d4d3ca317e
Model: fpadovani/eng-latn-100mb-after-ppt-Dp-100mb-ckpt500_seed10 Source: Original Platform
18068 lines
494 KiB
JSON
18068 lines
494 KiB
JSON
{
|
|
"best_global_step": null,
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 1.010782276632785,
|
|
"eval_steps": 3000,
|
|
"global_step": 9000,
|
|
"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
|
|
},
|
|
{
|
|
"entropy": 5.797139883041382,
|
|
"epoch": 0.33750772168248444,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004994248234418611,
|
|
"loss": 5.796,
|
|
"mean_token_accuracy": 0.16773131042718886,
|
|
"num_tokens": 6728059.0,
|
|
"step": 3005
|
|
},
|
|
{
|
|
"entropy": 5.8079345703125,
|
|
"epoch": 0.33806929859044194,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000499421950949953,
|
|
"loss": 5.745,
|
|
"mean_token_accuracy": 0.1608613207936287,
|
|
"num_tokens": 6740650.0,
|
|
"step": 3010
|
|
},
|
|
{
|
|
"entropy": 5.646337985992432,
|
|
"epoch": 0.3386308754983995,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000499419071312363,
|
|
"loss": 5.6525,
|
|
"mean_token_accuracy": 0.16906045228242875,
|
|
"num_tokens": 6751467.0,
|
|
"step": 3015
|
|
},
|
|
{
|
|
"entropy": 5.76656322479248,
|
|
"epoch": 0.33919245240635704,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004994161845291828,
|
|
"loss": 5.7581,
|
|
"mean_token_accuracy": 0.17018764317035676,
|
|
"num_tokens": 6761377.0,
|
|
"step": 3020
|
|
},
|
|
{
|
|
"entropy": 5.726734828948975,
|
|
"epoch": 0.3397540293143146,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004994132906005041,
|
|
"loss": 5.705,
|
|
"mean_token_accuracy": 0.16395393162965774,
|
|
"num_tokens": 6773296.0,
|
|
"step": 3025
|
|
},
|
|
{
|
|
"entropy": 5.838716316223144,
|
|
"epoch": 0.34031560622227214,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004994103895264193,
|
|
"loss": 5.7745,
|
|
"mean_token_accuracy": 0.161932972073555,
|
|
"num_tokens": 6784122.0,
|
|
"step": 3030
|
|
},
|
|
{
|
|
"entropy": 5.674428272247314,
|
|
"epoch": 0.3408771831302297,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004994074813070207,
|
|
"loss": 5.6042,
|
|
"mean_token_accuracy": 0.17229476273059846,
|
|
"num_tokens": 6795604.0,
|
|
"step": 3035
|
|
},
|
|
{
|
|
"entropy": 5.6493141651153564,
|
|
"epoch": 0.34143876003818724,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004994045659424007,
|
|
"loss": 5.7595,
|
|
"mean_token_accuracy": 0.16679226011037826,
|
|
"num_tokens": 6806671.0,
|
|
"step": 3040
|
|
},
|
|
{
|
|
"entropy": 5.8630341529846195,
|
|
"epoch": 0.3420003369461448,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004994016434326524,
|
|
"loss": 5.7728,
|
|
"mean_token_accuracy": 0.1652206763625145,
|
|
"num_tokens": 6818271.0,
|
|
"step": 3045
|
|
},
|
|
{
|
|
"entropy": 5.696822690963745,
|
|
"epoch": 0.34256191385410234,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004993987137778687,
|
|
"loss": 5.7857,
|
|
"mean_token_accuracy": 0.16273954063653945,
|
|
"num_tokens": 6830049.0,
|
|
"step": 3050
|
|
},
|
|
{
|
|
"entropy": 5.905836725234986,
|
|
"epoch": 0.3431234907620599,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000499395776978143,
|
|
"loss": 5.9022,
|
|
"mean_token_accuracy": 0.15248986333608627,
|
|
"num_tokens": 6842275.0,
|
|
"step": 3055
|
|
},
|
|
{
|
|
"entropy": 5.9171247482299805,
|
|
"epoch": 0.3436850676700174,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004993928330335686,
|
|
"loss": 5.8546,
|
|
"mean_token_accuracy": 0.16483362764120102,
|
|
"num_tokens": 6854910.0,
|
|
"step": 3060
|
|
},
|
|
{
|
|
"entropy": 5.752092409133911,
|
|
"epoch": 0.34424664457797494,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004993898819442395,
|
|
"loss": 5.7903,
|
|
"mean_token_accuracy": 0.1667594663798809,
|
|
"num_tokens": 6866031.0,
|
|
"step": 3065
|
|
},
|
|
{
|
|
"entropy": 5.815317583084107,
|
|
"epoch": 0.3448082214859325,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004993869237102494,
|
|
"loss": 5.8144,
|
|
"mean_token_accuracy": 0.15923599153757095,
|
|
"num_tokens": 6877672.0,
|
|
"step": 3070
|
|
},
|
|
{
|
|
"entropy": 5.785966444015503,
|
|
"epoch": 0.34536979839389004,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004993839583316927,
|
|
"loss": 5.7151,
|
|
"mean_token_accuracy": 0.16859218031167983,
|
|
"num_tokens": 6889089.0,
|
|
"step": 3075
|
|
},
|
|
{
|
|
"entropy": 5.629759502410889,
|
|
"epoch": 0.3459313753018476,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004993809858086638,
|
|
"loss": 5.6769,
|
|
"mean_token_accuracy": 0.17261210083961487,
|
|
"num_tokens": 6899877.0,
|
|
"step": 3080
|
|
},
|
|
{
|
|
"entropy": 5.7409021854400635,
|
|
"epoch": 0.34649295220980514,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004993780061412571,
|
|
"loss": 5.6428,
|
|
"mean_token_accuracy": 0.17341359704732895,
|
|
"num_tokens": 6910686.0,
|
|
"step": 3085
|
|
},
|
|
{
|
|
"entropy": 5.706187343597412,
|
|
"epoch": 0.3470545291177627,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004993750193295678,
|
|
"loss": 5.6723,
|
|
"mean_token_accuracy": 0.1697265088558197,
|
|
"num_tokens": 6920867.0,
|
|
"step": 3090
|
|
},
|
|
{
|
|
"entropy": 5.847270345687866,
|
|
"epoch": 0.34761610602572024,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004993720253736909,
|
|
"loss": 5.8704,
|
|
"mean_token_accuracy": 0.16412845253944397,
|
|
"num_tokens": 6932779.0,
|
|
"step": 3095
|
|
},
|
|
{
|
|
"entropy": 5.834012413024903,
|
|
"epoch": 0.3481776829336778,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004993690242737216,
|
|
"loss": 5.7723,
|
|
"mean_token_accuracy": 0.16963789165019988,
|
|
"num_tokens": 6943378.0,
|
|
"step": 3100
|
|
},
|
|
{
|
|
"entropy": 5.743947124481201,
|
|
"epoch": 0.3487392598416353,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004993660160297555,
|
|
"loss": 5.7406,
|
|
"mean_token_accuracy": 0.1705598309636116,
|
|
"num_tokens": 6955469.0,
|
|
"step": 3105
|
|
},
|
|
{
|
|
"entropy": 5.833663511276245,
|
|
"epoch": 0.34930083674959284,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004993630006418885,
|
|
"loss": 5.8522,
|
|
"mean_token_accuracy": 0.1633060470223427,
|
|
"num_tokens": 6966750.0,
|
|
"step": 3110
|
|
},
|
|
{
|
|
"entropy": 5.754387903213501,
|
|
"epoch": 0.3498624136575504,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004993599781102166,
|
|
"loss": 5.7665,
|
|
"mean_token_accuracy": 0.16051937490701676,
|
|
"num_tokens": 6979010.0,
|
|
"step": 3115
|
|
},
|
|
{
|
|
"entropy": 5.8001645565032955,
|
|
"epoch": 0.35042399056550794,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004993569484348359,
|
|
"loss": 5.7434,
|
|
"mean_token_accuracy": 0.16329153329133989,
|
|
"num_tokens": 6990566.0,
|
|
"step": 3120
|
|
},
|
|
{
|
|
"entropy": 5.7782989025115965,
|
|
"epoch": 0.3509855674734655,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004993539116158429,
|
|
"loss": 5.741,
|
|
"mean_token_accuracy": 0.16875308752059937,
|
|
"num_tokens": 7000288.0,
|
|
"step": 3125
|
|
},
|
|
{
|
|
"entropy": 5.653655910491944,
|
|
"epoch": 0.35154714438142304,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004993508676533346,
|
|
"loss": 5.6895,
|
|
"mean_token_accuracy": 0.1710754454135895,
|
|
"num_tokens": 7011143.0,
|
|
"step": 3130
|
|
},
|
|
{
|
|
"entropy": 5.924561262130737,
|
|
"epoch": 0.3521087212893806,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004993478165474074,
|
|
"loss": 5.8466,
|
|
"mean_token_accuracy": 0.1573910817503929,
|
|
"num_tokens": 7022797.0,
|
|
"step": 3135
|
|
},
|
|
{
|
|
"entropy": 5.79572319984436,
|
|
"epoch": 0.35267029819733814,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004993447582981588,
|
|
"loss": 5.8203,
|
|
"mean_token_accuracy": 0.1609862983226776,
|
|
"num_tokens": 7033477.0,
|
|
"step": 3140
|
|
},
|
|
{
|
|
"entropy": 5.796788358688355,
|
|
"epoch": 0.3532318751052957,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000499341692905686,
|
|
"loss": 5.8409,
|
|
"mean_token_accuracy": 0.16787751168012618,
|
|
"num_tokens": 7045249.0,
|
|
"step": 3145
|
|
},
|
|
{
|
|
"entropy": 5.885875225067139,
|
|
"epoch": 0.35379345201325324,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004993386203700868,
|
|
"loss": 5.8593,
|
|
"mean_token_accuracy": 0.16046667695045472,
|
|
"num_tokens": 7056890.0,
|
|
"step": 3150
|
|
},
|
|
{
|
|
"entropy": 5.823569345474243,
|
|
"epoch": 0.35435502892121074,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004993355406914589,
|
|
"loss": 5.7372,
|
|
"mean_token_accuracy": 0.167946894466877,
|
|
"num_tokens": 7067181.0,
|
|
"step": 3155
|
|
},
|
|
{
|
|
"entropy": 5.720935964584351,
|
|
"epoch": 0.3549166058291683,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004993324538699003,
|
|
"loss": 5.7053,
|
|
"mean_token_accuracy": 0.16719571501016617,
|
|
"num_tokens": 7078220.0,
|
|
"step": 3160
|
|
},
|
|
{
|
|
"entropy": 5.789358043670655,
|
|
"epoch": 0.35547818273712584,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004993293599055094,
|
|
"loss": 5.7769,
|
|
"mean_token_accuracy": 0.16728582233190536,
|
|
"num_tokens": 7089536.0,
|
|
"step": 3165
|
|
},
|
|
{
|
|
"entropy": 5.793011903762817,
|
|
"epoch": 0.3560397596450834,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004993262587983848,
|
|
"loss": 5.8472,
|
|
"mean_token_accuracy": 0.16243477910757065,
|
|
"num_tokens": 7101535.0,
|
|
"step": 3170
|
|
},
|
|
{
|
|
"entropy": 5.8326075077056885,
|
|
"epoch": 0.35660133655304094,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000499323150548625,
|
|
"loss": 5.7532,
|
|
"mean_token_accuracy": 0.1641256794333458,
|
|
"num_tokens": 7112468.0,
|
|
"step": 3175
|
|
},
|
|
{
|
|
"entropy": 5.757024145126342,
|
|
"epoch": 0.3571629134609985,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004993200351563291,
|
|
"loss": 5.7476,
|
|
"mean_token_accuracy": 0.17058625370264052,
|
|
"num_tokens": 7123192.0,
|
|
"step": 3180
|
|
},
|
|
{
|
|
"entropy": 5.735212516784668,
|
|
"epoch": 0.35772449036895604,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004993169126215962,
|
|
"loss": 5.6668,
|
|
"mean_token_accuracy": 0.17214720845222473,
|
|
"num_tokens": 7133063.0,
|
|
"step": 3185
|
|
},
|
|
{
|
|
"entropy": 5.774411916732788,
|
|
"epoch": 0.3582860672769136,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004993137829445259,
|
|
"loss": 5.7657,
|
|
"mean_token_accuracy": 0.1659478947520256,
|
|
"num_tokens": 7144190.0,
|
|
"step": 3190
|
|
},
|
|
{
|
|
"entropy": 5.727322626113891,
|
|
"epoch": 0.35884764418487114,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004993106461252177,
|
|
"loss": 5.7459,
|
|
"mean_token_accuracy": 0.1681210070848465,
|
|
"num_tokens": 7155433.0,
|
|
"step": 3195
|
|
},
|
|
{
|
|
"entropy": 5.87981481552124,
|
|
"epoch": 0.3594092210928287,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004993075021637716,
|
|
"loss": 5.8159,
|
|
"mean_token_accuracy": 0.16468181908130647,
|
|
"num_tokens": 7166084.0,
|
|
"step": 3200
|
|
},
|
|
{
|
|
"entropy": 5.841505908966065,
|
|
"epoch": 0.3599707980007862,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004993043510602875,
|
|
"loss": 5.8403,
|
|
"mean_token_accuracy": 0.16430858969688417,
|
|
"num_tokens": 7176948.0,
|
|
"step": 3205
|
|
},
|
|
{
|
|
"entropy": 5.764357376098633,
|
|
"epoch": 0.36053237490874374,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000499301192814866,
|
|
"loss": 5.6985,
|
|
"mean_token_accuracy": 0.170166976749897,
|
|
"num_tokens": 7188601.0,
|
|
"step": 3210
|
|
},
|
|
{
|
|
"entropy": 5.741007947921753,
|
|
"epoch": 0.3610939518167013,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004992980274276074,
|
|
"loss": 5.7379,
|
|
"mean_token_accuracy": 0.16825974434614183,
|
|
"num_tokens": 7198495.0,
|
|
"step": 3215
|
|
},
|
|
{
|
|
"entropy": 5.829579257965088,
|
|
"epoch": 0.36165552872465884,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004992948548986128,
|
|
"loss": 5.7144,
|
|
"mean_token_accuracy": 0.16826552152633667,
|
|
"num_tokens": 7209848.0,
|
|
"step": 3220
|
|
},
|
|
{
|
|
"entropy": 5.743291139602661,
|
|
"epoch": 0.3622171056326164,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004992916752279829,
|
|
"loss": 5.8554,
|
|
"mean_token_accuracy": 0.15997544676065445,
|
|
"num_tokens": 7220366.0,
|
|
"step": 3225
|
|
},
|
|
{
|
|
"entropy": 5.798778533935547,
|
|
"epoch": 0.36277868254057394,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000499288488415819,
|
|
"loss": 5.7465,
|
|
"mean_token_accuracy": 0.16187015026807786,
|
|
"num_tokens": 7231442.0,
|
|
"step": 3230
|
|
},
|
|
{
|
|
"entropy": 5.745628833770752,
|
|
"epoch": 0.3633402594485315,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004992852944622229,
|
|
"loss": 5.7875,
|
|
"mean_token_accuracy": 0.16286419332027435,
|
|
"num_tokens": 7242391.0,
|
|
"step": 3235
|
|
},
|
|
{
|
|
"entropy": 5.689303398132324,
|
|
"epoch": 0.36390183635648904,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004992820933672958,
|
|
"loss": 5.6783,
|
|
"mean_token_accuracy": 0.1670082300901413,
|
|
"num_tokens": 7252061.0,
|
|
"step": 3240
|
|
},
|
|
{
|
|
"entropy": 5.785434722900391,
|
|
"epoch": 0.3644634132644466,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004992788851311399,
|
|
"loss": 5.7548,
|
|
"mean_token_accuracy": 0.1655452072620392,
|
|
"num_tokens": 7264035.0,
|
|
"step": 3245
|
|
},
|
|
{
|
|
"entropy": 5.886760139465332,
|
|
"epoch": 0.3650249901724041,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004992756697538574,
|
|
"loss": 5.8265,
|
|
"mean_token_accuracy": 0.1640867918729782,
|
|
"num_tokens": 7275988.0,
|
|
"step": 3250
|
|
},
|
|
{
|
|
"entropy": 5.732627916336059,
|
|
"epoch": 0.36558656708036164,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004992724472355505,
|
|
"loss": 5.6994,
|
|
"mean_token_accuracy": 0.16559962779283524,
|
|
"num_tokens": 7286509.0,
|
|
"step": 3255
|
|
},
|
|
{
|
|
"entropy": 5.847105884552002,
|
|
"epoch": 0.3661481439883192,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004992692175763219,
|
|
"loss": 5.7743,
|
|
"mean_token_accuracy": 0.16747108101844788,
|
|
"num_tokens": 7296916.0,
|
|
"step": 3260
|
|
},
|
|
{
|
|
"entropy": 5.801908731460571,
|
|
"epoch": 0.36670972089627674,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004992659807762745,
|
|
"loss": 5.8594,
|
|
"mean_token_accuracy": 0.16267115846276284,
|
|
"num_tokens": 7309563.0,
|
|
"step": 3265
|
|
},
|
|
{
|
|
"entropy": 5.785950422286987,
|
|
"epoch": 0.3672712978042343,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004992627368355112,
|
|
"loss": 5.7251,
|
|
"mean_token_accuracy": 0.15922298580408095,
|
|
"num_tokens": 7320264.0,
|
|
"step": 3270
|
|
},
|
|
{
|
|
"entropy": 5.657385540008545,
|
|
"epoch": 0.36783287471219184,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004992594857541355,
|
|
"loss": 5.6763,
|
|
"mean_token_accuracy": 0.16557356864213943,
|
|
"num_tokens": 7330442.0,
|
|
"step": 3275
|
|
},
|
|
{
|
|
"entropy": 5.892805433273315,
|
|
"epoch": 0.3683944516201494,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004992562275322506,
|
|
"loss": 5.8867,
|
|
"mean_token_accuracy": 0.15922775268554687,
|
|
"num_tokens": 7342292.0,
|
|
"step": 3280
|
|
},
|
|
{
|
|
"entropy": 5.854403734207153,
|
|
"epoch": 0.36895602852810694,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004992529621699606,
|
|
"loss": 5.7803,
|
|
"mean_token_accuracy": 0.1635183572769165,
|
|
"num_tokens": 7353857.0,
|
|
"step": 3285
|
|
},
|
|
{
|
|
"entropy": 5.719515180587768,
|
|
"epoch": 0.3695176054360645,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004992496896673692,
|
|
"loss": 5.7124,
|
|
"mean_token_accuracy": 0.16950557231903077,
|
|
"num_tokens": 7365653.0,
|
|
"step": 3290
|
|
},
|
|
{
|
|
"entropy": 5.758349752426147,
|
|
"epoch": 0.37007918234402204,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004992464100245809,
|
|
"loss": 5.7199,
|
|
"mean_token_accuracy": 0.1599016636610031,
|
|
"num_tokens": 7376522.0,
|
|
"step": 3295
|
|
},
|
|
{
|
|
"entropy": 5.776468706130982,
|
|
"epoch": 0.37064075925197953,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004992431232416997,
|
|
"loss": 5.7175,
|
|
"mean_token_accuracy": 0.1696113720536232,
|
|
"num_tokens": 7388562.0,
|
|
"step": 3300
|
|
},
|
|
{
|
|
"entropy": 5.762558937072754,
|
|
"epoch": 0.3712023361599371,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004992398293188307,
|
|
"loss": 5.7681,
|
|
"mean_token_accuracy": 0.16615088731050492,
|
|
"num_tokens": 7398597.0,
|
|
"step": 3305
|
|
},
|
|
{
|
|
"entropy": 5.743051147460937,
|
|
"epoch": 0.37176391306789464,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004992365282560784,
|
|
"loss": 5.7173,
|
|
"mean_token_accuracy": 0.16997455507516862,
|
|
"num_tokens": 7409656.0,
|
|
"step": 3310
|
|
},
|
|
{
|
|
"entropy": 5.724304437637329,
|
|
"epoch": 0.3723254899758522,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004992332200535483,
|
|
"loss": 5.7505,
|
|
"mean_token_accuracy": 0.1614181160926819,
|
|
"num_tokens": 7420621.0,
|
|
"step": 3315
|
|
},
|
|
{
|
|
"entropy": 5.867142868041992,
|
|
"epoch": 0.37288706688380974,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004992299047113452,
|
|
"loss": 5.8013,
|
|
"mean_token_accuracy": 0.16799139082431794,
|
|
"num_tokens": 7432951.0,
|
|
"step": 3320
|
|
},
|
|
{
|
|
"entropy": 5.737457942962647,
|
|
"epoch": 0.3734486437917673,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004992265822295752,
|
|
"loss": 5.7682,
|
|
"mean_token_accuracy": 0.16687826067209244,
|
|
"num_tokens": 7443630.0,
|
|
"step": 3325
|
|
},
|
|
{
|
|
"entropy": 5.812999105453491,
|
|
"epoch": 0.37401022069972484,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004992232526083438,
|
|
"loss": 5.7764,
|
|
"mean_token_accuracy": 0.16452136635780334,
|
|
"num_tokens": 7454535.0,
|
|
"step": 3330
|
|
},
|
|
{
|
|
"entropy": 5.816757106781006,
|
|
"epoch": 0.3745717976076824,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000499219915847757,
|
|
"loss": 5.819,
|
|
"mean_token_accuracy": 0.16600556075572967,
|
|
"num_tokens": 7467751.0,
|
|
"step": 3335
|
|
},
|
|
{
|
|
"entropy": 5.722012186050415,
|
|
"epoch": 0.37513337451563994,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004992165719479211,
|
|
"loss": 5.6846,
|
|
"mean_token_accuracy": 0.17439237385988235,
|
|
"num_tokens": 7479347.0,
|
|
"step": 3340
|
|
},
|
|
{
|
|
"entropy": 5.720341777801513,
|
|
"epoch": 0.37569495142359743,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004992132209089427,
|
|
"loss": 5.7061,
|
|
"mean_token_accuracy": 0.16756229251623153,
|
|
"num_tokens": 7490916.0,
|
|
"step": 3345
|
|
},
|
|
{
|
|
"entropy": 5.762162923812866,
|
|
"epoch": 0.376256528331555,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004992098627309283,
|
|
"loss": 5.6934,
|
|
"mean_token_accuracy": 0.1669232428073883,
|
|
"num_tokens": 7500824.0,
|
|
"step": 3350
|
|
},
|
|
{
|
|
"entropy": 5.788598537445068,
|
|
"epoch": 0.37681810523951254,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000499206497413985,
|
|
"loss": 5.8349,
|
|
"mean_token_accuracy": 0.15951091349124907,
|
|
"num_tokens": 7511778.0,
|
|
"step": 3355
|
|
},
|
|
{
|
|
"entropy": 5.9402087211608885,
|
|
"epoch": 0.3773796821474701,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004992031249582197,
|
|
"loss": 5.8989,
|
|
"mean_token_accuracy": 0.1531204916536808,
|
|
"num_tokens": 7522616.0,
|
|
"step": 3360
|
|
},
|
|
{
|
|
"entropy": 5.83059024810791,
|
|
"epoch": 0.37794125905542764,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004991997453637401,
|
|
"loss": 5.7627,
|
|
"mean_token_accuracy": 0.16630529165267943,
|
|
"num_tokens": 7533019.0,
|
|
"step": 3365
|
|
},
|
|
{
|
|
"entropy": 5.763107776641846,
|
|
"epoch": 0.3785028359633852,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004991963586306536,
|
|
"loss": 5.7144,
|
|
"mean_token_accuracy": 0.16546949446201326,
|
|
"num_tokens": 7544139.0,
|
|
"step": 3370
|
|
},
|
|
{
|
|
"entropy": 5.744749355316162,
|
|
"epoch": 0.37906441287134274,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004991929647590682,
|
|
"loss": 5.7109,
|
|
"mean_token_accuracy": 0.16419145464897156,
|
|
"num_tokens": 7554638.0,
|
|
"step": 3375
|
|
},
|
|
{
|
|
"entropy": 5.8753022193908695,
|
|
"epoch": 0.3796259897793003,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004991895637490917,
|
|
"loss": 5.7744,
|
|
"mean_token_accuracy": 0.17059883773326873,
|
|
"num_tokens": 7565158.0,
|
|
"step": 3380
|
|
},
|
|
{
|
|
"entropy": 5.764221239089966,
|
|
"epoch": 0.38018756668725784,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004991861556008326,
|
|
"loss": 5.7757,
|
|
"mean_token_accuracy": 0.1676732838153839,
|
|
"num_tokens": 7576381.0,
|
|
"step": 3385
|
|
},
|
|
{
|
|
"entropy": 5.7199387550354,
|
|
"epoch": 0.3807491435952154,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004991827403143992,
|
|
"loss": 5.6552,
|
|
"mean_token_accuracy": 0.17059932500123978,
|
|
"num_tokens": 7586631.0,
|
|
"step": 3390
|
|
},
|
|
{
|
|
"entropy": 5.72076826095581,
|
|
"epoch": 0.3813107205031729,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004991793178899006,
|
|
"loss": 5.6992,
|
|
"mean_token_accuracy": 0.16320544332265854,
|
|
"num_tokens": 7598321.0,
|
|
"step": 3395
|
|
},
|
|
{
|
|
"entropy": 5.743707323074341,
|
|
"epoch": 0.38187229741113043,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004991758883274455,
|
|
"loss": 5.7504,
|
|
"mean_token_accuracy": 0.16687727868556976,
|
|
"num_tokens": 7609336.0,
|
|
"step": 3400
|
|
},
|
|
{
|
|
"entropy": 5.673875999450684,
|
|
"epoch": 0.382433874319088,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004991724516271432,
|
|
"loss": 5.6412,
|
|
"mean_token_accuracy": 0.16913782954216003,
|
|
"num_tokens": 7619116.0,
|
|
"step": 3405
|
|
},
|
|
{
|
|
"entropy": 5.788756227493286,
|
|
"epoch": 0.38299545122704554,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004991690077891032,
|
|
"loss": 5.7699,
|
|
"mean_token_accuracy": 0.16308848857879638,
|
|
"num_tokens": 7630567.0,
|
|
"step": 3410
|
|
},
|
|
{
|
|
"entropy": 5.7935224056243895,
|
|
"epoch": 0.3835570281350031,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004991655568134348,
|
|
"loss": 5.8374,
|
|
"mean_token_accuracy": 0.1602782800793648,
|
|
"num_tokens": 7642564.0,
|
|
"step": 3415
|
|
},
|
|
{
|
|
"entropy": 5.876939725875855,
|
|
"epoch": 0.38411860504296064,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004991620987002483,
|
|
"loss": 5.8651,
|
|
"mean_token_accuracy": 0.15797348022460939,
|
|
"num_tokens": 7654588.0,
|
|
"step": 3420
|
|
},
|
|
{
|
|
"entropy": 5.7633532047271725,
|
|
"epoch": 0.3846801819509182,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004991586334496536,
|
|
"loss": 5.6428,
|
|
"mean_token_accuracy": 0.1655205473303795,
|
|
"num_tokens": 7666120.0,
|
|
"step": 3425
|
|
},
|
|
{
|
|
"entropy": 5.729176092147827,
|
|
"epoch": 0.38524175885887574,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004991551610617611,
|
|
"loss": 5.8093,
|
|
"mean_token_accuracy": 0.16112280189990996,
|
|
"num_tokens": 7677132.0,
|
|
"step": 3430
|
|
},
|
|
{
|
|
"entropy": 5.9354095458984375,
|
|
"epoch": 0.3858033357668333,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004991516815366812,
|
|
"loss": 5.8653,
|
|
"mean_token_accuracy": 0.1617338925600052,
|
|
"num_tokens": 7687515.0,
|
|
"step": 3435
|
|
},
|
|
{
|
|
"entropy": 5.7069167137146,
|
|
"epoch": 0.38636491267479084,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.000499148194874525,
|
|
"loss": 5.6719,
|
|
"mean_token_accuracy": 0.16384845823049546,
|
|
"num_tokens": 7698454.0,
|
|
"step": 3440
|
|
},
|
|
{
|
|
"entropy": 5.6821191787719725,
|
|
"epoch": 0.38692648958274833,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004991447010754032,
|
|
"loss": 5.6562,
|
|
"mean_token_accuracy": 0.16871132850646972,
|
|
"num_tokens": 7708940.0,
|
|
"step": 3445
|
|
},
|
|
{
|
|
"entropy": 5.7896990299224855,
|
|
"epoch": 0.3874880664907059,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004991412001394273,
|
|
"loss": 5.6959,
|
|
"mean_token_accuracy": 0.16843825429677964,
|
|
"num_tokens": 7719705.0,
|
|
"step": 3450
|
|
},
|
|
{
|
|
"entropy": 5.832230281829834,
|
|
"epoch": 0.38804964339866344,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004991376920667086,
|
|
"loss": 5.8388,
|
|
"mean_token_accuracy": 0.16371525228023528,
|
|
"num_tokens": 7730649.0,
|
|
"step": 3455
|
|
},
|
|
{
|
|
"entropy": 5.676618766784668,
|
|
"epoch": 0.388611220306621,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004991341768573589,
|
|
"loss": 5.8568,
|
|
"mean_token_accuracy": 0.16013158112764359,
|
|
"num_tokens": 7742014.0,
|
|
"step": 3460
|
|
},
|
|
{
|
|
"entropy": 5.846466541290283,
|
|
"epoch": 0.38917279721457854,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.00049913065451149,
|
|
"loss": 5.7653,
|
|
"mean_token_accuracy": 0.15688156038522721,
|
|
"num_tokens": 7752892.0,
|
|
"step": 3465
|
|
},
|
|
{
|
|
"entropy": 5.8177694320678714,
|
|
"epoch": 0.3897343741225361,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004991271250292141,
|
|
"loss": 5.7855,
|
|
"mean_token_accuracy": 0.16310301572084426,
|
|
"num_tokens": 7762959.0,
|
|
"step": 3470
|
|
},
|
|
{
|
|
"entropy": 5.805336761474609,
|
|
"epoch": 0.39029595103049364,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004991235884106437,
|
|
"loss": 5.6786,
|
|
"mean_token_accuracy": 0.16769315004348756,
|
|
"num_tokens": 7773566.0,
|
|
"step": 3475
|
|
},
|
|
{
|
|
"entropy": 5.783961534500122,
|
|
"epoch": 0.3908575279384512,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004991200446558913,
|
|
"loss": 5.7125,
|
|
"mean_token_accuracy": 0.15630541294813155,
|
|
"num_tokens": 7785782.0,
|
|
"step": 3480
|
|
},
|
|
{
|
|
"entropy": 5.783238649368286,
|
|
"epoch": 0.39141910484640874,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004991164937650698,
|
|
"loss": 5.8792,
|
|
"mean_token_accuracy": 0.16230928599834443,
|
|
"num_tokens": 7797551.0,
|
|
"step": 3485
|
|
},
|
|
{
|
|
"entropy": 5.696440124511719,
|
|
"epoch": 0.39198068175436623,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004991129357382922,
|
|
"loss": 5.6555,
|
|
"mean_token_accuracy": 0.17688761949539183,
|
|
"num_tokens": 7808819.0,
|
|
"step": 3490
|
|
},
|
|
{
|
|
"entropy": 5.625875091552734,
|
|
"epoch": 0.3925422586623238,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004991093705756718,
|
|
"loss": 5.6004,
|
|
"mean_token_accuracy": 0.1714256227016449,
|
|
"num_tokens": 7818940.0,
|
|
"step": 3495
|
|
},
|
|
{
|
|
"entropy": 5.644198799133301,
|
|
"epoch": 0.39310383557028133,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004991057982773221,
|
|
"loss": 5.6226,
|
|
"mean_token_accuracy": 0.16977737098932266,
|
|
"num_tokens": 7829733.0,
|
|
"step": 3500
|
|
},
|
|
{
|
|
"entropy": 5.794569444656372,
|
|
"epoch": 0.3936654124782389,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004991022188433569,
|
|
"loss": 5.6837,
|
|
"mean_token_accuracy": 0.173957559466362,
|
|
"num_tokens": 7840427.0,
|
|
"step": 3505
|
|
},
|
|
{
|
|
"entropy": 5.803560733795166,
|
|
"epoch": 0.39422698938619644,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00049909863227389,
|
|
"loss": 5.7602,
|
|
"mean_token_accuracy": 0.16543414294719697,
|
|
"num_tokens": 7852834.0,
|
|
"step": 3510
|
|
},
|
|
{
|
|
"entropy": 5.725724458694458,
|
|
"epoch": 0.394788566294154,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004990950385690358,
|
|
"loss": 5.7975,
|
|
"mean_token_accuracy": 0.1662366047501564,
|
|
"num_tokens": 7864993.0,
|
|
"step": 3515
|
|
},
|
|
{
|
|
"entropy": 5.736254358291626,
|
|
"epoch": 0.39535014320211154,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004990914377289088,
|
|
"loss": 5.7733,
|
|
"mean_token_accuracy": 0.16539080888032914,
|
|
"num_tokens": 7876578.0,
|
|
"step": 3520
|
|
},
|
|
{
|
|
"entropy": 5.6808921813964846,
|
|
"epoch": 0.3959117201100691,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004990878297536233,
|
|
"loss": 5.602,
|
|
"mean_token_accuracy": 0.16962271183729172,
|
|
"num_tokens": 7886770.0,
|
|
"step": 3525
|
|
},
|
|
{
|
|
"entropy": 5.750912523269653,
|
|
"epoch": 0.39647329701802664,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004990842146432946,
|
|
"loss": 5.7544,
|
|
"mean_token_accuracy": 0.16750518679618837,
|
|
"num_tokens": 7897106.0,
|
|
"step": 3530
|
|
},
|
|
{
|
|
"entropy": 5.736833810806274,
|
|
"epoch": 0.3970348739259842,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004990805923980375,
|
|
"loss": 5.6173,
|
|
"mean_token_accuracy": 0.17670849114656448,
|
|
"num_tokens": 7907321.0,
|
|
"step": 3535
|
|
},
|
|
{
|
|
"entropy": 5.6947003364562985,
|
|
"epoch": 0.3975964508339417,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004990769630179673,
|
|
"loss": 5.6378,
|
|
"mean_token_accuracy": 0.1708067014813423,
|
|
"num_tokens": 7918628.0,
|
|
"step": 3540
|
|
},
|
|
{
|
|
"entropy": 5.804160213470459,
|
|
"epoch": 0.39815802774189923,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004990733265032,
|
|
"loss": 5.8033,
|
|
"mean_token_accuracy": 0.15756966173648834,
|
|
"num_tokens": 7929387.0,
|
|
"step": 3545
|
|
},
|
|
{
|
|
"entropy": 5.937828445434571,
|
|
"epoch": 0.3987196046498568,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004990696828538508,
|
|
"loss": 5.8303,
|
|
"mean_token_accuracy": 0.1656595528125763,
|
|
"num_tokens": 7940840.0,
|
|
"step": 3550
|
|
},
|
|
{
|
|
"entropy": 5.583690500259399,
|
|
"epoch": 0.39928118155781434,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000499066032070036,
|
|
"loss": 5.6996,
|
|
"mean_token_accuracy": 0.16692321449518205,
|
|
"num_tokens": 7952243.0,
|
|
"step": 3555
|
|
},
|
|
{
|
|
"entropy": 5.7877583503723145,
|
|
"epoch": 0.3998427584657719,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004990623741518719,
|
|
"loss": 5.7259,
|
|
"mean_token_accuracy": 0.1645309880375862,
|
|
"num_tokens": 7963150.0,
|
|
"step": 3560
|
|
},
|
|
{
|
|
"entropy": 5.867881965637207,
|
|
"epoch": 0.40040433537372944,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000499058709099475,
|
|
"loss": 5.8396,
|
|
"mean_token_accuracy": 0.15986913293600083,
|
|
"num_tokens": 7974862.0,
|
|
"step": 3565
|
|
},
|
|
{
|
|
"entropy": 5.838780927658081,
|
|
"epoch": 0.400965912281687,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004990550369129618,
|
|
"loss": 5.859,
|
|
"mean_token_accuracy": 0.1613443985581398,
|
|
"num_tokens": 7986438.0,
|
|
"step": 3570
|
|
},
|
|
{
|
|
"entropy": 5.721206903457642,
|
|
"epoch": 0.40152748918964454,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004990513575924494,
|
|
"loss": 5.6886,
|
|
"mean_token_accuracy": 0.16866439580917358,
|
|
"num_tokens": 7996958.0,
|
|
"step": 3575
|
|
},
|
|
{
|
|
"entropy": 5.814842224121094,
|
|
"epoch": 0.4020890660976021,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004990476711380548,
|
|
"loss": 5.7796,
|
|
"mean_token_accuracy": 0.1619115337729454,
|
|
"num_tokens": 8008862.0,
|
|
"step": 3580
|
|
},
|
|
{
|
|
"entropy": 5.754044866561889,
|
|
"epoch": 0.40265064300555964,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004990439775498954,
|
|
"loss": 5.7471,
|
|
"mean_token_accuracy": 0.16790588200092316,
|
|
"num_tokens": 8018940.0,
|
|
"step": 3585
|
|
},
|
|
{
|
|
"entropy": 5.823058938980102,
|
|
"epoch": 0.40321221991351713,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000499040276828089,
|
|
"loss": 5.7634,
|
|
"mean_token_accuracy": 0.15862593054771423,
|
|
"num_tokens": 8029148.0,
|
|
"step": 3590
|
|
},
|
|
{
|
|
"entropy": 5.768352890014649,
|
|
"epoch": 0.4037737968214747,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004990365689727533,
|
|
"loss": 5.6936,
|
|
"mean_token_accuracy": 0.17204392850399017,
|
|
"num_tokens": 8039618.0,
|
|
"step": 3595
|
|
},
|
|
{
|
|
"entropy": 5.713478374481201,
|
|
"epoch": 0.40433537372943223,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004990328539840062,
|
|
"loss": 5.6622,
|
|
"mean_token_accuracy": 0.1640905886888504,
|
|
"num_tokens": 8051145.0,
|
|
"step": 3600
|
|
},
|
|
{
|
|
"entropy": 5.762935543060303,
|
|
"epoch": 0.4048969506373898,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004990291318619663,
|
|
"loss": 5.7333,
|
|
"mean_token_accuracy": 0.1593351796269417,
|
|
"num_tokens": 8061520.0,
|
|
"step": 3605
|
|
},
|
|
{
|
|
"entropy": 5.703391027450562,
|
|
"epoch": 0.40545852754534734,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004990254026067518,
|
|
"loss": 5.6891,
|
|
"mean_token_accuracy": 0.16336395144462584,
|
|
"num_tokens": 8072876.0,
|
|
"step": 3610
|
|
},
|
|
{
|
|
"entropy": 5.851124668121338,
|
|
"epoch": 0.4060201044533049,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004990216662184817,
|
|
"loss": 5.7792,
|
|
"mean_token_accuracy": 0.17133180946111679,
|
|
"num_tokens": 8084240.0,
|
|
"step": 3615
|
|
},
|
|
{
|
|
"entropy": 5.714921951293945,
|
|
"epoch": 0.40658168136126244,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004990179226972749,
|
|
"loss": 5.6649,
|
|
"mean_token_accuracy": 0.17276083528995514,
|
|
"num_tokens": 8095773.0,
|
|
"step": 3620
|
|
},
|
|
{
|
|
"entropy": 5.614761018753052,
|
|
"epoch": 0.40714325826922,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004990141720432504,
|
|
"loss": 5.6632,
|
|
"mean_token_accuracy": 0.164325350522995,
|
|
"num_tokens": 8107003.0,
|
|
"step": 3625
|
|
},
|
|
{
|
|
"entropy": 5.77284688949585,
|
|
"epoch": 0.40770483517717754,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004990104142565279,
|
|
"loss": 5.634,
|
|
"mean_token_accuracy": 0.17135452032089232,
|
|
"num_tokens": 8117864.0,
|
|
"step": 3630
|
|
},
|
|
{
|
|
"entropy": 5.751232433319092,
|
|
"epoch": 0.40826641208513503,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000499006649337227,
|
|
"loss": 5.8332,
|
|
"mean_token_accuracy": 0.16449906975030898,
|
|
"num_tokens": 8129363.0,
|
|
"step": 3635
|
|
},
|
|
{
|
|
"entropy": 5.7713463306427,
|
|
"epoch": 0.4088279889930926,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004990028772854674,
|
|
"loss": 5.7403,
|
|
"mean_token_accuracy": 0.16790325492620467,
|
|
"num_tokens": 8141319.0,
|
|
"step": 3640
|
|
},
|
|
{
|
|
"entropy": 5.758999300003052,
|
|
"epoch": 0.40938956590105013,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004989990981013693,
|
|
"loss": 5.6544,
|
|
"mean_token_accuracy": 0.16989342421293258,
|
|
"num_tokens": 8153344.0,
|
|
"step": 3645
|
|
},
|
|
{
|
|
"entropy": 5.733306074142456,
|
|
"epoch": 0.4099511428090077,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000498995311785053,
|
|
"loss": 5.8208,
|
|
"mean_token_accuracy": 0.16506210714578629,
|
|
"num_tokens": 8164196.0,
|
|
"step": 3650
|
|
},
|
|
{
|
|
"entropy": 5.755592393875122,
|
|
"epoch": 0.41051271971696524,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004989915183366392,
|
|
"loss": 5.6837,
|
|
"mean_token_accuracy": 0.16661922484636307,
|
|
"num_tokens": 8174663.0,
|
|
"step": 3655
|
|
},
|
|
{
|
|
"entropy": 5.717682218551635,
|
|
"epoch": 0.4110742966249228,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004989877177562485,
|
|
"loss": 5.6592,
|
|
"mean_token_accuracy": 0.1678890362381935,
|
|
"num_tokens": 8185215.0,
|
|
"step": 3660
|
|
},
|
|
{
|
|
"entropy": 5.703695678710938,
|
|
"epoch": 0.41163587353288034,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000498983910044002,
|
|
"loss": 5.7415,
|
|
"mean_token_accuracy": 0.1730475068092346,
|
|
"num_tokens": 8195694.0,
|
|
"step": 3665
|
|
},
|
|
{
|
|
"entropy": 5.654563045501709,
|
|
"epoch": 0.4121974504408379,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004989800952000209,
|
|
"loss": 5.6326,
|
|
"mean_token_accuracy": 0.1769496351480484,
|
|
"num_tokens": 8206112.0,
|
|
"step": 3670
|
|
},
|
|
{
|
|
"entropy": 5.69666166305542,
|
|
"epoch": 0.41275902734879544,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004989762732244268,
|
|
"loss": 5.7306,
|
|
"mean_token_accuracy": 0.16730629801750183,
|
|
"num_tokens": 8216548.0,
|
|
"step": 3675
|
|
},
|
|
{
|
|
"entropy": 5.794802618026734,
|
|
"epoch": 0.413320604256753,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004989724441173413,
|
|
"loss": 5.754,
|
|
"mean_token_accuracy": 0.1663824200630188,
|
|
"num_tokens": 8226643.0,
|
|
"step": 3680
|
|
},
|
|
{
|
|
"entropy": 5.762028312683105,
|
|
"epoch": 0.4138821811647105,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004989686078788862,
|
|
"loss": 5.7755,
|
|
"mean_token_accuracy": 0.16354046761989594,
|
|
"num_tokens": 8236755.0,
|
|
"step": 3685
|
|
},
|
|
{
|
|
"entropy": 5.780991554260254,
|
|
"epoch": 0.41444375807266803,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004989647645091839,
|
|
"loss": 5.6652,
|
|
"mean_token_accuracy": 0.17011228799819947,
|
|
"num_tokens": 8247526.0,
|
|
"step": 3690
|
|
},
|
|
{
|
|
"entropy": 5.7317945003509525,
|
|
"epoch": 0.4150053349806256,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004989609140083565,
|
|
"loss": 5.7535,
|
|
"mean_token_accuracy": 0.16077264696359633,
|
|
"num_tokens": 8258649.0,
|
|
"step": 3695
|
|
},
|
|
{
|
|
"entropy": 5.719632863998413,
|
|
"epoch": 0.41556691188858313,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004989570563765269,
|
|
"loss": 5.6509,
|
|
"mean_token_accuracy": 0.1734781414270401,
|
|
"num_tokens": 8268260.0,
|
|
"step": 3700
|
|
},
|
|
{
|
|
"entropy": 5.832403326034546,
|
|
"epoch": 0.4161284887965407,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004989531916138176,
|
|
"loss": 5.8521,
|
|
"mean_token_accuracy": 0.1661074712872505,
|
|
"num_tokens": 8280090.0,
|
|
"step": 3705
|
|
},
|
|
{
|
|
"entropy": 5.770887136459351,
|
|
"epoch": 0.41669006570449824,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004989493197203519,
|
|
"loss": 5.7105,
|
|
"mean_token_accuracy": 0.17042227685451508,
|
|
"num_tokens": 8291217.0,
|
|
"step": 3710
|
|
},
|
|
{
|
|
"entropy": 5.712801837921143,
|
|
"epoch": 0.4172516426124558,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000498945440696253,
|
|
"loss": 5.6383,
|
|
"mean_token_accuracy": 0.17202145755290985,
|
|
"num_tokens": 8303541.0,
|
|
"step": 3715
|
|
},
|
|
{
|
|
"entropy": 5.691585826873779,
|
|
"epoch": 0.41781321952041334,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004989415545416444,
|
|
"loss": 5.7055,
|
|
"mean_token_accuracy": 0.16621753871440886,
|
|
"num_tokens": 8316104.0,
|
|
"step": 3720
|
|
},
|
|
{
|
|
"entropy": 5.714412450790405,
|
|
"epoch": 0.4183747964283709,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004989376612566498,
|
|
"loss": 5.6499,
|
|
"mean_token_accuracy": 0.1632611110806465,
|
|
"num_tokens": 8327158.0,
|
|
"step": 3725
|
|
},
|
|
{
|
|
"entropy": 5.792377138137818,
|
|
"epoch": 0.4189363733363284,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004989337608413933,
|
|
"loss": 5.8112,
|
|
"mean_token_accuracy": 0.16448640674352646,
|
|
"num_tokens": 8337685.0,
|
|
"step": 3730
|
|
},
|
|
{
|
|
"entropy": 5.860587453842163,
|
|
"epoch": 0.41949795024428593,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004989298532959989,
|
|
"loss": 5.8451,
|
|
"mean_token_accuracy": 0.16472315639257432,
|
|
"num_tokens": 8349778.0,
|
|
"step": 3735
|
|
},
|
|
{
|
|
"entropy": 5.750112152099609,
|
|
"epoch": 0.4200595271522435,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004989259386205912,
|
|
"loss": 5.666,
|
|
"mean_token_accuracy": 0.1754022315144539,
|
|
"num_tokens": 8361041.0,
|
|
"step": 3740
|
|
},
|
|
{
|
|
"entropy": 5.762225914001465,
|
|
"epoch": 0.42062110406020103,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004989220168152948,
|
|
"loss": 5.8574,
|
|
"mean_token_accuracy": 0.15982095003128052,
|
|
"num_tokens": 8373227.0,
|
|
"step": 3745
|
|
},
|
|
{
|
|
"entropy": 5.767544412612915,
|
|
"epoch": 0.4211826809681586,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004989180878802346,
