48123 lines
1.3 MiB
48123 lines
1.3 MiB
{
|
|
"best_global_step": null,
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 2.6954568428146235,
|
|
"eval_steps": 3000,
|
|
"global_step": 24000,
|
|
"is_hyper_param_search": false,
|
|
"is_local_process_zero": true,
|
|
"is_world_process_zero": true,
|
|
"log_history": [
|
|
{
|
|
"entropy": 10.691954421997071,
|
|
"epoch": 0.0005615769079575448,
|
|
"grad_norm": 13.75,
|
|
"learning_rate": 2e-06,
|
|
"loss": 10.8494,
|
|
"mean_token_accuracy": 0.0,
|
|
"num_tokens": 10897.0,
|
|
"step": 5
|
|
},
|
|
{
|
|
"entropy": 10.692028713226318,
|
|
"epoch": 0.0011231538159150896,
|
|
"grad_norm": 13.375,
|
|
"learning_rate": 4.5e-06,
|
|
"loss": 10.783,
|
|
"mean_token_accuracy": 7.102272938936949e-05,
|
|
"num_tokens": 23084.0,
|
|
"step": 10
|
|
},
|
|
{
|
|
"entropy": 10.69119052886963,
|
|
"epoch": 0.0016847307238726343,
|
|
"grad_norm": 10.5,
|
|
"learning_rate": 7e-06,
|
|
"loss": 10.5147,
|
|
"mean_token_accuracy": 0.01880119484849274,
|
|
"num_tokens": 35810.0,
|
|
"step": 15
|
|
},
|
|
{
|
|
"entropy": 10.683763885498047,
|
|
"epoch": 0.0022463076318301792,
|
|
"grad_norm": 6.15625,
|
|
"learning_rate": 9.5e-06,
|
|
"loss": 10.1375,
|
|
"mean_token_accuracy": 0.03672755789011717,
|
|
"num_tokens": 46019.0,
|
|
"step": 20
|
|
},
|
|
{
|
|
"entropy": 10.640995311737061,
|
|
"epoch": 0.002807884539787724,
|
|
"grad_norm": 4.375,
|
|
"learning_rate": 1.2e-05,
|
|
"loss": 9.8065,
|
|
"mean_token_accuracy": 0.0391056377440691,
|
|
"num_tokens": 57272.0,
|
|
"step": 25
|
|
},
|
|
{
|
|
"entropy": 10.578758907318115,
|
|
"epoch": 0.0033694614477452686,
|
|
"grad_norm": 3.28125,
|
|
"learning_rate": 1.4500000000000002e-05,
|
|
"loss": 9.6789,
|
|
"mean_token_accuracy": 0.036402178928256035,
|
|
"num_tokens": 68686.0,
|
|
"step": 30
|
|
},
|
|
{
|
|
"entropy": 10.573095703125,
|
|
"epoch": 0.003931038355702813,
|
|
"grad_norm": 2.90625,
|
|
"learning_rate": 1.7000000000000003e-05,
|
|
"loss": 9.5714,
|
|
"mean_token_accuracy": 0.04141928404569626,
|
|
"num_tokens": 79187.0,
|
|
"step": 35
|
|
},
|
|
{
|
|
"entropy": 10.575594806671143,
|
|
"epoch": 0.0044926152636603585,
|
|
"grad_norm": 2.75,
|
|
"learning_rate": 1.95e-05,
|
|
"loss": 9.5576,
|
|
"mean_token_accuracy": 0.044133822247385976,
|
|
"num_tokens": 90293.0,
|
|
"step": 40
|
|
},
|
|
{
|
|
"entropy": 10.556080150604249,
|
|
"epoch": 0.005054192171617903,
|
|
"grad_norm": 2.578125,
|
|
"learning_rate": 2.2e-05,
|
|
"loss": 9.4673,
|
|
"mean_token_accuracy": 0.04080899097025394,
|
|
"num_tokens": 100420.0,
|
|
"step": 45
|
|
},
|
|
{
|
|
"entropy": 10.538790798187256,
|
|
"epoch": 0.005615769079575448,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 2.4500000000000003e-05,
|
|
"loss": 9.4858,
|
|
"mean_token_accuracy": 0.03646625243127346,
|
|
"num_tokens": 111198.0,
|
|
"step": 50
|
|
},
|
|
{
|
|
"entropy": 10.547248840332031,
|
|
"epoch": 0.006177345987532993,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 2.7e-05,
|
|
"loss": 9.3988,
|
|
"mean_token_accuracy": 0.05780095718801022,
|
|
"num_tokens": 124723.0,
|
|
"step": 55
|
|
},
|
|
{
|
|
"entropy": 10.461988258361817,
|
|
"epoch": 0.006738922895490537,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 2.95e-05,
|
|
"loss": 9.2587,
|
|
"mean_token_accuracy": 0.061974577233195306,
|
|
"num_tokens": 136366.0,
|
|
"step": 60
|
|
},
|
|
{
|
|
"entropy": 10.363299369812012,
|
|
"epoch": 0.007300499803448083,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 3.2e-05,
|
|
"loss": 9.1817,
|
|
"mean_token_accuracy": 0.06283607967197895,
|
|
"num_tokens": 146536.0,
|
|
"step": 65
|
|
},
|
|
{
|
|
"entropy": 10.396018791198731,
|
|
"epoch": 0.007862076711405626,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 3.4500000000000005e-05,
|
|
"loss": 9.097,
|
|
"mean_token_accuracy": 0.0707736562937498,
|
|
"num_tokens": 157005.0,
|
|
"step": 70
|
|
},
|
|
{
|
|
"entropy": 10.386055850982666,
|
|
"epoch": 0.008423653619363172,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 3.7e-05,
|
|
"loss": 9.017,
|
|
"mean_token_accuracy": 0.07136933580040931,
|
|
"num_tokens": 167864.0,
|
|
"step": 75
|
|
},
|
|
{
|
|
"entropy": 10.352816581726074,
|
|
"epoch": 0.008985230527320717,
|
|
"grad_norm": 2.5625,
|
|
"learning_rate": 3.95e-05,
|
|
"loss": 8.9484,
|
|
"mean_token_accuracy": 0.06433885768055916,
|
|
"num_tokens": 179635.0,
|
|
"step": 80
|
|
},
|
|
{
|
|
"entropy": 10.24338674545288,
|
|
"epoch": 0.00954680743527826,
|
|
"grad_norm": 2.671875,
|
|
"learning_rate": 4.2000000000000004e-05,
|
|
"loss": 8.8572,
|
|
"mean_token_accuracy": 0.07211834266781807,
|
|
"num_tokens": 190614.0,
|
|
"step": 85
|
|
},
|
|
{
|
|
"entropy": 10.245021152496339,
|
|
"epoch": 0.010108384343235806,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 4.45e-05,
|
|
"loss": 8.7198,
|
|
"mean_token_accuracy": 0.07616456523537636,
|
|
"num_tokens": 201496.0,
|
|
"step": 90
|
|
},
|
|
{
|
|
"entropy": 10.094779968261719,
|
|
"epoch": 0.010669961251193351,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 4.7000000000000004e-05,
|
|
"loss": 8.6055,
|
|
"mean_token_accuracy": 0.0780682846903801,
|
|
"num_tokens": 211606.0,
|
|
"step": 95
|
|
},
|
|
{
|
|
"entropy": 10.115865230560303,
|
|
"epoch": 0.011231538159150897,
|
|
"grad_norm": 2.625,
|
|
"learning_rate": 4.9500000000000004e-05,
|
|
"loss": 8.4856,
|
|
"mean_token_accuracy": 0.07667104676365852,
|
|
"num_tokens": 223503.0,
|
|
"step": 100
|
|
},
|
|
{
|
|
"entropy": 10.032721042633057,
|
|
"epoch": 0.01179311506710844,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 5.2e-05,
|
|
"loss": 8.4196,
|
|
"mean_token_accuracy": 0.0808894768357277,
|
|
"num_tokens": 234744.0,
|
|
"step": 105
|
|
},
|
|
{
|
|
"entropy": 9.90083703994751,
|
|
"epoch": 0.012354691975065986,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 5.45e-05,
|
|
"loss": 8.3419,
|
|
"mean_token_accuracy": 0.08203728273510932,
|
|
"num_tokens": 247663.0,
|
|
"step": 110
|
|
},
|
|
{
|
|
"entropy": 9.945332717895507,
|
|
"epoch": 0.012916268883023531,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 5.7e-05,
|
|
"loss": 8.2013,
|
|
"mean_token_accuracy": 0.08452324643731117,
|
|
"num_tokens": 260326.0,
|
|
"step": 115
|
|
},
|
|
{
|
|
"entropy": 9.736694145202637,
|
|
"epoch": 0.013477845790981074,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 5.9499999999999996e-05,
|
|
"loss": 8.0563,
|
|
"mean_token_accuracy": 0.0793469488620758,
|
|
"num_tokens": 271568.0,
|
|
"step": 120
|
|
},
|
|
{
|
|
"entropy": 9.62724199295044,
|
|
"epoch": 0.01403942269893862,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 6.2e-05,
|
|
"loss": 7.8825,
|
|
"mean_token_accuracy": 0.08820232152938842,
|
|
"num_tokens": 282651.0,
|
|
"step": 125
|
|
},
|
|
{
|
|
"entropy": 9.494030666351318,
|
|
"epoch": 0.014600999606896165,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 6.450000000000001e-05,
|
|
"loss": 7.719,
|
|
"mean_token_accuracy": 0.08837165534496308,
|
|
"num_tokens": 292753.0,
|
|
"step": 130
|
|
},
|
|
{
|
|
"entropy": 9.272327136993407,
|
|
"epoch": 0.015162576514853709,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 6.7e-05,
|
|
"loss": 7.7167,
|
|
"mean_token_accuracy": 0.0898565836250782,
|
|
"num_tokens": 302981.0,
|
|
"step": 135
|
|
},
|
|
{
|
|
"entropy": 9.16934871673584,
|
|
"epoch": 0.015724153422811252,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 6.950000000000001e-05,
|
|
"loss": 7.6775,
|
|
"mean_token_accuracy": 0.08807501792907715,
|
|
"num_tokens": 314461.0,
|
|
"step": 140
|
|
},
|
|
{
|
|
"entropy": 8.914916038513184,
|
|
"epoch": 0.0162857303307688,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 7.2e-05,
|
|
"loss": 7.6052,
|
|
"mean_token_accuracy": 0.09032118767499923,
|
|
"num_tokens": 326877.0,
|
|
"step": 145
|
|
},
|
|
{
|
|
"entropy": 8.733859825134278,
|
|
"epoch": 0.016847307238726343,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 7.45e-05,
|
|
"loss": 7.3998,
|
|
"mean_token_accuracy": 0.09276190958917141,
|
|
"num_tokens": 337831.0,
|
|
"step": 150
|
|
},
|
|
{
|
|
"entropy": 8.528983402252198,
|
|
"epoch": 0.017408884146683887,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 7.7e-05,
|
|
"loss": 7.337,
|
|
"mean_token_accuracy": 0.09177347123622895,
|
|
"num_tokens": 348233.0,
|
|
"step": 155
|
|
},
|
|
{
|
|
"entropy": 8.35361089706421,
|
|
"epoch": 0.017970461054641434,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 7.950000000000001e-05,
|
|
"loss": 7.2213,
|
|
"mean_token_accuracy": 0.09552499204874039,
|
|
"num_tokens": 359113.0,
|
|
"step": 160
|
|
},
|
|
{
|
|
"entropy": 8.23711051940918,
|
|
"epoch": 0.018532037962598977,
|
|
"grad_norm": 2.703125,
|
|
"learning_rate": 8.2e-05,
|
|
"loss": 7.336,
|
|
"mean_token_accuracy": 0.10098176226019859,
|
|
"num_tokens": 370284.0,
|
|
"step": 165
|
|
},
|
|
{
|
|
"entropy": 8.123040294647216,
|
|
"epoch": 0.01909361487055652,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 8.450000000000001e-05,
|
|
"loss": 7.3538,
|
|
"mean_token_accuracy": 0.08904306292533874,
|
|
"num_tokens": 381415.0,
|
|
"step": 170
|
|
},
|
|
{
|
|
"entropy": 7.9991672992706295,
|
|
"epoch": 0.019655191778514068,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 8.7e-05,
|
|
"loss": 7.2764,
|
|
"mean_token_accuracy": 0.09914608523249627,
|
|
"num_tokens": 392080.0,
|
|
"step": 175
|
|
},
|
|
{
|
|
"entropy": 7.944419240951538,
|
|
"epoch": 0.020216768686471612,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 8.95e-05,
|
|
"loss": 7.2597,
|
|
"mean_token_accuracy": 0.09534113705158234,
|
|
"num_tokens": 402551.0,
|
|
"step": 180
|
|
},
|
|
{
|
|
"entropy": 7.984531497955322,
|
|
"epoch": 0.020778345594429155,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 9.2e-05,
|
|
"loss": 7.2418,
|
|
"mean_token_accuracy": 0.09288135915994644,
|
|
"num_tokens": 414670.0,
|
|
"step": 185
|
|
},
|
|
{
|
|
"entropy": 7.863457107543946,
|
|
"epoch": 0.021339922502386702,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 9.45e-05,
|
|
"loss": 7.2269,
|
|
"mean_token_accuracy": 0.09570453688502312,
|
|
"num_tokens": 427162.0,
|
|
"step": 190
|
|
},
|
|
{
|
|
"entropy": 7.844120883941651,
|
|
"epoch": 0.021901499410344246,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 9.7e-05,
|
|
"loss": 7.125,
|
|
"mean_token_accuracy": 0.09662900492548943,
|
|
"num_tokens": 438628.0,
|
|
"step": 195
|
|
},
|
|
{
|
|
"entropy": 7.827740716934204,
|
|
"epoch": 0.022463076318301793,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 9.95e-05,
|
|
"loss": 7.0534,
|
|
"mean_token_accuracy": 0.10476038753986358,
|
|
"num_tokens": 449248.0,
|
|
"step": 200
|
|
},
|
|
{
|
|
"entropy": 7.613120603561401,
|
|
"epoch": 0.023024653226259337,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000102,
|
|
"loss": 7.0291,
|
|
"mean_token_accuracy": 0.10421562120318413,
|
|
"num_tokens": 460815.0,
|
|
"step": 205
|
|
},
|
|
{
|
|
"entropy": 7.653258895874023,
|
|
"epoch": 0.02358623013421688,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00010449999999999999,
|
|
"loss": 7.1939,
|
|
"mean_token_accuracy": 0.09638625457882881,
|
|
"num_tokens": 471972.0,
|
|
"step": 210
|
|
},
|
|
{
|
|
"entropy": 7.694521474838257,
|
|
"epoch": 0.024147807042174427,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000107,
|
|
"loss": 7.1589,
|
|
"mean_token_accuracy": 0.1014483891427517,
|
|
"num_tokens": 482775.0,
|
|
"step": 215
|
|
},
|
|
{
|
|
"entropy": 7.650409984588623,
|
|
"epoch": 0.02470938395013197,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0001095,
|
|
"loss": 7.087,
|
|
"mean_token_accuracy": 0.10187960937619209,
|
|
"num_tokens": 495151.0,
|
|
"step": 220
|
|
},
|
|
{
|
|
"entropy": 7.605823087692261,
|
|
"epoch": 0.025270960858089515,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.000112,
|
|
"loss": 7.0608,
|
|
"mean_token_accuracy": 0.10176030248403549,
|
|
"num_tokens": 506947.0,
|
|
"step": 225
|
|
},
|
|
{
|
|
"entropy": 7.604726552963257,
|
|
"epoch": 0.025832537766047062,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0001145,
|
|
"loss": 7.0892,
|
|
"mean_token_accuracy": 0.10170613378286361,
|
|
"num_tokens": 519153.0,
|
|
"step": 230
|
|
},
|
|
{
|
|
"entropy": 7.570750951766968,
|
|
"epoch": 0.026394114674004605,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00011700000000000001,
|
|
"loss": 7.07,
|
|
"mean_token_accuracy": 0.10081414431333542,
|
|
"num_tokens": 531050.0,
|
|
"step": 235
|
|
},
|
|
{
|
|
"entropy": 7.4688334465026855,
|
|
"epoch": 0.02695569158196215,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00011949999999999999,
|
|
"loss": 7.006,
|
|
"mean_token_accuracy": 0.10289591774344445,
|
|
"num_tokens": 542744.0,
|
|
"step": 240
|
|
},
|
|
{
|
|
"entropy": 7.563732862472534,
|
|
"epoch": 0.027517268489919696,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.000122,
|
|
"loss": 7.0923,
|
|
"mean_token_accuracy": 0.0983924463391304,
|
|
"num_tokens": 554748.0,
|
|
"step": 245
|
|
},
|
|
{
|
|
"entropy": 7.534366416931152,
|
|
"epoch": 0.02807884539787724,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0001245,
|
|
"loss": 7.0106,
|
|
"mean_token_accuracy": 0.10552474185824394,
|
|
"num_tokens": 564868.0,
|
|
"step": 250
|
|
},
|
|
{
|
|
"entropy": 7.530099248886108,
|
|
"epoch": 0.028640422305834783,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.000127,
|
|
"loss": 7.0091,
|
|
"mean_token_accuracy": 0.11061361208558082,
|
|
"num_tokens": 575668.0,
|
|
"step": 255
|
|
},
|
|
{
|
|
"entropy": 7.455753898620605,
|
|
"epoch": 0.02920199921379233,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0001295,
|
|
"loss": 7.1352,
|
|
"mean_token_accuracy": 0.10184136554598808,
|
|
"num_tokens": 587956.0,
|
|
"step": 260
|
|
},
|
|
{
|
|
"entropy": 7.4932270526885985,
|
|
"epoch": 0.029763576121749874,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.000132,
|
|
"loss": 6.9785,
|
|
"mean_token_accuracy": 0.10903615280985832,
|
|
"num_tokens": 598246.0,
|
|
"step": 265
|
|
},
|
|
{
|
|
"entropy": 7.416919708251953,
|
|
"epoch": 0.030325153029707418,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00013450000000000002,
|
|
"loss": 7.1108,
|
|
"mean_token_accuracy": 0.10414381325244904,
|
|
"num_tokens": 610628.0,
|
|
"step": 270
|
|
},
|
|
{
|
|
"entropy": 7.3690831661224365,
|
|
"epoch": 0.030886729937664965,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00013700000000000002,
|
|
"loss": 6.8616,
|
|
"mean_token_accuracy": 0.1097691647708416,
|
|
"num_tokens": 621214.0,
|
|
"step": 275
|
|
},
|
|
{
|
|
"entropy": 7.360501384735107,
|
|
"epoch": 0.031448306845622505,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0001395,
|
|
"loss": 6.957,
|
|
"mean_token_accuracy": 0.1151120163500309,
|
|
"num_tokens": 631123.0,
|
|
"step": 280
|
|
},
|
|
{
|
|
"entropy": 7.397417736053467,
|
|
"epoch": 0.032009883753580055,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00014199999999999998,
|
|
"loss": 6.9474,
|
|
"mean_token_accuracy": 0.10703005790710449,
|
|
"num_tokens": 643434.0,
|
|
"step": 285
|
|
},
|
|
{
|
|
"entropy": 7.342480707168579,
|
|
"epoch": 0.0325714606615376,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0001445,
|
|
"loss": 6.9321,
|
|
"mean_token_accuracy": 0.11211270317435265,
|
|
"num_tokens": 655336.0,
|
|
"step": 290
|
|
},
|
|
{
|
|
"entropy": 7.372163486480713,
|
|
"epoch": 0.03313303756949514,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.000147,
|
|
"loss": 6.9245,
|
|
"mean_token_accuracy": 0.10963715985417366,
|
|
"num_tokens": 666591.0,
|
|
"step": 295
|
|
},
|
|
{
|
|
"entropy": 7.286645698547363,
|
|
"epoch": 0.033694614477452686,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0001495,
|
|
"loss": 6.9458,
|
|
"mean_token_accuracy": 0.10590762570500374,
|
|
"num_tokens": 678288.0,
|
|
"step": 300
|
|
},
|
|
{
|
|
"entropy": 7.292938613891602,
|
|
"epoch": 0.03425619138541023,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000152,
|
|
"loss": 6.8788,
|
|
"mean_token_accuracy": 0.11080723032355308,
|
|
"num_tokens": 688526.0,
|
|
"step": 305
|
|
},
|
|
{
|
|
"entropy": 7.20158314704895,
|
|
"epoch": 0.03481776829336777,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00015450000000000001,
|
|
"loss": 6.7955,
|
|
"mean_token_accuracy": 0.12063507586717606,
|
|
"num_tokens": 698727.0,
|
|
"step": 310
|
|
},
|
|
{
|
|
"entropy": 7.281469917297363,
|
|
"epoch": 0.035379345201325324,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.000157,
|
|
"loss": 6.8411,
|
|
"mean_token_accuracy": 0.1111941859126091,
|
|
"num_tokens": 710042.0,
|
|
"step": 315
|
|
},
|
|
{
|
|
"entropy": 7.2135881900787355,
|
|
"epoch": 0.03594092210928287,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0001595,
|
|
"loss": 6.7838,
|
|
"mean_token_accuracy": 0.11598038524389268,
|
|
"num_tokens": 721390.0,
|
|
"step": 320
|
|
},
|
|
{
|
|
"entropy": 7.166607904434204,
|
|
"epoch": 0.03650249901724041,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.000162,
|
|
"loss": 6.9676,
|
|
"mean_token_accuracy": 0.11324010118842125,
|
|
"num_tokens": 732949.0,
|
|
"step": 325
|
|
},
|
|
{
|
|
"entropy": 7.382533311843872,
|
|
"epoch": 0.037064075925197955,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00016450000000000001,
|
|
"loss": 6.983,
|
|
"mean_token_accuracy": 0.11112697571516036,
|
|
"num_tokens": 744943.0,
|
|
"step": 330
|
|
},
|
|
{
|
|
"entropy": 7.1175624370574955,
|
|
"epoch": 0.0376256528331555,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00016700000000000002,
|
|
"loss": 6.7549,
|
|
"mean_token_accuracy": 0.11743907704949379,
|
|
"num_tokens": 756579.0,
|
|
"step": 335
|
|
},
|
|
{
|
|
"entropy": 7.059293413162232,
|
|
"epoch": 0.03818722974111304,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00016950000000000003,
|
|
"loss": 6.7064,
|
|
"mean_token_accuracy": 0.11693573296070099,
|
|
"num_tokens": 767260.0,
|
|
"step": 340
|
|
},
|
|
{
|
|
"entropy": 7.129382991790772,
|
|
"epoch": 0.03874880664907059,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00017199999999999998,
|
|
"loss": 6.8055,
|
|
"mean_token_accuracy": 0.11503136828541756,
|
|
"num_tokens": 778163.0,
|
|
"step": 345
|
|
},
|
|
{
|
|
"entropy": 7.21411828994751,
|
|
"epoch": 0.039310383557028136,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00017449999999999999,
|
|
"loss": 6.841,
|
|
"mean_token_accuracy": 0.11127241551876069,
|
|
"num_tokens": 788912.0,
|
|
"step": 350
|
|
},
|
|
{
|
|
"entropy": 7.170050191879272,
|
|
"epoch": 0.03987196046498568,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000177,
|
|
"loss": 6.9508,
|
|
"mean_token_accuracy": 0.1135722354054451,
|
|
"num_tokens": 801405.0,
|
|
"step": 355
|
|
},
|
|
{
|
|
"entropy": 7.058458709716797,
|
|
"epoch": 0.040433537372943223,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0001795,
|
|
"loss": 6.7437,
|
|
"mean_token_accuracy": 0.11591695919632912,
|
|
"num_tokens": 813023.0,
|
|
"step": 360
|
|
},
|
|
{
|
|
"entropy": 7.132532978057862,
|
|
"epoch": 0.04099511428090077,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000182,
|
|
"loss": 6.7692,
|
|
"mean_token_accuracy": 0.1168873094022274,
|
|
"num_tokens": 823993.0,
|
|
"step": 365
|
|
},
|
|
{
|
|
"entropy": 7.123906469345092,
|
|
"epoch": 0.04155669118885831,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0001845,
|
|
"loss": 6.8202,
|
|
"mean_token_accuracy": 0.1134017400443554,
|
|
"num_tokens": 836642.0,
|
|
"step": 370
|
|
},
|
|
{
|
|
"entropy": 7.020151281356812,
|
|
"epoch": 0.04211826809681586,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000187,
|
|
"loss": 6.6249,
|
|
"mean_token_accuracy": 0.12558069303631783,
|
|
"num_tokens": 847475.0,
|
|
"step": 375
|
|
},
|
|
{
|
|
"entropy": 7.032984447479248,
|
|
"epoch": 0.042679845004773405,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0001895,
|
|
"loss": 6.6947,
|
|
"mean_token_accuracy": 0.12115299850702285,
|
|
"num_tokens": 857949.0,
|
|
"step": 380
|
|
},
|
|
{
|
|
"entropy": 7.027848196029663,
|
|
"epoch": 0.04324142191273095,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000192,
|
|
"loss": 6.7528,
|
|
"mean_token_accuracy": 0.11466690823435784,
|
|
"num_tokens": 868661.0,
|
|
"step": 385
|
|
},
|
|
{
|
|
"entropy": 7.095096111297607,
|
|
"epoch": 0.04380299882068849,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0001945,
|
|
"loss": 6.7906,
|
|
"mean_token_accuracy": 0.11758541241288185,
|
|
"num_tokens": 879651.0,
|
|
"step": 390
|
|
},
|
|
{
|
|
"entropy": 7.0685296058654785,
|
|
"epoch": 0.044364575728646036,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00019700000000000002,
|
|
"loss": 6.7722,
|
|
"mean_token_accuracy": 0.10885974839329719,
|
|
"num_tokens": 891189.0,
|
|
"step": 395
|
|
},
|
|
{
|
|
"entropy": 6.994202566146851,
|
|
"epoch": 0.044926152636603586,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00019950000000000002,
|
|
"loss": 6.6748,
|
|
"mean_token_accuracy": 0.119440957903862,
|
|
"num_tokens": 902915.0,
|
|
"step": 400
|
|
},
|
|
{
|
|
"entropy": 7.045473241806031,
|
|
"epoch": 0.04548772954456113,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.000202,
|
|
"loss": 6.7649,
|
|
"mean_token_accuracy": 0.11777753084897995,
|
|
"num_tokens": 914108.0,
|
|
"step": 405
|
|
},
|
|
{
|
|
"entropy": 7.049249458312988,
|
|
"epoch": 0.046049306452518673,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00020449999999999998,
|
|
"loss": 6.7918,
|
|
"mean_token_accuracy": 0.11295270174741745,
|
|
"num_tokens": 925729.0,
|
|
"step": 410
|
|
},
|
|
{
|
|
"entropy": 7.0732354640960695,
|
|
"epoch": 0.04661088336047622,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.000207,
|
|
"loss": 6.7993,
|
|
"mean_token_accuracy": 0.11720411777496338,
|
|
"num_tokens": 936912.0,
|
|
"step": 415
|
|
},
|
|
{
|
|
"entropy": 6.98739104270935,
|
|
"epoch": 0.04717246026843376,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0002095,
|
|
"loss": 6.7739,
|
|
"mean_token_accuracy": 0.11668220460414887,
|
|
"num_tokens": 948576.0,
|
|
"step": 420
|
|
},
|
|
{
|
|
"entropy": 6.989003896713257,
|
|
"epoch": 0.047734037176391304,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000212,
|
|
"loss": 6.6228,
|
|
"mean_token_accuracy": 0.12309176921844482,
|
|
"num_tokens": 959346.0,
|
|
"step": 425
|
|
},
|
|
{
|
|
"entropy": 6.867386531829834,
|
|
"epoch": 0.048295614084348855,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0002145,
|
|
"loss": 6.6393,
|
|
"mean_token_accuracy": 0.12302001640200615,
|
|
"num_tokens": 970124.0,
|
|
"step": 430
|
|
},
|
|
{
|
|
"entropy": 7.04110198020935,
|
|
"epoch": 0.0488571909923064,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00021700000000000002,
|
|
"loss": 6.7167,
|
|
"mean_token_accuracy": 0.12065900415182114,
|
|
"num_tokens": 981628.0,
|
|
"step": 435
|
|
},
|
|
{
|
|
"entropy": 6.839612150192261,
|
|
"epoch": 0.04941876790026394,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0002195,
|
|
"loss": 6.6603,
|
|
"mean_token_accuracy": 0.12483339831233024,
|
|
"num_tokens": 992423.0,
|
|
"step": 440
|
|
},
|
|
{
|
|
"entropy": 7.010668039321899,
|
|
"epoch": 0.049980344808221486,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000222,
|
|
"loss": 6.6703,
|
|
"mean_token_accuracy": 0.11580908223986626,
|
|
"num_tokens": 1002954.0,
|
|
"step": 445
|
|
},
|
|
{
|
|
"entropy": 6.892636823654175,
|
|
"epoch": 0.05054192171617903,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0002245,
|
|
"loss": 6.5524,
|
|
"mean_token_accuracy": 0.12802066281437874,
|
|
"num_tokens": 1013351.0,
|
|
"step": 450
|
|
},
|
|
{
|
|
"entropy": 6.97490382194519,
|
|
"epoch": 0.05110349862413657,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00022700000000000002,
|
|
"loss": 6.6699,
|
|
"mean_token_accuracy": 0.11892755851149558,
|
|
"num_tokens": 1023781.0,
|
|
"step": 455
|
|
},
|
|
{
|
|
"entropy": 7.029914331436157,
|
|
"epoch": 0.051665075532094124,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00022950000000000002,
|
|
"loss": 6.7291,
|
|
"mean_token_accuracy": 0.12224347591400146,
|
|
"num_tokens": 1034565.0,
|
|
"step": 460
|
|
},
|
|
{
|
|
"entropy": 6.768797492980957,
|
|
"epoch": 0.05222665244005167,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00023200000000000003,
|
|
"loss": 6.5403,
|
|
"mean_token_accuracy": 0.12486013248562813,
|
|
"num_tokens": 1045595.0,
|
|
"step": 465
|
|
},
|
|
{
|
|
"entropy": 6.811560869216919,
|
|
"epoch": 0.05278822934800921,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00023449999999999998,
|
|
"loss": 6.5365,
|
|
"mean_token_accuracy": 0.12281112596392632,
|
|
"num_tokens": 1056084.0,
|
|
"step": 470
|
|
},
|
|
{
|
|
"entropy": 6.891090345382691,
|
|
"epoch": 0.053349806255966754,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000237,
|
|
"loss": 6.5832,
|
|
"mean_token_accuracy": 0.12444683387875558,
|
|
"num_tokens": 1067014.0,
|
|
"step": 475
|
|
},
|
|
{
|
|
"entropy": 6.7909644603729244,
|
|
"epoch": 0.0539113831639243,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0002395,
|
|
"loss": 6.549,
|
|
"mean_token_accuracy": 0.1283904306590557,
|
|
"num_tokens": 1078557.0,
|
|
"step": 480
|
|
},
|
|
{
|
|
"entropy": 6.747442579269409,
|
|
"epoch": 0.05447296007188184,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000242,
|
|
"loss": 6.6193,
|
|
"mean_token_accuracy": 0.1250327579677105,
|
|
"num_tokens": 1090541.0,
|
|
"step": 485
|
|
},
|
|
{
|
|
"entropy": 6.929131269454956,
|
|
"epoch": 0.05503453697983939,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0002445,
|
|
"loss": 6.6901,
|
|
"mean_token_accuracy": 0.12543862983584403,
|
|
"num_tokens": 1101851.0,
|
|
"step": 490
|
|
},
|
|
{
|
|
"entropy": 6.778433561325073,
|
|
"epoch": 0.055596113887796936,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.000247,
|
|
"loss": 6.5898,
|
|
"mean_token_accuracy": 0.12135263979434967,
|
|
"num_tokens": 1112728.0,
|
|
"step": 495
|
|
},
|
|
{
|
|
"entropy": 6.916776704788208,
|
|
"epoch": 0.05615769079575448,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0002495,
|
|
"loss": 6.7185,
|
|
"mean_token_accuracy": 0.12112508118152618,
|
|
"num_tokens": 1124537.0,
|
|
"step": 500
|
|
},
|
|
{
|
|
"entropy": 6.7057990550994875,
|
|
"epoch": 0.05671926770371202,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.000252,
|
|
"loss": 6.6177,
|
|
"mean_token_accuracy": 0.11861735060811043,
|
|
"num_tokens": 1135749.0,
|
|
"step": 505
|
|
},
|
|
{
|
|
"entropy": 6.887033128738404,
|
|
"epoch": 0.05728084461166957,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0002545,
|
|
"loss": 6.523,
|
|
"mean_token_accuracy": 0.12177179381251335,
|
|
"num_tokens": 1147597.0,
|
|
"step": 510
|
|
},
|
|
{
|
|
"entropy": 6.736017560958862,
|
|
"epoch": 0.05784242151962711,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000257,
|
|
"loss": 6.483,
|
|
"mean_token_accuracy": 0.13104297444224358,
|
|
"num_tokens": 1158975.0,
|
|
"step": 515
|
|
},
|
|
{
|
|
"entropy": 6.74561619758606,
|
|
"epoch": 0.05840399842758466,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0002595,
|
|
"loss": 6.6127,
|
|
"mean_token_accuracy": 0.12473157271742821,
|
|
"num_tokens": 1170556.0,
|
|
"step": 520
|
|
},
|
|
{
|
|
"entropy": 6.734094333648682,
|
|
"epoch": 0.058965575335542204,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000262,
|
|
"loss": 6.4825,
|
|
"mean_token_accuracy": 0.12628087177872657,
|
|
"num_tokens": 1180757.0,
|
|
"step": 525
|
|
},
|
|
{
|
|
"entropy": 6.786943149566651,
|
|
"epoch": 0.05952715224349975,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00026450000000000003,
|
|
"loss": 6.5112,
|
|
"mean_token_accuracy": 0.12826752737164498,
|
|
"num_tokens": 1192428.0,
|
|
"step": 530
|
|
},
|
|
{
|
|
"entropy": 6.773551893234253,
|
|
"epoch": 0.06008872915145729,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00026700000000000004,
|
|
"loss": 6.5812,
|
|
"mean_token_accuracy": 0.1194170169532299,
|
|
"num_tokens": 1203867.0,
|
|
"step": 535
|
|
},
|
|
{
|
|
"entropy": 6.7591596126556395,
|
|
"epoch": 0.060650306059414835,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00026950000000000005,
|
|
"loss": 6.5734,
|
|
"mean_token_accuracy": 0.1305850028991699,
|
|
"num_tokens": 1214059.0,
|
|
"step": 540
|
|
},
|
|
{
|
|
"entropy": 6.792087364196777,
|
|
"epoch": 0.06121188296737238,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00027200000000000005,
|
|
"loss": 6.6338,
|
|
"mean_token_accuracy": 0.13109224960207938,
|
|
"num_tokens": 1224750.0,
|
|
"step": 545
|
|
},
|
|
{
|
|
"entropy": 6.816738271713257,
|
|
"epoch": 0.06177345987532993,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0002745,
|
|
"loss": 6.7109,
|
|
"mean_token_accuracy": 0.11931365355849266,
|
|
"num_tokens": 1235936.0,
|
|
"step": 550
|
|
},
|
|
{
|
|
"entropy": 6.697342395782471,
|
|
"epoch": 0.06233503678328747,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000277,
|
|
"loss": 6.5229,
|
|
"mean_token_accuracy": 0.12435328289866447,
|
|
"num_tokens": 1247619.0,
|
|
"step": 555
|
|
},
|
|
{
|
|
"entropy": 6.797955465316773,
|
|
"epoch": 0.06289661369124501,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0002795,
|
|
"loss": 6.5973,
|
|
"mean_token_accuracy": 0.12734515964984894,
|
|
"num_tokens": 1258089.0,
|
|
"step": 560
|
|
},
|
|
{
|
|
"entropy": 6.7907819747924805,
|
|
"epoch": 0.06345819059920256,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00028199999999999997,
|
|
"loss": 6.6714,
|
|
"mean_token_accuracy": 0.12250098884105683,
|
|
"num_tokens": 1270727.0,
|
|
"step": 565
|
|
},
|
|
{
|
|
"entropy": 6.718038558959961,
|
|
"epoch": 0.06401976750716011,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0002845,
|
|
"loss": 6.5278,
|
|
"mean_token_accuracy": 0.12575457990169525,
|
|
"num_tokens": 1280886.0,
|
|
"step": 570
|
|
},
|
|
{
|
|
"entropy": 6.816065120697021,
|
|
"epoch": 0.06458134441511765,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000287,
|
|
"loss": 6.5532,
|
|
"mean_token_accuracy": 0.13024218007922173,
|
|
"num_tokens": 1292205.0,
|
|
"step": 575
|
|
},
|
|
{
|
|
"entropy": 6.724169111251831,
|
|
"epoch": 0.0651429213230752,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0002895,
|
|
"loss": 6.5387,
|
|
"mean_token_accuracy": 0.12204434722661972,
|
|
"num_tokens": 1304621.0,
|
|
"step": 580
|
|
},
|
|
{
|
|
"entropy": 6.828542423248291,
|
|
"epoch": 0.06570449823103273,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000292,
|
|
"loss": 6.6198,
|
|
"mean_token_accuracy": 0.12465316653251649,
|
|
"num_tokens": 1315481.0,
|
|
"step": 585
|
|
},
|
|
{
|
|
"entropy": 6.641292333602905,
|
|
"epoch": 0.06626607513899029,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0002945,
|
|
"loss": 6.6021,
|
|
"mean_token_accuracy": 0.12428974732756615,
|
|
"num_tokens": 1328726.0,
|
|
"step": 590
|
|
},
|
|
{
|
|
"entropy": 6.790183639526367,
|
|
"epoch": 0.06682765204694784,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000297,
|
|
"loss": 6.6603,
|
|
"mean_token_accuracy": 0.12199008911848068,
|
|
"num_tokens": 1340151.0,
|
|
"step": 595
|
|
},
|
|
{
|
|
"entropy": 6.6274354457855225,
|
|
"epoch": 0.06738922895490537,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0002995,
|
|
"loss": 6.4411,
|
|
"mean_token_accuracy": 0.12323693186044693,
|
|
"num_tokens": 1350833.0,
|
|
"step": 600
|
|
},
|
|
{
|
|
"entropy": 6.738854312896729,
|
|
"epoch": 0.06795080586286292,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000302,
|
|
"loss": 6.6111,
|
|
"mean_token_accuracy": 0.12676038667559625,
|
|
"num_tokens": 1362332.0,
|
|
"step": 605
|
|
},
|
|
{
|
|
"entropy": 6.6895301818847654,
|
|
"epoch": 0.06851238277082046,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0003045,
|
|
"loss": 6.5002,
|
|
"mean_token_accuracy": 0.13042355701327324,
|
|
"num_tokens": 1373696.0,
|
|
"step": 610
|
|
},
|
|
{
|
|
"entropy": 6.526501417160034,
|
|
"epoch": 0.06907395967877801,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000307,
|
|
"loss": 6.4218,
|
|
"mean_token_accuracy": 0.1356612041592598,
|
|
"num_tokens": 1383553.0,
|
|
"step": 615
|
|
},
|
|
{
|
|
"entropy": 6.660169887542724,
|
|
"epoch": 0.06963553658673555,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0003095,
|
|
"loss": 6.5499,
|
|
"mean_token_accuracy": 0.1267920345067978,
|
|
"num_tokens": 1394487.0,
|
|
"step": 620
|
|
},
|
|
{
|
|
"entropy": 6.846566820144654,
|
|
"epoch": 0.0701971134946931,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000312,
|
|
"loss": 6.5606,
|
|
"mean_token_accuracy": 0.13110520616173743,
|
|
"num_tokens": 1404928.0,
|
|
"step": 625
|
|
},
|
|
{
|
|
"entropy": 6.503131103515625,
|
|
"epoch": 0.07075869040265065,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0003145,
|
|
"loss": 6.4294,
|
|
"mean_token_accuracy": 0.1311935856938362,
|
|
"num_tokens": 1415854.0,
|
|
"step": 630
|
|
},
|
|
{
|
|
"entropy": 6.592182874679565,
|
|
"epoch": 0.07132026731060818,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000317,
|
|
"loss": 6.4816,
|
|
"mean_token_accuracy": 0.1329976461827755,
|
|
"num_tokens": 1427153.0,
|
|
"step": 635
|
|
},
|
|
{
|
|
"entropy": 6.661157464981079,
|
|
"epoch": 0.07188184421856574,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0003195,
|
|
"loss": 6.5885,
|
|
"mean_token_accuracy": 0.12770819365978242,
|
|
"num_tokens": 1438907.0,
|
|
"step": 640
|
|
},
|
|
{
|
|
"entropy": 6.7143834114074705,
|
|
"epoch": 0.07244342112652327,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000322,
|
|
"loss": 6.4669,
|
|
"mean_token_accuracy": 0.12574334740638732,
|
|
"num_tokens": 1449975.0,
|
|
"step": 645
|
|
},
|
|
{
|
|
"entropy": 6.589789390563965,
|
|
"epoch": 0.07300499803448082,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00032450000000000003,
|
|
"loss": 6.4557,
|
|
"mean_token_accuracy": 0.12991306632757188,
|
|
"num_tokens": 1460815.0,
|
|
"step": 650
|
|
},
|
|
{
|
|
"entropy": 6.6092170715332035,
|
|
"epoch": 0.07356657494243837,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00032700000000000003,
|
|
"loss": 6.5044,
|
|
"mean_token_accuracy": 0.1279452659189701,
|
|
"num_tokens": 1472403.0,
|
|
"step": 655
|
|
},
|
|
{
|
|
"entropy": 6.639557504653931,
|
|
"epoch": 0.07412815185039591,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00032950000000000004,
|
|
"loss": 6.5141,
|
|
"mean_token_accuracy": 0.12161320745944977,
|
|
"num_tokens": 1484015.0,
|
|
"step": 660
|
|
},
|
|
{
|
|
"entropy": 6.653767776489258,
|
|
"epoch": 0.07468972875835346,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00033200000000000005,
|
|
"loss": 6.5425,
|
|
"mean_token_accuracy": 0.12279097139835357,
|
|
"num_tokens": 1495383.0,
|
|
"step": 665
|
|
},
|
|
{
|
|
"entropy": 6.608673715591431,
|
|
"epoch": 0.075251305666311,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00033450000000000005,
|
|
"loss": 6.468,
|
|
"mean_token_accuracy": 0.1286981873214245,
|
|
"num_tokens": 1505893.0,
|
|
"step": 670
|
|
},
|
|
{
|
|
"entropy": 6.724495363235474,
|
|
"epoch": 0.07581288257426855,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000337,
|
|
"loss": 6.6061,
|
|
"mean_token_accuracy": 0.12201442718505859,
|
|
"num_tokens": 1518933.0,
|
|
"step": 675
|
|
},
|
|
{
|
|
"entropy": 6.7100588321685795,
|
|
"epoch": 0.07637445948222608,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0003395,
|
|
"loss": 6.6149,
|
|
"mean_token_accuracy": 0.1266277812421322,
|
|
"num_tokens": 1530603.0,
|
|
"step": 680
|
|
},
|
|
{
|
|
"entropy": 6.643559837341309,
|
|
"epoch": 0.07693603639018363,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000342,
|
|
"loss": 6.4551,
|
|
"mean_token_accuracy": 0.131996688246727,
|
|
"num_tokens": 1540977.0,
|
|
"step": 685
|
|
},
|
|
{
|
|
"entropy": 6.6613860607147215,
|
|
"epoch": 0.07749761329814119,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00034449999999999997,
|
|
"loss": 6.5621,
|
|
"mean_token_accuracy": 0.12197319865226745,
|
|
"num_tokens": 1553004.0,
|
|
"step": 690
|
|
},
|
|
{
|
|
"entropy": 6.604646968841553,
|
|
"epoch": 0.07805919020609872,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000347,
|
|
"loss": 6.4726,
|
|
"mean_token_accuracy": 0.12990233227610587,
|
|
"num_tokens": 1563446.0,
|
|
"step": 695
|
|
},
|
|
{
|
|
"entropy": 6.59793119430542,
|
|
"epoch": 0.07862076711405627,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0003495,
|
|
"loss": 6.5153,
|
|
"mean_token_accuracy": 0.1260698601603508,
|
|
"num_tokens": 1573884.0,
|
|
"step": 700
|
|
},
|
|
{
|
|
"entropy": 6.554755544662475,
|
|
"epoch": 0.07918234402201381,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000352,
|
|
"loss": 6.3739,
|
|
"mean_token_accuracy": 0.13849396333098413,
|
|
"num_tokens": 1585396.0,
|
|
"step": 705
|
|
},
|
|
{
|
|
"entropy": 6.4631202697753904,
|
|
"epoch": 0.07974392092997136,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0003545,
|
|
"loss": 6.3757,
|
|
"mean_token_accuracy": 0.1374616429209709,
|
|
"num_tokens": 1596934.0,
|
|
"step": 710
|
|
},
|
|
{
|
|
"entropy": 6.508552122116089,
|
|
"epoch": 0.08030549783792891,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000357,
|
|
"loss": 6.4243,
|
|
"mean_token_accuracy": 0.13476341739296913,
|
|
"num_tokens": 1608069.0,
|
|
"step": 715
|
|
},
|
|
{
|
|
"entropy": 6.504626750946045,
|
|
"epoch": 0.08086707474588645,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0003595,
|
|
"loss": 6.345,
|
|
"mean_token_accuracy": 0.1367340750992298,
|
|
"num_tokens": 1619532.0,
|
|
"step": 720
|
|
},
|
|
{
|
|
"entropy": 6.577574253082275,
|
|
"epoch": 0.081428651653844,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000362,
|
|
"loss": 6.5057,
|
|
"mean_token_accuracy": 0.12562305480241776,
|
|
"num_tokens": 1630697.0,
|
|
"step": 725
|
|
},
|
|
{
|
|
"entropy": 6.569473791122436,
|
|
"epoch": 0.08199022856180153,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0003645,
|
|
"loss": 6.483,
|
|
"mean_token_accuracy": 0.12953646928071977,
|
|
"num_tokens": 1641854.0,
|
|
"step": 730
|
|
},
|
|
{
|
|
"entropy": 6.676255798339843,
|
|
"epoch": 0.08255180546975908,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000367,
|
|
"loss": 6.6127,
|
|
"mean_token_accuracy": 0.1251482017338276,
|
|
"num_tokens": 1653036.0,
|
|
"step": 735
|
|
},
|
|
{
|
|
"entropy": 6.500600099563599,
|
|
"epoch": 0.08311338237771662,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0003695,
|
|
"loss": 6.3686,
|
|
"mean_token_accuracy": 0.12898936495184898,
|
|
"num_tokens": 1664096.0,
|
|
"step": 740
|
|
},
|
|
{
|
|
"entropy": 6.575688219070434,
|
|
"epoch": 0.08367495928567417,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000372,
|
|
"loss": 6.5405,
|
|
"mean_token_accuracy": 0.12776357308030128,
|
|
"num_tokens": 1677890.0,
|
|
"step": 745
|
|
},
|
|
{
|
|
"entropy": 6.513050270080567,
|
|
"epoch": 0.08423653619363172,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0003745,
|
|
"loss": 6.4039,
|
|
"mean_token_accuracy": 0.13092774003744126,
|
|
"num_tokens": 1687627.0,
|
|
"step": 750
|
|
},
|
|
{
|
|
"entropy": 6.6496001243591305,
|
|
"epoch": 0.08479811310158926,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000377,
|
|
"loss": 6.6299,
|
|
"mean_token_accuracy": 0.12669486477971076,
|
|
"num_tokens": 1700843.0,
|
|
"step": 755
|
|
},
|
|
{
|
|
"entropy": 6.54553918838501,
|
|
"epoch": 0.08535969000954681,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0003795,
|
|
"loss": 6.4485,
|
|
"mean_token_accuracy": 0.12898636609315872,
|
|
"num_tokens": 1712356.0,
|
|
"step": 760
|
|
},
|
|
{
|
|
"entropy": 6.5033485889434814,
|
|
"epoch": 0.08592126691750435,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000382,
|
|
"loss": 6.44,
|
|
"mean_token_accuracy": 0.1329922027885914,
|
|
"num_tokens": 1722041.0,
|
|
"step": 765
|
|
},
|
|
{
|
|
"entropy": 6.540292739868164,
|
|
"epoch": 0.0864828438254619,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0003845,
|
|
"loss": 6.5334,
|
|
"mean_token_accuracy": 0.12715438082814218,
|
|
"num_tokens": 1733628.0,
|
|
"step": 770
|
|
},
|
|
{
|
|
"entropy": 6.52957124710083,
|
|
"epoch": 0.08704442073341945,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00038700000000000003,
|
|
"loss": 6.3951,
|
|
"mean_token_accuracy": 0.13516492396593094,
|
|
"num_tokens": 1745174.0,
|
|
"step": 775
|
|
},
|
|
{
|
|
"entropy": 6.472682189941406,
|
|
"epoch": 0.08760599764137698,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00038950000000000003,
|
|
"loss": 6.3261,
|
|
"mean_token_accuracy": 0.13572794049978257,
|
|
"num_tokens": 1757117.0,
|
|
"step": 780
|
|
},
|
|
{
|
|
"entropy": 6.4541521072387695,
|
|
"epoch": 0.08816757454933453,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00039200000000000004,
|
|
"loss": 6.3477,
|
|
"mean_token_accuracy": 0.13643818646669387,
|
|
"num_tokens": 1767343.0,
|
|
"step": 785
|
|
},
|
|
{
|
|
"entropy": 6.52891354560852,
|
|
"epoch": 0.08872915145729207,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00039450000000000005,
|
|
"loss": 6.4341,
|
|
"mean_token_accuracy": 0.1295755423605442,
|
|
"num_tokens": 1778500.0,
|
|
"step": 790
|
|
},
|
|
{
|
|
"entropy": 6.495887565612793,
|
|
"epoch": 0.08929072836524962,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00039700000000000005,
|
|
"loss": 6.4257,
|
|
"mean_token_accuracy": 0.13391977846622466,
|
|
"num_tokens": 1788474.0,
|
|
"step": 795
|
|
},
|
|
{
|
|
"entropy": 6.669151258468628,
|
|
"epoch": 0.08985230527320717,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0003995,
|
|
"loss": 6.6066,
|
|
"mean_token_accuracy": 0.12243209406733513,
|
|
"num_tokens": 1800756.0,
|
|
"step": 800
|
|
},
|
|
{
|
|
"entropy": 6.264161491394043,
|
|
"epoch": 0.09041388218116471,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000402,
|
|
"loss": 6.3051,
|
|
"mean_token_accuracy": 0.13255022764205932,
|
|
"num_tokens": 1812172.0,
|
|
"step": 805
|
|
},
|
|
{
|
|
"entropy": 6.581796360015869,
|
|
"epoch": 0.09097545908912226,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004045,
|
|
"loss": 6.4369,
|
|
"mean_token_accuracy": 0.13564810305833816,
|
|
"num_tokens": 1822057.0,
|
|
"step": 810
|
|
},
|
|
{
|
|
"entropy": 6.388931703567505,
|
|
"epoch": 0.0915370359970798,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00040699999999999997,
|
|
"loss": 6.3692,
|
|
"mean_token_accuracy": 0.13979063034057618,
|
|
"num_tokens": 1833074.0,
|
|
"step": 815
|
|
},
|
|
{
|
|
"entropy": 6.4439905166625975,
|
|
"epoch": 0.09209861290503735,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004095,
|
|
"loss": 6.3689,
|
|
"mean_token_accuracy": 0.1369178406894207,
|
|
"num_tokens": 1844932.0,
|
|
"step": 820
|
|
},
|
|
{
|
|
"entropy": 6.451093339920044,
|
|
"epoch": 0.09266018981299488,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000412,
|
|
"loss": 6.3812,
|
|
"mean_token_accuracy": 0.13171854838728905,
|
|
"num_tokens": 1855591.0,
|
|
"step": 825
|
|
},
|
|
{
|
|
"entropy": 6.412005949020386,
|
|
"epoch": 0.09322176672095243,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004145,
|
|
"loss": 6.3368,
|
|
"mean_token_accuracy": 0.13641790226101874,
|
|
"num_tokens": 1866726.0,
|
|
"step": 830
|
|
},
|
|
{
|
|
"entropy": 6.4959104537963865,
|
|
"epoch": 0.09378334362890998,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000417,
|
|
"loss": 6.3763,
|
|
"mean_token_accuracy": 0.13648990392684937,
|
|
"num_tokens": 1877385.0,
|
|
"step": 835
|
|
},
|
|
{
|
|
"entropy": 6.375614738464355,
|
|
"epoch": 0.09434492053686752,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004195,
|
|
"loss": 6.2828,
|
|
"mean_token_accuracy": 0.1361901879310608,
|
|
"num_tokens": 1887905.0,
|
|
"step": 840
|
|
},
|
|
{
|
|
"entropy": 6.32490758895874,
|
|
"epoch": 0.09490649744482507,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000422,
|
|
"loss": 6.3418,
|
|
"mean_token_accuracy": 0.13226142525672913,
|
|
"num_tokens": 1898649.0,
|
|
"step": 845
|
|
},
|
|
{
|
|
"entropy": 6.440097618103027,
|
|
"epoch": 0.09546807435278261,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004245,
|
|
"loss": 6.3581,
|
|
"mean_token_accuracy": 0.12981755211949347,
|
|
"num_tokens": 1908808.0,
|
|
"step": 850
|
|
},
|
|
{
|
|
"entropy": 6.449653148651123,
|
|
"epoch": 0.09602965126074016,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000427,
|
|
"loss": 6.4636,
|
|
"mean_token_accuracy": 0.13088747188448907,
|
|
"num_tokens": 1920360.0,
|
|
"step": 855
|
|
},
|
|
{
|
|
"entropy": 6.425679159164429,
|
|
"epoch": 0.09659122816869771,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004295,
|
|
"loss": 6.3601,
|
|
"mean_token_accuracy": 0.13659372106194495,
|
|
"num_tokens": 1931082.0,
|
|
"step": 860
|
|
},
|
|
{
|
|
"entropy": 6.450051259994507,
|
|
"epoch": 0.09715280507665525,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000432,
|
|
"loss": 6.5104,
|
|
"mean_token_accuracy": 0.13292263224720954,
|
|
"num_tokens": 1942712.0,
|
|
"step": 865
|
|
},
|
|
{
|
|
"entropy": 6.353779935836792,
|
|
"epoch": 0.0977143819846128,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004345,
|
|
"loss": 6.2649,
|
|
"mean_token_accuracy": 0.13690216466784477,
|
|
"num_tokens": 1953316.0,
|
|
"step": 870
|
|
},
|
|
{
|
|
"entropy": 6.438309907913208,
|
|
"epoch": 0.09827595889257033,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000437,
|
|
"loss": 6.3389,
|
|
"mean_token_accuracy": 0.13307465687394143,
|
|
"num_tokens": 1963936.0,
|
|
"step": 875
|
|
},
|
|
{
|
|
"entropy": 6.4518403053283695,
|
|
"epoch": 0.09883753580052788,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004395,
|
|
"loss": 6.3619,
|
|
"mean_token_accuracy": 0.1389799363911152,
|
|
"num_tokens": 1974502.0,
|
|
"step": 880
|
|
},
|
|
{
|
|
"entropy": 6.3525231838226315,
|
|
"epoch": 0.09939911270848542,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.000442,
|
|
"loss": 6.2961,
|
|
"mean_token_accuracy": 0.14234573692083358,
|
|
"num_tokens": 1985746.0,
|
|
"step": 885
|
|
},
|
|
{
|
|
"entropy": 6.370750093460083,
|
|
"epoch": 0.09996068961644297,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004445,
|
|
"loss": 6.3998,
|
|
"mean_token_accuracy": 0.1339979127049446,
|
|
"num_tokens": 1997696.0,
|
|
"step": 890
|
|
},
|
|
{
|
|
"entropy": 6.476981210708618,
|
|
"epoch": 0.10052226652440052,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000447,
|
|
"loss": 6.3688,
|
|
"mean_token_accuracy": 0.13148148730397224,
|
|
"num_tokens": 2009462.0,
|
|
"step": 895
|
|
},
|
|
{
|
|
"entropy": 6.306058502197265,
|
|
"epoch": 0.10108384343235806,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00044950000000000003,
|
|
"loss": 6.3004,
|
|
"mean_token_accuracy": 0.13532110527157784,
|
|
"num_tokens": 2019547.0,
|
|
"step": 900
|
|
},
|
|
{
|
|
"entropy": 6.276200008392334,
|
|
"epoch": 0.10164542034031561,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00045200000000000004,
|
|
"loss": 6.3087,
|
|
"mean_token_accuracy": 0.1303063564002514,
|
|
"num_tokens": 2030990.0,
|
|
"step": 905
|
|
},
|
|
{
|
|
"entropy": 6.328003215789795,
|
|
"epoch": 0.10220699724827315,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.00045450000000000004,
|
|
"loss": 6.379,
|
|
"mean_token_accuracy": 0.13275872617959977,
|
|
"num_tokens": 2042488.0,
|
|
"step": 910
|
|
},
|
|
{
|
|
"entropy": 6.5090795993804935,
|
|
"epoch": 0.1027685741562307,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00045700000000000005,
|
|
"loss": 6.4124,
|
|
"mean_token_accuracy": 0.13137131109833716,
|
|
"num_tokens": 2052822.0,
|
|
"step": 915
|
|
},
|
|
{
|
|
"entropy": 6.463271427154541,
|
|
"epoch": 0.10333015106418825,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00045950000000000006,
|
|
"loss": 6.3703,
|
|
"mean_token_accuracy": 0.1341596059501171,
|
|
"num_tokens": 2063274.0,
|
|
"step": 920
|
|
},
|
|
{
|
|
"entropy": 6.4825742721557615,
|
|
"epoch": 0.10389172797214578,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000462,
|
|
"loss": 6.4069,
|
|
"mean_token_accuracy": 0.13037585765123366,
|
|
"num_tokens": 2074424.0,
|
|
"step": 925
|
|
},
|
|
{
|
|
"entropy": 6.314002275466919,
|
|
"epoch": 0.10445330488010333,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004645,
|
|
"loss": 6.4013,
|
|
"mean_token_accuracy": 0.13306034207344056,
|
|
"num_tokens": 2085776.0,
|
|
"step": 930
|
|
},
|
|
{
|
|
"entropy": 6.591546201705933,
|
|
"epoch": 0.10501488178806087,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000467,
|
|
"loss": 6.4721,
|
|
"mean_token_accuracy": 0.13484944850206376,
|
|
"num_tokens": 2096789.0,
|
|
"step": 935
|
|
},
|
|
{
|
|
"entropy": 6.330018711090088,
|
|
"epoch": 0.10557645869601842,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004695,
|
|
"loss": 6.3848,
|
|
"mean_token_accuracy": 0.13674520328640938,
|
|
"num_tokens": 2108335.0,
|
|
"step": 940
|
|
},
|
|
{
|
|
"entropy": 6.46536111831665,
|
|
"epoch": 0.10613803560397596,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000472,
|
|
"loss": 6.4749,
|
|
"mean_token_accuracy": 0.13200692012906073,
|
|
"num_tokens": 2121063.0,
|
|
"step": 945
|
|
},
|
|
{
|
|
"entropy": 6.343993902206421,
|
|
"epoch": 0.10669961251193351,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004745,
|
|
"loss": 6.3351,
|
|
"mean_token_accuracy": 0.1397795021533966,
|
|
"num_tokens": 2132442.0,
|
|
"step": 950
|
|
},
|
|
{
|
|
"entropy": 6.362326002120971,
|
|
"epoch": 0.10726118941989106,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000477,
|
|
"loss": 6.2455,
|
|
"mean_token_accuracy": 0.1406833589076996,
|
|
"num_tokens": 2142155.0,
|
|
"step": 955
|
|
},
|
|
{
|
|
"entropy": 6.290420150756836,
|
|
"epoch": 0.1078227663278486,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004795,
|
|
"loss": 6.3118,
|
|
"mean_token_accuracy": 0.13632866069674493,
|
|
"num_tokens": 2152923.0,
|
|
"step": 960
|
|
},
|
|
{
|
|
"entropy": 6.347664928436279,
|
|
"epoch": 0.10838434323580615,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000482,
|
|
"loss": 6.3058,
|
|
"mean_token_accuracy": 0.13932796120643615,
|
|
"num_tokens": 2164640.0,
|
|
"step": 965
|
|
},
|
|
{
|
|
"entropy": 6.229414701461792,
|
|
"epoch": 0.10894592014376368,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004845,
|
|
"loss": 6.2222,
|
|
"mean_token_accuracy": 0.13819631040096284,
|
|
"num_tokens": 2175403.0,
|
|
"step": 970
|
|
},
|
|
{
|
|
"entropy": 6.34880313873291,
|
|
"epoch": 0.10950749705172123,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000487,
|
|
"loss": 6.3313,
|
|
"mean_token_accuracy": 0.1353020928800106,
|
|
"num_tokens": 2186031.0,
|
|
"step": 975
|
|
},
|
|
{
|
|
"entropy": 6.380644750595093,
|
|
"epoch": 0.11006907395967878,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004895,
|
|
"loss": 6.3329,
|
|
"mean_token_accuracy": 0.13262429535388948,
|
|
"num_tokens": 2198152.0,
|
|
"step": 980
|
|
},
|
|
{
|
|
"entropy": 6.278173971176147,
|
|
"epoch": 0.11063065086763632,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000492,
|
|
"loss": 6.338,
|
|
"mean_token_accuracy": 0.13674701675772666,
|
|
"num_tokens": 2209435.0,
|
|
"step": 985
|
|
},
|
|
{
|
|
"entropy": 6.350253009796143,
|
|
"epoch": 0.11119222777559387,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004945,
|
|
"loss": 6.2994,
|
|
"mean_token_accuracy": 0.14112076461315154,
|
|
"num_tokens": 2219476.0,
|
|
"step": 990
|
|
},
|
|
{
|
|
"entropy": 6.3657073974609375,
|
|
"epoch": 0.11175380468355141,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000497,
|
|
"loss": 6.3837,
|
|
"mean_token_accuracy": 0.13610237762331961,
|
|
"num_tokens": 2231131.0,
|
|
"step": 995
|
|
},
|
|
{
|
|
"entropy": 6.300810956954956,
|
|
"epoch": 0.11231538159150896,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004995,
|
|
"loss": 6.2892,
|
|
"mean_token_accuracy": 0.1371823087334633,
|
|
"num_tokens": 2242309.0,
|
|
"step": 1000
|
|
},
|
|
{
|
|
"entropy": 6.2305169105529785,
|
|
"epoch": 0.1128769584994665,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000499999997707492,
|
|
"loss": 6.1273,
|
|
"mean_token_accuracy": 0.1387334682047367,
|
|
"num_tokens": 2252236.0,
|
|
"step": 1005
|
|
},
|
|
{
|
|
"entropy": 6.3840419292449955,
|
|
"epoch": 0.11343853540742405,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999999883941787,
|
|
"loss": 6.4504,
|
|
"mean_token_accuracy": 0.1293959580361843,
|
|
"num_tokens": 2263529.0,
|
|
"step": 1010
|
|
},
|
|
{
|
|
"entropy": 6.223633098602295,
|
|
"epoch": 0.1140001123153816,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999999719167785,
|
|
"loss": 6.2809,
|
|
"mean_token_accuracy": 0.13737061843276024,
|
|
"num_tokens": 2275318.0,
|
|
"step": 1015
|
|
},
|
|
{
|
|
"entropy": 6.3728053092956545,
|
|
"epoch": 0.11456168922333913,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999999482752917,
|
|
"loss": 6.3265,
|
|
"mean_token_accuracy": 0.13787831887602806,
|
|
"num_tokens": 2287434.0,
|
|
"step": 1020
|
|
},
|
|
{
|
|
"entropy": 6.254129695892334,
|
|
"epoch": 0.11512326613129668,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999999174697195,
|
|
"loss": 6.2315,
|
|
"mean_token_accuracy": 0.13839245587587357,
|
|
"num_tokens": 2299145.0,
|
|
"step": 1025
|
|
},
|
|
{
|
|
"entropy": 6.261599349975586,
|
|
"epoch": 0.11568484303925422,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999998795000627,
|
|
"loss": 6.3257,
|
|
"mean_token_accuracy": 0.13926222771406174,
|
|
"num_tokens": 2309841.0,
|
|
"step": 1030
|
|
},
|
|
{
|
|
"entropy": 6.315525674819947,
|
|
"epoch": 0.11624641994721177,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004999998343663223,
|
|
"loss": 6.3193,
|
|
"mean_token_accuracy": 0.1403449870646,
|
|
"num_tokens": 2322143.0,
|
|
"step": 1035
|
|
},
|
|
{
|
|
"entropy": 6.261302518844604,
|
|
"epoch": 0.11680799685516932,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999997820685,
|
|
"loss": 6.2402,
|
|
"mean_token_accuracy": 0.13240669071674346,
|
|
"num_tokens": 2333207.0,
|
|
"step": 1040
|
|
},
|
|
{
|
|
"entropy": 6.1786919116973875,
|
|
"epoch": 0.11736957376312686,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004999997226065974,
|
|
"loss": 6.3105,
|
|
"mean_token_accuracy": 0.13664863780140876,
|
|
"num_tokens": 2345542.0,
|
|
"step": 1045
|
|
},
|
|
{
|
|
"entropy": 6.371749353408814,
|
|
"epoch": 0.11793115067108441,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999996559806163,
|
|
"loss": 6.3079,
|
|
"mean_token_accuracy": 0.14061758145689965,
|
|
"num_tokens": 2356612.0,
|
|
"step": 1050
|
|
},
|
|
{
|
|
"entropy": 6.225208377838134,
|
|
"epoch": 0.11849272757904195,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999995821905589,
|
|
"loss": 6.2306,
|
|
"mean_token_accuracy": 0.13814162313938141,
|
|
"num_tokens": 2368204.0,
|
|
"step": 1055
|
|
},
|
|
{
|
|
"entropy": 6.262781095504761,
|
|
"epoch": 0.1190543044869995,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999995012364276,
|
|
"loss": 6.264,
|
|
"mean_token_accuracy": 0.14789239913225175,
|
|
"num_tokens": 2379114.0,
|
|
"step": 1060
|
|
},
|
|
{
|
|
"entropy": 6.258517122268676,
|
|
"epoch": 0.11961588139495703,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004999994131182248,
|
|
"loss": 6.3024,
|
|
"mean_token_accuracy": 0.1361288011074066,
|
|
"num_tokens": 2390562.0,
|
|
"step": 1065
|
|
},
|
|
{
|
|
"entropy": 6.30267333984375,
|
|
"epoch": 0.12017745830291458,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999993178359535,
|
|
"loss": 6.3561,
|
|
"mean_token_accuracy": 0.13576339259743692,
|
|
"num_tokens": 2402352.0,
|
|
"step": 1070
|
|
},
|
|
{
|
|
"entropy": 6.422991371154785,
|
|
"epoch": 0.12073903521087213,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999992153896166,
|
|
"loss": 6.3906,
|
|
"mean_token_accuracy": 0.1379263438284397,
|
|
"num_tokens": 2415140.0,
|
|
"step": 1075
|
|
},
|
|
{
|
|
"entropy": 6.226438283920288,
|
|
"epoch": 0.12130061211882967,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999991057792175,
|
|
"loss": 6.2828,
|
|
"mean_token_accuracy": 0.13986248895525932,
|
|
"num_tokens": 2426679.0,
|
|
"step": 1080
|
|
},
|
|
{
|
|
"entropy": 6.307008361816406,
|
|
"epoch": 0.12186218902678722,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999989890047596,
|
|
"loss": 6.3213,
|
|
"mean_token_accuracy": 0.14080586433410644,
|
|
"num_tokens": 2437735.0,
|
|
"step": 1085
|
|
},
|
|
{
|
|
"entropy": 6.244773292541504,
|
|
"epoch": 0.12242376593474476,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999988650662467,
|
|
"loss": 6.2433,
|
|
"mean_token_accuracy": 0.13999149277806283,
|
|
"num_tokens": 2448611.0,
|
|
"step": 1090
|
|
},
|
|
{
|
|
"entropy": 6.176812791824341,
|
|
"epoch": 0.12298534284270231,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999987339636825,
|
|
"loss": 6.1729,
|
|
"mean_token_accuracy": 0.14464567825198174,
|
|
"num_tokens": 2461101.0,
|
|
"step": 1095
|
|
},
|
|
{
|
|
"entropy": 6.265973329544067,
|
|
"epoch": 0.12354691975065986,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999985956970713,
|
|
"loss": 6.3176,
|
|
"mean_token_accuracy": 0.13885853216052055,
|
|
"num_tokens": 2473569.0,
|
|
"step": 1100
|
|
},
|
|
{
|
|
"entropy": 6.171710395812989,
|
|
"epoch": 0.1241084966586174,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999984502664178,
|
|
"loss": 6.2382,
|
|
"mean_token_accuracy": 0.13876865357160567,
|
|
"num_tokens": 2483970.0,
|
|
"step": 1105
|
|
},
|
|
{
|
|
"entropy": 6.363559436798096,
|
|
"epoch": 0.12467007356657495,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004999982976717261,
|
|
"loss": 6.2895,
|
|
"mean_token_accuracy": 0.14146780967712402,
|
|
"num_tokens": 2494184.0,
|
|
"step": 1110
|
|
},
|
|
{
|
|
"entropy": 6.217218828201294,
|
|
"epoch": 0.1252316504745325,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004999981379130016,
|
|
"loss": 6.3041,
|
|
"mean_token_accuracy": 0.14307402372360228,
|
|
"num_tokens": 2505715.0,
|
|
"step": 1115
|
|
},
|
|
{
|
|
"entropy": 6.386610078811645,
|
|
"epoch": 0.12579322738249002,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000499997970990249,
|
|
"loss": 6.3412,
|
|
"mean_token_accuracy": 0.14221135526895523,
|
|
"num_tokens": 2517168.0,
|
|
"step": 1120
|
|
},
|
|
{
|
|
"entropy": 6.303906965255737,
|
|
"epoch": 0.12635480429044757,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004999977969034737,
|
|
"loss": 6.3674,
|
|
"mean_token_accuracy": 0.1398570343852043,
|
|
"num_tokens": 2528296.0,
|
|
"step": 1125
|
|
},
|
|
{
|
|
"entropy": 6.249405193328857,
|
|
"epoch": 0.12691638119840512,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999976156526814,
|
|
"loss": 6.3056,
|
|
"mean_token_accuracy": 0.14569928944110871,
|
|
"num_tokens": 2540648.0,
|
|
"step": 1130
|
|
},
|
|
{
|
|
"entropy": 6.177938985824585,
|
|
"epoch": 0.12747795810636267,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999974272378776,
|
|
"loss": 6.1885,
|
|
"mean_token_accuracy": 0.14313262403011323,
|
|
"num_tokens": 2551840.0,
|
|
"step": 1135
|
|
},
|
|
{
|
|
"entropy": 6.324184131622315,
|
|
"epoch": 0.12803953501432022,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999972316590685,
|
|
"loss": 6.2524,
|
|
"mean_token_accuracy": 0.1379991091787815,
|
|
"num_tokens": 2561362.0,
|
|
"step": 1140
|
|
},
|
|
{
|
|
"entropy": 6.31357970237732,
|
|
"epoch": 0.12860111192227774,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999970289162604,
|
|
"loss": 6.298,
|
|
"mean_token_accuracy": 0.14433052241802216,
|
|
"num_tokens": 2573584.0,
|
|
"step": 1145
|
|
},
|
|
{
|
|
"entropy": 6.446721315383911,
|
|
"epoch": 0.1291626888302353,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999968190094595,
|
|
"loss": 6.4204,
|
|
"mean_token_accuracy": 0.1336354859173298,
|
|
"num_tokens": 2585255.0,
|
|
"step": 1150
|
|
},
|
|
{
|
|
"entropy": 6.054596328735352,
|
|
"epoch": 0.12972426573819285,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999966019386727,
|
|
"loss": 6.226,
|
|
"mean_token_accuracy": 0.14078792110085486,
|
|
"num_tokens": 2596849.0,
|
|
"step": 1155
|
|
},
|
|
{
|
|
"entropy": 6.258234024047852,
|
|
"epoch": 0.1302858426461504,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999963777039067,
|
|
"loss": 6.2622,
|
|
"mean_token_accuracy": 0.13961924761533737,
|
|
"num_tokens": 2606918.0,
|
|
"step": 1160
|
|
},
|
|
{
|
|
"entropy": 6.1849829196929935,
|
|
"epoch": 0.13084741955410795,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000499996146305169,
|
|
"loss": 6.1952,
|
|
"mean_token_accuracy": 0.14556236416101456,
|
|
"num_tokens": 2617779.0,
|
|
"step": 1165
|
|
},
|
|
{
|
|
"entropy": 6.273143911361695,
|
|
"epoch": 0.13140899646206547,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999959077424665,
|
|
"loss": 6.2513,
|
|
"mean_token_accuracy": 0.13997638300061227,
|
|
"num_tokens": 2630294.0,
|
|
"step": 1170
|
|
},
|
|
{
|
|
"entropy": 6.12783145904541,
|
|
"epoch": 0.13197057337002302,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999956620158072,
|
|
"loss": 6.1548,
|
|
"mean_token_accuracy": 0.14402848556637765,
|
|
"num_tokens": 2641002.0,
|
|
"step": 1175
|
|
},
|
|
{
|
|
"entropy": 6.1911145687103275,
|
|
"epoch": 0.13253215027798057,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004999954091251987,
|
|
"loss": 6.1448,
|
|
"mean_token_accuracy": 0.14548660516738893,
|
|
"num_tokens": 2652188.0,
|
|
"step": 1180
|
|
},
|
|
{
|
|
"entropy": 6.125283575057983,
|
|
"epoch": 0.13309372718593812,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999951490706491,
|
|
"loss": 6.1865,
|
|
"mean_token_accuracy": 0.14291539043188095,
|
|
"num_tokens": 2662542.0,
|
|
"step": 1185
|
|
},
|
|
{
|
|
"entropy": 6.296076965332031,
|
|
"epoch": 0.13365530409389567,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004999948818521667,
|
|
"loss": 6.2038,
|
|
"mean_token_accuracy": 0.1425152152776718,
|
|
"num_tokens": 2673292.0,
|
|
"step": 1190
|
|
},
|
|
{
|
|
"entropy": 6.177773904800415,
|
|
"epoch": 0.1342168810018532,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00049999460746976,
|
|
"loss": 6.2022,
|
|
"mean_token_accuracy": 0.1450867235660553,
|
|
"num_tokens": 2684042.0,
|
|
"step": 1195
|
|
},
|
|
{
|
|
"entropy": 6.199269771575928,
|
|
"epoch": 0.13477845790981074,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999943259234377,
|
|
"loss": 6.1304,
|
|
"mean_token_accuracy": 0.1481417030096054,
|
|
"num_tokens": 2694716.0,
|
|
"step": 1200
|
|
},
|
|
{
|
|
"entropy": 6.261506462097168,
|
|
"epoch": 0.1353400348177683,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999940372132089,
|
|
"loss": 6.2723,
|
|
"mean_token_accuracy": 0.1427570842206478,
|
|
"num_tokens": 2706200.0,
|
|
"step": 1205
|
|
},
|
|
{
|
|
"entropy": 6.097541093826294,
|
|
"epoch": 0.13590161172572585,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004999937413390826,
|
|
"loss": 6.0978,
|
|
"mean_token_accuracy": 0.14956343919038773,
|
|
"num_tokens": 2716814.0,
|
|
"step": 1210
|
|
},
|
|
{
|
|
"entropy": 6.26879563331604,
|
|
"epoch": 0.1364631886336834,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999934383010683,
|
|
"loss": 6.2646,
|
|
"mean_token_accuracy": 0.13633433505892753,
|
|
"num_tokens": 2728042.0,
|
|
"step": 1215
|
|
},
|
|
{
|
|
"entropy": 6.117309093475342,
|
|
"epoch": 0.13702476554164092,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999931280991757,
|
|
"loss": 6.2276,
|
|
"mean_token_accuracy": 0.13767654895782472,
|
|
"num_tokens": 2739093.0,
|
|
"step": 1220
|
|
},
|
|
{
|
|
"entropy": 6.323478746414184,
|
|
"epoch": 0.13758634244959847,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999928107334146,
|
|
"loss": 6.2653,
|
|
"mean_token_accuracy": 0.14359876736998559,
|
|
"num_tokens": 2750307.0,
|
|
"step": 1225
|
|
},
|
|
{
|
|
"entropy": 6.146844863891602,
|
|
"epoch": 0.13814791935755602,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999924862037952,
|
|
"loss": 6.1785,
|
|
"mean_token_accuracy": 0.142026449739933,
|
|
"num_tokens": 2760534.0,
|
|
"step": 1230
|
|
},
|
|
{
|
|
"entropy": 6.146856021881104,
|
|
"epoch": 0.13870949626551357,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004999921545103278,
|
|
"loss": 6.2017,
|
|
"mean_token_accuracy": 0.1402510516345501,
|
|
"num_tokens": 2772459.0,
|
|
"step": 1235
|
|
},
|
|
{
|
|
"entropy": 6.118765497207642,
|
|
"epoch": 0.1392710731734711,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999918156530229,
|
|
"loss": 6.1162,
|
|
"mean_token_accuracy": 0.15379080772399903,
|
|
"num_tokens": 2784038.0,
|
|
"step": 1240
|
|
},
|
|
{
|
|
"entropy": 6.237395238876343,
|
|
"epoch": 0.13983265008142864,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004999914696318913,
|
|
"loss": 6.24,
|
|
"mean_token_accuracy": 0.14800693467259407,
|
|
"num_tokens": 2795756.0,
|
|
"step": 1245
|
|
},
|
|
{
|
|
"entropy": 6.129542446136474,
|
|
"epoch": 0.1403942269893862,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999911164469441,
|
|
"loss": 6.1721,
|
|
"mean_token_accuracy": 0.14674090445041657,
|
|
"num_tokens": 2806242.0,
|
|
"step": 1250
|
|
},
|
|
{
|
|
"entropy": 6.290287971496582,
|
|
"epoch": 0.14095580389734375,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999907560981925,
|
|
"loss": 6.2556,
|
|
"mean_token_accuracy": 0.14589913040399552,
|
|
"num_tokens": 2817017.0,
|
|
"step": 1255
|
|
},
|
|
{
|
|
"entropy": 6.189040660858154,
|
|
"epoch": 0.1415173808053013,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004999903885856479,
|
|
"loss": 6.1629,
|
|
"mean_token_accuracy": 0.15110919922590255,
|
|
"num_tokens": 2827415.0,
|
|
"step": 1260
|
|
},
|
|
{
|
|
"entropy": 6.141000080108642,
|
|
"epoch": 0.14207895771325882,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000499990013909322,
|
|
"loss": 6.1726,
|
|
"mean_token_accuracy": 0.14932918325066566,
|
|
"num_tokens": 2837595.0,
|
|
"step": 1265
|
|
},
|
|
{
|
|
"entropy": 6.088430595397949,
|
|
"epoch": 0.14264053462121637,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000499989632069227,
|
|
"loss": 6.1339,
|
|
"mean_token_accuracy": 0.14398894980549812,
|
|
"num_tokens": 2847906.0,
|
|
"step": 1270
|
|
},
|
|
{
|
|
"entropy": 6.23743634223938,
|
|
"epoch": 0.14320211152917392,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999892430653747,
|
|
"loss": 6.2346,
|
|
"mean_token_accuracy": 0.13501434922218322,
|
|
"num_tokens": 2859145.0,
|
|
"step": 1275
|
|
},
|
|
{
|
|
"entropy": 6.056405162811279,
|
|
"epoch": 0.14376368843713147,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004999888468977776,
|
|
"loss": 6.1648,
|
|
"mean_token_accuracy": 0.14927329123020172,
|
|
"num_tokens": 2870704.0,
|
|
"step": 1280
|
|
},
|
|
{
|
|
"entropy": 6.249700832366943,
|
|
"epoch": 0.14432526534508902,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004999884435664485,
|
|
"loss": 6.2647,
|
|
"mean_token_accuracy": 0.14412776455283166,
|
|
"num_tokens": 2881861.0,
|
|
"step": 1285
|
|
},
|
|
{
|
|
"entropy": 6.240557241439819,
|
|
"epoch": 0.14488684225304654,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004999880330714,
|
|
"loss": 6.1861,
|
|
"mean_token_accuracy": 0.14692625999450684,
|
|
"num_tokens": 2893247.0,
|
|
"step": 1290
|
|
},
|
|
{
|
|
"entropy": 6.075284337997436,
|
|
"epoch": 0.1454484191610041,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004999876154126453,
|
|
"loss": 6.0185,
|
|
"mean_token_accuracy": 0.1487583711743355,
|
|
"num_tokens": 2905351.0,
|
|
"step": 1295
|
|
},
|
|
{
|
|
"entropy": 6.0624950408935545,
|
|
"epoch": 0.14600999606896164,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999871905901977,
|
|
"loss": 6.1821,
|
|
"mean_token_accuracy": 0.14871341213583947,
|
|
"num_tokens": 2915153.0,
|
|
"step": 1300
|
|
},
|
|
{
|
|
"entropy": 6.169287776947021,
|
|
"epoch": 0.1465715729769192,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999867586040706,
|
|
"loss": 6.1416,
|
|
"mean_token_accuracy": 0.13760501518845558,
|
|
"num_tokens": 2926234.0,
|
|
"step": 1305
|
|
},
|
|
{
|
|
"entropy": 6.069522142410278,
|
|
"epoch": 0.14713314988487675,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004999863194542779,
|
|
"loss": 6.0943,
|
|
"mean_token_accuracy": 0.14693765938282013,
|
|
"num_tokens": 2937033.0,
|
|
"step": 1310
|
|
},
|
|
{
|
|
"entropy": 6.068335819244385,
|
|
"epoch": 0.14769472679283427,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999858731408336,
|
|
"loss": 6.0518,
|
|
"mean_token_accuracy": 0.14859263896942138,
|
|
"num_tokens": 2945904.0,
|
|
"step": 1315
|
|
},
|
|
{
|
|
"entropy": 6.208248567581177,
|
|
"epoch": 0.14825630370079182,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999854196637518,
|
|
"loss": 6.253,
|
|
"mean_token_accuracy": 0.14146910086274148,
|
|
"num_tokens": 2956298.0,
|
|
"step": 1320
|
|
},
|
|
{
|
|
"entropy": 6.151482725143433,
|
|
"epoch": 0.14881788060874937,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999849590230469,
|
|
"loss": 6.1522,
|
|
"mean_token_accuracy": 0.14781234338879584,
|
|
"num_tokens": 2967660.0,
|
|
"step": 1325
|
|
},
|
|
{
|
|
"entropy": 6.198898839950561,
|
|
"epoch": 0.14937945751670692,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999844912187336,
|
|
"loss": 6.2205,
|
|
"mean_token_accuracy": 0.1416272446513176,
|
|
"num_tokens": 2978616.0,
|
|
"step": 1330
|
|
},
|
|
{
|
|
"entropy": 6.0869788646698,
|
|
"epoch": 0.14994103442466447,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000499984016250827,
|
|
"loss": 6.0738,
|
|
"mean_token_accuracy": 0.15207655876874923,
|
|
"num_tokens": 2989731.0,
|
|
"step": 1335
|
|
},
|
|
{
|
|
"entropy": 6.171562576293946,
|
|
"epoch": 0.150502611332622,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000499983534119342,
|
|
"loss": 6.177,
|
|
"mean_token_accuracy": 0.14310620874166488,
|
|
"num_tokens": 3002110.0,
|
|
"step": 1340
|
|
},
|
|
{
|
|
"entropy": 5.928503322601318,
|
|
"epoch": 0.15106418824057954,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999830448242941,
|
|
"loss": 6.0135,
|
|
"mean_token_accuracy": 0.15312863737344742,
|
|
"num_tokens": 3012709.0,
|
|
"step": 1345
|
|
},
|
|
{
|
|
"entropy": 6.257901430130005,
|
|
"epoch": 0.1516257651485371,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004999825483656986,
|
|
"loss": 6.3139,
|
|
"mean_token_accuracy": 0.13134505301713945,
|
|
"num_tokens": 3025738.0,
|
|
"step": 1350
|
|
},
|
|
{
|
|
"entropy": 6.151828098297119,
|
|
"epoch": 0.15218734205649465,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004999820447435716,
|
|
"loss": 6.1416,
|
|
"mean_token_accuracy": 0.14338411912322044,
|
|
"num_tokens": 3037711.0,
|
|
"step": 1355
|
|
},
|
|
{
|
|
"entropy": 6.239610385894776,
|
|
"epoch": 0.15274891896445217,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999815339579291,
|
|
"loss": 6.3286,
|
|
"mean_token_accuracy": 0.13714671283960342,
|
|
"num_tokens": 3048929.0,
|
|
"step": 1360
|
|
},
|
|
{
|
|
"entropy": 6.117274618148803,
|
|
"epoch": 0.15331049587240972,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004999810160087872,
|
|
"loss": 6.0739,
|
|
"mean_token_accuracy": 0.15920419096946717,
|
|
"num_tokens": 3059717.0,
|
|
"step": 1365
|
|
},
|
|
{
|
|
"entropy": 6.133962488174438,
|
|
"epoch": 0.15387207278036727,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999804908961626,
|
|
"loss": 6.0778,
|
|
"mean_token_accuracy": 0.15217963755130767,
|
|
"num_tokens": 3069530.0,
|
|
"step": 1370
|
|
},
|
|
{
|
|
"entropy": 6.133673429489136,
|
|
"epoch": 0.15443364968832482,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999799586200719,
|
|
"loss": 6.2715,
|
|
"mean_token_accuracy": 0.14009033963084222,
|
|
"num_tokens": 3080705.0,
|
|
"step": 1375
|
|
},
|
|
{
|
|
"entropy": 6.1995704650878904,
|
|
"epoch": 0.15499522659628237,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000499979419180532,
|
|
"loss": 6.1198,
|
|
"mean_token_accuracy": 0.1425781100988388,
|
|
"num_tokens": 3092553.0,
|
|
"step": 1380
|
|
},
|
|
{
|
|
"entropy": 6.193589210510254,
|
|
"epoch": 0.1555568035042399,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999788725775601,
|
|
"loss": 6.2416,
|
|
"mean_token_accuracy": 0.1423923633992672,
|
|
"num_tokens": 3102947.0,
|
|
"step": 1385
|
|
},
|
|
{
|
|
"entropy": 6.08302493095398,
|
|
"epoch": 0.15611838041219744,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999783188111737,
|
|
"loss": 6.0833,
|
|
"mean_token_accuracy": 0.15142102390527726,
|
|
"num_tokens": 3114157.0,
|
|
"step": 1390
|
|
},
|
|
{
|
|
"entropy": 6.019034147262573,
|
|
"epoch": 0.156679957320155,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999777578813904,
|
|
"loss": 5.9512,
|
|
"mean_token_accuracy": 0.14669259935617446,
|
|
"num_tokens": 3125739.0,
|
|
"step": 1395
|
|
},
|
|
{
|
|
"entropy": 6.063040637969971,
|
|
"epoch": 0.15724153422811254,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.000499977189788228,
|
|
"loss": 6.1128,
|
|
"mean_token_accuracy": 0.15026577562093735,
|
|
"num_tokens": 3136970.0,
|
|
"step": 1400
|
|
},
|
|
{
|
|
"entropy": 6.108362627029419,
|
|
"epoch": 0.1578031111360701,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004999766145317046,
|
|
"loss": 6.0792,
|
|
"mean_token_accuracy": 0.14896431863307952,
|
|
"num_tokens": 3148512.0,
|
|
"step": 1405
|
|
},
|
|
{
|
|
"entropy": 6.111115980148315,
|
|
"epoch": 0.15836468804402762,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004999760321118385,
|
|
"loss": 6.1135,
|
|
"mean_token_accuracy": 0.15590201914310456,
|
|
"num_tokens": 3159477.0,
|
|
"step": 1410
|
|
},
|
|
{
|
|
"entropy": 6.05187873840332,
|
|
"epoch": 0.15892626495198517,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999754425286483,
|
|
"loss": 6.128,
|
|
"mean_token_accuracy": 0.15035361796617508,
|
|
"num_tokens": 3171361.0,
|
|
"step": 1415
|
|
},
|
|
{
|
|
"entropy": 6.220038843154907,
|
|
"epoch": 0.15948784185994272,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004999748457821529,
|
|
"loss": 6.2881,
|
|
"mean_token_accuracy": 0.13868645653128625,
|
|
"num_tokens": 3184652.0,
|
|
"step": 1420
|
|
},
|
|
{
|
|
"entropy": 6.1836763381958,
|
|
"epoch": 0.16004941876790027,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000499974241872371,
|
|
"loss": 6.1675,
|
|
"mean_token_accuracy": 0.14523480385541915,
|
|
"num_tokens": 3195557.0,
|
|
"step": 1425
|
|
},
|
|
{
|
|
"entropy": 6.168182754516602,
|
|
"epoch": 0.16061099567585782,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999736307993221,
|
|
"loss": 6.1987,
|
|
"mean_token_accuracy": 0.1331624984741211,
|
|
"num_tokens": 3207139.0,
|
|
"step": 1430
|
|
},
|
|
{
|
|
"entropy": 6.287556171417236,
|
|
"epoch": 0.16117257258381534,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004999730125630255,
|
|
"loss": 6.2968,
|
|
"mean_token_accuracy": 0.13671731874346732,
|
|
"num_tokens": 3218967.0,
|
|
"step": 1435
|
|
},
|
|
{
|
|
"entropy": 6.173974084854126,
|
|
"epoch": 0.1617341494917729,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999723871635008,
|
|
"loss": 6.1019,
|
|
"mean_token_accuracy": 0.1492471754550934,
|
|
"num_tokens": 3230168.0,
|
|
"step": 1440
|
|
},
|
|
{
|
|
"entropy": 6.022477769851685,
|
|
"epoch": 0.16229572639973044,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999717546007681,
|
|
"loss": 6.1451,
|
|
"mean_token_accuracy": 0.1437738373875618,
|
|
"num_tokens": 3241829.0,
|
|
"step": 1445
|
|
},
|
|
{
|
|
"entropy": 6.239676189422608,
|
|
"epoch": 0.162857303307688,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999711148748476,
|
|
"loss": 6.1597,
|
|
"mean_token_accuracy": 0.14430854842066765,
|
|
"num_tokens": 3253195.0,
|
|
"step": 1450
|
|
},
|
|
{
|
|
"entropy": 6.084852933883667,
|
|
"epoch": 0.16341888021564555,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999704679857594,
|
|
"loss": 6.2113,
|
|
"mean_token_accuracy": 0.14120337069034578,
|
|
"num_tokens": 3264951.0,
|
|
"step": 1455
|
|
},
|
|
{
|
|
"entropy": 6.022989225387573,
|
|
"epoch": 0.16398045712360307,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004999698139335243,
|
|
"loss": 6.0438,
|
|
"mean_token_accuracy": 0.14825797379016875,
|
|
"num_tokens": 3276054.0,
|
|
"step": 1460
|
|
},
|
|
{
|
|
"entropy": 6.0944970607757565,
|
|
"epoch": 0.16454203403156062,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999691527181632,
|
|
"loss": 6.0089,
|
|
"mean_token_accuracy": 0.1612110674381256,
|
|
"num_tokens": 3285540.0,
|
|
"step": 1465
|
|
},
|
|
{
|
|
"entropy": 6.161299562454223,
|
|
"epoch": 0.16510361093951817,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999684843396968,
|
|
"loss": 6.1427,
|
|
"mean_token_accuracy": 0.14661948680877684,
|
|
"num_tokens": 3296869.0,
|
|
"step": 1470
|
|
},
|
|
{
|
|
"entropy": 6.089122295379639,
|
|
"epoch": 0.16566518784747572,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999678087981467,
|
|
"loss": 6.0813,
|
|
"mean_token_accuracy": 0.1550757810473442,
|
|
"num_tokens": 3307554.0,
|
|
"step": 1475
|
|
},
|
|
{
|
|
"entropy": 5.974129676818848,
|
|
"epoch": 0.16622676475543324,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999671260935343,
|
|
"loss": 6.0369,
|
|
"mean_token_accuracy": 0.14905909150838853,
|
|
"num_tokens": 3319685.0,
|
|
"step": 1480
|
|
},
|
|
{
|
|
"entropy": 6.121063327789306,
|
|
"epoch": 0.1667883416633908,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999664362258814,
|
|
"loss": 6.1516,
|
|
"mean_token_accuracy": 0.14900618344545363,
|
|
"num_tokens": 3330742.0,
|
|
"step": 1485
|
|
},
|
|
{
|
|
"entropy": 6.037702798843384,
|
|
"epoch": 0.16734991857134834,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004999657391952099,
|
|
"loss": 6.1774,
|
|
"mean_token_accuracy": 0.14220552295446395,
|
|
"num_tokens": 3343613.0,
|
|
"step": 1490
|
|
},
|
|
{
|
|
"entropy": 6.289458322525024,
|
|
"epoch": 0.1679114954793059,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.000499965035001542,
|
|
"loss": 6.2146,
|
|
"mean_token_accuracy": 0.1457619272172451,
|
|
"num_tokens": 3355162.0,
|
|
"step": 1495
|
|
},
|
|
{
|
|
"entropy": 6.107675218582154,
|
|
"epoch": 0.16847307238726345,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004999643236449001,
|
|
"loss": 6.1513,
|
|
"mean_token_accuracy": 0.15243639126420022,
|
|
"num_tokens": 3366324.0,
|
|
"step": 1500
|
|
},
|
|
{
|
|
"entropy": 6.264118766784668,
|
|
"epoch": 0.16903464929522097,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999636051253069,
|
|
"loss": 6.292,
|
|
"mean_token_accuracy": 0.13710838407278061,
|
|
"num_tokens": 3378571.0,
|
|
"step": 1505
|
|
},
|
|
{
|
|
"entropy": 6.134381484985352,
|
|
"epoch": 0.16959622620317852,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999628794427854,
|
|
"loss": 6.1696,
|
|
"mean_token_accuracy": 0.13963365852832793,
|
|
"num_tokens": 3390605.0,
|
|
"step": 1510
|
|
},
|
|
{
|
|
"entropy": 6.0607460021972654,
|
|
"epoch": 0.17015780311113607,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999621465973583,
|
|
"loss": 6.0866,
|
|
"mean_token_accuracy": 0.14871912077069283,
|
|
"num_tokens": 3402735.0,
|
|
"step": 1515
|
|
},
|
|
{
|
|
"entropy": 6.100008773803711,
|
|
"epoch": 0.17071938001909362,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999614065890495,
|
|
"loss": 6.0991,
|
|
"mean_token_accuracy": 0.15326170325279237,
|
|
"num_tokens": 3413079.0,
|
|
"step": 1520
|
|
},
|
|
{
|
|
"entropy": 6.077723407745362,
|
|
"epoch": 0.17128095692705117,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999606594178821,
|
|
"loss": 6.0422,
|
|
"mean_token_accuracy": 0.14912576824426652,
|
|
"num_tokens": 3423098.0,
|
|
"step": 1525
|
|
},
|
|
{
|
|
"entropy": 6.100780582427978,
|
|
"epoch": 0.1718425338350087,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.00049995990508388,
|
|
"loss": 6.0769,
|
|
"mean_token_accuracy": 0.14803334027528764,
|
|
"num_tokens": 3435794.0,
|
|
"step": 1530
|
|
},
|
|
{
|
|
"entropy": 6.115665483474731,
|
|
"epoch": 0.17240411074296624,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999591435870674,
|
|
"loss": 6.2069,
|
|
"mean_token_accuracy": 0.13976619020104408,
|
|
"num_tokens": 3448125.0,
|
|
"step": 1535
|
|
},
|
|
{
|
|
"entropy": 6.065301561355591,
|
|
"epoch": 0.1729656876509238,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999583749274684,
|
|
"loss": 6.0397,
|
|
"mean_token_accuracy": 0.14901299476623536,
|
|
"num_tokens": 3458217.0,
|
|
"step": 1540
|
|
},
|
|
{
|
|
"entropy": 6.002480125427246,
|
|
"epoch": 0.17352726455888134,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999575991051074,
|
|
"loss": 6.0901,
|
|
"mean_token_accuracy": 0.1483938679099083,
|
|
"num_tokens": 3469553.0,
|
|
"step": 1545
|
|
},
|
|
{
|
|
"entropy": 6.146899223327637,
|
|
"epoch": 0.1740888414668389,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004999568161200093,
|
|
"loss": 6.0427,
|
|
"mean_token_accuracy": 0.15437329113483428,
|
|
"num_tokens": 3480928.0,
|
|
"step": 1550
|
|
},
|
|
{
|
|
"entropy": 6.065676021575928,
|
|
"epoch": 0.17465041837479642,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999560259721989,
|
|
"loss": 6.1347,
|
|
"mean_token_accuracy": 0.1498277299106121,
|
|
"num_tokens": 3492074.0,
|
|
"step": 1555
|
|
},
|
|
{
|
|
"entropy": 6.13408784866333,
|
|
"epoch": 0.17521199528275397,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999552286617014,
|
|
"loss": 6.1425,
|
|
"mean_token_accuracy": 0.14677510857582093,
|
|
"num_tokens": 3503320.0,
|
|
"step": 1560
|
|
},
|
|
{
|
|
"entropy": 6.015400695800781,
|
|
"epoch": 0.17577357219071152,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004999544241885421,
|
|
"loss": 6.136,
|
|
"mean_token_accuracy": 0.15524707436561586,
|
|
"num_tokens": 3515466.0,
|
|
"step": 1565
|
|
},
|
|
{
|
|
"entropy": 6.1630960464477536,
|
|
"epoch": 0.17633514909866907,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999536125527467,
|
|
"loss": 6.0079,
|
|
"mean_token_accuracy": 0.15108589679002762,
|
|
"num_tokens": 3525584.0,
|
|
"step": 1570
|
|
},
|
|
{
|
|
"entropy": 5.98162202835083,
|
|
"epoch": 0.17689672600662662,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000499952793754341,
|
|
"loss": 6.0963,
|
|
"mean_token_accuracy": 0.1469439223408699,
|
|
"num_tokens": 3536973.0,
|
|
"step": 1575
|
|
},
|
|
{
|
|
"entropy": 6.10207724571228,
|
|
"epoch": 0.17745830291458414,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999519677933512,
|
|
"loss": 6.1286,
|
|
"mean_token_accuracy": 0.14693209826946257,
|
|
"num_tokens": 3547799.0,
|
|
"step": 1580
|
|
},
|
|
{
|
|
"entropy": 6.159058141708374,
|
|
"epoch": 0.1780198798225417,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999511346698035,
|
|
"loss": 6.1786,
|
|
"mean_token_accuracy": 0.15070472061634063,
|
|
"num_tokens": 3558436.0,
|
|
"step": 1585
|
|
},
|
|
{
|
|
"entropy": 6.149427270889282,
|
|
"epoch": 0.17858145673049924,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999502943837244,
|
|
"loss": 6.1659,
|
|
"mean_token_accuracy": 0.15004989951848985,
|
|
"num_tokens": 3569851.0,
|
|
"step": 1590
|
|
},
|
|
{
|
|
"entropy": 6.135163640975952,
|
|
"epoch": 0.1791430336384568,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004999494469351406,
|
|
"loss": 6.0449,
|
|
"mean_token_accuracy": 0.14947315603494643,
|
|
"num_tokens": 3580797.0,
|
|
"step": 1595
|
|
},
|
|
{
|
|
"entropy": 6.05308346748352,
|
|
"epoch": 0.17970461054641435,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004999485923240793,
|
|
"loss": 6.0467,
|
|
"mean_token_accuracy": 0.1534357637166977,
|
|
"num_tokens": 3592552.0,
|
|
"step": 1600
|
|
},
|
|
{
|
|
"entropy": 5.9738929748535154,
|
|
"epoch": 0.18026618745437187,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999477305505675,
|
|
"loss": 6.0287,
|
|
"mean_token_accuracy": 0.15556652545928956,
|
|
"num_tokens": 3603932.0,
|
|
"step": 1605
|
|
},
|
|
{
|
|
"entropy": 6.095688581466675,
|
|
"epoch": 0.18082776436232942,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999468616146328,
|
|
"loss": 6.052,
|
|
"mean_token_accuracy": 0.1578151524066925,
|
|
"num_tokens": 3614865.0,
|
|
"step": 1610
|
|
},
|
|
{
|
|
"entropy": 5.861964559555053,
|
|
"epoch": 0.18138934127028697,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004999459855163026,
|
|
"loss": 5.9784,
|
|
"mean_token_accuracy": 0.1593295931816101,
|
|
"num_tokens": 3626275.0,
|
|
"step": 1615
|
|
},
|
|
{
|
|
"entropy": 6.140000581741333,
|
|
"epoch": 0.18195091817824452,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000499945102255605,
|
|
"loss": 6.1078,
|
|
"mean_token_accuracy": 0.1455901011824608,
|
|
"num_tokens": 3638416.0,
|
|
"step": 1620
|
|
},
|
|
{
|
|
"entropy": 5.946600866317749,
|
|
"epoch": 0.18251249508620204,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004999442118325682,
|
|
"loss": 5.9553,
|
|
"mean_token_accuracy": 0.1524277485907078,
|
|
"num_tokens": 3649651.0,
|
|
"step": 1625
|
|
},
|
|
{
|
|
"entropy": 6.132726192474365,
|
|
"epoch": 0.1830740719941596,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999433142472205,
|
|
"loss": 6.192,
|
|
"mean_token_accuracy": 0.15279360264539718,
|
|
"num_tokens": 3661172.0,
|
|
"step": 1630
|
|
},
|
|
{
|
|
"entropy": 6.108269739151001,
|
|
"epoch": 0.18363564890211714,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999424094995902,
|
|
"loss": 6.0268,
|
|
"mean_token_accuracy": 0.15440748035907745,
|
|
"num_tokens": 3672086.0,
|
|
"step": 1635
|
|
},
|
|
{
|
|
"entropy": 6.029655122756958,
|
|
"epoch": 0.1841972258100747,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004999414975897066,
|
|
"loss": 6.0021,
|
|
"mean_token_accuracy": 0.14995888769626617,
|
|
"num_tokens": 3682579.0,
|
|
"step": 1640
|
|
},
|
|
{
|
|
"entropy": 6.10533299446106,
|
|
"epoch": 0.18475880271803224,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004999405785175983,
|
|
"loss": 6.1253,
|
|
"mean_token_accuracy": 0.14912039935588836,
|
|
"num_tokens": 3694616.0,
|
|
"step": 1645
|
|
},
|
|
{
|
|
"entropy": 5.989877414703369,
|
|
"epoch": 0.18532037962598977,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004999396522832949,
|
|
"loss": 5.909,
|
|
"mean_token_accuracy": 0.1535977005958557,
|
|
"num_tokens": 3706821.0,
|
|
"step": 1650
|
|
},
|
|
{
|
|
"entropy": 5.970361423492432,
|
|
"epoch": 0.18588195653394732,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999387188868256,
|
|
"loss": 5.9652,
|
|
"mean_token_accuracy": 0.1572886511683464,
|
|
"num_tokens": 3717552.0,
|
|
"step": 1655
|
|
},
|
|
{
|
|
"entropy": 5.978477573394775,
|
|
"epoch": 0.18644353344190487,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004999377783282203,
|
|
"loss": 6.043,
|
|
"mean_token_accuracy": 0.15294748544692993,
|
|
"num_tokens": 3728300.0,
|
|
"step": 1660
|
|
},
|
|
{
|
|
"entropy": 6.069652843475342,
|
|
"epoch": 0.18700511034986242,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999368306075089,
|
|
"loss": 6.0383,
|
|
"mean_token_accuracy": 0.15796971321105957,
|
|
"num_tokens": 3738545.0,
|
|
"step": 1665
|
|
},
|
|
{
|
|
"entropy": 6.053223991394043,
|
|
"epoch": 0.18756668725781997,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999358757247215,
|
|
"loss": 6.031,
|
|
"mean_token_accuracy": 0.14949157685041428,
|
|
"num_tokens": 3749190.0,
|
|
"step": 1670
|
|
},
|
|
{
|
|
"entropy": 5.973500061035156,
|
|
"epoch": 0.1881282641657775,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999349136798886,
|
|
"loss": 6.0387,
|
|
"mean_token_accuracy": 0.15051646381616593,
|
|
"num_tokens": 3760978.0,
|
|
"step": 1675
|
|
},
|
|
{
|
|
"entropy": 5.94163761138916,
|
|
"epoch": 0.18868984107373504,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999339444730409,
|
|
"loss": 5.9304,
|
|
"mean_token_accuracy": 0.1564078763127327,
|
|
"num_tokens": 3771339.0,
|
|
"step": 1680
|
|
},
|
|
{
|
|
"entropy": 6.000215005874634,
|
|
"epoch": 0.1892514179816926,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999329681042092,
|
|
"loss": 5.9158,
|
|
"mean_token_accuracy": 0.15469563752412796,
|
|
"num_tokens": 3781550.0,
|
|
"step": 1685
|
|
},
|
|
{
|
|
"entropy": 5.960664081573486,
|
|
"epoch": 0.18981299488965014,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004999319845734243,
|
|
"loss": 6.1339,
|
|
"mean_token_accuracy": 0.14286689832806587,
|
|
"num_tokens": 3793700.0,
|
|
"step": 1690
|
|
},
|
|
{
|
|
"entropy": 6.237479496002197,
|
|
"epoch": 0.1903745717976077,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999309938807181,
|
|
"loss": 6.1323,
|
|
"mean_token_accuracy": 0.14619217813014984,
|
|
"num_tokens": 3806114.0,
|
|
"step": 1695
|
|
},
|
|
{
|
|
"entropy": 5.988754749298096,
|
|
"epoch": 0.19093614870556522,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999299960261216,
|
|
"loss": 6.0421,
|
|
"mean_token_accuracy": 0.15423230230808258,
|
|
"num_tokens": 3817251.0,
|
|
"step": 1700
|
|
},
|
|
{
|
|
"entropy": 6.091027498245239,
|
|
"epoch": 0.19149772561352277,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004999289910096669,
|
|
"loss": 6.0464,
|
|
"mean_token_accuracy": 0.15106936246156694,
|
|
"num_tokens": 3828544.0,
|
|
"step": 1705
|
|
},
|
|
{
|
|
"entropy": 5.994654273986816,
|
|
"epoch": 0.19205930252148032,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999279788313858,
|
|
"loss": 6.1189,
|
|
"mean_token_accuracy": 0.14720231145620347,
|
|
"num_tokens": 3840423.0,
|
|
"step": 1710
|
|
},
|
|
{
|
|
"entropy": 6.1074625015258786,
|
|
"epoch": 0.19262087942943787,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004999269594913107,
|
|
"loss": 6.0199,
|
|
"mean_token_accuracy": 0.15324137806892396,
|
|
"num_tokens": 3852751.0,
|
|
"step": 1715
|
|
},
|
|
{
|
|
"entropy": 5.966987991333008,
|
|
"epoch": 0.19318245633739542,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004999259329894739,
|
|
"loss": 6.0043,
|
|
"mean_token_accuracy": 0.15583723783493042,
|
|
"num_tokens": 3863382.0,
|
|
"step": 1720
|
|
},
|
|
{
|
|
"entropy": 5.978365659713745,
|
|
"epoch": 0.19374403324535294,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999248993259081,
|
|
"loss": 6.0004,
|
|
"mean_token_accuracy": 0.1522401787340641,
|
|
"num_tokens": 3874294.0,
|
|
"step": 1725
|
|
},
|
|
{
|
|
"entropy": 6.057207489013672,
|
|
"epoch": 0.1943056101533105,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999238585006463,
|
|
"loss": 6.0364,
|
|
"mean_token_accuracy": 0.14614153355360032,
|
|
"num_tokens": 3886693.0,
|
|
"step": 1730
|
|
},
|
|
{
|
|
"entropy": 5.985201740264893,
|
|
"epoch": 0.19486718706126804,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999228105137218,
|
|
"loss": 5.9488,
|
|
"mean_token_accuracy": 0.1587449014186859,
|
|
"num_tokens": 3897755.0,
|
|
"step": 1735
|
|
},
|
|
{
|
|
"entropy": 5.956290817260742,
|
|
"epoch": 0.1954287639692256,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999217553651676,
|
|
"loss": 5.9546,
|
|
"mean_token_accuracy": 0.15806302726268767,
|
|
"num_tokens": 3909418.0,
|
|
"step": 1740
|
|
},
|
|
{
|
|
"entropy": 6.051894617080689,
|
|
"epoch": 0.19599034087718312,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999206930550175,
|
|
"loss": 6.1081,
|
|
"mean_token_accuracy": 0.14818969666957854,
|
|
"num_tokens": 3919992.0,
|
|
"step": 1745
|
|
},
|
|
{
|
|
"entropy": 6.063493871688843,
|
|
"epoch": 0.19655191778514067,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999196235833054,
|
|
"loss": 5.9663,
|
|
"mean_token_accuracy": 0.16147716641426085,
|
|
"num_tokens": 3930648.0,
|
|
"step": 1750
|
|
},
|
|
{
|
|
"entropy": 5.885579061508179,
|
|
"epoch": 0.19711349469309822,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999185469500651,
|
|
"loss": 5.9529,
|
|
"mean_token_accuracy": 0.15516203343868257,
|
|
"num_tokens": 3941883.0,
|
|
"step": 1755
|
|
},
|
|
{
|
|
"entropy": 6.019442367553711,
|
|
"epoch": 0.19767507160105577,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000499917463155331,
|
|
"loss": 5.9987,
|
|
"mean_token_accuracy": 0.15911805033683776,
|
|
"num_tokens": 3952005.0,
|
|
"step": 1760
|
|
},
|
|
{
|
|
"entropy": 5.935513496398926,
|
|
"epoch": 0.19823664850901332,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999163721991378,
|
|
"loss": 5.9213,
|
|
"mean_token_accuracy": 0.15570384711027146,
|
|
"num_tokens": 3963720.0,
|
|
"step": 1765
|
|
},
|
|
{
|
|
"entropy": 5.93169755935669,
|
|
"epoch": 0.19879822541697084,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00049991527408152,
|
|
"loss": 6.0081,
|
|
"mean_token_accuracy": 0.15529269427061082,
|
|
"num_tokens": 3974998.0,
|
|
"step": 1770
|
|
},
|
|
{
|
|
"entropy": 6.000465297698975,
|
|
"epoch": 0.1993598023249284,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004999141688025127,
|
|
"loss": 6.048,
|
|
"mean_token_accuracy": 0.14723881632089614,
|
|
"num_tokens": 3986469.0,
|
|
"step": 1775
|
|
},
|
|
{
|
|
"entropy": 6.037735271453857,
|
|
"epoch": 0.19992137923288594,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.000499913056362151,
|
|
"loss": 5.8733,
|
|
"mean_token_accuracy": 0.1559750333428383,
|
|
"num_tokens": 3997553.0,
|
|
"step": 1780
|
|
},
|
|
{
|
|
"entropy": 5.848225831985474,
|
|
"epoch": 0.2004829561408435,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004999119367604703,
|
|
"loss": 5.958,
|
|
"mean_token_accuracy": 0.15345809012651443,
|
|
"num_tokens": 4008613.0,
|
|
"step": 1785
|
|
},
|
|
{
|
|
"entropy": 6.148313570022583,
|
|
"epoch": 0.20104453304880104,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999108099975064,
|
|
"loss": 6.1178,
|
|
"mean_token_accuracy": 0.1494819074869156,
|
|
"num_tokens": 4019860.0,
|
|
"step": 1790
|
|
},
|
|
{
|
|
"entropy": 5.971745538711548,
|
|
"epoch": 0.20160610995675857,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000499909676073295,
|
|
"loss": 6.0125,
|
|
"mean_token_accuracy": 0.15912038534879686,
|
|
"num_tokens": 4030602.0,
|
|
"step": 1795
|
|
},
|
|
{
|
|
"entropy": 5.967540597915649,
|
|
"epoch": 0.20216768686471612,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999085349878723,
|
|
"loss": 5.8881,
|
|
"mean_token_accuracy": 0.1551676794886589,
|
|
"num_tokens": 4041878.0,
|
|
"step": 1800
|
|
},
|
|
{
|
|
"entropy": 5.902796602249145,
|
|
"epoch": 0.20272926377267367,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999073867412746,
|
|
"loss": 5.985,
|
|
"mean_token_accuracy": 0.15298098027706147,
|
|
"num_tokens": 4052799.0,
|
|
"step": 1805
|
|
},
|
|
{
|
|
"entropy": 6.052335357666015,
|
|
"epoch": 0.20329084068063122,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999062313335385,
|
|
"loss": 5.977,
|
|
"mean_token_accuracy": 0.1513774089515209,
|
|
"num_tokens": 4064339.0,
|
|
"step": 1810
|
|
},
|
|
{
|
|
"entropy": 5.881051683425904,
|
|
"epoch": 0.20385241758858877,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999050687647008,
|
|
"loss": 5.9321,
|
|
"mean_token_accuracy": 0.15355904400348663,
|
|
"num_tokens": 4076246.0,
|
|
"step": 1815
|
|
},
|
|
{
|
|
"entropy": 5.9952904224395756,
|
|
"epoch": 0.2044139944965463,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004999038990347984,
|
|
"loss": 6.0102,
|
|
"mean_token_accuracy": 0.15132154226303102,
|
|
"num_tokens": 4088006.0,
|
|
"step": 1820
|
|
},
|
|
{
|
|
"entropy": 5.986813735961914,
|
|
"epoch": 0.20497557140450384,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999027221438688,
|
|
"loss": 6.0135,
|
|
"mean_token_accuracy": 0.1533118411898613,
|
|
"num_tokens": 4098122.0,
|
|
"step": 1825
|
|
},
|
|
{
|
|
"entropy": 6.179859924316406,
|
|
"epoch": 0.2055371483124614,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000499901538091949,
|
|
"loss": 6.2072,
|
|
"mean_token_accuracy": 0.14116512686014177,
|
|
"num_tokens": 4109958.0,
|
|
"step": 1830
|
|
},
|
|
{
|
|
"entropy": 6.044462394714356,
|
|
"epoch": 0.20609872522041894,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999003468790773,
|
|
"loss": 6.0967,
|
|
"mean_token_accuracy": 0.14568886607885362,
|
|
"num_tokens": 4121262.0,
|
|
"step": 1835
|
|
},
|
|
{
|
|
"entropy": 6.016641092300415,
|
|
"epoch": 0.2066603021283765,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998991485052911,
|
|
"loss": 5.87,
|
|
"mean_token_accuracy": 0.16044027954339982,
|
|
"num_tokens": 4130958.0,
|
|
"step": 1840
|
|
},
|
|
{
|
|
"entropy": 5.966278457641602,
|
|
"epoch": 0.20722187903633402,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000499897942970629,
|
|
"loss": 6.0778,
|
|
"mean_token_accuracy": 0.1423511266708374,
|
|
"num_tokens": 4143779.0,
|
|
"step": 1845
|
|
},
|
|
{
|
|
"entropy": 6.1042670726776125,
|
|
"epoch": 0.20778345594429157,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000499896730275129,
|
|
"loss": 6.1007,
|
|
"mean_token_accuracy": 0.14468785226345063,
|
|
"num_tokens": 4155367.0,
|
|
"step": 1850
|
|
},
|
|
{
|
|
"entropy": 5.985637760162353,
|
|
"epoch": 0.20834503285224912,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00049989551041883,
|
|
"loss": 5.9152,
|
|
"mean_token_accuracy": 0.15388040691614152,
|
|
"num_tokens": 4166657.0,
|
|
"step": 1855
|
|
},
|
|
{
|
|
"entropy": 5.961990070343018,
|
|
"epoch": 0.20890660976020667,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998942834017707,
|
|
"loss": 6.0298,
|
|
"mean_token_accuracy": 0.15152619555592536,
|
|
"num_tokens": 4177517.0,
|
|
"step": 1860
|
|
},
|
|
{
|
|
"entropy": 5.9690758228302006,
|
|
"epoch": 0.2094681866681642,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998930492239901,
|
|
"loss": 5.8913,
|
|
"mean_token_accuracy": 0.15565723478794097,
|
|
"num_tokens": 4188182.0,
|
|
"step": 1865
|
|
},
|
|
{
|
|
"entropy": 6.060051155090332,
|
|
"epoch": 0.21002976357612174,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998918078855277,
|
|
"loss": 6.0221,
|
|
"mean_token_accuracy": 0.1551324889063835,
|
|
"num_tokens": 4199415.0,
|
|
"step": 1870
|
|
},
|
|
{
|
|
"entropy": 5.884836721420288,
|
|
"epoch": 0.2105913404840793,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998905593864227,
|
|
"loss": 5.967,
|
|
"mean_token_accuracy": 0.15338498651981353,
|
|
"num_tokens": 4210025.0,
|
|
"step": 1875
|
|
},
|
|
{
|
|
"entropy": 5.985698986053467,
|
|
"epoch": 0.21115291739203684,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998893037267153,
|
|
"loss": 5.8966,
|
|
"mean_token_accuracy": 0.15888059735298157,
|
|
"num_tokens": 4219920.0,
|
|
"step": 1880
|
|
},
|
|
{
|
|
"entropy": 5.979580545425415,
|
|
"epoch": 0.2117144942999944,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004998880409064452,
|
|
"loss": 6.0678,
|
|
"mean_token_accuracy": 0.1490791544318199,
|
|
"num_tokens": 4232647.0,
|
|
"step": 1885
|
|
},
|
|
{
|
|
"entropy": 6.082404136657715,
|
|
"epoch": 0.21227607120795192,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004998867709256527,
|
|
"loss": 5.9527,
|
|
"mean_token_accuracy": 0.15514377057552337,
|
|
"num_tokens": 4242637.0,
|
|
"step": 1890
|
|
},
|
|
{
|
|
"entropy": 5.876793336868286,
|
|
"epoch": 0.21283764811590947,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000499885493784378,
|
|
"loss": 5.9242,
|
|
"mean_token_accuracy": 0.15735216736793517,
|
|
"num_tokens": 4253633.0,
|
|
"step": 1895
|
|
},
|
|
{
|
|
"entropy": 5.9101646900177,
|
|
"epoch": 0.21339922502386702,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004998842094826621,
|
|
"loss": 5.8893,
|
|
"mean_token_accuracy": 0.15901758521795273,
|
|
"num_tokens": 4264472.0,
|
|
"step": 1900
|
|
},
|
|
{
|
|
"entropy": 6.013765573501587,
|
|
"epoch": 0.21396080193182457,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004998829180205458,
|
|
"loss": 6.0058,
|
|
"mean_token_accuracy": 0.15594724267721177,
|
|
"num_tokens": 4275233.0,
|
|
"step": 1905
|
|
},
|
|
{
|
|
"entropy": 6.0052587509155275,
|
|
"epoch": 0.21452237883978212,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998816193980701,
|
|
"loss": 5.9606,
|
|
"mean_token_accuracy": 0.15338825732469558,
|
|
"num_tokens": 4287063.0,
|
|
"step": 1910
|
|
},
|
|
{
|
|
"entropy": 6.001710557937622,
|
|
"epoch": 0.21508395574773964,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998803136152764,
|
|
"loss": 5.9866,
|
|
"mean_token_accuracy": 0.15025851130485535,
|
|
"num_tokens": 4298761.0,
|
|
"step": 1915
|
|
},
|
|
{
|
|
"entropy": 5.735988998413086,
|
|
"epoch": 0.2156455326556972,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004998790006722063,
|
|
"loss": 5.8469,
|
|
"mean_token_accuracy": 0.16698734015226363,
|
|
"num_tokens": 4309650.0,
|
|
"step": 1920
|
|
},
|
|
{
|
|
"entropy": 6.018524694442749,
|
|
"epoch": 0.21620710956365474,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004998776805689016,
|
|
"loss": 5.9063,
|
|
"mean_token_accuracy": 0.16533491015434265,
|
|
"num_tokens": 4320403.0,
|
|
"step": 1925
|
|
},
|
|
{
|
|
"entropy": 5.84126296043396,
|
|
"epoch": 0.2167686864716123,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004998763533054045,
|
|
"loss": 5.932,
|
|
"mean_token_accuracy": 0.1564387321472168,
|
|
"num_tokens": 4332049.0,
|
|
"step": 1930
|
|
},
|
|
{
|
|
"entropy": 5.947682619094849,
|
|
"epoch": 0.21733026337956984,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004998750188817568,
|
|
"loss": 5.8358,
|
|
"mean_token_accuracy": 0.16291145533323287,
|
|
"num_tokens": 4342551.0,
|
|
"step": 1935
|
|
},
|
|
{
|
|
"entropy": 5.899789810180664,
|
|
"epoch": 0.21789184028752737,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004998736772980015,
|
|
"loss": 5.9692,
|
|
"mean_token_accuracy": 0.1594847857952118,
|
|
"num_tokens": 4355156.0,
|
|
"step": 1940
|
|
},
|
|
{
|
|
"entropy": 5.908867359161377,
|
|
"epoch": 0.21845341719548492,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000499872328554181,
|
|
"loss": 6.0218,
|
|
"mean_token_accuracy": 0.15519974678754805,
|
|
"num_tokens": 4367402.0,
|
|
"step": 1945
|
|
},
|
|
{
|
|
"entropy": 6.017113590240479,
|
|
"epoch": 0.21901499410344247,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004998709726503383,
|
|
"loss": 5.8973,
|
|
"mean_token_accuracy": 0.16066040098667145,
|
|
"num_tokens": 4378687.0,
|
|
"step": 1950
|
|
},
|
|
{
|
|
"entropy": 5.973746299743652,
|
|
"epoch": 0.21957657101140002,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998696095865168,
|
|
"loss": 6.0371,
|
|
"mean_token_accuracy": 0.1629161447286606,
|
|
"num_tokens": 4388871.0,
|
|
"step": 1955
|
|
},
|
|
{
|
|
"entropy": 5.922299194335937,
|
|
"epoch": 0.22013814791935757,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004998682393627595,
|
|
"loss": 5.8576,
|
|
"mean_token_accuracy": 0.16151300221681594,
|
|
"num_tokens": 4399440.0,
|
|
"step": 1960
|
|
},
|
|
{
|
|
"entropy": 5.825509119033813,
|
|
"epoch": 0.2206997248273151,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998668619791104,
|
|
"loss": 5.8555,
|
|
"mean_token_accuracy": 0.16079302430152892,
|
|
"num_tokens": 4409989.0,
|
|
"step": 1965
|
|
},
|
|
{
|
|
"entropy": 6.02225980758667,
|
|
"epoch": 0.22126130173527264,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998654774356131,
|
|
"loss": 6.0152,
|
|
"mean_token_accuracy": 0.15131131708621978,
|
|
"num_tokens": 4422149.0,
|
|
"step": 1970
|
|
},
|
|
{
|
|
"entropy": 6.051222705841065,
|
|
"epoch": 0.2218228786432302,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004998640857323118,
|
|
"loss": 6.0486,
|
|
"mean_token_accuracy": 0.15000825822353364,
|
|
"num_tokens": 4433157.0,
|
|
"step": 1975
|
|
},
|
|
{
|
|
"entropy": 6.00563907623291,
|
|
"epoch": 0.22238445555118774,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004998626868692509,
|
|
"loss": 5.973,
|
|
"mean_token_accuracy": 0.15266723185777664,
|
|
"num_tokens": 4444595.0,
|
|
"step": 1980
|
|
},
|
|
{
|
|
"entropy": 6.015877962112427,
|
|
"epoch": 0.2229460324591453,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004998612808464748,
|
|
"loss": 6.1061,
|
|
"mean_token_accuracy": 0.14999096170067788,
|
|
"num_tokens": 4456592.0,
|
|
"step": 1985
|
|
},
|
|
{
|
|
"entropy": 6.005351543426514,
|
|
"epoch": 0.22350760936710282,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004998598676640283,
|
|
"loss": 5.8623,
|
|
"mean_token_accuracy": 0.16657372564077377,
|
|
"num_tokens": 4467624.0,
|
|
"step": 1990
|
|
},
|
|
{
|
|
"entropy": 5.870333099365235,
|
|
"epoch": 0.22406918627506037,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004998584473219563,
|
|
"loss": 6.0578,
|
|
"mean_token_accuracy": 0.1522249922156334,
|
|
"num_tokens": 4479766.0,
|
|
"step": 1995
|
|
},
|
|
{
|
|
"entropy": 6.041551637649536,
|
|
"epoch": 0.22463076318301792,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998570198203043,
|
|
"loss": 5.927,
|
|
"mean_token_accuracy": 0.1541971117258072,
|
|
"num_tokens": 4490023.0,
|
|
"step": 2000
|
|
},
|
|
{
|
|
"entropy": 5.939703559875488,
|
|
"epoch": 0.22519234009097547,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004998555851591175,
|
|
"loss": 5.9578,
|
|
"mean_token_accuracy": 0.15466774851083756,
|
|
"num_tokens": 4500651.0,
|
|
"step": 2005
|
|
},
|
|
{
|
|
"entropy": 6.019627428054809,
|
|
"epoch": 0.225753916998933,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004998541433384416,
|
|
"loss": 6.0605,
|
|
"mean_token_accuracy": 0.1519089847803116,
|
|
"num_tokens": 4512934.0,
|
|
"step": 2010
|
|
},
|
|
{
|
|
"entropy": 5.9258240222930905,
|
|
"epoch": 0.22631549390689054,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004998526943583226,
|
|
"loss": 5.9379,
|
|
"mean_token_accuracy": 0.16064678132534027,
|
|
"num_tokens": 4524251.0,
|
|
"step": 2015
|
|
},
|
|
{
|
|
"entropy": 5.996880960464478,
|
|
"epoch": 0.2268770708148481,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004998512382188066,
|
|
"loss": 6.022,
|
|
"mean_token_accuracy": 0.14892027527093887,
|
|
"num_tokens": 4536025.0,
|
|
"step": 2020
|
|
},
|
|
{
|
|
"entropy": 6.004436492919922,
|
|
"epoch": 0.22743864772280564,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004998497749199401,
|
|
"loss": 5.9701,
|
|
"mean_token_accuracy": 0.158987794816494,
|
|
"num_tokens": 4546717.0,
|
|
"step": 2025
|
|
},
|
|
{
|
|
"entropy": 5.910756921768188,
|
|
"epoch": 0.2280002246307632,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004998483044617694,
|
|
"loss": 5.8651,
|
|
"mean_token_accuracy": 0.1554678872227669,
|
|
"num_tokens": 4557206.0,
|
|
"step": 2030
|
|
},
|
|
{
|
|
"entropy": 5.822503995895386,
|
|
"epoch": 0.22856180153872072,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004998468268443416,
|
|
"loss": 5.8574,
|
|
"mean_token_accuracy": 0.16205435246229172,
|
|
"num_tokens": 4568123.0,
|
|
"step": 2035
|
|
},
|
|
{
|
|
"entropy": 5.961733341217041,
|
|
"epoch": 0.22912337844667827,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004998453420677034,
|
|
"loss": 5.9819,
|
|
"mean_token_accuracy": 0.15619362890720367,
|
|
"num_tokens": 4579385.0,
|
|
"step": 2040
|
|
},
|
|
{
|
|
"entropy": 5.9808855056762695,
|
|
"epoch": 0.22968495535463582,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004998438501319025,
|
|
"loss": 6.0248,
|
|
"mean_token_accuracy": 0.15128423795104026,
|
|
"num_tokens": 4590514.0,
|
|
"step": 2045
|
|
},
|
|
{
|
|
"entropy": 6.025481367111206,
|
|
"epoch": 0.23024653226259337,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004998423510369862,
|
|
"loss": 5.9706,
|
|
"mean_token_accuracy": 0.15017401427030563,
|
|
"num_tokens": 4601624.0,
|
|
"step": 2050
|
|
},
|
|
{
|
|
"entropy": 5.990740871429443,
|
|
"epoch": 0.23080810917055092,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998408447830022,
|
|
"loss": 5.9518,
|
|
"mean_token_accuracy": 0.16115492284297944,
|
|
"num_tokens": 4612822.0,
|
|
"step": 2055
|
|
},
|
|
{
|
|
"entropy": 5.939420604705811,
|
|
"epoch": 0.23136968607850844,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998393313699985,
|
|
"loss": 5.9466,
|
|
"mean_token_accuracy": 0.16056140810251235,
|
|
"num_tokens": 4623443.0,
|
|
"step": 2060
|
|
},
|
|
{
|
|
"entropy": 5.930271577835083,
|
|
"epoch": 0.231931262986466,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004998378107980233,
|
|
"loss": 5.8579,
|
|
"mean_token_accuracy": 0.16032032370567323,
|
|
"num_tokens": 4633600.0,
|
|
"step": 2065
|
|
},
|
|
{
|
|
"entropy": 5.932555675506592,
|
|
"epoch": 0.23249283989442354,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004998362830671249,
|
|
"loss": 6.0102,
|
|
"mean_token_accuracy": 0.15435325503349304,
|
|
"num_tokens": 4644217.0,
|
|
"step": 2070
|
|
},
|
|
{
|
|
"entropy": 5.97379846572876,
|
|
"epoch": 0.2330544168023811,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998347481773522,
|
|
"loss": 6.0249,
|
|
"mean_token_accuracy": 0.1527538165450096,
|
|
"num_tokens": 4654671.0,
|
|
"step": 2075
|
|
},
|
|
{
|
|
"entropy": 5.9626545906066895,
|
|
"epoch": 0.23361599371033864,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998332061287538,
|
|
"loss": 6.0209,
|
|
"mean_token_accuracy": 0.1507769837975502,
|
|
"num_tokens": 4665920.0,
|
|
"step": 2080
|
|
},
|
|
{
|
|
"entropy": 5.939901208877563,
|
|
"epoch": 0.23417757061829617,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000499831656921379,
|
|
"loss": 5.8997,
|
|
"mean_token_accuracy": 0.1583072543144226,
|
|
"num_tokens": 4675406.0,
|
|
"step": 2085
|
|
},
|
|
{
|
|
"entropy": 6.018610954284668,
|
|
"epoch": 0.23473914752625372,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000499830100555277,
|
|
"loss": 5.9357,
|
|
"mean_token_accuracy": 0.15790688395500183,
|
|
"num_tokens": 4686870.0,
|
|
"step": 2090
|
|
},
|
|
{
|
|
"entropy": 5.953982305526734,
|
|
"epoch": 0.23530072443421127,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004998285370304974,
|
|
"loss": 6.0124,
|
|
"mean_token_accuracy": 0.15949206352233886,
|
|
"num_tokens": 4698926.0,
|
|
"step": 2095
|
|
},
|
|
{
|
|
"entropy": 6.0622725009918215,
|
|
"epoch": 0.23586230134216882,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00049982696634709,
|
|
"loss": 6.0882,
|
|
"mean_token_accuracy": 0.14462199285626412,
|
|
"num_tokens": 4709318.0,
|
|
"step": 2100
|
|
},
|
|
{
|
|
"entropy": 5.849839591979981,
|
|
"epoch": 0.23642387825012637,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004998253885051048,
|
|
"loss": 5.7796,
|
|
"mean_token_accuracy": 0.16810209602117537,
|
|
"num_tokens": 4718819.0,
|
|
"step": 2105
|
|
},
|
|
{
|
|
"entropy": 5.884680938720703,
|
|
"epoch": 0.2369854551580839,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000499823803504592,
|
|
"loss": 5.8314,
|
|
"mean_token_accuracy": 0.16093335300683975,
|
|
"num_tokens": 4729513.0,
|
|
"step": 2110
|
|
},
|
|
{
|
|
"entropy": 5.859940433502198,
|
|
"epoch": 0.23754703206604144,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998222113456022,
|
|
"loss": 5.9287,
|
|
"mean_token_accuracy": 0.15834257006645203,
|
|
"num_tokens": 4739875.0,
|
|
"step": 2115
|
|
},
|
|
{
|
|
"entropy": 6.060333490371704,
|
|
"epoch": 0.238108608973999,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004998206120281858,
|
|
"loss": 6.0609,
|
|
"mean_token_accuracy": 0.14767249599099158,
|
|
"num_tokens": 4752933.0,
|
|
"step": 2120
|
|
},
|
|
{
|
|
"entropy": 5.938970279693604,
|
|
"epoch": 0.23867018588195654,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000499819005552394,
|
|
"loss": 5.8526,
|
|
"mean_token_accuracy": 0.16048028618097304,
|
|
"num_tokens": 4762969.0,
|
|
"step": 2125
|
|
},
|
|
{
|
|
"entropy": 5.958646631240844,
|
|
"epoch": 0.23923176278991407,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004998173919182779,
|
|
"loss": 5.9439,
|
|
"mean_token_accuracy": 0.15564859807491302,
|
|
"num_tokens": 4773495.0,
|
|
"step": 2130
|
|
},
|
|
{
|
|
"entropy": 5.948372316360474,
|
|
"epoch": 0.23979333969787162,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000499815771125889,
|
|
"loss": 5.9773,
|
|
"mean_token_accuracy": 0.16150738894939423,
|
|
"num_tokens": 4785335.0,
|
|
"step": 2135
|
|
},
|
|
{
|
|
"entropy": 6.081469774246216,
|
|
"epoch": 0.24035491660582917,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004998141431752785,
|
|
"loss": 6.1175,
|
|
"mean_token_accuracy": 0.14878264293074608,
|
|
"num_tokens": 4798068.0,
|
|
"step": 2140
|
|
},
|
|
{
|
|
"entropy": 5.92440824508667,
|
|
"epoch": 0.24091649351378672,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004998125080664987,
|
|
"loss": 5.9373,
|
|
"mean_token_accuracy": 0.1596187397837639,
|
|
"num_tokens": 4809338.0,
|
|
"step": 2145
|
|
},
|
|
{
|
|
"entropy": 5.900418853759765,
|
|
"epoch": 0.24147807042174427,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998108657996012,
|
|
"loss": 5.9278,
|
|
"mean_token_accuracy": 0.1604372188448906,
|
|
"num_tokens": 4819636.0,
|
|
"step": 2150
|
|
},
|
|
{
|
|
"entropy": 5.9336934089660645,
|
|
"epoch": 0.2420396473297018,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004998092163746387,
|
|
"loss": 5.9066,
|
|
"mean_token_accuracy": 0.16119810789823533,
|
|
"num_tokens": 4830975.0,
|
|
"step": 2155
|
|
},
|
|
{
|
|
"entropy": 5.893611574172974,
|
|
"epoch": 0.24260122423765934,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004998075597916636,
|
|
"loss": 5.9428,
|
|
"mean_token_accuracy": 0.15798580050468444,
|
|
"num_tokens": 4841951.0,
|
|
"step": 2160
|
|
},
|
|
{
|
|
"entropy": 6.011291074752807,
|
|
"epoch": 0.2431628011456169,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998058960507286,
|
|
"loss": 5.9185,
|
|
"mean_token_accuracy": 0.15732098147273063,
|
|
"num_tokens": 4852919.0,
|
|
"step": 2165
|
|
},
|
|
{
|
|
"entropy": 5.955287456512451,
|
|
"epoch": 0.24372437805357444,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998042251518866,
|
|
"loss": 5.9264,
|
|
"mean_token_accuracy": 0.1588020294904709,
|
|
"num_tokens": 4863433.0,
|
|
"step": 2170
|
|
},
|
|
{
|
|
"entropy": 6.019167184829712,
|
|
"epoch": 0.244285954961532,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004998025470951908,
|
|
"loss": 6.0132,
|
|
"mean_token_accuracy": 0.15414848923683167,
|
|
"num_tokens": 4875685.0,
|
|
"step": 2175
|
|
},
|
|
{
|
|
"entropy": 5.848620128631592,
|
|
"epoch": 0.24484753186948952,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004998008618806949,
|
|
"loss": 5.9081,
|
|
"mean_token_accuracy": 0.15716440230607986,
|
|
"num_tokens": 4886347.0,
|
|
"step": 2180
|
|
},
|
|
{
|
|
"entropy": 5.924430418014526,
|
|
"epoch": 0.24540910877744707,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004997991695084523,
|
|
"loss": 5.8998,
|
|
"mean_token_accuracy": 0.16334613561630248,
|
|
"num_tokens": 4896898.0,
|
|
"step": 2185
|
|
},
|
|
{
|
|
"entropy": 5.999474620819091,
|
|
"epoch": 0.24597068568540462,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004997974699785169,
|
|
"loss": 6.0128,
|
|
"mean_token_accuracy": 0.15362882167100905,
|
|
"num_tokens": 4908892.0,
|
|
"step": 2190
|
|
},
|
|
{
|
|
"entropy": 5.907583093643188,
|
|
"epoch": 0.24653226259336217,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004997957632909429,
|
|
"loss": 5.9471,
|
|
"mean_token_accuracy": 0.15109152495861053,
|
|
"num_tokens": 4920855.0,
|
|
"step": 2195
|
|
},
|
|
{
|
|
"entropy": 6.013603639602661,
|
|
"epoch": 0.24709383950131972,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004997940494457846,
|
|
"loss": 5.9325,
|
|
"mean_token_accuracy": 0.16000126004219056,
|
|
"num_tokens": 4932857.0,
|
|
"step": 2200
|
|
},
|
|
{
|
|
"entropy": 5.8864202976226805,
|
|
"epoch": 0.24765541640927724,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004997923284430967,
|
|
"loss": 5.9747,
|
|
"mean_token_accuracy": 0.15626695305109023,
|
|
"num_tokens": 4944063.0,
|
|
"step": 2205
|
|
},
|
|
{
|
|
"entropy": 5.871590852737427,
|
|
"epoch": 0.2482169933172348,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004997906002829338,
|
|
"loss": 5.8432,
|
|
"mean_token_accuracy": 0.16545321345329284,
|
|
"num_tokens": 4955126.0,
|
|
"step": 2210
|
|
},
|
|
{
|
|
"entropy": 6.042226839065552,
|
|
"epoch": 0.24877857022519234,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000499788864965351,
|
|
"loss": 6.0353,
|
|
"mean_token_accuracy": 0.15824319273233414,
|
|
"num_tokens": 4965738.0,
|
|
"step": 2215
|
|
},
|
|
{
|
|
"entropy": 6.032025718688965,
|
|
"epoch": 0.2493401471331499,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004997871224904036,
|
|
"loss": 6.0553,
|
|
"mean_token_accuracy": 0.15088909566402436,
|
|
"num_tokens": 4976963.0,
|
|
"step": 2220
|
|
},
|
|
{
|
|
"entropy": 5.968750953674316,
|
|
"epoch": 0.24990172404110744,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004997853728581468,
|
|
"loss": 5.9356,
|
|
"mean_token_accuracy": 0.15454284846782684,
|
|
"num_tokens": 4987577.0,
|
|
"step": 2225
|
|
},
|
|
{
|
|
"entropy": 5.988882637023925,
|
|
"epoch": 0.250463300949065,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004997836160686368,
|
|
"loss": 6.0657,
|
|
"mean_token_accuracy": 0.15284020453691483,
|
|
"num_tokens": 5000234.0,
|
|
"step": 2230
|
|
},
|
|
{
|
|
"entropy": 5.972144842147827,
|
|
"epoch": 0.25102487785702254,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004997818521219291,
|
|
"loss": 5.8895,
|
|
"mean_token_accuracy": 0.15354024320840837,
|
|
"num_tokens": 5011652.0,
|
|
"step": 2235
|
|
},
|
|
{
|
|
"entropy": 5.973802328109741,
|
|
"epoch": 0.25158645476498004,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004997800810180803,
|
|
"loss": 5.9329,
|
|
"mean_token_accuracy": 0.1593118280172348,
|
|
"num_tokens": 5023603.0,
|
|
"step": 2240
|
|
},
|
|
{
|
|
"entropy": 5.892467927932739,
|
|
"epoch": 0.2521480316729376,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004997783027571464,
|
|
"loss": 5.9091,
|
|
"mean_token_accuracy": 0.15956079661846162,
|
|
"num_tokens": 5034427.0,
|
|
"step": 2245
|
|
},
|
|
{
|
|
"entropy": 5.859362268447876,
|
|
"epoch": 0.25270960858089514,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004997765173391841,
|
|
"loss": 5.8988,
|
|
"mean_token_accuracy": 0.15956594049930573,
|
|
"num_tokens": 5045738.0,
|
|
"step": 2250
|
|
},
|
|
{
|
|
"entropy": 5.869083404541016,
|
|
"epoch": 0.2532711854888527,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004997747247642505,
|
|
"loss": 5.8353,
|
|
"mean_token_accuracy": 0.15759642720222472,
|
|
"num_tokens": 5057021.0,
|
|
"step": 2255
|
|
},
|
|
{
|
|
"entropy": 5.92234172821045,
|
|
"epoch": 0.25383276239681024,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004997729250324023,
|
|
"loss": 5.9244,
|
|
"mean_token_accuracy": 0.15921089351177214,
|
|
"num_tokens": 5067676.0,
|
|
"step": 2260
|
|
},
|
|
{
|
|
"entropy": 5.886710166931152,
|
|
"epoch": 0.2543943393047678,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004997711181436971,
|
|
"loss": 5.8615,
|
|
"mean_token_accuracy": 0.15837088972330093,
|
|
"num_tokens": 5079422.0,
|
|
"step": 2265
|
|
},
|
|
{
|
|
"entropy": 5.822842216491699,
|
|
"epoch": 0.25495591621272534,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004997693040981922,
|
|
"loss": 5.8851,
|
|
"mean_token_accuracy": 0.16085467636585235,
|
|
"num_tokens": 5091242.0,
|
|
"step": 2270
|
|
},
|
|
{
|
|
"entropy": 6.006762552261352,
|
|
"epoch": 0.2555174931206829,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004997674828959456,
|
|
"loss": 5.8909,
|
|
"mean_token_accuracy": 0.15583527684211732,
|
|
"num_tokens": 5102251.0,
|
|
"step": 2275
|
|
},
|
|
{
|
|
"entropy": 5.857793092727661,
|
|
"epoch": 0.25607907002864044,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004997656545370151,
|
|
"loss": 5.9104,
|
|
"mean_token_accuracy": 0.1610156461596489,
|
|
"num_tokens": 5113276.0,
|
|
"step": 2280
|
|
},
|
|
{
|
|
"entropy": 5.934245014190674,
|
|
"epoch": 0.256640646936598,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000499763819021459,
|
|
"loss": 5.9191,
|
|
"mean_token_accuracy": 0.15731906294822692,
|
|
"num_tokens": 5124472.0,
|
|
"step": 2285
|
|
},
|
|
{
|
|
"entropy": 5.863279104232788,
|
|
"epoch": 0.2572022238445555,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004997619763493357,
|
|
"loss": 5.8698,
|
|
"mean_token_accuracy": 0.1613835647702217,
|
|
"num_tokens": 5134896.0,
|
|
"step": 2290
|
|
},
|
|
{
|
|
"entropy": 5.962464809417725,
|
|
"epoch": 0.25776380075251304,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000499760126520704,
|
|
"loss": 5.95,
|
|
"mean_token_accuracy": 0.1634097322821617,
|
|
"num_tokens": 5145115.0,
|
|
"step": 2295
|
|
},
|
|
{
|
|
"entropy": 5.927261829376221,
|
|
"epoch": 0.2583253776604706,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004997582695356225,
|
|
"loss": 5.9289,
|
|
"mean_token_accuracy": 0.15928202718496323,
|
|
"num_tokens": 5155620.0,
|
|
"step": 2300
|
|
},
|
|
{
|
|
"entropy": 6.070884418487549,
|
|
"epoch": 0.25888695456842814,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004997564053941507,
|
|
"loss": 6.0126,
|
|
"mean_token_accuracy": 0.15451653599739074,
|
|
"num_tokens": 5166260.0,
|
|
"step": 2305
|
|
},
|
|
{
|
|
"entropy": 5.954886245727539,
|
|
"epoch": 0.2594485314763857,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004997545340963478,
|
|
"loss": 5.8733,
|
|
"mean_token_accuracy": 0.15934662520885468,
|
|
"num_tokens": 5177143.0,
|
|
"step": 2310
|
|
},
|
|
{
|
|
"entropy": 5.921825218200683,
|
|
"epoch": 0.26001010838434324,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004997526556422733,
|
|
"loss": 6.0233,
|
|
"mean_token_accuracy": 0.15293444991111754,
|
|
"num_tokens": 5187795.0,
|
|
"step": 2315
|
|
},
|
|
{
|
|
"entropy": 5.922110557556152,
|
|
"epoch": 0.2605716852923008,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004997507700319872,
|
|
"loss": 5.8811,
|
|
"mean_token_accuracy": 0.16001545637845993,
|
|
"num_tokens": 5199365.0,
|
|
"step": 2320
|
|
},
|
|
{
|
|
"entropy": 5.971580982208252,
|
|
"epoch": 0.26113326220025834,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004997488772655492,
|
|
"loss": 6.0976,
|
|
"mean_token_accuracy": 0.15617025047540664,
|
|
"num_tokens": 5212264.0,
|
|
"step": 2325
|
|
},
|
|
{
|
|
"entropy": 6.042904090881348,
|
|
"epoch": 0.2616948391082159,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004997469773430199,
|
|
"loss": 5.9253,
|
|
"mean_token_accuracy": 0.15450814068317414,
|
|
"num_tokens": 5223544.0,
|
|
"step": 2330
|
|
},
|
|
{
|
|
"entropy": 5.868034029006958,
|
|
"epoch": 0.2622564160161734,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004997450702644596,
|
|
"loss": 5.875,
|
|
"mean_token_accuracy": 0.1604365214705467,
|
|
"num_tokens": 5234713.0,
|
|
"step": 2335
|
|
},
|
|
{
|
|
"entropy": 5.9823534965515135,
|
|
"epoch": 0.26281799292413094,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004997431560299292,
|
|
"loss": 5.9591,
|
|
"mean_token_accuracy": 0.15298095047473909,
|
|
"num_tokens": 5246103.0,
|
|
"step": 2340
|
|
},
|
|
{
|
|
"entropy": 5.814671277999878,
|
|
"epoch": 0.2633795698320885,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004997412346394894,
|
|
"loss": 5.7917,
|
|
"mean_token_accuracy": 0.16624176353216172,
|
|
"num_tokens": 5257372.0,
|
|
"step": 2345
|
|
},
|
|
{
|
|
"entropy": 5.792899942398071,
|
|
"epoch": 0.26394114674004604,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004997393060932017,
|
|
"loss": 5.8609,
|
|
"mean_token_accuracy": 0.16722605973482133,
|
|
"num_tokens": 5268677.0,
|
|
"step": 2350
|
|
},
|
|
{
|
|
"entropy": 5.997194576263428,
|
|
"epoch": 0.2645027236480036,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004997373703911273,
|
|
"loss": 5.9247,
|
|
"mean_token_accuracy": 0.16152105778455733,
|
|
"num_tokens": 5279056.0,
|
|
"step": 2355
|
|
},
|
|
{
|
|
"entropy": 5.786316013336181,
|
|
"epoch": 0.26506430055596114,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004997354275333277,
|
|
"loss": 5.8069,
|
|
"mean_token_accuracy": 0.16789699494838714,
|
|
"num_tokens": 5289310.0,
|
|
"step": 2360
|
|
},
|
|
{
|
|
"entropy": 5.953582143783569,
|
|
"epoch": 0.2656258774639187,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.000499733477519865,
|
|
"loss": 5.8956,
|
|
"mean_token_accuracy": 0.16771894991397857,
|
|
"num_tokens": 5300619.0,
|
|
"step": 2365
|
|
},
|
|
{
|
|
"entropy": 6.053738594055176,
|
|
"epoch": 0.26618745437187624,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004997315203508013,
|
|
"loss": 6.0608,
|
|
"mean_token_accuracy": 0.1562006339430809,
|
|
"num_tokens": 5311554.0,
|
|
"step": 2370
|
|
},
|
|
{
|
|
"entropy": 5.966435718536377,
|
|
"epoch": 0.2667490312798338,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004997295560261988,
|
|
"loss": 5.883,
|
|
"mean_token_accuracy": 0.1612299293279648,
|
|
"num_tokens": 5323592.0,
|
|
"step": 2375
|
|
},
|
|
{
|
|
"entropy": 5.942288255691528,
|
|
"epoch": 0.26731060818779134,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00049972758454612,
|
|
"loss": 5.9767,
|
|
"mean_token_accuracy": 0.15383181422948838,
|
|
"num_tokens": 5334978.0,
|
|
"step": 2380
|
|
},
|
|
{
|
|
"entropy": 5.898320913314819,
|
|
"epoch": 0.26787218509574884,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004997256059106279,
|
|
"loss": 5.8667,
|
|
"mean_token_accuracy": 0.15778945684432982,
|
|
"num_tokens": 5345724.0,
|
|
"step": 2385
|
|
},
|
|
{
|
|
"entropy": 5.94132432937622,
|
|
"epoch": 0.2684337620037064,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004997236201197853,
|
|
"loss": 5.9989,
|
|
"mean_token_accuracy": 0.15381949245929719,
|
|
"num_tokens": 5357141.0,
|
|
"step": 2390
|
|
},
|
|
{
|
|
"entropy": 5.9436756610870365,
|
|
"epoch": 0.26899533891166394,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004997216271736554,
|
|
"loss": 5.995,
|
|
"mean_token_accuracy": 0.15819256901741027,
|
|
"num_tokens": 5367889.0,
|
|
"step": 2395
|
|
},
|
|
{
|
|
"entropy": 5.786690282821655,
|
|
"epoch": 0.2695569158196215,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004997196270723018,
|
|
"loss": 5.7261,
|
|
"mean_token_accuracy": 0.16399870365858077,
|
|
"num_tokens": 5379329.0,
|
|
"step": 2400
|
|
},
|
|
{
|
|
"entropy": 5.895531129837036,
|
|
"epoch": 0.27011849272757904,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004997176198157881,
|
|
"loss": 5.8852,
|
|
"mean_token_accuracy": 0.1617034539580345,
|
|
"num_tokens": 5389525.0,
|
|
"step": 2405
|
|
},
|
|
{
|
|
"entropy": 5.895331811904907,
|
|
"epoch": 0.2706800696355366,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004997156054041781,
|
|
"loss": 5.7958,
|
|
"mean_token_accuracy": 0.16883354038000106,
|
|
"num_tokens": 5401061.0,
|
|
"step": 2410
|
|
},
|
|
{
|
|
"entropy": 5.873462343215943,
|
|
"epoch": 0.27124164654349414,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004997135838375362,
|
|
"loss": 5.8949,
|
|
"mean_token_accuracy": 0.1616640195250511,
|
|
"num_tokens": 5411791.0,
|
|
"step": 2415
|
|
},
|
|
{
|
|
"entropy": 5.908325338363648,
|
|
"epoch": 0.2718032234514517,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004997115551159267,
|
|
"loss": 5.8467,
|
|
"mean_token_accuracy": 0.16689947098493577,
|
|
"num_tokens": 5422790.0,
|
|
"step": 2420
|
|
},
|
|
{
|
|
"entropy": 5.738713026046753,
|
|
"epoch": 0.27236480035940924,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000499709519239414,
|
|
"loss": 5.7951,
|
|
"mean_token_accuracy": 0.1616228774189949,
|
|
"num_tokens": 5434170.0,
|
|
"step": 2425
|
|
},
|
|
{
|
|
"entropy": 5.972346496582031,
|
|
"epoch": 0.2729263772673668,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.0004997074762080632,
|
|
"loss": 5.922,
|
|
"mean_token_accuracy": 0.15746588557958602,
|
|
"num_tokens": 5445948.0,
|
|
"step": 2430
|
|
},
|
|
{
|
|
"entropy": 5.907391738891602,
|
|
"epoch": 0.2734879541753243,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000499705426021939,
|
|
"loss": 5.8828,
|
|
"mean_token_accuracy": 0.15904785543680192,
|
|
"num_tokens": 5457786.0,
|
|
"step": 2435
|
|
},
|
|
{
|
|
"entropy": 5.784610605239868,
|
|
"epoch": 0.27404953108328184,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000499703368681107,
|
|
"loss": 5.8589,
|
|
"mean_token_accuracy": 0.16070218682289122,
|
|
"num_tokens": 5469434.0,
|
|
"step": 2440
|
|
},
|
|
{
|
|
"entropy": 5.8818888664245605,
|
|
"epoch": 0.2746111079912394,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004997013041856326,
|
|
"loss": 5.8549,
|
|
"mean_token_accuracy": 0.1531570464372635,
|
|
"num_tokens": 5480393.0,
|
|
"step": 2445
|
|
},
|
|
{
|
|
"entropy": 5.844133996963501,
|
|
"epoch": 0.27517268489919694,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004996992325355815,
|
|
"loss": 5.8264,
|
|
"mean_token_accuracy": 0.16376967430114747,
|
|
"num_tokens": 5490452.0,
|
|
"step": 2450
|
|
},
|
|
{
|
|
"entropy": 5.843231868743897,
|
|
"epoch": 0.2757342618071545,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004996971537310198,
|
|
"loss": 5.7996,
|
|
"mean_token_accuracy": 0.16604796648025513,
|
|
"num_tokens": 5501404.0,
|
|
"step": 2455
|
|
},
|
|
{
|
|
"entropy": 5.97615795135498,
|
|
"epoch": 0.27629583871511204,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004996950677720133,
|
|
"loss": 5.9411,
|
|
"mean_token_accuracy": 0.15309768170118332,
|
|
"num_tokens": 5512938.0,
|
|
"step": 2460
|
|
},
|
|
{
|
|
"entropy": 5.879659843444824,
|
|
"epoch": 0.2768574156230696,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000499692974658629,
|
|
"loss": 5.8641,
|
|
"mean_token_accuracy": 0.15448336452245712,
|
|
"num_tokens": 5524009.0,
|
|
"step": 2465
|
|
},
|
|
{
|
|
"entropy": 5.961763477325439,
|
|
"epoch": 0.27741899253102714,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004996908743909331,
|
|
"loss": 5.9491,
|
|
"mean_token_accuracy": 0.15658549070358277,
|
|
"num_tokens": 5535930.0,
|
|
"step": 2470
|
|
},
|
|
{
|
|
"entropy": 5.943891477584839,
|
|
"epoch": 0.2779805694389847,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004996887669689926,
|
|
"loss": 5.9378,
|
|
"mean_token_accuracy": 0.1560988336801529,
|
|
"num_tokens": 5547295.0,
|
|
"step": 2475
|
|
},
|
|
{
|
|
"entropy": 5.934115314483643,
|
|
"epoch": 0.2785421463469422,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004996866523928747,
|
|
"loss": 5.8393,
|
|
"mean_token_accuracy": 0.1640307277441025,
|
|
"num_tokens": 5558447.0,
|
|
"step": 2480
|
|
},
|
|
{
|
|
"entropy": 5.91972165107727,
|
|
"epoch": 0.27910372325489974,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004996845306626467,
|
|
"loss": 5.9369,
|
|
"mean_token_accuracy": 0.16300042271614074,
|
|
"num_tokens": 5569822.0,
|
|
"step": 2485
|
|
},
|
|
{
|
|
"entropy": 5.9508904933929445,
|
|
"epoch": 0.2796653001628573,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004996824017783759,
|
|
"loss": 5.9902,
|
|
"mean_token_accuracy": 0.15508754998445512,
|
|
"num_tokens": 5582284.0,
|
|
"step": 2490
|
|
},
|
|
{
|
|
"entropy": 5.9683637619018555,
|
|
"epoch": 0.28022687707081484,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004996802657401304,
|
|
"loss": 5.879,
|
|
"mean_token_accuracy": 0.1611318975687027,
|
|
"num_tokens": 5593765.0,
|
|
"step": 2495
|
|
},
|
|
{
|
|
"entropy": 5.801318073272705,
|
|
"epoch": 0.2807884539787724,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004996781225479781,
|
|
"loss": 5.8487,
|
|
"mean_token_accuracy": 0.15998225808143615,
|
|
"num_tokens": 5605080.0,
|
|
"step": 2500
|
|
},
|
|
{
|
|
"entropy": 6.015531349182129,
|
|
"epoch": 0.28135003088672994,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004996759722019872,
|
|
"loss": 6.011,
|
|
"mean_token_accuracy": 0.15439892411231995,
|
|
"num_tokens": 5616739.0,
|
|
"step": 2505
|
|
},
|
|
{
|
|
"entropy": 5.904989242553711,
|
|
"epoch": 0.2819116077946875,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004996738147022262,
|
|
"loss": 5.8735,
|
|
"mean_token_accuracy": 0.1576665908098221,
|
|
"num_tokens": 5628779.0,
|
|
"step": 2510
|
|
},
|
|
{
|
|
"entropy": 5.889083909988403,
|
|
"epoch": 0.28247318470264504,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004996716500487638,
|
|
"loss": 5.909,
|
|
"mean_token_accuracy": 0.15748686641454696,
|
|
"num_tokens": 5639168.0,
|
|
"step": 2515
|
|
},
|
|
{
|
|
"entropy": 5.893275928497315,
|
|
"epoch": 0.2830347616106026,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000499669478241669,
|
|
"loss": 5.885,
|
|
"mean_token_accuracy": 0.15599167197942734,
|
|
"num_tokens": 5650739.0,
|
|
"step": 2520
|
|
},
|
|
{
|
|
"entropy": 5.933381366729736,
|
|
"epoch": 0.28359633851856014,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004996672992810108,
|
|
"loss": 5.9054,
|
|
"mean_token_accuracy": 0.15816623866558074,
|
|
"num_tokens": 5662630.0,
|
|
"step": 2525
|
|
},
|
|
{
|
|
"entropy": 5.921469497680664,
|
|
"epoch": 0.28415791542651764,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004996651131668587,
|
|
"loss": 5.9083,
|
|
"mean_token_accuracy": 0.1671989306807518,
|
|
"num_tokens": 5673473.0,
|
|
"step": 2530
|
|
},
|
|
{
|
|
"entropy": 5.915191793441773,
|
|
"epoch": 0.2847194923344752,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004996629198992823,
|
|
"loss": 6.0544,
|
|
"mean_token_accuracy": 0.15136269852519035,
|
|
"num_tokens": 5686577.0,
|
|
"step": 2535
|
|
},
|
|
{
|
|
"entropy": 5.963024854660034,
|
|
"epoch": 0.28528106924243274,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004996607194783513,
|
|
"loss": 5.8035,
|
|
"mean_token_accuracy": 0.15977411419153215,
|
|
"num_tokens": 5697570.0,
|
|
"step": 2540
|
|
},
|
|
{
|
|
"entropy": 5.849263906478882,
|
|
"epoch": 0.2858426461503903,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004996585119041359,
|
|
"loss": 5.8717,
|
|
"mean_token_accuracy": 0.15102790147066117,
|
|
"num_tokens": 5708601.0,
|
|
"step": 2545
|
|
},
|
|
{
|
|
"entropy": 5.817156410217285,
|
|
"epoch": 0.28640422305834784,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004996562971767063,
|
|
"loss": 5.8333,
|
|
"mean_token_accuracy": 0.1580057695508003,
|
|
"num_tokens": 5719619.0,
|
|
"step": 2550
|
|
},
|
|
{
|
|
"entropy": 5.881134510040283,
|
|
"epoch": 0.2869657999663054,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000499654075296133,
|
|
"loss": 5.854,
|
|
"mean_token_accuracy": 0.16304896473884584,
|
|
"num_tokens": 5730061.0,
|
|
"step": 2555
|
|
},
|
|
{
|
|
"entropy": 5.887245082855225,
|
|
"epoch": 0.28752737687426294,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000499651846262487,
|
|
"loss": 5.8781,
|
|
"mean_token_accuracy": 0.16307636797428132,
|
|
"num_tokens": 5741579.0,
|
|
"step": 2560
|
|
},
|
|
{
|
|
"entropy": 5.929854440689087,
|
|
"epoch": 0.2880889537822205,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004996496100758389,
|
|
"loss": 5.8899,
|
|
"mean_token_accuracy": 0.16015600562095642,
|
|
"num_tokens": 5754001.0,
|
|
"step": 2565
|
|
},
|
|
{
|
|
"entropy": 5.956954383850098,
|
|
"epoch": 0.28865053069017804,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004996473667362604,
|
|
"loss": 5.9762,
|
|
"mean_token_accuracy": 0.15367593243718147,
|
|
"num_tokens": 5766224.0,
|
|
"step": 2570
|
|
},
|
|
{
|
|
"entropy": 5.9173064708709715,
|
|
"epoch": 0.28921210759813554,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004996451162438224,
|
|
"loss": 5.9514,
|
|
"mean_token_accuracy": 0.1529170662164688,
|
|
"num_tokens": 5777475.0,
|
|
"step": 2575
|
|
},
|
|
{
|
|
"entropy": 5.9922263622283936,
|
|
"epoch": 0.2897736845060931,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004996428585985967,
|
|
"loss": 5.9243,
|
|
"mean_token_accuracy": 0.15300409942865373,
|
|
"num_tokens": 5788359.0,
|
|
"step": 2580
|
|
},
|
|
{
|
|
"entropy": 5.833764743804932,
|
|
"epoch": 0.29033526141405064,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004996405938006553,
|
|
"loss": 5.88,
|
|
"mean_token_accuracy": 0.1589822694659233,
|
|
"num_tokens": 5799116.0,
|
|
"step": 2585
|
|
},
|
|
{
|
|
"entropy": 5.849058294296265,
|
|
"epoch": 0.2908968383220082,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004996383218500703,
|
|
"loss": 5.8163,
|
|
"mean_token_accuracy": 0.16485902518033982,
|
|
"num_tokens": 5811221.0,
|
|
"step": 2590
|
|
},
|
|
{
|
|
"entropy": 5.903125619888305,
|
|
"epoch": 0.29145841522996574,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000499636042746914,
|
|
"loss": 5.8986,
|
|
"mean_token_accuracy": 0.1597510278224945,
|
|
"num_tokens": 5822099.0,
|
|
"step": 2595
|
|
},
|
|
{
|
|
"entropy": 5.908592653274536,
|
|
"epoch": 0.2920199921379233,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000499633756491259,
|
|
"loss": 5.8603,
|
|
"mean_token_accuracy": 0.154727041721344,
|
|
"num_tokens": 5832836.0,
|
|
"step": 2600
|
|
},
|
|
{
|
|
"entropy": 5.813444709777832,
|
|
"epoch": 0.29258156904588084,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004996314630831781,
|
|
"loss": 5.8066,
|
|
"mean_token_accuracy": 0.15686748921871185,
|
|
"num_tokens": 5842892.0,
|
|
"step": 2605
|
|
},
|
|
{
|
|
"entropy": 5.8215662956237795,
|
|
"epoch": 0.2931431459538384,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004996291625227443,
|
|
"loss": 5.7707,
|
|
"mean_token_accuracy": 0.17027000188827515,
|
|
"num_tokens": 5852909.0,
|
|
"step": 2610
|
|
},
|
|
{
|
|
"entropy": 5.975628280639649,
|
|
"epoch": 0.29370472286179594,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004996268548100307,
|
|
"loss": 5.9509,
|
|
"mean_token_accuracy": 0.15499749705195426,
|
|
"num_tokens": 5864676.0,
|
|
"step": 2615
|
|
},
|
|
{
|
|
"entropy": 5.67653169631958,
|
|
"epoch": 0.2942662997697535,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000499624539945111,
|
|
"loss": 5.6832,
|
|
"mean_token_accuracy": 0.17367247641086578,
|
|
"num_tokens": 5875258.0,
|
|
"step": 2620
|
|
},
|
|
{
|
|
"entropy": 5.918656921386718,
|
|
"epoch": 0.294827876677711,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004996222179280589,
|
|
"loss": 5.8505,
|
|
"mean_token_accuracy": 0.16116076856851577,
|
|
"num_tokens": 5885611.0,
|
|
"step": 2625
|
|
},
|
|
{
|
|
"entropy": 5.846941518783569,
|
|
"epoch": 0.29538945358566854,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004996198887589481,
|
|
"loss": 5.8257,
|
|
"mean_token_accuracy": 0.15930989608168603,
|
|
"num_tokens": 5896726.0,
|
|
"step": 2630
|
|
},
|
|
{
|
|
"entropy": 5.917367076873779,
|
|
"epoch": 0.2959510304936261,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004996175524378531,
|
|
"loss": 5.851,
|
|
"mean_token_accuracy": 0.1528210312128067,
|
|
"num_tokens": 5907860.0,
|
|
"step": 2635
|
|
},
|
|
{
|
|
"entropy": 5.806666278839112,
|
|
"epoch": 0.29651260740158364,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000499615208964848,
|
|
"loss": 5.798,
|
|
"mean_token_accuracy": 0.1638117402791977,
|
|
"num_tokens": 5918676.0,
|
|
"step": 2640
|
|
},
|
|
{
|
|
"entropy": 5.9251220703125,
|
|
"epoch": 0.2970741843095412,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004996128583400077,
|
|
"loss": 5.8618,
|
|
"mean_token_accuracy": 0.16403974294662477,
|
|
"num_tokens": 5928646.0,
|
|
"step": 2645
|
|
},
|
|
{
|
|
"entropy": 5.816641330718994,
|
|
"epoch": 0.29763576121749874,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004996105005634066,
|
|
"loss": 5.8735,
|
|
"mean_token_accuracy": 0.1569816768169403,
|
|
"num_tokens": 5938990.0,
|
|
"step": 2650
|
|
},
|
|
{
|
|
"entropy": 5.8617603302001955,
|
|
"epoch": 0.2981973381254563,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004996081356351202,
|
|
"loss": 5.8194,
|
|
"mean_token_accuracy": 0.16183129400014878,
|
|
"num_tokens": 5948811.0,
|
|
"step": 2655
|
|
},
|
|
{
|
|
"entropy": 5.812265920639038,
|
|
"epoch": 0.29875891503341384,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004996057635552237,
|
|
"loss": 5.8406,
|
|
"mean_token_accuracy": 0.16514092236757277,
|
|
"num_tokens": 5959227.0,
|
|
"step": 2660
|
|
},
|
|
{
|
|
"entropy": 5.8553258895874025,
|
|
"epoch": 0.2993204919413714,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004996033843237925,
|
|
"loss": 5.7535,
|
|
"mean_token_accuracy": 0.16563905775547028,
|
|
"num_tokens": 5970546.0,
|
|
"step": 2665
|
|
},
|
|
{
|
|
"entropy": 5.982068204879761,
|
|
"epoch": 0.29988206884932894,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004996009979409025,
|
|
"loss": 6.0502,
|
|
"mean_token_accuracy": 0.147099506855011,
|
|
"num_tokens": 5983936.0,
|
|
"step": 2670
|
|
},
|
|
{
|
|
"entropy": 5.802636957168579,
|
|
"epoch": 0.30044364575728644,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004995986044066295,
|
|
"loss": 5.8494,
|
|
"mean_token_accuracy": 0.15568828135728835,
|
|
"num_tokens": 5994963.0,
|
|
"step": 2675
|
|
},
|
|
{
|
|
"entropy": 5.762459421157837,
|
|
"epoch": 0.301005222665244,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00049959620372105,
|
|
"loss": 5.8079,
|
|
"mean_token_accuracy": 0.16270437240600585,
|
|
"num_tokens": 6005836.0,
|
|
"step": 2680
|
|
},
|
|
{
|
|
"entropy": 5.895258378982544,
|
|
"epoch": 0.30156679957320154,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004995937958842401,
|
|
"loss": 5.8057,
|
|
"mean_token_accuracy": 0.16682981103658676,
|
|
"num_tokens": 6017408.0,
|
|
"step": 2685
|
|
},
|
|
{
|
|
"entropy": 5.811723136901856,
|
|
"epoch": 0.3021283764811591,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004995913808962767,
|
|
"loss": 5.8192,
|
|
"mean_token_accuracy": 0.15878787338733674,
|
|
"num_tokens": 6029281.0,
|
|
"step": 2690
|
|
},
|
|
{
|
|
"entropy": 5.850067806243897,
|
|
"epoch": 0.30268995338911664,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004995889587572366,
|
|
"loss": 5.8088,
|
|
"mean_token_accuracy": 0.16636761128902436,
|
|
"num_tokens": 6039354.0,
|
|
"step": 2695
|
|
},
|
|
{
|
|
"entropy": 5.8515503883361815,
|
|
"epoch": 0.3032515302970742,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000499586529467197,
|
|
"loss": 5.785,
|
|
"mean_token_accuracy": 0.15962323993444444,
|
|
"num_tokens": 6050053.0,
|
|
"step": 2700
|
|
},
|
|
{
|
|
"entropy": 5.90614161491394,
|
|
"epoch": 0.30381310720503174,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004995840930262351,
|
|
"loss": 5.8451,
|
|
"mean_token_accuracy": 0.15831548869609832,
|
|
"num_tokens": 6060221.0,
|
|
"step": 2705
|
|
},
|
|
{
|
|
"entropy": 5.824668931961059,
|
|
"epoch": 0.3043746841129893,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004995816494344287,
|
|
"loss": 5.859,
|
|
"mean_token_accuracy": 0.1601285994052887,
|
|
"num_tokens": 6070963.0,
|
|
"step": 2710
|
|
},
|
|
{
|
|
"entropy": 5.989436864852905,
|
|
"epoch": 0.30493626102094684,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004995791986918554,
|
|
"loss": 5.9386,
|
|
"mean_token_accuracy": 0.15705745071172714,
|
|
"num_tokens": 6082028.0,
|
|
"step": 2715
|
|
},
|
|
{
|
|
"entropy": 5.949339580535889,
|
|
"epoch": 0.30549783792890434,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004995767407985933,
|
|
"loss": 5.8736,
|
|
"mean_token_accuracy": 0.16265355795621872,
|
|
"num_tokens": 6092778.0,
|
|
"step": 2720
|
|
},
|
|
{
|
|
"entropy": 5.677318954467774,
|
|
"epoch": 0.3060594148368619,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004995742757547207,
|
|
"loss": 5.6421,
|
|
"mean_token_accuracy": 0.16859253942966462,
|
|
"num_tokens": 6103093.0,
|
|
"step": 2725
|
|
},
|
|
{
|
|
"entropy": 5.772259378433228,
|
|
"epoch": 0.30662099174481944,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000499571803560316,
|
|
"loss": 5.7347,
|
|
"mean_token_accuracy": 0.16355275958776475,
|
|
"num_tokens": 6113516.0,
|
|
"step": 2730
|
|
},
|
|
{
|
|
"entropy": 5.810375738143921,
|
|
"epoch": 0.307182568652777,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004995693242154581,
|
|
"loss": 5.8036,
|
|
"mean_token_accuracy": 0.15890752524137497,
|
|
"num_tokens": 6125723.0,
|
|
"step": 2735
|
|
},
|
|
{
|
|
"entropy": 5.847309589385986,
|
|
"epoch": 0.30774414556073454,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004995668377202258,
|
|
"loss": 5.8136,
|
|
"mean_token_accuracy": 0.16112632900476456,
|
|
"num_tokens": 6137091.0,
|
|
"step": 2740
|
|
},
|
|
{
|
|
"entropy": 5.77405891418457,
|
|
"epoch": 0.3083057224686921,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004995643440746982,
|
|
"loss": 5.7528,
|
|
"mean_token_accuracy": 0.16945552676916123,
|
|
"num_tokens": 6147941.0,
|
|
"step": 2745
|
|
},
|
|
{
|
|
"entropy": 5.732852792739868,
|
|
"epoch": 0.30886729937664964,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004995618432789548,
|
|
"loss": 5.7549,
|
|
"mean_token_accuracy": 0.16648126393556595,
|
|
"num_tokens": 6158493.0,
|
|
"step": 2750
|
|
},
|
|
{
|
|
"entropy": 5.8287242412567135,
|
|
"epoch": 0.3094288762846072,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004995593353330753,
|
|
"loss": 5.8915,
|
|
"mean_token_accuracy": 0.15722588896751405,
|
|
"num_tokens": 6170759.0,
|
|
"step": 2755
|
|
},
|
|
{
|
|
"entropy": 5.898643875122071,
|
|
"epoch": 0.30999045319256474,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004995568202371393,
|
|
"loss": 5.724,
|
|
"mean_token_accuracy": 0.16514806002378463,
|
|
"num_tokens": 6182488.0,
|
|
"step": 2760
|
|
},
|
|
{
|
|
"entropy": 5.841040992736817,
|
|
"epoch": 0.3105520301005223,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004995542979912272,
|
|
"loss": 5.9165,
|
|
"mean_token_accuracy": 0.15282527059316636,
|
|
"num_tokens": 6193849.0,
|
|
"step": 2765
|
|
},
|
|
{
|
|
"entropy": 5.800279855728149,
|
|
"epoch": 0.3111136070084798,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004995517685954192,
|
|
"loss": 5.7598,
|
|
"mean_token_accuracy": 0.16608615219593048,
|
|
"num_tokens": 6204132.0,
|
|
"step": 2770
|
|
},
|
|
{
|
|
"entropy": 5.946976375579834,
|
|
"epoch": 0.31167518391643734,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004995492320497958,
|
|
"loss": 5.9018,
|
|
"mean_token_accuracy": 0.1554347574710846,
|
|
"num_tokens": 6215547.0,
|
|
"step": 2775
|
|
},
|
|
{
|
|
"entropy": 5.905535459518433,
|
|
"epoch": 0.3122367608243949,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004995466883544376,
|
|
"loss": 5.9293,
|
|
"mean_token_accuracy": 0.15042147785425186,
|
|
"num_tokens": 6227150.0,
|
|
"step": 2780
|
|
},
|
|
{
|
|
"entropy": 5.8855243682861325,
|
|
"epoch": 0.31279833773235244,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004995441375094258,
|
|
"loss": 5.9248,
|
|
"mean_token_accuracy": 0.15840522199869156,
|
|
"num_tokens": 6237387.0,
|
|
"step": 2785
|
|
},
|
|
{
|
|
"entropy": 5.872175312042236,
|
|
"epoch": 0.31335991464031,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004995415795148417,
|
|
"loss": 5.812,
|
|
"mean_token_accuracy": 0.16368252038955688,
|
|
"num_tokens": 6248623.0,
|
|
"step": 2790
|
|
},
|
|
{
|
|
"entropy": 5.76340684890747,
|
|
"epoch": 0.31392149154826754,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004995390143707665,
|
|
"loss": 5.7152,
|
|
"mean_token_accuracy": 0.17597836554050444,
|
|
"num_tokens": 6258596.0,
|
|
"step": 2795
|
|
},
|
|
{
|
|
"entropy": 5.822847366333008,
|
|
"epoch": 0.3144830684562251,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004995364420772821,
|
|
"loss": 5.9642,
|
|
"mean_token_accuracy": 0.15163593217730523,
|
|
"num_tokens": 6270529.0,
|
|
"step": 2800
|
|
},
|
|
{
|
|
"entropy": 6.0933667659759525,
|
|
"epoch": 0.31504464536418264,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004995338626344702,
|
|
"loss": 5.8579,
|
|
"mean_token_accuracy": 0.16046109050512314,
|
|
"num_tokens": 6280891.0,
|
|
"step": 2805
|
|
},
|
|
{
|
|
"entropy": 5.7229210376739506,
|
|
"epoch": 0.3156062222721402,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000499531276042413,
|
|
"loss": 5.7988,
|
|
"mean_token_accuracy": 0.15810492336750032,
|
|
"num_tokens": 6292247.0,
|
|
"step": 2810
|
|
},
|
|
{
|
|
"entropy": 5.79867639541626,
|
|
"epoch": 0.31616779918009774,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004995286823011929,
|
|
"loss": 5.7847,
|
|
"mean_token_accuracy": 0.16373041421175002,
|
|
"num_tokens": 6302403.0,
|
|
"step": 2815
|
|
},
|
|
{
|
|
"entropy": 5.7128393173217775,
|
|
"epoch": 0.31672937608805524,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004995260814108926,
|
|
"loss": 5.6696,
|
|
"mean_token_accuracy": 0.1683839187026024,
|
|
"num_tokens": 6313901.0,
|
|
"step": 2820
|
|
},
|
|
{
|
|
"entropy": 5.921040821075439,
|
|
"epoch": 0.3172909529960128,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004995234733715947,
|
|
"loss": 5.8928,
|
|
"mean_token_accuracy": 0.15783516615629195,
|
|
"num_tokens": 6323711.0,
|
|
"step": 2825
|
|
},
|
|
{
|
|
"entropy": 5.817658710479736,
|
|
"epoch": 0.31785252990397034,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004995208581833824,
|
|
"loss": 5.7877,
|
|
"mean_token_accuracy": 0.1626381605863571,
|
|
"num_tokens": 6334937.0,
|
|
"step": 2830
|
|
},
|
|
{
|
|
"entropy": 5.928051614761353,
|
|
"epoch": 0.3184141068119279,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004995182358463388,
|
|
"loss": 5.8838,
|
|
"mean_token_accuracy": 0.15879348814487457,
|
|
"num_tokens": 6345723.0,
|
|
"step": 2835
|
|
},
|
|
{
|
|
"entropy": 5.844352579116821,
|
|
"epoch": 0.31897568371988544,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004995156063605475,
|
|
"loss": 5.8219,
|
|
"mean_token_accuracy": 0.15776338502764703,
|
|
"num_tokens": 6357573.0,
|
|
"step": 2840
|
|
},
|
|
{
|
|
"entropy": 5.8675610542297365,
|
|
"epoch": 0.319537260627843,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004995129697260922,
|
|
"loss": 5.8322,
|
|
"mean_token_accuracy": 0.16539549678564072,
|
|
"num_tokens": 6367417.0,
|
|
"step": 2845
|
|
},
|
|
{
|
|
"entropy": 5.872849082946777,
|
|
"epoch": 0.32009883753580054,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004995103259430569,
|
|
"loss": 5.841,
|
|
"mean_token_accuracy": 0.16827336698770523,
|
|
"num_tokens": 6377753.0,
|
|
"step": 2850
|
|
},
|
|
{
|
|
"entropy": 5.839739036560059,
|
|
"epoch": 0.3206604144437581,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004995076750115258,
|
|
"loss": 5.8514,
|
|
"mean_token_accuracy": 0.15937740802764894,
|
|
"num_tokens": 6388613.0,
|
|
"step": 2855
|
|
},
|
|
{
|
|
"entropy": 5.815576601028442,
|
|
"epoch": 0.32122199135171564,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004995050169315832,
|
|
"loss": 5.796,
|
|
"mean_token_accuracy": 0.1593346953392029,
|
|
"num_tokens": 6399415.0,
|
|
"step": 2860
|
|
},
|
|
{
|
|
"entropy": 5.867472791671753,
|
|
"epoch": 0.32178356825967314,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004995023517033138,
|
|
"loss": 5.8285,
|
|
"mean_token_accuracy": 0.15754698514938353,
|
|
"num_tokens": 6411435.0,
|
|
"step": 2865
|
|
},
|
|
{
|
|
"entropy": 5.926137781143188,
|
|
"epoch": 0.3223451451676307,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004994996793268024,
|
|
"loss": 5.976,
|
|
"mean_token_accuracy": 0.15850219279527664,
|
|
"num_tokens": 6423030.0,
|
|
"step": 2870
|
|
},
|
|
{
|
|
"entropy": 5.888271427154541,
|
|
"epoch": 0.32290672207558824,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004994969998021342,
|
|
"loss": 5.7765,
|
|
"mean_token_accuracy": 0.16209373772144317,
|
|
"num_tokens": 6434330.0,
|
|
"step": 2875
|
|
},
|
|
{
|
|
"entropy": 5.859491014480591,
|
|
"epoch": 0.3234682989835458,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004994943131293944,
|
|
"loss": 5.8646,
|
|
"mean_token_accuracy": 0.16070864647626876,
|
|
"num_tokens": 6446452.0,
|
|
"step": 2880
|
|
},
|
|
{
|
|
"entropy": 5.8355710983276365,
|
|
"epoch": 0.32402987589150334,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004994916193086687,
|
|
"loss": 5.8139,
|
|
"mean_token_accuracy": 0.1690973237156868,
|
|
"num_tokens": 6456723.0,
|
|
"step": 2885
|
|
},
|
|
{
|
|
"entropy": 5.899684286117553,
|
|
"epoch": 0.3245914527994609,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004994889183400428,
|
|
"loss": 5.9365,
|
|
"mean_token_accuracy": 0.15811522603034972,
|
|
"num_tokens": 6468117.0,
|
|
"step": 2890
|
|
},
|
|
{
|
|
"entropy": 5.826454973220825,
|
|
"epoch": 0.32515302970741844,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004994862102236025,
|
|
"loss": 5.7204,
|
|
"mean_token_accuracy": 0.16832807213068007,
|
|
"num_tokens": 6479465.0,
|
|
"step": 2895
|
|
},
|
|
{
|
|
"entropy": 5.89757194519043,
|
|
"epoch": 0.325714606615376,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004994834949594342,
|
|
"loss": 5.9526,
|
|
"mean_token_accuracy": 0.1629941999912262,
|
|
"num_tokens": 6490868.0,
|
|
"step": 2900
|
|
},
|
|
{
|
|
"entropy": 5.972553682327271,
|
|
"epoch": 0.32627618352333354,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004994807725476246,
|
|
"loss": 5.8245,
|
|
"mean_token_accuracy": 0.16008032113313675,
|
|
"num_tokens": 6502126.0,
|
|
"step": 2905
|
|
},
|
|
{
|
|
"entropy": 5.72076644897461,
|
|
"epoch": 0.3268377604312911,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004994780429882599,
|
|
"loss": 5.9091,
|
|
"mean_token_accuracy": 0.15670095086097718,
|
|
"num_tokens": 6514382.0,
|
|
"step": 2910
|
|
},
|
|
{
|
|
"entropy": 5.882012605667114,
|
|
"epoch": 0.3273993373392486,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004994753062814274,
|
|
"loss": 5.7914,
|
|
"mean_token_accuracy": 0.15964423269033431,
|
|
"num_tokens": 6526272.0,
|
|
"step": 2915
|
|
},
|
|
{
|
|
"entropy": 5.866258335113526,
|
|
"epoch": 0.32796091424720614,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004994725624272139,
|
|
"loss": 5.8134,
|
|
"mean_token_accuracy": 0.16369341611862182,
|
|
"num_tokens": 6537511.0,
|
|
"step": 2920
|
|
},
|
|
{
|
|
"entropy": 5.805434799194336,
|
|
"epoch": 0.3285224911551637,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004994698114257071,
|
|
"loss": 5.7523,
|
|
"mean_token_accuracy": 0.16356185525655748,
|
|
"num_tokens": 6549737.0,
|
|
"step": 2925
|
|
},
|
|
{
|
|
"entropy": 5.735032749176026,
|
|
"epoch": 0.32908406806312124,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004994670532769944,
|
|
"loss": 5.842,
|
|
"mean_token_accuracy": 0.16296304613351822,
|
|
"num_tokens": 6560318.0,
|
|
"step": 2930
|
|
},
|
|
{
|
|
"entropy": 5.818574094772339,
|
|
"epoch": 0.3296456449710788,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004994642879811637,
|
|
"loss": 5.7497,
|
|
"mean_token_accuracy": 0.16560823023319243,
|
|
"num_tokens": 6570575.0,
|
|
"step": 2935
|
|
},
|
|
{
|
|
"entropy": 5.807329988479614,
|
|
"epoch": 0.33020722187903634,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000499461515538303,
|
|
"loss": 5.8172,
|
|
"mean_token_accuracy": 0.1601566642522812,
|
|
"num_tokens": 6582083.0,
|
|
"step": 2940
|
|
},
|
|
{
|
|
"entropy": 6.00074577331543,
|
|
"epoch": 0.3307687987869939,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004994587359485006,
|
|
"loss": 5.9414,
|
|
"mean_token_accuracy": 0.16097475886344909,
|
|
"num_tokens": 6592240.0,
|
|
"step": 2945
|
|
},
|
|
{
|
|
"entropy": 5.806456136703491,
|
|
"epoch": 0.33133037569495144,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000499455949211845,
|
|
"loss": 5.7185,
|
|
"mean_token_accuracy": 0.1677255555987358,
|
|
"num_tokens": 6602680.0,
|
|
"step": 2950
|
|
},
|
|
{
|
|
"entropy": 5.796722078323365,
|
|
"epoch": 0.331891952602909,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004994531553284248,
|
|
"loss": 5.8381,
|
|
"mean_token_accuracy": 0.16280671954154968,
|
|
"num_tokens": 6613399.0,
|
|
"step": 2955
|
|
},
|
|
{
|
|
"entropy": 5.918023681640625,
|
|
"epoch": 0.3324535295108665,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004994503542983293,
|
|
"loss": 5.91,
|
|
"mean_token_accuracy": 0.15692875981330873,
|
|
"num_tokens": 6624410.0,
|
|
"step": 2960
|
|
},
|
|
{
|
|
"entropy": 5.893260526657104,
|
|
"epoch": 0.33301510641882404,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004994475461216472,
|
|
"loss": 5.7623,
|
|
"mean_token_accuracy": 0.1689491778612137,
|
|
"num_tokens": 6635523.0,
|
|
"step": 2965
|
|
},
|
|
{
|
|
"entropy": 5.8270707607269285,
|
|
"epoch": 0.3335766833267816,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004994447307984684,
|
|
"loss": 5.9249,
|
|
"mean_token_accuracy": 0.1531895712018013,
|
|
"num_tokens": 6648416.0,
|
|
"step": 2970
|
|
},
|
|
{
|
|
"entropy": 5.764549970626831,
|
|
"epoch": 0.33413826023473914,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004994419083288823,
|
|
"loss": 5.7112,
|
|
"mean_token_accuracy": 0.16065409630537034,
|
|
"num_tokens": 6658907.0,
|
|
"step": 2975
|
|
},
|
|
{
|
|
"entropy": 5.840141725540161,
|
|
"epoch": 0.3346998371426967,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004994390787129787,
|
|
"loss": 5.8754,
|
|
"mean_token_accuracy": 0.1610553666949272,
|
|
"num_tokens": 6669682.0,
|
|
"step": 2980
|
|
},
|
|
{
|
|
"entropy": 5.9260087490081785,
|
|
"epoch": 0.33526141405065424,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004994362419508478,
|
|
"loss": 5.9334,
|
|
"mean_token_accuracy": 0.1567075252532959,
|
|
"num_tokens": 6681919.0,
|
|
"step": 2985
|
|
},
|
|
{
|
|
"entropy": 5.9462815284729,
|
|
"epoch": 0.3358229909586118,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00049943339804258,
|
|
"loss": 5.8707,
|
|
"mean_token_accuracy": 0.1613776594400406,
|
|
"num_tokens": 6693988.0,
|
|
"step": 2990
|
|
},
|
|
{
|
|
"entropy": 5.7616931915283205,
|
|
"epoch": 0.33638456786656934,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004994305469882657,
|
|
"loss": 5.8059,
|
|
"mean_token_accuracy": 0.15830975472927095,
|
|
"num_tokens": 6705413.0,
|
|
"step": 2995
|
|
},
|
|
{
|
|
"entropy": 5.859702157974243,
|
|
"epoch": 0.3369461447745269,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004994276887879957,
|
|
"loss": 5.763,
|
|
"mean_token_accuracy": 0.16223098933696747,
|
|
"num_tokens": 6716217.0,
|
|
"step": 3000
|
|
},
|
|
{
|
|
"epoch": 0.3369461447745269,
|
|
"eval_entropy": 5.720634406333059,
|
|
"eval_loss": 5.844816207885742,
|
|
"eval_mean_token_accuracy": 0.1682441681402459,
|
|
"eval_num_tokens": 6716217.0,
|
|
"eval_runtime": 23.7412,
|
|
"eval_samples_per_second": 1306.296,
|
|
"eval_steps_per_second": 163.303,
|
|
"step": 3000
|
|
},
|
|
{
|
|
"entropy": 5.799144506454468,
|
|
"epoch": 0.33750772168248444,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004994248234418611,
|
|
"loss": 5.8366,
|
|
"mean_token_accuracy": 0.162978595495224,
|
|
"num_tokens": 6728059.0,
|
|
"step": 3005
|
|
},
|
|
{
|
|
"entropy": 5.893440103530883,
|
|
"epoch": 0.33806929859044194,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000499421950949953,
|
|
"loss": 5.7807,
|
|
"mean_token_accuracy": 0.16390309780836104,
|
|
"num_tokens": 6740650.0,
|
|
"step": 3010
|
|
},
|
|
{
|
|
"entropy": 5.698744678497315,
|
|
"epoch": 0.3386308754983995,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000499419071312363,
|
|
"loss": 5.6836,
|
|
"mean_token_accuracy": 0.16469298750162126,
|
|
"num_tokens": 6751467.0,
|
|
"step": 3015
|
|
},
|
|
{
|
|
"entropy": 5.7961132526397705,
|
|
"epoch": 0.33919245240635704,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004994161845291828,
|
|
"loss": 5.7861,
|
|
"mean_token_accuracy": 0.16712161004543305,
|
|
"num_tokens": 6761377.0,
|
|
"step": 3020
|
|
},
|
|
{
|
|
"entropy": 5.79654335975647,
|
|
"epoch": 0.3397540293143146,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004994132906005041,
|
|
"loss": 5.7393,
|
|
"mean_token_accuracy": 0.16078124195337296,
|
|
"num_tokens": 6773296.0,
|
|
"step": 3025
|
|
},
|
|
{
|
|
"entropy": 5.845974779129028,
|
|
"epoch": 0.34031560622227214,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004994103895264193,
|
|
"loss": 5.7954,
|
|
"mean_token_accuracy": 0.15900143682956697,
|
|
"num_tokens": 6784122.0,
|
|
"step": 3030
|
|
},
|
|
{
|
|
"entropy": 5.704025363922119,
|
|
"epoch": 0.3408771831302297,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004994074813070207,
|
|
"loss": 5.6383,
|
|
"mean_token_accuracy": 0.16705414056777954,
|
|
"num_tokens": 6795604.0,
|
|
"step": 3035
|
|
},
|
|
{
|
|
"entropy": 5.769487285614014,
|
|
"epoch": 0.34143876003818724,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004994045659424007,
|
|
"loss": 5.7981,
|
|
"mean_token_accuracy": 0.16261281818151474,
|
|
"num_tokens": 6806671.0,
|
|
"step": 3040
|
|
},
|
|
{
|
|
"entropy": 5.9057597637176515,
|
|
"epoch": 0.3420003369461448,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004994016434326524,
|
|
"loss": 5.8216,
|
|
"mean_token_accuracy": 0.16332198679447174,
|
|
"num_tokens": 6818271.0,
