55bd702e53
Model: fpadovani/hin-deva-10mb-after-ppt-shuff-dyck-100mb-ckpt500_seed455 Source: Original Platform
6046 lines
164 KiB
JSON
6046 lines
164 KiB
JSON
{
|
|
"best_global_step": null,
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 0.2881844380403458,
|
|
"eval_steps": 3000,
|
|
"global_step": 3000,
|
|
"is_hyper_param_search": false,
|
|
"is_local_process_zero": true,
|
|
"is_world_process_zero": true,
|
|
"log_history": [
|
|
{
|
|
"entropy": 4.952998208999634,
|
|
"epoch": 0.0004803073967339097,
|
|
"grad_norm": 14.5625,
|
|
"learning_rate": 2e-06,
|
|
"loss": 14.2582,
|
|
"mean_token_accuracy": 0.0,
|
|
"num_tokens": 10821.0,
|
|
"step": 5
|
|
},
|
|
{
|
|
"entropy": 4.955690383911133,
|
|
"epoch": 0.0009606147934678194,
|
|
"grad_norm": 14.0,
|
|
"learning_rate": 4.5e-06,
|
|
"loss": 14.2611,
|
|
"mean_token_accuracy": 0.0,
|
|
"num_tokens": 21838.0,
|
|
"step": 10
|
|
},
|
|
{
|
|
"entropy": 4.961869859695435,
|
|
"epoch": 0.001440922190201729,
|
|
"grad_norm": 15.125,
|
|
"learning_rate": 7e-06,
|
|
"loss": 14.2406,
|
|
"mean_token_accuracy": 0.0001630714046768844,
|
|
"num_tokens": 33483.0,
|
|
"step": 15
|
|
},
|
|
{
|
|
"entropy": 5.000402975082397,
|
|
"epoch": 0.0019212295869356388,
|
|
"grad_norm": 17.625,
|
|
"learning_rate": 9.5e-06,
|
|
"loss": 14.0342,
|
|
"mean_token_accuracy": 0.0,
|
|
"num_tokens": 45150.0,
|
|
"step": 20
|
|
},
|
|
{
|
|
"entropy": 5.144548416137695,
|
|
"epoch": 0.0024015369836695487,
|
|
"grad_norm": 21.625,
|
|
"learning_rate": 1.2e-05,
|
|
"loss": 13.6497,
|
|
"mean_token_accuracy": 0.0,
|
|
"num_tokens": 55862.0,
|
|
"step": 25
|
|
},
|
|
{
|
|
"entropy": 5.467367696762085,
|
|
"epoch": 0.002881844380403458,
|
|
"grad_norm": 29.25,
|
|
"learning_rate": 1.4500000000000002e-05,
|
|
"loss": 13.0786,
|
|
"mean_token_accuracy": 0.0,
|
|
"num_tokens": 66766.0,
|
|
"step": 30
|
|
},
|
|
{
|
|
"entropy": 6.960640001296997,
|
|
"epoch": 0.0033621517771373678,
|
|
"grad_norm": 24.5,
|
|
"learning_rate": 1.7000000000000003e-05,
|
|
"loss": 11.9791,
|
|
"mean_token_accuracy": 0.0,
|
|
"num_tokens": 77012.0,
|
|
"step": 35
|
|
},
|
|
{
|
|
"entropy": 10.176104927062989,
|
|
"epoch": 0.0038424591738712775,
|
|
"grad_norm": 3.328125,
|
|
"learning_rate": 1.95e-05,
|
|
"loss": 10.8581,
|
|
"mean_token_accuracy": 0.0017824553069658577,
|
|
"num_tokens": 89034.0,
|
|
"step": 40
|
|
},
|
|
{
|
|
"entropy": 10.718319034576416,
|
|
"epoch": 0.004322766570605188,
|
|
"grad_norm": 2.9375,
|
|
"learning_rate": 2.2e-05,
|
|
"loss": 10.6429,
|
|
"mean_token_accuracy": 0.01355557688511908,
|
|
"num_tokens": 100341.0,
|
|
"step": 45
|
|
},
|
|
{
|
|
"entropy": 10.739382457733154,
|
|
"epoch": 0.004803073967339097,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 2.4500000000000003e-05,
|
|
"loss": 10.5214,
|
|
"mean_token_accuracy": 0.014157400839030743,
|
|
"num_tokens": 111997.0,
|
|
"step": 50
|
|
},
|
|
{
|
|
"entropy": 10.734613037109375,
|
|
"epoch": 0.005283381364073006,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 2.7e-05,
|
|
"loss": 10.3541,
|
|
"mean_token_accuracy": 0.014309123158454895,
|
|
"num_tokens": 123705.0,
|
|
"step": 55
|
|
},
|
|
{
|
|
"entropy": 10.708789348602295,
|
|
"epoch": 0.005763688760806916,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 2.95e-05,
|
|
"loss": 10.1416,
|
|
"mean_token_accuracy": 0.01604629335924983,
|
|
"num_tokens": 134091.0,
|
|
"step": 60
|
|
},
|
|
{
|
|
"entropy": 10.720145320892334,
|
|
"epoch": 0.006243996157540826,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 3.2e-05,
|
|
"loss": 10.0631,
|
|
"mean_token_accuracy": 0.01453780010342598,
|
|
"num_tokens": 145731.0,
|
|
"step": 65
|
|
},
|
|
{
|
|
"entropy": 10.739076805114745,
|
|
"epoch": 0.0067243035542747355,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 3.4500000000000005e-05,
|
|
"loss": 9.9517,
|
|
"mean_token_accuracy": 0.017807454522699117,
|
|
"num_tokens": 156979.0,
|
|
"step": 70
|
|
},
|
|
{
|
|
"entropy": 10.738404560089112,
|
|
"epoch": 0.007204610951008645,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 3.7e-05,
|
|
"loss": 9.8629,
|
|
"mean_token_accuracy": 0.024540318921208382,
|
|
"num_tokens": 167021.0,
|
|
"step": 75
|
|
},
|
|
{
|
|
"entropy": 10.731132507324219,
|
|
"epoch": 0.007684918347742555,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 3.95e-05,
|
|
"loss": 9.819,
|
|
"mean_token_accuracy": 0.020528202410787344,
|
|
"num_tokens": 179269.0,
|
|
"step": 80
|
|
},
|
|
{
|
|
"entropy": 10.73000726699829,
|
|
"epoch": 0.008165225744476465,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 4.2000000000000004e-05,
|
|
"loss": 9.7216,
|
|
"mean_token_accuracy": 0.020909248571842908,
|
|
"num_tokens": 190328.0,
|
|
"step": 85
|
|
},
|
|
{
|
|
"entropy": 10.728069496154784,
|
|
"epoch": 0.008645533141210375,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 4.45e-05,
|
|
"loss": 9.5738,
|
|
"mean_token_accuracy": 0.021778783388435842,
|
|
"num_tokens": 201522.0,
|
|
"step": 90
|
|
},
|
|
{
|
|
"entropy": 10.719436931610108,
|
|
"epoch": 0.009125840537944284,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 4.7000000000000004e-05,
|
|
"loss": 9.4983,
|
|
"mean_token_accuracy": 0.022924750670790674,
|
|
"num_tokens": 212963.0,
|
|
"step": 95
|
|
},
|
|
{
|
|
"entropy": 10.704556751251221,
|
|
"epoch": 0.009606147934678195,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 4.9500000000000004e-05,
|
|
"loss": 9.4627,
|
|
"mean_token_accuracy": 0.026258311606943606,
|
|
"num_tokens": 224446.0,
|
|
"step": 100
|
|
},
|
|
{
|
|
"entropy": 10.686229038238526,
|
|
"epoch": 0.010086455331412104,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 5.2e-05,
|
|
"loss": 9.2916,
|
|
"mean_token_accuracy": 0.03442668188363314,
|
|
"num_tokens": 235334.0,
|
|
"step": 105
|
|
},
|
|
{
|
|
"entropy": 10.660537052154542,
|
|
"epoch": 0.010566762728146013,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 5.45e-05,
|
|
"loss": 9.1974,
|
|
"mean_token_accuracy": 0.038018427044153216,
|
|
"num_tokens": 247024.0,
|
|
"step": 110
|
|
},
|
|
{
|
|
"entropy": 10.629736328125,
|
|
"epoch": 0.011047070124879923,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 5.7e-05,
|
|
"loss": 9.044,
|
|
"mean_token_accuracy": 0.03711554128676653,
|
|
"num_tokens": 258354.0,
|
|
"step": 115
|
|
},
|
|
{
|
|
"entropy": 10.596047592163085,
|
|
"epoch": 0.011527377521613832,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 5.9499999999999996e-05,
|
|
"loss": 8.954,
|
|
"mean_token_accuracy": 0.03982700537890196,
|
|
"num_tokens": 271202.0,
|
|
"step": 120
|
|
},
|
|
{
|
|
"entropy": 10.551871967315673,
|
|
"epoch": 0.012007684918347743,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 6.2e-05,
|
|
"loss": 8.8293,
|
|
"mean_token_accuracy": 0.03978835418820381,
|
|
"num_tokens": 282405.0,
|
|
"step": 125
|
|
},
|
|
{
|
|
"entropy": 10.49206190109253,
|
|
"epoch": 0.012487992315081652,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 6.450000000000001e-05,
|
|
"loss": 8.6826,
|
|
"mean_token_accuracy": 0.039380787685513494,
|
|
"num_tokens": 294211.0,
|
|
"step": 130
|
|
},
|
|
{
|
|
"entropy": 10.426816463470459,
|
|
"epoch": 0.012968299711815562,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 6.7e-05,
|
|
"loss": 8.6088,
|
|
"mean_token_accuracy": 0.03625727668404579,
|
|
"num_tokens": 305420.0,
|
|
"step": 135
|
|
},
|
|
{
|
|
"entropy": 10.343353271484375,
|
|
"epoch": 0.013448607108549471,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 6.950000000000001e-05,
|
|
"loss": 8.4538,
|
|
"mean_token_accuracy": 0.04094459749758243,
|
|
"num_tokens": 316430.0,
|
|
"step": 140
|
|
},
|
|
{
|
|
"entropy": 10.245965957641602,
|
|
"epoch": 0.013928914505283382,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 7.2e-05,
|
|
"loss": 8.3471,
|
|
"mean_token_accuracy": 0.03853845577687025,
|
|
"num_tokens": 328406.0,
|
|
"step": 145
|
|
},
|
|
{
|
|
"entropy": 10.129299736022949,
|
|
"epoch": 0.01440922190201729,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 7.45e-05,
|
|
"loss": 8.2251,
|
|
"mean_token_accuracy": 0.0405678428709507,
|
|
"num_tokens": 339051.0,
|
|
"step": 150
|
|
},
|
|
{
|
|
"entropy": 9.980317115783691,
|
|
"epoch": 0.014889529298751201,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 7.7e-05,
|
|
"loss": 8.1161,
|
|
"mean_token_accuracy": 0.04249956700950861,
|
|
"num_tokens": 350308.0,
|
|
"step": 155
|
|
},
|
|
{
|
|
"entropy": 9.8000244140625,
|
|
"epoch": 0.01536983669548511,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 7.950000000000001e-05,
|
|
"loss": 8.0193,
|
|
"mean_token_accuracy": 0.04042474515736103,
|
|
"num_tokens": 362159.0,
|
|
"step": 160
|
|
},
|
|
{
|
|
"entropy": 9.598854160308838,
|
|
"epoch": 0.01585014409221902,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 8.2e-05,
|
|
"loss": 7.951,
|
|
"mean_token_accuracy": 0.0442409684881568,
|
|
"num_tokens": 375157.0,
|
|
"step": 165
|
|
},
|
|
{
|
|
"entropy": 9.361251831054688,
|
|
"epoch": 0.01633045148895293,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 8.450000000000001e-05,
|
|
"loss": 7.7913,
|
|
"mean_token_accuracy": 0.05417908914387226,
|
|
"num_tokens": 387318.0,
|
|
"step": 170
|
|
},
|
|
{
|
|
"entropy": 9.094889831542968,
|
|
"epoch": 0.01681075888568684,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 8.7e-05,
|
|
"loss": 7.7466,
|
|
"mean_token_accuracy": 0.06120046563446522,
|
|
"num_tokens": 398933.0,
|
|
"step": 175
|
|
},
|
|
{
|
|
"entropy": 8.835952472686767,
|
|
"epoch": 0.01729106628242075,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 8.95e-05,
|
|
"loss": 7.6633,
|
|
"mean_token_accuracy": 0.05573962703347206,
|
|
"num_tokens": 410460.0,
|
|
"step": 180
|
|
},
|
|
{
|
|
"entropy": 8.607842922210693,
|
|
"epoch": 0.01777137367915466,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 9.2e-05,
|
|
"loss": 7.6204,
|
|
"mean_token_accuracy": 0.056572451069951055,
|
|
"num_tokens": 421894.0,
|
|
"step": 185
|
|
},
|
|
{
|
|
"entropy": 8.41255807876587,
|
|
"epoch": 0.01825168107588857,
|
|
"grad_norm": 0.69140625,
|
|
"learning_rate": 9.45e-05,
|
|
"loss": 7.6005,
|
|
"mean_token_accuracy": 0.05312460921704769,
|
|
"num_tokens": 432976.0,
|
|
"step": 190
|
|
},
|
|
{
|
|
"entropy": 8.314041900634766,
|
|
"epoch": 0.018731988472622477,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 9.7e-05,
|
|
"loss": 7.6613,
|
|
"mean_token_accuracy": 0.05617779567837715,
|
|
"num_tokens": 444859.0,
|
|
"step": 195
|
|
},
|
|
{
|
|
"entropy": 8.262031841278077,
|
|
"epoch": 0.01921229586935639,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 9.95e-05,
|
|
"loss": 7.5566,
|
|
"mean_token_accuracy": 0.06568880900740623,
|
|
"num_tokens": 456508.0,
|
|
"step": 200
|
|
},
|
|
{
|
|
"entropy": 8.133868789672851,
|
|
"epoch": 0.0196926032660903,
|
|
"grad_norm": 0.7578125,
|
|
"learning_rate": 0.000102,
|
|
"loss": 7.5667,
|
|
"mean_token_accuracy": 0.06184492409229279,
|
|
"num_tokens": 469064.0,
|
|
"step": 205
|
|
},
|
|
{
|
|
"entropy": 8.096502780914307,
|
|
"epoch": 0.020172910662824207,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00010449999999999999,
|
|
"loss": 7.4995,
|
|
"mean_token_accuracy": 0.06528568714857101,
|
|
"num_tokens": 480743.0,
|
|
"step": 210
|
|
},
|
|
{
|
|
"entropy": 8.07320432662964,
|
|
"epoch": 0.020653218059558116,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000107,
|
|
"loss": 7.5222,
|
|
"mean_token_accuracy": 0.07013107351958751,
|
|
"num_tokens": 493378.0,
|
|
"step": 215
|
|
},
|
|
{
|
|
"entropy": 8.062201929092407,
|
|
"epoch": 0.021133525456292025,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0001095,
|
|
"loss": 7.4632,
|
|
"mean_token_accuracy": 0.07239910811185837,
|
|
"num_tokens": 505641.0,
|
|
"step": 220
|
|
},
|
|
{
|
|
"entropy": 8.092798614501953,
|
|
"epoch": 0.021613832853025938,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.000112,
|
|
"loss": 7.5153,
|
|
"mean_token_accuracy": 0.0712558664381504,
|
|
"num_tokens": 517783.0,
|
|
"step": 225
|
|
},
|
|
{
|
|
"entropy": 8.056060886383056,
|
|
"epoch": 0.022094140249759846,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0001145,
|
|
"loss": 7.3885,
|
|
"mean_token_accuracy": 0.0776093952357769,
|
|
"num_tokens": 528407.0,
|
|
"step": 230
|
|
},
|
|
{
|
|
"entropy": 8.07971124649048,
|
|
"epoch": 0.022574447646493755,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00011700000000000001,
|
|
"loss": 7.499,
|
|
"mean_token_accuracy": 0.07200518772006034,
|
|
"num_tokens": 539974.0,
|
|
"step": 235
|
|
},
|
|
{
|
|
"entropy": 8.014474582672118,
|
|
"epoch": 0.023054755043227664,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00011949999999999999,
|
|
"loss": 7.3531,
|
|
"mean_token_accuracy": 0.07475511692464351,
|
|
"num_tokens": 551127.0,
|
|
"step": 240
|
|
},
|
|
{
|
|
"entropy": 8.012955379486083,
|
|
"epoch": 0.023535062439961577,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.000122,
|
|
"loss": 7.3664,
|
|
"mean_token_accuracy": 0.08100151270627975,
|
|
"num_tokens": 561980.0,
|
|
"step": 245
|
|
},
|
|
{
|
|
"entropy": 8.09322385787964,
|
|
"epoch": 0.024015369836695485,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0001245,
|
|
"loss": 7.3988,
|
|
"mean_token_accuracy": 0.07981968075037002,
|
|
"num_tokens": 573840.0,
|
|
"step": 250
|
|
},
|
|
{
|
|
"entropy": 7.97099084854126,
|
|
"epoch": 0.024495677233429394,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.000127,
|
|
"loss": 7.2948,
|
|
"mean_token_accuracy": 0.0818309374153614,
|
|
"num_tokens": 585110.0,
|
|
"step": 255
|
|
},
|
|
{
|
|
"entropy": 7.940869426727295,
|
|
"epoch": 0.024975984630163303,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0001295,
|
|
"loss": 7.2052,
|
|
"mean_token_accuracy": 0.08267272785305976,
|
|
"num_tokens": 596902.0,
|
|
"step": 260
|
|
},
|
|
{
|
|
"entropy": 7.915973138809204,
|
|
"epoch": 0.025456292026897216,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000132,
|
|
"loss": 7.3346,
|
|
"mean_token_accuracy": 0.08441563807427883,
|
|
"num_tokens": 608738.0,
|
|
"step": 265
|
|
},
|
|
{
|
|
"entropy": 7.930963659286499,
|
|
"epoch": 0.025936599423631124,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00013450000000000002,
|
|
"loss": 7.2662,
|
|
"mean_token_accuracy": 0.07967347651720047,
|
|
"num_tokens": 621078.0,
|
|
"step": 270
|
|
},
|
|
{
|
|
"entropy": 7.923765468597412,
|
|
"epoch": 0.026416906820365033,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00013700000000000002,
|
|
"loss": 7.3281,
|
|
"mean_token_accuracy": 0.08380152806639671,
|
|
"num_tokens": 632333.0,
|
|
"step": 275
|
|
},
|
|
{
|
|
"entropy": 7.8553708553314205,
|
|
"epoch": 0.026897214217098942,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0001395,
|
|
"loss": 7.1392,
|
|
"mean_token_accuracy": 0.08382196128368377,
|
|
"num_tokens": 644474.0,
|
|
"step": 280
|
|
},
|
|
{
|
|
"entropy": 7.874654054641724,
|
|
"epoch": 0.027377521613832854,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00014199999999999998,
|
|
"loss": 7.2046,
|
|
"mean_token_accuracy": 0.08822997659444809,
|
|
"num_tokens": 655608.0,
|
|
"step": 285
|
|
},
|
|
{
|
|
"entropy": 7.8405436992645265,
|
|
"epoch": 0.027857829010566763,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0001445,
|
|
"loss": 7.2322,
|
|
"mean_token_accuracy": 0.08056687787175179,
|
|
"num_tokens": 667371.0,
|
|
"step": 290
|
|
},
|
|
{
|
|
"entropy": 7.788603258132935,
|
|
"epoch": 0.028338136407300672,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.000147,
|
|
"loss": 7.2274,
|
|
"mean_token_accuracy": 0.08374285846948623,
|
|
"num_tokens": 679152.0,
|
|
"step": 295
|
|
},
|
|
{
|
|
"entropy": 7.757482385635376,
|
|
"epoch": 0.02881844380403458,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0001495,
|
|
"loss": 7.1415,
|
|
"mean_token_accuracy": 0.09327690675854683,
|
|
"num_tokens": 690359.0,
|
|
"step": 300
|
|
},
|
|
{
|
|
"entropy": 7.725837469100952,
|
|
"epoch": 0.029298751200768493,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000152,
|
|
"loss": 7.1113,
|
|
"mean_token_accuracy": 0.0908672846853733,
|
|
"num_tokens": 701819.0,
|
|
"step": 305
|
|
},
|
|
{
|
|
"entropy": 7.791640710830689,
|
|
"epoch": 0.029779058597502402,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.00015450000000000001,
|
|
"loss": 7.1544,
|
|
"mean_token_accuracy": 0.08916135728359223,
|
|
"num_tokens": 711048.0,
|
|
"step": 310
|
|
},
|
|
{
|
|
"entropy": 7.7330770015716555,
|
|
"epoch": 0.03025936599423631,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000157,
|
|
"loss": 7.0486,
|
|
"mean_token_accuracy": 0.0980133630335331,
|
|
"num_tokens": 721399.0,
|
|
"step": 315
|
|
},
|
|
{
|
|
"entropy": 7.682194662094116,
|
|
"epoch": 0.03073967339097022,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0001595,
|
|
"loss": 7.0748,
|
|
"mean_token_accuracy": 0.09791787564754487,
|
|
"num_tokens": 732144.0,
|
|
"step": 320
|
|
},
|
|
{
|
|
"entropy": 7.704891967773437,
|
|
"epoch": 0.03121998078770413,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.000162,
|
|
"loss": 7.0133,
|
|
"mean_token_accuracy": 0.09394430741667747,
|
|
"num_tokens": 743962.0,
|
|
"step": 325
|
|
},
|
|
{
|
|
"entropy": 7.67185001373291,
|
|
"epoch": 0.03170028818443804,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00016450000000000001,
|
|
"loss": 7.1606,
|
|
"mean_token_accuracy": 0.09519302621483802,
|
|
"num_tokens": 755641.0,
|
|
"step": 330
|
|
},
|
|
{
|
|
"entropy": 7.65534348487854,
|
|
"epoch": 0.03218059558117195,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.00016700000000000002,
|
|
"loss": 6.9888,
|
|
"mean_token_accuracy": 0.1040790244936943,
|
|
"num_tokens": 766798.0,
|
|
"step": 335
|
|
},
|
|
{
|
|
"entropy": 7.634436845779419,
|
|
"epoch": 0.03266090297790586,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00016950000000000003,
|
|
"loss": 7.0797,
|
|
"mean_token_accuracy": 0.10063858479261398,
|
|
"num_tokens": 778097.0,
|
|
"step": 340
|
|
},
|
|
{
|
|
"entropy": 7.547883176803589,
|
|
"epoch": 0.03314121037463977,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00017199999999999998,
|
|
"loss": 6.9963,
|
|
"mean_token_accuracy": 0.10573035553097725,
|
|
"num_tokens": 789775.0,
|
|
"step": 345
|
|
},
|
|
{
|
|
"entropy": 7.640296983718872,
|
|
"epoch": 0.03362151777137368,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00017449999999999999,
|
|
"loss": 7.0568,
|
|
"mean_token_accuracy": 0.09917445480823517,
|
|
"num_tokens": 800155.0,
|
|
"step": 350
|
|
},
|
|
{
|
|
"entropy": 7.624283695220948,
|
|
"epoch": 0.034101825168107586,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.000177,
|
|
"loss": 7.0508,
|
|
"mean_token_accuracy": 0.10235279574990272,
|
|
"num_tokens": 811213.0,
|
|
"step": 355
|
|
},
|
|
{
|
|
"entropy": 7.644110107421875,
|
|
"epoch": 0.0345821325648415,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0001795,
|
|
"loss": 7.0427,
|
|
"mean_token_accuracy": 0.09794286787509918,
|
|
"num_tokens": 822832.0,
|
|
"step": 360
|
|
},
|
|
{
|
|
"entropy": 7.549008846282959,
|
|
"epoch": 0.03506243996157541,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000182,
|
|
"loss": 7.0118,
|
|
"mean_token_accuracy": 0.10539761856198311,
|
|
"num_tokens": 834824.0,
|
|
"step": 365
|
|
},
|
|
{
|
|
"entropy": 7.598927068710327,
|
|
"epoch": 0.03554274735830932,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0001845,
|
|
"loss": 7.046,
|
|
"mean_token_accuracy": 0.10215208157896996,
|
|
"num_tokens": 846969.0,
|
|
"step": 370
|
|
},
|
|
{
|
|
"entropy": 7.629372644424438,
|
|
"epoch": 0.03602305475504323,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.000187,
|
|
"loss": 7.1144,
|
|
"mean_token_accuracy": 0.09570988789200782,
|
|
"num_tokens": 859271.0,
|
|
"step": 375
|
|
},
|
|
{
|
|
"entropy": 7.489568710327148,
|
|
"epoch": 0.03650336215177714,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0001895,
