6046 lines
164 KiB
JSON
6046 lines
164 KiB
JSON
|
{
|
||
|
|
"best_global_step": null,
|
||
|
|
"best_metric": null,
|
||
|
|
"best_model_checkpoint": null,
|
||
|
|
"epoch": 0.27213352685050796,
|
||
|
|
"eval_steps": 3000,
|
||
|
|
"global_step": 3000,
|
||
|
|
"is_hyper_param_search": false,
|
||
|
|
"is_local_process_zero": true,
|
||
|
|
"is_world_process_zero": true,
|
||
|
|
"log_history": [
|
||
|
|
{
|
||
|
|
"entropy": 10.69201955795288,
|
||
|
|
"epoch": 0.00045355587808418,
|
||
|
|
"grad_norm": 14.125,
|
||
|
|
"learning_rate": 2e-06,
|
||
|
|
"loss": 10.8421,
|
||
|
|
"mean_token_accuracy": 0.0,
|
||
|
|
"num_tokens": 10827.0,
|
||
|
|
"step": 5
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.691895008087158,
|
||
|
|
"epoch": 0.00090711175616836,
|
||
|
|
"grad_norm": 13.0,
|
||
|
|
"learning_rate": 4.5e-06,
|
||
|
|
"loss": 10.7626,
|
||
|
|
"mean_token_accuracy": 0.0,
|
||
|
|
"num_tokens": 21025.0,
|
||
|
|
"step": 10
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.690971279144287,
|
||
|
|
"epoch": 0.00136066763425254,
|
||
|
|
"grad_norm": 9.875,
|
||
|
|
"learning_rate": 7e-06,
|
||
|
|
"loss": 10.5141,
|
||
|
|
"mean_token_accuracy": 0.02440520448144525,
|
||
|
|
"num_tokens": 31678.0,
|
||
|
|
"step": 15
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.678609657287598,
|
||
|
|
"epoch": 0.00181422351233672,
|
||
|
|
"grad_norm": 6.3125,
|
||
|
|
"learning_rate": 9.5e-06,
|
||
|
|
"loss": 10.1495,
|
||
|
|
"mean_token_accuracy": 0.04602932706475258,
|
||
|
|
"num_tokens": 41025.0,
|
||
|
|
"step": 20
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.615153217315674,
|
||
|
|
"epoch": 0.0022677793904208998,
|
||
|
|
"grad_norm": 4.25,
|
||
|
|
"learning_rate": 1.2e-05,
|
||
|
|
"loss": 9.9137,
|
||
|
|
"mean_token_accuracy": 0.043584797717630866,
|
||
|
|
"num_tokens": 51270.0,
|
||
|
|
"step": 25
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.595486927032471,
|
||
|
|
"epoch": 0.00272133526850508,
|
||
|
|
"grad_norm": 3.3125,
|
||
|
|
"learning_rate": 1.4500000000000002e-05,
|
||
|
|
"loss": 9.7488,
|
||
|
|
"mean_token_accuracy": 0.04369584359228611,
|
||
|
|
"num_tokens": 62142.0,
|
||
|
|
"step": 30
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.605365085601807,
|
||
|
|
"epoch": 0.00317489114658926,
|
||
|
|
"grad_norm": 2.890625,
|
||
|
|
"learning_rate": 1.7000000000000003e-05,
|
||
|
|
"loss": 9.6708,
|
||
|
|
"mean_token_accuracy": 0.0410692248493433,
|
||
|
|
"num_tokens": 72709.0,
|
||
|
|
"step": 35
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.59789743423462,
|
||
|
|
"epoch": 0.00362844702467344,
|
||
|
|
"grad_norm": 2.609375,
|
||
|
|
"learning_rate": 1.95e-05,
|
||
|
|
"loss": 9.6037,
|
||
|
|
"mean_token_accuracy": 0.042245643213391304,
|
||
|
|
"num_tokens": 82313.0,
|
||
|
|
"step": 40
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.562069129943847,
|
||
|
|
"epoch": 0.00408200290275762,
|
||
|
|
"grad_norm": 2.859375,
|
||
|
|
"learning_rate": 2.2e-05,
|
||
|
|
"loss": 9.5375,
|
||
|
|
"mean_token_accuracy": 0.047857620567083356,
|
||
|
|
"num_tokens": 92450.0,
|
||
|
|
"step": 45
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.572824478149414,
|
||
|
|
"epoch": 0.0045355587808417995,
|
||
|
|
"grad_norm": 2.5,
|
||
|
|
"learning_rate": 2.4500000000000003e-05,
|
||
|
|
"loss": 9.5533,
|
||
|
|
"mean_token_accuracy": 0.04238316640257835,
|
||
|
|
"num_tokens": 103978.0,
|
||
|
|
"step": 50
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.59686508178711,
|
||
|
|
"epoch": 0.00498911465892598,
|
||
|
|
"grad_norm": 2.28125,
|
||
|
|
"learning_rate": 2.7e-05,
|
||
|
|
"loss": 9.451,
|
||
|
|
"mean_token_accuracy": 0.04611069448292256,
|
||
|
|
"num_tokens": 114134.0,
|
||
|
|
"step": 55
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.546150016784669,
|
||
|
|
"epoch": 0.00544267053701016,
|
||
|
|
"grad_norm": 2.40625,
|
||
|
|
"learning_rate": 2.95e-05,
|
||
|
|
"loss": 9.4197,
|
||
|
|
"mean_token_accuracy": 0.049464210495352746,
|
||
|
|
"num_tokens": 125037.0,
|
||
|
|
"step": 60
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.460656833648681,
|
||
|
|
"epoch": 0.00589622641509434,
|
||
|
|
"grad_norm": 2.40625,
|
||
|
|
"learning_rate": 3.2e-05,
|
||
|
|
"loss": 9.2345,
|
||
|
|
"mean_token_accuracy": 0.06379429697990417,
|
||
|
|
"num_tokens": 134721.0,
|
||
|
|
"step": 65
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.382928371429443,
|
||
|
|
"epoch": 0.00634978229317852,
|
||
|
|
"grad_norm": 2.546875,
|
||
|
|
"learning_rate": 3.4500000000000005e-05,
|
||
|
|
"loss": 9.143,
|
||
|
|
"mean_token_accuracy": 0.06433153599500656,
|
||
|
|
"num_tokens": 144448.0,
|
||
|
|
"step": 70
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.468272972106934,
|
||
|
|
"epoch": 0.006803338171262699,
|
||
|
|
"grad_norm": 2.40625,
|
||
|
|
"learning_rate": 3.7e-05,
|
||
|
|
"loss": 9.0501,
|
||
|
|
"mean_token_accuracy": 0.0702673528343439,
|
||
|
|
"num_tokens": 154343.0,
|
||
|
|
"step": 75
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.42321710586548,
|
||
|
|
"epoch": 0.00725689404934688,
|
||
|
|
"grad_norm": 2.359375,
|
||
|
|
"learning_rate": 3.95e-05,
|
||
|
|
"loss": 9.0122,
|
||
|
|
"mean_token_accuracy": 0.07085253149271012,
|
||
|
|
"num_tokens": 165650.0,
|
||
|
|
"step": 80
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.375396060943604,
|
||
|
|
"epoch": 0.007710449927431059,
|
||
|
|
"grad_norm": 2.21875,
|
||
|
|
"learning_rate": 4.2000000000000004e-05,
|
||
|
|
"loss": 9.0095,
|
||
|
|
"mean_token_accuracy": 0.06769064106047154,
|
||
|
|
"num_tokens": 177098.0,
|
||
|
|
"step": 85
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.209734153747558,
|
||
|
|
"epoch": 0.00816400580551524,
|
||
|
|
"grad_norm": 2.46875,
|
||
|
|
"learning_rate": 4.45e-05,
|
||
|
|
"loss": 8.7346,
|
||
|
|
"mean_token_accuracy": 0.08102216497063637,
|
||
|
|
"num_tokens": 187903.0,
|
||
|
|
"step": 90
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.184309768676759,
|
||
|
|
"epoch": 0.00861756168359942,
|
||
|
|
"grad_norm": 2.9375,
|
||
|
|
"learning_rate": 4.7000000000000004e-05,
|
||
|
|
"loss": 8.6625,
|
||
|
|
"mean_token_accuracy": 0.07625751569867134,
|
||
|
|
"num_tokens": 198077.0,
|
||
|
|
"step": 95
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.164143085479736,
|
||
|
|
"epoch": 0.009071117561683599,
|
||
|
|
"grad_norm": 2.0625,
|
||
|
|
"learning_rate": 4.9500000000000004e-05,
|
||
|
|
"loss": 8.6488,
|
||
|
|
"mean_token_accuracy": 0.0765529602766037,
|
||
|
|
"num_tokens": 208641.0,
|
||
|
|
"step": 100
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.11404504776001,
|
||
|
|
"epoch": 0.009524673439767779,
|
||
|
|
"grad_norm": 2.21875,
|
||
|
|
"learning_rate": 5.2e-05,
|
||
|
|
"loss": 8.4459,
|
||
|
|
"mean_token_accuracy": 0.07904929965734482,
|
||
|
|
"num_tokens": 218398.0,
|
||
|
|
"step": 105
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.020095443725586,
|
||
|
|
"epoch": 0.00997822931785196,
|
||
|
|
"grad_norm": 1.796875,
|
||
|
|
"learning_rate": 5.45e-05,
|
||
|
|
"loss": 8.3096,
|
||
|
|
"mean_token_accuracy": 0.08072945550084114,
|
||
|
|
"num_tokens": 229059.0,
|
||
|
|
"step": 110
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 9.92689781188965,
|
||
|
|
"epoch": 0.01043178519593614,
|
||
|
|
"grad_norm": 1.6796875,
|
||
|
|
"learning_rate": 5.7e-05,
|
||
|
|
"loss": 8.2562,
|
||
|
|
"mean_token_accuracy": 0.07845577970147133,
|
||
|
|
"num_tokens": 239775.0,
|
||
|
|
"step": 115
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 9.88659610748291,
|
||
|
|
"epoch": 0.01088534107402032,
|
||
|
|
"grad_norm": 1.90625,
|
||
|
|
"learning_rate": 5.9499999999999996e-05,
|
||
|
|
"loss": 8.0783,
|
||
|
|
"mean_token_accuracy": 0.08167890310287476,
|
||
|
|
"num_tokens": 249954.0,
|
||
|
|
"step": 120
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 9.705071830749512,
|
||
|
|
"epoch": 0.011338896952104499,
|
||
|
|
"grad_norm": 1.6875,
|
||
|
|
"learning_rate": 6.2e-05,
|
||
|
|
"loss": 7.9982,
|
||
|
|
"mean_token_accuracy": 0.08171927258372307,
|
||
|
|
"num_tokens": 260056.0,
|
||
|
|
"step": 125
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 9.503845977783204,
|
||
|
|
"epoch": 0.01179245283018868,
|
||
|
|
"grad_norm": 1.7421875,
|
||
|
|
"learning_rate": 6.450000000000001e-05,
|
||
|
|
"loss": 7.8979,
|
||
|
|
"mean_token_accuracy": 0.08274013251066208,
|
||
|
|
"num_tokens": 269904.0,
|
||
|
|
"step": 130
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 9.399583435058593,
|
||
|
|
"epoch": 0.01224600870827286,
|
||
|
|
"grad_norm": 1.640625,
|
||
|
|
"learning_rate": 6.7e-05,
|
||
|
|
"loss": 7.8002,
|
||
|
|
"mean_token_accuracy": 0.08209368959069252,
|
||
|
|
"num_tokens": 280900.0,
|
||
|
|
"step": 135
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 9.210491371154784,
|
||
|
|
"epoch": 0.01269956458635704,
|
||
|
|
"grad_norm": 1.84375,
|
||
|
|
"learning_rate": 6.950000000000001e-05,
|
||
|
|
"loss": 7.7037,
|
||
|
|
"mean_token_accuracy": 0.08104285597801208,
|
||
|
|
"num_tokens": 290844.0,
|
||
|
|
"step": 140
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.886974906921386,
|
||
|
|
"epoch": 0.013153120464441219,
|
||
|
|
"grad_norm": 1.203125,
|
||
|
|
"learning_rate": 7.2e-05,
|
||
|
|
"loss": 7.6102,
|
||
|
|
"mean_token_accuracy": 0.08451902270317077,
|
||
|
|
"num_tokens": 301345.0,
|
||
|
|
"step": 145
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.810495853424072,
|
||
|
|
"epoch": 0.013606676342525399,
|
||
|
|
"grad_norm": 1.2109375,
|
||
|
|
"learning_rate": 7.45e-05,
|
||
|
|
"loss": 7.5207,
|
||
|
|
"mean_token_accuracy": 0.08492689803242684,
|
||
|
|
"num_tokens": 312681.0,
|
||
|
|
"step": 150
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.537842845916748,
|
||
|
|
"epoch": 0.01406023222060958,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 7.7e-05,
|
||
|
|
"loss": 7.4392,
|
||
|
|
"mean_token_accuracy": 0.08759672790765763,
|
||
|
|
"num_tokens": 323492.0,
|
||
|
|
"step": 155
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.368613147735596,
|
||
|
|
"epoch": 0.01451378809869376,
|
||
|
|
"grad_norm": 1.4296875,
|
||
|
|
"learning_rate": 7.950000000000001e-05,
|
||
|
|
"loss": 7.4411,
|
||
|
|
"mean_token_accuracy": 0.08510910198092461,
|
||
|
|
"num_tokens": 334521.0,
|
||
|
|
"step": 160
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.248584079742432,
|
||
|
|
"epoch": 0.014967343976777939,
|
||
|
|
"grad_norm": 1.1953125,
|
||
|
|
"learning_rate": 8.2e-05,
|
||
|
|
"loss": 7.4246,
|
||
|
|
"mean_token_accuracy": 0.08887577280402184,
|
||
|
|
"num_tokens": 345468.0,
|
||
|
|
"step": 165
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.11111536026001,
|
||
|
|
"epoch": 0.015420899854862119,
|
||
|
|
"grad_norm": 1.4375,
|
||
|
|
"learning_rate": 8.450000000000001e-05,
|
||
|
|
"loss": 7.3297,
|
||
|
|
"mean_token_accuracy": 0.0877467267215252,
|
||
|
|
"num_tokens": 355911.0,
|
||
|
|
"step": 170
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.027539014816284,
|
||
|
|
"epoch": 0.0158744557329463,
|
||
|
|
"grad_norm": 1.25,
|
||
|
|
"learning_rate": 8.7e-05,
|
||
|
|
"loss": 7.3504,
|
||
|
|
"mean_token_accuracy": 0.08467918261885643,
|
||
|
|
"num_tokens": 367537.0,
|
||
|
|
"step": 175
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.06540780067444,
|
||
|
|
"epoch": 0.01632801161103048,
|
||
|
|
"grad_norm": 1.3984375,
|
||
|
|
"learning_rate": 8.95e-05,
|
||
|
|
"loss": 7.4771,
|
||
|
|
"mean_token_accuracy": 0.0847482830286026,
|
||
|
|
"num_tokens": 377918.0,
|
||
|
|
"step": 180
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.908505392074585,
|
||
|
|
"epoch": 0.01678156748911466,
|
||
|
|
"grad_norm": 1.3125,
|
||
|
|
"learning_rate": 9.2e-05,
|
||
|
|
"loss": 7.3165,
|
||
|
|
"mean_token_accuracy": 0.08902316763997078,
|
||
|
|
"num_tokens": 388461.0,
|
||
|
|
"step": 185
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.000589084625243,
|
||
|
|
"epoch": 0.01723512336719884,
|
||
|
|
"grad_norm": 1.3125,
|
||
|
|
"learning_rate": 9.45e-05,
|
||
|
|
"loss": 7.2895,
|
||
|
|
"mean_token_accuracy": 0.08787789791822434,
|
||
|
|
"num_tokens": 399771.0,
|
||
|
|
"step": 190
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.731726121902466,
|
||
|
|
"epoch": 0.01768867924528302,
|
||
|
|
"grad_norm": 1.234375,
|
||
|
|
"learning_rate": 9.7e-05,
|
||
|
|
"loss": 7.1673,
|
||
|
|
"mean_token_accuracy": 0.08963026329874993,
|
||
|
|
"num_tokens": 410254.0,
|
||
|
|
"step": 195
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.811504650115967,
|
||
|
|
"epoch": 0.018142235123367198,
|
||
|
|
"grad_norm": 1.390625,
|
||
|
|
"learning_rate": 9.95e-05,
|
||
|
|
"loss": 7.1894,
|
||
|
|
"mean_token_accuracy": 0.08560735136270523,
|
||
|
|
"num_tokens": 419792.0,
|
||
|
|
"step": 200
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.708149337768555,
|
||
|
|
"epoch": 0.018595791001451378,
|
||
|
|
"grad_norm": 1.46875,
|
||
|
|
"learning_rate": 0.000102,
|
||
|
|
"loss": 7.1962,
|
||
|
|
"mean_token_accuracy": 0.09234726577997207,
|
||
|
|
"num_tokens": 429264.0,
|
||
|
|
"step": 205
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.65235538482666,
|
||
|
|
"epoch": 0.019049346879535557,
|
||
|
|
"grad_norm": 1.4375,
|
||
|
|
"learning_rate": 0.00010449999999999999,
|
||
|
|
"loss": 7.1416,
|
||
|
|
"mean_token_accuracy": 0.09288287535309792,
|
||
|
|
"num_tokens": 439624.0,
|
||
|
|
"step": 210
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.664721393585205,
|
||
|
|
"epoch": 0.01950290275761974,
|
||
|
|
"grad_norm": 1.2578125,
|
||
|
|
"learning_rate": 0.000107,
|
||
|
|
"loss": 7.1224,
|
||
|
|
"mean_token_accuracy": 0.0913820892572403,
|
||
|
|
"num_tokens": 449556.0,
|
||
|
|
"step": 215
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.666817283630371,
|
||
|
|
"epoch": 0.01995645863570392,
|
||
|
|
"grad_norm": 1.53125,
|
||
|
|
"learning_rate": 0.0001095,
|
||
|
|
"loss": 7.1527,
|
||
|
|
"mean_token_accuracy": 0.09391891658306122,
|
||
|
|
"num_tokens": 460243.0,
|
||
|
|
"step": 220
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.6871044635772705,
|
||
|
|
"epoch": 0.0204100145137881,
|
||
|
|
"grad_norm": 1.3046875,
|
||
|
|
"learning_rate": 0.000112,
|
||
|
|
"loss": 7.193,
|
||
|
|
"mean_token_accuracy": 0.08998195976018905,
|
||
|
|
"num_tokens": 469767.0,
|
||
|
|
"step": 225
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.621262836456299,
|
||
|
|
"epoch": 0.02086357039187228,
|
||
|
|
"grad_norm": 1.3125,
|
||
|
|
"learning_rate": 0.0001145,
|
||
|
|
"loss": 7.1106,
|
||
|
|
"mean_token_accuracy": 0.09542692303657532,
|
||
|
|
"num_tokens": 480329.0,
|
||
|
|
"step": 230
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.601617050170899,
|
||
|
|
"epoch": 0.02131712626995646,
|
||
|
|
"grad_norm": 1.28125,
|
||
|
|
"learning_rate": 0.00011700000000000001,
|
||
|
|
"loss": 7.0818,
|
||
|
|
"mean_token_accuracy": 0.08891230374574662,
|
||
|
|
"num_tokens": 490096.0,
|
||
|
|
"step": 235
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.60865626335144,
|
||
|
|
"epoch": 0.02177068214804064,
|
||
|
|
"grad_norm": 1.3359375,
|
||
|
|
"learning_rate": 0.00011949999999999999,
|
||
|
|
"loss": 7.1143,
|
||
|
|
"mean_token_accuracy": 0.08756190165877342,
|
||
|
|
"num_tokens": 501231.0,
|
||
|
|
"step": 240
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.543486261367798,
|
||
|
|
"epoch": 0.022224238026124818,
|
||
|
|
"grad_norm": 1.6640625,
|
||
|
|
"learning_rate": 0.000122,
|
||
|
|
"loss": 7.0258,
|
||
|
|
"mean_token_accuracy": 0.09758798629045487,
|
||
|
|
"num_tokens": 510722.0,
|
||
|
|
"step": 245
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.489023685455322,
|
||
|
|
"epoch": 0.022677793904208998,
|
||
|
|
"grad_norm": 1.1796875,
|
||
|
|
"learning_rate": 0.0001245,
|
||
|
|
"loss": 7.0792,
|
||
|
|
"mean_token_accuracy": 0.09397116005420685,
|
||
|
|
"num_tokens": 521452.0,
|
||
|
|
"step": 250
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.515778923034668,
|
||
|
|
"epoch": 0.023131349782293177,
|
||
|
|
"grad_norm": 1.34375,
|
||
|
|
"learning_rate": 0.000127,
|
||
|
|
"loss": 7.0911,
|
||
|
|
"mean_token_accuracy": 0.09408443942666053,
|
||
|
|
"num_tokens": 532397.0,
|
||
|
|
"step": 255
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.523461151123047,
|
||
|
|
"epoch": 0.02358490566037736,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.0001295,
|
||
|
|
"loss": 7.0524,
|
||
|
|
"mean_token_accuracy": 0.09337728172540664,
|
||
|
|
"num_tokens": 542271.0,
|
||
|
|
"step": 260
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.498798656463623,
|
||
|
|
"epoch": 0.02403846153846154,
|
||
|
|
"grad_norm": 1.296875,
|
||
|
|
"learning_rate": 0.000132,
|
||
|
|
"loss": 7.0403,
|
||
|
|
"mean_token_accuracy": 0.09828322902321815,
|
||
|
|
"num_tokens": 552411.0,
|
||
|
|
"step": 265
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.433657121658325,
|
||
|
|
"epoch": 0.02449201741654572,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.00013450000000000002,
|
||
|
|
"loss": 7.0246,
|
||
|
|
"mean_token_accuracy": 0.09725753068923951,
|
||
|
|
"num_tokens": 561518.0,
|
||
|
|
"step": 270
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.546285247802734,
|
||
|
|
"epoch": 0.0249455732946299,
|
||
|
|
"grad_norm": 1.265625,
|
||
|
|
"learning_rate": 0.00013700000000000002,
|
||
|
|
"loss": 7.0652,
|
||
|
|
"mean_token_accuracy": 0.09419438466429711,
|
||
|
|
"num_tokens": 571361.0,
|
||
|
|
"step": 275
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.3379639148712155,
|
||
|
|
"epoch": 0.02539912917271408,
|
||
|
|
"grad_norm": 1.3515625,
|
||
|
|
"learning_rate": 0.0001395,
|
||
|
|
"loss": 6.9636,
|
||
|
|
"mean_token_accuracy": 0.10313116908073425,
|
||
|
|
"num_tokens": 580926.0,
|
||
|
|
"step": 280
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.439048814773559,
|
||
|
|
"epoch": 0.025852685050798258,
|
||
|
|
"grad_norm": 1.1875,
|
||
|
|
"learning_rate": 0.00014199999999999998,
|
||
|
|
"loss": 7.0476,
|
||
|
|
"mean_token_accuracy": 0.09056098833680153,
|
||
|
|
"num_tokens": 592282.0,
|
||
|
|
"step": 285
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.535349416732788,
|
||
|
|
"epoch": 0.026306240928882438,
|
||
|
|
"grad_norm": 1.2578125,
|
||
|
|
"learning_rate": 0.0001445,
|
||
|
|
"loss": 7.0665,
|
||
|
|
"mean_token_accuracy": 0.09440166875720024,
|
||
|
|
"num_tokens": 602767.0,
|
||
|
|
"step": 290
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.4240789890289305,
|
||
|
|
"epoch": 0.026759796806966617,
|
||
|
|
"grad_norm": 1.2109375,
|
||
|
|
"learning_rate": 0.000147,
|
||
|
|
"loss": 6.9896,
|
||
|
|
"mean_token_accuracy": 0.0924597330391407,
|
||
|
|
"num_tokens": 612763.0,
|
||
|
|
"step": 295
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.324904584884644,
|
||
|
|
"epoch": 0.027213352685050797,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0001495,
|
||
|
|
"loss": 6.9363,
|
||
|
|
"mean_token_accuracy": 0.09375968724489211,
|
||
|
|
"num_tokens": 622796.0,
|
||
|
|
"step": 300
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.385919713973999,
|
||
|
|
"epoch": 0.027666908563134977,
|
||
|
|
"grad_norm": 1.3203125,
|
||
|
|
"learning_rate": 0.000152,
|
||
|
|
"loss": 6.9192,
|
||
|
|
"mean_token_accuracy": 0.09953035265207291,
|
||
|
|
"num_tokens": 633136.0,
|
||
|
|
"step": 305
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.27361741065979,
|
||
|
|
"epoch": 0.02812046444121916,
|
||
|
|
"grad_norm": 1.1875,
|
||
|
|
"learning_rate": 0.00015450000000000001,
|
||
|
|
"loss": 6.9231,
|
||
|
|
"mean_token_accuracy": 0.10048090890049935,
|
||
|
|
"num_tokens": 643347.0,
|
||
|
|
"step": 310
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.3609613418579105,
|
||
|
|
"epoch": 0.02857402031930334,
|
||
|
|
"grad_norm": 1.28125,
|
||
|
|
"learning_rate": 0.000157,
|
||
|
|
"loss": 6.9037,
|
||
|
|
"mean_token_accuracy": 0.10072512328624725,
|
||
|
|
"num_tokens": 653096.0,
|
||
|
|
"step": 315
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.219988059997559,
|
||
|
|
"epoch": 0.02902757619738752,
|
||
|
|
"grad_norm": 1.2421875,
|
||
|
|
"learning_rate": 0.0001595,
|
||
|
|
"loss": 6.9318,
|
||
|
|
"mean_token_accuracy": 0.09513700902462005,
|
||
|
|
"num_tokens": 663557.0,
|
||
|
|
"step": 320
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.375028610229492,
|
||
|
|
"epoch": 0.0294811320754717,
|
||
|
|
"grad_norm": 1.4609375,
|
||
|
|
"learning_rate": 0.000162,
|
||
|
|
"loss": 7.0052,
|
||
|
|
"mean_token_accuracy": 0.0983717530965805,
|
||
|
|
"num_tokens": 674395.0,
|
||
|
|
"step": 325
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.270230674743653,
|
||
|
|
"epoch": 0.029934687953555878,
|
||
|
|
"grad_norm": 1.265625,
|
||
|
|
"learning_rate": 0.00016450000000000001,
|
||
|
|
"loss": 6.9129,
|
||
|
|
"mean_token_accuracy": 0.10161509737372398,
|
||
|
|
"num_tokens": 684776.0,
|
||
|
|
"step": 330
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.269373607635498,
|
||
|
|
"epoch": 0.030388243831640058,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.00016700000000000002,
|
||
|
|
"loss": 6.8875,
|
||
|
|
"mean_token_accuracy": 0.0997242234647274,
|
||
|
|
"num_tokens": 694886.0,
|
||
|
|
"step": 335
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.338870811462402,
|
||
|
|
"epoch": 0.030841799709724237,
|
||
|
|
"grad_norm": 1.1875,
|
||
|
|
"learning_rate": 0.00016950000000000003,
|
||
|
|
"loss": 6.9575,
|
||
|
|
"mean_token_accuracy": 0.09762076139450074,
|
||
|
|
"num_tokens": 705426.0,
|
||
|
|
"step": 340
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.253270244598388,
|
||
|
|
"epoch": 0.03129535558780842,
|
||
|
|
"grad_norm": 1.3203125,
|
||
|
|
"learning_rate": 0.00017199999999999998,
|
||
|
|
"loss": 6.9498,
|
||
|
|
"mean_token_accuracy": 0.09457632303237914,
|
||
|
|
"num_tokens": 716271.0,
|
||
|
|
"step": 345
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.2550302028656,
|
||
|
|
"epoch": 0.0317489114658926,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.00017449999999999999,
|
||
|
|
"loss": 6.9409,
|
||
|
|
"mean_token_accuracy": 0.09868695959448814,
|
||
|
|
"num_tokens": 726875.0,
|
||
|
|
"step": 350
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.2600914478302006,
|
||
|
|
"epoch": 0.032202467343976776,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.000177,
|
||
|
|
"loss": 6.8738,
|
||
|
|
"mean_token_accuracy": 0.09764649495482444,
|
||
|
|
"num_tokens": 737825.0,
|
||
|
|
"step": 355
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.240714120864868,
|
||
|
|
"epoch": 0.03265602322206096,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.0001795,
|
||
|
|
"loss": 6.8413,
|
||
|
|
"mean_token_accuracy": 0.10239819139242172,
|
||
|
|
"num_tokens": 747424.0,
|
||
|
|
"step": 360
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.195548105239868,
|
||
|
|
"epoch": 0.033109579100145135,
|
||
|
|
"grad_norm": 1.1640625,
|
||
|
|
"learning_rate": 0.000182,
|
||
|
|
"loss": 6.854,
|
||
|
|
"mean_token_accuracy": 0.10043720304965972,
|
||
|
|
"num_tokens": 757649.0,
|
||
|
|
"step": 365
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.267161417007446,
|
||
|
|
"epoch": 0.03356313497822932,
|
||
|
|
"grad_norm": 1.1953125,
|
||
|
|
"learning_rate": 0.0001845,
|
||
|
|
"loss": 6.8436,
|
||
|
|
"mean_token_accuracy": 0.09980886504054069,
|
||
|
|
"num_tokens": 768556.0,
|
||
|
|
"step": 370
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.0987019538879395,
|
||
|
|
"epoch": 0.034016690856313495,
|
||
|
|
"grad_norm": 1.234375,
|
||
|
|
"learning_rate": 0.000187,
|
||
|
|
"loss": 6.8373,
|
||
|
|
"mean_token_accuracy": 0.10219831764698029,
|
||
|
|
"num_tokens": 778331.0,
|
||
|
|
"step": 375
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.19783296585083,
|
||
|
|
"epoch": 0.03447024673439768,
|
||
|
|
"grad_norm": 1.265625,
|
