79fddc95bb
Model: fpadovani/eng-latn-100mb-after-ppt-shuff-dyck-100mb-ckpt500_seed3407 Source: Original Platform
6046 lines
164 KiB
JSON
6046 lines
164 KiB
JSON
{
|
|
"best_global_step": null,
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 0.3369461447745269,
|
|
"eval_steps": 3000,
|
|
"global_step": 3000,
|
|
"is_hyper_param_search": false,
|
|
"is_local_process_zero": true,
|
|
"is_world_process_zero": true,
|
|
"log_history": [
|
|
{
|
|
"entropy": 4.799633407592774,
|
|
"epoch": 0.0005615769079575448,
|
|
"grad_norm": 14.6875,
|
|
"learning_rate": 2e-06,
|
|
"loss": 14.5557,
|
|
"mean_token_accuracy": 0.0,
|
|
"num_tokens": 11659.0,
|
|
"step": 5
|
|
},
|
|
{
|
|
"entropy": 4.788970327377319,
|
|
"epoch": 0.0011231538159150896,
|
|
"grad_norm": 14.625,
|
|
"learning_rate": 4.5e-06,
|
|
"loss": 14.4346,
|
|
"mean_token_accuracy": 0.0,
|
|
"num_tokens": 21794.0,
|
|
"step": 10
|
|
},
|
|
{
|
|
"entropy": 4.845954370498657,
|
|
"epoch": 0.0016847307238726343,
|
|
"grad_norm": 16.5,
|
|
"learning_rate": 7e-06,
|
|
"loss": 14.2561,
|
|
"mean_token_accuracy": 0.0,
|
|
"num_tokens": 33206.0,
|
|
"step": 15
|
|
},
|
|
{
|
|
"entropy": 4.982930469512939,
|
|
"epoch": 0.0022463076318301792,
|
|
"grad_norm": 22.75,
|
|
"learning_rate": 9.5e-06,
|
|
"loss": 13.7895,
|
|
"mean_token_accuracy": 9.009009227156639e-05,
|
|
"num_tokens": 44487.0,
|
|
"step": 20
|
|
},
|
|
{
|
|
"entropy": 6.338765239715576,
|
|
"epoch": 0.002807884539787724,
|
|
"grad_norm": 28.25,
|
|
"learning_rate": 1.2e-05,
|
|
"loss": 12.4105,
|
|
"mean_token_accuracy": 0.0,
|
|
"num_tokens": 56062.0,
|
|
"step": 25
|
|
},
|
|
{
|
|
"entropy": 9.909645938873291,
|
|
"epoch": 0.0033694614477452686,
|
|
"grad_norm": 3.625,
|
|
"learning_rate": 1.4500000000000002e-05,
|
|
"loss": 10.9952,
|
|
"mean_token_accuracy": 0.00023980815894901751,
|
|
"num_tokens": 67453.0,
|
|
"step": 30
|
|
},
|
|
{
|
|
"entropy": 10.690417957305907,
|
|
"epoch": 0.003931038355702813,
|
|
"grad_norm": 3.203125,
|
|
"learning_rate": 1.7000000000000003e-05,
|
|
"loss": 10.6677,
|
|
"mean_token_accuracy": 0.012192816147580743,
|
|
"num_tokens": 78527.0,
|
|
"step": 35
|
|
},
|
|
{
|
|
"entropy": 10.696582508087157,
|
|
"epoch": 0.0044926152636603585,
|
|
"grad_norm": 2.859375,
|
|
"learning_rate": 1.95e-05,
|
|
"loss": 10.3258,
|
|
"mean_token_accuracy": 0.01598402885720134,
|
|
"num_tokens": 89267.0,
|
|
"step": 40
|
|
},
|
|
{
|
|
"entropy": 10.660813236236573,
|
|
"epoch": 0.005054192171617903,
|
|
"grad_norm": 2.734375,
|
|
"learning_rate": 2.2e-05,
|
|
"loss": 9.9837,
|
|
"mean_token_accuracy": 0.0142933520488441,
|
|
"num_tokens": 102035.0,
|
|
"step": 45
|
|
},
|
|
{
|
|
"entropy": 10.618993759155273,
|
|
"epoch": 0.005615769079575448,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 2.4500000000000003e-05,
|
|
"loss": 9.7405,
|
|
"mean_token_accuracy": 0.03635566085577011,
|
|
"num_tokens": 112734.0,
|
|
"step": 50
|
|
},
|
|
{
|
|
"entropy": 10.588664054870605,
|
|
"epoch": 0.006177345987532993,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 2.7e-05,
|
|
"loss": 9.5631,
|
|
"mean_token_accuracy": 0.03734342660754919,
|
|
"num_tokens": 123854.0,
|
|
"step": 55
|
|
},
|
|
{
|
|
"entropy": 10.573542404174805,
|
|
"epoch": 0.006738922895490537,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 2.95e-05,
|
|
"loss": 9.4769,
|
|
"mean_token_accuracy": 0.036952446401119235,
|
|
"num_tokens": 133444.0,
|
|
"step": 60
|
|
},
|
|
{
|
|
"entropy": 10.567419147491455,
|
|
"epoch": 0.007300499803448083,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 3.2e-05,
|
|
"loss": 9.3825,
|
|
"mean_token_accuracy": 0.03926227204501629,
|
|
"num_tokens": 144678.0,
|
|
"step": 65
|
|
},
|
|
{
|
|
"entropy": 10.560663509368897,
|
|
"epoch": 0.007862076711405626,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 3.4500000000000005e-05,
|
|
"loss": 9.3132,
|
|
"mean_token_accuracy": 0.040116249769926074,
|
|
"num_tokens": 155866.0,
|
|
"step": 70
|
|
},
|
|
{
|
|
"entropy": 10.53321475982666,
|
|
"epoch": 0.008423653619363172,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 3.7e-05,
|
|
"loss": 9.2394,
|
|
"mean_token_accuracy": 0.03705750666558742,
|
|
"num_tokens": 166965.0,
|
|
"step": 75
|
|
},
|
|
{
|
|
"entropy": 10.505771923065186,
|
|
"epoch": 0.008985230527320717,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 3.95e-05,
|
|
"loss": 9.148,
|
|
"mean_token_accuracy": 0.038686181604862216,
|
|
"num_tokens": 177423.0,
|
|
"step": 80
|
|
},
|
|
{
|
|
"entropy": 10.492299270629882,
|
|
"epoch": 0.00954680743527826,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 4.2000000000000004e-05,
|
|
"loss": 9.0453,
|
|
"mean_token_accuracy": 0.03904180806130171,
|
|
"num_tokens": 188687.0,
|
|
"step": 85
|
|
},
|
|
{
|
|
"entropy": 10.44793472290039,
|
|
"epoch": 0.010108384343235806,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 4.45e-05,
|
|
"loss": 9.0036,
|
|
"mean_token_accuracy": 0.03891269974410534,
|
|
"num_tokens": 200173.0,
|
|
"step": 90
|
|
},
|
|
{
|
|
"entropy": 10.397690582275391,
|
|
"epoch": 0.010669961251193351,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 4.7000000000000004e-05,
|
|
"loss": 8.877,
|
|
"mean_token_accuracy": 0.04189660474658012,
|
|
"num_tokens": 210877.0,
|
|
"step": 95
|
|
},
|
|
{
|
|
"entropy": 10.355337524414063,
|
|
"epoch": 0.011231538159150897,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 4.9500000000000004e-05,
|
|
"loss": 8.7438,
|
|
"mean_token_accuracy": 0.04301192462444305,
|
|
"num_tokens": 221770.0,
|
|
"step": 100
|
|
},
|
|
{
|
|
"entropy": 10.287545108795166,
|
|
"epoch": 0.01179311506710844,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 5.2e-05,
|
|
"loss": 8.6419,
|
|
"mean_token_accuracy": 0.03942227344959974,
|
|
"num_tokens": 232140.0,
|
|
"step": 105
|
|
},
|
|
{
|
|
"entropy": 10.178714561462403,
|
|
"epoch": 0.012354691975065986,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 5.45e-05,
|
|
"loss": 8.5694,
|
|
"mean_token_accuracy": 0.0399751354008913,
|
|
"num_tokens": 244186.0,
|
|
"step": 110
|
|
},
|
|
{
|
|
"entropy": 10.056532287597657,
|
|
"epoch": 0.012916268883023531,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 5.7e-05,
|
|
"loss": 8.3694,
|
|
"mean_token_accuracy": 0.04193062111735344,
|
|
"num_tokens": 254805.0,
|
|
"step": 115
|
|
},
|
|
{
|
|
"entropy": 9.897430610656738,
|
|
"epoch": 0.013477845790981074,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 5.9499999999999996e-05,
|
|
"loss": 8.1667,
|
|
"mean_token_accuracy": 0.05483008846640587,
|
|
"num_tokens": 265055.0,
|
|
"step": 120
|
|
},
|
|
{
|
|
"entropy": 9.6635272026062,
|
|
"epoch": 0.01403942269893862,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 6.2e-05,
|
|
"loss": 8.0303,
|
|
"mean_token_accuracy": 0.05366372875869274,
|
|
"num_tokens": 275850.0,
|
|
"step": 125
|
|
},
|
|
{
|
|
"entropy": 9.444734287261962,
|
|
"epoch": 0.014600999606896165,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 6.450000000000001e-05,
|
|
"loss": 7.9378,
|
|
"mean_token_accuracy": 0.04993940331041813,
|
|
"num_tokens": 286802.0,
|
|
"step": 130
|
|
},
|
|
{
|
|
"entropy": 9.225319862365723,
|
|
"epoch": 0.015162576514853709,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 6.7e-05,
|
|
"loss": 7.8838,
|
|
"mean_token_accuracy": 0.05432286374270916,
|
|
"num_tokens": 297070.0,
|
|
"step": 135
|
|
},
|
|
{
|
|
"entropy": 8.997181510925293,
|
|
"epoch": 0.015724153422811252,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 6.950000000000001e-05,
|
|
"loss": 7.7723,
|
|
"mean_token_accuracy": 0.049000997096300125,
|
|
"num_tokens": 309617.0,
|
|
"step": 140
|
|
},
|
|
{
|
|
"entropy": 8.685122966766357,
|
|
"epoch": 0.0162857303307688,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 7.2e-05,
|
|
"loss": 7.6868,
|
|
"mean_token_accuracy": 0.05469490811228752,
|
|
"num_tokens": 321310.0,
|
|
"step": 145
|
|
},
|
|
{
|
|
"entropy": 8.375407505035401,
|
|
"epoch": 0.016847307238726343,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 7.45e-05,
|
|
"loss": 7.5755,
|
|
"mean_token_accuracy": 0.060717220231890676,
|
|
"num_tokens": 332243.0,
|
|
"step": 150
|
|
},
|
|
{
|
|
"entropy": 8.259093475341796,
|
|
"epoch": 0.017408884146683887,
|
|
"grad_norm": 0.76171875,
|
|
"learning_rate": 7.7e-05,
|
|
"loss": 7.5338,
|
|
"mean_token_accuracy": 0.054727142304182054,
|
|
"num_tokens": 342847.0,
|
|
"step": 155
|
|
},
|
|
{
|
|
"entropy": 8.08473482131958,
|
|
"epoch": 0.017970461054641434,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 7.950000000000001e-05,
|
|
"loss": 7.4611,
|
|
"mean_token_accuracy": 0.05515093542635441,
|
|
"num_tokens": 353570.0,
|
|
"step": 160
|
|
},
|
|
{
|
|
"entropy": 7.938348913192749,
|
|
"epoch": 0.018532037962598977,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 8.2e-05,
|
|
"loss": 7.4358,
|
|
"mean_token_accuracy": 0.06007346101105213,
|
|
"num_tokens": 364330.0,
|
|
"step": 165
|
|
},
|
|
{
|
|
"entropy": 7.877144718170166,
|
|
"epoch": 0.01909361487055652,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 8.450000000000001e-05,
|
|
"loss": 7.4554,
|
|
"mean_token_accuracy": 0.0588134877383709,
|
|
"num_tokens": 374930.0,
|
|
"step": 170
|
|
},
|
|
{
|
|
"entropy": 7.905826044082642,
|
|
"epoch": 0.019655191778514068,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 8.7e-05,
|
|
"loss": 7.4192,
|
|
"mean_token_accuracy": 0.06769459694623947,
|
|
"num_tokens": 384690.0,
|
|
"step": 175
|
|
},
|
|
{
|
|
"entropy": 7.834839868545532,
|
|
"epoch": 0.020216768686471612,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 8.95e-05,
|
|
"loss": 7.4338,
|
|
"mean_token_accuracy": 0.06734748221933842,
|
|
"num_tokens": 395753.0,
|
|
"step": 180
|
|
},
|
|
{
|
|
"entropy": 7.7875371932983395,
|
|
"epoch": 0.020778345594429155,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 9.2e-05,
|
|
"loss": 7.3766,
