy": 0.1341836556792259,
|
|
"num_tokens": 6219203.0,
|
|
"step": 2845
|
|
},
|
|
{
|
|
"entropy": 5.947698497772217,
|
|
"epoch": 0.18836125706354714,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.00019458722522967952,
|
|
"loss": 5.8754,
|
|
"mean_token_accuracy": 0.12944985404610634,
|
|
"num_tokens": 6231500.0,
|
|
"step": 2850
|
|
},
|
|
{
|
|
"entropy": 5.971322393417358,
|
|
"epoch": 0.18869171540927265,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00019348804249147723,
|
|
"loss": 5.7964,
|
|
"mean_token_accuracy": 0.1253560371696949,
|
|
"num_tokens": 6243036.0,
|
|
"step": 2855
|
|
},
|
|
{
|
|
"entropy": 5.942532634735107,
|
|
"epoch": 0.1890221737549982,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0001923910944447655,
|
|
"loss": 5.8258,
|
|
"mean_token_accuracy": 0.13415401577949523,
|
|
"num_tokens": 6255318.0,
|
|
"step": 2860
|
|
},
|
|
{
|
|
"entropy": 5.926486968994141,
|
|
"epoch": 0.1893526321007237,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00019129641116292928,
|
|
"loss": 5.7723,
|
|
"mean_token_accuracy": 0.1318974457681179,
|
|
"num_tokens": 6266448.0,
|
|
"step": 2865
|
|
},
|
|
{
|
|
"entropy": 5.918528604507446,
|
|
"epoch": 0.18968309044644924,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00019020402265726343,
|
|
"loss": 5.7209,
|
|
"mean_token_accuracy": 0.13305251002311708,
|
|
"num_tokens": 6277109.0,
|
|
"step": 2870
|
|
},
|
|
{
|
|
"entropy": 5.934632968902588,
|
|
"epoch": 0.19001354879217475,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0001891139588761509,
|
|
"loss": 5.7769,
|
|
"mean_token_accuracy": 0.13269107863307,
|
|
"num_tokens": 6287584.0,
|
|
"step": 2875
|
|
},
|
|
{
|
|
"entropy": 5.853770637512207,
|
|
"epoch": 0.19034400713790026,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00018802624970424076,
|
|
"loss": 5.7003,
|
|
"mean_token_accuracy": 0.13467251360416413,
|
|
"num_tokens": 6298343.0,
|
|
"step": 2880
|
|
},
|
|
{
|
|
"entropy": 5.844192457199097,
|
|
"epoch": 0.1906744654836258,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00018694092496162945,
|
|
"loss": 5.6989,
|
|
"mean_token_accuracy": 0.13245631009340286,
|
|
"num_tokens": 6308719.0,
|
|
"step": 2885
|
|
},
|
|
{
|
|
"entropy": 5.922165870666504,
|
|
"epoch": 0.1910049238293513,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.00018585801440304306,
|
|
"loss": 5.7227,
|
|
"mean_token_accuracy": 0.13221848830580712,
|
|
"num_tokens": 6319631.0,
|
|
"step": 2890
|
|
},
|
|
{
|
|
"entropy": 5.876812410354614,
|
|
"epoch": 0.19133538217507684,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00018477754771702165,
|
|
"loss": 5.7329,
|
|
"mean_token_accuracy": 0.13582441881299018,
|
|
"num_tokens": 6330532.0,
|
|
"step": 2895
|
|
},
|
|
{
|
|
"entropy": 5.8470336437225345,
|
|
"epoch": 0.19166584052080235,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00018369955452510506,
|
|
"loss": 5.7021,
|
|
"mean_token_accuracy": 0.13708783611655234,
|
|
"num_tokens": 6341822.0,
|
|
"step": 2900
|
|
},
|
|
{
|
|
"entropy": 5.87399730682373,
|
|
"epoch": 0.1919962988665279,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0001826240643810212,
|
|
"loss": 5.7125,
|
|
"mean_token_accuracy": 0.13449812978506087,
|
|
"num_tokens": 6350958.0,
|
|
"step": 2905
|
|
},
|
|
{
|
|
"entropy": 5.9052070617675785,
|
|
"epoch": 0.1923267572122534,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0001815511067698758,
|
|
"loss": 5.7662,
|
|
"mean_token_accuracy": 0.1324750617146492,
|
|
"num_tokens": 6362164.0,
|
|
"step": 2910
|
|
},
|
|
{
|
|
"entropy": 5.888023567199707,
|
|
"epoch": 0.1926572155579789,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0001804807111073436,
|
|
"loss": 5.7476,
|
|
"mean_token_accuracy": 0.13659745901823045,
|
|
"num_tokens": 6373103.0,
|
|
"step": 2915
|
|
},
|
|
{
|
|
"entropy": 5.875131130218506,
|
|
"epoch": 0.19298767390370444,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0001794129067388625,
|
|
"loss": 5.7134,
|
|
"mean_token_accuracy": 0.12950658276677132,
|
|
"num_tokens": 6383856.0,
|
|
"step": 2920
|
|
},
|
|
{
|
|
"entropy": 5.914546394348145,
|
|
"epoch": 0.19331813224942995,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00017834772293882868,
|
|
"loss": 5.7373,
|
|
"mean_token_accuracy": 0.13638598695397378,
|
|
"num_tokens": 6395671.0,
|
|
"step": 2925
|
|
},
|
|
{
|
|
"entropy": 5.862661552429199,
|
|
"epoch": 0.1936485905951555,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.000177285188909794,
|
|
"loss": 5.6586,
|
|
"mean_token_accuracy": 0.13922369331121445,
|
|
"num_tokens": 6405504.0,
|
|
"step": 2930
|
|
},
|
|
{
|
|
"entropy": 5.928665208816528,
|
|
"epoch": 0.193979048940881,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0001762253337816656,
|
|
"loss": 5.7793,
|
|
"mean_token_accuracy": 0.1335356689989567,
|
|
"num_tokens": 6416515.0,
|
|
"step": 2935
|
|
},
|
|
{
|
|
"entropy": 5.903650331497192,
|
|
"epoch": 0.19430950728660654,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.00017516818661090738,
|
|
"loss": 5.7391,
|
|
"mean_token_accuracy": 0.1345689333975315,
|
|
"num_tokens": 6428201.0,
|
|
"step": 2940
|
|
},
|
|
{
|
|
"entropy": 5.8590717792510985,
|
|
"epoch": 0.19463996563233205,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0001741137763797428,
|
|
"loss": 5.6536,
|
|
"mean_token_accuracy": 0.13888152316212654,
|
|
"num_tokens": 6439123.0,
|
|
"step": 2945
|
|
},
|
|
{
|
|
"entropy": 5.835010099411011,
|
|
"epoch": 0.19497042397805756,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00017306213199536115,
|
|
"loss": 5.6907,
|
|
"mean_token_accuracy": 0.1345870465040207,
|
|
"num_tokens": 6449460.0,
|
|
"step": 2950
|
|
},
|
|
{
|
|
"entropy": 5.830094289779663,
|
|
"epoch": 0.1953008823237831,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0001720132822891243,
|
|
"loss": 5.6365,
|
|
"mean_token_accuracy": 0.1362414538860321,
|
|
"num_tokens": 6459563.0,
|
|
"step": 2955
|
|
},
|
|
{
|
|
"entropy": 5.810039710998535,
|
|
"epoch": 0.1956313406695086,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0001709672560157769,
|
|
"loss": 5.6626,
|
|
"mean_token_accuracy": 0.14219122529029846,
|
|
"num_tokens": 6469380.0,
|
|
"step": 2960
|
|
},
|
|
{
|
|
"entropy": 5.84861912727356,
|
|
"epoch": 0.19596179901523414,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00016992408185265758,
|
|
"loss": 5.6972,
|
|
"mean_token_accuracy": 0.14117302522063255,
|
|
"num_tokens": 6479467.0,
|
|
"step": 2965
|
|
},
|
|
{
|
|
"entropy": 5.911595487594605,
|
|
"epoch": 0.19629225736095965,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00016888378839891298,
|
|
"loss": 5.7484,
|
|
"mean_token_accuracy": 0.1344449259340763,
|
|
"num_tokens": 6489598.0,
|
|
"step": 2970
|
|
},
|
|
{
|
|
"entropy": 5.934767484664917,
|
|
"epoch": 0.19662271570668519,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0001678464041747137,
|
|
"loss": 5.7726,
|
|
"mean_token_accuracy": 0.13162114918231965,
|
|
"num_tokens": 6500139.0,
|
|
"step": 2975
|
|
},
|
|
{
|
|
"entropy": 5.858961486816407,
|
|
"epoch": 0.1969531740524107,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00016681195762047223,
|
|
"loss": 5.589,
|
|
"mean_token_accuracy": 0.14562461003661156,
|
|
"num_tokens": 6509829.0,
|
|
"step": 2980
|
|
},
|
|
{
|
|
"entropy": 5.923531866073608,
|
|
"epoch": 0.1972836323981362,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00016578047709606337,
|
|
"loss": 5.7712,
|
|
"mean_token_accuracy": 0.13152742758393288,
|
|
"num_tokens": 6521097.0,
|
|
"step": 2985
|
|
},
|
|
{
|
|
"entropy": 5.922328662872315,
|
|
"epoch": 0.19761409074386174,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00016475199088004678,
|
|
"loss": 5.78,
|
|
"mean_token_accuracy": 0.13350266441702843,
|
|
"num_tokens": 6533681.0,
|
|
"step": 2990
|
|
},
|
|