|
|
"loss": 7.0168,
|
|
"mean_token_accuracy": 0.1066791370511055,
|
|
"num_tokens": 869754.0,
|
|
"step": 380
|
|
},
|
|
{
|
|
"entropy": 7.518455076217651,
|
|
"epoch": 0.036983669548511046,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.000192,
|
|
"loss": 6.9428,
|
|
"mean_token_accuracy": 0.10733397230505944,
|
|
"num_tokens": 880519.0,
|
|
"step": 385
|
|
},
|
|
{
|
|
"entropy": 7.433148956298828,
|
|
"epoch": 0.037463976945244955,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0001945,
|
|
"loss": 6.9057,
|
|
"mean_token_accuracy": 0.10587815120816231,
|
|
"num_tokens": 890765.0,
|
|
"step": 390
|
|
},
|
|
{
|
|
"entropy": 7.51275486946106,
|
|
"epoch": 0.037944284341978864,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00019700000000000002,
|
|
"loss": 6.9144,
|
|
"mean_token_accuracy": 0.10545952916145325,
|
|
"num_tokens": 901717.0,
|
|
"step": 395
|
|
},
|
|
{
|
|
"entropy": 7.56442084312439,
|
|
"epoch": 0.03842459173871278,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00019950000000000002,
|
|
"loss": 6.9775,
|
|
"mean_token_accuracy": 0.10485790073871612,
|
|
"num_tokens": 913334.0,
|
|
"step": 400
|
|
},
|
|
{
|
|
"entropy": 7.5254968166351315,
|
|
"epoch": 0.03890489913544669,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000202,
|
|
"loss": 6.9865,
|
|
"mean_token_accuracy": 0.10525585263967514,
|
|
"num_tokens": 924753.0,
|
|
"step": 405
|
|
},
|
|
{
|
|
"entropy": 7.441157817840576,
|
|
"epoch": 0.0393852065321806,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00020449999999999998,
|
|
"loss": 6.921,
|
|
"mean_token_accuracy": 0.10738600119948387,
|
|
"num_tokens": 935692.0,
|
|
"step": 410
|
|
},
|
|
{
|
|
"entropy": 7.468551778793335,
|
|
"epoch": 0.039865513928914506,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000207,
|
|
"loss": 7.0066,
|
|
"mean_token_accuracy": 0.10407103821635247,
|
|
"num_tokens": 947902.0,
|
|
"step": 415
|
|
},
|
|
{
|
|
"entropy": 7.422157144546508,
|
|
"epoch": 0.040345821325648415,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0002095,
|
|
"loss": 6.9215,
|
|
"mean_token_accuracy": 0.10983402356505394,
|
|
"num_tokens": 959437.0,
|
|
"step": 420
|
|
},
|
|
{
|
|
"entropy": 7.329869747161865,
|
|
"epoch": 0.040826128722382324,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.000212,
|
|
"loss": 6.7483,
|
|
"mean_token_accuracy": 0.11806870326399803,
|
|
"num_tokens": 970191.0,
|
|
"step": 425
|
|
},
|
|
{
|
|
"entropy": 7.379027938842773,
|
|
"epoch": 0.04130643611911623,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0002145,
|
|
"loss": 6.8638,
|
|
"mean_token_accuracy": 0.10865884721279144,
|
|
"num_tokens": 981811.0,
|
|
"step": 430
|
|
},
|
|
{
|
|
"entropy": 7.4306111335754395,
|
|
"epoch": 0.04178674351585014,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00021700000000000002,
|
|
"loss": 6.9707,
|
|
"mean_token_accuracy": 0.10563067272305489,
|
|
"num_tokens": 994034.0,
|
|
"step": 435
|
|
},
|
|
{
|
|
"entropy": 7.317675256729126,
|
|
"epoch": 0.04226705091258405,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0002195,
|
|
"loss": 6.9255,
|
|
"mean_token_accuracy": 0.10667062103748322,
|
|
"num_tokens": 1005506.0,
|
|
"step": 440
|
|
},
|
|
{
|
|
"entropy": 7.382990884780884,
|
|
"epoch": 0.042747358309317966,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.000222,
|
|
"loss": 6.8792,
|
|
"mean_token_accuracy": 0.10067129284143447,
|
|
"num_tokens": 1017103.0,
|
|
"step": 445
|
|
},
|
|
{
|
|
"entropy": 7.375922918319702,
|
|
"epoch": 0.043227665706051875,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0002245,
|
|
"loss": 6.9606,
|
|
"mean_token_accuracy": 0.10542604103684425,
|
|
"num_tokens": 1029606.0,
|
|
"step": 450
|
|
},
|
|
{
|
|
"entropy": 7.423660087585449,
|
|
"epoch": 0.043707973102785784,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00022700000000000002,
|
|
"loss": 6.9113,
|
|
"mean_token_accuracy": 0.10665275976061821,
|
|
"num_tokens": 1041899.0,
|
|
"step": 455
|
|
},
|
|
{
|
|
"entropy": 7.303192949295044,
|
|
"epoch": 0.04418828049951969,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00022950000000000002,
|
|
"loss": 6.8294,
|
|
"mean_token_accuracy": 0.11543489247560501,
|
|
"num_tokens": 1053577.0,
|
|
"step": 460
|
|
},
|
|
{
|
|
"entropy": 7.357319164276123,
|
|
"epoch": 0.0446685878962536,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00023200000000000003,
|
|
"loss": 6.8798,
|
|
"mean_token_accuracy": 0.11370891258120537,
|
|
"num_tokens": 1065541.0,
|
|
"step": 465
|
|
},
|
|
{
|
|
"entropy": 7.381957864761352,
|
|
"epoch": 0.04514889529298751,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00023449999999999998,
|
|
"loss": 6.8192,
|
|
"mean_token_accuracy": 0.1103691153228283,
|
|
"num_tokens": 1076138.0,
|
|
"step": 470
|
|
},
|
|
{
|
|
"entropy": 7.3531769752502445,
|
|
"epoch": 0.04562920268972142,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000237,
|
|
"loss": 6.8676,
|
|
"mean_token_accuracy": 0.11432998552918434,
|
|
"num_tokens": 1087620.0,
|
|
"step": 475
|
|
},
|
|
{
|
|
"entropy": 7.271972751617431,
|
|
"epoch": 0.04610951008645533,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0002395,
|
|
"loss": 6.765,
|
|
"mean_token_accuracy": 0.11456627622246743,
|
|
"num_tokens": 1099493.0,
|
|
"step": 480
|
|
},
|
|
{
|
|
"entropy": 7.294817638397217,
|
|
"epoch": 0.046589817483189244,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000242,
|
|
"loss": 6.8052,
|
|
"mean_token_accuracy": 0.11549188196659088,
|
|
"num_tokens": 1110559.0,
|
|
"step": 485
|
|
},
|
|
{
|
|
"entropy": 7.216236162185669,
|
|
"epoch": 0.04707012487992315,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0002445,
|
|
"loss": 6.7756,
|
|
"mean_token_accuracy": 0.10924254432320595,
|
|
"num_tokens": 1121051.0,
|
|
"step": 490
|
|
},
|
|
{
|
|
"entropy": 7.257420635223388,
|
|
"epoch": 0.04755043227665706,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000247,
|
|
"loss": 6.7499,
|
|
"mean_token_accuracy": 0.11539025753736495,
|
|
"num_tokens": 1132305.0,
|
|
"step": 495
|
|
},
|
|
{
|
|
"entropy": 7.321677541732788,
|
|
"epoch": 0.04803073967339097,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0002495,
|
|
"loss": 6.7571,
|
|
"mean_token_accuracy": 0.11674077361822129,
|
|
"num_tokens": 1142979.0,
|
|
"step": 500
|
|
},
|
|
{
|
|
"entropy": 7.188573884963989,
|
|
"epoch": 0.04851104707012488,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.000252,
|
|
"loss": 6.7549,
|
|
"mean_token_accuracy": 0.11924750506877899,
|
|
"num_tokens": 1153889.0,
|
|
"step": 505
|
|
},
|
|
{
|
|
"entropy": 7.244559097290039,
|
|
"epoch": 0.04899135446685879,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0002545,
|
|
"loss": 6.7565,
|
|
"mean_token_accuracy": 0.11460114493966103,
|
|
"num_tokens": 1166030.0,
|
|
"step": 510
|
|
},
|
|
{
|
|
"entropy": 7.383937501907349,
|
|
"epoch": 0.0494716618635927,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.000257,
|
|
"loss": 6.9289,
|
|
"mean_token_accuracy": 0.10644723549485206,
|
|
"num_tokens": 1177545.0,
|
|
"step": 515
|
|
},
|
|
{
|
|
"entropy": 7.166497278213501,
|
|
"epoch": 0.049951969260326606,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0002595,
|
|
"loss": 6.7357,
|
|
"mean_token_accuracy": 0.12091782912611962,
|
|
"num_tokens": 1188944.0,
|
|
"step": 520
|
|
},
|
|
{
|
|
"entropy": 7.2184765338897705,
|
|
"epoch": 0.05043227665706052,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.000262,
|
|
"loss": 6.8006,
|
|
"mean_token_accuracy": 0.11136688962578774,
|
|
"num_tokens": 1199517.0,
|
|
"step": 525
|
|
},
|
|
{
|
|
"entropy": 7.175792932510376,
|
|
"epoch": 0.05091258405379443,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00026450000000000003,
|
|
"loss": 6.7376,
|
|
"mean_token_accuracy": 0.11152568534016609,
|
|
"num_tokens": 1211536.0,
|
|
"step": 530
|
|
},
|
|
{
|
|
"entropy": 7.124487686157226,
|
|
"epoch": 0.05139289145052834,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00026700000000000004,
|
|
"loss": 6.6428,
|
|
"mean_token_accuracy": 0.12353976517915725,
|
|
"num_tokens": 1224159.0,
|
|
"step": 535
|
|
},
|
|
{
|
|
"entropy": 7.199137878417969,
|
|
"epoch": 0.05187319884726225,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00026950000000000005,
|
|
"loss": 6.7006,
|
|
"mean_token_accuracy": 0.12614266201853752,
|
|
"num_tokens": 1235226.0,
|
|
"step": 540
|
|
},
|
|
{
|
|
"entropy": 7.1002240657806395,
|
|
"epoch": 0.05235350624399616,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00027200000000000005,
|
|
"loss": 6.6409,
|
|
"mean_token_accuracy": 0.12885337471961975,
|
|
"num_tokens": 1245862.0,
|
|
"step": 545
|
|
},
|
|
{
|
|
"entropy": 7.0684572696685795,
|
|
"epoch": 0.052833813640730067,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0002745,
|
|
"loss": 6.6448,
|
|
"mean_token_accuracy": 0.12506688982248307,
|
|
"num_tokens": 1257512.0,
|
|
"step": 550
|
|
},
|
|
{
|
|
"entropy": 7.15536675453186,
|
|
"epoch": 0.053314121037463975,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.000277,
|
|
"loss": 6.7532,
|
|
"mean_token_accuracy": 0.11791636049747467,
|
|
"num_tokens": 1269317.0,
|
|
"step": 555
|
|
},
|
|
{
|
|
"entropy": 7.05263729095459,
|
|
"epoch": 0.053794428434197884,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0002795,
|
|
"loss": 6.6387,
|
|
"mean_token_accuracy": 0.11247576996684075,
|
|
"num_tokens": 1281878.0,
|
|
"step": 560
|
|
},
|
|
{
|
|
"entropy": 7.032025909423828,
|
|
"epoch": 0.05427473583093179,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00028199999999999997,
|
|
"loss": 6.6567,
|
|
"mean_token_accuracy": 0.12334890589118004,
|
|
"num_tokens": 1293178.0,
|
|
"step": 565
|
|
},
|
|
{
|
|
"entropy": 7.021555423736572,
|
|
"epoch": 0.05475504322766571,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0002845,
|
|
"loss": 6.641,
|
|
"mean_token_accuracy": 0.12092255204916,
|
|
"num_tokens": 1304969.0,
|
|
"step": 570
|
|
},
|
|
{
|
|
"entropy": 7.173486518859863,
|
|
"epoch": 0.05523535062439962,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000287,
|
|
"loss": 6.6615,
|
|
"mean_token_accuracy": 0.12557224780321122,
|
|
"num_tokens": 1317301.0,
|
|
"step": 575
|
|
},
|
|
{
|
|
"entropy": 7.086919069290161,
|
|
"epoch": 0.05571565802113353,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0002895,
|
|
"loss": 6.6481,
|
|
"mean_token_accuracy": 0.12229160591959953,
|
|
"num_tokens": 1327688.0,
|
|
"step": 580
|
|
},
|
|
{
|
|
"entropy": 7.105197381973267,
|
|
"epoch": 0.056195965417867436,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.000292,
|
|
"loss": 6.5803,
|
|
"mean_token_accuracy": 0.1251593180000782,
|
|
"num_tokens": 1338750.0,
|
|
"step": 585
|
|
},
|
|
{
|
|
"entropy": 7.099721193313599,
|
|
"epoch": 0.056676272814601344,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0002945,
|
|
"loss": 6.7331,
|
|
"mean_token_accuracy": 0.11501363664865494,
|
|
"num_tokens": 1350899.0,
|
|
"step": 590
|
|
},
|
|
{
|
|
"entropy": 7.106310939788818,
|
|
"epoch": 0.05715658021133525,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.000297,
|
|
"loss": 6.6048,
|
|
"mean_token_accuracy": 0.12520924732089042,
|
|
"num_tokens": 1363184.0,
|
|
"step": 595
|
|
},
|
|
{
|
|
"entropy": 7.0411724090576175,
|
|
"epoch": 0.05763688760806916,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0002995,
|
|
"loss": 6.582,
|
|
"mean_token_accuracy": 0.1271129161119461,
|
|
"num_tokens": 1374192.0,
|
|
"step": 600
|
|
},
|
|
{
|
|
"entropy": 6.922922134399414,
|
|
"epoch": 0.05811719500480307,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.000302,
|
|
"loss": 6.594,
|
|
"mean_token_accuracy": 0.12445875108242035,
|
|
"num_tokens": 1384888.0,
|
|
"step": 605
|
|
},
|
|
{
|
|
"entropy": 7.115780639648437,
|
|
"epoch": 0.05859750240153699,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0003045,
|
|
"loss": 6.6765,
|
|
"mean_token_accuracy": 0.1298594705760479,
|
|
"num_tokens": 1395139.0,
|
|
"step": 610
|
|
},
|
|
{
|
|
"entropy": 6.956879568099976,
|
|
"epoch": 0.059077809798270896,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.000307,
|
|
"loss": 6.487,
|
|
"mean_token_accuracy": 0.12400545477867127,
|
|
"num_tokens": 1407219.0,
|
|
"step": 615
|
|
},
|
|
{
|
|
"entropy": 7.013321304321289,
|
|
"epoch": 0.059558117195004805,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0003095,
|
|
"loss": 6.6015,
|
|
"mean_token_accuracy": 0.12258810997009277,
|
|
"num_tokens": 1418917.0,
|
|
"step": 620
|
|
},
|
|
{
|
|
"entropy": 7.036109256744385,
|
|
"epoch": 0.060038424591738714,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000312,
|
|
"loss": 6.5567,
|
|
"mean_token_accuracy": 0.12197562456130981,
|
|
"num_tokens": 1430792.0,
|
|
"step": 625
|
|
},
|
|
{
|
|
"entropy": 6.967579412460327,
|
|
"epoch": 0.06051873198847262,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0003145,
|
|
"loss": 6.5753,
|
|
"mean_token_accuracy": 0.12886715084314346,
|
|
"num_tokens": 1442825.0,
|
|
"step": 630
|
|
},
|
|
{
|
|
"entropy": 7.002191114425659,
|
|
"epoch": 0.06099903938520653,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000317,
|
|
"loss": 6.6694,
|
|
"mean_token_accuracy": 0.1262420743703842,
|
|
"num_tokens": 1454078.0,
|
|
"step": 635
|
|
},
|
|
{
|
|
"entropy": 6.952101945877075,
|
|
"epoch": 0.06147934678194044,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0003195,
|
|
"loss": 6.6083,
|
|
"mean_token_accuracy": 0.12252153679728509,
|
|
"num_tokens": 1465164.0,
|
|
"step": 640
|
|
},
|
|
{
|
|
"entropy": 7.042235279083252,
|
|
"epoch": 0.06195965417867435,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.000322,
|
|
"loss": 6.5864,
|
|
"mean_token_accuracy": 0.12691230326890945,
|
|
"num_tokens": 1476813.0,
|
|
"step": 645
|
|
},
|
|
{
|
|
"entropy": 6.95318078994751,
|
|
"epoch": 0.06243996157540826,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00032450000000000003,
|
|
"loss": 6.6147,
|
|
"mean_token_accuracy": 0.12464898824691772,
|
|
"num_tokens": 1488547.0,
|
|
"step": 650
|
|
},
|
|
{
|
|
"entropy": 7.05318603515625,
|
|
"epoch": 0.06292026897214217,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00032700000000000003,
|
|
"loss": 6.6125,
|
|
"mean_token_accuracy": 0.12129621878266335,
|
|
"num_tokens": 1500714.0,
|
|
"step": 655
|
|
},
|
|
{
|
|
"entropy": 6.901967525482178,
|
|
"epoch": 0.06340057636887608,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00032950000000000004,
|
|
"loss": 6.5812,
|
|
"mean_token_accuracy": 0.13022611066699027,
|
|
"num_tokens": 1512212.0,
|
|
"step": 660
|
|
},
|
|
{
|
|
"entropy": 6.97374701499939,
|
|
"epoch": 0.06388088376560999,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00033200000000000005,
|
|
"loss": 6.5642,
|
|
"mean_token_accuracy": 0.1291198454797268,
|
|
"num_tokens": 1523610.0,
|
|
"step": 665
|
|
},
|
|
{
|
|
"entropy": 6.8925048351287845,
|
|
"epoch": 0.0643611911623439,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00033450000000000005,
|
|
"loss": 6.5201,
|
|
"mean_token_accuracy": 0.12605366334319115,
|
|
"num_tokens": 1535543.0,
|
|
"step": 670
|
|
},
|
|
{
|
|
"entropy": 7.089626169204712,
|
|
"epoch": 0.06484149855907781,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.000337,
|
|
"loss": 6.74,
|
|
"mean_token_accuracy": 0.12375304996967315,
|
|
"num_tokens": 1547183.0,
|
|
"step": 675
|
|
},
|
|
{
|
|
"entropy": 6.861551904678345,
|
|
"epoch": 0.06532180595581172,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0003395,
|
|
"loss": 6.4903,
|
|
"mean_token_accuracy": 0.13013082817196847,
|
|
"num_tokens": 1559265.0,
|
|
"step": 680
|
|
},
|
|
{
|
|
"entropy": 6.936911153793335,
|
|
"epoch": 0.06580211335254563,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.000342,
|
|
"loss": 6.5209,
|
|
"mean_token_accuracy": 0.1260334573686123,
|
|
"num_tokens": 1569774.0,
|
|
"step": 685
|
|
},
|
|
{
|
|
"entropy": 6.816721200942993,
|
|
"epoch": 0.06628242074927954,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00034449999999999997,
|
|
"loss": 6.4525,
|
|
"mean_token_accuracy": 0.13374078422784805,
|
|
"num_tokens": 1579408.0,
|
|
"step": 690
|
|
},
|
|
{
|
|
"entropy": 6.881241273880005,
|
|
"epoch": 0.06676272814601344,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.000347,
|
|
"loss": 6.4841,
|
|
"mean_token_accuracy": 0.13311079293489456,
|
|
"num_tokens": 1591849.0,
|
|
"step": 695
|
|
},
|
|
{
|
|
"entropy": 6.893535804748535,
|
|
"epoch": 0.06724303554274735,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0003495,
|
|
"loss": 6.5399,
|
|
"mean_token_accuracy": 0.1287438191473484,
|
|
"num_tokens": 1603269.0,
|
|
"step": 700
|
|
},
|
|
{
|
|
"entropy": 6.999371290206909,
|
|
"epoch": 0.06772334293948126,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.000352,
|
|
"loss": 6.579,
|
|
"mean_token_accuracy": 0.12688603401184081,
|
|
"num_tokens": 1613639.0,
|
|
"step": 705
|
|
},
|
|
{
|
|
"entropy": 6.96681170463562,
|
|
"epoch": 0.06820365033621517,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0003545,
|
|
"loss": 6.6065,
|
|
"mean_token_accuracy": 0.1259676620364189,
|
|
"num_tokens": 1625393.0,
|
|
"step": 710
|
|
},
|
|
{
|
|
"entropy": 6.8337006092071535,
|
|
"epoch": 0.0686839577329491,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000357,
|
|
"loss": 6.4307,
|
|
"mean_token_accuracy": 0.1348931148648262,
|
|
"num_tokens": 1636355.0,
|
|
"step": 715
|
|
},
|
|
{
|
|
"entropy": 6.902727127075195,
|
|
"epoch": 0.069164265129683,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0003595,
|
|
"loss": 6.4784,
|
|
"mean_token_accuracy": 0.13106829673051834,
|
|
"num_tokens": 1646157.0,
|
|
"step": 720
|
|
},
|
|
{
|
|
"entropy": 6.7788458347320555,
|
|
"epoch": 0.06964457252641691,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000362,
|
|
"loss": 6.4699,
|
|
"mean_token_accuracy": 0.12550933212041854,
|
|
"num_tokens": 1657827.0,
|
|
"step": 725
|
|
},
|
|
{
|
|
"entropy": 6.847135925292969,
|
|
"epoch": 0.07012487992315082,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0003645,
|
|
"loss": 6.5532,
|
|
"mean_token_accuracy": 0.13552703633904456,
|
|
"num_tokens": 1669023.0,
|
|
"step": 730
|
|
},
|
|
{
|
|
"entropy": 6.893656158447266,
|
|
"epoch": 0.07060518731988473,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.000367,
|
|
"loss": 6.4955,
|
|
"mean_token_accuracy": 0.12944890484213828,
|
|
"num_tokens": 1680048.0,
|
|
"step": 735
|
|
},
|
|
{
|
|
"entropy": 6.9871117115020756,
|
|
"epoch": 0.07108549471661864,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0003695,
|
|
"loss": 6.6982,
|
|
"mean_token_accuracy": 0.11849347949028015,
|
|
"num_tokens": 1690907.0,
|
|
"step": 740
|
|
},
|
|
{
|
|
"entropy": 6.907092571258545,
|
|
"epoch": 0.07156580211335255,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.000372,
|
|
"loss": 6.525,
|
|
"mean_token_accuracy": 0.13299438506364822,
|
|
"num_tokens": 1702337.0,
|
|
"step": 745
|
|
},
|
|
{
|
|
"entropy": 6.883594512939453,
|
|
"epoch": 0.07204610951008646,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0003745,
|
|
"loss": 6.4486,
|
|
"mean_token_accuracy": 0.1341588594019413,
|
|
"num_tokens": 1713242.0,
|
|
"step": 750
|
|
},
|
|
{
|
|
"entropy": 6.749587869644165,
|
|
"epoch": 0.07252641690682037,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.000377,
|
|
"loss": 6.4226,
|
|
"mean_token_accuracy": 0.13001055493950844,
|
|
"num_tokens": 1724939.0,
|
|
"step": 755
|
|
},
|
|
{
|
|
"entropy": 6.8215819835662845,
|
|
"epoch": 0.07300672430355427,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0003795,
|
|
"loss": 6.3946,
|
|
"mean_token_accuracy": 0.1426876053214073,
|
|
"num_tokens": 1737311.0,
|
|
"step": 760
|
|
},
|
|
{
|
|
"entropy": 6.9048539161682125,
|
|
"epoch": 0.07348703170028818,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.000382,