||
|
|
"learning_rate": 0.0001895,
|
||
|
|
"loss": 6.8352,
|
||
|
|
"mean_token_accuracy": 0.09996062368154526,
|
||
|
|
"num_tokens": 788065.0,
|
||
|
|
"step": 380
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.185236835479737,
|
||
|
|
"epoch": 0.03492380261248186,
|
||
|
|
"grad_norm": 1.2265625,
|
||
|
|
"learning_rate": 0.000192,
|
||
|
|
"loss": 6.8695,
|
||
|
|
"mean_token_accuracy": 0.10359352231025695,
|
||
|
|
"num_tokens": 798912.0,
|
||
|
|
"step": 385
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.1850183486938475,
|
||
|
|
"epoch": 0.03537735849056604,
|
||
|
|
"grad_norm": 1.15625,
|
||
|
|
"learning_rate": 0.0001945,
|
||
|
|
"loss": 6.8211,
|
||
|
|
"mean_token_accuracy": 0.10563454255461693,
|
||
|
|
"num_tokens": 809580.0,
|
||
|
|
"step": 390
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.208040618896485,
|
||
|
|
"epoch": 0.03583091436865022,
|
||
|
|
"grad_norm": 1.15625,
|
||
|
|
"learning_rate": 0.00019700000000000002,
|
||
|
|
"loss": 6.8958,
|
||
|
|
"mean_token_accuracy": 0.10004983395338059,
|
||
|
|
"num_tokens": 820207.0,
|
||
|
|
"step": 395
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.000587606430054,
|
||
|
|
"epoch": 0.036284470246734396,
|
||
|
|
"grad_norm": 1.2421875,
|
||
|
|
"learning_rate": 0.00019950000000000002,
|
||
|
|
"loss": 6.7196,
|
||
|
|
"mean_token_accuracy": 0.09804629981517791,
|
||
|
|
"num_tokens": 831038.0,
|
||
|
|
"step": 400
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.166787433624267,
|
||
|
|
"epoch": 0.03673802612481858,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.000202,
|
||
|
|
"loss": 6.8141,
|
||
|
|
"mean_token_accuracy": 0.10281971544027328,
|
||
|
|
"num_tokens": 842144.0,
|
||
|
|
"step": 405
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.101940298080445,
|
||
|
|
"epoch": 0.037191582002902755,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.00020449999999999998,
|
||
|
|
"loss": 6.8197,
|
||
|
|
"mean_token_accuracy": 0.10505499988794327,
|
||
|
|
"num_tokens": 851315.0,
|
||
|
|
"step": 410
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.090035247802734,
|
||
|
|
"epoch": 0.03764513788098694,
|
||
|
|
"grad_norm": 1.265625,
|
||
|
|
"learning_rate": 0.000207,
|
||
|
|
"loss": 6.8306,
|
||
|
|
"mean_token_accuracy": 0.10175477415323257,
|
||
|
|
"num_tokens": 861233.0,
|
||
|
|
"step": 415
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.051157379150391,
|
||
|
|
"epoch": 0.038098693759071114,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 0.0002095,
|
||
|
|
"loss": 6.8096,
|
||
|
|
"mean_token_accuracy": 0.0993909016251564,
|
||
|
|
"num_tokens": 871131.0,
|
||
|
|
"step": 420
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.143013191223145,
|
||
|
|
"epoch": 0.0385522496371553,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.000212,
|
||
|
|
"loss": 6.7764,
|
||
|
|
"mean_token_accuracy": 0.09792252779006957,
|
||
|
|
"num_tokens": 882195.0,
|
||
|
|
"step": 425
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.111673784255982,
|
||
|
|
"epoch": 0.03900580551523948,
|
||
|
|
"grad_norm": 1.203125,
|
||
|
|
"learning_rate": 0.0002145,
|
||
|
|
"loss": 6.761,
|
||
|
|
"mean_token_accuracy": 0.10355701595544815,
|
||
|
|
"num_tokens": 891806.0,
|
||
|
|
"step": 430
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.103079462051392,
|
||
|
|
"epoch": 0.03945936139332366,
|
||
|
|
"grad_norm": 1.1640625,
|
||
|
|
"learning_rate": 0.00021700000000000002,
|
||
|
|
"loss": 6.8234,
|
||
|
|
"mean_token_accuracy": 0.09959669709205628,
|
||
|
|
"num_tokens": 901350.0,
|
||
|
|
"step": 435
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.085621690750122,
|
||
|
|
"epoch": 0.03991291727140784,
|
||
|
|
"grad_norm": 1.4296875,
|
||
|
|
"learning_rate": 0.0002195,
|
||
|
|
"loss": 6.7362,
|
||
|
|
"mean_token_accuracy": 0.09833786115050316,
|
||
|
|
"num_tokens": 912061.0,
|
||
|
|
"step": 440
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.99485411643982,
|
||
|
|
"epoch": 0.040366473149492016,
|
||
|
|
"grad_norm": 1.1640625,
|
||
|
|
"learning_rate": 0.000222,
|
||
|
|
"loss": 6.6882,
|
||
|
|
"mean_token_accuracy": 0.1011364847421646,
|
||
|
|
"num_tokens": 922220.0,
|
||
|
|
"step": 445
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.05831937789917,
|
||
|
|
"epoch": 0.0408200290275762,
|
||
|
|
"grad_norm": 1.1875,
|
||
|
|
"learning_rate": 0.0002245,
|
||
|
|
"loss": 6.7282,
|
||
|
|
"mean_token_accuracy": 0.10195261687040329,
|
||
|
|
"num_tokens": 932319.0,
|
||
|
|
"step": 450
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.9827405452728275,
|
||
|
|
"epoch": 0.041273584905660375,
|
||
|
|
"grad_norm": 1.2421875,
|
||
|
|
"learning_rate": 0.00022700000000000002,
|
||
|
|
"loss": 6.7504,
|
||
|
|
"mean_token_accuracy": 0.10525996536016465,
|
||
|
|
"num_tokens": 943254.0,
|
||
|
|
"step": 455
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.01410927772522,
|
||
|
|
"epoch": 0.04172714078374456,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.00022950000000000002,
|
||
|
|
"loss": 6.7792,
|
||
|
|
"mean_token_accuracy": 0.0980103112757206,
|
||
|
|
"num_tokens": 953921.0,
|
||
|
|
"step": 460
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.935913562774658,
|
||
|
|
"epoch": 0.042180696661828734,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.00023200000000000003,
|
||
|
|
"loss": 6.6898,
|
||
|
|
"mean_token_accuracy": 0.10519141629338265,
|
||
|
|
"num_tokens": 963832.0,
|
||
|
|
"step": 465
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.9887090682983395,
|
||
|
|
"epoch": 0.04263425253991292,
|
||
|
|
"grad_norm": 1.3671875,
|
||
|
|
"learning_rate": 0.00023449999999999998,
|
||
|
|
"loss": 6.7863,
|
||
|
|
"mean_token_accuracy": 0.0979742519557476,
|
||
|
|
"num_tokens": 974066.0,
|
||
|
|
"step": 470
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.043638467788696,
|
||
|
|
"epoch": 0.0430878084179971,
|
||
|
|
"grad_norm": 1.15625,
|
||
|
|
"learning_rate": 0.000237,
|
||
|
|
"loss": 6.7626,
|
||
|
|
"mean_token_accuracy": 0.10633939728140832,
|
||
|
|
"num_tokens": 984402.0,
|
||
|
|
"step": 475
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.972577047348023,
|
||
|
|
"epoch": 0.04354136429608128,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.0002395,
|
||
|
|
"loss": 6.6771,
|
||
|
|
"mean_token_accuracy": 0.10603873878717422,
|
||
|
|
"num_tokens": 993555.0,
|
||
|
|
"step": 480
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.969974994659424,
|
||
|
|
"epoch": 0.04399492017416546,
|
||
|
|
"grad_norm": 1.234375,
|
||
|
|
"learning_rate": 0.000242,
|
||
|
|
"loss": 6.6629,
|
||
|
|
"mean_token_accuracy": 0.11064062714576721,
|
||
|
|
"num_tokens": 1002920.0,
|
||
|
|
"step": 485
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.993032169342041,
|
||
|
|
"epoch": 0.044448476052249636,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.0002445,
|
||
|
|
"loss": 6.7527,
|
||
|
|
"mean_token_accuracy": 0.09811311662197113,
|
||
|
|
"num_tokens": 1013611.0,
|
||
|
|
"step": 490
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.870787668228149,
|
||
|
|
"epoch": 0.04490203193033382,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.000247,
|
||
|
|
"loss": 6.6381,
|
||
|
|
"mean_token_accuracy": 0.102886413782835,
|
||
|
|
"num_tokens": 1024121.0,
|
||
|
|
"step": 495
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.048051881790161,
|
||
|
|
"epoch": 0.045355587808417995,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.0002495,
|
||
|
|
"loss": 6.8934,
|
||
|
|
"mean_token_accuracy": 0.1061844177544117,
|
||
|
|
"num_tokens": 1033845.0,
|
||
|
|
"step": 500
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.991887521743775,
|
||
|
|
"epoch": 0.04580914368650218,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.000252,
|
||
|
|
"loss": 6.6783,
|
||
|
|
"mean_token_accuracy": 0.1054874338209629,
|
||
|
|
"num_tokens": 1044642.0,
|
||
|
|
"step": 505
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.883953094482422,
|
||
|
|
"epoch": 0.046262699564586354,
|
||
|
|
"grad_norm": 1.2890625,
|
||
|
|
"learning_rate": 0.0002545,
|
||
|
|
"loss": 6.7359,
|
||
|
|
"mean_token_accuracy": 0.10576739087700844,
|
||
|
|
"num_tokens": 1054728.0,
|
||
|
|
"step": 510
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.952514743804931,
|
||
|
|
"epoch": 0.04671625544267054,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.000257,
|
||
|
|
"loss": 6.6919,
|
||
|
|
"mean_token_accuracy": 0.09888017326593398,
|
||
|
|
"num_tokens": 1065743.0,
|
||
|
|
"step": 515
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.847628164291382,
|
||
|
|
"epoch": 0.04716981132075472,
|
||
|
|
"grad_norm": 1.1796875,
|
||
|
|
"learning_rate": 0.0002595,
|
||
|
|
"loss": 6.6143,
|
||
|
|
"mean_token_accuracy": 0.10563460439443588,
|
||
|
|
"num_tokens": 1076798.0,
|
||
|
|
"step": 520
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.913150882720947,
|
||
|
|
"epoch": 0.047623367198838897,
|
||
|
|
"grad_norm": 1.15625,
|
||
|
|
"learning_rate": 0.000262,
|
||
|
|
"loss": 6.7491,
|
||
|
|
"mean_token_accuracy": 0.09963728263974189,
|
||
|
|
"num_tokens": 1087445.0,
|
||
|
|
"step": 525
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.850391578674317,
|
||
|
|
"epoch": 0.04807692307692308,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.00026450000000000003,
|
||
|
|
"loss": 6.6457,
|
||
|
|
"mean_token_accuracy": 0.10645358338952064,
|
||
|
|
"num_tokens": 1098379.0,
|
||
|
|
"step": 530
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.9510291576385494,
|
||
|
|
"epoch": 0.048530478955007256,
|
||
|
|
"grad_norm": 1.21875,
|
||
|
|
"learning_rate": 0.00026700000000000004,
|
||
|
|
"loss": 6.7504,
|
||
|
|
"mean_token_accuracy": 0.10485646203160286,
|
||
|
|
"num_tokens": 1108016.0,
|
||
|
|
"step": 535
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.889407110214234,
|
||
|
|
"epoch": 0.04898403483309144,
|
||
|
|
"grad_norm": 1.3046875,
|
||
|
|
"learning_rate": 0.00026950000000000005,
|
||
|
|
"loss": 6.6183,
|
||
|
|
"mean_token_accuracy": 0.10373573526740074,
|
||
|
|
"num_tokens": 1117887.0,
|
||
|
|
"step": 540
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.825150203704834,
|
||
|
|
"epoch": 0.049437590711175615,
|
||
|
|
"grad_norm": 1.171875,
|
||
|
|
"learning_rate": 0.00027200000000000005,
|
||
|
|
"loss": 6.6096,
|
||
|
|
"mean_token_accuracy": 0.10104240402579308,
|
||
|
|
"num_tokens": 1128497.0,
|
||
|
|
"step": 545
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.80326771736145,
|
||
|
|
"epoch": 0.0498911465892598,
|
||
|
|
"grad_norm": 1.1953125,
|
||
|
|
"learning_rate": 0.0002745,
|
||
|
|
"loss": 6.6592,
|
||
|
|
"mean_token_accuracy": 0.10856908708810806,
|
||
|
|
"num_tokens": 1138168.0,
|
||
|
|
"step": 550
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.879168224334717,
|
||
|
|
"epoch": 0.050344702467343974,
|
||
|
|
"grad_norm": 1.2578125,
|
||
|
|
"learning_rate": 0.000277,
|
||
|
|
"loss": 6.6407,
|
||
|
|
"mean_token_accuracy": 0.10094325393438339,
|
||
|
|
"num_tokens": 1148357.0,
|
||
|
|
"step": 555
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.832116413116455,
|
||
|
|
"epoch": 0.05079825834542816,
|
||
|
|
"grad_norm": 1.1640625,
|
||
|
|
"learning_rate": 0.0002795,
|
||
|
|
"loss": 6.6591,
|
||
|
|
"mean_token_accuracy": 0.10421488359570504,
|
||
|
|
"num_tokens": 1159964.0,
|
||
|
|
"step": 560
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.893824195861816,
|
||
|
|
"epoch": 0.05125181422351233,
|
||
|
|
"grad_norm": 1.1875,
|
||
|
|
"learning_rate": 0.00028199999999999997,
|
||
|
|
"loss": 6.7137,
|
||
|
|
"mean_token_accuracy": 0.1055032454431057,
|
||
|
|
"num_tokens": 1170683.0,
|
||
|
|
"step": 565
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.914015007019043,
|
||
|
|
"epoch": 0.051705370101596516,
|
||
|
|
"grad_norm": 1.2734375,
|
||
|
|
"learning_rate": 0.0002845,
|
||
|
|
"loss": 6.6792,
|
||
|
|
"mean_token_accuracy": 0.10148620307445526,
|
||
|
|
"num_tokens": 1181680.0,
|
||
|
|
"step": 570
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.74883451461792,
|
||
|
|
"epoch": 0.0521589259796807,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.000287,
|
||
|
|
"loss": 6.5654,
|
||
|
|
"mean_token_accuracy": 0.10732218623161316,
|
||
|
|
"num_tokens": 1191619.0,
|
||
|
|
"step": 575
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.685351276397705,
|
||
|
|
"epoch": 0.052612481857764876,
|
||
|
|
"grad_norm": 1.203125,
|
||
|
|
"learning_rate": 0.0002895,
|
||
|
|
"loss": 6.5629,
|
||
|
|
"mean_token_accuracy": 0.10640141144394874,
|
||
|
|
"num_tokens": 1202264.0,
|
||
|
|
"step": 580
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.805472993850708,
|
||
|
|
"epoch": 0.05306603773584906,
|
||
|
|
"grad_norm": 1.1875,
|
||
|
|
"learning_rate": 0.000292,
|
||
|
|
"loss": 6.5815,
|
||
|
|
"mean_token_accuracy": 0.1027822844684124,
|
||
|
|
"num_tokens": 1212119.0,
|
||
|
|
"step": 585
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.801087665557861,
|
||
|
|
"epoch": 0.053519593613933235,
|
||
|
|
"grad_norm": 1.171875,
|
||
|
|
"learning_rate": 0.0002945,
|
||
|
|
"loss": 6.7049,
|
||
|
|
"mean_token_accuracy": 0.10856684222817421,
|
||
|
|
"num_tokens": 1222317.0,
|
||
|
|
"step": 590
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.853984594345093,
|
||
|
|
"epoch": 0.05397314949201742,
|
||
|
|
"grad_norm": 1.21875,
|
||
|
|
"learning_rate": 0.000297,
|
||
|
|
"loss": 6.6443,
|
||
|
|
"mean_token_accuracy": 0.1087227538228035,
|
||
|
|
"num_tokens": 1232914.0,
|
||
|
|
"step": 595
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.680654525756836,
|
||
|
|
"epoch": 0.054426705370101594,
|
||
|
|
"grad_norm": 0.98046875,
|
||
|
|
"learning_rate": 0.0002995,
|
||
|
|
"loss": 6.487,
|
||
|
|
"mean_token_accuracy": 0.11319171860814095,
|
||
|
|
"num_tokens": 1244214.0,
|
||
|
|
"step": 600
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.830823040008545,
|
||
|
|
"epoch": 0.05488026124818578,
|
||
|
|
"grad_norm": 1.265625,
|
||
|
|
"learning_rate": 0.000302,
|
||
|
|
"loss": 6.5837,
|
||
|
|
"mean_token_accuracy": 0.10821337848901749,
|
||
|
|
"num_tokens": 1254626.0,
|
||
|
|
"step": 605
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.7139935970306395,
|
||
|
|
"epoch": 0.05533381712626995,
|
||
|
|
"grad_norm": 1.265625,
|
||
|
|
"learning_rate": 0.0003045,
|
||
|
|
"loss": 6.6937,
|
||
|
|
"mean_token_accuracy": 0.10711480379104614,
|
||
|
|
"num_tokens": 1265461.0,
|
||
|
|
"step": 610
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.8157871723175045,
|
||
|
|
"epoch": 0.055787373004354136,
|
||
|
|
"grad_norm": 1.21875,
|
||
|
|
"learning_rate": 0.000307,
|
||
|
|
"loss": 6.5595,
|
||
|
|
"mean_token_accuracy": 0.1111778050661087,
|
||
|
|
"num_tokens": 1275810.0,
|
||
|
|
"step": 615
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.6582403659820555,
|
||
|
|
"epoch": 0.05624092888243832,
|
||
|
|
"grad_norm": 1.359375,
|
||
|
|
"learning_rate": 0.0003095,
|
||
|
|
"loss": 6.5723,
|
||
|
|
"mean_token_accuracy": 0.11056382060050965,
|
||
|
|
"num_tokens": 1285170.0,
|
||
|
|
"step": 620
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.752780246734619,
|
||
|
|
"epoch": 0.056694484760522496,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.000312,
|
||
|
|
"loss": 6.5104,
|
||
|
|
"mean_token_accuracy": 0.11242734342813492,
|
||
|
|
"num_tokens": 1295460.0,
|
||
|
|
"step": 625
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.783557653427124,
|
||
|
|
"epoch": 0.05714804063860668,
|
||
|
|
"grad_norm": 1.375,
|
||
|
|
"learning_rate": 0.0003145,
|
||
|
|
"loss": 6.647,
|
||
|
|
"mean_token_accuracy": 0.10393900722265244,
|
||
|
|
"num_tokens": 1306656.0,
|
||
|
|
"step": 630
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.771673727035522,
|
||
|
|
"epoch": 0.057601596516690855,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.000317,
|
||
|
|
"loss": 6.6099,
|
||
|
|
"mean_token_accuracy": 0.10909517779946327,
|
||
|
|
"num_tokens": 1318019.0,
|
||
|
|
"step": 635
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.627294826507568,
|
||
|
|
"epoch": 0.05805515239477504,
|
||
|
|
"grad_norm": 1.140625,
|
||
|
|
"learning_rate": 0.0003195,
|
||
|
|
"loss": 6.5314,
|
||
|
|
"mean_token_accuracy": 0.114180638641119,
|
||
|
|
"num_tokens": 1328120.0,
|
||
|
|
"step": 640
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.828495216369629,
|
||
|
|
"epoch": 0.058508708272859214,
|
||
|
|
"grad_norm": 1.15625,
|
||
|
|
"learning_rate": 0.000322,
|
||
|
|
"loss": 6.6283,
|
||
|
|
"mean_token_accuracy": 0.1077908605337143,
|
||
|
|
"num_tokens": 1338354.0,
|
||
|
|
"step": 645
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.780737257003784,
|
||
|
|
"epoch": 0.0589622641509434,
|
||
|
|
"grad_norm": 1.3515625,
|
||
|
|
"learning_rate": 0.00032450000000000003,
|
||
|
|
"loss": 6.6005,
|
||
|
|
"mean_token_accuracy": 0.10598717033863067,
|
||
|
|
"num_tokens": 1348666.0,
|
||
|
|
"step": 650
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.688767719268799,
|
||
|
|
"epoch": 0.05941582002902757,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.00032700000000000003,
|
||
|
|
"loss": 6.6481,
|
||
|
|
"mean_token_accuracy": 0.11127779558300972,
|
||
|
|
"num_tokens": 1359713.0,
|
||
|
|
"step": 655
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.6816778659820555,
|
||
|
|
"epoch": 0.059869375907111756,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.00032950000000000004,
|
||
|
|
"loss": 6.4972,
|
||
|
|
"mean_token_accuracy": 0.11233635172247887,
|
||
|
|
"num_tokens": 1369507.0,
|
||
|
|
"step": 660
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.753318500518799,
|
||
|
|
"epoch": 0.06032293178519594,
|
||
|
|
"grad_norm": 1.15625,
|
||
|
|
"learning_rate": 0.00033200000000000005,
|
||
|
|
"loss": 6.6613,
|
||
|
|
"mean_token_accuracy": 0.10458081513643265,
|
||
|
|
"num_tokens": 1380726.0,
|
||
|
|
"step": 665
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.791505956649781,
|
||
|
|
"epoch": 0.060776487663280115,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.00033450000000000005,
|
||
|
|
"loss": 6.5884,
|
||
|
|
"mean_token_accuracy": 0.1085951142013073,
|
||
|
|
"num_tokens": 1391423.0,
|
||
|
|
"step": 670
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.758508014678955,
|
||
|
|
"epoch": 0.0612300435413643,
|
||
|
|
"grad_norm": 1.2734375,
|
||
|
|
"learning_rate": 0.000337,
|
||
|
|
"loss": 6.5566,
|
||
|
|
"mean_token_accuracy": 0.1129811353981495,
|
||
|
|
"num_tokens": 1402492.0,
|
||
|
|
"step": 675
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.64742956161499,
|
||
|
|
"epoch": 0.061683599419448475,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0003395,
|
||
|
|
"loss": 6.6151,
|
||
|
|
"mean_token_accuracy": 0.11265368685126305,
|
||
|
|
"num_tokens": 1412497.0,
|
||
|
|
"step": 680
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.80935697555542,
|
||
|
|
"epoch": 0.06213715529753266,
|
||
|
|
"grad_norm": 1.203125,
|
||
|
|
"learning_rate": 0.000342,
|
||
|
|
"loss": 6.5751,
|
||
|
|
"mean_token_accuracy": 0.11512991040945053,
|
||
|
|
"num_tokens": 1423214.0,
|
||
|
|
"step": 685
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.651473712921143,
|
||
|
|
"epoch": 0.06259071117561683,
|
||
|
|
"grad_norm": 1.4140625,
|
||
|
|
"learning_rate": 0.00034449999999999997,
|
||
|
|
"loss": 6.5673,
|
||
|
|
"mean_token_accuracy": 0.1103017933666706,
|
||
|
|
"num_tokens": 1434044.0,
|
||
|
|
"step": 690
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.6841058254241945,
|
||
|
|
"epoch": 0.06304426705370102,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.000347,
|
||
|
|
"loss": 6.5303,
|
||
|
|
"mean_token_accuracy": 0.1138860672712326,
|
||
|
|
"num_tokens": 1444387.0,
|
||
|
|
"step": 695
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.592344141006469,
|
||
|
|
"epoch": 0.0634978229317852,
|
||
|
|
"grad_norm": 1.1640625,
|
||
|
|
"learning_rate": 0.0003495,
|
||
|
|
"loss": 6.4809,
|
||
|
|
"mean_token_accuracy": 0.10669072344899178,
|
||
|
|
"num_tokens": 1455157.0,
|
||
|
|
"step": 700
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.729357099533081,
|
||
|
|
"epoch": 0.06395137880986937,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.000352,
|
||
|
|
"loss": 6.595,
|
||
|
|
"mean_token_accuracy": 0.11270184963941574,
|
||
|
|
"num_tokens": 1466145.0,
|
||
|
|
"step": 705
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.65928430557251,
|
||
|
|
"epoch": 0.06440493468795355,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0003545,
|
||
|
|
"loss": 6.5818,
|
||
|
|
"mean_token_accuracy": 0.11218819990754128,
|
||
|
|
"num_tokens": 1476713.0,
|
||
|
|
"step": 710
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.686679744720459,
|
||
|
|
"epoch": 0.06485849056603774,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.000357,
|
||
|
|
"loss": 6.581,
|
||
|
|
"mean_token_accuracy": 0.11432325467467308,
|
||
|
|
"num_tokens": 1486908.0,
|
||
|
|
"step": 715
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.704012012481689,
|
||
|
|
"epoch": 0.06531204644412192,
|
||
|
|
"grad_norm": 0.96875,
|
||
|
|
"learning_rate": 0.0003595,
|
||
|
|
"loss": 6.5049,
|
||
|
|
"mean_token_accuracy": 0.1139966145157814,
|
||
|
|
"num_tokens": 1498185.0,
|
||
|
|
"step": 720
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.605288028717041,
|
||
|
|
"epoch": 0.0657656023222061,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.000362,
|
||
|
|
"loss": 6.5477,
|
||
|
|
"mean_token_accuracy": 0.11151361390948296,
|
||
|
|
"num_tokens": 1508376.0,
|
||
|
|
"step": 725
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.708197355270386,
|
||
|
|
"epoch": 0.06621915820029027,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.0003645,
|
||
|
|
"loss": 6.6343,
|
||
|
|
"mean_token_accuracy": 0.1107229582965374,
|
||
|
|
"num_tokens": 1519953.0,
|
||
|
|
"step": 730
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.5456921577453615,
|
||
|
|
"epoch": 0.06667271407837445,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.000367,
|
||
|
|
"loss": 6.4996,
|
||
|
|
"mean_token_accuracy": 0.11313785165548325,
|
||
|
|
"num_tokens": 1529793.0,
|
||
|
|
"step": 735
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.6532182693481445,
|
||
|
|
"epoch": 0.06712626995645864,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0003695,
|
||
|
|
"loss": 6.4993,
|
||
|
|
"mean_token_accuracy": 0.11373248919844628,
|
||
|
|
"num_tokens": 1540859.0,
|
||
|
|
"step": 740
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.61553168296814,
|
||
|
|
"epoch": 0.06757982583454282,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.000372,
|
||
|
|
"loss": 6.4324,
|
||
|
|
"mean_token_accuracy": 0.1168427474796772,
|
||
|
|
"num_tokens": 1549783.0,
|
||
|
|
"step": 745
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.514708757400513,
|
||
|
|
"epoch": 0.06803338171262699,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.0003745,
|
||
|
|
"loss": 6.4901,
|
||
|
|
"mean_token_accuracy": 0.11619689613580704,
|
||
|
|
"num_tokens": 1560522.0,
|
||
|
|
"step": 750
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.587539339065552,
|
||
|
|
"epoch": 0.06848693759071117,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.000377,
|
||
|
|
"loss": 6.4759,
|
||
|
|
"mean_token_accuracy": 0.11305172964930535,
|
||
|
|
"num_tokens": 1570668.0,
|
||
|
|
"step": 755
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.66793270111084,
|
||
|
|
"epoch": 0.06894049346879536,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0003795,
|
||
|
|
"loss": 6.5919,
|
||
|
|
"mean_token_accuracy": 0.11405429989099503,
|
||
|
|
"num_tokens": 1581523.0,
|
||
|
|
"step": 760
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.56304898262024,
|
||
|
|
"epoch": 0.06939404934687954,
|
||
|
|