{
|
|
"entropy": 5.933759546279907,
|
|
"epoch": 0.19794454908958725,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.00016372652716889163,
|
|
"loss": 5.8564,
|
|
"mean_token_accuracy": 0.1268802359700203,
|
|
"num_tokens": 6545554.0,
|
|
"step": 2995
|
|
},
|
|
{
|
|
"entropy": 5.893554210662842,
|
|
"epoch": 0.1982750074353128,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0001627041140762035,
|
|
"loss": 5.7338,
|
|
"mean_token_accuracy": 0.12668615952134132,
|
|
"num_tokens": 6556650.0,
|
|
"step": 3000
|
|
},
|
|
{
|
|
"entropy": 5.936082220077514,
|
|
"epoch": 0.1986054657810383,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00016168477963195382,
|
|
"loss": 5.7035,
|
|
"mean_token_accuracy": 0.13888585790991784,
|
|
"num_tokens": 6566987.0,
|
|
"step": 3005
|
|
},
|
|
{
|
|
"entropy": 5.900719833374024,
|
|
"epoch": 0.1989359241267638,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0001606685517817114,
|
|
"loss": 5.7207,
|
|
"mean_token_accuracy": 0.13485446497797965,
|
|
"num_tokens": 6579024.0,
|
|
"step": 3010
|
|
},
|
|
{
|
|
"entropy": 5.914967012405396,
|
|
"epoch": 0.19926638247248935,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.00015965545838587592,
|
|
"loss": 5.7947,
|
|
"mean_token_accuracy": 0.13368737772107125,
|
|
"num_tokens": 6590924.0,
|
|
"step": 3015
|
|
},
|
|
{
|
|
"entropy": 5.855221796035766,
|
|
"epoch": 0.19959684081821485,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.00015864552721891467,
|
|
"loss": 5.7129,
|
|
"mean_token_accuracy": 0.13739510476589203,
|
|
"num_tokens": 6601011.0,
|
|
"step": 3020
|
|
},
|
|
{
|
|
"entropy": 5.917990732192993,
|
|
"epoch": 0.1999272991639404,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00015763878596860076,
|
|
"loss": 5.7283,
|
|
"mean_token_accuracy": 0.14128526896238328,
|
|
"num_tokens": 6612123.0,
|
|
"step": 3025
|
|
},
|
|
{
|
|
"entropy": 5.950723552703858,
|
|
"epoch": 0.2002577575096659,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.00015663526223525412,
|
|
"loss": 5.8075,
|
|
"mean_token_accuracy": 0.13171337470412253,
|
|
"num_tokens": 6624074.0,
|
|
"step": 3030
|
|
},
|
|
{
|
|
"entropy": 5.938178253173828,
|
|
"epoch": 0.20058821585539144,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0001556349835309848,
|
|
"loss": 5.7648,
|
|
"mean_token_accuracy": 0.13453471586108207,
|
|
"num_tokens": 6634897.0,
|
|
"step": 3035
|
|
},
|
|
{
|
|
"entropy": 5.904913330078125,
|
|
"epoch": 0.20091867420111695,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0001546379772789389,
|
|
"loss": 5.7006,
|
|
"mean_token_accuracy": 0.13694698587059975,
|
|
"num_tokens": 6644943.0,
|
|
"step": 3040
|
|
},
|
|
{
|
|
"entropy": 5.910674333572388,
|
|
"epoch": 0.20124913254684246,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00015364427081254622,
|
|
"loss": 5.7483,
|
|
"mean_token_accuracy": 0.12902513816952704,
|
|
"num_tokens": 6655947.0,
|
|
"step": 3045
|
|
},
|
|
{
|
|
"entropy": 5.885967779159546,
|
|
"epoch": 0.201579590892568,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00015265389137477165,
|
|
"loss": 5.6903,
|
|
"mean_token_accuracy": 0.13488838002085685,
|
|
"num_tokens": 6667222.0,
|
|
"step": 3050
|
|
},
|
|
{
|
|
"entropy": 5.959286689758301,
|
|
"epoch": 0.2019100492382935,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.00015166686611736786,
|
|
"loss": 5.7997,
|
|
"mean_token_accuracy": 0.1302309028804302,
|
|
"num_tokens": 6679009.0,
|
|
"step": 3055
|
|
},
|
|
{
|
|
"entropy": 5.9368431091308596,
|
|
"epoch": 0.20224050758401904,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00015068322210013064,
|
|
"loss": 5.8561,
|
|
"mean_token_accuracy": 0.1319039210677147,
|
|
"num_tokens": 6690809.0,
|
|
"step": 3060
|
|
},
|
|
{
|
|
"entropy": 5.9024168968200685,
|
|
"epoch": 0.20257096592974455,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0001497029862901578,
|
|
"loss": 5.6164,
|
|
"mean_token_accuracy": 0.13519689440727234,
|
|
"num_tokens": 6700372.0,
|
|
"step": 3065
|
|
},
|
|
{
|
|
"entropy": 5.874724340438843,
|
|
"epoch": 0.2029014242754701,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00014872618556110905,
|
|
"loss": 5.8536,
|
|
"mean_token_accuracy": 0.13188557624816893,
|
|
"num_tokens": 6711625.0,
|
|
"step": 3070
|
|
},
|
|
{
|
|
"entropy": 5.887697744369507,
|
|
"epoch": 0.2032318826211956,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00014775284669246992,
|
|
"loss": 5.7054,
|
|
"mean_token_accuracy": 0.13882121592760086,
|
|
"num_tokens": 6723529.0,
|
|
"step": 3075
|
|
},
|
|
{
|
|
"entropy": 5.9651023864746096,
|
|
"epoch": 0.2035623409669211,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00014678299636881716,
|
|
"loss": 5.7819,
|
|
"mean_token_accuracy": 0.1331796869635582,
|
|
"num_tokens": 6735257.0,
|
|
"step": 3080
|
|
},
|
|
{
|
|
"entropy": 5.900224447250366,
|
|
"epoch": 0.20389279931264664,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0001458166611790873,
|
|
"loss": 5.7528,
|
|
"mean_token_accuracy": 0.13558293133974075,
|
|
"num_tokens": 6746659.0,
|
|
"step": 3085
|
|
},
|
|
{
|
|
"entropy": 5.917281293869019,
|
|
"epoch": 0.20422325765837215,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00014485386761584773,
|
|
"loss": 5.7349,
|
|
"mean_token_accuracy": 0.13664421439170837,
|
|
"num_tokens": 6758006.0,
|
|
"step": 3090
|
|
},
|
|
{
|
|
"entropy": 5.8846211433410645,
|
|
"epoch": 0.2045537160040977,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00014389464207457042,
|
|
"loss": 5.6826,
|
|
"mean_token_accuracy": 0.13643834367394447,
|
|
"num_tokens": 6768483.0,
|
|
"step": 3095
|
|
},
|
|
{
|
|
"entropy": 5.797060966491699,
|
|
"epoch": 0.2048841743498232,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.00014293901085290795,
|
|
"loss": 5.551,
|
|
"mean_token_accuracy": 0.14907735958695412,
|
|
"num_tokens": 6779089.0,
|
|
"step": 3100
|
|
},
|
|
{
|
|
"entropy": 5.860115957260132,
|
|
"epoch": 0.20521463269554874,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00014198700014997307,
|
|
"loss": 5.6312,
|
|
"mean_token_accuracy": 0.1365334175527096,
|
|
"num_tokens": 6788830.0,
|
|
"step": 3105
|
|
},
|
|
{
|
|
"entropy": 5.839931917190552,
|
|
"epoch": 0.20554509104127425,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.00014103863606562016,
|
|
"loss": 5.7109,
|
|
"mean_token_accuracy": 0.13470903784036636,
|
|
"num_tokens": 6800747.0,
|
|
"step": 3110
|
|
},
|
|
{
|
|
"entropy": 5.856809425354004,
|
|
"epoch": 0.20587554938699976,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00014009394459972964,
|
|
"loss": 5.6944,
|
|
"mean_token_accuracy": 0.13628971800208092,
|
|
"num_tokens": 6811129.0,
|
|
"step": 3115
|
|
},
|
|
{
|
|
"entropy": 5.9715972423553465,
|
|
"epoch": 0.2062060077327253,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00013915295165149513,
|
|
"loss": 5.7863,
|
|
"mean_token_accuracy": 0.1377706430852413,
|
|
"num_tokens": 6822800.0,
|
|
"step": 3120
|
|
},
|
|
{
|
|
"entropy": 5.920284175872803,
|
|
"epoch": 0.2065364660784508,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.00013821568301871384,
|
|
"loss": 5.7252,
|
|
"mean_token_accuracy": 0.13686419725418092,
|
|
"num_tokens": 6833766.0,
|
|
"step": 3125
|
|
},
|
|
{
|
|
"entropy": 5.892817163467408,
|
|
"epoch": 0.20686692442417634,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00013728216439707862,
|
|
"loss": 5.7076,
|
|
"mean_token_accuracy": 0.13766199499368667,
|
|
"num_tokens": 6845556.0,
|
|
"step": 3130
|
|
},
|
|
{
|
|
"entropy": 5.8084001541137695,
|
|
"epoch": 0.20719738276990185,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00013635242137947419,
|
|
"loss": 5.6203,
|
|
"mean_token_accuracy": 0.134769968688488,
|
|
"num_tokens": 6855333.0,
|
|
"step": 3135
|
|
},
|
|
{
|
|
"entropy": 5.871804332733154,
|
|