|
|
"loss": 6.5289,
|
|
"mean_token_accuracy": 0.13060924485325814,
|
|
"num_tokens": 1749528.0,
|
|
"step": 765
|
|
},
|
|
{
|
|
"entropy": 6.729816436767578,
|
|
"epoch": 0.07396733909702209,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0003845,
|
|
"loss": 6.3903,
|
|
"mean_token_accuracy": 0.13687298968434333,
|
|
"num_tokens": 1760304.0,
|
|
"step": 770
|
|
},
|
|
{
|
|
"entropy": 6.770515632629395,
|
|
"epoch": 0.074447646493756,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00038700000000000003,
|
|
"loss": 6.3784,
|
|
"mean_token_accuracy": 0.13586725369095803,
|
|
"num_tokens": 1772014.0,
|
|
"step": 775
|
|
},
|
|
{
|
|
"entropy": 6.735719966888428,
|
|
"epoch": 0.07492795389048991,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00038950000000000003,
|
|
"loss": 6.4403,
|
|
"mean_token_accuracy": 0.13041759729385377,
|
|
"num_tokens": 1784585.0,
|
|
"step": 780
|
|
},
|
|
{
|
|
"entropy": 6.807892465591431,
|
|
"epoch": 0.07540826128722382,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00039200000000000004,
|
|
"loss": 6.3763,
|
|
"mean_token_accuracy": 0.1385021425783634,
|
|
"num_tokens": 1795246.0,
|
|
"step": 785
|
|
},
|
|
{
|
|
"entropy": 6.708891773223877,
|
|
"epoch": 0.07588856868395773,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.00039450000000000005,
|
|
"loss": 6.3674,
|
|
"mean_token_accuracy": 0.13637370616197586,
|
|
"num_tokens": 1806826.0,
|
|
"step": 790
|
|
},
|
|
{
|
|
"entropy": 6.739760875701904,
|
|
"epoch": 0.07636887608069164,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00039700000000000005,
|
|
"loss": 6.4892,
|
|
"mean_token_accuracy": 0.13308436870574952,
|
|
"num_tokens": 1818766.0,
|
|
"step": 795
|
|
},
|
|
{
|
|
"entropy": 6.768296575546264,
|
|
"epoch": 0.07684918347742556,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0003995,
|
|
"loss": 6.3435,
|
|
"mean_token_accuracy": 0.141699942946434,
|
|
"num_tokens": 1830824.0,
|
|
"step": 800
|
|
},
|
|
{
|
|
"entropy": 6.714781379699707,
|
|
"epoch": 0.07732949087415947,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000402,
|
|
"loss": 6.4306,
|
|
"mean_token_accuracy": 0.13212079629302026,
|
|
"num_tokens": 1841792.0,
|
|
"step": 805
|
|
},
|
|
{
|
|
"entropy": 6.706526756286621,
|
|
"epoch": 0.07780979827089338,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004045,
|
|
"loss": 6.3676,
|
|
"mean_token_accuracy": 0.13363081067800522,
|
|
"num_tokens": 1854683.0,
|
|
"step": 810
|
|
},
|
|
{
|
|
"entropy": 6.775065326690674,
|
|
"epoch": 0.07829010566762729,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00040699999999999997,
|
|
"loss": 6.4657,
|
|
"mean_token_accuracy": 0.13291899263858795,
|
|
"num_tokens": 1865826.0,
|
|
"step": 815
|
|
},
|
|
{
|
|
"entropy": 6.768963766098023,
|
|
"epoch": 0.0787704130643612,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004095,
|
|
"loss": 6.4149,
|
|
"mean_token_accuracy": 0.13940379321575164,
|
|
"num_tokens": 1876759.0,
|
|
"step": 820
|
|
},
|
|
{
|
|
"entropy": 6.710623407363892,
|
|
"epoch": 0.0792507204610951,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000412,
|
|
"loss": 6.4535,
|
|
"mean_token_accuracy": 0.1341131992638111,
|
|
"num_tokens": 1888013.0,
|
|
"step": 825
|
|
},
|
|
{
|
|
"entropy": 6.827510213851928,
|
|
"epoch": 0.07973102785782901,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004145,
|
|
"loss": 6.4581,
|
|
"mean_token_accuracy": 0.1362846978008747,
|
|
"num_tokens": 1898964.0,
|
|
"step": 830
|
|
},
|
|
{
|
|
"entropy": 6.655255270004273,
|
|
"epoch": 0.08021133525456292,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.000417,
|
|
"loss": 6.3854,
|
|
"mean_token_accuracy": 0.13690235167741777,
|
|
"num_tokens": 1909728.0,
|
|
"step": 835
|
|
},
|
|
{
|
|
"entropy": 6.653443908691406,
|
|
"epoch": 0.08069164265129683,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004195,
|
|
"loss": 6.3046,
|
|
"mean_token_accuracy": 0.14418013766407967,
|
|
"num_tokens": 1919895.0,
|
|
"step": 840
|
|
},
|
|
{
|
|
"entropy": 6.61823296546936,
|
|
"epoch": 0.08117195004803074,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000422,
|
|
"loss": 6.2275,
|
|
"mean_token_accuracy": 0.14545366540551186,
|
|
"num_tokens": 1930839.0,
|
|
"step": 845
|
|
},
|
|
{
|
|
"entropy": 6.723414564132691,
|
|
"epoch": 0.08165225744476465,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004245,
|
|
"loss": 6.4191,
|
|
"mean_token_accuracy": 0.14012102857232095,
|
|
"num_tokens": 1942605.0,
|
|
"step": 850
|
|
},
|
|
{
|
|
"entropy": 6.665984439849853,
|
|
"epoch": 0.08213256484149856,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000427,
|
|
"loss": 6.4117,
|
|
"mean_token_accuracy": 0.13332209810614587,
|
|
"num_tokens": 1954863.0,
|
|
"step": 855
|
|
},
|
|
{
|
|
"entropy": 6.725205516815185,
|
|
"epoch": 0.08261287223823247,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004295,
|
|
"loss": 6.4879,
|
|
"mean_token_accuracy": 0.1358294278383255,
|
|
"num_tokens": 1966088.0,
|
|
"step": 860
|
|
},
|
|
{
|
|
"entropy": 6.663434267044067,
|
|
"epoch": 0.08309317963496637,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.000432,
|
|
"loss": 6.3286,
|
|
"mean_token_accuracy": 0.13870726078748702,
|
|
"num_tokens": 1978081.0,
|
|
"step": 865
|
|
},
|
|
{
|
|
"entropy": 6.728060007095337,
|
|
"epoch": 0.08357348703170028,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004345,
|
|
"loss": 6.3965,
|
|
"mean_token_accuracy": 0.12974184826016427,
|
|
"num_tokens": 1991212.0,
|
|
"step": 870
|
|
},
|
|
{
|
|
"entropy": 6.6904360294342045,
|
|
"epoch": 0.08405379442843419,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.000437,
|
|
"loss": 6.3822,
|
|
"mean_token_accuracy": 0.13286416828632355,
|
|
"num_tokens": 2002074.0,
|
|
"step": 875
|
|
},
|
|
{
|
|
"entropy": 6.6402044773101805,
|
|
"epoch": 0.0845341018251681,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004395,
|
|
"loss": 6.2916,
|
|
"mean_token_accuracy": 0.14489293247461318,
|
|
"num_tokens": 2013039.0,
|
|
"step": 880
|
|
},
|
|
{
|
|
"entropy": 6.650302171707153,
|
|
"epoch": 0.08501440922190202,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000442,
|
|
"loss": 6.4218,
|
|
"mean_token_accuracy": 0.13508904427289964,
|
|
"num_tokens": 2024744.0,
|
|
"step": 885
|
|
},
|
|
{
|
|
"entropy": 6.657005834579468,
|
|
"epoch": 0.08549471661863593,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004445,
|
|
"loss": 6.2951,
|
|
"mean_token_accuracy": 0.144847309589386,
|
|
"num_tokens": 2035587.0,
|
|
"step": 890
|
|
},
|
|
{
|
|
"entropy": 6.607360124588013,
|
|
"epoch": 0.08597502401536984,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000447,
|
|
"loss": 6.3681,
|
|
"mean_token_accuracy": 0.13551491349935532,
|
|
"num_tokens": 2047924.0,
|
|
"step": 895
|
|
},
|
|
{
|
|
"entropy": 6.6262932300567625,
|
|
"epoch": 0.08645533141210375,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00044950000000000003,
|
|
"loss": 6.3086,
|
|
"mean_token_accuracy": 0.14029427096247674,
|
|
"num_tokens": 2060161.0,
|
|
"step": 900
|
|
},
|
|
{
|
|
"entropy": 6.626390981674194,
|
|
"epoch": 0.08693563880883766,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00045200000000000004,
|
|
"loss": 6.3231,
|
|
"mean_token_accuracy": 0.14045732319355012,
|
|
"num_tokens": 2071674.0,
|
|
"step": 905
|
|
},
|
|
{
|
|
"entropy": 6.669071340560913,
|
|
"epoch": 0.08741594620557157,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00045450000000000004,
|
|
"loss": 6.4579,
|
|
"mean_token_accuracy": 0.13296820148825644,
|
|
"num_tokens": 2084025.0,
|
|
"step": 910
|
|
},
|
|
{
|
|
"entropy": 6.6538848876953125,
|
|
"epoch": 0.08789625360230548,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00045700000000000005,
|
|
"loss": 6.3756,
|
|
"mean_token_accuracy": 0.14029246047139168,
|
|
"num_tokens": 2094501.0,
|
|
"step": 915
|
|
},
|
|
{
|
|
"entropy": 6.681252670288086,
|
|
"epoch": 0.08837656099903939,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00045950000000000006,
|
|
"loss": 6.3749,
|
|
"mean_token_accuracy": 0.14268773496150972,
|
|
"num_tokens": 2106207.0,
|
|
"step": 920
|
|
},
|
|
{
|
|
"entropy": 6.6069988250732425,
|
|
"epoch": 0.0888568683957733,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.000462,
|
|
"loss": 6.2643,
|
|
"mean_token_accuracy": 0.14611646607518197,
|
|
"num_tokens": 2116879.0,
|
|
"step": 925
|
|
},
|
|
{
|
|
"entropy": 6.578690099716186,
|
|
"epoch": 0.0893371757925072,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004645,
|
|
"loss": 6.3318,
|
|
"mean_token_accuracy": 0.13842730224132538,
|
|
"num_tokens": 2128884.0,
|
|
"step": 930
|
|
},
|
|
{
|
|
"entropy": 6.4773077964782715,
|
|
"epoch": 0.08981748318924111,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000467,
|
|
"loss": 6.2839,
|
|
"mean_token_accuracy": 0.13629047125577926,
|
|
"num_tokens": 2140810.0,
|
|
"step": 935
|
|
},
|
|
{
|
|
"entropy": 6.670573139190674,
|
|
"epoch": 0.09029779058597502,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004695,
|
|
"loss": 6.3424,
|
|
"mean_token_accuracy": 0.13401698023080827,
|
|
"num_tokens": 2152312.0,
|
|
"step": 940
|
|
},
|
|
{
|
|
"entropy": 6.51163682937622,
|
|
"epoch": 0.09077809798270893,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000472,
|
|
"loss": 6.2788,
|
|
"mean_token_accuracy": 0.136185372620821,
|
|
"num_tokens": 2164408.0,
|
|
"step": 945
|
|
},
|
|
{
|
|
"entropy": 6.558056449890136,
|
|
"epoch": 0.09125840537944284,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004745,
|
|
"loss": 6.2898,
|
|
"mean_token_accuracy": 0.1440206691622734,
|
|
"num_tokens": 2176050.0,
|
|
"step": 950
|
|
},
|
|
{
|
|
"entropy": 6.531415700912476,
|
|
"epoch": 0.09173871277617675,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000477,
|
|
"loss": 6.1747,
|
|
"mean_token_accuracy": 0.14442746862769126,
|
|
"num_tokens": 2187354.0,
|
|
"step": 955
|
|
},
|
|
{
|
|
"entropy": 6.446061897277832,
|
|
"epoch": 0.09221902017291066,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004795,
|
|
"loss": 6.1956,
|
|
"mean_token_accuracy": 0.14385264068841935,
|
|
"num_tokens": 2198686.0,
|
|
"step": 960
|
|
},
|
|
{
|
|
"entropy": 6.423680925369263,
|
|
"epoch": 0.09269932756964457,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.000482,
|
|
"loss": 6.2228,
|
|
"mean_token_accuracy": 0.14219090715050697,
|
|
"num_tokens": 2209780.0,
|
|
"step": 965
|
|
},
|
|
{
|
|
"entropy": 6.576705598831177,
|
|
"epoch": 0.09317963496637849,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004845,
|
|
"loss": 6.3136,
|
|
"mean_token_accuracy": 0.14841534793376923,
|
|
"num_tokens": 2221760.0,
|
|
"step": 970
|
|
},
|
|
{
|
|
"entropy": 6.538150453567505,
|
|
"epoch": 0.0936599423631124,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000487,
|
|
"loss": 6.3321,
|
|
"mean_token_accuracy": 0.14067101255059242,
|
|
"num_tokens": 2233767.0,
|
|
"step": 975
|
|
},
|
|
{
|
|
"entropy": 6.526997327804565,
|
|
"epoch": 0.0941402497598463,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004895,
|
|
"loss": 6.2696,
|
|
"mean_token_accuracy": 0.13998018503189086,
|
|
"num_tokens": 2244841.0,
|
|
"step": 980
|
|
},
|
|
{
|
|
"entropy": 6.529129076004028,
|
|
"epoch": 0.09462055715658022,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000492,
|
|
"loss": 6.1252,
|
|
"mean_token_accuracy": 0.14948576986789702,
|
|
"num_tokens": 2255620.0,
|
|
"step": 985
|
|
},
|
|
{
|
|
"entropy": 6.469129943847657,
|
|
"epoch": 0.09510086455331412,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004945,
|
|
"loss": 6.3184,
|
|
"mean_token_accuracy": 0.14613131657242776,
|
|
"num_tokens": 2266345.0,
|
|
"step": 990
|
|
},
|
|
{
|
|
"entropy": 6.5079692840576175,
|
|
"epoch": 0.09558117195004803,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.000497,
|
|
"loss": 6.2527,
|
|
"mean_token_accuracy": 0.1458457499742508,
|
|
"num_tokens": 2277190.0,
|
|
"step": 995
|
|
},
|
|
{
|
|
"entropy": 6.46534948348999,
|
|
"epoch": 0.09606147934678194,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004995,
|
|
"loss": 6.1264,
|
|
"mean_token_accuracy": 0.15072371661663056,
|
|
"num_tokens": 2288241.0,
|
|
"step": 1000
|
|
},
|
|
{
|
|
"entropy": 6.495367813110351,
|
|
"epoch": 0.09654178674351585,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999999983283737,
|
|
"loss": 6.2644,
|
|
"mean_token_accuracy": 0.1425079435110092,
|
|
"num_tokens": 2301092.0,
|
|
"step": 1005
|
|
},
|
|
{
|
|
"entropy": 6.48754186630249,
|
|
"epoch": 0.09702209414024976,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004999999915373924,
|
|
"loss": 6.1828,
|
|
"mean_token_accuracy": 0.14111206606030463,
|
|
"num_tokens": 2313622.0,
|
|
"step": 1010
|
|
},
|
|
{
|
|
"entropy": 6.343118476867676,
|
|
"epoch": 0.09750240153698367,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004999999795225793,
|
|
"loss": 6.1425,
|
|
"mean_token_accuracy": 0.14880686104297638,
|
|
"num_tokens": 2325699.0,
|
|
"step": 1015
|
|
},
|
|
{
|
|
"entropy": 6.502762937545777,
|
|
"epoch": 0.09798270893371758,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999999622839347,
|
|
"loss": 6.2125,
|
|
"mean_token_accuracy": 0.1470236748456955,
|
|
"num_tokens": 2337816.0,
|
|
"step": 1020
|
|
},
|
|
{
|
|
"entropy": 6.620756721496582,
|
|
"epoch": 0.09846301633045149,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004999999398214593,
|
|
"loss": 6.3494,
|
|
"mean_token_accuracy": 0.1372337594628334,
|
|
"num_tokens": 2348793.0,
|
|
"step": 1025
|
|
},
|
|
{
|
|
"entropy": 6.463247442245484,
|
|
"epoch": 0.0989433237271854,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999999121351532,
|
|
"loss": 6.2452,
|
|
"mean_token_accuracy": 0.14675871282815933,
|
|
"num_tokens": 2360209.0,
|
|
"step": 1030
|
|
},
|
|
{
|
|
"entropy": 6.566287660598755,
|
|
"epoch": 0.0994236311239193,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004999998792250173,
|
|
"loss": 6.2558,
|
|
"mean_token_accuracy": 0.14142224341630935,
|
|
"num_tokens": 2370597.0,
|
|
"step": 1035
|
|
},
|
|
{
|
|
"entropy": 6.506043529510498,
|
|
"epoch": 0.09990393852065321,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004999998410910524,
|
|
"loss": 6.2907,
|
|
"mean_token_accuracy": 0.14004258513450624,
|
|
"num_tokens": 2381466.0,
|
|
"step": 1040
|
|
},
|
|
{
|
|
"entropy": 6.63688383102417,
|
|
"epoch": 0.10038424591738712,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004999997977332592,
|
|
"loss": 6.3923,
|
|
"mean_token_accuracy": 0.1357167035341263,
|
|
"num_tokens": 2394507.0,
|
|
"step": 1045
|
|
},
|
|
{
|
|
"entropy": 6.429609298706055,
|
|
"epoch": 0.10086455331412104,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004999997491516389,
|
|
"loss": 6.2382,
|
|
"mean_token_accuracy": 0.14680789411067963,
|
|
"num_tokens": 2406367.0,
|
|
"step": 1050
|
|
},
|
|
{
|
|
"entropy": 6.439948606491089,
|
|
"epoch": 0.10134486071085495,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004999996953461925,
|
|
"loss": 6.2089,
|
|
"mean_token_accuracy": 0.1446738436818123,
|
|
"num_tokens": 2416962.0,
|
|
"step": 1055
|
|
},
|
|
{
|
|
"entropy": 6.582912969589233,
|
|
"epoch": 0.10182516810758886,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004999996363169212,
|
|
"loss": 6.2643,
|
|
"mean_token_accuracy": 0.13576384484767914,
|
|
"num_tokens": 2429441.0,
|
|
"step": 1060
|
|
},
|
|
{
|
|
"entropy": 6.374668884277344,
|
|
"epoch": 0.10230547550432277,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004999995720638266,
|
|
"loss": 6.1497,
|
|
"mean_token_accuracy": 0.1466536670923233,
|
|
"num_tokens": 2441360.0,
|
|
"step": 1065
|
|
},
|
|
{
|
|
"entropy": 6.437990379333496,
|
|
"epoch": 0.10278578290105668,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00049999950258691,
|
|
"loss": 6.1671,
|
|
"mean_token_accuracy": 0.14428199231624603,
|
|
"num_tokens": 2452928.0,
|
|
"step": 1070
|
|
},
|
|
{
|
|
"entropy": 6.362707710266113,
|
|
"epoch": 0.10326609029779059,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999994278861731,
|
|
"loss": 6.0991,
|
|
"mean_token_accuracy": 0.14837993010878564,
|
|
"num_tokens": 2464218.0,
|
|
"step": 1075
|
|
},
|
|
{
|
|
"entropy": 6.4544370651245115,
|
|
"epoch": 0.1037463976945245,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004999993479616175,
|
|
"loss": 6.183,
|
|
"mean_token_accuracy": 0.14867693558335304,
|
|
"num_tokens": 2475084.0,
|
|
"step": 1080
|
|
},
|
|
{
|
|
"entropy": 6.419835948944092,
|
|
"epoch": 0.1042267050912584,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004999992628132451,
|
|
"loss": 6.1854,
|
|
"mean_token_accuracy": 0.14430805891752244,
|
|
"num_tokens": 2486845.0,
|
|
"step": 1085
|
|
},
|
|
{
|
|
"entropy": 6.383818006515503,
|
|
"epoch": 0.10470701248799232,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004999991724410582,
|
|
"loss": 6.2687,
|
|
"mean_token_accuracy": 0.14187756553292274,
|
|
"num_tokens": 2498049.0,
|
|
"step": 1090
|
|
},
|
|
{
|
|
"entropy": 6.444679689407349,
|
|
"epoch": 0.10518731988472622,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999990768450583,
|
|
"loss": 6.1959,
|
|
"mean_token_accuracy": 0.14557206630706787,
|
|
"num_tokens": 2509511.0,
|
|
"step": 1095
|
|
},
|
|
{
|
|
"entropy": 6.473533487319946,
|
|
"epoch": 0.10566762728146013,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999989760252482,
|
|
"loss": 6.1493,
|
|
"mean_token_accuracy": 0.15422460734844207,
|
|
"num_tokens": 2521518.0,
|
|
"step": 1100
|
|
},
|
|
{
|
|
"entropy": 6.244095516204834,
|
|
"epoch": 0.10614793467819404,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999988699816299,
|
|
"loss": 5.9871,
|
|
"mean_token_accuracy": 0.1582183226943016,
|
|
"num_tokens": 2533141.0,
|
|
"step": 1105
|
|
},
|
|
{
|
|
"entropy": 6.313006591796875,
|
|
"epoch": 0.10662824207492795,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004999987587142058,
|
|
"loss": 5.987,
|
|
"mean_token_accuracy": 0.1536654606461525,
|
|
"num_tokens": 2542907.0,
|
|
"step": 1110
|
|
},
|
|
{
|
|
"entropy": 6.3394622802734375,
|
|
"epoch": 0.10710854947166186,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004999986422229789,
|
|
"loss": 6.1417,
|
|
"mean_token_accuracy": 0.14201202169060706,
|
|
"num_tokens": 2554497.0,
|
|
"step": 1115
|
|
},
|
|
{
|
|
"entropy": 6.543412351608277,
|
|
"epoch": 0.10758885686839577,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999985205079514,
|
|
"loss": 6.2688,
|
|
"mean_token_accuracy": 0.14553593546152116,
|
|
"num_tokens": 2567035.0,
|
|
"step": 1120
|
|
},
|
|
{
|
|
"entropy": 6.282679748535156,
|
|
"epoch": 0.10806916426512968,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004999983935691265,
|
|
"loss": 6.0562,
|
|
"mean_token_accuracy": 0.15392716675996782,
|
|
"num_tokens": 2578003.0,
|
|
"step": 1125
|
|
},
|
|
{
|
|
"entropy": 6.480337524414063,
|
|
"epoch": 0.10854947166186359,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000499998261406507,
|
|
"loss": 6.3434,
|
|
"mean_token_accuracy": 0.1433580659329891,
|
|
"num_tokens": 2590272.0,
|
|
"step": 1130
|
|
},
|
|
{
|
|
"entropy": 6.362969541549683,
|
|
"epoch": 0.10902977905859751,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999981240200958,
|
|
"loss": 6.1541,
|
|
"mean_token_accuracy": 0.145244736969471,
|
|
"num_tokens": 2602874.0,
|
|
"step": 1135
|
|
},
|
|
{
|
|
"entropy": 6.355509281158447,
|
|
"epoch": 0.10951008645533142,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004999979814098966,
|
|
"loss": 6.1054,
|
|
"mean_token_accuracy": 0.1554892733693123,
|
|
"num_tokens": 2613835.0,
|
|
"step": 1140
|
|
},
|
|
{
|
|
"entropy": 6.463612365722656,
|
|
"epoch": 0.10999039385206533,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999978335759121,
|
|
"loss": 6.238,
|
|
