d4d3ca317e
Model: fpadovani/eng-latn-100mb-after-ppt-Dp-100mb-ckpt500_seed10 Source: Original Platform
6046 lines
164 KiB
JSON
6046 lines
164 KiB
JSON
{
|
|
"best_global_step": null,
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 0.3369461447745269,
|
|
"eval_steps": 3000,
|
|
"global_step": 3000,
|
|
"is_hyper_param_search": false,
|
|
"is_local_process_zero": true,
|
|
"is_world_process_zero": true,
|
|
"log_history": [
|
|
{
|
|
"entropy": 6.9715465068817135,
|
|
"epoch": 0.0005615769079575448,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 2e-06,
|
|
"loss": 6.5009,
|
|
"mean_token_accuracy": 0.12504197284579277,
|
|
"num_tokens": 10897.0,
|
|
"step": 5
|
|
},
|
|
{
|
|
"entropy": 7.049736070632934,
|
|
"epoch": 0.0011231538159150896,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 4.5e-06,
|
|
"loss": 6.7123,
|
|
"mean_token_accuracy": 0.11760373637080193,
|
|
"num_tokens": 23084.0,
|
|
"step": 10
|
|
},
|
|
{
|
|
"entropy": 6.9343400478363035,
|
|
"epoch": 0.0016847307238726343,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 7e-06,
|
|
"loss": 6.5938,
|
|
"mean_token_accuracy": 0.12289839833974839,
|
|
"num_tokens": 35810.0,
|
|
"step": 15
|
|
},
|
|
{
|
|
"entropy": 6.872401380538941,
|
|
"epoch": 0.0022463076318301792,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 9.5e-06,
|
|
"loss": 6.5266,
|
|
"mean_token_accuracy": 0.12619762793183326,
|
|
"num_tokens": 46019.0,
|
|
"step": 20
|
|
},
|
|
{
|
|
"entropy": 6.928314447402954,
|
|
"epoch": 0.002807884539787724,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 1.2e-05,
|
|
"loss": 6.7033,
|
|
"mean_token_accuracy": 0.12512994706630706,
|
|
"num_tokens": 57272.0,
|
|
"step": 25
|
|
},
|
|
{
|
|
"entropy": 6.887799406051636,
|
|
"epoch": 0.0033694614477452686,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 1.4500000000000002e-05,
|
|
"loss": 6.6137,
|
|
"mean_token_accuracy": 0.12870856747031212,
|
|
"num_tokens": 68686.0,
|
|
"step": 30
|
|
},
|
|
{
|
|
"entropy": 6.7613860130310055,
|
|
"epoch": 0.003931038355702813,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 1.7000000000000003e-05,
|
|
"loss": 6.6104,
|
|
"mean_token_accuracy": 0.12690498679876328,
|
|
"num_tokens": 79187.0,
|
|
"step": 35
|
|
},
|
|
{
|
|
"entropy": 6.846365690231323,
|
|
"epoch": 0.0044926152636603585,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 1.95e-05,
|
|
"loss": 6.6592,
|
|
"mean_token_accuracy": 0.12534694746136665,
|
|
"num_tokens": 90293.0,
|
|
"step": 40
|
|
},
|
|
{
|
|
"entropy": 6.876943588256836,
|
|
"epoch": 0.005054192171617903,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 2.2e-05,
|
|
"loss": 6.5845,
|
|
"mean_token_accuracy": 0.1326958194375038,
|
|
"num_tokens": 100420.0,
|
|
"step": 45
|
|
},
|
|
{
|
|
"entropy": 6.864708757400512,
|
|
"epoch": 0.005615769079575448,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 2.4500000000000003e-05,
|
|
"loss": 6.5891,
|
|
"mean_token_accuracy": 0.12609511613845825,
|
|
"num_tokens": 111198.0,
|
|
"step": 50
|
|
},
|
|
{
|
|
"entropy": 6.86231632232666,
|
|
"epoch": 0.006177345987532993,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 2.7e-05,
|
|
"loss": 6.7008,
|
|
"mean_token_accuracy": 0.12189886942505837,
|
|
"num_tokens": 124723.0,
|
|
"step": 55
|
|
},
|
|
{
|
|
"entropy": 6.8431285381317135,
|
|
"epoch": 0.006738922895490537,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 2.95e-05,
|
|
"loss": 6.6151,
|
|
"mean_token_accuracy": 0.12724459022283555,
|
|
"num_tokens": 136366.0,
|
|
"step": 60
|
|
},
|
|
{
|
|
"entropy": 6.854820919036865,
|
|
"epoch": 0.007300499803448083,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 3.2e-05,
|
|
"loss": 6.5486,
|
|
"mean_token_accuracy": 0.1308780401945114,
|
|
"num_tokens": 146536.0,
|
|
"step": 65
|
|
},
|
|
{
|
|
"entropy": 6.873655176162719,
|
|
"epoch": 0.007862076711405626,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 3.4500000000000005e-05,
|
|
"loss": 6.6367,
|
|
"mean_token_accuracy": 0.13169211596250535,
|
|
"num_tokens": 157005.0,
|
|
"step": 70
|
|
},
|
|
{
|
|
"entropy": 6.878752136230469,
|
|
"epoch": 0.008423653619363172,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 3.7e-05,
|
|
"loss": 6.7055,
|
|
"mean_token_accuracy": 0.1302464373409748,
|
|
"num_tokens": 167864.0,
|
|
"step": 75
|
|
},
|
|
{
|
|
"entropy": 6.8558965682983395,
|
|
"epoch": 0.008985230527320717,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 3.95e-05,
|
|
"loss": 6.5699,
|
|
"mean_token_accuracy": 0.12809699773788452,
|
|
"num_tokens": 179635.0,
|
|
"step": 80
|
|
},
|
|
{
|
|
"entropy": 6.8296217918396,
|
|
"epoch": 0.00954680743527826,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 4.2000000000000004e-05,
|
|
"loss": 6.6094,
|
|
"mean_token_accuracy": 0.12677174359560012,
|
|
"num_tokens": 190614.0,
|
|
"step": 85
|
|
},
|
|
{
|
|
"entropy": 6.814341592788696,
|
|
"epoch": 0.010108384343235806,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 4.45e-05,
|
|
"loss": 6.5818,
|
|
"mean_token_accuracy": 0.12706689015030861,
|
|
"num_tokens": 201496.0,
|
|
"step": 90
|
|
},
|
|
{
|
|
"entropy": 6.866008996963501,
|
|
"epoch": 0.010669961251193351,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 4.7000000000000004e-05,
|
|
"loss": 6.5635,
|
|
"mean_token_accuracy": 0.13106250390410423,
|
|
"num_tokens": 211606.0,
|
|
"step": 95
|
|
},
|
|
{
|
|
"entropy": 6.757302713394165,
|
|
"epoch": 0.011231538159150897,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 4.9500000000000004e-05,
|
|
"loss": 6.5545,
|
|
"mean_token_accuracy": 0.12546624690294267,
|
|
"num_tokens": 223503.0,
|
|
"step": 100
|
|
},
|
|
{
|
|
"entropy": 6.679348611831665,
|
|
"epoch": 0.01179311506710844,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 5.2e-05,
|
|
"loss": 6.5318,
|
|
"mean_token_accuracy": 0.1324719898402691,
|
|
"num_tokens": 234744.0,
|
|
"step": 105
|
|
},
|
|
{
|
|
"entropy": 6.899774217605591,
|
|
"epoch": 0.012354691975065986,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 5.45e-05,
|
|
"loss": 6.6481,
|
|
"mean_token_accuracy": 0.12616777494549752,
|
|
"num_tokens": 247663.0,
|
|
"step": 110
|
|
},
|
|
{
|
|
"entropy": 6.789312171936035,
|
|
"epoch": 0.012916268883023531,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 5.7e-05,
|
|
"loss": 6.5751,
|
|
"mean_token_accuracy": 0.1263405404984951,
|
|
"num_tokens": 260326.0,
|
|
"step": 115
|
|
},
|
|
{
|
|
"entropy": 6.808723449707031,
|
|
"epoch": 0.013477845790981074,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 5.9499999999999996e-05,
|
|
"loss": 6.4864,
|
|
"mean_token_accuracy": 0.1300912842154503,
|
|
"num_tokens": 271568.0,
|
|
"step": 120
|
|
},
|
|
{
|
|
"entropy": 6.786760902404785,
|
|
"epoch": 0.01403942269893862,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 6.2e-05,
|
|
"loss": 6.4907,
|
|
"mean_token_accuracy": 0.13793076798319817,
|
|
"num_tokens": 282651.0,
|
|
"step": 125
|
|
},
|
|
{
|
|
"entropy": 6.70629243850708,
|
|
"epoch": 0.014600999606896165,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 6.450000000000001e-05,
|
|
"loss": 6.3861,
|
|
"mean_token_accuracy": 0.13955857902765273,
|
|
"num_tokens": 292753.0,
|
|
"step": 130
|
|
},
|
|
{
|
|
"entropy": 6.774137878417969,
|
|
"epoch": 0.015162576514853709,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 6.7e-05,
|
|
"loss": 6.5303,
|
|
"mean_token_accuracy": 0.1323573298752308,
|
|
"num_tokens": 302981.0,
|
|
"step": 135
|
|
},
|
|
{
|
|
"entropy": 6.851047706604004,
|
|
"epoch": 0.015724153422811252,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 6.950000000000001e-05,
|
|
"loss": 6.6127,
|
|
"mean_token_accuracy": 0.12808732613921164,
|
|
"num_tokens": 314461.0,
|
|
"step": 140
|
|
},
|
|
{
|
|
"entropy": 6.8475244522094725,
|
|
"epoch": 0.0162857303307688,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 7.2e-05,
|
|
"loss": 6.6439,
|
|
"mean_token_accuracy": 0.1281725898385048,
|
|
"num_tokens": 326877.0,
|
|
"step": 145
|
|
},
|
|
{
|
|
"entropy": 6.798589849472046,
|
|
"epoch": 0.016847307238726343,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 7.45e-05,
|
|
"loss": 6.486,
|
|
"mean_token_accuracy": 0.12972471341490746,
|
|
"num_tokens": 337831.0,
|
|
"step": 150
|
|
},
|
|
{
|
|
"entropy": 6.802658319473267,
|
|
"epoch": 0.017408884146683887,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 7.7e-05,
|
|
"loss": 6.4452,
|
|
"mean_token_accuracy": 0.13188212886452674,
|
|
"num_tokens": 348233.0,
|
|
"step": 155
|
|
},
|
|
{
|
|
"entropy": 6.666369390487671,
|
|
"epoch": 0.017970461054641434,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 7.950000000000001e-05,
|
|
"loss": 6.3958,
|
|
"mean_token_accuracy": 0.13498541787266732,
|
|
"num_tokens": 359113.0,
|
|
"step": 160
|
|
},
|
|
{
|
|
"entropy": 6.8577258586883545,
|
|
"epoch": 0.018532037962598977,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 8.2e-05,
|
|
"loss": 6.5486,
|
|
"mean_token_accuracy": 0.13562301099300383,
|
|
"num_tokens": 370284.0,
|
|
"step": 165
|
|
},
|
|
{
|
|
"entropy": 6.831363582611084,
|
|
"epoch": 0.01909361487055652,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 8.450000000000001e-05,
|
|
"loss": 6.6247,
|
|
"mean_token_accuracy": 0.12740110382437705,
|
|
"num_tokens": 381415.0,
|
|
"step": 170
|
|
},
|
|
{
|
|
"entropy": 6.940152168273926,
|
|
"epoch": 0.019655191778514068,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 8.7e-05,
|
|
"loss": 6.5445,
|
|
"mean_token_accuracy": 0.1410522811114788,
|
|
"num_tokens": 392080.0,
|
|
"step": 175
|
|
},
|
|
{
|
|
"entropy": 6.750535249710083,
|
|
"epoch": 0.020216768686471612,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 8.95e-05,
|
|
"loss": 6.5776,
|
|
"mean_token_accuracy": 0.12494335547089577,
|
|
"num_tokens": 402551.0,
|
|
"step": 180
|
|
},
|
|
{
|
|
"entropy": 6.859799718856811,
|
|
"epoch": 0.020778345594429155,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 9.2e-05,
|
|
"loss": 6.5809,
|
|
"mean_token_accuracy": 0.12796007245779037,
|
|
"num_tokens": 414670.0,
|
|
"step": 185
|
|
},
|
|
{
|
|
"entropy": 6.842173910140991,
|
|
"epoch": 0.021339922502386702,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 9.45e-05,
|
|
"loss": 6.6053,
|
|
"mean_token_accuracy": 0.1283198118209839,
|
|
"num_tokens": 427162.0,
|
|
"step": 190
|
|
},
|
|
{
|
|
"entropy": 6.696497917175293,
|
|
"epoch": 0.021901499410344246,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 9.7e-05,
|
|
"loss": 6.4728,
|
|
"mean_token_accuracy": 0.12769378274679183,
|
|
"num_tokens": 438628.0,
|
|
"step": 195
|
|
},
|
|
{
|
|
"entropy": 6.769975423812866,
|
|
"epoch": 0.022463076318301793,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 9.95e-05,
|
|
"loss": 6.4425,
|
|
"mean_token_accuracy": 0.1354153960943222,
|
|
"num_tokens": 449248.0,
|
|
"step": 200
|
|
},
|
|
{
|
|
"entropy": 6.633104753494263,
|
|
"epoch": 0.023024653226259337,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000102,
|
|
"loss": 6.4247,
|
|
"mean_token_accuracy": 0.13229422345757486,
|
|
"num_tokens": 460815.0,
|
|
"step": 205
|
|
},
|
|
{
|
|
"entropy": 6.824441957473755,
|
|
"epoch": 0.02358623013421688,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00010449999999999999,
|
|
"loss": 6.6504,
|
|
"mean_token_accuracy": 0.12349236905574798,
|
|
"num_tokens": 471972.0,
|
|
"step": 210
|
|
},
|
|
{
|
|
"entropy": 6.949941158294678,
|
|
"epoch": 0.024147807042174427,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000107,
|
|
"loss": 6.577,
|
|
"mean_token_accuracy": 0.13404853641986847,
|
|
"num_tokens": 482775.0,
|
|
"step": 215
|
|
},
|
|
{
|
|
"entropy": 6.768435144424439,
|
|
"epoch": 0.02470938395013197,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0001095,
|
|
"loss": 6.5225,
|
|
"mean_token_accuracy": 0.13128132298588752,
|
|
"num_tokens": 495151.0,
|
|
"step": 220
|
|
},
|
|
{
|
|
"entropy": 6.803989410400391,
|
|
"epoch": 0.025270960858089515,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000112,
|
|
"loss": 6.5203,
|
|
"mean_token_accuracy": 0.13371702432632446,
|
|
"num_tokens": 506947.0,
|
|
"step": 225
|
|
},
|
|
{
|
|
"entropy": 6.785508298873902,
|
|
"epoch": 0.025832537766047062,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0001145,
|
|
"loss": 6.5712,
|
|
"mean_token_accuracy": 0.1285259947180748,
|
|
"num_tokens": 519153.0,
|
|
"step": 230
|
|
},
|
|
{
|
|
"entropy": 6.7967840194702145,
|
|
"epoch": 0.026394114674004605,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00011700000000000001,
|
|
"loss": 6.5665,
|
|
"mean_token_accuracy": 0.1290400132536888,
|
|
"num_tokens": 531050.0,
|
|
"step": 235
|
|
},
|
|
{
|
|
"entropy": 6.792671823501587,
|
|
"epoch": 0.02695569158196215,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00011949999999999999,
|
|
"loss": 6.505,
|
|
"mean_token_accuracy": 0.12736395224928856,
|
|
"num_tokens": 542744.0,
|
|
"step": 240
|
|
},
|
|
{
|
|
"entropy": 6.795737361907959,
|
|
"epoch": 0.027517268489919696,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000122,
|
|
"loss": 6.6051,
|
|
"mean_token_accuracy": 0.12416600063443184,
|
|
"num_tokens": 554748.0,
|
|
"step": 245
|
|
},
|
|
{
|
|
"entropy": 6.864370918273925,
|
|
"epoch": 0.02807884539787724,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0001245,
|
|
"loss": 6.53,
|
|
"mean_token_accuracy": 0.13027690425515176,
|
|
"num_tokens": 564868.0,
|
|
"step": 250
|
|
},
|
|
{
|
|
"entropy": 6.807267904281616,
|
|
"epoch": 0.028640422305834783,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.000127,
|
|
"loss": 6.5181,
|
|
"mean_token_accuracy": 0.1389558993279934,
|
|
"num_tokens": 575668.0,
|
|
"step": 255
|
|
},
|
|
{
|
|
"entropy": 6.819407367706299,
|
|
"epoch": 0.02920199921379233,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0001295,
|
|
"loss": 6.6849,
|
|
"mean_token_accuracy": 0.12314404994249344,
|
|
"num_tokens": 587956.0,
|
|
"step": 260
|
|
},
|
|
{
|
|
"entropy": 6.897285461425781,
|
|
"epoch": 0.029763576121749874,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.000132,
|
|
"loss": 6.5222,
|
|
"mean_token_accuracy": 0.13143857643008233,
|
|
"num_tokens": 598246.0,
|
|
"step": 265
|
|
},
|
|
{
|
|
"entropy": 6.817195844650269,
|
|
"epoch": 0.030325153029707418,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00013450000000000002,
|
|
"loss": 6.6765,
|
|
"mean_token_accuracy": 0.12888288870453835,
|
|
"num_tokens": 610628.0,
|
|
"step": 270
|
|
},
|
|
{
|
|
"entropy": 6.681700706481934,
|
|
"epoch": 0.030886729937664965,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00013700000000000002,
|
|
"loss": 6.4107,
|
|
"mean_token_accuracy": 0.13505152836441994,
|
|
"num_tokens": 621214.0,
|
|
"step": 275
|
|
},
|
|
{
|
|
"entropy": 6.855287408828735,
|
|
"epoch": 0.031448306845622505,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0001395,
|
|
"loss": 6.5283,
|
|
"mean_token_accuracy": 0.13292622640728952,
|
|
"num_tokens": 631123.0,
|
|
"step": 280
|
|
},
|
|
{
|
|
"entropy": 6.703789567947387,
|
|
"epoch": 0.032009883753580055,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00014199999999999998,
|
|
"loss": 6.5043,
|
|
"mean_token_accuracy": 0.13257981985807418,
|
|
"num_tokens": 643434.0,
|
|
"step": 285
|
|
},
|
|
{
|
|
"entropy": 6.787659692764282,
|
|
"epoch": 0.0325714606615376,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0001445,
|
|
"loss": 6.5228,
|
|
"mean_token_accuracy": 0.12901086285710334,
|
|
"num_tokens": 655336.0,
|
|
"step": 290
|
|
},
|
|
{
|
|
"entropy": 6.773025608062744,
|
|
"epoch": 0.03313303756949514,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.000147,
|
|
"loss": 6.5225,
|
|
"mean_token_accuracy": 0.12936050444841385,
|
|
"num_tokens": 666591.0,
|
|
"step": 295
|
|
},
|
|
{
|
|
"entropy": 6.766870307922363,
|
|
"epoch": 0.033694614477452686,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0001495,
|
|
"loss": 6.5539,
|
|
"mean_token_accuracy": 0.1262955389916897,
|
|
"num_tokens": 678288.0,
|
|
"step": 300
|
|
},
|
|
{
|
|
"entropy": 6.700440359115601,
|
|
"epoch": 0.03425619138541023,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000152,
|
|
"loss": 6.5051,
|
|
"mean_token_accuracy": 0.12933695763349534,
|
|
"num_tokens": 688526.0,
|
|
"step": 305
|
|
},
|
|
{
|
|
"entropy": 6.716910123825073,
|
|
"epoch": 0.03481776829336777,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00015450000000000001,
|
|
"loss": 6.4003,
|
|
"mean_token_accuracy": 0.1389426000416279,
|
|
"num_tokens": 698727.0,
|
|
"step": 310
|
|
},
|
|
{
|
|
"entropy": 6.7672779083251955,
|
|
"epoch": 0.035379345201325324,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000157,
|
|
"loss": 6.4518,
|
|
"mean_token_accuracy": 0.13233318105340003,
|
|
"num_tokens": 710042.0,
|
|
"step": 315
|
|
},
|
|
{
|
|
"entropy": 6.699503803253174,
|
|
"epoch": 0.03594092210928287,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0001595,
|
|
"loss": 6.4025,
|
|
"mean_token_accuracy": 0.1324545383453369,
|
|
"num_tokens": 721390.0,
|
|
"step": 320
|
|
},
|
|
{
|
|
"entropy": 6.715420770645141,
|
|
"epoch": 0.03650249901724041,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.000162,
|
|
"loss": 6.629,
|
|
"mean_token_accuracy": 0.1291418768465519,
|
|
"num_tokens": 732949.0,
|
|
"step": 325
|
|
},
|
|
{
|
|
"entropy": 6.902552509307862,
|
|
"epoch": 0.037064075925197955,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00016450000000000001,
|
|
"loss": 6.6134,
|
|
"mean_token_accuracy": 0.12573065236210823,
|
|
"num_tokens": 744943.0,
|
|
"step": 330
|
|
},
|
|
{
|
|
"entropy": 6.661505699157715,
|
|
"epoch": 0.0376256528331555,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00016700000000000002,
|
|
"loss": 6.3951,
|
|
"mean_token_accuracy": 0.1361982524394989,
|
|
"num_tokens": 756579.0,
|
|
"step": 335
|
|
},
|
|
{
|
|
"entropy": 6.612162971496582,
|
|
"epoch": 0.03818722974111304,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00016950000000000003,
|
|
"loss": 6.3675,
|
|
"mean_token_accuracy": 0.13559021651744843,
|
|
"num_tokens": 767260.0,
|
|
"step": 340
|
|
},
|
|
{
|
|
"entropy": 6.6629081726074215,
|
|
"epoch": 0.03874880664907059,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00017199999999999998,
|
|
"loss": 6.4972,
|
|
"mean_token_accuracy": 0.1315748445689678,
|
|
"num_tokens": 778163.0,
|
|
"step": 345
|
|
},
|
|
{
|
|
"entropy": 6.747300863265991,
|
|
"epoch": 0.039310383557028136,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00017449999999999999,
|
|
"loss": 6.5003,
|
|
"mean_token_accuracy": 0.13013652414083482,
|
|
"num_tokens": 788912.0,
|
|
"step": 350
|
|
},
|
|
{
|
|
"entropy": 6.859929609298706,
|
|
"epoch": 0.03987196046498568,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.000177,
|
|
"loss": 6.6443,
|
|
"mean_token_accuracy": 0.12974906489253044,
|
|
"num_tokens": 801405.0,
|
|
"step": 355
|
|
},
|
|
{
|
|
"entropy": 6.579695367813111,
|
|
"epoch": 0.040433537372943223,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0001795,
|
|
"loss": 6.4399,
|
|
"mean_token_accuracy": 0.12944767922163009,
|
|
"num_tokens": 813023.0,
|
|
"step": 360
|
|
},
|
|
{
|
|
"entropy": 6.7528997421264645,
|
|
"epoch": 0.04099511428090077,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000182,
|
|
"loss": 6.461,
|
|
"mean_token_accuracy": 0.1318572238087654,
|
|
"num_tokens": 823993.0,
|
|
"step": 365
|
|
},
|
|
{
|
|
"entropy": 6.6921186447143555,
|
|
"epoch": 0.04155669118885831,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0001845,
|
|
"loss": 6.5245,
|
|
"mean_token_accuracy": 0.12879264652729033,
|
|
"num_tokens": 836642.0,
|
|
"step": 370
|
|
},
|
|
{
|
|
"entropy": 6.551775407791138,
|
|
"epoch": 0.04211826809681586,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000187,
|
|
"loss": 6.3077,
|
|
"mean_token_accuracy": 0.14068796634674072,
|
|
"num_tokens": 847475.0,
|
|
"step": 375
|
|
},