"epoch": 0.2075278411156274,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00013542647945527498,
|
|
"loss": 5.7224,
|
|
"mean_token_accuracy": 0.13278324902057648,
|
|
"num_tokens": 6866815.0,
|
|
"step": 3140
|
|
},
|
|
{
|
|
"entropy": 5.9232306480407715,
|
|
"epoch": 0.2078582994613529,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0001345043640096465,
|
|
"loss": 5.7752,
|
|
"mean_token_accuracy": 0.13382752537727355,
|
|
"num_tokens": 6877075.0,
|
|
"step": 3145
|
|
},
|
|
{
|
|
"entropy": 5.984255409240722,
|
|
"epoch": 0.2081887578070784,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.00013358610032284957,
|
|
"loss": 5.8104,
|
|
"mean_token_accuracy": 0.1365076072514057,
|
|
"num_tokens": 6888783.0,
|
|
"step": 3150
|
|
},
|
|
{
|
|
"entropy": 5.947588872909546,
|
|
"epoch": 0.20851921615280394,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000132671713569547,
|
|
"loss": 5.6524,
|
|
"mean_token_accuracy": 0.13704709261655806,
|
|
"num_tokens": 6899198.0,
|
|
"step": 3155
|
|
},
|
|
{
|
|
"entropy": 5.827290105819702,
|
|
"epoch": 0.20884967449852945,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0001317612288181136,
|
|
"loss": 5.6407,
|
|
"mean_token_accuracy": 0.13922041282057762,
|
|
"num_tokens": 6910367.0,
|
|
"step": 3160
|
|
},
|
|
{
|
|
"entropy": 5.859632444381714,
|
|
"epoch": 0.209180132844255,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00013085467102994864,
|
|
"loss": 5.6683,
|
|
"mean_token_accuracy": 0.13375854268670082,
|
|
"num_tokens": 6920810.0,
|
|
"step": 3165
|
|
},
|
|
{
|
|
"entropy": 5.848427391052246,
|
|
"epoch": 0.2095105911899805,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00012995206505879198,
|
|
"loss": 5.6479,
|
|
"mean_token_accuracy": 0.13818870037794112,
|
|
"num_tokens": 6931641.0,
|
|
"step": 3170
|
|
},
|
|
{
|
|
"entropy": 5.909488296508789,
|
|
"epoch": 0.20984104953570604,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0001290534356500421,
|
|
"loss": 5.7034,
|
|
"mean_token_accuracy": 0.13799260407686234,
|
|
"num_tokens": 6942284.0,
|
|
"step": 3175
|
|
},
|
|
{
|
|
"entropy": 5.964718198776245,
|
|
"epoch": 0.21017150788143155,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00012815880744007827,
|
|
"loss": 5.7954,
|
|
"mean_token_accuracy": 0.1347345195710659,
|
|
"num_tokens": 6954351.0,
|
|
"step": 3180
|
|
},
|
|
{
|
|
"entropy": 5.88338828086853,
|
|
"epoch": 0.21050196622715706,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00012726820495558483,
|
|
"loss": 5.654,
|
|
"mean_token_accuracy": 0.13747705817222594,
|
|
"num_tokens": 6965324.0,
|
|
"step": 3185
|
|
},
|
|
{
|
|
"entropy": 5.793405914306641,
|
|
"epoch": 0.2108324245728826,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00012638165261287868,
|
|
"loss": 5.6114,
|
|
"mean_token_accuracy": 0.13950905352830886,
|
|
"num_tokens": 6975442.0,
|
|
"step": 3190
|
|
},
|
|
{
|
|
"entropy": 5.834900712966919,
|
|
"epoch": 0.2111628829186081,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0001254991747172402,
|
|
"loss": 5.6808,
|
|
"mean_token_accuracy": 0.13490288332104683,
|
|
"num_tokens": 6987295.0,
|
|
"step": 3195
|
|
},
|
|
{
|
|
"entropy": 5.842488241195679,
|
|
"epoch": 0.21149334126433364,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00012462079546224662,
|
|
"loss": 5.6215,
|
|
"mean_token_accuracy": 0.14077782705426217,
|
|
"num_tokens": 6998052.0,
|
|
"step": 3200
|
|
},
|
|
{
|
|
"entropy": 5.862717151641846,
|
|
"epoch": 0.21182379961005915,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.00012374653892910896,
|
|
"loss": 5.6348,
|
|
"mean_token_accuracy": 0.13540926948189735,
|
|
"num_tokens": 7009795.0,
|
|
"step": 3205
|
|
},
|
|
{
|
|
"entropy": 5.866790151596069,
|
|
"epoch": 0.2121542579557847,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.00012287642908601166,
|
|
"loss": 5.6829,
|
|
"mean_token_accuracy": 0.14160369485616683,
|
|
"num_tokens": 7020200.0,
|
|
"step": 3210
|
|
},
|
|
{
|
|
"entropy": 5.86772985458374,
|
|
"epoch": 0.2124847163015102,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00012201048978745569,
|
|
"loss": 5.7354,
|
|
"mean_token_accuracy": 0.1372774288058281,
|
|
"num_tokens": 7030671.0,
|
|
"step": 3215
|
|
},
|
|
{
|
|
"entropy": 5.918194770812988,
|
|
"epoch": 0.2128151746472357,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00012114874477360427,
|
|
"loss": 5.696,
|
|
"mean_token_accuracy": 0.13978851437568665,
|
|
"num_tokens": 7041569.0,
|
|
"step": 3220
|
|
},
|
|
{
|
|
"entropy": 5.896883487701416,
|
|
"epoch": 0.21314563299296124,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00012029121766963236,
|
|
"loss": 5.6661,
|
|
"mean_token_accuracy": 0.13380060568451882,
|
|
"num_tokens": 7051671.0,
|
|
"step": 3225
|
|
},
|
|
{
|
|
"entropy": 5.877505302429199,
|
|
"epoch": 0.21347609133868675,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.00011943793198507858,
|
|
"loss": 5.634,
|
|
"mean_token_accuracy": 0.13919970840215684,
|
|
"num_tokens": 7062486.0,
|
|
"step": 3230
|
|
},
|
|
{
|
|
"entropy": 5.963419961929321,
|
|
"epoch": 0.2138065496844123,
|
|
"grad_norm": 0.7578125,
|
|
"learning_rate": 0.00011858891111320104,
|
|
"loss": 5.8385,
|
|
"mean_token_accuracy": 0.13032898157835007,
|
|
"num_tokens": 7076055.0,
|
|
"step": 3235
|
|
},
|
|
{
|
|
"entropy": 5.845752573013305,
|
|
"epoch": 0.2141370080301378,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0001177441783303359,
|
|
"loss": 5.6926,
|
|
"mean_token_accuracy": 0.13243373110890388,
|
|
"num_tokens": 7088429.0,
|
|
"step": 3240
|
|
},
|
|
{
|
|
"entropy": 5.927858018875122,
|
|
"epoch": 0.21446746637586334,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00011690375679525896,
|
|
"loss": 5.6711,
|
|
"mean_token_accuracy": 0.13816561698913574,
|
|
"num_tokens": 7099258.0,
|
|
"step": 3245
|
|
},
|
|
{
|
|
"entropy": 5.925355339050293,
|
|
"epoch": 0.21479792472158885,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.00011606766954855124,
|
|
"loss": 5.6773,
|
|
"mean_token_accuracy": 0.1331708960235119,
|
|
"num_tokens": 7111313.0,
|
|
"step": 3250
|
|
},
|
|
{
|
|
"entropy": 5.807668256759643,
|
|
"epoch": 0.21512838306731435,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.00011523593951196702,
|
|
"loss": 5.6063,
|
|
"mean_token_accuracy": 0.13701514303684234,
|
|
"num_tokens": 7122162.0,
|
|
"step": 3255
|
|
},
|
|
{
|
|
"entropy": 5.786475753784179,
|
|
"epoch": 0.2154588414130399,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00011440858948780523,
|
|
"loss": 5.5952,
|
|
"mean_token_accuracy": 0.1421409398317337,
|
|
"num_tokens": 7132566.0,
|
|
"step": 3260
|
|
},
|
|
{
|
|
"entropy": 5.8856871128082275,
|
|
"epoch": 0.2157892997587654,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00011358564215828484,
|
|
"loss": 5.7463,
|
|
"mean_token_accuracy": 0.13328613415360452,
|
|
"num_tokens": 7143353.0,
|
|
"step": 3265
|
|
},
|
|
{
|
|
"entropy": 5.914799547195434,
|
|
"epoch": 0.21611975810449094,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00011276712008492254,
|
|
"loss": 5.7519,
|
|
"mean_token_accuracy": 0.13540842682123183,
|
|
"num_tokens": 7155208.0,
|
|
"step": 3270
|
|
},
|
|
{
|
|
"entropy": 5.893627786636353,
|
|
"epoch": 0.21645021645021645,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00011195304570791451,
|
|
"loss": 5.7111,
|
|
"mean_token_accuracy": 0.13022805750370026,
|
|
"num_tokens": 7166229.0,
|
|
"step": 3275
|
|
},
|
|
{
|
|
"entropy": 5.857798004150391,
|
|
"epoch": 0.21678067479594196,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.00011114344134552094,
|
|
"loss": 5.5996,
|
|
"mean_token_accuracy": 0.13822720646858216,
|
|
"num_tokens": 7177193.0,
|
|
"step": 3280
|
|
},
|
|
{
|
|
"entropy": 5.881317090988159,
|
|
"epoch": 0.2171111331416675,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0001103383291934545,