"mean_token_accuracy": 0.1424919068813324,
|
|
"num_tokens": 2624986.0,
|
|
"step": 1145
|
|
},
|
|
{
|
|
"entropy": 6.391502523422242,
|
|
"epoch": 0.11047070124879924,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999976805181461,
|
|
"loss": 6.2362,
|
|
"mean_token_accuracy": 0.14005767554044724,
|
|
"num_tokens": 2637654.0,
|
|
"step": 1150
|
|
},
|
|
{
|
|
"entropy": 6.405415058135986,
|
|
"epoch": 0.11095100864553314,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000499997522236602,
|
|
"loss": 6.1399,
|
|
"mean_token_accuracy": 0.15252109467983246,
|
|
"num_tokens": 2648947.0,
|
|
"step": 1155
|
|
},
|
|
{
|
|
"entropy": 6.3985276222229,
|
|
"epoch": 0.11143131604226705,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999973587312837,
|
|
"loss": 6.1239,
|
|
"mean_token_accuracy": 0.14815355390310286,
|
|
"num_tokens": 2659573.0,
|
|
"step": 1160
|
|
},
|
|
{
|
|
"entropy": 6.249864339828491,
|
|
"epoch": 0.11191162343900096,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999971900021947,
|
|
"loss": 6.0978,
|
|
"mean_token_accuracy": 0.1548936977982521,
|
|
"num_tokens": 2671491.0,
|
|
"step": 1165
|
|
},
|
|
{
|
|
"entropy": 6.381734895706177,
|
|
"epoch": 0.11239193083573487,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999970160493391,
|
|
"loss": 6.0828,
|
|
"mean_token_accuracy": 0.1447075366973877,
|
|
"num_tokens": 2682705.0,
|
|
"step": 1170
|
|
},
|
|
{
|
|
"entropy": 6.272091722488403,
|
|
"epoch": 0.11287223823246878,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999968368727209,
|
|
"loss": 6.0287,
|
|
"mean_token_accuracy": 0.14921507537364959,
|
|
"num_tokens": 2693539.0,
|
|
"step": 1175
|
|
},
|
|
{
|
|
"entropy": 6.254890108108521,
|
|
"epoch": 0.11335254562920269,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999966524723442,
|
|
"loss": 6.075,
|
|
"mean_token_accuracy": 0.15476031005382537,
|
|
"num_tokens": 2705403.0,
|
|
"step": 1180
|
|
},
|
|
{
|
|
"entropy": 6.456190967559815,
|
|
"epoch": 0.1138328530259366,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004999964628482135,
|
|
"loss": 6.1955,
|
|
"mean_token_accuracy": 0.1451671041548252,
|
|
"num_tokens": 2717320.0,
|
|
"step": 1185
|
|
},
|
|
{
|
|
"entropy": 6.350939464569092,
|
|
"epoch": 0.1143131604226705,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999962680003328,
|
|
"loss": 6.1526,
|
|
"mean_token_accuracy": 0.1435933716595173,
|
|
"num_tokens": 2730056.0,
|
|
"step": 1190
|
|
},
|
|
{
|
|
"entropy": 6.3369707584381105,
|
|
"epoch": 0.11479346781940442,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000499996067928707,
|
|
"loss": 6.0253,
|
|
"mean_token_accuracy": 0.15263447314500808,
|
|
"num_tokens": 2741399.0,
|
|
"step": 1195
|
|
},
|
|
{
|
|
"entropy": 6.4518022537231445,
|
|
"epoch": 0.11527377521613832,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004999958626333406,
|
|
"loss": 6.2564,
|
|
"mean_token_accuracy": 0.1389774426817894,
|
|
"num_tokens": 2752277.0,
|
|
"step": 1200
|
|
},
|
|
{
|
|
"entropy": 6.364963531494141,
|
|
"epoch": 0.11575408261287223,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004999956521142383,
|
|
"loss": 6.134,
|
|
"mean_token_accuracy": 0.14522297084331512,
|
|
"num_tokens": 2763172.0,
|
|
"step": 1205
|
|
},
|
|
{
|
|
"entropy": 6.406414270401001,
|
|
"epoch": 0.11623439000960614,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999954363714051,
|
|
"loss": 6.1445,
|
|
"mean_token_accuracy": 0.15052591264247894,
|
|
"num_tokens": 2775096.0,
|
|
"step": 1210
|
|
},
|
|
{
|
|
"entropy": 6.3844269752502445,
|
|
"epoch": 0.11671469740634005,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999952154048459,
|
|
"loss": 6.221,
|
|
"mean_token_accuracy": 0.1505927786231041,
|
|
"num_tokens": 2786007.0,
|
|
"step": 1215
|
|
},
|
|
{
|
|
"entropy": 6.287612104415894,
|
|
"epoch": 0.11719500480307397,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000499994989214566,
|
|
"loss": 6.0292,
|
|
"mean_token_accuracy": 0.15772099494934083,
|
|
"num_tokens": 2797265.0,
|
|
"step": 1220
|
|
},
|
|
{
|
|
"entropy": 6.365857458114624,
|
|
"epoch": 0.11767531219980788,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999947578005705,
|
|
"loss": 6.1966,
|
|
"mean_token_accuracy": 0.14764621183276178,
|
|
"num_tokens": 2809427.0,
|
|
"step": 1225
|
|
},
|
|
{
|
|
"entropy": 6.3595850467681885,
|
|
"epoch": 0.11815561959654179,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999945211628648,
|
|
"loss": 6.1154,
|
|
"mean_token_accuracy": 0.15281978696584703,
|
|
"num_tokens": 2822880.0,
|
|
"step": 1230
|
|
},
|
|
{
|
|
"entropy": 6.394454145431519,
|
|
"epoch": 0.1186359269932757,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999942793014544,
|
|
"loss": 6.201,
|
|
"mean_token_accuracy": 0.14849669709801674,
|
|
"num_tokens": 2834760.0,
|
|
"step": 1235
|
|
},
|
|
{
|
|
"entropy": 6.325704431533813,
|
|
"epoch": 0.11911623439000961,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000499994032216345,
|
|
"loss": 6.1413,
|
|
"mean_token_accuracy": 0.14735834896564484,
|
|
"num_tokens": 2846517.0,
|
|
"step": 1240
|
|
},
|
|
{
|
|
"entropy": 6.302383375167847,
|
|
"epoch": 0.11959654178674352,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999937799075422,
|
|
"loss": 6.0306,
|
|
"mean_token_accuracy": 0.15673189759254455,
|
|
"num_tokens": 2857280.0,
|
|
"step": 1245
|
|
},
|
|
{
|
|
"entropy": 6.341720819473267,
|
|
"epoch": 0.12007684918347743,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000499993522375052,
|
|
"loss": 6.0833,
|
|
"mean_token_accuracy": 0.15285103321075438,
|
|
"num_tokens": 2869735.0,
|
|
"step": 1250
|
|
},
|
|
{
|
|
"entropy": 6.2822376728057865,
|
|
"epoch": 0.12055715658021134,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999932596188802,
|
|
"loss": 6.0779,
|
|
"mean_token_accuracy": 0.15265348553657532,
|
|
"num_tokens": 2881681.0,
|
|
"step": 1255
|
|
},
|
|
{
|
|
"entropy": 6.21174373626709,
|
|
"epoch": 0.12103746397694524,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999929916390331,
|
|
"loss": 6.0949,
|
|
"mean_token_accuracy": 0.154794842004776,
|
|
"num_tokens": 2893828.0,
|
|
"step": 1260
|
|
},
|
|
{
|
|
"entropy": 6.129497814178467,
|
|
"epoch": 0.12151777137367915,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999927184355169,
|
|
"loss": 6.036,
|
|
"mean_token_accuracy": 0.1517324849963188,
|
|
"num_tokens": 2905804.0,
|
|
"step": 1265
|
|
},
|
|
{
|
|
"entropy": 6.52538423538208,
|
|
"epoch": 0.12199807877041306,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999924400083377,
|
|
"loss": 6.1836,
|
|
"mean_token_accuracy": 0.14400093555450438,
|
|
"num_tokens": 2918709.0,
|
|
"step": 1270
|
|
},
|
|
{
|
|
"entropy": 6.26390323638916,
|
|
"epoch": 0.12247838616714697,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999921563575022,
|
|
"loss": 6.0853,
|
|
"mean_token_accuracy": 0.1494814559817314,
|
|
"num_tokens": 2930589.0,
|
|
"step": 1275
|
|
},
|
|
{
|
|
"entropy": 6.3428949356079105,
|
|
"epoch": 0.12295869356388088,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999918674830169,
|
|
"loss": 6.15,
|
|
"mean_token_accuracy": 0.15355577766895295,
|
|
"num_tokens": 2940635.0,
|
|
"step": 1280
|
|
},
|
|
{
|
|
"entropy": 6.185381269454956,
|
|
"epoch": 0.12343900096061479,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999915733848886,
|
|
"loss": 6.0204,
|
|
"mean_token_accuracy": 0.15577883869409562,
|
|
"num_tokens": 2952731.0,
|
|
"step": 1285
|
|
},
|
|
{
|
|
"entropy": 6.257724475860596,
|
|
"epoch": 0.1239193083573487,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000499991274063124,
|
|
"loss": 6.0307,
|
|
"mean_token_accuracy": 0.15278594493865966,
|
|
"num_tokens": 2964544.0,
|
|
"step": 1290
|
|
},
|
|
{
|
|
"entropy": 6.300468444824219,
|
|
"epoch": 0.12439961575408261,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004999909695177301,
|
|
"loss": 5.9802,
|
|
"mean_token_accuracy": 0.15509692430496216,
|
|
"num_tokens": 2974996.0,
|
|
"step": 1295
|
|
},
|
|
{
|
|
"entropy": 6.149973678588867,
|
|
"epoch": 0.12487992315081652,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000499990659748714,
|
|
"loss": 5.9729,
|
|
"mean_token_accuracy": 0.15493070483207702,
|
|
"num_tokens": 2986496.0,
|
|
"step": 1300
|
|
},
|
|
{
|
|
"entropy": 6.232842063903808,
|
|
"epoch": 0.12536023054755044,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999903447560828,
|
|
"loss": 6.0612,
|
|
"mean_token_accuracy": 0.15265824794769287,
|
|
"num_tokens": 2997693.0,
|
|
"step": 1305
|
|
},
|
|
{
|
|
"entropy": 6.226562786102295,
|
|
"epoch": 0.12584053794428435,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999900245398439,
|
|
"loss": 6.0157,
|
|
"mean_token_accuracy": 0.15674570202827454,
|
|
"num_tokens": 3009155.0,
|
|
"step": 1310
|
|
},
|
|
{
|
|
"entropy": 6.221279764175415,
|
|
"epoch": 0.12632084534101826,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999896991000047,
|
|
"loss": 5.9339,
|
|
"mean_token_accuracy": 0.16307595893740653,
|
|
"num_tokens": 3020944.0,
|
|
"step": 1315
|
|
},
|
|
{
|
|
"entropy": 6.228196477890014,
|
|
"epoch": 0.12680115273775217,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999893684365729,
|
|
"loss": 5.9926,
|
|
"mean_token_accuracy": 0.15848468393087387,
|
|
"num_tokens": 3032893.0,
|
|
"step": 1320
|
|
},
|
|
{
|
|
"entropy": 6.234899044036865,
|
|
"epoch": 0.12728146013448607,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004999890325495559,
|
|
"loss": 6.0734,
|
|
"mean_token_accuracy": 0.14982036575675012,
|
|
"num_tokens": 3044937.0,
|
|
"step": 1325
|
|
},
|
|
{
|
|
"entropy": 6.239958381652832,
|
|
"epoch": 0.12776176753121998,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999886914389617,
|
|
"loss": 5.9763,
|
|
"mean_token_accuracy": 0.16002579778432846,
|
|
"num_tokens": 3056071.0,
|
|
"step": 1330
|
|
},
|
|
{
|
|
"entropy": 6.2782426357269285,
|
|
"epoch": 0.1282420749279539,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004999883451047981,
|
|
"loss": 6.1258,
|
|
"mean_token_accuracy": 0.15075602605938912,
|
|
"num_tokens": 3067724.0,
|
|
"step": 1335
|
|
},
|
|
{
|
|
"entropy": 6.279479598999023,
|
|
"epoch": 0.1287223823246878,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999879935470733,
|
|
"loss": 6.029,
|
|
"mean_token_accuracy": 0.159932242333889,
|
|
"num_tokens": 3080779.0,
|
|
"step": 1340
|
|
},
|
|
{
|
|
"entropy": 6.198295736312867,
|
|
"epoch": 0.1292026897214217,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999876367657954,
|
|
"loss": 6.0253,
|
|
"mean_token_accuracy": 0.15193908512592316,
|
|
"num_tokens": 3091991.0,
|
|
"step": 1345
|
|
},
|
|
{
|
|
"entropy": 6.165930318832397,
|
|
"epoch": 0.12968299711815562,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999872747609725,
|
|
"loss": 6.0053,
|
|
"mean_token_accuracy": 0.15580039322376252,
|
|
"num_tokens": 3103713.0,
|
|
"step": 1350
|
|
},
|
|
{
|
|
"entropy": 6.256294059753418,
|
|
"epoch": 0.13016330451488953,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999869075326132,
|
|
"loss": 6.0243,
|
|
"mean_token_accuracy": 0.15310140401124955,
|
|
"num_tokens": 3115891.0,
|
|
"step": 1355
|
|
},
|
|
{
|
|
"entropy": 6.100836944580078,
|
|
"epoch": 0.13064361191162344,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000499986535080726,
|
|
"loss": 5.8932,
|
|
"mean_token_accuracy": 0.16618788689374925,
|
|
"num_tokens": 3126223.0,
|
|
"step": 1360
|
|
},
|
|
{
|
|
"entropy": 6.277415800094604,
|
|
"epoch": 0.13112391930835735,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999861574053196,
|
|
"loss": 6.0803,
|
|
"mean_token_accuracy": 0.1464972734451294,
|
|
"num_tokens": 3137537.0,
|
|
"step": 1365
|
|
},
|
|
{
|
|
"entropy": 6.311663389205933,
|
|
"epoch": 0.13160422670509125,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999857745064027,
|
|
"loss": 6.0675,
|
|
"mean_token_accuracy": 0.15843178257346152,
|
|
"num_tokens": 3150126.0,
|
|
"step": 1370
|
|
},
|
|
{
|
|
"entropy": 6.187855768203735,
|
|
"epoch": 0.13208453410182516,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000499985386383984,
|
|
"loss": 6.0576,
|
|
"mean_token_accuracy": 0.15574488639831544,
|
|
"num_tokens": 3161684.0,
|
|
"step": 1375
|
|
},
|
|
{
|
|
"entropy": 6.19967212677002,
|
|
"epoch": 0.13256484149855907,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999849930380729,
|
|
"loss": 5.9453,
|
|
"mean_token_accuracy": 0.1588939517736435,
|
|
"num_tokens": 3172342.0,
|
|
"step": 1380
|
|
},
|
|
{
|
|
"entropy": 6.310555124282837,
|
|
"epoch": 0.13304514889529298,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999845944686781,
|
|
"loss": 6.0841,
|
|
"mean_token_accuracy": 0.15674352198839187,
|
|
"num_tokens": 3183681.0,
|
|
"step": 1385
|
|
},
|
|
{
|
|
"entropy": 6.053848028182983,
|
|
"epoch": 0.1335254562920269,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999841906758093,
|
|
"loss": 5.8837,
|
|
"mean_token_accuracy": 0.16934000104665756,
|
|
"num_tokens": 3194122.0,
|
|
"step": 1390
|
|
},
|
|
{
|
|
"entropy": 6.18535680770874,
|
|
"epoch": 0.1340057636887608,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999837816594757,
|
|
"loss": 5.9358,
|
|
"mean_token_accuracy": 0.15829690545797348,
|
|
"num_tokens": 3205719.0,
|
|
"step": 1395
|
|
},
|
|
{
|
|
"entropy": 6.125392961502075,
|
|
"epoch": 0.1344860710854947,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999833674196865,
|
|
"loss": 5.9729,
|
|
"mean_token_accuracy": 0.15530545860528946,
|
|
"num_tokens": 3216262.0,
|
|
"step": 1400
|
|
},
|
|
{
|
|
"entropy": 6.297972679138184,
|
|
"epoch": 0.13496637848222862,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004999829479564518,
|
|
"loss": 6.0252,
|
|
"mean_token_accuracy": 0.1493932545185089,
|
|
"num_tokens": 3228035.0,
|
|
"step": 1405
|
|
},
|
|
{
|
|
"entropy": 6.070080995559692,
|
|
"epoch": 0.13544668587896252,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000499982523269781,
|
|
"loss": 5.8804,
|
|
"mean_token_accuracy": 0.16375838965177536,
|
|
"num_tokens": 3239643.0,
|
|
"step": 1410
|
|
},
|
|
{
|
|
"entropy": 6.191074371337891,
|
|
"epoch": 0.13592699327569643,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999820933596842,
|
|
"loss": 5.9715,
|
|
"mean_token_accuracy": 0.16024953722953797,
|
|
"num_tokens": 3250293.0,
|
|
"step": 1415
|
|
},
|
|
{
|
|
"entropy": 6.235940551757812,
|
|
"epoch": 0.13640730067243034,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000499981658226171,
|
|
"loss": 6.0849,
|
|
"mean_token_accuracy": 0.14876422584056853,
|
|
"num_tokens": 3262448.0,
|
|
"step": 1420
|
|
},
|
|
{
|
|
"entropy": 6.09799861907959,
|
|
"epoch": 0.13688760806916425,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000499981217869252,
|
|
"loss": 5.9479,
|
|
"mean_token_accuracy": 0.16196773797273636,
|
|
"num_tokens": 3274041.0,
|
|
"step": 1425
|
|
},
|
|
{
|
|
"entropy": 6.258628892898559,
|
|
"epoch": 0.1373679154658982,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000499980772288937,
|
|
"loss": 5.9781,
|
|
"mean_token_accuracy": 0.15339865237474443,
|
|
"num_tokens": 3285063.0,
|
|
"step": 1430
|
|
},
|
|
{
|
|
"entropy": 6.194421911239624,
|
|
"epoch": 0.1378482228626321,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999803214852367,
|
|
"loss": 5.9904,
|
|
"mean_token_accuracy": 0.15928526520729064,
|
|
"num_tokens": 3297031.0,
|
|
"step": 1435
|
|
},
|
|
{
|
|
"entropy": 6.193781995773316,
|
|
"epoch": 0.138328530259366,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999798654581613,
|
|
"loss": 5.9831,
|
|
"mean_token_accuracy": 0.15303055197000504,
|
|
"num_tokens": 3308187.0,
|
|
"step": 1440
|
|
},
|
|
{
|
|
"entropy": 6.149940299987793,
|
|
"epoch": 0.13880883765609991,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999794042077214,
|
|
"loss": 5.9776,
|
|
"mean_token_accuracy": 0.15377987325191497,
|
|
"num_tokens": 3319439.0,
|
|
"step": 1445
|
|
},
|
|
{
|
|
"entropy": 6.193714046478272,
|
|
"epoch": 0.13928914505283382,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999789377339279,
|
|
"loss": 5.9825,
|
|
"mean_token_accuracy": 0.15619124472141266,
|
|
"num_tokens": 3331715.0,
|
|
"step": 1450
|
|
},
|
|
{
|
|
"entropy": 6.1586973667144775,
|
|
"epoch": 0.13976945244956773,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999784660367915,
|
|
"loss": 5.9445,
|
|
"mean_token_accuracy": 0.16621134728193282,
|
|
"num_tokens": 3342281.0,
|
|
"step": 1455
|
|
},
|
|
{
|
|
"entropy": 6.333666086196899,
|
|
"epoch": 0.14024975984630164,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004999779891163231,
|
|
"loss": 6.0767,
|
|
"mean_token_accuracy": 0.1537630721926689,
|
|
"num_tokens": 3353530.0,
|
|
"step": 1460
|
|
},
|
|
{
|
|
"entropy": 6.150418090820312,
|
|
"epoch": 0.14073006724303555,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999775069725339,
|
|
"loss": 6.0413,
|
|
"mean_token_accuracy": 0.14952244013547897,
|
|
"num_tokens": 3365083.0,
|
|
"step": 1465
|
|
},
|
|
{
|
|
"entropy": 6.237746095657348,
|
|
"epoch": 0.14121037463976946,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000499977019605435,
|
|
"loss": 5.994,
|
|
"mean_token_accuracy": 0.15313961654901503,
|
|
"num_tokens": 3378143.0,
|
|
"step": 1470
|
|
},
|
|
{
|
|
"entropy": 6.189295482635498,
|
|
"epoch": 0.14169068203650337,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004999765270150378,
|
|
"loss": 5.9751,
|
|
"mean_token_accuracy": 0.15560294240713118,
|
|
"num_tokens": 3388438.0,
|
|
"step": 1475
|
|
},
|
|
{
|
|
"entropy": 6.083598518371582,
|
|
"epoch": 0.14217098943323728,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999760292013536,
|
|
"loss": 5.9712,
|
|
"mean_token_accuracy": 0.1537217065691948,
|
|
"num_tokens": 3400150.0,
|
|
"step": 1480
|
|
},
|
|
{
|
|
"entropy": 6.116258144378662,
|
|
"epoch": 0.14265129682997119,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999755261643941,
|
|
"loss": 5.842,
|
|
"mean_token_accuracy": 0.1626240774989128,
|
|
"num_tokens": 3411073.0,
|
|
"step": 1485
|
|
},
|
|
{
|
|
"entropy": 6.100852298736572,
|
|
"epoch": 0.1431316042267051,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999750179041709,
|
|
"loss": 5.8908,
|
|
"mean_token_accuracy": 0.17015900164842607,
|
|
"num_tokens": 3422196.0,
|
|
"step": 1490
|
|
},
|
|
{
|
|
"entropy": 6.193173599243164,
|
|
"epoch": 0.143611911623439,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004999745044206959,
|
|
"loss": 5.9324,
|
|
"mean_token_accuracy": 0.15437426567077636,
|
|
"num_tokens": 3432568.0,
|
|
"step": 1495
|
|
},
|
|
{
|
|
"entropy": 6.133666181564331,
|
|
"epoch": 0.1440922190201729,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999739857139809,
|
|
"loss": 5.9461,
|
|
"mean_token_accuracy": 0.15741463452577592,
|
|
"num_tokens": 3444096.0,
|
|
"step": 1500
|
|
},
|
|
{
|
|
"entropy": 6.035371446609497,
|
|
"epoch": 0.14457252641690682,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000499973461784038,
|
|
"loss": 5.8437,
|
|
"mean_token_accuracy": 0.164261032640934,
|
|
"num_tokens": 3455502.0,
|
|
"step": 1505
|
|
},
|
|
{
|
|
"entropy": 6.17965931892395,
|
|
"epoch": 0.14505283381364073,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999729326308792,
|
|
"loss": 5.9825,
|
|
"mean_token_accuracy": 0.152863709628582,
|
|
"num_tokens": 3467753.0,
|
|
"step": 1510
|
|
},
|
|
{
|
|
"entropy": 6.079440689086914,
|
|
"epoch": 0.14553314121037464,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000499972398254517,
|
|
"loss": 5.8548,
|
|
"mean_token_accuracy": 0.16266588419675826,
|
|
"num_tokens": 3479206.0,
|
|
"step": 1515
|
|
},
|
|
{
|
|
"entropy": 6.087345123291016,
|
|
"epoch": 0.14601344860710855,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000499971858654964,
|
|
"loss": 5.8727,
|
|
"mean_token_accuracy": 0.16008733659982682,
|