|
|
"step": 3045
|
|
},
|
|
{
|
|
"entropy": 5.7448649406433105,
|
|
"epoch": 0.34256191385410234,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004993987137778687,
|
|
"loss": 5.8169,
|
|
"mean_token_accuracy": 0.1635512739419937,
|
|
"num_tokens": 6830049.0,
|
|
"step": 3050
|
|
},
|
|
{
|
|
"entropy": 5.942811059951782,
|
|
"epoch": 0.3431234907620599,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000499395776978143,
|
|
"loss": 5.9403,
|
|
"mean_token_accuracy": 0.15486131906509398,
|
|
"num_tokens": 6842275.0,
|
|
"step": 3055
|
|
},
|
|
{
|
|
"entropy": 5.956660890579224,
|
|
"epoch": 0.3436850676700174,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004993928330335686,
|
|
"loss": 5.8766,
|
|
"mean_token_accuracy": 0.1637545719742775,
|
|
"num_tokens": 6854910.0,
|
|
"step": 3060
|
|
},
|
|
{
|
|
"entropy": 5.791312170028687,
|
|
"epoch": 0.34424664457797494,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004993898819442395,
|
|
"loss": 5.8284,
|
|
"mean_token_accuracy": 0.16965375244617462,
|
|
"num_tokens": 6866031.0,
|
|
"step": 3065
|
|
},
|
|
{
|
|
"entropy": 5.93616361618042,
|
|
"epoch": 0.3448082214859325,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004993869237102494,
|
|
"loss": 5.8471,
|
|
"mean_token_accuracy": 0.15883387625217438,
|
|
"num_tokens": 6877672.0,
|
|
"step": 3070
|
|
},
|
|
{
|
|
"entropy": 5.765334987640381,
|
|
"epoch": 0.34536979839389004,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004993839583316927,
|
|
"loss": 5.7543,
|
|
"mean_token_accuracy": 0.16836509853601456,
|
|
"num_tokens": 6889089.0,
|
|
"step": 3075
|
|
},
|
|
{
|
|
"entropy": 5.673844814300537,
|
|
"epoch": 0.3459313753018476,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004993809858086638,
|
|
"loss": 5.6994,
|
|
"mean_token_accuracy": 0.1676324874162674,
|
|
"num_tokens": 6899877.0,
|
|
"step": 3080
|
|
},
|
|
{
|
|
"entropy": 5.793374395370483,
|
|
"epoch": 0.34649295220980514,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004993780061412571,
|
|
"loss": 5.6829,
|
|
"mean_token_accuracy": 0.1715866893529892,
|
|
"num_tokens": 6910686.0,
|
|
"step": 3085
|
|
},
|
|
{
|
|
"entropy": 5.734429454803466,
|
|
"epoch": 0.3470545291177627,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004993750193295678,
|
|
"loss": 5.7143,
|
|
"mean_token_accuracy": 0.17135517448186874,
|
|
"num_tokens": 6920867.0,
|
|
"step": 3090
|
|
},
|
|
{
|
|
"entropy": 5.899741554260254,
|
|
"epoch": 0.34761610602572024,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004993720253736909,
|
|
"loss": 5.9044,
|
|
"mean_token_accuracy": 0.16466446667909623,
|
|
"num_tokens": 6932779.0,
|
|
"step": 3095
|
|
},
|
|
{
|
|
"entropy": 5.86834020614624,
|
|
"epoch": 0.3481776829336778,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004993690242737216,
|
|
"loss": 5.8055,
|
|
"mean_token_accuracy": 0.16673210114240647,
|
|
"num_tokens": 6943378.0,
|
|
"step": 3100
|
|
},
|
|
{
|
|
"entropy": 5.760788822174073,
|
|
"epoch": 0.3487392598416353,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004993660160297555,
|
|
"loss": 5.7867,
|
|
"mean_token_accuracy": 0.16799272298812867,
|
|
"num_tokens": 6955469.0,
|
|
"step": 3105
|
|
},
|
|
{
|
|
"entropy": 5.971051931381226,
|
|
"epoch": 0.34930083674959284,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004993630006418885,
|
|
"loss": 5.8788,
|
|
"mean_token_accuracy": 0.16197884529829026,
|
|
"num_tokens": 6966750.0,
|
|
"step": 3110
|
|
},
|
|
{
|
|
"entropy": 5.811239528656006,
|
|
"epoch": 0.3498624136575504,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004993599781102166,
|
|
"loss": 5.7912,
|
|
"mean_token_accuracy": 0.16256844401359558,
|
|
"num_tokens": 6979010.0,
|
|
"step": 3115
|
|
},
|
|
{
|
|
"entropy": 5.775843524932862,
|
|
"epoch": 0.35042399056550794,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004993569484348359,
|
|
"loss": 5.7764,
|
|
"mean_token_accuracy": 0.16187913715839386,
|
|
"num_tokens": 6990566.0,
|
|
"step": 3120
|
|
},
|
|
{
|
|
"entropy": 5.8379576206207275,
|
|
"epoch": 0.3509855674734655,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004993539116158429,
|
|
"loss": 5.7852,
|
|
"mean_token_accuracy": 0.1654660627245903,
|
|
"num_tokens": 7000288.0,
|
|
"step": 3125
|
|
},
|
|
{
|
|
"entropy": 5.689918518066406,
|
|
"epoch": 0.35154714438142304,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004993508676533346,
|
|
"loss": 5.7248,
|
|
"mean_token_accuracy": 0.16818051636219025,
|
|
"num_tokens": 7011143.0,
|
|
"step": 3130
|
|
},
|
|
{
|
|
"entropy": 5.967591333389282,
|
|
"epoch": 0.3521087212893806,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004993478165474074,
|
|
"loss": 5.8802,
|
|
"mean_token_accuracy": 0.15500763505697251,
|
|
"num_tokens": 7022797.0,
|
|
"step": 3135
|
|
},
|
|
{
|
|
"entropy": 5.829250907897949,
|
|
"epoch": 0.35267029819733814,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004993447582981588,
|
|
"loss": 5.8523,
|
|
"mean_token_accuracy": 0.15978631526231765,
|
|
"num_tokens": 7033477.0,
|
|
"step": 3140
|
|
},
|
|
{
|
|
"entropy": 5.825192642211914,
|
|
"epoch": 0.3532318751052957,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000499341692905686,
|
|
"loss": 5.8713,
|
|
"mean_token_accuracy": 0.16687492281198502,
|
|
"num_tokens": 7045249.0,
|
|
"step": 3145
|
|
},
|
|
{
|
|
"entropy": 5.924324893951416,
|
|
"epoch": 0.35379345201325324,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004993386203700868,
|
|
"loss": 5.8924,
|
|
"mean_token_accuracy": 0.16145936846733094,
|
|
"num_tokens": 7056890.0,
|
|
"step": 3150
|
|
},
|
|
{
|
|
"entropy": 5.861443424224854,
|
|
"epoch": 0.35435502892121074,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004993355406914589,
|
|
"loss": 5.7678,
|
|
"mean_token_accuracy": 0.1675198808312416,
|
|
"num_tokens": 7067181.0,
|
|
"step": 3155
|
|
},
|
|
{
|
|
"entropy": 5.785042476654053,
|
|
"epoch": 0.3549166058291683,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004993324538699003,
|
|
"loss": 5.7324,
|
|
"mean_token_accuracy": 0.16697331219911576,
|
|
"num_tokens": 7078220.0,
|
|
"step": 3160
|
|
},
|
|
{
|
|
"entropy": 5.833939266204834,
|
|
"epoch": 0.35547818273712584,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004993293599055094,
|
|
"loss": 5.8066,
|
|
"mean_token_accuracy": 0.16511004269123078,
|
|
"num_tokens": 7089536.0,
|
|
"step": 3165
|
|
},
|
|
{
|
|
"entropy": 5.8496153354644775,
|
|
"epoch": 0.3560397596450834,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004993262587983848,
|
|
"loss": 5.8848,
|
|
"mean_token_accuracy": 0.16400568187236786,
|
|
"num_tokens": 7101535.0,
|
|
"step": 3170
|
|
},
|
|
{
|
|
"entropy": 5.862979078292847,
|
|
"epoch": 0.35660133655304094,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000499323150548625,
|
|
"loss": 5.7782,
|
|
"mean_token_accuracy": 0.1608920007944107,
|
|
"num_tokens": 7112468.0,
|
|
"step": 3175
|
|
},
|
|
{
|
|
"entropy": 5.801843690872192,
|
|
"epoch": 0.3571629134609985,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004993200351563291,
|
|
"loss": 5.7695,
|
|
"mean_token_accuracy": 0.16856954991817474,
|
|
"num_tokens": 7123192.0,
|
|
"step": 3180
|
|
},
|
|
{
|
|
"entropy": 5.776076078414917,
|
|
"epoch": 0.35772449036895604,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004993169126215962,
|
|
"loss": 5.6971,
|
|
"mean_token_accuracy": 0.17152681350708007,
|
|
"num_tokens": 7133063.0,
|
|
"step": 3185
|
|
},
|
|
{
|
|
"entropy": 5.832470464706421,
|
|
"epoch": 0.3582860672769136,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004993137829445259,
|
|
"loss": 5.7899,
|
|
"mean_token_accuracy": 0.16362055987119675,
|
|
"num_tokens": 7144190.0,
|
|
"step": 3190
|
|
},
|
|
{
|
|
"entropy": 5.7901458740234375,
|
|
"epoch": 0.35884764418487114,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004993106461252177,
|
|
"loss": 5.779,
|
|
"mean_token_accuracy": 0.1660066932439804,
|
|
"num_tokens": 7155433.0,
|
|
"step": 3195
|
|
},
|
|
{
|
|
"entropy": 5.8804432392120365,
|
|
"epoch": 0.3594092210928287,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004993075021637716,
|
|
"loss": 5.8442,
|
|
"mean_token_accuracy": 0.16579061150550842,
|
|
"num_tokens": 7166084.0,
|
|
"step": 3200
|
|
},
|
|
{
|
|
"entropy": 5.849256277084351,
|
|
"epoch": 0.3599707980007862,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004993043510602875,
|
|
"loss": 5.8714,
|
|
"mean_token_accuracy": 0.1630292773246765,
|
|
"num_tokens": 7176948.0,
|
|
"step": 3205
|
|
},
|
|
{
|
|
"entropy": 5.846883821487427,
|
|
"epoch": 0.36053237490874374,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000499301192814866,
|
|
"loss": 5.7289,
|
|
"mean_token_accuracy": 0.16961728185415267,
|
|
"num_tokens": 7188601.0,
|
|
"step": 3210
|
|
},
|
|
{
|
|
"entropy": 5.7951243877410885,
|
|
"epoch": 0.3610939518167013,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004992980274276074,
|
|
"loss": 5.7635,
|
|
"mean_token_accuracy": 0.16846298575401306,
|
|
"num_tokens": 7198495.0,
|
|
"step": 3215
|
|
},
|
|
{
|
|
"entropy": 5.826298189163208,
|
|
"epoch": 0.36165552872465884,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004992948548986128,
|
|
"loss": 5.753,
|
|
"mean_token_accuracy": 0.16387602537870408,
|
|
"num_tokens": 7209848.0,
|
|
"step": 3220
|
|
},
|
|
{
|
|
"entropy": 5.814381456375122,
|
|
"epoch": 0.3622171056326164,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004992916752279829,
|
|
"loss": 5.8787,
|
|
"mean_token_accuracy": 0.16065715700387956,
|
|
"num_tokens": 7220366.0,
|
|
"step": 3225
|
|
},
|
|
{
|
|
"entropy": 5.806219387054443,
|
|
"epoch": 0.36277868254057394,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000499288488415819,
|
|
"loss": 5.7833,
|
|
"mean_token_accuracy": 0.16056074649095536,
|
|
"num_tokens": 7231442.0,
|
|
"step": 3230
|
|
},
|
|
{
|
|
"entropy": 5.850152111053466,
|
|
"epoch": 0.3633402594485315,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004992852944622229,
|
|
"loss": 5.825,
|
|
"mean_token_accuracy": 0.1608233243227005,
|
|
"num_tokens": 7242391.0,
|
|
"step": 3235
|
|
},
|
|
{
|
|
"entropy": 5.733070659637451,
|
|
"epoch": 0.36390183635648904,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004992820933672958,
|
|
"loss": 5.7124,
|
|
"mean_token_accuracy": 0.16292389035224913,
|
|
"num_tokens": 7252061.0,
|
|
"step": 3240
|
|
},
|
|
{
|
|
"entropy": 5.832701826095581,
|
|
"epoch": 0.3644634132644466,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004992788851311399,
|
|
"loss": 5.7926,
|
|
"mean_token_accuracy": 0.1660913810133934,
|
|
"num_tokens": 7264035.0,
|
|
"step": 3245
|
|
},
|
|
{
|
|
"entropy": 5.919405937194824,
|
|
"epoch": 0.3650249901724041,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004992756697538574,
|
|
"loss": 5.8652,
|
|
"mean_token_accuracy": 0.16157617121934892,
|
|
"num_tokens": 7275988.0,
|
|
"step": 3250
|
|
},
|
|
{
|
|
"entropy": 5.77119779586792,
|
|
"epoch": 0.36558656708036164,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004992724472355505,
|
|
"loss": 5.7206,
|
|
"mean_token_accuracy": 0.16446294635534286,
|
|
"num_tokens": 7286509.0,
|
|
"step": 3255
|
|
},
|
|
{
|
|
"entropy": 5.865907192230225,
|
|
"epoch": 0.3661481439883192,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004992692175763219,
|
|
"loss": 5.8134,
|
|
"mean_token_accuracy": 0.16690248399972915,
|
|
"num_tokens": 7296916.0,
|
|
"step": 3260
|
|
},
|
|
{
|
|
"entropy": 5.820225429534912,
|
|
"epoch": 0.36670972089627674,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004992659807762745,
|
|
"loss": 5.8982,
|
|
"mean_token_accuracy": 0.15828224942088126,
|
|
"num_tokens": 7309563.0,
|
|
"step": 3265
|
|
},
|
|
{
|
|
"entropy": 5.88502197265625,
|
|
"epoch": 0.3672712978042343,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004992627368355112,
|
|
"loss": 5.7505,
|
|
"mean_token_accuracy": 0.16168039441108703,
|
|
"num_tokens": 7320264.0,
|
|
"step": 3270
|
|
},
|
|
{
|
|
"entropy": 5.719604015350342,
|
|
"epoch": 0.36783287471219184,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004992594857541355,
|
|
"loss": 5.7186,
|
|
"mean_token_accuracy": 0.16655558794736863,
|
|
"num_tokens": 7330442.0,
|
|
"step": 3275
|
|
},
|
|
{
|
|
"entropy": 5.853730297088623,
|
|
"epoch": 0.3683944516201494,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004992562275322506,
|
|
"loss": 5.9159,
|
|
"mean_token_accuracy": 0.1572217419743538,
|
|
"num_tokens": 7342292.0,
|
|
"step": 3280
|
|
},
|
|
{
|
|
"entropy": 5.909031820297241,
|
|
"epoch": 0.36895602852810694,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004992529621699606,
|
|
"loss": 5.8141,
|
|
"mean_token_accuracy": 0.16075354367494582,
|
|
"num_tokens": 7353857.0,
|
|
"step": 3285
|
|
},
|
|
{
|
|
"entropy": 5.804742479324341,
|
|
"epoch": 0.3695176054360645,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004992496896673692,
|
|
"loss": 5.7377,
|
|
"mean_token_accuracy": 0.16423878073692322,
|
|
"num_tokens": 7365653.0,
|
|
"step": 3290
|
|
},
|
|
{
|
|
"entropy": 5.790262269973755,
|
|
"epoch": 0.37007918234402204,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004992464100245809,
|
|
"loss": 5.7455,
|
|
"mean_token_accuracy": 0.15999912321567536,
|
|
"num_tokens": 7376522.0,
|
|
"step": 3295
|
|
},
|
|
{
|
|
"entropy": 5.796634531021118,
|
|
"epoch": 0.37064075925197953,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004992431232416997,
|
|
"loss": 5.7407,
|
|
"mean_token_accuracy": 0.1694473460316658,
|
|
"num_tokens": 7388562.0,
|
|
"step": 3300
|
|
},
|
|
{
|
|
"entropy": 5.8152648448944095,
|
|
"epoch": 0.3712023361599371,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004992398293188307,
|
|
"loss": 5.794,
|
|
"mean_token_accuracy": 0.16164605543017388,
|
|
"num_tokens": 7398597.0,
|
|
"step": 3305
|
|
},
|
|
{
|
|
"entropy": 5.75906810760498,
|
|
"epoch": 0.37176391306789464,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004992365282560784,
|
|
"loss": 5.7432,
|
|
"mean_token_accuracy": 0.16698759496212007,
|
|
"num_tokens": 7409656.0,
|
|
"step": 3310
|
|
},
|
|
{
|
|
"entropy": 5.769649410247803,
|
|
"epoch": 0.3723254899758522,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004992332200535483,
|
|
"loss": 5.7906,
|
|
"mean_token_accuracy": 0.1635170191526413,
|
|
"num_tokens": 7420621.0,
|
|
"step": 3315
|
|
},
|
|
{
|
|
"entropy": 5.914590549468994,
|
|
"epoch": 0.37288706688380974,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004992299047113452,
|
|
"loss": 5.8258,
|
|
"mean_token_accuracy": 0.1644177705049515,
|
|
"num_tokens": 7432951.0,
|
|
"step": 3320
|
|
},
|
|
{
|
|
"entropy": 5.746472978591919,
|
|
"epoch": 0.3734486437917673,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004992265822295752,
|
|
"loss": 5.8086,
|
|
"mean_token_accuracy": 0.1657330572605133,
|
|
"num_tokens": 7443630.0,
|
|
"step": 3325
|
|
},
|
|
{
|
|
"entropy": 5.878232765197754,
|
|
"epoch": 0.37401022069972484,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004992232526083438,
|
|
"loss": 5.7904,
|
|
"mean_token_accuracy": 0.1630190759897232,
|
|
"num_tokens": 7454535.0,
|
|
"step": 3330
|
|
},
|
|
{
|
|
"entropy": 5.851468801498413,
|
|
"epoch": 0.3745717976076824,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000499219915847757,
|
|
"loss": 5.8617,
|
|
"mean_token_accuracy": 0.16609936952590942,
|
|
"num_tokens": 7467751.0,
|
|
"step": 3335
|
|
},
|
|
{
|
|
"entropy": 5.7327392578125,
|
|
"epoch": 0.37513337451563994,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004992165719479211,
|
|
"loss": 5.7229,
|
|
"mean_token_accuracy": 0.1723914325237274,
|
|
"num_tokens": 7479347.0,
|
|
"step": 3340
|
|
},
|
|
{
|
|
"entropy": 5.792557239532471,
|
|
"epoch": 0.37569495142359743,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004992132209089427,
|
|
"loss": 5.7559,
|
|
"mean_token_accuracy": 0.16422603875398636,
|
|
"num_tokens": 7490916.0,
|
|
"step": 3345
|
|
},
|
|
{
|
|
"entropy": 5.839074325561524,
|
|
"epoch": 0.376256528331555,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004992098627309283,
|
|
"loss": 5.7285,
|
|
"mean_token_accuracy": 0.16606951653957366,
|
|
"num_tokens": 7500824.0,
|
|
"step": 3350
|
|
},
|
|
{
|
|
"entropy": 5.8109547138214115,
|
|
"epoch": 0.37681810523951254,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000499206497413985,
|
|
"loss": 5.8818,
|
|
"mean_token_accuracy": 0.15842843651771546,
|
|
"num_tokens": 7511778.0,
|
|
"step": 3355
|
|
},
|
|
{
|
|
"entropy": 5.980834197998047,
|
|
"epoch": 0.3773796821474701,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004992031249582197,
|
|
"loss": 5.9424,
|
|
"mean_token_accuracy": 0.15256146043539048,
|
|
"num_tokens": 7522616.0,
|
|
"step": 3360
|
|
},
|
|
{
|
|
"entropy": 5.881027460098267,
|
|
"epoch": 0.37794125905542764,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004991997453637401,
|
|
"loss": 5.8116,
|
|
"mean_token_accuracy": 0.1650218188762665,
|
|
"num_tokens": 7533019.0,
|
|
"step": 3365
|
|
},
|
|
{
|
|
"entropy": 5.749409818649292,
|
|
"epoch": 0.3785028359633852,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004991963586306536,
|
|
"loss": 5.7544,
|
|
"mean_token_accuracy": 0.16154202967882156,
|
|
"num_tokens": 7544139.0,
|
|
"step": 3370
|
|
},
|
|
{
|
|
"entropy": 5.80066704750061,
|
|
"epoch": 0.37906441287134274,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004991929647590682,
|
|
"loss": 5.7377,
|
|
"mean_token_accuracy": 0.16260901242494583,
|
|
"num_tokens": 7554638.0,
|
|
"step": 3375
|
|
},
|
|
{
|
|
"entropy": 5.953235530853272,
|
|
"epoch": 0.3796259897793003,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004991895637490917,
|
|
"loss": 5.8049,
|
|
"mean_token_accuracy": 0.16714229732751845,
|
|
"num_tokens": 7565158.0,
|
|
"step": 3380
|
|
},
|
|
{
|
|
"entropy": 5.809656095504761,
|
|
"epoch": 0.38018756668725784,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004991861556008326,
|
|
"loss": 5.811,
|
|
"mean_token_accuracy": 0.16301512867212295,
|
|
"num_tokens": 7576381.0,
|
|
"step": 3385
|
|
},
|
|
{
|
|
"entropy": 5.718403387069702,
|
|
"epoch": 0.3807491435952154,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004991827403143992,
|
|
"loss": 5.6948,
|
|
"mean_token_accuracy": 0.1689286082983017,
|
|
"num_tokens": 7586631.0,
|
|
"step": 3390
|
|
},
|
|
{
|
|
"entropy": 5.807317209243775,
|
|
"epoch": 0.3813107205031729,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004991793178899006,
|
|
"loss": 5.7382,
|
|
"mean_token_accuracy": 0.165502168238163,
|
|
"num_tokens": 7598321.0,
|
|
"step": 3395
|
|
},
|
|
{
|
|
"entropy": 5.771745109558106,
|
|
"epoch": 0.38187229741113043,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004991758883274455,
|
|
"loss": 5.7698,
|
|
"mean_token_accuracy": 0.1654894694685936,
|
|
"num_tokens": 7609336.0,
|
|
"step": 3400
|
|
},
|
|
{
|
|
"entropy": 5.721436452865601,
|
|
"epoch": 0.382433874319088,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004991724516271432,
|
|
"loss": 5.6716,
|
|
"mean_token_accuracy": 0.16680669486522676,
|
|
"num_tokens": 7619116.0,
|
|
"step": 3405
|
|
},
|
|
{
|
|
"entropy": 5.82664680480957,
|
|
"epoch": 0.38299545122704554,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004991690077891032,
|
|
"loss": 5.8092,
|
|
"mean_token_accuracy": 0.15846319049596785,
|
|
"num_tokens": 7630567.0,
|
|
"step": 3410
|
|
},
|
|
{
|
|
"entropy": 5.8768939018249515,
|
|
"epoch": 0.3835570281350031,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004991655568134348,
|
|
"loss": 5.8718,
|
|
"mean_token_accuracy": 0.16050247251987457,
|
|
"num_tokens": 7642564.0,
|
|
"step": 3415
|
|
},
|
|
{
|
|
"entropy": 5.909596014022827,
|
|
"epoch": 0.38411860504296064,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004991620987002483,
|
|
"loss": 5.8983,
|
|
"mean_token_accuracy": 0.15932083278894424,
|
|
"num_tokens": 7654588.0,
|
|
"step": 3420
|
|
},
|
|
{
|
|
"entropy": 5.780777931213379,
|
|
"epoch": 0.3846801819509182,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004991586334496536,
|
|
"loss": 5.6903,
|
|
"mean_token_accuracy": 0.1646028310060501,
|
|
"num_tokens": 7666120.0,
|
|
"step": 3425
|
|
},
|
|
{
|
|
"entropy": 5.796514987945557,
|
|
"epoch": 0.38524175885887574,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004991551610617611,
|
|
"loss": 5.8408,
|
|
"mean_token_accuracy": 0.16049385517835618,
|
|
"num_tokens": 7677132.0,
|
|
"step": 3430
|
|
},
|
|
{
|
|
"entropy": 5.968781232833862,
|
|
"epoch": 0.3858033357668333,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004991516815366812,
|
|
"loss": 5.9041,
|
|
"mean_token_accuracy": 0.1601366326212883,
|
|
"num_tokens": 7687515.0,
|
|
"step": 3435
|
|
},
|
|
{
|
|
"entropy": 5.767029762268066,
|
|
"epoch": 0.38636491267479084,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000499148194874525,
|
|
"loss": 5.7118,
|
|
"mean_token_accuracy": 0.16504708528518677,
|
|
"num_tokens": 7698454.0,
|
|
"step": 3440
|
|
},
|
|
{
|
|
"entropy": 5.698157548904419,
|
|
"epoch": 0.38692648958274833,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004991447010754032,
|
|
"loss": 5.6899,
|
|
"mean_token_accuracy": 0.1678033024072647,
|
|
"num_tokens": 7708940.0,
|
|
"step": 3445
|
|
},
|
|
{
|
|
"entropy": 5.8262519359588625,
|
|
"epoch": 0.3874880664907059,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004991412001394273,
|
|
"loss": 5.7239,
|
|
"mean_token_accuracy": 0.16594443321228028,
|
|
"num_tokens": 7719705.0,
|
|
"step": 3450
|
|
},
|
|
{
|
|
"entropy": 5.863242149353027,
|
|
"epoch": 0.38804964339866344,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004991376920667086,
|
|
"loss": 5.8811,
|
|
"mean_token_accuracy": 0.15880899280309677,
|
|
"num_tokens": 7730649.0,
|
|
"step": 3455
|
|
},
|
|
{
|
|
"entropy": 5.779720497131348,
|
|
"epoch": 0.388611220306621,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004991341768573589,
|
|
"loss": 5.8953,
|
|
"mean_token_accuracy": 0.1590091198682785,
|
|
"num_tokens": 7742014.0,
|
|
"step": 3460
|
|
},
|
|
{
|
|
"entropy": 5.901068115234375,
|
|
"epoch": 0.38917279721457854,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00049913065451149,
|
|
"loss": 5.799,
|
|
"mean_token_accuracy": 0.1558951511979103,
|
|
"num_tokens": 7752892.0,
|
|
"step": 3465
|
|
},
|
|
{
|
|
"entropy": 5.8446044921875,
|
|
"epoch": 0.3897343741225361,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004991271250292141,
|
|
"loss": 5.81,
|
|
"mean_token_accuracy": 0.157416270673275,
|
|
"num_tokens": 7762959.0,
|
|
"step": 3470
|
|
},
|
|
{
|
|
"entropy": 5.81669659614563,
|
|
"epoch": 0.39029595103049364,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004991235884106437,
|
|
"loss": 5.7144,
|
|
"mean_token_accuracy": 0.16509674340486527,
|
|
"num_tokens": 7773566.0,
|
|
"step": 3475
|
|
},
|
|
{
|
|
"entropy": 5.7814857959747314,
|
|
"epoch": 0.3908575279384512,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004991200446558913,
|
|
"loss": 5.748,
|
|
"mean_token_accuracy": 0.15518904775381087,
|
|
"num_tokens": 7785782.0,
|
|
"step": 3480
|
|
},
|
|
{
|
|
"entropy": 5.841710948944092,
|
|
"epoch": 0.39141910484640874,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004991164937650698,
|
|
"loss": 5.9032,
|
|
"mean_token_accuracy": 0.16198572665452957,
|
|
"num_tokens": 7797551.0,
|
|
"step": 3485
|
|
},
|
|
{
|
|
"entropy": 5.751931428909302,
|
|
"epoch": 0.39198068175436623,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004991129357382922,
|
|
"loss": 5.6772,
|
|
"mean_token_accuracy": 0.17679855972528458,
|
|
"num_tokens": 7808819.0,
|
|
"step": 3490
|
|
},
|
|
{
|
|
"entropy": 5.647474765777588,
|
|
"epoch": 0.3925422586623238,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004991093705756718,
|
|
"loss": 5.6283,
|
|
"mean_token_accuracy": 0.16952918767929076,
|
|
"num_tokens": 7818940.0,
|
|
"step": 3495
|
|
},
|
|
{
|
|
"entropy": 5.671689987182617,
|
|
"epoch": 0.39310383557028133,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004991057982773221,
|
|
"loss": 5.6507,
|
|
"mean_token_accuracy": 0.17054159790277482,
|
|
"num_tokens": 7829733.0,
|
|
"step": 3500
|
|
},
|
|
{
|
|
"entropy": 5.847164916992187,
|
|
"epoch": 0.3936654124782389,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004991022188433569,
|
|
"loss": 5.7133,
|
|
"mean_token_accuracy": 0.17065165787935258,
|
|
"num_tokens": 7840427.0,
|
|
"step": 3505
|
|
},
|
|
{
|
|
"entropy": 5.859947633743286,
|
|
"epoch": 0.39422698938619644,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00049909863227389,
|
|
"loss": 5.775,
|
|
"mean_token_accuracy": 0.16124107241630553,
|
|
"num_tokens": 7852834.0,
|
|
"step": 3510
|
|
},
|
|
{
|
|
"entropy": 5.7385765552520756,
|
|
"epoch": 0.394788566294154,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004990950385690358,
|
|
"loss": 5.8178,
|
|
"mean_token_accuracy": 0.1656463325023651,
|
|
"num_tokens": 7864993.0,
|
|
"step": 3515
|
|
},
|
|
{
|
|
"entropy": 5.750460052490235,
|
|
"epoch": 0.39535014320211154,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004990914377289088,
|
|
"loss": 5.793,
|
|
"mean_token_accuracy": 0.16076247096061708,
|
|
"num_tokens": 7876578.0,
|
|
"step": 3520
|
|
},
|
|
{
|
|
"entropy": 5.729760694503784,
|
|
"epoch": 0.3959117201100691,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004990878297536233,
|
|
"loss": 5.6272,
|
|
"mean_token_accuracy": 0.17054133117198944,
|
|
"num_tokens": 7886770.0,
|
|
"step": 3525
|
|
},
|
|
{
|
|
"entropy": 5.800265884399414,
|
|
"epoch": 0.39647329701802664,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004990842146432946,
|
|
"loss": 5.7904,
|
|
"mean_token_accuracy": 0.1667746052145958,
|
|
"num_tokens": 7897106.0,
|
|
"step": 3530
|
|
},
|
|
{
|
|
"entropy": 5.749977684020996,
|
|
"epoch": 0.3970348739259842,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004990805923980375,
|
|
"loss": 5.6444,
|
|
"mean_token_accuracy": 0.17652151733636856,
|
|
"num_tokens": 7907321.0,
|
|
"step": 3535
|
|
},
|
|
{
|
|
"entropy": 5.651272344589233,
|
|
"epoch": 0.3975964508339417,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004990769630179673,
|
|
"loss": 5.6569,
|
|
"mean_token_accuracy": 0.170053867995739,
|
|
"num_tokens": 7918628.0,
|
|
"step": 3540
|
|
},
|
|
{
|
|
"entropy": 5.872209167480468,
|
|
"epoch": 0.39815802774189923,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004990733265032,
|
|
"loss": 5.8387,
|
|
"mean_token_accuracy": 0.15291183888912202,
|
|
"num_tokens": 7929387.0,
|
|
"step": 3545
|
|
},
|
|
{
|
|
"entropy": 5.92167649269104,
|
|
"epoch": 0.3987196046498568,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004990696828538508,
|
|
"loss": 5.8595,
|
|
"mean_token_accuracy": 0.16960857212543487,
|
|
"num_tokens": 7940840.0,
|
|
"step": 3550
|
|
},
|
|
{
|
|
"entropy": 5.664200639724731,
|
|
"epoch": 0.39928118155781434,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000499066032070036,
|
|
"loss": 5.7269,
|
|
"mean_token_accuracy": 0.1674627184867859,
|
|
"num_tokens": 7952243.0,
|
|
"step": 3555
|
|
},
|
|
{
|
|
"entropy": 5.863605737686157,
|
|
"epoch": 0.3998427584657719,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004990623741518719,
|
|
"loss": 5.7724,
|
|
"mean_token_accuracy": 0.16179074645042418,
|
|
"num_tokens": 7963150.0,
|
|
"step": 3560
|
|
},
|
|
{
|
|
"entropy": 5.818461227416992,
|
|
"epoch": 0.40040433537372944,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000499058709099475,
|
|
"loss": 5.8741,
|
|
"mean_token_accuracy": 0.15937056988477707,
|
|
"num_tokens": 7974862.0,
|
|
"step": 3565
|
|
},
|
|
{
|
|
"entropy": 5.877570915222168,
|
|
"epoch": 0.400965912281687,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004990550369129618,
|
|
"loss": 5.8819,
|
|
"mean_token_accuracy": 0.16194065660238266,
|
|
"num_tokens": 7986438.0,
|
|
"step": 3570
|
|
},
|
|
{
|
|
"entropy": 5.8217613697052,
|
|
"epoch": 0.40152748918964454,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004990513575924494,
|
|
"loss": 5.7173,
|
|
"mean_token_accuracy": 0.16897953897714615,
|
|
"num_tokens": 7996958.0,
|
|
"step": 3575
|
|
},
|
|
{
|
|
"entropy": 5.835204267501831,
|
|
"epoch": 0.4020890660976021,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004990476711380548,
|
|
"loss": 5.8001,
|
|
"mean_token_accuracy": 0.1581471100449562,
|
|
"num_tokens": 8008862.0,
|
|
"step": 3580
|
|
},
|
|
{
|
|
"entropy": 5.774871110916138,
|
|
"epoch": 0.40265064300555964,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004990439775498954,
|
|
"loss": 5.7798,
|
|
"mean_token_accuracy": 0.1676494598388672,
|
|
"num_tokens": 8018940.0,
|
|
"step": 3585
|
|
},
|
|
{
|
|
"entropy": 5.914262056350708,
|
|
"epoch": 0.40321221991351713,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000499040276828089,
|
|
"loss": 5.7946,
|
|
"mean_token_accuracy": 0.15799015909433364,
|
|
"num_tokens": 8029148.0,
|
|
"step": 3590
|
|
},
|
|
{
|
|
"entropy": 5.742766189575195,
|
|
"epoch": 0.4037737968214747,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004990365689727533,
|
|
"loss": 5.7104,
|
|
"mean_token_accuracy": 0.1686326339840889,
|
|
"num_tokens": 8039618.0,
|
|
"step": 3595
|
|
},
|
|
{
|
|
"entropy": 5.744286060333252,
|
|
"epoch": 0.40433537372943223,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004990328539840062,
|
|
"loss": 5.6934,
|
|
"mean_token_accuracy": 0.16474545300006865,
|
|
"num_tokens": 8051145.0,
|
|
"step": 3600
|
|
},
|
|
{
|
|
"entropy": 5.7836991310119625,
|
|
"epoch": 0.4048969506373898,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004990291318619663,
|
|
"loss": 5.7609,
|
|
"mean_token_accuracy": 0.1606362998485565,
|
|
"num_tokens": 8061520.0,
|
|
"step": 3605
|
|
},
|
|
{
|
|
"entropy": 5.726670598983764,
|
|
"epoch": 0.40545852754534734,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004990254026067518,
|
|
"loss": 5.7099,
|
|
"mean_token_accuracy": 0.16285099536180497,
|
|
"num_tokens": 8072876.0,
|
|
"step": 3610
|
|
},
|
|
{
|
|
"entropy": 5.934379577636719,
|
|
"epoch": 0.4060201044533049,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004990216662184817,
|
|
"loss": 5.8154,
|
|
"mean_token_accuracy": 0.16516112834215163,
|
|
"num_tokens": 8084240.0,
|
|
"step": 3615
|
|
},
|
|
{
|
|
"entropy": 5.753713512420655,
|
|
"epoch": 0.40658168136126244,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004990179226972749,
|
|
"loss": 5.6932,
|
|
"mean_token_accuracy": 0.16864500045776368,
|
|
"num_tokens": 8095773.0,
|
|
"step": 3620
|
|
},
|
|
{
|
|
"entropy": 5.629334354400635,
|
|
"epoch": 0.40714325826922,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004990141720432504,
|
|
"loss": 5.6819,
|
|
"mean_token_accuracy": 0.167998369038105,
|
|
"num_tokens": 8107003.0,
|
|
"step": 3625
|
|
},
|
|
{
|
|
"entropy": 5.72817096710205,
|
|
"epoch": 0.40770483517717754,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004990104142565279,
|
|
"loss": 5.6439,
|
|
"mean_token_accuracy": 0.17401827424764632,
|
|
"num_tokens": 8117864.0,
|
|
"step": 3630
|
|
},
|
|
{
|
|
"entropy": 5.835469007492065,
|
|
"epoch": 0.40826641208513503,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000499006649337227,
|
|
"loss": 5.86,
|
|
"mean_token_accuracy": 0.16062401831150055,
|
|
"num_tokens": 8129363.0,
|
|
"step": 3635
|
|
},
|
|
{
|
|
"entropy": 5.805969905853272,
|
|
"epoch": 0.4088279889930926,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004990028772854674,
|
|
"loss": 5.7791,
|
|
"mean_token_accuracy": 0.1627799391746521,
|
|
"num_tokens": 8141319.0,
|
|
"step": 3640
|
|
},
|
|
{
|
|
"entropy": 5.784128999710083,
|
|
"epoch": 0.40938956590105013,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004989990981013693,
|
|
"loss": 5.6802,
|
|
"mean_token_accuracy": 0.1702434554696083,
|
|
"num_tokens": 8153344.0,
|
|
"step": 3645
|
|
},
|
|
{
|
|
"entropy": 5.774145793914795,
|
|
"epoch": 0.4099511428090077,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000498995311785053,
|
|
"loss": 5.8402,
|
|
"mean_token_accuracy": 0.162425434589386,
|
|
"num_tokens": 8164196.0,
|
|
"step": 3650
|
|
},
|
|
{
|
|
"entropy": 5.816594219207763,
|
|
"epoch": 0.41051271971696524,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004989915183366392,
|
|
"loss": 5.7159,
|
|
"mean_token_accuracy": 0.16790103316307067,
|
|
"num_tokens": 8174663.0,
|
|
"step": 3655
|
|
},
|
|
{
|
|
"entropy": 5.713854694366455,
|
|
"epoch": 0.4110742966249228,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004989877177562485,
|
|
"loss": 5.683,
|
|
"mean_token_accuracy": 0.1685110315680504,
|
|
"num_tokens": 8185215.0,
|
|
"step": 3660
|
|
},
|
|
{
|
|
"entropy": 5.739247465133667,
|
|
"epoch": 0.41163587353288034,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000498983910044002,
|
|
"loss": 5.7765,
|
|
"mean_token_accuracy": 0.17141249477863313,
|
|
"num_tokens": 8195694.0,
|
|
"step": 3665
|
|
},
|
|
{
|
|
"entropy": 5.681199550628662,
|
|
"epoch": 0.4121974504408379,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004989800952000209,
|
|
"loss": 5.6616,
|
|
"mean_token_accuracy": 0.17553078830242158,
|
|
"num_tokens": 8206112.0,
|
|
"step": 3670
|
|
},
|
|
{
|
|
"entropy": 5.731632661819458,
|
|
"epoch": 0.41275902734879544,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004989762732244268,
|
|
"loss": 5.7515,
|
|
"mean_token_accuracy": 0.1661844179034233,
|
|
"num_tokens": 8216548.0,
|
|
"step": 3675
|
|
},
|
|
{
|
|
"entropy": 5.843146276473999,
|
|
"epoch": 0.413320604256753,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004989724441173413,
|
|
"loss": 5.7867,
|
|
"mean_token_accuracy": 0.16781337559223175,
|
|
"num_tokens": 8226643.0,
|
|
"step": 3680
|
|
},
|
|
{
|
|
"entropy": 5.857947587966919,
|
|
"epoch": 0.4138821811647105,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004989686078788862,
|
|
"loss": 5.8183,
|
|
"mean_token_accuracy": 0.16166319102048873,
|
|
"num_tokens": 8236755.0,
|
|
"step": 3685
|
|
},
|
|
{
|
|
"entropy": 5.782751274108887,
|
|
"epoch": 0.41444375807266803,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004989647645091839,
|
|
"loss": 5.6963,
|
|
"mean_token_accuracy": 0.16801404505968093,
|
|
"num_tokens": 8247526.0,
|
|
"step": 3690
|
|
},
|
|
{
|
|
"entropy": 5.734130477905273,
|
|
"epoch": 0.4150053349806256,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004989609140083565,
|
|
"loss": 5.794,
|
|
"mean_token_accuracy": 0.15583045184612274,
|
|
"num_tokens": 8258649.0,
|
|
"step": 3695
|
|
},
|
|
{
|
|
"entropy": 5.765203428268433,
|
|
"epoch": 0.41556691188858313,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004989570563765269,
|
|
"loss": 5.676,
|
|
"mean_token_accuracy": 0.1731864795088768,
|
|
"num_tokens": 8268260.0,
|
|
"step": 3700
|
|
},
|
|
{
|
|
"entropy": 5.9308096408844,
|
|
"epoch": 0.4161284887965407,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004989531916138176,
|
|
"loss": 5.8785,
|
|
"mean_token_accuracy": 0.1627708837389946,
|
|
"num_tokens": 8280090.0,
|
|
"step": 3705
|
|
},
|
|
{
|
|
"entropy": 5.841350793838501,
|
|
"epoch": 0.41669006570449824,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004989493197203519,
|
|
"loss": 5.7489,
|
|
"mean_token_accuracy": 0.1697134330868721,
|
|
"num_tokens": 8291217.0,
|
|
"step": 3710
|
|
},
|
|
{
|
|
"entropy": 5.754220199584961,
|
|
"epoch": 0.4172516426124558,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000498945440696253,
|
|
"loss": 5.6683,
|
|
"mean_token_accuracy": 0.17081218361854553,
|
|
"num_tokens": 8303541.0,
|
|
"step": 3715
|
|
},
|
|
{
|
|
"entropy": 5.719450426101685,
|
|
"epoch": 0.41781321952041334,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004989415545416444,
|
|
"loss": 5.7355,
|
|
"mean_token_accuracy": 0.1609584018588066,
|
|
"num_tokens": 8316104.0,
|
|
"step": 3720
|
|
},
|
|
{
|
|
"entropy": 5.714957666397095,
|
|
"epoch": 0.4183747964283709,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004989376612566498,
|
|
"loss": 5.6832,
|
|
"mean_token_accuracy": 0.16480520740151405,
|
|
"num_tokens": 8327158.0,
|
|
"step": 3725
|
|
},
|
|
{
|
|
"entropy": 5.846664381027222,
|
|
"epoch": 0.4189363733363284,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004989337608413933,
|
|
"loss": 5.8338,
|
|
"mean_token_accuracy": 0.16076735854148866,
|
|
"num_tokens": 8337685.0,
|
|
"step": 3730
|
|
},
|
|
{
|
|
"entropy": 5.870333480834961,
|
|
"epoch": 0.41949795024428593,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004989298532959989,
|
|
"loss": 5.8683,
|
|
"mean_token_accuracy": 0.16113072335720063,
|
|
"num_tokens": 8349778.0,
|
|
"step": 3735
|
|
},
|
|
{
|
|
"entropy": 5.7798456192016605,
|
|
"epoch": 0.4200595271522435,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004989259386205912,
|
|
"loss": 5.7038,
|
|
"mean_token_accuracy": 0.176594515144825,
|
|
"num_tokens": 8361041.0,
|
|
"step": 3740
|
|
},
|
|
{
|
|
"entropy": 5.8628821849823,
|
|
"epoch": 0.42062110406020103,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004989220168152948,
|
|
"loss": 5.8965,
|
|
"mean_token_accuracy": 0.15907129645347595,
|
|
"num_tokens": 8373227.0,
|
|
"step": 3745
|
|
},
|
|
{
|
|
"entropy": 5.7868818759918215,
|
|
"epoch": 0.4211826809681586,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004989180878802346,
|
|
"loss": 5.7209,
|
|
"mean_token_accuracy": 0.16800411641597748,
|
|
"num_tokens": 8384223.0,
|
|
"step": 3750
|
|
},
|
|
{
|
|
"entropy": 5.731780624389648,
|
|
"epoch": 0.42174425787611614,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004989141518155354,
|
|
"loss": 5.7506,
|
|
"mean_token_accuracy": 0.1691988691687584,
|
|
"num_tokens": 8395014.0,
|
|
"step": 3755
|
|
},
|
|
{
|
|
"entropy": 5.823819208145141,
|
|
"epoch": 0.4223058347840737,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004989102086213229,
|
|
"loss": 5.7283,
|
|
"mean_token_accuracy": 0.16270644217729568,
|
|
"num_tokens": 8406445.0,
|
|
"step": 3760
|
|
},
|
|
{
|
|
"entropy": 5.693364000320434,
|
|
"epoch": 0.42286741169203124,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004989062582977225,
|
|
"loss": 5.665,
|
|
"mean_token_accuracy": 0.1706314980983734,
|
|
"num_tokens": 8417488.0,
|
|
"step": 3765
|
|
},
|
|
{
|
|
"entropy": 5.793571662902832,
|
|
"epoch": 0.4234289885999888,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004989023008448599,
|
|
"loss": 5.8689,
|
|
"mean_token_accuracy": 0.15837376266717912,
|
|
"num_tokens": 8430582.0,
|
|
"step": 3770
|
|
},
|
|
{
|
|
"entropy": 5.831238794326782,
|
|
"epoch": 0.42399056550794634,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004988983362628614,
|
|
"loss": 5.6906,
|
|
"mean_token_accuracy": 0.164572674036026,
|
|
"num_tokens": 8442033.0,
|
|
"step": 3775
|
|
},
|
|
{
|
|
"entropy": 5.690927267074585,
|
|
"epoch": 0.42455214241590383,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004988943645518528,
|
|
"loss": 5.6636,
|
|
"mean_token_accuracy": 0.16775935739278794,
|
|
"num_tokens": 8451722.0,
|
|
"step": 3780
|
|
},
|
|
{
|
|
"entropy": 5.668238401412964,
|
|
"epoch": 0.4251137193238614,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004988903857119611,
|
|
"loss": 5.75,
|
|
"mean_token_accuracy": 0.1658486858010292,
|
|
"num_tokens": 8462753.0,
|
|
"step": 3785
|
|
},
|
|
{
|
|
"entropy": 5.861290073394775,
|
|
"epoch": 0.42567529623181893,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004988863997433125,
|
|
"loss": 5.7587,
|
|
"mean_token_accuracy": 0.16550534069538117,
|
|
"num_tokens": 8472755.0,
|
|
"step": 3790
|
|
},
|
|
{
|
|
"entropy": 5.766337490081787,
|
|
"epoch": 0.4262368731397765,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004988824066460341,
|
|
"loss": 5.7399,
|
|
"mean_token_accuracy": 0.16958845853805543,
|
|
"num_tokens": 8483296.0,
|
|
"step": 3795
|
|
},
|
|
{
|
|
"entropy": 5.7786054611206055,
|
|
"epoch": 0.42679845004773403,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000498878406420253,
|
|
"loss": 5.6058,
|
|
"mean_token_accuracy": 0.17350622415542602,
|
|
"num_tokens": 8493739.0,
|
|
"step": 3800
|
|
},
|
|
{
|
|
"entropy": 5.682381916046142,
|
|
"epoch": 0.4273600269556916,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004988743990660967,
|
|
"loss": 5.7767,
|
|
"mean_token_accuracy": 0.162274731695652,
|
|
"num_tokens": 8504788.0,
|
|
"step": 3805
|
|
},
|
|
{
|
|
"entropy": 5.797802543640136,
|
|
"epoch": 0.42792160386364914,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004988703845836927,
|
|
"loss": 5.7306,
|
|
"mean_token_accuracy": 0.1645368903875351,
|
|
"num_tokens": 8514708.0,
|
|
"step": 3810
|
|
},
|
|
{
|
|
"entropy": 5.790168046951294,
|
|
"epoch": 0.4284831807716067,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004988663629731687,
|
|
"loss": 5.6135,
|
|
"mean_token_accuracy": 0.17496834099292755,
|
|
"num_tokens": 8525227.0,
|
|
"step": 3815
|
|
},
|
|
{
|
|
"entropy": 5.622102165222168,
|
|
"epoch": 0.42904475767956424,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000498862334234653,
|
|
"loss": 5.6619,
|
|
"mean_token_accuracy": 0.17011212110519408,
|
|
"num_tokens": 8536502.0,
|
|
"step": 3820
|
|
},
|
|
{
|
|
"entropy": 5.7700787544250485,
|
|
"epoch": 0.4296063345875218,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004988582983682737,
|
|
"loss": 5.8033,
|
|
"mean_token_accuracy": 0.16546136736869813,
|
|
"num_tokens": 8548087.0,
|
|
"step": 3825
|
|
},
|
|
{
|
|
"entropy": 5.85570330619812,
|
|
"epoch": 0.4301679114954793,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004988542553741594,
|
|
"loss": 5.809,
|
|
"mean_token_accuracy": 0.1667978622019291,
|
|
"num_tokens": 8560856.0,
|
|
"step": 3830
|
|
},
|
|
{
|
|
"entropy": 5.931719970703125,
|
|
"epoch": 0.43072948840343683,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004988502052524388,
|
|
"loss": 5.9145,
|
|
"mean_token_accuracy": 0.16501590609550476,
|
|
"num_tokens": 8572521.0,
|
|
"step": 3835
|
|
},
|
|
{
|
|
"entropy": 5.84990963935852,
|
|
"epoch": 0.4312910653113944,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004988461480032408,
|
|
"loss": 5.7442,
|
|
"mean_token_accuracy": 0.1674473449587822,
|
|
"num_tokens": 8583977.0,
|
|
"step": 3840
|
|
},
|
|
{
|
|
"entropy": 5.704129409790039,
|
|
"epoch": 0.43185264221935193,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004988420836266946,
|
|
"loss": 5.6924,
|
|
"mean_token_accuracy": 0.16754663586616517,
|
|
"num_tokens": 8594441.0,
|
|
"step": 3845
|
|
},
|
|
{
|
|
"entropy": 5.84066071510315,
|
|
"epoch": 0.4324142191273095,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004988380121229298,
|
|
"loss": 5.7392,
|
|
"mean_token_accuracy": 0.16255563497543335,
|
|
"num_tokens": 8604843.0,
|
|
"step": 3850
|
|
},
|
|
{
|
|
"entropy": 5.746822309494019,
|
|
"epoch": 0.43297579603526704,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004988339334920757,
|
|
"loss": 5.7298,
|
|
"mean_token_accuracy": 0.16818083822727203,
|
|
"num_tokens": 8616059.0,
|
|
"step": 3855
|
|
},
|
|
{
|
|
"entropy": 5.74391360282898,
|
|
"epoch": 0.4335373729432246,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004988298477342625,
|
|
"loss": 5.6845,
|
|
"mean_token_accuracy": 0.17156679034233094,
|
|
"num_tokens": 8626203.0,
|
|
"step": 3860
|
|
},
|
|
{
|
|
"entropy": 5.739895057678223,
|
|
"epoch": 0.43409894985118214,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00049882575484962,
|
|
"loss": 5.684,
|
|
"mean_token_accuracy": 0.16509181261062622,
|
|
"num_tokens": 8636921.0,
|
|
"step": 3865
|
|
},
|
|
{
|
|
"entropy": 5.6815019130706785,
|
|
"epoch": 0.4346605267591397,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004988216548382787,
|
|
"loss": 5.6579,
|
|
"mean_token_accuracy": 0.17124742418527603,
|
|
"num_tokens": 8648526.0,
|
|
"step": 3870
|
|
},
|
|
{
|
|
"entropy": 5.796351671218872,
|
|
"epoch": 0.4352221036670972,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004988175477003691,
|
|
"loss": 5.8049,
|
|
"mean_token_accuracy": 0.15377746522426605,
|
|
"num_tokens": 8660339.0,
|
|
"step": 3875
|
|
},
|
|
{
|
|
"entropy": 5.9060732364654545,
|
|
"epoch": 0.43578368057505473,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000498813433436022,
|
|
"loss": 5.8632,
|
|
"mean_token_accuracy": 0.1561919257044792,
|
|
"num_tokens": 8671835.0,
|
|
"step": 3880
|
|
},
|
|
{
|
|
"entropy": 5.678639030456543,
|
|
"epoch": 0.4363452574830123,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004988093120453684,
|
|
"loss": 5.5652,
|
|
"mean_token_accuracy": 0.17134900540113449,
|
|
"num_tokens": 8681146.0,
|
|
"step": 3885
|
|
},
|
|
{
|
|
"entropy": 5.650815439224243,
|
|
"epoch": 0.43690683439096983,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004988051835285394,
|
|
"loss": 5.6231,
|
|
"mean_token_accuracy": 0.17194372713565825,
|
|
"num_tokens": 8691623.0,
|
|
"step": 3890
|
|
},
|
|
{
|
|
"entropy": 5.765362548828125,
|
|
"epoch": 0.4374684112989274,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004988010478856667,
|
|
"loss": 5.7243,
|
|
"mean_token_accuracy": 0.16024973541498183,
|
|
"num_tokens": 8703702.0,
|
|
"step": 3895
|
|
},
|
|
{
|
|
"entropy": 5.937811851501465,
|
|
"epoch": 0.43802998820688493,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004987969051168816,
|
|
"loss": 5.8895,
|
|
"mean_token_accuracy": 0.16733449399471284,
|
|
"num_tokens": 8715434.0,
|
|
"step": 3900
|
|
},
|
|
{
|
|
"entropy": 5.7049939155578615,
|
|
"epoch": 0.4385915651148425,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004987927552223165,
|
|
"loss": 5.6636,
|
|
"mean_token_accuracy": 0.17958703339099885,
|
|
"num_tokens": 8726135.0,
|
|
"step": 3905
|
|
},
|
|
{
|
|
"entropy": 5.635489463806152,
|
|
"epoch": 0.43915314202280004,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004987885982021032,
|
|
"loss": 5.761,
|
|
"mean_token_accuracy": 0.16973788887262345,
|
|
"num_tokens": 8736538.0,
|
|
"step": 3910
|
|
},
|
|
{
|
|
"entropy": 5.879006290435791,
|
|
"epoch": 0.4397147189307576,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004987844340563741,
|
|
"loss": 5.6806,
|
|
"mean_token_accuracy": 0.17044662386178971,
|
|
"num_tokens": 8746456.0,
|
|
"step": 3915
|
|
},
|
|
{
|
|
"entropy": 5.7940206050872805,
|
|
"epoch": 0.44027629583871514,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004987802627852619,
|
|
"loss": 5.7909,
|
|
"mean_token_accuracy": 0.16806718856096267,
|
|
"num_tokens": 8757143.0,
|
|
"step": 3920
|
|
},
|
|
{
|
|
"entropy": 5.737888336181641,
|
|
"epoch": 0.44083787274667263,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004987760843888992,
|
|
"loss": 5.7794,
|
|
"mean_token_accuracy": 0.17163707613945006,
|
|
"num_tokens": 8769084.0,
|
|
"step": 3925
|
|
},
|
|
{
|
|
"entropy": 5.792534828186035,
|
|
"epoch": 0.4413994496546302,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004987718988674193,
|
|
"loss": 5.7753,
|
|
"mean_token_accuracy": 0.16346744000911712,
|
|
"num_tokens": 8780707.0,
|
|
"step": 3930
|
|
},
|
|
{
|
|
"entropy": 5.78266863822937,
|
|
"epoch": 0.44196102656258773,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004987677062209552,
|
|
"loss": 5.7305,
|
|
"mean_token_accuracy": 0.16145867258310317,
|
|
"num_tokens": 8792157.0,
|
|
"step": 3935
|
|
},
|
|
{
|
|
"entropy": 5.824311637878418,
|
|
"epoch": 0.4425226034705453,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004987635064496407,
|
|
"loss": 5.7576,
|
|
"mean_token_accuracy": 0.16702643185853958,
|
|
"num_tokens": 8802691.0,
|
|
"step": 3940
|
|
},
|
|
{
|
|
"entropy": 5.8741062641143795,
|
|
"epoch": 0.44308418037850283,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004987592995536093,
|
|
"loss": 5.7672,
|
|
"mean_token_accuracy": 0.1658184953033924,
|
|
"num_tokens": 8814869.0,
|
|
"step": 3945
|
|
},
|
|
{
|
|
"entropy": 5.73998441696167,
|
|
"epoch": 0.4436457572864604,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004987550855329951,
|
|
"loss": 5.7099,
|
|
"mean_token_accuracy": 0.17231065332889556,
|
|
"num_tokens": 8825264.0,
|
|
"step": 3950
|
|
},
|
|
{
|
|
"entropy": 5.8049551486969,
|
|
"epoch": 0.44420733419441794,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004987508643879322,
|
|
"loss": 5.787,
|
|
"mean_token_accuracy": 0.16581701785326003,
|
|
"num_tokens": 8837128.0,
|
|
"step": 3955
|
|
},
|
|
{
|
|
"entropy": 5.801353025436401,
|
|
"epoch": 0.4447689111023755,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004987466361185549,
|
|
"loss": 5.7861,
|
|
"mean_token_accuracy": 0.15883654057979585,
|
|
"num_tokens": 8848587.0,
|
|
"step": 3960
|
|
},
|
|
{
|
|
"entropy": 5.848768043518066,
|
|
"epoch": 0.44533048801033304,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004987424007249979,
|
|
"loss": 5.8546,
|
|
"mean_token_accuracy": 0.16280081868171692,
|
|
"num_tokens": 8859219.0,
|
|
"step": 3965
|
|
},
|
|
{
|
|
"entropy": 5.788423871994018,
|
|
"epoch": 0.4458920649182906,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004987381582073962,
|
|
"loss": 5.7406,
|
|
"mean_token_accuracy": 0.17112360298633575,
|
|
"num_tokens": 8868780.0,
|
|
"step": 3970
|
|
},
|
|
{
|
|
"entropy": 5.834964323043823,
|
|
"epoch": 0.4464536418262481,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004987339085658848,
|
|
"loss": 5.7172,
|
|
"mean_token_accuracy": 0.1637463465332985,
|
|
"num_tokens": 8880903.0,
|
|
"step": 3975
|
|
},
|
|
{
|
|
"entropy": 5.660829162597656,
|
|
"epoch": 0.44701521873420563,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004987296518005988,
|
|
"loss": 5.5606,
|
|
"mean_token_accuracy": 0.17245692163705825,
|
|
"num_tokens": 8890335.0,
|
|
"step": 3980
|
|
},
|
|
{
|
|
"entropy": 5.665368318557739,
|
|
"epoch": 0.4475767956421632,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000498725387911674,
|
|
"loss": 5.7033,
|
|
"mean_token_accuracy": 0.16330161690711975,
|
|
"num_tokens": 8904104.0,
|
|
"step": 3985
|
|
},
|
|
{
|
|
"entropy": 5.9002443790435795,
|
|
"epoch": 0.44813837255012073,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004987211168992461,
|
|
"loss": 5.7955,
|
|
"mean_token_accuracy": 0.1588960111141205,
|
|
"num_tokens": 8915118.0,
|
|
"step": 3990
|
|
},
|
|
{
|
|
"entropy": 5.748874807357788,
|
|
"epoch": 0.4486999494580783,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000498716838763451,
|
|
"loss": 5.7518,
|
|
"mean_token_accuracy": 0.16183157116174698,
|
|
"num_tokens": 8927450.0,
|
|
"step": 3995
|
|
},
|
|
{
|
|
"entropy": 5.855266857147217,
|
|
"epoch": 0.44926152636603583,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000498712553504425,
|
|
"loss": 5.8327,
|
|
"mean_token_accuracy": 0.16530437469482423,
|
|
"num_tokens": 8939902.0,
|
|
"step": 4000
|
|
},
|
|
{
|
|
"entropy": 5.803925609588623,
|
|
"epoch": 0.4498231032739934,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004987082611223046,
|
|
"loss": 5.6966,
|
|
"mean_token_accuracy": 0.16004012376070023,
|
|
"num_tokens": 8951736.0,
|
|
"step": 4005
|
|
},
|
|
{
|
|
"entropy": 5.824748182296753,
|
|
"epoch": 0.45038468018195094,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004987039616172265,
|
|
"loss": 5.7918,
|
|
"mean_token_accuracy": 0.16543588787317276,
|
|
"num_tokens": 8963283.0,
|
|
"step": 4010
|
|
},
|
|
{
|
|
"entropy": 5.746975517272949,
|
|
"epoch": 0.4509462570899085,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004986996549893273,
|
|
"loss": 5.6875,
|
|
"mean_token_accuracy": 0.1728332132101059,
|
|
"num_tokens": 8974323.0,
|
|
"step": 4015
|
|
},
|
|
{
|
|
"entropy": 5.742187404632569,
|
|
"epoch": 0.451507833997866,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004986953412387445,
|
|
"loss": 5.7779,
|
|
"mean_token_accuracy": 0.1621204733848572,
|
|
"num_tokens": 8986687.0,
|
|
"step": 4020
|
|
},
|
|
{
|
|
"entropy": 5.705374097824096,
|
|
"epoch": 0.45206941090582353,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004986910203656151,
|
|
"loss": 5.6662,
|
|
"mean_token_accuracy": 0.17241707146167756,
|
|
"num_tokens": 8997734.0,
|
|
"step": 4025
|
|
},
|
|
{
|
|
"entropy": 5.743109798431396,
|
|
"epoch": 0.4526309878137811,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004986866923700769,
|
|
"loss": 5.79,
|
|
"mean_token_accuracy": 0.15861670374870301,
|
|
"num_tokens": 9008743.0,
|
|
"step": 4030
|
|
},
|
|
{
|
|
"entropy": 5.864490699768067,
|
|
"epoch": 0.45319256472173863,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004986823572522677,
|
|
"loss": 5.649,
|
|
"mean_token_accuracy": 0.167484150826931,
|
|
"num_tokens": 9019495.0,
|
|
"step": 4035
|
|
},
|
|
{
|
|
"entropy": 5.750733947753906,
|
|
"epoch": 0.4537541416296962,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004986780150123254,
|
|
"loss": 5.7626,
|
|
"mean_token_accuracy": 0.16347892284393312,
|
|
"num_tokens": 9029546.0,
|
|
"step": 4040
|
|
},
|
|
{
|
|
"entropy": 5.62654070854187,
|
|
"epoch": 0.45431571853765373,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004986736656503885,
|
|
"loss": 5.5203,
|
|
"mean_token_accuracy": 0.17364439517259597,
|
|
"num_tokens": 9040393.0,
|
|
"step": 4045
|
|
},
|
|
{
|
|
"entropy": 5.732595634460449,
|
|
"epoch": 0.4548772954456113,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004986693091665952,
|
|
"loss": 5.7232,
|
|
"mean_token_accuracy": 0.16511399149894715,
|
|
"num_tokens": 9050840.0,
|
|
"step": 4050
|
|
},
|
|
{
|
|
"entropy": 5.76080846786499,
|
|
"epoch": 0.45543887235356884,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004986649455610845,
|
|
"loss": 5.6551,
|
|
"mean_token_accuracy": 0.16657507717609404,
|
|
"num_tokens": 9061615.0,
|
|
"step": 4055
|
|
},
|
|
{
|
|
"entropy": 5.688541269302368,
|
|
"epoch": 0.4560004492615264,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.000498660574833995,
|
|
"loss": 5.6307,
|
|
"mean_token_accuracy": 0.17303157597780228,
|
|
"num_tokens": 9071902.0,
|
|
"step": 4060
|
|
},
|
|
{
|
|
"entropy": 5.747698211669922,
|
|
"epoch": 0.45656202616948394,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004986561969854661,
|
|
"loss": 5.7872,
|
|
"mean_token_accuracy": 0.16532022655010223,
|
|
"num_tokens": 9083613.0,
|
|
"step": 4065
|
|
},
|
|
{
|
|
"entropy": 5.754197359085083,
|
|
"epoch": 0.45712360307744143,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004986518120156373,
|
|
"loss": 5.6888,
|
|
"mean_token_accuracy": 0.16673017293214798,
|
|
"num_tokens": 9095678.0,
|
|
"step": 4070
|
|
},
|
|
{
|
|
"entropy": 5.761954212188721,
|
|
"epoch": 0.457685179985399,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000498647419924648,
|
|
"loss": 5.696,
|
|
"mean_token_accuracy": 0.17291476875543593,
|
|
"num_tokens": 9106637.0,
|
|
"step": 4075
|
|
},
|
|
{
|
|
"entropy": 5.667988586425781,
|
|
"epoch": 0.45824675689335653,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000498643020712638,
|
|
"loss": 5.6597,
|
|
"mean_token_accuracy": 0.17288853377103805,
|
|
"num_tokens": 9117343.0,
|
|
"step": 4080
|
|
},
|
|
{
|
|
"entropy": 5.798785257339477,
|
|
"epoch": 0.4588083338013141,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004986386143797475,
|
|
"loss": 5.7887,
|
|
"mean_token_accuracy": 0.15990065932273864,
|
|
"num_tokens": 9129315.0,
|
|
"step": 4085
|
|
},
|
|
{
|
|
"entropy": 5.7697852611541744,
|
|
"epoch": 0.45936991070927163,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004986342009261169,
|
|
"loss": 5.6784,
|
|
"mean_token_accuracy": 0.16411612257361413,
|
|
"num_tokens": 9139701.0,
|
|
"step": 4090
|
|
},
|
|
{
|
|
"entropy": 5.79812912940979,
|
|
"epoch": 0.4599314876172292,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004986297803518865,
|
|
"loss": 5.8133,
|
|
"mean_token_accuracy": 0.16509659737348556,
|
|
"num_tokens": 9152334.0,
|
|
"step": 4095
|
|
},
|
|
{
|
|
"entropy": 5.762947416305542,
|
|
"epoch": 0.46049306452518673,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004986253526571971,
|
|
"loss": 5.6195,
|
|
"mean_token_accuracy": 0.17192814201116563,
|
|
"num_tokens": 9163277.0,
|
|
"step": 4100
|
|
},
|
|
{
|
|
"entropy": 5.772461366653443,
|
|
"epoch": 0.4610546414331443,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004986209178421899,
|
|
"loss": 5.802,
|
|
"mean_token_accuracy": 0.1619513064622879,
|
|
"num_tokens": 9174909.0,
|
|
"step": 4105
|
|
},
|
|
{
|
|
"entropy": 5.647283840179443,
|
|
"epoch": 0.46161621834110184,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000498616475907006,
|
|
"loss": 5.5928,
|
|
"mean_token_accuracy": 0.16549195647239684,
|
|
"num_tokens": 9186058.0,
|
|
"step": 4110
|
|
},
|
|
{
|
|
"entropy": 5.73241286277771,
|
|
"epoch": 0.46217779524905933,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004986120268517865,
|
|
"loss": 5.7547,
|
|
"mean_token_accuracy": 0.16822669506072999,
|
|
"num_tokens": 9196919.0,
|
|
"step": 4115
|
|
},
|
|
{
|
|
"entropy": 5.772916507720947,
|
|
"epoch": 0.4627393721570169,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004986075706766736,
|
|
"loss": 5.7294,
|
|
"mean_token_accuracy": 0.16655745655298232,
|
|
"num_tokens": 9208452.0,
|
|
"step": 4120
|
|
},
|
|
{
|
|
"entropy": 5.783675956726074,
|
|
"epoch": 0.46330094906497443,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004986031073818088,
|
|
"loss": 5.7842,
|
|
"mean_token_accuracy": 0.1649884581565857,
|
|
"num_tokens": 9219605.0,
|
|
"step": 4125
|
|
},
|
|
{
|
|
"entropy": 5.74765625,
|
|
"epoch": 0.463862525972932,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004985986369673343,
|
|
"loss": 5.6159,
|
|
"mean_token_accuracy": 0.17641097754240037,
|
|
"num_tokens": 9230491.0,
|
|
"step": 4130
|
|
},
|
|
{
|
|
"entropy": 5.717433166503906,
|
|
"epoch": 0.46442410288088953,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004985941594333926,
|
|
"loss": 5.7567,
|
|
"mean_token_accuracy": 0.16423618644475937,
|
|
"num_tokens": 9241768.0,
|
|
"step": 4135
|
|
},
|
|
{
|
|
"entropy": 5.800970554351807,
|
|
"epoch": 0.4649856797888471,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000498589674780126,
|
|
"loss": 5.7934,
|
|
"mean_token_accuracy": 0.16235399544239043,
|
|
"num_tokens": 9253779.0,
|
|
"step": 4140
|
|
},
|
|
{
|
|
"entropy": 5.94872088432312,
|
|
"epoch": 0.46554725669680463,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004985851830076775,
|
|
"loss": 5.6916,
|
|
"mean_token_accuracy": 0.17534759044647216,
|
|
"num_tokens": 9264567.0,
|
|
"step": 4145
|
|
},
|
|
{
|
|
"entropy": 5.591338491439819,
|
|
"epoch": 0.4661088336047622,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004985806841161901,
|
|
"loss": 5.6529,
|
|
"mean_token_accuracy": 0.17427073419094086,
|
|
"num_tokens": 9275960.0,
|
|
"step": 4150
|
|
},
|
|
{
|
|
"entropy": 5.708569431304932,
|
|
"epoch": 0.46667041051271974,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.000498576178105807,
|
|
"loss": 5.7891,
|
|
"mean_token_accuracy": 0.17374880164861678,
|
|
"num_tokens": 9288305.0,
|
|
"step": 4155
|
|
},
|
|
{
|
|
"entropy": 5.802067136764526,
|
|
"epoch": 0.4672319874206773,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004985716649766717,
|
|
"loss": 5.6165,
|
|
"mean_token_accuracy": 0.17416664063930512,
|
|
"num_tokens": 9299579.0,
|
|
"step": 4160
|
|
},
|
|
{
|
|
"entropy": 5.667328643798828,
|
|
"epoch": 0.4677935643286348,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004985671447289277,
|
|
"loss": 5.6468,
|
|
"mean_token_accuracy": 0.16909621357917787,
|
|
"num_tokens": 9311221.0,
|
|
"step": 4165
|
|
},
|
|
{
|
|
"entropy": 5.732243394851684,
|
|
"epoch": 0.46835514123659233,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004985626173627194,
|
|
"loss": 5.7524,
|
|
"mean_token_accuracy": 0.16208277642726898,
|
|
"num_tokens": 9322488.0,
|
|
"step": 4170
|
|
},
|
|
{
|
|
"entropy": 5.74122986793518,
|
|
"epoch": 0.4689167181445499,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004985580828781904,
|
|
"loss": 5.7099,
|
|
"mean_token_accuracy": 0.16819628775119783,
|
|
"num_tokens": 9333672.0,
|
|
"step": 4175
|
|
},
|
|
{
|
|
"entropy": 5.8608152866363525,
|
|
"epoch": 0.46947829505250743,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004985535412754855,
|
|
"loss": 5.7418,
|
|
"mean_token_accuracy": 0.16545120030641555,
|
|
"num_tokens": 9344449.0,
|
|
"step": 4180
|
|
},
|
|
{
|
|
"entropy": 5.826900577545166,
|
|
"epoch": 0.470039871960465,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.000498548992554749,
|
|
"loss": 5.8074,
|
|
"mean_token_accuracy": 0.1609753578901291,
|
|
"num_tokens": 9355279.0,
|
|
"step": 4185
|
|
},
|
|
{
|
|
"entropy": 5.751828336715699,
|
|
"epoch": 0.47060144886842253,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004985444367161259,
|
|
"loss": 5.7103,
|
|
"mean_token_accuracy": 0.16859401911497116,
|
|
"num_tokens": 9366942.0,
|
|
"step": 4190
|
|
},
|
|
{
|
|
"entropy": 5.685658740997314,
|
|
"epoch": 0.4711630257763801,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004985398737597614,
|
|
"loss": 5.6355,
|
|
"mean_token_accuracy": 0.1736157312989235,
|
|
"num_tokens": 9378129.0,
|
|
"step": 4195
|
|
},
|
|
{
|
|
"entropy": 5.801950359344483,
|
|
"epoch": 0.47172460268433763,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004985353036858004,
|
|
"loss": 5.7287,
|
|
"mean_token_accuracy": 0.16660770624876023,
|
|
"num_tokens": 9388757.0,
|
|
"step": 4200
|
|
},
|
|
{
|
|
"entropy": 5.744151067733765,
|
|
"epoch": 0.4722861795922952,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004985307264943887,
|
|
"loss": 5.6745,
|
|
"mean_token_accuracy": 0.16941459774971007,
|
|
"num_tokens": 9399112.0,
|
|
"step": 4205
|
|
},
|
|
{
|
|
"entropy": 5.7844664573669435,
|
|
"epoch": 0.47284775650025274,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004985261421856721,
|
|
"loss": 5.7691,
|
|
"mean_token_accuracy": 0.16700249612331391,
|
|
"num_tokens": 9410156.0,
|
|
"step": 4210
|
|
},
|
|
{
|
|
"entropy": 5.833684635162354,
|
|
"epoch": 0.47340933340821023,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004985215507597963,
|
|
"loss": 5.7515,
|
|
"mean_token_accuracy": 0.17010293602943422,
|
|
"num_tokens": 9420402.0,
|
|
"step": 4215
|
|
},
|
|
{
|
|
"entropy": 5.729236125946045,
|
|
"epoch": 0.4739709103161678,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004985169522169076,
|
|
"loss": 5.7532,
|
|
"mean_token_accuracy": 0.1657623678445816,
|
|
"num_tokens": 9431159.0,
|
|
"step": 4220
|
|
},
|
|
{
|
|
"entropy": 5.701308298110962,
|
|
"epoch": 0.47453248722412533,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004985123465571526,
|
|
"loss": 5.6592,
|
|
"mean_token_accuracy": 0.17336241155862808,
|
|
"num_tokens": 9441737.0,
|
|
"step": 4225
|
|
},
|
|
{
|
|
"entropy": 5.6865349292755125,
|
|
"epoch": 0.4750940641320829,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004985077337806777,
|
|
"loss": 5.6196,
|
|
"mean_token_accuracy": 0.1779865562915802,
|
|
"num_tokens": 9452756.0,
|
|
"step": 4230
|
|
},
|
|
{
|
|
"entropy": 5.739285612106324,
|
|
"epoch": 0.47565564104004043,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004985031138876299,
|
|
"loss": 5.6878,
|
|
"mean_token_accuracy": 0.1680801346898079,
|
|
"num_tokens": 9464231.0,
|
|
"step": 4235
|
|
},
|
|
{
|
|
"entropy": 5.764004802703857,
|
|
"epoch": 0.476217217947998,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004984984868781563,
|
|
"loss": 5.7067,
|
|
"mean_token_accuracy": 0.1760090947151184,
|
|
"num_tokens": 9475648.0,
|
|
"step": 4240
|
|
},
|
|
{
|
|
"entropy": 5.744698429107666,
|
|
"epoch": 0.47677879485595553,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004984938527524041,
|
|
"loss": 5.751,
|
|
"mean_token_accuracy": 0.16820831894874572,
|
|
"num_tokens": 9486594.0,
|
|
"step": 4245
|
|
},
|
|
{
|
|
"entropy": 5.672558355331421,
|
|
"epoch": 0.4773403717639131,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000498489211510521,
|
|
"loss": 5.6621,
|
|
"mean_token_accuracy": 0.17208858728408813,
|
|
"num_tokens": 9497085.0,
|
|
"step": 4250
|
|
},
|
|
{
|
|
"entropy": 5.784761142730713,
|
|
"epoch": 0.47790194867187064,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004984845631526547,
|
|
"loss": 5.7477,
|
|
"mean_token_accuracy": 0.16722307056188584,
|
|
"num_tokens": 9509765.0,
|
|
"step": 4255
|
|
},
|
|
{
|
|
"entropy": 5.725100564956665,
|
|
"epoch": 0.47846352557982813,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004984799076789534,
|
|
"loss": 5.5731,
|
|
"mean_token_accuracy": 0.16857376992702483,
|
|
"num_tokens": 9521341.0,
|
|
"step": 4260
|
|
},
|
|
{
|
|
"entropy": 5.630601024627685,
|
|
"epoch": 0.4790251024877857,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004984752450895649,
|
|
"loss": 5.6929,
|
|
"mean_token_accuracy": 0.1659396380186081,
|
|
"num_tokens": 9533196.0,
|
|
"step": 4265
|
|
},
|
|
{
|
|
"entropy": 5.8102864742279055,
|
|
"epoch": 0.47958667939574323,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.000498470575384638,
|
|
"loss": 5.8286,
|
|
"mean_token_accuracy": 0.15910447090864183,
|
|
"num_tokens": 9543687.0,
|
|
"step": 4270
|
|
},
|
|
{
|
|
"entropy": 5.903976631164551,
|
|
"epoch": 0.4801482563037008,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004984658985643214,
|
|
"loss": 5.7156,
|
|
"mean_token_accuracy": 0.16543746441602708,
|
|
"num_tokens": 9555320.0,
|
|
"step": 4275
|
|
},
|
|
{
|
|
"entropy": 5.636949110031128,
|
|
"epoch": 0.48070983321165833,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004984612146287638,
|
|
"loss": 5.6659,
|
|
"mean_token_accuracy": 0.16941267549991607,
|
|
"num_tokens": 9566347.0,
|
|
"step": 4280
|
|
},
|
|
{
|
|
"entropy": 5.636159801483155,
|
|
"epoch": 0.4812714101196159,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004984565235781147,
|
|
"loss": 5.6669,
|
|
"mean_token_accuracy": 0.16980277746915817,
|
|
"num_tokens": 9577111.0,
|
|
"step": 4285
|
|
},
|
|
{
|
|
"entropy": 5.761268234252929,
|
|
"epoch": 0.48183298702757343,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.000498451825412523,
|
|
"loss": 5.671,
|
|
"mean_token_accuracy": 0.16593389809131623,
|
|
"num_tokens": 9586612.0,
|
|
"step": 4290
|
|
},
|
|
{
|
|
"entropy": 5.774903297424316,
|
|
"epoch": 0.482394563935531,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004984471201321386,
|
|
"loss": 5.6786,
|
|
"mean_token_accuracy": 0.17062007635831833,
|
|
"num_tokens": 9597347.0,
|
|
"step": 4295
|
|
},
|
|
{
|
|
"entropy": 5.674345445632935,
|
|
"epoch": 0.48295614084348854,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004984424077371112,
|
|
"loss": 5.6524,
|
|
"mean_token_accuracy": 0.17706192433834075,
|
|
"num_tokens": 9608507.0,
|
|
"step": 4300
|
|
},
|
|
{
|
|
"entropy": 5.708226156234741,
|
|
"epoch": 0.4835177177514461,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004984376882275909,
|
|
"loss": 5.7082,
|
|
"mean_token_accuracy": 0.17436117678880692,
|
|
"num_tokens": 9619449.0,
|
|
"step": 4305
|
|
},
|
|
{
|
|
"entropy": 5.680789613723755,
|
|
"epoch": 0.4840792946594036,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004984329616037279,
|
|
"loss": 5.6346,
|
|
"mean_token_accuracy": 0.16903165727853775,
|
|
"num_tokens": 9630613.0,
|
|
"step": 4310
|
|
},
|
|
{
|
|
"entropy": 5.761481714248657,
|
|
"epoch": 0.48464087156736113,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004984282278656727,
|
|
"loss": 5.7086,
|
|
"mean_token_accuracy": 0.16750625967979432,
|
|
"num_tokens": 9642149.0,
|
|
"step": 4315
|
|
},
|
|
{
|
|
"entropy": 5.755221033096314,
|
|
"epoch": 0.4852024484753187,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004984234870135762,
|
|
"loss": 5.6496,
|
|
"mean_token_accuracy": 0.17484654635190963,
|
|
"num_tokens": 9652960.0,
|
|
"step": 4320
|
|
},
|
|
{
|
|
"entropy": 5.68124532699585,
|
|
"epoch": 0.48576402538327623,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004984187390475891,
|
|
"loss": 5.6417,
|
|
"mean_token_accuracy": 0.17295996993780136,
|
|
"num_tokens": 9662676.0,
|
|
"step": 4325
|
|
},
|
|
{
|
|
"entropy": 5.838757276535034,
|
|
"epoch": 0.4863256022912338,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004984139839678628,
|
|
"loss": 5.7493,
|
|
"mean_token_accuracy": 0.16618652939796447,
|
|
"num_tokens": 9674138.0,
|
|
"step": 4330
|
|
},
|
|
{
|
|
"entropy": 5.714073657989502,
|
|
"epoch": 0.48688717919919133,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004984092217745486,
|
|
"loss": 5.7113,
|
|
"mean_token_accuracy": 0.1709674835205078,
|
|
"num_tokens": 9685397.0,
|
|
"step": 4335
|
|
},
|
|
{
|
|
"entropy": 5.790579319000244,
|
|
"epoch": 0.4874487561071489,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004984044524677981,
|
|
"loss": 5.8231,
|
|
"mean_token_accuracy": 0.1605924040079117,
|
|
"num_tokens": 9697266.0,
|
|
"step": 4340
|
|
},
|
|
{
|
|
"entropy": 5.828333997726441,
|
|
"epoch": 0.48801033301510643,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004983996760477632,
|
|
"loss": 5.6552,
|
|
"mean_token_accuracy": 0.16677314341068267,
|
|
"num_tokens": 9707967.0,
|
|
"step": 4345
|
|
},
|
|
{
|
|
"entropy": 5.62044587135315,
|
|
"epoch": 0.488571909923064,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000498394892514596,
|
|
"loss": 5.6341,
|
|
"mean_token_accuracy": 0.17084338515996933,
|
|
"num_tokens": 9718162.0,
|
|
"step": 4350
|
|
},
|
|
{
|
|
"entropy": 5.717535734176636,
|
|
"epoch": 0.48913348683102154,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004983901018684486,
|
|
"loss": 5.6886,
|
|
"mean_token_accuracy": 0.16895658969879152,
|
|
"num_tokens": 9729439.0,
|
|
"step": 4355
|
|
},
|
|
{
|
|
"entropy": 5.775072956085205,
|
|
"epoch": 0.48969506373897903,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004983853041094739,
|
|
"loss": 5.7112,
|
|
"mean_token_accuracy": 0.16845377534627914,
|
|
"num_tokens": 9741383.0,
|
|
"step": 4360
|
|
},
|
|
{
|
|
"entropy": 5.712487268447876,
|
|
"epoch": 0.4902566406469366,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004983804992378243,
|
|
"loss": 5.7325,
|
|
"mean_token_accuracy": 0.17263987958431243,
|
|
"num_tokens": 9753050.0,
|
|
"step": 4365
|
|
},
|
|
{
|
|
"entropy": 5.681834554672241,
|
|
"epoch": 0.49081821755489413,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004983756872536532,
|
|
"loss": 5.6141,
|
|
"mean_token_accuracy": 0.1744478538632393,
|
|
"num_tokens": 9763715.0,
|
|
"step": 4370
|
|
},
|
|
{
|
|
"entropy": 5.699193477630615,
|
|
"epoch": 0.4913797944628517,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004983708681571134,
|
|
"loss": 5.5872,
|
|
"mean_token_accuracy": 0.1801524966955185,
|
|
"num_tokens": 9774145.0,
|
|
"step": 4375
|
|
},
|
|
{
|
|
"entropy": 5.711805200576782,
|
|
"epoch": 0.49194137137080923,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004983660419483586,
|
|
"loss": 5.6484,
|
|
"mean_token_accuracy": 0.1740181788802147,
|
|
"num_tokens": 9784703.0,
|
|
"step": 4380
|
|
},
|
|
{
|
|
"entropy": 5.7284644603729244,
|
|
"epoch": 0.4925029482787668,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004983612086275424,
|
|
"loss": 5.6657,
|
|
"mean_token_accuracy": 0.16666370034217834,
|
|
"num_tokens": 9795426.0,
|
|
"step": 4385
|
|
},
|
|
{
|
|
"entropy": 5.744356107711792,
|
|
"epoch": 0.49306452518672433,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004983563681948187,
|
|
"loss": 5.7488,
|
|
"mean_token_accuracy": 0.16563860327005386,
|
|
"num_tokens": 9806539.0,
|
|
"step": 4390
|
|
},
|
|
{
|
|
"entropy": 5.838592100143432,
|
|
"epoch": 0.4936261020946819,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004983515206503416,
|
|
"loss": 5.7354,
|
|
"mean_token_accuracy": 0.16389266550540924,
|
|
"num_tokens": 9816806.0,
|
|
"step": 4395
|
|
},
|
|
{
|
|
"entropy": 5.741393136978149,
|
|
"epoch": 0.49418767900263944,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004983466659942655,
|
|
"loss": 5.6239,
|
|
"mean_token_accuracy": 0.1763622909784317,
|
|
"num_tokens": 9828001.0,
|
|
"step": 4400
|
|
},
|
|
{
|
|
"entropy": 5.568348503112793,
|
|
"epoch": 0.49474925591059693,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004983418042267449,
|
|
"loss": 5.6675,
|
|
"mean_token_accuracy": 0.17209520637989045,
|
|
"num_tokens": 9838773.0,
|
|
"step": 4405
|
|
},
|
|
{
|
|
"entropy": 5.723768329620361,
|
|
"epoch": 0.4953108328185545,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004983369353479345,
|
|
"loss": 5.664,
|
|
"mean_token_accuracy": 0.17434099316596985,
|
|
"num_tokens": 9848680.0,
|
|
"step": 4410
|
|
},
|
|
{
|
|
"entropy": 5.700279903411865,
|
|
"epoch": 0.49587240972651203,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004983320593579895,
|
|
"loss": 5.6349,
|
|
"mean_token_accuracy": 0.16858525723218917,
|
|
"num_tokens": 9859168.0,
|
|
"step": 4415
|
|
},
|
|
{
|
|
"entropy": 5.66675705909729,
|
|
"epoch": 0.4964339866344696,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004983271762570653,
|
|
"loss": 5.671,
|
|
"mean_token_accuracy": 0.17040987610816954,
|
|
"num_tokens": 9869071.0,
|
|
"step": 4420
|
|
},
|
|
{
|
|
"entropy": 5.750021266937256,
|
|
"epoch": 0.49699556354242713,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000498322286045317,
|
|
"loss": 5.6767,
|
|
"mean_token_accuracy": 0.17082203477621077,
|
|
"num_tokens": 9880208.0,
|
|
"step": 4425
|
|
},
|
|
{
|
|
"entropy": 5.7331212043762205,
|
|
"epoch": 0.4975571404503847,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004983173887229006,
|
|
"loss": 5.7172,
|
|
"mean_token_accuracy": 0.17034917324781418,
|
|
"num_tokens": 9891192.0,
|
|
"step": 4430
|
|
},
|
|
{
|
|
"entropy": 5.790711212158203,
|
|
"epoch": 0.49811871735834223,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004983124842899719,
|
|
"loss": 5.7379,
|
|
"mean_token_accuracy": 0.16513569355010987,
|
|
"num_tokens": 9903038.0,
|
|
"step": 4435
|
|
},
|
|
{
|
|
"entropy": 5.830787420272827,
|
|
"epoch": 0.4986802942662998,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004983075727466871,
|
|
"loss": 5.7921,
|
|
"mean_token_accuracy": 0.1677357569336891,
|
|
"num_tokens": 9916104.0,
|
|
"step": 4440
|
|
},
|
|
{
|
|
"entropy": 5.6895956039428714,
|
|
"epoch": 0.49924187117425733,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004983026540932026,
|
|
"loss": 5.6103,
|
|
"mean_token_accuracy": 0.171831975877285,
|
|
"num_tokens": 9927094.0,
|
|
"step": 4445
|
|
},
|
|
{
|
|
"entropy": 5.784496068954468,
|
|
"epoch": 0.4998034480822149,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004982977283296749,
|
|
"loss": 5.8228,
|
|
"mean_token_accuracy": 0.1600668027997017,
|
|
"num_tokens": 9937964.0,
|
|
"step": 4450
|
|
},
|
|
{
|
|
"entropy": 5.8589826107025145,
|
|
"epoch": 0.5003650249901724,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000498292795456261,
|
|
"loss": 5.7841,
|
|
"mean_token_accuracy": 0.16068200916051864,
|
|
"num_tokens": 9949238.0,
|
|
"step": 4455
|
|
},
|
|
{
|
|
"entropy": 5.740886306762695,
|
|
"epoch": 0.50092660189813,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004982878554731178,
|
|
"loss": 5.6144,
|
|
"mean_token_accuracy": 0.17186491191387177,
|
|
"num_tokens": 9960125.0,
|
|
"step": 4460
|
|
},
|
|
{
|
|
"entropy": 5.579822969436646,
|
|
"epoch": 0.5014881788060875,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004982829083804028,
|
|
"loss": 5.6379,
|
|
"mean_token_accuracy": 0.1658797100186348,
|
|
"num_tokens": 9971130.0,
|
|
"step": 4465
|
|
},
|
|
{
|
|
"entropy": 5.683795070648193,
|
|
"epoch": 0.5020497557140451,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004982779541782733,
|
|
"loss": 5.5301,
|
|
"mean_token_accuracy": 0.17982134222984314,
|
|
"num_tokens": 9981516.0,
|
|
"step": 4470
|
|
},
|
|
{
|
|
"entropy": 5.691908359527588,
|
|
"epoch": 0.5026113326220026,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004982729928668872,
|
|
"loss": 5.765,
|
|
"mean_token_accuracy": 0.16426052749156952,
|
|
"num_tokens": 9992360.0,
|
|
"step": 4475
|
|
},
|
|
{
|
|
"entropy": 5.844257497787476,
|
|
"epoch": 0.5031729095299601,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004982680244464024,
|
|
"loss": 5.865,
|
|
"mean_token_accuracy": 0.16424636989831926,
|
|
"num_tokens": 10003410.0,
|
|
"step": 4480
|
|
},
|
|
{
|
|
"entropy": 5.831128740310669,
|
|
"epoch": 0.5037344864379176,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004982630489169771,
|
|
"loss": 5.6665,
|
|
"mean_token_accuracy": 0.1697389677166939,
|
|
"num_tokens": 10014974.0,
|
|
"step": 4485
|
|
},
|
|
{
|
|
"entropy": 5.730645370483399,
|
|
"epoch": 0.5042960633458752,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004982580662787697,
|
|
"loss": 5.7355,
|
|
"mean_token_accuracy": 0.1644341304898262,
|
|
"num_tokens": 10026702.0,
|
|
"step": 4490
|
|
},
|
|
{
|
|
"entropy": 5.7113964557647705,
|
|
"epoch": 0.5048576402538327,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004982530765319389,
|
|
"loss": 5.7192,
|
|
"mean_token_accuracy": 0.1672709807753563,
|
|
"num_tokens": 10039318.0,
|
|
"step": 4495
|
|
},
|
|
{
|
|
"entropy": 5.741805553436279,
|
|
"epoch": 0.5054192171617903,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004982480796766436,
|
|
"loss": 5.6632,
|
|
"mean_token_accuracy": 0.1635326474905014,
|
|
"num_tokens": 10049726.0,
|
|
"step": 4500
|
|
},
|
|
{
|
|
"entropy": 5.691263341903687,
|
|
"epoch": 0.5059807940697478,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004982430757130429,
|
|
"loss": 5.5585,
|
|
"mean_token_accuracy": 0.1718662425875664,
|
|
"num_tokens": 10059663.0,
|
|
"step": 4505
|
|
},
|
|
{
|
|
"entropy": 5.583151340484619,
|
|
"epoch": 0.5065423709777054,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004982380646412959,
|
|
"loss": 5.6013,
|
|
"mean_token_accuracy": 0.16774161756038666,
|
|
"num_tokens": 10071195.0,
|
|
"step": 4510
|
|
},
|
|
{
|
|
"entropy": 5.827329444885254,
|
|
"epoch": 0.5071039478856629,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004982330464615625,
|
|
"loss": 5.8071,
|
|
"mean_token_accuracy": 0.16533977538347244,
|
|
"num_tokens": 10082014.0,
|
|
"step": 4515
|
|
},
|
|
{
|
|
"entropy": 5.811189365386963,
|
|
"epoch": 0.5076655247936205,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004982280211740023,
|
|
"loss": 5.6143,
|
|
"mean_token_accuracy": 0.17575001269578933,
|
|
"num_tokens": 10093156.0,
|
|
"step": 4520
|
|
},
|
|
{
|
|
"entropy": 5.631749963760376,
|
|
"epoch": 0.508227101701578,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004982229887787753,
|
|
"loss": 5.7599,
|
|
"mean_token_accuracy": 0.1561910793185234,
|
|
"num_tokens": 10104993.0,
|
|
"step": 4525
|
|
},
|
|
{
|
|
"entropy": 5.7125547409057615,
|
|
"epoch": 0.5087886786095356,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004982179492760418,
|
|
"loss": 5.5668,
|
|
"mean_token_accuracy": 0.18113714456558228,
|
|
"num_tokens": 10114590.0,
|
|
"step": 4530
|
|
},
|
|
{
|
|
"entropy": 5.67285680770874,
|
|
"epoch": 0.5093502555174931,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004982129026659621,
|
|
"loss": 5.5738,
|
|
"mean_token_accuracy": 0.17499979734420776,
|
|
"num_tokens": 10125849.0,
|
|
"step": 4535
|
|
},
|
|
{
|
|
"entropy": 5.626177024841309,
|
|
"epoch": 0.5099118324254507,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004982078489486972,
|
|
"loss": 5.5941,
|
|
"mean_token_accuracy": 0.17779029458761214,
|
|
"num_tokens": 10135493.0,
|
|
"step": 4540
|
|
},
|
|
{
|
|
"entropy": 5.7630730152130125,
|
|
"epoch": 0.5104734093334082,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004982027881244076,
|
|
"loss": 5.7775,
|
|
"mean_token_accuracy": 0.1641564130783081,
|
|
"num_tokens": 10146987.0,
|
|
"step": 4545
|
|
},
|
|
{
|
|
"entropy": 5.765534067153931,
|
|
"epoch": 0.5110349862413658,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004981977201932549,
|
|
"loss": 5.7086,
|
|
"mean_token_accuracy": 0.17529913783073425,
|
|
"num_tokens": 10157823.0,
|
|
"step": 4550
|
|
},
|
|
{
|
|
"entropy": 5.639018440246582,
|
|
"epoch": 0.5115965631493233,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004981926451554001,
|
|
"loss": 5.6758,
|
|
"mean_token_accuracy": 0.17088306099176406,
|
|
"num_tokens": 10169305.0,
|
|
"step": 4555
|
|
},
|
|
{
|
|
"entropy": 5.824262237548828,
|
|
"epoch": 0.5121581400572809,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004981875630110048,
|
|
"loss": 5.7553,
|
|
"mean_token_accuracy": 0.1605099081993103,
|
|
"num_tokens": 10180346.0,
|
|
"step": 4560
|
|
},
|
|
{
|
|
"entropy": 5.753881549835205,
|
|
"epoch": 0.5127197169652384,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004981824737602311,
|
|
"loss": 5.6425,
|
|
"mean_token_accuracy": 0.17663276344537734,
|
|
"num_tokens": 10190870.0,
|
|
"step": 4565
|
|
},
|
|
{
|
|
"entropy": 5.745822525024414,
|
|
"epoch": 0.513281293873196,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004981773774032409,
|
|
"loss": 5.7113,
|
|
"mean_token_accuracy": 0.15780248045921325,
|
|
"num_tokens": 10202408.0,
|
|
"step": 4570
|
|
},
|
|
{
|
|
"entropy": 5.637575244903564,
|
|
"epoch": 0.5138428707811534,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004981722739401962,
|
|
"loss": 5.5405,
|
|
"mean_token_accuracy": 0.17590135782957078,
|
|
"num_tokens": 10213367.0,
|
|
"step": 4575
|
|
},
|
|
{
|
|
"entropy": 5.701434135437012,
|
|
"epoch": 0.514404447689111,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00049816716337126,
|
|
"loss": 5.6765,
|
|
"mean_token_accuracy": 0.16563864946365356,
|
|
"num_tokens": 10223865.0,
|
|
"step": 4580
|
|
},
|
|
{
|
|
"entropy": 5.599912309646607,
|
|
"epoch": 0.5149660245970685,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004981620456965946,
|
|
"loss": 5.4468,
|
|
"mean_token_accuracy": 0.17510706782341004,
|
|
"num_tokens": 10235268.0,
|
|
"step": 4585
|
|
},
|
|
{
|
|
"entropy": 5.6726030826568605,
|
|
"epoch": 0.5155276015050261,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004981569209163633,
|
|
"loss": 5.7124,
|
|
"mean_token_accuracy": 0.16576266586780547,
|
|
"num_tokens": 10247700.0,
|
|
"step": 4590
|
|
},
|
|
{
|
|
"entropy": 5.761053800582886,
|
|
"epoch": 0.5160891784129836,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004981517890307288,
|
|
"loss": 5.76,
|
|
"mean_token_accuracy": 0.16685858815908433,
|
|
"num_tokens": 10258553.0,
|
|
"step": 4595
|
|
},
|
|
{
|
|
"entropy": 5.758320093154907,
|
|
"epoch": 0.5166507553209412,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000498146650039855,
|
|
"loss": 5.6481,
|
|
"mean_token_accuracy": 0.17269993275403978,
|
|
"num_tokens": 10268496.0,
|
|
"step": 4600
|
|
},
|
|
{
|
|
"entropy": 5.774955701828003,
|
|
"epoch": 0.5172123322288987,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004981415039439054,
|
|
"loss": 5.7253,
|
|
"mean_token_accuracy": 0.16718546748161317,
|
|
"num_tokens": 10278803.0,
|
|
"step": 4605
|
|
},
|
|
{
|
|
"entropy": 5.711667108535766,
|
|
"epoch": 0.5177739091368563,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004981363507430436,
|
|
"loss": 5.5835,
|
|
"mean_token_accuracy": 0.1724689558148384,
|
|
"num_tokens": 10289805.0,
|
|
"step": 4610
|
|
},
|
|
{
|
|
"entropy": 5.688625192642212,
|
|
"epoch": 0.5183354860448138,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004981311904374339,
|
|
"loss": 5.7046,
|
|
"mean_token_accuracy": 0.174521566927433,
|
|
"num_tokens": 10300295.0,
|
|
"step": 4615
|
|
},
|
|
{
|
|
"entropy": 5.841267871856689,
|
|
"epoch": 0.5188970629527714,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004981260230272405,
|
|
"loss": 5.7889,
|
|
"mean_token_accuracy": 0.16799403876066207,
|
|
"num_tokens": 10312175.0,
|
|
"step": 4620
|
|
},
|
|
{
|
|
"entropy": 5.63864483833313,
|
|
"epoch": 0.5194586398607289,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004981208485126281,
|
|
"loss": 5.6779,
|
|
"mean_token_accuracy": 0.1660699799656868,
|
|
"num_tokens": 10322888.0,
|
|
"step": 4625
|
|
},
|
|
{
|
|
"entropy": 5.693124485015869,
|
|
"epoch": 0.5200202167686865,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004981156668937613,
|
|
"loss": 5.6516,
|
|
"mean_token_accuracy": 0.17714009433984756,
|
|
"num_tokens": 10333305.0,
|
|
"step": 4630
|
|
},
|
|
{
|
|
"entropy": 5.757165384292603,
|
|
"epoch": 0.520581793676644,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004981104781708051,
|
|
"loss": 5.6988,
|
|
"mean_token_accuracy": 0.16862452477216722,
|
|
"num_tokens": 10344190.0,
|
|
"step": 4635
|
|
},
|
|
{
|
|
"entropy": 5.797582530975342,
|
|
"epoch": 0.5211433705846016,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004981052823439247,
|
|
"loss": 5.7742,
|
|
"mean_token_accuracy": 0.16717695221304893,
|
|
"num_tokens": 10356271.0,
|
|
"step": 4640
|
|
},
|
|
{
|
|
"entropy": 5.836018705368042,
|
|
"epoch": 0.5217049474925591,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004981000794132858,
|
|
"loss": 5.8366,
|
|
"mean_token_accuracy": 0.15832895487546922,
|
|
"num_tokens": 10368756.0,
|
|
"step": 4645
|
|
},
|
|
{
|
|
"entropy": 5.814976835250855,
|
|
"epoch": 0.5222665244005167,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004980948693790536,
|
|
"loss": 5.6962,
|
|
"mean_token_accuracy": 0.1687784492969513,
|
|
"num_tokens": 10380029.0,
|
|
"step": 4650
|
|
},
|
|
{
|
|
"entropy": 5.691782474517822,
|
|
"epoch": 0.5228281013084742,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004980896522413943,
|
|
"loss": 5.6803,
|
|
"mean_token_accuracy": 0.16841885596513748,
|
|
"num_tokens": 10390358.0,
|
|
"step": 4655
|
|
},
|
|
{
|
|
"entropy": 5.686275625228882,
|
|
"epoch": 0.5233896782164318,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004980844280004739,
|
|
"loss": 5.6551,
|
|
"mean_token_accuracy": 0.1711376890540123,
|
|
"num_tokens": 10401331.0,
|
|
"step": 4660
|
|
},
|
|
{
|
|
"entropy": 5.753196573257446,
|
|
"epoch": 0.5239512551243893,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004980791966564589,
|
|
"loss": 5.6783,
|
|
"mean_token_accuracy": 0.16949976235628128,
|
|
"num_tokens": 10412755.0,
|
|
"step": 4665
|
|
},
|
|
{
|
|
"entropy": 5.692148733139038,
|
|
"epoch": 0.5245128320323468,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004980739582095158,
|
|
"loss": 5.6194,
|
|
"mean_token_accuracy": 0.17993575930595399,
|
|
"num_tokens": 10422698.0,
|
|
"step": 4670
|
|
},
|
|
{
|
|
"entropy": 5.739432430267334,
|
|
"epoch": 0.5250744089403043,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004980687126598111,
|
|
"loss": 5.753,
|
|
"mean_token_accuracy": 0.16443512141704558,
|
|
"num_tokens": 10434467.0,
|
|
"step": 4675
|
|
},
|
|
{
|
|
"entropy": 5.691123342514038,
|
|
"epoch": 0.5256359858482619,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004980634600075123,
|
|
"loss": 5.6647,
|
|
"mean_token_accuracy": 0.17190593779087066,
|
|
"num_tokens": 10446007.0,
|
|
"step": 4680
|
|
},
|
|
{
|
|
"entropy": 5.758034658432007,
|
|
"epoch": 0.5261975627562194,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004980582002527863,
|
|
"loss": 5.6857,
|
|
"mean_token_accuracy": 0.17210673540830612,
|
|
"num_tokens": 10457538.0,
|
|
"step": 4685
|
|
},
|
|
{
|
|
"entropy": 5.737921142578125,
|
|
"epoch": 0.526759139664177,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004980529333958008,
|
|
"loss": 5.6438,
|
|
"mean_token_accuracy": 0.17155391573905945,
|
|
"num_tokens": 10468389.0,
|
|
"step": 4690
|
|
},
|
|
{
|
|
"entropy": 5.64755654335022,
|
|
"epoch": 0.5273207165721345,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004980476594367233,
|
|
"loss": 5.6167,
|
|
"mean_token_accuracy": 0.166074176132679,
|
|
"num_tokens": 10479032.0,
|
|
"step": 4695
|
|
},
|
|
{
|
|
"entropy": 5.7380961894989015,
|
|
"epoch": 0.5278822934800921,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004980423783757219,
|
|
"loss": 5.6203,
|
|
"mean_token_accuracy": 0.1761274218559265,
|
|
"num_tokens": 10490505.0,
|
|
"step": 4700
|
|
},
|
|
{
|
|
"entropy": 5.777146339416504,
|
|
"epoch": 0.5284438703880496,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004980370902129646,
|
|
"loss": 5.6841,
|
|
"mean_token_accuracy": 0.17220447063446045,
|
|
"num_tokens": 10501382.0,
|
|
"step": 4705
|
|
},
|
|
{
|
|
"entropy": 5.7597027778625485,
|
|
"epoch": 0.5290054472960072,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00049803179494862,
|
|
"loss": 5.6519,
|
|
"mean_token_accuracy": 0.17078416049480438,
|
|
"num_tokens": 10512727.0,
|
|
"step": 4710
|
|
},
|
|
{
|
|
"entropy": 5.627700519561768,
|
|
"epoch": 0.5295670242039647,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004980264925828563,
|
|
"loss": 5.6379,
|
|
"mean_token_accuracy": 0.17503894567489625,
|
|
"num_tokens": 10523383.0,
|
|
"step": 4715
|
|
},
|
|
{
|
|
"entropy": 5.723991012573242,
|
|
"epoch": 0.5301286011119223,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004980211831158427,
|
|
"loss": 5.6443,
|
|
"mean_token_accuracy": 0.17036737948656083,
|
|
"num_tokens": 10534416.0,
|
|
"step": 4720
|
|
},
|
|
{
|
|
"entropy": 5.713537502288818,
|
|
"epoch": 0.5306901780198798,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004980158665477481,
|
|
"loss": 5.6192,
|
|
"mean_token_accuracy": 0.1723712608218193,
|
|
"num_tokens": 10544291.0,
|
|
"step": 4725
|
|
},
|
|
{
|
|
"entropy": 5.703956174850464,
|
|
"epoch": 0.5312517549278374,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004980105428787419,
|
|
"loss": 5.585,
|
|
"mean_token_accuracy": 0.1744757741689682,
|
|
"num_tokens": 10555291.0,
|
|
"step": 4730
|
|
},
|
|
{
|
|
"entropy": 5.739058351516723,
|
|
"epoch": 0.5318133318357949,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004980052121089934,
|
|
"loss": 5.6839,
|
|
"mean_token_accuracy": 0.1688266322016716,
|
|
"num_tokens": 10565812.0,
|
|
"step": 4735
|
|
},
|
|
{
|
|
"entropy": 5.644025564193726,
|
|
"epoch": 0.5323749087437525,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004979998742386725,
|
|
"loss": 5.6093,
|
|
"mean_token_accuracy": 0.17441638559103012,
|
|
"num_tokens": 10577351.0,
|
|
"step": 4740
|
|
},
|
|
{
|
|
"entropy": 5.761340379714966,
|
|
"epoch": 0.53293648565171,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004979945292679492,
|
|
"loss": 5.6919,
|
|
"mean_token_accuracy": 0.1682047963142395,
|
|
"num_tokens": 10589236.0,
|
|
"step": 4745
|
|
},
|
|
{
|
|
"entropy": 5.650798368453979,
|
|
"epoch": 0.5334980625596676,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004979891771969935,
|
|
"loss": 5.6363,
|
|
"mean_token_accuracy": 0.17235926836729049,
|
|
"num_tokens": 10599926.0,
|
|
"step": 4750
|
|
},
|
|
{
|
|
"entropy": 5.7528852939605715,
|
|
"epoch": 0.5340596394676251,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000497983818025976,
|
|
"loss": 5.7496,
|
|
"mean_token_accuracy": 0.16808155328035354,
|
|
"num_tokens": 10611495.0,
|
|
"step": 4755
|
|
},
|
|
{
|
|
"entropy": 5.749897480010986,
|
|
"epoch": 0.5346212163755827,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004979784517550671,
|
|
"loss": 5.7608,
|
|
"mean_token_accuracy": 0.1683972179889679,
|
|
"num_tokens": 10622455.0,
|
|
"step": 4760
|
|
},
|
|
{
|
|
"entropy": 5.70879487991333,
|
|
"epoch": 0.5351827932835401,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004979730783844379,
|
|
"loss": 5.6031,
|
|
"mean_token_accuracy": 0.17482960671186448,
|
|
"num_tokens": 10634255.0,
|
|
"step": 4765
|
|
},
|
|
{
|
|
"entropy": 5.737195301055908,
|
|
"epoch": 0.5357443701914977,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004979676979142595,
|
|
"loss": 5.7169,
|
|
"mean_token_accuracy": 0.1722305104136467,
|
|
"num_tokens": 10644816.0,
|
|
"step": 4770
|
|
},
|
|
{
|
|
"entropy": 5.732215309143067,
|
|
"epoch": 0.5363059470994552,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000497962310344703,
|
|
"loss": 5.6459,
|
|
"mean_token_accuracy": 0.17166779786348343,
|
|
"num_tokens": 10655449.0,
|
|
"step": 4775
|
|
},
|
|
{
|
|
"entropy": 5.718864822387696,
|
|
"epoch": 0.5368675240074128,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00049795691567594,
|
|
"loss": 5.6553,
|
|
"mean_token_accuracy": 0.16806258261203766,
|
|
"num_tokens": 10666343.0,
|
|
"step": 4780
|
|
},
|
|
{
|
|
"entropy": 5.72328372001648,
|
|
"epoch": 0.5374291009153703,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004979515139081426,
|
|
"loss": 5.7064,
|
|
"mean_token_accuracy": 0.16548898369073867,
|
|
"num_tokens": 10678511.0,
|
|
"step": 4785
|
|
},
|
|
{
|
|
"entropy": 5.665549087524414,
|
|
"epoch": 0.5379906778233279,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004979461050414822,
|
|
"loss": 5.6909,
|
|
"mean_token_accuracy": 0.17560625523328782,
|
|
"num_tokens": 10690005.0,
|
|
"step": 4790
|
|
},
|
|
{
|
|
"entropy": 5.679067897796631,
|
|
"epoch": 0.5385522547312854,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004979406890761315,
|
|
"loss": 5.681,
|
|
"mean_token_accuracy": 0.1686423435807228,
|
|
"num_tokens": 10701062.0,
|
|
"step": 4795
|
|
},
|
|
{
|
|
"entropy": 5.821629285812378,
|
|
"epoch": 0.539113831639243,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004979352660122629,
|
|
"loss": 5.5993,
|
|
"mean_token_accuracy": 0.1772200345993042,
|
|
"num_tokens": 10711986.0,
|
|
"step": 4800
|
|
},
|
|
{
|
|
"entropy": 5.744456338882446,
|
|
"epoch": 0.5396754085472005,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004979298358500488,
|
|
"loss": 5.7093,
|
|
"mean_token_accuracy": 0.16843186989426612,
|
|
"num_tokens": 10722509.0,
|
|
"step": 4805
|
|
},
|
|
{
|
|
"entropy": 5.742955589294434,
|
|
"epoch": 0.5402369854551581,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004979243985896624,
|
|
"loss": 5.6577,
|
|
"mean_token_accuracy": 0.16745564192533494,
|
|
"num_tokens": 10733755.0,
|
|
"step": 4810
|
|
},
|
|
{
|
|
"entropy": 5.69589319229126,
|
|
"epoch": 0.5407985623631156,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004979189542312765,
|
|
"loss": 5.688,
|
|
"mean_token_accuracy": 0.16879853308200837,
|
|
"num_tokens": 10744356.0,
|
|
"step": 4815
|
|
},
|
|
{
|
|
"entropy": 5.710256290435791,
|
|
"epoch": 0.5413601392710732,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.0004979135027750649,
|
|
"loss": 5.5928,
|
|
"mean_token_accuracy": 0.17196511775255202,
|
|
"num_tokens": 10756474.0,
|
|
"step": 4820
|
|
},
|
|
{
|
|
"entropy": 5.702636575698852,
|
|
"epoch": 0.5419217161790307,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004979080442212007,
|
|
"loss": 5.6718,
|
|
"mean_token_accuracy": 0.17200553864240647,
|
|
"num_tokens": 10767551.0,
|
|
"step": 4825
|
|
},
|
|
{
|
|
"entropy": 5.7792284965515135,
|
|
"epoch": 0.5424832930869883,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004979025785698581,
|
|
"loss": 5.7624,
|
|
"mean_token_accuracy": 0.16749392002820968,
|
|
"num_tokens": 10778524.0,
|
|
"step": 4830
|
|
},
|
|
{
|
|
"entropy": 5.679055833816529,
|
|
"epoch": 0.5430448699949458,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004978971058212108,
|
|
"loss": 5.6711,
|
|
"mean_token_accuracy": 0.17368635684251785,
|
|
"num_tokens": 10789798.0,
|
|
"step": 4835
|
|
},
|
|
{
|
|
"entropy": 5.730114889144898,
|
|
"epoch": 0.5436064469029034,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004978916259754331,
|
|
"loss": 5.6202,
|
|
"mean_token_accuracy": 0.1732513874769211,
|
|
"num_tokens": 10800500.0,
|
|
"step": 4840
|
|
},
|
|
{
|
|
"entropy": 5.761911201477051,
|
|
"epoch": 0.5441680238108609,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004978861390326998,
|
|
"loss": 5.6492,
|
|
"mean_token_accuracy": 0.17786261439323425,
|
|
"num_tokens": 10812047.0,
|
|
"step": 4845
|
|
},
|
|
{
|
|
"entropy": 5.655855131149292,
|
|
"epoch": 0.5447296007188185,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004978806449931854,
|
|
"loss": 5.6656,
|
|
"mean_token_accuracy": 0.1673392355442047,
|
|
"num_tokens": 10823272.0,
|
|
"step": 4850
|
|
},
|
|
{
|
|
"entropy": 5.585034036636353,
|
|
"epoch": 0.545291177626776,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004978751438570647,
|
|
"loss": 5.5368,
|
|
"mean_token_accuracy": 0.17088105529546738,
|
|
"num_tokens": 10834485.0,
|
|
"step": 4855
|
|
},
|
|
{
|
|
"entropy": 5.683445978164673,
|
|
"epoch": 0.5458527545347336,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004978696356245129,
|
|
"loss": 5.614,
|
|
"mean_token_accuracy": 0.16837672442197799,
|
|
"num_tokens": 10843547.0,
|
|
"step": 4860
|
|
},
|
|
{
|
|
"entropy": 5.719631719589233,
|
|
"epoch": 0.546414331442691,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004978641202957057,
|
|
"loss": 5.7497,
|
|
"mean_token_accuracy": 0.16445043236017226,
|
|
"num_tokens": 10855890.0,
|
|
"step": 4865
|
|
},
|
|
{
|
|
"entropy": 5.91353702545166,
|
|
"epoch": 0.5469759083506486,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004978585978708183,
|
|
"loss": 5.7949,
|
|
"mean_token_accuracy": 0.16377429962158202,
|
|
"num_tokens": 10868060.0,
|
|
"step": 4870
|
|
},
|
|
{
|
|
"entropy": 5.783869218826294,
|
|
"epoch": 0.5475374852586061,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004978530683500267,
|
|
"loss": 5.7163,
|
|
"mean_token_accuracy": 0.1670852780342102,
|
|
"num_tokens": 10879323.0,
|
|
"step": 4875
|
|
},
|
|
{
|
|
"entropy": 5.661490631103516,
|
|
"epoch": 0.5480990621665637,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004978475317335071,
|
|
"loss": 5.5598,
|
|
"mean_token_accuracy": 0.1758361741900444,
|
|
"num_tokens": 10890545.0,
|
|
"step": 4880
|
|
},
|
|
{
|
|
"entropy": 5.658501005172729,
|
|
"epoch": 0.5486606390745212,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004978419880214356,
|
|
"loss": 5.6612,
|
|
"mean_token_accuracy": 0.16851151436567308,
|
|
"num_tokens": 10900761.0,
|
|
"step": 4885
|
|
},
|
|
{
|
|
"entropy": 5.717454147338867,
|
|
"epoch": 0.5492222159824788,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004978364372139887,
|
|
"loss": 5.6471,
|
|
"mean_token_accuracy": 0.17221338003873826,
|
|
"num_tokens": 10911874.0,
|
|
"step": 4890
|
|
},
|
|
{
|
|
"entropy": 5.68519868850708,
|
|
"epoch": 0.5497837928904363,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004978308793113434,
|
|
"loss": 5.5666,
|
|
"mean_token_accuracy": 0.1797461986541748,
|
|
"num_tokens": 10922949.0,
|
|
"step": 4895
|
|
},
|
|
{
|
|
"entropy": 5.734178066253662,
|
|
"epoch": 0.5503453697983939,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004978253143136762,
|
|
"loss": 5.7637,
|
|
"mean_token_accuracy": 0.16003435403108596,
|
|
"num_tokens": 10935415.0,
|
|
"step": 4900
|
|
},
|
|
{
|
|
"entropy": 5.712212610244751,
|
|
"epoch": 0.5509069467063514,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004978197422211647,
|
|
"loss": 5.5989,
|
|
"mean_token_accuracy": 0.1794376477599144,
|
|
"num_tokens": 10946983.0,
|
|
"step": 4905
|
|
},
|
|
{
|
|
"entropy": 5.645990180969238,
|
|
"epoch": 0.551468523614309,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004978141630339863,
|
|
"loss": 5.6755,
|
|
"mean_token_accuracy": 0.16025410294532777,
|
|
"num_tokens": 10957884.0,
|
|
"step": 4910
|
|
},
|
|
{
|
|
"entropy": 5.732716608047485,
|
|
"epoch": 0.5520301005222665,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004978085767523184,
|
|
"loss": 5.6752,
|
|
"mean_token_accuracy": 0.17449066042900085,
|
|
"num_tokens": 10968518.0,
|
|
"step": 4915
|
|
},
|
|
{
|
|
"entropy": 5.708969449996948,
|
|
"epoch": 0.5525916774302241,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.000497802983376339,
|
|
"loss": 5.6864,
|
|
"mean_token_accuracy": 0.16695939302444457,
|
|
"num_tokens": 10979621.0,
|
|
"step": 4920
|
|
},
|
|
{
|
|
"entropy": 5.764673709869385,
|
|
"epoch": 0.5531532543381816,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.0004977973829062263,
|
|
"loss": 5.619,
|
|
"mean_token_accuracy": 0.1710394114255905,
|
|
"num_tokens": 10990158.0,
|
|
"step": 4925
|
|
},
|
|
{
|
|
"entropy": 5.673544979095459,
|
|
"epoch": 0.5537148312461392,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004977917753421585,
|
|
"loss": 5.7305,
|
|
"mean_token_accuracy": 0.16447483003139496,
|
|
"num_tokens": 11001732.0,
|
|
"step": 4930
|
|
},
|
|
{
|
|
"entropy": 5.843268728256225,
|
|
"epoch": 0.5542764081540967,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.000497786160684314,
|
|
"loss": 5.7428,
|
|
"mean_token_accuracy": 0.1634986564517021,
|
|
"num_tokens": 11013483.0,
|
|
"step": 4935
|
|
},
|
|
{
|
|
"entropy": 5.796664619445801,
|
|
"epoch": 0.5548379850620543,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004977805389328719,
|
|
"loss": 5.7391,
|
|
"mean_token_accuracy": 0.16766392290592194,
|
|
"num_tokens": 11025423.0,
|
|
"step": 4940
|
|
},
|
|
{
|
|
"entropy": 5.703360080718994,
|
|
"epoch": 0.5553995619700118,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.000497774910088011,
|
|
"loss": 5.5716,
|
|
"mean_token_accuracy": 0.17025255560874938,
|
|
"num_tokens": 11037041.0,
|
|
"step": 4945
|
|
},
|
|
{
|
|
"entropy": 5.723888826370239,
|
|
"epoch": 0.5559611388779694,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004977692741499106,
|
|
"loss": 5.7208,
|
|
"mean_token_accuracy": 0.16566304564476014,
|
|
"num_tokens": 11049206.0,
|
|
"step": 4950
|
|
},
|
|
{
|
|
"entropy": 5.74290828704834,
|
|
"epoch": 0.5565227157859269,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.00049776363111875,
|
|
"loss": 5.6884,
|
|
"mean_token_accuracy": 0.17315239310264588,
|
|
"num_tokens": 11060407.0,
|
|
"step": 4955
|
|
},
|
|
{
|
|
"entropy": 5.688162040710449,
|
|
"epoch": 0.5570842926938844,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004977579809947091,
|
|
"loss": 5.6215,
|
|
"mean_token_accuracy": 0.1681760311126709,
|
|
"num_tokens": 11071269.0,
|
|
"step": 4960
|
|
},
|
|
{
|
|
"entropy": 5.701694965362549,
|
|
"epoch": 0.5576458696018419,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004977523237779676,
|
|
"loss": 5.6215,
|
|
"mean_token_accuracy": 0.17521134316921233,
|
|
"num_tokens": 11082078.0,
|
|
"step": 4965
|
|
},
|
|
{
|
|
"entropy": 5.906933164596557,
|
|
"epoch": 0.5582074465097995,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004977466594687057,
|
|
"loss": 5.8526,
|
|
"mean_token_accuracy": 0.1614489182829857,
|
|
"num_tokens": 11094596.0,
|
|
"step": 4970
|
|
},
|
|
{
|
|
"entropy": 5.737157964706421,
|
|
"epoch": 0.558769023417757,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004977409880671039,
|
|
"loss": 5.7163,
|
|
"mean_token_accuracy": 0.16220240145921708,
|
|
"num_tokens": 11107705.0,
|
|
"step": 4975
|
|
},
|
|
{
|
|
"entropy": 5.703377056121826,
|
|
"epoch": 0.5593306003257146,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004977353095733427,
|
|
"loss": 5.622,
|
|
"mean_token_accuracy": 0.17367908358573914,
|
|
"num_tokens": 11118152.0,
|
|
"step": 4980
|
|
},
|
|
{
|
|
"entropy": 5.711778259277343,
|
|
"epoch": 0.5598921772336721,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004977296239876026,
|
|
"loss": 5.6611,
|
|
"mean_token_accuracy": 0.17005926817655564,
|
|
"num_tokens": 11129261.0,
|
|
"step": 4985
|
|
},
|
|
{
|
|
"entropy": 5.815555191040039,
|
|
"epoch": 0.5604537541416297,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000497723931310065,
|
|
"loss": 5.7661,
|
|
"mean_token_accuracy": 0.1613462135195732,
|
|
"num_tokens": 11142227.0,
|
|
"step": 4990
|
|
},
|
|
{
|
|
"entropy": 5.781078052520752,
|
|
"epoch": 0.5610153310495872,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004977182315409111,
|
|
"loss": 5.6717,
|
|
"mean_token_accuracy": 0.1686568960547447,
|
|
"num_tokens": 11154277.0,
|
|
"step": 4995
|
|
},
|
|
{
|
|
"entropy": 5.681065464019776,
|
|
"epoch": 0.5615769079575448,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004977125246803224,
|
|
"loss": 5.6813,
|
|
"mean_token_accuracy": 0.1690026491880417,
|
|
"num_tokens": 11164902.0,
|
|
"step": 5000
|
|
},
|
|
{
|
|
"entropy": 5.634833431243896,
|
|
"epoch": 0.5621384848655023,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004977068107284803,
|
|
"loss": 5.5775,
|
|
"mean_token_accuracy": 0.16621919125318527,
|
|
"num_tokens": 11176010.0,
|
|
"step": 5005
|
|
},
|
|
{
|
|
"entropy": 5.798631000518799,
|
|
"epoch": 0.5627000617734599,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004977010896855672,
|
|
"loss": 5.6064,
|
|
"mean_token_accuracy": 0.17368722558021546,
|
|
"num_tokens": 11187773.0,
|
|
"step": 5010
|
|
},
|
|
{
|
|
"entropy": 5.680552387237549,
|
|
"epoch": 0.5632616386814174,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004976953615517649,
|
|
"loss": 5.6802,
|
|
"mean_token_accuracy": 0.17477964162826537,
|
|
"num_tokens": 11198420.0,
|
|
"step": 5015
|
|
},
|
|
{
|
|
"entropy": 5.5892163753509525,
|
|
"epoch": 0.563823215589375,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.000497689626327256,
|
|
"loss": 5.4906,
|
|
"mean_token_accuracy": 0.17867352068424225,
|
|
"num_tokens": 11208553.0,
|
|
"step": 5020
|
|
},
|
|
{
|
|
"entropy": 5.70281949043274,
|
|
"epoch": 0.5643847924973325,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.000497683884012223,
|
|
"loss": 5.6524,
|
|
"mean_token_accuracy": 0.1714022785425186,
|
|
"num_tokens": 11219737.0,
|
|
"step": 5025
|
|
},
|
|
{
|
|
"entropy": 5.650163793563843,
|
|
"epoch": 0.5649463694052901,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004976781346068487,
|
|
"loss": 5.6602,
|
|
"mean_token_accuracy": 0.16621274948120118,
|
|
"num_tokens": 11230997.0,
|
|
"step": 5030
|
|
},
|
|
{
|
|
"entropy": 5.775289058685303,
|
|
"epoch": 0.5655079463132476,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004976723781113163,
|
|
"loss": 5.658,
|
|
"mean_token_accuracy": 0.17257270216941833,
|
|
"num_tokens": 11242338.0,
|
|
"step": 5035
|
|
},
|
|
{
|
|
"entropy": 5.775376224517823,
|
|
"epoch": 0.5660695232212052,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004976666145258089,
|
|
"loss": 5.6957,
|
|
"mean_token_accuracy": 0.17020781189203263,
|
|
"num_tokens": 11252671.0,
|
|
"step": 5040
|
|
},
|
|
{
|
|
"entropy": 5.555762767791748,
|
|
"epoch": 0.5666311001291627,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004976608438505103,
|
|
"loss": 5.5207,
|
|
"mean_token_accuracy": 0.17949869185686113,
|
|
"num_tokens": 11262721.0,
|
|
"step": 5045
|
|
},
|
|
{
|
|
"entropy": 5.700231218338013,
|
|
"epoch": 0.5671926770371203,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004976550660856041,
|
|
"loss": 5.7102,
|
|
"mean_token_accuracy": 0.16806024610996245,
|
|
"num_tokens": 11274074.0,
|
|
"step": 5050
|
|
},
|
|
{
|
|
"entropy": 5.789868927001953,
|
|
"epoch": 0.5677542539450777,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000497649281231274,
|
|
"loss": 5.6467,
|
|
"mean_token_accuracy": 0.1738978683948517,
|
|
"num_tokens": 11286051.0,
|
|
"step": 5055
|
|
},
|
|
{
|
|
"entropy": 5.801263046264649,
|
|
"epoch": 0.5683158308530353,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004976434892877046,
|
|
"loss": 5.7707,
|
|
"mean_token_accuracy": 0.16562236547470094,
|
|
"num_tokens": 11298841.0,
|
|
"step": 5060
|
|
},
|
|
{
|
|
"entropy": 5.760428190231323,
|
|
"epoch": 0.5688774077609928,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004976376902550802,
|
|
"loss": 5.7601,
|
|
"mean_token_accuracy": 0.1714622288942337,
|
|
"num_tokens": 11309898.0,
|
|
"step": 5065
|
|
},
|
|
{
|
|
"entropy": 5.770657253265381,
|
|
"epoch": 0.5694389846689504,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004976318841335854,
|
|
"loss": 5.7862,
|
|
"mean_token_accuracy": 0.16856923401355745,
|
|
"num_tokens": 11322163.0,
|
|
"step": 5070
|
|
},
|
|
{
|
|
"entropy": 5.779578781127929,
|
|
"epoch": 0.5700005615769079,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004976260709234049,
|
|
"loss": 5.7287,
|
|
"mean_token_accuracy": 0.165048947930336,
|
|
"num_tokens": 11333405.0,
|
|
"step": 5075
|
|
},
|
|
{
|
|
"entropy": 5.838383293151855,
|
|
"epoch": 0.5705621384848655,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000497620250624724,
|
|
"loss": 5.7896,
|
|
"mean_token_accuracy": 0.16699133217334747,
|
|
"num_tokens": 11345037.0,
|
|
"step": 5080
|
|
},
|
|
{
|
|
"entropy": 5.788431072235108,
|
|
"epoch": 0.571123715392823,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.000497614423237728,
|
|
"loss": 5.7095,
|
|
"mean_token_accuracy": 0.16881436556577684,
|
|
"num_tokens": 11356403.0,
|
|
"step": 5085
|
|
},
|
|
{
|
|
"entropy": 5.6463860988616945,
|
|
"epoch": 0.5716852923007806,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004976085887626026,
|
|
"loss": 5.6361,
|
|
"mean_token_accuracy": 0.1750362992286682,
|
|
"num_tokens": 11367913.0,
|
|
"step": 5090
|
|
},
|
|
{
|
|
"entropy": 5.6775815963745115,
|
|
"epoch": 0.5722468692087381,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004976027471995331,
|
|
"loss": 5.6461,
|
|
"mean_token_accuracy": 0.17520785629749297,
|
|
"num_tokens": 11378519.0,
|
|
"step": 5095
|
|
},
|
|
{
|
|
"entropy": 5.759826040267944,
|
|
"epoch": 0.5728084461166957,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.000497596898548706,
|
|
"loss": 5.6073,
|
|
"mean_token_accuracy": 0.17434988915920258,
|
|
"num_tokens": 11389530.0,
|
|
"step": 5100
|
|
},
|
|
{
|
|
"entropy": 5.59257664680481,
|
|
"epoch": 0.5733700230246532,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004975910428103072,
|
|
"loss": 5.5348,
|
|
"mean_token_accuracy": 0.17843396216630936,
|
|
"num_tokens": 11400468.0,
|
|
"step": 5105
|
|
},
|
|
{
|
|
"entropy": 5.500880479812622,
|
|
"epoch": 0.5739315999326108,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004975851799845233,
|
|
"loss": 5.544,
|
|
"mean_token_accuracy": 0.1740495353937149,
|
|
"num_tokens": 11411242.0,
|
|
"step": 5110
|
|
},
|
|
{
|
|
"entropy": 5.757795429229736,
|
|
"epoch": 0.5744931768405683,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.000497579310071541,
|
|
"loss": 5.6211,
|
|
"mean_token_accuracy": 0.17112922221422194,
|
|
"num_tokens": 11420909.0,
|
|
"step": 5115
|
|
},
|
|
{
|
|
"entropy": 5.599933767318726,
|
|
"epoch": 0.5750547537485259,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004975734330715471,
|
|
"loss": 5.5078,
|
|
"mean_token_accuracy": 0.17252909243106843,
|
|
"num_tokens": 11431791.0,
|
|
"step": 5120
|
|
},
|
|
{
|
|
"entropy": 5.802357625961304,
|
|
"epoch": 0.5756163306564834,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004975675489847287,
|
|
"loss": 5.7397,
|
|
"mean_token_accuracy": 0.16458898186683654,
|
|
"num_tokens": 11443056.0,
|
|
"step": 5125
|
|
},
|
|
{
|
|
"entropy": 5.745362329483032,
|
|
"epoch": 0.576177907564441,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004975616578112734,
|
|
"loss": 5.7048,
|
|
"mean_token_accuracy": 0.17184705585241317,
|
|
"num_tokens": 11453413.0,
|
|
"step": 5130
|
|
},
|
|
{
|
|
"entropy": 5.848228311538696,
|
|
"epoch": 0.5767394844723985,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004975557595513684,
|
|
"loss": 5.9266,
|
|
"mean_token_accuracy": 0.15690554976463317,
|
|
"num_tokens": 11465457.0,
|
|
"step": 5135
|
|
},
|
|
{
|
|
"entropy": 5.914571619033813,
|
|
"epoch": 0.5773010613803561,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004975498542052018,
|
|
"loss": 5.7023,
|
|
"mean_token_accuracy": 0.1729892149567604,
|
|
"num_tokens": 11476899.0,
|
|
"step": 5140
|
|
},
|
|
{
|
|
"entropy": 5.682943296432495,
|
|
"epoch": 0.5778626382883136,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004975439417729615,
|
|
"loss": 5.6611,
|
|
"mean_token_accuracy": 0.17298050820827485,
|
|
"num_tokens": 11488652.0,
|
|
"step": 5145
|
|
},
|
|
{
|
|
"entropy": 5.711069393157959,
|
|
"epoch": 0.5784242151962711,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004975380222548358,
|
|
"loss": 5.7013,
|
|
"mean_token_accuracy": 0.16747490912675858,
|
|
"num_tokens": 11499540.0,
|
|
"step": 5150
|
|
},
|
|
{
|
|
"entropy": 5.864771842956543,
|
|
"epoch": 0.5789857921042286,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004975320956510131,
|
|
"loss": 5.7277,
|
|
"mean_token_accuracy": 0.17383481860160827,
|
|
"num_tokens": 11511156.0,
|
|
"step": 5155
|
|
},
|
|
{
|
|
"entropy": 5.793862915039062,
|
|
"epoch": 0.5795473690121862,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004975261619616822,
|
|
"loss": 5.7969,
|
|
"mean_token_accuracy": 0.16044799983501434,
|
|
"num_tokens": 11523489.0,
|
|
"step": 5160
|
|
},
|
|
{
|
|
"entropy": 5.701024532318115,
|
|
"epoch": 0.5801089459201437,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004975202211870321,
|
|
"loss": 5.62,
|
|
"mean_token_accuracy": 0.16963277608156205,
|
|
"num_tokens": 11534497.0,
|
|
"step": 5165
|
|
},
|
|
{
|
|
"entropy": 5.849947166442871,
|
|
"epoch": 0.5806705228281013,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004975142733272518,
|
|
"loss": 5.7043,
|
|
"mean_token_accuracy": 0.16341470927000046,
|
|
"num_tokens": 11545585.0,
|
|
"step": 5170
|
|
},
|
|
{
|
|
"entropy": 5.594762372970581,
|
|
"epoch": 0.5812320997360588,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004975083183825306,
|
|
"loss": 5.553,
|
|
"mean_token_accuracy": 0.17195095419883727,
|
|
"num_tokens": 11556278.0,
|
|
"step": 5175
|
|
},
|
|
{
|
|
"entropy": 5.634889745712281,
|
|
"epoch": 0.5817936766440164,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004975023563530584,
|
|
"loss": 5.6343,
|
|
"mean_token_accuracy": 0.17483613938093184,
|
|
"num_tokens": 11568358.0,
|
|
"step": 5180
|
|
},
|
|
{
|
|
"entropy": 5.6792529106140135,
|
|
"epoch": 0.5823552535519739,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004974963872390249,
|
|
"loss": 5.6092,
|
|
"mean_token_accuracy": 0.17366641908884048,
|
|
"num_tokens": 11579777.0,
|
|
"step": 5185
|
|
},
|
|
{
|
|
"entropy": 5.678589296340943,
|
|
"epoch": 0.5829168304599315,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00049749041104062,
|
|
"loss": 5.6641,
|
|
"mean_token_accuracy": 0.1732245460152626,
|
|
"num_tokens": 11591479.0,
|
|
"step": 5190
|
|
},
|
|
{
|
|
"entropy": 5.741658306121826,
|
|
"epoch": 0.583478407367889,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004974844277580343,
|
|
"loss": 5.6151,
|
|
"mean_token_accuracy": 0.1689417690038681,
|
|
"num_tokens": 11601452.0,
|
|
"step": 5195
|
|
},
|
|
{
|
|
"entropy": 5.639203977584839,
|
|
"epoch": 0.5840399842758466,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004974784373914579,
|
|
"loss": 5.479,
|
|
"mean_token_accuracy": 0.1778860330581665,
|
|
"num_tokens": 11611661.0,
|
|
"step": 5200
|
|
},
|
|
{
|
|
"entropy": 5.637208557128906,
|
|
"epoch": 0.5846015611838041,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004974724399410818,
|
|
"loss": 5.662,
|
|
"mean_token_accuracy": 0.16758041232824325,
|
|
"num_tokens": 11622940.0,
|
|
"step": 5205
|
|
},
|
|
{
|
|
"entropy": 5.700867700576782,
|
|
"epoch": 0.5851631380917617,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004974664354070971,
|
|
"loss": 5.6744,
|
|
"mean_token_accuracy": 0.17014639526605607,
|
|
"num_tokens": 11634290.0,
|
|
"step": 5210
|
|
},
|
|
{
|
|
"entropy": 5.802171611785889,
|
|
"epoch": 0.5857247149997192,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004974604237896947,
|
|
"loss": 5.7173,
|
|
"mean_token_accuracy": 0.16413109749555588,
|
|
"num_tokens": 11645812.0,
|
|
"step": 5215
|
|
},
|
|
{
|
|
"entropy": 5.730967092514038,
|
|
"epoch": 0.5862862919076768,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004974544050890662,
|
|
"loss": 5.711,
|
|
"mean_token_accuracy": 0.16343657672405243,
|
|
"num_tokens": 11657520.0,
|
|
"step": 5220
|
|
},
|
|
{
|
|
"entropy": 5.6769603252410885,
|
|
"epoch": 0.5868478688156343,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.000497448379305403,
|
|
"loss": 5.567,
|
|
"mean_token_accuracy": 0.17653037905693053,
|
|
"num_tokens": 11666887.0,
|
|
"step": 5225
|
|
},
|
|
{
|
|
"entropy": 5.796042203903198,
|
|
"epoch": 0.5874094457235919,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004974423464388973,
|
|
"loss": 5.7423,
|
|
"mean_token_accuracy": 0.16953345388174057,
|
|
"num_tokens": 11677337.0,
|
|
"step": 5230
|
|
},
|
|
{
|
|
"entropy": 5.756515645980835,
|
|
"epoch": 0.5879710226315494,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.000497436306489741,
|
|
"loss": 5.6623,
|
|
"mean_token_accuracy": 0.17309503853321076,
|
|
"num_tokens": 11688203.0,
|
|
"step": 5235
|
|
},
|
|
{
|
|
"entropy": 5.702898836135864,
|
|
"epoch": 0.588532599539507,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004974302594581264,
|
|
"loss": 5.702,
|
|
"mean_token_accuracy": 0.16658136248588562,
|
|
"num_tokens": 11699727.0,
|
|
"step": 5240
|
|
},
|
|
{
|
|
"entropy": 5.732393646240235,
|
|
"epoch": 0.5890941764474645,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004974242053442461,
|
|
"loss": 5.7085,
|
|
"mean_token_accuracy": 0.16990188509225845,
|
|
"num_tokens": 11710956.0,
|
|
"step": 5245
|
|
},
|
|
{
|
|
"entropy": 5.743574380874634,
|
|
"epoch": 0.589655753355422,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004974181441482927,
|
|
"loss": 5.5437,
|
|
"mean_token_accuracy": 0.17698764950037002,
|
|
"num_tokens": 11721681.0,
|
|
"step": 5250
|
|
},
|
|
{
|
|
"entropy": 5.713166904449463,
|
|
"epoch": 0.5902173302633795,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004974120758704595,
|
|
"loss": 5.6719,
|
|
"mean_token_accuracy": 0.16816408634185792,
|
|
"num_tokens": 11731679.0,
|
|
"step": 5255
|
|
},
|
|
{
|
|
"entropy": 5.8048162937164305,
|
|
"epoch": 0.5907789071713371,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004974060005109394,
|
|
"loss": 5.8048,
|
|
"mean_token_accuracy": 0.1657121554017067,
|
|
"num_tokens": 11743953.0,
|
|
"step": 5260
|
|
},
|
|
{
|
|
"entropy": 5.6638165473937985,
|
|
"epoch": 0.5913404840792946,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.000497399918069926,
|
|
"loss": 5.5795,
|
|
"mean_token_accuracy": 0.17744518518447877,
|
|
"num_tokens": 11754091.0,
|
|
"step": 5265
|
|
},
|
|
{
|
|
"entropy": 5.639192199707031,
|
|
"epoch": 0.5919020609872522,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004973938285476131,
|
|
"loss": 5.6066,
|
|
"mean_token_accuracy": 0.1745060995221138,
|
|
"num_tokens": 11764771.0,
|
|
"step": 5270
|
|
},
|
|
{
|
|
"entropy": 5.734188079833984,
|
|
"epoch": 0.5924636378952097,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004973877319441943,
|
|
"loss": 5.6757,
|
|
"mean_token_accuracy": 0.16847294121980666,
|
|
"num_tokens": 11776287.0,
|
|
"step": 5275
|
|
},
|
|
{
|
|
"entropy": 5.747639417648315,
|
|
"epoch": 0.5930252148031673,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004973816282598639,
|
|
"loss": 5.6861,
|
|
"mean_token_accuracy": 0.16214133352041243,
|
|
"num_tokens": 11787142.0,
|
|
"step": 5280
|
|
},
|
|
{
|
|
"entropy": 5.72074031829834,
|
|
"epoch": 0.5935867917111248,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004973755174948162,
|
|
"loss": 5.6593,
|
|
"mean_token_accuracy": 0.16755084693431854,
|
|
"num_tokens": 11798966.0,
|
|
"step": 5285
|
|
},
|
|
{
|
|
"entropy": 5.771004104614258,
|
|
"epoch": 0.5941483686190824,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004973693996492458,
|
|
"loss": 5.7396,
|
|
"mean_token_accuracy": 0.16607423722743989,
|
|
"num_tokens": 11810529.0,
|
|
"step": 5290
|
|
},
|
|
{
|
|
"entropy": 5.65753321647644,
|
|
"epoch": 0.5947099455270399,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004973632747233475,
|
|
"loss": 5.584,
|
|
"mean_token_accuracy": 0.1776696190237999,
|
|
"num_tokens": 11821965.0,
|
|
"step": 5295
|
|
},
|
|
{
|
|
"entropy": 5.7572873592376705,
|
|
"epoch": 0.5952715224349975,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004973571427173163,
|
|
"loss": 5.7412,
|
|
"mean_token_accuracy": 0.1662243828177452,
|
|
"num_tokens": 11833936.0,
|
|
"step": 5300
|
|
},
|
|
{
|
|
"entropy": 5.793422603607178,
|
|
"epoch": 0.595833099342955,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004973510036313473,
|
|
"loss": 5.6572,
|
|
"mean_token_accuracy": 0.17151601612567902,
|
|
"num_tokens": 11845245.0,
|
|
"step": 5305
|
|
},
|
|
{
|
|
"entropy": 5.701361179351807,
|
|
"epoch": 0.5963946762509126,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004973448574656362,
|
|
"loss": 5.6248,
|
|
"mean_token_accuracy": 0.17118371576070784,
|
|
"num_tokens": 11856010.0,
|
|
"step": 5310
|
|
},
|
|
{
|
|
"entropy": 5.748444557189941,
|
|
"epoch": 0.5969562531588701,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004973387042203786,
|
|
"loss": 5.7801,
|
|
"mean_token_accuracy": 0.16333963572978974,
|
|
"num_tokens": 11866194.0,
|
|
"step": 5315
|
|
},
|
|
{
|
|
"entropy": 5.785281944274902,
|
|
"epoch": 0.5975178300668277,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004973325438957704,
|
|
"loss": 5.6244,
|
|
"mean_token_accuracy": 0.170792356133461,
|
|
"num_tokens": 11877224.0,
|
|
"step": 5320
|
|
},
|
|
{
|
|
"entropy": 5.662514305114746,
|
|
"epoch": 0.5980794069747852,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004973263764920079,
|
|
"loss": 5.5478,
|
|
"mean_token_accuracy": 0.17639639377593994,
|
|
"num_tokens": 11887410.0,
|
|
"step": 5325
|
|
},
|
|
{
|
|
"entropy": 5.627243566513061,
|
|
"epoch": 0.5986409838827428,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004973202020092871,
|
|
"loss": 5.7129,
|
|
"mean_token_accuracy": 0.1726754367351532,
|
|
"num_tokens": 11898816.0,
|
|
"step": 5330
|
|
},
|
|
{
|
|
"entropy": 5.750458002090454,
|
|
"epoch": 0.5992025607907003,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.000497314020447805,
|
|
"loss": 5.6623,
|
|
"mean_token_accuracy": 0.16915512531995774,
|
|
"num_tokens": 11909220.0,
|
|
"step": 5335
|
|
},
|
|
{
|
|
"entropy": 5.7871287822723385,
|
|
"epoch": 0.5997641376986579,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004973078318077583,
|
|
"loss": 5.6694,
|
|
"mean_token_accuracy": 0.16608534008264542,
|
|
"num_tokens": 11919584.0,
|
|
"step": 5340
|
|
},
|
|
{
|
|
"entropy": 5.664968776702881,
|
|
"epoch": 0.6003257146066153,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.000497301636089344,
|
|
"loss": 5.6782,
|
|
"mean_token_accuracy": 0.16855976581573487,
|
|
"num_tokens": 11929298.0,
|
|
"step": 5345
|
|
},
|
|
{
|
|
"entropy": 5.701796770095825,
|
|
"epoch": 0.6008872915145729,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004972954332927592,
|
|
"loss": 5.6465,
|
|
"mean_token_accuracy": 0.17208643406629562,
|
|
"num_tokens": 11939809.0,
|
|
"step": 5350
|
|
},
|
|
{
|
|
"entropy": 5.727794981002807,
|
|
"epoch": 0.6014488684225304,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004972892234182018,
|
|
"loss": 5.541,
|
|
"mean_token_accuracy": 0.1775716796517372,
|
|
"num_tokens": 11950292.0,
|
|
"step": 5355
|
|
},
|
|
{
|
|
"entropy": 5.610636901855469,
|
|
"epoch": 0.602010445330488,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004972830064658692,
|
|
"loss": 5.568,
|
|
"mean_token_accuracy": 0.17599292993545532,
|
|
"num_tokens": 11961774.0,
|
|
"step": 5360
|
|
},
|
|
{
|
|
"entropy": 5.764124965667724,
|
|
"epoch": 0.6025720222384455,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004972767824359596,
|
|
"loss": 5.6824,
|
|
"mean_token_accuracy": 0.16461727768182755,
|
|
"num_tokens": 11973351.0,
|
|
"step": 5365
|
|
},
|
|
{
|
|
"entropy": 5.664096021652222,
|
|
"epoch": 0.6031335991464031,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004972705513286709,
|
|
"loss": 5.5476,
|
|
"mean_token_accuracy": 0.178704696893692,
|
|
"num_tokens": 11984472.0,
|
|
"step": 5370
|
|
},
|
|
{
|
|
"entropy": 5.647040939331054,
|
|
"epoch": 0.6036951760543606,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004972643131442017,
|
|
"loss": 5.6518,
|
|
"mean_token_accuracy": 0.17527108937501906,
|
|
"num_tokens": 11994271.0,
|
|
"step": 5375
|
|
},
|
|
{
|
|
"entropy": 5.860633420944214,
|
|
"epoch": 0.6042567529623182,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004972580678827506,
|
|
"loss": 5.7576,
|
|
"mean_token_accuracy": 0.16238637864589692,
|
|
"num_tokens": 12007647.0,
|
|
"step": 5380
|
|
},
|
|
{
|
|
"entropy": 5.786860418319702,
|
|
"epoch": 0.6048183298702757,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004972518155445163,
|
|
"loss": 5.7092,
|
|
"mean_token_accuracy": 0.16535102427005768,
|
|
"num_tokens": 12020331.0,
|
|
"step": 5385
|
|
},
|
|
{
|
|
"entropy": 5.657439231872559,
|
|
"epoch": 0.6053799067782333,
|
|
"grad_norm": 2.59375,
|
|
"learning_rate": 0.0004972455561296982,
|
|
"loss": 5.7088,
|
|
"mean_token_accuracy": 0.16050323843955994,
|
|
"num_tokens": 12031616.0,
|
|
"step": 5390
|
|
},
|
|
{
|
|
"entropy": 5.811110305786133,
|
|
"epoch": 0.6059414836861908,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004972392896384952,
|
|
"loss": 5.6699,
|
|
"mean_token_accuracy": 0.1691645324230194,
|
|
"num_tokens": 12044107.0,
|
|
"step": 5395
|
|
},
|
|
{
|
|
"entropy": 5.748564100265503,
|
|
"epoch": 0.6065030605941484,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004972330160711071,
|
|
"loss": 5.6608,
|
|
"mean_token_accuracy": 0.17236095368862153,
|
|
"num_tokens": 12055747.0,
|
|
"step": 5400
|
|
},
|
|
{
|
|
"entropy": 5.757844591140747,
|
|
"epoch": 0.6070646375021059,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004972267354277336,
|
|
"loss": 5.6581,
|
|
"mean_token_accuracy": 0.17029646039009094,
|
|
"num_tokens": 12067849.0,
|
|
"step": 5405
|
|
},
|
|
{
|
|
"entropy": 5.722942781448364,
|
|
"epoch": 0.6076262144100635,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004972204477085746,
|
|
"loss": 5.6759,
|
|
"mean_token_accuracy": 0.16894526779651642,
|
|
"num_tokens": 12078534.0,
|
|
"step": 5410
|
|
},
|
|
{
|
|
"entropy": 5.657567405700684,
|
|
"epoch": 0.608187791318021,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004972141529138303,
|
|
"loss": 5.6041,
|
|
"mean_token_accuracy": 0.17073164135217667,
|
|
"num_tokens": 12089534.0,
|
|
"step": 5415
|
|
},
|
|
{
|
|
"entropy": 5.70810079574585,
|
|
"epoch": 0.6087493682259786,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004972078510437013,
|
|
"loss": 5.5066,
|
|
"mean_token_accuracy": 0.18743069767951964,
|
|
"num_tokens": 12099513.0,
|
|
"step": 5420
|
|
},
|
|
{
|
|
"entropy": 5.70379114151001,
|
|
"epoch": 0.6093109451339361,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004972015420983882,
|
|
"loss": 5.712,
|
|
"mean_token_accuracy": 0.17635903805494307,
|
|
"num_tokens": 12110106.0,
|
|
"step": 5425
|
|
},
|
|
{
|
|
"entropy": 5.705994033813477,
|
|
"epoch": 0.6098725220418937,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004971952260780915,
|
|
"loss": 5.604,
|
|
"mean_token_accuracy": 0.1767367586493492,
|
|
"num_tokens": 12121302.0,
|
|
"step": 5430
|
|
},
|
|
{
|
|
"entropy": 5.692618274688721,
|
|
"epoch": 0.6104340989498512,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.000497188902983013,
|
|
"loss": 5.6502,
|
|
"mean_token_accuracy": 0.17055889666080476,
|
|
"num_tokens": 12132879.0,
|
|
"step": 5435
|
|
},
|
|
{
|
|
"entropy": 5.642355585098267,
|
|
"epoch": 0.6109956758578087,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004971825728133535,
|
|
"loss": 5.5734,
|
|
"mean_token_accuracy": 0.17844846993684768,
|
|
"num_tokens": 12143597.0,
|
|
"step": 5440
|
|
},
|
|
{
|
|
"entropy": 5.729561996459961,
|
|
"epoch": 0.6115572527657662,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004971762355693146,
|
|
"loss": 5.6705,
|
|
"mean_token_accuracy": 0.17112083733081818,
|
|
"num_tokens": 12156036.0,
|
|
"step": 5445
|
|
},
|
|
{
|
|
"entropy": 5.774557399749756,
|
|
"epoch": 0.6121188296737238,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004971698912510983,
|
|
"loss": 5.6849,
|
|
"mean_token_accuracy": 0.1741700991988182,
|
|
"num_tokens": 12167305.0,
|
|
"step": 5450
|
|
},
|
|
{
|
|
"entropy": 5.718290376663208,
|
|
"epoch": 0.6126804065816813,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004971635398589066,
|
|
"loss": 5.6458,
|
|
"mean_token_accuracy": 0.17421892285346985,
|
|
"num_tokens": 12176772.0,
|
|
"step": 5455
|
|
},
|
|
{
|
|
"entropy": 5.706922245025635,
|
|
"epoch": 0.6132419834896389,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004971571813929415,
|
|
"loss": 5.6452,
|
|
"mean_token_accuracy": 0.17209067046642304,
|
|
"num_tokens": 12187852.0,
|
|
"step": 5460
|
|
},
|
|
{
|
|
"entropy": 5.790262699127197,
|
|
"epoch": 0.6138035603975964,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004971508158534056,
|
|
"loss": 5.7057,
|
|
"mean_token_accuracy": 0.17010461091995238,
|
|
"num_tokens": 12198574.0,
|
|
"step": 5465
|
|
},
|
|
{
|
|
"entropy": 5.622075748443604,
|
|
"epoch": 0.614365137305554,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004971444432405015,
|
|
"loss": 5.4607,
|
|
"mean_token_accuracy": 0.18198293149471284,
|
|
"num_tokens": 12209463.0,
|
|
"step": 5470
|
|
},
|
|
{
|
|
"entropy": 5.731533527374268,
|
|
"epoch": 0.6149267142135115,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004971380635544323,
|
|
"loss": 5.7366,
|
|
"mean_token_accuracy": 0.16922779083251954,
|
|
"num_tokens": 12220993.0,
|
|
"step": 5475
|
|
},
|
|
{
|
|
"entropy": 5.730971240997315,
|
|
"epoch": 0.6154882911214691,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004971316767954009,
|
|
"loss": 5.6102,
|
|
"mean_token_accuracy": 0.17507601529359818,
|
|
"num_tokens": 12232648.0,
|
|
"step": 5480
|
|
},
|
|
{
|
|
"entropy": 5.736530876159668,
|
|
"epoch": 0.6160498680294266,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004971252829636108,
|
|
"loss": 5.65,
|
|
"mean_token_accuracy": 0.17610020488500594,
|
|
"num_tokens": 12243931.0,
|
|
"step": 5485
|
|
},
|
|
{
|
|
"entropy": 5.787777423858643,
|
|
"epoch": 0.6166114449373842,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004971188820592656,
|
|
"loss": 5.6509,
|
|
"mean_token_accuracy": 0.17270122319459916,
|
|
"num_tokens": 12254821.0,
|
|
"step": 5490
|
|
},
|
|
{
|
|
"entropy": 5.583421754837036,
|
|
"epoch": 0.6171730218453417,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000497112474082569,
|
|
"loss": 5.6572,
|
|
"mean_token_accuracy": 0.17220793664455414,
|
|
"num_tokens": 12265440.0,
|
|
"step": 5495
|
|
},
|
|
{
|
|
"entropy": 5.727280187606811,
|
|
"epoch": 0.6177345987532993,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.000497106059033725,
|
|
"loss": 5.6329,
|
|
"mean_token_accuracy": 0.17365415692329406,
|
|
"num_tokens": 12276636.0,
|
|
"step": 5500
|
|
},
|
|
{
|
|
"entropy": 5.766627502441406,
|
|
"epoch": 0.6182961756612568,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004970996369129381,
|
|
"loss": 5.5133,
|
|
"mean_token_accuracy": 0.17947188764810562,
|
|
"num_tokens": 12287404.0,
|
|
"step": 5505
|
|
},
|
|
{
|
|
"entropy": 5.672186088562012,
|
|
"epoch": 0.6188577525692144,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004970932077204125,
|
|
"loss": 5.7397,
|
|
"mean_token_accuracy": 0.1642993837594986,
|
|
"num_tokens": 12299283.0,
|
|
"step": 5510
|
|
},
|
|
{
|
|
"entropy": 5.666852855682373,
|
|
"epoch": 0.6194193294771719,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.000497086771456353,
|
|
"loss": 5.6404,
|
|
"mean_token_accuracy": 0.16676075011491776,
|
|
"num_tokens": 12310281.0,
|
|
"step": 5515
|
|
},
|
|
{
|
|
"entropy": 5.804997062683105,
|
|
"epoch": 0.6199809063851295,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004970803281209646,
|
|
"loss": 5.6661,
|
|
"mean_token_accuracy": 0.17195305079221726,
|
|
"num_tokens": 12320839.0,
|
|
"step": 5520
|
|
},
|
|
{
|
|
"entropy": 5.676700162887573,
|
|
"epoch": 0.620542483293087,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004970738777144524,
|
|
"loss": 5.6211,
|
|
"mean_token_accuracy": 0.17245084047317505,
|
|
"num_tokens": 12332845.0,
|
|
"step": 5525
|
|
},
|
|
{
|
|
"entropy": 5.554922676086425,
|
|
"epoch": 0.6211040602010446,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004970674202370218,
|
|
"loss": 5.5204,
|
|
"mean_token_accuracy": 0.1806936517357826,
|
|
"num_tokens": 12343327.0,
|
|
"step": 5530
|
|
},
|
|
{
|
|
"entropy": 5.72095046043396,
|
|
"epoch": 0.621665637109002,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004970609556888785,
|
|
"loss": 5.6445,
|
|
"mean_token_accuracy": 0.17047364860773087,
|
|
"num_tokens": 12353224.0,
|
|
"step": 5535
|
|
},
|
|
{
|
|
"entropy": 5.682199335098266,
|
|
"epoch": 0.6222272140169596,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004970544840702282,
|
|
"loss": 5.5634,
|
|
"mean_token_accuracy": 0.17255714684724807,
|
|
"num_tokens": 12363981.0,
|
|
"step": 5540
|
|
},
|
|
{
|
|
"entropy": 5.584892797470093,
|
|
"epoch": 0.6227887909249171,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004970480053812771,
|
|
"loss": 5.5853,
|
|
"mean_token_accuracy": 0.1800747200846672,
|
|
"num_tokens": 12374769.0,
|
|
"step": 5545
|
|
},
|
|
{
|
|
"entropy": 5.814059019088745,
|
|
"epoch": 0.6233503678328747,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004970415196222312,
|
|
"loss": 5.8038,
|
|
"mean_token_accuracy": 0.16921334117650985,
|
|
"num_tokens": 12387247.0,
|
|
"step": 5550
|
|
},
|
|
{
|
|
"entropy": 5.793169641494751,
|
|
"epoch": 0.6239119447408322,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004970350267932973,
|
|
"loss": 5.6566,
|
|
"mean_token_accuracy": 0.17780971080064772,
|
|
"num_tokens": 12398347.0,
|
|
"step": 5555
|
|
},
|
|
{
|
|
"entropy": 5.531301593780517,
|
|
"epoch": 0.6244735216487898,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.000497028526894682,
|
|
"loss": 5.5502,
|
|
"mean_token_accuracy": 0.17427618205547332,
|
|
"num_tokens": 12409763.0,
|
|
"step": 5560
|
|
},
|
|
{
|
|
"entropy": 5.740422582626342,
|
|
"epoch": 0.6250350985567473,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004970220199265923,
|
|
"loss": 5.6429,
|
|
"mean_token_accuracy": 0.17239355593919753,
|
|
"num_tokens": 12420658.0,
|
|
"step": 5565
|
|
},
|
|
{
|
|
"entropy": 5.830804109573364,
|
|
"epoch": 0.6255966754647049,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004970155058892354,
|
|
"loss": 5.7334,
|
|
"mean_token_accuracy": 0.16390733271837235,
|
|
"num_tokens": 12433959.0,
|
|
"step": 5570
|
|
},
|
|
{
|
|
"entropy": 5.738416051864624,
|
|
"epoch": 0.6261582523726624,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004970089847828187,
|
|
"loss": 5.7218,
|
|
"mean_token_accuracy": 0.16629742383956908,
|
|
"num_tokens": 12444756.0,
|
|
"step": 5575
|
|
},
|
|
{
|
|
"entropy": 5.73380479812622,
|
|
"epoch": 0.62671982928062,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004970024566075497,
|
|
"loss": 5.6352,
|
|
"mean_token_accuracy": 0.17590337246656418,
|
|
"num_tokens": 12456114.0,
|
|
"step": 5580
|
|
},
|
|
{
|
|
"entropy": 5.736455249786377,
|
|
"epoch": 0.6272814061885775,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004969959213636365,
|
|
"loss": 5.6718,
|
|
"mean_token_accuracy": 0.17344282269477845,
|
|
"num_tokens": 12466927.0,
|
|
"step": 5585
|
|
},
|
|
{
|
|
"entropy": 5.701116847991943,
|
|
"epoch": 0.6278429830965351,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004969893790512871,
|
|
"loss": 5.723,
|
|
"mean_token_accuracy": 0.16070540398359298,
|
|
"num_tokens": 12477834.0,
|
|
"step": 5590
|
|
},
|
|
{
|
|
"entropy": 5.750099849700928,
|
|
"epoch": 0.6284045600044926,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004969828296707097,
|
|
"loss": 5.6247,
|
|
"mean_token_accuracy": 0.1745440736413002,
|
|
"num_tokens": 12488219.0,
|
|
"step": 5595
|
|
},
|
|
{
|
|
"entropy": 5.8359832763671875,
|
|
"epoch": 0.6289661369124502,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004969762732221129,
|
|
"loss": 5.7385,
|
|
"mean_token_accuracy": 0.17294516116380693,
|
|
"num_tokens": 12498947.0,
|
|
"step": 5600
|
|
},
|
|
{
|
|
"entropy": 5.66269965171814,
|
|
"epoch": 0.6295277138204077,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004969697097057054,
|
|
"loss": 5.6343,
|
|
"mean_token_accuracy": 0.1720503583550453,
|
|
"num_tokens": 12510142.0,
|
|
"step": 5605
|
|
},
|
|
{
|
|
"entropy": 5.79200439453125,
|
|
"epoch": 0.6300892907283653,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004969631391216964,
|
|
"loss": 5.6472,
|
|
"mean_token_accuracy": 0.1704936742782593,
|
|
"num_tokens": 12521350.0,
|
|
"step": 5610
|
|
},
|
|
{
|
|
"entropy": 5.521368408203125,
|
|
"epoch": 0.6306508676363228,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004969565614702948,
|
|
"loss": 5.4855,
|
|
"mean_token_accuracy": 0.1774906650185585,
|
|
"num_tokens": 12532579.0,
|
|
"step": 5615
|
|
},
|
|
{
|
|
"entropy": 5.734045362472534,
|
|
"epoch": 0.6312124445442804,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004969499767517104,
|
|
"loss": 5.6044,
|
|
"mean_token_accuracy": 0.17279993891716003,
|
|
"num_tokens": 12542885.0,
|
|
"step": 5620
|
|
},
|
|
{
|
|
"entropy": 5.80007586479187,
|
|
"epoch": 0.6317740214522379,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004969433849661525,
|
|
"loss": 5.7554,
|
|
"mean_token_accuracy": 0.1622144266963005,
|
|
"num_tokens": 12554881.0,
|
|
"step": 5625
|
|
},
|
|
{
|
|
"entropy": 5.737228202819824,
|
|
"epoch": 0.6323355983601955,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004969367861138313,
|
|
"loss": 5.6993,
|
|
"mean_token_accuracy": 0.16859257966279984,
|
|
"num_tokens": 12564626.0,
|
|
"step": 5630
|
|
},
|
|
{
|
|
"entropy": 5.745629692077637,
|
|
"epoch": 0.6328971752681529,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004969301801949565,
|
|
"loss": 5.5502,
|
|
"mean_token_accuracy": 0.17777176648378373,
|
|
"num_tokens": 12576180.0,
|
|
"step": 5635
|
|
},
|
|
{
|
|
"entropy": 5.658581924438477,
|
|
"epoch": 0.6334587521761105,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000496923567209739,
|
|
"loss": 5.6427,
|
|
"mean_token_accuracy": 0.16927312016487123,
|
|
"num_tokens": 12587487.0,
|
|
"step": 5640
|
|
},
|
|
{
|
|
"entropy": 5.788752126693725,
|
|
"epoch": 0.634020329084068,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004969169471583889,
|
|
"loss": 5.7908,
|
|
"mean_token_accuracy": 0.16504471004009247,
|
|
"num_tokens": 12598268.0,
|
|
"step": 5645
|
|
},
|
|
{
|
|
"entropy": 5.807561635971069,
|
|
"epoch": 0.6345819059920256,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004969103200411171,
|
|
"loss": 5.6686,
|
|
"mean_token_accuracy": 0.1691132053732872,
|
|
"num_tokens": 12609287.0,
|
|
"step": 5650
|
|
},
|
|
{
|
|
"entropy": 5.669478559494019,
|
|
"epoch": 0.6351434828999831,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004969036858581346,
|
|
"loss": 5.5726,
|
|
"mean_token_accuracy": 0.17225826978683473,
|
|
"num_tokens": 12620317.0,
|
|
"step": 5655
|
|
},
|
|
{
|
|
"entropy": 5.70239109992981,
|
|
"epoch": 0.6357050598079407,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004968970446096527,
|
|
"loss": 5.6395,
|
|
"mean_token_accuracy": 0.17853050231933593,
|
|
"num_tokens": 12631420.0,
|
|
"step": 5660
|
|
},
|
|
{
|
|
"entropy": 5.694774198532104,
|
|
"epoch": 0.6362666367158982,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.000496890396295883,
|
|
"loss": 5.5798,
|
|
"mean_token_accuracy": 0.1807517871260643,
|
|
"num_tokens": 12641319.0,
|
|
"step": 5665
|
|
},
|
|
{
|
|
"entropy": 5.760483884811402,
|
|
"epoch": 0.6368282136238558,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004968837409170368,
|
|
"loss": 5.6805,
|
|
"mean_token_accuracy": 0.1660526767373085,
|
|
"num_tokens": 12651662.0,
|
|
"step": 5670
|
|
},
|
|
{
|
|
"entropy": 5.768562316894531,
|
|
"epoch": 0.6373897905318133,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004968770784733263,
|
|
"loss": 5.7284,
|
|
"mean_token_accuracy": 0.1657192662358284,
|
|
"num_tokens": 12663488.0,
|
|
"step": 5675
|
|
},
|
|
{
|
|
"entropy": 5.687350702285767,
|
|
"epoch": 0.6379513674397709,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004968704089649636,
|
|
"loss": 5.6362,
|
|
"mean_token_accuracy": 0.1720639333128929,
|
|
"num_tokens": 12675848.0,
|
|
"step": 5680
|
|
},
|
|
{
|
|
"entropy": 5.735997581481934,
|
|
"epoch": 0.6385129443477284,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004968637323921611,
|
|
"loss": 5.6178,
|
|
"mean_token_accuracy": 0.1734489381313324,
|
|
"num_tokens": 12686541.0,
|
|
"step": 5685
|
|
},
|
|
{
|
|
"entropy": 5.710645627975464,
|
|
"epoch": 0.639074521255686,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004968570487551312,
|
|
"loss": 5.6499,
|
|
"mean_token_accuracy": 0.17180876433849335,
|
|
"num_tokens": 12698001.0,
|
|
"step": 5690
|
|
},
|
|
{
|
|
"entropy": 5.720677328109741,
|
|
"epoch": 0.6396360981636435,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004968503580540869,
|
|
"loss": 5.6477,
|
|
"mean_token_accuracy": 0.1650005429983139,
|
|
"num_tokens": 12709069.0,
|
|
"step": 5695
|
|
},
|
|
{
|
|
"entropy": 5.759660863876343,
|
|
"epoch": 0.6401976750716011,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004968436602892411,
|
|
"loss": 5.6475,
|
|
"mean_token_accuracy": 0.16808155924081802,
|
|
"num_tokens": 12719916.0,
|
|
"step": 5700
|
|
},
|
|
{
|
|
"entropy": 5.743867063522339,
|
|
"epoch": 0.6407592519795586,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004968369554608071,
|
|
"loss": 5.7584,
|
|
"mean_token_accuracy": 0.16313536167144777,
|
|
"num_tokens": 12732079.0,
|
|
"step": 5705
|
|
},
|
|
{
|
|
"entropy": 5.852132272720337,
|
|
"epoch": 0.6413208288875162,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004968302435689985,
|
|
"loss": 5.7338,
|
|
"mean_token_accuracy": 0.16560664474964143,
|
|
"num_tokens": 12742708.0,
|
|
"step": 5710
|
|
},
|
|
{
|
|
"entropy": 5.792535924911499,
|
|
"epoch": 0.6418824057954737,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.0004968235246140288,
|
|
"loss": 5.6781,
|
|
"mean_token_accuracy": 0.1690981075167656,
|
|
"num_tokens": 12753952.0,
|
|
"step": 5715
|
|
},
|
|
{
|
|
"entropy": 5.677698373794556,
|
|
"epoch": 0.6424439827034313,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004968167985961121,
|
|
"loss": 5.6078,
|
|
"mean_token_accuracy": 0.17256635576486587,
|
|
"num_tokens": 12765226.0,
|
|
"step": 5720
|
|
},
|
|
{
|
|
"entropy": 5.602059602737427,
|
|
"epoch": 0.6430055596113888,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004968100655154625,
|
|
"loss": 5.5366,
|
|
"mean_token_accuracy": 0.17826073467731476,
|
|
"num_tokens": 12776455.0,
|
|
"step": 5725
|
|
},
|
|
{
|
|
"entropy": 5.672917366027832,
|
|
"epoch": 0.6435671365193463,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004968033253722943,
|
|
"loss": 5.5564,
|
|
"mean_token_accuracy": 0.17404053062200547,
|
|
"num_tokens": 12787054.0,
|
|
"step": 5730
|
|
},
|
|
{
|
|
"entropy": 5.719582462310791,
|
|
"epoch": 0.6441287134273038,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004967965781668223,
|
|
"loss": 5.6866,
|
|
"mean_token_accuracy": 0.170250004529953,
|
|
"num_tokens": 12798223.0,
|
|
"step": 5735
|
|
},
|
|
{
|
|
"entropy": 5.715972423553467,
|
|
"epoch": 0.6446902903352614,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004967898238992613,
|
|
"loss": 5.5732,
|
|
"mean_token_accuracy": 0.17579154819250106,
|
|
"num_tokens": 12809388.0,
|
|
"step": 5740
|
|
},
|
|
{
|
|
"entropy": 5.686679077148438,
|
|
"epoch": 0.6452518672432189,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004967830625698262,
|
|
"loss": 5.6769,
|
|
"mean_token_accuracy": 0.17444596737623214,
|
|
"num_tokens": 12820116.0,
|
|
"step": 5745
|
|
},
|
|
{
|
|
"entropy": 5.6671665668487545,
|
|
"epoch": 0.6458134441511765,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004967762941787323,
|
|
"loss": 5.5967,
|
|
"mean_token_accuracy": 0.17919077277183532,
|
|
"num_tokens": 12831590.0,
|
|
"step": 5750
|
|
},
|
|
{
|
|
"entropy": 5.747342586517334,
|
|
"epoch": 0.646375021059134,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004967695187261952,
|
|
"loss": 5.7564,
|
|
"mean_token_accuracy": 0.16459435522556304,
|
|
"num_tokens": 12843510.0,
|
|
"step": 5755
|
|
},
|
|
{
|
|
"entropy": 5.7117125511169435,
|
|
"epoch": 0.6469365979670916,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004967627362124306,
|
|
"loss": 5.6307,
|
|
"mean_token_accuracy": 0.1705598846077919,
|
|
"num_tokens": 12854907.0,
|
|
"step": 5760
|
|
},
|
|
{
|
|
"entropy": 5.658813190460205,
|
|
"epoch": 0.6474981748750491,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004967559466376546,
|
|
"loss": 5.5959,
|
|
"mean_token_accuracy": 0.1710912510752678,
|
|
"num_tokens": 12865753.0,
|
|
"step": 5765
|
|
},
|
|
{
|
|
"entropy": 5.6811473846435545,
|
|
"epoch": 0.6480597517830067,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.0004967491500020831,
|
|
"loss": 5.5035,
|
|
"mean_token_accuracy": 0.17676436007022858,
|
|
"num_tokens": 12877116.0,
|
|
"step": 5770
|
|
},
|
|
{
|
|
"entropy": 5.5508228778839115,
|
|
"epoch": 0.6486213286909642,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004967423463059328,
|
|
"loss": 5.4959,
|
|
"mean_token_accuracy": 0.17579397261142732,
|
|
"num_tokens": 12887685.0,
|
|
"step": 5775
|
|
},
|
|
{
|
|
"entropy": 5.713850355148315,
|
|
"epoch": 0.6491829055989218,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004967355355494201,
|
|
"loss": 5.6584,
|
|
"mean_token_accuracy": 0.1692407101392746,
|
|
"num_tokens": 12898519.0,
|
|
"step": 5780
|
|
},
|
|
{
|
|
"entropy": 5.742898797988891,
|
|
"epoch": 0.6497444825068793,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.000496728717732762,
|
|
"loss": 5.586,
|
|
"mean_token_accuracy": 0.17314111143350602,
|
|
"num_tokens": 12908400.0,
|
|
"step": 5785
|
|
},
|
|
{
|
|
"entropy": 5.602768039703369,
|
|
"epoch": 0.6503060594148369,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004967218928561755,
|
|
"loss": 5.56,
|
|
"mean_token_accuracy": 0.17106268554925919,
|
|
"num_tokens": 12919159.0,
|
|
"step": 5790
|
|
},
|
|
{
|
|
"entropy": 5.631039237976074,
|
|
"epoch": 0.6508676363227944,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004967150609198779,
|
|
"loss": 5.523,
|
|
"mean_token_accuracy": 0.1793055310845375,
|
|
"num_tokens": 12929838.0,
|
|
"step": 5795
|
|
},
|
|
{
|
|
"entropy": 5.732568550109863,
|
|
"epoch": 0.651429213230752,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004967082219240869,
|
|
"loss": 5.6285,
|
|
"mean_token_accuracy": 0.1695741206407547,
|
|
"num_tokens": 12939976.0,
|
|
"step": 5800
|
|
},
|
|
{
|
|
"entropy": 5.758488702774048,
|
|
"epoch": 0.6519907901387095,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004967013758690199,
|
|
"loss": 5.6404,
|
|
"mean_token_accuracy": 0.1749062106013298,
|
|
"num_tokens": 12950493.0,
|
|
"step": 5805
|
|
},
|
|
{
|
|
"entropy": 5.654942989349365,
|
|
"epoch": 0.6525523670466671,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004966945227548953,
|
|
"loss": 5.6052,
|
|
"mean_token_accuracy": 0.17201246023178102,
|
|
"num_tokens": 12961267.0,
|
|
"step": 5810
|
|
},
|
|
{
|
|
"entropy": 5.66741909980774,
|
|
"epoch": 0.6531139439546246,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004966876625819309,
|
|
"loss": 5.6493,
|
|
"mean_token_accuracy": 0.16587674468755723,
|
|
"num_tokens": 12972720.0,
|
|
"step": 5815
|
|
},
|
|
{
|
|
"entropy": 5.8147331237792965,
|
|
"epoch": 0.6536755208625822,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004966807953503456,
|
|
"loss": 5.7294,
|
|
"mean_token_accuracy": 0.16530007719993592,
|
|
"num_tokens": 12984025.0,
|
|
"step": 5820
|
|
},
|
|
{
|
|
"entropy": 5.751352405548095,
|
|
"epoch": 0.6542370977705396,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004966739210603578,
|
|
"loss": 5.6064,
|
|
"mean_token_accuracy": 0.17820507735013963,
|
|
"num_tokens": 12994422.0,
|
|
"step": 5825
|
|
},
|
|
{
|
|
"entropy": 5.753329849243164,
|
|
"epoch": 0.6547986746784972,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004966670397121862,
|
|
"loss": 5.7651,
|
|
"mean_token_accuracy": 0.1632770538330078,
|
|
"num_tokens": 13005040.0,
|
|
"step": 5830
|
|
},
|
|
{
|
|
"entropy": 5.65441665649414,
|
|
"epoch": 0.6553602515864547,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004966601513060502,
|
|
"loss": 5.5259,
|
|
"mean_token_accuracy": 0.17237963378429413,
|
|
"num_tokens": 13015720.0,
|
|
"step": 5835
|
|
},
|
|
{
|
|
"entropy": 5.689071893692017,
|
|
"epoch": 0.6559218284944123,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000496653255842169,
|
|
"loss": 5.4925,
|
|
"mean_token_accuracy": 0.17613681703805922,
|
|
"num_tokens": 13026269.0,
|
|
"step": 5840
|
|
},
|
|
{
|
|
"entropy": 5.638681697845459,
|
|
"epoch": 0.6564834054023698,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004966463533207621,
|
|
"loss": 5.6659,
|
|
"mean_token_accuracy": 0.16914643421769143,
|
|
"num_tokens": 13037102.0,
|
|
"step": 5845
|
|
},
|
|
{
|
|
"entropy": 5.634537220001221,
|
|
"epoch": 0.6570449823103274,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004966394437420493,
|
|
"loss": 5.5301,
|
|
"mean_token_accuracy": 0.1786402016878128,
|
|
"num_tokens": 13047149.0,
|
|
"step": 5850
|
|
},
|
|
{
|
|
"entropy": 5.6855401515960695,
|
|
"epoch": 0.6576065592182849,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004966325271062508,
|
|
"loss": 5.5626,
|
|
"mean_token_accuracy": 0.17522660344839097,
|
|
"num_tokens": 13058196.0,
|
|
"step": 5855
|
|
},
|
|
{
|
|
"entropy": 5.617813682556152,
|
|
"epoch": 0.6581681361262425,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004966256034135866,
|
|
"loss": 5.575,
|
|
"mean_token_accuracy": 0.17152782380580903,
|
|
"num_tokens": 13067897.0,
|
|
"step": 5860
|
|
},
|
|
{
|
|
"entropy": 5.704078626632691,
|
|
"epoch": 0.6587297130342,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004966186726642772,
|
|
"loss": 5.6755,
|
|
"mean_token_accuracy": 0.1717715382575989,
|
|
"num_tokens": 13079720.0,
|
|
"step": 5865
|
|
},
|
|
{
|
|
"entropy": 5.634116268157959,
|
|
"epoch": 0.6592912899421576,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004966117348585434,
|
|
"loss": 5.5258,
|
|
"mean_token_accuracy": 0.167197148501873,
|
|
"num_tokens": 13090995.0,
|
|
"step": 5870
|
|
},
|
|
{
|
|
"entropy": 5.605711269378662,
|
|
"epoch": 0.6598528668501151,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004966047899966059,
|
|
"loss": 5.572,
|
|
"mean_token_accuracy": 0.17753074020147325,
|
|
"num_tokens": 13101945.0,
|
|
"step": 5875
|
|
},
|
|
{
|
|
"entropy": 5.679044914245606,
|
|
"epoch": 0.6604144437580727,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.000496597838078686,
|
|
"loss": 5.5155,
|
|
"mean_token_accuracy": 0.1752203419804573,
|
|
"num_tokens": 13112869.0,
|
|
"step": 5880
|
|
},
|
|
{
|
|
"entropy": 5.710168552398682,
|
|
"epoch": 0.6609760206660302,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.000496590879105005,
|
|
"loss": 5.6074,
|
|
"mean_token_accuracy": 0.16586030423641204,
|
|
"num_tokens": 13123242.0,
|
|
"step": 5885
|
|
},
|
|
{
|
|
"entropy": 5.776198816299439,
|
|
"epoch": 0.6615375975739878,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004965839130757845,
|
|
"loss": 5.7182,
|
|
"mean_token_accuracy": 0.1584482118487358,
|
|
"num_tokens": 13133981.0,
|
|
"step": 5890
|
|
},
|
|
{
|
|
"entropy": 5.67058835029602,
|
|
"epoch": 0.6620991744819453,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004965769399912462,
|
|
"loss": 5.6804,
|
|
"mean_token_accuracy": 0.16925962790846824,
|
|
"num_tokens": 13144696.0,
|
|
"step": 5895
|
|
},
|
|
{
|
|
"entropy": 5.770441007614136,
|
|
"epoch": 0.6626607513899029,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004965699598516122,
|
|
"loss": 5.7219,
|
|
"mean_token_accuracy": 0.17378196567296983,
|
|
"num_tokens": 13156674.0,
|
|
"step": 5900
|
|
},
|
|
{
|
|
"entropy": 5.704008340835571,
|
|
"epoch": 0.6632223282978604,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004965629726571047,
|
|
"loss": 5.5632,
|
|
"mean_token_accuracy": 0.17381847351789476,
|
|
"num_tokens": 13167757.0,
|
|
"step": 5905
|
|
},
|
|
{
|
|
"entropy": 5.748448419570923,
|
|
"epoch": 0.663783905205818,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004965559784079463,
|
|
"loss": 5.6488,
|
|
"mean_token_accuracy": 0.16911055743694306,
|
|
"num_tokens": 13177701.0,
|
|
"step": 5910
|
|
},
|
|
{
|
|
"entropy": 5.785614109039306,
|
|
"epoch": 0.6643454821137755,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004965489771043596,
|
|
"loss": 5.6658,
|
|
"mean_token_accuracy": 0.16642796993255615,
|
|
"num_tokens": 13189840.0,
|
|
"step": 5915
|
|
},
|
|
{
|
|
"entropy": 5.5934004306793215,
|
|
"epoch": 0.664907059021733,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004965419687465676,
|
|
"loss": 5.4739,
|
|
"mean_token_accuracy": 0.17768412381410598,
|
|
"num_tokens": 13200206.0,
|
|
"step": 5920
|
|
},
|
|
{
|
|
"entropy": 5.586026859283447,
|
|
"epoch": 0.6654686359296905,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004965349533347934,
|
|
"loss": 5.588,
|
|
"mean_token_accuracy": 0.17564436197280883,
|
|
"num_tokens": 13211474.0,
|
|
"step": 5925
|
|
},
|
|
{
|
|
"entropy": 5.733428430557251,
|
|
"epoch": 0.6660302128376481,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004965279308692602,
|
|
"loss": 5.6484,
|
|
"mean_token_accuracy": 0.1843220919370651,
|
|
"num_tokens": 13223337.0,
|
|
"step": 5930
|
|
},
|
|
{
|
|
"entropy": 5.801119422912597,
|
|
"epoch": 0.6665917897456056,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004965209013501919,
|
|
"loss": 5.7285,
|
|
"mean_token_accuracy": 0.17110735177993774,
|
|
"num_tokens": 13234977.0,
|
|
"step": 5935
|
|
},
|
|
{
|
|
"entropy": 5.70616512298584,
|
|
"epoch": 0.6671533666535632,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004965138647778122,
|
|
"loss": 5.6768,
|
|
"mean_token_accuracy": 0.17690228521823884,
|
|
"num_tokens": 13245315.0,
|
|
"step": 5940
|
|
},
|
|
{
|
|
"entropy": 5.685105466842652,
|
|
"epoch": 0.6677149435615207,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.000496506821152345,
|
|
"loss": 5.5582,
|
|
"mean_token_accuracy": 0.1749824121594429,
|
|
"num_tokens": 13255829.0,
|
|
"step": 5945
|
|
},
|
|
{
|
|
"entropy": 5.66689453125,
|
|
"epoch": 0.6682765204694783,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004964997704740147,
|
|
"loss": 5.6256,
|
|
"mean_token_accuracy": 0.170874160528183,
|
|
"num_tokens": 13266964.0,
|
|
"step": 5950
|
|
},
|
|
{
|
|
"entropy": 5.796186685562134,
|
|
"epoch": 0.6688380973774358,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000496492712743046,
|
|
"loss": 5.6614,
|
|
"mean_token_accuracy": 0.1689567595720291,
|
|
"num_tokens": 13279416.0,
|
|
"step": 5955
|
|
},
|
|
{
|
|
"entropy": 5.723680639266968,
|
|
"epoch": 0.6693996742853934,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004964856479596632,
|
|
"loss": 5.6919,
|
|
"mean_token_accuracy": 0.1676722764968872,
|
|
"num_tokens": 13290633.0,
|
|
"step": 5960
|
|
},
|
|
{
|
|
"entropy": 5.7067337989807125,
|
|
"epoch": 0.6699612511933509,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004964785761240915,
|
|
"loss": 5.5734,
|
|
"mean_token_accuracy": 0.17108363509178162,
|
|
"num_tokens": 13302236.0,
|
|
"step": 5965
|
|
},
|
|
{
|
|
"entropy": 5.7176580905914305,
|
|
"epoch": 0.6705228281013085,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004964714972365562,
|
|
"loss": 5.6724,
|
|
"mean_token_accuracy": 0.17194082885980605,
|
|
"num_tokens": 13315356.0,
|
|
"step": 5970
|
|
},
|
|
{
|
|
"entropy": 5.516757583618164,
|
|
"epoch": 0.671084405009266,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004964644112972824,
|
|
"loss": 5.5327,
|
|
"mean_token_accuracy": 0.1755928486585617,
|
|
"num_tokens": 13326037.0,
|
|
"step": 5975
|
|
},
|
|
{
|
|
"entropy": 5.632549905776978,
|
|
"epoch": 0.6716459819172236,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004964573183064959,
|
|
"loss": 5.5914,
|
|
"mean_token_accuracy": 0.17360655069351197,
|
|
"num_tokens": 13336278.0,
|
|
"step": 5980
|
|
},
|
|
{
|
|
"entropy": 5.736466360092163,
|
|
"epoch": 0.6722075588251811,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004964502182644225,
|
|
"loss": 5.7065,
|
|
"mean_token_accuracy": 0.17162298858165742,
|
|
"num_tokens": 13348147.0,
|
|
"step": 5985
|
|
},
|
|
{
|
|
"entropy": 5.71574764251709,
|
|
"epoch": 0.6727691357331387,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004964431111712883,
|
|
"loss": 5.6413,
|
|
"mean_token_accuracy": 0.17189154624938965,
|
|
"num_tokens": 13360181.0,
|
|
"step": 5990
|
|
},
|
|
{
|
|
"entropy": 5.774587678909302,
|
|
"epoch": 0.6733307126410962,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004964359970273195,
|
|
"loss": 5.7266,
|
|
"mean_token_accuracy": 0.16633295267820358,
|
|
"num_tokens": 13372258.0,
|
|
"step": 5995
|
|
},
|
|
{
|
|
"entropy": 5.71021146774292,
|
|
"epoch": 0.6738922895490538,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004964288758327426,
|
|
"loss": 5.6378,
|
|
"mean_token_accuracy": 0.16402822285890578,
|
|
"num_tokens": 13384332.0,
|
|
"step": 6000
|
|
},
|
|
{
|
|
"epoch": 0.6738922895490538,
|
|
"eval_entropy": 5.5617586172269675,
|
|
"eval_loss": 5.65424108505249,
|
|
"eval_mean_token_accuracy": 0.17736698931749925,
|
|
"eval_num_tokens": 13384332.0,
|
|
"eval_runtime": 23.6897,
|
|
"eval_samples_per_second": 1309.134,
|
|
"eval_steps_per_second": 163.658,
|
|
"step": 6000
|
|
},
|
|
{
|
|
"entropy": 5.7171698093414305,
|
|
"epoch": 0.6744538664570113,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004964217475877846,
|
|
"loss": 5.6314,
|
|
"mean_token_accuracy": 0.16942399442195893,
|
|
"num_tokens": 13396345.0,
|
|
"step": 6005
|
|
},
|
|
{
|
|
"entropy": 5.591657829284668,
|
|
"epoch": 0.6750154433649689,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.000496414612292672,
|
|
"loss": 5.4644,
|
|
"mean_token_accuracy": 0.17689456790685654,
|
|
"num_tokens": 13407325.0,
|
|
"step": 6010
|
|
},
|
|
{
|
|
"entropy": 5.689947080612183,
|
|
"epoch": 0.6755770202729264,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004964074699476325,
|
|
"loss": 5.6021,
|
|
"mean_token_accuracy": 0.17259112149477004,
|
|
"num_tokens": 13417476.0,
|
|
"step": 6015
|
|
},
|
|
{
|
|
"entropy": 5.656712484359741,
|
|
"epoch": 0.6761385971808839,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004964003205528933,
|
|
"loss": 5.6096,
|
|
"mean_token_accuracy": 0.1726845309138298,
|
|
"num_tokens": 13428792.0,
|
|
"step": 6020
|
|
},
|
|
{
|
|
"entropy": 5.700129842758178,
|
|
"epoch": 0.6767001740888414,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004963931641086819,
|
|
"loss": 5.6682,
|
|
"mean_token_accuracy": 0.1713205248117447,
|
|
"num_tokens": 13440043.0,
|
|
"step": 6025
|
|
},
|
|
{
|
|
"entropy": 5.7401378631591795,
|
|
"epoch": 0.677261750996799,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004963860006152262,
|
|
"loss": 5.6353,
|
|
"mean_token_accuracy": 0.17090512961149215,
|
|
"num_tokens": 13451637.0,
|
|
"step": 6030
|
|
},
|
|
{
|
|
"entropy": 5.824400568008423,
|
|
"epoch": 0.6778233279047565,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004963788300727546,
|
|
"loss": 5.6046,
|
|
"mean_token_accuracy": 0.17313029766082763,
|
|
"num_tokens": 13463205.0,
|
|
"step": 6035
|
|
},
|
|
{
|
|
"entropy": 5.660120248794556,
|
|
"epoch": 0.6783849048127141,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004963716524814951,
|
|
"loss": 5.6569,
|
|
"mean_token_accuracy": 0.17166511565446854,
|
|
"num_tokens": 13474201.0,
|
|
"step": 6040
|
|
},
|
|
{
|
|
"entropy": 5.62141170501709,
|
|
"epoch": 0.6789464817206716,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004963644678416763,
|
|
"loss": 5.5434,
|
|
"mean_token_accuracy": 0.17378048449754716,
|
|
"num_tokens": 13485439.0,
|
|
"step": 6045
|
|
},
|
|
{
|
|
"entropy": 5.730491065979004,
|
|
"epoch": 0.6795080586286292,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000496357276153527,
|
|
"loss": 5.7492,
|
|
"mean_token_accuracy": 0.16852689236402513,
|
|
"num_tokens": 13497257.0,
|
|
"step": 6050
|
|
},
|
|
{
|
|
"entropy": 5.730785655975342,
|
|
"epoch": 0.6800696355365867,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004963500774172763,
|
|
"loss": 5.5958,
|
|
"mean_token_accuracy": 0.17269592732191086,
|
|
"num_tokens": 13508689.0,
|
|
"step": 6055
|
|