|
|
"loss": 5.727,
|
|
"mean_token_accuracy": 0.132208863645792,
|
|
"num_tokens": 7188847.0,
|
|
"step": 3285
|
|
},
|
|
{
|
|
"entropy": 5.899473714828491,
|
|
"epoch": 0.217441591487393,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00010953773132427141,
|
|
"loss": 5.7076,
|
|
"mean_token_accuracy": 0.13607660457491874,
|
|
"num_tokens": 7198743.0,
|
|
"step": 3290
|
|
},
|
|
{
|
|
"entropy": 5.898403787612915,
|
|
"epoch": 0.21777204983311854,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00010874166968676677,
|
|
"loss": 5.6749,
|
|
"mean_token_accuracy": 0.1393097683787346,
|
|
"num_tokens": 7209399.0,
|
|
"step": 3295
|
|
},
|
|
{
|
|
"entropy": 5.883461427688599,
|
|
"epoch": 0.21810250817884405,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00010795016610537251,
|
|
"loss": 5.7021,
|
|
"mean_token_accuracy": 0.13569648191332817,
|
|
"num_tokens": 7220284.0,
|
|
"step": 3300
|
|
},
|
|
{
|
|
"entropy": 5.833291816711426,
|
|
"epoch": 0.2184329665245696,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.00010716324227955904,
|
|
"loss": 5.6177,
|
|
"mean_token_accuracy": 0.13869571536779404,
|
|
"num_tokens": 7231673.0,
|
|
"step": 3305
|
|
},
|
|
{
|
|
"entropy": 5.929307079315185,
|
|
"epoch": 0.2187634248702951,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0001063809197832406,
|
|
"loss": 5.7324,
|
|
"mean_token_accuracy": 0.1328418642282486,
|
|
"num_tokens": 7243121.0,
|
|
"step": 3310
|
|
},
|
|
{
|
|
"entropy": 5.878785228729248,
|
|
"epoch": 0.2190938832160206,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00010560322006418368,
|
|
"loss": 5.6785,
|
|
"mean_token_accuracy": 0.13327658474445342,
|
|
"num_tokens": 7253276.0,
|
|
"step": 3315
|
|
},
|
|
{
|
|
"entropy": 5.898368549346924,
|
|
"epoch": 0.21942434156174614,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00010483016444341887,
|
|
"loss": 5.6643,
|
|
"mean_token_accuracy": 0.1371166817843914,
|
|
"num_tokens": 7263476.0,
|
|
"step": 3320
|
|
},
|
|
{
|
|
"entropy": 5.899287128448487,
|
|
"epoch": 0.21975479990747165,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00010406177411465654,
|
|
"loss": 5.7044,
|
|
"mean_token_accuracy": 0.13159782141447068,
|
|
"num_tokens": 7274176.0,
|
|
"step": 3325
|
|
},
|
|
{
|
|
"entropy": 5.926574802398681,
|
|
"epoch": 0.2200852582531972,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00010329807014370562,
|
|
"loss": 5.678,
|
|
"mean_token_accuracy": 0.1405092015862465,
|
|
"num_tokens": 7284620.0,
|
|
"step": 3330
|
|
},
|
|
{
|
|
"entropy": 5.942532110214233,
|
|
"epoch": 0.2204157165989227,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00010253907346789632,
|
|
"loss": 5.8361,
|
|
"mean_token_accuracy": 0.12633465975522995,
|
|
"num_tokens": 7296356.0,
|
|
"step": 3335
|
|
},
|
|
{
|
|
"entropy": 5.883289909362793,
|
|
"epoch": 0.22074617494464824,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.00010178480489550596,
|
|
"loss": 5.6198,
|
|
"mean_token_accuracy": 0.14438143372535706,
|
|
"num_tokens": 7307244.0,
|
|
"step": 3340
|
|
},
|
|
{
|
|
"entropy": 5.881373357772827,
|
|
"epoch": 0.22107663329037375,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.00010103528510518836,
|
|
"loss": 5.6289,
|
|
"mean_token_accuracy": 0.13569636642932892,
|
|
"num_tokens": 7317539.0,
|
|
"step": 3345
|
|
},
|
|
{
|
|
"entropy": 5.854809951782227,
|
|
"epoch": 0.22140709163609926,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0001002905346454073,
|
|
"loss": 5.6122,
|
|
"mean_token_accuracy": 0.14215047433972358,
|
|
"num_tokens": 7329204.0,
|
|
"step": 3350
|
|
},
|
|
{
|
|
"entropy": 5.798730325698853,
|
|
"epoch": 0.2217375499818248,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 9.955057393387285e-05,
|
|
"loss": 5.5873,
|
|
"mean_token_accuracy": 0.14260976612567902,
|
|
"num_tokens": 7340944.0,
|
|
"step": 3355
|
|
},
|
|
{
|
|
"entropy": 5.8539642810821535,
|
|
"epoch": 0.2220680083275503,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 9.88154232569816e-05,
|
|
"loss": 5.7041,
|
|
"mean_token_accuracy": 0.132188281416893,
|
|
"num_tokens": 7352737.0,
|
|
"step": 3360
|
|
},
|
|
{
|
|
"entropy": 5.892398023605347,
|
|
"epoch": 0.22239846667327584,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 9.808510276926075e-05,
|
|
"loss": 5.6647,
|
|
"mean_token_accuracy": 0.13629622384905815,
|
|
"num_tokens": 7363903.0,
|
|
"step": 3365
|
|
},
|
|
{
|
|
"entropy": 5.862296533584595,
|
|
"epoch": 0.22272892501900135,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 9.735963249281549e-05,
|
|
"loss": 5.6399,
|
|
"mean_token_accuracy": 0.14137136489152907,
|
|
"num_tokens": 7374228.0,
|
|
"step": 3370
|
|
},
|
|
{
|
|
"entropy": 5.921883964538575,
|
|
"epoch": 0.2230593833647269,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 9.663903231677974e-05,
|
|
"loss": 5.6482,
|
|
"mean_token_accuracy": 0.13913541287183762,
|
|
"num_tokens": 7384293.0,
|
|
"step": 3375
|
|
},
|
|
{
|
|
"entropy": 5.830757188796997,
|
|
"epoch": 0.2233898417104524,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 9.592332199677145e-05,
|
|
"loss": 5.6695,
|
|
"mean_token_accuracy": 0.13818631321191788,
|
|
"num_tokens": 7396028.0,
|
|
"step": 3380
|
|
},
|
|
{
|
|
"entropy": 5.816541957855224,
|
|
"epoch": 0.2237203000561779,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 9.521252115435061e-05,
|
|
"loss": 5.7013,
|
|
"mean_token_accuracy": 0.13372969925403594,
|
|
"num_tokens": 7407571.0,
|
|
"step": 3385
|
|
},
|
|
{
|
|
"entropy": 5.905441045761108,
|
|
"epoch": 0.22405075840190344,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 9.450664927648126e-05,
|
|
"loss": 5.7024,
|
|
"mean_token_accuracy": 0.14113420993089676,
|
|
"num_tokens": 7418544.0,
|
|
"step": 3390
|
|
},
|
|
{
|
|
"entropy": 5.892168188095093,
|
|
"epoch": 0.22438121674762895,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 9.380572571499758e-05,
|
|
"loss": 5.6377,
|
|
"mean_token_accuracy": 0.13635780811309814,
|
|
"num_tokens": 7428410.0,
|
|
"step": 3395
|
|
},
|
|
{
|
|
"entropy": 5.880476474761963,
|
|
"epoch": 0.2247116750933545,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 9.310976968607307e-05,
|
|
"loss": 5.6373,
|
|
"mean_token_accuracy": 0.14264874905347824,
|
|
"num_tokens": 7438031.0,
|
|
"step": 3400
|
|
},
|
|
{
|
|
"entropy": 5.928950691223145,
|
|
"epoch": 0.22504213343908,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 9.241880026969381e-05,
|
|
"loss": 5.7202,
|
|
"mean_token_accuracy": 0.13688563033938408,
|
|
"num_tokens": 7451180.0,
|
|
"step": 3405
|
|
},
|
|
{
|
|
"entropy": 5.849502754211426,
|
|
"epoch": 0.22537259178480554,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 9.173283640913537e-05,
|
|
"loss": 5.6637,
|
|
"mean_token_accuracy": 0.13840832263231279,
|
|
"num_tokens": 7462418.0,
|
|
"step": 3410
|
|
},
|
|
{
|
|
"entropy": 5.890940761566162,
|
|
"epoch": 0.22570305013053105,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 9.10518969104436e-05,
|
|
"loss": 5.6303,
|
|
"mean_token_accuracy": 0.14072022214531898,
|
|
"num_tokens": 7472891.0,
|
|
"step": 3415
|
|
},
|
|
{
|
|
"entropy": 5.930741930007935,
|
|
"epoch": 0.22603350847625656,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 9.037600044191868e-05,
|
|
"loss": 5.7151,
|
|
"mean_token_accuracy": 0.13800646364688873,
|
|
"num_tokens": 7484335.0,
|
|
"step": 3420
|
|
},
|
|
{
|
|
"entropy": 5.903060865402222,
|
|
"epoch": 0.2263639668219821,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 8.970516553360383e-05,
|
|
"loss": 5.7796,
|
|
"mean_token_accuracy": 0.1306549273431301,
|
|
"num_tokens": 7495502.0,
|
|
"step": 3425
|
|
},
|
|
{
|
|
"entropy": 5.84915862083435,
|
|
"epoch": 0.2266944251677076,
|
|
"grad_norm": 0.7734375,
|
|
"learning_rate": 8.903941057677692e-05,
|
|
"loss": 5.701,
|
|