"grad_norm": 1.171875,
|
||
|
|
"learning_rate": 0.000382,
|
||
|
|
"loss": 6.4933,
|
||
|
|
"mean_token_accuracy": 0.11518137082457543,
|
||
|
|
"num_tokens": 1591356.0,
|
||
|
|
"step": 765
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.5586266040802,
|
||
|
|
"epoch": 0.06984760522496372,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.0003845,
|
||
|
|
"loss": 6.4862,
|
||
|
|
"mean_token_accuracy": 0.11520140692591667,
|
||
|
|
"num_tokens": 1601779.0,
|
||
|
|
"step": 770
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.645415878295898,
|
||
|
|
"epoch": 0.07030116110304789,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.00038700000000000003,
|
||
|
|
"loss": 6.4799,
|
||
|
|
"mean_token_accuracy": 0.11675522029399872,
|
||
|
|
"num_tokens": 1611995.0,
|
||
|
|
"step": 775
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.643508338928223,
|
||
|
|
"epoch": 0.07075471698113207,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.00038950000000000003,
|
||
|
|
"loss": 6.51,
|
||
|
|
"mean_token_accuracy": 0.11030993685126304,
|
||
|
|
"num_tokens": 1621834.0,
|
||
|
|
"step": 780
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.5690505027771,
|
||
|
|
"epoch": 0.07120827285921626,
|
||
|
|
"grad_norm": 1.28125,
|
||
|
|
"learning_rate": 0.00039200000000000004,
|
||
|
|
"loss": 6.5502,
|
||
|
|
"mean_token_accuracy": 0.10731691345572472,
|
||
|
|
"num_tokens": 1632881.0,
|
||
|
|
"step": 785
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.497133684158325,
|
||
|
|
"epoch": 0.07166182873730044,
|
||
|
|
"grad_norm": 1.1875,
|
||
|
|
"learning_rate": 0.00039450000000000005,
|
||
|
|
"loss": 6.5383,
|
||
|
|
"mean_token_accuracy": 0.11029602736234664,
|
||
|
|
"num_tokens": 1642870.0,
|
||
|
|
"step": 790
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.5692647933959964,
|
||
|
|
"epoch": 0.07211538461538461,
|
||
|
|
"grad_norm": 1.21875,
|
||
|
|
"learning_rate": 0.00039700000000000005,
|
||
|
|
"loss": 6.4224,
|
||
|
|
"mean_token_accuracy": 0.12195004150271416,
|
||
|
|
"num_tokens": 1653390.0,
|
||
|
|
"step": 795
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.5903912544250485,
|
||
|
|
"epoch": 0.07256894049346879,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.0003995,
|
||
|
|
"loss": 6.5359,
|
||
|
|
"mean_token_accuracy": 0.11937625855207443,
|
||
|
|
"num_tokens": 1663382.0,
|
||
|
|
"step": 800
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.648660278320312,
|
||
|
|
"epoch": 0.07302249637155298,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.000402,
|
||
|
|
"loss": 6.5463,
|
||
|
|
"mean_token_accuracy": 0.11221321672201157,
|
||
|
|
"num_tokens": 1673601.0,
|
||
|
|
"step": 805
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.414686155319214,
|
||
|
|
"epoch": 0.07347605224963716,
|
||
|
|
"grad_norm": 1.328125,
|
||
|
|
"learning_rate": 0.0004045,
|
||
|
|
"loss": 6.4486,
|
||
|
|
"mean_token_accuracy": 0.11948997676372528,
|
||
|
|
"num_tokens": 1683565.0,
|
||
|
|
"step": 810
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.576791286468506,
|
||
|
|
"epoch": 0.07392960812772134,
|
||
|
|
"grad_norm": 1.9609375,
|
||
|
|
"learning_rate": 0.00040699999999999997,
|
||
|
|
"loss": 6.4393,
|
||
|
|
"mean_token_accuracy": 0.11694891527295112,
|
||
|
|
"num_tokens": 1693636.0,
|
||
|
|
"step": 815
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.726799058914184,
|
||
|
|
"epoch": 0.07438316400580551,
|
||
|
|
"grad_norm": 1.1953125,
|
||
|
|
"learning_rate": 0.0004095,
|
||
|
|
"loss": 6.543,
|
||
|
|
"mean_token_accuracy": 0.1100502498447895,
|
||
|
|
"num_tokens": 1703415.0,
|
||
|
|
"step": 820
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.53825044631958,
|
||
|
|
"epoch": 0.0748367198838897,
|
||
|
|
"grad_norm": 1.265625,
|
||
|
|
"learning_rate": 0.000412,
|
||
|
|
"loss": 6.5077,
|
||
|
|
"mean_token_accuracy": 0.1171564668416977,
|
||
|
|
"num_tokens": 1713579.0,
|
||
|
|
"step": 825
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.537848711013794,
|
||
|
|
"epoch": 0.07529027576197388,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0004145,
|
||
|
|
"loss": 6.5234,
|
||
|
|
"mean_token_accuracy": 0.11068456545472145,
|
||
|
|
"num_tokens": 1724583.0,
|
||
|
|
"step": 830
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.56220064163208,
|
||
|
|
"epoch": 0.07574383164005806,
|
||
|
|
"grad_norm": 1.1796875,
|
||
|
|
"learning_rate": 0.000417,
|
||
|
|
"loss": 6.4309,
|
||
|
|
"mean_token_accuracy": 0.12289080545306205,
|
||
|
|
"num_tokens": 1735293.0,
|
||
|
|
"step": 835
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.558898782730102,
|
||
|
|
"epoch": 0.07619738751814223,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004195,
|
||
|
|
"loss": 6.4543,
|
||
|
|
"mean_token_accuracy": 0.11800618395209313,
|
||
|
|
"num_tokens": 1745623.0,
|
||
|
|
"step": 840
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.5176109790802,
|
||
|
|
"epoch": 0.07665094339622641,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.000422,
|
||
|
|
"loss": 6.4841,
|
||
|
|
"mean_token_accuracy": 0.11565901786088943,
|
||
|
|
"num_tokens": 1755713.0,
|
||
|
|
"step": 845
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.523326635360718,
|
||
|
|
"epoch": 0.0771044992743106,
|
||
|
|
"grad_norm": 1.1796875,
|
||
|
|
"learning_rate": 0.0004245,
|
||
|
|
"loss": 6.4853,
|
||
|
|
"mean_token_accuracy": 0.11440500319004059,
|
||
|
|
"num_tokens": 1765264.0,
|
||
|
|
"step": 850
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.563967895507813,
|
||
|
|
"epoch": 0.07755805515239478,
|
||
|
|
"grad_norm": 1.21875,
|
||
|
|
"learning_rate": 0.000427,
|
||
|
|
"loss": 6.5002,
|
||
|
|
"mean_token_accuracy": 0.11388131231069565,
|
||
|
|
"num_tokens": 1775769.0,
|
||
|
|
"step": 855
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.483576726913452,
|
||
|
|
"epoch": 0.07801161103047896,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.0004295,
|
||
|
|
"loss": 6.4249,
|
||
|
|
"mean_token_accuracy": 0.11765370443463326,
|
||
|
|
"num_tokens": 1786245.0,
|
||
|
|
"step": 860
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.497152996063233,
|
||
|
|
"epoch": 0.07846516690856313,
|
||
|
|
"grad_norm": 1.1796875,
|
||
|
|
"learning_rate": 0.000432,
|
||
|
|
"loss": 6.4549,
|
||
|
|
"mean_token_accuracy": 0.12084143534302712,
|
||
|
|
"num_tokens": 1796040.0,
|
||
|
|
"step": 865
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.451007413864136,
|
||
|
|
"epoch": 0.07891872278664731,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0004345,
|
||
|
|
"loss": 6.4846,
|
||
|
|
"mean_token_accuracy": 0.11668049693107604,
|
||
|
|
"num_tokens": 1806007.0,
|
||
|
|
"step": 870
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.6562886238098145,
|
||
|
|
"epoch": 0.0793722786647315,
|
||
|
|
"grad_norm": 1.1953125,
|
||
|
|
"learning_rate": 0.000437,
|
||
|
|
"loss": 6.5641,
|
||
|
|
"mean_token_accuracy": 0.10741591677069665,
|
||
|
|
"num_tokens": 1816935.0,
|
||
|
|
"step": 875
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.411975765228272,
|
||
|
|
"epoch": 0.07982583454281568,
|
||
|
|
"grad_norm": 1.171875,
|
||
|
|
"learning_rate": 0.0004395,
|
||
|
|
"loss": 6.4055,
|
||
|
|
"mean_token_accuracy": 0.11737755388021469,
|
||
|
|
"num_tokens": 1827419.0,
|
||
|
|
"step": 880
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.580957078933716,
|
||
|
|
"epoch": 0.08027939042089985,
|
||
|
|
"grad_norm": 1.234375,
|
||
|
|
"learning_rate": 0.000442,
|
||
|
|
"loss": 6.5167,
|
||
|
|
"mean_token_accuracy": 0.11306339800357819,
|
||
|
|
"num_tokens": 1837933.0,
|
||
|
|
"step": 885
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.480378532409668,
|
||
|
|
"epoch": 0.08073294629898403,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0004445,
|
||
|
|
"loss": 6.5671,
|
||
|
|
"mean_token_accuracy": 0.11678754836320877,
|
||
|
|
"num_tokens": 1848551.0,
|
||
|
|
"step": 890
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.546552562713623,
|
||
|
|
"epoch": 0.08118650217706821,
|
||
|
|
"grad_norm": 1.21875,
|
||
|
|
"learning_rate": 0.000447,
|
||
|
|
"loss": 6.4439,
|
||
|
|
"mean_token_accuracy": 0.11490961909294128,
|
||
|
|
"num_tokens": 1858380.0,
|
||
|
|
"step": 895
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.448764801025391,
|
||
|
|
"epoch": 0.0816400580551524,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.00044950000000000003,
|
||
|
|
"loss": 6.3688,
|
||
|
|
"mean_token_accuracy": 0.11925693526864052,
|
||
|
|
"num_tokens": 1868291.0,
|
||
|
|
"step": 900
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.491116046905518,
|
||
|
|
"epoch": 0.08209361393323658,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.00045200000000000004,
|
||
|
|
"loss": 6.4651,
|
||
|
|
"mean_token_accuracy": 0.11819546893239022,
|
||
|
|
"num_tokens": 1879219.0,
|
||
|
|
"step": 905
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.526374053955078,
|
||
|
|
"epoch": 0.08254716981132075,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.00045450000000000004,
|
||
|
|
"loss": 6.4579,
|
||
|
|
"mean_token_accuracy": 0.1181636244058609,
|
||
|
|
"num_tokens": 1889809.0,
|
||
|
|
"step": 910
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.414980411529541,
|
||
|
|
"epoch": 0.08300072568940493,
|
||
|
|
"grad_norm": 1.15625,
|
||
|
|
"learning_rate": 0.00045700000000000005,
|
||
|
|
"loss": 6.431,
|
||
|
|
"mean_token_accuracy": 0.11433882117271424,
|
||
|
|
"num_tokens": 1899986.0,
|
||
|
|
"step": 915
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.483574247360229,
|
||
|
|
"epoch": 0.08345428156748912,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.00045950000000000006,
|
||
|
|
"loss": 6.4028,
|
||
|
|
"mean_token_accuracy": 0.11887709498405456,
|
||
|
|
"num_tokens": 1909314.0,
|
||
|
|
"step": 920
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.4847499370574955,
|
||
|
|
"epoch": 0.0839078374455733,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.000462,
|
||
|
|
"loss": 6.4628,
|
||
|
|
"mean_token_accuracy": 0.11896910145878792,
|
||
|
|
"num_tokens": 1918443.0,
|
||
|
|
"step": 925
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.4445396900177006,
|
||
|
|
"epoch": 0.08436139332365747,
|
||
|
|
"grad_norm": 1.28125,
|
||
|
|
"learning_rate": 0.0004645,
|
||
|
|
"loss": 6.4045,
|
||
|
|
"mean_token_accuracy": 0.12024879306554795,
|
||
|
|
"num_tokens": 1928683.0,
|
||
|
|
"step": 930
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.317193126678466,
|
||
|
|
"epoch": 0.08481494920174165,
|
||
|
|
"grad_norm": 1.140625,
|
||
|
|
"learning_rate": 0.000467,
|
||
|
|
"loss": 6.3318,
|
||
|
|
"mean_token_accuracy": 0.1153000108897686,
|
||
|
|
"num_tokens": 1938293.0,
|
||
|
|
"step": 935
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.431926250457764,
|
||
|
|
"epoch": 0.08526850507982583,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.0004695,
|
||
|
|
"loss": 6.4353,
|
||
|
|
"mean_token_accuracy": 0.11641831621527672,
|
||
|
|
"num_tokens": 1948233.0,
|
||
|
|
"step": 940
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.480042028427124,
|
||
|
|
"epoch": 0.08572206095791002,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.000472,
|
||
|
|
"loss": 6.3302,
|
||
|
|
"mean_token_accuracy": 0.12561678364872933,
|
||
|
|
"num_tokens": 1958611.0,
|
||
|
|
"step": 945
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.443802785873413,
|
||
|
|
"epoch": 0.0861756168359942,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004745,
|
||
|
|
"loss": 6.4923,
|
||
|
|
"mean_token_accuracy": 0.12038066908717156,
|
||
|
|
"num_tokens": 1968957.0,
|
||
|
|
"step": 950
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.41972770690918,
|
||
|
|
"epoch": 0.08662917271407837,
|
||
|
|
"grad_norm": 1.2265625,
|
||
|
|
"learning_rate": 0.000477,
|
||
|
|
"loss": 6.3452,
|
||
|
|
"mean_token_accuracy": 0.12305001318454742,
|
||
|
|
"num_tokens": 1978503.0,
|
||
|
|
"step": 955
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.331937170028686,
|
||
|
|
"epoch": 0.08708272859216255,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.0004795,
|
||
|
|
"loss": 6.3407,
|
||
|
|
"mean_token_accuracy": 0.12022828236222267,
|
||
|
|
"num_tokens": 1988458.0,
|
||
|
|
"step": 960
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.463285970687866,
|
||
|
|
"epoch": 0.08753628447024674,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.000482,
|
||
|
|
"loss": 6.4719,
|
||
|
|
"mean_token_accuracy": 0.11548013314604759,
|
||
|
|
"num_tokens": 1999984.0,
|
||
|
|
"step": 965
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.286208868026733,
|
||
|
|
"epoch": 0.08798984034833092,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.0004845,
|
||
|
|
"loss": 6.3288,
|
||
|
|
"mean_token_accuracy": 0.12638000547885894,
|
||
|
|
"num_tokens": 2010645.0,
|
||
|
|
"step": 970
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.497215414047242,
|
||
|
|
"epoch": 0.08844339622641509,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.000487,
|
||
|
|
"loss": 6.4547,
|
||
|
|
"mean_token_accuracy": 0.11661298498511315,
|
||
|
|
"num_tokens": 2020196.0,
|
||
|
|
"step": 975
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.386039924621582,
|
||
|
|
"epoch": 0.08889695210449927,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.0004895,
|
||
|
|
"loss": 6.347,
|
||
|
|
"mean_token_accuracy": 0.11794270873069763,
|
||
|
|
"num_tokens": 2030101.0,
|
||
|
|
"step": 980
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.388373708724975,
|
||
|
|
"epoch": 0.08935050798258345,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.000492,
|
||
|
|
"loss": 6.4225,
|
||
|
|
"mean_token_accuracy": 0.11813583448529244,
|
||
|
|
"num_tokens": 2040454.0,
|
||
|
|
"step": 985
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.357129955291748,
|
||
|
|
"epoch": 0.08980406386066764,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004945,
|
||
|
|
"loss": 6.3631,
|
||
|
|
"mean_token_accuracy": 0.11890257149934769,
|
||
|
|
"num_tokens": 2050378.0,
|
||
|
|
"step": 990
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.4591563701629635,
|
||
|
|
"epoch": 0.09025761973875182,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.000497,
|
||
|
|
"loss": 6.4206,
|
||
|
|
"mean_token_accuracy": 0.11803730875253678,
|
||
|
|
"num_tokens": 2060282.0,
|
||
|
|
"step": 995
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.331292963027954,
|
||
|
|
"epoch": 0.09071117561683599,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.0004995,
|
||
|
|
"loss": 6.4023,
|
||
|
|
"mean_token_accuracy": 0.11980631649494171,
|
||
|
|
"num_tokens": 2070563.0,
|
||
|
|
"step": 1000
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.491535806655884,
|
||
|
|
"epoch": 0.09116473149492017,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.0004999999985110217,
|
||
|
|
"loss": 6.4912,
|
||
|
|
"mean_token_accuracy": 0.11830355301499366,
|
||
|
|
"num_tokens": 2080153.0,
|
||
|
|
"step": 1005
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.275622034072876,
|
||
|
|
"epoch": 0.09161828737300436,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.0004999999924620471,
|
||
|
|
"loss": 6.3284,
|
||
|
|
"mean_token_accuracy": 0.1242703415453434,
|
||
|
|
"num_tokens": 2090590.0,
|
||
|
|
"step": 1010
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.441268587112427,
|
||
|
|
"epoch": 0.09207184325108854,
|
||
|
|
"grad_norm": 0.96875,
|
||
|
|
"learning_rate": 0.0004999999817600155,
|
||
|
|
"loss": 6.4116,
|
||
|
|
"mean_token_accuracy": 0.11299227103590966,
|
||
|
|
"num_tokens": 2101945.0,
|
||
|
|
"step": 1015
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.446867227554321,
|
||
|
|
"epoch": 0.09252539912917271,
|
||
|
|
"grad_norm": 0.9375,
|
||
|
|
"learning_rate": 0.0004999999664049268,
|
||
|
|
"loss": 6.394,
|
||
|
|
"mean_token_accuracy": 0.12263479754328728,
|
||
|
|
"num_tokens": 2112514.0,
|
||
|
|
"step": 1020
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.262259101867675,
|
||
|
|
"epoch": 0.09297895500725689,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0004999999463967816,
|
||
|
|
"loss": 6.3454,
|
||
|
|
"mean_token_accuracy": 0.12117168605327606,
|
||
|
|
"num_tokens": 2122296.0,
|
||
|
|
"step": 1025
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.523186826705933,
|
||
|
|
"epoch": 0.09343251088534107,
|
||
|
|
"grad_norm": 0.96484375,
|
||
|
|
"learning_rate": 0.00049999992173558,
|
||
|
|
"loss": 6.4913,
|
||
|
|
"mean_token_accuracy": 0.10856073573231698,
|
||
|
|
"num_tokens": 2134512.0,
|
||
|
|
"step": 1030
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.369787693023682,
|
||
|
|
"epoch": 0.09388606676342526,
|
||
|
|
"grad_norm": 1.15625,
|
||
|
|
"learning_rate": 0.0004999998924213228,
|
||
|
|
"loss": 6.421,
|
||
|
|
"mean_token_accuracy": 0.1210160993039608,
|
||
|
|
"num_tokens": 2143934.0,
|
||
|
|
"step": 1035
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.265434217453003,
|
||
|
|
"epoch": 0.09433962264150944,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.0004999998584540105,
|
||
|
|
"loss": 6.298,
|
||
|
|
"mean_token_accuracy": 0.1182013526558876,
|
||
|
|
"num_tokens": 2155730.0,
|
||
|
|
"step": 1040
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.436200380325317,
|
||
|
|
"epoch": 0.09479317851959361,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004999998198336437,
|
||
|
|
"loss": 6.323,
|
||
|
|
"mean_token_accuracy": 0.1117444783449173,
|
||
|
|
"num_tokens": 2166422.0,
|
||
|
|
"step": 1045
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.347907590866089,
|
||
|
|
"epoch": 0.09524673439767779,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004999997765602233,
|
||
|
|
"loss": 6.4449,
|
||
|
|
"mean_token_accuracy": 0.1139302246272564,
|
||
|
|
"num_tokens": 2177842.0,
|
||
|
|
"step": 1050
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.457770681381225,
|
||
|
|
"epoch": 0.09570029027576198,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004999997286337502,
|
||
|
|
"loss": 6.504,
|
||
|
|
"mean_token_accuracy": 0.11967741474509239,
|
||
|
|
"num_tokens": 2188614.0,
|
||
|
|
"step": 1055
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.377467250823974,
|
||
|
|
"epoch": 0.09615384615384616,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.0004999996760542254,
|
||
|
|
"loss": 6.2878,
|
||
|
|
"mean_token_accuracy": 0.12623362839221955,
|
||
|
|
"num_tokens": 2197886.0,
|
||
|
|
"step": 1060
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.229464912414551,
|
||
|
|
"epoch": 0.09660740203193033,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.00049999961882165,
|
||
|
|
"loss": 6.3599,
|
||
|
|
"mean_token_accuracy": 0.12299013957381248,
|
||
|
|
"num_tokens": 2209930.0,
|
||
|
|
"step": 1065
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.440615034103393,
|
||
|
|
"epoch": 0.09706095791001451,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.0004999995569360251,
|
||
|
|
"loss": 6.3759,
|
||
|
|
"mean_token_accuracy": 0.11413345336914063,
|
||
|
|
"num_tokens": 2219767.0,
|
||
|
|
"step": 1070
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.328685569763183,
|
||
|
|
"epoch": 0.0975145137880987,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.000499999490397352,
|
||
|
|
"loss": 6.3049,
|
||
|
|
"mean_token_accuracy": 0.1205204777419567,
|
||
|
|
"num_tokens": 2230082.0,
|
||
|
|
"step": 1075
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.243273115158081,
|
||
|
|
"epoch": 0.09796806966618288,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004999994192056321,
|
||
|
|
"loss": 6.3255,
|
||
|
|
"mean_token_accuracy": 0.12633560076355935,
|
||
|
|
"num_tokens": 2240066.0,
|
||
|
|
"step": 1080
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.374665594100952,
|
||
|
|
"epoch": 0.09842162554426705,
|
||
|
|
"grad_norm": 0.98828125,
|
||
|
|
"learning_rate": 0.0004999993433608669,
|
||
|
|
"loss": 6.3561,
|
||
|
|
"mean_token_accuracy": 0.1187953770160675,
|
||
|
|
"num_tokens": 2250732.0,
|
||
|
|
"step": 1085
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.321237421035766,
|
||
|
|
"epoch": 0.09887518142235123,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.0004999992628630579,
|
||
|
|
"loss": 6.2454,
|
||
|
|
"mean_token_accuracy": 0.11912132352590561,
|
||
|
|
"num_tokens": 2261452.0,
|
||
|
|
"step": 1090
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.250462293624878,
|
||
|
|
"epoch": 0.09932873730043541,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004999991777122069,
|
||
|
|
"loss": 6.3636,
|
||
|
|
"mean_token_accuracy": 0.12190868705511093,
|
||
|
|
"num_tokens": 2271929.0,
|
||
|
|
"step": 1095
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.321765327453614,
|
||
|
|
"epoch": 0.0997822931785196,
|
||
|
|
"grad_norm": 0.97265625,
|
||
|
|
"learning_rate": 0.0004999990879083156,
|
||
|
|
"loss": 6.3264,
|
||
|
|
"mean_token_accuracy": 0.12127640098333359,
|
||
|
|
"num_tokens": 2282987.0,
|
||
|
|
"step": 1100
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.319233846664429,
|
||
|
|
"epoch": 0.10023584905660378,
|
||
|
|
"grad_norm": 1.15625,
|
||
|
|
"learning_rate": 0.0004999989934513857,
|
||
|
|
"loss": 6.3136,
|
||
|
|
"mean_token_accuracy": 0.1254054971039295,
|
||
|
|
"num_tokens": 2292796.0,
|
||
|
|
"step": 1105
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.332448720932007,
|
||
|
|
"epoch": 0.10068940493468795,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.0004999988943414193,
|
||
|
|
"loss": 6.3567,
|
||
|
|
"mean_token_accuracy": 0.12186149284243583,
|
||
|
|
"num_tokens": 2303057.0,
|
||
|
|
"step": 1110
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.252414035797119,
|
||
|
|
"epoch": 0.10114296081277213,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.0004999987905784184,
|
||
|
|
"loss": 6.3422,
|
||
|
|
"mean_token_accuracy": 0.12239331230521203,
|
||
|
|
"num_tokens": 2314168.0,
|
||
|
|
"step": 1115
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.341477918624878,
|
||
|
|
"epoch": 0.10159651669085631,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004999986821623853,
|
||
|
|
"loss": 6.3088,
|
||
|
|
"mean_token_accuracy": 0.1192399226129055,
|
||
|
|
"num_tokens": 2325241.0,
|
||
|
|
"step": 1120
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.351327323913575,
|
||
|
|
"epoch": 0.1020500725689405,
|
||
|
|
"grad_norm": 1.1875,
|
||
|
|
"learning_rate": 0.0004999985690933219,
|
||
|
|
"loss": 6.3276,
|
||
|
|
"mean_token_accuracy": 0.12044254839420318,
|
||
|
|
"num_tokens": 2334866.0,
|
||
|
|
"step": 1125
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.211726427078247,
|
||
|
|
"epoch": 0.10250362844702467,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.0004999984513712311,
|
||
|
|
"loss": 6.3425,
|
||
|
|
"mean_token_accuracy": 0.11830557957291603,
|
||
|
|
"num_tokens": 2345422.0,
|
||
|
|
"step": 1130
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.417554903030395,
|
||
|
|
"epoch": 0.10295718432510885,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.0004999983289961146,
|
||
|
|
"loss": 6.349,
|
||
|
|
"mean_token_accuracy": 0.11906943917274475,
|
||
|
|
"num_tokens": 2356285.0,
|
||
|
|
"step": 1135
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.214526510238647,
|
||
|
|
"epoch": 0.10341074020319303,
|
||
|
|
"grad_norm": 1.140625,
|
||
|
|
"learning_rate": 0.0004999982019679755,
|
||
|
|
"loss": 6.2793,
|
||
|
|
"mean_token_accuracy": 0.12734896019101144,
|
||
|
|
"num_tokens": 2366861.0,
|
||
|
|
"step": 1140
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.289835214614868,
|
||
|
|
"epoch": 0.10386429608127722,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004999980702868164,
|
||
|
|
"loss": 6.2976,
|
||
|
|
"mean_token_accuracy": 0.12919359803199768,
|
||
|
|