|
|
{
|
|
"entropy": 6.706428289413452,
|
|
"epoch": 0.042679845004773405,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0001895,
|
|
"loss": 6.3997,
|
|
"mean_token_accuracy": 0.1378198005259037,
|
|
"num_tokens": 857949.0,
|
|
"step": 380
|
|
},
|
|
{
|
|
"entropy": 6.653968048095703,
|
|
"epoch": 0.04324142191273095,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000192,
|
|
"loss": 6.4495,
|
|
"mean_token_accuracy": 0.13037263453006745,
|
|
"num_tokens": 868661.0,
|
|
"step": 385
|
|
},
|
|
{
|
|
"entropy": 6.691042804718018,
|
|
"epoch": 0.04380299882068849,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0001945,
|
|
"loss": 6.4988,
|
|
"mean_token_accuracy": 0.13211527988314628,
|
|
"num_tokens": 879651.0,
|
|
"step": 390
|
|
},
|
|
{
|
|
"entropy": 6.751509189605713,
|
|
"epoch": 0.044364575728646036,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00019700000000000002,
|
|
"loss": 6.4875,
|
|
"mean_token_accuracy": 0.12362533882260322,
|
|
"num_tokens": 891189.0,
|
|
"step": 395
|
|
},
|
|
{
|
|
"entropy": 6.630907487869263,
|
|
"epoch": 0.044926152636603586,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00019950000000000002,
|
|
"loss": 6.4002,
|
|
"mean_token_accuracy": 0.13191765397787095,
|
|
"num_tokens": 902915.0,
|
|
"step": 400
|
|
},
|
|
{
|
|
"entropy": 6.7248283386230465,
|
|
"epoch": 0.04548772954456113,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.000202,
|
|
"loss": 6.4744,
|
|
"mean_token_accuracy": 0.12763879969716072,
|
|
"num_tokens": 914108.0,
|
|
"step": 405
|
|
},
|
|
{
|
|
"entropy": 6.690525770187378,
|
|
"epoch": 0.046049306452518673,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00020449999999999998,
|
|
"loss": 6.5282,
|
|
"mean_token_accuracy": 0.12373311445116997,
|
|
"num_tokens": 925729.0,
|
|
"step": 410
|
|
},
|
|
{
|
|
"entropy": 6.712349891662598,
|
|
"epoch": 0.04661088336047622,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000207,
|
|
"loss": 6.5347,
|
|
"mean_token_accuracy": 0.13032480850815772,
|
|
"num_tokens": 936912.0,
|
|
"step": 415
|
|
},
|
|
{
|
|
"entropy": 6.775314521789551,
|
|
"epoch": 0.04717246026843376,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0002095,
|
|
"loss": 6.5176,
|
|
"mean_token_accuracy": 0.13044203147292138,
|
|
"num_tokens": 948576.0,
|
|
"step": 420
|
|
},
|
|
{
|
|
"entropy": 6.574384355545044,
|
|
"epoch": 0.047734037176391304,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.000212,
|
|
"loss": 6.3716,
|
|
"mean_token_accuracy": 0.13324426487088203,
|
|
"num_tokens": 959346.0,
|
|
"step": 425
|
|
},
|
|
{
|
|
"entropy": 6.540327358245849,
|
|
"epoch": 0.048295614084348855,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0002145,
|
|
"loss": 6.3851,
|
|
"mean_token_accuracy": 0.13386972919106482,
|
|
"num_tokens": 970124.0,
|
|
"step": 430
|
|
},
|
|
{
|
|
"entropy": 6.735883665084839,
|
|
"epoch": 0.0488571909923064,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00021700000000000002,
|
|
"loss": 6.4621,
|
|
"mean_token_accuracy": 0.1355781562626362,
|
|
"num_tokens": 981628.0,
|
|
"step": 435
|
|
},
|
|
{
|
|
"entropy": 6.577527189254761,
|
|
"epoch": 0.04941876790026394,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0002195,
|
|
"loss": 6.4176,
|
|
"mean_token_accuracy": 0.13505651876330377,
|
|
"num_tokens": 992423.0,
|
|
"step": 440
|
|
},
|
|
{
|
|
"entropy": 6.7072450637817385,
|
|
"epoch": 0.049980344808221486,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000222,
|
|
"loss": 6.4294,
|
|
"mean_token_accuracy": 0.12828949466347694,
|
|
"num_tokens": 1002954.0,
|
|
"step": 445
|
|
},
|
|
{
|
|
"entropy": 6.559535694122315,
|
|
"epoch": 0.05054192171617903,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0002245,
|
|
"loss": 6.3184,
|
|
"mean_token_accuracy": 0.13954212963581086,
|
|
"num_tokens": 1013351.0,
|
|
"step": 450
|
|
},
|
|
{
|
|
"entropy": 6.735851097106933,
|
|
"epoch": 0.05110349862413657,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00022700000000000002,
|
|
"loss": 6.4267,
|
|
"mean_token_accuracy": 0.1300646774470806,
|
|
"num_tokens": 1023781.0,
|
|
"step": 455
|
|
},
|
|
{
|
|
"entropy": 6.7095380306243895,
|
|
"epoch": 0.051665075532094124,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00022950000000000002,
|
|
"loss": 6.4772,
|
|
"mean_token_accuracy": 0.1330593556165695,
|
|
"num_tokens": 1034565.0,
|
|
"step": 460
|
|
},
|
|
{
|
|
"entropy": 6.535807943344116,
|
|
"epoch": 0.05222665244005167,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00023200000000000003,
|
|
"loss": 6.3159,
|
|
"mean_token_accuracy": 0.13358335345983505,
|
|
"num_tokens": 1045595.0,
|
|
"step": 465
|
|
},
|
|
{
|
|
"entropy": 6.531654977798462,
|
|
"epoch": 0.05278822934800921,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00023449999999999998,
|
|
"loss": 6.3056,
|
|
"mean_token_accuracy": 0.13400183171033858,
|
|
"num_tokens": 1056084.0,
|
|
"step": 470
|
|
},
|
|
{
|
|
"entropy": 6.593910646438599,
|
|
"epoch": 0.053349806255966754,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000237,
|
|
"loss": 6.3604,
|
|
"mean_token_accuracy": 0.1359560400247574,
|
|
"num_tokens": 1067014.0,
|
|
"step": 475
|
|
},
|
|
{
|
|
"entropy": 6.536575841903686,
|
|
"epoch": 0.0539113831639243,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0002395,
|
|
"loss": 6.3441,
|
|
"mean_token_accuracy": 0.13619447946548463,
|
|
"num_tokens": 1078557.0,
|
|
"step": 480
|
|
},
|
|
{
|
|
"entropy": 6.5822559833526615,
|
|
"epoch": 0.05447296007188184,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000242,
|
|
"loss": 6.4061,
|
|
"mean_token_accuracy": 0.13504692241549493,
|
|
"num_tokens": 1090541.0,
|
|
"step": 485
|
|
},
|
|
{
|
|
"entropy": 6.661154747009277,
|
|
"epoch": 0.05503453697983939,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0002445,
|
|
"loss": 6.479,
|
|
"mean_token_accuracy": 0.13549330905079843,
|
|
"num_tokens": 1101851.0,
|
|
"step": 490
|
|
},
|
|
{
|
|
"entropy": 6.586714506149292,
|
|
"epoch": 0.055596113887796936,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.000247,
|
|
"loss": 6.3725,
|
|
"mean_token_accuracy": 0.1318344421684742,
|
|
"num_tokens": 1112728.0,
|
|
"step": 495
|
|
},
|
|
{
|
|
"entropy": 6.666340303421021,
|
|
"epoch": 0.05615769079575448,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0002495,
|
|
"loss": 6.4961,
|
|
"mean_token_accuracy": 0.13488958552479743,
|
|
"num_tokens": 1124537.0,
|
|
"step": 500
|
|
},
|
|
{
|
|
"entropy": 6.5284497261047365,
|
|
"epoch": 0.05671926770371202,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.000252,
|
|
"loss": 6.4173,
|
|
"mean_token_accuracy": 0.1345018796622753,
|
|
"num_tokens": 1135749.0,
|
|
"step": 505
|
|
},
|
|
{
|
|
"entropy": 6.623070526123047,
|
|
"epoch": 0.05728084461166957,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0002545,
|
|
"loss": 6.3271,
|
|
"mean_token_accuracy": 0.1346582993865013,
|
|
"num_tokens": 1147597.0,
|
|
"step": 510
|
|
},
|
|
{
|
|
"entropy": 6.447442674636841,
|
|
"epoch": 0.05784242151962711,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000257,
|
|
"loss": 6.2776,
|
|
"mean_token_accuracy": 0.14209385365247726,
|
|
"num_tokens": 1158975.0,
|
|
"step": 515
|
|
},
|
|
{
|
|
"entropy": 6.61184515953064,
|
|
"epoch": 0.05840399842758466,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0002595,
|
|
"loss": 6.4139,
|
|
"mean_token_accuracy": 0.13491497561335564,
|
|
"num_tokens": 1170556.0,
|
|
"step": 520
|
|
},
|
|
{
|
|
"entropy": 6.5176115989685055,
|
|
"epoch": 0.058965575335542204,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.000262,
|
|
"loss": 6.2865,
|
|
"mean_token_accuracy": 0.1368475705385208,
|
|
"num_tokens": 1180757.0,
|
|
"step": 525
|
|
},
|
|
{
|
|
"entropy": 6.529765558242798,
|
|
"epoch": 0.05952715224349975,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00026450000000000003,
|
|
"loss": 6.3284,
|
|
"mean_token_accuracy": 0.13527121916413307,
|
|
"num_tokens": 1192428.0,
|
|
"step": 530
|
|
},
|
|
{
|
|
"entropy": 6.621386337280273,
|
|
"epoch": 0.06008872915145729,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00026700000000000004,
|
|
"loss": 6.3937,
|
|
"mean_token_accuracy": 0.1324701189994812,
|
|
"num_tokens": 1203867.0,
|
|
"step": 535
|
|
},
|
|
{
|
|
"entropy": 6.546226501464844,
|
|
"epoch": 0.060650306059414835,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00026950000000000005,
|
|
"loss": 6.3847,
|
|
"mean_token_accuracy": 0.1400379404425621,
|
|
"num_tokens": 1214059.0,
|
|
"step": 540
|
|
},
|
|
{
|
|
"entropy": 6.574158668518066,
|
|
"epoch": 0.06121188296737238,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00027200000000000005,
|
|
"loss": 6.4522,
|
|
"mean_token_accuracy": 0.13733250200748442,
|
|
"num_tokens": 1224750.0,
|
|
"step": 545
|
|
},
|
|
{
|
|
"entropy": 6.659890937805176,
|
|
"epoch": 0.06177345987532993,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0002745,
|
|
"loss": 6.5351,
|
|
"mean_token_accuracy": 0.1279556542634964,
|
|
"num_tokens": 1235936.0,
|
|
"step": 550
|
|
},
|
|
{
|
|
"entropy": 6.560004234313965,
|
|
"epoch": 0.06233503678328747,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000277,
|
|
"loss": 6.3308,
|
|
"mean_token_accuracy": 0.1354156717658043,
|
|
"num_tokens": 1247619.0,
|
|
"step": 555
|
|
},
|
|
{
|
|
"entropy": 6.568575429916382,
|
|
"epoch": 0.06289661369124501,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0002795,
|
|
"loss": 6.3972,
|
|
"mean_token_accuracy": 0.13855155184864998,
|
|
"num_tokens": 1258089.0,
|
|
"step": 560
|
|
},
|
|
{
|
|
"entropy": 6.636307573318481,
|
|
"epoch": 0.06345819059920256,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00028199999999999997,
|
|
"loss": 6.4835,
|
|
"mean_token_accuracy": 0.12968146279454232,
|
|
"num_tokens": 1270727.0,
|
|
"step": 565
|
|
},
|
|
{
|
|
"entropy": 6.513255167007446,
|
|
"epoch": 0.06401976750716011,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0002845,
|
|
"loss": 6.3531,
|
|
"mean_token_accuracy": 0.13295062705874444,
|
|
"num_tokens": 1280886.0,
|
|
"step": 570
|
|
},
|
|
{
|
|
"entropy": 6.659465265274048,
|
|
"epoch": 0.06458134441511765,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.000287,
|
|
"loss": 6.3734,
|
|
"mean_token_accuracy": 0.13972493261098862,
|
|
"num_tokens": 1292205.0,
|
|
"step": 575
|
|
},
|
|
{
|
|
"entropy": 6.5016227722167965,
|
|
"epoch": 0.0651429213230752,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0002895,
|
|
"loss": 6.3582,
|
|
"mean_token_accuracy": 0.13386574983596802,
|
|
"num_tokens": 1304621.0,
|
|
"step": 580
|
|
},
|
|
{
|
|
"entropy": 6.649503421783447,
|
|
"epoch": 0.06570449823103273,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000292,
|
|
"loss": 6.4403,
|
|
"mean_token_accuracy": 0.13231186792254448,
|
|
"num_tokens": 1315481.0,
|
|
"step": 585
|
|
},
|
|
{
|
|
"entropy": 6.50060453414917,
|
|
"epoch": 0.06626607513899029,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0002945,
|
|
"loss": 6.4252,
|
|
"mean_token_accuracy": 0.13465353846549988,
|
|
"num_tokens": 1328726.0,
|
|
"step": 590
|
|
},
|
|
{
|
|
"entropy": 6.672741794586182,
|
|
"epoch": 0.06682765204694784,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000297,
|
|
"loss": 6.4919,
|
|
"mean_token_accuracy": 0.12951735854148866,
|
|
"num_tokens": 1340151.0,
|
|
"step": 595
|
|
},
|
|
{
|
|
"entropy": 6.402231216430664,
|
|
"epoch": 0.06738922895490537,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0002995,
|
|
"loss": 6.2674,
|
|
"mean_token_accuracy": 0.12976990938186644,
|
|
"num_tokens": 1350833.0,
|
|
"step": 600
|
|
},
|
|
{
|
|
"entropy": 6.60262622833252,
|
|
"epoch": 0.06795080586286292,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000302,
|
|
"loss": 6.4286,
|
|
"mean_token_accuracy": 0.13295263051986694,
|
|
"num_tokens": 1362332.0,
|
|
"step": 605
|
|
},
|
|
{
|
|
"entropy": 6.466546201705933,
|
|
"epoch": 0.06851238277082046,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0003045,
|
|
"loss": 6.3442,
|
|
"mean_token_accuracy": 0.13722798079252244,
|
|
"num_tokens": 1373696.0,
|
|
"step": 610
|
|
},
|
|
{
|
|
"entropy": 6.441986417770385,
|
|
"epoch": 0.06907395967877801,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000307,
|
|
"loss": 6.2523,
|
|
"mean_token_accuracy": 0.14421699643135072,
|
|
"num_tokens": 1383553.0,
|
|
"step": 615
|
|
},
|
|
{
|
|
"entropy": 6.502252292633057,
|
|
"epoch": 0.06963553658673555,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0003095,
|
|
"loss": 6.3813,
|
|
"mean_token_accuracy": 0.13401498645544052,
|
|
"num_tokens": 1394487.0,
|
|
"step": 620
|
|
},
|
|
{
|
|
"entropy": 6.637560892105102,
|
|
"epoch": 0.0701971134946931,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000312,
|
|
"loss": 6.395,
|
|
"mean_token_accuracy": 0.13866457417607309,
|
|
"num_tokens": 1404928.0,
|
|
"step": 625
|
|
},
|
|
{
|
|
"entropy": 6.425406217575073,
|
|
"epoch": 0.07075869040265065,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0003145,
|
|
"loss": 6.2753,
|
|
"mean_token_accuracy": 0.13876649886369705,
|
|
"num_tokens": 1415854.0,
|
|
"step": 630
|
|
},
|
|
{
|
|
"entropy": 6.423026084899902,
|
|
"epoch": 0.07132026731060818,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000317,
|
|
"loss": 6.3298,
|
|
"mean_token_accuracy": 0.13941421657800673,
|
|
"num_tokens": 1427153.0,
|
|
"step": 635
|
|
},
|
|
{
|
|
"entropy": 6.467883777618408,
|
|
"epoch": 0.07188184421856574,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0003195,
|
|
"loss": 6.4321,
|
|
"mean_token_accuracy": 0.13852172642946242,
|
|
"num_tokens": 1438907.0,
|
|
"step": 640
|
|
},
|
|
{
|
|
"entropy": 6.5902872562408445,
|
|
"epoch": 0.07244342112652327,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000322,
|
|
"loss": 6.3201,
|
|
"mean_token_accuracy": 0.13026409447193146,
|
|
"num_tokens": 1449975.0,
|
|
"step": 645
|
|
},
|
|
{
|
|
"entropy": 6.460627508163452,
|
|
"epoch": 0.07300499803448082,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00032450000000000003,
|
|
"loss": 6.3011,
|
|
"mean_token_accuracy": 0.14136423021554947,
|
|
"num_tokens": 1460815.0,
|
|
"step": 650
|
|
},
|
|
{
|
|
"entropy": 6.525569152832031,
|
|
"epoch": 0.07356657494243837,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00032700000000000003,
|
|
"loss": 6.3666,
|
|
"mean_token_accuracy": 0.13360349088907242,
|
|
"num_tokens": 1472403.0,
|
|
"step": 655
|
|
},
|
|
{
|
|
"entropy": 6.469359874725342,
|
|
"epoch": 0.07412815185039591,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00032950000000000004,
|
|
"loss": 6.3808,
|
|
"mean_token_accuracy": 0.12803015038371085,
|
|
"num_tokens": 1484015.0,
|
|
"step": 660
|
|
},
|
|
{
|
|
"entropy": 6.534909439086914,
|
|
"epoch": 0.07468972875835346,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00033200000000000005,
|
|
"loss": 6.3977,
|
|
"mean_token_accuracy": 0.1342173106968403,
|
|
"num_tokens": 1495383.0,
|
|
"step": 665
|
|
},
|
|
{
|
|
"entropy": 6.443075227737427,
|
|
"epoch": 0.075251305666311,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00033450000000000005,
|
|
"loss": 6.3031,
|
|
"mean_token_accuracy": 0.13773341178894044,
|
|
"num_tokens": 1505893.0,
|
|
"step": 670
|
|
},
|
|
{
|
|
"entropy": 6.620420742034912,
|
|
"epoch": 0.07581288257426855,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000337,
|
|
"loss": 6.4651,
|
|
"mean_token_accuracy": 0.1332511968910694,
|
|
"num_tokens": 1518933.0,
|
|
"step": 675
|
|
},
|
|
{
|
|
"entropy": 6.569113636016846,
|
|
"epoch": 0.07637445948222608,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0003395,
|
|
"loss": 6.4764,
|
|
"mean_token_accuracy": 0.13463966101408004,
|
|
"num_tokens": 1530603.0,
|
|
"step": 680
|
|
},
|
|
{
|
|
"entropy": 6.500573587417603,
|
|
"epoch": 0.07693603639018363,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000342,
|
|
"loss": 6.3103,
|
|
"mean_token_accuracy": 0.13940601274371148,
|
|
"num_tokens": 1540977.0,
|
|
"step": 685
|
|
},
|
|
{
|
|
"entropy": 6.481778717041015,
|
|
"epoch": 0.07749761329814119,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00034449999999999997,
|
|
"loss": 6.4076,
|
|
"mean_token_accuracy": 0.1277073837816715,
|
|
"num_tokens": 1553004.0,
|
|
"step": 690
|
|
},
|
|
{
|
|
"entropy": 6.4691490650177,
|
|
"epoch": 0.07805919020609872,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000347,
|
|
"loss": 6.3331,
|
|
"mean_token_accuracy": 0.13752775639295578,
|
|
"num_tokens": 1563446.0,
|
|
"step": 695
|
|
},
|
|
{
|
|
"entropy": 6.5088294506072994,
|
|
"epoch": 0.07862076711405627,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0003495,
|
|
"loss": 6.3828,
|
|
"mean_token_accuracy": 0.13829699009656907,
|
|
"num_tokens": 1573884.0,
|
|
"step": 700
|
|
},
|
|
{
|
|
"entropy": 6.4070014476776125,
|
|
"epoch": 0.07918234402201381,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000352,
|
|
"loss": 6.2347,
|
|
"mean_token_accuracy": 0.14527149349451066,
|
|
"num_tokens": 1585396.0,
|
|
"step": 705
|
|
},
|
|
{
|
|
"entropy": 6.339435338973999,
|
|
"epoch": 0.07974392092997136,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0003545,
|
|
"loss": 6.2386,
|
|
"mean_token_accuracy": 0.14462128803133964,
|
|
"num_tokens": 1596934.0,
|
|
"step": 710
|
|
},
|
|
{
|
|
"entropy": 6.393019104003907,
|
|
"epoch": 0.08030549783792891,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000357,
|
|
"loss": 6.2904,
|
|
"mean_token_accuracy": 0.14003824442625046,
|
|
"num_tokens": 1608069.0,
|
|
"step": 715
|
|
},
|
|
{
|
|
"entropy": 6.421917963027954,
|
|
"epoch": 0.08086707474588645,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0003595,
|
|
"loss": 6.213,
|
|
"mean_token_accuracy": 0.1437910795211792,
|
|
"num_tokens": 1619532.0,
|
|
"step": 720
|
|
},
|
|
{
|
|
"entropy": 6.441302394866943,
|
|
"epoch": 0.081428651653844,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000362,
|
|
"loss": 6.3734,
|
|
"mean_token_accuracy": 0.13529681786894798,
|
|
"num_tokens": 1630697.0,
|
|
"step": 725
|
|
},
|
|
{
|
|
"entropy": 6.426795148849488,
|
|
"epoch": 0.08199022856180153,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0003645,
|
|
"loss": 6.3413,
|
|
"mean_token_accuracy": 0.1360257886350155,
|
|
"num_tokens": 1641854.0,
|
|
"step": 730
|
|
},
|
|
{
|
|
"entropy": 6.509672975540161,
|
|
"epoch": 0.08255180546975908,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000367,
|
|
"loss": 6.4867,
|
|
"mean_token_accuracy": 0.13371353596448898,
|
|
"num_tokens": 1653036.0,
|
|
"step": 735
|
|
},
|
|
{
|
|
"entropy": 6.43353681564331,
|
|
"epoch": 0.08311338237771662,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0003695,
|
|
"loss": 6.2558,
|
|
"mean_token_accuracy": 0.13888908326625823,
|
|
"num_tokens": 1664096.0,
|
|
"step": 740
|
|
},
|
|
{
|
|
"entropy": 6.476845026016235,
|
|
"epoch": 0.08367495928567417,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000372,
|
|
"loss": 6.418,
|
|
"mean_token_accuracy": 0.13414328247308732,
|
|
"num_tokens": 1677890.0,
|
|
"step": 745
|
|
},
|
|
{
|
|
"entropy": 6.379944086074829,
|
|
"epoch": 0.08423653619363172,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0003745,
|
|
"loss": 6.276,
|
|
"mean_token_accuracy": 0.1345861591398716,
|
|
"num_tokens": 1687627.0,
|
|
"step": 750
|
|
},
|
|
{
|
|
"entropy": 6.61228575706482,
|
|
"epoch": 0.08479811310158926,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000377,
|
|
"loss": 6.4958,
|
|
"mean_token_accuracy": 0.1333550438284874,
|
|
"num_tokens": 1700843.0,
|
|
"step": 755
|
|
},
|
|
{
|
|
"entropy": 6.359044981002808,
|
|
"epoch": 0.08535969000954681,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0003795,
|
|
"loss": 6.3148,
|
|
"mean_token_accuracy": 0.13619839102029802,
|
|
"num_tokens": 1712356.0,
|
|
"step": 760
|
|
},
|
|
{
|
|
"entropy": 6.433030843734741,