"mean_token_accuracy": 0.1325448028743267,
|
|
"num_tokens": 7508019.0,
|
|
"step": 3430
|
|
},
|
|
{
|
|
"entropy": 5.880918884277344,
|
|
"epoch": 0.22702488351343314,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 8.837875382344635e-05,
|
|
"loss": 5.7409,
|
|
"mean_token_accuracy": 0.1335568830370903,
|
|
"num_tokens": 7519590.0,
|
|
"step": 3435
|
|
},
|
|
{
|
|
"entropy": 5.915548801422119,
|
|
"epoch": 0.22735534185915865,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 8.772321338585076e-05,
|
|
"loss": 5.6972,
|
|
"mean_token_accuracy": 0.1360980376601219,
|
|
"num_tokens": 7531271.0,
|
|
"step": 3440
|
|
},
|
|
{
|
|
"entropy": 5.91066689491272,
|
|
"epoch": 0.2276858002048842,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 8.707280723596242e-05,
|
|
"loss": 5.6817,
|
|
"mean_token_accuracy": 0.13812316209077835,
|
|
"num_tokens": 7542171.0,
|
|
"step": 3445
|
|
},
|
|
{
|
|
"entropy": 5.8889318943023685,
|
|
"epoch": 0.2280162585506097,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 8.64275532049944e-05,
|
|
"loss": 5.7034,
|
|
"mean_token_accuracy": 0.14258769974112512,
|
|
"num_tokens": 7553451.0,
|
|
"step": 3450
|
|
},
|
|
{
|
|
"entropy": 5.829347896575928,
|
|
"epoch": 0.2283467168963352,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 8.578746898291198e-05,
|
|
"loss": 5.5533,
|
|
"mean_token_accuracy": 0.15147023946046828,
|
|
"num_tokens": 7563149.0,
|
|
"step": 3455
|
|
},
|
|
{
|
|
"entropy": 5.881611490249634,
|
|
"epoch": 0.22867717524206074,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 8.515257211794742e-05,
|
|
"loss": 5.7221,
|
|
"mean_token_accuracy": 0.1403438240289688,
|
|
"num_tokens": 7572345.0,
|
|
"step": 3460
|
|
},
|
|
{
|
|
"entropy": 5.8791145324707035,
|
|
"epoch": 0.22900763358778625,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 8.452288001611896e-05,
|
|
"loss": 5.6449,
|
|
"mean_token_accuracy": 0.13822180032730103,
|
|
"num_tokens": 7583785.0,
|
|
"step": 3465
|
|
},
|
|
{
|
|
"entropy": 5.918779611587524,
|
|
"epoch": 0.2293380919335118,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 8.389840994075379e-05,
|
|
"loss": 5.6907,
|
|
"mean_token_accuracy": 0.14257237017154695,
|
|
"num_tokens": 7594009.0,
|
|
"step": 3470
|
|
},
|
|
{
|
|
"entropy": 5.897044038772583,
|
|
"epoch": 0.2296685502792373,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 8.327917901201435e-05,
|
|
"loss": 5.7474,
|
|
"mean_token_accuracy": 0.13281714916229248,
|
|
"num_tokens": 7605070.0,
|
|
"step": 3475
|
|
},
|
|
{
|
|
"entropy": 5.851497459411621,
|
|
"epoch": 0.22999900862496284,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 8.266520420642931e-05,
|
|
"loss": 5.6383,
|
|
"mean_token_accuracy": 0.14405745416879653,
|
|
"num_tokens": 7616461.0,
|
|
"step": 3480
|
|
},
|
|
{
|
|
"entropy": 5.981378602981567,
|
|
"epoch": 0.23032946697068835,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 8.205650235642828e-05,
|
|
"loss": 5.7999,
|
|
"mean_token_accuracy": 0.1334066517651081,
|
|
"num_tokens": 7627910.0,
|
|
"step": 3485
|
|
},
|
|
{
|
|
"entropy": 5.883039855957032,
|
|
"epoch": 0.23065992531641386,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 8.145309014987978e-05,
|
|
"loss": 5.6582,
|
|
"mean_token_accuracy": 0.1352257512509823,
|
|
"num_tokens": 7638568.0,
|
|
"step": 3490
|
|
},
|
|
{
|
|
"entropy": 5.897251892089844,
|
|
"epoch": 0.2309903836621394,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 8.085498412963437e-05,
|
|
"loss": 5.6244,
|
|
"mean_token_accuracy": 0.13900393545627593,
|
|
"num_tokens": 7649952.0,
|
|
"step": 3495
|
|
},
|
|
{
|
|
"entropy": 5.9021800518035885,
|
|
"epoch": 0.2313208420078649,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 8.026220069307078e-05,
|
|
"loss": 5.6744,
|
|
"mean_token_accuracy": 0.1381089061498642,
|
|
"num_tokens": 7662199.0,
|
|
"step": 3500
|
|
},
|
|
{
|
|
"entropy": 5.944462728500366,
|
|
"epoch": 0.23165130035359044,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 7.967475609164621e-05,
|
|
"loss": 5.7839,
|
|
"mean_token_accuracy": 0.12930288463830947,
|
|
"num_tokens": 7673306.0,
|
|
"step": 3505
|
|
},
|
|
{
|
|
"entropy": 5.8761971950531,
|
|
"epoch": 0.23198175869931595,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 7.909266643045124e-05,
|
|
"loss": 5.6551,
|
|
"mean_token_accuracy": 0.1397716924548149,
|
|
"num_tokens": 7683986.0,
|
|
"step": 3510
|
|
},
|
|
{
|
|
"entropy": 5.904594135284424,
|
|
"epoch": 0.23231221704504149,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 7.851594766776802e-05,
|
|
"loss": 5.7167,
|
|
"mean_token_accuracy": 0.13597722575068474,
|
|
"num_tokens": 7694238.0,
|
|
"step": 3515
|
|
},
|
|
{
|
|
"entropy": 5.8800036907196045,
|
|
"epoch": 0.232642675390767,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 7.794461561463265e-05,
|
|
"loss": 5.7132,
|
|
"mean_token_accuracy": 0.13757646158337594,
|
|
"num_tokens": 7704653.0,
|
|
"step": 3520
|
|
},
|
|
{
|
|
"entropy": 5.834752750396729,
|
|
"epoch": 0.2329731337364925,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 7.7378685934402e-05,
|
|
"loss": 5.6666,
|
|
"mean_token_accuracy": 0.13624841645359992,
|
|
"num_tokens": 7715562.0,
|
|
"step": 3525
|
|
},
|
|
{
|
|
"entropy": 5.903016376495361,
|
|
"epoch": 0.23330359208221804,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 7.68181741423242e-05,
|
|
"loss": 5.7183,
|
|
"mean_token_accuracy": 0.13697295933961867,
|
|
"num_tokens": 7725588.0,
|
|
"step": 3530
|
|
},
|
|
{
|
|
"entropy": 5.904219675064087,
|
|
"epoch": 0.23363405042794355,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 7.626309560511313e-05,
|
|
"loss": 5.6728,
|
|
"mean_token_accuracy": 0.1383320599794388,
|
|
"num_tokens": 7736860.0,
|
|
"step": 3535
|
|
},
|
|
{
|
|
"entropy": 5.945114660263061,
|
|
"epoch": 0.2339645087736691,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 7.571346554052724e-05,
|
|
"loss": 5.7246,
|
|
"mean_token_accuracy": 0.13508757203817368,
|
|
"num_tokens": 7748160.0,
|
|
"step": 3540
|
|
},
|
|
{
|
|
"entropy": 5.885511779785157,
|
|
"epoch": 0.2342949671193946,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 7.516929901695249e-05,
|
|
"loss": 5.6492,
|
|
"mean_token_accuracy": 0.13907805681228638,
|
|
"num_tokens": 7759071.0,
|
|
"step": 3545
|
|
},
|
|
{
|
|
"entropy": 5.918601846694946,
|
|
"epoch": 0.23462542546512014,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 7.463061095298893e-05,
|
|
"loss": 5.6464,
|
|
"mean_token_accuracy": 0.14159049242734909,
|
|
"num_tokens": 7769745.0,
|
|
"step": 3550
|
|
},
|
|
{
|
|
"entropy": 5.868560361862182,
|
|
"epoch": 0.23495588381084564,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 7.409741611704198e-05,
|
|
"loss": 5.602,
|
|
"mean_token_accuracy": 0.13948422893881798,
|
|
"num_tokens": 7781045.0,
|
|
"step": 3555
|
|
},
|
|
{
|
|
"entropy": 5.889551258087158,
|
|
"epoch": 0.23528634215657115,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 7.35697291269174e-05,
|
|
"loss": 5.6929,
|
|
"mean_token_accuracy": 0.1362750731408596,
|
|
"num_tokens": 7791919.0,
|
|
"step": 3560
|
|
},
|
|
{
|
|
"entropy": 5.910737133026123,
|
|
"epoch": 0.2356168005022967,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 7.304756444942056e-05,
|
|
"loss": 5.6918,
|
|
"mean_token_accuracy": 0.13770592585206032,
|
|
"num_tokens": 7803098.0,
|
|
"step": 3565
|
|
},
|
|
{
|
|
"entropy": 5.898753929138183,
|
|
"epoch": 0.2359472588480222,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 7.253093639995994e-05,
|
|
"loss": 5.6669,
|
|
"mean_token_accuracy": 0.1381296142935753,
|
|
"num_tokens": 7813985.0,
|
|
"step": 3570
|
|
},
|
|
{
|
|
"entropy": 5.87054181098938,
|
|
"epoch": 0.23627771719374774,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 7.20198591421544e-05,
|
|
"loss": 5.6485,
|
|
"mean_token_accuracy": 0.13859054148197175,