|
|
"loss": 5.6921,
|
|
"mean_token_accuracy": 0.1750807821750641,
|
|
"num_tokens": 8384223.0,
|
|
"step": 3750
|
|
},
|
|
{
|
|
"entropy": 5.73232593536377,
|
|
"epoch": 0.42174425787611614,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004989141518155354,
|
|
"loss": 5.7327,
|
|
"mean_token_accuracy": 0.17130927443504335,
|
|
"num_tokens": 8395014.0,
|
|
"step": 3755
|
|
},
|
|
{
|
|
"entropy": 5.773546504974365,
|
|
"epoch": 0.4223058347840737,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004989102086213229,
|
|
"loss": 5.7043,
|
|
"mean_token_accuracy": 0.16679086536169052,
|
|
"num_tokens": 8406445.0,
|
|
"step": 3760
|
|
},
|
|
{
|
|
"entropy": 5.659664297103882,
|
|
"epoch": 0.42286741169203124,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004989062582977225,
|
|
"loss": 5.6355,
|
|
"mean_token_accuracy": 0.17889782637357712,
|
|
"num_tokens": 8417488.0,
|
|
"step": 3765
|
|
},
|
|
{
|
|
"entropy": 5.866618633270264,
|
|
"epoch": 0.4234289885999888,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004989023008448599,
|
|
"loss": 5.846,
|
|
"mean_token_accuracy": 0.16034092754125595,
|
|
"num_tokens": 8430582.0,
|
|
"step": 3770
|
|
},
|
|
{
|
|
"entropy": 5.660808086395264,
|
|
"epoch": 0.42399056550794634,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004988983362628614,
|
|
"loss": 5.659,
|
|
"mean_token_accuracy": 0.1664969280362129,
|
|
"num_tokens": 8442033.0,
|
|
"step": 3775
|
|
},
|
|
{
|
|
"entropy": 5.699296998977661,
|
|
"epoch": 0.42455214241590383,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004988943645518528,
|
|
"loss": 5.6395,
|
|
"mean_token_accuracy": 0.1659386932849884,
|
|
"num_tokens": 8451722.0,
|
|
"step": 3780
|
|
},
|
|
{
|
|
"entropy": 5.705109691619873,
|
|
"epoch": 0.4251137193238614,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004988903857119611,
|
|
"loss": 5.725,
|
|
"mean_token_accuracy": 0.16892832964658738,
|
|
"num_tokens": 8462753.0,
|
|
"step": 3785
|
|
},
|
|
{
|
|
"entropy": 5.83537015914917,
|
|
"epoch": 0.42567529623181893,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004988863997433125,
|
|
"loss": 5.7304,
|
|
"mean_token_accuracy": 0.16631137132644652,
|
|
"num_tokens": 8472755.0,
|
|
"step": 3790
|
|
},
|
|
{
|
|
"entropy": 5.653184795379639,
|
|
"epoch": 0.4262368731397765,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004988824066460341,
|
|
"loss": 5.7289,
|
|
"mean_token_accuracy": 0.16911315321922302,
|
|
"num_tokens": 8483296.0,
|
|
"step": 3795
|
|
},
|
|
{
|
|
"entropy": 5.733007955551147,
|
|
"epoch": 0.42679845004773403,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000498878406420253,
|
|
"loss": 5.5794,
|
|
"mean_token_accuracy": 0.17343849092721939,
|
|
"num_tokens": 8493739.0,
|
|
"step": 3800
|
|
},
|
|
{
|
|
"entropy": 5.726877450942993,
|
|
"epoch": 0.4273600269556916,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004988743990660967,
|
|
"loss": 5.7495,
|
|
"mean_token_accuracy": 0.16324111968278884,
|
|
"num_tokens": 8504788.0,
|
|
"step": 3805
|
|
},
|
|
{
|
|
"entropy": 5.762627601623535,
|
|
"epoch": 0.42792160386364914,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004988703845836927,
|
|
"loss": 5.6911,
|
|
"mean_token_accuracy": 0.16882169172167777,
|
|
"num_tokens": 8514708.0,
|
|
"step": 3810
|
|
},
|
|
{
|
|
"entropy": 5.695466566085815,
|
|
"epoch": 0.4284831807716067,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004988663629731687,
|
|
"loss": 5.5865,
|
|
"mean_token_accuracy": 0.17727579772472382,
|
|
"num_tokens": 8525227.0,
|
|
"step": 3815
|
|
},
|
|
{
|
|
"entropy": 5.613619995117188,
|
|
"epoch": 0.42904475767956424,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000498862334234653,
|
|
"loss": 5.6397,
|
|
"mean_token_accuracy": 0.172760471701622,
|
|
"num_tokens": 8536502.0,
|
|
"step": 3820
|
|
},
|
|
{
|
|
"entropy": 5.705569934844971,
|
|
"epoch": 0.4296063345875218,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004988582983682737,
|
|
"loss": 5.778,
|
|
"mean_token_accuracy": 0.165872523188591,
|
|
"num_tokens": 8548087.0,
|
|
"step": 3825
|
|
},
|
|
{
|
|
"entropy": 5.775690650939941,
|
|
"epoch": 0.4301679114954793,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004988542553741594,
|
|
"loss": 5.7594,
|
|
"mean_token_accuracy": 0.16778652966022492,
|
|
"num_tokens": 8560856.0,
|
|
"step": 3830
|
|
},
|
|
{
|
|
"entropy": 5.875372838973999,
|
|
"epoch": 0.43072948840343683,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004988502052524388,
|
|
"loss": 5.8852,
|
|
"mean_token_accuracy": 0.1638791508972645,
|
|
"num_tokens": 8572521.0,
|
|
"step": 3835
|
|
},
|
|
{
|
|
"entropy": 5.8166440486907955,
|
|
"epoch": 0.4312910653113944,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004988461480032408,
|
|
"loss": 5.7083,
|
|
"mean_token_accuracy": 0.1705876812338829,
|
|
"num_tokens": 8583977.0,
|
|
"step": 3840
|
|
},
|
|
{
|
|
"entropy": 5.676244163513184,
|
|
"epoch": 0.43185264221935193,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004988420836266946,
|
|
"loss": 5.6631,
|
|
"mean_token_accuracy": 0.16948182731866837,
|
|
"num_tokens": 8594441.0,
|
|
"step": 3845
|
|
},
|
|
{
|
|
"entropy": 5.81585054397583,
|
|
"epoch": 0.4324142191273095,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004988380121229298,
|
|
"loss": 5.7011,
|
|
"mean_token_accuracy": 0.1648661583662033,
|
|
"num_tokens": 8604843.0,
|
|
"step": 3850
|
|
},
|
|
{
|
|
"entropy": 5.7531821727752686,
|
|
"epoch": 0.43297579603526704,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004988339334920757,
|
|
"loss": 5.7079,
|
|
"mean_token_accuracy": 0.165433070063591,
|
|
"num_tokens": 8616059.0,
|
|
"step": 3855
|
|
},
|
|
{
|
|
"entropy": 5.6965405464172365,
|
|
"epoch": 0.4335373729432246,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004988298477342625,
|
|
"loss": 5.6474,
|
|
"mean_token_accuracy": 0.17442899346351623,
|
|
"num_tokens": 8626203.0,
|
|
"step": 3860
|
|
},
|
|
{
|
|
"entropy": 5.664996099472046,
|
|
"epoch": 0.43409894985118214,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00049882575484962,
|
|
"loss": 5.6561,
|
|
"mean_token_accuracy": 0.16710033118724824,
|
|
"num_tokens": 8636921.0,
|
|
"step": 3865
|
|
},
|
|
{
|
|
"entropy": 5.586138296127319,
|
|
"epoch": 0.4346605267591397,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004988216548382787,
|
|
"loss": 5.6233,
|
|
"mean_token_accuracy": 0.17516982704401016,
|
|
"num_tokens": 8648526.0,
|
|
"step": 3870
|
|
},
|
|
{
|
|
"entropy": 5.766515398025513,
|
|
"epoch": 0.4352221036670972,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004988175477003691,
|
|
"loss": 5.761,
|
|
"mean_token_accuracy": 0.15909429639577866,
|
|
"num_tokens": 8660339.0,
|
|
"step": 3875
|
|
},
|
|
{
|
|
"entropy": 5.930771207809448,
|
|
"epoch": 0.43578368057505473,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000498813433436022,
|
|
"loss": 5.831,
|
|
"mean_token_accuracy": 0.1586817055940628,
|
|
"num_tokens": 8671835.0,
|
|
"step": 3880
|
|
},
|
|
{
|
|
"entropy": 5.657417297363281,
|
|
"epoch": 0.4363452574830123,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004988093120453684,
|
|
"loss": 5.5231,
|
|
"mean_token_accuracy": 0.17392702847719194,
|
|
"num_tokens": 8681146.0,
|
|
"step": 3885
|
|
},
|
|
{
|
|
"entropy": 5.591185855865478,
|
|
"epoch": 0.43690683439096983,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004988051835285394,
|
|
"loss": 5.5869,
|
|
"mean_token_accuracy": 0.17523194551467897,
|
|
"num_tokens": 8691623.0,
|
|
"step": 3890
|
|
},
|
|
{
|
|
"entropy": 5.744294738769531,
|
|
"epoch": 0.4374684112989274,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004988010478856667,
|
|
"loss": 5.6812,
|
|
"mean_token_accuracy": 0.16285532414913179,
|
|
"num_tokens": 8703702.0,
|
|
"step": 3895
|
|
},
|
|
{
|
|
"entropy": 5.907511281967163,
|
|
"epoch": 0.43802998820688493,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004987969051168816,
|
|
"loss": 5.856,
|
|
"mean_token_accuracy": 0.16955171376466752,
|
|
"num_tokens": 8715434.0,
|
|
"step": 3900
|
|
},
|
|
{
|
|
"entropy": 5.651218271255493,
|
|
"epoch": 0.4385915651148425,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004987927552223165,
|
|
"loss": 5.6291,
|
|
"mean_token_accuracy": 0.17835401892662048,
|
|
"num_tokens": 8726135.0,
|
|
"step": 3905
|
|
},
|
|
{
|
|
"entropy": 5.591823434829712,
|
|
"epoch": 0.43915314202280004,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004987885982021032,
|
|
"loss": 5.7447,
|
|
"mean_token_accuracy": 0.165838785469532,
|
|
"num_tokens": 8736538.0,
|
|
"step": 3910
|
|
},
|
|
{
|
|
"entropy": 5.785422945022583,
|
|
"epoch": 0.4397147189307576,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004987844340563741,
|
|
"loss": 5.6393,
|
|
"mean_token_accuracy": 0.18060767352581025,
|
|
"num_tokens": 8746456.0,
|
|
"step": 3915
|
|
},
|
|
{
|
|
"entropy": 5.717219448089599,
|
|
"epoch": 0.44027629583871514,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004987802627852619,
|
|
"loss": 5.7718,
|
|
"mean_token_accuracy": 0.17131387591362,
|
|
"num_tokens": 8757143.0,
|
|
"step": 3920
|
|
},
|
|
{
|
|
"entropy": 5.758051156997681,
|
|
"epoch": 0.44083787274667263,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004987760843888992,
|
|
"loss": 5.7367,
|
|
"mean_token_accuracy": 0.1723605528473854,
|
|
"num_tokens": 8769084.0,
|
|
"step": 3925
|
|
},
|
|
{
|
|
"entropy": 5.711410713195801,
|
|
"epoch": 0.4413994496546302,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004987718988674193,
|
|
"loss": 5.7422,
|
|
"mean_token_accuracy": 0.16336573362350465,
|
|
"num_tokens": 8780707.0,
|
|
"step": 3930
|
|
},
|
|
{
|
|
"entropy": 5.729125833511352,
|
|
"epoch": 0.44196102656258773,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004987677062209552,
|
|
"loss": 5.7204,
|
|
"mean_token_accuracy": 0.16337183564901353,
|
|
"num_tokens": 8792157.0,
|
|
"step": 3935
|
|
},
|
|
{
|
|
"entropy": 5.8027397155761715,
|
|
"epoch": 0.4425226034705453,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004987635064496407,
|
|
"loss": 5.7221,
|
|
"mean_token_accuracy": 0.1694505989551544,
|
|
"num_tokens": 8802691.0,
|
|
"step": 3940
|
|
},
|
|
{
|
|
"entropy": 5.763846731185913,
|
|
"epoch": 0.44308418037850283,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004987592995536093,
|
|
"loss": 5.7259,
|
|
"mean_token_accuracy": 0.16735922396183014,
|
|
"num_tokens": 8814869.0,
|
|
"step": 3945
|
|
},
|
|
{
|
|
"entropy": 5.680597734451294,
|
|
"epoch": 0.4436457572864604,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004987550855329951,
|
|
"loss": 5.6768,
|
|
"mean_token_accuracy": 0.1748446121811867,
|
|
"num_tokens": 8825264.0,
|
|
"step": 3950
|
|
},
|
|
{
|
|
"entropy": 5.769941759109497,
|
|
"epoch": 0.44420733419441794,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004987508643879322,
|
|
"loss": 5.753,
|
|
"mean_token_accuracy": 0.16739851534366607,
|
|
"num_tokens": 8837128.0,
|
|
"step": 3955
|
|
},
|
|
{
|
|
"entropy": 5.7737284183502195,
|
|
"epoch": 0.4447689111023755,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004987466361185549,
|
|
"loss": 5.7603,
|
|
"mean_token_accuracy": 0.1679315373301506,
|
|
"num_tokens": 8848587.0,
|
|
"step": 3960
|
|
},
|
|
{
|
|
"entropy": 5.812390375137329,
|
|
"epoch": 0.44533048801033304,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004987424007249979,
|
|
"loss": 5.8151,
|
|
"mean_token_accuracy": 0.15971253663301468,
|
|
"num_tokens": 8859219.0,
|
|
"step": 3965
|
|
},
|
|
{
|
|
"entropy": 5.727692079544068,
|
|
"epoch": 0.4458920649182906,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004987381582073962,
|
|
"loss": 5.6971,
|
|
"mean_token_accuracy": 0.17240041941404344,
|
|
"num_tokens": 8868780.0,
|
|
"step": 3970
|
|
},
|
|
{
|
|
"entropy": 5.791679239273071,
|
|
"epoch": 0.4464536418262481,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004987339085658848,
|
|
"loss": 5.6899,
|
|
"mean_token_accuracy": 0.16668667495250702,
|
|
"num_tokens": 8880903.0,
|
|
"step": 3975
|
|
},
|
|
{
|
|
"entropy": 5.649108505249023,
|
|
"epoch": 0.44701521873420563,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004987296518005988,
|
|
"loss": 5.5393,
|
|
"mean_token_accuracy": 0.17514702826738357,
|
|
"num_tokens": 8890335.0,
|
|
"step": 3980
|
|
},
|
|
{
|
|
"entropy": 5.624079895019531,
|
|
"epoch": 0.4475767956421632,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000498725387911674,
|
|
"loss": 5.6665,
|
|
"mean_token_accuracy": 0.1657211109995842,
|
|
"num_tokens": 8904104.0,
|
|
"step": 3985
|
|
},
|
|
{
|
|
"entropy": 5.848477840423584,
|
|
"epoch": 0.44813837255012073,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004987211168992461,
|
|
"loss": 5.7579,
|
|
"mean_token_accuracy": 0.16290821582078935,
|
|
"num_tokens": 8915118.0,
|
|
"step": 3990
|
|
},
|
|
{
|
|
"entropy": 5.786362743377685,
|
|
"epoch": 0.4486999494580783,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000498716838763451,
|
|
"loss": 5.7224,
|
|
"mean_token_accuracy": 0.16304679960012436,
|
|
"num_tokens": 8927450.0,
|
|
"step": 3995
|
|
},
|
|
{
|
|
"entropy": 5.777005243301391,
|
|
"epoch": 0.44926152636603583,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000498712553504425,
|
|
"loss": 5.8174,
|
|
"mean_token_accuracy": 0.16654790043830872,
|
|
"num_tokens": 8939902.0,
|
|
"step": 4000
|
|
},
|
|
{
|
|
"entropy": 5.749442529678345,
|
|
"epoch": 0.4498231032739934,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004987082611223046,
|
|
"loss": 5.6648,
|
|
"mean_token_accuracy": 0.16342007368803024,
|
|
"num_tokens": 8951736.0,
|
|
"step": 4005
|
|
},
|
|
{
|
|
"entropy": 5.79229736328125,
|
|
"epoch": 0.45038468018195094,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004987039616172265,
|
|
"loss": 5.7553,
|
|
"mean_token_accuracy": 0.16775904297828675,
|
|
"num_tokens": 8963283.0,
|
|
"step": 4010
|
|
},
|
|
{
|
|
"entropy": 5.679261112213135,
|
|
"epoch": 0.4509462570899085,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004986996549893273,
|
|
"loss": 5.6551,
|
|
"mean_token_accuracy": 0.17308196276426316,
|
|
"num_tokens": 8974323.0,
|
|
"step": 4015
|
|
},
|
|
{
|
|
"entropy": 5.739497232437134,
|
|
"epoch": 0.451507833997866,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004986953412387445,
|
|
"loss": 5.737,
|
|
"mean_token_accuracy": 0.1673332244157791,
|
|
"num_tokens": 8986687.0,
|
|
"step": 4020
|
|
},
|
|
{
|
|
"entropy": 5.712039232254028,
|
|
"epoch": 0.45206941090582353,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004986910203656151,
|
|
"loss": 5.6278,
|
|
"mean_token_accuracy": 0.17758648693561555,
|
|
"num_tokens": 8997734.0,
|
|
"step": 4025
|
|
},
|
|
{
|
|
"entropy": 5.682044124603271,
|
|
"epoch": 0.4526309878137811,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004986866923700769,
|
|
"loss": 5.7475,
|
|
"mean_token_accuracy": 0.16049894392490388,
|
|
"num_tokens": 9008743.0,
|
|
"step": 4030
|
|
},
|
|
{
|
|
"entropy": 5.782350063323975,
|
|
"epoch": 0.45319256472173863,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004986823572522677,
|
|
"loss": 5.6252,
|
|
"mean_token_accuracy": 0.17187685519456863,
|
|
"num_tokens": 9019495.0,
|
|
"step": 4035
|
|
},
|
|
{
|
|
"entropy": 5.733756399154663,
|
|
"epoch": 0.4537541416296962,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004986780150123254,
|
|
"loss": 5.7322,
|
|
"mean_token_accuracy": 0.16945061981678008,
|
|
"num_tokens": 9029546.0,
|
|
"step": 4040
|
|
},
|
|
{
|
|
"entropy": 5.579219961166382,
|
|
"epoch": 0.45431571853765373,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004986736656503885,
|
|
"loss": 5.4897,
|
|
"mean_token_accuracy": 0.17369079887866973,
|
|
"num_tokens": 9040393.0,
|
|
"step": 4045
|
|
},
|
|
{
|
|
"entropy": 5.6706140518188475,
|
|
"epoch": 0.4548772954456113,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004986693091665952,
|
|
"loss": 5.701,
|
|
"mean_token_accuracy": 0.16996229141950608,
|
|
"num_tokens": 9050840.0,
|
|
"step": 4050
|
|
},
|
|
{
|
|
"entropy": 5.732314014434815,
|
|
"epoch": 0.45543887235356884,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004986649455610845,
|
|
"loss": 5.6243,
|
|
"mean_token_accuracy": 0.17240490168333053,
|
|
"num_tokens": 9061615.0,
|
|
"step": 4055
|
|
},
|
|
{
|
|
"entropy": 5.684764099121094,
|
|
"epoch": 0.4560004492615264,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.000498660574833995,
|
|
"loss": 5.5871,
|
|
"mean_token_accuracy": 0.17155140936374663,
|
|
"num_tokens": 9071902.0,
|
|
"step": 4060
|
|
},
|
|
{
|
|
"entropy": 5.666956281661987,
|
|
"epoch": 0.45656202616948394,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004986561969854661,
|
|
"loss": 5.7637,
|
|
"mean_token_accuracy": 0.1654072195291519,
|
|
"num_tokens": 9083613.0,
|
|
"step": 4065
|
|
},
|
|
{
|
|
"entropy": 5.69202036857605,
|
|
"epoch": 0.45712360307744143,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004986518120156373,
|
|
"loss": 5.6514,
|
|
"mean_token_accuracy": 0.16597033590078353,
|
|
"num_tokens": 9095678.0,
|
|
"step": 4070
|
|
},
|
|
{
|
|
"entropy": 5.74427604675293,
|
|
"epoch": 0.457685179985399,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000498647419924648,
|
|
"loss": 5.6637,
|
|
"mean_token_accuracy": 0.1713939815759659,
|
|
"num_tokens": 9106637.0,
|
|
"step": 4075
|
|
},
|
|
{
|
|
"entropy": 5.585138130187988,
|
|
"epoch": 0.45824675689335653,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000498643020712638,
|
|
"loss": 5.6161,
|
|
"mean_token_accuracy": 0.17725679874420167,
|
|
"num_tokens": 9117343.0,
|
|
"step": 4080
|
|
},
|
|
{
|
|
"entropy": 5.77268385887146,
|
|
"epoch": 0.4588083338013141,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004986386143797475,
|
|
"loss": 5.7538,
|
|
"mean_token_accuracy": 0.16286227554082872,
|
|
"num_tokens": 9129315.0,
|
|
"step": 4085
|
|
},
|
|
{
|
|
"entropy": 5.703229570388794,
|
|
"epoch": 0.45936991070927163,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004986342009261169,
|
|
"loss": 5.6384,
|
|
"mean_token_accuracy": 0.1681533232331276,
|
|
"num_tokens": 9139701.0,
|
|
"step": 4090
|
|
},
|
|
{
|
|
"entropy": 5.753712129592896,
|
|
"epoch": 0.4599314876172292,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004986297803518865,
|
|
"loss": 5.7745,
|
|
"mean_token_accuracy": 0.16588501930236815,
|
|
"num_tokens": 9152334.0,
|
|
"step": 4095
|
|
},
|
|
{
|
|
"entropy": 5.758871126174927,
|
|
"epoch": 0.46049306452518673,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004986253526571971,
|
|
"loss": 5.5925,
|
|
"mean_token_accuracy": 0.17100529074668885,
|
|
"num_tokens": 9163277.0,
|
|
"step": 4100
|
|
},
|
|
{
|
|
"entropy": 5.745195817947388,
|
|
"epoch": 0.4610546414331443,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004986209178421899,
|
|
"loss": 5.7742,
|
|
"mean_token_accuracy": 0.16090487837791442,
|
|
"num_tokens": 9174909.0,
|
|
"step": 4105
|
|
},
|
|
{
|
|
"entropy": 5.631056690216065,
|
|
"epoch": 0.46161621834110184,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000498616475907006,
|
|
"loss": 5.5651,
|
|
"mean_token_accuracy": 0.16614989340305328,
|
|
"num_tokens": 9186058.0,
|
|
"step": 4110
|
|
},
|
|
{
|
|
"entropy": 5.661126184463501,
|
|
"epoch": 0.46217779524905933,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004986120268517865,
|
|
"loss": 5.726,
|
|
"mean_token_accuracy": 0.1702674373984337,
|
|
"num_tokens": 9196919.0,
|
|
"step": 4115
|
|
},
|
|
{
|
|
"entropy": 5.7698023319244385,
|
|
"epoch": 0.4627393721570169,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004986075706766736,
|
|
"loss": 5.7029,
|
|
"mean_token_accuracy": 0.16950358003377913,
|
|
"num_tokens": 9208452.0,
|
|
"step": 4120
|
|
},
|
|
{
|
|
"entropy": 5.759048509597778,
|
|
"epoch": 0.46330094906497443,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004986031073818088,
|
|
"loss": 5.7702,
|
|
"mean_token_accuracy": 0.1635267660021782,
|
|
"num_tokens": 9219605.0,
|
|
"step": 4125
|
|
},
|
|
{
|
|
"entropy": 5.737527894973755,
|
|
"epoch": 0.463862525972932,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004985986369673343,
|
|
"loss": 5.5885,
|
|
"mean_token_accuracy": 0.1740850031375885,
|
|
"num_tokens": 9230491.0,
|
|
"step": 4130
|
|
},
|
|
{
|
|
"entropy": 5.708728551864624,
|
|
"epoch": 0.46442410288088953,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004985941594333926,
|
|
"loss": 5.7342,
|
|
"mean_token_accuracy": 0.16121432185173035,
|
|
"num_tokens": 9241768.0,
|
|
"step": 4135
|
|
},
|
|
{
|
|
"entropy": 5.751010942459106,
|
|
"epoch": 0.4649856797888471,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.000498589674780126,
|
|
"loss": 5.7415,
|
|
"mean_token_accuracy": 0.16545218527317046,
|
|
"num_tokens": 9253779.0,
|
|
"step": 4140
|
|
},
|
|
{
|
|
"entropy": 5.8127830028533936,
|
|
"epoch": 0.46554725669680463,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004985851830076775,
|
|
"loss": 5.6421,
|
|
"mean_token_accuracy": 0.18010046929121018,
|
|
"num_tokens": 9264567.0,
|
|
"step": 4145
|
|
},
|
|
{
|
|
"entropy": 5.5897307872772215,
|
|
"epoch": 0.4661088336047622,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004985806841161901,
|
|
"loss": 5.6178,
|
|
"mean_token_accuracy": 0.1743156135082245,
|
|
"num_tokens": 9275960.0,
|
|
"step": 4150
|
|
},
|
|
{
|
|
"entropy": 5.756761169433593,
|
|
"epoch": 0.46667041051271974,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.000498576178105807,
|
|
"loss": 5.7571,
|
|
"mean_token_accuracy": 0.17624003142118455,
|
|
"num_tokens": 9288305.0,
|
|
"step": 4155
|
|
},
|
|
{
|
|
"entropy": 5.746865701675415,
|
|
"epoch": 0.4672319874206773,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004985716649766717,
|
|
"loss": 5.5756,
|
|
"mean_token_accuracy": 0.17748844623565674,
|
|
"num_tokens": 9299579.0,
|
|
"step": 4160
|
|
},
|
|
{
|
|
"entropy": 5.603367328643799,
|
|
"epoch": 0.4677935643286348,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004985671447289277,
|
|
"loss": 5.62,
|
|
"mean_token_accuracy": 0.1722979098558426,
|
|
"num_tokens": 9311221.0,
|
|
"step": 4165
|
|
},
|
|
{
|
|
"entropy": 5.70216932296753,
|
|
"epoch": 0.46835514123659233,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004985626173627194,
|
|
"loss": 5.7166,
|
|
"mean_token_accuracy": 0.16188061684370042,
|
|
"num_tokens": 9322488.0,
|
|
"step": 4170
|
|
},
|
|
{
|
|
"entropy": 5.706109285354614,
|
|
"epoch": 0.4689167181445499,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004985580828781904,
|
|
"loss": 5.6632,
|
|
"mean_token_accuracy": 0.168344084918499,
|
|
"num_tokens": 9333672.0,
|
|
"step": 4175
|
|
},
|
|
{
|
|
"entropy": 5.821729946136474,
|
|
"epoch": 0.46947829505250743,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004985535412754855,
|
|
"loss": 5.7122,
|
|
"mean_token_accuracy": 0.1685151770710945,
|
|
"num_tokens": 9344449.0,
|
|
"step": 4180
|
|
},
|
|
{
|
|
"entropy": 5.793760919570923,
|
|
"epoch": 0.470039871960465,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000498548992554749,
|
|
"loss": 5.7711,
|
|
"mean_token_accuracy": 0.16195064634084702,
|
|
"num_tokens": 9355279.0,
|
|
"step": 4185
|
|
},
|
|
{
|
|
"entropy": 5.722224378585816,
|
|
"epoch": 0.47060144886842253,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004985444367161259,
|
|
"loss": 5.6877,
|
|
"mean_token_accuracy": 0.1694555401802063,
|
|
"num_tokens": 9366942.0,
|
|
"step": 4190
|
|
},
|
|
{
|
|
"entropy": 5.643642234802246,
|
|
"epoch": 0.4711630257763801,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004985398737597614,
|
|
"loss": 5.6033,
|
|
"mean_token_accuracy": 0.1772357314825058,
|
|
"num_tokens": 9378129.0,
|
|
"step": 4195
|
|
},
|
|
{
|
|
"entropy": 5.739987754821778,
|
|
"epoch": 0.47172460268433763,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004985353036858004,
|
|
"loss": 5.6938,
|
|
"mean_token_accuracy": 0.1689502105116844,
|
|
"num_tokens": 9388757.0,
|
|
"step": 4200
|
|
},
|
|
{
|
|
"entropy": 5.720378780364991,
|
|
"epoch": 0.4722861795922952,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004985307264943887,
|
|
"loss": 5.633,
|
|
"mean_token_accuracy": 0.16822650730609895,
|
|
"num_tokens": 9399112.0,
|
|
"step": 4205
|
|
},
|
|
{
|
|
"entropy": 5.736804008483887,
|
|
"epoch": 0.47284775650025274,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004985261421856721,
|
|
"loss": 5.7386,
|
|
"mean_token_accuracy": 0.17064763754606246,
|
|
"num_tokens": 9410156.0,
|
|
"step": 4210
|
|
},
|
|
{
|
|
"entropy": 5.791450309753418,
|
|
"epoch": 0.47340933340821023,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004985215507597963,
|
|
"loss": 5.7085,
|
|
"mean_token_accuracy": 0.17250441908836364,
|
|
"num_tokens": 9420402.0,
|
|
"step": 4215
|
|
},
|
|
{
|
|
"entropy": 5.74765305519104,
|
|
"epoch": 0.4739709103161678,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004985169522169076,
|
|
"loss": 5.728,
|
|
"mean_token_accuracy": 0.1658301383256912,
|
|
"num_tokens": 9431159.0,
|
|
"step": 4220
|
|
},
|
|
{
|
|
"entropy": 5.646982717514038,
|
|
"epoch": 0.47453248722412533,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004985123465571526,
|
|
"loss": 5.6258,
|
|
"mean_token_accuracy": 0.17545929700136184,
|
|
"num_tokens": 9441737.0,
|
|
"step": 4225
|
|
},
|
|
{
|
|
"entropy": 5.675642204284668,
|
|
"epoch": 0.4750940641320829,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004985077337806777,
|
|
"loss": 5.5844,
|
|
"mean_token_accuracy": 0.1804198741912842,
|
|
"num_tokens": 9452756.0,
|
|
"step": 4230
|
|
},
|
|
{
|
|
"entropy": 5.6871847152709964,
|
|
"epoch": 0.47565564104004043,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004985031138876299,
|
|
"loss": 5.6585,
|
|
"mean_token_accuracy": 0.16903969794511794,
|
|
"num_tokens": 9464231.0,
|
|
"step": 4235
|
|
},
|
|
{
|
|
"entropy": 5.761657667160034,
|
|
"epoch": 0.476217217947998,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004984984868781563,
|
|
"loss": 5.6924,
|
|
"mean_token_accuracy": 0.1775568440556526,
|
|
"num_tokens": 9475648.0,
|
|
"step": 4240
|
|
},
|
|
{
|
|
"entropy": 5.722880506515503,
|
|
"epoch": 0.47677879485595553,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004984938527524041,
|
|
"loss": 5.7179,
|
|
"mean_token_accuracy": 0.1703099086880684,
|
|
"num_tokens": 9486594.0,
|
|
"step": 4245
|
|
},
|
|
{
|
|
"entropy": 5.6348882675170895,
|
|
"epoch": 0.4773403717639131,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000498489211510521,
|
|
"loss": 5.6212,
|
|
"mean_token_accuracy": 0.17380516678094865,
|
|
"num_tokens": 9497085.0,
|
|
"step": 4250
|
|
},
|
|
{
|
|
"entropy": 5.788146924972534,
|
|
"epoch": 0.47790194867187064,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004984845631526547,
|
|
"loss": 5.7141,
|
|
"mean_token_accuracy": 0.1695077672600746,
|
|
"num_tokens": 9509765.0,
|
|
"step": 4255
|
|
},
|
|
{
|
|
"entropy": 5.657717037200928,
|
|
"epoch": 0.47846352557982813,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004984799076789534,
|
|
"loss": 5.5242,
|
|
"mean_token_accuracy": 0.1715771660208702,
|
|
"num_tokens": 9521341.0,
|
|
"step": 4260
|
|
},
|
|
{
|
|
"entropy": 5.610888338088989,
|
|
"epoch": 0.4790251024877857,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004984752450895649,
|
|
"loss": 5.6587,
|
|
"mean_token_accuracy": 0.16588249504566194,
|
|
"num_tokens": 9533196.0,
|
|
"step": 4265
|
|
},
|
|
{
|
|
"entropy": 5.784460639953613,
|
|
"epoch": 0.47958667939574323,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000498470575384638,
|
|
"loss": 5.7994,
|
|
"mean_token_accuracy": 0.16206895112991332,
|
|
"num_tokens": 9543687.0,
|
|
"step": 4270
|
|
},
|
|
{
|
|
"entropy": 5.819685459136963,
|
|
"epoch": 0.4801482563037008,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004984658985643214,
|
|
"loss": 5.6756,
|
|
"mean_token_accuracy": 0.16454316526651383,
|
|
"num_tokens": 9555320.0,
|
|
"step": 4275
|
|
},
|
|
{
|
|
"entropy": 5.674014759063721,
|
|
"epoch": 0.48070983321165833,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004984612146287638,
|
|
"loss": 5.6227,
|
|
"mean_token_accuracy": 0.17176014930009842,
|
|
"num_tokens": 9566347.0,
|
|
"step": 4280
|
|
},
|
|
{
|
|
"entropy": 5.627931928634643,
|
|
"epoch": 0.4812714101196159,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004984565235781147,
|
|
"loss": 5.6381,
|
|
"mean_token_accuracy": 0.16882239282131195,
|
|
"num_tokens": 9577111.0,
|
|
"step": 4285
|
|
},
|
|
{
|
|
"entropy": 5.704267787933349,
|
|
"epoch": 0.48183298702757343,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000498451825412523,
|
|
"loss": 5.6408,
|
|
"mean_token_accuracy": 0.16688065081834794,
|
|
"num_tokens": 9586612.0,
|
|
"step": 4290
|
|
},
|
|
{
|
|
"entropy": 5.721601247787476,
|
|
"epoch": 0.482394563935531,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004984471201321386,
|
|
"loss": 5.6637,
|
|
"mean_token_accuracy": 0.17094948291778564,
|
|
"num_tokens": 9597347.0,
|
|
"step": 4295
|
|
},
|
|
{
|
|
"entropy": 5.640413522720337,
|
|
"epoch": 0.48295614084348854,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004984424077371112,
|
|
"loss": 5.6209,
|
|
"mean_token_accuracy": 0.17714740931987763,
|
|
"num_tokens": 9608507.0,
|
|
"step": 4300
|
|
},
|
|
{
|
|
"entropy": 5.665226554870605,
|
|
"epoch": 0.4835177177514461,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004984376882275909,
|
|
"loss": 5.6765,
|
|
"mean_token_accuracy": 0.17560769915580748,
|
|
"num_tokens": 9619449.0,
|
|
"step": 4305
|
|
},
|
|
{
|
|
"entropy": 5.638707685470581,
|
|
"epoch": 0.4840792946594036,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004984329616037279,
|
|
"loss": 5.61,
|
|
"mean_token_accuracy": 0.17127044796943663,
|
|
"num_tokens": 9630613.0,
|
|
"step": 4310
|
|
},
|
|
{
|
|
"entropy": 5.747069358825684,
|
|
"epoch": 0.48464087156736113,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004984282278656727,
|
|
"loss": 5.6949,
|
|
"mean_token_accuracy": 0.16782187074422836,
|
|
"num_tokens": 9642149.0,
|
|
"step": 4315
|
|
},
|
|
{
|
|
"entropy": 5.731757974624633,
|
|
"epoch": 0.4852024484753187,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004984234870135762,
|
|
"loss": 5.6162,
|
|
"mean_token_accuracy": 0.17159442603588104,
|
|
"num_tokens": 9652960.0,
|
|
"step": 4320
|
|
},
|
|
{
|
|
"entropy": 5.633257913589477,
|
|
"epoch": 0.48576402538327623,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004984187390475891,
|
|
"loss": 5.6183,
|
|
"mean_token_accuracy": 0.17428087145090104,
|
|
"num_tokens": 9662676.0,
|
|
"step": 4325
|
|
},
|
|
{
|
|
"entropy": 5.80910964012146,
|
|
"epoch": 0.4863256022912338,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004984139839678628,
|
|
"loss": 5.729,
|
|
"mean_token_accuracy": 0.1634234681725502,
|
|
"num_tokens": 9674138.0,
|
|
"step": 4330
|
|
},
|
|
{
|
|
"entropy": 5.708944082260132,
|
|
"epoch": 0.48688717919919133,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004984092217745486,
|
|
"loss": 5.6848,
|
|
"mean_token_accuracy": 0.1723746046423912,
|
|
"num_tokens": 9685397.0,
|
|
"step": 4335
|
|
},
|
|
{
|
|
"entropy": 5.719421005249023,
|
|
"epoch": 0.4874487561071489,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004984044524677981,
|
|
"loss": 5.799,
|
|
"mean_token_accuracy": 0.15916237533092498,
|
|
"num_tokens": 9697266.0,
|
|
"step": 4340
|
|
},
|
|
{
|
|
"entropy": 5.8168723583221436,
|
|
"epoch": 0.48801033301510643,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004983996760477632,
|
|
"loss": 5.6213,
|
|
"mean_token_accuracy": 0.1681630089879036,
|
|
"num_tokens": 9707967.0,
|
|
"step": 4345
|
|
},
|
|
{
|
|
"entropy": 5.569722032546997,
|
|
"epoch": 0.488571909923064,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000498394892514596,
|
|
"loss": 5.6051,
|
|
"mean_token_accuracy": 0.17206544578075408,
|
|
"num_tokens": 9718162.0,
|
|
"step": 4350
|
|
},
|
|
{
|
|
"entropy": 5.7391273021698,
|
|
"epoch": 0.48913348683102154,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004983901018684486,
|
|
"loss": 5.6457,
|
|
"mean_token_accuracy": 0.16926445066928864,
|
|
"num_tokens": 9729439.0,
|
|
"step": 4355
|
|
},
|
|
{
|
|
"entropy": 5.718689966201782,
|
|
"epoch": 0.48969506373897903,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004983853041094739,
|
|
"loss": 5.6759,
|
|
"mean_token_accuracy": 0.17224766165018082,
|
|
"num_tokens": 9741383.0,
|
|
"step": 4360
|
|
},
|
|
{
|
|
"entropy": 5.671913051605225,
|
|
"epoch": 0.4902566406469366,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004983804992378243,
|
|
"loss": 5.7076,
|
|
"mean_token_accuracy": 0.17305777966976166,
|
|
"num_tokens": 9753050.0,
|
|
"step": 4365
|
|
},
|
|
{
|
|
"entropy": 5.626379585266113,
|
|
"epoch": 0.49081821755489413,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004983756872536532,
|
|
"loss": 5.5757,
|
|
"mean_token_accuracy": 0.17507124394178392,
|
|
"num_tokens": 9763715.0,
|
|
"step": 4370
|
|
},
|
|
{
|
|
"entropy": 5.69524884223938,
|
|
"epoch": 0.4913797944628517,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004983708681571134,
|
|
"loss": 5.5449,
|
|
"mean_token_accuracy": 0.182700777053833,
|
|
"num_tokens": 9774145.0,
|
|
"step": 4375
|
|
},
|
|
{
|
|
"entropy": 5.648786020278931,
|
|
"epoch": 0.49194137137080923,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004983660419483586,
|
|
"loss": 5.614,
|
|
"mean_token_accuracy": 0.17637461721897124,
|
|
"num_tokens": 9784703.0,
|
|
"step": 4380
|
|
},
|
|
{
|
|
"entropy": 5.677385234832764,
|
|
"epoch": 0.4925029482787668,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004983612086275424,
|
|
"loss": 5.6336,
|
|
"mean_token_accuracy": 0.16861145943403244,
|
|
"num_tokens": 9795426.0,
|
|
"step": 4385
|
|
},
|
|
{
|
|
"entropy": 5.697136497497558,
|
|
"epoch": 0.49306452518672433,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004983563681948187,
|
|
"loss": 5.7185,
|
|
"mean_token_accuracy": 0.16922592371702194,
|
|
"num_tokens": 9806539.0,
|
|
"step": 4390
|
|
},
|
|
{
|
|
"entropy": 5.79005708694458,
|
|
"epoch": 0.4936261020946819,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004983515206503416,
|
|
"loss": 5.6962,
|
|
"mean_token_accuracy": 0.16803440004587172,
|
|
"num_tokens": 9816806.0,
|
|
"step": 4395
|
|
},
|
|
{
|
|
"entropy": 5.686528062820434,
|
|
"epoch": 0.49418767900263944,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004983466659942655,
|
|
"loss": 5.6066,
|
|
"mean_token_accuracy": 0.1756485402584076,
|
|
"num_tokens": 9828001.0,
|
|
"step": 4400
|
|
},
|
|
{
|
|
"entropy": 5.5848475933074955,
|
|
"epoch": 0.49474925591059693,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004983418042267449,
|
|
"loss": 5.6396,
|
|
"mean_token_accuracy": 0.17311501652002334,
|
|
"num_tokens": 9838773.0,
|
|
"step": 4405
|
|
},
|
|
{
|
|
"entropy": 5.700955247879028,
|
|
"epoch": 0.4953108328185545,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004983369353479345,
|
|
"loss": 5.6322,
|
|
"mean_token_accuracy": 0.17581406533718108,
|
|
"num_tokens": 9848680.0,
|
|
"step": 4410
|
|
},
|
|
{
|
|
"entropy": 5.6178875923156735,
|
|
"epoch": 0.49587240972651203,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004983320593579895,
|
|
"loss": 5.6067,
|
|
"mean_token_accuracy": 0.16638704091310502,
|
|
"num_tokens": 9859168.0,
|
|
"step": 4415
|
|
},
|
|
{
|
|
"entropy": 5.607037162780761,
|
|
"epoch": 0.4964339866344696,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004983271762570653,
|
|
"loss": 5.6387,
|
|
"mean_token_accuracy": 0.1737781807780266,
|
|
"num_tokens": 9869071.0,
|
|
"step": 4420
|
|
},
|
|
{
|
|
"entropy": 5.730302572250366,
|
|
"epoch": 0.49699556354242713,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000498322286045317,
|
|
"loss": 5.6462,
|
|
"mean_token_accuracy": 0.17305319458246232,
|
|
"num_tokens": 9880208.0,
|
|
"step": 4425
|
|
},
|
|
{
|
|
"entropy": 5.744824552536011,
|
|
"epoch": 0.4975571404503847,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004983173887229006,
|
|
"loss": 5.6813,
|
|
"mean_token_accuracy": 0.16881180852651595,
|
|
"num_tokens": 9891192.0,
|
|
"step": 4430
|
|
},
|
|
{
|
|
"entropy": 5.7692972183227536,
|
|
"epoch": 0.49811871735834223,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004983124842899719,
|
|
"loss": 5.7041,
|
|
"mean_token_accuracy": 0.16658677607774736,
|
|
"num_tokens": 9903038.0,
|
|
"step": 4435
|
|
},
|
|
{
|
|
"entropy": 5.781491041183472,
|
|
"epoch": 0.4986802942662998,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004983075727466871,
|
|
"loss": 5.7453,
|
|
"mean_token_accuracy": 0.16752920895814896,
|
|
"num_tokens": 9916104.0,
|
|
"step": 4440
|
|
},
|
|
{
|
|
"entropy": 5.643881177902221,
|
|
"epoch": 0.49924187117425733,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004983026540932026,
|
|
"loss": 5.5871,
|
|
"mean_token_accuracy": 0.17617910206317902,
|
|
"num_tokens": 9927094.0,
|
|
"step": 4445
|
|
},
|
|
{
|
|
"entropy": 5.77818808555603,
|
|
"epoch": 0.4998034480822149,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004982977283296749,
|
|
"loss": 5.7878,
|
|
"mean_token_accuracy": 0.16070730984210968,
|
|
"num_tokens": 9937964.0,
|
|
"step": 4450
|
|
},
|
|
{
|
|
"entropy": 5.802535629272461,
|
|
"epoch": 0.5003650249901724,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000498292795456261,
|
|
"loss": 5.7481,
|
|
"mean_token_accuracy": 0.16224943697452546,
|
|
"num_tokens": 9949238.0,
|
|
"step": 4455
|
|
},
|
|
{
|
|
"entropy": 5.7079521179199215,
|
|
"epoch": 0.50092660189813,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004982878554731178,
|
|
"loss": 5.5858,
|
|
"mean_token_accuracy": 0.17275109589099885,
|
|
"num_tokens": 9960125.0,
|
|
"step": 4460
|
|
},
|
|
{
|
|
"entropy": 5.567731332778931,
|
|
"epoch": 0.5014881788060875,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004982829083804028,
|
|
"loss": 5.6065,
|
|
"mean_token_accuracy": 0.16887205690145493,
|
|
"num_tokens": 9971130.0,
|
|
"step": 4465
|
|
},
|
|
{
|
|
"entropy": 5.6556477546691895,
|
|
"epoch": 0.5020497557140451,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004982779541782733,
|
|
"loss": 5.5052,
|
|
"mean_token_accuracy": 0.18310710787773132,
|
|
"num_tokens": 9981516.0,
|
|
"step": 4470
|
|
},
|
|
{
|
|
"entropy": 5.678966808319092,
|
|
"epoch": 0.5026113326220026,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004982729928668872,
|
|
"loss": 5.7269,
|
|
"mean_token_accuracy": 0.1666250094771385,
|
|
"num_tokens": 9992360.0,
|
|
"step": 4475
|
|
},
|
|
{
|
|
"entropy": 5.839245319366455,
|
|
"epoch": 0.5031729095299601,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004982680244464024,
|
|
"loss": 5.8428,
|
|
"mean_token_accuracy": 0.16329461485147476,
|
|
"num_tokens": 10003410.0,
|
|
"step": 4480
|
|
},
|
|
{
|
|
"entropy": 5.730415296554566,
|
|
"epoch": 0.5037344864379176,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004982630489169771,
|
|
"loss": 5.6341,
|
|
"mean_token_accuracy": 0.17327534258365632,
|
|
"num_tokens": 10014974.0,
|
|
"step": 4485
|
|
},
|
|
{
|
|
"entropy": 5.645501375198364,
|
|
"epoch": 0.5042960633458752,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004982580662787697,
|
|
"loss": 5.692,
|
|
"mean_token_accuracy": 0.17022943496704102,
|
|
"num_tokens": 10026702.0,
|
|
"step": 4490
|
|
},
|
|
{
|
|
"entropy": 5.717843055725098,
|
|
"epoch": 0.5048576402538327,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004982530765319389,
|
|
"loss": 5.6904,
|
|
"mean_token_accuracy": 0.16830755323171614,
|
|
"num_tokens": 10039318.0,
|
|
"step": 4495
|
|
},
|
|
{
|
|
"entropy": 5.691276502609253,
|
|
"epoch": 0.5054192171617903,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004982480796766436,
|
|
"loss": 5.6313,
|
|
"mean_token_accuracy": 0.16913439482450485,
|
|
"num_tokens": 10049726.0,
|
|
"step": 4500
|
|
},
|
|
{
|
|
"entropy": 5.651545238494873,
|
|