},
|
|
{
|
|
"entropy": 5.698699808120727,
|
|
"epoch": 0.6806312124445443,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000496342871633153,
|
|
"loss": 5.5497,
|
|
"mean_token_accuracy": 0.18048133552074433,
|
|
"num_tokens": 13519392.0,
|
|
"step": 6060
|
|
},
|
|
{
|
|
"entropy": 5.62058744430542,
|
|
"epoch": 0.6811927893525018,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004963356588013871,
|
|
"loss": 5.605,
|
|
"mean_token_accuracy": 0.1779961258172989,
|
|
"num_tokens": 13530503.0,
|
|
"step": 6065
|
|
},
|
|
{
|
|
"entropy": 5.707237100601196,
|
|
"epoch": 0.6817543662604594,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004963284389222078,
|
|
"loss": 5.674,
|
|
"mean_token_accuracy": 0.1740332290530205,
|
|
"num_tokens": 13541668.0,
|
|
"step": 6070
|
|
},
|
|
{
|
|
"entropy": 5.699452447891235,
|
|
"epoch": 0.6823159431684169,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004963212119958453,
|
|
"loss": 5.5067,
|
|
"mean_token_accuracy": 0.1787132978439331,
|
|
"num_tokens": 13552692.0,
|
|
"step": 6075
|
|
},
|
|
{
|
|
"entropy": 5.577724456787109,
|
|
"epoch": 0.6828775200763745,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004963139780225295,
|
|
"loss": 5.6074,
|
|
"mean_token_accuracy": 0.1706698417663574,
|
|
"num_tokens": 13563813.0,
|
|
"step": 6080
|
|
},
|
|
{
|
|
"entropy": 5.6306346416473385,
|
|
"epoch": 0.683439096984332,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004963067370024909,
|
|
"loss": 5.5537,
|
|
"mean_token_accuracy": 0.17718004286289216,
|
|
"num_tokens": 13573818.0,
|
|
"step": 6085
|
|
},
|
|
{
|
|
"entropy": 5.760622024536133,
|
|
"epoch": 0.6840006738922896,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004962994889359598,
|
|
"loss": 5.6771,
|
|
"mean_token_accuracy": 0.16787791550159453,
|
|
"num_tokens": 13585416.0,
|
|
"step": 6090
|
|
},
|
|
{
|
|
"entropy": 5.631905651092529,
|
|
"epoch": 0.6845622508002471,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004962922338231673,
|
|
"loss": 5.5727,
|
|
"mean_token_accuracy": 0.17555365860462188,
|
|
"num_tokens": 13596645.0,
|
|
"step": 6095
|
|
},
|
|
{
|
|
"entropy": 5.68451681137085,
|
|
"epoch": 0.6851238277082047,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004962849716643441,
|
|
"loss": 5.5218,
|
|
"mean_token_accuracy": 0.177066071331501,
|
|
"num_tokens": 13607206.0,
|
|
"step": 6100
|
|
},
|
|
{
|
|
"entropy": 5.7633359909057615,
|
|
"epoch": 0.6856854046161622,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004962777024597216,
|
|
"loss": 5.7316,
|
|
"mean_token_accuracy": 0.16855940222740173,
|
|
"num_tokens": 13619418.0,
|
|
"step": 6105
|
|
},
|
|
{
|
|
"entropy": 5.643983459472656,
|
|
"epoch": 0.6862469815241198,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004962704262095314,
|
|
"loss": 5.5224,
|
|
"mean_token_accuracy": 0.17984748929738997,
|
|
"num_tokens": 13630098.0,
|
|
"step": 6110
|
|
},
|
|
{
|
|
"entropy": 5.625010013580322,
|
|
"epoch": 0.6868085584320772,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004962631429140048,
|
|
"loss": 5.6491,
|
|
"mean_token_accuracy": 0.17171284705400466,
|
|
"num_tokens": 13641401.0,
|
|
"step": 6115
|
|
},
|
|
{
|
|
"entropy": 5.739342164993286,
|
|
"epoch": 0.6873701353400348,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.000496255852573374,
|
|
"loss": 5.6075,
|
|
"mean_token_accuracy": 0.1670444905757904,
|
|
"num_tokens": 13653099.0,
|
|
"step": 6120
|
|
},
|
|
{
|
|
"entropy": 5.795357084274292,
|
|
"epoch": 0.6879317122479923,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004962485551878711,
|
|
"loss": 5.622,
|
|
"mean_token_accuracy": 0.16640905737876893,
|
|
"num_tokens": 13665381.0,
|
|
"step": 6125
|
|
},
|
|
{
|
|
"entropy": 5.661467742919922,
|
|
"epoch": 0.6884932891559499,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004962412507577283,
|
|
"loss": 5.6346,
|
|
"mean_token_accuracy": 0.17221850603818895,
|
|
"num_tokens": 13676767.0,
|
|
"step": 6130
|
|
},
|
|
{
|
|
"entropy": 5.627943468093872,
|
|
"epoch": 0.6890548660639074,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004962339392831783,
|
|
"loss": 5.6228,
|
|
"mean_token_accuracy": 0.17215524911880492,
|
|
"num_tokens": 13688552.0,
|
|
"step": 6135
|
|
},
|
|
{
|
|
"entropy": 5.70760407447815,
|
|
"epoch": 0.689616442971865,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.000496226620764454,
|
|
"loss": 5.5953,
|
|
"mean_token_accuracy": 0.17065925300121307,
|
|
"num_tokens": 13700160.0,
|
|
"step": 6140
|
|
},
|
|
{
|
|
"entropy": 5.671698188781738,
|
|
"epoch": 0.6901780198798225,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.000496219295201788,
|
|
"loss": 5.6011,
|
|
"mean_token_accuracy": 0.1736286088824272,
|
|
"num_tokens": 13710828.0,
|
|
"step": 6145
|
|
},
|
|
{
|
|
"entropy": 5.744783687591553,
|
|
"epoch": 0.6907395967877801,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004962119625954141,
|
|
"loss": 5.7163,
|
|
"mean_token_accuracy": 0.16494496762752534,
|
|
"num_tokens": 13721912.0,
|
|
"step": 6150
|
|
},
|
|
{
|
|
"entropy": 5.773995733261108,
|
|
"epoch": 0.6913011736957376,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004962046229455653,
|
|
"loss": 5.7312,
|
|
"mean_token_accuracy": 0.1703624963760376,
|
|
"num_tokens": 13733662.0,
|
|
"step": 6155
|
|
},
|
|
{
|
|
"entropy": 5.625052499771118,
|
|
"epoch": 0.6918627506036952,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004961972762524757,
|
|
"loss": 5.549,
|
|
"mean_token_accuracy": 0.1760735273361206,
|
|
"num_tokens": 13743699.0,
|
|
"step": 6160
|
|
},
|
|
{
|
|
"entropy": 5.629493951797485,
|
|
"epoch": 0.6924243275116527,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.000496189922516379,
|
|
"loss": 5.5554,
|
|
"mean_token_accuracy": 0.17835567742586136,
|
|
"num_tokens": 13754918.0,
|
|
"step": 6165
|
|
},
|
|
{
|
|
"entropy": 5.802048397064209,
|
|
"epoch": 0.6929859044196103,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004961825617375093,
|
|
"loss": 5.589,
|
|
"mean_token_accuracy": 0.1810780867934227,
|
|
"num_tokens": 13764432.0,
|
|
"step": 6170
|
|
},
|
|
{
|
|
"entropy": 5.56612720489502,
|
|
"epoch": 0.6935474813275678,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004961751939161011,
|
|
"loss": 5.5101,
|
|
"mean_token_accuracy": 0.1665957048535347,
|
|
"num_tokens": 13777049.0,
|
|
"step": 6175
|
|
},
|
|
{
|
|
"entropy": 5.613159084320069,
|
|
"epoch": 0.6941090582355254,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.000496167819052389,
|
|
"loss": 5.6285,
|
|
"mean_token_accuracy": 0.17187547385692598,
|
|
"num_tokens": 13788324.0,
|
|
"step": 6180
|
|
},
|
|
{
|
|
"entropy": 5.774720954895019,
|
|
"epoch": 0.6946706351434829,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004961604371466077,
|
|
"loss": 5.7071,
|
|
"mean_token_accuracy": 0.1715664029121399,
|
|
"num_tokens": 13800443.0,
|
|
"step": 6185
|
|
},
|
|
{
|
|
"entropy": 5.813463592529297,
|
|
"epoch": 0.6952322120514405,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004961530481989923,
|
|
"loss": 5.7471,
|
|
"mean_token_accuracy": 0.1697026953101158,
|
|
"num_tokens": 13811982.0,
|
|
"step": 6190
|
|
},
|
|
{
|
|
"entropy": 5.664430713653564,
|
|
"epoch": 0.695793788959398,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004961456522097782,
|
|
"loss": 5.5307,
|
|
"mean_token_accuracy": 0.17545289546251297,
|
|
"num_tokens": 13822005.0,
|
|
"step": 6195
|
|
},
|
|
{
|
|
"entropy": 5.580399084091186,
|
|
"epoch": 0.6963553658673556,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004961382491792006,
|
|
"loss": 5.5458,
|
|
"mean_token_accuracy": 0.1745297133922577,
|
|
"num_tokens": 13831943.0,
|
|
"step": 6200
|
|
},
|
|
{
|
|
"entropy": 5.800264644622803,
|
|
"epoch": 0.6969169427753131,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004961308391074953,
|
|
"loss": 5.7382,
|
|
"mean_token_accuracy": 0.16787344366312026,
|
|
"num_tokens": 13842517.0,
|
|
"step": 6205
|
|
},
|
|
{
|
|
"entropy": 5.726728725433349,
|
|
"epoch": 0.6974785196832706,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004961234219948986,
|
|
"loss": 5.6109,
|
|
"mean_token_accuracy": 0.1686943292617798,
|
|
"num_tokens": 13853636.0,
|
|
"step": 6210
|
|
},
|
|
{
|
|
"entropy": 5.655916929244995,
|
|
"epoch": 0.6980400965912281,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004961159978416461,
|
|
"loss": 5.5513,
|
|
"mean_token_accuracy": 0.1721298947930336,
|
|
"num_tokens": 13864378.0,
|
|
"step": 6215
|
|
},
|
|
{
|
|
"entropy": 5.713779544830322,
|
|
"epoch": 0.6986016734991857,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004961085666479746,
|
|
"loss": 5.5778,
|
|
"mean_token_accuracy": 0.17656196355819703,
|
|
"num_tokens": 13874964.0,
|
|
"step": 6220
|
|
},
|
|
{
|
|
"entropy": 5.689186382293701,
|
|
"epoch": 0.6991632504071432,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004961011284141206,
|
|
"loss": 5.5644,
|
|
"mean_token_accuracy": 0.16974303126335144,
|
|
"num_tokens": 13885852.0,
|
|
"step": 6225
|
|
},
|
|
{
|
|
"entropy": 5.630877304077148,
|
|
"epoch": 0.6997248273151008,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004960936831403209,
|
|
"loss": 5.6134,
|
|
"mean_token_accuracy": 0.17150009721517562,
|
|
"num_tokens": 13896101.0,
|
|
"step": 6230
|
|
},
|
|
{
|
|
"entropy": 5.648992586135864,
|
|
"epoch": 0.7002864042230583,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004960862308268126,
|
|
"loss": 5.5052,
|
|
"mean_token_accuracy": 0.17886769622564316,
|
|
"num_tokens": 13907129.0,
|
|
"step": 6235
|
|
},
|
|
{
|
|
"entropy": 5.720948791503906,
|
|
"epoch": 0.7008479811310159,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004960787714738329,
|
|
"loss": 5.6951,
|
|
"mean_token_accuracy": 0.1737249031662941,
|
|
"num_tokens": 13918662.0,
|
|
"step": 6240
|
|
},
|
|
{
|
|
"entropy": 5.685187721252442,
|
|
"epoch": 0.7014095580389734,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004960713050816194,
|
|
"loss": 5.6562,
|
|
"mean_token_accuracy": 0.17299176901578903,
|
|
"num_tokens": 13930717.0,
|
|
"step": 6245
|
|
},
|
|
{
|
|
"entropy": 5.633158874511719,
|
|
"epoch": 0.701971134946931,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004960638316504098,
|
|
"loss": 5.5279,
|
|
"mean_token_accuracy": 0.17130255252122878,
|
|
"num_tokens": 13941299.0,
|
|
"step": 6250
|
|
},
|
|
{
|
|
"entropy": 5.780350589752198,
|
|
"epoch": 0.7025327118548885,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004960563511804421,
|
|
"loss": 5.6119,
|
|
"mean_token_accuracy": 0.17323518246412278,
|
|
"num_tokens": 13951807.0,
|
|
"step": 6255
|
|
},
|
|
{
|
|
"entropy": 5.650942611694336,
|
|
"epoch": 0.7030942887628461,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004960488636719545,
|
|
"loss": 5.5209,
|
|
"mean_token_accuracy": 0.17925544530153276,
|
|
"num_tokens": 13962994.0,
|
|
"step": 6260
|
|
},
|
|
{
|
|
"entropy": 5.566241312026977,
|
|
"epoch": 0.7036558656708036,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004960413691251852,
|
|
"loss": 5.5587,
|
|
"mean_token_accuracy": 0.17189284712076186,
|
|
"num_tokens": 13973731.0,
|
|
"step": 6265
|
|
},
|
|
{
|
|
"entropy": 5.686014032363891,
|
|
"epoch": 0.7042174425787612,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004960338675403731,
|
|
"loss": 5.6194,
|
|
"mean_token_accuracy": 0.16850770264863968,
|
|
"num_tokens": 13983772.0,
|
|
"step": 6270
|
|
},
|
|
{
|
|
"entropy": 5.6831377983093265,
|
|
"epoch": 0.7047790194867187,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004960263589177568,
|
|
"loss": 5.6285,
|
|
"mean_token_accuracy": 0.17523877322673798,
|
|
"num_tokens": 13994935.0,
|
|
"step": 6275
|
|
},
|
|
{
|
|
"entropy": 5.693459796905517,
|
|
"epoch": 0.7053405963946763,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004960188432575757,
|
|
"loss": 5.5889,
|
|
"mean_token_accuracy": 0.17878624945878982,
|
|
"num_tokens": 14006225.0,
|
|
"step": 6280
|
|
},
|
|
{
|
|
"entropy": 5.69208722114563,
|
|
"epoch": 0.7059021733026338,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004960113205600688,
|
|
"loss": 5.6025,
|
|
"mean_token_accuracy": 0.18202067613601686,
|
|
"num_tokens": 14017693.0,
|
|
"step": 6285
|
|
},
|
|
{
|
|
"entropy": 5.67942214012146,
|
|
"epoch": 0.7064637502105914,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004960037908254757,
|
|
"loss": 5.5771,
|
|
"mean_token_accuracy": 0.17393409013748168,
|
|
"num_tokens": 14027264.0,
|
|
"step": 6290
|
|
},
|
|
{
|
|
"entropy": 5.7325080871582035,
|
|
"epoch": 0.7070253271185489,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004959962540540361,
|
|
"loss": 5.6781,
|
|
"mean_token_accuracy": 0.17509326040744783,
|
|
"num_tokens": 14039422.0,
|
|
"step": 6295
|
|
},
|
|
{
|
|
"entropy": 5.694810819625855,
|
|
"epoch": 0.7075869040265065,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004959887102459903,
|
|
"loss": 5.6026,
|
|
"mean_token_accuracy": 0.17309763431549072,
|
|
"num_tokens": 14051619.0,
|
|
"step": 6300
|
|
},
|
|
{
|
|
"entropy": 5.518226671218872,
|
|
"epoch": 0.7081484809344639,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004959811594015781,
|
|
"loss": 5.6008,
|
|
"mean_token_accuracy": 0.17118653059005737,
|
|
"num_tokens": 14061752.0,
|
|
"step": 6305
|
|
},
|
|
{
|
|
"entropy": 5.7187727928161625,
|
|
"epoch": 0.7087100578424215,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004959736015210401,
|
|
"loss": 5.5499,
|
|
"mean_token_accuracy": 0.17870223075151442,
|
|
"num_tokens": 14072931.0,
|
|
"step": 6310
|
|
},
|
|
{
|
|
"entropy": 5.670480346679687,
|
|
"epoch": 0.709271634750379,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004959660366046169,
|
|
"loss": 5.6354,
|
|
"mean_token_accuracy": 0.1812950477004051,
|
|
"num_tokens": 14084137.0,
|
|
"step": 6315
|
|
},
|
|
{
|
|
"entropy": 5.733542203903198,
|
|
"epoch": 0.7098332116583366,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004959584646525494,
|
|
"loss": 5.643,
|
|
"mean_token_accuracy": 0.16594423800706865,
|
|
"num_tokens": 14096251.0,
|
|
"step": 6320
|
|
},
|
|
{
|
|
"entropy": 5.834647226333618,
|
|
"epoch": 0.7103947885662941,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004959508856650788,
|
|
"loss": 5.747,
|
|
"mean_token_accuracy": 0.15990046858787538,
|
|
"num_tokens": 14107844.0,
|
|
"step": 6325
|
|
},
|
|
{
|
|
"entropy": 5.701244258880616,
|
|
"epoch": 0.7109563654742517,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004959432996424463,
|
|
"loss": 5.5159,
|
|
"mean_token_accuracy": 0.1764766052365303,
|
|
"num_tokens": 14118344.0,
|
|
"step": 6330
|
|
},
|
|
{
|
|
"entropy": 5.683355712890625,
|
|
"epoch": 0.7115179423822092,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004959357065848932,
|
|
"loss": 5.5731,
|
|
"mean_token_accuracy": 0.17560436129570006,
|
|
"num_tokens": 14128767.0,
|
|
"step": 6335
|
|
},
|
|
{
|
|
"entropy": 5.676946210861206,
|
|
"epoch": 0.7120795192901668,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004959281064926618,
|
|
"loss": 5.7624,
|
|
"mean_token_accuracy": 0.1625056892633438,
|
|
"num_tokens": 14141593.0,
|
|
"step": 6340
|
|
},
|
|
{
|
|
"entropy": 5.787940835952758,
|
|
"epoch": 0.7126410961981243,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004959204993659936,
|
|
"loss": 5.658,
|
|
"mean_token_accuracy": 0.16435816437005996,
|
|
"num_tokens": 14151488.0,
|
|
"step": 6345
|
|
},
|
|
{
|
|
"entropy": 5.709534454345703,
|
|
"epoch": 0.7132026731060819,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004959128852051311,
|
|
"loss": 5.6446,
|
|
"mean_token_accuracy": 0.17000896334648133,
|
|
"num_tokens": 14162399.0,
|
|
"step": 6350
|
|
},
|
|
{
|
|
"entropy": 5.681110572814942,
|
|
"epoch": 0.7137642500140394,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004959052640103167,
|
|
"loss": 5.6154,
|
|
"mean_token_accuracy": 0.1655770495533943,
|
|
"num_tokens": 14173528.0,
|
|
"step": 6355
|
|
},
|
|
{
|
|
"entropy": 5.737189197540284,
|
|
"epoch": 0.714325826921997,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.000495897635781793,
|
|
"loss": 5.5977,
|
|
"mean_token_accuracy": 0.1738772988319397,
|
|
"num_tokens": 14184119.0,
|
|
"step": 6360
|
|
},
|
|
{
|
|
"entropy": 5.783509731292725,
|
|
"epoch": 0.7148874038299545,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004958900005198029,
|
|
"loss": 5.6966,
|
|
"mean_token_accuracy": 0.16666410118341446,
|
|
"num_tokens": 14196225.0,
|
|
"step": 6365
|
|
},
|
|
{
|
|
"entropy": 5.5992560386657715,
|
|
"epoch": 0.7154489807379121,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004958823582245894,
|
|
"loss": 5.5122,
|
|
"mean_token_accuracy": 0.1770908787846565,
|
|
"num_tokens": 14207541.0,
|
|
"step": 6370
|
|
},
|
|
{
|
|
"entropy": 5.713044595718384,
|
|
"epoch": 0.7160105576458696,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004958747088963961,
|
|
"loss": 5.62,
|
|
"mean_token_accuracy": 0.17931632846593856,
|
|
"num_tokens": 14218713.0,
|
|
"step": 6375
|
|
},
|
|
{
|
|
"entropy": 5.576667070388794,
|
|
"epoch": 0.7165721345538272,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004958670525354663,
|
|
"loss": 5.4876,
|
|
"mean_token_accuracy": 0.17556754648685455,
|
|
"num_tokens": 14229626.0,
|
|
"step": 6380
|
|
},
|
|
{
|
|
"entropy": 5.67002272605896,
|
|
"epoch": 0.7171337114617847,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.000495859389142044,
|
|
"loss": 5.6633,
|
|
"mean_token_accuracy": 0.16710093021392822,
|
|
"num_tokens": 14240320.0,
|
|
"step": 6385
|
|
},
|
|
{
|
|
"entropy": 5.830556774139405,
|
|
"epoch": 0.7176952883697423,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.000495851718716373,
|
|
"loss": 5.719,
|
|
"mean_token_accuracy": 0.17310031801462172,
|
|
"num_tokens": 14252233.0,
|
|
"step": 6390
|
|
},
|
|
{
|
|
"entropy": 5.79133095741272,
|
|
"epoch": 0.7182568652776998,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004958440412586977,
|
|
"loss": 5.7307,
|
|
"mean_token_accuracy": 0.15904613435268403,
|
|
"num_tokens": 14264421.0,
|
|
"step": 6395
|
|
},
|
|
{
|
|
"entropy": 5.731802177429199,
|
|
"epoch": 0.7188184421856574,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004958363567692624,
|
|
"loss": 5.6031,
|
|
"mean_token_accuracy": 0.17360225617885588,
|
|
"num_tokens": 14275320.0,
|
|
"step": 6400
|
|
},
|
|
{
|
|
"entropy": 5.638220739364624,
|
|
"epoch": 0.7193800190936148,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004958286652483118,
|
|
"loss": 5.5668,
|
|
"mean_token_accuracy": 0.1780466377735138,
|
|
"num_tokens": 14286099.0,
|
|
"step": 6405
|
|
},
|
|
{
|
|
"entropy": 5.66323037147522,
|
|
"epoch": 0.7199415960015724,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004958209666960909,
|
|
"loss": 5.6835,
|
|
"mean_token_accuracy": 0.16914550662040712,
|
|
"num_tokens": 14297795.0,
|
|
"step": 6410
|
|
},
|
|
{
|
|
"entropy": 5.638380813598633,
|
|
"epoch": 0.7205031729095299,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004958132611128448,
|
|
"loss": 5.5828,
|
|
"mean_token_accuracy": 0.17390582710504532,
|
|
"num_tokens": 14309424.0,
|
|
"step": 6415
|
|
},
|
|
{
|
|
"entropy": 5.784746742248535,
|
|
"epoch": 0.7210647498174875,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004958055484988188,
|
|
"loss": 5.6623,
|
|
"mean_token_accuracy": 0.16943105459213256,
|
|
"num_tokens": 14320763.0,
|
|
"step": 6420
|
|
},
|
|
{
|
|
"entropy": 5.7342438220977785,
|
|
"epoch": 0.721626326725445,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004957978288542585,
|
|
"loss": 5.6264,
|
|
"mean_token_accuracy": 0.1723559558391571,
|
|
"num_tokens": 14331704.0,
|
|
"step": 6425
|
|
},
|
|
{
|
|
"entropy": 5.756981945037841,
|
|
"epoch": 0.7221879036334026,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004957901021794098,
|
|
"loss": 5.675,
|
|
"mean_token_accuracy": 0.16486780792474748,
|
|
"num_tokens": 14343694.0,
|
|
"step": 6430
|
|
},
|
|
{
|
|
"entropy": 5.680773448944092,
|
|
"epoch": 0.7227494805413601,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004957823684745184,
|
|
"loss": 5.572,
|
|
"mean_token_accuracy": 0.17167100310325623,
|
|
"num_tokens": 14355408.0,
|
|
"step": 6435
|
|
},
|
|
{
|
|
"entropy": 5.703755664825439,
|
|
"epoch": 0.7233110574493177,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004957746277398309,
|
|
"loss": 5.7254,
|
|
"mean_token_accuracy": 0.16364069730043412,
|
|
"num_tokens": 14366778.0,
|
|
"step": 6440
|
|
},
|
|
{
|
|
"entropy": 5.712000751495362,
|
|
"epoch": 0.7238726343572752,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004957668799755937,
|
|
"loss": 5.5799,
|
|
"mean_token_accuracy": 0.17299263626337053,
|
|
"num_tokens": 14377947.0,
|
|
"step": 6445
|
|
},
|
|
{
|
|
"entropy": 5.705758762359619,
|
|
"epoch": 0.7244342112652328,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004957591251820532,
|
|
"loss": 5.6688,
|
|
"mean_token_accuracy": 0.1714080259203911,
|
|
"num_tokens": 14389571.0,
|
|
"step": 6450
|
|
},
|
|
{
|
|
"entropy": 5.8451415538787845,
|
|
"epoch": 0.7249957881731903,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004957513633594567,
|
|
"loss": 5.7455,
|
|
"mean_token_accuracy": 0.1655985251069069,
|
|
"num_tokens": 14401865.0,
|
|
"step": 6455
|
|
},
|
|
{
|
|
"entropy": 5.643240690231323,
|
|
"epoch": 0.7255573650811479,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004957435945080512,
|
|
"loss": 5.576,
|
|
"mean_token_accuracy": 0.17257309556007386,
|
|
"num_tokens": 14413676.0,
|
|
"step": 6460
|
|
},
|
|
{
|
|
"entropy": 5.6537106990814205,
|
|
"epoch": 0.7261189419891054,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004957358186280839,
|
|
"loss": 5.6016,
|
|
"mean_token_accuracy": 0.1794086754322052,
|
|
"num_tokens": 14424675.0,
|
|
"step": 6465
|
|
},
|
|
{
|
|
"entropy": 5.618784666061401,
|
|
"epoch": 0.726680518897063,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004957280357198026,
|
|
"loss": 5.5149,
|
|
"mean_token_accuracy": 0.17647840976715087,
|
|
"num_tokens": 14437238.0,
|
|
"step": 6470
|
|
},
|
|
{
|
|
"entropy": 5.549806547164917,
|
|
"epoch": 0.7272420958050205,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004957202457834551,
|
|
"loss": 5.4673,
|
|
"mean_token_accuracy": 0.17938644886016847,
|
|
"num_tokens": 14448003.0,
|
|
"step": 6475
|
|
},
|
|
{
|
|
"entropy": 5.528613138198852,
|
|
"epoch": 0.7278036727129781,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004957124488192893,
|
|
"loss": 5.4236,
|
|
"mean_token_accuracy": 0.18780238777399064,
|
|
"num_tokens": 14458440.0,
|
|
"step": 6480
|
|
},
|
|
{
|
|
"entropy": 5.688983345031739,
|
|
"epoch": 0.7283652496209356,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004957046448275535,
|
|
"loss": 5.6076,
|
|
"mean_token_accuracy": 0.17096126079559326,
|
|
"num_tokens": 14470127.0,
|
|
"step": 6485
|
|
},
|
|
{
|
|
"entropy": 5.652023792266846,
|
|
"epoch": 0.7289268265288932,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004956968338084961,
|
|
"loss": 5.5194,
|
|
"mean_token_accuracy": 0.17799320966005325,
|
|
"num_tokens": 14480993.0,
|
|
"step": 6490
|
|
},
|
|
{
|
|
"entropy": 5.667353630065918,
|
|
"epoch": 0.7294884034368507,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004956890157623661,
|
|
"loss": 5.6216,
|
|
"mean_token_accuracy": 0.16608051508665084,
|
|
"num_tokens": 14492789.0,
|
|
"step": 6495
|
|
},
|
|
{
|
|
"entropy": 5.735092353820801,
|
|
"epoch": 0.7300499803448082,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004956811906894122,
|
|
"loss": 5.7142,
|
|
"mean_token_accuracy": 0.16898949593305587,
|
|
"num_tokens": 14504528.0,
|
|
"step": 6500
|
|
},
|
|
{
|
|
"entropy": 5.777708959579468,
|
|
"epoch": 0.7306115572527657,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004956733585898836,
|
|
"loss": 5.6052,
|
|
"mean_token_accuracy": 0.17461458444595337,
|
|
"num_tokens": 14515739.0,
|
|
"step": 6505
|
|
},
|
|
{
|
|
"entropy": 5.7372722148895265,
|
|
"epoch": 0.7311731341607233,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004956655194640297,
|
|
"loss": 5.7253,
|
|
"mean_token_accuracy": 0.165912227332592,
|
|
"num_tokens": 14527120.0,
|
|
"step": 6510
|
|
},
|
|
{
|
|
"entropy": 5.734869432449341,
|
|
"epoch": 0.7317347110686808,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004956576733121,
|
|
"loss": 5.6732,
|
|
"mean_token_accuracy": 0.17188447639346122,
|
|
"num_tokens": 14539390.0,
|
|
"step": 6515
|
|
},
|
|
{
|
|
"entropy": 5.7428192615509035,
|
|
"epoch": 0.7322962879766384,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004956498201343444,
|
|
"loss": 5.6542,
|
|
"mean_token_accuracy": 0.17126702666282653,
|
|
"num_tokens": 14549905.0,
|
|
"step": 6520
|
|
},
|
|
{
|
|
"entropy": 5.7277122974395756,
|
|
"epoch": 0.7328578648845959,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.000495641959931013,
|
|
"loss": 5.7013,
|
|
"mean_token_accuracy": 0.17059755474328994,
|
|
"num_tokens": 14561519.0,
|
|
"step": 6525
|
|
},
|
|
{
|
|
"entropy": 5.656032657623291,
|
|
"epoch": 0.7334194417925535,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004956340927023561,
|
|
"loss": 5.4721,
|
|
"mean_token_accuracy": 0.17097557485103607,
|
|
"num_tokens": 14572704.0,
|
|
"step": 6530
|
|
},
|
|
{
|
|
"entropy": 5.733268117904663,
|
|
"epoch": 0.733981018700511,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000495626218448624,
|
|
"loss": 5.6477,
|
|
"mean_token_accuracy": 0.17309343367815017,
|
|
"num_tokens": 14584055.0,
|
|
"step": 6535
|
|
},
|
|
{
|
|
"entropy": 5.528829097747803,
|
|
"epoch": 0.7345425956084686,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004956183371700676,
|
|
"loss": 5.4578,
|
|
"mean_token_accuracy": 0.17761017978191376,
|
|
"num_tokens": 14595271.0,
|
|
"step": 6540
|
|
},
|
|
{
|
|
"entropy": 5.687887334823609,
|
|
"epoch": 0.7351041725164261,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004956104488669377,
|
|
"loss": 5.6217,
|
|
"mean_token_accuracy": 0.1771188572049141,
|
|
"num_tokens": 14605748.0,
|
|
"step": 6545
|
|
},
|
|
{
|
|
"entropy": 5.658285093307495,
|
|
"epoch": 0.7356657494243837,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004956025535394856,
|
|
"loss": 5.5326,
|
|
"mean_token_accuracy": 0.18142949491739274,
|
|
"num_tokens": 14616295.0,
|
|
"step": 6550
|
|
},
|
|
{
|
|
"entropy": 5.633347415924073,
|
|
"epoch": 0.7362273263323412,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004955946511879626,
|
|
"loss": 5.625,
|
|
"mean_token_accuracy": 0.16703985631465912,
|
|
"num_tokens": 14626690.0,
|
|
"step": 6555
|
|
},
|
|
{
|
|
"entropy": 5.678591918945313,
|
|
"epoch": 0.7367889032402988,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004955867418126205,
|
|
"loss": 5.6293,
|
|
"mean_token_accuracy": 0.17487271279096603,
|
|
"num_tokens": 14637685.0,
|
|
"step": 6560
|
|
},
|
|
{
|
|
"entropy": 5.738638973236084,
|
|
"epoch": 0.7373504801482563,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004955788254137108,
|
|
"loss": 5.5306,
|
|
"mean_token_accuracy": 0.17113898396492006,
|
|
"num_tokens": 14648098.0,
|
|
"step": 6565
|
|
},
|
|
{
|
|
"entropy": 5.746050071716309,
|
|
"epoch": 0.7379120570562139,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004955709019914857,
|
|
"loss": 5.6727,
|
|
"mean_token_accuracy": 0.16656773388385773,
|
|
"num_tokens": 14661134.0,
|
|
"step": 6570
|
|
},
|
|
{
|
|
"entropy": 5.746538877487183,
|
|
"epoch": 0.7384736339641714,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004955629715461977,
|
|
"loss": 5.6445,
|
|
"mean_token_accuracy": 0.17216980457305908,
|
|
"num_tokens": 14672699.0,
|
|
"step": 6575
|
|
},
|
|
{
|
|
"entropy": 5.747246170043946,
|
|
"epoch": 0.739035210872129,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004955550340780991,
|
|
"loss": 5.6143,
|
|
"mean_token_accuracy": 0.16882283240556717,
|
|
"num_tokens": 14682994.0,
|
|
"step": 6580
|
|
},
|
|
{
|
|
"entropy": 5.672818374633789,
|
|
"epoch": 0.7395967877800865,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004955470895874427,
|
|
"loss": 5.6186,
|
|
"mean_token_accuracy": 0.17457711100578308,
|
|
"num_tokens": 14694828.0,
|
|
"step": 6585
|
|
},
|
|
{
|
|
"entropy": 5.648428583145142,
|
|
"epoch": 0.7401583646880441,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004955391380744813,
|
|
"loss": 5.6108,
|
|
"mean_token_accuracy": 0.17359036207199097,
|
|
"num_tokens": 14705975.0,
|
|
"step": 6590
|
|
},
|
|
{
|
|
"entropy": 5.726032495498657,
|
|
"epoch": 0.7407199415960015,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004955311795394684,
|
|
"loss": 5.5944,
|
|
"mean_token_accuracy": 0.1734750136733055,
|
|
"num_tokens": 14717717.0,
|
|
"step": 6595
|
|
},
|
|
{
|
|
"entropy": 5.711815071105957,
|
|
"epoch": 0.7412815185039591,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.000495523213982657,
|
|
"loss": 5.5662,
|
|
"mean_token_accuracy": 0.1741805464029312,
|
|
"num_tokens": 14729254.0,
|
|
"step": 6600
|
|
},
|
|
{
|
|
"entropy": 5.6931883811950685,
|
|
"epoch": 0.7418430954119166,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004955152414043011,
|
|
"loss": 5.7119,
|
|
"mean_token_accuracy": 0.1718486949801445,
|
|
"num_tokens": 14739733.0,
|
|
"step": 6605
|
|
},
|
|
{
|
|
"entropy": 5.752079057693481,
|
|
"epoch": 0.7424046723198742,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004955072618046543,
|
|
"loss": 5.6666,
|
|
"mean_token_accuracy": 0.17087932378053666,
|
|
"num_tokens": 14750855.0,
|
|
"step": 6610
|
|
},
|
|
{
|
|
"entropy": 5.71418023109436,
|
|
"epoch": 0.7429662492278317,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004954992751839708,
|
|
"loss": 5.6614,
|
|
"mean_token_accuracy": 0.1698993593454361,
|
|
"num_tokens": 14762762.0,
|
|
"step": 6615
|
|
},
|
|
{
|
|
"entropy": 5.688072967529297,
|
|
"epoch": 0.7435278261357893,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004954912815425048,
|
|
"loss": 5.5299,
|
|
"mean_token_accuracy": 0.1700862854719162,
|
|
"num_tokens": 14773690.0,
|
|
"step": 6620
|
|
},
|
|
{
|
|
"entropy": 5.640633058547974,
|
|
"epoch": 0.7440894030437468,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.000495483280880511,
|
|
"loss": 5.6447,
|
|
"mean_token_accuracy": 0.17218244969844818,
|
|
"num_tokens": 14785019.0,
|
|
"step": 6625
|
|
},
|
|
{
|
|
"entropy": 5.643097877502441,
|
|
"epoch": 0.7446509799517044,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000495475273198244,
|
|
"loss": 5.6206,
|
|
"mean_token_accuracy": 0.16789701133966445,
|
|
"num_tokens": 14795638.0,
|
|
"step": 6630
|
|
},
|
|
{
|
|
"entropy": 5.715163087844848,
|
|
"epoch": 0.7452125568596619,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004954672584959588,
|
|
"loss": 5.549,
|
|
"mean_token_accuracy": 0.17813322842121124,
|
|
"num_tokens": 14806546.0,
|
|
"step": 6635
|
|
},
|
|
{
|
|
"entropy": 5.596341991424561,
|
|
"epoch": 0.7457741337676195,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004954592367739104,
|
|
"loss": 5.5626,
|
|
"mean_token_accuracy": 0.17497475147247316,
|
|
"num_tokens": 14816918.0,
|
|
"step": 6640
|
|
},
|
|
{
|
|
"entropy": 5.6133809089660645,
|
|
"epoch": 0.746335710675577,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004954512080323546,
|
|
"loss": 5.5571,
|
|
"mean_token_accuracy": 0.18172363042831421,
|
|
"num_tokens": 14827420.0,
|
|
"step": 6645
|
|
},
|
|
{
|
|
"entropy": 5.7528026580810545,
|
|
"epoch": 0.7468972875835346,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004954431722715468,
|
|
"loss": 5.7731,
|
|
"mean_token_accuracy": 0.17284041196107863,
|
|
"num_tokens": 14839209.0,
|
|
"step": 6650
|
|
},
|
|
{
|
|
"entropy": 5.772123146057129,
|
|
"epoch": 0.7474588644914921,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004954351294917428,
|
|
"loss": 5.6546,
|
|
"mean_token_accuracy": 0.16983917206525803,
|
|
"num_tokens": 14849916.0,
|
|
"step": 6655
|
|
},
|
|
{
|
|
"entropy": 5.593883991241455,
|
|
"epoch": 0.7480204413994497,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004954270796931989,
|
|
"loss": 5.5467,
|
|
"mean_token_accuracy": 0.17545504868030548,
|
|
"num_tokens": 14860946.0,
|
|
"step": 6660
|
|
},
|
|
{
|
|
"entropy": 5.773710012435913,
|
|
"epoch": 0.7485820183074072,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004954190228761712,
|
|
"loss": 5.6383,
|
|
"mean_token_accuracy": 0.16717524081468582,
|
|
"num_tokens": 14872750.0,
|
|
"step": 6665
|
|
},
|
|
{
|
|
"entropy": 5.68846116065979,
|
|
"epoch": 0.7491435952153648,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004954109590409164,
|
|
"loss": 5.6227,
|
|
"mean_token_accuracy": 0.17093631327152253,
|
|
"num_tokens": 14883714.0,
|
|
"step": 6670
|
|
},
|
|
{
|
|
"entropy": 5.633935451507568,
|
|
"epoch": 0.7497051721233223,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004954028881876911,
|
|
"loss": 5.6325,
|
|
"mean_token_accuracy": 0.17225925624370575,
|
|
"num_tokens": 14895147.0,
|
|
"step": 6675
|
|
},
|
|
{
|
|
"entropy": 5.698961019515991,
|
|
"epoch": 0.7502667490312799,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004953948103167524,
|
|
"loss": 5.5536,
|
|
"mean_token_accuracy": 0.1762816697359085,
|
|
"num_tokens": 14905914.0,
|
|
"step": 6680
|
|
},
|
|
{
|
|
"entropy": 5.582836866378784,
|
|
"epoch": 0.7508283259392374,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004953867254283575,
|
|
"loss": 5.5428,
|
|
"mean_token_accuracy": 0.17713676244020463,
|
|
"num_tokens": 14916988.0,
|
|
"step": 6685
|
|
},
|
|
{
|
|
"entropy": 5.6897834777832035,
|
|
"epoch": 0.7513899028471949,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004953786335227636,
|
|
"loss": 5.6518,
|
|
"mean_token_accuracy": 0.17040350288152695,
|
|
"num_tokens": 14928675.0,
|
|
"step": 6690
|
|
},
|
|
{
|
|
"entropy": 5.795252656936645,
|
|
"epoch": 0.7519514797551524,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004953705346002287,
|
|
"loss": 5.6581,
|
|
"mean_token_accuracy": 0.17117824405431747,
|
|
"num_tokens": 14939422.0,
|
|
"step": 6695
|
|
},
|
|
{
|
|
"entropy": 5.6437677383422855,
|
|
"epoch": 0.75251305666311,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004953624286610106,
|
|
"loss": 5.6086,
|
|
"mean_token_accuracy": 0.17704180479049683,
|
|
"num_tokens": 14950156.0,
|
|
"step": 6700
|
|
},
|
|
{
|
|
"entropy": 5.65733003616333,
|
|
"epoch": 0.7530746335710675,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004953543157053672,
|
|
"loss": 5.5983,
|
|
"mean_token_accuracy": 0.1764406979084015,
|
|
"num_tokens": 14960535.0,
|
|
"step": 6705
|
|
},
|
|
{
|
|
"entropy": 5.767850303649903,
|
|
"epoch": 0.7536362104790251,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004953461957335569,
|
|
"loss": 5.6239,
|
|
"mean_token_accuracy": 0.1750498056411743,
|
|
"num_tokens": 14970975.0,
|
|
"step": 6710
|
|
},
|
|
{
|
|
"entropy": 5.632910871505738,
|
|
"epoch": 0.7541977873869826,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004953380687458382,
|
|
"loss": 5.4731,
|
|
"mean_token_accuracy": 0.18237796127796174,
|
|
"num_tokens": 14981204.0,
|
|
"step": 6715
|
|
},
|
|
{
|
|
"entropy": 5.653511953353882,
|
|
"epoch": 0.7547593642949402,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004953299347424701,
|
|
"loss": 5.6468,
|
|
"mean_token_accuracy": 0.17152471095323563,
|
|
"num_tokens": 14991631.0,
|
|
"step": 6720
|
|
},
|
|
{
|
|
"entropy": 5.657448101043701,
|
|
"epoch": 0.7553209412028977,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004953217937237114,
|
|
"loss": 5.5735,
|
|
"mean_token_accuracy": 0.17640465199947358,
|
|
"num_tokens": 15003873.0,
|
|
"step": 6725
|
|
},
|
|
{
|
|
"entropy": 5.69847002029419,
|
|
"epoch": 0.7558825181108553,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004953136456898212,
|
|
"loss": 5.6493,
|
|
"mean_token_accuracy": 0.17125397473573684,
|
|
"num_tokens": 15014890.0,
|
|
"step": 6730
|
|
},
|
|
{
|
|
"entropy": 5.604665327072143,
|
|
"epoch": 0.7564440950188128,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004953054906410593,
|
|
"loss": 5.5194,
|
|
"mean_token_accuracy": 0.18065904527902604,
|
|
"num_tokens": 15025037.0,
|
|
"step": 6735
|
|
},
|
|
{
|
|
"entropy": 5.690511035919189,
|
|
"epoch": 0.7570056719267704,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.0004952973285776848,
|
|
"loss": 5.6233,
|
|
"mean_token_accuracy": 0.17375240176916124,
|
|
"num_tokens": 15035722.0,
|
|
"step": 6740
|
|
},
|
|
{
|
|
"entropy": 5.696527576446533,
|
|
"epoch": 0.7575672488347279,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004952891594999582,
|
|
"loss": 5.6224,
|
|
"mean_token_accuracy": 0.16907656490802764,
|
|
"num_tokens": 15047138.0,
|
|
"step": 6745
|
|
},
|
|
{
|
|
"entropy": 5.616460132598877,
|
|
"epoch": 0.7581288257426855,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004952809834081392,
|
|
"loss": 5.5799,
|
|
"mean_token_accuracy": 0.17677342891693115,
|
|
"num_tokens": 15058559.0,
|
|
"step": 6750
|
|
},
|
|
{
|
|
"entropy": 5.669347715377808,
|
|
"epoch": 0.758690402650643,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004952728003024883,
|
|
"loss": 5.6034,
|
|
"mean_token_accuracy": 0.17386410832405091,
|
|
"num_tokens": 15070481.0,
|
|
"step": 6755
|
|
},
|
|
{
|
|
"entropy": 5.746075916290283,
|
|
"epoch": 0.7592519795586006,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004952646101832659,
|
|
"loss": 5.525,
|
|
"mean_token_accuracy": 0.1773831456899643,
|
|
"num_tokens": 15079844.0,
|
|
"step": 6760
|
|
},
|
|
{
|
|
"entropy": 5.575839519500732,
|
|
"epoch": 0.7598135564665581,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004952564130507331,
|
|
"loss": 5.5459,
|
|
"mean_token_accuracy": 0.1829729363322258,
|
|
"num_tokens": 15091197.0,
|
|
"step": 6765
|
|
},
|
|
{
|
|
"entropy": 5.63728141784668,
|
|
"epoch": 0.7603751333745157,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004952482089051506,
|
|
"loss": 5.6395,
|
|
"mean_token_accuracy": 0.16757640540599822,
|
|
"num_tokens": 15102130.0,
|
|
"step": 6770
|
|
},
|
|
{
|
|
"entropy": 5.80513825416565,
|
|
"epoch": 0.7609367102824732,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004952399977467796,
|
|
"loss": 5.7159,
|
|
"mean_token_accuracy": 0.164860138297081,
|
|
"num_tokens": 15113886.0,
|
|
"step": 6775
|
|
},
|
|
{
|
|
"entropy": 5.695002603530884,
|
|
"epoch": 0.7614982871904308,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004952317795758817,
|
|
"loss": 5.5309,
|
|
"mean_token_accuracy": 0.1707255095243454,
|
|
"num_tokens": 15125284.0,
|
|
"step": 6780
|
|
},
|
|
{
|
|
"entropy": 5.693516254425049,
|
|
"epoch": 0.7620598640983883,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004952235543927185,
|
|
"loss": 5.6013,
|
|
"mean_token_accuracy": 0.17872631102800368,
|
|
"num_tokens": 15136486.0,
|
|
"step": 6785
|
|
},
|
|
{
|
|
"entropy": 5.5827912330627445,
|
|
"epoch": 0.7626214410063458,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.000495215322197552,
|
|
"loss": 5.4942,
|
|
"mean_token_accuracy": 0.1766755223274231,
|
|
"num_tokens": 15145937.0,
|
|
"step": 6790
|
|
},
|
|
{
|
|
"entropy": 5.606060981750488,
|
|
"epoch": 0.7631830179143033,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004952070829906442,
|
|
"loss": 5.5703,
|
|
"mean_token_accuracy": 0.17622093558311464,
|
|
"num_tokens": 15156923.0,
|
|
"step": 6795
|
|
},
|
|
{
|
|
"entropy": 5.764186716079712,
|
|
"epoch": 0.7637445948222609,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004951988367722574,
|
|
"loss": 5.701,
|
|
"mean_token_accuracy": 0.17148951441049576,
|
|
"num_tokens": 15169793.0,
|
|
"step": 6800
|
|
},
|
|
{
|
|
"entropy": 5.666046524047852,
|
|
"epoch": 0.7643061717302184,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004951905835426544,
|
|
"loss": 5.4701,
|
|
"mean_token_accuracy": 0.18407936692237853,
|
|
"num_tokens": 15180679.0,
|
|
"step": 6805
|
|
},
|
|
{
|
|
"entropy": 5.658257055282593,
|
|
"epoch": 0.764867748638176,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004951823233020976,
|
|
"loss": 5.6771,
|
|
"mean_token_accuracy": 0.1721682906150818,
|
|
"num_tokens": 15192298.0,
|
|
"step": 6810
|
|
},
|
|
{
|
|
"entropy": 5.657361793518066,
|
|
"epoch": 0.7654293255461335,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004951740560508504,
|
|
"loss": 5.7427,
|
|
"mean_token_accuracy": 0.1654340222477913,
|
|
"num_tokens": 15204759.0,
|
|
"step": 6815
|
|
},
|
|
{
|
|
"entropy": 5.795834302902222,
|
|
"epoch": 0.7659909024540911,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004951657817891758,
|
|
"loss": 5.6181,
|
|
"mean_token_accuracy": 0.17172770649194719,
|
|
"num_tokens": 15217166.0,
|
|
"step": 6820
|
|
},
|
|
{
|
|
"entropy": 5.596086502075195,
|
|
"epoch": 0.7665524793620486,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004951575005173373,
|
|
"loss": 5.5908,
|
|
"mean_token_accuracy": 0.17772889286279678,
|
|
"num_tokens": 15227022.0,
|
|
"step": 6825
|
|
},
|
|
{
|
|
"entropy": 5.7071445941925045,
|
|
"epoch": 0.7671140562700062,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004951492122355986,
|
|
"loss": 5.6438,
|
|
"mean_token_accuracy": 0.16916121244430543,
|
|
"num_tokens": 15239088.0,
|
|
"step": 6830
|
|
},
|
|
{
|
|
"entropy": 5.74067268371582,
|
|
"epoch": 0.7676756331779637,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004951409169442236,
|
|
"loss": 5.6636,
|
|
"mean_token_accuracy": 0.17377155274152756,
|
|
"num_tokens": 15250263.0,
|
|
"step": 6835
|
|
},
|
|
{
|
|
"entropy": 5.614690923690796,
|
|
"epoch": 0.7682372100859213,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004951326146434765,
|
|
"loss": 5.56,
|
|
"mean_token_accuracy": 0.17508067339658737,
|
|
"num_tokens": 15263014.0,
|
|
"step": 6840
|
|
},
|
|
{
|
|
"entropy": 5.698054409027099,
|
|
"epoch": 0.7687987869938788,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004951243053336214,
|
|
"loss": 5.5488,
|
|
"mean_token_accuracy": 0.17616119384765624,
|
|
"num_tokens": 15274261.0,
|
|
"step": 6845
|
|
},
|
|
{
|
|
"entropy": 5.617717838287353,
|
|
"epoch": 0.7693603639018364,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004951159890149232,
|
|
"loss": 5.4812,
|
|
"mean_token_accuracy": 0.17868284434080123,
|
|
"num_tokens": 15284929.0,
|
|
"step": 6850
|
|
},
|
|
{
|
|
"entropy": 5.601969814300537,
|
|
"epoch": 0.7699219408097939,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004951076656876466,
|
|
"loss": 5.5905,
|
|
"mean_token_accuracy": 0.1784390926361084,
|
|
"num_tokens": 15296622.0,
|
|
"step": 6855
|
|
},
|
|
{
|
|
"entropy": 5.671678590774536,
|
|
"epoch": 0.7704835177177515,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004950993353520564,
|
|
"loss": 5.6416,
|
|
"mean_token_accuracy": 0.16959952116012572,
|
|
"num_tokens": 15308373.0,
|
|
"step": 6860
|
|
},
|
|
{
|
|
"entropy": 5.633020448684692,
|
|
"epoch": 0.771045094625709,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.000495090998008418,
|
|
"loss": 5.5145,
|
|
"mean_token_accuracy": 0.18185887783765792,
|
|
"num_tokens": 15319705.0,
|
|
"step": 6865
|
|
},
|
|
{
|
|
"entropy": 5.718202543258667,
|
|
"epoch": 0.7716066715336666,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.000495082653656997,
|
|
"loss": 5.6745,
|
|
"mean_token_accuracy": 0.16872720867395402,
|
|
"num_tokens": 15330883.0,
|
|
"step": 6870
|
|
},
|
|
{
|
|
"entropy": 5.695891237258911,
|
|
"epoch": 0.7721682484416241,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004950743022980587,
|
|
"loss": 5.5826,
|
|
"mean_token_accuracy": 0.17275900691747664,
|
|
"num_tokens": 15342294.0,
|
|
"step": 6875
|
|
},
|
|
{
|
|
"entropy": 5.698135662078857,
|
|
"epoch": 0.7727298253495817,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004950659439318696,
|
|
"loss": 5.5901,
|
|
"mean_token_accuracy": 0.1722102403640747,
|
|
"num_tokens": 15352615.0,
|
|
"step": 6880
|
|
},
|
|
{
|
|
"entropy": 5.6508818626403805,
|
|
"epoch": 0.7732914022575391,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004950575785586952,
|
|
"loss": 5.6341,
|
|
"mean_token_accuracy": 0.168660968542099,
|
|
"num_tokens": 15364516.0,
|
|
"step": 6885
|
|
},
|
|
{
|
|
"entropy": 5.67797999382019,
|
|
"epoch": 0.7738529791654967,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004950492061788023,
|
|
"loss": 5.527,
|
|
"mean_token_accuracy": 0.173749241232872,
|
|
"num_tokens": 15374877.0,
|
|
"step": 6890
|
|
},
|
|
{
|
|
"entropy": 5.673302030563354,
|
|
"epoch": 0.7744145560734542,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004950408267924573,
|
|
"loss": 5.4688,
|
|
"mean_token_accuracy": 0.18849669992923737,
|
|
"num_tokens": 15385250.0,
|
|
"step": 6895
|
|
},
|
|
{
|
|
"entropy": 5.630706882476806,
|
|
"epoch": 0.7749761329814118,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004950324403999271,
|
|
"loss": 5.6217,
|
|
"mean_token_accuracy": 0.178818379342556,
|
|
"num_tokens": 15397074.0,
|
|
"step": 6900
|
|
},
|
|
{
|
|
"entropy": 5.6523487091064455,
|
|
"epoch": 0.7755377098893693,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004950240470014785,
|
|
"loss": 5.6633,
|
|
"mean_token_accuracy": 0.16847054213285445,
|
|
"num_tokens": 15408575.0,
|
|
"step": 6905
|
|
},
|
|
{
|
|
"entropy": 5.721060371398925,
|
|
"epoch": 0.7760992867973269,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004950156465973791,
|
|
"loss": 5.5786,
|
|
"mean_token_accuracy": 0.17714389264583588,
|
|
"num_tokens": 15419071.0,
|
|
"step": 6910
|
|
},
|
|
{
|
|
"entropy": 5.595917701721191,
|
|
"epoch": 0.7766608637052844,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.000495007239187896,
|
|
"loss": 5.4627,
|
|
"mean_token_accuracy": 0.1753948897123337,
|
|
"num_tokens": 15430137.0,
|
|
"step": 6915
|
|
},
|
|
{
|
|
"entropy": 5.549996185302734,
|
|
"epoch": 0.777222440613242,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004949988247732972,
|
|
"loss": 5.536,
|
|
"mean_token_accuracy": 0.18008177876472473,
|
|
"num_tokens": 15440661.0,
|
|
"step": 6920
|
|
},
|
|
{
|
|
"entropy": 5.577071666717529,
|
|
"epoch": 0.7777840175211995,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004949904033538504,
|
|
"loss": 5.5443,
|
|
"mean_token_accuracy": 0.18011982291936873,
|
|
"num_tokens": 15451909.0,
|
|
"step": 6925
|
|
},
|
|
{
|
|
"entropy": 5.744392728805542,
|
|
"epoch": 0.7783455944291571,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.000494981974929824,
|
|
"loss": 5.6133,
|
|
"mean_token_accuracy": 0.17083452343940736,
|
|
"num_tokens": 15462244.0,
|
|
"step": 6930
|
|
},
|
|
{
|
|
"entropy": 5.644606256484986,
|
|
"epoch": 0.7789071713371146,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.000494973539501486,
|
|
"loss": 5.6585,
|
|
"mean_token_accuracy": 0.17281380891799927,
|
|
"num_tokens": 15473284.0,
|
|
"step": 6935
|
|
},
|
|
{
|
|
"entropy": 5.587286949157715,
|
|
"epoch": 0.7794687482450722,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004949650970691052,
|
|
"loss": 5.5591,
|
|
"mean_token_accuracy": 0.1845861554145813,
|
|
"num_tokens": 15484964.0,
|
|
"step": 6940
|
|
},
|
|
{
|
|
"entropy": 5.646401405334473,
|
|
"epoch": 0.7800303251530297,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004949566476329505,
|
|
"loss": 5.5877,
|
|
"mean_token_accuracy": 0.17619993090629577,
|
|
"num_tokens": 15495922.0,
|
|
"step": 6945
|
|
},
|
|
{
|
|
"entropy": 5.780960130691528,
|
|
"epoch": 0.7805919020609873,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004949481911932908,
|
|
"loss": 5.6492,
|
|
"mean_token_accuracy": 0.17256713807582855,
|
|
"num_tokens": 15507173.0,
|
|
"step": 6950
|
|
},
|
|
{
|
|
"entropy": 5.70377368927002,
|
|
"epoch": 0.7811534789689448,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004949397277503954,
|
|
"loss": 5.6209,
|
|
"mean_token_accuracy": 0.17474339306354522,
|
|
"num_tokens": 15517720.0,
|
|
"step": 6955
|
|
},
|
|
{
|
|
"entropy": 5.71235990524292,
|
|
"epoch": 0.7817150558769024,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004949312573045338,
|
|
"loss": 5.6394,
|
|
"mean_token_accuracy": 0.1703775092959404,
|
|
"num_tokens": 15529482.0,
|
|
"step": 6960
|
|
},
|
|
{
|
|
"entropy": 5.76483187675476,
|
|
"epoch": 0.7822766327848599,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004949227798559757,
|
|
"loss": 5.6429,
|
|
"mean_token_accuracy": 0.1658545657992363,
|
|
"num_tokens": 15540522.0,
|
|
"step": 6965
|
|
},
|
|
{
|
|
"entropy": 5.700478982925415,
|
|
"epoch": 0.7828382096928175,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004949142954049909,
|
|
"loss": 5.6267,
|
|
"mean_token_accuracy": 0.17000363171100616,
|
|
"num_tokens": 15552443.0,
|
|
"step": 6970
|
|
},
|
|
{
|
|
"entropy": 5.766734600067139,
|
|
"epoch": 0.783399786600775,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004949058039518496,
|
|
"loss": 5.664,
|
|
"mean_token_accuracy": 0.17442309558391572,
|
|
"num_tokens": 15563418.0,
|
|
"step": 6975
|
|
},
|
|
{
|
|
"entropy": 5.721600914001465,
|
|
"epoch": 0.7839613635087325,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004948973054968222,
|
|
"loss": 5.6809,
|
|
"mean_token_accuracy": 0.1688017174601555,
|
|
"num_tokens": 15574301.0,
|
|
"step": 6980
|
|
},
|
|
{
|
|
"entropy": 5.780105543136597,
|
|
"epoch": 0.78452294041669,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004948888000401794,
|
|
"loss": 5.5844,
|
|
"mean_token_accuracy": 0.1704667940735817,
|
|
"num_tokens": 15585125.0,
|
|
"step": 6985
|
|
},
|
|
{
|
|
"entropy": 5.7562014102935795,
|
|
"epoch": 0.7850845173246476,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004948802875821918,
|
|
"loss": 5.6937,
|
|
"mean_token_accuracy": 0.17066754549741744,
|
|
"num_tokens": 15595822.0,
|
|
"step": 6990
|
|
},
|
|
{
|
|
"entropy": 5.5500236511230465,
|
|
"epoch": 0.7856460942326051,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004948717681231308,
|
|
"loss": 5.5279,
|
|
"mean_token_accuracy": 0.17664736062288283,
|
|
"num_tokens": 15606835.0,
|
|
"step": 6995
|
|
},
|
|
{
|
|
"entropy": 5.632187032699585,
|
|
"epoch": 0.7862076711405627,
|
|
"grad_norm": 3.125,
|
|
"learning_rate": 0.0004948632416632672,
|
|
"loss": 5.6124,
|
|
"mean_token_accuracy": 0.17274107187986373,
|
|
"num_tokens": 15617287.0,
|
|
"step": 7000
|
|
},
|
|
{
|
|
"entropy": 5.8710390567779545,
|
|
"epoch": 0.7867692480485202,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004948547082028728,
|
|
"loss": 5.6573,
|
|
"mean_token_accuracy": 0.16424071788787842,
|
|
"num_tokens": 15628440.0,
|
|
"step": 7005
|
|
},
|
|
{
|
|
"entropy": 5.7740159034729,
|
|
"epoch": 0.7873308249564778,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004948461677422193,
|
|
"loss": 5.7659,
|
|
"mean_token_accuracy": 0.16086588203907012,
|
|
"num_tokens": 15640677.0,
|
|
"step": 7010
|
|
},
|
|
{
|
|
"entropy": 5.702903985977173,
|
|
"epoch": 0.7878924018644353,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004948376202815785,
|
|
"loss": 5.5799,
|
|
"mean_token_accuracy": 0.17863162457942963,
|
|
"num_tokens": 15651941.0,
|
|
"step": 7015
|
|
},
|
|
{
|
|
"entropy": 5.643584585189819,
|
|
"epoch": 0.7884539787723929,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004948290658212225,
|
|
"loss": 5.5872,
|
|
"mean_token_accuracy": 0.1744334802031517,
|
|
"num_tokens": 15663513.0,
|
|
"step": 7020
|
|
},
|
|
{
|
|
"entropy": 5.612797451019287,
|
|
"epoch": 0.7890155556803504,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004948205043614239,
|
|
"loss": 5.5694,
|
|
"mean_token_accuracy": 0.17362559586763382,
|
|
"num_tokens": 15675548.0,
|
|
"step": 7025
|
|
},
|
|
{
|
|
"entropy": 5.7275231838226315,
|
|
"epoch": 0.789577132588308,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004948119359024551,
|
|
"loss": 5.6234,
|
|
"mean_token_accuracy": 0.17916473597288132,
|
|
"num_tokens": 15685365.0,
|
|
"step": 7030
|
|
},
|
|
{
|
|
"entropy": 5.686577701568604,
|
|
"epoch": 0.7901387094962655,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004948033604445891,
|
|
"loss": 5.6126,
|
|
"mean_token_accuracy": 0.17018286287784576,
|
|
"num_tokens": 15696112.0,
|
|
"step": 7035
|
|
},
|
|
{
|
|
"entropy": 5.621775579452515,
|
|
"epoch": 0.7907002864042231,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004947947779880988,
|
|
"loss": 5.5484,
|
|
"mean_token_accuracy": 0.1771180063486099,
|
|
"num_tokens": 15707414.0,
|
|
"step": 7040
|
|
},
|
|
{
|
|
"entropy": 5.734884214401245,
|
|
"epoch": 0.7912618633121806,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004947861885332576,
|
|
"loss": 5.6507,
|
|
"mean_token_accuracy": 0.17650367319583893,
|
|
"num_tokens": 15719077.0,
|
|
"step": 7045
|
|
},
|
|
{
|
|
"entropy": 5.712475728988648,
|
|
"epoch": 0.7918234402201382,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004947775920803388,
|
|
"loss": 5.6426,
|
|
"mean_token_accuracy": 0.1715145543217659,
|
|
"num_tokens": 15730497.0,
|
|
"step": 7050
|
|
},
|
|
{
|
|
"entropy": 5.666735076904297,
|
|
"epoch": 0.7923850171280957,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004947689886296162,
|
|
"loss": 5.5464,
|
|
"mean_token_accuracy": 0.1741068556904793,
|
|
"num_tokens": 15741724.0,
|
|
"step": 7055
|
|
},
|
|
{
|
|
"entropy": 5.691272640228272,
|
|
"epoch": 0.7929465940360533,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.000494760378181364,
|
|
"loss": 5.627,
|
|
"mean_token_accuracy": 0.1703273355960846,
|
|
"num_tokens": 15751868.0,
|
|
"step": 7060
|
|
},
|
|
{
|
|
"entropy": 5.659696960449219,
|
|
"epoch": 0.7935081709440108,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004947517607358559,
|
|
"loss": 5.6401,
|
|
"mean_token_accuracy": 0.16680581122636795,
|
|
"num_tokens": 15762783.0,
|
|
"step": 7065
|
|
},
|
|
{
|
|
"entropy": 5.722996759414673,
|
|
"epoch": 0.7940697478519684,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004947431362933666,
|
|
"loss": 5.6208,
|
|
"mean_token_accuracy": 0.17095878720283508,
|
|
"num_tokens": 15774155.0,
|
|
"step": 7070
|
|
},
|
|
{
|
|
"entropy": 5.82449369430542,
|
|
"epoch": 0.7946313247599258,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004947345048541706,
|
|
"loss": 5.6404,
|
|
"mean_token_accuracy": 0.1689218834042549,
|
|
"num_tokens": 15785034.0,
|
|
"step": 7075
|
|
},
|
|
{
|
|
"entropy": 5.595941543579102,
|
|
"epoch": 0.7951929016678834,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004947258664185427,
|
|
"loss": 5.5844,
|
|
"mean_token_accuracy": 0.17003095299005508,
|
|
"num_tokens": 15795959.0,
|
|
"step": 7080
|
|
},
|
|
{
|
|
"entropy": 5.658422422409058,
|
|
"epoch": 0.7957544785758409,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004947172209867581,
|
|
"loss": 5.4638,
|
|
"mean_token_accuracy": 0.18406398892402648,
|
|
"num_tokens": 15805561.0,
|
|
"step": 7085
|
|
},
|
|
{
|
|
"entropy": 5.713173961639404,
|
|
"epoch": 0.7963160554837985,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004947085685590919,
|
|
"loss": 5.5692,
|
|
"mean_token_accuracy": 0.17338566929101945,
|
|
"num_tokens": 15816883.0,
|
|
"step": 7090
|
|
},
|
|
{
|
|
"entropy": 5.580157470703125,
|
|
"epoch": 0.796877632391756,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004946999091358196,
|
|
"loss": 5.5261,
|
|
"mean_token_accuracy": 0.17477951496839522,
|
|
"num_tokens": 15827753.0,
|
|
"step": 7095
|
|
},
|
|
{
|
|
"entropy": 5.665834951400757,
|
|
"epoch": 0.7974392092997136,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.000494691242717217,
|
|
"loss": 5.6449,
|
|
"mean_token_accuracy": 0.1671520546078682,
|
|
"num_tokens": 15840346.0,
|
|
"step": 7100
|
|
},
|
|
{
|
|
"entropy": 5.718213987350464,
|
|
"epoch": 0.7980007862076711,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004946825693035601,
|
|
"loss": 5.5982,
|
|
"mean_token_accuracy": 0.17325277775526046,
|
|
"num_tokens": 15851036.0,
|
|
"step": 7105
|
|
},
|
|
{
|
|
"entropy": 5.6614522457122805,
|
|
"epoch": 0.7985623631156287,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000494673888895125,
|
|
"loss": 5.5575,
|
|
"mean_token_accuracy": 0.16837076246738433,
|
|
"num_tokens": 15863154.0,
|
|
"step": 7110
|
|
},
|
|
{
|
|
"entropy": 5.720604181289673,
|
|
"epoch": 0.7991239400235862,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004946652014921881,
|
|
"loss": 5.6639,
|
|
"mean_token_accuracy": 0.16528711915016175,
|
|
"num_tokens": 15874543.0,
|
|
"step": 7115
|
|
},
|
|
{
|
|
"entropy": 5.706193590164185,
|
|
"epoch": 0.7996855169315438,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004946565070950259,
|
|
"loss": 5.5968,
|
|
"mean_token_accuracy": 0.17797693461179734,
|
|
"num_tokens": 15886221.0,
|
|
"step": 7120
|
|
},
|
|
{
|
|
"entropy": 5.709640121459961,
|
|
"epoch": 0.8002470938395013,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004946478057039153,
|
|
"loss": 5.6053,
|
|
"mean_token_accuracy": 0.17097271531820296,
|
|
"num_tokens": 15897602.0,
|
|
"step": 7125
|
|
},
|
|
{
|
|
"entropy": 5.709883308410644,
|
|
"epoch": 0.8008086707474589,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004946390973191335,
|
|
"loss": 5.6058,
|
|
"mean_token_accuracy": 0.171327905356884,
|
|
"num_tokens": 15908030.0,
|
|
"step": 7130
|
|
},
|
|
{
|
|
"entropy": 5.781009912490845,
|
|
"epoch": 0.8013702476554164,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004946303819409575,
|
|
"loss": 5.6467,
|
|
"mean_token_accuracy": 0.17163679897785186,
|
|
"num_tokens": 15918341.0,
|
|
"step": 7135
|
|
},
|
|
{
|
|
"entropy": 5.623637104034424,
|
|
"epoch": 0.801931824563374,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004946216595696652,
|
|
"loss": 5.6264,
|
|
"mean_token_accuracy": 0.17764584273099898,
|
|
"num_tokens": 15929144.0,
|
|
"step": 7140
|
|
},
|
|
{
|
|
"entropy": 5.7017920970916744,
|
|
"epoch": 0.8024934014713315,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004946129302055338,
|
|
"loss": 5.5534,
|
|
"mean_token_accuracy": 0.1748026505112648,
|
|
"num_tokens": 15940013.0,
|
|
"step": 7145
|
|
},
|
|
{
|
|
"entropy": 5.746622562408447,
|
|
"epoch": 0.8030549783792891,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004946041938488417,
|
|
"loss": 5.6151,
|
|
"mean_token_accuracy": 0.17079914808273317,
|
|
"num_tokens": 15950680.0,
|
|
"step": 7150
|
|
},
|
|
{
|
|
"entropy": 5.644058322906494,
|
|
"epoch": 0.8036165552872466,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004945954504998668,
|
|
"loss": 5.6012,
|
|
"mean_token_accuracy": 0.17851518392562865,
|
|
"num_tokens": 15961462.0,
|
|
"step": 7155
|
|
},
|
|
{
|
|
"entropy": 5.67428412437439,
|
|
"epoch": 0.8041781321952042,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004945867001588877,
|
|
"loss": 5.5232,
|
|
"mean_token_accuracy": 0.17970660775899888,
|
|
"num_tokens": 15972788.0,
|
|
"step": 7160
|
|
},
|
|
{
|
|
"entropy": 5.655921173095703,
|
|
"epoch": 0.8047397091031617,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004945779428261827,
|
|
"loss": 5.5807,
|
|
"mean_token_accuracy": 0.17457723915576934,
|
|
"num_tokens": 15983244.0,
|
|
"step": 7165
|
|
},
|
|
{
|
|
"entropy": 5.596137046813965,
|
|
"epoch": 0.8053012860111193,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.000494569178502031,
|
|
"loss": 5.6844,
|
|
"mean_token_accuracy": 0.16675399839878083,
|
|
"num_tokens": 15994325.0,
|
|
"step": 7170
|
|
},
|
|
{
|
|
"entropy": 5.77509298324585,
|
|
"epoch": 0.8058628629190767,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004945604071867114,
|
|
"loss": 5.6754,
|
|
"mean_token_accuracy": 0.1712609902024269,
|
|
"num_tokens": 16005237.0,
|
|
"step": 7175
|
|
},
|
|
{
|
|
"entropy": 5.679333925247192,
|
|
"epoch": 0.8064244398270343,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004945516288805035,
|
|
"loss": 5.5028,
|
|
"mean_token_accuracy": 0.180667944252491,
|
|
"num_tokens": 16015943.0,
|
|
"step": 7180
|
|
},
|
|
{
|
|
"entropy": 5.576353931427002,
|
|
"epoch": 0.8069860167349918,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004945428435836864,
|
|
"loss": 5.5114,
|
|
"mean_token_accuracy": 0.17413717806339263,
|
|
"num_tokens": 16026727.0,
|
|
"step": 7185
|
|
},
|
|
{
|
|
"entropy": 5.622631072998047,
|
|
"epoch": 0.8075475936429494,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004945340512965401,
|
|
"loss": 5.5532,
|
|
"mean_token_accuracy": 0.16718171387910843,
|
|
"num_tokens": 16039021.0,
|
|
"step": 7190
|
|
},
|
|
{
|
|
"entropy": 5.626061344146729,
|
|
"epoch": 0.8081091705509069,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004945252520193443,
|
|
"loss": 5.5031,
|
|
"mean_token_accuracy": 0.17845340073108673,
|
|
"num_tokens": 16050312.0,
|
|
"step": 7195
|
|
},
|
|
{
|
|
"entropy": 5.668435192108154,
|
|
"epoch": 0.8086707474588645,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004945164457523795,
|
|
"loss": 5.4561,
|
|
"mean_token_accuracy": 0.18104152232408524,
|
|
"num_tokens": 16060009.0,
|
|
"step": 7200
|
|
},
|
|
{
|
|
"entropy": 5.589456796646118,
|
|
"epoch": 0.809232324366822,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004945076324959258,
|
|
"loss": 5.5798,
|
|
"mean_token_accuracy": 0.17277259826660157,
|
|
"num_tokens": 16072025.0,
|
|
"step": 7205
|
|
},
|
|
{
|
|
"entropy": 5.730244207382202,
|
|
"epoch": 0.8097939012747796,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004944988122502641,
|
|
"loss": 5.6001,
|
|
"mean_token_accuracy": 0.17296409606933594,
|
|
"num_tokens": 16083229.0,
|
|
"step": 7210
|
|
},
|
|
{
|
|
"entropy": 5.6034921169281,
|
|
"epoch": 0.8103554781827371,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.000494489985015675,
|
|
"loss": 5.4848,
|
|
"mean_token_accuracy": 0.17338486462831498,
|
|
"num_tokens": 16094936.0,
|
|
"step": 7215
|
|
},
|
|
{
|
|
"entropy": 5.629249382019043,
|
|
"epoch": 0.8109170550906947,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004944811507924396,
|
|
"loss": 5.5966,
|
|
"mean_token_accuracy": 0.17871529906988143,
|
|
"num_tokens": 16106182.0,
|
|
"step": 7220
|
|
},
|
|
{
|
|
"entropy": 5.612615060806275,
|
|
"epoch": 0.8114786319986522,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004944723095808393,
|
|
"loss": 5.5095,
|
|
"mean_token_accuracy": 0.18377710580825807,
|
|
"num_tokens": 16117006.0,
|
|
"step": 7225
|
|
},
|
|
{
|
|
"entropy": 5.6077577590942385,
|
|
"epoch": 0.8120402089066098,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004944634613811555,
|
|
"loss": 5.5422,
|
|
"mean_token_accuracy": 0.1714983433485031,
|
|
"num_tokens": 16128892.0,
|
|
"step": 7230
|
|
},
|
|
{
|
|
"entropy": 5.727390718460083,
|
|
"epoch": 0.8126017858145673,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00049445460619367,
|
|
"loss": 5.6503,
|
|
"mean_token_accuracy": 0.17741401940584184,
|
|
"num_tokens": 16139953.0,
|
|
"step": 7235
|
|
},
|
|
{
|
|
"entropy": 5.771072483062744,
|
|
"epoch": 0.8131633627225249,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004944457440186648,
|
|
"loss": 5.6187,
|
|
"mean_token_accuracy": 0.1663561910390854,
|
|
"num_tokens": 16150103.0,
|
|
"step": 7240
|
|
},
|
|
{
|
|
"entropy": 5.621788215637207,
|
|
"epoch": 0.8137249396304824,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004944368748564219,
|
|
"loss": 5.7002,
|
|
"mean_token_accuracy": 0.167274634540081,
|
|
"num_tokens": 16161666.0,
|
|
"step": 7245
|
|
},
|
|
{
|
|
"entropy": 5.6615965366363525,
|
|
"epoch": 0.81428651653844,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004944279987072238,
|
|
"loss": 5.6388,
|
|
"mean_token_accuracy": 0.16890483051538469,
|
|
"num_tokens": 16172524.0,
|
|
"step": 7250
|
|
},
|
|
{
|
|
"entropy": 5.7637022018432615,
|
|
"epoch": 0.8148480934463975,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004944191155713531,
|
|
"loss": 5.5756,
|
|
"mean_token_accuracy": 0.1765427216887474,
|
|
"num_tokens": 16183023.0,
|
|
"step": 7255
|
|
},
|
|
{
|
|
"entropy": 5.686658239364624,
|
|
"epoch": 0.8154096703543551,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004944102254490928,
|
|
"loss": 5.5918,
|
|
"mean_token_accuracy": 0.17796089202165605,
|
|
"num_tokens": 16193504.0,
|
|
"step": 7260
|
|
},
|
|
{
|
|
"entropy": 5.630303049087525,
|
|
"epoch": 0.8159712472623126,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004944013283407257,
|
|
"loss": 5.5496,
|
|
"mean_token_accuracy": 0.17709226608276368,
|
|
"num_tokens": 16204730.0,
|
|
"step": 7265
|
|
},
|
|
{
|
|
"entropy": 5.6650426387786865,
|
|
"epoch": 0.8165328241702701,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004943924242465352,
|
|
"loss": 5.5613,
|
|
"mean_token_accuracy": 0.1778118908405304,
|
|
"num_tokens": 16214496.0,
|
|
"step": 7270
|
|
},
|
|
{
|
|
"entropy": 5.608745145797729,
|
|
"epoch": 0.8170944010782276,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004943835131668049,
|
|
"loss": 5.5023,
|
|
"mean_token_accuracy": 0.18091920465230943,
|
|
"num_tokens": 16225494.0,
|
|
"step": 7275
|
|
},
|
|
{
|
|
"entropy": 5.569278240203857,
|
|
"epoch": 0.8176559779861852,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004943745951018184,
|
|
"loss": 5.4483,
|
|
"mean_token_accuracy": 0.17797216773033142,
|
|
"num_tokens": 16236385.0,
|
|
"step": 7280
|
|
},
|
|
{
|
|
"entropy": 5.640453624725342,
|
|
"epoch": 0.8182175548941427,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004943656700518597,
|
|
"loss": 5.6211,
|
|
"mean_token_accuracy": 0.1828884169459343,
|
|
"num_tokens": 16247300.0,
|
|
"step": 7285
|
|
},
|
|
{
|
|
"entropy": 5.715027952194214,
|
|
"epoch": 0.8187791318021003,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004943567380172129,
|
|
"loss": 5.6553,
|
|
"mean_token_accuracy": 0.17173643559217452,
|
|
"num_tokens": 16259326.0,
|
|
"step": 7290
|
|
},
|
|
{
|
|
"entropy": 5.711592769622802,
|
|
"epoch": 0.8193407087100578,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004943477989981627,
|
|
"loss": 5.6291,
|
|
"mean_token_accuracy": 0.17496313005685807,
|
|
"num_tokens": 16270559.0,
|
|
"step": 7295
|
|
},
|
|
{
|
|
"entropy": 5.681230926513672,
|
|
"epoch": 0.8199022856180154,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004943388529949933,
|
|
"loss": 5.6011,
|
|
"mean_token_accuracy": 0.16669342219829558,
|
|
"num_tokens": 16283120.0,
|
|
"step": 7300
|
|
},
|
|
{
|
|
"entropy": 5.798020315170288,
|
|
"epoch": 0.8204638625259729,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004943299000079899,
|
|
"loss": 5.6213,
|
|
"mean_token_accuracy": 0.17745826691389083,
|
|
"num_tokens": 16293449.0,
|
|
"step": 7305
|
|
},
|
|
{
|
|
"entropy": 5.665607500076294,
|
|
"epoch": 0.8210254394339305,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004943209400374373,
|
|
"loss": 5.6342,
|
|
"mean_token_accuracy": 0.16801470518112183,
|
|
"num_tokens": 16305144.0,
|
|
"step": 7310
|
|
},
|
|
{
|
|
"entropy": 5.592559432983398,
|
|
"epoch": 0.821587016341888,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.000494311973083621,
|
|
"loss": 5.4582,
|
|
"mean_token_accuracy": 0.17840937823057174,
|
|
"num_tokens": 16316728.0,
|
|
"step": 7315
|
|
},
|
|
{
|
|
"entropy": 5.7071305274963375,
|
|
"epoch": 0.8221485932498456,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004943029991468264,
|
|
"loss": 5.7375,
|
|
"mean_token_accuracy": 0.16938112676143646,
|
|
"num_tokens": 16329117.0,
|
|
"step": 7320
|
|
},
|
|
{
|
|
"entropy": 5.769921779632568,
|
|
"epoch": 0.8227101701578031,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004942940182273393,
|
|
"loss": 5.6999,
|
|
"mean_token_accuracy": 0.1706177443265915,
|
|
"num_tokens": 16341651.0,
|
|
"step": 7325
|
|
},
|
|
{
|
|
"entropy": 5.79766092300415,
|
|
"epoch": 0.8232717470657607,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004942850303254455,
|
|
"loss": 5.6691,
|
|
"mean_token_accuracy": 0.17348309159278869,
|
|
"num_tokens": 16353220.0,
|
|
"step": 7330
|
|
},
|
|
{
|
|
"entropy": 5.774486017227173,
|
|
"epoch": 0.8238333239737182,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004942760354414313,
|
|
"loss": 5.706,
|
|
"mean_token_accuracy": 0.1695014789700508,
|
|
"num_tokens": 16363748.0,
|
|
"step": 7335
|
|
},
|
|
{
|
|
"entropy": 5.521135091781616,
|
|
"epoch": 0.8243949008816758,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004942670335755831,
|
|
"loss": 5.3854,
|
|
"mean_token_accuracy": 0.18615321964025497,
|
|
"num_tokens": 16374086.0,
|
|
"step": 7340
|
|
},
|
|
{
|
|
"entropy": 5.6541694641113285,
|
|
"epoch": 0.8249564777896333,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004942580247281876,
|
|
"loss": 5.5564,
|
|
"mean_token_accuracy": 0.17574853003025054,
|
|
"num_tokens": 16384140.0,
|
|
"step": 7345
|
|
},
|
|
{
|
|
"entropy": 5.707195806503296,
|
|
"epoch": 0.8255180546975909,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004942490088995315,
|
|
"loss": 5.6636,
|
|
"mean_token_accuracy": 0.1692671984434128,
|
|
"num_tokens": 16395940.0,
|
|
"step": 7350
|
|
},
|
|
{
|
|
"entropy": 5.629947328567505,
|
|
"epoch": 0.8260796316055484,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004942399860899018,
|
|
"loss": 5.5087,
|
|
"mean_token_accuracy": 0.18015119284391404,
|
|
"num_tokens": 16406667.0,
|
|
"step": 7355
|
|
},
|
|
{
|
|
"entropy": 5.7489300727844235,
|
|
"epoch": 0.826641208513506,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004942309562995862,
|
|
"loss": 5.6606,
|
|
"mean_token_accuracy": 0.165461665391922,
|
|
"num_tokens": 16418621.0,
|
|
"step": 7360
|
|
},
|
|
{
|
|
"entropy": 5.661215448379517,
|
|
"epoch": 0.8272027854214634,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004942219195288716,
|
|
"loss": 5.5629,
|
|
"mean_token_accuracy": 0.1782558485865593,
|
|
"num_tokens": 16429576.0,
|
|
"step": 7365
|
|
},
|
|
{
|
|
"entropy": 5.675850677490234,
|
|
"epoch": 0.827764362329421,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004942128757780463,
|
|
"loss": 5.6791,
|
|
"mean_token_accuracy": 0.16648157685995102,
|
|
"num_tokens": 16441004.0,
|
|
"step": 7370
|
|
},
|
|
{
|
|
"entropy": 5.695897388458252,
|
|
"epoch": 0.8283259392373785,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004942038250473979,
|
|
"loss": 5.6208,
|
|
"mean_token_accuracy": 0.16576655954122543,
|
|
"num_tokens": 16452183.0,
|
|
"step": 7375
|
|
},
|
|
{
|
|
"entropy": 5.650100517272949,
|
|
"epoch": 0.8288875161453361,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004941947673372147,
|
|
"loss": 5.5744,
|
|
"mean_token_accuracy": 0.17556263953447343,
|
|
"num_tokens": 16463552.0,
|
|
"step": 7380
|
|
},
|
|
{
|
|
"entropy": 5.723178291320801,
|
|
"epoch": 0.8294490930532936,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004941857026477851,
|
|
"loss": 5.6099,
|
|
"mean_token_accuracy": 0.1799635797739029,
|
|
"num_tokens": 16474062.0,
|
|
"step": 7385
|
|
},
|
|
{
|
|
"entropy": 5.752410173416138,
|
|
"epoch": 0.8300106699612512,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004941766309793978,
|
|
"loss": 5.6976,
|
|
"mean_token_accuracy": 0.17354531735181808,
|
|
"num_tokens": 16487377.0,
|
|
"step": 7390
|
|
},
|
|
{
|
|
"entropy": 5.755760908126831,
|
|
"epoch": 0.8305722468692087,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004941675523323414,
|
|
"loss": 5.6332,
|
|
"mean_token_accuracy": 0.18097470849752426,
|
|
"num_tokens": 16499704.0,
|
|
"step": 7395
|
|
},
|
|
{
|
|
"entropy": 5.6458765983581545,
|
|
"epoch": 0.8311338237771663,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004941584667069052,
|
|
"loss": 5.6438,
|
|
"mean_token_accuracy": 0.17571662366390228,
|
|
"num_tokens": 16511954.0,
|
|
"step": 7400
|
|
},
|
|
{
|
|
"entropy": 5.5650115489959715,
|
|
"epoch": 0.8316954006851238,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004941493741033784,
|
|
"loss": 5.479,
|
|
"mean_token_accuracy": 0.1725131541490555,
|
|
"num_tokens": 16522602.0,
|
|
"step": 7405
|
|
},
|
|
{
|
|
"entropy": 5.740706253051758,
|
|
"epoch": 0.8322569775930814,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004941402745220507,
|
|
"loss": 5.6325,
|
|
"mean_token_accuracy": 0.16962281316518785,
|
|
"num_tokens": 16534233.0,
|
|
"step": 7410
|
|
},
|
|
{
|
|
"entropy": 5.7556068897247314,
|
|
"epoch": 0.8328185545010389,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004941311679632115,
|
|
"loss": 5.7121,
|
|
"mean_token_accuracy": 0.17037609368562698,
|
|
"num_tokens": 16546120.0,
|
|
"step": 7415
|
|
},
|
|
{
|
|
"entropy": 5.709545755386353,
|
|
"epoch": 0.8333801314089965,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.000494122054427151,
|
|
"loss": 5.5935,
|
|
"mean_token_accuracy": 0.1746015027165413,
|
|
"num_tokens": 16556830.0,
|
|
"step": 7420
|
|
},
|
|
{
|
|
"entropy": 5.644628953933716,
|
|
"epoch": 0.833941708316954,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004941129339141592,
|
|
"loss": 5.5573,
|
|
"mean_token_accuracy": 0.17804006040096282,
|
|
"num_tokens": 16567436.0,
|
|
"step": 7425
|
|
},
|
|
{
|
|
"entropy": 5.660109615325927,
|
|
"epoch": 0.8345032852249116,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004941038064245267,
|
|
"loss": 5.5257,
|
|
"mean_token_accuracy": 0.1747888594865799,
|
|
"num_tokens": 16577807.0,
|
|
"step": 7430
|
|
},
|
|
{
|
|
"entropy": 5.707765102386475,
|
|
"epoch": 0.8350648621328691,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.000494094671958544,
|
|
"loss": 5.6211,
|
|
"mean_token_accuracy": 0.17427547425031661,
|
|
"num_tokens": 16589745.0,
|
|
"step": 7435
|
|
},
|
|
{
|
|
"entropy": 5.779169940948487,
|
|
"epoch": 0.8356264390408267,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004940855305165019,
|
|
"loss": 5.6572,
|
|
"mean_token_accuracy": 0.17683361768722533,
|
|
"num_tokens": 16600727.0,
|
|
"step": 7440
|
|
},
|
|
{
|
|
"entropy": 5.661066389083862,
|
|
"epoch": 0.8361880159487842,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004940763820986916,
|
|
"loss": 5.5597,
|
|
"mean_token_accuracy": 0.17430997490882874,
|
|
"num_tokens": 16611091.0,
|
|
"step": 7445
|
|
},
|
|
{
|
|
"entropy": 5.582389688491821,
|
|
"epoch": 0.8367495928567418,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004940672267054044,
|
|
"loss": 5.5401,
|
|
"mean_token_accuracy": 0.17366688549518586,
|
|
"num_tokens": 16622550.0,
|
|
"step": 7450
|
|
},
|
|
{
|
|
"entropy": 5.662583303451538,
|
|
"epoch": 0.8373111697646993,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004940580643369316,
|
|
"loss": 5.5482,
|
|
"mean_token_accuracy": 0.17264899015426635,
|
|
"num_tokens": 16634243.0,
|
|
"step": 7455
|
|
},
|
|
{
|
|
"entropy": 5.637042140960693,
|
|
"epoch": 0.8378727466726568,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004940488949935651,
|
|
"loss": 5.5622,
|
|
"mean_token_accuracy": 0.1711127832531929,
|
|
"num_tokens": 16645266.0,
|
|
"step": 7460
|
|
},
|
|
{
|
|
"entropy": 5.686684608459473,
|
|
"epoch": 0.8384343235806143,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004940397186755968,
|
|
"loss": 5.5659,
|
|
"mean_token_accuracy": 0.17493919879198075,
|
|
"num_tokens": 16654365.0,
|
|
"step": 7465
|
|
},
|
|
{
|
|
"entropy": 5.683757019042969,
|
|
"epoch": 0.8389959004885719,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004940305353833191,
|
|
"loss": 5.5409,
|
|
"mean_token_accuracy": 0.18146927505731583,
|
|
"num_tokens": 16665251.0,
|
|
"step": 7470
|
|
},
|
|
{
|
|
"entropy": 5.676362562179565,
|
|
"epoch": 0.8395574773965294,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.000494021345117024,
|
|
"loss": 5.5938,
|
|
"mean_token_accuracy": 0.17529145181179046,
|
|
"num_tokens": 16676209.0,
|
|
"step": 7475
|
|
},
|
|
{
|
|
"entropy": 5.618336915969849,
|
|
"epoch": 0.840119054304487,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004940121478770044,
|
|
"loss": 5.5403,
|
|
"mean_token_accuracy": 0.17493845522403717,
|
|
"num_tokens": 16687213.0,
|
|
"step": 7480
|
|
},
|
|
{
|
|
"entropy": 5.630944728851318,
|
|
"epoch": 0.8406806312124445,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004940029436635531,
|
|
"loss": 5.5802,
|
|
"mean_token_accuracy": 0.18078657239675522,
|
|
"num_tokens": 16697920.0,
|
|
"step": 7485
|
|
},
|
|
{
|
|
"entropy": 5.627004718780517,
|
|
"epoch": 0.8412422081204021,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004939937324769631,
|
|
"loss": 5.5623,
|
|
"mean_token_accuracy": 0.17084627151489257,
|
|
"num_tokens": 16707815.0,
|
|
"step": 7490
|
|
},
|
|
{
|
|
"entropy": 5.632286834716797,
|
|
"epoch": 0.8418037850283596,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004939845143175276,
|
|
"loss": 5.4714,
|
|
"mean_token_accuracy": 0.1783707097172737,
|
|
"num_tokens": 16719221.0,
|
|
"step": 7495
|
|
},
|
|
{
|
|
"entropy": 5.597582626342773,
|
|
"epoch": 0.8423653619363172,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.0004939752891855404,
|
|
"loss": 5.5105,
|
|
"mean_token_accuracy": 0.17155885994434356,
|
|
"num_tokens": 16731741.0,
|
|
"step": 7500
|
|
},
|
|
{
|
|
"entropy": 5.613684749603271,
|
|
"epoch": 0.8429269388442747,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004939660570812951,
|
|
"loss": 5.5279,
|
|
"mean_token_accuracy": 0.18077764958143233,
|
|
"num_tokens": 16742795.0,
|
|
"step": 7505
|
|
},
|
|
{
|
|
"entropy": 5.636168098449707,
|
|
"epoch": 0.8434885157522323,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004939568180050855,
|
|
"loss": 5.524,
|
|
"mean_token_accuracy": 0.177456533908844,
|
|
"num_tokens": 16753139.0,
|
|
"step": 7510
|
|
},
|
|
{
|
|
"entropy": 5.653849363327026,
|
|
"epoch": 0.8440500926601898,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004939475719572059,
|
|
"loss": 5.5368,
|
|
"mean_token_accuracy": 0.17530351132154465,
|
|
"num_tokens": 16764246.0,
|
|
"step": 7515
|
|
},
|
|
{
|
|
"entropy": 5.70451078414917,
|
|
"epoch": 0.8446116695681474,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004939383189379507,
|
|
"loss": 5.6509,
|
|
"mean_token_accuracy": 0.1700239211320877,
|
|
"num_tokens": 16776039.0,
|
|
"step": 7520
|
|
},
|
|
{
|
|
"entropy": 5.718337535858154,
|
|
"epoch": 0.8451732464761049,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004939290589476145,
|
|
"loss": 5.6344,
|
|
"mean_token_accuracy": 0.17975671738386154,
|
|
"num_tokens": 16786979.0,
|
|
"step": 7525
|
|
},
|
|
{
|
|
"entropy": 5.705946540832519,
|
|
"epoch": 0.8457348233840625,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004939197919864922,
|
|
"loss": 5.6571,
|
|
"mean_token_accuracy": 0.17143665701150895,
|
|
"num_tokens": 16798113.0,
|
|
"step": 7530
|
|
},
|
|
{
|
|
"entropy": 5.6824140548706055,
|
|
"epoch": 0.84629640029202,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004939105180548788,
|
|
"loss": 5.5921,
|
|
"mean_token_accuracy": 0.17321973741054536,
|
|
"num_tokens": 16809072.0,
|
|
"step": 7535
|
|
},
|
|
{
|
|
"entropy": 5.61365909576416,
|
|
"epoch": 0.8468579771999776,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004939012371530696,
|
|
"loss": 5.3964,
|
|
"mean_token_accuracy": 0.17975719422101974,
|
|
"num_tokens": 16819548.0,
|
|
"step": 7540
|
|
},
|
|
{
|
|
"entropy": 5.733366680145264,
|
|
"epoch": 0.8474195541079351,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004938919492813601,
|
|
"loss": 5.7082,
|
|
"mean_token_accuracy": 0.16560092866420745,
|
|
"num_tokens": 16831935.0,
|
|
"step": 7545
|
|
},
|
|
{
|
|
"entropy": 5.675737428665161,
|
|
"epoch": 0.8479811310158927,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004938826544400461,
|
|
"loss": 5.604,
|
|
"mean_token_accuracy": 0.17931524962186812,
|
|
"num_tokens": 16842961.0,
|
|
"step": 7550
|
|
},
|
|
{
|
|
"entropy": 5.6335454940795895,
|
|
"epoch": 0.8485427079238502,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004938733526294234,
|
|
"loss": 5.5092,
|
|
"mean_token_accuracy": 0.17333014458417892,
|
|
"num_tokens": 16854392.0,
|
|
"step": 7555
|
|
},
|
|
{
|
|
"entropy": 5.620349311828614,
|
|
"epoch": 0.8491042848318077,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004938640438497883,
|
|
"loss": 5.5988,
|
|
"mean_token_accuracy": 0.16811076998710633,
|
|
"num_tokens": 16865443.0,
|
|
"step": 7560
|
|
},
|
|
{
|
|
"entropy": 5.677863216400146,
|
|
"epoch": 0.8496658617397652,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004938547281014372,
|
|
"loss": 5.5517,
|
|
"mean_token_accuracy": 0.17474559247493743,
|
|
"num_tokens": 16876854.0,
|
|
"step": 7565
|
|
},
|
|
{
|
|
"entropy": 5.7703766345977785,
|
|
"epoch": 0.8502274386477228,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004938454053846666,
|
|
"loss": 5.6388,
|
|
"mean_token_accuracy": 0.1716684192419052,
|
|
"num_tokens": 16888823.0,
|
|
"step": 7570
|
|
},
|
|
{
|
|
"entropy": 5.61264853477478,
|
|
"epoch": 0.8507890155556803,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.0004938360756997735,
|
|
"loss": 5.565,
|
|
"mean_token_accuracy": 0.1738715797662735,
|
|
"num_tokens": 16898807.0,
|
|
"step": 7575
|
|
},
|
|
{
|
|
"entropy": 5.690545082092285,
|
|
"epoch": 0.8513505924636379,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.0004938267390470547,
|
|
"loss": 5.6812,
|
|
"mean_token_accuracy": 0.16348067820072174,
|
|
"num_tokens": 16911258.0,
|
|
"step": 7580
|
|
},
|
|
{
|
|
"entropy": 5.783576726913452,
|
|
"epoch": 0.8519121693715954,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004938173954268079,
|
|
"loss": 5.6417,
|
|
"mean_token_accuracy": 0.17234276682138444,
|
|
"num_tokens": 16922557.0,
|
|
"step": 7585
|
|
},
|
|
{
|
|
"entropy": 5.723300170898438,
|
|
"epoch": 0.852473746279553,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004938080448393302,
|
|
"loss": 5.66,
|
|
"mean_token_accuracy": 0.16851891279220582,
|
|
"num_tokens": 16935330.0,
|
|
"step": 7590
|
|
},
|
|
{
|
|
"entropy": 5.723967742919922,
|
|
"epoch": 0.8530353231875105,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004937986872849195,
|
|
"loss": 5.5626,
|
|
"mean_token_accuracy": 0.1776669666171074,
|
|
"num_tokens": 16945361.0,
|
|
"step": 7595
|
|
},
|
|
{
|
|
"entropy": 5.565654373168945,
|
|
"epoch": 0.8535969000954681,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004937893227638738,
|
|
"loss": 5.4383,
|
|
"mean_token_accuracy": 0.18152663558721543,
|
|
"num_tokens": 16955363.0,
|
|
"step": 7600
|
|
},
|
|
{
|
|
"entropy": 5.56234769821167,
|
|
"epoch": 0.8541584770034256,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004937799512764912,
|
|
"loss": 5.5148,
|
|
"mean_token_accuracy": 0.17852590829133988,
|
|
"num_tokens": 16965267.0,
|
|
"step": 7605
|
|
},
|
|
{
|
|
"entropy": 5.671128654479981,
|
|
"epoch": 0.8547200539113832,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.00049377057282307,
|
|
"loss": 5.7321,
|
|
"mean_token_accuracy": 0.17176787555217743,
|
|
"num_tokens": 16977528.0,
|
|
"step": 7610
|
|
},
|
|
{
|
|
"entropy": 5.715606927871704,
|
|
"epoch": 0.8552816308193407,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.000493761187403909,
|
|
"loss": 5.5643,
|
|
"mean_token_accuracy": 0.17219118773937225,
|
|
"num_tokens": 16987326.0,
|
|
"step": 7615
|
|
},
|
|
{
|
|
"entropy": 5.799017238616943,
|
|
"epoch": 0.8558432077272983,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.000493751795019307,
|
|
"loss": 5.6114,
|
|
"mean_token_accuracy": 0.1744072198867798,
|
|
"num_tokens": 16999127.0,
|
|
"step": 7620
|
|
},
|
|
{
|
|
"entropy": 5.582177782058716,
|
|
"epoch": 0.8564047846352558,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004937423956695629,
|
|
"loss": 5.5232,
|
|
"mean_token_accuracy": 0.18371396213769914,
|
|
"num_tokens": 17009929.0,
|
|
"step": 7625
|
|
},
|
|
{
|
|
"entropy": 5.713424921035767,
|
|
"epoch": 0.8569663615432134,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004937329893549762,
|
|
"loss": 5.6514,
|
|
"mean_token_accuracy": 0.17402349263429642,
|
|
"num_tokens": 17020909.0,
|
|
"step": 7630
|
|
},
|
|
{
|
|
"entropy": 5.744926929473877,
|
|
"epoch": 0.8575279384511709,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004937235760758462,
|
|
"loss": 5.5807,
|
|
"mean_token_accuracy": 0.17321668565273285,
|
|
"num_tokens": 17031358.0,
|
|
"step": 7635
|
|
},
|
|
{
|
|
"entropy": 5.654985761642456,
|
|
"epoch": 0.8580895153591285,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004937141558324726,
|
|
"loss": 5.6242,
|
|
"mean_token_accuracy": 0.17349520176649094,
|
|
"num_tokens": 17042566.0,
|
|
"step": 7640
|
|
},
|
|
{
|
|
"entropy": 5.677562236785889,
|
|
"epoch": 0.858651092267086,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004937047286251556,
|
|
"loss": 5.6472,
|
|
"mean_token_accuracy": 0.16312987059354783,
|
|
"num_tokens": 17054998.0,
|
|
"step": 7645
|
|
},
|
|
{
|
|
"entropy": 5.6565553665161135,
|
|
"epoch": 0.8592126691750436,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.0004936952944541952,
|
|
"loss": 5.512,
|
|
"mean_token_accuracy": 0.17477733939886092,
|
|
"num_tokens": 17064876.0,
|
|
"step": 7650
|
|
},
|
|
{
|
|
"entropy": 5.647423267364502,
|
|
"epoch": 0.859774246083001,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004936858533198917,
|
|
"loss": 5.5621,
|
|
"mean_token_accuracy": 0.17949966639280318,
|
|
"num_tokens": 17075310.0,
|
|
"step": 7655
|
|
},
|
|
{
|
|
"entropy": 5.519606304168701,
|
|
"epoch": 0.8603358229909586,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.000493676405222546,
|
|
"loss": 5.4676,
|
|
"mean_token_accuracy": 0.17772774249315262,
|
|
"num_tokens": 17086023.0,
|
|
"step": 7660
|
|
},
|
|
{
|
|
"entropy": 5.5962433338165285,
|
|
"epoch": 0.8608973998989161,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004936669501624586,
|
|
"loss": 5.5539,
|
|
"mean_token_accuracy": 0.17585509717464448,
|
|
"num_tokens": 17097554.0,
|
|
"step": 7665
|
|
},
|
|
{
|
|
"entropy": 5.8958173274993895,
|
|
"epoch": 0.8614589768068737,
|
|
"grad_norm": 6.15625,
|
|
"learning_rate": 0.0004936574881399308,
|
|
"loss": 5.6789,
|
|
"mean_token_accuracy": 0.17030972838401795,
|
|
"num_tokens": 17108890.0,
|
|
"step": 7670
|
|
},
|
|
{
|
|
"entropy": 5.694438219070435,
|
|
"epoch": 0.8620205537148312,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004936480191552637,
|
|
"loss": 5.5134,
|
|
"mean_token_accuracy": 0.17637402266263963,
|
|
"num_tokens": 17120651.0,
|
|
"step": 7675
|
|
},
|
|
{
|
|
"entropy": 5.666385555267334,
|
|
"epoch": 0.8625821306227888,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004936385432087589,
|
|
"loss": 5.651,
|
|
"mean_token_accuracy": 0.17565001398324967,
|
|
"num_tokens": 17131306.0,
|
|
"step": 7680
|
|
},
|
|
{
|
|
"entropy": 5.812044906616211,
|
|
"epoch": 0.8631437075307463,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004936290603007181,
|
|
"loss": 5.798,
|
|
"mean_token_accuracy": 0.16602026224136351,
|
|
"num_tokens": 17142779.0,
|
|
"step": 7685
|
|
},
|
|
{
|
|
"entropy": 5.860309505462647,
|
|
"epoch": 0.8637052844387039,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004936195704314432,
|
|
"loss": 5.6687,
|
|
"mean_token_accuracy": 0.18110954910516738,
|
|
"num_tokens": 17154992.0,
|
|
"step": 7690
|
|
},
|
|
{
|
|
"entropy": 5.662728500366211,
|
|
"epoch": 0.8642668613466614,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004936100736012363,
|
|
"loss": 5.6427,
|
|
"mean_token_accuracy": 0.17859661132097243,
|
|
"num_tokens": 17166089.0,
|
|
"step": 7695
|
|
},
|
|
{
|
|
"entropy": 5.610977554321289,
|
|
"epoch": 0.864828438254619,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004936005698104,
|
|
"loss": 5.5468,
|
|
"mean_token_accuracy": 0.1707144245505333,
|
|
"num_tokens": 17175691.0,
|
|
"step": 7700
|
|
},
|
|
{
|
|
"entropy": 5.6774708271026615,
|
|
"epoch": 0.8653900151625765,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004935910590592367,
|
|
"loss": 5.602,
|
|
"mean_token_accuracy": 0.16899661272764205,
|
|
"num_tokens": 17186466.0,
|
|
"step": 7705
|
|
},
|
|
{
|
|
"entropy": 5.582030820846557,
|
|
"epoch": 0.8659515920705341,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004935815413480494,
|
|
"loss": 5.3873,
|
|
"mean_token_accuracy": 0.18827227801084517,
|
|
"num_tokens": 17198520.0,
|
|
"step": 7710
|
|
},
|
|
{
|
|
"entropy": 5.670034170150757,
|
|
"epoch": 0.8665131689784916,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.000493572016677141,
|
|
"loss": 5.6234,
|
|
"mean_token_accuracy": 0.16890666335821153,
|
|
"num_tokens": 17210496.0,
|
|
"step": 7715
|
|
},
|
|
{
|
|
"entropy": 5.68838415145874,
|
|
"epoch": 0.8670747458864492,
|
|
"grad_norm": 3.328125,
|
|
"learning_rate": 0.0004935624850468148,
|
|
"loss": 5.6152,
|
|
"mean_token_accuracy": 0.17695807665586472,
|
|
"num_tokens": 17221631.0,
|
|
"step": 7720
|
|
},
|
|
{
|
|
"entropy": 5.682717370986938,
|
|
"epoch": 0.8676363227944067,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004935529464573742,
|
|
"loss": 5.65,
|
|
"mean_token_accuracy": 0.16548071503639222,
|
|
"num_tokens": 17233316.0,
|
|
"step": 7725
|
|
},
|
|
{
|
|
"entropy": 5.678200769424438,
|
|
"epoch": 0.8681978997023643,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004935434009091232,
|
|
"loss": 5.5573,
|
|
"mean_token_accuracy": 0.1785666510462761,
|
|
"num_tokens": 17245761.0,
|
|
"step": 7730
|
|
},
|
|
{
|
|
"entropy": 5.697708415985107,
|
|
"epoch": 0.8687594766103218,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004935338484023655,
|
|
"loss": 5.5596,
|
|
"mean_token_accuracy": 0.1804763749241829,
|
|
"num_tokens": 17255007.0,
|
|
"step": 7735
|
|
},
|
|
{
|
|
"entropy": 5.644683218002319,
|
|
"epoch": 0.8693210535182794,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004935242889374052,
|
|
"loss": 5.536,
|
|
"mean_token_accuracy": 0.17835524082183837,
|
|
"num_tokens": 17265378.0,
|
|
"step": 7740
|
|
},
|
|
{
|
|
"entropy": 5.724565315246582,
|
|
"epoch": 0.8698826304262369,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004935147225145469,
|
|
"loss": 5.6105,
|
|
"mean_token_accuracy": 0.17023085206747054,
|
|
"num_tokens": 17277202.0,
|
|
"step": 7745
|
|
},
|
|
{
|
|
"entropy": 5.6139226913452145,
|
|
"epoch": 0.8704442073341944,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004935051491340951,
|
|
"loss": 5.5543,
|
|
"mean_token_accuracy": 0.1805954396724701,
|
|
"num_tokens": 17287006.0,
|
|
"step": 7750
|
|
},
|
|
{
|
|
"entropy": 5.649082994461059,
|
|
"epoch": 0.8710057842421519,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004934955687963546,
|
|
"loss": 5.52,
|
|
"mean_token_accuracy": 0.18563045263290406,
|
|
"num_tokens": 17297387.0,
|
|
"step": 7755
|
|
},
|
|
{
|
|
"entropy": 5.797161531448364,
|
|
"epoch": 0.8715673611501095,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004934859815016304,
|
|
"loss": 5.7537,
|
|
"mean_token_accuracy": 0.16585738137364386,
|
|
"num_tokens": 17310364.0,
|
|
"step": 7760
|
|
},
|
|
{
|
|
"entropy": 5.6904988288879395,
|
|
"epoch": 0.872128938058067,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004934763872502278,
|
|
"loss": 5.5897,
|
|
"mean_token_accuracy": 0.17995432764291763,
|
|
"num_tokens": 17321282.0,
|
|
"step": 7765
|
|
},
|
|
{
|
|
"entropy": 5.684155511856079,
|
|
"epoch": 0.8726905149660246,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004934667860424523,
|
|
"loss": 5.632,
|
|
"mean_token_accuracy": 0.1700143799185753,
|
|
"num_tokens": 17331755.0,
|
|
"step": 7770
|
|
},
|
|
{
|
|
"entropy": 5.656625986099243,
|
|
"epoch": 0.8732520918739821,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004934571778786096,
|
|
"loss": 5.5745,
|
|
"mean_token_accuracy": 0.17331324964761735,
|
|
"num_tokens": 17342542.0,
|
|
"step": 7775
|
|
},
|
|
{
|
|
"entropy": 5.652045154571534,
|
|
"epoch": 0.8738136687819397,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004934475627590057,
|
|
"loss": 5.5215,
|
|
"mean_token_accuracy": 0.17376778274774551,
|
|
"num_tokens": 17353150.0,
|
|
"step": 7780
|
|
},
|
|
{
|
|
"entropy": 5.65459680557251,
|
|
"epoch": 0.8743752456898972,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004934379406839466,
|
|
"loss": 5.5644,
|
|
"mean_token_accuracy": 0.17380731254816056,
|
|
"num_tokens": 17363901.0,
|
|
"step": 7785
|
|
},
|
|
{
|
|
"entropy": 5.67426061630249,
|
|
"epoch": 0.8749368225978548,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004934283116537387,
|
|
"loss": 5.488,
|
|
"mean_token_accuracy": 0.17831778526306152,
|
|
"num_tokens": 17374429.0,
|
|
"step": 7790
|
|
},
|
|
{
|
|
"entropy": 5.673512268066406,
|
|
"epoch": 0.8754983995058123,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004934186756686888,
|
|
"loss": 5.6291,
|
|
"mean_token_accuracy": 0.17127451598644255,
|
|
"num_tokens": 17384952.0,
|
|
"step": 7795
|
|
},
|
|
{
|
|
"entropy": 5.670864820480347,
|
|
"epoch": 0.8760599764137699,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004934090327291034,
|
|
"loss": 5.5948,
|
|
"mean_token_accuracy": 0.17161913961172104,
|
|
"num_tokens": 17397771.0,
|
|
"step": 7800
|
|
},
|
|
{
|
|
"entropy": 5.670876312255859,
|
|
"epoch": 0.8766215533217274,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004933993828352898,
|
|
"loss": 5.5027,
|
|
"mean_token_accuracy": 0.17967257499694825,
|
|
"num_tokens": 17407748.0,
|
|
"step": 7805
|
|
},
|
|
{
|
|
"entropy": 5.611726522445679,
|
|
"epoch": 0.877183130229685,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004933897259875551,
|
|
"loss": 5.4843,
|
|
"mean_token_accuracy": 0.175080007314682,
|
|
"num_tokens": 17418572.0,
|
|
"step": 7810
|
|
},
|
|
{
|
|
"entropy": 5.52510027885437,
|
|
"epoch": 0.8777447071376425,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004933800621862069,
|
|
"loss": 5.5306,
|
|
"mean_token_accuracy": 0.17571943253278732,
|
|
"num_tokens": 17429909.0,
|
|
"step": 7815
|
|
},
|
|
{
|
|
"entropy": 5.638761234283447,
|
|
"epoch": 0.8783062840456001,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004933703914315527,
|
|
"loss": 5.5553,
|
|
"mean_token_accuracy": 0.1714665785431862,
|
|
"num_tokens": 17441143.0,
|
|
"step": 7820
|
|
},
|
|
{
|
|
"entropy": 5.736855459213257,
|
|
"epoch": 0.8788678609535576,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004933607137239006,
|
|
"loss": 5.6724,
|
|
"mean_token_accuracy": 0.16394690573215484,
|
|
"num_tokens": 17452156.0,
|
|
"step": 7825
|
|
},
|
|
{
|
|
"entropy": 5.618521738052368,
|
|
"epoch": 0.8794294378615152,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004933510290635587,
|
|
"loss": 5.574,
|
|
"mean_token_accuracy": 0.17211691588163375,
|
|
"num_tokens": 17463873.0,
|
|
"step": 7830
|
|
},
|
|
{
|
|
"entropy": 5.598127937316894,
|
|
"epoch": 0.8799910147694727,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004933413374508353,
|
|
"loss": 5.5071,
|
|
"mean_token_accuracy": 0.17668081372976302,
|
|
"num_tokens": 17474180.0,
|
|
"step": 7835
|
|
},
|
|
{
|
|
"entropy": 5.652832412719727,
|
|
"epoch": 0.8805525916774303,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004933316388860391,
|
|
"loss": 5.539,
|
|
"mean_token_accuracy": 0.1772014617919922,
|
|
"num_tokens": 17486903.0,
|
|
"step": 7840
|
|
},
|
|
{
|
|
"entropy": 5.573214387893676,
|
|
"epoch": 0.8811141685853877,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004933219333694787,
|
|
"loss": 5.567,
|
|
"mean_token_accuracy": 0.17032884508371354,
|
|
"num_tokens": 17498790.0,
|
|
"step": 7845
|
|
},
|
|
{
|
|
"entropy": 5.723428106307983,
|
|
"epoch": 0.8816757454933453,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004933122209014634,
|
|
"loss": 5.5983,
|
|
"mean_token_accuracy": 0.16774654984474183,
|
|
"num_tokens": 17510061.0,
|
|
"step": 7850
|
|
},
|
|
{
|
|
"entropy": 5.679811573028564,
|
|
"epoch": 0.8822373224013028,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004933025014823022,
|
|
"loss": 5.6114,
|
|
"mean_token_accuracy": 0.17310027331113814,
|
|
"num_tokens": 17522414.0,
|
|
"step": 7855
|
|
},
|
|
{
|
|
"entropy": 5.8511148452758786,
|
|
"epoch": 0.8827988993092604,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004932927751123048,
|
|
"loss": 5.7443,
|
|
"mean_token_accuracy": 0.16237847954034806,
|
|
"num_tokens": 17532745.0,
|
|
"step": 7860
|
|
},
|
|
{
|
|
"entropy": 5.631840419769287,
|
|
"epoch": 0.8833604762172179,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004932830417917808,
|
|
"loss": 5.5358,
|
|
"mean_token_accuracy": 0.17639891058206558,
|
|
"num_tokens": 17545329.0,
|
|
"step": 7865
|
|
},
|
|
{
|
|
"entropy": 5.729234743118286,
|
|
"epoch": 0.8839220531251755,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00049327330152104,
|
|
"loss": 5.6476,
|
|
"mean_token_accuracy": 0.1724901929497719,
|
|
"num_tokens": 17557789.0,
|
|
"step": 7870
|
|
},
|
|
{
|
|
"entropy": 5.672587299346924,
|
|
"epoch": 0.884483630033133,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004932635543003927,
|
|
"loss": 5.4769,
|
|
"mean_token_accuracy": 0.18150333017110826,
|
|
"num_tokens": 17568338.0,
|
|
"step": 7875
|
|
},
|
|
{
|
|
"entropy": 5.638689804077148,
|
|
"epoch": 0.8850452069410906,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004932538001301491,
|
|
"loss": 5.5781,
|
|
"mean_token_accuracy": 0.1726062461733818,
|
|
"num_tokens": 17581199.0,
|
|
"step": 7880
|
|
},
|
|
{
|
|
"entropy": 5.544777345657349,
|
|
"epoch": 0.8856067838490481,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004932440390106199,
|
|
"loss": 5.5334,
|
|
"mean_token_accuracy": 0.1764208197593689,
|
|
"num_tokens": 17592937.0,
|
|
"step": 7885
|
|
},
|
|
{
|
|
"entropy": 5.629625701904297,
|
|
"epoch": 0.8861683607570057,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004932342709421159,
|
|
"loss": 5.5926,
|
|
"mean_token_accuracy": 0.17708465456962585,
|
|
"num_tokens": 17604003.0,
|
|
"step": 7890
|
|
},
|
|
{
|
|
"entropy": 5.90011510848999,
|
|
"epoch": 0.8867299376649632,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.000493224495924948,
|
|
"loss": 5.7302,
|
|
"mean_token_accuracy": 0.16930215954780578,
|
|
"num_tokens": 17617283.0,
|
|
"step": 7895
|
|
},
|
|
{
|
|
"entropy": 5.677170133590698,
|
|
"epoch": 0.8872915145729208,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004932147139594276,
|
|
"loss": 5.5707,
|
|
"mean_token_accuracy": 0.1770807087421417,
|
|
"num_tokens": 17628161.0,
|
|
"step": 7900
|
|
},
|
|
{
|
|
"entropy": 5.728165149688721,
|
|
"epoch": 0.8878530914808783,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004932049250458659,
|
|
"loss": 5.6503,
|
|
"mean_token_accuracy": 0.16944217383861543,
|
|
"num_tokens": 17639226.0,
|
|
"step": 7905
|
|
},
|
|
{
|
|
"entropy": 5.592314767837524,
|
|
"epoch": 0.8884146683888359,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004931951291845749,
|
|
"loss": 5.4893,
|
|
"mean_token_accuracy": 0.18333953768014907,
|
|
"num_tokens": 17652114.0,
|
|
"step": 7910
|
|
},
|
|
{
|
|
"entropy": 5.5825001239776615,
|
|
"epoch": 0.8889762452967934,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004931853263758663,
|
|
"loss": 5.529,
|
|
"mean_token_accuracy": 0.18106401562690735,
|
|
"num_tokens": 17663280.0,
|
|
"step": 7915
|
|
},
|
|
{
|
|
"entropy": 5.623987007141113,
|
|
"epoch": 0.889537822204751,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004931755166200523,
|
|
"loss": 5.6155,
|
|
"mean_token_accuracy": 0.17368122637271882,
|
|
"num_tokens": 17674445.0,
|
|
"step": 7920
|
|
},
|
|
{
|
|
"entropy": 5.691004753112793,
|
|
"epoch": 0.8900993991127085,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004931656999174452,
|
|
"loss": 5.5071,
|
|
"mean_token_accuracy": 0.17749142944812774,
|
|
"num_tokens": 17685046.0,
|
|
"step": 7925
|
|
},
|
|
{
|
|
"entropy": 5.591828203201294,
|
|
"epoch": 0.8906609760206661,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004931558762683577,
|
|
"loss": 5.507,
|
|
"mean_token_accuracy": 0.17967617213726045,
|
|
"num_tokens": 17695269.0,
|
|
"step": 7930
|
|
},
|
|
{
|
|
"entropy": 5.559813833236694,
|
|
"epoch": 0.8912225529286236,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004931460456731024,
|
|
"loss": 5.5466,
|
|
"mean_token_accuracy": 0.17714540660381317,
|
|
"num_tokens": 17706296.0,
|
|
"step": 7935
|
|
},
|
|
{
|
|
"entropy": 5.6044251918792725,
|
|
"epoch": 0.8917841298365812,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004931362081319925,
|
|
"loss": 5.4769,
|
|
"mean_token_accuracy": 0.17915261387825013,
|
|
"num_tokens": 17716262.0,
|
|
"step": 7940
|
|
},
|
|
{
|
|
"entropy": 5.66194977760315,
|
|
"epoch": 0.8923457067445386,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004931263636453409,
|
|
"loss": 5.5201,
|
|
"mean_token_accuracy": 0.17992712408304215,
|
|
"num_tokens": 17726818.0,
|
|
"step": 7945
|
|
},
|
|
{
|
|
"entropy": 5.589525651931763,
|
|
"epoch": 0.8929072836524962,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004931165122134616,
|
|
"loss": 5.5256,
|
|
"mean_token_accuracy": 0.18117809742689134,
|
|
"num_tokens": 17737112.0,
|
|
"step": 7950
|
|
},
|
|
{
|
|
"entropy": 5.660979413986206,
|
|
"epoch": 0.8934688605604537,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004931066538366677,
|
|
"loss": 5.5984,
|
|
"mean_token_accuracy": 0.17052928656339644,
|
|
"num_tokens": 17747558.0,
|
|
"step": 7955
|
|
},
|
|
{
|
|
"entropy": 5.712664318084717,
|
|
"epoch": 0.8940304374684113,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004930967885152734,
|
|
"loss": 5.536,
|
|
"mean_token_accuracy": 0.17624609172344208,
|
|
"num_tokens": 17757495.0,
|
|
"step": 7960
|
|
},
|
|
{
|
|
"entropy": 5.624363279342651,
|
|
"epoch": 0.8945920143763688,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004930869162495929,
|
|
"loss": 5.5294,
|
|
"mean_token_accuracy": 0.1765795186161995,
|
|
"num_tokens": 17767562.0,
|
|
"step": 7965
|
|
},
|
|
{
|
|
"entropy": 5.6667194843292235,
|
|
"epoch": 0.8951535912843264,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004930770370399403,
|
|
"loss": 5.6186,
|
|
"mean_token_accuracy": 0.16974660009145737,
|
|
"num_tokens": 17779800.0,
|
|
"step": 7970
|
|
},
|
|
{
|
|
"entropy": 5.610093069076538,
|
|
"epoch": 0.8957151681922839,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004930671508866303,
|
|
"loss": 5.4308,
|
|
"mean_token_accuracy": 0.17751775681972504,
|
|
"num_tokens": 17791183.0,
|
|
"step": 7975
|
|
},
|
|
{
|
|
"entropy": 5.681202840805054,
|
|
"epoch": 0.8962767451002415,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004930572577899776,
|
|
"loss": 5.5975,
|
|
"mean_token_accuracy": 0.1753363460302353,
|
|
"num_tokens": 17802547.0,
|
|
"step": 7980
|
|
},
|
|
{
|
|
"entropy": 5.511297702789307,
|
|
"epoch": 0.896838322008199,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.0004930473577502972,
|
|
"loss": 5.492,
|
|
"mean_token_accuracy": 0.17547860294580458,
|
|
"num_tokens": 17815406.0,
|
|
"step": 7985
|
|
},
|
|
{
|
|
"entropy": 5.631451606750488,
|
|
"epoch": 0.8973998989161566,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004930374507679044,
|
|
"loss": 5.521,
|
|
"mean_token_accuracy": 0.17684534192085266,
|
|
"num_tokens": 17826516.0,
|
|
"step": 7990
|
|
},
|
|
{
|
|
"entropy": 5.646472406387329,
|
|
"epoch": 0.8979614758241141,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004930275368431146,
|
|
"loss": 5.4978,
|
|
"mean_token_accuracy": 0.1771871417760849,
|
|
"num_tokens": 17838193.0,
|
|
"step": 7995
|
|
},
|
|
{
|
|
"entropy": 5.624480295181274,
|
|
"epoch": 0.8985230527320717,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004930176159762435,
|
|
"loss": 5.5205,
|
|
"mean_token_accuracy": 0.1750570610165596,
|
|
"num_tokens": 17849564.0,
|
|
"step": 8000
|
|
},
|
|
{
|
|
"entropy": 5.736857175827026,
|
|
"epoch": 0.8990846296400292,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004930076881676069,
|
|
"loss": 5.662,
|
|
"mean_token_accuracy": 0.17136270999908448,
|
|
"num_tokens": 17861874.0,
|
|
"step": 8005
|
|
},
|
|
{
|
|
"entropy": 5.575713205337524,
|
|
"epoch": 0.8996462065479868,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004929977534175211,
|
|
"loss": 5.5055,
|
|
"mean_token_accuracy": 0.17983078062534333,
|
|
"num_tokens": 17873139.0,
|
|
"step": 8010
|
|
},
|
|
{
|
|
"entropy": 5.736148262023926,
|
|
"epoch": 0.9002077834559443,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004929878117263021,
|
|
"loss": 5.572,
|
|
"mean_token_accuracy": 0.17753154337406157,
|
|
"num_tokens": 17883262.0,
|
|
"step": 8015
|
|
},
|
|
{
|
|
"entropy": 5.554032325744629,
|
|
"epoch": 0.9007693603639019,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004929778630942668,
|
|
"loss": 5.4604,
|
|
"mean_token_accuracy": 0.18278993517160416,
|
|
"num_tokens": 17895041.0,
|
|
"step": 8020
|
|
},
|
|
{
|
|
"entropy": 5.528722429275513,
|
|
"epoch": 0.9013309372718594,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004929679075217317,
|
|
"loss": 5.5034,
|
|
"mean_token_accuracy": 0.17425708770751952,
|
|
"num_tokens": 17905154.0,
|
|
"step": 8025
|
|
},
|
|
{
|
|
"entropy": 5.616612911224365,
|
|
"epoch": 0.901892514179817,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004929579450090139,
|
|
"loss": 5.5601,
|
|
"mean_token_accuracy": 0.17341381311416626,
|
|
"num_tokens": 17916287.0,
|
|
"step": 8030
|
|
},
|
|
{
|
|
"entropy": 5.7543384552001955,
|
|
"epoch": 0.9024540910877745,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004929479755564305,
|
|
"loss": 5.5673,
|
|
"mean_token_accuracy": 0.17662589699029924,
|
|
"num_tokens": 17927269.0,
|
|
"step": 8035
|
|
},
|
|
{
|
|
"entropy": 5.6863922595977785,
|
|
"epoch": 0.903015667995732,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004929379991642991,
|
|
"loss": 5.5818,
|
|
"mean_token_accuracy": 0.1742201864719391,
|
|
"num_tokens": 17938142.0,
|
|
"step": 8040
|
|
},
|
|
{
|
|
"entropy": 5.675807046890259,
|
|
"epoch": 0.9035772449036895,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004929280158329373,
|
|
"loss": 5.5645,
|
|
"mean_token_accuracy": 0.1757965698838234,
|
|
"num_tokens": 17950229.0,
|
|
"step": 8045
|
|
},
|
|
{
|
|
"entropy": 5.612723159790039,
|
|
"epoch": 0.9041388218116471,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.000492918025562663,
|
|
"loss": 5.548,
|
|
"mean_token_accuracy": 0.18230236321687698,
|
|
"num_tokens": 17961757.0,
|
|
"step": 8050
|
|
},
|
|
{
|
|
"entropy": 5.685063695907592,
|
|
"epoch": 0.9047003987196046,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004929080283537942,
|
|
"loss": 5.6233,
|
|
"mean_token_accuracy": 0.1663338214159012,
|
|
"num_tokens": 17972564.0,
|
|
"step": 8055
|
|
},
|
|
{
|
|
"entropy": 5.735013771057129,
|
|
"epoch": 0.9052619756275622,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004928980242066492,
|
|
"loss": 5.5325,
|
|
"mean_token_accuracy": 0.18212261348962783,
|
|
"num_tokens": 17982776.0,
|
|
"step": 8060
|
|
},
|
|
{
|
|
"entropy": 5.688648509979248,
|
|
"epoch": 0.9058235525355197,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004928880131215467,
|
|
"loss": 5.6463,
|
|
"mean_token_accuracy": 0.1749667137861252,
|
|
"num_tokens": 17994460.0,
|
|
"step": 8065
|
|
},
|
|
{
|
|
"entropy": 5.624743270874023,
|
|
"epoch": 0.9063851294434773,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004928779950988053,
|
|
"loss": 5.62,
|
|
"mean_token_accuracy": 0.17174448817968369,
|
|
"num_tokens": 18005744.0,
|
|
"step": 8070
|
|
},
|
|
{
|
|
"entropy": 5.611772775650024,
|
|
"epoch": 0.9069467063514348,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.000492867970138744,
|
|
"loss": 5.4754,
|
|
"mean_token_accuracy": 0.18351303040981293,
|
|
"num_tokens": 18016517.0,
|
|
"step": 8075
|
|
},
|
|
{
|
|
"entropy": 5.675594282150269,
|
|
"epoch": 0.9075082832593924,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004928579382416821,
|
|
"loss": 5.5975,
|
|
"mean_token_accuracy": 0.16978041380643843,
|
|
"num_tokens": 18027653.0,
|
|
"step": 8080
|
|
},
|
|
{
|
|
"entropy": 5.675237369537354,
|
|
"epoch": 0.9080698601673499,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.000492847899407939,
|
|
"loss": 5.636,
|
|
"mean_token_accuracy": 0.17045610696077346,
|
|
"num_tokens": 18038741.0,
|
|
"step": 8085
|
|
},
|
|
{
|
|
"entropy": 5.7510435581207275,
|
|
"epoch": 0.9086314370753075,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004928378536378341,
|
|
"loss": 5.5802,
|
|
"mean_token_accuracy": 0.17184377759695052,
|
|
"num_tokens": 18049188.0,
|
|
"step": 8090
|
|
},
|
|
{
|
|
"entropy": 5.608703708648681,
|
|
"epoch": 0.909193013983265,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004928278009316877,
|
|
"loss": 5.482,
|
|
"mean_token_accuracy": 0.17725870013237,
|
|
"num_tokens": 18059979.0,
|
|
"step": 8095
|
|
},
|
|
{
|
|
"entropy": 5.6458415508270265,
|
|
"epoch": 0.9097545908912226,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004928177412898195,
|
|
"loss": 5.4967,
|
|
"mean_token_accuracy": 0.1831892564892769,
|
|
"num_tokens": 18070712.0,
|
|
"step": 8100
|
|
},
|
|
{
|
|
"entropy": 5.670635318756103,
|
|
"epoch": 0.9103161677991801,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004928076747125499,
|
|
"loss": 5.5632,
|
|
"mean_token_accuracy": 0.18162725418806075,
|
|
"num_tokens": 18081372.0,
|
|
"step": 8105
|
|
},
|
|
{
|
|
"entropy": 5.577960062026977,
|
|
"epoch": 0.9108777447071377,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004927976012001995,
|
|
"loss": 5.4888,
|
|
"mean_token_accuracy": 0.17665131241083146,
|
|
"num_tokens": 18093033.0,
|
|
"step": 8110
|
|
},
|
|
{
|
|
"entropy": 5.555771923065185,
|
|
"epoch": 0.9114393216150952,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004927875207530889,
|
|
"loss": 5.4461,
|
|
"mean_token_accuracy": 0.18108128160238265,
|
|
"num_tokens": 18104808.0,
|
|
"step": 8115
|
|
},
|
|
{
|
|
"entropy": 5.730599784851075,
|
|
"epoch": 0.9120008985230528,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004927774333715394,
|
|
"loss": 5.5846,
|
|
"mean_token_accuracy": 0.17475593835115433,
|
|
"num_tokens": 18115450.0,
|
|
"step": 8120
|
|
},
|
|
{
|
|
"entropy": 5.730729341506958,
|
|
"epoch": 0.9125624754310103,
|
|
"grad_norm": 2.90625,
|
|
"learning_rate": 0.0004927673390558718,
|
|
"loss": 5.6786,
|
|
"mean_token_accuracy": 0.17357307821512222,
|
|
"num_tokens": 18127437.0,
|
|
"step": 8125
|
|
},
|
|
{
|
|
"entropy": 5.705981349945068,
|
|
"epoch": 0.9131240523389679,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004927572378064077,
|
|
"loss": 5.5123,
|
|
"mean_token_accuracy": 0.1819301575422287,
|
|
"num_tokens": 18137371.0,
|
|
"step": 8130
|
|
},
|
|
{
|
|
"entropy": 5.618573713302612,
|
|
"epoch": 0.9136856292469253,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004927471296234687,
|
|
"loss": 5.5725,
|
|
"mean_token_accuracy": 0.17275052070617675,
|
|
"num_tokens": 18148332.0,
|
|
"step": 8135
|
|
},
|
|
{
|
|
"entropy": 5.588826656341553,
|
|
"epoch": 0.9142472061548829,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004927370145073767,
|
|
"loss": 5.5549,
|
|
"mean_token_accuracy": 0.17383279651403427,
|
|
"num_tokens": 18159918.0,
|
|
"step": 8140
|
|
},
|
|
{
|
|
"entropy": 5.65464768409729,
|
|
"epoch": 0.9148087830628404,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004927268924584536,
|
|
"loss": 5.5406,
|
|
"mean_token_accuracy": 0.18160120993852616,
|
|
"num_tokens": 18170911.0,
|
|
"step": 8145
|
|
},
|
|
{
|
|
"entropy": 5.667963266372681,
|
|
"epoch": 0.915370359970798,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004927167634770219,
|
|
"loss": 5.5562,
|
|
"mean_token_accuracy": 0.17828303426504136,
|
|
"num_tokens": 18183089.0,
|
|
"step": 8150
|
|
},
|
|
{
|
|
"entropy": 5.7810358047485355,
|
|
"epoch": 0.9159319368787555,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.000492706627563404,
|
|
"loss": 5.8173,
|
|
"mean_token_accuracy": 0.15935783535242082,
|
|
"num_tokens": 18195467.0,
|
|
"step": 8155
|
|
},
|
|
{
|
|
"entropy": 5.740857410430908,
|
|
"epoch": 0.9164935137867131,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004926964847179225,
|
|
"loss": 5.572,
|
|
"mean_token_accuracy": 0.1790512040257454,
|
|
"num_tokens": 18206766.0,
|
|
"step": 8160
|
|
},
|
|
{
|
|
"entropy": 5.679031610488892,
|
|
"epoch": 0.9170550906946706,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004926863349409006,
|
|
"loss": 5.5629,
|
|
"mean_token_accuracy": 0.17597046494483948,
|
|
"num_tokens": 18217840.0,
|
|
"step": 8165
|
|
},
|
|
{
|
|
"entropy": 5.649716377258301,
|
|
"epoch": 0.9176166676026282,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004926761782326613,
|
|
"loss": 5.5758,
|
|
"mean_token_accuracy": 0.17311379611492156,
|
|
"num_tokens": 18229514.0,
|
|
"step": 8170
|
|
},
|
|
{
|
|
"entropy": 5.5854212760925295,
|
|
"epoch": 0.9181782445105857,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004926660145935282,
|
|
"loss": 5.5559,
|
|
"mean_token_accuracy": 0.1705981135368347,
|
|
"num_tokens": 18241949.0,
|
|
"step": 8175
|
|
},
|
|
{
|
|
"entropy": 5.651837682723999,
|
|
"epoch": 0.9187398214185433,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004926558440238247,
|
|
"loss": 5.5314,
|
|
"mean_token_accuracy": 0.17833069413900376,
|
|
"num_tokens": 18252938.0,
|
|
"step": 8180
|
|
},
|
|
{
|
|
"entropy": 5.624422931671143,
|
|
"epoch": 0.9193013983265008,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004926456665238746,
|
|
"loss": 5.479,
|
|
"mean_token_accuracy": 0.18345132768154143,
|
|
"num_tokens": 18263417.0,
|
|
"step": 8185
|
|
},
|
|
{
|
|
"entropy": 5.661493015289307,
|
|
"epoch": 0.9198629752344584,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004926354820940023,
|
|
"loss": 5.6485,
|
|
"mean_token_accuracy": 0.17259145379066468,
|
|
"num_tokens": 18275595.0,
|
|
"step": 8190
|
|
},
|
|
{
|
|
"entropy": 5.592373466491699,
|
|
"epoch": 0.9204245521424159,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004926252907345317,
|
|
"loss": 5.4836,
|
|
"mean_token_accuracy": 0.17857701629400252,
|
|
"num_tokens": 18287510.0,
|
|
"step": 8195
|
|
},
|
|
{
|
|
"entropy": 5.717923927307129,
|
|
"epoch": 0.9209861290503735,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004926150924457874,
|
|
"loss": 5.5838,
|
|
"mean_token_accuracy": 0.17386380732059478,
|
|
"num_tokens": 18298764.0,
|
|
"step": 8200
|
|
},
|
|
{
|
|
"entropy": 5.588229608535767,
|
|
"epoch": 0.921547705958331,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004926048872280943,
|
|
"loss": 5.4009,
|
|
"mean_token_accuracy": 0.17802754789590836,
|
|
"num_tokens": 18310427.0,
|
|
"step": 8205
|
|
},
|
|
{
|
|
"entropy": 5.580872583389282,
|
|
"epoch": 0.9221092828662886,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000492594675081777,
|
|
"loss": 5.532,
|
|
"mean_token_accuracy": 0.17346930950880052,
|
|
"num_tokens": 18322174.0,
|
|
"step": 8210
|
|
},
|
|
{
|
|
"entropy": 5.584685850143432,
|
|
"epoch": 0.9226708597742461,
|
|
"grad_norm": 2.8125,
|
|
"learning_rate": 0.000492584456007161,
|
|
"loss": 5.4795,
|
|
"mean_token_accuracy": 0.17690377533435822,
|
|
"num_tokens": 18332372.0,
|
|
"step": 8215
|
|
},
|
|
{
|
|
"entropy": 5.672969627380371,
|
|
"epoch": 0.9232324366822037,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004925742300045716,
|
|
"loss": 5.5459,
|
|
"mean_token_accuracy": 0.1704122766852379,
|
|
"num_tokens": 18343201.0,
|
|
"step": 8220
|
|
},
|
|
{
|
|
"entropy": 5.634353446960449,
|
|
"epoch": 0.9237940135901612,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004925639970743341,
|
|
"loss": 5.5613,
|
|
"mean_token_accuracy": 0.1783763960003853,
|
|
"num_tokens": 18354124.0,
|
|
"step": 8225
|
|
},
|
|
{
|
|
"entropy": 5.626930046081543,
|
|
"epoch": 0.9243555904981187,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004925537572167746,
|
|
"loss": 5.5138,
|
|
"mean_token_accuracy": 0.18148281127214433,
|
|
"num_tokens": 18365148.0,
|
|
"step": 8230
|
|
},
|
|
{
|
|
"entropy": 5.467441701889038,
|
|
"epoch": 0.9249171674060762,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004925435104322192,
|
|
"loss": 5.3908,
|
|
"mean_token_accuracy": 0.18088495582342148,
|
|
"num_tokens": 18376244.0,
|
|
"step": 8235
|
|
},
|
|
{
|
|
"entropy": 5.6002789497375485,
|
|
"epoch": 0.9254787443140338,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.000492533256720994,
|
|
"loss": 5.5533,
|
|
"mean_token_accuracy": 0.17563220411539077,
|
|
"num_tokens": 18386728.0,
|
|
"step": 8240
|
|
},
|
|
{
|
|
"entropy": 5.666000461578369,
|
|
"epoch": 0.9260403212219913,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004925229960834256,
|
|
"loss": 5.5451,
|
|
"mean_token_accuracy": 0.17448101937770844,
|
|
"num_tokens": 18397008.0,
|
|
"step": 8245
|
|
},
|
|
{
|
|
"entropy": 5.637777423858642,
|
|
"epoch": 0.9266018981299489,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004925127285198407,
|
|
"loss": 5.5305,
|
|
"mean_token_accuracy": 0.18294473737478256,
|
|
"num_tokens": 18408348.0,
|
|
"step": 8250
|
|
},
|
|
{
|
|
"entropy": 5.5927502632141115,
|
|
"epoch": 0.9271634750379064,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.000492502454030566,
|
|
"loss": 5.5562,
|
|
"mean_token_accuracy": 0.18002525418996812,
|
|
"num_tokens": 18419239.0,
|
|
"step": 8255
|
|
},
|
|
{
|
|
"entropy": 5.727730941772461,
|
|
"epoch": 0.927725051945864,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004924921726159288,
|
|
"loss": 5.561,
|
|
"mean_token_accuracy": 0.17431779056787491,
|
|
"num_tokens": 18428918.0,
|
|
"step": 8260
|
|
},
|
|
{
|
|
"entropy": 5.725991296768188,
|
|
"epoch": 0.9282866288538215,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004924818842762565,
|
|
"loss": 5.5523,
|
|
"mean_token_accuracy": 0.1816506192088127,
|
|
"num_tokens": 18440361.0,
|
|
"step": 8265
|
|
},
|
|
{
|
|
"entropy": 5.559592771530151,
|
|
"epoch": 0.9288482057617791,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004924715890118768,
|
|
"loss": 5.4345,
|
|
"mean_token_accuracy": 0.180571249127388,
|
|
"num_tokens": 18450678.0,
|
|
"step": 8270
|
|
},
|
|
{
|
|
"entropy": 5.608138799667358,
|
|
"epoch": 0.9294097826697366,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004924612868231173,
|
|
"loss": 5.6334,
|
|
"mean_token_accuracy": 0.17058404982089997,
|
|
"num_tokens": 18462364.0,
|
|
"step": 8275
|
|
},
|
|
{
|
|
"entropy": 5.645278215408325,
|
|
"epoch": 0.9299713595776942,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004924509777103059,
|
|
"loss": 5.5226,
|
|
"mean_token_accuracy": 0.17628366500139236,
|
|
"num_tokens": 18472896.0,
|
|
"step": 8280
|
|
},
|
|
{
|
|
"entropy": 5.787207078933716,
|
|
"epoch": 0.9305329364856517,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004924406616737712,
|
|
"loss": 5.6589,
|
|
"mean_token_accuracy": 0.16721024066209794,
|
|
"num_tokens": 18484951.0,
|
|
"step": 8285
|
|
},
|
|
{
|
|
"entropy": 5.628914451599121,
|
|
"epoch": 0.9310945133936093,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004924303387138415,
|
|
"loss": 5.5925,
|
|
"mean_token_accuracy": 0.174946691095829,
|
|
"num_tokens": 18496006.0,
|
|
"step": 8290
|
|
},
|
|
{
|
|
"entropy": 5.748250484466553,
|
|
"epoch": 0.9316560903015668,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004924200088308455,
|
|
"loss": 5.5748,
|
|
"mean_token_accuracy": 0.17472342401742935,
|
|
"num_tokens": 18508069.0,
|
|
"step": 8295
|
|
},
|
|
{
|
|
"entropy": 5.7464500904083256,
|
|
"epoch": 0.9322176672095244,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.000492409672025112,
|
|
"loss": 5.6889,
|
|
"mean_token_accuracy": 0.16791522353887559,
|
|
"num_tokens": 18519746.0,
|
|
"step": 8300
|
|
},
|
|
{
|
|
"entropy": 5.742476892471314,
|
|
"epoch": 0.9327792441174819,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004923993282969703,
|
|
"loss": 5.592,
|
|
"mean_token_accuracy": 0.17625355273485183,
|
|
"num_tokens": 18530249.0,
|
|
"step": 8305
|
|
},
|
|
{
|
|
"entropy": 5.6794898986816404,
|
|
"epoch": 0.9333408210254395,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004923889776467495,
|
|
"loss": 5.613,
|
|
"mean_token_accuracy": 0.17979559898376465,
|
|
"num_tokens": 18543306.0,
|
|
"step": 8310
|
|
},
|
|
{
|
|
"entropy": 5.634688186645508,
|
|
"epoch": 0.933902397933397,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004923786200747795,
|
|
"loss": 5.6575,
|
|
"mean_token_accuracy": 0.17098734974861146,
|
|
"num_tokens": 18555250.0,
|
|
"step": 8315
|
|
},
|
|
{
|
|
"entropy": 5.6697102069854735,
|
|
"epoch": 0.9344639748413546,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00049236825558139,
|
|
"loss": 5.402,
|
|
"mean_token_accuracy": 0.1727229595184326,
|
|
"num_tokens": 18566378.0,
|
|
"step": 8320
|
|
},
|
|
{
|
|
"entropy": 5.67743182182312,
|
|
"epoch": 0.9350255517493121,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004923578841669108,
|
|
"loss": 5.6108,
|
|
"mean_token_accuracy": 0.17351700663566588,
|
|
"num_tokens": 18576827.0,
|
|
"step": 8325
|
|
},
|
|
{
|
|
"entropy": 5.616914176940918,
|
|
"epoch": 0.9355871286572696,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004923475058316723,
|
|
"loss": 5.5397,
|
|
"mean_token_accuracy": 0.17626303136348725,
|
|
"num_tokens": 18589209.0,
|
|
"step": 8330
|
|
},
|
|
{
|
|
"entropy": 5.6495646953582765,
|
|
"epoch": 0.9361487055652271,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004923371205760049,
|
|
"loss": 5.5529,
|
|
"mean_token_accuracy": 0.17969396114349365,
|
|
"num_tokens": 18599367.0,
|
|
"step": 8335
|
|
},
|
|
{
|
|
"entropy": 5.666165113449097,
|
|
"epoch": 0.9367102824731847,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004923267284002394,
|
|
"loss": 5.5904,
|
|
"mean_token_accuracy": 0.1729588732123375,
|
|
"num_tokens": 18610505.0,
|
|
"step": 8340
|
|
},
|
|
{
|
|
"entropy": 5.692822408676148,
|
|
"epoch": 0.9372718593811422,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004923163293047065,
|
|
"loss": 5.5945,
|
|
"mean_token_accuracy": 0.17593003809452057,
|
|
"num_tokens": 18622616.0,
|
|
"step": 8345
|
|
},
|
|
{
|
|
"entropy": 5.594743490219116,
|
|
"epoch": 0.9378334362890998,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004923059232897374,
|
|
"loss": 5.4359,
|
|
"mean_token_accuracy": 0.18015130013227462,
|
|
"num_tokens": 18634127.0,
|
|
"step": 8350
|
|
},
|
|
{
|
|
"entropy": 5.634627008438111,
|
|
"epoch": 0.9383950131970573,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004922955103556633,
|
|
"loss": 5.6466,
|
|
"mean_token_accuracy": 0.17177557200193405,
|
|
"num_tokens": 18646196.0,
|
|
"step": 8355
|
|
},
|
|
{
|
|
"entropy": 5.645306730270386,
|
|
"epoch": 0.9389565901050149,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.000492285090502816,
|
|
"loss": 5.552,
|
|
"mean_token_accuracy": 0.1770355746150017,
|
|
"num_tokens": 18656911.0,
|
|
"step": 8360
|
|
},
|
|
{
|
|
"entropy": 5.7078851699829105,
|
|
"epoch": 0.9395181670129724,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004922746637315272,
|
|
"loss": 5.5278,
|
|
"mean_token_accuracy": 0.1755846068263054,
|
|
"num_tokens": 18667553.0,
|
|
"step": 8365
|
|
},
|
|
{
|
|
"entropy": 5.620309591293335,
|
|
"epoch": 0.94007974392093,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004922642300421288,
|
|
"loss": 5.5011,
|
|
"mean_token_accuracy": 0.1790532335639,
|
|
"num_tokens": 18678087.0,
|
|
"step": 8370
|
|
},
|
|
{
|
|
"entropy": 5.6581525802612305,
|
|
"epoch": 0.9406413208288875,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.000492253789434953,
|
|
"loss": 5.6158,
|
|
"mean_token_accuracy": 0.1750505179166794,
|
|
"num_tokens": 18689946.0,
|
|
"step": 8375
|
|
},
|
|
{
|
|
"entropy": 5.625391101837158,
|
|
"epoch": 0.9412028977368451,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004922433419103323,
|
|
"loss": 5.5269,
|
|
"mean_token_accuracy": 0.18149401843547822,
|
|
"num_tokens": 18700944.0,
|
|
"step": 8380
|
|
},
|
|
{
|
|
"entropy": 5.687411165237426,
|
|
"epoch": 0.9417644746448026,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004922328874685993,
|
|
"loss": 5.6265,
|
|
"mean_token_accuracy": 0.17350946068763734,
|
|
"num_tokens": 18712901.0,
|
|
"step": 8385
|
|
},
|
|
{
|
|
"entropy": 5.6175501346588135,
|
|
"epoch": 0.9423260515527602,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 0.0004922224261100869,
|
|
"loss": 5.4589,
|
|
"mean_token_accuracy": 0.17959638684988022,
|
|
"num_tokens": 18724322.0,
|
|
"step": 8390
|
|
},
|
|
{
|
|
"entropy": 5.593675136566162,
|
|
"epoch": 0.9428876284607177,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004922119578351283,
|
|
"loss": 5.5165,
|
|
"mean_token_accuracy": 0.17416234016418458,
|
|
"num_tokens": 18735315.0,
|
|
"step": 8395
|
|
},
|
|
{
|
|
"entropy": 5.61961555480957,
|
|
"epoch": 0.9434492053686753,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004922014826440566,
|
|
"loss": 5.5541,
|
|
"mean_token_accuracy": 0.18015410602092743,
|
|
"num_tokens": 18747497.0,
|
|
"step": 8400
|
|
},
|
|
{
|
|
"entropy": 5.691785049438477,
|
|
"epoch": 0.9440107822766328,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004921910005372056,
|
|
"loss": 5.5891,
|
|
"mean_token_accuracy": 0.1704226091504097,
|
|
"num_tokens": 18758835.0,
|
|
"step": 8405
|
|
},
|
|
{
|
|
"entropy": 5.671810340881348,
|
|
"epoch": 0.9445723591845904,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004921805115149088,
|
|
"loss": 5.483,
|
|
"mean_token_accuracy": 0.18468721210956573,
|
|
"num_tokens": 18770325.0,
|
|
"step": 8410
|
|
},
|
|
{
|
|
"entropy": 5.520982933044434,
|
|
"epoch": 0.9451339360925479,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004921700155775002,
|
|
"loss": 5.3773,
|
|
"mean_token_accuracy": 0.18612601608037949,
|
|
"num_tokens": 18781204.0,
|
|
"step": 8415
|
|
},
|
|
{
|
|
"entropy": 5.526636171340942,
|
|
"epoch": 0.9456955130005055,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004921595127253142,
|
|
"loss": 5.4905,
|
|
"mean_token_accuracy": 0.18205440640449524,
|
|
"num_tokens": 18791899.0,
|
|
"step": 8420
|
|
},
|
|
{
|
|
"entropy": 5.603455257415772,
|
|
"epoch": 0.9462570899084629,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004921490029586852,
|
|
"loss": 5.4779,
|
|
"mean_token_accuracy": 0.1817940965294838,
|
|
"num_tokens": 18803043.0,
|
|
"step": 8425
|
|
},
|
|
{
|
|
"entropy": 5.60422306060791,
|
|
"epoch": 0.9468186668164205,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004921384862779475,
|
|
"loss": 5.4969,
|
|
"mean_token_accuracy": 0.17535765916109086,
|
|
"num_tokens": 18814316.0,
|
|
"step": 8430
|
|
},
|
|
{
|
|
"entropy": 5.586996269226074,
|
|
"epoch": 0.947380243724378,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004921279626834363,
|
|
"loss": 5.5614,
|
|
"mean_token_accuracy": 0.17469020187854767,
|
|
"num_tokens": 18825490.0,
|
|
"step": 8435
|
|
},
|
|
{
|
|
"entropy": 5.758854627609253,
|
|
"epoch": 0.9479418206323356,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004921174321754865,
|
|
"loss": 5.6497,
|
|
"mean_token_accuracy": 0.1785335808992386,
|
|
"num_tokens": 18836479.0,
|
|
"step": 8440
|
|
},
|
|
{
|
|
"entropy": 5.655997276306152,
|
|
"epoch": 0.9485033975402931,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004921068947544335,
|
|
"loss": 5.5424,
|
|
"mean_token_accuracy": 0.17748990803956985,
|
|
"num_tokens": 18848634.0,
|
|
"step": 8445
|
|
},
|
|
{
|
|
"entropy": 5.593111944198609,
|
|
"epoch": 0.9490649744482507,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004920963504206128,
|
|
"loss": 5.5003,
|
|
"mean_token_accuracy": 0.18238631188869475,
|
|
"num_tokens": 18858451.0,
|
|
"step": 8450
|
|
},
|
|
{
|
|
"entropy": 5.757823705673218,
|
|
"epoch": 0.9496265513562082,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.00049208579917436,
|
|
"loss": 5.6392,
|
|
"mean_token_accuracy": 0.16730133891105653,
|
|
"num_tokens": 18869561.0,
|
|
"step": 8455
|
|
},
|
|
{
|
|
"entropy": 5.777918672561645,
|
|
"epoch": 0.9501881282641658,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004920752410160113,
|
|
"loss": 5.6417,
|
|
"mean_token_accuracy": 0.16759925112128257,
|
|
"num_tokens": 18880232.0,
|
|
"step": 8460
|
|
},
|
|
{
|
|
"entropy": 5.7202564716339115,
|
|
"epoch": 0.9507497051721233,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004920646759459026,
|
|
"loss": 5.6543,
|
|
"mean_token_accuracy": 0.17059721201658248,
|
|
"num_tokens": 18892562.0,
|
|
"step": 8465
|
|
},
|
|
{
|
|
"entropy": 5.640997695922851,
|
|
"epoch": 0.9513112820800809,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004920541039643705,
|
|
"loss": 5.5844,
|
|
"mean_token_accuracy": 0.17161750495433808,
|
|
"num_tokens": 18903566.0,
|
|
"step": 8470
|
|
},
|
|
{
|
|
"entropy": 5.633873176574707,
|
|
"epoch": 0.9518728589880384,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004920435250717515,
|
|
"loss": 5.5761,
|
|
"mean_token_accuracy": 0.17739747911691667,
|
|
"num_tokens": 18914619.0,
|
|
"step": 8475
|
|
},
|
|
{
|
|
"entropy": 5.76814079284668,
|
|
"epoch": 0.952434435895996,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004920329392683826,
|
|
"loss": 5.6495,
|
|
"mean_token_accuracy": 0.17262647897005082,
|
|
"num_tokens": 18927039.0,
|
|
"step": 8480
|
|
},
|
|
{
|
|
"entropy": 5.777394104003906,
|
|
"epoch": 0.9529960128039535,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004920223465546006,
|
|
"loss": 5.7291,
|
|
"mean_token_accuracy": 0.16832094341516496,
|
|
"num_tokens": 18940449.0,
|
|
"step": 8485
|
|
},
|
|
{
|
|
"entropy": 5.695525121688843,
|
|
"epoch": 0.9535575897119111,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004920117469307429,
|
|
"loss": 5.6045,
|
|
"mean_token_accuracy": 0.17119804620742798,
|
|
"num_tokens": 18950798.0,
|
|
"step": 8490
|
|
},
|
|
{
|
|
"entropy": 5.686978483200074,
|
|
"epoch": 0.9541191666198686,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004920011403971471,
|
|
"loss": 5.4587,
|
|
"mean_token_accuracy": 0.17551997900009156,
|
|
"num_tokens": 18960958.0,
|
|
"step": 8495
|
|
},
|
|
{
|
|
"entropy": 5.588903331756592,
|
|
"epoch": 0.9546807435278262,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004919905269541508,
|
|
"loss": 5.4933,
|
|
"mean_token_accuracy": 0.17877306193113326,
|
|
"num_tokens": 18971890.0,
|
|
"step": 8500
|
|
},
|
|
{
|
|
"entropy": 5.560519123077393,
|
|
"epoch": 0.9552423204357837,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.000491979906602092,
|
|
"loss": 5.4282,
|
|
"mean_token_accuracy": 0.18534162938594817,
|
|
"num_tokens": 18982309.0,
|
|
"step": 8505
|
|
},
|
|
{
|
|
"entropy": 5.67816572189331,
|
|
"epoch": 0.9558038973437413,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004919692793413089,
|
|
"loss": 5.6482,
|
|
"mean_token_accuracy": 0.16850887835025788,
|
|
"num_tokens": 18993648.0,
|
|
"step": 8510
|
|
},
|
|
{
|
|
"entropy": 5.667968082427978,
|
|
"epoch": 0.9563654742516988,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004919586451721396,
|
|
"loss": 5.4243,
|
|
"mean_token_accuracy": 0.18356293588876724,
|
|
"num_tokens": 19003613.0,
|
|
"step": 8515
|
|
},
|
|
{
|
|
"entropy": 5.685746192932129,
|
|
"epoch": 0.9569270511596563,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004919480040949229,
|
|
"loss": 5.5428,
|
|
"mean_token_accuracy": 0.17324323505163192,
|
|
"num_tokens": 19014720.0,
|
|
"step": 8520
|
|
},
|
|
{
|
|
"entropy": 5.643367195129395,
|
|
"epoch": 0.9574886280676138,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004919373561099977,
|
|
"loss": 5.5788,
|
|
"mean_token_accuracy": 0.17302146852016448,
|
|
"num_tokens": 19026635.0,
|
|
"step": 8525
|
|
},
|
|
{
|
|
"entropy": 5.673974132537841,
|
|
"epoch": 0.9580502049755714,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.000491926701217703,
|
|
"loss": 5.5794,
|
|
"mean_token_accuracy": 0.1681892067193985,
|
|
"num_tokens": 19037433.0,
|
|
"step": 8530
|
|
},
|
|
{
|
|
"entropy": 5.6716055393219,
|
|
"epoch": 0.9586117818835289,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.0004919160394183779,
|
|
"loss": 5.4346,
|
|
"mean_token_accuracy": 0.18276526629924775,
|
|
"num_tokens": 19047351.0,
|
|
"step": 8535
|
|
},
|
|
{
|
|
"entropy": 5.513965892791748,
|
|
"epoch": 0.9591733587914865,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.000491905370712362,
|
|
"loss": 5.4747,
|
|
"mean_token_accuracy": 0.1769762381911278,
|
|
"num_tokens": 19058561.0,
|
|
"step": 8540
|
|
},
|
|
{
|
|
"entropy": 5.654763650894165,
|
|
"epoch": 0.959734935699444,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004918946950999949,
|
|
"loss": 5.5741,
|
|
"mean_token_accuracy": 0.16921738386154175,
|
|
"num_tokens": 19069877.0,
|
|
"step": 8545
|
|
},
|
|
{
|
|
"entropy": 5.7251872539520265,
|
|
"epoch": 0.9602965126074016,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004918840125816167,
|
|
"loss": 5.5792,
|
|
"mean_token_accuracy": 0.17826244831085206,
|
|
"num_tokens": 19081962.0,
|
|
"step": 8550
|
|
},
|
|
{
|
|
"entropy": 5.646814775466919,
|
|
"epoch": 0.9608580895153591,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004918733231575673,
|
|
"loss": 5.6367,
|
|
"mean_token_accuracy": 0.1751244530081749,
|
|
"num_tokens": 19092955.0,
|
|
"step": 8555
|
|
},
|
|
{
|
|
"entropy": 5.690008735656738,
|
|
"epoch": 0.9614196664233167,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004918626268281874,
|
|
"loss": 5.4435,
|
|
"mean_token_accuracy": 0.18832328021526337,
|
|
"num_tokens": 19103521.0,
|
|
"step": 8560
|
|
},
|
|
{
|
|
"entropy": 5.521415567398071,
|
|
"epoch": 0.9619812433312742,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004918519235938171,
|
|
"loss": 5.4644,
|
|
"mean_token_accuracy": 0.18721356838941575,
|
|
"num_tokens": 19114190.0,
|
|
"step": 8565
|
|
},
|
|
{
|
|
"entropy": 5.628028392791748,
|
|
"epoch": 0.9625428202392318,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004918412134547976,
|
|
"loss": 5.5215,
|
|
"mean_token_accuracy": 0.1752006560564041,
|
|
"num_tokens": 19123815.0,
|
|
"step": 8570
|
|
},
|
|
{
|
|
"entropy": 5.675377082824707,
|
|
"epoch": 0.9631043971471893,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004918304964114696,
|
|
"loss": 5.6645,
|
|
"mean_token_accuracy": 0.17109055519104005,
|
|
"num_tokens": 19135805.0,
|
|
"step": 8575
|
|
},
|
|
{
|
|
"entropy": 5.735991382598877,
|
|
"epoch": 0.9636659740551469,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004918197724641747,
|
|
"loss": 5.4943,
|
|
"mean_token_accuracy": 0.17655572593212127,
|
|
"num_tokens": 19146656.0,
|
|
"step": 8580
|
|
},
|
|
{
|
|
"entropy": 5.620199251174927,
|
|
"epoch": 0.9642275509631044,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.000491809041613254,
|
|
"loss": 5.5713,
|
|
"mean_token_accuracy": 0.1704343155026436,
|
|
"num_tokens": 19158271.0,
|
|
"step": 8585
|
|
},
|
|
{
|
|
"entropy": 5.580804252624512,
|
|
"epoch": 0.964789127871062,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004917983038590495,
|
|
"loss": 5.484,
|
|
"mean_token_accuracy": 0.17846604883670808,
|
|
"num_tokens": 19168439.0,
|
|
"step": 8590
|
|
},
|
|
{
|
|
"entropy": 5.6851584911346436,
|
|
"epoch": 0.9653507047790195,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004917875592019028,
|
|
"loss": 5.5721,
|
|
"mean_token_accuracy": 0.17893614768981933,
|
|
"num_tokens": 19179411.0,
|
|
"step": 8595
|
|
},
|
|
{
|
|
"entropy": 5.689495515823364,
|
|
"epoch": 0.9659122816869771,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004917768076421561,
|
|
"loss": 5.5917,
|
|
"mean_token_accuracy": 0.174559023976326,
|
|
"num_tokens": 19189377.0,
|
|
"step": 8600
|
|
},
|
|
{
|
|
"entropy": 5.615097713470459,
|
|
"epoch": 0.9664738585949346,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004917660491801518,
|
|
"loss": 5.5604,
|
|
"mean_token_accuracy": 0.17394228130578995,
|
|
"num_tokens": 19200662.0,
|
|
"step": 8605
|
|
},
|
|
{
|
|
"entropy": 5.648424863815308,
|
|
"epoch": 0.9670354355028922,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004917552838162324,
|
|
"loss": 5.4598,
|
|
"mean_token_accuracy": 0.18265042901039125,
|
|
"num_tokens": 19211535.0,
|
|
"step": 8610
|
|
},
|
|
{
|
|
"entropy": 5.628148460388184,
|
|
"epoch": 0.9675970124108496,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.0004917445115507408,
|
|
"loss": 5.4433,
|
|
"mean_token_accuracy": 0.18630209118127822,
|
|
"num_tokens": 19223402.0,
|
|
"step": 8615
|
|
},
|
|
{
|
|
"entropy": 5.487207746505737,
|
|
"epoch": 0.9681585893188072,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004917337323840198,
|
|
"loss": 5.5248,
|
|
"mean_token_accuracy": 0.17707892805337905,
|
|
"num_tokens": 19234976.0,
|
|
"step": 8620
|
|
},
|
|
{
|
|
"entropy": 5.468156814575195,
|
|
"epoch": 0.9687201662267647,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004917229463164128,
|
|
"loss": 5.3766,
|
|
"mean_token_accuracy": 0.18640546053647994,
|
|
"num_tokens": 19247328.0,
|
|
"step": 8625
|
|
},
|
|
{
|
|
"entropy": 5.678643655776978,
|
|
"epoch": 0.9692817431347223,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004917121533482631,
|
|
"loss": 5.5186,
|
|
"mean_token_accuracy": 0.17082815170288085,
|
|
"num_tokens": 19259021.0,
|
|
"step": 8630
|
|
},
|
|
{
|
|
"entropy": 5.5514545917510985,
|
|
"epoch": 0.9698433200426798,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.0004917013534799144,
|
|
"loss": 5.4829,
|
|
"mean_token_accuracy": 0.17271644324064256,
|
|
"num_tokens": 19270021.0,
|
|
"step": 8635
|
|
},
|
|
{
|
|
"entropy": 5.603173446655274,
|
|
"epoch": 0.9704048969506374,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004916905467117104,
|
|
"loss": 5.5294,
|
|
"mean_token_accuracy": 0.18102877885103225,
|
|
"num_tokens": 19281520.0,
|
|
"step": 8640
|
|
},
|
|
{
|
|
"entropy": 5.627556180953979,
|
|
"epoch": 0.9709664738585949,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004916797330439955,
|
|
"loss": 5.4723,
|
|
"mean_token_accuracy": 0.1788710445165634,
|
|
"num_tokens": 19292761.0,
|
|
"step": 8645
|
|
},
|
|
{
|
|
"entropy": 5.644547462463379,
|
|
"epoch": 0.9715280507665525,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004916689124771138,
|
|
"loss": 5.5805,
|
|
"mean_token_accuracy": 0.17524223029613495,
|
|
"num_tokens": 19305022.0,
|
|
"step": 8650
|
|
},
|
|
{
|
|
"entropy": 5.744730758666992,
|
|
"epoch": 0.97208962767451,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004916580850114099,
|
|
"loss": 5.6912,
|
|
"mean_token_accuracy": 0.1697470173239708,
|
|
"num_tokens": 19316162.0,
|
|
"step": 8655
|
|
},
|
|
{
|
|
"entropy": 5.853869438171387,
|
|
"epoch": 0.9726512045824676,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004916472506472286,
|
|
"loss": 5.6904,
|
|
"mean_token_accuracy": 0.16199478805065154,
|
|
"num_tokens": 19327015.0,
|
|
"step": 8660
|
|
},
|
|
{
|
|
"entropy": 5.628166675567627,
|
|
"epoch": 0.9732127814904251,
|
|
"grad_norm": 2.703125,
|
|
"learning_rate": 0.0004916364093849147,
|
|
"loss": 5.5602,
|
|
"mean_token_accuracy": 0.1737251363694668,
|
|
"num_tokens": 19338384.0,
|
|
"step": 8665
|
|
},
|
|
{
|
|
"entropy": 5.600831985473633,
|
|
"epoch": 0.9737743583983827,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004916255612248136,
|
|
"loss": 5.4773,
|
|
"mean_token_accuracy": 0.18174067735671998,
|
|
"num_tokens": 19349846.0,
|
|
"step": 8670
|
|
},
|
|
{
|
|
"entropy": 5.7154128074646,
|
|
"epoch": 0.9743359353063402,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004916147061672706,
|
|
"loss": 5.5172,
|
|
"mean_token_accuracy": 0.17738369554281236,
|
|
"num_tokens": 19361399.0,
|
|
"step": 8675
|
|
},
|
|
{
|
|
"entropy": 5.6050217628479,
|
|
"epoch": 0.9748975122142978,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004916038442126314,
|
|
"loss": 5.4925,
|
|
"mean_token_accuracy": 0.1719199925661087,
|
|
"num_tokens": 19371990.0,
|
|
"step": 8680
|
|
},
|
|
{
|
|
"entropy": 5.553276252746582,
|
|
"epoch": 0.9754590891222553,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004915929753612416,
|
|
"loss": 5.4993,
|
|
"mean_token_accuracy": 0.17748630344867705,
|
|
"num_tokens": 19383135.0,
|
|
"step": 8685
|
|
},
|
|
{
|
|
"entropy": 5.666282701492309,
|
|
"epoch": 0.9760206660302129,
|
|
"grad_norm": 2.625,
|
|
"learning_rate": 0.0004915820996134477,
|
|
"loss": 5.5743,
|
|
"mean_token_accuracy": 0.17527981400489806,
|
|
"num_tokens": 19393942.0,
|
|
"step": 8690
|
|
},
|
|
{
|
|
"entropy": 5.59716305732727,
|
|
"epoch": 0.9765822429381704,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004915712169695956,
|
|
"loss": 5.411,
|
|
"mean_token_accuracy": 0.1805658981204033,
|
|
"num_tokens": 19404255.0,
|
|
"step": 8695
|
|
},
|
|
{
|
|
"entropy": 5.596176338195801,
|
|
"epoch": 0.977143819846128,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.000491560327430032,
|
|
"loss": 5.5122,
|
|
"mean_token_accuracy": 0.17859420478343963,
|
|
"num_tokens": 19415425.0,
|
|
"step": 8700
|
|
},
|
|
{
|
|
"entropy": 5.594195079803467,
|
|
"epoch": 0.9777053967540855,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004915494309951035,
|
|
"loss": 5.4588,
|
|
"mean_token_accuracy": 0.18495271801948548,
|
|
"num_tokens": 19426050.0,
|
|
"step": 8705
|
|
},
|
|
{
|
|
"entropy": 5.647588205337525,
|
|
"epoch": 0.9782669736620431,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004915385276651573,
|
|
"loss": 5.5586,
|
|
"mean_token_accuracy": 0.1710285097360611,
|
|
"num_tokens": 19437471.0,
|
|
"step": 8710
|
|
},
|
|
{
|
|
"entropy": 5.6465130805969235,
|
|
"epoch": 0.9788285505700005,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004915276174405403,
|
|
"loss": 5.587,
|
|
"mean_token_accuracy": 0.17624323666095734,
|
|
"num_tokens": 19449569.0,
|
|
"step": 8715
|
|
},
|
|
{
|
|
"entropy": 5.666909074783325,
|
|
"epoch": 0.9793901274779581,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004915167003215999,
|
|
"loss": 5.6053,
|
|
"mean_token_accuracy": 0.17028293907642364,
|
|
"num_tokens": 19461630.0,
|
|
"step": 8720
|
|
},
|
|
{
|
|
"entropy": 5.637751913070678,
|
|
"epoch": 0.9799517043859156,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004915057763086838,
|
|
"loss": 5.5337,
|
|
"mean_token_accuracy": 0.17756096571683883,
|
|
"num_tokens": 19472626.0,
|
|
"step": 8725
|
|
},
|
|
{
|
|
"entropy": 5.57206540107727,
|
|
"epoch": 0.9805132812938732,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.00049149484540214,
|
|
"loss": 5.5253,
|
|
"mean_token_accuracy": 0.1777624398469925,
|
|
"num_tokens": 19483141.0,
|
|
"step": 8730
|
|
},
|
|
{
|
|
"entropy": 5.650867986679077,
|
|
"epoch": 0.9810748582018307,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004914839076023161,
|
|
"loss": 5.499,
|
|
"mean_token_accuracy": 0.18341919481754304,
|
|
"num_tokens": 19495052.0,
|
|
"step": 8735
|
|
},
|
|
{
|
|
"entropy": 5.702249383926391,
|
|
"epoch": 0.9816364351097883,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004914729629095609,
|
|
"loss": 5.5682,
|
|
"mean_token_accuracy": 0.17288218587636947,
|
|
"num_tokens": 19506911.0,
|
|
"step": 8740
|
|
},
|
|
{
|
|
"entropy": 5.562432861328125,
|
|
"epoch": 0.9821980120177458,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004914620113242224,
|
|
"loss": 5.4369,
|
|
"mean_token_accuracy": 0.18190908581018447,
|
|
"num_tokens": 19517812.0,
|
|
"step": 8745
|
|
},
|
|
{
|
|
"entropy": 5.673620414733887,
|
|
"epoch": 0.9827595889257034,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004914510528466495,
|
|
"loss": 5.5298,
|
|
"mean_token_accuracy": 0.176532019674778,
|
|
"num_tokens": 19529857.0,
|
|
"step": 8750
|
|
},
|
|
{
|
|
"entropy": 5.6598528861999515,
|
|
"epoch": 0.9833211658336609,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004914400874771913,
|
|
"loss": 5.5514,
|
|
"mean_token_accuracy": 0.17500680088996887,
|
|
"num_tokens": 19541082.0,
|
|
"step": 8755
|
|
},
|
|
{
|
|
"entropy": 5.5744036674499515,
|
|
"epoch": 0.9838827427416185,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004914291152161967,
|
|
"loss": 5.4743,
|
|
"mean_token_accuracy": 0.18563976138830185,
|
|
"num_tokens": 19551266.0,
|
|
"step": 8760
|
|
},
|
|
{
|
|
"entropy": 5.674076700210572,
|
|
"epoch": 0.984444319649576,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.000491418136064015,
|
|
"loss": 5.662,
|
|
"mean_token_accuracy": 0.17542957365512848,
|
|
"num_tokens": 19563381.0,
|
|
"step": 8765
|
|
},
|
|
{
|
|
"entropy": 5.752225589752197,
|
|
"epoch": 0.9850058965575336,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.000491407150020996,
|
|
"loss": 5.6875,
|
|
"mean_token_accuracy": 0.174013951420784,
|
|
"num_tokens": 19575078.0,
|
|
"step": 8770
|
|
},
|
|
{
|
|
"entropy": 5.6871308326721195,
|
|
"epoch": 0.9855674734654911,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004913961570874895,
|
|
"loss": 5.4838,
|
|
"mean_token_accuracy": 0.1798838794231415,
|
|
"num_tokens": 19585273.0,
|
|
"step": 8775
|
|
},
|
|
{
|
|
"entropy": 5.567116832733154,
|
|
"epoch": 0.9861290503734487,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004913851572638453,
|
|
"loss": 5.4983,
|
|
"mean_token_accuracy": 0.17919607013463973,
|
|
"num_tokens": 19594245.0,
|
|
"step": 8780
|
|
},
|
|
{
|
|
"entropy": 5.678967380523682,
|
|
"epoch": 0.9866906272814062,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004913741505504138,
|
|
"loss": 5.5321,
|
|
"mean_token_accuracy": 0.17172959744930266,
|
|
"num_tokens": 19604920.0,
|
|
"step": 8785
|
|
},
|
|
{
|
|
"entropy": 5.7392435550689695,
|
|
"epoch": 0.9872522041893638,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004913631369475454,
|
|
"loss": 5.6313,
|
|
"mean_token_accuracy": 0.17030101865530015,
|
|
"num_tokens": 19616592.0,
|
|
"step": 8790
|
|
},
|
|
{
|
|
"entropy": 5.726884555816651,
|
|
"epoch": 0.9878137810973213,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004913521164555909,
|
|
"loss": 5.5896,
|
|
"mean_token_accuracy": 0.17396857142448424,
|
|
"num_tokens": 19627359.0,
|
|
"step": 8795
|
|
},
|
|
{
|
|
"entropy": 5.6828028678894045,
|
|
"epoch": 0.9883753580052789,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.000491341089074901,
|
|
"loss": 5.5506,
|
|
"mean_token_accuracy": 0.1802465796470642,
|
|
"num_tokens": 19639685.0,
|
|
"step": 8800
|
|
},
|
|
{
|
|
"entropy": 5.56529130935669,
|
|
"epoch": 0.9889369349132364,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.000491330054805827,
|
|
"loss": 5.3945,
|
|
"mean_token_accuracy": 0.18767881393432617,
|
|
"num_tokens": 19650525.0,
|
|
"step": 8805
|
|
},
|
|
{
|
|
"entropy": 5.508602094650269,
|
|
"epoch": 0.9894985118211939,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004913190136487201,
|
|
"loss": 5.4621,
|
|
"mean_token_accuracy": 0.1844386488199234,
|
|
"num_tokens": 19662241.0,
|
|
"step": 8810
|
|
},
|
|
{
|
|
"entropy": 5.670568418502808,
|
|
"epoch": 0.9900600887291514,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004913079656039318,
|
|
"loss": 5.5329,
|
|
"mean_token_accuracy": 0.17866535037755965,
|
|
"num_tokens": 19673752.0,
|
|
"step": 8815
|
|
},
|
|
{
|
|
"entropy": 5.600825834274292,
|
|
"epoch": 0.990621665637109,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.0004912969106718142,
|
|
"loss": 5.5253,
|
|
"mean_token_accuracy": 0.17793213129043578,
|
|
"num_tokens": 19685309.0,
|
|
"step": 8820
|
|
},
|
|
{
|
|
"entropy": 5.5946839332580565,
|
|
"epoch": 0.9911832425450665,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.000491285848852719,
|
|
"loss": 5.6214,
|
|
"mean_token_accuracy": 0.1743100419640541,
|
|
"num_tokens": 19697391.0,
|
|
"step": 8825
|
|
},
|
|
{
|
|
"entropy": 5.695317173004151,
|
|
"epoch": 0.9917448194530241,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004912747801469984,
|
|
"loss": 5.5893,
|
|
"mean_token_accuracy": 0.17411051988601683,
|
|
"num_tokens": 19707426.0,
|
|
"step": 8830
|
|
},
|
|
{
|
|
"entropy": 5.710868787765503,
|
|
"epoch": 0.9923063963609816,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.000491263704555005,
|
|
"loss": 5.6053,
|
|
"mean_token_accuracy": 0.17150882482528687,
|
|
"num_tokens": 19719800.0,
|
|
"step": 8835
|
|
},
|
|
{
|
|
"entropy": 5.579995489120483,
|
|
"epoch": 0.9928679732689392,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004912526220770913,
|
|
"loss": 5.5116,
|
|
"mean_token_accuracy": 0.17503908276557922,
|
|
"num_tokens": 19731600.0,
|
|
"step": 8840
|
|
},
|
|
{
|
|
"entropy": 5.720822381973266,
|
|
"epoch": 0.9934295501768967,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004912415327136103,
|
|
"loss": 5.5118,
|
|
"mean_token_accuracy": 0.1760959282517433,
|
|
"num_tokens": 19742610.0,
|
|
"step": 8845
|
|
},
|
|
{
|
|
"entropy": 5.776559829711914,
|
|
"epoch": 0.9939911270848543,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.000491230436464915,
|
|
"loss": 5.721,
|
|
"mean_token_accuracy": 0.1640644207596779,
|
|
"num_tokens": 19754207.0,
|
|
"step": 8850
|
|
},
|
|
{
|
|
"entropy": 5.636538934707642,
|
|
"epoch": 0.9945527039928118,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004912193333313589,
|
|
"loss": 5.4245,
|
|
"mean_token_accuracy": 0.1815497785806656,
|
|
"num_tokens": 19765894.0,
|
|
"step": 8855
|
|
},
|
|
{
|
|
"entropy": 5.662306404113769,
|
|
"epoch": 0.9951142809007694,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004912082233132951,
|
|
"loss": 5.5738,
|
|
"mean_token_accuracy": 0.17184434235095977,
|
|
"num_tokens": 19777867.0,
|
|
"step": 8860
|
|
},
|
|
{
|
|
"entropy": 5.616130352020264,
|
|
"epoch": 0.9956758578087269,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004911971064110778,
|
|
"loss": 5.461,
|
|
"mean_token_accuracy": 0.1819846212863922,
|
|
"num_tokens": 19788346.0,
|
|
"step": 8865
|
|
},
|
|
{
|
|
"entropy": 5.745035696029663,
|
|
"epoch": 0.9962374347166845,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004911859826250607,
|
|
"loss": 5.6139,
|
|
"mean_token_accuracy": 0.18041548728942872,
|
|
"num_tokens": 19799752.0,
|
|
"step": 8870
|
|
},
|
|
{
|
|
"entropy": 5.649567937850952,
|
|
"epoch": 0.996799011624642,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004911748519555981,
|
|
"loss": 5.5514,
|
|
"mean_token_accuracy": 0.1762547880411148,
|
|
"num_tokens": 19810387.0,
|
|
"step": 8875
|
|
},
|
|
{
|
|
"entropy": 5.572876071929931,
|
|
"epoch": 0.9973605885325996,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004911637144030444,
|
|
"loss": 5.521,
|
|
"mean_token_accuracy": 0.17834608554840087,
|
|
"num_tokens": 19822092.0,
|
|
"step": 8880
|
|
},
|
|
{
|
|
"entropy": 5.707835960388183,
|
|
"epoch": 0.9979221654405571,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004911525699677541,
|
|
"loss": 5.6279,
|
|
"mean_token_accuracy": 0.16719121038913726,
|
|
"num_tokens": 19833731.0,
|
|
"step": 8885
|
|
},
|
|
{
|
|
"entropy": 5.668497037887573,
|
|
"epoch": 0.9984837423485147,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004911414186500822,
|
|
"loss": 5.5636,
|
|
"mean_token_accuracy": 0.1742876499891281,
|
|
"num_tokens": 19845101.0,
|
|
"step": 8890
|
|
},
|
|
{
|
|
"entropy": 5.6994829177856445,
|
|
"epoch": 0.9990453192564722,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004911302604503837,
|
|
"loss": 5.6231,
|
|
"mean_token_accuracy": 0.17030643969774245,
|
|
"num_tokens": 19857006.0,
|
|
"step": 8895
|
|
},
|
|
{
|
|
"entropy": 5.674806213378906,
|
|
"epoch": 0.9996068961644298,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004911190953690139,
|
|
"loss": 5.4978,
|
|
"mean_token_accuracy": 0.18147013634443282,
|
|
"num_tokens": 19868007.0,
|
|
"step": 8900
|
|
},
|
|
{
|
|
"entropy": 5.7907646497090655,
|
|
"epoch": 1.0001123153815914,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004911079234063284,
|
|
"loss": 5.4717,
|
|
"mean_token_accuracy": 0.18072778979937235,
|
|
"num_tokens": 19877897.0,
|
|
"step": 8905
|
|
},
|
|
{
|
|
"entropy": 5.650493812561035,
|
|
"epoch": 1.000673892289549,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004910967445626826,
|
|
"loss": 5.496,
|
|
"mean_token_accuracy": 0.17796591967344283,
|
|
"num_tokens": 19888449.0,
|
|
"step": 8910
|
|
},
|
|
{
|
|
"entropy": 5.612166070938111,
|
|
"epoch": 1.0012354691975065,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004910855588384327,
|
|
"loss": 5.4678,
|
|
"mean_token_accuracy": 0.17649304419755935,
|
|
"num_tokens": 19898998.0,
|
|
"step": 8915
|
|
},
|
|
{
|
|
"entropy": 5.6738122463226315,
|
|
"epoch": 1.0017970461054642,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004910743662339348,
|
|
"loss": 5.4831,
|
|
"mean_token_accuracy": 0.18333123475313187,
|
|
"num_tokens": 19910369.0,
|
|
"step": 8920
|
|
},
|
|
{
|
|
"entropy": 5.721463680267334,
|
|
"epoch": 1.0023586230134216,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004910631667495452,
|
|
"loss": 5.5219,
|
|
"mean_token_accuracy": 0.1823783427476883,
|
|
"num_tokens": 19921936.0,
|
|
"step": 8925
|
|
},
|
|
{
|
|
"entropy": 5.657253789901733,
|
|
"epoch": 1.0029201999213793,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.0004910519603856207,
|
|
"loss": 5.5097,
|
|
"mean_token_accuracy": 0.17559026032686234,
|
|
"num_tokens": 19933943.0,
|
|
"step": 8930
|
|
},
|
|
{
|
|
"entropy": 5.494042158126831,
|
|
"epoch": 1.0034817768293367,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004910407471425179,
|
|
"loss": 5.3106,
|
|
"mean_token_accuracy": 0.18985848128795624,
|
|
"num_tokens": 19944377.0,
|
|
"step": 8935
|
|
},
|
|
{
|
|
"entropy": 5.521006155014038,
|
|
"epoch": 1.0040433537372944,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.000491029527020594,
|
|
"loss": 5.4144,
|
|
"mean_token_accuracy": 0.18066316545009614,
|
|
"num_tokens": 19954865.0,
|
|
"step": 8940
|
|
},
|
|
{
|
|
"entropy": 5.543346166610718,
|
|
"epoch": 1.0046049306452518,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004910183000202061,
|
|
"loss": 5.3318,
|
|
"mean_token_accuracy": 0.19103278070688248,
|
|
"num_tokens": 19965021.0,
|
|
"step": 8945
|
|
},
|
|
{
|
|
"entropy": 5.634443902969361,
|
|
"epoch": 1.0051665075532095,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004910070661417119,
|
|
"loss": 5.4471,
|
|
"mean_token_accuracy": 0.17768314927816392,
|
|
"num_tokens": 19977068.0,
|
|
"step": 8950
|
|
},
|
|
{
|
|
"entropy": 5.5534903049469,
|
|
"epoch": 1.005728084461167,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004909958253854687,
|
|
"loss": 5.474,
|
|
"mean_token_accuracy": 0.17667020857334137,
|
|
"num_tokens": 19987994.0,
|
|
"step": 8955
|
|
},
|
|
{
|
|
"entropy": 5.651862049102784,
|
|
"epoch": 1.0062896613691246,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004909845777518347,
|
|
"loss": 5.4939,
|
|
"mean_token_accuracy": 0.17481962591409683,
|
|
"num_tokens": 19998598.0,
|
|
"step": 8960
|
|
},
|
|
{
|
|
"entropy": 5.622123050689697,
|
|
"epoch": 1.006851238277082,
|
|
"grad_norm": 2.984375,
|
|
"learning_rate": 0.0004909733232411681,
|
|
"loss": 5.385,
|
|
"mean_token_accuracy": 0.1836555555462837,
|
|
"num_tokens": 20008881.0,
|
|
"step": 8965
|
|
},
|
|
{
|
|
"entropy": 5.586540174484253,
|
|
"epoch": 1.0074128151850397,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004909620618538271,
|
|
"loss": 5.4177,
|
|
"mean_token_accuracy": 0.17951451539993285,
|
|
"num_tokens": 20019105.0,
|
|
"step": 8970
|
|
},
|
|
{
|
|
"entropy": 5.579048728942871,
|
|
"epoch": 1.007974392092997,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004909507935901702,
|
|
"loss": 5.4769,
|
|
"mean_token_accuracy": 0.17605098336935043,
|
|
"num_tokens": 20031805.0,
|
|
"step": 8975
|
|
},
|
|
{
|
|
"entropy": 5.62233076095581,
|
|
"epoch": 1.0085359690009548,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004909395184505564,
|
|
"loss": 5.4234,
|
|
"mean_token_accuracy": 0.18534507006406784,
|
|
"num_tokens": 20041493.0,
|
|
"step": 8980
|
|
},
|
|
{
|
|
"entropy": 5.607890892028808,
|
|
"epoch": 1.0090975459089122,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004909282364353445,
|
|
"loss": 5.4807,
|
|
"mean_token_accuracy": 0.18110638111829758,
|
|
"num_tokens": 20052489.0,
|
|
"step": 8985
|
|
},
|
|
{
|
|
"entropy": 5.46955451965332,
|
|
"epoch": 1.0096591228168699,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004909169475448938,
|
|
"loss": 5.4328,
|
|
"mean_token_accuracy": 0.1797465994954109,
|
|
"num_tokens": 20064252.0,
|
|
"step": 8990
|
|
},
|
|
{
|
|
"entropy": 5.621907567977905,
|
|
"epoch": 1.0102206997248273,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004909056517795638,
|
|
"loss": 5.3744,
|
|
"mean_token_accuracy": 0.17497411817312242,
|
|
"num_tokens": 20075171.0,
|
|
"step": 8995
|
|
},
|
|
{
|
|
"entropy": 5.624486780166626,
|
|
"epoch": 1.010782276632785,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004908943491397141,
|
|
"loss": 5.376,
|
|
"mean_token_accuracy": 0.18161926418542862,
|
|
"num_tokens": 20085746.0,
|
|
"step": 9000
|
|
},
|
|
{
|
|
"epoch": 1.010782276632785,
|
|
"eval_entropy": 5.459080059872112,
|
|
"eval_loss": 5.578691005706787,
|
|
"eval_mean_token_accuracy": 0.1821541891581993,
|
|
"eval_num_tokens": 20085746.0,
|
|
"eval_runtime": 23.814,
|
|
"eval_samples_per_second": 1302.304,
|
|
"eval_steps_per_second": 162.804,
|
|
"step": 9000
|
|
},
|
|
{
|
|
"entropy": 5.554215002059936,
|
|
"epoch": 1.0113438535407424,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004908830396257045,
|
|
"loss": 5.4536,
|
|
"mean_token_accuracy": 0.17544384002685548,
|
|
"num_tokens": 20097435.0,
|
|
"step": 9005
|
|
},
|
|
{
|
|
"entropy": 5.565097761154175,
|
|
"epoch": 1.0119054304486998,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004908717232378953,
|
|
"loss": 5.4455,
|
|
"mean_token_accuracy": 0.17849185615777968,
|
|
"num_tokens": 20108100.0,
|
|
"step": 9010
|
|
},
|
|
{
|
|
"entropy": 5.682046175003052,
|
|
"epoch": 1.0124670073566575,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004908603999766467,
|
|
"loss": 5.4581,
|
|
"mean_token_accuracy": 0.17797257453203202,
|
|
"num_tokens": 20119042.0,
|
|
"step": 9015
|
|
},
|
|
{
|
|
"entropy": 5.565086078643799,
|
|
"epoch": 1.013028584264615,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004908490698423191,
|
|
"loss": 5.5158,
|
|
"mean_token_accuracy": 0.17789216041564943,
|
|
"num_tokens": 20130275.0,
|
|
"step": 9020
|
|
},
|
|
{
|
|
"entropy": 5.555480098724365,
|
|
"epoch": 1.0135901611725726,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004908377328352736,
|
|
"loss": 5.4629,
|
|
"mean_token_accuracy": 0.17693307846784592,
|
|
"num_tokens": 20142523.0,
|
|
"step": 9025
|
|
},
|
|
{
|
|
"entropy": 5.602287340164184,
|
|
"epoch": 1.01415173808053,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004908263889558709,
|
|
"loss": 5.4208,
|
|
"mean_token_accuracy": 0.18608217239379882,
|
|
"num_tokens": 20153732.0,
|
|
"step": 9030
|
|
},
|
|
{
|
|
"entropy": 5.6788112163543705,
|
|
"epoch": 1.0147133149884877,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004908150382044722,
|
|
"loss": 5.4983,
|
|
"mean_token_accuracy": 0.17320408672094345,
|
|
"num_tokens": 20165136.0,
|
|
"step": 9035
|
|
},
|
|
{
|
|
"entropy": 5.568822240829467,
|
|
"epoch": 1.0152748918964452,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.000490803680581439,
|
|
"loss": 5.4291,
|
|
"mean_token_accuracy": 0.18082266598939895,
|
|
"num_tokens": 20175326.0,
|
|
"step": 9040
|
|
},
|
|
{
|
|
"entropy": 5.587617254257202,
|
|
"epoch": 1.0158364688044028,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.000490792316087133,
|
|
"loss": 5.3695,
|
|
"mean_token_accuracy": 0.18594837188720703,
|
|
"num_tokens": 20186678.0,
|
|
"step": 9045
|
|
},
|
|
{
|
|
"entropy": 5.539478063583374,
|
|
"epoch": 1.0163980457123603,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004907809447219158,
|
|
"loss": 5.3786,
|
|
"mean_token_accuracy": 0.18022306710481645,
|
|
"num_tokens": 20196696.0,
|
|
"step": 9050
|
|
},
|
|
{
|
|
"entropy": 5.565349864959717,
|
|
"epoch": 1.016959622620318,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004907695664861498,
|
|
"loss": 5.4002,
|
|
"mean_token_accuracy": 0.18411532640457154,
|
|
"num_tokens": 20207566.0,
|
|
"step": 9055
|
|
},
|
|
{
|
|
"entropy": 5.537447357177735,
|
|
"epoch": 1.0175211995282754,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004907581813801971,
|
|
"loss": 5.4409,
|
|
"mean_token_accuracy": 0.17487737089395522,
|
|
"num_tokens": 20218233.0,
|
|
"step": 9060
|
|
},
|
|
{
|
|
"entropy": 5.616069173812866,
|
|