|
|
"num_tokens": 7824215.0,
|
|
"step": 3575
|
|
},
|
|
{
|
|
"entropy": 5.898317337036133,
|
|
"epoch": 0.23660817553947325,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 7.151434668744517e-05,
|
|
"loss": 5.6535,
|
|
"mean_token_accuracy": 0.13811268135905266,
|
|
"num_tokens": 7834603.0,
|
|
"step": 3580
|
|
},
|
|
{
|
|
"entropy": 5.907620429992676,
|
|
"epoch": 0.23693863388519876,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 7.101441289471153e-05,
|
|
"loss": 5.6511,
|
|
"mean_token_accuracy": 0.1421773724257946,
|
|
"num_tokens": 7845599.0,
|
|
"step": 3585
|
|
},
|
|
{
|
|
"entropy": 5.936473560333252,
|
|
"epoch": 0.2372690922309243,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 7.052007146989098e-05,
|
|
"loss": 5.6623,
|
|
"mean_token_accuracy": 0.14186413884162902,
|
|
"num_tokens": 7857264.0,
|
|
"step": 3590
|
|
},
|
|
{
|
|
"entropy": 5.873426342010498,
|
|
"epoch": 0.2375995505766498,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 7.003133596560341e-05,
|
|
"loss": 5.566,
|
|
"mean_token_accuracy": 0.14154938757419586,
|
|
"num_tokens": 7867585.0,
|
|
"step": 3595
|
|
},
|
|
{
|
|
"entropy": 5.87112717628479,
|
|
"epoch": 0.23793000892237534,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 6.954821978077952e-05,
|
|
"loss": 5.6267,
|
|
"mean_token_accuracy": 0.14067178592085838,
|
|
"num_tokens": 7878939.0,
|
|
"step": 3600
|
|
},
|
|
{
|
|
"entropy": 5.96750020980835,
|
|
"epoch": 0.23826046726810085,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 6.907073616029356e-05,
|
|
"loss": 5.7916,
|
|
"mean_token_accuracy": 0.13341709822416306,
|
|
"num_tokens": 7891125.0,
|
|
"step": 3605
|
|
},
|
|
{
|
|
"entropy": 5.900440120697022,
|
|
"epoch": 0.2385909256138264,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 6.85988981946002e-05,
|
|
"loss": 5.6879,
|
|
"mean_token_accuracy": 0.134479159116745,
|
|
"num_tokens": 7902396.0,
|
|
"step": 3610
|
|
},
|
|
{
|
|
"entropy": 5.890104055404663,
|
|
"epoch": 0.2389213839595519,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 6.813271881937564e-05,
|
|
"loss": 5.7191,
|
|
"mean_token_accuracy": 0.13083444610238076,
|
|
"num_tokens": 7913461.0,
|
|
"step": 3615
|
|
},
|
|
{
|
|
"entropy": 5.998109674453735,
|
|
"epoch": 0.2392518423052774,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 6.767221081516286e-05,
|
|
"loss": 5.7883,
|
|
"mean_token_accuracy": 0.13527448996901512,
|
|
"num_tokens": 7924673.0,
|
|
"step": 3620
|
|
},
|
|
{
|
|
"entropy": 5.8834105968475345,
|
|
"epoch": 0.23958230065100294,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 6.72173868070215e-05,
|
|
"loss": 5.5953,
|
|
"mean_token_accuracy": 0.13941466957330703,
|
|
"num_tokens": 7936310.0,
|
|
"step": 3625
|
|
},
|
|
{
|
|
"entropy": 5.847474002838135,
|
|
"epoch": 0.23991275899672845,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 6.676825926418149e-05,
|
|
"loss": 5.6787,
|
|
"mean_token_accuracy": 0.1388331763446331,
|
|
"num_tokens": 7947586.0,
|
|
"step": 3630
|
|
},
|
|
{
|
|
"entropy": 5.878710126876831,
|
|
"epoch": 0.240243217342454,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 6.632484049970122e-05,
|
|
"loss": 5.6437,
|
|
"mean_token_accuracy": 0.14084229245781898,
|
|
"num_tokens": 7957750.0,
|
|
"step": 3635
|
|
},
|
|
{
|
|
"entropy": 5.831011533737183,
|
|
"epoch": 0.2405736756881795,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 6.588714267013019e-05,
|
|
"loss": 5.5954,
|
|
"mean_token_accuracy": 0.14481737539172174,
|
|
"num_tokens": 7967158.0,
|
|
"step": 3640
|
|
},
|
|
{
|
|
"entropy": 5.93735523223877,
|
|
"epoch": 0.24090413403390504,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 6.545517777517544e-05,
|
|
"loss": 5.7731,
|
|
"mean_token_accuracy": 0.13431408256292343,
|
|
"num_tokens": 7979653.0,
|
|
"step": 3645
|
|
},
|
|
{
|
|
"entropy": 5.910138368606567,
|
|
"epoch": 0.24123459237963055,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 6.502895765737281e-05,
|
|
"loss": 5.698,
|
|
"mean_token_accuracy": 0.13666667565703391,
|
|
"num_tokens": 7990270.0,
|
|
"step": 3650
|
|
},
|
|
{
|
|
"entropy": 5.9155762672424315,
|
|
"epoch": 0.24156505072535606,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 6.460849400176212e-05,
|
|
"loss": 5.71,
|
|
"mean_token_accuracy": 0.13943733274936676,
|
|
"num_tokens": 8001449.0,
|
|
"step": 3655
|
|
},
|
|
{
|
|
"entropy": 5.907400751113892,
|
|
"epoch": 0.2418955090710816,
|
|
"grad_norm": 0.77734375,
|
|
"learning_rate": 6.419379833556694e-05,
|
|
"loss": 5.7057,
|
|
"mean_token_accuracy": 0.13635673001408577,
|
|
"num_tokens": 8014034.0,
|
|
"step": 3660
|
|
},
|
|
{
|
|
"entropy": 5.860155439376831,
|
|
"epoch": 0.2422259674168071,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 6.378488202787835e-05,
|
|
"loss": 5.6489,
|
|
"mean_token_accuracy": 0.14182029217481612,
|
|
"num_tokens": 8025252.0,
|
|
"step": 3665
|
|
},
|
|
{
|
|
"entropy": 5.937619543075561,
|
|
"epoch": 0.24255642576253264,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 6.33817562893435e-05,
|
|
"loss": 5.7214,
|
|
"mean_token_accuracy": 0.13614063784480096,
|
|
"num_tokens": 8036686.0,
|
|
"step": 3670
|
|
},
|
|
{
|
|
"entropy": 5.880292367935181,
|
|
"epoch": 0.24288688410825815,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 6.29844321718582e-05,
|
|
"loss": 5.67,
|
|
"mean_token_accuracy": 0.135041756182909,
|
|
"num_tokens": 8048119.0,
|
|
"step": 3675
|
|
},
|
|
{
|
|
"entropy": 5.900365972518921,
|
|
"epoch": 0.2432173424539837,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 6.259292056826383e-05,
|
|
"loss": 5.6476,
|
|
"mean_token_accuracy": 0.14176308661699294,
|
|
"num_tokens": 8058731.0,
|
|
"step": 3680
|
|
},
|
|
{
|
|
"entropy": 5.928038835525513,
|
|
"epoch": 0.2435478007997092,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 6.220723221204873e-05,
|
|
"loss": 5.7549,
|
|
"mean_token_accuracy": 0.13365652933716773,
|
|
"num_tokens": 8069982.0,
|
|
"step": 3685
|
|
},
|
|
{
|
|
"entropy": 5.869929599761963,
|
|
"epoch": 0.2438782591454347,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 6.182737767705406e-05,
|
|
"loss": 5.685,
|
|
"mean_token_accuracy": 0.13663748055696487,
|
|
"num_tokens": 8081048.0,
|
|
"step": 3690
|
|
},
|
|
{
|
|
"entropy": 5.95166425704956,
|
|
"epoch": 0.24420871749116024,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 6.145336737718375e-05,
|
|
"loss": 5.7682,
|
|
"mean_token_accuracy": 0.13238061219453812,
|
|
"num_tokens": 8092282.0,
|
|
"step": 3695
|
|
},
|
|
{
|
|
"entropy": 5.91133484840393,
|
|
"epoch": 0.24453917583688575,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 6.10852115661191e-05,
|
|
"loss": 5.6892,
|
|
"mean_token_accuracy": 0.14257566034793853,
|
|
"num_tokens": 8104213.0,
|
|
"step": 3700
|
|
},
|
|
{
|
|
"entropy": 5.931214475631714,
|
|
"epoch": 0.2448696341826113,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 6.072292033703766e-05,
|
|
"loss": 5.657,
|
|
"mean_token_accuracy": 0.1396171972155571,
|
|
"num_tokens": 8115495.0,
|
|
"step": 3705
|
|
},
|
|
{
|
|
"entropy": 5.878456735610962,
|
|
"epoch": 0.2452000925283368,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 6.036650362233648e-05,
|
|
"loss": 5.6111,
|
|
"mean_token_accuracy": 0.14638498574495315,
|
|
"num_tokens": 8124812.0,
|
|
"step": 3710
|
|
},
|
|
{
|
|
"entropy": 5.844263410568237,
|
|
"epoch": 0.24553055087406234,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 6.0015971193359824e-05,
|
|
"loss": 5.6021,
|
|
"mean_token_accuracy": 0.14121845364570618,
|
|
"num_tokens": 8135122.0,
|
|
"step": 3715
|
|
},
|
|
{
|
|
"entropy": 5.844045972824096,
|
|
"epoch": 0.24586100921978785,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 5.9671332660131306e-05,
|
|
"loss": 5.6248,
|
|
"mean_token_accuracy": 0.14790114536881446,
|
|