"epoch": 0.5059807940697478,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004982430757130429,
|
|
"loss": 5.5268,
|
|
"mean_token_accuracy": 0.1748660534620285,
|
|
"num_tokens": 10059663.0,
|
|
"step": 4505
|
|
},
|
|
{
|
|
"entropy": 5.548322534561157,
|
|
"epoch": 0.5065423709777054,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004982380646412959,
|
|
"loss": 5.5688,
|
|
"mean_token_accuracy": 0.17039882987737656,
|
|
"num_tokens": 10071195.0,
|
|
"step": 4510
|
|
},
|
|
{
|
|
"entropy": 5.772416973114014,
|
|
"epoch": 0.5071039478856629,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004982330464615625,
|
|
"loss": 5.7723,
|
|
"mean_token_accuracy": 0.16733259409666063,
|
|
"num_tokens": 10082014.0,
|
|
"step": 4515
|
|
},
|
|
{
|
|
"entropy": 5.7822339057922365,
|
|
"epoch": 0.5076655247936205,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004982280211740023,
|
|
"loss": 5.5619,
|
|
"mean_token_accuracy": 0.17931777387857437,
|
|
"num_tokens": 10093156.0,
|
|
"step": 4520
|
|
},
|
|
{
|
|
"entropy": 5.630906343460083,
|
|
"epoch": 0.508227101701578,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004982229887787753,
|
|
"loss": 5.7225,
|
|
"mean_token_accuracy": 0.15692505463957787,
|
|
"num_tokens": 10104993.0,
|
|
"step": 4525
|
|
},
|
|
{
|
|
"entropy": 5.623170804977417,
|
|
"epoch": 0.5087886786095356,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004982179492760418,
|
|
"loss": 5.5433,
|
|
"mean_token_accuracy": 0.18549727499485016,
|
|
"num_tokens": 10114590.0,
|
|
"step": 4530
|
|
},
|
|
{
|
|
"entropy": 5.620031547546387,
|
|
"epoch": 0.5093502555174931,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004982129026659621,
|
|
"loss": 5.5362,
|
|
"mean_token_accuracy": 0.17239733338356017,
|
|
"num_tokens": 10125849.0,
|
|
"step": 4535
|
|
},
|
|
{
|
|
"entropy": 5.655484962463379,
|
|
"epoch": 0.5099118324254507,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004982078489486972,
|
|
"loss": 5.5576,
|
|
"mean_token_accuracy": 0.17747237533330917,
|
|
"num_tokens": 10135493.0,
|
|
"step": 4540
|
|
},
|
|
{
|
|
"entropy": 5.7081160068511965,
|
|
"epoch": 0.5104734093334082,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004982027881244076,
|
|
"loss": 5.7341,
|
|
"mean_token_accuracy": 0.16819901168346404,
|
|
"num_tokens": 10146987.0,
|
|
"step": 4545
|
|
},
|
|
{
|
|
"entropy": 5.719932889938354,
|
|
"epoch": 0.5110349862413658,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004981977201932549,
|
|
"loss": 5.6656,
|
|
"mean_token_accuracy": 0.17887501418590546,
|
|
"num_tokens": 10157823.0,
|
|
"step": 4550
|
|
},
|
|
{
|
|
"entropy": 5.6378978252410885,
|
|
"epoch": 0.5115965631493233,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004981926451554001,
|
|
"loss": 5.6569,
|
|
"mean_token_accuracy": 0.17371900528669357,
|
|
"num_tokens": 10169305.0,
|
|
"step": 4555
|
|
},
|
|
{
|
|
"entropy": 5.785696792602539,
|
|
"epoch": 0.5121581400572809,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004981875630110048,
|
|
"loss": 5.7376,
|
|
"mean_token_accuracy": 0.1624615266919136,
|
|
"num_tokens": 10180346.0,
|
|
"step": 4560
|
|
},
|
|
{
|
|
"entropy": 5.702666568756103,
|
|
"epoch": 0.5127197169652384,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004981824737602311,
|
|
"loss": 5.6137,
|
|
"mean_token_accuracy": 0.17633271366357803,
|
|
"num_tokens": 10190870.0,
|
|
"step": 4565
|
|
},
|
|
{
|
|
"entropy": 5.693664836883545,
|
|
"epoch": 0.513281293873196,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004981773774032409,
|
|
"loss": 5.6682,
|
|
"mean_token_accuracy": 0.16116494238376616,
|
|
"num_tokens": 10202408.0,
|
|
"step": 4570
|
|
},
|
|
{
|
|
"entropy": 5.604257106781006,
|
|
"epoch": 0.5138428707811534,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004981722739401962,
|
|
"loss": 5.4986,
|
|
"mean_token_accuracy": 0.17710939943790435,
|
|
"num_tokens": 10213367.0,
|
|
"step": 4575
|
|
},
|
|
{
|
|
"entropy": 5.6924216747283936,
|
|
"epoch": 0.514404447689111,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00049816716337126,
|
|
"loss": 5.633,
|
|
"mean_token_accuracy": 0.16881851553916932,
|
|
"num_tokens": 10223865.0,
|
|
"step": 4580
|
|
},
|
|
{
|
|
"entropy": 5.5264606952667235,
|
|
"epoch": 0.5149660245970685,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004981620456965946,
|
|
"loss": 5.4274,
|
|
"mean_token_accuracy": 0.1748136982321739,
|
|
"num_tokens": 10235268.0,
|
|
"step": 4585
|
|
},
|
|
{
|
|
"entropy": 5.683719491958618,
|
|
"epoch": 0.5155276015050261,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004981569209163633,
|
|
"loss": 5.6751,
|
|
"mean_token_accuracy": 0.16938816010951996,
|
|
"num_tokens": 10247700.0,
|
|
"step": 4590
|
|
},
|
|
{
|
|
"entropy": 5.759853172302246,
|
|
"epoch": 0.5160891784129836,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004981517890307288,
|
|
"loss": 5.7207,
|
|
"mean_token_accuracy": 0.16935187876224517,
|
|
"num_tokens": 10258553.0,
|
|
"step": 4595
|
|
},
|
|
{
|
|
"entropy": 5.713398599624634,
|
|
"epoch": 0.5166507553209412,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000498146650039855,
|
|
"loss": 5.6092,
|
|
"mean_token_accuracy": 0.17318242639303208,
|
|
"num_tokens": 10268496.0,
|
|
"step": 4600
|
|
},
|
|
{
|
|
"entropy": 5.6950586318969725,
|
|
"epoch": 0.5172123322288987,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004981415039439054,
|
|
"loss": 5.6798,
|
|
"mean_token_accuracy": 0.17141563594341278,
|
|
"num_tokens": 10278803.0,
|
|
"step": 4605
|
|
},
|
|
{
|
|
"entropy": 5.671297550201416,
|
|
"epoch": 0.5177739091368563,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004981363507430436,
|
|
"loss": 5.5471,
|
|
"mean_token_accuracy": 0.17581456750631333,
|
|
"num_tokens": 10289805.0,
|
|
"step": 4610
|
|
},
|
|
{
|
|
"entropy": 5.673239088058471,
|
|
"epoch": 0.5183354860448138,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004981311904374339,
|
|
"loss": 5.678,
|
|
"mean_token_accuracy": 0.1728196620941162,
|
|
"num_tokens": 10300295.0,
|
|
"step": 4615
|
|
},
|
|
{
|
|
"entropy": 5.780479097366333,
|
|
"epoch": 0.5188970629527714,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004981260230272405,
|
|
"loss": 5.745,
|
|
"mean_token_accuracy": 0.1719092071056366,
|
|
"num_tokens": 10312175.0,
|
|
"step": 4620
|
|
},
|
|
{
|
|
"entropy": 5.639265680313111,
|
|
"epoch": 0.5194586398607289,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004981208485126281,
|
|
"loss": 5.6355,
|
|
"mean_token_accuracy": 0.16984736174345016,
|
|
"num_tokens": 10322888.0,
|
|
"step": 4625
|
|
},
|
|
{
|
|
"entropy": 5.687180709838867,
|
|
"epoch": 0.5200202167686865,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004981156668937613,
|
|
"loss": 5.6169,
|
|
"mean_token_accuracy": 0.1815125674009323,
|
|
"num_tokens": 10333305.0,
|
|
"step": 4630
|
|
},
|
|
{
|
|
"entropy": 5.658804559707642,
|
|
"epoch": 0.520581793676644,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004981104781708051,
|
|
"loss": 5.6688,
|
|
"mean_token_accuracy": 0.16768985539674758,
|
|
"num_tokens": 10344190.0,
|
|
"step": 4635
|
|
},
|
|
{
|
|
"entropy": 5.763923454284668,
|
|
"epoch": 0.5211433705846016,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004981052823439247,
|
|
"loss": 5.7474,
|
|
"mean_token_accuracy": 0.17006112560629844,
|
|
"num_tokens": 10356271.0,
|
|
"step": 4640
|
|
},
|
|
{
|
|
"entropy": 5.838035821914673,
|
|
"epoch": 0.5217049474925591,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004981000794132858,
|
|
"loss": 5.8013,
|
|
"mean_token_accuracy": 0.15764160305261612,
|
|
"num_tokens": 10368756.0,
|
|
"step": 4645
|
|
},
|
|
{
|
|
"entropy": 5.729043960571289,
|
|
"epoch": 0.5222665244005167,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004980948693790536,
|
|
"loss": 5.6624,
|
|
"mean_token_accuracy": 0.1676638439297676,
|
|
"num_tokens": 10380029.0,
|
|
"step": 4650
|
|
},
|
|
{
|
|
"entropy": 5.651753520965576,
|
|
"epoch": 0.5228281013084742,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004980896522413943,
|
|
"loss": 5.6539,
|
|
"mean_token_accuracy": 0.17108668088912965,
|
|
"num_tokens": 10390358.0,
|
|
"step": 4655
|
|
},
|
|
{
|
|
"entropy": 5.642056274414062,
|
|
"epoch": 0.5233896782164318,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004980844280004739,
|
|
"loss": 5.6068,
|
|
"mean_token_accuracy": 0.17424631267786025,
|
|
"num_tokens": 10401331.0,
|
|
"step": 4660
|
|
},
|
|
{
|
|
"entropy": 5.728770446777344,
|
|
"epoch": 0.5239512551243893,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004980791966564589,
|
|
"loss": 5.6435,
|
|
"mean_token_accuracy": 0.17400711625814438,
|
|
"num_tokens": 10412755.0,
|
|
"step": 4665
|
|
},
|
|
{
|
|
"entropy": 5.644752550125122,
|
|
"epoch": 0.5245128320323468,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004980739582095158,
|
|
"loss": 5.5824,
|
|
"mean_token_accuracy": 0.17636563628911972,
|
|
"num_tokens": 10422698.0,
|
|
"step": 4670
|
|
},
|
|
{
|
|
"entropy": 5.684335708618164,
|
|
"epoch": 0.5250744089403043,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004980687126598111,
|
|
"loss": 5.7166,
|
|
"mean_token_accuracy": 0.1701930895447731,
|
|
"num_tokens": 10434467.0,
|
|
"step": 4675
|
|
},
|
|
{
|
|
"entropy": 5.679470062255859,
|
|
"epoch": 0.5256359858482619,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004980634600075123,
|
|
"loss": 5.6312,
|
|
"mean_token_accuracy": 0.17567130476236342,
|
|
"num_tokens": 10446007.0,
|
|
"step": 4680
|
|
},
|
|
{
|
|
"entropy": 5.720688152313232,
|
|
"epoch": 0.5261975627562194,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004980582002527863,
|
|
"loss": 5.651,
|
|
"mean_token_accuracy": 0.1724422499537468,
|
|
"num_tokens": 10457538.0,
|
|
"step": 4685
|
|
},
|
|
{
|
|
"entropy": 5.695949745178223,
|
|
"epoch": 0.526759139664177,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004980529333958008,
|
|
"loss": 5.6071,
|
|
"mean_token_accuracy": 0.1715559646487236,
|
|
"num_tokens": 10468389.0,
|
|
"step": 4690
|
|
},
|
|
{
|
|
"entropy": 5.65442590713501,
|
|
"epoch": 0.5273207165721345,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004980476594367233,
|
|
"loss": 5.5938,
|
|
"mean_token_accuracy": 0.16828423291444777,
|
|
"num_tokens": 10479032.0,
|
|
"step": 4695
|
|
},
|
|
{
|
|
"entropy": 5.666888570785522,
|
|
"epoch": 0.5278822934800921,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004980423783757219,
|
|
"loss": 5.5921,
|
|
"mean_token_accuracy": 0.17834182530641557,
|
|
"num_tokens": 10490505.0,
|
|
"step": 4700
|
|
},
|
|
{
|
|
"entropy": 5.68553581237793,
|
|
"epoch": 0.5284438703880496,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004980370902129646,
|
|
"loss": 5.6543,
|
|
"mean_token_accuracy": 0.17590366452932357,
|
|
"num_tokens": 10501382.0,
|
|
"step": 4705
|
|
},
|
|
{
|
|
"entropy": 5.767058181762695,
|
|
"epoch": 0.5290054472960072,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00049803179494862,
|
|
"loss": 5.6184,
|
|
"mean_token_accuracy": 0.17120394557714463,
|
|
"num_tokens": 10512727.0,
|
|
"step": 4710
|
|
},
|
|
{
|
|
"entropy": 5.640833616256714,
|
|
"epoch": 0.5295670242039647,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004980264925828563,
|
|
"loss": 5.5805,
|
|
"mean_token_accuracy": 0.17655617594718934,
|
|
"num_tokens": 10523383.0,
|
|
"step": 4715
|
|
},
|
|
{
|
|
"entropy": 5.692377233505249,
|
|
"epoch": 0.5301286011119223,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004980211831158427,
|
|
"loss": 5.5938,
|
|
"mean_token_accuracy": 0.17477969080209732,
|
|
"num_tokens": 10534416.0,
|
|
"step": 4720
|
|
},
|
|
{
|
|
"entropy": 5.636052513122559,
|
|
"epoch": 0.5306901780198798,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004980158665477481,
|
|
"loss": 5.606,
|
|
"mean_token_accuracy": 0.1745822846889496,
|
|
"num_tokens": 10544291.0,
|
|
"step": 4725
|
|
},
|
|
{
|
|
"entropy": 5.627340173721313,
|
|
"epoch": 0.5312517549278374,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004980105428787419,
|
|
"loss": 5.5563,
|
|
"mean_token_accuracy": 0.17512871325016022,
|
|
"num_tokens": 10555291.0,
|
|
"step": 4730
|
|
},
|
|
{
|
|
"entropy": 5.715940952301025,
|
|
"epoch": 0.5318133318357949,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004980052121089934,
|
|
"loss": 5.6402,
|
|
"mean_token_accuracy": 0.17134194672107697,
|
|
"num_tokens": 10565812.0,
|
|
"step": 4735
|
|
},
|
|
{
|
|
"entropy": 5.658925914764405,
|
|
"epoch": 0.5323749087437525,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004979998742386725,
|
|
"loss": 5.5754,
|
|
"mean_token_accuracy": 0.17661993503570556,
|
|
"num_tokens": 10577351.0,
|
|
"step": 4740
|
|
},
|
|
{
|
|
"entropy": 5.706424760818481,
|
|
"epoch": 0.53293648565171,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004979945292679492,
|
|
"loss": 5.666,
|
|
"mean_token_accuracy": 0.1707717016339302,
|
|
"num_tokens": 10589236.0,
|
|
"step": 4745
|
|
},
|
|
{
|
|
"entropy": 5.593056678771973,
|
|
"epoch": 0.5334980625596676,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004979891771969935,
|
|
"loss": 5.6056,
|
|
"mean_token_accuracy": 0.17743002623319626,
|
|
"num_tokens": 10599926.0,
|
|
"step": 4750
|
|
},
|
|
{
|
|
"entropy": 5.7533165454864506,
|
|
"epoch": 0.5340596394676251,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000497983818025976,
|
|
"loss": 5.7135,
|
|
"mean_token_accuracy": 0.1705836147069931,
|
|
"num_tokens": 10611495.0,
|
|
"step": 4755
|
|
},
|
|
{
|
|
"entropy": 5.714666652679443,
|
|
"epoch": 0.5346212163755827,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004979784517550671,
|
|
"loss": 5.7435,
|
|
"mean_token_accuracy": 0.1691248208284378,
|
|
"num_tokens": 10622455.0,
|
|
"step": 4760
|
|
},
|
|
{
|
|
"entropy": 5.684794950485229,
|
|
"epoch": 0.5351827932835401,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004979730783844379,
|
|
"loss": 5.5835,
|
|
"mean_token_accuracy": 0.1737462729215622,
|
|
"num_tokens": 10634255.0,
|
|
"step": 4765
|
|
},
|
|
{
|
|
"entropy": 5.689221143722534,
|
|
"epoch": 0.5357443701914977,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004979676979142595,
|
|
"loss": 5.6818,
|
|
"mean_token_accuracy": 0.1724657878279686,
|
|
"num_tokens": 10644816.0,
|
|
"step": 4770
|
|
},
|
|
{
|
|
"entropy": 5.732210254669189,
|
|
"epoch": 0.5363059470994552,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000497962310344703,
|
|
"loss": 5.616,
|
|
"mean_token_accuracy": 0.1718454420566559,
|
|
"num_tokens": 10655449.0,
|
|
"step": 4775
|
|
},
|
|
{
|
|
"entropy": 5.66964955329895,
|
|
"epoch": 0.5368675240074128,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00049795691567594,
|
|
"loss": 5.6069,
|
|
"mean_token_accuracy": 0.17253539860248565,
|
|
"num_tokens": 10666343.0,
|
|
"step": 4780
|
|
},
|
|
{
|
|
"entropy": 5.63892126083374,
|
|
"epoch": 0.5374291009153703,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004979515139081426,
|
|
"loss": 5.6725,
|
|
"mean_token_accuracy": 0.17037845253944398,
|
|
"num_tokens": 10678511.0,
|
|
"step": 4785
|
|
},
|
|
{
|
|
"entropy": 5.634674549102783,
|
|
"epoch": 0.5379906778233279,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004979461050414822,
|
|
"loss": 5.6575,
|
|
"mean_token_accuracy": 0.17591144740581513,
|
|
"num_tokens": 10690005.0,
|
|
"step": 4790
|
|
},
|
|
{
|
|
"entropy": 5.6640965938568115,
|
|
"epoch": 0.5385522547312854,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004979406890761315,
|
|
"loss": 5.6599,
|
|
"mean_token_accuracy": 0.1662555977702141,
|
|
"num_tokens": 10701062.0,
|
|
"step": 4795
|
|
},
|
|
{
|
|
"entropy": 5.74897952079773,
|
|
"epoch": 0.539113831639243,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004979352660122629,
|
|
"loss": 5.5587,
|
|
"mean_token_accuracy": 0.1803977981209755,
|
|
"num_tokens": 10711986.0,
|
|
"step": 4800
|
|
},
|
|
{
|
|
"entropy": 5.6566814422607425,
|
|
"epoch": 0.5396754085472005,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004979298358500488,
|
|
"loss": 5.6847,
|
|
"mean_token_accuracy": 0.17314658015966417,
|
|
"num_tokens": 10722509.0,
|
|
"step": 4805
|
|
},
|
|
{
|
|
"entropy": 5.707429361343384,
|
|
"epoch": 0.5402369854551581,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004979243985896624,
|
|
"loss": 5.6159,
|
|
"mean_token_accuracy": 0.16971182972192764,
|
|
"num_tokens": 10733755.0,
|
|
"step": 4810
|
|
},
|
|
{
|
|
"entropy": 5.680144786834717,
|
|
"epoch": 0.5407985623631156,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004979189542312765,
|
|
"loss": 5.6535,
|
|
"mean_token_accuracy": 0.16832537651062013,
|
|
"num_tokens": 10744356.0,
|
|
"step": 4815
|
|
},
|
|
{
|
|
"entropy": 5.659034156799317,
|
|
"epoch": 0.5413601392710732,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004979135027750649,
|
|
"loss": 5.5605,
|
|
"mean_token_accuracy": 0.1717216894030571,
|
|
"num_tokens": 10756474.0,
|
|
"step": 4820
|
|
},
|
|
{
|
|
"entropy": 5.667814826965332,
|
|
"epoch": 0.5419217161790307,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004979080442212007,
|
|
"loss": 5.6387,
|
|
"mean_token_accuracy": 0.17375161051750182,
|
|
"num_tokens": 10767551.0,
|
|
"step": 4825
|
|
},
|
|
{
|
|
"entropy": 5.7569873332977295,
|
|
"epoch": 0.5424832930869883,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004979025785698581,
|
|
"loss": 5.7258,
|
|
"mean_token_accuracy": 0.17252913415431975,
|
|
"num_tokens": 10778524.0,
|
|
"step": 4830
|
|
},
|
|
{
|
|
"entropy": 5.717951011657715,
|
|
"epoch": 0.5430448699949458,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004978971058212108,
|
|
"loss": 5.6297,
|
|
"mean_token_accuracy": 0.17748113572597504,
|
|
"num_tokens": 10789798.0,
|
|
"step": 4835
|
|
},
|
|
{
|
|
"entropy": 5.657502698898315,
|
|
"epoch": 0.5436064469029034,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004978916259754331,
|
|
"loss": 5.5844,
|
|
"mean_token_accuracy": 0.1749957248568535,
|
|
"num_tokens": 10800500.0,
|
|
"step": 4840
|
|
},
|
|
{
|
|
"entropy": 5.69773235321045,
|
|
"epoch": 0.5441680238108609,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004978861390326998,
|
|
"loss": 5.6113,
|
|
"mean_token_accuracy": 0.17990991473197937,
|
|
"num_tokens": 10812047.0,
|
|
"step": 4845
|
|
},
|
|
{
|
|
"entropy": 5.653618431091308,
|
|
"epoch": 0.5447296007188185,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004978806449931854,
|
|
"loss": 5.6186,
|
|
"mean_token_accuracy": 0.1680773600935936,
|
|
"num_tokens": 10823272.0,
|
|
"step": 4850
|
|
},
|
|
{
|
|
"entropy": 5.604005479812622,
|
|
"epoch": 0.545291177626776,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004978751438570647,
|
|
"loss": 5.5149,
|
|
"mean_token_accuracy": 0.17104035317897798,
|
|
"num_tokens": 10834485.0,
|
|
"step": 4855
|
|
},
|
|
{
|
|
"entropy": 5.648079872131348,
|
|
"epoch": 0.5458527545347336,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004978696356245129,
|
|
"loss": 5.5946,
|
|
"mean_token_accuracy": 0.1701516628265381,
|
|
"num_tokens": 10843547.0,
|
|
"step": 4860
|
|
},
|
|
{
|
|
"entropy": 5.672043561935425,
|
|
"epoch": 0.546414331442691,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004978641202957057,
|
|
"loss": 5.7232,
|
|
"mean_token_accuracy": 0.16402387917041777,
|
|
"num_tokens": 10855890.0,
|
|
"step": 4865
|
|
},
|
|
{
|
|
"entropy": 5.848533487319946,
|
|
"epoch": 0.5469759083506486,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004978585978708183,
|
|
"loss": 5.7589,
|
|
"mean_token_accuracy": 0.1661063998937607,
|
|
"num_tokens": 10868060.0,
|
|
"step": 4870
|
|
},
|
|
{
|
|
"entropy": 5.792843866348266,
|
|
"epoch": 0.5475374852586061,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004978530683500267,
|
|
"loss": 5.6788,
|
|
"mean_token_accuracy": 0.1726283013820648,
|
|
"num_tokens": 10879323.0,
|
|
"step": 4875
|
|
},
|
|
{
|
|
"entropy": 5.589828443527222,
|
|
"epoch": 0.5480990621665637,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004978475317335071,
|
|
"loss": 5.5335,
|
|
"mean_token_accuracy": 0.17753928154706955,
|
|
"num_tokens": 10890545.0,
|
|
"step": 4880
|
|
},
|
|
{
|
|
"entropy": 5.638375663757325,
|
|
"epoch": 0.5486606390745212,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004978419880214356,
|
|
"loss": 5.6366,
|
|
"mean_token_accuracy": 0.16857508420944214,
|
|
"num_tokens": 10900761.0,
|
|
"step": 4885
|
|
},
|
|
{
|
|
"entropy": 5.664461660385132,
|
|
"epoch": 0.5492222159824788,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004978364372139887,
|
|
"loss": 5.6203,
|
|
"mean_token_accuracy": 0.17409153133630753,
|
|
"num_tokens": 10911874.0,
|
|
"step": 4890
|
|
},
|
|
{
|
|
"entropy": 5.638637113571167,
|
|
"epoch": 0.5497837928904363,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004978308793113434,
|
|
"loss": 5.5202,
|
|
"mean_token_accuracy": 0.1825590178370476,
|
|
"num_tokens": 10922949.0,
|
|
"step": 4895
|
|
},
|
|
{
|
|
"entropy": 5.703222703933716,
|
|
"epoch": 0.5503453697983939,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004978253143136762,
|
|
"loss": 5.7261,
|
|
"mean_token_accuracy": 0.16369061470031737,
|
|
"num_tokens": 10935415.0,
|
|
"step": 4900
|
|
},
|
|
{
|
|
"entropy": 5.642512226104737,
|
|
"epoch": 0.5509069467063514,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004978197422211647,
|
|
"loss": 5.5557,
|
|
"mean_token_accuracy": 0.17979144155979157,
|
|
"num_tokens": 10946983.0,
|
|
"step": 4905
|
|
},
|
|
{
|
|
"entropy": 5.634710216522217,
|
|
"epoch": 0.551468523614309,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004978141630339863,
|
|
"loss": 5.6412,
|
|
"mean_token_accuracy": 0.16508993357419968,
|
|
"num_tokens": 10957884.0,
|
|
"step": 4910
|
|
},
|
|
{
|
|
"entropy": 5.666868877410889,
|
|
"epoch": 0.5520301005222665,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004978085767523184,
|
|
"loss": 5.66,
|
|
"mean_token_accuracy": 0.1756490260362625,
|
|
"num_tokens": 10968518.0,
|
|
"step": 4915
|
|
},
|
|
{
|
|
"entropy": 5.683876085281372,
|
|
"epoch": 0.5525916774302241,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000497802983376339,
|
|
"loss": 5.6515,
|
|
"mean_token_accuracy": 0.1680527150630951,
|
|
"num_tokens": 10979621.0,
|
|
"step": 4920
|
|
},
|
|
{
|
|
"entropy": 5.6596965312957765,
|
|
"epoch": 0.5531532543381816,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004977973829062263,
|
|
"loss": 5.5791,
|
|
"mean_token_accuracy": 0.17575374245643616,
|
|
"num_tokens": 10990158.0,
|
|
"step": 4925
|
|
},
|
|
{
|
|
"entropy": 5.683869028091431,
|
|
"epoch": 0.5537148312461392,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004977917753421585,
|
|
"loss": 5.6936,
|
|
"mean_token_accuracy": 0.16995401680469513,
|
|
"num_tokens": 11001732.0,
|
|
"step": 4930
|
|
},
|
|
{
|
|
"entropy": 5.811647081375122,
|
|
"epoch": 0.5542764081540967,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000497786160684314,
|
|
"loss": 5.7094,
|
|
"mean_token_accuracy": 0.16645046770572663,
|
|
"num_tokens": 11013483.0,
|
|
"step": 4935
|
|
},
|
|
{
|
|
"entropy": 5.766137170791626,
|
|
"epoch": 0.5548379850620543,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004977805389328719,
|
|
"loss": 5.7058,
|
|
"mean_token_accuracy": 0.16747778952121734,
|
|
"num_tokens": 11025423.0,
|
|
"step": 4940
|
|
},
|
|
{
|
|
"entropy": 5.683235168457031,
|
|
"epoch": 0.5553995619700118,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.000497774910088011,
|
|
"loss": 5.5321,
|
|
"mean_token_accuracy": 0.17452547699213028,
|
|
"num_tokens": 11037041.0,
|
|
"step": 4945
|
|
},
|
|
{
|
|
"entropy": 5.62727837562561,
|
|
"epoch": 0.5559611388779694,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004977692741499106,
|
|
"loss": 5.6784,
|
|
"mean_token_accuracy": 0.17244722098112106,
|
|
"num_tokens": 11049206.0,
|
|
"step": 4950
|
|
},
|
|
{
|
|
"entropy": 5.6918176174163815,
|
|
"epoch": 0.5565227157859269,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.00049776363111875,
|
|
"loss": 5.6507,
|
|
"mean_token_accuracy": 0.17321952879428865,
|
|
"num_tokens": 11060407.0,
|
|
"step": 4955
|
|
},
|
|
{
|
|
"entropy": 5.665940999984741,
|
|
"epoch": 0.5570842926938844,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004977579809947091,
|
|
"loss": 5.5935,
|
|
"mean_token_accuracy": 0.16961163729429246,
|
|
"num_tokens": 11071269.0,
|
|
"step": 4960
|
|
},
|
|
{
|
|
"entropy": 5.670188331604004,
|
|
"epoch": 0.5576458696018419,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004977523237779676,
|
|
"loss": 5.5764,
|
|
"mean_token_accuracy": 0.17973648011684418,
|
|
"num_tokens": 11082078.0,
|
|
"step": 4965
|
|
},
|
|
{
|
|
"entropy": 5.848326587677002,
|
|
"epoch": 0.5582074465097995,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004977466594687057,
|
|
"loss": 5.826,
|
|
"mean_token_accuracy": 0.15897191315889359,
|
|
"num_tokens": 11094596.0,
|
|
"step": 4970
|
|
},
|
|
{
|
|
"entropy": 5.739849805831909,
|
|
"epoch": 0.558769023417757,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004977409880671039,
|
|
"loss": 5.6725,
|
|
"mean_token_accuracy": 0.16561551690101622,
|
|
"num_tokens": 11107705.0,
|
|
"step": 4975
|
|
},
|
|
{
|
|
"entropy": 5.647367143630982,
|
|
"epoch": 0.5593306003257146,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004977353095733427,
|
|
"loss": 5.5917,
|
|
"mean_token_accuracy": 0.1732107475399971,
|
|
"num_tokens": 11118152.0,
|
|
"step": 4980
|
|
},
|
|
{
|
|
"entropy": 5.6580524921417235,
|
|
"epoch": 0.5598921772336721,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004977296239876026,
|
|
"loss": 5.6035,
|
|
"mean_token_accuracy": 0.1706430971622467,
|
|
"num_tokens": 11129261.0,
|
|
"step": 4985
|
|
},
|
|
{
|
|
"entropy": 5.774927043914795,
|
|
"epoch": 0.5604537541416297,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.000497723931310065,
|
|
"loss": 5.7303,
|
|
"mean_token_accuracy": 0.1615266591310501,
|
|
"num_tokens": 11142227.0,
|
|
"step": 4990
|
|
},
|
|
{
|
|
"entropy": 5.783212327957154,
|
|
"epoch": 0.5610153310495872,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004977182315409111,
|
|
"loss": 5.6525,
|
|
"mean_token_accuracy": 0.1708063527941704,
|
|
"num_tokens": 11154277.0,
|
|
"step": 4995
|
|
},
|
|
{
|
|
"entropy": 5.637371063232422,
|
|
"epoch": 0.5615769079575448,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004977125246803224,
|
|
"loss": 5.6481,
|
|
"mean_token_accuracy": 0.17097974419593812,
|
|
"num_tokens": 11164902.0,
|
|
"step": 5000
|
|
},
|
|
{
|
|
"entropy": 5.627787637710571,
|
|
"epoch": 0.5621384848655023,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004977068107284803,
|
|
"loss": 5.5274,
|
|
"mean_token_accuracy": 0.17404485791921614,
|
|
"num_tokens": 11176010.0,
|
|
"step": 5005
|
|
},
|
|
{
|
|
"entropy": 5.6504889011383055,
|
|
"epoch": 0.5627000617734599,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004977010896855672,
|
|
"loss": 5.5751,
|
|
"mean_token_accuracy": 0.17597310543060302,
|
|
"num_tokens": 11187773.0,
|
|
"step": 5010
|
|
},
|
|
{
|
|
"entropy": 5.6809529781341555,
|
|
"epoch": 0.5632616386814174,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004976953615517649,
|
|
"loss": 5.6592,
|
|
"mean_token_accuracy": 0.1747044324874878,
|
|
"num_tokens": 11198420.0,
|
|
"step": 5015
|
|
},
|
|
{
|
|
"entropy": 5.578175115585327,
|
|
"epoch": 0.563823215589375,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000497689626327256,
|
|
"loss": 5.4566,
|
|
"mean_token_accuracy": 0.18271085619926453,
|
|
"num_tokens": 11208553.0,
|
|
"step": 5020
|
|
},
|
|
{
|
|
"entropy": 5.608962726593018,
|
|
"epoch": 0.5643847924973325,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000497683884012223,
|
|
"loss": 5.6329,
|
|
"mean_token_accuracy": 0.17676953077316285,
|
|
"num_tokens": 11219737.0,
|
|
"step": 5025
|
|
},
|
|
{
|
|
"entropy": 5.601259374618531,
|
|
"epoch": 0.5649463694052901,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004976781346068487,
|
|
"loss": 5.6241,
|
|
"mean_token_accuracy": 0.1708438515663147,
|
|
"num_tokens": 11230997.0,
|
|
"step": 5030
|
|
},
|
|
{
|
|
"entropy": 5.761299896240234,
|
|
"epoch": 0.5655079463132476,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004976723781113163,
|
|
"loss": 5.6272,
|
|
"mean_token_accuracy": 0.17421030551195144,
|
|
"num_tokens": 11242338.0,
|
|
"step": 5035
|
|
},
|
|
{
|
|
"entropy": 5.774703121185302,
|
|
"epoch": 0.5660695232212052,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004976666145258089,
|
|
"loss": 5.6627,
|
|
"mean_token_accuracy": 0.17134836912155152,
|
|
"num_tokens": 11252671.0,
|
|
"step": 5040
|
|
},
|
|
{
|
|
"entropy": 5.499648857116699,
|
|
"epoch": 0.5666311001291627,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004976608438505103,
|
|
"loss": 5.4949,
|
|
"mean_token_accuracy": 0.1794860765337944,
|
|
"num_tokens": 11262721.0,
|
|
"step": 5045
|
|
},
|
|
{
|
|
"entropy": 5.63766450881958,
|
|
"epoch": 0.5671926770371203,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004976550660856041,
|
|
"loss": 5.6903,
|
|
"mean_token_accuracy": 0.1703629180788994,
|
|
"num_tokens": 11274074.0,
|
|
"step": 5050
|
|
},
|
|
{
|
|
"entropy": 5.791182565689087,
|
|
"epoch": 0.5677542539450777,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000497649281231274,
|
|
"loss": 5.6181,
|
|
"mean_token_accuracy": 0.1732160970568657,
|
|
"num_tokens": 11286051.0,
|
|
"step": 5055
|
|
},
|
|
{
|
|
"entropy": 5.7704356670379635,
|
|
"epoch": 0.5683158308530353,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004976434892877046,
|
|
"loss": 5.7375,
|
|
"mean_token_accuracy": 0.1661434069275856,
|
|
"num_tokens": 11298841.0,
|
|
"step": 5060
|
|
},
|
|
{
|
|
"entropy": 5.70151424407959,
|
|
"epoch": 0.5688774077609928,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004976376902550802,
|
|
"loss": 5.7113,
|
|
"mean_token_accuracy": 0.1755992740392685,
|
|
"num_tokens": 11309898.0,
|
|
"step": 5065
|
|
},
|
|
{
|
|
"entropy": 5.717077732086182,
|
|
"epoch": 0.5694389846689504,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004976318841335854,
|
|
"loss": 5.7546,
|
|
"mean_token_accuracy": 0.1697839990258217,
|
|
"num_tokens": 11322163.0,
|
|
"step": 5070
|
|
},
|
|
{
|
|
"entropy": 5.738639974594117,
|
|
"epoch": 0.5700005615769079,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004976260709234049,
|
|
"loss": 5.6927,
|
|
"mean_token_accuracy": 0.16664426475763322,
|
|
"num_tokens": 11333405.0,
|
|
"step": 5075
|
|
},
|
|
{
|
|
"entropy": 5.826970052719116,
|
|
"epoch": 0.5705621384848655,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000497620250624724,
|
|
"loss": 5.7438,
|
|
"mean_token_accuracy": 0.16764499396085739,
|
|
"num_tokens": 11345037.0,
|
|
"step": 5080
|
|
},
|
|
{
|
|
"entropy": 5.70676474571228,
|
|
"epoch": 0.571123715392823,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.000497614423237728,
|
|
"loss": 5.6702,
|
|
"mean_token_accuracy": 0.16873674914240838,
|
|
"num_tokens": 11356403.0,
|
|
"step": 5085
|
|
},
|
|
{
|
|
"entropy": 5.616442728042602,
|
|
"epoch": 0.5716852923007806,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004976085887626026,
|
|
"loss": 5.6027,
|
|
"mean_token_accuracy": 0.17377539873123168,
|
|
"num_tokens": 11367913.0,
|
|
"step": 5090
|
|
},
|
|
{
|
|
"entropy": 5.659976625442505,
|
|
"epoch": 0.5722468692087381,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004976027471995331,
|
|
"loss": 5.5998,
|
|
"mean_token_accuracy": 0.17778513878583907,
|
|
"num_tokens": 11378519.0,
|
|
"step": 5095
|
|
},
|
|
{
|
|
"entropy": 5.630605316162109,
|
|
"epoch": 0.5728084461166957,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.000497596898548706,
|
|
"loss": 5.5687,
|
|
"mean_token_accuracy": 0.1734382063150406,
|
|
"num_tokens": 11389530.0,
|
|
"step": 5100
|
|
},
|
|
{
|
|
"entropy": 5.514801502227783,
|
|
"epoch": 0.5733700230246532,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004975910428103072,
|
|
"loss": 5.4936,
|
|
"mean_token_accuracy": 0.17790030539035798,
|
|
"num_tokens": 11400468.0,
|
|
"step": 5105
|
|
},
|
|
{
|
|
"entropy": 5.539993667602539,
|
|
"epoch": 0.5739315999326108,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004975851799845233,
|
|
"loss": 5.4962,
|
|
"mean_token_accuracy": 0.178937928378582,
|
|
"num_tokens": 11411242.0,
|
|
"step": 5110
|
|
},
|
|
{
|
|
"entropy": 5.745843410491943,
|
|
"epoch": 0.5744931768405683,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.000497579310071541,
|
|
"loss": 5.5791,
|
|
"mean_token_accuracy": 0.17534930258989334,
|
|
"num_tokens": 11420909.0,
|
|
"step": 5115
|
|
},
|
|
{
|
|
"entropy": 5.551583623886108,
|
|
"epoch": 0.5750547537485259,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004975734330715471,
|
|
"loss": 5.4648,
|
|
"mean_token_accuracy": 0.17187040895223618,
|
|
"num_tokens": 11431791.0,
|
|
"step": 5120
|
|
},
|
|
{
|
|
"entropy": 5.759070348739624,
|
|
"epoch": 0.5756163306564834,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004975675489847287,
|
|
"loss": 5.6982,
|
|
"mean_token_accuracy": 0.16646568775177,
|
|
"num_tokens": 11443056.0,
|
|
"step": 5125
|
|
},
|
|
{
|
|
"entropy": 5.707419967651367,
|
|
"epoch": 0.576177907564441,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004975616578112734,
|
|
"loss": 5.6707,
|
|
"mean_token_accuracy": 0.174280746281147,
|
|
"num_tokens": 11453413.0,
|
|
"step": 5130
|
|
},
|
|
{
|
|
"entropy": 5.758253908157348,
|
|
"epoch": 0.5767394844723985,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004975557595513684,
|
|
"loss": 5.8787,
|
|
"mean_token_accuracy": 0.15964249670505523,
|
|
"num_tokens": 11465457.0,
|
|
"step": 5135
|
|
},
|
|
{
|
|
"entropy": 5.847833681106567,
|
|
"epoch": 0.5773010613803561,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004975498542052018,
|
|
"loss": 5.6674,
|
|
"mean_token_accuracy": 0.17582339346408843,
|
|
"num_tokens": 11476899.0,
|
|
"step": 5140
|
|
},
|
|
{
|
|
"entropy": 5.62633786201477,
|
|
"epoch": 0.5778626382883136,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004975439417729615,
|
|
"loss": 5.6328,
|
|
"mean_token_accuracy": 0.17490290701389313,
|
|
"num_tokens": 11488652.0,
|
|
"step": 5145
|
|
},
|
|
{
|
|
"entropy": 5.697226476669312,
|
|
"epoch": 0.5784242151962711,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004975380222548358,
|
|
"loss": 5.6636,
|
|
"mean_token_accuracy": 0.1697861820459366,
|
|
"num_tokens": 11499540.0,
|
|
"step": 5150
|
|
},
|
|
{
|
|
"entropy": 5.795323753356934,
|
|
"epoch": 0.5789857921042286,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004975320956510131,
|
|
"loss": 5.6917,
|
|
"mean_token_accuracy": 0.17290201038122177,
|
|
"num_tokens": 11511156.0,
|
|
"step": 5155
|
|
},
|
|
{
|
|
"entropy": 5.7587597370147705,
|
|
"epoch": 0.5795473690121862,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004975261619616822,
|
|
"loss": 5.7541,
|
|
"mean_token_accuracy": 0.15890361815690995,
|
|
"num_tokens": 11523489.0,
|
|
"step": 5160
|
|
},
|
|
{
|
|
"entropy": 5.669517660140992,
|
|
"epoch": 0.5801089459201437,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004975202211870321,
|
|
"loss": 5.5848,
|
|
"mean_token_accuracy": 0.17221621572971343,
|
|
"num_tokens": 11534497.0,
|
|
"step": 5165
|
|
},
|
|
{
|
|
"entropy": 5.80835223197937,
|
|
"epoch": 0.5806705228281013,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004975142733272518,
|
|
"loss": 5.6799,
|
|
"mean_token_accuracy": 0.1659674733877182,
|
|
"num_tokens": 11545585.0,
|
|
"step": 5170
|
|
},
|
|
{
|
|
"entropy": 5.570547103881836,
|
|
"epoch": 0.5812320997360588,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004975083183825306,
|
|
"loss": 5.5123,
|
|
"mean_token_accuracy": 0.17563536912202835,
|
|
"num_tokens": 11556278.0,
|
|
"step": 5175
|
|
},
|
|
{
|
|
"entropy": 5.597272300720215,
|
|
"epoch": 0.5817936766440164,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004975023563530584,
|
|
"loss": 5.5972,
|
|
"mean_token_accuracy": 0.17913515418767928,
|
|
"num_tokens": 11568358.0,
|
|
"step": 5180
|
|
},
|
|
{
|
|
"entropy": 5.628659582138061,
|
|
"epoch": 0.5823552535519739,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004974963872390249,
|
|
"loss": 5.5695,
|
|
"mean_token_accuracy": 0.17839607149362563,
|
|
"num_tokens": 11579777.0,
|
|
"step": 5185
|
|
},
|
|
{
|
|
"entropy": 5.6159820556640625,
|
|
"epoch": 0.5829168304599315,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00049749041104062,
|
|
"loss": 5.6376,
|
|
"mean_token_accuracy": 0.17163055539131164,
|
|
"num_tokens": 11591479.0,
|
|
"step": 5190
|
|
},
|
|
{
|
|
"entropy": 5.712009477615356,
|
|
"epoch": 0.583478407367889,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004974844277580343,
|
|
"loss": 5.5815,
|
|
"mean_token_accuracy": 0.17472826391458512,
|
|
"num_tokens": 11601452.0,
|
|
"step": 5195
|
|
},
|
|
{
|
|
"entropy": 5.571263408660888,
|
|
"epoch": 0.5840399842758466,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004974784373914579,
|
|
"loss": 5.4471,
|
|
"mean_token_accuracy": 0.1794617861509323,
|
|
"num_tokens": 11611661.0,
|
|
"step": 5200
|
|
},
|
|
{
|
|
"entropy": 5.595188236236572,
|
|
"epoch": 0.5846015611838041,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004974724399410818,
|
|
"loss": 5.622,
|
|
"mean_token_accuracy": 0.16921583861112593,
|
|
"num_tokens": 11622940.0,
|
|
"step": 5205
|
|
},
|
|
{
|
|
"entropy": 5.68701491355896,
|
|
"epoch": 0.5851631380917617,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004974664354070971,
|
|
"loss": 5.6525,
|
|
"mean_token_accuracy": 0.1670906201004982,
|
|
"num_tokens": 11634290.0,
|
|
"step": 5210
|
|
},
|
|
{
|
|
"entropy": 5.743814182281494,
|
|
"epoch": 0.5857247149997192,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004974604237896947,
|
|
"loss": 5.6741,
|
|
"mean_token_accuracy": 0.16699134707450866,
|
|
"num_tokens": 11645812.0,
|
|
"step": 5215
|
|
},
|
|
{
|
|
"entropy": 5.656312322616577,
|
|
"epoch": 0.5862862919076768,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004974544050890662,
|
|
"loss": 5.6633,
|
|
"mean_token_accuracy": 0.16812316328287125,
|
|
"num_tokens": 11657520.0,
|
|
"step": 5220
|
|
},
|
|
{
|
|
"entropy": 5.676590347290039,
|
|
"epoch": 0.5868478688156343,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.000497448379305403,
|
|
"loss": 5.5326,
|
|
"mean_token_accuracy": 0.18476960957050323,
|
|
"num_tokens": 11666887.0,
|
|
"step": 5225
|
|
},
|
|
{
|
|
"entropy": 5.706187677383423,
|
|
"epoch": 0.5874094457235919,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004974423464388973,
|
|
"loss": 5.7146,
|
|
"mean_token_accuracy": 0.1689675807952881,
|
|
"num_tokens": 11677337.0,
|
|
"step": 5230
|
|
},
|
|
{
|
|
"entropy": 5.660748863220215,
|
|
"epoch": 0.5879710226315494,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.000497436306489741,
|
|
"loss": 5.641,
|
|
"mean_token_accuracy": 0.1716355100274086,
|
|
"num_tokens": 11688203.0,
|
|
"step": 5235
|
|
},
|
|
{
|
|
"entropy": 5.7210413932800295,
|
|
"epoch": 0.588532599539507,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004974302594581264,
|
|
"loss": 5.6772,
|
|
"mean_token_accuracy": 0.16715651899576187,
|
|
"num_tokens": 11699727.0,
|
|
"step": 5240
|
|
},
|
|
{
|
|
"entropy": 5.720707702636719,
|
|
"epoch": 0.5890941764474645,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004974242053442461,
|
|
"loss": 5.6691,
|
|
"mean_token_accuracy": 0.17226083129644393,
|
|
"num_tokens": 11710956.0,
|
|
"step": 5245
|
|
},
|
|
{
|
|
"entropy": 5.712599658966065,
|
|
"epoch": 0.589655753355422,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004974181441482927,
|
|
"loss": 5.5179,
|
|
"mean_token_accuracy": 0.17833440005779266,
|
|
"num_tokens": 11721681.0,
|
|
"step": 5250
|
|
},
|
|
{
|
|
"entropy": 5.632621574401855,
|
|
"epoch": 0.5902173302633795,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004974120758704595,
|
|
"loss": 5.6377,
|
|
"mean_token_accuracy": 0.16659789979457856,
|
|