|
|
"epoch": 0.08592126691750435,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000382,
|
|
"loss": 6.3095,
|
|
"mean_token_accuracy": 0.13844826743006705,
|
|
"num_tokens": 1722041.0,
|
|
"step": 765
|
|
},
|
|
{
|
|
"entropy": 6.451205539703369,
|
|
"epoch": 0.0864828438254619,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0003845,
|
|
"loss": 6.4199,
|
|
"mean_token_accuracy": 0.13872063755989075,
|
|
"num_tokens": 1733628.0,
|
|
"step": 770
|
|
},
|
|
{
|
|
"entropy": 6.397660779953003,
|
|
"epoch": 0.08704442073341945,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00038700000000000003,
|
|
"loss": 6.2845,
|
|
"mean_token_accuracy": 0.13980024233460425,
|
|
"num_tokens": 1745174.0,
|
|
"step": 775
|
|
},
|
|
{
|
|
"entropy": 6.333204936981201,
|
|
"epoch": 0.08760599764137698,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00038950000000000003,
|
|
"loss": 6.2032,
|
|
"mean_token_accuracy": 0.14358293414115905,
|
|
"num_tokens": 1757117.0,
|
|
"step": 780
|
|
},
|
|
{
|
|
"entropy": 6.3692162990570065,
|
|
"epoch": 0.08816757454933453,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00039200000000000004,
|
|
"loss": 6.2193,
|
|
"mean_token_accuracy": 0.14303260445594787,
|
|
"num_tokens": 1767343.0,
|
|
"step": 785
|
|
},
|
|
{
|
|
"entropy": 6.413911199569702,
|
|
"epoch": 0.08872915145729207,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00039450000000000005,
|
|
"loss": 6.3127,
|
|
"mean_token_accuracy": 0.13739153444767,
|
|
"num_tokens": 1778500.0,
|
|
"step": 790
|
|
},
|
|
{
|
|
"entropy": 6.385387420654297,
|
|
"epoch": 0.08929072836524962,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00039700000000000005,
|
|
"loss": 6.3131,
|
|
"mean_token_accuracy": 0.14397693797945976,
|
|
"num_tokens": 1788474.0,
|
|
"step": 795
|
|
},
|
|
{
|
|
"entropy": 6.558474445343018,
|
|
"epoch": 0.08985230527320717,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0003995,
|
|
"loss": 6.4813,
|
|
"mean_token_accuracy": 0.12978689670562743,
|
|
"num_tokens": 1800756.0,
|
|
"step": 800
|
|
},
|
|
{
|
|
"entropy": 6.22222056388855,
|
|
"epoch": 0.09041388218116471,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000402,
|
|
"loss": 6.1941,
|
|
"mean_token_accuracy": 0.13742919713258744,
|
|
"num_tokens": 1812172.0,
|
|
"step": 805
|
|
},
|
|
{
|
|
"entropy": 6.475030994415283,
|
|
"epoch": 0.09097545908912226,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004045,
|
|
"loss": 6.3167,
|
|
"mean_token_accuracy": 0.14302188903093338,
|
|
"num_tokens": 1822057.0,
|
|
"step": 810
|
|
},
|
|
{
|
|
"entropy": 6.314649343490601,
|
|
"epoch": 0.0915370359970798,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00040699999999999997,
|
|
"loss": 6.2581,
|
|
"mean_token_accuracy": 0.14811700135469436,
|
|
"num_tokens": 1833074.0,
|
|
"step": 815
|
|
},
|
|
{
|
|
"entropy": 6.365461254119873,
|
|
"epoch": 0.09209861290503735,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004095,
|
|
"loss": 6.259,
|
|
"mean_token_accuracy": 0.14124332517385482,
|
|
"num_tokens": 1844932.0,
|
|
"step": 820
|
|
},
|
|
{
|
|
"entropy": 6.352189779281616,
|
|
"epoch": 0.09266018981299488,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000412,
|
|
"loss": 6.2793,
|
|
"mean_token_accuracy": 0.13838022351264953,
|
|
"num_tokens": 1855591.0,
|
|
"step": 825
|
|
},
|
|
{
|
|
"entropy": 6.308280038833618,
|
|
"epoch": 0.09322176672095243,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004145,
|
|
"loss": 6.2166,
|
|
"mean_token_accuracy": 0.14280629456043242,
|
|
"num_tokens": 1866726.0,
|
|
"step": 830
|
|
},
|
|
{
|
|
"entropy": 6.375708055496216,
|
|
"epoch": 0.09378334362890998,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000417,
|
|
"loss": 6.2487,
|
|
"mean_token_accuracy": 0.14352674633264542,
|
|
"num_tokens": 1877385.0,
|
|
"step": 835
|
|
},
|
|
{
|
|
"entropy": 6.320023250579834,
|
|
"epoch": 0.09434492053686752,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004195,
|
|
"loss": 6.1641,
|
|
"mean_token_accuracy": 0.1380472607910633,
|
|
"num_tokens": 1887905.0,
|
|
"step": 840
|
|
},
|
|
{
|
|
"entropy": 6.247666931152343,
|
|
"epoch": 0.09490649744482507,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000422,
|
|
"loss": 6.222,
|
|
"mean_token_accuracy": 0.14042351841926576,
|
|
"num_tokens": 1898649.0,
|
|
"step": 845
|
|
},
|
|
{
|
|
"entropy": 6.318536806106567,
|
|
"epoch": 0.09546807435278261,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004245,
|
|
"loss": 6.2541,
|
|
"mean_token_accuracy": 0.13877154663205146,
|
|
"num_tokens": 1908808.0,
|
|
"step": 850
|
|
},
|
|
{
|
|
"entropy": 6.376451063156128,
|
|
"epoch": 0.09602965126074016,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000427,
|
|
"loss": 6.3473,
|
|
"mean_token_accuracy": 0.13623209297657013,
|
|
"num_tokens": 1920360.0,
|
|
"step": 855
|
|
},
|
|
{
|
|
"entropy": 6.361136341094971,
|
|
"epoch": 0.09659122816869771,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004295,
|
|
"loss": 6.2538,
|
|
"mean_token_accuracy": 0.14060918912291526,
|
|
"num_tokens": 1931082.0,
|
|
"step": 860
|
|
},
|
|
{
|
|
"entropy": 6.365381669998169,
|
|
"epoch": 0.09715280507665525,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000432,
|
|
"loss": 6.4102,
|
|
"mean_token_accuracy": 0.1356579177081585,
|
|
"num_tokens": 1942712.0,
|
|
"step": 865
|
|
},
|
|
{
|
|
"entropy": 6.260768222808838,
|
|
"epoch": 0.0977143819846128,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004345,
|
|
"loss": 6.1667,
|
|
"mean_token_accuracy": 0.1418852239847183,
|
|
"num_tokens": 1953316.0,
|
|
"step": 870
|
|
},
|
|
{
|
|
"entropy": 6.327302694320679,
|
|
"epoch": 0.09827595889257033,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000437,
|
|
"loss": 6.2268,
|
|
"mean_token_accuracy": 0.1380545549094677,
|
|
"num_tokens": 1963936.0,
|
|
"step": 875
|
|
},
|
|
{
|
|
"entropy": 6.39926381111145,
|
|
"epoch": 0.09883753580052788,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004395,
|
|
"loss": 6.2569,
|
|
"mean_token_accuracy": 0.14306407570838928,
|
|
"num_tokens": 1974502.0,
|
|
"step": 880
|
|
},
|
|
{
|
|
"entropy": 6.246096086502075,
|
|
"epoch": 0.09939911270848542,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000442,
|
|
"loss": 6.1911,
|
|
"mean_token_accuracy": 0.1470048740506172,
|
|
"num_tokens": 1985746.0,
|
|
"step": 885
|
|
},
|
|
{
|
|
"entropy": 6.329217004776001,
|
|
"epoch": 0.09996068961644297,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004445,
|
|
"loss": 6.2811,
|
|
"mean_token_accuracy": 0.1449923798441887,
|
|
"num_tokens": 1997696.0,
|
|
"step": 890
|
|
},
|
|
{
|
|
"entropy": 6.319565534591675,
|
|
"epoch": 0.10052226652440052,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000447,
|
|
"loss": 6.2515,
|
|
"mean_token_accuracy": 0.13921126648783683,
|
|
"num_tokens": 2009462.0,
|
|
"step": 895
|
|
},
|
|
{
|
|
"entropy": 6.299167490005493,
|
|
"epoch": 0.10108384343235806,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00044950000000000003,
|
|
"loss": 6.1943,
|
|
"mean_token_accuracy": 0.14123865887522696,
|
|
"num_tokens": 2019547.0,
|
|
"step": 900
|
|
},
|
|
{
|
|
"entropy": 6.215220594406128,
|
|
"epoch": 0.10164542034031561,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00045200000000000004,
|
|
"loss": 6.2076,
|
|
"mean_token_accuracy": 0.13563288748264313,
|
|
"num_tokens": 2030990.0,
|
|
"step": 905
|
|
},
|
|
{
|
|
"entropy": 6.280846071243286,
|
|
"epoch": 0.10220699724827315,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00045450000000000004,
|
|
"loss": 6.2843,
|
|
"mean_token_accuracy": 0.1405322201550007,
|
|
"num_tokens": 2042488.0,
|
|
"step": 910
|
|
},
|
|
{
|
|
"entropy": 6.4303792953491214,
|
|
"epoch": 0.1027685741562307,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00045700000000000005,
|
|
"loss": 6.3146,
|
|
"mean_token_accuracy": 0.14428061097860337,
|
|
"num_tokens": 2052822.0,
|
|
"step": 915
|
|
},
|
|
{
|
|
"entropy": 6.324028205871582,
|
|
"epoch": 0.10333015106418825,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00045950000000000006,
|
|
"loss": 6.2659,
|
|
"mean_token_accuracy": 0.14203638806939126,
|
|
"num_tokens": 2063274.0,
|
|
"step": 920
|
|
},
|
|
{
|
|
"entropy": 6.39445915222168,
|
|
"epoch": 0.10389172797214578,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000462,
|
|
"loss": 6.2983,
|
|
"mean_token_accuracy": 0.13992432355880738,
|
|
"num_tokens": 2074424.0,
|
|
"step": 925
|
|
},
|
|
{
|
|
"entropy": 6.275038862228394,
|
|
"epoch": 0.10445330488010333,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004645,
|
|
"loss": 6.304,
|
|
"mean_token_accuracy": 0.13862451538443565,
|
|
"num_tokens": 2085776.0,
|
|
"step": 930
|
|
},
|
|
{
|
|
"entropy": 6.48033709526062,
|
|
"epoch": 0.10501488178806087,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000467,
|
|
"loss": 6.3847,
|
|
"mean_token_accuracy": 0.13938564360141753,
|
|
"num_tokens": 2096789.0,
|
|
"step": 935
|
|
},
|
|
{
|
|
"entropy": 6.249989175796509,
|
|
"epoch": 0.10557645869601842,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004695,
|
|
"loss": 6.2845,
|
|
"mean_token_accuracy": 0.1425858847796917,
|
|
"num_tokens": 2108335.0,
|
|
"step": 940
|
|
},
|
|
{
|
|
"entropy": 6.3461168766021725,
|
|
"epoch": 0.10613803560397596,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000472,
|
|
"loss": 6.3783,
|
|
"mean_token_accuracy": 0.13689238354563713,
|
|
"num_tokens": 2121063.0,
|
|
"step": 945
|
|
},
|
|
{
|
|
"entropy": 6.310664415359497,
|
|
"epoch": 0.10669961251193351,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004745,
|
|
"loss": 6.2339,
|
|
"mean_token_accuracy": 0.14697037637233734,
|
|
"num_tokens": 2132442.0,
|
|
"step": 950
|
|
},
|
|
{
|
|
"entropy": 6.282202577590942,
|
|
"epoch": 0.10726118941989106,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000477,
|
|
"loss": 6.1467,
|
|
"mean_token_accuracy": 0.14595110565423966,
|
|
"num_tokens": 2142155.0,
|
|
"step": 955
|
|
},
|
|
{
|
|
"entropy": 6.206936550140381,
|
|
"epoch": 0.1078227663278486,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004795,
|
|
"loss": 6.2061,
|
|
"mean_token_accuracy": 0.14317777305841445,
|
|
"num_tokens": 2152923.0,
|
|
"step": 960
|
|
},
|
|
{
|
|
"entropy": 6.278789472579956,
|
|
"epoch": 0.10838434323580615,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000482,
|
|
"loss": 6.2013,
|
|
"mean_token_accuracy": 0.14196177273988725,
|
|
"num_tokens": 2164640.0,
|
|
"step": 965
|
|
},
|
|
{
|
|
"entropy": 6.120584154129029,
|
|
"epoch": 0.10894592014376368,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004845,
|
|
"loss": 6.122,
|
|
"mean_token_accuracy": 0.145785391330719,
|
|
"num_tokens": 2175403.0,
|
|
"step": 970
|
|
},
|
|
{
|
|
"entropy": 6.303649282455444,
|
|
"epoch": 0.10950749705172123,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000487,
|
|
"loss": 6.2428,
|
|
"mean_token_accuracy": 0.1391301706433296,
|
|
"num_tokens": 2186031.0,
|
|
"step": 975
|
|
},
|
|
{
|
|
"entropy": 6.307226181030273,
|
|
"epoch": 0.11006907395967878,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004895,
|
|
"loss": 6.2344,
|
|
"mean_token_accuracy": 0.1373376451432705,
|
|
"num_tokens": 2198152.0,
|
|
"step": 980
|
|
},
|
|
{
|
|
"entropy": 6.197272729873657,
|
|
"epoch": 0.11063065086763632,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000492,
|
|
"loss": 6.2457,
|
|
"mean_token_accuracy": 0.14293301850557327,
|
|
"num_tokens": 2209435.0,
|
|
"step": 985
|
|
},
|
|
{
|
|
"entropy": 6.24814772605896,
|
|
"epoch": 0.11119222777559387,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004945,
|
|
"loss": 6.1923,
|
|
"mean_token_accuracy": 0.14344990402460098,
|
|
"num_tokens": 2219476.0,
|
|
"step": 990
|
|
},
|
|
{
|
|
"entropy": 6.30175142288208,
|
|
"epoch": 0.11175380468355141,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000497,
|
|
"loss": 6.2951,
|
|
"mean_token_accuracy": 0.14248230829834937,
|
|
"num_tokens": 2231131.0,
|
|
"step": 995
|
|
},
|
|
{
|
|
"entropy": 6.274282073974609,
|
|
"epoch": 0.11231538159150896,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004995,
|
|
"loss": 6.2009,
|
|
"mean_token_accuracy": 0.14308610409498215,
|
|
"num_tokens": 2242309.0,
|
|
"step": 1000
|
|
},
|
|
{
|
|
"entropy": 6.0826170444488525,
|
|
"epoch": 0.1128769584994665,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000499999997707492,
|
|
"loss": 6.0337,
|
|
"mean_token_accuracy": 0.14380623400211334,
|
|
"num_tokens": 2252236.0,
|
|
"step": 1005
|
|
},
|
|
{
|
|
"entropy": 6.321280860900879,
|
|
"epoch": 0.11343853540742405,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004999999883941787,
|
|
"loss": 6.3576,
|
|
"mean_token_accuracy": 0.13597082048654557,
|
|
"num_tokens": 2263529.0,
|
|
"step": 1010
|
|
},
|
|
{
|
|
"entropy": 6.195325422286987,
|
|
"epoch": 0.1140001123153816,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999999719167785,
|
|
"loss": 6.1973,
|
|
"mean_token_accuracy": 0.14396406784653665,
|
|
"num_tokens": 2275318.0,
|
|
"step": 1015
|
|
},
|
|
{
|
|
"entropy": 6.279222393035889,
|
|
"epoch": 0.11456168922333913,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999999482752917,
|
|
"loss": 6.2363,
|
|
"mean_token_accuracy": 0.13996139094233512,
|
|
"num_tokens": 2287434.0,
|
|
"step": 1020
|
|
},
|
|
{
|
|
"entropy": 6.148661851882935,
|
|
"epoch": 0.11512326613129668,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999999174697195,
|
|
"loss": 6.1446,
|
|
"mean_token_accuracy": 0.14569470137357712,
|
|
"num_tokens": 2299145.0,
|
|
"step": 1025
|
|
},
|
|
{
|
|
"entropy": 6.20902419090271,
|
|
"epoch": 0.11568484303925422,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999998795000627,
|
|
"loss": 6.2361,
|
|
"mean_token_accuracy": 0.1427035741508007,
|
|
"num_tokens": 2309841.0,
|
|
"step": 1030
|
|
},
|
|
{
|
|
"entropy": 6.245785093307495,
|
|
"epoch": 0.11624641994721177,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004999998343663223,
|
|
"loss": 6.2287,
|
|
"mean_token_accuracy": 0.14689236134290695,
|
|
"num_tokens": 2322143.0,
|
|
"step": 1035
|
|
},
|
|
{
|
|
"entropy": 6.207674169540406,
|
|
"epoch": 0.11680799685516932,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999997820685,
|
|
"loss": 6.1692,
|
|
"mean_token_accuracy": 0.13607257902622222,
|
|
"num_tokens": 2333207.0,
|
|
"step": 1040
|
|
},
|
|
{
|
|
"entropy": 6.142008590698242,
|
|
"epoch": 0.11736957376312686,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999997226065974,
|
|
"loss": 6.2345,
|
|
"mean_token_accuracy": 0.14303019344806672,
|
|
"num_tokens": 2345542.0,
|
|
"step": 1045
|
|
},
|
|
{
|
|
"entropy": 6.261992979049682,
|
|
"epoch": 0.11793115067108441,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999996559806163,
|
|
"loss": 6.2239,
|
|
"mean_token_accuracy": 0.1461116559803486,
|
|
"num_tokens": 2356612.0,
|
|
"step": 1050
|
|
},
|
|
{
|
|
"entropy": 6.193447542190552,
|
|
"epoch": 0.11849272757904195,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999995821905589,
|
|
"loss": 6.1494,
|
|
"mean_token_accuracy": 0.141853466629982,
|
|
"num_tokens": 2368204.0,
|
|
"step": 1055
|
|
},
|
|
{
|
|
"entropy": 6.205967950820923,
|
|
"epoch": 0.1190543044869995,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004999995012364276,
|
|
"loss": 6.1814,
|
|
"mean_token_accuracy": 0.14840566962957383,
|
|
"num_tokens": 2379114.0,
|
|
"step": 1060
|
|
},
|
|
{
|
|
"entropy": 6.179318475723266,
|
|
"epoch": 0.11961588139495703,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004999994131182248,
|
|
"loss": 6.2279,
|
|
"mean_token_accuracy": 0.14043206125497817,
|
|
"num_tokens": 2390562.0,
|
|
"step": 1065
|
|
},
|
|
{
|
|
"entropy": 6.196050500869751,
|
|
"epoch": 0.12017745830291458,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999993178359535,
|
|
"loss": 6.279,
|
|
"mean_token_accuracy": 0.14168791845440865,
|
|
"num_tokens": 2402352.0,
|
|
"step": 1070
|
|
},
|
|
{
|
|
"entropy": 6.337009239196777,
|
|
"epoch": 0.12073903521087213,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999992153896166,
|
|
"loss": 6.3117,
|
|
"mean_token_accuracy": 0.13706706911325456,
|
|
"num_tokens": 2415140.0,
|
|
"step": 1075
|
|
},
|
|
{
|
|
"entropy": 6.167864894866943,
|
|
"epoch": 0.12130061211882967,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999991057792175,
|
|
"loss": 6.2003,
|
|
"mean_token_accuracy": 0.14278843253850937,
|
|
"num_tokens": 2426679.0,
|
|
"step": 1080
|
|
},
|
|
{
|
|
"entropy": 6.219503736495971,
|
|
"epoch": 0.12186218902678722,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999989890047596,
|
|
"loss": 6.248,
|
|
"mean_token_accuracy": 0.14479811787605285,
|
|
"num_tokens": 2437735.0,
|
|
"step": 1085
|
|
},
|
|
{
|
|
"entropy": 6.216965055465698,
|
|
"epoch": 0.12242376593474476,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999988650662467,
|
|
"loss": 6.1609,
|
|
"mean_token_accuracy": 0.14553387016057967,
|
|
"num_tokens": 2448611.0,
|
|
"step": 1090
|
|
},
|
|
{
|
|
"entropy": 6.157275009155273,
|
|
"epoch": 0.12298534284270231,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999987339636825,
|
|
"loss": 6.0967,
|
|
"mean_token_accuracy": 0.14453600123524665,
|
|
"num_tokens": 2461101.0,
|
|
"step": 1095
|
|
},
|
|
{
|
|
"entropy": 6.17122073173523,
|
|
"epoch": 0.12354691975065986,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999985956970713,
|
|
"loss": 6.2337,
|
|
"mean_token_accuracy": 0.1435968115925789,
|
|
"num_tokens": 2473569.0,
|
|
"step": 1100
|
|
},
|
|
{
|
|
"entropy": 6.128605556488037,
|
|
"epoch": 0.1241084966586174,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999984502664178,
|
|
"loss": 6.154,
|
|
"mean_token_accuracy": 0.14440926015377045,
|
|
"num_tokens": 2483970.0,
|
|
"step": 1105
|
|
},
|
|
{
|
|
"entropy": 6.243288946151734,
|
|
"epoch": 0.12467007356657495,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999982976717261,
|
|
"loss": 6.2036,
|
|
"mean_token_accuracy": 0.14929257482290267,
|
|
"num_tokens": 2494184.0,
|
|
"step": 1110
|
|
},
|
|
{
|
|
"entropy": 6.202071237564087,
|
|
"epoch": 0.1252316504745325,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999981379130016,
|
|
"loss": 6.217,
|
|
"mean_token_accuracy": 0.15150351971387863,
|
|
"num_tokens": 2505715.0,
|
|
"step": 1115
|
|
},
|
|
{
|
|
"entropy": 6.336061334609985,
|
|
"epoch": 0.12579322738249002,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000499997970990249,
|
|
"loss": 6.2511,
|
|
"mean_token_accuracy": 0.1450079247355461,
|
|
"num_tokens": 2517168.0,
|
|
"step": 1120
|
|
},
|
|
{
|
|
"entropy": 6.201480865478516,
|
|
"epoch": 0.12635480429044757,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999977969034737,
|
|
"loss": 6.2848,
|
|
"mean_token_accuracy": 0.14069784805178642,
|
|
"num_tokens": 2528296.0,
|
|
"step": 1125
|
|
},
|
|
{
|
|
"entropy": 6.183384132385254,
|
|
"epoch": 0.12691638119840512,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999976156526814,
|
|
"loss": 6.2323,
|
|
"mean_token_accuracy": 0.14923904538154603,
|
|
"num_tokens": 2540648.0,
|
|
"step": 1130
|
|
},
|
|
{
|
|
"entropy": 6.105208444595337,
|
|
"epoch": 0.12747795810636267,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999974272378776,
|
|
"loss": 6.1074,
|
|
"mean_token_accuracy": 0.14755125045776368,
|
|
"num_tokens": 2551840.0,
|
|
"step": 1135
|
|
},
|
|
{
|
|
"entropy": 6.281982707977295,
|
|
"epoch": 0.12803953501432022,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999972316590685,
|
|
"loss": 6.1796,
|
|
"mean_token_accuracy": 0.14292501285672188,
|
|
"num_tokens": 2561362.0,
|
|
"step": 1140
|
|
},
|
|
{
|
|
"entropy": 6.233172225952148,
|
|
"epoch": 0.12860111192227774,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999970289162604,
|
|
"loss": 6.2202,
|
|