|
|
"mean_token_accuracy": 0.070906263589859,
|
|
"num_tokens": 407049.0,
|
|
"step": 185
|
|
},
|
|
{
|
|
"entropy": 7.763374948501587,
|
|
"epoch": 0.021339922502386702,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 9.45e-05,
|
|
"loss": 7.3517,
|
|
"mean_token_accuracy": 0.08063211217522621,
|
|
"num_tokens": 417942.0,
|
|
"step": 190
|
|
},
|
|
{
|
|
"entropy": 7.7808509349823,
|
|
"epoch": 0.021901499410344246,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 9.7e-05,
|
|
"loss": 7.3703,
|
|
"mean_token_accuracy": 0.0755468975752592,
|
|
"num_tokens": 428151.0,
|
|
"step": 195
|
|
},
|
|
{
|
|
"entropy": 7.772652101516724,
|
|
"epoch": 0.022463076318301793,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 9.95e-05,
|
|
"loss": 7.4319,
|
|
"mean_token_accuracy": 0.07449556142091751,
|
|
"num_tokens": 439837.0,
|
|
"step": 200
|
|
},
|
|
{
|
|
"entropy": 7.81195764541626,
|
|
"epoch": 0.023024653226259337,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000102,
|
|
"loss": 7.2708,
|
|
"mean_token_accuracy": 0.08094515725970268,
|
|
"num_tokens": 450357.0,
|
|
"step": 205
|
|
},
|
|
{
|
|
"entropy": 7.7834734439849855,
|
|
"epoch": 0.02358623013421688,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00010449999999999999,
|
|
"loss": 7.259,
|
|
"mean_token_accuracy": 0.08583413660526276,
|
|
"num_tokens": 461174.0,
|
|
"step": 210
|
|
},
|
|
{
|
|
"entropy": 7.716898488998413,
|
|
"epoch": 0.024147807042174427,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000107,
|
|
"loss": 7.3163,
|
|
"mean_token_accuracy": 0.08057258948683739,
|
|
"num_tokens": 472785.0,
|
|
"step": 215
|
|
},
|
|
{
|
|
"entropy": 7.6768852233886715,
|
|
"epoch": 0.02470938395013197,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0001095,
|
|
"loss": 7.2606,
|
|
"mean_token_accuracy": 0.0886429488658905,
|
|
"num_tokens": 483248.0,
|
|
"step": 220
|
|
},
|
|
{
|
|
"entropy": 7.674954032897949,
|
|
"epoch": 0.025270960858089515,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000112,
|
|
"loss": 7.1547,
|
|
"mean_token_accuracy": 0.08543359860777855,
|
|
"num_tokens": 494690.0,
|
|
"step": 225
|
|
},
|
|
{
|
|
"entropy": 7.694804096221924,
|
|
"epoch": 0.025832537766047062,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0001145,
|
|
"loss": 7.3437,
|
|
"mean_token_accuracy": 0.0837646782398224,
|
|
"num_tokens": 506192.0,
|
|
"step": 230
|
|
},
|
|
{
|
|
"entropy": 7.681186056137085,
|
|
"epoch": 0.026394114674004605,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00011700000000000001,
|
|
"loss": 7.2056,
|
|
"mean_token_accuracy": 0.08629952967166901,
|
|
"num_tokens": 517152.0,
|
|
"step": 235
|
|
},
|
|
{
|
|
"entropy": 7.538256502151489,
|
|
"epoch": 0.02695569158196215,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00011949999999999999,
|
|
"loss": 7.1298,
|
|
"mean_token_accuracy": 0.09271039292216302,
|
|
"num_tokens": 527836.0,
|
|
"step": 240
|
|
},
|
|
{
|
|
"entropy": 7.712969779968262,
|
|
"epoch": 0.027517268489919696,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.000122,
|
|
"loss": 7.2466,
|
|
"mean_token_accuracy": 0.08624056577682496,
|
|
"num_tokens": 539491.0,
|
|
"step": 245
|
|
},
|
|
{
|
|
"entropy": 7.584847354888916,
|
|
"epoch": 0.02807884539787724,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0001245,
|
|
"loss": 7.219,
|
|
"mean_token_accuracy": 0.08856328502297402,
|
|
"num_tokens": 550816.0,
|
|
"step": 250
|
|
},
|
|
{
|
|
"entropy": 7.612125205993652,
|
|
"epoch": 0.028640422305834783,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.000127,
|
|
"loss": 7.249,
|
|
"mean_token_accuracy": 0.08498690947890282,
|
|
"num_tokens": 561566.0,
|
|
"step": 255
|
|
},
|
|
{
|
|
"entropy": 7.637190675735473,
|
|
"epoch": 0.02920199921379233,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0001295,
|
|
"loss": 7.1759,
|
|
"mean_token_accuracy": 0.09114351570606231,
|
|
"num_tokens": 573032.0,
|
|
"step": 260
|
|
},
|
|
{
|
|
"entropy": 7.649462938308716,
|
|
"epoch": 0.029763576121749874,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000132,
|
|
"loss": 7.1046,
|
|
"mean_token_accuracy": 0.09311182051897049,
|
|
"num_tokens": 584140.0,
|
|
"step": 265
|
|
},
|
|
{
|
|
"entropy": 7.557653856277466,
|
|
"epoch": 0.030325153029707418,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.00013450000000000002,
|
|
"loss": 7.1759,
|
|
"mean_token_accuracy": 0.09324203431606293,
|
|
"num_tokens": 595097.0,
|
|
"step": 270
|
|
},
|
|
{
|
|
"entropy": 7.557107162475586,
|
|
"epoch": 0.030886729937664965,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00013700000000000002,
|
|
"loss": 7.1836,
|
|
"mean_token_accuracy": 0.09248357862234116,
|
|
"num_tokens": 606797.0,
|
|
"step": 275
|
|
},
|
|
{
|
|
"entropy": 7.505317544937133,
|
|
"epoch": 0.031448306845622505,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0001395,
|
|
"loss": 7.1357,
|
|
"mean_token_accuracy": 0.09568876847624778,
|
|
"num_tokens": 618187.0,
|
|
"step": 280
|
|
},
|
|
{
|
|
"entropy": 7.587315082550049,
|
|
"epoch": 0.032009883753580055,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00014199999999999998,
|
|
"loss": 7.0694,
|
|
"mean_token_accuracy": 0.09733563140034676,
|
|
"num_tokens": 629829.0,
|
|
"step": 285
|
|
},
|
|
{
|
|
"entropy": 7.454817771911621,
|
|
"epoch": 0.0325714606615376,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0001445,
|
|
"loss": 7.0751,
|
|
"mean_token_accuracy": 0.09884163439273834,
|
|
"num_tokens": 640914.0,
|
|
"step": 290
|
|
},
|
|
{
|
|
"entropy": 7.540893125534057,
|
|
"epoch": 0.03313303756949514,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000147,
|
|
"loss": 7.0809,
|
|
"mean_token_accuracy": 0.09153685793280601,
|
|
"num_tokens": 653057.0,
|
|
"step": 295
|
|
},
|
|
{
|
|
"entropy": 7.441942119598389,
|
|
"epoch": 0.033694614477452686,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0001495,
|
|
"loss": 7.0141,
|
|
"mean_token_accuracy": 0.10246249213814736,
|
|
"num_tokens": 663437.0,
|
|
"step": 300
|
|
},
|
|
{
|
|
"entropy": 7.427733898162842,
|
|
"epoch": 0.03425619138541023,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000152,
|
|
"loss": 7.0828,
|
|
"mean_token_accuracy": 0.09505958333611489,
|
|
"num_tokens": 675416.0,
|
|
"step": 305
|
|
},
|
|
{
|
|
"entropy": 7.327917146682739,
|
|
"epoch": 0.03481776829336777,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.00015450000000000001,
|
|
"loss": 6.8761,
|
|
"mean_token_accuracy": 0.10240658894181251,
|
|
"num_tokens": 686633.0,
|
|
"step": 310
|
|
},
|
|
{
|
|
"entropy": 7.421519470214844,
|
|
"epoch": 0.035379345201325324,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000157,
|
|
"loss": 6.9702,
|
|
"mean_token_accuracy": 0.10307649448513985,
|
|
"num_tokens": 698065.0,
|
|
"step": 315
|
|
},
|
|
{
|
|
"entropy": 7.40921802520752,
|
|
"epoch": 0.03594092210928287,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0001595,
|
|
"loss": 6.9708,
|
|
"mean_token_accuracy": 0.1034545697271824,
|
|
"num_tokens": 708652.0,
|
|
"step": 320
|
|
},
|
|
{
|
|
"entropy": 7.3969964504241945,
|
|
"epoch": 0.03650249901724041,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000162,
|
|
"loss": 7.1225,
|
|
"mean_token_accuracy": 0.09705277755856515,
|
|
"num_tokens": 720199.0,
|
|
"step": 325
|
|
},
|
|
{
|
|
"entropy": 7.317982196807861,
|
|
"epoch": 0.037064075925197955,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.00016450000000000001,
|
|
"loss": 7.1133,
|
|
"mean_token_accuracy": 0.09536896646022797,
|
|
"num_tokens": 732964.0,
|
|
"step": 330
|
|
},
|
|
{
|
|
"entropy": 7.344883298873901,
|
|
"epoch": 0.0376256528331555,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00016700000000000002,
|
|
"loss": 6.8741,
|
|
"mean_token_accuracy": 0.10452906191349029,
|
|
"num_tokens": 743528.0,
|
|
"step": 335
|
|
},
|
|
{
|
|
"entropy": 7.326264238357544,
|
|
"epoch": 0.03818722974111304,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00016950000000000003,
|
|
"loss": 6.9363,
|
|
"mean_token_accuracy": 0.10507969111204148,
|
|
"num_tokens": 754365.0,
|
|
"step": 340
|
|
},
|
|
{
|
|
"entropy": 7.219662475585937,
|
|
"epoch": 0.03874880664907059,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.00017199999999999998,
|
|
"loss": 6.8577,
|
|
"mean_token_accuracy": 0.10085783675312995,
|
|
"num_tokens": 766094.0,
|
|
"step": 345
|
|
},
|
|
{
|
|
"entropy": 7.265485715866089,
|
|
"epoch": 0.039310383557028136,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00017449999999999999,
|
|
"loss": 6.9116,
|
|
"mean_token_accuracy": 0.10725476443767548,
|
|
"num_tokens": 777275.0,
|
|
"step": 350
|
|
},
|
|
{
|
|
"entropy": 7.303876209259033,
|
|
"epoch": 0.03987196046498568,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000177,
|
|
"loss": 6.973,
|
|
"mean_token_accuracy": 0.10475650802254677,
|
|
"num_tokens": 789436.0,
|
|
"step": 355
|
|
},
|
|
{
|
|
"entropy": 7.291001510620117,
|
|
"epoch": 0.040433537372943223,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0001795,
|
|
"loss": 6.988,
|
|
"mean_token_accuracy": 0.10399318337440491,
|
|
"num_tokens": 800164.0,
|
|
"step": 360
|
|
},
|
|
{
|
|
"entropy": 7.15556755065918,
|
|
"epoch": 0.04099511428090077,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000182,
|
|
"loss": 6.8667,
|
|
"mean_token_accuracy": 0.10801982134580612,
|
|
"num_tokens": 811797.0,
|
|
"step": 365
|
|
},
|
|
{
|
|
"entropy": 7.239162635803223,
|
|
"epoch": 0.04155669118885831,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0001845,
|
|
"loss": 6.864,
|
|
"mean_token_accuracy": 0.1076484501361847,
|
|
"num_tokens": 824158.0,
|
|
"step": 370
|
|
},
|
|
{
|
|
"entropy": 7.216827726364135,
|
|
"epoch": 0.04211826809681586,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000187,
|
|
"loss": 6.8616,
|
|
"mean_token_accuracy": 0.1121969074010849,