"epoch": 1.018082776436233,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004907467894044202,
|
|
"loss": 5.3577,
|
|
"mean_token_accuracy": 0.18108492195606232,
|
|
"num_tokens": 20228524.0,
|
|
"step": 9065
|
|
},
|
|
{
|
|
"entropy": 5.5232336044311525,
|
|
"epoch": 1.0186443533441905,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004907353905591817,
|
|
"loss": 5.4619,
|
|
"mean_token_accuracy": 0.1800857111811638,
|
|
"num_tokens": 20240821.0,
|
|
"step": 9070
|
|
},
|
|
{
|
|
"entropy": 5.537438440322876,
|
|
"epoch": 1.0192059302521481,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.000490723984844845,
|
|
"loss": 5.4308,
|
|
"mean_token_accuracy": 0.18032869696617126,
|
|
"num_tokens": 20252282.0,
|
|
"step": 9075
|
|
},
|
|
{
|
|
"entropy": 5.6138331413269045,
|
|
"epoch": 1.0197675071601056,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004907125722617727,
|
|
"loss": 5.4367,
|
|
"mean_token_accuracy": 0.18050792068243027,
|
|
"num_tokens": 20263462.0,
|
|
"step": 9080
|
|
},
|
|
{
|
|
"entropy": 5.6108558177948,
|
|
"epoch": 1.0203290840680632,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004907011528103285,
|
|
"loss": 5.4753,
|
|
"mean_token_accuracy": 0.17466021329164505,
|
|
"num_tokens": 20275062.0,
|
|
"step": 9085
|
|
},
|
|
{
|
|
"entropy": 5.608004331588745,
|
|
"epoch": 1.0208906609760207,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004906897264908759,
|
|
"loss": 5.4529,
|
|
"mean_token_accuracy": 0.1767593130469322,
|
|
"num_tokens": 20286243.0,
|
|
"step": 9090
|
|
},
|
|
{
|
|
"entropy": 5.569535255432129,
|
|
"epoch": 1.0214522378839783,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004906782933037789,
|
|
"loss": 5.4607,
|
|
"mean_token_accuracy": 0.17864596843719482,
|
|
"num_tokens": 20296929.0,
|
|
"step": 9095
|
|
},
|
|
{
|
|
"entropy": 5.589272975921631,
|
|
"epoch": 1.0220138147919358,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004906668532494012,
|
|
"loss": 5.3494,
|
|
"mean_token_accuracy": 0.18342964649200438,
|
|
"num_tokens": 20308354.0,
|
|
"step": 9100
|
|
},
|
|
{
|
|
"entropy": 5.610014581680298,
|
|
"epoch": 1.0225753916998932,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004906554063281074,
|
|
"loss": 5.5226,
|
|
"mean_token_accuracy": 0.1788520559668541,
|
|
"num_tokens": 20319487.0,
|
|
"step": 9105
|
|
},
|
|
{
|
|
"entropy": 5.516573715209961,
|
|
"epoch": 1.0231369686078509,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004906439525402618,
|
|
"loss": 5.4296,
|
|
"mean_token_accuracy": 0.18768656700849534,
|
|
"num_tokens": 20329967.0,
|
|
"step": 9110
|
|
},
|
|
{
|
|
"entropy": 5.652112627029419,
|
|
"epoch": 1.0236985455158083,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004906324918862291,
|
|
"loss": 5.5061,
|
|
"mean_token_accuracy": 0.17268284261226655,
|
|
"num_tokens": 20341442.0,
|
|
"step": 9115
|
|
},
|
|
{
|
|
"entropy": 5.684236621856689,
|
|
"epoch": 1.024260122423766,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004906210243663742,
|
|
"loss": 5.6184,
|
|
"mean_token_accuracy": 0.1690230995416641,
|
|
"num_tokens": 20352818.0,
|
|
"step": 9120
|
|
},
|
|
{
|
|
"entropy": 5.731576585769654,
|
|
"epoch": 1.0248216993317234,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004906095499810622,
|
|
"loss": 5.5189,
|
|
"mean_token_accuracy": 0.17407773584127426,
|
|
"num_tokens": 20364787.0,
|
|
"step": 9125
|
|
},
|
|
{
|
|
"entropy": 5.6368835926055905,
|
|
"epoch": 1.025383276239681,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004905980687306586,
|
|
"loss": 5.3863,
|
|
"mean_token_accuracy": 0.193366876244545,
|
|
"num_tokens": 20375491.0,
|
|
"step": 9130
|
|
},
|
|
{
|
|
"entropy": 5.580576801300049,
|
|
"epoch": 1.0259448531476385,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004905865806155288,
|
|
"loss": 5.449,
|
|
"mean_token_accuracy": 0.18474821895360946,
|
|
"num_tokens": 20386270.0,
|
|
"step": 9135
|
|
},
|
|
{
|
|
"entropy": 5.697377729415893,
|
|
"epoch": 1.0265064300555962,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004905750856360387,
|
|
"loss": 5.5493,
|
|
"mean_token_accuracy": 0.17359945625066758,
|
|
"num_tokens": 20397953.0,
|
|
"step": 9140
|
|
},
|
|
{
|
|
"entropy": 5.658065843582153,
|
|
"epoch": 1.0270680069635536,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004905635837925543,
|
|
"loss": 5.5395,
|
|
"mean_token_accuracy": 0.17324478775262833,
|
|
"num_tokens": 20409847.0,
|
|
"step": 9145
|
|
},
|
|
{
|
|
"entropy": 5.628514909744263,
|
|
"epoch": 1.0276295838715113,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004905520750854418,
|
|
"loss": 5.5244,
|
|
"mean_token_accuracy": 0.18113597482442856,
|
|
"num_tokens": 20420737.0,
|
|
"step": 9150
|
|
},
|
|
{
|
|
"entropy": 5.598775434494018,
|
|
"epoch": 1.0281911607794687,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.0004905405595150674,
|
|
"loss": 5.4158,
|
|
"mean_token_accuracy": 0.17999387234449388,
|
|
"num_tokens": 20432395.0,
|
|
"step": 9155
|
|
},
|
|
{
|
|
"entropy": 5.570962142944336,
|
|
"epoch": 1.0287527376874264,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004905290370817982,
|
|
"loss": 5.4113,
|
|
"mean_token_accuracy": 0.1848587855696678,
|
|
"num_tokens": 20442964.0,
|
|
"step": 9160
|
|
},
|
|
{
|
|
"entropy": 5.589252853393555,
|
|
"epoch": 1.0293143145953838,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.000490517507786001,
|
|
"loss": 5.4535,
|
|
"mean_token_accuracy": 0.1752680480480194,
|
|
"num_tokens": 20454050.0,
|
|
"step": 9165
|
|
},
|
|
{
|
|
"entropy": 5.611699819564819,
|
|
"epoch": 1.0298758915033415,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004905059716280425,
|
|
"loss": 5.4671,
|
|
"mean_token_accuracy": 0.17207229137420654,
|
|
"num_tokens": 20465335.0,
|
|
"step": 9170
|
|
},
|
|
{
|
|
"entropy": 5.591488790512085,
|
|
"epoch": 1.030437468411299,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.0004904944286082904,
|
|
"loss": 5.439,
|
|
"mean_token_accuracy": 0.1793852284550667,
|
|
"num_tokens": 20476781.0,
|
|
"step": 9175
|
|
},
|
|
{
|
|
"entropy": 5.579262685775757,
|
|
"epoch": 1.0309990453192566,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004904828787271121,
|
|
"loss": 5.4773,
|
|
"mean_token_accuracy": 0.17789653241634368,
|
|
"num_tokens": 20488599.0,
|
|
"step": 9180
|
|
},
|
|
{
|
|
"entropy": 5.502214145660401,
|
|
"epoch": 1.031560622227214,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004904713219848753,
|
|
"loss": 5.3622,
|
|
"mean_token_accuracy": 0.18779534250497817,
|
|
"num_tokens": 20498215.0,
|
|
"step": 9185
|
|
},
|
|
{
|
|
"entropy": 5.621550893783569,
|
|
"epoch": 1.0321221991351717,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.0004904597583819481,
|
|
"loss": 5.3901,
|
|
"mean_token_accuracy": 0.1827726513147354,
|
|
"num_tokens": 20509764.0,
|
|
"step": 9190
|
|
},
|
|
{
|
|
"entropy": 5.771495628356933,
|
|
"epoch": 1.032683776043129,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004904481879186987,
|
|
"loss": 5.6073,
|
|
"mean_token_accuracy": 0.17733301371335983,
|
|
"num_tokens": 20521582.0,
|
|
"step": 9195
|
|
},
|
|
{
|
|
"entropy": 5.563735485076904,
|
|
"epoch": 1.0332453529510865,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004904366105954954,
|
|
"loss": 5.4825,
|
|
"mean_token_accuracy": 0.17996705174446107,
|
|
"num_tokens": 20532050.0,
|
|
"step": 9200
|
|
},
|
|
{
|
|
"entropy": 5.589707326889038,
|
|
"epoch": 1.0338069298590442,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004904250264127067,
|
|
"loss": 5.4864,
|
|
"mean_token_accuracy": 0.17125514298677444,
|
|
"num_tokens": 20543733.0,
|
|
"step": 9205
|
|
},
|
|
{
|
|
"entropy": 5.674970865249634,
|
|
"epoch": 1.0343685067670016,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004904134353707018,
|
|
"loss": 5.511,
|
|
"mean_token_accuracy": 0.17877715229988098,
|
|
"num_tokens": 20554898.0,
|
|
"step": 9210
|
|
},
|
|
{
|
|
"entropy": 5.539908313751221,
|
|
"epoch": 1.0349300836749593,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004904018374698496,
|
|
"loss": 5.3852,
|
|
"mean_token_accuracy": 0.18103183954954147,
|
|
"num_tokens": 20565243.0,
|
|
"step": 9215
|
|
},
|
|
{
|
|
"entropy": 5.526424217224121,
|
|
"epoch": 1.0354916605829168,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004903902327105191,
|
|
"loss": 5.3783,
|
|
"mean_token_accuracy": 0.18287476301193237,
|
|
"num_tokens": 20575321.0,
|
|
"step": 9220
|
|
},
|
|
{
|
|
"entropy": 5.642215061187744,
|
|
"epoch": 1.0360532374908744,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004903786210930803,
|
|
"loss": 5.55,
|
|
"mean_token_accuracy": 0.16923462599515915,
|
|
"num_tokens": 20586450.0,
|
|
"step": 9225
|
|
},
|
|
{
|
|
"entropy": 5.652804899215698,
|
|
"epoch": 1.0366148143988319,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004903670026179025,
|
|
"loss": 5.5276,
|
|
"mean_token_accuracy": 0.18359616696834563,
|
|
"num_tokens": 20596996.0,
|
|
"step": 9230
|
|
},
|
|
{
|
|
"entropy": 5.593594217300415,
|
|
"epoch": 1.0371763913067895,
|
|
"grad_norm": 3.09375,
|
|
"learning_rate": 0.000490355377285356,
|
|
"loss": 5.4321,
|
|
"mean_token_accuracy": 0.1745638743042946,
|
|
"num_tokens": 20609136.0,
|
|
"step": 9235
|
|
},
|
|
{
|
|
"entropy": 5.649332761764526,
|
|
"epoch": 1.037737968214747,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004903437450958106,
|
|
"loss": 5.509,
|
|
"mean_token_accuracy": 0.17722001522779465,
|
|
"num_tokens": 20620246.0,
|
|
"step": 9240
|
|
},
|
|
{
|
|
"entropy": 5.5271008014678955,
|
|
"epoch": 1.0382995451227046,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004903321060496369,
|
|
"loss": 5.4402,
|
|
"mean_token_accuracy": 0.17385232001543044,
|
|
"num_tokens": 20631678.0,
|
|
"step": 9245
|
|
},
|
|
{
|
|
"entropy": 5.603906536102295,
|
|
"epoch": 1.038861122030662,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004903204601472054,
|
|
"loss": 5.3884,
|
|
"mean_token_accuracy": 0.18640923500061035,
|
|
"num_tokens": 20643287.0,
|
|
"step": 9250
|
|
},
|
|
{
|
|
"entropy": 5.604735088348389,
|
|
"epoch": 1.0394226989386197,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004903088073888869,
|
|
"loss": 5.4314,
|
|
"mean_token_accuracy": 0.18265591114759444,
|
|
"num_tokens": 20655091.0,
|
|
"step": 9255
|
|
},
|
|
{
|
|
"entropy": 5.589794301986695,
|
|
"epoch": 1.0399842758465772,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004902971477750526,
|
|
"loss": 5.4618,
|
|
"mean_token_accuracy": 0.18000126481056214,
|
|
"num_tokens": 20665043.0,
|
|
"step": 9260
|
|
},
|
|
{
|
|
"entropy": 5.543551874160767,
|
|
"epoch": 1.0405458527545348,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004902854813060736,
|
|
"loss": 5.3904,
|
|
"mean_token_accuracy": 0.18817973136901855,
|
|
"num_tokens": 20675225.0,
|
|
"step": 9265
|
|
},
|
|
{
|
|
"entropy": 5.551910877227783,
|
|
"epoch": 1.0411074296624923,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004902738079823213,
|
|
"loss": 5.4656,
|
|
"mean_token_accuracy": 0.17844348698854445,
|
|
"num_tokens": 20686542.0,
|
|
"step": 9270
|
|
},
|
|
{
|
|
"entropy": 5.541519689559936,
|
|
"epoch": 1.04166900657045,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004902621278041674,
|
|
"loss": 5.3959,
|
|
"mean_token_accuracy": 0.18315559178590773,
|
|
"num_tokens": 20697926.0,
|
|
"step": 9275
|
|
},
|
|
{
|
|
"entropy": 5.589543962478638,
|
|
"epoch": 1.0422305834784074,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004902504407719839,
|
|
"loss": 5.5135,
|
|
"mean_token_accuracy": 0.17791294157505036,
|
|
"num_tokens": 20707890.0,
|
|
"step": 9280
|
|
},
|
|
{
|
|
"entropy": 5.623344087600708,
|
|
"epoch": 1.042792160386365,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004902387468861429,
|
|
"loss": 5.4447,
|
|
"mean_token_accuracy": 0.17739499360322952,
|
|
"num_tokens": 20719554.0,
|
|
"step": 9285
|
|
},
|
|
{
|
|
"entropy": 5.6102501392364506,
|
|
"epoch": 1.0433537372943225,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.0004902270461470169,
|
|
"loss": 5.4078,
|
|
"mean_token_accuracy": 0.18083870112895967,
|
|
"num_tokens": 20730899.0,
|
|
"step": 9290
|
|
},
|
|
{
|
|
"entropy": 5.58493447303772,
|
|
"epoch": 1.04391531420228,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.000490215338554978,
|
|
"loss": 5.522,
|
|
"mean_token_accuracy": 0.17751231491565705,
|
|
"num_tokens": 20741839.0,
|
|
"step": 9295
|
|
},
|
|
{
|
|
"entropy": 5.591024684906006,
|
|
"epoch": 1.0444768911102376,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004902036241103994,
|
|
"loss": 5.4857,
|
|
"mean_token_accuracy": 0.18067652583122254,
|
|
"num_tokens": 20753199.0,
|
|
"step": 9300
|
|
},
|
|
{
|
|
"entropy": 5.661981391906738,
|
|
"epoch": 1.045038468018195,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004901919028136539,
|
|
"loss": 5.5496,
|
|
"mean_token_accuracy": 0.17503437399864197,
|
|
"num_tokens": 20764827.0,
|
|
"step": 9305
|
|
},
|
|
{
|
|
"entropy": 5.610328722000122,
|
|
"epoch": 1.0456000449261527,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004901801746651147,
|
|
"loss": 5.4256,
|
|
"mean_token_accuracy": 0.18545343726873398,
|
|
"num_tokens": 20774953.0,
|
|
"step": 9310
|
|
},
|
|
{
|
|
"entropy": 5.571823215484619,
|
|
"epoch": 1.04616162183411,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004901684396651554,
|
|
"loss": 5.4427,
|
|
"mean_token_accuracy": 0.18092939853668213,
|
|
"num_tokens": 20784428.0,
|
|
"step": 9315
|
|
},
|
|
{
|
|
"entropy": 5.598528337478638,
|
|
"epoch": 1.0467231987420678,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004901566978141494,
|
|
"loss": 5.512,
|
|
"mean_token_accuracy": 0.17941481471061707,
|
|
"num_tokens": 20795672.0,
|
|
"step": 9320
|
|
},
|
|
{
|
|
"entropy": 5.651431894302368,
|
|
"epoch": 1.0472847756500252,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004901449491124708,
|
|
"loss": 5.5068,
|
|
"mean_token_accuracy": 0.1770174965262413,
|
|
"num_tokens": 20806972.0,
|
|
"step": 9325
|
|
},
|
|
{
|
|
"entropy": 5.64578070640564,
|
|
"epoch": 1.0478463525579829,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004901331935604936,
|
|
"loss": 5.5248,
|
|
"mean_token_accuracy": 0.17678644359111786,
|
|
"num_tokens": 20817867.0,
|
|
"step": 9330
|
|
},
|
|
{
|
|
"entropy": 5.498245143890381,
|
|
"epoch": 1.0484079294659403,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.000490121431158592,
|
|
"loss": 5.3575,
|
|
"mean_token_accuracy": 0.18257005363702775,
|
|
"num_tokens": 20829205.0,
|
|
"step": 9335
|
|
},
|
|
{
|
|
"entropy": 5.572736358642578,
|
|
"epoch": 1.048969506373898,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004901096619071407,
|
|
"loss": 5.4797,
|
|
"mean_token_accuracy": 0.18204336166381835,
|
|
"num_tokens": 20840478.0,
|
|
"step": 9340
|
|
},
|
|
{
|
|
"entropy": 5.658757066726684,
|
|
"epoch": 1.0495310832818554,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004900978858065142,
|
|
"loss": 5.4306,
|
|
"mean_token_accuracy": 0.18008593916893006,
|
|
"num_tokens": 20850752.0,
|
|
"step": 9345
|
|
},
|
|
{
|
|
"entropy": 5.604446268081665,
|
|
"epoch": 1.050092660189813,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004900861028570877,
|
|
"loss": 5.4501,
|
|
"mean_token_accuracy": 0.17572760283946992,
|
|
"num_tokens": 20862261.0,
|
|
"step": 9350
|
|
},
|
|
{
|
|
"entropy": 5.5822326183319095,
|
|
"epoch": 1.0506542370977705,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004900743130592362,
|
|
"loss": 5.4086,
|
|
"mean_token_accuracy": 0.18594421893358232,
|
|
"num_tokens": 20872604.0,
|
|
"step": 9355
|
|
},
|
|
{
|
|
"entropy": 5.4873597621917725,
|
|
"epoch": 1.0512158140057282,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004900625164133351,
|
|
"loss": 5.3491,
|
|
"mean_token_accuracy": 0.19344383776187896,
|
|
"num_tokens": 20882751.0,
|
|
"step": 9360
|
|
},
|
|
{
|
|
"entropy": 5.581871128082275,
|
|
"epoch": 1.0517773909136856,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.0004900507129197601,
|
|
"loss": 5.4704,
|
|
"mean_token_accuracy": 0.17706203758716582,
|
|
"num_tokens": 20893809.0,
|
|
"step": 9365
|
|
},
|
|
{
|
|
"entropy": 5.692767477035522,
|
|
"epoch": 1.0523389678216433,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004900389025788871,
|
|
"loss": 5.3872,
|
|
"mean_token_accuracy": 0.18640353083610534,
|
|
"num_tokens": 20904201.0,
|
|
"step": 9370
|
|
},
|
|
{
|
|
"entropy": 5.554631233215332,
|
|
"epoch": 1.0529005447296007,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.000490027085391092,
|
|
"loss": 5.4679,
|
|
"mean_token_accuracy": 0.17571618407964706,
|
|
"num_tokens": 20915226.0,
|
|
"step": 9375
|
|
},
|
|
{
|
|
"entropy": 5.554903602600097,
|
|
"epoch": 1.0534621216375584,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.000490015261356751,
|
|
"loss": 5.4384,
|
|
"mean_token_accuracy": 0.1765777975320816,
|
|
"num_tokens": 20926040.0,
|
|
"step": 9380
|
|
},
|
|
{
|
|
"entropy": 5.656567096710205,
|
|
"epoch": 1.0540236985455158,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004900034304762408,
|
|
"loss": 5.4719,
|
|
"mean_token_accuracy": 0.18317525684833527,
|
|
"num_tokens": 20937051.0,
|
|
"step": 9385
|
|
},
|
|
{
|
|
"entropy": 5.586511945724487,
|
|
"epoch": 1.0545852754534732,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.000489991592749938,
|
|
"loss": 5.4956,
|
|
"mean_token_accuracy": 0.17753477841615678,
|
|
"num_tokens": 20947810.0,
|
|
"step": 9390
|
|
},
|
|
{
|
|
"entropy": 5.570503187179566,
|
|
"epoch": 1.055146852361431,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004899797481782193,
|
|
"loss": 5.4455,
|
|
"mean_token_accuracy": 0.17481617033481597,
|
|
"num_tokens": 20958307.0,
|
|
"step": 9395
|
|
},
|
|
{
|
|
"entropy": 5.539948797225952,
|
|
"epoch": 1.0557084292693883,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004899678967614623,
|
|
"loss": 5.3425,
|
|
"mean_token_accuracy": 0.18573132604360582,
|
|
"num_tokens": 20969493.0,
|
|
"step": 9400
|
|
},
|
|
{
|
|
"entropy": 5.6041279315948485,
|
|
"epoch": 1.056270006177346,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004899560385000439,
|
|
"loss": 5.505,
|
|
"mean_token_accuracy": 0.1813835933804512,
|
|
"num_tokens": 20980224.0,
|
|
"step": 9405
|
|
},
|
|
{
|
|
"entropy": 5.611564826965332,
|
|
"epoch": 1.0568315830853034,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.000489944173394342,
|
|
"loss": 5.465,
|
|
"mean_token_accuracy": 0.18255140036344528,
|
|
"num_tokens": 20991282.0,
|
|
"step": 9410
|
|
},
|
|
{
|
|
"entropy": 5.660673666000366,
|
|
"epoch": 1.0573931599932611,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004899323014447342,
|
|
"loss": 5.4889,
|
|
"mean_token_accuracy": 0.17426551580429078,
|
|
"num_tokens": 21002395.0,
|
|
"step": 9415
|
|
},
|
|
{
|
|
"entropy": 5.554814577102661,
|
|
"epoch": 1.0579547369012186,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004899204226515985,
|
|
"loss": 5.4145,
|
|
"mean_token_accuracy": 0.17696548700332643,
|
|
"num_tokens": 21014136.0,
|
|
"step": 9420
|
|
},
|
|
{
|
|
"entropy": 5.621621894836426,
|
|
"epoch": 1.0585163138091762,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004899085370153133,
|
|
"loss": 5.5344,
|
|
"mean_token_accuracy": 0.1757613092660904,
|
|
"num_tokens": 21025637.0,
|
|
"step": 9425
|
|
},
|
|
{
|
|
"entropy": 5.781061601638794,
|
|
"epoch": 1.0590778907171337,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004898966445362569,
|
|
"loss": 5.5789,
|
|
"mean_token_accuracy": 0.1691136360168457,
|
|
"num_tokens": 21036393.0,
|
|
"step": 9430
|
|
},
|
|
{
|
|
"entropy": 5.683920192718506,
|
|
"epoch": 1.0596394676250913,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004898847452148079,
|
|
"loss": 5.5224,
|
|
"mean_token_accuracy": 0.1836437076330185,
|
|
"num_tokens": 21047339.0,
|
|
"step": 9435
|
|
},
|
|
{
|
|
"entropy": 5.654892826080323,
|
|
"epoch": 1.0602010445330488,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004898728390513454,
|
|
"loss": 5.6236,
|
|
"mean_token_accuracy": 0.17097096592187883,
|
|
"num_tokens": 21059427.0,
|
|
"step": 9440
|
|
},
|
|
{
|
|
"entropy": 5.628730916976929,
|
|
"epoch": 1.0607626214410064,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004898609260462483,
|
|
"loss": 5.4506,
|
|
"mean_token_accuracy": 0.17322685420513154,
|
|
"num_tokens": 21068666.0,
|
|
"step": 9445
|
|
},
|
|
{
|
|
"entropy": 5.65942964553833,
|
|
"epoch": 1.0613241983489639,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004898490061998961,
|
|
"loss": 5.4612,
|
|
"mean_token_accuracy": 0.17689654380083084,
|
|
"num_tokens": 21080161.0,
|
|
"step": 9450
|
|
},
|
|
{
|
|
"entropy": 5.6597339630126955,
|
|
"epoch": 1.0618857752569215,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004898370795126681,
|
|
"loss": 5.5456,
|
|
"mean_token_accuracy": 0.17456338703632354,
|
|
"num_tokens": 21092363.0,
|
|
"step": 9455
|
|
},
|
|
{
|
|
"entropy": 5.5144401550292965,
|
|
"epoch": 1.062447352164879,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004898251459849441,
|
|
"loss": 5.4438,
|
|
"mean_token_accuracy": 0.18251396864652633,
|
|
"num_tokens": 21103683.0,
|
|
"step": 9460
|
|
},
|
|
{
|
|
"entropy": 5.56109733581543,
|
|
"epoch": 1.0630089290728366,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004898132056171041,
|
|
"loss": 5.3997,
|
|
"mean_token_accuracy": 0.18426249623298646,
|
|
"num_tokens": 21115110.0,
|
|
"step": 9465
|
|
},
|
|
{
|
|
"entropy": 5.616233873367309,
|
|
"epoch": 1.063570505980794,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004898012584095285,
|
|
"loss": 5.3795,
|
|
"mean_token_accuracy": 0.1885729670524597,
|
|
"num_tokens": 21124327.0,
|
|
"step": 9470
|
|
},
|
|
{
|
|
"entropy": 5.565642499923706,
|
|
"epoch": 1.0641320828887517,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004897893043625975,
|
|
"loss": 5.5125,
|
|
"mean_token_accuracy": 0.17969844341278077,
|
|
"num_tokens": 21135542.0,
|
|
"step": 9475
|
|
},
|
|
{
|
|
"entropy": 5.537214708328247,
|
|
"epoch": 1.0646936597967092,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004897773434766917,
|
|
"loss": 5.4006,
|
|
"mean_token_accuracy": 0.17806485891342164,
|
|
"num_tokens": 21147621.0,
|
|
"step": 9480
|
|
},
|
|
{
|
|
"entropy": 5.565270471572876,
|
|
"epoch": 1.0652552367046666,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.000489765375752192,
|
|
"loss": 5.4054,
|
|
"mean_token_accuracy": 0.18055632710456848,
|
|
"num_tokens": 21159725.0,
|
|
"step": 9485
|
|
},
|
|
{
|
|
"entropy": 5.556740951538086,
|
|
"epoch": 1.0658168136126243,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004897534011894793,
|
|
"loss": 5.4692,
|
|
"mean_token_accuracy": 0.1807580292224884,
|
|
"num_tokens": 21171303.0,
|
|
"step": 9490
|
|
},
|
|
{
|
|
"entropy": 5.706756448745727,
|
|
"epoch": 1.0663783905205817,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004897414197889352,
|
|
"loss": 5.5675,
|
|
"mean_token_accuracy": 0.17455703616142274,
|
|
"num_tokens": 21183376.0,
|
|
"step": 9495
|
|
},
|
|
{
|
|
"entropy": 5.659519624710083,
|
|
"epoch": 1.0669399674285394,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.000489729431550941,
|
|
"loss": 5.4447,
|
|
"mean_token_accuracy": 0.17345247715711593,
|
|
"num_tokens": 21194365.0,
|
|
"step": 9500
|
|
},
|
|
{
|
|
"entropy": 5.444472789764404,
|
|
"epoch": 1.0675015443364968,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004897174364758783,
|
|
"loss": 5.3153,
|
|
"mean_token_accuracy": 0.18512341380119324,
|
|
"num_tokens": 21206440.0,
|
|
"step": 9505
|
|
},
|
|
{
|
|
"entropy": 5.455184984207153,
|
|
"epoch": 1.0680631212444545,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004897054345641291,
|
|
"loss": 5.369,
|
|
"mean_token_accuracy": 0.18379151225090026,
|
|
"num_tokens": 21217188.0,
|
|
"step": 9510
|
|
},
|
|
{
|
|
"entropy": 5.570040655136109,
|
|
"epoch": 1.068624698152412,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004896934258160757,
|
|
"loss": 5.4465,
|
|
"mean_token_accuracy": 0.17723545730113982,
|
|
"num_tokens": 21227716.0,
|
|
"step": 9515
|
|
},
|
|
{
|
|
"entropy": 5.643634176254272,
|
|
"epoch": 1.0691862750603696,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004896814102321004,
|
|
"loss": 5.5694,
|
|
"mean_token_accuracy": 0.17157238572835923,
|
|
"num_tokens": 21241258.0,
|
|
"step": 9520
|
|
},
|
|
{
|
|
"entropy": 5.599542284011841,
|
|
"epoch": 1.069747851968327,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004896693878125857,
|
|
"loss": 5.3809,
|
|
"mean_token_accuracy": 0.1786022424697876,
|
|
"num_tokens": 21252543.0,
|
|
"step": 9525
|
|
},
|
|
{
|
|
"entropy": 5.616940689086914,
|
|
"epoch": 1.0703094288762847,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004896573585579144,
|
|
"loss": 5.4974,
|
|
"mean_token_accuracy": 0.17120815068483353,
|
|
"num_tokens": 21264829.0,
|
|
"step": 9530
|
|
},
|
|
{
|
|
"entropy": 5.66899471282959,
|
|
"epoch": 1.070871005784242,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004896453224684695,
|
|
"loss": 5.4994,
|
|
"mean_token_accuracy": 0.179149766266346,
|
|
"num_tokens": 21276240.0,
|
|
"step": 9535
|
|
},
|
|
{
|
|
"entropy": 5.620451879501343,
|
|
"epoch": 1.0714325826921998,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004896332795446345,
|
|
"loss": 5.5129,
|
|
"mean_token_accuracy": 0.17478324174880983,
|
|
"num_tokens": 21288877.0,
|
|
"step": 9540
|
|
},
|
|
{
|
|
"entropy": 5.644775009155273,
|
|
"epoch": 1.0719941596001572,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004896212297867924,
|
|
"loss": 5.5498,
|
|
"mean_token_accuracy": 0.17083704620599746,
|
|
"num_tokens": 21300147.0,
|
|
"step": 9545
|
|
},
|
|
{
|
|
"entropy": 5.564145803451538,
|
|
"epoch": 1.0725557365081149,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004896091731953271,
|
|
"loss": 5.3379,
|
|
"mean_token_accuracy": 0.1834096446633339,
|
|
"num_tokens": 21309731.0,
|
|
"step": 9550
|
|
},
|
|
{
|
|
"entropy": 5.54395546913147,
|
|
"epoch": 1.0731173134160723,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.0004895971097706227,
|
|
"loss": 5.413,
|
|
"mean_token_accuracy": 0.17877567708492278,
|
|
"num_tokens": 21320358.0,
|
|
"step": 9555
|
|
},
|
|
{
|
|
"entropy": 5.487132596969604,
|
|
"epoch": 1.07367889032403,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004895850395130629,
|
|
"loss": 5.3176,
|
|
"mean_token_accuracy": 0.19092220366001128,
|
|
"num_tokens": 21331077.0,
|
|
"step": 9560
|
|
},
|
|
{
|
|
"entropy": 5.564539003372192,
|
|
"epoch": 1.0742404672319874,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004895729624230323,
|
|
"loss": 5.5168,
|
|
"mean_token_accuracy": 0.18183142989873885,
|
|
"num_tokens": 21341304.0,
|
|
"step": 9565
|
|
},
|
|
{
|
|
"entropy": 5.6389447212219235,
|
|
"epoch": 1.074802044139945,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004895608785009153,
|
|
"loss": 5.495,
|
|
"mean_token_accuracy": 0.1784301996231079,
|
|
"num_tokens": 21353663.0,
|
|
"step": 9570
|
|
},
|
|
{
|
|
"entropy": 5.57873568534851,
|
|
"epoch": 1.0753636210479025,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004895487877470969,
|
|
"loss": 5.4624,
|
|
"mean_token_accuracy": 0.17929406017065047,
|
|
"num_tokens": 21364987.0,
|
|
"step": 9575
|
|
},
|
|
{
|
|
"entropy": 5.507581281661987,
|
|
"epoch": 1.07592519795586,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004895366901619617,
|
|
"loss": 5.4332,
|
|
"mean_token_accuracy": 0.17917827069759368,
|
|
"num_tokens": 21376169.0,
|
|
"step": 9580
|
|
},
|
|
{
|
|
"entropy": 5.57572569847107,
|
|
"epoch": 1.0764867748638176,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004895245857458951,
|
|
"loss": 5.409,
|
|
"mean_token_accuracy": 0.17978260666131973,
|
|
"num_tokens": 21387141.0,
|
|
"step": 9585
|
|
},
|
|
{
|
|
"entropy": 5.60054030418396,
|
|
"epoch": 1.077048351771775,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004895124744992825,
|
|
"loss": 5.392,
|
|
"mean_token_accuracy": 0.18548154681921006,
|
|
"num_tokens": 21396804.0,
|
|
"step": 9590
|
|
},
|
|
{
|
|
"entropy": 5.509835720062256,
|
|
"epoch": 1.0776099286797327,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004895003564225095,
|
|
"loss": 5.4276,
|
|
"mean_token_accuracy": 0.18453317284584045,
|
|
"num_tokens": 21406948.0,
|
|
"step": 9595
|
|
},
|
|
{
|
|
"entropy": 5.553013610839844,
|
|
"epoch": 1.0781715055876901,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004894882315159621,
|
|
"loss": 5.4084,
|
|
"mean_token_accuracy": 0.18084955364465713,
|
|
"num_tokens": 21417560.0,
|
|
"step": 9600
|
|
},
|
|
{
|
|
"entropy": 5.538203001022339,
|
|
"epoch": 1.0787330824956478,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.000489476099780026,
|
|
"loss": 5.4176,
|
|
"mean_token_accuracy": 0.18558336198329925,
|
|
"num_tokens": 21428596.0,
|
|
"step": 9605
|
|
},
|
|
{
|
|
"entropy": 5.594052362442016,
|
|
"epoch": 1.0792946594036052,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004894639612150879,
|
|
"loss": 5.5009,
|
|
"mean_token_accuracy": 0.1776292786002159,
|
|
"num_tokens": 21440004.0,
|
|
"step": 9610
|
|
},
|
|
{
|
|
"entropy": 5.603554058074951,
|
|
"epoch": 1.079856236311563,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004894518158215339,
|
|
"loss": 5.437,
|
|
"mean_token_accuracy": 0.18182192593812943,
|
|
"num_tokens": 21451423.0,
|
|
"step": 9615
|
|
},
|
|
{
|
|
"entropy": 5.6315145015716555,
|
|
"epoch": 1.0804178132195204,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.000489439663599751,
|
|
"loss": 5.502,
|
|
"mean_token_accuracy": 0.17420097291469575,
|
|
"num_tokens": 21462065.0,
|
|
"step": 9620
|
|
},
|
|
{
|
|
"entropy": 5.565780210494995,
|
|
"epoch": 1.080979390127478,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.000489427504550126,
|
|
"loss": 5.4329,
|
|
"mean_token_accuracy": 0.17715296298265457,
|
|
"num_tokens": 21473476.0,
|
|
"step": 9625
|
|
},
|
|
{
|
|
"entropy": 5.676029396057129,
|
|
"epoch": 1.0815409670354355,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004894153386730462,
|
|
"loss": 5.5517,
|
|
"mean_token_accuracy": 0.1776492029428482,
|
|
"num_tokens": 21485591.0,
|
|
"step": 9630
|
|
},
|
|
{
|
|
"entropy": 5.641856098175049,
|
|
"epoch": 1.0821025439433931,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004894031659688988,
|
|
"loss": 5.6286,
|
|
"mean_token_accuracy": 0.17196228802204133,
|
|
"num_tokens": 21497016.0,
|
|
"step": 9635
|
|
},
|
|
{
|
|
"entropy": 5.563565683364868,
|
|
"epoch": 1.0826641208513506,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004893909864380714,
|
|
"loss": 5.4241,
|
|
"mean_token_accuracy": 0.18089785128831865,
|
|
"num_tokens": 21508179.0,
|
|
"step": 9640
|
|
},
|
|
{
|
|
"entropy": 5.661916208267212,
|
|
"epoch": 1.0832256977593082,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.000489378800080952,
|
|
"loss": 5.5514,
|
|
"mean_token_accuracy": 0.16957199722528457,
|
|
"num_tokens": 21520053.0,
|
|
"step": 9645
|
|
},
|
|
{
|
|
"entropy": 5.662601566314697,
|
|
"epoch": 1.0837872746672657,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004893666068979283,
|
|
"loss": 5.4513,
|
|
"mean_token_accuracy": 0.18505332469940186,
|
|
"num_tokens": 21530746.0,
|
|
"step": 9650
|
|
},
|
|
{
|
|
"entropy": 5.561122179031372,
|
|
"epoch": 1.0843488515752233,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004893544068893887,
|
|
"loss": 5.4699,
|
|
"mean_token_accuracy": 0.17847533524036407,
|
|
"num_tokens": 21540829.0,
|
|
"step": 9655
|
|
},
|
|
{
|
|
"entropy": 5.55997633934021,
|
|
"epoch": 1.0849104284831808,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004893422000557217,
|
|
"loss": 5.4025,
|
|
"mean_token_accuracy": 0.1824072703719139,
|
|
"num_tokens": 21552337.0,
|
|
"step": 9660
|
|
},
|
|
{
|
|
"entropy": 5.600814437866211,
|
|
"epoch": 1.0854720053911384,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004893299863973159,
|
|
"loss": 5.4138,
|
|
"mean_token_accuracy": 0.18376973569393157,
|
|
"num_tokens": 21563752.0,
|
|
"step": 9665
|
|
},
|
|
{
|
|
"entropy": 5.642785453796387,
|
|
"epoch": 1.0860335822990959,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004893177659145601,
|
|
"loss": 5.5625,
|
|
"mean_token_accuracy": 0.17684261351823807,
|
|
"num_tokens": 21574834.0,
|
|
"step": 9670
|
|
},
|
|
{
|
|
"entropy": 5.6293717384338375,
|
|
"epoch": 1.0865951592070533,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004893055386078438,
|
|
"loss": 5.4672,
|
|
"mean_token_accuracy": 0.17502747774124144,
|
|
"num_tokens": 21586674.0,
|
|
"step": 9675
|
|
},
|
|
{
|
|
"entropy": 5.620609474182129,
|
|
"epoch": 1.087156736115011,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004892933044775558,
|
|
"loss": 5.403,
|
|
"mean_token_accuracy": 0.1848546639084816,
|
|
"num_tokens": 21595998.0,
|
|
"step": 9680
|
|
},
|
|
{
|
|
"entropy": 5.600088262557984,
|
|
"epoch": 1.0877183130229684,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004892810635240859,
|
|
"loss": 5.484,
|
|
"mean_token_accuracy": 0.17975264489650727,
|
|
"num_tokens": 21607122.0,
|
|
"step": 9685
|
|
},
|
|
{
|
|
"entropy": 5.5601122856140135,
|
|
"epoch": 1.088279889930926,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004892688157478238,
|
|
"loss": 5.3974,
|
|
"mean_token_accuracy": 0.18241830170154572,
|
|
"num_tokens": 21618780.0,
|
|
"step": 9690
|
|
},
|
|
{
|
|
"entropy": 5.5932230949401855,
|
|
"epoch": 1.0888414668388835,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004892565611491597,
|
|
"loss": 5.4617,
|
|
"mean_token_accuracy": 0.1802744448184967,
|
|
"num_tokens": 21628868.0,
|
|
"step": 9695
|
|
},
|
|
{
|
|
"entropy": 5.6138755798339846,
|
|
"epoch": 1.0894030437468412,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004892442997284834,
|
|
"loss": 5.3442,
|
|
"mean_token_accuracy": 0.19054587185382843,
|
|
"num_tokens": 21640189.0,
|
|
"step": 9700
|
|
},
|
|
{
|
|
"entropy": 5.5858148574829105,
|
|
"epoch": 1.0899646206547986,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004892320314861855,
|
|
"loss": 5.5968,
|
|
"mean_token_accuracy": 0.17798891812562942,
|
|
"num_tokens": 21651452.0,
|
|
"step": 9705
|
|
},
|
|
{
|
|
"entropy": 5.505543899536133,
|
|
"epoch": 1.0905261975627563,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004892197564226568,
|
|
"loss": 5.3238,
|
|
"mean_token_accuracy": 0.18632598519325255,
|
|
"num_tokens": 21662555.0,
|
|
"step": 9710
|
|
},
|
|
{
|
|
"entropy": 5.577691555023193,
|
|
"epoch": 1.0910877744707137,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004892074745382878,
|
|
"loss": 5.3675,
|
|
"mean_token_accuracy": 0.18600122332572938,
|
|
"num_tokens": 21673087.0,
|
|
"step": 9715
|
|
},
|
|
{
|
|
"entropy": 5.559349918365479,
|
|
"epoch": 1.0916493513786714,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004891951858334698,
|
|
"loss": 5.4592,
|
|
"mean_token_accuracy": 0.17866172939538955,
|
|
"num_tokens": 21684084.0,
|
|
"step": 9720
|
|
},
|
|
{
|
|
"entropy": 5.5244140625,
|
|
"epoch": 1.0922109282866288,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004891828903085939,
|
|
"loss": 5.4018,
|
|
"mean_token_accuracy": 0.1834845647215843,
|
|
"num_tokens": 21695765.0,
|
|
"step": 9725
|
|
},
|
|
{
|
|
"entropy": 5.6586473941802975,
|
|
"epoch": 1.0927725051945865,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004891705879640518,
|
|
"loss": 5.4871,
|
|
"mean_token_accuracy": 0.17867584228515626,
|
|
"num_tokens": 21707396.0,
|
|
"step": 9730
|
|
},
|
|
{
|
|
"entropy": 5.589698791503906,
|
|
"epoch": 1.093334082102544,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004891582788002351,
|
|
"loss": 5.4206,
|
|
"mean_token_accuracy": 0.1840369150042534,
|
|
"num_tokens": 21718330.0,
|
|
"step": 9735
|
|
},
|
|
{
|
|
"entropy": 5.627910423278808,
|
|
"epoch": 1.0938956590105016,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004891459628175358,
|
|
"loss": 5.5333,
|
|
"mean_token_accuracy": 0.17498715370893478,
|
|
"num_tokens": 21729841.0,
|
|
"step": 9740
|
|
},
|
|
{
|
|
"entropy": 5.586634826660156,
|
|
"epoch": 1.094457235918459,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.000489133640016346,
|
|
"loss": 5.4779,
|
|
"mean_token_accuracy": 0.18365336507558822,
|
|
"num_tokens": 21740403.0,
|
|
"step": 9745
|
|
},
|
|
{
|
|
"entropy": 5.6356080055236815,
|
|
"epoch": 1.0950188128264167,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004891213103970579,
|
|
"loss": 5.4621,
|
|
"mean_token_accuracy": 0.18089024871587753,
|
|
"num_tokens": 21750696.0,
|
|
"step": 9750
|
|
},
|
|
{
|
|
"entropy": 5.52034821510315,
|
|
"epoch": 1.095580389734374,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004891089739600643,
|
|
"loss": 5.361,
|
|
"mean_token_accuracy": 0.18476004898548126,
|
|
"num_tokens": 21761324.0,
|
|
"step": 9755
|
|
},
|
|
{
|
|
"entropy": 5.6163732528686525,
|
|
"epoch": 1.0961419666423318,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004890966307057581,
|
|
"loss": 5.4558,
|
|
"mean_token_accuracy": 0.1767112657427788,
|
|
"num_tokens": 21774046.0,
|
|
"step": 9760
|
|
},
|
|
{
|
|
"entropy": 5.5504951000213625,
|
|
"epoch": 1.0967035435502892,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.000489084280634532,
|
|
"loss": 5.4554,
|
|
"mean_token_accuracy": 0.1811685934662819,
|
|
"num_tokens": 21784625.0,
|
|
"step": 9765
|
|
},
|
|
{
|
|
"entropy": 5.644229459762573,
|
|
"epoch": 1.0972651204582466,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004890719237467794,
|
|
"loss": 5.556,
|
|
"mean_token_accuracy": 0.17533084750175476,
|
|
"num_tokens": 21795971.0,
|
|
"step": 9770
|
|
},
|
|
{
|
|
"entropy": 5.702903461456299,
|
|
"epoch": 1.0978266973662043,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004890595600428937,
|
|
"loss": 5.517,
|
|
"mean_token_accuracy": 0.17991171777248383,
|
|
"num_tokens": 21806624.0,
|
|
"step": 9775
|
|
},
|
|
{
|
|
"entropy": 5.603931522369384,
|
|
"epoch": 1.0983882742741617,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004890471895232684,
|
|
"loss": 5.4447,
|
|
"mean_token_accuracy": 0.1773332729935646,
|
|
"num_tokens": 21817830.0,
|
|
"step": 9780
|
|
},
|
|
{
|
|
"entropy": 5.577806615829468,
|
|
"epoch": 1.0989498511821194,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004890348121882978,
|
|
"loss": 5.4297,
|
|
"mean_token_accuracy": 0.18548934012651444,
|
|
"num_tokens": 21829540.0,
|
|
"step": 9785
|
|
},
|
|
{
|
|
"entropy": 5.702232933044433,
|
|
"epoch": 1.0995114280900768,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004890224280383758,
|
|
"loss": 5.6124,
|
|
"mean_token_accuracy": 0.17456040531396866,
|
|
"num_tokens": 21840550.0,
|
|
"step": 9790
|
|
},
|
|
{
|
|
"entropy": 5.6826036930084225,
|
|
"epoch": 1.1000730049980345,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004890100370738966,
|
|
"loss": 5.5526,
|
|
"mean_token_accuracy": 0.17297013401985167,
|
|
"num_tokens": 21853366.0,
|
|
"step": 9795
|
|
},
|
|
{
|
|
"entropy": 5.567359399795532,
|
|
"epoch": 1.100634581905992,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004889976392952548,
|
|
"loss": 5.4677,
|
|
"mean_token_accuracy": 0.1834318980574608,
|
|
"num_tokens": 21863522.0,
|
|
"step": 9800
|
|
},
|
|
{
|
|
"entropy": 5.617341470718384,
|
|
"epoch": 1.1011961588139496,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004889852347028452,
|
|
"loss": 5.427,
|
|
"mean_token_accuracy": 0.18069212436676024,
|
|
"num_tokens": 21873988.0,
|
|
"step": 9805
|
|
},
|
|
{
|
|
"entropy": 5.5770001888275145,
|
|
"epoch": 1.101757735721907,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004889728232970626,
|
|
"loss": 5.3645,
|
|
"mean_token_accuracy": 0.18551873415708542,
|
|
"num_tokens": 21884595.0,
|
|
"step": 9810
|
|
},
|
|
{
|
|
"entropy": 5.559672927856445,
|
|
"epoch": 1.1023193126298647,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004889604050783025,
|
|
"loss": 5.4049,
|
|
"mean_token_accuracy": 0.18870704919099807,
|
|
"num_tokens": 21894643.0,
|
|
"step": 9815
|
|
},
|
|
{
|
|
"entropy": 5.608105182647705,
|
|
"epoch": 1.1028808895378222,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.00048894798004696,
|
|
"loss": 5.4151,
|
|
"mean_token_accuracy": 0.18534329533576965,
|
|
"num_tokens": 21906608.0,
|
|
"step": 9820
|
|
},
|
|
{
|
|
"entropy": 5.72157301902771,
|
|
"epoch": 1.1034424664457798,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004889355482034309,
|
|
"loss": 5.5454,
|
|
"mean_token_accuracy": 0.17869509905576705,
|
|
"num_tokens": 21919386.0,
|
|
"step": 9825
|
|
},
|
|
{
|
|
"entropy": 5.524839878082275,
|
|
"epoch": 1.1040040433537373,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004889231095481111,
|
|
"loss": 5.4214,
|
|
"mean_token_accuracy": 0.18391776829957962,
|
|
"num_tokens": 21930554.0,
|
|
"step": 9830
|
|
},
|
|
{
|
|
"entropy": 5.654389429092407,
|
|
"epoch": 1.104565620261695,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004889106640813964,
|
|
"loss": 5.5247,
|
|
"mean_token_accuracy": 0.17893804013729095,
|
|
"num_tokens": 21941764.0,
|
|
"step": 9835
|
|
},
|
|
{
|
|
"entropy": 5.54154601097107,
|
|
"epoch": 1.1051271971696524,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004888982118036831,
|
|
"loss": 5.351,
|
|
"mean_token_accuracy": 0.18850825279951094,
|
|
"num_tokens": 21951804.0,
|
|
"step": 9840
|
|
},
|
|
{
|
|
"entropy": 5.612653160095215,
|
|
"epoch": 1.10568877407761,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004888857527153679,
|
|
"loss": 5.5164,
|
|
"mean_token_accuracy": 0.1715184286236763,
|
|
"num_tokens": 21963356.0,
|
|
"step": 9845
|
|
},
|
|
{
|
|
"entropy": 5.585508584976196,
|
|
"epoch": 1.1062503509855675,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004888732868168473,
|
|
"loss": 5.4373,
|
|
"mean_token_accuracy": 0.18316725194454192,
|
|
"num_tokens": 21973785.0,
|
|
"step": 9850
|
|
},
|
|
{
|
|
"entropy": 5.632301330566406,
|
|
"epoch": 1.1068119278935251,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004888608141085183,
|
|
"loss": 5.4351,
|
|
"mean_token_accuracy": 0.17661972790956498,
|
|
"num_tokens": 21985057.0,
|
|
"step": 9855
|
|
},
|
|
{
|
|
"entropy": 5.623175954818725,
|
|
"epoch": 1.1073735048014826,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004888483345907781,
|
|
"loss": 5.5038,
|
|
"mean_token_accuracy": 0.18079903870820999,
|
|
"num_tokens": 21996554.0,
|
|
"step": 9860
|
|
},
|
|
{
|
|
"entropy": 5.564160585403442,
|
|
"epoch": 1.10793508170944,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.000488835848264024,
|
|
"loss": 5.4428,
|
|
"mean_token_accuracy": 0.17722105979919434,
|
|
"num_tokens": 22008284.0,
|
|
"step": 9865
|
|
},
|
|
{
|
|
"entropy": 5.536996221542358,
|
|
"epoch": 1.1084966586173977,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004888233551286534,
|
|
"loss": 5.4887,
|
|
"mean_token_accuracy": 0.1781219720840454,
|
|
"num_tokens": 22019322.0,
|
|
"step": 9870
|
|
},
|
|
{
|
|
"entropy": 5.670701122283935,
|
|
"epoch": 1.109058235525355,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004888108551850644,
|
|
"loss": 5.5697,
|
|
"mean_token_accuracy": 0.16928135007619857,
|
|
"num_tokens": 22031444.0,
|
|
"step": 9875
|
|
},
|
|
{
|
|
"entropy": 5.598286533355713,
|
|
"epoch": 1.1096198124333128,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.0004887983484336548,
|
|
"loss": 5.3813,
|
|
"mean_token_accuracy": 0.18684137463569642,
|
|
"num_tokens": 22042704.0,
|
|
"step": 9880
|
|
},
|
|
{
|
|
"entropy": 5.579814386367798,
|
|
"epoch": 1.1101813893412702,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004887858348748229,
|
|
"loss": 5.4732,
|
|
"mean_token_accuracy": 0.18037536442279817,
|
|
"num_tokens": 22052721.0,
|
|
"step": 9885
|
|
},
|
|
{
|
|
"entropy": 5.651267671585083,
|
|
"epoch": 1.1107429662492279,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.000488773314508967,
|
|
"loss": 5.4894,
|
|
"mean_token_accuracy": 0.17873190343379974,
|
|
"num_tokens": 22063857.0,
|
|
"step": 9890
|
|
},
|
|
{
|
|
"entropy": 5.5537378787994385,
|
|
"epoch": 1.1113045431571853,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004887607873364859,
|
|
"loss": 5.423,
|
|
"mean_token_accuracy": 0.183661812543869,
|
|
"num_tokens": 22074777.0,
|
|
"step": 9895
|
|
},
|
|
{
|
|
"entropy": 5.627150440216065,
|
|
"epoch": 1.111866120065143,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.0004887482533577786,
|
|
"loss": 5.5092,
|
|
"mean_token_accuracy": 0.17283634841442108,
|
|
"num_tokens": 22085301.0,
|
|
"step": 9900
|
|
},
|
|
{
|
|
"entropy": 5.6233783721923825,
|
|
"epoch": 1.1124276969731004,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.0004887357125732438,
|
|
"loss": 5.4252,
|
|
"mean_token_accuracy": 0.1815194621682167,
|
|
"num_tokens": 22095635.0,
|
|
"step": 9905
|
|
},
|
|
{
|
|
"entropy": 5.591199684143066,
|
|
"epoch": 1.112989273881058,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 0.000488723164983281,
|
|
"loss": 5.4432,
|
|
"mean_token_accuracy": 0.17690271586179734,
|
|
"num_tokens": 22105965.0,
|
|
"step": 9910
|
|
},
|
|
{
|
|
"entropy": 5.499814510345459,
|
|
"epoch": 1.1135508507890155,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004887106105882898,
|
|
"loss": 5.3705,
|
|
"mean_token_accuracy": 0.1817806765437126,
|
|
"num_tokens": 22117122.0,
|
|
"step": 9915
|
|
},
|
|
{
|
|
"entropy": 5.653459739685059,
|
|
"epoch": 1.1141124276969732,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004886980493886699,
|
|
"loss": 5.4242,
|
|
"mean_token_accuracy": 0.18367586880922318,
|
|
"num_tokens": 22128642.0,
|
|
"step": 9920
|
|
},
|
|
{
|
|
"entropy": 5.592040252685547,
|
|
"epoch": 1.1146740046049306,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004886854813848212,
|
|
"loss": 5.4187,
|
|
"mean_token_accuracy": 0.1819361686706543,
|
|
"num_tokens": 22140260.0,
|
|
"step": 9925
|
|
},
|
|
{
|
|
"entropy": 5.504345655441284,
|
|
"epoch": 1.1152355815128883,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004886729065771439,
|
|
"loss": 5.5463,
|
|
"mean_token_accuracy": 0.17537332624197005,
|
|
"num_tokens": 22152460.0,
|
|
"step": 9930
|
|
},
|
|
{
|
|
"entropy": 5.600211524963379,
|
|
"epoch": 1.1157971584208457,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004886603249660384,
|
|
"loss": 5.3025,
|
|
"mean_token_accuracy": 0.18542418330907823,
|
|
"num_tokens": 22163134.0,
|
|
"step": 9935
|
|
},
|
|
{
|
|
"entropy": 5.666353702545166,
|
|
"epoch": 1.1163587353288034,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004886477365519052,
|
|
"loss": 5.4622,
|
|
"mean_token_accuracy": 0.17874416559934617,
|
|
"num_tokens": 22173956.0,
|
|
"step": 9940
|
|
},
|
|
{
|
|
"entropy": 5.529520034790039,
|
|
"epoch": 1.1169203122367608,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004886351413351453,
|
|
"loss": 5.4463,
|
|
"mean_token_accuracy": 0.17844821363687516,
|
|
"num_tokens": 22185506.0,
|
|
"step": 9945
|
|
},
|
|
{
|
|
"entropy": 5.517136430740356,
|
|
"epoch": 1.1174818891447185,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004886225393161596,
|
|
"loss": 5.4379,
|
|
"mean_token_accuracy": 0.1817207857966423,
|
|
"num_tokens": 22196934.0,
|
|
"step": 9950
|
|
},
|
|
{
|
|
"entropy": 5.585705089569092,
|
|
"epoch": 1.118043466052676,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004886099304953495,
|
|
"loss": 5.4573,
|
|
"mean_token_accuracy": 0.17639363408088685,
|
|
"num_tokens": 22209013.0,
|
|
"step": 9955
|
|
},
|
|
{
|
|
"entropy": 5.688259077072144,
|
|
"epoch": 1.1186050429606333,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004885973148731162,
|
|
"loss": 5.5883,
|
|
"mean_token_accuracy": 0.1751970171928406,
|
|
"num_tokens": 22220890.0,
|
|
"step": 9960
|
|
},
|
|
{
|
|
"entropy": 5.6196691513061525,
|
|
"epoch": 1.119166619868591,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004885846924498617,
|
|
"loss": 5.4045,
|
|
"mean_token_accuracy": 0.18046572655439377,
|
|
"num_tokens": 22232899.0,
|
|
"step": 9965
|
|
},
|
|
{
|
|
"entropy": 5.553362655639648,
|
|
"epoch": 1.1197281967765484,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004885720632259876,
|
|
"loss": 5.4285,
|
|
"mean_token_accuracy": 0.17943229377269745,
|
|
"num_tokens": 22243839.0,
|
|
"step": 9970
|
|
},
|
|
{
|
|
"entropy": 5.6693480014801025,
|
|
"epoch": 1.120289773684506,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004885594272018963,
|
|
"loss": 5.4645,
|
|
"mean_token_accuracy": 0.17993124127388,
|
|
"num_tokens": 22253970.0,
|
|
"step": 9975
|
|
},
|
|
{
|
|
"entropy": 5.530833959579468,
|
|
"epoch": 1.1208513505924635,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00048854678437799,
|
|
"loss": 5.3467,
|
|
"mean_token_accuracy": 0.18927840441465377,
|
|
"num_tokens": 22263598.0,
|
|
"step": 9980
|
|
},
|
|
{
|
|
"entropy": 5.483437776565552,
|
|
"epoch": 1.1214129275004212,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004885341347546713,
|
|
"loss": 5.5413,
|
|
"mean_token_accuracy": 0.17272351831197738,
|
|
"num_tokens": 22274385.0,
|
|
"step": 9985
|
|
},
|
|
{
|
|
"entropy": 5.579334831237793,
|
|
"epoch": 1.1219745044083786,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004885214783323428,
|
|
"loss": 5.4064,
|
|
"mean_token_accuracy": 0.1820865660905838,
|
|
"num_tokens": 22285837.0,
|
|
"step": 9990
|
|
},
|
|
{
|
|
"entropy": 5.6654328346252445,
|
|
"epoch": 1.1225360813163363,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004885088151114076,
|
|
"loss": 5.5008,
|
|
"mean_token_accuracy": 0.17633887529373168,
|
|
"num_tokens": 22296882.0,
|
|
"step": 9995
|
|
},
|
|
{
|
|
"entropy": 5.509787464141846,
|
|
"epoch": 1.1230976582242937,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004884961450922691,
|
|
"loss": 5.3913,
|
|
"mean_token_accuracy": 0.18201883286237716,
|
|
"num_tokens": 22308110.0,
|
|
"step": 10000
|
|
},
|
|
{
|
|
"entropy": 5.510275602340698,
|
|
"epoch": 1.1236592351322514,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004884834682753305,
|
|
"loss": 5.4198,
|
|
"mean_token_accuracy": 0.18542241752147676,
|
|
"num_tokens": 22318541.0,
|
|
"step": 10005
|
|
},
|
|
{
|
|
"entropy": 5.536625671386719,
|
|
"epoch": 1.1242208120402089,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004884707846609953,
|
|
"loss": 5.4128,
|
|
"mean_token_accuracy": 0.18137142658233643,
|
|
"num_tokens": 22328713.0,
|
|
"step": 10010
|
|
},
|
|
{
|
|
"entropy": 5.661680412292481,
|
|
"epoch": 1.1247823889481665,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004884580942496677,
|
|
"loss": 5.4751,
|
|
"mean_token_accuracy": 0.17806675732135774,
|
|
"num_tokens": 22341050.0,
|
|
"step": 10015
|
|
},
|
|
{
|
|
"entropy": 5.58024754524231,
|
|
"epoch": 1.125343965856124,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004884453970417515,
|
|
"loss": 5.3569,
|
|
"mean_token_accuracy": 0.18561971783638,
|
|
"num_tokens": 22351184.0,
|
|
"step": 10020
|
|
},
|
|
{
|
|
"entropy": 5.555691528320312,
|
|
"epoch": 1.1259055427640816,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.000488432693037651,
|
|
"loss": 5.4249,
|
|
"mean_token_accuracy": 0.18320182114839553,
|
|
"num_tokens": 22361651.0,
|
|
"step": 10025
|
|
},
|
|
{
|
|
"entropy": 5.648286199569702,
|
|
"epoch": 1.126467119672039,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.000488419982237771,
|
|
"loss": 5.532,
|
|
"mean_token_accuracy": 0.17271254062652588,
|
|
"num_tokens": 22373672.0,
|
|
"step": 10030
|
|
},
|
|
{
|
|
"entropy": 5.636139965057373,
|
|
"epoch": 1.1270286965799967,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004884072646425157,
|
|
"loss": 5.5091,
|
|
"mean_token_accuracy": 0.1779921069741249,
|
|
"num_tokens": 22384924.0,
|
|
"step": 10035
|
|
},
|
|
{
|
|
"entropy": 5.6113080978393555,
|
|
"epoch": 1.1275902734879542,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004883945402522907,
|
|
"loss": 5.4102,
|
|
"mean_token_accuracy": 0.18566200882196426,
|
|
"num_tokens": 22396091.0,
|
|
"step": 10040
|
|
},
|
|
{
|
|
"entropy": 5.697112512588501,
|
|
"epoch": 1.1281518503959118,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004883818090675005,
|
|
"loss": 5.5023,
|
|
"mean_token_accuracy": 0.17411854714155198,
|
|
"num_tokens": 22407925.0,
|
|
"step": 10045
|
|
},
|
|
{
|
|
"entropy": 5.580139541625977,
|
|
"epoch": 1.1287134273038693,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004883690710885507,
|
|
"loss": 5.4206,
|
|
"mean_token_accuracy": 0.18167119473218918,
|
|
"num_tokens": 22417917.0,
|
|
"step": 10050
|
|
},
|
|
{
|
|
"entropy": 5.612313365936279,
|
|
"epoch": 1.1292750042118267,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004883563263158471,
|
|
"loss": 5.5153,
|
|
"mean_token_accuracy": 0.17684295028448105,
|
|
"num_tokens": 22429836.0,
|
|
"step": 10055
|
|
},
|
|
{
|
|
"entropy": 5.661643743515015,
|
|
"epoch": 1.1298365811197844,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.0004883435747497952,
|
|
"loss": 5.585,
|
|
"mean_token_accuracy": 0.17540506571531295,
|
|
"num_tokens": 22440720.0,
|
|
"step": 10060
|
|
},
|
|
{
|
|
"entropy": 5.5146032810211185,
|
|
"epoch": 1.130398158027742,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004883308163908012,
|
|
"loss": 5.3064,
|
|
"mean_token_accuracy": 0.18266170024871825,
|
|
"num_tokens": 22452587.0,
|
|
"step": 10065
|
|
},
|
|
{
|
|
"entropy": 5.582793140411377,
|
|
"epoch": 1.1309597349356995,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004883180512392714,
|
|
"loss": 5.4896,
|
|
"mean_token_accuracy": 0.18124875873327256,
|
|
"num_tokens": 22464063.0,
|
|
"step": 10070
|
|
},
|
|
{
|
|
"entropy": 5.57654972076416,
|
|
"epoch": 1.131521311843657,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004883052792956119,
|
|
"loss": 5.4545,
|
|
"mean_token_accuracy": 0.1777760937809944,
|
|
"num_tokens": 22474956.0,
|
|
"step": 10075
|
|
},
|
|
{
|
|
"entropy": 5.572151613235474,
|
|
"epoch": 1.1320828887516146,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004882925005602296,
|
|
"loss": 5.4247,
|
|
"mean_token_accuracy": 0.17617421299219133,
|
|
"num_tokens": 22486499.0,
|
|
"step": 10080
|
|
},
|
|
{
|
|
"entropy": 5.5781739234924315,
|
|
"epoch": 1.132644465659572,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004882797150335314,
|
|
"loss": 5.3386,
|
|
"mean_token_accuracy": 0.18663488775491716,
|
|
"num_tokens": 22497736.0,
|
|
"step": 10085
|
|
},
|
|
{
|
|
"entropy": 5.540691328048706,
|
|
"epoch": 1.1332060425675297,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00048826692271592434,
|
|
"loss": 5.4169,
|
|
"mean_token_accuracy": 0.17964298129081727,
|
|
"num_tokens": 22509997.0,
|
|
"step": 10090
|
|
},
|
|
{
|
|
"entropy": 5.574131822586059,
|
|
"epoch": 1.133767619475487,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004882541236078158,
|
|
"loss": 5.4949,
|
|
"mean_token_accuracy": 0.18007486909627915,
|
|
"num_tokens": 22519721.0,
|
|
"step": 10095
|
|
},
|
|
{
|
|
"entropy": 5.661850929260254,
|
|
"epoch": 1.1343291963834448,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00048824131770961316,
|
|
"loss": 5.3899,
|
|
"mean_token_accuracy": 0.1807657703757286,
|
|
"num_tokens": 22530219.0,
|
|
"step": 10100
|
|
},
|
|
{
|
|
"entropy": 5.590708684921265,
|
|
"epoch": 1.1348907732914022,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.00048822850502172437,
|
|
"loss": 5.4249,
|
|
"mean_token_accuracy": 0.17643967866897584,
|
|
"num_tokens": 22541373.0,
|
|
"step": 10105
|
|
},
|
|
{
|
|
"entropy": 5.462498426437378,
|
|
"epoch": 1.1354523501993599,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004882156855445571,
|
|
"loss": 5.3623,
|
|
"mean_token_accuracy": 0.17757754027843475,
|
|
"num_tokens": 22552974.0,
|
|
"step": 10110
|
|
},
|
|
{
|
|
"entropy": 5.580391216278076,
|
|
"epoch": 1.1360139271073173,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004882028592785199,
|
|
"loss": 5.3721,
|
|
"mean_token_accuracy": 0.18000393509864807,
|
|
"num_tokens": 22563468.0,
|
|
"step": 10115
|
|
},
|
|
{
|
|
"entropy": 5.569001054763794,
|
|
"epoch": 1.136575504015275,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.00048819002622402095,
|
|
"loss": 5.5069,
|
|
"mean_token_accuracy": 0.17577992826700212,
|
|
"num_tokens": 22574386.0,
|
|
"step": 10120
|
|
},
|
|
{
|
|
"entropy": 5.556534337997436,
|
|
"epoch": 1.1371370809232324,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004881771863814688,
|
|
"loss": 5.4123,
|
|
"mean_token_accuracy": 0.18740794956684112,
|
|
"num_tokens": 22585369.0,
|
|
"step": 10125
|
|
},
|
|
{
|
|
"entropy": 5.537963247299194,
|
|
"epoch": 1.13769865783119,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.00048816433975127244,
|
|
"loss": 5.4334,
|
|
"mean_token_accuracy": 0.18183194398880004,
|
|
"num_tokens": 22595853.0,
|
|
"step": 10130
|
|
},
|
|
{
|
|
"entropy": 5.610812759399414,
|
|
"epoch": 1.1382602347391475,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004881514863338407,
|
|
"loss": 5.5028,
|
|
"mean_token_accuracy": 0.18175214976072313,
|
|
"num_tokens": 22606596.0,
|
|
"step": 10135
|
|
},
|
|
{
|
|
"entropy": 5.613374710083008,
|
|
"epoch": 1.1388218116471052,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.00048813862612958307,
|
|
"loss": 5.3744,
|
|
"mean_token_accuracy": 0.17816888988018037,
|
|
"num_tokens": 22617196.0,
|
|
"step": 10140
|
|
},
|
|
{
|
|
"entropy": 5.451364135742187,
|
|
"epoch": 1.1393833885550626,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004881257591389089,
|
|
"loss": 5.3344,
|
|
"mean_token_accuracy": 0.18494184762239457,
|
|
"num_tokens": 22627817.0,
|
|
"step": 10145
|
|
},
|
|
{
|
|
"entropy": 5.496274614334107,
|
|
"epoch": 1.13994496546302,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00048811288536222794,
|
|
"loss": 5.4362,
|
|
"mean_token_accuracy": 0.1737013503909111,
|
|
"num_tokens": 22637877.0,
|
|
"step": 10150
|
|
},
|
|
{
|
|
"entropy": 5.640788221359253,
|
|
"epoch": 1.1405065423709777,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.00048810000479995,
|
|
"loss": 5.4677,
|
|
"mean_token_accuracy": 0.17672027200460433,
|
|
"num_tokens": 22648770.0,
|
|
"step": 10155
|
|
},
|
|
{
|
|
"entropy": 5.753425788879395,
|
|
"epoch": 1.1410681192789354,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.00048808711745248524,
|
|
"loss": 5.5346,
|
|
"mean_token_accuracy": 0.17500863820314408,
|
|
"num_tokens": 22659626.0,
|
|
"step": 10160
|
|
},
|
|
{
|
|
"entropy": 5.588730239868164,
|
|
"epoch": 1.1416296961868928,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00048807422332024404,
|
|
"loss": 5.5057,
|
|
"mean_token_accuracy": 0.17713336348533631,
|
|
"num_tokens": 22669035.0,
|
|
"step": 10165
|
|
},
|
|
{
|
|
"entropy": 5.668708276748657,
|
|
"epoch": 1.1421912730948502,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004880613224036369,
|
|
"loss": 5.4893,
|
|
"mean_token_accuracy": 0.18129380345344542,
|
|
"num_tokens": 22680536.0,
|
|
"step": 10170
|
|
},
|
|
{
|
|
"entropy": 5.655089092254639,
|
|
"epoch": 1.142752850002808,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00048804841470307466,
|
|
"loss": 5.4386,
|
|
"mean_token_accuracy": 0.1854078873991966,
|
|
"num_tokens": 22692732.0,
|
|
"step": 10175
|
|
},
|
|
{
|
|
"entropy": 5.620869159698486,
|
|
"epoch": 1.1433144269107653,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00048803550021896824,
|
|
"loss": 5.563,
|
|
"mean_token_accuracy": 0.17335400730371475,
|
|
"num_tokens": 22703677.0,
|
|
"step": 10180
|
|
},
|
|
{
|
|
"entropy": 5.660672235488891,
|
|
"epoch": 1.143876003818723,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004880225789517289,
|
|
"loss": 5.4861,
|
|
"mean_token_accuracy": 0.17455905973911284,
|
|
"num_tokens": 22714826.0,
|
|
"step": 10185
|
|
},
|
|
{
|
|
"entropy": 5.6227153778076175,
|
|
"epoch": 1.1444375807266804,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.000488009650901768,
|
|
"loss": 5.5619,
|
|
"mean_token_accuracy": 0.17745715528726577,
|
|
"num_tokens": 22726013.0,
|
|
"step": 10190
|
|
},
|
|
{
|
|
"entropy": 5.58302526473999,
|
|
"epoch": 1.144999157634638,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.00048799671606949724,
|
|
"loss": 5.3963,
|
|
"mean_token_accuracy": 0.17846509218215942,
|
|
"num_tokens": 22737494.0,
|
|
"step": 10195
|
|
},
|
|
{
|
|
"entropy": 5.5372984409332275,
|
|
"epoch": 1.1455607345425955,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00048798377445532837,
|
|
"loss": 5.3188,
|
|
"mean_token_accuracy": 0.18994600474834442,
|
|
"num_tokens": 22746916.0,
|
|
"step": 10200
|
|
},
|
|
{
|
|
"entropy": 5.630187463760376,
|
|
"epoch": 1.1461223114505532,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.0004879708260596736,
|
|
"loss": 5.5628,
|
|
"mean_token_accuracy": 0.16555242538452147,
|
|
"num_tokens": 22759197.0,
|
|
"step": 10205
|
|
},
|
|
{
|
|
"entropy": 5.631412601470947,
|
|
"epoch": 1.1466838883585107,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004879578708829451,
|
|
"loss": 5.5195,
|
|
"mean_token_accuracy": 0.17430828064680098,
|
|
"num_tokens": 22770744.0,
|
|
"step": 10210
|
|
},
|
|
{
|
|
"entropy": 5.604301023483276,
|
|
"epoch": 1.1472454652664683,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004879449089255553,
|
|
"loss": 5.446,
|
|
"mean_token_accuracy": 0.17849487960338592,
|
|
"num_tokens": 22781989.0,
|
|
"step": 10215
|
|
},
|
|
{
|
|
"entropy": 5.541107559204102,
|
|
"epoch": 1.1478070421744258,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004879319401879171,
|
|
"loss": 5.3642,
|
|
"mean_token_accuracy": 0.18781604170799254,
|
|
"num_tokens": 22792972.0,
|
|
"step": 10220
|
|
},
|
|
{
|
|
"entropy": 5.562822389602661,
|
|
"epoch": 1.1483686190823834,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.00048791896467044335,
|
|
"loss": 5.436,
|
|
"mean_token_accuracy": 0.18912334442138673,
|
|
"num_tokens": 22802623.0,
|
|
"step": 10225
|
|
},
|
|
{
|
|
"entropy": 5.459062576293945,
|
|
"epoch": 1.1489301959903409,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00048790598237354716,
|
|
"loss": 5.382,
|
|
"mean_token_accuracy": 0.18711169362068175,
|
|
"num_tokens": 22813564.0,
|
|
"step": 10230
|
|
},
|
|
{
|
|
"entropy": 5.596525096893311,
|
|
"epoch": 1.1494917728982985,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004878929932976419,
|
|
"loss": 5.5297,
|
|
"mean_token_accuracy": 0.17973680347204207,
|
|
"num_tokens": 22824681.0,
|
|
"step": 10235
|
|
},
|
|
{
|
|
"entropy": 5.55367226600647,
|
|
"epoch": 1.150053349806256,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004878799974431412,
|
|
"loss": 5.3573,
|
|
"mean_token_accuracy": 0.19110948592424393,
|
|
"num_tokens": 22836030.0,
|
|
"step": 10240
|
|
},
|
|
{
|
|
"entropy": 5.58520393371582,
|
|
"epoch": 1.1506149267142134,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004878669948104588,
|
|
"loss": 5.3781,
|
|
"mean_token_accuracy": 0.1786734029650688,
|
|
"num_tokens": 22847213.0,
|
|
"step": 10245
|
|
},
|
|
{
|
|
"entropy": 5.638460493087768,
|
|
"epoch": 1.151176503622171,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00048785398540000867,
|
|
"loss": 5.3846,
|
|
"mean_token_accuracy": 0.18784808963537217,
|
|
"num_tokens": 22857904.0,
|
|
"step": 10250
|
|
},
|
|
{
|
|
"entropy": 5.559061765670776,
|
|
"epoch": 1.1517380805301287,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00048784096921220514,
|
|
"loss": 5.526,
|
|
"mean_token_accuracy": 0.17414491176605223,
|
|
"num_tokens": 22868975.0,
|
|
"step": 10255
|
|
},
|
|
{
|
|
"entropy": 5.657341861724854,
|
|
"epoch": 1.1522996574380862,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004878279462474627,
|
|
"loss": 5.4727,
|
|
"mean_token_accuracy": 0.1808004006743431,
|
|
"num_tokens": 22879463.0,
|
|
"step": 10260
|
|
},
|
|
{
|
|
"entropy": 5.637919902801514,
|
|
"epoch": 1.1528612343460436,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00048781491650619574,
|
|
"loss": 5.4019,
|
|
"mean_token_accuracy": 0.18174820393323898,
|
|
"num_tokens": 22890382.0,
|
|
"step": 10265
|
|
},
|
|
{
|
|
"entropy": 5.621941804885864,
|
|
"epoch": 1.1534228112540013,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.00048780187998881944,
|
|
"loss": 5.4951,
|
|
"mean_token_accuracy": 0.1807561531662941,
|
|
"num_tokens": 22901968.0,
|
|
"step": 10270
|
|
},
|
|
{
|
|
"entropy": 5.671910381317138,
|
|
"epoch": 1.1539843881619587,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004877888366957486,
|
|
"loss": 5.5287,
|
|
"mean_token_accuracy": 0.17953866124153137,
|
|
"num_tokens": 22912147.0,
|
|
"step": 10275
|
|
},
|
|
{
|
|
"entropy": 5.588748836517334,
|
|
"epoch": 1.1545459650699164,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004877757866273988,
|
|
"loss": 5.4154,
|
|
"mean_token_accuracy": 0.1782118409872055,
|
|
"num_tokens": 22923744.0,
|
|
"step": 10280
|
|
},
|
|
{
|
|
"entropy": 5.587154865264893,
|
|
"epoch": 1.1551075419778738,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004877627297841853,
|
|
"loss": 5.385,
|
|
"mean_token_accuracy": 0.1853589504957199,
|
|
"num_tokens": 22935487.0,
|
|
"step": 10285
|
|
},
|
|
{
|
|
"entropy": 5.589299440383911,
|
|
"epoch": 1.1556691188858315,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004877496661665241,
|
|
"loss": 5.4237,
|
|
"mean_token_accuracy": 0.18607935905456544,
|
|
"num_tokens": 22946379.0,
|
|
"step": 10290
|
|
},
|
|
{
|
|
"entropy": 5.605984210968018,
|
|
"epoch": 1.156230695793789,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.000487736595774831,
|
|
"loss": 5.4308,
|
|
"mean_token_accuracy": 0.17865341305732726,
|
|
"num_tokens": 22957219.0,
|
|
"step": 10295
|
|
},
|
|
{
|
|
"entropy": 5.564409446716309,
|
|
"epoch": 1.1567922727017466,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.00048772351860952215,
|
|
"loss": 5.3854,
|
|
"mean_token_accuracy": 0.18352195173501967,
|
|
"num_tokens": 22967749.0,
|
|
"step": 10300
|
|
},
|
|
{
|
|
"entropy": 5.553499841690064,
|
|
"epoch": 1.157353849609704,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004877104346710139,
|
|
"loss": 5.4037,
|
|
"mean_token_accuracy": 0.18055881708860397,
|
|
"num_tokens": 22978317.0,
|
|
"step": 10305
|
|
},
|
|
{
|
|
"entropy": 5.5471031665802,
|
|
"epoch": 1.1579154265176617,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.000487697343959723,
|
|
"loss": 5.4296,
|
|
"mean_token_accuracy": 0.17836801707744598,
|
|
"num_tokens": 22988793.0,
|
|
"step": 10310
|
|
},
|
|
{
|
|
"entropy": 5.6121556758880615,
|
|
"epoch": 1.158477003425619,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004876842464760661,
|
|
"loss": 5.4918,
|
|
"mean_token_accuracy": 0.17678036242723466,
|
|
"num_tokens": 23000073.0,
|
|
"step": 10315
|
|
},
|
|
{
|
|
"entropy": 5.615738248825073,
|
|
"epoch": 1.1590385803335768,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.00048767114222046036,
|
|
"loss": 5.4653,
|
|
"mean_token_accuracy": 0.17593652456998826,
|
|
"num_tokens": 23011260.0,
|
|
"step": 10320
|
|
},
|
|
{
|
|
"entropy": 5.559394311904907,
|
|
"epoch": 1.1596001572415342,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.000487658031193323,
|
|
"loss": 5.4388,
|
|
"mean_token_accuracy": 0.1824623391032219,
|
|
"num_tokens": 23022129.0,
|
|
"step": 10325
|
|
},
|
|
{
|
|
"entropy": 5.504612159729004,
|
|
"epoch": 1.1601617341494919,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004876449133950714,
|
|
"loss": 5.3838,
|
|
"mean_token_accuracy": 0.17638918459415437,
|
|
"num_tokens": 23033666.0,
|
|
"step": 10330
|
|
},
|
|
{
|
|
"entropy": 5.549623918533325,
|
|
"epoch": 1.1607233110574493,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.0004876317888261233,
|
|
"loss": 5.4085,
|
|
"mean_token_accuracy": 0.18171306997537612,
|
|
"num_tokens": 23044133.0,
|
|
"step": 10335
|
|
},
|
|
{
|
|
"entropy": 5.570271778106689,
|
|
"epoch": 1.1612848879654067,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.00048761865748689657,
|
|
"loss": 5.4217,
|
|
"mean_token_accuracy": 0.17687359154224397,
|
|
"num_tokens": 23055877.0,
|
|
"step": 10340
|
|
},
|
|
{
|
|
"entropy": 5.649858665466309,
|
|
"epoch": 1.1618464648733644,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.00048760551937780927,
|
|
"loss": 5.5343,
|
|
"mean_token_accuracy": 0.1781652018427849,
|
|
"num_tokens": 23066811.0,
|
|
"step": 10345
|
|
},
|
|
{
|
|
"entropy": 5.694931364059448,
|
|
"epoch": 1.162408041781322,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.00048759237449927986,
|
|
"loss": 5.4794,
|
|
"mean_token_accuracy": 0.17494654953479766,
|
|
"num_tokens": 23078928.0,
|
|
"step": 10350
|
|
},
|
|
{
|
|
"entropy": 5.621661186218262,
|
|
"epoch": 1.1629696186892795,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.00048757922285172674,
|
|
"loss": 5.4635,
|
|
"mean_token_accuracy": 0.1786074697971344,
|
|
"num_tokens": 23090685.0,
|
|
"step": 10355
|
|
},
|
|
{
|
|
"entropy": 5.539975881576538,
|
|
"epoch": 1.163531195597237,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00048756606443556874,
|
|
"loss": 5.3683,
|
|
"mean_token_accuracy": 0.1829329326748848,
|
|
"num_tokens": 23101659.0,
|
|
"step": 10360
|
|
},
|
|
{
|
|
"entropy": 5.580107975006103,
|
|
"epoch": 1.1640927725051946,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00048755289925122474,
|
|
"loss": 5.4497,
|
|
"mean_token_accuracy": 0.18081278949975968,
|
|
"num_tokens": 23112970.0,
|
|
"step": 10365
|
|
},
|
|
{
|
|
"entropy": 5.639863586425781,
|
|
"epoch": 1.164654349413152,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.0004875397272991141,
|
|
"loss": 5.4728,
|
|
"mean_token_accuracy": 0.1762469530105591,
|
|
"num_tokens": 23125391.0,
|
|
"step": 10370
|
|
},
|
|
{
|
|
"entropy": 5.6568304061889645,
|
|
"epoch": 1.1652159263211097,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.000487526548579656,
|
|
"loss": 5.5143,
|
|
"mean_token_accuracy": 0.17894838154315948,
|
|
"num_tokens": 23138195.0,
|
|
"step": 10375
|
|
},
|
|
{
|
|
"entropy": 5.670497846603394,
|
|
"epoch": 1.1657775032290671,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.00048751336309327026,
|
|
"loss": 5.5022,
|
|
"mean_token_accuracy": 0.17685108482837678,
|
|
"num_tokens": 23149378.0,
|
|
"step": 10380
|
|
},
|
|
{
|
|
"entropy": 5.484286737442017,
|
|
"epoch": 1.1663390801370248,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004875001708403766,
|
|
"loss": 5.3319,
|
|
"mean_token_accuracy": 0.18941258490085602,
|
|
"num_tokens": 23159394.0,
|
|
"step": 10385
|
|
},
|
|
{
|
|
"entropy": 5.664628553390503,
|
|
"epoch": 1.1669006570449822,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00048748697182139503,
|
|
"loss": 5.5844,
|
|
"mean_token_accuracy": 0.17606203109025956,
|
|
"num_tokens": 23171512.0,
|
|
"step": 10390
|
|
},
|
|
{
|
|
"entropy": 5.568928146362305,
|
|
"epoch": 1.16746223395294,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.0004874737660367459,
|
|
"loss": 5.4147,
|
|
"mean_token_accuracy": 0.18418188095092775,
|
|
"num_tokens": 23181635.0,
|
|
"step": 10395
|
|
},
|
|
{
|
|
"entropy": 5.715925979614258,
|
|
"epoch": 1.1680238108608973,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.00048746055348684967,
|
|
"loss": 5.6897,
|
|
"mean_token_accuracy": 0.16924521178007126,
|
|
"num_tokens": 23194510.0,
|
|
"step": 10400
|
|
},
|
|
{
|
|
"entropy": 5.7471662044525145,
|
|
"epoch": 1.168585387768855,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.000487447334172127,
|
|
"loss": 5.5551,
|
|
"mean_token_accuracy": 0.18067686855793,
|
|
"num_tokens": 23205146.0,
|
|
"step": 10405
|
|
},
|
|
{
|
|
"entropy": 5.60310001373291,
|
|
"epoch": 1.1691469646768125,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.00048743410809299877,
|
|
"loss": 5.463,
|
|
"mean_token_accuracy": 0.17559536695480346,
|
|
"num_tokens": 23216621.0,
|
|
"step": 10410
|
|
},
|
|
{
|
|
"entropy": 5.574869012832641,
|
|
"epoch": 1.1697085415847701,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004874208752498862,
|
|
"loss": 5.4021,
|
|
"mean_token_accuracy": 0.1809071496129036,
|
|
"num_tokens": 23226401.0,
|
|
"step": 10415
|
|
},
|
|
{
|
|
"entropy": 5.549800872802734,
|
|
"epoch": 1.1702701184927276,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004874076356432106,
|
|
"loss": 5.4653,
|
|
"mean_token_accuracy": 0.17664449661970139,
|
|
"num_tokens": 23237921.0,
|
|
"step": 10420
|
|
},
|
|
{
|
|
"entropy": 5.608479022979736,
|
|
"epoch": 1.1708316954006852,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.00048739438927339346,
|
|
"loss": 5.4292,
|
|
"mean_token_accuracy": 0.18261185586452483,
|
|
"num_tokens": 23250015.0,
|
|
"step": 10425
|
|
},
|
|
{
|
|
"entropy": 5.578491735458374,
|
|
"epoch": 1.1713932723086427,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.00048738113614085656,
|
|
"loss": 5.4575,
|
|
"mean_token_accuracy": 0.17823632657527924,
|
|
"num_tokens": 23261243.0,
|
|
"step": 10430
|
|
},
|
|
{
|
|
"entropy": 5.68017430305481,
|
|
"epoch": 1.1719548492166,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.000487367876246022,
|
|
"loss": 5.6097,
|
|
"mean_token_accuracy": 0.17084814310073854,
|
|
"num_tokens": 23273264.0,
|
|
"step": 10435
|
|
},
|
|
{
|
|
"entropy": 5.8019805431365965,
|
|
"epoch": 1.1725164261245578,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004873546095893118,
|
|
"loss": 5.6237,
|
|
"mean_token_accuracy": 0.17058354765176773,
|
|
"num_tokens": 23285031.0,
|
|
"step": 10440
|
|
},
|
|
{
|
|
"entropy": 5.589553451538086,
|
|
"epoch": 1.1730780030325154,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004873413361711485,
|
|
"loss": 5.3735,
|
|
"mean_token_accuracy": 0.18483428210020064,
|
|
"num_tokens": 23296387.0,
|
|
"step": 10445
|
|
},
|
|
{
|
|
"entropy": 5.635595417022705,
|
|
"epoch": 1.1736395799404729,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.00048732805599195465,
|
|
"loss": 5.493,
|
|
"mean_token_accuracy": 0.18177550584077834,
|
|
"num_tokens": 23307950.0,
|
|
"step": 10450
|
|
},
|
|
{
|
|
"entropy": 5.472813606262207,
|
|
"epoch": 1.1742011568484303,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00048731476905215326,
|
|
"loss": 5.3059,
|
|
"mean_token_accuracy": 0.18500818759202958,
|
|
"num_tokens": 23318424.0,
|
|
"step": 10455
|
|
},
|
|
{
|
|
"entropy": 5.584354305267334,
|
|
"epoch": 1.174762733756388,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004873014753521673,
|
|
"loss": 5.5634,
|
|
"mean_token_accuracy": 0.17263590097427367,
|
|
"num_tokens": 23330186.0,
|
|
"step": 10460
|
|
},
|
|
{
|
|
"entropy": 5.649318361282349,
|
|
"epoch": 1.1753243106643454,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004872881748924199,
|
|
"loss": 5.3496,
|
|
"mean_token_accuracy": 0.18661798983812333,
|
|
"num_tokens": 23341878.0,
|
|
"step": 10465
|
|
},
|
|
{
|
|
"entropy": 5.615511178970337,
|
|
"epoch": 1.175885887572303,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004872748676733347,
|
|
"loss": 5.4777,
|
|
"mean_token_accuracy": 0.17548347413539886,
|
|
"num_tokens": 23352471.0,
|
|
"step": 10470
|
|
},
|
|
{
|
|
"entropy": 5.621794986724853,
|
|
"epoch": 1.1764474644802605,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.00048726155369533547,
|
|
"loss": 5.4891,
|
|
"mean_token_accuracy": 0.18269820213317872,
|
|
"num_tokens": 23363871.0,
|
|
"step": 10475
|
|
},
|
|
{
|
|
"entropy": 5.656167221069336,
|
|
"epoch": 1.1770090413882182,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.000487248232958846,
|
|
"loss": 5.5134,
|
|
"mean_token_accuracy": 0.17936725318431854,
|
|
"num_tokens": 23376072.0,
|
|
"step": 10480
|
|
},
|
|
{
|
|
"entropy": 5.487087917327881,
|
|
"epoch": 1.1775706182961756,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004872349054642904,
|
|
"loss": 5.3773,
|
|
"mean_token_accuracy": 0.18486556112766267,
|
|
"num_tokens": 23386670.0,
|
|
"step": 10485
|
|
},
|
|
{
|
|
"entropy": 5.646738195419312,
|
|
"epoch": 1.1781321952041333,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004872215712120932,
|
|
"loss": 5.4282,
|
|
"mean_token_accuracy": 0.1851399466395378,
|
|
"num_tokens": 23396499.0,
|
|
"step": 10490
|
|
},
|
|
{
|
|
"entropy": 5.627827501296997,
|
|
"epoch": 1.1786937721120907,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004872082302026788,
|
|
"loss": 5.4626,
|
|
"mean_token_accuracy": 0.1846533477306366,
|
|
"num_tokens": 23407898.0,
|
|
"step": 10495
|
|
},
|
|
{
|
|
"entropy": 5.552610301971436,
|
|
"epoch": 1.1792553490200484,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004871948824364721,
|
|
"loss": 5.4426,
|
|
"mean_token_accuracy": 0.1783500924706459,
|
|
"num_tokens": 23418877.0,
|
|
"step": 10500
|
|
},
|
|
{
|
|
"entropy": 5.524981164932251,
|
|
"epoch": 1.1798169259280058,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.000487181527913898,
|
|
"loss": 5.4091,
|
|
"mean_token_accuracy": 0.1811755284667015,
|
|
"num_tokens": 23431378.0,
|
|
"step": 10505
|
|
},
|
|
{
|
|
"entropy": 5.616604232788086,
|
|
"epoch": 1.1803785028359635,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.00048716816663538177,
|
|
"loss": 5.4221,
|
|
"mean_token_accuracy": 0.18377246409654618,
|
|
"num_tokens": 23442590.0,
|
|
"step": 10510
|
|
},
|
|
{
|
|
"entropy": 5.645650339126587,
|
|
"epoch": 1.180940079743921,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004871547986013488,
|
|
"loss": 5.5129,
|
|
"mean_token_accuracy": 0.176759235560894,
|
|
"num_tokens": 23454139.0,
|
|
"step": 10515
|
|
},
|
|
{
|
|
"entropy": 5.634320497512817,
|
|
"epoch": 1.1815016566518786,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004871414238122248,
|
|
"loss": 5.4535,
|
|
"mean_token_accuracy": 0.18437889814376832,
|
|
"num_tokens": 23464908.0,
|
|
"step": 10520
|
|
},
|
|
{
|
|
"entropy": 5.548039531707763,
|
|
"epoch": 1.182063233559836,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004871280422684355,
|
|
"loss": 5.4039,
|
|
"mean_token_accuracy": 0.18599554449319838,
|
|
"num_tokens": 23475436.0,
|
|
"step": 10525
|
|
},
|
|
{
|
|
"entropy": 5.6510828018188475,
|
|
"epoch": 1.1826248104677934,
|
|
"grad_norm": 2.71875,
|
|
"learning_rate": 0.00048711465397040726,
|
|
"loss": 5.5688,
|
|
"mean_token_accuracy": 0.17750822007656097,
|
|
"num_tokens": 23487384.0,
|
|
"step": 10530
|
|
},
|
|
{
|
|
"entropy": 5.718241024017334,
|
|
"epoch": 1.183186387375751,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.00048710125891856604,
|
|
"loss": 5.5207,
|
|
"mean_token_accuracy": 0.17472441494464874,
|
|
"num_tokens": 23498978.0,
|
|
"step": 10535
|
|
},
|
|
{
|
|
"entropy": 5.529882097244263,
|
|
"epoch": 1.1837479642837088,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00048708785711333845,
|
|
"loss": 5.3981,
|
|
"mean_token_accuracy": 0.18602953851222992,
|
|
"num_tokens": 23510825.0,
|
|
"step": 10540
|
|
},
|
|
{
|
|
"entropy": 5.53178858757019,
|
|
"epoch": 1.1843095411916662,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00048707444855515124,
|
|
"loss": 5.3904,
|
|
"mean_token_accuracy": 0.18575898855924605,
|
|
"num_tokens": 23522383.0,
|
|
"step": 10545
|
|
},
|
|
{
|
|
"entropy": 5.6463545799255375,
|
|
"epoch": 1.1848711180996236,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004870610332444314,
|
|
"loss": 5.5725,
|
|
"mean_token_accuracy": 0.17957879304885865,
|
|
"num_tokens": 23534255.0,
|
|
"step": 10550
|
|
},
|
|
{
|
|
"entropy": 5.630608129501343,
|
|
"epoch": 1.1854326950075813,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004870476111816059,
|
|
"loss": 5.4772,
|
|
"mean_token_accuracy": 0.17648603469133378,
|
|
"num_tokens": 23545888.0,
|
|
"step": 10555
|
|
},
|
|
{
|
|
"entropy": 5.59116530418396,
|
|
"epoch": 1.1859942719155387,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.00048703418236710234,
|
|
"loss": 5.479,
|
|
"mean_token_accuracy": 0.17763277441263198,
|
|
"num_tokens": 23556776.0,
|
|
"step": 10560
|
|
},
|
|
{
|
|
"entropy": 5.703448057174683,
|
|
"epoch": 1.1865558488234964,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004870207468013481,
|
|
"loss": 5.4081,
|
|
"mean_token_accuracy": 0.18237634003162384,
|
|
"num_tokens": 23569971.0,
|
|
"step": 10565
|
|
},
|
|
{
|
|
"entropy": 5.602100801467896,
|
|
"epoch": 1.1871174257314538,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004870073044847711,
|
|
"loss": 5.5371,
|
|
"mean_token_accuracy": 0.1801938682794571,
|
|
"num_tokens": 23580751.0,
|
|
"step": 10570
|
|
},
|
|
{
|
|
"entropy": 5.501537895202636,
|
|
"epoch": 1.1876790026394115,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004869938554177993,
|
|
"loss": 5.3992,
|
|
"mean_token_accuracy": 0.18619302660226822,
|
|
"num_tokens": 23591423.0,
|
|
"step": 10575
|
|
},
|
|
{
|
|
"entropy": 5.630936050415039,
|
|
"epoch": 1.188240579547369,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.00048698039960086084,
|
|
"loss": 5.3665,
|
|
"mean_token_accuracy": 0.17726145088672637,
|
|
"num_tokens": 23601552.0,
|
|
"step": 10580
|
|
},
|
|
{
|
|
"entropy": 5.55292820930481,
|
|
"epoch": 1.1888021564553266,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.0004869669370343843,
|
|
"loss": 5.466,
|
|
"mean_token_accuracy": 0.18769415318965912,
|
|
"num_tokens": 23613080.0,
|
|
"step": 10585
|
|
},
|
|
{
|
|
"entropy": 5.550881624221802,
|
|
"epoch": 1.189363733363284,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004869534677187983,
|
|
"loss": 5.3534,
|
|
"mean_token_accuracy": 0.18469875305891037,
|
|
"num_tokens": 23623559.0,
|
|
"step": 10590
|
|
},
|
|
{
|
|
"entropy": 5.566106939315796,
|
|
"epoch": 1.1899253102712417,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004869399916545317,
|
|
"loss": 5.3683,
|
|
"mean_token_accuracy": 0.18476739078760146,
|
|
"num_tokens": 23634113.0,
|
|
"step": 10595
|
|
},
|
|
{
|
|
"entropy": 5.513452339172363,
|
|
"epoch": 1.1904868871791991,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004869265088420135,
|
|
"loss": 5.2838,
|
|
"mean_token_accuracy": 0.19047885537147521,
|
|
"num_tokens": 23645203.0,
|
|
"step": 10600
|
|
},
|
|
{
|
|
"entropy": 5.523169946670532,
|
|
"epoch": 1.1910484640871568,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004869130192816731,
|
|
"loss": 5.4231,
|
|
"mean_token_accuracy": 0.18399088382720946,
|
|
"num_tokens": 23654880.0,
|
|
"step": 10605
|
|
},
|
|
{
|
|
"entropy": 5.537129068374634,
|
|
"epoch": 1.1916100409951143,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.00048689952297394,
|
|
"loss": 5.3309,
|
|
"mean_token_accuracy": 0.1929388478398323,
|
|
"num_tokens": 23664962.0,
|
|
"step": 10610
|
|
},
|
|
{
|
|
"entropy": 5.602372550964356,
|
|
"epoch": 1.192171617903072,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004868860199192438,
|
|
"loss": 5.3893,
|
|
"mean_token_accuracy": 0.19017872512340545,
|
|
"num_tokens": 23675288.0,
|
|
"step": 10615
|
|
},
|
|
{
|
|
"entropy": 5.52705454826355,
|
|
"epoch": 1.1927331948110294,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004868725101180146,
|
|
"loss": 5.3964,
|
|
"mean_token_accuracy": 0.18070517629384994,
|
|
"num_tokens": 23685948.0,
|
|
"step": 10620
|
|
},
|
|
{
|
|
"entropy": 5.641992568969727,
|
|
"epoch": 1.1932947717189868,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004868589935706826,
|
|
"loss": 5.4599,
|
|
"mean_token_accuracy": 0.17490803301334382,
|
|
"num_tokens": 23696980.0,
|
|
"step": 10625
|
|
},
|
|
{
|
|
"entropy": 5.663866281509399,
|
|
"epoch": 1.1938563486269445,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.00048684547027767793,
|
|
"loss": 5.4986,
|
|
"mean_token_accuracy": 0.17656034231185913,
|
|
"num_tokens": 23708644.0,
|
|
"step": 10630
|
|
},
|
|
{
|
|
"entropy": 5.59591007232666,
|
|
"epoch": 1.1944179255349021,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004868319402394314,
|
|
"loss": 5.4738,
|
|
"mean_token_accuracy": 0.18437945246696472,
|
|
"num_tokens": 23719652.0,
|
|
"step": 10635
|
|
},
|
|
{
|
|
"entropy": 5.6034361839294435,
|
|
"epoch": 1.1949795024428596,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.00048681840345637375,
|
|
"loss": 5.4253,
|
|
"mean_token_accuracy": 0.18002281337976456,
|
|
"num_tokens": 23731906.0,
|
|
"step": 10640
|
|
},
|
|
{
|
|
"entropy": 5.614962434768676,
|
|
"epoch": 1.195541079350817,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.00048680485992893597,
|
|
"loss": 5.475,
|
|
"mean_token_accuracy": 0.18151820302009583,
|
|
"num_tokens": 23744184.0,
|
|
"step": 10645
|
|
},
|
|
{
|
|
"entropy": 5.541026449203491,
|
|
"epoch": 1.1961026562587747,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.00048679130965754926,
|
|
"loss": 5.298,
|
|
"mean_token_accuracy": 0.1837436631321907,
|
|
"num_tokens": 23754807.0,
|
|
"step": 10650
|
|
},
|
|
{
|
|
"entropy": 5.514839363098145,
|
|
"epoch": 1.196664233166732,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004867777526426451,
|
|
"loss": 5.3977,
|
|
"mean_token_accuracy": 0.1806316688656807,
|
|
"num_tokens": 23765907.0,
|
|
"step": 10655
|
|
},
|
|
{
|
|
"entropy": 5.6018781661987305,
|
|
"epoch": 1.1972258100746898,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.00048676418888465525,
|
|
"loss": 5.4269,
|
|
"mean_token_accuracy": 0.1833296984434128,
|
|
"num_tokens": 23776217.0,
|
|
"step": 10660
|
|
},
|
|
{
|
|
"entropy": 5.576879549026489,
|
|
"epoch": 1.1977873869826472,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.0004867506183840114,
|
|
"loss": 5.3802,
|
|
"mean_token_accuracy": 0.18599339574575424,
|
|
"num_tokens": 23786170.0,
|
|
"step": 10665
|
|
},
|
|
{
|
|
"entropy": 5.650488471984863,
|
|
"epoch": 1.1983489638906049,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.0004867370411411459,
|
|
"loss": 5.5168,
|
|
"mean_token_accuracy": 0.1732734113931656,
|
|
"num_tokens": 23796491.0,
|
|
"step": 10670
|
|
},
|
|
{
|
|
"entropy": 5.564750051498413,
|
|
"epoch": 1.1989105407985623,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.00048672345715649066,
|
|
"loss": 5.3899,
|
|
"mean_token_accuracy": 0.1827486753463745,
|
|
"num_tokens": 23807718.0,
|
|
"step": 10675
|
|
},
|
|
{
|
|
"entropy": 5.5354297161102295,
|
|
"epoch": 1.19947211770652,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004867098664304785,
|
|
"loss": 5.5055,
|
|
"mean_token_accuracy": 0.1804208055138588,
|
|
"num_tokens": 23818623.0,
|
|
"step": 10680
|
|
},
|
|
{
|
|
"entropy": 5.555293941497803,
|
|
"epoch": 1.2000336946144774,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004866962689635422,
|
|
"loss": 5.425,
|
|
"mean_token_accuracy": 0.1853599354624748,
|
|
"num_tokens": 23829173.0,
|
|
"step": 10685
|
|
},
|
|
{
|
|
"entropy": 5.594825649261475,
|
|
"epoch": 1.200595271522435,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.00048668266475611447,
|
|
"loss": 5.3517,
|
|
"mean_token_accuracy": 0.1820319652557373,
|
|
"num_tokens": 23840689.0,
|
|
"step": 10690
|
|
},
|
|
{
|
|
"entropy": 5.675231122970581,
|
|
"epoch": 1.2011568484303925,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004866690538086286,
|
|
"loss": 5.5828,
|
|
"mean_token_accuracy": 0.17370163053274154,
|
|
"num_tokens": 23852858.0,
|
|
"step": 10695
|
|
},
|
|
{
|
|
"entropy": 5.607054805755615,
|
|
"epoch": 1.2017184253383502,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.00048665543612151803,
|
|
"loss": 5.3814,
|
|
"mean_token_accuracy": 0.1894412964582443,
|
|
"num_tokens": 23864137.0,
|
|
"step": 10700
|
|
},
|
|
{
|
|
"entropy": 5.575736999511719,
|
|
"epoch": 1.2022800022463076,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.00048664181169521625,
|
|
"loss": 5.4326,
|
|
"mean_token_accuracy": 0.18311810344457627,
|
|
"num_tokens": 23875087.0,
|
|
"step": 10705
|
|
},
|
|
{
|
|
"entropy": 5.549623203277588,
|
|
"epoch": 1.2028415791542653,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.0004866281805301571,
|
|
"loss": 5.3219,
|
|
"mean_token_accuracy": 0.1916783109307289,
|
|
"num_tokens": 23886521.0,
|
|
"step": 10710
|
|
},
|
|
{
|
|
"entropy": 5.567817354202271,
|
|
"epoch": 1.2034031560622227,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004866145426267746,
|
|
"loss": 5.4351,
|
|
"mean_token_accuracy": 0.17877652496099472,
|
|
"num_tokens": 23897660.0,
|
|
"step": 10715
|
|
},
|
|
{
|
|
"entropy": 5.569176912307739,
|
|
"epoch": 1.2039647329701804,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.000486600897985503,
|
|
"loss": 5.4775,
|
|
"mean_token_accuracy": 0.18148595541715623,
|
|
"num_tokens": 23910543.0,
|
|
"step": 10720
|
|
},
|
|
{
|
|
"entropy": 5.651079368591309,
|
|
"epoch": 1.2045263098781378,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.00048658724660677674,
|
|
"loss": 5.3545,
|
|
"mean_token_accuracy": 0.18516494184732438,
|
|
"num_tokens": 23921687.0,
|
|
"step": 10725
|
|
},
|
|
{
|
|
"entropy": 5.644492149353027,
|
|
"epoch": 1.2050878867860955,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.0004865735884910305,
|
|
"loss": 5.4527,
|
|
"mean_token_accuracy": 0.17805104255676268,
|
|
"num_tokens": 23933717.0,
|
|
"step": 10730
|
|
},
|
|
{
|
|
"entropy": 5.565663385391235,
|
|
"epoch": 1.205649463694053,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004865599236386991,
|
|
"loss": 5.5131,
|
|
"mean_token_accuracy": 0.17860305160284043,
|
|
"num_tokens": 23947764.0,
|
|
"step": 10735
|
|
},
|
|
{
|
|
"entropy": 5.548420000076294,
|
|
"epoch": 1.2062110406020103,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004865462520502177,
|
|
"loss": 5.3857,
|
|
"mean_token_accuracy": 0.17887697070837022,
|
|
"num_tokens": 23960096.0,
|
|
"step": 10740
|
|
},
|
|
{
|
|
"entropy": 5.641502857208252,
|
|
"epoch": 1.206772617509968,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004865325737260216,
|
|
"loss": 5.4026,
|
|
"mean_token_accuracy": 0.17797549962997436,
|
|
"num_tokens": 23971573.0,
|
|
"step": 10745
|
|
},
|
|
{
|
|
"entropy": 5.594951152801514,
|
|
"epoch": 1.2073341944179254,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.00048651888866654624,
|
|
"loss": 5.3613,
|
|
"mean_token_accuracy": 0.19261209070682525,
|
|
"num_tokens": 23982710.0,
|
|
"step": 10750
|
|
},
|
|
{
|
|
"entropy": 5.460863971710205,
|
|
"epoch": 1.207895771325883,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004865051968722275,
|
|
"loss": 5.3161,
|
|
"mean_token_accuracy": 0.1874060869216919,
|
|
"num_tokens": 23993663.0,
|
|
"step": 10755
|
|
},
|
|
{
|
|
"entropy": 5.5636594772338865,
|
|
"epoch": 1.2084573482338405,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00048649149834350126,
|
|
"loss": 5.561,
|
|
"mean_token_accuracy": 0.1814848840236664,
|
|
"num_tokens": 24005112.0,
|
|
"step": 10760
|
|
},
|
|
{
|
|
"entropy": 5.523722505569458,
|
|
"epoch": 1.2090189251417982,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004864777930808037,
|
|
"loss": 5.3079,
|
|
"mean_token_accuracy": 0.1889803558588028,
|
|
"num_tokens": 24015855.0,
|
|
"step": 10765
|
|
},
|
|
{
|
|
"entropy": 5.533093738555908,
|
|
"epoch": 1.2095805020497556,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004864640810845711,
|
|
"loss": 5.3611,
|
|
"mean_token_accuracy": 0.18602087199687958,
|
|
"num_tokens": 24027232.0,
|
|
"step": 10770
|
|
},
|
|
{
|
|
"entropy": 5.5402055263519285,
|
|
"epoch": 1.2101420789577133,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004864503623552402,
|
|
"loss": 5.3606,
|
|
"mean_token_accuracy": 0.1877458542585373,
|
|
"num_tokens": 24039127.0,
|
|
"step": 10775
|
|
},
|
|
{
|
|
"entropy": 5.627122831344605,
|
|
"epoch": 1.2107036558656707,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004864366368932478,
|
|
"loss": 5.4973,
|
|
"mean_token_accuracy": 0.1808575674891472,
|
|
"num_tokens": 24049821.0,
|
|
"step": 10780
|
|
},
|
|
{
|
|
"entropy": 5.597670602798462,
|
|
"epoch": 1.2112652327736284,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.00048642290469903083,
|
|
"loss": 5.5212,
|
|
"mean_token_accuracy": 0.17994545847177507,
|
|
"num_tokens": 24060305.0,
|
|
"step": 10785
|
|
},
|
|
{
|
|
"entropy": 5.579167890548706,
|
|
"epoch": 1.2118268096815858,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.00048640916577302664,
|
|
"loss": 5.3939,
|
|
"mean_token_accuracy": 0.18764331489801406,
|
|
"num_tokens": 24071193.0,
|
|
"step": 10790
|
|
},
|
|
{
|
|
"entropy": 5.47999062538147,
|
|
"epoch": 1.2123883865895435,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.00048639542011567243,
|
|
"loss": 5.2623,
|
|
"mean_token_accuracy": 0.2041529268026352,
|
|
"num_tokens": 24082380.0,
|
|
"step": 10795
|
|
},
|
|
{
|
|
"entropy": 5.653561067581177,
|
|
"epoch": 1.212949963497501,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004863816677274062,
|
|
"loss": 5.5384,
|
|
"mean_token_accuracy": 0.179527847468853,
|
|
"num_tokens": 24093168.0,
|
|
"step": 10800
|
|
},
|
|
{
|
|
"entropy": 5.539981079101563,
|
|
"epoch": 1.2135115404054586,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.00048636790860866576,
|
|
"loss": 5.3951,
|
|
"mean_token_accuracy": 0.18281326144933702,
|
|
"num_tokens": 24105355.0,
|
|
"step": 10805
|
|
},
|
|
{
|
|
"entropy": 5.488740491867065,
|
|
"epoch": 1.214073117313416,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004863541427598889,
|
|
"loss": 5.3561,
|
|
"mean_token_accuracy": 0.18512464463710784,
|
|
"num_tokens": 24117062.0,
|
|
"step": 10810
|
|
},
|
|
{
|
|
"entropy": 5.651952171325684,
|
|
"epoch": 1.2146346942213737,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004863403701815144,
|
|
"loss": 5.5061,
|
|
"mean_token_accuracy": 0.17755191177129745,
|
|
"num_tokens": 24127770.0,
|
|
"step": 10815
|
|
},
|
|
{
|
|
"entropy": 5.588659286499023,
|
|
"epoch": 1.2151962711293312,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004863265908739805,
|
|
"loss": 5.582,
|
|
"mean_token_accuracy": 0.17055042684078217,
|
|
"num_tokens": 24139894.0,
|
|
"step": 10820
|
|
},
|
|
{
|
|
"entropy": 5.603845548629761,
|
|
"epoch": 1.2157578480372888,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004863128048377259,
|
|
"loss": 5.3819,
|
|
"mean_token_accuracy": 0.19205069839954375,
|
|
"num_tokens": 24150799.0,
|
|
"step": 10825
|
|
},
|
|
{
|
|
"entropy": 5.6096703052520756,
|
|
"epoch": 1.2163194249452463,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004862990120731896,
|
|
"loss": 5.4246,
|
|
"mean_token_accuracy": 0.18172770291566848,
|
|
"num_tokens": 24161406.0,
|
|
"step": 10830
|
|
},
|
|
{
|
|
"entropy": 5.434682083129883,
|
|
"epoch": 1.2168810018532037,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.00048628521258081096,
|
|
"loss": 5.3194,
|
|
"mean_token_accuracy": 0.18648598492145538,
|
|
"num_tokens": 24171884.0,
|
|
"step": 10835
|
|
},
|
|
{
|
|
"entropy": 5.543994188308716,
|
|
"epoch": 1.2174425787611614,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00048627140636102906,
|
|
"loss": 5.3909,
|
|
"mean_token_accuracy": 0.18740372359752655,
|
|
"num_tokens": 24183873.0,
|
|
"step": 10840
|
|
},
|
|
{
|
|
"entropy": 5.662725353240967,
|
|
"epoch": 1.2180041556691188,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004862575934142837,
|
|
"loss": 5.4401,
|
|
"mean_token_accuracy": 0.18730383813381196,
|
|
"num_tokens": 24194689.0,
|
|
"step": 10845
|
|
},
|
|
{
|
|
"entropy": 5.545740222930908,
|
|
"epoch": 1.2185657325770765,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004862437737410147,
|
|
"loss": 5.3497,
|
|
"mean_token_accuracy": 0.18136660158634185,
|
|
"num_tokens": 24206675.0,
|
|
"step": 10850
|
|
},
|
|
{
|
|
"entropy": 5.513843154907226,
|
|
"epoch": 1.219127309485034,
|
|
"grad_norm": 2.921875,
|
|
"learning_rate": 0.0004862299473416619,
|
|
"loss": 5.4377,
|
|
"mean_token_accuracy": 0.17925103157758712,
|
|
"num_tokens": 24218845.0,
|
|
"step": 10855
|
|
},
|
|
{
|
|
"entropy": 5.570048236846924,
|
|
"epoch": 1.2196888863929916,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.00048621611421666573,
|
|
"loss": 5.4684,
|
|
"mean_token_accuracy": 0.17514824569225312,
|
|
"num_tokens": 24229889.0,
|
|
"step": 10860
|
|
},
|
|
{
|
|
"entropy": 5.662149095535279,
|
|
"epoch": 1.220250463300949,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004862022743664665,
|
|
"loss": 5.5148,
|
|
"mean_token_accuracy": 0.1838795378804207,
|
|
"num_tokens": 24240729.0,
|
|
"step": 10865
|
|
},
|
|
{
|
|
"entropy": 5.6571629524230955,
|
|
"epoch": 1.2208120402089067,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.00048618842779150494,
|
|
"loss": 5.5292,
|
|
"mean_token_accuracy": 0.17597716152668,
|
|
"num_tokens": 24251765.0,
|
|
"step": 10870
|
|
},
|
|
{
|
|
"entropy": 5.558348178863525,
|
|
"epoch": 1.221373617116864,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.00048617457449222205,
|
|
"loss": 5.4365,
|
|
"mean_token_accuracy": 0.1781846523284912,
|
|
"num_tokens": 24262273.0,
|
|
"step": 10875
|
|
},
|
|
{
|
|
"entropy": 5.612859439849854,
|
|
"epoch": 1.2219351940248218,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004861607144690587,
|
|
"loss": 5.4272,
|
|
"mean_token_accuracy": 0.17829763144254684,
|
|
"num_tokens": 24272313.0,
|
|
"step": 10880
|
|
},
|
|
{
|
|
"entropy": 5.64711561203003,
|
|
"epoch": 1.2224967709327792,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004861468477224563,
|
|
"loss": 5.4948,
|
|
"mean_token_accuracy": 0.1757294699549675,
|
|
"num_tokens": 24283971.0,
|
|
"step": 10885
|
|
},
|
|
{
|
|
"entropy": 5.55884313583374,
|
|
"epoch": 1.2230583478407369,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.00048613297425285635,
|
|
"loss": 5.4284,
|
|
"mean_token_accuracy": 0.18071170300245284,
|
|
"num_tokens": 24294357.0,
|
|
"step": 10890
|
|
},
|
|
{
|
|
"entropy": 5.53272123336792,
|
|
"epoch": 1.2236199247486943,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004861190940607007,
|
|
"loss": 5.2968,
|
|
"mean_token_accuracy": 0.1882367879152298,
|
|
"num_tokens": 24305894.0,
|
|
"step": 10895
|
|
},
|
|
{
|
|
"entropy": 5.5826810836792,
|
|
"epoch": 1.224181501656652,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004861052071464312,
|
|
"loss": 5.4099,
|
|
"mean_token_accuracy": 0.1851435512304306,
|
|
"num_tokens": 24318506.0,
|
|
"step": 10900
|
|
},
|
|
{
|
|
"entropy": 5.564007949829102,
|
|
"epoch": 1.2247430785646094,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.00048609131351048994,
|
|
"loss": 5.4156,
|
|
"mean_token_accuracy": 0.17732575088739394,
|
|
"num_tokens": 24330169.0,
|
|
"step": 10905
|
|
},
|
|
{
|
|
"entropy": 5.518369913101196,
|
|
"epoch": 1.225304655472567,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004860774131533195,
|
|
"loss": 5.3681,
|
|
"mean_token_accuracy": 0.1917150542140007,
|
|
"num_tokens": 24340063.0,
|
|
"step": 10910
|
|
},
|
|
{
|
|
"entropy": 5.599963855743408,
|
|
"epoch": 1.2258662323805245,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.00048606350607536235,
|
|
"loss": 5.4386,
|
|
"mean_token_accuracy": 0.18412175327539443,
|
|
"num_tokens": 24351506.0,
|
|
"step": 10915
|
|
},
|
|
{
|
|
"entropy": 5.537996482849121,
|
|
"epoch": 1.2264278092884822,
|
|
"grad_norm": 2.9375,
|
|
"learning_rate": 0.0004860495922770612,
|
|
"loss": 5.4124,
|
|
"mean_token_accuracy": 0.17802354991436004,
|
|
"num_tokens": 24362168.0,
|
|
"step": 10920
|
|
},
|
|
{
|
|
"entropy": 5.511146926879883,
|
|
"epoch": 1.2269893861964396,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.00048603567175885926,
|
|
"loss": 5.3564,
|
|
"mean_token_accuracy": 0.1828833281993866,
|
|
"num_tokens": 24372269.0,
|
|
"step": 10925
|
|
},
|
|
{
|
|
"entropy": 5.5755280494689945,
|
|
"epoch": 1.227550963104397,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004860217445211997,
|
|
"loss": 5.4694,
|
|
"mean_token_accuracy": 0.18339033424854279,
|
|
"num_tokens": 24384368.0,
|
|
"step": 10930
|
|
},
|
|
{
|
|
"entropy": 5.639485788345337,
|
|
"epoch": 1.2281125400123547,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004860078105645259,
|
|
"loss": 5.3821,
|
|
"mean_token_accuracy": 0.18572250306606292,
|
|
"num_tokens": 24395395.0,
|
|
"step": 10935
|
|
},
|
|
{
|
|
"entropy": 5.521928453445435,
|
|
"epoch": 1.2286741169203121,
|
|
"grad_norm": 3.046875,
|
|
"learning_rate": 0.0004859938698892816,
|
|
"loss": 5.34,
|
|
"mean_token_accuracy": 0.1804175704717636,
|
|
"num_tokens": 24406709.0,
|
|
"step": 10940
|
|
},
|
|
{
|
|
"entropy": 5.538202095031738,
|
|
"epoch": 1.2292356938282698,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.00048597992249591065,
|
|
"loss": 5.4913,
|
|
"mean_token_accuracy": 0.18075333684682846,
|
|
"num_tokens": 24418574.0,
|
|
"step": 10945
|
|
},
|
|
{
|
|
"entropy": 5.719617748260498,
|
|
"epoch": 1.2297972707362272,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.00048596596838485704,
|
|
"loss": 5.4447,
|
|
"mean_token_accuracy": 0.18116745054721833,
|
|
"num_tokens": 24429418.0,
|
|
"step": 10950
|
|
},
|
|
{
|
|
"entropy": 5.615225076675415,
|
|
"epoch": 1.230358847644185,
|
|
"grad_norm": 2.671875,
|
|
"learning_rate": 0.0004859520075565654,
|
|
"loss": 5.5106,
|
|
"mean_token_accuracy": 0.18256430327892303,
|
|
"num_tokens": 24440301.0,
|
|
"step": 10955
|
|
},
|
|
{
|
|
"entropy": 5.574560832977295,
|
|
"epoch": 1.2309204245521423,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.00048593804001147986,
|
|
"loss": 5.5404,
|
|
"mean_token_accuracy": 0.1761474683880806,
|
|
"num_tokens": 24451987.0,
|
|
"step": 10960
|
|
},
|
|
{
|
|
"entropy": 5.59624605178833,
|
|
"epoch": 1.2314820014601,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004859240657500453,
|
|
"loss": 5.3956,
|
|
"mean_token_accuracy": 0.18446308821439744,
|
|
"num_tokens": 24461971.0,
|
|
"step": 10965
|
|
},
|
|
{
|
|
"entropy": 5.531461906433106,
|
|
"epoch": 1.2320435783680574,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00048591008477270675,
|
|
"loss": 5.3155,
|
|
"mean_token_accuracy": 0.18719284236431122,
|
|
"num_tokens": 24472193.0,
|
|
"step": 10970
|
|
},
|
|
{
|
|
"entropy": 5.4965959072113035,
|
|
"epoch": 1.232605155276015,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.00048589609707990925,
|
|
"loss": 5.4151,
|
|
"mean_token_accuracy": 0.1810591474175453,
|
|
"num_tokens": 24483075.0,
|
|
"step": 10975
|
|
},
|
|
{
|
|
"entropy": 5.516279792785644,
|
|
"epoch": 1.2331667321839725,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.00048588210267209823,
|
|
"loss": 5.3412,
|
|
"mean_token_accuracy": 0.19502355754375458,
|
|
"num_tokens": 24493070.0,
|
|
"step": 10980
|
|
},
|
|
{
|
|
"entropy": 5.492527437210083,
|
|
"epoch": 1.2337283090919302,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.00048586810154971935,
|
|
"loss": 5.4668,
|
|
"mean_token_accuracy": 0.17707120180130004,
|
|
"num_tokens": 24502866.0,
|
|
"step": 10985
|
|
},
|
|
{
|
|
"entropy": 5.54741096496582,
|
|
"epoch": 1.2342898859998876,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.00048585409371321826,
|
|
"loss": 5.3397,
|
|
"mean_token_accuracy": 0.19318298250436783,
|
|
"num_tokens": 24514169.0,
|
|
"step": 10990
|
|
},
|
|
{
|
|
"entropy": 5.664519739151001,
|
|
"epoch": 1.2348514629078453,
|
|
"grad_norm": 2.609375,
|
|
"learning_rate": 0.00048584007916304106,
|
|
"loss": 5.5396,
|
|
"mean_token_accuracy": 0.1791799932718277,
|
|
"num_tokens": 24525552.0,
|
|
"step": 10995
|
|
},
|
|
{
|
|
"entropy": 5.563682317733765,
|
|
"epoch": 1.2354130398158027,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.00048582605789963395,
|
|
"loss": 5.4504,
|
|
"mean_token_accuracy": 0.18420275896787644,
|
|
"num_tokens": 24536370.0,
|
|
"step": 11000
|
|
},
|
|
{
|
|
"entropy": 5.597484731674195,
|
|
"epoch": 1.2359746167237604,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 0.0004858120299234434,
|
|
"loss": 5.4714,
|
|
"mean_token_accuracy": 0.1837515950202942,
|
|
"num_tokens": 24546868.0,
|
|
"step": 11005
|
|
},
|
|
{
|
|
"entropy": 5.65571551322937,
|
|
"epoch": 1.2365361936317179,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.00048579799523491607,
|
|
"loss": 5.4293,
|
|
"mean_token_accuracy": 0.17340353578329087,
|
|
"num_tokens": 24558279.0,
|
|
"step": 11010
|
|
},
|
|
{
|
|
"entropy": 5.577965450286865,
|
|
"epoch": 1.2370977705396755,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004857839538344988,
|
|
"loss": 5.3583,
|
|
"mean_token_accuracy": 0.18387570977210999,
|
|
"num_tokens": 24568321.0,
|
|
"step": 11015
|
|
},
|
|
{
|
|
"entropy": 5.52414608001709,
|
|
"epoch": 1.237659347447633,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.00048576990572263875,
|
|
"loss": 5.417,
|
|
"mean_token_accuracy": 0.17986870557069778,
|
|
"num_tokens": 24579137.0,
|
|
"step": 11020
|
|
},
|
|
{
|
|
"entropy": 5.611784029006958,
|
|
"epoch": 1.2382209243555904,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004857558508997831,
|
|
"loss": 5.4729,
|
|
"mean_token_accuracy": 0.1754674106836319,
|
|
"num_tokens": 24591523.0,
|
|
"step": 11025
|
|
},
|
|
{
|
|
"entropy": 5.613817977905273,
|
|
"epoch": 1.238782501263548,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004857417893663794,
|
|
"loss": 5.3944,
|
|
"mean_token_accuracy": 0.18179088830947876,
|
|
"num_tokens": 24601998.0,
|
|
"step": 11030
|
|
},
|
|
{
|
|
"entropy": 5.542374229431152,
|
|
"epoch": 1.2393440781715055,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004857277211228754,
|
|
"loss": 5.3645,
|
|
"mean_token_accuracy": 0.18529855608940124,
|
|
"num_tokens": 24612371.0,
|
|
"step": 11035
|
|
},
|
|
{
|
|
"entropy": 5.59985466003418,
|
|
"epoch": 1.2399056550794632,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004857136461697191,
|
|
"loss": 5.4681,
|
|
"mean_token_accuracy": 0.18155949413776398,
|
|
"num_tokens": 24623350.0,
|
|
"step": 11040
|
|
},
|
|
{
|
|
"entropy": 5.641364288330078,
|
|
"epoch": 1.2404672319874206,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00048569956450735853,
|
|
"loss": 5.4495,
|
|
"mean_token_accuracy": 0.18078392893075942,
|
|
"num_tokens": 24634365.0,
|
|
"step": 11045
|
|
},
|
|
{
|
|
"entropy": 5.6573450565338135,
|
|
"epoch": 1.2410288088953783,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.00048568547613624206,
|
|
"loss": 5.541,
|
|
"mean_token_accuracy": 0.18133490532636642,
|
|
"num_tokens": 24645227.0,
|
|
"step": 11050
|
|
},
|
|
{
|
|
"entropy": 5.669416999816894,
|
|
"epoch": 1.2415903858033357,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00048567138105681833,
|
|
"loss": 5.4892,
|
|
"mean_token_accuracy": 0.1802353411912918,
|
|
"num_tokens": 24656807.0,
|
|
"step": 11055
|
|
},
|
|
{
|
|
"entropy": 5.605979776382446,
|
|
"epoch": 1.2421519627112934,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.00048565727926953617,
|
|
"loss": 5.4928,
|
|
"mean_token_accuracy": 0.18245369344949722,
|
|
"num_tokens": 24669021.0,
|
|
"step": 11060
|
|
},
|
|
{
|
|
"entropy": 5.581379795074463,
|
|
"epoch": 1.2427135396192508,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004856431707748445,
|
|
"loss": 5.393,
|
|
"mean_token_accuracy": 0.18967633247375487,
|
|
"num_tokens": 24678802.0,
|
|
"step": 11065
|
|
},
|
|
{
|
|
"entropy": 5.587186098098755,
|
|
"epoch": 1.2432751165272085,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004856290555731926,
|
|
"loss": 5.3781,
|
|
"mean_token_accuracy": 0.18544357568025588,
|
|
"num_tokens": 24688449.0,
|
|
"step": 11070
|
|
},
|
|
{
|
|
"entropy": 5.535901975631714,
|
|
"epoch": 1.243836693435166,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004856149336650299,
|
|
"loss": 5.4521,
|
|
"mean_token_accuracy": 0.17772786617279052,
|
|
"num_tokens": 24700272.0,
|
|
"step": 11075
|
|
},
|
|
{
|
|
"entropy": 5.649112796783447,
|
|
"epoch": 1.2443982703431236,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004856008050508059,
|
|
"loss": 5.5979,
|
|
"mean_token_accuracy": 0.17577450573444367,
|
|
"num_tokens": 24711949.0,
|
|
"step": 11080
|
|
},
|
|
{
|
|
"entropy": 5.661371088027954,
|
|
"epoch": 1.244959847251081,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004855866697309707,
|
|
"loss": 5.4132,
|
|
"mean_token_accuracy": 0.1884407803416252,
|
|
"num_tokens": 24723535.0,
|
|
"step": 11085
|
|
},
|
|
{
|
|
"entropy": 5.493203115463257,
|
|
"epoch": 1.2455214241590387,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004855725277059742,
|
|
"loss": 5.4221,
|
|
"mean_token_accuracy": 0.17563299536705018,
|
|
"num_tokens": 24734915.0,
|
|
"step": 11090
|
|
},
|
|
{
|
|
"entropy": 5.537456607818603,
|
|
"epoch": 1.246083001066996,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004855583789762668,
|
|
"loss": 5.3471,
|
|
"mean_token_accuracy": 0.19495553225278855,
|
|
"num_tokens": 24745744.0,
|
|
"step": 11095
|
|
},
|
|
{
|
|
"entropy": 5.653546333312988,
|
|
"epoch": 1.2466445779749538,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.000485544223542299,
|
|
"loss": 5.5627,
|
|
"mean_token_accuracy": 0.18065301030874253,
|
|
"num_tokens": 24758158.0,
|
|
"step": 11100
|
|
},
|
|
{
|
|
"entropy": 5.655344104766845,
|
|
"epoch": 1.2472061548829112,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004855300614045214,
|
|
"loss": 5.426,
|
|
"mean_token_accuracy": 0.184110064804554,
|
|
"num_tokens": 24768607.0,
|
|
"step": 11105
|
|
},
|
|
{
|
|
"entropy": 5.563532066345215,
|
|
"epoch": 1.2477677317908689,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00048551589256338497,
|
|
"loss": 5.4019,
|
|
"mean_token_accuracy": 0.18666046857833862,
|
|
"num_tokens": 24779845.0,
|
|
"step": 11110
|
|
},
|
|
{
|
|
"entropy": 5.534594440460205,
|
|
"epoch": 1.2483293086988263,
|
|
"grad_norm": 2.6875,
|
|
"learning_rate": 0.00048550171701934087,
|
|
"loss": 5.3665,
|
|
"mean_token_accuracy": 0.17801106125116348,
|
|
"num_tokens": 24790049.0,
|
|
"step": 11115
|
|
},
|
|
{
|
|
"entropy": 5.672994184494018,
|
|
"epoch": 1.2488908856067837,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.00048548753477284053,
|
|
"loss": 5.4315,
|
|
"mean_token_accuracy": 0.18115769624710082,
|
|
"num_tokens": 24802112.0,
|
|
"step": 11120
|
|
},
|
|
{
|
|
"entropy": 5.597347974777222,
|
|
"epoch": 1.2494524625147414,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004854733458243354,
|
|
"loss": 5.3822,
|
|
"mean_token_accuracy": 0.1801334246993065,
|
|
"num_tokens": 24812630.0,
|
|
"step": 11125
|
|
},
|
|
{
|
|
"entropy": 5.534896183013916,
|
|
"epoch": 1.250014039422699,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004854591501742773,
|
|
"loss": 5.3699,
|
|
"mean_token_accuracy": 0.1891779601573944,
|
|
"num_tokens": 24823346.0,
|
|
"step": 11130
|
|
},
|
|
{
|
|
"entropy": 5.553601455688477,
|
|
"epoch": 1.2505756163306565,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.00048544494782311825,
|
|
"loss": 5.4509,
|
|
"mean_token_accuracy": 0.1782315269112587,
|
|
"num_tokens": 24834374.0,
|
|
"step": 11135
|
|
},
|
|
{
|
|
"entropy": 5.551606559753418,
|
|
"epoch": 1.251137193238614,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00048543073877131037,
|
|
"loss": 5.2873,
|
|
"mean_token_accuracy": 0.18320416659116745,
|
|
"num_tokens": 24845474.0,
|
|
"step": 11140
|
|
},
|
|
{
|
|
"entropy": 5.59578857421875,
|
|
"epoch": 1.2516987701465716,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00048541652301930627,
|
|
"loss": 5.3773,
|
|
"mean_token_accuracy": 0.1898516371846199,
|
|
"num_tokens": 24857427.0,
|
|
"step": 11145
|
|
},
|
|
{
|
|
"entropy": 5.592479515075683,
|
|
"epoch": 1.252260347054529,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004854023005675585,
|
|
"loss": 5.3868,
|
|
"mean_token_accuracy": 0.18503573685884475,
|
|
"num_tokens": 24868352.0,
|
|
"step": 11150
|
|
},
|
|
{
|
|
"entropy": 5.593089580535889,
|
|
"epoch": 1.2528219239624867,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004853880714165197,
|
|
"loss": 5.4574,
|
|
"mean_token_accuracy": 0.17789413332939147,
|
|
"num_tokens": 24878499.0,
|
|
"step": 11155
|
|
},
|
|
{
|
|
"entropy": 5.557291555404663,
|
|
"epoch": 1.2533835008704441,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.00048537383556664315,
|
|
"loss": 5.4106,
|
|
"mean_token_accuracy": 0.18766220808029174,
|
|
"num_tokens": 24888290.0,
|
|
"step": 11160
|
|
},
|
|
{
|
|
"entropy": 5.606050968170166,
|
|
"epoch": 1.2539450777784018,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004853595930183822,
|
|
"loss": 5.4775,
|
|
"mean_token_accuracy": 0.1763698562979698,
|
|
"num_tokens": 24900201.0,
|
|
"step": 11165
|
|
},
|
|
{
|
|
"entropy": 5.540960454940796,
|
|
"epoch": 1.2545066546863592,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004853453437721901,
|
|
"loss": 5.3913,
|
|
"mean_token_accuracy": 0.1846339926123619,
|
|
"num_tokens": 24910895.0,
|
|
"step": 11170
|
|
},
|
|
{
|
|
"entropy": 5.543153429031372,
|
|
"epoch": 1.255068231594317,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004853310878285208,
|
|
"loss": 5.3216,
|
|
"mean_token_accuracy": 0.19082948118448256,
|
|
"num_tokens": 24922079.0,
|
|
"step": 11175
|
|
},
|
|
{
|
|
"entropy": 5.720382261276245,
|
|
"epoch": 1.2556298085022743,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.00048531682518782797,
|
|
"loss": 5.6323,
|
|
"mean_token_accuracy": 0.17555736601352692,
|
|
"num_tokens": 24935093.0,
|
|
"step": 11180
|
|
},
|
|
{
|
|
"entropy": 5.695417308807373,
|
|
"epoch": 1.256191385410232,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.00048530255585056594,
|
|
"loss": 5.5707,
|
|
"mean_token_accuracy": 0.17180080711841583,
|
|
"num_tokens": 24947316.0,
|
|
"step": 11185
|
|
},
|
|
{
|
|
"entropy": 5.511158132553101,
|
|
"epoch": 1.2567529623181894,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004852882798171889,
|
|
"loss": 5.2863,
|
|
"mean_token_accuracy": 0.19156352430582047,
|
|
"num_tokens": 24957255.0,
|
|
"step": 11190
|
|
},
|
|
{
|
|
"entropy": 5.510053825378418,
|
|
"epoch": 1.2573145392261469,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004852739970881515,
|
|
"loss": 5.4074,
|
|
"mean_token_accuracy": 0.18630828112363815,
|
|
"num_tokens": 24967646.0,
|
|
"step": 11195
|
|
},
|
|
{
|
|
"entropy": 5.659108686447143,
|
|
"epoch": 1.2578761161341045,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00048525970766390847,
|
|
"loss": 5.5345,
|
|
"mean_token_accuracy": 0.17736627161502838,
|
|
"num_tokens": 24979748.0,
|
|
"step": 11200
|
|
},
|
|
{
|
|
"entropy": 5.711154413223267,
|
|
"epoch": 1.2584376930420622,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004852454115449148,
|
|
"loss": 5.5567,
|
|
"mean_token_accuracy": 0.1786679282784462,
|
|
"num_tokens": 24990727.0,
|
|
"step": 11205
|
|
},
|
|
{
|
|
"entropy": 5.538746738433838,
|
|
"epoch": 1.2589992699500197,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004852311087316257,
|
|
"loss": 5.364,
|
|
"mean_token_accuracy": 0.1842673733830452,
|
|
"num_tokens": 25001912.0,
|
|
"step": 11210
|
|
},
|
|
{
|
|
"entropy": 5.581915807723999,
|
|
"epoch": 1.259560846857977,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004852167992244966,
|
|
"loss": 5.4349,
|
|
"mean_token_accuracy": 0.1812129110097885,
|
|
"num_tokens": 25012952.0,
|
|
"step": 11215
|
|
},
|
|
{
|
|
"entropy": 5.576125526428223,
|
|
"epoch": 1.2601224237659348,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.000485202483023983,
|
|
"loss": 5.3562,
|
|
"mean_token_accuracy": 0.18378958404064177,
|
|
"num_tokens": 25022851.0,
|
|
"step": 11220
|
|
},
|
|
{
|
|
"entropy": 5.520572996139526,
|
|
"epoch": 1.2606840006738924,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.00048518816013054083,
|
|
"loss": 5.3738,
|
|
"mean_token_accuracy": 0.1824027717113495,
|
|
"num_tokens": 25033177.0,
|
|
"step": 11225
|
|
},
|
|
{
|
|
"entropy": 5.541713047027588,
|
|
"epoch": 1.2612455775818499,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00048517383054462617,
|
|
"loss": 5.3387,
|
|
"mean_token_accuracy": 0.18704062849283218,
|
|
"num_tokens": 25044140.0,
|
|
"step": 11230
|
|
},
|
|
{
|
|
"entropy": 5.530812120437622,
|
|
"epoch": 1.2618071544898073,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004851594942666952,
|
|
"loss": 5.3636,
|
|
"mean_token_accuracy": 0.18201253265142442,
|
|
"num_tokens": 25054480.0,
|
|
"step": 11235
|
|
},
|
|
{
|
|
"entropy": 5.585394048690796,
|
|
"epoch": 1.262368731397765,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00048514515129720445,
|
|
"loss": 5.4568,
|
|
"mean_token_accuracy": 0.17366419583559037,
|
|
"num_tokens": 25065673.0,
|
|
"step": 11240
|
|
},
|
|
{
|
|
"entropy": 5.634736585617065,
|
|
"epoch": 1.2629303083057224,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004851308016366105,
|
|
"loss": 5.4308,
|
|
"mean_token_accuracy": 0.18477717638015748,
|
|
"num_tokens": 25076691.0,
|
|
"step": 11245
|
|
},
|
|
{
|
|
"entropy": 5.619279193878174,
|
|
"epoch": 1.26349188521368,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.00048511644528537043,
|
|
"loss": 5.4084,
|
|
"mean_token_accuracy": 0.18738510608673095,
|
|
"num_tokens": 25087882.0,
|
|
"step": 11250
|
|
},
|
|
{
|
|
"entropy": 5.62109408378601,
|
|
"epoch": 1.2640534621216375,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004851020822439412,
|
|
"loss": 5.5222,
|
|
"mean_token_accuracy": 0.17479465305805206,
|
|
"num_tokens": 25099325.0,
|
|
"step": 11255
|
|
},
|
|
{
|
|
"entropy": 5.484981060028076,
|
|
"epoch": 1.2646150390295952,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.00048508771251278015,
|
|
"loss": 5.3035,
|
|
"mean_token_accuracy": 0.1885041892528534,
|
|
"num_tokens": 25110304.0,
|
|
"step": 11260
|
|
},
|
|
{
|
|
"entropy": 5.5678627490997314,
|
|
"epoch": 1.2651766159375526,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004850733360923449,
|
|
"loss": 5.4497,
|
|
"mean_token_accuracy": 0.18248049467802047,
|
|
"num_tokens": 25121597.0,
|
|
"step": 11265
|
|
},
|
|
{
|
|
"entropy": 5.579066419601441,
|
|
"epoch": 1.2657381928455103,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.0004850589529830931,
|
|
"loss": 5.4294,
|
|
"mean_token_accuracy": 0.17716689109802247,
|
|
"num_tokens": 25132817.0,
|
|
"step": 11270
|
|
},
|
|
{
|
|
"entropy": 5.643011140823364,
|
|
"epoch": 1.2662997697534677,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00048504456318548285,
|
|
"loss": 5.4824,
|
|
"mean_token_accuracy": 0.18197162598371505,
|
|
"num_tokens": 25143740.0,
|
|
"step": 11275
|
|
},
|
|
{
|
|
"entropy": 5.647823524475098,
|
|
"epoch": 1.2668613466614254,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004850301666999722,
|
|
"loss": 5.4238,
|
|
"mean_token_accuracy": 0.18020653128623962,
|
|
"num_tokens": 25155889.0,
|
|
"step": 11280
|
|
},
|
|
{
|
|
"entropy": 5.519939231872558,
|
|
"epoch": 1.2674229235693828,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004850157635270196,
|
|
"loss": 5.5169,
|
|
"mean_token_accuracy": 0.1792319491505623,
|
|
"num_tokens": 25166043.0,
|
|
"step": 11285
|
|
},
|
|
{
|
|
"entropy": 5.558336400985718,
|
|
"epoch": 1.2679845004773402,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004850013536670836,
|
|
"loss": 5.4013,
|
|
"mean_token_accuracy": 0.18788154423236847,
|
|
"num_tokens": 25176906.0,
|
|
"step": 11290
|
|
},
|
|
{
|
|
"entropy": 5.520482540130615,
|
|
"epoch": 1.268546077385298,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004849869371206231,
|
|
"loss": 5.3926,
|
|
"mean_token_accuracy": 0.18359485119581223,
|
|
"num_tokens": 25187803.0,
|
|
"step": 11295
|
|
},
|
|
{
|
|
"entropy": 5.554761219024658,
|
|
"epoch": 1.2691076542932556,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00048497251388809697,
|
|
"loss": 5.344,
|
|
"mean_token_accuracy": 0.1825688436627388,
|
|
"num_tokens": 25199067.0,
|
|
"step": 11300
|
|
},
|
|
{
|
|
"entropy": 5.5986857414245605,
|
|
"epoch": 1.269669231201213,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004849580839699647,
|
|
"loss": 5.4171,
|
|
"mean_token_accuracy": 0.1777142956852913,
|
|
"num_tokens": 25210768.0,
|
|
"step": 11305
|
|
},
|
|
{
|
|
"entropy": 5.627563095092773,
|
|
"epoch": 1.2702308081091704,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00048494364736668554,
|
|
"loss": 5.4782,
|
|
"mean_token_accuracy": 0.1803862363100052,
|
|
"num_tokens": 25221602.0,
|
|
"step": 11310
|
|
},
|
|
{
|
|
"entropy": 5.6025909900665285,
|
|
"epoch": 1.270792385017128,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004849292040787192,
|
|
"loss": 5.4338,
|
|
"mean_token_accuracy": 0.18276409357786177,
|
|
"num_tokens": 25232791.0,
|
|
"step": 11315
|
|
},
|
|
{
|
|
"entropy": 5.598787879943847,
|
|
"epoch": 1.2713539619250858,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004849147541065256,
|
|
"loss": 5.3964,
|
|
"mean_token_accuracy": 0.18757463693618776,
|
|
"num_tokens": 25243962.0,
|
|
"step": 11320
|
|
},
|
|
{
|
|
"entropy": 5.591303873062134,
|
|
"epoch": 1.2719155388330432,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004849002974505649,
|
|
"loss": 5.3985,
|
|
"mean_token_accuracy": 0.1832546666264534,
|
|
"num_tokens": 25254636.0,
|
|
"step": 11325
|
|
},
|
|
{
|
|
"entropy": 5.515753889083863,
|
|
"epoch": 1.2724771157410006,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.00048488583411129723,
|
|
"loss": 5.3738,
|
|
"mean_token_accuracy": 0.1880288988351822,
|
|
"num_tokens": 25265255.0,
|
|
"step": 11330
|
|
},
|
|
{
|
|
"entropy": 5.610970878601075,
|
|
"epoch": 1.2730386926489583,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004848713640891832,
|
|
"loss": 5.5106,
|
|
"mean_token_accuracy": 0.18308686316013337,
|
|
"num_tokens": 25276721.0,
|
|
"step": 11335
|
|
},
|
|
{
|
|
"entropy": 5.599207973480224,
|
|
"epoch": 1.2736002695569157,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004848568873846835,
|
|
"loss": 5.3997,
|
|
"mean_token_accuracy": 0.19108064770698546,
|
|
"num_tokens": 25287451.0,
|
|
"step": 11340
|
|
},
|
|
{
|
|
"entropy": 5.557778167724609,
|
|
"epoch": 1.2741618464648734,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.00048484240399825925,
|
|
"loss": 5.3552,
|
|
"mean_token_accuracy": 0.18809493035078048,
|
|
"num_tokens": 25298609.0,
|
|
"step": 11345
|
|
},
|
|
{
|
|
"entropy": 5.579873132705688,
|
|
"epoch": 1.2747234233728308,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00048482791393037134,
|
|
"loss": 5.4116,
|
|
"mean_token_accuracy": 0.184177727997303,
|
|
"num_tokens": 25310058.0,
|
|
"step": 11350
|
|
},
|
|
{
|
|
"entropy": 5.59803032875061,
|
|
"epoch": 1.2752850002807885,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00048481341718148137,
|
|
"loss": 5.4147,
|
|
"mean_token_accuracy": 0.18216343820095063,
|
|
"num_tokens": 25321249.0,
|
|
"step": 11355
|
|
},
|
|
{
|
|
"entropy": 5.567466831207275,
|
|
"epoch": 1.275846577188746,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00048479891375205074,
|
|
"loss": 5.3734,
|
|
"mean_token_accuracy": 0.1836025670170784,
|
|
"num_tokens": 25332603.0,
|
|
"step": 11360
|
|
},
|
|
{
|
|
"entropy": 5.538301849365235,
|
|
"epoch": 1.2764081540967036,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.00048478440364254136,
|
|
"loss": 5.3926,
|
|
"mean_token_accuracy": 0.19262938499450682,
|
|
"num_tokens": 25344955.0,
|
|
"step": 11365
|
|
},
|
|
{
|
|
"entropy": 5.593557691574096,
|
|
"epoch": 1.276969731004661,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004847698868534152,
|
|
"loss": 5.522,
|
|
"mean_token_accuracy": 0.17380810678005218,
|
|
"num_tokens": 25356125.0,
|
|
"step": 11370
|
|
},
|
|
{
|
|
"entropy": 5.587371444702148,
|
|
"epoch": 1.2775313079126187,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004847553633851345,
|
|
"loss": 5.3496,
|
|
"mean_token_accuracy": 0.1864945501089096,
|
|
"num_tokens": 25366969.0,
|
|
"step": 11375
|
|
},
|
|
{
|
|
"entropy": 5.659316301345825,
|
|
"epoch": 1.2780928848205761,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004847408332381616,
|
|
"loss": 5.4353,
|
|
"mean_token_accuracy": 0.1855549156665802,
|
|
"num_tokens": 25378815.0,
|
|
"step": 11380
|
|
},
|
|
{
|
|
"entropy": 5.514390516281128,
|
|
"epoch": 1.2786544617285336,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.00048472629641295933,
|
|
"loss": 5.3468,
|
|
"mean_token_accuracy": 0.18857791572809218,
|
|
"num_tokens": 25389969.0,
|
|
"step": 11385
|
|
},
|
|
{
|
|
"entropy": 5.539934206008911,
|
|
"epoch": 1.2792160386364912,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004847117529099904,
|
|
"loss": 5.4205,
|
|
"mean_token_accuracy": 0.17841923385858535,
|
|
"num_tokens": 25401443.0,
|
|
"step": 11390
|
|
},
|
|
{
|
|
"entropy": 5.61718053817749,
|
|
"epoch": 1.279777615544449,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.00048469720272971797,
|
|
"loss": 5.4406,
|
|
"mean_token_accuracy": 0.18052399754524232,
|
|
"num_tokens": 25412857.0,
|
|
"step": 11395
|
|
},
|
|
{
|
|
"entropy": 5.517834424972534,
|
|
"epoch": 1.2803391924524063,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004846826458726052,
|
|
"loss": 5.3263,
|
|
"mean_token_accuracy": 0.1841700106859207,
|
|
"num_tokens": 25423804.0,
|
|
"step": 11400
|
|
},
|
|
{
|
|
"entropy": 5.569157838821411,
|
|
"epoch": 1.2809007693603638,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00048466808233911567,
|
|
"loss": 5.4815,
|
|
"mean_token_accuracy": 0.17656506299972535,
|
|
"num_tokens": 25435686.0,
|
|
"step": 11405
|
|
},
|
|
{
|
|
"entropy": 5.654522323608399,
|
|
"epoch": 1.2814623462683215,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00048465351212971313,
|
|
"loss": 5.4205,
|
|
"mean_token_accuracy": 0.1811635062098503,
|
|
"num_tokens": 25446012.0,
|
|
"step": 11410
|
|
},
|
|
{
|
|
"entropy": 5.654188346862793,
|
|
"epoch": 1.2820239231762791,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004846389352448614,
|
|
"loss": 5.4819,
|
|
"mean_token_accuracy": 0.18275005370378494,
|
|
"num_tokens": 25457768.0,
|
|
"step": 11415
|
|
},
|
|
{
|
|
"entropy": 5.60784878730774,
|
|
"epoch": 1.2825855000842366,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004846243516850247,
|
|
"loss": 5.4008,
|
|
"mean_token_accuracy": 0.1821306124329567,
|
|
"num_tokens": 25468706.0,
|
|
"step": 11420
|
|
},
|
|
{
|
|
"entropy": 5.647635555267334,
|
|
"epoch": 1.283147076992194,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004846097614506673,
|
|
"loss": 5.4781,
|
|
"mean_token_accuracy": 0.17850955724716186,
|
|
"num_tokens": 25479446.0,
|
|
"step": 11425
|
|
},
|
|
{
|
|
"entropy": 5.589556455612183,
|
|
"epoch": 1.2837086539001517,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.00048459516454225384,
|
|
"loss": 5.4035,
|
|
"mean_token_accuracy": 0.18292578905820847,
|
|
"num_tokens": 25491090.0,
|
|
"step": 11430
|
|
},
|
|
{
|
|
"entropy": 5.669900703430176,
|
|
"epoch": 1.284270230808109,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.000484580560960249,
|
|
"loss": 5.4949,
|
|
"mean_token_accuracy": 0.18713346719741822,
|
|
"num_tokens": 25502105.0,
|
|
"step": 11435
|
|
},
|
|
{
|
|
"entropy": 5.716572904586792,
|
|
"epoch": 1.2848318077160668,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004845659507051178,
|
|
"loss": 5.5657,
|
|
"mean_token_accuracy": 0.17665825933218002,
|
|
"num_tokens": 25513970.0,
|
|
"step": 11440
|
|
},
|
|
{
|
|
"entropy": 5.581077337265015,
|
|
"epoch": 1.2853933846240242,
|
|
"grad_norm": 2.65625,
|
|
"learning_rate": 0.0004845513337773255,
|
|
"loss": 5.3877,
|
|
"mean_token_accuracy": 0.18205983340740203,
|
|
"num_tokens": 25524508.0,
|
|
"step": 11445
|
|
},
|
|
{
|
|
"entropy": 5.575494241714478,
|
|
"epoch": 1.2859549615319819,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.00048453671017733755,
|
|
"loss": 5.3989,
|
|
"mean_token_accuracy": 0.17941714376211165,
|
|
"num_tokens": 25536006.0,
|
|
"step": 11450
|
|
},
|
|
{
|
|
"entropy": 5.538037443161011,
|
|
"epoch": 1.2865165384399393,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004845220799056194,
|
|
"loss": 5.4167,
|
|
"mean_token_accuracy": 0.17841051369905472,
|
|
"num_tokens": 25545726.0,
|
|
"step": 11455
|
|
},
|
|
{
|
|
"entropy": 5.547820711135865,
|
|
"epoch": 1.287078115347897,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.00048450744296263685,
|
|
"loss": 5.3506,
|
|
"mean_token_accuracy": 0.1820966675877571,
|
|
"num_tokens": 25555914.0,
|
|
"step": 11460
|
|
},
|
|
{
|
|
"entropy": 5.636511039733887,
|
|
"epoch": 1.2876396922558544,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.00048449279934885625,
|
|
"loss": 5.5396,
|
|
"mean_token_accuracy": 0.17541532963514328,
|
|
"num_tokens": 25568021.0,
|
|
"step": 11465
|
|
},
|
|
{
|
|
"entropy": 5.657505226135254,
|
|
"epoch": 1.288201269163812,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004844781490647435,
|
|
"loss": 5.434,
|
|
"mean_token_accuracy": 0.18049876689910888,
|
|
"num_tokens": 25578788.0,
|
|
"step": 11470
|
|
},
|
|
{
|
|
"entropy": 5.582758998870849,
|
|
"epoch": 1.2887628460717695,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.0004844634921107654,
|
|
"loss": 5.4571,
|
|
"mean_token_accuracy": 0.18426980525255204,
|
|
"num_tokens": 25590997.0,
|
|
"step": 11475
|
|
},
|
|
{
|
|
"entropy": 5.624828338623047,
|
|
"epoch": 1.289324422979727,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.00048444882848738835,
|
|
"loss": 5.5133,
|
|
"mean_token_accuracy": 0.17030210494995118,
|
|
"num_tokens": 25602810.0,
|
|
"step": 11480
|
|
},
|
|
{
|
|
"entropy": 5.700673151016235,
|
|
"epoch": 1.2898859998876846,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00048443415819507944,
|
|
"loss": 5.4931,
|
|
"mean_token_accuracy": 0.18021892607212067,
|
|
"num_tokens": 25614251.0,
|
|
"step": 11485
|
|
},
|
|
{
|
|
"entropy": 5.600652503967285,
|
|
"epoch": 1.2904475767956423,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004844194812343057,
|
|
"loss": 5.4952,
|
|
"mean_token_accuracy": 0.18398517966270447,
|
|
"num_tokens": 25626162.0,
|
|
"step": 11490
|
|
},
|
|
{
|
|
"entropy": 5.621218585968018,
|
|
"epoch": 1.2910091537035997,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.0004844047976055344,
|
|
"loss": 5.473,
|
|
"mean_token_accuracy": 0.1821221113204956,
|
|
"num_tokens": 25637598.0,
|
|
"step": 11495
|
|
},
|
|
{
|
|
"entropy": 5.6588897705078125,
|
|
"epoch": 1.2915707306115571,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.00048439010730923313,
|
|
"loss": 5.4176,
|
|
"mean_token_accuracy": 0.18844881355762483,
|
|
"num_tokens": 25648297.0,
|
|
"step": 11500
|
|
},
|
|
{
|
|
"entropy": 5.634639263153076,
|
|
"epoch": 1.2921323075195148,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.00048437541034586964,
|
|
"loss": 5.4856,
|
|
"mean_token_accuracy": 0.17767189294099808,
|
|
"num_tokens": 25660139.0,
|
|
"step": 11505
|
|
},
|
|
{
|
|
"entropy": 5.563700008392334,
|
|
"epoch": 1.2926938844274725,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.00048436070671591195,
|
|
"loss": 5.4008,
|
|
"mean_token_accuracy": 0.18382530957460402,
|
|
"num_tokens": 25671947.0,
|
|
"step": 11510
|
|
},
|
|
{
|
|
"entropy": 5.540437698364258,
|
|
"epoch": 1.29325546133543,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.00048434599641982806,
|
|
"loss": 5.3415,
|
|
"mean_token_accuracy": 0.18799777030944825,
|
|
"num_tokens": 25682059.0,
|
|
"step": 11515
|
|
},
|
|
{
|
|
"entropy": 5.595335960388184,
|
|
"epoch": 1.2938170382433873,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.00048433127945808645,
|
|
"loss": 5.4388,
|
|
"mean_token_accuracy": 0.1800031155347824,
|
|
"num_tokens": 25692792.0,
|
|
"step": 11520
|
|
},
|
|
{
|
|
"entropy": 5.577079010009766,
|
|
"epoch": 1.294378615151345,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004843165558311558,
|
|
"loss": 5.4565,
|
|
"mean_token_accuracy": 0.17733431309461595,
|
|
"num_tokens": 25703253.0,
|
|
"step": 11525
|
|
},
|
|
{
|
|
"entropy": 5.642816686630249,
|
|
"epoch": 1.2949401920593024,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004843018255395048,
|
|
"loss": 5.3965,
|
|
"mean_token_accuracy": 0.1866176277399063,
|
|
"num_tokens": 25714169.0,
|
|
"step": 11530
|
|
},
|
|
{
|
|
"entropy": 5.609458255767822,
|
|
"epoch": 1.29550176896726,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.00048428708858360244,
|
|
"loss": 5.4945,
|
|
"mean_token_accuracy": 0.17917241752147675,
|
|
"num_tokens": 25725827.0,
|
|
"step": 11535
|
|
},
|
|
{
|
|
"entropy": 5.56046314239502,
|
|
"epoch": 1.2960633458752175,
|
|
"grad_norm": 3.4375,
|
|
"learning_rate": 0.00048427234496391816,
|
|
"loss": 5.4327,
|
|
"mean_token_accuracy": 0.18428800702095033,
|
|
"num_tokens": 25737951.0,
|
|
"step": 11540
|
|
},
|
|
{
|
|
"entropy": 5.581019639968872,
|
|
"epoch": 1.2966249227831752,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.00048425759468092113,
|
|
"loss": 5.4824,
|
|
"mean_token_accuracy": 0.17608369290828704,
|
|
"num_tokens": 25749676.0,
|
|
"step": 11545
|
|
},
|
|
{
|
|
"entropy": 5.661048555374146,
|
|
"epoch": 1.2971864996911326,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.0004842428377350811,
|
|
"loss": 5.4637,
|
|
"mean_token_accuracy": 0.18972608149051667,
|
|
"num_tokens": 25760005.0,
|
|
"step": 11550
|
|
},
|
|
{
|
|
"entropy": 5.671072864532471,
|
|
"epoch": 1.2977480765990903,
|
|
"grad_norm": 2.6875,
|
|
"learning_rate": 0.00048422807412686796,
|
|
"loss": 5.5169,
|
|
"mean_token_accuracy": 0.17256719172000884,
|
|
"num_tokens": 25770595.0,
|
|
"step": 11555
|
|
},
|
|
{
|
|
"entropy": 5.661506319046021,
|
|
"epoch": 1.2983096535070477,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004842133038567519,
|
|
"loss": 5.5335,
|
|
"mean_token_accuracy": 0.18202261179685592,
|
|
"num_tokens": 25782301.0,
|
|
"step": 11560
|
|
},
|
|
{
|
|
"entropy": 5.594887542724609,
|
|
"epoch": 1.2988712304150054,
|
|
"grad_norm": 2.765625,
|
|
"learning_rate": 0.000484198526925203,
|
|
"loss": 5.3719,
|
|
"mean_token_accuracy": 0.18578586727380753,
|
|
"num_tokens": 25792904.0,
|
|
"step": 11565
|
|
},
|
|
{
|
|
"entropy": 5.600375318527222,
|
|
"epoch": 1.2994328073229628,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004841837433326919,
|
|
"loss": 5.4983,
|
|
"mean_token_accuracy": 0.17811461091041564,
|
|
"num_tokens": 25804594.0,
|
|
"step": 11570
|
|
},
|
|
{
|
|
"entropy": 5.605722141265869,
|
|
"epoch": 1.2999943842309205,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004841689530796893,
|
|
"loss": 5.3978,
|
|
"mean_token_accuracy": 0.18363674581050873,
|
|
"num_tokens": 25816496.0,
|
|
"step": 11575
|
|
},
|
|
{
|
|
"entropy": 5.576470279693604,
|
|
"epoch": 1.300555961138878,
|
|
"grad_norm": 3.25,
|
|
"learning_rate": 0.0004841541561666661,
|
|
"loss": 5.3506,
|
|
"mean_token_accuracy": 0.18314846009016036,
|
|
"num_tokens": 25827271.0,
|
|
"step": 11580
|
|
},
|
|
{
|
|
"entropy": 5.49079384803772,
|
|
"epoch": 1.3011175380468356,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.00048413935259409343,
|
|
"loss": 5.4112,
|
|
"mean_token_accuracy": 0.17746203988790513,
|
|
"num_tokens": 25837869.0,
|
|
"step": 11585
|
|
},
|
|
{
|
|
"entropy": 5.539881849288941,
|
|
"epoch": 1.301679114954793,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.00048412454236244267,
|
|
"loss": 5.3612,
|
|
"mean_token_accuracy": 0.1847861185669899,
|
|
"num_tokens": 25850244.0,
|
|
"step": 11590
|
|
},
|
|
{
|
|
"entropy": 5.626516580581665,
|
|
"epoch": 1.3022406918627505,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.00048410972547218545,
|
|
"loss": 5.451,
|
|
"mean_token_accuracy": 0.18317297101020813,
|
|
"num_tokens": 25859981.0,
|
|
"step": 11595
|
|
},
|
|
{
|
|
"entropy": 5.539654350280761,
|
|
"epoch": 1.3028022687707081,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.00048409490192379337,
|
|
"loss": 5.3361,
|
|
"mean_token_accuracy": 0.19252536147832872,
|
|
"num_tokens": 25870393.0,
|
|
"step": 11600
|
|
},
|
|
{
|
|
"entropy": 5.587570095062256,
|
|
"epoch": 1.3033638456786658,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004840800717177386,
|
|
"loss": 5.4834,
|
|
"mean_token_accuracy": 0.18229357302188873,
|
|
"num_tokens": 25882517.0,
|
|
"step": 11605
|
|
},
|
|
{
|
|
"entropy": 5.586652374267578,
|
|
"epoch": 1.3039254225866233,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004840652348544931,
|
|
"loss": 5.4173,
|
|
"mean_token_accuracy": 0.1851235270500183,
|
|
"num_tokens": 25893628.0,
|
|
"step": 11610
|
|
},
|
|
{
|
|
"entropy": 5.658670234680176,
|
|
"epoch": 1.3044869994945807,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004840503913345296,
|
|
"loss": 5.4557,
|
|
"mean_token_accuracy": 0.17808904200792314,
|
|
"num_tokens": 25904891.0,
|
|
"step": 11615
|
|
},
|
|
{
|
|
"entropy": 5.6350267887115475,
|
|
"epoch": 1.3050485764025384,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004840355411583205,
|
|
"loss": 5.4281,
|
|
"mean_token_accuracy": 0.17956867814064026,
|
|
"num_tokens": 25914598.0,
|
|
"step": 11620
|
|
},
|
|
{
|
|
"entropy": 5.635906028747558,
|
|
"epoch": 1.3056101533104958,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 0.00048402068432633864,
|
|
"loss": 5.4167,
|
|
"mean_token_accuracy": 0.18526556342840195,
|
|
"num_tokens": 25924412.0,
|
|
"step": 11625
|
|
},
|
|
{
|
|
"entropy": 5.537234210968018,
|
|
"epoch": 1.3061717302184535,
|
|
"grad_norm": 3.171875,
|
|
"learning_rate": 0.0004840058208390572,
|
|
"loss": 5.4194,
|
|
"mean_token_accuracy": 0.17871478348970413,
|
|
"num_tokens": 25935583.0,
|
|
"step": 11630
|
|
},
|
|
{
|
|
"entropy": 5.512251567840576,
|
|
"epoch": 1.306733307126411,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004839909506969494,
|
|
"loss": 5.338,
|
|
"mean_token_accuracy": 0.18482319563627242,
|
|
"num_tokens": 25946949.0,
|
|
"step": 11635
|
|
},
|
|
{
|
|
"entropy": 5.515132904052734,
|
|
"epoch": 1.3072948840343686,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004839760739004886,
|
|
"loss": 5.3429,
|
|
"mean_token_accuracy": 0.18653517663478852,
|
|
"num_tokens": 25957070.0,
|
|
"step": 11640
|
|
},
|
|
{
|
|
"entropy": 5.604286241531372,
|
|
"epoch": 1.307856460942326,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.00048396119045014853,
|
|
"loss": 5.4657,
|
|
"mean_token_accuracy": 0.1766536921262741,
|
|
"num_tokens": 25968375.0,
|
|
"step": 11645
|
|
},
|
|
{
|
|
"entropy": 5.687704467773438,
|
|
"epoch": 1.3084180378502837,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004839463003464032,
|
|
"loss": 5.4541,
|
|
"mean_token_accuracy": 0.18244671523571016,
|
|
"num_tokens": 25979690.0,
|
|
"step": 11650
|
|
},
|
|
{
|
|
"entropy": 5.653723621368409,
|
|
"epoch": 1.308979614758241,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004839314035897265,
|
|
"loss": 5.5593,
|
|
"mean_token_accuracy": 0.1719047576189041,
|
|
"num_tokens": 25990660.0,
|
|
"step": 11655
|
|
},
|
|
{
|
|
"entropy": 5.43707971572876,
|
|
"epoch": 1.3095411916661988,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.000483916500180593,
|
|
"loss": 5.3169,
|
|
"mean_token_accuracy": 0.18557359874248505,
|
|
"num_tokens": 26002158.0,
|
|
"step": 11660
|
|
},
|
|
{
|
|
"entropy": 5.6041358470916744,
|
|
"epoch": 1.3101027685741562,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.00048390159011947706,
|
|
"loss": 5.3403,
|
|
"mean_token_accuracy": 0.18800112903118132,
|
|
"num_tokens": 26011890.0,
|
|
"step": 11665
|
|
},
|
|
{
|
|
"entropy": 5.591357707977295,
|
|
"epoch": 1.3106643454821139,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004838866734068535,
|
|
"loss": 5.4562,
|
|
"mean_token_accuracy": 0.17782177180051803,
|
|
"num_tokens": 26023548.0,
|
|
"step": 11670
|
|
},
|
|
{
|
|
"entropy": 5.581407451629639,
|
|
"epoch": 1.3112259223900713,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.00048387175004319723,
|
|
"loss": 5.4621,
|
|
"mean_token_accuracy": 0.18198118060827256,
|
|
"num_tokens": 26034178.0,
|
|
"step": 11675
|
|
},
|
|
{
|
|
"entropy": 5.562361097335815,
|
|
"epoch": 1.311787499298029,
|
|
"grad_norm": 3.0,
|
|
"learning_rate": 0.0004838568200289834,
|
|
"loss": 5.3856,
|
|
"mean_token_accuracy": 0.18595320582389832,
|
|
"num_tokens": 26045068.0,
|
|
"step": 11680
|
|
},
|
|
{
|
|
"entropy": 5.599232959747314,
|
|
"epoch": 1.3123490762059864,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004838418833646875,
|
|
"loss": 5.5081,
|
|
"mean_token_accuracy": 0.17779320776462554,
|
|
"num_tokens": 26057400.0,
|
|
"step": 11685
|
|
},
|
|
{
|
|
"entropy": 5.562916946411133,
|
|
"epoch": 1.3129106531139438,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.00048382694005078485,
|
|
"loss": 5.4286,
|
|
"mean_token_accuracy": 0.1821630820631981,
|
|
"num_tokens": 26068981.0,
|
|
"step": 11690
|
|
},
|
|
{
|
|
"entropy": 5.64361310005188,
|
|
"epoch": 1.3134722300219015,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.00048381199008775165,
|
|
"loss": 5.3865,
|
|
"mean_token_accuracy": 0.18470406383275986,
|
|
"num_tokens": 26078902.0,
|
|
"step": 11695
|
|
},
|
|
{
|
|
"entropy": 5.46088490486145,
|
|
"epoch": 1.3140338069298592,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004837970334760635,
|
|
"loss": 5.2692,
|
|
"mean_token_accuracy": 0.19096807092428209,
|
|
"num_tokens": 26089891.0,
|
|
"step": 11700
|
|
},
|
|
{
|
|
"entropy": 5.485475730895996,
|
|
"epoch": 1.3145953838378166,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.000483782070216197,
|
|
"loss": 5.3797,
|
|
"mean_token_accuracy": 0.18987158834934234,
|
|
"num_tokens": 26100701.0,
|
|
"step": 11705
|
|
},
|
|
{
|
|
"entropy": 5.52687087059021,
|
|
"epoch": 1.315156960745774,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004837671003086283,
|
|
"loss": 5.3908,
|
|
"mean_token_accuracy": 0.18701540678739548,
|
|
"num_tokens": 26110496.0,
|
|
"step": 11710
|
|
},
|
|
{
|
|
"entropy": 5.523316240310669,
|
|
"epoch": 1.3157185376537317,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004837521237538342,
|
|
"loss": 5.3529,
|
|
"mean_token_accuracy": 0.18877830654382705,
|
|
"num_tokens": 26120580.0,
|
|
"step": 11715
|
|
},
|
|
{
|
|
"entropy": 5.506276321411133,
|
|
"epoch": 1.3162801145616891,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004837371405522915,
|
|
"loss": 5.4204,
|
|
"mean_token_accuracy": 0.18576560616493226,
|
|
"num_tokens": 26130936.0,
|
|
"step": 11720
|
|
},
|
|
{
|
|
"entropy": 5.65242748260498,
|
|
"epoch": 1.3168416914696468,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.00048372215070447734,
|
|
"loss": 5.4132,
|
|
"mean_token_accuracy": 0.18514294624328614,
|
|
"num_tokens": 26143027.0,
|
|
"step": 11725
|
|
},
|
|
{
|
|
"entropy": 5.596934413909912,
|
|
"epoch": 1.3174032683776042,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.00048370715421086884,
|
|
"loss": 5.3053,
|
|
"mean_token_accuracy": 0.18550607711076736,
|
|
"num_tokens": 26152874.0,
|
|
"step": 11730
|
|
},
|
|
{
|
|
"entropy": 5.498037242889405,
|
|
"epoch": 1.317964845285562,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004836921510719438,
|
|
"loss": 5.2872,
|
|
"mean_token_accuracy": 0.18218962997198104,
|
|
"num_tokens": 26162781.0,
|
|
"step": 11735
|
|
},
|
|
{
|
|
"entropy": 5.490464353561402,
|
|
"epoch": 1.3185264221935193,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004836771412881795,
|
|
"loss": 5.3809,
|
|
"mean_token_accuracy": 0.187151300907135,
|
|
"num_tokens": 26173498.0,
|
|
"step": 11740
|
|
},
|
|
{
|
|
"entropy": 5.562977123260498,
|
|
"epoch": 1.319087999101477,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004836621248600542,
|
|
"loss": 5.3842,
|
|
"mean_token_accuracy": 0.18796051293611526,
|
|
"num_tokens": 26185090.0,
|
|
"step": 11745
|
|
},
|
|
{
|
|
"entropy": 5.658957481384277,
|
|
"epoch": 1.3196495760094344,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004836471017880459,
|
|
"loss": 5.6025,
|
|
"mean_token_accuracy": 0.1729616180062294,
|
|
"num_tokens": 26197048.0,
|
|
"step": 11750
|
|
},
|
|
{
|
|
"entropy": 5.568052053451538,
|
|
"epoch": 1.320211152917392,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004836320720726329,
|
|
"loss": 5.4367,
|
|
"mean_token_accuracy": 0.18527210354804993,
|
|
"num_tokens": 26208037.0,
|
|
"step": 11755
|
|
},
|
|
{
|
|
"entropy": 5.6516584873199465,
|
|
"epoch": 1.3207727298253495,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004836170357142939,
|
|
"loss": 5.4554,
|
|
"mean_token_accuracy": 0.18128653913736342,
|
|
"num_tokens": 26219345.0,
|
|
"step": 11760
|
|
},
|
|
{
|
|
"entropy": 5.66205587387085,
|
|
"epoch": 1.3213343067333072,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.0004836019927135076,
|
|
"loss": 5.4583,
|
|
"mean_token_accuracy": 0.1837382659316063,
|
|
"num_tokens": 26230299.0,
|
|
"step": 11765
|
|
},
|
|
{
|
|
"entropy": 5.693551540374756,
|
|
"epoch": 1.3218958836412646,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004835869430707529,
|
|
"loss": 5.5218,
|
|
"mean_token_accuracy": 0.17959502041339875,
|
|
"num_tokens": 26241427.0,
|
|
"step": 11770
|
|
},
|
|
{
|
|
"entropy": 5.5806210994720455,
|
|
"epoch": 1.3224574605492223,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.00048357188678650905,
|
|
"loss": 5.4826,
|
|
"mean_token_accuracy": 0.18851787298917771,
|
|
"num_tokens": 26252051.0,
|
|
"step": 11775
|
|
},
|
|
{
|
|
"entropy": 5.569334602355957,
|
|
"epoch": 1.3230190374571797,
|
|
"grad_norm": 4.59375,
|
|
"learning_rate": 0.0004835568238612553,
|
|
"loss": 5.4019,
|
|
"mean_token_accuracy": 0.17965350449085235,
|
|
"num_tokens": 26263640.0,
|
|
"step": 11780
|
|
},
|
|
{
|
|
"entropy": 5.71147723197937,
|
|
"epoch": 1.3235806143651372,
|
|
"grad_norm": 2.875,
|
|
"learning_rate": 0.00048354175429547155,
|
|
"loss": 5.5939,
|
|
"mean_token_accuracy": 0.1769303485751152,
|
|
"num_tokens": 26274996.0,
|
|
"step": 11785
|
|
},
|
|
{
|
|
"entropy": 5.760419845581055,
|
|
"epoch": 1.3241421912730948,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.0004835266780896374,
|
|
"loss": 5.5576,
|
|
"mean_token_accuracy": 0.17181482911109924,
|
|
"num_tokens": 26287859.0,
|
|
"step": 11790
|
|
},
|
|
{
|
|
"entropy": 5.569895267486572,
|
|
"epoch": 1.3247037681810525,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004835115952442329,
|
|
"loss": 5.3491,
|
|
"mean_token_accuracy": 0.18307339251041413,
|
|
"num_tokens": 26298302.0,
|
|
"step": 11795
|
|
},
|
|
{
|
|
"entropy": 5.614945650100708,
|
|
"epoch": 1.32526534508901,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.00048349650575973843,
|
|
"loss": 5.4486,
|
|
"mean_token_accuracy": 0.1809273272752762,
|
|
"num_tokens": 26310755.0,
|
|
"step": 11800
|
|
},
|
|
{
|
|
"entropy": 5.631687355041504,
|
|
"epoch": 1.3258269219969674,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.00048348140963663436,
|
|
"loss": 5.542,
|
|
"mean_token_accuracy": 0.17422901540994645,
|
|
"num_tokens": 26322041.0,
|
|
"step": 11805
|
|
},
|
|
{
|
|
"entropy": 5.630207347869873,
|
|
"epoch": 1.326388498904925,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004834663068754012,
|
|
"loss": 5.4791,
|
|
"mean_token_accuracy": 0.18391888439655305,
|
|
"num_tokens": 26334028.0,
|
|
"step": 11810
|
|
},
|
|
{
|
|
"entropy": 5.544382095336914,
|
|
"epoch": 1.3269500758128827,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.0004834511974765202,
|
|
"loss": 5.3836,
|
|
"mean_token_accuracy": 0.18592217117547988,
|
|
"num_tokens": 26344834.0,
|
|
"step": 11815
|
|
},
|
|
{
|
|
"entropy": 5.559587526321411,
|
|
"epoch": 1.3275116527208402,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.00048343608144047194,
|
|
"loss": 5.394,
|
|
"mean_token_accuracy": 0.18360603153705596,
|
|
"num_tokens": 26354896.0,
|
|
"step": 11820
|
|
},
|
|
{
|
|
"entropy": 5.644568014144897,
|
|
"epoch": 1.3280732296287976,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.00048342095876773825,
|
|
"loss": 5.4762,
|
|
"mean_token_accuracy": 0.18239444643259048,
|
|
"num_tokens": 26367487.0,
|
|
"step": 11825
|
|
},
|
|
{
|
|
"entropy": 5.630744314193725,
|
|
"epoch": 1.3286348065367553,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004834058294588003,
|
|
"loss": 5.479,
|
|
"mean_token_accuracy": 0.17969143390655518,
|
|
"num_tokens": 26379384.0,
|
|
"step": 11830
|
|
},
|
|
{
|
|
"entropy": 5.6427594184875485,
|
|
"epoch": 1.3291963834447127,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.00048339069351413993,
|
|
"loss": 5.429,
|
|
"mean_token_accuracy": 0.18330038636922835,
|
|
"num_tokens": 26390268.0,
|
|
"step": 11835
|
|
},
|
|
{
|
|
"entropy": 5.535543394088745,
|
|
"epoch": 1.3297579603526704,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.000483375550934239,
|
|
"loss": 5.5305,
|
|
"mean_token_accuracy": 0.17828609347343444,
|
|
"num_tokens": 26401348.0,
|
|
"step": 11840
|
|
},
|
|
{
|
|
"entropy": 5.5631701946258545,
|
|
"epoch": 1.3303195372606278,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004833604017195798,
|
|
"loss": 5.3935,
|
|
"mean_token_accuracy": 0.1797025293111801,
|
|
"num_tokens": 26411955.0,
|
|
"step": 11845
|
|
},
|
|
{
|
|
"entropy": 5.5863142013549805,
|
|
"epoch": 1.3308811141685855,
|
|
"grad_norm": 2.703125,
|
|
"learning_rate": 0.0004833452458706445,
|
|
"loss": 5.3328,
|
|
"mean_token_accuracy": 0.1938882663846016,
|
|
"num_tokens": 26422200.0,
|
|
"step": 11850
|
|
},
|
|
{
|
|
"entropy": 5.592746877670288,
|
|
"epoch": 1.331442691076543,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.0004833300833879159,
|
|
"loss": 5.3499,
|
|
"mean_token_accuracy": 0.18699274361133575,
|
|
"num_tokens": 26433292.0,
|
|
"step": 11855
|
|
},
|
|
{
|
|
"entropy": 5.554074811935425,
|
|
"epoch": 1.3320042679845006,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004833149142718765,
|
|
"loss": 5.3882,
|
|
"mean_token_accuracy": 0.1879195973277092,
|
|
"num_tokens": 26444003.0,
|
|
"step": 11860
|
|
},
|
|
{
|
|
"entropy": 5.555953025817871,
|
|
"epoch": 1.332565844892458,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004832997385230096,
|
|
"loss": 5.3987,
|
|
"mean_token_accuracy": 0.18996921330690383,
|
|
"num_tokens": 26455743.0,
|
|
"step": 11865
|
|
},
|
|
{
|
|
"entropy": 5.543155670166016,
|
|
"epoch": 1.3331274218004157,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.0004832845561417981,
|
|
"loss": 5.3767,
|
|
"mean_token_accuracy": 0.18165364116430283,
|
|
"num_tokens": 26466032.0,
|
|
"step": 11870
|
|
},
|
|
{
|
|
"entropy": 5.601006317138672,
|
|
"epoch": 1.333688998708373,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004832693671287256,
|
|
"loss": 5.401,
|
|
"mean_token_accuracy": 0.1820191591978073,
|
|
"num_tokens": 26477660.0,
|
|
"step": 11875
|
|
},
|
|
{
|
|
"entropy": 5.540877723693848,
|
|
"epoch": 1.3342505756163305,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004832541714842757,
|
|
"loss": 5.3848,
|
|
"mean_token_accuracy": 0.18291471302509307,
|
|
"num_tokens": 26488778.0,
|
|
"step": 11880
|
|
},
|
|
{
|
|
"entropy": 5.655148315429687,
|
|
"epoch": 1.3348121525242882,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004832389692089321,
|
|
"loss": 5.4454,
|
|
"mean_token_accuracy": 0.1753410890698433,
|
|
"num_tokens": 26500771.0,
|
|
"step": 11885
|
|
},
|
|
{
|
|
"entropy": 5.571166133880615,
|
|
"epoch": 1.3353737294322459,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.00048322376030317905,
|
|
"loss": 5.3715,
|
|
"mean_token_accuracy": 0.1887003391981125,
|
|
"num_tokens": 26511786.0,
|
|
"step": 11890
|
|
},
|
|
{
|
|
"entropy": 5.556343078613281,
|
|
"epoch": 1.3359353063402033,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004832085447675007,
|
|
"loss": 5.4463,
|
|
"mean_token_accuracy": 0.18483859449625015,
|
|
"num_tokens": 26522273.0,
|
|
"step": 11895
|
|
},
|
|
{
|
|
"entropy": 5.75804123878479,
|
|
"epoch": 1.3364968832481607,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.00048319332260238153,
|
|
"loss": 5.7205,
|
|
"mean_token_accuracy": 0.16999229341745375,
|
|
"num_tokens": 26536619.0,
|
|
"step": 11900
|
|
},
|
|
{
|
|
"entropy": 5.735089111328125,
|
|
"epoch": 1.3370584601561184,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.00048317809380830624,
|
|
"loss": 5.4625,
|
|
"mean_token_accuracy": 0.17418597191572188,
|
|
"num_tokens": 26547807.0,
|
|
"step": 11905
|
|
},
|
|
{
|
|
"entropy": 5.627963924407959,
|
|
"epoch": 1.337620037064076,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004831628583857597,
|
|
"loss": 5.4546,
|
|
"mean_token_accuracy": 0.1782565787434578,
|
|
"num_tokens": 26558924.0,
|
|
"step": 11910
|
|
},
|
|
{
|
|
"entropy": 5.571965122222901,
|
|
"epoch": 1.3381816139720335,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.00048314761633522696,
|
|
"loss": 5.4068,
|
|
"mean_token_accuracy": 0.18269326090812682,
|
|
"num_tokens": 26570123.0,
|
|
"step": 11915
|
|
},
|
|
{
|
|
"entropy": 5.65542631149292,
|
|
"epoch": 1.338743190879991,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004831323676571934,
|
|
"loss": 5.4918,
|
|
"mean_token_accuracy": 0.18208651542663573,
|
|
"num_tokens": 26582841.0,
|
|
"step": 11920
|
|
},
|
|
{
|
|
"entropy": 5.607376909255981,
|
|
"epoch": 1.3393047677879486,
|
|
"grad_norm": 3.15625,
|
|
"learning_rate": 0.0004831171123521446,
|
|
"loss": 5.3852,
|
|
"mean_token_accuracy": 0.18670095056295394,
|
|
"num_tokens": 26594397.0,
|
|
"step": 11925
|
|
},
|
|
{
|
|
"entropy": 5.5590019702911375,
|
|
"epoch": 1.339866344695906,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004831018504205662,
|
|
"loss": 5.4673,
|
|
"mean_token_accuracy": 0.17675997614860534,
|
|
"num_tokens": 26605055.0,
|
|
"step": 11930
|
|
},
|
|
{
|
|
"entropy": 5.593759393692016,
|
|
"epoch": 1.3404279216038637,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00048308658186294414,
|
|
"loss": 5.514,
|
|
"mean_token_accuracy": 0.1753700017929077,
|
|
"num_tokens": 26616110.0,
|
|
"step": 11935
|
|
},
|
|
{
|
|
"entropy": 5.627068376541137,
|
|
"epoch": 1.3409894985118211,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.0004830713066797646,
|
|
"loss": 5.4105,
|
|
"mean_token_accuracy": 0.18769517093896865,
|
|
"num_tokens": 26627196.0,
|
|
"step": 11940
|
|
},
|
|
{
|
|
"entropy": 5.584965181350708,
|
|
"epoch": 1.3415510754197788,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.00048305602487151396,
|
|
"loss": 5.4821,
|
|
"mean_token_accuracy": 0.18012309074401855,
|
|
"num_tokens": 26637962.0,
|
|
"step": 11945
|
|
},
|
|
{
|
|
"entropy": 5.51606125831604,
|
|
"epoch": 1.3421126523277362,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.0004830407364386789,
|
|
"loss": 5.3846,
|
|
"mean_token_accuracy": 0.18352729231119155,
|
|
"num_tokens": 26649366.0,
|
|
"step": 11950
|
|
},
|
|
{
|
|
"entropy": 5.768883609771729,
|
|
"epoch": 1.342674229235694,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.000483025441381746,
|
|
"loss": 5.6188,
|
|
"mean_token_accuracy": 0.17198943495750427,
|
|
"num_tokens": 26662455.0,
|
|
"step": 11955
|
|
},
|
|
{
|
|
"entropy": 5.583873987197876,
|
|
"epoch": 1.3432358061436513,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00048301013970120235,
|
|
"loss": 5.4889,
|
|
"mean_token_accuracy": 0.18145816326141356,
|
|
"num_tokens": 26673467.0,
|
|
"step": 11960
|
|
},
|
|
{
|
|
"entropy": 5.538484048843384,
|
|
"epoch": 1.343797383051609,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.00048299483139753517,
|
|
"loss": 5.3531,
|
|
"mean_token_accuracy": 0.1864481821656227,
|
|
"num_tokens": 26684803.0,
|
|
"step": 11965
|
|
},
|
|
{
|
|
"entropy": 5.667122411727905,
|
|
"epoch": 1.3443589599595664,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004829795164712319,
|
|
"loss": 5.4569,
|
|
"mean_token_accuracy": 0.1781364396214485,
|
|
"num_tokens": 26696886.0,
|
|
"step": 11970
|
|
},
|
|
{
|
|
"entropy": 5.429471158981324,
|
|
"epoch": 1.3449205368675239,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.00048296419492278023,
|
|
"loss": 5.2782,
|
|
"mean_token_accuracy": 0.1929266095161438,
|
|
"num_tokens": 26708489.0,
|
|
"step": 11975
|
|
},
|
|
{
|
|
"entropy": 5.556291913986206,
|
|
"epoch": 1.3454821137754815,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004829488667526679,
|
|
"loss": 5.4411,
|
|
"mean_token_accuracy": 0.18234337568283082,
|
|
"num_tokens": 26719599.0,
|
|
"step": 11980
|
|
},
|
|
{
|
|
"entropy": 5.543146467208862,
|
|
"epoch": 1.3460436906834392,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.00048293353196138294,
|
|
"loss": 5.3606,
|
|
"mean_token_accuracy": 0.18849279433488847,
|
|
"num_tokens": 26730359.0,
|
|
"step": 11985
|
|
},
|
|
{
|
|
"entropy": 5.640635585784912,
|
|
"epoch": 1.3466052675913966,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.00048291819054941375,
|
|
"loss": 5.5639,
|
|
"mean_token_accuracy": 0.17377166748046874,
|
|
"num_tokens": 26742363.0,
|
|
"step": 11990
|
|
},
|
|
{
|
|
"entropy": 5.627382469177246,
|
|
"epoch": 1.347166844499354,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004829028425172487,
|
|
"loss": 5.5331,
|
|
"mean_token_accuracy": 0.17799247652292252,
|
|
"num_tokens": 26754058.0,
|
|
"step": 11995
|
|
},
|
|
{
|
|
"entropy": 5.582808637619019,
|
|
"epoch": 1.3477284214073117,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.00048288748786537656,
|
|
"loss": 5.4443,
|
|
"mean_token_accuracy": 0.17711522728204726,
|
|
"num_tokens": 26765602.0,
|
|
"step": 12000
|
|
},
|
|
{
|
|
"epoch": 1.3477284214073117,
|
|
"eval_entropy": 5.474635892901987,
|
|
"eval_loss": 5.5089006423950195,
|
|
"eval_mean_token_accuracy": 0.18679746414583032,
|
|
"eval_num_tokens": 26765602.0,
|
|
"eval_runtime": 23.9588,
|
|
"eval_samples_per_second": 1294.432,
|
|
"eval_steps_per_second": 161.82,
|
|
"step": 12000
|
|
},
|
|
{
|
|
"entropy": 5.619168281555176,
|
|
"epoch": 1.3482899983152694,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004828721265942861,
|
|
"loss": 5.3781,
|
|
"mean_token_accuracy": 0.18612894862890245,
|
|
"num_tokens": 26776867.0,
|
|
"step": 12005
|
|
},
|
|
{
|
|
"entropy": 5.525385332107544,
|
|
"epoch": 1.3488515752232269,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.00048285675870446653,
|
|
"loss": 5.3686,
|
|
"mean_token_accuracy": 0.18679242134094237,
|
|
"num_tokens": 26786383.0,
|
|
"step": 12010
|
|
},
|
|
{
|
|
"entropy": 5.659783935546875,
|
|
"epoch": 1.3494131521311843,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00048284138419640724,
|
|
"loss": 5.5115,
|
|
"mean_token_accuracy": 0.1743268057703972,
|
|
"num_tokens": 26797647.0,
|
|
"step": 12015
|
|
},
|
|
{
|
|
"entropy": 5.650413465499878,
|
|
"epoch": 1.349974729039142,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004828260030705976,
|
|
"loss": 5.364,
|
|
"mean_token_accuracy": 0.1815338224172592,
|
|
"num_tokens": 26808674.0,
|
|
"step": 12020
|
|
},
|
|
{
|
|
"entropy": 5.514647388458252,
|
|
"epoch": 1.3505363059470994,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00048281061532752734,
|
|
"loss": 5.2714,
|
|
"mean_token_accuracy": 0.1890656590461731,
|
|
"num_tokens": 26820858.0,
|
|
"step": 12025
|
|
},
|
|
{
|
|
"entropy": 5.549510478973389,
|
|
"epoch": 1.351097882855057,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004827952209676866,
|
|
"loss": 5.3452,
|
|
"mean_token_accuracy": 0.18801091462373734,
|
|
"num_tokens": 26831432.0,
|
|
"step": 12030
|
|
},
|
|
{
|
|
"entropy": 5.600547218322754,
|
|
"epoch": 1.3516594597630145,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.00048277981999156534,
|
|
"loss": 5.4652,
|
|
"mean_token_accuracy": 0.18412834256887436,
|
|
"num_tokens": 26843240.0,
|
|
"step": 12035
|
|
},
|
|
{
|
|
"entropy": 5.650083303451538,
|
|
"epoch": 1.3522210366709722,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00048276441239965414,
|
|
"loss": 5.4694,
|
|
"mean_token_accuracy": 0.18023325204849244,
|
|
"num_tokens": 26853556.0,
|
|
"step": 12040
|
|
},
|
|
{
|
|
"entropy": 5.595720195770264,
|
|
"epoch": 1.3527826135789296,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004827489981924434,
|
|
"loss": 5.4097,
|
|
"mean_token_accuracy": 0.18325205147266388,
|
|
"num_tokens": 26866040.0,
|
|
"step": 12045
|
|
},
|
|
{
|
|
"entropy": 5.494285726547242,
|
|
"epoch": 1.3533441904868873,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.00048273357737042393,
|
|
"loss": 5.263,
|
|
"mean_token_accuracy": 0.18558333963155746,
|
|
"num_tokens": 26876796.0,
|
|
"step": 12050
|
|
},
|
|
{
|
|
"entropy": 5.495880937576294,
|
|
"epoch": 1.3539057673948447,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00048271814993408694,
|
|
"loss": 5.4558,
|
|
"mean_token_accuracy": 0.17964325249195098,
|
|