"num_tokens": 11731679.0,
|
|
"step": 5255
|
|
},
|
|
{
|
|
"entropy": 5.728541469573974,
|
|
"epoch": 0.5907789071713371,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004974060005109394,
|
|
"loss": 5.7755,
|
|
"mean_token_accuracy": 0.1653306633234024,
|
|
"num_tokens": 11743953.0,
|
|
"step": 5260
|
|
},
|
|
{
|
|
"entropy": 5.594753456115723,
|
|
"epoch": 0.5913404840792946,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.000497399918069926,
|
|
"loss": 5.5474,
|
|
"mean_token_accuracy": 0.18174650222063066,
|
|
"num_tokens": 11754091.0,
|
|
"step": 5265
|
|
},
|
|
{
|
|
"entropy": 5.627842760086059,
|
|
"epoch": 0.5919020609872522,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004973938285476131,
|
|
"loss": 5.5626,
|
|
"mean_token_accuracy": 0.17435735017061232,
|
|
"num_tokens": 11764771.0,
|
|
"step": 5270
|
|
},
|
|
{
|
|
"entropy": 5.697529935836792,
|
|
"epoch": 0.5924636378952097,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004973877319441943,
|
|
"loss": 5.6312,
|
|
"mean_token_accuracy": 0.17113209813833236,
|
|
"num_tokens": 11776287.0,
|
|
"step": 5275
|
|
},
|
|
{
|
|
"entropy": 5.753840065002441,
|
|
"epoch": 0.5930252148031673,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004973816282598639,
|
|
"loss": 5.6464,
|
|
"mean_token_accuracy": 0.16645084768533708,
|
|
"num_tokens": 11787142.0,
|
|
"step": 5280
|
|
},
|
|
{
|
|
"entropy": 5.680408906936646,
|
|
"epoch": 0.5935867917111248,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004973755174948162,
|
|
"loss": 5.6125,
|
|
"mean_token_accuracy": 0.17083410918712616,
|
|
"num_tokens": 11798966.0,
|
|
"step": 5285
|
|
},
|
|
{
|
|
"entropy": 5.725675773620606,
|
|
"epoch": 0.5941483686190824,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004973693996492458,
|
|
"loss": 5.7044,
|
|
"mean_token_accuracy": 0.16556227803230286,
|
|
"num_tokens": 11810529.0,
|
|
"step": 5290
|
|
},
|
|
{
|
|
"entropy": 5.629840993881226,
|
|
"epoch": 0.5947099455270399,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004973632747233475,
|
|
"loss": 5.5437,
|
|
"mean_token_accuracy": 0.1780479669570923,
|
|
"num_tokens": 11821965.0,
|
|
"step": 5295
|
|
},
|
|
{
|
|
"entropy": 5.711505270004272,
|
|
"epoch": 0.5952715224349975,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004973571427173163,
|
|
"loss": 5.7247,
|
|
"mean_token_accuracy": 0.1672951638698578,
|
|
"num_tokens": 11833936.0,
|
|
"step": 5300
|
|
},
|
|
{
|
|
"entropy": 5.700901937484741,
|
|
"epoch": 0.595833099342955,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004973510036313473,
|
|
"loss": 5.6155,
|
|
"mean_token_accuracy": 0.17391461730003357,
|
|
"num_tokens": 11845245.0,
|
|
"step": 5305
|
|
},
|
|
{
|
|
"entropy": 5.671370553970337,
|
|
"epoch": 0.5963946762509126,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004973448574656362,
|
|
"loss": 5.6032,
|
|
"mean_token_accuracy": 0.17481126338243486,
|
|
"num_tokens": 11856010.0,
|
|
"step": 5310
|
|
},
|
|
{
|
|
"entropy": 5.723221778869629,
|
|
"epoch": 0.5969562531588701,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004973387042203786,
|
|
"loss": 5.7506,
|
|
"mean_token_accuracy": 0.16535574719309806,
|
|
"num_tokens": 11866194.0,
|
|
"step": 5315
|
|
},
|
|
{
|
|
"entropy": 5.698858833312988,
|
|
"epoch": 0.5975178300668277,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004973325438957704,
|
|
"loss": 5.5977,
|
|
"mean_token_accuracy": 0.17356279492378235,
|
|
"num_tokens": 11877224.0,
|
|
"step": 5320
|
|
},
|
|
{
|
|
"entropy": 5.613062620162964,
|
|
"epoch": 0.5980794069747852,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004973263764920079,
|
|
"loss": 5.5367,
|
|
"mean_token_accuracy": 0.17539132684469222,
|
|
"num_tokens": 11887410.0,
|
|
"step": 5325
|
|
},
|
|
{
|
|
"entropy": 5.612221336364746,
|
|
"epoch": 0.5986409838827428,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004973202020092871,
|
|
"loss": 5.6733,
|
|
"mean_token_accuracy": 0.1710530251264572,
|
|
"num_tokens": 11898816.0,
|
|
"step": 5330
|
|
},
|
|
{
|
|
"entropy": 5.7131434917449955,
|
|
"epoch": 0.5992025607907003,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.000497314020447805,
|
|
"loss": 5.6277,
|
|
"mean_token_accuracy": 0.17206395864486695,
|
|
"num_tokens": 11909220.0,
|
|
"step": 5335
|
|
},
|
|
{
|
|
"entropy": 5.730351209640503,
|
|
"epoch": 0.5997641376986579,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004973078318077583,
|
|
"loss": 5.6455,
|
|
"mean_token_accuracy": 0.17104278057813643,
|
|
"num_tokens": 11919584.0,
|
|
"step": 5340
|
|
},
|
|
{
|
|
"entropy": 5.644850635528565,
|
|
"epoch": 0.6003257146066153,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000497301636089344,
|
|
"loss": 5.6466,
|
|
"mean_token_accuracy": 0.17016790807247162,
|
|
"num_tokens": 11929298.0,
|
|
"step": 5345
|
|
},
|
|
{
|
|
"entropy": 5.665215969085693,
|
|
"epoch": 0.6008872915145729,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004972954332927592,
|
|
"loss": 5.6091,
|
|
"mean_token_accuracy": 0.17349499166011811,
|
|
"num_tokens": 11939809.0,
|
|
"step": 5350
|
|
},
|
|
{
|
|
"entropy": 5.692801570892334,
|
|
"epoch": 0.6014488684225304,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004972892234182018,
|
|
"loss": 5.5161,
|
|
"mean_token_accuracy": 0.177711646258831,
|
|
"num_tokens": 11950292.0,
|
|
"step": 5355
|
|
},
|
|
{
|
|
"entropy": 5.553488254547119,
|
|
"epoch": 0.602010445330488,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004972830064658692,
|
|
"loss": 5.5336,
|
|
"mean_token_accuracy": 0.176306089758873,
|
|
"num_tokens": 11961774.0,
|
|
"step": 5360
|
|
},
|
|
{
|
|
"entropy": 5.70540566444397,
|
|
"epoch": 0.6025720222384455,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004972767824359596,
|
|
"loss": 5.6333,
|
|
"mean_token_accuracy": 0.166362926363945,
|
|
"num_tokens": 11973351.0,
|
|
"step": 5365
|
|
},
|
|
{
|
|
"entropy": 5.646889591217041,
|
|
"epoch": 0.6031335991464031,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004972705513286709,
|
|
"loss": 5.5109,
|
|
"mean_token_accuracy": 0.17552825957536697,
|
|
"num_tokens": 11984472.0,
|
|
"step": 5370
|
|
},
|
|
{
|
|
"entropy": 5.614611673355102,
|
|
"epoch": 0.6036951760543606,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004972643131442017,
|
|
"loss": 5.6038,
|
|
"mean_token_accuracy": 0.1751638501882553,
|
|
"num_tokens": 11994271.0,
|
|
"step": 5375
|
|
},
|
|
{
|
|
"entropy": 5.795274305343628,
|
|
"epoch": 0.6042567529623182,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004972580678827506,
|
|
"loss": 5.7312,
|
|
"mean_token_accuracy": 0.1628146305680275,
|
|
"num_tokens": 12007647.0,
|
|
"step": 5380
|
|
},
|
|
{
|
|
"entropy": 5.777073907852173,
|
|
"epoch": 0.6048183298702757,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004972518155445163,
|
|
"loss": 5.6806,
|
|
"mean_token_accuracy": 0.16595635712146758,
|
|
"num_tokens": 12020331.0,
|
|
"step": 5385
|
|
},
|
|
{
|
|
"entropy": 5.63973183631897,
|
|
"epoch": 0.6053799067782333,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004972455561296982,
|
|
"loss": 5.6848,
|
|
"mean_token_accuracy": 0.1646930456161499,
|
|
"num_tokens": 12031616.0,
|
|
"step": 5390
|
|
},
|
|
{
|
|
"entropy": 5.767481946945191,
|
|
"epoch": 0.6059414836861908,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004972392896384952,
|
|
"loss": 5.6298,
|
|
"mean_token_accuracy": 0.1701526015996933,
|
|
"num_tokens": 12044107.0,
|
|
"step": 5395
|
|
},
|
|
{
|
|
"entropy": 5.671582365036011,
|
|
"epoch": 0.6065030605941484,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004972330160711071,
|
|
"loss": 5.6197,
|
|
"mean_token_accuracy": 0.17153621464967728,
|
|
"num_tokens": 12055747.0,
|
|
"step": 5400
|
|
},
|
|
{
|
|
"entropy": 5.646366167068481,
|
|
"epoch": 0.6070646375021059,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004972267354277336,
|
|
"loss": 5.6218,
|
|
"mean_token_accuracy": 0.17101967036724092,
|
|
"num_tokens": 12067849.0,
|
|
"step": 5405
|
|
},
|
|
{
|
|
"entropy": 5.710489177703858,
|
|
"epoch": 0.6076262144100635,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004972204477085746,
|
|
"loss": 5.6282,
|
|
"mean_token_accuracy": 0.16910918354988097,
|
|
"num_tokens": 12078534.0,
|
|
"step": 5410
|
|
},
|
|
{
|
|
"entropy": 5.581234264373779,
|
|
"epoch": 0.608187791318021,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004972141529138303,
|
|
"loss": 5.5764,
|
|
"mean_token_accuracy": 0.17210591286420823,
|
|
"num_tokens": 12089534.0,
|
|
"step": 5415
|
|
},
|
|
{
|
|
"entropy": 5.615314579010009,
|
|
"epoch": 0.6087493682259786,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004972078510437013,
|
|
"loss": 5.4629,
|
|
"mean_token_accuracy": 0.19327283203601836,
|
|
"num_tokens": 12099513.0,
|
|
"step": 5420
|
|
},
|
|
{
|
|
"entropy": 5.717644596099854,
|
|
"epoch": 0.6093109451339361,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004972015420983882,
|
|
"loss": 5.6801,
|
|
"mean_token_accuracy": 0.17841842472553254,
|
|
"num_tokens": 12110106.0,
|
|
"step": 5425
|
|
},
|
|
{
|
|
"entropy": 5.622862911224365,
|
|
"epoch": 0.6098725220418937,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004971952260780915,
|
|
"loss": 5.5628,
|
|
"mean_token_accuracy": 0.17866639345884322,
|
|
"num_tokens": 12121302.0,
|
|
"step": 5430
|
|
},
|
|
{
|
|
"entropy": 5.637872409820557,
|
|
"epoch": 0.6104340989498512,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.000497188902983013,
|
|
"loss": 5.6058,
|
|
"mean_token_accuracy": 0.17580058574676513,
|
|
"num_tokens": 12132879.0,
|
|
"step": 5435
|
|
},
|
|
{
|
|
"entropy": 5.635155820846558,
|
|
"epoch": 0.6109956758578087,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004971825728133535,
|
|
"loss": 5.535,
|
|
"mean_token_accuracy": 0.1831826612353325,
|
|
"num_tokens": 12143597.0,
|
|
"step": 5440
|
|
},
|
|
{
|
|
"entropy": 5.710077810287475,
|
|
"epoch": 0.6115572527657662,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004971762355693146,
|
|
"loss": 5.6405,
|
|
"mean_token_accuracy": 0.17502407729625702,
|
|
"num_tokens": 12156036.0,
|
|
"step": 5445
|
|
},
|
|
{
|
|
"entropy": 5.697023344039917,
|
|
"epoch": 0.6121188296737238,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004971698912510983,
|
|
"loss": 5.6548,
|
|
"mean_token_accuracy": 0.17419305592775344,
|
|
"num_tokens": 12167305.0,
|
|
"step": 5450
|
|
},
|
|
{
|
|
"entropy": 5.680604028701782,
|
|
"epoch": 0.6126804065816813,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004971635398589066,
|
|
"loss": 5.5965,
|
|
"mean_token_accuracy": 0.18156216144561768,
|
|
"num_tokens": 12176772.0,
|
|
"step": 5455
|
|
},
|
|
{
|
|
"entropy": 5.625756549835205,
|
|
"epoch": 0.6132419834896389,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004971571813929415,
|
|
"loss": 5.6001,
|
|
"mean_token_accuracy": 0.17258601784706115,
|
|
"num_tokens": 12187852.0,
|
|
"step": 5460
|
|
},
|
|
{
|
|
"entropy": 5.721166896820068,
|
|
"epoch": 0.6138035603975964,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004971508158534056,
|
|
"loss": 5.6759,
|
|
"mean_token_accuracy": 0.1719754308462143,
|
|
"num_tokens": 12198574.0,
|
|
"step": 5465
|
|
},
|
|
{
|
|
"entropy": 5.600162649154663,
|
|
"epoch": 0.614365137305554,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004971444432405015,
|
|
"loss": 5.4301,
|
|
"mean_token_accuracy": 0.18324994742870332,
|
|
"num_tokens": 12209463.0,
|
|
"step": 5470
|
|
},
|
|
{
|
|
"entropy": 5.694200801849365,
|
|
"epoch": 0.6149267142135115,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004971380635544323,
|
|
"loss": 5.702,
|
|
"mean_token_accuracy": 0.17309850305318833,
|
|
"num_tokens": 12220993.0,
|
|
"step": 5475
|
|
},
|
|
{
|
|
"entropy": 5.669279670715332,
|
|
"epoch": 0.6154882911214691,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004971316767954009,
|
|
"loss": 5.5814,
|
|
"mean_token_accuracy": 0.17764147818088533,
|
|
"num_tokens": 12232648.0,
|
|
"step": 5480
|
|
},
|
|
{
|
|
"entropy": 5.661475801467896,
|
|
"epoch": 0.6160498680294266,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004971252829636108,
|
|
"loss": 5.6158,
|
|
"mean_token_accuracy": 0.17939849495887755,
|
|
"num_tokens": 12243931.0,
|
|
"step": 5485
|
|
},
|
|
{
|
|
"entropy": 5.749674463272095,
|
|
"epoch": 0.6166114449373842,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004971188820592656,
|
|
"loss": 5.6216,
|
|
"mean_token_accuracy": 0.17430118024349212,
|
|
"num_tokens": 12254821.0,
|
|
"step": 5490
|
|
},
|
|
{
|
|
"entropy": 5.601816129684448,
|
|
"epoch": 0.6171730218453417,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.000497112474082569,
|
|
"loss": 5.6144,
|
|
"mean_token_accuracy": 0.17476628869771957,
|
|
"num_tokens": 12265440.0,
|
|
"step": 5495
|
|
},
|
|
{
|
|
"entropy": 5.711391925811768,
|
|
"epoch": 0.6177345987532993,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.000497106059033725,
|
|
"loss": 5.6053,
|
|
"mean_token_accuracy": 0.16843282133340837,
|
|
"num_tokens": 12276636.0,
|
|
"step": 5500
|
|
},
|
|
{
|
|
"entropy": 5.67732515335083,
|
|
"epoch": 0.6182961756612568,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004970996369129381,
|
|
"loss": 5.4789,
|
|
"mean_token_accuracy": 0.18082829862833022,
|
|
"num_tokens": 12287404.0,
|
|
"step": 5505
|
|
},
|
|
{
|
|
"entropy": 5.600045490264892,
|
|
"epoch": 0.6188577525692144,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004970932077204125,
|
|
"loss": 5.7025,
|
|
"mean_token_accuracy": 0.16326996237039565,
|
|
"num_tokens": 12299283.0,
|
|
"step": 5510
|
|
},
|
|
{
|
|
"entropy": 5.662515306472779,
|
|
"epoch": 0.6194193294771719,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000497086771456353,
|
|
"loss": 5.6164,
|
|
"mean_token_accuracy": 0.16795926988124849,
|
|
"num_tokens": 12310281.0,
|
|
"step": 5515
|
|
},
|
|
{
|
|
"entropy": 5.72507610321045,
|
|
"epoch": 0.6199809063851295,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004970803281209646,
|
|
"loss": 5.6194,
|
|
"mean_token_accuracy": 0.17485337555408478,
|
|
"num_tokens": 12320839.0,
|
|
"step": 5520
|
|
},
|
|
{
|
|
"entropy": 5.595881175994873,
|
|
"epoch": 0.620542483293087,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004970738777144524,
|
|
"loss": 5.5838,
|
|
"mean_token_accuracy": 0.17471523135900496,
|
|
"num_tokens": 12332845.0,
|
|
"step": 5525
|
|
},
|
|
{
|
|
"entropy": 5.540711259841919,
|
|
"epoch": 0.6211040602010446,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004970674202370218,
|
|
"loss": 5.4885,
|
|
"mean_token_accuracy": 0.18502375334501267,
|
|
"num_tokens": 12343327.0,
|
|
"step": 5530
|
|
},
|
|
{
|
|
"entropy": 5.699438810348511,
|
|
"epoch": 0.621665637109002,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004970609556888785,
|
|
"loss": 5.606,
|
|
"mean_token_accuracy": 0.17476841658353806,
|
|
"num_tokens": 12353224.0,
|
|
"step": 5535
|
|
},
|
|
{
|
|
"entropy": 5.65339035987854,
|
|
"epoch": 0.6222272140169596,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004970544840702282,
|
|
"loss": 5.5214,
|
|
"mean_token_accuracy": 0.1761195182800293,
|
|
"num_tokens": 12363981.0,
|
|
"step": 5540
|
|
},
|
|
{
|
|
"entropy": 5.5299407005310055,
|
|
"epoch": 0.6227887909249171,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004970480053812771,
|
|
"loss": 5.5588,
|
|
"mean_token_accuracy": 0.18119494020938873,
|
|
"num_tokens": 12374769.0,
|
|
"step": 5545
|
|
},
|
|
{
|
|
"entropy": 5.797530746459961,
|
|
"epoch": 0.6233503678328747,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004970415196222312,
|
|
"loss": 5.7607,
|
|
"mean_token_accuracy": 0.1693173035979271,
|
|
"num_tokens": 12387247.0,
|
|
"step": 5550
|
|
},
|
|
{
|
|
"entropy": 5.794617938995361,
|
|
"epoch": 0.6239119447408322,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004970350267932973,
|
|
"loss": 5.6308,
|
|
"mean_token_accuracy": 0.17739299386739732,
|
|
"num_tokens": 12398347.0,
|
|
"step": 5555
|
|
},
|
|
{
|
|
"entropy": 5.495401000976562,
|
|
"epoch": 0.6244735216487898,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.000497028526894682,
|
|
"loss": 5.5179,
|
|
"mean_token_accuracy": 0.17569345086812974,
|
|
"num_tokens": 12409763.0,
|
|
"step": 5560
|
|
},
|
|
{
|
|
"entropy": 5.676819562911987,
|
|
"epoch": 0.6250350985567473,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004970220199265923,
|
|
"loss": 5.6119,
|
|
"mean_token_accuracy": 0.17253024280071258,
|
|
"num_tokens": 12420658.0,
|
|
"step": 5565
|
|
},
|
|
{
|
|
"entropy": 5.7752360820770265,
|
|
"epoch": 0.6255966754647049,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004970155058892354,
|
|
"loss": 5.7087,
|
|
"mean_token_accuracy": 0.16537702679634095,
|
|
"num_tokens": 12433959.0,
|
|
"step": 5570
|
|
},
|
|
{
|
|
"entropy": 5.6649754524230955,
|
|
"epoch": 0.6261582523726624,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004970089847828187,
|
|
"loss": 5.6856,
|
|
"mean_token_accuracy": 0.16697013080120088,
|
|
"num_tokens": 12444756.0,
|
|
"step": 5575
|
|
},
|
|
{
|
|
"entropy": 5.68948450088501,
|
|
"epoch": 0.62671982928062,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004970024566075497,
|
|
"loss": 5.6067,
|
|
"mean_token_accuracy": 0.17880495637655258,
|
|
"num_tokens": 12456114.0,
|
|
"step": 5580
|
|
},
|
|
{
|
|
"entropy": 5.708434152603149,
|
|
"epoch": 0.6272814061885775,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004969959213636365,
|
|
"loss": 5.6377,
|
|
"mean_token_accuracy": 0.17167994678020476,
|
|
"num_tokens": 12466927.0,
|
|
"step": 5585
|
|
},
|
|
{
|
|
"entropy": 5.707558822631836,
|
|
"epoch": 0.6278429830965351,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004969893790512871,
|
|
"loss": 5.683,
|
|
"mean_token_accuracy": 0.1643095552921295,
|
|
"num_tokens": 12477834.0,
|
|
"step": 5590
|
|
},
|
|
{
|
|
"entropy": 5.720361518859863,
|
|
"epoch": 0.6284045600044926,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004969828296707097,
|
|
"loss": 5.5766,
|
|
"mean_token_accuracy": 0.17566854059696196,
|
|
"num_tokens": 12488219.0,
|
|
"step": 5595
|
|
},
|
|
{
|
|
"entropy": 5.786182403564453,
|
|
"epoch": 0.6289661369124502,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004969762732221129,
|
|
"loss": 5.697,
|
|
"mean_token_accuracy": 0.17253458499908447,
|
|
"num_tokens": 12498947.0,
|
|
"step": 5600
|
|
},
|
|
{
|
|
"entropy": 5.611429262161255,
|
|
"epoch": 0.6295277138204077,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004969697097057054,
|
|
"loss": 5.5998,
|
|
"mean_token_accuracy": 0.17203421890735626,
|
|
"num_tokens": 12510142.0,
|
|
"step": 5605
|
|
},
|
|
{
|
|
"entropy": 5.736240100860596,
|
|
"epoch": 0.6300892907283653,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004969631391216964,
|
|
"loss": 5.6063,
|
|
"mean_token_accuracy": 0.17511310577392578,
|
|
"num_tokens": 12521350.0,
|
|
"step": 5610
|
|
},
|
|
{
|
|
"entropy": 5.482321262359619,
|
|
"epoch": 0.6306508676363228,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004969565614702948,
|
|
"loss": 5.4598,
|
|
"mean_token_accuracy": 0.17874122858047486,
|
|
"num_tokens": 12532579.0,
|
|
"step": 5615
|
|
},
|
|
{
|
|
"entropy": 5.71073546409607,
|
|
"epoch": 0.6312124445442804,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004969499767517104,
|
|
"loss": 5.5633,
|
|
"mean_token_accuracy": 0.17784105390310287,
|
|
"num_tokens": 12542885.0,
|
|
"step": 5620
|
|
},
|
|
{
|
|
"entropy": 5.781512451171875,
|
|
"epoch": 0.6317740214522379,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004969433849661525,
|
|
"loss": 5.7247,
|
|
"mean_token_accuracy": 0.1618916004896164,
|
|
"num_tokens": 12554881.0,
|
|
"step": 5625
|
|
},
|
|
{
|
|
"entropy": 5.7107549667358395,
|
|
"epoch": 0.6323355983601955,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004969367861138313,
|
|
"loss": 5.6733,
|
|
"mean_token_accuracy": 0.17335644364356995,
|
|
"num_tokens": 12564626.0,
|
|
"step": 5630
|
|
},
|
|
{
|
|
"entropy": 5.668147563934326,
|
|
"epoch": 0.6328971752681529,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004969301801949565,
|
|
"loss": 5.5281,
|
|
"mean_token_accuracy": 0.17630668729543686,
|
|
"num_tokens": 12576180.0,
|
|
"step": 5635
|
|
},
|
|
{
|
|
"entropy": 5.602819442749023,
|
|
"epoch": 0.6334587521761105,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.000496923567209739,
|
|
"loss": 5.6093,
|
|
"mean_token_accuracy": 0.17012349963188172,
|
|
"num_tokens": 12587487.0,
|
|
"step": 5640
|
|
},
|
|
{
|
|
"entropy": 5.788228225708008,
|
|
"epoch": 0.634020329084068,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004969169471583889,
|
|
"loss": 5.7522,
|
|
"mean_token_accuracy": 0.1662036031484604,
|
|
"num_tokens": 12598268.0,
|
|
"step": 5645
|
|
},
|
|
{
|
|
"entropy": 5.7226934909820555,
|
|
"epoch": 0.6345819059920256,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004969103200411171,
|
|
"loss": 5.6364,
|
|
"mean_token_accuracy": 0.17244216650724412,
|
|
"num_tokens": 12609287.0,
|
|
"step": 5650
|
|
},
|
|
{
|
|
"entropy": 5.6732985496521,
|
|
"epoch": 0.6351434828999831,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004969036858581346,
|
|
"loss": 5.5473,
|
|
"mean_token_accuracy": 0.17432162314653396,
|
|
"num_tokens": 12620317.0,
|
|
"step": 5655
|
|
},
|
|
{
|
|
"entropy": 5.707332944869995,
|
|
"epoch": 0.6357050598079407,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004968970446096527,
|
|
"loss": 5.6214,
|
|
"mean_token_accuracy": 0.17808055579662324,
|
|
"num_tokens": 12631420.0,
|
|
"step": 5660
|
|
},
|
|
{
|
|
"entropy": 5.649207353591919,
|
|
"epoch": 0.6362666367158982,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.000496890396295883,
|
|
"loss": 5.5638,
|
|
"mean_token_accuracy": 0.18193436712026595,
|
|
"num_tokens": 12641319.0,
|
|
"step": 5665
|
|
},
|
|
{
|
|
"entropy": 5.7742164611816404,
|
|
"epoch": 0.6368282136238558,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004968837409170368,
|
|
"loss": 5.662,
|
|
"mean_token_accuracy": 0.1652297332882881,
|
|
"num_tokens": 12651662.0,
|
|
"step": 5670
|
|
},
|
|
{
|
|
"entropy": 5.747282695770264,
|
|
"epoch": 0.6373897905318133,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004968770784733263,
|
|
"loss": 5.6885,
|
|
"mean_token_accuracy": 0.16822757571935654,
|
|
"num_tokens": 12663488.0,
|
|
"step": 5675
|
|
},
|
|
{
|
|
"entropy": 5.5741418361663815,
|
|
"epoch": 0.6379513674397709,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004968704089649636,
|
|
"loss": 5.6055,
|
|
"mean_token_accuracy": 0.17450159043073654,
|
|
"num_tokens": 12675848.0,
|
|
"step": 5680
|
|
},
|
|
{
|
|
"entropy": 5.722741222381591,
|
|
"epoch": 0.6385129443477284,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004968637323921611,
|
|
"loss": 5.5733,
|
|
"mean_token_accuracy": 0.17421268075704574,
|
|
"num_tokens": 12686541.0,
|
|
"step": 5685
|
|
},
|
|
{
|
|
"entropy": 5.654550075531006,
|
|
"epoch": 0.639074521255686,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004968570487551312,
|
|
"loss": 5.6068,
|
|
"mean_token_accuracy": 0.1739215910434723,
|
|
"num_tokens": 12698001.0,
|
|
"step": 5690
|
|
},
|
|
{
|
|
"entropy": 5.637372016906738,
|
|
"epoch": 0.6396360981636435,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004968503580540869,
|
|
"loss": 5.6182,
|
|
"mean_token_accuracy": 0.16848254203796387,
|
|
"num_tokens": 12709069.0,
|
|
"step": 5695
|
|
},
|
|
{
|
|
"entropy": 5.756517314910889,
|
|
"epoch": 0.6401976750716011,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004968436602892411,
|
|
"loss": 5.6112,
|
|
"mean_token_accuracy": 0.16800208687782286,
|
|
"num_tokens": 12719916.0,
|
|
"step": 5700
|
|
},
|
|
{
|
|
"entropy": 5.690023374557495,
|
|
"epoch": 0.6407592519795586,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004968369554608071,
|
|
"loss": 5.7296,
|
|
"mean_token_accuracy": 0.16412134766578673,
|
|
"num_tokens": 12732079.0,
|
|
"step": 5705
|
|
},
|
|
{
|
|
"entropy": 5.808725261688233,
|
|
"epoch": 0.6413208288875162,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004968302435689985,
|
|
"loss": 5.7081,
|
|
"mean_token_accuracy": 0.16667189449071884,
|
|
"num_tokens": 12742708.0,
|
|
"step": 5710
|
|
},
|
|
{
|
|
"entropy": 5.790198421478271,
|
|
"epoch": 0.6418824057954737,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004968235246140288,
|
|
"loss": 5.6479,
|
|
"mean_token_accuracy": 0.17510836720466613,
|
|
"num_tokens": 12753952.0,
|
|
"step": 5715
|
|
},
|
|
{
|
|
"entropy": 5.599614763259888,
|
|
"epoch": 0.6424439827034313,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004968167985961121,
|
|
"loss": 5.5645,
|
|
"mean_token_accuracy": 0.17351250052452089,
|
|
"num_tokens": 12765226.0,
|
|
"step": 5720
|
|
},
|
|
{
|
|
"entropy": 5.620680046081543,
|
|
"epoch": 0.6430055596113888,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004968100655154625,
|
|
"loss": 5.4919,
|
|
"mean_token_accuracy": 0.17808186560869216,
|
|
"num_tokens": 12776455.0,
|
|
"step": 5725
|
|
},
|
|
{
|
|
"entropy": 5.6246801853179935,
|
|
"epoch": 0.6435671365193463,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004968033253722943,
|
|
"loss": 5.5309,
|
|
"mean_token_accuracy": 0.17319415956735612,
|
|
"num_tokens": 12787054.0,
|
|
"step": 5730
|
|
},
|
|
{
|
|
"entropy": 5.650282096862793,
|
|
"epoch": 0.6441287134273038,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004967965781668223,
|
|
"loss": 5.6539,
|
|
"mean_token_accuracy": 0.17257371842861174,
|
|
"num_tokens": 12798223.0,
|
|
"step": 5735
|
|
},
|
|
{
|
|
"entropy": 5.737652349472046,
|
|
"epoch": 0.6446902903352614,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004967898238992613,
|
|
"loss": 5.5423,
|
|
"mean_token_accuracy": 0.17632485330104827,
|
|
"num_tokens": 12809388.0,
|
|
"step": 5740
|
|
},
|
|
{
|
|
"entropy": 5.639012813568115,
|
|
"epoch": 0.6452518672432189,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004967830625698262,
|
|
"loss": 5.6512,
|
|
"mean_token_accuracy": 0.17425873428583144,
|
|
"num_tokens": 12820116.0,
|
|
"step": 5745
|
|
},
|
|
{
|
|
"entropy": 5.621536827087402,
|
|
"epoch": 0.6458134441511765,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004967762941787323,
|
|
"loss": 5.5731,
|
|
"mean_token_accuracy": 0.18141271770000458,
|
|
"num_tokens": 12831590.0,
|
|
"step": 5750
|
|
},
|
|
{
|
|
"entropy": 5.7020574569702145,
|
|
"epoch": 0.646375021059134,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004967695187261952,
|
|
"loss": 5.7267,
|
|
"mean_token_accuracy": 0.16695149689912797,
|
|
"num_tokens": 12843510.0,
|
|
"step": 5755
|
|
},
|
|
{
|
|
"entropy": 5.727086067199707,
|
|
"epoch": 0.6469365979670916,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004967627362124306,
|
|
"loss": 5.5941,
|
|
"mean_token_accuracy": 0.17229423075914382,
|
|
"num_tokens": 12854907.0,
|
|
"step": 5760
|
|
},
|
|
{
|
|
"entropy": 5.631988191604615,
|
|
"epoch": 0.6474981748750491,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004967559466376546,
|
|
"loss": 5.557,
|
|
"mean_token_accuracy": 0.17227508127689362,
|
|
"num_tokens": 12865753.0,
|
|
"step": 5765
|
|
},
|
|
{
|
|
"entropy": 5.579543685913086,
|
|
"epoch": 0.6480597517830067,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004967491500020831,
|
|
"loss": 5.47,
|
|
"mean_token_accuracy": 0.17146981209516526,
|
|
"num_tokens": 12877116.0,
|
|
"step": 5770
|
|
},
|
|
{
|
|
"entropy": 5.496050834655762,
|
|
"epoch": 0.6486213286909642,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004967423463059328,
|
|
"loss": 5.4667,
|
|
"mean_token_accuracy": 0.17616490721702577,
|
|
"num_tokens": 12887685.0,
|
|
"step": 5775
|
|
},
|
|
{
|
|
"entropy": 5.647918558120727,
|
|
"epoch": 0.6491829055989218,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004967355355494201,
|
|
"loss": 5.6154,
|
|
"mean_token_accuracy": 0.17251012623310089,
|
|
"num_tokens": 12898519.0,
|
|
"step": 5780
|
|
},
|
|
{
|
|
"entropy": 5.687884330749512,
|
|
"epoch": 0.6497444825068793,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.000496728717732762,
|
|
"loss": 5.5528,
|
|
"mean_token_accuracy": 0.17906497567892074,
|
|
"num_tokens": 12908400.0,
|
|
"step": 5785
|
|
},
|
|
{
|
|
"entropy": 5.572654962539673,
|
|
"epoch": 0.6503060594148369,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004967218928561755,
|
|
"loss": 5.5179,
|
|
"mean_token_accuracy": 0.17277845591306687,
|
|
"num_tokens": 12919159.0,
|
|
"step": 5790
|
|
},
|
|
{
|
|
"entropy": 5.598859167098999,
|
|
"epoch": 0.6508676363227944,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004967150609198779,
|
|
"loss": 5.4793,
|
|
"mean_token_accuracy": 0.18125012367963791,
|
|
"num_tokens": 12929838.0,
|
|
"step": 5795
|
|
},
|
|
{
|
|
"entropy": 5.678771162033081,
|
|
"epoch": 0.651429213230752,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004967082219240869,
|
|
"loss": 5.6225,
|
|
"mean_token_accuracy": 0.1733581766486168,
|
|
"num_tokens": 12939976.0,
|
|
"step": 5800
|
|
},
|
|
{
|
|
"entropy": 5.659549808502197,
|
|
"epoch": 0.6519907901387095,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004967013758690199,
|
|
"loss": 5.6054,
|
|
"mean_token_accuracy": 0.17625022381544114,
|
|
"num_tokens": 12950493.0,
|
|
"step": 5805
|
|
},
|
|
{
|
|
"entropy": 5.595048475265503,
|
|
"epoch": 0.6525523670466671,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004966945227548953,
|
|
"loss": 5.5767,
|
|
"mean_token_accuracy": 0.17267046123743057,
|
|
"num_tokens": 12961267.0,
|
|
"step": 5810
|
|
},
|
|
{
|
|
"entropy": 5.653221082687378,
|
|
"epoch": 0.6531139439546246,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004966876625819309,
|
|
"loss": 5.6155,
|
|
"mean_token_accuracy": 0.1685887962579727,
|
|
"num_tokens": 12972720.0,
|
|
"step": 5815
|
|
},
|
|
{
|
|
"entropy": 5.764229726791382,
|
|
"epoch": 0.6536755208625822,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004966807953503456,
|
|
"loss": 5.7041,
|
|
"mean_token_accuracy": 0.1689188852906227,
|
|
"num_tokens": 12984025.0,
|
|
"step": 5820
|
|
},
|
|
{
|
|
"entropy": 5.653743600845337,
|
|
"epoch": 0.6542370977705396,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004966739210603578,
|
|
"loss": 5.5791,
|
|
"mean_token_accuracy": 0.18255457282066345,
|
|
"num_tokens": 12994422.0,
|
|
"step": 5825
|
|
},
|
|
{
|
|
"entropy": 5.69578709602356,
|
|
"epoch": 0.6547986746784972,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004966670397121862,
|
|
"loss": 5.7342,
|
|
"mean_token_accuracy": 0.1653668463230133,
|
|
"num_tokens": 13005040.0,
|
|
"step": 5830
|
|
},
|
|
{
|
|
"entropy": 5.631675720214844,
|
|
"epoch": 0.6553602515864547,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004966601513060502,
|
|
"loss": 5.4872,
|
|
"mean_token_accuracy": 0.1735595166683197,
|
|
"num_tokens": 13015720.0,
|
|
"step": 5835
|
|
},
|
|
{
|
|
"entropy": 5.664030075073242,
|
|
"epoch": 0.6559218284944123,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.000496653255842169,
|
|
"loss": 5.456,
|
|
"mean_token_accuracy": 0.17706273645162582,
|
|
"num_tokens": 13026269.0,
|
|
"step": 5840
|
|
},
|
|
{
|
|
"entropy": 5.587836980819702,
|
|
"epoch": 0.6564834054023698,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004966463533207621,
|
|
"loss": 5.6411,
|
|
"mean_token_accuracy": 0.16916483342647554,
|
|
"num_tokens": 13037102.0,
|
|
"step": 5845
|
|
},
|
|
{
|
|
"entropy": 5.565196752548218,
|
|
"epoch": 0.6570449823103274,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004966394437420493,
|
|
"loss": 5.4987,
|
|
"mean_token_accuracy": 0.1794200822710991,
|
|
"num_tokens": 13047149.0,
|
|
"step": 5850
|
|
},
|
|
{
|
|
"entropy": 5.635978364944458,
|
|
"epoch": 0.6576065592182849,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004966325271062508,
|
|
"loss": 5.5227,
|
|
"mean_token_accuracy": 0.1787479981780052,
|
|
"num_tokens": 13058196.0,
|
|
"step": 5855
|
|
},
|
|
{
|
|
"entropy": 5.579664039611816,
|
|
"epoch": 0.6581681361262425,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004966256034135866,
|
|
"loss": 5.5295,
|
|
"mean_token_accuracy": 0.1742333471775055,
|
|
"num_tokens": 13067897.0,
|
|
"step": 5860
|
|
},
|
|
{
|
|
"entropy": 5.698275136947632,
|
|
"epoch": 0.6587297130342,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004966186726642772,
|
|
"loss": 5.635,
|
|
"mean_token_accuracy": 0.17574080675840378,
|
|
"num_tokens": 13079720.0,
|
|
"step": 5865
|
|
},
|
|
{
|
|
"entropy": 5.574722671508789,
|
|
"epoch": 0.6592912899421576,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004966117348585434,
|
|
"loss": 5.4888,
|
|
"mean_token_accuracy": 0.16819144785404205,
|
|
"num_tokens": 13090995.0,
|
|
"step": 5870
|
|
},
|
|
{
|
|
"entropy": 5.54297103881836,
|
|
"epoch": 0.6598528668501151,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004966047899966059,
|
|
"loss": 5.5265,
|
|
"mean_token_accuracy": 0.1767219915986061,
|
|
"num_tokens": 13101945.0,
|
|
"step": 5875
|
|
},
|
|
{
|
|
"entropy": 5.61340446472168,
|
|
"epoch": 0.6604144437580727,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.000496597838078686,
|
|
"loss": 5.4911,
|
|
"mean_token_accuracy": 0.17884684056043626,
|
|
"num_tokens": 13112869.0,
|
|
"step": 5880
|
|
},
|
|
{
|
|
"entropy": 5.620800542831421,
|
|
"epoch": 0.6609760206660302,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.000496590879105005,
|
|
"loss": 5.5668,
|
|
"mean_token_accuracy": 0.1711410477757454,
|
|
"num_tokens": 13123242.0,
|
|
"step": 5885
|
|
},
|
|
{
|
|
"entropy": 5.754458475112915,
|
|
"epoch": 0.6615375975739878,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004965839130757845,
|
|
"loss": 5.6847,
|
|
"mean_token_accuracy": 0.15932814925909042,
|
|
"num_tokens": 13133981.0,
|
|
"step": 5890
|
|
},
|
|
{
|
|
"entropy": 5.641813087463379,
|
|
"epoch": 0.6620991744819453,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004965769399912462,
|
|
"loss": 5.6335,
|
|
"mean_token_accuracy": 0.16635715514421462,
|
|
"num_tokens": 13144696.0,
|
|
"step": 5895
|
|
},
|
|
{
|
|
"entropy": 5.699152851104737,
|
|
"epoch": 0.6626607513899029,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004965699598516122,
|
|
"loss": 5.6927,
|
|
"mean_token_accuracy": 0.1730930507183075,
|
|
"num_tokens": 13156674.0,
|
|
"step": 5900
|
|
},
|
|
{
|
|
"entropy": 5.7478724956512455,
|
|
"epoch": 0.6632223282978604,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004965629726571047,
|
|
"loss": 5.5338,
|
|
"mean_token_accuracy": 0.17766428291797637,
|
|
"num_tokens": 13167757.0,
|
|
"step": 5905
|
|
},
|
|
{
|
|
"entropy": 5.621576976776123,
|
|
"epoch": 0.663783905205818,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004965559784079463,
|
|
"loss": 5.6222,
|
|
"mean_token_accuracy": 0.1702948644757271,
|
|
"num_tokens": 13177701.0,
|
|
"step": 5910
|
|
},
|
|
{
|
|
"entropy": 5.676689195632934,
|
|
"epoch": 0.6643454821137755,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004965489771043596,
|
|
"loss": 5.6425,
|
|
"mean_token_accuracy": 0.1648521825671196,
|
|
"num_tokens": 13189840.0,
|
|
"step": 5915
|
|
},
|
|
{
|
|
"entropy": 5.583516311645508,
|
|
"epoch": 0.664907059021733,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004965419687465676,
|
|
"loss": 5.4456,
|
|
"mean_token_accuracy": 0.17676418423652648,
|
|
"num_tokens": 13200206.0,
|
|
"step": 5920
|
|
},
|
|
{
|
|
"entropy": 5.599092197418213,
|
|
"epoch": 0.6654686359296905,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004965349533347934,
|
|
"loss": 5.5445,
|
|
"mean_token_accuracy": 0.1835288867354393,
|
|
"num_tokens": 13211474.0,
|
|
"step": 5925
|
|
},
|
|
{
|
|
"entropy": 5.670661783218383,
|
|
"epoch": 0.6660302128376481,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004965279308692602,
|
|
"loss": 5.6273,
|
|
"mean_token_accuracy": 0.18714107125997542,
|
|
"num_tokens": 13223337.0,
|
|
"step": 5930
|
|
},
|
|
{
|
|
"entropy": 5.759874725341797,
|
|
"epoch": 0.6665917897456056,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004965209013501919,
|
|
"loss": 5.6771,
|
|
"mean_token_accuracy": 0.17174635380506514,
|
|
"num_tokens": 13234977.0,
|
|
"step": 5935
|
|
},
|
|
{
|
|
"entropy": 5.7041192054748535,
|
|
"epoch": 0.6671533666535632,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004965138647778122,
|
|
"loss": 5.6458,
|
|
"mean_token_accuracy": 0.17671692371368408,
|
|
"num_tokens": 13245315.0,
|
|
"step": 5940
|
|
},
|
|
{
|
|
"entropy": 5.615558910369873,
|
|
"epoch": 0.6677149435615207,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.000496506821152345,
|
|
"loss": 5.5231,
|
|
"mean_token_accuracy": 0.1777236580848694,
|
|
"num_tokens": 13255829.0,
|
|
"step": 5945
|
|
},
|
|
{
|
|
"entropy": 5.563561296463012,
|
|
"epoch": 0.6682765204694783,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004964997704740147,
|
|
"loss": 5.5983,
|
|
"mean_token_accuracy": 0.17270694375038148,
|
|
"num_tokens": 13266964.0,
|
|
"step": 5950
|
|
},
|
|
{
|
|
"entropy": 5.757982492446899,
|
|
"epoch": 0.6688380973774358,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.000496492712743046,
|
|
"loss": 5.6345,
|
|
"mean_token_accuracy": 0.17003155946731568,
|
|
"num_tokens": 13279416.0,
|
|
"step": 5955
|
|
},
|
|
{
|
|
"entropy": 5.692528820037841,
|
|
"epoch": 0.6693996742853934,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004964856479596632,
|
|
"loss": 5.6564,
|
|
"mean_token_accuracy": 0.170363450050354,
|
|
"num_tokens": 13290633.0,
|
|
"step": 5960
|
|
},
|
|
{
|
|
"entropy": 5.66019229888916,
|
|
"epoch": 0.6699612511933509,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004964785761240915,
|
|
"loss": 5.543,
|
|
"mean_token_accuracy": 0.17228578329086303,
|
|
"num_tokens": 13302236.0,
|
|
"step": 5965
|
|
},
|
|
{
|
|
"entropy": 5.694251203536988,
|
|
"epoch": 0.6705228281013085,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004964714972365562,
|
|
"loss": 5.6259,
|
|
"mean_token_accuracy": 0.17424766719341278,
|
|
"num_tokens": 13315356.0,
|
|
"step": 5970
|
|
},
|
|
{
|
|
"entropy": 5.51495590209961,
|
|
"epoch": 0.671084405009266,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004964644112972824,
|
|
"loss": 5.5024,
|
|
"mean_token_accuracy": 0.17342642247676848,
|
|
"num_tokens": 13326037.0,
|
|
"step": 5975
|
|
},
|
|
{
|
|
"entropy": 5.599312210083008,
|
|
"epoch": 0.6716459819172236,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004964573183064959,
|
|
"loss": 5.5732,
|
|
"mean_token_accuracy": 0.17227093875408173,
|
|
"num_tokens": 13336278.0,
|
|
"step": 5980
|
|
},
|
|
{
|
|
"entropy": 5.717516326904297,
|
|
"epoch": 0.6722075588251811,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004964502182644225,
|
|
"loss": 5.6631,
|
|
"mean_token_accuracy": 0.17465528398752211,
|
|
"num_tokens": 13348147.0,
|
|
"step": 5985
|
|
},
|
|
{
|
|
"entropy": 5.62519588470459,
|
|
"epoch": 0.6727691357331387,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004964431111712883,
|
|
"loss": 5.6203,
|
|
"mean_token_accuracy": 0.16747196167707443,
|
|
"num_tokens": 13360181.0,
|
|
"step": 5990
|
|
},
|
|
{
|
|
"entropy": 5.726006364822387,
|
|
"epoch": 0.6733307126410962,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004964359970273195,
|
|
"loss": 5.6981,
|
|
"mean_token_accuracy": 0.16642380952835084,
|
|
"num_tokens": 13372258.0,
|
|
"step": 5995
|
|
},
|
|
{
|
|
"entropy": 5.691050386428833,
|
|
"epoch": 0.6738922895490538,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004964288758327426,
|
|
"loss": 5.6053,
|
|
"mean_token_accuracy": 0.167339289188385,
|
|
"num_tokens": 13384332.0,
|
|
"step": 6000
|
|
},
|
|
{
|
|
"epoch": 0.6738922895490538,
|
|
"eval_entropy": 5.532601383318445,
|
|
"eval_loss": 5.626047611236572,
|
|
"eval_mean_token_accuracy": 0.17870768900554235,
|
|
"eval_num_tokens": 13384332.0,
|
|
"eval_runtime": 23.6926,
|
|
"eval_samples_per_second": 1308.974,
|
|
"eval_steps_per_second": 163.638,
|
|
"step": 6000
|
|
},
|
|
{
|
|
"entropy": 5.671579360961914,