|
|
"num_tokens": 835803.0,
|
|
"step": 375
|
|
},
|
|
{
|
|
"entropy": 7.260309410095215,
|
|
"epoch": 0.042679845004773405,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0001895,
|
|
"loss": 6.9411,
|
|
"mean_token_accuracy": 0.10338237062096596,
|
|
"num_tokens": 848106.0,
|
|
"step": 380
|
|
},
|
|
{
|
|
"entropy": 7.208122730255127,
|
|
"epoch": 0.04324142191273095,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000192,
|
|
"loss": 6.9009,
|
|
"mean_token_accuracy": 0.10842320248484612,
|
|
"num_tokens": 859101.0,
|
|
"step": 385
|
|
},
|
|
{
|
|
"entropy": 7.150190019607544,
|
|
"epoch": 0.04380299882068849,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0001945,
|
|
"loss": 6.7826,
|
|
"mean_token_accuracy": 0.1109951414167881,
|
|
"num_tokens": 870309.0,
|
|
"step": 390
|
|
},
|
|
{
|
|
"entropy": 7.0933675289154055,
|
|
"epoch": 0.044364575728646036,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00019700000000000002,
|
|
"loss": 6.8608,
|
|
"mean_token_accuracy": 0.10988331884145737,
|
|
"num_tokens": 881515.0,
|
|
"step": 395
|
|
},
|
|
{
|
|
"entropy": 7.202591133117676,
|
|
"epoch": 0.044926152636603586,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00019950000000000002,
|
|
"loss": 6.8292,
|
|
"mean_token_accuracy": 0.10998395457863808,
|
|
"num_tokens": 892129.0,
|
|
"step": 400
|
|
},
|
|
{
|
|
"entropy": 7.136573028564453,
|
|
"epoch": 0.04548772954456113,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000202,
|
|
"loss": 6.8465,
|
|
"mean_token_accuracy": 0.10337187349796295,
|
|
"num_tokens": 903186.0,
|
|
"step": 405
|
|
},
|
|
{
|
|
"entropy": 7.1220067024230955,
|
|
"epoch": 0.046049306452518673,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.00020449999999999998,
|
|
"loss": 6.8047,
|
|
"mean_token_accuracy": 0.11569347232580185,
|
|
"num_tokens": 913471.0,
|
|
"step": 410
|
|
},
|
|
{
|
|
"entropy": 7.141632843017578,
|
|
"epoch": 0.04661088336047622,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000207,
|
|
"loss": 6.8051,
|
|
"mean_token_accuracy": 0.10749553069472313,
|
|
"num_tokens": 924283.0,
|
|
"step": 415
|
|
},
|
|
{
|
|
"entropy": 7.063813877105713,
|
|
"epoch": 0.04717246026843376,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0002095,
|
|
"loss": 6.8408,
|
|
"mean_token_accuracy": 0.11442757770419121,
|
|
"num_tokens": 934975.0,
|
|
"step": 420
|
|
},
|
|
{
|
|
"entropy": 7.101827573776245,
|
|
"epoch": 0.047734037176391304,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.000212,
|
|
"loss": 6.705,
|
|
"mean_token_accuracy": 0.11826195791363717,
|
|
"num_tokens": 945587.0,
|
|
"step": 425
|
|
},
|
|
{
|
|
"entropy": 7.012417364120483,
|
|
"epoch": 0.048295614084348855,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0002145,
|
|
"loss": 6.7701,
|
|
"mean_token_accuracy": 0.11151043251156807,
|
|
"num_tokens": 955935.0,
|
|
"step": 430
|
|
},
|
|
{
|
|
"entropy": 7.108279705047607,
|
|
"epoch": 0.0488571909923064,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00021700000000000002,
|
|
"loss": 6.7326,
|
|
"mean_token_accuracy": 0.11344726905226707,
|
|
"num_tokens": 967960.0,
|
|
"step": 435
|
|
},
|
|
{
|
|
"entropy": 7.063254356384277,
|
|
"epoch": 0.04941876790026394,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0002195,
|
|
"loss": 6.7808,
|
|
"mean_token_accuracy": 0.11375493034720421,
|
|
"num_tokens": 979680.0,
|
|
"step": 440
|
|
},
|
|
{
|
|
"entropy": 7.0870774269104,
|
|
"epoch": 0.049980344808221486,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.000222,
|
|
"loss": 6.8463,
|
|
"mean_token_accuracy": 0.11385233402252197,
|
|
"num_tokens": 990600.0,
|
|
"step": 445
|
|
},
|
|
{
|
|
"entropy": 7.130812168121338,
|
|
"epoch": 0.05054192171617903,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0002245,
|
|
"loss": 6.8797,
|
|
"mean_token_accuracy": 0.11623142063617706,
|
|
"num_tokens": 1002331.0,
|
|
"step": 450
|
|
},
|
|
{
|
|
"entropy": 6.960196018218994,
|
|
"epoch": 0.05110349862413657,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.00022700000000000002,
|
|
"loss": 6.6839,
|
|
"mean_token_accuracy": 0.11727181151509285,
|
|
"num_tokens": 1013473.0,
|
|
"step": 455
|
|
},
|
|
{
|
|
"entropy": 7.0530540466308596,
|
|
"epoch": 0.051665075532094124,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00022950000000000002,
|
|
"loss": 6.7589,
|
|
"mean_token_accuracy": 0.11695582792162895,
|
|
"num_tokens": 1024434.0,
|
|
"step": 460
|
|
},
|
|
{
|
|
"entropy": 7.068104553222656,
|
|
"epoch": 0.05222665244005167,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00023200000000000003,
|
|
"loss": 6.7928,
|
|
"mean_token_accuracy": 0.10744224488735199,
|
|
"num_tokens": 1035452.0,
|
|
"step": 465
|
|
},
|
|
{
|
|
"entropy": 7.012246704101562,
|
|
"epoch": 0.05278822934800921,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00023449999999999998,
|
|
"loss": 6.6691,
|
|
"mean_token_accuracy": 0.11236618980765342,
|
|
"num_tokens": 1046213.0,
|
|
"step": 470
|
|
},
|
|
{
|
|
"entropy": 6.907792472839356,
|
|
"epoch": 0.053349806255966754,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000237,
|
|
"loss": 6.69,
|
|
"mean_token_accuracy": 0.11790019795298576,
|
|
"num_tokens": 1057469.0,
|
|
"step": 475
|
|
},
|
|
{
|
|
"entropy": 7.105744743347168,
|
|
"epoch": 0.0539113831639243,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0002395,
|
|
"loss": 6.8301,
|
|
"mean_token_accuracy": 0.11361000612378121,
|
|
"num_tokens": 1069543.0,
|
|
"step": 480
|
|
},
|
|
{
|
|
"entropy": 6.806726551055908,
|
|
"epoch": 0.05447296007188184,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.000242,
|
|
"loss": 6.7071,
|
|
"mean_token_accuracy": 0.11520676463842391,
|
|
"num_tokens": 1080476.0,
|
|
"step": 485
|
|
},
|
|
{
|
|
"entropy": 7.111533737182617,
|
|
"epoch": 0.05503453697983939,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0002445,
|
|
"loss": 6.8287,
|
|
"mean_token_accuracy": 0.11254625618457795,
|
|
"num_tokens": 1091700.0,
|
|
"step": 490
|
|
},
|
|
{
|
|
"entropy": 6.96989221572876,
|
|
"epoch": 0.055596113887796936,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000247,
|
|
"loss": 6.7132,
|
|
"mean_token_accuracy": 0.11217723339796067,
|
|
"num_tokens": 1103056.0,
|
|
"step": 495
|
|
},
|
|
{
|
|
"entropy": 6.942185974121093,
|
|
"epoch": 0.05615769079575448,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0002495,
|
|
"loss": 6.7678,
|
|
"mean_token_accuracy": 0.11992822587490082,
|
|
"num_tokens": 1114836.0,
|
|
"step": 500
|
|
},
|
|
{
|
|
"entropy": 6.93104133605957,
|
|
"epoch": 0.05671926770371202,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.000252,
|
|
"loss": 6.6666,
|
|
"mean_token_accuracy": 0.11608512848615646,
|
|
"num_tokens": 1125993.0,
|
|
"step": 505
|
|
},
|
|
{
|
|
"entropy": 7.019130229949951,
|
|
"epoch": 0.05728084461166957,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0002545,
|
|
"loss": 6.7356,
|
|
"mean_token_accuracy": 0.12077120542526246,
|
|
"num_tokens": 1136719.0,
|
|
"step": 510
|
|
},
|
|
{
|
|
"entropy": 6.877520227432251,
|
|
"epoch": 0.05784242151962711,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.000257,
|
|
"loss": 6.605,
|
|
"mean_token_accuracy": 0.12040217965841293,
|
|
"num_tokens": 1146947.0,
|
|
"step": 515
|
|
},
|
|
{
|
|
"entropy": 6.971859741210937,
|
|
"epoch": 0.05840399842758466,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0002595,
|
|
"loss": 6.736,
|
|
"mean_token_accuracy": 0.11773492619395257,
|
|
"num_tokens": 1157974.0,
|
|
"step": 520
|
|
},
|
|
{
|
|
"entropy": 6.8482812404632565,
|
|
"epoch": 0.058965575335542204,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000262,
|
|
"loss": 6.6668,
|
|
"mean_token_accuracy": 0.11813957914710045,
|
|
"num_tokens": 1168573.0,
|
|
"step": 525
|
|
},
|
|
{
|
|
"entropy": 6.854047727584839,
|
|
"epoch": 0.05952715224349975,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00026450000000000003,
|
|
"loss": 6.5609,
|
|
"mean_token_accuracy": 0.11992745697498322,
|
|
"num_tokens": 1178446.0,
|
|
"step": 530
|
|
},
|
|
{
|
|
"entropy": 6.924405860900879,
|
|
"epoch": 0.06008872915145729,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00026700000000000004,
|
|
"loss": 6.5966,
|
|
"mean_token_accuracy": 0.12243785858154296,
|
|
"num_tokens": 1190558.0,
|
|
"step": 535
|
|
},
|
|
{
|
|
"entropy": 6.876425790786743,
|
|
"epoch": 0.060650306059414835,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.00026950000000000005,
|
|
"loss": 6.7667,
|
|
"mean_token_accuracy": 0.11598537936806678,
|
|
"num_tokens": 1201929.0,
|
|
"step": 540
|
|
},
|
|
{
|
|
"entropy": 6.789496803283692,
|
|
"epoch": 0.06121188296737238,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00027200000000000005,
|
|
"loss": 6.6055,
|
|
"mean_token_accuracy": 0.12160162925720215,
|
|
"num_tokens": 1213155.0,
|
|
"step": 545
|
|
},
|
|
{
|
|
"entropy": 6.950420570373535,
|
|
"epoch": 0.06177345987532993,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0002745,
|
|
"loss": 6.6558,
|
|
"mean_token_accuracy": 0.12115484923124313,
|
|
"num_tokens": 1223961.0,
|
|
"step": 550
|
|
},
|
|
{
|
|
"entropy": 6.740339994430542,
|
|
"epoch": 0.06233503678328747,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000277,
|
|
"loss": 6.5575,
|
|
"mean_token_accuracy": 0.12820586189627647,
|
|
"num_tokens": 1233888.0,
|
|
"step": 555
|
|
},
|
|
{
|
|
"entropy": 6.817170190811157,
|
|
"epoch": 0.06289661369124501,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0002795,
|
|
"loss": 6.6744,
|
|
"mean_token_accuracy": 0.11722169443964958,
|
|
"num_tokens": 1244405.0,
|
|
"step": 560
|
|
},
|
|
{
|
|
"entropy": 6.862272119522094,
|
|
"epoch": 0.06345819059920256,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00028199999999999997,
|
|
"loss": 6.6067,
|
|
"mean_token_accuracy": 0.12411838248372078,
|
|