"mean_token_accuracy": 0.14763520807027816,
|
|
"num_tokens": 2573584.0,
|
|
"step": 1145
|
|
},
|
|
{
|
|
"entropy": 6.409511280059815,
|
|
"epoch": 0.1291626888302353,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999968190094595,
|
|
"loss": 6.3481,
|
|
"mean_token_accuracy": 0.13643453121185303,
|
|
"num_tokens": 2585255.0,
|
|
"step": 1150
|
|
},
|
|
{
|
|
"entropy": 5.988052415847778,
|
|
"epoch": 0.12972426573819285,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999966019386727,
|
|
"loss": 6.1576,
|
|
"mean_token_accuracy": 0.1477419465780258,
|
|
"num_tokens": 2596849.0,
|
|
"step": 1155
|
|
},
|
|
{
|
|
"entropy": 6.210149669647217,
|
|
"epoch": 0.1302858426461504,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999963777039067,
|
|
"loss": 6.173,
|
|
"mean_token_accuracy": 0.1465044140815735,
|
|
"num_tokens": 2606918.0,
|
|
"step": 1160
|
|
},
|
|
{
|
|
"entropy": 6.072638034820557,
|
|
"epoch": 0.13084741955410795,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000499996146305169,
|
|
"loss": 6.1161,
|
|
"mean_token_accuracy": 0.14757418036460876,
|
|
"num_tokens": 2617779.0,
|
|
"step": 1165
|
|
},
|
|
{
|
|
"entropy": 6.211462831497192,
|
|
"epoch": 0.13140899646206547,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999959077424665,
|
|
"loss": 6.18,
|
|
"mean_token_accuracy": 0.1446642979979515,
|
|
"num_tokens": 2630294.0,
|
|
"step": 1170
|
|
},
|
|
{
|
|
"entropy": 6.054007196426392,
|
|
"epoch": 0.13197057337002302,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999956620158072,
|
|
"loss": 6.0855,
|
|
"mean_token_accuracy": 0.14947691634297372,
|
|
"num_tokens": 2641002.0,
|
|
"step": 1175
|
|
},
|
|
{
|
|
"entropy": 6.122717094421387,
|
|
"epoch": 0.13253215027798057,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999954091251987,
|
|
"loss": 6.0758,
|
|
"mean_token_accuracy": 0.14981181919574738,
|
|
"num_tokens": 2652188.0,
|
|
"step": 1180
|
|
},
|
|
{
|
|
"entropy": 6.109769439697265,
|
|
"epoch": 0.13309372718593812,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004999951490706491,
|
|
"loss": 6.1264,
|
|
"mean_token_accuracy": 0.1440470039844513,
|
|
"num_tokens": 2662542.0,
|
|
"step": 1185
|
|
},
|
|
{
|
|
"entropy": 6.21925458908081,
|
|
"epoch": 0.13365530409389567,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999948818521667,
|
|
"loss": 6.1272,
|
|
"mean_token_accuracy": 0.14722256660461425,
|
|
"num_tokens": 2673292.0,
|
|
"step": 1190
|
|
},
|
|
{
|
|
"entropy": 6.075178432464599,
|
|
"epoch": 0.1342168810018532,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00049999460746976,
|
|
"loss": 6.1347,
|
|
"mean_token_accuracy": 0.14970383197069168,
|
|
"num_tokens": 2684042.0,
|
|
"step": 1195
|
|
},
|
|
{
|
|
"entropy": 6.1581121444702145,
|
|
"epoch": 0.13477845790981074,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999943259234377,
|
|
"loss": 6.0663,
|
|
"mean_token_accuracy": 0.15224399790167809,
|
|
"num_tokens": 2694716.0,
|
|
"step": 1200
|
|
},
|
|
{
|
|
"entropy": 6.207530212402344,
|
|
"epoch": 0.1353400348177683,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999940372132089,
|
|
"loss": 6.2015,
|
|
"mean_token_accuracy": 0.14769889712333678,
|
|
"num_tokens": 2706200.0,
|
|
"step": 1205
|
|
},
|
|
{
|
|
"entropy": 6.00968189239502,
|
|
"epoch": 0.13590161172572585,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999937413390826,
|
|
"loss": 6.029,
|
|
"mean_token_accuracy": 0.1579593226313591,
|
|
"num_tokens": 2716814.0,
|
|
"step": 1210
|
|
},
|
|
{
|
|
"entropy": 6.197681665420532,
|
|
"epoch": 0.1364631886336834,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999934383010683,
|
|
"loss": 6.1915,
|
|
"mean_token_accuracy": 0.1422519750893116,
|
|
"num_tokens": 2728042.0,
|
|
"step": 1215
|
|
},
|
|
{
|
|
"entropy": 6.090554714202881,
|
|
"epoch": 0.13702476554164092,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999931280991757,
|
|
"loss": 6.1574,
|
|
"mean_token_accuracy": 0.14087326154112817,
|
|
"num_tokens": 2739093.0,
|
|
"step": 1220
|
|
},
|
|
{
|
|
"entropy": 6.269927358627319,
|
|
"epoch": 0.13758634244959847,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999928107334146,
|
|
"loss": 6.1912,
|
|
"mean_token_accuracy": 0.1486273668706417,
|
|
"num_tokens": 2750307.0,
|
|
"step": 1225
|
|
},
|
|
{
|
|
"entropy": 6.043987274169922,
|
|
"epoch": 0.13814791935755602,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999924862037952,
|
|
"loss": 6.1095,
|
|
"mean_token_accuracy": 0.14710069075226784,
|
|
"num_tokens": 2760534.0,
|
|
"step": 1230
|
|
},
|
|
{
|
|
"entropy": 6.096903324127197,
|
|
"epoch": 0.13870949626551357,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999921545103278,
|
|
"loss": 6.1318,
|
|
"mean_token_accuracy": 0.1434743322432041,
|
|
"num_tokens": 2772459.0,
|
|
"step": 1235
|
|
},
|
|
{
|
|
"entropy": 6.099786233901978,
|
|
"epoch": 0.1392710731734711,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999918156530229,
|
|
"loss": 6.0683,
|
|
"mean_token_accuracy": 0.15236157774925232,
|
|
"num_tokens": 2784038.0,
|
|
"step": 1240
|
|
},
|
|
{
|
|
"entropy": 6.175437688827515,
|
|
"epoch": 0.13983265008142864,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004999914696318913,
|
|
"loss": 6.1715,
|
|
"mean_token_accuracy": 0.15088060572743417,
|
|
"num_tokens": 2795756.0,
|
|
"step": 1245
|
|
},
|
|
{
|
|
"entropy": 6.024715280532837,
|
|
"epoch": 0.1403942269893862,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999911164469441,
|
|
"loss": 6.0995,
|
|
"mean_token_accuracy": 0.15212466195225716,
|
|
"num_tokens": 2806242.0,
|
|
"step": 1250
|
|
},
|
|
{
|
|
"entropy": 6.247219705581665,
|
|
"epoch": 0.14095580389734375,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999907560981925,
|
|
"loss": 6.1857,
|
|
"mean_token_accuracy": 0.15046648532152176,
|
|
"num_tokens": 2817017.0,
|
|
"step": 1255
|
|
},
|
|
{
|
|
"entropy": 6.09092493057251,
|
|
"epoch": 0.1415173808053013,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004999903885856479,
|
|
"loss": 6.0958,
|
|
"mean_token_accuracy": 0.1522834211587906,
|
|
"num_tokens": 2827415.0,
|
|
"step": 1260
|
|
},
|
|
{
|
|
"entropy": 6.107750749588012,
|
|
"epoch": 0.14207895771325882,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000499990013909322,
|
|
"loss": 6.1021,
|
|
"mean_token_accuracy": 0.15155476704239845,
|
|
"num_tokens": 2837595.0,
|
|
"step": 1265
|
|
},
|
|
{
|
|
"entropy": 6.04247636795044,
|
|
"epoch": 0.14264053462121637,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000499989632069227,
|
|
"loss": 6.0541,
|
|
"mean_token_accuracy": 0.15045821368694307,
|
|
"num_tokens": 2847906.0,
|
|
"step": 1270
|
|
},
|
|
{
|
|
"entropy": 6.18963623046875,
|
|
"epoch": 0.14320211152917392,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999892430653747,
|
|
"loss": 6.1627,
|
|
"mean_token_accuracy": 0.14105737060308457,
|
|
"num_tokens": 2859145.0,
|
|
"step": 1275
|
|
},
|
|
{
|
|
"entropy": 6.007845020294189,
|
|
"epoch": 0.14376368843713147,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999888468977776,
|
|
"loss": 6.0959,
|
|
"mean_token_accuracy": 0.15220187604427338,
|
|
"num_tokens": 2870704.0,
|
|
"step": 1280
|
|
},
|
|
{
|
|
"entropy": 6.178721904754639,
|
|
"epoch": 0.14432526534508902,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004999884435664485,
|
|
"loss": 6.1953,
|
|
"mean_token_accuracy": 0.14668623208999634,
|
|
"num_tokens": 2881861.0,
|
|
"step": 1285
|
|
},
|
|
{
|
|
"entropy": 6.141765451431274,
|
|
"epoch": 0.14488684225304654,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004999880330714,
|
|
"loss": 6.1209,
|
|
"mean_token_accuracy": 0.14705499708652497,
|
|
"num_tokens": 2893247.0,
|
|
"step": 1290
|
|
},
|
|
{
|
|
"entropy": 6.0013285160064695,
|
|
"epoch": 0.1454484191610041,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999876154126453,
|
|
"loss": 5.9583,
|
|
"mean_token_accuracy": 0.15296627581119537,
|
|
"num_tokens": 2905351.0,
|
|
"step": 1295
|
|
},
|
|
{
|
|
"entropy": 6.037969493865967,
|
|
"epoch": 0.14600999606896164,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004999871905901977,
|
|
"loss": 6.1225,
|
|
"mean_token_accuracy": 0.1543628215789795,
|
|
"num_tokens": 2915153.0,
|
|
"step": 1300
|
|
},
|
|
{
|
|
"entropy": 6.088203096389771,
|
|
"epoch": 0.1465715729769192,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999867586040706,
|
|
"loss": 6.0818,
|
|
"mean_token_accuracy": 0.1409442000091076,
|
|
"num_tokens": 2926234.0,
|
|
"step": 1305
|
|
},
|
|
{
|
|
"entropy": 6.034757328033447,
|
|
"epoch": 0.14713314988487675,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004999863194542779,
|
|
"loss": 6.0382,
|
|
"mean_token_accuracy": 0.14932841658592225,
|
|
"num_tokens": 2937033.0,
|
|
"step": 1310
|
|
},
|
|
{
|
|
"entropy": 5.98197832107544,
|
|
"epoch": 0.14769472679283427,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999858731408336,
|
|
"loss": 5.9892,
|
|
"mean_token_accuracy": 0.15037224739789962,
|
|
"num_tokens": 2945904.0,
|
|
"step": 1315
|
|
},
|
|
{
|
|
"entropy": 6.145388412475586,
|
|
"epoch": 0.14825630370079182,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999854196637518,
|
|
"loss": 6.1932,
|
|
"mean_token_accuracy": 0.14344180449843408,
|
|
"num_tokens": 2956298.0,
|
|
"step": 1320
|
|
},
|
|
{
|
|
"entropy": 6.1224785327911375,
|
|
"epoch": 0.14881788060874937,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999849590230469,
|
|
"loss": 6.086,
|
|
"mean_token_accuracy": 0.14912800639867782,
|
|
"num_tokens": 2967660.0,
|
|
"step": 1325
|
|
},
|
|
{
|
|
"entropy": 6.100721311569214,
|
|
"epoch": 0.14937945751670692,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999844912187336,
|
|
"loss": 6.1553,
|
|
"mean_token_accuracy": 0.144637381285429,
|
|
"num_tokens": 2978616.0,
|
|
"step": 1330
|
|
},
|
|
{
|
|
"entropy": 6.073033952713013,
|
|
"epoch": 0.14994103442466447,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000499984016250827,
|
|
"loss": 6.0141,
|
|
"mean_token_accuracy": 0.15408604294061662,
|
|
"num_tokens": 2989731.0,
|
|
"step": 1335
|
|
},
|
|
{
|
|
"entropy": 6.064854526519776,
|
|
"epoch": 0.150502611332622,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000499983534119342,
|
|
"loss": 6.1129,
|
|
"mean_token_accuracy": 0.14977738112211228,
|
|
"num_tokens": 3002110.0,
|
|
"step": 1340
|
|
},
|
|
{
|
|
"entropy": 5.9426251411437985,
|
|
"epoch": 0.15106418824057954,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999830448242941,
|
|
"loss": 5.9475,
|
|
"mean_token_accuracy": 0.15703770220279695,
|
|
"num_tokens": 3012709.0,
|
|
"step": 1345
|
|
},
|
|
{
|
|
"entropy": 6.131820631027222,
|
|
"epoch": 0.1516257651485371,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999825483656986,
|
|
"loss": 6.2455,
|
|
"mean_token_accuracy": 0.1342325508594513,
|
|
"num_tokens": 3025738.0,
|
|
"step": 1350
|
|
},
|
|
{
|
|
"entropy": 6.112554025650025,
|
|
"epoch": 0.15218734205649465,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999820447435716,
|
|
"loss": 6.0857,
|
|
"mean_token_accuracy": 0.14610055312514306,
|
|
"num_tokens": 3037711.0,
|
|
"step": 1355
|
|
},
|
|
{
|
|
"entropy": 6.128893566131592,
|
|
"epoch": 0.15274891896445217,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004999815339579291,
|
|
"loss": 6.2663,
|
|
"mean_token_accuracy": 0.14104711413383483,
|
|
"num_tokens": 3048929.0,
|
|
"step": 1360
|
|
},
|
|
{
|
|
"entropy": 6.004623556137085,
|
|
"epoch": 0.15331049587240972,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999810160087872,
|
|
"loss": 6.0124,
|
|
"mean_token_accuracy": 0.16021226793527604,
|
|
"num_tokens": 3059717.0,
|
|
"step": 1365
|
|
},
|
|
{
|
|
"entropy": 6.133885765075684,
|
|
"epoch": 0.15387207278036727,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999804908961626,
|
|
"loss": 6.021,
|
|
"mean_token_accuracy": 0.15278894901275636,
|
|
"num_tokens": 3069530.0,
|
|
"step": 1370
|
|
},
|
|
{
|
|
"entropy": 6.060817289352417,
|
|
"epoch": 0.15443364968832482,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999799586200719,
|
|
"loss": 6.2034,
|
|
"mean_token_accuracy": 0.14277547895908355,
|
|
"num_tokens": 3080705.0,
|
|
"step": 1375
|
|
},
|
|
{
|
|
"entropy": 6.12487678527832,
|
|
"epoch": 0.15499522659628237,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000499979419180532,
|
|
"loss": 6.05,
|
|
"mean_token_accuracy": 0.14793222546577453,
|
|
"num_tokens": 3092553.0,
|
|
"step": 1380
|
|
},
|
|
{
|
|
"entropy": 6.1220231533050535,
|
|
"epoch": 0.1555568035042399,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999788725775601,
|
|
"loss": 6.1698,
|
|
"mean_token_accuracy": 0.14677260369062423,
|
|
"num_tokens": 3102947.0,
|
|
"step": 1385
|
|
},
|
|
{
|
|
"entropy": 6.0232137680053714,
|
|
"epoch": 0.15611838041219744,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999783188111737,
|
|
"loss": 6.0268,
|
|
"mean_token_accuracy": 0.15328849405050277,
|
|
"num_tokens": 3114157.0,
|
|
"step": 1390
|
|
},
|
|
{
|
|
"entropy": 5.97393045425415,
|
|
"epoch": 0.156679957320155,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999777578813904,
|
|
"loss": 5.8774,
|
|
"mean_token_accuracy": 0.15145869851112365,
|
|
"num_tokens": 3125739.0,
|
|
"step": 1395
|
|
},
|
|
{
|
|
"entropy": 5.978219079971313,
|
|
"epoch": 0.15724153422811254,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000499977189788228,
|
|
"loss": 6.0612,
|
|
"mean_token_accuracy": 0.14800369888544082,
|
|
"num_tokens": 3136970.0,
|
|
"step": 1400
|
|
},
|
|
{
|
|
"entropy": 6.052120590209961,
|
|
"epoch": 0.1578031111360701,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004999766145317046,
|
|
"loss": 6.0165,
|
|
"mean_token_accuracy": 0.1507661908864975,
|
|
"num_tokens": 3148512.0,
|
|
"step": 1405
|
|
},
|
|
{
|
|
"entropy": 6.046875762939453,
|
|
"epoch": 0.15836468804402762,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004999760321118385,
|
|
"loss": 6.0514,
|
|
"mean_token_accuracy": 0.15795802175998688,
|
|
"num_tokens": 3159477.0,
|
|
"step": 1410
|
|
},
|
|
{
|
|
"entropy": 6.054330587387085,
|
|
"epoch": 0.15892626495198517,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004999754425286483,
|
|
"loss": 6.0805,
|
|
"mean_token_accuracy": 0.1510605439543724,
|
|
"num_tokens": 3171361.0,
|
|
"step": 1415
|
|
},
|
|
{
|
|
"entropy": 6.137837696075439,
|
|
"epoch": 0.15948784185994272,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004999748457821529,
|
|
"loss": 6.2381,
|
|
"mean_token_accuracy": 0.14512607157230378,
|
|
"num_tokens": 3184652.0,
|
|
"step": 1420
|
|
},
|
|
{
|
|
"entropy": 6.12110710144043,
|
|
"epoch": 0.16004941876790027,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000499974241872371,
|
|
"loss": 6.1198,
|
|
"mean_token_accuracy": 0.1497162714600563,
|
|
"num_tokens": 3195557.0,
|
|
"step": 1425
|
|
},
|
|
{
|
|
"entropy": 6.106506776809693,
|
|
"epoch": 0.16061099567585782,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999736307993221,
|
|
"loss": 6.1607,
|
|
"mean_token_accuracy": 0.14291600361466408,
|
|
"num_tokens": 3207139.0,
|
|
"step": 1430
|
|
},
|
|
{
|
|
"entropy": 6.2219688415527346,
|
|
"epoch": 0.16117257258381534,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999730125630255,
|
|
"loss": 6.2392,
|
|
"mean_token_accuracy": 0.14155336767435073,
|
|
"num_tokens": 3218967.0,
|
|
"step": 1435
|
|
},
|
|
{
|
|
"entropy": 6.109693098068237,
|
|
"epoch": 0.1617341494917729,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999723871635008,
|
|
"loss": 6.0436,
|
|
"mean_token_accuracy": 0.15356535315513611,
|
|
"num_tokens": 3230168.0,
|
|
"step": 1440
|
|
},
|
|
{
|
|
"entropy": 5.984784889221191,
|
|
"epoch": 0.16229572639973044,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999717546007681,
|
|
"loss": 6.0847,
|
|
"mean_token_accuracy": 0.14737009704113008,
|
|
"num_tokens": 3241829.0,
|
|
"step": 1445
|
|
},
|
|
{
|
|
"entropy": 6.153935098648072,
|
|
"epoch": 0.162857303307688,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999711148748476,
|
|
"loss": 6.1063,
|
|
"mean_token_accuracy": 0.14692701324820517,
|
|
"num_tokens": 3253195.0,
|
|
"step": 1450
|
|
},
|
|
{
|
|
"entropy": 5.995780324935913,
|
|
"epoch": 0.16341888021564555,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999704679857594,
|
|
"loss": 6.1558,
|
|
"mean_token_accuracy": 0.14414109736680986,
|
|
"num_tokens": 3264951.0,
|
|
"step": 1455
|
|
},
|
|
{
|
|
"entropy": 6.000380754470825,
|
|
"epoch": 0.16398045712360307,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004999698139335243,
|
|
"loss": 5.9889,
|
|
"mean_token_accuracy": 0.15342536345124244,
|
|
"num_tokens": 3276054.0,
|
|
"step": 1460
|
|
},
|
|
{
|
|
"entropy": 6.0266814708709715,
|
|
"epoch": 0.16454203403156062,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999691527181632,
|
|
"loss": 5.9538,
|
|
"mean_token_accuracy": 0.16273668259382248,
|
|
"num_tokens": 3285540.0,
|
|
"step": 1465
|
|
},
|
|
{
|
|
"entropy": 6.139036989212036,
|
|
"epoch": 0.16510361093951817,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999684843396968,
|
|
"loss": 6.0966,
|
|
"mean_token_accuracy": 0.15268264412879945,
|
|
"num_tokens": 3296869.0,
|
|
"step": 1470
|
|
},
|
|
{
|
|
"entropy": 5.987323665618897,
|
|
"epoch": 0.16566518784747572,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999678087981467,
|
|
"loss": 6.0341,
|
|
"mean_token_accuracy": 0.15864946991205214,
|
|
"num_tokens": 3307554.0,
|
|
"step": 1475
|
|
},
|
|
{
|
|
"entropy": 5.990738153457642,
|
|
"epoch": 0.16622676475543324,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999671260935343,
|
|
"loss": 5.9785,
|
|
"mean_token_accuracy": 0.1486981876194477,
|
|
"num_tokens": 3319685.0,
|
|
"step": 1480
|
|
},
|
|
{
|
|
"entropy": 6.0045812129974365,
|
|
"epoch": 0.1667883416633908,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999664362258814,
|
|
"loss": 6.0908,
|
|
"mean_token_accuracy": 0.15280628502368926,
|
|
"num_tokens": 3330742.0,
|
|
"step": 1485
|
|
},
|
|
{
|
|
"entropy": 6.038333177566528,
|
|
"epoch": 0.16734991857134834,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004999657391952099,
|
|
"loss": 6.1239,
|
|
"mean_token_accuracy": 0.14859175980091094,
|
|
"num_tokens": 3343613.0,
|
|
"step": 1490
|
|
},
|
|
{
|
|
"entropy": 6.221092224121094,
|
|
"epoch": 0.1679114954793059,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.000499965035001542,
|
|
"loss": 6.1615,
|
|
"mean_token_accuracy": 0.1505799412727356,
|
|
"num_tokens": 3355162.0,
|
|
"step": 1495
|
|
},
|
|
{
|
|
"entropy": 6.0329444885253904,
|
|
"epoch": 0.16847307238726345,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004999643236449001,
|
|
"loss": 6.0893,
|
|
"mean_token_accuracy": 0.15589706897735595,
|
|
"num_tokens": 3366324.0,
|
|
"step": 1500
|
|
},
|
|
{
|
|
"entropy": 6.223443603515625,
|
|
"epoch": 0.16903464929522097,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999636051253069,
|
|
"loss": 6.2532,
|
|
"mean_token_accuracy": 0.14020101502537727,
|
|
"num_tokens": 3378571.0,
|
|
"step": 1505
|
|
},
|
|
{
|
|
"entropy": 6.0646978378295895,
|
|
"epoch": 0.16959622620317852,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999628794427854,
|
|
"loss": 6.1196,
|
|
"mean_token_accuracy": 0.14431381821632386,
|
|
"num_tokens": 3390605.0,
|
|
"step": 1510
|
|
},
|
|
{
|
|
"entropy": 6.004722833633423,
|
|
"epoch": 0.17015780311113607,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004999621465973583,
|
|
"loss": 6.0392,
|
|
"mean_token_accuracy": 0.15314660519361495,
|
|
"num_tokens": 3402735.0,
|
|
"step": 1515
|
|
},
|
|
{
|
|
"entropy": 6.060815286636353,
|
|
"epoch": 0.17071938001909362,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999614065890495,
|
|
"loss": 6.0447,
|
|
"mean_token_accuracy": 0.15331753641366958,