"num_tokens": 2376851.0,
|
||
|
|
"step": 1145
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.3659947395324705,
|
||
|
|
"epoch": 0.1043178519593614,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.0004999979339526396,
|
||
|
|
"loss": 6.3591,
|
||
|
|
"mean_token_accuracy": 0.12571399062871932,
|
||
|
|
"num_tokens": 2386857.0,
|
||
|
|
"step": 1150
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.303523445129395,
|
||
|
|
"epoch": 0.10477140783744557,
|
||
|
|
"grad_norm": 0.98046875,
|
||
|
|
"learning_rate": 0.0004999977929654484,
|
||
|
|
"loss": 6.268,
|
||
|
|
"mean_token_accuracy": 0.12874414026737213,
|
||
|
|
"num_tokens": 2397035.0,
|
||
|
|
"step": 1155
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.3552806854248045,
|
||
|
|
"epoch": 0.10522496371552975,
|
||
|
|
"grad_norm": 1.21875,
|
||
|
|
"learning_rate": 0.0004999976473252453,
|
||
|
|
"loss": 6.3744,
|
||
|
|
"mean_token_accuracy": 0.12097596004605293,
|
||
|
|
"num_tokens": 2408177.0,
|
||
|
|
"step": 1160
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.359548139572143,
|
||
|
|
"epoch": 0.10567851959361393,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004999974970320338,
|
||
|
|
"loss": 6.3076,
|
||
|
|
"mean_token_accuracy": 0.127739118039608,
|
||
|
|
"num_tokens": 2418445.0,
|
||
|
|
"step": 1165
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.25285906791687,
|
||
|
|
"epoch": 0.10613207547169812,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.0004999973420858165,
|
||
|
|
"loss": 6.3116,
|
||
|
|
"mean_token_accuracy": 0.12409163489937783,
|
||
|
|
"num_tokens": 2428990.0,
|
||
|
|
"step": 1170
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.301597690582275,
|
||
|
|
"epoch": 0.10658563134978229,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0004999971824865968,
|
||
|
|
"loss": 6.3509,
|
||
|
|
"mean_token_accuracy": 0.11999165937304497,
|
||
|
|
"num_tokens": 2439643.0,
|
||
|
|
"step": 1175
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.453162050247192,
|
||
|
|
"epoch": 0.10703918722786647,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004999970182343782,
|
||
|
|
"loss": 6.3972,
|
||
|
|
"mean_token_accuracy": 0.12346342280507087,
|
||
|
|
"num_tokens": 2450691.0,
|
||
|
|
"step": 1180
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.286817169189453,
|
||
|
|
"epoch": 0.10749274310595065,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.0004999968493291638,
|
||
|
|
"loss": 6.3281,
|
||
|
|
"mean_token_accuracy": 0.12339968159794808,
|
||
|
|
"num_tokens": 2460706.0,
|
||
|
|
"step": 1185
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.101443719863892,
|
||
|
|
"epoch": 0.10794629898403484,
|
||
|
|
"grad_norm": 0.9609375,
|
||
|
|
"learning_rate": 0.0004999966757709573,
|
||
|
|
"loss": 6.223,
|
||
|
|
"mean_token_accuracy": 0.12936578840017318,
|
||
|
|
"num_tokens": 2470947.0,
|
||
|
|
"step": 1190
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.308624172210694,
|
||
|
|
"epoch": 0.10839985486211902,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.0004999964975597622,
|
||
|
|
"loss": 6.1877,
|
||
|
|
"mean_token_accuracy": 0.12678698301315308,
|
||
|
|
"num_tokens": 2481132.0,
|
||
|
|
"step": 1195
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.23999056816101,
|
||
|
|
"epoch": 0.10885341074020319,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.0004999963146955821,
|
||
|
|
"loss": 6.2221,
|
||
|
|
"mean_token_accuracy": 0.13168013989925384,
|
||
|
|
"num_tokens": 2491701.0,
|
||
|
|
"step": 1200
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.209512996673584,
|
||
|
|
"epoch": 0.10930696661828737,
|
||
|
|
"grad_norm": 0.98046875,
|
||
|
|
"learning_rate": 0.000499996127178421,
|
||
|
|
"loss": 6.3154,
|
||
|
|
"mean_token_accuracy": 0.12373346984386444,
|
||
|
|
"num_tokens": 2502360.0,
|
||
|
|
"step": 1205
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.259164810180664,
|
||
|
|
"epoch": 0.10976052249637155,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.0004999959350082825,
|
||
|
|
"loss": 6.1911,
|
||
|
|
"mean_token_accuracy": 0.12604912146925926,
|
||
|
|
"num_tokens": 2512140.0,
|
||
|
|
"step": 1210
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.277319002151489,
|
||
|
|
"epoch": 0.11021407837445574,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0004999957381851709,
|
||
|
|
"loss": 6.3226,
|
||
|
|
"mean_token_accuracy": 0.11895870566368102,
|
||
|
|
"num_tokens": 2522721.0,
|
||
|
|
"step": 1215
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.195718097686767,
|
||
|
|
"epoch": 0.1106676342525399,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.0004999955367090901,
|
||
|
|
"loss": 6.1883,
|
||
|
|
"mean_token_accuracy": 0.12740988954901694,
|
||
|
|
"num_tokens": 2531786.0,
|
||
|
|
"step": 1220
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.27605619430542,
|
||
|
|
"epoch": 0.11112119013062409,
|
||
|
|
"grad_norm": 0.97265625,
|
||
|
|
"learning_rate": 0.0004999953305800441,
|
||
|
|
"loss": 6.3046,
|
||
|
|
"mean_token_accuracy": 0.1145807795226574,
|
||
|
|
"num_tokens": 2542895.0,
|
||
|
|
"step": 1225
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.222184085845948,
|
||
|
|
"epoch": 0.11157474600870827,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004999951197980374,
|
||
|
|
"loss": 6.2913,
|
||
|
|
"mean_token_accuracy": 0.12083523273468018,
|
||
|
|
"num_tokens": 2554120.0,
|
||
|
|
"step": 1230
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.31572117805481,
|
||
|
|
"epoch": 0.11202830188679246,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.0004999949043630744,
|
||
|
|
"loss": 6.3231,
|
||
|
|
"mean_token_accuracy": 0.12528388127684592,
|
||
|
|
"num_tokens": 2563935.0,
|
||
|
|
"step": 1235
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.163136672973633,
|
||
|
|
"epoch": 0.11248185776487664,
|
||
|
|
"grad_norm": 1.140625,
|
||
|
|
"learning_rate": 0.0004999946842751593,
|
||
|
|
"loss": 6.2399,
|
||
|
|
"mean_token_accuracy": 0.12615554332733153,
|
||
|
|
"num_tokens": 2574465.0,
|
||
|
|
"step": 1240
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.261920547485351,
|
||
|
|
"epoch": 0.11293541364296081,
|
||
|
|
"grad_norm": 0.99609375,
|
||
|
|
"learning_rate": 0.0004999944595342968,
|
||
|
|
"loss": 6.1907,
|
||
|
|
"mean_token_accuracy": 0.12804502844810486,
|
||
|
|
"num_tokens": 2584694.0,
|
||
|
|
"step": 1245
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.215864896774292,
|
||
|
|
"epoch": 0.11338896952104499,
|
||
|
|
"grad_norm": 0.99609375,
|
||
|
|
"learning_rate": 0.0004999942301404916,
|
||
|
|
"loss": 6.165,
|
||
|
|
"mean_token_accuracy": 0.1279282294213772,
|
||
|
|
"num_tokens": 2594540.0,
|
||
|
|
"step": 1250
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.151381015777588,
|
||
|
|
"epoch": 0.11384252539912917,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.0004999939960937484,
|
||
|
|
"loss": 6.0988,
|
||
|
|
"mean_token_accuracy": 0.1311326391994953,
|
||
|
|
"num_tokens": 2604896.0,
|
||
|
|
"step": 1255
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.2653666019439695,
|
||
|
|
"epoch": 0.11429608127721336,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0004999937573940721,
|
||
|
|
"loss": 6.2806,
|
||
|
|
"mean_token_accuracy": 0.13130278512835503,
|
||
|
|
"num_tokens": 2614143.0,
|
||
|
|
"step": 1260
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.085949420928955,
|
||
|
|
"epoch": 0.11474963715529753,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.0004999935140414674,
|
||
|
|
"loss": 6.1738,
|
||
|
|
"mean_token_accuracy": 0.12467294484376908,
|
||
|
|
"num_tokens": 2623999.0,
|
||
|
|
"step": 1265
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.378130960464477,
|
||
|
|
"epoch": 0.11520319303338171,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0004999932660359395,
|
||
|
|
"loss": 6.3881,
|
||
|
|
"mean_token_accuracy": 0.12474165633320808,
|
||
|
|
"num_tokens": 2636208.0,
|
||
|
|
"step": 1270
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.177397966384888,
|
||
|
|
"epoch": 0.11565674891146589,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.0004999930133774936,
|
||
|
|
"loss": 6.2635,
|
||
|
|
"mean_token_accuracy": 0.1310955010354519,
|
||
|
|
"num_tokens": 2645854.0,
|
||
|
|
"step": 1275
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.334166765213013,
|
||
|
|
"epoch": 0.11611030478955008,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.0004999927560661348,
|
||
|
|
"loss": 6.2513,
|
||
|
|
"mean_token_accuracy": 0.13245694637298583,
|
||
|
|
"num_tokens": 2655877.0,
|
||
|
|
"step": 1280
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.226203727722168,
|
||
|
|
"epoch": 0.11656386066763426,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004999924941018685,
|
||
|
|
"loss": 6.2578,
|
||
|
|
"mean_token_accuracy": 0.12858212292194365,
|
||
|
|
"num_tokens": 2666157.0,
|
||
|
|
"step": 1285
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.180522871017456,
|
||
|
|
"epoch": 0.11701741654571843,
|
||
|
|
"grad_norm": 0.99609375,
|
||
|
|
"learning_rate": 0.0004999922274847,
|
||
|
|
"loss": 6.1825,
|
||
|
|
"mean_token_accuracy": 0.1282689355313778,
|
||
|
|
"num_tokens": 2676647.0,
|
||
|
|
"step": 1290
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.1607826232910154,
|
||
|
|
"epoch": 0.11747097242380261,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.000499991956214635,
|
||
|
|
"loss": 6.2123,
|
||
|
|
"mean_token_accuracy": 0.14043712615966797,
|
||
|
|
"num_tokens": 2686417.0,
|
||
|
|
"step": 1295
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.220397090911865,
|
||
|
|
"epoch": 0.1179245283018868,
|
||
|
|
"grad_norm": 0.9921875,
|
||
|
|
"learning_rate": 0.000499991680291679,
|
||
|
|
"loss": 6.2217,
|
||
|
|
"mean_token_accuracy": 0.1216107651591301,
|
||
|
|
"num_tokens": 2697540.0,
|
||
|
|
"step": 1300
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.173789548873901,
|
||
|
|
"epoch": 0.11837808417997098,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.0004999913997158378,
|
||
|
|
"loss": 6.2622,
|
||
|
|
"mean_token_accuracy": 0.11780738160014152,
|
||
|
|
"num_tokens": 2709397.0,
|
||
|
|
"step": 1305
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.271051549911499,
|
||
|
|
"epoch": 0.11883164005805515,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.0004999911144871169,
|
||
|
|
"loss": 6.2158,
|
||
|
|
"mean_token_accuracy": 0.1249967023730278,
|
||
|
|
"num_tokens": 2720430.0,
|
||
|
|
"step": 1310
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.155363607406616,
|
||
|
|
"epoch": 0.11928519593613933,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.0004999908246055226,
|
||
|
|
"loss": 6.1669,
|
||
|
|
"mean_token_accuracy": 0.12677768394351005,
|
||
|
|
"num_tokens": 2730648.0,
|
||
|
|
"step": 1315
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.153974342346191,
|
||
|
|
"epoch": 0.11973875181422351,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0004999905300710607,
|
||
|
|
"loss": 6.1472,
|
||
|
|
"mean_token_accuracy": 0.1284649021923542,
|
||
|
|
"num_tokens": 2739979.0,
|
||
|
|
"step": 1320
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.25038104057312,
|
||
|
|
"epoch": 0.1201923076923077,
|
||
|
|
"grad_norm": 1.2109375,
|
||
|
|
"learning_rate": 0.0004999902308837373,
|
||
|
|
"loss": 6.3028,
|
||
|
|
"mean_token_accuracy": 0.12176627144217492,
|
||
|
|
"num_tokens": 2750329.0,
|
||
|
|
"step": 1325
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.140483713150024,
|
||
|
|
"epoch": 0.12064586357039188,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004999899270435584,
|
||
|
|
"loss": 6.1728,
|
||
|
|
"mean_token_accuracy": 0.1314334973692894,
|
||
|
|
"num_tokens": 2760535.0,
|
||
|
|
"step": 1330
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.230471897125244,
|
||
|
|
"epoch": 0.12109941944847605,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.0004999896185505307,
|
||
|
|
"loss": 6.2044,
|
||
|
|
"mean_token_accuracy": 0.12265649288892747,
|
||
|
|
"num_tokens": 2770470.0,
|
||
|
|
"step": 1335
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.159397172927856,
|
||
|
|
"epoch": 0.12155297532656023,
|
||
|
|
"grad_norm": 0.97265625,
|
||
|
|
"learning_rate": 0.0004999893054046603,
|
||
|
|
"loss": 6.2145,
|
||
|
|
"mean_token_accuracy": 0.12754668965935706,
|
||
|
|
"num_tokens": 2781506.0,
|
||
|
|
"step": 1340
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.125198554992676,
|
||
|
|
"epoch": 0.12200653120464441,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004999889876059537,
|
||
|
|
"loss": 6.1021,
|
||
|
|
"mean_token_accuracy": 0.13616543412208557,
|
||
|
|
"num_tokens": 2791245.0,
|
||
|
|
"step": 1345
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.152018737792969,
|
||
|
|
"epoch": 0.1224600870827286,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0004999886651544176,
|
||
|
|
"loss": 6.1054,
|
||
|
|
"mean_token_accuracy": 0.13110152259469032,
|
||
|
|
"num_tokens": 2801680.0,
|
||
|
|
"step": 1350
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.157893323898316,
|
||
|
|
"epoch": 0.12291364296081277,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004999883380500584,
|
||
|
|
"loss": 6.1862,
|
||
|
|
"mean_token_accuracy": 0.13278760090470315,
|
||
|
|
"num_tokens": 2812805.0,
|
||
|
|
"step": 1355
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.238238143920898,
|
||
|
|
"epoch": 0.12336719883889695,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.0004999880062928831,
|
||
|
|
"loss": 6.2099,
|
||
|
|
"mean_token_accuracy": 0.12580350860953332,
|
||
|
|
"num_tokens": 2822834.0,
|
||
|
|
"step": 1360
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.129199361801147,
|
||
|
|
"epoch": 0.12382075471698113,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.0004999876698828985,
|
||
|
|
"loss": 6.1785,
|
||
|
|
"mean_token_accuracy": 0.1322852909564972,
|
||
|
|
"num_tokens": 2832312.0,
|
||
|
|
"step": 1365
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.211675024032592,
|
||
|
|
"epoch": 0.12427431059506532,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.0004999873288201116,
|
||
|
|
"loss": 6.1859,
|
||
|
|
"mean_token_accuracy": 0.13278617039322854,
|
||
|
|
"num_tokens": 2842998.0,
|
||
|
|
"step": 1370
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.222190952301025,
|
||
|
|
"epoch": 0.1247278664731495,
|
||
|
|
"grad_norm": 1.4609375,
|
||
|
|
"learning_rate": 0.0004999869831045294,
|
||
|
|
"loss": 6.22,
|
||
|
|
"mean_token_accuracy": 0.12911526262760162,
|
||
|
|
"num_tokens": 2854218.0,
|
||
|
|
"step": 1375
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.1174554347991945,
|
||
|
|
"epoch": 0.12518142235123367,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004999866327361589,
|
||
|
|
"loss": 6.0953,
|
||
|
|
"mean_token_accuracy": 0.13779579773545264,
|
||
|
|
"num_tokens": 2864484.0,
|
||
|
|
"step": 1380
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.212736892700195,
|
||
|
|
"epoch": 0.12563497822931785,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.0004999862777150077,
|
||
|
|
"loss": 6.2057,
|
||
|
|
"mean_token_accuracy": 0.12786780819296836,
|
||
|
|
"num_tokens": 2873800.0,
|
||
|
|
"step": 1385
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.171827030181885,
|
||
|
|
"epoch": 0.12608853410740203,
|
||
|
|
"grad_norm": 0.984375,
|
||
|
|
"learning_rate": 0.0004999859180410829,
|
||
|
|
"loss": 6.2171,
|
||
|
|
"mean_token_accuracy": 0.1288387209177017,
|
||
|
|
"num_tokens": 2884247.0,
|
||
|
|
"step": 1390
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.141082382202148,
|
||
|
|
"epoch": 0.12654208998548622,
|
||
|
|
"grad_norm": 0.98828125,
|
||
|
|
"learning_rate": 0.0004999855537143919,
|
||
|
|
"loss": 6.1257,
|
||
|
|
"mean_token_accuracy": 0.12706563696265222,
|
||
|
|
"num_tokens": 2894739.0,
|
||
|
|
"step": 1395
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.073680734634399,
|
||
|
|
"epoch": 0.1269956458635704,
|
||
|
|
"grad_norm": 0.99609375,
|
||
|
|
"learning_rate": 0.0004999851847349425,
|
||
|
|
"loss": 6.1807,
|
||
|
|
"mean_token_accuracy": 0.13040847554802895,
|
||
|
|
"num_tokens": 2904376.0,
|
||
|
|
"step": 1400
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.245872640609742,
|
||
|
|
"epoch": 0.12744920174165458,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0004999848111027419,
|
||
|
|
"loss": 6.2325,
|
||
|
|
"mean_token_accuracy": 0.127915970236063,
|
||
|
|
"num_tokens": 2914304.0,
|
||
|
|
"step": 1405
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.183934211730957,
|
||
|
|
"epoch": 0.12790275761973874,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0004999844328177983,
|
||
|
|
"loss": 6.1235,
|
||
|
|
"mean_token_accuracy": 0.12716101333498955,
|
||
|
|
"num_tokens": 2924400.0,
|
||
|
|
"step": 1410
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.2829203605651855,
|
||
|
|
"epoch": 0.12835631349782292,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0004999840498801191,
|
||
|
|
"loss": 6.347,
|
||
|
|
"mean_token_accuracy": 0.13103133216500282,
|
||
|
|
"num_tokens": 2935040.0,
|
||
|
|
"step": 1415
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.135620164871216,
|
||
|
|
"epoch": 0.1288098693759071,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.0004999836622897126,
|
||
|
|
"loss": 6.1366,
|
||
|
|
"mean_token_accuracy": 0.13396168127655983,
|
||
|
|
"num_tokens": 2945536.0,
|
||
|
|
"step": 1420
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.0857262134552,
|
||
|
|
"epoch": 0.1292634252539913,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.0004999832700465865,
|
||
|
|
"loss": 6.0541,
|
||
|
|
"mean_token_accuracy": 0.13348359540104865,
|
||
|
|
"num_tokens": 2954969.0,
|
||
|
|
"step": 1425
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.16528549194336,
|
||
|
|
"epoch": 0.12971698113207547,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0004999828731507491,
|
||
|
|
"loss": 6.1774,
|
||
|
|
"mean_token_accuracy": 0.12718980759382248,
|
||
|
|
"num_tokens": 2966218.0,
|
||
|
|
"step": 1430
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.185882234573365,
|
||
|
|
"epoch": 0.13017053701015965,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.0004999824716022085,
|
||
|
|
"loss": 6.1999,
|
||
|
|
"mean_token_accuracy": 0.12183153331279754,
|
||
|
|
"num_tokens": 2976640.0,
|
||
|
|
"step": 1435
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.093891048431397,
|
||
|
|
"epoch": 0.13062409288824384,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.0004999820654009731,
|
||
|
|
"loss": 6.1687,
|
||
|
|
"mean_token_accuracy": 0.131185482442379,
|
||
|
|
"num_tokens": 2985883.0,
|
||
|
|
"step": 1440
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.16903977394104,
|
||
|
|
"epoch": 0.13107764876632802,
|
||
|
|
"grad_norm": 0.9921875,
|
||
|
|
"learning_rate": 0.0004999816545470513,
|
||
|
|
"loss": 6.1739,
|
||
|
|
"mean_token_accuracy": 0.12456371188163758,
|
||
|
|
"num_tokens": 2996695.0,
|
||
|
|
"step": 1445
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.17958173751831,
|
||
|
|
"epoch": 0.1315312046444122,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0004999812390404514,
|
||
|
|
"loss": 6.1945,
|
||
|
|
"mean_token_accuracy": 0.128679159283638,
|
||
|
|
"num_tokens": 3007500.0,
|
||
|
|
"step": 1450
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.967514085769653,
|
||
|
|
"epoch": 0.13198476052249636,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0004999808188811823,
|
||
|
|
"loss": 6.0384,
|
||
|
|
"mean_token_accuracy": 0.13110998794436454,
|
||
|
|
"num_tokens": 3017299.0,
|
||
|
|
"step": 1455
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.2758769512176515,
|
||
|
|
"epoch": 0.13243831640058054,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004999803940692524,
|
||
|
|
"loss": 6.3073,
|
||
|
|
"mean_token_accuracy": 0.1230485461652279,
|
||
|
|
"num_tokens": 3028389.0,
|
||
|
|
"step": 1460
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.220829582214355,
|
||
|
|
"epoch": 0.13289187227866472,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0004999799646046707,
|
||
|
|
"loss": 6.1307,
|
||
|
|
"mean_token_accuracy": 0.13422513082623483,
|
||
|
|
"num_tokens": 3038883.0,
|
||
|
|
"step": 1465
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.163057661056518,
|
||
|
|
"epoch": 0.1333454281567489,
|
||
|
|
"grad_norm": 0.97265625,
|
||
|
|
"learning_rate": 0.0004999795304874461,
|
||
|
|
"loss": 6.2457,
|
||
|
|
"mean_token_accuracy": 0.13295281678438187,
|
||
|
|
"num_tokens": 3049904.0,
|
||
|
|
"step": 1470
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.084758853912353,
|
||
|
|
"epoch": 0.1337989840348331,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.0004999790917175873,
|
||
|
|
"loss": 6.0809,
|
||
|
|
"mean_token_accuracy": 0.13047859445214272,
|
||
|
|
"num_tokens": 3059788.0,
|
||
|
|
"step": 1475
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.1702046394348145,
|
||
|
|
"epoch": 0.13425253991291727,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.0004999786482951036,
|
||
|
|
"loss": 6.0729,
|
||
|
|
"mean_token_accuracy": 0.1356496147811413,
|
||
|
|
"num_tokens": 3070413.0,
|
||
|
|
"step": 1480
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.121113586425781,
|
||
|
|
"epoch": 0.13470609579100146,
|
||
|
|
"grad_norm": 0.890625,
|
||
|
|
"learning_rate": 0.0004999782002200041,
|
||
|
|
"loss": 6.2024,
|
||
|
|
"mean_token_accuracy": 0.12601577937602998,
|
||
|
|
"num_tokens": 3081093.0,
|
||
|
|
"step": 1485
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.136486053466797,
|
||
|
|
"epoch": 0.13515965166908564,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0004999777474922982,
|
||
|
|
"loss": 6.1304,
|
||
|
|
"mean_token_accuracy": 0.12720816284418107,
|
||
|
|
"num_tokens": 3090594.0,
|
||
|
|
"step": 1490
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.193129396438598,
|
||
|
|
"epoch": 0.13561320754716982,
|
||
|
|
"grad_norm": 0.99609375,
|
||
|
|
"learning_rate": 0.0004999772901119951,
|
||
|
|
"loss": 6.2432,
|
||
|
|
"mean_token_accuracy": 0.12697395980358123,
|
||
|
|
"num_tokens": 3101061.0,
|
||
|
|
"step": 1495
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.138486433029175,
|
||
|
|
"epoch": 0.13606676342525398,
|
||
|
|
"grad_norm": 0.984375,
|
||
|
|
"learning_rate": 0.0004999768280791043,
|
||
|
|
"loss": 6.1538,
|
||
|
|
"mean_token_accuracy": 0.13143179193139076,
|
||
|
|
"num_tokens": 3111715.0,
|
||
|
|
"step": 1500
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.113825941085816,
|
||
|
|
"epoch": 0.13652031930333816,
|
||
|
|
"grad_norm": 0.9921875,
|
||
|
|
"learning_rate": 0.0004999763613936352,
|
||
|
|
"loss": 6.0641,
|
||
|
|
"mean_token_accuracy": 0.13530101105570794,
|
||
|
|
"num_tokens": 3121378.0,
|
||
|
|
"step": 1505
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.079781913757325,
|
||
|
|
"epoch": 0.13697387518142234,
|
||
|
|
"grad_norm": 0.98828125,
|
||
|
|
"learning_rate": 0.0004999758900555979,
|
||
|
|
"loss": 6.013,
|
||
|
|
"mean_token_accuracy": 0.13859829008579255,
|
||
|
|
"num_tokens": 3131229.0,
|
||
|
|
"step": 1510
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.068106603622437,
|
||
|
|
"epoch": 0.13742743105950653,
|
||
|
|
"grad_norm": 1.1875,
|
||
|
|
"learning_rate": 0.0004999754140650017,
|
||
|
|
"loss": 6.1133,
|
||
|
|
"mean_token_accuracy": 0.12841149419546127,
|
||
|
|
"num_tokens": 3140859.0,
|
||
|
|
"step": 1515
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.186432981491089,
|
||
|
|
"epoch": 0.1378809869375907,
|
||
|
|
"grad_norm": 0.96484375,
|
||
|
|
"learning_rate": 0.0004999749334218567,
|
||
|
|
"loss": 6.1079,
|
||
|
|
"mean_token_accuracy": 0.13175800815224648,
|