|
"num_tokens": 3490914.0,
|
|
"step": 1520
|
|
},
|
|
{
|
|
"entropy": 6.117412471771241,
|
|
"epoch": 0.14649375600384246,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999713138322321,
|
|
"loss": 5.9381,
|
|
"mean_token_accuracy": 0.15474505573511124,
|
|
"num_tokens": 3502932.0,
|
|
"step": 1525
|
|
},
|
|
{
|
|
"entropy": 6.052666330337525,
|
|
"epoch": 0.14697406340057637,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999707637863346,
|
|
"loss": 5.8568,
|
|
"mean_token_accuracy": 0.16760103702545165,
|
|
"num_tokens": 3515071.0,
|
|
"step": 1530
|
|
},
|
|
{
|
|
"entropy": 6.197118139266967,
|
|
"epoch": 0.14745437079731027,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004999702085172838,
|
|
"loss": 5.9731,
|
|
"mean_token_accuracy": 0.15752421617507933,
|
|
"num_tokens": 3526845.0,
|
|
"step": 1535
|
|
},
|
|
{
|
|
"entropy": 6.107962656021118,
|
|
"epoch": 0.14793467819404418,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004999696480250929,
|
|
"loss": 5.97,
|
|
"mean_token_accuracy": 0.15250069200992583,
|
|
"num_tokens": 3538810.0,
|
|
"step": 1540
|
|
},
|
|
{
|
|
"entropy": 6.2200414657592775,
|
|
"epoch": 0.1484149855907781,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004999690823097747,
|
|
"loss": 5.9264,
|
|
"mean_token_accuracy": 0.16580826342105864,
|
|
"num_tokens": 3549570.0,
|
|
"step": 1545
|
|
},
|
|
{
|
|
"entropy": 5.904806661605835,
|
|
"epoch": 0.148895292987512,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999685113713426,
|
|
"loss": 5.8501,
|
|
"mean_token_accuracy": 0.16919772773981095,
|
|
"num_tokens": 3560937.0,
|
|
"step": 1550
|
|
},
|
|
{
|
|
"entropy": 6.123501825332641,
|
|
"epoch": 0.1493756003842459,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999679352098096,
|
|
"loss": 5.8894,
|
|
"mean_token_accuracy": 0.15619551986455918,
|
|
"num_tokens": 3573603.0,
|
|
"step": 1555
|
|
},
|
|
{
|
|
"entropy": 6.082352209091186,
|
|
"epoch": 0.14985590778097982,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999673538251891,
|
|
"loss": 5.9088,
|
|
"mean_token_accuracy": 0.1532599925994873,
|
|
"num_tokens": 3586034.0,
|
|
"step": 1560
|
|
},
|
|
{
|
|
"entropy": 6.018591833114624,
|
|
"epoch": 0.15033621517771373,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999667672174947,
|
|
"loss": 5.8289,
|
|
"mean_token_accuracy": 0.1625208377838135,
|
|
"num_tokens": 3597305.0,
|
|
"step": 1565
|
|
},
|
|
{
|
|
"entropy": 6.1929418563842775,
|
|
"epoch": 0.15081652257444764,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00049996617538674,
|
|
"loss": 5.9833,
|
|
"mean_token_accuracy": 0.14946810826659201,
|
|
"num_tokens": 3608758.0,
|
|
"step": 1570
|
|
},
|
|
{
|
|
"entropy": 6.1501671314239506,
|
|
"epoch": 0.15129682997118155,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999655783329386,
|
|
"loss": 5.9919,
|
|
"mean_token_accuracy": 0.15281759947538376,
|
|
"num_tokens": 3621508.0,
|
|
"step": 1575
|
|
},
|
|
{
|
|
"entropy": 6.159276962280273,
|
|
"epoch": 0.15177713736791545,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004999649760561046,
|
|
"loss": 5.9382,
|
|
"mean_token_accuracy": 0.16324293464422227,
|
|
"num_tokens": 3634826.0,
|
|
"step": 1580
|
|
},
|
|
{
|
|
"entropy": 5.917337799072266,
|
|
"epoch": 0.15225744476464936,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999643685562519,
|
|
"loss": 5.7775,
|
|
"mean_token_accuracy": 0.17960015386343003,
|
|
"num_tokens": 3646427.0,
|
|
"step": 1585
|
|
},
|
|
{
|
|
"entropy": 6.045775270462036,
|
|
"epoch": 0.15273775216138327,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999637558333945,
|
|
"loss": 5.9014,
|
|
"mean_token_accuracy": 0.16223143190145492,
|
|
"num_tokens": 3658157.0,
|
|
"step": 1590
|
|
},
|
|
{
|
|
"entropy": 6.132830429077148,
|
|
"epoch": 0.15321805955811718,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999631378875467,
|
|
"loss": 5.9486,
|
|
"mean_token_accuracy": 0.15801500529050827,
|
|
"num_tokens": 3670695.0,
|
|
"step": 1595
|
|
},
|
|
{
|
|
"entropy": 6.065447902679443,
|
|
"epoch": 0.15369836695485112,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999625147187228,
|
|
"loss": 5.8667,
|
|
"mean_token_accuracy": 0.1583435446023941,
|
|
"num_tokens": 3683379.0,
|
|
"step": 1600
|
|
},
|
|
{
|
|
"entropy": 6.047661972045899,
|
|
"epoch": 0.15417867435158503,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999618863269373,
|
|
"loss": 5.7623,
|
|
"mean_token_accuracy": 0.17143424898386,
|
|
"num_tokens": 3694411.0,
|
|
"step": 1605
|
|
},
|
|
{
|
|
"entropy": 5.992631816864014,
|
|
"epoch": 0.15465898174831894,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004999612527122049,
|
|
"loss": 5.8231,
|
|
"mean_token_accuracy": 0.1685330703854561,
|
|
"num_tokens": 3703833.0,
|
|
"step": 1610
|
|
},
|
|
{
|
|
"entropy": 6.119769525527954,
|
|
"epoch": 0.15513928914505284,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999606138745402,
|
|
"loss": 5.8962,
|
|
"mean_token_accuracy": 0.16868149489164352,
|
|
"num_tokens": 3714702.0,
|
|
"step": 1615
|
|
},
|
|
{
|
|
"entropy": 6.150318717956543,
|
|
"epoch": 0.15561959654178675,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999599698139581,
|
|
"loss": 5.9627,
|
|
"mean_token_accuracy": 0.16385385543107986,
|
|
"num_tokens": 3726000.0,
|
|
"step": 1620
|
|
},
|
|
{
|
|
"entropy": 6.108389234542846,
|
|
"epoch": 0.15609990393852066,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999593205304734,
|
|
"loss": 5.859,
|
|
"mean_token_accuracy": 0.15902963280677795,
|
|
"num_tokens": 3737681.0,
|
|
"step": 1625
|
|
},
|
|
{
|
|
"entropy": 6.1753983974456785,
|
|
"epoch": 0.15658021133525457,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999586660241012,
|
|
"loss": 5.9649,
|
|
"mean_token_accuracy": 0.15404864847660066,
|
|
"num_tokens": 3749477.0,
|
|
"step": 1630
|
|
},
|
|
{
|
|
"entropy": 6.151984453201294,
|
|
"epoch": 0.15706051873198848,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999580062948569,
|
|
"loss": 5.9426,
|
|
"mean_token_accuracy": 0.15559921264648438,
|
|
"num_tokens": 3759946.0,
|
|
"step": 1635
|
|
},
|
|
{
|
|
"entropy": 6.033643436431885,
|
|
"epoch": 0.1575408261287224,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999573413427556,
|
|
"loss": 5.8405,
|
|
"mean_token_accuracy": 0.160524982213974,
|
|
"num_tokens": 3770147.0,
|
|
"step": 1640
|
|
},
|
|
{
|
|
"entropy": 6.0757527351379395,
|
|
"epoch": 0.1580211335254563,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999566711678128,
|
|
"loss": 5.794,
|
|
"mean_token_accuracy": 0.16993406414985657,
|
|
"num_tokens": 3781028.0,
|
|
"step": 1645
|
|
},
|
|
{
|
|
"entropy": 6.029065990447998,
|
|
"epoch": 0.1585014409221902,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999559957700442,
|
|
"loss": 5.8655,
|
|
"mean_token_accuracy": 0.15539842694997788,
|
|
"num_tokens": 3792529.0,
|
|
"step": 1650
|
|
},
|
|
{
|
|
"entropy": 6.171193170547485,
|
|
"epoch": 0.15898174831892412,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999553151494653,
|
|
"loss": 5.9723,
|
|
"mean_token_accuracy": 0.16454491764307022,
|
|
"num_tokens": 3804630.0,
|
|
"step": 1655
|
|
},
|
|
{
|
|
"entropy": 5.867986536026001,
|
|
"epoch": 0.15946205571565802,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999546293060919,
|
|
"loss": 5.7366,
|
|
"mean_token_accuracy": 0.17225825041532516,
|
|
"num_tokens": 3815019.0,
|
|
"step": 1660
|
|
},
|
|
{
|
|
"entropy": 6.107065629959107,
|
|
"epoch": 0.15994236311239193,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00049995393823994,
|
|
"loss": 5.8429,
|
|
"mean_token_accuracy": 0.16143251210451126,
|
|
"num_tokens": 3825648.0,
|
|
"step": 1665
|
|
},
|
|
{
|
|
"entropy": 6.041478061676026,
|
|
"epoch": 0.16042267050912584,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999532419510255,
|
|
"loss": 5.8323,
|
|
"mean_token_accuracy": 0.16772198379039766,
|
|
"num_tokens": 3836779.0,
|
|
"step": 1670
|
|
},
|
|
{
|
|
"entropy": 5.989100790023803,
|
|
"epoch": 0.16090297790585975,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.000499952540439365,
|
|
"loss": 5.8595,
|
|
"mean_token_accuracy": 0.1596663162112236,
|
|
"num_tokens": 3848350.0,
|
|
"step": 1675
|
|
},
|
|
{
|
|
"entropy": 6.105287694931031,
|
|
"epoch": 0.16138328530259366,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999518337049743,
|
|
"loss": 5.8766,
|
|
"mean_token_accuracy": 0.16466120183467864,
|
|
"num_tokens": 3859792.0,
|
|
"step": 1680
|
|
},
|
|
{
|
|
"entropy": 6.038152456283569,
|
|
"epoch": 0.16186359269932757,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00049995112174787,
|
|
"loss": 5.8118,
|
|
"mean_token_accuracy": 0.1610649883747101,
|
|
"num_tokens": 3871539.0,
|
|
"step": 1685
|
|
},
|
|
{
|
|
"entropy": 5.94040699005127,
|
|
"epoch": 0.16234390009606148,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004999504045680687,
|
|
"loss": 5.8553,
|
|
"mean_token_accuracy": 0.165919728577137,
|
|
"num_tokens": 3885025.0,
|
|
"step": 1690
|
|
},
|
|
{
|
|
"entropy": 6.108747243881226,
|
|
"epoch": 0.1628242074927954,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999496821655869,
|
|
"loss": 5.9671,
|
|
"mean_token_accuracy": 0.15593098998069763,
|
|
"num_tokens": 3896519.0,
|
|
"step": 1695
|
|
},
|
|
{
|
|
"entropy": 6.010381031036377,
|
|
"epoch": 0.1633045148895293,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999489545404414,
|
|
"loss": 5.7259,
|
|
"mean_token_accuracy": 0.16787517666816712,
|
|
"num_tokens": 3907636.0,
|
|
"step": 1700
|
|
},
|
|
{
|
|
"entropy": 5.983977651596069,
|
|
"epoch": 0.1637848222862632,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999482216926493,
|
|
"loss": 5.8537,
|
|
"mean_token_accuracy": 0.16455249339342118,
|
|
"num_tokens": 3917746.0,
|
|
"step": 1705
|
|
},
|
|
{
|
|
"entropy": 6.00126838684082,
|
|
"epoch": 0.1642651296829971,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999474836222273,
|
|
"loss": 5.7735,
|
|
"mean_token_accuracy": 0.16910521686077118,
|
|
"num_tokens": 3928901.0,
|
|
"step": 1710
|
|
},
|
|
{
|
|
"entropy": 5.979851198196411,
|
|
"epoch": 0.16474543707973102,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999467403291928,
|
|
"loss": 5.8926,
|
|
"mean_token_accuracy": 0.16778817474842073,
|
|
"num_tokens": 3940094.0,
|
|
"step": 1715
|
|
},
|
|
{
|
|
"entropy": 5.993012142181397,
|
|
"epoch": 0.16522574447646493,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999459918135628,
|
|
"loss": 5.8116,
|
|
"mean_token_accuracy": 0.1678248405456543,
|
|
"num_tokens": 3952714.0,
|
|
"step": 1720
|
|
},
|
|
{
|
|
"entropy": 5.990395832061767,
|
|
"epoch": 0.16570605187319884,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000499945238075355,
|
|
"loss": 5.8016,
|
|
"mean_token_accuracy": 0.16812108904123307,
|
|
"num_tokens": 3963107.0,
|
|
"step": 1725
|
|
},
|
|
{
|
|
"entropy": 5.992589044570923,
|
|
"epoch": 0.16618635926993275,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999444791145865,
|
|
"loss": 5.7408,
|
|
"mean_token_accuracy": 0.1692016214132309,
|
|
"num_tokens": 3973454.0,
|
|
"step": 1730
|
|
},
|
|
{
|
|
"entropy": 5.983733463287353,
|
|
"epoch": 0.16666666666666666,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999437149312754,
|
|
"loss": 5.8393,
|
|
"mean_token_accuracy": 0.16407619565725326,
|
|
"num_tokens": 3985352.0,
|
|
"step": 1735
|
|
},
|
|
{
|
|
"entropy": 6.094290447235108,
|
|
"epoch": 0.16714697406340057,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000499942945525439,
|
|
"loss": 5.8161,
|
|
"mean_token_accuracy": 0.1678325891494751,
|
|
"num_tokens": 3997088.0,
|
|
"step": 1740
|
|
},
|
|
{
|
|
"entropy": 5.9968156814575195,
|
|
"epoch": 0.16762728146013448,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999421708970954,
|
|
"loss": 5.8345,
|
|
"mean_token_accuracy": 0.1668623298406601,
|
|
"num_tokens": 4008551.0,
|
|
"step": 1745
|
|
},
|
|
{
|
|
"entropy": 5.992422819137573,
|
|
"epoch": 0.16810758885686838,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999413910462625,
|
|
"loss": 5.8707,
|
|
"mean_token_accuracy": 0.1622787207365036,
|
|
"num_tokens": 4020886.0,
|
|
"step": 1750
|
|
},
|
|
{
|
|
"entropy": 6.026627683639527,
|
|
"epoch": 0.1685878962536023,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004999406059729586,
|
|
"loss": 5.8259,
|
|
"mean_token_accuracy": 0.15881873518228531,
|
|
"num_tokens": 4032811.0,
|
|
"step": 1755
|
|
},
|
|
{
|
|
"entropy": 6.032187414169312,
|
|
"epoch": 0.1690682036503362,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999398156772016,
|
|
"loss": 5.8069,
|
|
"mean_token_accuracy": 0.1716371476650238,
|
|
"num_tokens": 4044102.0,
|
|
"step": 1760
|
|
},
|
|
{
|
|
"entropy": 5.965451192855835,
|
|
"epoch": 0.16954851104707014,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00049993902015901,
|
|
"loss": 5.8225,
|
|
"mean_token_accuracy": 0.16970249265432358,
|
|
"num_tokens": 4056849.0,
|
|
"step": 1765
|
|
},
|
|
{
|
|
"entropy": 5.969043207168579,
|
|
"epoch": 0.17002881844380405,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999382194184023,
|
|
"loss": 5.8634,
|
|
"mean_token_accuracy": 0.16509611159563065,
|
|
"num_tokens": 4068392.0,
|
|
"step": 1770
|
|
},
|
|
{
|
|
"entropy": 6.03976616859436,
|
|
"epoch": 0.17050912584053796,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999374134553972,
|
|
"loss": 5.6964,
|
|
"mean_token_accuracy": 0.16902782618999482,
|
|
"num_tokens": 4078949.0,
|
|
"step": 1775
|
|
},
|
|
{
|
|
"entropy": 5.9731302738189695,
|
|
"epoch": 0.17098943323727187,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999366022700131,
|
|
"loss": 5.8517,
|
|
"mean_token_accuracy": 0.15924588441848755,
|
|
"num_tokens": 4091432.0,
|
|
"step": 1780
|
|
},
|
|
{
|
|
"entropy": 5.927183818817139,
|
|
"epoch": 0.17146974063400577,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999357858622691,
|
|
"loss": 5.7154,
|
|
"mean_token_accuracy": 0.17314967513084412,
|
|
"num_tokens": 4103001.0,
|
|
"step": 1785
|
|
},
|
|
{
|
|
"entropy": 6.011290836334228,
|
|
"epoch": 0.17195004803073968,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999349642321842,
|
|
"loss": 5.8191,
|
|
"mean_token_accuracy": 0.17158177942037584,
|
|
"num_tokens": 4113570.0,
|
|
"step": 1790
|
|
},
|
|
{
|
|
"entropy": 5.992266416549683,
|
|
"epoch": 0.1724303554274736,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999341373797772,
|
|
"loss": 5.8541,
|
|
"mean_token_accuracy": 0.16368370950222016,
|
|
"num_tokens": 4125658.0,
|
|
"step": 1795
|
|
},
|
|
{
|
|
"entropy": 5.947376489639282,
|
|
"epoch": 0.1729106628242075,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999333053050675,
|
|
"loss": 5.7418,
|
|
"mean_token_accuracy": 0.17171041816473007,
|
|
"num_tokens": 4137424.0,
|
|
"step": 1800
|
|
},
|
|
{
|
|
"entropy": 5.968177795410156,
|
|
"epoch": 0.1733909702209414,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999324680080744,
|
|
"loss": 5.7765,
|
|
"mean_token_accuracy": 0.16682788729667664,
|
|
"num_tokens": 4149772.0,
|
|
"step": 1805
|
|
},
|
|
{
|
|
"entropy": 5.920679140090942,
|
|
"epoch": 0.17387127761767532,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999316254888172,
|
|
"loss": 5.7741,
|
|
"mean_token_accuracy": 0.1707597255706787,
|
|
"num_tokens": 4162246.0,
|
|
"step": 1810
|
|
},
|
|
{
|
|
"entropy": 5.959510278701782,
|
|
"epoch": 0.17435158501440923,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999307777473157,
|
|
"loss": 5.7535,
|
|
"mean_token_accuracy": 0.1732211798429489,
|
|
"num_tokens": 4173449.0,
|
|
"step": 1815
|
|
},
|
|
{
|
|
"entropy": 5.920207357406616,
|
|
"epoch": 0.17483189241114314,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004999299247835893,
|
|
"loss": 5.7832,
|
|
"mean_token_accuracy": 0.16665025502443315,
|
|
"num_tokens": 4185560.0,
|
|
"step": 1820
|
|
},
|
|
{
|
|
"entropy": 5.9777604103088375,
|
|
"epoch": 0.17531219980787704,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.000499929066597658,
|
|
"loss": 5.8396,
|
|
"mean_token_accuracy": 0.15737783163785934,
|
|
"num_tokens": 4197843.0,
|
|
"step": 1825
|
|
},
|
|
{
|
|
"entropy": 6.042659330368042,
|
|
"epoch": 0.17579250720461095,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999282031895418,
|
|
"loss": 5.697,
|
|
"mean_token_accuracy": 0.16807238161563873,
|
|
"num_tokens": 4210009.0,
|
|
"step": 1830
|
|
},
|
|
{
|
|
"entropy": 5.951578092575073,
|
|
"epoch": 0.17627281460134486,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999273345592604,
|
|
"loss": 5.9491,
|
|
"mean_token_accuracy": 0.1559513933956623,
|
|
"num_tokens": 4222213.0,
|
|
"step": 1835
|
|
},
|
|
{
|
|
"entropy": 6.02875337600708,
|
|
"epoch": 0.17675312199807877,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999264607068343,
|
|
"loss": 5.7886,
|
|
"mean_token_accuracy": 0.1635829284787178,
|
|
"num_tokens": 4234159.0,
|
|
"step": 1840
|
|
},
|
|
{
|
|
"entropy": 5.958674907684326,
|
|
"epoch": 0.17723342939481268,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999255816322837,
|
|
"loss": 5.8528,
|
|
"mean_token_accuracy": 0.15672947987914085,
|
|
"num_tokens": 4246358.0,
|
|
"step": 1845
|
|
},
|
|
{
|
|
"entropy": 6.076961183547974,
|
|
"epoch": 0.1777137367915466,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000499924697335629,
|
|
"loss": 5.9279,
|
|
"mean_token_accuracy": 0.16347040683031083,
|
|
"num_tokens": 4256698.0,
|
|
"step": 1850
|
|
},
|
|
{
|
|
"entropy": 5.922059392929077,
|
|
"epoch": 0.1781940441882805,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999238078168906,
|
|
"loss": 5.7106,
|
|
"mean_token_accuracy": 0.17682354152202606,
|
|
"num_tokens": 4268007.0,
|
|
"step": 1855
|
|
},
|
|
{
|
|
"entropy": 6.002375745773316,
|
|
"epoch": 0.1786743515850144,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999229130760894,
|
|
"loss": 5.8196,
|
|
"mean_token_accuracy": 0.16765979379415513,
|
|
"num_tokens": 4278583.0,
|
|
"step": 1860
|
|
},
|
|
{
|
|
"entropy": 6.071978282928467,
|
|
"epoch": 0.17915465898174832,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000499922013113246,
|
|
"loss": 5.8557,
|
|
"mean_token_accuracy": 0.15993767529726027,
|
|
"num_tokens": 4290267.0,
|
|
"step": 1865
|
|
},
|
|
{
|
|
"entropy": 5.926740837097168,
|
|
"epoch": 0.17963496637848222,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999211079283814,
|
|
"loss": 5.7515,
|
|
"mean_token_accuracy": 0.17423082739114762,
|
|
"num_tokens": 4302177.0,
|
|
"step": 1870
|
|
},
|
|
{
|
|
"entropy": 5.883774328231811,
|
|
"epoch": 0.18011527377521613,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999201975215164,
|
|
"loss": 5.7041,
|
|
"mean_token_accuracy": 0.17202669382095337,
|
|
"num_tokens": 4312420.0,
|
|
"step": 1875
|
|
},
|
|
{
|
|
"entropy": 6.049909019470215,
|
|
"epoch": 0.18059558117195004,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004999192818926725,
|
|
"loss": 5.8324,
|
|
"mean_token_accuracy": 0.16264985203742982,
|
|
"num_tokens": 4324050.0,
|
|
"step": 1880
|
|
},
|
|
{
|
|
"entropy": 5.910491991043091,
|
|
"epoch": 0.18107588856868395,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999183610418706,
|
|
"loss": 5.6986,
|
|
"mean_token_accuracy": 0.1735323429107666,
|
|
"num_tokens": 4335336.0,
|
|
"step": 1885
|
|
},
|
|
{
|
|
"entropy": 5.850298452377319,
|
|
"epoch": 0.18155619596541786,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999174349691322,
|
|
"loss": 5.7101,
|
|
"mean_token_accuracy": 0.1698858320713043,
|
|
"num_tokens": 4346239.0,
|
|
"step": 1890
|
|
},
|
|
{
|
|
"entropy": 5.930282306671143,
|
|
"epoch": 0.18203650336215177,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999165036744788,
|
|
"loss": 5.7899,
|
|
"mean_token_accuracy": 0.1672823816537857,
|
|
"num_tokens": 4357195.0,
|
|
"step": 1895
|