"num_tokens": 26888081.0,
|
|
"step": 12055
|
|
},
|
|
{
|
|
"entropy": 5.584234189987183,
|
|
"epoch": 1.3544673443028024,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004827027158839233,
|
|
"loss": 5.422,
|
|
"mean_token_accuracy": 0.17885801792144776,
|
|
"num_tokens": 26898511.0,
|
|
"step": 12060
|
|
},
|
|
{
|
|
"entropy": 5.638433265686035,
|
|
"epoch": 1.3550289212107598,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004826872752204248,
|
|
"loss": 5.4271,
|
|
"mean_token_accuracy": 0.18308894336223602,
|
|
"num_tokens": 26909525.0,
|
|
"step": 12065
|
|
},
|
|
{
|
|
"entropy": 5.599750947952271,
|
|
"epoch": 1.3555904981187172,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.00048267182794408276,
|
|
"loss": 5.4611,
|
|
"mean_token_accuracy": 0.18938700258731841,
|
|
"num_tokens": 26920267.0,
|
|
"step": 12070
|
|
},
|
|
{
|
|
"entropy": 5.596344470977783,
|
|
"epoch": 1.356152075026675,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004826563740553893,
|
|
"loss": 5.4296,
|
|
"mean_token_accuracy": 0.18646478950977324,
|
|
"num_tokens": 26931351.0,
|
|
"step": 12075
|
|
},
|
|
{
|
|
"entropy": 5.497289943695068,
|
|
"epoch": 1.3567136519346326,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004826409135548363,
|
|
"loss": 5.3661,
|
|
"mean_token_accuracy": 0.17962656319141387,
|
|
"num_tokens": 26942235.0,
|
|
"step": 12080
|
|
},
|
|
{
|
|
"entropy": 5.645137453079224,
|
|
"epoch": 1.35727522884259,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004826254464429161,
|
|
"loss": 5.5326,
|
|
"mean_token_accuracy": 0.1759307160973549,
|
|
"num_tokens": 26953375.0,
|
|
"step": 12085
|
|
},
|
|
{
|
|
"entropy": 5.621385192871093,
|
|
"epoch": 1.3578368057505474,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.00048260997272012114,
|
|
"loss": 5.4295,
|
|
"mean_token_accuracy": 0.18265892565250397,
|
|
"num_tokens": 26965081.0,
|
|
"step": 12090
|
|
},
|
|
{
|
|
"entropy": 5.610290002822876,
|
|
"epoch": 1.358398382658505,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004825944923869441,
|
|
"loss": 5.4589,
|
|
"mean_token_accuracy": 0.1742696687579155,
|
|
"num_tokens": 26975428.0,
|
|
"step": 12095
|
|
},
|
|
{
|
|
"entropy": 5.584657144546509,
|
|
"epoch": 1.3589599595664628,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.00048257900544387795,
|
|
"loss": 5.3793,
|
|
"mean_token_accuracy": 0.18407012820243834,
|
|
"num_tokens": 26987040.0,
|
|
"step": 12100
|
|
},
|
|
{
|
|
"entropy": 5.59127950668335,
|
|
"epoch": 1.3595215364744202,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00048256351189141574,
|
|
"loss": 5.4826,
|
|
"mean_token_accuracy": 0.17611093670129777,
|
|
"num_tokens": 26997931.0,
|
|
"step": 12105
|
|
},
|
|
{
|
|
"entropy": 5.63390531539917,
|
|
"epoch": 1.3600831133823776,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004825480117300508,
|
|
"loss": 5.3812,
|
|
"mean_token_accuracy": 0.1833555981516838,
|
|
"num_tokens": 27009528.0,
|
|
"step": 12110
|
|
},
|
|
{
|
|
"entropy": 5.441861200332641,
|
|
"epoch": 1.3606446902903353,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.00048253250496027675,
|
|
"loss": 5.2788,
|
|
"mean_token_accuracy": 0.19329649358987808,
|
|
"num_tokens": 27020161.0,
|
|
"step": 12115
|
|
},
|
|
{
|
|
"entropy": 5.574842214584351,
|
|
"epoch": 1.3612062671982927,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.00048251699158258714,
|
|
"loss": 5.4026,
|
|
"mean_token_accuracy": 0.18437140434980392,
|
|
"num_tokens": 27032246.0,
|
|
"step": 12120
|
|
},
|
|
{
|
|
"entropy": 5.6189673900604244,
|
|
"epoch": 1.3617678441062504,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004825014715974761,
|
|
"loss": 5.4676,
|
|
"mean_token_accuracy": 0.18131349235773087,
|
|
"num_tokens": 27042903.0,
|
|
"step": 12125
|
|
},
|
|
{
|
|
"entropy": 5.668713092803955,
|
|
"epoch": 1.3623294210142078,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.00048248594500543767,
|
|
"loss": 5.5788,
|
|
"mean_token_accuracy": 0.17454876899719238,
|
|
"num_tokens": 27054854.0,
|
|
"step": 12130
|
|
},
|
|
{
|
|
"entropy": 5.61062593460083,
|
|
"epoch": 1.3628909979221655,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00048247041180696633,
|
|
"loss": 5.401,
|
|
"mean_token_accuracy": 0.19103506803512574,
|
|
"num_tokens": 27065021.0,
|
|
"step": 12135
|
|
},
|
|
{
|
|
"entropy": 5.56108980178833,
|
|
"epoch": 1.363452574830123,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.0004824548720025566,
|
|
"loss": 5.4468,
|
|
"mean_token_accuracy": 0.17915666699409485,
|
|
"num_tokens": 27075717.0,
|
|
"step": 12140
|
|
},
|
|
{
|
|
"entropy": 5.608147001266479,
|
|
"epoch": 1.3640141517380806,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004824393255927033,
|
|
"loss": 5.5546,
|
|
"mean_token_accuracy": 0.1782521888613701,
|
|
"num_tokens": 27087310.0,
|
|
"step": 12145
|
|
},
|
|
{
|
|
"entropy": 5.69928469657898,
|
|
"epoch": 1.364575728646038,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00048242377257790145,
|
|
"loss": 5.5615,
|
|
"mean_token_accuracy": 0.1710447758436203,
|
|
"num_tokens": 27100218.0,
|
|
"step": 12150
|
|
},
|
|
{
|
|
"entropy": 5.532822942733764,
|
|
"epoch": 1.3651373055539957,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00048240821295864614,
|
|
"loss": 5.3169,
|
|
"mean_token_accuracy": 0.18881547152996064,
|
|
"num_tokens": 27111548.0,
|
|
"step": 12155
|
|
},
|
|
{
|
|
"entropy": 5.564854431152344,
|
|
"epoch": 1.3656988824619531,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.000482392646735433,
|
|
"loss": 5.4586,
|
|
"mean_token_accuracy": 0.18205681890249253,
|
|
"num_tokens": 27123434.0,
|
|
"step": 12160
|
|
},
|
|
{
|
|
"entropy": 5.627358484268188,
|
|
"epoch": 1.3662604593699106,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004823770739087574,
|
|
"loss": 5.4814,
|
|
"mean_token_accuracy": 0.18017132431268693,
|
|
"num_tokens": 27135936.0,
|
|
"step": 12165
|
|
},
|
|
{
|
|
"entropy": 5.766518306732178,
|
|
"epoch": 1.3668220362778682,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004823614944791154,
|
|
"loss": 5.6394,
|
|
"mean_token_accuracy": 0.17236140221357346,
|
|
"num_tokens": 27148240.0,
|
|
"step": 12170
|
|
},
|
|
{
|
|
"entropy": 5.628880310058594,
|
|
"epoch": 1.367383613185826,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004823459084470031,
|
|
"loss": 5.3949,
|
|
"mean_token_accuracy": 0.18684293627738952,
|
|
"num_tokens": 27159057.0,
|
|
"step": 12175
|
|
},
|
|
{
|
|
"entropy": 5.5123375415802,
|
|
"epoch": 1.3679451900937833,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004823303158129165,
|
|
"loss": 5.4063,
|
|
"mean_token_accuracy": 0.18343780785799027,
|
|
"num_tokens": 27169189.0,
|
|
"step": 12180
|
|
},
|
|
{
|
|
"entropy": 5.538809442520142,
|
|
"epoch": 1.3685067670017408,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004823147165773523,
|
|
"loss": 5.3756,
|
|
"mean_token_accuracy": 0.18663349747657776,
|
|
"num_tokens": 27180777.0,
|
|
"step": 12185
|
|
},
|
|
{
|
|
"entropy": 5.608754634857178,
|
|
"epoch": 1.3690683439096984,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.00048229911074080715,
|
|
"loss": 5.4179,
|
|
"mean_token_accuracy": 0.1894705057144165,
|
|
"num_tokens": 27190991.0,
|
|
"step": 12190
|
|
},
|
|
{
|
|
"entropy": 5.571418428421021,
|
|
"epoch": 1.369629920817656,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.00048228349830377787,
|
|
"loss": 5.4526,
|
|
"mean_token_accuracy": 0.17986156195402145,
|
|
"num_tokens": 27203776.0,
|
|
"step": 12195
|
|
},
|
|
{
|
|
"entropy": 5.492271375656128,
|
|
"epoch": 1.3701914977256135,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.00048226787926676165,
|
|
"loss": 5.3669,
|
|
"mean_token_accuracy": 0.18599619418382646,
|
|
"num_tokens": 27213533.0,
|
|
"step": 12200
|
|
},
|
|
{
|
|
"entropy": 5.615678501129151,
|
|
"epoch": 1.370753074633571,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.00048225225363025576,
|
|
"loss": 5.4857,
|
|
"mean_token_accuracy": 0.17912229895591736,
|
|
"num_tokens": 27224832.0,
|
|
"step": 12205
|
|
},
|
|
{
|
|
"entropy": 5.665140295028687,
|
|
"epoch": 1.3713146515415287,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.00048223662139475773,
|
|
"loss": 5.5298,
|
|
"mean_token_accuracy": 0.17312545627355574,
|
|
"num_tokens": 27237313.0,
|
|
"step": 12210
|
|
},
|
|
{
|
|
"entropy": 5.6187337875366214,
|
|
"epoch": 1.371876228449486,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.00048222098256076523,
|
|
"loss": 5.3418,
|
|
"mean_token_accuracy": 0.18424533009529115,
|
|
"num_tokens": 27248159.0,
|
|
"step": 12215
|
|
},
|
|
{
|
|
"entropy": 5.623969841003418,
|
|
"epoch": 1.3724378053574438,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004822053371287763,
|
|
"loss": 5.4661,
|
|
"mean_token_accuracy": 0.18050478100776673,
|
|
"num_tokens": 27259723.0,
|
|
"step": 12220
|
|
},
|
|
{
|
|
"entropy": 5.574584579467773,
|
|
"epoch": 1.3729993822654012,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004821896850992891,
|
|
"loss": 5.4104,
|
|
"mean_token_accuracy": 0.17844849526882173,
|
|
"num_tokens": 27270207.0,
|
|
"step": 12225
|
|
},
|
|
{
|
|
"entropy": 5.568454647064209,
|
|
"epoch": 1.3735609591733589,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.000482174026472802,
|
|
"loss": 5.4621,
|
|
"mean_token_accuracy": 0.188611501455307,
|
|
"num_tokens": 27281243.0,
|
|
"step": 12230
|
|
},
|
|
{
|
|
"entropy": 5.4445079326629635,
|
|
"epoch": 1.3741225360813163,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004821583612498135,
|
|
"loss": 5.2634,
|
|
"mean_token_accuracy": 0.18975935131311417,
|
|
"num_tokens": 27292816.0,
|
|
"step": 12235
|
|
},
|
|
{
|
|
"entropy": 5.51634955406189,
|
|
"epoch": 1.374684112989274,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.00048214268943082246,
|
|
"loss": 5.4411,
|
|
"mean_token_accuracy": 0.18239236921072005,
|
|
"num_tokens": 27304254.0,
|
|
"step": 12240
|
|
},
|
|
{
|
|
"entropy": 5.529271507263184,
|
|
"epoch": 1.3752456898972314,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004821270110163278,
|
|
"loss": 5.3758,
|
|
"mean_token_accuracy": 0.17939476817846298,
|
|
"num_tokens": 27314974.0,
|
|
"step": 12245
|
|
},
|
|
{
|
|
"entropy": 5.587137651443482,
|
|
"epoch": 1.375807266805189,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004821113260068288,
|
|
"loss": 5.4711,
|
|
"mean_token_accuracy": 0.17995233684778214,
|
|
"num_tokens": 27326051.0,
|
|
"step": 12250
|
|
},
|
|
{
|
|
"entropy": 5.519277620315552,
|
|
"epoch": 1.3763688437131465,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004820956344028249,
|
|
"loss": 5.3203,
|
|
"mean_token_accuracy": 0.18622014671564102,
|
|
"num_tokens": 27337589.0,
|
|
"step": 12255
|
|
},
|
|
{
|
|
"entropy": 5.579274892807007,
|
|
"epoch": 1.376930420621104,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00048207993620481566,
|
|
"loss": 5.4029,
|
|
"mean_token_accuracy": 0.18406821340322493,
|
|
"num_tokens": 27348581.0,
|
|
"step": 12260
|
|
},
|
|
{
|
|
"entropy": 5.6482140064239506,
|
|
"epoch": 1.3774919975290616,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.0004820642314133009,
|
|
"loss": 5.5,
|
|
"mean_token_accuracy": 0.1824349656701088,
|
|
"num_tokens": 27359963.0,
|
|
"step": 12265
|
|
},
|
|
{
|
|
"entropy": 5.583898305892944,
|
|
"epoch": 1.3780535744370193,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00048204852002878073,
|
|
"loss": 5.3464,
|
|
"mean_token_accuracy": 0.18646378070116043,
|
|
"num_tokens": 27370149.0,
|
|
"step": 12270
|
|
},
|
|
{
|
|
"entropy": 5.462600898742676,
|
|
"epoch": 1.3786151513449767,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.00048203280205175544,
|
|
"loss": 5.3477,
|
|
"mean_token_accuracy": 0.1911865547299385,
|
|
"num_tokens": 27381657.0,
|
|
"step": 12275
|
|
},
|
|
{
|
|
"entropy": 5.587764310836792,
|
|
"epoch": 1.3791767282529341,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004820170774827253,
|
|
"loss": 5.4043,
|
|
"mean_token_accuracy": 0.17355224043130874,
|
|
"num_tokens": 27392679.0,
|
|
"step": 12280
|
|
},
|
|
{
|
|
"entropy": 5.503405570983887,
|
|
"epoch": 1.3797383051608918,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004820013463221912,
|
|
"loss": 5.3837,
|
|
"mean_token_accuracy": 0.18209337592124938,
|
|
"num_tokens": 27404003.0,
|
|
"step": 12285
|
|
},
|
|
{
|
|
"entropy": 5.5964930057525635,
|
|
"epoch": 1.3802998820688495,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.000481985608570654,
|
|
"loss": 5.4163,
|
|
"mean_token_accuracy": 0.18666171431541442,
|
|
"num_tokens": 27414593.0,
|
|
"step": 12290
|
|
},
|
|
{
|
|
"entropy": 5.658124732971191,
|
|
"epoch": 1.380861458976807,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004819698642286147,
|
|
"loss": 5.5594,
|
|
"mean_token_accuracy": 0.17700323164463044,
|
|
"num_tokens": 27426549.0,
|
|
"step": 12295
|
|
},
|
|
{
|
|
"entropy": 5.61198239326477,
|
|
"epoch": 1.3814230358847643,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00048195411329657464,
|
|
"loss": 5.5078,
|
|
"mean_token_accuracy": 0.1794409230351448,
|
|
"num_tokens": 27439451.0,
|
|
"step": 12300
|
|
},
|
|
{
|
|
"entropy": 5.658680152893067,
|
|
"epoch": 1.381984612792722,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004819383557750353,
|
|
"loss": 5.4367,
|
|
"mean_token_accuracy": 0.18478858917951585,
|
|
"num_tokens": 27451153.0,
|
|
"step": 12305
|
|
},
|
|
{
|
|
"entropy": 5.594944858551026,
|
|
"epoch": 1.3825461897006794,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00048192259166449845,
|
|
"loss": 5.3848,
|
|
"mean_token_accuracy": 0.18378443419933319,
|
|
"num_tokens": 27462229.0,
|
|
"step": 12310
|
|
},
|
|
{
|
|
"entropy": 5.531543779373169,
|
|
"epoch": 1.383107766608637,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.00048190682096546606,
|
|
"loss": 5.3906,
|
|
"mean_token_accuracy": 0.18350973427295686,
|
|
"num_tokens": 27473901.0,
|
|
"step": 12315
|
|
},
|
|
{
|
|
"entropy": 5.493347024917602,
|
|
"epoch": 1.3836693435165945,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.00048189104367844034,
|
|
"loss": 5.3864,
|
|
"mean_token_accuracy": 0.1844016879796982,
|
|
"num_tokens": 27485981.0,
|
|
"step": 12320
|
|
},
|
|
{
|
|
"entropy": 5.548513746261596,
|
|
"epoch": 1.3842309204245522,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.00048187525980392343,
|
|
"loss": 5.3151,
|
|
"mean_token_accuracy": 0.1873913511633873,
|
|
"num_tokens": 27495764.0,
|
|
"step": 12325
|
|
},
|
|
{
|
|
"entropy": 5.561328363418579,
|
|
"epoch": 1.3847924973325096,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.000481859469342418,
|
|
"loss": 5.4035,
|
|
"mean_token_accuracy": 0.185747367143631,
|
|
"num_tokens": 27506602.0,
|
|
"step": 12330
|
|
},
|
|
{
|
|
"entropy": 5.430418491363525,
|
|
"epoch": 1.3853540742404673,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004818436722944269,
|
|
"loss": 5.3569,
|
|
"mean_token_accuracy": 0.184988309442997,
|
|
"num_tokens": 27517482.0,
|
|
"step": 12335
|
|
},
|
|
{
|
|
"entropy": 5.559353876113891,
|
|
"epoch": 1.3859156511484247,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004818278686604531,
|
|
"loss": 5.4023,
|
|
"mean_token_accuracy": 0.18987395912408828,
|
|
"num_tokens": 27528560.0,
|
|
"step": 12340
|
|
},
|
|
{
|
|
"entropy": 5.590506649017334,
|
|
"epoch": 1.3864772280563824,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004818120584409996,
|
|
"loss": 5.4171,
|
|
"mean_token_accuracy": 0.18152203857898713,
|
|
"num_tokens": 27540019.0,
|
|
"step": 12345
|
|
},
|
|
{
|
|
"entropy": 5.635791635513305,
|
|
"epoch": 1.3870388049643398,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004817962416365701,
|
|
"loss": 5.4703,
|
|
"mean_token_accuracy": 0.1841760665178299,
|
|
"num_tokens": 27550553.0,
|
|
"step": 12350
|
|
},
|
|
{
|
|
"entropy": 5.652179098129272,
|
|
"epoch": 1.3876003818722973,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.00048178041824766796,
|
|
"loss": 5.3921,
|
|
"mean_token_accuracy": 0.18463724851608276,
|
|
"num_tokens": 27562169.0,
|
|
"step": 12355
|
|
},
|
|
{
|
|
"entropy": 5.573112106323242,
|
|
"epoch": 1.388161958780255,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004817645882747971,
|
|
"loss": 5.3501,
|
|
"mean_token_accuracy": 0.18608878701925277,
|
|
"num_tokens": 27571732.0,
|
|
"step": 12360
|
|
},
|
|
{
|
|
"entropy": 5.548039531707763,
|
|
"epoch": 1.3887235356882126,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004817487517184616,
|
|
"loss": 5.3879,
|
|
"mean_token_accuracy": 0.18541265428066253,
|
|
"num_tokens": 27584394.0,
|
|
"step": 12365
|
|
},
|
|
{
|
|
"entropy": 5.508686971664429,
|
|
"epoch": 1.38928511259617,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004817329085791657,
|
|
"loss": 5.3564,
|
|
"mean_token_accuracy": 0.19151072800159455,
|
|
"num_tokens": 27594813.0,
|
|
"step": 12370
|
|
},
|
|
{
|
|
"entropy": 5.497928047180176,
|
|
"epoch": 1.3898466895041275,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004817170588574138,
|
|
"loss": 5.3126,
|
|
"mean_token_accuracy": 0.19099864661693572,
|
|
"num_tokens": 27605375.0,
|
|
"step": 12375
|
|
},
|
|
{
|
|
"entropy": 5.497993659973145,
|
|
"epoch": 1.3904082664120851,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004817012025537105,
|
|
"loss": 5.3271,
|
|
"mean_token_accuracy": 0.18947082310914992,
|
|
"num_tokens": 27617066.0,
|
|
"step": 12380
|
|
},
|
|
{
|
|
"entropy": 5.597756481170654,
|
|
"epoch": 1.3909698433200428,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004816853396685608,
|
|
"loss": 5.4817,
|
|
"mean_token_accuracy": 0.18175812810659409,
|
|
"num_tokens": 27628667.0,
|
|
"step": 12385
|
|
},
|
|
{
|
|
"entropy": 5.560773801803589,
|
|
"epoch": 1.3915314202280002,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.00048166947020246973,
|
|
"loss": 5.4373,
|
|
"mean_token_accuracy": 0.18439250141382219,
|
|
"num_tokens": 27638858.0,
|
|
"step": 12390
|
|
},
|
|
{
|
|
"entropy": 5.639008903503418,
|
|
"epoch": 1.3920929971359577,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00048165359415594245,
|
|
"loss": 5.5106,
|
|
"mean_token_accuracy": 0.18048693388700485,
|
|
"num_tokens": 27650518.0,
|
|
"step": 12395
|
|
},
|
|
{
|
|
"entropy": 5.587079381942749,
|
|
"epoch": 1.3926545740439153,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.00048163771152948473,
|
|
"loss": 5.4689,
|
|
"mean_token_accuracy": 0.18535237908363342,
|
|
"num_tokens": 27661781.0,
|
|
"step": 12400
|
|
},
|
|
{
|
|
"entropy": 5.548201274871826,
|
|
"epoch": 1.3932161509518728,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.000481621822323602,
|
|
"loss": 5.4116,
|
|
"mean_token_accuracy": 0.1857258066534996,
|
|
"num_tokens": 27673040.0,
|
|
"step": 12405
|
|
},
|
|
{
|
|
"entropy": 5.57417516708374,
|
|
"epoch": 1.3937777278598305,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004816059265388004,
|
|
"loss": 5.4514,
|
|
"mean_token_accuracy": 0.1865248292684555,
|
|
"num_tokens": 27683541.0,
|
|
"step": 12410
|
|
},
|
|
{
|
|
"entropy": 5.655316543579102,
|
|
"epoch": 1.394339304767788,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00048159002417558596,
|
|
"loss": 5.4949,
|
|
"mean_token_accuracy": 0.1792720377445221,
|
|
"num_tokens": 27693648.0,
|
|
"step": 12415
|
|
},
|
|
{
|
|
"entropy": 5.596675729751587,
|
|
"epoch": 1.3949008816757456,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004815741152344651,
|
|
"loss": 5.322,
|
|
"mean_token_accuracy": 0.18869377970695494,
|
|
"num_tokens": 27703920.0,
|
|
"step": 12420
|
|
},
|
|
{
|
|
"entropy": 5.652033138275146,
|
|
"epoch": 1.395462458583703,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004815581997159442,
|
|
"loss": 5.4572,
|
|
"mean_token_accuracy": 0.17444158643484114,
|
|
"num_tokens": 27715869.0,
|
|
"step": 12425
|
|
},
|
|
{
|
|
"entropy": 5.5294694900512695,
|
|
"epoch": 1.3960240354916607,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00048154227762053003,
|
|
"loss": 5.402,
|
|
"mean_token_accuracy": 0.18923304080963135,
|
|
"num_tokens": 27726727.0,
|
|
"step": 12430
|
|
},
|
|
{
|
|
"entropy": 5.565631341934204,
|
|
"epoch": 1.396585612399618,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004815263489487298,
|
|
"loss": 5.3971,
|
|
"mean_token_accuracy": 0.18441684991121293,
|
|
"num_tokens": 27738217.0,
|
|
"step": 12435
|
|
},
|
|
{
|
|
"entropy": 5.597028398513794,
|
|
"epoch": 1.3971471893075758,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004815104137010504,
|
|
"loss": 5.4008,
|
|
"mean_token_accuracy": 0.183449324965477,
|
|
"num_tokens": 27749022.0,
|
|
"step": 12440
|
|
},
|
|
{
|
|
"entropy": 5.541413402557373,
|
|
"epoch": 1.3977087662155332,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004814944718779993,
|
|
"loss": 5.3621,
|
|
"mean_token_accuracy": 0.18739566802978516,
|
|
"num_tokens": 27760589.0,
|
|
"step": 12445
|
|
},
|
|
{
|
|
"entropy": 5.665905904769898,
|
|
"epoch": 1.3982703431234906,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004814785234800843,
|
|
"loss": 5.4442,
|
|
"mean_token_accuracy": 0.18137060031294822,
|
|
"num_tokens": 27772460.0,
|
|
"step": 12450
|
|
},
|
|
{
|
|
"entropy": 5.499793148040771,
|
|
"epoch": 1.3988319200314483,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00048146256850781287,
|
|
"loss": 5.3198,
|
|
"mean_token_accuracy": 0.1835328683257103,
|
|
"num_tokens": 27783921.0,
|
|
"step": 12455
|
|
},
|
|
{
|
|
"entropy": 5.597337436676026,
|
|
"epoch": 1.399393496939406,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.00048144660696169327,
|
|
"loss": 5.4682,
|
|
"mean_token_accuracy": 0.1830869808793068,
|
|
"num_tokens": 27794843.0,
|
|
"step": 12460
|
|
},
|
|
{
|
|
"entropy": 5.643671464920044,
|
|
"epoch": 1.3999550738473634,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.00048143063884223365,
|
|
"loss": 5.364,
|
|
"mean_token_accuracy": 0.1830323278903961,
|
|
"num_tokens": 27805973.0,
|
|
"step": 12465
|
|
},
|
|
{
|
|
"entropy": 5.555152940750122,
|
|
"epoch": 1.4005166507553208,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004814146641499424,
|
|
"loss": 5.4186,
|
|
"mean_token_accuracy": 0.18221746683120726,
|
|
"num_tokens": 27816916.0,
|
|
"step": 12470
|
|
},
|
|
{
|
|
"entropy": 5.5165797710418705,
|
|
"epoch": 1.4010782276632785,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.00048139868288532816,
|
|
"loss": 5.4158,
|
|
"mean_token_accuracy": 0.18309104293584824,
|
|
"num_tokens": 27828077.0,
|
|
"step": 12475
|
|
},
|
|
{
|
|
"entropy": 5.526023244857788,
|
|
"epoch": 1.4016398045712362,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.0004813826950488998,
|
|
"loss": 5.3147,
|
|
"mean_token_accuracy": 0.18483598977327348,
|
|
"num_tokens": 27838502.0,
|
|
"step": 12480
|
|
},
|
|
{
|
|
"entropy": 5.578309106826782,
|
|
"epoch": 1.4022013814791936,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.00048136670064116645,
|
|
"loss": 5.4476,
|
|
"mean_token_accuracy": 0.17935547083616257,
|
|
"num_tokens": 27850125.0,
|
|
"step": 12485
|
|
},
|
|
{
|
|
"entropy": 5.602385520935059,
|
|
"epoch": 1.402762958387151,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004813506996626373,
|
|
"loss": 5.3996,
|
|
"mean_token_accuracy": 0.18731053471565245,
|
|
"num_tokens": 27861099.0,
|
|
"step": 12490
|
|
},
|
|
{
|
|
"entropy": 5.608717012405395,
|
|
"epoch": 1.4033245352951087,
|
|
"grad_norm": 2.6875,
|
|
"learning_rate": 0.0004813346921138218,
|
|
"loss": 5.3996,
|
|
"mean_token_accuracy": 0.18824754655361176,
|
|
"num_tokens": 27872769.0,
|
|
"step": 12495
|
|
},
|
|
{
|
|
"entropy": 5.632760953903198,
|
|
"epoch": 1.4038861122030661,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004813186779952297,
|
|
"loss": 5.4829,
|
|
"mean_token_accuracy": 0.1809535726904869,
|
|
"num_tokens": 27884448.0,
|
|
"step": 12500
|
|
},
|
|
{
|
|
"entropy": 5.465057134628296,
|
|
"epoch": 1.4044476891110238,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004813026573073708,
|
|
"loss": 5.3272,
|
|
"mean_token_accuracy": 0.17773733884096146,
|
|
"num_tokens": 27894074.0,
|
|
"step": 12505
|
|
},
|
|
{
|
|
"entropy": 5.678692483901978,
|
|
"epoch": 1.4050092660189812,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004812866300507554,
|
|
"loss": 5.5052,
|
|
"mean_token_accuracy": 0.18612149655818938,
|
|
"num_tokens": 27905150.0,
|
|
"step": 12510
|
|
},
|
|
{
|
|
"entropy": 5.655053567886353,
|
|
"epoch": 1.405570842926939,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004812705962258936,
|
|
"loss": 5.4147,
|
|
"mean_token_accuracy": 0.1827722519636154,
|
|
"num_tokens": 27916471.0,
|
|
"step": 12515
|
|
},
|
|
{
|
|
"entropy": 5.563557434082031,
|
|
"epoch": 1.4061324198348963,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004812545558332961,
|
|
"loss": 5.3875,
|
|
"mean_token_accuracy": 0.18819346278905869,
|
|
"num_tokens": 27928276.0,
|
|
"step": 12520
|
|
},
|
|
{
|
|
"entropy": 5.621595621109009,
|
|
"epoch": 1.406693996742854,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.00048123850887347346,
|
|
"loss": 5.4148,
|
|
"mean_token_accuracy": 0.17566152215003966,
|
|
"num_tokens": 27940417.0,
|
|
"step": 12525
|
|
},
|
|
{
|
|
"entropy": 5.474638271331787,
|
|
"epoch": 1.4072555736508114,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.00048122245534693676,
|
|
"loss": 5.2741,
|
|
"mean_token_accuracy": 0.19022467583417893,
|
|
"num_tokens": 27950490.0,
|
|
"step": 12530
|
|
},
|
|
{
|
|
"entropy": 5.6266542911529545,
|
|
"epoch": 1.407817150558769,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.0004812063952541971,
|
|
"loss": 5.4814,
|
|
"mean_token_accuracy": 0.17631009668111802,
|
|
"num_tokens": 27962593.0,
|
|
"step": 12535
|
|
},
|
|
{
|
|
"entropy": 5.678593349456787,
|
|
"epoch": 1.4083787274667265,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.00048119032859576577,
|
|
"loss": 5.5351,
|
|
"mean_token_accuracy": 0.1745996281504631,
|
|
"num_tokens": 27973567.0,
|
|
"step": 12540
|
|
},
|
|
{
|
|
"entropy": 5.501290893554687,
|
|
"epoch": 1.408940304374684,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004811742553721545,
|
|
"loss": 5.3323,
|
|
"mean_token_accuracy": 0.1903274819254875,
|
|
"num_tokens": 27984383.0,
|
|
"step": 12545
|
|
},
|
|
{
|
|
"entropy": 5.646518278121948,
|
|
"epoch": 1.4095018812826416,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.00048115817558387494,
|
|
"loss": 5.4665,
|
|
"mean_token_accuracy": 0.17970054000616073,
|
|
"num_tokens": 27995735.0,
|
|
"step": 12550
|
|
},
|
|
{
|
|
"entropy": 5.6405247211456295,
|
|
"epoch": 1.4100634581905993,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004811420892314391,
|
|
"loss": 5.5232,
|
|
"mean_token_accuracy": 0.17082713842391967,
|
|
"num_tokens": 28008261.0,
|
|
"step": 12555
|
|
},
|
|
{
|
|
"entropy": 5.518653488159179,
|
|
"epoch": 1.4106250350985567,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004811259963153592,
|
|
"loss": 5.3617,
|
|
"mean_token_accuracy": 0.18512748330831527,
|
|
"num_tokens": 28019424.0,
|
|
"step": 12560
|
|
},
|
|
{
|
|
"entropy": 5.602254915237427,
|
|
"epoch": 1.4111866120065142,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004811098968361476,
|
|
"loss": 5.4736,
|
|
"mean_token_accuracy": 0.18438162207603453,
|
|
"num_tokens": 28030961.0,
|
|
"step": 12565
|
|
},
|
|
{
|
|
"entropy": 5.580341243743897,
|
|
"epoch": 1.4117481889144718,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.000481093790794317,
|
|
"loss": 5.4445,
|
|
"mean_token_accuracy": 0.17799729555845262,
|
|
"num_tokens": 28042580.0,
|
|
"step": 12570
|
|
},
|
|
{
|
|
"entropy": 5.760495996475219,
|
|
"epoch": 1.4123097658224295,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004810776781903801,
|
|
"loss": 5.5708,
|
|
"mean_token_accuracy": 0.1800316646695137,
|
|
"num_tokens": 28053435.0,
|
|
"step": 12575
|
|
},
|
|
{
|
|
"entropy": 5.72199559211731,
|
|
"epoch": 1.412871342730387,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.00048106155902485003,
|
|
"loss": 5.543,
|
|
"mean_token_accuracy": 0.17407634854316711,
|
|
"num_tokens": 28065195.0,
|
|
"step": 12580
|
|
},
|
|
{
|
|
"entropy": 5.580473899841309,
|
|
"epoch": 1.4134329196383444,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004810454332982401,
|
|
"loss": 5.4714,
|
|
"mean_token_accuracy": 0.18441999405622483,
|
|
"num_tokens": 28077457.0,
|
|
"step": 12585
|
|
},
|
|
{
|
|
"entropy": 5.530069398880005,
|
|
"epoch": 1.413994496546302,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004810293010110635,
|
|
"loss": 5.374,
|
|
"mean_token_accuracy": 0.18203333616256714,
|
|
"num_tokens": 28087598.0,
|
|
"step": 12590
|
|
},
|
|
{
|
|
"entropy": 5.564488935470581,
|
|
"epoch": 1.4145560734542595,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004810131621638342,
|
|
"loss": 5.3185,
|
|
"mean_token_accuracy": 0.18823318481445311,
|
|
"num_tokens": 28097232.0,
|
|
"step": 12595
|
|
},
|
|
{
|
|
"entropy": 5.5692249774932865,
|
|
"epoch": 1.4151176503622171,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.00048099701675706583,
|
|
"loss": 5.4612,
|
|
"mean_token_accuracy": 0.18515441864728927,
|
|
"num_tokens": 28107333.0,
|
|
"step": 12600
|
|
},
|
|
{
|
|
"entropy": 5.607000064849854,
|
|
"epoch": 1.4156792272701746,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004809808647912725,
|
|
"loss": 5.4363,
|
|
"mean_token_accuracy": 0.17578344345092772,
|
|
"num_tokens": 28117886.0,
|
|
"step": 12605
|
|
},
|
|
{
|
|
"entropy": 5.625807571411133,
|
|
"epoch": 1.4162408041781323,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004809647062669686,
|
|
"loss": 5.4257,
|
|
"mean_token_accuracy": 0.18431251794099807,
|
|
"num_tokens": 28128884.0,
|
|
"step": 12610
|
|
},
|
|
{
|
|
"entropy": 5.611122894287109,
|
|
"epoch": 1.4168023810860897,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.00048094854118466856,
|
|
"loss": 5.5125,
|
|
"mean_token_accuracy": 0.17216638326644898,
|
|
"num_tokens": 28139859.0,
|
|
"step": 12615
|
|
},
|
|
{
|
|
"entropy": 5.722675848007202,
|
|
"epoch": 1.4173639579940474,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.00048093236954488715,
|
|
"loss": 5.4578,
|
|
"mean_token_accuracy": 0.18167351186275482,
|
|
"num_tokens": 28150398.0,
|
|
"step": 12620
|
|
},
|
|
{
|
|
"entropy": 5.565816211700439,
|
|
"epoch": 1.4179255349020048,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004809161913481392,
|
|
"loss": 5.3456,
|
|
"mean_token_accuracy": 0.19193344712257385,
|
|
"num_tokens": 28160766.0,
|
|
"step": 12625
|
|
},
|
|
{
|
|
"entropy": 5.537726974487304,
|
|
"epoch": 1.4184871118099625,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.00048090000659493985,
|
|
"loss": 5.4534,
|
|
"mean_token_accuracy": 0.1803365468978882,
|
|
"num_tokens": 28171583.0,
|
|
"step": 12630
|
|
},
|
|
{
|
|
"entropy": 5.526329898834229,
|
|
"epoch": 1.41904868871792,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.00048088381528580445,
|
|
"loss": 5.2915,
|
|
"mean_token_accuracy": 0.1874199703335762,
|
|
"num_tokens": 28183598.0,
|
|
"step": 12635
|
|
},
|
|
{
|
|
"entropy": 5.602271223068238,
|
|
"epoch": 1.4196102656258773,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.00048086761742124846,
|
|
"loss": 5.4352,
|
|
"mean_token_accuracy": 0.17657459378242493,
|
|
"num_tokens": 28193377.0,
|
|
"step": 12640
|
|
},
|
|
{
|
|
"entropy": 5.519383335113526,
|
|
"epoch": 1.420171842533835,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00048085141300178774,
|
|
"loss": 5.3145,
|
|
"mean_token_accuracy": 0.19562322795391082,
|
|
"num_tokens": 28204536.0,
|
|
"step": 12645
|
|
},
|
|
{
|
|
"entropy": 5.523086929321289,
|
|
"epoch": 1.4207334194417927,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00048083520202793815,
|
|
"loss": 5.4666,
|
|
"mean_token_accuracy": 0.18537127673625947,
|
|
"num_tokens": 28215806.0,
|
|
"step": 12650
|
|
},
|
|
{
|
|
"entropy": 5.608553647994995,
|
|
"epoch": 1.42129499634975,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004808189845002159,
|
|
"loss": 5.4048,
|
|
"mean_token_accuracy": 0.1814317598938942,
|
|
"num_tokens": 28226765.0,
|
|
"step": 12655
|
|
},
|
|
{
|
|
"entropy": 5.74329023361206,
|
|
"epoch": 1.4218565732577075,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004808027604191374,
|
|
"loss": 5.5899,
|
|
"mean_token_accuracy": 0.17849552035331726,
|
|
"num_tokens": 28238077.0,
|
|
"step": 12660
|
|
},
|
|
{
|
|
"entropy": 5.542377138137818,
|
|
"epoch": 1.4224181501656652,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00048078652978521914,
|
|
"loss": 5.4332,
|
|
"mean_token_accuracy": 0.1853796973824501,
|
|
"num_tokens": 28248992.0,
|
|
"step": 12665
|
|
},
|
|
{
|
|
"entropy": 5.575919246673584,
|
|
"epoch": 1.4229797270736229,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.00048077029259897797,
|
|
"loss": 5.403,
|
|
"mean_token_accuracy": 0.18549903780221938,
|
|
"num_tokens": 28259818.0,
|
|
"step": 12670
|
|
},
|
|
{
|
|
"entropy": 5.549159860610962,
|
|
"epoch": 1.4235413039815803,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00048075404886093094,
|
|
"loss": 5.3757,
|
|
"mean_token_accuracy": 0.1832862064242363,
|
|
"num_tokens": 28271139.0,
|
|
"step": 12675
|
|
},
|
|
{
|
|
"entropy": 5.616514015197754,
|
|
"epoch": 1.4241028808895377,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.00048073779857159504,
|
|
"loss": 5.4163,
|
|
"mean_token_accuracy": 0.18590553998947143,
|
|
"num_tokens": 28282093.0,
|
|
"step": 12680
|
|
},
|
|
{
|
|
"entropy": 5.550446653366089,
|
|
"epoch": 1.4246644577974954,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.000480721541731488,
|
|
"loss": 5.3172,
|
|
"mean_token_accuracy": 0.19124546498060227,
|
|
"num_tokens": 28292701.0,
|
|
"step": 12685
|
|
},
|
|
{
|
|
"entropy": 5.481839513778686,
|
|
"epoch": 1.4252260347054528,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00048070527834112727,
|
|
"loss": 5.365,
|
|
"mean_token_accuracy": 0.18471651673316955,
|
|
"num_tokens": 28303585.0,
|
|
"step": 12690
|
|
},
|
|
{
|
|
"entropy": 5.536582088470459,
|
|
"epoch": 1.4257876116134105,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004806890084010306,
|
|
"loss": 5.3138,
|
|
"mean_token_accuracy": 0.1883379191160202,
|
|
"num_tokens": 28314583.0,
|
|
"step": 12695
|
|
},
|
|
{
|
|
"entropy": 5.511456155776978,
|
|
"epoch": 1.426349188521368,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00048067273191171615,
|
|
"loss": 5.3755,
|
|
"mean_token_accuracy": 0.1849355146288872,
|
|
"num_tokens": 28325895.0,
|
|
"step": 12700
|
|
},
|
|
{
|
|
"entropy": 5.630955028533935,
|
|
"epoch": 1.4269107654293256,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004806564488737022,
|
|
"loss": 5.4393,
|
|
"mean_token_accuracy": 0.17738497406244277,
|
|
"num_tokens": 28337011.0,
|
|
"step": 12705
|
|
},
|
|
{
|
|
"entropy": 5.73394136428833,
|
|
"epoch": 1.427472342337283,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004806401592875071,
|
|
"loss": 5.4884,
|
|
"mean_token_accuracy": 0.17780508249998092,
|
|
"num_tokens": 28347468.0,
|
|
"step": 12710
|
|
},
|
|
{
|
|
"entropy": 5.582927083969116,
|
|
"epoch": 1.4280339192452407,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.00048062386315364964,
|
|
"loss": 5.409,
|
|
"mean_token_accuracy": 0.1885148122906685,
|
|
"num_tokens": 28357287.0,
|
|
"step": 12715
|
|
},
|
|
{
|
|
"entropy": 5.632099342346192,
|
|
"epoch": 1.4285954961531981,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004806075604726485,
|
|
"loss": 5.4255,
|
|
"mean_token_accuracy": 0.19006743729114534,
|
|
"num_tokens": 28368508.0,
|
|
"step": 12720
|
|
},
|
|
{
|
|
"entropy": 5.629025793075561,
|
|
"epoch": 1.4291570730611558,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00048059125124502304,
|
|
"loss": 5.3773,
|
|
"mean_token_accuracy": 0.18756729513406753,
|
|
"num_tokens": 28378211.0,
|
|
"step": 12725
|
|
},
|
|
{
|
|
"entropy": 5.47719259262085,
|
|
"epoch": 1.4297186499691132,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004805749354712924,
|
|
"loss": 5.3437,
|
|
"mean_token_accuracy": 0.1933674082159996,
|
|
"num_tokens": 28389083.0,
|
|
"step": 12730
|
|
},
|
|
{
|
|
"entropy": 5.546667385101318,
|
|
"epoch": 1.4302802268770707,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.000480558613151976,
|
|
"loss": 5.3948,
|
|
"mean_token_accuracy": 0.18546858429908752,
|
|
"num_tokens": 28399786.0,
|
|
"step": 12735
|
|
},
|
|
{
|
|
"entropy": 5.515288591384888,
|
|
"epoch": 1.4308418037850283,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004805422842875936,
|
|
"loss": 5.4403,
|
|
"mean_token_accuracy": 0.17986469864845275,
|
|
"num_tokens": 28410650.0,
|
|
"step": 12740
|
|
},
|
|
{
|
|
"entropy": 5.658247184753418,
|
|
"epoch": 1.431403380692986,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00048052594887866524,
|
|
"loss": 5.4536,
|
|
"mean_token_accuracy": 0.18518347442150115,
|
|
"num_tokens": 28421485.0,
|
|
"step": 12745
|
|
},
|
|
{
|
|
"entropy": 5.559001684188843,
|
|
"epoch": 1.4319649576009434,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.00048050960692571086,
|
|
"loss": 5.4078,
|
|
"mean_token_accuracy": 0.17889249175786973,
|
|
"num_tokens": 28432469.0,
|
|
"step": 12750
|
|
},
|
|
{
|
|
"entropy": 5.473956680297851,
|
|
"epoch": 1.4325265345089009,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.000480493258429251,
|
|
"loss": 5.3408,
|
|
"mean_token_accuracy": 0.18645906299352646,
|
|
"num_tokens": 28443628.0,
|
|
"step": 12755
|
|
},
|
|
{
|
|
"entropy": 5.631206893920899,
|
|
"epoch": 1.4330881114168585,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.000480476903389806,
|
|
"loss": 5.4609,
|
|
"mean_token_accuracy": 0.17793752402067184,
|
|
"num_tokens": 28455106.0,
|
|
"step": 12760
|
|
},
|
|
{
|
|
"entropy": 5.617642450332641,
|
|
"epoch": 1.4336496883248162,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004804605418078968,
|
|
"loss": 5.4179,
|
|
"mean_token_accuracy": 0.18299987465143203,
|
|
"num_tokens": 28466326.0,
|
|
"step": 12765
|
|
},
|
|
{
|
|
"entropy": 5.567136287689209,
|
|
"epoch": 1.4342112652327736,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.00048044417368404426,
|
|
"loss": 5.5462,
|
|
"mean_token_accuracy": 0.18090612143278123,
|
|
"num_tokens": 28477490.0,
|
|
"step": 12770
|
|
},
|
|
{
|
|
"entropy": 5.567657136917115,
|
|
"epoch": 1.434772842140731,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00048042779901876946,
|
|
"loss": 5.3405,
|
|
"mean_token_accuracy": 0.18477673530578614,
|
|
"num_tokens": 28489780.0,
|
|
"step": 12775
|
|
},
|
|
{
|
|
"entropy": 5.6495922088623045,
|
|
"epoch": 1.4353344190486887,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004804114178125939,
|
|
"loss": 5.4825,
|
|
"mean_token_accuracy": 0.18110819458961486,
|
|
"num_tokens": 28500335.0,
|
|
"step": 12780
|
|
},
|
|
{
|
|
"entropy": 5.478008508682251,
|
|
"epoch": 1.4358959959566462,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004803950300660391,
|
|
"loss": 5.2718,
|
|
"mean_token_accuracy": 0.1903608411550522,
|
|
"num_tokens": 28510680.0,
|
|
"step": 12785
|
|
},
|
|
{
|
|
"entropy": 5.486847877502441,
|
|
"epoch": 1.4364575728646038,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004803786357796269,
|
|
"loss": 5.3116,
|
|
"mean_token_accuracy": 0.18844760060310364,
|
|
"num_tokens": 28521719.0,
|
|
"step": 12790
|
|
},
|
|
{
|
|
"entropy": 5.55893497467041,
|
|
"epoch": 1.4370191497725613,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00048036223495387934,
|
|
"loss": 5.4082,
|
|
"mean_token_accuracy": 0.1853305444121361,
|
|
"num_tokens": 28531935.0,
|
|
"step": 12795
|
|
},
|
|
{
|
|
"entropy": 5.608813142776489,
|
|
"epoch": 1.437580726680519,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004803458275893185,
|
|
"loss": 5.3988,
|
|
"mean_token_accuracy": 0.18346945196390152,
|
|
"num_tokens": 28542529.0,
|
|
"step": 12800
|
|
},
|
|
{
|
|
"entropy": 5.550368213653565,
|
|
"epoch": 1.4381423035884764,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004803294136864669,
|
|
"loss": 5.4149,
|
|
"mean_token_accuracy": 0.18546790927648543,
|
|
"num_tokens": 28554724.0,
|
|
"step": 12805
|
|
},
|
|
{
|
|
"entropy": 5.576000595092774,
|
|
"epoch": 1.438703880496434,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.00048031299324584716,
|
|
"loss": 5.3648,
|
|
"mean_token_accuracy": 0.18881458044052124,
|
|
"num_tokens": 28565781.0,
|
|
"step": 12810
|
|
},
|
|
{
|
|
"entropy": 5.5950792789459225,
|
|
"epoch": 1.4392654574043915,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.000480296566267982,
|
|
"loss": 5.3744,
|
|
"mean_token_accuracy": 0.18683136254549026,
|
|
"num_tokens": 28576186.0,
|
|
"step": 12815
|
|
},
|
|
{
|
|
"entropy": 5.525846147537232,
|
|
"epoch": 1.4398270343123492,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004802801327533947,
|
|
"loss": 5.3999,
|
|
"mean_token_accuracy": 0.18060891479253768,
|
|
"num_tokens": 28588240.0,
|
|
"step": 12820
|
|
},
|
|
{
|
|
"entropy": 5.628109312057495,
|
|
"epoch": 1.4403886112203066,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.00048026369270260814,
|
|
"loss": 5.4325,
|
|
"mean_token_accuracy": 0.18242243230342864,
|
|
"num_tokens": 28598240.0,
|
|
"step": 12825
|
|
},
|
|
{
|
|
"entropy": 5.609430503845215,
|
|
"epoch": 1.440950188128264,
|
|
"grad_norm": 2.734375,
|
|
"learning_rate": 0.0004802472461161462,
|
|
"loss": 5.4613,
|
|
"mean_token_accuracy": 0.18128970116376877,
|
|
"num_tokens": 28610091.0,
|
|
"step": 12830
|
|
},
|
|
{
|
|
"entropy": 5.628044462203979,
|
|
"epoch": 1.4415117650362217,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004802307929945322,
|
|
"loss": 5.4469,
|
|
"mean_token_accuracy": 0.18347975760698318,
|
|
"num_tokens": 28621060.0,
|
|
"step": 12835
|
|
},
|
|
{
|
|
"entropy": 5.635926198959351,
|
|
"epoch": 1.4420733419441794,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00048021433333829015,
|
|
"loss": 5.4789,
|
|
"mean_token_accuracy": 0.18282741606235503,
|
|
"num_tokens": 28632027.0,
|
|
"step": 12840
|
|
},
|
|
{
|
|
"entropy": 5.671726369857788,
|
|
"epoch": 1.4426349188521368,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.00048019786714794424,
|
|
"loss": 5.5139,
|
|
"mean_token_accuracy": 0.183630333840847,
|
|
"num_tokens": 28643959.0,
|
|
"step": 12845
|
|
},
|
|
{
|
|
"entropy": 5.591601991653443,
|
|
"epoch": 1.4431964957600942,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004801813944240186,
|
|
"loss": 5.4171,
|
|
"mean_token_accuracy": 0.1879538491368294,
|
|
"num_tokens": 28654166.0,
|
|
"step": 12850
|
|
},
|
|
{
|
|
"entropy": 5.6133091926574705,
|
|
"epoch": 1.443758072668052,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004801649151670378,
|
|
"loss": 5.4046,
|
|
"mean_token_accuracy": 0.18230132460594178,
|
|
"num_tokens": 28667975.0,
|
|
"step": 12855
|
|
},
|
|
{
|
|
"entropy": 5.492213249206543,
|
|
"epoch": 1.4443196495760096,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004801484293775265,
|
|
"loss": 5.3787,
|
|
"mean_token_accuracy": 0.18387535512447356,
|
|
"num_tokens": 28679333.0,
|
|
"step": 12860
|
|
},
|
|
{
|
|
"entropy": 5.522174453735351,
|
|
"epoch": 1.444881226483967,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004801319370560097,
|
|
"loss": 5.2824,
|
|
"mean_token_accuracy": 0.18480635285377503,
|
|
"num_tokens": 28689333.0,
|
|
"step": 12865
|
|
},
|
|
{
|
|
"entropy": 5.563249206542968,
|
|
"epoch": 1.4454428033919244,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004801154382030124,
|
|
"loss": 5.4743,
|
|
"mean_token_accuracy": 0.16807381361722945,
|
|
"num_tokens": 28700625.0,
|
|
"step": 12870
|
|
},
|
|
{
|
|
"entropy": 5.6666676044464115,
|
|
"epoch": 1.446004380299882,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.00048009893281906004,
|
|
"loss": 5.4905,
|
|
"mean_token_accuracy": 0.1777285158634186,
|
|
"num_tokens": 28711768.0,
|
|
"step": 12875
|
|
},
|
|
{
|
|
"entropy": 5.589005374908448,
|
|
"epoch": 1.4465659572078395,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00048008242090467803,
|
|
"loss": 5.4779,
|
|
"mean_token_accuracy": 0.1786105677485466,
|
|
"num_tokens": 28722521.0,
|
|
"step": 12880
|
|
},
|
|
{
|
|
"entropy": 5.579559087753296,
|
|
"epoch": 1.4471275341157972,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004800659024603923,
|
|
"loss": 5.422,
|
|
"mean_token_accuracy": 0.18361022770404817,
|
|
"num_tokens": 28733293.0,
|
|
"step": 12885
|
|
},
|
|
{
|
|
"entropy": 5.630140066146851,
|
|
"epoch": 1.4476891110237546,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00048004937748672864,
|
|
"loss": 5.4078,
|
|
"mean_token_accuracy": 0.18235597312450408,
|
|
"num_tokens": 28744351.0,
|
|
"step": 12890
|
|
},
|
|
{
|
|
"entropy": 5.592684125900268,
|
|
"epoch": 1.4482506879317123,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00048003284598421327,
|
|
"loss": 5.347,
|
|
"mean_token_accuracy": 0.17893218547105788,
|
|
"num_tokens": 28755140.0,
|
|
"step": 12895
|
|
},
|
|
{
|
|
"entropy": 5.5412681102752686,
|
|
"epoch": 1.4488122648396697,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004800163079533726,
|
|
"loss": 5.4643,
|
|
"mean_token_accuracy": 0.1798962414264679,
|
|
"num_tokens": 28767161.0,
|
|
"step": 12900
|
|
},
|
|
{
|
|
"entropy": 5.583915328979492,
|
|
"epoch": 1.4493738417476274,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004799997633947332,
|
|
"loss": 5.4035,
|
|
"mean_token_accuracy": 0.18006214052438735,
|
|
"num_tokens": 28779501.0,
|
|
"step": 12905
|
|
},
|
|
{
|
|
"entropy": 5.656120872497558,
|
|
"epoch": 1.4499354186555848,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.00047998321230882174,
|
|
"loss": 5.5706,
|
|
"mean_token_accuracy": 0.17843035608530045,
|
|
"num_tokens": 28792021.0,
|
|
"step": 12910
|
|
},
|
|
{
|
|
"entropy": 5.5608038902282715,
|
|
"epoch": 1.4504969955635425,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.00047996665469616536,
|
|
"loss": 5.3407,
|
|
"mean_token_accuracy": 0.18791882395744325,
|
|
"num_tokens": 28802445.0,
|
|
"step": 12915
|
|
},
|
|
{
|
|
"entropy": 5.532950925827026,
|
|
"epoch": 1.4510585724715,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.00047995009055729114,
|
|
"loss": 5.3515,
|
|
"mean_token_accuracy": 0.17671438902616501,
|
|
"num_tokens": 28813821.0,
|
|
"step": 12920
|
|
},
|
|
{
|
|
"entropy": 5.575395822525024,
|
|
"epoch": 1.4516201493794574,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004799335198927266,
|
|
"loss": 5.4052,
|
|
"mean_token_accuracy": 0.18110319525003432,
|
|
"num_tokens": 28824764.0,
|
|
"step": 12925
|
|
},
|
|
{
|
|
"entropy": 5.645011758804321,
|
|
"epoch": 1.452181726287415,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004799169427029993,
|
|
"loss": 5.4385,
|
|
"mean_token_accuracy": 0.18372306376695632,
|
|
"num_tokens": 28836720.0,
|
|
"step": 12930
|
|
},
|
|
{
|
|
"entropy": 5.567357015609741,
|
|
"epoch": 1.4527433031953727,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.00047990035898863706,
|
|
"loss": 5.3383,
|
|
"mean_token_accuracy": 0.18835611790418624,
|
|
"num_tokens": 28848846.0,
|
|
"step": 12935
|
|
},
|
|
{
|
|
"entropy": 5.512576341629028,
|
|
"epoch": 1.4533048801033301,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004798837687501679,
|
|
"loss": 5.368,
|
|
"mean_token_accuracy": 0.1866194039583206,
|
|
"num_tokens": 28859453.0,
|
|
"step": 12940
|
|
},
|
|
{
|
|
"entropy": 5.541036367416382,
|
|
"epoch": 1.4538664570112876,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004798671719881201,
|
|
"loss": 5.4521,
|
|
"mean_token_accuracy": 0.1791348472237587,
|
|
"num_tokens": 28869447.0,
|
|
"step": 12945
|
|
},
|
|
{
|
|
"entropy": 5.652652931213379,
|
|
"epoch": 1.4544280339192452,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004798505687030221,
|
|
"loss": 5.4959,
|
|
"mean_token_accuracy": 0.18058837205171585,
|
|
"num_tokens": 28881660.0,
|
|
"step": 12950
|
|
},
|
|
{
|
|
"entropy": 5.6639848232269285,
|
|
"epoch": 1.454989610827203,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004798339588954025,
|
|
"loss": 5.4952,
|
|
"mean_token_accuracy": 0.1759917840361595,
|
|
"num_tokens": 28893128.0,
|
|
"step": 12955
|
|
},
|
|
{
|
|
"entropy": 5.5727091312408445,
|
|
"epoch": 1.4555511877351603,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004798173425657903,
|
|
"loss": 5.4054,
|
|
"mean_token_accuracy": 0.1861330583691597,
|
|
"num_tokens": 28904323.0,
|
|
"step": 12960
|
|
},
|
|
{
|
|
"entropy": 5.6069197177886965,
|
|
"epoch": 1.4561127646431178,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.0004798007197147144,
|
|
"loss": 5.4407,
|
|
"mean_token_accuracy": 0.18523162007331848,
|
|
"num_tokens": 28915672.0,
|
|
"step": 12965
|
|
},
|
|
{
|
|
"entropy": 5.73742413520813,
|
|
"epoch": 1.4566743415510754,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.0004797840903427042,
|
|
"loss": 5.5245,
|
|
"mean_token_accuracy": 0.1795831501483917,
|
|
"num_tokens": 28926657.0,
|
|
"step": 12970
|
|
},
|
|
{
|
|
"entropy": 5.563154983520508,
|
|
"epoch": 1.4572359184590329,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.00047976745445028906,
|
|
"loss": 5.3409,
|
|
"mean_token_accuracy": 0.18444264233112334,
|
|
"num_tokens": 28938787.0,
|
|
"step": 12975
|
|
},
|
|
{
|
|
"entropy": 5.519552993774414,
|
|
"epoch": 1.4577974953669905,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.00047975081203799883,
|
|
"loss": 5.4254,
|
|
"mean_token_accuracy": 0.18172381669282914,
|
|
"num_tokens": 28949836.0,
|
|
"step": 12980
|
|
},
|
|
{
|
|
"entropy": 5.532623434066773,
|
|
"epoch": 1.458359072274948,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00047973416310636327,
|
|
"loss": 5.3584,
|
|
"mean_token_accuracy": 0.18170606344938278,
|
|
"num_tokens": 28960053.0,
|
|
"step": 12985
|
|
},
|
|
{
|
|
"entropy": 5.6591089248657225,
|
|
"epoch": 1.4589206491829056,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004797175076559126,
|
|
"loss": 5.5321,
|
|
"mean_token_accuracy": 0.18378119617700578,
|
|
"num_tokens": 28972698.0,
|
|
"step": 12990
|
|
},
|
|
{
|
|
"entropy": 5.645683240890503,
|
|
"epoch": 1.459482226090863,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.00047970084568717703,
|
|
"loss": 5.5249,
|
|
"mean_token_accuracy": 0.18232111632823944,
|
|
"num_tokens": 28984756.0,
|
|
"step": 12995
|
|
},
|
|
{
|
|
"entropy": 5.6243682384490965,
|
|
"epoch": 1.4600438029988208,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004796841772006872,
|
|
"loss": 5.4459,
|
|
"mean_token_accuracy": 0.17344191670417786,
|
|
"num_tokens": 28996915.0,
|
|
"step": 13000
|
|
},
|
|
{
|
|
"entropy": 5.540755319595337,
|
|
"epoch": 1.4606053799067782,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.00047966750219697376,
|
|
"loss": 5.3666,
|
|
"mean_token_accuracy": 0.18296120762825013,
|
|
"num_tokens": 29007462.0,
|
|
"step": 13005
|
|
},
|
|
{
|
|
"entropy": 5.591592836380005,
|
|
"epoch": 1.4611669568147359,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004796508206765677,
|
|
"loss": 5.4545,
|
|
"mean_token_accuracy": 0.18116957396268846,
|
|
"num_tokens": 29017790.0,
|
|
"step": 13010
|
|
},
|
|
{
|
|
"entropy": 5.630393075942993,
|
|
"epoch": 1.4617285337226933,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00047963413264000005,
|
|
"loss": 5.5117,
|
|
"mean_token_accuracy": 0.18219025880098344,
|
|
"num_tokens": 29029536.0,
|
|
"step": 13015
|
|
},
|
|
{
|
|
"entropy": 5.560514307022094,
|
|
"epoch": 1.4622901106306507,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004796174380878023,
|
|
"loss": 5.3121,
|
|
"mean_token_accuracy": 0.18617115467786788,
|
|
"num_tokens": 29039840.0,
|
|
"step": 13020
|
|
},
|
|
{
|
|
"entropy": 5.667528057098389,
|
|
"epoch": 1.4628516875386084,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.000479600737020506,
|
|
"loss": 5.4887,
|
|
"mean_token_accuracy": 0.17511072009801865,
|
|
"num_tokens": 29052769.0,
|
|
"step": 13025
|
|
},
|
|
{
|
|
"entropy": 5.5814313888549805,
|
|
"epoch": 1.463413264446566,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.0004795840294386429,
|
|
"loss": 5.3535,
|
|
"mean_token_accuracy": 0.1846114620566368,
|
|
"num_tokens": 29063645.0,
|
|
"step": 13030
|
|
},
|
|
{
|
|
"entropy": 5.602754878997803,
|
|
"epoch": 1.4639748413545235,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.00047956731534274483,
|
|
"loss": 5.4582,
|
|
"mean_token_accuracy": 0.17893723547458648,
|
|
"num_tokens": 29075241.0,
|
|
"step": 13035
|
|
},
|
|
{
|
|
"entropy": 5.6240301609039305,
|
|
"epoch": 1.464536418262481,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.00047955059473334425,
|
|
"loss": 5.4224,
|
|
"mean_token_accuracy": 0.1843517988920212,
|
|
"num_tokens": 29087592.0,
|
|
"step": 13040
|
|
},
|
|
{
|
|
"entropy": 5.545098924636841,
|
|
"epoch": 1.4650979951704386,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004795338676109733,
|
|
"loss": 5.391,
|
|
"mean_token_accuracy": 0.18238293528556823,
|
|
"num_tokens": 29099314.0,
|
|
"step": 13045
|
|
},
|
|
{
|
|
"entropy": 5.586019706726074,
|
|
"epoch": 1.4656595720783963,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004795171339761647,
|
|
"loss": 5.4493,
|
|
"mean_token_accuracy": 0.1814487487077713,
|
|
"num_tokens": 29111916.0,
|
|
"step": 13050
|
|
},
|
|
{
|
|
"entropy": 5.6290851593017575,
|
|
"epoch": 1.4662211489863537,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00047950039382945126,
|
|
"loss": 5.4251,
|
|
"mean_token_accuracy": 0.18521298468112946,
|
|
"num_tokens": 29122871.0,
|
|
"step": 13055
|
|
},
|
|
{
|
|
"entropy": 5.560302591323852,
|
|
"epoch": 1.4667827258943111,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.00047948364717136587,
|
|
"loss": 5.4137,
|
|
"mean_token_accuracy": 0.18072257339954376,
|
|
"num_tokens": 29133873.0,
|
|
"step": 13060
|
|
},
|
|
{
|
|
"entropy": 5.498769521713257,
|
|
"epoch": 1.4673443028022688,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00047946689400244196,
|
|
"loss": 5.3212,
|
|
"mean_token_accuracy": 0.18523789048194886,
|
|
"num_tokens": 29144995.0,
|
|
"step": 13065
|
|
},
|
|
{
|
|
"entropy": 5.644399929046631,
|
|
"epoch": 1.4679058797102262,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.00047945013432321284,
|
|
"loss": 5.4945,
|
|
"mean_token_accuracy": 0.17930782586336136,
|
|
"num_tokens": 29156801.0,
|
|
"step": 13070
|
|
},
|
|
{
|
|
"entropy": 5.604148054122925,
|
|
"epoch": 1.468467456618184,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.00047943336813421205,
|
|
"loss": 5.5131,
|
|
"mean_token_accuracy": 0.17270220518112184,
|
|
"num_tokens": 29168072.0,
|
|
"step": 13075
|
|
},
|
|
{
|
|
"entropy": 5.550663137435913,
|
|
"epoch": 1.4690290335261413,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004794165954359736,
|
|
"loss": 5.3695,
|
|
"mean_token_accuracy": 0.18234278857707978,
|
|
"num_tokens": 29179314.0,
|
|
"step": 13080
|
|
},
|
|
{
|
|
"entropy": 5.630499362945557,
|
|
"epoch": 1.469590610434099,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004793998162290315,
|
|
"loss": 5.4712,
|
|
"mean_token_accuracy": 0.17594666928052902,
|
|
"num_tokens": 29190808.0,
|
|
"step": 13085
|
|
},
|
|
{
|
|
"entropy": 5.7291069507598875,
|
|
"epoch": 1.4701521873420564,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004793830305139199,
|
|
"loss": 5.5508,
|
|
"mean_token_accuracy": 0.17875656634569168,
|
|
"num_tokens": 29202557.0,
|
|
"step": 13090
|
|
},
|
|
{
|
|
"entropy": 5.5481040477752686,
|
|
"epoch": 1.470713764250014,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004793662382911734,
|
|
"loss": 5.3192,
|
|
"mean_token_accuracy": 0.19619740098714827,
|
|
"num_tokens": 29213959.0,
|
|
"step": 13095
|
|
},
|
|
{
|
|
"entropy": 5.595314407348633,
|
|
"epoch": 1.4712753411579715,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004793494395613265,
|
|
"loss": 5.4464,
|
|
"mean_token_accuracy": 0.1871610775589943,
|
|
"num_tokens": 29226069.0,
|
|
"step": 13100
|
|
},
|
|
{
|
|
"entropy": 5.649613761901856,
|
|
"epoch": 1.4718369180659292,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004793326343249144,
|
|
"loss": 5.4764,
|
|
"mean_token_accuracy": 0.17758978456258773,
|
|
"num_tokens": 29237882.0,
|
|
"step": 13105
|
|
},
|
|
{
|
|
"entropy": 5.53978533744812,
|
|
"epoch": 1.4723984949738866,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.0004793158225824718,
|
|
"loss": 5.4077,
|
|
"mean_token_accuracy": 0.19019132256507873,
|
|
"num_tokens": 29248642.0,
|
|
"step": 13110
|
|
},
|
|
{
|
|
"entropy": 5.496613502502441,
|
|
"epoch": 1.4729600718818443,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.00047929900433453423,
|
|
"loss": 5.3945,
|
|
"mean_token_accuracy": 0.18171194493770598,
|
|
"num_tokens": 29260632.0,
|
|
"step": 13115
|
|
},
|
|
{
|
|
"entropy": 5.694778394699097,
|
|
"epoch": 1.4735216487898017,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00047928217958163703,
|
|
"loss": 5.5104,
|
|
"mean_token_accuracy": 0.18265950977802276,
|
|
"num_tokens": 29272563.0,
|
|
"step": 13120
|
|
},
|
|
{
|
|
"entropy": 5.673144721984864,
|
|
"epoch": 1.4740832256977594,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00047926534832431615,
|
|
"loss": 5.477,
|
|
"mean_token_accuracy": 0.18252675831317902,
|
|
"num_tokens": 29284307.0,
|
|
"step": 13125
|
|
},
|
|
{
|
|
"entropy": 5.536691761016845,
|
|
"epoch": 1.4746448026057168,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004792485105631073,
|
|
"loss": 5.3236,
|
|
"mean_token_accuracy": 0.18838772028684617,
|
|
"num_tokens": 29295413.0,
|
|
"step": 13130
|
|
},
|
|
{
|
|
"entropy": 5.6502501487731935,
|
|
"epoch": 1.4752063795136743,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.0004792316662985467,
|
|
"loss": 5.4561,
|
|
"mean_token_accuracy": 0.18947436511516572,
|
|
"num_tokens": 29306612.0,
|
|
"step": 13135
|
|
},
|
|
{
|
|
"entropy": 5.562028217315674,
|
|
"epoch": 1.475767956421632,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.00047921481553117053,
|
|
"loss": 5.3896,
|
|
"mean_token_accuracy": 0.18733631670475007,
|
|
"num_tokens": 29316168.0,
|
|
"step": 13140
|
|
},
|
|
{
|
|
"entropy": 5.562285995483398,
|
|
"epoch": 1.4763295333295896,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00047919795826151544,
|
|
"loss": 5.5198,
|
|
"mean_token_accuracy": 0.1820887580513954,
|
|
"num_tokens": 29326949.0,
|
|
"step": 13145
|
|
},
|
|
{
|
|
"entropy": 5.575417566299438,
|
|
"epoch": 1.476891110237547,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.0004791810944901183,
|
|
"loss": 5.3574,
|
|
"mean_token_accuracy": 0.17930267602205277,
|
|
"num_tokens": 29336744.0,
|
|
"step": 13150
|
|
},
|
|
{
|
|
"entropy": 5.6073588848114015,
|
|
"epoch": 1.4774526871455045,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004791642242175158,
|
|
"loss": 5.384,
|
|
"mean_token_accuracy": 0.18314199000597,
|
|
"num_tokens": 29346964.0,
|
|
"step": 13155
|
|
},
|
|
{
|
|
"entropy": 5.590050077438354,
|
|
"epoch": 1.4780142640534621,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00047914734744424517,
|
|
"loss": 5.4227,
|
|
"mean_token_accuracy": 0.18171590864658355,
|
|
"num_tokens": 29358689.0,
|
|
"step": 13160
|
|
},
|
|
{
|
|
"entropy": 5.576000499725342,
|
|
"epoch": 1.4785758409614196,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00047913046417084393,
|
|
"loss": 5.4339,
|
|
"mean_token_accuracy": 0.1828928828239441,
|
|
"num_tokens": 29371243.0,
|
|
"step": 13165
|
|
},
|
|
{
|
|
"entropy": 5.574913835525512,
|
|
"epoch": 1.4791374178693772,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00047911357439784947,
|
|
"loss": 5.434,
|
|
"mean_token_accuracy": 0.18351355493068694,
|
|
"num_tokens": 29383185.0,
|
|
"step": 13170
|
|
},
|
|
{
|
|
"entropy": 5.481876945495605,
|
|
"epoch": 1.4796989947773347,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.00047909667812579964,
|
|
"loss": 5.2203,
|
|
"mean_token_accuracy": 0.1933044970035553,
|
|
"num_tokens": 29393986.0,
|
|
"step": 13175
|
|
},
|
|
{
|
|
"entropy": 5.500658226013184,
|
|
"epoch": 1.4802605716852923,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00047907977535523253,
|
|
"loss": 5.4469,
|
|
"mean_token_accuracy": 0.18550995141267776,
|
|
"num_tokens": 29405407.0,
|
|
"step": 13180
|
|
},
|
|
{
|
|
"entropy": 5.555845069885254,
|
|
"epoch": 1.4808221485932498,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004790628660866861,
|
|
"loss": 5.3541,
|
|
"mean_token_accuracy": 0.18297166675329207,
|
|
"num_tokens": 29416352.0,
|
|
"step": 13185
|
|
},
|
|
{
|
|
"entropy": 5.556106805801392,
|
|
"epoch": 1.4813837255012074,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004790459503206989,
|
|
"loss": 5.2981,
|
|
"mean_token_accuracy": 0.18662861436605455,
|
|
"num_tokens": 29428369.0,
|
|
"step": 13190
|
|
},
|
|
{
|
|
"entropy": 5.486964416503906,
|
|
"epoch": 1.4819453024091649,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004790290280578095,
|
|
"loss": 5.3957,
|
|
"mean_token_accuracy": 0.18780310004949569,
|
|
"num_tokens": 29439276.0,
|
|
"step": 13195
|
|
},
|
|
{
|
|
"entropy": 5.645100069046021,
|
|
"epoch": 1.4825068793171226,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00047901209929855675,
|
|
"loss": 5.4164,
|
|
"mean_token_accuracy": 0.18187098652124406,
|
|
"num_tokens": 29451361.0,
|
|
"step": 13200
|
|
},
|
|
{
|
|
"entropy": 5.531702375411987,
|
|
"epoch": 1.48306845622508,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004789951640434796,
|
|
"loss": 5.4417,
|
|
"mean_token_accuracy": 0.18351416289806366,
|
|
"num_tokens": 29462977.0,
|
|
"step": 13205
|
|
},
|
|
{
|
|
"entropy": 5.537817907333374,
|
|
"epoch": 1.4836300331330377,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004789782222931173,
|
|
"loss": 5.3729,
|
|
"mean_token_accuracy": 0.1877996265888214,
|
|
"num_tokens": 29474641.0,
|
|
"step": 13210
|
|
},
|
|
{
|
|
"entropy": 5.55263385772705,
|
|
"epoch": 1.484191610040995,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.00047896127404800935,
|
|
"loss": 5.2718,
|
|
"mean_token_accuracy": 0.1885400354862213,
|
|
"num_tokens": 29485560.0,
|
|
"step": 13215
|
|
},
|
|
{
|
|
"entropy": 5.521211004257202,
|
|
"epoch": 1.4847531869489528,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004789443193086953,
|
|
"loss": 5.3831,
|
|
"mean_token_accuracy": 0.18604848980903627,
|
|
"num_tokens": 29495872.0,
|
|
"step": 13220
|
|
},
|
|
{
|
|
"entropy": 5.511582851409912,
|
|
"epoch": 1.4853147638569102,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00047892735807571505,
|
|
"loss": 5.3327,
|
|
"mean_token_accuracy": 0.1902692899107933,
|
|
"num_tokens": 29506704.0,
|
|
"step": 13225
|
|
},
|
|
{
|
|
"entropy": 5.564581727981567,
|
|
"epoch": 1.4858763407648676,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004789103903496086,
|
|
"loss": 5.3683,
|
|
"mean_token_accuracy": 0.18327164202928542,
|
|
"num_tokens": 29518226.0,
|
|
"step": 13230
|
|
},
|
|
{
|
|
"entropy": 5.5849768161773685,
|
|
"epoch": 1.4864379176728253,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004788934161309161,
|
|
"loss": 5.3296,
|
|
"mean_token_accuracy": 0.19128019660711287,
|
|
"num_tokens": 29529176.0,
|
|
"step": 13235
|
|
},
|
|
{
|
|
"entropy": 5.470476198196411,
|
|
"epoch": 1.486999494580783,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.00047887643542017836,
|
|
"loss": 5.2218,
|
|
"mean_token_accuracy": 0.18971727937459945,
|
|
"num_tokens": 29539268.0,
|
|
"step": 13240
|
|
},
|
|
{
|
|
"entropy": 5.569934368133545,
|
|
"epoch": 1.4875610714887404,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00047885944821793574,
|
|
"loss": 5.5137,
|
|
"mean_token_accuracy": 0.1754368558526039,
|
|
"num_tokens": 29550491.0,
|
|
"step": 13245
|
|
},
|
|
{
|
|
"entropy": 5.50352201461792,
|
|
"epoch": 1.4881226483966978,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.00047884245452472926,
|
|
"loss": 5.3284,
|
|
"mean_token_accuracy": 0.1866819903254509,
|
|
"num_tokens": 29561520.0,
|
|
"step": 13250
|
|
},
|
|
{
|
|
"entropy": 5.517250204086304,
|
|
"epoch": 1.4886842253046555,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004788254543410999,
|
|
"loss": 5.3886,
|
|
"mean_token_accuracy": 0.18395980447530746,
|
|
"num_tokens": 29573974.0,
|
|
"step": 13255
|
|
},
|
|
{
|
|
"entropy": 5.493844413757325,
|
|
"epoch": 1.489245802212613,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.00047880844766758914,
|
|
"loss": 5.2992,
|
|
"mean_token_accuracy": 0.19390214681625367,
|
|
"num_tokens": 29584059.0,
|
|
"step": 13260
|
|
},
|
|
{
|
|
"entropy": 5.647783708572388,
|
|
"epoch": 1.4898073791205706,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.00047879143450473824,
|
|
"loss": 5.5231,
|
|
"mean_token_accuracy": 0.1793433427810669,
|
|
"num_tokens": 29595726.0,
|
|
"step": 13265
|
|
},
|
|
{
|
|
"entropy": 5.555963134765625,
|
|
"epoch": 1.490368956028528,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.00047877441485308917,
|
|
"loss": 5.4138,
|
|
"mean_token_accuracy": 0.18182573169469834,
|
|
"num_tokens": 29607354.0,
|
|
"step": 13270
|
|
},
|
|
{
|
|
"entropy": 5.549566316604614,
|
|
"epoch": 1.4909305329364857,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.00047875738871318356,
|
|
"loss": 5.3485,
|
|
"mean_token_accuracy": 0.18683600872755052,
|
|
"num_tokens": 29618698.0,
|
|
"step": 13275
|
|
},
|
|
{
|
|
"entropy": 5.464523887634277,
|
|
"epoch": 1.4914921098444431,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004787403560855637,
|
|
"loss": 5.3188,
|
|
"mean_token_accuracy": 0.18717088401317597,
|
|
"num_tokens": 29629578.0,
|
|
"step": 13280
|
|
},
|
|
{
|
|
"entropy": 5.492139101028442,
|
|
"epoch": 1.4920536867524008,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004787233169707719,
|
|
"loss": 5.1961,
|
|
"mean_token_accuracy": 0.19385868310928345,
|
|
"num_tokens": 29640277.0,
|
|
"step": 13285
|
|
},
|
|
{
|
|
"entropy": 5.497411632537842,
|
|
"epoch": 1.4926152636603582,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004787062713693507,
|
|
"loss": 5.4392,
|
|
"mean_token_accuracy": 0.18391389548778533,
|
|
"num_tokens": 29652029.0,
|
|
"step": 13290
|
|
},
|
|
{
|
|
"entropy": 5.581491851806641,
|
|
"epoch": 1.493176840568316,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.00047868921928184276,
|
|
"loss": 5.4319,
|
|
"mean_token_accuracy": 0.18335914015769958,
|
|
"num_tokens": 29663191.0,
|
|
"step": 13295
|
|
},
|
|
{
|
|
"entropy": 5.638195371627807,
|
|
"epoch": 1.4937384174762733,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.0004786721607087911,
|
|
"loss": 5.4582,
|
|
"mean_token_accuracy": 0.17531873881816865,
|
|
"num_tokens": 29674238.0,
|
|
"step": 13300
|
|
},
|
|
{
|
|
"entropy": 5.566009187698365,
|
|
"epoch": 1.494299994384231,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004786550956507389,
|
|
"loss": 5.3684,
|
|
"mean_token_accuracy": 0.18569211661815643,
|
|
"num_tokens": 29687255.0,
|
|
"step": 13305
|
|
},
|
|
{
|
|
"entropy": 5.474252653121948,
|
|
"epoch": 1.4948615712921884,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004786380241082294,
|
|
"loss": 5.3085,
|
|
"mean_token_accuracy": 0.18408209681510926,
|
|
"num_tokens": 29699769.0,
|
|
"step": 13310
|
|
},
|
|
{
|
|
"entropy": 5.601528692245483,
|
|
"epoch": 1.495423148200146,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00047862094608180623,
|
|
"loss": 5.4829,
|
|
"mean_token_accuracy": 0.17950135916471482,
|
|
"num_tokens": 29710281.0,
|
|
"step": 13315
|
|
},
|
|
{
|
|
"entropy": 5.551890897750854,
|
|
"epoch": 1.4959847251081035,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004786038615720132,
|
|
"loss": 5.2745,
|
|
"mean_token_accuracy": 0.1837810605764389,
|
|
"num_tokens": 29720647.0,
|
|
"step": 13320
|
|
},
|
|
{
|
|
"entropy": 5.549169540405273,
|
|
"epoch": 1.496546302016061,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00047858677057939427,
|
|
"loss": 5.4406,
|
|
"mean_token_accuracy": 0.1845221921801567,
|
|
"num_tokens": 29731565.0,
|
|
"step": 13325
|
|
},
|
|
{
|
|
"entropy": 5.552046060562134,
|
|
"epoch": 1.4971078789240186,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.00047856967310449356,
|
|
"loss": 5.3408,
|
|
"mean_token_accuracy": 0.18324533998966216,
|
|
"num_tokens": 29743361.0,
|
|
"step": 13330
|
|
},
|
|
{
|
|
"entropy": 5.5653197288513185,
|
|
"epoch": 1.4976694558319763,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00047855256914785556,
|
|
"loss": 5.3985,
|
|
"mean_token_accuracy": 0.18504771292209626,
|
|
"num_tokens": 29754799.0,
|
|
"step": 13335
|
|
},
|
|
{
|
|
"entropy": 5.57679591178894,
|
|
"epoch": 1.4982310327399337,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.00047853545871002476,
|
|
"loss": 5.5172,
|
|
"mean_token_accuracy": 0.18125257045030593,
|
|
"num_tokens": 29766401.0,
|
|
"step": 13340
|
|
},
|
|
{
|
|
"entropy": 5.487023830413818,
|
|
"epoch": 1.4987926096478912,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00047851834179154595,
|
|
"loss": 5.2762,
|
|
"mean_token_accuracy": 0.19227621853351592,
|
|
"num_tokens": 29778268.0,
|
|
"step": 13345
|
|
},
|
|
{
|
|
"entropy": 5.4932716369628904,
|
|
"epoch": 1.4993541865558488,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004785012183929643,
|
|
"loss": 5.3409,
|
|
"mean_token_accuracy": 0.1875157192349434,
|
|
"num_tokens": 29788551.0,
|
|
"step": 13350
|
|
},
|
|
{
|
|
"entropy": 5.5828437328338625,
|
|
"epoch": 1.4999157634638065,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004784840885148249,
|
|
"loss": 5.3323,
|
|
"mean_token_accuracy": 0.1854691818356514,
|
|
"num_tokens": 29799726.0,
|
|
"step": 13355
|
|
},
|
|
{
|
|
"entropy": 5.564011764526367,
|
|
"epoch": 1.500477340371764,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004784669521576732,
|
|
"loss": 5.4717,
|
|
"mean_token_accuracy": 0.1789710581302643,
|
|
"num_tokens": 29810615.0,
|
|
"step": 13360
|
|
},
|
|
{
|
|
"entropy": 5.5941304683685305,
|
|
"epoch": 1.5010389172797214,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004784498093220549,
|
|
"loss": 5.3797,
|
|
"mean_token_accuracy": 0.18280550539493562,
|
|
"num_tokens": 29821766.0,
|
|
"step": 13365
|
|
},
|
|
{
|
|
"entropy": 5.513896894454956,
|
|
"epoch": 1.501600494187679,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004784326600085157,
|
|
"loss": 5.4186,
|
|
"mean_token_accuracy": 0.18026091903448105,
|
|
"num_tokens": 29833724.0,
|
|
"step": 13370
|
|
},
|
|
{
|
|
"entropy": 5.505526065826416,
|
|
"epoch": 1.5021620710956367,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.00047841550421760164,
|
|
"loss": 5.3227,
|
|
"mean_token_accuracy": 0.18708880245685577,
|
|
"num_tokens": 29845057.0,
|
|
"step": 13375
|
|
},
|
|
{
|
|
"entropy": 5.651104593276978,
|
|
"epoch": 1.502723648003594,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.00047839834194985916,
|
|
"loss": 5.4529,
|
|
"mean_token_accuracy": 0.18251316100358964,
|
|
"num_tokens": 29855649.0,
|
|
"step": 13380
|
|
},
|
|
{
|
|
"entropy": 5.469983243942261,
|
|
"epoch": 1.5032852249115516,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004783811732058345,
|
|
"loss": 5.274,
|
|
"mean_token_accuracy": 0.18951803594827651,
|
|
"num_tokens": 29866873.0,
|
|
"step": 13385
|
|
},
|
|
{
|
|
"entropy": 5.519393491744995,
|
|
"epoch": 1.5038468018195092,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.00047836399798607446,
|
|
"loss": 5.331,
|
|
"mean_token_accuracy": 0.18913227319717407,
|
|
"num_tokens": 29877690.0,
|
|
"step": 13390
|
|
},
|
|
{
|
|
"entropy": 5.528921747207642,
|
|
"epoch": 1.5044083787274667,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00047834681629112583,
|
|
"loss": 5.3901,
|
|
"mean_token_accuracy": 0.19536549896001815,
|
|
"num_tokens": 29888461.0,
|
|
"step": 13395
|
|
},
|
|
{
|
|
"entropy": 5.482246589660645,
|
|
"epoch": 1.5049699556354241,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004783296281215357,
|
|
"loss": 5.3671,
|
|
"mean_token_accuracy": 0.1873343139886856,
|
|
"num_tokens": 29900559.0,
|
|
"step": 13400
|
|
},
|
|
{
|
|
"entropy": 5.457982730865479,
|
|
"epoch": 1.5055315325433818,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004783124334778513,
|
|
"loss": 5.2906,
|
|
"mean_token_accuracy": 0.19076751917600632,
|
|
"num_tokens": 29910815.0,
|
|
"step": 13405
|
|
},
|
|
{
|
|
"entropy": 5.6054411888122555,
|
|
"epoch": 1.5060931094513395,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004782952323606202,
|
|
"loss": 5.532,
|
|
"mean_token_accuracy": 0.18430778980255128,
|
|
"num_tokens": 29923262.0,
|
|
"step": 13410
|
|
},
|
|
{
|
|
"entropy": 5.541047430038452,
|
|
"epoch": 1.506654686359297,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004782780247703901,
|
|
"loss": 5.3602,
|
|
"mean_token_accuracy": 0.18784934133291245,
|
|
"num_tokens": 29934744.0,
|
|
"step": 13415
|
|
},
|
|
{
|
|
"entropy": 5.644116735458374,
|
|
"epoch": 1.5072162632672543,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004782608107077088,
|
|
"loss": 5.5336,
|
|
"mean_token_accuracy": 0.17931553572416306,
|
|
"num_tokens": 29945828.0,
|
|
"step": 13420
|
|
},
|
|
{
|
|
"entropy": 5.485628843307495,
|
|
"epoch": 1.507777840175212,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.00047824359017312445,
|
|
"loss": 5.3171,
|
|
"mean_token_accuracy": 0.1859288841485977,
|
|
"num_tokens": 29956964.0,
|
|
"step": 13425
|
|
},
|
|
{
|
|
"entropy": 5.5612828731536865,
|
|
"epoch": 1.5083394170831697,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004782263631671854,
|
|
"loss": 5.3824,
|
|
"mean_token_accuracy": 0.1855710193514824,
|
|
"num_tokens": 29968004.0,
|
|
"step": 13430
|
|
},
|
|
{
|
|
"entropy": 5.571560430526733,
|
|
"epoch": 1.508900993991127,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.00047820912969044014,
|
|
"loss": 5.3444,
|
|
"mean_token_accuracy": 0.189272677898407,
|
|
"num_tokens": 29978237.0,
|
|
"step": 13435
|
|
},
|
|
{
|
|
"entropy": 5.493322277069092,
|
|
"epoch": 1.5094625708990845,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.00047819188974343734,
|
|
"loss": 5.4205,
|
|
"mean_token_accuracy": 0.17970777153968812,
|
|
"num_tokens": 29988379.0,
|
|
"step": 13440
|
|
},
|
|
{
|
|
"entropy": 5.5735115051269535,
|
|
"epoch": 1.5100241478070422,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004781746433267259,
|
|
"loss": 5.4585,
|
|
"mean_token_accuracy": 0.18298395723104477,
|
|
"num_tokens": 29999024.0,
|
|
"step": 13445
|
|
},
|
|
{
|
|
"entropy": 5.618076181411743,
|
|
"epoch": 1.5105857247149999,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.00047815739044085515,
|
|
"loss": 5.3546,
|
|
"mean_token_accuracy": 0.18803201615810394,
|
|
"num_tokens": 30009411.0,
|
|
"step": 13450
|
|
},
|
|
{
|
|
"entropy": 5.50294942855835,
|
|
"epoch": 1.5111473016229573,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00047814013108637423,
|
|
"loss": 5.3741,
|
|
"mean_token_accuracy": 0.18963730782270433,
|
|
"num_tokens": 30020746.0,
|
|
"step": 13455
|
|
},
|
|
{
|
|
"entropy": 5.566942977905273,
|
|
"epoch": 1.5117088785309147,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00047812286526383274,
|
|
"loss": 5.3481,
|
|
"mean_token_accuracy": 0.18417930454015732,
|
|
"num_tokens": 30032568.0,
|
|
"step": 13460
|
|
},
|
|
{
|
|
"entropy": 5.58520917892456,
|
|
"epoch": 1.5122704554388724,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004781055929737804,
|
|
"loss": 5.4001,
|
|
"mean_token_accuracy": 0.18209205716848373,
|
|
"num_tokens": 30042772.0,
|
|
"step": 13465
|
|
},
|
|
{
|
|
"entropy": 5.557912015914917,
|
|
"epoch": 1.51283203234683,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.00047808831421676724,
|
|
"loss": 5.4403,
|
|
"mean_token_accuracy": 0.1883595496416092,
|
|
"num_tokens": 30053842.0,
|
|
"step": 13470
|
|
},
|
|
{
|
|
"entropy": 5.63917121887207,
|
|
"epoch": 1.5133936092547875,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004780710289933435,
|
|
"loss": 5.4059,
|
|
"mean_token_accuracy": 0.1867174282670021,
|
|
"num_tokens": 30064744.0,
|
|
"step": 13475
|
|
},
|
|
{
|
|
"entropy": 5.541257667541504,
|
|
"epoch": 1.513955186162745,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004780537373040593,
|
|
"loss": 5.3928,
|
|
"mean_token_accuracy": 0.1826452910900116,
|
|
"num_tokens": 30075475.0,
|
|
"step": 13480
|
|
},
|
|
{
|
|
"entropy": 5.565896034240723,
|
|
"epoch": 1.5145167630707026,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.00047803643914946537,
|
|
"loss": 5.3805,
|
|
"mean_token_accuracy": 0.18455331176519393,
|
|
"num_tokens": 30087189.0,
|
|
"step": 13485
|
|
},
|
|
{
|
|
"entropy": 5.576182174682617,
|
|
"epoch": 1.51507833997866,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004780191345301125,
|
|
"loss": 5.4967,
|
|
"mean_token_accuracy": 0.17630792707204818,
|
|
"num_tokens": 30099263.0,
|
|
"step": 13490
|
|
},
|
|
{
|
|
"entropy": 5.564552450180054,
|
|
"epoch": 1.5156399168866175,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00047800182344655165,
|
|
"loss": 5.417,
|
|
"mean_token_accuracy": 0.18011668920516968,
|
|
"num_tokens": 30110925.0,
|
|
"step": 13495
|
|
},
|
|
{
|
|
"entropy": 5.598606777191162,
|
|
"epoch": 1.5162014937945751,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000477984505899334,
|
|
"loss": 5.4129,
|
|
"mean_token_accuracy": 0.17879739701747893,
|
|
"num_tokens": 30122708.0,
|
|
"step": 13500
|
|
},
|
|
{
|
|
"entropy": 5.53363790512085,
|
|
"epoch": 1.5167630707025328,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00047796718188901095,
|
|
"loss": 5.2992,
|
|
"mean_token_accuracy": 0.18720662593841553,
|
|
"num_tokens": 30133624.0,
|
|
"step": 13505
|
|
},
|
|
{
|
|
"entropy": 5.4703856945037845,
|
|
"epoch": 1.5173246476104902,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.00047794985141613413,
|
|
"loss": 5.3796,
|
|
"mean_token_accuracy": 0.18744681477546693,
|
|
"num_tokens": 30144501.0,
|
|
"step": 13510
|
|
},
|
|
{
|
|
"entropy": 5.5106078624725345,
|
|
"epoch": 1.5178862245184477,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.00047793251448125526,
|
|
"loss": 5.3317,
|
|
"mean_token_accuracy": 0.1898783937096596,
|
|
"num_tokens": 30156351.0,
|
|
"step": 13515
|
|
},
|
|
{
|
|
"entropy": 5.570866870880127,
|
|
"epoch": 1.5184478014264053,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004779151710849265,
|
|
"loss": 5.4284,
|
|
"mean_token_accuracy": 0.1814264938235283,
|
|
"num_tokens": 30167445.0,
|
|
"step": 13520
|
|
},
|
|
{
|
|
"entropy": 5.620449876785278,
|
|
"epoch": 1.519009378334363,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004778978212276999,
|
|
"loss": 5.49,
|
|
"mean_token_accuracy": 0.17341291755437852,
|
|
"num_tokens": 30179054.0,
|
|
"step": 13525
|
|
},
|
|
{
|
|
"entropy": 5.637458610534668,
|
|
"epoch": 1.5195709552423204,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004778804649101281,
|
|
"loss": 5.4138,
|
|
"mean_token_accuracy": 0.18240256160497664,
|
|
"num_tokens": 30189412.0,
|
|
"step": 13530
|
|
},
|
|
{
|
|
"entropy": 5.5557867050170895,
|
|
"epoch": 1.5201325321502779,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004778631021327636,
|
|
"loss": 5.3996,
|
|
"mean_token_accuracy": 0.18172027468681334,
|
|
"num_tokens": 30200775.0,
|
|
"step": 13535
|
|
},
|
|
{
|
|
"entropy": 5.553967905044556,
|
|
"epoch": 1.5206941090582355,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004778457328961592,
|
|
"loss": 5.3454,
|
|
"mean_token_accuracy": 0.18539057523012162,
|
|
"num_tokens": 30212121.0,
|
|
"step": 13540
|
|
},
|
|
{
|
|
"entropy": 5.494845914840698,
|
|
"epoch": 1.5212556859661932,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.00047782835720086797,
|
|
"loss": 5.3007,
|
|
"mean_token_accuracy": 0.18967946916818618,
|
|
"num_tokens": 30222814.0,
|
|
"step": 13545
|
|
},
|
|
{
|
|
"entropy": 5.5532997131347654,
|
|
"epoch": 1.5218172628741506,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004778109750474432,
|
|
"loss": 5.4067,
|
|
"mean_token_accuracy": 0.18181711733341216,
|
|
"num_tokens": 30232414.0,
|
|
"step": 13550
|
|
},
|
|
{
|
|
"entropy": 5.634558773040771,
|
|
"epoch": 1.522378839782108,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004777935864364383,
|
|
"loss": 5.5068,
|
|
"mean_token_accuracy": 0.1819259151816368,
|
|
"num_tokens": 30243479.0,
|
|
"step": 13555
|
|
},
|
|
{
|
|
"entropy": 5.6132118701934814,
|
|
"epoch": 1.5229404166900657,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.000477776191368407,
|
|
"loss": 5.4383,
|
|
"mean_token_accuracy": 0.1828339710831642,
|
|
"num_tokens": 30254721.0,
|
|
"step": 13560
|
|
},
|
|
{
|
|
"entropy": 5.567163944244385,
|
|
"epoch": 1.5235019935980234,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004777587898439031,
|
|
"loss": 5.3443,
|
|
"mean_token_accuracy": 0.18657080829143524,
|
|
"num_tokens": 30266962.0,
|
|
"step": 13565
|
|
},
|
|
{
|
|
"entropy": 5.559728813171387,
|
|
"epoch": 1.5240635705059808,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.00047774138186348073,
|
|
"loss": 5.3792,
|
|
"mean_token_accuracy": 0.18521272838115693,
|
|
"num_tokens": 30278773.0,
|
|
"step": 13570
|
|
},
|
|
{
|
|
"entropy": 5.475287580490113,
|
|
"epoch": 1.5246251474139383,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004777239674276941,
|
|
"loss": 5.3051,
|
|
"mean_token_accuracy": 0.1914447709918022,
|
|
"num_tokens": 30289631.0,
|
|
"step": 13575
|
|
},
|
|
{
|
|
"entropy": 5.525226402282715,
|
|
"epoch": 1.525186724321896,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004777065465370977,
|
|
"loss": 5.4079,
|
|
"mean_token_accuracy": 0.1838540181517601,
|
|
"num_tokens": 30301433.0,
|
|
"step": 13580
|
|
},
|
|
{
|
|
"entropy": 5.593246507644653,
|
|
"epoch": 1.5257483012298534,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004776891191922463,
|
|
"loss": 5.3571,
|
|
"mean_token_accuracy": 0.18819249272346497,
|
|
"num_tokens": 30312695.0,
|
|
"step": 13585
|
|
},
|
|
{
|
|
"entropy": 5.51133131980896,
|
|
"epoch": 1.5263098781378108,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004776716853936947,
|
|
"loss": 5.4017,
|
|
"mean_token_accuracy": 0.18176380246877671,
|
|
"num_tokens": 30324254.0,
|
|
"step": 13590
|
|
},
|
|
{
|
|
"entropy": 5.558914995193481,
|
|
"epoch": 1.5268714550457685,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.000477654245141998,
|
|
"loss": 5.4717,
|
|
"mean_token_accuracy": 0.18200935274362565,
|
|
"num_tokens": 30335389.0,
|
|
"step": 13595
|
|
},
|
|
{
|
|
"entropy": 5.565616607666016,
|
|
"epoch": 1.5274330319537262,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004776367984377116,
|
|
"loss": 5.3476,
|
|
"mean_token_accuracy": 0.19087966978549958,
|
|
"num_tokens": 30346627.0,
|
|
"step": 13600
|
|
},
|
|
{
|
|
"entropy": 5.504670524597168,
|
|
"epoch": 1.5279946088616836,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00047761934528139086,
|
|
"loss": 5.4383,
|
|
"mean_token_accuracy": 0.1850270837545395,
|
|
"num_tokens": 30358215.0,
|
|
"step": 13605
|
|
},
|
|
{
|
|
"entropy": 5.568783950805664,
|
|
"epoch": 1.528556185769641,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004776018856735916,
|
|
"loss": 5.3368,
|
|
"mean_token_accuracy": 0.1884455904364586,
|
|
"num_tokens": 30369793.0,
|
|
"step": 13610
|
|
},
|
|
{
|
|
"entropy": 5.527515125274658,
|
|
"epoch": 1.5291177626775987,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004775844196148698,
|
|
"loss": 5.2814,
|
|
"mean_token_accuracy": 0.1938552275300026,
|
|
"num_tokens": 30380200.0,
|
|
"step": 13615
|
|
},
|
|
{
|
|
"entropy": 5.462940740585327,
|
|
"epoch": 1.5296793395855564,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.00047756694710578146,
|
|
"loss": 5.4801,
|
|
"mean_token_accuracy": 0.17716196030378342,
|
|
"num_tokens": 30392282.0,
|
|
"step": 13620
|
|
},
|
|
{
|
|
"entropy": 5.697913360595703,
|
|
"epoch": 1.5302409164935138,
|
|
"grad_norm": 5.25,
|
|
"learning_rate": 0.000477549468146883,
|
|
"loss": 5.6244,
|
|
"mean_token_accuracy": 0.17258382290601731,
|
|
"num_tokens": 30405365.0,
|
|
"step": 13625
|
|
},
|
|
{
|
|
"entropy": 5.589715194702149,
|
|
"epoch": 1.5308024934014712,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004775319827387309,
|
|
"loss": 5.4209,
|
|
"mean_token_accuracy": 0.1872163236141205,
|
|
"num_tokens": 30416513.0,
|
|
"step": 13630
|
|
},
|
|
{
|
|
"entropy": 5.475887632369995,
|
|
"epoch": 1.531364070309429,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004775144908818818,
|
|
"loss": 5.2946,
|
|
"mean_token_accuracy": 0.19170508086681365,
|
|
"num_tokens": 30427245.0,
|
|
"step": 13635
|
|
},
|
|
{
|
|
"entropy": 5.621194076538086,
|
|
"epoch": 1.5319256472173866,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00047749699257689296,
|
|
"loss": 5.4364,
|
|
"mean_token_accuracy": 0.18304508030414582,
|
|
"num_tokens": 30438437.0,
|
|
"step": 13640
|
|
},
|
|
{
|
|
"entropy": 5.528850936889649,
|
|
"epoch": 1.532487224125344,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004774794878243212,
|
|
"loss": 5.3897,
|
|
"mean_token_accuracy": 0.18640411049127578,
|
|
"num_tokens": 30449726.0,
|
|
"step": 13645
|
|
},
|
|
{
|
|
"entropy": 5.555571460723877,
|
|
"epoch": 1.5330488010333014,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.000477461976624724,
|
|
"loss": 5.4298,
|
|
"mean_token_accuracy": 0.18499019593000413,
|
|
"num_tokens": 30460024.0,
|
|
"step": 13650
|
|
},
|
|
{
|
|
"entropy": 5.652355289459228,
|
|
"epoch": 1.533610377941259,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00047744445897865905,
|
|
"loss": 5.5162,
|
|
"mean_token_accuracy": 0.17776869386434554,
|
|
"num_tokens": 30471981.0,
|
|
"step": 13655
|
|
},
|
|
{
|
|
"entropy": 5.560834503173828,
|
|
"epoch": 1.5341719548492168,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.000477426934886684,
|
|
"loss": 5.3272,
|
|
"mean_token_accuracy": 0.19395865648984909,
|
|
"num_tokens": 30483143.0,
|
|
"step": 13660
|
|
},
|
|
{
|
|
"entropy": 5.465796852111817,
|
|
"epoch": 1.5347335317571742,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00047740940434935677,
|
|
"loss": 5.3583,
|
|
"mean_token_accuracy": 0.18184324204921723,
|
|
"num_tokens": 30495049.0,
|
|
"step": 13665
|
|
},
|
|
{
|
|
"entropy": 5.548905324935913,
|
|
"epoch": 1.5352951086651316,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004773918673672356,
|
|
"loss": 5.4642,
|
|
"mean_token_accuracy": 0.18481016606092454,
|
|
"num_tokens": 30506736.0,
|
|
"step": 13670
|
|
},
|
|
{
|
|
"entropy": 5.741988182067871,
|
|
"epoch": 1.5358566855730893,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.00047737432394087887,
|
|
"loss": 5.5595,
|
|
"mean_token_accuracy": 0.18076975047588348,
|
|
"num_tokens": 30520130.0,
|
|
"step": 13675
|
|
},
|
|
{
|
|
"entropy": 5.625166940689087,
|
|
"epoch": 1.5364182624810467,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.00047735677407084525,
|
|
"loss": 5.5307,
|
|
"mean_token_accuracy": 0.17583049535751344,
|
|
"num_tokens": 30531480.0,
|
|
"step": 13680
|
|
},
|
|
{
|
|
"entropy": 5.514678812026977,
|
|
"epoch": 1.5369798393890042,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004773392177576934,
|
|
"loss": 5.3671,
|
|
"mean_token_accuracy": 0.18170706778764725,
|
|
"num_tokens": 30541760.0,
|
|
"step": 13685
|
|
},
|
|
{
|
|
"entropy": 5.593460512161255,
|
|
"epoch": 1.5375414162969618,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004773216550019824,
|
|
"loss": 5.382,
|
|
"mean_token_accuracy": 0.18787881731987,
|
|
"num_tokens": 30551162.0,
|
|
"step": 13690
|
|
},
|
|
{
|
|
"entropy": 5.531304979324341,
|
|
"epoch": 1.5381029932049195,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00047730408580427136,
|
|
"loss": 5.3488,
|
|
"mean_token_accuracy": 0.18768645823001862,
|
|
"num_tokens": 30562601.0,
|
|
"step": 13695
|
|
},
|
|
{
|
|
"entropy": 5.5491913795471195,
|
|
"epoch": 1.538664570112877,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00047728651016511994,
|
|
"loss": 5.4301,
|
|
"mean_token_accuracy": 0.18237154334783554,
|
|
"num_tokens": 30573923.0,
|
|
"step": 13700
|
|
},
|
|
{
|
|
"entropy": 5.629022026062012,
|
|
"epoch": 1.5392261470208344,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00047726892808508744,
|
|
"loss": 5.4916,
|
|
"mean_token_accuracy": 0.17828229665756226,
|
|
"num_tokens": 30586400.0,
|
|
"step": 13705
|
|
},
|
|
{
|
|
"entropy": 5.633077812194824,
|
|
"epoch": 1.539787723928792,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004772513395647339,
|
|
"loss": 5.4615,
|
|
"mean_token_accuracy": 0.17952902764081954,
|
|
"num_tokens": 30598317.0,
|
|
"step": 13710
|
|
},
|
|
{
|
|
"entropy": 5.614277791976929,
|
|
"epoch": 1.5403493008367497,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004772337446046192,
|
|
"loss": 5.4242,
|
|
"mean_token_accuracy": 0.18551861345767975,
|
|
"num_tokens": 30609413.0,
|
|
"step": 13715
|
|
},
|
|
{
|
|
"entropy": 5.6229565143585205,
|
|
"epoch": 1.5409108777447071,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00047721614320530366,
|
|
"loss": 5.3359,
|
|
"mean_token_accuracy": 0.18386495858430862,
|
|
"num_tokens": 30619252.0,
|
|
"step": 13720
|
|
},
|
|
{
|
|
"entropy": 5.507887458801269,
|
|
"epoch": 1.5414724546526646,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00047719853536734764,
|
|
"loss": 5.3582,
|
|
"mean_token_accuracy": 0.19007731080055237,
|
|
"num_tokens": 30630477.0,
|
|
"step": 13725
|
|
},
|
|
{
|
|
"entropy": 5.527295351028442,
|
|
"epoch": 1.5420340315606222,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004771809210913119,
|
|
"loss": 5.4153,
|
|
"mean_token_accuracy": 0.1849319592118263,
|
|
"num_tokens": 30641977.0,
|
|
"step": 13730
|
|
},
|
|
{
|
|
"entropy": 5.61675181388855,
|
|
"epoch": 1.54259560846858,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.00047716330037775724,
|
|
"loss": 5.355,
|
|
"mean_token_accuracy": 0.18888724744319915,
|
|
"num_tokens": 30653547.0,
|
|
"step": 13735
|
|
},
|
|
{
|
|
"entropy": 5.5287590503692625,
|
|
"epoch": 1.5431571853765373,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004771456732272446,
|
|
"loss": 5.3886,
|
|
"mean_token_accuracy": 0.18013912588357925,
|
|
"num_tokens": 30664270.0,
|
|
"step": 13740
|
|
},
|
|
{
|
|
"entropy": 5.659532165527343,
|
|
"epoch": 1.5437187622844948,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00047712803964033545,
|
|
"loss": 5.5812,
|
|
"mean_token_accuracy": 0.17014667391777039,
|
|
"num_tokens": 30677172.0,
|
|
"step": 13745
|
|
},
|
|
{
|
|
"entropy": 5.616595029830933,
|
|
"epoch": 1.5442803391924524,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.00047711039961759107,
|
|
"loss": 5.448,
|
|
"mean_token_accuracy": 0.18428623527288437,
|
|
"num_tokens": 30688657.0,
|
|
"step": 13750
|
|
},
|
|
{
|
|
"entropy": 5.585419130325318,
|
|
"epoch": 1.54484191610041,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004770927531595731,
|
|
"loss": 5.4416,
|
|
"mean_token_accuracy": 0.18118552267551422,
|
|
"num_tokens": 30699103.0,
|
|
"step": 13755
|
|
},
|
|
{
|
|
"entropy": 5.558484268188477,
|
|
"epoch": 1.5454034930083675,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00047707510026684353,
|
|
"loss": 5.3876,
|
|
"mean_token_accuracy": 0.18183284252882004,
|
|
"num_tokens": 30711352.0,
|
|
"step": 13760
|
|
},
|
|
{
|
|
"entropy": 5.675160837173462,
|
|
"epoch": 1.545965069916325,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00047705744093996447,
|
|
"loss": 5.4765,
|
|
"mean_token_accuracy": 0.18024851083755494,
|
|
"num_tokens": 30722224.0,
|
|
"step": 13765
|
|
},
|
|
{
|
|
"entropy": 5.607077360153198,
|
|
"epoch": 1.5465266468242826,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.000477039775179498,
|
|
"loss": 5.4422,
|
|
"mean_token_accuracy": 0.17536765933036805,
|
|
"num_tokens": 30733113.0,
|
|
"step": 13770
|
|
},
|
|
{
|
|
"entropy": 5.573582410812378,
|
|
"epoch": 1.54708822373224,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.00047702210298600684,
|
|
"loss": 5.4511,
|
|
"mean_token_accuracy": 0.1805928409099579,
|
|
"num_tokens": 30744903.0,
|
|
"step": 13775
|
|
},
|
|
{
|
|
"entropy": 5.633671283721924,
|
|
"epoch": 1.5476498006401975,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00047700442436005356,
|
|
"loss": 5.4317,
|
|
"mean_token_accuracy": 0.18018018305301667,
|
|
"num_tokens": 30756034.0,
|
|
"step": 13780
|
|
},
|
|
{
|
|
"entropy": 5.542671060562133,
|
|
"epoch": 1.5482113775481552,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.000476986739302201,
|
|
"loss": 5.3462,
|
|
"mean_token_accuracy": 0.18649798780679702,
|
|
"num_tokens": 30766139.0,
|
|
"step": 13785
|
|
},
|
|
{
|
|
"entropy": 5.567276573181152,
|
|
"epoch": 1.5487729544561128,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.00047696904781301233,
|
|
"loss": 5.4416,
|
|
"mean_token_accuracy": 0.18002934902906417,
|
|
"num_tokens": 30777505.0,
|
|
"step": 13790
|
|
},
|
|
{
|
|
"entropy": 5.5490563869476315,
|
|
"epoch": 1.5493345313640703,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004769513498930508,
|
|
"loss": 5.3241,
|
|
"mean_token_accuracy": 0.18992604166269303,
|
|
"num_tokens": 30788520.0,
|
|
"step": 13795
|
|
},
|
|
{
|
|
"entropy": 5.523218870162964,
|
|
"epoch": 1.5498961082720277,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00047693364554288,
|
|
"loss": 5.3192,
|
|
"mean_token_accuracy": 0.1855691209435463,
|
|
"num_tokens": 30799051.0,
|
|
"step": 13800
|
|
},
|
|
{
|
|
"entropy": 5.521050930023193,
|
|
"epoch": 1.5504576851799854,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.00047691593476306373,
|
|
"loss": 5.336,
|
|
"mean_token_accuracy": 0.19566950649023057,
|
|
"num_tokens": 30809375.0,
|
|
"step": 13805
|
|
},
|
|
{
|
|
"entropy": 5.539036464691162,
|
|
"epoch": 1.551019262087943,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004768982175541656,
|
|
"loss": 5.3418,
|
|
"mean_token_accuracy": 0.18851928114891053,
|
|
"num_tokens": 30821330.0,
|
|
"step": 13810
|
|
},
|
|
{
|
|
"entropy": 5.633591508865356,
|
|
"epoch": 1.5515808389959005,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00047688049391675006,
|
|
"loss": 5.4827,
|
|
"mean_token_accuracy": 0.17657239884138107,
|
|
"num_tokens": 30832366.0,
|
|
"step": 13815
|
|
},
|
|
{
|
|
"entropy": 5.594413089752197,
|
|
"epoch": 1.552142415903858,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004768627638513813,
|
|
"loss": 5.4264,
|
|
"mean_token_accuracy": 0.17895372062921525,
|
|
"num_tokens": 30843550.0,
|
|
"step": 13820
|
|
},
|
|
{
|
|
"entropy": 5.482576704025268,
|
|
"epoch": 1.5527039928118156,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004768450273586237,
|
|
"loss": 5.258,
|
|
"mean_token_accuracy": 0.1935638576745987,
|
|
"num_tokens": 30854727.0,
|
|
"step": 13825
|
|
},
|
|
{
|
|
"entropy": 5.589857721328736,
|
|
"epoch": 1.5532655697197733,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00047682728443904223,
|
|
"loss": 5.3835,
|
|
"mean_token_accuracy": 0.18434152752161026,
|
|
"num_tokens": 30865594.0,
|
|
"step": 13830
|
|
},
|
|
{
|
|
"entropy": 5.580872392654419,
|
|
"epoch": 1.5538271466277307,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00047680953509320176,
|
|
"loss": 5.3871,
|
|
"mean_token_accuracy": 0.18392160683870315,
|
|
"num_tokens": 30877386.0,
|
|
"step": 13835
|
|
},
|
|
{
|
|
"entropy": 5.657144498825073,
|
|
"epoch": 1.5543887235356881,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004767917793216674,
|
|
"loss": 5.4923,
|
|
"mean_token_accuracy": 0.1839445412158966,
|
|
"num_tokens": 30889052.0,
|
|
"step": 13840
|
|
},
|
|
{
|
|
"entropy": 5.562966823577881,
|
|
"epoch": 1.5549503004436458,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00047677401712500455,
|
|
"loss": 5.3473,
|
|
"mean_token_accuracy": 0.18103903234004975,
|
|
"num_tokens": 30900524.0,
|
|
"step": 13845
|
|
},
|
|
{
|
|
"entropy": 5.576873540878296,
|
|
"epoch": 1.5555118773516035,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004767562485037787,
|
|
"loss": 5.4734,
|
|
"mean_token_accuracy": 0.17559579908847808,
|
|
"num_tokens": 30911770.0,
|
|
"step": 13850
|
|
},
|
|
{
|
|
"entropy": 5.4913770198822025,
|
|
"epoch": 1.556073454259561,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00047673847345855566,
|
|
"loss": 5.2639,
|
|
"mean_token_accuracy": 0.19188567548990249,
|
|
"num_tokens": 30921662.0,
|
|
"step": 13855
|
|
},
|
|
{
|
|
"entropy": 5.6478245735168455,
|
|
"epoch": 1.5566350311675183,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004767206919899014,
|
|
"loss": 5.5509,
|
|
"mean_token_accuracy": 0.18133361339569093,
|
|
"num_tokens": 30934138.0,
|
|
"step": 13860
|
|
},
|
|
{
|
|
"entropy": 5.631950092315674,
|
|
"epoch": 1.557196608075476,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.000476702904098382,
|
|
"loss": 5.3804,
|
|
"mean_token_accuracy": 0.1829290822148323,
|
|
"num_tokens": 30945561.0,
|
|
"step": 13865
|
|
},
|
|
{
|
|
"entropy": 5.502339935302734,
|
|
"epoch": 1.5577581849834334,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000476685109784564,
|
|
"loss": 5.2657,
|
|
"mean_token_accuracy": 0.19422535449266434,
|
|
"num_tokens": 30957210.0,
|
|
"step": 13870
|
|
},
|
|
{
|
|
"entropy": 5.546827745437622,
|
|
"epoch": 1.5583197618913909,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00047666730904901377,
|
|
"loss": 5.3774,
|
|
"mean_token_accuracy": 0.18659260720014573,
|
|
"num_tokens": 30968782.0,
|
|
"step": 13875
|
|
},
|
|
{
|
|
"entropy": 5.553039169311523,
|
|
"epoch": 1.5588813387993485,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00047664950189229833,
|
|
"loss": 5.42,
|
|
"mean_token_accuracy": 0.18063327074050903,
|
|
"num_tokens": 30981239.0,
|
|
"step": 13880
|
|
},
|
|
{
|
|
"entropy": 5.620796632766724,
|
|
"epoch": 1.5594429157073062,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004766316883149845,
|
|
"loss": 5.4496,
|
|
"mean_token_accuracy": 0.18674004524946214,
|
|
"num_tokens": 30991773.0,
|
|
"step": 13885
|
|
},
|
|
{
|
|
"entropy": 5.666515827178955,
|
|
"epoch": 1.5600044926152636,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00047661386831763955,
|
|
"loss": 5.4382,
|
|
"mean_token_accuracy": 0.1887378215789795,
|
|
"num_tokens": 31002646.0,
|
|
"step": 13890
|
|
},
|
|
{
|
|
"entropy": 5.505196619033813,
|
|
"epoch": 1.560566069523221,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00047659604190083076,
|
|
"loss": 5.4008,
|
|
"mean_token_accuracy": 0.1821158915758133,
|
|
"num_tokens": 31014405.0,
|
|
"step": 13895
|
|
},
|
|
{
|
|
"entropy": 5.5668925762176515,
|
|
"epoch": 1.5611276464311787,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00047657820906512585,
|
|
"loss": 5.3414,
|
|
"mean_token_accuracy": 0.18443161994218826,
|
|
"num_tokens": 31025529.0,
|
|
"step": 13900
|
|
},
|
|
{
|
|
"entropy": 5.684357118606568,
|
|
"epoch": 1.5616892233391364,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00047656036981109256,
|
|
"loss": 5.487,
|
|
"mean_token_accuracy": 0.17803749591112136,
|
|
"num_tokens": 31037558.0,
|
|
"step": 13905
|
|
},
|
|
{
|
|
"entropy": 5.430062532424927,
|
|
"epoch": 1.5622508002470938,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.00047654252413929896,
|
|
"loss": 5.2432,
|
|
"mean_token_accuracy": 0.19305500388145447,
|
|
"num_tokens": 31048918.0,
|
|
"step": 13910
|
|
},
|
|
{
|
|
"entropy": 5.454860258102417,
|
|
"epoch": 1.5628123771550513,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00047652467205031317,
|
|
"loss": 5.3506,
|
|
"mean_token_accuracy": 0.1870207667350769,
|
|
"num_tokens": 31060149.0,
|
|
"step": 13915
|
|
},
|
|
{
|
|
"entropy": 5.548892307281494,
|
|
"epoch": 1.563373954063009,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00047650681354470363,
|
|
"loss": 5.3699,
|
|
"mean_token_accuracy": 0.18815428167581558,
|
|
"num_tokens": 31071197.0,
|
|
"step": 13920
|
|
},
|
|
{
|
|
"entropy": 5.613787508010864,
|
|
"epoch": 1.5639355309709666,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00047648894862303907,
|
|
"loss": 5.4866,
|
|
"mean_token_accuracy": 0.18950826525688172,
|
|
"num_tokens": 31083385.0,
|
|
"step": 13925
|
|
},
|
|
{
|
|
"entropy": 5.54557957649231,
|
|
"epoch": 1.564497107878924,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00047647107728588826,
|
|
"loss": 5.39,
|
|
"mean_token_accuracy": 0.18100087195634842,
|
|
"num_tokens": 31094807.0,
|
|
"step": 13930
|
|
},
|
|
{
|
|
"entropy": 5.502994585037231,
|
|
"epoch": 1.5650586847868815,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00047645319953382024,
|
|
"loss": 5.3025,
|
|
"mean_token_accuracy": 0.19468299448490142,
|
|
"num_tokens": 31105622.0,
|
|
"step": 13935
|
|
},
|
|
{
|
|
"entropy": 5.588700962066651,
|
|
"epoch": 1.5656202616948391,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.00047643531536740405,
|
|
"loss": 5.3365,
|
|
"mean_token_accuracy": 0.18804485201835633,
|
|
"num_tokens": 31115684.0,
|
|
"step": 13940
|
|
},
|
|
{
|
|
"entropy": 5.490893077850342,
|
|
"epoch": 1.5661818386027968,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004764174247872094,
|
|
"loss": 5.3033,
|
|
"mean_token_accuracy": 0.19590633511543273,
|
|
"num_tokens": 31126449.0,
|
|
"step": 13945
|
|
},
|
|
{
|
|
"entropy": 5.538293886184692,
|
|
"epoch": 1.5667434155107542,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00047639952779380586,
|
|
"loss": 5.3283,
|
|
"mean_token_accuracy": 0.19549835920333863,
|
|
"num_tokens": 31136894.0,
|
|
"step": 13950
|
|
},
|
|
{
|
|
"entropy": 5.574567747116089,
|
|
"epoch": 1.5673049924187117,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004763816243877632,
|
|
"loss": 5.4235,
|
|
"mean_token_accuracy": 0.18958259820938111,
|
|
"num_tokens": 31147131.0,
|
|
"step": 13955
|
|
},
|
|
{
|
|
"entropy": 5.464069890975952,
|
|
"epoch": 1.5678665693266693,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004763637145696515,
|
|
"loss": 5.2629,
|
|
"mean_token_accuracy": 0.19027214348316193,
|
|
"num_tokens": 31157903.0,
|
|
"step": 13960
|
|
},
|
|
{
|
|
"entropy": 5.558705472946167,
|
|
"epoch": 1.5684281462346268,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.000476345798340041,
|
|
"loss": 5.4313,
|
|
"mean_token_accuracy": 0.1850793793797493,
|
|
"num_tokens": 31169087.0,
|
|
"step": 13965
|
|
},
|
|
{
|
|
"entropy": 5.64756031036377,
|
|
"epoch": 1.5689897231425842,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004763278756995022,
|
|
"loss": 5.5032,
|
|
"mean_token_accuracy": 0.17865439653396606,
|
|
"num_tokens": 31180253.0,
|
|
"step": 13970
|
|
},
|
|
{
|
|
"entropy": 5.640758609771728,
|
|
"epoch": 1.5695513000505419,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.00047630994664860576,
|
|
"loss": 5.4382,
|
|
"mean_token_accuracy": 0.18289659172296524,
|
|
"num_tokens": 31191857.0,
|
|
"step": 13975
|
|
},
|
|
{
|
|
"entropy": 5.55273962020874,
|
|
"epoch": 1.5701128769584995,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004762920111879226,
|
|
"loss": 5.4536,
|
|
"mean_token_accuracy": 0.1757165178656578,
|
|
"num_tokens": 31201868.0,
|
|
"step": 13980
|
|
},
|
|
{
|
|
"entropy": 5.563938236236572,
|
|
"epoch": 1.570674453866457,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004762740693180237,
|
|
"loss": 5.4015,
|
|
"mean_token_accuracy": 0.18728701025247574,
|
|
"num_tokens": 31212716.0,
|
|
"step": 13985
|
|
},
|
|
{
|
|
"entropy": 5.596206521987915,
|
|
"epoch": 1.5712360307744144,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00047625612103948035,
|
|
"loss": 5.474,
|
|
"mean_token_accuracy": 0.17948551028966903,
|
|
"num_tokens": 31224823.0,
|
|
"step": 13990
|
|
},
|
|
{
|
|
"entropy": 5.570262765884399,
|
|
"epoch": 1.571797607682372,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004762381663528641,
|
|
"loss": 5.3656,
|
|
"mean_token_accuracy": 0.1848146378993988,
|
|
"num_tokens": 31236798.0,
|
|
"step": 13995
|
|
},
|
|
{
|
|
"entropy": 5.609161281585694,
|
|
"epoch": 1.5723591845903298,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004762202052587466,
|
|
"loss": 5.3998,
|
|
"mean_token_accuracy": 0.1816373810172081,
|
|
"num_tokens": 31248687.0,
|
|
"step": 14000
|
|
},
|
|
{
|
|
"entropy": 5.572255611419678,
|
|
"epoch": 1.5729207614982872,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004762022377576996,
|
|
"loss": 5.4599,
|
|
"mean_token_accuracy": 0.18094970881938935,
|
|
"num_tokens": 31258385.0,
|
|
"step": 14005
|
|
},
|
|
{
|
|
"entropy": 5.676636552810669,
|
|
"epoch": 1.5734823384062446,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004761842638502954,
|
|
"loss": 5.4744,
|
|
"mean_token_accuracy": 0.1854086771607399,
|
|
"num_tokens": 31269308.0,
|
|
"step": 14010
|
|
},
|
|
{
|
|
"entropy": 5.608185768127441,
|
|
"epoch": 1.5740439153142023,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004761662835371062,
|
|
"loss": 5.3744,
|
|
"mean_token_accuracy": 0.18948292285203933,
|
|
"num_tokens": 31279900.0,
|
|
"step": 14015
|
|
},
|
|
{
|
|
"entropy": 5.543855428695679,
|
|
"epoch": 1.57460549222216,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004761482968187045,
|
|
"loss": 5.3849,
|
|
"mean_token_accuracy": 0.1922425866127014,
|
|
"num_tokens": 31290456.0,
|
|
"step": 14020
|
|
},
|
|
{
|
|
"entropy": 5.491939544677734,
|
|
"epoch": 1.5751670691301174,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004761303036956631,
|
|
"loss": 5.3621,
|
|
"mean_token_accuracy": 0.18260688036680223,
|
|
"num_tokens": 31301398.0,
|
|
"step": 14025
|
|
},
|
|
{
|
|
"entropy": 5.658075141906738,
|
|
"epoch": 1.5757286460380748,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004761123041685547,
|
|
"loss": 5.4558,
|
|
"mean_token_accuracy": 0.1853075996041298,
|
|
"num_tokens": 31311149.0,
|
|
"step": 14030
|
|
},
|
|
{
|
|
"entropy": 5.464800119400024,
|
|
"epoch": 1.5762902229460325,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004760942982379526,
|
|
"loss": 5.2795,
|
|
"mean_token_accuracy": 0.1985880345106125,
|
|
"num_tokens": 31321099.0,
|
|
"step": 14035
|
|
},
|
|
{
|
|
"entropy": 5.521101665496826,
|
|
"epoch": 1.5768517998539902,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.00047607628590443004,
|
|
"loss": 5.413,
|
|
"mean_token_accuracy": 0.1805889293551445,
|
|
"num_tokens": 31331872.0,
|
|
"step": 14040
|
|
},
|
|
{
|
|
"entropy": 5.685874986648559,
|
|
"epoch": 1.5774133767619476,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00047605826716856056,
|
|
"loss": 5.4529,
|
|
"mean_token_accuracy": 0.1793512836098671,
|
|
"num_tokens": 31342024.0,
|
|
"step": 14045
|
|
},
|
|
{
|
|
"entropy": 5.614808082580566,
|
|
"epoch": 1.577974953669905,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004760402420309178,
|
|
"loss": 5.2957,
|
|
"mean_token_accuracy": 0.1913559079170227,
|
|
"num_tokens": 31351857.0,
|
|
"step": 14050
|
|
},
|
|
{
|
|
"entropy": 5.503947019577026,
|
|
"epoch": 1.5785365305778627,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004760222104920759,
|
|
"loss": 5.3928,
|
|
"mean_token_accuracy": 0.18860056549310683,
|
|
"num_tokens": 31362609.0,
|
|
"step": 14055
|
|
},
|
|
{
|
|
"entropy": 5.478338956832886,
|
|
"epoch": 1.5790981074858201,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004760041725526088,
|
|
"loss": 5.3232,
|
|
"mean_token_accuracy": 0.18444042205810546,
|
|
"num_tokens": 31373129.0,
|
|
"step": 14060
|
|
},
|
|
{
|
|
"entropy": 5.550362205505371,
|
|
"epoch": 1.5796596843937776,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00047598612821309077,
|
|
"loss": 5.2925,
|
|
"mean_token_accuracy": 0.1911611244082451,
|
|
"num_tokens": 31383109.0,
|
|
"step": 14065
|
|
},
|
|
{
|
|
"entropy": 5.484701251983642,
|
|
"epoch": 1.5802212613017352,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004759680774740966,
|
|
"loss": 5.2678,
|
|
"mean_token_accuracy": 0.18637271523475646,
|
|
"num_tokens": 31393603.0,
|
|
"step": 14070
|
|
},
|
|
{
|
|
"entropy": 5.60389404296875,
|
|
"epoch": 1.580782838209693,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004759500203362008,
|
|
"loss": 5.3491,
|
|
"mean_token_accuracy": 0.18680666238069535,
|
|
"num_tokens": 31404011.0,
|
|
"step": 14075
|
|
},
|
|
{
|
|
"entropy": 5.502894592285156,
|
|
"epoch": 1.5813444151176503,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004759319567999785,
|
|
"loss": 5.2939,
|
|
"mean_token_accuracy": 0.18432048857212066,
|
|
"num_tokens": 31414239.0,
|
|
"step": 14080
|
|
},
|
|
{
|
|
"entropy": 5.53234281539917,
|
|
"epoch": 1.5819059920256078,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004759138868660048,
|
|
"loss": 5.4073,
|
|
"mean_token_accuracy": 0.18384866714477538,
|
|
"num_tokens": 31425055.0,
|
|
"step": 14085
|
|
},
|
|
{
|
|
"entropy": 5.602566194534302,
|
|
"epoch": 1.5824675689335654,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00047589581053485494,
|
|
"loss": 5.3752,
|
|
"mean_token_accuracy": 0.18901110738515853,
|
|
"num_tokens": 31435537.0,
|
|
"step": 14090
|
|
},
|
|
{
|
|
"entropy": 5.62176251411438,
|
|
"epoch": 1.583029145841523,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.00047587772780710455,
|
|
"loss": 5.4438,
|
|
"mean_token_accuracy": 0.18455122858285905,
|
|
"num_tokens": 31446056.0,
|
|
"step": 14095
|
|
},
|
|
{
|
|
"entropy": 5.594608354568481,
|
|
"epoch": 1.5835907227494805,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.00047585963868332945,
|
|
"loss": 5.4112,
|
|
"mean_token_accuracy": 0.18492064177989959,
|
|
"num_tokens": 31457452.0,
|
|
"step": 14100
|
|
},
|
|
{
|
|
"entropy": 5.514397048950196,
|
|
"epoch": 1.584152299657438,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004758415431641055,
|
|
"loss": 5.359,
|
|
"mean_token_accuracy": 0.1876969188451767,
|
|
"num_tokens": 31469038.0,
|
|
"step": 14105
|
|
},
|
|
{
|
|
"entropy": 5.5730689525604244,
|
|
"epoch": 1.5847138765653956,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004758234412500089,
|
|
"loss": 5.4638,
|
|
"mean_token_accuracy": 0.1851399928331375,
|
|
"num_tokens": 31481069.0,
|
|
"step": 14110
|
|
},
|
|
{
|
|
"entropy": 5.519595813751221,
|
|
"epoch": 1.5852754534733533,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.00047580533294161616,
|
|
"loss": 5.4108,
|
|
"mean_token_accuracy": 0.18213094621896744,
|
|
"num_tokens": 31491393.0,
|
|
"step": 14115
|
|
},
|
|
{
|
|
"entropy": 5.528887176513672,
|
|
"epoch": 1.5858370303813107,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004757872182395036,
|
|
"loss": 5.4077,
|
|
"mean_token_accuracy": 0.18127547353506088,
|
|
"num_tokens": 31502627.0,
|
|
"step": 14120
|
|
},
|
|
{
|
|
"entropy": 5.699723100662231,
|
|
"epoch": 1.5863986072892682,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00047576909714424823,
|
|
"loss": 5.4438,
|
|
"mean_token_accuracy": 0.17827050983905793,
|
|
"num_tokens": 31513995.0,
|
|
"step": 14125
|
|
},
|
|
{
|
|
"entropy": 5.525648593902588,
|
|
"epoch": 1.5869601841972258,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.00047575096965642687,
|
|
"loss": 5.3752,
|
|
"mean_token_accuracy": 0.18316685557365417,
|
|
"num_tokens": 31524625.0,
|
|
"step": 14130
|
|
},
|
|
{
|
|
"entropy": 5.481736183166504,
|
|
"epoch": 1.5875217611051835,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00047573283577661684,
|
|
"loss": 5.3392,
|
|
"mean_token_accuracy": 0.18936698287725448,
|
|
"num_tokens": 31535940.0,
|
|
"step": 14135
|
|
},
|
|
{
|
|
"entropy": 5.566658544540405,
|
|
"epoch": 1.588083338013141,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004757146955053955,
|
|
"loss": 5.3906,
|
|
"mean_token_accuracy": 0.1862411007285118,
|
|
"num_tokens": 31546557.0,
|
|
"step": 14140
|
|
},
|
|
{
|
|
"entropy": 5.578667545318604,
|
|
"epoch": 1.5886449149210984,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00047569654884334036,
|
|
"loss": 5.4245,
|
|
"mean_token_accuracy": 0.17833538800477983,
|
|
"num_tokens": 31559335.0,
|
|
"step": 14145
|
|
},
|
|
{
|
|
"entropy": 5.6002030849456785,
|
|
"epoch": 1.589206491829056,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004756783957910292,
|
|
"loss": 5.3658,
|
|
"mean_token_accuracy": 0.18090360909700393,
|
|
"num_tokens": 31570698.0,
|
|
"step": 14150
|
|
},
|
|
{
|
|
"entropy": 5.581079721450806,
|
|
"epoch": 1.5897680687370135,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00047566023634904015,
|
|
"loss": 5.4318,
|
|
"mean_token_accuracy": 0.18585970848798752,
|
|
"num_tokens": 31582524.0,
|
|
"step": 14155
|
|
},
|
|
{
|
|
"entropy": 5.575134134292602,
|
|
"epoch": 1.590329645644971,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004756420705179513,
|
|
"loss": 5.3635,
|
|
"mean_token_accuracy": 0.18733209520578384,
|
|
"num_tokens": 31593399.0,
|
|
"step": 14160
|
|
},
|
|
{
|
|
"entropy": 5.506226110458374,
|
|
"epoch": 1.5908912225529286,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004756238982983412,
|
|
"loss": 5.3904,
|
|
"mean_token_accuracy": 0.17625253051519393,
|
|
"num_tokens": 31604169.0,
|
|
"step": 14165
|
|
},
|
|
{
|
|
"entropy": 5.500355672836304,
|
|
"epoch": 1.5914527994608862,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004756057196907883,
|
|
"loss": 5.3312,
|
|
"mean_token_accuracy": 0.19254590421915055,
|
|
"num_tokens": 31614671.0,
|
|
"step": 14170
|
|
},
|
|
{
|
|
"entropy": 5.490681123733521,
|
|
"epoch": 1.5920143763688437,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00047558753469587154,
|
|
"loss": 5.3185,
|
|
"mean_token_accuracy": 0.19051374346017838,
|
|
"num_tokens": 31625793.0,
|
|
"step": 14175
|
|
},
|
|
{
|
|
"entropy": 5.542859077453613,
|
|
"epoch": 1.5925759532768011,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00047556934331416986,
|
|
"loss": 5.3358,
|
|
"mean_token_accuracy": 0.19105246514081956,
|
|
"num_tokens": 31637632.0,
|
|
"step": 14180
|
|
},
|
|
{
|
|
"entropy": 5.545540714263916,
|
|
"epoch": 1.5931375301847588,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004755511455462624,
|
|
"loss": 5.3291,
|
|
"mean_token_accuracy": 0.19029556959867477,
|
|
"num_tokens": 31648314.0,
|
|
"step": 14185
|
|
},
|
|
{
|
|
"entropy": 5.577873563766479,
|
|
"epoch": 1.5936991070927164,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004755329413927287,
|
|
"loss": 5.3908,
|
|
"mean_token_accuracy": 0.18803092539310456,
|
|
"num_tokens": 31659152.0,
|
|
"step": 14190
|
|
},
|
|
{
|
|
"entropy": 5.5810370445251465,
|
|
"epoch": 1.5942606840006739,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004755147308541485,
|
|
"loss": 5.3344,
|
|
"mean_token_accuracy": 0.19057308733463288,
|
|
"num_tokens": 31669837.0,
|
|
"step": 14195
|
|
},
|
|
{
|
|
"entropy": 5.511269760131836,
|
|
"epoch": 1.5948222609086313,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.00047549651393110145,
|
|
"loss": 5.3664,
|
|
"mean_token_accuracy": 0.18276496827602387,
|
|
"num_tokens": 31680663.0,
|
|
"step": 14200
|
|
},
|
|
{
|
|
"entropy": 5.553107500076294,
|
|
"epoch": 1.595383837816589,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.00047547829062416757,
|
|
"loss": 5.3588,
|
|
"mean_token_accuracy": 0.18153503388166428,
|
|
"num_tokens": 31691484.0,
|
|
"step": 14205
|
|
},
|
|
{
|
|
"entropy": 5.55496916770935,
|
|
"epoch": 1.5959454147245467,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00047546006093392726,
|
|
"loss": 5.31,
|
|
"mean_token_accuracy": 0.18103923350572587,
|
|
"num_tokens": 31701642.0,
|
|
"step": 14210
|
|
},
|
|
{
|
|
"entropy": 5.492617607116699,
|
|
"epoch": 1.596506991632504,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004754418248609608,
|
|
"loss": 5.3719,
|
|
"mean_token_accuracy": 0.1854472577571869,
|
|
"num_tokens": 31714203.0,
|
|
"step": 14215
|
|
},
|
|
{
|
|
"entropy": 5.548641633987427,
|
|
"epoch": 1.5970685685404615,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004754235824058489,
|
|
"loss": 5.3546,
|
|
"mean_token_accuracy": 0.18786930292844772,
|
|
"num_tokens": 31725890.0,
|
|
"step": 14220
|
|
},
|
|
{
|
|
"entropy": 5.523428344726563,
|
|
"epoch": 1.5976301454484192,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004754053335691724,
|
|
"loss": 5.3097,
|
|
"mean_token_accuracy": 0.18873031437397003,
|
|
"num_tokens": 31738058.0,
|
|
"step": 14225
|
|
},
|
|
{
|
|
"entropy": 5.5686602115631105,
|
|
"epoch": 1.5981917223563769,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00047538707835151237,
|
|
"loss": 5.3769,
|
|
"mean_token_accuracy": 0.19276683628559113,
|
|
"num_tokens": 31748983.0,
|
|
"step": 14230
|
|
},
|
|
{
|
|
"entropy": 5.562123250961304,
|
|
"epoch": 1.5987532992643343,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00047536881675345,
|
|
"loss": 5.3753,
|
|
"mean_token_accuracy": 0.18837305456399916,
|
|
"num_tokens": 31760083.0,
|
|
"step": 14235
|
|
},
|
|
{
|
|
"entropy": 5.50814642906189,
|
|
"epoch": 1.5993148761722917,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004753505487755669,
|
|
"loss": 5.3182,
|
|
"mean_token_accuracy": 0.19211919456720353,
|
|
"num_tokens": 31771627.0,
|
|
"step": 14240
|
|
},
|
|
{
|
|
"entropy": 5.563792991638183,
|
|
"epoch": 1.5998764530802494,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00047533227441844453,
|
|
"loss": 5.4112,
|
|
"mean_token_accuracy": 0.19014624506235123,
|
|
"num_tokens": 31783476.0,
|
|
"step": 14245
|
|
},
|
|
{
|
|
"entropy": 5.61142635345459,
|
|
"epoch": 1.6004380299882068,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.00047531399368266485,
|
|
"loss": 5.4226,
|
|
"mean_token_accuracy": 0.18333071917295457,
|
|
"num_tokens": 31794072.0,
|
|
"step": 14250
|
|
},
|
|
{
|
|
"entropy": 5.547273302078247,
|
|
"epoch": 1.6009996068961643,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004752957065688099,
|
|
"loss": 5.3179,
|
|
"mean_token_accuracy": 0.19077218621969222,
|
|
"num_tokens": 31803613.0,
|
|
"step": 14255
|
|
},
|
|
{
|
|
"entropy": 5.63131275177002,
|
|
"epoch": 1.601561183804122,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.000475277413077462,
|
|
"loss": 5.4515,
|
|
"mean_token_accuracy": 0.18376434296369554,
|
|
"num_tokens": 31815018.0,
|
|
"step": 14260
|
|
},
|
|
{
|
|
"entropy": 5.41245551109314,
|
|
"epoch": 1.6021227607120796,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.00047525911320920363,
|
|
"loss": 5.288,
|
|
"mean_token_accuracy": 0.19167415499687196,
|
|
"num_tokens": 31825603.0,
|
|
"step": 14265
|
|
},
|
|
{
|
|
"entropy": 5.483716344833374,
|
|
"epoch": 1.602684337620037,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004752408069646174,
|
|
"loss": 5.3519,
|
|
"mean_token_accuracy": 0.18703959584236146,
|
|
"num_tokens": 31835988.0,
|
|
"step": 14270
|
|
},
|
|
{
|
|
"entropy": 5.582781457901001,
|
|
"epoch": 1.6032459145279945,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00047522249434428623,
|
|
"loss": 5.3838,
|
|
"mean_token_accuracy": 0.1827508196234703,
|
|
"num_tokens": 31846378.0,
|
|
"step": 14275
|
|
},
|
|
{
|
|
"entropy": 5.6581432819366455,
|
|
"epoch": 1.6038074914359521,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004752041753487931,
|
|
"loss": 5.4543,
|
|
"mean_token_accuracy": 0.17981308996677398,
|
|
"num_tokens": 31858836.0,
|
|
"step": 14280
|
|
},
|
|
{
|
|
"entropy": 5.505344343185425,
|
|
"epoch": 1.6043690683439098,
|
|
"grad_norm": 2.609375,
|
|
"learning_rate": 0.0004751858499787215,
|
|
"loss": 5.3224,
|
|
"mean_token_accuracy": 0.18830745071172714,
|
|
"num_tokens": 31869315.0,
|
|
"step": 14285
|
|
},
|
|
{
|
|
"entropy": 5.605330228805542,
|
|
"epoch": 1.6049306452518672,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.0004751675182346547,
|
|
"loss": 5.5195,
|
|
"mean_token_accuracy": 0.17846543937921525,
|
|
"num_tokens": 31880527.0,
|
|
"step": 14290
|
|
},
|
|
{
|
|
"entropy": 5.636462545394897,
|
|
"epoch": 1.6054922221598247,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.00047514918011717656,
|
|
"loss": 5.3828,
|
|
"mean_token_accuracy": 0.18812797218561172,
|
|
"num_tokens": 31891890.0,
|
|
"step": 14295
|
|
},
|
|
{
|
|
"entropy": 5.603710079193116,
|
|
"epoch": 1.6060537990677823,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.00047513083562687085,
|
|
"loss": 5.3857,
|
|
"mean_token_accuracy": 0.18741926103830336,
|
|
"num_tokens": 31902735.0,
|
|
"step": 14300
|
|
},
|
|
{
|
|
"entropy": 5.541609287261963,
|
|
"epoch": 1.60661537597574,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004751124847643217,
|
|
"loss": 5.437,
|
|
"mean_token_accuracy": 0.1817302241921425,
|
|
"num_tokens": 31914504.0,
|
|
"step": 14305
|
|
},
|
|
{
|
|
"entropy": 5.598568391799927,
|
|
"epoch": 1.6071769528836974,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004750941275301135,
|
|
"loss": 5.3956,
|
|
"mean_token_accuracy": 0.18769104033708572,
|
|
"num_tokens": 31925287.0,
|
|
"step": 14310
|
|
},
|
|
{
|
|
"entropy": 5.546432113647461,
|
|
"epoch": 1.6077385297916549,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.0004750757639248306,
|
|
"loss": 5.3295,
|
|
"mean_token_accuracy": 0.19074969589710236,
|
|
"num_tokens": 31935845.0,
|
|
"step": 14315
|
|
},
|
|
{
|
|
"entropy": 5.5763781547546385,
|
|
"epoch": 1.6083001066996125,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00047505739394905776,
|
|
"loss": 5.415,
|
|
"mean_token_accuracy": 0.18895251154899598,
|
|
"num_tokens": 31946771.0,
|
|
"step": 14320
|
|
},
|
|
{
|
|
"entropy": 5.539247798919678,
|
|
"epoch": 1.6088616836075702,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00047503901760338003,
|
|
"loss": 5.3768,
|
|
"mean_token_accuracy": 0.18517448455095292,
|
|
"num_tokens": 31957733.0,
|
|
"step": 14325
|
|
},
|
|
{
|
|
"entropy": 5.55397400856018,
|
|
"epoch": 1.6094232605155276,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.00047502063488838225,
|
|
"loss": 5.2744,
|
|
"mean_token_accuracy": 0.19239411056041716,
|
|
"num_tokens": 31967809.0,
|
|
"step": 14330
|
|
},
|
|
{
|
|
"entropy": 5.42648458480835,
|
|
"epoch": 1.609984837423485,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00047500224580464994,
|
|
"loss": 5.2446,
|
|
"mean_token_accuracy": 0.1935966953635216,
|
|
"num_tokens": 31978673.0,
|
|
"step": 14335
|
|
},
|
|
{
|
|
"entropy": 5.491064739227295,
|
|
"epoch": 1.6105464143314427,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00047498385035276856,
|
|
"loss": 5.3765,
|
|
"mean_token_accuracy": 0.18715526312589645,
|
|
"num_tokens": 31990535.0,
|
|
"step": 14340
|
|
},
|
|
{
|
|
"entropy": 5.580092477798462,
|
|
"epoch": 1.6111079912394002,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004749654485333238,
|
|
"loss": 5.4287,
|
|
"mean_token_accuracy": 0.1823533996939659,
|
|
"num_tokens": 32002164.0,
|
|
"step": 14345
|
|
},
|
|
{
|
|
"entropy": 5.6803051948547365,
|
|
"epoch": 1.6116695681473576,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.00047494704034690163,
|
|
"loss": 5.4777,
|
|
"mean_token_accuracy": 0.17761383950710297,
|
|
"num_tokens": 32013651.0,
|
|
"step": 14350
|
|
},
|
|
{
|
|
"entropy": 5.604819202423096,
|
|
"epoch": 1.6122311450553153,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.00047492862579408816,
|
|
"loss": 5.3738,
|
|
"mean_token_accuracy": 0.18794151097536088,
|
|
"num_tokens": 32025128.0,
|
|
"step": 14355
|
|
},
|
|
{
|
|
"entropy": 5.550415658950806,
|
|
"epoch": 1.612792721963273,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.00047491020487546966,
|
|
"loss": 5.407,
|
|
"mean_token_accuracy": 0.17649219334125518,
|
|
"num_tokens": 32036359.0,
|
|
"step": 14360
|
|
},
|
|
{
|
|
"entropy": 5.558035135269165,
|
|
"epoch": 1.6133542988712304,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004748917775916327,
|
|
"loss": 5.3206,
|
|
"mean_token_accuracy": 0.18939928710460663,
|
|
"num_tokens": 32047803.0,
|
|
"step": 14365
|
|
},
|
|
{
|
|
"entropy": 5.541605043411255,
|
|
"epoch": 1.6139158757791878,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00047487334394316405,
|
|
"loss": 5.4889,
|
|
"mean_token_accuracy": 0.183787302672863,
|
|
"num_tokens": 32060156.0,
|
|
"step": 14370
|
|
},
|
|
{
|
|
"entropy": 5.596155071258545,
|
|
"epoch": 1.6144774526871455,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004748549039306506,
|
|
"loss": 5.3777,
|
|
"mean_token_accuracy": 0.18946214765310287,
|
|
"num_tokens": 32071398.0,
|
|
"step": 14375
|
|
},
|
|
{
|
|
"entropy": 5.495157909393311,
|
|
"epoch": 1.6150390295951031,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004748364575546795,
|
|
"loss": 5.2052,
|
|
"mean_token_accuracy": 0.1963065445423126,
|
|
"num_tokens": 32082472.0,
|
|
"step": 14380
|
|
},
|
|
{
|
|
"entropy": 5.486556148529052,
|
|
"epoch": 1.6156006065030606,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00047481800481583806,
|
|
"loss": 5.3856,
|
|
"mean_token_accuracy": 0.18367727398872374,
|
|
"num_tokens": 32093103.0,
|
|
"step": 14385
|
|
},
|
|
{
|
|
"entropy": 5.569084644317627,
|
|
"epoch": 1.616162183411018,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004747995457147139,
|
|
"loss": 5.3978,
|
|
"mean_token_accuracy": 0.1878577098250389,
|
|
"num_tokens": 32104526.0,
|
|
"step": 14390
|
|
},
|
|
{
|
|
"entropy": 5.643805456161499,
|
|
"epoch": 1.6167237603189757,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.00047478108025189467,
|
|
"loss": 5.4471,
|
|
"mean_token_accuracy": 0.1791172981262207,
|
|
"num_tokens": 32116018.0,
|
|
"step": 14395
|
|
},
|
|
{
|
|
"entropy": 5.530964612960815,
|
|
"epoch": 1.6172853372269334,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.00047476260842796837,
|
|
"loss": 5.2966,
|
|
"mean_token_accuracy": 0.19313062429428102,
|
|
"num_tokens": 32127385.0,
|
|
"step": 14400
|
|
},
|
|
{
|
|
"entropy": 5.568222522735596,
|
|
"epoch": 1.6178469141348908,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004747441302435231,
|
|
"loss": 5.4237,
|
|
"mean_token_accuracy": 0.18586568534374237,
|
|
"num_tokens": 32137376.0,
|
|
"step": 14405
|
|
},
|
|
{
|
|
"entropy": 5.570278549194336,
|
|
"epoch": 1.6184084910428482,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00047472564569914726,
|
|
"loss": 5.4094,
|
|
"mean_token_accuracy": 0.18463828414678574,
|
|
"num_tokens": 32148263.0,
|
|
"step": 14410
|
|
},
|
|
{
|
|
"entropy": 5.5898205757141115,
|
|
"epoch": 1.618970067950806,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00047470715479542945,
|
|
"loss": 5.3361,
|
|
"mean_token_accuracy": 0.18114308267831802,
|
|
"num_tokens": 32161323.0,
|
|
"step": 14415
|
|
},
|
|
{
|
|
"entropy": 5.596181488037109,
|
|
"epoch": 1.6195316448587636,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004746886575329584,
|
|
"loss": 5.398,
|
|
"mean_token_accuracy": 0.17863700091838836,
|
|
"num_tokens": 32172294.0,
|
|
"step": 14420
|
|
},
|
|
{
|
|
"entropy": 5.478462219238281,
|
|
"epoch": 1.620093221766721,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.00047467015391232305,
|
|
"loss": 5.3537,
|
|
"mean_token_accuracy": 0.17806696742773057,
|
|
"num_tokens": 32182619.0,
|
|
"step": 14425
|
|
},
|
|
{
|
|
"entropy": 5.515846109390258,
|
|
"epoch": 1.6206547986746784,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00047465164393411245,
|
|
"loss": 5.3377,
|
|
"mean_token_accuracy": 0.18611229509115218,
|
|
"num_tokens": 32193078.0,
|
|
"step": 14430
|
|
},
|
|
{
|
|
"entropy": 5.565969944000244,
|
|
"epoch": 1.621216375582636,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.00047463312759891615,
|
|
"loss": 5.3396,
|
|
"mean_token_accuracy": 0.18058524578809737,
|
|
"num_tokens": 32204134.0,
|
|
"step": 14435
|
|
},
|
|
{
|
|
"entropy": 5.634787082672119,
|
|
"epoch": 1.6217779524905935,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004746146049073236,
|
|
"loss": 5.4189,
|
|
"mean_token_accuracy": 0.1862504377961159,
|
|
"num_tokens": 32215136.0,
|
|
"step": 14440
|
|
},
|
|
{
|
|
"entropy": 5.527179718017578,
|
|
"epoch": 1.622339529398551,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.00047459607585992466,
|
|
"loss": 5.4068,
|
|
"mean_token_accuracy": 0.18511534482240677,
|
|
"num_tokens": 32225727.0,
|
|
"step": 14445
|
|
},
|
|
{
|
|
"entropy": 5.558506059646606,
|
|
"epoch": 1.6229011063065086,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.00047457754045730923,
|
|
"loss": 5.3752,
|
|
"mean_token_accuracy": 0.1840720921754837,
|
|
"num_tokens": 32236376.0,
|
|
"step": 14450
|
|
},
|
|
{
|
|
"entropy": 5.51150336265564,
|
|
"epoch": 1.6234626832144663,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.00047455899870006745,
|
|
"loss": 5.3122,
|
|
"mean_token_accuracy": 0.1918402850627899,
|
|
"num_tokens": 32247202.0,
|
|
"step": 14455
|
|
},
|
|
{
|
|
"entropy": 5.516626405715942,
|
|
"epoch": 1.6240242601224237,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004745404505887899,
|
|
"loss": 5.4447,
|
|
"mean_token_accuracy": 0.18239740282297134,
|
|
"num_tokens": 32258625.0,
|
|
"step": 14460
|
|
},
|
|
{
|
|
"entropy": 5.598090410232544,
|
|
"epoch": 1.6245858370303812,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004745218961240669,
|
|
"loss": 5.3397,
|
|
"mean_token_accuracy": 0.1882559359073639,
|
|
"num_tokens": 32269288.0,
|
|
"step": 14465
|
|
},
|
|
{
|
|
"entropy": 5.580713844299316,
|
|
"epoch": 1.6251474139383388,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004745033353064893,
|
|
"loss": 5.3915,
|
|
"mean_token_accuracy": 0.18425026386976243,
|
|
"num_tokens": 32279888.0,
|
|
"step": 14470
|
|
},
|
|
{
|
|
"entropy": 5.590251159667969,
|
|
"epoch": 1.6257089908462965,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004744847681366482,
|
|
"loss": 5.3984,
|
|
"mean_token_accuracy": 0.19061071127653123,
|
|
"num_tokens": 32291153.0,
|
|
"step": 14475
|
|
},
|
|
{
|
|
"entropy": 5.473784732818603,
|
|
"epoch": 1.626270567754254,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00047446619461513466,
|
|
"loss": 5.2835,
|
|
"mean_token_accuracy": 0.18975742161273956,
|
|
"num_tokens": 32302291.0,
|
|
"step": 14480
|
|
},
|
|
{
|
|
"entropy": 5.510013628005981,
|
|
"epoch": 1.6268321446622114,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004744476147425402,
|
|
"loss": 5.2811,
|
|
"mean_token_accuracy": 0.19587058573961258,
|
|
"num_tokens": 32312015.0,
|
|
"step": 14485
|
|
},
|
|
{
|
|
"entropy": 5.558365535736084,
|
|
"epoch": 1.627393721570169,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.00047442902851945634,
|
|
"loss": 5.4003,
|
|
"mean_token_accuracy": 0.1832302913069725,
|
|
"num_tokens": 32323967.0,
|
|
"step": 14490
|
|
},
|
|
{
|
|
"entropy": 5.5684449672698975,
|
|
"epoch": 1.6279552984781267,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00047441043594647486,
|
|
"loss": 5.4173,
|
|
"mean_token_accuracy": 0.17932213246822357,
|
|
"num_tokens": 32336181.0,
|
|
"step": 14495
|
|
},
|
|
{
|
|
"entropy": 5.585696220397949,
|
|
"epoch": 1.6285168753860841,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00047439183702418765,
|
|
"loss": 5.3534,
|
|
"mean_token_accuracy": 0.1898641675710678,
|
|
"num_tokens": 32346843.0,
|
|
"step": 14500
|
|
},
|
|
{
|
|
"entropy": 5.596896839141846,
|
|
"epoch": 1.6290784522940416,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.00047437323175318716,
|
|
"loss": 5.4467,
|
|
"mean_token_accuracy": 0.18356406092643737,
|
|
"num_tokens": 32358511.0,
|
|
"step": 14505
|
|
},
|
|
{
|
|
"entropy": 5.567827415466309,
|
|
"epoch": 1.6296400292019992,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.00047435462013406554,
|
|
"loss": 5.3398,
|
|
"mean_token_accuracy": 0.18778470605611802,
|
|
"num_tokens": 32370319.0,
|
|
"step": 14510
|
|
},
|
|
{
|
|
"entropy": 5.555706453323364,
|
|
"epoch": 1.630201606109957,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004743360021674155,
|
|
"loss": 5.4285,
|
|
"mean_token_accuracy": 0.18525870591402055,
|
|
"num_tokens": 32381455.0,
|
|
"step": 14515
|
|
},
|
|
{
|
|
"entropy": 5.579962825775146,
|
|
"epoch": 1.6307631830179143,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00047431737785382996,
|
|
"loss": 5.4032,
|
|
"mean_token_accuracy": 0.18517621904611586,
|
|
"num_tokens": 32392553.0,
|
|
"step": 14520
|
|
},
|
|
{
|
|
"entropy": 5.733662414550781,
|
|
"epoch": 1.6313247599258718,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.00047429874719390165,
|
|
"loss": 5.4754,
|
|
"mean_token_accuracy": 0.18362810909748079,
|
|
"num_tokens": 32404736.0,
|
|
"step": 14525
|
|
},
|
|
{
|
|
"entropy": 5.5754382610321045,
|
|
"epoch": 1.6318863368338294,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.00047428011018822404,
|
|
"loss": 5.3613,
|
|
"mean_token_accuracy": 0.18830402046442032,
|
|
"num_tokens": 32415089.0,
|
|
"step": 14530
|
|
},
|
|
{
|
|
"entropy": 5.501427221298218,
|
|
"epoch": 1.6324479137417869,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00047426146683739043,
|
|
"loss": 5.3667,
|
|
"mean_token_accuracy": 0.18111147731542587,
|
|
"num_tokens": 32426814.0,
|
|
"step": 14535
|
|
},
|
|
{
|
|
"entropy": 5.560883188247681,
|
|
"epoch": 1.6330094906497443,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.00047424281714199436,
|
|
"loss": 5.4213,
|
|
"mean_token_accuracy": 0.17635942846536637,
|
|
"num_tokens": 32437173.0,
|
|
"step": 14540
|
|
},
|
|
{
|
|
"entropy": 5.584721612930298,
|
|
"epoch": 1.633571067557702,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00047422416110262975,
|
|
"loss": 5.393,
|
|
"mean_token_accuracy": 0.18085627853870392,
|
|
"num_tokens": 32448597.0,
|
|
"step": 14545
|
|
},
|
|
{
|
|
"entropy": 5.672222852706909,
|
|
"epoch": 1.6341326444656596,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.00047420549871989053,
|
|
"loss": 5.5749,
|
|
"mean_token_accuracy": 0.17191092818975448,
|
|
"num_tokens": 32460906.0,
|
|
"step": 14550
|
|
},
|
|
{
|
|
"entropy": 5.663802146911621,
|
|
"epoch": 1.634694221373617,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.000474186829994371,
|
|
"loss": 5.3813,
|
|
"mean_token_accuracy": 0.18450928777456282,
|
|
"num_tokens": 32473756.0,
|
|
"step": 14555
|
|
},
|
|
{
|
|
"entropy": 5.5878105640411375,
|
|
"epoch": 1.6352557982815745,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.00047416815492666564,
|
|
"loss": 5.4435,
|
|
"mean_token_accuracy": 0.1797104686498642,
|
|
"num_tokens": 32483912.0,
|
|
"step": 14560
|
|
},
|
|
{
|
|
"entropy": 5.566701984405517,
|
|
"epoch": 1.6358173751895322,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004741494735173689,
|
|
"loss": 5.3784,
|
|
"mean_token_accuracy": 0.17997499853372573,
|
|
"num_tokens": 32493899.0,
|
|
"step": 14565
|
|
},
|
|
{
|
|
"entropy": 5.574539089202881,
|
|
"epoch": 1.6363789520974898,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004741307857670757,
|
|
"loss": 5.401,
|
|
"mean_token_accuracy": 0.18635640144348145,
|
|
"num_tokens": 32505215.0,
|
|
"step": 14570
|
|
},
|
|
{
|
|
"entropy": 5.566939735412598,
|
|
"epoch": 1.6369405290054473,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.00047411209167638106,
|
|
"loss": 5.4666,
|
|
"mean_token_accuracy": 0.1814038038253784,
|
|
"num_tokens": 32517288.0,
|
|
"step": 14575
|
|
},
|
|
{
|
|
"entropy": 5.639643812179566,
|
|
"epoch": 1.6375021059134047,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004740933912458801,
|
|
"loss": 5.4262,
|
|
"mean_token_accuracy": 0.18364346027374268,
|
|
"num_tokens": 32529705.0,
|
|
"step": 14580
|
|
},
|
|
{
|
|
"entropy": 5.718049049377441,
|
|
"epoch": 1.6380636828213624,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00047407468447616845,
|
|
"loss": 5.4315,
|
|
"mean_token_accuracy": 0.18514339476823807,
|
|
"num_tokens": 32540868.0,
|
|
"step": 14585
|
|
},
|
|
{
|
|
"entropy": 5.495394134521485,
|
|
"epoch": 1.63862525972932,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.00047405597136784166,
|
|
"loss": 5.3822,
|
|
"mean_token_accuracy": 0.18800296634435654,
|
|
"num_tokens": 32552129.0,
|
|
"step": 14590
|
|
},
|
|
{
|
|
"entropy": 5.505461692810059,
|
|
"epoch": 1.6391868366372775,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004740372519214955,
|
|
"loss": 5.303,
|
|
"mean_token_accuracy": 0.19333642572164536,
|
|
"num_tokens": 32563059.0,
|
|
"step": 14595
|
|
},
|
|
{
|
|
"entropy": 5.553788805007935,
|
|
"epoch": 1.639748413545235,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00047401852613772604,
|
|
"loss": 5.4939,
|
|
"mean_token_accuracy": 0.17190300822257995,
|
|
"num_tokens": 32576628.0,
|
|
"step": 14600
|
|
},
|
|
{
|
|
"entropy": 5.697915983200073,
|
|
"epoch": 1.6403099904531926,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004739997940171295,
|
|
"loss": 5.442,
|
|
"mean_token_accuracy": 0.18500046133995057,
|
|
"num_tokens": 32589138.0,
|
|
"step": 14605
|
|
},
|
|
{
|
|
"entropy": 5.6585431575775145,
|
|
"epoch": 1.6408715673611503,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00047398105556030234,
|
|
"loss": 5.4269,
|
|
"mean_token_accuracy": 0.18122628927230836,
|
|
"num_tokens": 32601865.0,
|
|
"step": 14610
|
|
},
|
|
{
|
|
"entropy": 5.551347351074218,
|
|
"epoch": 1.6414331442691077,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00047396231076784123,
|
|
"loss": 5.389,
|
|
"mean_token_accuracy": 0.18326832950115204,
|
|
"num_tokens": 32612439.0,
|
|
"step": 14615
|
|
},
|
|
{
|
|
"entropy": 5.5520836353302006,
|
|
"epoch": 1.6419947211770651,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004739435596403429,
|
|
"loss": 5.3862,
|
|
"mean_token_accuracy": 0.18279039412736892,
|
|
"num_tokens": 32623002.0,
|
|
"step": 14620
|
|
},
|
|
{
|
|
"entropy": 5.542112588882446,
|
|
"epoch": 1.6425562980850228,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004739248021784046,
|
|
"loss": 5.3594,
|
|
"mean_token_accuracy": 0.1901555374264717,
|
|
"num_tokens": 32632529.0,
|
|
"step": 14625
|
|
},
|
|
{
|
|
"entropy": 5.594372749328613,
|
|
"epoch": 1.6431178749929805,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.0004739060383826234,
|
|
"loss": 5.3717,
|
|
"mean_token_accuracy": 0.18834180235862732,
|
|
"num_tokens": 32643584.0,
|
|
"step": 14630
|
|
},
|
|
{
|
|
"entropy": 5.636145973205567,
|
|
"epoch": 1.6436794519009377,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00047388726825359673,
|
|
"loss": 5.4677,
|
|
"mean_token_accuracy": 0.17899191230535508,
|
|
"num_tokens": 32655899.0,
|
|
"step": 14635
|
|
},
|
|
{
|
|
"entropy": 5.59476408958435,
|
|
"epoch": 1.6442410288088953,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.00047386849179192235,
|
|
"loss": 5.4077,
|
|
"mean_token_accuracy": 0.18391844779253005,
|
|
"num_tokens": 32666747.0,
|
|
"step": 14640
|
|
},
|
|
{
|
|
"entropy": 5.5709222793579105,
|
|
"epoch": 1.644802605716853,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00047384970899819813,
|
|
"loss": 5.3547,
|
|
"mean_token_accuracy": 0.18639909625053405,
|
|
"num_tokens": 32678025.0,
|
|
"step": 14645
|
|
},
|
|
{
|
|
"entropy": 5.5783929347991945,
|
|
"epoch": 1.6453641826248104,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004738309198730219,
|
|
"loss": 5.3089,
|
|
"mean_token_accuracy": 0.1884949326515198,
|
|
"num_tokens": 32688894.0,
|
|
"step": 14650
|
|
},
|
|
{
|
|
"entropy": 5.545256853103638,
|
|
"epoch": 1.6459257595327679,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.00047381212441699217,
|
|
"loss": 5.4134,
|
|
"mean_token_accuracy": 0.18252882212400437,
|
|
"num_tokens": 32699530.0,
|
|
"step": 14655
|
|
},
|
|
{
|
|
"entropy": 5.611769962310791,
|
|
"epoch": 1.6464873364407255,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004737933226307072,
|
|
"loss": 5.4599,
|
|
"mean_token_accuracy": 0.18351722806692122,
|
|
"num_tokens": 32710969.0,
|
|
"step": 14660
|
|
},
|
|
{
|
|
"entropy": 5.597371339797974,
|
|
"epoch": 1.6470489133486832,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00047377451451476586,
|
|
"loss": 5.3096,
|
|
"mean_token_accuracy": 0.19139499962329865,
|
|
"num_tokens": 32723715.0,
|
|
"step": 14665
|
|
},
|
|
{
|
|
"entropy": 5.516621255874634,
|
|
"epoch": 1.6476104902566406,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004737557000697668,
|
|
"loss": 5.3892,
|
|
"mean_token_accuracy": 0.18492224663496018,
|
|
"num_tokens": 32735406.0,
|
|
"step": 14670
|
|
},
|
|
{
|
|
"entropy": 5.529916048049927,
|
|
"epoch": 1.648172067164598,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004737368792963092,
|
|
"loss": 5.3963,
|
|
"mean_token_accuracy": 0.180710369348526,
|
|
"num_tokens": 32746123.0,
|
|
"step": 14675
|
|
},
|
|
{
|
|
"entropy": 5.5279628276824955,
|
|
"epoch": 1.6487336440725557,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.00047371805219499223,
|
|
"loss": 5.3562,
|
|
"mean_token_accuracy": 0.18163390457630157,
|
|
"num_tokens": 32757172.0,
|
|
"step": 14680
|
|
},
|
|
{
|
|
"entropy": 5.475903463363648,
|
|
"epoch": 1.6492952209805134,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00047369921876641547,
|
|
"loss": 5.2677,
|
|
"mean_token_accuracy": 0.18968770056962966,
|
|
"num_tokens": 32767810.0,
|
|
"step": 14685
|
|
},
|
|
{
|
|
"entropy": 5.519390487670899,
|
|
"epoch": 1.6498567978884708,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.00047368037901117854,
|
|
"loss": 5.3575,
|
|
"mean_token_accuracy": 0.1805579200387001,
|
|
"num_tokens": 32779723.0,
|
|
"step": 14690
|
|
},
|
|
{
|
|
"entropy": 5.715040779113769,
|
|
"epoch": 1.6504183747964283,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004736615329298812,
|
|
"loss": 5.6407,
|
|
"mean_token_accuracy": 0.16966511011123658,
|
|
"num_tokens": 32793378.0,
|
|
"step": 14695
|
|
},
|
|
{
|
|
"entropy": 5.625489521026611,
|
|
"epoch": 1.650979951704386,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00047364268052312367,
|
|
"loss": 5.3899,
|
|
"mean_token_accuracy": 0.18817970603704454,
|
|
"num_tokens": 32805643.0,
|
|
"step": 14700
|
|
},
|
|
{
|
|
"entropy": 5.6128757953643795,
|
|
"epoch": 1.6515415286123436,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004736238217915061,
|
|
"loss": 5.3579,
|
|
"mean_token_accuracy": 0.18191513121128083,
|
|
"num_tokens": 32818275.0,
|
|
"step": 14705
|
|
},
|
|
{
|
|
"entropy": 5.448544979095459,
|
|
"epoch": 1.652103105520301,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00047360495673562906,
|
|
"loss": 5.2436,
|
|
"mean_token_accuracy": 0.19300651252269746,
|
|
"num_tokens": 32829548.0,
|
|
"step": 14710
|
|
},
|
|
{
|
|
"entropy": 5.503378009796142,
|
|
"epoch": 1.6526646824282585,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004735860853560931,
|
|
"loss": 5.438,
|
|
"mean_token_accuracy": 0.18519551455974578,
|
|
"num_tokens": 32841472.0,
|
|
"step": 14715
|
|
},
|
|
{
|
|
"entropy": 5.618911838531494,
|
|
"epoch": 1.6532262593362161,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00047356720765349926,
|
|
"loss": 5.455,
|
|
"mean_token_accuracy": 0.18254597783088683,
|
|
"num_tokens": 32852589.0,
|
|
"step": 14720
|
|
},
|
|
{
|
|
"entropy": 5.575884246826172,
|
|
"epoch": 1.6537878362441738,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004735483236284485,
|
|
"loss": 5.3696,
|
|
"mean_token_accuracy": 0.18488479107618333,
|
|
"num_tokens": 32863100.0,
|
|
"step": 14725
|
|
},
|
|
{
|
|
"entropy": 5.642951726913452,
|
|
"epoch": 1.654349413152131,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00047352943328154203,
|
|
"loss": 5.3704,
|
|
"mean_token_accuracy": 0.18474053591489792,
|
|
"num_tokens": 32874912.0,
|
|
"step": 14730
|
|
},
|
|
{
|
|
"entropy": 5.496847915649414,
|
|
"epoch": 1.6549109900600887,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00047351053661338145,
|
|
"loss": 5.3078,
|
|
"mean_token_accuracy": 0.18862911462783813,
|
|
"num_tokens": 32886249.0,
|
|
"step": 14735
|
|
},
|
|
{
|
|
"entropy": 5.495778131484985,
|
|
"epoch": 1.6554725669680463,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004734916336245684,
|
|
"loss": 5.3942,
|
|
"mean_token_accuracy": 0.17536802887916564,
|
|
"num_tokens": 32898010.0,
|
|
"step": 14740
|
|
},
|
|
{
|
|
"entropy": 5.533234310150147,
|
|
"epoch": 1.6560341438760038,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004734727243157047,
|
|
"loss": 5.2644,
|
|
"mean_token_accuracy": 0.18930499851703644,
|
|
"num_tokens": 32909103.0,
|
|
"step": 14745
|
|
},
|
|
{
|
|
"entropy": 5.517409420013427,
|
|
"epoch": 1.6565957207839612,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00047345380868739253,
|
|
"loss": 5.3499,
|
|
"mean_token_accuracy": 0.18766181766986847,
|
|
"num_tokens": 32919612.0,
|
|
"step": 14750
|
|
},
|
|
{
|
|
"entropy": 5.461494255065918,
|
|
"epoch": 1.6571572976919189,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004734348867402341,
|
|
"loss": 5.3019,
|
|
"mean_token_accuracy": 0.19135154634714127,
|
|
"num_tokens": 32930072.0,
|
|
"step": 14755
|
|
},
|
|
{
|
|
"entropy": 5.66618070602417,
|
|
"epoch": 1.6577188745998765,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004734159584748319,
|
|
"loss": 5.5138,
|
|
"mean_token_accuracy": 0.1844464957714081,
|
|
"num_tokens": 32941984.0,
|
|
"step": 14760
|
|
},
|
|
{
|
|
"entropy": 5.592111968994141,
|
|
"epoch": 1.658280451507834,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00047339702389178874,
|
|
"loss": 5.3599,
|
|
"mean_token_accuracy": 0.19003164023160934,
|
|
"num_tokens": 32952767.0,
|
|
"step": 14765
|
|
},
|
|
{
|
|
"entropy": 5.589803028106689,
|
|
"epoch": 1.6588420284157914,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.00047337808299170725,
|
|
"loss": 5.3993,
|
|
"mean_token_accuracy": 0.18156627118587493,
|
|
"num_tokens": 32964553.0,
|
|
"step": 14770
|
|
},
|
|
{
|
|
"entropy": 5.563896179199219,
|
|
"epoch": 1.659403605323749,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.00047335913577519075,
|
|
"loss": 5.3401,
|
|
"mean_token_accuracy": 0.1827165275812149,
|
|
"num_tokens": 32975526.0,
|
|
"step": 14775
|
|
},
|
|
{
|
|
"entropy": 5.505002069473266,
|
|
"epoch": 1.6599651822317067,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00047334018224284244,
|
|
"loss": 5.3922,
|
|
"mean_token_accuracy": 0.18905986547470094,
|
|
"num_tokens": 32987025.0,
|
|
"step": 14780
|
|
},
|
|
{
|
|
"entropy": 5.696928310394287,
|
|
"epoch": 1.6605267591396642,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004733212223952657,
|
|
"loss": 5.393,
|
|
"mean_token_accuracy": 0.18647790253162383,
|
|
"num_tokens": 32997447.0,
|
|
"step": 14785
|
|
},
|
|
{
|
|
"entropy": 5.665005445480347,
|
|
"epoch": 1.6610883360476216,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.00047330225623306443,
|
|
"loss": 5.4116,
|
|
"mean_token_accuracy": 0.18931203484535217,
|
|
"num_tokens": 33007432.0,
|
|
"step": 14790
|
|
},
|
|
{
|
|
"entropy": 5.550873756408691,
|
|
"epoch": 1.6616499129555793,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.00047328328375684237,
|
|
"loss": 5.4022,
|
|
"mean_token_accuracy": 0.18748948872089385,
|
|
"num_tokens": 33018547.0,
|
|
"step": 14795
|
|
},
|
|
{
|
|
"entropy": 5.556125783920288,
|
|
"epoch": 1.662211489863537,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004732643049672036,
|
|
"loss": 5.3341,
|
|
"mean_token_accuracy": 0.1916821777820587,
|
|
"num_tokens": 33029092.0,
|
|
"step": 14800
|
|
},
|
|
{
|
|
"entropy": 5.5294407367706295,
|
|
"epoch": 1.6627730667714944,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004732453198647525,
|
|
"loss": 5.3738,
|
|
"mean_token_accuracy": 0.18623017370700837,
|
|
"num_tokens": 33040498.0,
|
|
"step": 14805
|
|
},
|
|
{
|
|
"entropy": 5.674070644378662,
|
|
"epoch": 1.6633346436794518,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004732263284500936,
|
|
"loss": 5.4432,
|
|
"mean_token_accuracy": 0.17861680388450624,
|
|
"num_tokens": 33052203.0,
|
|
"step": 14810
|
|
},
|
|
{
|
|
"entropy": 5.612527561187744,
|
|
"epoch": 1.6638962205874095,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004732073307238314,
|
|
"loss": 5.3706,
|
|
"mean_token_accuracy": 0.18829278647899628,
|
|
"num_tokens": 33063453.0,
|
|
"step": 14815
|
|
},
|
|
{
|
|
"entropy": 5.528048753738403,
|
|
"epoch": 1.6644577974953672,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.000473188326686571,
|
|
"loss": 5.4549,
|
|
"mean_token_accuracy": 0.18797820508480073,
|
|
"num_tokens": 33075511.0,
|
|
"step": 14820
|
|
},
|
|
{
|
|
"entropy": 5.544820976257324,
|
|
"epoch": 1.6650193744033244,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.00047316931633891736,
|
|
"loss": 5.4192,
|
|
"mean_token_accuracy": 0.18570923805236816,
|
|
"num_tokens": 33086094.0,
|
|
"step": 14825
|
|
},
|
|
{
|
|
"entropy": 5.723085737228393,
|
|
"epoch": 1.665580951311282,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004731502996814759,
|
|
"loss": 5.4785,
|
|
"mean_token_accuracy": 0.18691678792238237,
|
|
"num_tokens": 33096430.0,
|
|
"step": 14830
|
|
},
|
|
{
|
|
"entropy": 5.544121360778808,
|
|
"epoch": 1.6661425282192397,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.00047313127671485194,
|
|
"loss": 5.3575,
|
|
"mean_token_accuracy": 0.18353654593229293,
|
|
"num_tokens": 33108040.0,
|
|
"step": 14835
|
|
},
|
|
{
|
|
"entropy": 5.521466827392578,
|
|
"epoch": 1.6667041051271971,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004731122474396514,
|
|
"loss": 5.3552,
|
|
"mean_token_accuracy": 0.18125558495521546,
|
|
"num_tokens": 33118282.0,
|
|
"step": 14840
|
|
},
|
|
{
|
|
"entropy": 5.588000249862671,
|
|
"epoch": 1.6672656820351546,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00047309321185648,
|
|
"loss": 5.4326,
|
|
"mean_token_accuracy": 0.18425653874874115,
|
|
"num_tokens": 33130308.0,
|
|
"step": 14845
|
|
},
|
|
{
|
|
"entropy": 5.67760157585144,
|
|
"epoch": 1.6678272589431122,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00047307416996594386,
|
|
"loss": 5.4662,
|
|
"mean_token_accuracy": 0.18178492337465285,
|
|
"num_tokens": 33140260.0,
|
|
"step": 14850
|
|
},
|
|
{
|
|
"entropy": 5.555676698684692,
|
|
"epoch": 1.66838883585107,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004730551217686495,
|
|
"loss": 5.3738,
|
|
"mean_token_accuracy": 0.1839437499642372,
|
|
"num_tokens": 33152064.0,
|
|
"step": 14855
|
|
},
|
|
{
|
|
"entropy": 5.609837865829467,
|
|
"epoch": 1.6689504127590273,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004730360672652031,
|
|
"loss": 5.4331,
|
|
"mean_token_accuracy": 0.18601180613040924,
|
|
"num_tokens": 33164057.0,
|
|
"step": 14860
|
|
},
|
|
{
|
|
"entropy": 5.552616930007934,
|
|
"epoch": 1.6695119896669848,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00047301700645621154,
|
|
"loss": 5.3969,
|
|
"mean_token_accuracy": 0.186902716755867,
|
|
"num_tokens": 33175281.0,
|
|
"step": 14865
|
|
},
|
|
{
|
|
"entropy": 5.562746953964234,
|
|
"epoch": 1.6700735665749424,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004729979393422817,
|
|
"loss": 5.3373,
|
|
"mean_token_accuracy": 0.18874657303094863,
|
|
"num_tokens": 33186615.0,
|
|
"step": 14870
|
|
},
|
|
{
|
|
"entropy": 5.572027587890625,
|
|
"epoch": 1.6706351434829,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004729788659240206,
|
|
"loss": 5.4406,
|
|
"mean_token_accuracy": 0.18436575084924697,
|
|
"num_tokens": 33198693.0,
|
|
"step": 14875
|
|
},
|
|
{
|
|
"entropy": 5.623181486129761,
|
|
"epoch": 1.6711967203908575,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004729597862020358,
|
|
"loss": 5.4047,
|
|
"mean_token_accuracy": 0.1872449114918709,
|
|
"num_tokens": 33209743.0,
|
|
"step": 14880
|
|
},
|
|
{
|
|
"entropy": 5.558723306655883,
|
|
"epoch": 1.671758297298815,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00047294070017693453,
|
|
"loss": 5.3082,
|
|
"mean_token_accuracy": 0.19150487333536148,
|
|
"num_tokens": 33220907.0,
|
|
"step": 14885
|
|
},
|
|
{
|
|
"entropy": 5.617772722244263,
|
|
"epoch": 1.6723198742067726,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.00047292160784932454,
|
|
"loss": 5.4746,
|
|
"mean_token_accuracy": 0.1800364747643471,
|
|
"num_tokens": 33232278.0,
|
|
"step": 14890
|
|
},
|
|
{
|
|
"entropy": 5.626573467254639,
|
|
"epoch": 1.6728814511147303,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00047290250921981386,
|
|
"loss": 5.3738,
|
|
"mean_token_accuracy": 0.1844427466392517,
|
|
"num_tokens": 33243920.0,
|
|
"step": 14895
|
|
},
|
|
{
|
|
"entropy": 5.598547506332397,
|
|
"epoch": 1.6734430280226877,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00047288340428901053,
|
|
"loss": 5.4237,
|
|
"mean_token_accuracy": 0.18580759763717652,
|
|
"num_tokens": 33254467.0,
|
|
"step": 14900
|
|
},
|
|
{
|
|
"entropy": 5.502971839904785,
|
|
"epoch": 1.6740046049306452,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.00047286429305752283,
|
|
"loss": 5.3679,
|
|
"mean_token_accuracy": 0.18248131275177001,
|
|
"num_tokens": 33265536.0,
|
|
"step": 14905
|
|
},
|
|
{
|
|
"entropy": 5.5815403938293455,
|
|
"epoch": 1.6745661818386028,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.00047284517552595933,
|
|
"loss": 5.412,
|
|
"mean_token_accuracy": 0.18008261770009995,
|
|
"num_tokens": 33277233.0,
|
|
"step": 14910
|
|
},
|
|
{
|
|
"entropy": 5.517041254043579,
|
|
"epoch": 1.6751277587465605,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004728260516949287,
|
|
"loss": 5.2767,
|
|
"mean_token_accuracy": 0.19094849675893782,
|
|
"num_tokens": 33287873.0,
|
|
"step": 14915
|
|
},
|
|
{
|
|
"entropy": 5.530544853210449,
|
|
"epoch": 1.6756893356545177,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004728069215650399,
|
|
"loss": 5.3918,
|
|
"mean_token_accuracy": 0.18779995441436767,
|
|
"num_tokens": 33298888.0,
|
|
"step": 14920
|
|
},
|
|
{
|
|
"entropy": 5.499293565750122,
|
|
"epoch": 1.6762509125624754,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.0004727877851369019,
|
|
"loss": 5.2611,
|
|
"mean_token_accuracy": 0.19046627432107927,
|
|
"num_tokens": 33309607.0,
|
|
"step": 14925
|
|
},
|
|
{
|
|
"entropy": 5.550456094741821,
|
|
"epoch": 1.676812489470433,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00047276864241112417,
|
|
"loss": 5.3027,
|
|
"mean_token_accuracy": 0.19379159212112426,
|
|
"num_tokens": 33320582.0,
|
|
"step": 14930
|
|
},
|
|
{
|
|
"entropy": 5.508336687088013,
|
|
"epoch": 1.6773740663783905,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004727494933883161,
|
|
"loss": 5.3578,
|
|
"mean_token_accuracy": 0.19197508096694946,
|
|
"num_tokens": 33332145.0,
|
|
"step": 14935
|
|
},
|
|
{
|
|
"entropy": 5.694448089599609,
|
|
"epoch": 1.677935643286348,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004727303380690876,
|
|
"loss": 5.6083,
|
|
"mean_token_accuracy": 0.17880181670188905,
|
|
"num_tokens": 33343963.0,
|
|
"step": 14940
|
|
},
|
|
{
|
|
"entropy": 5.568664169311523,
|
|
"epoch": 1.6784972201943056,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004727111764540484,
|
|
"loss": 5.4014,
|
|
"mean_token_accuracy": 0.18977900594472885,
|
|
"num_tokens": 33354931.0,
|
|
"step": 14945
|
|
},
|
|
{
|
|
"entropy": 5.5538811683654785,
|
|
"epoch": 1.6790587971022632,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00047269200854380854,
|
|
"loss": 5.3958,
|
|
"mean_token_accuracy": 0.1820443630218506,
|
|
"num_tokens": 33365686.0,
|
|
"step": 14950
|
|
},
|
|
{
|
|
"entropy": 5.643840694427491,
|
|
"epoch": 1.6796203740102207,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00047267283433897854,
|
|
"loss": 5.3946,
|
|
"mean_token_accuracy": 0.18865703791379929,
|
|
"num_tokens": 33377099.0,
|
|
"step": 14955
|
|
},
|
|
{
|
|
"entropy": 5.581523275375366,
|
|
"epoch": 1.6801819509181781,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.00047265365384016887,
|
|
"loss": 5.4437,
|
|
"mean_token_accuracy": 0.1765981525182724,
|
|
"num_tokens": 33389477.0,
|
|
"step": 14960
|
|
},
|
|
{
|
|
"entropy": 5.618612241744995,
|
|
"epoch": 1.6807435278261358,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00047263446704799017,
|
|
"loss": 5.4663,
|
|
"mean_token_accuracy": 0.18694839626550674,
|
|
"num_tokens": 33401970.0,
|
|
"step": 14965
|
|
},
|
|
{
|
|
"entropy": 5.5506926536560055,
|
|
"epoch": 1.6813051047340934,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00047261527396305343,
|
|
"loss": 5.3398,
|
|
"mean_token_accuracy": 0.182860167324543,
|
|
"num_tokens": 33412986.0,
|
|
"step": 14970
|
|
},
|
|
{
|
|
"entropy": 5.588017368316651,
|
|
"epoch": 1.6818666816420509,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00047259607458596966,
|
|
"loss": 5.4763,
|
|
"mean_token_accuracy": 0.18464904576539992,
|
|
"num_tokens": 33424717.0,
|
|
"step": 14975
|
|
},
|
|
{
|
|
"entropy": 5.476791286468506,
|
|
"epoch": 1.6824282585500083,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.00047257686891735023,
|
|
"loss": 5.287,
|
|
"mean_token_accuracy": 0.18902431577444076,
|
|
"num_tokens": 33436713.0,
|
|
"step": 14980
|
|
},
|
|
{
|
|
"entropy": 5.656904935836792,
|
|
"epoch": 1.682989835457966,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00047255765695780665,
|
|
"loss": 5.4831,
|
|
"mean_token_accuracy": 0.17948793321847917,
|
|
"num_tokens": 33447532.0,
|
|
"step": 14985
|
|
},
|
|
{
|
|
"entropy": 5.4818048000335695,
|
|
"epoch": 1.6835514123659236,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004725384387079507,
|
|
"loss": 5.3035,
|
|
"mean_token_accuracy": 0.18263816684484482,
|
|
"num_tokens": 33458530.0,
|
|
"step": 14990
|
|
},
|
|
{
|
|
"entropy": 5.551608562469482,
|
|
"epoch": 1.684112989273881,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.00047251921416839425,
|
|
"loss": 5.4123,
|
|
"mean_token_accuracy": 0.17943487763404847,
|
|
"num_tokens": 33469617.0,
|
|
"step": 14995
|
|
},
|
|
{
|
|
"entropy": 5.626010417938232,
|
|
"epoch": 1.6846745661818385,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004724999833397494,
|
|
"loss": 5.323,
|
|
"mean_token_accuracy": 0.19285964518785476,
|
|
"num_tokens": 33479622.0,
|
|
"step": 15000
|
|
},
|
|
{
|
|
"epoch": 1.6846745661818385,
|
|
"eval_entropy": 5.383775010870264,
|
|
"eval_loss": 5.4565653800964355,
|
|
"eval_mean_token_accuracy": 0.1902181858315522,
|
|
"eval_num_tokens": 33479622.0,
|
|
"eval_runtime": 24.0402,
|
|
"eval_samples_per_second": 1290.047,
|
|
"eval_steps_per_second": 161.271,
|
|
"step": 15000
|
|
},
|
|
{
|
|
"entropy": 5.4471039295196535,
|
|
"epoch": 1.6852361430897962,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004724807462226285,
|
|
"loss": 5.2883,
|
|
"mean_token_accuracy": 0.19635369181632994,
|
|
"num_tokens": 33490907.0,
|
|
"step": 15005
|
|
},
|
|
{
|
|
"entropy": 5.551421070098877,
|
|
"epoch": 1.6857977199977539,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.000472461502817644,
|
|
"loss": 5.4051,
|
|
"mean_token_accuracy": 0.18559968769550322,
|
|
"num_tokens": 33501884.0,
|
|
"step": 15010
|
|
},
|
|
{
|
|
"entropy": 5.557754468917847,
|
|
"epoch": 1.6863592969057113,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004724422531254087,
|
|
"loss": 5.2736,
|
|
"mean_token_accuracy": 0.18997342735528946,
|
|
"num_tokens": 33512106.0,
|
|
"step": 15015
|
|
},
|
|
{
|
|
"entropy": 5.582626485824585,
|
|
"epoch": 1.6869208738136687,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004724229971465355,
|
|
"loss": 5.3867,
|
|
"mean_token_accuracy": 0.19005310386419297,
|
|
"num_tokens": 33522889.0,
|
|
"step": 15020
|
|
},
|
|
{
|
|
"entropy": 5.546910095214844,
|
|
"epoch": 1.6874824507216264,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004724037348816375,
|
|
"loss": 5.3544,
|
|
"mean_token_accuracy": 0.18871113210916518,
|
|
"num_tokens": 33534601.0,
|
|
"step": 15025
|
|
},
|
|
{
|
|
"entropy": 5.513442134857177,
|
|
"epoch": 1.6880440276295838,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.000472384466331328,
|
|
"loss": 5.4522,
|
|
"mean_token_accuracy": 0.1847732901573181,
|
|
"num_tokens": 33545300.0,
|
|
"step": 15030
|
|
},
|
|
{
|
|
"entropy": 5.687134075164795,
|
|
"epoch": 1.6886056045375413,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004723651914962205,
|
|
"loss": 5.4112,
|
|
"mean_token_accuracy": 0.18240966796875,
|
|
"num_tokens": 33555581.0,
|
|
"step": 15035
|
|
},
|
|
{
|
|
"entropy": 5.613533639907837,
|
|
"epoch": 1.689167181445499,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.00047234591037692884,