"num_tokens": 1257099.0,
|
|
"step": 565
|
|
},
|
|
{
|
|
"entropy": 6.882076740264893,
|
|
"epoch": 0.06401976750716011,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0002845,
|
|
"loss": 6.7212,
|
|
"mean_token_accuracy": 0.12341399341821671,
|
|
"num_tokens": 1267965.0,
|
|
"step": 570
|
|
},
|
|
{
|
|
"entropy": 6.852020120620727,
|
|
"epoch": 0.06458134441511765,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.000287,
|
|
"loss": 6.6231,
|
|
"mean_token_accuracy": 0.12452883943915367,
|
|
"num_tokens": 1280075.0,
|
|
"step": 575
|
|
},
|
|
{
|
|
"entropy": 6.82808027267456,
|
|
"epoch": 0.0651429213230752,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0002895,
|
|
"loss": 6.6336,
|
|
"mean_token_accuracy": 0.12447365745902061,
|
|
"num_tokens": 1290574.0,
|
|
"step": 580
|
|
},
|
|
{
|
|
"entropy": 6.803577661514282,
|
|
"epoch": 0.06570449823103273,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000292,
|
|
"loss": 6.5981,
|
|
"mean_token_accuracy": 0.12608856037259103,
|
|
"num_tokens": 1302680.0,
|
|
"step": 585
|
|
},
|
|
{
|
|
"entropy": 6.73208703994751,
|
|
"epoch": 0.06626607513899029,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0002945,
|
|
"loss": 6.591,
|
|
"mean_token_accuracy": 0.12613771557807923,
|
|
"num_tokens": 1314577.0,
|
|
"step": 590
|
|
},
|
|
{
|
|
"entropy": 6.796487188339233,
|
|
"epoch": 0.06682765204694784,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000297,
|
|
"loss": 6.7192,
|
|
"mean_token_accuracy": 0.12332894131541253,
|
|
"num_tokens": 1326560.0,
|
|
"step": 595
|
|
},
|
|
{
|
|
"entropy": 6.990584993362427,
|
|
"epoch": 0.06738922895490537,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0002995,
|
|
"loss": 6.7842,
|
|
"mean_token_accuracy": 0.11380501464009285,
|
|
"num_tokens": 1339105.0,
|
|
"step": 600
|
|
},
|
|
{
|
|
"entropy": 6.57991738319397,
|
|
"epoch": 0.06795080586286292,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000302,
|
|
"loss": 6.4443,
|
|
"mean_token_accuracy": 0.13007400184869766,
|
|
"num_tokens": 1349914.0,
|
|
"step": 605
|
|
},
|
|
{
|
|
"entropy": 6.823658180236817,
|
|
"epoch": 0.06851238277082046,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0003045,
|
|
"loss": 6.6728,
|
|
"mean_token_accuracy": 0.12215135470032693,
|
|
"num_tokens": 1361700.0,
|
|
"step": 610
|
|
},
|
|
{
|
|
"entropy": 6.7814453125,
|
|
"epoch": 0.06907395967877801,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000307,
|
|
"loss": 6.6743,
|
|
"mean_token_accuracy": 0.12424325123429299,
|
|
"num_tokens": 1373103.0,
|
|
"step": 615
|
|
},
|
|
{
|
|
"entropy": 6.68872766494751,
|
|
"epoch": 0.06963553658673555,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0003095,
|
|
"loss": 6.4991,
|
|
"mean_token_accuracy": 0.1282663404941559,
|
|
"num_tokens": 1383742.0,
|
|
"step": 620
|
|
},
|
|
{
|
|
"entropy": 6.695285606384277,
|
|
"epoch": 0.0701971134946931,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.000312,
|
|
"loss": 6.6344,
|
|
"mean_token_accuracy": 0.1173564150929451,
|
|
"num_tokens": 1396656.0,
|
|
"step": 625
|
|
},
|
|
{
|
|
"entropy": 6.7927330493927,
|
|
"epoch": 0.07075869040265065,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0003145,
|
|
"loss": 6.5057,
|
|
"mean_token_accuracy": 0.13664172142744063,
|
|
"num_tokens": 1406709.0,
|
|
"step": 630
|
|
},
|
|
{
|
|
"entropy": 6.760857725143433,
|
|
"epoch": 0.07132026731060818,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000317,
|
|
"loss": 6.5346,
|
|
"mean_token_accuracy": 0.13074129149317743,
|
|
"num_tokens": 1417793.0,
|
|
"step": 635
|
|
},
|
|
{
|
|
"entropy": 6.764607715606689,
|
|
"epoch": 0.07188184421856574,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0003195,
|
|
"loss": 6.6279,
|
|
"mean_token_accuracy": 0.12794213369488716,
|
|
"num_tokens": 1429093.0,
|
|
"step": 640
|
|
},
|
|
{
|
|
"entropy": 6.65194787979126,
|
|
"epoch": 0.07244342112652327,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000322,
|
|
"loss": 6.5454,
|
|
"mean_token_accuracy": 0.13121496513485909,
|
|
"num_tokens": 1440907.0,
|
|
"step": 645
|
|
},
|
|
{
|
|
"entropy": 6.690778017044067,
|
|
"epoch": 0.07300499803448082,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00032450000000000003,
|
|
"loss": 6.6135,
|
|
"mean_token_accuracy": 0.1266121596097946,
|
|
"num_tokens": 1452089.0,
|
|
"step": 650
|
|
},
|
|
{
|
|
"entropy": 6.808844184875488,
|
|
"epoch": 0.07356657494243837,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00032700000000000003,
|
|
"loss": 6.6337,
|
|
"mean_token_accuracy": 0.1225229762494564,
|
|
"num_tokens": 1464378.0,
|
|
"step": 655
|
|
},
|
|
{
|
|
"entropy": 6.704527997970581,
|
|
"epoch": 0.07412815185039591,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00032950000000000004,
|
|
"loss": 6.5677,
|
|
"mean_token_accuracy": 0.12628930658102036,
|
|
"num_tokens": 1476678.0,
|
|
"step": 660
|
|
},
|
|
{
|
|
"entropy": 6.637593460083008,
|
|
"epoch": 0.07468972875835346,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00033200000000000005,
|
|
"loss": 6.4052,
|
|
"mean_token_accuracy": 0.13140960410237312,
|
|
"num_tokens": 1486808.0,
|
|
"step": 665
|
|
},
|
|
{
|
|
"entropy": 6.757417011260986,
|
|
"epoch": 0.075251305666311,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00033450000000000005,
|
|
"loss": 6.6957,
|
|
"mean_token_accuracy": 0.12566189095377922,
|
|
"num_tokens": 1499281.0,
|
|
"step": 670
|
|
},
|
|
{
|
|
"entropy": 6.700873708724975,
|
|
"epoch": 0.07581288257426855,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000337,
|
|
"loss": 6.5875,
|
|
"mean_token_accuracy": 0.12513456344604493,
|
|
"num_tokens": 1510202.0,
|
|
"step": 675
|
|
},
|
|
{
|
|
"entropy": 6.68131456375122,
|
|
"epoch": 0.07637445948222608,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0003395,
|
|
"loss": 6.4684,
|
|
"mean_token_accuracy": 0.13036980405449866,
|
|
"num_tokens": 1521492.0,
|
|
"step": 680
|
|
},
|
|
{
|
|
"entropy": 6.599414730072022,
|
|
"epoch": 0.07693603639018363,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000342,
|
|
"loss": 6.4806,
|
|
"mean_token_accuracy": 0.13861154913902282,
|
|
"num_tokens": 1532856.0,
|
|
"step": 685
|
|
},
|
|
{
|
|
"entropy": 6.614651203155518,
|
|
"epoch": 0.07749761329814119,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00034449999999999997,
|
|
"loss": 6.4823,
|
|
"mean_token_accuracy": 0.1309678554534912,
|
|
"num_tokens": 1543408.0,
|
|
"step": 690
|
|
},
|
|
{
|
|
"entropy": 6.596418333053589,
|
|
"epoch": 0.07805919020609872,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000347,
|
|
"loss": 6.5167,
|
|
"mean_token_accuracy": 0.12967425882816314,
|
|
"num_tokens": 1555474.0,
|
|
"step": 695
|
|
},
|
|
{
|
|
"entropy": 6.689687299728393,
|
|
"epoch": 0.07862076711405627,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0003495,
|
|
"loss": 6.6084,
|
|
"mean_token_accuracy": 0.1304874062538147,
|
|
"num_tokens": 1567484.0,
|
|
"step": 700
|
|
},
|
|
{
|
|
"entropy": 6.589553880691528,
|
|
"epoch": 0.07918234402201381,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000352,
|
|
"loss": 6.4484,
|
|
"mean_token_accuracy": 0.13632451072335244,
|
|
"num_tokens": 1578204.0,
|
|
"step": 705
|
|
},
|
|
{
|
|
"entropy": 6.66821985244751,
|
|
"epoch": 0.07974392092997136,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0003545,
|
|
"loss": 6.4521,
|
|
"mean_token_accuracy": 0.13238313496112825,
|
|
"num_tokens": 1589012.0,
|
|
"step": 710
|
|
},
|
|
{
|
|
"entropy": 6.522986221313476,
|
|
"epoch": 0.08030549783792891,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000357,
|
|
"loss": 6.4476,
|
|
"mean_token_accuracy": 0.1307396411895752,
|
|
"num_tokens": 1601099.0,
|
|
"step": 715
|
|
},
|
|
{
|
|
"entropy": 6.685805368423462,
|
|
"epoch": 0.08086707474588645,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0003595,
|
|
"loss": 6.6162,
|
|
"mean_token_accuracy": 0.12508113980293273,
|
|
"num_tokens": 1612814.0,
|
|
"step": 720
|
|
},
|
|
{
|
|
"entropy": 6.628611469268799,
|
|
"epoch": 0.081428651653844,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000362,
|
|
"loss": 6.4967,
|
|
"mean_token_accuracy": 0.1275397375226021,
|
|
"num_tokens": 1624953.0,
|
|
"step": 725
|
|
},
|
|
{
|
|
"entropy": 6.6380833148956295,
|
|
"epoch": 0.08199022856180153,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0003645,
|
|
"loss": 6.5367,
|
|
"mean_token_accuracy": 0.13109428957104682,
|
|
"num_tokens": 1635673.0,
|
|
"step": 730
|
|
},
|
|
{
|
|
"entropy": 6.542795658111572,
|
|
"epoch": 0.08255180546975908,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000367,
|
|
"loss": 6.4406,
|
|
"mean_token_accuracy": 0.1324732281267643,
|
|
"num_tokens": 1647282.0,
|
|
"step": 735
|
|
},
|
|
{
|
|
"entropy": 6.581196880340576,
|
|
"epoch": 0.08311338237771662,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0003695,
|
|
"loss": 6.4511,
|
|
"mean_token_accuracy": 0.1369396723806858,
|
|
"num_tokens": 1658426.0,
|
|
"step": 740
|
|
},
|
|
{
|
|
"entropy": 6.588415479660034,
|
|
"epoch": 0.08367495928567417,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000372,
|
|
"loss": 6.4821,
|
|
"mean_token_accuracy": 0.13475994616746903,
|
|
"num_tokens": 1669958.0,
|
|
"step": 745
|
|
},
|
|
{
|
|
"entropy": 6.565198183059692,
|
|
"epoch": 0.08423653619363172,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0003745,
|
|
"loss": 6.5368,
|
|
"mean_token_accuracy": 0.13080626279115676,
|
|
"num_tokens": 1682409.0,
|
|
"step": 750
|
|
},
|
|
{
|
|
"entropy": 6.551465749740601,
|
|
"epoch": 0.08479811310158926,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000377,
|
|
"loss": 6.4584,
|
|
"mean_token_accuracy": 0.13542011380195618,
|
|
"num_tokens": 1692409.0,
|
|
"step": 755
|
|
},
|
|
{
|
|
"entropy": 6.6324629306793215,
|
|
"epoch": 0.08535969000954681,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0003795,