||
|
|
"num_tokens": 3151692.0,
|
||
|
|
"step": 1520
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.034256410598755,
|
||
|
|
"epoch": 0.1383345428156749,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0004999744481261726,
|
||
|
|
"loss": 6.1773,
|
||
|
|
"mean_token_accuracy": 0.12917248532176018,
|
||
|
|
"num_tokens": 3161879.0,
|
||
|
|
"step": 1525
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.104421138763428,
|
||
|
|
"epoch": 0.13878809869375908,
|
||
|
|
"grad_norm": 1.171875,
|
||
|
|
"learning_rate": 0.0004999739581779597,
|
||
|
|
"loss": 6.0365,
|
||
|
|
"mean_token_accuracy": 0.1392836257815361,
|
||
|
|
"num_tokens": 3171282.0,
|
||
|
|
"step": 1530
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.098322439193725,
|
||
|
|
"epoch": 0.13924165457184326,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.000499973463577228,
|
||
|
|
"loss": 6.0919,
|
||
|
|
"mean_token_accuracy": 0.13791340962052345,
|
||
|
|
"num_tokens": 3181398.0,
|
||
|
|
"step": 1535
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.116310262680054,
|
||
|
|
"epoch": 0.13969521044992744,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.0004999729643239877,
|
||
|
|
"loss": 6.221,
|
||
|
|
"mean_token_accuracy": 0.13014425411820413,
|
||
|
|
"num_tokens": 3191431.0,
|
||
|
|
"step": 1540
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.162513589859008,
|
||
|
|
"epoch": 0.1401487663280116,
|
||
|
|
"grad_norm": 0.98046875,
|
||
|
|
"learning_rate": 0.0004999724604182492,
|
||
|
|
"loss": 6.2272,
|
||
|
|
"mean_token_accuracy": 0.12255278900265694,
|
||
|
|
"num_tokens": 3202147.0,
|
||
|
|
"step": 1545
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.2134605884552006,
|
||
|
|
"epoch": 0.14060232220609578,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.0004999719518600229,
|
||
|
|
"loss": 6.0894,
|
||
|
|
"mean_token_accuracy": 0.13580598905682564,
|
||
|
|
"num_tokens": 3212428.0,
|
||
|
|
"step": 1550
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.07160701751709,
|
||
|
|
"epoch": 0.14105587808417996,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0004999714386493192,
|
||
|
|
"loss": 6.1527,
|
||
|
|
"mean_token_accuracy": 0.13032715693116187,
|
||
|
|
"num_tokens": 3222099.0,
|
||
|
|
"step": 1555
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.135047817230225,
|
||
|
|
"epoch": 0.14150943396226415,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0004999709207861489,
|
||
|
|
"loss": 6.0821,
|
||
|
|
"mean_token_accuracy": 0.13343799188733102,
|
||
|
|
"num_tokens": 3232079.0,
|
||
|
|
"step": 1560
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.043800163269043,
|
||
|
|
"epoch": 0.14196298984034833,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.0004999703982705227,
|
||
|
|
"loss": 6.0044,
|
||
|
|
"mean_token_accuracy": 0.14089397639036177,
|
||
|
|
"num_tokens": 3241762.0,
|
||
|
|
"step": 1565
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.056787490844727,
|
||
|
|
"epoch": 0.1424165457184325,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.0004999698711024513,
|
||
|
|
"loss": 6.0942,
|
||
|
|
"mean_token_accuracy": 0.13566121682524682,
|
||
|
|
"num_tokens": 3252571.0,
|
||
|
|
"step": 1570
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.119260835647583,
|
||
|
|
"epoch": 0.1428701015965167,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.0004999693392819456,
|
||
|
|
"loss": 6.1276,
|
||
|
|
"mean_token_accuracy": 0.12969395369291306,
|
||
|
|
"num_tokens": 3263542.0,
|
||
|
|
"step": 1575
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.129227113723755,
|
||
|
|
"epoch": 0.14332365747460088,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.0004999688028090166,
|
||
|
|
"loss": 6.2,
|
||
|
|
"mean_token_accuracy": 0.12882068231701851,
|
||
|
|
"num_tokens": 3273295.0,
|
||
|
|
"step": 1580
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.217692804336548,
|
||
|
|
"epoch": 0.14377721335268506,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004999682616836755,
|
||
|
|
"loss": 6.23,
|
||
|
|
"mean_token_accuracy": 0.13299182802438736,
|
||
|
|
"num_tokens": 3283605.0,
|
||
|
|
"step": 1585
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.094928216934204,
|
||
|
|
"epoch": 0.14423076923076922,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.0004999677159059334,
|
||
|
|
"loss": 6.0657,
|
||
|
|
"mean_token_accuracy": 0.1365733303129673,
|
||
|
|
"num_tokens": 3293837.0,
|
||
|
|
"step": 1590
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.993037939071655,
|
||
|
|
"epoch": 0.1446843251088534,
|
||
|
|
"grad_norm": 0.95703125,
|
||
|
|
"learning_rate": 0.0004999671654758016,
|
||
|
|
"loss": 6.0685,
|
||
|
|
"mean_token_accuracy": 0.14040320217609406,
|
||
|
|
"num_tokens": 3304131.0,
|
||
|
|
"step": 1595
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.073614025115967,
|
||
|
|
"epoch": 0.14513788098693758,
|
||
|
|
"grad_norm": 1.359375,
|
||
|
|
"learning_rate": 0.0004999666103932915,
|
||
|
|
"loss": 6.0992,
|
||
|
|
"mean_token_accuracy": 0.13104889690876007,
|
||
|
|
"num_tokens": 3313543.0,
|
||
|
|
"step": 1600
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.087307071685791,
|
||
|
|
"epoch": 0.14559143686502177,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.0004999660506584145,
|
||
|
|
"loss": 6.0907,
|
||
|
|
"mean_token_accuracy": 0.13283502534031869,
|
||
|
|
"num_tokens": 3324487.0,
|
||
|
|
"step": 1605
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.13335018157959,
|
||
|
|
"epoch": 0.14604499274310595,
|
||
|
|
"grad_norm": 0.96875,
|
||
|
|
"learning_rate": 0.0004999654862711823,
|
||
|
|
"loss": 6.0993,
|
||
|
|
"mean_token_accuracy": 0.13403137400746346,
|
||
|
|
"num_tokens": 3335094.0,
|
||
|
|
"step": 1610
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.077793455123901,
|
||
|
|
"epoch": 0.14649854862119013,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.0004999649172316065,
|
||
|
|
"loss": 6.033,
|
||
|
|
"mean_token_accuracy": 0.13351959139108657,
|
||
|
|
"num_tokens": 3344252.0,
|
||
|
|
"step": 1615
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.051349306106568,
|
||
|
|
"epoch": 0.14695210449927432,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.000499964343539699,
|
||
|
|
"loss": 6.1092,
|
||
|
|
"mean_token_accuracy": 0.12948338314890862,
|
||
|
|
"num_tokens": 3354265.0,
|
||
|
|
"step": 1620
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.167207384109497,
|
||
|
|
"epoch": 0.1474056603773585,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.0004999637651954714,
|
||
|
|
"loss": 6.2254,
|
||
|
|
"mean_token_accuracy": 0.1327558323740959,
|
||
|
|
"num_tokens": 3364616.0,
|
||
|
|
"step": 1625
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.135294818878174,
|
||
|
|
"epoch": 0.14785921625544268,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.0004999631821989358,
|
||
|
|
"loss": 6.1636,
|
||
|
|
"mean_token_accuracy": 0.1339091271162033,
|
||
|
|
"num_tokens": 3373650.0,
|
||
|
|
"step": 1630
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.991321992874146,
|
||
|
|
"epoch": 0.14831277213352684,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.0004999625945501043,
|
||
|
|
"loss": 6.0624,
|
||
|
|
"mean_token_accuracy": 0.13642672672867776,
|
||
|
|
"num_tokens": 3384590.0,
|
||
|
|
"step": 1635
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.221540021896362,
|
||
|
|
"epoch": 0.14876632801161102,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.000499962002248989,
|
||
|
|
"loss": 6.1045,
|
||
|
|
"mean_token_accuracy": 0.13118307739496232,
|
||
|
|
"num_tokens": 3395616.0,
|
||
|
|
"step": 1640
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.03116774559021,
|
||
|
|
"epoch": 0.1492198838896952,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.0004999614052956024,
|
||
|
|
"loss": 6.092,
|
||
|
|
"mean_token_accuracy": 0.13425416350364686,
|
||
|
|
"num_tokens": 3405810.0,
|
||
|
|
"step": 1645
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.0968505859375,
|
||
|
|
"epoch": 0.1496734397677794,
|
||
|
|
"grad_norm": 0.96875,
|
||
|
|
"learning_rate": 0.0004999608036899563,
|
||
|
|
"loss": 6.1287,
|
||
|
|
"mean_token_accuracy": 0.13202429711818695,
|
||
|
|
"num_tokens": 3415932.0,
|
||
|
|
"step": 1650
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.095308542251587,
|
||
|
|
"epoch": 0.15012699564586357,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.0004999601974320636,
|
||
|
|
"loss": 6.0899,
|
||
|
|
"mean_token_accuracy": 0.12914085909724235,
|
||
|
|
"num_tokens": 3425626.0,
|
||
|
|
"step": 1655
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.025156164169312,
|
||
|
|
"epoch": 0.15058055152394775,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.0004999595865219367,
|
||
|
|
"loss": 6.0764,
|
||
|
|
"mean_token_accuracy": 0.12880702540278435,
|
||
|
|
"num_tokens": 3434837.0,
|
||
|
|
"step": 1660
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.111604022979736,
|
||
|
|
"epoch": 0.15103410740203194,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0004999589709595881,
|
||
|
|
"loss": 6.1073,
|
||
|
|
"mean_token_accuracy": 0.13633522242307664,
|
||
|
|
"num_tokens": 3445238.0,
|
||
|
|
"step": 1665
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.0251708984375,
|
||
|
|
"epoch": 0.15148766328011612,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.0004999583507450308,
|
||
|
|
"loss": 6.0934,
|
||
|
|
"mean_token_accuracy": 0.1300239272415638,
|
||
|
|
"num_tokens": 3456738.0,
|
||
|
|
"step": 1670
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.999286699295044,
|
||
|
|
"epoch": 0.1519412191582003,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004999577258782774,
|
||
|
|
"loss": 5.957,
|
||
|
|
"mean_token_accuracy": 0.13702991008758544,
|
||
|
|
"num_tokens": 3466296.0,
|
||
|
|
"step": 1675
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.128127813339233,
|
||
|
|
"epoch": 0.15239477503628446,
|
||
|
|
"grad_norm": 0.98828125,
|
||
|
|
"learning_rate": 0.000499957096359341,
|
||
|
|
"loss": 6.1536,
|
||
|
|
"mean_token_accuracy": 0.12765773385763168,
|
||
|
|
"num_tokens": 3476989.0,
|
||
|
|
"step": 1680
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.0421911716461185,
|
||
|
|
"epoch": 0.15284833091436864,
|
||
|
|
"grad_norm": 1.21875,
|
||
|
|
"learning_rate": 0.0004999564621882343,
|
||
|
|
"loss": 6.0026,
|
||
|
|
"mean_token_accuracy": 0.1342094786465168,
|
||
|
|
"num_tokens": 3487050.0,
|
||
|
|
"step": 1685
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.144343376159668,
|
||
|
|
"epoch": 0.15330188679245282,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004999558233649708,
|
||
|
|
"loss": 6.2183,
|
||
|
|
"mean_token_accuracy": 0.12711812555789948,
|
||
|
|
"num_tokens": 3497777.0,
|
||
|
|
"step": 1690
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.131715631484985,
|
||
|
|
"epoch": 0.153755442670537,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004999551798895636,
|
||
|
|
"loss": 6.1137,
|
||
|
|
"mean_token_accuracy": 0.12770443707704543,
|
||
|
|
"num_tokens": 3509066.0,
|
||
|
|
"step": 1695
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.020261526107788,
|
||
|
|
"epoch": 0.1542089985486212,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.0004999545317620258,
|
||
|
|
"loss": 6.0385,
|
||
|
|
"mean_token_accuracy": 0.1325708270072937,
|
||
|
|
"num_tokens": 3519567.0,
|
||
|
|
"step": 1700
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.05970869064331,
|
||
|
|
"epoch": 0.15466255442670537,
|
||
|
|
"grad_norm": 0.984375,
|
||
|
|
"learning_rate": 0.0004999538789823711,
|
||
|
|
"loss": 6.0921,
|
||
|
|
"mean_token_accuracy": 0.13301847204566003,
|
||
|
|
"num_tokens": 3529402.0,
|
||
|
|
"step": 1705
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.176769733428955,
|
||
|
|
"epoch": 0.15511611030478956,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004999532215506127,
|
||
|
|
"loss": 6.0909,
|
||
|
|
"mean_token_accuracy": 0.14401522800326347,
|
||
|
|
"num_tokens": 3539805.0,
|
||
|
|
"step": 1710
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.969664430618286,
|
||
|
|
"epoch": 0.15556966618287374,
|
||
|
|
"grad_norm": 0.98828125,
|
||
|
|
"learning_rate": 0.0004999525594667645,
|
||
|
|
"loss": 5.9514,
|
||
|
|
"mean_token_accuracy": 0.13585785627365113,
|
||
|
|
"num_tokens": 3550477.0,
|
||
|
|
"step": 1715
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.984322881698608,
|
||
|
|
"epoch": 0.15602322206095792,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.00049995189273084,
|
||
|
|
"loss": 6.0522,
|
||
|
|
"mean_token_accuracy": 0.13302028104662894,
|
||
|
|
"num_tokens": 3560729.0,
|
||
|
|
"step": 1720
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.111390686035156,
|
||
|
|
"epoch": 0.15647677793904208,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.000499951221342853,
|
||
|
|
"loss": 6.1395,
|
||
|
|
"mean_token_accuracy": 0.12391486763954163,
|
||
|
|
"num_tokens": 3571538.0,
|
||
|
|
"step": 1725
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.122786998748779,
|
||
|
|
"epoch": 0.15693033381712626,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004999505453028174,
|
||
|
|
"loss": 6.1449,
|
||
|
|
"mean_token_accuracy": 0.1329157382249832,
|
||
|
|
"num_tokens": 3583128.0,
|
||
|
|
"step": 1730
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.065582609176635,
|
||
|
|
"epoch": 0.15738388969521044,
|
||
|
|
"grad_norm": 0.96875,
|
||
|
|
"learning_rate": 0.0004999498646107472,
|
||
|
|
"loss": 6.0667,
|
||
|
|
"mean_token_accuracy": 0.13652407601475716,
|
||
|
|
"num_tokens": 3594358.0,
|
||
|
|
"step": 1735
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.036913299560547,
|
||
|
|
"epoch": 0.15783744557329463,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.0004999491792666566,
|
||
|
|
"loss": 6.0088,
|
||
|
|
"mean_token_accuracy": 0.1374991677701473,
|
||
|
|
"num_tokens": 3604345.0,
|
||
|
|
"step": 1740
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.039101409912109,
|
||
|
|
"epoch": 0.1582910014513788,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004999484892705597,
|
||
|
|
"loss": 6.055,
|
||
|
|
"mean_token_accuracy": 0.13434040173888206,
|
||
|
|
"num_tokens": 3616129.0,
|
||
|
|
"step": 1745
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.09887547492981,
|
||
|
|
"epoch": 0.158744557329463,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0004999477946224705,
|
||
|
|
"loss": 6.1052,
|
||
|
|
"mean_token_accuracy": 0.13473358303308486,
|
||
|
|
"num_tokens": 3627458.0,
|
||
|
|
"step": 1750
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.10147271156311,
|
||
|
|
"epoch": 0.15919811320754718,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.0004999470953224037,
|
||
|
|
"loss": 5.9868,
|
||
|
|
"mean_token_accuracy": 0.1373836562037468,
|
||
|
|
"num_tokens": 3636047.0,
|
||
|
|
"step": 1755
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.975709295272827,
|
||
|
|
"epoch": 0.15965166908563136,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.0004999463913703735,
|
||
|
|
"loss": 5.9717,
|
||
|
|
"mean_token_accuracy": 0.13532424792647363,
|
||
|
|
"num_tokens": 3646930.0,
|
||
|
|
"step": 1760
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.0145656108856205,
|
||
|
|
"epoch": 0.16010522496371554,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.0004999456827663948,
|
||
|
|
"loss": 6.0672,
|
||
|
|
"mean_token_accuracy": 0.13636473268270494,
|
||
|
|
"num_tokens": 3657279.0,
|
||
|
|
"step": 1765
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.016043090820313,
|
||
|
|
"epoch": 0.1605587808417997,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.000499944969510482,
|
||
|
|
"loss": 5.9569,
|
||
|
|
"mean_token_accuracy": 0.13713241890072822,
|
||
|
|
"num_tokens": 3667070.0,
|
||
|
|
"step": 1770
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.058058595657348,
|
||
|
|
"epoch": 0.16101233671988388,
|
||
|
|
"grad_norm": 0.94140625,
|
||
|
|
"learning_rate": 0.0004999442516026498,
|
||
|
|
"loss": 5.9892,
|
||
|
|
"mean_token_accuracy": 0.13559969365596772,
|
||
|
|
"num_tokens": 3677560.0,
|
||
|
|
"step": 1775
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.985709571838379,
|
||
|
|
"epoch": 0.16146589259796806,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0004999435290429133,
|
||
|
|
"loss": 5.946,
|
||
|
|
"mean_token_accuracy": 0.14185371547937392,
|
||
|
|
"num_tokens": 3686701.0,
|
||
|
|
"step": 1780
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.999032068252563,
|
||
|
|
"epoch": 0.16191944847605225,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004999428018312872,
|
||
|
|
"loss": 6.0462,
|
||
|
|
"mean_token_accuracy": 0.14263416901230813,
|
||
|
|
"num_tokens": 3696338.0,
|
||
|
|
"step": 1785
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.082455444335937,
|
||
|
|
"epoch": 0.16237300435413643,
|
||
|
|
"grad_norm": 0.98828125,
|
||
|
|
"learning_rate": 0.0004999420699677867,
|
||
|
|
"loss": 6.0388,
|
||
|
|
"mean_token_accuracy": 0.1367315612733364,
|
||
|
|
"num_tokens": 3705752.0,
|
||
|
|
"step": 1790
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.089331150054932,
|
||
|
|
"epoch": 0.1628265602322206,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0004999413334524269,
|
||
|
|
"loss": 6.1127,
|
||
|
|
"mean_token_accuracy": 0.13379622250795364,
|
||
|
|
"num_tokens": 3716225.0,
|
||
|
|
"step": 1795
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.001873111724853,
|
||
|
|
"epoch": 0.1632801161103048,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.0004999405922852229,
|
||
|
|
"loss": 5.9867,
|
||
|
|
"mean_token_accuracy": 0.13304651603102685,
|
||
|
|
"num_tokens": 3726593.0,
|
||
|
|
"step": 1800
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.997346496582031,
|
||
|
|
"epoch": 0.16373367198838898,
|
||
|
|
"grad_norm": 0.92578125,
|
||
|
|
"learning_rate": 0.0004999398464661901,
|
||
|
|
"loss": 6.0555,
|
||
|
|
"mean_token_accuracy": 0.13038523942232133,
|
||
|
|
"num_tokens": 3737563.0,
|
||
|
|
"step": 1805
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.145504331588745,
|
||
|
|
"epoch": 0.16418722786647316,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.0004999390959953441,
|
||
|
|
"loss": 6.1043,
|
||
|
|
"mean_token_accuracy": 0.13330675959587096,
|
||
|
|
"num_tokens": 3747752.0,
|
||
|
|
"step": 1810
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.9703622341156,
|
||
|
|
"epoch": 0.16464078374455732,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.0004999383408727002,
|
||
|
|
"loss": 6.0364,
|
||
|
|
"mean_token_accuracy": 0.13549003675580024,
|
||
|
|
"num_tokens": 3758795.0,
|
||
|
|
"step": 1815
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.059307003021241,
|
||
|
|
"epoch": 0.1650943396226415,
|
||
|
|
"grad_norm": 1.2578125,
|
||
|
|
"learning_rate": 0.0004999375810982741,
|
||
|
|
"loss": 6.0177,
|
||
|
|
"mean_token_accuracy": 0.1396925114095211,
|
||
|
|
"num_tokens": 3768690.0,
|
||
|
|
"step": 1820
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.01865873336792,
|
||
|
|
"epoch": 0.16554789550072568,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004999368166720815,
|
||
|
|
"loss": 6.0841,
|
||
|
|
"mean_token_accuracy": 0.13427145406603813,
|
||
|
|
"num_tokens": 3779018.0,
|
||
|
|
"step": 1825
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.140135812759399,
|
||
|
|
"epoch": 0.16600145137880987,
|
||
|
|
"grad_norm": 0.9921875,
|
||
|
|
"learning_rate": 0.0004999360475941382,
|
||
|
|
"loss": 5.9842,
|
||
|
|
"mean_token_accuracy": 0.14041623398661612,
|
||
|
|
"num_tokens": 3788985.0,
|
||
|
|
"step": 1830
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.026188707351684,
|
||
|
|
"epoch": 0.16645500725689405,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.00049993527386446,
|
||
|
|
"loss": 6.1309,
|
||
|
|
"mean_token_accuracy": 0.12635482400655745,
|
||
|
|
"num_tokens": 3800787.0,
|
||
|
|
"step": 1835
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.024060583114624,
|
||
|
|
"epoch": 0.16690856313497823,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.0004999344954830633,
|
||
|
|
"loss": 6.0076,
|
||
|
|
"mean_token_accuracy": 0.13396736234426498,
|
||
|
|
"num_tokens": 3811381.0,
|
||
|
|
"step": 1840
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.089121675491333,
|
||
|
|
"epoch": 0.16736211901306242,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.0004999337124499638,
|
||
|
|
"loss": 6.1121,
|
||
|
|
"mean_token_accuracy": 0.13973291739821433,
|
||
|
|
"num_tokens": 3822055.0,
|
||
|
|
"step": 1845
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.998512506484985,
|
||
|
|
"epoch": 0.1678156748911466,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.0004999329247651777,
|
||
|
|
"loss": 6.0637,
|
||
|
|
"mean_token_accuracy": 0.1306314118206501,
|
||
|
|
"num_tokens": 3831900.0,
|
||
|
|
"step": 1850
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.045335531234741,
|
||
|
|
"epoch": 0.16826923076923078,
|
||
|
|
"grad_norm": 1.1640625,
|
||
|
|
"learning_rate": 0.0004999321324287213,
|
||
|
|
"loss": 6.0357,
|
||
|
|
"mean_token_accuracy": 0.13573757112026213,
|
||
|
|
"num_tokens": 3842702.0,
|
||
|
|
"step": 1855
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.1244423389434814,
|
||
|
|
"epoch": 0.16872278664731494,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0004999313354406114,
|
||
|
|
"loss": 5.9929,
|
||
|
|
"mean_token_accuracy": 0.13379636257886887,
|
||
|
|
"num_tokens": 3852690.0,
|
||
|
|
"step": 1860
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.9076738357543945,
|
||
|
|
"epoch": 0.16917634252539912,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.000499930533800864,
|
||
|
|
"loss": 5.993,
|
||
|
|
"mean_token_accuracy": 0.14352267235517502,
|
||
|
|
"num_tokens": 3863040.0,
|
||
|
|
"step": 1865
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.074823522567749,
|
||
|
|
"epoch": 0.1696298984034833,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004999297275094958,
|
||
|
|
"loss": 6.0803,
|
||
|
|
"mean_token_accuracy": 0.13035911098122596,
|
||
|
|
"num_tokens": 3873613.0,
|
||
|
|
"step": 1870
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.932005929946899,
|
||
|
|
"epoch": 0.1700834542815675,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 0.0004999289165665235,
|
||
|
|
"loss": 5.8793,
|
||
|
|
"mean_token_accuracy": 0.14385106191039085,
|
||
|
|
"num_tokens": 3883936.0,
|
||
|
|
"step": 1875
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.965173816680908,
|
||
|
|
"epoch": 0.17053701015965167,
|
||
|
|
"grad_norm": 1.3984375,
|
||
|
|
"learning_rate": 0.0004999281009719639,
|
||
|
|
"loss": 5.8597,
|
||
|
|
"mean_token_accuracy": 0.14646447375416755,
|
||
|
|
"num_tokens": 3893788.0,
|
||
|
|
"step": 1880
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.964988851547242,
|
||
|
|
"epoch": 0.17099056603773585,
|
||
|
|
"grad_norm": 1.1640625,
|
||
|
|
"learning_rate": 0.0004999272807258339,
|
||
|
|
"loss": 5.9165,
|
||
|
|
"mean_token_accuracy": 0.14181002825498581,
|
||
|
|
"num_tokens": 3903434.0,
|
||
|
|
"step": 1885
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.97712721824646,
|
||
|
|
"epoch": 0.17144412191582004,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.0004999264558281504,
|
||
|
|
"loss": 5.9377,
|
||
|
|
"mean_token_accuracy": 0.14012128487229347,
|
||
|
|
"num_tokens": 3913476.0,
|
||
|
|
"step": 1890
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.872003698348999,
|
||
|
|
"epoch": 0.17189767779390422,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.0004999256262789305,
|
||
|
|
"loss": 5.8922,
|
||
|
|
"mean_token_accuracy": 0.14096907377243043,
|
||
|
|
"num_tokens": 3923301.0,
|
||
|
|
"step": 1895