|
|
"loss": 5.4,
|
|
"mean_token_accuracy": 0.18385293036699296,
|
|
"num_tokens": 33566902.0,
|
|
"step": 15040
|
|
},
|
|
{
|
|
"entropy": 5.57280707359314,
|
|
"epoch": 1.6897287583534566,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.00047232662297406683,
|
|
"loss": 5.4161,
|
|
"mean_token_accuracy": 0.18380822986364365,
|
|
"num_tokens": 33578316.0,
|
|
"step": 15045
|
|
},
|
|
{
|
|
"entropy": 5.603354120254517,
|
|
"epoch": 1.690290335261414,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004723073292882485,
|
|
"loss": 5.4311,
|
|
"mean_token_accuracy": 0.17819164395332338,
|
|
"num_tokens": 33590242.0,
|
|
"step": 15050
|
|
},
|
|
{
|
|
"entropy": 5.548894309997559,
|
|
"epoch": 1.6908519121693715,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00047228802932008836,
|
|
"loss": 5.3229,
|
|
"mean_token_accuracy": 0.1852489396929741,
|
|
"num_tokens": 33601277.0,
|
|
"step": 15055
|
|
},
|
|
{
|
|
"entropy": 5.528900814056397,
|
|
"epoch": 1.6914134890773291,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004722687230702009,
|
|
"loss": 5.3619,
|
|
"mean_token_accuracy": 0.1814175859093666,
|
|
"num_tokens": 33612423.0,
|
|
"step": 15060
|
|
},
|
|
{
|
|
"entropy": 5.672621393203736,
|
|
"epoch": 1.6919750659852868,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004722494105392007,
|
|
"loss": 5.4417,
|
|
"mean_token_accuracy": 0.18055731058120728,
|
|
"num_tokens": 33624250.0,
|
|
"step": 15065
|
|
},
|
|
{
|
|
"entropy": 5.6068737506866455,
|
|
"epoch": 1.6925366428932442,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004722300917277029,
|
|
"loss": 5.3778,
|
|
"mean_token_accuracy": 0.18464804738759993,
|
|
"num_tokens": 33636379.0,
|
|
"step": 15070
|
|
},
|
|
{
|
|
"entropy": 5.537733650207519,
|
|
"epoch": 1.6930982198012017,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004722107666363224,
|
|
"loss": 5.3834,
|
|
"mean_token_accuracy": 0.18061763942241668,
|
|
"num_tokens": 33648296.0,
|
|
"step": 15075
|
|
},
|
|
{
|
|
"entropy": 5.479118394851684,
|
|
"epoch": 1.6936597967091593,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004721914352656746,
|
|
"loss": 5.4005,
|
|
"mean_token_accuracy": 0.18329438269138337,
|
|
"num_tokens": 33659438.0,
|
|
"step": 15080
|
|
},
|
|
{
|
|
"entropy": 5.636709928512573,
|
|
"epoch": 1.694221373617117,
|
|
"grad_norm": 2.71875,
|
|
"learning_rate": 0.000472172097616375,
|
|
"loss": 5.4973,
|
|
"mean_token_accuracy": 0.18170636296272277,
|
|
"num_tokens": 33670893.0,
|
|
"step": 15085
|
|
},
|
|
{
|
|
"entropy": 5.621981287002564,
|
|
"epoch": 1.6947829505250744,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004721527536890394,
|
|
"loss": 5.3633,
|
|
"mean_token_accuracy": 0.1880887269973755,
|
|
"num_tokens": 33681487.0,
|
|
"step": 15090
|
|
},
|
|
{
|
|
"entropy": 5.557020998001098,
|
|
"epoch": 1.6953445274330319,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004721334034842836,
|
|
"loss": 5.3835,
|
|
"mean_token_accuracy": 0.19438282400369644,
|
|
"num_tokens": 33692925.0,
|
|
"step": 15095
|
|
},
|
|
{
|
|
"entropy": 5.584948348999023,
|
|
"epoch": 1.6959061043409895,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004721140470027238,
|
|
"loss": 5.3541,
|
|
"mean_token_accuracy": 0.18742522597312927,
|
|
"num_tokens": 33703559.0,
|
|
"step": 15100
|
|
},
|
|
{
|
|
"entropy": 5.504276752471924,
|
|
"epoch": 1.6964676812489472,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.00047209468424497627,
|
|
"loss": 5.3614,
|
|
"mean_token_accuracy": 0.18574756234884263,
|
|
"num_tokens": 33715041.0,
|
|
"step": 15105
|
|
},
|
|
{
|
|
"entropy": 5.49846305847168,
|
|
"epoch": 1.6970292581569046,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.0004720753152116576,
|
|
"loss": 5.3071,
|
|
"mean_token_accuracy": 0.18679920136928557,
|
|
"num_tokens": 33726334.0,
|
|
"step": 15110
|
|
},
|
|
{
|
|
"entropy": 5.611520433425904,
|
|
"epoch": 1.697590835064862,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00047205593990338443,
|
|
"loss": 5.3407,
|
|
"mean_token_accuracy": 0.18786376416683198,
|
|
"num_tokens": 33738663.0,
|
|
"step": 15115
|
|
},
|
|
{
|
|
"entropy": 5.489375638961792,
|
|
"epoch": 1.6981524119728197,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004720365583207737,
|
|
"loss": 5.3027,
|
|
"mean_token_accuracy": 0.19285307973623275,
|
|
"num_tokens": 33749202.0,
|
|
"step": 15120
|
|
},
|
|
{
|
|
"entropy": 5.4849128246307375,
|
|
"epoch": 1.6987139888807772,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004720171704644425,
|
|
"loss": 5.2708,
|
|
"mean_token_accuracy": 0.19944576025009156,
|
|
"num_tokens": 33759809.0,
|
|
"step": 15125
|
|
},
|
|
{
|
|
"entropy": 5.494880485534668,
|
|
"epoch": 1.6992755657887346,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004719977763350083,
|
|
"loss": 5.3711,
|
|
"mean_token_accuracy": 0.18570796847343446,
|
|
"num_tokens": 33771374.0,
|
|
"step": 15130
|
|
},
|
|
{
|
|
"entropy": 5.537381267547607,
|
|
"epoch": 1.6998371426966923,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.00047197837593308833,
|
|
"loss": 5.3648,
|
|
"mean_token_accuracy": 0.18862795382738112,
|
|
"num_tokens": 33781645.0,
|
|
"step": 15135
|
|
},
|
|
{
|
|
"entropy": 5.565759325027466,
|
|
"epoch": 1.70039871960465,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004719589692593006,
|
|
"loss": 5.3458,
|
|
"mean_token_accuracy": 0.18986233025789262,
|
|
"num_tokens": 33793032.0,
|
|
"step": 15140
|
|
},
|
|
{
|
|
"entropy": 5.6880542755126955,
|
|
"epoch": 1.7009602965126074,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004719395563142629,
|
|
"loss": 5.5586,
|
|
"mean_token_accuracy": 0.17638744413852692,
|
|
"num_tokens": 33805116.0,
|
|
"step": 15145
|
|
},
|
|
{
|
|
"entropy": 5.646629333496094,
|
|
"epoch": 1.7015218734205648,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.0004719201370985933,
|
|
"loss": 5.3964,
|
|
"mean_token_accuracy": 0.18295258432626724,
|
|
"num_tokens": 33817135.0,
|
|
"step": 15150
|
|
},
|
|
{
|
|
"entropy": 5.574564695358276,
|
|
"epoch": 1.7020834503285225,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00047190071161291007,
|
|
"loss": 5.3841,
|
|
"mean_token_accuracy": 0.18291592746973037,
|
|
"num_tokens": 33830187.0,
|
|
"step": 15155
|
|
},
|
|
{
|
|
"entropy": 5.458574628829956,
|
|
"epoch": 1.7026450272364801,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.00047188127985783195,
|
|
"loss": 5.3872,
|
|
"mean_token_accuracy": 0.17977226823568343,
|
|
"num_tokens": 33841297.0,
|
|
"step": 15160
|
|
},
|
|
{
|
|
"entropy": 5.59752893447876,
|
|
"epoch": 1.7032066041444376,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00047186184183397754,
|
|
"loss": 5.3761,
|
|
"mean_token_accuracy": 0.18661357313394547,
|
|
"num_tokens": 33852888.0,
|
|
"step": 15165
|
|
},
|
|
{
|
|
"entropy": 5.568714380264282,
|
|
"epoch": 1.703768181052395,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00047184239754196564,
|
|
"loss": 5.4437,
|
|
"mean_token_accuracy": 0.18394217193126677,
|
|
"num_tokens": 33865165.0,
|
|
"step": 15170
|
|
},
|
|
{
|
|
"entropy": 5.533801794052124,
|
|
"epoch": 1.7043297579603527,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004718229469824155,
|
|
"loss": 5.2487,
|
|
"mean_token_accuracy": 0.19285314679145812,
|
|
"num_tokens": 33875865.0,
|
|
"step": 15175
|
|
},
|
|
{
|
|
"entropy": 5.592979621887207,
|
|
"epoch": 1.7048913348683103,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.00047180349015594634,
|
|
"loss": 5.482,
|
|
"mean_token_accuracy": 0.17598691284656526,
|
|
"num_tokens": 33887519.0,
|
|
"step": 15180
|
|
},
|
|
{
|
|
"entropy": 5.504102420806885,
|
|
"epoch": 1.7054529117762678,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004717840270631778,
|
|
"loss": 5.2914,
|
|
"mean_token_accuracy": 0.19494041949510574,
|
|
"num_tokens": 33898762.0,
|
|
"step": 15185
|
|
},
|
|
{
|
|
"entropy": 5.438482666015625,
|
|
"epoch": 1.7060144886842252,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.00047176455770472946,
|
|
"loss": 5.2926,
|
|
"mean_token_accuracy": 0.1906571790575981,
|
|
"num_tokens": 33911109.0,
|
|
"step": 15190
|
|
},
|
|
{
|
|
"entropy": 5.634068346023559,
|
|
"epoch": 1.706576065592183,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.00047174508208122135,
|
|
"loss": 5.5684,
|
|
"mean_token_accuracy": 0.17408591955900193,
|
|
"num_tokens": 33922741.0,
|
|
"step": 15195
|
|
},
|
|
{
|
|
"entropy": 5.581002140045166,
|
|
"epoch": 1.7071376425001406,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004717256001932735,
|
|
"loss": 5.3811,
|
|
"mean_token_accuracy": 0.18276015520095826,
|
|
"num_tokens": 33933234.0,
|
|
"step": 15200
|
|
},
|
|
{
|
|
"entropy": 5.526957702636719,
|
|
"epoch": 1.707699219408098,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00047170611204150624,
|
|
"loss": 5.3139,
|
|
"mean_token_accuracy": 0.18669446408748627,
|
|
"num_tokens": 33943667.0,
|
|
"step": 15205
|
|
},
|
|
{
|
|
"entropy": 5.519064235687256,
|
|
"epoch": 1.7082607963160554,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004716866176265401,
|
|
"loss": 5.2847,
|
|
"mean_token_accuracy": 0.19637755006551744,
|
|
"num_tokens": 33954499.0,
|
|
"step": 15210
|
|
},
|
|
{
|
|
"entropy": 5.502477359771729,
|
|
"epoch": 1.708822373224013,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.00047166711694899573,
|
|
"loss": 5.3491,
|
|
"mean_token_accuracy": 0.19001880586147307,
|
|
"num_tokens": 33964700.0,
|
|
"step": 15215
|
|
},
|
|
{
|
|
"entropy": 5.514243841171265,
|
|
"epoch": 1.7093839501319705,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00047164761000949404,
|
|
"loss": 5.4042,
|
|
"mean_token_accuracy": 0.18515589386224746,
|
|
"num_tokens": 33977759.0,
|
|
"step": 15220
|
|
},
|
|
{
|
|
"entropy": 5.6283937931060795,
|
|
"epoch": 1.709945527039928,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004716280968086563,
|
|
"loss": 5.4639,
|
|
"mean_token_accuracy": 0.1797819197177887,
|
|
"num_tokens": 33990019.0,
|
|
"step": 15225
|
|
},
|
|
{
|
|
"entropy": 5.613171672821045,
|
|
"epoch": 1.7105071039478856,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004716085773471036,
|
|
"loss": 5.3503,
|
|
"mean_token_accuracy": 0.18897001296281815,
|
|
"num_tokens": 34000663.0,
|
|
"step": 15230
|
|
},
|
|
{
|
|
"entropy": 5.459926891326904,
|
|
"epoch": 1.7110686808558433,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.00047158905162545756,
|
|
"loss": 5.2561,
|
|
"mean_token_accuracy": 0.19417371451854706,
|
|
"num_tokens": 34012768.0,
|
|
"step": 15235
|
|
},
|
|
{
|
|
"entropy": 5.470266914367675,
|
|
"epoch": 1.7116302577638007,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.00047156951964433984,
|
|
"loss": 5.2923,
|
|
"mean_token_accuracy": 0.19037491083145142,
|
|
"num_tokens": 34025801.0,
|
|
"step": 15240
|
|
},
|
|
{
|
|
"entropy": 5.491405773162842,
|
|
"epoch": 1.7121918346717582,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.00047154998140437246,
|
|
"loss": 5.2082,
|
|
"mean_token_accuracy": 0.20296344310045242,
|
|
"num_tokens": 34036553.0,
|
|
"step": 15245
|
|
},
|
|
{
|
|
"entropy": 5.527611255645752,
|
|
"epoch": 1.7127534115797158,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00047153043690617737,
|
|
"loss": 5.3886,
|
|
"mean_token_accuracy": 0.18829963505268096,
|
|
"num_tokens": 34048352.0,
|
|
"step": 15250
|
|
},
|
|
{
|
|
"entropy": 5.576293706893921,
|
|
"epoch": 1.7133149884876735,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.000471510886150377,
|
|
"loss": 5.3432,
|
|
"mean_token_accuracy": 0.19270518571138381,
|
|
"num_tokens": 34059617.0,
|
|
"step": 15255
|
|
},
|
|
{
|
|
"entropy": 5.562987804412842,
|
|
"epoch": 1.713876565395631,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004714913291375938,
|
|
"loss": 5.4001,
|
|
"mean_token_accuracy": 0.18346952199935912,
|
|
"num_tokens": 34071176.0,
|
|
"step": 15260
|
|
},
|
|
{
|
|
"entropy": 5.4848121166229244,
|
|
"epoch": 1.7144381423035884,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00047147176586845036,
|
|
"loss": 5.3518,
|
|
"mean_token_accuracy": 0.18714902997016908,
|
|
"num_tokens": 34081883.0,
|
|
"step": 15265
|
|
},
|
|
{
|
|
"entropy": 5.551849412918091,
|
|
"epoch": 1.714999719211546,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004714521963435698,
|
|
"loss": 5.3679,
|
|
"mean_token_accuracy": 0.18345563858747482,
|
|
"num_tokens": 34092938.0,
|
|
"step": 15270
|
|
},
|
|
{
|
|
"entropy": 5.604917812347412,
|
|
"epoch": 1.7155612961195037,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00047143262056357506,
|
|
"loss": 5.3316,
|
|
"mean_token_accuracy": 0.19288102239370347,
|
|
"num_tokens": 34104758.0,
|
|
"step": 15275
|
|
},
|
|
{
|
|
"entropy": 5.555082178115844,
|
|
"epoch": 1.7161228730274611,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00047141303852908965,
|
|
"loss": 5.2539,
|
|
"mean_token_accuracy": 0.19242660254240035,
|
|
"num_tokens": 34114752.0,
|
|
"step": 15280
|
|
},
|
|
{
|
|
"entropy": 5.581843376159668,
|
|
"epoch": 1.7166844499354186,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004713934502407367,
|
|
"loss": 5.4126,
|
|
"mean_token_accuracy": 0.18007928133010864,
|
|
"num_tokens": 34125547.0,
|
|
"step": 15285
|
|
},
|
|
{
|
|
"entropy": 5.675565767288208,
|
|
"epoch": 1.7172460268433762,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004713738556991402,
|
|
"loss": 5.4546,
|
|
"mean_token_accuracy": 0.1848657414317131,
|
|
"num_tokens": 34136085.0,
|
|
"step": 15290
|
|
},
|
|
{
|
|
"entropy": 5.5911674976348875,
|
|
"epoch": 1.717807603751334,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.000471354254904924,
|
|
"loss": 5.3871,
|
|
"mean_token_accuracy": 0.19026076495647432,
|
|
"num_tokens": 34147536.0,
|
|
"step": 15295
|
|
},
|
|
{
|
|
"entropy": 5.579338026046753,
|
|
"epoch": 1.7183691806592913,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00047133464785871216,
|
|
"loss": 5.5024,
|
|
"mean_token_accuracy": 0.1849495455622673,
|
|
"num_tokens": 34158238.0,
|
|
"step": 15300
|
|
},
|
|
{
|
|
"entropy": 5.500206089019775,
|
|
"epoch": 1.7189307575672488,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.000471315034561129,
|
|
"loss": 5.2063,
|
|
"mean_token_accuracy": 0.1989926964044571,
|
|
"num_tokens": 34169793.0,
|
|
"step": 15305
|
|
},
|
|
{
|
|
"entropy": 5.59913649559021,
|
|
"epoch": 1.7194923344752064,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00047129541501279897,
|
|
"loss": 5.4041,
|
|
"mean_token_accuracy": 0.19394327849149703,
|
|
"num_tokens": 34179753.0,
|
|
"step": 15310
|
|
},
|
|
{
|
|
"entropy": 5.600598907470703,
|
|
"epoch": 1.7200539113831639,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004712757892143468,
|
|
"loss": 5.4824,
|
|
"mean_token_accuracy": 0.18532252162694932,
|
|
"num_tokens": 34189947.0,
|
|
"step": 15315
|
|
},
|
|
{
|
|
"entropy": 5.636711502075196,
|
|
"epoch": 1.7206154882911213,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.00047125615716639744,
|
|
"loss": 5.4322,
|
|
"mean_token_accuracy": 0.1880556896328926,
|
|
"num_tokens": 34201197.0,
|
|
"step": 15320
|
|
},
|
|
{
|
|
"entropy": 5.590401458740234,
|
|
"epoch": 1.721177065199079,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004712365188695758,
|
|
"loss": 5.4262,
|
|
"mean_token_accuracy": 0.19257451444864274,
|
|
"num_tokens": 34212762.0,
|
|
"step": 15325
|
|
},
|
|
{
|
|
"entropy": 5.569433212280273,
|
|
"epoch": 1.7217386421070366,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004712168743245074,
|
|
"loss": 5.3809,
|
|
"mean_token_accuracy": 0.18759627640247345,
|
|
"num_tokens": 34223928.0,
|
|
"step": 15330
|
|
},
|
|
{
|
|
"entropy": 5.529983615875244,
|
|
"epoch": 1.722300219014994,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.00047119722353181754,
|
|
"loss": 5.283,
|
|
"mean_token_accuracy": 0.20313519090414048,
|
|
"num_tokens": 34233888.0,
|
|
"step": 15335
|
|
},
|
|
{
|
|
"entropy": 5.627472019195556,
|
|
"epoch": 1.7228617959229515,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.00047117756649213204,
|
|
"loss": 5.3958,
|
|
"mean_token_accuracy": 0.18413452059030533,
|
|
"num_tokens": 34245894.0,
|
|
"step": 15340
|
|
},
|
|
{
|
|
"entropy": 5.563360166549683,
|
|
"epoch": 1.7234233728309092,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004711579032060767,
|
|
"loss": 5.2997,
|
|
"mean_token_accuracy": 0.19482649117708206,
|
|
"num_tokens": 34256288.0,
|
|
"step": 15345
|
|
},
|
|
{
|
|
"entropy": 5.566926193237305,
|
|
"epoch": 1.7239849497388668,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004711382336742777,
|
|
"loss": 5.351,
|
|
"mean_token_accuracy": 0.1786728397011757,
|
|
"num_tokens": 34266515.0,
|
|
"step": 15350
|
|
},
|
|
{
|
|
"entropy": 5.59462161064148,
|
|
"epoch": 1.7245465266468243,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004711185578973612,
|
|
"loss": 5.4231,
|
|
"mean_token_accuracy": 0.1808302104473114,
|
|
"num_tokens": 34278681.0,
|
|
"step": 15355
|
|
},
|
|
{
|
|
"entropy": 5.609726810455323,
|
|
"epoch": 1.7251081035547817,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004710988758759538,
|
|
"loss": 5.3395,
|
|
"mean_token_accuracy": 0.19018030911684036,
|
|
"num_tokens": 34289161.0,
|
|
"step": 15360
|
|
},
|
|
{
|
|
"entropy": 5.545761442184448,
|
|
"epoch": 1.7256696804627394,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004710791876106821,
|
|
"loss": 5.319,
|
|
"mean_token_accuracy": 0.18373594731092452,
|
|
"num_tokens": 34300323.0,
|
|
"step": 15365
|
|
},
|
|
{
|
|
"entropy": 5.518750762939453,
|
|
"epoch": 1.726231257370697,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.00047105949310217304,
|
|
"loss": 5.2944,
|
|
"mean_token_accuracy": 0.18588107079267502,
|
|
"num_tokens": 34311558.0,
|
|
"step": 15370
|
|
},
|
|
{
|
|
"entropy": 5.4772566795349125,
|
|
"epoch": 1.7267928342786545,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004710397923510537,
|
|
"loss": 5.4157,
|
|
"mean_token_accuracy": 0.18117000311613082,
|
|
"num_tokens": 34323573.0,
|
|
"step": 15375
|
|
},
|
|
{
|
|
"entropy": 5.546475267410278,
|
|
"epoch": 1.727354411186612,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.00047102008535795134,
|
|
"loss": 5.3554,
|
|
"mean_token_accuracy": 0.18172081112861632,
|
|
"num_tokens": 34334698.0,
|
|
"step": 15380
|
|
},
|
|
{
|
|
"entropy": 5.602615737915039,
|
|
"epoch": 1.7279159880945696,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004710003721234934,
|
|
"loss": 5.3293,
|
|
"mean_token_accuracy": 0.1962783992290497,
|
|
"num_tokens": 34345948.0,
|
|
"step": 15385
|
|
},
|
|
{
|
|
"entropy": 5.559959602355957,
|
|
"epoch": 1.7284775650025272,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.00047098065264830754,
|
|
"loss": 5.3905,
|
|
"mean_token_accuracy": 0.18383126109838485,
|
|
"num_tokens": 34359067.0,
|
|
"step": 15390
|
|
},
|
|
{
|
|
"entropy": 5.403591728210449,
|
|
"epoch": 1.7290391419104847,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.00047096092693302174,
|
|
"loss": 5.2503,
|
|
"mean_token_accuracy": 0.19293245822191238,
|
|
"num_tokens": 34370895.0,
|
|
"step": 15395
|
|
},
|
|
{
|
|
"entropy": 5.506108713150025,
|
|
"epoch": 1.7296007188184421,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.00047094119497826406,
|
|
"loss": 5.3551,
|
|
"mean_token_accuracy": 0.18479404747486114,
|
|
"num_tokens": 34382039.0,
|
|
"step": 15400
|
|
},
|
|
{
|
|
"entropy": 5.632439422607422,
|
|
"epoch": 1.7301622957263998,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.00047092145678466273,
|
|
"loss": 5.4327,
|
|
"mean_token_accuracy": 0.18405346870422362,
|
|
"num_tokens": 34392939.0,
|
|
"step": 15405
|
|
},
|
|
{
|
|
"entropy": 5.674262189865113,
|
|
"epoch": 1.7307238726343572,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004709017123528462,
|
|
"loss": 5.4423,
|
|
"mean_token_accuracy": 0.18372531682252885,
|
|
"num_tokens": 34404402.0,
|
|
"step": 15410
|
|
},
|
|
{
|
|
"entropy": 5.486842155456543,
|
|
"epoch": 1.7312854495423147,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.00047088196168344315,
|
|
"loss": 5.3434,
|
|
"mean_token_accuracy": 0.19193651378154755,
|
|
"num_tokens": 34415563.0,
|
|
"step": 15415
|
|
},
|
|
{
|
|
"entropy": 5.603653287887573,
|
|
"epoch": 1.7318470264502723,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.00047086220477708256,
|
|
"loss": 5.4514,
|
|
"mean_token_accuracy": 0.17992481589317322,
|
|
"num_tokens": 34426993.0,
|
|
"step": 15420
|
|
},
|
|
{
|
|
"entropy": 5.6662970066070555,
|
|
"epoch": 1.73240860335823,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.00047084244163439335,
|
|
"loss": 5.3841,
|
|
"mean_token_accuracy": 0.19330619722604753,
|
|
"num_tokens": 34436697.0,
|
|
"step": 15425
|
|
},
|
|
{
|
|
"entropy": 5.587507629394532,
|
|
"epoch": 1.7329701802661874,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004708226722560049,
|
|
"loss": 5.3638,
|
|
"mean_token_accuracy": 0.1874844491481781,
|
|
"num_tokens": 34448076.0,
|
|
"step": 15430
|
|
},
|
|
{
|
|
"entropy": 5.508535099029541,
|
|
"epoch": 1.7335317571741449,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004708028966425465,
|
|
"loss": 5.4078,
|
|
"mean_token_accuracy": 0.18446434140205384,
|
|
"num_tokens": 34460369.0,
|
|
"step": 15435
|
|
},
|
|
{
|
|
"entropy": 5.63477840423584,
|
|
"epoch": 1.7340933340821025,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00047078311479464797,
|
|
"loss": 5.4748,
|
|
"mean_token_accuracy": 0.1780938521027565,
|
|
"num_tokens": 34472693.0,
|
|
"step": 15440
|
|
},
|
|
{
|
|
"entropy": 5.7154499053955075,
|
|
"epoch": 1.7346549109900602,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 0.00047076332671293917,
|
|
"loss": 5.4107,
|
|
"mean_token_accuracy": 0.19212453812360764,
|
|
"num_tokens": 34485258.0,
|
|
"step": 15445
|
|
},
|
|
{
|
|
"entropy": 5.629126977920532,
|
|
"epoch": 1.7352164878980176,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.00047074353239805005,
|
|
"loss": 5.387,
|
|
"mean_token_accuracy": 0.18570349365472794,
|
|
"num_tokens": 34496450.0,
|
|
"step": 15450
|
|
},
|
|
{
|
|
"entropy": 5.530909729003906,
|
|
"epoch": 1.735778064805975,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004707237318506111,
|
|
"loss": 5.4207,
|
|
"mean_token_accuracy": 0.18627371042966842,
|
|
"num_tokens": 34508062.0,
|
|
"step": 15455
|
|
},
|
|
{
|
|
"entropy": 5.5551708221435545,
|
|
"epoch": 1.7363396417139327,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00047070392507125245,
|
|
"loss": 5.3716,
|
|
"mean_token_accuracy": 0.19078274071216583,
|
|
"num_tokens": 34519817.0,
|
|
"step": 15460
|
|
},
|
|
{
|
|
"entropy": 5.569928073883057,
|
|
"epoch": 1.7369012186218904,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.000470684112060605,
|
|
"loss": 5.3789,
|
|
"mean_token_accuracy": 0.1850120022892952,
|
|
"num_tokens": 34532628.0,
|
|
"step": 15465
|
|
},
|
|
{
|
|
"entropy": 5.620344400405884,
|
|
"epoch": 1.7374627955298478,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.00047066429281929944,
|
|
"loss": 5.4333,
|
|
"mean_token_accuracy": 0.1882002368569374,
|
|
"num_tokens": 34543558.0,
|
|
"step": 15470
|
|
},
|
|
{
|
|
"entropy": 5.661240339279175,
|
|
"epoch": 1.7380243724378053,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.000470644467347967,
|
|
"loss": 5.4705,
|
|
"mean_token_accuracy": 0.18023901879787446,
|
|
"num_tokens": 34553720.0,
|
|
"step": 15475
|
|
},
|
|
{
|
|
"entropy": 5.57817497253418,
|
|
"epoch": 1.738585949345763,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.00047062463564723884,
|
|
"loss": 5.3512,
|
|
"mean_token_accuracy": 0.1927105724811554,
|
|
"num_tokens": 34564641.0,
|
|
"step": 15480
|
|
},
|
|
{
|
|
"entropy": 5.629330730438232,
|
|
"epoch": 1.7391475262537206,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004706047977177464,
|
|
"loss": 5.4506,
|
|
"mean_token_accuracy": 0.17920246571302414,
|
|
"num_tokens": 34576470.0,
|
|
"step": 15485
|
|
},
|
|
{
|
|
"entropy": 5.660240888595581,
|
|
"epoch": 1.739709103161678,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00047058495356012135,
|
|
"loss": 5.4717,
|
|
"mean_token_accuracy": 0.18309042900800704,
|
|
"num_tokens": 34589158.0,
|
|
"step": 15490
|
|
},
|
|
{
|
|
"entropy": 5.585483837127685,
|
|
"epoch": 1.7402706800696355,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00047056510317499545,
|
|
"loss": 5.2674,
|
|
"mean_token_accuracy": 0.19525233805179595,
|
|
"num_tokens": 34599192.0,
|
|
"step": 15495
|
|
},
|
|
{
|
|
"entropy": 5.536190557479858,
|
|
"epoch": 1.7408322569775931,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.00047054524656300087,
|
|
"loss": 5.3848,
|
|
"mean_token_accuracy": 0.18656711727380754,
|
|
"num_tokens": 34611922.0,
|
|
"step": 15500
|
|
},
|
|
{
|
|
"entropy": 5.612058496475219,
|
|
"epoch": 1.7413938338855506,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00047052538372476985,
|
|
"loss": 5.4424,
|
|
"mean_token_accuracy": 0.18274508863687516,
|
|
"num_tokens": 34623618.0,
|
|
"step": 15505
|
|
},
|
|
{
|
|
"entropy": 5.63532280921936,
|
|
"epoch": 1.741955410793508,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.00047050551466093466,
|
|
"loss": 5.448,
|
|
"mean_token_accuracy": 0.18087286949157716,
|
|
"num_tokens": 34635057.0,
|
|
"step": 15510
|
|
},
|
|
{
|
|
"entropy": 5.588735723495484,
|
|
"epoch": 1.7425169877014657,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004704856393721281,
|
|
"loss": 5.3885,
|
|
"mean_token_accuracy": 0.18542587012052536,
|
|
"num_tokens": 34647527.0,
|
|
"step": 15515
|
|
},
|
|
{
|
|
"entropy": 5.525556564331055,
|
|
"epoch": 1.7430785646094233,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.00047046575785898297,
|
|
"loss": 5.3501,
|
|
"mean_token_accuracy": 0.18491790890693666,
|
|
"num_tokens": 34658615.0,
|
|
"step": 15520
|
|
},
|
|
{
|
|
"entropy": 5.6457047939300535,
|
|
"epoch": 1.7436401415173808,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004704458701221323,
|
|
"loss": 5.3801,
|
|
"mean_token_accuracy": 0.18849466741085052,
|
|
"num_tokens": 34668485.0,
|
|
"step": 15525
|
|
},
|
|
{
|
|
"entropy": 5.581352806091308,
|
|
"epoch": 1.7442017184253382,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004704259761622094,
|
|
"loss": 5.3613,
|
|
"mean_token_accuracy": 0.1857620045542717,
|
|
"num_tokens": 34681181.0,
|
|
"step": 15530
|
|
},
|
|
{
|
|
"entropy": 5.473740434646606,
|
|
"epoch": 1.7447632953332959,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.00047040607597984745,
|
|
"loss": 5.3262,
|
|
"mean_token_accuracy": 0.1866876021027565,
|
|
"num_tokens": 34692954.0,
|
|
"step": 15535
|
|
},
|
|
{
|
|
"entropy": 5.446321678161621,
|
|
"epoch": 1.7453248722412535,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004703861695756804,
|
|
"loss": 5.2443,
|
|
"mean_token_accuracy": 0.19230304658412933,
|
|
"num_tokens": 34705120.0,
|
|
"step": 15540
|
|
},
|
|
{
|
|
"entropy": 5.566729164123535,
|
|
"epoch": 1.745886449149211,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004703662569503419,
|
|
"loss": 5.3736,
|
|
"mean_token_accuracy": 0.1882579505443573,
|
|
"num_tokens": 34716589.0,
|
|
"step": 15545
|
|
},
|
|
{
|
|
"entropy": 5.573837327957153,
|
|
"epoch": 1.7464480260571684,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00047034633810446604,
|
|
"loss": 5.3529,
|
|
"mean_token_accuracy": 0.18860515356063842,
|
|
"num_tokens": 34727551.0,
|
|
"step": 15550
|
|
},
|
|
{
|
|
"entropy": 5.502696371078491,
|
|
"epoch": 1.747009602965126,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004703264130386869,
|
|
"loss": 5.3878,
|
|
"mean_token_accuracy": 0.1905357763171196,
|
|
"num_tokens": 34738887.0,
|
|
"step": 15555
|
|
},
|
|
{
|
|
"entropy": 5.505575323104859,
|
|
"epoch": 1.7475711798730837,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.00047030648175363913,
|
|
"loss": 5.324,
|
|
"mean_token_accuracy": 0.1926727384328842,
|
|
"num_tokens": 34750264.0,
|
|
"step": 15560
|
|
},
|
|
{
|
|
"entropy": 5.564579248428345,
|
|
"epoch": 1.7481327567810412,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004702865442499572,
|
|
"loss": 5.401,
|
|
"mean_token_accuracy": 0.18318630903959274,
|
|
"num_tokens": 34761335.0,
|
|
"step": 15565
|
|
},
|
|
{
|
|
"entropy": 5.5248524188995365,
|
|
"epoch": 1.7486943336889986,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004702666005282759,
|
|
"loss": 5.3712,
|
|
"mean_token_accuracy": 0.18553073108196258,
|
|
"num_tokens": 34772237.0,
|
|
"step": 15570
|
|
},
|
|
{
|
|
"entropy": 5.5324851989746096,
|
|
"epoch": 1.7492559105969563,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004702466505892304,
|
|
"loss": 5.2694,
|
|
"mean_token_accuracy": 0.19213333427906037,
|
|
"num_tokens": 34784648.0,
|
|
"step": 15575
|
|
},
|
|
{
|
|
"entropy": 5.604431247711181,
|
|
"epoch": 1.749817487504914,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00047022669443345575,
|
|
"loss": 5.3849,
|
|
"mean_token_accuracy": 0.1935294434428215,
|
|
"num_tokens": 34794505.0,
|
|
"step": 15580
|
|
},
|
|
{
|
|
"entropy": 5.572837781906128,
|
|
"epoch": 1.7503790644128714,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.00047020673206158743,
|
|
"loss": 5.3806,
|
|
"mean_token_accuracy": 0.1911494642496109,
|
|
"num_tokens": 34804887.0,
|
|
"step": 15585
|
|
},
|
|
{
|
|
"entropy": 5.637475967407227,
|
|
"epoch": 1.7509406413208288,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 0.000470186763474261,
|
|
"loss": 5.3844,
|
|
"mean_token_accuracy": 0.18640556037425995,
|
|
"num_tokens": 34816814.0,
|
|
"step": 15590
|
|
},
|
|
{
|
|
"entropy": 5.561314725875855,
|
|
"epoch": 1.7515022182287865,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004701667886721125,
|
|
"loss": 5.3015,
|
|
"mean_token_accuracy": 0.19368523210287095,
|
|
"num_tokens": 34827251.0,
|
|
"step": 15595
|
|
},
|
|
{
|
|
"entropy": 5.576226997375488,
|
|
"epoch": 1.752063795136744,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004701468076557776,
|
|
"loss": 5.4243,
|
|
"mean_token_accuracy": 0.18055089116096495,
|
|
"num_tokens": 34839010.0,
|
|
"step": 15600
|
|
},
|
|
{
|
|
"entropy": 5.589766645431519,
|
|
"epoch": 1.7526253720447014,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00047012682042589277,
|
|
"loss": 5.4225,
|
|
"mean_token_accuracy": 0.18299496173858643,
|
|
"num_tokens": 34850435.0,
|
|
"step": 15605
|
|
},
|
|
{
|
|
"entropy": 5.545932340621948,
|
|
"epoch": 1.753186948952659,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00047010682698309423,
|
|
"loss": 5.2576,
|
|
"mean_token_accuracy": 0.19708157777786256,
|
|
"num_tokens": 34861222.0,
|
|
"step": 15610
|
|
},
|
|
{
|
|
"entropy": 5.637009000778198,
|
|
"epoch": 1.7537485258606167,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004700868273280186,
|
|
"loss": 5.4984,
|
|
"mean_token_accuracy": 0.1692656770348549,
|
|
"num_tokens": 34872650.0,
|
|
"step": 15615
|
|
},
|
|
{
|
|
"entropy": 5.627308702468872,
|
|
"epoch": 1.7543101027685741,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.00047006682146130273,
|
|
"loss": 5.3025,
|
|
"mean_token_accuracy": 0.19773675948381425,
|
|
"num_tokens": 34883201.0,
|
|
"step": 15620
|
|
},
|
|
{
|
|
"entropy": 5.656827211380005,
|
|
"epoch": 1.7548716796765316,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004700468093835837,
|
|
"loss": 5.5374,
|
|
"mean_token_accuracy": 0.17450018972158432,
|
|
"num_tokens": 34895936.0,
|
|
"step": 15625
|
|
},
|
|
{
|
|
"entropy": 5.571184539794922,
|
|
"epoch": 1.7554332565844892,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00047002679109549864,
|
|
"loss": 5.3689,
|
|
"mean_token_accuracy": 0.19319046586751937,
|
|
"num_tokens": 34906491.0,
|
|
"step": 15630
|
|
},
|
|
{
|
|
"entropy": 5.555408477783203,
|
|
"epoch": 1.755994833492447,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.00047000676659768477,
|
|
"loss": 5.3749,
|
|
"mean_token_accuracy": 0.18406349867582322,
|
|
"num_tokens": 34918300.0,
|
|
"step": 15635
|
|
},
|
|
{
|
|
"entropy": 5.471654033660888,
|
|
"epoch": 1.7565564104004043,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004699867358907799,
|
|
"loss": 5.3172,
|
|
"mean_token_accuracy": 0.1846435323357582,
|
|
"num_tokens": 34928573.0,
|
|
"step": 15640
|
|
},
|
|
{
|
|
"entropy": 5.605314159393311,
|
|
"epoch": 1.7571179873083618,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004699666989754217,
|
|
"loss": 5.3651,
|
|
"mean_token_accuracy": 0.18511402755975723,
|
|
"num_tokens": 34940378.0,
|
|
"step": 15645
|
|
},
|
|
{
|
|
"entropy": 5.564402055740357,
|
|
"epoch": 1.7576795642163194,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004699466558522482,
|
|
"loss": 5.4219,
|
|
"mean_token_accuracy": 0.18588894307613374,
|
|
"num_tokens": 34951627.0,
|
|
"step": 15650
|
|
},
|
|
{
|
|
"entropy": 5.560405826568603,
|
|
"epoch": 1.758241141124277,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.00046992660652189755,
|
|
"loss": 5.3548,
|
|
"mean_token_accuracy": 0.1835366114974022,
|
|
"num_tokens": 34961428.0,
|
|
"step": 15655
|
|
},
|
|
{
|
|
"entropy": 5.6877467155456545,
|
|
"epoch": 1.7588027180322345,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.00046990655098500824,
|
|
"loss": 5.4902,
|
|
"mean_token_accuracy": 0.18185962587594987,
|
|
"num_tokens": 34973736.0,
|
|
"step": 15660
|
|
},
|
|
{
|
|
"entropy": 5.570611047744751,
|
|
"epoch": 1.759364294940192,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00046988648924221866,
|
|
"loss": 5.3559,
|
|
"mean_token_accuracy": 0.19374988228082657,
|
|
"num_tokens": 34984510.0,
|
|
"step": 15665
|
|
},
|
|
{
|
|
"entropy": 5.577480983734131,
|
|
"epoch": 1.7599258718481496,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004698664212941677,
|
|
"loss": 5.3475,
|
|
"mean_token_accuracy": 0.1899129033088684,
|
|
"num_tokens": 34995218.0,
|
|
"step": 15670
|
|
},
|
|
{
|
|
"entropy": 5.426718807220459,
|
|
"epoch": 1.7604874487561073,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.00046984634714149437,
|
|
"loss": 5.1614,
|
|
"mean_token_accuracy": 0.19524444937705993,
|
|
"num_tokens": 35006681.0,
|
|
"step": 15675
|
|
},
|
|
{
|
|
"entropy": 5.510039281845093,
|
|
"epoch": 1.7610490256640647,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.0004698262667848377,
|
|
"loss": 5.4053,
|
|
"mean_token_accuracy": 0.18200305998325347,
|
|
"num_tokens": 35017341.0,
|
|
"step": 15680
|
|
},
|
|
{
|
|
"entropy": 5.5395721912384035,
|
|
"epoch": 1.7616106025720222,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00046980618022483714,
|
|
"loss": 5.2968,
|
|
"mean_token_accuracy": 0.19315295964479445,
|
|
"num_tokens": 35027718.0,
|
|
"step": 15685
|
|
},
|
|
{
|
|
"entropy": 5.602697229385376,
|
|
"epoch": 1.7621721794799798,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.00046978608746213224,
|
|
"loss": 5.3811,
|
|
"mean_token_accuracy": 0.19060612320899964,
|
|
"num_tokens": 35038100.0,
|
|
"step": 15690
|
|
},
|
|
{
|
|
"entropy": 5.52765793800354,
|
|
"epoch": 1.7627337563879373,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004697659884973628,
|
|
"loss": 5.4062,
|
|
"mean_token_accuracy": 0.18741343915462494,
|
|
"num_tokens": 35049077.0,
|
|
"step": 15695
|
|
},
|
|
{
|
|
"entropy": 5.6450201034545895,
|
|
"epoch": 1.7632953332958947,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004697458833311687,
|
|
"loss": 5.5438,
|
|
"mean_token_accuracy": 0.1795817032456398,
|
|
"num_tokens": 35060685.0,
|
|
"step": 15700
|
|
},
|
|
{
|
|
"entropy": 5.549354219436646,
|
|
"epoch": 1.7638569102038524,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004697257719641902,
|
|
"loss": 5.3062,
|
|
"mean_token_accuracy": 0.19198077917099,
|
|
"num_tokens": 35072122.0,
|
|
"step": 15705
|
|
},
|
|
{
|
|
"entropy": 5.583201789855957,
|
|
"epoch": 1.76441848711181,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004697056543970676,
|
|
"loss": 5.3449,
|
|
"mean_token_accuracy": 0.19073683619499207,
|
|
"num_tokens": 35082427.0,
|
|
"step": 15710
|
|
},
|
|
{
|
|
"entropy": 5.568373775482177,
|
|
"epoch": 1.7649800640197675,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00046968553063044146,
|
|
"loss": 5.3858,
|
|
"mean_token_accuracy": 0.1903146043419838,
|
|
"num_tokens": 35093061.0,
|
|
"step": 15715
|
|
},
|
|
{
|
|
"entropy": 5.621543550491333,
|
|
"epoch": 1.765541640927725,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00046966540066495247,
|
|
"loss": 5.4004,
|
|
"mean_token_accuracy": 0.18613336980342865,
|
|
"num_tokens": 35103226.0,
|
|
"step": 15720
|
|
},
|
|
{
|
|
"entropy": 5.614335441589356,
|
|
"epoch": 1.7661032178356826,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.00046964526450124164,
|
|
"loss": 5.3784,
|
|
"mean_token_accuracy": 0.18761180490255355,
|
|
"num_tokens": 35113977.0,
|
|
"step": 15725
|
|
},
|
|
{
|
|
"entropy": 5.5389328956604,
|
|
"epoch": 1.7666647947436402,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.00046962512213995,
|
|
"loss": 5.361,
|
|
"mean_token_accuracy": 0.18948362320661544,
|
|
"num_tokens": 35125132.0,
|
|
"step": 15730
|
|
},
|
|
{
|
|
"entropy": 5.5051295280456545,
|
|
"epoch": 1.7672263716515977,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00046960497358171913,
|
|
"loss": 5.3016,
|
|
"mean_token_accuracy": 0.18765170276165008,
|
|
"num_tokens": 35135266.0,
|
|
"step": 15735
|
|
},
|
|
{
|
|
"entropy": 5.596678066253662,
|
|
"epoch": 1.7677879485595551,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00046958481882719035,
|
|
"loss": 5.3735,
|
|
"mean_token_accuracy": 0.19410445392131806,
|
|
"num_tokens": 35146268.0,
|
|
"step": 15740
|
|
},
|
|
{
|
|
"entropy": 5.561468648910522,
|
|
"epoch": 1.7683495254675128,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.00046956465787700554,
|
|
"loss": 5.297,
|
|
"mean_token_accuracy": 0.1890968218445778,
|
|
"num_tokens": 35157046.0,
|
|
"step": 15745
|
|
},
|
|
{
|
|
"entropy": 5.57606053352356,
|
|
"epoch": 1.7689111023754704,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00046954449073180644,
|
|
"loss": 5.4801,
|
|
"mean_token_accuracy": 0.18432846516370774,
|
|
"num_tokens": 35167624.0,
|
|
"step": 15750
|
|
},
|
|
{
|
|
"entropy": 5.592984199523926,
|
|
"epoch": 1.7694726792834279,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004695243173922354,
|
|
"loss": 5.4458,
|
|
"mean_token_accuracy": 0.18281312584877013,
|
|
"num_tokens": 35178987.0,
|
|
"step": 15755
|
|
},
|
|
{
|
|
"entropy": 5.515202236175537,
|
|
"epoch": 1.7700342561913853,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00046950413785893465,
|
|
"loss": 5.3005,
|
|
"mean_token_accuracy": 0.1893632858991623,
|
|
"num_tokens": 35189804.0,
|
|
"step": 15760
|
|
},
|
|
{
|
|
"entropy": 5.620057249069214,
|
|
"epoch": 1.770595833099343,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00046948395213254667,
|
|
"loss": 5.363,
|
|
"mean_token_accuracy": 0.18398898243904113,
|
|
"num_tokens": 35200677.0,
|
|
"step": 15765
|
|
},
|
|
{
|
|
"entropy": 5.463645362854004,
|
|
"epoch": 1.7711574100073006,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004694637602137143,
|
|
"loss": 5.3334,
|
|
"mean_token_accuracy": 0.190482397377491,
|
|
"num_tokens": 35211570.0,
|
|
"step": 15770
|
|
},
|
|
{
|
|
"entropy": 5.477284479141235,
|
|
"epoch": 1.771718986915258,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004694435621030803,
|
|
"loss": 5.3739,
|
|
"mean_token_accuracy": 0.1894892379641533,
|
|
"num_tokens": 35222451.0,
|
|
"step": 15775
|
|
},
|
|
{
|
|
"entropy": 5.678949451446533,
|
|
"epoch": 1.7722805638232155,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.00046942335780128785,
|
|
"loss": 5.4806,
|
|
"mean_token_accuracy": 0.18306827545166016,
|
|
"num_tokens": 35233588.0,
|
|
"step": 15780
|
|
},
|
|
{
|
|
"entropy": 5.648662281036377,
|
|
"epoch": 1.7728421407311732,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00046940314730898035,
|
|
"loss": 5.4473,
|
|
"mean_token_accuracy": 0.17744902074337005,
|
|
"num_tokens": 35245766.0,
|
|
"step": 15785
|
|
},
|
|
{
|
|
"entropy": 5.507218599319458,
|
|
"epoch": 1.7734037176391306,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004693829306268012,
|
|
"loss": 5.3599,
|
|
"mean_token_accuracy": 0.19044422805309297,
|
|
"num_tokens": 35255635.0,
|
|
"step": 15790
|
|
},
|
|
{
|
|
"entropy": 5.595747947692871,
|
|
"epoch": 1.773965294547088,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004693627077553942,
|
|
"loss": 5.3711,
|
|
"mean_token_accuracy": 0.1829087480902672,
|
|
"num_tokens": 35269342.0,
|
|
"step": 15795
|
|
},
|
|
{
|
|
"entropy": 5.600680637359619,
|
|
"epoch": 1.7745268714550457,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004693424786954031,
|
|
"loss": 5.3806,
|
|
"mean_token_accuracy": 0.18079588264226915,
|
|
"num_tokens": 35280735.0,
|
|
"step": 15800
|
|
},
|
|
{
|
|
"entropy": 5.570738458633423,
|
|
"epoch": 1.7750884483630034,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00046932224344747224,
|
|
"loss": 5.3907,
|
|
"mean_token_accuracy": 0.1817556396126747,
|
|
"num_tokens": 35290803.0,
|
|
"step": 15805
|
|
},
|
|
{
|
|
"entropy": 5.615657567977905,
|
|
"epoch": 1.7756500252709608,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00046930200201224573,
|
|
"loss": 5.3779,
|
|
"mean_token_accuracy": 0.1841071903705597,
|
|
"num_tokens": 35301811.0,
|
|
"step": 15810
|
|
},
|
|
{
|
|
"entropy": 5.597724437713623,
|
|
"epoch": 1.7762116021789183,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004692817543903681,
|
|
"loss": 5.4635,
|
|
"mean_token_accuracy": 0.17897940576076507,
|
|
"num_tokens": 35313374.0,
|
|
"step": 15815
|
|
},
|
|
{
|
|
"entropy": 5.610829925537109,
|
|
"epoch": 1.776773179086876,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.000469261500582484,
|
|
"loss": 5.324,
|
|
"mean_token_accuracy": 0.19385354369878768,
|
|
"num_tokens": 35323272.0,
|
|
"step": 15820
|
|
},
|
|
{
|
|
"entropy": 5.6619956493377686,
|
|
"epoch": 1.7773347559948336,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00046924124058923843,
|
|
"loss": 5.458,
|
|
"mean_token_accuracy": 0.1730327844619751,
|
|
"num_tokens": 35335720.0,
|
|
"step": 15825
|
|
},
|
|
{
|
|
"entropy": 5.5761558532714846,
|
|
"epoch": 1.777896332902791,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004692209744112765,
|
|
"loss": 5.4976,
|
|
"mean_token_accuracy": 0.1847943678498268,
|
|
"num_tokens": 35347621.0,
|
|
"step": 15830
|
|
},
|
|
{
|
|
"entropy": 5.718498373031617,
|
|
"epoch": 1.7784579098107485,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004692007020492433,
|
|
"loss": 5.5732,
|
|
"mean_token_accuracy": 0.17302506268024445,
|
|
"num_tokens": 35360611.0,
|
|
"step": 15835
|
|
},
|
|
{
|
|
"entropy": 5.602990007400512,
|
|
"epoch": 1.7790194867187061,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004691804235037845,
|
|
"loss": 5.4609,
|
|
"mean_token_accuracy": 0.18267596065998076,
|
|
"num_tokens": 35372242.0,
|
|
"step": 15840
|
|
},
|
|
{
|
|
"entropy": 5.611075305938721,
|
|
"epoch": 1.7795810636266638,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004691601387755456,
|
|
"loss": 5.3618,
|
|
"mean_token_accuracy": 0.19045183807611465,
|
|
"num_tokens": 35385718.0,
|
|
"step": 15845
|
|
},
|
|
{
|
|
"entropy": 5.603568363189697,
|
|
"epoch": 1.7801426405346212,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00046913984786517275,
|
|
"loss": 5.4757,
|
|
"mean_token_accuracy": 0.17845510244369506,
|
|
"num_tokens": 35398298.0,
|
|
"step": 15850
|
|
},
|
|
{
|
|
"entropy": 5.565671443939209,
|
|
"epoch": 1.7807042174425787,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00046911955077331177,
|
|
"loss": 5.2554,
|
|
"mean_token_accuracy": 0.1875331446528435,
|
|
"num_tokens": 35408765.0,
|
|
"step": 15855
|
|
},
|
|
{
|
|
"entropy": 5.49656195640564,
|
|
"epoch": 1.7812657943505363,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00046909924750060893,
|
|
"loss": 5.2602,
|
|
"mean_token_accuracy": 0.19083157181739807,
|
|
"num_tokens": 35418547.0,
|
|
"step": 15860
|
|
},
|
|
{
|
|
"entropy": 5.5733802795410154,
|
|
"epoch": 1.781827371258494,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004690789380477109,
|
|
"loss": 5.381,
|
|
"mean_token_accuracy": 0.1814642384648323,
|
|
"num_tokens": 35428743.0,
|
|
"step": 15865
|
|
},
|
|
{
|
|
"entropy": 5.482580661773682,
|
|
"epoch": 1.7823889481664514,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004690586224152641,
|
|
"loss": 5.2973,
|
|
"mean_token_accuracy": 0.1893284648656845,
|
|
"num_tokens": 35439557.0,
|
|
"step": 15870
|
|
},
|
|
{
|
|
"entropy": 5.544387578964233,
|
|
"epoch": 1.7829505250744089,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004690383006039156,
|
|
"loss": 5.4617,
|
|
"mean_token_accuracy": 0.18211542963981628,
|
|
"num_tokens": 35452041.0,
|
|
"step": 15875
|
|
},
|
|
{
|
|
"entropy": 5.624589967727661,
|
|
"epoch": 1.7835121019823665,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004690179726143123,
|
|
"loss": 5.3825,
|
|
"mean_token_accuracy": 0.19349778741598128,
|
|
"num_tokens": 35463283.0,
|
|
"step": 15880
|
|
},
|
|
{
|
|
"entropy": 5.676436138153076,
|
|
"epoch": 1.784073678890324,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004689976384471014,
|
|
"loss": 5.5068,
|
|
"mean_token_accuracy": 0.1909259706735611,
|
|
"num_tokens": 35475802.0,
|
|
"step": 15885
|
|
},
|
|
{
|
|
"entropy": 5.500989723205566,
|
|
"epoch": 1.7846352557982814,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004689772981029306,
|
|
"loss": 5.3019,
|
|
"mean_token_accuracy": 0.1928515240550041,
|
|
"num_tokens": 35486322.0,
|
|
"step": 15890
|
|
},
|
|
{
|
|
"entropy": 5.553930282592773,
|
|
"epoch": 1.785196832706239,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004689569515824473,
|
|
"loss": 5.3452,
|
|
"mean_token_accuracy": 0.19019032567739486,
|
|
"num_tokens": 35497021.0,
|
|
"step": 15895
|
|
},
|
|
{
|
|
"entropy": 5.555098581314087,
|
|
"epoch": 1.7857584096141967,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004689365988862995,
|
|
"loss": 5.3244,
|
|
"mean_token_accuracy": 0.1960470959544182,
|
|
"num_tokens": 35507579.0,
|
|
"step": 15900
|
|
},
|
|
{
|
|
"entropy": 5.478539276123047,
|
|
"epoch": 1.7863199865221542,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00046891624001513515,
|
|
"loss": 5.2773,
|
|
"mean_token_accuracy": 0.18713027983903885,
|
|
"num_tokens": 35518131.0,
|
|
"step": 15905
|
|
},
|
|
{
|
|
"entropy": 5.560598850250244,
|
|
"epoch": 1.7868815634301116,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00046889587496960257,
|
|
"loss": 5.4211,
|
|
"mean_token_accuracy": 0.18091222941875457,
|
|
"num_tokens": 35529577.0,
|
|
"step": 15910
|
|
},
|
|
{
|
|
"entropy": 5.609899806976318,
|
|
"epoch": 1.7874431403380693,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00046887550375034997,
|
|
"loss": 5.3448,
|
|
"mean_token_accuracy": 0.1910657912492752,
|
|
"num_tokens": 35541555.0,
|
|
"step": 15915
|
|
},
|
|
{
|
|
"entropy": 5.5346800804138185,
|
|
"epoch": 1.788004717246027,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00046885512635802627,
|
|
"loss": 5.2772,
|
|
"mean_token_accuracy": 0.1943323016166687,
|
|
"num_tokens": 35552596.0,
|
|
"step": 15920
|
|
},
|
|
{
|
|
"entropy": 5.407305765151977,
|
|
"epoch": 1.7885662941539844,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004688347427932801,
|
|
"loss": 5.3629,
|
|
"mean_token_accuracy": 0.18243516087532044,
|
|
"num_tokens": 35564962.0,
|
|
"step": 15925
|
|
},
|
|
{
|
|
"entropy": 5.618680953979492,
|
|
"epoch": 1.7891278710619418,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00046881435305676055,
|
|
"loss": 5.4494,
|
|
"mean_token_accuracy": 0.17935291826725006,
|
|
"num_tokens": 35576436.0,
|
|
"step": 15930
|
|
},
|
|
{
|
|
"entropy": 5.633065271377563,
|
|
"epoch": 1.7896894479698995,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00046879395714911686,
|
|
"loss": 5.3908,
|
|
"mean_token_accuracy": 0.18873339146375656,
|
|
"num_tokens": 35587467.0,
|
|
"step": 15935
|
|
},
|
|
{
|
|
"entropy": 5.633873844146729,
|
|
"epoch": 1.7902510248778571,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00046877355507099846,
|
|
"loss": 5.4434,
|
|
"mean_token_accuracy": 0.17776518166065217,
|
|
"num_tokens": 35600302.0,
|
|
"step": 15940
|
|
},
|
|
{
|
|
"entropy": 5.563335609436035,
|
|
"epoch": 1.7908126017858146,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004687531468230549,
|
|
"loss": 5.3727,
|
|
"mean_token_accuracy": 0.1925714984536171,
|
|
"num_tokens": 35611757.0,
|
|
"step": 15945
|
|
},
|
|
{
|
|
"entropy": 5.531421899795532,
|
|
"epoch": 1.791374178693772,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004687327324059359,
|
|
"loss": 5.4276,
|
|
"mean_token_accuracy": 0.18253857344388963,
|
|
"num_tokens": 35621991.0,
|
|
"step": 15950
|
|
},
|
|
{
|
|
"entropy": 5.577724266052246,
|
|
"epoch": 1.7919357556017297,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004687123118202916,
|
|
"loss": 5.3962,
|
|
"mean_token_accuracy": 0.18589919358491896,
|
|
"num_tokens": 35633744.0,
|
|
"step": 15955
|
|
},
|
|
{
|
|
"entropy": 5.53998908996582,
|
|
"epoch": 1.7924973325096873,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004686918850667722,
|
|
"loss": 5.2911,
|
|
"mean_token_accuracy": 0.1892552986741066,
|
|
"num_tokens": 35645523.0,
|
|
"step": 15960
|
|
},
|
|
{
|
|
"entropy": 5.590689468383789,
|
|
"epoch": 1.7930589094176448,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.000468671452146028,
|
|
"loss": 5.4468,
|
|
"mean_token_accuracy": 0.1826014667749405,
|
|
"num_tokens": 35657670.0,
|
|
"step": 15965
|
|
},
|
|
{
|
|
"entropy": 5.529779481887817,
|
|
"epoch": 1.7936204863256022,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00046865101305870965,
|
|
"loss": 5.2516,
|
|
"mean_token_accuracy": 0.1899636507034302,
|
|
"num_tokens": 35668149.0,
|
|
"step": 15970
|
|
},
|
|
{
|
|
"entropy": 5.494525718688965,
|
|
"epoch": 1.7941820632335599,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.000468630567805468,
|
|
"loss": 5.34,
|
|
"mean_token_accuracy": 0.18510247766971588,
|
|
"num_tokens": 35680225.0,
|
|
"step": 15975
|
|
},
|
|
{
|
|
"entropy": 5.430608177185059,
|
|
"epoch": 1.7947436401415173,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.000468610116386954,
|
|
"loss": 5.249,
|
|
"mean_token_accuracy": 0.195359405875206,
|
|
"num_tokens": 35691042.0,
|
|
"step": 15980
|
|
},
|
|
{
|
|
"entropy": 5.530224704742432,
|
|
"epoch": 1.7953052170494748,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004685896588038187,
|
|
"loss": 5.3675,
|
|
"mean_token_accuracy": 0.1856921836733818,
|
|
"num_tokens": 35702895.0,
|
|
"step": 15985
|
|
},
|
|
{
|
|
"entropy": 5.588540363311767,
|
|
"epoch": 1.7958667939574324,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004685691950567136,
|
|
"loss": 5.3112,
|
|
"mean_token_accuracy": 0.18628643453121185,
|
|
"num_tokens": 35714765.0,
|
|
"step": 15990
|
|
},
|
|
{
|
|
"entropy": 5.632132482528687,
|
|
"epoch": 1.79642837086539,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.00046854872514629035,
|
|
"loss": 5.4812,
|
|
"mean_token_accuracy": 0.1774725615978241,
|
|
"num_tokens": 35725832.0,
|
|
"step": 15995
|
|
},
|
|
{
|
|
"entropy": 5.540455150604248,
|
|
"epoch": 1.7969899477733475,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004685282490732005,
|
|
"loss": 5.3074,
|
|
"mean_token_accuracy": 0.19379405677318573,
|
|
"num_tokens": 35736619.0,
|
|
"step": 16000
|
|
},
|
|
{
|
|
"entropy": 5.50766134262085,
|
|
"epoch": 1.797551524681305,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00046850776683809623,
|
|
"loss": 5.262,
|
|
"mean_token_accuracy": 0.18469182550907134,
|
|
"num_tokens": 35748243.0,
|
|
"step": 16005
|
|
},
|
|
{
|
|
"entropy": 5.541708898544312,
|
|
"epoch": 1.7981131015892626,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004684872784416295,
|
|
"loss": 5.3748,
|
|
"mean_token_accuracy": 0.18503991067409514,
|
|
"num_tokens": 35759126.0,
|
|
"step": 16010
|
|
},
|
|
{
|
|
"entropy": 5.648258066177368,
|
|
"epoch": 1.7986746784972203,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004684667838844529,
|
|
"loss": 5.3932,
|
|
"mean_token_accuracy": 0.1819484680891037,
|
|
"num_tokens": 35770998.0,
|
|
"step": 16015
|
|
},
|
|
{
|
|
"entropy": 5.525299501419068,
|
|
"epoch": 1.7992362554051777,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004684462831672188,
|
|
"loss": 5.329,
|
|
"mean_token_accuracy": 0.1874153807759285,
|
|
"num_tokens": 35782835.0,
|
|
"step": 16020
|
|
},
|
|
{
|
|
"entropy": 5.549390172958374,
|
|
"epoch": 1.7997978323131352,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00046842577629058006,
|
|
"loss": 5.3128,
|
|
"mean_token_accuracy": 0.1882465064525604,
|
|
"num_tokens": 35792828.0,
|
|
"step": 16025
|
|
},
|
|
{
|
|
"entropy": 5.642633104324341,
|
|
"epoch": 1.8003594092210928,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004684052632551896,
|
|
"loss": 5.5487,
|
|
"mean_token_accuracy": 0.1810038223862648,
|
|
"num_tokens": 35804449.0,
|
|
"step": 16030
|
|
},
|
|
{
|
|
"entropy": 5.574741077423096,
|
|
"epoch": 1.8009209861290505,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00046838474406170046,
|
|
"loss": 5.302,
|
|
"mean_token_accuracy": 0.18773899972438812,
|
|
"num_tokens": 35815903.0,
|
|
"step": 16035
|
|
},
|
|
{
|
|
"entropy": 5.491513681411743,
|
|
"epoch": 1.801482563037008,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00046836421871076616,
|
|
"loss": 5.3141,
|
|
"mean_token_accuracy": 0.19241884350776672,
|
|
"num_tokens": 35827872.0,
|
|
"step": 16040
|
|
},
|
|
{
|
|
"entropy": 5.521188020706177,
|
|
"epoch": 1.8020441399449654,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004683436872030401,
|
|
"loss": 5.3027,
|
|
"mean_token_accuracy": 0.19239161610603334,
|
|
"num_tokens": 35838864.0,
|
|
"step": 16045
|
|
},
|
|
{
|
|
"entropy": 5.490436601638794,
|
|
"epoch": 1.802605716852923,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00046832314953917605,
|
|
"loss": 5.2212,
|
|
"mean_token_accuracy": 0.18229456543922423,
|
|
"num_tokens": 35850178.0,
|
|
"step": 16050
|
|
},
|
|
{
|
|
"entropy": 5.544579124450683,
|
|
"epoch": 1.8031672937608807,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00046830260571982795,
|
|
"loss": 5.3763,
|
|
"mean_token_accuracy": 0.1876939445734024,
|
|
"num_tokens": 35861904.0,
|
|
"step": 16055
|
|
},
|
|
{
|
|
"entropy": 5.4166254043579105,
|
|
"epoch": 1.8037288706688381,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004682820557456499,
|
|
"loss": 5.2574,
|
|
"mean_token_accuracy": 0.19551395773887634,
|
|
"num_tokens": 35872977.0,
|
|
"step": 16060
|
|
},
|
|
{
|
|
"entropy": 5.621083164215088,
|
|
"epoch": 1.8042904475767956,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00046826149961729625,
|
|
"loss": 5.4566,
|
|
"mean_token_accuracy": 0.18301086127758026,
|
|
"num_tokens": 35886094.0,
|
|
"step": 16065
|
|
},
|
|
{
|
|
"entropy": 5.537100791931152,
|
|
"epoch": 1.8048520244847532,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00046824093733542144,
|
|
"loss": 5.279,
|
|
"mean_token_accuracy": 0.19515191167593002,
|
|
"num_tokens": 35897557.0,
|
|
"step": 16070
|
|
},
|
|
{
|
|
"entropy": 5.579884958267212,
|
|
"epoch": 1.8054136013927107,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00046822036890068033,
|
|
"loss": 5.4973,
|
|
"mean_token_accuracy": 0.17925168871879577,
|
|
"num_tokens": 35910605.0,
|
|
"step": 16075
|
|
},
|
|
{
|
|
"entropy": 5.554397964477539,
|
|
"epoch": 1.8059751783006681,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00046819979431372773,
|
|
"loss": 5.2688,
|
|
"mean_token_accuracy": 0.1950139656662941,
|
|
"num_tokens": 35921062.0,
|
|
"step": 16080
|
|
},
|
|
{
|
|
"entropy": 5.548288822174072,
|
|
"epoch": 1.8065367552086258,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.00046817921357521865,
|
|
"loss": 5.3555,
|
|
"mean_token_accuracy": 0.1850862443447113,
|
|
"num_tokens": 35932385.0,
|
|
"step": 16085
|
|
},
|
|
{
|
|
"entropy": 5.47045931816101,
|
|
"epoch": 1.8070983321165834,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00046815862668580854,
|
|
"loss": 5.3434,
|
|
"mean_token_accuracy": 0.19163644313812256,
|
|
"num_tokens": 35943628.0,
|
|
"step": 16090
|
|
},
|
|
{
|
|
"entropy": 5.60513014793396,
|
|
"epoch": 1.8076599090245409,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004681380336461528,
|
|
"loss": 5.4026,
|
|
"mean_token_accuracy": 0.1782854288816452,
|
|
"num_tokens": 35955074.0,
|
|
"step": 16095
|
|
},
|
|
{
|
|
"entropy": 5.593359375,
|
|
"epoch": 1.8082214859324983,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00046811743445690724,
|
|
"loss": 5.3292,
|
|
"mean_token_accuracy": 0.1858907625079155,
|
|
"num_tokens": 35966200.0,
|
|
"step": 16100
|
|
},
|
|
{
|
|
"entropy": 5.467005634307862,
|
|
"epoch": 1.808783062840456,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004680968291187276,
|
|
"loss": 5.2271,
|
|
"mean_token_accuracy": 0.19870145320892335,
|
|
"num_tokens": 35975638.0,
|
|
"step": 16105
|
|
},
|
|
{
|
|
"entropy": 5.513053369522095,
|
|
"epoch": 1.8093446397484136,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004680762176322701,
|
|
"loss": 5.3487,
|
|
"mean_token_accuracy": 0.1926051288843155,
|
|
"num_tokens": 35986486.0,
|
|
"step": 16110
|
|
},
|
|
{
|
|
"entropy": 5.490559530258179,
|
|
"epoch": 1.809906216656371,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00046805559999819093,
|
|
"loss": 5.2737,
|
|
"mean_token_accuracy": 0.19124430269002915,
|
|
"num_tokens": 35996612.0,
|
|
"step": 16115
|
|
},
|
|
{
|
|
"entropy": 5.415689134597779,
|
|
"epoch": 1.8104677935643285,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004680349762171465,
|
|
"loss": 5.3365,
|
|
"mean_token_accuracy": 0.18895064294338226,
|
|
"num_tokens": 36006936.0,
|
|
"step": 16120
|
|
},
|
|
{
|
|
"entropy": 5.6507463455200195,
|
|
"epoch": 1.8110293704722862,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004680143462897936,
|
|
"loss": 5.461,
|
|
"mean_token_accuracy": 0.18231729716062545,
|
|
"num_tokens": 36019562.0,
|
|
"step": 16125
|
|
},
|
|
{
|
|
"entropy": 5.540613079071045,
|
|
"epoch": 1.8115909473802438,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004679937102167891,
|
|
"loss": 5.2565,
|
|
"mean_token_accuracy": 0.19357980042696,
|
|
"num_tokens": 36029585.0,
|
|
"step": 16130
|
|
},
|
|
{
|
|
"entropy": 5.472490930557251,
|
|
"epoch": 1.8121525242882013,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00046797306799879,
|
|
"loss": 5.3391,
|
|
"mean_token_accuracy": 0.19227437376976014,
|
|
"num_tokens": 36041495.0,
|
|
"step": 16135
|
|
},
|
|
{
|
|
"entropy": 5.490143156051635,
|
|
"epoch": 1.8127141011961587,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00046795241963645356,
|
|
"loss": 5.3793,
|
|
"mean_token_accuracy": 0.18855390399694444,
|
|
"num_tokens": 36052087.0,
|
|
"step": 16140
|
|
},
|
|
{
|
|
"entropy": 5.549077892303467,
|
|
"epoch": 1.8132756781041164,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004679317651304373,
|
|
"loss": 5.3439,
|
|
"mean_token_accuracy": 0.1903028041124344,
|
|
"num_tokens": 36065011.0,
|
|
"step": 16145
|
|
},
|
|
{
|
|
"entropy": 5.59675784111023,
|
|
"epoch": 1.813837255012074,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004679111044813987,
|
|
"loss": 5.4232,
|
|
"mean_token_accuracy": 0.18762087523937226,
|
|
"num_tokens": 36075912.0,
|
|
"step": 16150
|
|
},
|
|
{
|
|
"entropy": 5.610179901123047,
|
|
"epoch": 1.8143988319200315,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00046789043768999573,
|
|
"loss": 5.3904,
|
|
"mean_token_accuracy": 0.18435035198926925,
|
|
"num_tokens": 36086757.0,
|
|
"step": 16155
|
|
},
|
|
{
|
|
"entropy": 5.515399742126465,
|
|
"epoch": 1.814960408827989,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.0004678697647568865,
|
|
"loss": 5.2643,
|
|
"mean_token_accuracy": 0.19338752776384355,
|
|
"num_tokens": 36097319.0,
|
|
"step": 16160
|
|
},
|
|
{
|
|
"entropy": 5.522013235092163,
|
|
"epoch": 1.8155219857359466,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.00046784908568272903,
|
|
"loss": 5.4083,
|
|
"mean_token_accuracy": 0.18334012925624849,
|
|
"num_tokens": 36108416.0,
|
|
"step": 16165
|
|
},
|
|
{
|
|
"entropy": 5.463136053085327,
|
|
"epoch": 1.8160835626439042,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.000467828400468182,
|
|
"loss": 5.3351,
|
|
"mean_token_accuracy": 0.18444680869579316,
|
|
"num_tokens": 36120833.0,
|
|
"step": 16170
|
|
},
|
|
{
|
|
"entropy": 5.610969066619873,
|
|
"epoch": 1.8166451395518615,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00046780770911390387,
|
|
"loss": 5.4616,
|
|
"mean_token_accuracy": 0.18258167505264283,
|
|
"num_tokens": 36132348.0,
|
|
"step": 16175
|
|
},
|
|
{
|
|
"entropy": 5.541339874267578,
|
|
"epoch": 1.8172067164598191,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004677870116205534,
|
|
"loss": 5.2378,
|
|
"mean_token_accuracy": 0.19122178256511688,
|
|
"num_tokens": 36142829.0,
|
|
"step": 16180
|
|
},
|
|
{
|
|
"entropy": 5.566759204864502,
|
|
"epoch": 1.8177682933677768,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00046776630798878985,
|
|
"loss": 5.5088,
|
|
"mean_token_accuracy": 0.18053208142518998,
|
|
"num_tokens": 36155931.0,
|
|
"step": 16185
|
|
},
|
|
{
|
|
"entropy": 5.606925439834595,
|
|
"epoch": 1.8183298702757342,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004677455982192723,
|
|
"loss": 5.4102,
|
|
"mean_token_accuracy": 0.17741843014955522,
|
|
"num_tokens": 36167591.0,
|
|
"step": 16190
|
|
},
|
|
{
|
|
"entropy": 5.513416719436646,
|
|
"epoch": 1.8188914471836917,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00046772488231266004,
|
|
"loss": 5.2858,
|
|
"mean_token_accuracy": 0.1894127681851387,
|
|
"num_tokens": 36178867.0,
|
|
"step": 16195
|
|
},
|
|
{
|
|
"entropy": 5.39373745918274,
|
|
"epoch": 1.8194530240916493,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.00046770416026961284,
|
|
"loss": 5.2578,
|
|
"mean_token_accuracy": 0.2004848062992096,
|
|
"num_tokens": 36190691.0,
|
|
"step": 16200
|
|
},
|
|
{
|
|
"entropy": 5.625265455245971,
|
|
"epoch": 1.820014600999607,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004676834320907904,
|
|
"loss": 5.4731,
|
|
"mean_token_accuracy": 0.18121488094329835,
|
|
"num_tokens": 36202222.0,
|
|
"step": 16205
|
|
},
|
|
{
|
|
"entropy": 5.610524082183838,
|
|
"epoch": 1.8205761779075644,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004676626977768528,
|
|
"loss": 5.2545,
|
|
"mean_token_accuracy": 0.19390959143638611,
|
|
"num_tokens": 36214303.0,
|
|
"step": 16210
|
|
},
|
|
{
|
|
"entropy": 5.452145576477051,
|
|
"epoch": 1.8211377548155219,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00046764195732846013,
|
|
"loss": 5.2808,
|
|
"mean_token_accuracy": 0.18949127495288848,
|
|
"num_tokens": 36224440.0,
|
|
"step": 16215
|
|
},
|
|
{
|
|
"entropy": 5.421571397781372,
|
|
"epoch": 1.8216993317234795,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00046762121074627285,
|
|
"loss": 5.2891,
|
|
"mean_token_accuracy": 0.1903606489300728,
|
|
"num_tokens": 36235445.0,
|
|
"step": 16220
|
|
},
|
|
{
|
|
"entropy": 5.569859313964844,
|
|
"epoch": 1.8222609086314372,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00046760045803095153,
|
|
"loss": 5.3156,
|
|
"mean_token_accuracy": 0.19223127663135528,
|
|
"num_tokens": 36247024.0,
|
|
"step": 16225
|
|
},
|
|
{
|
|
"entropy": 5.606548643112182,
|
|
"epoch": 1.8228224855393946,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004675796991831569,
|
|
"loss": 5.3367,
|
|
"mean_token_accuracy": 0.18688896000385286,
|
|
"num_tokens": 36257406.0,
|
|
"step": 16230
|
|
},
|
|
{
|
|
"entropy": 5.524360275268554,
|
|
"epoch": 1.823384062447352,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.00046755893420355,
|
|
"loss": 5.3498,
|
|
"mean_token_accuracy": 0.18490929454565047,
|
|
"num_tokens": 36270266.0,
|
|
"step": 16235
|
|
},
|
|
{
|
|
"entropy": 5.566007661819458,
|
|
"epoch": 1.8239456393553097,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004675381630927919,
|
|
"loss": 5.4291,
|
|
"mean_token_accuracy": 0.1858387365937233,
|
|
"num_tokens": 36281470.0,
|
|
"step": 16240
|
|
},
|
|
{
|
|
"entropy": 5.534808826446533,
|
|
"epoch": 1.8245072162632674,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00046751738585154405,
|
|
"loss": 5.3248,
|
|
"mean_token_accuracy": 0.18495461493730544,
|
|
"num_tokens": 36293315.0,
|
|
"step": 16245
|
|
},
|
|
{
|
|
"entropy": 5.557805871963501,
|
|
"epoch": 1.8250687931712248,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.00046749660248046794,
|
|
"loss": 5.3685,
|
|
"mean_token_accuracy": 0.19024549275636674,
|
|
"num_tokens": 36304688.0,
|
|
"step": 16250
|
|
},
|
|
{
|
|
"entropy": 5.6081033706665036,
|
|
"epoch": 1.8256303700791823,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00046747581298022537,
|
|
"loss": 5.434,
|
|
"mean_token_accuracy": 0.18934669643640517,
|
|
"num_tokens": 36315773.0,
|
|
"step": 16255
|
|
},
|
|
{
|
|
"entropy": 5.626693439483643,
|
|
"epoch": 1.82619194698714,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004674550173514782,
|
|
"loss": 5.3524,
|
|
"mean_token_accuracy": 0.1872216284275055,
|
|
"num_tokens": 36327914.0,
|
|
"step": 16260
|
|
},
|
|
{
|
|
"entropy": 5.603176641464233,
|
|
"epoch": 1.8267535238950976,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.00046743421559488875,
|
|
"loss": 5.4365,
|
|
"mean_token_accuracy": 0.17932053208351134,
|
|
"num_tokens": 36339617.0,
|
|
"step": 16265
|
|
},
|
|
{
|
|
"entropy": 5.630232667922973,
|
|
"epoch": 1.8273151008030548,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00046741340771111917,
|
|
"loss": 5.4864,
|
|
"mean_token_accuracy": 0.17964668124914168,
|
|
"num_tokens": 36350768.0,
|
|
"step": 16270
|
|
},
|
|
{
|
|
"entropy": 5.530461740493775,
|
|
"epoch": 1.8278766777110125,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.00046739259370083205,
|
|
"loss": 5.3582,
|
|
"mean_token_accuracy": 0.18999661654233932,
|
|
"num_tokens": 36361267.0,
|
|
"step": 16275
|
|
},
|
|
{
|
|
"entropy": 5.583748197555542,
|
|
"epoch": 1.8284382546189701,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004673717735646902,
|
|
"loss": 5.389,
|
|
"mean_token_accuracy": 0.18332965970039367,
|
|
"num_tokens": 36373259.0,
|
|
"step": 16280
|
|
},
|
|
{
|
|
"entropy": 5.590427303314209,
|
|
"epoch": 1.8289998315269276,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004673509473033564,
|
|
"loss": 5.3283,
|
|
"mean_token_accuracy": 0.18604336231946944,
|
|
"num_tokens": 36384295.0,
|
|
"step": 16285
|
|
},
|
|
{
|
|
"entropy": 5.571167469024658,
|
|
"epoch": 1.829561408434885,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00046733011491749383,
|
|
"loss": 5.3173,
|
|
"mean_token_accuracy": 0.19359821528196336,
|
|
"num_tokens": 36394928.0,
|
|
"step": 16290
|
|
},
|
|
{
|
|
"entropy": 5.515721654891967,
|
|
"epoch": 1.8301229853428427,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004673092764077658,
|
|
"loss": 5.3815,
|
|
"mean_token_accuracy": 0.19220682084560395,
|
|
"num_tokens": 36407038.0,
|
|
"step": 16295
|
|
},
|
|
{
|
|
"entropy": 5.661236715316773,
|
|
"epoch": 1.8306845622508003,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004672884317748359,
|
|
"loss": 5.3604,
|
|
"mean_token_accuracy": 0.18396896719932557,
|
|
"num_tokens": 36418221.0,
|
|
"step": 16300
|
|
},
|
|
{
|
|
"entropy": 5.525816154479981,
|
|
"epoch": 1.8312461391587578,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004672675810193677,
|
|
"loss": 5.3054,
|
|
"mean_token_accuracy": 0.1906868487596512,
|
|
"num_tokens": 36429036.0,
|
|
"step": 16305
|
|
},
|
|
{
|
|
"entropy": 5.512045383453369,
|
|
"epoch": 1.8318077160667152,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.00046724672414202514,
|
|
"loss": 5.3631,
|
|
"mean_token_accuracy": 0.18964605480432511,
|
|
"num_tokens": 36439851.0,
|
|
"step": 16310
|
|
},
|
|
{
|
|
"entropy": 5.591065883636475,
|
|
"epoch": 1.8323692929746729,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004672258611434724,
|
|
"loss": 5.3747,
|
|
"mean_token_accuracy": 0.18101801127195358,
|
|
"num_tokens": 36451612.0,
|
|
"step": 16315
|
|
},
|
|
{
|
|
"entropy": 5.631992769241333,
|
|
"epoch": 1.8329308698826305,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00046720499202437354,
|
|
"loss": 5.4328,
|
|
"mean_token_accuracy": 0.1815750315785408,
|
|
"num_tokens": 36462883.0,
|
|
"step": 16320
|
|
},
|
|
{
|
|
"entropy": 5.5189462184906,
|
|
"epoch": 1.833492446790588,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004671841167853933,
|
|
"loss": 5.324,
|
|
"mean_token_accuracy": 0.19218890368938446,
|
|
"num_tokens": 36473609.0,
|
|
"step": 16325
|
|
},
|
|
{
|
|
"entropy": 5.573424434661865,
|
|
"epoch": 1.8340540236985454,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004671632354271962,
|
|
"loss": 5.3145,
|
|
"mean_token_accuracy": 0.18836932480335236,
|
|
"num_tokens": 36484058.0,
|
|
"step": 16330
|
|
},
|
|
{
|
|
"entropy": 5.640398120880127,
|
|
"epoch": 1.834615600606503,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00046714234795044724,
|
|
"loss": 5.36,
|
|
"mean_token_accuracy": 0.18595891892910005,
|
|
"num_tokens": 36496445.0,
|
|
"step": 16335
|
|
},
|
|
{
|
|
"entropy": 5.503306198120117,
|
|
"epoch": 1.8351771775144607,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004671214543558113,
|
|
"loss": 5.2861,
|
|
"mean_token_accuracy": 0.19019471257925033,
|
|
"num_tokens": 36507553.0,
|
|
"step": 16340
|
|
},
|
|
{
|
|
"entropy": 5.503566837310791,
|
|
"epoch": 1.8357387544224182,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004671005546439538,
|
|
"loss": 5.3336,
|
|
"mean_token_accuracy": 0.1920084074139595,
|
|
"num_tokens": 36517887.0,
|
|
"step": 16345
|
|
},
|
|
{
|
|
"entropy": 5.527010250091553,
|
|
"epoch": 1.8363003313303756,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00046707964881554005,
|
|
"loss": 5.2848,
|
|
"mean_token_accuracy": 0.18495176434516908,
|
|
"num_tokens": 36529185.0,
|
|
"step": 16350
|
|
},
|
|
{
|
|
"entropy": 5.528638744354248,
|
|
"epoch": 1.8368619082383333,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00046705873687123586,
|
|
"loss": 5.3722,
|
|
"mean_token_accuracy": 0.19100251346826552,
|
|
"num_tokens": 36539473.0,
|
|
"step": 16355
|
|
},
|
|
{
|
|
"entropy": 5.5641679763793945,
|
|
"epoch": 1.837423485146291,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00046703781881170703,
|
|
"loss": 5.3711,
|
|
"mean_token_accuracy": 0.18921186923980712,
|
|
"num_tokens": 36549603.0,
|
|
"step": 16360
|
|
},
|
|
{
|
|
"entropy": 5.534250068664551,
|
|
"epoch": 1.8379850620542482,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00046701689463761947,
|
|
"loss": 5.3379,
|
|
"mean_token_accuracy": 0.19235465973615645,
|
|
"num_tokens": 36560394.0,
|
|
"step": 16365
|
|
},
|
|
{
|
|
"entropy": 5.61123833656311,
|
|
"epoch": 1.8385466389622058,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00046699596434963953,
|
|
"loss": 5.3686,
|
|
"mean_token_accuracy": 0.18490458726882936,
|
|
"num_tokens": 36570657.0,
|
|
"step": 16370
|
|
},
|
|
{
|
|
"entropy": 5.4530211925506595,
|
|
"epoch": 1.8391082158701635,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004669750279484337,
|
|
"loss": 5.2226,
|
|
"mean_token_accuracy": 0.19429712146520614,
|
|
"num_tokens": 36580810.0,
|
|
"step": 16375
|
|
},
|
|
{
|
|
"entropy": 5.473446083068848,
|
|
"epoch": 1.839669792778121,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004669540854346685,
|
|
"loss": 5.2702,
|
|
"mean_token_accuracy": 0.18894062936306,
|
|
"num_tokens": 36592981.0,
|
|
"step": 16380
|
|
},
|
|
{
|
|
"entropy": 5.488171720504761,
|
|
"epoch": 1.8402313696860784,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00046693313680901073,
|
|
"loss": 5.2653,
|
|
"mean_token_accuracy": 0.1925550326704979,
|
|
"num_tokens": 36604130.0,
|
|
"step": 16385
|
|
},
|
|
{
|
|
"entropy": 5.470244550704956,
|
|
"epoch": 1.840792946594036,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00046691218207212744,
|
|
"loss": 5.2851,
|
|
"mean_token_accuracy": 0.1861992135643959,
|
|
"num_tokens": 36614833.0,
|
|
"step": 16390
|
|
},
|
|
{
|
|
"entropy": 5.596527481079102,
|
|
"epoch": 1.8413545235019937,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004668912212246859,
|
|
"loss": 5.2951,
|
|
"mean_token_accuracy": 0.19008202254772186,
|
|
"num_tokens": 36625306.0,
|
|
"step": 16395
|
|
},
|
|
{
|
|
"entropy": 5.712037181854248,
|
|
"epoch": 1.8419161004099511,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00046687025426735335,
|
|
"loss": 5.5507,
|
|
"mean_token_accuracy": 0.17697899043560028,
|
|
"num_tokens": 36637396.0,
|
|
"step": 16400
|
|
},
|
|
{
|
|
"entropy": 5.578679132461548,
|
|
"epoch": 1.8424776773179086,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004668492812007976,
|
|
"loss": 5.339,
|
|
"mean_token_accuracy": 0.18426618576049805,
|
|
"num_tokens": 36648175.0,
|
|
"step": 16405
|
|
},
|
|
{
|
|
"entropy": 5.5641011714935305,
|
|
"epoch": 1.8430392542258662,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004668283020256863,
|
|
"loss": 5.3825,
|
|
"mean_token_accuracy": 0.18374981880187988,
|
|
"num_tokens": 36659876.0,
|
|
"step": 16410
|
|
},
|
|
{
|
|
"entropy": 5.546352672576904,
|
|
"epoch": 1.843600831133824,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00046680731674268744,
|
|
"loss": 5.388,
|
|
"mean_token_accuracy": 0.1864971250295639,
|
|
"num_tokens": 36671168.0,
|
|
"step": 16415
|
|
},
|
|
{
|
|
"entropy": 5.492926692962646,
|
|
"epoch": 1.8441624080417813,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004667863253524692,
|
|
"loss": 5.3088,
|
|
"mean_token_accuracy": 0.19539319574832917,
|
|
"num_tokens": 36680987.0,
|
|
"step": 16420
|
|
},
|
|
{
|
|
"entropy": 5.5537152767181395,
|
|
"epoch": 1.8447239849497388,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00046676532785569995,
|
|
"loss": 5.376,
|
|
"mean_token_accuracy": 0.185614974796772,
|
|
"num_tokens": 36692396.0,
|
|
"step": 16425
|
|
},
|
|
{
|
|
"entropy": 5.494251823425293,
|
|
"epoch": 1.8452855618576964,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004667443242530484,
|
|
"loss": 5.2681,
|
|
"mean_token_accuracy": 0.19782126992940902,
|
|
"num_tokens": 36702696.0,
|
|
"step": 16430
|
|
},
|
|
{
|
|
"entropy": 5.4757472515106205,
|
|
"epoch": 1.845847138765654,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00046672331454518314,
|
|
"loss": 5.2973,
|
|
"mean_token_accuracy": 0.19498538821935654,
|
|
"num_tokens": 36713582.0,
|
|
"step": 16435
|
|
},
|
|
{
|
|
"entropy": 5.494393634796142,
|
|
"epoch": 1.8464087156736115,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004667022987327732,
|
|
"loss": 5.2826,
|
|
"mean_token_accuracy": 0.1949489161372185,
|
|
"num_tokens": 36724324.0,
|
|
"step": 16440
|
|
},
|
|
{
|
|
"entropy": 5.568372821807861,
|
|
"epoch": 1.846970292581569,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004666812768164877,
|
|
"loss": 5.3701,
|
|
"mean_token_accuracy": 0.19605543613433837,
|
|
"num_tokens": 36736369.0,
|
|
"step": 16445
|
|
},
|
|
{
|
|
"entropy": 5.556389713287354,
|
|
"epoch": 1.8475318694895266,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00046666024879699606,
|
|
"loss": 5.3992,
|
|
"mean_token_accuracy": 0.19371566474437713,
|
|
"num_tokens": 36748047.0,
|
|
"step": 16450
|
|
},
|
|
{
|
|
"entropy": 5.557503271102905,
|
|
"epoch": 1.8480934463974843,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.00046663921467496766,
|
|
"loss": 5.3201,
|
|
"mean_token_accuracy": 0.19459699243307113,
|
|
"num_tokens": 36758943.0,
|
|
"step": 16455
|
|
},
|
|
{
|
|
"entropy": 5.612880420684815,
|
|
"epoch": 1.8486550233054415,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004666181744510724,
|
|
"loss": 5.3868,
|
|
"mean_token_accuracy": 0.1820188581943512,
|
|
"num_tokens": 36769807.0,
|
|
"step": 16460
|
|
},
|
|
{
|
|
"entropy": 5.468385457992554,
|
|
"epoch": 1.8492166002133992,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00046659712812598017,
|
|
"loss": 5.2466,
|
|
"mean_token_accuracy": 0.19445807486772537,
|
|
"num_tokens": 36780370.0,
|
|
"step": 16465
|
|
},
|
|
{
|
|
"entropy": 5.431660175323486,
|
|
"epoch": 1.8497781771213568,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00046657607570036103,
|
|
"loss": 5.2679,
|
|
"mean_token_accuracy": 0.19591842740774154,
|
|
"num_tokens": 36789757.0,
|
|
"step": 16470
|
|
},
|
|
{
|
|
"entropy": 5.495207262039185,
|
|
"epoch": 1.8503397540293143,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00046655501717488533,
|
|
"loss": 5.3225,
|
|
"mean_token_accuracy": 0.1907737597823143,
|
|
"num_tokens": 36800531.0,
|
|
"step": 16475
|
|
},
|
|
{
|
|
"entropy": 5.57843246459961,
|
|
"epoch": 1.8509013309372717,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004665339525502236,
|
|
"loss": 5.4184,
|
|
"mean_token_accuracy": 0.18473077565431595,
|
|
"num_tokens": 36811666.0,
|
|
"step": 16480
|
|
},
|
|
{
|
|
"entropy": 5.522574234008789,
|
|
"epoch": 1.8514629078452294,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00046651288182704653,
|
|
"loss": 5.2653,
|
|
"mean_token_accuracy": 0.18938798904418946,
|
|
"num_tokens": 36822443.0,
|
|
"step": 16485
|
|
},
|
|
{
|
|
"entropy": 5.5522459030151365,
|
|
"epoch": 1.852024484753187,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004664918050060251,
|
|
"loss": 5.3293,
|
|
"mean_token_accuracy": 0.1872788116335869,
|
|
"num_tokens": 36835517.0,
|
|
"step": 16490
|
|
},
|
|
{
|
|
"entropy": 5.519955110549927,
|
|
"epoch": 1.8525860616611445,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004664707220878302,
|
|
"loss": 5.3371,
|
|
"mean_token_accuracy": 0.19462635815143586,
|
|
"num_tokens": 36845177.0,
|
|
"step": 16495
|
|
},
|
|
{
|
|
"entropy": 5.438331222534179,
|
|
"epoch": 1.853147638569102,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004664496330731334,
|
|
"loss": 5.2798,
|
|
"mean_token_accuracy": 0.18872665315866471,
|
|
"num_tokens": 36855821.0,
|
|
"step": 16500
|
|
},
|
|
{
|
|
"entropy": 5.556100273132325,
|
|
"epoch": 1.8537092154770596,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004664285379626059,
|
|
"loss": 5.389,
|
|
"mean_token_accuracy": 0.1765715792775154,
|
|
"num_tokens": 36866254.0,
|
|
"step": 16505
|
|
},
|
|
{
|
|
"entropy": 5.507565927505493,
|
|
"epoch": 1.8542707923850172,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00046640743675691954,
|
|
"loss": 5.2211,
|
|
"mean_token_accuracy": 0.19270853847265243,
|
|
"num_tokens": 36876348.0,
|
|
"step": 16510
|
|
},
|
|
{
|
|
"entropy": 5.560690546035767,
|
|
"epoch": 1.8548323692929747,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004663863294567462,
|
|
"loss": 5.3788,
|
|
"mean_token_accuracy": 0.1828359082341194,
|
|
"num_tokens": 36888088.0,
|
|
"step": 16515
|
|
},
|
|
{
|
|
"entropy": 5.677534580230713,
|
|
"epoch": 1.8553939462009321,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004663652160627579,
|
|
"loss": 5.4796,
|
|
"mean_token_accuracy": 0.18595814406871797,
|
|
"num_tokens": 36900203.0,
|
|
"step": 16520
|
|
},
|
|
{
|
|
"entropy": 5.587461280822754,
|
|
"epoch": 1.8559555231088898,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00046634409657562683,
|
|
"loss": 5.348,
|
|
"mean_token_accuracy": 0.1860669359564781,
|
|
"num_tokens": 36911321.0,
|
|
"step": 16525
|
|
},
|
|
{
|
|
"entropy": 5.57177586555481,
|
|
"epoch": 1.8565171000168474,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004663229709960255,
|
|
"loss": 5.4303,
|
|
"mean_token_accuracy": 0.18599589318037033,
|
|
"num_tokens": 36922562.0,
|
|
"step": 16530
|
|
},
|
|
{
|
|
"entropy": 5.52012825012207,
|
|
"epoch": 1.8570786769248049,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00046630183932462664,
|
|
"loss": 5.2886,
|
|
"mean_token_accuracy": 0.18841566741466523,
|
|
"num_tokens": 36933923.0,
|
|
"step": 16535
|
|
},
|
|
{
|
|
"entropy": 5.484059810638428,
|
|
"epoch": 1.8576402538327623,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004662807015621031,
|
|
"loss": 5.3064,
|
|
"mean_token_accuracy": 0.1898571565747261,
|
|
"num_tokens": 36945203.0,
|
|
"step": 16540
|
|
},
|
|
{
|
|
"entropy": 5.523033905029297,
|
|
"epoch": 1.85820183074072,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00046625955770912764,
|
|
"loss": 5.2992,
|
|
"mean_token_accuracy": 0.18876135647296904,
|
|
"num_tokens": 36956094.0,
|
|
"step": 16545
|
|
},
|
|
{
|
|
"entropy": 5.586569976806641,
|
|
"epoch": 1.8587634076486776,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00046623840776637384,
|
|
"loss": 5.3545,
|
|
"mean_token_accuracy": 0.19304639995098113,
|
|
"num_tokens": 36967375.0,
|
|
"step": 16550
|
|
},
|
|
{
|
|
"entropy": 5.418436574935913,
|
|
"epoch": 1.859324984556635,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004662172517345149,
|
|
"loss": 5.247,
|
|
"mean_token_accuracy": 0.19597518146038057,
|
|
"num_tokens": 36977674.0,
|
|
"step": 16555
|
|
},
|
|
{
|
|
"entropy": 5.527724647521973,
|
|
"epoch": 1.8598865614645925,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004661960896142245,
|
|
"loss": 5.4098,
|
|
"mean_token_accuracy": 0.19291428476572037,
|
|
"num_tokens": 36990241.0,
|
|
"step": 16560
|
|
},
|
|
{
|
|
"entropy": 5.545258331298828,
|
|
"epoch": 1.8604481383725502,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.00046617492140617654,
|
|
"loss": 5.3528,
|
|
"mean_token_accuracy": 0.1865066796541214,
|
|
"num_tokens": 37002322.0,
|
|
"step": 16565
|
|
},
|
|
{
|
|
"entropy": 5.5665429592132565,
|
|
"epoch": 1.8610097152805076,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004661537471110448,
|
|
"loss": 5.3697,
|
|
"mean_token_accuracy": 0.1901166707277298,
|
|
"num_tokens": 37014524.0,
|
|
"step": 16570
|
|
},
|
|
{
|
|
"entropy": 5.5150861740112305,
|
|
"epoch": 1.861571292188465,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004661325667295037,
|
|
"loss": 5.2295,
|
|
"mean_token_accuracy": 0.19875368624925613,
|
|
"num_tokens": 37025057.0,
|
|
"step": 16575
|
|
},
|
|
{
|
|
"entropy": 5.495872449874878,
|
|
"epoch": 1.8621328690964227,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004661113802622275,
|
|
"loss": 5.382,
|
|
"mean_token_accuracy": 0.1921732857823372,
|
|
"num_tokens": 37035311.0,
|
|
"step": 16580
|
|
},
|
|
{
|
|
"entropy": 5.515810537338257,
|
|
"epoch": 1.8626944460043804,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004660901877098908,
|
|
"loss": 5.3676,
|
|
"mean_token_accuracy": 0.19142916351556777,
|
|
"num_tokens": 37046275.0,
|
|
"step": 16585
|
|
},
|
|
{
|
|
"entropy": 5.527347612380981,
|
|
"epoch": 1.8632560229123378,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004660689890731685,
|
|
"loss": 5.2279,
|
|
"mean_token_accuracy": 0.19131554663181305,
|
|
"num_tokens": 37057658.0,
|
|
"step": 16590
|
|
},
|
|
{
|
|
"entropy": 5.513562154769898,
|
|
"epoch": 1.8638175998202953,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00046604778435273546,
|
|
"loss": 5.2489,
|
|
"mean_token_accuracy": 0.19852979779243468,
|
|
"num_tokens": 37067946.0,
|
|
"step": 16595
|
|
},
|
|
{
|
|
"entropy": 5.453700017929077,
|
|
"epoch": 1.864379176728253,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00046602657354926686,
|
|
"loss": 5.2634,
|
|
"mean_token_accuracy": 0.19169158935546876,
|
|
"num_tokens": 37078881.0,
|
|
"step": 16600
|
|
},
|
|
{
|
|
"entropy": 5.513870763778686,
|
|
"epoch": 1.8649407536362106,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.000466005356663438,
|
|
"loss": 5.3893,
|
|
"mean_token_accuracy": 0.18352641761302949,
|
|
"num_tokens": 37090474.0,
|
|
"step": 16605
|
|
},
|
|
{
|
|
"entropy": 5.539599275588989,
|
|
"epoch": 1.865502330544168,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00046598413369592463,
|
|
"loss": 5.4367,
|
|
"mean_token_accuracy": 0.19055111408233644,
|
|
"num_tokens": 37101527.0,
|
|
"step": 16610
|
|
},
|
|
{
|
|
"entropy": 5.585215616226196,
|
|
"epoch": 1.8660639074521255,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004659629046474023,
|
|
"loss": 5.355,
|
|
"mean_token_accuracy": 0.18252760022878647,
|
|
"num_tokens": 37112615.0,
|
|
"step": 16615
|
|
},
|
|
{
|
|
"entropy": 5.5295312881469725,
|
|
"epoch": 1.8666254843600831,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.000465941669518547,
|
|
"loss": 5.2566,
|
|
"mean_token_accuracy": 0.19171176999807357,
|
|
"num_tokens": 37122922.0,
|
|
"step": 16620
|
|
},
|
|
{
|
|
"entropy": 5.498215818405152,
|
|
"epoch": 1.8671870612680408,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004659204283100349,
|
|
"loss": 5.2786,
|
|
"mean_token_accuracy": 0.19974020570516587,
|
|
"num_tokens": 37133215.0,
|
|
"step": 16625
|
|
},
|
|
{
|
|
"entropy": 5.424301290512085,
|
|
"epoch": 1.8677486381759982,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00046589918102254237,
|
|
"loss": 5.1965,
|
|
"mean_token_accuracy": 0.19507750272750854,
|
|
"num_tokens": 37144292.0,
|
|
"step": 16630
|
|
},
|
|
{
|
|
"entropy": 5.477900838851928,
|
|
"epoch": 1.8683102150839557,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004658779276567458,
|
|
"loss": 5.3558,
|
|
"mean_token_accuracy": 0.18585943430662155,
|
|
"num_tokens": 37155623.0,
|
|
"step": 16635
|
|
},
|
|
{
|
|
"entropy": 5.630840015411377,
|
|
"epoch": 1.8688717919919133,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00046585666821332203,
|
|
"loss": 5.3456,
|
|
"mean_token_accuracy": 0.190969055891037,
|
|
"num_tokens": 37165406.0,
|
|
"step": 16640
|
|
},
|
|
{
|
|
"entropy": 5.563094186782837,
|
|
"epoch": 1.869433368899871,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00046583540269294794,
|
|
"loss": 5.3656,
|
|
"mean_token_accuracy": 0.19431325793266296,
|
|
"num_tokens": 37175522.0,
|
|
"step": 16645
|
|
},
|
|
{
|
|
"entropy": 5.492715883255005,
|
|
"epoch": 1.8699949458078284,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004658141310963006,
|
|
"loss": 5.3912,
|
|
"mean_token_accuracy": 0.19230775833129882,
|
|
"num_tokens": 37186745.0,
|
|
"step": 16650
|
|
},
|
|
{
|
|
"entropy": 5.479142761230468,
|
|
"epoch": 1.8705565227157859,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004657928534240573,
|
|
"loss": 5.2403,
|
|
"mean_token_accuracy": 0.19582124352455138,
|
|
"num_tokens": 37197357.0,
|
|
"step": 16655
|
|
},
|
|
{
|
|
"entropy": 5.554664564132691,
|
|
"epoch": 1.8711180996237435,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.0004657715696768955,
|
|
"loss": 5.3881,
|
|
"mean_token_accuracy": 0.18799951076507568,
|
|
"num_tokens": 37209839.0,
|
|
"step": 16660
|
|
},
|
|
{
|
|
"entropy": 5.596767520904541,
|
|
"epoch": 1.871679676531701,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000465750279855493,
|
|
"loss": 5.4143,
|
|
"mean_token_accuracy": 0.1821955546736717,
|
|
"num_tokens": 37221314.0,
|
|
"step": 16665
|
|
},
|
|
{
|
|
"entropy": 5.569704675674439,
|
|
"epoch": 1.8722412534396584,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004657289839605276,
|
|
"loss": 5.2706,
|
|
"mean_token_accuracy": 0.1906728371977806,
|
|
"num_tokens": 37233372.0,
|
|
"step": 16670
|
|
},
|
|
{
|
|
"entropy": 5.593374586105346,
|
|
"epoch": 1.872802830347616,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004657076819926774,
|
|
"loss": 5.3701,
|
|
"mean_token_accuracy": 0.18732914477586746,
|
|
"num_tokens": 37244758.0,
|
|
"step": 16675
|
|
},
|
|
{
|
|
"entropy": 5.568263387680053,
|
|
"epoch": 1.8733644072555737,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004656863739526206,
|
|
"loss": 5.3281,
|
|
"mean_token_accuracy": 0.18720599859952927,
|
|
"num_tokens": 37255848.0,
|
|
"step": 16680
|
|
},
|
|
{
|
|
"entropy": 5.488857936859131,
|
|
"epoch": 1.8739259841635312,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00046566505984103575,
|
|
"loss": 5.2712,
|
|
"mean_token_accuracy": 0.1951414555311203,
|
|
"num_tokens": 37266010.0,
|
|
"step": 16685
|
|
},
|
|
{
|
|
"entropy": 5.4241259574890135,
|
|
"epoch": 1.8744875610714886,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004656437396586014,
|
|
"loss": 5.2931,
|
|
"mean_token_accuracy": 0.18768802732229234,
|
|
"num_tokens": 37278445.0,
|
|
"step": 16690
|
|
},
|
|
{
|
|
"entropy": 5.642972850799561,
|
|
"epoch": 1.8750491379794463,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004656224134059964,
|
|
"loss": 5.4392,
|
|
"mean_token_accuracy": 0.18230196088552475,
|
|
"num_tokens": 37291181.0,
|
|
"step": 16695
|
|
},
|
|
{
|
|
"entropy": 5.6833336353302,
|
|
"epoch": 1.875610714887404,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00046560108108389985,
|
|
"loss": 5.52,
|
|
"mean_token_accuracy": 0.18521885722875595,
|
|
"num_tokens": 37302333.0,
|
|
"step": 16700
|
|
},
|
|
{
|
|
"entropy": 5.516350030899048,
|
|
"epoch": 1.8761722917953614,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.000465579742692991,
|
|
"loss": 5.2709,
|
|
"mean_token_accuracy": 0.1961539715528488,
|
|
"num_tokens": 37312754.0,
|
|
"step": 16705
|
|
},
|
|
{
|
|
"entropy": 5.5581494808197025,
|
|
"epoch": 1.8767338687033188,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004655583982339492,
|
|
"loss": 5.3492,
|
|
"mean_token_accuracy": 0.19225821644067764,
|
|
"num_tokens": 37323335.0,
|
|
"step": 16710
|
|
},
|
|
{
|
|
"entropy": 5.565476655960083,
|
|
"epoch": 1.8772954456112765,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004655370477074541,
|
|
"loss": 5.3435,
|
|
"mean_token_accuracy": 0.1916085883975029,
|
|
"num_tokens": 37334332.0,
|
|
"step": 16715
|
|
},
|
|
{
|
|
"entropy": 5.5233629703521725,
|
|
"epoch": 1.8778570225192341,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004655156911141855,
|
|
"loss": 5.3511,
|
|
"mean_token_accuracy": 0.18915074169635773,
|
|
"num_tokens": 37344770.0,
|
|
"step": 16720
|
|
},
|
|
{
|
|
"entropy": 5.549921321868896,
|
|
"epoch": 1.8784185994271916,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004654943284548234,
|
|
"loss": 5.2933,
|
|
"mean_token_accuracy": 0.1868213325738907,
|
|
"num_tokens": 37356009.0,
|
|
"step": 16725
|
|
},
|
|
{
|
|
"entropy": 5.4536461353302,
|
|
"epoch": 1.878980176335149,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.00046547295973004807,
|
|
"loss": 5.2729,
|
|
"mean_token_accuracy": 0.19684419333934783,
|
|
"num_tokens": 37367823.0,
|
|
"step": 16730
|
|
},
|
|
{
|
|
"entropy": 5.45973949432373,
|
|
"epoch": 1.8795417532431067,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00046545158494053966,
|
|
"loss": 5.3001,
|
|
"mean_token_accuracy": 0.18995605856180192,
|
|
"num_tokens": 37378156.0,
|
|
"step": 16735
|
|
},
|
|
{
|
|
"entropy": 5.555756092071533,
|
|
"epoch": 1.8801033301510643,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00046543020408697905,
|
|
"loss": 5.339,
|
|
"mean_token_accuracy": 0.1906617671251297,
|
|
"num_tokens": 37388378.0,
|
|
"step": 16740
|
|
},
|
|
{
|
|
"entropy": 5.4716565132141115,
|
|
"epoch": 1.8806649070590218,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00046540881717004685,
|
|
"loss": 5.2365,
|
|
"mean_token_accuracy": 0.18968347012996672,
|
|
"num_tokens": 37398457.0,
|
|
"step": 16745
|
|
},
|
|
{
|
|
"entropy": 5.553845930099487,
|
|
"epoch": 1.8812264839669792,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004653874241904241,
|
|
"loss": 5.4273,
|
|
"mean_token_accuracy": 0.1854670152068138,
|
|
"num_tokens": 37409341.0,
|
|
"step": 16750
|
|
},
|
|
{
|
|
"entropy": 5.5429408073425295,
|
|
"epoch": 1.8817880608749369,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004653660251487919,
|
|
"loss": 5.2391,
|
|
"mean_token_accuracy": 0.19419020563364028,
|
|
"num_tokens": 37420081.0,
|
|
"step": 16755
|
|
},
|
|
{
|
|
"entropy": 5.446212291717529,
|
|
"epoch": 1.8823496377828943,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.00046534462004583154,
|
|
"loss": 5.2324,
|
|
"mean_token_accuracy": 0.20230178385972977,
|
|
"num_tokens": 37430707.0,
|
|
"step": 16760
|
|
},
|
|
{
|
|
"entropy": 5.4975244998931885,
|
|
"epoch": 1.8829112146908518,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004653232088822248,
|
|
"loss": 5.3504,
|
|
"mean_token_accuracy": 0.18768247067928315,
|
|
"num_tokens": 37441250.0,
|
|
"step": 16765
|
|
},
|
|
{
|
|
"entropy": 5.561507081985473,
|
|
"epoch": 1.8834727915988094,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004653017916586532,
|
|
"loss": 5.4027,
|
|
"mean_token_accuracy": 0.18384319096803664,
|
|
"num_tokens": 37452909.0,
|
|
"step": 16770
|
|
},
|
|
{
|
|
"entropy": 5.5425133228302,
|
|
"epoch": 1.884034368506767,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004652803683757987,
|
|
"loss": 5.3365,
|
|
"mean_token_accuracy": 0.1840794563293457,
|
|
"num_tokens": 37463833.0,
|
|
"step": 16775
|
|
},
|
|
{
|
|
"entropy": 5.441729974746704,
|
|
"epoch": 1.8845959454147245,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004652589390343436,
|
|
"loss": 5.2705,
|
|
"mean_token_accuracy": 0.19357890188694,
|
|
"num_tokens": 37473967.0,
|
|
"step": 16780
|
|
},
|
|
{
|
|
"entropy": 5.564308452606201,
|
|
"epoch": 1.885157522322682,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00046523750363497,
|
|
"loss": 5.3053,
|
|
"mean_token_accuracy": 0.19836509376764297,
|
|
"num_tokens": 37484748.0,
|
|
"step": 16785
|
|
},
|
|
{
|
|
"entropy": 5.549997997283936,
|
|
"epoch": 1.8857190992306396,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004652160621783605,
|
|
"loss": 5.3301,
|
|
"mean_token_accuracy": 0.1822197899222374,
|
|
"num_tokens": 37495757.0,
|
|
"step": 16790
|
|
},
|
|
{
|
|
"entropy": 5.497464179992676,
|
|
"epoch": 1.8862806761385973,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00046519461466519785,
|
|
"loss": 5.3374,
|
|
"mean_token_accuracy": 0.1866649031639099,
|
|
"num_tokens": 37506612.0,
|
|
"step": 16795
|
|
},
|
|
{
|
|
"entropy": 5.467371129989624,
|
|
"epoch": 1.8868422530465547,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004651731610961649,
|
|
"loss": 5.2538,
|
|
"mean_token_accuracy": 0.19866592735052108,
|
|
"num_tokens": 37518639.0,
|
|
"step": 16800
|
|
},
|
|
{
|
|
"entropy": 5.52176194190979,
|
|
"epoch": 1.8874038299545122,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004651517014719446,
|
|
"loss": 5.3212,
|
|
"mean_token_accuracy": 0.18694213777780533,
|
|
"num_tokens": 37530020.0,
|
|
"step": 16805
|
|
},
|
|
{
|
|
"entropy": 5.483829069137573,
|
|
"epoch": 1.8879654068624698,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004651302357932206,
|
|
"loss": 5.2563,
|
|
"mean_token_accuracy": 0.1908920630812645,
|
|
"num_tokens": 37540737.0,
|
|
"step": 16810
|
|
},
|
|
{
|
|
"entropy": 5.427550506591797,
|
|
"epoch": 1.8885269837704275,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000465108764060676,
|
|
"loss": 5.275,
|
|
"mean_token_accuracy": 0.18921370804309845,
|
|
"num_tokens": 37551091.0,
|
|
"step": 16815
|
|
},
|
|
{
|
|
"entropy": 5.542868661880493,
|
|
"epoch": 1.889088560678385,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00046508728627499464,
|
|
"loss": 5.3951,
|
|
"mean_token_accuracy": 0.18349259197711945,
|
|
"num_tokens": 37561904.0,
|
|
"step": 16820
|
|
},
|
|
{
|
|
"entropy": 5.62216272354126,
|
|
"epoch": 1.8896501375863424,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004650658024368604,
|
|
"loss": 5.4204,
|
|
"mean_token_accuracy": 0.1816960707306862,
|
|
"num_tokens": 37573532.0,
|
|
"step": 16825
|
|
},
|
|
{
|
|
"entropy": 5.659744358062744,
|
|
"epoch": 1.8902117144943,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004650443125469573,
|
|
"loss": 5.4083,
|
|
"mean_token_accuracy": 0.19345381557941438,
|
|
"num_tokens": 37584886.0,
|
|
"step": 16830
|
|
},
|
|
{
|
|
"entropy": 5.502018308639526,
|
|
"epoch": 1.8907732914022577,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004650228166059695,
|
|
"loss": 5.3367,
|
|
"mean_token_accuracy": 0.18997133523225784,
|
|
"num_tokens": 37595190.0,
|
|
"step": 16835
|
|
},
|
|
{
|
|
"entropy": 5.446289587020874,
|
|
"epoch": 1.8913348683102151,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004650013146145816,
|
|
"loss": 5.2862,
|
|
"mean_token_accuracy": 0.19220385253429412,
|
|
"num_tokens": 37605776.0,
|
|
"step": 16840
|
|
},
|
|
{
|
|
"entropy": 5.606544780731201,
|
|
"epoch": 1.8918964452181726,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004649798065734781,
|
|
"loss": 5.3897,
|
|
"mean_token_accuracy": 0.18499674052000045,
|
|
"num_tokens": 37616882.0,
|
|
"step": 16845
|
|
},
|
|
{
|
|
"entropy": 5.664537143707276,
|
|
"epoch": 1.8924580221261302,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00046495829248334393,
|
|
"loss": 5.4515,
|
|
"mean_token_accuracy": 0.18400414884090424,
|
|
"num_tokens": 37628528.0,
|
|
"step": 16850
|
|
},
|
|
{
|
|
"entropy": 5.551404237747192,
|
|
"epoch": 1.8930195990340877,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004649367723448641,
|
|
"loss": 5.3587,
|
|
"mean_token_accuracy": 0.18622815757989883,
|
|
"num_tokens": 37640502.0,
|
|
"step": 16855
|
|
},
|
|
{
|
|
"entropy": 5.4735455989837645,
|
|
"epoch": 1.8935811759420451,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00046491524615872366,
|
|
"loss": 5.3133,
|
|
"mean_token_accuracy": 0.1845741242170334,
|
|
"num_tokens": 37652845.0,
|
|
"step": 16860
|
|
},
|
|
{
|
|
"entropy": 5.5555400371551515,
|
|
"epoch": 1.8941427528500028,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00046489371392560816,
|
|
"loss": 5.451,
|
|
"mean_token_accuracy": 0.1814900740981102,
|
|
"num_tokens": 37665418.0,
|
|
"step": 16865
|
|
},
|
|
{
|
|
"entropy": 5.5555469512939455,
|
|
"epoch": 1.8947043297579604,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.00046487217564620317,
|
|
"loss": 5.3789,
|
|
"mean_token_accuracy": 0.1876147910952568,
|
|
"num_tokens": 37676429.0,
|
|
"step": 16870
|
|
},
|
|
{
|
|
"entropy": 5.571235418319702,
|
|
"epoch": 1.8952659066659179,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004648506313211945,
|
|
"loss": 5.3486,
|
|
"mean_token_accuracy": 0.19341038316488265,
|
|
"num_tokens": 37686779.0,
|
|
"step": 16875
|
|
},
|
|
{
|
|
"entropy": 5.491058588027954,
|
|
"epoch": 1.8958274835738753,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00046482908095126803,
|
|
"loss": 5.3897,
|
|
"mean_token_accuracy": 0.18769828379154205,
|
|
"num_tokens": 37697665.0,
|
|
"step": 16880
|
|
},
|
|
{
|
|
"entropy": 5.5995521068573,
|
|
"epoch": 1.896389060481833,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00046480752453711,
|
|
"loss": 5.3992,
|
|
"mean_token_accuracy": 0.18566225469112396,
|
|
"num_tokens": 37708987.0,
|
|
"step": 16885
|
|
},
|
|
{
|
|
"entropy": 5.495259618759155,
|
|
"epoch": 1.8969506373897906,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004647859620794068,
|
|
"loss": 5.2325,
|
|
"mean_token_accuracy": 0.1924973323941231,
|
|
"num_tokens": 37720335.0,
|
|
"step": 16890
|
|
},
|
|
{
|
|
"entropy": 5.579281902313232,
|
|
"epoch": 1.897512214297748,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00046476439357884497,
|
|
"loss": 5.4145,
|
|
"mean_token_accuracy": 0.18679735511541368,
|
|
"num_tokens": 37731586.0,
|
|
"step": 16895
|
|
},
|
|
{
|
|
"entropy": 5.562653350830078,
|
|
"epoch": 1.8980737912057055,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.00046474281903611126,
|
|
"loss": 5.3104,
|
|
"mean_token_accuracy": 0.19232197701931,
|
|
"num_tokens": 37742907.0,
|
|
"step": 16900
|
|
},
|
|
{
|
|
"entropy": 5.62323112487793,
|
|
"epoch": 1.8986353681136632,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00046472123845189253,
|
|
"loss": 5.3992,
|
|
"mean_token_accuracy": 0.18631621599197387,
|
|
"num_tokens": 37753787.0,
|
|
"step": 16905
|
|
},
|
|
{
|
|
"entropy": 5.490570402145385,
|
|
"epoch": 1.8991969450216208,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000464699651826876,
|
|
"loss": 5.3081,
|
|
"mean_token_accuracy": 0.1899639844894409,
|
|
"num_tokens": 37766047.0,
|
|
"step": 16910
|
|
},
|
|
{
|
|
"entropy": 5.505640983581543,
|
|
"epoch": 1.8997585219295783,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00046467805916174907,
|
|
"loss": 5.2912,
|
|
"mean_token_accuracy": 0.1874990016222,
|
|
"num_tokens": 37777651.0,
|
|
"step": 16915
|
|
},
|
|
{
|
|
"entropy": 5.486234426498413,
|
|
"epoch": 1.9003200988375357,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.00046465646045719915,
|
|
"loss": 5.3304,
|
|
"mean_token_accuracy": 0.1921023830771446,
|
|
"num_tokens": 37788527.0,
|
|
"step": 16920
|
|
},
|
|
{
|
|
"entropy": 5.444620609283447,
|
|
"epoch": 1.9008816757454934,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004646348557139139,
|
|
"loss": 5.2755,
|
|
"mean_token_accuracy": 0.18400513976812363,
|
|
"num_tokens": 37800727.0,
|
|
"step": 16925
|
|
},
|
|
{
|
|
"entropy": 5.529443979263306,
|
|
"epoch": 1.901443252653451,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.00046461324493258133,
|
|
"loss": 5.2671,
|
|
"mean_token_accuracy": 0.1931947410106659,
|
|
"num_tokens": 37812332.0,
|
|
"step": 16930
|
|
},
|
|
{
|
|
"entropy": 5.5595433712005615,
|
|
"epoch": 1.9020048295614085,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00046459162811388955,
|
|
"loss": 5.3685,
|
|
"mean_token_accuracy": 0.18835092037916185,
|
|
"num_tokens": 37823665.0,
|
|
"step": 16935
|
|
},
|
|
{
|
|
"entropy": 5.451412010192871,
|
|
"epoch": 1.902566406469366,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004645700052585267,
|
|
"loss": 5.1889,
|
|
"mean_token_accuracy": 0.20055983066558838,
|
|
"num_tokens": 37833793.0,
|
|
"step": 16940
|
|
},
|
|
{
|
|
"entropy": 5.42030701637268,
|
|
"epoch": 1.9031279833773236,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004645483763671815,
|
|
"loss": 5.222,
|
|
"mean_token_accuracy": 0.1994650512933731,
|
|
"num_tokens": 37844104.0,
|
|
"step": 16945
|
|
},
|
|
{
|
|
"entropy": 5.556173849105835,
|
|
"epoch": 1.903689560285281,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00046452674144054236,
|
|
"loss": 5.3015,
|
|
"mean_token_accuracy": 0.19548871517181396,
|
|
"num_tokens": 37853920.0,
|
|
"step": 16950
|
|
},
|
|
{
|
|
"entropy": 5.505234622955323,
|
|
"epoch": 1.9042511371932385,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00046450510047929826,
|
|
"loss": 5.3638,
|
|
"mean_token_accuracy": 0.18661977350711823,
|
|
"num_tokens": 37865749.0,
|
|
"step": 16955
|
|
},
|
|
{
|
|
"entropy": 5.4916908740997314,
|
|
"epoch": 1.9048127141011961,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00046448345348413833,
|
|
"loss": 5.3213,
|
|
"mean_token_accuracy": 0.18939271867275237,
|
|
"num_tokens": 37876259.0,
|
|
"step": 16960
|
|
},
|
|
{
|
|
"entropy": 5.591541385650634,
|
|
"epoch": 1.9053742910091538,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004644618004557517,
|
|
"loss": 5.3973,
|
|
"mean_token_accuracy": 0.18937608003616332,
|
|
"num_tokens": 37887186.0,
|
|
"step": 16965
|
|
},
|
|
{
|
|
"entropy": 5.450802040100098,
|
|
"epoch": 1.9059358679171112,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004644401413948279,
|
|
"loss": 5.2058,
|
|
"mean_token_accuracy": 0.19802374243736268,
|
|
"num_tokens": 37898210.0,
|
|
"step": 16970
|
|
},
|
|
{
|
|
"entropy": 5.5113931655883786,
|
|
"epoch": 1.9064974448250687,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004644184763020565,
|
|
"loss": 5.3294,
|
|
"mean_token_accuracy": 0.1850786715745926,
|
|
"num_tokens": 37909332.0,
|
|
"step": 16975
|
|
},
|
|
{
|
|
"entropy": 5.499251031875611,
|
|
"epoch": 1.9070590217330263,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004643968051781273,
|
|
"loss": 5.2756,
|
|
"mean_token_accuracy": 0.1952410012483597,
|
|
"num_tokens": 37919796.0,
|
|
"step": 16980
|
|
},
|
|
{
|
|
"entropy": 5.546873712539673,
|
|
"epoch": 1.907620598640984,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004643751280237305,
|
|
"loss": 5.4289,
|
|
"mean_token_accuracy": 0.18502222895622253,
|
|
"num_tokens": 37931135.0,
|
|
"step": 16985
|
|
},
|
|
{
|
|
"entropy": 5.632438373565674,
|
|
"epoch": 1.9081821755489414,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004643534448395561,
|
|
"loss": 5.4213,
|
|
"mean_token_accuracy": 0.18655699491500854,
|
|
"num_tokens": 37942302.0,
|
|
"step": 16990
|
|
},
|
|
{
|
|
"entropy": 5.503334045410156,
|
|
"epoch": 1.9087437524568989,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004643317556262946,
|
|
"loss": 5.3274,
|
|
"mean_token_accuracy": 0.18913712799549104,
|
|
"num_tokens": 37954188.0,
|
|
"step": 16995
|
|
},
|
|
{
|
|
"entropy": 5.523032188415527,
|
|
"epoch": 1.9093053293648565,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00046431006038463653,
|
|
"loss": 5.3595,
|
|
"mean_token_accuracy": 0.18022434711456298,
|
|
"num_tokens": 37964778.0,
|
|
"step": 17000
|
|
},
|
|
{
|
|
"entropy": 5.638865041732788,
|
|
"epoch": 1.9098669062728142,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004642883591152727,
|
|
"loss": 5.3805,
|
|
"mean_token_accuracy": 0.1816907823085785,
|
|
"num_tokens": 37976384.0,
|
|
"step": 17005
|
|
},
|
|
{
|
|
"entropy": 5.5630089282989506,
|
|
"epoch": 1.9104284831807716,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004642666518188942,
|
|
"loss": 5.3749,
|
|
"mean_token_accuracy": 0.18493264317512512,
|
|
"num_tokens": 37986975.0,
|
|
"step": 17010
|
|
},
|
|
{
|
|
"entropy": 5.65526819229126,
|
|
"epoch": 1.910990060088729,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00046424493849619205,
|
|
"loss": 5.486,
|
|
"mean_token_accuracy": 0.18746909946203233,
|
|
"num_tokens": 37999255.0,
|
|
"step": 17015
|
|
},
|
|
{
|
|
"entropy": 5.624090242385864,
|
|
"epoch": 1.9115516369966867,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.00046422321914785757,
|
|
"loss": 5.4296,
|
|
"mean_token_accuracy": 0.18602934181690217,
|
|
"num_tokens": 38010436.0,
|
|
"step": 17020
|
|
},
|
|
{
|
|
"entropy": 5.434043741226196,
|
|
"epoch": 1.9121132139046444,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00046420149377458255,
|
|
"loss": 5.2446,
|
|
"mean_token_accuracy": 0.19463708102703095,
|
|
"num_tokens": 38021537.0,
|
|
"step": 17025
|
|
},
|
|
{
|
|
"entropy": 5.514421558380127,
|
|
"epoch": 1.9126747908126018,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00046417976237705846,
|
|
"loss": 5.3261,
|
|
"mean_token_accuracy": 0.18595751821994783,
|
|
"num_tokens": 38033396.0,
|
|
"step": 17030
|
|
},
|
|
{
|
|
"entropy": 5.533701801300049,
|
|
"epoch": 1.9132363677205593,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00046415802495597744,
|
|
"loss": 5.2384,
|
|
"mean_token_accuracy": 0.20455720126628876,
|
|
"num_tokens": 38044917.0,
|
|
"step": 17035
|
|
},
|
|
{
|
|
"entropy": 5.525361251831055,
|
|
"epoch": 1.913797944628517,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00046413628151203154,
|
|
"loss": 5.4001,
|
|
"mean_token_accuracy": 0.19001386910676957,
|
|
"num_tokens": 38057002.0,
|
|
"step": 17040
|
|
},
|
|
{
|
|
"entropy": 5.448178672790528,
|
|
"epoch": 1.9143595215364744,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00046411453204591303,
|
|
"loss": 5.1667,
|
|
"mean_token_accuracy": 0.20019909888505935,
|
|
"num_tokens": 38068023.0,
|
|
"step": 17045
|
|
},
|
|
{
|
|
"entropy": 5.618009853363037,
|
|
"epoch": 1.9149210984444318,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.00046409277655831455,
|
|
"loss": 5.4787,
|
|
"mean_token_accuracy": 0.17797086536884307,
|
|
"num_tokens": 38080137.0,
|
|
"step": 17050
|
|
},
|
|
{
|
|
"entropy": 5.601627683639526,
|
|
"epoch": 1.9154826753523895,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004640710150499287,
|
|
"loss": 5.2752,
|
|
"mean_token_accuracy": 0.19400590062141418,
|
|
"num_tokens": 38090078.0,
|
|
"step": 17055
|
|
},
|
|
{
|
|
"entropy": 5.5804304599761965,
|
|
"epoch": 1.9160442522603471,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.00046404924752144834,
|
|
"loss": 5.3996,
|
|
"mean_token_accuracy": 0.18672227412462233,
|
|
"num_tokens": 38101410.0,
|
|
"step": 17060
|
|
},
|
|
{
|
|
"entropy": 5.512361478805542,
|
|
"epoch": 1.9166058291683046,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00046402747397356666,
|
|
"loss": 5.2792,
|
|
"mean_token_accuracy": 0.19851553738117217,
|
|
"num_tokens": 38111610.0,
|
|
"step": 17065
|
|
},
|
|
{
|
|
"entropy": 5.558873319625855,
|
|
"epoch": 1.917167406076262,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004640056944069768,
|
|
"loss": 5.3149,
|
|
"mean_token_accuracy": 0.19130940288305281,
|
|
"num_tokens": 38122947.0,
|
|
"step": 17070
|
|
},
|
|
{
|
|
"entropy": 5.499215221405029,
|
|
"epoch": 1.9177289829842197,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004639839088223725,
|
|
"loss": 5.2677,
|
|
"mean_token_accuracy": 0.20023803561925888,
|
|
"num_tokens": 38133083.0,
|
|
"step": 17075
|
|
},
|
|
{
|
|
"entropy": 5.53978419303894,
|
|
"epoch": 1.9182905598921773,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00046396211722044716,
|
|
"loss": 5.315,
|
|
"mean_token_accuracy": 0.1979520857334137,
|
|
"num_tokens": 38142941.0,
|
|
"step": 17080
|
|
},
|
|
{
|
|
"entropy": 5.56115345954895,
|
|
"epoch": 1.9188521368001348,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.00046394031960189473,
|
|
"loss": 5.3485,
|
|
"mean_token_accuracy": 0.18756425976753235,
|
|
"num_tokens": 38154269.0,
|
|
"step": 17085
|
|
},
|
|
{
|
|
"entropy": 5.49371976852417,
|
|
"epoch": 1.9194137137080922,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004639185159674093,
|
|
"loss": 5.266,
|
|
"mean_token_accuracy": 0.19421560764312745,
|
|
"num_tokens": 38164153.0,
|
|
"step": 17090
|
|
},
|
|
{
|
|
"entropy": 5.554946804046631,
|
|
"epoch": 1.9199752906160499,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.00046389670631768494,
|
|
"loss": 5.3929,
|
|
"mean_token_accuracy": 0.1864183157682419,
|
|
"num_tokens": 38174704.0,
|
|
"step": 17095
|
|
},
|
|
{
|
|
"entropy": 5.675718641281128,
|
|
"epoch": 1.9205368675240075,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004638748906534162,
|
|
"loss": 5.423,
|
|
"mean_token_accuracy": 0.18479039371013642,
|
|
"num_tokens": 38186292.0,
|
|
"step": 17100
|
|
},
|
|
{
|
|
"entropy": 5.5812060832977295,
|
|
"epoch": 1.921098444431965,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004638530689752977,
|
|
"loss": 5.3528,
|
|
"mean_token_accuracy": 0.1936494678258896,
|
|
"num_tokens": 38197419.0,
|
|
"step": 17105
|
|
},
|
|
{
|
|
"entropy": 5.524025583267212,
|
|
"epoch": 1.9216600213399224,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00046383124128402433,
|
|
"loss": 5.359,
|
|
"mean_token_accuracy": 0.18838028460741044,
|
|
"num_tokens": 38208276.0,
|
|
"step": 17110
|
|
},
|
|
{
|
|
"entropy": 5.435537338256836,
|
|
"epoch": 1.92222159824788,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00046380940758029095,
|
|
"loss": 5.2467,
|
|
"mean_token_accuracy": 0.1975184515118599,
|
|
"num_tokens": 38220276.0,
|
|
"step": 17115
|
|
},
|
|
{
|
|
"entropy": 5.510719680786133,
|
|
"epoch": 1.9227831751558377,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00046378756786479274,
|
|
"loss": 5.3592,
|
|
"mean_token_accuracy": 0.1928332716226578,
|
|
"num_tokens": 38230760.0,
|
|
"step": 17120
|
|
},
|
|
{
|
|
"entropy": 5.502442646026611,
|
|
"epoch": 1.9233447520637952,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004637657221382252,
|
|
"loss": 5.2511,
|
|
"mean_token_accuracy": 0.19449742287397384,
|
|
"num_tokens": 38241769.0,
|
|
"step": 17125
|
|
},
|
|
{
|
|
"entropy": 5.562748861312866,
|
|
"epoch": 1.9239063289717526,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00046374387040128384,
|
|
"loss": 5.3496,
|
|
"mean_token_accuracy": 0.18859248012304305,
|
|
"num_tokens": 38252800.0,
|
|
"step": 17130
|
|
},
|
|
{
|
|
"entropy": 5.461896514892578,
|
|
"epoch": 1.9244679058797103,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.00046372201265466444,
|
|
"loss": 5.2612,
|
|
"mean_token_accuracy": 0.1905917689204216,
|
|
"num_tokens": 38264319.0,
|
|
"step": 17135
|
|
},
|
|
{
|
|
"entropy": 5.46633825302124,
|
|
"epoch": 1.9250294827876677,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.000463700148899063,
|
|
"loss": 5.3072,
|
|
"mean_token_accuracy": 0.1901361256837845,
|
|
"num_tokens": 38275118.0,
|
|
"step": 17140
|
|
},
|
|
{
|
|
"entropy": 5.656360721588134,
|
|
"epoch": 1.9255910596956252,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004636782791351756,
|
|
"loss": 5.4582,
|
|
"mean_token_accuracy": 0.18556168526411057,
|
|
"num_tokens": 38286264.0,
|
|
"step": 17145
|
|
},
|
|
{
|
|
"entropy": 5.5240942478179935,
|
|
"epoch": 1.9261526366035828,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004636564033636987,
|
|
"loss": 5.2513,
|
|
"mean_token_accuracy": 0.19560887068510055,
|
|
"num_tokens": 38297603.0,
|
|
"step": 17150
|
|
},
|
|
{
|
|
"entropy": 5.538367128372192,
|
|
"epoch": 1.9267142135115405,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00046363452158532857,
|
|
"loss": 5.3964,
|
|
"mean_token_accuracy": 0.1822678416967392,
|
|
"num_tokens": 38308760.0,
|
|
"step": 17155
|
|
},
|
|
{
|
|
"entropy": 5.582892894744873,
|
|
"epoch": 1.927275790419498,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004636126338007622,
|
|
"loss": 5.3517,
|
|
"mean_token_accuracy": 0.18947700262069703,
|
|
"num_tokens": 38320807.0,
|
|
"step": 17160
|
|
},
|
|
{
|
|
"entropy": 5.46394453048706,
|
|
"epoch": 1.9278373673274554,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004635907400106965,
|
|
"loss": 5.3272,
|
|
"mean_token_accuracy": 0.18540936410427095,
|
|
"num_tokens": 38331087.0,
|
|
"step": 17165
|
|
},
|
|
{
|
|
"entropy": 5.478472423553467,
|
|
"epoch": 1.928398944235413,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004635688402158285,
|
|
"loss": 5.2903,
|
|
"mean_token_accuracy": 0.19315948486328124,
|
|
"num_tokens": 38341659.0,
|
|
"step": 17170
|
|
},
|
|
{
|
|
"entropy": 5.470145225524902,
|
|
"epoch": 1.9289605211433707,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00046354693441685537,
|
|
"loss": 5.254,
|
|
"mean_token_accuracy": 0.1987090140581131,
|
|
"num_tokens": 38351371.0,
|
|
"step": 17175
|
|
},
|
|
{
|
|
"entropy": 5.468095541000366,
|
|
"epoch": 1.9295220980513281,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00046352502261447475,
|
|
"loss": 5.262,
|
|
"mean_token_accuracy": 0.1989993393421173,
|
|
"num_tokens": 38362677.0,
|
|
"step": 17180
|
|
},
|
|
{
|
|
"entropy": 5.46759262084961,
|
|
"epoch": 1.9300836749592856,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004635031048093843,
|
|
"loss": 5.3095,
|
|
"mean_token_accuracy": 0.19176963865756988,
|
|
"num_tokens": 38372882.0,
|
|
"step": 17185
|
|
},
|
|
{
|
|
"entropy": 5.596657609939575,
|
|
"epoch": 1.9306452518672432,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004634811810022819,
|
|
"loss": 5.4029,
|
|
"mean_token_accuracy": 0.18605346381664276,
|
|
"num_tokens": 38383401.0,
|
|
"step": 17190
|
|
},
|
|
{
|
|
"entropy": 5.599388122558594,
|
|
"epoch": 1.931206828775201,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00046345925119386556,
|
|
"loss": 5.432,
|
|
"mean_token_accuracy": 0.1843906819820404,
|
|
"num_tokens": 38394733.0,
|
|
"step": 17195
|
|
},
|
|
{
|
|
"entropy": 5.609647226333618,
|
|
"epoch": 1.9317684056831583,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004634373153848336,
|
|
"loss": 5.3993,
|
|
"mean_token_accuracy": 0.19139508306980133,
|
|
"num_tokens": 38406482.0,
|
|
"step": 17200
|
|
},
|
|
{
|
|
"entropy": 5.578036069869995,
|
|
"epoch": 1.9323299825911158,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004634153735758845,
|
|
"loss": 5.3039,
|
|
"mean_token_accuracy": 0.19059739410877227,
|
|
"num_tokens": 38417366.0,
|
|
"step": 17205
|
|
},
|
|
{
|
|
"entropy": 5.554816341400146,
|
|
"epoch": 1.9328915594990734,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004633934257677167,
|
|
"loss": 5.37,
|
|
"mean_token_accuracy": 0.19673199206590652,
|
|
"num_tokens": 38428440.0,
|
|
"step": 17210
|
|
},
|
|
{
|
|
"entropy": 5.5706367015838625,
|
|
"epoch": 1.933453136407031,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004633714719610292,
|
|
"loss": 5.3233,
|
|
"mean_token_accuracy": 0.1908646509051323,
|
|
"num_tokens": 38438471.0,
|
|
"step": 17215
|
|
},
|
|
{
|
|
"entropy": 5.588924694061279,
|
|
"epoch": 1.9340147133149885,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00046334951215652097,
|
|
"loss": 5.3018,
|
|
"mean_token_accuracy": 0.19423958659172058,
|
|
"num_tokens": 38448990.0,
|
|
"step": 17220
|
|
},
|
|
{
|
|
"entropy": 5.582559108734131,
|
|
"epoch": 1.934576290222946,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.00046332754635489126,
|
|
"loss": 5.3657,
|
|
"mean_token_accuracy": 0.18794859498739241,
|
|
"num_tokens": 38460990.0,
|
|
"step": 17225
|
|
},
|
|
{
|
|
"entropy": 5.569936895370484,
|
|
"epoch": 1.9351378671309036,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004633055745568394,
|
|
"loss": 5.4139,
|
|
"mean_token_accuracy": 0.1809059590101242,
|
|
"num_tokens": 38471672.0,
|
|
"step": 17230
|
|
},
|
|
{
|
|
"entropy": 5.4709044933319095,
|
|
"epoch": 1.935699444038861,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00046328359676306506,
|
|
"loss": 5.2884,
|
|
"mean_token_accuracy": 0.1941262200474739,
|
|
"num_tokens": 38483248.0,
|
|
"step": 17235
|
|
},
|
|
{
|
|
"entropy": 5.566699647903443,
|
|
"epoch": 1.9362610209468185,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.000463261612974268,
|
|
"loss": 5.3048,
|
|
"mean_token_accuracy": 0.19185658544301987,
|
|
"num_tokens": 38494795.0,
|
|
"step": 17240
|
|
},
|
|
{
|
|
"entropy": 5.485395050048828,
|
|
"epoch": 1.9368225978547762,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004632396231911481,
|
|
"loss": 5.3053,
|
|
"mean_token_accuracy": 0.19147204756736755,
|
|
"num_tokens": 38505276.0,
|
|
"step": 17245
|
|
},
|
|
{
|
|
"entropy": 5.625464916229248,
|
|
"epoch": 1.9373841747627338,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004632176274144056,
|
|
"loss": 5.3527,
|
|
"mean_token_accuracy": 0.18187369257211686,
|
|
"num_tokens": 38515536.0,
|
|
"step": 17250
|
|
},
|
|
{
|
|
"entropy": 5.529721355438232,
|
|
"epoch": 1.9379457516706913,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.00046319562564474083,
|
|
"loss": 5.3186,
|
|
"mean_token_accuracy": 0.19153500944375992,
|
|
"num_tokens": 38525579.0,
|
|
"step": 17255
|
|
},
|
|
{
|
|
"entropy": 5.624566459655762,
|
|
"epoch": 1.9385073285786487,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00046317361788285436,
|
|
"loss": 5.4925,
|
|
"mean_token_accuracy": 0.185320383310318,
|
|
"num_tokens": 38536963.0,
|
|
"step": 17260
|
|
},
|
|
{
|
|
"entropy": 5.534394025802612,
|
|
"epoch": 1.9390689054866064,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004631516041294469,
|
|
"loss": 5.3881,
|
|
"mean_token_accuracy": 0.18485718071460724,
|
|
"num_tokens": 38547497.0,
|
|
"step": 17265
|
|
},
|
|
{
|
|
"entropy": 5.5887068748474125,
|
|
"epoch": 1.939630482394564,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004631295843852194,
|
|
"loss": 5.2752,
|
|
"mean_token_accuracy": 0.1898737668991089,
|
|
"num_tokens": 38558840.0,
|
|
"step": 17270
|
|
},
|
|
{
|
|
"entropy": 5.5194587230682375,
|
|
"epoch": 1.9401920593025215,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.000463107558650873,
|
|
"loss": 5.2474,
|
|
"mean_token_accuracy": 0.19837641566991807,
|
|
"num_tokens": 38568670.0,
|
|
"step": 17275
|
|
},
|
|
{
|
|
"entropy": 5.5173698425292965,
|
|
"epoch": 1.940753636210479,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00046308552692710895,
|
|
"loss": 5.3187,
|
|
"mean_token_accuracy": 0.19002542942762374,
|
|
"num_tokens": 38578565.0,
|
|
"step": 17280
|
|
},
|
|
{
|
|
"entropy": 5.474986362457275,
|
|
"epoch": 1.9413152131184366,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00046306348921462876,
|
|
"loss": 5.288,
|
|
"mean_token_accuracy": 0.1900528132915497,
|
|
"num_tokens": 38589126.0,
|
|
"step": 17285
|
|
},
|
|
{
|
|
"entropy": 5.606071805953979,
|
|
"epoch": 1.9418767900263942,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004630414455141342,
|
|
"loss": 5.4005,
|
|
"mean_token_accuracy": 0.18429171591997145,
|
|
"num_tokens": 38601008.0,
|
|
"step": 17290
|
|
},
|
|
{
|
|
"entropy": 5.630123853683472,
|
|
"epoch": 1.9424383669343517,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.000463019395826327,
|
|
"loss": 5.3852,
|
|
"mean_token_accuracy": 0.18718257397413254,
|
|
"num_tokens": 38611756.0,
|
|
"step": 17295
|
|
},
|
|
{
|
|
"entropy": 5.587280988693237,
|
|
"epoch": 1.9429999438423091,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00046299734015190934,
|
|
"loss": 5.2927,
|
|
"mean_token_accuracy": 0.18605223894119263,
|
|
"num_tokens": 38623156.0,
|
|
"step": 17300
|
|
},
|
|
{
|
|
"entropy": 5.6102910995483395,
|
|
"epoch": 1.9435615207502668,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.00046297527849158344,
|
|
"loss": 5.3622,
|
|
"mean_token_accuracy": 0.19393292516469957,
|
|
"num_tokens": 38633920.0,
|
|
"step": 17305
|
|
},
|
|
{
|
|
"entropy": 5.530622434616089,
|
|
"epoch": 1.9441230976582244,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004629532108460519,
|
|
"loss": 5.28,
|
|
"mean_token_accuracy": 0.18657930195331573,
|
|
"num_tokens": 38644744.0,
|
|
"step": 17310
|
|
},
|
|
{
|
|
"entropy": 5.489866828918457,
|
|
"epoch": 1.9446846745661819,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00046293113721601706,
|
|
"loss": 5.2804,
|
|
"mean_token_accuracy": 0.19437275379896163,
|
|
"num_tokens": 38656524.0,
|
|
"step": 17315
|
|
},
|
|
{
|
|
"entropy": 5.491071319580078,
|
|
"epoch": 1.9452462514741393,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00046290905760218193,
|
|
"loss": 5.3309,
|
|
"mean_token_accuracy": 0.19527771025896073,
|
|
"num_tokens": 38668386.0,
|
|
"step": 17320
|
|
},
|
|
{
|
|
"entropy": 5.539380073547363,
|
|
"epoch": 1.945807828382097,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00046288697200524964,
|
|
"loss": 5.2443,
|
|
"mean_token_accuracy": 0.18934347331523896,
|
|
"num_tokens": 38678498.0,
|
|
"step": 17325
|
|
},
|
|
{
|
|
"entropy": 5.673765754699707,
|
|
"epoch": 1.9463694052900544,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00046286488042592325,
|
|
"loss": 5.4794,
|
|
"mean_token_accuracy": 0.17748477309942245,
|
|
"num_tokens": 38690084.0,
|
|
"step": 17330
|
|
},
|
|
{
|
|
"entropy": 5.50318169593811,
|
|
"epoch": 1.9469309821980119,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004628427828649062,
|
|
"loss": 5.3193,
|
|
"mean_token_accuracy": 0.18965124636888503,
|
|
"num_tokens": 38701282.0,
|
|
"step": 17335
|
|
},
|
|
{
|
|
"entropy": 5.447755956649781,
|
|
"epoch": 1.9474925591059695,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00046282067932290204,
|
|
"loss": 5.2044,
|
|
"mean_token_accuracy": 0.19539620876312255,
|
|
"num_tokens": 38713012.0,
|
|
"step": 17340
|
|
},
|
|
{
|
|
"entropy": 5.437713670730591,
|
|
"epoch": 1.9480541360139272,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004627985698006146,
|
|
"loss": 5.2604,
|
|
"mean_token_accuracy": 0.19580089300870895,
|
|
"num_tokens": 38723179.0,
|
|
"step": 17345
|
|
},
|
|
{
|
|
"entropy": 5.55149245262146,
|
|
"epoch": 1.9486157129218846,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.000462776454298748,
|
|
"loss": 5.2899,
|
|
"mean_token_accuracy": 0.1989804908633232,
|
|
"num_tokens": 38733729.0,
|
|
"step": 17350
|
|
},
|
|
{
|
|
"entropy": 5.560542345046997,
|
|
"epoch": 1.949177289829842,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.00046275433281800613,
|
|
"loss": 5.2477,
|
|
"mean_token_accuracy": 0.19693769216537477,
|
|
"num_tokens": 38743139.0,
|
|
"step": 17355
|
|
},
|
|
{
|
|
"entropy": 5.517525005340576,
|
|
"epoch": 1.9497388667377997,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004627322053590935,
|
|
"loss": 5.3276,
|
|
"mean_token_accuracy": 0.18538037538528443,
|
|
"num_tokens": 38754697.0,
|
|
"step": 17360
|
|
},
|
|
{
|
|
"entropy": 5.4607631206512455,
|
|
"epoch": 1.9503004436457574,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004627100719227147,
|
|
"loss": 5.3546,
|
|
"mean_token_accuracy": 0.1893941804766655,
|
|
"num_tokens": 38765999.0,
|
|
"step": 17365
|
|
},
|
|
{
|
|
"entropy": 5.526936388015747,
|
|
"epoch": 1.9508620205537148,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00046268793250957437,
|
|
"loss": 5.3623,
|
|
"mean_token_accuracy": 0.18579252511262895,
|
|
"num_tokens": 38776912.0,
|
|
"step": 17370
|
|
},
|
|
{
|
|
"entropy": 5.6296142578125,
|
|
"epoch": 1.9514235974616723,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00046266578712037747,
|
|
"loss": 5.3569,
|
|
"mean_token_accuracy": 0.18661235719919206,
|
|
"num_tokens": 38787296.0,
|
|
"step": 17375
|
|
},
|
|
{
|
|
"entropy": 5.546997785568237,
|
|
"epoch": 1.95198517436963,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00046264363575582916,
|
|
"loss": 5.3471,
|
|
"mean_token_accuracy": 0.18177139461040498,
|
|
"num_tokens": 38798013.0,
|
|
"step": 17380
|
|
},
|
|
{
|
|
"entropy": 5.458870315551758,
|
|
"epoch": 1.9525467512775876,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004626214784166347,
|
|
"loss": 5.2857,
|
|
"mean_token_accuracy": 0.1914055496454239,
|
|
"num_tokens": 38808842.0,
|
|
"step": 17385
|
|
},
|
|
{
|
|
"entropy": 5.490812921524048,
|
|
"epoch": 1.953108328185545,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004625993151034995,
|
|
"loss": 5.23,
|
|
"mean_token_accuracy": 0.19331282377243042,
|
|
"num_tokens": 38819094.0,
|
|
"step": 17390
|
|
},
|
|
{
|
|
"entropy": 5.512252330780029,
|
|
"epoch": 1.9536699050935025,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004625771458171294,
|
|
"loss": 5.3282,
|
|
"mean_token_accuracy": 0.1918247625231743,
|
|
"num_tokens": 38830348.0,
|
|
"step": 17395
|
|
},
|
|
{
|
|
"entropy": 5.566256141662597,
|
|
"epoch": 1.9542314820014601,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.00046255497055823025,
|
|
"loss": 5.3399,
|
|
"mean_token_accuracy": 0.1917381003499031,
|
|
"num_tokens": 38841927.0,
|
|
"step": 17400
|
|
},
|
|
{
|
|
"entropy": 5.427985715866089,
|
|
"epoch": 1.9547930589094178,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004625327893275082,
|
|
"loss": 5.1462,
|
|
"mean_token_accuracy": 0.19760164022445678,
|
|
"num_tokens": 38852817.0,
|
|
"step": 17405
|
|
},
|
|
{
|
|
"entropy": 5.3728128433227536,
|
|
"epoch": 1.9553546358173752,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.00046251060212566927,
|
|
"loss": 5.2575,
|
|
"mean_token_accuracy": 0.1909310519695282,
|
|
"num_tokens": 38864181.0,
|
|
"step": 17410
|
|
},
|
|
{
|
|
"entropy": 5.542944860458374,
|
|
"epoch": 1.9559162127253327,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004624884089534201,
|
|
"loss": 5.3244,
|
|
"mean_token_accuracy": 0.19081388413906097,
|
|
"num_tokens": 38873827.0,
|
|
"step": 17415
|
|
},
|
|
{
|
|
"entropy": 5.567887163162231,
|
|
"epoch": 1.9564777896332903,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004624662098114672,
|
|
"loss": 5.3318,
|
|
"mean_token_accuracy": 0.18709559440612794,
|
|
"num_tokens": 38884540.0,
|
|
"step": 17420
|
|
},
|
|
{
|
|
"entropy": 5.431196308135986,
|
|
"epoch": 1.9570393665412478,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00046244400470051754,
|
|
"loss": 5.1872,
|
|
"mean_token_accuracy": 0.1930992603302002,
|
|
"num_tokens": 38895600.0,
|
|
"step": 17425
|
|
},
|
|
{
|
|
"entropy": 5.472609519958496,
|
|
"epoch": 1.9576009434492052,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.000462421793621278,
|
|
"loss": 5.2644,
|
|
"mean_token_accuracy": 0.1968981981277466,
|
|
"num_tokens": 38906166.0,
|
|
"step": 17430
|
|
},
|
|
{
|
|
"entropy": 5.4246618270874025,
|
|
"epoch": 1.9581625203571629,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.000462399576574456,
|
|
"loss": 5.1718,
|
|
"mean_token_accuracy": 0.19477488696575165,
|
|
"num_tokens": 38916247.0,
|
|
"step": 17435
|
|
},
|
|
{
|
|
"entropy": 5.590512895584107,
|
|
"epoch": 1.9587240972651205,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004623773535607587,
|
|
"loss": 5.3942,
|
|
"mean_token_accuracy": 0.18519411832094193,
|
|
"num_tokens": 38928276.0,
|
|
"step": 17440
|
|
},
|
|
{
|
|
"entropy": 5.571941566467285,
|
|
"epoch": 1.959285674173078,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004623551245808938,
|
|
"loss": 5.2973,
|
|
"mean_token_accuracy": 0.1899605467915535,
|
|
"num_tokens": 38939460.0,
|
|
"step": 17445
|
|
},
|
|
{
|
|
"entropy": 5.4758216381073,
|
|
"epoch": 1.9598472510810354,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.0004623328896355691,
|
|
"loss": 5.2473,
|
|
"mean_token_accuracy": 0.19702684879302979,
|
|
"num_tokens": 38950381.0,
|
|
"step": 17450
|
|
},
|
|
{
|
|
"entropy": 5.425159168243408,
|
|
"epoch": 1.960408827988993,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.00046231064872549244,
|
|
"loss": 5.2431,
|
|
"mean_token_accuracy": 0.19221047610044478,
|
|
"num_tokens": 38961312.0,
|
|
"step": 17455
|
|
},
|
|
{
|
|
"entropy": 5.555955028533935,
|
|
"epoch": 1.9609704048969507,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.00046228840185137215,
|
|
"loss": 5.3428,
|
|
"mean_token_accuracy": 0.18744023889303207,
|
|
"num_tokens": 38974030.0,
|
|
"step": 17460
|
|
},
|
|
{
|
|
"entropy": 5.639015769958496,
|
|
"epoch": 1.9615319818049082,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.0004622661490139165,
|
|
"loss": 5.3969,
|
|
"mean_token_accuracy": 0.18619923293590546,
|
|
"num_tokens": 38984640.0,
|
|
"step": 17465
|
|
},
|
|
{
|
|
"entropy": 5.480964279174804,
|
|
"epoch": 1.9620935587128656,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004622438902138341,
|
|
"loss": 5.2907,
|
|
"mean_token_accuracy": 0.18884125500917434,
|
|
"num_tokens": 38996206.0,
|
|
"step": 17470
|
|
},
|
|
{
|
|
"entropy": 5.4575084209442135,
|
|
"epoch": 1.9626551356208233,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00046222162545183357,
|
|
"loss": 5.2196,
|
|
"mean_token_accuracy": 0.2025580108165741,
|
|
"num_tokens": 39007765.0,
|
|
"step": 17475
|
|
},
|
|
{
|
|
"entropy": 5.498712062835693,
|
|
"epoch": 1.963216712528781,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00046219935472862386,
|
|
"loss": 5.336,
|
|
"mean_token_accuracy": 0.18791389167308808,
|
|
"num_tokens": 39020691.0,
|
|
"step": 17480
|
|
},
|
|
{
|
|
"entropy": 5.477165222167969,
|
|
"epoch": 1.9637782894367384,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00046217707804491404,
|
|
"loss": 5.2596,
|
|
"mean_token_accuracy": 0.19700903445482254,
|
|
"num_tokens": 39032003.0,
|
|
"step": 17485
|
|
},
|
|
{
|
|
"entropy": 5.587220335006714,
|
|
"epoch": 1.9643398663446958,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004621547954014135,
|
|
"loss": 5.3542,
|
|
"mean_token_accuracy": 0.1912691980600357,
|
|
"num_tokens": 39042783.0,
|
|
"step": 17490
|
|
},
|
|
{
|
|
"entropy": 5.501882886886596,
|
|
"epoch": 1.9649014432526535,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004621325067988317,
|
|
"loss": 5.2566,
|
|
"mean_token_accuracy": 0.19201208055019378,
|
|
"num_tokens": 39054395.0,
|
|
"step": 17495
|
|
},
|
|
{
|
|
"entropy": 5.465988636016846,
|
|
"epoch": 1.9654630201606111,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.00046211021223787827,
|
|
"loss": 5.2412,
|
|
"mean_token_accuracy": 0.19983402639627457,
|
|
"num_tokens": 39064619.0,
|
|
"step": 17500
|
|
},
|
|
{
|
|
"entropy": 5.610533666610718,
|
|
"epoch": 1.9660245970685686,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00046208791171926315,
|
|
"loss": 5.3812,
|
|
"mean_token_accuracy": 0.18333709388971328,
|
|
"num_tokens": 39076112.0,
|
|
"step": 17505
|
|
},
|
|
{
|
|
"entropy": 5.487556791305542,
|
|
"epoch": 1.966586173976526,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00046206560524369636,
|
|
"loss": 5.277,
|
|
"mean_token_accuracy": 0.19122491031885147,
|
|
"num_tokens": 39087669.0,
|
|
"step": 17510
|
|
},
|
|
{
|
|
"entropy": 5.493722581863404,
|
|
"epoch": 1.9671477508844837,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.00046204329281188816,
|
|
"loss": 5.2796,
|
|
"mean_token_accuracy": 0.19010273963212967,
|
|
"num_tokens": 39098506.0,
|
|
"step": 17515
|
|
},
|
|
{
|
|
"entropy": 5.525453519821167,
|
|
"epoch": 1.9677093277924411,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004620209744245489,
|
|
"loss": 5.3252,
|
|
"mean_token_accuracy": 0.19333317130804062,
|
|
"num_tokens": 39109441.0,
|
|
"step": 17520
|
|
},
|
|
{
|
|
"entropy": 5.5208498477935795,
|
|
"epoch": 1.9682709047003986,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00046199865008238937,
|
|
"loss": 5.2342,
|
|
"mean_token_accuracy": 0.19754558205604553,
|
|
"num_tokens": 39119765.0,
|
|
"step": 17525
|
|
},
|
|
{
|
|
"entropy": 5.461196804046631,
|
|
"epoch": 1.9688324816083562,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004619763197861203,
|
|
"loss": 5.2053,
|
|
"mean_token_accuracy": 0.1979791358113289,
|
|
"num_tokens": 39129794.0,
|
|
"step": 17530
|
|
},
|
|
{
|
|
"entropy": 5.445248079299927,
|
|
"epoch": 1.9693940585163139,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00046195398353645256,
|
|
"loss": 5.2251,
|
|
"mean_token_accuracy": 0.1986946478486061,
|
|
"num_tokens": 39140095.0,
|
|
"step": 17535
|
|
},
|
|
{
|
|
"entropy": 5.523592758178711,
|
|
"epoch": 1.9699556354242713,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004619316413340976,
|
|
"loss": 5.3281,
|
|
"mean_token_accuracy": 0.19205934107303618,
|
|
"num_tokens": 39150855.0,
|
|
"step": 17540
|
|
},
|
|
{
|
|
"entropy": 5.537033891677856,
|
|
"epoch": 1.9705172123322288,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00046190929317976664,
|
|
"loss": 5.2485,
|
|
"mean_token_accuracy": 0.19780316054821015,
|
|
"num_tokens": 39161455.0,
|
|
"step": 17545
|
|
},
|
|
{
|
|
"entropy": 5.557616186141968,
|
|
"epoch": 1.9710787892401864,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004618869390741713,
|
|
"loss": 5.452,
|
|
"mean_token_accuracy": 0.1836066022515297,
|
|
"num_tokens": 39173199.0,
|
|
"step": 17550
|
|
},
|
|
{
|
|
"entropy": 5.576978015899658,
|
|
"epoch": 1.971640366148144,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004618645790180233,
|
|
"loss": 5.3265,
|
|
"mean_token_accuracy": 0.1939622327685356,
|
|
"num_tokens": 39183145.0,
|
|
"step": 17555
|
|
},
|
|
{
|
|
"entropy": 5.551261377334595,
|
|
"epoch": 1.9722019430561015,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004618422130120347,
|
|
"loss": 5.3381,
|
|
"mean_token_accuracy": 0.1918054074048996,
|
|
"num_tokens": 39194900.0,
|
|
"step": 17560
|
|
},
|
|
{
|
|
"entropy": 5.606948375701904,
|
|
"epoch": 1.972763519964059,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004618198410569175,
|
|
"loss": 5.4062,
|
|
"mean_token_accuracy": 0.1801542103290558,
|
|
"num_tokens": 39206651.0,
|
|
"step": 17565
|
|
},
|
|
{
|
|
"entropy": 5.48220682144165,
|
|
"epoch": 1.9733250968720166,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.00046179746315338414,
|
|
"loss": 5.3049,
|
|
"mean_token_accuracy": 0.19232531934976577,
|
|
"num_tokens": 39217635.0,
|
|
"step": 17570
|
|
},
|
|
{
|
|
"entropy": 5.553248882293701,
|
|
"epoch": 1.9738866737799743,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.00046177507930214714,
|
|
"loss": 5.32,
|
|
"mean_token_accuracy": 0.1951992079615593,
|
|
"num_tokens": 39227937.0,
|
|
"step": 17575
|
|
},
|
|
{
|
|
"entropy": 5.525927400588989,
|
|
"epoch": 1.9744482506879317,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004617526895039191,
|
|
"loss": 5.3167,
|
|
"mean_token_accuracy": 0.19994789361953735,
|
|
"num_tokens": 39238776.0,
|
|
"step": 17580
|
|
},
|
|
{
|
|
"entropy": 5.517746210098267,
|
|
"epoch": 1.9750098275958892,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.00046173029375941305,
|
|
"loss": 5.3422,
|
|
"mean_token_accuracy": 0.1904160737991333,
|
|
"num_tokens": 39250043.0,
|
|
"step": 17585
|
|
},
|
|
{
|
|
"entropy": 5.452392292022705,
|
|
"epoch": 1.9755714045038468,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.000461707892069342,
|
|
"loss": 5.2713,
|
|
"mean_token_accuracy": 0.19367802739143372,
|
|
"num_tokens": 39261440.0,
|
|
"step": 17590
|
|
},
|
|
{
|
|
"entropy": 5.573949670791626,
|
|
"epoch": 1.9761329814118045,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.00046168548443441926,
|
|
"loss": 5.4926,
|
|
"mean_token_accuracy": 0.1838779166340828,
|
|
"num_tokens": 39272151.0,
|
|
"step": 17595
|
|
},
|
|
{
|
|
"entropy": 5.716833066940308,
|
|
"epoch": 1.976694558319762,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004616630708553583,
|
|
"loss": 5.4842,
|
|
"mean_token_accuracy": 0.17978556901216508,
|
|
"num_tokens": 39284794.0,
|
|
"step": 17600
|
|
},
|
|
{
|
|
"entropy": 5.511546230316162,
|
|
"epoch": 1.9772561352277194,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.00046164065133287276,
|
|
"loss": 5.3741,
|
|
"mean_token_accuracy": 0.18695790320634842,
|
|
"num_tokens": 39296660.0,
|
|
"step": 17605
|
|
},
|
|
{
|
|
"entropy": 5.5483684062957765,
|
|
"epoch": 1.977817712135677,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004616182258676765,
|
|
"loss": 5.4013,
|
|
"mean_token_accuracy": 0.18527230769395828,
|
|
"num_tokens": 39308609.0,
|
|
"step": 17610
|
|
},
|
|
{
|
|
"entropy": 5.561050224304199,
|
|
"epoch": 1.9783792890436345,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004615957944604835,
|
|
"loss": 5.2039,
|
|
"mean_token_accuracy": 0.1979954198002815,
|
|
"num_tokens": 39319295.0,
|
|
"step": 17615
|
|
},
|
|
{
|
|
"entropy": 5.566237926483154,
|
|
"epoch": 1.978940865951592,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004615733571120081,
|
|
"loss": 5.3266,
|
|
"mean_token_accuracy": 0.19095246493816376,
|
|
"num_tokens": 39330874.0,
|
|
"step": 17620
|
|
},
|
|
{
|
|
"entropy": 5.475045394897461,
|
|
"epoch": 1.9795024428595496,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004615509138229646,
|
|
"loss": 5.3228,
|
|
"mean_token_accuracy": 0.18548815399408342,
|
|
"num_tokens": 39343574.0,
|
|
"step": 17625
|
|
},
|
|
{
|
|
"entropy": 5.5390052318573,
|
|
"epoch": 1.9800640197675072,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00046152846459406765,
|
|
"loss": 5.3286,
|
|
"mean_token_accuracy": 0.18938498497009276,
|
|
"num_tokens": 39355761.0,
|
|
"step": 17630
|
|
},
|
|
{
|
|
"entropy": 5.59404616355896,
|
|
"epoch": 1.9806255966754647,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004615060094260321,
|
|
"loss": 5.46,
|
|
"mean_token_accuracy": 0.17910851389169694,
|
|
"num_tokens": 39368116.0,
|
|
"step": 17635
|
|
},
|
|
{
|
|
"entropy": 5.5500890731811525,
|
|
"epoch": 1.9811871735834221,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.00046148354831957285,
|
|
"loss": 5.3128,
|
|
"mean_token_accuracy": 0.2022144928574562,
|
|
"num_tokens": 39378619.0,
|
|
"step": 17640
|
|
},
|
|
{
|
|
"entropy": 5.644384860992432,
|
|
"epoch": 1.9817487504913798,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00046146108127540506,
|
|
"loss": 5.4388,
|
|
"mean_token_accuracy": 0.1837463304400444,
|
|
"num_tokens": 39391595.0,
|
|
"step": 17645
|
|
},
|
|
{
|
|
"entropy": 5.555820560455322,
|
|
"epoch": 1.9823103273993374,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004614386082942442,
|
|
"loss": 5.392,
|
|
"mean_token_accuracy": 0.18424100875854493,
|
|
"num_tokens": 39402494.0,
|
|
"step": 17650
|
|
},
|
|
{
|
|
"entropy": 5.5125528335571286,
|
|
"epoch": 1.9828719043072949,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004614161293768057,
|
|
"loss": 5.3069,
|
|
"mean_token_accuracy": 0.18762837648391723,
|
|
"num_tokens": 39413371.0,
|
|
"step": 17655
|
|
},
|
|
{
|
|
"entropy": 5.4820473194122314,
|
|
"epoch": 1.9834334812152523,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00046139364452380536,
|
|
"loss": 5.3068,
|
|
"mean_token_accuracy": 0.18936399519443511,
|
|
"num_tokens": 39424170.0,
|
|
"step": 17660
|
|
},
|
|
{
|
|
"entropy": 5.6062427997589115,
|
|
"epoch": 1.98399505812321,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.000461371153735959,
|
|
"loss": 5.3933,
|
|
"mean_token_accuracy": 0.18909017294645308,
|
|
"num_tokens": 39434438.0,
|
|
"step": 17665
|
|
},
|
|
{
|
|
"entropy": 5.569085121154785,
|
|
"epoch": 1.9845566350311676,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00046134865701398287,
|
|
"loss": 5.3152,
|
|
"mean_token_accuracy": 0.1891639858484268,
|
|
"num_tokens": 39445116.0,
|
|
"step": 17670
|
|
},
|
|
{
|
|
"entropy": 5.559984445571899,
|
|
"epoch": 1.985118211939125,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00046132615435859326,
|
|
"loss": 5.3,
|
|
"mean_token_accuracy": 0.1926518663764,
|
|
"num_tokens": 39457296.0,
|
|
"step": 17675
|
|
},
|
|
{
|
|
"entropy": 5.575274229049683,
|
|
"epoch": 1.9856797888470825,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.00046130364577050655,
|
|
"loss": 5.3801,
|
|
"mean_token_accuracy": 0.19589262902736665,
|
|
"num_tokens": 39468499.0,
|
|
"step": 17680
|
|
},
|
|
{
|
|
"entropy": 5.4970090866088865,
|
|
"epoch": 1.9862413657550402,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.00046128113125043957,
|
|
"loss": 5.2647,
|
|
"mean_token_accuracy": 0.19170113205909728,
|
|
"num_tokens": 39479594.0,
|
|
"step": 17685
|
|
},
|
|
{
|
|
"entropy": 5.50139741897583,
|
|
"epoch": 1.9868029426629978,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00046125861079910913,
|
|
"loss": 5.3264,
|
|
"mean_token_accuracy": 0.19295964688062667,
|
|
"num_tokens": 39490048.0,
|
|
"step": 17690
|
|
},
|
|
{
|
|
"entropy": 5.533599758148194,
|
|
"epoch": 1.9873645195709553,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004612360844172322,
|
|
"loss": 5.3194,
|
|
"mean_token_accuracy": 0.18845418840646744,
|
|
"num_tokens": 39501454.0,
|
|
"step": 17695
|
|
},
|
|
{
|
|
"entropy": 5.5037353515625,
|
|
"epoch": 1.9879260964789127,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00046121355210552626,
|
|
"loss": 5.2705,
|
|
"mean_token_accuracy": 0.20236016660928727,
|
|
"num_tokens": 39512782.0,
|
|
"step": 17700
|
|
},
|
|
{
|
|
"entropy": 5.522071170806885,
|
|
"epoch": 1.9884876733868704,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004611910138647085,
|
|
"loss": 5.3381,
|
|
"mean_token_accuracy": 0.19241473227739334,
|
|
"num_tokens": 39524342.0,
|
|
"step": 17705
|
|
},
|
|
{
|
|
"entropy": 5.498077297210694,
|
|
"epoch": 1.989049250294828,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00046116846969549666,
|
|
"loss": 5.2337,
|
|
"mean_token_accuracy": 0.19326062351465226,
|
|
"num_tokens": 39534744.0,
|
|
"step": 17710
|
|
},
|
|
{
|
|
"entropy": 5.5863272190094,
|
|
"epoch": 1.9896108272027853,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004611459195986085,
|
|
"loss": 5.3922,
|
|
"mean_token_accuracy": 0.1856262743473053,
|
|
"num_tokens": 39547729.0,
|
|
"step": 17715
|
|
},
|
|
{
|
|
"entropy": 5.544296026229858,
|
|
"epoch": 1.990172404110743,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.00046112336357476217,
|
|
"loss": 5.2421,
|
|
"mean_token_accuracy": 0.1931598663330078,
|
|
"num_tokens": 39558194.0,
|
|
"step": 17720
|
|
},
|
|
{
|
|
"entropy": 5.458015441894531,
|
|
"epoch": 1.9907339810187006,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004611008016246757,
|
|
"loss": 5.1788,
|
|
"mean_token_accuracy": 0.19584223181009291,
|
|
"num_tokens": 39568265.0,
|
|
"step": 17725
|
|
},
|
|
{
|
|
"entropy": 5.533123588562011,
|
|
"epoch": 1.991295557926658,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.00046107823374906754,
|
|
"loss": 5.4039,
|
|
"mean_token_accuracy": 0.18655110001564026,
|
|
"num_tokens": 39578936.0,
|
|
"step": 17730
|
|
},
|
|
{
|
|
"entropy": 5.576171779632569,
|
|
"epoch": 1.9918571348346155,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.00046105565994865614,
|
|
"loss": 5.3929,
|
|
"mean_token_accuracy": 0.18787167370319366,
|
|
"num_tokens": 39590180.0,
|
|
"step": 17735
|
|
},
|
|
{
|
|
"entropy": 5.543496084213257,
|
|
"epoch": 1.9924187117425731,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004610330802241605,
|
|
"loss": 5.3289,
|
|
"mean_token_accuracy": 0.1881959080696106,
|
|
"num_tokens": 39601226.0,
|
|
"step": 17740
|
|
},
|
|
{
|
|
"entropy": 5.500477027893067,
|
|
"epoch": 1.9929802886505308,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004610104945762994,
|
|
"loss": 5.3614,
|
|
"mean_token_accuracy": 0.19314012080430984,
|
|
"num_tokens": 39613119.0,
|
|
"step": 17745
|
|
},
|
|
{
|
|
"entropy": 5.558902978897095,
|
|
"epoch": 1.9935418655584882,
|
|
"grad_norm": 2.53125,
|
|
"learning_rate": 0.000460987903005792,
|
|
"loss": 5.335,
|
|
"mean_token_accuracy": 0.19106521159410478,
|
|
"num_tokens": 39625269.0,
|
|
"step": 17750
|
|
},
|
|
{
|
|
"entropy": 5.540250253677368,
|
|
"epoch": 1.9941034424664457,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004609653055133576,
|
|
"loss": 5.2332,
|
|
"mean_token_accuracy": 0.1961716890335083,
|
|
"num_tokens": 39635883.0,
|
|
"step": 17755
|
|
},
|
|
{
|
|
"entropy": 5.466345310211182,
|
|
"epoch": 1.9946650193744033,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00046094270209971576,
|
|
"loss": 5.2585,
|
|
"mean_token_accuracy": 0.1985495701432228,
|
|
"num_tokens": 39646425.0,
|
|
"step": 17760
|
|
},
|
|
{
|
|
"entropy": 5.542253732681274,
|
|
"epoch": 1.995226596282361,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004609200927655862,
|
|
"loss": 5.3831,
|
|
"mean_token_accuracy": 0.1871304541826248,
|
|
"num_tokens": 39658874.0,
|
|
"step": 17765
|
|
},
|
|
{
|
|
"entropy": 5.542967891693115,
|
|
"epoch": 1.9957881731903184,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004608974775116888,
|
|
"loss": 5.3358,
|
|
"mean_token_accuracy": 0.1885174185037613,
|
|
"num_tokens": 39670401.0,
|
|
"step": 17770
|
|
},
|
|
{
|
|
"entropy": 5.4775111198425295,
|
|
"epoch": 1.9963497500982759,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004608748563387436,
|
|
"loss": 5.2638,
|
|
"mean_token_accuracy": 0.19434180855751038,
|
|
"num_tokens": 39681005.0,
|
|
"step": 17775
|
|
},
|
|
{
|
|
"entropy": 5.652531719207763,
|
|
"epoch": 1.9969113270062335,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004608522292474708,
|
|
"loss": 5.4188,
|
|
"mean_token_accuracy": 0.18446086794137956,
|
|
"num_tokens": 39692311.0,
|
|
"step": 17780
|
|
},
|
|
{
|
|
"entropy": 5.564651441574097,
|
|
"epoch": 1.9974729039141912,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004608295962385911,
|
|
"loss": 5.2163,
|
|
"mean_token_accuracy": 0.20410524904727936,
|
|
"num_tokens": 39702782.0,
|
|
"step": 17785
|
|
},
|
|
{
|
|
"entropy": 5.481700038909912,
|
|
"epoch": 1.9980344808221486,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.00046080695731282484,
|
|
"loss": 5.3719,
|
|
"mean_token_accuracy": 0.18634167909622193,
|
|
"num_tokens": 39713497.0,
|
|
"step": 17790
|
|
},
|
|
{
|
|
"entropy": 5.501364040374756,
|
|
"epoch": 1.998596057730106,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.000460784312470893,
|
|
"loss": 5.2912,
|
|
"mean_token_accuracy": 0.1885882779955864,
|
|
"num_tokens": 39724355.0,
|
|
"step": 17795
|
|
},
|
|
{
|
|
"entropy": 5.64681191444397,
|
|
"epoch": 1.9991576346380637,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.00046076166171351673,
|
|
"loss": 5.3714,
|
|
"mean_token_accuracy": 0.18769290298223495,
|
|
"num_tokens": 39736523.0,
|
|
"step": 17800
|
|
},
|
|
{
|
|
"entropy": 5.553428077697754,
|
|
"epoch": 1.9997192115460214,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000460739005041417,
|
|
"loss": 5.3153,
|
|
"mean_token_accuracy": 0.18943432122468948,
|
|
"num_tokens": 39746297.0,
|
|
"step": 17805
|
|
},
|
|
{
|
|
"entropy": 5.368327299753825,
|
|
"epoch": 2.000224630763183,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004607163424553153,
|
|
"loss": 5.1191,
|
|
"mean_token_accuracy": 0.20146067440509796,
|
|
"num_tokens": 39755163.0,
|
|
"step": 17810
|
|
},
|
|
{
|
|
"entropy": 5.5035772800445555,
|
|
"epoch": 2.0007862076711405,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.00046069367395593325,
|
|
"loss": 5.344,
|
|
"mean_token_accuracy": 0.1846245363354683,
|
|
"num_tokens": 39766444.0,
|
|
"step": 17815
|
|
},
|
|
{
|
|
"entropy": 5.594197034835815,
|
|
"epoch": 2.001347784579098,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004606709995439926,
|
|
"loss": 5.27,
|
|
"mean_token_accuracy": 0.19674184620380403,
|
|
"num_tokens": 39778051.0,
|
|
"step": 17820
|
|
},
|
|
{
|
|
"entropy": 5.56218900680542,
|
|
"epoch": 2.001909361487056,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00046064831922021534,
|
|
"loss": 5.2984,
|
|
"mean_token_accuracy": 0.18967250138521194,
|
|
"num_tokens": 39787850.0,
|
|
"step": 17825
|
|
},
|
|
{
|
|
"entropy": 5.579576730728149,
|
|
"epoch": 2.002470938395013,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004606256329853235,
|
|
"loss": 5.2277,
|
|
"mean_token_accuracy": 0.1949354574084282,
|
|
"num_tokens": 39799428.0,
|
|
"step": 17830
|
|
},
|
|
{
|
|
"entropy": 5.67228889465332,
|
|
"epoch": 2.0030325153029707,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004606029408400396,
|
|
"loss": 5.4265,
|
|
"mean_token_accuracy": 0.18604052811861038,
|
|
"num_tokens": 39811688.0,
|
|
"step": 17835
|
|
},
|
|
{
|
|
"entropy": 5.519627952575684,
|
|
"epoch": 2.0035940922109283,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004605802427850861,
|
|
"loss": 5.1929,
|
|
"mean_token_accuracy": 0.19501004368066788,
|
|
"num_tokens": 39822243.0,
|
|
"step": 17840
|
|
},
|
|
{
|
|
"entropy": 5.526254272460937,
|
|
"epoch": 2.004155669118886,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00046055753882118564,
|
|
"loss": 5.2935,
|
|
"mean_token_accuracy": 0.19255979508161544,
|
|
"num_tokens": 39833699.0,
|
|
"step": 17845
|
|
},
|
|
{
|
|
"entropy": 5.647405385971069,
|
|
"epoch": 2.004717246026843,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004605348289490611,
|
|
"loss": 5.4164,
|
|
"mean_token_accuracy": 0.18332097232341765,
|
|
"num_tokens": 39844177.0,
|
|
"step": 17850
|
|
},
|
|
{
|
|
"entropy": 5.5685715675354,
|
|
"epoch": 2.005278822934801,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004605121131694358,
|
|
"loss": 5.2962,
|
|
"mean_token_accuracy": 0.18893337696790696,
|
|
"num_tokens": 39856008.0,
|
|
"step": 17855
|
|
},
|
|
{
|
|
"entropy": 5.5060914039611815,
|
|
"epoch": 2.0058403998427585,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004604893914830328,
|
|
"loss": 5.186,
|
|
"mean_token_accuracy": 0.1934990867972374,
|
|
"num_tokens": 39866209.0,
|
|
"step": 17860
|
|
},
|
|
{
|
|
"entropy": 5.571491956710815,
|
|
"epoch": 2.006401976750716,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.00046046666389057563,
|
|
"loss": 5.2418,
|
|
"mean_token_accuracy": 0.19273425042629241,
|
|
"num_tokens": 39876986.0,
|
|
"step": 17865
|
|
},
|
|
{
|
|
"entropy": 5.462259197235108,
|
|
"epoch": 2.0069635536586734,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.000460443930392788,
|
|
"loss": 5.2117,
|
|
"mean_token_accuracy": 0.1915942072868347,
|
|
"num_tokens": 39886994.0,
|
|
"step": 17870
|
|
},
|
|
{
|
|
"entropy": 5.534856605529785,
|
|
"epoch": 2.007525130566631,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00046042119099039367,
|
|
"loss": 5.2735,
|
|
"mean_token_accuracy": 0.19172825962305068,
|
|
"num_tokens": 39897514.0,
|
|
"step": 17875
|
|
},
|
|
{
|
|
"entropy": 5.6715551853179935,
|
|
"epoch": 2.0080867074745887,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.00046039844568411667,
|
|
"loss": 5.4847,
|
|
"mean_token_accuracy": 0.18386076986789704,
|
|
"num_tokens": 39909102.0,
|
|
"step": 17880
|
|
},
|
|
{
|
|
"entropy": 5.58957953453064,
|
|
"epoch": 2.0086482843825464,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004603756944746813,
|
|
"loss": 5.1636,
|
|
"mean_token_accuracy": 0.20065847486257554,
|
|
"num_tokens": 39919450.0,
|
|
"step": 17885
|
|
},
|
|
{
|
|
"entropy": 5.45687198638916,
|
|
"epoch": 2.0092098612905036,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00046035293736281185,
|
|
"loss": 5.2136,
|
|
"mean_token_accuracy": 0.1846734568476677,
|
|
"num_tokens": 39930362.0,
|
|
"step": 17890
|
|
},
|
|
{
|
|
"entropy": 5.455288505554199,
|
|
"epoch": 2.0097714381984613,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004603301743492331,
|
|
"loss": 5.3014,
|
|
"mean_token_accuracy": 0.19423362314701081,
|
|
"num_tokens": 39942047.0,
|
|
"step": 17895
|
|
},
|
|
{
|
|
"entropy": 5.581796312332154,
|
|
"epoch": 2.010333015106419,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004603074054346696,
|
|
"loss": 5.2827,
|
|
"mean_token_accuracy": 0.192690934240818,
|
|
"num_tokens": 39954870.0,
|
|
"step": 17900
|
|
},
|
|
{
|
|
"entropy": 5.542372322082519,
|
|
"epoch": 2.0108945920143766,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004602846306198465,
|
|
"loss": 5.277,
|
|
"mean_token_accuracy": 0.1974707990884781,
|
|
"num_tokens": 39966345.0,
|
|
"step": 17905
|
|
},
|
|
{
|
|
"entropy": 5.446708822250367,
|
|
"epoch": 2.011456168922334,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004602618499054889,
|
|
"loss": 5.1439,
|
|
"mean_token_accuracy": 0.20305910855531692,
|
|
"num_tokens": 39976453.0,
|
|
"step": 17910
|
|
},
|
|
{
|
|
"entropy": 5.52267370223999,
|
|
"epoch": 2.0120177458302915,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004602390632923221,
|
|
"loss": 5.3192,
|
|
"mean_token_accuracy": 0.1889155015349388,
|
|
"num_tokens": 39988990.0,
|
|
"step": 17915
|
|
},
|
|
{
|
|
"entropy": 5.476548767089843,
|
|
"epoch": 2.012579322738249,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00046021627078107177,
|
|
"loss": 5.2649,
|
|
"mean_token_accuracy": 0.19363445937633514,
|
|
"num_tokens": 39999131.0,
|
|
"step": 17920
|
|
},
|
|
{
|
|
"entropy": 5.587501525878906,
|
|
"epoch": 2.0131408996462063,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00046019347237246343,
|
|
"loss": 5.2734,
|
|
"mean_token_accuracy": 0.1963441863656044,
|
|
"num_tokens": 40010197.0,
|
|
"step": 17925
|
|
},
|
|
{
|
|
"entropy": 5.512665128707885,
|
|
"epoch": 2.013702476554164,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004601706680672232,
|
|
"loss": 5.1319,
|
|
"mean_token_accuracy": 0.20290805995464326,
|
|
"num_tokens": 40021388.0,
|
|
"step": 17930
|
|
},
|
|
{
|
|
"entropy": 5.488842630386353,
|
|
"epoch": 2.0142640534621217,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004601478578660771,
|
|
"loss": 5.249,
|
|
"mean_token_accuracy": 0.19694442749023439,
|
|
"num_tokens": 40032485.0,
|
|
"step": 17935
|
|
},
|
|
{
|
|
"entropy": 5.497480344772339,
|
|
"epoch": 2.0148256303700793,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004601250417697513,
|
|
"loss": 5.3509,
|
|
"mean_token_accuracy": 0.18763996362686158,
|
|
"num_tokens": 40043465.0,
|
|
"step": 17940
|
|
},
|
|
{
|
|
"entropy": 5.541256999969482,
|
|
"epoch": 2.0153872072780366,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004601022197789724,
|
|
"loss": 5.2459,
|
|
"mean_token_accuracy": 0.20102934986352922,
|
|
"num_tokens": 40054934.0,
|
|
"step": 17945
|
|
},
|
|
{
|
|
"entropy": 5.561784648895264,
|
|
"epoch": 2.015948784185994,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004600793918944671,
|
|
"loss": 5.3272,
|
|
"mean_token_accuracy": 0.193603977560997,
|
|
"num_tokens": 40066159.0,
|
|
"step": 17950
|
|
},
|
|
{
|
|
"entropy": 5.434869384765625,
|
|
"epoch": 2.016510361093952,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004600565581169621,
|
|
"loss": 5.1608,
|
|
"mean_token_accuracy": 0.2008107379078865,
|
|
"num_tokens": 40076169.0,
|
|
"step": 17955
|
|
},
|
|
{
|
|
"entropy": 5.544534301757812,
|
|
"epoch": 2.0170719380019095,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00046003371844718455,
|
|
"loss": 5.2355,
|
|
"mean_token_accuracy": 0.19955367594957352,
|
|
"num_tokens": 40086852.0,
|
|
"step": 17960
|
|
},
|
|
{
|
|
"entropy": 5.498943424224853,
|
|
"epoch": 2.0176335149098668,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00046001087288586164,
|
|
"loss": 5.2003,
|
|
"mean_token_accuracy": 0.19517784118652343,
|
|
"num_tokens": 40097588.0,
|
|
"step": 17965
|
|
},
|
|
{
|
|
"entropy": 5.5377825736999515,
|
|
"epoch": 2.0181950918178244,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004599880214337208,
|
|
"loss": 5.1569,
|
|
"mean_token_accuracy": 0.1989293575286865,
|
|
"num_tokens": 40108797.0,
|
|
"step": 17970
|
|
},
|
|
{
|
|
"entropy": 5.527046203613281,
|
|
"epoch": 2.018756668725782,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004599651640914896,
|
|
"loss": 5.3207,
|
|
"mean_token_accuracy": 0.18557970672845842,
|
|
"num_tokens": 40119700.0,
|
|
"step": 17975
|
|
},
|
|
{
|
|
"entropy": 5.520626354217529,
|
|
"epoch": 2.0193182456337397,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004599423008598957,
|
|
"loss": 5.3341,
|
|
"mean_token_accuracy": 0.18865351974964142,
|
|
"num_tokens": 40131611.0,
|
|
"step": 17980
|
|
},
|
|
{
|
|
"entropy": 5.5383241176605225,
|
|
"epoch": 2.019879822541697,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00045991943173966744,
|
|
"loss": 5.2092,
|
|
"mean_token_accuracy": 0.20510743260383607,
|
|
"num_tokens": 40142186.0,
|
|
"step": 17985
|
|
},
|
|
{
|
|
"entropy": 5.493134546279907,
|
|
"epoch": 2.0204413994496546,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004598965567315326,
|
|
"loss": 5.2485,
|
|
"mean_token_accuracy": 0.19158689975738524,
|
|
"num_tokens": 40153856.0,
|
|
"step": 17990
|
|
},
|
|
{
|
|
"entropy": 5.443471145629883,
|
|
"epoch": 2.0210029763576123,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004598736758362198,
|
|
"loss": 5.1661,
|
|
"mean_token_accuracy": 0.20336588323116303,
|
|
"num_tokens": 40164158.0,
|
|
"step": 17995
|
|
},
|
|
{
|
|
"entropy": 5.499774360656739,
|
|
"epoch": 2.02156455326557,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.00045985078905445734,
|
|
"loss": 5.317,
|
|
"mean_token_accuracy": 0.19301238358020784,
|
|
"num_tokens": 40176751.0,
|
|
"step": 18000
|
|
},
|
|
{
|
|
"epoch": 2.02156455326557,
|
|
"eval_entropy": 5.307580244365906,
|
|
"eval_loss": 5.397276878356934,
|
|
"eval_mean_token_accuracy": 0.1952238485528416,
|
|
"eval_num_tokens": 40176751.0,
|
|
"eval_runtime": 23.8922,
|
|
"eval_samples_per_second": 1298.038,
|
|
"eval_steps_per_second": 162.27,
|
|
"step": 18000
|
|
},
|
|
{
|
|
"entropy": 5.572664880752564,
|
|
"epoch": 2.022126130173527,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00045982789638697414,
|
|
"loss": 5.2942,
|
|
"mean_token_accuracy": 0.19219646900892257,
|
|
"num_tokens": 40188000.0,
|
|
"step": 18005
|
|
},
|
|
{
|
|
"entropy": 5.58684229850769,
|
|
"epoch": 2.022687707081485,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00045980499783449897,
|
|
"loss": 5.3019,
|
|
"mean_token_accuracy": 0.19214947074651717,
|
|
"num_tokens": 40199177.0,
|
|
"step": 18010
|
|
},
|
|
{
|
|
"entropy": 5.53514928817749,
|
|
"epoch": 2.0232492839894425,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.00045978209339776104,
|
|
"loss": 5.2818,
|
|
"mean_token_accuracy": 0.19240461587905883,
|
|
"num_tokens": 40210082.0,
|
|
"step": 18015
|
|
},
|
|
{
|
|
"entropy": 5.528062963485718,
|
|
"epoch": 2.0238108608973997,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00045975918307748965,
|
|
"loss": 5.2939,
|
|
"mean_token_accuracy": 0.18675119578838348,
|
|
"num_tokens": 40222503.0,
|
|
"step": 18020
|
|
},
|
|
{
|
|
"entropy": 5.530700254440307,
|
|
"epoch": 2.0243724378053574,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004597362668744141,
|
|
"loss": 5.2483,
|
|
"mean_token_accuracy": 0.194814969599247,
|