|
|
"epoch": 0.6744538664570113,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004964217475877846,
|
|
"loss": 5.5892,
|
|
"mean_token_accuracy": 0.1686641350388527,
|
|
"num_tokens": 13396345.0,
|
|
"step": 6005
|
|
},
|
|
{
|
|
"entropy": 5.565827560424805,
|
|
"epoch": 0.6750154433649689,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.000496414612292672,
|
|
"loss": 5.4306,
|
|
"mean_token_accuracy": 0.17658377736806868,
|
|
"num_tokens": 13407325.0,
|
|
"step": 6010
|
|
},
|
|
{
|
|
"entropy": 5.641993141174316,
|
|
"epoch": 0.6755770202729264,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004964074699476325,
|
|
"loss": 5.5657,
|
|
"mean_token_accuracy": 0.1769910454750061,
|
|
"num_tokens": 13417476.0,
|
|
"step": 6015
|
|
},
|
|
{
|
|
"entropy": 5.610236787796021,
|
|
"epoch": 0.6761385971808839,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004964003205528933,
|
|
"loss": 5.5942,
|
|
"mean_token_accuracy": 0.1738465040922165,
|
|
"num_tokens": 13428792.0,
|
|
"step": 6020
|
|
},
|
|
{
|
|
"entropy": 5.671332788467407,
|
|
"epoch": 0.6767001740888414,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004963931641086819,
|
|
"loss": 5.6357,
|
|
"mean_token_accuracy": 0.17450349926948547,
|
|
"num_tokens": 13440043.0,
|
|
"step": 6025
|
|
},
|
|
{
|
|
"entropy": 5.730217218399048,
|
|
"epoch": 0.677261750996799,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.0004963860006152262,
|
|
"loss": 5.6036,
|
|
"mean_token_accuracy": 0.17270937263965608,
|
|
"num_tokens": 13451637.0,
|
|
"step": 6030
|
|
},
|
|
{
|
|
"entropy": 5.8008123397827145,
|
|
"epoch": 0.6778233279047565,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004963788300727546,
|
|
"loss": 5.5751,
|
|
"mean_token_accuracy": 0.17561036795377732,
|
|
"num_tokens": 13463205.0,
|
|
"step": 6035
|
|
},
|
|
{
|
|
"entropy": 5.631853675842285,
|
|
"epoch": 0.6783849048127141,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004963716524814951,
|
|
"loss": 5.6141,
|
|
"mean_token_accuracy": 0.17544583976268768,
|
|
"num_tokens": 13474201.0,
|
|
"step": 6040
|
|
},
|
|
{
|
|
"entropy": 5.584092998504639,
|
|
"epoch": 0.6789464817206716,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004963644678416763,
|
|
"loss": 5.5182,
|
|
"mean_token_accuracy": 0.17484917789697646,
|
|
"num_tokens": 13485439.0,
|
|
"step": 6045
|
|
},
|
|
{
|
|
"entropy": 5.69404616355896,
|
|
"epoch": 0.6795080586286292,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000496357276153527,
|
|
"loss": 5.7123,
|
|
"mean_token_accuracy": 0.16630343794822694,
|
|
"num_tokens": 13497257.0,
|
|
"step": 6050
|
|
},
|
|
{
|
|
"entropy": 5.680776309967041,
|
|
"epoch": 0.6800696355365867,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004963500774172763,
|
|
"loss": 5.5578,
|
|
"mean_token_accuracy": 0.17639838308095931,
|
|
"num_tokens": 13508689.0,
|
|
"step": 6055
|
|
},
|
|
{
|
|
"entropy": 5.659711933135986,
|
|
"epoch": 0.6806312124445443,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.000496342871633153,
|
|
"loss": 5.522,
|
|
"mean_token_accuracy": 0.1836621195077896,
|
|
"num_tokens": 13519392.0,
|
|
"step": 6060
|
|
},
|
|
{
|
|
"entropy": 5.604054117202759,
|
|
"epoch": 0.6811927893525018,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004963356588013871,
|
|
"loss": 5.5638,
|
|
"mean_token_accuracy": 0.17962913662195207,
|
|
"num_tokens": 13530503.0,
|
|
"step": 6065
|
|
},
|
|
{
|
|
"entropy": 5.647364234924316,
|
|
"epoch": 0.6817543662604594,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004963284389222078,
|
|
"loss": 5.6504,
|
|
"mean_token_accuracy": 0.17519838213920594,
|
|
"num_tokens": 13541668.0,
|
|
"step": 6070
|
|
},
|
|
{
|
|
"entropy": 5.655250120162964,
|
|
"epoch": 0.6823159431684169,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004963212119958453,
|
|
"loss": 5.4839,
|
|
"mean_token_accuracy": 0.17619259804487228,
|
|
"num_tokens": 13552692.0,
|
|
"step": 6075
|
|
},
|
|
{
|
|
"entropy": 5.570859432220459,
|
|
"epoch": 0.6828775200763745,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004963139780225295,
|
|
"loss": 5.5786,
|
|
"mean_token_accuracy": 0.17264179289340972,
|
|
"num_tokens": 13563813.0,
|
|
"step": 6080
|
|
},
|
|
{
|
|
"entropy": 5.62108883857727,
|
|
"epoch": 0.683439096984332,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004963067370024909,
|
|
"loss": 5.5209,
|
|
"mean_token_accuracy": 0.17658937573432923,
|
|
"num_tokens": 13573818.0,
|
|
"step": 6085
|
|
},
|
|
{
|
|
"entropy": 5.723570108413696,
|
|
"epoch": 0.6840006738922896,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.0004962994889359598,
|
|
"loss": 5.6471,
|
|
"mean_token_accuracy": 0.16989783197641373,
|
|
"num_tokens": 13585416.0,
|
|
"step": 6090
|
|
},
|
|
{
|
|
"entropy": 5.621691656112671,
|
|
"epoch": 0.6845622508002471,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.0004962922338231673,
|
|
"loss": 5.5493,
|
|
"mean_token_accuracy": 0.17433664649724961,
|
|
"num_tokens": 13596645.0,
|
|
"step": 6095
|
|
},
|
|
{
|
|
"entropy": 5.6432146549224855,
|
|
"epoch": 0.6851238277082047,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004962849716643441,
|
|
"loss": 5.4878,
|
|
"mean_token_accuracy": 0.175603224337101,
|
|
"num_tokens": 13607206.0,
|
|
"step": 6100
|
|
},
|
|
{
|
|
"entropy": 5.684325551986694,
|
|
"epoch": 0.6856854046161622,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004962777024597216,
|
|
"loss": 5.7015,
|
|
"mean_token_accuracy": 0.16782047748565673,
|
|
"num_tokens": 13619418.0,
|
|
"step": 6105
|
|
},
|
|
{
|
|
"entropy": 5.657474613189697,
|
|
"epoch": 0.6862469815241198,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004962704262095314,
|
|
"loss": 5.4912,
|
|
"mean_token_accuracy": 0.1779582068324089,
|
|
"num_tokens": 13630098.0,
|
|
"step": 6110
|
|
},
|
|
{
|
|
"entropy": 5.643915796279908,
|
|
"epoch": 0.6868085584320772,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004962631429140048,
|
|
"loss": 5.6176,
|
|
"mean_token_accuracy": 0.17652909606695175,
|
|
"num_tokens": 13641401.0,
|
|
"step": 6115
|
|
},
|
|
{
|
|
"entropy": 5.62016716003418,
|
|
"epoch": 0.6873701353400348,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.000496255852573374,
|
|
"loss": 5.5914,
|
|
"mean_token_accuracy": 0.16748359501361848,
|
|
"num_tokens": 13653099.0,
|
|
"step": 6120
|
|
},
|
|
{
|
|
"entropy": 5.754742240905761,
|
|
"epoch": 0.6879317122479923,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004962485551878711,
|
|
"loss": 5.606,
|
|
"mean_token_accuracy": 0.16977982074022294,
|
|
"num_tokens": 13665381.0,
|
|
"step": 6125
|
|
},
|
|
{
|
|
"entropy": 5.6740623950958256,
|
|
"epoch": 0.6884932891559499,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004962412507577283,
|
|
"loss": 5.5911,
|
|
"mean_token_accuracy": 0.17530799210071563,
|
|
"num_tokens": 13676767.0,
|
|
"step": 6130
|
|
},
|
|
{
|
|
"entropy": 5.611109638214112,
|
|
"epoch": 0.6890548660639074,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004962339392831783,
|
|
"loss": 5.5921,
|
|
"mean_token_accuracy": 0.1735776200890541,
|
|
"num_tokens": 13688552.0,
|
|
"step": 6135
|
|
},
|
|
{
|
|
"entropy": 5.67639684677124,
|
|
"epoch": 0.689616442971865,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.000496226620764454,
|
|
"loss": 5.5678,
|
|
"mean_token_accuracy": 0.16896845996379853,
|
|
"num_tokens": 13700160.0,
|
|
"step": 6140
|
|
},
|
|
{
|
|
"entropy": 5.687887811660767,
|
|
"epoch": 0.6901780198798225,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.000496219295201788,
|
|
"loss": 5.5711,
|
|
"mean_token_accuracy": 0.17359737306833267,
|
|
"num_tokens": 13710828.0,
|
|
"step": 6145
|
|
},
|
|
{
|
|
"entropy": 5.6879595756530765,
|
|
"epoch": 0.6907395967877801,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004962119625954141,
|
|
"loss": 5.6813,
|
|
"mean_token_accuracy": 0.16563436836004258,
|
|
"num_tokens": 13721912.0,
|
|
"step": 6150
|
|
},
|
|
{
|
|
"entropy": 5.711553955078125,
|
|
"epoch": 0.6913011736957376,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.0004962046229455653,
|
|
"loss": 5.7096,
|
|
"mean_token_accuracy": 0.16787867695093156,
|
|
"num_tokens": 13733662.0,
|
|
"step": 6155
|
|
},
|
|
{
|
|
"entropy": 5.689278268814087,
|
|
"epoch": 0.6918627506036952,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004961972762524757,
|
|
"loss": 5.5264,
|
|
"mean_token_accuracy": 0.1785564512014389,
|
|
"num_tokens": 13743699.0,
|
|
"step": 6160
|
|
},
|
|
{
|
|
"entropy": 5.599921655654907,
|
|
"epoch": 0.6924243275116527,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.000496189922516379,
|
|
"loss": 5.5251,
|
|
"mean_token_accuracy": 0.17855373322963713,
|
|
"num_tokens": 13754918.0,
|
|
"step": 6165
|
|
},
|
|
{
|
|
"entropy": 5.6636881828308105,
|
|
"epoch": 0.6929859044196103,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004961825617375093,
|
|
"loss": 5.5559,
|
|
"mean_token_accuracy": 0.18213798403739928,
|
|
"num_tokens": 13764432.0,
|
|
"step": 6170
|
|
},
|
|
{
|
|
"entropy": 5.573491191864013,
|
|
"epoch": 0.6935474813275678,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004961751939161011,
|
|
"loss": 5.4867,
|
|
"mean_token_accuracy": 0.17127821147441863,
|
|
"num_tokens": 13777049.0,
|
|
"step": 6175
|
|
},
|
|
{
|
|
"entropy": 5.617477607727051,
|
|
"epoch": 0.6941090582355254,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.000496167819052389,
|
|
"loss": 5.5861,
|
|
"mean_token_accuracy": 0.17270912528038024,
|
|
"num_tokens": 13788324.0,
|
|
"step": 6180
|
|
},
|
|
{
|
|
"entropy": 5.745663785934449,
|
|
"epoch": 0.6946706351434829,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004961604371466077,
|
|
"loss": 5.6771,
|
|
"mean_token_accuracy": 0.1689326748251915,
|
|
"num_tokens": 13800443.0,
|
|
"step": 6185
|
|
},
|
|
{
|
|
"entropy": 5.7633007049560545,
|
|
"epoch": 0.6952322120514405,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004961530481989923,
|
|
"loss": 5.7149,
|
|
"mean_token_accuracy": 0.17268342524766922,
|
|
"num_tokens": 13811982.0,
|
|
"step": 6190
|
|
},
|
|
{
|
|
"entropy": 5.623760461807251,
|
|
"epoch": 0.695793788959398,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004961456522097782,
|
|
"loss": 5.4827,
|
|
"mean_token_accuracy": 0.18210517019033431,
|
|
"num_tokens": 13822005.0,
|
|
"step": 6195
|
|
},
|
|
{
|
|
"entropy": 5.581566524505615,
|
|
"epoch": 0.6963553658673556,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004961382491792006,
|
|
"loss": 5.5203,
|
|
"mean_token_accuracy": 0.17446937412023544,
|
|
"num_tokens": 13831943.0,
|
|
"step": 6200
|
|
},
|
|
{
|
|
"entropy": 5.749774646759033,
|
|
"epoch": 0.6969169427753131,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004961308391074953,
|
|
"loss": 5.7079,
|
|
"mean_token_accuracy": 0.16813873499631882,
|
|
"num_tokens": 13842517.0,
|
|
"step": 6205
|
|
},
|
|
{
|
|
"entropy": 5.720541095733642,
|
|
"epoch": 0.6974785196832706,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004961234219948986,
|
|
"loss": 5.5941,
|
|
"mean_token_accuracy": 0.1731325715780258,
|
|
"num_tokens": 13853636.0,
|
|
"step": 6210
|
|
},
|
|
{
|
|
"entropy": 5.690590953826904,
|
|
"epoch": 0.6980400965912281,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004961159978416461,
|
|
"loss": 5.4992,
|
|
"mean_token_accuracy": 0.17299422025680541,
|
|
"num_tokens": 13864378.0,
|
|
"step": 6215
|
|
},
|
|
{
|
|
"entropy": 5.713303709030152,
|
|
"epoch": 0.6986016734991857,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004961085666479746,
|
|
"loss": 5.5556,
|
|
"mean_token_accuracy": 0.1790371745824814,
|
|
"num_tokens": 13874964.0,
|
|
"step": 6220
|
|
},
|
|
{
|
|
"entropy": 5.598604440689087,
|
|
"epoch": 0.6991632504071432,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004961011284141206,
|
|
"loss": 5.5165,
|
|
"mean_token_accuracy": 0.1740249678492546,
|
|
"num_tokens": 13885852.0,
|
|
"step": 6225
|
|
},
|
|
{
|
|
"entropy": 5.5999308109283445,
|
|
"epoch": 0.6997248273151008,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004960936831403209,
|
|
"loss": 5.5772,
|
|
"mean_token_accuracy": 0.17389026731252671,
|
|
"num_tokens": 13896101.0,
|
|
"step": 6230
|
|
},
|
|
{
|
|
"entropy": 5.692754793167114,
|
|
"epoch": 0.7002864042230583,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004960862308268126,
|
|
"loss": 5.476,
|
|
"mean_token_accuracy": 0.18120343387126922,
|
|
"num_tokens": 13907129.0,
|
|
"step": 6235
|
|
},
|
|
{
|
|
"entropy": 5.672752523422242,
|
|
"epoch": 0.7008479811310159,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004960787714738329,
|
|
"loss": 5.6655,
|
|
"mean_token_accuracy": 0.17421342730522155,
|
|
"num_tokens": 13918662.0,
|
|
"step": 6240
|
|
},
|
|
{
|
|
"entropy": 5.624834775924683,
|
|
"epoch": 0.7014095580389734,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004960713050816194,
|
|
"loss": 5.6282,
|
|
"mean_token_accuracy": 0.17071471959352494,
|
|
"num_tokens": 13930717.0,
|
|
"step": 6245
|
|
},
|
|
{
|
|
"entropy": 5.649770259857178,
|
|
"epoch": 0.701971134946931,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004960638316504098,
|
|
"loss": 5.5122,
|
|
"mean_token_accuracy": 0.17426857799291612,
|
|
"num_tokens": 13941299.0,
|
|
"step": 6250
|
|
},
|
|
{
|
|
"entropy": 5.767297792434692,
|
|
"epoch": 0.7025327118548885,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004960563511804421,
|
|
"loss": 5.5899,
|
|
"mean_token_accuracy": 0.17348022907972335,
|
|
"num_tokens": 13951807.0,
|
|
"step": 6255
|
|
},
|
|
{
|
|
"entropy": 5.643262004852295,
|
|
"epoch": 0.7030942887628461,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004960488636719545,
|
|
"loss": 5.4954,
|
|
"mean_token_accuracy": 0.17652663141489028,
|
|
"num_tokens": 13962994.0,
|
|
"step": 6260
|
|
},
|
|
{
|
|
"entropy": 5.538077116012573,
|
|
"epoch": 0.7036558656708036,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004960413691251852,
|
|
"loss": 5.5278,
|
|
"mean_token_accuracy": 0.17574441879987718,
|
|
"num_tokens": 13973731.0,
|
|
"step": 6265
|
|
},
|
|
{
|
|
"entropy": 5.670338439941406,
|
|
"epoch": 0.7042174425787612,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004960338675403731,
|
|
"loss": 5.5905,
|
|
"mean_token_accuracy": 0.1732581928372383,
|
|
"num_tokens": 13983772.0,
|
|
"step": 6270
|
|
},
|
|
{
|
|
"entropy": 5.681479978561401,
|
|
"epoch": 0.7047790194867187,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004960263589177568,
|
|
"loss": 5.6011,
|
|
"mean_token_accuracy": 0.17718179821968078,
|
|
"num_tokens": 13994935.0,
|
|
"step": 6275
|
|
},
|
|
{
|
|
"entropy": 5.666521310806274,
|
|
"epoch": 0.7053405963946763,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.0004960188432575757,
|
|
"loss": 5.5539,
|
|
"mean_token_accuracy": 0.18053411543369294,
|
|
"num_tokens": 14006225.0,
|
|
"step": 6280
|
|
},
|
|
{
|
|
"entropy": 5.6680680274963375,
|
|
"epoch": 0.7059021733026338,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004960113205600688,
|
|
"loss": 5.5814,
|
|
"mean_token_accuracy": 0.18225925415754318,
|
|
"num_tokens": 14017693.0,
|
|
"step": 6285
|
|
},
|
|
{
|
|
"entropy": 5.633757448196411,
|
|
"epoch": 0.7064637502105914,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.0004960037908254757,
|
|
"loss": 5.5464,
|
|
"mean_token_accuracy": 0.17420191317796707,
|
|
"num_tokens": 14027264.0,
|
|
"step": 6290
|
|
},
|
|
{
|
|
"entropy": 5.6471082210540775,
|
|
"epoch": 0.7070253271185489,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004959962540540361,
|
|
"loss": 5.6514,
|
|
"mean_token_accuracy": 0.1764003425836563,
|
|
"num_tokens": 14039422.0,
|
|
"step": 6295
|
|
},
|
|
{
|
|
"entropy": 5.681409168243408,
|
|
"epoch": 0.7075869040265065,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004959887102459903,
|
|
"loss": 5.572,
|
|
"mean_token_accuracy": 0.1713883399963379,
|
|
"num_tokens": 14051619.0,
|
|
"step": 6300
|
|
},
|
|
{
|
|
"entropy": 5.546450853347778,
|
|
"epoch": 0.7081484809344639,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004959811594015781,
|
|
"loss": 5.5685,
|
|
"mean_token_accuracy": 0.16898404508829118,
|
|
"num_tokens": 14061752.0,
|
|
"step": 6305
|
|
},
|
|
{
|
|
"entropy": 5.625461530685425,
|
|
"epoch": 0.7087100578424215,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004959736015210401,
|
|
"loss": 5.52,
|
|
"mean_token_accuracy": 0.17708743810653688,
|
|
"num_tokens": 14072931.0,
|
|
"step": 6310
|
|
},
|
|
{
|
|
"entropy": 5.6599406719207765,
|
|
"epoch": 0.709271634750379,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004959660366046169,
|
|
"loss": 5.6033,
|
|
"mean_token_accuracy": 0.18181025236845016,
|
|
"num_tokens": 14084137.0,
|
|
"step": 6315
|
|
},
|
|
{
|
|
"entropy": 5.703351354598999,
|
|
"epoch": 0.7098332116583366,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004959584646525494,
|
|
"loss": 5.6038,
|
|
"mean_token_accuracy": 0.1693190410733223,
|
|
"num_tokens": 14096251.0,
|
|
"step": 6320
|
|
},
|
|
{
|
|
"entropy": 5.749358987808227,
|
|
"epoch": 0.7103947885662941,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004959508856650788,
|
|
"loss": 5.7173,
|
|
"mean_token_accuracy": 0.16368509382009505,
|
|
"num_tokens": 14107844.0,
|
|
"step": 6325
|
|
},
|
|
{
|
|
"entropy": 5.677271127700806,
|
|
"epoch": 0.7109563654742517,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004959432996424463,
|
|
"loss": 5.4922,
|
|
"mean_token_accuracy": 0.17752016186714173,
|
|
"num_tokens": 14118344.0,
|
|
"step": 6330
|
|
},
|
|
{
|
|
"entropy": 5.657236385345459,
|
|
"epoch": 0.7115179423822092,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004959357065848932,
|
|
"loss": 5.5492,
|
|
"mean_token_accuracy": 0.17667852491140365,
|
|
"num_tokens": 14128767.0,
|
|
"step": 6335
|
|
},
|
|
{
|
|
"entropy": 5.677089643478394,
|
|
"epoch": 0.7120795192901668,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004959281064926618,
|
|
"loss": 5.7319,
|
|
"mean_token_accuracy": 0.16099997460842133,
|
|
"num_tokens": 14141593.0,
|
|
"step": 6340
|
|
},
|
|
{
|
|
"entropy": 5.783927011489868,
|
|
"epoch": 0.7126410961981243,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004959204993659936,
|
|
"loss": 5.624,
|
|
"mean_token_accuracy": 0.16535269916057588,
|
|
"num_tokens": 14151488.0,
|
|
"step": 6345
|
|
},
|
|
{
|
|
"entropy": 5.688516616821289,
|
|
"epoch": 0.7132026731060819,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004959128852051311,
|
|
"loss": 5.6207,
|
|
"mean_token_accuracy": 0.17363276481628417,
|
|
"num_tokens": 14162399.0,
|
|
"step": 6350
|
|
},
|
|
{
|
|
"entropy": 5.608430862426758,
|
|
"epoch": 0.7137642500140394,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004959052640103167,
|
|
"loss": 5.6018,
|
|
"mean_token_accuracy": 0.1652752012014389,
|
|
"num_tokens": 14173528.0,
|
|
"step": 6355
|
|
},
|
|
{
|
|
"entropy": 5.723161792755127,
|
|
"epoch": 0.714325826921997,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000495897635781793,
|
|
"loss": 5.5672,
|
|
"mean_token_accuracy": 0.17343024760484696,
|
|
"num_tokens": 14184119.0,
|
|
"step": 6360
|
|
},
|
|
{
|
|
"entropy": 5.765113830566406,
|
|
"epoch": 0.7148874038299545,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004958900005198029,
|
|
"loss": 5.6565,
|
|
"mean_token_accuracy": 0.17184285819530487,
|
|
"num_tokens": 14196225.0,
|
|
"step": 6365
|
|
},
|
|
{
|
|
"entropy": 5.558107233047485,
|
|
"epoch": 0.7154489807379121,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004958823582245894,
|
|
"loss": 5.4565,
|
|
"mean_token_accuracy": 0.1826736494898796,
|
|
"num_tokens": 14207541.0,
|
|
"step": 6370
|
|
},
|
|
{
|
|
"entropy": 5.684723377227783,
|
|
"epoch": 0.7160105576458696,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004958747088963961,
|
|
"loss": 5.5904,
|
|
"mean_token_accuracy": 0.1781718447804451,
|
|
"num_tokens": 14218713.0,
|
|
"step": 6375
|
|
},
|
|
{
|
|
"entropy": 5.5385583400726315,
|
|
"epoch": 0.7165721345538272,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004958670525354663,
|
|
"loss": 5.4554,
|
|
"mean_token_accuracy": 0.17795900702476503,
|
|
"num_tokens": 14229626.0,
|
|
"step": 6380
|
|
},
|
|
{
|
|
"entropy": 5.622214508056641,
|
|
"epoch": 0.7171337114617847,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.000495859389142044,
|
|
"loss": 5.6303,
|
|
"mean_token_accuracy": 0.16791053861379623,
|
|
"num_tokens": 14240320.0,
|
|
"step": 6385
|
|
},
|
|
{
|
|
"entropy": 5.791961145401001,
|
|
"epoch": 0.7176952883697423,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.000495851718716373,
|
|
"loss": 5.6807,
|
|
"mean_token_accuracy": 0.17302863150835038,
|
|
"num_tokens": 14252233.0,
|
|
"step": 6390
|
|
},
|
|
{
|
|
"entropy": 5.766545009613037,
|
|
"epoch": 0.7182568652776998,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004958440412586977,
|
|
"loss": 5.7034,
|
|
"mean_token_accuracy": 0.16096434891223907,
|
|
"num_tokens": 14264421.0,
|
|
"step": 6395
|
|
},
|
|
{
|
|
"entropy": 5.740488815307617,
|
|
"epoch": 0.7188184421856574,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004958363567692624,
|
|
"loss": 5.586,
|
|
"mean_token_accuracy": 0.1753292351961136,
|
|
"num_tokens": 14275320.0,
|
|
"step": 6400
|
|
},
|
|
{
|
|
"entropy": 5.594245147705078,
|
|
"epoch": 0.7193800190936148,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004958286652483118,
|
|
"loss": 5.5321,
|
|
"mean_token_accuracy": 0.1775944471359253,
|
|
"num_tokens": 14286099.0,
|
|
"step": 6405
|
|
},
|
|
{
|
|
"entropy": 5.678374862670898,
|
|
"epoch": 0.7199415960015724,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004958209666960909,
|
|
"loss": 5.6494,
|
|
"mean_token_accuracy": 0.1721476286649704,
|
|
"num_tokens": 14297795.0,
|
|
"step": 6410
|
|
},
|
|
{
|
|
"entropy": 5.6068220138549805,
|
|
"epoch": 0.7205031729095299,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004958132611128448,
|
|
"loss": 5.5631,
|
|
"mean_token_accuracy": 0.1775932416319847,
|
|
"num_tokens": 14309424.0,
|
|
"step": 6415
|
|
},
|
|
{
|
|
"entropy": 5.723865270614624,
|
|
"epoch": 0.7210647498174875,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004958055484988188,
|
|
"loss": 5.6316,
|
|
"mean_token_accuracy": 0.1743297293782234,
|
|
"num_tokens": 14320763.0,
|
|
"step": 6420
|
|
},
|
|
{
|
|
"entropy": 5.715590620040894,
|
|
"epoch": 0.721626326725445,
|
|
"grad_norm": 2.890625,
|
|
"learning_rate": 0.0004957978288542585,
|
|
"loss": 5.6015,
|
|
"mean_token_accuracy": 0.17502039074897766,
|
|
"num_tokens": 14331704.0,
|
|
"step": 6425
|
|
},
|
|
{
|
|
"entropy": 5.662281227111817,
|
|
"epoch": 0.7221879036334026,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004957901021794098,
|
|
"loss": 5.6592,
|
|
"mean_token_accuracy": 0.16564459949731827,
|
|
"num_tokens": 14343694.0,
|
|
"step": 6430
|
|
},
|
|
{
|
|
"entropy": 5.684270763397217,
|
|
"epoch": 0.7227494805413601,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004957823684745184,
|
|
"loss": 5.5492,
|
|
"mean_token_accuracy": 0.17231962233781814,
|
|
"num_tokens": 14355408.0,
|
|
"step": 6435
|
|
},
|
|
{
|
|
"entropy": 5.726321792602539,
|
|
"epoch": 0.7233110574493177,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004957746277398309,
|
|
"loss": 5.683,
|
|
"mean_token_accuracy": 0.166460257768631,
|
|
"num_tokens": 14366778.0,
|
|
"step": 6440
|
|
},
|
|
{
|
|
"entropy": 5.656356143951416,
|
|
"epoch": 0.7238726343572752,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004957668799755937,
|
|
"loss": 5.5587,
|
|
"mean_token_accuracy": 0.17831654250621795,
|
|
"num_tokens": 14377947.0,
|
|
"step": 6445
|
|
},
|
|
{
|
|
"entropy": 5.669637393951416,
|
|
"epoch": 0.7244342112652328,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004957591251820532,
|
|
"loss": 5.6442,
|
|
"mean_token_accuracy": 0.16868468523025512,
|
|
"num_tokens": 14389571.0,
|
|
"step": 6450
|
|
},
|
|
{
|
|
"entropy": 5.779145002365112,
|
|
"epoch": 0.7249957881731903,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004957513633594567,
|
|
"loss": 5.7115,
|
|
"mean_token_accuracy": 0.16774388700723647,
|
|
"num_tokens": 14401865.0,
|
|
"step": 6455
|
|
},
|
|
{
|
|
"entropy": 5.645418262481689,
|
|
"epoch": 0.7255573650811479,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004957435945080512,
|
|
"loss": 5.5448,
|
|
"mean_token_accuracy": 0.17675366550683974,
|
|
"num_tokens": 14413676.0,
|
|
"step": 6460
|
|
},
|
|
{
|
|
"entropy": 5.659231424331665,
|
|
"epoch": 0.7261189419891054,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004957358186280839,
|
|
"loss": 5.5645,
|
|
"mean_token_accuracy": 0.1817861244082451,
|
|
"num_tokens": 14424675.0,
|
|
"step": 6465
|
|
},
|
|
{
|
|
"entropy": 5.575326585769654,
|
|
"epoch": 0.726680518897063,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004957280357198026,
|
|
"loss": 5.4856,
|
|
"mean_token_accuracy": 0.1767103597521782,
|
|
"num_tokens": 14437238.0,
|
|
"step": 6470
|
|
},
|
|
{
|
|
"entropy": 5.507313680648804,
|
|
"epoch": 0.7272420958050205,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004957202457834551,
|
|
"loss": 5.4453,
|
|
"mean_token_accuracy": 0.1846798002719879,
|
|
"num_tokens": 14448003.0,
|
|
"step": 6475
|
|
},
|
|
{
|
|
"entropy": 5.498897981643677,
|
|
"epoch": 0.7278036727129781,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004957124488192893,
|
|
"loss": 5.3902,
|
|
"mean_token_accuracy": 0.1894318252801895,
|
|
"num_tokens": 14458440.0,
|
|
"step": 6480
|
|
},
|
|
{
|
|
"entropy": 5.632628965377807,
|
|
"epoch": 0.7283652496209356,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.0004957046448275535,
|
|
"loss": 5.5842,
|
|
"mean_token_accuracy": 0.17388828545808793,
|
|
"num_tokens": 14470127.0,
|
|
"step": 6485
|
|
},
|
|
{
|
|
"entropy": 5.567687845230102,
|
|
"epoch": 0.7289268265288932,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004956968338084961,
|
|
"loss": 5.4943,
|
|
"mean_token_accuracy": 0.18040443062782288,
|
|
"num_tokens": 14480993.0,
|
|
"step": 6490
|
|
},
|
|
{
|
|
"entropy": 5.6706554889678955,
|
|
"epoch": 0.7294884034368507,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004956890157623661,
|
|
"loss": 5.592,
|
|
"mean_token_accuracy": 0.1692513033747673,
|
|
"num_tokens": 14492789.0,
|
|
"step": 6495
|
|
},
|
|
{
|
|
"entropy": 5.72467269897461,
|
|
"epoch": 0.7300499803448082,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004956811906894122,
|
|
"loss": 5.696,
|
|
"mean_token_accuracy": 0.1679220139980316,
|
|
"num_tokens": 14504528.0,
|
|
"step": 6500
|
|
},
|
|
{
|
|
"entropy": 5.766086673736572,
|
|
"epoch": 0.7306115572527657,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004956733585898836,
|
|
"loss": 5.5764,
|
|
"mean_token_accuracy": 0.17388349622488022,
|
|
"num_tokens": 14515739.0,
|
|
"step": 6505
|
|
},
|
|
{
|
|
"entropy": 5.742607545852661,
|
|
"epoch": 0.7311731341607233,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004956655194640297,
|
|
"loss": 5.7013,
|
|
"mean_token_accuracy": 0.16888848841190338,
|
|
"num_tokens": 14527120.0,
|
|
"step": 6510
|
|
},
|
|
{
|
|
"entropy": 5.673899459838867,
|
|
"epoch": 0.7317347110686808,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004956576733121,
|
|
"loss": 5.6474,
|
|
"mean_token_accuracy": 0.1741111882030964,
|
|
"num_tokens": 14539390.0,
|
|
"step": 6515
|
|
},
|
|
{
|
|
"entropy": 5.7319371700286865,
|
|
"epoch": 0.7322962879766384,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004956498201343444,
|
|
"loss": 5.6457,
|
|
"mean_token_accuracy": 0.17107407450675965,
|
|
"num_tokens": 14549905.0,
|
|
"step": 6520
|
|
},
|
|
{
|
|
"entropy": 5.7245110988616945,
|
|
"epoch": 0.7328578648845959,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000495641959931013,
|
|
"loss": 5.6655,
|
|
"mean_token_accuracy": 0.17252781093120576,
|
|
"num_tokens": 14561519.0,
|
|
"step": 6525
|
|
},
|
|
{
|
|
"entropy": 5.610703468322754,
|
|
"epoch": 0.7334194417925535,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004956340927023561,
|
|
"loss": 5.4382,
|
|
"mean_token_accuracy": 0.17527818828821182,
|
|
"num_tokens": 14572704.0,
|
|
"step": 6530
|
|
},
|
|
{
|
|
"entropy": 5.68189582824707,
|
|
"epoch": 0.733981018700511,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.000495626218448624,
|
|
"loss": 5.6235,
|
|
"mean_token_accuracy": 0.17428021728992463,
|
|
"num_tokens": 14584055.0,
|
|
"step": 6535
|
|
},
|
|
{
|
|
"entropy": 5.544544982910156,
|
|
"epoch": 0.7345425956084686,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004956183371700676,
|
|
"loss": 5.4384,
|
|
"mean_token_accuracy": 0.17765936106443406,
|
|
"num_tokens": 14595271.0,
|
|
"step": 6540
|
|
},
|
|
{
|
|
"entropy": 5.677876710891724,
|
|
"epoch": 0.7351041725164261,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004956104488669377,
|
|
"loss": 5.5979,
|
|
"mean_token_accuracy": 0.1767997145652771,
|
|
"num_tokens": 14605748.0,
|
|
"step": 6545
|
|
},
|
|
{
|
|
"entropy": 5.640767431259155,
|
|
"epoch": 0.7356657494243837,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004956025535394856,
|
|
"loss": 5.5253,
|
|
"mean_token_accuracy": 0.18051766753196716,
|
|
"num_tokens": 14616295.0,
|
|
"step": 6550
|
|
},
|
|
{
|
|
"entropy": 5.613051509857177,
|
|
"epoch": 0.7362273263323412,
|
|
"grad_norm": 2.703125,
|
|
"learning_rate": 0.0004955946511879626,
|
|
"loss": 5.5899,
|
|
"mean_token_accuracy": 0.17333509624004365,
|
|
"num_tokens": 14626690.0,
|
|
"step": 6555
|
|
},
|
|
{
|
|
"entropy": 5.654295921325684,
|
|
"epoch": 0.7367889032402988,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004955867418126205,
|
|
"loss": 5.5925,
|
|
"mean_token_accuracy": 0.17576799988746644,
|
|
"num_tokens": 14637685.0,
|
|
"step": 6560
|
|
},
|
|
{
|
|
"entropy": 5.714108848571778,
|
|
"epoch": 0.7373504801482563,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.0004955788254137108,
|
|
"loss": 5.4992,
|
|
"mean_token_accuracy": 0.17065490037202835,
|
|
"num_tokens": 14648098.0,
|
|
"step": 6565
|
|
},
|
|
{
|
|
"entropy": 5.752398300170898,
|
|
"epoch": 0.7379120570562139,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004955709019914857,
|
|
"loss": 5.6571,
|
|
"mean_token_accuracy": 0.16791386604309083,
|
|
"num_tokens": 14661134.0,
|
|
"step": 6570
|
|
},
|
|
{
|
|
"entropy": 5.726694536209107,
|
|
"epoch": 0.7384736339641714,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004955629715461977,
|
|
"loss": 5.6146,
|
|
"mean_token_accuracy": 0.1718799889087677,
|
|
"num_tokens": 14672699.0,
|
|
"step": 6575
|
|
},
|
|
{
|
|
"entropy": 5.722080993652344,
|
|
"epoch": 0.739035210872129,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.0004955550340780991,
|
|
"loss": 5.6028,
|
|
"mean_token_accuracy": 0.17119617015123367,
|
|
"num_tokens": 14682994.0,
|
|
"step": 6580
|
|
},
|
|
{
|
|
"entropy": 5.686217212677002,
|
|
"epoch": 0.7395967877800865,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004955470895874427,
|
|
"loss": 5.5908,
|
|
"mean_token_accuracy": 0.1740305818617344,
|
|
"num_tokens": 14694828.0,
|
|
"step": 6585
|
|
},
|
|
{
|
|
"entropy": 5.652625989913941,
|
|
"epoch": 0.7401583646880441,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004955391380744813,
|
|
"loss": 5.5776,
|
|
"mean_token_accuracy": 0.17652767300605773,
|
|
"num_tokens": 14705975.0,
|
|
"step": 6590
|
|
},
|
|
{
|
|
"entropy": 5.678385496139526,
|
|
"epoch": 0.7407199415960015,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004955311795394684,
|
|
"loss": 5.5566,
|
|
"mean_token_accuracy": 0.17292129546403884,
|
|
"num_tokens": 14717717.0,
|
|
"step": 6595
|
|
},
|
|
{
|
|
"entropy": 5.6449932098388675,
|
|
"epoch": 0.7412815185039591,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.000495523213982657,
|
|
"loss": 5.522,
|
|
"mean_token_accuracy": 0.17537171840667726,
|
|
"num_tokens": 14729254.0,
|
|
"step": 6600
|
|
},
|
|
{
|
|
"entropy": 5.668190240859985,
|
|
"epoch": 0.7418430954119166,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004955152414043011,
|
|
"loss": 5.6797,
|
|
"mean_token_accuracy": 0.17303741574287415,
|
|
"num_tokens": 14739733.0,
|
|
"step": 6605
|
|
},
|
|
{
|
|
"entropy": 5.685405921936035,
|
|
"epoch": 0.7424046723198742,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004955072618046543,
|
|
"loss": 5.6274,
|
|
"mean_token_accuracy": 0.17229688316583633,
|
|
"num_tokens": 14750855.0,
|
|
"step": 6610
|
|
},
|
|
{
|
|
"entropy": 5.694899272918701,
|
|
"epoch": 0.7429662492278317,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004954992751839708,
|
|
"loss": 5.6375,
|
|
"mean_token_accuracy": 0.16860194653272628,
|
|
"num_tokens": 14762762.0,
|
|
"step": 6615
|
|
},
|
|
{
|
|
"entropy": 5.714443302154541,
|
|
"epoch": 0.7435278261357893,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004954912815425048,
|
|
"loss": 5.5067,
|
|
"mean_token_accuracy": 0.16969477534294128,
|
|
"num_tokens": 14773690.0,
|
|
"step": 6620
|
|
},
|
|
{
|
|
"entropy": 5.6447425365448,
|
|
"epoch": 0.7440894030437468,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.000495483280880511,
|
|
"loss": 5.6185,
|
|
"mean_token_accuracy": 0.17139164060354234,
|
|
"num_tokens": 14785019.0,
|
|
"step": 6625
|
|
},
|
|
{
|
|
"entropy": 5.599686574935913,
|
|
"epoch": 0.7446509799517044,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.000495475273198244,
|
|
"loss": 5.583,
|
|
"mean_token_accuracy": 0.17097049206495285,
|
|
"num_tokens": 14795638.0,
|
|
"step": 6630
|
|
},
|
|
{
|
|
"entropy": 5.705252981185913,
|
|
"epoch": 0.7452125568596619,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004954672584959588,
|
|
"loss": 5.5195,
|
|
"mean_token_accuracy": 0.1778087317943573,
|
|
"num_tokens": 14806546.0,
|
|
"step": 6635
|
|
},
|
|
{
|
|
"entropy": 5.641622686386109,
|
|
"epoch": 0.7457741337676195,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004954592367739104,
|
|
"loss": 5.5639,
|
|
"mean_token_accuracy": 0.17897435277700424,
|
|
"num_tokens": 14816918.0,
|
|
"step": 6640
|
|
},
|
|
{
|
|
"entropy": 5.57894549369812,
|
|
"epoch": 0.746335710675577,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004954512080323546,
|
|
"loss": 5.5302,
|
|
"mean_token_accuracy": 0.1821251705288887,
|
|
"num_tokens": 14827420.0,
|
|
"step": 6645
|
|
},
|
|
{
|
|
"entropy": 5.697102022171021,
|
|
"epoch": 0.7468972875835346,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004954431722715468,
|
|
"loss": 5.7557,
|
|
"mean_token_accuracy": 0.1726679638028145,
|
|
"num_tokens": 14839209.0,
|
|
"step": 6650
|
|
},
|
|
{
|
|
"entropy": 5.783769321441651,
|
|
"epoch": 0.7474588644914921,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004954351294917428,
|
|
"loss": 5.6373,
|
|
"mean_token_accuracy": 0.16879186183214187,
|
|
"num_tokens": 14849916.0,
|
|
"step": 6655
|
|
},
|
|
{
|
|
"entropy": 5.58750810623169,
|
|
"epoch": 0.7480204413994497,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004954270796931989,
|
|
"loss": 5.5116,
|
|
"mean_token_accuracy": 0.17819211781024932,
|
|
"num_tokens": 14860946.0,
|
|
"step": 6660
|
|
},
|
|
{
|
|
"entropy": 5.718907070159912,
|
|
"epoch": 0.7485820183074072,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004954190228761712,
|
|
"loss": 5.6219,
|
|
"mean_token_accuracy": 0.16795709282159804,
|
|
"num_tokens": 14872750.0,
|
|
"step": 6665
|
|
},
|
|
{
|
|
"entropy": 5.723129653930664,
|
|
"epoch": 0.7491435952153648,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004954109590409164,
|
|
"loss": 5.5852,
|
|
"mean_token_accuracy": 0.17279770374298095,
|
|
"num_tokens": 14883714.0,
|
|
"step": 6670
|
|
},
|
|
{
|
|
"entropy": 5.640544652938843,
|
|
"epoch": 0.7497051721233223,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004954028881876911,
|
|
"loss": 5.6116,
|
|
"mean_token_accuracy": 0.1742043063044548,
|
|
"num_tokens": 14895147.0,
|
|
"step": 6675
|
|
},
|
|
{
|
|
"entropy": 5.568828439712524,
|
|
"epoch": 0.7502667490312799,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004953948103167524,
|
|
"loss": 5.5114,
|
|
"mean_token_accuracy": 0.17742622196674346,
|
|
"num_tokens": 14905914.0,
|
|
"step": 6680
|
|
},
|
|
{
|
|
"entropy": 5.633767747879029,
|
|
"epoch": 0.7508283259392374,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004953867254283575,
|
|
"loss": 5.5256,
|
|
"mean_token_accuracy": 0.17404744029045105,
|
|
"num_tokens": 14916988.0,
|
|
"step": 6685
|
|
},
|
|
{
|
|
"entropy": 5.773840427398682,
|
|
"epoch": 0.7513899028471949,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004953786335227636,
|
|
"loss": 5.6313,
|
|
"mean_token_accuracy": 0.17394339740276338,
|
|
"num_tokens": 14928675.0,
|
|
"step": 6690
|
|
},
|
|
{
|
|
"entropy": 5.762109804153442,
|
|
"epoch": 0.7519514797551524,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004953705346002287,
|
|
"loss": 5.6169,
|
|
"mean_token_accuracy": 0.17867628782987593,
|
|
"num_tokens": 14939422.0,
|
|
"step": 6695
|
|
},
|
|
{
|
|
"entropy": 5.63875093460083,
|
|
"epoch": 0.75251305666311,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004953624286610106,
|
|
"loss": 5.5895,
|
|
"mean_token_accuracy": 0.17518542855978012,
|
|
"num_tokens": 14950156.0,
|
|
"step": 6700
|
|
},
|
|
{
|
|
"entropy": 5.685830545425415,
|
|
"epoch": 0.7530746335710675,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004953543157053672,
|
|
"loss": 5.5764,
|
|
"mean_token_accuracy": 0.17458546608686448,
|
|
"num_tokens": 14960535.0,
|
|
"step": 6705
|
|
},
|
|
{
|
|
"entropy": 5.73161563873291,
|
|
"epoch": 0.7536362104790251,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004953461957335569,
|
|
"loss": 5.594,
|
|
"mean_token_accuracy": 0.173647703230381,
|
|
"num_tokens": 14970975.0,
|
|
"step": 6710
|
|
},
|
|
{
|
|
"entropy": 5.578568029403686,
|
|
"epoch": 0.7541977873869826,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004953380687458382,
|
|
"loss": 5.4501,
|
|
"mean_token_accuracy": 0.18154784440994262,
|
|
"num_tokens": 14981204.0,
|
|
"step": 6715
|
|
},
|
|
{
|
|
"entropy": 5.685376596450806,
|
|
"epoch": 0.7547593642949402,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004953299347424701,
|
|
"loss": 5.6364,
|
|
"mean_token_accuracy": 0.1709104746580124,
|
|
"num_tokens": 14991631.0,
|
|
"step": 6720
|
|
},
|
|
{
|
|
"entropy": 5.669009828567505,
|
|
"epoch": 0.7553209412028977,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004953217937237114,
|
|
"loss": 5.5515,
|
|
"mean_token_accuracy": 0.17797055393457412,
|
|
"num_tokens": 15003873.0,
|
|
"step": 6725
|
|
},
|
|
{
|
|
"entropy": 5.643837356567383,
|
|
"epoch": 0.7558825181108553,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004953136456898212,
|
|
"loss": 5.6366,
|
|
"mean_token_accuracy": 0.16726253926753998,
|
|
"num_tokens": 15014890.0,
|
|
"step": 6730
|
|
},
|
|
{
|
|
"entropy": 5.619820594787598,
|
|
"epoch": 0.7564440950188128,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004953054906410593,
|
|
"loss": 5.4983,
|
|
"mean_token_accuracy": 0.1796386569738388,
|
|
"num_tokens": 15025037.0,
|
|
"step": 6735
|
|
},
|
|
{
|
|
"entropy": 5.708780145645141,
|
|
"epoch": 0.7570056719267704,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004952973285776848,
|
|
"loss": 5.5973,
|
|
"mean_token_accuracy": 0.1785723552107811,
|
|
"num_tokens": 15035722.0,
|
|
"step": 6740
|
|
},
|
|
{
|
|
"entropy": 5.636859607696533,
|
|
"epoch": 0.7575672488347279,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004952891594999582,
|
|
"loss": 5.5911,
|
|
"mean_token_accuracy": 0.17289981991052628,
|
|
"num_tokens": 15047138.0,
|
|
"step": 6745
|
|
},
|
|
{
|
|
"entropy": 5.625335550308227,
|
|
"epoch": 0.7581288257426855,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.0004952809834081392,
|
|
"loss": 5.5561,
|
|
"mean_token_accuracy": 0.1788078024983406,
|
|
"num_tokens": 15058559.0,
|
|
"step": 6750
|
|
},
|
|
{
|
|
"entropy": 5.6669196605682375,
|
|
"epoch": 0.758690402650643,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004952728003024883,
|
|