"num_tokens": 8145111.0,
|
|
"step": 3720
|
|
},
|
|
{
|
|
"entropy": 5.875703620910644,
|
|
"epoch": 0.24619146756551336,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 5.933259747109042e-05,
|
|
"loss": 5.7036,
|
|
"mean_token_accuracy": 0.13291041776537896,
|
|
"num_tokens": 8156221.0,
|
|
"step": 3725
|
|
},
|
|
{
|
|
"entropy": 5.937348461151123,
|
|
"epoch": 0.2465219259112389,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 5.899977491283351e-05,
|
|
"loss": 5.7197,
|
|
"mean_token_accuracy": 0.1332882598042488,
|
|
"num_tokens": 8167311.0,
|
|
"step": 3730
|
|
},
|
|
{
|
|
"entropy": 5.904255533218384,
|
|
"epoch": 0.2468523842569644,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 5.867287410985908e-05,
|
|
"loss": 5.6395,
|
|
"mean_token_accuracy": 0.1315557360649109,
|
|
"num_tokens": 8177795.0,
|
|
"step": 3735
|
|
},
|
|
{
|
|
"entropy": 5.886803483963012,
|
|
"epoch": 0.24718284260268994,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 5.835190402431779e-05,
|
|
"loss": 5.6287,
|
|
"mean_token_accuracy": 0.13824278563261033,
|
|
"num_tokens": 8188694.0,
|
|
"step": 3740
|
|
},
|
|
{
|
|
"entropy": 5.940566635131836,
|
|
"epoch": 0.24751330094841545,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 5.803687345576673e-05,
|
|
"loss": 5.737,
|
|
"mean_token_accuracy": 0.13532990142703055,
|
|
"num_tokens": 8200445.0,
|
|
"step": 3745
|
|
},
|
|
{
|
|
"entropy": 5.855631351470947,
|
|
"epoch": 0.247843759294141,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 5.7727791040927977e-05,
|
|
"loss": 5.5617,
|
|
"mean_token_accuracy": 0.14734672755002975,
|
|
"num_tokens": 8211140.0,
|
|
"step": 3750
|
|
},
|
|
{
|
|
"entropy": 5.937415504455567,
|
|
"epoch": 0.2481742176398665,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 5.742466525345213e-05,
|
|
"loss": 5.7436,
|
|
"mean_token_accuracy": 0.13322122693061828,
|
|
"num_tokens": 8222300.0,
|
|
"step": 3755
|
|
},
|
|
{
|
|
"entropy": 5.861875820159912,
|
|
"epoch": 0.248504675985592,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 5.7127504403685775e-05,
|
|
"loss": 5.6298,
|
|
"mean_token_accuracy": 0.13292261436581612,
|
|
"num_tokens": 8232157.0,
|
|
"step": 3760
|
|
},
|
|
{
|
|
"entropy": 5.879819345474243,
|
|
"epoch": 0.24883513433131754,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 5.6836316638443664e-05,
|
|
"loss": 5.6851,
|
|
"mean_token_accuracy": 0.13655460849404336,
|
|
"num_tokens": 8243670.0,
|
|
"step": 3765
|
|
},
|
|
{
|
|
"entropy": 5.871481418609619,
|
|
"epoch": 0.24916559267704305,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 5.655110994078553e-05,
|
|
"loss": 5.5952,
|
|
"mean_token_accuracy": 0.14377059042453766,
|
|
"num_tokens": 8253818.0,
|
|
"step": 3770
|
|
},
|
|
{
|
|
"entropy": 5.872085809707642,
|
|
"epoch": 0.2494960510227686,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 5.6271892129797056e-05,
|
|
"loss": 5.6525,
|
|
"mean_token_accuracy": 0.13854095041751863,
|
|
"num_tokens": 8264139.0,
|
|
"step": 3775
|
|
},
|
|
{
|
|
"entropy": 5.904009675979614,
|
|
"epoch": 0.2498265093684941,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 5.599867086037556e-05,
|
|
"loss": 5.6916,
|
|
"mean_token_accuracy": 0.13885634392499924,
|
|
"num_tokens": 8275589.0,
|
|
"step": 3780
|
|
},
|
|
{
|
|
"entropy": 5.905103778839111,
|
|
"epoch": 0.25015696771421964,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 5.573145362302012e-05,
|
|
"loss": 5.6419,
|
|
"mean_token_accuracy": 0.13871270418167114,
|
|
"num_tokens": 8287208.0,
|
|
"step": 3785
|
|
},
|
|
{
|
|
"entropy": 5.834312105178833,
|
|
"epoch": 0.2504874260599451,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 5.5470247743626404e-05,
|
|
"loss": 5.6092,
|
|
"mean_token_accuracy": 0.13695236667990685,
|
|
"num_tokens": 8299157.0,
|
|
"step": 3790
|
|
},
|
|
{
|
|
"entropy": 5.917389822006226,
|
|
"epoch": 0.25081788440567065,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 5.5215060383285414e-05,
|
|
"loss": 5.6609,
|
|
"mean_token_accuracy": 0.14447827115654946,
|
|
"num_tokens": 8309159.0,
|
|
"step": 3795
|
|
},
|
|
{
|
|
"entropy": 5.851535844802856,
|
|
"epoch": 0.2511483427513962,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 5.496589853808759e-05,
|
|
"loss": 5.6689,
|
|
"mean_token_accuracy": 0.13691438660025596,
|
|
"num_tokens": 8320081.0,
|
|
"step": 3800
|
|
},
|
|
{
|
|
"entropy": 5.819961214065552,
|
|
"epoch": 0.25147880109712173,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 5.47227690389308e-05,
|
|
"loss": 5.6084,
|
|
"mean_token_accuracy": 0.14831512421369553,
|
|
"num_tokens": 8330552.0,
|
|
"step": 3805
|
|
},
|
|
{
|
|
"entropy": 5.868292808532715,
|
|
"epoch": 0.2518092594428472,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 5.448567855133306e-05,
|
|
"loss": 5.6169,
|
|
"mean_token_accuracy": 0.1440398260951042,
|
|
"num_tokens": 8342197.0,
|
|
"step": 3810
|
|
},
|
|
{
|
|
"entropy": 5.924297857284546,
|
|
"epoch": 0.25213971778857275,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 5.425463357524986e-05,
|
|
"loss": 5.7513,
|
|
"mean_token_accuracy": 0.13409114852547646,
|
|
"num_tokens": 8353838.0,
|
|
"step": 3815
|
|
},
|
|
{
|
|
"entropy": 5.885556364059449,
|
|
"epoch": 0.2524701761342983,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 5.402964044489591e-05,
|
|
"loss": 5.6563,
|
|
"mean_token_accuracy": 0.13761540576815606,
|
|
"num_tokens": 8364440.0,
|
|
"step": 3820
|
|
},
|
|
{
|
|
"entropy": 5.903522157669068,
|
|
"epoch": 0.25280063448002377,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 5.381070532857153e-05,
|
|
"loss": 5.6824,
|
|
"mean_token_accuracy": 0.1436450257897377,
|
|
"num_tokens": 8374268.0,
|
|
"step": 3825
|
|
},
|
|
{
|
|
"entropy": 5.854737567901611,
|
|
"epoch": 0.2531310928257493,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 5.359783422849357e-05,
|
|
"loss": 5.6727,
|
|
"mean_token_accuracy": 0.13474718183279039,
|
|
"num_tokens": 8386400.0,
|
|
"step": 3830
|
|
},
|
|
{
|
|
"entropy": 5.900430583953858,
|
|
"epoch": 0.25346155117147484,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 5.3391032980630736e-05,
|
|
"loss": 5.7219,
|
|
"mean_token_accuracy": 0.13347632810473442,
|
|
"num_tokens": 8397621.0,
|
|
"step": 3835
|
|
},
|
|
{
|
|
"entropy": 5.904160785675049,
|
|
"epoch": 0.2537920095172004,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 5.31903072545437e-05,
|
|
"loss": 5.6537,
|
|
"mean_token_accuracy": 0.13893108069896698,
|
|
"num_tokens": 8407889.0,
|
|
"step": 3840
|
|
},
|
|
{
|
|
"entropy": 5.893474674224853,
|
|
"epoch": 0.25412246786292586,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 5.29956625532297e-05,
|
|
"loss": 5.6645,
|
|
"mean_token_accuracy": 0.13427941352128983,
|
|
"num_tokens": 8419220.0,
|
|
"step": 3845
|
|
},
|
|
{
|
|
"entropy": 5.854588365554809,
|
|
"epoch": 0.2544529262086514,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 5.280710421297146e-05,
|
|
"loss": 5.5302,
|
|
"mean_token_accuracy": 0.1467102810740471,
|
|
"num_tokens": 8430111.0,
|
|
"step": 3850
|
|
},
|
|
{
|
|
"entropy": 5.860107326507569,
|
|
"epoch": 0.25478338455437693,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 5.2624637403191165e-05,
|
|
"loss": 5.5739,
|
|
"mean_token_accuracy": 0.1393480308353901,
|
|
"num_tokens": 8440518.0,
|
|
"step": 3855
|
|
},
|
|
{
|
|
"entropy": 5.878525924682617,
|
|
"epoch": 0.2551138429001024,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 5.2448267126308605e-05,
|
|
"loss": 5.6657,
|
|
"mean_token_accuracy": 0.14847966730594636,
|
|
"num_tokens": 8450722.0,
|
|
"step": 3860
|
|
},
|
|
{
|
|
"entropy": 5.92284460067749,
|
|
"epoch": 0.25544430124582795,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 5.2277998217603954e-05,
|
|
"loss": 5.7396,
|
|
"mean_token_accuracy": 0.13405784517526625,
|
|