|
"num_tokens": 40233690.0,
|
|
"step": 18025
|
|
},
|
|
{
|
|
"entropy": 5.608551025390625,
|
|
"epoch": 2.024934014713315,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004597133447892642,
|
|
"loss": 5.3615,
|
|
"mean_token_accuracy": 0.18277624100446702,
|
|
"num_tokens": 40246274.0,
|
|
"step": 18030
|
|
},
|
|
{
|
|
"entropy": 5.566758012771606,
|
|
"epoch": 2.0254955916212727,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004596904168227698,
|
|
"loss": 5.2937,
|
|
"mean_token_accuracy": 0.1910557433962822,
|
|
"num_tokens": 40257469.0,
|
|
"step": 18035
|
|
},
|
|
{
|
|
"entropy": 5.496110296249389,
|
|
"epoch": 2.02605716852923,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00045966748297566085,
|
|
"loss": 5.2682,
|
|
"mean_token_accuracy": 0.19804832339286804,
|
|
"num_tokens": 40268982.0,
|
|
"step": 18040
|
|
},
|
|
{
|
|
"entropy": 5.5884966373443605,
|
|
"epoch": 2.0266187454371876,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00045964454324866767,
|
|
"loss": 5.321,
|
|
"mean_token_accuracy": 0.19124726802110673,
|
|
"num_tokens": 40280301.0,
|
|
"step": 18045
|
|
},
|
|
{
|
|
"entropy": 5.555725860595703,
|
|
"epoch": 2.0271803223451452,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.00045962159764252055,
|
|
"loss": 5.2283,
|
|
"mean_token_accuracy": 0.20217628479003907,
|
|
"num_tokens": 40292058.0,
|
|
"step": 18050
|
|
},
|
|
{
|
|
"entropy": 5.50323371887207,
|
|
"epoch": 2.027741899253103,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004595986461579502,
|
|
"loss": 5.278,
|
|
"mean_token_accuracy": 0.1922963097691536,
|
|
"num_tokens": 40301957.0,
|
|
"step": 18055
|
|
},
|
|
{
|
|
"entropy": 5.54264121055603,
|
|
"epoch": 2.02830347616106,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00045957568879568736,
|
|
"loss": 5.2499,
|
|
"mean_token_accuracy": 0.19339917600154877,
|
|
"num_tokens": 40313645.0,
|
|
"step": 18060
|
|
},
|
|
{
|
|
"entropy": 5.562793493270874,
|
|
"epoch": 2.0288650530690178,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.00045955272555646306,
|
|
"loss": 5.324,
|
|
"mean_token_accuracy": 0.18938728421926498,
|
|
"num_tokens": 40324416.0,
|
|
"step": 18065
|
|
},
|
|
{
|
|
"entropy": 5.667379379272461,
|
|
"epoch": 2.0294266299769754,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004595297564410083,
|
|
"loss": 5.4299,
|
|
"mean_token_accuracy": 0.1929930791258812,
|
|
"num_tokens": 40335596.0,
|
|
"step": 18070
|
|
},
|
|
{
|
|
"entropy": 5.568173885345459,
|
|
"epoch": 2.029988206884933,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.00045950678145005456,
|
|
"loss": 5.3745,
|
|
"mean_token_accuracy": 0.18585854768753052,
|
|
"num_tokens": 40346426.0,
|
|
"step": 18075
|
|
},
|
|
{
|
|
"entropy": 5.45464940071106,
|
|
"epoch": 2.0305497837928903,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004594838005843333,
|
|
"loss": 5.1245,
|
|
"mean_token_accuracy": 0.20244470238685608,
|
|
"num_tokens": 40357435.0,
|
|
"step": 18080
|
|
},
|
|
{
|
|
"entropy": 5.481536197662353,
|
|
"epoch": 2.031111360700848,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.00045946081384457633,
|
|
"loss": 5.2141,
|
|
"mean_token_accuracy": 0.19537506103515626,
|
|
"num_tokens": 40367332.0,
|
|
"step": 18085
|
|
},
|
|
{
|
|
"entropy": 5.492844438552856,
|
|
"epoch": 2.0316729376088056,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.00045943782123151556,
|
|
"loss": 5.202,
|
|
"mean_token_accuracy": 0.18720657825469972,
|
|
"num_tokens": 40378571.0,
|
|
"step": 18090
|
|
},
|
|
{
|
|
"entropy": 5.509575033187867,
|
|
"epoch": 2.0322345145167633,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 0.0004594148227458829,
|
|
"loss": 5.2389,
|
|
"mean_token_accuracy": 0.19426094591617585,
|
|
"num_tokens": 40389467.0,
|
|
"step": 18095
|
|
},
|
|
{
|
|
"entropy": 5.525057935714722,
|
|
"epoch": 2.0327960914247205,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004593918183884108,
|
|
"loss": 5.2614,
|
|
"mean_token_accuracy": 0.19487734884023666,
|
|
"num_tokens": 40399785.0,
|
|
"step": 18100
|
|
},
|
|
{
|
|
"entropy": 5.477648210525513,
|
|
"epoch": 2.033357668332678,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004593688081598318,
|
|
"loss": 5.2425,
|
|
"mean_token_accuracy": 0.19481801688671113,
|
|
"num_tokens": 40409862.0,
|
|
"step": 18105
|
|
},
|
|
{
|
|
"entropy": 5.519769477844238,
|
|
"epoch": 2.033919245240636,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00045934579206087837,
|
|
"loss": 5.3306,
|
|
"mean_token_accuracy": 0.18670503050088882,
|
|
"num_tokens": 40421627.0,
|
|
"step": 18110
|
|
},
|
|
{
|
|
"entropy": 5.57765679359436,
|
|
"epoch": 2.034480822148593,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00045932277009228336,
|
|
"loss": 5.3041,
|
|
"mean_token_accuracy": 0.1881491169333458,
|
|
"num_tokens": 40433327.0,
|
|
"step": 18115
|
|
},
|
|
{
|
|
"entropy": 5.469289350509643,
|
|
"epoch": 2.0350423990565507,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00045929974225477986,
|
|
"loss": 5.1752,
|
|
"mean_token_accuracy": 0.19770171791315078,
|
|
"num_tokens": 40444217.0,
|
|
"step": 18120
|
|
},
|
|
{
|
|
"entropy": 5.471521329879761,
|
|
"epoch": 2.0356039759645084,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00045927670854910117,
|
|
"loss": 5.2566,
|
|
"mean_token_accuracy": 0.196864578127861,
|
|
"num_tokens": 40454760.0,
|
|
"step": 18125
|
|
},
|
|
{
|
|
"entropy": 5.540667867660522,
|
|
"epoch": 2.036165552872466,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004592536689759806,
|
|
"loss": 5.2724,
|
|
"mean_token_accuracy": 0.1880270317196846,
|
|
"num_tokens": 40464638.0,
|
|
"step": 18130
|
|
},
|
|
{
|
|
"entropy": 5.55751748085022,
|
|
"epoch": 2.0367271297804233,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00045923062353615167,
|
|
"loss": 5.2412,
|
|
"mean_token_accuracy": 0.1920843541622162,
|
|
"num_tokens": 40474911.0,
|
|
"step": 18135
|
|
},
|
|
{
|
|
"entropy": 5.519346380233765,
|
|
"epoch": 2.037288706688381,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00045920757223034833,
|
|
"loss": 5.2607,
|
|
"mean_token_accuracy": 0.18908546715974808,
|
|
"num_tokens": 40485369.0,
|
|
"step": 18140
|
|
},
|
|
{
|
|
"entropy": 5.544115161895752,
|
|
"epoch": 2.0378502835963386,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004591845150593044,
|
|
"loss": 5.3029,
|
|
"mean_token_accuracy": 0.18528816252946853,
|
|
"num_tokens": 40495955.0,
|
|
"step": 18145
|
|
},
|
|
{
|
|
"entropy": 5.547362422943115,
|
|
"epoch": 2.0384118605042962,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.00045916145202375407,
|
|
"loss": 5.3241,
|
|
"mean_token_accuracy": 0.19307520538568496,
|
|
"num_tokens": 40506633.0,
|
|
"step": 18150
|
|
},
|
|
{
|
|
"entropy": 5.591632890701294,
|
|
"epoch": 2.0389734374122535,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004591383831244317,
|
|
"loss": 5.2975,
|
|
"mean_token_accuracy": 0.18528449535369873,
|
|
"num_tokens": 40516868.0,
|
|
"step": 18155
|
|
},
|
|
{
|
|
"entropy": 5.4388343334198,
|
|
"epoch": 2.039535014320211,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.00045911530836207173,
|
|
"loss": 5.1988,
|
|
"mean_token_accuracy": 0.1996513158082962,
|
|
"num_tokens": 40528873.0,
|
|
"step": 18160
|
|
},
|
|
{
|
|
"entropy": 5.533275032043457,
|
|
"epoch": 2.0400965912281688,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.00045909222773740904,
|
|
"loss": 5.2567,
|
|
"mean_token_accuracy": 0.18681711852550506,
|
|
"num_tokens": 40539124.0,
|
|
"step": 18165
|
|
},
|
|
{
|
|
"entropy": 5.480309343338012,
|
|
"epoch": 2.0406581681361264,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.00045906914125117833,
|
|
"loss": 5.2506,
|
|
"mean_token_accuracy": 0.1957709088921547,
|
|
"num_tokens": 40550264.0,
|
|
"step": 18170
|
|
},
|
|
{
|
|
"entropy": 5.414032602310181,
|
|
"epoch": 2.0412197450440837,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00045904604890411476,
|
|
"loss": 5.1305,
|
|
"mean_token_accuracy": 0.20195517539978028,
|
|
"num_tokens": 40562319.0,
|
|
"step": 18175
|
|
},
|
|
{
|
|
"entropy": 5.468103647232056,
|
|
"epoch": 2.0417813219520413,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.00045902295069695373,
|
|
"loss": 5.3122,
|
|
"mean_token_accuracy": 0.1947186753153801,
|
|
"num_tokens": 40573962.0,
|
|
"step": 18180
|
|
},
|
|
{
|
|
"entropy": 5.465974998474121,
|
|
"epoch": 2.042342898859999,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004589998466304305,
|
|
"loss": 5.1894,
|
|
"mean_token_accuracy": 0.19121768772602082,
|
|
"num_tokens": 40584620.0,
|
|
"step": 18185
|
|
},
|
|
{
|
|
"entropy": 5.559465408325195,
|
|
"epoch": 2.0429044757679566,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00045897673670528086,
|
|
"loss": 5.3399,
|
|
"mean_token_accuracy": 0.19162847250699996,
|
|
"num_tokens": 40596670.0,
|
|
"step": 18190
|
|
},
|
|
{
|
|
"entropy": 5.552762269973755,
|
|
"epoch": 2.043466052675914,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004589536209222404,
|
|
"loss": 5.2521,
|
|
"mean_token_accuracy": 0.19699085652828216,
|
|
"num_tokens": 40607742.0,
|
|
"step": 18195
|
|
},
|
|
{
|
|
"entropy": 5.483900547027588,
|
|
"epoch": 2.0440276295838715,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004589304992820454,
|
|
"loss": 5.1679,
|
|
"mean_token_accuracy": 0.20076052248477935,
|
|
"num_tokens": 40618873.0,
|
|
"step": 18200
|
|
},
|
|
{
|
|
"entropy": 5.487114143371582,
|
|
"epoch": 2.044589206491829,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.000458907371785432,
|
|
"loss": 5.2223,
|
|
"mean_token_accuracy": 0.19629937112331391,
|
|
"num_tokens": 40630327.0,
|
|
"step": 18205
|
|
},
|
|
{
|
|
"entropy": 5.441974925994873,
|
|
"epoch": 2.0451507833997864,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004588842384331366,
|
|
"loss": 5.2029,
|
|
"mean_token_accuracy": 0.19794509708881378,
|
|
"num_tokens": 40641515.0,
|
|
"step": 18210
|
|
},
|
|
{
|
|
"entropy": 5.5347236633300785,
|
|
"epoch": 2.045712360307744,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00045886109922589564,
|
|
"loss": 5.2387,
|
|
"mean_token_accuracy": 0.1935408443212509,
|
|
"num_tokens": 40652123.0,
|
|
"step": 18215
|
|
},
|
|
{
|
|
"entropy": 5.496812772750855,
|
|
"epoch": 2.0462739372157017,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00045883795416444594,
|
|
"loss": 5.2093,
|
|
"mean_token_accuracy": 0.19317083507776261,
|
|
"num_tokens": 40662895.0,
|
|
"step": 18220
|
|
},
|
|
{
|
|
"entropy": 5.437646150588989,
|
|
"epoch": 2.0468355141236594,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00045881480324952455,
|
|
"loss": 5.1526,
|
|
"mean_token_accuracy": 0.20172156244516373,
|
|
"num_tokens": 40673243.0,
|
|
"step": 18225
|
|
},
|
|
{
|
|
"entropy": 5.540271282196045,
|
|
"epoch": 2.0473970910316166,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00045879164648186853,
|
|
"loss": 5.2218,
|
|
"mean_token_accuracy": 0.20120328664779663,
|
|
"num_tokens": 40683861.0,
|
|
"step": 18230
|
|
},
|
|
{
|
|
"entropy": 5.514056062698364,
|
|
"epoch": 2.0479586679395743,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00045876848386221513,
|
|
"loss": 5.1805,
|
|
"mean_token_accuracy": 0.19275143146514892,
|
|
"num_tokens": 40694995.0,
|
|
"step": 18235
|
|
},
|
|
{
|
|
"entropy": 5.487927627563477,
|
|
"epoch": 2.048520244847532,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00045874531539130204,
|
|
"loss": 5.2497,
|
|
"mean_token_accuracy": 0.19804618507623672,
|
|
"num_tokens": 40705203.0,
|
|
"step": 18240
|
|
},
|
|
{
|
|
"entropy": 5.519061422348022,
|
|
"epoch": 2.0490818217554896,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.00045872214106986684,
|
|
"loss": 5.256,
|
|
"mean_token_accuracy": 0.19467736333608626,
|
|
"num_tokens": 40716439.0,
|
|
"step": 18245
|
|
},
|
|
{
|
|
"entropy": 5.4585394859313965,
|
|
"epoch": 2.049643398663447,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.00045869896089864733,
|
|
"loss": 5.214,
|
|
"mean_token_accuracy": 0.1964782804250717,
|
|
"num_tokens": 40727436.0,
|
|
"step": 18250
|
|
},
|
|
{
|
|
"entropy": 5.493454456329346,
|
|
"epoch": 2.0502049755714045,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004586757748783817,
|
|
"loss": 5.1926,
|
|
"mean_token_accuracy": 0.20115760266780852,
|
|
"num_tokens": 40738423.0,
|
|
"step": 18255
|
|
},
|
|
{
|
|
"entropy": 5.658260202407837,
|
|
"epoch": 2.050766552479362,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.00045865258300980817,
|
|
"loss": 5.4002,
|
|
"mean_token_accuracy": 0.1902313143014908,
|
|
"num_tokens": 40749506.0,
|
|
"step": 18260
|
|
},
|
|
{
|
|
"entropy": 5.581439590454101,
|
|
"epoch": 2.05132812938732,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00045862938529366514,
|
|
"loss": 5.2558,
|
|
"mean_token_accuracy": 0.2016041696071625,
|
|
"num_tokens": 40762165.0,
|
|
"step": 18265
|
|
},
|
|
{
|
|
"entropy": 5.5209489345550535,
|
|
"epoch": 2.051889706295277,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004586061817306913,
|
|
"loss": 5.3314,
|
|
"mean_token_accuracy": 0.18586129695177078,
|
|
"num_tokens": 40774043.0,
|
|
"step": 18270
|
|
},
|
|
{
|
|
"entropy": 5.446827602386475,
|
|
"epoch": 2.0524512832032347,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00045858297232162536,
|
|
"loss": 5.211,
|
|
"mean_token_accuracy": 0.19647075086832047,
|
|
"num_tokens": 40784758.0,
|
|
"step": 18275
|
|
},
|
|
{
|
|
"entropy": 5.5446666240692135,
|
|
"epoch": 2.0530128601111923,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00045855975706720644,
|
|
"loss": 5.2333,
|
|
"mean_token_accuracy": 0.19913334995508195,
|
|
"num_tokens": 40794735.0,
|
|
"step": 18280
|
|
},
|
|
{
|
|
"entropy": 5.438759994506836,
|
|
"epoch": 2.05357443701915,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004585365359681736,
|
|
"loss": 5.1257,
|
|
"mean_token_accuracy": 0.2007010981440544,
|
|
"num_tokens": 40805491.0,
|
|
"step": 18285
|
|
},
|
|
{
|
|
"entropy": 5.546117210388184,
|
|
"epoch": 2.054136013927107,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.00045851330902526633,
|
|
"loss": 5.3535,
|
|
"mean_token_accuracy": 0.19056230485439302,
|
|
"num_tokens": 40816945.0,
|
|
"step": 18290
|
|
},
|
|
{
|
|
"entropy": 5.613444900512695,
|
|
"epoch": 2.054697590835065,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00045849007623922406,
|
|
"loss": 5.3182,
|
|
"mean_token_accuracy": 0.19508860260248184,
|
|
"num_tokens": 40828199.0,
|
|
"step": 18295
|
|
},
|
|
{
|
|
"entropy": 5.528549337387085,
|
|
"epoch": 2.0552591677430225,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004584668376107867,
|
|
"loss": 5.3363,
|
|
"mean_token_accuracy": 0.19062856286764146,
|
|
"num_tokens": 40839618.0,
|
|
"step": 18300
|
|
},
|
|
{
|
|
"entropy": 5.464557266235351,
|
|
"epoch": 2.0558207446509797,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000458443593140694,
|
|
"loss": 5.2184,
|
|
"mean_token_accuracy": 0.19472844153642654,
|
|
"num_tokens": 40851078.0,
|
|
"step": 18305
|
|
},
|
|
{
|
|
"entropy": 5.544152736663818,
|
|
"epoch": 2.0563823215589374,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00045842034282968615,
|
|
"loss": 5.2072,
|
|
"mean_token_accuracy": 0.19696956127882004,
|
|
"num_tokens": 40862397.0,
|
|
"step": 18310
|
|
},
|
|
{
|
|
"entropy": 5.4796758651733395,
|
|
"epoch": 2.056943898466895,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004583970866785035,
|
|
"loss": 5.215,
|
|
"mean_token_accuracy": 0.19224913716316222,
|
|
"num_tokens": 40872739.0,
|
|
"step": 18315
|
|
},
|
|
{
|
|
"entropy": 5.625690078735351,
|
|
"epoch": 2.0575054753748527,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00045837382468788643,
|
|
"loss": 5.3098,
|
|
"mean_token_accuracy": 0.19087839126586914,
|
|
"num_tokens": 40884723.0,
|
|
"step": 18320
|
|
},
|
|
{
|
|
"entropy": 5.544408082962036,
|
|
"epoch": 2.05806705228281,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004583505568585757,
|
|
"loss": 5.2939,
|
|
"mean_token_accuracy": 0.19208989590406417,
|
|
"num_tokens": 40895927.0,
|
|
"step": 18325
|
|
},
|
|
{
|
|
"entropy": 5.457180213928223,
|
|
"epoch": 2.0586286291907676,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.00045832728319131205,
|
|
"loss": 5.258,
|
|
"mean_token_accuracy": 0.1920614942908287,
|
|
"num_tokens": 40906504.0,
|
|
"step": 18330
|
|
},
|
|
{
|
|
"entropy": 5.464088249206543,
|
|
"epoch": 2.0591902060987253,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004583040036868367,
|
|
"loss": 5.1613,
|
|
"mean_token_accuracy": 0.19689573645591735,
|
|
"num_tokens": 40918420.0,
|
|
"step": 18335
|
|
},
|
|
{
|
|
"entropy": 5.5200577735900875,
|
|
"epoch": 2.059751783006683,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004582807183458907,
|
|
"loss": 5.2778,
|
|
"mean_token_accuracy": 0.19521691650152206,
|
|
"num_tokens": 40929665.0,
|
|
"step": 18340
|
|
},
|
|
{
|
|
"entropy": 5.528092098236084,
|
|
"epoch": 2.06031335991464,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.00045825742716921553,
|
|
"loss": 5.2535,
|
|
"mean_token_accuracy": 0.18861947506666182,
|
|
"num_tokens": 40941134.0,
|
|
"step": 18345
|
|
},
|
|
{
|
|
"entropy": 5.539303970336914,
|
|
"epoch": 2.060874936822598,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004582341301575529,
|
|
"loss": 5.2767,
|
|
"mean_token_accuracy": 0.1965376242995262,
|
|
"num_tokens": 40953230.0,
|
|
"step": 18350
|
|
},
|
|
{
|
|
"entropy": 5.47193751335144,
|
|
"epoch": 2.0614365137305555,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00045821082731164445,
|
|
"loss": 5.2186,
|
|
"mean_token_accuracy": 0.1976081594824791,
|
|
"num_tokens": 40964398.0,
|
|
"step": 18355
|
|
},
|
|
{
|
|
"entropy": 5.57206244468689,
|
|
"epoch": 2.061998090638513,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004581875186322322,
|
|
"loss": 5.2787,
|
|
"mean_token_accuracy": 0.19481647461652757,
|
|
"num_tokens": 40975561.0,
|
|
"step": 18360
|
|
},
|
|
{
|
|
"entropy": 5.4444647312164305,
|
|
"epoch": 2.0625596675464704,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00045816420412005826,
|
|
"loss": 5.1623,
|
|
"mean_token_accuracy": 0.2018464043736458,
|
|
"num_tokens": 40986393.0,
|
|
"step": 18365
|
|
},
|
|
{
|
|
"entropy": 5.467040348052978,
|
|
"epoch": 2.063121244454428,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.00045814088377586505,
|
|
"loss": 5.2849,
|
|
"mean_token_accuracy": 0.19812929183244704,
|
|
"num_tokens": 40998143.0,
|
|
"step": 18370
|
|
},
|
|
{
|
|
"entropy": 5.554757833480835,
|
|
"epoch": 2.0636828213623857,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00045811755760039513,
|
|
"loss": 5.295,
|
|
"mean_token_accuracy": 0.1946550041437149,
|
|
"num_tokens": 41009747.0,
|
|
"step": 18375
|
|
},
|
|
{
|
|
"entropy": 5.511597061157227,
|
|
"epoch": 2.0642443982703433,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00045809422559439113,
|
|
"loss": 5.2092,
|
|
"mean_token_accuracy": 0.1940724790096283,
|
|
"num_tokens": 41023146.0,
|
|
"step": 18380
|
|
},
|
|
{
|
|
"entropy": 5.526904296875,
|
|
"epoch": 2.0648059751783006,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00045807088775859595,
|
|
"loss": 5.3336,
|
|
"mean_token_accuracy": 0.1882246345281601,
|
|
"num_tokens": 41034138.0,
|
|
"step": 18385
|
|
},
|
|
{
|
|
"entropy": 5.50452070236206,
|
|
"epoch": 2.065367552086258,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004580475440937527,
|
|
"loss": 5.1359,
|
|
"mean_token_accuracy": 0.1989658758044243,
|
|
"num_tokens": 41045457.0,
|
|
"step": 18390
|
|
},
|
|
{
|
|
"entropy": 5.465430545806885,
|
|
"epoch": 2.065929128994216,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00045802419460060464,
|
|
"loss": 5.2332,
|
|
"mean_token_accuracy": 0.19728562235832214,
|
|
"num_tokens": 41056264.0,
|
|
"step": 18395
|
|
},
|
|
{
|
|
"entropy": 5.546510696411133,
|
|
"epoch": 2.066490705902173,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004580008392798953,
|
|
"loss": 5.3919,
|
|
"mean_token_accuracy": 0.18524643480777742,
|
|
"num_tokens": 41067206.0,
|
|
"step": 18400
|
|
},
|
|
{
|
|
"entropy": 5.422588682174682,
|
|
"epoch": 2.0670522828101308,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00045797747813236815,
|
|
"loss": 5.1246,
|
|
"mean_token_accuracy": 0.19666744470596315,
|
|
"num_tokens": 41077897.0,
|
|
"step": 18405
|
|
},
|
|
{
|
|
"entropy": 5.471376037597656,
|
|
"epoch": 2.0676138597180884,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00045795411115876725,
|
|
"loss": 5.2099,
|
|
"mean_token_accuracy": 0.19427814334630966,
|
|
"num_tokens": 41088964.0,
|
|
"step": 18410
|
|
},
|
|
{
|
|
"entropy": 5.49049596786499,
|
|
"epoch": 2.068175436626046,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00045793073835983644,
|
|
"loss": 5.1571,
|
|
"mean_token_accuracy": 0.2011103078722954,
|
|
"num_tokens": 41098818.0,
|
|
"step": 18415
|
|
},
|
|
{
|
|
"entropy": 5.587615966796875,
|
|
"epoch": 2.0687370135340033,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00045790735973631996,
|
|
"loss": 5.364,
|
|
"mean_token_accuracy": 0.18901024609804154,
|
|
"num_tokens": 41111222.0,
|
|
"step": 18420
|
|
},
|
|
{
|
|
"entropy": 5.530643653869629,
|
|
"epoch": 2.069298590441961,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00045788397528896224,
|
|
"loss": 5.2167,
|
|
"mean_token_accuracy": 0.19260232746601105,
|
|
"num_tokens": 41122875.0,
|
|
"step": 18425
|
|
},
|
|
{
|
|
"entropy": 5.506813621520996,
|
|
"epoch": 2.0698601673499186,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00045786058501850774,
|
|
"loss": 5.2538,
|
|
"mean_token_accuracy": 0.18410073071718216,
|
|
"num_tokens": 41133869.0,
|
|
"step": 18430
|
|
},
|
|
{
|
|
"entropy": 5.508162975311279,
|
|
"epoch": 2.0704217442578763,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00045783718892570136,
|
|
"loss": 5.1777,
|
|
"mean_token_accuracy": 0.19572405219078065,
|
|
"num_tokens": 41144482.0,
|
|
"step": 18435
|
|
},
|
|
{
|
|
"entropy": 5.415844249725342,
|
|
"epoch": 2.0709833211658335,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.000457813787011288,
|
|
"loss": 5.1835,
|
|
"mean_token_accuracy": 0.19369978755712508,
|
|
"num_tokens": 41154997.0,
|
|
"step": 18440
|
|
},
|
|
{
|
|
"entropy": 5.39900164604187,
|
|
"epoch": 2.071544898073791,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004577903792760127,
|
|
"loss": 5.2225,
|
|
"mean_token_accuracy": 0.19413264840841293,
|
|
"num_tokens": 41167852.0,
|
|
"step": 18445
|
|
},
|
|
{
|
|
"entropy": 5.523342895507812,
|
|
"epoch": 2.072106474981749,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004577669657206209,
|
|
"loss": 5.2132,
|
|
"mean_token_accuracy": 0.19986539632081984,
|
|
"num_tokens": 41178364.0,
|
|
"step": 18450
|
|
},
|
|
{
|
|
"entropy": 5.528639316558838,
|
|
"epoch": 2.0726680518897065,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004577435463458579,
|
|
"loss": 5.3268,
|
|
"mean_token_accuracy": 0.18822480142116546,
|
|
"num_tokens": 41190003.0,
|
|
"step": 18455
|
|
},
|
|
{
|
|
"entropy": 5.46252064704895,
|
|
"epoch": 2.0732296287976637,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004577201211524696,
|
|
"loss": 5.1594,
|
|
"mean_token_accuracy": 0.19574379473924636,
|
|
"num_tokens": 41201574.0,
|
|
"step": 18460
|
|
},
|
|
{
|
|
"entropy": 5.432068252563477,
|
|
"epoch": 2.0737912057056214,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004576966901412018,
|
|
"loss": 5.1589,
|
|
"mean_token_accuracy": 0.20136497765779496,
|
|
"num_tokens": 41211913.0,
|
|
"step": 18465
|
|
},
|
|
{
|
|
"entropy": 5.419327163696289,
|
|
"epoch": 2.074352782613579,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00045767325331280044,
|
|
"loss": 5.177,
|
|
"mean_token_accuracy": 0.1994516834616661,
|
|
"num_tokens": 41222626.0,
|
|
"step": 18470
|
|
},
|
|
{
|
|
"entropy": 5.540180206298828,
|
|
"epoch": 2.0749143595215367,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004576498106680119,
|
|
"loss": 5.3444,
|
|
"mean_token_accuracy": 0.1827343687415123,
|
|
"num_tokens": 41234321.0,
|
|
"step": 18475
|
|
},
|
|
{
|
|
"entropy": 5.5479310035705565,
|
|
"epoch": 2.075475936429494,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004576263622075826,
|
|
"loss": 5.1779,
|
|
"mean_token_accuracy": 0.20113203227519988,
|
|
"num_tokens": 41244889.0,
|
|
"step": 18480
|
|
},
|
|
{
|
|
"entropy": 5.574405193328857,
|
|
"epoch": 2.0760375133374516,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.000457602907932259,
|
|
"loss": 5.3946,
|
|
"mean_token_accuracy": 0.18477905839681624,
|
|
"num_tokens": 41255710.0,
|
|
"step": 18485
|
|
},
|
|
{
|
|
"entropy": 5.56986894607544,
|
|
"epoch": 2.0765990902454092,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00045757944784278803,
|
|
"loss": 5.2966,
|
|
"mean_token_accuracy": 0.19818877577781677,
|
|
"num_tokens": 41265786.0,
|
|
"step": 18490
|
|
},
|
|
{
|
|
"entropy": 5.501178836822509,
|
|
"epoch": 2.0771606671533664,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004575559819399166,
|
|
"loss": 5.2142,
|
|
"mean_token_accuracy": 0.1905228704214096,
|
|
"num_tokens": 41276755.0,
|
|
"step": 18495
|
|
},
|
|
{
|
|
"entropy": 5.527812051773071,
|
|
"epoch": 2.077722244061324,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00045753251022439195,
|
|
"loss": 5.1731,
|
|
"mean_token_accuracy": 0.19660303592681885,
|
|
"num_tokens": 41287219.0,
|
|
"step": 18500
|
|
},
|
|
{
|
|
"entropy": 5.547694540023803,
|
|
"epoch": 2.0782838209692818,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004575090326969614,
|
|
"loss": 5.2488,
|
|
"mean_token_accuracy": 0.19359165132045747,
|
|
"num_tokens": 41297356.0,
|
|
"step": 18505
|
|
},
|
|
{
|
|
"entropy": 5.397096443176269,
|
|
"epoch": 2.0788453978772394,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004574855493583723,
|
|
"loss": 5.1614,
|
|
"mean_token_accuracy": 0.2053090140223503,
|
|
"num_tokens": 41307219.0,
|
|
"step": 18510
|
|
},
|
|
{
|
|
"entropy": 5.516602182388306,
|
|
"epoch": 2.0794069747851966,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00045746206020937276,
|
|
"loss": 5.2944,
|
|
"mean_token_accuracy": 0.19071929454803466,
|
|
"num_tokens": 41318827.0,
|
|
"step": 18515
|
|
},
|
|
{
|
|
"entropy": 5.575522708892822,
|
|
"epoch": 2.0799685516931543,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.00045743856525071034,
|
|
"loss": 5.3056,
|
|
"mean_token_accuracy": 0.19240287989377974,
|
|
"num_tokens": 41329497.0,
|
|
"step": 18520
|
|
},
|
|
{
|
|
"entropy": 5.531044864654541,
|
|
"epoch": 2.080530128601112,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00045741506448313327,
|
|
"loss": 5.2407,
|
|
"mean_token_accuracy": 0.1947307512164116,
|
|
"num_tokens": 41340577.0,
|
|
"step": 18525
|
|
},
|
|
{
|
|
"entropy": 5.509425687789917,
|
|
"epoch": 2.0810917055090696,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.00045739155790738975,
|
|
"loss": 5.2418,
|
|
"mean_token_accuracy": 0.18887036442756652,
|
|
"num_tokens": 41351685.0,
|
|
"step": 18530
|
|
},
|
|
{
|
|
"entropy": 5.650399875640869,
|
|
"epoch": 2.081653282417027,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.00045736804552422836,
|
|
"loss": 5.3743,
|
|
"mean_token_accuracy": 0.18694644272327424,
|
|
"num_tokens": 41363053.0,
|
|
"step": 18535
|
|
},
|
|
{
|
|
"entropy": 5.678454971313476,
|
|
"epoch": 2.0822148593249845,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004573445273343976,
|
|
"loss": 5.3827,
|
|
"mean_token_accuracy": 0.18889155685901643,
|
|
"num_tokens": 41374847.0,
|
|
"step": 18540
|
|
},
|
|
{
|
|
"entropy": 5.481970024108887,
|
|
"epoch": 2.082776436232942,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004573210033386464,
|
|
"loss": 5.3257,
|
|
"mean_token_accuracy": 0.18636160343885422,
|
|
"num_tokens": 41386114.0,
|
|
"step": 18545
|
|
},
|
|
{
|
|
"entropy": 5.462983226776123,
|
|
"epoch": 2.0833380131409,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004572974735377238,
|
|
"loss": 5.1213,
|
|
"mean_token_accuracy": 0.19758780896663666,
|
|
"num_tokens": 41397842.0,
|
|
"step": 18550
|
|
},
|
|
{
|
|
"entropy": 5.509663248062134,
|
|
"epoch": 2.083899590048857,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004572739379323788,
|
|
"loss": 5.2399,
|
|
"mean_token_accuracy": 0.19286703318357468,
|
|
"num_tokens": 41409824.0,
|
|
"step": 18555
|
|
},
|
|
{
|
|
"entropy": 5.453081274032593,
|
|
"epoch": 2.0844611669568147,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00045725039652336105,
|
|
"loss": 5.2259,
|
|
"mean_token_accuracy": 0.18826664984226227,
|
|
"num_tokens": 41422260.0,
|
|
"step": 18560
|
|
},
|
|
{
|
|
"entropy": 5.517183828353882,
|
|
"epoch": 2.0850227438647724,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004572268493114199,
|
|
"loss": 5.2298,
|
|
"mean_token_accuracy": 0.1965215101838112,
|
|
"num_tokens": 41433068.0,
|
|
"step": 18565
|
|
},
|
|
{
|
|
"entropy": 5.508039379119873,
|
|
"epoch": 2.08558432077273,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004572032962973052,
|
|
"loss": 5.2056,
|
|
"mean_token_accuracy": 0.19768486469984053,
|
|
"num_tokens": 41443759.0,
|
|
"step": 18570
|
|
},
|
|
{
|
|
"entropy": 5.49811019897461,
|
|
"epoch": 2.0861458976806873,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00045717973748176695,
|
|
"loss": 5.2836,
|
|
"mean_token_accuracy": 0.19462305605411528,
|
|
"num_tokens": 41453876.0,
|
|
"step": 18575
|
|
},
|
|
{
|
|
"entropy": 5.466852378845215,
|
|
"epoch": 2.086707474588645,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.00045715617286555516,
|
|
"loss": 5.2182,
|
|
"mean_token_accuracy": 0.19392173439264299,
|
|
"num_tokens": 41464731.0,
|
|
"step": 18580
|
|
},
|
|
{
|
|
"entropy": 5.573261833190918,
|
|
"epoch": 2.0872690514966026,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.00045713260244942017,
|
|
"loss": 5.3091,
|
|
"mean_token_accuracy": 0.18790953904390334,
|
|
"num_tokens": 41476288.0,
|
|
"step": 18585
|
|
},
|
|
{
|
|
"entropy": 5.573249006271363,
|
|
"epoch": 2.08783062840456,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004571090262341125,
|
|
"loss": 5.2252,
|
|
"mean_token_accuracy": 0.19779866933822632,
|
|
"num_tokens": 41485968.0,
|
|
"step": 18590
|
|
},
|
|
{
|
|
"entropy": 5.522953653335572,
|
|
"epoch": 2.0883922053125175,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00045708544422038284,
|
|
"loss": 5.2661,
|
|
"mean_token_accuracy": 0.19240011423826217,
|
|
"num_tokens": 41496393.0,
|
|
"step": 18595
|
|
},
|
|
{
|
|
"entropy": 5.467296504974366,
|
|
"epoch": 2.088953782220475,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004570618564089819,
|
|
"loss": 5.243,
|
|
"mean_token_accuracy": 0.19548484683036804,
|
|
"num_tokens": 41507539.0,
|
|
"step": 18600
|
|
},
|
|
{
|
|
"entropy": 5.596036577224732,
|
|
"epoch": 2.089515359128433,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00045703826280066095,
|
|
"loss": 5.3252,
|
|
"mean_token_accuracy": 0.1854417070746422,
|
|
"num_tokens": 41517845.0,
|
|
"step": 18605
|
|
},
|
|
{
|
|
"entropy": 5.524791860580445,
|
|
"epoch": 2.09007693603639,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004570146633961711,
|
|
"loss": 5.2259,
|
|
"mean_token_accuracy": 0.19945240616798401,
|
|
"num_tokens": 41528204.0,
|
|
"step": 18610
|
|
},
|
|
{
|
|
"entropy": 5.528181171417236,
|
|
"epoch": 2.0906385129443477,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00045699105819626374,
|
|
"loss": 5.276,
|
|
"mean_token_accuracy": 0.19378704726696014,
|
|
"num_tokens": 41538425.0,
|
|
"step": 18615
|
|
},
|
|
{
|
|
"entropy": 5.5230772495269775,
|
|
"epoch": 2.0912000898523053,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004569674472016904,
|
|
"loss": 5.3237,
|
|
"mean_token_accuracy": 0.19206100851297378,
|
|
"num_tokens": 41548762.0,
|
|
"step": 18620
|
|
},
|
|
{
|
|
"entropy": 5.452923059463501,
|
|
"epoch": 2.091761666760263,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004569438304132031,
|
|
"loss": 5.1839,
|
|
"mean_token_accuracy": 0.199401193857193,
|
|
"num_tokens": 41559003.0,
|
|
"step": 18625
|
|
},
|
|
{
|
|
"entropy": 5.472324323654175,
|
|
"epoch": 2.09232324366822,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00045692020783155376,
|
|
"loss": 5.1982,
|
|
"mean_token_accuracy": 0.1943460151553154,
|
|
"num_tokens": 41569630.0,
|
|
"step": 18630
|
|
},
|
|
{
|
|
"entropy": 5.567695569992066,
|
|
"epoch": 2.092884820576178,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004568965794574943,
|
|
"loss": 5.3137,
|
|
"mean_token_accuracy": 0.19472360759973525,
|
|
"num_tokens": 41580671.0,
|
|
"step": 18635
|
|
},
|
|
{
|
|
"entropy": 5.5831156253814695,
|
|
"epoch": 2.0934463974841355,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004568729452917772,
|
|
"loss": 5.3094,
|
|
"mean_token_accuracy": 0.18963203132152556,
|
|
"num_tokens": 41592475.0,
|
|
"step": 18640
|
|
},
|
|
{
|
|
"entropy": 5.539744853973389,
|
|
"epoch": 2.094007974392093,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00045684930533515506,
|
|
"loss": 5.2669,
|
|
"mean_token_accuracy": 0.18983601927757263,
|
|
"num_tokens": 41603675.0,
|
|
"step": 18645
|
|
},
|
|
{
|
|
"entropy": 5.532234525680542,
|
|
"epoch": 2.0945695513000504,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.00045682565958838045,
|
|
"loss": 5.2171,
|
|
"mean_token_accuracy": 0.19250726699829102,
|
|
"num_tokens": 41614684.0,
|
|
"step": 18650
|
|
},
|
|
{
|
|
"entropy": 5.4813155174255375,
|
|
"epoch": 2.095131128208008,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004568020080522063,
|
|
"loss": 5.3144,
|
|
"mean_token_accuracy": 0.19253091961145402,
|
|
"num_tokens": 41625368.0,
|
|
"step": 18655
|
|
},
|
|
{
|
|
"entropy": 5.555939674377441,
|
|
"epoch": 2.0956927051159657,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004567783507273858,
|
|
"loss": 5.2503,
|
|
"mean_token_accuracy": 0.19352529495954512,
|
|
"num_tokens": 41636542.0,
|
|
"step": 18660
|
|
},
|
|
{
|
|
"entropy": 5.597741222381591,
|
|
"epoch": 2.0962542820239234,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00045675468761467204,
|
|
"loss": 5.3119,
|
|
"mean_token_accuracy": 0.19495112150907518,
|
|
"num_tokens": 41646654.0,
|
|
"step": 18665
|
|
},
|
|
{
|
|
"entropy": 5.592956924438477,
|
|
"epoch": 2.0968158589318806,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00045673101871481853,
|
|
"loss": 5.4201,
|
|
"mean_token_accuracy": 0.1823358029127121,
|
|
"num_tokens": 41659160.0,
|
|
"step": 18670
|
|
},
|
|
{
|
|
"entropy": 5.543447494506836,
|
|
"epoch": 2.0973774358398383,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004567073440285789,
|
|
"loss": 5.2523,
|
|
"mean_token_accuracy": 0.19714139848947526,
|
|
"num_tokens": 41670864.0,
|
|
"step": 18675
|
|
},
|
|
{
|
|
"entropy": 5.494233083724976,
|
|
"epoch": 2.097939012747796,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00045668366355670697,
|
|
"loss": 5.1755,
|
|
"mean_token_accuracy": 0.19407217502593993,
|
|
"num_tokens": 41681947.0,
|
|
"step": 18680
|
|
},
|
|
{
|
|
"entropy": 5.510460996627808,
|
|
"epoch": 2.098500589655753,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004566599772999567,
|
|
"loss": 5.3112,
|
|
"mean_token_accuracy": 0.18885926455259322,
|
|
"num_tokens": 41692625.0,
|
|
"step": 18685
|
|
},
|
|
{
|
|
"entropy": 5.617909145355225,
|
|
"epoch": 2.099062166563711,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.00045663628525908237,
|
|
"loss": 5.3429,
|
|
"mean_token_accuracy": 0.18358024060726166,
|
|
"num_tokens": 41703118.0,
|
|
"step": 18690
|
|
},
|
|
{
|
|
"entropy": 5.574043846130371,
|
|
"epoch": 2.0996237434716685,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004566125874348382,
|
|
"loss": 5.2765,
|
|
"mean_token_accuracy": 0.19572641253471373,
|
|
"num_tokens": 41713910.0,
|
|
"step": 18695
|
|
},
|
|
{
|
|
"entropy": 5.522626638412476,
|
|
"epoch": 2.100185320379626,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00045658888382797886,
|
|
"loss": 5.2512,
|
|
"mean_token_accuracy": 0.19443645179271699,
|
|
"num_tokens": 41725290.0,
|
|
"step": 18700
|
|
},
|
|
{
|
|
"entropy": 5.572107410430908,
|
|
"epoch": 2.1007468972875833,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.00045656517443925897,
|
|
"loss": 5.2982,
|
|
"mean_token_accuracy": 0.19033897370100022,
|
|
"num_tokens": 41736265.0,
|
|
"step": 18705
|
|
},
|
|
{
|
|
"entropy": 5.57664270401001,
|
|
"epoch": 2.101308474195541,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004565414592694336,
|
|
"loss": 5.3173,
|
|
"mean_token_accuracy": 0.1888023942708969,
|
|
"num_tokens": 41746702.0,
|
|
"step": 18710
|
|
},
|
|
{
|
|
"entropy": 5.643450450897217,
|
|
"epoch": 2.1018700511034987,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004565177383192577,
|
|
"loss": 5.4193,
|
|
"mean_token_accuracy": 0.18916128873825072,
|
|
"num_tokens": 41758570.0,
|
|
"step": 18715
|
|
},
|
|
{
|
|
"entropy": 5.602493619918823,
|
|
"epoch": 2.1024316280114563,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.00045649401158948664,
|
|
"loss": 5.3028,
|
|
"mean_token_accuracy": 0.20153228789567948,
|
|
"num_tokens": 41769507.0,
|
|
"step": 18720
|
|
},
|
|
{
|
|
"entropy": 5.514243793487549,
|
|
"epoch": 2.1029932049194136,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004564702790808758,
|
|
"loss": 5.2622,
|
|
"mean_token_accuracy": 0.20066044330596924,
|
|
"num_tokens": 41780558.0,
|
|
"step": 18725
|
|
},
|
|
{
|
|
"entropy": 5.454886388778687,
|
|
"epoch": 2.103554781827371,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004564465407941809,
|
|
"loss": 5.1833,
|
|
"mean_token_accuracy": 0.1996917173266411,
|
|
"num_tokens": 41790518.0,
|
|
"step": 18730
|
|
},
|
|
{
|
|
"entropy": 5.53684434890747,
|
|
"epoch": 2.104116358735329,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00045642279673015787,
|
|
"loss": 5.301,
|
|
"mean_token_accuracy": 0.19263856112957,
|
|
"num_tokens": 41800329.0,
|
|
"step": 18735
|
|
},
|
|
{
|
|
"entropy": 5.483575105667114,
|
|
"epoch": 2.1046779356432865,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004563990468895625,
|
|
"loss": 5.1409,
|
|
"mean_token_accuracy": 0.19947306662797928,
|
|
"num_tokens": 41811231.0,
|
|
"step": 18740
|
|
},
|
|
{
|
|
"entropy": 5.435629844665527,
|
|
"epoch": 2.1052395125512438,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004563752912731512,
|
|
"loss": 5.1808,
|
|
"mean_token_accuracy": 0.19311793446540831,
|
|
"num_tokens": 41821544.0,
|
|
"step": 18745
|
|
},
|
|
{
|
|
"entropy": 5.447556829452514,
|
|
"epoch": 2.1058010894592014,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004563515298816803,
|
|
"loss": 5.2246,
|
|
"mean_token_accuracy": 0.19453134685754775,
|
|
"num_tokens": 41832371.0,
|
|
"step": 18750
|
|
},
|
|
{
|
|
"entropy": 5.540677452087403,
|
|
"epoch": 2.106362666367159,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00045632776271590624,
|
|
"loss": 5.2118,
|
|
"mean_token_accuracy": 0.19812269806861876,
|
|
"num_tokens": 41842828.0,
|
|
"step": 18755
|
|
},
|
|
{
|
|
"entropy": 5.381276988983155,
|
|
"epoch": 2.1069242432751167,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004563039897765859,
|
|
"loss": 5.1851,
|
|
"mean_token_accuracy": 0.19802186340093614,
|
|
"num_tokens": 41855128.0,
|
|
"step": 18760
|
|
},
|
|
{
|
|
"entropy": 5.4975542545318605,
|
|
"epoch": 2.107485820183074,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004562802110644764,
|
|
"loss": 5.2678,
|
|
"mean_token_accuracy": 0.19369828552007676,
|
|
"num_tokens": 41866258.0,
|
|
"step": 18765
|
|
},
|
|
{
|
|
"entropy": 5.563699722290039,
|
|
"epoch": 2.1080473970910316,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.00045625642658033447,
|
|
"loss": 5.2483,
|
|
"mean_token_accuracy": 0.19284942299127578,
|
|
"num_tokens": 41877713.0,
|
|
"step": 18770
|
|
},
|
|
{
|
|
"entropy": 5.580010843276978,
|
|
"epoch": 2.1086089739989893,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00045623263632491766,
|
|
"loss": 5.2598,
|
|
"mean_token_accuracy": 0.19463108032941817,
|
|
"num_tokens": 41888592.0,
|
|
"step": 18775
|
|
},
|
|
{
|
|
"entropy": 5.532656049728393,
|
|
"epoch": 2.1091705509069465,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.00045620884029898344,
|
|
"loss": 5.347,
|
|
"mean_token_accuracy": 0.1923212856054306,
|
|
"num_tokens": 41901024.0,
|
|
"step": 18780
|
|
},
|
|
{
|
|
"entropy": 5.5249697208404545,
|
|
"epoch": 2.109732127814904,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00045618503850328954,
|
|
"loss": 5.2645,
|
|
"mean_token_accuracy": 0.19209007024765015,
|
|
"num_tokens": 41911184.0,
|
|
"step": 18785
|
|
},
|
|
{
|
|
"entropy": 5.554409790039062,
|
|
"epoch": 2.110293704722862,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004561612309385936,
|
|
"loss": 5.2922,
|
|
"mean_token_accuracy": 0.1893538936972618,
|
|
"num_tokens": 41922799.0,
|
|
"step": 18790
|
|
},
|
|
{
|
|
"entropy": 5.554865884780884,
|
|
"epoch": 2.1108552816308195,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00045613741760565385,
|
|
"loss": 5.2531,
|
|
"mean_token_accuracy": 0.20113448053598404,
|
|
"num_tokens": 41933223.0,
|
|
"step": 18795
|
|
},
|
|
{
|
|
"entropy": 5.484144639968872,
|
|
"epoch": 2.1114168585387767,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004561135985052285,
|
|
"loss": 5.2725,
|
|
"mean_token_accuracy": 0.1906439855694771,
|
|
"num_tokens": 41944288.0,
|
|
"step": 18800
|
|
},
|
|
{
|
|
"entropy": 5.463064861297608,
|
|
"epoch": 2.1119784354467344,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.000456089773638076,
|
|
"loss": 5.2092,
|
|
"mean_token_accuracy": 0.19603820592164994,
|
|
"num_tokens": 41954312.0,
|
|
"step": 18805
|
|
},
|
|
{
|
|
"entropy": 5.504269123077393,
|
|
"epoch": 2.112540012354692,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.0004560659430049548,
|
|
"loss": 5.3058,
|
|
"mean_token_accuracy": 0.1928422585129738,
|
|
"num_tokens": 41966871.0,
|
|
"step": 18810
|
|
},
|
|
{
|
|
"entropy": 5.491275882720947,
|
|
"epoch": 2.1131015892626497,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004560421066066237,
|
|
"loss": 5.204,
|
|
"mean_token_accuracy": 0.200209341943264,
|
|
"num_tokens": 41979087.0,
|
|
"step": 18815
|
|
},
|
|
{
|
|
"entropy": 5.499590873718262,
|
|
"epoch": 2.113663166170607,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00045601826444384175,
|
|
"loss": 5.2582,
|
|
"mean_token_accuracy": 0.18966676145792008,
|
|
"num_tokens": 41989867.0,
|
|
"step": 18820
|
|
},
|
|
{
|
|
"entropy": 5.482534122467041,
|
|
"epoch": 2.1142247430785646,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00045599441651736805,
|
|
"loss": 5.2403,
|
|
"mean_token_accuracy": 0.20110277086496353,
|
|
"num_tokens": 42001205.0,
|
|
"step": 18825
|
|
},
|
|
{
|
|
"entropy": 5.620621919631958,
|
|
"epoch": 2.1147863199865222,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00045597056282796196,
|
|
"loss": 5.3692,
|
|
"mean_token_accuracy": 0.188943313062191,
|
|
"num_tokens": 42012466.0,
|
|
"step": 18830
|
|
},
|
|
{
|
|
"entropy": 5.310191583633423,
|
|
"epoch": 2.11534789689448,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004559467033763829,
|
|
"loss": 5.0241,
|
|
"mean_token_accuracy": 0.20320245176553725,
|
|
"num_tokens": 42022517.0,
|
|
"step": 18835
|
|
},
|
|
{
|
|
"entropy": 5.48411374092102,
|
|
"epoch": 2.115909473802437,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004559228381633907,
|
|
"loss": 5.1775,
|
|
"mean_token_accuracy": 0.20534804165363313,
|
|
"num_tokens": 42032253.0,
|
|
"step": 18840
|
|
},
|
|
{
|
|
"entropy": 5.523025321960449,
|
|
"epoch": 2.1164710507103948,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00045589896718974517,
|
|
"loss": 5.1944,
|
|
"mean_token_accuracy": 0.20150178372859956,
|
|
"num_tokens": 42042943.0,
|
|
"step": 18845
|
|
},
|
|
{
|
|
"entropy": 5.4963047981262205,
|
|
"epoch": 2.1170326276183524,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004558750904562063,
|
|
"loss": 5.1569,
|
|
"mean_token_accuracy": 0.20104045122861863,
|
|
"num_tokens": 42054302.0,
|
|
"step": 18850
|
|
},
|
|
{
|
|
"entropy": 5.498264455795288,
|
|
"epoch": 2.11759420452631,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004558512079635345,
|
|
"loss": 5.2042,
|
|
"mean_token_accuracy": 0.18445347845554352,
|
|
"num_tokens": 42064810.0,
|
|
"step": 18855
|
|
},
|
|
{
|
|
"entropy": 5.427771425247192,
|
|
"epoch": 2.1181557814342673,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004558273197124899,
|
|
"loss": 5.2823,
|
|
"mean_token_accuracy": 0.1854138121008873,
|
|
"num_tokens": 42076468.0,
|
|
"step": 18860
|
|
},
|
|
{
|
|
"entropy": 5.481720781326294,
|
|
"epoch": 2.118717358342225,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00045580342570383347,
|
|
"loss": 5.194,
|
|
"mean_token_accuracy": 0.1916309341788292,
|
|
"num_tokens": 42087488.0,
|
|
"step": 18865
|
|
},
|
|
{
|
|
"entropy": 5.539413976669311,
|
|
"epoch": 2.1192789352501826,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004557795259383258,
|
|
"loss": 5.3174,
|
|
"mean_token_accuracy": 0.18633429408073426,
|
|
"num_tokens": 42099992.0,
|
|
"step": 18870
|
|
},
|
|
{
|
|
"entropy": 5.5242226123809814,
|
|
"epoch": 2.11984051215814,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00045575562041672794,
|
|
"loss": 5.2672,
|
|
"mean_token_accuracy": 0.1954810306429863,
|
|
"num_tokens": 42111073.0,
|
|
"step": 18875
|
|
},
|
|
{
|
|
"entropy": 5.504447937011719,
|
|
"epoch": 2.1204020890660975,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00045573170913980094,
|
|
"loss": 5.2449,
|
|
"mean_token_accuracy": 0.19019717127084732,
|
|
"num_tokens": 42121413.0,
|
|
"step": 18880
|
|
},
|
|
{
|
|
"entropy": 5.624015855789184,
|
|
"epoch": 2.120963665974055,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.00045570779210830627,
|
|
"loss": 5.3335,
|
|
"mean_token_accuracy": 0.18814467787742614,
|
|
"num_tokens": 42132239.0,
|
|
"step": 18885
|
|
},
|
|
{
|
|
"entropy": 5.500932502746582,
|
|
"epoch": 2.121525242882013,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004556838693230054,
|
|
"loss": 5.2791,
|
|
"mean_token_accuracy": 0.1989013895392418,
|
|
"num_tokens": 42143124.0,
|
|
"step": 18890
|
|
},
|
|
{
|
|
"entropy": 5.544722843170166,
|
|
"epoch": 2.12208681978997,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.00045565994078466005,
|
|
"loss": 5.2792,
|
|
"mean_token_accuracy": 0.18843552768230437,
|
|
"num_tokens": 42152653.0,
|
|
"step": 18895
|
|
},
|
|
{
|
|
"entropy": 5.598435783386231,
|
|
"epoch": 2.1226483966979277,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.00045563600649403213,
|
|
"loss": 5.2902,
|
|
"mean_token_accuracy": 0.19514897912740709,
|
|
"num_tokens": 42162734.0,
|
|
"step": 18900
|
|
},
|
|
{
|
|
"entropy": 5.5806882858276365,
|
|
"epoch": 2.1232099736058854,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004556120664518838,
|
|
"loss": 5.3694,
|
|
"mean_token_accuracy": 0.18368770629167558,
|
|
"num_tokens": 42175312.0,
|
|
"step": 18905
|
|
},
|
|
{
|
|
"entropy": 5.542457532882691,
|
|
"epoch": 2.123771550513843,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004555881206589771,
|
|
"loss": 5.2823,
|
|
"mean_token_accuracy": 0.19374412000179292,
|
|
"num_tokens": 42186512.0,
|
|
"step": 18910
|
|
},
|
|
{
|
|
"entropy": 5.506154775619507,
|
|
"epoch": 2.1243331274218002,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004555641691160746,
|
|
"loss": 5.2942,
|
|
"mean_token_accuracy": 0.19333634078502654,
|
|
"num_tokens": 42197698.0,
|
|
"step": 18915
|
|
},
|
|
{
|
|
"entropy": 5.461877727508545,
|
|
"epoch": 2.124894704329758,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000455540211823939,
|
|
"loss": 5.2573,
|
|
"mean_token_accuracy": 0.19873272776603698,
|
|
"num_tokens": 42208761.0,
|
|
"step": 18920
|
|
},
|
|
{
|
|
"entropy": 5.528551912307739,
|
|
"epoch": 2.1254562812377156,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.00045551624878333296,
|
|
"loss": 5.2581,
|
|
"mean_token_accuracy": 0.19103594720363617,
|
|
"num_tokens": 42218920.0,
|
|
"step": 18925
|
|
},
|
|
{
|
|
"entropy": 5.556779098510742,
|
|
"epoch": 2.1260178581456732,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00045549227999501957,
|
|
"loss": 5.2387,
|
|
"mean_token_accuracy": 0.19957176297903062,
|
|
"num_tokens": 42229819.0,
|
|
"step": 18930
|
|
},
|
|
{
|
|
"entropy": 5.454245948791504,
|
|
"epoch": 2.1265794350536305,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00045546830545976203,
|
|
"loss": 5.2067,
|
|
"mean_token_accuracy": 0.1932344540953636,
|
|
"num_tokens": 42241189.0,
|
|
"step": 18935
|
|
},
|
|
{
|
|
"entropy": 5.484561920166016,
|
|
"epoch": 2.127141011961588,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00045544432517832356,
|
|
"loss": 5.1614,
|
|
"mean_token_accuracy": 0.198034605383873,
|
|
"num_tokens": 42252665.0,
|
|
"step": 18940
|
|
},
|
|
{
|
|
"entropy": 5.482719039916992,
|
|
"epoch": 2.1277025888695458,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00045542033915146787,
|
|
"loss": 5.2222,
|
|
"mean_token_accuracy": 0.1934773027896881,
|
|
"num_tokens": 42264514.0,
|
|
"step": 18945
|
|
},
|
|
{
|
|
"entropy": 5.532171821594238,
|
|
"epoch": 2.1282641657775034,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.00045539634737995857,
|
|
"loss": 5.263,
|
|
"mean_token_accuracy": 0.19248943775892258,
|
|
"num_tokens": 42275229.0,
|
|
"step": 18950
|
|
},
|
|
{
|
|
"entropy": 5.535907793045044,
|
|
"epoch": 2.1288257426854607,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00045537234986455964,
|
|
"loss": 5.2618,
|
|
"mean_token_accuracy": 0.19488944113254547,
|
|
"num_tokens": 42286819.0,
|
|
"step": 18955
|
|
},
|
|
{
|
|
"entropy": 5.54831371307373,
|
|
"epoch": 2.1293873195934183,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004553483466060351,
|
|
"loss": 5.2815,
|
|
"mean_token_accuracy": 0.19568655043840408,
|
|
"num_tokens": 42298329.0,
|
|
"step": 18960
|
|
},
|
|
{
|
|
"entropy": 5.376667451858521,
|
|
"epoch": 2.129948896501376,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00045532433760514925,
|
|
"loss": 5.1636,
|
|
"mean_token_accuracy": 0.19899864345788956,
|
|
"num_tokens": 42308813.0,
|
|
"step": 18965
|
|
},
|
|
{
|
|
"entropy": 5.546373701095581,
|
|
"epoch": 2.130510473409333,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004553003228626665,
|
|
"loss": 5.3032,
|
|
"mean_token_accuracy": 0.19323157519102097,
|
|
"num_tokens": 42321264.0,
|
|
"step": 18970
|
|
},
|
|
{
|
|
"entropy": 5.470273780822754,
|
|
"epoch": 2.131072050317291,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004552763023793517,
|
|
"loss": 5.1835,
|
|
"mean_token_accuracy": 0.19296262860298158,
|
|
"num_tokens": 42332301.0,
|
|
"step": 18975
|
|
},
|
|
{
|
|
"entropy": 5.4789141654968265,
|
|
"epoch": 2.1316336272252485,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004552522761559694,
|
|
"loss": 5.1546,
|
|
"mean_token_accuracy": 0.19569229185581208,
|
|
"num_tokens": 42343424.0,
|
|
"step": 18980
|
|
},
|
|
{
|
|
"entropy": 5.499362564086914,
|
|
"epoch": 2.132195204133206,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00045522824419328475,
|
|
"loss": 5.2499,
|
|
"mean_token_accuracy": 0.19062476903200148,
|
|
"num_tokens": 42354350.0,
|
|
"step": 18985
|
|
},
|
|
{
|
|
"entropy": 5.484207105636597,
|
|
"epoch": 2.1327567810411634,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.00045520420649206283,
|
|
"loss": 5.1596,
|
|
"mean_token_accuracy": 0.19860177040100097,
|
|
"num_tokens": 42365110.0,
|
|
"step": 18990
|
|
},
|
|
{
|
|
"entropy": 5.5182812213897705,
|
|
"epoch": 2.133318357949121,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004551801630530692,
|
|
"loss": 5.285,
|
|
"mean_token_accuracy": 0.1936671495437622,
|
|
"num_tokens": 42376345.0,
|
|
"step": 18995
|
|
},
|
|
{
|
|
"entropy": 5.475411128997803,
|
|
"epoch": 2.1338799348570787,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004551561138770693,
|
|
"loss": 5.1672,
|
|
"mean_token_accuracy": 0.19906097054481506,
|
|
"num_tokens": 42387161.0,
|
|
"step": 19000
|
|
},
|
|
{
|
|
"entropy": 5.461827754974365,
|
|
"epoch": 2.1344415117650364,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00045513205896482875,
|
|
"loss": 5.205,
|
|
"mean_token_accuracy": 0.19788686484098433,
|
|
"num_tokens": 42397468.0,
|
|
"step": 19005
|
|
},
|
|
{
|
|
"entropy": 5.456885766983032,
|
|
"epoch": 2.1350030886729936,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00045510799831711366,
|
|
"loss": 5.2461,
|
|
"mean_token_accuracy": 0.19609155505895615,
|
|
"num_tokens": 42408547.0,
|
|
"step": 19010
|
|
},
|
|
{
|
|
"entropy": 5.428559732437134,
|
|
"epoch": 2.1355646655809513,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00045508393193469,
|
|
"loss": 5.1474,
|
|
"mean_token_accuracy": 0.20036545246839524,
|
|
"num_tokens": 42420383.0,
|
|
"step": 19015
|
|
},
|
|
{
|
|
"entropy": 5.536728191375732,
|
|
"epoch": 2.136126242488909,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004550598598183241,
|
|
"loss": 5.2935,
|
|
"mean_token_accuracy": 0.19071185141801833,
|
|
"num_tokens": 42431723.0,
|
|
"step": 19020
|
|
},
|
|
{
|
|
"entropy": 5.604503440856933,
|
|
"epoch": 2.1366878193968666,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004550357819687825,
|
|
"loss": 5.2857,
|
|
"mean_token_accuracy": 0.19198835790157318,
|
|
"num_tokens": 42443740.0,
|
|
"step": 19025
|
|
},
|
|
{
|
|
"entropy": 5.447312259674073,
|
|
"epoch": 2.137249396304824,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004550116983868317,
|
|
"loss": 5.2151,
|
|
"mean_token_accuracy": 0.20047879517078399,
|
|
"num_tokens": 42454288.0,
|
|
"step": 19030
|
|
},
|
|
{
|
|
"entropy": 5.507414150238037,
|
|
"epoch": 2.1378109732127815,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004549876090732386,
|
|
"loss": 5.2465,
|
|
"mean_token_accuracy": 0.19338610917329788,
|
|
"num_tokens": 42467576.0,
|
|
"step": 19035
|
|
},
|
|
{
|
|
"entropy": 5.53527603149414,
|
|
"epoch": 2.138372550120739,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004549635140287703,
|
|
"loss": 5.2209,
|
|
"mean_token_accuracy": 0.19276407808065416,
|
|
"num_tokens": 42477839.0,
|
|
"step": 19040
|
|
},
|
|
{
|
|
"entropy": 5.437886476516724,
|
|
"epoch": 2.138934127028697,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00045493941325419385,
|
|
"loss": 5.1649,
|
|
"mean_token_accuracy": 0.19419862031936647,
|
|
"num_tokens": 42489875.0,
|
|
"step": 19045
|
|
},
|
|
{
|
|
"entropy": 5.536298608779907,
|
|
"epoch": 2.139495703936654,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004549153067502768,
|
|
"loss": 5.3179,
|
|
"mean_token_accuracy": 0.18805031925439836,
|
|
"num_tokens": 42500946.0,
|
|
"step": 19050
|
|
},
|
|
{
|
|
"entropy": 5.467712688446045,
|
|
"epoch": 2.1400572808446117,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00045489119451778645,
|
|
"loss": 5.1996,
|
|
"mean_token_accuracy": 0.19779159426689147,
|
|
"num_tokens": 42511503.0,
|
|
"step": 19055
|
|
},
|
|
{
|
|
"entropy": 5.585913610458374,
|
|
"epoch": 2.1406188577525693,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004548670765574908,
|
|
"loss": 5.3816,
|
|
"mean_token_accuracy": 0.18621216118335723,
|
|
"num_tokens": 42523436.0,
|
|
"step": 19060
|
|
},
|
|
{
|
|
"entropy": 5.525981807708741,
|
|
"epoch": 2.1411804346605265,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.00045484295287015757,
|
|
"loss": 5.2927,
|
|
"mean_token_accuracy": 0.1896200805902481,
|
|
"num_tokens": 42534777.0,
|
|
"step": 19065
|
|
},
|
|
{
|
|
"entropy": 5.5501199722290036,
|
|
"epoch": 2.141742011568484,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004548188234565551,
|
|
"loss": 5.2539,
|
|
"mean_token_accuracy": 0.19365346133708955,
|
|
"num_tokens": 42545803.0,
|
|
"step": 19070
|
|
},
|
|
{
|
|
"entropy": 5.571218347549438,
|
|
"epoch": 2.142303588476442,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00045479468831745144,
|
|
"loss": 5.2811,
|
|
"mean_token_accuracy": 0.18831623047590257,
|
|
"num_tokens": 42556803.0,
|
|
"step": 19075
|
|
},
|
|
{
|
|
"entropy": 5.602970314025879,
|
|
"epoch": 2.1428651653843995,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004547705474536152,
|
|
"loss": 5.3413,
|
|
"mean_token_accuracy": 0.18605442792177201,
|
|
"num_tokens": 42568357.0,
|
|
"step": 19080
|
|
},
|
|
{
|
|
"entropy": 5.487061882019043,
|
|
"epoch": 2.1434267422923567,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00045474640086581506,
|
|
"loss": 5.2097,
|
|
"mean_token_accuracy": 0.19671832770109177,
|
|
"num_tokens": 42578990.0,
|
|
"step": 19085
|
|
},
|
|
{
|
|
"entropy": 5.529238843917847,
|
|
"epoch": 2.1439883192003144,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00045472224855481975,
|
|
"loss": 5.2819,
|
|
"mean_token_accuracy": 0.19358625262975693,
|
|
"num_tokens": 42589823.0,
|
|
"step": 19090
|
|
},
|
|
{
|
|
"entropy": 5.5032336711883545,
|
|
"epoch": 2.144549896108272,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00045469809052139844,
|
|
"loss": 5.2068,
|
|
"mean_token_accuracy": 0.1942850321531296,
|
|
"num_tokens": 42600508.0,
|
|
"step": 19095
|
|
},
|
|
{
|
|
"entropy": 5.481950139999389,
|
|
"epoch": 2.1451114730162297,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00045467392676632016,
|
|
"loss": 5.2492,
|
|
"mean_token_accuracy": 0.19504590183496476,
|
|
"num_tokens": 42611061.0,
|
|
"step": 19100
|
|
},
|
|
{
|
|
"entropy": 5.525798988342285,
|
|
"epoch": 2.145673049924187,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004546497572903543,
|
|
"loss": 5.2237,
|
|
"mean_token_accuracy": 0.19559953808784486,
|
|
"num_tokens": 42621936.0,
|
|
"step": 19105
|
|
},
|
|
{
|
|
"entropy": 5.520177984237671,
|
|
"epoch": 2.1462346268321446,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004546255820942706,
|
|
"loss": 5.2898,
|
|
"mean_token_accuracy": 0.19541528075933456,
|
|
"num_tokens": 42632880.0,
|
|
"step": 19110
|
|
},
|
|
{
|
|
"entropy": 5.521885728836059,
|
|
"epoch": 2.1467962037401023,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004546014011788386,
|
|
"loss": 5.174,
|
|
"mean_token_accuracy": 0.2015230044722557,
|
|
"num_tokens": 42642819.0,
|
|
"step": 19115
|
|
},
|
|
{
|
|
"entropy": 5.482599973678589,
|
|
"epoch": 2.14735778064806,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004545772145448284,
|
|
"loss": 5.2632,
|
|
"mean_token_accuracy": 0.19289801716804506,
|
|
"num_tokens": 42654581.0,
|
|
"step": 19120
|
|
},
|
|
{
|
|
"entropy": 5.525862836837769,
|
|
"epoch": 2.147919357556017,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00045455302219301,
|
|
"loss": 5.3143,
|
|
"mean_token_accuracy": 0.19050929099321365,
|
|
"num_tokens": 42665323.0,
|
|
"step": 19125
|
|
},
|
|
{
|
|
"entropy": 5.602271509170532,
|
|
"epoch": 2.148480934463975,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004545288241241538,
|
|
"loss": 5.3037,
|
|
"mean_token_accuracy": 0.19070056080818176,
|
|
"num_tokens": 42676465.0,
|
|
"step": 19130
|
|
},
|
|
{
|
|
"entropy": 5.487083911895752,
|
|
"epoch": 2.1490425113719325,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004545046203390302,
|
|
"loss": 5.2911,
|
|
"mean_token_accuracy": 0.19485869854688645,
|
|
"num_tokens": 42688242.0,
|
|
"step": 19135
|
|
},
|
|
{
|
|
"entropy": 5.505398273468018,
|
|
"epoch": 2.14960408827989,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00045448041083840973,
|
|
"loss": 5.2802,
|
|
"mean_token_accuracy": 0.19949985444545745,
|
|
"num_tokens": 42699498.0,
|
|
"step": 19140
|
|
},
|
|
{
|
|
"entropy": 5.571474504470825,
|
|
"epoch": 2.1501656651878474,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00045445619562306354,
|
|
"loss": 5.2712,
|
|
"mean_token_accuracy": 0.19473840445280075,
|
|
"num_tokens": 42710330.0,
|
|
"step": 19145
|
|
},
|
|
{
|
|
"entropy": 5.4964793682098385,
|
|
"epoch": 2.150727242095805,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00045443197469376243,
|
|
"loss": 5.2784,
|
|
"mean_token_accuracy": 0.19105039834976195,
|
|
"num_tokens": 42721210.0,
|
|
"step": 19150
|
|
},
|
|
{
|
|
"entropy": 5.545171403884888,
|
|
"epoch": 2.1512888190037627,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004544077480512776,
|
|
"loss": 5.2683,
|
|
"mean_token_accuracy": 0.1932425916194916,
|
|
"num_tokens": 42732272.0,
|
|
"step": 19155
|
|
},
|
|
{
|
|
"entropy": 5.666682529449463,
|
|
"epoch": 2.15185039591172,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00045438351569638055,
|
|
"loss": 5.3999,
|
|
"mean_token_accuracy": 0.18227856308221818,
|
|
"num_tokens": 42745737.0,
|
|
"step": 19160
|
|
},
|
|
{
|
|
"entropy": 5.538751029968262,
|
|
"epoch": 2.1524119728196776,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00045435927762984277,
|
|
"loss": 5.2754,
|
|
"mean_token_accuracy": 0.19352304339408874,
|
|
"num_tokens": 42756405.0,
|
|
"step": 19165
|
|
},
|
|
{
|
|
"entropy": 5.544000720977783,
|
|
"epoch": 2.152973549727635,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000454335033852436,
|
|
"loss": 5.2795,
|
|
"mean_token_accuracy": 0.1869244635105133,
|
|
"num_tokens": 42767991.0,
|
|
"step": 19170
|
|
},
|
|
{
|
|
"entropy": 5.5490223407745365,
|
|
"epoch": 2.153535126635593,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004543107843649322,
|
|
"loss": 5.3411,
|
|
"mean_token_accuracy": 0.1835654318332672,
|
|
"num_tokens": 42779177.0,
|
|
"step": 19175
|
|
},
|
|
{
|
|
"entropy": 5.48776159286499,
|
|
"epoch": 2.15409670354355,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004542865291681035,
|
|
"loss": 5.2396,
|
|
"mean_token_accuracy": 0.2039228767156601,
|
|
"num_tokens": 42789748.0,
|
|
"step": 19180
|
|
},
|
|
{
|
|
"entropy": 5.585640907287598,
|
|
"epoch": 2.1546582804515078,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00045426226826272213,
|
|
"loss": 5.3021,
|
|
"mean_token_accuracy": 0.19389602839946746,
|
|
"num_tokens": 42802741.0,
|
|
"step": 19185
|
|
},
|
|
{
|
|
"entropy": 5.556554841995239,
|
|
"epoch": 2.1552198573594654,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004542380016495607,
|
|
"loss": 5.2857,
|
|
"mean_token_accuracy": 0.18895589113235473,
|
|
"num_tokens": 42813091.0,
|
|
"step": 19190
|
|
},
|
|
{
|
|
"entropy": 5.544634866714477,
|
|
"epoch": 2.155781434267423,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00045421372932939177,
|
|
"loss": 5.2909,
|
|
"mean_token_accuracy": 0.1943572133779526,
|
|
"num_tokens": 42823711.0,
|
|
"step": 19195
|
|
},
|
|
{
|
|
"entropy": 5.430270099639893,
|
|
"epoch": 2.1563430111753803,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004541894513029881,
|
|
"loss": 5.2306,
|
|
"mean_token_accuracy": 0.17984076887369155,
|
|
"num_tokens": 42835057.0,
|
|
"step": 19200
|
|
},
|
|
{
|
|
"entropy": 5.62523398399353,
|
|
"epoch": 2.156904588083338,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00045416516757112286,
|
|
"loss": 5.3007,
|
|
"mean_token_accuracy": 0.19330391734838487,
|
|
"num_tokens": 42846784.0,
|
|
"step": 19205
|
|
},
|
|
{
|
|
"entropy": 5.54594054222107,
|
|
"epoch": 2.1574661649912956,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00045414087813456925,
|
|
"loss": 5.2205,
|
|
"mean_token_accuracy": 0.19698640555143357,
|
|
"num_tokens": 42857618.0,
|
|
"step": 19210
|
|
},
|
|
{
|
|
"entropy": 5.509330224990845,
|
|
"epoch": 2.1580277418992533,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004541165829941006,
|
|
"loss": 5.2704,
|
|
"mean_token_accuracy": 0.1926967903971672,
|
|
"num_tokens": 42869076.0,
|
|
"step": 19215
|
|
},
|
|
{
|
|
"entropy": 5.469746065139771,
|
|
"epoch": 2.1585893188072105,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004540922821504904,
|
|
"loss": 5.2445,
|
|
"mean_token_accuracy": 0.19599961191415788,
|
|
"num_tokens": 42879714.0,
|
|
"step": 19220
|
|
},
|
|
{
|
|
"entropy": 5.562300205230713,
|
|
"epoch": 2.159150895715168,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004540679756045125,
|
|
"loss": 5.2632,
|
|
"mean_token_accuracy": 0.19898033887147903,
|
|
"num_tokens": 42890187.0,
|
|
"step": 19225
|
|
},
|
|
{
|
|
"entropy": 5.476594686508179,
|
|
"epoch": 2.159712472623126,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004540436633569407,
|
|
"loss": 5.212,
|
|
"mean_token_accuracy": 0.195633165538311,
|
|
"num_tokens": 42900713.0,
|
|
"step": 19230
|
|
},
|
|
{
|
|
"entropy": 5.4860940933227536,
|
|
"epoch": 2.1602740495310835,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.00045401934540854937,
|
|
"loss": 5.2614,
|
|
"mean_token_accuracy": 0.19223775267601012,
|
|
"num_tokens": 42911703.0,
|
|
"step": 19235
|
|
},
|
|
{
|
|
"entropy": 5.465535259246826,
|
|
"epoch": 2.1608356264390407,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004539950217601127,
|
|
"loss": 5.2205,
|
|
"mean_token_accuracy": 0.19699688851833344,
|
|
"num_tokens": 42922684.0,
|
|
"step": 19240
|
|
},
|
|
{
|
|
"entropy": 5.531664657592773,
|
|
"epoch": 2.1613972033469984,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00045397069241240497,
|
|
"loss": 5.2297,
|
|
"mean_token_accuracy": 0.19130341410636903,
|
|
"num_tokens": 42933095.0,
|
|
"step": 19245
|
|
},
|
|
{
|
|
"entropy": 5.508335542678833,
|
|
"epoch": 2.161958780254956,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000453946357366201,
|
|
"loss": 5.3344,
|
|
"mean_token_accuracy": 0.19552526026964187,
|
|
"num_tokens": 42944508.0,
|
|
"step": 19250
|
|
},
|
|
{
|
|
"entropy": 5.432960367202758,
|
|
"epoch": 2.1625203571629132,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00045392201662227565,
|
|
"loss": 5.1937,
|
|
"mean_token_accuracy": 0.20042930394411088,
|
|
"num_tokens": 42954902.0,
|
|
"step": 19255
|
|
},
|
|
{
|
|
"entropy": 5.507016992568969,
|
|
"epoch": 2.163081934070871,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00045389767018140395,
|
|
"loss": 5.1887,
|
|
"mean_token_accuracy": 0.19380445778369904,
|
|
"num_tokens": 42965165.0,
|
|
"step": 19260
|
|
},
|
|
{
|
|
"entropy": 5.495782041549683,
|
|
"epoch": 2.1636435109788286,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.00045387331804436096,
|
|
"loss": 5.2073,
|
|
"mean_token_accuracy": 0.1978279322385788,
|
|
"num_tokens": 42975025.0,
|
|
"step": 19265
|
|
},
|
|
{
|
|
"entropy": 5.5999737739562985,
|
|
"epoch": 2.1642050878867862,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004538489602119222,
|
|
"loss": 5.3737,
|
|
"mean_token_accuracy": 0.1898595005273819,
|
|
"num_tokens": 42986666.0,
|
|
"step": 19270
|
|
},
|
|
{
|
|
"entropy": 5.559444284439087,
|
|
"epoch": 2.1647666647947434,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004538245966848632,
|
|
"loss": 5.3116,
|
|
"mean_token_accuracy": 0.1925888329744339,
|
|
"num_tokens": 42998607.0,
|
|
"step": 19275
|
|
},
|
|
{
|
|
"entropy": 5.489432144165039,
|
|
"epoch": 2.165328241702701,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00045380022746395953,
|
|
"loss": 5.2562,
|
|
"mean_token_accuracy": 0.1940259099006653,
|
|
"num_tokens": 43009969.0,
|
|
"step": 19280
|
|
},
|
|
{
|
|
"entropy": 5.631491947174072,
|
|
"epoch": 2.1658898186106588,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00045377585254998743,
|
|
"loss": 5.4061,
|
|
"mean_token_accuracy": 0.18729043006896973,
|
|
"num_tokens": 43023255.0,
|
|
"step": 19285
|
|
},
|
|
{
|
|
"entropy": 5.515974521636963,
|
|
"epoch": 2.1664513955186164,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004537514719437228,
|
|
"loss": 5.2342,
|
|
"mean_token_accuracy": 0.19376095682382583,
|
|
"num_tokens": 43033995.0,
|
|
"step": 19290
|
|
},
|
|
{
|
|
"entropy": 5.524006271362305,
|
|
"epoch": 2.1670129724265736,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00045372708564594196,
|
|
"loss": 5.3422,
|
|
"mean_token_accuracy": 0.18745407909154893,
|
|
"num_tokens": 43046239.0,
|
|
"step": 19295
|
|
},
|
|
{
|
|
"entropy": 5.482912874221801,
|
|
"epoch": 2.1675745493345313,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00045370269365742143,
|
|
"loss": 5.2212,
|
|
"mean_token_accuracy": 0.19853470623493194,
|
|
"num_tokens": 43057262.0,
|
|
"step": 19300
|
|
},
|
|
{
|
|
"entropy": 5.552854442596436,
|
|
"epoch": 2.168136126242489,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.00045367829597893776,
|
|
"loss": 5.3334,
|
|
"mean_token_accuracy": 0.1878657042980194,
|
|
"num_tokens": 43068495.0,
|
|
"step": 19305
|
|
},
|
|
{
|
|
"entropy": 5.47726035118103,
|
|
"epoch": 2.1686977031504466,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00045365389261126793,
|
|
"loss": 5.2281,
|
|
"mean_token_accuracy": 0.19548221826553344,
|
|
"num_tokens": 43080706.0,
|
|
"step": 19310
|
|
},
|
|
{
|
|
"entropy": 5.40993070602417,
|
|
"epoch": 2.169259280058404,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00045362948355518883,
|
|
"loss": 5.2152,
|
|
"mean_token_accuracy": 0.2017691984772682,
|
|
"num_tokens": 43091444.0,
|
|
"step": 19315
|
|
},
|
|
{
|
|
"entropy": 5.591124582290649,
|
|
"epoch": 2.1698208569663615,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004536050688114777,
|
|
"loss": 5.3168,
|
|
"mean_token_accuracy": 0.18960983604192733,
|
|
"num_tokens": 43103648.0,
|
|
"step": 19320
|
|
},
|
|
{
|
|
"entropy": 5.622720718383789,
|
|
"epoch": 2.170382433874319,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00045358064838091187,
|
|
"loss": 5.3027,
|
|
"mean_token_accuracy": 0.1937421292066574,
|
|
"num_tokens": 43116183.0,
|
|
"step": 19325
|
|
},
|
|
{
|
|
"entropy": 5.513739442825317,
|
|
"epoch": 2.170944010782277,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00045355622226426903,
|
|
"loss": 5.2599,
|
|
"mean_token_accuracy": 0.19330281019210815,
|
|
"num_tokens": 43126557.0,
|
|
"step": 19330
|
|
},
|
|
{
|
|
"entropy": 5.492511558532715,
|
|
"epoch": 2.171505587690234,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00045353179046232674,
|
|
"loss": 5.2923,
|
|
"mean_token_accuracy": 0.18933189362287522,
|
|
"num_tokens": 43137753.0,
|
|
"step": 19335
|
|
},
|
|
{
|
|
"entropy": 5.576199960708618,
|
|
"epoch": 2.1720671645981917,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.000453507352975863,
|
|
"loss": 5.3037,
|
|
"mean_token_accuracy": 0.19113630056381226,
|
|
"num_tokens": 43148461.0,
|
|
"step": 19340
|
|
},
|
|
{
|
|
"entropy": 5.485734653472901,
|
|
"epoch": 2.1726287415061494,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00045348290980565595,
|
|
"loss": 5.2074,
|
|
"mean_token_accuracy": 0.19547132551670074,
|
|
"num_tokens": 43161174.0,
|
|
"step": 19345
|
|
},
|
|
{
|
|
"entropy": 5.534107446670532,
|
|
"epoch": 2.1731903184141066,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00045345846095248376,
|
|
"loss": 5.3086,
|
|
"mean_token_accuracy": 0.18765278458595275,
|
|
"num_tokens": 43172844.0,
|
|
"step": 19350
|
|
},
|
|
{
|
|
"entropy": 5.435306215286255,
|
|
"epoch": 2.1737518953220643,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00045343400641712503,
|
|
"loss": 5.1853,
|
|
"mean_token_accuracy": 0.19814585745334626,
|
|
"num_tokens": 43183476.0,
|
|
"step": 19355
|
|
},
|
|
{
|
|
"entropy": 5.5760307788848875,
|
|
"epoch": 2.174313472230022,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00045340954620035827,
|
|
"loss": 5.2708,
|
|
"mean_token_accuracy": 0.18906071782112122,
|
|
"num_tokens": 43195563.0,
|
|
"step": 19360
|
|
},
|
|
{
|
|
"entropy": 5.560254907608032,
|
|
"epoch": 2.1748750491379796,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.00045338508030296246,
|
|
"loss": 5.3118,
|
|
"mean_token_accuracy": 0.19427053928375243,
|
|
"num_tokens": 43206067.0,
|
|
"step": 19365
|
|
},
|
|
{
|
|
"entropy": 5.569857263565064,
|
|
"epoch": 2.175436626045937,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00045336060872571646,
|
|
"loss": 5.2062,
|
|
"mean_token_accuracy": 0.20014894902706146,
|
|
"num_tokens": 43216912.0,
|
|
"step": 19370
|
|
},
|
|
{
|
|
"entropy": 5.59420075416565,
|
|
"epoch": 2.1759982029538945,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004533361314693994,
|
|
"loss": 5.262,
|
|
"mean_token_accuracy": 0.19414740800857544,
|
|
"num_tokens": 43228746.0,
|
|
"step": 19375
|
|
},
|
|
{
|
|
"entropy": 5.496267700195313,
|
|
"epoch": 2.176559779861852,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00045331164853479084,
|
|
"loss": 5.2727,
|
|
"mean_token_accuracy": 0.18966237902641297,
|
|
"num_tokens": 43241228.0,
|
|
"step": 19380
|
|
},
|
|
{
|
|
"entropy": 5.47652006149292,
|
|
"epoch": 2.17712135676981,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00045328715992267024,
|
|
"loss": 5.3169,
|
|
"mean_token_accuracy": 0.19196716099977493,
|
|
"num_tokens": 43252916.0,
|
|
"step": 19385
|
|
},
|
|
{
|
|
"entropy": 5.528986120223999,
|
|
"epoch": 2.177682933677767,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00045326266563381734,
|
|
"loss": 5.1475,
|
|
"mean_token_accuracy": 0.20205250829458238,
|
|
"num_tokens": 43264357.0,
|
|
"step": 19390
|
|
},
|
|
{
|
|
"entropy": 5.483857774734497,
|
|
"epoch": 2.1782445105857247,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00045323816566901205,
|
|
"loss": 5.2905,
|
|
"mean_token_accuracy": 0.19976740777492524,
|
|
"num_tokens": 43274547.0,
|
|
"step": 19395
|
|
},
|
|
{
|
|
"entropy": 5.432673501968384,
|
|
"epoch": 2.1788060874936823,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004532136600290343,
|
|
"loss": 5.1778,
|
|
"mean_token_accuracy": 0.1993179976940155,
|
|
"num_tokens": 43284225.0,
|
|
"step": 19400
|
|
},
|
|
{
|
|
"entropy": 5.515079498291016,
|
|
"epoch": 2.17936766440164,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004531891487146646,
|
|
"loss": 5.2657,
|
|
"mean_token_accuracy": 0.19107242226600646,
|
|
"num_tokens": 43295218.0,
|
|
"step": 19405
|
|
},
|
|
{
|
|
"entropy": 5.449270248413086,
|
|
"epoch": 2.179929241309597,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004531646317266833,
|
|
"loss": 5.2055,
|
|
"mean_token_accuracy": 0.19958023428916932,
|
|
"num_tokens": 43305169.0,
|
|
"step": 19410
|
|
},
|
|
{
|
|
"entropy": 5.487324333190918,
|
|
"epoch": 2.180490818217555,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00045314010906587096,
|
|
"loss": 5.1992,
|
|
"mean_token_accuracy": 0.19760687202215194,
|
|
"num_tokens": 43317119.0,
|
|
"step": 19415
|
|
},
|
|
{
|
|
"entropy": 5.540035152435303,
|
|
"epoch": 2.1810523951255125,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00045311558073300853,
|
|
"loss": 5.2468,
|
|
"mean_token_accuracy": 0.19819342941045762,
|
|
"num_tokens": 43327800.0,
|
|
"step": 19420
|
|
},
|
|
{
|
|
"entropy": 5.427812194824218,
|
|
"epoch": 2.18161397203347,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004530910467288769,
|
|
"loss": 5.167,
|
|
"mean_token_accuracy": 0.19073342978954316,
|
|
"num_tokens": 43338607.0,
|
|
"step": 19425
|
|
},
|
|
{
|
|
"entropy": 5.5063619136810305,
|
|
"epoch": 2.1821755489414274,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.00045306650705425727,
|
|
"loss": 5.2748,
|
|
"mean_token_accuracy": 0.2007783278822899,
|
|
"num_tokens": 43350621.0,
|
|
"step": 19430
|
|
},
|
|
{
|
|
"entropy": 5.451795053482056,
|
|
"epoch": 2.182737125849385,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00045304196170993093,
|
|
"loss": 5.2293,
|
|
"mean_token_accuracy": 0.19908606112003327,
|
|
"num_tokens": 43360327.0,
|
|
"step": 19435
|
|
},
|
|
{
|
|
"entropy": 5.433092975616455,
|
|
"epoch": 2.1832987027573427,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004530174106966795,
|
|
"loss": 5.2496,
|
|
"mean_token_accuracy": 0.19363509863615036,
|
|
"num_tokens": 43371538.0,
|
|
"step": 19440
|
|
},
|
|
{
|
|
"entropy": 5.579623603820801,
|
|
"epoch": 2.1838602796653,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.00045299285401528475,
|
|
"loss": 5.2938,
|
|
"mean_token_accuracy": 0.1886764571070671,
|
|
"num_tokens": 43381818.0,
|
|
"step": 19445
|
|
},
|
|
{
|
|
"entropy": 5.508121538162231,
|
|
"epoch": 2.1844218565732576,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004529682916665285,
|
|
"loss": 5.2413,
|
|
"mean_token_accuracy": 0.18868270218372346,
|
|
"num_tokens": 43391977.0,
|
|
"step": 19450
|
|
},
|
|
{
|
|
"entropy": 5.557366466522216,
|
|
"epoch": 2.1849834334812153,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00045294372365119276,
|
|
"loss": 5.2948,
|
|
"mean_token_accuracy": 0.19008123278617858,
|
|
"num_tokens": 43403657.0,
|
|
"step": 19455
|
|
},
|
|
{
|
|
"entropy": 5.4605669498443605,
|
|
"epoch": 2.185545010389173,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004529191499700598,
|
|
"loss": 5.1872,
|
|
"mean_token_accuracy": 0.1950461596250534,
|
|
"num_tokens": 43414325.0,
|
|
"step": 19460
|
|
},
|
|
{
|
|
"entropy": 5.612634515762329,
|
|
"epoch": 2.18610658729713,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004528945706239122,
|
|
"loss": 5.3737,
|
|
"mean_token_accuracy": 0.1871746674180031,
|
|
"num_tokens": 43425864.0,
|
|
"step": 19465
|
|
},
|
|
{
|
|
"entropy": 5.569682264328003,
|
|
"epoch": 2.186668164205088,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00045286998561353236,
|
|
"loss": 5.2945,
|
|
"mean_token_accuracy": 0.19014448523521424,
|
|
"num_tokens": 43437135.0,
|
|
"step": 19470
|
|
},
|
|
{
|
|
"entropy": 5.616008567810058,
|
|
"epoch": 2.1872297411130455,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004528453949397033,
|
|
"loss": 5.3293,
|
|
"mean_token_accuracy": 0.19414877742528916,
|
|
"num_tokens": 43448603.0,
|
|
"step": 19475
|
|
},
|
|
{
|
|
"entropy": 5.4768781661987305,
|
|
"epoch": 2.187791318021003,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00045282079860320786,
|
|
"loss": 5.1723,
|
|
"mean_token_accuracy": 0.20090740621089936,
|
|
"num_tokens": 43460316.0,
|
|
"step": 19480
|
|
},
|
|
{
|
|
"entropy": 5.444617891311646,
|
|
"epoch": 2.1883528949289603,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00045279619660482925,
|
|
"loss": 5.24,
|
|
"mean_token_accuracy": 0.19947486370801926,
|
|
"num_tokens": 43471869.0,
|
|
"step": 19485
|
|
},
|
|
{
|
|
"entropy": 5.498412704467773,
|
|
"epoch": 2.188914471836918,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00045277158894535075,
|
|
"loss": 5.3088,
|
|
"mean_token_accuracy": 0.19135208129882814,
|
|
"num_tokens": 43484004.0,
|
|
"step": 19490
|
|
},
|
|
{
|
|
"entropy": 5.5440808773040775,
|
|
"epoch": 2.1894760487448757,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00045274697562555584,
|
|
"loss": 5.2708,
|
|
"mean_token_accuracy": 0.19465432912111283,
|
|
"num_tokens": 43494401.0,
|
|
"step": 19495
|
|
},
|
|
{
|
|
"entropy": 5.435019683837891,
|
|
"epoch": 2.1900376256528333,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004527223566462284,
|
|
"loss": 5.2078,
|
|
"mean_token_accuracy": 0.19536787867546082,
|
|
"num_tokens": 43505437.0,
|
|
"step": 19500
|
|
},
|
|
{
|
|
"entropy": 5.445728874206543,
|
|
"epoch": 2.1905992025607905,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004526977320081522,
|
|
"loss": 5.1652,
|
|
"mean_token_accuracy": 0.2000671371817589,
|
|
"num_tokens": 43516177.0,
|
|
"step": 19505
|
|
},
|
|
{
|
|
"entropy": 5.536247062683105,
|
|
"epoch": 2.191160779468748,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004526731017121111,
|
|
"loss": 5.249,
|
|
"mean_token_accuracy": 0.19590997099876403,
|
|
"num_tokens": 43527070.0,
|
|
"step": 19510
|
|
},
|
|
{
|
|
"entropy": 5.512525987625122,
|
|
"epoch": 2.191722356376706,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00045264846575888973,
|
|
"loss": 5.2887,
|
|
"mean_token_accuracy": 0.19077699780464172,
|
|
"num_tokens": 43538247.0,
|
|
"step": 19515
|
|
},
|
|
{
|
|
"entropy": 5.5083921432495115,
|
|
"epoch": 2.1922839332846635,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00045262382414927235,
|
|
"loss": 5.2159,
|
|
"mean_token_accuracy": 0.19949048310518264,
|
|
"num_tokens": 43549994.0,
|
|
"step": 19520
|
|
},
|
|
{
|
|
"entropy": 5.587218761444092,
|
|
"epoch": 2.1928455101926208,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00045259917688404336,
|
|
"loss": 5.3478,
|
|
"mean_token_accuracy": 0.18835411220788956,
|
|
"num_tokens": 43562171.0,
|
|
"step": 19525
|
|
},
|
|
{
|
|
"entropy": 5.538046073913574,
|
|
"epoch": 2.1934070871005784,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004525745239639877,
|
|
"loss": 5.2338,
|
|
"mean_token_accuracy": 0.1900772526860237,
|
|
"num_tokens": 43572308.0,
|
|
"step": 19530
|
|
},
|
|
{
|
|
"entropy": 5.439638900756836,
|
|
"epoch": 2.193968664008536,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00045254986538989045,
|
|
"loss": 5.2285,
|
|
"mean_token_accuracy": 0.1969294786453247,
|
|
"num_tokens": 43583565.0,
|
|
"step": 19535
|
|
},
|
|
{
|
|
"entropy": 5.52717399597168,
|
|
"epoch": 2.1945302409164933,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004525252011625366,
|
|
"loss": 5.3539,
|
|
"mean_token_accuracy": 0.19046106040477753,
|
|
"num_tokens": 43595921.0,
|
|
"step": 19540
|
|
},
|
|
{
|
|
"entropy": 5.534983587265015,
|
|
"epoch": 2.195091817824451,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004525005312827114,
|
|
"loss": 5.2135,
|
|
"mean_token_accuracy": 0.1939015194773674,
|
|
"num_tokens": 43606957.0,
|
|
"step": 19545
|
|
},
|
|
{
|
|
"entropy": 5.460388612747193,
|
|
"epoch": 2.1956533947324086,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004524758557512005,
|
|
"loss": 5.1451,
|
|
"mean_token_accuracy": 0.1989664301276207,
|
|
"num_tokens": 43616983.0,
|
|
"step": 19550
|
|
},
|
|
{
|
|
"entropy": 5.371473550796509,
|
|
"epoch": 2.1962149716403663,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004524511745687895,
|
|
"loss": 5.0985,
|
|
"mean_token_accuracy": 0.20401592552661896,
|
|
"num_tokens": 43626951.0,
|
|
"step": 19555
|
|
},
|
|
{
|
|
"entropy": 5.467970275878907,
|
|
"epoch": 2.1967765485483235,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004524264877362643,
|
|
"loss": 5.2212,
|
|
"mean_token_accuracy": 0.19011069536209108,
|
|
"num_tokens": 43638446.0,
|
|
"step": 19560
|
|
},
|
|
{
|
|
"entropy": 5.563729953765869,
|
|
"epoch": 2.197338125456281,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00045240179525441094,
|
|
"loss": 5.298,
|
|
"mean_token_accuracy": 0.19505397528409957,
|
|
"num_tokens": 43649646.0,
|
|
"step": 19565
|
|
},
|
|
{
|
|
"entropy": 5.522436189651489,
|
|
"epoch": 2.197899702364239,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004523770971240156,
|
|
"loss": 5.3053,
|
|
"mean_token_accuracy": 0.1905547097325325,
|
|
"num_tokens": 43661633.0,
|
|
"step": 19570
|
|
},
|
|
{
|
|
"entropy": 5.519252109527588,
|
|
"epoch": 2.1984612792721965,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004523523933458647,
|
|
"loss": 5.2681,
|
|
"mean_token_accuracy": 0.19578531235456467,
|
|
"num_tokens": 43672671.0,
|
|
"step": 19575
|
|
},
|
|
{
|
|
"entropy": 5.544933891296386,
|
|
"epoch": 2.1990228561801537,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004523276839207448,
|
|
"loss": 5.2544,
|
|
"mean_token_accuracy": 0.1938066765666008,
|
|
"num_tokens": 43683426.0,
|
|
"step": 19580
|
|
},
|
|
{
|
|
"entropy": 5.501959133148193,
|
|
"epoch": 2.1995844330881114,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00045230296884944264,
|
|
"loss": 5.3057,
|
|
"mean_token_accuracy": 0.19192762821912765,
|
|
"num_tokens": 43694460.0,
|
|
"step": 19585
|
|
},
|
|
{
|
|
"entropy": 5.433472204208374,
|
|
"epoch": 2.200146009996069,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00045227824813274517,
|
|
"loss": 5.1042,
|
|
"mean_token_accuracy": 0.19947481900453568,
|
|
"num_tokens": 43706047.0,
|
|
"step": 19590
|
|
},
|
|
{
|
|
"entropy": 5.42898736000061,
|
|
"epoch": 2.2007075869040267,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004522535217714396,
|
|
"loss": 5.2102,
|
|
"mean_token_accuracy": 0.19789150953292847,
|
|
"num_tokens": 43715879.0,
|
|
"step": 19595
|
|
},
|
|
{
|
|
"entropy": 5.480247116088867,
|
|
"epoch": 2.201269163811984,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004522287897663131,
|
|
"loss": 5.2518,
|
|
"mean_token_accuracy": 0.1936460942029953,
|
|
"num_tokens": 43726870.0,
|
|
"step": 19600
|
|
},
|
|
{
|
|
"entropy": 5.516616773605347,
|
|
"epoch": 2.2018307407199416,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00045220405211815327,
|
|
"loss": 5.2939,
|
|
"mean_token_accuracy": 0.18914685398340225,
|
|
"num_tokens": 43739116.0,
|
|
"step": 19605
|
|
},
|
|
{
|
|
"entropy": 5.528266954421997,
|
|
"epoch": 2.202392317627899,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.00045217930882774754,
|
|
"loss": 5.2623,
|
|
"mean_token_accuracy": 0.19535401314496995,
|
|
"num_tokens": 43750239.0,
|
|
"step": 19610
|
|
},
|
|
{
|
|
"entropy": 5.587613439559936,
|
|
"epoch": 2.202953894535857,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00045215455989588396,
|
|
"loss": 5.3587,
|
|
"mean_token_accuracy": 0.19037794768810273,
|
|
"num_tokens": 43762391.0,
|
|
"step": 19615
|
|
},
|
|
{
|
|
"entropy": 5.461773538589478,
|
|
"epoch": 2.203515471443814,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00045212980532335055,
|
|
"loss": 5.2609,
|
|
"mean_token_accuracy": 0.19787550270557402,
|
|
"num_tokens": 43773514.0,
|
|
"step": 19620
|
|
},
|
|
{
|
|
"entropy": 5.482375383377075,
|
|
"epoch": 2.2040770483517718,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00045210504511093534,
|
|
"loss": 5.2409,
|
|
"mean_token_accuracy": 0.18991211652755738,
|
|
"num_tokens": 43784617.0,
|
|
"step": 19625
|
|
},
|
|
{
|
|
"entropy": 5.592576026916504,
|
|
"epoch": 2.2046386252597294,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004520802792594269,
|
|
"loss": 5.3333,
|
|
"mean_token_accuracy": 0.19061177223920822,
|
|
"num_tokens": 43795396.0,
|
|
"step": 19630
|
|
},
|
|
{
|
|
"entropy": 5.5489280223846436,
|
|
"epoch": 2.2052002021676866,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00045205550776961366,
|
|
"loss": 5.2761,
|
|
"mean_token_accuracy": 0.18839634358882903,
|
|
"num_tokens": 43805512.0,
|
|
"step": 19635
|
|
},
|
|
{
|
|
"entropy": 5.564304447174072,
|
|
"epoch": 2.2057617790756443,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004520307306422844,
|
|
"loss": 5.3972,
|
|
"mean_token_accuracy": 0.1884940579533577,
|
|
"num_tokens": 43815874.0,
|
|
"step": 19640
|
|
},
|
|
{
|
|
"entropy": 5.5941956520080565,
|
|
"epoch": 2.206323355983602,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00045200594787822795,
|
|
"loss": 5.3185,
|
|
"mean_token_accuracy": 0.18378949761390687,
|
|
"num_tokens": 43827948.0,
|
|
"step": 19645
|
|
},
|
|
{
|
|
"entropy": 5.535559368133545,
|
|
"epoch": 2.2068849328915596,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004519811594782335,
|
|
"loss": 5.1839,
|
|
"mean_token_accuracy": 0.19542222768068312,
|
|
"num_tokens": 43838306.0,
|
|
"step": 19650
|
|
},
|
|
{
|
|
"entropy": 5.485494756698609,
|
|
"epoch": 2.207446509799517,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00045195636544309033,
|
|
"loss": 5.2243,
|
|
"mean_token_accuracy": 0.19710462540388107,
|
|
"num_tokens": 43848716.0,
|
|
"step": 19655
|
|
},
|
|
{
|
|
"entropy": 5.551632356643677,
|
|
"epoch": 2.2080080867074745,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00045193156577358784,
|
|
"loss": 5.3156,
|
|
"mean_token_accuracy": 0.19411621540784835,
|
|
"num_tokens": 43859707.0,
|
|
"step": 19660
|
|
},
|
|
{
|
|
"entropy": 5.48183274269104,
|
|
"epoch": 2.208569663615432,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004519067604705157,
|
|
"loss": 5.1787,
|
|
"mean_token_accuracy": 0.20226583778858184,
|
|
"num_tokens": 43870599.0,
|
|
"step": 19665
|
|
},
|
|
{
|
|
"entropy": 5.541427850723267,
|
|
"epoch": 2.20913124052339,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00045188194953466363,
|
|
"loss": 5.2715,
|
|
"mean_token_accuracy": 0.19070045202970504,
|
|
"num_tokens": 43881843.0,
|
|
"step": 19670
|
|
},
|
|
{
|
|
"entropy": 5.483605813980103,
|
|
"epoch": 2.209692817431347,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00045185713296682175,
|
|
"loss": 5.164,
|
|
"mean_token_accuracy": 0.1961521476507187,
|
|
"num_tokens": 43892206.0,
|
|
"step": 19675
|
|
},
|
|
{
|
|
"entropy": 5.513283586502075,
|
|
"epoch": 2.2102543943393047,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00045183231076778005,
|
|
"loss": 5.2411,
|
|
"mean_token_accuracy": 0.19523411244153976,
|
|
"num_tokens": 43905255.0,
|
|
"step": 19680
|
|
},
|
|
{
|
|
"entropy": 5.473288345336914,
|
|
"epoch": 2.2108159712472624,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00045180748293832906,
|
|
"loss": 5.3078,
|
|
"mean_token_accuracy": 0.18868002742528917,
|
|
"num_tokens": 43917774.0,
|
|
"step": 19685
|
|
},
|
|
{
|
|
"entropy": 5.468965673446656,
|
|
"epoch": 2.21137754815522,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00045178264947925924,
|
|
"loss": 5.2187,
|
|
"mean_token_accuracy": 0.20265576839447022,
|
|
"num_tokens": 43929127.0,
|
|
"step": 19690
|
|
},
|
|
{
|
|
"entropy": 5.583199739456177,
|
|
"epoch": 2.2119391250631772,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00045175781039136133,
|
|
"loss": 5.2709,
|
|
"mean_token_accuracy": 0.18844543993473054,
|
|
"num_tokens": 43942558.0,
|
|
"step": 19695
|
|
},
|
|
{
|
|
"entropy": 5.471088981628418,
|
|
"epoch": 2.212500701971135,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004517329656754261,
|
|
"loss": 5.2716,
|
|
"mean_token_accuracy": 0.1902107387781143,
|
|
"num_tokens": 43952966.0,
|
|
"step": 19700
|
|
},
|
|
{
|
|
"entropy": 5.564641714096069,
|
|
"epoch": 2.2130622788790926,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004517081153322448,
|
|
"loss": 5.2755,
|
|
"mean_token_accuracy": 0.19167562574148178,
|
|
"num_tokens": 43964725.0,
|
|
"step": 19705
|
|
},
|
|
{
|
|
"entropy": 5.51898226737976,
|
|
"epoch": 2.2136238557870502,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004516832593626085,
|
|
"loss": 5.1585,
|
|
"mean_token_accuracy": 0.2001033678650856,
|
|
"num_tokens": 43976356.0,
|
|
"step": 19710
|
|
},
|
|
{
|
|
"entropy": 5.399066019058227,
|
|
"epoch": 2.2141854326950074,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004516583977673087,
|
|
"loss": 5.2039,
|
|
"mean_token_accuracy": 0.1964070677757263,
|
|
"num_tokens": 43987732.0,
|
|
"step": 19715
|
|
},
|
|
{
|
|
"entropy": 5.535548686981201,
|
|
"epoch": 2.214747009602965,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00045163353054713704,
|
|
"loss": 5.3434,
|
|
"mean_token_accuracy": 0.18696456402540207,
|
|
"num_tokens": 43998701.0,
|
|
"step": 19720
|
|
},
|
|
{
|
|
"entropy": 5.634602832794189,
|
|
"epoch": 2.2153085865109228,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004516086577028852,
|
|
"loss": 5.2706,
|
|
"mean_token_accuracy": 0.1942870184779167,
|
|
"num_tokens": 44008978.0,
|
|
"step": 19725
|
|
},
|
|
{
|
|
"entropy": 5.499393081665039,
|
|
"epoch": 2.21587016341888,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004515837792353453,
|
|
"loss": 5.2563,
|
|
"mean_token_accuracy": 0.19361717849969864,
|
|
"num_tokens": 44018928.0,
|
|
"step": 19730
|
|
},
|
|
{
|
|
"entropy": 5.452484560012818,
|
|
"epoch": 2.2164317403268377,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004515588951453093,
|
|
"loss": 5.2428,
|
|
"mean_token_accuracy": 0.1916105180978775,
|
|
"num_tokens": 44030044.0,
|
|
"step": 19735
|
|
},
|
|
{
|
|
"entropy": 5.396527433395386,
|
|
"epoch": 2.2169933172347953,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004515340054335696,
|
|
"loss": 5.1809,
|
|
"mean_token_accuracy": 0.19517827033996582,
|
|
"num_tokens": 44041851.0,
|
|
"step": 19740
|
|
},
|
|
{
|
|
"entropy": 5.490589284896851,
|
|
"epoch": 2.217554894142753,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004515091101009188,
|
|
"loss": 5.1613,
|
|
"mean_token_accuracy": 0.19913836121559142,
|
|
"num_tokens": 44051871.0,
|
|
"step": 19745
|
|
},
|
|
{
|
|
"entropy": 5.524836778640747,
|
|
"epoch": 2.21811647105071,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004514842091481493,
|
|
"loss": 5.3633,
|
|
"mean_token_accuracy": 0.18144014328718186,
|
|
"num_tokens": 44063222.0,
|
|
"step": 19750
|
|
},
|
|
{
|
|
"entropy": 5.620134353637695,
|
|
"epoch": 2.218678047958668,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004514593025760543,
|
|
"loss": 5.3185,
|
|
"mean_token_accuracy": 0.19031717330217363,
|
|
"num_tokens": 44075020.0,
|
|
"step": 19755
|
|
},
|
|
{
|
|
"entropy": 5.52335376739502,
|
|
"epoch": 2.2192396248666255,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00045143439038542653,
|
|
"loss": 5.2453,
|
|
"mean_token_accuracy": 0.1905816301703453,
|
|
"num_tokens": 44086696.0,
|
|
"step": 19760
|
|
},
|
|
{
|
|
"entropy": 5.5227399349212645,
|
|
"epoch": 2.219801201774583,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004514094725770594,
|
|
"loss": 5.2048,
|
|
"mean_token_accuracy": 0.1949351578950882,
|
|
"num_tokens": 44096768.0,
|
|
"step": 19765
|
|
},
|
|
{
|
|
"entropy": 5.469168615341187,
|
|
"epoch": 2.2203627786825404,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00045138454915174625,
|
|
"loss": 5.2209,
|
|
"mean_token_accuracy": 0.2001909077167511,
|
|
"num_tokens": 44108008.0,
|
|
"step": 19770
|
|
},
|
|
{
|
|
"entropy": 5.481593942642212,
|
|
"epoch": 2.220924355590498,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.00045135962011028064,
|
|
"loss": 5.179,
|
|
"mean_token_accuracy": 0.1917398080229759,
|
|
"num_tokens": 44119231.0,
|
|
"step": 19775
|
|
},
|
|
{
|
|
"entropy": 5.4186042785644535,
|
|
"epoch": 2.2214859324984557,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004513346854534564,
|
|
"loss": 5.1678,
|
|
"mean_token_accuracy": 0.19441763311624527,
|
|
"num_tokens": 44129264.0,
|
|
"step": 19780
|
|
},
|
|
{
|
|
"entropy": 5.50796217918396,
|
|
"epoch": 2.2220475094064134,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004513097451820673,
|
|
"loss": 5.3098,
|
|
"mean_token_accuracy": 0.19406169652938843,
|
|
"num_tokens": 44141234.0,
|
|
"step": 19785
|
|
},
|
|
{
|
|
"entropy": 5.545570611953735,
|
|
"epoch": 2.2226090863143706,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.00045128479929690756,
|
|
"loss": 5.1761,
|
|
"mean_token_accuracy": 0.20019723176956178,
|
|
"num_tokens": 44151751.0,
|
|
"step": 19790
|
|
},
|
|
{
|
|
"entropy": 5.376328468322754,
|
|
"epoch": 2.2231706632223283,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004512598477987714,
|
|
"loss": 5.1131,
|
|
"mean_token_accuracy": 0.19938686341047288,
|
|
"num_tokens": 44162687.0,
|
|
"step": 19795
|
|
},
|
|
{
|
|
"entropy": 5.472272872924805,
|
|
"epoch": 2.223732240130286,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00045123489068845334,
|
|
"loss": 5.1861,
|
|
"mean_token_accuracy": 0.19867129176855086,
|
|
"num_tokens": 44173758.0,
|
|
"step": 19800
|
|
},
|
|
{
|
|
"entropy": 5.488106441497803,
|
|
"epoch": 2.2242938170382436,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00045120992796674804,
|
|
"loss": 5.2227,
|
|
"mean_token_accuracy": 0.1970738038420677,
|
|
"num_tokens": 44184176.0,
|
|
"step": 19805
|
|
},
|
|
{
|
|
"entropy": 5.5556807041168215,
|
|
"epoch": 2.224855393946201,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004511849596344503,
|
|
"loss": 5.2982,
|
|
"mean_token_accuracy": 0.1883039206266403,
|
|
"num_tokens": 44195155.0,
|
|
"step": 19810
|
|
},
|
|
{
|
|
"entropy": 5.601989316940307,
|
|
"epoch": 2.2254169708541585,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00045115998569235507,
|
|
"loss": 5.3327,
|
|
"mean_token_accuracy": 0.18982167840003966,
|
|
"num_tokens": 44207139.0,
|
|
"step": 19815
|
|
},
|
|
{
|
|
"entropy": 5.55784125328064,
|
|
"epoch": 2.225978547762116,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00045113500614125756,
|
|
"loss": 5.2924,
|
|
"mean_token_accuracy": 0.19552985280752183,
|
|
"num_tokens": 44218317.0,
|
|
"step": 19820
|
|
},
|
|
{
|
|
"entropy": 5.513452816009521,
|
|
"epoch": 2.2265401246700733,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004511100209819532,
|
|
"loss": 5.2196,
|
|
"mean_token_accuracy": 0.20117057114839554,
|
|
"num_tokens": 44228700.0,
|
|
"step": 19825
|
|
},
|
|
{
|
|
"entropy": 5.381744909286499,
|
|
"epoch": 2.227101701578031,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00045108503021523737,
|
|
"loss": 5.1642,
|
|
"mean_token_accuracy": 0.2060288295149803,
|
|
"num_tokens": 44239991.0,
|
|
"step": 19830
|
|
},
|
|
{
|
|
"entropy": 5.341881990432739,
|
|
"epoch": 2.2276632784859887,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00045106003384190604,
|
|
"loss": 5.0701,
|
|
"mean_token_accuracy": 0.20321475267410277,
|
|
"num_tokens": 44250224.0,
|
|
"step": 19835
|
|
},
|
|
{
|
|
"entropy": 5.462254285812378,
|
|
"epoch": 2.2282248553939463,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00045103503186275486,
|
|
"loss": 5.2653,
|
|
"mean_token_accuracy": 0.1943323627114296,
|
|
"num_tokens": 44261403.0,
|
|
"step": 19840
|
|
},
|
|
{
|
|
"entropy": 5.443727731704712,
|
|
"epoch": 2.2287864323019035,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00045101002427857997,
|
|
"loss": 5.1813,
|
|
"mean_token_accuracy": 0.19533726274967195,
|
|
"num_tokens": 44272935.0,
|
|
"step": 19845
|
|
},
|
|
{
|
|
"entropy": 5.4540385723114015,
|
|
"epoch": 2.229348009209861,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00045098501109017765,
|
|
"loss": 5.1805,
|
|
"mean_token_accuracy": 0.20066781789064408,
|
|
"num_tokens": 44283458.0,
|
|
"step": 19850
|
|
},
|
|
{
|
|
"entropy": 5.448845720291137,
|
|
"epoch": 2.229909586117819,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.00045095999229834437,
|
|
"loss": 5.194,
|
|
"mean_token_accuracy": 0.19300126135349274,
|
|
"num_tokens": 44294847.0,
|
|
"step": 19855
|
|
},
|
|
{
|
|
"entropy": 5.503479719161987,
|
|
"epoch": 2.2304711630257765,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004509349679038767,
|
|
"loss": 5.3141,
|
|
"mean_token_accuracy": 0.1934979274868965,
|
|
"num_tokens": 44306395.0,
|
|
"step": 19860
|
|
},
|
|
{
|
|
"entropy": 5.52719554901123,
|
|
"epoch": 2.2310327399337337,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00045090993790757137,
|
|
"loss": 5.2291,
|
|
"mean_token_accuracy": 0.19407544285058975,
|
|
"num_tokens": 44317452.0,
|
|
"step": 19865
|
|
},
|
|
{
|
|
"entropy": 5.47685546875,
|
|
"epoch": 2.2315943168416914,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004508849023102253,
|
|
"loss": 5.2109,
|
|
"mean_token_accuracy": 0.20183431953191758,
|
|
"num_tokens": 44329862.0,
|
|
"step": 19870
|
|
},
|
|
{
|
|
"entropy": 5.507463693618774,
|
|
"epoch": 2.232155893749649,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004508598611126359,
|
|
"loss": 5.2912,
|
|
"mean_token_accuracy": 0.19494223594665527,
|
|
"num_tokens": 44340334.0,
|
|
"step": 19875
|
|
},
|
|
{
|
|
"entropy": 5.570824003219604,
|
|
"epoch": 2.2327174706576067,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004508348143156002,
|
|
"loss": 5.3593,
|
|
"mean_token_accuracy": 0.18573096096515657,
|
|
"num_tokens": 44351810.0,
|
|
"step": 19880
|
|
},
|
|
{
|
|
"entropy": 5.6180867671966555,
|
|
"epoch": 2.233279047565564,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00045080976191991587,
|
|
"loss": 5.4113,
|
|
"mean_token_accuracy": 0.18101848810911178,
|
|
"num_tokens": 44365143.0,
|
|
"step": 19885
|
|
},
|
|
{
|
|
"entropy": 5.504892826080322,
|
|
"epoch": 2.2338406244735216,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004507847039263805,
|
|
"loss": 5.29,
|
|
"mean_token_accuracy": 0.19741635918617248,
|
|
"num_tokens": 44375895.0,
|
|
"step": 19890
|
|
},
|
|
{
|
|
"entropy": 5.499074125289917,
|
|
"epoch": 2.2344022013814793,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000450759640335792,
|
|
"loss": 5.188,
|
|
"mean_token_accuracy": 0.19528525769710542,
|
|
"num_tokens": 44387378.0,
|
|
"step": 19895
|
|
},
|
|
{
|
|
"entropy": 5.442280435562134,
|
|
"epoch": 2.234963778289437,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004507345711489484,
|
|
"loss": 5.1585,
|
|
"mean_token_accuracy": 0.20831980258226396,
|
|
"num_tokens": 44398460.0,
|
|
"step": 19900
|
|
},
|
|
{
|
|
"entropy": 5.422170114517212,
|
|
"epoch": 2.235525355197394,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00045070949636664785,
|
|
"loss": 5.1875,
|
|
"mean_token_accuracy": 0.19626613408327104,
|
|
"num_tokens": 44409885.0,
|
|
"step": 19905
|
|
},
|
|
{
|
|
"entropy": 5.440979242324829,
|
|
"epoch": 2.236086932105352,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004506844159896888,
|
|
"loss": 5.1271,
|
|
"mean_token_accuracy": 0.20281644463539122,
|
|
"num_tokens": 44420897.0,
|
|
"step": 19910
|
|
},
|
|
{
|
|
"entropy": 5.553892469406128,
|
|
"epoch": 2.2366485090133095,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004506593300188698,
|
|
"loss": 5.3214,
|
|
"mean_token_accuracy": 0.188603737950325,
|
|
"num_tokens": 44432691.0,
|
|
"step": 19915
|
|
},
|
|
{
|
|
"entropy": 5.532892465591431,
|
|
"epoch": 2.2372100859212667,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004506342384549897,
|
|
"loss": 5.2373,
|
|
"mean_token_accuracy": 0.19359887689352034,
|
|
"num_tokens": 44444731.0,
|
|
"step": 19920
|
|
},
|
|
{
|
|
"entropy": 5.584154844284058,
|
|
"epoch": 2.2377716628292244,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004506091412988472,
|
|
"loss": 5.2339,
|
|
"mean_token_accuracy": 0.20170113146305085,
|
|
"num_tokens": 44456959.0,
|
|
"step": 19925
|
|
},
|
|
{
|
|
"entropy": 5.5804445266723635,
|
|
"epoch": 2.238333239737182,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00045058403855124165,
|
|
"loss": 5.2942,
|
|
"mean_token_accuracy": 0.19498781263828277,
|
|
"num_tokens": 44468970.0,
|
|
"step": 19930
|
|
},
|
|
{
|
|
"entropy": 5.452075576782226,
|
|
"epoch": 2.2388948166451397,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004505589302129721,
|
|
"loss": 5.1701,
|
|
"mean_token_accuracy": 0.20246293842792512,
|
|
"num_tokens": 44480485.0,
|
|
"step": 19935
|
|
},
|
|
{
|
|
"entropy": 5.51645679473877,
|
|
"epoch": 2.239456393553097,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004505338162848382,
|
|
"loss": 5.338,
|
|
"mean_token_accuracy": 0.19500317871570588,
|
|
"num_tokens": 44492890.0,
|
|
"step": 19940
|
|
},
|
|
{
|
|
"entropy": 5.5942668437957765,
|
|
"epoch": 2.2400179704610546,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004505086967676395,
|
|
"loss": 5.4195,
|
|
"mean_token_accuracy": 0.18069773763418198,
|
|
"num_tokens": 44504743.0,
|
|
"step": 19945
|
|
},
|
|
{
|
|
"entropy": 5.570518827438354,
|
|
"epoch": 2.240579547369012,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004504835716621757,
|
|
"loss": 5.2083,
|
|
"mean_token_accuracy": 0.19530122280120848,
|
|
"num_tokens": 44514998.0,
|
|
"step": 19950
|
|
},
|
|
{
|
|
"entropy": 5.438938236236572,
|
|
"epoch": 2.24114112427697,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004504584409692471,
|
|
"loss": 5.1848,
|
|
"mean_token_accuracy": 0.20347164571285248,
|
|
"num_tokens": 44527530.0,
|
|
"step": 19955
|
|
},
|
|
{
|
|
"entropy": 5.556153011322022,
|
|
"epoch": 2.241702701184927,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00045043330468965364,
|
|
"loss": 5.3963,
|
|
"mean_token_accuracy": 0.1878069669008255,
|
|
"num_tokens": 44540939.0,
|
|
"step": 19960
|
|
},
|
|
{
|
|
"entropy": 5.589362144470215,
|
|
"epoch": 2.2422642780928848,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00045040816282419566,
|
|
"loss": 5.2659,
|
|
"mean_token_accuracy": 0.19184372276067735,
|
|
"num_tokens": 44551557.0,
|
|
"step": 19965
|
|
},
|
|
{
|
|
"entropy": 5.439628791809082,
|
|
"epoch": 2.2428258550008424,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00045038301537367374,
|
|
"loss": 5.1595,
|
|
"mean_token_accuracy": 0.19913299679756163,
|
|
"num_tokens": 44561969.0,
|
|
"step": 19970
|
|
},
|
|
{
|
|
"entropy": 5.372342681884765,
|
|
"epoch": 2.2433874319088,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00045035786233888864,
|
|
"loss": 5.1541,
|
|
"mean_token_accuracy": 0.19579712003469468,
|
|
"num_tokens": 44573542.0,
|
|
"step": 19975
|
|
},
|
|
{
|
|
"entropy": 5.559537076950074,
|
|
"epoch": 2.2439490088167573,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00045033270372064123,
|
|
"loss": 5.2257,
|
|
"mean_token_accuracy": 0.204598106443882,
|
|
"num_tokens": 44583720.0,
|
|
"step": 19980
|
|
},
|
|
{
|
|
"entropy": 5.485935354232788,
|
|
"epoch": 2.244510585724715,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00045030753951973243,
|
|
"loss": 5.3023,
|
|
"mean_token_accuracy": 0.1947477087378502,
|
|
"num_tokens": 44595314.0,
|
|
"step": 19985
|
|
},
|
|
{
|
|
"entropy": 5.6282354354858395,
|
|
"epoch": 2.2450721626326726,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00045028236973696363,
|
|
"loss": 5.4322,
|
|
"mean_token_accuracy": 0.18839803487062454,
|
|
"num_tokens": 44608569.0,
|
|
"step": 19990
|
|
},
|
|
{
|
|
"entropy": 5.493777847290039,
|
|
"epoch": 2.2456337395406303,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004502571943731362,
|
|
"loss": 5.2371,
|
|
"mean_token_accuracy": 0.1939469173550606,
|
|
"num_tokens": 44619389.0,
|
|
"step": 19995
|
|
},
|
|
{
|
|
"entropy": 5.514086818695068,
|
|
"epoch": 2.2461953164485875,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004502320134290517,
|
|
"loss": 5.32,
|
|
"mean_token_accuracy": 0.19063089042901993,
|
|
"num_tokens": 44629945.0,
|
|
"step": 20000
|
|
},
|
|
{
|
|
"entropy": 5.556463289260864,
|
|
"epoch": 2.246756893356545,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00045020682690551203,
|
|
"loss": 5.3412,
|
|
"mean_token_accuracy": 0.18668145984411239,
|
|
"num_tokens": 44640741.0,
|
|
"step": 20005
|
|
},
|
|
{
|
|
"entropy": 5.524778699874878,
|
|
"epoch": 2.247318470264503,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00045018163480331887,
|
|
"loss": 5.1792,
|
|
"mean_token_accuracy": 0.2004580393433571,
|
|
"num_tokens": 44651312.0,
|
|
"step": 20010
|
|
},
|
|
{
|
|
"entropy": 5.449014711380005,
|
|
"epoch": 2.24788004717246,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00045015643712327465,
|
|
"loss": 5.2182,
|
|
"mean_token_accuracy": 0.19613993614912034,
|
|
"num_tokens": 44663156.0,
|
|
"step": 20015
|
|
},
|
|
{
|
|
"entropy": 5.4309642791748045,
|
|
"epoch": 2.2484416240804177,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004501312338661815,
|
|
"loss": 5.2239,
|
|
"mean_token_accuracy": 0.20006002634763717,
|
|
"num_tokens": 44673479.0,
|
|
"step": 20020
|
|
},
|
|
{
|
|
"entropy": 5.492065954208374,
|
|
"epoch": 2.2490032009883754,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004501060250328419,
|
|
"loss": 5.2484,
|
|
"mean_token_accuracy": 0.19600303024053572,
|
|
"num_tokens": 44684207.0,
|
|
"step": 20025
|
|
},
|
|
{
|
|
"entropy": 5.522979259490967,
|
|
"epoch": 2.249564777896333,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004500808106240586,
|
|
"loss": 5.2219,
|
|
"mean_token_accuracy": 0.19826527833938598,
|
|
"num_tokens": 44695611.0,
|
|
"step": 20030
|
|
},
|
|
{
|
|
"entropy": 5.499130344390869,
|
|
"epoch": 2.2501263548042907,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004500555906406343,
|
|
"loss": 5.2581,
|
|
"mean_token_accuracy": 0.19427683651447297,
|
|
"num_tokens": 44707061.0,
|
|
"step": 20035
|
|
},
|
|
{
|
|
"entropy": 5.58782844543457,
|
|
"epoch": 2.250687931712248,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004500303650833722,
|
|
"loss": 5.3577,
|
|
"mean_token_accuracy": 0.1854730948805809,
|
|
"num_tokens": 44719366.0,
|
|
"step": 20040
|
|
},
|
|
{
|
|
"entropy": 5.556455802917481,
|
|
"epoch": 2.2512495086202056,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004500051339530754,
|
|
"loss": 5.2256,
|
|
"mean_token_accuracy": 0.20091187506914138,
|
|
"num_tokens": 44730578.0,
|
|
"step": 20045
|
|
},
|
|
{
|
|
"entropy": 5.457146549224854,
|
|
"epoch": 2.2518110855281632,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004499798972505472,
|
|
"loss": 5.1848,
|
|
"mean_token_accuracy": 0.19817287474870682,
|
|
"num_tokens": 44740620.0,
|
|
"step": 20050
|
|
},
|
|
{
|
|
"entropy": 5.484510374069214,
|
|
"epoch": 2.2523726624361204,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00044995465497659127,
|
|
"loss": 5.2389,
|
|
"mean_token_accuracy": 0.20124588906764984,
|
|
"num_tokens": 44751518.0,
|
|
"step": 20055
|
|
},
|
|
{
|
|
"entropy": 5.510428333282471,
|
|
"epoch": 2.252934239344078,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004499294071320112,
|
|
"loss": 5.2686,
|
|
"mean_token_accuracy": 0.19703642874956132,
|
|
"num_tokens": 44761563.0,
|
|
"step": 20060
|
|
},
|
|
{
|
|
"entropy": 5.5353888988494875,
|
|
"epoch": 2.2534958162520358,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000449904153717611,
|
|
"loss": 5.2805,
|
|
"mean_token_accuracy": 0.1933363363146782,
|
|
"num_tokens": 44773330.0,
|
|
"step": 20065
|
|
},
|
|
{
|
|
"entropy": 5.53394832611084,
|
|
"epoch": 2.2540573931599934,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004498788947341947,
|
|
"loss": 5.2463,
|
|
"mean_token_accuracy": 0.19813215285539626,
|
|
"num_tokens": 44786198.0,
|
|
"step": 20070
|
|
},
|
|
{
|
|
"entropy": 5.387781095504761,
|
|
"epoch": 2.2546189700679506,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004498536301825665,
|
|
"loss": 5.1404,
|
|
"mean_token_accuracy": 0.2007957324385643,
|
|
"num_tokens": 44797643.0,
|
|
"step": 20075
|
|
},
|
|
{
|
|
"entropy": 5.407376337051391,
|
|
"epoch": 2.2551805469759083,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000449828360063531,
|
|
"loss": 5.168,
|
|
"mean_token_accuracy": 0.2013155400753021,
|
|
"num_tokens": 44808283.0,
|
|
"step": 20080
|
|
},
|
|
{
|
|
"entropy": 5.447269535064697,
|
|
"epoch": 2.255742123883866,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00044980308437789267,
|
|
"loss": 5.0732,
|
|
"mean_token_accuracy": 0.20297736674547195,
|
|
"num_tokens": 44817699.0,
|
|
"step": 20085
|
|
},
|
|
{
|
|
"entropy": 5.486398029327392,
|
|
"epoch": 2.2563037007918236,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004497778031264564,
|
|
"loss": 5.2906,
|
|
"mean_token_accuracy": 0.19047022014856338,
|
|
"num_tokens": 44828428.0,
|
|
"step": 20090
|
|
},
|
|
{
|
|
"entropy": 5.40444598197937,
|
|
"epoch": 2.256865277699781,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00044975251631002694,
|
|
"loss": 5.2049,
|
|
"mean_token_accuracy": 0.19405728727579116,
|
|
"num_tokens": 44839288.0,
|
|
"step": 20095
|
|
},
|
|
{
|
|
"entropy": 5.518749046325683,
|
|
"epoch": 2.2574268546077385,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004497272239294097,
|
|
"loss": 5.4182,
|
|
"mean_token_accuracy": 0.1873346209526062,
|
|
"num_tokens": 44850250.0,
|
|
"step": 20100
|
|
},
|
|
{
|
|
"entropy": 5.575524854660034,
|
|
"epoch": 2.257988431515696,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004497019259854099,
|
|
"loss": 5.255,
|
|
"mean_token_accuracy": 0.1953403204679489,
|
|
"num_tokens": 44862186.0,
|
|
"step": 20105
|
|
},
|
|
{
|
|
"entropy": 5.54745135307312,
|
|
"epoch": 2.2585500084236534,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00044967662247883295,
|
|
"loss": 5.3404,
|
|
"mean_token_accuracy": 0.19116792529821397,
|
|
"num_tokens": 44874266.0,
|
|
"step": 20110
|
|
},
|
|
{
|
|
"entropy": 5.553813028335571,
|
|
"epoch": 2.259111585331611,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00044965131341048454,
|
|
"loss": 5.2877,
|
|
"mean_token_accuracy": 0.19943919479846955,
|
|
"num_tokens": 44885783.0,
|
|
"step": 20115
|
|
},
|
|
{
|
|
"entropy": 5.480351400375366,
|
|
"epoch": 2.2596731622395687,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004496259987811707,
|
|
"loss": 5.1375,
|
|
"mean_token_accuracy": 0.2034609317779541,
|
|
"num_tokens": 44896972.0,
|
|
"step": 20120
|
|
},
|
|
{
|
|
"entropy": 5.466098499298096,
|
|
"epoch": 2.2602347391475264,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004496006785916973,
|
|
"loss": 5.246,
|
|
"mean_token_accuracy": 0.19787174910306932,
|
|
"num_tokens": 44907414.0,
|
|
"step": 20125
|
|
},
|
|
{
|
|
"entropy": 5.498031806945801,
|
|
"epoch": 2.260796316055484,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00044957535284287055,
|
|
"loss": 5.1722,
|
|
"mean_token_accuracy": 0.19434682428836822,
|
|
"num_tokens": 44917150.0,
|
|
"step": 20130
|
|
},
|
|
{
|
|
"entropy": 5.469934034347534,
|
|
"epoch": 2.2613578929634413,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00044955002153549686,
|
|
"loss": 5.211,
|
|
"mean_token_accuracy": 0.19735645353794098,
|
|
"num_tokens": 44928927.0,
|
|
"step": 20135
|
|
},
|
|
{
|
|
"entropy": 5.467767143249512,
|
|
"epoch": 2.261919469871399,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004495246846703828,
|
|
"loss": 5.2256,
|
|
"mean_token_accuracy": 0.19621748328208924,
|
|
"num_tokens": 44938987.0,
|
|
"step": 20140
|
|
},
|
|
{
|
|
"entropy": 5.498761415481567,
|
|
"epoch": 2.2624810467793566,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00044949934224833505,
|
|
"loss": 5.1625,
|
|
"mean_token_accuracy": 0.1975456029176712,
|
|
"num_tokens": 44950395.0,
|
|
"step": 20145
|
|
},
|
|
{
|
|
"entropy": 5.505730009078979,
|
|
"epoch": 2.263042623687314,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004494739942701606,
|
|
"loss": 5.1744,
|
|
"mean_token_accuracy": 0.20360083431005477,
|
|
"num_tokens": 44961389.0,
|
|
"step": 20150
|
|
},
|
|
{
|
|
"entropy": 5.532986211776733,
|
|
"epoch": 2.2636042005952715,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00044944864073666655,
|
|
"loss": 5.3595,
|
|
"mean_token_accuracy": 0.19310897290706636,
|
|
"num_tokens": 44973142.0,
|
|
"step": 20155
|
|
},
|
|
{
|
|
"entropy": 5.401855993270874,
|
|
"epoch": 2.264165777503229,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00044942328164866,
|
|
"loss": 5.1518,
|
|
"mean_token_accuracy": 0.20104912370443345,
|
|
"num_tokens": 44983831.0,
|
|
"step": 20160
|
|
},
|
|
{
|
|
"entropy": 5.500086736679077,
|
|
"epoch": 2.2647273544111868,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004493979170069486,
|
|
"loss": 5.2509,
|
|
"mean_token_accuracy": 0.2013973131775856,
|
|
"num_tokens": 44996386.0,
|
|
"step": 20165
|
|
},
|
|
{
|
|
"entropy": 5.498330402374267,
|
|
"epoch": 2.265288931319144,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00044937254681233984,
|
|
"loss": 5.1929,
|
|
"mean_token_accuracy": 0.19184104055166246,
|
|
"num_tokens": 45007607.0,
|
|
"step": 20170
|
|
},
|
|
{
|
|
"entropy": 5.427362871170044,
|
|
"epoch": 2.2658505082271017,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00044934717106564164,
|
|
"loss": 5.2193,
|
|
"mean_token_accuracy": 0.19729479551315307,
|
|
"num_tokens": 45019637.0,
|
|
"step": 20175
|
|
},
|
|
{
|
|
"entropy": 5.422962856292725,
|
|
"epoch": 2.2664120851350593,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00044932178976766183,
|
|
"loss": 5.2172,
|
|
"mean_token_accuracy": 0.19794851690530776,
|
|
"num_tokens": 45031329.0,
|
|
"step": 20180
|
|
},
|
|
{
|
|
"entropy": 5.463313817977905,
|
|
"epoch": 2.266973662043017,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00044929640291920865,
|
|
"loss": 5.2061,
|
|
"mean_token_accuracy": 0.19512274116277695,
|
|
"num_tokens": 45042539.0,
|
|
"step": 20185
|
|
},
|
|
{
|
|
"entropy": 5.391692638397217,
|
|
"epoch": 2.267535238950974,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004492710105210904,
|
|
"loss": 5.098,
|
|
"mean_token_accuracy": 0.20303086936473846,
|
|
"num_tokens": 45054021.0,
|
|
"step": 20190
|
|
},
|
|
{
|
|
"entropy": 5.570929288864136,
|
|
"epoch": 2.268096815858932,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00044924561257411554,
|
|
"loss": 5.2995,
|
|
"mean_token_accuracy": 0.19303088784217834,
|
|
"num_tokens": 45065912.0,
|
|
"step": 20195
|
|
},
|
|
{
|
|
"entropy": 5.4894567966461185,
|
|
"epoch": 2.2686583927668895,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004492202090790928,
|
|
"loss": 5.1844,
|
|
"mean_token_accuracy": 0.20377012491226196,
|
|
"num_tokens": 45075965.0,
|
|
"step": 20200
|
|
},
|
|
{
|
|
"entropy": 5.381528711318969,
|
|
"epoch": 2.2692199696748467,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004491948000368311,
|
|
"loss": 5.1851,
|
|
"mean_token_accuracy": 0.1979663237929344,
|
|
"num_tokens": 45086676.0,
|
|
"step": 20205
|
|
},
|
|
{
|
|
"entropy": 5.445681858062744,
|
|
"epoch": 2.2697815465828044,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00044916938544813936,
|
|
"loss": 5.2159,
|
|
"mean_token_accuracy": 0.20002556443214417,
|
|
"num_tokens": 45097747.0,
|
|
"step": 20210
|
|
},
|
|
{
|
|
"entropy": 5.54331488609314,
|
|
"epoch": 2.270343123490762,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00044914396531382686,
|
|
"loss": 5.1724,
|
|
"mean_token_accuracy": 0.20359463840723038,
|
|
"num_tokens": 45107506.0,
|
|
"step": 20215
|
|
},
|
|
{
|
|
"entropy": 5.4871217727661135,
|
|
"epoch": 2.2709047003987197,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00044911853963470295,
|
|
"loss": 5.2335,
|
|
"mean_token_accuracy": 0.20210439264774321,
|
|
"num_tokens": 45119939.0,
|
|
"step": 20220
|
|
},
|
|
{
|
|
"entropy": 5.48626184463501,
|
|
"epoch": 2.2714662773066774,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004490931084115772,
|
|
"loss": 5.3068,
|
|
"mean_token_accuracy": 0.18659437596797943,
|
|
"num_tokens": 45133749.0,
|
|
"step": 20225
|
|
},
|
|
{
|
|
"entropy": 5.516075468063354,
|
|
"epoch": 2.2720278542146346,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00044906767164525936,
|
|
"loss": 5.2831,
|
|
"mean_token_accuracy": 0.19292282611131667,
|
|
"num_tokens": 45144696.0,
|
|
"step": 20230
|
|
},
|
|
{
|
|
"entropy": 5.484831094741821,
|
|
"epoch": 2.2725894311225923,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004490422293365594,
|
|
"loss": 5.1476,
|
|
"mean_token_accuracy": 0.19563103020191192,
|
|
"num_tokens": 45154921.0,
|
|
"step": 20235
|
|
},
|
|
{
|
|
"entropy": 5.409498834609986,
|
|
"epoch": 2.27315100803055,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004490167814862872,
|
|
"loss": 5.1423,
|
|
"mean_token_accuracy": 0.20068973451852798,
|
|
"num_tokens": 45164769.0,
|
|
"step": 20240
|
|
},
|
|
{
|
|
"entropy": 5.550851106643677,
|
|
"epoch": 2.273712584938507,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004489913280952533,
|
|
"loss": 5.3287,
|
|
"mean_token_accuracy": 0.19520364105701446,
|
|
"num_tokens": 45176619.0,
|
|
"step": 20245
|
|
},
|
|
{
|
|
"entropy": 5.460875177383423,
|
|
"epoch": 2.274274161846465,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004489658691642681,
|
|
"loss": 5.2376,
|
|
"mean_token_accuracy": 0.1926131084561348,
|
|
"num_tokens": 45186508.0,
|
|
"step": 20250
|
|
},
|
|
{
|
|
"entropy": 5.578034257888794,
|
|
"epoch": 2.2748357387544225,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00044894040469414207,
|
|
"loss": 5.3442,
|
|
"mean_token_accuracy": 0.1901059105992317,
|
|
"num_tokens": 45198213.0,
|
|
"step": 20255
|
|
},
|
|
{
|
|
"entropy": 5.486166191101074,
|
|
"epoch": 2.27539731566238,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00044891493468568607,
|
|
"loss": 5.2244,
|
|
"mean_token_accuracy": 0.18832046240568162,
|
|
"num_tokens": 45209328.0,
|
|
"step": 20260
|
|
},
|
|
{
|
|
"entropy": 5.503150701522827,
|
|
"epoch": 2.2759588925703373,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00044888945913971106,
|
|
"loss": 5.2118,
|
|
"mean_token_accuracy": 0.19665393978357315,
|
|
"num_tokens": 45219722.0,
|
|
"step": 20265
|
|
},
|
|
{
|
|
"entropy": 5.591525936126709,
|
|
"epoch": 2.276520469478295,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00044886397805702835,
|
|
"loss": 5.2907,
|
|
"mean_token_accuracy": 0.18618952333927155,
|
|
"num_tokens": 45230377.0,
|
|
"step": 20270
|
|
},
|
|
{
|
|
"entropy": 5.579563331604004,
|
|
"epoch": 2.2770820463862527,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00044883849143844914,
|
|
"loss": 5.2096,
|
|
"mean_token_accuracy": 0.19831510931253432,
|
|
"num_tokens": 45241598.0,
|
|
"step": 20275
|
|
},
|
|
{
|
|
"entropy": 5.5415668964385985,
|
|
"epoch": 2.2776436232942103,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004488129992847848,
|
|
"loss": 5.4183,
|
|
"mean_token_accuracy": 0.18950254023075103,
|
|
"num_tokens": 45253153.0,
|
|
"step": 20280
|
|
},
|
|
{
|
|
"entropy": 5.513988065719604,
|
|
"epoch": 2.2782052002021675,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004487875015968473,
|
|
"loss": 5.2859,
|
|
"mean_token_accuracy": 0.1942953109741211,
|
|
"num_tokens": 45264523.0,
|
|
"step": 20285
|
|
},
|
|
{
|
|
"entropy": 5.477509784698486,
|
|
"epoch": 2.278766777110125,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004487619983754483,
|
|
"loss": 5.2018,
|
|
"mean_token_accuracy": 0.1925478085875511,
|
|
"num_tokens": 45275320.0,
|
|
"step": 20290
|
|
},
|
|
{
|
|
"entropy": 5.522681856155396,
|
|
"epoch": 2.279328354018083,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00044873648962139983,
|
|
"loss": 5.2232,
|
|
"mean_token_accuracy": 0.19909849315881728,
|
|
"num_tokens": 45286704.0,
|
|
"step": 20295
|
|
},
|
|
{
|
|
"entropy": 5.540631628036499,
|
|
"epoch": 2.27988993092604,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004487109753355142,
|
|
"loss": 5.259,
|
|
"mean_token_accuracy": 0.19319239258766174,
|
|
"num_tokens": 45299098.0,
|
|
"step": 20300
|
|
},
|
|
{
|
|
"entropy": 5.49213342666626,
|
|
"epoch": 2.2804515078339977,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004486854555186037,
|
|
"loss": 5.1904,
|
|
"mean_token_accuracy": 0.19423681497573853,
|
|
"num_tokens": 45309995.0,
|
|
"step": 20305
|
|
},
|
|
{
|
|
"entropy": 5.580655097961426,
|
|
"epoch": 2.2810130847419554,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004486599301714809,
|
|
"loss": 5.377,
|
|
"mean_token_accuracy": 0.19141939878463746,
|
|
"num_tokens": 45321711.0,
|
|
"step": 20310
|
|
},
|
|
{
|
|
"entropy": 5.499113750457764,
|
|
"epoch": 2.281574661649913,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004486343992949587,
|
|
"loss": 5.2829,
|
|
"mean_token_accuracy": 0.19541093707084656,
|
|
"num_tokens": 45332401.0,
|
|
"step": 20315
|
|
},
|
|
{
|
|
"entropy": 5.573700761795044,
|
|
"epoch": 2.2821362385578707,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00044860886288984977,
|
|
"loss": 5.3328,
|
|
"mean_token_accuracy": 0.1919061630964279,
|
|
"num_tokens": 45344138.0,
|
|
"step": 20320
|
|
},
|
|
{
|
|
"entropy": 5.442095041275024,
|
|
"epoch": 2.282697815465828,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004485833209569674,
|
|
"loss": 5.2385,
|
|
"mean_token_accuracy": 0.19264374673366547,
|
|
"num_tokens": 45355913.0,
|
|
"step": 20325
|
|
},
|
|
{
|
|
"entropy": 5.498832941055298,
|
|
"epoch": 2.2832593923737856,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004485577734971247,
|
|
"loss": 5.1837,
|
|
"mean_token_accuracy": 0.1980019763112068,
|
|
"num_tokens": 45367342.0,
|
|
"step": 20330
|
|
},
|
|
{
|
|
"entropy": 5.50741286277771,
|
|
"epoch": 2.2838209692817433,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00044853222051113525,
|
|
"loss": 5.2307,
|
|
"mean_token_accuracy": 0.19548344910144805,
|
|
"num_tokens": 45377866.0,
|
|
"step": 20335
|
|
},
|
|
{
|
|
"entropy": 5.472334480285644,
|
|
"epoch": 2.2843825461897005,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00044850666199981244,
|
|
"loss": 5.2634,
|
|
"mean_token_accuracy": 0.19072347432374953,
|
|
"num_tokens": 45389346.0,
|
|
"step": 20340
|
|
},
|
|
{
|
|
"entropy": 5.437552738189697,
|
|
"epoch": 2.284944123097658,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00044848109796397035,
|
|
"loss": 5.1789,
|
|
"mean_token_accuracy": 0.19399820417165756,
|
|
"num_tokens": 45400112.0,
|
|
"step": 20345
|
|
},
|
|
{
|
|
"entropy": 5.4474702835083,
|
|
"epoch": 2.285505700005616,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00044845552840442276,
|
|
"loss": 5.1763,
|
|
"mean_token_accuracy": 0.19980261623859405,
|
|
"num_tokens": 45411666.0,
|
|
"step": 20350
|
|
},
|
|
{
|
|
"entropy": 5.428030920028687,
|
|
"epoch": 2.2860672769135735,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00044842995332198393,
|
|
"loss": 5.1573,
|
|
"mean_token_accuracy": 0.20993824154138566,
|
|
"num_tokens": 45423631.0,
|
|
"step": 20355
|
|
},
|
|
{
|
|
"entropy": 5.345173454284668,
|
|
"epoch": 2.2866288538215307,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00044840437271746807,
|
|
"loss": 5.1262,
|
|
"mean_token_accuracy": 0.198094242811203,
|
|
"num_tokens": 45434697.0,
|
|
"step": 20360
|
|
},
|
|
{
|
|
"entropy": 5.534241247177124,
|
|
"epoch": 2.2871904307294884,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004483787865916898,
|
|
"loss": 5.2774,
|
|
"mean_token_accuracy": 0.18845348060131073,
|
|
"num_tokens": 45446637.0,
|
|
"step": 20365
|
|
},
|
|
{
|
|
"entropy": 5.472633218765258,
|
|
"epoch": 2.287752007637446,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00044835319494546366,
|
|
"loss": 5.2002,
|
|
"mean_token_accuracy": 0.19916970729827882,
|
|
"num_tokens": 45456750.0,
|
|
"step": 20370
|
|
},
|
|
{
|
|
"entropy": 5.430306768417358,
|
|
"epoch": 2.2883135845454037,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.00044832759777960456,
|
|
"loss": 5.2257,
|
|
"mean_token_accuracy": 0.19966684579849242,
|
|
"num_tokens": 45469383.0,
|
|
"step": 20375
|
|
},
|
|
{
|
|
"entropy": 5.4830526351928714,
|
|
"epoch": 2.288875161453361,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004483019950949276,
|
|
"loss": 5.1962,
|
|
"mean_token_accuracy": 0.2003369987010956,
|
|
"num_tokens": 45479668.0,
|
|
"step": 20380
|
|
},
|
|
{
|
|
"entropy": 5.445210313796997,
|
|
"epoch": 2.2894367383613186,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004482763868922478,
|
|
"loss": 5.2717,
|
|
"mean_token_accuracy": 0.19506213515996934,
|
|
"num_tokens": 45490888.0,
|
|
"step": 20385
|
|
},
|
|
{
|
|
"entropy": 5.512267637252807,
|
|
"epoch": 2.289998315269276,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004482507731723807,
|
|
"loss": 5.2628,
|
|
"mean_token_accuracy": 0.19120286852121354,
|
|
"num_tokens": 45501973.0,
|
|
"step": 20390
|
|
},
|
|
{
|
|
"entropy": 5.498227834701538,
|
|
"epoch": 2.2905598921772334,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004482251539361418,
|
|
"loss": 5.2486,
|
|
"mean_token_accuracy": 0.19746894091367723,
|
|
"num_tokens": 45513171.0,
|
|
"step": 20395
|
|
},
|
|
{
|
|
"entropy": 5.418797159194947,
|
|
"epoch": 2.291121469085191,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004481995291843467,
|
|
"loss": 5.1761,
|
|
"mean_token_accuracy": 0.19927647709846497,
|
|
"num_tokens": 45523642.0,
|
|
"step": 20400
|
|
},
|
|
{
|
|
"entropy": 5.523365068435669,
|
|
"epoch": 2.2916830459931488,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004481738989178115,
|
|
"loss": 5.2533,
|
|
"mean_token_accuracy": 0.19765454083681105,
|
|
"num_tokens": 45534467.0,
|
|
"step": 20405
|
|
},
|
|
{
|
|
"entropy": 5.52879753112793,
|
|
"epoch": 2.2922446229011064,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004481482631373522,
|
|
"loss": 5.2405,
|
|
"mean_token_accuracy": 0.18979344069957732,
|
|
"num_tokens": 45545902.0,
|
|
"step": 20410
|
|
},
|
|
{
|
|
"entropy": 5.439551973342896,
|
|
"epoch": 2.292806199809064,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00044812262184378503,
|
|
"loss": 5.1216,
|
|
"mean_token_accuracy": 0.20488597005605697,
|
|
"num_tokens": 45556270.0,
|
|
"step": 20415
|
|
},
|
|
{
|
|
"entropy": 5.3579466342926025,
|
|
"epoch": 2.2933677767170213,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00044809697503792647,
|
|
"loss": 5.175,
|
|
"mean_token_accuracy": 0.20420384109020234,
|
|
"num_tokens": 45566773.0,
|
|
"step": 20420
|
|
},
|
|
{
|
|
"entropy": 5.464023017883301,
|
|
"epoch": 2.293929353624979,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00044807132272059306,
|
|
"loss": 5.2818,
|
|
"mean_token_accuracy": 0.1917489230632782,
|
|
"num_tokens": 45578819.0,
|
|
"step": 20425
|
|
},
|
|
{
|
|
"entropy": 5.527934646606445,
|
|
"epoch": 2.2944909305329366,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004480456648926016,
|
|
"loss": 5.233,
|
|
"mean_token_accuracy": 0.19213209748268129,
|
|
"num_tokens": 45589128.0,
|
|
"step": 20430
|
|
},
|
|
{
|
|
"entropy": 5.528298330307007,
|
|
"epoch": 2.295052507440894,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004480200015547691,
|
|
"loss": 5.2864,
|
|
"mean_token_accuracy": 0.1943219929933548,
|
|
"num_tokens": 45600253.0,
|
|
"step": 20435
|
|
},
|
|
{
|
|
"entropy": 5.560419750213623,
|
|
"epoch": 2.2956140843488515,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00044799433270791255,
|
|
"loss": 5.2608,
|
|
"mean_token_accuracy": 0.19483513832092286,
|
|
"num_tokens": 45611258.0,
|
|
"step": 20440
|
|
},
|
|
{
|
|
"entropy": 5.508506965637207,
|
|
"epoch": 2.296175661256809,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004479686583528494,
|
|
"loss": 5.2134,
|
|
"mean_token_accuracy": 0.20238776803016661,
|
|
"num_tokens": 45622720.0,
|
|
"step": 20445
|
|
},
|
|
{
|
|
"entropy": 5.422779130935669,
|
|
"epoch": 2.296737238164767,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004479429784903971,
|
|
"loss": 5.2001,
|
|
"mean_token_accuracy": 0.19343502968549728,
|
|
"num_tokens": 45634748.0,
|
|
"step": 20450
|
|
},
|
|
{
|
|
"entropy": 5.4938685417175295,
|
|
"epoch": 2.297298815072724,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004479172931213733,
|
|
"loss": 5.1436,
|
|
"mean_token_accuracy": 0.19243053793907167,
|
|
"num_tokens": 45645735.0,
|
|
"step": 20455
|
|
},
|
|
{
|
|
"entropy": 5.469387865066528,
|
|
"epoch": 2.2978603919806817,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004478916022465958,
|
|
"loss": 5.1393,
|
|
"mean_token_accuracy": 0.20273699313402177,
|
|
"num_tokens": 45656309.0,
|
|
"step": 20460
|
|
},
|
|
{
|
|
"entropy": 5.423810958862305,
|
|
"epoch": 2.2984219688886394,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004478659058668827,
|
|
"loss": 5.2987,
|
|
"mean_token_accuracy": 0.19772691130638123,
|
|
"num_tokens": 45667925.0,
|
|
"step": 20465
|
|
},
|
|
{
|
|
"entropy": 5.490616941452027,
|
|
"epoch": 2.298983545796597,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00044784020398305204,
|
|
"loss": 5.2781,
|
|
"mean_token_accuracy": 0.19499016106128692,
|
|
"num_tokens": 45679352.0,
|
|
"step": 20470
|
|
},
|
|
{
|
|
"entropy": 5.454271745681763,
|
|
"epoch": 2.2995451227045542,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004478144965959222,
|
|
"loss": 5.2407,
|
|
"mean_token_accuracy": 0.19642347991466522,
|
|
"num_tokens": 45689723.0,
|
|
"step": 20475
|
|
},
|
|
{
|
|
"entropy": 5.563471889495849,
|
|
"epoch": 2.300106699612512,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00044778878370631183,
|
|
"loss": 5.3727,
|
|
"mean_token_accuracy": 0.18927737176418305,
|
|
"num_tokens": 45701270.0,
|
|
"step": 20480
|
|
},
|
|
{
|
|
"entropy": 5.473050928115844,
|
|
"epoch": 2.3006682765204696,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00044776306531503957,
|
|
"loss": 5.1355,
|
|
"mean_token_accuracy": 0.2100411131978035,
|
|
"num_tokens": 45711409.0,
|
|
"step": 20485
|
|
},
|
|
{
|
|
"entropy": 5.419238758087158,
|
|
"epoch": 2.301229853428427,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00044773734142292425,
|
|
"loss": 5.2152,
|
|
"mean_token_accuracy": 0.19952069371938705,
|
|
"num_tokens": 45722032.0,
|
|
"step": 20490
|
|
},
|
|
{
|
|
"entropy": 5.48419713973999,
|
|
"epoch": 2.3017914303363844,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004477116120307851,
|
|
"loss": 5.212,
|
|
"mean_token_accuracy": 0.20220494419336318,
|
|
"num_tokens": 45733211.0,
|
|
"step": 20495
|
|
},
|
|
{
|
|
"entropy": 5.574658441543579,
|
|
"epoch": 2.302353007244342,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004476858771394412,
|
|
"loss": 5.3393,
|
|
"mean_token_accuracy": 0.19307047575712205,
|
|
"num_tokens": 45744585.0,
|
|
"step": 20500
|
|
},
|
|
{
|
|
"entropy": 5.520409202575683,
|
|
"epoch": 2.3029145841522998,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004476601367497119,
|
|
"loss": 5.2771,
|
|
"mean_token_accuracy": 0.19734428375959395,
|
|
"num_tokens": 45756040.0,
|
|
"step": 20505
|
|
},
|
|
{
|
|
"entropy": 5.503814029693603,
|
|
"epoch": 2.3034761610602574,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000447634390862417,
|
|
"loss": 5.2667,
|
|
"mean_token_accuracy": 0.19268766641616822,
|
|
"num_tokens": 45767717.0,
|
|
"step": 20510
|
|
},
|
|
{
|
|
"entropy": 5.559252071380615,
|
|
"epoch": 2.3040377379682146,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00044760863947837607,
|
|
"loss": 5.2832,
|
|
"mean_token_accuracy": 0.1924678087234497,
|
|
"num_tokens": 45778326.0,
|
|
"step": 20515
|
|
},
|
|
{
|
|
"entropy": 5.476704788208008,
|
|
"epoch": 2.3045993148761723,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00044758288259840904,
|
|
"loss": 5.1972,
|
|
"mean_token_accuracy": 0.20741473585367204,
|
|
"num_tokens": 45789780.0,
|
|
"step": 20520
|
|
},
|
|
{
|
|
"entropy": 5.437363147735596,
|
|
"epoch": 2.30516089178413,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004475571202233363,
|
|
"loss": 5.3431,
|
|
"mean_token_accuracy": 0.18793452829122542,
|
|
"num_tokens": 45801686.0,
|
|
"step": 20525
|
|
},
|
|
{
|
|
"entropy": 5.4736144065856935,
|
|
"epoch": 2.305722468692087,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004475313523539778,
|
|
"loss": 5.1862,
|
|
"mean_token_accuracy": 0.1942782148718834,
|
|
"num_tokens": 45812123.0,
|
|
"step": 20530
|
|
},
|
|
{
|
|
"entropy": 5.545000171661377,
|
|
"epoch": 2.306284045600045,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00044750557899115407,
|
|
"loss": 5.27,
|
|
"mean_token_accuracy": 0.1891551986336708,
|
|
"num_tokens": 45822863.0,
|
|
"step": 20535
|
|
},
|
|
{
|
|
"entropy": 5.529285907745361,
|
|
"epoch": 2.3068456225080025,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004474798001356859,
|
|
"loss": 5.2805,
|
|
"mean_token_accuracy": 0.1944286823272705,
|
|
"num_tokens": 45833585.0,
|
|
"step": 20540
|
|
},
|
|
{
|
|
"entropy": 5.366938209533691,
|
|
"epoch": 2.30740719941596,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.000447454015788394,
|
|
"loss": 5.0982,
|
|
"mean_token_accuracy": 0.20143962204456328,
|
|
"num_tokens": 45844745.0,
|
|
"step": 20545
|
|
},
|
|
{
|
|
"entropy": 5.422857475280762,
|
|
"epoch": 2.3079687763239174,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004474282259500992,
|
|
"loss": 5.185,
|
|
"mean_token_accuracy": 0.20190047919750215,
|
|
"num_tokens": 45856018.0,
|
|
"step": 20550
|
|
},
|
|
{
|
|
"entropy": 5.541861200332642,
|
|
"epoch": 2.308530353231875,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000447402430621623,
|
|
"loss": 5.2822,
|
|
"mean_token_accuracy": 0.19415438324213027,
|
|
"num_tokens": 45867182.0,
|
|
"step": 20555
|
|
},
|
|
{
|
|
"entropy": 5.525685834884643,
|
|
"epoch": 2.3090919301398327,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004473766298037865,
|
|
"loss": 5.3643,
|
|
"mean_token_accuracy": 0.18285060822963714,
|
|
"num_tokens": 45880116.0,
|
|
"step": 20560
|
|
},
|
|
{
|
|
"entropy": 5.571984338760376,
|
|
"epoch": 2.3096535070477904,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00044735082349741116,
|
|
"loss": 5.3002,
|
|
"mean_token_accuracy": 0.19150526374578475,
|
|
"num_tokens": 45891143.0,
|
|
"step": 20565
|
|
},
|
|
{
|
|
"entropy": 5.514363384246826,
|
|
"epoch": 2.3102150839557476,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00044732501170331886,
|
|
"loss": 5.1928,
|
|
"mean_token_accuracy": 0.19794349521398544,
|
|
"num_tokens": 45901443.0,
|
|
"step": 20570
|
|
},
|
|
{
|
|
"entropy": 5.568791723251342,
|
|
"epoch": 2.3107766608637053,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004472991944223313,
|
|
"loss": 5.2944,
|
|
"mean_token_accuracy": 0.18966622203588485,
|
|
"num_tokens": 45913313.0,
|
|
"step": 20575
|
|
},
|
|
{
|
|
"entropy": 5.533223104476929,
|
|
"epoch": 2.311338237771663,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00044727337165527056,
|
|
"loss": 5.3339,
|
|
"mean_token_accuracy": 0.18738346099853515,
|
|
"num_tokens": 45925248.0,
|
|
"step": 20580
|
|
},
|
|
{
|
|
"entropy": 5.617816352844239,
|
|
"epoch": 2.31189981467962,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00044724754340295887,
|
|
"loss": 5.3318,
|
|
"mean_token_accuracy": 0.19027050882577895,
|
|
"num_tokens": 45936366.0,
|
|
"step": 20585
|
|
},
|
|
{
|
|
"entropy": 5.450673580169678,
|
|
"epoch": 2.312461391587578,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004472217096662186,
|
|
"loss": 5.1696,
|
|
"mean_token_accuracy": 0.20805188417434692,
|
|
"num_tokens": 45947732.0,
|
|
"step": 20590
|
|
},
|
|
{
|
|
"entropy": 5.46936731338501,
|
|
"epoch": 2.3130229684955355,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004471958704458723,
|
|
"loss": 5.2308,
|
|
"mean_token_accuracy": 0.19785091131925583,
|
|
"num_tokens": 45958655.0,
|
|
"step": 20595
|
|
},
|
|
{
|
|
"entropy": 5.523629999160766,
|
|
"epoch": 2.313584545403493,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00044717002574274267,
|
|
"loss": 5.3072,
|
|
"mean_token_accuracy": 0.19829923659563065,
|
|
"num_tokens": 45970767.0,
|
|
"step": 20600
|
|
},
|
|
{
|
|
"entropy": 5.422164011001587,
|
|
"epoch": 2.314146122311451,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004471441755576527,
|
|
"loss": 5.1213,
|
|
"mean_token_accuracy": 0.20740276277065278,
|
|
"num_tokens": 45981063.0,
|
|
"step": 20605
|
|
},
|
|
{
|
|
"entropy": 5.392886590957642,
|
|
"epoch": 2.314707699219408,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00044711831989142534,
|
|
"loss": 5.0888,
|
|
"mean_token_accuracy": 0.20422577857971191,
|
|
"num_tokens": 45991963.0,
|
|
"step": 20610
|
|
},
|
|
{
|
|
"entropy": 5.4641026020050045,
|
|
"epoch": 2.3152692761273657,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00044709245874488405,
|
|
"loss": 5.3477,
|
|
"mean_token_accuracy": 0.18637771755456925,
|
|
"num_tokens": 46003460.0,
|
|
"step": 20615
|
|
},
|
|
{
|
|
"entropy": 5.521129322052002,
|
|
"epoch": 2.3158308530353233,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004470665921188519,
|
|
"loss": 5.2284,
|
|
"mean_token_accuracy": 0.19587883800268174,
|
|
"num_tokens": 46014338.0,
|
|
"step": 20620
|
|
},
|
|
{
|
|
"entropy": 5.4204026222229,
|
|
"epoch": 2.3163924299432805,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00044704072001415285,
|
|
"loss": 5.1001,
|
|
"mean_token_accuracy": 0.20640003085136413,
|
|
"num_tokens": 46025282.0,
|
|
"step": 20625
|
|
},
|
|
{
|
|
"entropy": 5.452847051620483,
|
|
"epoch": 2.316954006851238,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00044701484243161055,
|
|
"loss": 5.2719,
|
|
"mean_token_accuracy": 0.1958751544356346,
|
|
"num_tokens": 46035303.0,
|
|
"step": 20630
|
|
},
|
|
{
|
|
"entropy": 5.46298303604126,
|
|
"epoch": 2.317515583759196,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000446988959372049,
|
|
"loss": 5.2433,
|
|
"mean_token_accuracy": 0.2012130707502365,
|
|
"num_tokens": 46046336.0,
|
|
"step": 20635
|
|
},
|
|
{
|
|
"entropy": 5.400800323486328,
|
|
"epoch": 2.3180771606671535,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004469630708362922,
|
|
"loss": 5.1206,
|
|
"mean_token_accuracy": 0.19708970487117766,
|
|
"num_tokens": 46056862.0,
|
|
"step": 20640
|
|
},
|
|
{
|
|
"entropy": 5.591737842559814,
|
|
"epoch": 2.3186387375751107,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004469371768251646,
|
|
"loss": 5.2662,
|
|
"mean_token_accuracy": 0.19652716517448426,
|
|
"num_tokens": 46067785.0,
|
|
"step": 20645
|
|
},
|
|
{
|
|
"entropy": 5.46607027053833,
|
|
"epoch": 2.3192003144830684,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004469112773394906,
|
|
"loss": 5.2525,
|
|
"mean_token_accuracy": 0.18587084263563156,
|
|
"num_tokens": 46080553.0,
|
|
"step": 20650
|
|
},
|
|
{
|
|
"entropy": 5.50519323348999,
|
|
"epoch": 2.319761891391026,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004468853723800948,
|
|
"loss": 5.2042,
|
|
"mean_token_accuracy": 0.19355346262454987,
|
|
"num_tokens": 46090985.0,
|
|
"step": 20655
|
|
},
|
|
{
|
|
"entropy": 5.560759830474853,
|
|
"epoch": 2.3203234682989837,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004468594619478021,
|
|
"loss": 5.2913,
|
|
"mean_token_accuracy": 0.1927972510457039,
|
|
"num_tokens": 46101990.0,
|
|
"step": 20660
|
|
},
|
|
{
|
|
"entropy": 5.394636392593384,
|
|
"epoch": 2.320885045206941,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004468335460434375,
|
|
"loss": 5.1439,
|
|
"mean_token_accuracy": 0.203435218334198,
|
|
"num_tokens": 46112853.0,
|
|
"step": 20665
|
|
},
|
|
{
|
|
"entropy": 5.463116931915283,
|
|
"epoch": 2.3214466221148986,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004468076246678261,
|
|
"loss": 5.2555,
|
|
"mean_token_accuracy": 0.19200120866298676,
|
|
"num_tokens": 46123508.0,
|
|
"step": 20670
|
|
},
|
|
{
|
|
"entropy": 5.627512788772583,
|
|
"epoch": 2.3220081990228563,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00044678169782179334,
|
|
"loss": 5.3533,
|
|
"mean_token_accuracy": 0.19093358218669892,
|
|
"num_tokens": 46135394.0,
|
|
"step": 20675
|
|
},
|
|
{
|
|
"entropy": 5.581290245056152,
|
|
"epoch": 2.3225697759308135,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00044675576550616466,
|
|
"loss": 5.3046,
|
|
"mean_token_accuracy": 0.1954210266470909,
|
|
"num_tokens": 46146838.0,
|
|
"step": 20680
|
|
},
|
|
{
|
|
"entropy": 5.542792224884034,
|
|
"epoch": 2.323131352838771,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00044672982772176584,
|
|
"loss": 5.1875,
|
|
"mean_token_accuracy": 0.20086237639188767,
|
|
"num_tokens": 46157116.0,
|
|
"step": 20685
|
|
},
|
|
{
|
|
"entropy": 5.413563823699951,
|
|
"epoch": 2.323692929746729,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004467038844694227,
|
|
"loss": 5.1904,
|
|
"mean_token_accuracy": 0.19913049936294555,
|
|
"num_tokens": 46168405.0,
|
|
"step": 20690
|
|
},
|
|
{
|
|
"entropy": 5.4855122566223145,
|
|
"epoch": 2.3242545066546865,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004466779357499612,
|
|
"loss": 5.2279,
|
|
"mean_token_accuracy": 0.19788960069417955,
|
|
"num_tokens": 46179907.0,
|
|
"step": 20695
|
|
},
|
|
{
|
|
"entropy": 5.473715448379517,
|
|
"epoch": 2.324816083562644,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00044665198156420774,
|
|
"loss": 5.1498,
|
|
"mean_token_accuracy": 0.1955687463283539,
|
|
"num_tokens": 46190750.0,
|
|
"step": 20700
|
|
},
|
|
{
|
|
"entropy": 5.458232975006103,
|
|
"epoch": 2.3253776604706013,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00044662602191298856,
|
|
"loss": 5.1499,
|
|
"mean_token_accuracy": 0.20274998545646666,
|
|
"num_tokens": 46201364.0,
|
|
"step": 20705
|
|
},
|
|
{
|
|
"entropy": 5.477144384384156,
|
|
"epoch": 2.325939237378559,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00044660005679713027,
|
|
"loss": 5.1724,
|
|
"mean_token_accuracy": 0.19556164145469665,
|
|
"num_tokens": 46212341.0,
|
|
"step": 20710
|
|
},
|
|
{
|
|
"entropy": 5.454949378967285,
|
|
"epoch": 2.3265008142865167,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00044657408621745964,
|
|
"loss": 5.2605,
|
|
"mean_token_accuracy": 0.19336785972118378,
|
|
"num_tokens": 46223286.0,
|
|
"step": 20715
|
|
},
|
|
{
|
|
"entropy": 5.395768880844116,
|
|
"epoch": 2.327062391194474,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004465481101748036,
|
|
"loss": 5.2775,
|
|
"mean_token_accuracy": 0.19591585844755172,
|
|
"num_tokens": 46234787.0,
|
|
"step": 20720
|
|
},
|
|
{
|
|
"entropy": 5.513534641265869,
|
|
"epoch": 2.3276239681024316,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00044652212866998914,
|
|
"loss": 5.1267,
|
|
"mean_token_accuracy": 0.20190000236034394,
|
|
"num_tokens": 46244845.0,
|
|
"step": 20725
|
|
},
|
|
{
|
|
"entropy": 5.5209887504577635,
|
|
"epoch": 2.328185545010389,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00044649614170384354,
|
|
"loss": 5.2636,
|
|
"mean_token_accuracy": 0.1971845492720604,
|
|
"num_tokens": 46256352.0,
|
|
"step": 20730
|
|
},
|
|
{
|
|
"entropy": 5.631619215011597,
|
|
"epoch": 2.328747121918347,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00044647014927719436,
|
|
"loss": 5.4191,
|
|
"mean_token_accuracy": 0.18905749171972275,
|
|
"num_tokens": 46268535.0,
|
|
"step": 20735
|
|
},
|
|
{
|
|
"entropy": 5.476808261871338,
|
|
"epoch": 2.329308698826304,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00044644415139086913,
|
|
"loss": 5.213,
|
|
"mean_token_accuracy": 0.20166843831539155,
|
|
"num_tokens": 46279164.0,
|
|
"step": 20740
|
|
},
|
|
{
|
|
"entropy": 5.431314468383789,
|
|
"epoch": 2.3298702757342618,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004464181480456955,
|
|
"loss": 5.0825,
|
|
"mean_token_accuracy": 0.2080667272210121,
|
|
"num_tokens": 46289379.0,
|
|
"step": 20745
|
|
},
|
|
{
|
|
"entropy": 5.424643087387085,
|
|
"epoch": 2.3304318526422194,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004463921392425017,
|
|
"loss": 5.1219,
|
|
"mean_token_accuracy": 0.2021471932530403,
|
|
"num_tokens": 46301023.0,
|
|
"step": 20750
|
|
},
|
|
{
|
|
"entropy": 5.475365257263183,
|
|
"epoch": 2.330993429550177,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00044636612498211566,
|
|
"loss": 5.2373,
|
|
"mean_token_accuracy": 0.2012315347790718,
|
|
"num_tokens": 46312043.0,
|
|
"step": 20755
|
|
},
|
|
{
|
|
"entropy": 5.406970405578614,
|
|
"epoch": 2.3315550064581343,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00044634010526536575,
|
|
"loss": 5.1932,
|
|
"mean_token_accuracy": 0.19140066504478453,
|
|
"num_tokens": 46322808.0,
|
|
"step": 20760
|
|
},
|
|
{
|
|
"entropy": 5.508573865890503,
|
|
"epoch": 2.332116583366092,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004463140800930804,
|
|
"loss": 5.2605,
|
|
"mean_token_accuracy": 0.19064713418483734,
|
|
"num_tokens": 46334260.0,
|
|
"step": 20765
|
|
},
|
|
{
|
|
"entropy": 5.501081562042236,
|
|
"epoch": 2.3326781602740496,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004462880494660883,
|
|
"loss": 5.2287,
|
|
"mean_token_accuracy": 0.1961723119020462,
|
|
"num_tokens": 46344245.0,
|
|
"step": 20770
|
|
},
|
|
{
|
|
"entropy": 5.452253627777099,
|
|
"epoch": 2.333239737182007,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00044626201338521834,
|
|
"loss": 5.1576,
|
|
"mean_token_accuracy": 0.1990344777703285,
|
|
"num_tokens": 46356105.0,
|
|
"step": 20775
|
|
},
|
|
{
|
|
"entropy": 5.375404214859008,
|
|
"epoch": 2.3338013140899645,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004462359718512993,
|
|
"loss": 5.1464,
|
|
"mean_token_accuracy": 0.20020316839218139,
|
|
"num_tokens": 46367591.0,
|
|
"step": 20780
|
|
},
|
|
{
|
|
"entropy": 5.444856309890747,
|
|
"epoch": 2.334362890997922,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00044620992486516073,
|
|
"loss": 5.1699,
|
|
"mean_token_accuracy": 0.19651600420475007,
|
|
"num_tokens": 46379022.0,
|
|
"step": 20785
|
|
},
|
|
{
|
|
"entropy": 5.448221921920776,
|
|
"epoch": 2.33492446790588,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004461838724276316,
|
|
"loss": 5.1906,
|
|
"mean_token_accuracy": 0.20681209713220597,
|
|
"num_tokens": 46390988.0,
|
|
"step": 20790
|
|
},
|
|
{
|
|
"entropy": 5.493107652664184,
|
|
"epoch": 2.3354860448138375,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00044615781453954164,
|
|
"loss": 5.2515,
|
|
"mean_token_accuracy": 0.1984211578965187,
|
|
"num_tokens": 46401576.0,
|
|
"step": 20795
|
|
},
|
|
{
|
|
"entropy": 5.46716947555542,
|
|
"epoch": 2.3360476217217947,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00044613175120172035,
|
|
"loss": 5.1302,
|
|
"mean_token_accuracy": 0.2037460535764694,
|
|
"num_tokens": 46413114.0,
|
|
"step": 20800
|
|
},
|
|
{
|
|
"entropy": 5.38899416923523,
|
|
"epoch": 2.3366091986297524,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004461056824149979,
|
|
"loss": 5.1383,
|
|
"mean_token_accuracy": 0.20543973594903947,
|
|
"num_tokens": 46424000.0,
|
|
"step": 20805
|
|
},
|
|
{
|
|
"entropy": 5.492922019958496,
|
|
"epoch": 2.33717077553771,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.000446079608180204,
|
|
"loss": 5.1985,
|
|
"mean_token_accuracy": 0.19603900611400604,
|
|
"num_tokens": 46435392.0,
|
|
"step": 20810
|
|
},
|
|
{
|
|
"entropy": 5.388095331192017,
|
|
"epoch": 2.3377323524456672,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004460535284981692,
|
|
"loss": 5.1047,
|
|
"mean_token_accuracy": 0.19755102396011354,
|
|
"num_tokens": 46445876.0,
|
|
"step": 20815
|
|
},
|
|
{
|
|
"entropy": 5.492770433425903,
|
|
"epoch": 2.338293929353625,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004460274433697235,
|
|
"loss": 5.1972,
|
|
"mean_token_accuracy": 0.19560093581676483,
|
|
"num_tokens": 46457175.0,
|
|
"step": 20820
|
|
},
|
|
{
|
|
"entropy": 5.529646205902099,
|
|
"epoch": 2.3388555062615826,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00044600135279569784,
|
|
"loss": 5.3371,
|
|
"mean_token_accuracy": 0.19093599766492844,
|
|
"num_tokens": 46469100.0,
|
|
"step": 20825
|
|
},
|
|
{
|
|
"entropy": 5.451491498947144,
|
|
"epoch": 2.3394170831695402,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00044597525677692273,
|
|
"loss": 5.1585,
|
|
"mean_token_accuracy": 0.19938063323497773,
|
|
"num_tokens": 46481221.0,
|
|
"step": 20830
|
|
},
|
|
{
|
|
"entropy": 5.414064264297485,
|
|
"epoch": 2.3399786600774974,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004459491553142291,
|
|
"loss": 5.1088,
|
|
"mean_token_accuracy": 0.2074011042714119,
|
|
"num_tokens": 46492127.0,
|
|
"step": 20835
|
|
},
|
|
{
|
|
"entropy": 5.471398162841797,
|
|
"epoch": 2.340540236985455,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00044592304840844813,
|
|
"loss": 5.2045,
|
|
"mean_token_accuracy": 0.19230275005102157,
|
|
"num_tokens": 46502880.0,
|
|
"step": 20840
|
|
},
|
|
{
|
|
"entropy": 5.4528186321258545,
|
|
"epoch": 2.3411018138934128,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000445896936060411,
|
|
"loss": 5.1434,
|
|
"mean_token_accuracy": 0.20249173939228057,
|
|
"num_tokens": 46513483.0,
|
|
"step": 20845
|
|
},
|
|
{
|
|
"entropy": 5.447299814224243,
|
|
"epoch": 2.3416633908013704,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00044587081827094906,
|
|
"loss": 5.2349,
|
|
"mean_token_accuracy": 0.19579770565032958,
|
|
"num_tokens": 46526110.0,
|
|
"step": 20850
|
|
},
|
|
{
|
|
"entropy": 5.451260757446289,
|
|
"epoch": 2.3422249677093276,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00044584469504089407,
|
|
"loss": 5.2106,
|
|
"mean_token_accuracy": 0.19846130758523942,
|
|
"num_tokens": 46537832.0,
|
|
"step": 20855
|
|
},
|
|
{
|
|
"entropy": 5.39276089668274,
|
|
"epoch": 2.3427865446172853,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004458185663710777,
|
|
"loss": 5.1322,
|
|
"mean_token_accuracy": 0.19853869676589966,
|
|
"num_tokens": 46548553.0,
|
|
"step": 20860
|
|
},
|
|
{
|
|
"entropy": 5.538682842254639,
|
|
"epoch": 2.343348121525243,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004457924322623319,
|
|
"loss": 5.3082,
|
|
"mean_token_accuracy": 0.19690529853105546,
|
|
"num_tokens": 46561095.0,
|
|
"step": 20865
|
|
},
|
|
{
|
|
"entropy": 5.572622776031494,
|
|
"epoch": 2.3439096984332,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00044576629271548884,
|
|
"loss": 5.3001,
|
|
"mean_token_accuracy": 0.19458558559417724,
|
|
"num_tokens": 46572070.0,
|
|
"step": 20870
|
|
},
|
|
{
|
|
"entropy": 5.58575325012207,
|
|
"epoch": 2.344471275341158,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004457401477313808,
|
|
"loss": 5.324,
|
|
"mean_token_accuracy": 0.19038349390029907,
|
|
"num_tokens": 46583355.0,
|
|
"step": 20875
|
|
},
|
|
{
|
|
"entropy": 5.484343814849853,
|
|
"epoch": 2.3450328522491155,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004457139973108403,
|
|
"loss": 5.2034,
|
|
"mean_token_accuracy": 0.1940722569823265,
|
|
"num_tokens": 46594909.0,
|
|
"step": 20880
|
|
},
|
|
{
|
|
"entropy": 5.560077762603759,
|
|
"epoch": 2.345594429157073,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004456878414546998,
|
|
"loss": 5.2618,
|
|
"mean_token_accuracy": 0.19874756783246994,
|
|
"num_tokens": 46606245.0,
|
|
"step": 20885
|
|
},
|
|
{
|
|
"entropy": 5.407064533233642,
|
|
"epoch": 2.346156006065031,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00044566168016379234,
|
|
"loss": 5.1625,
|
|
"mean_token_accuracy": 0.19909542053937912,
|
|
"num_tokens": 46617761.0,
|
|
"step": 20890
|
|
},
|
|
{
|
|
"entropy": 5.4622338771820065,
|
|
"epoch": 2.346717582972988,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004456355134389507,
|
|
"loss": 5.1911,
|
|
"mean_token_accuracy": 0.19062627702951432,
|
|
"num_tokens": 46628947.0,
|
|
"step": 20895
|
|
},
|
|
{
|
|
"entropy": 5.466204071044922,
|
|
"epoch": 2.3472791598809457,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00044560934128100814,
|
|
"loss": 5.2053,
|
|
"mean_token_accuracy": 0.1994910404086113,
|
|
"num_tokens": 46640243.0,
|
|
"step": 20900
|
|
},
|
|
{
|
|
"entropy": 5.38988094329834,
|
|
"epoch": 2.3478407367889034,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00044558316369079805,
|
|
"loss": 5.1334,
|
|
"mean_token_accuracy": 0.19735938757658006,
|
|
"num_tokens": 46650328.0,
|
|
"step": 20905
|
|
},
|
|
{
|
|
"entropy": 5.369638967514038,
|
|
"epoch": 2.3484023136968606,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00044555698066915385,
|
|
"loss": 5.1271,
|
|
"mean_token_accuracy": 0.19721096605062485,
|
|
"num_tokens": 46661770.0,
|
|
"step": 20910
|
|
},
|
|
{
|
|
"entropy": 5.419118976593017,
|
|
"epoch": 2.3489638906048182,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004455307922169092,
|
|
"loss": 5.0799,
|
|
"mean_token_accuracy": 0.2022887259721756,
|
|
"num_tokens": 46673075.0,
|
|
"step": 20915
|
|
},
|
|
{
|
|
"entropy": 5.484280824661255,
|
|
"epoch": 2.349525467512776,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004455045983348979,
|
|
"loss": 5.2202,
|
|
"mean_token_accuracy": 0.1938351273536682,
|
|
"num_tokens": 46684040.0,
|
|
"step": 20920
|
|
},
|
|
{
|
|
"entropy": 5.423160791397095,
|
|
"epoch": 2.3500870444207336,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004454783990239542,
|
|
"loss": 5.1123,
|
|
"mean_token_accuracy": 0.2010540097951889,
|
|
"num_tokens": 46696295.0,
|
|
"step": 20925
|
|
},
|
|
{
|
|
"entropy": 5.433575105667114,
|
|
"epoch": 2.350648621328691,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00044545219428491215,
|
|
"loss": 5.1991,
|
|
"mean_token_accuracy": 0.200055393576622,
|
|
"num_tokens": 46706399.0,
|
|
"step": 20930
|
|
},
|
|
{
|
|
"entropy": 5.505274534225464,
|
|
"epoch": 2.3512101982366485,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00044542598411860605,
|
|
"loss": 5.3113,
|
|
"mean_token_accuracy": 0.1915813311934471,
|
|
"num_tokens": 46717644.0,
|
|
"step": 20935
|
|
},
|
|
{
|
|
"entropy": 5.613769245147705,
|
|
"epoch": 2.351771775144606,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004453997685258706,
|
|
"loss": 5.2798,
|
|
"mean_token_accuracy": 0.19733862429857255,
|
|
"num_tokens": 46728556.0,
|
|
"step": 20940
|
|
},
|
|
{
|
|
"entropy": 5.487457799911499,
|
|
"epoch": 2.3523333520525638,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00044537354750754033,
|
|
"loss": 5.19,
|
|
"mean_token_accuracy": 0.20072409212589265,
|
|
"num_tokens": 46739730.0,
|
|
"step": 20945
|
|
},
|
|
{
|
|
"entropy": 5.520910835266113,
|
|
"epoch": 2.352894928960521,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004453473210644503,
|
|
"loss": 5.286,
|
|
"mean_token_accuracy": 0.19550357908010482,
|
|
"num_tokens": 46752349.0,
|
|
"step": 20950
|
|
},
|
|
{
|
|
"entropy": 5.52295446395874,
|
|
"epoch": 2.3534565058684787,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004453210891974355,
|
|
"loss": 5.2533,
|
|
"mean_token_accuracy": 0.19241360276937486,
|
|
"num_tokens": 46763771.0,
|
|
"step": 20955
|
|
},
|
|
{
|
|
"entropy": 5.5087450504302975,
|
|
"epoch": 2.3540180827764363,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00044529485190733113,
|
|
"loss": 5.1847,
|
|
"mean_token_accuracy": 0.19992031306028366,
|
|
"num_tokens": 46773371.0,
|
|
"step": 20960
|
|
},
|
|
{
|
|
"entropy": 5.435989713668823,
|
|
"epoch": 2.3545796596843935,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004452686091949727,
|
|
"loss": 5.1631,
|
|
"mean_token_accuracy": 0.20077840387821197,
|
|
"num_tokens": 46784244.0,
|
|
"step": 20965
|
|
},
|
|
{
|
|
"entropy": 5.4940653324127195,
|
|
"epoch": 2.355141236592351,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00044524236106119563,
|
|
"loss": 5.2489,
|
|
"mean_token_accuracy": 0.1923815131187439,
|
|
"num_tokens": 46795373.0,
|
|
"step": 20970
|
|
},
|
|
{
|
|
"entropy": 5.559467124938965,
|
|
"epoch": 2.355702813500309,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00044521610750683586,
|
|
"loss": 5.2519,
|
|
"mean_token_accuracy": 0.1975223660469055,
|
|
"num_tokens": 46806342.0,
|
|
"step": 20975
|
|
},
|
|
{
|
|
"entropy": 5.41952109336853,
|
|
"epoch": 2.3562643904082665,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004451898485327291,
|
|
"loss": 5.1612,
|
|
"mean_token_accuracy": 0.20110985189676284,
|
|
"num_tokens": 46817576.0,
|
|
"step": 20980
|
|
},
|
|
{
|
|
"entropy": 5.420933961868286,
|
|
"epoch": 2.356825967316224,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004451635841397116,
|
|
"loss": 5.2282,
|
|
"mean_token_accuracy": 0.19303133636713027,
|
|
"num_tokens": 46829335.0,
|
|
"step": 20985
|
|
},
|
|
{
|
|
"entropy": 5.519724988937378,
|
|
"epoch": 2.3573875442241814,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004451373143286195,
|
|
"loss": 5.2745,
|
|
"mean_token_accuracy": 0.19118888974189757,
|
|
"num_tokens": 46841334.0,
|
|
"step": 20990
|
|
},
|
|
{
|
|
"entropy": 5.57857232093811,
|
|
"epoch": 2.357949121132139,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00044511103910028945,
|
|
"loss": 5.4278,
|
|
"mean_token_accuracy": 0.19080803245306016,
|
|
"num_tokens": 46852418.0,
|
|
"step": 20995
|
|
},
|
|
{
|
|
"entropy": 5.577915334701538,
|
|
"epoch": 2.3585106980400967,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004450847584555579,
|
|
"loss": 5.2815,
|
|
"mean_token_accuracy": 0.19626296162605286,
|
|
"num_tokens": 46863743.0,
|
|
"step": 21000
|
|
},
|
|
{
|
|
"epoch": 2.3585106980400967,
|
|
"eval_entropy": 5.332942704118833,
|
|
"eval_loss": 5.344221591949463,
|
|
"eval_mean_token_accuracy": 0.19913381254139528,
|
|
"eval_num_tokens": 46863743.0,
|
|
"eval_runtime": 23.697,
|
|
"eval_samples_per_second": 1308.728,
|
|
"eval_steps_per_second": 163.607,
|
|
"step": 21000
|
|
},
|
|
{
|
|
"entropy": 5.425669097900391,
|
|
"epoch": 2.359072274948054,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004450584723952617,
|
|
"loss": 5.1023,
|
|
"mean_token_accuracy": 0.19782320261001587,
|
|
"num_tokens": 46873628.0,
|
|
"step": 21005
|
|
},
|
|
{
|
|
"entropy": 5.528709173202515,
|
|
"epoch": 2.3596338518560116,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004450321809202377,
|
|
"loss": 5.2874,
|
|
"mean_token_accuracy": 0.18882786184549333,
|
|
"num_tokens": 46885288.0,
|
|
"step": 21010
|
|
},
|
|
{
|
|
"entropy": 5.531344079971314,
|
|
"epoch": 2.3601954287639693,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004450058840313232,
|
|