"loss": 5.5909,
|
|
"mean_token_accuracy": 0.1738209381699562,
|
|
"num_tokens": 15070481.0,
|
|
"step": 6755
|
|
},
|
|
{
|
|
"entropy": 5.677978229522705,
|
|
"epoch": 0.7592519795586006,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004952646101832659,
|
|
"loss": 5.5096,
|
|
"mean_token_accuracy": 0.1810382291674614,
|
|
"num_tokens": 15079844.0,
|
|
"step": 6760
|
|
},
|
|
{
|
|
"entropy": 5.561579084396362,
|
|
"epoch": 0.7598135564665581,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004952564130507331,
|
|
"loss": 5.5281,
|
|
"mean_token_accuracy": 0.1803469717502594,
|
|
"num_tokens": 15091197.0,
|
|
"step": 6765
|
|
},
|
|
{
|
|
"entropy": 5.596119832992554,
|
|
"epoch": 0.7603751333745157,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004952482089051506,
|
|
"loss": 5.6134,
|
|
"mean_token_accuracy": 0.1722786858677864,
|
|
"num_tokens": 15102130.0,
|
|
"step": 6770
|
|
},
|
|
{
|
|
"entropy": 5.793495559692383,
|
|
"epoch": 0.7609367102824732,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004952399977467796,
|
|
"loss": 5.6886,
|
|
"mean_token_accuracy": 0.16494995057582856,
|
|
"num_tokens": 15113886.0,
|
|
"step": 6775
|
|
},
|
|
{
|
|
"entropy": 5.653849744796753,
|
|
"epoch": 0.7614982871904308,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.0004952317795758817,
|
|
"loss": 5.5085,
|
|
"mean_token_accuracy": 0.17455629110336304,
|
|
"num_tokens": 15125284.0,
|
|
"step": 6780
|
|
},
|
|
{
|
|
"entropy": 5.707993984222412,
|
|
"epoch": 0.7620598640983883,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004952235543927185,
|
|
"loss": 5.5732,
|
|
"mean_token_accuracy": 0.17695511132478714,
|
|
"num_tokens": 15136486.0,
|
|
"step": 6785
|
|
},
|
|
{
|
|
"entropy": 5.595456552505493,
|
|
"epoch": 0.7626214410063458,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.000495215322197552,
|
|
"loss": 5.4514,
|
|
"mean_token_accuracy": 0.1823273316025734,
|
|
"num_tokens": 15145937.0,
|
|
"step": 6790
|
|
},
|
|
{
|
|
"entropy": 5.571471548080444,
|
|
"epoch": 0.7631830179143033,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004952070829906442,
|
|
"loss": 5.5408,
|
|
"mean_token_accuracy": 0.17444423735141754,
|
|
"num_tokens": 15156923.0,
|
|
"step": 6795
|
|
},
|
|
{
|
|
"entropy": 5.742830657958985,
|
|
"epoch": 0.7637445948222609,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004951988367722574,
|
|
"loss": 5.6702,
|
|
"mean_token_accuracy": 0.1720725566148758,
|
|
"num_tokens": 15169793.0,
|
|
"step": 6800
|
|
},
|
|
{
|
|
"entropy": 5.623646593093872,
|
|
"epoch": 0.7643061717302184,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004951905835426544,
|
|
"loss": 5.4409,
|
|
"mean_token_accuracy": 0.18333717286586762,
|
|
"num_tokens": 15180679.0,
|
|
"step": 6805
|
|
},
|
|
{
|
|
"entropy": 5.633894968032837,
|
|
"epoch": 0.764867748638176,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004951823233020976,
|
|
"loss": 5.636,
|
|
"mean_token_accuracy": 0.17393151819705963,
|
|
"num_tokens": 15192298.0,
|
|
"step": 6810
|
|
},
|
|
{
|
|
"entropy": 5.7002646923065186,
|
|
"epoch": 0.7654293255461335,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004951740560508504,
|
|
"loss": 5.7206,
|
|
"mean_token_accuracy": 0.16596095710992814,
|
|
"num_tokens": 15204759.0,
|
|
"step": 6815
|
|
},
|
|
{
|
|
"entropy": 5.765062427520752,
|
|
"epoch": 0.7659909024540911,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004951657817891758,
|
|
"loss": 5.5881,
|
|
"mean_token_accuracy": 0.17510877549648285,
|
|
"num_tokens": 15217166.0,
|
|
"step": 6820
|
|
},
|
|
{
|
|
"entropy": 5.567334747314453,
|
|
"epoch": 0.7665524793620486,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004951575005173373,
|
|
"loss": 5.5606,
|
|
"mean_token_accuracy": 0.17338118553161622,
|
|
"num_tokens": 15227022.0,
|
|
"step": 6825
|
|
},
|
|
{
|
|
"entropy": 5.691093778610229,
|
|
"epoch": 0.7671140562700062,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004951492122355986,
|
|
"loss": 5.6094,
|
|
"mean_token_accuracy": 0.17153313159942626,
|
|
"num_tokens": 15239088.0,
|
|
"step": 6830
|
|
},
|
|
{
|
|
"entropy": 5.713991022109985,
|
|
"epoch": 0.7676756331779637,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004951409169442236,
|
|
"loss": 5.6416,
|
|
"mean_token_accuracy": 0.17613879442214966,
|
|
"num_tokens": 15250263.0,
|
|
"step": 6835
|
|
},
|
|
{
|
|
"entropy": 5.564354515075683,
|
|
"epoch": 0.7682372100859213,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004951326146434765,
|
|
"loss": 5.5323,
|
|
"mean_token_accuracy": 0.1793072611093521,
|
|
"num_tokens": 15263014.0,
|
|
"step": 6840
|
|
},
|
|
{
|
|
"entropy": 5.687871646881104,
|
|
"epoch": 0.7687987869938788,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004951243053336214,
|
|
"loss": 5.5291,
|
|
"mean_token_accuracy": 0.17732672691345214,
|
|
"num_tokens": 15274261.0,
|
|
"step": 6845
|
|
},
|
|
{
|
|
"entropy": 5.631127500534058,
|
|
"epoch": 0.7693603639018364,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004951159890149232,
|
|
"loss": 5.4497,
|
|
"mean_token_accuracy": 0.1830949068069458,
|
|
"num_tokens": 15284929.0,
|
|
"step": 6850
|
|
},
|
|
{
|
|
"entropy": 5.537542104721069,
|
|
"epoch": 0.7699219408097939,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004951076656876466,
|
|
"loss": 5.5506,
|
|
"mean_token_accuracy": 0.17952288836240768,
|
|
"num_tokens": 15296622.0,
|
|
"step": 6855
|
|
},
|
|
{
|
|
"entropy": 5.601659297943115,
|
|
"epoch": 0.7704835177177515,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004950993353520564,
|
|
"loss": 5.6329,
|
|
"mean_token_accuracy": 0.17123521119356155,
|
|
"num_tokens": 15308373.0,
|
|
"step": 6860
|
|
},
|
|
{
|
|
"entropy": 5.67266526222229,
|
|
"epoch": 0.771045094625709,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.000495090998008418,
|
|
"loss": 5.4987,
|
|
"mean_token_accuracy": 0.18144238889217376,
|
|
"num_tokens": 15319705.0,
|
|
"step": 6865
|
|
},
|
|
{
|
|
"entropy": 5.685407447814941,
|
|
"epoch": 0.7716066715336666,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.000495082653656997,
|
|
"loss": 5.6549,
|
|
"mean_token_accuracy": 0.1676367312669754,
|
|
"num_tokens": 15330883.0,
|
|
"step": 6870
|
|
},
|
|
{
|
|
"entropy": 5.68987021446228,
|
|
"epoch": 0.7721682484416241,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004950743022980587,
|
|
"loss": 5.5568,
|
|
"mean_token_accuracy": 0.1752520591020584,
|
|
"num_tokens": 15342294.0,
|
|
"step": 6875
|
|
},
|
|
{
|
|
"entropy": 5.670950174331665,
|
|
"epoch": 0.7727298253495817,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004950659439318696,
|
|
"loss": 5.5487,
|
|
"mean_token_accuracy": 0.17589346170425416,
|
|
"num_tokens": 15352615.0,
|
|
"step": 6880
|
|
},
|
|
{
|
|
"entropy": 5.61051378250122,
|
|
"epoch": 0.7732914022575391,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004950575785586952,
|
|
"loss": 5.6005,
|
|
"mean_token_accuracy": 0.17050575762987136,
|
|
"num_tokens": 15364516.0,
|
|
"step": 6885
|
|
},
|
|
{
|
|
"entropy": 5.633886671066284,
|
|
"epoch": 0.7738529791654967,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004950492061788023,
|
|
"loss": 5.5102,
|
|
"mean_token_accuracy": 0.1734094351530075,
|
|
"num_tokens": 15374877.0,
|
|
"step": 6890
|
|
},
|
|
{
|
|
"entropy": 5.621919727325439,
|
|
"epoch": 0.7744145560734542,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004950408267924573,
|
|
"loss": 5.4405,
|
|
"mean_token_accuracy": 0.18854133188724517,
|
|
"num_tokens": 15385250.0,
|
|
"step": 6895
|
|
},
|
|
{
|
|
"entropy": 5.600653457641601,
|
|
"epoch": 0.7749761329814118,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004950324403999271,
|
|
"loss": 5.5892,
|
|
"mean_token_accuracy": 0.18425043821334838,
|
|
"num_tokens": 15397074.0,
|
|
"step": 6900
|
|
},
|
|
{
|
|
"entropy": 5.701744604110718,
|
|
"epoch": 0.7755377098893693,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004950240470014785,
|
|
"loss": 5.6301,
|
|
"mean_token_accuracy": 0.17118001580238343,
|
|
"num_tokens": 15408575.0,
|
|
"step": 6905
|
|
},
|
|
{
|
|
"entropy": 5.693548107147217,
|
|
"epoch": 0.7760992867973269,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004950156465973791,
|
|
"loss": 5.5571,
|
|
"mean_token_accuracy": 0.17781548649072648,
|
|
"num_tokens": 15419071.0,
|
|
"step": 6910
|
|
},
|
|
{
|
|
"entropy": 5.50706295967102,
|
|
"epoch": 0.7766608637052844,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.000495007239187896,
|
|
"loss": 5.4332,
|
|
"mean_token_accuracy": 0.1781666323542595,
|
|
"num_tokens": 15430137.0,
|
|
"step": 6915
|
|
},
|
|
{
|
|
"entropy": 5.536088609695435,
|
|
"epoch": 0.777222440613242,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004949988247732972,
|
|
"loss": 5.5091,
|
|
"mean_token_accuracy": 0.18007286190986632,
|
|
"num_tokens": 15440661.0,
|
|
"step": 6920
|
|
},
|
|
{
|
|
"entropy": 5.539862203598022,
|
|
"epoch": 0.7777840175211995,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004949904033538504,
|
|
"loss": 5.5074,
|
|
"mean_token_accuracy": 0.18067346066236495,
|
|
"num_tokens": 15451909.0,
|
|
"step": 6925
|
|
},
|
|
{
|
|
"entropy": 5.734219360351562,
|
|
"epoch": 0.7783455944291571,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.000494981974929824,
|
|
"loss": 5.5822,
|
|
"mean_token_accuracy": 0.17215592712163924,
|
|
"num_tokens": 15462244.0,
|
|
"step": 6930
|
|
},
|
|
{
|
|
"entropy": 5.664867830276489,
|
|
"epoch": 0.7789071713371146,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.000494973539501486,
|
|
"loss": 5.6361,
|
|
"mean_token_accuracy": 0.17244648337364196,
|
|
"num_tokens": 15473284.0,
|
|
"step": 6935
|
|
},
|
|
{
|
|
"entropy": 5.6097170352935795,
|
|
"epoch": 0.7794687482450722,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004949650970691052,
|
|
"loss": 5.5296,
|
|
"mean_token_accuracy": 0.18466857969760894,
|
|
"num_tokens": 15484964.0,
|
|
"step": 6940
|
|
},
|
|
{
|
|
"entropy": 5.683780574798584,
|
|
"epoch": 0.7800303251530297,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004949566476329505,
|
|
"loss": 5.5627,
|
|
"mean_token_accuracy": 0.17425339072942733,
|
|
"num_tokens": 15495922.0,
|
|
"step": 6945
|
|
},
|
|
{
|
|
"entropy": 5.622462797164917,
|
|
"epoch": 0.7805919020609873,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004949481911932908,
|
|
"loss": 5.6272,
|
|
"mean_token_accuracy": 0.17403968870639802,
|
|
"num_tokens": 15507173.0,
|
|
"step": 6950
|
|
},
|
|
{
|
|
"entropy": 5.679885530471802,
|
|
"epoch": 0.7811534789689448,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004949397277503954,
|
|
"loss": 5.5809,
|
|
"mean_token_accuracy": 0.17489976584911346,
|
|
"num_tokens": 15517720.0,
|
|
"step": 6955
|
|
},
|
|
{
|
|
"entropy": 5.696992206573486,
|
|
"epoch": 0.7817150558769024,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004949312573045338,
|
|
"loss": 5.6134,
|
|
"mean_token_accuracy": 0.1722379595041275,
|
|
"num_tokens": 15529482.0,
|
|
"step": 6960
|
|
},
|
|
{
|
|
"entropy": 5.745795774459839,
|
|
"epoch": 0.7822766327848599,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.0004949227798559757,
|
|
"loss": 5.6237,
|
|
"mean_token_accuracy": 0.17065105736255645,
|
|
"num_tokens": 15540522.0,
|
|
"step": 6965
|
|
},
|
|
{
|
|
"entropy": 5.667511510848999,
|
|
"epoch": 0.7828382096928175,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004949142954049909,
|
|
"loss": 5.6107,
|
|
"mean_token_accuracy": 0.17157721072435378,
|
|
"num_tokens": 15552443.0,
|
|
"step": 6970
|
|
},
|
|
{
|
|
"entropy": 5.699892997741699,
|
|
"epoch": 0.783399786600775,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004949058039518496,
|
|
"loss": 5.6307,
|
|
"mean_token_accuracy": 0.1806534305214882,
|
|
"num_tokens": 15563418.0,
|
|
"step": 6975
|
|
},
|
|
{
|
|
"entropy": 5.704437255859375,
|
|
"epoch": 0.7839613635087325,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004948973054968222,
|
|
"loss": 5.6551,
|
|
"mean_token_accuracy": 0.17082856297492982,
|
|
"num_tokens": 15574301.0,
|
|
"step": 6980
|
|
},
|
|
{
|
|
"entropy": 5.81133074760437,
|
|
"epoch": 0.78452294041669,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004948888000401794,
|
|
"loss": 5.5619,
|
|
"mean_token_accuracy": 0.169041807949543,
|
|
"num_tokens": 15585125.0,
|
|
"step": 6985
|
|
},
|
|
{
|
|
"entropy": 5.733863353729248,
|
|
"epoch": 0.7850845173246476,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004948802875821918,
|
|
"loss": 5.6748,
|
|
"mean_token_accuracy": 0.17066787481307982,
|
|
"num_tokens": 15595822.0,
|
|
"step": 6990
|
|
},
|
|
{
|
|
"entropy": 5.579914474487305,
|
|
"epoch": 0.7856460942326051,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004948717681231308,
|
|
"loss": 5.5106,
|
|
"mean_token_accuracy": 0.17668165266513824,
|
|
"num_tokens": 15606835.0,
|
|
"step": 6995
|
|
},
|
|
{
|
|
"entropy": 5.665369892120362,
|
|
"epoch": 0.7862076711405627,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004948632416632672,
|
|
"loss": 5.5745,
|
|
"mean_token_accuracy": 0.17439241260290145,
|
|
"num_tokens": 15617287.0,
|
|
"step": 7000
|
|
},
|
|
{
|
|
"entropy": 5.80098557472229,
|
|
"epoch": 0.7867692480485202,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004948547082028728,
|
|
"loss": 5.6324,
|
|
"mean_token_accuracy": 0.1664173424243927,
|
|
"num_tokens": 15628440.0,
|
|
"step": 7005
|
|
},
|
|
{
|
|
"entropy": 5.748582553863526,
|
|
"epoch": 0.7873308249564778,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.0004948461677422193,
|
|
"loss": 5.738,
|
|
"mean_token_accuracy": 0.1651600942015648,
|
|
"num_tokens": 15640677.0,
|
|
"step": 7010
|
|
},
|
|
{
|
|
"entropy": 5.713280200958252,
|
|
"epoch": 0.7878924018644353,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004948376202815785,
|
|
"loss": 5.571,
|
|
"mean_token_accuracy": 0.17927639484405516,
|
|
"num_tokens": 15651941.0,
|
|
"step": 7015
|
|
},
|
|
{
|
|
"entropy": 5.667389392852783,
|
|
"epoch": 0.7884539787723929,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004948290658212225,
|
|
"loss": 5.5609,
|
|
"mean_token_accuracy": 0.1750228151679039,
|
|
"num_tokens": 15663513.0,
|
|
"step": 7020
|
|
},
|
|
{
|
|
"entropy": 5.627860116958618,
|
|
"epoch": 0.7890155556803504,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004948205043614239,
|
|
"loss": 5.5443,
|
|
"mean_token_accuracy": 0.17534425258636474,
|
|
"num_tokens": 15675548.0,
|
|
"step": 7025
|
|
},
|
|
{
|
|
"entropy": 5.704278659820557,
|
|
"epoch": 0.789577132588308,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004948119359024551,
|
|
"loss": 5.5789,
|
|
"mean_token_accuracy": 0.1815459504723549,
|
|
"num_tokens": 15685365.0,
|
|
"step": 7030
|
|
},
|
|
{
|
|
"entropy": 5.657306861877442,
|
|
"epoch": 0.7901387094962655,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004948033604445891,
|
|
"loss": 5.5941,
|
|
"mean_token_accuracy": 0.17289290726184844,
|
|
"num_tokens": 15696112.0,
|
|
"step": 7035
|
|
},
|
|
{
|
|
"entropy": 5.614476346969605,
|
|
"epoch": 0.7907002864042231,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004947947779880988,
|
|
"loss": 5.5255,
|
|
"mean_token_accuracy": 0.17538561969995498,
|
|
"num_tokens": 15707414.0,
|
|
"step": 7040
|
|
},
|
|
{
|
|
"entropy": 5.690111589431763,
|
|
"epoch": 0.7912618633121806,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004947861885332576,
|
|
"loss": 5.6133,
|
|
"mean_token_accuracy": 0.17803962975740434,
|
|
"num_tokens": 15719077.0,
|
|
"step": 7045
|
|
},
|
|
{
|
|
"entropy": 5.6438501358032225,
|
|
"epoch": 0.7918234402201382,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004947775920803388,
|
|
"loss": 5.6231,
|
|
"mean_token_accuracy": 0.17299479693174363,
|
|
"num_tokens": 15730497.0,
|
|
"step": 7050
|
|
},
|
|
{
|
|
"entropy": 5.718972492218017,
|
|
"epoch": 0.7923850171280957,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004947689886296162,
|
|
"loss": 5.5022,
|
|
"mean_token_accuracy": 0.17456527948379516,
|
|
"num_tokens": 15741724.0,
|
|
"step": 7055
|
|
},
|
|
{
|
|
"entropy": 5.741605949401856,
|
|
"epoch": 0.7929465940360533,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.000494760378181364,
|
|
"loss": 5.6166,
|
|
"mean_token_accuracy": 0.16815846562385559,
|
|
"num_tokens": 15751868.0,
|
|
"step": 7060
|
|
},
|
|
{
|
|
"entropy": 5.645622396469117,
|
|
"epoch": 0.7935081709440108,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.0004947517607358559,
|
|
"loss": 5.605,
|
|
"mean_token_accuracy": 0.17208277434110641,
|
|
"num_tokens": 15762783.0,
|
|
"step": 7065
|
|
},
|
|
{
|
|
"entropy": 5.670810794830322,
|
|
"epoch": 0.7940697478519684,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004947431362933666,
|
|
"loss": 5.6045,
|
|
"mean_token_accuracy": 0.17175351977348327,
|
|
"num_tokens": 15774155.0,
|
|
"step": 7070
|
|
},
|
|
{
|
|
"entropy": 5.779428291320801,
|
|
"epoch": 0.7946313247599258,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004947345048541706,
|
|
"loss": 5.6244,
|
|
"mean_token_accuracy": 0.16937934160232543,
|
|
"num_tokens": 15785034.0,
|
|
"step": 7075
|
|
},
|
|
{
|
|
"entropy": 5.59167218208313,
|
|
"epoch": 0.7951929016678834,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.0004947258664185427,
|
|
"loss": 5.5372,
|
|
"mean_token_accuracy": 0.17441104650497435,
|
|
"num_tokens": 15795959.0,
|
|
"step": 7080
|
|
},
|
|
{
|
|
"entropy": 5.556308221817017,
|
|
"epoch": 0.7957544785758409,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004947172209867581,
|
|
"loss": 5.4359,
|
|
"mean_token_accuracy": 0.19030603319406508,
|
|
"num_tokens": 15805561.0,
|
|
"step": 7085
|
|
},
|
|
{
|
|
"entropy": 5.670266580581665,
|
|
"epoch": 0.7963160554837985,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004947085685590919,
|
|
"loss": 5.5429,
|
|
"mean_token_accuracy": 0.17361840307712556,
|
|
"num_tokens": 15816883.0,
|
|
"step": 7090
|
|
},
|
|
{
|
|
"entropy": 5.599012088775635,
|
|
"epoch": 0.796877632391756,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.0004946999091358196,
|
|
"loss": 5.5143,
|
|
"mean_token_accuracy": 0.1750064343214035,
|
|
"num_tokens": 15827753.0,
|
|
"step": 7095
|
|
},
|
|
{
|
|
"entropy": 5.696438932418824,
|
|
"epoch": 0.7974392092997136,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.000494691242717217,
|
|
"loss": 5.6216,
|
|
"mean_token_accuracy": 0.17230924516916274,
|
|
"num_tokens": 15840346.0,
|
|
"step": 7100
|
|
},
|
|
{
|
|
"entropy": 5.719204664230347,
|
|
"epoch": 0.7980007862076711,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.0004946825693035601,
|
|
"loss": 5.5637,
|
|
"mean_token_accuracy": 0.1729196384549141,
|
|
"num_tokens": 15851036.0,
|
|
"step": 7105
|
|
},
|
|
{
|
|
"entropy": 5.587104845046997,
|
|
"epoch": 0.7985623631156287,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.000494673888895125,
|
|
"loss": 5.5275,
|
|
"mean_token_accuracy": 0.17146896272897721,
|
|
"num_tokens": 15863154.0,
|
|
"step": 7110
|
|
},
|
|
{
|
|
"entropy": 5.701065158843994,
|
|
"epoch": 0.7991239400235862,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004946652014921881,
|
|
"loss": 5.6278,
|
|
"mean_token_accuracy": 0.17063457816839217,
|
|
"num_tokens": 15874543.0,
|
|
"step": 7115
|
|
},
|
|
{
|
|
"entropy": 5.72304859161377,
|
|
"epoch": 0.7996855169315438,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004946565070950259,
|
|
"loss": 5.5733,
|
|
"mean_token_accuracy": 0.1790310725569725,
|
|
"num_tokens": 15886221.0,
|
|
"step": 7120
|
|
},
|
|
{
|
|
"entropy": 5.629907655715942,
|
|
"epoch": 0.8002470938395013,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004946478057039153,
|
|
"loss": 5.5753,
|
|
"mean_token_accuracy": 0.1713734373450279,
|
|
"num_tokens": 15897602.0,
|
|
"step": 7125
|
|
},
|
|
{
|
|
"entropy": 5.666342258453369,
|
|
"epoch": 0.8008086707474589,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004946390973191335,
|
|
"loss": 5.5831,
|
|
"mean_token_accuracy": 0.17319839596748351,
|
|
"num_tokens": 15908030.0,
|
|
"step": 7130
|
|
},
|
|
{
|
|
"entropy": 5.7924469947814945,
|
|
"epoch": 0.8013702476554164,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004946303819409575,
|
|
"loss": 5.6163,
|
|
"mean_token_accuracy": 0.1725103735923767,
|
|
"num_tokens": 15918341.0,
|
|
"step": 7135
|
|
},
|
|
{
|
|
"entropy": 5.695781326293945,
|
|
"epoch": 0.801931824563374,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004946216595696652,
|
|
"loss": 5.603,
|
|
"mean_token_accuracy": 0.17535879611968994,
|
|
"num_tokens": 15929144.0,
|
|
"step": 7140
|
|
},
|
|
{
|
|
"entropy": 5.606329917907715,
|
|
"epoch": 0.8024934014713315,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004946129302055338,
|
|
"loss": 5.5329,
|
|
"mean_token_accuracy": 0.1738716945052147,
|
|
"num_tokens": 15940013.0,
|
|
"step": 7145
|
|
},
|
|
{
|
|
"entropy": 5.688619184494018,
|
|
"epoch": 0.8030549783792891,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004946041938488417,
|
|
"loss": 5.5763,
|
|
"mean_token_accuracy": 0.17095780223608018,
|
|
"num_tokens": 15950680.0,
|
|
"step": 7150
|
|
},
|
|
{
|
|
"entropy": 5.677084684371948,
|
|
"epoch": 0.8036165552872466,
|
|
"grad_norm": 2.703125,
|
|
"learning_rate": 0.0004945954504998668,
|
|
"loss": 5.5851,
|
|
"mean_token_accuracy": 0.17680688053369523,
|
|
"num_tokens": 15961462.0,
|
|
"step": 7155
|
|
},
|
|
{
|
|
"entropy": 5.642971038818359,
|
|
"epoch": 0.8041781321952042,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004945867001588877,
|
|
"loss": 5.4868,
|
|
"mean_token_accuracy": 0.18069790601730346,
|
|
"num_tokens": 15972788.0,
|
|
"step": 7160
|
|
},
|
|
{
|
|
"entropy": 5.6513982772827145,
|
|
"epoch": 0.8047397091031617,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004945779428261827,
|
|
"loss": 5.5576,
|
|
"mean_token_accuracy": 0.17967688292264938,
|
|
"num_tokens": 15983244.0,
|
|
"step": 7165
|
|
},
|
|
{
|
|
"entropy": 5.625182867050171,
|
|
"epoch": 0.8053012860111193,
|
|
"grad_norm": 3.5625,
|
|
"learning_rate": 0.000494569178502031,
|
|
"loss": 5.6605,
|
|
"mean_token_accuracy": 0.17140335887670516,
|
|
"num_tokens": 15994325.0,
|
|
"step": 7170
|
|
},
|
|
{
|
|
"entropy": 5.70230770111084,
|
|
"epoch": 0.8058628629190767,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004945604071867114,
|
|
"loss": 5.6433,
|
|
"mean_token_accuracy": 0.17412107884883882,
|
|
"num_tokens": 16005237.0,
|
|
"step": 7175
|
|
},
|
|
{
|
|
"entropy": 5.666613674163818,
|
|
"epoch": 0.8064244398270343,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.0004945516288805035,
|
|
"loss": 5.4701,
|
|
"mean_token_accuracy": 0.18182881772518159,
|
|
"num_tokens": 16015943.0,
|
|
"step": 7180
|
|
},
|
|
{
|
|
"entropy": 5.5966148853302,
|
|
"epoch": 0.8069860167349918,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004945428435836864,
|
|
"loss": 5.4701,
|
|
"mean_token_accuracy": 0.17533185780048371,
|
|
"num_tokens": 16026727.0,
|
|
"step": 7185
|
|
},
|
|
{
|
|
"entropy": 5.5975841045379635,
|
|
"epoch": 0.8075475936429494,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004945340512965401,
|
|
"loss": 5.5215,
|
|
"mean_token_accuracy": 0.170279598236084,
|
|
"num_tokens": 16039021.0,
|
|
"step": 7190
|
|
},
|
|
{
|
|
"entropy": 5.595854949951172,
|
|
"epoch": 0.8081091705509069,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.0004945252520193443,
|
|
"loss": 5.4756,
|
|
"mean_token_accuracy": 0.18279372304677963,
|
|
"num_tokens": 16050312.0,
|
|
"step": 7195
|
|
},
|
|
{
|
|
"entropy": 5.648495817184449,
|
|
"epoch": 0.8086707474588645,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004945164457523795,
|
|
"loss": 5.4123,
|
|
"mean_token_accuracy": 0.18160255551338195,
|
|
"num_tokens": 16060009.0,
|
|
"step": 7200
|
|
},
|
|
{
|
|
"entropy": 5.5399068832397464,
|
|
"epoch": 0.809232324366822,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004945076324959258,
|
|
"loss": 5.5771,
|
|
"mean_token_accuracy": 0.1707659438252449,
|
|
"num_tokens": 16072025.0,
|
|
"step": 7205
|
|
},
|
|
{
|
|
"entropy": 5.722390604019165,
|
|
"epoch": 0.8097939012747796,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004944988122502641,
|
|
"loss": 5.5741,
|
|
"mean_token_accuracy": 0.17293899059295653,
|
|
"num_tokens": 16083229.0,
|
|
"step": 7210
|
|
},
|
|
{
|
|
"entropy": 5.6083807945251465,
|
|
"epoch": 0.8103554781827371,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.000494489985015675,
|
|
"loss": 5.454,
|
|
"mean_token_accuracy": 0.17317892163991927,
|
|
"num_tokens": 16094936.0,
|
|
"step": 7215
|
|
},
|
|
{
|
|
"entropy": 5.573290109634399,
|
|
"epoch": 0.8109170550906947,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004944811507924396,
|
|
"loss": 5.5796,
|
|
"mean_token_accuracy": 0.17928414642810822,
|
|
"num_tokens": 16106182.0,
|
|
"step": 7220
|
|
},
|
|
{
|
|
"entropy": 5.627031373977661,
|
|
"epoch": 0.8114786319986522,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.0004944723095808393,
|
|
"loss": 5.4925,
|
|
"mean_token_accuracy": 0.18525396138429642,
|
|
"num_tokens": 16117006.0,
|
|
"step": 7225
|
|
},
|
|
{
|
|
"entropy": 5.60356388092041,
|
|
"epoch": 0.8120402089066098,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004944634613811555,
|
|
"loss": 5.5393,
|
|
"mean_token_accuracy": 0.17033829987049104,
|
|
"num_tokens": 16128892.0,
|
|
"step": 7230
|
|
},
|
|
{
|
|
"entropy": 5.674500131607056,
|
|
"epoch": 0.8126017858145673,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.00049445460619367,
|
|
"loss": 5.6377,
|
|
"mean_token_accuracy": 0.17414042353630066,
|
|
"num_tokens": 16139953.0,
|
|
"step": 7235
|
|
},
|
|
{
|
|
"entropy": 5.80377082824707,
|
|
"epoch": 0.8131633627225249,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 0.0004944457440186648,
|
|
"loss": 5.608,
|
|
"mean_token_accuracy": 0.16899279356002808,
|
|
"num_tokens": 16150103.0,
|
|
"step": 7240
|
|
},
|
|
{
|
|
"entropy": 5.686002254486084,
|
|
"epoch": 0.8137249396304824,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004944368748564219,
|
|
"loss": 5.6741,
|
|
"mean_token_accuracy": 0.1670638456940651,
|
|
"num_tokens": 16161666.0,
|
|
"step": 7245
|
|
},
|
|
{
|
|
"entropy": 5.637912130355835,
|
|
"epoch": 0.81428651653844,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004944279987072238,
|
|
"loss": 5.6185,
|
|
"mean_token_accuracy": 0.17147823870182038,
|
|
"num_tokens": 16172524.0,
|
|
"step": 7250
|
|
},
|
|
{
|
|
"entropy": 5.670833396911621,
|
|
"epoch": 0.8148480934463975,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004944191155713531,
|
|
"loss": 5.5546,
|
|
"mean_token_accuracy": 0.17929590195417405,
|
|
"num_tokens": 16183023.0,
|
|
"step": 7255
|
|
},
|
|
{
|
|
"entropy": 5.630833387374878,
|
|
"epoch": 0.8154096703543551,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004944102254490928,
|
|
"loss": 5.5812,
|
|
"mean_token_accuracy": 0.17907315492630005,
|
|
"num_tokens": 16193504.0,
|
|
"step": 7260
|
|
},
|
|
{
|
|
"entropy": 5.6302539825439455,
|
|
"epoch": 0.8159712472623126,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004944013283407257,
|
|
"loss": 5.524,
|
|
"mean_token_accuracy": 0.17752917259931564,
|
|
"num_tokens": 16204730.0,
|
|
"step": 7265
|
|
},
|
|
{
|
|
"entropy": 5.677153396606445,
|
|
"epoch": 0.8165328241702701,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.0004943924242465352,
|
|
"loss": 5.546,
|
|
"mean_token_accuracy": 0.17661892920732497,
|
|
"num_tokens": 16214496.0,
|
|
"step": 7270
|
|
},
|
|
{
|
|
"entropy": 5.601825809478759,
|
|
"epoch": 0.8170944010782276,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004943835131668049,
|
|
"loss": 5.4818,
|
|
"mean_token_accuracy": 0.18293384313583375,
|
|
"num_tokens": 16225494.0,
|
|
"step": 7275
|
|
},
|
|
{
|
|
"entropy": 5.547914457321167,
|
|
"epoch": 0.8176559779861852,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004943745951018184,
|
|
"loss": 5.4374,
|
|
"mean_token_accuracy": 0.17961118072271348,
|
|
"num_tokens": 16236385.0,
|
|
"step": 7280
|
|
},
|
|
{
|
|
"entropy": 5.641435241699218,
|
|
"epoch": 0.8182175548941427,
|
|
"grad_norm": 2.859375,
|
|
"learning_rate": 0.0004943656700518597,
|
|
"loss": 5.6054,
|
|
"mean_token_accuracy": 0.18158860951662065,
|
|
"num_tokens": 16247300.0,
|
|
"step": 7285
|
|
},
|
|
{
|
|
"entropy": 5.732605123519898,
|
|
"epoch": 0.8187791318021003,
|
|
"grad_norm": 2.96875,
|
|
"learning_rate": 0.0004943567380172129,
|
|
"loss": 5.6305,
|
|
"mean_token_accuracy": 0.17236913442611695,
|
|
"num_tokens": 16259326.0,
|
|
"step": 7290
|
|
},
|
|
{
|
|
"entropy": 5.7591828346252445,
|
|
"epoch": 0.8193407087100578,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004943477989981627,
|
|
"loss": 5.602,
|
|
"mean_token_accuracy": 0.17550345212221147,
|
|
"num_tokens": 16270559.0,
|
|
"step": 7295
|
|
},
|
|
{
|
|
"entropy": 5.639893245697022,
|
|
"epoch": 0.8199022856180154,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004943388529949933,
|
|
"loss": 5.5772,
|
|
"mean_token_accuracy": 0.1705007091164589,
|
|
"num_tokens": 16283120.0,
|
|
"step": 7300
|
|
},
|
|
{
|
|
"entropy": 5.718288516998291,
|
|
"epoch": 0.8204638625259729,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004943299000079899,
|
|
"loss": 5.5973,
|
|
"mean_token_accuracy": 0.17923042923212051,
|
|
"num_tokens": 16293449.0,
|
|
"step": 7305
|
|
},
|
|
{
|
|
"entropy": 5.689585828781128,
|
|
"epoch": 0.8210254394339305,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004943209400374373,
|
|
"loss": 5.6226,
|
|
"mean_token_accuracy": 0.1675799623131752,
|
|
"num_tokens": 16305144.0,
|
|
"step": 7310
|
|
},
|
|
{
|
|
"entropy": 5.600336360931396,
|
|
"epoch": 0.821587016341888,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.000494311973083621,
|
|
"loss": 5.4373,
|
|
"mean_token_accuracy": 0.1817849412560463,
|
|
"num_tokens": 16316728.0,
|
|
"step": 7315
|
|
},
|
|
{
|
|
"entropy": 5.700897979736328,
|
|
"epoch": 0.8221485932498456,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004943029991468264,
|
|
"loss": 5.7131,
|
|
"mean_token_accuracy": 0.16940131336450576,
|
|
"num_tokens": 16329117.0,
|
|
"step": 7320
|
|
},
|
|
{
|
|
"entropy": 5.785341358184814,
|
|
"epoch": 0.8227101701578031,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004942940182273393,
|
|
"loss": 5.6723,
|
|
"mean_token_accuracy": 0.1732812389731407,
|
|
"num_tokens": 16341651.0,
|
|
"step": 7325
|
|
},
|
|
{
|
|
"entropy": 5.781979703903199,
|
|
"epoch": 0.8232717470657607,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.0004942850303254455,
|
|
"loss": 5.6388,
|
|
"mean_token_accuracy": 0.1734175890684128,
|
|
"num_tokens": 16353220.0,
|
|
"step": 7330
|
|
},
|
|
{
|
|
"entropy": 5.787456226348877,
|
|
"epoch": 0.8238333239737182,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004942760354414313,
|
|
"loss": 5.6728,
|
|
"mean_token_accuracy": 0.16955814212560655,
|
|
"num_tokens": 16363748.0,
|
|
"step": 7335
|
|
},
|
|
{
|
|
"entropy": 5.504583692550659,
|
|
"epoch": 0.8243949008816758,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004942670335755831,
|
|
"loss": 5.3632,
|
|
"mean_token_accuracy": 0.18503506630659103,
|
|
"num_tokens": 16374086.0,
|
|
"step": 7340
|
|
},
|
|
{
|
|
"entropy": 5.61326494216919,
|
|
"epoch": 0.8249564777896333,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004942580247281876,
|
|
"loss": 5.5252,
|
|
"mean_token_accuracy": 0.18080331087112428,
|
|
"num_tokens": 16384140.0,
|
|
"step": 7345
|
|
},
|
|
{
|
|
"entropy": 5.739736843109131,
|
|
"epoch": 0.8255180546975909,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004942490088995315,
|
|
"loss": 5.6474,
|
|
"mean_token_accuracy": 0.16896117627620696,
|
|
"num_tokens": 16395940.0,
|
|
"step": 7350
|
|
},
|
|
{
|
|
"entropy": 5.641144847869873,
|
|
"epoch": 0.8260796316055484,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004942399860899018,
|
|
"loss": 5.4953,
|
|
"mean_token_accuracy": 0.17636250406503678,
|
|
"num_tokens": 16406667.0,
|
|
"step": 7355
|
|
},
|
|
{
|
|
"entropy": 5.708989858627319,
|
|
"epoch": 0.826641208513506,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004942309562995862,
|
|
"loss": 5.6242,
|
|
"mean_token_accuracy": 0.1691759780049324,
|
|
"num_tokens": 16418621.0,
|
|
"step": 7360
|
|
},
|
|
{
|
|
"entropy": 5.633051013946533,
|
|
"epoch": 0.8272027854214634,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.0004942219195288716,
|
|
"loss": 5.5534,
|
|
"mean_token_accuracy": 0.18062943816184998,
|
|
"num_tokens": 16429576.0,
|
|
"step": 7365
|
|
},
|
|
{
|
|
"entropy": 5.6591043949127195,
|
|
"epoch": 0.827764362329421,
|
|
"grad_norm": 3.015625,
|
|
"learning_rate": 0.0004942128757780463,
|
|
"loss": 5.6542,
|
|
"mean_token_accuracy": 0.16728534400463105,
|
|
"num_tokens": 16441004.0,
|
|
"step": 7370
|
|
},
|
|
{
|
|
"entropy": 5.645237064361572,
|
|
"epoch": 0.8283259392373785,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004942038250473979,
|
|
"loss": 5.6023,
|
|
"mean_token_accuracy": 0.16919308304786682,
|
|
"num_tokens": 16452183.0,
|
|
"step": 7375
|
|
},
|
|
{
|
|
"entropy": 5.686494016647339,
|
|
"epoch": 0.8288875161453361,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004941947673372147,
|
|
"loss": 5.5464,
|
|
"mean_token_accuracy": 0.17770857363939285,
|
|
"num_tokens": 16463552.0,
|
|
"step": 7380
|
|
},
|
|
{
|
|
"entropy": 5.699704217910766,
|
|
"epoch": 0.8294490930532936,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004941857026477851,
|
|
"loss": 5.5845,
|
|
"mean_token_accuracy": 0.18207204043865205,
|
|
"num_tokens": 16474062.0,
|
|
"step": 7385
|
|
},
|
|
{
|
|
"entropy": 5.745741939544677,
|
|
"epoch": 0.8300106699612512,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.0004941766309793978,
|
|
"loss": 5.6979,
|
|
"mean_token_accuracy": 0.17188157886266708,
|
|
"num_tokens": 16487377.0,
|
|
"step": 7390
|
|
},
|
|
{
|
|
"entropy": 5.786658191680909,
|
|
"epoch": 0.8305722468692087,
|
|
"grad_norm": 2.84375,
|
|
"learning_rate": 0.0004941675523323414,
|
|
"loss": 5.6126,
|
|
"mean_token_accuracy": 0.18275642096996308,
|
|
"num_tokens": 16499704.0,
|
|
"step": 7395
|
|
},
|
|
{
|
|
"entropy": 5.634381628036499,
|
|
"epoch": 0.8311338237771663,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004941584667069052,
|
|
"loss": 5.6333,
|
|
"mean_token_accuracy": 0.1756630226969719,
|
|
"num_tokens": 16511954.0,
|
|
"step": 7400
|
|
},
|
|
{
|
|
"entropy": 5.5319935321807865,
|
|
"epoch": 0.8316954006851238,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.0004941493741033784,
|
|
"loss": 5.4618,
|
|
"mean_token_accuracy": 0.17399709224700927,
|
|
"num_tokens": 16522602.0,
|
|
"step": 7405
|
|
},
|
|
{
|
|
"entropy": 5.719286727905273,
|
|
"epoch": 0.8322569775930814,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.0004941402745220507,
|
|
"loss": 5.614,
|
|
"mean_token_accuracy": 0.16763484328985215,
|
|
"num_tokens": 16534233.0,
|
|
"step": 7410
|
|
},
|
|
{
|
|
"entropy": 5.790324878692627,
|
|
"epoch": 0.8328185545010389,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 0.0004941311679632115,
|
|
"loss": 5.6848,
|
|
"mean_token_accuracy": 0.16965586543083191,
|
|
"num_tokens": 16546120.0,
|
|
"step": 7415
|
|
},
|
|
{
|
|
"entropy": 5.696516418457032,
|
|
"epoch": 0.8333801314089965,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.000494122054427151,
|
|
"loss": 5.5825,
|
|
"mean_token_accuracy": 0.17838511914014815,
|
|
"num_tokens": 16556830.0,
|
|
"step": 7420
|
|
},
|
|
{
|
|
"entropy": 5.579590797424316,
|
|
"epoch": 0.833941708316954,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004941129339141592,
|
|
"loss": 5.5518,
|
|
"mean_token_accuracy": 0.17398969531059266,
|
|
"num_tokens": 16567436.0,
|
|
"step": 7425
|
|
},
|
|
{
|
|
"entropy": 5.674097537994385,
|
|
"epoch": 0.8345032852249116,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004941038064245267,
|
|
"loss": 5.511,
|
|
"mean_token_accuracy": 0.17446282207965852,
|
|
"num_tokens": 16577807.0,
|
|
"step": 7430
|
|
},
|
|
{
|
|
"entropy": 5.77416353225708,
|
|
"epoch": 0.8350648621328691,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.000494094671958544,
|
|
"loss": 5.5872,
|
|
"mean_token_accuracy": 0.17741088271141053,
|
|
"num_tokens": 16589745.0,
|
|
"step": 7435
|
|
},
|
|
{
|
|
"entropy": 5.740570402145385,
|
|
"epoch": 0.8356264390408267,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004940855305165019,
|
|
"loss": 5.6479,
|
|
"mean_token_accuracy": 0.17407170534133912,
|
|
"num_tokens": 16600727.0,
|
|
"step": 7440
|
|
},
|
|
{
|
|
"entropy": 5.6241954326629635,
|
|
"epoch": 0.8361880159487842,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004940763820986916,
|
|
"loss": 5.5494,
|
|
"mean_token_accuracy": 0.1744701460003853,
|
|
"num_tokens": 16611091.0,
|
|
"step": 7445
|
|
},
|
|
{
|
|
"entropy": 5.561136770248413,
|
|
"epoch": 0.8367495928567418,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004940672267054044,
|
|
"loss": 5.5236,
|
|
"mean_token_accuracy": 0.17295840829610826,
|
|
"num_tokens": 16622550.0,
|
|
"step": 7450
|
|
},
|
|
{
|
|
"entropy": 5.650055027008056,
|
|
"epoch": 0.8373111697646993,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004940580643369316,
|
|
"loss": 5.5293,
|
|
"mean_token_accuracy": 0.17199278622865677,
|
|
"num_tokens": 16634243.0,
|
|
"step": 7455
|
|
},
|
|
{
|
|
"entropy": 5.626168346405029,
|
|
"epoch": 0.8378727466726568,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004940488949935651,
|
|
"loss": 5.5426,
|
|
"mean_token_accuracy": 0.1746353030204773,
|
|
"num_tokens": 16645266.0,
|
|
"step": 7460
|
|
},
|
|
{
|
|
"entropy": 5.662431383132935,
|
|
"epoch": 0.8384343235806143,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004940397186755968,
|
|
"loss": 5.5385,
|
|
"mean_token_accuracy": 0.1740131050348282,
|
|
"num_tokens": 16654365.0,
|
|
"step": 7465
|
|
},
|
|
{
|
|
"entropy": 5.678260850906372,
|
|
"epoch": 0.8389959004885719,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004940305353833191,
|
|
"loss": 5.5223,
|
|
"mean_token_accuracy": 0.17889359295368196,
|
|
"num_tokens": 16665251.0,
|
|
"step": 7470
|
|
},
|
|
{
|
|
"entropy": 5.683456897735596,
|
|
"epoch": 0.8395574773965294,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.000494021345117024,
|
|
"loss": 5.5801,
|
|
"mean_token_accuracy": 0.17653381526470185,
|
|
"num_tokens": 16676209.0,
|
|
"step": 7475
|
|
},
|
|
{
|
|
"entropy": 5.65171365737915,
|
|
"epoch": 0.840119054304487,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004940121478770044,
|
|
"loss": 5.509,
|
|
"mean_token_accuracy": 0.17750734388828276,
|
|
"num_tokens": 16687213.0,
|
|
"step": 7480
|
|
},
|
|
{
|
|
"entropy": 5.599236917495728,
|
|
"epoch": 0.8406806312124445,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004940029436635531,
|
|
"loss": 5.5587,
|
|
"mean_token_accuracy": 0.1815314069390297,
|
|
"num_tokens": 16697920.0,
|
|
"step": 7485
|
|
},
|
|
{
|
|
"entropy": 5.644923448562622,
|
|
"epoch": 0.8412422081204021,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004939937324769631,
|
|
"loss": 5.5343,
|
|
"mean_token_accuracy": 0.1698709785938263,
|
|
"num_tokens": 16707815.0,
|
|
"step": 7490
|
|
},
|
|
{
|
|
"entropy": 5.684829998016357,
|
|
"epoch": 0.8418037850283596,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004939845143175276,
|
|
"loss": 5.4632,
|
|
"mean_token_accuracy": 0.17765185087919236,
|
|
"num_tokens": 16719221.0,
|
|
"step": 7495
|
|
},
|
|
{
|
|
"entropy": 5.598668909072876,
|
|
"epoch": 0.8423653619363172,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004939752891855404,
|
|
"loss": 5.4956,
|
|
"mean_token_accuracy": 0.17193463742733,
|
|
"num_tokens": 16731741.0,
|
|
"step": 7500
|
|
},
|
|
{
|
|
"entropy": 5.585342645645142,
|
|
"epoch": 0.8429269388442747,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004939660570812951,
|
|
"loss": 5.4995,
|
|
"mean_token_accuracy": 0.18328134715557098,
|
|
"num_tokens": 16742795.0,
|
|
"step": 7505
|