|
|
"loss": 6.5569,
|
|
"mean_token_accuracy": 0.12928430885076522,
|
|
"num_tokens": 1705018.0,
|
|
"step": 760
|
|
},
|
|
{
|
|
"entropy": 6.529924488067627,
|
|
"epoch": 0.08592126691750435,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000382,
|
|
"loss": 6.4759,
|
|
"mean_token_accuracy": 0.12947854325175284,
|
|
"num_tokens": 1715625.0,
|
|
"step": 765
|
|
},
|
|
{
|
|
"entropy": 6.624479961395264,
|
|
"epoch": 0.0864828438254619,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0003845,
|
|
"loss": 6.5534,
|
|
"mean_token_accuracy": 0.12158236727118492,
|
|
"num_tokens": 1727045.0,
|
|
"step": 770
|
|
},
|
|
{
|
|
"entropy": 6.64137897491455,
|
|
"epoch": 0.08704442073341945,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00038700000000000003,
|
|
"loss": 6.6148,
|
|
"mean_token_accuracy": 0.13262347802519797,
|
|
"num_tokens": 1737374.0,
|
|
"step": 775
|
|
},
|
|
{
|
|
"entropy": 6.616215944290161,
|
|
"epoch": 0.08760599764137698,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00038950000000000003,
|
|
"loss": 6.6163,
|
|
"mean_token_accuracy": 0.13496674597263336,
|
|
"num_tokens": 1747788.0,
|
|
"step": 780
|
|
},
|
|
{
|
|
"entropy": 6.421903228759765,
|
|
"epoch": 0.08816757454933453,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00039200000000000004,
|
|
"loss": 6.3084,
|
|
"mean_token_accuracy": 0.14094914942979814,
|
|
"num_tokens": 1757769.0,
|
|
"step": 785
|
|
},
|
|
{
|
|
"entropy": 6.548354005813598,
|
|
"epoch": 0.08872915145729207,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00039450000000000005,
|
|
"loss": 6.4146,
|
|
"mean_token_accuracy": 0.13216090872883796,
|
|
"num_tokens": 1769246.0,
|
|
"step": 790
|
|
},
|
|
{
|
|
"entropy": 6.5623010158538815,
|
|
"epoch": 0.08929072836524962,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00039700000000000005,
|
|
"loss": 6.554,
|
|
"mean_token_accuracy": 0.12859445959329605,
|
|
"num_tokens": 1781306.0,
|
|
"step": 795
|
|
},
|
|
{
|
|
"entropy": 6.527663707733154,
|
|
"epoch": 0.08985230527320717,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0003995,
|
|
"loss": 6.4493,
|
|
"mean_token_accuracy": 0.1310065895318985,
|
|
"num_tokens": 1792888.0,
|
|
"step": 800
|
|
},
|
|
{
|
|
"entropy": 6.516381120681762,
|
|
"epoch": 0.09041388218116471,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000402,
|
|
"loss": 6.4648,
|
|
"mean_token_accuracy": 0.13185214772820472,
|
|
"num_tokens": 1802938.0,
|
|
"step": 805
|
|
},
|
|
{
|
|
"entropy": 6.583385372161866,
|
|
"epoch": 0.09097545908912226,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004045,
|
|
"loss": 6.4746,
|
|
"mean_token_accuracy": 0.13560603633522988,
|
|
"num_tokens": 1814738.0,
|
|
"step": 810
|
|
},
|
|
{
|
|
"entropy": 6.595263147354126,
|
|
"epoch": 0.0915370359970798,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00040699999999999997,
|
|
"loss": 6.5531,
|
|
"mean_token_accuracy": 0.1318923979997635,
|
|
"num_tokens": 1825100.0,
|
|
"step": 815
|
|
},
|
|
{
|
|
"entropy": 6.3817685604095455,
|
|
"epoch": 0.09209861290503735,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004095,
|
|
"loss": 6.3926,
|
|
"mean_token_accuracy": 0.13854454085230827,
|
|
"num_tokens": 1835879.0,
|
|
"step": 820
|
|
},
|
|
{
|
|
"entropy": 6.663535404205322,
|
|
"epoch": 0.09266018981299488,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000412,
|
|
"loss": 6.5323,
|
|
"mean_token_accuracy": 0.12780267298221587,
|
|
"num_tokens": 1848352.0,
|
|
"step": 825
|
|
},
|
|
{
|
|
"entropy": 6.477813053131103,
|
|
"epoch": 0.09322176672095243,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004145,
|
|
"loss": 6.4859,
|
|
"mean_token_accuracy": 0.13047706484794616,
|
|
"num_tokens": 1859687.0,
|
|
"step": 830
|
|
},
|
|
{
|
|
"entropy": 6.532577610015869,
|
|
"epoch": 0.09378334362890998,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000417,
|
|
"loss": 6.4749,
|
|
"mean_token_accuracy": 0.13406161218881607,
|
|
"num_tokens": 1871438.0,
|
|
"step": 835
|
|
},
|
|
{
|
|
"entropy": 6.455235624313355,
|
|
"epoch": 0.09434492053686752,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004195,
|
|
"loss": 6.3513,
|
|
"mean_token_accuracy": 0.1425087571144104,
|
|
"num_tokens": 1881519.0,
|
|
"step": 840
|
|
},
|
|
{
|
|
"entropy": 6.609141397476196,
|
|
"epoch": 0.09490649744482507,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000422,
|
|
"loss": 6.5414,
|
|
"mean_token_accuracy": 0.1294293776154518,
|
|
"num_tokens": 1892428.0,
|
|
"step": 845
|
|
},
|
|
{
|
|
"entropy": 6.550697469711304,
|
|
"epoch": 0.09546807435278261,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004245,
|
|
"loss": 6.4251,
|
|
"mean_token_accuracy": 0.13496895208954812,
|
|
"num_tokens": 1903760.0,
|
|
"step": 850
|
|
},
|
|
{
|
|
"entropy": 6.508064842224121,
|
|
"epoch": 0.09602965126074016,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.000427,
|
|
"loss": 6.4953,
|
|
"mean_token_accuracy": 0.12665094286203385,
|
|
"num_tokens": 1915430.0,
|
|
"step": 855
|
|
},
|
|
{
|
|
"entropy": 6.478051090240479,
|
|
"epoch": 0.09659122816869771,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004295,
|
|
"loss": 6.4524,
|
|
"mean_token_accuracy": 0.12965421453118325,
|
|
"num_tokens": 1925709.0,
|
|
"step": 860
|
|
},
|
|
{
|
|
"entropy": 6.517416477203369,
|
|
"epoch": 0.09715280507665525,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000432,
|
|
"loss": 6.4937,
|
|
"mean_token_accuracy": 0.13162111937999726,
|
|
"num_tokens": 1938148.0,
|
|
"step": 865
|
|
},
|
|
{
|
|
"entropy": 6.323285913467407,
|
|
"epoch": 0.0977143819846128,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004345,
|
|
"loss": 6.3699,
|
|
"mean_token_accuracy": 0.13734893202781678,
|
|
"num_tokens": 1949028.0,
|
|
"step": 870
|
|
},
|
|
{
|
|
"entropy": 6.510279512405395,
|
|
"epoch": 0.09827595889257033,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000437,
|
|
"loss": 6.4184,
|
|
"mean_token_accuracy": 0.13602244704961777,
|
|
"num_tokens": 1960353.0,
|
|
"step": 875
|
|
},
|
|
{
|
|
"entropy": 6.504331731796265,
|
|
"epoch": 0.09883753580052788,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004395,
|
|
"loss": 6.5146,
|
|
"mean_token_accuracy": 0.13366802632808686,
|
|
"num_tokens": 1972335.0,
|
|
"step": 880
|
|
},
|
|
{
|
|
"entropy": 6.485915279388427,
|
|
"epoch": 0.09939911270848542,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000442,
|
|
"loss": 6.3532,
|
|
"mean_token_accuracy": 0.1334136687219143,
|
|
"num_tokens": 1982851.0,
|
|
"step": 885
|
|
},
|
|
{
|
|
"entropy": 6.433965969085693,
|
|
"epoch": 0.09996068961644297,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004445,
|
|
"loss": 6.3522,
|
|
"mean_token_accuracy": 0.1376023381948471,
|
|
"num_tokens": 1993931.0,
|
|
"step": 890
|
|
},
|
|
{
|
|
"entropy": 6.434508419036865,
|
|
"epoch": 0.10052226652440052,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.000447,
|
|
"loss": 6.4802,
|
|
"mean_token_accuracy": 0.13329798057675363,
|
|
"num_tokens": 2004838.0,
|
|
"step": 895
|
|
},
|
|
{
|
|
"entropy": 6.3818906307220455,
|
|
"epoch": 0.10108384343235806,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00044950000000000003,
|
|
"loss": 6.2804,
|
|
"mean_token_accuracy": 0.1390576109290123,
|
|
"num_tokens": 2015620.0,
|
|
"step": 900
|
|
},
|
|
{
|
|
"entropy": 6.456867647171021,
|
|
"epoch": 0.10164542034031561,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00045200000000000004,
|
|
"loss": 6.4092,
|
|
"mean_token_accuracy": 0.1347552627325058,
|
|
"num_tokens": 2027489.0,
|
|
"step": 905
|
|
},
|
|
{
|
|
"entropy": 6.344513940811157,
|
|
"epoch": 0.10220699724827315,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00045450000000000004,
|
|
"loss": 6.2881,
|
|
"mean_token_accuracy": 0.14329898431897165,
|
|
"num_tokens": 2038475.0,
|
|
"step": 910
|
|
},
|
|
{
|
|
"entropy": 6.311835908889771,
|
|
"epoch": 0.1027685741562307,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00045700000000000005,
|
|
"loss": 6.2934,
|
|
"mean_token_accuracy": 0.1361900806427002,
|
|
"num_tokens": 2048938.0,
|
|
"step": 915
|
|
},
|
|
{
|
|
"entropy": 6.3546638011932375,
|
|
"epoch": 0.10333015106418825,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00045950000000000006,
|
|
"loss": 6.3841,
|
|
"mean_token_accuracy": 0.1331220120191574,
|
|
"num_tokens": 2060372.0,
|
|
"step": 920
|
|
},
|
|
{
|
|
"entropy": 6.428075313568115,
|
|
"epoch": 0.10389172797214578,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000462,
|
|
"loss": 6.3677,
|
|
"mean_token_accuracy": 0.13431201800704,
|
|
"num_tokens": 2071558.0,
|
|
"step": 925
|
|
},
|
|
{
|
|
"entropy": 6.419263553619385,
|
|
"epoch": 0.10445330488010333,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004645,
|
|
"loss": 6.4142,
|
|
"mean_token_accuracy": 0.13359070122241973,
|
|
"num_tokens": 2082350.0,
|
|
"step": 930
|
|
},
|
|
{
|
|
"entropy": 6.386594343185425,
|
|
"epoch": 0.10501488178806087,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000467,
|
|
"loss": 6.4635,
|
|
"mean_token_accuracy": 0.13304929211735725,
|
|
"num_tokens": 2093448.0,
|
|
"step": 935
|
|
},
|
|
{
|
|
"entropy": 6.608812284469605,
|
|
"epoch": 0.10557645869601842,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004695,
|
|
"loss": 6.5099,
|
|
"mean_token_accuracy": 0.13017828315496444,
|
|
"num_tokens": 2104171.0,
|
|
"step": 940
|
|
},
|
|
{
|
|
"entropy": 6.355282163619995,
|
|
"epoch": 0.10613803560397596,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000472,
|
|
"loss": 6.3814,
|
|
"mean_token_accuracy": 0.13445304855704307,
|
|
"num_tokens": 2114496.0,
|
|
"step": 945
|
|
},
|
|
{
|
|
"entropy": 6.452987957000732,
|
|
"epoch": 0.10669961251193351,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004745,
|
|
"loss": 6.379,
|
|