"loss": 5.2575,
|
|
"mean_token_accuracy": 0.19361186623573304,
|
|
"num_tokens": 46897027.0,
|
|
"step": 21015
|
|
},
|
|
{
|
|
"entropy": 5.409613800048828,
|
|
"epoch": 2.360757005671927,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00044497958172935536,
|
|
"loss": 5.1471,
|
|
"mean_token_accuracy": 0.19863545894622803,
|
|
"num_tokens": 46907947.0,
|
|
"step": 21020
|
|
},
|
|
{
|
|
"entropy": 5.421298170089722,
|
|
"epoch": 2.361318582579884,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004449532740151717,
|
|
"loss": 5.1952,
|
|
"mean_token_accuracy": 0.20064647346735,
|
|
"num_tokens": 46918334.0,
|
|
"step": 21025
|
|
},
|
|
{
|
|
"entropy": 5.468659114837647,
|
|
"epoch": 2.361880159487842,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00044492696088960985,
|
|
"loss": 5.2638,
|
|
"mean_token_accuracy": 0.20052294433116913,
|
|
"num_tokens": 46929710.0,
|
|
"step": 21030
|
|
},
|
|
{
|
|
"entropy": 5.478493356704712,
|
|
"epoch": 2.3624417363957995,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004449006423535078,
|
|
"loss": 5.2107,
|
|
"mean_token_accuracy": 0.1907900795340538,
|
|
"num_tokens": 46941436.0,
|
|
"step": 21035
|
|
},
|
|
{
|
|
"entropy": 5.561452436447143,
|
|
"epoch": 2.363003313303757,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00044487431840770325,
|
|
"loss": 5.2492,
|
|
"mean_token_accuracy": 0.19540422409772873,
|
|
"num_tokens": 46953673.0,
|
|
"step": 21040
|
|
},
|
|
{
|
|
"entropy": 5.4241691589355465,
|
|
"epoch": 2.3635648902117143,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004448479890530347,
|
|
"loss": 5.1262,
|
|
"mean_token_accuracy": 0.20031379014253617,
|
|
"num_tokens": 46964412.0,
|
|
"step": 21045
|
|
},
|
|
{
|
|
"entropy": 5.394551086425781,
|
|
"epoch": 2.364126467119672,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00044482165429034014,
|
|
"loss": 5.1978,
|
|
"mean_token_accuracy": 0.19813333153724672,
|
|
"num_tokens": 46975159.0,
|
|
"step": 21050
|
|
},
|
|
{
|
|
"entropy": 5.475469446182251,
|
|
"epoch": 2.3646880440276297,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004447953141204583,
|
|
"loss": 5.1862,
|
|
"mean_token_accuracy": 0.2049855351448059,
|
|
"num_tokens": 46987165.0,
|
|
"step": 21055
|
|
},
|
|
{
|
|
"entropy": 5.560744094848633,
|
|
"epoch": 2.365249620935587,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00044476896854422785,
|
|
"loss": 5.2877,
|
|
"mean_token_accuracy": 0.18687691390514374,
|
|
"num_tokens": 46999085.0,
|
|
"step": 21060
|
|
},
|
|
{
|
|
"entropy": 5.496333026885987,
|
|
"epoch": 2.3658111978435445,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00044474261756248745,
|
|
"loss": 5.2659,
|
|
"mean_token_accuracy": 0.19189661294221877,
|
|
"num_tokens": 47010970.0,
|
|
"step": 21065
|
|
},
|
|
{
|
|
"entropy": 5.507092428207398,
|
|
"epoch": 2.366372774751502,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004447162611760764,
|
|
"loss": 5.1938,
|
|
"mean_token_accuracy": 0.20141583383083345,
|
|
"num_tokens": 47021396.0,
|
|
"step": 21070
|
|
},
|
|
{
|
|
"entropy": 5.526192331314087,
|
|
"epoch": 2.36693435165946,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004446898993858338,
|
|
"loss": 5.2316,
|
|
"mean_token_accuracy": 0.1941898286342621,
|
|
"num_tokens": 47033394.0,
|
|
"step": 21075
|
|
},
|
|
{
|
|
"entropy": 5.485520839691162,
|
|
"epoch": 2.3674959285674175,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00044466353219259884,
|
|
"loss": 5.2322,
|
|
"mean_token_accuracy": 0.19840211272239686,
|
|
"num_tokens": 47044688.0,
|
|
"step": 21080
|
|
},
|
|
{
|
|
"entropy": 5.578689193725586,
|
|
"epoch": 2.3680575054753747,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004446371595972114,
|
|
"loss": 5.2939,
|
|
"mean_token_accuracy": 0.19130343198776245,
|
|
"num_tokens": 47057483.0,
|
|
"step": 21085
|
|
},
|
|
{
|
|
"entropy": 5.521618032455445,
|
|
"epoch": 2.3686190823833324,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004446107816005109,
|
|
"loss": 5.2024,
|
|
"mean_token_accuracy": 0.1980918064713478,
|
|
"num_tokens": 47069031.0,
|
|
"step": 21090
|
|
},
|
|
{
|
|
"entropy": 5.469498348236084,
|
|
"epoch": 2.36918065929129,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004445843982033373,
|
|
"loss": 5.229,
|
|
"mean_token_accuracy": 0.19595300406217575,
|
|
"num_tokens": 47080998.0,
|
|
"step": 21095
|
|
},
|
|
{
|
|
"entropy": 5.411626386642456,
|
|
"epoch": 2.3697422361992473,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004445580094065307,
|
|
"loss": 5.2143,
|
|
"mean_token_accuracy": 0.19779896587133408,
|
|
"num_tokens": 47092065.0,
|
|
"step": 21100
|
|
},
|
|
{
|
|
"entropy": 5.495804166793823,
|
|
"epoch": 2.370303813107205,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004445316152109313,
|
|
"loss": 5.2135,
|
|
"mean_token_accuracy": 0.1879710540175438,
|
|
"num_tokens": 47102207.0,
|
|
"step": 21105
|
|
},
|
|
{
|
|
"entropy": 5.464909505844116,
|
|
"epoch": 2.3708653900151626,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004445052156173796,
|
|
"loss": 5.1925,
|
|
"mean_token_accuracy": 0.19657965153455734,
|
|
"num_tokens": 47112675.0,
|
|
"step": 21110
|
|
},
|
|
{
|
|
"entropy": 5.494316959381104,
|
|
"epoch": 2.3714269669231203,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004444788106267161,
|
|
"loss": 5.2422,
|
|
"mean_token_accuracy": 0.20091370046138762,
|
|
"num_tokens": 47123728.0,
|
|
"step": 21115
|
|
},
|
|
{
|
|
"entropy": 5.499920082092285,
|
|
"epoch": 2.3719885438310775,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004444524002397815,
|
|
"loss": 5.2291,
|
|
"mean_token_accuracy": 0.1928659752011299,
|
|
"num_tokens": 47136194.0,
|
|
"step": 21120
|
|
},
|
|
{
|
|
"entropy": 5.387128734588623,
|
|
"epoch": 2.372550120739035,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004444259844574167,
|
|
"loss": 5.0844,
|
|
"mean_token_accuracy": 0.19661763608455657,
|
|
"num_tokens": 47146539.0,
|
|
"step": 21125
|
|
},
|
|
{
|
|
"entropy": 5.5167817115783695,
|
|
"epoch": 2.373111697646993,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00044439956328046296,
|
|
"loss": 5.2679,
|
|
"mean_token_accuracy": 0.19259125292301177,
|
|
"num_tokens": 47158449.0,
|
|
"step": 21130
|
|
},
|
|
{
|
|
"entropy": 5.467296409606933,
|
|
"epoch": 2.3736732745549505,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004443731367097613,
|
|
"loss": 5.1154,
|
|
"mean_token_accuracy": 0.20548777729272844,
|
|
"num_tokens": 47169687.0,
|
|
"step": 21135
|
|
},
|
|
{
|
|
"entropy": 5.304896688461303,
|
|
"epoch": 2.3742348514629077,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00044434670474615334,
|
|
"loss": 5.0061,
|
|
"mean_token_accuracy": 0.20976399332284928,
|
|
"num_tokens": 47179731.0,
|
|
"step": 21140
|
|
},
|
|
{
|
|
"entropy": 5.37644329071045,
|
|
"epoch": 2.3747964283708654,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00044432026739048064,
|
|
"loss": 5.1509,
|
|
"mean_token_accuracy": 0.20831314772367476,
|
|
"num_tokens": 47189925.0,
|
|
"step": 21145
|
|
},
|
|
{
|
|
"entropy": 5.468923187255859,
|
|
"epoch": 2.375358005278823,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000444293824643585,
|
|
"loss": 5.1981,
|
|
"mean_token_accuracy": 0.20327981561422348,
|
|
"num_tokens": 47200637.0,
|
|
"step": 21150
|
|
},
|
|
{
|
|
"entropy": 5.496252775192261,
|
|
"epoch": 2.3759195821867802,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004442673765063082,
|
|
"loss": 5.1965,
|
|
"mean_token_accuracy": 0.19572321623563765,
|
|
"num_tokens": 47211969.0,
|
|
"step": 21155
|
|
},
|
|
{
|
|
"entropy": 5.51967978477478,
|
|
"epoch": 2.376481159094738,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004442409229794925,
|
|
"loss": 5.3411,
|
|
"mean_token_accuracy": 0.19481445103883743,
|
|
"num_tokens": 47223150.0,
|
|
"step": 21160
|
|
},
|
|
{
|
|
"entropy": 5.558747005462647,
|
|
"epoch": 2.3770427360026956,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004442144640639803,
|
|
"loss": 5.2928,
|
|
"mean_token_accuracy": 0.1921680375933647,
|
|
"num_tokens": 47234403.0,
|
|
"step": 21165
|
|
},
|
|
{
|
|
"entropy": 5.467461252212525,
|
|
"epoch": 2.377604312910653,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004441879997606138,
|
|
"loss": 5.1148,
|
|
"mean_token_accuracy": 0.19939623326063155,
|
|
"num_tokens": 47245800.0,
|
|
"step": 21170
|
|
},
|
|
{
|
|
"entropy": 5.438232564926148,
|
|
"epoch": 2.378165889818611,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004441615300702358,
|
|
"loss": 5.1934,
|
|
"mean_token_accuracy": 0.1920433059334755,
|
|
"num_tokens": 47256109.0,
|
|
"step": 21175
|
|
},
|
|
{
|
|
"entropy": 5.431833076477051,
|
|
"epoch": 2.378727466726568,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004441350549936891,
|
|
"loss": 5.1239,
|
|
"mean_token_accuracy": 0.20218961238861083,
|
|
"num_tokens": 47266502.0,
|
|
"step": 21180
|
|
},
|
|
{
|
|
"entropy": 5.517393159866333,
|
|
"epoch": 2.3792890436345258,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004441085745318167,
|
|
"loss": 5.2107,
|
|
"mean_token_accuracy": 0.20080445408821107,
|
|
"num_tokens": 47278866.0,
|
|
"step": 21185
|
|
},
|
|
{
|
|
"entropy": 5.371696949005127,
|
|
"epoch": 2.3798506205424834,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00044408208868546164,
|
|
"loss": 5.1539,
|
|
"mean_token_accuracy": 0.20703070163726806,
|
|
"num_tokens": 47289449.0,
|
|
"step": 21190
|
|
},
|
|
{
|
|
"entropy": 5.440367364883423,
|
|
"epoch": 2.3804121974504406,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004440555974554673,
|
|
"loss": 5.2964,
|
|
"mean_token_accuracy": 0.2001742973923683,
|
|
"num_tokens": 47301026.0,
|
|
"step": 21195
|
|
},
|
|
{
|
|
"entropy": 5.483521270751953,
|
|
"epoch": 2.3809737743583983,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00044402910084267717,
|
|
"loss": 5.1938,
|
|
"mean_token_accuracy": 0.1970280796289444,
|
|
"num_tokens": 47311579.0,
|
|
"step": 21200
|
|
},
|
|
{
|
|
"entropy": 5.457720613479614,
|
|
"epoch": 2.381535351266356,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004440025988479349,
|
|
"loss": 5.1977,
|
|
"mean_token_accuracy": 0.2033959746360779,
|
|
"num_tokens": 47322042.0,
|
|
"step": 21205
|
|
},
|
|
{
|
|
"entropy": 5.470384311676026,
|
|
"epoch": 2.3820969281743136,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00044397609147208436,
|
|
"loss": 5.156,
|
|
"mean_token_accuracy": 0.2049620494246483,
|
|
"num_tokens": 47332821.0,
|
|
"step": 21210
|
|
},
|
|
{
|
|
"entropy": 5.454410362243652,
|
|
"epoch": 2.382658505082271,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004439495787159695,
|
|
"loss": 5.2077,
|
|
"mean_token_accuracy": 0.1985888212919235,
|
|
"num_tokens": 47344221.0,
|
|
"step": 21215
|
|
},
|
|
{
|
|
"entropy": 5.586800050735474,
|
|
"epoch": 2.3832200819902285,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00044392306058043453,
|
|
"loss": 5.3565,
|
|
"mean_token_accuracy": 0.19308149218559265,
|
|
"num_tokens": 47356424.0,
|
|
"step": 21220
|
|
},
|
|
{
|
|
"entropy": 5.4759235858917235,
|
|
"epoch": 2.383781658898186,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004438965370663238,
|
|
"loss": 5.1769,
|
|
"mean_token_accuracy": 0.20478518456220626,
|
|
"num_tokens": 47367546.0,
|
|
"step": 21225
|
|
},
|
|
{
|
|
"entropy": 5.512812709808349,
|
|
"epoch": 2.384343235806144,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004438700081744819,
|
|
"loss": 5.2764,
|
|
"mean_token_accuracy": 0.1924913927912712,
|
|
"num_tokens": 47378281.0,
|
|
"step": 21230
|
|
},
|
|
{
|
|
"entropy": 5.460228967666626,
|
|
"epoch": 2.384904812714101,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00044384347390575337,
|
|
"loss": 5.1493,
|
|
"mean_token_accuracy": 0.20389873534440994,
|
|
"num_tokens": 47389233.0,
|
|
"step": 21235
|
|
},
|
|
{
|
|
"entropy": 5.42513484954834,
|
|
"epoch": 2.3854663896220587,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004438169342609831,
|
|
"loss": 5.1965,
|
|
"mean_token_accuracy": 0.19487940967082978,
|
|
"num_tokens": 47400114.0,
|
|
"step": 21240
|
|
},
|
|
{
|
|
"entropy": 5.627143526077271,
|
|
"epoch": 2.3860279665300164,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00044379038924101627,
|
|
"loss": 5.374,
|
|
"mean_token_accuracy": 0.19131412953138352,
|
|
"num_tokens": 47411926.0,
|
|
"step": 21245
|
|
},
|
|
{
|
|
"entropy": 5.578207778930664,
|
|
"epoch": 2.3865895434379736,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004437638388466979,
|
|
"loss": 5.2383,
|
|
"mean_token_accuracy": 0.1985018417239189,
|
|
"num_tokens": 47424048.0,
|
|
"step": 21250
|
|
},
|
|
{
|
|
"entropy": 5.4164690494537355,
|
|
"epoch": 2.3871511203459312,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00044373728307887353,
|
|
"loss": 5.148,
|
|
"mean_token_accuracy": 0.19993937909603118,
|
|
"num_tokens": 47435581.0,
|
|
"step": 21255
|
|
},
|
|
{
|
|
"entropy": 5.447855997085571,
|
|
"epoch": 2.387712697253889,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00044371072193838857,
|
|
"loss": 5.1636,
|
|
"mean_token_accuracy": 0.20491148233413697,
|
|
"num_tokens": 47446831.0,
|
|
"step": 21260
|
|
},
|
|
{
|
|
"entropy": 5.3792437553405765,
|
|
"epoch": 2.3882742741618466,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00044368415542608874,
|
|
"loss": 5.1374,
|
|
"mean_token_accuracy": 0.19673147648572922,
|
|
"num_tokens": 47457885.0,
|
|
"step": 21265
|
|
},
|
|
{
|
|
"entropy": 5.497529602050781,
|
|
"epoch": 2.3888358510698042,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00044365758354282005,
|
|
"loss": 5.2463,
|
|
"mean_token_accuracy": 0.19050194919109345,
|
|
"num_tokens": 47470195.0,
|
|
"step": 21270
|
|
},
|
|
{
|
|
"entropy": 5.492781734466552,
|
|
"epoch": 2.3893974279777614,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004436310062894285,
|
|
"loss": 5.1939,
|
|
"mean_token_accuracy": 0.20272512584924698,
|
|
"num_tokens": 47481068.0,
|
|
"step": 21275
|
|
},
|
|
{
|
|
"entropy": 5.52130765914917,
|
|
"epoch": 2.389959004885719,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004436044236667603,
|
|
"loss": 5.1542,
|
|
"mean_token_accuracy": 0.2017817109823227,
|
|
"num_tokens": 47491409.0,
|
|
"step": 21280
|
|
},
|
|
{
|
|
"entropy": 5.424414110183716,
|
|
"epoch": 2.3905205817936768,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004435778356756618,
|
|
"loss": 5.2363,
|
|
"mean_token_accuracy": 0.19426699727773666,
|
|
"num_tokens": 47504440.0,
|
|
"step": 21285
|
|
},
|
|
{
|
|
"entropy": 5.434523010253907,
|
|
"epoch": 2.391082158701634,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00044355124231697967,
|
|
"loss": 5.124,
|
|
"mean_token_accuracy": 0.20635359287261962,
|
|
"num_tokens": 47514370.0,
|
|
"step": 21290
|
|
},
|
|
{
|
|
"entropy": 5.462828874588013,
|
|
"epoch": 2.3916437356095916,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004435246435915607,
|
|
"loss": 5.1682,
|
|
"mean_token_accuracy": 0.2015223890542984,
|
|
"num_tokens": 47525415.0,
|
|
"step": 21295
|
|
},
|
|
{
|
|
"entropy": 5.521757555007935,
|
|
"epoch": 2.3922053125175493,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004434980395002516,
|
|
"loss": 5.2496,
|
|
"mean_token_accuracy": 0.19774934351444245,
|
|
"num_tokens": 47537029.0,
|
|
"step": 21300
|
|
},
|
|
{
|
|
"entropy": 5.470596027374268,
|
|
"epoch": 2.392766889425507,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00044347143004389955,
|
|
"loss": 5.1567,
|
|
"mean_token_accuracy": 0.19732739329338073,
|
|
"num_tokens": 47550434.0,
|
|
"step": 21305
|
|
},
|
|
{
|
|
"entropy": 5.438879728317261,
|
|
"epoch": 2.393328466333464,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004434448152233519,
|
|
"loss": 5.1772,
|
|
"mean_token_accuracy": 0.20404388010501862,
|
|
"num_tokens": 47560985.0,
|
|
"step": 21310
|
|
},
|
|
{
|
|
"entropy": 5.51512770652771,
|
|
"epoch": 2.393890043241422,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00044341819503945594,
|
|
"loss": 5.2735,
|
|
"mean_token_accuracy": 0.19304731190204621,
|
|
"num_tokens": 47573207.0,
|
|
"step": 21315
|
|
},
|
|
{
|
|
"entropy": 5.487081050872803,
|
|
"epoch": 2.3944516201493795,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004433915694930594,
|
|
"loss": 5.0995,
|
|
"mean_token_accuracy": 0.21096139401197433,
|
|
"num_tokens": 47584666.0,
|
|
"step": 21320
|
|
},
|
|
{
|
|
"entropy": 5.474404954910279,
|
|
"epoch": 2.395013197057337,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004433649385850099,
|
|
"loss": 5.1937,
|
|
"mean_token_accuracy": 0.19833858609199523,
|
|
"num_tokens": 47598017.0,
|
|
"step": 21325
|
|
},
|
|
{
|
|
"entropy": 5.507979106903076,
|
|
"epoch": 2.3955747739652944,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004433383023161555,
|
|
"loss": 5.3571,
|
|
"mean_token_accuracy": 0.18930508196353912,
|
|
"num_tokens": 47610947.0,
|
|
"step": 21330
|
|
},
|
|
{
|
|
"entropy": 5.5602569580078125,
|
|
"epoch": 2.396136350873252,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004433116606873443,
|
|
"loss": 5.2842,
|
|
"mean_token_accuracy": 0.1920780673623085,
|
|
"num_tokens": 47621393.0,
|
|
"step": 21335
|
|
},
|
|
{
|
|
"entropy": 5.562190246582031,
|
|
"epoch": 2.3966979277812097,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00044328501369942454,
|
|
"loss": 5.246,
|
|
"mean_token_accuracy": 0.19772695749998093,
|
|
"num_tokens": 47631615.0,
|
|
"step": 21340
|
|
},
|
|
{
|
|
"entropy": 5.461170768737793,
|
|
"epoch": 2.3972595046891674,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004432583613532446,
|
|
"loss": 5.215,
|
|
"mean_token_accuracy": 0.19658462107181549,
|
|
"num_tokens": 47642813.0,
|
|
"step": 21345
|
|
},
|
|
{
|
|
"entropy": 5.640759611129761,
|
|
"epoch": 2.3978210815971246,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004432317036496533,
|
|
"loss": 5.2835,
|
|
"mean_token_accuracy": 0.19452656507492067,
|
|
"num_tokens": 47654012.0,
|
|
"step": 21350
|
|
},
|
|
{
|
|
"entropy": 5.476614236831665,
|
|
"epoch": 2.3983826585050823,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00044320504058949916,
|
|
"loss": 5.1519,
|
|
"mean_token_accuracy": 0.20887311398983002,
|
|
"num_tokens": 47664575.0,
|
|
"step": 21355
|
|
},
|
|
{
|
|
"entropy": 5.422935676574707,
|
|
"epoch": 2.39894423541304,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004431783721736314,
|
|
"loss": 5.2253,
|
|
"mean_token_accuracy": 0.19494512677192688,
|
|
"num_tokens": 47674763.0,
|
|
"step": 21360
|
|
},
|
|
{
|
|
"entropy": 5.421364879608154,
|
|
"epoch": 2.3995058123209976,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00044315169840289896,
|
|
"loss": 5.1746,
|
|
"mean_token_accuracy": 0.20039768964052201,
|
|
"num_tokens": 47685435.0,
|
|
"step": 21365
|
|
},
|
|
{
|
|
"entropy": 5.609927320480347,
|
|
"epoch": 2.400067389228955,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004431250192781513,
|
|
"loss": 5.3662,
|
|
"mean_token_accuracy": 0.19823579341173173,
|
|
"num_tokens": 47696634.0,
|
|
"step": 21370
|
|
},
|
|
{
|
|
"entropy": 5.501060819625854,
|
|
"epoch": 2.4006289661369125,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004430983348002378,
|
|
"loss": 5.2362,
|
|
"mean_token_accuracy": 0.19303722083568572,
|
|
"num_tokens": 47707737.0,
|
|
"step": 21375
|
|
},
|
|
{
|
|
"entropy": 5.535626077651978,
|
|
"epoch": 2.40119054304487,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00044307164497000813,
|
|
"loss": 5.2156,
|
|
"mean_token_accuracy": 0.19697881042957305,
|
|
"num_tokens": 47718131.0,
|
|
"step": 21380
|
|
},
|
|
{
|
|
"entropy": 5.419151163101196,
|
|
"epoch": 2.4017521199528273,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00044304494978831204,
|
|
"loss": 5.1904,
|
|
"mean_token_accuracy": 0.19738378822803498,
|
|
"num_tokens": 47730154.0,
|
|
"step": 21385
|
|
},
|
|
{
|
|
"entropy": 5.4863170146942135,
|
|
"epoch": 2.402313696860785,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004430182492559997,
|
|
"loss": 5.1709,
|
|
"mean_token_accuracy": 0.19812498688697816,
|
|
"num_tokens": 47741893.0,
|
|
"step": 21390
|
|
},
|
|
{
|
|
"entropy": 5.505048179626465,
|
|
"epoch": 2.4028752737687427,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000442991543373921,
|
|
"loss": 5.2499,
|
|
"mean_token_accuracy": 0.19859177023172378,
|
|
"num_tokens": 47753430.0,
|
|
"step": 21395
|
|
},
|
|
{
|
|
"entropy": 5.3799785614013675,
|
|
"epoch": 2.4034368506767003,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004429648321429264,
|
|
"loss": 5.159,
|
|
"mean_token_accuracy": 0.2043390080332756,
|
|
"num_tokens": 47765181.0,
|
|
"step": 21400
|
|
},
|
|
{
|
|
"entropy": 5.588997793197632,
|
|
"epoch": 2.4039984275846575,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00044293811556386656,
|
|
"loss": 5.3652,
|
|
"mean_token_accuracy": 0.18540471643209458,
|
|
"num_tokens": 47777211.0,
|
|
"step": 21405
|
|
},
|
|
{
|
|
"entropy": 5.46024489402771,
|
|
"epoch": 2.404560004492615,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004429113936375918,
|
|
"loss": 5.1676,
|
|
"mean_token_accuracy": 0.2016657367348671,
|
|
"num_tokens": 47788397.0,
|
|
"step": 21410
|
|
},
|
|
{
|
|
"entropy": 5.524742555618286,
|
|
"epoch": 2.405121581400573,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00044288466636495323,
|
|
"loss": 5.2796,
|
|
"mean_token_accuracy": 0.19366027265787125,
|
|
"num_tokens": 47799870.0,
|
|
"step": 21415
|
|
},
|
|
{
|
|
"entropy": 5.476950454711914,
|
|
"epoch": 2.4056831583085305,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00044285793374680184,
|
|
"loss": 5.2725,
|
|
"mean_token_accuracy": 0.19704962372779847,
|
|
"num_tokens": 47810696.0,
|
|
"step": 21420
|
|
},
|
|
{
|
|
"entropy": 5.512076807022095,
|
|
"epoch": 2.4062447352164877,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00044283119578398866,
|
|
"loss": 5.2361,
|
|
"mean_token_accuracy": 0.1989618495106697,
|
|
"num_tokens": 47822579.0,
|
|
"step": 21425
|
|
},
|
|
{
|
|
"entropy": 5.459765291213989,
|
|
"epoch": 2.4068063121244454,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004428044524773651,
|
|
"loss": 5.1445,
|
|
"mean_token_accuracy": 0.19508033692836763,
|
|
"num_tokens": 47832556.0,
|
|
"step": 21430
|
|
},
|
|
{
|
|
"entropy": 5.459570598602295,
|
|
"epoch": 2.407367889032403,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004427777038277827,
|
|
"loss": 5.2222,
|
|
"mean_token_accuracy": 0.19387545585632324,
|
|
"num_tokens": 47844409.0,
|
|
"step": 21435
|
|
},
|
|
{
|
|
"entropy": 5.482930707931518,
|
|
"epoch": 2.4079294659403607,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00044275094983609313,
|
|
"loss": 5.1683,
|
|
"mean_token_accuracy": 0.20039867460727692,
|
|
"num_tokens": 47855666.0,
|
|
"step": 21440
|
|
},
|
|
{
|
|
"entropy": 5.3964927196502686,
|
|
"epoch": 2.408491042848318,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00044272419050314833,
|
|
"loss": 5.0914,
|
|
"mean_token_accuracy": 0.2102293461561203,
|
|
"num_tokens": 47866261.0,
|
|
"step": 21445
|
|
},
|
|
{
|
|
"entropy": 5.434059476852417,
|
|
"epoch": 2.4090526197562756,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00044269742582980017,
|
|
"loss": 5.3075,
|
|
"mean_token_accuracy": 0.19146720468997955,
|
|
"num_tokens": 47878807.0,
|
|
"step": 21450
|
|
},
|
|
{
|
|
"entropy": 5.467469930648804,
|
|
"epoch": 2.4096141966642333,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.000442670655816901,
|
|
"loss": 5.1535,
|
|
"mean_token_accuracy": 0.20308677107095718,
|
|
"num_tokens": 47888935.0,
|
|
"step": 21455
|
|
},
|
|
{
|
|
"entropy": 5.539342975616455,
|
|
"epoch": 2.410175773572191,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00044264388046530304,
|
|
"loss": 5.1845,
|
|
"mean_token_accuracy": 0.20222682803869246,
|
|
"num_tokens": 47900208.0,
|
|
"step": 21460
|
|
},
|
|
{
|
|
"entropy": 5.5797394752502445,
|
|
"epoch": 2.410737350480148,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00044261709977585893,
|
|
"loss": 5.3258,
|
|
"mean_token_accuracy": 0.1934771865606308,
|
|
"num_tokens": 47911131.0,
|
|
"step": 21465
|
|
},
|
|
{
|
|
"entropy": 5.493864965438843,
|
|
"epoch": 2.411298927388106,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004425903137494214,
|
|
"loss": 5.2858,
|
|
"mean_token_accuracy": 0.19310020953416823,
|
|
"num_tokens": 47922601.0,
|
|
"step": 21470
|
|
},
|
|
{
|
|
"entropy": 5.562084770202636,
|
|
"epoch": 2.4118605042960635,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004425635223868433,
|
|
"loss": 5.2483,
|
|
"mean_token_accuracy": 0.19078425019979478,
|
|
"num_tokens": 47933168.0,
|
|
"step": 21475
|
|
},
|
|
{
|
|
"entropy": 5.567868947982788,
|
|
"epoch": 2.4124220812040207,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.00044253672568897754,
|
|
"loss": 5.326,
|
|
"mean_token_accuracy": 0.18399229794740676,
|
|
"num_tokens": 47945433.0,
|
|
"step": 21480
|
|
},
|
|
{
|
|
"entropy": 5.510581064224243,
|
|
"epoch": 2.4129836581119783,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004425099236566775,
|
|
"loss": 5.253,
|
|
"mean_token_accuracy": 0.19290145188570024,
|
|
"num_tokens": 47957513.0,
|
|
"step": 21485
|
|
},
|
|
{
|
|
"entropy": 5.476819801330566,
|
|
"epoch": 2.413545235019936,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00044248311629079657,
|
|
"loss": 5.1942,
|
|
"mean_token_accuracy": 0.19590148329734802,
|
|
"num_tokens": 47968817.0,
|
|
"step": 21490
|
|
},
|
|
{
|
|
"entropy": 5.492171716690064,
|
|
"epoch": 2.4141068119278937,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004424563035921882,
|
|
"loss": 5.1331,
|
|
"mean_token_accuracy": 0.2000505194067955,
|
|
"num_tokens": 47979034.0,
|
|
"step": 21495
|
|
},
|
|
{
|
|
"entropy": 5.542651653289795,
|
|
"epoch": 2.414668388835851,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00044242948556170634,
|
|
"loss": 5.2197,
|
|
"mean_token_accuracy": 0.2020846948027611,
|
|
"num_tokens": 47990459.0,
|
|
"step": 21500
|
|
},
|
|
{
|
|
"entropy": 5.4815925598144535,
|
|
"epoch": 2.4152299657438085,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.00044240266220020455,
|
|
"loss": 5.2593,
|
|
"mean_token_accuracy": 0.19531419426202773,
|
|
"num_tokens": 48000007.0,
|
|
"step": 21505
|
|
},
|
|
{
|
|
"entropy": 5.507301902770996,
|
|
"epoch": 2.415791542651766,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004423758335085371,
|
|
"loss": 5.2188,
|
|
"mean_token_accuracy": 0.19626193791627883,
|
|
"num_tokens": 48012962.0,
|
|
"step": 21510
|
|
},
|
|
{
|
|
"entropy": 5.465673303604126,
|
|
"epoch": 2.416353119559724,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00044234899948755827,
|
|
"loss": 5.2093,
|
|
"mean_token_accuracy": 0.1957627147436142,
|
|
"num_tokens": 48025916.0,
|
|
"step": 21515
|
|
},
|
|
{
|
|
"entropy": 5.455223655700683,
|
|
"epoch": 2.416914696467681,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00044232216013812226,
|
|
"loss": 5.2095,
|
|
"mean_token_accuracy": 0.20134610384702684,
|
|
"num_tokens": 48036255.0,
|
|
"step": 21520
|
|
},
|
|
{
|
|
"entropy": 5.489645862579346,
|
|
"epoch": 2.4174762733756388,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004422953154610838,
|
|
"loss": 5.2089,
|
|
"mean_token_accuracy": 0.20038269311189652,
|
|
"num_tokens": 48045943.0,
|
|
"step": 21525
|
|
},
|
|
{
|
|
"entropy": 5.406678152084351,
|
|
"epoch": 2.4180378502835964,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004422684654572977,
|
|
"loss": 5.1716,
|
|
"mean_token_accuracy": 0.20007821619510652,
|
|
"num_tokens": 48056562.0,
|
|
"step": 21530
|
|
},
|
|
{
|
|
"entropy": 5.414686012268066,
|
|
"epoch": 2.418599427191554,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00044224161012761874,
|
|
"loss": 5.1455,
|
|
"mean_token_accuracy": 0.19966147243976592,
|
|
"num_tokens": 48066997.0,
|
|
"step": 21535
|
|
},
|
|
{
|
|
"entropy": 5.52472152709961,
|
|
"epoch": 2.4191610040995113,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00044221474947290205,
|
|
"loss": 5.2624,
|
|
"mean_token_accuracy": 0.19443010538816452,
|
|
"num_tokens": 48077810.0,
|
|
"step": 21540
|
|
},
|
|
{
|
|
"entropy": 5.542490816116333,
|
|
"epoch": 2.419722581007469,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004421878834940029,
|
|
"loss": 5.3266,
|
|
"mean_token_accuracy": 0.18872090429067612,
|
|
"num_tokens": 48089422.0,
|
|
"step": 21545
|
|
},
|
|
{
|
|
"entropy": 5.4717436790466305,
|
|
"epoch": 2.4202841579154266,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00044216101219177667,
|
|
"loss": 5.18,
|
|
"mean_token_accuracy": 0.19570807367563248,
|
|
"num_tokens": 48101114.0,
|
|
"step": 21550
|
|
},
|
|
{
|
|
"entropy": 5.48274073600769,
|
|
"epoch": 2.4208457348233843,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00044213413556707905,
|
|
"loss": 5.1681,
|
|
"mean_token_accuracy": 0.2029666617512703,
|
|
"num_tokens": 48110991.0,
|
|
"step": 21555
|
|
},
|
|
{
|
|
"entropy": 5.508170175552368,
|
|
"epoch": 2.4214073117313415,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004421072536207656,
|
|
"loss": 5.2141,
|
|
"mean_token_accuracy": 0.2002914935350418,
|
|
"num_tokens": 48122889.0,
|
|
"step": 21560
|
|
},
|
|
{
|
|
"entropy": 5.533147811889648,
|
|
"epoch": 2.421968888639299,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00044208036635369247,
|
|
"loss": 5.2218,
|
|
"mean_token_accuracy": 0.20043204873800277,
|
|
"num_tokens": 48133586.0,
|
|
"step": 21565
|
|
},
|
|
{
|
|
"entropy": 5.443800926208496,
|
|
"epoch": 2.422530465547257,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004420534737667157,
|
|
"loss": 5.1527,
|
|
"mean_token_accuracy": 0.20333350151777269,
|
|
"num_tokens": 48144060.0,
|
|
"step": 21570
|
|
},
|
|
{
|
|
"entropy": 5.54448938369751,
|
|
"epoch": 2.423092042455214,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00044202657586069153,
|
|
"loss": 5.2599,
|
|
"mean_token_accuracy": 0.2001522049307823,
|
|
"num_tokens": 48155197.0,
|
|
"step": 21575
|
|
},
|
|
{
|
|
"entropy": 5.5493550300598145,
|
|
"epoch": 2.4236536193631717,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00044199967263647635,
|
|
"loss": 5.3169,
|
|
"mean_token_accuracy": 0.19386566579341888,
|
|
"num_tokens": 48166990.0,
|
|
"step": 21580
|
|
},
|
|
{
|
|
"entropy": 5.567315483093262,
|
|
"epoch": 2.4242151962711294,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004419727640949268,
|
|
"loss": 5.3224,
|
|
"mean_token_accuracy": 0.18650861829519272,
|
|
"num_tokens": 48179454.0,
|
|
"step": 21585
|
|
},
|
|
{
|
|
"entropy": 5.418863344192505,
|
|
"epoch": 2.424776773179087,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004419458502368998,
|
|
"loss": 5.1721,
|
|
"mean_token_accuracy": 0.20034961998462678,
|
|
"num_tokens": 48192009.0,
|
|
"step": 21590
|
|
},
|
|
{
|
|
"entropy": 5.5574883937835695,
|
|
"epoch": 2.4253383500870442,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00044191893106325207,
|
|
"loss": 5.2552,
|
|
"mean_token_accuracy": 0.197950841486454,
|
|
"num_tokens": 48203111.0,
|
|
"step": 21595
|
|
},
|
|
{
|
|
"entropy": 5.595216894149781,
|
|
"epoch": 2.425899926995002,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004418920065748409,
|
|
"loss": 5.4157,
|
|
"mean_token_accuracy": 0.1881189227104187,
|
|
"num_tokens": 48214766.0,
|
|
"step": 21600
|
|
},
|
|
{
|
|
"entropy": 5.544545269012451,
|
|
"epoch": 2.4264615039029596,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00044186507677252345,
|
|
"loss": 5.3159,
|
|
"mean_token_accuracy": 0.2030021384358406,
|
|
"num_tokens": 48225061.0,
|
|
"step": 21605
|
|
},
|
|
{
|
|
"entropy": 5.469171810150146,
|
|
"epoch": 2.427023080810917,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004418381416571573,
|
|
"loss": 5.2038,
|
|
"mean_token_accuracy": 0.19727595150470734,
|
|
"num_tokens": 48236101.0,
|
|
"step": 21610
|
|
},
|
|
{
|
|
"entropy": 5.4103844165802,
|
|
"epoch": 2.4275846577188744,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004418112012296,
|
|
"loss": 5.1742,
|
|
"mean_token_accuracy": 0.1981567308306694,
|
|
"num_tokens": 48248080.0,
|
|
"step": 21615
|
|
},
|
|
{
|
|
"entropy": 5.42638144493103,
|
|
"epoch": 2.428146234626832,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.00044178425549070934,
|
|
"loss": 5.1343,
|
|
"mean_token_accuracy": 0.20125969499349594,
|
|
"num_tokens": 48259177.0,
|
|
"step": 21620
|
|
},
|
|
{
|
|
"entropy": 5.496696472167969,
|
|
"epoch": 2.4287078115347898,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00044175730444134326,
|
|
"loss": 5.1755,
|
|
"mean_token_accuracy": 0.19469186514616013,
|
|
"num_tokens": 48271345.0,
|
|
"step": 21625
|
|
},
|
|
{
|
|
"entropy": 5.517582368850708,
|
|
"epoch": 2.4292693884427474,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00044173034808236,
|
|
"loss": 5.2608,
|
|
"mean_token_accuracy": 0.19164094030857087,
|
|
"num_tokens": 48284219.0,
|
|
"step": 21630
|
|
},
|
|
{
|
|
"entropy": 5.498813247680664,
|
|
"epoch": 2.4298309653507046,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004417033864146177,
|
|
"loss": 5.1755,
|
|
"mean_token_accuracy": 0.19849569201469422,
|
|
"num_tokens": 48294626.0,
|
|
"step": 21635
|
|
},
|
|
{
|
|
"entropy": 5.380316543579101,
|
|
"epoch": 2.4303925422586623,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004416764194389751,
|
|
"loss": 5.1676,
|
|
"mean_token_accuracy": 0.1984646886587143,
|
|
"num_tokens": 48305459.0,
|
|
"step": 21640
|
|
},
|
|
{
|
|
"entropy": 5.464716053009033,
|
|
"epoch": 2.43095411916662,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004416494471562904,
|
|
"loss": 5.1715,
|
|
"mean_token_accuracy": 0.2041002705693245,
|
|
"num_tokens": 48316232.0,
|
|
"step": 21645
|
|
},
|
|
{
|
|
"entropy": 5.470191144943238,
|
|
"epoch": 2.4315156960745776,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004416224695674229,
|
|
"loss": 5.145,
|
|
"mean_token_accuracy": 0.2063722714781761,
|
|
"num_tokens": 48326711.0,
|
|
"step": 21650
|
|
},
|
|
{
|
|
"entropy": 5.318240833282471,
|
|
"epoch": 2.432077272982535,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00044159548667323126,
|
|
"loss": 4.9612,
|
|
"mean_token_accuracy": 0.22063706517219545,
|
|
"num_tokens": 48336860.0,
|
|
"step": 21655
|
|
},
|
|
{
|
|
"entropy": 5.347515010833741,
|
|
"epoch": 2.4326388498904925,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004415684984745747,
|
|
"loss": 5.2694,
|
|
"mean_token_accuracy": 0.19604750275611876,
|
|
"num_tokens": 48348503.0,
|
|
"step": 21660
|
|
},
|
|
{
|
|
"entropy": 5.524180173873901,
|
|
"epoch": 2.43320042679845,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004415415049723126,
|
|
"loss": 5.2929,
|
|
"mean_token_accuracy": 0.19336607158184052,
|
|
"num_tokens": 48359855.0,
|
|
"step": 21665
|
|
},
|
|
{
|
|
"entropy": 5.56565842628479,
|
|
"epoch": 2.4337620037064074,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004415145061673043,
|
|
"loss": 5.2444,
|
|
"mean_token_accuracy": 0.1919916331768036,
|
|
"num_tokens": 48370188.0,
|
|
"step": 21670
|
|
},
|
|
{
|
|
"entropy": 5.478146171569824,
|
|
"epoch": 2.434323580614365,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004414875020604096,
|
|
"loss": 5.1624,
|
|
"mean_token_accuracy": 0.20773671567440033,
|
|
"num_tokens": 48381152.0,
|
|
"step": 21675
|
|
},
|
|
{
|
|
"entropy": 5.454023694992065,
|
|
"epoch": 2.4348851575223227,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004414604926524882,
|
|
"loss": 5.2145,
|
|
"mean_token_accuracy": 0.1982116147875786,
|
|
"num_tokens": 48392721.0,
|
|
"step": 21680
|
|
},
|
|
{
|
|
"entropy": 5.455103158950806,
|
|
"epoch": 2.4354467344302804,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004414334779444002,
|
|
"loss": 5.1895,
|
|
"mean_token_accuracy": 0.1979516863822937,
|
|
"num_tokens": 48404071.0,
|
|
"step": 21685
|
|
},
|
|
{
|
|
"entropy": 5.473447799682617,
|
|
"epoch": 2.4360083113382376,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00044140645793700573,
|
|
"loss": 5.2013,
|
|
"mean_token_accuracy": 0.19501965045928954,
|
|
"num_tokens": 48416001.0,
|
|
"step": 21690
|
|
},
|
|
{
|
|
"entropy": 5.4764386177062985,
|
|
"epoch": 2.4365698882461952,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00044137943263116515,
|
|
"loss": 5.204,
|
|
"mean_token_accuracy": 0.19583554565906525,
|
|
"num_tokens": 48426880.0,
|
|
"step": 21695
|
|
},
|
|
{
|
|
"entropy": 5.583257532119751,
|
|
"epoch": 2.437131465154153,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004413524020277388,
|
|
"loss": 5.3075,
|
|
"mean_token_accuracy": 0.19080916196107864,
|
|
"num_tokens": 48437147.0,
|
|
"step": 21700
|
|
},
|
|
{
|
|
"entropy": 5.4255836486816404,
|
|
"epoch": 2.4376930420621106,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004413253661275875,
|
|
"loss": 5.0882,
|
|
"mean_token_accuracy": 0.2037639334797859,
|
|
"num_tokens": 48448706.0,
|
|
"step": 21705
|
|
},
|
|
{
|
|
"entropy": 5.435296058654785,
|
|
"epoch": 2.438254618970068,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00044129832493157195,
|
|
"loss": 5.1096,
|
|
"mean_token_accuracy": 0.20613910853862763,
|
|
"num_tokens": 48458873.0,
|
|
"step": 21710
|
|
},
|
|
{
|
|
"entropy": 5.489786100387573,
|
|
"epoch": 2.4388161958780255,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00044127127844055335,
|
|
"loss": 5.2789,
|
|
"mean_token_accuracy": 0.19208460450172424,
|
|
"num_tokens": 48470726.0,
|
|
"step": 21715
|
|
},
|
|
{
|
|
"entropy": 5.503612422943116,
|
|
"epoch": 2.439377772785983,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00044124422665539273,
|
|
"loss": 5.103,
|
|
"mean_token_accuracy": 0.20683069825172423,
|
|
"num_tokens": 48481912.0,
|
|
"step": 21720
|
|
},
|
|
{
|
|
"entropy": 5.476216745376587,
|
|
"epoch": 2.4399393496939408,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004412171695769515,
|
|
"loss": 5.228,
|
|
"mean_token_accuracy": 0.20174122005701065,
|
|
"num_tokens": 48492048.0,
|
|
"step": 21725
|
|
},
|
|
{
|
|
"entropy": 5.468652677536011,
|
|
"epoch": 2.440500926601898,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00044119010720609106,
|
|
"loss": 5.2593,
|
|
"mean_token_accuracy": 0.19893279373645784,
|
|
"num_tokens": 48503190.0,
|
|
"step": 21730
|
|
},
|
|
{
|
|
"entropy": 5.560579586029053,
|
|
"epoch": 2.4410625035098557,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00044116303954367314,
|
|
"loss": 5.1611,
|
|
"mean_token_accuracy": 0.19728001654148103,
|
|
"num_tokens": 48514956.0,
|
|
"step": 21735
|
|
},
|
|
{
|
|
"entropy": 5.579486322402954,
|
|
"epoch": 2.4416240804178133,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004411359665905596,
|
|
"loss": 5.3054,
|
|
"mean_token_accuracy": 0.19709682762622832,
|
|
"num_tokens": 48526372.0,
|
|
"step": 21740
|
|
},
|
|
{
|
|
"entropy": 5.377999258041382,
|
|
"epoch": 2.442185657325771,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004411088883476125,
|
|
"loss": 5.1493,
|
|
"mean_token_accuracy": 0.20003522783517838,
|
|
"num_tokens": 48536985.0,
|
|
"step": 21745
|
|
},
|
|
{
|
|
"entropy": 5.459693336486817,
|
|
"epoch": 2.442747234233728,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00044108180481569387,
|
|
"loss": 5.2078,
|
|
"mean_token_accuracy": 0.20046344995498658,
|
|
"num_tokens": 48547505.0,
|
|
"step": 21750
|
|
},
|
|
{
|
|
"entropy": 5.511417961120605,
|
|
"epoch": 2.443308811141686,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00044105471599566626,
|
|
"loss": 5.2378,
|
|
"mean_token_accuracy": 0.19674644917249678,
|
|
"num_tokens": 48560104.0,
|
|
"step": 21755
|
|
},
|
|
{
|
|
"entropy": 5.521594619750976,
|
|
"epoch": 2.4438703880496435,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000441027621888392,
|
|
"loss": 5.3197,
|
|
"mean_token_accuracy": 0.19993076771497725,
|
|
"num_tokens": 48571203.0,
|
|
"step": 21760
|
|
},
|
|
{
|
|
"entropy": 5.4625563621521,
|
|
"epoch": 2.4444319649576007,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00044100052249473393,
|
|
"loss": 5.1109,
|
|
"mean_token_accuracy": 0.19899989515542985,
|
|
"num_tokens": 48581480.0,
|
|
"step": 21765
|
|
},
|
|
{
|
|
"entropy": 5.509932231903076,
|
|
"epoch": 2.4449935418655584,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004409734178155548,
|
|
"loss": 5.1919,
|
|
"mean_token_accuracy": 0.20069716721773148,
|
|
"num_tokens": 48592811.0,
|
|
"step": 21770
|
|
},
|
|
{
|
|
"entropy": 5.420577096939087,
|
|
"epoch": 2.445555118773516,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004409463078517178,
|
|
"loss": 5.2034,
|
|
"mean_token_accuracy": 0.203411503136158,
|
|
"num_tokens": 48604245.0,
|
|
"step": 21775
|
|
},
|
|
{
|
|
"entropy": 5.5184472560882565,
|
|
"epoch": 2.4461166956814737,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00044091919260408585,
|
|
"loss": 5.1847,
|
|
"mean_token_accuracy": 0.20057608783245087,
|
|
"num_tokens": 48615138.0,
|
|
"step": 21780
|
|
},
|
|
{
|
|
"entropy": 5.48538908958435,
|
|
"epoch": 2.446678272589431,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004408920720735225,
|
|
"loss": 5.2473,
|
|
"mean_token_accuracy": 0.19808796793222427,
|
|
"num_tokens": 48626084.0,
|
|
"step": 21785
|
|
},
|
|
{
|
|
"entropy": 5.453407573699951,
|
|
"epoch": 2.4472398494973886,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00044086494626089127,
|
|
"loss": 5.1067,
|
|
"mean_token_accuracy": 0.1999150887131691,
|
|
"num_tokens": 48636425.0,
|
|
"step": 21790
|
|
},
|
|
{
|
|
"entropy": 5.417506361007691,
|
|
"epoch": 2.4478014264053463,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004408378151670558,
|
|
"loss": 5.2456,
|
|
"mean_token_accuracy": 0.1862782880663872,
|
|
"num_tokens": 48646941.0,
|
|
"step": 21795
|
|
},
|
|
{
|
|
"entropy": 5.443913698196411,
|
|
"epoch": 2.448363003313304,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00044081067879288,
|
|
"loss": 5.1036,
|
|
"mean_token_accuracy": 0.20425938665866852,
|
|
"num_tokens": 48657481.0,
|
|
"step": 21800
|
|
},
|
|
{
|
|
"entropy": 5.540360164642334,
|
|
"epoch": 2.448924580221261,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004407835371392279,
|
|
"loss": 5.2293,
|
|
"mean_token_accuracy": 0.19924686402082442,
|
|
"num_tokens": 48669306.0,
|
|
"step": 21805
|
|
},
|
|
{
|
|
"entropy": 5.438464879989624,
|
|
"epoch": 2.449486157129219,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004407563902069636,
|
|
"loss": 5.1822,
|
|
"mean_token_accuracy": 0.20206608772277831,
|
|
"num_tokens": 48680789.0,
|
|
"step": 21810
|
|
},
|
|
{
|
|
"entropy": 5.499397230148316,
|
|
"epoch": 2.4500477340371765,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004407292379969515,
|
|
"loss": 5.2781,
|
|
"mean_token_accuracy": 0.19427161812782287,
|
|
"num_tokens": 48691811.0,
|
|
"step": 21815
|
|
},
|
|
{
|
|
"entropy": 5.505946969985962,
|
|
"epoch": 2.450609310945134,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004407020805100563,
|
|
"loss": 5.268,
|
|
"mean_token_accuracy": 0.19791758358478545,
|
|
"num_tokens": 48704248.0,
|
|
"step": 21820
|
|
},
|
|
{
|
|
"entropy": 5.492702436447144,
|
|
"epoch": 2.4511708878530913,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004406749177471425,
|
|
"loss": 5.1747,
|
|
"mean_token_accuracy": 0.20821383446455002,
|
|
"num_tokens": 48714452.0,
|
|
"step": 21825
|
|
},
|
|
{
|
|
"entropy": 5.477393770217896,
|
|
"epoch": 2.451732464761049,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00044064774970907516,
|
|
"loss": 5.1556,
|
|
"mean_token_accuracy": 0.20354018807411195,
|
|
"num_tokens": 48725481.0,
|
|
"step": 21830
|
|
},
|
|
{
|
|
"entropy": 5.532561540603638,
|
|
"epoch": 2.4522940416690067,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004406205763967193,
|
|
"loss": 5.2707,
|
|
"mean_token_accuracy": 0.1989121988415718,
|
|
"num_tokens": 48737704.0,
|
|
"step": 21835
|
|
},
|
|
{
|
|
"entropy": 5.521845436096191,
|
|
"epoch": 2.4528556185769643,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004405933978109398,
|
|
"loss": 5.2581,
|
|
"mean_token_accuracy": 0.1946515366435051,
|
|
"num_tokens": 48749085.0,
|
|
"step": 21840
|
|
},
|
|
{
|
|
"entropy": 5.5241645812988285,
|
|
"epoch": 2.4534171954849215,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00044056621395260247,
|
|
"loss": 5.2389,
|
|
"mean_token_accuracy": 0.19579836428165437,
|
|
"num_tokens": 48759432.0,
|
|
"step": 21845
|
|
},
|
|
{
|
|
"entropy": 5.38377537727356,
|
|
"epoch": 2.453978772392879,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00044053902482257265,
|
|
"loss": 5.1048,
|
|
"mean_token_accuracy": 0.1968403398990631,
|
|
"num_tokens": 48769549.0,
|
|
"step": 21850
|
|
},
|
|
{
|
|
"entropy": 5.428978109359742,
|
|
"epoch": 2.454540349300837,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000440511830421716,
|
|
"loss": 5.1542,
|
|
"mean_token_accuracy": 0.20203926116228105,
|
|
"num_tokens": 48779630.0,
|
|
"step": 21855
|
|
},
|
|
{
|
|
"entropy": 5.5175073623657225,
|
|
"epoch": 2.455101926208794,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004404846307508985,
|
|
"loss": 5.2374,
|
|
"mean_token_accuracy": 0.19475793093442917,
|
|
"num_tokens": 48790489.0,
|
|
"step": 21860
|
|
},
|
|
{
|
|
"entropy": 5.581151103973388,
|
|
"epoch": 2.4556635031167517,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00044045742581098624,
|
|
"loss": 5.2892,
|
|
"mean_token_accuracy": 0.19683291167020797,
|
|
"num_tokens": 48802310.0,
|
|
"step": 21865
|
|
},
|
|
{
|
|
"entropy": 5.43082184791565,
|
|
"epoch": 2.4562250800247094,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004404302156028453,
|
|
"loss": 5.1457,
|
|
"mean_token_accuracy": 0.20765147358179092,
|
|
"num_tokens": 48812066.0,
|
|
"step": 21870
|
|
},
|
|
{
|
|
"entropy": 5.533325910568237,
|
|
"epoch": 2.456786656932667,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00044040300012734217,
|
|
"loss": 5.3751,
|
|
"mean_token_accuracy": 0.18804677575826645,
|
|
"num_tokens": 48824477.0,
|
|
"step": 21875
|
|
},
|
|
{
|
|
"entropy": 5.545376491546631,
|
|
"epoch": 2.4573482338406243,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004403757793853434,
|
|
"loss": 5.2161,
|
|
"mean_token_accuracy": 0.1918596476316452,
|
|
"num_tokens": 48835147.0,
|
|
"step": 21880
|
|
},
|
|
{
|
|
"entropy": 5.436745023727417,
|
|
"epoch": 2.457909810748582,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004403485533777157,
|
|
"loss": 5.2452,
|
|
"mean_token_accuracy": 0.19451164007186889,
|
|
"num_tokens": 48846147.0,
|
|
"step": 21885
|
|
},
|
|
{
|
|
"entropy": 5.581682920455933,
|
|
"epoch": 2.4584713876565396,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004403213221053258,
|
|
"loss": 5.3094,
|
|
"mean_token_accuracy": 0.19171257615089415,
|
|
"num_tokens": 48857340.0,
|
|
"step": 21890
|
|
},
|
|
{
|
|
"entropy": 5.432861423492431,
|
|
"epoch": 2.4590329645644973,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00044029408556904093,
|
|
"loss": 5.1574,
|
|
"mean_token_accuracy": 0.2004673019051552,
|
|
"num_tokens": 48868256.0,
|
|
"step": 21895
|
|
},
|
|
{
|
|
"entropy": 5.587519788742066,
|
|
"epoch": 2.4595945414724545,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004402668437697283,
|
|
"loss": 5.2699,
|
|
"mean_token_accuracy": 0.19470858573913574,
|
|
"num_tokens": 48879346.0,
|
|
"step": 21900
|
|
},
|
|
{
|
|
"entropy": 5.5088897228240965,
|
|
"epoch": 2.460156118380412,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.00044023959670825533,
|
|
"loss": 5.3029,
|
|
"mean_token_accuracy": 0.18948156833648683,
|
|
"num_tokens": 48890939.0,
|
|
"step": 21905
|
|
},
|
|
{
|
|
"entropy": 5.495760679244995,
|
|
"epoch": 2.46071769528837,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004402123443854894,
|
|
"loss": 5.2963,
|
|
"mean_token_accuracy": 0.19572442770004272,
|
|
"num_tokens": 48902239.0,
|
|
"step": 21910
|
|
},
|
|
{
|
|
"entropy": 5.535546922683716,
|
|
"epoch": 2.4612792721963275,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004401850868022984,
|
|
"loss": 5.2571,
|
|
"mean_token_accuracy": 0.19931843429803847,
|
|
"num_tokens": 48913810.0,
|
|
"step": 21915
|
|
},
|
|
{
|
|
"entropy": 5.428094720840454,
|
|
"epoch": 2.4618408491042847,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004401578239595501,
|
|
"loss": 5.1343,
|
|
"mean_token_accuracy": 0.2021462619304657,
|
|
"num_tokens": 48925180.0,
|
|
"step": 21920
|
|
},
|
|
{
|
|
"entropy": 5.452257299423218,
|
|
"epoch": 2.4624024260122424,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00044013055585811274,
|
|
"loss": 5.2308,
|
|
"mean_token_accuracy": 0.1900040999054909,
|
|
"num_tokens": 48937067.0,
|
|
"step": 21925
|
|
},
|
|
{
|
|
"entropy": 5.523362016677856,
|
|
"epoch": 2.4629640029202,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00044010328249885434,
|
|
"loss": 5.2799,
|
|
"mean_token_accuracy": 0.19059958010911943,
|
|
"num_tokens": 48949220.0,
|
|
"step": 21930
|
|
},
|
|
{
|
|
"entropy": 5.5175337314605715,
|
|
"epoch": 2.4635255798281577,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004400760038826434,
|
|
"loss": 5.222,
|
|
"mean_token_accuracy": 0.1970979243516922,
|
|
"num_tokens": 48960604.0,
|
|
"step": 21935
|
|
},
|
|
{
|
|
"entropy": 5.439581394195557,
|
|
"epoch": 2.464087156736115,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00044004872001034856,
|
|
"loss": 5.1474,
|
|
"mean_token_accuracy": 0.20640051662921904,
|
|
"num_tokens": 48970561.0,
|
|
"step": 21940
|
|
},
|
|
{
|
|
"entropy": 5.477488899230957,
|
|
"epoch": 2.4646487336440726,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004400214308828384,
|
|
"loss": 5.2323,
|
|
"mean_token_accuracy": 0.19332142323255538,
|
|
"num_tokens": 48981639.0,
|
|
"step": 21945
|
|
},
|
|
{
|
|
"entropy": 5.587163972854614,
|
|
"epoch": 2.46521031055203,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.00043999413650098193,
|
|
"loss": 5.2597,
|
|
"mean_token_accuracy": 0.19523866027593612,
|
|
"num_tokens": 48992872.0,
|
|
"step": 21950
|
|
},
|
|
{
|
|
"entropy": 5.494712686538696,
|
|
"epoch": 2.4657718874599874,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004399668368656481,
|
|
"loss": 5.2396,
|
|
"mean_token_accuracy": 0.19345155358314514,
|
|
"num_tokens": 49004942.0,
|
|
"step": 21955
|
|
},
|
|
{
|
|
"entropy": 5.554857301712036,
|
|
"epoch": 2.466333464367945,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004399395319777062,
|
|
"loss": 5.2049,
|
|
"mean_token_accuracy": 0.19897417575120926,
|
|
"num_tokens": 49016493.0,
|
|
"step": 21960
|
|
},
|
|
{
|
|
"entropy": 5.5130510330200195,
|
|
"epoch": 2.4668950412759028,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00043991222183802564,
|
|
"loss": 5.2279,
|
|
"mean_token_accuracy": 0.19936139434576033,
|
|
"num_tokens": 49027780.0,
|
|
"step": 21965
|
|
},
|
|
{
|
|
"entropy": 5.462654781341553,
|
|
"epoch": 2.4674566181838604,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000439884906447476,
|
|
"loss": 5.2214,
|
|
"mean_token_accuracy": 0.2021893158555031,
|
|
"num_tokens": 49039441.0,
|
|
"step": 21970
|
|
},
|
|
{
|
|
"entropy": 5.486788558959961,
|
|
"epoch": 2.4680181950918176,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000439857585806927,
|
|
"loss": 5.2275,
|
|
"mean_token_accuracy": 0.20156155675649642,
|
|
"num_tokens": 49050740.0,
|
|
"step": 21975
|
|
},
|
|
{
|
|
"entropy": 5.44096884727478,
|
|
"epoch": 2.4685797719997753,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00043983025991724847,
|
|
"loss": 5.1937,
|
|
"mean_token_accuracy": 0.20292574316263198,
|
|
"num_tokens": 49062216.0,
|
|
"step": 21980
|
|
},
|
|
{
|
|
"entropy": 5.4507551193237305,
|
|
"epoch": 2.469141348907733,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004398029287793106,
|
|
"loss": 5.1409,
|
|
"mean_token_accuracy": 0.2044414147734642,
|
|
"num_tokens": 49072848.0,
|
|
"step": 21985
|
|
},
|
|
{
|
|
"entropy": 5.417329263687134,
|
|
"epoch": 2.4697029258156906,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00043977559239398353,
|
|
"loss": 5.113,
|
|
"mean_token_accuracy": 0.20254876464605331,
|
|
"num_tokens": 49083382.0,
|
|
"step": 21990
|
|
},
|
|
{
|
|
"entropy": 5.438059234619141,
|
|
"epoch": 2.470264502723648,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004397482507621376,
|
|
"loss": 5.157,
|
|
"mean_token_accuracy": 0.20100490599870682,
|
|
"num_tokens": 49095102.0,
|
|
"step": 21995
|
|
},
|
|
{
|
|
"entropy": 5.436920309066773,
|
|
"epoch": 2.4708260796316055,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004397209038846436,
|
|
"loss": 5.18,
|
|
"mean_token_accuracy": 0.1987630844116211,
|
|
"num_tokens": 49105964.0,
|
|
"step": 22000
|
|
},
|
|
{
|
|
"entropy": 5.499797201156616,
|
|
"epoch": 2.471387656539563,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00043969355176237207,
|
|
"loss": 5.2966,
|
|
"mean_token_accuracy": 0.18655095845460892,
|
|
"num_tokens": 49117748.0,
|
|
"step": 22005
|
|
},
|
|
{
|
|
"entropy": 5.416675806045532,
|
|
"epoch": 2.471949233447521,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004396661943961941,
|
|
"loss": 5.038,
|
|
"mean_token_accuracy": 0.20946522504091264,
|
|
"num_tokens": 49128217.0,
|
|
"step": 22010
|
|
},
|
|
{
|
|
"entropy": 5.483416557312012,
|
|
"epoch": 2.472510810355478,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004396388317869805,
|
|
"loss": 5.3003,
|
|
"mean_token_accuracy": 0.19545274823904038,
|
|
"num_tokens": 49139272.0,
|
|
"step": 22015
|
|
},
|
|
{
|
|
"entropy": 5.467224025726319,
|
|
"epoch": 2.4730723872634357,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004396114639356027,
|
|
"loss": 5.1912,
|
|
"mean_token_accuracy": 0.19524904191493989,
|
|
"num_tokens": 49149570.0,
|
|
"step": 22020
|
|
},
|
|
{
|
|
"entropy": 5.424163293838501,
|
|
"epoch": 2.4736339641713934,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.000439584090842932,
|
|
"loss": 5.1432,
|
|
"mean_token_accuracy": 0.20249621123075484,
|
|
"num_tokens": 49160892.0,
|
|
"step": 22025
|
|
},
|
|
{
|
|
"entropy": 5.456919622421265,
|
|
"epoch": 2.474195541079351,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00043955671250984005,
|
|
"loss": 5.1554,
|
|
"mean_token_accuracy": 0.19948485046625136,
|
|
"num_tokens": 49172476.0,
|
|
"step": 22030
|
|
},
|
|
{
|
|
"entropy": 5.538638353347778,
|
|
"epoch": 2.4747571179873082,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00043952932893719847,
|
|
"loss": 5.2515,
|
|
"mean_token_accuracy": 0.20217922627925872,
|
|
"num_tokens": 49184052.0,
|
|
"step": 22035
|
|
},
|
|
{
|
|
"entropy": 5.451108980178833,
|
|
"epoch": 2.475318694895266,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004395019401258794,
|
|
"loss": 5.2382,
|
|
"mean_token_accuracy": 0.191593736410141,
|
|
"num_tokens": 49195441.0,
|
|
"step": 22040
|
|
},
|
|
{
|
|
"entropy": 5.394437646865844,
|
|
"epoch": 2.4758802718032236,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00043947454607675464,
|
|
"loss": 5.1473,
|
|
"mean_token_accuracy": 0.20122386366128922,
|
|
"num_tokens": 49206395.0,
|
|
"step": 22045
|
|
},
|
|
{
|
|
"entropy": 5.50679383277893,
|
|
"epoch": 2.476441848711181,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004394471467906966,
|
|
"loss": 5.2255,
|
|
"mean_token_accuracy": 0.19376638978719712,
|
|
"num_tokens": 49217705.0,
|
|
"step": 22050
|
|
},
|
|
{
|
|
"entropy": 5.476305437088013,
|
|
"epoch": 2.4770034256191384,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00043941974226857763,
|
|
"loss": 5.0971,
|
|
"mean_token_accuracy": 0.20508005619049072,
|
|
"num_tokens": 49228348.0,
|
|
"step": 22055
|
|
},
|
|
{
|
|
"entropy": 5.401055812835693,
|
|
"epoch": 2.477565002527096,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004393923325112702,
|
|
"loss": 5.1686,
|
|
"mean_token_accuracy": 0.19700507819652557,
|
|
"num_tokens": 49239031.0,
|
|
"step": 22060
|
|
},
|
|
{
|
|
"entropy": 5.494280433654785,
|
|
"epoch": 2.4781265794350538,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004393649175196472,
|
|
"loss": 5.2852,
|
|
"mean_token_accuracy": 0.19698485136032104,
|
|
"num_tokens": 49250918.0,
|
|
"step": 22065
|
|
},
|
|
{
|
|
"entropy": 5.4980357646942135,
|
|
"epoch": 2.478688156343011,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004393374972945815,
|
|
"loss": 5.2338,
|
|
"mean_token_accuracy": 0.19626788049936295,
|
|
"num_tokens": 49262305.0,
|
|
"step": 22070
|
|
},
|
|
{
|
|
"entropy": 5.432592868804932,
|
|
"epoch": 2.4792497332509686,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00043931007183694616,
|
|
"loss": 5.1535,
|
|
"mean_token_accuracy": 0.19390892535448073,
|
|
"num_tokens": 49273106.0,
|
|
"step": 22075
|
|
},
|
|
{
|
|
"entropy": 5.387322902679443,
|
|
"epoch": 2.4798113101589263,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00043928264114761437,
|
|
"loss": 5.1157,
|
|
"mean_token_accuracy": 0.208780637383461,
|
|
"num_tokens": 49284519.0,
|
|
"step": 22080
|
|
},
|
|
{
|
|
"entropy": 5.422154474258423,
|
|
"epoch": 2.480372887066884,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00043925520522745953,
|
|
"loss": 5.1449,
|
|
"mean_token_accuracy": 0.2027816042304039,
|
|
"num_tokens": 49295753.0,
|
|
"step": 22085
|
|
},
|
|
{
|
|
"entropy": 5.475007152557373,
|
|
"epoch": 2.480934463974841,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004392277640773553,
|
|
"loss": 5.239,
|
|
"mean_token_accuracy": 0.20320538878440858,
|
|
"num_tokens": 49307682.0,
|
|
"step": 22090
|
|
},
|
|
{
|
|
"entropy": 5.445680761337281,
|
|
"epoch": 2.481496040882799,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00043920031769817543,
|
|
"loss": 5.1785,
|
|
"mean_token_accuracy": 0.19945676475763321,
|
|
"num_tokens": 49318445.0,
|
|
"step": 22095
|
|
},
|
|
{
|
|
"entropy": 5.479609203338623,
|
|
"epoch": 2.4820576177907565,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00043917286609079364,
|
|
"loss": 5.3012,
|
|
"mean_token_accuracy": 0.19467789083719253,
|
|
"num_tokens": 49328559.0,
|
|
"step": 22100
|
|
},
|
|
{
|
|
"entropy": 5.451708126068115,
|
|
"epoch": 2.482619194698714,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00043914540925608426,
|
|
"loss": 5.1993,
|
|
"mean_token_accuracy": 0.19196963608264922,
|
|
"num_tokens": 49340177.0,
|
|
"step": 22105
|
|
},
|
|
{
|
|
"entropy": 5.479378271102905,
|
|
"epoch": 2.4831807716066714,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004391179471949213,
|
|
"loss": 5.1648,
|
|
"mean_token_accuracy": 0.20082276165485383,
|
|
"num_tokens": 49351214.0,
|
|
"step": 22110
|
|
},
|
|
{
|
|
"entropy": 5.456046485900879,
|
|
"epoch": 2.483742348514629,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00043909047990817917,
|
|
"loss": 5.2031,
|
|
"mean_token_accuracy": 0.20369723588228225,
|
|
"num_tokens": 49362697.0,
|
|
"step": 22115
|
|
},
|
|
{
|
|
"entropy": 5.489879846572876,
|
|
"epoch": 2.4843039254225867,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00043906300739673265,
|
|
"loss": 5.1976,
|
|
"mean_token_accuracy": 0.19850983321666718,
|
|
"num_tokens": 49374439.0,
|
|
"step": 22120
|
|
},
|
|
{
|
|
"entropy": 5.426640176773072,
|
|
"epoch": 2.4848655023305444,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00043903552966145624,
|
|
"loss": 5.1042,
|
|
"mean_token_accuracy": 0.19865205734968186,
|
|
"num_tokens": 49385834.0,
|
|
"step": 22125
|
|
},
|
|
{
|
|
"entropy": 5.398649120330811,
|
|
"epoch": 2.4854270792385016,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000439008046703225,
|
|
"loss": 5.1314,
|
|
"mean_token_accuracy": 0.20927066951990128,
|
|
"num_tokens": 49396562.0,
|
|
"step": 22130
|
|
},
|
|
{
|
|
"entropy": 5.3768110275268555,
|
|
"epoch": 2.4859886561464593,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000438980558522914,
|
|
"loss": 5.1646,
|
|
"mean_token_accuracy": 0.19566589295864106,
|
|
"num_tokens": 49407339.0,
|
|
"step": 22135
|
|
},
|
|
{
|
|
"entropy": 5.489607906341552,
|
|
"epoch": 2.486550233054417,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004389530651213983,
|
|
"loss": 5.1722,
|
|
"mean_token_accuracy": 0.20103365033864976,
|
|
"num_tokens": 49419190.0,
|
|
"step": 22140
|
|
},
|
|
{
|
|
"entropy": 5.600993347167969,
|
|
"epoch": 2.487111809962374,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00043892556649955354,
|
|
"loss": 5.3011,
|
|
"mean_token_accuracy": 0.1875125840306282,
|
|
"num_tokens": 49430559.0,
|
|
"step": 22145
|
|
},
|
|
{
|
|
"entropy": 5.476229190826416,
|
|
"epoch": 2.487673386870332,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004388980626582551,
|
|
"loss": 5.242,
|
|
"mean_token_accuracy": 0.2010987728834152,
|
|
"num_tokens": 49441862.0,
|
|
"step": 22150
|
|
},
|
|
{
|
|
"entropy": 5.444450426101684,
|
|
"epoch": 2.4882349637782895,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004388705535983788,
|
|
"loss": 5.175,
|
|
"mean_token_accuracy": 0.19661868512630462,
|
|
"num_tokens": 49452839.0,
|
|
"step": 22155
|
|
},
|
|
{
|
|
"entropy": 5.452764892578125,
|
|
"epoch": 2.488796540686247,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004388430393208005,
|
|
"loss": 5.1788,
|
|
"mean_token_accuracy": 0.20446619242429734,
|
|
"num_tokens": 49463683.0,
|
|
"step": 22160
|
|
},
|
|
{
|
|
"entropy": 5.446353578567505,
|
|
"epoch": 2.4893581175942043,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004388155198263963,
|
|
"loss": 5.1476,
|
|
"mean_token_accuracy": 0.20625588297843933,
|
|
"num_tokens": 49474338.0,
|
|
"step": 22165
|
|
},
|
|
{
|
|
"entropy": 5.427867126464844,
|
|
"epoch": 2.489919694502162,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004387879951160424,
|
|
"loss": 5.2375,
|
|
"mean_token_accuracy": 0.19345259219408034,
|
|
"num_tokens": 49485888.0,
|
|
"step": 22170
|
|
},
|
|
{
|
|
"entropy": 5.536109256744385,
|
|
"epoch": 2.4904812714101197,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004387604651906152,
|
|
"loss": 5.2665,
|
|
"mean_token_accuracy": 0.19629083275794984,
|
|
"num_tokens": 49497270.0,
|
|
"step": 22175
|
|
},
|
|
{
|
|
"entropy": 5.575623607635498,
|
|
"epoch": 2.4910428483180773,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004387329300509913,
|
|
"loss": 5.2388,
|
|
"mean_token_accuracy": 0.19408587366342545,
|
|
"num_tokens": 49509099.0,
|
|
"step": 22180
|
|
},
|
|
{
|
|
"entropy": 5.409361982345581,
|
|
"epoch": 2.4916044252260345,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00043870538969804733,
|
|
"loss": 5.1599,
|
|
"mean_token_accuracy": 0.20205197781324385,
|
|
"num_tokens": 49520110.0,
|
|
"step": 22185
|
|
},
|
|
{
|
|
"entropy": 5.396758556365967,
|
|
"epoch": 2.492166002133992,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004386778441326603,
|
|
"loss": 5.137,
|
|
"mean_token_accuracy": 0.20351825505495072,
|
|
"num_tokens": 49531866.0,
|
|
"step": 22190
|
|
},
|
|
{
|
|
"entropy": 5.498166799545288,
|
|
"epoch": 2.49272757904195,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00043865029335570725,
|
|
"loss": 5.2137,
|
|
"mean_token_accuracy": 0.19389698952436446,
|
|
"num_tokens": 49541022.0,
|
|
"step": 22195
|
|
},
|
|
{
|
|
"entropy": 5.445477771759033,
|
|
"epoch": 2.4932891559499075,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004386227373680655,
|
|
"loss": 5.212,
|
|
"mean_token_accuracy": 0.1959021046757698,
|
|
"num_tokens": 49551908.0,
|
|
"step": 22200
|
|
},
|
|
{
|
|
"entropy": 5.492675018310547,
|
|
"epoch": 2.4938507328578647,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004385951761706122,
|
|
"loss": 5.1593,
|
|
"mean_token_accuracy": 0.1995590701699257,
|
|
"num_tokens": 49562475.0,
|
|
"step": 22205
|
|
},
|
|
{
|
|
"entropy": 5.437918663024902,
|
|
"epoch": 2.4944123097658224,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00043856760976422506,
|
|
"loss": 5.1178,
|
|
"mean_token_accuracy": 0.203217613697052,
|
|
"num_tokens": 49572916.0,
|
|
"step": 22210
|
|
},
|
|
{
|
|
"entropy": 5.459088373184204,
|
|
"epoch": 2.49497388667378,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00043854003814978174,
|
|
"loss": 5.2094,
|
|
"mean_token_accuracy": 0.19507265239953994,
|
|
"num_tokens": 49584584.0,
|
|
"step": 22215
|
|
},
|
|
{
|
|
"entropy": 5.373010683059692,
|
|
"epoch": 2.4955354635817377,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00043851246132816025,
|
|
"loss": 5.1991,
|
|
"mean_token_accuracy": 0.19947243630886077,
|
|
"num_tokens": 49595792.0,
|
|
"step": 22220
|
|
},
|
|
{
|
|
"entropy": 5.495765686035156,
|
|
"epoch": 2.496097040489695,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004384848793002385,
|
|
"loss": 5.2434,
|
|
"mean_token_accuracy": 0.1998839020729065,
|
|
"num_tokens": 49607596.0,
|
|
"step": 22225
|
|
},
|
|
{
|
|
"entropy": 5.537977695465088,
|
|
"epoch": 2.4966586173976526,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004384572920668949,
|
|
"loss": 5.1741,
|
|
"mean_token_accuracy": 0.19015215188264847,
|
|
"num_tokens": 49617990.0,
|
|
"step": 22230
|
|
},
|
|
{
|
|
"entropy": 5.540008544921875,
|
|
"epoch": 2.4972201943056103,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004384296996290076,
|
|
"loss": 5.2626,
|
|
"mean_token_accuracy": 0.19752211570739747,
|
|
"num_tokens": 49629458.0,
|
|
"step": 22235
|
|
},
|
|
{
|
|
"entropy": 5.544511508941651,
|
|
"epoch": 2.4977817712135675,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00043840210198745533,
|
|
"loss": 5.2221,
|
|
"mean_token_accuracy": 0.20264557451009751,
|
|
"num_tokens": 49641227.0,
|
|
"step": 22240
|
|
},
|
|
{
|
|
"entropy": 5.440906286239624,
|
|
"epoch": 2.498343348121525,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00043837449914311676,
|
|
"loss": 5.2815,
|
|
"mean_token_accuracy": 0.19710609763860704,
|
|
"num_tokens": 49652655.0,
|
|
"step": 22245
|
|
},
|
|
{
|
|
"entropy": 5.441756629943848,
|
|
"epoch": 2.498904925029483,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00043834689109687077,
|
|
"loss": 5.2406,
|
|
"mean_token_accuracy": 0.2054051637649536,
|
|
"num_tokens": 49664308.0,
|
|
"step": 22250
|
|
},
|
|
{
|
|
"entropy": 5.509242963790894,
|
|
"epoch": 2.4994665019374405,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004383192778495964,
|
|
"loss": 5.1792,
|
|
"mean_token_accuracy": 0.1972736269235611,
|
|
"num_tokens": 49676656.0,
|
|
"step": 22255
|
|
},
|
|
{
|
|
"entropy": 5.466150522232056,
|
|
"epoch": 2.500028078845398,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000438291659402173,
|
|
"loss": 5.1198,
|
|
"mean_token_accuracy": 0.19730150699615479,
|
|
"num_tokens": 49687706.0,
|
|
"step": 22260
|
|
},
|
|
{
|
|
"entropy": 5.483819627761841,
|
|
"epoch": 2.5005896557533553,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00043826403575547974,
|
|
"loss": 5.1724,
|
|
"mean_token_accuracy": 0.2053607791662216,
|
|
"num_tokens": 49699139.0,
|
|
"step": 22265
|
|
},
|
|
{
|
|
"entropy": 5.318334102630615,
|
|
"epoch": 2.501151232661313,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004382364069103962,
|
|
"loss": 5.1748,
|
|
"mean_token_accuracy": 0.20242644846439362,
|
|
"num_tokens": 49710690.0,
|
|
"step": 22270
|
|
},
|
|
{
|
|
"entropy": 5.437481832504273,
|
|
"epoch": 2.5017128095692707,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00043820877286780224,
|
|
"loss": 5.2127,
|
|
"mean_token_accuracy": 0.20191237777471543,
|
|
"num_tokens": 49721920.0,
|
|
"step": 22275
|
|
},
|
|
{
|
|
"entropy": 5.555009126663208,
|
|
"epoch": 2.502274386477228,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004381811336285776,
|
|
"loss": 5.2056,
|
|
"mean_token_accuracy": 0.19992334693670272,
|
|
"num_tokens": 49732923.0,
|
|
"step": 22280
|
|
},
|
|
{
|
|
"entropy": 5.366896629333496,
|
|
"epoch": 2.5028359633851855,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004381534891936024,
|
|
"loss": 5.089,
|
|
"mean_token_accuracy": 0.20133124887943268,
|
|
"num_tokens": 49744755.0,
|
|
"step": 22285
|
|
},
|
|
{
|
|
"entropy": 5.423555660247803,
|
|
"epoch": 2.503397540293143,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004381258395637568,
|
|
"loss": 5.1612,
|
|
"mean_token_accuracy": 0.20267312824726105,
|
|
"num_tokens": 49756126.0,
|
|
"step": 22290
|
|
},
|
|
{
|
|
"entropy": 5.458829307556153,
|
|
"epoch": 2.5039591172011004,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004380981847399212,
|
|
"loss": 5.1599,
|
|
"mean_token_accuracy": 0.20250371396541594,
|
|
"num_tokens": 49767137.0,
|
|
"step": 22295
|
|
},
|
|
{
|
|
"entropy": 5.454941463470459,
|
|
"epoch": 2.504520694109058,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00043807052472297626,
|
|
"loss": 5.2492,
|
|
"mean_token_accuracy": 0.1909842610359192,
|
|
"num_tokens": 49778533.0,
|
|
"step": 22300
|
|
},
|
|
{
|
|
"entropy": 5.4665198802948,
|
|
"epoch": 2.5050822710170157,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004380428595138024,
|
|
"loss": 5.1992,
|
|
"mean_token_accuracy": 0.20529264956712723,
|
|
"num_tokens": 49789494.0,
|
|
"step": 22305
|
|
},
|
|
{
|
|
"entropy": 5.496833467483521,
|
|
"epoch": 2.5056438479249734,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00043801518911328074,
|
|
"loss": 5.2049,
|
|
"mean_token_accuracy": 0.19738632589578628,
|
|
"num_tokens": 49799546.0,
|
|
"step": 22310
|
|
},
|
|
{
|
|
"entropy": 5.388626050949097,
|
|
"epoch": 2.506205424832931,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00043798751352229227,
|
|
"loss": 5.099,
|
|
"mean_token_accuracy": 0.20380640029907227,
|
|
"num_tokens": 49810643.0,
|
|
"step": 22315
|
|
},
|
|
{
|
|
"entropy": 5.487656784057617,
|
|
"epoch": 2.5067670017408883,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00043795983274171806,
|
|
"loss": 5.2221,
|
|
"mean_token_accuracy": 0.1948302373290062,
|
|
"num_tokens": 49821410.0,
|
|
"step": 22320
|
|
},
|
|
{
|
|
"entropy": 5.460285186767578,
|
|
"epoch": 2.507328578648846,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00043793214677243967,
|
|
"loss": 5.2431,
|
|
"mean_token_accuracy": 0.19352083653211594,
|
|
"num_tokens": 49832911.0,
|
|
"step": 22325
|
|
},
|
|
{
|
|
"entropy": 5.508481025695801,
|
|
"epoch": 2.5078901555568036,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004379044556153384,
|
|
"loss": 5.2308,
|
|
"mean_token_accuracy": 0.19389263391494752,
|
|
"num_tokens": 49845458.0,
|
|
"step": 22330
|
|
},
|
|
{
|
|
"entropy": 5.5135880470275875,
|
|
"epoch": 2.508451732464761,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00043787675927129625,
|
|
"loss": 5.3314,
|
|
"mean_token_accuracy": 0.18994753211736679,
|
|
"num_tokens": 49857054.0,
|
|
"step": 22335
|
|
},
|
|
{
|
|
"entropy": 5.456147384643555,
|
|
"epoch": 2.5090133093727185,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00043784905774119483,
|
|
"loss": 5.1243,
|
|
"mean_token_accuracy": 0.2006603807210922,
|
|
"num_tokens": 49867223.0,
|
|
"step": 22340
|
|
},
|
|
{
|
|
"entropy": 5.401931667327881,
|
|
"epoch": 2.509574886280676,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00043782135102591626,
|
|
"loss": 5.1865,
|
|
"mean_token_accuracy": 0.1990416169166565,
|
|
"num_tokens": 49877801.0,
|
|
"step": 22345
|
|
},
|
|
{
|
|
"entropy": 5.417321872711182,
|
|
"epoch": 2.510136463188634,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004377936391263427,
|
|
"loss": 5.1859,
|
|
"mean_token_accuracy": 0.19792087376117706,
|
|
"num_tokens": 49888853.0,
|
|
"step": 22350
|
|
},
|
|
{
|
|
"entropy": 5.473415946960449,
|
|
"epoch": 2.5106980400965915,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00043776592204335655,
|
|
"loss": 5.1834,
|
|
"mean_token_accuracy": 0.20324978977441788,
|
|
"num_tokens": 49899989.0,
|
|
"step": 22355
|
|
},
|
|
{
|
|
"entropy": 5.481160116195679,
|
|
"epoch": 2.5112596170045487,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004377381997778403,
|
|
"loss": 5.1571,
|
|
"mean_token_accuracy": 0.20386865437030793,
|
|
"num_tokens": 49910993.0,
|
|
"step": 22360
|
|
},
|
|
{
|
|
"entropy": 5.478058338165283,
|
|
"epoch": 2.5118211939125064,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004377104723306767,
|
|
"loss": 5.2194,
|
|
"mean_token_accuracy": 0.19816150814294814,
|
|
"num_tokens": 49922169.0,
|
|
"step": 22365
|
|
},
|
|
{
|
|
"entropy": 5.466850137710571,
|
|
"epoch": 2.512382770820464,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004376827397027485,
|
|
"loss": 5.2746,
|
|
"mean_token_accuracy": 0.1932577133178711,
|
|
"num_tokens": 49933700.0,
|
|
"step": 22370
|
|
},
|
|
{
|
|
"entropy": 5.500583648681641,
|
|
"epoch": 2.5129443477284212,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004376550018949388,
|
|
"loss": 5.197,
|
|
"mean_token_accuracy": 0.19715379923582077,
|
|
"num_tokens": 49944689.0,
|
|
"step": 22375
|
|
},
|
|
{
|
|
"entropy": 5.479571199417114,
|
|
"epoch": 2.513505924636379,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00043762725890813083,
|
|
"loss": 5.2258,
|
|
"mean_token_accuracy": 0.19828970432281495,
|
|
"num_tokens": 49955818.0,
|
|
"step": 22380
|
|
},
|
|
{
|
|
"entropy": 5.396988105773926,
|
|
"epoch": 2.5140675015443366,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004375995107432077,
|
|
"loss": 5.1085,
|
|
"mean_token_accuracy": 0.20480271130800248,
|
|
"num_tokens": 49965799.0,
|
|
"step": 22385
|
|
},
|
|
{
|
|
"entropy": 5.441124486923218,
|
|
"epoch": 2.5146290784522938,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00043757175740105316,
|
|
"loss": 5.1998,
|
|
"mean_token_accuracy": 0.19720589220523835,
|
|
"num_tokens": 49977742.0,
|
|
"step": 22390
|
|
},
|
|
{
|
|
"entropy": 5.502358627319336,
|
|
"epoch": 2.5151906553602514,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004375439988825508,
|
|
"loss": 5.1811,
|
|
"mean_token_accuracy": 0.1966991201043129,
|
|
"num_tokens": 49988382.0,
|
|
"step": 22395
|
|
},
|
|
{
|
|
"entropy": 5.50432333946228,
|
|
"epoch": 2.515752232268209,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004375162351885845,
|
|
"loss": 5.3039,
|
|
"mean_token_accuracy": 0.19249147176742554,
|
|
"num_tokens": 50000190.0,
|
|
"step": 22400
|
|
},
|
|
{
|
|
"entropy": 5.528553104400634,
|
|
"epoch": 2.5163138091761668,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00043748846632003823,
|
|
"loss": 5.2138,
|
|
"mean_token_accuracy": 0.20334574729204177,
|
|
"num_tokens": 50011297.0,
|
|
"step": 22405
|
|
},
|
|
{
|
|
"entropy": 5.4859010696411135,
|
|
"epoch": 2.5168753860841244,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00043746069227779615,
|
|
"loss": 5.2268,
|
|
"mean_token_accuracy": 0.1949320390820503,
|
|
"num_tokens": 50023165.0,
|
|
"step": 22410
|
|
},
|
|
{
|
|
"entropy": 5.510264921188354,
|
|
"epoch": 2.5174369629920816,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004374329130627427,
|
|
"loss": 5.234,
|
|
"mean_token_accuracy": 0.19958595037460328,
|
|
"num_tokens": 50035803.0,
|
|
"step": 22415
|
|
},
|
|
{
|
|
"entropy": 5.445142030715942,
|
|
"epoch": 2.5179985399000393,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00043740512867576224,
|
|
"loss": 5.1186,
|
|
"mean_token_accuracy": 0.20306495279073716,
|
|
"num_tokens": 50046599.0,
|
|
"step": 22420
|
|
},
|
|
{
|
|
"entropy": 5.471498155593872,
|
|
"epoch": 2.518560116807997,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004373773391177395,
|
|
"loss": 5.3363,
|
|
"mean_token_accuracy": 0.18993393331766129,
|
|
"num_tokens": 50058170.0,
|
|
"step": 22425
|
|
},
|
|
{
|
|
"entropy": 5.440329074859619,
|
|
"epoch": 2.519121693715954,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004373495443895593,
|
|
"loss": 5.1424,
|
|
"mean_token_accuracy": 0.20907102674245834,
|
|
"num_tokens": 50068818.0,
|
|
"step": 22430
|
|
},
|
|
{
|
|
"entropy": 5.506471872329712,
|
|
"epoch": 2.519683270623912,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004373217444921066,
|
|
"loss": 5.2896,
|
|
"mean_token_accuracy": 0.19338531494140626,
|
|
"num_tokens": 50080533.0,
|
|
"step": 22435
|
|
},
|
|
{
|
|
"entropy": 5.434464168548584,
|
|
"epoch": 2.5202448475318695,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00043729393942626665,
|
|
"loss": 5.1146,
|
|
"mean_token_accuracy": 0.20435652881860733,
|
|
"num_tokens": 50090897.0,
|
|
"step": 22440
|
|
},
|
|
{
|
|
"entropy": 5.371607303619385,
|
|
"epoch": 2.520806424439827,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00043726612919292476,
|
|
"loss": 5.0809,
|
|
"mean_token_accuracy": 0.20662710517644883,
|
|
"num_tokens": 50101594.0,
|
|
"step": 22445
|
|
},
|
|
{
|
|
"entropy": 5.419979047775269,
|
|
"epoch": 2.521368001347785,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004372383137929663,
|
|
"loss": 5.1598,
|
|
"mean_token_accuracy": 0.20202449411153794,
|
|
"num_tokens": 50111923.0,
|
|
"step": 22450
|
|
},
|
|
{
|
|
"entropy": 5.500240087509155,
|
|
"epoch": 2.521929578255742,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00043721049322727705,
|
|
"loss": 5.2375,
|
|
"mean_token_accuracy": 0.2016470327973366,
|
|
"num_tokens": 50123295.0,
|
|
"step": 22455
|
|
},
|
|
{
|
|
"entropy": 5.538443660736084,
|
|
"epoch": 2.5224911551636997,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004371826674967428,
|
|
"loss": 5.2995,
|
|
"mean_token_accuracy": 0.19865900725126268,
|
|
"num_tokens": 50133245.0,
|
|
"step": 22460
|
|
},
|
|
{
|
|
"entropy": 5.416790199279785,
|
|
"epoch": 2.5230527320716574,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00043715483660224943,
|
|
"loss": 5.1531,
|
|
"mean_token_accuracy": 0.2004664197564125,
|
|
"num_tokens": 50144827.0,
|
|
"step": 22465
|
|
},
|
|
{
|
|
"entropy": 5.56309289932251,
|
|
"epoch": 2.5236143089796146,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004371270005446833,
|
|
"loss": 5.2798,
|
|
"mean_token_accuracy": 0.19326076358556749,
|
|
"num_tokens": 50156244.0,
|
|
"step": 22470
|
|
},
|
|
{
|
|
"entropy": 5.544798040390015,
|
|
"epoch": 2.5241758858875722,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004370991593249305,
|
|
"loss": 5.2527,
|
|
"mean_token_accuracy": 0.19526829123497008,
|
|
"num_tokens": 50168363.0,
|
|
"step": 22475
|
|
},
|
|
{
|
|
"entropy": 5.50516448020935,
|
|
"epoch": 2.52473746279553,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00043707131294387766,
|
|
"loss": 5.1814,
|
|
"mean_token_accuracy": 0.1983770489692688,
|
|
"num_tokens": 50179370.0,
|
|
"step": 22480
|
|
},
|
|
{
|
|
"entropy": 5.5335962772369385,
|
|
"epoch": 2.525299039703487,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004370434614024113,
|
|
"loss": 5.2165,
|
|
"mean_token_accuracy": 0.2053406596183777,
|
|
"num_tokens": 50191583.0,
|
|
"step": 22485
|
|
},
|
|
{
|
|
"entropy": 5.489752197265625,
|
|
"epoch": 2.525860616611445,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00043701560470141824,
|
|
"loss": 5.1718,
|
|
"mean_token_accuracy": 0.1955375775694847,
|
|
"num_tokens": 50202008.0,
|
|
"step": 22490
|
|
},
|
|
{
|
|
"entropy": 5.420732212066651,
|
|
"epoch": 2.5264221935194024,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004369877428417856,
|
|
"loss": 5.226,
|
|
"mean_token_accuracy": 0.19432284235954284,
|
|
"num_tokens": 50212632.0,
|
|
"step": 22495
|
|
},
|
|
{
|
|
"entropy": 5.474782037734985,
|
|
"epoch": 2.52698377042736,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004369598758244003,
|
|
"loss": 5.2266,
|
|
"mean_token_accuracy": 0.20370943248271942,
|
|
"num_tokens": 50223485.0,
|
|
"step": 22500
|
|
},
|
|
{
|
|
"entropy": 5.567892932891846,
|
|
"epoch": 2.5275453473353178,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00043693200365014985,
|
|
"loss": 5.2945,
|
|
"mean_token_accuracy": 0.19657267183065413,
|
|
"num_tokens": 50235516.0,
|
|
"step": 22505
|
|
},
|
|
{
|
|
"entropy": 5.475609064102173,
|
|
"epoch": 2.528106924243275,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00043690412631992154,
|
|
"loss": 5.1424,
|
|
"mean_token_accuracy": 0.20403032153844833,
|
|
"num_tokens": 50246846.0,
|
|
"step": 22510
|
|
},
|
|
{
|
|
"entropy": 5.420966577529907,
|
|
"epoch": 2.5286685011512327,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00043687624383460306,
|
|
"loss": 5.219,
|
|
"mean_token_accuracy": 0.1896538943052292,
|
|
"num_tokens": 50258433.0,
|
|
"step": 22515
|
|
},
|
|
{
|
|
"entropy": 5.553134536743164,
|
|
"epoch": 2.5292300780591903,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00043684835619508215,
|
|
"loss": 5.3207,
|
|
"mean_token_accuracy": 0.1976487845182419,
|
|
"num_tokens": 50269111.0,
|
|
"step": 22520
|
|
},
|
|
{
|
|
"entropy": 5.492173671722412,
|
|
"epoch": 2.5297916549671475,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004368204634022469,
|
|
"loss": 5.3164,
|
|
"mean_token_accuracy": 0.19301936626434327,
|
|
"num_tokens": 50280137.0,
|
|
"step": 22525
|
|
},
|
|
{
|
|
"entropy": 5.49051604270935,
|
|
"epoch": 2.530353231875105,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004367925654569852,
|
|
"loss": 5.1619,
|
|
"mean_token_accuracy": 0.20840794444084168,
|
|
"num_tokens": 50291717.0,
|
|
"step": 22530
|
|
},
|
|
{
|
|
"entropy": 5.510760068893433,
|
|
"epoch": 2.530914808783063,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004367646623601856,
|
|
"loss": 5.246,
|
|
"mean_token_accuracy": 0.19451362788677215,
|
|
"num_tokens": 50303107.0,
|
|
"step": 22535
|
|
},
|
|
{
|
|
"entropy": 5.374897003173828,
|
|
"epoch": 2.5314763856910205,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004367367541127364,
|
|
"loss": 5.16,
|
|
"mean_token_accuracy": 0.20004209876060486,
|
|
"num_tokens": 50313997.0,
|
|
"step": 22540
|
|
},
|
|
{
|
|
"entropy": 5.437381267547607,
|
|
"epoch": 2.532037962598978,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004367088407155261,
|
|
"loss": 5.1711,
|
|
"mean_token_accuracy": 0.20653210282325746,
|
|
"num_tokens": 50324327.0,
|
|
"step": 22545
|
|
},
|
|
{
|
|
"entropy": 5.412775897979737,
|
|
"epoch": 2.5325995395069354,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004366809221694437,
|
|
"loss": 5.1087,
|
|
"mean_token_accuracy": 0.20845651477575303,
|
|
"num_tokens": 50334787.0,
|
|
"step": 22550
|
|
},
|
|
{
|
|
"entropy": 5.393438243865967,
|
|
"epoch": 2.533161116414893,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00043665299847537805,
|
|
"loss": 5.0917,
|
|
"mean_token_accuracy": 0.20833459943532945,
|
|
"num_tokens": 50345418.0,
|
|
"step": 22555
|
|
},
|
|
{
|
|
"entropy": 5.4462038516998295,
|
|
"epoch": 2.5337226933228507,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00043662506963421815,
|
|
"loss": 5.21,
|
|
"mean_token_accuracy": 0.2001356914639473,
|
|
"num_tokens": 50357047.0,
|
|
"step": 22560
|
|
},
|
|
{
|
|
"entropy": 5.437898397445679,
|
|
"epoch": 2.534284270230808,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004365971356468534,
|
|
"loss": 5.1666,
|
|
"mean_token_accuracy": 0.2075835272669792,
|
|
"num_tokens": 50368385.0,
|
|
"step": 22565
|
|
},
|
|
{
|
|
"entropy": 5.465651798248291,
|
|
"epoch": 2.5348458471387656,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00043656919651417314,
|
|
"loss": 5.2319,
|
|
"mean_token_accuracy": 0.2005552276968956,
|
|
"num_tokens": 50379389.0,
|
|
"step": 22570
|
|
},
|
|
{
|
|
"entropy": 5.500934362411499,
|
|
"epoch": 2.5354074240467233,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000436541252237067,
|
|
"loss": 5.1982,
|
|
"mean_token_accuracy": 0.20028745979070664,
|
|
"num_tokens": 50390124.0,
|
|
"step": 22575
|
|
},
|
|
{
|
|
"entropy": 5.495947074890137,
|
|
"epoch": 2.5359690009546805,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004365133028164248,
|
|
"loss": 5.212,
|
|
"mean_token_accuracy": 0.20381075590848924,
|
|
"num_tokens": 50401385.0,
|
|
"step": 22580
|
|
},
|
|
{
|
|
"entropy": 5.4653639793396,
|
|
"epoch": 2.536530577862638,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004364853482531363,
|
|
"loss": 5.2541,
|
|
"mean_token_accuracy": 0.19280862361192702,
|
|
"num_tokens": 50412890.0,
|
|
"step": 22585
|
|
},
|
|
{
|
|
"entropy": 5.487146472930908,
|
|
"epoch": 2.537092154770596,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00043645738854809177,
|
|
"loss": 5.2635,
|
|
"mean_token_accuracy": 0.20081137865781784,
|
|
"num_tokens": 50424403.0,
|
|
"step": 22590
|
|
},
|
|
{
|
|
"entropy": 5.578891134262085,
|
|
"epoch": 2.5376537316785535,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004364294237021813,
|
|
"loss": 5.2179,
|
|
"mean_token_accuracy": 0.19921068251132965,
|
|
"num_tokens": 50434598.0,
|
|
"step": 22595
|
|
},
|
|
{
|
|
"entropy": 5.575385189056396,
|
|
"epoch": 2.538215308586511,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00043640145371629544,
|
|
"loss": 5.2863,
|
|
"mean_token_accuracy": 0.19035972505807877,
|
|
"num_tokens": 50446661.0,
|
|
"step": 22600
|
|
},
|
|
{
|
|
"entropy": 5.566793584823609,
|
|
"epoch": 2.5387768854944683,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004363734785913246,
|
|
"loss": 5.2841,
|
|
"mean_token_accuracy": 0.19049828946590425,
|
|
"num_tokens": 50458188.0,
|
|
"step": 22605
|
|
},
|
|
{
|
|
"entropy": 5.502074956893921,
|
|
"epoch": 2.539338462402426,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004363454983281597,
|
|
"loss": 5.2551,
|
|
"mean_token_accuracy": 0.20060526132583617,
|
|
"num_tokens": 50469305.0,
|
|
"step": 22610
|
|
},
|
|
{
|
|
"entropy": 5.516038227081299,
|
|
"epoch": 2.5399000393103837,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004363175129276915,
|
|
"loss": 5.2024,
|
|
"mean_token_accuracy": 0.20006683319807053,
|
|
"num_tokens": 50480450.0,
|
|
"step": 22615
|
|
},
|
|
{
|
|
"entropy": 5.439752578735352,
|
|
"epoch": 2.540461616218341,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00043628952239081113,
|
|
"loss": 5.1684,
|
|
"mean_token_accuracy": 0.19881519228219985,
|
|
"num_tokens": 50490397.0,
|
|
"step": 22620
|
|
},
|
|
{
|
|
"entropy": 5.377489328384399,
|
|
"epoch": 2.5410231931262985,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00043626152671840984,
|
|
"loss": 5.1397,
|
|
"mean_token_accuracy": 0.20063460767269134,
|
|
"num_tokens": 50501068.0,
|
|
"step": 22625
|
|
},
|
|
{
|
|
"entropy": 5.532137823104859,
|
|
"epoch": 2.541584770034256,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000436233525911379,
|
|
"loss": 5.4097,
|
|
"mean_token_accuracy": 0.1885458707809448,
|
|
"num_tokens": 50513268.0,
|
|
"step": 22630
|
|
},
|
|
{
|
|
"entropy": 5.467395544052124,
|
|
"epoch": 2.542146346942214,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004362055199706101,
|
|
"loss": 5.1054,
|
|
"mean_token_accuracy": 0.20370217710733413,
|
|
"num_tokens": 50523806.0,
|
|
"step": 22635
|
|
},
|
|
{
|
|
"entropy": 5.480954504013061,
|
|
"epoch": 2.5427079238501715,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00043617750889699496,
|
|
"loss": 5.1612,
|
|
"mean_token_accuracy": 0.1982889235019684,
|
|
"num_tokens": 50535000.0,
|
|
"step": 22640
|
|
},
|
|
{
|
|
"entropy": 5.490712070465088,
|
|
"epoch": 2.5432695007581287,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00043614949269142546,
|
|
"loss": 5.2655,
|
|
"mean_token_accuracy": 0.19457219839096068,
|
|
"num_tokens": 50546042.0,
|
|
"step": 22645
|
|
},
|
|
{
|
|
"entropy": 5.574697399139405,
|
|
"epoch": 2.5438310776660864,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00043612147135479356,
|
|
"loss": 5.2525,
|
|
"mean_token_accuracy": 0.19598281979560853,
|
|
"num_tokens": 50556645.0,
|
|
"step": 22650
|
|
},
|
|
{
|
|
"entropy": 5.558626699447632,
|
|
"epoch": 2.544392654574044,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004360934448879916,
|
|
"loss": 5.2675,
|
|
"mean_token_accuracy": 0.1959284171462059,
|
|
"num_tokens": 50567904.0,
|
|
"step": 22655
|
|
},
|
|
{
|
|
"entropy": 5.389188003540039,
|
|
"epoch": 2.5449542314820013,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004360654132919118,
|
|
"loss": 5.0798,
|
|
"mean_token_accuracy": 0.20017922520637513,
|
|
"num_tokens": 50578280.0,
|
|
"step": 22660
|
|
},
|
|
{
|
|
"entropy": 5.408729982376099,
|
|
"epoch": 2.545515808389959,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004360373765674467,
|
|
"loss": 5.1929,
|
|
"mean_token_accuracy": 0.20137256681919097,
|
|
"num_tokens": 50590232.0,
|
|
"step": 22665
|
|
},
|
|
{
|
|
"entropy": 5.453761339187622,
|
|
"epoch": 2.5460773852979166,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00043600933471548927,
|
|
"loss": 5.0839,
|
|
"mean_token_accuracy": 0.20683782547712326,
|
|
"num_tokens": 50601469.0,
|
|
"step": 22670
|
|
},
|
|
{
|
|
"entropy": 5.401768207550049,
|
|
"epoch": 2.546638962205874,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004359812877369321,
|
|
"loss": 5.0664,
|
|
"mean_token_accuracy": 0.20404326915740967,
|
|
"num_tokens": 50612090.0,
|
|
"step": 22675
|
|
},
|
|
{
|
|
"entropy": 5.395300674438476,
|
|
"epoch": 2.5472005391138315,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00043595323563266815,
|
|
"loss": 5.1831,
|
|
"mean_token_accuracy": 0.19551308006048201,
|
|
"num_tokens": 50623834.0,
|
|
"step": 22680
|
|
},
|
|
{
|
|
"entropy": 5.485017538070679,
|
|
"epoch": 2.547762116021789,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00043592517840359093,
|
|
"loss": 5.2384,
|
|
"mean_token_accuracy": 0.1948726862668991,
|
|
"num_tokens": 50633966.0,
|
|
"step": 22685
|
|
},
|
|
{
|
|
"entropy": 5.438422155380249,
|
|
"epoch": 2.548323692929747,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004358971160505936,
|
|
"loss": 5.0889,
|
|
"mean_token_accuracy": 0.20339812934398652,
|
|
"num_tokens": 50644354.0,
|
|
"step": 22690
|
|
},
|
|
{
|
|
"entropy": 5.429444885253906,
|
|
"epoch": 2.5488852698377045,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00043586904857456963,
|
|
"loss": 5.0863,
|
|
"mean_token_accuracy": 0.20113642066717147,
|
|
"num_tokens": 50655525.0,
|
|
"step": 22695
|
|
},
|
|
{
|
|
"entropy": 5.491053676605224,
|
|
"epoch": 2.5494468467456617,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00043584097597641275,
|
|
"loss": 5.3234,
|
|
"mean_token_accuracy": 0.19047256857156752,
|
|
"num_tokens": 50667879.0,
|
|
"step": 22700
|
|
},
|
|
{
|
|
"entropy": 5.393489217758178,
|
|
"epoch": 2.5500084236536193,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00043581289825701683,
|
|
"loss": 5.0668,
|
|
"mean_token_accuracy": 0.20350636243820192,
|
|
"num_tokens": 50679568.0,
|
|
"step": 22705
|
|
},
|
|
{
|
|
"entropy": 5.448760032653809,
|
|
"epoch": 2.550570000561577,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004357848154172759,
|
|
"loss": 5.2297,
|
|
"mean_token_accuracy": 0.20112274587154388,
|
|
"num_tokens": 50690172.0,
|
|
"step": 22710
|
|
},
|
|
{
|
|
"entropy": 5.433311319351196,
|
|
"epoch": 2.5511315774695342,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00043575672745808404,
|
|
"loss": 5.1244,
|
|
"mean_token_accuracy": 0.20036081075668336,
|
|
"num_tokens": 50701150.0,
|
|
"step": 22715
|
|
},
|
|
{
|
|
"entropy": 5.471509742736816,
|
|
"epoch": 2.551693154377492,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00043572863438033556,
|
|
"loss": 5.2306,
|
|
"mean_token_accuracy": 0.20599816590547562,
|
|
"num_tokens": 50712407.0,
|
|
"step": 22720
|
|
},
|
|
{
|
|
"entropy": 5.449364757537841,
|
|
"epoch": 2.5522547312854496,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004357005361849251,
|
|
"loss": 5.1526,
|
|
"mean_token_accuracy": 0.19876994341611862,
|
|
"num_tokens": 50723122.0,
|
|
"step": 22725
|
|
},
|
|
{
|
|
"entropy": 5.477801656723022,
|
|
"epoch": 2.552816308193407,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00043567243287274726,
|
|
"loss": 5.2063,
|
|
"mean_token_accuracy": 0.19595978260040284,
|
|
"num_tokens": 50734479.0,
|
|
"step": 22730
|
|
},
|
|
{
|
|
"entropy": 5.380903196334839,
|
|
"epoch": 2.553377885101365,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00043564432444469686,
|
|
"loss": 5.168,
|
|
"mean_token_accuracy": 0.20650181621313096,
|
|
"num_tokens": 50745098.0,
|
|
"step": 22735
|
|
},
|
|
{
|
|
"entropy": 5.489142274856567,
|
|
"epoch": 2.553939462009322,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00043561621090166885,
|
|
"loss": 5.2122,
|
|
"mean_token_accuracy": 0.1987846463918686,
|
|
"num_tokens": 50755793.0,
|
|
"step": 22740
|
|
},
|
|
{
|
|
"entropy": 5.4806722640991214,
|
|
"epoch": 2.5545010389172798,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004355880922445584,
|
|
"loss": 5.2219,
|
|
"mean_token_accuracy": 0.19182201474905014,
|
|
"num_tokens": 50767685.0,
|
|
"step": 22745
|
|
},
|
|
{
|
|
"entropy": 5.517179250717163,
|
|
"epoch": 2.5550626158252374,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.00043555996847426077,
|
|
"loss": 5.2962,
|
|
"mean_token_accuracy": 0.19072840809822084,
|
|
"num_tokens": 50778583.0,
|
|
"step": 22750
|
|
},
|
|
{
|
|
"entropy": 5.492299604415893,
|
|
"epoch": 2.5556241927331946,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00043553183959167154,
|
|
"loss": 5.1876,
|
|
"mean_token_accuracy": 0.2016289323568344,
|
|
"num_tokens": 50789651.0,
|
|
"step": 22755
|
|
},
|
|
{
|
|
"entropy": 5.546571874618531,
|
|
"epoch": 2.5561857696411523,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00043550370559768614,
|
|
"loss": 5.3283,
|
|
"mean_token_accuracy": 0.19424901008605958,
|
|
"num_tokens": 50800846.0,
|
|
"step": 22760
|
|
},
|
|
{
|
|
"entropy": 5.488478755950927,
|
|
"epoch": 2.55674734654911,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004354755664932006,
|
|
"loss": 5.0754,
|
|
"mean_token_accuracy": 0.2037645012140274,
|
|
"num_tokens": 50812532.0,
|
|
"step": 22765
|
|
},
|
|
{
|
|
"entropy": 5.517052888870239,
|
|
"epoch": 2.557308923457067,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00043544742227911076,
|
|
"loss": 5.235,
|
|
"mean_token_accuracy": 0.19830751568078994,
|
|
"num_tokens": 50823592.0,
|
|
"step": 22770
|
|
},
|
|
{
|
|
"entropy": 5.446296691894531,
|
|
"epoch": 2.557870500365025,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00043541927295631276,
|
|
"loss": 5.1188,
|
|
"mean_token_accuracy": 0.2011640876531601,
|
|
"num_tokens": 50834392.0,
|
|
"step": 22775
|
|
},
|
|
{
|
|
"entropy": 5.541642093658448,
|
|
"epoch": 2.5584320772729825,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00043539111852570296,
|
|
"loss": 5.2677,
|
|
"mean_token_accuracy": 0.19484104365110397,
|
|
"num_tokens": 50845371.0,
|
|
"step": 22780
|
|
},
|
|
{
|
|
"entropy": 5.506129312515259,
|
|
"epoch": 2.55899365418094,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00043536295898817767,
|
|
"loss": 5.2706,
|
|
"mean_token_accuracy": 0.1952488377690315,
|
|
"num_tokens": 50857748.0,
|
|
"step": 22785
|
|
},
|
|
{
|
|
"entropy": 5.424519681930542,
|
|
"epoch": 2.559555231088898,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004353347943446336,
|
|
"loss": 5.0747,
|
|
"mean_token_accuracy": 0.2082340955734253,
|
|
"num_tokens": 50868646.0,
|
|
"step": 22790
|
|
},
|
|
{
|
|
"entropy": 5.4368438720703125,
|
|
"epoch": 2.560116807996855,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00043530662459596744,
|
|
"loss": 5.1143,
|
|
"mean_token_accuracy": 0.204285891354084,
|
|
"num_tokens": 50880566.0,
|
|
"step": 22795
|
|
},
|
|
{
|
|
"entropy": 5.462652015686035,
|
|
"epoch": 2.5606783849048127,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004352784497430762,
|
|
"loss": 5.2017,
|
|
"mean_token_accuracy": 0.2011650323867798,
|
|
"num_tokens": 50891487.0,
|
|
"step": 22800
|
|
},
|
|
{
|
|
"entropy": 5.471800041198731,
|
|
"epoch": 2.5612399618127704,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00043525026978685706,
|
|
"loss": 5.245,
|
|
"mean_token_accuracy": 0.19139301478862764,
|
|
"num_tokens": 50902522.0,
|
|
"step": 22805
|
|
},
|
|
{
|
|
"entropy": 5.590824174880981,
|
|
"epoch": 2.5618015387207276,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00043522208472820706,
|
|
"loss": 5.2266,
|
|
"mean_token_accuracy": 0.19290973246097565,
|
|
"num_tokens": 50913363.0,
|
|
"step": 22810
|
|
},
|
|
{
|
|
"entropy": 5.479837369918823,
|
|
"epoch": 2.5623631156286852,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004351938945680238,
|
|
"loss": 5.2048,
|
|
"mean_token_accuracy": 0.20074327141046525,
|
|
"num_tokens": 50923724.0,
|
|
"step": 22815
|
|
},
|
|
{
|
|
"entropy": 5.470147228240966,
|
|
"epoch": 2.562924692536643,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004351656993072048,
|
|
"loss": 5.1929,
|
|
"mean_token_accuracy": 0.20039606094360352,
|
|
"num_tokens": 50933575.0,
|
|
"step": 22820
|
|
},
|
|
{
|
|
"entropy": 5.43289155960083,
|
|
"epoch": 2.5634862694446006,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004351374989466477,
|
|
"loss": 5.1707,
|
|
"mean_token_accuracy": 0.2038708046078682,
|
|
"num_tokens": 50944619.0,
|
|
"step": 22825
|
|
},
|
|
{
|
|
"entropy": 5.409995031356812,
|
|
"epoch": 2.5640478463525582,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00043510929348725065,
|
|
"loss": 5.179,
|
|
"mean_token_accuracy": 0.20432940125465393,
|
|
"num_tokens": 50955701.0,
|
|
"step": 22830
|
|
},
|
|
{
|
|
"entropy": 5.415213918685913,
|
|
"epoch": 2.5646094232605154,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00043508108292991156,
|
|
"loss": 5.043,
|
|
"mean_token_accuracy": 0.20145202428102493,
|
|
"num_tokens": 50966544.0,
|
|
"step": 22835
|
|
},
|
|
{
|
|
"entropy": 5.467957401275635,
|
|
"epoch": 2.565171000168473,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004350528672755287,
|
|
"loss": 5.2507,
|
|
"mean_token_accuracy": 0.20001019388437272,
|
|
"num_tokens": 50976648.0,
|
|
"step": 22840
|
|
},
|
|
{
|
|
"entropy": 5.550426721572876,
|
|
"epoch": 2.5657325770764308,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004350246465250005,
|
|
"loss": 5.2135,
|
|
"mean_token_accuracy": 0.19686073064804077,
|
|
"num_tokens": 50988173.0,
|
|
"step": 22845
|
|
},
|
|
{
|
|
"entropy": 5.446621656417847,
|
|
"epoch": 2.566294153984388,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00043499642067922544,
|
|
"loss": 5.079,
|
|
"mean_token_accuracy": 0.20425282418727875,
|
|
"num_tokens": 50999274.0,
|
|
"step": 22850
|
|
},
|
|
{
|
|
"entropy": 5.344490814208984,
|
|
"epoch": 2.5668557308923456,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00043496818973910235,
|
|
"loss": 5.1445,
|
|
"mean_token_accuracy": 0.20603708922863007,
|
|
"num_tokens": 51010213.0,
|
|
"step": 22855
|
|
},
|
|
{
|
|
"entropy": 5.440465784072876,
|
|
"epoch": 2.5674173078003033,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00043493995370553,
|
|
"loss": 5.2107,
|
|
"mean_token_accuracy": 0.20147900581359862,
|
|
"num_tokens": 51021460.0,
|
|
"step": 22860
|
|
},
|
|
{
|
|
"entropy": 5.586348199844361,
|
|
"epoch": 2.5679788847082605,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00043491171257940755,
|
|
"loss": 5.2025,
|
|
"mean_token_accuracy": 0.19831876158714296,
|
|
"num_tokens": 51031713.0,
|
|
"step": 22865
|
|
},
|
|
{
|
|
"entropy": 5.510029125213623,
|
|
"epoch": 2.568540461616218,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00043488346636163405,
|
|
"loss": 5.2917,
|
|
"mean_token_accuracy": 0.19384196400642395,
|
|
"num_tokens": 51043026.0,
|
|
"step": 22870
|
|
},
|
|
{
|
|
"entropy": 5.571712589263916,
|
|
"epoch": 2.569102038524176,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004348552150531091,
|
|
"loss": 5.2381,
|
|
"mean_token_accuracy": 0.19675661921501159,
|
|
"num_tokens": 51054838.0,
|
|
"step": 22875
|
|
},
|
|
{
|
|
"entropy": 5.467933416366577,
|
|
"epoch": 2.5696636154321335,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00043482695865473207,
|
|
"loss": 5.0715,
|
|
"mean_token_accuracy": 0.20232197344303132,
|
|
"num_tokens": 51065574.0,
|
|
"step": 22880
|
|
},
|
|
{
|
|
"entropy": 5.409094667434692,
|
|
"epoch": 2.570225192340091,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004347986971674026,
|
|
"loss": 5.1494,
|
|
"mean_token_accuracy": 0.20092492699623107,
|
|
"num_tokens": 51076814.0,
|
|
"step": 22885
|
|
},
|
|
{
|
|
"entropy": 5.415322494506836,
|
|
"epoch": 2.5707867692480484,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00043477043059202077,
|
|
"loss": 5.2407,
|
|
"mean_token_accuracy": 0.19303952008485795,
|
|
"num_tokens": 51089075.0,
|
|
"step": 22890
|
|
},
|
|
{
|
|
"entropy": 5.505451917648315,
|
|
"epoch": 2.571348346156006,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004347421589294864,
|
|
"loss": 5.2667,
|
|
"mean_token_accuracy": 0.1963049903512001,
|
|
"num_tokens": 51100148.0,
|
|
"step": 22895
|
|
},
|
|
{
|
|
"entropy": 5.574727296829224,
|
|
"epoch": 2.5719099230639637,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004347138821806997,
|
|
"loss": 5.3076,
|
|
"mean_token_accuracy": 0.1986745685338974,
|
|
"num_tokens": 51111148.0,
|
|
"step": 22900
|
|
},
|
|
{
|
|
"entropy": 5.625747489929199,
|
|
"epoch": 2.572471499971921,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000434685600346561,
|
|
"loss": 5.2892,
|
|
"mean_token_accuracy": 0.19100103825330733,
|
|
"num_tokens": 51122563.0,
|
|
"step": 22905
|
|
},
|
|
{
|
|
"entropy": 5.407369470596313,
|
|
"epoch": 2.5730330768798786,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000434657313427971,
|
|
"loss": 5.1609,
|
|
"mean_token_accuracy": 0.19958069324493408,
|
|
"num_tokens": 51132676.0,
|
|
"step": 22910
|
|
},
|
|
{
|
|
"entropy": 5.435240173339844,
|
|
"epoch": 2.5735946537878363,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004346290214258301,
|
|
"loss": 5.1567,
|
|
"mean_token_accuracy": 0.19375762194395066,
|
|
"num_tokens": 51144317.0,
|
|
"step": 22915
|
|
},
|
|
{
|
|
"entropy": 5.6386651515960695,
|
|
"epoch": 2.574156230695794,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00043460072434103934,
|
|
"loss": 5.3721,
|
|
"mean_token_accuracy": 0.18261118978261948,
|
|
"num_tokens": 51156181.0,
|
|
"step": 22920
|
|
},
|
|
{
|
|
"entropy": 5.426962900161743,
|
|
"epoch": 2.5747178076037516,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004345724221744996,
|
|
"loss": 5.1135,
|
|
"mean_token_accuracy": 0.20535062551498412,
|
|
"num_tokens": 51166825.0,
|
|
"step": 22925
|
|
},
|
|
{
|
|
"entropy": 5.504230594635009,
|
|
"epoch": 2.575279384511709,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00043454411492711197,
|
|
"loss": 5.3378,
|
|
"mean_token_accuracy": 0.1932621866464615,
|
|
"num_tokens": 51178839.0,
|
|
"step": 22930
|
|
},
|
|
{
|
|
"entropy": 5.446401357650757,
|
|
"epoch": 2.5758409614196665,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00043451580259977793,
|
|
"loss": 5.2076,
|
|
"mean_token_accuracy": 0.19552009999752046,
|
|
"num_tokens": 51190811.0,
|
|
"step": 22935
|
|
},
|
|
{
|
|
"entropy": 5.473272323608398,
|
|
"epoch": 2.576402538327624,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00043448748519339875,
|
|
"loss": 5.1934,
|
|
"mean_token_accuracy": 0.19591692537069322,
|
|
"num_tokens": 51201991.0,
|
|
"step": 22940
|
|
},
|
|
{
|
|
"entropy": 5.526747941970825,
|
|
"epoch": 2.5769641152355813,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00043445916270887626,
|
|
"loss": 5.2256,
|
|
"mean_token_accuracy": 0.20157719552516937,
|
|
"num_tokens": 51213017.0,
|
|
"step": 22945
|
|
},
|
|
{
|
|
"entropy": 5.49044189453125,
|
|
"epoch": 2.577525692143539,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004344308351471123,
|
|
"loss": 5.1731,
|
|
"mean_token_accuracy": 0.1987592473626137,
|
|
"num_tokens": 51224412.0,
|
|
"step": 22950
|
|
},
|
|
{
|
|
"entropy": 5.507965898513794,
|
|
"epoch": 2.5780872690514967,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00043440250250900854,
|
|
"loss": 5.24,
|
|
"mean_token_accuracy": 0.19685512632131577,
|
|
"num_tokens": 51235043.0,
|
|
"step": 22955
|
|
},
|
|
{
|
|
"entropy": 5.484808254241943,
|
|
"epoch": 2.578648845959454,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004343741647954673,
|
|
"loss": 5.2642,
|
|
"mean_token_accuracy": 0.1931155279278755,
|
|
"num_tokens": 51246182.0,
|
|
"step": 22960
|
|
},
|
|
{
|
|
"entropy": 5.567646455764771,
|
|
"epoch": 2.5792104228674115,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004343458220073909,
|
|
"loss": 5.327,
|
|
"mean_token_accuracy": 0.19570422619581224,
|
|
"num_tokens": 51259791.0,
|
|
"step": 22965
|
|
},
|
|
{
|
|
"entropy": 5.588500118255615,
|
|
"epoch": 2.579771999775369,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004343174741456817,
|
|
"loss": 5.327,
|
|
"mean_token_accuracy": 0.1901649221777916,
|
|
"num_tokens": 51270530.0,
|
|
"step": 22970
|
|
},
|
|
{
|
|
"entropy": 5.408082675933838,
|
|
"epoch": 2.580333576683327,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004342891212112423,
|
|
"loss": 5.1613,
|
|
"mean_token_accuracy": 0.19526751935482026,
|
|
"num_tokens": 51281969.0,
|
|
"step": 22975
|
|
},
|
|
{
|
|
"entropy": 5.436216831207275,
|
|
"epoch": 2.5808951535912845,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00043426076320497557,
|
|
"loss": 5.086,
|
|
"mean_token_accuracy": 0.2031923860311508,
|
|
"num_tokens": 51292790.0,
|
|
"step": 22980
|
|
},
|
|
{
|
|
"entropy": 5.453107118606567,
|
|
"epoch": 2.5814567304992417,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00043423240012778437,
|
|
"loss": 5.1859,
|
|
"mean_token_accuracy": 0.19469663947820665,
|
|
"num_tokens": 51303949.0,
|
|
"step": 22985
|
|
},
|
|
{
|
|
"entropy": 5.448466014862061,
|
|
"epoch": 2.5820183074071994,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004342040319805717,
|
|
"loss": 5.1273,
|
|
"mean_token_accuracy": 0.20429383367300033,
|
|
"num_tokens": 51314570.0,
|
|
"step": 22990
|
|
},
|
|
{
|
|
"entropy": 5.350348806381225,
|
|
"epoch": 2.582579884315157,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000434175658764241,
|
|
"loss": 5.0804,
|
|
"mean_token_accuracy": 0.20541241019964218,
|
|
"num_tokens": 51325210.0,
|
|
"step": 22995
|
|
},
|
|
{
|
|
"entropy": 5.420697450637817,
|
|
"epoch": 2.5831414612231143,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00043414728047969553,
|
|
"loss": 5.0501,
|
|
"mean_token_accuracy": 0.2020192414522171,
|
|
"num_tokens": 51335871.0,
|
|
"step": 23000
|
|
},
|
|
{
|
|
"entropy": 5.459543085098266,
|
|
"epoch": 2.583703038131072,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00043411889712783897,
|
|
"loss": 5.2261,
|
|
"mean_token_accuracy": 0.20133862346410752,
|
|
"num_tokens": 51346821.0,
|
|
"step": 23005
|
|
},
|
|
{
|
|
"entropy": 5.494036054611206,
|
|
"epoch": 2.5842646150390296,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00043409050870957505,
|
|
"loss": 5.2234,
|
|
"mean_token_accuracy": 0.1899457350373268,
|
|
"num_tokens": 51358746.0,
|
|
"step": 23010
|
|
},
|
|
{
|
|
"entropy": 5.5528693199157715,
|
|
"epoch": 2.5848261919469873,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004340621152258075,
|
|
"loss": 5.2553,
|
|
"mean_token_accuracy": 0.19268431812524794,
|
|
"num_tokens": 51369628.0,
|
|
"step": 23015
|
|
},
|
|
{
|
|
"entropy": 5.575812244415284,
|
|
"epoch": 2.585387768854945,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00043403371667744055,
|
|
"loss": 5.2254,
|
|
"mean_token_accuracy": 0.20492194443941117,
|
|
"num_tokens": 51382160.0,
|
|
"step": 23020
|
|
},
|
|
{
|
|
"entropy": 5.488270616531372,
|
|
"epoch": 2.585949345762902,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004340053130653785,
|
|
"loss": 5.2482,
|
|
"mean_token_accuracy": 0.1930004522204399,
|
|
"num_tokens": 51394843.0,
|
|
"step": 23025
|
|
},
|
|
{
|
|
"entropy": 5.458188247680664,
|
|
"epoch": 2.58651092267086,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004339769043905255,
|
|
"loss": 5.1908,
|
|
"mean_token_accuracy": 0.2022606372833252,
|
|
"num_tokens": 51405714.0,
|
|
"step": 23030
|
|
},
|
|
{
|
|
"entropy": 5.505884313583374,
|
|
"epoch": 2.5870724995788175,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00043394849065378624,
|
|
"loss": 5.1488,
|
|
"mean_token_accuracy": 0.1990939497947693,
|
|
"num_tokens": 51416292.0,
|
|
"step": 23035
|
|
},
|
|
{
|
|
"entropy": 5.4181712627410885,
|
|
"epoch": 2.5876340764867747,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00043392007185606533,
|
|
"loss": 5.1202,
|
|
"mean_token_accuracy": 0.2047677993774414,
|
|
"num_tokens": 51426993.0,
|
|
"step": 23040
|
|
},
|
|
{
|
|
"entropy": 5.430881786346435,
|
|
"epoch": 2.5881956533947323,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004338916479982678,
|
|
"loss": 5.261,
|
|
"mean_token_accuracy": 0.19708542823791503,
|
|
"num_tokens": 51439493.0,
|
|
"step": 23045
|
|
},
|
|
{
|
|
"entropy": 5.531647872924805,
|
|
"epoch": 2.58875723030269,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00043386321908129856,
|
|
"loss": 5.1841,
|
|
"mean_token_accuracy": 0.20050522834062576,
|
|
"num_tokens": 51451705.0,
|
|
"step": 23050
|
|
},
|
|
{
|
|
"entropy": 5.560615825653076,
|
|
"epoch": 2.589318807210647,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.00043383478510606276,
|
|
"loss": 5.155,
|
|
"mean_token_accuracy": 0.20101606696844102,
|
|
"num_tokens": 51463044.0,
|
|
"step": 23055
|
|
},
|
|
{
|
|
"entropy": 5.390435457229614,
|
|
"epoch": 2.589880384118605,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004338063460734658,
|
|
"loss": 5.1888,
|
|
"mean_token_accuracy": 0.2007523164153099,
|
|
"num_tokens": 51475009.0,
|
|
"step": 23060
|
|
},
|
|
{
|
|
"entropy": 5.416891384124756,
|
|
"epoch": 2.5904419610265625,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004337779019844132,
|
|
"loss": 5.1968,
|
|
"mean_token_accuracy": 0.1994771331548691,
|
|
"num_tokens": 51486068.0,
|
|
"step": 23065
|
|
},
|
|
{
|
|
"entropy": 5.532764530181884,
|
|
"epoch": 2.59100353793452,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00043374945283981066,
|
|
"loss": 5.2478,
|
|
"mean_token_accuracy": 0.20258497595787048,
|
|
"num_tokens": 51497642.0,
|
|
"step": 23070
|
|
},
|
|
{
|
|
"entropy": 5.575276184082031,
|
|
"epoch": 2.591565114842478,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004337209986405639,
|
|
"loss": 5.248,
|
|
"mean_token_accuracy": 0.19231952279806136,
|
|
"num_tokens": 51511013.0,
|
|
"step": 23075
|
|
},
|
|
{
|
|
"entropy": 5.547844696044922,
|
|
"epoch": 2.592126691750435,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000433692539387579,
|
|
"loss": 5.3667,
|
|
"mean_token_accuracy": 0.1921800434589386,
|
|
"num_tokens": 51521687.0,
|
|
"step": 23080
|
|
},
|
|
{
|
|
"entropy": 5.525119400024414,
|
|
"epoch": 2.5926882686583927,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004336640750817621,
|
|
"loss": 5.2325,
|
|
"mean_token_accuracy": 0.19389444291591645,
|
|
"num_tokens": 51532288.0,
|
|
"step": 23085
|
|
},
|
|
{
|
|
"entropy": 5.534699010848999,
|
|
"epoch": 2.5932498455663504,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00043363560572401953,
|
|
"loss": 5.2335,
|
|
"mean_token_accuracy": 0.19883880764245987,
|
|
"num_tokens": 51543101.0,
|
|
"step": 23090
|
|
},
|
|
{
|
|
"entropy": 5.462389039993286,
|
|
"epoch": 2.5938114224743076,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00043360713131525774,
|
|
"loss": 5.2866,
|
|
"mean_token_accuracy": 0.19957807213068007,
|
|
"num_tokens": 51554729.0,
|
|
"step": 23095
|
|
},
|
|
{
|
|
"entropy": 5.492091512680053,
|
|
"epoch": 2.5943729993822653,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004335786518563834,
|
|
"loss": 5.2021,
|
|
"mean_token_accuracy": 0.19596800506114959,
|
|
"num_tokens": 51567232.0,
|
|
"step": 23100
|
|
},
|
|
{
|
|
"entropy": 5.553070068359375,
|
|
"epoch": 2.594934576290223,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004335501673483033,
|
|
"loss": 5.1923,
|
|
"mean_token_accuracy": 0.1995108276605606,
|
|
"num_tokens": 51577679.0,
|
|
"step": 23105
|
|
},
|
|
{
|
|
"entropy": 5.453506088256836,
|
|
"epoch": 2.5954961531981806,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00043352167779192423,
|
|
"loss": 5.1237,
|
|
"mean_token_accuracy": 0.196798375248909,
|
|
"num_tokens": 51588656.0,
|
|
"step": 23110
|
|
},
|
|
{
|
|
"entropy": 5.468847608566284,
|
|
"epoch": 2.5960577301061383,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00043349318318815363,
|
|
"loss": 5.2261,
|
|
"mean_token_accuracy": 0.1949308842420578,
|
|
"num_tokens": 51599016.0,
|
|
"step": 23115
|
|
},
|
|
{
|
|
"entropy": 5.317247819900513,
|
|
"epoch": 2.5966193070140955,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00043346468353789853,
|
|
"loss": 4.9954,
|
|
"mean_token_accuracy": 0.21364231258630753,
|
|
"num_tokens": 51610288.0,
|
|
"step": 23120
|
|
},
|
|
{
|
|
"entropy": 5.483580780029297,
|
|
"epoch": 2.597180883922053,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004334361788420664,
|
|
"loss": 5.2992,
|
|
"mean_token_accuracy": 0.19442235231399535,
|
|
"num_tokens": 51622450.0,
|
|
"step": 23125
|
|
},
|
|
{
|
|
"entropy": 5.531235551834106,
|
|
"epoch": 2.597742460830011,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00043340766910156497,
|
|
"loss": 5.1118,
|
|
"mean_token_accuracy": 0.20397164821624755,
|
|
"num_tokens": 51635111.0,
|
|
"step": 23130
|
|
},
|
|
{
|
|
"entropy": 5.473828744888306,
|
|
"epoch": 2.598304037737968,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00043337915431730195,
|
|
"loss": 5.2457,
|
|
"mean_token_accuracy": 0.1937500387430191,
|
|
"num_tokens": 51646088.0,
|
|
"step": 23135
|
|
},
|
|
{
|
|
"entropy": 5.447720718383789,
|
|
"epoch": 2.5988656146459257,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00043335063449018515,
|
|
"loss": 5.1647,
|
|
"mean_token_accuracy": 0.19829271733760834,
|
|
"num_tokens": 51659337.0,
|
|
"step": 23140
|
|
},
|
|
{
|
|
"entropy": 5.547460508346558,
|
|
"epoch": 2.5994271915538834,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004333221096211227,
|
|
"loss": 5.3022,
|
|
"mean_token_accuracy": 0.1992781475186348,
|
|
"num_tokens": 51670954.0,
|
|
"step": 23145
|
|
},
|
|
{
|
|
"entropy": 5.447976112365723,
|
|
"epoch": 2.599988768461841,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00043329357971102296,
|
|
"loss": 5.1381,
|
|
"mean_token_accuracy": 0.1973046228289604,
|
|
"num_tokens": 51681104.0,
|
|
"step": 23150
|
|
},
|
|
{
|
|
"entropy": 5.321099185943604,
|
|
"epoch": 2.6005503453697982,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00043326504476079425,
|
|
"loss": 5.0318,
|
|
"mean_token_accuracy": 0.2073124334216118,
|
|
"num_tokens": 51691337.0,
|
|
"step": 23155
|
|
},
|
|
{
|
|
"entropy": 5.390917158126831,
|
|
"epoch": 2.601111922277756,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004332365047713451,
|
|
"loss": 5.1477,
|
|
"mean_token_accuracy": 0.2008199766278267,
|
|
"num_tokens": 51702488.0,
|
|
"step": 23160
|
|
},
|
|
{
|
|
"entropy": 5.53355302810669,
|
|
"epoch": 2.6016734991857136,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004332079597435842,
|
|
"loss": 5.2438,
|
|
"mean_token_accuracy": 0.19955824315547943,
|
|
"num_tokens": 51714439.0,
|
|
"step": 23165
|
|
},
|
|
{
|
|
"entropy": 5.630756664276123,
|
|
"epoch": 2.602235076093671,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004331794096784206,
|
|
"loss": 5.288,
|
|
"mean_token_accuracy": 0.19511518627405167,
|
|
"num_tokens": 51726423.0,
|
|
"step": 23170
|
|
},
|
|
{
|
|
"entropy": 5.529940795898438,
|
|
"epoch": 2.6027966530016284,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004331508545767633,
|
|
"loss": 5.2563,
|
|
"mean_token_accuracy": 0.20738064795732497,
|
|
"num_tokens": 51736198.0,
|
|
"step": 23175
|
|
},
|
|
{
|
|
"entropy": 5.395144462585449,
|
|
"epoch": 2.603358229909586,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004331222944395213,
|
|
"loss": 5.1376,
|
|
"mean_token_accuracy": 0.20435541719198227,
|
|
"num_tokens": 51746993.0,
|
|
"step": 23180
|
|
},
|
|
{
|
|
"entropy": 5.437501335144043,
|
|
"epoch": 2.6039198068175438,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004330937292676042,
|
|
"loss": 5.1534,
|
|
"mean_token_accuracy": 0.20632504522800446,
|
|
"num_tokens": 51756981.0,
|
|
"step": 23185
|
|
},
|
|
{
|
|
"entropy": 5.400945997238159,
|
|
"epoch": 2.604481383725501,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004330651590619214,
|
|
"loss": 5.161,
|
|
"mean_token_accuracy": 0.20466522127389908,
|
|
"num_tokens": 51768192.0,
|
|
"step": 23190
|
|
},
|
|
{
|
|
"entropy": 5.4939188957214355,
|
|
"epoch": 2.6050429606334586,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004330365838233827,
|
|
"loss": 5.2165,
|
|
"mean_token_accuracy": 0.19679141342639922,
|
|
"num_tokens": 51778996.0,
|
|
"step": 23195
|
|
},
|
|
{
|
|
"entropy": 5.5277821063995365,
|
|
"epoch": 2.6056045375414163,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00043300800355289786,
|
|
"loss": 5.2444,
|
|
"mean_token_accuracy": 0.1924500972032547,
|
|
"num_tokens": 51790179.0,
|
|
"step": 23200
|
|
},
|
|
{
|
|
"entropy": 5.470696496963501,
|
|
"epoch": 2.606166114449374,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00043297941825137684,
|
|
"loss": 5.2489,
|
|
"mean_token_accuracy": 0.20165283530950545,
|
|
"num_tokens": 51801312.0,
|
|
"step": 23205
|
|
},
|
|
{
|
|
"entropy": 5.46109676361084,
|
|
"epoch": 2.6067276913573316,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00043295082791972993,
|
|
"loss": 5.1642,
|
|
"mean_token_accuracy": 0.2015443429350853,
|
|
"num_tokens": 51811960.0,
|
|
"step": 23210
|
|
},
|
|
{
|
|
"entropy": 5.454913663864136,
|
|
"epoch": 2.607289268265289,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00043292223255886737,
|
|
"loss": 5.2618,
|
|
"mean_token_accuracy": 0.19244524836540222,
|
|
"num_tokens": 51823166.0,
|
|
"step": 23215
|
|
},
|
|
{
|
|
"entropy": 5.479498434066772,
|
|
"epoch": 2.6078508451732465,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00043289363216969973,
|
|
"loss": 5.1326,
|
|
"mean_token_accuracy": 0.19873957484960555,
|
|
"num_tokens": 51835517.0,
|
|
"step": 23220
|
|
},
|
|
{
|
|
"entropy": 5.452497148513794,
|
|
"epoch": 2.608412422081204,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00043286502675313757,
|
|
"loss": 5.1666,
|
|
"mean_token_accuracy": 0.2023353934288025,
|
|
"num_tokens": 51846690.0,
|
|
"step": 23225
|
|
},
|
|
{
|
|
"entropy": 5.389071798324585,
|
|
"epoch": 2.6089739989891614,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004328364163100917,
|
|
"loss": 5.159,
|
|
"mean_token_accuracy": 0.20219334661960603,
|
|
"num_tokens": 51857234.0,
|
|
"step": 23230
|
|
},
|
|
{
|
|
"entropy": 5.48324146270752,
|
|
"epoch": 2.609535575897119,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004328078008414731,
|
|
"loss": 5.243,
|
|
"mean_token_accuracy": 0.20180547386407852,
|
|
"num_tokens": 51867913.0,
|
|
"step": 23235
|
|
},
|
|
{
|
|
"entropy": 5.437986230850219,
|
|
"epoch": 2.6100971528050767,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000432779180348193,
|
|
"loss": 5.1851,
|
|
"mean_token_accuracy": 0.2051671788096428,
|
|
"num_tokens": 51878252.0,
|
|
"step": 23240
|
|
},
|
|
{
|
|
"entropy": 5.383799028396607,
|
|
"epoch": 2.6106587297130344,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00043275055483116254,
|
|
"loss": 5.1143,
|
|
"mean_token_accuracy": 0.20199795216321945,
|
|
"num_tokens": 51888407.0,
|
|
"step": 23245
|
|
},
|
|
{
|
|
"entropy": 5.508200931549072,
|
|
"epoch": 2.6112203066209916,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004327219242912933,
|
|
"loss": 5.1982,
|
|
"mean_token_accuracy": 0.19967449456453323,
|
|
"num_tokens": 51900042.0,
|
|
"step": 23250
|
|
},
|
|
{
|
|
"entropy": 5.510458517074585,
|
|
"epoch": 2.6117818835289492,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004326932887294967,
|
|
"loss": 5.21,
|
|
"mean_token_accuracy": 0.19857455641031266,
|
|
"num_tokens": 51909691.0,
|
|
"step": 23255
|
|
},
|
|
{
|
|
"entropy": 5.560432863235474,
|
|
"epoch": 2.612343460436907,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004326646481466848,
|
|
"loss": 5.2666,
|
|
"mean_token_accuracy": 0.19549815654754638,
|
|
"num_tokens": 51921691.0,
|
|
"step": 23260
|
|
},
|
|
{
|
|
"entropy": 5.457535886764527,
|
|
"epoch": 2.6129050373448646,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004326360025437692,
|
|
"loss": 5.1382,
|
|
"mean_token_accuracy": 0.20069834738969802,
|
|
"num_tokens": 51934050.0,
|
|
"step": 23265
|
|
},
|
|
{
|
|
"entropy": 5.486303091049194,
|
|
"epoch": 2.613466614252822,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00043260735192166217,
|
|
"loss": 5.1686,
|
|
"mean_token_accuracy": 0.2039589539170265,
|
|
"num_tokens": 51944566.0,
|
|
"step": 23270
|
|
},
|
|
{
|
|
"entropy": 5.459819507598877,
|
|
"epoch": 2.6140281911607794,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000432578696281276,
|
|
"loss": 5.0944,
|
|
"mean_token_accuracy": 0.20982656031847,
|
|
"num_tokens": 51955485.0,
|
|
"step": 23275
|
|
},
|
|
{
|
|
"entropy": 5.425382089614868,
|
|
"epoch": 2.614589768068737,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000432550035623523,
|
|
"loss": 5.1682,
|
|
"mean_token_accuracy": 0.20477787256240845,
|
|
"num_tokens": 51965124.0,
|
|
"step": 23280
|
|
},
|
|
{
|
|
"entropy": 5.551755666732788,
|
|
"epoch": 2.6151513449766943,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004325213699493157,
|
|
"loss": 5.2096,
|
|
"mean_token_accuracy": 0.2066628560423851,
|
|
"num_tokens": 51976362.0,
|
|
"step": 23285
|
|
},
|
|
{
|
|
"entropy": 5.376646900177002,
|
|
"epoch": 2.615712921884652,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004324926992595669,
|
|
"loss": 5.0861,
|
|
"mean_token_accuracy": 0.19803429394960403,
|
|
"num_tokens": 51988068.0,
|
|
"step": 23290
|
|
},
|
|
{
|
|
"entropy": 5.44796347618103,
|
|
"epoch": 2.6162744987926096,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004324640235551895,
|
|
"loss": 5.1431,
|
|
"mean_token_accuracy": 0.20669957399368286,
|
|
"num_tokens": 51998392.0,
|
|
"step": 23295
|
|
},
|
|
{
|
|
"entropy": 5.409528064727783,
|
|
"epoch": 2.6168360757005673,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004324353428370965,
|
|
"loss": 5.1153,
|
|
"mean_token_accuracy": 0.19969575405120848,
|
|
"num_tokens": 52009416.0,
|
|
"step": 23300
|
|
},
|
|
{
|
|
"entropy": 5.540070486068726,
|
|
"epoch": 2.617397652608525,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004324066571062012,
|
|
"loss": 5.1928,
|
|
"mean_token_accuracy": 0.20413899719715117,
|
|
"num_tokens": 52020554.0,
|
|
"step": 23305
|
|
},
|
|
{
|
|
"entropy": 5.405008935928345,
|
|
"epoch": 2.617959229516482,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004323779663634168,
|
|
"loss": 5.1964,
|
|
"mean_token_accuracy": 0.19754453748464584,
|
|
"num_tokens": 52031301.0,
|
|
"step": 23310
|
|
},
|
|
{
|
|
"entropy": 5.419484329223633,
|
|
"epoch": 2.61852080642444,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000432349270609657,
|
|
"loss": 5.1435,
|
|
"mean_token_accuracy": 0.2014838293194771,
|
|
"num_tokens": 52041720.0,
|
|
"step": 23315
|
|
},
|
|
{
|
|
"entropy": 5.39289870262146,
|
|
"epoch": 2.6190823833323975,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00043232056984583527,
|
|
"loss": 5.0732,
|
|
"mean_token_accuracy": 0.2068752959370613,
|
|
"num_tokens": 52051911.0,
|
|
"step": 23320
|
|
},
|
|
{
|
|
"entropy": 5.439510345458984,
|
|
"epoch": 2.6196439602403547,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004322918640728656,
|
|
"loss": 5.1656,
|
|
"mean_token_accuracy": 0.20078354924917222,
|
|
"num_tokens": 52062842.0,
|
|
"step": 23325
|
|
},
|
|
{
|
|
"entropy": 5.469933795928955,
|
|
"epoch": 2.6202055371483124,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00043226315329166203,
|
|
"loss": 5.305,
|
|
"mean_token_accuracy": 0.19540444612503052,
|
|
"num_tokens": 52075034.0,
|
|
"step": 23330
|
|
},
|
|
{
|
|
"entropy": 5.499102926254272,
|
|
"epoch": 2.62076711405627,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00043223443750313873,
|
|
"loss": 5.0946,
|
|
"mean_token_accuracy": 0.21070630103349686,
|
|
"num_tokens": 52084782.0,
|
|
"step": 23335
|
|
},
|
|
{
|
|
"entropy": 5.3721761226654055,
|
|
"epoch": 2.6213286909642277,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004322057167082099,
|
|
"loss": 5.1122,
|
|
"mean_token_accuracy": 0.19998955577611924,
|
|
"num_tokens": 52095623.0,
|
|
"step": 23340
|
|
},
|
|
{
|
|
"entropy": 5.439248418807983,
|
|
"epoch": 2.621890267872185,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00043217699090779006,
|
|
"loss": 5.1704,
|
|
"mean_token_accuracy": 0.20737988203763963,
|
|
"num_tokens": 52107240.0,
|
|
"step": 23345
|
|
},
|
|
{
|
|
"entropy": 5.4496763229370115,
|
|
"epoch": 2.6224518447801426,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00043214826010279383,
|
|
"loss": 5.2667,
|
|
"mean_token_accuracy": 0.19826025366783143,
|
|
"num_tokens": 52118157.0,
|
|
"step": 23350
|
|
},
|
|
{
|
|
"entropy": 5.565532588958741,
|
|
"epoch": 2.6230134216881003,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004321195242941361,
|
|
"loss": 5.2864,
|
|
"mean_token_accuracy": 0.18660368919372558,
|
|
"num_tokens": 52130578.0,
|
|
"step": 23355
|
|
},
|
|
{
|
|
"entropy": 5.540079402923584,
|
|
"epoch": 2.623574998596058,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00043209078348273175,
|
|
"loss": 5.1551,
|
|
"mean_token_accuracy": 0.2040082111954689,
|
|
"num_tokens": 52142057.0,
|
|
"step": 23360
|
|
},
|
|
{
|
|
"entropy": 5.5023033618927,
|
|
"epoch": 2.624136575504015,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004320620376694959,
|
|
"loss": 5.2609,
|
|
"mean_token_accuracy": 0.19550875574350357,
|
|
"num_tokens": 52152370.0,
|
|
"step": 23365
|
|
},
|
|
{
|
|
"entropy": 5.404144763946533,
|
|
"epoch": 2.624698152411973,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00043203328685534396,
|
|
"loss": 5.1575,
|
|
"mean_token_accuracy": 0.20197988003492356,
|
|
"num_tokens": 52162139.0,
|
|
"step": 23370
|
|
},
|
|
{
|
|
"entropy": 5.493215322494507,
|
|
"epoch": 2.6252597293199305,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004320045310411912,
|
|
"loss": 5.2252,
|
|
"mean_token_accuracy": 0.20067870914936065,
|
|
"num_tokens": 52172820.0,
|
|
"step": 23375
|
|
},
|
|
{
|
|
"entropy": 5.429520177841186,
|
|
"epoch": 2.6258213062278877,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00043197577022795327,
|
|
"loss": 5.0699,
|
|
"mean_token_accuracy": 0.20700942426919938,
|
|
"num_tokens": 52183315.0,
|
|
"step": 23380
|
|
},
|
|
{
|
|
"entropy": 5.355142116546631,
|
|
"epoch": 2.6263828831358453,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004319470044165459,
|
|
"loss": 5.1411,
|
|
"mean_token_accuracy": 0.20844318121671676,
|
|
"num_tokens": 52194776.0,
|
|
"step": 23385
|
|
},
|
|
{
|
|
"entropy": 5.56971287727356,
|
|
"epoch": 2.626944460043803,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004319182336078852,
|
|
"loss": 5.3254,
|
|
"mean_token_accuracy": 0.19389017671346664,
|
|
"num_tokens": 52207370.0,
|
|
"step": 23390
|
|
},
|
|
{
|
|
"entropy": 5.484973049163818,
|
|
"epoch": 2.6275060369517607,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000431889457802887,
|
|
"loss": 5.1299,
|
|
"mean_token_accuracy": 0.20800730139017104,
|
|
"num_tokens": 52218287.0,
|
|
"step": 23395
|
|
},
|
|
{
|
|
"entropy": 5.44383020401001,
|
|
"epoch": 2.6280676138597183,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004318606770024675,
|
|
"loss": 5.255,
|
|
"mean_token_accuracy": 0.19475822299718856,
|
|
"num_tokens": 52229418.0,
|
|
"step": 23400
|
|
},
|
|
{
|
|
"entropy": 5.563400936126709,
|
|
"epoch": 2.6286291907676755,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004318318912075433,
|
|
"loss": 5.2024,
|
|
"mean_token_accuracy": 0.19832005500793456,
|
|
"num_tokens": 52240382.0,
|
|
"step": 23405
|
|
},
|
|
{
|
|
"entropy": 5.518240451812744,
|
|
"epoch": 2.629190767675633,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004318031004190308,
|
|
"loss": 5.2272,
|
|
"mean_token_accuracy": 0.19684348702430726,
|
|
"num_tokens": 52252608.0,
|
|
"step": 23410
|
|
},
|
|
{
|
|
"entropy": 5.431765222549439,
|
|
"epoch": 2.629752344583591,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00043177430463784685,
|
|
"loss": 5.133,
|
|
"mean_token_accuracy": 0.2142768010497093,
|
|
"num_tokens": 52262940.0,
|
|
"step": 23415
|
|
},
|
|
{
|
|
"entropy": 5.367644214630127,
|
|
"epoch": 2.630313921491548,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00043174550386490816,
|
|
"loss": 5.0846,
|
|
"mean_token_accuracy": 0.20578556060791015,
|
|
"num_tokens": 52273270.0,
|
|
"step": 23420
|
|
},
|
|
{
|
|
"entropy": 5.427347135543823,
|
|
"epoch": 2.6308754983995057,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004317166981011319,
|
|
"loss": 5.1611,
|
|
"mean_token_accuracy": 0.200395405292511,
|
|
"num_tokens": 52284433.0,
|
|
"step": 23425
|
|
},
|
|
{
|
|
"entropy": 5.548338174819946,
|
|
"epoch": 2.6314370753074634,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00043168788734743516,
|
|
"loss": 5.1775,
|
|
"mean_token_accuracy": 0.20473337322473525,
|
|
"num_tokens": 52296088.0,
|
|
"step": 23430
|
|
},
|
|
{
|
|
"entropy": 5.497882080078125,
|
|
"epoch": 2.631998652215421,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00043165907160473525,
|
|
"loss": 5.2498,
|
|
"mean_token_accuracy": 0.19243747889995574,
|
|
"num_tokens": 52307683.0,
|
|
"step": 23435
|
|
},
|
|
{
|
|
"entropy": 5.447935438156128,
|
|
"epoch": 2.6325602291233783,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004316302508739499,
|
|
"loss": 5.2304,
|
|
"mean_token_accuracy": 0.19726531058549882,
|
|
"num_tokens": 52319845.0,
|
|
"step": 23440
|
|
},
|
|
{
|
|
"entropy": 5.488337135314941,
|
|
"epoch": 2.633121806031336,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004316014251559965,
|
|
"loss": 5.1653,
|
|
"mean_token_accuracy": 0.2008945792913437,
|
|
"num_tokens": 52330196.0,
|
|
"step": 23445
|
|
},
|
|
{
|
|
"entropy": 5.593804883956909,
|
|
"epoch": 2.6336833829392936,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00043157259445179304,
|
|
"loss": 5.3748,
|
|
"mean_token_accuracy": 0.19053859859704972,
|
|
"num_tokens": 52341510.0,
|
|
"step": 23450
|
|
},
|
|
{
|
|
"entropy": 5.471933364868164,
|
|
"epoch": 2.6342449598472513,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004315437587622574,
|
|
"loss": 5.1341,
|
|
"mean_token_accuracy": 0.2022364392876625,
|
|
"num_tokens": 52351848.0,
|
|
"step": 23455
|
|
},
|
|
{
|
|
"entropy": 5.483906698226929,
|
|
"epoch": 2.6348065367552085,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00043151491808830777,
|
|
"loss": 5.1955,
|
|
"mean_token_accuracy": 0.1995692566037178,
|
|
"num_tokens": 52363698.0,
|
|
"step": 23460
|
|
},
|
|
{
|
|
"entropy": 5.477593946456909,
|
|
"epoch": 2.635368113663166,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00043148607243086255,
|
|
"loss": 5.1555,
|
|
"mean_token_accuracy": 0.1993621587753296,
|
|
"num_tokens": 52374433.0,
|
|
"step": 23465
|
|
},
|
|
{
|
|
"entropy": 5.4144477367401125,
|
|
"epoch": 2.635929690571124,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004314572217908399,
|
|
"loss": 5.2165,
|
|
"mean_token_accuracy": 0.20255142897367479,
|
|
"num_tokens": 52385762.0,
|
|
"step": 23470
|
|
},
|
|
{
|
|
"entropy": 5.481233692169189,
|
|
"epoch": 2.636491267479081,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004314283661691587,
|
|
"loss": 4.9868,
|
|
"mean_token_accuracy": 0.21361292004585267,
|
|
"num_tokens": 52397058.0,
|
|
"step": 23475
|
|
},
|
|
{
|
|
"entropy": 5.512315082550049,
|
|
"epoch": 2.6370528443870387,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004313995055667377,
|
|
"loss": 5.2547,
|
|
"mean_token_accuracy": 0.1977449432015419,
|
|
"num_tokens": 52407671.0,
|
|
"step": 23480
|
|
},
|
|
{
|
|
"entropy": 5.477112340927124,
|
|
"epoch": 2.6376144212949963,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004313706399844958,
|
|
"loss": 5.2396,
|
|
"mean_token_accuracy": 0.1980699732899666,
|
|
"num_tokens": 52419511.0,
|
|
"step": 23485
|
|
},
|
|
{
|
|
"entropy": 5.394292974472046,
|
|
"epoch": 2.638175998202954,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000431341769423352,
|
|
"loss": 5.1114,
|
|
"mean_token_accuracy": 0.1963311478495598,
|
|
"num_tokens": 52431311.0,
|
|
"step": 23490
|
|
},
|
|
{
|
|
"entropy": 5.493609428405762,
|
|
"epoch": 2.6387375751109117,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004313128938842257,
|
|
"loss": 5.152,
|
|
"mean_token_accuracy": 0.19902120381593705,
|
|
"num_tokens": 52442184.0,
|
|
"step": 23495
|
|
},
|
|
{
|
|
"entropy": 5.515880727767945,
|
|
"epoch": 2.639299152018869,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00043128401336803616,
|
|
"loss": 5.223,
|
|
"mean_token_accuracy": 0.19565608203411103,
|
|
"num_tokens": 52454837.0,
|
|
"step": 23500
|
|
},
|
|
{
|
|
"entropy": 5.5168108463287355,
|
|
"epoch": 2.6398607289268265,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00043125512787570305,
|
|
"loss": 5.2155,
|
|
"mean_token_accuracy": 0.199556864798069,
|
|
"num_tokens": 52465378.0,
|
|
"step": 23505
|
|
},
|
|
{
|
|
"entropy": 5.483809185028076,
|
|
"epoch": 2.640422305834784,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004312262374081461,
|
|
"loss": 5.2363,
|
|
"mean_token_accuracy": 0.19988692104816436,
|
|
"num_tokens": 52476025.0,
|
|
"step": 23510
|
|
},
|
|
{
|
|
"entropy": 5.536465692520141,
|
|
"epoch": 2.6409838827427414,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00043119734196628507,
|
|
"loss": 5.1809,
|
|
"mean_token_accuracy": 0.1984606832265854,
|
|
"num_tokens": 52487408.0,
|
|
"step": 23515
|
|
},
|
|
{
|
|
"entropy": 5.496368551254273,
|
|
"epoch": 2.641545459650699,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00043116844155104025,
|
|
"loss": 5.1245,
|
|
"mean_token_accuracy": 0.20686034560203553,
|
|
"num_tokens": 52497801.0,
|
|
"step": 23520
|
|
},
|
|
{
|
|
"entropy": 5.411055946350098,
|
|
"epoch": 2.6421070365586568,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004311395361633316,
|
|
"loss": 5.1853,
|
|
"mean_token_accuracy": 0.19698130935430527,
|
|
"num_tokens": 52508918.0,
|
|
"step": 23525
|
|
},
|
|
{
|
|
"entropy": 5.412768316268921,
|
|
"epoch": 2.6426686134666144,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004311106258040795,
|
|
"loss": 5.1194,
|
|
"mean_token_accuracy": 0.20621820837259291,
|
|
"num_tokens": 52519951.0,
|
|
"step": 23530
|
|
},
|
|
{
|
|
"entropy": 5.340115308761597,
|
|
"epoch": 2.643230190374572,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00043108171047420463,
|
|
"loss": 5.122,
|
|
"mean_token_accuracy": 0.1990943282842636,
|
|
"num_tokens": 52530710.0,
|
|
"step": 23535
|
|
},
|
|
{
|
|
"entropy": 5.361363506317138,
|
|
"epoch": 2.6437917672825293,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004310527901746275,
|
|
"loss": 5.086,
|
|
"mean_token_accuracy": 0.20682694166898727,
|
|
"num_tokens": 52542188.0,
|
|
"step": 23540
|
|
},
|
|
{
|
|
"entropy": 5.488569259643555,
|
|
"epoch": 2.644353344190487,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000431023864906269,
|
|
"loss": 5.2185,
|
|
"mean_token_accuracy": 0.20059878677129744,
|
|
"num_tokens": 52553848.0,
|
|
"step": 23545
|
|
},
|
|
{
|
|
"entropy": 5.427157735824585,
|
|
"epoch": 2.6449149210984446,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00043099493467005015,
|
|
"loss": 5.1484,
|
|
"mean_token_accuracy": 0.2035217434167862,
|
|
"num_tokens": 52563338.0,
|
|
"step": 23550
|
|
},
|
|
{
|
|
"entropy": 5.470952558517456,
|
|
"epoch": 2.645476498006402,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000430965999466892,
|
|
"loss": 5.2901,
|
|
"mean_token_accuracy": 0.19292771965265273,
|
|
"num_tokens": 52576369.0,
|
|
"step": 23555
|
|
},
|
|
{
|
|
"entropy": 5.481601095199585,
|
|
"epoch": 2.6460380749143595,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00043093705929771604,
|
|
"loss": 5.199,
|
|
"mean_token_accuracy": 0.20293420553207397,
|
|
"num_tokens": 52587409.0,
|
|
"step": 23560
|
|
},
|
|
{
|
|
"entropy": 5.458005094528199,
|
|
"epoch": 2.646599651822317,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004309081141634436,
|
|
"loss": 5.138,
|
|
"mean_token_accuracy": 0.19908208400011063,
|
|
"num_tokens": 52599398.0,
|
|
"step": 23565
|
|
},
|
|
{
|
|
"entropy": 5.462128734588623,
|
|
"epoch": 2.6471612287302744,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00043087916406499635,
|
|
"loss": 5.1289,
|
|
"mean_token_accuracy": 0.2062810480594635,
|
|
"num_tokens": 52609565.0,
|
|
"step": 23570
|
|
},
|
|
{
|
|
"entropy": 5.42417426109314,
|
|
"epoch": 2.647722805638232,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00043085020900329604,
|
|
"loss": 5.1929,
|
|
"mean_token_accuracy": 0.203407683968544,
|
|
"num_tokens": 52621150.0,
|
|
"step": 23575
|
|
},
|
|
{
|
|
"entropy": 5.440845346450805,
|
|
"epoch": 2.6482843825461897,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00043082124897926463,
|
|
"loss": 5.1862,
|
|
"mean_token_accuracy": 0.20108286887407303,
|
|
"num_tokens": 52632030.0,
|
|
"step": 23580
|
|
},
|
|
{
|
|
"entropy": 5.509593296051025,
|
|
"epoch": 2.6488459594541474,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004307922839938242,
|
|
"loss": 5.2972,
|
|
"mean_token_accuracy": 0.195563405752182,
|
|
"num_tokens": 52643447.0,
|
|
"step": 23585
|
|
},
|
|
{
|
|
"entropy": 5.509720754623413,
|
|
"epoch": 2.649407536362105,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00043076331404789703,
|
|
"loss": 5.1771,
|
|
"mean_token_accuracy": 0.2076278507709503,
|
|
"num_tokens": 52655017.0,
|
|
"step": 23590
|
|
},
|
|
{
|
|
"entropy": 5.5232213020324705,
|
|
"epoch": 2.6499691132700622,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004307343391424055,
|
|
"loss": 5.2104,
|
|
"mean_token_accuracy": 0.19614923596382142,
|
|
"num_tokens": 52665674.0,
|
|
"step": 23595
|
|
},
|
|
{
|
|
"entropy": 5.39630389213562,
|
|
"epoch": 2.65053069017802,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004307053592782723,
|
|
"loss": 5.1602,
|
|
"mean_token_accuracy": 0.20166541785001754,
|
|
"num_tokens": 52678177.0,
|
|
"step": 23600
|
|
},
|
|
{
|
|
"entropy": 5.471887302398682,
|
|
"epoch": 2.6510922670859776,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00043067637445642004,
|
|
"loss": 5.2367,
|
|
"mean_token_accuracy": 0.199528306722641,
|
|
"num_tokens": 52689326.0,
|
|
"step": 23605
|
|
},
|
|
{
|
|
"entropy": 5.503168153762817,
|
|
"epoch": 2.651653843993935,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00043064738467777166,
|
|
"loss": 5.2686,
|
|
"mean_token_accuracy": 0.1897120252251625,
|
|
"num_tokens": 52701686.0,
|
|
"step": 23610
|
|
},
|
|
{
|
|
"entropy": 5.455009794235229,
|
|
"epoch": 2.6522154209018924,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00043061838994325007,
|
|
"loss": 5.1746,
|
|
"mean_token_accuracy": 0.20472166687250137,
|
|
"num_tokens": 52713422.0,
|
|
"step": 23615
|
|
},
|
|
{
|
|
"entropy": 5.4553224563598635,
|
|
"epoch": 2.65277699780985,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00043058939025377867,
|
|
"loss": 5.2259,
|
|
"mean_token_accuracy": 0.19934384673833846,
|
|
"num_tokens": 52724438.0,
|
|
"step": 23620
|
|
},
|
|
{
|
|
"entropy": 5.455756664276123,
|
|
"epoch": 2.6533385747178078,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004305603856102808,
|
|
"loss": 5.1782,
|
|
"mean_token_accuracy": 0.20492662936449052,
|
|
"num_tokens": 52734657.0,
|
|
"step": 23625
|
|
},
|
|
{
|
|
"entropy": 5.455070829391479,
|
|
"epoch": 2.6539001516257654,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004305313760136799,
|
|
"loss": 5.1379,
|
|
"mean_token_accuracy": 0.20828091055154802,
|
|
"num_tokens": 52745832.0,
|
|
"step": 23630
|
|
},
|
|
{
|
|
"entropy": 5.506795835494995,
|
|
"epoch": 2.6544617285337226,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00043050236146489955,
|
|
"loss": 5.3156,
|
|
"mean_token_accuracy": 0.1952225759625435,
|
|
"num_tokens": 52758795.0,
|
|
"step": 23635
|
|
},
|
|
{
|
|
"entropy": 5.488795757293701,
|
|
"epoch": 2.6550233054416803,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004304733419648638,
|
|
"loss": 5.2211,
|
|
"mean_token_accuracy": 0.2016402930021286,
|
|
"num_tokens": 52769154.0,
|
|
"step": 23640
|
|
},
|
|
{
|
|
"entropy": 5.472024202346802,
|
|
"epoch": 2.655584882349638,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00043044431751449656,
|
|
"loss": 5.1591,
|
|
"mean_token_accuracy": 0.20421334505081176,
|
|
"num_tokens": 52779189.0,
|
|
"step": 23645
|
|
},
|
|
{
|
|
"entropy": 5.516177177429199,
|
|
"epoch": 2.656146459257595,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004304152881147219,
|
|
"loss": 5.2928,
|
|
"mean_token_accuracy": 0.20140977799892426,
|
|
"num_tokens": 52789545.0,
|
|
"step": 23650
|
|
},
|
|
{
|
|
"entropy": 5.587547445297242,
|
|
"epoch": 2.656708036165553,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004303862537664642,
|
|
"loss": 5.4089,
|
|
"mean_token_accuracy": 0.18406397551298143,
|
|
"num_tokens": 52802410.0,
|
|
"step": 23655
|
|
},
|
|
{
|
|
"entropy": 5.433873414993286,
|
|
"epoch": 2.6572696130735105,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000430357214470648,
|
|
"loss": 5.1877,
|
|
"mean_token_accuracy": 0.20008882135152817,
|
|
"num_tokens": 52814223.0,
|
|
"step": 23660
|
|
},
|
|
{
|
|
"entropy": 5.400897598266601,
|
|
"epoch": 2.6578311899814677,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004303281702281977,
|
|
"loss": 5.1332,
|
|
"mean_token_accuracy": 0.2064850002527237,
|
|
"num_tokens": 52824554.0,
|
|
"step": 23665
|
|
},
|
|
{
|
|
"entropy": 5.553000831604004,
|
|
"epoch": 2.6583927668894254,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00043029912104003827,
|
|
"loss": 5.3241,
|
|
"mean_token_accuracy": 0.1995888665318489,
|
|
"num_tokens": 52836058.0,
|
|
"step": 23670
|
|
},
|
|
{
|
|
"entropy": 5.467930746078491,
|
|
"epoch": 2.658954343797383,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00043027006690709457,
|
|
"loss": 5.265,
|
|
"mean_token_accuracy": 0.19593652337789536,
|
|
"num_tokens": 52847220.0,
|
|
"step": 23675
|
|
},
|
|
{
|
|
"entropy": 5.468914222717285,
|
|
"epoch": 2.6595159207053407,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004302410078302918,
|
|
"loss": 5.1019,
|
|
"mean_token_accuracy": 0.20464342683553696,
|
|
"num_tokens": 52858242.0,
|
|
"step": 23680
|
|
},
|
|
{
|
|
"entropy": 5.384401178359985,
|
|
"epoch": 2.6600774976132984,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00043021194381055505,
|
|
"loss": 5.0472,
|
|
"mean_token_accuracy": 0.20356269925832748,
|
|
"num_tokens": 52869439.0,
|
|
"step": 23685
|
|
},
|
|
{
|
|
"entropy": 5.583893728256226,
|
|
"epoch": 2.6606390745212556,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00043018287484880986,
|
|
"loss": 5.3961,
|
|
"mean_token_accuracy": 0.19009190201759338,
|
|
"num_tokens": 52879893.0,
|
|
"step": 23690
|
|
},
|
|
{
|
|
"entropy": 5.540567922592163,
|
|
"epoch": 2.6612006514292132,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004301538009459817,
|
|
"loss": 5.2299,
|
|
"mean_token_accuracy": 0.1975465565919876,
|
|
"num_tokens": 52891352.0,
|
|
"step": 23695
|
|
},
|
|
{
|
|
"entropy": 5.431209564208984,
|
|
"epoch": 2.661762228337171,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004301247221029964,
|
|
"loss": 5.2186,
|
|
"mean_token_accuracy": 0.19581498354673385,
|
|
"num_tokens": 52904202.0,
|
|
"step": 23700
|
|
},
|
|
{
|
|
"entropy": 5.466895246505738,
|
|
"epoch": 2.662323805245128,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00043009563832077977,
|
|
"loss": 5.1392,
|
|
"mean_token_accuracy": 0.2047729477286339,
|
|
"num_tokens": 52914495.0,
|
|
"step": 23705
|
|
},
|
|
{
|
|
"entropy": 5.477147245407105,
|
|
"epoch": 2.662885382153086,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004300665496002578,
|
|
"loss": 5.213,
|
|
"mean_token_accuracy": 0.19413714557886125,
|
|
"num_tokens": 52925930.0,
|
|
"step": 23710
|
|
},
|
|
{
|
|
"entropy": 5.504684257507324,
|
|
"epoch": 2.6634469590610435,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00043003745594235687,
|
|
"loss": 5.1831,
|
|
"mean_token_accuracy": 0.19708070307970046,
|
|
"num_tokens": 52936310.0,
|
|
"step": 23715
|
|
},
|
|
{
|
|
"entropy": 5.488216876983643,
|
|
"epoch": 2.664008535969001,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004300083573480031,
|
|
"loss": 5.2992,
|
|
"mean_token_accuracy": 0.19424211531877517,
|
|
"num_tokens": 52948801.0,
|
|
"step": 23720
|
|
},
|
|
{
|
|
"entropy": 5.553876447677612,
|
|
"epoch": 2.6645701128769588,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00042997925381812313,
|
|
"loss": 5.3393,
|
|
"mean_token_accuracy": 0.19497064799070357,
|
|
"num_tokens": 52960541.0,
|
|
"step": 23725
|
|
},
|
|
{
|
|
"entropy": 5.481603574752808,
|
|
"epoch": 2.665131689784916,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00042995014535364363,
|
|
"loss": 5.2075,
|
|
"mean_token_accuracy": 0.1960158884525299,
|
|
"num_tokens": 52971973.0,
|
|
"step": 23730
|
|
},
|
|
{
|
|
"entropy": 5.4324750900268555,
|
|
"epoch": 2.6656932666928737,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004299210319554914,
|
|
"loss": 5.1737,
|
|
"mean_token_accuracy": 0.21714765429496766,
|
|
"num_tokens": 52983124.0,
|
|
"step": 23735
|
|
},
|
|
{
|
|
"entropy": 5.479479217529297,
|
|
"epoch": 2.6662548436008313,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00042989191362459347,
|
|
"loss": 5.1177,
|
|
"mean_token_accuracy": 0.2090711385011673,
|
|
"num_tokens": 52994402.0,
|
|
"step": 23740
|
|
},
|
|
{
|
|
"entropy": 5.466092920303344,
|
|
"epoch": 2.6668164205087885,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004298627903618769,
|
|
"loss": 5.2374,
|
|
"mean_token_accuracy": 0.19495458900928497,
|
|
"num_tokens": 53005253.0,
|
|
"step": 23745
|
|
},
|
|
{
|
|
"entropy": 5.487114906311035,
|
|
"epoch": 2.667377997416746,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00042983366216826907,
|
|
"loss": 5.2558,
|
|
"mean_token_accuracy": 0.20063638240098952,
|
|
"num_tokens": 53016599.0,
|
|
"step": 23750
|
|
},
|
|
{
|
|
"entropy": 5.452792739868164,
|
|
"epoch": 2.667939574324704,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004298045290446973,
|
|
"loss": 5.1789,
|
|
"mean_token_accuracy": 0.20471510142087937,
|
|
"num_tokens": 53027412.0,
|
|
"step": 23755
|
|
},
|
|
{
|
|
"entropy": 5.491108417510986,
|
|
"epoch": 2.668501151232661,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00042977539099208937,
|
|
"loss": 5.2177,
|
|
"mean_token_accuracy": 0.19474119395017625,
|
|
"num_tokens": 53039490.0,
|
|
"step": 23760
|
|
},
|
|
{
|
|
"entropy": 5.478243064880371,
|
|
"epoch": 2.6690627281406187,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00042974624801137283,
|
|
"loss": 5.1946,
|
|
"mean_token_accuracy": 0.2009686827659607,
|
|
"num_tokens": 53049837.0,
|
|
"step": 23765
|
|
},
|
|
{
|
|
"entropy": 5.433179664611816,
|
|
"epoch": 2.6696243050485764,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00042971710010347594,
|
|
"loss": 5.1118,
|
|
"mean_token_accuracy": 0.211330346763134,
|
|
"num_tokens": 53060187.0,
|
|
"step": 23770
|
|
},
|
|
{
|
|
"entropy": 5.42611174583435,
|
|
"epoch": 2.670185881956534,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00042968794726932634,
|
|
"loss": 5.1688,
|
|
"mean_token_accuracy": 0.2024862825870514,
|
|
"num_tokens": 53072050.0,
|
|
"step": 23775
|
|
},
|
|
{
|
|
"entropy": 5.451820421218872,
|
|
"epoch": 2.6707474588644917,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004296587895098527,
|
|
"loss": 5.2358,
|
|
"mean_token_accuracy": 0.19662144035100937,
|
|
"num_tokens": 53083235.0,
|
|
"step": 23780
|
|
},
|
|
{
|
|
"entropy": 5.5170825004577635,
|
|
"epoch": 2.671309035772449,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00042962962682598316,
|
|
"loss": 5.2409,
|
|
"mean_token_accuracy": 0.19715406000614166,
|
|
"num_tokens": 53093615.0,
|
|
"step": 23785
|
|
},
|
|
{
|
|
"entropy": 5.5463752269744875,
|
|
"epoch": 2.6718706126804066,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00042960045921864627,
|
|
"loss": 5.2889,
|
|
"mean_token_accuracy": 0.19199395626783372,
|
|
"num_tokens": 53105611.0,
|
|
"step": 23790
|
|
},
|
|
{
|
|
"entropy": 5.471039342880249,
|
|
"epoch": 2.6724321895883643,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004295712866887709,
|
|
"loss": 5.0522,
|
|
"mean_token_accuracy": 0.2054540604352951,
|
|
"num_tokens": 53116343.0,
|
|
"step": 23795
|
|
},
|
|
{
|
|
"entropy": 5.454292106628418,
|
|
"epoch": 2.6729937664963215,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00042954210923728565,
|
|
"loss": 5.2195,
|
|
"mean_token_accuracy": 0.2033547967672348,
|
|
"num_tokens": 53128754.0,
|
|
"step": 23800
|
|
},
|
|
{
|
|
"entropy": 5.388036823272705,
|
|
"epoch": 2.673555343404279,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004295129268651198,
|
|
"loss": 5.091,
|
|
"mean_token_accuracy": 0.210646091401577,
|
|
"num_tokens": 53139508.0,
|
|
"step": 23805
|
|
},
|
|
{
|
|
"entropy": 5.411625480651855,
|
|
"epoch": 2.674116920312237,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004294837395732025,
|
|
"loss": 5.0998,
|
|
"mean_token_accuracy": 0.20751608312129974,
|
|
"num_tokens": 53149925.0,
|
|
"step": 23810
|
|
},
|
|
{
|
|
"entropy": 5.435418653488159,
|
|
"epoch": 2.6746784972201945,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00042945454736246293,
|
|
"loss": 5.1634,
|
|
"mean_token_accuracy": 0.20198342949151993,
|
|
"num_tokens": 53160053.0,
|
|
"step": 23815
|
|
},
|
|
{
|
|
"entropy": 5.495969581604004,
|
|
"epoch": 2.675240074128152,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00042942535023383075,
|
|
"loss": 5.1703,
|
|
"mean_token_accuracy": 0.20624391883611679,
|
|
"num_tokens": 53170723.0,
|
|
"step": 23820
|
|
},
|
|
{
|
|
"entropy": 5.39514856338501,
|
|
"epoch": 2.6758016510361093,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00042939614818823547,
|
|
"loss": 5.2044,
|
|
"mean_token_accuracy": 0.19773222655057907,
|
|
"num_tokens": 53182120.0,
|
|
"step": 23825
|
|
},
|
|
{
|
|
"entropy": 5.435149335861206,
|
|
"epoch": 2.676363227944067,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004293669412266069,
|
|
"loss": 5.1888,
|
|
"mean_token_accuracy": 0.19621680080890655,
|
|
"num_tokens": 53192481.0,
|
|
"step": 23830
|
|
},
|
|
{
|
|
"entropy": 5.4549168109893795,
|
|
"epoch": 2.6769248048520247,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004293377293498751,
|
|
"loss": 5.1761,
|
|
"mean_token_accuracy": 0.1969471037387848,
|
|
"num_tokens": 53203710.0,
|
|
"step": 23835
|
|
},
|
|
{
|
|
"entropy": 5.467357540130616,
|
|
"epoch": 2.677486381759982,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00042930851255897014,
|
|
"loss": 5.0953,
|
|
"mean_token_accuracy": 0.20897049307823182,
|
|
"num_tokens": 53214051.0,
|
|
"step": 23840
|
|
},
|
|
{
|
|
"entropy": 5.39466700553894,
|
|
"epoch": 2.6780479586679395,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004292792908548223,
|
|
"loss": 5.1258,
|
|
"mean_token_accuracy": 0.20404789447784424,
|
|
"num_tokens": 53224981.0,
|
|
"step": 23845
|
|
},
|
|
{
|
|
"entropy": 5.334466934204102,
|
|
"epoch": 2.678609535575897,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00042925006423836197,
|
|
"loss": 4.9957,
|
|
"mean_token_accuracy": 0.2121786430478096,
|
|
"num_tokens": 53236336.0,
|
|
"step": 23850
|
|
},
|
|
{
|
|
"entropy": 5.428548002243042,
|
|
"epoch": 2.6791711124838544,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00042922083271051975,
|
|
"loss": 5.2174,
|
|
"mean_token_accuracy": 0.20053329914808274,
|
|
"num_tokens": 53248212.0,
|
|
"step": 23855
|
|
},
|
|
{
|
|
"entropy": 5.479628276824951,
|
|
"epoch": 2.679732689391812,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004291915962722265,
|
|
"loss": 5.1958,
|
|
"mean_token_accuracy": 0.20091208964586257,
|
|
"num_tokens": 53258910.0,
|
|
"step": 23860
|
|
},
|
|
{
|
|
"entropy": 5.550708818435669,
|
|
"epoch": 2.6802942662997697,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004291623549244129,
|
|
"loss": 5.2285,
|
|
"mean_token_accuracy": 0.1984703153371811,
|
|
"num_tokens": 53269445.0,
|
|
"step": 23865
|
|
},
|
|
{
|
|
"entropy": 5.455594396591186,
|
|
"epoch": 2.6808558432077274,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00042913310866801024,
|
|
"loss": 5.1566,
|
|
"mean_token_accuracy": 0.20768319070339203,
|
|
"num_tokens": 53280119.0,
|
|
"step": 23870
|
|
},
|
|
{
|
|
"entropy": 5.500387048721313,
|
|
"epoch": 2.681417420115685,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00042910385750394964,
|
|
"loss": 5.1934,
|
|
"mean_token_accuracy": 0.20669564604759216,
|
|
"num_tokens": 53291496.0,
|
|
"step": 23875
|
|
},
|
|
{
|
|
"entropy": 5.46678991317749,
|
|
"epoch": 2.6819789970236423,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004290746014331623,
|
|
"loss": 5.1631,
|
|
"mean_token_accuracy": 0.19575610905885696,
|
|
"num_tokens": 53303470.0,
|
|
"step": 23880
|
|
},
|
|
{
|
|
"entropy": 5.520257139205933,
|
|
"epoch": 2.6825405739316,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00042904534045658,
|
|
"loss": 5.2588,
|
|
"mean_token_accuracy": 0.20200514942407607,
|
|
"num_tokens": 53313552.0,
|
|
"step": 23885
|
|
},
|
|
{
|
|
"entropy": 5.437272071838379,
|
|
"epoch": 2.6831021508395576,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004290160745751343,
|
|
"loss": 5.2804,
|
|
"mean_token_accuracy": 0.1971744939684868,
|
|
"num_tokens": 53325280.0,
|
|
"step": 23890
|
|
},
|
|
{
|
|
"entropy": 5.3667339324951175,
|
|
"epoch": 2.683663727747515,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004289868037897571,
|
|
"loss": 5.044,
|
|
"mean_token_accuracy": 0.2140959158539772,
|
|
"num_tokens": 53334982.0,
|
|
"step": 23895
|
|
},
|
|
{
|
|
"entropy": 5.50390248298645,
|
|
"epoch": 2.6842253046554725,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004289575281013802,
|
|
"loss": 5.2249,
|
|
"mean_token_accuracy": 0.19505434781312941,
|
|
"num_tokens": 53346367.0,
|
|
"step": 23900
|
|
},
|
|
{
|
|
"entropy": 5.463916778564453,
|
|
"epoch": 2.68478688156343,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000428928247510936,
|
|
"loss": 5.1597,
|
|
"mean_token_accuracy": 0.20073503702878953,
|
|
"num_tokens": 53356907.0,
|
|
"step": 23905
|
|
},
|
|
{
|
|
"entropy": 5.451604270935059,
|
|
"epoch": 2.685348458471388,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004288989620193567,
|
|
"loss": 5.1413,
|
|
"mean_token_accuracy": 0.2048221156001091,
|
|
"num_tokens": 53366619.0,
|
|
"step": 23910
|
|
},
|
|
{
|
|
"entropy": 5.489072227478028,
|
|
"epoch": 2.6859100353793455,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00042886967162757475,
|
|
"loss": 5.2027,
|
|
"mean_token_accuracy": 0.20132599025964737,
|
|
"num_tokens": 53377578.0,
|
|
"step": 23915
|
|
},
|
|
{
|
|
"entropy": 5.532238483428955,
|
|
"epoch": 2.6864716122873027,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00042884037633652276,
|
|
"loss": 5.1694,
|
|
"mean_token_accuracy": 0.19484029412269593,
|
|
"num_tokens": 53389416.0,
|
|
"step": 23920
|
|
},
|
|
{
|
|
"entropy": 5.399318790435791,
|
|
"epoch": 2.6870331891952604,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00042881107614713355,
|
|
"loss": 5.0257,
|
|
"mean_token_accuracy": 0.2138148456811905,
|
|
"num_tokens": 53399453.0,
|
|
"step": 23925
|
|
},
|
|
{
|
|
"entropy": 5.337710618972778,
|
|
"epoch": 2.687594766103218,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00042878177106034,
|
|
"loss": 5.1795,
|
|
"mean_token_accuracy": 0.19844985008239746,
|
|
"num_tokens": 53409933.0,
|
|
"step": 23930
|
|
},
|
|
{
|
|
"entropy": 5.467342567443848,
|
|
"epoch": 2.6881563430111752,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004287524610770752,
|
|
"loss": 5.2255,
|
|
"mean_token_accuracy": 0.20246859788894653,
|
|
"num_tokens": 53420943.0,
|
|
"step": 23935
|
|
},
|
|
{
|
|
"entropy": 5.390620326995849,
|
|
"epoch": 2.688717919919133,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00042872314619827234,
|
|
"loss": 5.0613,
|
|
"mean_token_accuracy": 0.2050351619720459,
|
|
"num_tokens": 53431450.0,
|
|
"step": 23940
|
|
},
|
|
{
|
|
"entropy": 5.334903001785278,
|
|
"epoch": 2.6892794968270906,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000428693826424865,
|
|
"loss": 5.0148,
|
|
"mean_token_accuracy": 0.2082084074616432,
|
|
"num_tokens": 53442198.0,
|
|
"step": 23945
|
|
},
|
|
{
|
|
"entropy": 5.386764860153198,
|
|
"epoch": 2.6898410737350478,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004286645017577866,
|
|
"loss": 5.0642,
|
|
"mean_token_accuracy": 0.20550597161054612,
|
|
"num_tokens": 53452411.0,
|
|
"step": 23950
|
|
},
|
|
{
|
|
"entropy": 5.39258222579956,
|
|
"epoch": 2.6904026506430054,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00042863517219797085,
|
|
"loss": 5.1279,
|
|
"mean_token_accuracy": 0.20574878752231598,
|
|
"num_tokens": 53462644.0,
|
|
"step": 23955
|
|
},
|
|
{
|
|
"entropy": 5.3428794860839846,
|
|
"epoch": 2.690964227550963,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00042860583774635165,
|
|
"loss": 5.1363,
|
|
"mean_token_accuracy": 0.2001335307955742,
|
|
"num_tokens": 53473258.0,
|
|
"step": 23960
|
|
},
|
|
{
|
|
"entropy": 5.435537242889405,
|
|
"epoch": 2.6915258044589208,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000428576498403863,
|
|
"loss": 5.128,
|
|
"mean_token_accuracy": 0.20437007397413254,
|
|
"num_tokens": 53484011.0,
|
|
"step": 23965
|
|
},
|
|
{
|
|
"entropy": 5.470778512954712,
|
|
"epoch": 2.6920873813668784,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000428547154171439,
|
|
"loss": 5.168,
|
|
"mean_token_accuracy": 0.20754805952310562,
|
|
"num_tokens": 53495549.0,
|
|
"step": 23970
|
|
},
|
|
{
|
|
"entropy": 5.4761251449584964,
|
|
"epoch": 2.6926489582748356,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004285178050500142,
|
|
"loss": 5.2413,
|
|
"mean_token_accuracy": 0.1998326763510704,
|
|
"num_tokens": 53506721.0,
|
|
"step": 23975
|
|
},
|
|
{
|
|
"entropy": 5.546339750289917,
|
|
"epoch": 2.6932105351827933,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004284884510405228,
|
|
"loss": 5.3391,
|
|
"mean_token_accuracy": 0.19034197330474853,
|
|
"num_tokens": 53518363.0,
|
|
"step": 23980
|
|
},
|
|
{
|
|
"entropy": 5.354467725753784,
|
|
"epoch": 2.693772112090751,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004284590921438997,
|
|
"loss": 5.077,
|
|
"mean_token_accuracy": 0.20418502986431122,
|
|
"num_tokens": 53529140.0,
|
|
"step": 23985
|
|
},
|
|
{
|
|
"entropy": 5.362538194656372,
|
|
"epoch": 2.694333688998708,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00042842972836107954,
|
|
"loss": 5.1498,
|
|
"mean_token_accuracy": 0.19923700243234635,
|
|
"num_tokens": 53540707.0,
|
|
"step": 23990
|
|
},
|
|
{
|
|
"entropy": 5.478306627273559,
|
|
"epoch": 2.694895265906666,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004284003596929973,
|
|
"loss": 5.1625,
|
|
"mean_token_accuracy": 0.2027212679386139,
|
|
"num_tokens": 53551297.0,
|
|
"step": 23995
|
|
},
|
|
{
|
|
"entropy": 5.385969114303589,
|
|
"epoch": 2.6954568428146235,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00042837098614058815,
|
|
"loss": 5.0659,
|
|
"mean_token_accuracy": 0.19970440119504929,
|
|
"num_tokens": 53562207.0,
|
|
"step": 24000
|
|
},
|
|
{
|
|
"epoch": 2.6954568428146235,
|
|
"eval_entropy": 5.194862051356967,
|
|
"eval_loss": 5.287596225738525,
|
|
"eval_mean_token_accuracy": 0.2040473656488166,
|
|
"eval_num_tokens": 53562207.0,
|
|
"eval_runtime": 23.7018,
|
|
"eval_samples_per_second": 1308.465,
|
|
"eval_steps_per_second": 163.574,
|
|
"step": 24000
|
|
}
|
|
],
|
|
"logging_steps": 5,
|
|
"max_steps": 89030,
|
|
"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": 8.4070431631872e+16,
|
|
"train_batch_size": 16,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|