|
},
|
|
{
|
|
"entropy": 5.596073246002197,
|
|
"epoch": 0.8434885157522323,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004939568180050855,
|
|
"loss": 5.5018,
|
|
"mean_token_accuracy": 0.17426613122224807,
|
|
"num_tokens": 16753139.0,
|
|
"step": 7510
|
|
},
|
|
{
|
|
"entropy": 5.642351818084717,
|
|
"epoch": 0.8440500926601898,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004939475719572059,
|
|
"loss": 5.5202,
|
|
"mean_token_accuracy": 0.17698739916086198,
|
|
"num_tokens": 16764246.0,
|
|
"step": 7515
|
|
},
|
|
{
|
|
"entropy": 5.725074625015258,
|
|
"epoch": 0.8446116695681474,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004939383189379507,
|
|
"loss": 5.6383,
|
|
"mean_token_accuracy": 0.16711130291223525,
|
|
"num_tokens": 16776039.0,
|
|
"step": 7520
|
|
},
|
|
{
|
|
"entropy": 5.707843255996704,
|
|
"epoch": 0.8451732464761049,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.0004939290589476145,
|
|
"loss": 5.6164,
|
|
"mean_token_accuracy": 0.17707410156726838,
|
|
"num_tokens": 16786979.0,
|
|
"step": 7525
|
|
},
|
|
{
|
|
"entropy": 5.695209598541259,
|
|
"epoch": 0.8457348233840625,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004939197919864922,
|
|
"loss": 5.6391,
|
|
"mean_token_accuracy": 0.17317430824041366,
|
|
"num_tokens": 16798113.0,
|
|
"step": 7530
|
|
},
|
|
{
|
|
"entropy": 5.639262914657593,
|
|
"epoch": 0.84629640029202,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004939105180548788,
|
|
"loss": 5.5605,
|
|
"mean_token_accuracy": 0.1727459102869034,
|
|
"num_tokens": 16809072.0,
|
|
"step": 7535
|
|
},
|
|
{
|
|
"entropy": 5.579399967193604,
|
|
"epoch": 0.8468579771999776,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004939012371530696,
|
|
"loss": 5.3667,
|
|
"mean_token_accuracy": 0.17584865242242814,
|
|
"num_tokens": 16819548.0,
|
|
"step": 7540
|
|
},
|
|
{
|
|
"entropy": 5.764654064178467,
|
|
"epoch": 0.8474195541079351,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.0004938919492813601,
|
|
"loss": 5.6841,
|
|
"mean_token_accuracy": 0.16631856858730315,
|
|
"num_tokens": 16831935.0,
|
|
"step": 7545
|
|
},
|
|
{
|
|
"entropy": 5.695077657699585,
|
|
"epoch": 0.8479811310158927,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004938826544400461,
|
|
"loss": 5.5864,
|
|
"mean_token_accuracy": 0.1799225017428398,
|
|
"num_tokens": 16842961.0,
|
|
"step": 7550
|
|
},
|
|
{
|
|
"entropy": 5.617971754074096,
|
|
"epoch": 0.8485427079238502,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004938733526294234,
|
|
"loss": 5.4868,
|
|
"mean_token_accuracy": 0.17287273705005646,
|
|
"num_tokens": 16854392.0,
|
|
"step": 7555
|
|
},
|
|
{
|
|
"entropy": 5.696143531799317,
|
|
"epoch": 0.8491042848318077,
|
|
"grad_norm": 3.96875,
|
|
"learning_rate": 0.0004938640438497883,
|
|
"loss": 5.5815,
|
|
"mean_token_accuracy": 0.1726732447743416,
|
|
"num_tokens": 16865443.0,
|
|
"step": 7560
|
|
},
|
|
{
|
|
"entropy": 5.720878171920776,
|
|
"epoch": 0.8496658617397652,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004938547281014372,
|
|
"loss": 5.5305,
|
|
"mean_token_accuracy": 0.17506200224161148,
|
|
"num_tokens": 16876854.0,
|
|
"step": 7565
|
|
},
|
|
{
|
|
"entropy": 5.691568088531494,
|
|
"epoch": 0.8502274386477228,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004938454053846666,
|
|
"loss": 5.6048,
|
|
"mean_token_accuracy": 0.1708382248878479,
|
|
"num_tokens": 16888823.0,
|
|
"step": 7570
|
|
},
|
|
{
|
|
"entropy": 5.561884880065918,
|
|
"epoch": 0.8507890155556803,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004938360756997735,
|
|
"loss": 5.5381,
|
|
"mean_token_accuracy": 0.178067547082901,
|
|
"num_tokens": 16898807.0,
|
|
"step": 7575
|
|
},
|
|
{
|
|
"entropy": 5.7173820495605465,
|
|
"epoch": 0.8513505924636379,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004938267390470547,
|
|
"loss": 5.6597,
|
|
"mean_token_accuracy": 0.16430477797985077,
|
|
"num_tokens": 16911258.0,
|
|
"step": 7580
|
|
},
|
|
{
|
|
"entropy": 5.764630603790283,
|
|
"epoch": 0.8519121693715954,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004938173954268079,
|
|
"loss": 5.6159,
|
|
"mean_token_accuracy": 0.17393420338630677,
|
|
"num_tokens": 16922557.0,
|
|
"step": 7585
|
|
},
|
|
{
|
|
"entropy": 5.660285234451294,
|
|
"epoch": 0.852473746279553,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004938080448393302,
|
|
"loss": 5.6466,
|
|
"mean_token_accuracy": 0.16738674640655518,
|
|
"num_tokens": 16935330.0,
|
|
"step": 7590
|
|
},
|
|
{
|
|
"entropy": 5.715785789489746,
|
|
"epoch": 0.8530353231875105,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004937986872849195,
|
|
"loss": 5.564,
|
|
"mean_token_accuracy": 0.1769200623035431,
|
|
"num_tokens": 16945361.0,
|
|
"step": 7595
|
|
},
|
|
{
|
|
"entropy": 5.593125534057617,
|
|
"epoch": 0.8535969000954681,
|
|
"grad_norm": 3.21875,
|
|
"learning_rate": 0.0004937893227638738,
|
|
"loss": 5.4239,
|
|
"mean_token_accuracy": 0.18120268732309341,
|
|
"num_tokens": 16955363.0,
|
|
"step": 7600
|
|
},
|
|
{
|
|
"entropy": 5.5371777534484865,
|
|
"epoch": 0.8541584770034256,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.0004937799512764912,
|
|
"loss": 5.4883,
|
|
"mean_token_accuracy": 0.1764076679944992,
|
|
"num_tokens": 16965267.0,
|
|
"step": 7605
|
|
},
|
|
{
|
|
"entropy": 5.720862817764282,
|
|
"epoch": 0.8547200539113832,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00049377057282307,
|
|
"loss": 5.7036,
|
|
"mean_token_accuracy": 0.1694671779870987,
|
|
"num_tokens": 16977528.0,
|
|
"step": 7610
|
|
},
|
|
{
|
|
"entropy": 5.666491079330444,
|
|
"epoch": 0.8552816308193407,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.000493761187403909,
|
|
"loss": 5.551,
|
|
"mean_token_accuracy": 0.17010014057159423,
|
|
"num_tokens": 16987326.0,
|
|
"step": 7615
|
|
},
|
|
{
|
|
"entropy": 5.744333124160766,
|
|
"epoch": 0.8558432077272983,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.000493751795019307,
|
|
"loss": 5.6014,
|
|
"mean_token_accuracy": 0.17535028159618377,
|
|
"num_tokens": 16999127.0,
|
|
"step": 7620
|
|
},
|
|
{
|
|
"entropy": 5.636659574508667,
|
|
"epoch": 0.8564047846352558,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004937423956695629,
|
|
"loss": 5.4968,
|
|
"mean_token_accuracy": 0.18116801530122756,
|
|
"num_tokens": 17009929.0,
|
|
"step": 7625
|
|
},
|
|
{
|
|
"entropy": 5.737601280212402,
|
|
"epoch": 0.8569663615432134,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004937329893549762,
|
|
"loss": 5.6286,
|
|
"mean_token_accuracy": 0.17096799463033677,
|
|
"num_tokens": 17020909.0,
|
|
"step": 7630
|
|
},
|
|
{
|
|
"entropy": 5.701044321060181,
|
|
"epoch": 0.8575279384511709,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004937235760758462,
|
|
"loss": 5.5512,
|
|
"mean_token_accuracy": 0.1736280143260956,
|
|
"num_tokens": 17031358.0,
|
|
"step": 7635
|
|
},
|
|
{
|
|
"entropy": 5.593687915802002,
|
|
"epoch": 0.8580895153591285,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004937141558324726,
|
|
"loss": 5.5988,
|
|
"mean_token_accuracy": 0.17965880483388902,
|
|
"num_tokens": 17042566.0,
|
|
"step": 7640
|
|
},
|
|
{
|
|
"entropy": 5.725991582870483,
|
|
"epoch": 0.858651092267086,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004937047286251556,
|
|
"loss": 5.6186,
|
|
"mean_token_accuracy": 0.16632862389087677,
|
|
"num_tokens": 17054998.0,
|
|
"step": 7645
|
|
},
|
|
{
|
|
"entropy": 5.731683683395386,
|
|
"epoch": 0.8592126691750436,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004936952944541952,
|
|
"loss": 5.4812,
|
|
"mean_token_accuracy": 0.1752291664481163,
|
|
"num_tokens": 17064876.0,
|
|
"step": 7650
|
|
},
|
|
{
|
|
"entropy": 5.5959851264953615,
|
|
"epoch": 0.859774246083001,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004936858533198917,
|
|
"loss": 5.5308,
|
|
"mean_token_accuracy": 0.17613427937030793,
|
|
"num_tokens": 17075310.0,
|
|
"step": 7655
|
|
},
|
|
{
|
|
"entropy": 5.535517358779908,
|
|
"epoch": 0.8603358229909586,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.000493676405222546,
|
|
"loss": 5.4516,
|
|
"mean_token_accuracy": 0.18418441861867904,
|
|
"num_tokens": 17086023.0,
|
|
"step": 7660
|
|
},
|
|
{
|
|
"entropy": 5.640001392364502,
|
|
"epoch": 0.8608973998989161,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004936669501624586,
|
|
"loss": 5.5222,
|
|
"mean_token_accuracy": 0.1752171367406845,
|
|
"num_tokens": 17097554.0,
|
|
"step": 7665
|
|
},
|
|
{
|
|
"entropy": 5.877073812484741,
|
|
"epoch": 0.8614589768068737,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.0004936574881399308,
|
|
"loss": 5.6591,
|
|
"mean_token_accuracy": 0.16699210405349732,
|
|
"num_tokens": 17108890.0,
|
|
"step": 7670
|
|
},
|
|
{
|
|
"entropy": 5.629813098907471,
|
|
"epoch": 0.8620205537148312,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.0004936480191552637,
|
|
"loss": 5.4859,
|
|
"mean_token_accuracy": 0.1760300353169441,
|
|
"num_tokens": 17120651.0,
|
|
"step": 7675
|
|
},
|
|
{
|
|
"entropy": 5.688474035263061,
|
|
"epoch": 0.8625821306227888,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004936385432087589,
|
|
"loss": 5.6257,
|
|
"mean_token_accuracy": 0.17594545781612397,
|
|
"num_tokens": 17131306.0,
|
|
"step": 7680
|
|
},
|
|
{
|
|
"entropy": 5.794492387771607,
|
|
"epoch": 0.8631437075307463,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004936290603007181,
|
|
"loss": 5.7663,
|
|
"mean_token_accuracy": 0.1662360265851021,
|
|
"num_tokens": 17142779.0,
|
|
"step": 7685
|
|
},
|
|
{
|
|
"entropy": 5.786104488372803,
|
|
"epoch": 0.8637052844387039,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004936195704314432,
|
|
"loss": 5.6502,
|
|
"mean_token_accuracy": 0.179743430018425,
|
|
"num_tokens": 17154992.0,
|
|
"step": 7690
|
|
},
|
|
{
|
|
"entropy": 5.664245700836181,
|
|
"epoch": 0.8642668613466614,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 0.0004936100736012363,
|
|
"loss": 5.6156,
|
|
"mean_token_accuracy": 0.1801836758852005,
|
|
"num_tokens": 17166089.0,
|
|
"step": 7695
|
|
},
|
|
{
|
|
"entropy": 5.6404181003570555,
|
|
"epoch": 0.864828438254619,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004936005698104,
|
|
"loss": 5.5369,
|
|
"mean_token_accuracy": 0.17083394825458526,
|
|
"num_tokens": 17175691.0,
|
|
"step": 7700
|
|
},
|
|
{
|
|
"entropy": 5.680741786956787,
|
|
"epoch": 0.8653900151625765,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.0004935910590592367,
|
|
"loss": 5.5842,
|
|
"mean_token_accuracy": 0.17225186973810197,
|
|
"num_tokens": 17186466.0,
|
|
"step": 7705
|
|
},
|
|
{
|
|
"entropy": 5.57908411026001,
|
|
"epoch": 0.8659515920705341,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004935815413480494,
|
|
"loss": 5.3712,
|
|
"mean_token_accuracy": 0.18632677644491197,
|
|
"num_tokens": 17198520.0,
|
|
"step": 7710
|
|
},
|
|
{
|
|
"entropy": 5.621090602874756,
|
|
"epoch": 0.8665131689784916,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.000493572016677141,
|
|
"loss": 5.5928,
|
|
"mean_token_accuracy": 0.16931649297475815,
|
|
"num_tokens": 17210496.0,
|
|
"step": 7715
|
|
},
|
|
{
|
|
"entropy": 5.646635103225708,
|
|
"epoch": 0.8670747458864492,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004935624850468148,
|
|
"loss": 5.5841,
|
|
"mean_token_accuracy": 0.17751506716012955,
|
|
"num_tokens": 17221631.0,
|
|
"step": 7720
|
|
},
|
|
{
|
|
"entropy": 5.721542406082153,
|
|
"epoch": 0.8676363227944067,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004935529464573742,
|
|
"loss": 5.6406,
|
|
"mean_token_accuracy": 0.16330553442239762,
|
|
"num_tokens": 17233316.0,
|
|
"step": 7725
|
|
},
|
|
{
|
|
"entropy": 5.686434936523438,
|
|
"epoch": 0.8681978997023643,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004935434009091232,
|
|
"loss": 5.5368,
|
|
"mean_token_accuracy": 0.18126085251569748,
|
|
"num_tokens": 17245761.0,
|
|
"step": 7730
|
|
},
|
|
{
|
|
"entropy": 5.636671352386474,
|
|
"epoch": 0.8687594766103218,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004935338484023655,
|
|
"loss": 5.5442,
|
|
"mean_token_accuracy": 0.1800290733575821,
|
|
"num_tokens": 17255007.0,
|
|
"step": 7735
|
|
},
|
|
{
|
|
"entropy": 5.705508899688721,
|
|
"epoch": 0.8693210535182794,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004935242889374052,
|
|
"loss": 5.4918,
|
|
"mean_token_accuracy": 0.18120547384023666,
|
|
"num_tokens": 17265378.0,
|
|
"step": 7740
|
|
},
|
|
{
|
|
"entropy": 5.703558301925659,
|
|
"epoch": 0.8698826304262369,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004935147225145469,
|
|
"loss": 5.586,
|
|
"mean_token_accuracy": 0.1717560335993767,
|
|
"num_tokens": 17277202.0,
|
|
"step": 7745
|
|
},
|
|
{
|
|
"entropy": 5.601219987869262,
|
|
"epoch": 0.8704442073341944,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004935051491340951,
|
|
"loss": 5.5416,
|
|
"mean_token_accuracy": 0.18179851174354553,
|
|
"num_tokens": 17287006.0,
|
|
"step": 7750
|
|
},
|
|
{
|
|
"entropy": 5.65317587852478,
|
|
"epoch": 0.8710057842421519,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004934955687963546,
|
|
"loss": 5.5011,
|
|
"mean_token_accuracy": 0.1875390663743019,
|
|
"num_tokens": 17297387.0,
|
|
"step": 7755
|
|
},
|
|
{
|
|
"entropy": 5.761202096939087,
|
|
"epoch": 0.8715673611501095,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.0004934859815016304,
|
|
"loss": 5.7233,
|
|
"mean_token_accuracy": 0.1688181608915329,
|
|
"num_tokens": 17310364.0,
|
|
"step": 7760
|
|
},
|
|
{
|
|
"entropy": 5.607451915740967,
|
|
"epoch": 0.872128938058067,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004934763872502278,
|
|
"loss": 5.5627,
|
|
"mean_token_accuracy": 0.1814206749200821,
|
|
"num_tokens": 17321282.0,
|
|
"step": 7765
|
|
},
|
|
{
|
|
"entropy": 5.700820446014404,
|
|
"epoch": 0.8726905149660246,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004934667860424523,
|
|
"loss": 5.6121,
|
|
"mean_token_accuracy": 0.1698084369301796,
|
|
"num_tokens": 17331755.0,
|
|
"step": 7770
|
|
},
|
|
{
|
|
"entropy": 5.639352035522461,
|
|
"epoch": 0.8732520918739821,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004934571778786096,
|
|
"loss": 5.5432,
|
|
"mean_token_accuracy": 0.17260874658823014,
|
|
"num_tokens": 17342542.0,
|
|
"step": 7775
|
|
},
|
|
{
|
|
"entropy": 5.652365875244141,
|
|
"epoch": 0.8738136687819397,
|
|
"grad_norm": 3.546875,
|
|
"learning_rate": 0.0004934475627590057,
|
|
"loss": 5.5132,
|
|
"mean_token_accuracy": 0.17599326968193055,
|
|
"num_tokens": 17353150.0,
|
|
"step": 7780
|
|
},
|
|
{
|
|
"entropy": 5.651996517181397,
|
|
"epoch": 0.8743752456898972,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004934379406839466,
|
|
"loss": 5.5507,
|
|
"mean_token_accuracy": 0.17613325417041778,
|
|
"num_tokens": 17363901.0,
|
|
"step": 7785
|
|
},
|
|
{
|
|
"entropy": 5.692946100234986,
|
|
"epoch": 0.8749368225978548,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004934283116537387,
|
|
"loss": 5.4675,
|
|
"mean_token_accuracy": 0.18212807178497314,
|
|
"num_tokens": 17374429.0,
|
|
"step": 7790
|
|
},
|
|
{
|
|
"entropy": 5.648609066009522,
|
|
"epoch": 0.8754983995058123,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004934186756686888,
|
|
"loss": 5.6034,
|
|
"mean_token_accuracy": 0.17457506209611892,
|
|
"num_tokens": 17384952.0,
|
|
"step": 7795
|
|
},
|
|
{
|
|
"entropy": 5.608210659027099,
|
|
"epoch": 0.8760599764137699,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004934090327291034,
|
|
"loss": 5.568,
|
|
"mean_token_accuracy": 0.17070787400007248,
|
|
"num_tokens": 17397771.0,
|
|
"step": 7800
|
|
},
|
|
{
|
|
"entropy": 5.661837339401245,
|
|
"epoch": 0.8766215533217274,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004933993828352898,
|
|
"loss": 5.4723,
|
|
"mean_token_accuracy": 0.17718206495046615,
|
|
"num_tokens": 17407748.0,
|
|
"step": 7805
|
|
},
|
|
{
|
|
"entropy": 5.594266033172607,
|
|
"epoch": 0.877183130229685,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004933897259875551,
|
|
"loss": 5.4573,
|
|
"mean_token_accuracy": 0.17614827752113343,
|
|
"num_tokens": 17418572.0,
|
|
"step": 7810
|
|
},
|
|
{
|
|
"entropy": 5.580442571640015,
|
|
"epoch": 0.8777447071376425,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.0004933800621862069,
|
|
"loss": 5.4914,
|
|
"mean_token_accuracy": 0.1770696833729744,
|
|
"num_tokens": 17429909.0,
|
|
"step": 7815
|
|
},
|
|
{
|
|
"entropy": 5.638146686553955,
|
|
"epoch": 0.8783062840456001,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004933703914315527,
|
|
"loss": 5.5361,
|
|
"mean_token_accuracy": 0.1720555230975151,
|
|
"num_tokens": 17441143.0,
|
|
"step": 7820
|
|
},
|
|
{
|
|
"entropy": 5.721170806884766,
|
|
"epoch": 0.8788678609535576,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004933607137239006,
|
|
"loss": 5.6498,
|
|
"mean_token_accuracy": 0.1660382330417633,
|
|
"num_tokens": 17452156.0,
|
|
"step": 7825
|
|
},
|
|
{
|
|
"entropy": 5.608365058898926,
|
|
"epoch": 0.8794294378615152,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004933510290635587,
|
|
"loss": 5.5563,
|
|
"mean_token_accuracy": 0.17311571389436722,
|
|
"num_tokens": 17463873.0,
|
|
"step": 7830
|
|
},
|
|
{
|
|
"entropy": 5.59021520614624,
|
|
"epoch": 0.8799910147694727,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004933413374508353,
|
|
"loss": 5.4763,
|
|
"mean_token_accuracy": 0.1821392759680748,
|
|
"num_tokens": 17474180.0,
|
|
"step": 7835
|
|
},
|
|
{
|
|
"entropy": 5.651054191589355,
|
|
"epoch": 0.8805525916774303,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004933316388860391,
|
|
"loss": 5.499,
|
|
"mean_token_accuracy": 0.17971526384353637,
|
|
"num_tokens": 17486903.0,
|
|
"step": 7840
|
|
},
|
|
{
|
|
"entropy": 5.606143474578857,
|
|
"epoch": 0.8811141685853877,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004933219333694787,
|
|
"loss": 5.5293,
|
|
"mean_token_accuracy": 0.17288160622119902,
|
|
"num_tokens": 17498790.0,
|
|
"step": 7845
|
|
},
|
|
{
|
|
"entropy": 5.714953851699829,
|
|
"epoch": 0.8816757454933453,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004933122209014634,
|
|
"loss": 5.5955,
|
|
"mean_token_accuracy": 0.16601091772317886,
|
|
"num_tokens": 17510061.0,
|
|
"step": 7850
|
|
},
|
|
{
|
|
"entropy": 5.633646059036255,
|
|
"epoch": 0.8822373224013028,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004933025014823022,
|
|
"loss": 5.5903,
|
|
"mean_token_accuracy": 0.17064592093229294,
|
|
"num_tokens": 17522414.0,
|
|
"step": 7855
|
|
},
|
|
{
|
|
"entropy": 5.8329545021057125,
|
|
"epoch": 0.8827988993092604,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004932927751123048,
|
|
"loss": 5.7145,
|
|
"mean_token_accuracy": 0.16631321161985396,
|
|
"num_tokens": 17532745.0,
|
|
"step": 7860
|
|
},
|
|
{
|
|
"entropy": 5.611430501937866,
|
|
"epoch": 0.8833604762172179,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004932830417917808,
|
|
"loss": 5.529,
|
|
"mean_token_accuracy": 0.17476555854082107,
|
|
"num_tokens": 17545329.0,
|
|
"step": 7865
|
|
},
|
|
{
|
|
"entropy": 5.751594734191895,
|
|
"epoch": 0.8839220531251755,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.00049327330152104,
|
|
"loss": 5.6138,
|
|
"mean_token_accuracy": 0.17362827211618423,
|
|
"num_tokens": 17557789.0,
|
|
"step": 7870
|
|
},
|
|
{
|
|
"entropy": 5.6656910419464115,
|
|
"epoch": 0.884483630033133,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004932635543003927,
|
|
"loss": 5.4396,
|
|
"mean_token_accuracy": 0.1843024507164955,
|
|
"num_tokens": 17568338.0,
|
|
"step": 7875
|
|
},
|
|
{
|
|
"entropy": 5.613920211791992,
|
|
"epoch": 0.8850452069410906,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.0004932538001301491,
|
|
"loss": 5.5463,
|
|
"mean_token_accuracy": 0.17667528986930847,
|
|
"num_tokens": 17581199.0,
|
|
"step": 7880
|
|
},
|
|
{
|
|
"entropy": 5.55684175491333,
|
|
"epoch": 0.8856067838490481,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004932440390106199,
|
|
"loss": 5.4989,
|
|
"mean_token_accuracy": 0.1783109188079834,
|
|
"num_tokens": 17592937.0,
|
|
"step": 7885
|
|
},
|
|
{
|
|
"entropy": 5.640095186233521,
|
|
"epoch": 0.8861683607570057,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004932342709421159,
|
|
"loss": 5.5871,
|
|
"mean_token_accuracy": 0.17936155050992966,
|
|
"num_tokens": 17604003.0,
|
|
"step": 7890
|
|
},
|
|
{
|
|
"entropy": 5.869416236877441,
|
|
"epoch": 0.8867299376649632,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.000493224495924948,
|
|
"loss": 5.6946,
|
|
"mean_token_accuracy": 0.17143333107233047,
|
|
"num_tokens": 17617283.0,
|
|
"step": 7895
|
|
},
|
|
{
|
|
"entropy": 5.6359922885894775,
|
|
"epoch": 0.8872915145729208,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.0004932147139594276,
|
|
"loss": 5.5536,
|
|
"mean_token_accuracy": 0.1794540524482727,
|
|
"num_tokens": 17628161.0,
|
|
"step": 7900
|
|
},
|
|
{
|
|
"entropy": 5.672177648544311,
|
|
"epoch": 0.8878530914808783,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004932049250458659,
|
|
"loss": 5.6287,
|
|
"mean_token_accuracy": 0.16972751319408416,
|
|
"num_tokens": 17639226.0,
|
|
"step": 7905
|
|
},
|
|
{
|
|
"entropy": 5.686139869689941,
|
|
"epoch": 0.8884146683888359,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.0004931951291845749,
|
|
"loss": 5.4628,
|
|
"mean_token_accuracy": 0.18074344098567963,
|
|
"num_tokens": 17652114.0,
|
|
"step": 7910
|
|
},
|
|
{
|
|
"entropy": 5.577626514434814,
|
|
"epoch": 0.8889762452967934,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004931853263758663,
|
|
"loss": 5.5073,
|
|
"mean_token_accuracy": 0.17764090299606322,
|
|
"num_tokens": 17663280.0,
|
|
"step": 7915
|
|
},
|
|
{
|
|
"entropy": 5.590498542785644,
|
|
"epoch": 0.889537822204751,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.0004931755166200523,
|
|
"loss": 5.5878,
|
|
"mean_token_accuracy": 0.17220348939299585,
|
|
"num_tokens": 17674445.0,
|
|
"step": 7920
|
|
},
|
|
{
|
|
"entropy": 5.639855527877808,
|
|
"epoch": 0.8900993991127085,
|
|
"grad_norm": 2.53125,
|
|
"learning_rate": 0.0004931656999174452,
|
|
"loss": 5.4832,
|
|
"mean_token_accuracy": 0.18151286989450455,
|
|
"num_tokens": 17685046.0,
|
|
"step": 7925
|
|
},
|
|
{
|
|
"entropy": 5.586451196670533,
|
|
"epoch": 0.8906609760206661,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004931558762683577,
|
|
"loss": 5.471,
|
|
"mean_token_accuracy": 0.18444847762584687,
|
|
"num_tokens": 17695269.0,
|
|
"step": 7930
|
|
},
|
|
{
|
|
"entropy": 5.5997796058654785,
|
|
"epoch": 0.8912225529286236,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004931460456731024,
|
|
"loss": 5.5106,
|
|
"mean_token_accuracy": 0.1799800679087639,
|
|
"num_tokens": 17706296.0,
|
|
"step": 7935
|
|
},
|
|
{
|
|
"entropy": 5.632136487960816,
|
|
"epoch": 0.8917841298365812,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004931362081319925,
|
|
"loss": 5.4439,
|
|
"mean_token_accuracy": 0.17908146381378173,
|
|
"num_tokens": 17716262.0,
|
|
"step": 7940
|
|
},
|
|
{
|
|
"entropy": 5.652977037429809,
|
|
"epoch": 0.8923457067445386,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004931263636453409,
|
|
"loss": 5.4931,
|
|
"mean_token_accuracy": 0.17886744290590287,
|
|
"num_tokens": 17726818.0,
|
|
"step": 7945
|
|
},
|
|
{
|
|
"entropy": 5.621751928329468,
|
|
"epoch": 0.8929072836524962,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004931165122134616,
|
|
"loss": 5.5089,
|
|
"mean_token_accuracy": 0.18139076977968216,
|
|
"num_tokens": 17737112.0,
|
|
"step": 7950
|
|
},
|
|
{
|
|
"entropy": 5.664386367797851,
|
|
"epoch": 0.8934688605604537,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.0004931066538366677,
|
|
"loss": 5.5745,
|
|
"mean_token_accuracy": 0.17089226245880126,
|
|
"num_tokens": 17747558.0,
|
|
"step": 7955
|
|
},
|
|
{
|
|
"entropy": 5.670001602172851,
|
|
"epoch": 0.8940304374684113,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004930967885152734,
|
|
"loss": 5.5075,
|
|
"mean_token_accuracy": 0.1767207995057106,
|
|
"num_tokens": 17757495.0,
|
|
"step": 7960
|
|
},
|
|
{
|
|
"entropy": 5.672038412094116,
|
|
"epoch": 0.8945920143763688,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004930869162495929,
|
|
"loss": 5.5068,
|
|
"mean_token_accuracy": 0.17910125553607942,
|
|
"num_tokens": 17767562.0,
|
|
"step": 7965
|
|
},
|
|
{
|
|
"entropy": 5.670077705383301,
|
|
"epoch": 0.8951535912843264,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004930770370399403,
|
|
"loss": 5.5957,
|
|
"mean_token_accuracy": 0.17012177258729935,
|
|
"num_tokens": 17779800.0,
|
|
"step": 7970
|
|
},
|
|
{
|
|
"entropy": 5.607109260559082,
|
|
"epoch": 0.8957151681922839,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004930671508866303,
|
|
"loss": 5.4193,
|
|
"mean_token_accuracy": 0.178867843747139,
|
|
"num_tokens": 17791183.0,
|
|
"step": 7975
|
|
},
|
|
{
|
|
"entropy": 5.670008182525635,
|
|
"epoch": 0.8962767451002415,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004930572577899776,
|
|
"loss": 5.5824,
|
|
"mean_token_accuracy": 0.17333045303821565,
|
|
"num_tokens": 17802547.0,
|
|
"step": 7980
|
|
},
|
|
{
|
|
"entropy": 5.523604488372802,
|
|
"epoch": 0.896838322008199,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004930473577502972,
|
|
"loss": 5.4773,
|
|
"mean_token_accuracy": 0.1762331023812294,
|
|
"num_tokens": 17815406.0,
|
|
"step": 7985
|
|
},
|
|
{
|
|
"entropy": 5.5631507396697994,
|
|
"epoch": 0.8973998989161566,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004930374507679044,
|
|
"loss": 5.4882,
|
|
"mean_token_accuracy": 0.17375995814800263,
|
|
"num_tokens": 17826516.0,
|
|
"step": 7990
|
|
},
|
|
{
|
|
"entropy": 5.649429225921631,
|
|
"epoch": 0.8979614758241141,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004930275368431146,
|
|
"loss": 5.4744,
|
|
"mean_token_accuracy": 0.177804072201252,
|
|
"num_tokens": 17838193.0,
|
|
"step": 7995
|
|
},
|
|
{
|
|
"entropy": 5.613844108581543,
|
|
"epoch": 0.8985230527320717,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004930176159762435,
|
|
"loss": 5.503,
|
|
"mean_token_accuracy": 0.17666814029216765,
|
|
"num_tokens": 17849564.0,
|
|
"step": 8000
|
|
},
|
|
{
|
|
"entropy": 5.723873519897461,
|
|
"epoch": 0.8990846296400292,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004930076881676069,
|
|
"loss": 5.6244,
|
|
"mean_token_accuracy": 0.1691985934972763,
|
|
"num_tokens": 17861874.0,
|
|
"step": 8005
|
|
},
|
|
{
|
|
"entropy": 5.641931200027466,
|
|
"epoch": 0.8996462065479868,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004929977534175211,
|
|
"loss": 5.4687,
|
|
"mean_token_accuracy": 0.17922749370336533,
|
|
"num_tokens": 17873139.0,
|
|
"step": 8010
|
|
},
|
|
{
|
|
"entropy": 5.693650436401367,
|
|
"epoch": 0.9002077834559443,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004929878117263021,
|
|
"loss": 5.5457,
|
|
"mean_token_accuracy": 0.17990801036357879,
|
|
"num_tokens": 17883262.0,
|
|
"step": 8015
|
|
},
|
|
{
|
|
"entropy": 5.486669683456421,
|
|
"epoch": 0.9007693603639019,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004929778630942668,
|
|
"loss": 5.4435,
|
|
"mean_token_accuracy": 0.1851835086941719,
|
|
"num_tokens": 17895041.0,
|
|
"step": 8020
|
|
},
|
|
{
|
|
"entropy": 5.548582124710083,
|
|
"epoch": 0.9013309372718594,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004929679075217317,
|
|
"loss": 5.4943,
|
|
"mean_token_accuracy": 0.17466065436601638,
|
|
"num_tokens": 17905154.0,
|
|
"step": 8025
|
|
},
|
|
{
|
|
"entropy": 5.609206008911133,
|
|
"epoch": 0.901892514179817,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.0004929579450090139,
|
|
"loss": 5.529,
|
|
"mean_token_accuracy": 0.177594855427742,
|
|
"num_tokens": 17916287.0,
|
|
"step": 8030
|
|
},
|
|
{
|
|
"entropy": 5.682128095626831,
|
|
"epoch": 0.9024540910877745,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004929479755564305,
|
|
"loss": 5.5437,
|
|
"mean_token_accuracy": 0.18083585947751998,
|
|
"num_tokens": 17927269.0,
|
|
"step": 8035
|
|
},
|
|
{
|
|
"entropy": 5.707501840591431,
|
|
"epoch": 0.903015667995732,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.0004929379991642991,
|
|
"loss": 5.5655,
|
|
"mean_token_accuracy": 0.1747921198606491,
|
|
"num_tokens": 17938142.0,
|
|
"step": 8040
|
|
},
|
|
{
|
|
"entropy": 5.681667613983154,
|
|
"epoch": 0.9035772449036895,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004929280158329373,
|
|
"loss": 5.5408,
|
|
"mean_token_accuracy": 0.17408334463834763,
|
|
"num_tokens": 17950229.0,
|
|
"step": 8045
|
|
},
|
|
{
|
|
"entropy": 5.65967059135437,
|
|
"epoch": 0.9041388218116471,
|
|
"grad_norm": 3.078125,
|
|
"learning_rate": 0.000492918025562663,
|
|
"loss": 5.5165,
|
|
"mean_token_accuracy": 0.18341777324676514,
|
|
"num_tokens": 17961757.0,
|
|
"step": 8050
|
|
},
|
|
{
|
|
"entropy": 5.714594793319702,
|
|
"epoch": 0.9047003987196046,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004929080283537942,
|
|
"loss": 5.6086,
|
|
"mean_token_accuracy": 0.16795896589756013,
|
|
"num_tokens": 17972564.0,
|
|
"step": 8055
|
|
},
|
|
{
|
|
"entropy": 5.670015001296997,
|
|
"epoch": 0.9052619756275622,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004928980242066492,
|
|
"loss": 5.5112,
|
|
"mean_token_accuracy": 0.1830298900604248,
|
|
"num_tokens": 17982776.0,
|
|
"step": 8060
|
|
},
|
|
{
|
|
"entropy": 5.725727081298828,
|
|
"epoch": 0.9058235525355197,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004928880131215467,
|
|
"loss": 5.6352,
|
|
"mean_token_accuracy": 0.17631023973226548,
|
|
"num_tokens": 17994460.0,
|
|
"step": 8065
|
|
},
|
|
{
|
|
"entropy": 5.633108329772949,
|
|
"epoch": 0.9063851294434773,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004928779950988053,
|
|
"loss": 5.5856,
|
|
"mean_token_accuracy": 0.17719729989767075,
|
|
"num_tokens": 18005744.0,
|
|
"step": 8070
|
|
},
|
|
{
|
|
"entropy": 5.594573354721069,
|
|
"epoch": 0.9069467063514348,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.000492867970138744,
|
|
"loss": 5.4574,
|
|
"mean_token_accuracy": 0.1850307449698448,
|
|
"num_tokens": 18016517.0,
|
|
"step": 8075
|
|
},
|
|
{
|
|
"entropy": 5.673829412460327,
|
|
"epoch": 0.9075082832593924,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004928579382416821,
|
|
"loss": 5.5721,
|
|
"mean_token_accuracy": 0.1693943738937378,
|
|
"num_tokens": 18027653.0,
|
|
"step": 8080
|
|
},
|
|
{
|
|
"entropy": 5.665168237686157,
|
|
"epoch": 0.9080698601673499,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.000492847899407939,
|
|
"loss": 5.612,
|
|
"mean_token_accuracy": 0.1709613621234894,
|
|
"num_tokens": 18038741.0,
|
|
"step": 8085
|
|
},
|
|
{
|
|
"entropy": 5.692080497741699,
|
|
"epoch": 0.9086314370753075,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.0004928378536378341,
|
|
"loss": 5.5453,
|
|
"mean_token_accuracy": 0.17879764288663863,
|
|
"num_tokens": 18049188.0,
|
|
"step": 8090
|
|
},
|
|
{
|
|
"entropy": 5.670418739318848,
|
|
"epoch": 0.909193013983265,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.0004928278009316877,
|
|
"loss": 5.4784,
|
|
"mean_token_accuracy": 0.17552203685045242,
|
|
"num_tokens": 18059979.0,
|
|
"step": 8095
|
|
},
|
|
{
|
|
"entropy": 5.69766640663147,
|
|
"epoch": 0.9097545908912226,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004928177412898195,
|
|
"loss": 5.4659,
|
|
"mean_token_accuracy": 0.18187967985868453,
|
|
"num_tokens": 18070712.0,
|
|
"step": 8100
|
|
},
|
|
{
|
|
"entropy": 5.649283695220947,
|
|
"epoch": 0.9103161677991801,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.0004928076747125499,
|
|
"loss": 5.5447,
|
|
"mean_token_accuracy": 0.1823956623673439,
|
|
"num_tokens": 18081372.0,
|
|
"step": 8105
|
|
},
|
|
{
|
|
"entropy": 5.573438119888306,
|
|
"epoch": 0.9108777447071377,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.0004927976012001995,
|
|
"loss": 5.469,
|
|
"mean_token_accuracy": 0.17894431054592133,
|
|
"num_tokens": 18093033.0,
|
|
"step": 8110
|
|
},
|
|
{
|
|
"entropy": 5.607672262191772,
|
|
"epoch": 0.9114393216150952,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004927875207530889,
|
|
"loss": 5.434,
|
|
"mean_token_accuracy": 0.1770060122013092,
|
|
"num_tokens": 18104808.0,
|
|
"step": 8115
|
|
},
|
|
{
|
|
"entropy": 5.694924211502075,
|
|
"epoch": 0.9120008985230528,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004927774333715394,
|
|
"loss": 5.5524,
|
|
"mean_token_accuracy": 0.17589583694934846,
|
|
"num_tokens": 18115450.0,
|
|
"step": 8120
|
|
},
|
|
{
|
|
"entropy": 5.691878318786621,
|
|
"epoch": 0.9125624754310103,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004927673390558718,
|
|
"loss": 5.6605,
|
|
"mean_token_accuracy": 0.17123398184776306,
|
|
"num_tokens": 18127437.0,
|
|
"step": 8125
|
|
},
|
|
{
|
|
"entropy": 5.644760465621948,
|
|
"epoch": 0.9131240523389679,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004927572378064077,
|
|
"loss": 5.4932,
|
|
"mean_token_accuracy": 0.18329223692417146,
|
|
"num_tokens": 18137371.0,
|
|
"step": 8130
|
|
},
|
|
{
|
|
"entropy": 5.644264268875122,
|
|
"epoch": 0.9136856292469253,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004927471296234687,
|
|
"loss": 5.5498,
|
|
"mean_token_accuracy": 0.17313000112771987,
|
|
"num_tokens": 18148332.0,
|
|
"step": 8135
|
|
},
|
|
{
|
|
"entropy": 5.604533100128174,
|
|
"epoch": 0.9142472061548829,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004927370145073767,
|
|
"loss": 5.5353,
|
|
"mean_token_accuracy": 0.1796187862753868,
|
|
"num_tokens": 18159918.0,
|
|
"step": 8140
|
|
},
|
|
{
|
|
"entropy": 5.631461429595947,
|
|
"epoch": 0.9148087830628404,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.0004927268924584536,
|
|
"loss": 5.5075,
|
|
"mean_token_accuracy": 0.1854100286960602,
|
|
"num_tokens": 18170911.0,
|
|
"step": 8145
|
|
},
|
|
{
|
|
"entropy": 5.688991403579712,
|
|
"epoch": 0.915370359970798,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004927167634770219,
|
|
"loss": 5.531,
|
|
"mean_token_accuracy": 0.1810923382639885,
|
|
"num_tokens": 18183089.0,
|
|
"step": 8150
|
|
},
|
|
{
|
|
"entropy": 5.8137617111206055,
|
|
"epoch": 0.9159319368787555,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.000492706627563404,
|
|
"loss": 5.7904,
|
|
"mean_token_accuracy": 0.1582899883389473,
|
|
"num_tokens": 18195467.0,
|
|
"step": 8155
|
|
},
|
|
{
|
|
"entropy": 5.767338752746582,
|
|
"epoch": 0.9164935137867131,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.0004926964847179225,
|
|
"loss": 5.5644,
|
|
"mean_token_accuracy": 0.17545745968818666,
|
|
"num_tokens": 18206766.0,
|
|
"step": 8160
|
|
},
|
|
{
|
|
"entropy": 5.606827974319458,
|
|
"epoch": 0.9170550906946706,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004926863349409006,
|
|
"loss": 5.5445,
|
|
"mean_token_accuracy": 0.17473639249801637,
|
|
"num_tokens": 18217840.0,
|
|
"step": 8165
|
|
},
|
|
{
|
|
"entropy": 5.62703504562378,
|
|
"epoch": 0.9176166676026282,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004926761782326613,
|
|
"loss": 5.569,
|
|
"mean_token_accuracy": 0.17187792658805848,
|
|
"num_tokens": 18229514.0,
|
|
"step": 8170
|
|
},
|
|
{
|
|
"entropy": 5.646729373931885,
|
|
"epoch": 0.9181782445105857,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004926660145935282,
|
|
"loss": 5.5421,
|
|
"mean_token_accuracy": 0.17318500429391862,
|
|
"num_tokens": 18241949.0,
|
|
"step": 8175
|
|
},
|
|
{
|
|
"entropy": 5.679330444335937,
|
|
"epoch": 0.9187398214185433,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004926558440238247,
|
|
"loss": 5.5131,
|
|
"mean_token_accuracy": 0.17542119920253754,
|
|
"num_tokens": 18252938.0,
|
|
"step": 8180
|
|
},
|
|
{
|
|
"entropy": 5.637924528121948,
|
|
"epoch": 0.9193013983265008,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004926456665238746,
|
|
"loss": 5.4677,
|
|
"mean_token_accuracy": 0.184273599088192,
|
|
"num_tokens": 18263417.0,
|
|
"step": 8185
|
|
},
|
|
{
|
|
"entropy": 5.662953853607178,
|
|
"epoch": 0.9198629752344584,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004926354820940023,
|
|
"loss": 5.633,
|
|
"mean_token_accuracy": 0.173651821911335,
|
|
"num_tokens": 18275595.0,
|
|
"step": 8190
|
|
},
|
|
{
|
|
"entropy": 5.602357959747314,
|
|
"epoch": 0.9204245521424159,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004926252907345317,
|
|
"loss": 5.4657,
|
|
"mean_token_accuracy": 0.17716097235679626,
|
|
"num_tokens": 18287510.0,
|
|
"step": 8195
|
|
},
|
|
{
|
|
"entropy": 5.701159238815308,
|
|
"epoch": 0.9209861290503735,
|
|
"grad_norm": 2.796875,
|
|
"learning_rate": 0.0004926150924457874,
|
|
"loss": 5.5649,
|
|
"mean_token_accuracy": 0.17682331204414367,
|
|
"num_tokens": 18298764.0,
|
|
"step": 8200
|
|
},
|
|
{
|
|
"entropy": 5.498835897445678,
|
|
"epoch": 0.921547705958331,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.0004926048872280943,
|
|
"loss": 5.3814,
|
|
"mean_token_accuracy": 0.1786089673638344,
|
|
"num_tokens": 18310427.0,
|
|
"step": 8205
|
|
},
|
|
{
|
|
"entropy": 5.562673568725586,
|
|
"epoch": 0.9221092828662886,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.000492594675081777,
|
|
"loss": 5.5189,
|
|
"mean_token_accuracy": 0.1743911549448967,
|
|
"num_tokens": 18322174.0,
|
|
"step": 8210
|
|
},
|
|
{
|
|
"entropy": 5.6444212913513185,
|
|
"epoch": 0.9226708597742461,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.000492584456007161,
|
|
"loss": 5.4591,
|
|
"mean_token_accuracy": 0.17580502182245256,
|
|
"num_tokens": 18332372.0,
|
|
"step": 8215
|
|
},
|
|
{
|
|
"entropy": 5.637707901000977,
|
|
"epoch": 0.9232324366822037,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004925742300045716,
|
|
"loss": 5.5303,
|
|
"mean_token_accuracy": 0.17169395238161086,
|
|
"num_tokens": 18343201.0,
|
|
"step": 8220
|
|
},
|
|
{
|
|
"entropy": 5.601301670074463,
|
|
"epoch": 0.9237940135901612,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004925639970743341,
|
|
"loss": 5.5478,
|
|
"mean_token_accuracy": 0.17713602930307387,
|
|
"num_tokens": 18354124.0,
|
|
"step": 8225
|
|
},
|
|
{
|
|
"entropy": 5.591428613662719,
|
|
"epoch": 0.9243555904981187,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.0004925537572167746,
|
|
"loss": 5.4811,
|
|
"mean_token_accuracy": 0.18419933170080185,
|
|
"num_tokens": 18365148.0,
|
|
"step": 8230
|
|
},
|
|
{
|
|
"entropy": 5.496890592575073,
|
|
"epoch": 0.9249171674060762,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004925435104322192,
|
|
"loss": 5.3674,
|
|
"mean_token_accuracy": 0.18393095582723618,
|
|
"num_tokens": 18376244.0,
|
|
"step": 8235
|
|
},
|
|
{
|
|
"entropy": 5.639883899688721,
|
|
"epoch": 0.9254787443140338,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.000492533256720994,
|
|
"loss": 5.5346,
|
|
"mean_token_accuracy": 0.1793355867266655,
|
|
"num_tokens": 18386728.0,
|
|
"step": 8240
|
|
},
|
|
{
|
|
"entropy": 5.669590425491333,
|
|
"epoch": 0.9260403212219913,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004925229960834256,
|
|
"loss": 5.5192,
|
|
"mean_token_accuracy": 0.17597363889217377,
|
|
"num_tokens": 18397008.0,
|
|
"step": 8245
|
|
},
|
|
{
|
|
"entropy": 5.675183486938477,
|
|
"epoch": 0.9266018981299489,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004925127285198407,
|
|
"loss": 5.5088,
|
|
"mean_token_accuracy": 0.1826247587800026,
|
|
"num_tokens": 18408348.0,
|
|
"step": 8250
|
|
},
|
|
{
|
|
"entropy": 5.588458681106568,
|
|
"epoch": 0.9271634750379064,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.000492502454030566,
|
|
"loss": 5.5383,
|
|
"mean_token_accuracy": 0.1786420926451683,
|
|
"num_tokens": 18419239.0,
|
|
"step": 8255
|
|
},
|
|
{
|
|
"entropy": 5.677526330947876,
|
|
"epoch": 0.927725051945864,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004924921726159288,