"mean_token_accuracy": 0.13855226784944535,
|
|
"num_tokens": 2125930.0,
|
|
"step": 950
|
|
},
|
|
{
|
|
"entropy": 6.360589504241943,
|
|
"epoch": 0.10726118941989106,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000477,
|
|
"loss": 6.3377,
|
|
"mean_token_accuracy": 0.13913045451045036,
|
|
"num_tokens": 2136452.0,
|
|
"step": 955
|
|
},
|
|
{
|
|
"entropy": 6.399038314819336,
|
|
"epoch": 0.1078227663278486,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004795,
|
|
"loss": 6.4486,
|
|
"mean_token_accuracy": 0.13280693516135217,
|
|
"num_tokens": 2148233.0,
|
|
"step": 960
|
|
},
|
|
{
|
|
"entropy": 6.3246174335479735,
|
|
"epoch": 0.10838434323580615,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000482,
|
|
"loss": 6.2221,
|
|
"mean_token_accuracy": 0.14445948973298073,
|
|
"num_tokens": 2159475.0,
|
|
"step": 965
|
|
},
|
|
{
|
|
"entropy": 6.350338172912598,
|
|
"epoch": 0.10894592014376368,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004845,
|
|
"loss": 6.3454,
|
|
"mean_token_accuracy": 0.13676348254084586,
|
|
"num_tokens": 2170042.0,
|
|
"step": 970
|
|
},
|
|
{
|
|
"entropy": 6.358055448532104,
|
|
"epoch": 0.10950749705172123,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000487,
|
|
"loss": 6.3533,
|
|
"mean_token_accuracy": 0.13602220565080642,
|
|
"num_tokens": 2182234.0,
|
|
"step": 975
|
|
},
|
|
{
|
|
"entropy": 6.287888669967652,
|
|
"epoch": 0.11006907395967878,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004895,
|
|
"loss": 6.3348,
|
|
"mean_token_accuracy": 0.13971530720591546,
|
|
"num_tokens": 2192477.0,
|
|
"step": 980
|
|
},
|
|
{
|
|
"entropy": 6.348295879364014,
|
|
"epoch": 0.11063065086763632,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000492,
|
|
"loss": 6.3239,
|
|
"mean_token_accuracy": 0.1356002353131771,
|
|
"num_tokens": 2203082.0,
|
|
"step": 985
|
|
},
|
|
{
|
|
"entropy": 6.3176719665527346,
|
|
"epoch": 0.11119222777559387,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004945,
|
|
"loss": 6.29,
|
|
"mean_token_accuracy": 0.14067138880491256,
|
|
"num_tokens": 2213684.0,
|
|
"step": 990
|
|
},
|
|
{
|
|
"entropy": 6.312493705749512,
|
|
"epoch": 0.11175380468355141,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000497,
|
|
"loss": 6.3034,
|
|
"mean_token_accuracy": 0.1373144119977951,
|
|
"num_tokens": 2225524.0,
|
|
"step": 995
|
|
},
|
|
{
|
|
"entropy": 6.38683066368103,
|
|
"epoch": 0.11231538159150896,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004995,
|
|
"loss": 6.2591,
|
|
"mean_token_accuracy": 0.14032192155718803,
|
|
"num_tokens": 2236004.0,
|
|
"step": 1000
|
|
},
|
|
{
|
|
"entropy": 6.363068675994873,
|
|
"epoch": 0.1128769584994665,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000499999997707492,
|
|
"loss": 6.4203,
|
|
"mean_token_accuracy": 0.12891897335648536,
|
|
"num_tokens": 2247730.0,
|
|
"step": 1005
|
|
},
|
|
{
|
|
"entropy": 6.390230703353882,
|
|
"epoch": 0.11343853540742405,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004999999883941787,
|
|
"loss": 6.3767,
|
|
"mean_token_accuracy": 0.13985844999551772,
|
|
"num_tokens": 2260132.0,
|
|
"step": 1010
|
|
},
|
|
{
|
|
"entropy": 6.254923486709595,
|
|
"epoch": 0.1140001123153816,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999999719167785,
|
|
"loss": 6.3404,
|
|
"mean_token_accuracy": 0.1435151532292366,
|
|
"num_tokens": 2270060.0,
|
|
"step": 1015
|
|
},
|
|
{
|
|
"entropy": 6.382527685165405,
|
|
"epoch": 0.11456168922333913,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999999482752917,
|
|
"loss": 6.3631,
|
|
"mean_token_accuracy": 0.13998973742127419,
|
|
"num_tokens": 2281568.0,
|
|
"step": 1020
|
|
},
|
|
{
|
|
"entropy": 6.354326391220093,
|
|
"epoch": 0.11512326613129668,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004999999174697195,
|
|
"loss": 6.3815,
|
|
"mean_token_accuracy": 0.13222115933895112,
|
|
"num_tokens": 2293325.0,
|
|
"step": 1025
|
|
},
|
|
{
|
|
"entropy": 6.438601779937744,
|
|
"epoch": 0.11568484303925422,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999998795000627,
|
|
"loss": 6.3794,
|
|
"mean_token_accuracy": 0.1392307199537754,
|
|
"num_tokens": 2304780.0,
|
|
"step": 1030
|
|
},
|
|
{
|
|
"entropy": 6.276957988739014,
|
|
"epoch": 0.11624641994721177,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004999998343663223,
|
|
"loss": 6.3166,
|
|
"mean_token_accuracy": 0.1334988869726658,
|
|
"num_tokens": 2315999.0,
|
|
"step": 1035
|
|
},
|
|
{
|
|
"entropy": 6.314444875717163,
|
|
"epoch": 0.11680799685516932,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999997820685,
|
|
"loss": 6.4675,
|
|
"mean_token_accuracy": 0.13674540892243386,
|
|
"num_tokens": 2326695.0,
|
|
"step": 1040
|
|
},
|
|
{
|
|
"entropy": 6.406942319869995,
|
|
"epoch": 0.11736957376312686,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999997226065974,
|
|
"loss": 6.3016,
|
|
"mean_token_accuracy": 0.1462261736392975,
|
|
"num_tokens": 2336925.0,
|
|
"step": 1045
|
|
},
|
|
{
|
|
"entropy": 6.263730525970459,
|
|
"epoch": 0.11793115067108441,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004999996559806163,
|
|
"loss": 6.1958,
|
|
"mean_token_accuracy": 0.14441620260477067,
|
|
"num_tokens": 2347431.0,
|
|
"step": 1050
|
|
},
|
|
{
|
|
"entropy": 6.244428634643555,
|
|
"epoch": 0.11849272757904195,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004999995821905589,
|
|
"loss": 6.3172,
|
|
"mean_token_accuracy": 0.1421760179102421,
|
|
"num_tokens": 2359894.0,
|
|
"step": 1055
|
|
},
|
|
{
|
|
"entropy": 6.303659820556641,
|
|
"epoch": 0.1190543044869995,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999995012364276,
|
|
"loss": 6.337,
|
|
"mean_token_accuracy": 0.13856007382273675,
|
|
"num_tokens": 2371181.0,
|
|
"step": 1060
|
|
},
|
|
{
|
|
"entropy": 6.324774694442749,
|
|
"epoch": 0.11961588139495703,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004999994131182248,
|
|
"loss": 6.2517,
|
|
"mean_token_accuracy": 0.1395735837519169,
|
|
"num_tokens": 2381531.0,
|
|
"step": 1065
|
|
},
|
|
{
|
|
"entropy": 6.371315765380859,
|
|
"epoch": 0.12017745830291458,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999993178359535,
|
|
"loss": 6.3653,
|
|
"mean_token_accuracy": 0.13924674913287163,
|
|
"num_tokens": 2391573.0,
|
|
"step": 1070
|
|
},
|
|
{
|
|
"entropy": 6.3575451374053955,
|
|
"epoch": 0.12073903521087213,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999992153896166,
|
|
"loss": 6.3265,
|
|
"mean_token_accuracy": 0.1408253751695156,
|
|
"num_tokens": 2402822.0,
|
|
"step": 1075
|
|
},
|
|
{
|
|
"entropy": 6.25819411277771,
|
|
"epoch": 0.12130061211882967,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999991057792175,
|
|
"loss": 6.2388,
|
|
"mean_token_accuracy": 0.14113450944423675,
|
|
"num_tokens": 2414322.0,
|
|
"step": 1080
|
|
},
|
|
{
|
|
"entropy": 6.331667757034301,
|
|
"epoch": 0.12186218902678722,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999989890047596,
|
|
"loss": 6.4214,
|
|
"mean_token_accuracy": 0.14067383036017417,
|
|
"num_tokens": 2426560.0,
|
|
"step": 1085
|
|
},
|
|
{
|
|
"entropy": 6.356629800796509,
|
|
"epoch": 0.12242376593474476,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999988650662467,
|
|
"loss": 6.3375,
|
|
"mean_token_accuracy": 0.13867293000221254,
|
|
"num_tokens": 2437723.0,
|
|
"step": 1090
|
|
},
|
|
{
|
|
"entropy": 6.203175830841064,
|
|
"epoch": 0.12298534284270231,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999987339636825,
|
|
"loss": 6.2935,
|
|
"mean_token_accuracy": 0.14306040480732918,
|
|
"num_tokens": 2448497.0,
|
|
"step": 1095
|
|
},
|
|
{
|
|
"entropy": 6.248790836334228,
|
|
"epoch": 0.12354691975065986,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999985956970713,
|
|
"loss": 6.1472,
|
|
"mean_token_accuracy": 0.15073004588484765,
|
|
"num_tokens": 2459089.0,
|
|
"step": 1100
|
|
},
|
|
{
|
|
"entropy": 6.2033332824707035,
|
|
"epoch": 0.1241084966586174,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999984502664178,
|
|
"loss": 6.2462,
|
|
"mean_token_accuracy": 0.1456376627087593,
|
|
"num_tokens": 2469882.0,
|
|
"step": 1105
|
|
},
|
|
{
|
|
"entropy": 6.280349397659302,
|
|
"epoch": 0.12467007356657495,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999982976717261,
|
|
"loss": 6.294,
|
|
"mean_token_accuracy": 0.1401812620460987,
|
|
"num_tokens": 2482120.0,
|
|
"step": 1110
|
|
},
|
|
{
|
|
"entropy": 6.249101734161377,
|
|
"epoch": 0.1252316504745325,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999981379130016,
|
|
"loss": 6.2899,
|
|
"mean_token_accuracy": 0.14231890588998794,
|
|
"num_tokens": 2492626.0,
|
|
"step": 1115
|
|
},
|
|
{
|
|
"entropy": 6.41325273513794,
|
|
"epoch": 0.12579322738249002,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.000499997970990249,
|
|
"loss": 6.3502,
|
|
"mean_token_accuracy": 0.13953726515173911,
|
|
"num_tokens": 2506347.0,
|
|
"step": 1120
|
|
},
|
|
{
|
|
"entropy": 6.118116569519043,
|
|
"epoch": 0.12635480429044757,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999977969034737,
|
|
"loss": 6.231,
|
|
"mean_token_accuracy": 0.14573983773589133,
|
|
"num_tokens": 2516584.0,
|
|
"step": 1125
|
|
},
|
|
{
|
|
"entropy": 6.293763732910156,
|
|
"epoch": 0.12691638119840512,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999976156526814,
|
|
"loss": 6.2808,
|
|
"mean_token_accuracy": 0.14250900223851204,
|
|
"num_tokens": 2526731.0,
|
|
"step": 1130
|
|
},
|
|
{
|
|
"entropy": 6.255453729629517,
|
|
"epoch": 0.12747795810636267,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999974272378776,
|
|
"loss": 6.1823,
|
|
"mean_token_accuracy": 0.14683502316474914,
|
|
"num_tokens": 2537180.0,
|
|
"step": 1135
|
|
},
|
|
{
|
|
"entropy": 6.250594902038574,
|
|
"epoch": 0.12803953501432022,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999972316590685,