|
},
|
|
{
|
|
"entropy": 5.934293127059936,
|
|
"epoch": 0.18251681075888568,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999155671579322,
|
|
"loss": 5.713,
|
|
"mean_token_accuracy": 0.17279640585184097,
|
|
"num_tokens": 4368905.0,
|
|
"step": 1900
|
|
},
|
|
{
|
|
"entropy": 5.985248327255249,
|
|
"epoch": 0.1829971181556196,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.000499914625419514,
|
|
"loss": 5.7924,
|
|
"mean_token_accuracy": 0.16554614007472992,
|
|
"num_tokens": 4381708.0,
|
|
"step": 1905
|
|
},
|
|
{
|
|
"entropy": 5.808998727798462,
|
|
"epoch": 0.1834774255523535,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999136784592459,
|
|
"loss": 5.6416,
|
|
"mean_token_accuracy": 0.18022481054067613,
|
|
"num_tokens": 4393199.0,
|
|
"step": 1910
|
|
},
|
|
{
|
|
"entropy": 5.969259786605835,
|
|
"epoch": 0.1839577329490874,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999127262771502,
|
|
"loss": 5.8635,
|
|
"mean_token_accuracy": 0.1600896716117859,
|
|
"num_tokens": 4403986.0,
|
|
"step": 1915
|
|
},
|
|
{
|
|
"entropy": 5.962497043609619,
|
|
"epoch": 0.1844380403458213,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004999117688732487,
|
|
"loss": 5.7064,
|
|
"mean_token_accuracy": 0.1686962679028511,
|
|
"num_tokens": 4415574.0,
|
|
"step": 1920
|
|
},
|
|
{
|
|
"entropy": 5.917124795913696,
|
|
"epoch": 0.18491834774255522,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999108062475638,
|
|
"loss": 5.7456,
|
|
"mean_token_accuracy": 0.1732297196984291,
|
|
"num_tokens": 4427579.0,
|
|
"step": 1925
|
|
},
|
|
{
|
|
"entropy": 5.935105228424073,
|
|
"epoch": 0.18539865513928913,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.000499909838400118,
|
|
"loss": 5.7297,
|
|
"mean_token_accuracy": 0.1685871258378029,
|
|
"num_tokens": 4440045.0,
|
|
"step": 1930
|
|
},
|
|
{
|
|
"entropy": 5.947299671173096,
|
|
"epoch": 0.18587896253602307,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999088653309334,
|
|
"loss": 5.8274,
|
|
"mean_token_accuracy": 0.16587052941322328,
|
|
"num_tokens": 4450129.0,
|
|
"step": 1935
|
|
},
|
|
{
|
|
"entropy": 5.921767616271973,
|
|
"epoch": 0.18635926993275698,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004999078870400329,
|
|
"loss": 5.6916,
|
|
"mean_token_accuracy": 0.17326790392398833,
|
|
"num_tokens": 4461378.0,
|
|
"step": 1940
|
|
},
|
|
{
|
|
"entropy": 5.938140058517456,
|
|
"epoch": 0.18683957732949089,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999069035274391,
|
|
"loss": 5.7165,
|
|
"mean_token_accuracy": 0.1744956612586975,
|
|
"num_tokens": 4472249.0,
|
|
"step": 1945
|
|
},
|
|
{
|
|
"entropy": 5.883719635009766,
|
|
"epoch": 0.1873198847262248,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004999059147931747,
|
|
"loss": 5.7713,
|
|
"mean_token_accuracy": 0.16725743114948272,
|
|
"num_tokens": 4484243.0,
|
|
"step": 1950
|
|
},
|
|
{
|
|
"entropy": 5.955920314788818,
|
|
"epoch": 0.1878001921229587,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999049208372629,
|
|
"loss": 5.6979,
|
|
"mean_token_accuracy": 0.1676156923174858,
|
|
"num_tokens": 4495776.0,
|
|
"step": 1955
|
|
},
|
|
{
|
|
"entropy": 5.874173736572265,
|
|
"epoch": 0.1882804995196926,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999039216597267,
|
|
"loss": 5.7708,
|
|
"mean_token_accuracy": 0.17022369354963302,
|
|
"num_tokens": 4508581.0,
|
|
"step": 1960
|
|
},
|
|
{
|
|
"entropy": 5.967559289932251,
|
|
"epoch": 0.18876080691642652,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999029172605892,
|
|
"loss": 5.7088,
|
|
"mean_token_accuracy": 0.16853721737861632,
|
|
"num_tokens": 4519753.0,
|
|
"step": 1965
|
|
},
|
|
{
|
|
"entropy": 5.8548189163208,
|
|
"epoch": 0.18924111431316043,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999019076398738,
|
|
"loss": 5.7709,
|
|
"mean_token_accuracy": 0.17433851957321167,
|
|
"num_tokens": 4529957.0,
|
|
"step": 1970
|
|
},
|
|
{
|
|
"entropy": 5.984222507476806,
|
|
"epoch": 0.18972142170989434,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000499900892797604,
|
|
"loss": 5.7479,
|
|
"mean_token_accuracy": 0.16784974783658982,
|
|
"num_tokens": 4541181.0,
|
|
"step": 1975
|
|
},
|
|
{
|
|
"entropy": 5.887285852432251,
|
|
"epoch": 0.19020172910662825,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004998998727338031,
|
|
"loss": 5.7067,
|
|
"mean_token_accuracy": 0.17156032621860504,
|
|
"num_tokens": 4552235.0,
|
|
"step": 1980
|
|
},
|
|
{
|
|
"entropy": 5.951331043243409,
|
|
"epoch": 0.19068203650336216,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004998988474484952,
|
|
"loss": 5.7343,
|
|
"mean_token_accuracy": 0.17553815692663194,
|
|
"num_tokens": 4564045.0,
|
|
"step": 1985
|
|
},
|
|
{
|
|
"entropy": 5.845712804794312,
|
|
"epoch": 0.19116234390009607,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004998978169417038,
|
|
"loss": 5.6063,
|
|
"mean_token_accuracy": 0.1784340426325798,
|
|
"num_tokens": 4575141.0,
|
|
"step": 1990
|
|
},
|
|
{
|
|
"entropy": 5.845089387893677,
|
|
"epoch": 0.19164265129682997,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004998967812134529,
|
|
"loss": 5.7324,
|
|
"mean_token_accuracy": 0.1685302123427391,
|
|
"num_tokens": 4586491.0,
|
|
"step": 1995
|
|
},
|
|
{
|
|
"entropy": 5.947291421890259,
|
|
"epoch": 0.19212295869356388,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998957402637664,
|
|
"loss": 5.722,
|
|
"mean_token_accuracy": 0.17145114988088608,
|
|
"num_tokens": 4598421.0,
|
|
"step": 2000
|
|
},
|
|
{
|
|
"entropy": 5.85858998298645,
|
|
"epoch": 0.1926032660902978,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998946940926687,
|
|
"loss": 5.6278,
|
|
"mean_token_accuracy": 0.18301957547664643,
|
|
"num_tokens": 4609688.0,
|
|
"step": 2005
|
|
},
|
|
{
|
|
"entropy": 5.852959537506104,
|
|
"epoch": 0.1930835734870317,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000499893642700184,
|
|
"loss": 5.7817,
|
|
"mean_token_accuracy": 0.16823463290929794,
|
|
"num_tokens": 4621169.0,
|
|
"step": 2010
|
|
},
|
|
{
|
|
"entropy": 5.936551713943482,
|
|
"epoch": 0.1935638808837656,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004998925860863368,
|
|
"loss": 5.7287,
|
|
"mean_token_accuracy": 0.1727944165468216,
|
|
"num_tokens": 4632512.0,
|
|
"step": 2015
|
|
},
|
|
{
|
|
"entropy": 5.921540403366089,
|
|
"epoch": 0.19404418828049952,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004998915242511516,
|
|
"loss": 5.8023,
|
|
"mean_token_accuracy": 0.16758645325899124,
|
|
"num_tokens": 4644356.0,
|
|
"step": 2020
|
|
},
|
|
{
|
|
"entropy": 5.950337505340576,
|
|
"epoch": 0.19452449567723343,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998904571946528,
|
|
"loss": 5.7704,
|
|
"mean_token_accuracy": 0.16971734017133713,
|
|
"num_tokens": 4655601.0,
|
|
"step": 2025
|
|
},
|
|
{
|
|
"entropy": 5.899324655532837,
|
|
"epoch": 0.19500480307396734,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004998893849168655,
|
|
"loss": 5.7704,
|
|
"mean_token_accuracy": 0.16545508950948715,
|
|
"num_tokens": 4666813.0,
|
|
"step": 2030
|
|
},
|
|
{
|
|
"entropy": 5.944556856155396,
|
|
"epoch": 0.19548511047070125,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004998883074178144,
|
|
"loss": 5.764,
|
|
"mean_token_accuracy": 0.16672957092523574,
|
|
"num_tokens": 4679123.0,
|
|
"step": 2035
|
|
},
|
|
{
|
|
"entropy": 5.964180326461792,
|
|
"epoch": 0.19596541786743515,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998872246975247,
|
|
"loss": 5.658,
|
|
"mean_token_accuracy": 0.175301992893219,
|
|
"num_tokens": 4690485.0,
|
|
"step": 2040
|
|
},
|
|
{
|
|
"entropy": 5.712597417831421,
|
|
"epoch": 0.19644572526416906,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004998861367560213,
|
|
"loss": 5.685,
|
|
"mean_token_accuracy": 0.17356650531291962,
|
|
"num_tokens": 4702573.0,
|
|
"step": 2045
|
|
},
|
|
{
|
|
"entropy": 6.018131875991822,
|
|
"epoch": 0.19692603266090297,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004998850435933296,
|
|
"loss": 5.7212,
|
|
"mean_token_accuracy": 0.16638207733631133,
|
|
"num_tokens": 4715653.0,
|
|
"step": 2050
|
|
},
|
|
{
|
|
"entropy": 5.8512365341186525,
|
|
"epoch": 0.19740634005763688,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004998839452094749,
|
|
"loss": 5.7248,
|
|
"mean_token_accuracy": 0.17304063439369202,
|
|
"num_tokens": 4726051.0,
|
|
"step": 2055
|
|
},
|
|
{
|
|
"entropy": 5.898526000976562,
|
|
"epoch": 0.1978866474543708,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004998828416044829,
|
|
"loss": 5.8526,
|
|
"mean_token_accuracy": 0.16188929975032806,
|
|
"num_tokens": 4738176.0,
|
|
"step": 2060
|
|
},
|
|
{
|
|
"entropy": 5.963538885116577,
|
|
"epoch": 0.1983669548511047,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000499881732778379,
|
|
"loss": 5.7637,
|
|
"mean_token_accuracy": 0.16928643435239793,
|
|
"num_tokens": 4749547.0,
|
|
"step": 2065
|
|
},
|
|
{
|
|
"entropy": 5.823513078689575,
|
|
"epoch": 0.1988472622478386,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000499880618731189,
|
|
"loss": 5.6765,
|
|
"mean_token_accuracy": 0.17271803468465804,
|
|
"num_tokens": 4761967.0,
|
|
"step": 2070
|
|
},
|
|
{
|
|
"entropy": 5.874024534225464,
|
|
"epoch": 0.19932756964457252,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998794994629388,
|
|
"loss": 5.6645,
|
|
"mean_token_accuracy": 0.17876208424568177,
|
|
"num_tokens": 4772847.0,
|
|
"step": 2075
|
|
},
|
|
{
|
|
"entropy": 5.877955722808838,
|
|
"epoch": 0.19980787704130643,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004998783749736545,
|
|
"loss": 5.7292,
|
|
"mean_token_accuracy": 0.16857509166002274,
|
|
"num_tokens": 4785049.0,
|
|
"step": 2080
|
|
},
|
|
{
|
|
"entropy": 5.901623296737671,
|
|
"epoch": 0.20028818443804033,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004998772452633619,
|
|
"loss": 5.7387,
|
|
"mean_token_accuracy": 0.16586733162403106,
|
|
"num_tokens": 4797484.0,
|
|
"step": 2085
|
|
},
|
|
{
|
|
"entropy": 5.869886159896851,
|
|
"epoch": 0.20076849183477424,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004998761103320876,
|
|
"loss": 5.6839,
|
|
"mean_token_accuracy": 0.16756847649812698,
|
|
"num_tokens": 4809422.0,
|
|
"step": 2090
|
|
},
|
|
{
|
|
"entropy": 5.904060888290405,
|
|
"epoch": 0.20124879923150815,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004998749701798577,
|
|
"loss": 5.8555,
|
|
"mean_token_accuracy": 0.16425696462392808,
|
|
"num_tokens": 4822340.0,
|
|
"step": 2095
|
|
},
|
|
{
|
|
"entropy": 5.91972541809082,
|
|
"epoch": 0.2017291066282421,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998738248066986,
|
|
"loss": 5.6478,
|
|
"mean_token_accuracy": 0.1721834734082222,
|
|
"num_tokens": 4833382.0,
|
|
"step": 2100
|
|
},
|
|
{
|
|
"entropy": 5.785834503173828,
|
|
"epoch": 0.202209414024976,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004998726742126372,
|
|
"loss": 5.6559,
|
|
"mean_token_accuracy": 0.17670872658491135,
|
|
"num_tokens": 4843916.0,
|
|
"step": 2105
|
|
},
|
|
{
|
|
"entropy": 5.9129715919494625,
|
|
"epoch": 0.2026897214217099,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004998715183976999,
|
|
"loss": 5.6465,
|
|
"mean_token_accuracy": 0.175136299431324,
|
|
"num_tokens": 4855420.0,
|
|
"step": 2110
|
|
},
|
|
{
|
|
"entropy": 5.899812126159668,
|
|
"epoch": 0.20317002881844382,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998703573619137,
|
|
"loss": 5.7348,
|
|
"mean_token_accuracy": 0.16458186358213425,
|
|
"num_tokens": 4866540.0,
|
|
"step": 2115
|
|
},
|
|
{
|
|
"entropy": 5.9016939163208,
|
|
"epoch": 0.20365033621517772,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004998691911053056,
|
|
"loss": 5.6732,
|
|
"mean_token_accuracy": 0.17268897444009781,
|
|
"num_tokens": 4878860.0,
|
|
"step": 2120
|
|
},
|
|
{
|
|
"entropy": 5.974357414245605,
|
|
"epoch": 0.20413064361191163,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004998680196279026,
|
|
"loss": 5.7979,
|
|
"mean_token_accuracy": 0.16729146391153335,
|
|
"num_tokens": 4889692.0,
|
|
"step": 2125
|
|
},
|
|
{
|
|
"entropy": 5.968846464157105,
|
|
"epoch": 0.20461095100864554,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004998668429297319,
|
|
"loss": 5.7415,
|
|
"mean_token_accuracy": 0.1737045720219612,
|
|
"num_tokens": 4901337.0,
|
|
"step": 2130
|
|
},
|
|
{
|
|
"entropy": 5.777680540084839,
|
|
"epoch": 0.20509125840537945,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004998656610108208,
|
|
"loss": 5.6488,
|
|
"mean_token_accuracy": 0.1813000425696373,
|
|
"num_tokens": 4912340.0,
|
|
"step": 2135
|
|
},
|
|
{
|
|
"entropy": 5.86177020072937,
|
|
"epoch": 0.20557156580211336,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004998644738711969,
|
|
"loss": 5.6257,
|
|
"mean_token_accuracy": 0.1789335146546364,
|
|
"num_tokens": 4923429.0,
|
|
"step": 2140
|
|
},
|
|
{
|
|
"entropy": 5.904550504684448,
|
|
"epoch": 0.20605187319884727,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004998632815108874,
|
|
"loss": 5.6893,
|
|
"mean_token_accuracy": 0.1724928915500641,
|
|
"num_tokens": 4934826.0,
|
|
"step": 2145
|
|
},
|
|
{
|
|
"entropy": 5.867998170852661,
|
|
"epoch": 0.20653218059558118,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004998620839299203,
|
|
"loss": 5.766,
|
|
"mean_token_accuracy": 0.17130101472139359,
|
|
"num_tokens": 4945189.0,
|
|
"step": 2150
|
|
},
|
|
{
|
|
"entropy": 5.955338764190674,
|
|
"epoch": 0.2070124879923151,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998608811283233,
|
|
"loss": 5.6609,
|
|
"mean_token_accuracy": 0.17488691955804825,
|
|
"num_tokens": 4956060.0,
|
|
"step": 2155
|
|
},
|
|
{
|
|
"entropy": 5.850173854827881,
|
|
"epoch": 0.207492795389049,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004998596731061244,
|
|
"loss": 5.6778,
|
|
"mean_token_accuracy": 0.1728389099240303,
|
|
"num_tokens": 4967710.0,
|
|
"step": 2160
|
|
},
|
|
{
|
|
"entropy": 5.8504749774932865,
|
|
"epoch": 0.2079731027857829,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004998584598633516,
|
|
"loss": 5.6944,
|
|
"mean_token_accuracy": 0.17247060984373092,
|
|
"num_tokens": 4978716.0,
|
|
"step": 2165
|
|
},
|
|
{
|
|
"entropy": 5.9108704090118405,
|
|
"epoch": 0.2084534101825168,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998572414000329,
|
|
"loss": 5.7613,
|
|
"mean_token_accuracy": 0.16938658952713012,
|
|
"num_tokens": 4990742.0,
|
|
"step": 2170
|
|
},
|
|
{
|
|
"entropy": 5.872229480743409,
|
|
"epoch": 0.20893371757925072,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998560177161969,
|
|
"loss": 5.7111,
|
|
"mean_token_accuracy": 0.170537830889225,
|
|
"num_tokens": 5001217.0,
|
|
"step": 2175
|
|
},
|
|
{
|
|
"entropy": 5.884965562820435,
|
|
"epoch": 0.20941402497598463,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004998547888118718,
|
|
"loss": 5.6905,
|
|
"mean_token_accuracy": 0.17088903486728668,
|
|
"num_tokens": 5012750.0,
|
|
"step": 2180
|
|
},
|
|
{
|
|
"entropy": 5.863210535049438,
|
|
"epoch": 0.20989433237271854,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004998535546870862,
|
|
"loss": 5.7103,
|
|
"mean_token_accuracy": 0.1782528981566429,
|
|
"num_tokens": 5023818.0,
|
|
"step": 2185
|
|
},
|
|
{
|
|
"entropy": 5.938375854492188,
|
|
"epoch": 0.21037463976945245,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004998523153418687,
|
|
"loss": 5.7242,
|
|
"mean_token_accuracy": 0.1727166622877121,
|
|
"num_tokens": 5035060.0,
|
|
"step": 2190
|
|
},
|
|
{
|
|
"entropy": 5.894730424880981,
|
|
"epoch": 0.21085494716618636,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004998510707762481,
|
|
"loss": 5.7598,
|
|
"mean_token_accuracy": 0.16584042757749556,
|
|
"num_tokens": 5046780.0,
|
|
"step": 2195
|
|
},
|
|
{
|
|
"entropy": 5.820294713973999,
|
|
"epoch": 0.21133525456292027,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998498209902533,
|
|
"loss": 5.7333,
|
|
"mean_token_accuracy": 0.16727135479450225,
|
|
"num_tokens": 5059152.0,
|
|
"step": 2200
|
|
},
|
|
{
|
|
"entropy": 5.911803770065307,
|
|
"epoch": 0.21181556195965417,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004998485659839134,
|
|
"loss": 5.6956,
|
|
"mean_token_accuracy": 0.17464353293180465,
|
|
"num_tokens": 5069971.0,
|
|
"step": 2205
|
|
},
|
|
{
|
|
"entropy": 5.827769708633423,
|
|
"epoch": 0.21229586935638808,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004998473057572575,
|
|
"loss": 5.644,
|
|
"mean_token_accuracy": 0.17635224610567093,
|
|
"num_tokens": 5080640.0,
|
|
"step": 2210
|
|
},
|
|
{
|
|
"entropy": 5.841212940216065,
|
|
"epoch": 0.212776176753122,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998460403103146,
|
|
"loss": 5.6737,
|
|
"mean_token_accuracy": 0.1733733147382736,
|
|
"num_tokens": 5091240.0,
|
|
"step": 2215
|
|
},
|
|
{
|
|
"entropy": 5.77046570777893,
|
|
"epoch": 0.2132564841498559,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004998447696431146,
|
|
"loss": 5.6845,
|
|
"mean_token_accuracy": 0.16993408799171447,
|
|
"num_tokens": 5102920.0,
|
|
"step": 2220
|
|
},
|
|
{
|
|
"entropy": 5.9066606044769285,
|
|
"epoch": 0.2137367915465898,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004998434937556865,
|
|
"loss": 5.7005,
|
|
"mean_token_accuracy": 0.1688303142786026,
|
|
"num_tokens": 5114240.0,
|
|
"step": 2225
|
|
},
|
|
{
|
|
"entropy": 5.993351554870605,
|
|
"epoch": 0.21421709894332372,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004998422126480602,
|
|
"loss": 5.9259,
|
|
"mean_token_accuracy": 0.15784672945737838,
|
|
"num_tokens": 5126653.0,
|
|
"step": 2230
|
|
},
|
|
{
|
|
"entropy": 5.971493339538574,
|
|
"epoch": 0.21469740634005763,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998409263202653,
|
|
"loss": 5.7667,
|
|
"mean_token_accuracy": 0.1656375914812088,
|
|
"num_tokens": 5138778.0,
|
|
"step": 2235
|
|
},
|
|
{
|
|
"entropy": 5.849447393417359,
|
|
"epoch": 0.21517771373679154,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004998396347723318,
|
|
"loss": 5.624,
|
|
"mean_token_accuracy": 0.17630810886621476,
|
|
"num_tokens": 5148670.0,
|
|
"step": 2240
|
|
},
|
|
{
|
|
"entropy": 5.685166835784912,
|
|
"epoch": 0.21565802113352545,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004998383380042895,
|
|
"loss": 5.6681,
|
|
"mean_token_accuracy": 0.17174769341945648,
|
|
"num_tokens": 5159617.0,
|
|
"step": 2245
|
|
},
|
|
{
|
|
"entropy": 5.921658134460449,
|
|
"epoch": 0.21613832853025935,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998370360161688,
|
|
"loss": 5.7246,
|
|
"mean_token_accuracy": 0.17249593138694763,
|
|
"num_tokens": 5171225.0,
|
|
"step": 2250
|
|
},
|
|
{
|
|
"entropy": 5.881531429290772,
|
|
"epoch": 0.21661863592699326,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004998357288079996,
|
|
"loss": 5.7225,
|
|
"mean_token_accuracy": 0.17121425718069078,
|
|
"num_tokens": 5184586.0,
|
|
"step": 2255
|
|
},
|
|
{
|
|
"entropy": 5.809099578857422,
|
|
"epoch": 0.21709894332372717,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004998344163798125,
|
|
"loss": 5.6839,
|
|
"mean_token_accuracy": 0.16990743279457093,
|
|
"num_tokens": 5196089.0,
|
|
"step": 2260
|
|
},
|
|
{
|
|
"entropy": 5.88064432144165,
|
|
"epoch": 0.21757925072046108,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004998330987316379,
|
|
"loss": 5.7237,
|
|
"mean_token_accuracy": 0.17189674377441405,
|
|
"num_tokens": 5207581.0,
|
|
"step": 2265
|
|
},
|
|
{
|
|
"entropy": 5.819460391998291,
|
|
"epoch": 0.21805955811719502,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998317758635062,
|
|
"loss": 5.6785,
|
|
"mean_token_accuracy": 0.1701069101691246,
|
|