|
|
"loss": 5.5237,
|
|
"mean_token_accuracy": 0.1732431247830391,
|
|
"num_tokens": 18428918.0,
|
|
"step": 8260
|
|
},
|
|
{
|
|
"entropy": 5.687090539932251,
|
|
"epoch": 0.9282866288538215,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.0004924818842762565,
|
|
"loss": 5.5221,
|
|
"mean_token_accuracy": 0.17917510569095613,
|
|
"num_tokens": 18440361.0,
|
|
"step": 8265
|
|
},
|
|
{
|
|
"entropy": 5.532576036453247,
|
|
"epoch": 0.9288482057617791,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004924715890118768,
|
|
"loss": 5.4126,
|
|
"mean_token_accuracy": 0.18281398266553878,
|
|
"num_tokens": 18450678.0,
|
|
"step": 8270
|
|
},
|
|
{
|
|
"entropy": 5.60647611618042,
|
|
"epoch": 0.9294097826697366,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004924612868231173,
|
|
"loss": 5.6214,
|
|
"mean_token_accuracy": 0.17365727424621583,
|
|
"num_tokens": 18462364.0,
|
|
"step": 8275
|
|
},
|
|
{
|
|
"entropy": 5.605989933013916,
|
|
"epoch": 0.9299713595776942,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004924509777103059,
|
|
"loss": 5.504,
|
|
"mean_token_accuracy": 0.1794855087995529,
|
|
"num_tokens": 18472896.0,
|
|
"step": 8280
|
|
},
|
|
{
|
|
"entropy": 5.771299171447754,
|
|
"epoch": 0.9305329364856517,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004924406616737712,
|
|
"loss": 5.6395,
|
|
"mean_token_accuracy": 0.16835574805736542,
|
|
"num_tokens": 18484951.0,
|
|
"step": 8285
|
|
},
|
|
{
|
|
"entropy": 5.657807922363281,
|
|
"epoch": 0.9310945133936093,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004924303387138415,
|
|
"loss": 5.5924,
|
|
"mean_token_accuracy": 0.1721227765083313,
|
|
"num_tokens": 18496006.0,
|
|
"step": 8290
|
|
},
|
|
{
|
|
"entropy": 5.720281362533569,
|
|
"epoch": 0.9316560903015668,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.0004924200088308455,
|
|
"loss": 5.5696,
|
|
"mean_token_accuracy": 0.17478319853544236,
|
|
"num_tokens": 18508069.0,
|
|
"step": 8295
|
|
},
|
|
{
|
|
"entropy": 5.7622028350830075,
|
|
"epoch": 0.9322176672095244,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.000492409672025112,
|
|
"loss": 5.6811,
|
|
"mean_token_accuracy": 0.16892137974500657,
|
|
"num_tokens": 18519746.0,
|
|
"step": 8300
|
|
},
|
|
{
|
|
"entropy": 5.723033142089844,
|
|
"epoch": 0.9327792441174819,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004923993282969703,
|
|
"loss": 5.5853,
|
|
"mean_token_accuracy": 0.17646910399198532,
|
|
"num_tokens": 18530249.0,
|
|
"step": 8305
|
|
},
|
|
{
|
|
"entropy": 5.662984371185303,
|
|
"epoch": 0.9333408210254395,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004923889776467495,
|
|
"loss": 5.5956,
|
|
"mean_token_accuracy": 0.17596546709537506,
|
|
"num_tokens": 18543306.0,
|
|
"step": 8310
|
|
},
|
|
{
|
|
"entropy": 5.648860502243042,
|
|
"epoch": 0.933902397933397,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 0.0004923786200747795,
|
|
"loss": 5.6411,
|
|
"mean_token_accuracy": 0.1686694398522377,
|
|
"num_tokens": 18555250.0,
|
|
"step": 8315
|
|
},
|
|
{
|
|
"entropy": 5.648197746276855,
|
|
"epoch": 0.9344639748413546,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.00049236825558139,
|
|
"loss": 5.4011,
|
|
"mean_token_accuracy": 0.17841222137212753,
|
|
"num_tokens": 18566378.0,
|
|
"step": 8320
|
|
},
|
|
{
|
|
"entropy": 5.677195978164673,
|
|
"epoch": 0.9350255517493121,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.0004923578841669108,
|
|
"loss": 5.5991,
|
|
"mean_token_accuracy": 0.17169099897146226,
|
|
"num_tokens": 18576827.0,
|
|
"step": 8325
|
|
},
|
|
{
|
|
"entropy": 5.666315364837646,
|
|
"epoch": 0.9355871286572696,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004923475058316723,
|
|
"loss": 5.5327,
|
|
"mean_token_accuracy": 0.17996591031551362,
|
|
"num_tokens": 18589209.0,
|
|
"step": 8330
|
|
},
|
|
{
|
|
"entropy": 5.665826988220215,
|
|
"epoch": 0.9361487055652271,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.0004923371205760049,
|
|
"loss": 5.5448,
|
|
"mean_token_accuracy": 0.17993804365396499,
|
|
"num_tokens": 18599367.0,
|
|
"step": 8335
|
|
},
|
|
{
|
|
"entropy": 5.685740804672241,
|
|
"epoch": 0.9367102824731847,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004923267284002394,
|
|
"loss": 5.5596,
|
|
"mean_token_accuracy": 0.17554907500743866,
|
|
"num_tokens": 18610505.0,
|
|
"step": 8340
|
|
},
|
|
{
|
|
"entropy": 5.728540515899658,
|
|
"epoch": 0.9372718593811422,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004923163293047065,
|
|
"loss": 5.576,
|
|
"mean_token_accuracy": 0.17635622173547744,
|
|
"num_tokens": 18622616.0,
|
|
"step": 8345
|
|
},
|
|
{
|
|
"entropy": 5.564018392562867,
|
|
"epoch": 0.9378334362890998,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004923059232897374,
|
|
"loss": 5.4279,
|
|
"mean_token_accuracy": 0.18282887041568757,
|
|
"num_tokens": 18634127.0,
|
|
"step": 8350
|
|
},
|
|
{
|
|
"entropy": 5.643030595779419,
|
|
"epoch": 0.9383950131970573,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004922955103556633,
|
|
"loss": 5.6351,
|
|
"mean_token_accuracy": 0.16937693655490876,
|
|
"num_tokens": 18646196.0,
|
|
"step": 8355
|
|
},
|
|
{
|
|
"entropy": 5.6739662170410154,
|
|
"epoch": 0.9389565901050149,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.000492285090502816,
|
|
"loss": 5.551,
|
|
"mean_token_accuracy": 0.17348477840423585,
|
|
"num_tokens": 18656911.0,
|
|
"step": 8360
|
|
},
|
|
{
|
|
"entropy": 5.690097999572754,
|
|
"epoch": 0.9395181670129724,
|
|
"grad_norm": 2.796875,
|
|
"learning_rate": 0.0004922746637315272,
|
|
"loss": 5.4999,
|
|
"mean_token_accuracy": 0.17673232406377792,
|
|
"num_tokens": 18667553.0,
|
|
"step": 8365
|
|
},
|
|
{
|
|
"entropy": 5.607486772537231,
|
|
"epoch": 0.94007974392093,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004922642300421288,
|
|
"loss": 5.4848,
|
|
"mean_token_accuracy": 0.1837180271744728,
|
|
"num_tokens": 18678087.0,
|
|
"step": 8370
|
|
},
|
|
{
|
|
"entropy": 5.692394685745239,
|
|
"epoch": 0.9406413208288875,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.000492253789434953,
|
|
"loss": 5.5953,
|
|
"mean_token_accuracy": 0.17041603922843934,
|
|
"num_tokens": 18689946.0,
|
|
"step": 8375
|
|
},
|
|
{
|
|
"entropy": 5.636316347122192,
|
|
"epoch": 0.9412028977368451,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004922433419103323,
|
|
"loss": 5.5125,
|
|
"mean_token_accuracy": 0.18106106370687486,
|
|
"num_tokens": 18700944.0,
|
|
"step": 8380
|
|
},
|
|
{
|
|
"entropy": 5.650438690185547,
|
|
"epoch": 0.9417644746448026,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004922328874685993,
|
|
"loss": 5.6032,
|
|
"mean_token_accuracy": 0.17495706230401992,
|
|
"num_tokens": 18712901.0,
|
|
"step": 8385
|
|
},
|
|
{
|
|
"entropy": 5.540583372116089,
|
|
"epoch": 0.9423260515527602,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004922224261100869,
|
|
"loss": 5.4363,
|
|
"mean_token_accuracy": 0.1819579929113388,
|
|
"num_tokens": 18724322.0,
|
|
"step": 8390
|
|
},
|
|
{
|
|
"entropy": 5.585246801376343,
|
|
"epoch": 0.9428876284607177,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004922119578351283,
|
|
"loss": 5.5008,
|
|
"mean_token_accuracy": 0.179002782702446,
|
|
"num_tokens": 18735315.0,
|
|
"step": 8395
|
|
},
|
|
{
|
|
"entropy": 5.671797847747802,
|
|
"epoch": 0.9434492053686753,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004922014826440566,
|
|
"loss": 5.5273,
|
|
"mean_token_accuracy": 0.1750408634543419,
|
|
"num_tokens": 18747497.0,
|
|
"step": 8400
|
|
},
|
|
{
|
|
"entropy": 5.65489935874939,
|
|
"epoch": 0.9440107822766328,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004921910005372056,
|
|
"loss": 5.578,
|
|
"mean_token_accuracy": 0.17129521816968918,
|
|
"num_tokens": 18758835.0,
|
|
"step": 8405
|
|
},
|
|
{
|
|
"entropy": 5.587268304824829,
|
|
"epoch": 0.9445723591845904,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004921805115149088,
|
|
"loss": 5.4588,
|
|
"mean_token_accuracy": 0.1864311844110489,
|
|
"num_tokens": 18770325.0,
|
|
"step": 8410
|
|
},
|
|
{
|
|
"entropy": 5.533601760864258,
|
|
"epoch": 0.9451339360925479,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004921700155775002,
|
|
"loss": 5.3553,
|
|
"mean_token_accuracy": 0.1877336859703064,
|
|
"num_tokens": 18781204.0,
|
|
"step": 8415
|
|
},
|
|
{
|
|
"entropy": 5.54454984664917,
|
|
"epoch": 0.9456955130005055,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004921595127253142,
|
|
"loss": 5.4738,
|
|
"mean_token_accuracy": 0.1795824110507965,
|
|
"num_tokens": 18791899.0,
|
|
"step": 8420
|
|
},
|
|
{
|
|
"entropy": 5.628634262084961,
|
|
"epoch": 0.9462570899084629,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004921490029586852,
|
|
"loss": 5.4824,
|
|
"mean_token_accuracy": 0.18252576887607574,
|
|
"num_tokens": 18803043.0,
|
|
"step": 8425
|
|
},
|
|
{
|
|
"entropy": 5.620337009429932,
|
|
"epoch": 0.9468186668164205,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004921384862779475,
|
|
"loss": 5.4719,
|
|
"mean_token_accuracy": 0.17355618476867676,
|
|
"num_tokens": 18814316.0,
|
|
"step": 8430
|
|
},
|
|
{
|
|
"entropy": 5.566678285598755,
|
|
"epoch": 0.947380243724378,
|
|
"grad_norm": 2.546875,
|
|
"learning_rate": 0.0004921279626834363,
|
|
"loss": 5.5389,
|
|
"mean_token_accuracy": 0.176765838265419,
|
|
"num_tokens": 18825490.0,
|
|
"step": 8435
|
|
},
|
|
{
|
|
"entropy": 5.739933109283447,
|
|
"epoch": 0.9479418206323356,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004921174321754865,
|
|
"loss": 5.6345,
|
|
"mean_token_accuracy": 0.17682459503412246,
|
|
"num_tokens": 18836479.0,
|
|
"step": 8440
|
|
},
|
|
{
|
|
"entropy": 5.66730318069458,
|
|
"epoch": 0.9485033975402931,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004921068947544335,
|
|
"loss": 5.5274,
|
|
"mean_token_accuracy": 0.1786904901266098,
|
|
"num_tokens": 18848634.0,
|
|
"step": 8445
|
|
},
|
|
{
|
|
"entropy": 5.5759529113769535,
|
|
"epoch": 0.9490649744482507,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004920963504206128,
|
|
"loss": 5.4761,
|
|
"mean_token_accuracy": 0.18332092612981796,
|
|
"num_tokens": 18858451.0,
|
|
"step": 8450
|
|
},
|
|
{
|
|
"entropy": 5.704009485244751,
|
|
"epoch": 0.9496265513562082,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.00049208579917436,
|
|
"loss": 5.629,
|
|
"mean_token_accuracy": 0.16765221506357192,
|
|
"num_tokens": 18869561.0,
|
|
"step": 8455
|
|
},
|
|
{
|
|
"entropy": 5.748137140274048,
|
|
"epoch": 0.9501881282641658,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004920752410160113,
|
|
"loss": 5.6237,
|
|
"mean_token_accuracy": 0.17096092998981477,
|
|
"num_tokens": 18880232.0,
|
|
"step": 8460
|
|
},
|
|
{
|
|
"entropy": 5.719062423706054,
|
|
"epoch": 0.9507497051721233,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004920646759459026,
|
|
"loss": 5.629,
|
|
"mean_token_accuracy": 0.1731480121612549,
|
|
"num_tokens": 18892562.0,
|
|
"step": 8465
|
|
},
|
|
{
|
|
"entropy": 5.592465019226074,
|
|
"epoch": 0.9513112820800809,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004920541039643705,
|
|
"loss": 5.5561,
|
|
"mean_token_accuracy": 0.17277975529432296,
|
|
"num_tokens": 18903566.0,
|
|
"step": 8470
|
|
},
|
|
{
|
|
"entropy": 5.675828313827514,
|
|
"epoch": 0.9518728589880384,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004920435250717515,
|
|
"loss": 5.5655,
|
|
"mean_token_accuracy": 0.1776389241218567,
|
|
"num_tokens": 18914619.0,
|
|
"step": 8475
|
|
},
|
|
{
|
|
"entropy": 5.735453033447266,
|
|
"epoch": 0.952434435895996,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004920329392683826,
|
|
"loss": 5.6239,
|
|
"mean_token_accuracy": 0.17360732406377793,
|
|
"num_tokens": 18927039.0,
|
|
"step": 8480
|
|
},
|
|
{
|
|
"entropy": 5.774961996078491,
|
|
"epoch": 0.9529960128039535,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004920223465546006,
|
|
"loss": 5.7189,
|
|
"mean_token_accuracy": 0.16708040982484818,
|
|
"num_tokens": 18940449.0,
|
|
"step": 8485
|
|
},
|
|
{
|
|
"entropy": 5.72331280708313,
|
|
"epoch": 0.9535575897119111,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004920117469307429,
|
|
"loss": 5.6015,
|
|
"mean_token_accuracy": 0.17253665924072265,
|
|
"num_tokens": 18950798.0,
|
|
"step": 8490
|
|
},
|
|
{
|
|
"entropy": 5.619016313552857,
|
|
"epoch": 0.9541191666198686,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004920011403971471,
|
|
"loss": 5.4213,
|
|
"mean_token_accuracy": 0.18002093583345413,
|
|
"num_tokens": 18960958.0,
|
|
"step": 8495
|
|
},
|
|
{
|
|
"entropy": 5.577800607681274,
|
|
"epoch": 0.9546807435278262,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004919905269541508,
|
|
"loss": 5.4735,
|
|
"mean_token_accuracy": 0.18079969435930252,
|
|
"num_tokens": 18971890.0,
|
|
"step": 8500
|
|
},
|
|
{
|
|
"entropy": 5.553391981124878,
|
|
"epoch": 0.9552423204357837,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.000491979906602092,
|
|
"loss": 5.4118,
|
|
"mean_token_accuracy": 0.18525581508874894,
|
|
"num_tokens": 18982309.0,
|
|
"step": 8505
|
|
},
|
|
{
|
|
"entropy": 5.653248834609985,
|
|
"epoch": 0.9558038973437413,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004919692793413089,
|
|
"loss": 5.6365,
|
|
"mean_token_accuracy": 0.17167770266532897,
|
|
"num_tokens": 18993648.0,
|
|
"step": 8510
|
|
},
|
|
{
|
|
"entropy": 5.618438673019409,
|
|
"epoch": 0.9563654742516988,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004919586451721396,
|
|
"loss": 5.3874,
|
|
"mean_token_accuracy": 0.1847936049103737,
|
|
"num_tokens": 19003613.0,
|
|
"step": 8515
|
|
},
|
|
{
|
|
"entropy": 5.648805570602417,
|
|
"epoch": 0.9569270511596563,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004919480040949229,
|
|
"loss": 5.5124,
|
|
"mean_token_accuracy": 0.1734914854168892,
|
|
"num_tokens": 19014720.0,
|
|
"step": 8520
|
|
},
|
|
{
|
|
"entropy": 5.6832746982574465,
|
|
"epoch": 0.9574886280676138,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004919373561099977,
|
|
"loss": 5.5675,
|
|
"mean_token_accuracy": 0.17109125405550002,
|
|
"num_tokens": 19026635.0,
|
|
"step": 8525
|
|
},
|
|
{
|
|
"entropy": 5.6451033592224125,
|
|
"epoch": 0.9580502049755714,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.000491926701217703,
|
|
"loss": 5.5607,
|
|
"mean_token_accuracy": 0.1728762060403824,
|
|
"num_tokens": 19037433.0,
|
|
"step": 8530
|
|
},
|
|
{
|
|
"entropy": 5.660763597488403,
|
|
"epoch": 0.9586117818835289,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004919160394183779,
|
|
"loss": 5.4263,
|
|
"mean_token_accuracy": 0.18210633993148803,
|
|
"num_tokens": 19047351.0,
|
|
"step": 8535
|
|
},
|
|
{
|
|
"entropy": 5.5106230735778805,
|
|
"epoch": 0.9591733587914865,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.000491905370712362,
|
|
"loss": 5.4452,
|
|
"mean_token_accuracy": 0.1771640196442604,
|
|
"num_tokens": 19058561.0,
|
|
"step": 8540
|
|
},
|
|
{
|
|
"entropy": 5.622301530838013,
|
|
"epoch": 0.959734935699444,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004918946950999949,
|
|
"loss": 5.5518,
|
|
"mean_token_accuracy": 0.17158325761556625,
|
|
"num_tokens": 19069877.0,
|
|
"step": 8545
|
|
},
|
|
{
|
|
"entropy": 5.715827512741089,
|
|
"epoch": 0.9602965126074016,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004918840125816167,
|
|
"loss": 5.5672,
|
|
"mean_token_accuracy": 0.17627336978912353,
|
|
"num_tokens": 19081962.0,
|
|
"step": 8550
|
|
},
|
|
{
|
|
"entropy": 5.691046953201294,
|
|
"epoch": 0.9608580895153591,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004918733231575673,
|
|
"loss": 5.6206,
|
|
"mean_token_accuracy": 0.17397646605968475,
|
|
"num_tokens": 19092955.0,
|
|
"step": 8555
|
|
},
|
|
{
|
|
"entropy": 5.656470251083374,
|
|
"epoch": 0.9614196664233167,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004918626268281874,
|
|
"loss": 5.4262,
|
|
"mean_token_accuracy": 0.18749939501285554,
|
|
"num_tokens": 19103521.0,
|
|
"step": 8560
|
|
},
|
|
{
|
|
"entropy": 5.496189260482788,
|
|
"epoch": 0.9619812433312742,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004918519235938171,
|
|
"loss": 5.4577,
|
|
"mean_token_accuracy": 0.18570137321949004,
|
|
"num_tokens": 19114190.0,
|
|
"step": 8565
|
|
},
|
|
{
|
|
"entropy": 5.622612047195434,
|
|
"epoch": 0.9625428202392318,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004918412134547976,
|
|
"loss": 5.5029,
|
|
"mean_token_accuracy": 0.180270779132843,
|
|
"num_tokens": 19123815.0,
|
|
"step": 8570
|
|
},
|
|
{
|
|
"entropy": 5.688246822357177,
|
|
"epoch": 0.9631043971471893,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.0004918304964114696,
|
|
"loss": 5.6501,
|
|
"mean_token_accuracy": 0.17408276945352555,
|
|
"num_tokens": 19135805.0,
|
|
"step": 8575
|
|
},
|
|
{
|
|
"entropy": 5.650302362442017,
|
|
"epoch": 0.9636659740551469,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004918197724641747,
|
|
"loss": 5.4845,
|
|
"mean_token_accuracy": 0.17529771775007247,
|
|
"num_tokens": 19146656.0,
|
|
"step": 8580
|
|
},
|
|
{
|
|
"entropy": 5.603388833999634,
|
|
"epoch": 0.9642275509631044,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.000491809041613254,
|
|
"loss": 5.5432,
|
|
"mean_token_accuracy": 0.17583068758249282,
|
|
"num_tokens": 19158271.0,
|
|
"step": 8585
|
|
},
|
|
{
|
|
"entropy": 5.6231530666351315,
|
|
"epoch": 0.964789127871062,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004917983038590495,
|
|
"loss": 5.452,
|
|
"mean_token_accuracy": 0.1768071934580803,
|
|
"num_tokens": 19168439.0,
|
|
"step": 8590
|
|
},
|
|
{
|
|
"entropy": 5.678795385360718,
|
|
"epoch": 0.9653507047790195,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004917875592019028,
|
|
"loss": 5.5416,
|
|
"mean_token_accuracy": 0.18070913702249528,
|
|
"num_tokens": 19179411.0,
|
|
"step": 8595
|
|
},
|
|
{
|
|
"entropy": 5.648492097854614,
|
|
"epoch": 0.9659122816869771,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004917768076421561,
|
|
"loss": 5.5694,
|
|
"mean_token_accuracy": 0.17678338289260864,
|
|
"num_tokens": 19189377.0,
|
|
"step": 8600
|
|
},
|
|
{
|
|
"entropy": 5.610542869567871,
|
|
"epoch": 0.9664738585949346,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004917660491801518,
|
|
"loss": 5.545,
|
|
"mean_token_accuracy": 0.17916877418756486,
|
|
"num_tokens": 19200662.0,
|
|
"step": 8605
|
|
},
|
|
{
|
|
"entropy": 5.662050104141235,
|
|
"epoch": 0.9670354355028922,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004917552838162324,
|
|
"loss": 5.445,
|
|
"mean_token_accuracy": 0.18179134726524354,
|
|
"num_tokens": 19211535.0,
|
|
"step": 8610
|
|
},
|
|
{
|
|
"entropy": 5.622387981414795,
|
|
"epoch": 0.9675970124108496,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.0004917445115507408,
|
|
"loss": 5.413,
|
|
"mean_token_accuracy": 0.1857159271836281,
|
|
"num_tokens": 19223402.0,
|
|
"step": 8615
|
|
},
|
|
{
|
|
"entropy": 5.4861372947692875,
|
|
"epoch": 0.9681585893188072,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004917337323840198,
|
|
"loss": 5.4962,
|
|
"mean_token_accuracy": 0.1825364947319031,
|
|
"num_tokens": 19234976.0,
|
|
"step": 8620
|
|
},
|
|
{
|
|
"entropy": 5.48188362121582,
|
|
"epoch": 0.9687201662267647,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004917229463164128,
|
|
"loss": 5.3596,
|
|
"mean_token_accuracy": 0.18579547554254533,
|
|
"num_tokens": 19247328.0,
|
|
"step": 8625
|
|
},
|
|
{
|
|
"entropy": 5.658888292312622,
|
|
"epoch": 0.9692817431347223,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004917121533482631,
|
|
"loss": 5.5013,
|
|
"mean_token_accuracy": 0.17166814506053923,
|
|
"num_tokens": 19259021.0,
|
|
"step": 8630
|
|
},
|
|
{
|
|
"entropy": 5.588575410842895,
|
|
"epoch": 0.9698433200426798,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004917013534799144,
|
|
"loss": 5.4659,
|
|
"mean_token_accuracy": 0.1785414397716522,
|
|
"num_tokens": 19270021.0,
|
|
"step": 8635
|
|
},
|
|
{
|
|
"entropy": 5.614198637008667,
|
|
"epoch": 0.9704048969506374,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004916905467117104,
|
|
"loss": 5.5187,
|
|
"mean_token_accuracy": 0.18298740983009337,
|
|
"num_tokens": 19281520.0,
|
|
"step": 8640
|
|
},
|
|
{
|
|
"entropy": 5.649200105667115,
|
|
"epoch": 0.9709664738585949,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004916797330439955,
|
|
"loss": 5.467,
|
|
"mean_token_accuracy": 0.1780417174100876,
|
|
"num_tokens": 19292761.0,
|
|
"step": 8645
|
|
},
|
|
{
|
|
"entropy": 5.603718090057373,
|
|
"epoch": 0.9715280507665525,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004916689124771138,
|
|
"loss": 5.5702,
|
|
"mean_token_accuracy": 0.17657738775014878,
|
|
"num_tokens": 19305022.0,
|
|
"step": 8650
|
|
},
|
|
{
|
|
"entropy": 5.737547111511231,
|
|
"epoch": 0.97208962767451,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004916580850114099,
|
|
"loss": 5.6603,
|
|
"mean_token_accuracy": 0.16766298413276673,
|
|
"num_tokens": 19316162.0,
|
|
"step": 8655
|
|
},
|
|
{
|
|
"entropy": 5.833925056457519,
|
|
"epoch": 0.9726512045824676,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004916472506472286,
|
|
"loss": 5.6852,
|
|
"mean_token_accuracy": 0.16427507549524306,
|
|
"num_tokens": 19327015.0,
|
|
"step": 8660
|
|
},
|
|
{
|
|
"entropy": 5.584185552597046,
|
|
"epoch": 0.9732127814904251,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004916364093849147,
|
|
"loss": 5.5389,
|
|
"mean_token_accuracy": 0.17456586062908172,
|
|
"num_tokens": 19338384.0,
|
|
"step": 8665
|
|
},
|
|
{
|
|
"entropy": 5.598966312408447,
|
|
"epoch": 0.9737743583983827,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004916255612248136,
|
|
"loss": 5.4516,
|
|
"mean_token_accuracy": 0.1824479803442955,
|
|
"num_tokens": 19349846.0,
|
|
"step": 8670
|
|
},
|
|
{
|
|
"entropy": 5.685277938842773,
|
|
"epoch": 0.9743359353063402,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004916147061672706,
|
|
"loss": 5.5014,
|
|
"mean_token_accuracy": 0.1820174366235733,
|
|
"num_tokens": 19361399.0,
|
|
"step": 8675
|
|
},
|
|
{
|
|
"entropy": 5.5525007247924805,
|
|
"epoch": 0.9748975122142978,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004916038442126314,
|
|
"loss": 5.4698,
|
|
"mean_token_accuracy": 0.17418861240148545,
|
|
"num_tokens": 19371990.0,
|
|
"step": 8680
|
|
},
|
|
{
|
|
"entropy": 5.551935911178589,
|
|
"epoch": 0.9754590891222553,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004915929753612416,
|
|
"loss": 5.4782,
|
|
"mean_token_accuracy": 0.1789302036166191,
|
|
"num_tokens": 19383135.0,
|
|
"step": 8685
|
|
},
|
|
{
|
|
"entropy": 5.651277351379394,
|
|
"epoch": 0.9760206660302129,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004915820996134477,
|
|
"loss": 5.5687,
|
|
"mean_token_accuracy": 0.1756932929158211,
|
|
"num_tokens": 19393942.0,
|
|
"step": 8690
|
|
},
|
|
{
|
|
"entropy": 5.626863956451416,
|
|
"epoch": 0.9765822429381704,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004915712169695956,
|
|
"loss": 5.3976,
|
|
"mean_token_accuracy": 0.18496251702308655,
|
|
"num_tokens": 19404255.0,
|
|
"step": 8695
|
|
},
|
|
{
|
|
"entropy": 5.5789430141448975,
|
|
"epoch": 0.977143819846128,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.000491560327430032,
|
|
"loss": 5.4973,
|
|
"mean_token_accuracy": 0.18038258850574493,
|
|
"num_tokens": 19415425.0,
|
|
"step": 8700
|
|
},
|
|
{
|
|
"entropy": 5.551576948165893,
|
|
"epoch": 0.9777053967540855,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.0004915494309951035,
|
|
"loss": 5.4342,
|
|
"mean_token_accuracy": 0.18573567420244216,
|
|
"num_tokens": 19426050.0,
|
|
"step": 8705
|
|
},
|
|
{
|
|
"entropy": 5.610976696014404,
|
|
"epoch": 0.9782669736620431,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004915385276651573,
|
|
"loss": 5.5406,
|
|
"mean_token_accuracy": 0.17139376550912858,
|
|
"num_tokens": 19437471.0,
|
|
"step": 8710
|
|
},
|
|
{
|
|
"entropy": 5.681982946395874,
|
|
"epoch": 0.9788285505700005,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004915276174405403,
|
|
"loss": 5.5628,
|
|
"mean_token_accuracy": 0.1820400983095169,
|
|
"num_tokens": 19449569.0,
|
|
"step": 8715
|
|
},
|
|
{
|
|
"entropy": 5.675716352462769,
|
|
"epoch": 0.9793901274779581,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004915167003215999,
|
|
"loss": 5.5874,
|
|
"mean_token_accuracy": 0.17075849324464798,
|
|
"num_tokens": 19461630.0,
|
|
"step": 8720
|
|
},
|
|
{
|
|
"entropy": 5.6025676250457765,
|
|
"epoch": 0.9799517043859156,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004915057763086838,
|
|
"loss": 5.5142,
|
|
"mean_token_accuracy": 0.1801046311855316,
|
|
"num_tokens": 19472626.0,
|
|
"step": 8725
|
|
},
|
|
{
|
|
"entropy": 5.55344967842102,
|
|
"epoch": 0.9805132812938732,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.00049149484540214,
|
|
"loss": 5.4924,
|
|
"mean_token_accuracy": 0.17231539785861968,
|
|
"num_tokens": 19483141.0,
|
|
"step": 8730
|
|
},
|
|
{
|
|
"entropy": 5.604358911514282,
|
|
"epoch": 0.9810748582018307,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004914839076023161,
|
|
"loss": 5.4767,
|
|
"mean_token_accuracy": 0.18122661858797073,
|
|
"num_tokens": 19495052.0,
|
|
"step": 8735
|
|
},
|
|
{
|
|
"entropy": 5.7132368087768555,
|
|
"epoch": 0.9816364351097883,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.0004914729629095609,
|
|
"loss": 5.5313,
|
|
"mean_token_accuracy": 0.17553042620420456,
|
|
"num_tokens": 19506911.0,
|
|
"step": 8740
|
|
},
|
|
{
|
|
"entropy": 5.570093441009521,
|
|
"epoch": 0.9821980120177458,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004914620113242224,
|
|
"loss": 5.4156,
|
|
"mean_token_accuracy": 0.1812910720705986,
|
|
"num_tokens": 19517812.0,
|
|
"step": 8745
|
|
},
|
|
{
|
|
"entropy": 5.59376711845398,
|
|
"epoch": 0.9827595889257034,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004914510528466495,
|
|
"loss": 5.5074,
|
|
"mean_token_accuracy": 0.17824313044548035,
|
|
"num_tokens": 19529857.0,
|
|
"step": 8750
|
|
},
|
|
{
|
|
"entropy": 5.63494029045105,
|
|
"epoch": 0.9833211658336609,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004914400874771913,
|
|
"loss": 5.5232,
|
|
"mean_token_accuracy": 0.17526382505893706,
|
|
"num_tokens": 19541082.0,
|
|
"step": 8755
|
|
},
|
|
{
|
|
"entropy": 5.60880331993103,
|
|
"epoch": 0.9838827427416185,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004914291152161967,
|
|
"loss": 5.456,
|
|
"mean_token_accuracy": 0.1860918864607811,
|
|
"num_tokens": 19551266.0,
|
|
"step": 8760
|
|
},
|
|
{
|
|
"entropy": 5.626666784286499,
|
|
"epoch": 0.984444319649576,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.000491418136064015,
|
|
"loss": 5.6394,
|
|
"mean_token_accuracy": 0.1742235541343689,
|
|
"num_tokens": 19563381.0,
|
|
"step": 8765
|
|
},
|
|
{
|
|
"entropy": 5.7155595302581785,
|
|
"epoch": 0.9850058965575336,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.000491407150020996,
|
|
"loss": 5.6704,
|
|
"mean_token_accuracy": 0.17258958965539933,
|
|
"num_tokens": 19575078.0,
|
|
"step": 8770
|
|
},
|
|
{
|
|
"entropy": 5.729107093811035,
|
|
"epoch": 0.9855674734654911,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004913961570874895,
|
|
"loss": 5.4732,
|
|
"mean_token_accuracy": 0.1780588820576668,
|
|
"num_tokens": 19585273.0,
|
|
"step": 8775
|
|
},
|
|
{
|
|
"entropy": 5.573114252090454,
|
|
"epoch": 0.9861290503734487,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004913851572638453,
|
|
"loss": 5.4844,
|
|
"mean_token_accuracy": 0.18068378269672394,
|
|
"num_tokens": 19594245.0,
|
|
"step": 8780
|
|
},
|
|
{
|
|
"entropy": 5.616564607620239,
|
|
"epoch": 0.9866906272814062,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004913741505504138,
|
|
"loss": 5.5179,
|
|
"mean_token_accuracy": 0.17540809363126755,
|
|
"num_tokens": 19604920.0,
|
|
"step": 8785
|
|
},
|
|
{
|
|
"entropy": 5.742310619354248,
|
|
"epoch": 0.9872522041893638,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004913631369475454,
|
|
"loss": 5.6151,
|
|
"mean_token_accuracy": 0.16787779331207275,
|
|
"num_tokens": 19616592.0,
|
|
"step": 8790
|
|
},
|
|
{
|
|
"entropy": 5.746342325210572,
|
|
"epoch": 0.9878137810973213,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004913521164555909,
|
|
"loss": 5.5731,
|
|
"mean_token_accuracy": 0.17372505962848664,
|
|
"num_tokens": 19627359.0,
|
|
"step": 8795
|
|
},
|
|
{
|
|
"entropy": 5.615099811553955,
|
|
"epoch": 0.9883753580052789,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.000491341089074901,
|
|
"loss": 5.545,
|
|
"mean_token_accuracy": 0.17857607156038285,
|
|
"num_tokens": 19639685.0,
|
|
"step": 8800
|
|
},
|
|
{
|
|
"entropy": 5.524734354019165,
|
|
"epoch": 0.9889369349132364,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.000491330054805827,
|
|
"loss": 5.3761,
|
|
"mean_token_accuracy": 0.18857753574848174,
|
|
"num_tokens": 19650525.0,
|
|
"step": 8805
|
|
},
|
|
{
|
|
"entropy": 5.498490571975708,
|
|
"epoch": 0.9894985118211939,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004913190136487201,
|
|
"loss": 5.4373,
|
|
"mean_token_accuracy": 0.1854410395026207,
|
|
"num_tokens": 19662241.0,
|
|
"step": 8810
|
|
},
|
|
{
|
|
"entropy": 5.654824876785279,
|
|
"epoch": 0.9900600887291514,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004913079656039318,
|
|
"loss": 5.5172,
|
|
"mean_token_accuracy": 0.18074833750724792,
|
|
"num_tokens": 19673752.0,
|
|
"step": 8815
|
|
},
|
|
{
|
|
"entropy": 5.616615200042725,
|
|
"epoch": 0.990621665637109,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004912969106718142,
|
|
"loss": 5.5075,
|
|
"mean_token_accuracy": 0.17563024759292603,
|
|
"num_tokens": 19685309.0,
|
|
"step": 8820
|
|
},
|
|
{
|
|
"entropy": 5.632031345367432,
|
|
"epoch": 0.9911832425450665,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.000491285848852719,
|
|
"loss": 5.5913,
|
|
"mean_token_accuracy": 0.17363901883363725,
|
|
"num_tokens": 19697391.0,
|
|
"step": 8825
|
|
},
|
|
{
|
|
"entropy": 5.68126072883606,
|
|
"epoch": 0.9917448194530241,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004912747801469984,
|
|
"loss": 5.57,
|
|
"mean_token_accuracy": 0.17301420569419862,
|
|
"num_tokens": 19707426.0,
|
|
"step": 8830
|
|
},
|
|
{
|
|
"entropy": 5.703397417068482,
|
|
"epoch": 0.9923063963609816,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.000491263704555005,
|
|
"loss": 5.5836,
|
|
"mean_token_accuracy": 0.17198873162269593,
|
|
"num_tokens": 19719800.0,
|
|
"step": 8835
|
|
},
|
|
{
|
|
"entropy": 5.584424638748169,
|
|
"epoch": 0.9928679732689392,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004912526220770913,
|
|
"loss": 5.4809,
|
|
"mean_token_accuracy": 0.1769191265106201,
|
|
"num_tokens": 19731600.0,
|
|
"step": 8840
|
|
},
|
|
{
|
|
"entropy": 5.6541845321655275,
|
|
"epoch": 0.9934295501768967,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004912415327136103,
|
|
"loss": 5.4843,
|
|
"mean_token_accuracy": 0.17787706553936006,
|
|
"num_tokens": 19742610.0,
|
|
"step": 8845
|
|
},
|
|
{
|
|
"entropy": 5.724423742294311,
|
|
"epoch": 0.9939911270848543,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.000491230436464915,
|
|
"loss": 5.6993,
|
|
"mean_token_accuracy": 0.1644985169172287,
|
|
"num_tokens": 19754207.0,
|
|
"step": 8850
|
|
},
|
|
{
|
|
"entropy": 5.5799237251281735,
|
|
"epoch": 0.9945527039928118,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004912193333313589,
|
|
"loss": 5.4021,
|
|
"mean_token_accuracy": 0.18267642706632614,
|
|
"num_tokens": 19765894.0,
|
|
"step": 8855
|
|
},
|
|
{
|
|
"entropy": 5.591323518753052,
|
|
"epoch": 0.9951142809007694,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.0004912082233132951,
|
|
"loss": 5.5578,
|
|
"mean_token_accuracy": 0.17752243727445602,
|
|
"num_tokens": 19777867.0,
|
|
"step": 8860
|
|
},
|
|
{
|
|
"entropy": 5.57280912399292,
|
|
"epoch": 0.9956758578087269,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004911971064110778,
|
|
"loss": 5.4377,
|
|
"mean_token_accuracy": 0.18364784568548204,
|
|
"num_tokens": 19788346.0,
|
|
"step": 8865
|
|
},
|
|
{
|
|
"entropy": 5.741678953170776,
|
|
"epoch": 0.9962374347166845,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004911859826250607,
|
|
"loss": 5.5949,
|
|
"mean_token_accuracy": 0.17850873172283171,
|
|
"num_tokens": 19799752.0,
|
|
"step": 8870
|
|
},
|
|
{
|
|
"entropy": 5.609176158905029,
|
|
"epoch": 0.996799011624642,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004911748519555981,
|
|
"loss": 5.5538,
|
|
"mean_token_accuracy": 0.1760181277990341,
|
|
"num_tokens": 19810387.0,
|
|
"step": 8875
|
|
},
|
|
{
|
|
"entropy": 5.578026247024536,
|
|
"epoch": 0.9973605885325996,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004911637144030444,
|
|
"loss": 5.5034,
|
|
"mean_token_accuracy": 0.17903240770101547,
|
|
"num_tokens": 19822092.0,
|
|
"step": 8880
|
|
},
|
|
{
|
|
"entropy": 5.6890615940094,
|
|
"epoch": 0.9979221654405571,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004911525699677541,
|
|
"loss": 5.6177,
|
|
"mean_token_accuracy": 0.16711452305316926,
|
|
"num_tokens": 19833731.0,
|
|
"step": 8885
|
|
},
|
|
{
|
|
"entropy": 5.576133823394775,
|
|
"epoch": 0.9984837423485147,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004911414186500822,
|
|
"loss": 5.5329,
|
|
"mean_token_accuracy": 0.17381285578012468,
|
|
"num_tokens": 19845101.0,
|
|
"step": 8890
|
|
},
|
|
{
|
|
"entropy": 5.6682299137115475,
|
|
"epoch": 0.9990453192564722,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004911302604503837,
|
|
"loss": 5.5943,
|
|
"mean_token_accuracy": 0.17127314656972886,
|
|
"num_tokens": 19857006.0,
|
|
"step": 8895
|
|
},
|
|
{
|
|
"entropy": 5.625555515289307,
|
|
"epoch": 0.9996068961644298,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004911190953690139,
|
|
"loss": 5.4729,
|
|
"mean_token_accuracy": 0.1820724353194237,
|
|
"num_tokens": 19868007.0,
|
|
"step": 8900
|
|
},
|
|
{
|
|
"entropy": 5.767914666069879,
|
|
"epoch": 1.0001123153815914,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004911079234063284,
|
|
"loss": 5.4298,
|
|
"mean_token_accuracy": 0.17969958318604362,
|
|
"num_tokens": 19877897.0,
|
|
"step": 8905
|
|
},
|
|
{
|
|
"entropy": 5.662891292572022,
|
|
"epoch": 1.000673892289549,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004910967445626826,
|
|
"loss": 5.471,
|
|
"mean_token_accuracy": 0.17959870249032975,
|
|
"num_tokens": 19888449.0,
|
|
"step": 8910
|
|
},
|
|
{
|
|
"entropy": 5.563129615783692,
|
|
"epoch": 1.0012354691975065,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004910855588384327,
|
|
"loss": 5.4442,
|
|
"mean_token_accuracy": 0.17572594285011292,
|
|
"num_tokens": 19898998.0,
|
|
"step": 8915
|
|
},
|
|
{
|
|
"entropy": 5.665928220748901,
|
|
"epoch": 1.0017970461054642,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004910743662339348,
|
|
"loss": 5.4742,
|
|
"mean_token_accuracy": 0.18103645443916322,
|
|
"num_tokens": 19910369.0,
|
|
"step": 8920
|
|
},
|
|
{
|
|
"entropy": 5.720305252075195,
|
|
"epoch": 1.0023586230134216,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004910631667495452,
|
|
"loss": 5.5022,
|
|
"mean_token_accuracy": 0.18460525572299957,
|
|
"num_tokens": 19921936.0,
|
|
"step": 8925
|
|
},
|
|
{
|
|
"entropy": 5.625992298126221,
|
|
"epoch": 1.0029201999213793,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004910519603856207,
|
|
"loss": 5.4848,
|
|
"mean_token_accuracy": 0.18052565753459932,
|
|
"num_tokens": 19933943.0,
|
|
"step": 8930
|
|
},
|
|
{
|
|
"entropy": 5.505383253097534,
|
|
"epoch": 1.0034817768293367,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004910407471425179,
|
|
"loss": 5.285,
|
|
"mean_token_accuracy": 0.1897411197423935,
|
|
"num_tokens": 19944377.0,
|
|
"step": 8935
|
|
},
|
|
{
|
|
"entropy": 5.518276691436768,
|
|
"epoch": 1.0040433537372944,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.000491029527020594,
|
|
"loss": 5.3929,
|
|
"mean_token_accuracy": 0.18249510377645492,
|
|
"num_tokens": 19954865.0,
|
|
"step": 8940
|
|
},
|
|
{
|
|
"entropy": 5.50196852684021,
|
|
"epoch": 1.0046049306452518,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004910183000202061,
|
|
"loss": 5.3375,
|
|
"mean_token_accuracy": 0.1866047516465187,
|
|
"num_tokens": 19965021.0,
|
|
"step": 8945
|
|
},
|
|
{
|
|
"entropy": 5.63343825340271,
|
|
"epoch": 1.0051665075532095,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004910070661417119,
|
|
"loss": 5.4252,
|
|
"mean_token_accuracy": 0.18166023045778273,
|
|
"num_tokens": 19977068.0,
|
|
"step": 8950
|
|
},
|
|
{
|
|
"entropy": 5.5770731449127195,
|
|
"epoch": 1.005728084461167,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004909958253854687,
|
|
"loss": 5.4513,
|
|
"mean_token_accuracy": 0.17523814588785172,
|
|
"num_tokens": 19987994.0,
|
|
"step": 8955
|
|
},
|
|
{
|
|
"entropy": 5.617107915878296,
|
|
"epoch": 1.0062896613691246,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004909845777518347,
|
|
"loss": 5.4644,
|
|
"mean_token_accuracy": 0.17608024179935455,
|
|
"num_tokens": 19998598.0,
|
|
"step": 8960
|
|
},
|
|
{
|
|
"entropy": 5.595203256607055,
|
|
"epoch": 1.006851238277082,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004909733232411681,
|
|
"loss": 5.3372,
|
|
"mean_token_accuracy": 0.19038300067186356,
|
|
"num_tokens": 20008881.0,
|
|
"step": 8965
|
|
},
|
|
{
|
|
"entropy": 5.557106304168701,
|
|
"epoch": 1.0074128151850397,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004909620618538271,
|
|
"loss": 5.4043,
|
|
"mean_token_accuracy": 0.1821080982685089,
|
|
"num_tokens": 20019105.0,
|
|
"step": 8970
|
|
},
|
|
{
|
|
"entropy": 5.5577679634094235,
|
|
"epoch": 1.007974392092997,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004909507935901702,
|
|
"loss": 5.4484,
|
|
"mean_token_accuracy": 0.17803366631269454,
|
|
"num_tokens": 20031805.0,
|
|
"step": 8975
|
|
},
|
|
{
|
|
"entropy": 5.641224002838134,
|
|
"epoch": 1.0085359690009548,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004909395184505564,
|
|
"loss": 5.3903,
|
|
"mean_token_accuracy": 0.18695543855428695,
|
|
"num_tokens": 20041493.0,
|
|
"step": 8980
|
|
},
|
|
{
|
|
"entropy": 5.587377309799194,
|
|
"epoch": 1.0090975459089122,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004909282364353445,
|
|
"loss": 5.4433,
|
|
"mean_token_accuracy": 0.18386414647102356,
|
|
"num_tokens": 20052489.0,
|
|
"step": 8985
|
|
},
|
|
{
|
|
"entropy": 5.470388507843017,
|
|
"epoch": 1.0096591228168699,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004909169475448938,
|
|
"loss": 5.4052,
|
|
"mean_token_accuracy": 0.18192545473575591,
|
|
"num_tokens": 20064252.0,
|
|
"step": 8990
|
|
},
|
|
{
|
|
"entropy": 5.54841570854187,
|
|
"epoch": 1.0102206997248273,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004909056517795638,
|
|
"loss": 5.3505,
|
|
"mean_token_accuracy": 0.1826937735080719,
|
|
"num_tokens": 20075171.0,
|
|
"step": 8995
|
|
},
|
|
{
|
|
"entropy": 5.557896327972412,
|
|
"epoch": 1.010782276632785,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004908943491397141,
|
|
"loss": 5.3446,
|
|
"mean_token_accuracy": 0.17997617572546004,
|
|
"num_tokens": 20085746.0,
|
|
"step": 9000
|
|
},
|
|
{
|
|
"epoch": 1.010782276632785,
|
|
"eval_entropy": 5.397618952380464,
|
|
"eval_loss": 5.550064563751221,
|
|
"eval_mean_token_accuracy": 0.18335057606044766,
|
|
"eval_num_tokens": 20085746.0,
|
|
"eval_runtime": 23.8339,
|
|
"eval_samples_per_second": 1301.214,
|
|
"eval_steps_per_second": 162.668,
|
|
"step": 9000
|
|
}
|
|
],
|
|
"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": 3.1507094368512e+16,
|
|
"train_batch_size": 16,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|