|
|
"loss": 6.2542,
|
|
"mean_token_accuracy": 0.14406149387359618,
|
|
"num_tokens": 2547617.0,
|
|
"step": 1140
|
|
},
|
|
{
|
|
"entropy": 6.249514532089234,
|
|
"epoch": 0.12860111192227774,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999970289162604,
|
|
"loss": 6.1485,
|
|
"mean_token_accuracy": 0.15137399435043336,
|
|
"num_tokens": 2557743.0,
|
|
"step": 1145
|
|
},
|
|
{
|
|
"entropy": 6.165639209747314,
|
|
"epoch": 0.1291626888302353,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999968190094595,
|
|
"loss": 6.2457,
|
|
"mean_token_accuracy": 0.14083524644374848,
|
|
"num_tokens": 2568351.0,
|
|
"step": 1150
|
|
},
|
|
{
|
|
"entropy": 6.251227760314942,
|
|
"epoch": 0.12972426573819285,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999966019386727,
|
|
"loss": 6.2939,
|
|
"mean_token_accuracy": 0.14459053725004195,
|
|
"num_tokens": 2579703.0,
|
|
"step": 1155
|
|
},
|
|
{
|
|
"entropy": 6.3433530807495115,
|
|
"epoch": 0.1302858426461504,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999963777039067,
|
|
"loss": 6.2756,
|
|
"mean_token_accuracy": 0.14344643652439118,
|
|
"num_tokens": 2591197.0,
|
|
"step": 1160
|
|
},
|
|
{
|
|
"entropy": 6.212835693359375,
|
|
"epoch": 0.13084741955410795,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000499996146305169,
|
|
"loss": 6.2425,
|
|
"mean_token_accuracy": 0.14024166837334634,
|
|
"num_tokens": 2601836.0,
|
|
"step": 1165
|
|
},
|
|
{
|
|
"entropy": 6.174261999130249,
|
|
"epoch": 0.13140899646206547,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999959077424665,
|
|
"loss": 6.1914,
|
|
"mean_token_accuracy": 0.14582822620868682,
|
|
"num_tokens": 2613513.0,
|
|
"step": 1170
|
|
},
|
|
{
|
|
"entropy": 6.215035343170166,
|
|
"epoch": 0.13197057337002302,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004999956620158072,
|
|
"loss": 6.2188,
|
|
"mean_token_accuracy": 0.1405838191509247,
|
|
"num_tokens": 2625246.0,
|
|
"step": 1175
|
|
},
|
|
{
|
|
"entropy": 6.209453153610229,
|
|
"epoch": 0.13253215027798057,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999954091251987,
|
|
"loss": 6.1998,
|
|
"mean_token_accuracy": 0.145721872150898,
|
|
"num_tokens": 2636375.0,
|
|
"step": 1180
|
|
},
|
|
{
|
|
"entropy": 6.258368968963623,
|
|
"epoch": 0.13309372718593812,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999951490706491,
|
|
"loss": 6.2813,
|
|
"mean_token_accuracy": 0.1400119759142399,
|
|
"num_tokens": 2648586.0,
|
|
"step": 1185
|
|
},
|
|
{
|
|
"entropy": 6.228626394271851,
|
|
"epoch": 0.13365530409389567,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999948818521667,
|
|
"loss": 6.2922,
|
|
"mean_token_accuracy": 0.14909495860338212,
|
|
"num_tokens": 2660847.0,
|
|
"step": 1190
|
|
},
|
|
{
|
|
"entropy": 6.27654242515564,
|
|
"epoch": 0.1342168810018532,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00049999460746976,
|
|
"loss": 6.1995,
|
|
"mean_token_accuracy": 0.15112631320953368,
|
|
"num_tokens": 2671160.0,
|
|
"step": 1195
|
|
},
|
|
{
|
|
"entropy": 6.2761036396026615,
|
|
"epoch": 0.13477845790981074,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999943259234377,
|
|
"loss": 6.3332,
|
|
"mean_token_accuracy": 0.1402974992990494,
|
|
"num_tokens": 2681622.0,
|
|
"step": 1200
|
|
},
|
|
{
|
|
"entropy": 6.138793230056763,
|
|
"epoch": 0.1353400348177683,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999940372132089,
|
|
"loss": 6.1344,
|
|
"mean_token_accuracy": 0.15093236565589904,
|
|
"num_tokens": 2691503.0,
|
|
"step": 1205
|
|
},
|
|
{
|
|
"entropy": 6.240342044830323,
|
|
"epoch": 0.13590161172572585,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999937413390826,
|
|
"loss": 6.2271,
|
|
"mean_token_accuracy": 0.1419438488781452,
|
|
"num_tokens": 2702207.0,
|
|
"step": 1210
|
|
},
|
|
{
|
|
"entropy": 6.202216148376465,
|
|
"epoch": 0.1364631886336834,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004999934383010683,
|
|
"loss": 6.2241,
|
|
"mean_token_accuracy": 0.14322525262832642,
|
|
"num_tokens": 2713178.0,
|
|
"step": 1215
|
|
},
|
|
{
|
|
"entropy": 6.297481489181519,
|
|
"epoch": 0.13702476554164092,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999931280991757,
|
|
"loss": 6.2245,
|
|
"mean_token_accuracy": 0.14976111873984338,
|
|
"num_tokens": 2723717.0,
|
|
"step": 1220
|
|
},
|
|
{
|
|
"entropy": 6.216017818450927,
|
|
"epoch": 0.13758634244959847,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999928107334146,
|
|
"loss": 6.2951,
|
|
"mean_token_accuracy": 0.136559446901083,
|
|
"num_tokens": 2735669.0,
|
|
"step": 1225
|
|
},
|
|
{
|
|
"entropy": 6.167074728012085,
|
|
"epoch": 0.13814791935755602,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999924862037952,
|
|
"loss": 6.1884,
|
|
"mean_token_accuracy": 0.14789925068616866,
|
|
"num_tokens": 2746087.0,
|
|
"step": 1230
|
|
},
|
|
{
|
|
"entropy": 6.147751665115356,
|
|
"epoch": 0.13870949626551357,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999921545103278,
|
|
"loss": 6.2034,
|
|
"mean_token_accuracy": 0.14419680163264276,
|
|
"num_tokens": 2757143.0,
|
|
"step": 1235
|
|
},
|
|
{
|
|
"entropy": 6.358134937286377,
|
|
"epoch": 0.1392710731734711,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999918156530229,
|
|
"loss": 6.3213,
|
|
"mean_token_accuracy": 0.13962023183703423,
|
|
"num_tokens": 2769340.0,
|
|
"step": 1240
|
|
},
|
|
{
|
|
"entropy": 6.162968301773072,
|
|
"epoch": 0.13983265008142864,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999914696318913,
|
|
"loss": 6.2232,
|
|
"mean_token_accuracy": 0.14598722010850906,
|
|
"num_tokens": 2779514.0,
|
|
"step": 1245
|
|
},
|
|
{
|
|
"entropy": 6.283104515075683,
|
|
"epoch": 0.1403942269893862,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999911164469441,
|
|
"loss": 6.1679,
|
|
"mean_token_accuracy": 0.1477931559085846,
|
|
"num_tokens": 2790801.0,
|
|
"step": 1250
|
|
},
|
|
{
|
|
"entropy": 6.126214218139649,
|
|
"epoch": 0.14095580389734375,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999907560981925,
|
|
"loss": 6.1673,
|
|
"mean_token_accuracy": 0.14310122951865195,
|
|
"num_tokens": 2801082.0,
|
|
"step": 1255
|
|
},
|
|
{
|
|
"entropy": 6.248990869522094,
|
|
"epoch": 0.1415173808053013,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004999903885856479,
|
|
"loss": 6.1766,
|
|
"mean_token_accuracy": 0.14449185878038406,
|
|
"num_tokens": 2812719.0,
|
|
"step": 1260
|
|
},
|
|
{
|
|
"entropy": 6.088176202774048,
|
|
"epoch": 0.14207895771325882,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000499990013909322,
|
|
"loss": 6.1826,
|
|
"mean_token_accuracy": 0.1402534618973732,
|
|
"num_tokens": 2823766.0,
|
|
"step": 1265
|
|
},
|
|
{
|
|
"entropy": 6.18324728012085,
|
|
"epoch": 0.14264053462121637,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.000499989632069227,
|
|
"loss": 6.2595,
|
|
"mean_token_accuracy": 0.14025890976190566,
|
|
"num_tokens": 2834801.0,
|
|
"step": 1270
|
|
},
|
|
{
|
|
"entropy": 6.208938646316528,
|
|
"epoch": 0.14320211152917392,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999892430653747,
|
|
"loss": 6.075,
|
|
"mean_token_accuracy": 0.14267505779862405,
|
|
"num_tokens": 2845769.0,
|
|
"step": 1275
|
|
},
|
|
{
|
|
"entropy": 6.056669235229492,
|
|
"epoch": 0.14376368843713147,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999888468977776,
|
|
"loss": 6.1233,
|
|
"mean_token_accuracy": 0.15102226734161378,
|
|
"num_tokens": 2856001.0,
|
|
"step": 1280
|
|
},
|
|
{
|
|
"entropy": 6.231183815002441,
|
|
"epoch": 0.14432526534508902,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999884435664485,
|
|
"loss": 6.1527,
|
|
"mean_token_accuracy": 0.1492895245552063,
|
|
"num_tokens": 2867703.0,
|
|
"step": 1285
|
|
},
|
|
{
|
|
"entropy": 6.038867378234864,
|
|
"epoch": 0.14488684225304654,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999880330714,
|
|
"loss": 6.1031,
|
|
"mean_token_accuracy": 0.14959244281053544,
|
|
"num_tokens": 2878671.0,
|
|
"step": 1290
|
|
},
|
|
{
|
|
"entropy": 6.206944847106934,
|
|
"epoch": 0.1454484191610041,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999876154126453,
|
|
"loss": 6.218,
|
|
"mean_token_accuracy": 0.139216335862875,
|
|
"num_tokens": 2890137.0,
|
|
"step": 1295
|
|
},
|
|
{
|
|
"entropy": 6.149424123764038,
|
|
"epoch": 0.14600999606896164,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999871905901977,
|
|
"loss": 6.1208,
|
|
"mean_token_accuracy": 0.14582841619849204,
|
|
"num_tokens": 2900344.0,
|
|
"step": 1300
|
|
},
|
|
{
|
|
"entropy": 6.129654502868652,
|
|
"epoch": 0.1465715729769192,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999867586040706,
|
|
"loss": 6.1297,
|
|
"mean_token_accuracy": 0.1448382779955864,
|
|
"num_tokens": 2912270.0,
|
|
"step": 1305
|
|
},
|
|
{
|
|
"entropy": 6.205135250091553,
|
|
"epoch": 0.14713314988487675,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999863194542779,
|
|
"loss": 6.2111,
|
|
"mean_token_accuracy": 0.13794636726379395,
|
|
"num_tokens": 2924677.0,
|
|
"step": 1310
|
|
},
|
|
{
|
|
"entropy": 6.095851850509644,
|
|
"epoch": 0.14769472679283427,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999858731408336,
|
|
"loss": 6.1288,
|
|
"mean_token_accuracy": 0.14932863563299179,
|
|
"num_tokens": 2935794.0,
|
|
"step": 1315
|
|
},
|
|
{
|
|
"entropy": 6.201195335388183,
|
|
"epoch": 0.14825630370079182,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999854196637518,
|
|
"loss": 6.2348,
|
|
"mean_token_accuracy": 0.14271686151623725,
|
|
"num_tokens": 2945958.0,
|
|
"step": 1320
|
|
},
|
|
{
|
|
"entropy": 6.227007293701172,
|
|
"epoch": 0.14881788060874937,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999849590230469,
|
|
"loss": 6.191,
|
|
"mean_token_accuracy": 0.14383039027452468,