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.992045307159424,
|
||
|
|
"epoch": 0.1723512336719884,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.0004999247920781913,
|
||
|
|
"loss": 6.0344,
|
||
|
|
"mean_token_accuracy": 0.13852274641394616,
|
||
|
|
"num_tokens": 3933335.0,
|
||
|
|
"step": 1900
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.088766717910767,
|
||
|
|
"epoch": 0.17280478955007256,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004999239532259502,
|
||
|
|
"loss": 6.0646,
|
||
|
|
"mean_token_accuracy": 0.1291509412229061,
|
||
|
|
"num_tokens": 3944171.0,
|
||
|
|
"step": 1905
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.080254316329956,
|
||
|
|
"epoch": 0.17325834542815674,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.0004999231097222244,
|
||
|
|
"loss": 6.1305,
|
||
|
|
"mean_token_accuracy": 0.13909375816583633,
|
||
|
|
"num_tokens": 3954160.0,
|
||
|
|
"step": 1910
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.020297527313232,
|
||
|
|
"epoch": 0.17371190130624092,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.0004999222615670312,
|
||
|
|
"loss": 5.9253,
|
||
|
|
"mean_token_accuracy": 0.14530864879488944,
|
||
|
|
"num_tokens": 3964110.0,
|
||
|
|
"step": 1915
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.07570161819458,
|
||
|
|
"epoch": 0.1741654571843251,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.0004999214087603885,
|
||
|
|
"loss": 6.0159,
|
||
|
|
"mean_token_accuracy": 0.13602590560913086,
|
||
|
|
"num_tokens": 3974293.0,
|
||
|
|
"step": 1920
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.922182607650757,
|
||
|
|
"epoch": 0.1746190130624093,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.0004999205513023135,
|
||
|
|
"loss": 5.991,
|
||
|
|
"mean_token_accuracy": 0.1404339738190174,
|
||
|
|
"num_tokens": 3984346.0,
|
||
|
|
"step": 1925
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.97127251625061,
|
||
|
|
"epoch": 0.17507256894049347,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004999196891928245,
|
||
|
|
"loss": 5.9094,
|
||
|
|
"mean_token_accuracy": 0.1484488442540169,
|
||
|
|
"num_tokens": 3992897.0,
|
||
|
|
"step": 1930
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.9334413528442385,
|
||
|
|
"epoch": 0.17552612481857766,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.0004999188224319388,
|
||
|
|
"loss": 5.9525,
|
||
|
|
"mean_token_accuracy": 0.1443849354982376,
|
||
|
|
"num_tokens": 4002575.0,
|
||
|
|
"step": 1935
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.02183780670166,
|
||
|
|
"epoch": 0.17597968069666184,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.0004999179510196746,
|
||
|
|
"loss": 6.027,
|
||
|
|
"mean_token_accuracy": 0.13418469578027725,
|
||
|
|
"num_tokens": 4013752.0,
|
||
|
|
"step": 1940
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.056840991973877,
|
||
|
|
"epoch": 0.17643323657474602,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.0004999170749560498,
|
||
|
|
"loss": 5.9132,
|
||
|
|
"mean_token_accuracy": 0.14471341520547867,
|
||
|
|
"num_tokens": 4023718.0,
|
||
|
|
"step": 1945
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.9298981666564945,
|
||
|
|
"epoch": 0.17688679245283018,
|
||
|
|
"grad_norm": 1.203125,
|
||
|
|
"learning_rate": 0.0004999161942410827,
|
||
|
|
"loss": 5.9974,
|
||
|
|
"mean_token_accuracy": 0.13362503573298454,
|
||
|
|
"num_tokens": 4034210.0,
|
||
|
|
"step": 1950
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.088183450698852,
|
||
|
|
"epoch": 0.17734034833091436,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.0004999153088747913,
|
||
|
|
"loss": 6.0029,
|
||
|
|
"mean_token_accuracy": 0.1354498915374279,
|
||
|
|
"num_tokens": 4044868.0,
|
||
|
|
"step": 1955
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.887863874435425,
|
||
|
|
"epoch": 0.17779390420899854,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.000499914418857194,
|
||
|
|
"loss": 6.0004,
|
||
|
|
"mean_token_accuracy": 0.13930529579520226,
|
||
|
|
"num_tokens": 4055049.0,
|
||
|
|
"step": 1960
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.098280572891236,
|
||
|
|
"epoch": 0.17824746008708273,
|
||
|
|
"grad_norm": 0.96875,
|
||
|
|
"learning_rate": 0.0004999135241883092,
|
||
|
|
"loss": 6.0537,
|
||
|
|
"mean_token_accuracy": 0.13831883370876313,
|
||
|
|
"num_tokens": 4065889.0,
|
||
|
|
"step": 1965
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.039399814605713,
|
||
|
|
"epoch": 0.1787010159651669,
|
||
|
|
"grad_norm": 1.15625,
|
||
|
|
"learning_rate": 0.0004999126248681555,
|
||
|
|
"loss": 6.0688,
|
||
|
|
"mean_token_accuracy": 0.13603949919342995,
|
||
|
|
"num_tokens": 4077288.0,
|
||
|
|
"step": 1970
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.006522798538208,
|
||
|
|
"epoch": 0.1791545718432511,
|
||
|
|
"grad_norm": 1.171875,
|
||
|
|
"learning_rate": 0.0004999117208967513,
|
||
|
|
"loss": 6.0125,
|
||
|
|
"mean_token_accuracy": 0.13738583624362946,
|
||
|
|
"num_tokens": 4087402.0,
|
||
|
|
"step": 1975
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.079785299301148,
|
||
|
|
"epoch": 0.17960812772133528,
|
||
|
|
"grad_norm": 0.984375,
|
||
|
|
"learning_rate": 0.0004999108122741154,
|
||
|
|
"loss": 6.0676,
|
||
|
|
"mean_token_accuracy": 0.13442711606621743,
|
||
|
|
"num_tokens": 4098150.0,
|
||
|
|
"step": 1980
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.926851367950439,
|
||
|
|
"epoch": 0.18006168359941946,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.0004999098990002666,
|
||
|
|
"loss": 5.9194,
|
||
|
|
"mean_token_accuracy": 0.14138512015342714,
|
||
|
|
"num_tokens": 4108134.0,
|
||
|
|
"step": 1985
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.07075514793396,
|
||
|
|
"epoch": 0.18051523947750364,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.0004999089810752237,
|
||
|
|
"loss": 6.0739,
|
||
|
|
"mean_token_accuracy": 0.12807230651378632,
|
||
|
|
"num_tokens": 4118251.0,
|
||
|
|
"step": 1990
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.945065689086914,
|
||
|
|
"epoch": 0.1809687953555878,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.000499908058499006,
|
||
|
|
"loss": 5.9098,
|
||
|
|
"mean_token_accuracy": 0.14311220571398736,
|
||
|
|
"num_tokens": 4129228.0,
|
||
|
|
"step": 1995
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.959850263595581,
|
||
|
|
"epoch": 0.18142235123367198,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.0004999071312716321,
|
||
|
|
"loss": 5.9727,
|
||
|
|
"mean_token_accuracy": 0.14519958719611167,
|
||
|
|
"num_tokens": 4139391.0,
|
||
|
|
"step": 2000
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.003384590148926,
|
||
|
|
"epoch": 0.18187590711175616,
|
||
|
|
"grad_norm": 1.1875,
|
||
|
|
"learning_rate": 0.0004999061993931215,
|
||
|
|
"loss": 5.9024,
|
||
|
|
"mean_token_accuracy": 0.1432528540492058,
|
||
|
|
"num_tokens": 4148891.0,
|
||
|
|
"step": 2005
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.182823896408081,
|
||
|
|
"epoch": 0.18232946298984035,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.0004999052628634934,
|
||
|
|
"loss": 6.2626,
|
||
|
|
"mean_token_accuracy": 0.12997814267873764,
|
||
|
|
"num_tokens": 4159551.0,
|
||
|
|
"step": 2010
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.064494609832764,
|
||
|
|
"epoch": 0.18278301886792453,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.0004999043216827671,
|
||
|
|
"loss": 6.0504,
|
||
|
|
"mean_token_accuracy": 0.13733192086219786,
|
||
|
|
"num_tokens": 4170055.0,
|
||
|
|
"step": 2015
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.916315412521362,
|
||
|
|
"epoch": 0.1832365747460087,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.0004999033758509621,
|
||
|
|
"loss": 5.9017,
|
||
|
|
"mean_token_accuracy": 0.1404242791235447,
|
||
|
|
"num_tokens": 4180767.0,
|
||
|
|
"step": 2020
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.9719846725463865,
|
||
|
|
"epoch": 0.1836901306240929,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.000499902425368098,
|
||
|
|
"loss": 6.0294,
|
||
|
|
"mean_token_accuracy": 0.1393634244799614,
|
||
|
|
"num_tokens": 4190654.0,
|
||
|
|
"step": 2025
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.984382581710816,
|
||
|
|
"epoch": 0.18414368650217708,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.0004999014702341944,
|
||
|
|
"loss": 5.9548,
|
||
|
|
"mean_token_accuracy": 0.13900689631700516,
|
||
|
|
"num_tokens": 4200753.0,
|
||
|
|
"step": 2030
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.028017377853393,
|
||
|
|
"epoch": 0.18459724238026126,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0004999005104492712,
|
||
|
|
"loss": 6.0411,
|
||
|
|
"mean_token_accuracy": 0.1343386575579643,
|
||
|
|
"num_tokens": 4210994.0,
|
||
|
|
"step": 2035
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.9925353050231935,
|
||
|
|
"epoch": 0.18505079825834542,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.0004998995460133481,
|
||
|
|
"loss": 5.9756,
|
||
|
|
"mean_token_accuracy": 0.1370024561882019,
|
||
|
|
"num_tokens": 4220883.0,
|
||
|
|
"step": 2040
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.067998695373535,
|
||
|
|
"epoch": 0.1855043541364296,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004998985769264451,
|
||
|
|
"loss": 6.0217,
|
||
|
|
"mean_token_accuracy": 0.13243423029780388,
|
||
|
|
"num_tokens": 4231269.0,
|
||
|
|
"step": 2045
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.975101900100708,
|
||
|
|
"epoch": 0.18595791001451378,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.0004998976031885821,
|
||
|
|
"loss": 6.0222,
|
||
|
|
"mean_token_accuracy": 0.1368092842400074,
|
||
|
|
"num_tokens": 4241559.0,
|
||
|
|
"step": 2050
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.964649868011475,
|
||
|
|
"epoch": 0.18641146589259797,
|
||
|
|
"grad_norm": 1.171875,
|
||
|
|
"learning_rate": 0.0004998966247997794,
|
||
|
|
"loss": 5.8999,
|
||
|
|
"mean_token_accuracy": 0.14066432118415834,
|
||
|
|
"num_tokens": 4250870.0,
|
||
|
|
"step": 2055
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.934762763977051,
|
||
|
|
"epoch": 0.18686502177068215,
|
||
|
|
"grad_norm": 1.171875,
|
||
|
|
"learning_rate": 0.0004998956417600572,
|
||
|
|
"loss": 5.8707,
|
||
|
|
"mean_token_accuracy": 0.14538644403219222,
|
||
|
|
"num_tokens": 4260848.0,
|
||
|
|
"step": 2060
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.93128457069397,
|
||
|
|
"epoch": 0.18731857764876633,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.0004998946540694358,
|
||
|
|
"loss": 5.9914,
|
||
|
|
"mean_token_accuracy": 0.14326113611459732,
|
||
|
|
"num_tokens": 4270973.0,
|
||
|
|
"step": 2065
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.073555898666382,
|
||
|
|
"epoch": 0.18777213352685052,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.0004998936617279357,
|
||
|
|
"loss": 6.0634,
|
||
|
|
"mean_token_accuracy": 0.13676538169384003,
|
||
|
|
"num_tokens": 4281211.0,
|
||
|
|
"step": 2070
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.9082581996917725,
|
||
|
|
"epoch": 0.1882256894049347,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.0004998926647355773,
|
||
|
|
"loss": 5.9195,
|
||
|
|
"mean_token_accuracy": 0.14342071637511253,
|
||
|
|
"num_tokens": 4291425.0,
|
||
|
|
"step": 2075
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.059259080886841,
|
||
|
|
"epoch": 0.18867924528301888,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.0004998916630923813,
|
||
|
|
"loss": 6.0163,
|
||
|
|
"mean_token_accuracy": 0.13589237108826638,
|
||
|
|
"num_tokens": 4301079.0,
|
||
|
|
"step": 2080
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.99994306564331,
|
||
|
|
"epoch": 0.18913280116110304,
|
||
|
|
"grad_norm": 1.1875,
|
||
|
|
"learning_rate": 0.0004998906567983685,
|
||
|
|
"loss": 6.0042,
|
||
|
|
"mean_token_accuracy": 0.13732029348611832,
|
||
|
|
"num_tokens": 4312374.0,
|
||
|
|
"step": 2085
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.953618669509888,
|
||
|
|
"epoch": 0.18958635703918722,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0004998896458535595,
|
||
|
|
"loss": 5.9273,
|
||
|
|
"mean_token_accuracy": 0.1498640865087509,
|
||
|
|
"num_tokens": 4322810.0,
|
||
|
|
"step": 2090
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.99668779373169,
|
||
|
|
"epoch": 0.1900399129172714,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.0004998886302579752,
|
||
|
|
"loss": 5.9219,
|
||
|
|
"mean_token_accuracy": 0.14000264406204224,
|
||
|
|
"num_tokens": 4332082.0,
|
||
|
|
"step": 2095
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.013230466842652,
|
||
|
|
"epoch": 0.19049346879535559,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.000499887610011637,
|
||
|
|
"loss": 6.0153,
|
||
|
|
"mean_token_accuracy": 0.13956746608018875,
|
||
|
|
"num_tokens": 4342632.0,
|
||
|
|
"step": 2100
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.974089479446411,
|
||
|
|
"epoch": 0.19094702467343977,
|
||
|
|
"grad_norm": 1.25,
|
||
|
|
"learning_rate": 0.0004998865851145656,
|
||
|
|
"loss": 5.9374,
|
||
|
|
"mean_token_accuracy": 0.13679615035653114,
|
||
|
|
"num_tokens": 4353544.0,
|
||
|
|
"step": 2105
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.911929941177368,
|
||
|
|
"epoch": 0.19140058055152395,
|
||
|
|
"grad_norm": 1.25,
|
||
|
|
"learning_rate": 0.0004998855555667822,
|
||
|
|
"loss": 6.0663,
|
||
|
|
"mean_token_accuracy": 0.13838788717985154,
|
||
|
|
"num_tokens": 4363636.0,
|
||
|
|
"step": 2110
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.095745468139649,
|
||
|
|
"epoch": 0.19185413642960814,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.0004998845213683084,
|
||
|
|
"loss": 5.9418,
|
||
|
|
"mean_token_accuracy": 0.13569523617625237,
|
||
|
|
"num_tokens": 4373672.0,
|
||
|
|
"step": 2115
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.816546630859375,
|
||
|
|
"epoch": 0.19230769230769232,
|
||
|
|
"grad_norm": 1.1953125,
|
||
|
|
"learning_rate": 0.0004998834825191652,
|
||
|
|
"loss": 5.9133,
|
||
|
|
"mean_token_accuracy": 0.14208602756261826,
|
||
|
|
"num_tokens": 4383199.0,
|
||
|
|
"step": 2120
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.015786647796631,
|
||
|
|
"epoch": 0.1927612481857765,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0004998824390193743,
|
||
|
|
"loss": 5.983,
|
||
|
|
"mean_token_accuracy": 0.13925845474004744,
|
||
|
|
"num_tokens": 4394446.0,
|
||
|
|
"step": 2125
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.1271813869476315,
|
||
|
|
"epoch": 0.19321480406386066,
|
||
|
|
"grad_norm": 1.234375,
|
||
|
|
"learning_rate": 0.0004998813908689573,
|
||
|
|
"loss": 6.0262,
|
||
|
|
"mean_token_accuracy": 0.13644398227334023,
|
||
|
|
"num_tokens": 4405882.0,
|
||
|
|
"step": 2130
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.8932281017303465,
|
||
|
|
"epoch": 0.19366835994194484,
|
||
|
|
"grad_norm": 1.6171875,
|
||
|
|
"learning_rate": 0.0004998803380679359,
|
||
|
|
"loss": 5.8922,
|
||
|
|
"mean_token_accuracy": 0.14466665238142012,
|
||
|
|
"num_tokens": 4415280.0,
|
||
|
|
"step": 2135
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.9923975467681885,
|
||
|
|
"epoch": 0.19412191582002902,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 0.0004998792806163317,
|
||
|
|
"loss": 6.0927,
|
||
|
|
"mean_token_accuracy": 0.13269788771867752,
|
||
|
|
"num_tokens": 4425755.0,
|
||
|
|
"step": 2140
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.003790664672851,
|
||
|
|
"epoch": 0.1945754716981132,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.0004998782185141667,
|
||
|
|
"loss": 5.961,
|
||
|
|
"mean_token_accuracy": 0.13688114881515503,
|
||
|
|
"num_tokens": 4436259.0,
|
||
|
|
"step": 2145
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.004357957839966,
|
||
|
|
"epoch": 0.1950290275761974,
|
||
|
|
"grad_norm": 1.1796875,
|
||
|
|
"learning_rate": 0.0004998771517614629,
|
||
|
|
"loss": 5.9919,
|
||
|
|
"mean_token_accuracy": 0.13306296169757842,
|
||
|
|
"num_tokens": 4446423.0,
|
||
|
|
"step": 2150
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.005547332763672,
|
||
|
|
"epoch": 0.19548258345428157,
|
||
|
|
"grad_norm": 1.171875,
|
||
|
|
"learning_rate": 0.0004998760803582422,
|
||
|
|
"loss": 5.9289,
|
||
|
|
"mean_token_accuracy": 0.14951801002025605,
|
||
|
|
"num_tokens": 4456678.0,
|
||
|
|
"step": 2155
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.9408186912536625,
|
||
|
|
"epoch": 0.19593613933236576,
|
||
|
|
"grad_norm": 1.21875,
|
||
|
|
"learning_rate": 0.0004998750043045269,
|
||
|
|
"loss": 5.924,
|
||
|
|
"mean_token_accuracy": 0.14363801032304763,
|
||
|
|
"num_tokens": 4467031.0,
|
||
|
|
"step": 2160
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.0042197704315186,
|
||
|
|
"epoch": 0.19638969521044994,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004998739236003392,
|
||
|
|
"loss": 5.9952,
|
||
|
|
"mean_token_accuracy": 0.13384947553277016,
|
||
|
|
"num_tokens": 4477771.0,
|
||
|
|
"step": 2165
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.994749736785889,
|
||
|
|
"epoch": 0.1968432510885341,
|
||
|
|
"grad_norm": 1.171875,
|
||
|
|
"learning_rate": 0.0004998728382457014,
|
||
|
|
"loss": 6.0132,
|
||
|
|
"mean_token_accuracy": 0.13731033354997635,
|
||
|
|
"num_tokens": 4488426.0,
|
||
|
|
"step": 2170
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.060128211975098,
|
||
|
|
"epoch": 0.19729680696661828,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0004998717482406362,
|
||
|
|
"loss": 5.9842,
|
||
|
|
"mean_token_accuracy": 0.13427486047148704,
|
||
|
|
"num_tokens": 4499735.0,
|
||
|
|
"step": 2175
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.945842647552491,
|
||
|
|
"epoch": 0.19775036284470246,
|
||
|
|
"grad_norm": 1.2421875,
|
||
|
|
"learning_rate": 0.0004998706535851657,
|
||
|
|
"loss": 5.9344,
|
||
|
|
"mean_token_accuracy": 0.13740400075912476,
|
||
|
|
"num_tokens": 4509500.0,
|
||
|
|
"step": 2180
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.9569385051727295,
|
||
|
|
"epoch": 0.19820391872278664,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.0004998695542793129,
|
||
|
|
"loss": 5.9392,
|
||
|
|
"mean_token_accuracy": 0.13562830910086632,
|
||
|
|
"num_tokens": 4520431.0,
|
||
|
|
"step": 2185
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.98747034072876,
|
||
|
|
"epoch": 0.19865747460087083,
|
||
|
|
"grad_norm": 1.140625,
|
||
|
|
"learning_rate": 0.0004998684503231003,
|
||
|
|
"loss": 6.0309,
|
||
|
|
"mean_token_accuracy": 0.13986979350447654,
|
||
|
|
"num_tokens": 4532294.0,
|
||
|
|
"step": 2190
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.934312200546264,
|
||
|
|
"epoch": 0.199111030478955,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 0.000499867341716551,
|
||
|
|
"loss": 5.948,
|
||
|
|
"mean_token_accuracy": 0.1377948857843876,
|
||
|
|
"num_tokens": 4542488.0,
|
||
|
|
"step": 2195
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.966859626770019,
|
||
|
|
"epoch": 0.1995645863570392,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 0.0004998662284596878,
|
||
|
|
"loss": 5.8828,
|
||
|
|
"mean_token_accuracy": 0.13661633133888246,
|
||
|
|
"num_tokens": 4552933.0,
|
||
|
|
"step": 2200
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.952669095993042,
|
||
|
|
"epoch": 0.20001814223512338,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0004998651105525335,
|
||
|
|
"loss": 5.8786,
|
||
|
|
"mean_token_accuracy": 0.1433972269296646,
|
||
|
|
"num_tokens": 4562373.0,
|
||
|
|
"step": 2205
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.883717727661133,
|
||
|
|
"epoch": 0.20047169811320756,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0004998639879951115,
|
||
|
|
"loss": 6.0106,
|
||
|
|
"mean_token_accuracy": 0.13773834556341172,
|
||
|
|
"num_tokens": 4572715.0,
|
||
|
|
"step": 2210
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.062313556671143,
|
||
|
|
"epoch": 0.2009252539912917,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.000499862860787445,
|
||
|
|
"loss": 5.8879,
|
||
|
|
"mean_token_accuracy": 0.13721229061484336,
|
||
|
|
"num_tokens": 4582782.0,
|
||
|
|
"step": 2215
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.980919361114502,
|
||
|
|
"epoch": 0.2013788098693759,
|
||
|
|
"grad_norm": 1.171875,
|
||
|
|
"learning_rate": 0.0004998617289295571,
|
||
|
|
"loss": 5.9939,
|
||
|
|
"mean_token_accuracy": 0.13345705717802048,
|
||
|
|
"num_tokens": 4594108.0,
|
||
|
|
"step": 2220
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.007939147949219,
|
||
|
|
"epoch": 0.20183236574746008,
|
||
|
|
"grad_norm": 1.3671875,
|
||
|
|
"learning_rate": 0.0004998605924214714,
|
||
|
|
"loss": 5.9503,
|
||
|
|
"mean_token_accuracy": 0.13709166496992112,
|
||
|
|
"num_tokens": 4604732.0,
|
||
|
|
"step": 2225
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.984397983551025,
|
||
|
|
"epoch": 0.20228592162554426,
|
||
|
|
"grad_norm": 1.2265625,
|
||
|
|
"learning_rate": 0.0004998594512632114,
|
||
|
|
"loss": 6.0782,
|
||
|
|
"mean_token_accuracy": 0.12725423350930215,
|
||
|
|
"num_tokens": 4614998.0,
|
||
|
|
"step": 2230
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.951976251602173,
|
||
|
|
"epoch": 0.20273947750362845,
|
||
|
|
"grad_norm": 1.421875,
|
||
|
|
"learning_rate": 0.0004998583054548006,
|
||
|
|
"loss": 5.9087,
|
||
|
|
"mean_token_accuracy": 0.13761360049247742,
|
||
|
|
"num_tokens": 4624665.0,
|
||
|
|
"step": 2235
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.996311187744141,
|
||
|
|
"epoch": 0.20319303338171263,
|
||
|
|
"grad_norm": 1.2734375,
|
||
|
|
"learning_rate": 0.0004998571549962628,
|
||
|
|
"loss": 5.9052,
|
||
|
|
"mean_token_accuracy": 0.14659312665462493,
|
||
|
|
"num_tokens": 4633731.0,
|
||
|
|
"step": 2240
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.99422254562378,
|
||
|
|
"epoch": 0.2036465892597968,
|
||
|
|
"grad_norm": 1.171875,
|
||
|
|
"learning_rate": 0.0004998559998876216,
|
||
|
|
"loss": 5.9297,
|
||
|
|
"mean_token_accuracy": 0.13845302835106849,
|
||
|
|
"num_tokens": 4643421.0,
|
||
|
|
"step": 2245
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.973086881637573,
|
||
|
|
"epoch": 0.204100145137881,
|
||
|
|
"grad_norm": 1.2890625,
|
||
|
|
"learning_rate": 0.0004998548401289012,
|
||
|
|
"loss": 6.0172,
|
||
|
|
"mean_token_accuracy": 0.13639747053384782,
|
||
|
|
"num_tokens": 4653795.0,
|
||
|
|
"step": 2250
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.01025357246399,
|
||
|
|
"epoch": 0.20455370101596518,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0004998536757201253,
|
||
|
|
"loss": 5.9909,
|
||
|
|
"mean_token_accuracy": 0.13689780980348587,
|
||
|
|
"num_tokens": 4664840.0,
|
||
|
|
"step": 2255
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.023299217224121,
|
||
|
|
"epoch": 0.20500725689404933,
|
||
|
|
"grad_norm": 1.3203125,
|
||
|
|
"learning_rate": 0.0004998525066613181,
|
||
|
|
"loss": 6.0004,
|
||
|
|
"mean_token_accuracy": 0.1407467246055603,
|
||
|
|
"num_tokens": 4675508.0,
|
||
|
|
"step": 2260
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.931134462356567,
|
||
|
|
"epoch": 0.20546081277213352,
|
||
|
|
"grad_norm": 1.1796875,
|
||
|
|
"learning_rate": 0.0004998513329525038,
|
||
|
|
"loss": 5.9157,
|
||
|
|
"mean_token_accuracy": 0.14364449679851532,
|
||
|
|
"num_tokens": 4685995.0,
|
||
|
|
"step": 2265
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.031408452987671,
|
||
|
|
"epoch": 0.2059143686502177,
|
||
|
|
"grad_norm": 1.140625,
|
||
|
|
"learning_rate": 0.0004998501545937066,
|
||
|
|
"loss": 5.9397,
|
||
|
|
"mean_token_accuracy": 0.13526451364159583,
|
||
|
|
"num_tokens": 4696659.0,