"num_tokens": 5219108.0,
|
|
"step": 2270
|
|
},
|
|
{
|
|
"entropy": 5.844608736038208,
|
|
"epoch": 0.21853986551392893,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004998304477754484,
|
|
"loss": 5.6322,
|
|
"mean_token_accuracy": 0.17310244739055633,
|
|
"num_tokens": 5231137.0,
|
|
"step": 2275
|
|
},
|
|
{
|
|
"entropy": 5.944477605819702,
|
|
"epoch": 0.21902017291066284,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004998291144674952,
|
|
"loss": 5.7005,
|
|
"mean_token_accuracy": 0.1749888077378273,
|
|
"num_tokens": 5243528.0,
|
|
"step": 2280
|
|
},
|
|
{
|
|
"entropy": 5.702851104736328,
|
|
"epoch": 0.21950048030739674,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004998277759396776,
|
|
"loss": 5.6449,
|
|
"mean_token_accuracy": 0.1756882846355438,
|
|
"num_tokens": 5254869.0,
|
|
"step": 2285
|
|
},
|
|
{
|
|
"entropy": 5.825752067565918,
|
|
"epoch": 0.21998078770413065,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004998264321920265,
|
|
"loss": 5.6384,
|
|
"mean_token_accuracy": 0.1748126581311226,
|
|
"num_tokens": 5265370.0,
|
|
"step": 2290
|
|
},
|
|
{
|
|
"entropy": 5.841421604156494,
|
|
"epoch": 0.22046109510086456,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004998250832245734,
|
|
"loss": 5.5943,
|
|
"mean_token_accuracy": 0.1766410768032074,
|
|
"num_tokens": 5277812.0,
|
|
"step": 2295
|
|
},
|
|
{
|
|
"entropy": 5.787303256988525,
|
|
"epoch": 0.22094140249759847,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998237290373494,
|
|
"loss": 5.5874,
|
|
"mean_token_accuracy": 0.17861277461051941,
|
|
"num_tokens": 5289107.0,
|
|
"step": 2300
|
|
},
|
|
{
|
|
"entropy": 5.789830303192138,
|
|
"epoch": 0.22142170989433238,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000499822369630386,
|
|
"loss": 5.6356,
|
|
"mean_token_accuracy": 0.16736368983983993,
|
|
"num_tokens": 5301489.0,
|
|
"step": 2305
|
|
},
|
|
{
|
|
"entropy": 5.7769101619720455,
|
|
"epoch": 0.2219020172910663,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004998210050037148,
|
|
"loss": 5.618,
|
|
"mean_token_accuracy": 0.1812180057168007,
|
|
"num_tokens": 5313273.0,
|
|
"step": 2310
|
|
},
|
|
{
|
|
"entropy": 5.85909104347229,
|
|
"epoch": 0.2223823246878002,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004998196351573674,
|
|
"loss": 5.6456,
|
|
"mean_token_accuracy": 0.17510980367660522,
|
|
"num_tokens": 5324227.0,
|
|
"step": 2315
|
|
},
|
|
{
|
|
"entropy": 5.776947546005249,
|
|
"epoch": 0.2228626320845341,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998182600913757,
|
|
"loss": 5.5856,
|
|
"mean_token_accuracy": 0.18297051787376403,
|
|
"num_tokens": 5335138.0,
|
|
"step": 2320
|
|
},
|
|
{
|
|
"entropy": 5.796558809280396,
|
|
"epoch": 0.22334293948126802,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004998168798057715,
|
|
"loss": 5.6683,
|
|
"mean_token_accuracy": 0.17540759295225145,
|
|
"num_tokens": 5345652.0,
|
|
"step": 2325
|
|
},
|
|
{
|
|
"entropy": 5.9193799018859865,
|
|
"epoch": 0.22382324687800192,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.000499815494300587,
|
|
"loss": 5.7596,
|
|
"mean_token_accuracy": 0.17200602740049362,
|
|
"num_tokens": 5357999.0,
|
|
"step": 2330
|
|
},
|
|
{
|
|
"entropy": 5.852154779434204,
|
|
"epoch": 0.22430355427473583,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004998141035758542,
|
|
"loss": 5.669,
|
|
"mean_token_accuracy": 0.17199552208185195,
|
|
"num_tokens": 5369032.0,
|
|
"step": 2335
|
|
},
|
|
{
|
|
"entropy": 5.799731969833374,
|
|
"epoch": 0.22478386167146974,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004998127076316054,
|
|
"loss": 5.5855,
|
|
"mean_token_accuracy": 0.17641636580228806,
|
|
"num_tokens": 5380692.0,
|
|
"step": 2340
|
|
},
|
|
{
|
|
"entropy": 5.864359760284424,
|
|
"epoch": 0.22526416906820365,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004998113064678734,
|
|
"loss": 5.7228,
|
|
"mean_token_accuracy": 0.16467591673135756,
|
|
"num_tokens": 5392320.0,
|
|
"step": 2345
|
|
},
|
|
{
|
|
"entropy": 5.877440690994263,
|
|
"epoch": 0.22574447646493756,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004998099000846901,
|
|
"loss": 5.7007,
|
|
"mean_token_accuracy": 0.1754738360643387,
|
|
"num_tokens": 5404374.0,
|
|
"step": 2350
|
|
},
|
|
{
|
|
"entropy": 5.855792570114136,
|
|
"epoch": 0.22622478386167147,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004998084884820887,
|
|
"loss": 5.6965,
|
|
"mean_token_accuracy": 0.17115845978260041,
|
|
"num_tokens": 5415471.0,
|
|
"step": 2355
|
|
},
|
|
{
|
|
"entropy": 5.710199642181396,
|
|
"epoch": 0.22670509125840538,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004998070716601016,
|
|
"loss": 5.5231,
|
|
"mean_token_accuracy": 0.17625806480646133,
|
|
"num_tokens": 5425971.0,
|
|
"step": 2360
|
|
},
|
|
{
|
|
"entropy": 5.852556991577148,
|
|
"epoch": 0.2271853986551393,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998056496187618,
|
|
"loss": 5.6506,
|
|
"mean_token_accuracy": 0.17488612681627275,
|
|
"num_tokens": 5437638.0,
|
|
"step": 2365
|
|
},
|
|
{
|
|
"entropy": 5.849278402328491,
|
|
"epoch": 0.2276657060518732,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004998042223581025,
|
|
"loss": 5.6783,
|
|
"mean_token_accuracy": 0.1768277943134308,
|
|
"num_tokens": 5449463.0,
|
|
"step": 2370
|
|
},
|
|
{
|
|
"entropy": 5.841348314285279,
|
|
"epoch": 0.2281460134486071,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998027898781565,
|
|
"loss": 5.7432,
|
|
"mean_token_accuracy": 0.1705165147781372,
|
|
"num_tokens": 5460972.0,
|
|
"step": 2375
|
|
},
|
|
{
|
|
"entropy": 5.983591842651367,
|
|
"epoch": 0.228626320845341,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004998013521789574,
|
|
"loss": 5.7514,
|
|
"mean_token_accuracy": 0.16724159568548203,
|
|
"num_tokens": 5471575.0,
|
|
"step": 2380
|
|
},
|
|
{
|
|
"entropy": 5.754042243957519,
|
|
"epoch": 0.22910662824207492,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004997999092605384,
|
|
"loss": 5.6009,
|
|
"mean_token_accuracy": 0.178335303068161,
|
|
"num_tokens": 5483041.0,
|
|
"step": 2385
|
|
},
|
|
{
|
|
"entropy": 5.795910120010376,
|
|
"epoch": 0.22958693563880883,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000499798461122933,
|
|
"loss": 5.6288,
|
|
"mean_token_accuracy": 0.1755184829235077,
|
|
"num_tokens": 5494040.0,
|
|
"step": 2390
|
|
},
|
|
{
|
|
"entropy": 5.774956464767456,
|
|
"epoch": 0.23006724303554274,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004997970077661748,
|
|
"loss": 5.5311,
|
|
"mean_token_accuracy": 0.18456185460090638,
|
|
"num_tokens": 5504217.0,
|
|
"step": 2395
|
|
},
|
|
{
|
|
"entropy": 5.877355241775513,
|
|
"epoch": 0.23054755043227665,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004997955491902977,
|
|
"loss": 5.6954,
|
|
"mean_token_accuracy": 0.1742586001753807,
|
|
"num_tokens": 5517180.0,
|
|
"step": 2400
|
|
},
|
|
{
|
|
"entropy": 5.792226076126099,
|
|
"epoch": 0.23102785782901056,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004997940853953354,
|
|
"loss": 5.6086,
|
|
"mean_token_accuracy": 0.17229509651660918,
|
|
"num_tokens": 5529626.0,
|
|
"step": 2405
|
|
},
|
|
{
|
|
"entropy": 5.843723583221435,
|
|
"epoch": 0.23150816522574447,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.000499792616381322,
|
|
"loss": 5.6466,
|
|
"mean_token_accuracy": 0.18131813108921052,
|
|
"num_tokens": 5540844.0,
|
|
"step": 2410
|
|
},
|
|
{
|
|
"entropy": 5.8429769515991214,
|
|
"epoch": 0.23198847262247838,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004997911421482914,
|
|
"loss": 5.57,
|
|
"mean_token_accuracy": 0.1793536514043808,
|
|
"num_tokens": 5551732.0,
|
|
"step": 2415
|
|
},
|
|
{
|
|
"entropy": 5.815704107284546,
|
|
"epoch": 0.23246878001921228,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000499789662696278,
|
|
"loss": 5.7051,
|
|
"mean_token_accuracy": 0.17402584850788116,
|
|
"num_tokens": 5562692.0,
|
|
"step": 2420
|
|
},
|
|
{
|
|
"entropy": 5.91572937965393,
|
|
"epoch": 0.2329490874159462,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004997881780253162,
|
|
"loss": 5.7007,
|
|
"mean_token_accuracy": 0.17055609226226806,
|
|
"num_tokens": 5574884.0,
|
|
"step": 2425
|
|
},
|
|
{
|
|
"entropy": 5.709230899810791,
|
|
"epoch": 0.2334293948126801,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004997866881354403,
|
|
"loss": 5.5462,
|
|
"mean_token_accuracy": 0.18206045031547546,
|
|
"num_tokens": 5585335.0,
|
|
"step": 2430
|
|
},
|
|
{
|
|
"entropy": 5.862868022918701,
|
|
"epoch": 0.23390970220941404,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.000499785193026685,
|
|
"loss": 5.6923,
|
|
"mean_token_accuracy": 0.17130919694900512,
|
|
"num_tokens": 5597621.0,
|
|
"step": 2435
|
|
},
|
|
{
|
|
"entropy": 5.702938747406006,
|
|
"epoch": 0.23439000960614795,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004997836926990851,
|
|
"loss": 5.5569,
|
|
"mean_token_accuracy": 0.17519160956144333,
|
|
"num_tokens": 5609795.0,
|
|
"step": 2440
|
|
},
|
|
{
|
|
"entropy": 5.82079005241394,
|
|
"epoch": 0.23487031700288186,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004997821871526752,
|
|
"loss": 5.6514,
|
|
"mean_token_accuracy": 0.17482785731554032,
|
|
"num_tokens": 5621473.0,
|
|
"step": 2445
|
|
},
|
|
{
|
|
"entropy": 5.843278980255127,
|
|
"epoch": 0.23535062439961577,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004997806763874905,
|
|
"loss": 5.7307,
|
|
"mean_token_accuracy": 0.174130442738533,
|
|
"num_tokens": 5635064.0,
|
|
"step": 2450
|
|
},
|
|
{
|
|
"entropy": 5.9370584964752195,
|
|
"epoch": 0.23583093179634967,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004997791604035659,
|
|
"loss": 5.7352,
|
|
"mean_token_accuracy": 0.17039123475551604,
|
|
"num_tokens": 5647382.0,
|
|
"step": 2455
|
|
},
|
|
{
|
|
"entropy": 5.830444431304931,
|
|
"epoch": 0.23631123919308358,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004997776392009366,
|
|
"loss": 5.6191,
|
|
"mean_token_accuracy": 0.17757430523633957,
|
|
"num_tokens": 5658417.0,
|
|
"step": 2460
|
|
},
|
|
{
|
|
"entropy": 5.7811634063720705,
|
|
"epoch": 0.2367915465898175,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004997761127796381,
|
|
"loss": 5.5757,
|
|
"mean_token_accuracy": 0.1834951251745224,
|
|
"num_tokens": 5672190.0,
|
|
"step": 2465
|
|
},
|
|
{
|
|
"entropy": 5.717312669754028,
|
|
"epoch": 0.2372718539865514,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004997745811397056,
|
|
"loss": 5.5926,
|
|
"mean_token_accuracy": 0.1851950004696846,
|
|
"num_tokens": 5684259.0,
|
|
"step": 2470
|
|
},
|
|
{
|
|
"entropy": 5.784187078475952,
|
|
"epoch": 0.2377521613832853,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004997730442811748,
|
|
"loss": 5.6604,
|
|
"mean_token_accuracy": 0.17508698701858522,
|
|
"num_tokens": 5696505.0,
|
|
"step": 2475
|
|
},
|
|
{
|
|
"entropy": 5.720936918258667,
|
|
"epoch": 0.23823246878001922,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004997715022040814,
|
|
"loss": 5.5441,
|
|
"mean_token_accuracy": 0.1788373351097107,
|
|
"num_tokens": 5707638.0,
|
|
"step": 2480
|
|
},
|
|
{
|
|
"entropy": 5.753598546981811,
|
|
"epoch": 0.23871277617675313,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.000499769954908461,
|
|
"loss": 5.5293,
|
|
"mean_token_accuracy": 0.1850265458226204,
|
|
"num_tokens": 5719098.0,
|
|
"step": 2485
|
|
},
|
|
{
|
|
"entropy": 5.9342193603515625,
|
|
"epoch": 0.23919308357348704,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004997684023943498,
|
|
"loss": 5.7511,
|
|
"mean_token_accuracy": 0.16247327476739884,
|
|
"num_tokens": 5731345.0,
|
|
"step": 2490
|
|
},
|
|
{
|
|
"entropy": 5.649840927124023,
|
|
"epoch": 0.23967339097022095,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004997668446617837,
|
|
"loss": 5.525,
|
|
"mean_token_accuracy": 0.17844921350479126,
|
|
"num_tokens": 5742604.0,
|
|
"step": 2495
|
|
},
|
|
{
|
|
"entropy": 5.754658555984497,
|
|
"epoch": 0.24015369836695485,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004997652817107989,
|
|
"loss": 5.5469,
|
|
"mean_token_accuracy": 0.18343215733766555,
|
|
"num_tokens": 5754620.0,
|
|
"step": 2500
|
|
},
|
|
{
|
|
"entropy": 5.781588220596314,
|
|
"epoch": 0.24063400576368876,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004997637135414315,
|
|
"loss": 5.6402,
|
|
"mean_token_accuracy": 0.17647155076265336,
|
|
"num_tokens": 5764764.0,
|
|
"step": 2505
|
|
},
|
|
{
|
|
"entropy": 5.660699033737183,
|
|
"epoch": 0.24111431316042267,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004997621401537183,
|
|
"loss": 5.5191,
|
|
"mean_token_accuracy": 0.18696373254060744,
|
|
"num_tokens": 5776341.0,
|
|
"step": 2510
|
|
},
|
|
{
|
|
"entropy": 5.818323850631714,
|
|
"epoch": 0.24159462055715658,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004997605615476955,
|
|
"loss": 5.739,
|
|
"mean_token_accuracy": 0.16692858338356018,
|
|
"num_tokens": 5788604.0,
|
|
"step": 2515
|
|
},
|
|
{
|
|
"entropy": 5.825610828399658,
|
|
"epoch": 0.2420749279538905,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004997589777234,
|
|
"loss": 5.6251,
|
|
"mean_token_accuracy": 0.17850779592990876,
|
|
"num_tokens": 5800194.0,
|
|
"step": 2520
|
|
},
|
|
{
|
|
"entropy": 5.751928377151489,
|
|
"epoch": 0.2425552353506244,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004997573886808684,
|
|
"loss": 5.6256,
|
|
"mean_token_accuracy": 0.18556526601314544,
|
|
"num_tokens": 5812978.0,
|
|
"step": 2525
|
|
},
|
|
{
|
|
"entropy": 5.761942911148071,
|
|
"epoch": 0.2430355427473583,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004997557944201375,
|
|
"loss": 5.535,
|
|
"mean_token_accuracy": 0.18203383684158325,
|
|
"num_tokens": 5824591.0,
|
|
"step": 2530
|
|
},
|
|
{
|
|
"entropy": 5.713061332702637,
|
|
"epoch": 0.24351585014409222,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004997541949412445,
|
|
"loss": 5.6289,
|
|
"mean_token_accuracy": 0.1750789538025856,
|
|
"num_tokens": 5835970.0,
|
|
"step": 2535
|
|
},
|
|
{
|
|
"entropy": 5.851242256164551,
|
|
"epoch": 0.24399615754082613,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004997525902442266,
|
|
"loss": 5.6674,
|
|
"mean_token_accuracy": 0.17141913771629333,
|
|
"num_tokens": 5848687.0,
|
|
"step": 2540
|
|
},
|
|
{
|
|
"entropy": 5.764578819274902,
|
|
"epoch": 0.24447646493756003,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004997509803291207,
|
|
"loss": 5.641,
|
|
"mean_token_accuracy": 0.1750764176249504,
|
|
"num_tokens": 5860820.0,
|
|
"step": 2545
|
|
},
|
|
{
|
|
"entropy": 5.759086322784424,
|
|
"epoch": 0.24495677233429394,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004997493651959647,
|
|
"loss": 5.5807,
|
|
"mean_token_accuracy": 0.1781640961766243,
|
|
"num_tokens": 5872172.0,
|
|
"step": 2550
|
|
},
|
|
{
|
|
"entropy": 5.821686220169068,
|
|
"epoch": 0.24543707973102785,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004997477448447955,
|
|
"loss": 5.6243,
|
|
"mean_token_accuracy": 0.17710455805063247,
|
|
"num_tokens": 5883574.0,
|
|
"step": 2555
|
|
},
|
|
{
|
|
"entropy": 5.838350677490235,
|
|
"epoch": 0.24591738712776176,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004997461192756512,
|
|
"loss": 5.7091,
|
|
"mean_token_accuracy": 0.17892282754182814,
|
|
"num_tokens": 5895223.0,
|
|
"step": 2560
|
|
},
|
|
{
|
|
"entropy": 5.739510202407837,
|
|
"epoch": 0.24639769452449567,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004997444884885694,
|
|
"loss": 5.5408,
|
|
"mean_token_accuracy": 0.1767376109957695,
|
|
"num_tokens": 5907448.0,
|
|
"step": 2565
|
|
},
|
|
{
|
|
"entropy": 5.812138986587525,
|
|
"epoch": 0.24687800192122958,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004997428524835879,
|
|
"loss": 5.6334,
|
|
"mean_token_accuracy": 0.1804532065987587,
|
|
"num_tokens": 5918906.0,
|
|
"step": 2570
|
|
},
|
|
{
|
|
"entropy": 5.752865028381348,
|
|
"epoch": 0.2473583093179635,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004997412112607446,
|
|
"loss": 5.501,
|
|
"mean_token_accuracy": 0.18547787815332412,
|
|
"num_tokens": 5930619.0,
|
|
"step": 2575
|
|
},
|
|
{
|
|
"entropy": 5.849464845657349,
|
|
"epoch": 0.2478386167146974,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004997395648200778,
|
|
"loss": 5.7079,
|
|
"mean_token_accuracy": 0.17087607085704803,
|
|
"num_tokens": 5941554.0,
|
|
"step": 2580
|
|
},
|
|
{
|
|
"entropy": 5.8415814399719235,
|
|
"epoch": 0.2483189241114313,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004997379131616257,
|
|
"loss": 5.6732,
|
|
"mean_token_accuracy": 0.17775924354791642,
|
|
"num_tokens": 5953309.0,
|
|
"step": 2585
|
|
},
|
|
{
|
|
"entropy": 5.769577217102051,
|
|
"epoch": 0.24879923150816521,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004997362562854266,
|
|
"loss": 5.6135,
|
|
"mean_token_accuracy": 0.17712407559156418,
|
|
"num_tokens": 5965286.0,
|
|
"step": 2590
|
|
},
|
|
{
|
|
"entropy": 5.778793144226074,
|
|
"epoch": 0.24927953890489912,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004997345941915187,
|
|
"loss": 5.5918,
|
|
"mean_token_accuracy": 0.17737313807010652,
|
|
"num_tokens": 5976558.0,
|
|
"step": 2595
|
|
},
|
|
{
|
|
"entropy": 5.780767154693604,
|
|
"epoch": 0.24975984630163303,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004997329268799412,
|
|
"loss": 5.6362,
|
|
"mean_token_accuracy": 0.17200108617544174,
|
|
"num_tokens": 5988793.0,
|
|
"step": 2600
|
|
},
|
|
{
|
|
"entropy": 5.7742997169494625,
|
|
"epoch": 0.25024015369836694,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004997312543507322,
|
|
"loss": 5.6641,
|
|
"mean_token_accuracy": 0.16963352560997008,
|
|
"num_tokens": 5999825.0,
|
|
"step": 2605
|
|
},
|
|
{
|
|
"entropy": 5.83264274597168,
|
|
"epoch": 0.2507204610951009,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004997295766039309,
|
|
"loss": 5.6299,
|
|
"mean_token_accuracy": 0.1738866686820984,
|
|
"num_tokens": 6010408.0,
|
|
"step": 2610
|
|
},
|
|
{
|
|
"entropy": 5.799222660064697,
|
|
"epoch": 0.25120076849183476,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004997278936395761,
|
|
"loss": 5.6418,
|
|
"mean_token_accuracy": 0.1749333217740059,
|
|
"num_tokens": 6021161.0,
|
|
"step": 2615
|
|
},
|
|
{
|
|
"entropy": 5.686932611465454,
|
|
"epoch": 0.2516810758885687,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004997262054577071,
|
|
"loss": 5.4878,
|
|
"mean_token_accuracy": 0.18859331905841828,
|
|
"num_tokens": 6032646.0,
|
|
"step": 2620
|
|
},
|
|
{
|
|
"entropy": 5.804806661605835,
|
|
"epoch": 0.2521613832853026,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004997245120583627,
|
|
"loss": 5.6657,
|
|
"mean_token_accuracy": 0.1764261692762375,
|
|
"num_tokens": 6045019.0,
|
|
"step": 2625
|
|
},
|
|
{
|
|
"entropy": 5.651595687866211,
|
|
"epoch": 0.2526416906820365,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004997228134415825,
|
|
"loss": 5.5362,
|
|
"mean_token_accuracy": 0.18478751182556152,
|
|
"num_tokens": 6055644.0,
|
|
"step": 2630
|
|
},
|
|
{
|
|
"entropy": 5.809038543701172,
|
|
"epoch": 0.2531219980787704,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004997211096074059,
|
|
"loss": 5.5779,
|
|
"mean_token_accuracy": 0.18167155236005783,
|
|
"num_tokens": 6066488.0,
|
|
"step": 2635
|
|
},
|
|
{
|
|
"entropy": 5.771279287338257,
|
|
"epoch": 0.25360230547550433,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004997194005558722,
|
|
"loss": 5.6018,
|
|
"mean_token_accuracy": 0.17499032467603684,
|
|
"num_tokens": 6078300.0,
|
|
"step": 2640
|
|
},
|
|
{
|
|
"entropy": 5.731289052963257,
|
|
"epoch": 0.2540826128722382,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004997176862870216,
