6046 lines
164 KiB
JSON
6046 lines
164 KiB
JSON
{
|
|
"best_global_step": null,
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 0.3369461447745269,
|
|
"eval_steps": 3000,
|
|
"global_step": 3000,
|
|
"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
|
|
}
|
|
],
|
|
"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": 1.0538862999552e+16,
|
|
"train_batch_size": 16,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|