|
|
"num_tokens": 3413079.0,
|
|
"step": 1520
|
|
},
|
|
{
|
|
"entropy": 6.024934005737305,
|
|
"epoch": 0.17128095692705117,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999606594178821,
|
|
"loss": 5.981,
|
|
"mean_token_accuracy": 0.1547686666250229,
|
|
"num_tokens": 3423098.0,
|
|
"step": 1525
|
|
},
|
|
{
|
|
"entropy": 5.996307277679444,
|
|
"epoch": 0.1718425338350087,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00049995990508388,
|
|
"loss": 6.0304,
|
|
"mean_token_accuracy": 0.14579071775078772,
|
|
"num_tokens": 3435794.0,
|
|
"step": 1530
|
|
},
|
|
{
|
|
"entropy": 6.084369087219239,
|
|
"epoch": 0.17240411074296624,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999591435870674,
|
|
"loss": 6.1508,
|
|
"mean_token_accuracy": 0.14353759735822677,
|
|
"num_tokens": 3448125.0,
|
|
"step": 1535
|
|
},
|
|
{
|
|
"entropy": 6.049730348587036,
|
|
"epoch": 0.1729656876509238,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004999583749274684,
|
|
"loss": 5.9901,
|
|
"mean_token_accuracy": 0.14831836372613907,
|
|
"num_tokens": 3458217.0,
|
|
"step": 1540
|
|
},
|
|
{
|
|
"entropy": 5.919715738296508,
|
|
"epoch": 0.17352726455888134,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004999575991051074,
|
|
"loss": 6.0305,
|
|
"mean_token_accuracy": 0.15307833701372148,
|
|
"num_tokens": 3469553.0,
|
|
"step": 1545
|
|
},
|
|
{
|
|
"entropy": 6.114363336563111,
|
|
"epoch": 0.1740888414668389,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004999568161200093,
|
|
"loss": 5.9779,
|
|
"mean_token_accuracy": 0.1559588521718979,
|
|
"num_tokens": 3480928.0,
|
|
"step": 1550
|
|
},
|
|
{
|
|
"entropy": 5.951780652999878,
|
|
"epoch": 0.17465041837479642,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999560259721989,
|
|
"loss": 6.0732,
|
|
"mean_token_accuracy": 0.15480699986219407,
|
|
"num_tokens": 3492074.0,
|
|
"step": 1555
|
|
},
|
|
{
|
|
"entropy": 6.126809167861938,
|
|
"epoch": 0.17521199528275397,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999552286617014,
|
|
"loss": 6.0929,
|
|
"mean_token_accuracy": 0.14737773016095163,
|
|
"num_tokens": 3503320.0,
|
|
"step": 1560
|
|
},
|
|
{
|
|
"entropy": 5.924575614929199,
|
|
"epoch": 0.17577357219071152,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004999544241885421,
|
|
"loss": 6.0907,
|
|
"mean_token_accuracy": 0.15473493337631225,
|
|
"num_tokens": 3515466.0,
|
|
"step": 1565
|
|
},
|
|
{
|
|
"entropy": 6.097070169448853,
|
|
"epoch": 0.17633514909866907,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999536125527467,
|
|
"loss": 5.9621,
|
|
"mean_token_accuracy": 0.15532948821783066,
|
|
"num_tokens": 3525584.0,
|
|
"step": 1570
|
|
},
|
|
{
|
|
"entropy": 5.932310962677002,
|
|
"epoch": 0.17689672600662662,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000499952793754341,
|
|
"loss": 6.0479,
|
|
"mean_token_accuracy": 0.15254408866167068,
|
|
"num_tokens": 3536973.0,
|
|
"step": 1575
|
|
},
|
|
{
|
|
"entropy": 6.076006174087524,
|
|
"epoch": 0.17745830291458414,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999519677933512,
|
|
"loss": 6.068,
|
|
"mean_token_accuracy": 0.1462039828300476,
|
|
"num_tokens": 3547799.0,
|
|
"step": 1580
|
|
},
|
|
{
|
|
"entropy": 6.051251935958862,
|
|
"epoch": 0.1780198798225417,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999511346698035,
|
|
"loss": 6.1402,
|
|
"mean_token_accuracy": 0.15270229279994965,
|
|
"num_tokens": 3558436.0,
|
|
"step": 1585
|
|
},
|
|
{
|
|
"entropy": 6.075060796737671,
|
|
"epoch": 0.17858145673049924,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999502943837244,
|
|
"loss": 6.1099,
|
|
"mean_token_accuracy": 0.14984554573893547,
|
|
"num_tokens": 3569851.0,
|
|
"step": 1590
|
|
},
|
|
{
|
|
"entropy": 6.072784328460694,
|
|
"epoch": 0.1791430336384568,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999494469351406,
|
|
"loss": 5.9975,
|
|
"mean_token_accuracy": 0.1523696780204773,
|
|
"num_tokens": 3580797.0,
|
|
"step": 1595
|
|
},
|
|
{
|
|
"entropy": 5.95513882637024,
|
|
"epoch": 0.17970461054641435,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004999485923240793,
|
|
"loss": 6.0015,
|
|
"mean_token_accuracy": 0.15557911098003388,
|
|
"num_tokens": 3592552.0,
|
|
"step": 1600
|
|
},
|
|
{
|
|
"entropy": 5.924554920196533,
|
|
"epoch": 0.18026618745437187,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999477305505675,
|
|
"loss": 5.9749,
|
|
"mean_token_accuracy": 0.15742649883031845,
|
|
"num_tokens": 3603932.0,
|
|
"step": 1605
|
|
},
|
|
{
|
|
"entropy": 6.073954391479492,
|
|
"epoch": 0.18082776436232942,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999468616146328,
|
|
"loss": 6.0011,
|
|
"mean_token_accuracy": 0.15938193053007127,
|
|
"num_tokens": 3614865.0,
|
|
"step": 1610
|
|
},
|
|
{
|
|
"entropy": 5.830797386169434,
|
|
"epoch": 0.18138934127028697,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004999459855163026,
|
|
"loss": 5.9145,
|
|
"mean_token_accuracy": 0.16182959228754043,
|
|
"num_tokens": 3626275.0,
|
|
"step": 1615
|
|
},
|
|
{
|
|
"entropy": 6.119184446334839,
|
|
"epoch": 0.18195091817824452,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000499945102255605,
|
|
"loss": 6.0521,
|
|
"mean_token_accuracy": 0.14493129253387452,
|
|
"num_tokens": 3638416.0,
|
|
"step": 1620
|
|
},
|
|
{
|
|
"entropy": 5.841647100448609,
|
|
"epoch": 0.18251249508620204,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999442118325682,
|
|
"loss": 5.914,
|
|
"mean_token_accuracy": 0.15349768698215485,
|
|
"num_tokens": 3649651.0,
|
|
"step": 1625
|
|
},
|
|
{
|
|
"entropy": 6.104454708099365,
|
|
"epoch": 0.1830740719941596,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999433142472205,
|
|
"loss": 6.1421,
|
|
"mean_token_accuracy": 0.15380819290876388,
|
|
"num_tokens": 3661172.0,
|
|
"step": 1630
|
|
},
|
|
{
|
|
"entropy": 6.020826244354248,
|
|
"epoch": 0.18363564890211714,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999424094995902,
|
|
"loss": 5.9808,
|
|
"mean_token_accuracy": 0.15556206181645393,
|
|
"num_tokens": 3672086.0,
|
|
"step": 1635
|
|
},
|
|
{
|
|
"entropy": 5.994270944595337,
|
|
"epoch": 0.1841972258100747,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999414975897066,
|
|
"loss": 5.9515,
|
|
"mean_token_accuracy": 0.14953627586364746,
|
|
"num_tokens": 3682579.0,
|
|
"step": 1640
|
|
},
|
|
{
|
|
"entropy": 5.990695476531982,
|
|
"epoch": 0.18475880271803224,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999405785175983,
|
|
"loss": 6.079,
|
|
"mean_token_accuracy": 0.14778541773557663,
|
|
"num_tokens": 3694616.0,
|
|
"step": 1645
|
|
},
|
|
{
|
|
"entropy": 5.978005743026733,
|
|
"epoch": 0.18532037962598977,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004999396522832949,
|
|
"loss": 5.8758,
|
|
"mean_token_accuracy": 0.1531972438097,
|
|
"num_tokens": 3706821.0,
|
|
"step": 1650
|
|
},
|
|
{
|
|
"entropy": 5.889989376068115,
|
|
"epoch": 0.18588195653394732,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999387188868256,
|
|
"loss": 5.9273,
|
|
"mean_token_accuracy": 0.15852929949760436,
|
|
"num_tokens": 3717552.0,
|
|
"step": 1655
|
|
},
|
|
{
|
|
"entropy": 5.905278635025025,
|
|
"epoch": 0.18644353344190487,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999377783282203,
|
|
"loss": 5.9912,
|
|
"mean_token_accuracy": 0.15589216947555543,
|
|
"num_tokens": 3728300.0,
|
|
"step": 1660
|
|
},
|
|
{
|
|
"entropy": 6.02183518409729,
|
|
"epoch": 0.18700511034986242,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999368306075089,
|
|
"loss": 5.9972,
|
|
"mean_token_accuracy": 0.1597116097807884,
|
|
"num_tokens": 3738545.0,
|
|
"step": 1665
|
|
},
|
|
{
|
|
"entropy": 5.979436302185059,
|
|
"epoch": 0.18756668725781997,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999358757247215,
|
|
"loss": 5.9783,
|
|
"mean_token_accuracy": 0.14943412095308303,
|
|
"num_tokens": 3749190.0,
|
|
"step": 1670
|
|
},
|
|
{
|
|
"entropy": 5.959722089767456,
|
|
"epoch": 0.1881282641657775,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999349136798886,
|
|
"loss": 5.981,
|
|
"mean_token_accuracy": 0.15386179089546204,
|
|
"num_tokens": 3760978.0,
|
|
"step": 1675
|
|
},
|
|
{
|
|
"entropy": 5.930982160568237,
|
|
"epoch": 0.18868984107373504,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999339444730409,
|
|
"loss": 5.8861,
|
|
"mean_token_accuracy": 0.16179933100938798,
|
|
"num_tokens": 3771339.0,
|
|
"step": 1680
|
|
},
|
|
{
|
|
"entropy": 5.894923877716065,
|
|
"epoch": 0.1892514179816926,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999329681042092,
|
|
"loss": 5.8776,
|
|
"mean_token_accuracy": 0.1578032448887825,
|
|
"num_tokens": 3781550.0,
|
|
"step": 1685
|
|
},
|
|
{
|
|
"entropy": 5.945049524307251,
|
|
"epoch": 0.18981299488965014,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999319845734243,
|
|
"loss": 6.0749,
|
|
"mean_token_accuracy": 0.14614835679531096,
|
|
"num_tokens": 3793700.0,
|
|
"step": 1690
|
|
},
|
|
{
|
|
"entropy": 6.10129976272583,
|
|
"epoch": 0.1903745717976077,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004999309938807181,
|
|
"loss": 6.0877,
|
|
"mean_token_accuracy": 0.14818220138549804,
|
|
"num_tokens": 3806114.0,
|
|
"step": 1695
|
|
},
|
|
{
|
|
"entropy": 6.009927606582641,
|
|
"epoch": 0.19093614870556522,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999299960261216,
|
|
"loss": 5.9971,
|
|
"mean_token_accuracy": 0.15579494088888168,
|
|
"num_tokens": 3817251.0,
|
|
"step": 1700
|
|
},
|
|
{
|
|
"entropy": 6.021753025054932,
|
|
"epoch": 0.19149772561352277,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999289910096669,
|
|
"loss": 5.9984,
|
|
"mean_token_accuracy": 0.15699151009321213,
|
|
"num_tokens": 3828544.0,
|
|
"step": 1705
|
|
},
|
|
{
|
|
"entropy": 5.936778211593628,
|
|
"epoch": 0.19205930252148032,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999279788313858,
|
|
"loss": 6.0784,
|
|
"mean_token_accuracy": 0.1482350543141365,
|
|
"num_tokens": 3840423.0,
|
|
"step": 1710
|
|
},
|
|
{
|
|
"entropy": 6.044998502731323,
|
|
"epoch": 0.19262087942943787,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999269594913107,
|
|
"loss": 5.9499,
|
|
"mean_token_accuracy": 0.1557842820882797,
|
|
"num_tokens": 3852751.0,
|
|
"step": 1715
|
|
},
|
|
{
|
|
"entropy": 5.923951292037964,
|
|
"epoch": 0.19318245633739542,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999259329894739,
|
|
"loss": 5.9688,
|
|
"mean_token_accuracy": 0.15682801008224487,
|
|
"num_tokens": 3863382.0,
|
|
"step": 1720
|
|
},
|
|
{
|
|
"entropy": 5.945568609237671,
|
|
"epoch": 0.19374403324535294,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999248993259081,
|
|
"loss": 5.9551,
|
|
"mean_token_accuracy": 0.15532025545835496,
|
|
"num_tokens": 3874294.0,
|
|
"step": 1725
|
|
},
|
|
{
|
|
"entropy": 6.029332208633423,
|
|
"epoch": 0.1943056101533105,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999238585006463,
|
|
"loss": 5.9936,
|
|
"mean_token_accuracy": 0.14985496252775193,
|
|
"num_tokens": 3886693.0,
|
|
"step": 1730
|
|
},
|
|
{
|
|
"entropy": 5.920456075668335,
|
|
"epoch": 0.19486718706126804,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999228105137218,
|
|
"loss": 5.903,
|
|
"mean_token_accuracy": 0.15718905329704286,
|
|
"num_tokens": 3897755.0,
|
|
"step": 1735
|
|
},
|
|
{
|
|
"entropy": 5.919322395324707,
|
|
"epoch": 0.1954287639692256,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999217553651676,
|
|
"loss": 5.911,
|
|
"mean_token_accuracy": 0.15721050798892974,
|
|
"num_tokens": 3909418.0,
|
|
"step": 1740
|
|
},
|
|
{
|
|
"entropy": 6.016758823394776,
|
|
"epoch": 0.19599034087718312,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999206930550175,
|
|
"loss": 6.0567,
|
|
"mean_token_accuracy": 0.155558230727911,
|
|
"num_tokens": 3919992.0,
|
|
"step": 1745
|
|
},
|
|
{
|
|
"entropy": 5.989148473739624,
|
|
"epoch": 0.19655191778514067,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999196235833054,
|
|
"loss": 5.9243,
|
|
"mean_token_accuracy": 0.16066254824399948,
|
|
"num_tokens": 3930648.0,
|
|
"step": 1750
|
|
},
|
|
{
|
|
"entropy": 5.874900245666504,
|
|
"epoch": 0.19711349469309822,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004999185469500651,
|
|
"loss": 5.912,
|
|
"mean_token_accuracy": 0.1617908239364624,
|
|
"num_tokens": 3941883.0,
|
|
"step": 1755
|
|
},
|
|
{
|
|
"entropy": 5.944765615463257,
|
|
"epoch": 0.19767507160105577,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000499917463155331,
|
|
"loss": 5.9595,
|
|
"mean_token_accuracy": 0.16456409245729448,
|
|
"num_tokens": 3952005.0,
|
|
"step": 1760
|
|
},
|
|
{
|
|
"entropy": 5.885277271270752,
|
|
"epoch": 0.19823664850901332,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999163721991378,
|
|
"loss": 5.8826,
|
|
"mean_token_accuracy": 0.15741392374038696,
|
|
"num_tokens": 3963720.0,
|
|
"step": 1765
|
|
},
|
|
{
|
|
"entropy": 5.905065631866455,
|
|
"epoch": 0.19879822541697084,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00049991527408152,
|
|
"loss": 5.9648,
|
|
"mean_token_accuracy": 0.16098345518112184,
|
|
"num_tokens": 3974998.0,
|
|
"step": 1770
|
|
},
|
|
{
|
|
"entropy": 5.939936733245849,
|
|
"epoch": 0.1993598023249284,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999141688025127,
|
|
"loss": 6.0086,
|
|
"mean_token_accuracy": 0.15405713021755219,
|
|
"num_tokens": 3986469.0,
|
|
"step": 1775
|
|
},
|
|
{
|
|
"entropy": 6.004413080215454,
|
|
"epoch": 0.19992137923288594,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000499913056362151,
|
|
"loss": 5.824,
|
|
"mean_token_accuracy": 0.16189389824867248,
|
|
"num_tokens": 3997553.0,
|
|
"step": 1780
|
|
},
|
|
{
|
|
"entropy": 5.793145561218262,
|
|
"epoch": 0.2004829561408435,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999119367604703,
|
|
"loss": 5.9104,
|
|
"mean_token_accuracy": 0.15678525865077972,
|
|
"num_tokens": 4008613.0,
|
|
"step": 1785
|
|
},
|
|
{
|
|
"entropy": 6.080949354171753,
|
|
"epoch": 0.20104453304880104,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999108099975064,
|
|
"loss": 6.0728,
|
|
"mean_token_accuracy": 0.15349212139844895,
|
|
"num_tokens": 4019860.0,
|
|
"step": 1790
|
|
},
|
|
{
|
|
"entropy": 5.921809196472168,
|
|
"epoch": 0.20160610995675857,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000499909676073295,
|
|
"loss": 5.9738,
|
|
"mean_token_accuracy": 0.15834996849298477,
|
|
"num_tokens": 4030602.0,
|
|
"step": 1795
|
|
},
|
|
{
|
|
"entropy": 5.928923511505127,
|
|
"epoch": 0.20216768686471612,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999085349878723,
|
|
"loss": 5.8614,
|
|
"mean_token_accuracy": 0.15655360370874405,
|
|
"num_tokens": 4041878.0,
|
|
"step": 1800
|
|
},
|
|
{
|
|
"entropy": 5.847475194931031,
|
|
"epoch": 0.20272926377267367,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999073867412746,
|
|
"loss": 5.94,
|
|
"mean_token_accuracy": 0.15588581711053848,
|
|
"num_tokens": 4052799.0,
|
|
"step": 1805
|
|
},
|
|
{
|
|
"entropy": 6.010671329498291,
|
|
"epoch": 0.20329084068063122,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999062313335385,
|
|
"loss": 5.9363,
|
|
"mean_token_accuracy": 0.15314798802137375,
|
|
"num_tokens": 4064339.0,
|
|
"step": 1810
|
|
},
|
|
{
|
|
"entropy": 5.795467042922974,
|
|
"epoch": 0.20385241758858877,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999050687647008,
|
|
"loss": 5.8921,
|
|
"mean_token_accuracy": 0.1576225660741329,
|
|
"num_tokens": 4076246.0,
|
|
"step": 1815
|
|
},
|
|
{
|
|
"entropy": 5.920024633407593,
|
|
"epoch": 0.2044139944965463,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999038990347984,
|
|
"loss": 5.9769,
|
|
"mean_token_accuracy": 0.15226117819547652,
|
|
"num_tokens": 4088006.0,
|
|
"step": 1820
|
|
},
|
|
{
|
|
"entropy": 5.900297832489014,
|
|
"epoch": 0.20497557140450384,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999027221438688,
|
|
"loss": 5.9779,
|
|
"mean_token_accuracy": 0.15600630193948745,
|
|
"num_tokens": 4098122.0,
|
|
"step": 1825
|
|
},
|
|
{
|
|
"entropy": 6.116163063049316,
|
|
"epoch": 0.2055371483124614,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000499901538091949,
|
|
"loss": 6.1664,
|
|
"mean_token_accuracy": 0.14209582880139351,
|
|
"num_tokens": 4109958.0,
|
|
"step": 1830
|
|
},
|
|
{
|
|
"entropy": 5.965924406051636,
|
|
"epoch": 0.20609872522041894,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999003468790773,
|
|
"loss": 6.0659,
|
|
"mean_token_accuracy": 0.14896188750863076,
|
|
"num_tokens": 4121262.0,
|
|
"step": 1835
|
|
},
|
|
{
|
|
"entropy": 6.004169178009033,
|
|
"epoch": 0.2066603021283765,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998991485052911,
|
|
"loss": 5.836,
|
|
"mean_token_accuracy": 0.1599961906671524,
|
|
"num_tokens": 4130958.0,
|
|
"step": 1840
|
|
},
|
|
{
|
|
"entropy": 5.922296380996704,
|
|
"epoch": 0.20722187903633402,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000499897942970629,
|
|
"loss": 6.0519,
|
|
"mean_token_accuracy": 0.14188435971736907,
|
|
"num_tokens": 4143779.0,
|
|
"step": 1845
|
|
},
|
|
{
|
|
"entropy": 6.03759388923645,
|
|
"epoch": 0.20778345594429157,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000499896730275129,
|
|
"loss": 6.061,
|
|
"mean_token_accuracy": 0.14728911221027374,
|
|
"num_tokens": 4155367.0,
|
|
"step": 1850
|
|
},
|
|
{
|
|
"entropy": 5.955372905731201,
|
|
"epoch": 0.20834503285224912,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00049989551041883,
|
|
"loss": 5.8791,
|
|
"mean_token_accuracy": 0.1581292748451233,
|
|
"num_tokens": 4166657.0,
|
|
"step": 1855
|
|
},
|
|
{
|
|
"entropy": 5.908914852142334,
|
|
"epoch": 0.20890660976020667,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004998942834017707,
|
|
"loss": 5.9954,
|
|
"mean_token_accuracy": 0.15104548633098602,
|
|
"num_tokens": 4177517.0,
|
|
"step": 1860
|
|
},
|
|
{
|
|
"entropy": 5.932256698608398,
|
|
"epoch": 0.2094681866681642,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998930492239901,
|
|
"loss": 5.8581,
|
|
"mean_token_accuracy": 0.15925859063863754,
|
|
"num_tokens": 4188182.0,
|
|
"step": 1865
|
|
},
|
|
{
|
|
"entropy": 5.994066762924194,
|
|
"epoch": 0.21002976357612174,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004998918078855277,
|
|
"loss": 5.9848,
|
|
"mean_token_accuracy": 0.15541445910930635,
|
|
"num_tokens": 4199415.0,
|
|
"step": 1870
|
|
},
|
|
{
|
|
"entropy": 5.8985308647155765,
|
|
"epoch": 0.2105913404840793,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004998905593864227,
|
|
"loss": 5.923,
|
|
"mean_token_accuracy": 0.1541277676820755,
|
|
"num_tokens": 4210025.0,
|
|
"step": 1875
|
|
},
|
|
{
|
|
"entropy": 5.926507902145386,
|
|
"epoch": 0.21115291739203684,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998893037267153,
|
|
"loss": 5.8543,
|
|
"mean_token_accuracy": 0.16579070389270784,
|
|
"num_tokens": 4219920.0,
|
|
"step": 1880
|
|
},
|
|
{
|
|
"entropy": 5.9615906238555905,
|
|
"epoch": 0.2117144942999944,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998880409064452,
|
|
"loss": 6.0301,
|
|
"mean_token_accuracy": 0.1539834037423134,
|
|
"num_tokens": 4232647.0,
|
|
"step": 1885
|
|
},
|
|
{
|
|
"entropy": 6.008305406570434,
|
|
"epoch": 0.21227607120795192,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004998867709256527,
|
|
"loss": 5.9046,
|
|
"mean_token_accuracy": 0.15788092017173766,
|
|
"num_tokens": 4242637.0,
|
|
"step": 1890
|
|
},
|
|
{
|
|
"entropy": 5.804602575302124,
|
|
"epoch": 0.21283764811590947,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000499885493784378,
|
|
"loss": 5.8783,
|
|
"mean_token_accuracy": 0.16034948229789733,
|
|
"num_tokens": 4253633.0,
|
|
"step": 1895