|
|
"loss": 5.5867,
|
|
"mean_token_accuracy": 0.1714366629719734,
|
|
"num_tokens": 6089180.0,
|
|
"step": 2645
|
|
},
|
|
{
|
|
"entropy": 5.78031816482544,
|
|
"epoch": 0.25456292026897215,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004997159668008933,
|
|
"loss": 5.6185,
|
|
"mean_token_accuracy": 0.18340758681297303,
|
|
"num_tokens": 6099093.0,
|
|
"step": 2650
|
|
},
|
|
{
|
|
"entropy": 5.818167781829834,
|
|
"epoch": 0.25504322766570603,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004997142420975277,
|
|
"loss": 5.6335,
|
|
"mean_token_accuracy": 0.178047214448452,
|
|
"num_tokens": 6109161.0,
|
|
"step": 2655
|
|
},
|
|
{
|
|
"entropy": 5.863713979721069,
|
|
"epoch": 0.25552353506243997,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004997125121769647,
|
|
"loss": 5.7377,
|
|
"mean_token_accuracy": 0.16746834814548492,
|
|
"num_tokens": 6120031.0,
|
|
"step": 2660
|
|
},
|
|
{
|
|
"entropy": 5.716607522964478,
|
|
"epoch": 0.25600384245917385,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004997107770392444,
|
|
"loss": 5.5956,
|
|
"mean_token_accuracy": 0.17772964537143707,
|
|
"num_tokens": 6132398.0,
|
|
"step": 2665
|
|
},
|
|
{
|
|
"entropy": 5.752996158599854,
|
|
"epoch": 0.2564841498559078,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000499709036684407,
|
|
"loss": 5.5746,
|
|
"mean_token_accuracy": 0.17592063248157502,
|
|
"num_tokens": 6143099.0,
|
|
"step": 2670
|
|
},
|
|
{
|
|
"entropy": 5.736369705200195,
|
|
"epoch": 0.25696445725264166,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004997072911124932,
|
|
"loss": 5.5385,
|
|
"mean_token_accuracy": 0.18297111839056016,
|
|
"num_tokens": 6154815.0,
|
|
"step": 2675
|
|
},
|
|
{
|
|
"entropy": 5.770055437088013,
|
|
"epoch": 0.2574447646493756,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004997055403235432,
|
|
"loss": 5.6053,
|
|
"mean_token_accuracy": 0.18265556544065475,
|
|
"num_tokens": 6165696.0,
|
|
"step": 2680
|
|
},
|
|
{
|
|
"entropy": 5.7239914894104,
|
|
"epoch": 0.2579250720461095,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004997037843175978,
|
|
"loss": 5.6237,
|
|
"mean_token_accuracy": 0.17451792806386948,
|
|
"num_tokens": 6177042.0,
|
|
"step": 2685
|
|
},
|
|
{
|
|
"entropy": 5.856169700622559,
|
|
"epoch": 0.2584053794428434,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004997020230946978,
|
|
"loss": 5.6197,
|
|
"mean_token_accuracy": 0.1756477549672127,
|
|
"num_tokens": 6188691.0,
|
|
"step": 2690
|
|
},
|
|
{
|
|
"entropy": 5.612815475463867,
|
|
"epoch": 0.25888568683957736,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004997002566548841,
|
|
"loss": 5.4458,
|
|
"mean_token_accuracy": 0.184897281229496,
|
|
"num_tokens": 6199931.0,
|
|
"step": 2695
|
|
},
|
|
{
|
|
"entropy": 5.721167039871216,
|
|
"epoch": 0.25936599423631124,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004996984849981976,
|
|
"loss": 5.5864,
|
|
"mean_token_accuracy": 0.18731192648410797,
|
|
"num_tokens": 6211493.0,
|
|
"step": 2700
|
|
},
|
|
{
|
|
"entropy": 5.792260313034058,
|
|
"epoch": 0.2598463016330452,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004996967081246794,
|
|
"loss": 5.5167,
|
|
"mean_token_accuracy": 0.17840367555618286,
|
|
"num_tokens": 6221505.0,
|
|
"step": 2705
|
|
},
|
|
{
|
|
"entropy": 5.643460273742676,
|
|
"epoch": 0.26032660902977905,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004996949260343711,
|
|
"loss": 5.4986,
|
|
"mean_token_accuracy": 0.18759121745824814,
|
|
"num_tokens": 6233058.0,
|
|
"step": 2710
|
|
},
|
|
{
|
|
"entropy": 5.726798248291016,
|
|
"epoch": 0.260806916426513,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004996931387273137,
|
|
"loss": 5.6449,
|
|
"mean_token_accuracy": 0.17207851707935334,
|
|
"num_tokens": 6244713.0,
|
|
"step": 2715
|
|
},
|
|
{
|
|
"entropy": 5.75096960067749,
|
|
"epoch": 0.2612872238232469,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004996913462035487,
|
|
"loss": 5.59,
|
|
"mean_token_accuracy": 0.17319334894418717,
|
|
"num_tokens": 6256624.0,
|
|
"step": 2720
|
|
},
|
|
{
|
|
"entropy": 5.7101236343383786,
|
|
"epoch": 0.2617675312199808,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.000499689548463118,
|
|
"loss": 5.5794,
|
|
"mean_token_accuracy": 0.17421182990074158,
|
|
"num_tokens": 6271134.0,
|
|
"step": 2725
|
|
},
|
|
{
|
|
"entropy": 5.844261217117309,
|
|
"epoch": 0.2622478386167147,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004996877455060631,
|
|
"loss": 5.6879,
|
|
"mean_token_accuracy": 0.17699914574623107,
|
|
"num_tokens": 6282082.0,
|
|
"step": 2730
|
|
},
|
|
{
|
|
"entropy": 5.764342355728149,
|
|
"epoch": 0.2627281460134486,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004996859373324259,
|
|
"loss": 5.6248,
|
|
"mean_token_accuracy": 0.17453763633966446,
|
|
"num_tokens": 6293869.0,
|
|
"step": 2735
|
|
},
|
|
{
|
|
"entropy": 5.779357290267944,
|
|
"epoch": 0.2632084534101825,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004996841239422485,
|
|
"loss": 5.6448,
|
|
"mean_token_accuracy": 0.1693587228655815,
|
|
"num_tokens": 6304858.0,
|
|
"step": 2740
|
|
},
|
|
{
|
|
"entropy": 5.76701545715332,
|
|
"epoch": 0.26368876080691644,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004996823053355729,
|
|
"loss": 5.5765,
|
|
"mean_token_accuracy": 0.17856617122888566,
|
|
"num_tokens": 6316738.0,
|
|
"step": 2745
|
|
},
|
|
{
|
|
"entropy": 5.723379611968994,
|
|
"epoch": 0.2641690682036503,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004996804815124413,
|
|
"loss": 5.548,
|
|
"mean_token_accuracy": 0.17553849667310714,
|
|
"num_tokens": 6327691.0,
|
|
"step": 2750
|
|
},
|
|
{
|
|
"entropy": 5.798751974105835,
|
|
"epoch": 0.26464937560038426,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004996786524728962,
|
|
"loss": 5.5599,
|
|
"mean_token_accuracy": 0.176359224319458,
|
|
"num_tokens": 6337964.0,
|
|
"step": 2755
|
|
},
|
|
{
|
|
"entropy": 5.669320964813233,
|
|
"epoch": 0.26512968299711814,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004996768182169797,
|
|
"loss": 5.6018,
|
|
"mean_token_accuracy": 0.177447210252285,
|
|
"num_tokens": 6349764.0,
|
|
"step": 2760
|
|
},
|
|
{
|
|
"entropy": 5.802992105484009,
|
|
"epoch": 0.2656099903938521,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004996749787447349,
|
|
"loss": 5.5699,
|
|
"mean_token_accuracy": 0.17743425965309143,
|
|
"num_tokens": 6360538.0,
|
|
"step": 2765
|
|
},
|
|
{
|
|
"entropy": 5.745979881286621,
|
|
"epoch": 0.26609029779058596,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000499673134056204,
|
|
"loss": 5.5983,
|
|
"mean_token_accuracy": 0.1776156932115555,
|
|
"num_tokens": 6372489.0,
|
|
"step": 2770
|
|
},
|
|
{
|
|
"entropy": 5.608844423294068,
|
|
"epoch": 0.2665706051873199,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004996712841514303,
|
|
"loss": 5.4713,
|
|
"mean_token_accuracy": 0.18549432456493378,
|
|
"num_tokens": 6383080.0,
|
|
"step": 2775
|
|
},
|
|
{
|
|
"entropy": 5.823545598983765,
|
|
"epoch": 0.2670509125840538,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004996694290304563,
|
|
"loss": 5.5946,
|
|
"mean_token_accuracy": 0.1786493942141533,
|
|
"num_tokens": 6394033.0,
|
|
"step": 2780
|
|
},
|
|
{
|
|
"entropy": 5.703853988647461,
|
|
"epoch": 0.2675312199807877,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004996675686933255,
|
|
"loss": 5.597,
|
|
"mean_token_accuracy": 0.17830613106489182,
|
|
"num_tokens": 6404990.0,
|
|
"step": 2785
|
|
},
|
|
{
|
|
"entropy": 5.722035598754883,
|
|
"epoch": 0.2680115273775216,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004996657031400807,
|
|
"loss": 5.4683,
|
|
"mean_token_accuracy": 0.186190427839756,
|
|
"num_tokens": 6416337.0,
|
|
"step": 2790
|
|
},
|
|
{
|
|
"entropy": 5.710982465744019,
|
|
"epoch": 0.26849183477425553,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004996638323707655,
|
|
"loss": 5.6723,
|
|
"mean_token_accuracy": 0.1744049683213234,
|
|
"num_tokens": 6427892.0,
|
|
"step": 2795
|
|
},
|
|
{
|
|
"entropy": 5.754525852203369,
|
|
"epoch": 0.2689721421709894,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004996619563854232,
|
|
"loss": 5.5776,
|
|
"mean_token_accuracy": 0.18131734281778336,
|
|
"num_tokens": 6440300.0,
|
|
"step": 2800
|
|
},
|
|
{
|
|
"entropy": 5.676147937774658,
|
|
"epoch": 0.26945244956772335,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004996600751840974,
|
|
"loss": 5.4817,
|
|
"mean_token_accuracy": 0.18177040964365004,
|
|
"num_tokens": 6451499.0,
|
|
"step": 2805
|
|
},
|
|
{
|
|
"entropy": 5.7406394481658936,
|
|
"epoch": 0.26993275696445723,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004996581887668317,
|
|
"loss": 5.5633,
|
|
"mean_token_accuracy": 0.18365933150053024,
|
|
"num_tokens": 6462882.0,
|
|
"step": 2810
|
|
},
|
|
{
|
|
"entropy": 5.697629499435425,
|
|
"epoch": 0.27041306436119117,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00049965629713367,
|
|
"loss": 5.5503,
|
|
"mean_token_accuracy": 0.17984720915555955,
|
|
"num_tokens": 6475042.0,
|
|
"step": 2815
|
|
},
|
|
{
|
|
"entropy": 5.7321325778961185,
|
|
"epoch": 0.27089337175792505,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004996544002846561,
|
|
"loss": 5.5598,
|
|
"mean_token_accuracy": 0.17862652242183685,
|
|
"num_tokens": 6486245.0,
|
|
"step": 2820
|
|
},
|
|
{
|
|
"entropy": 5.704649543762207,
|
|
"epoch": 0.271373679154659,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004996524982198343,
|
|
"loss": 5.4526,
|
|
"mean_token_accuracy": 0.1825141653418541,
|
|
"num_tokens": 6497705.0,
|
|
"step": 2825
|
|
},
|
|
{
|
|
"entropy": 5.639297246932983,
|
|
"epoch": 0.27185398655139287,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004996505909392485,
|
|
"loss": 5.4936,
|
|
"mean_token_accuracy": 0.1846439689397812,
|
|
"num_tokens": 6508193.0,
|
|
"step": 2830
|
|
},
|
|
{
|
|
"entropy": 5.765617036819458,
|
|
"epoch": 0.2723342939481268,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004996486784429429,
|
|
"loss": 5.612,
|
|
"mean_token_accuracy": 0.18255474865436555,
|
|
"num_tokens": 6519228.0,
|
|
"step": 2835
|
|
},
|
|
{
|
|
"entropy": 5.747947263717651,
|
|
"epoch": 0.2728146013448607,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004996467607309622,
|
|
"loss": 5.5679,
|
|
"mean_token_accuracy": 0.17834291160106658,
|
|
"num_tokens": 6530743.0,
|
|
"step": 2840
|
|
},
|
|
{
|
|
"entropy": 5.690560340881348,
|
|
"epoch": 0.2732949087415946,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004996448378033507,
|
|
"loss": 5.4551,
|
|
"mean_token_accuracy": 0.17746061682701111,
|
|
"num_tokens": 6542588.0,
|
|
"step": 2845
|
|
},
|
|
{
|
|
"entropy": 5.786451196670532,
|
|
"epoch": 0.2737752161383285,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004996429096601532,
|
|
"loss": 5.6517,
|
|
"mean_token_accuracy": 0.16629489734768868,
|
|
"num_tokens": 6554002.0,
|
|
"step": 2850
|
|
},
|
|
{
|
|
"entropy": 5.8046431064605715,
|
|
"epoch": 0.27425552353506244,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004996409763014144,
|
|
"loss": 5.6878,
|
|
"mean_token_accuracy": 0.17579563558101655,
|
|
"num_tokens": 6563358.0,
|
|
"step": 2855
|
|
},
|
|
{
|
|
"entropy": 5.70266695022583,
|
|
"epoch": 0.2747358309317964,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004996390377271791,
|
|
"loss": 5.597,
|
|
"mean_token_accuracy": 0.17393501996994018,
|
|
"num_tokens": 6574986.0,
|
|
"step": 2860
|
|
},
|
|
{
|
|
"entropy": 5.694790029525757,
|
|
"epoch": 0.27521613832853026,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004996370939374924,
|
|
"loss": 5.5337,
|
|
"mean_token_accuracy": 0.17862565964460372,
|
|
"num_tokens": 6587407.0,
|
|
"step": 2865
|
|
},
|
|
{
|
|
"entropy": 5.679986953735352,
|
|
"epoch": 0.2756964457252642,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004996351449323994,
|
|
"loss": 5.4914,
|
|
"mean_token_accuracy": 0.18411503434181214,
|
|
"num_tokens": 6598483.0,
|
|
"step": 2870
|
|
},
|
|
{
|
|
"entropy": 5.684548234939575,
|
|
"epoch": 0.2761767531219981,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004996331907119455,
|
|
"loss": 5.5874,
|
|
"mean_token_accuracy": 0.18107069432735443,
|
|
"num_tokens": 6610749.0,
|
|
"step": 2875
|
|
},
|
|
{
|
|
"entropy": 5.7515064716339115,
|
|
"epoch": 0.276657060518732,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004996312312761758,
|
|
"loss": 5.5523,
|
|
"mean_token_accuracy": 0.1702647790312767,
|
|
"num_tokens": 6621762.0,
|
|
"step": 2880
|
|
},
|
|
{
|
|
"entropy": 5.740266036987305,
|
|
"epoch": 0.2771373679154659,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000499629266625136,
|
|
"loss": 5.6195,
|
|
"mean_token_accuracy": 0.1732449159026146,
|
|
"num_tokens": 6632296.0,
|
|
"step": 2885
|
|
},
|
|
{
|
|
"entropy": 5.732256841659546,
|
|
"epoch": 0.27761767531219983,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004996272967588715,
|
|
"loss": 5.5649,
|
|
"mean_token_accuracy": 0.18136372566223144,
|
|
"num_tokens": 6644413.0,
|
|
"step": 2890
|
|
},
|
|
{
|
|
"entropy": 5.668825292587281,
|
|
"epoch": 0.2780979827089337,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004996253216774283,
|
|
"loss": 5.5148,
|
|
"mean_token_accuracy": 0.18241942077875137,
|
|
"num_tokens": 6655634.0,
|
|
"step": 2895
|
|
},
|
|
{
|
|
"entropy": 5.68368968963623,
|
|
"epoch": 0.27857829010566765,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004996233413808521,
|
|
"loss": 5.4722,
|
|
"mean_token_accuracy": 0.18518155813217163,
|
|
"num_tokens": 6665977.0,
|
|
"step": 2900
|
|
},
|
|
{
|
|
"entropy": 5.742200183868408,
|
|
"epoch": 0.27905859750240153,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004996213558691889,
|
|
"loss": 5.5236,
|
|
"mean_token_accuracy": 0.17702546864748,
|
|
"num_tokens": 6677165.0,
|
|
"step": 2905
|
|
},
|
|
{
|
|
"entropy": 5.718938302993775,
|
|
"epoch": 0.27953890489913547,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004996193651424848,
|
|
"loss": 5.6368,
|
|
"mean_token_accuracy": 0.1747002512216568,
|
|
"num_tokens": 6688182.0,
|
|
"step": 2910
|
|
},
|
|
{
|
|
"entropy": 5.719934892654419,
|
|
"epoch": 0.28001921229586935,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000499617369200786,
|
|
"loss": 5.5332,
|
|
"mean_token_accuracy": 0.1799617737531662,
|
|
"num_tokens": 6699259.0,
|
|
"step": 2915
|
|
},
|
|
{
|
|
"entropy": 5.722778844833374,
|
|
"epoch": 0.2804995196926033,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004996153680441389,
|
|
"loss": 5.5587,
|
|
"mean_token_accuracy": 0.1818137377500534,
|
|
"num_tokens": 6710071.0,
|
|
"step": 2920
|
|
},
|
|
{
|
|
"entropy": 5.74660005569458,
|
|
"epoch": 0.28097982708933716,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00049961336167259,
|
|
"loss": 5.5901,
|
|
"mean_token_accuracy": 0.18049627989530564,
|
|
"num_tokens": 6720267.0,
|
|
"step": 2925
|
|
},
|
|
{
|
|
"entropy": 5.77274603843689,
|
|
"epoch": 0.2814601344860711,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004996113500861857,
|
|
"loss": 5.5781,
|
|
"mean_token_accuracy": 0.17617071717977523,
|
|
"num_tokens": 6730919.0,
|
|
"step": 2930
|
|
},
|
|
{
|
|
"entropy": 5.648800373077393,
|
|
"epoch": 0.281940441882805,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004996093332849729,
|
|
"loss": 5.5655,
|
|
"mean_token_accuracy": 0.18327539116144181,
|
|
"num_tokens": 6741480.0,
|
|
"step": 2935
|
|
},
|
|
{
|
|
"entropy": 5.748388051986694,
|
|
"epoch": 0.2824207492795389,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004996073112689983,
|
|
"loss": 5.5065,
|
|
"mean_token_accuracy": 0.18213073313236236,
|
|
"num_tokens": 6751816.0,
|
|
"step": 2940
|
|
},
|
|
{
|
|
"entropy": 5.665603494644165,
|
|
"epoch": 0.2829010566762728,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004996052840383088,
|
|
"loss": 5.5378,
|
|
"mean_token_accuracy": 0.18160058706998825,
|
|
"num_tokens": 6763645.0,
|
|
"step": 2945
|
|
},
|
|
{
|
|
"entropy": 5.678023004531861,
|
|
"epoch": 0.28338136407300674,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004996032515929516,
|
|
"loss": 5.5128,
|
|
"mean_token_accuracy": 0.18091680556535722,
|
|
"num_tokens": 6774795.0,
|
|
"step": 2950
|
|
},
|
|
{
|
|
"entropy": 5.664436340332031,
|
|
"epoch": 0.2838616714697406,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004996012139329738,
|
|
"loss": 5.4312,
|
|
"mean_token_accuracy": 0.18459193110466005,
|
|
"num_tokens": 6786833.0,
|
|
"step": 2955
|
|
},
|
|
{
|
|
"entropy": 5.591051626205444,
|
|
"epoch": 0.28434197886647455,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004995991710584228,
|
|
"loss": 5.4431,
|
|
"mean_token_accuracy": 0.18741845786571504,
|
|
"num_tokens": 6798134.0,
|
|
"step": 2960
|
|
},
|
|
{
|
|
"entropy": 5.7143707275390625,
|
|
"epoch": 0.28482228626320844,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004995971229693459,
|
|
"loss": 5.564,
|
|
"mean_token_accuracy": 0.18205250948667526,
|
|
"num_tokens": 6807918.0,
|
|
"step": 2965
|
|
},
|
|
{
|
|
"entropy": 5.700773429870606,
|
|
"epoch": 0.28530259365994237,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004995950696657909,
|
|
"loss": 5.6352,
|
|
"mean_token_accuracy": 0.17493324726819992,
|
|
"num_tokens": 6818689.0,
|
|
"step": 2970
|
|
},
|
|
{
|
|
"entropy": 5.689798498153687,
|
|
"epoch": 0.28578290105667625,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004995930111478051,
|
|
"loss": 5.4959,
|
|
"mean_token_accuracy": 0.18560752868652344,
|
|
"num_tokens": 6830871.0,
|
|
"step": 2975
|
|
},
|
|
{
|
|
"entropy": 5.646875667572021,
|
|
"epoch": 0.2862632084534102,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004995909474154365,
|
|
"loss": 5.486,
|
|
"mean_token_accuracy": 0.18816983848810195,
|
|
"num_tokens": 6842857.0,
|
|
"step": 2980
|
|
},
|
|
{
|
|
"entropy": 5.6857727527618405,
|
|
"epoch": 0.28674351585014407,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004995888784687331,
|
|
"loss": 5.5149,
|
|
"mean_token_accuracy": 0.1798010364174843,
|
|
"num_tokens": 6853727.0,
|
|
"step": 2985
|
|
},
|
|
{
|
|
"entropy": 5.747433519363403,
|
|
"epoch": 0.287223823246878,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004995868043077428,
|
|
"loss": 5.5493,
|
|
"mean_token_accuracy": 0.18155408054590225,
|
|
"num_tokens": 6864728.0,
|
|
"step": 2990
|
|
},
|
|
{
|
|
"entropy": 5.74623293876648,
|
|
"epoch": 0.2877041306436119,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004995847249325137,
|
|
"loss": 5.6145,
|
|
"mean_token_accuracy": 0.17592370361089707,
|
|
"num_tokens": 6875001.0,
|
|
"step": 2995
|
|
},
|
|
{
|
|
"entropy": 5.656736660003662,
|
|
"epoch": 0.2881844380403458,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004995826403430942,
|
|
"loss": 5.4857,
|
|
"mean_token_accuracy": 0.1892928287386894,
|
|
"num_tokens": 6887026.0,
|
|
"step": 3000
|
|
},
|
|
{
|
|
"epoch": 0.2881844380403458,
|
|
"eval_entropy": 5.517254452656561,
|
|
"eval_loss": 5.54893159866333,
|
|
"eval_mean_token_accuracy": 0.18836901158363223,
|
|
"eval_num_tokens": 6887026.0,
|
|
"eval_runtime": 20.6637,
|
|
"eval_samples_per_second": 1588.05,
|
|
"eval_steps_per_second": 198.512,
|
|
"step": 3000
|
|
}
|
|
],
|
|
"logging_steps": 5,
|
|
"max_steps": 104090,
|
|
"num_input_tokens_seen": 0,
|
|
"num_train_epochs": 10,
|
|
"save_steps": 3000,
|
|
"stateful_callbacks": {
|
|
"TrainerControl": {
|
|
"args": {
|
|
"should_epoch_stop": false,
|
|
"should_evaluate": false,
|
|
"should_log": false,
|
|
"should_save": true,
|
|
"should_training_stop": false
|
|
},
|
|
"attributes": {}
|
|
}
|
|
},
|
|
"total_flos": 1569715698401280.0,
|
|
"train_batch_size": 16,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|