"num_tokens": 8461913.0,
|
|
"step": 3865
|
|
},
|
|
{
|
|
"entropy": 5.860252714157104,
|
|
"epoch": 0.2557747595915535,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 5.211383534508541e-05,
|
|
"loss": 5.7041,
|
|
"mean_token_accuracy": 0.1366371512413025,
|
|
"num_tokens": 8473322.0,
|
|
"step": 3870
|
|
},
|
|
{
|
|
"entropy": 5.8827465057373045,
|
|
"epoch": 0.25610521793727903,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 5.1955783009361044e-05,
|
|
"loss": 5.6672,
|
|
"mean_token_accuracy": 0.1417103372514248,
|
|
"num_tokens": 8483738.0,
|
|
"step": 3875
|
|
},
|
|
{
|
|
"entropy": 5.861397361755371,
|
|
"epoch": 0.2564356762830045,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 5.180384554351543e-05,
|
|
"loss": 5.5956,
|
|
"mean_token_accuracy": 0.14689040333032607,
|
|
"num_tokens": 8494579.0,
|
|
"step": 3880
|
|
},
|
|
{
|
|
"entropy": 5.86222357749939,
|
|
"epoch": 0.25676613462873005,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 5.1658027112990976e-05,
|
|
"loss": 5.6686,
|
|
"mean_token_accuracy": 0.14400768354535104,
|
|
"num_tokens": 8505489.0,
|
|
"step": 3885
|
|
},
|
|
{
|
|
"entropy": 5.922516202926635,
|
|
"epoch": 0.2570965929744556,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 5.151833171547365e-05,
|
|
"loss": 5.6861,
|
|
"mean_token_accuracy": 0.13254987671971322,
|
|
"num_tokens": 8516439.0,
|
|
"step": 3890
|
|
},
|
|
{
|
|
"entropy": 5.881091451644897,
|
|
"epoch": 0.25742705132018107,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 5.1384763180783274e-05,
|
|
"loss": 5.5606,
|
|
"mean_token_accuracy": 0.15305296778678895,
|
|
"num_tokens": 8526806.0,
|
|
"step": 3895
|
|
},
|
|
{
|
|
"entropy": 5.845441627502441,
|
|
"epoch": 0.2577575096659066,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 5.125732517076876e-05,
|
|
"loss": 5.5777,
|
|
"mean_token_accuracy": 0.14758340120315552,
|
|
"num_tokens": 8536179.0,
|
|
"step": 3900
|
|
},
|
|
{
|
|
"entropy": 5.903719806671143,
|
|
"epoch": 0.25808796801163214,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 5.113602117920747e-05,
|
|
"loss": 5.6485,
|
|
"mean_token_accuracy": 0.1381620056927204,
|
|
"num_tokens": 8546414.0,
|
|
"step": 3905
|
|
},
|
|
{
|
|
"entropy": 5.8703046321868895,
|
|
"epoch": 0.2584184263573577,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 5.102085453170966e-05,
|
|
"loss": 5.6868,
|
|
"mean_token_accuracy": 0.13792558386921883,
|
|
"num_tokens": 8557823.0,
|
|
"step": 3910
|
|
},
|
|
{
|
|
"entropy": 5.923294973373413,
|
|
"epoch": 0.25874888470308316,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 5.091182838562709e-05,
|
|
"loss": 5.7142,
|
|
"mean_token_accuracy": 0.139863783121109,
|
|
"num_tokens": 8568711.0,
|
|
"step": 3915
|
|
},
|
|
{
|
|
"entropy": 5.926609992980957,
|
|
"epoch": 0.2590793430488087,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 5.0808945729966716e-05,
|
|
"loss": 5.7719,
|
|
"mean_token_accuracy": 0.13211013078689576,
|
|
"num_tokens": 8580149.0,
|
|
"step": 3920
|
|
},
|
|
{
|
|
"entropy": 5.845376014709473,
|
|
"epoch": 0.25940980139453423,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 5.071220938530844e-05,
|
|
"loss": 5.6442,
|
|
"mean_token_accuracy": 0.13983132019639016,
|
|
"num_tokens": 8590960.0,
|
|
"step": 3925
|
|
},
|
|
{
|
|
"entropy": 5.8832306385040285,
|
|
"epoch": 0.2597402597402597,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 5.0621622003728026e-05,
|
|
"loss": 5.6599,
|
|
"mean_token_accuracy": 0.14308942034840583,
|
|
"num_tokens": 8602046.0,
|
|
"step": 3930
|
|
},
|
|
{
|
|
"entropy": 5.918454694747925,
|
|
"epoch": 0.26007071808598525,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 5.053718606872433e-05,
|
|
"loss": 5.6275,
|
|
"mean_token_accuracy": 0.13847853764891624,
|
|
"num_tokens": 8612338.0,
|
|
"step": 3935
|
|
},
|
|
{
|
|
"entropy": 5.922020101547242,
|
|
"epoch": 0.2604011764317108,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 5.0458903895151134e-05,
|
|
"loss": 5.7431,
|
|
"mean_token_accuracy": 0.1376209080219269,
|
|
"num_tokens": 8624657.0,
|
|
"step": 3940
|
|
},
|
|
{
|
|
"entropy": 5.870155143737793,
|
|
"epoch": 0.2607316347774363,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 5.038677762915381e-05,
|
|
"loss": 5.592,
|
|
"mean_token_accuracy": 0.1357843890786171,
|
|
"num_tokens": 8635233.0,
|
|
"step": 3945
|
|
},
|
|
{
|
|
"entropy": 5.854328536987305,
|
|
"epoch": 0.2610620931231618,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 5.032080924811033e-05,
|
|
"loss": 5.6396,
|
|
"mean_token_accuracy": 0.13857543990015983,
|
|
"num_tokens": 8647296.0,
|
|
"step": 3950
|
|
},
|
|
{
|
|
"entropy": 5.893777704238891,
|
|
"epoch": 0.26139255146888735,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 5.026100056057718e-05,
|
|
"loss": 5.6646,
|
|
"mean_token_accuracy": 0.1354524441063404,
|
|
"num_tokens": 8658910.0,
|
|
"step": 3955
|
|
},
|
|
{
|
|
"entropy": 5.865193510055542,
|
|
"epoch": 0.2617230098146129,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 5.0207353206239764e-05,
|
|
"loss": 5.6738,
|
|
"mean_token_accuracy": 0.1390821561217308,
|
|
"num_tokens": 8670387.0,
|
|
"step": 3960
|
|
},
|
|
{
|
|
"entropy": 5.855801057815552,
|
|
"epoch": 0.26205346816033837,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 5.0159868655867436e-05,
|
|
"loss": 5.5922,
|
|
"mean_token_accuracy": 0.13821387887001038,
|
|
"num_tokens": 8680545.0,
|
|
"step": 3965
|
|
},
|
|
{
|
|
"entropy": 5.898570585250854,
|
|
"epoch": 0.2623839265060639,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 5.011854821127305e-05,
|
|
"loss": 5.6866,
|
|
"mean_token_accuracy": 0.13515527695417404,
|
|
"num_tokens": 8691804.0,
|
|
"step": 3970
|
|
},
|
|
{
|
|
"entropy": 5.834101581573487,
|
|
"epoch": 0.26271438485178944,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 5.008339300527755e-05,
|
|
"loss": 5.5391,
|
|
"mean_token_accuracy": 0.14825590401887895,
|
|
"num_tokens": 8702841.0,
|
|
"step": 3975
|
|
},
|
|
{
|
|
"entropy": 5.938614749908448,
|
|
"epoch": 0.263044843197515,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 5.005440400167859e-05,
|
|
"loss": 5.7474,
|
|
"mean_token_accuracy": 0.13597587645053863,
|
|
"num_tokens": 8713573.0,
|
|
"step": 3980
|
|
},
|
|
{
|
|
"entropy": 5.835966300964356,
|
|
"epoch": 0.26337530154324046,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 5.003158199522442e-05,
|
|
"loss": 5.5809,
|
|
"mean_token_accuracy": 0.1514606758952141,
|
|
"num_tokens": 8723156.0,
|
|
"step": 3985
|
|
},
|
|
{
|
|
"entropy": 5.8698670864105225,
|
|
"epoch": 0.263705759888966,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 5.0014927611591806e-05,
|
|
"loss": 5.6166,
|
|
"mean_token_accuracy": 0.13953590840101243,
|
|
"num_tokens": 8733206.0,
|
|
"step": 3990
|
|
},
|
|
{
|
|
"entropy": 5.859228706359863,
|
|
"epoch": 0.26403621823469153,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 5.000444130736916e-05,
|
|
"loss": 5.6511,
|
|
"mean_token_accuracy": 0.14344030618667603,
|
|
"num_tokens": 8743817.0,
|
|
"step": 3995
|
|
},
|
|
{
|
|
"entropy": 5.878951597213745,
|
|
"epoch": 0.264366676580417,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 5.0000123370043736e-05,
|
|
"loss": 5.5572,
|
|
"mean_token_accuracy": 0.14432633221149443,
|
|
"num_tokens": 8753830.0,
|
|
"step": 4000
|
|
}
|
|
],
|
|
"logging_steps": 5,
|
|
"max_steps": 4000,
|
|
"num_input_tokens_seen": 0,
|
|
"num_train_epochs": 1,
|
|
"save_steps": 500,
|
|
"stateful_callbacks": {
|
|
"TrainerControl": {
|
|
"args": {
|
|
"should_epoch_stop": false,
|
|
"should_evaluate": false,
|
|
"should_log": false,
|
|
"should_save": true,
|
|
"should_training_stop": true
|
|
},
|
|
"attributes": {}
|
|
}
|
|
},
|
|
"total_flos": 1.4580144377856e+16,
|
|
"train_batch_size": 16,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|