|
|
},
|
|
{
|
|
"entropy": 5.849146509170533,
|
|
"epoch": 0.21339922502386702,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004998842094826621,
|
|
"loss": 5.8499,
|
|
"mean_token_accuracy": 0.1599858209490776,
|
|
"num_tokens": 4264472.0,
|
|
"step": 1900
|
|
},
|
|
{
|
|
"entropy": 5.9965856075286865,
|
|
"epoch": 0.21396080193182457,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004998829180205458,
|
|
"loss": 5.9683,
|
|
"mean_token_accuracy": 0.1586238294839859,
|
|
"num_tokens": 4275233.0,
|
|
"step": 1905
|
|
},
|
|
{
|
|
"entropy": 5.921886920928955,
|
|
"epoch": 0.21452237883978212,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998816193980701,
|
|
"loss": 5.9225,
|
|
"mean_token_accuracy": 0.15562328100204467,
|
|
"num_tokens": 4287063.0,
|
|
"step": 1910
|
|
},
|
|
{
|
|
"entropy": 5.956019353866577,
|
|
"epoch": 0.21508395574773964,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004998803136152764,
|
|
"loss": 5.9382,
|
|
"mean_token_accuracy": 0.15174477100372313,
|
|
"num_tokens": 4298761.0,
|
|
"step": 1915
|
|
},
|
|
{
|
|
"entropy": 5.6909819602966305,
|
|
"epoch": 0.2156455326556972,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004998790006722063,
|
|
"loss": 5.8025,
|
|
"mean_token_accuracy": 0.16909222900867463,
|
|
"num_tokens": 4309650.0,
|
|
"step": 1920
|
|
},
|
|
{
|
|
"entropy": 5.97760043144226,
|
|
"epoch": 0.21620710956365474,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998776805689016,
|
|
"loss": 5.8692,
|
|
"mean_token_accuracy": 0.164499531686306,
|
|
"num_tokens": 4320403.0,
|
|
"step": 1925
|
|
},
|
|
{
|
|
"entropy": 5.788105821609497,
|
|
"epoch": 0.2167686864716123,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004998763533054045,
|
|
"loss": 5.8941,
|
|
"mean_token_accuracy": 0.1588720202445984,
|
|
"num_tokens": 4332049.0,
|
|
"step": 1930
|
|
},
|
|
{
|
|
"entropy": 5.891367673873901,
|
|
"epoch": 0.21733026337956984,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004998750188817568,
|
|
"loss": 5.7892,
|
|
"mean_token_accuracy": 0.1653592273592949,
|
|
"num_tokens": 4342551.0,
|
|
"step": 1935
|
|
},
|
|
{
|
|
"entropy": 5.881437730789185,
|
|
"epoch": 0.21789184028752737,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004998736772980015,
|
|
"loss": 5.9313,
|
|
"mean_token_accuracy": 0.15979696661233903,
|
|
"num_tokens": 4355156.0,
|
|
"step": 1940
|
|
},
|
|
{
|
|
"entropy": 5.881273078918457,
|
|
"epoch": 0.21845341719548492,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000499872328554181,
|
|
"loss": 5.9757,
|
|
"mean_token_accuracy": 0.15472270399332047,
|
|
"num_tokens": 4367402.0,
|
|
"step": 1945
|
|
},
|
|
{
|
|
"entropy": 5.952515125274658,
|
|
"epoch": 0.21901499410344247,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004998709726503383,
|
|
"loss": 5.8614,
|
|
"mean_token_accuracy": 0.163260118663311,
|
|
"num_tokens": 4378687.0,
|
|
"step": 1950
|
|
},
|
|
{
|
|
"entropy": 5.963690710067749,
|
|
"epoch": 0.21957657101140002,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004998696095865168,
|
|
"loss": 5.9794,
|
|
"mean_token_accuracy": 0.1667193129658699,
|
|
"num_tokens": 4388871.0,
|
|
"step": 1955
|
|
},
|
|
{
|
|
"entropy": 5.828725910186767,
|
|
"epoch": 0.22013814791935757,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004998682393627595,
|
|
"loss": 5.8275,
|
|
"mean_token_accuracy": 0.16537183821201323,
|
|
"num_tokens": 4399440.0,
|
|
"step": 1960
|
|
},
|
|
{
|
|
"entropy": 5.788938188552857,
|
|
"epoch": 0.2206997248273151,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998668619791104,
|
|
"loss": 5.8247,
|
|
"mean_token_accuracy": 0.16133374571800232,
|
|
"num_tokens": 4409989.0,
|
|
"step": 1965
|
|
},
|
|
{
|
|
"entropy": 5.989469337463379,
|
|
"epoch": 0.22126130173527264,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998654774356131,
|
|
"loss": 5.9763,
|
|
"mean_token_accuracy": 0.15554798543453216,
|
|
"num_tokens": 4422149.0,
|
|
"step": 1970
|
|
},
|
|
{
|
|
"entropy": 6.000893068313599,
|
|
"epoch": 0.2218228786432302,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004998640857323118,
|
|
"loss": 6.0168,
|
|
"mean_token_accuracy": 0.15017584413290025,
|
|
"num_tokens": 4433157.0,
|
|
"step": 1975
|
|
},
|
|
{
|
|
"entropy": 5.92146635055542,
|
|
"epoch": 0.22238445555118774,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004998626868692509,
|
|
"loss": 5.9251,
|
|
"mean_token_accuracy": 0.1548605166375637,
|
|
"num_tokens": 4444595.0,
|
|
"step": 1980
|
|
},
|
|
{
|
|
"entropy": 6.009850740432739,
|
|
"epoch": 0.2229460324591453,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004998612808464748,
|
|
"loss": 6.06,
|
|
"mean_token_accuracy": 0.15171846598386765,
|
|
"num_tokens": 4456592.0,
|
|
"step": 1985
|
|
},
|
|
{
|
|
"entropy": 5.936912870407104,
|
|
"epoch": 0.22350760936710282,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004998598676640283,
|
|
"loss": 5.8223,
|
|
"mean_token_accuracy": 0.1676265835762024,
|
|
"num_tokens": 4467624.0,
|
|
"step": 1990
|
|
},
|
|
{
|
|
"entropy": 5.815617418289184,
|
|
"epoch": 0.22406918627506037,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004998584473219563,
|
|
"loss": 6.015,
|
|
"mean_token_accuracy": 0.15404653251171113,
|
|
"num_tokens": 4479766.0,
|
|
"step": 1995
|
|
},
|
|
{
|
|
"entropy": 5.964367246627807,
|
|
"epoch": 0.22463076318301792,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998570198203043,
|
|
"loss": 5.8958,
|
|
"mean_token_accuracy": 0.15508440732955933,
|
|
"num_tokens": 4490023.0,
|
|
"step": 2000
|
|
},
|
|
{
|
|
"entropy": 5.886840057373047,
|
|
"epoch": 0.22519234009097547,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998555851591175,
|
|
"loss": 5.9304,
|
|
"mean_token_accuracy": 0.15414074063301086,
|
|
"num_tokens": 4500651.0,
|
|
"step": 2005
|
|
},
|
|
{
|
|
"entropy": 5.974041604995728,
|
|
"epoch": 0.225753916998933,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004998541433384416,
|
|
"loss": 6.0254,
|
|
"mean_token_accuracy": 0.15283730775117874,
|
|
"num_tokens": 4512934.0,
|
|
"step": 2010
|
|
},
|
|
{
|
|
"entropy": 5.865922832489014,
|
|
"epoch": 0.22631549390689054,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004998526943583226,
|
|
"loss": 5.8999,
|
|
"mean_token_accuracy": 0.1615584284067154,
|
|
"num_tokens": 4524251.0,
|
|
"step": 2015
|
|
},
|
|
{
|
|
"entropy": 5.944715785980224,
|
|
"epoch": 0.2268770708148481,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998512382188066,
|
|
"loss": 5.9869,
|
|
"mean_token_accuracy": 0.15048470497131347,
|
|
"num_tokens": 4536025.0,
|
|
"step": 2020
|
|
},
|
|
{
|
|
"entropy": 5.948613405227661,
|
|
"epoch": 0.22743864772280564,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998497749199401,
|
|
"loss": 5.9227,
|
|
"mean_token_accuracy": 0.16197280138731002,
|
|
"num_tokens": 4546717.0,
|
|
"step": 2025
|
|
},
|
|
{
|
|
"entropy": 5.885292673110962,
|
|
"epoch": 0.2280002246307632,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004998483044617694,
|
|
"loss": 5.83,
|
|
"mean_token_accuracy": 0.1600128546357155,
|
|
"num_tokens": 4557206.0,
|
|
"step": 2030
|
|
},
|
|
{
|
|
"entropy": 5.792216968536377,
|
|
"epoch": 0.22856180153872072,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004998468268443416,
|
|
"loss": 5.8042,
|
|
"mean_token_accuracy": 0.1661403089761734,
|
|
"num_tokens": 4568123.0,
|
|
"step": 2035
|
|
},
|
|
{
|
|
"entropy": 5.922398662567138,
|
|
"epoch": 0.22912337844667827,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998453420677034,
|
|
"loss": 5.9317,
|
|
"mean_token_accuracy": 0.16073161512613296,
|
|
"num_tokens": 4579385.0,
|
|
"step": 2040
|
|
},
|
|
{
|
|
"entropy": 5.948491716384888,
|
|
"epoch": 0.22968495535463582,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004998438501319025,
|
|
"loss": 5.9989,
|
|
"mean_token_accuracy": 0.15271369516849517,
|
|
"num_tokens": 4590514.0,
|
|
"step": 2045
|
|
},
|
|
{
|
|
"entropy": 5.942990636825561,
|
|
"epoch": 0.23024653226259337,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004998423510369862,
|
|
"loss": 5.9391,
|
|
"mean_token_accuracy": 0.1535491645336151,
|
|
"num_tokens": 4601624.0,
|
|
"step": 2050
|
|
},
|
|
{
|
|
"entropy": 5.956568479537964,
|
|
"epoch": 0.23080810917055092,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998408447830022,
|
|
"loss": 5.9106,
|
|
"mean_token_accuracy": 0.16113350540399551,
|
|
"num_tokens": 4612822.0,
|
|
"step": 2055
|
|
},
|
|
{
|
|
"entropy": 5.887269592285156,
|
|
"epoch": 0.23136968607850844,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998393313699985,
|
|
"loss": 5.9078,
|
|
"mean_token_accuracy": 0.16328109800815582,
|
|
"num_tokens": 4623443.0,
|
|
"step": 2060
|
|
},
|
|
{
|
|
"entropy": 5.8864829540252686,
|
|
"epoch": 0.231931262986466,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998378107980233,
|
|
"loss": 5.8264,
|
|
"mean_token_accuracy": 0.164647077023983,
|
|
"num_tokens": 4633600.0,
|
|
"step": 2065
|
|
},
|
|
{
|
|
"entropy": 5.920262145996094,
|
|
"epoch": 0.23249283989442354,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004998362830671249,
|
|
"loss": 5.9662,
|
|
"mean_token_accuracy": 0.1570918917655945,
|
|
"num_tokens": 4644217.0,
|
|
"step": 2070
|
|
},
|
|
{
|
|
"entropy": 5.933908748626709,
|
|
"epoch": 0.2330544168023811,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998347481773522,
|
|
"loss": 5.9835,
|
|
"mean_token_accuracy": 0.15711799710989,
|
|
"num_tokens": 4654671.0,
|
|
"step": 2075
|
|
},
|
|
{
|
|
"entropy": 5.950888347625733,
|
|
"epoch": 0.23361599371033864,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004998332061287538,
|
|
"loss": 5.9889,
|
|
"mean_token_accuracy": 0.14997301772236823,
|
|
"num_tokens": 4665920.0,
|
|
"step": 2080
|
|
},
|
|
{
|
|
"entropy": 5.8428487300872805,
|
|
"epoch": 0.23417757061829617,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000499831656921379,
|
|
"loss": 5.8717,
|
|
"mean_token_accuracy": 0.15921460837125778,
|
|
"num_tokens": 4675406.0,
|
|
"step": 2085
|
|
},
|
|
{
|
|
"entropy": 5.99163818359375,
|
|
"epoch": 0.23473914752625372,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000499830100555277,
|
|
"loss": 5.8908,
|
|
"mean_token_accuracy": 0.16001009494066237,
|
|
"num_tokens": 4686870.0,
|
|
"step": 2090
|
|
},
|
|
{
|
|
"entropy": 5.922211599349976,
|
|
"epoch": 0.23530072443421127,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998285370304974,
|
|
"loss": 5.9799,
|
|
"mean_token_accuracy": 0.1588357299566269,
|
|
"num_tokens": 4698926.0,
|
|
"step": 2095
|
|
},
|
|
{
|
|
"entropy": 5.979310846328735,
|
|
"epoch": 0.23586230134216882,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00049982696634709,
|
|
"loss": 6.0667,
|
|
"mean_token_accuracy": 0.1482769340276718,
|
|
"num_tokens": 4709318.0,
|
|
"step": 2100
|
|
},
|
|
{
|
|
"entropy": 5.8210399627685545,
|
|
"epoch": 0.23642387825012637,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998253885051048,
|
|
"loss": 5.7439,
|
|
"mean_token_accuracy": 0.16988635659217835,
|
|
"num_tokens": 4718819.0,
|
|
"step": 2105
|
|
},
|
|
{
|
|
"entropy": 5.833800458908081,
|
|
"epoch": 0.2369854551580839,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000499823803504592,
|
|
"loss": 5.7884,
|
|
"mean_token_accuracy": 0.16458115875720977,
|
|
"num_tokens": 4729513.0,
|
|
"step": 2110
|
|
},
|
|
{
|
|
"entropy": 5.833691692352295,
|
|
"epoch": 0.23754703206604144,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998222113456022,
|
|
"loss": 5.8959,
|
|
"mean_token_accuracy": 0.15621652752161025,
|
|
"num_tokens": 4739875.0,
|
|
"step": 2115
|
|
},
|
|
{
|
|
"entropy": 5.996620178222656,
|
|
"epoch": 0.238108608973999,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004998206120281858,
|
|
"loss": 6.0193,
|
|
"mean_token_accuracy": 0.15316891372203828,
|
|
"num_tokens": 4752933.0,
|
|
"step": 2120
|
|
},
|
|
{
|
|
"entropy": 5.844056224822998,
|
|
"epoch": 0.23867018588195654,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000499819005552394,
|
|
"loss": 5.8077,
|
|
"mean_token_accuracy": 0.15859929621219634,
|
|
"num_tokens": 4762969.0,
|
|
"step": 2125
|
|
},
|
|
{
|
|
"entropy": 5.906571960449218,
|
|
"epoch": 0.23923176278991407,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998173919182779,
|
|
"loss": 5.9062,
|
|
"mean_token_accuracy": 0.15946385115385056,
|
|
"num_tokens": 4773495.0,
|
|
"step": 2130
|
|
},
|
|
{
|
|
"entropy": 5.9517632007598875,
|
|
"epoch": 0.23979333969787162,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000499815771125889,
|
|
"loss": 5.9242,
|
|
"mean_token_accuracy": 0.1614214599132538,
|
|
"num_tokens": 4785335.0,
|
|
"step": 2135
|
|
},
|
|
{
|
|
"entropy": 6.040471792221069,
|
|
"epoch": 0.24035491660582917,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004998141431752785,
|
|
"loss": 6.0859,
|
|
"mean_token_accuracy": 0.15251848995685577,
|
|
"num_tokens": 4798068.0,
|
|
"step": 2140
|
|
},
|
|
{
|
|
"entropy": 5.858961009979248,
|
|
"epoch": 0.24091649351378672,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998125080664987,
|
|
"loss": 5.8954,
|
|
"mean_token_accuracy": 0.16209042817354202,
|
|
"num_tokens": 4809338.0,
|
|
"step": 2145
|
|
},
|
|
{
|
|
"entropy": 5.864888381958008,
|
|
"epoch": 0.24147807042174427,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004998108657996012,
|
|
"loss": 5.8966,
|
|
"mean_token_accuracy": 0.16215386986732483,
|
|
"num_tokens": 4819636.0,
|
|
"step": 2150
|
|
},
|
|
{
|
|
"entropy": 5.886841058731079,
|
|
"epoch": 0.2420396473297018,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004998092163746387,
|
|
"loss": 5.8769,
|
|
"mean_token_accuracy": 0.15902756452560424,
|
|
"num_tokens": 4830975.0,
|
|
"step": 2155
|
|
},
|
|
{
|
|
"entropy": 5.838779735565185,
|
|
"epoch": 0.24260122423765934,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004998075597916636,
|
|
"loss": 5.909,
|
|
"mean_token_accuracy": 0.15607747733592986,
|
|
"num_tokens": 4841951.0,
|
|
"step": 2160
|
|
},
|
|
{
|
|
"entropy": 5.997031497955322,
|
|
"epoch": 0.2431628011456169,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998058960507286,
|
|
"loss": 5.8733,
|
|
"mean_token_accuracy": 0.1630635976791382,
|
|
"num_tokens": 4852919.0,
|
|
"step": 2165
|
|
},
|
|
{
|
|
"entropy": 5.89027967453003,
|
|
"epoch": 0.24372437805357444,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998042251518866,
|
|
"loss": 5.9002,
|
|
"mean_token_accuracy": 0.16249769777059556,
|
|
"num_tokens": 4863433.0,
|
|
"step": 2170
|
|
},
|
|
{
|
|
"entropy": 5.926810932159424,
|
|
"epoch": 0.244285954961532,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004998025470951908,
|
|
"loss": 5.9761,
|
|
"mean_token_accuracy": 0.15455071330070497,
|
|
"num_tokens": 4875685.0,
|
|
"step": 2175
|
|
},
|
|
{
|
|
"entropy": 5.869753360748291,
|
|
"epoch": 0.24484753186948952,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998008618806949,
|
|
"loss": 5.8728,
|
|
"mean_token_accuracy": 0.1591688722372055,
|
|
"num_tokens": 4886347.0,
|
|
"step": 2180
|
|
},
|
|
{
|
|
"entropy": 5.861783599853515,
|
|
"epoch": 0.24540910877744707,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004997991695084523,
|
|
"loss": 5.8697,
|
|
"mean_token_accuracy": 0.1650501862168312,
|
|
"num_tokens": 4896898.0,
|
|
"step": 2185
|
|
},
|
|
{
|
|
"entropy": 5.944435453414917,
|
|
"epoch": 0.24597068568540462,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004997974699785169,
|
|
"loss": 5.9649,
|
|
"mean_token_accuracy": 0.15616948157548904,
|
|
"num_tokens": 4908892.0,
|
|
"step": 2190
|
|
},
|
|
{
|
|
"entropy": 5.90886378288269,
|
|
"epoch": 0.24653226259336217,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004997957632909429,
|
|
"loss": 5.9227,
|
|
"mean_token_accuracy": 0.15143503323197366,
|
|
"num_tokens": 4920855.0,
|
|
"step": 2195
|
|
},
|
|
{
|
|
"entropy": 5.940524053573609,
|
|
"epoch": 0.24709383950131972,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004997940494457846,
|
|
"loss": 5.9019,
|
|
"mean_token_accuracy": 0.16185556203126908,
|
|
"num_tokens": 4932857.0,
|
|
"step": 2200
|
|
},
|
|
{
|
|
"entropy": 5.840349340438843,
|
|
"epoch": 0.24765541640927724,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004997923284430967,
|
|
"loss": 5.9269,
|
|
"mean_token_accuracy": 0.15865219086408616,
|
|
"num_tokens": 4944063.0,
|
|
"step": 2205
|
|
},
|
|
{
|
|
"entropy": 5.840737771987915,
|
|
"epoch": 0.2482169933172348,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004997906002829338,
|
|
"loss": 5.8171,
|
|
"mean_token_accuracy": 0.16315427124500276,
|
|
"num_tokens": 4955126.0,
|
|
"step": 2210
|
|
},
|
|
{
|
|
"entropy": 5.974541473388672,
|
|
"epoch": 0.24877857022519234,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000499788864965351,
|
|
"loss": 5.9916,
|
|
"mean_token_accuracy": 0.15862064212560653,
|
|
"num_tokens": 4965738.0,
|
|
"step": 2215
|
|
},
|
|
{
|
|
"entropy": 6.033790445327758,
|
|
"epoch": 0.2493401471331499,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004997871224904036,
|
|
"loss": 6.0161,
|
|
"mean_token_accuracy": 0.15496434420347213,
|
|
"num_tokens": 4976963.0,
|
|
"step": 2220
|
|
},
|
|
{
|
|
"entropy": 5.871994352340698,
|
|
"epoch": 0.24990172404110744,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004997853728581468,
|
|
"loss": 5.8972,
|
|
"mean_token_accuracy": 0.15883660763502122,
|
|
"num_tokens": 4987577.0,
|
|
"step": 2225
|
|
},
|
|
{
|
|
"entropy": 5.947416067123413,
|
|
"epoch": 0.250463300949065,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004997836160686368,
|
|
"loss": 6.03,
|
|
"mean_token_accuracy": 0.15736178755760194,
|
|
"num_tokens": 5000234.0,
|
|
"step": 2230
|
|
},
|
|
{
|
|
"entropy": 5.9184082508087155,
|
|
"epoch": 0.25102487785702254,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004997818521219291,
|
|
"loss": 5.8461,
|
|
"mean_token_accuracy": 0.1566610097885132,
|
|
"num_tokens": 5011652.0,
|
|
"step": 2235
|
|
},
|
|
{
|
|
"entropy": 5.882735061645508,
|
|
"epoch": 0.25158645476498004,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004997800810180803,
|
|
"loss": 5.9064,
|
|
"mean_token_accuracy": 0.15962962210178375,
|
|
"num_tokens": 5023603.0,
|
|
"step": 2240
|
|
},
|
|
{
|
|
"entropy": 5.894164323806763,
|
|
"epoch": 0.2521480316729376,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004997783027571464,
|
|
"loss": 5.8769,
|
|
"mean_token_accuracy": 0.16312634348869323,
|
|
"num_tokens": 5034427.0,
|
|
"step": 2245
|
|
},
|
|
{
|
|
"entropy": 5.836391019821167,
|
|
"epoch": 0.25270960858089514,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004997765173391841,
|
|
"loss": 5.8599,
|
|
"mean_token_accuracy": 0.1607695162296295,
|
|
"num_tokens": 5045738.0,
|
|
"step": 2250
|
|
},
|
|
{
|
|
"entropy": 5.778099393844604,
|
|
"epoch": 0.2532711854888527,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004997747247642505,
|
|
"loss": 5.8042,
|
|
"mean_token_accuracy": 0.15976118296384811,
|
|
"num_tokens": 5057021.0,
|
|
"step": 2255
|
|
},
|
|
{
|
|
"entropy": 5.927276754379273,
|
|
"epoch": 0.25383276239681024,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004997729250324023,
|
|
"loss": 5.8905,
|
|
"mean_token_accuracy": 0.16150345653295517,
|
|
"num_tokens": 5067676.0,
|
|
"step": 2260
|
|
},
|
|
{
|
|
"entropy": 5.8269829750061035,
|
|
"epoch": 0.2543943393047678,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004997711181436971,
|
|
"loss": 5.8336,
|
|
"mean_token_accuracy": 0.1601359650492668,
|
|
"num_tokens": 5079422.0,
|
|
"step": 2265
|
|
},
|
|
{
|
|
"entropy": 5.7728053569793705,
|
|
"epoch": 0.25495591621272534,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004997693040981922,
|
|
"loss": 5.8469,
|
|
"mean_token_accuracy": 0.16109928190708162,