|
||
|
|
"step": 2270
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.900203275680542,
|
||
|
|
"epoch": 0.20636792452830188,
|
||
|
|
"grad_norm": 1.1640625,
|
||
|
|
"learning_rate": 0.000499848971584951,
|
||
|
|
"loss": 5.8941,
|
||
|
|
"mean_token_accuracy": 0.14944595396518706,
|
||
|
|
"num_tokens": 4706438.0,
|
||
|
|
"step": 2275
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.911033678054809,
|
||
|
|
"epoch": 0.20682148040638607,
|
||
|
|
"grad_norm": 1.265625,
|
||
|
|
"learning_rate": 0.0004998477839262611,
|
||
|
|
"loss": 5.9105,
|
||
|
|
"mean_token_accuracy": 0.14088572859764098,
|
||
|
|
"num_tokens": 4716402.0,
|
||
|
|
"step": 2280
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.99247899055481,
|
||
|
|
"epoch": 0.20727503628447025,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.000499846591617662,
|
||
|
|
"loss": 6.001,
|
||
|
|
"mean_token_accuracy": 0.1439184844493866,
|
||
|
|
"num_tokens": 4728488.0,
|
||
|
|
"step": 2285
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.915400600433349,
|
||
|
|
"epoch": 0.20772859216255443,
|
||
|
|
"grad_norm": 1.2265625,
|
||
|
|
"learning_rate": 0.0004998453946591779,
|
||
|
|
"loss": 6.0241,
|
||
|
|
"mean_token_accuracy": 0.1419094666838646,
|
||
|
|
"num_tokens": 4738693.0,
|
||
|
|
"step": 2290
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.9869701862335205,
|
||
|
|
"epoch": 0.20818214804063861,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.0004998441930508339,
|
||
|
|
"loss": 5.9132,
|
||
|
|
"mean_token_accuracy": 0.1442976713180542,
|
||
|
|
"num_tokens": 4748895.0,
|
||
|
|
"step": 2295
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.020207309722901,
|
||
|
|
"epoch": 0.2086357039187228,
|
||
|
|
"grad_norm": 1.171875,
|
||
|
|
"learning_rate": 0.0004998429867926547,
|
||
|
|
"loss": 6.0203,
|
||
|
|
"mean_token_accuracy": 0.13464172631502153,
|
||
|
|
"num_tokens": 4760135.0,
|
||
|
|
"step": 2300
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.043022537231446,
|
||
|
|
"epoch": 0.20908925979680695,
|
||
|
|
"grad_norm": 1.171875,
|
||
|
|
"learning_rate": 0.0004998417758846651,
|
||
|
|
"loss": 6.0728,
|
||
|
|
"mean_token_accuracy": 0.14229417890310286,
|
||
|
|
"num_tokens": 4769935.0,
|
||
|
|
"step": 2305
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.088847494125366,
|
||
|
|
"epoch": 0.20954281567489114,
|
||
|
|
"grad_norm": 1.1953125,
|
||
|
|
"learning_rate": 0.0004998405603268903,
|
||
|
|
"loss": 5.9793,
|
||
|
|
"mean_token_accuracy": 0.14080933183431626,
|
||
|
|
"num_tokens": 4779520.0,
|
||
|
|
"step": 2310
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.910649347305298,
|
||
|
|
"epoch": 0.20999637155297532,
|
||
|
|
"grad_norm": 1.1640625,
|
||
|
|
"learning_rate": 0.0004998393401193554,
|
||
|
|
"loss": 5.9004,
|
||
|
|
"mean_token_accuracy": 0.14728002548217772,
|
||
|
|
"num_tokens": 4791256.0,
|
||
|
|
"step": 2315
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.814291381835938,
|
||
|
|
"epoch": 0.2104499274310595,
|
||
|
|
"grad_norm": 1.171875,
|
||
|
|
"learning_rate": 0.0004998381152620857,
|
||
|
|
"loss": 5.8551,
|
||
|
|
"mean_token_accuracy": 0.14871017038822174,
|
||
|
|
"num_tokens": 4801334.0,
|
||
|
|
"step": 2320
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.910569524765014,
|
||
|
|
"epoch": 0.21090348330914369,
|
||
|
|
"grad_norm": 1.28125,
|
||
|
|
"learning_rate": 0.0004998368857551067,
|
||
|
|
"loss": 5.8394,
|
||
|
|
"mean_token_accuracy": 0.145636598020792,
|
||
|
|
"num_tokens": 4811361.0,
|
||
|
|
"step": 2325
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.91206111907959,
|
||
|
|
"epoch": 0.21135703918722787,
|
||
|
|
"grad_norm": 1.2421875,
|
||
|
|
"learning_rate": 0.0004998356515984433,
|
||
|
|
"loss": 5.9207,
|
||
|
|
"mean_token_accuracy": 0.14299503937363625,
|
||
|
|
"num_tokens": 4821190.0,
|
||
|
|
"step": 2330
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.959600400924683,
|
||
|
|
"epoch": 0.21181059506531205,
|
||
|
|
"grad_norm": 1.1640625,
|
||
|
|
"learning_rate": 0.0004998344127921213,
|
||
|
|
"loss": 5.9476,
|
||
|
|
"mean_token_accuracy": 0.14232189506292342,
|
||
|
|
"num_tokens": 4830694.0,
|
||
|
|
"step": 2335
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.944343614578247,
|
||
|
|
"epoch": 0.21226415094339623,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 0.0004998331693361666,
|
||
|
|
"loss": 5.9274,
|
||
|
|
"mean_token_accuracy": 0.137859558314085,
|
||
|
|
"num_tokens": 4841344.0,
|
||
|
|
"step": 2340
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.9577583312988285,
|
||
|
|
"epoch": 0.21271770682148042,
|
||
|
|
"grad_norm": 1.265625,
|
||
|
|
"learning_rate": 0.0004998319212306046,
|
||
|
|
"loss": 5.8928,
|
||
|
|
"mean_token_accuracy": 0.14234141260385513,
|
||
|
|
"num_tokens": 4851161.0,
|
||
|
|
"step": 2345
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.885667610168457,
|
||
|
|
"epoch": 0.21317126269956457,
|
||
|
|
"grad_norm": 1.3984375,
|
||
|
|
"learning_rate": 0.000499830668475461,
|
||
|
|
"loss": 5.8742,
|
||
|
|
"mean_token_accuracy": 0.14236741438508033,
|
||
|
|
"num_tokens": 4860740.0,
|
||
|
|
"step": 2350
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.944697475433349,
|
||
|
|
"epoch": 0.21362481857764876,
|
||
|
|
"grad_norm": 1.2578125,
|
||
|
|
"learning_rate": 0.000499829411070762,
|
||
|
|
"loss": 5.9118,
|
||
|
|
"mean_token_accuracy": 0.14243801087141036,
|
||
|
|
"num_tokens": 4871733.0,
|
||
|
|
"step": 2355
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.945801448822022,
|
||
|
|
"epoch": 0.21407837445573294,
|
||
|
|
"grad_norm": 1.1875,
|
||
|
|
"learning_rate": 0.0004998281490165335,
|
||
|
|
"loss": 5.9669,
|
||
|
|
"mean_token_accuracy": 0.13472701087594033,
|
||
|
|
"num_tokens": 4883617.0,
|
||
|
|
"step": 2360
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.939307308197021,
|
||
|
|
"epoch": 0.21453193033381712,
|
||
|
|
"grad_norm": 1.203125,
|
||
|
|
"learning_rate": 0.0004998268823128016,
|
||
|
|
"loss": 5.9302,
|
||
|
|
"mean_token_accuracy": 0.1350124605000019,
|
||
|
|
"num_tokens": 4894519.0,
|
||
|
|
"step": 2365
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.977178955078125,
|
||
|
|
"epoch": 0.2149854862119013,
|
||
|
|
"grad_norm": 1.328125,
|
||
|
|
"learning_rate": 0.0004998256109595923,
|
||
|
|
"loss": 5.8817,
|
||
|
|
"mean_token_accuracy": 0.1414977490901947,
|
||
|
|
"num_tokens": 4904965.0,
|
||
|
|
"step": 2370
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.86356201171875,
|
||
|
|
"epoch": 0.2154390420899855,
|
||
|
|
"grad_norm": 1.3359375,
|
||
|
|
"learning_rate": 0.0004998243349569323,
|
||
|
|
"loss": 5.7913,
|
||
|
|
"mean_token_accuracy": 0.1485743671655655,
|
||
|
|
"num_tokens": 4914618.0,
|
||
|
|
"step": 2375
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.848833799362183,
|
||
|
|
"epoch": 0.21589259796806967,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.0004998230543048477,
|
||
|
|
"loss": 5.8575,
|
||
|
|
"mean_token_accuracy": 0.14849701523780823,
|
||
|
|
"num_tokens": 4924341.0,
|
||
|
|
"step": 2380
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.913916826248169,
|
||
|
|
"epoch": 0.21634615384615385,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.000499821769003365,
|
||
|
|
"loss": 5.8344,
|
||
|
|
"mean_token_accuracy": 0.14421416819095612,
|
||
|
|
"num_tokens": 4934231.0,
|
||
|
|
"step": 2385
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.868072605133056,
|
||
|
|
"epoch": 0.21679970972423804,
|
||
|
|
"grad_norm": 1.2109375,
|
||
|
|
"learning_rate": 0.0004998204790525109,
|
||
|
|
"loss": 5.8489,
|
||
|
|
"mean_token_accuracy": 0.1429114505648613,
|
||
|
|
"num_tokens": 4944303.0,
|
||
|
|
"step": 2390
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.908360385894776,
|
||
|
|
"epoch": 0.2172532656023222,
|
||
|
|
"grad_norm": 1.1640625,
|
||
|
|
"learning_rate": 0.0004998191844523119,
|
||
|
|
"loss": 5.9351,
|
||
|
|
"mean_token_accuracy": 0.14515570178627968,
|
||
|
|
"num_tokens": 4954571.0,
|
||
|
|
"step": 2395
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.965419578552246,
|
||
|
|
"epoch": 0.21770682148040638,
|
||
|
|
"grad_norm": 1.203125,
|
||
|
|
"learning_rate": 0.000499817885202795,
|
||
|
|
"loss": 5.8968,
|
||
|
|
"mean_token_accuracy": 0.14096556901931762,
|
||
|
|
"num_tokens": 4964418.0,
|
||
|
|
"step": 2400
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.979696035385132,
|
||
|
|
"epoch": 0.21816037735849056,
|
||
|
|
"grad_norm": 1.2109375,
|
||
|
|
"learning_rate": 0.0004998165813039869,
|
||
|
|
"loss": 5.8835,
|
||
|
|
"mean_token_accuracy": 0.14295963644981385,
|
||
|
|
"num_tokens": 4975036.0,
|
||
|
|
"step": 2405
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.873979759216309,
|
||
|
|
"epoch": 0.21861393323657474,
|
||
|
|
"grad_norm": 1.3359375,
|
||
|
|
"learning_rate": 0.0004998152727559145,
|
||
|
|
"loss": 5.9914,
|
||
|
|
"mean_token_accuracy": 0.13900846913456916,
|
||
|
|
"num_tokens": 4985272.0,
|
||
|
|
"step": 2410
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.005450963973999,
|
||
|
|
"epoch": 0.21906748911465893,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.000499813959558605,
|
||
|
|
"loss": 5.9213,
|
||
|
|
"mean_token_accuracy": 0.14803757071495055,
|
||
|
|
"num_tokens": 4995187.0,
|
||
|
|
"step": 2415
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.996357822418213,
|
||
|
|
"epoch": 0.2195210449927431,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 0.0004998126417120856,
|
||
|
|
"loss": 5.9681,
|
||
|
|
"mean_token_accuracy": 0.14800111576914787,
|
||
|
|
"num_tokens": 5005013.0,
|
||
|
|
"step": 2420
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.017085218429566,
|
||
|
|
"epoch": 0.2199746008708273,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.0004998113192163835,
|
||
|
|
"loss": 5.9755,
|
||
|
|
"mean_token_accuracy": 0.13796148598194122,
|
||
|
|
"num_tokens": 5016789.0,
|
||
|
|
"step": 2425
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.947689533233643,
|
||
|
|
"epoch": 0.22042815674891147,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.000499809992071526,
|
||
|
|
"loss": 5.9331,
|
||
|
|
"mean_token_accuracy": 0.14225904271006584,
|
||
|
|
"num_tokens": 5026913.0,
|
||
|
|
"step": 2430
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.922537040710449,
|
||
|
|
"epoch": 0.22088171262699566,
|
||
|
|
"grad_norm": 1.2265625,
|
||
|
|
"learning_rate": 0.0004998086602775406,
|
||
|
|
"loss": 6.0365,
|
||
|
|
"mean_token_accuracy": 0.13978781476616858,
|
||
|
|
"num_tokens": 5037501.0,
|
||
|
|
"step": 2435
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.976426696777343,
|
||
|
|
"epoch": 0.2213352685050798,
|
||
|
|
"grad_norm": 1.2265625,
|
||
|
|
"learning_rate": 0.0004998073238344547,
|
||
|
|
"loss": 5.8812,
|
||
|
|
"mean_token_accuracy": 0.13661929443478585,
|
||
|
|
"num_tokens": 5048478.0,
|
||
|
|
"step": 2440
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.931379604339599,
|
||
|
|
"epoch": 0.221788824383164,
|
||
|
|
"grad_norm": 1.2421875,
|
||
|
|
"learning_rate": 0.0004998059827422962,
|
||
|
|
"loss": 5.9411,
|
||
|
|
"mean_token_accuracy": 0.1370401792228222,
|
||
|
|
"num_tokens": 5059118.0,
|
||
|
|
"step": 2445
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.984925699234009,
|
||
|
|
"epoch": 0.22224238026124818,
|
||
|
|
"grad_norm": 1.171875,
|
||
|
|
"learning_rate": 0.0004998046370010926,
|
||
|
|
"loss": 5.8956,
|
||
|
|
"mean_token_accuracy": 0.14508832097053528,
|
||
|
|
"num_tokens": 5070180.0,
|
||
|
|
"step": 2450
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.882190847396851,
|
||
|
|
"epoch": 0.22269593613933236,
|
||
|
|
"grad_norm": 1.2578125,
|
||
|
|
"learning_rate": 0.0004998032866108718,
|
||
|
|
"loss": 5.8958,
|
||
|
|
"mean_token_accuracy": 0.14208046942949296,
|
||
|
|
"num_tokens": 5079912.0,
|
||
|
|
"step": 2455
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.956144332885742,
|
||
|
|
"epoch": 0.22314949201741655,
|
||
|
|
"grad_norm": 1.140625,
|
||
|
|
"learning_rate": 0.0004998019315716618,
|
||
|
|
"loss": 5.9767,
|
||
|
|
"mean_token_accuracy": 0.14252351969480515,
|
||
|
|
"num_tokens": 5090549.0,
|
||
|
|
"step": 2460
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.902889060974121,
|
||
|
|
"epoch": 0.22360304789550073,
|
||
|
|
"grad_norm": 1.2265625,
|
||
|
|
"learning_rate": 0.0004998005718834905,
|
||
|
|
"loss": 5.8293,
|
||
|
|
"mean_token_accuracy": 0.15000268071889877,
|
||
|
|
"num_tokens": 5100880.0,
|
||
|
|
"step": 2465
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.912509965896606,
|
||
|
|
"epoch": 0.2240566037735849,
|
||
|
|
"grad_norm": 1.140625,
|
||
|
|
"learning_rate": 0.0004997992075463862,
|
||
|
|
"loss": 5.9424,
|
||
|
|
"mean_token_accuracy": 0.1433528684079647,
|
||
|
|
"num_tokens": 5111796.0,
|
||
|
|
"step": 2470
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.958014440536499,
|
||
|
|
"epoch": 0.2245101596516691,
|
||
|
|
"grad_norm": 1.234375,
|
||
|
|
"learning_rate": 0.0004997978385603769,
|
||
|
|
"loss": 5.935,
|
||
|
|
"mean_token_accuracy": 0.14096981883049012,
|
||
|
|
"num_tokens": 5123468.0,
|
||
|
|
"step": 2475
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.9337944984436035,
|
||
|
|
"epoch": 0.22496371552975328,
|
||
|
|
"grad_norm": 1.171875,
|
||
|
|
"learning_rate": 0.0004997964649254911,
|
||
|
|
"loss": 5.8641,
|
||
|
|
"mean_token_accuracy": 0.1491854891180992,
|
||
|
|
"num_tokens": 5132925.0,
|
||
|
|
"step": 2480
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.011470174789428,
|
||
|
|
"epoch": 0.22541727140783743,
|
||
|
|
"grad_norm": 1.28125,
|
||
|
|
"learning_rate": 0.0004997950866417572,
|
||
|
|
"loss": 5.9448,
|
||
|
|
"mean_token_accuracy": 0.1389354422688484,
|
||
|
|
"num_tokens": 5143445.0,
|
||
|
|
"step": 2485
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.92656307220459,
|
||
|
|
"epoch": 0.22587082728592162,
|
||
|
|
"grad_norm": 1.3359375,
|
||
|
|
"learning_rate": 0.0004997937037092034,
|
||
|
|
"loss": 5.8551,
|
||
|
|
"mean_token_accuracy": 0.13968046829104425,
|
||
|
|
"num_tokens": 5153176.0,
|
||
|
|
"step": 2490
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.953498363494873,
|
||
|
|
"epoch": 0.2263243831640058,
|
||
|
|
"grad_norm": 1.2265625,
|
||
|
|
"learning_rate": 0.0004997923161278587,
|
||
|
|
"loss": 5.9041,
|
||
|
|
"mean_token_accuracy": 0.1428646430373192,
|
||
|
|
"num_tokens": 5162765.0,
|
||
|
|
"step": 2495
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.978867244720459,
|
||
|
|
"epoch": 0.22677793904208998,
|
||
|
|
"grad_norm": 1.2578125,
|
||
|
|
"learning_rate": 0.0004997909238977514,
|
||
|
|
"loss": 5.9606,
|
||
|
|
"mean_token_accuracy": 0.14364035278558732,
|
||
|
|
"num_tokens": 5173390.0,
|
||
|
|
"step": 2500
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.906553840637207,
|
||
|
|
"epoch": 0.22723149492017417,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.0004997895270189108,
|
||
|
|
"loss": 5.8628,
|
||
|
|
"mean_token_accuracy": 0.1373254232108593,
|
||
|
|
"num_tokens": 5184212.0,
|
||
|
|
"step": 2505
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.853435754776001,
|
||
|
|
"epoch": 0.22768505079825835,
|
||
|
|
"grad_norm": 1.1796875,
|
||
|
|
"learning_rate": 0.0004997881254913653,
|
||
|
|
"loss": 5.8602,
|
||
|
|
"mean_token_accuracy": 0.13991171047091483,
|
||
|
|
"num_tokens": 5194311.0,
|
||
|
|
"step": 2510
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.888242435455322,
|
||
|
|
"epoch": 0.22813860667634253,
|
||
|
|
"grad_norm": 1.2109375,
|
||
|
|
"learning_rate": 0.0004997867193151441,
|
||
|
|
"loss": 5.8408,
|
||
|
|
"mean_token_accuracy": 0.1456891916692257,
|
||
|
|
"num_tokens": 5204708.0,
|
||
|
|
"step": 2515
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.830229997634888,
|
||
|
|
"epoch": 0.22859216255442671,
|
||
|
|
"grad_norm": 1.21875,
|
||
|
|
"learning_rate": 0.0004997853084902763,
|
||
|
|
"loss": 5.843,
|
||
|
|
"mean_token_accuracy": 0.14071134552359582,
|
||
|
|
"num_tokens": 5214566.0,
|
||
|
|
"step": 2520
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.903006267547608,
|
||
|
|
"epoch": 0.2290457184325109,
|
||
|
|
"grad_norm": 1.1953125,
|
||
|
|
"learning_rate": 0.0004997838930167911,
|
||
|
|
"loss": 5.8779,
|
||
|
|
"mean_token_accuracy": 0.14581192210316657,
|
||
|
|
"num_tokens": 5224762.0,
|
||
|
|
"step": 2525
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.952599906921387,
|
||
|
|
"epoch": 0.22949927431059505,
|
||
|
|
"grad_norm": 1.2265625,
|
||
|
|
"learning_rate": 0.0004997824728947176,
|
||
|
|
"loss": 5.9372,
|
||
|
|
"mean_token_accuracy": 0.13909635022282602,
|
||
|
|
"num_tokens": 5235146.0,
|
||
|
|
"step": 2530
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.936500406265258,
|
||
|
|
"epoch": 0.22995283018867924,
|
||
|
|
"grad_norm": 1.1875,
|
||
|
|
"learning_rate": 0.0004997810481240853,
|
||
|
|
"loss": 5.9115,
|
||
|
|
"mean_token_accuracy": 0.1376205012202263,
|
||
|
|
"num_tokens": 5243867.0,
|
||
|
|
"step": 2535
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.910394525527954,
|
||
|
|
"epoch": 0.23040638606676342,
|
||
|
|
"grad_norm": 1.21875,
|
||
|
|
"learning_rate": 0.0004997796187049238,
|
||
|
|
"loss": 5.831,
|
||
|
|
"mean_token_accuracy": 0.14185473769903184,
|
||
|
|
"num_tokens": 5254279.0,
|
||
|
|
"step": 2540
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.032854747772217,
|
||
|
|
"epoch": 0.2308599419448476,
|
||
|
|
"grad_norm": 1.2421875,
|
||
|
|
"learning_rate": 0.0004997781846372623,
|
||
|
|
"loss": 5.9444,
|
||
|
|
"mean_token_accuracy": 0.1413105957210064,
|
||
|
|
"num_tokens": 5264769.0,
|
||
|
|
"step": 2545
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.892349815368652,
|
||
|
|
"epoch": 0.23131349782293179,
|
||
|
|
"grad_norm": 1.2734375,
|
||
|
|
"learning_rate": 0.0004997767459211307,
|
||
|
|
"loss": 5.8757,
|
||
|
|
"mean_token_accuracy": 0.1384491316974163,
|
||
|
|
"num_tokens": 5274291.0,
|
||
|
|
"step": 2550
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.9222578525543215,
|
||
|
|
"epoch": 0.23176705370101597,
|
||
|
|
"grad_norm": 1.4453125,
|
||
|
|
"learning_rate": 0.0004997753025565587,
|
||
|
|
"loss": 5.8226,
|
||
|
|
"mean_token_accuracy": 0.14413735643029213,
|
||
|
|
"num_tokens": 5284366.0,
|
||
|
|
"step": 2555
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.923757791519165,
|
||
|
|
"epoch": 0.23222060957910015,
|
||
|
|
"grad_norm": 1.3515625,
|
||
|
|
"learning_rate": 0.0004997738545435763,
|
||
|
|
"loss": 5.9218,
|
||
|
|
"mean_token_accuracy": 0.14310500398278236,
|
||
|
|
"num_tokens": 5294494.0,
|
||
|
|
"step": 2560
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.835726594924926,
|
||
|
|
"epoch": 0.23267416545718433,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 0.0004997724018822133,
|
||
|
|
"loss": 5.9402,
|
||
|
|
"mean_token_accuracy": 0.14283815771341324,
|
||
|
|
"num_tokens": 5305606.0,
|
||
|
|
"step": 2565
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.938771772384643,
|
||
|
|
"epoch": 0.23312772133526852,
|
||
|
|
"grad_norm": 1.4296875,
|
||
|
|
"learning_rate": 0.0004997709445724996,
|
||
|
|
"loss": 5.9326,
|
||
|
|
"mean_token_accuracy": 0.13846345022320747,
|
||
|
|
"num_tokens": 5315677.0,
|
||
|
|
"step": 2570
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.001786565780639,
|
||
|
|
"epoch": 0.23358127721335267,
|
||
|
|
"grad_norm": 1.1796875,
|
||
|
|
"learning_rate": 0.0004997694826144656,
|
||
|
|
"loss": 5.987,
|
||
|
|
"mean_token_accuracy": 0.13663317039608955,
|
||
|
|
"num_tokens": 5326453.0,
|
||
|
|
"step": 2575
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.945255422592163,
|
||
|
|
"epoch": 0.23403483309143686,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004997680160081414,
|
||
|
|
"loss": 5.8746,
|
||
|
|
"mean_token_accuracy": 0.14533428698778153,
|
||
|
|
"num_tokens": 5337591.0,
|
||
|
|
"step": 2580
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.880674076080322,
|
||
|
|
"epoch": 0.23448838896952104,
|
||
|
|
"grad_norm": 1.1640625,
|
||
|
|
"learning_rate": 0.0004997665447535573,
|
||
|
|
"loss": 5.8792,
|
||
|
|
"mean_token_accuracy": 0.14644460529088973,
|
||
|
|
"num_tokens": 5349400.0,
|
||
|
|
"step": 2585
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.976725244522095,
|
||
|
|
"epoch": 0.23494194484760522,
|
||
|
|
"grad_norm": 1.296875,
|
||
|
|
"learning_rate": 0.0004997650688507438,
|
||
|
|
"loss": 5.8647,
|
||
|
|
"mean_token_accuracy": 0.14361676946282387,
|
||
|
|
"num_tokens": 5359984.0,
|
||
|
|
"step": 2590
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.860870790481568,
|
||
|
|
"epoch": 0.2353955007256894,
|
||
|
|
"grad_norm": 1.3203125,
|
||
|
|
"learning_rate": 0.0004997635882997314,
|
||
|
|
"loss": 5.9341,
|
||
|
|
"mean_token_accuracy": 0.14296606034040452,
|
||
|
|
"num_tokens": 5369254.0,
|
||
|
|
"step": 2595
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.9094048023223875,
|
||
|
|
"epoch": 0.2358490566037736,
|
||
|
|
"grad_norm": 1.3984375,
|
||
|
|
"learning_rate": 0.0004997621031005507,
|
||
|
|
"loss": 5.8609,
|
||
|
|
"mean_token_accuracy": 0.14291658252477646,
|
||
|
|
"num_tokens": 5379648.0,
|
||
|
|
"step": 2600
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.866974496841431,
|
||
|
|
"epoch": 0.23630261248185777,
|
||
|
|
"grad_norm": 1.3046875,
|
||
|
|
"learning_rate": 0.0004997606132532325,
|
||
|
|
"loss": 5.8309,
|
||
|
|
"mean_token_accuracy": 0.14787738099694253,
|
||
|
|
"num_tokens": 5390321.0,
|
||
|
|
"step": 2605
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.867215776443482,
|
||
|
|
"epoch": 0.23675616835994195,
|
||
|
|
"grad_norm": 1.3359375,
|
||
|
|
"learning_rate": 0.0004997591187578075,
|
||
|
|
"loss": 5.8596,
|
||
|
|
"mean_token_accuracy": 0.14872283935546876,
|
||
|
|
"num_tokens": 5401078.0,
|
||
|
|
"step": 2610
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.8993391513824465,
|
||
|
|
"epoch": 0.23720972423802614,
|
||
|
|
"grad_norm": 1.390625,
|
||
|
|
"learning_rate": 0.0004997576196143067,
|
||
|
|
"loss": 5.8513,
|
||
|
|
"mean_token_accuracy": 0.1461376279592514,
|
||
|
|
"num_tokens": 5411977.0,
|
||
|
|
"step": 2615
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.88139500617981,
|
||
|
|
"epoch": 0.2376632801161103,
|
||
|
|
"grad_norm": 1.3203125,
|
||
|
|
"learning_rate": 0.000499756115822761,
|
||
|
|
"loss": 5.841,
|
||
|
|
"mean_token_accuracy": 0.13903868198394775,
|
||
|
|
"num_tokens": 5422967.0,
|
||
|
|
"step": 2620
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.967788743972778,
|
||
|
|
"epoch": 0.23811683599419448,
|
||
|
|
"grad_norm": 1.265625,
|
||
|
|
"learning_rate": 0.0004997546073832015,
|
||
|
|
"loss": 5.8848,
|
||
|
|
"mean_token_accuracy": 0.15244564265012742,
|
||
|
|
"num_tokens": 5432260.0,
|
||
|
|
"step": 2625
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.894135141372681,
|
||
|
|
"epoch": 0.23857039187227866,
|
||
|
|
"grad_norm": 1.53125,
|
||
|
|
"learning_rate": 0.0004997530942956595,
|
||
|
|
"loss": 5.8465,
|
||
|
|
"mean_token_accuracy": 0.14635367840528488,
|
||
|
|
"num_tokens": 5441706.0,
|
||
|
|
"step": 2630
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.897868919372558,
|
||
|
|
"epoch": 0.23902394775036284,
|
||
|
|
"grad_norm": 1.234375,
|
||
|
|
"learning_rate": 0.0004997515765601662,
|
||
|
|
"loss": 5.8558,
|
||
|
|
"mean_token_accuracy": 0.15220582336187363,
|
||
|
|
"num_tokens": 5452397.0,
|
||
|
|
"step": 2635
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.880718660354614,
|
||
|
|
"epoch": 0.23947750362844702,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.0004997500541767531,
|
||
|
|
"loss": 5.8202,
|
||
|
|
"mean_token_accuracy": 0.14415100812911988,
|
||
|
|
"num_tokens": 5463762.0,
|
||
|
|