|
|
"num_tokens": 5091242.0,
|
|
"step": 2270
|
|
},
|
|
{
|
|
"entropy": 5.990598201751709,
|
|
"epoch": 0.2555174931206829,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004997674828959456,
|
|
"loss": 5.8491,
|
|
"mean_token_accuracy": 0.15938674956560134,
|
|
"num_tokens": 5102251.0,
|
|
"step": 2275
|
|
},
|
|
{
|
|
"entropy": 5.729700899124145,
|
|
"epoch": 0.25607907002864044,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004997656545370151,
|
|
"loss": 5.8852,
|
|
"mean_token_accuracy": 0.16283274069428444,
|
|
"num_tokens": 5113276.0,
|
|
"step": 2280
|
|
},
|
|
{
|
|
"entropy": 5.919237375259399,
|
|
"epoch": 0.256640646936598,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000499763819021459,
|
|
"loss": 5.886,
|
|
"mean_token_accuracy": 0.1575261250138283,
|
|
"num_tokens": 5124472.0,
|
|
"step": 2285
|
|
},
|
|
{
|
|
"entropy": 5.845501375198364,
|
|
"epoch": 0.2572022238445555,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004997619763493357,
|
|
"loss": 5.8236,
|
|
"mean_token_accuracy": 0.16404707133769988,
|
|
"num_tokens": 5134896.0,
|
|
"step": 2290
|
|
},
|
|
{
|
|
"entropy": 5.844338417053223,
|
|
"epoch": 0.25776380075251304,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000499760126520704,
|
|
"loss": 5.9119,
|
|
"mean_token_accuracy": 0.16496196687221526,
|
|
"num_tokens": 5145115.0,
|
|
"step": 2295
|
|
},
|
|
{
|
|
"entropy": 5.968642473220825,
|
|
"epoch": 0.2583253776604706,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004997582695356225,
|
|
"loss": 5.8779,
|
|
"mean_token_accuracy": 0.1621330961585045,
|
|
"num_tokens": 5155620.0,
|
|
"step": 2300
|
|
},
|
|
{
|
|
"entropy": 5.922991991043091,
|
|
"epoch": 0.25888695456842814,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004997564053941507,
|
|
"loss": 5.9557,
|
|
"mean_token_accuracy": 0.1564936578273773,
|
|
"num_tokens": 5166260.0,
|
|
"step": 2305
|
|
},
|
|
{
|
|
"entropy": 5.91731972694397,
|
|
"epoch": 0.2594485314763857,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004997545340963478,
|
|
"loss": 5.828,
|
|
"mean_token_accuracy": 0.16110915541648865,
|
|
"num_tokens": 5177143.0,
|
|
"step": 2310
|
|
},
|
|
{
|
|
"entropy": 5.899685716629028,
|
|
"epoch": 0.26001010838434324,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004997526556422733,
|
|
"loss": 5.9873,
|
|
"mean_token_accuracy": 0.1551265999674797,
|
|
"num_tokens": 5187795.0,
|
|
"step": 2315
|
|
},
|
|
{
|
|
"entropy": 5.851340389251709,
|
|
"epoch": 0.2605716852923008,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004997507700319872,
|
|
"loss": 5.8519,
|
|
"mean_token_accuracy": 0.15984025597572327,
|
|
"num_tokens": 5199365.0,
|
|
"step": 2320
|
|
},
|
|
{
|
|
"entropy": 5.976457357406616,
|
|
"epoch": 0.26113326220025834,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004997488772655492,
|
|
"loss": 6.0566,
|
|
"mean_token_accuracy": 0.15742886140942575,
|
|
"num_tokens": 5212264.0,
|
|
"step": 2325
|
|
},
|
|
{
|
|
"entropy": 5.996505832672119,
|
|
"epoch": 0.2616948391082159,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004997469773430199,
|
|
"loss": 5.8966,
|
|
"mean_token_accuracy": 0.15872514396905898,
|
|
"num_tokens": 5223544.0,
|
|
"step": 2330
|
|
},
|
|
{
|
|
"entropy": 5.7976573467254635,
|
|
"epoch": 0.2622564160161734,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004997450702644596,
|
|
"loss": 5.8392,
|
|
"mean_token_accuracy": 0.164206762611866,
|
|
"num_tokens": 5234713.0,
|
|
"step": 2335
|
|
},
|
|
{
|
|
"entropy": 5.894666624069214,
|
|
"epoch": 0.26281799292413094,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004997431560299292,
|
|
"loss": 5.9186,
|
|
"mean_token_accuracy": 0.1576240837574005,
|
|
"num_tokens": 5246103.0,
|
|
"step": 2340
|
|
},
|
|
{
|
|
"entropy": 5.8023473739624025,
|
|
"epoch": 0.2633795698320885,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004997412346394894,
|
|
"loss": 5.7619,
|
|
"mean_token_accuracy": 0.16748271733522416,
|
|
"num_tokens": 5257372.0,
|
|
"step": 2345
|
|
},
|
|
{
|
|
"entropy": 5.750147676467895,
|
|
"epoch": 0.26394114674004604,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004997393060932017,
|
|
"loss": 5.8174,
|
|
"mean_token_accuracy": 0.16950322389602662,
|
|
"num_tokens": 5268677.0,
|
|
"step": 2350
|
|
},
|
|
{
|
|
"entropy": 5.896950960159302,
|
|
"epoch": 0.2645027236480036,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004997373703911273,
|
|
"loss": 5.882,
|
|
"mean_token_accuracy": 0.16510013192892076,
|
|
"num_tokens": 5279056.0,
|
|
"step": 2355
|
|
},
|
|
{
|
|
"entropy": 5.777258491516113,
|
|
"epoch": 0.26506430055596114,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004997354275333277,
|
|
"loss": 5.7788,
|
|
"mean_token_accuracy": 0.16966423392295837,
|
|
"num_tokens": 5289310.0,
|
|
"step": 2360
|
|
},
|
|
{
|
|
"entropy": 5.9493550777435305,
|
|
"epoch": 0.2656258774639187,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.000499733477519865,
|
|
"loss": 5.867,
|
|
"mean_token_accuracy": 0.16966673880815505,
|
|
"num_tokens": 5300619.0,
|
|
"step": 2365
|
|
},
|
|
{
|
|
"entropy": 5.969382953643799,
|
|
"epoch": 0.26618745437187624,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004997315203508013,
|
|
"loss": 6.0231,
|
|
"mean_token_accuracy": 0.15661545246839523,
|
|
"num_tokens": 5311554.0,
|
|
"step": 2370
|
|
},
|
|
{
|
|
"entropy": 5.884856653213501,
|
|
"epoch": 0.2667490312798338,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004997295560261988,
|
|
"loss": 5.8581,
|
|
"mean_token_accuracy": 0.16036505699157716,
|
|
"num_tokens": 5323592.0,
|
|
"step": 2375
|
|
},
|
|
{
|
|
"entropy": 5.894713497161865,
|
|
"epoch": 0.26731060818779134,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00049972758454612,
|
|
"loss": 5.9369,
|
|
"mean_token_accuracy": 0.15631330013275146,
|
|
"num_tokens": 5334978.0,
|
|
"step": 2380
|
|
},
|
|
{
|
|
"entropy": 5.851967906951904,
|
|
"epoch": 0.26787218509574884,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004997256059106279,
|
|
"loss": 5.8263,
|
|
"mean_token_accuracy": 0.1627744436264038,
|
|
"num_tokens": 5345724.0,
|
|
"step": 2385
|
|
},
|
|
{
|
|
"entropy": 5.937517786026001,
|
|
"epoch": 0.2684337620037064,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004997236201197853,
|
|
"loss": 5.9538,
|
|
"mean_token_accuracy": 0.15579489171504973,
|
|
"num_tokens": 5357141.0,
|
|
"step": 2390
|
|
},
|
|
{
|
|
"entropy": 5.8911901950836185,
|
|
"epoch": 0.26899533891166394,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004997216271736554,
|
|
"loss": 5.9489,
|
|
"mean_token_accuracy": 0.15976700633764268,
|
|
"num_tokens": 5367889.0,
|
|
"step": 2395
|
|
},
|
|
{
|
|
"entropy": 5.73674750328064,
|
|
"epoch": 0.2695569158196215,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004997196270723018,
|
|
"loss": 5.6811,
|
|
"mean_token_accuracy": 0.16924870163202285,
|
|
"num_tokens": 5379329.0,
|
|
"step": 2400
|
|
},
|
|
{
|
|
"entropy": 5.813704013824463,
|
|
"epoch": 0.27011849272757904,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004997176198157881,
|
|
"loss": 5.8625,
|
|
"mean_token_accuracy": 0.16214843541383744,
|
|
"num_tokens": 5389525.0,
|
|
"step": 2405
|
|
},
|
|
{
|
|
"entropy": 5.811829280853272,
|
|
"epoch": 0.2706800696355366,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004997156054041781,
|
|
"loss": 5.7567,
|
|
"mean_token_accuracy": 0.16782970875501632,
|
|
"num_tokens": 5401061.0,
|
|
"step": 2410
|
|
},
|
|
{
|
|
"entropy": 5.799409866333008,
|
|
"epoch": 0.27124164654349414,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004997135838375362,
|
|
"loss": 5.8719,
|
|
"mean_token_accuracy": 0.16424075216054917,
|
|
"num_tokens": 5411791.0,
|
|
"step": 2415
|
|
},
|
|
{
|
|
"entropy": 5.8548118591308596,
|
|
"epoch": 0.2718032234514517,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004997115551159267,
|
|
"loss": 5.8149,
|
|
"mean_token_accuracy": 0.1655492290854454,
|
|
"num_tokens": 5422790.0,
|
|
"step": 2420
|
|
},
|
|
{
|
|
"entropy": 5.73070912361145,
|
|
"epoch": 0.27236480035940924,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000499709519239414,
|
|
"loss": 5.7664,
|
|
"mean_token_accuracy": 0.162947778403759,
|
|
"num_tokens": 5434170.0,
|
|
"step": 2425
|
|
},
|
|
{
|
|
"entropy": 5.8987569332122805,
|
|
"epoch": 0.2729263772673668,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.0004997074762080632,
|
|
"loss": 5.9044,
|
|
"mean_token_accuracy": 0.1554044485092163,
|
|
"num_tokens": 5445948.0,
|
|
"step": 2430
|
|
},
|
|
{
|
|
"entropy": 5.8786403179168705,
|
|
"epoch": 0.2734879541753243,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000499705426021939,
|
|
"loss": 5.8463,
|
|
"mean_token_accuracy": 0.15968216806650162,
|
|
"num_tokens": 5457786.0,
|
|
"step": 2435
|
|
},
|
|
{
|
|
"entropy": 5.741592025756836,
|
|
"epoch": 0.27404953108328184,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000499703368681107,
|
|
"loss": 5.8246,
|
|
"mean_token_accuracy": 0.16183126270771026,
|
|
"num_tokens": 5469434.0,
|
|
"step": 2440
|
|
},
|
|
{
|
|
"entropy": 5.820113945007324,
|
|
"epoch": 0.2746111079912394,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004997013041856326,
|
|
"loss": 5.8181,
|
|
"mean_token_accuracy": 0.15362994968891144,
|
|
"num_tokens": 5480393.0,
|
|
"step": 2445
|
|
},
|
|
{
|
|
"entropy": 5.839815759658814,
|
|
"epoch": 0.27517268489919694,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004996992325355815,
|
|
"loss": 5.7913,
|
|
"mean_token_accuracy": 0.16776337772607802,
|
|
"num_tokens": 5490452.0,
|
|
"step": 2450
|
|
},
|
|
{
|
|
"entropy": 5.746620035171508,
|
|
"epoch": 0.2757342618071545,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004996971537310198,
|
|
"loss": 5.7604,
|
|
"mean_token_accuracy": 0.16507340222597122,
|
|
"num_tokens": 5501404.0,
|
|
"step": 2455
|
|
},
|
|
{
|
|
"entropy": 5.909250211715698,
|
|
"epoch": 0.27629583871511204,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004996950677720133,
|
|
"loss": 5.9082,
|
|
"mean_token_accuracy": 0.1567159414291382,
|
|
"num_tokens": 5512938.0,
|
|
"step": 2460
|
|
},
|
|
{
|
|
"entropy": 5.787460136413574,
|
|
"epoch": 0.2768574156230696,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000499692974658629,
|
|
"loss": 5.8266,
|
|
"mean_token_accuracy": 0.15562744736671447,
|
|
"num_tokens": 5524009.0,
|
|
"step": 2465
|
|
},
|
|
{
|
|
"entropy": 5.938859176635742,
|
|
"epoch": 0.27741899253102714,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004996908743909331,
|
|
"loss": 5.9223,
|
|
"mean_token_accuracy": 0.16114431321620942,
|
|
"num_tokens": 5535930.0,
|
|
"step": 2470
|
|
},
|
|
{
|
|
"entropy": 5.872061681747437,
|
|
"epoch": 0.2779805694389847,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004996887669689926,
|
|
"loss": 5.9041,
|
|
"mean_token_accuracy": 0.1604764387011528,
|
|
"num_tokens": 5547295.0,
|
|
"step": 2475
|
|
},
|
|
{
|
|
"entropy": 5.919583368301391,
|
|
"epoch": 0.2785421463469422,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004996866523928747,
|
|
"loss": 5.8132,
|
|
"mean_token_accuracy": 0.17077299803495408,
|
|
"num_tokens": 5558447.0,
|
|
"step": 2480
|
|
},
|
|
{
|
|
"entropy": 5.856130313873291,
|
|
"epoch": 0.27910372325489974,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004996845306626467,
|
|
"loss": 5.8985,
|
|
"mean_token_accuracy": 0.16235149949789046,
|
|
"num_tokens": 5569822.0,
|
|
"step": 2485
|
|
},
|
|
{
|
|
"entropy": 5.92427625656128,
|
|
"epoch": 0.2796653001628573,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004996824017783759,
|
|
"loss": 5.9638,
|
|
"mean_token_accuracy": 0.15235039740800857,
|
|
"num_tokens": 5582284.0,
|
|
"step": 2490
|
|
},
|
|
{
|
|
"entropy": 5.959985637664795,
|
|
"epoch": 0.28022687707081484,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004996802657401304,
|
|
"loss": 5.8473,
|
|
"mean_token_accuracy": 0.16248423457145691,
|
|
"num_tokens": 5593765.0,
|
|
"step": 2495
|
|
},
|
|
{
|
|
"entropy": 5.739575672149658,
|
|
"epoch": 0.2807884539787724,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004996781225479781,
|
|
"loss": 5.8307,
|
|
"mean_token_accuracy": 0.162098728120327,
|
|
"num_tokens": 5605080.0,
|
|
"step": 2500
|
|
},
|
|
{
|
|
"entropy": 5.929462480545044,
|
|
"epoch": 0.28135003088672994,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004996759722019872,
|
|
"loss": 5.9806,
|
|
"mean_token_accuracy": 0.1570798173546791,
|
|
"num_tokens": 5616739.0,
|
|
"step": 2505
|
|
},
|
|
{
|
|
"entropy": 5.820597314834595,
|
|
"epoch": 0.2819116077946875,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004996738147022262,
|
|
"loss": 5.8397,
|
|
"mean_token_accuracy": 0.15744382441043853,
|
|
"num_tokens": 5628779.0,
|
|
"step": 2510
|
|
},
|
|
{
|
|
"entropy": 5.893591260910034,
|
|
"epoch": 0.28247318470264504,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004996716500487638,
|
|
"loss": 5.869,
|
|
"mean_token_accuracy": 0.16222879737615586,
|
|
"num_tokens": 5639168.0,
|
|
"step": 2515
|
|
},
|
|
{
|
|
"entropy": 5.841968250274658,
|
|
"epoch": 0.2830347616106026,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000499669478241669,
|
|
"loss": 5.8605,
|
|
"mean_token_accuracy": 0.15638342201709748,
|
|
"num_tokens": 5650739.0,
|
|
"step": 2520
|
|
},
|
|
{
|
|
"entropy": 5.8755299091339115,
|
|
"epoch": 0.28359633851856014,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004996672992810108,
|
|
"loss": 5.8714,
|
|
"mean_token_accuracy": 0.1581589788198471,
|
|
"num_tokens": 5662630.0,
|
|
"step": 2525
|
|
},
|
|
{
|
|
"entropy": 5.844922351837158,
|
|
"epoch": 0.28415791542651764,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004996651131668587,
|
|
"loss": 5.8787,
|
|
"mean_token_accuracy": 0.17241379320621492,
|
|
"num_tokens": 5673473.0,
|
|
"step": 2530
|
|
},
|
|
{
|
|
"entropy": 5.889810848236084,
|
|
"epoch": 0.2847194923344752,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004996629198992823,
|
|
"loss": 6.0159,
|
|
"mean_token_accuracy": 0.15564603805541993,
|
|
"num_tokens": 5686577.0,
|
|
"step": 2535
|
|
},
|
|
{
|
|
"entropy": 5.873380708694458,
|
|
"epoch": 0.28528106924243274,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004996607194783513,
|
|
"loss": 5.7735,
|
|
"mean_token_accuracy": 0.16043300777673722,
|
|
"num_tokens": 5697570.0,
|
|
"step": 2540
|
|
},
|
|
{
|
|
"entropy": 5.865016794204712,
|
|
"epoch": 0.2858426461503903,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004996585119041359,
|
|
"loss": 5.8411,
|
|
"mean_token_accuracy": 0.15766210556030275,
|
|
"num_tokens": 5708601.0,
|
|
"step": 2545
|
|
},
|
|
{
|
|
"entropy": 5.752566909790039,
|
|
"epoch": 0.28640422305834784,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004996562971767063,
|
|
"loss": 5.779,
|
|
"mean_token_accuracy": 0.16273874640464783,
|
|
"num_tokens": 5719619.0,
|
|
"step": 2550
|
|
},
|
|
{
|
|
"entropy": 5.794800090789795,
|
|
"epoch": 0.2869657999663054,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000499654075296133,
|
|
"loss": 5.8048,
|
|
"mean_token_accuracy": 0.16589817106723787,
|
|
"num_tokens": 5730061.0,
|
|
"step": 2555
|
|
},
|
|
{
|
|
"entropy": 5.912380218505859,
|
|
"epoch": 0.28752737687426294,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000499651846262487,
|
|
"loss": 5.837,
|
|
"mean_token_accuracy": 0.16605120301246643,
|
|
"num_tokens": 5741579.0,
|
|
"step": 2560
|
|
},
|
|
{
|
|
"entropy": 5.8115198612213135,
|
|
"epoch": 0.2880889537822205,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004996496100758389,
|
|
"loss": 5.8445,
|
|
"mean_token_accuracy": 0.16317956894636154,
|
|
"num_tokens": 5754001.0,
|
|
"step": 2565
|
|
},
|
|
{
|
|
"entropy": 5.875561904907227,
|
|
"epoch": 0.28865053069017804,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004996473667362604,
|
|
"loss": 5.9419,
|
|
"mean_token_accuracy": 0.15564240291714668,
|
|
"num_tokens": 5766224.0,
|
|
"step": 2570
|
|
},
|
|
{
|
|
"entropy": 5.90215277671814,
|
|
"epoch": 0.28921210759813554,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004996451162438224,
|
|
"loss": 5.9139,
|
|
"mean_token_accuracy": 0.15471576601266862,
|
|
"num_tokens": 5777475.0,
|
|
"step": 2575
|
|
},
|
|
{
|
|
"entropy": 5.950841808319092,
|
|
"epoch": 0.2897736845060931,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004996428585985967,
|
|
"loss": 5.8954,
|
|
"mean_token_accuracy": 0.15479824990034102,
|
|
"num_tokens": 5788359.0,
|
|
"step": 2580
|
|
},
|
|
{
|
|
"entropy": 5.766581010818482,
|
|
"epoch": 0.29033526141405064,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004996405938006553,
|
|
"loss": 5.8326,
|
|
"mean_token_accuracy": 0.1614225149154663,
|
|
"num_tokens": 5799116.0,
|
|
"step": 2585
|
|
},
|
|
{
|
|
"entropy": 5.759355449676514,
|
|
"epoch": 0.2908968383220082,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004996383218500703,
|
|
"loss": 5.7769,
|
|
"mean_token_accuracy": 0.16205016821622847,
|
|
"num_tokens": 5811221.0,
|
|
"step": 2590
|
|
},
|
|
{
|
|
"entropy": 5.86917290687561,
|
|
"epoch": 0.29145841522996574,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000499636042746914,
|
|
"loss": 5.8707,
|
|
"mean_token_accuracy": 0.15995543599128723,
|
|
"num_tokens": 5822099.0,
|
|
"step": 2595
|
|
},
|
|
{
|
|
"entropy": 5.838931655883789,
|
|
"epoch": 0.2920199921379233,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000499633756491259,
|
|
"loss": 5.8211,
|
|
"mean_token_accuracy": 0.15889843851327895,
|
|
"num_tokens": 5832836.0,
|
|
"step": 2600
|
|
},
|
|
{
|
|
"entropy": 5.781684303283692,
|
|
"epoch": 0.29258156904588084,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004996314630831781,
|
|
"loss": 5.7721,
|
|
"mean_token_accuracy": 0.15894242227077485,
|
|
"num_tokens": 5842892.0,
|
|
"step": 2605
|
|
},
|
|
{
|
|
"entropy": 5.837478494644165,
|
|
"epoch": 0.2931431459538384,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004996291625227443,
|
|
"loss": 5.7457,
|
|
"mean_token_accuracy": 0.17291262596845627,
|
|
"num_tokens": 5852909.0,
|
|
"step": 2610
|
|
},
|
|
{
|
|
"entropy": 5.885805130004883,
|
|
"epoch": 0.29370472286179594,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004996268548100307,
|
|
"loss": 5.9012,
|
|
"mean_token_accuracy": 0.15841708928346634,
|
|
"num_tokens": 5864676.0,
|
|
"step": 2615
|
|
},
|
|
{
|
|
"entropy": 5.65041446685791,
|
|
"epoch": 0.2942662997697535,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000499624539945111,
|
|
"loss": 5.6493,
|
|
"mean_token_accuracy": 0.17354976683855056,
|
|
"num_tokens": 5875258.0,
|
|
"step": 2620
|
|
},
|
|
{
|
|
"entropy": 5.831318807601929,
|
|
"epoch": 0.294827876677711,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004996222179280589,
|
|
"loss": 5.8205,
|
|
"mean_token_accuracy": 0.16486375480890275,
|
|
"num_tokens": 5885611.0,
|
|
"step": 2625
|
|
},
|
|
{
|
|
"entropy": 5.823601865768433,
|
|
"epoch": 0.29538945358566854,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004996198887589481,
|
|
"loss": 5.7816,
|
|
"mean_token_accuracy": 0.16281627342104912,
|
|
"num_tokens": 5896726.0,
|
|
"step": 2630
|
|
},
|
|
{
|
|
"entropy": 5.850169324874878,
|
|
"epoch": 0.2959510304936261,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004996175524378531,
|
|
"loss": 5.7982,
|
|
"mean_token_accuracy": 0.15578736662864684,
|
|
"num_tokens": 5907860.0,
|
|
"step": 2635
|
|
},
|
|
{
|
|
"entropy": 5.76372652053833,
|
|
"epoch": 0.29651260740158364,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000499615208964848,
|
|
"loss": 5.7388,
|
|
"mean_token_accuracy": 0.16492382287979127,
|
|
"num_tokens": 5918676.0,
|
|
"step": 2640
|
|
},
|
|
{
|
|
"entropy": 5.81892352104187,
|
|
"epoch": 0.2970741843095412,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004996128583400077,