"step": 2640
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.870383977890015,
|
||
|
|
"epoch": 0.2399310595065312,
|
||
|
|
"grad_norm": 1.2109375,
|
||
|
|
"learning_rate": 0.0004997485271454516,
|
||
|
|
"loss": 5.8788,
|
||
|
|
"mean_token_accuracy": 0.13774784579873084,
|
||
|
|
"num_tokens": 5474622.0,
|
||
|
|
"step": 2645
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.96224799156189,
|
||
|
|
"epoch": 0.2403846153846154,
|
||
|
|
"grad_norm": 1.3203125,
|
||
|
|
"learning_rate": 0.0004997469954662933,
|
||
|
|
"loss": 5.8695,
|
||
|
|
"mean_token_accuracy": 0.14564383402466774,
|
||
|
|
"num_tokens": 5484697.0,
|
||
|
|
"step": 2650
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.851238155364991,
|
||
|
|
"epoch": 0.24083817126269957,
|
||
|
|
"grad_norm": 1.2734375,
|
||
|
|
"learning_rate": 0.0004997454591393097,
|
||
|
|
"loss": 5.8667,
|
||
|
|
"mean_token_accuracy": 0.1427861526608467,
|
||
|
|
"num_tokens": 5496433.0,
|
||
|
|
"step": 2655
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.973064804077149,
|
||
|
|
"epoch": 0.24129172714078376,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0004997439181645329,
|
||
|
|
"loss": 5.97,
|
||
|
|
"mean_token_accuracy": 0.14119771718978882,
|
||
|
|
"num_tokens": 5507917.0,
|
||
|
|
"step": 2660
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.047526073455811,
|
||
|
|
"epoch": 0.2417452830188679,
|
||
|
|
"grad_norm": 1.21875,
|
||
|
|
"learning_rate": 0.0004997423725419945,
|
||
|
|
"loss": 5.9544,
|
||
|
|
"mean_token_accuracy": 0.1415584534406662,
|
||
|
|
"num_tokens": 5519159.0,
|
||
|
|
"step": 2665
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.842634201049805,
|
||
|
|
"epoch": 0.2421988388969521,
|
||
|
|
"grad_norm": 1.3671875,
|
||
|
|
"learning_rate": 0.0004997408222717267,
|
||
|
|
"loss": 5.9242,
|
||
|
|
"mean_token_accuracy": 0.14665919542312622,
|
||
|
|
"num_tokens": 5529180.0,
|
||
|
|
"step": 2670
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.897845602035522,
|
||
|
|
"epoch": 0.24265239477503628,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.0004997392673537612,
|
||
|
|
"loss": 5.8381,
|
||
|
|
"mean_token_accuracy": 0.15111086070537566,
|
||
|
|
"num_tokens": 5539363.0,
|
||
|
|
"step": 2675
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.8370285987854,
|
||
|
|
"epoch": 0.24310595065312046,
|
||
|
|
"grad_norm": 1.234375,
|
||
|
|
"learning_rate": 0.0004997377077881306,
|
||
|
|
"loss": 5.946,
|
||
|
|
"mean_token_accuracy": 0.14330666437745093,
|
||
|
|
"num_tokens": 5549841.0,
|
||
|
|
"step": 2680
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.904944038391113,
|
||
|
|
"epoch": 0.24355950653120464,
|
||
|
|
"grad_norm": 1.1640625,
|
||
|
|
"learning_rate": 0.0004997361435748668,
|
||
|
|
"loss": 5.8349,
|
||
|
|
"mean_token_accuracy": 0.14796256124973298,
|
||
|
|
"num_tokens": 5560299.0,
|
||
|
|
"step": 2685
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.9934006690979,
|
||
|
|
"epoch": 0.24401306240928883,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 0.0004997345747140024,
|
||
|
|
"loss": 5.8923,
|
||
|
|
"mean_token_accuracy": 0.14425792098045348,
|
||
|
|
"num_tokens": 5571081.0,
|
||
|
|
"step": 2690
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.856541490554809,
|
||
|
|
"epoch": 0.244466618287373,
|
||
|
|
"grad_norm": 1.171875,
|
||
|
|
"learning_rate": 0.0004997330012055695,
|
||
|
|
"loss": 5.8447,
|
||
|
|
"mean_token_accuracy": 0.149576073884964,
|
||
|
|
"num_tokens": 5581389.0,
|
||
|
|
"step": 2695
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.9023360252380375,
|
||
|
|
"epoch": 0.2449201741654572,
|
||
|
|
"grad_norm": 1.265625,
|
||
|
|
"learning_rate": 0.0004997314230496011,
|
||
|
|
"loss": 5.8683,
|
||
|
|
"mean_token_accuracy": 0.14250419288873672,
|
||
|
|
"num_tokens": 5592347.0,
|
||
|
|
"step": 2700
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.878292608261108,
|
||
|
|
"epoch": 0.24537373004354138,
|
||
|
|
"grad_norm": 1.1796875,
|
||
|
|
"learning_rate": 0.0004997298402461296,
|
||
|
|
"loss": 5.8384,
|
||
|
|
"mean_token_accuracy": 0.14773763567209244,
|
||
|
|
"num_tokens": 5603411.0,
|
||
|
|
"step": 2705
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.920032787322998,
|
||
|
|
"epoch": 0.24582728592162553,
|
||
|
|
"grad_norm": 1.15625,
|
||
|
|
"learning_rate": 0.0004997282527951876,
|
||
|
|
"loss": 5.844,
|
||
|
|
"mean_token_accuracy": 0.14941513240337373,
|
||
|
|
"num_tokens": 5614615.0,
|
||
|
|
"step": 2710
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.869028520584107,
|
||
|
|
"epoch": 0.24628084179970972,
|
||
|
|
"grad_norm": 1.390625,
|
||
|
|
"learning_rate": 0.0004997266606968081,
|
||
|
|
"loss": 5.8137,
|
||
|
|
"mean_token_accuracy": 0.1474539414048195,
|
||
|
|
"num_tokens": 5624582.0,
|
||
|
|
"step": 2715
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.876409101486206,
|
||
|
|
"epoch": 0.2467343976777939,
|
||
|
|
"grad_norm": 1.2578125,
|
||
|
|
"learning_rate": 0.0004997250639510241,
|
||
|
|
"loss": 5.8213,
|
||
|
|
"mean_token_accuracy": 0.14212239235639573,
|
||
|
|
"num_tokens": 5634310.0,
|
||
|
|
"step": 2720
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.889693927764893,
|
||
|
|
"epoch": 0.24718795355587808,
|
||
|
|
"grad_norm": 1.328125,
|
||
|
|
"learning_rate": 0.0004997234625578684,
|
||
|
|
"loss": 5.9165,
|
||
|
|
"mean_token_accuracy": 0.14168269485235213,
|
||
|
|
"num_tokens": 5644018.0,
|
||
|
|
"step": 2725
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.872516393661499,
|
||
|
|
"epoch": 0.24764150943396226,
|
||
|
|
"grad_norm": 1.3125,
|
||
|
|
"learning_rate": 0.0004997218565173742,
|
||
|
|
"loss": 5.8501,
|
||
|
|
"mean_token_accuracy": 0.1477284774184227,
|
||
|
|
"num_tokens": 5653592.0,
|
||
|
|
"step": 2730
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.970296859741211,
|
||
|
|
"epoch": 0.24809506531204645,
|
||
|
|
"grad_norm": 1.3671875,
|
||
|
|
"learning_rate": 0.0004997202458295748,
|
||
|
|
"loss": 5.8983,
|
||
|
|
"mean_token_accuracy": 0.14910974949598313,
|
||
|
|
"num_tokens": 5662812.0,
|
||
|
|
"step": 2735
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.877613735198975,
|
||
|
|
"epoch": 0.24854862119013063,
|
||
|
|
"grad_norm": 1.140625,
|
||
|
|
"learning_rate": 0.0004997186304945034,
|
||
|
|
"loss": 5.8589,
|
||
|
|
"mean_token_accuracy": 0.14394548833370208,
|
||
|
|
"num_tokens": 5672939.0,
|
||
|
|
"step": 2740
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.869716453552246,
|
||
|
|
"epoch": 0.24900217706821481,
|
||
|
|
"grad_norm": 1.171875,
|
||
|
|
"learning_rate": 0.0004997170105121935,
|
||
|
|
"loss": 5.8577,
|
||
|
|
"mean_token_accuracy": 0.14621407687664031,
|
||
|
|
"num_tokens": 5683350.0,
|
||
|
|
"step": 2745
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.0468605041503904,
|
||
|
|
"epoch": 0.249455732946299,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.0004997153858826786,
|
||
|
|
"loss": 5.9484,
|
||
|
|
"mean_token_accuracy": 0.13753940612077714,
|
||
|
|
"num_tokens": 5694516.0,
|
||
|
|
"step": 2750
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.836617755889892,
|
||
|
|
"epoch": 0.24990928882438315,
|
||
|
|
"grad_norm": 1.203125,
|
||
|
|
"learning_rate": 0.0004997137566059922,
|
||
|
|
"loss": 5.7658,
|
||
|
|
"mean_token_accuracy": 0.1503409966826439,
|
||
|
|
"num_tokens": 5705443.0,
|
||
|
|
"step": 2755
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.8198834419250485,
|
||
|
|
"epoch": 0.25036284470246734,
|
||
|
|
"grad_norm": 1.234375,
|
||
|
|
"learning_rate": 0.0004997121226821681,
|
||
|
|
"loss": 5.8859,
|
||
|
|
"mean_token_accuracy": 0.13909180611371993,
|
||
|
|
"num_tokens": 5715933.0,
|
||
|
|
"step": 2760
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.972828674316406,
|
||
|
|
"epoch": 0.25081640058055155,
|
||
|
|
"grad_norm": 1.2578125,
|
||
|
|
"learning_rate": 0.00049971048411124,
|
||
|
|
"loss": 5.9315,
|
||
|
|
"mean_token_accuracy": 0.1365823417901993,
|
||
|
|
"num_tokens": 5726630.0,
|
||
|
|
"step": 2765
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.025601530075074,
|
||
|
|
"epoch": 0.2512699564586357,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 0.0004997088408932418,
|
||
|
|
"loss": 5.8606,
|
||
|
|
"mean_token_accuracy": 0.14626222401857375,
|
||
|
|
"num_tokens": 5736890.0,
|
||
|
|
"step": 2770
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.7838927745819095,
|
||
|
|
"epoch": 0.25172351233671986,
|
||
|
|
"grad_norm": 1.2265625,
|
||
|
|
"learning_rate": 0.0004997071930282076,
|
||
|
|
"loss": 5.7814,
|
||
|
|
"mean_token_accuracy": 0.15587268024683,
|
||
|
|
"num_tokens": 5747042.0,
|
||
|
|
"step": 2775
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.836866760253907,
|
||
|
|
"epoch": 0.25217706821480407,
|
||
|
|
"grad_norm": 1.3359375,
|
||
|
|
"learning_rate": 0.0004997055405161712,
|
||
|
|
"loss": 5.904,
|
||
|
|
"mean_token_accuracy": 0.14357635378837585,
|
||
|
|
"num_tokens": 5757367.0,
|
||
|
|
"step": 2780
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.944021129608155,
|
||
|
|
"epoch": 0.2526306240928882,
|
||
|
|
"grad_norm": 1.1953125,
|
||
|
|
"learning_rate": 0.0004997038833571671,
|
||
|
|
"loss": 5.9615,
|
||
|
|
"mean_token_accuracy": 0.1422647625207901,
|
||
|
|
"num_tokens": 5769557.0,
|
||
|
|
"step": 2785
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.940666151046753,
|
||
|
|
"epoch": 0.25308417997097243,
|
||
|
|
"grad_norm": 1.34375,
|
||
|
|
"learning_rate": 0.0004997022215512295,
|
||
|
|
"loss": 5.8503,
|
||
|
|
"mean_token_accuracy": 0.15143156200647354,
|
||
|
|
"num_tokens": 5780615.0,
|
||
|
|
"step": 2790
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.937691497802734,
|
||
|
|
"epoch": 0.2535377358490566,
|
||
|
|
"grad_norm": 1.15625,
|
||
|
|
"learning_rate": 0.0004997005550983925,
|
||
|
|
"loss": 5.827,
|
||
|
|
"mean_token_accuracy": 0.14720471799373627,
|
||
|
|
"num_tokens": 5791271.0,
|
||
|
|
"step": 2795
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.830975341796875,
|
||
|
|
"epoch": 0.2539912917271408,
|
||
|
|
"grad_norm": 1.3046875,
|
||
|
|
"learning_rate": 0.000499698883998691,
|
||
|
|
"loss": 5.7719,
|
||
|
|
"mean_token_accuracy": 0.14439669102430344,
|
||
|
|
"num_tokens": 5801117.0,
|
||
|
|
"step": 2800
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.828149271011353,
|
||
|
|
"epoch": 0.25444484760522496,
|
||
|
|
"grad_norm": 1.2734375,
|
||
|
|
"learning_rate": 0.0004996972082521591,
|
||
|
|
"loss": 5.7958,
|
||
|
|
"mean_token_accuracy": 0.1420363336801529,
|
||
|
|
"num_tokens": 5811696.0,
|
||
|
|
"step": 2805
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.868321561813355,
|
||
|
|
"epoch": 0.25489840348330917,
|
||
|
|
"grad_norm": 1.25,
|
||
|
|
"learning_rate": 0.0004996955278588319,
|
||
|
|
"loss": 5.8318,
|
||
|
|
"mean_token_accuracy": 0.15537209510803224,
|
||
|
|
"num_tokens": 5822207.0,
|
||
|
|
"step": 2810
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.808701229095459,
|
||
|
|
"epoch": 0.2553519593613933,
|
||
|
|
"grad_norm": 1.4921875,
|
||
|
|
"learning_rate": 0.0004996938428187437,
|
||
|
|
"loss": 5.7714,
|
||
|
|
"mean_token_accuracy": 0.15279726982116698,
|
||
|
|
"num_tokens": 5831927.0,
|
||
|
|
"step": 2815
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.886981678009033,
|
||
|
|
"epoch": 0.2558055152394775,
|
||
|
|
"grad_norm": 1.1875,
|
||
|
|
"learning_rate": 0.0004996921531319297,
|
||
|
|
"loss": 5.8415,
|
||
|
|
"mean_token_accuracy": 0.14455378502607347,
|
||
|
|
"num_tokens": 5842093.0,
|
||
|
|
"step": 2820
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.86587119102478,
|
||
|
|
"epoch": 0.2562590711175617,
|
||
|
|
"grad_norm": 1.34375,
|
||
|
|
"learning_rate": 0.0004996904587984246,
|
||
|
|
"loss": 5.7803,
|
||
|
|
"mean_token_accuracy": 0.15339562743902208,
|
||
|
|
"num_tokens": 5850551.0,
|
||
|
|
"step": 2825
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.764548873901367,
|
||
|
|
"epoch": 0.25671262699564584,
|
||
|
|
"grad_norm": 1.3046875,
|
||
|
|
"learning_rate": 0.0004996887598182636,
|
||
|
|
"loss": 5.7714,
|
||
|
|
"mean_token_accuracy": 0.1484563708305359,
|
||
|
|
"num_tokens": 5860651.0,
|
||
|
|
"step": 2830
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.840695333480835,
|
||
|
|
"epoch": 0.25716618287373005,
|
||
|
|
"grad_norm": 1.2734375,
|
||
|
|
"learning_rate": 0.0004996870561914819,
|
||
|
|
"loss": 5.7878,
|
||
|
|
"mean_token_accuracy": 0.14319953173398972,
|
||
|
|
"num_tokens": 5871500.0,
|
||
|
|
"step": 2835
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.857464742660523,
|
||
|
|
"epoch": 0.2576197387518142,
|
||
|
|
"grad_norm": 1.1640625,
|
||
|
|
"learning_rate": 0.0004996853479181145,
|
||
|
|
"loss": 5.7638,
|
||
|
|
"mean_token_accuracy": 0.1445399969816208,
|
||
|
|
"num_tokens": 5881523.0,
|
||
|
|
"step": 2840
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.928007984161377,
|
||
|
|
"epoch": 0.2580732946298984,
|
||
|
|
"grad_norm": 1.2578125,
|
||
|
|
"learning_rate": 0.0004996836349981969,
|
||
|
|
"loss": 5.9088,
|
||
|
|
"mean_token_accuracy": 0.14473725184798242,
|
||
|
|
"num_tokens": 5891162.0,
|
||
|
|
"step": 2845
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.846505928039551,
|
||
|
|
"epoch": 0.2585268505079826,
|
||
|
|
"grad_norm": 1.3828125,
|
||
|
|
"learning_rate": 0.0004996819174317645,
|
||
|
|
"loss": 5.7977,
|
||
|
|
"mean_token_accuracy": 0.14666571021080016,
|
||
|
|
"num_tokens": 5901818.0,
|
||
|
|
"step": 2850
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.829140758514404,
|
||
|
|
"epoch": 0.2589804063860668,
|
||
|
|
"grad_norm": 1.296875,
|
||
|
|
"learning_rate": 0.0004996801952188528,
|
||
|
|
"loss": 5.895,
|
||
|
|
"mean_token_accuracy": 0.14497522860765458,
|
||
|
|
"num_tokens": 5913889.0,
|
||
|
|
"step": 2855
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.888280963897705,
|
||
|
|
"epoch": 0.25943396226415094,
|
||
|
|
"grad_norm": 1.328125,
|
||
|
|
"learning_rate": 0.0004996784683594973,
|
||
|
|
"loss": 5.8485,
|
||
|
|
"mean_token_accuracy": 0.14567365497350693,
|
||
|
|
"num_tokens": 5923429.0,
|
||
|
|
"step": 2860
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.998221731185913,
|
||
|
|
"epoch": 0.2598875181422351,
|
||
|
|
"grad_norm": 1.3125,
|
||
|
|
"learning_rate": 0.0004996767368537338,
|
||
|
|
"loss": 5.8844,
|
||
|
|
"mean_token_accuracy": 0.14624838829040526,
|
||
|
|
"num_tokens": 5933847.0,
|
||
|
|
"step": 2865
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.8100090503692625,
|
||
|
|
"epoch": 0.2603410740203193,
|
||
|
|
"grad_norm": 1.1953125,
|
||
|
|
"learning_rate": 0.0004996750007015983,
|
||
|
|
"loss": 5.7683,
|
||
|
|
"mean_token_accuracy": 0.14520363360643387,
|
||
|
|
"num_tokens": 5943874.0,
|
||
|
|
"step": 2870
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.848591136932373,
|
||
|
|
"epoch": 0.26079462989840346,
|
||
|
|
"grad_norm": 1.1875,
|
||
|
|
"learning_rate": 0.0004996732599031264,
|
||
|
|
"loss": 5.8297,
|
||
|
|
"mean_token_accuracy": 0.14542661756277084,
|
||
|
|
"num_tokens": 5953653.0,
|
||
|
|
"step": 2875
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.917650747299194,
|
||
|
|
"epoch": 0.2612481857764877,
|
||
|
|
"grad_norm": 1.265625,
|
||
|
|
"learning_rate": 0.0004996715144583543,
|
||
|
|
"loss": 5.7734,
|
||
|
|
"mean_token_accuracy": 0.14755018949508666,
|
||
|
|
"num_tokens": 5964039.0,
|
||
|
|
"step": 2880
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.900532245635986,
|
||
|
|
"epoch": 0.26170174165457183,
|
||
|
|
"grad_norm": 1.2265625,
|
||
|
|
"learning_rate": 0.000499669764367318,
|
||
|
|
"loss": 5.9012,
|
||
|
|
"mean_token_accuracy": 0.14746888726949692,
|
||
|
|
"num_tokens": 5974083.0,
|
||
|
|
"step": 2885
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.8273969173431395,
|
||
|
|
"epoch": 0.26215529753265604,
|
||
|
|
"grad_norm": 1.25,
|
||
|
|
"learning_rate": 0.0004996680096300537,
|
||
|
|
"loss": 5.8462,
|
||
|
|
"mean_token_accuracy": 0.14346672594547272,
|
||
|
|
"num_tokens": 5984629.0,
|
||
|
|
"step": 2890
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.839718961715699,
|
||
|
|
"epoch": 0.2626088534107402,
|
||
|
|
"grad_norm": 1.5,
|
||
|
|
"learning_rate": 0.0004996662502465978,
|
||
|
|
"loss": 5.7524,
|
||
|
|
"mean_token_accuracy": 0.16117057502269744,
|
||
|
|
"num_tokens": 5994295.0,
|
||
|
|
"step": 2895
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.838645267486572,
|
||
|
|
"epoch": 0.2630624092888244,
|
||
|
|
"grad_norm": 1.1953125,
|
||
|
|
"learning_rate": 0.0004996644862169864,
|
||
|
|
"loss": 5.7866,
|
||
|
|
"mean_token_accuracy": 0.14446460008621215,
|
||
|
|
"num_tokens": 6004156.0,
|
||
|
|
"step": 2900
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.901477813720703,
|
||
|
|
"epoch": 0.26351596516690856,
|
||
|
|
"grad_norm": 1.28125,
|
||
|
|
"learning_rate": 0.0004996627175412563,
|
||
|
|
"loss": 5.8837,
|
||
|
|
"mean_token_accuracy": 0.14486180245876312,
|
||
|
|
"num_tokens": 6014188.0,
|
||
|
|
"step": 2905
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.949041032791138,
|
||
|
|
"epoch": 0.2639695210449927,
|
||
|
|
"grad_norm": 1.21875,
|
||
|
|
"learning_rate": 0.000499660944219444,
|
||
|
|
"loss": 5.9405,
|
||
|
|
"mean_token_accuracy": 0.1410454109311104,
|
||
|
|
"num_tokens": 6024879.0,
|
||
|
|
"step": 2910
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.967418909072876,
|
||
|
|
"epoch": 0.2644230769230769,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.0004996591662515861,
|
||
|
|
"loss": 5.9944,
|
||
|
|
"mean_token_accuracy": 0.13865989670157433,
|
||
|
|
"num_tokens": 6036374.0,
|
||
|
|
"step": 2915
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.901403713226318,
|
||
|
|
"epoch": 0.2648766328011611,
|
||
|
|
"grad_norm": 1.3671875,
|
||
|
|
"learning_rate": 0.0004996573836377193,
|
||
|
|
"loss": 5.8373,
|
||
|
|
"mean_token_accuracy": 0.14499613642692566,
|
||
|
|
"num_tokens": 6046432.0,
|
||
|
|
"step": 2920
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.943468523025513,
|
||
|
|
"epoch": 0.2653301886792453,
|
||
|
|
"grad_norm": 1.2890625,
|
||
|
|
"learning_rate": 0.0004996555963778806,
|
||
|
|
"loss": 5.8592,
|
||
|
|
"mean_token_accuracy": 0.14138642624020575,
|
||
|
|
"num_tokens": 6056864.0,
|
||
|
|
"step": 2925
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.995022583007812,
|
||
|
|
"epoch": 0.26578374455732945,
|
||
|
|
"grad_norm": 1.3671875,
|
||
|
|
"learning_rate": 0.000499653804472107,
|
||
|
|
"loss": 5.8844,
|
||
|
|
"mean_token_accuracy": 0.15080390572547914,
|
||
|
|
"num_tokens": 6067294.0,
|
||
|
|
"step": 2930
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.905005168914795,
|
||
|
|
"epoch": 0.26623730043541366,
|
||
|
|
"grad_norm": 1.3671875,
|
||
|
|
"learning_rate": 0.0004996520079204353,
|
||
|
|
"loss": 5.8871,
|
||
|
|
"mean_token_accuracy": 0.14075151458382607,
|
||
|
|
"num_tokens": 6077587.0,
|
||
|
|
"step": 2935
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.918993663787842,
|
||
|
|
"epoch": 0.2666908563134978,
|
||
|
|
"grad_norm": 1.28125,
|
||
|
|
"learning_rate": 0.000499650206722903,
|
||
|
|
"loss": 5.8385,
|
||
|
|
"mean_token_accuracy": 0.14215887933969498,
|
||
|
|
"num_tokens": 6089306.0,
|
||
|
|
"step": 2940
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.827713394165039,
|
||
|
|
"epoch": 0.267144412191582,
|
||
|
|
"grad_norm": 1.578125,
|
||
|
|
"learning_rate": 0.0004996484008795471,
|
||
|
|
"loss": 5.7875,
|
||
|
|
"mean_token_accuracy": 0.1460879400372505,
|
||
|
|
"num_tokens": 6099651.0,
|
||
|
|
"step": 2945
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.838403844833374,
|
||
|
|
"epoch": 0.2675979680696662,
|
||
|
|
"grad_norm": 1.34375,
|
||
|
|
"learning_rate": 0.000499646590390405,
|
||
|
|
"loss": 5.7932,
|
||
|
|
"mean_token_accuracy": 0.14292585104703903,
|
||
|
|
"num_tokens": 6110063.0,
|
||
|
|
"step": 2950
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.874997091293335,
|
||
|
|
"epoch": 0.26805152394775034,
|
||
|
|
"grad_norm": 1.234375,
|
||
|
|
"learning_rate": 0.0004996447752555142,
|
||
|
|
"loss": 5.8194,
|
||
|
|
"mean_token_accuracy": 0.1502259336411953,
|
||
|
|
"num_tokens": 6120031.0,
|
||
|
|
"step": 2955
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.802283811569214,
|
||
|
|
"epoch": 0.26850507982583455,
|
||
|
|
"grad_norm": 1.171875,
|
||
|
|
"learning_rate": 0.0004996429554749122,
|
||
|
|
"loss": 5.8655,
|
||
|
|
"mean_token_accuracy": 0.15023885816335678,
|
||
|
|
"num_tokens": 6131274.0,
|
||
|
|
"step": 2960
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.964536857604981,
|
||
|
|
"epoch": 0.2689586357039187,
|
||
|
|
"grad_norm": 1.2109375,
|
||
|
|
"learning_rate": 0.0004996411310486367,
|
||
|
|
"loss": 5.8932,
|
||
|
|
"mean_token_accuracy": 0.1471738301217556,
|
||
|
|
"num_tokens": 6140878.0,
|
||
|
|
"step": 2965
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.937205791473389,
|
||
|
|
"epoch": 0.2694121915820029,
|
||
|
|
"grad_norm": 1.1875,
|
||
|
|
"learning_rate": 0.0004996393019767253,
|
||
|
|
"loss": 5.8875,
|
||
|
|
"mean_token_accuracy": 0.14035830050706863,
|
||
|
|
"num_tokens": 6152229.0,
|
||
|
|
"step": 2970
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.76689043045044,
|
||
|
|
"epoch": 0.26986574746008707,
|
||
|
|
"grad_norm": 1.5703125,
|
||
|
|
"learning_rate": 0.0004996374682592158,
|
||
|
|
"loss": 5.7879,
|
||
|
|
"mean_token_accuracy": 0.14796984195709229,
|
||
|
|
"num_tokens": 6162311.0,
|
||
|
|
"step": 2975
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.934810733795166,
|
||
|
|
"epoch": 0.2703193033381713,
|
||
|
|
"grad_norm": 1.2890625,
|
||
|
|
"learning_rate": 0.0004996356298961463,
|
||
|
|
"loss": 5.9202,
|
||
|
|
"mean_token_accuracy": 0.14373642206192017,
|
||
|
|
"num_tokens": 6172806.0,
|
||
|
|
"step": 2980
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.891864681243897,
|
||
|
|
"epoch": 0.27077285921625543,
|
||
|
|
"grad_norm": 1.359375,
|
||
|
|
"learning_rate": 0.0004996337868875549,
|
||
|
|
"loss": 5.879,
|
||
|
|
"mean_token_accuracy": 0.14369452446699144,
|
||
|
|
"num_tokens": 6183479.0,
|
||
|
|
"step": 2985
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.89184536933899,
|
||
|
|
"epoch": 0.27122641509433965,
|
||
|
|
"grad_norm": 1.2421875,
|
||
|
|
"learning_rate": 0.0004996319392334792,
|
||
|
|
"loss": 5.8281,
|
||
|
|
"mean_token_accuracy": 0.14598268270492554,
|
||
|
|
"num_tokens": 6194201.0,
|
||
|
|
"step": 2990
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.824180364608765,
|
||
|
|
"epoch": 0.2716799709724238,
|
||
|
|
"grad_norm": 1.2734375,
|
||
|
|
"learning_rate": 0.000499630086933958,
|
||
|
|
"loss": 5.7868,
|
||
|
|
"mean_token_accuracy": 0.14525872468948364,
|
||
|
|
"num_tokens": 6204774.0,
|
||
|
|
"step": 2995
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.86897759437561,
|
||
|
|
"epoch": 0.27213352685050796,
|
||
|
|
"grad_norm": 1.34375,
|
||
|
|
"learning_rate": 0.0004996282299890292,
|
||
|
|
"loss": 5.7866,
|
||
|
|
"mean_token_accuracy": 0.1425388991832733,
|
||
|
|
"num_tokens": 6215056.0,
|
||
|
|
"step": 3000
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.27213352685050796,
|
||
|
|
"eval_entropy": 5.760963649555569,
|
||
|
|
"eval_loss": 5.879345417022705,
|
||
|
|
"eval_mean_token_accuracy": 0.15095411169330053,
|
||
|
|
"eval_num_tokens": 6215056.0,
|
||
|
|
"eval_runtime": 26.6633,
|
||
|
|
"eval_samples_per_second": 1326.167,
|
||
|
|
"eval_steps_per_second": 165.771,
|
||
|
|
"step": 3000
|
||
|
|
}
|
||
|
|
],
|
||
|
|
"logging_steps": 5,
|
||
|
|
"max_steps": 110230,
|
||
|
|
"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": 9028611385344000.0,
|
||
|
|
"train_batch_size": 16,
|
||
|
|
"trial_name": null,
|
||
|
|
"trial_params": null
|
||
|
|
}
|