|
|
"loss": 5.8202,
|
|
"mean_token_accuracy": 0.1684228152036667,
|
|
"num_tokens": 5928646.0,
|
|
"step": 2645
|
|
},
|
|
{
|
|
"entropy": 5.8090407371521,
|
|
"epoch": 0.29763576121749874,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004996105005634066,
|
|
"loss": 5.8284,
|
|
"mean_token_accuracy": 0.15891904681921004,
|
|
"num_tokens": 5938990.0,
|
|
"step": 2650
|
|
},
|
|
{
|
|
"entropy": 5.7710151195526125,
|
|
"epoch": 0.2981973381254563,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004996081356351202,
|
|
"loss": 5.7624,
|
|
"mean_token_accuracy": 0.16903775036334992,
|
|
"num_tokens": 5948811.0,
|
|
"step": 2655
|
|
},
|
|
{
|
|
"entropy": 5.782888793945313,
|
|
"epoch": 0.29875891503341384,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004996057635552237,
|
|
"loss": 5.8036,
|
|
"mean_token_accuracy": 0.16821091026067733,
|
|
"num_tokens": 5959227.0,
|
|
"step": 2660
|
|
},
|
|
{
|
|
"entropy": 5.81490797996521,
|
|
"epoch": 0.2993204919413714,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004996033843237925,
|
|
"loss": 5.7205,
|
|
"mean_token_accuracy": 0.1657700628042221,
|
|
"num_tokens": 5970546.0,
|
|
"step": 2665
|
|
},
|
|
{
|
|
"entropy": 5.87456316947937,
|
|
"epoch": 0.29988206884932894,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004996009979409025,
|
|
"loss": 5.9995,
|
|
"mean_token_accuracy": 0.15168312638998033,
|
|
"num_tokens": 5983936.0,
|
|
"step": 2670
|
|
},
|
|
{
|
|
"entropy": 5.771059894561768,
|
|
"epoch": 0.30044364575728644,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004995986044066295,
|
|
"loss": 5.8058,
|
|
"mean_token_accuracy": 0.15828435719013215,
|
|
"num_tokens": 5994963.0,
|
|
"step": 2675
|
|
},
|
|
{
|
|
"entropy": 5.721059083938599,
|
|
"epoch": 0.301005222665244,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00049959620372105,
|
|
"loss": 5.769,
|
|
"mean_token_accuracy": 0.16122942715883254,
|
|
"num_tokens": 6005836.0,
|
|
"step": 2680
|
|
},
|
|
{
|
|
"entropy": 5.866373682022095,
|
|
"epoch": 0.30156679957320154,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004995937958842401,
|
|
"loss": 5.7657,
|
|
"mean_token_accuracy": 0.16774309277534485,
|
|
"num_tokens": 6017408.0,
|
|
"step": 2685
|
|
},
|
|
{
|
|
"entropy": 5.714548254013062,
|
|
"epoch": 0.3021283764811591,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004995913808962767,
|
|
"loss": 5.7917,
|
|
"mean_token_accuracy": 0.1594940260052681,
|
|
"num_tokens": 6029281.0,
|
|
"step": 2690
|
|
},
|
|
{
|
|
"entropy": 5.793282842636108,
|
|
"epoch": 0.30268995338911664,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004995889587572366,
|
|
"loss": 5.7786,
|
|
"mean_token_accuracy": 0.17166001200675965,
|
|
"num_tokens": 6039354.0,
|
|
"step": 2695
|
|
},
|
|
{
|
|
"entropy": 5.848501586914063,
|
|
"epoch": 0.3032515302970742,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000499586529467197,
|
|
"loss": 5.7438,
|
|
"mean_token_accuracy": 0.1634358808398247,
|
|
"num_tokens": 6050053.0,
|
|
"step": 2700
|
|
},
|
|
{
|
|
"entropy": 5.810464668273926,
|
|
"epoch": 0.30381310720503174,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004995840930262351,
|
|
"loss": 5.796,
|
|
"mean_token_accuracy": 0.16307734251022338,
|
|
"num_tokens": 6060221.0,
|
|
"step": 2705
|
|
},
|
|
{
|
|
"entropy": 5.813358402252197,
|
|
"epoch": 0.3043746841129893,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004995816494344287,
|
|
"loss": 5.8148,
|
|
"mean_token_accuracy": 0.164472234249115,
|
|
"num_tokens": 6070963.0,
|
|
"step": 2710
|
|
},
|
|
{
|
|
"entropy": 5.880467271804809,
|
|
"epoch": 0.30493626102094684,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004995791986918554,
|
|
"loss": 5.8965,
|
|
"mean_token_accuracy": 0.15967645049095153,
|
|
"num_tokens": 6082028.0,
|
|
"step": 2715
|
|
},
|
|
{
|
|
"entropy": 5.90054931640625,
|
|
"epoch": 0.30549783792890434,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004995767407985933,
|
|
"loss": 5.8354,
|
|
"mean_token_accuracy": 0.1607940226793289,
|
|
"num_tokens": 6092778.0,
|
|
"step": 2720
|
|
},
|
|
{
|
|
"entropy": 5.654600763320923,
|
|
"epoch": 0.3060594148368619,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004995742757547207,
|
|
"loss": 5.5836,
|
|
"mean_token_accuracy": 0.17212673127651215,
|
|
"num_tokens": 6103093.0,
|
|
"step": 2725
|
|
},
|
|
{
|
|
"entropy": 5.72548508644104,
|
|
"epoch": 0.30662099174481944,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000499571803560316,
|
|
"loss": 5.688,
|
|
"mean_token_accuracy": 0.16738756895065307,
|
|
"num_tokens": 6113516.0,
|
|
"step": 2730
|
|
},
|
|
{
|
|
"entropy": 5.73843092918396,
|
|
"epoch": 0.307182568652777,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004995693242154581,
|
|
"loss": 5.7662,
|
|
"mean_token_accuracy": 0.16290439814329147,
|
|
"num_tokens": 6125723.0,
|
|
"step": 2735
|
|
},
|
|
{
|
|
"entropy": 5.800117921829224,
|
|
"epoch": 0.30774414556073454,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004995668377202258,
|
|
"loss": 5.769,
|
|
"mean_token_accuracy": 0.16410442739725112,
|
|
"num_tokens": 6137091.0,
|
|
"step": 2740
|
|
},
|
|
{
|
|
"entropy": 5.694072914123535,
|
|
"epoch": 0.3083057224686921,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004995643440746982,
|
|
"loss": 5.7067,
|
|
"mean_token_accuracy": 0.17022011578083038,
|
|
"num_tokens": 6147941.0,
|
|
"step": 2745
|
|
},
|
|
{
|
|
"entropy": 5.722031736373902,
|
|
"epoch": 0.30886729937664964,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004995618432789548,
|
|
"loss": 5.7176,
|
|
"mean_token_accuracy": 0.1659976676106453,
|
|
"num_tokens": 6158493.0,
|
|
"step": 2750
|
|
},
|
|
{
|
|
"entropy": 5.759584665298462,
|
|
"epoch": 0.3094288762846072,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004995593353330753,
|
|
"loss": 5.8521,
|
|
"mean_token_accuracy": 0.16094479858875274,
|
|
"num_tokens": 6170759.0,
|
|
"step": 2755
|
|
},
|
|
{
|
|
"entropy": 5.833408498764038,
|
|
"epoch": 0.30999045319256474,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004995568202371393,
|
|
"loss": 5.6907,
|
|
"mean_token_accuracy": 0.1637557715177536,
|
|
"num_tokens": 6182488.0,
|
|
"step": 2760
|
|
},
|
|
{
|
|
"entropy": 5.804695177078247,
|
|
"epoch": 0.3105520301005223,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004995542979912272,
|
|
"loss": 5.8707,
|
|
"mean_token_accuracy": 0.1571161836385727,
|
|
"num_tokens": 6193849.0,
|
|
"step": 2765
|
|
},
|
|
{
|
|
"entropy": 5.790905427932739,
|
|
"epoch": 0.3111136070084798,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004995517685954192,
|
|
"loss": 5.7189,
|
|
"mean_token_accuracy": 0.16910731494426728,
|
|
"num_tokens": 6204132.0,
|
|
"step": 2770
|
|
},
|
|
{
|
|
"entropy": 5.909777641296387,
|
|
"epoch": 0.31167518391643734,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004995492320497958,
|
|
"loss": 5.8598,
|
|
"mean_token_accuracy": 0.1597845435142517,
|
|
"num_tokens": 6215547.0,
|
|
"step": 2775
|
|
},
|
|
{
|
|
"entropy": 5.801691675186158,
|
|
"epoch": 0.3122367608243949,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004995466883544376,
|
|
"loss": 5.8907,
|
|
"mean_token_accuracy": 0.15422286093235016,
|
|
"num_tokens": 6227150.0,
|
|
"step": 2780
|
|
},
|
|
{
|
|
"entropy": 5.87442626953125,
|
|
"epoch": 0.31279833773235244,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004995441375094258,
|
|
"loss": 5.8844,
|
|
"mean_token_accuracy": 0.16403253972530366,
|
|
"num_tokens": 6237387.0,
|
|
"step": 2785
|
|
},
|
|
{
|
|
"entropy": 5.840343379974366,
|
|
"epoch": 0.31335991464031,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004995415795148417,
|
|
"loss": 5.7749,
|
|
"mean_token_accuracy": 0.17121776640415193,
|
|
"num_tokens": 6248623.0,
|
|
"step": 2790
|
|
},
|
|
{
|
|
"entropy": 5.708501529693604,
|
|
"epoch": 0.31392149154826754,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004995390143707665,
|
|
"loss": 5.6884,
|
|
"mean_token_accuracy": 0.17336638271808624,
|
|
"num_tokens": 6258596.0,
|
|
"step": 2795
|
|
},
|
|
{
|
|
"entropy": 5.771423864364624,
|
|
"epoch": 0.3144830684562251,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004995364420772821,
|
|
"loss": 5.9251,
|
|
"mean_token_accuracy": 0.1520102985203266,
|
|
"num_tokens": 6270529.0,
|
|
"step": 2800
|
|
},
|
|
{
|
|
"entropy": 5.995839786529541,
|
|
"epoch": 0.31504464536418264,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004995338626344702,
|
|
"loss": 5.8159,
|
|
"mean_token_accuracy": 0.16036106050014495,
|
|
"num_tokens": 6280891.0,
|
|
"step": 2805
|
|
},
|
|
{
|
|
"entropy": 5.727972602844238,
|
|
"epoch": 0.3156062222721402,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000499531276042413,
|
|
"loss": 5.7623,
|
|
"mean_token_accuracy": 0.1606262966990471,
|
|
"num_tokens": 6292247.0,
|
|
"step": 2810
|
|
},
|
|
{
|
|
"entropy": 5.745919132232666,
|
|
"epoch": 0.31616779918009774,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004995286823011929,
|
|
"loss": 5.743,
|
|
"mean_token_accuracy": 0.16411550790071489,
|
|
"num_tokens": 6302403.0,
|
|
"step": 2815
|
|
},
|
|
{
|
|
"entropy": 5.725137090682983,
|
|
"epoch": 0.31672937608805524,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004995260814108926,
|
|
"loss": 5.6207,
|
|
"mean_token_accuracy": 0.17178634107112883,
|
|
"num_tokens": 6313901.0,
|
|
"step": 2820
|
|
},
|
|
{
|
|
"entropy": 5.81232967376709,
|
|
"epoch": 0.3172909529960128,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004995234733715947,
|
|
"loss": 5.854,
|
|
"mean_token_accuracy": 0.1643539547920227,
|
|
"num_tokens": 6323711.0,
|
|
"step": 2825
|
|
},
|
|
{
|
|
"entropy": 5.800817775726318,
|
|
"epoch": 0.31785252990397034,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004995208581833824,
|
|
"loss": 5.7541,
|
|
"mean_token_accuracy": 0.16257323026657106,
|
|
"num_tokens": 6334937.0,
|
|
"step": 2830
|
|
},
|
|
{
|
|
"entropy": 5.859487771987915,
|
|
"epoch": 0.3184141068119279,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004995182358463388,
|
|
"loss": 5.8384,
|
|
"mean_token_accuracy": 0.16172128021717072,
|
|
"num_tokens": 6345723.0,
|
|
"step": 2835
|
|
},
|
|
{
|
|
"entropy": 5.77629508972168,
|
|
"epoch": 0.31897568371988544,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004995156063605475,
|
|
"loss": 5.7774,
|
|
"mean_token_accuracy": 0.16092146784067154,
|
|
"num_tokens": 6357573.0,
|
|
"step": 2840
|
|
},
|
|
{
|
|
"entropy": 5.80016713142395,
|
|
"epoch": 0.319537260627843,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004995129697260922,
|
|
"loss": 5.789,
|
|
"mean_token_accuracy": 0.1699286863207817,
|
|
"num_tokens": 6367417.0,
|
|
"step": 2845
|
|
},
|
|
{
|
|
"entropy": 5.8359129428863525,
|
|
"epoch": 0.32009883753580054,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004995103259430569,
|
|
"loss": 5.8108,
|
|
"mean_token_accuracy": 0.16924816370010376,
|
|
"num_tokens": 6377753.0,
|
|
"step": 2850
|
|
},
|
|
{
|
|
"entropy": 5.801795578002929,
|
|
"epoch": 0.3206604144437581,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004995076750115258,
|
|
"loss": 5.7995,
|
|
"mean_token_accuracy": 0.16497709155082702,
|
|
"num_tokens": 6388613.0,
|
|
"step": 2855
|
|
},
|
|
{
|
|
"entropy": 5.760921764373779,
|
|
"epoch": 0.32122199135171564,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004995050169315832,
|
|
"loss": 5.7595,
|
|
"mean_token_accuracy": 0.15997344106435776,
|
|
"num_tokens": 6399415.0,
|
|
"step": 2860
|
|
},
|
|
{
|
|
"entropy": 5.789756345748901,
|
|
"epoch": 0.32178356825967314,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004995023517033138,
|
|
"loss": 5.7914,
|
|
"mean_token_accuracy": 0.1634930342435837,
|
|
"num_tokens": 6411435.0,
|
|
"step": 2865
|
|
},
|
|
{
|
|
"entropy": 5.870270442962647,
|
|
"epoch": 0.3223451451676307,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004994996793268024,
|
|
"loss": 5.9323,
|
|
"mean_token_accuracy": 0.1633247122168541,
|
|
"num_tokens": 6423030.0,
|
|
"step": 2870
|
|
},
|
|
{
|
|
"entropy": 5.857495498657227,
|
|
"epoch": 0.32290672207558824,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004994969998021342,
|
|
"loss": 5.7201,
|
|
"mean_token_accuracy": 0.16738023161888121,
|
|
"num_tokens": 6434330.0,
|
|
"step": 2875
|
|
},
|
|
{
|
|
"entropy": 5.769474983215332,
|
|
"epoch": 0.3234682989835458,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004994943131293944,
|
|
"loss": 5.8217,
|
|
"mean_token_accuracy": 0.16210121810436248,
|
|
"num_tokens": 6446452.0,
|
|
"step": 2880
|
|
},
|
|
{
|
|
"entropy": 5.821052694320679,
|
|
"epoch": 0.32402987589150334,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004994916193086687,
|
|
"loss": 5.7826,
|
|
"mean_token_accuracy": 0.16928485482931138,
|
|
"num_tokens": 6456723.0,
|
|
"step": 2885
|
|
},
|
|
{
|
|
"entropy": 5.84451904296875,
|
|
"epoch": 0.3245914527994609,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004994889183400428,
|
|
"loss": 5.8996,
|
|
"mean_token_accuracy": 0.15721678286790847,
|
|
"num_tokens": 6468117.0,
|
|
"step": 2890
|
|
},
|
|
{
|
|
"entropy": 5.75935549736023,
|
|
"epoch": 0.32515302970741844,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004994862102236025,
|
|
"loss": 5.6807,
|
|
"mean_token_accuracy": 0.16875990331172944,
|
|
"num_tokens": 6479465.0,
|
|
"step": 2895
|
|
},
|
|
{
|
|
"entropy": 5.867430257797241,
|
|
"epoch": 0.325714606615376,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004994834949594342,
|
|
"loss": 5.9102,
|
|
"mean_token_accuracy": 0.16001443415880204,
|
|
"num_tokens": 6490868.0,
|
|
"step": 2900
|
|
},
|
|
{
|
|
"entropy": 5.984825801849365,
|
|
"epoch": 0.32627618352333354,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004994807725476246,
|
|
"loss": 5.7957,
|
|
"mean_token_accuracy": 0.16391244530677795,
|
|
"num_tokens": 6502126.0,
|
|
"step": 2905
|
|
},
|
|
{
|
|
"entropy": 5.706523084640503,
|
|
"epoch": 0.3268377604312911,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004994780429882599,
|
|
"loss": 5.8769,
|
|
"mean_token_accuracy": 0.1568797692656517,
|
|
"num_tokens": 6514382.0,
|
|
"step": 2910
|
|
},
|
|
{
|
|
"entropy": 5.8119182109832765,
|
|
"epoch": 0.3273993373392486,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004994753062814274,
|
|
"loss": 5.7535,
|
|
"mean_token_accuracy": 0.16137978285551072,
|
|
"num_tokens": 6526272.0,
|
|
"step": 2915
|
|
},
|
|
{
|
|
"entropy": 5.7386698722839355,
|
|
"epoch": 0.32796091424720614,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004994725624272139,
|
|
"loss": 5.7728,
|
|
"mean_token_accuracy": 0.1649998188018799,
|
|
"num_tokens": 6537511.0,
|
|
"step": 2920
|
|
},
|
|
{
|
|
"entropy": 5.808128547668457,
|
|
"epoch": 0.3285224911551637,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004994698114257071,
|
|
"loss": 5.7152,
|
|
"mean_token_accuracy": 0.16380638182163237,
|
|
"num_tokens": 6549737.0,
|
|
"step": 2925
|
|
},
|
|
{
|
|
"entropy": 5.764562511444092,
|
|
"epoch": 0.32908406806312124,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004994670532769944,
|
|
"loss": 5.8017,
|
|
"mean_token_accuracy": 0.16241833567619324,
|
|
"num_tokens": 6560318.0,
|
|
"step": 2930
|
|
},
|
|
{
|
|
"entropy": 5.774281787872314,
|
|
"epoch": 0.3296456449710788,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004994642879811637,
|
|
"loss": 5.7263,
|
|
"mean_token_accuracy": 0.1679333508014679,
|
|
"num_tokens": 6570575.0,
|
|
"step": 2935
|
|
},
|
|
{
|
|
"entropy": 5.764078998565674,
|
|
"epoch": 0.33020722187903634,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000499461515538303,
|
|
"loss": 5.784,
|
|
"mean_token_accuracy": 0.1587074115872383,
|
|
"num_tokens": 6582083.0,
|
|
"step": 2940
|
|
},
|
|
{
|
|
"entropy": 5.93672661781311,
|
|
"epoch": 0.3307687987869939,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004994587359485006,
|
|
"loss": 5.9026,
|
|
"mean_token_accuracy": 0.1658690318465233,
|
|
"num_tokens": 6592240.0,
|
|
"step": 2945
|
|
},
|
|
{
|
|
"entropy": 5.766451597213745,
|
|
"epoch": 0.33133037569495144,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000499455949211845,
|
|
"loss": 5.681,
|
|
"mean_token_accuracy": 0.17034200876951217,
|
|
"num_tokens": 6602680.0,
|
|
"step": 2950
|
|
},
|
|
{
|
|
"entropy": 5.727759552001953,
|
|
"epoch": 0.331891952602909,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004994531553284248,
|
|
"loss": 5.7982,
|
|
"mean_token_accuracy": 0.16611240208148956,
|
|
"num_tokens": 6613399.0,
|
|
"step": 2955
|
|
},
|
|
{
|
|
"entropy": 5.876832723617554,
|
|
"epoch": 0.3324535295108665,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004994503542983293,
|
|
"loss": 5.87,
|
|
"mean_token_accuracy": 0.1549868866801262,
|
|
"num_tokens": 6624410.0,
|
|
"step": 2960
|
|
},
|
|
{
|
|
"entropy": 5.81924524307251,
|
|
"epoch": 0.33301510641882404,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004994475461216472,
|
|
"loss": 5.723,
|
|
"mean_token_accuracy": 0.1706065744161606,
|
|
"num_tokens": 6635523.0,
|
|
"step": 2965
|
|
},
|
|
{
|
|
"entropy": 5.7495808601379395,
|
|
"epoch": 0.3335766833267816,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004994447307984684,
|
|
"loss": 5.8791,
|
|
"mean_token_accuracy": 0.1590138331055641,
|
|
"num_tokens": 6648416.0,
|
|
"step": 2970
|
|
},
|
|
{
|
|
"entropy": 5.705846691131592,
|
|
"epoch": 0.33413826023473914,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004994419083288823,
|
|
"loss": 5.6685,
|
|
"mean_token_accuracy": 0.16495705097913743,
|
|
"num_tokens": 6658907.0,
|
|
"step": 2975
|
|
},
|
|
{
|
|
"entropy": 5.836928033828736,
|
|
"epoch": 0.3346998371426967,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004994390787129787,
|
|
"loss": 5.829,
|
|
"mean_token_accuracy": 0.16485339403152466,
|
|
"num_tokens": 6669682.0,
|
|
"step": 2980
|
|
},
|
|
{
|
|
"entropy": 5.863325500488282,
|
|
"epoch": 0.33526141405065424,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004994362419508478,
|
|
"loss": 5.9078,
|
|
"mean_token_accuracy": 0.15432428419589997,
|
|
"num_tokens": 6681919.0,
|
|
"step": 2985
|
|
},
|
|
{
|
|
"entropy": 5.885800790786743,
|
|
"epoch": 0.3358229909586118,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00049943339804258,
|
|
"loss": 5.8511,
|
|
"mean_token_accuracy": 0.1624743551015854,
|
|
"num_tokens": 6693988.0,
|
|
"step": 2990
|
|
},
|
|
{
|
|
"entropy": 5.735952138900757,
|
|
"epoch": 0.33638456786656934,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004994305469882657,
|
|
"loss": 5.788,
|
|
"mean_token_accuracy": 0.16164974868297577,
|
|
"num_tokens": 6705413.0,
|
|
"step": 2995
|
|
},
|
|
{
|
|
"entropy": 5.796762180328369,
|
|
"epoch": 0.3369461447745269,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004994276887879957,
|
|
"loss": 5.72,
|
|
"mean_token_accuracy": 0.16385204046964646,
|
|
"num_tokens": 6716217.0,
|
|
"step": 3000
|
|
},
|
|
{
|
|
"epoch": 0.3369461447745269,
|
|
"eval_entropy": 5.6763698884375104,
|
|
"eval_loss": 5.810102939605713,
|
|
"eval_mean_token_accuracy": 0.16994755314353172,
|
|
"eval_num_tokens": 6716217.0,
|
|
"eval_runtime": 23.769,
|
|
"eval_samples_per_second": 1304.767,
|
|
"eval_steps_per_second": 163.112,
|
|
"step": 3000
|
|
}
|
|
],
|
|
"logging_steps": 5,
|
|
"max_steps": 89030,
|
|
"num_input_tokens_seen": 0,
|
|
"num_train_epochs": 10,
|
|
"save_steps": 3000,
|
|
"stateful_callbacks": {
|
|
"TrainerControl": {
|
|
"args": {
|
|
"should_epoch_stop": false,
|
|
"should_evaluate": false,
|
|
"should_log": false,
|
|
"should_save": true,
|
|
"should_training_stop": false
|
|
},
|
|
"attributes": {}
|
|
}
|
|
},
|
|
"total_flos": 1.0538862999552e+16,
|
|
"train_batch_size": 16,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|