|
|
"num_tokens": 2957536.0,
|
|
"step": 1325
|
|
},
|
|
{
|
|
"entropy": 6.134780406951904,
|
|
"epoch": 0.14937945751670692,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999844912187336,
|
|
"loss": 6.1875,
|
|
"mean_token_accuracy": 0.1435810834169388,
|
|
"num_tokens": 2967787.0,
|
|
"step": 1330
|
|
},
|
|
{
|
|
"entropy": 6.221927547454834,
|
|
"epoch": 0.14994103442466447,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000499984016250827,
|
|
"loss": 6.2061,
|
|
"mean_token_accuracy": 0.14361153468489646,
|
|
"num_tokens": 2980522.0,
|
|
"step": 1335
|
|
},
|
|
{
|
|
"entropy": 6.042116403579712,
|
|
"epoch": 0.150502611332622,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000499983534119342,
|
|
"loss": 6.1357,
|
|
"mean_token_accuracy": 0.14881859421730043,
|
|
"num_tokens": 2990497.0,
|
|
"step": 1340
|
|
},
|
|
{
|
|
"entropy": 6.260757350921631,
|
|
"epoch": 0.15106418824057954,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004999830448242941,
|
|
"loss": 6.2239,
|
|
"mean_token_accuracy": 0.14589421674609185,
|
|
"num_tokens": 3002931.0,
|
|
"step": 1345
|
|
},
|
|
{
|
|
"entropy": 6.185908365249634,
|
|
"epoch": 0.1516257651485371,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999825483656986,
|
|
"loss": 6.1498,
|
|
"mean_token_accuracy": 0.15437110215425492,
|
|
"num_tokens": 3014137.0,
|
|
"step": 1350
|
|
},
|
|
{
|
|
"entropy": 6.2453696727752686,
|
|
"epoch": 0.15218734205649465,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999820447435716,
|
|
"loss": 6.3187,
|
|
"mean_token_accuracy": 0.13783042505383492,
|
|
"num_tokens": 3026145.0,
|
|
"step": 1355
|
|
},
|
|
{
|
|
"entropy": 6.102747440338135,
|
|
"epoch": 0.15274891896445217,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999815339579291,
|
|
"loss": 6.1756,
|
|
"mean_token_accuracy": 0.14163123667240143,
|
|
"num_tokens": 3037068.0,
|
|
"step": 1360
|
|
},
|
|
{
|
|
"entropy": 6.226761770248413,
|
|
"epoch": 0.15331049587240972,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004999810160087872,
|
|
"loss": 6.0993,
|
|
"mean_token_accuracy": 0.1480005696415901,
|
|
"num_tokens": 3047836.0,
|
|
"step": 1365
|
|
},
|
|
{
|
|
"entropy": 6.135635757446289,
|
|
"epoch": 0.15387207278036727,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004999804908961626,
|
|
"loss": 6.2293,
|
|
"mean_token_accuracy": 0.1483537584543228,
|
|
"num_tokens": 3060309.0,
|
|
"step": 1370
|
|
},
|
|
{
|
|
"entropy": 6.175763988494873,
|
|
"epoch": 0.15443364968832482,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999799586200719,
|
|
"loss": 6.1913,
|
|
"mean_token_accuracy": 0.15013613551855087,
|
|
"num_tokens": 3071789.0,
|
|
"step": 1375
|
|
},
|
|
{
|
|
"entropy": 6.160604238510132,
|
|
"epoch": 0.15499522659628237,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000499979419180532,
|
|
"loss": 6.0957,
|
|
"mean_token_accuracy": 0.15357528924942015,
|
|
"num_tokens": 3081756.0,
|
|
"step": 1380
|
|
},
|
|
{
|
|
"entropy": 6.104126453399658,
|
|
"epoch": 0.1555568035042399,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999788725775601,
|
|
"loss": 6.2207,
|
|
"mean_token_accuracy": 0.1406393028795719,
|
|
"num_tokens": 3093456.0,
|
|
"step": 1385
|
|
},
|
|
{
|
|
"entropy": 6.2420367240905765,
|
|
"epoch": 0.15611838041219744,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004999783188111737,
|
|
"loss": 6.1335,
|
|
"mean_token_accuracy": 0.1524800807237625,
|
|
"num_tokens": 3104565.0,
|
|
"step": 1390
|
|
},
|
|
{
|
|
"entropy": 6.143574810028076,
|
|
"epoch": 0.156679957320155,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999777578813904,
|
|
"loss": 6.1554,
|
|
"mean_token_accuracy": 0.14844489991664886,
|
|
"num_tokens": 3115577.0,
|
|
"step": 1395
|
|
},
|
|
{
|
|
"entropy": 6.128584003448486,
|
|
"epoch": 0.15724153422811254,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000499977189788228,
|
|
"loss": 6.0467,
|
|
"mean_token_accuracy": 0.14999896585941314,
|
|
"num_tokens": 3126019.0,
|
|
"step": 1400
|
|
},
|
|
{
|
|
"entropy": 6.168298864364624,
|
|
"epoch": 0.1578031111360701,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999766145317046,
|
|
"loss": 6.2184,
|
|
"mean_token_accuracy": 0.13864450231194497,
|
|
"num_tokens": 3136191.0,
|
|
"step": 1405
|
|
},
|
|
{
|
|
"entropy": 6.245380020141601,
|
|
"epoch": 0.15836468804402762,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999760321118385,
|
|
"loss": 6.0875,
|
|
"mean_token_accuracy": 0.1503506787121296,
|
|
"num_tokens": 3147737.0,
|
|
"step": 1410
|
|
},
|
|
{
|
|
"entropy": 6.0368874073028564,
|
|
"epoch": 0.15892626495198517,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999754425286483,
|
|
"loss": 6.1608,
|
|
"mean_token_accuracy": 0.14620319604873658,
|
|
"num_tokens": 3158494.0,
|
|
"step": 1415
|
|
},
|
|
{
|
|
"entropy": 6.1492870330810545,
|
|
"epoch": 0.15948784185994272,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004999748457821529,
|
|
"loss": 6.1833,
|
|
"mean_token_accuracy": 0.1447380617260933,
|
|
"num_tokens": 3170550.0,
|
|
"step": 1420
|
|
},
|
|
{
|
|
"entropy": 6.0979039669036865,
|
|
"epoch": 0.16004941876790027,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.000499974241872371,
|
|
"loss": 6.1609,
|
|
"mean_token_accuracy": 0.15229749754071237,
|
|
"num_tokens": 3182860.0,
|
|
"step": 1425
|
|
},
|
|
{
|
|
"entropy": 6.11085262298584,
|
|
"epoch": 0.16061099567585782,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999736307993221,
|
|
"loss": 6.1698,
|
|
"mean_token_accuracy": 0.1435732513666153,
|
|
"num_tokens": 3193807.0,
|
|
"step": 1430
|
|
},
|
|
{
|
|
"entropy": 6.072397756576538,
|
|
"epoch": 0.16117257258381534,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004999730125630255,
|
|
"loss": 6.0308,
|
|
"mean_token_accuracy": 0.15132891982793809,
|
|
"num_tokens": 3203959.0,
|
|
"step": 1435
|
|
},
|
|
{
|
|
"entropy": 6.119855213165283,
|
|
"epoch": 0.1617341494917729,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004999723871635008,
|
|
"loss": 6.0406,
|
|
"mean_token_accuracy": 0.15461250096559526,
|
|
"num_tokens": 3215416.0,
|
|
"step": 1440
|
|
},
|
|
{
|
|
"entropy": 6.184870100021362,
|
|
"epoch": 0.16229572639973044,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999717546007681,
|
|
"loss": 6.1993,
|
|
"mean_token_accuracy": 0.14106006175279617,
|
|
"num_tokens": 3226938.0,
|
|
"step": 1445
|
|
},
|
|
{
|
|
"entropy": 5.983025455474854,
|
|
"epoch": 0.162857303307688,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999711148748476,
|
|
"loss": 6.0115,
|
|
"mean_token_accuracy": 0.15607472509145737,
|
|
"num_tokens": 3238406.0,
|
|
"step": 1450
|
|
},
|
|
{
|
|
"entropy": 6.070747804641724,
|
|
"epoch": 0.16341888021564555,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999704679857594,
|
|
"loss": 6.0323,
|
|
"mean_token_accuracy": 0.14664915949106216,
|
|
"num_tokens": 3249695.0,
|
|
"step": 1455
|
|
},
|
|
{
|
|
"entropy": 6.213888835906983,
|
|
"epoch": 0.16398045712360307,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999698139335243,
|
|
"loss": 6.1773,
|
|
"mean_token_accuracy": 0.15213444456458092,
|
|
"num_tokens": 3259656.0,
|
|
"step": 1460
|
|
},
|
|
{
|
|
"entropy": 6.050896024703979,
|
|
"epoch": 0.16454203403156062,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999691527181632,
|
|
"loss": 6.015,
|
|
"mean_token_accuracy": 0.1554547891020775,
|
|
"num_tokens": 3269712.0,
|
|
"step": 1465
|
|
},
|
|
{
|
|
"entropy": 5.951676607131958,
|
|
"epoch": 0.16510361093951817,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004999684843396968,
|
|
"loss": 6.0044,
|
|
"mean_token_accuracy": 0.1552644908428192,
|
|
"num_tokens": 3280343.0,
|
|
"step": 1470
|
|
},
|
|
{
|
|
"entropy": 6.096579122543335,
|
|
"epoch": 0.16566518784747572,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004999678087981467,
|
|
"loss": 6.0393,
|
|
"mean_token_accuracy": 0.15125902444124223,
|
|
"num_tokens": 3291649.0,
|
|
"step": 1475
|
|
},
|
|
{
|
|
"entropy": 6.175355672836304,
|
|
"epoch": 0.16622676475543324,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004999671260935343,
|
|
"loss": 6.2151,
|
|
"mean_token_accuracy": 0.14770857915282248,
|
|
"num_tokens": 3304190.0,
|
|
"step": 1480
|
|
},
|
|
{
|
|
"entropy": 6.013831090927124,
|
|
"epoch": 0.1667883416633908,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999664362258814,
|
|
"loss": 5.9392,
|
|
"mean_token_accuracy": 0.16093746125698088,
|
|
"num_tokens": 3313966.0,
|
|
"step": 1485
|
|
},
|
|
{
|
|
"entropy": 6.109157514572144,
|
|
"epoch": 0.16734991857134834,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999657391952099,
|
|
"loss": 6.1968,
|
|
"mean_token_accuracy": 0.1453491024672985,
|
|
"num_tokens": 3326017.0,
|
|
"step": 1490
|
|
},
|
|
{
|
|
"entropy": 6.128896427154541,
|
|
"epoch": 0.1679114954793059,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.000499965035001542,
|
|
"loss": 6.0754,
|
|
"mean_token_accuracy": 0.14839625358581543,
|
|
"num_tokens": 3338264.0,
|
|
"step": 1495
|
|
},
|
|
{
|
|
"entropy": 6.084127426147461,
|
|
"epoch": 0.16847307238726345,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999643236449001,
|
|
"loss": 6.1332,
|
|
"mean_token_accuracy": 0.1588374301791191,
|
|
"num_tokens": 3348901.0,
|
|
"step": 1500
|
|
},
|
|
{
|
|
"entropy": 6.147513389587402,
|
|
"epoch": 0.16903464929522097,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999636051253069,
|
|
"loss": 6.0628,
|
|
"mean_token_accuracy": 0.1494102582335472,
|
|
"num_tokens": 3358441.0,
|
|
"step": 1505
|
|
},
|
|
{
|
|
"entropy": 6.085050630569458,
|
|
"epoch": 0.16959622620317852,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999628794427854,
|
|
"loss": 6.147,
|
|
"mean_token_accuracy": 0.1559033215045929,
|
|
"num_tokens": 3369334.0,
|
|
"step": 1510
|
|
},
|
|
{
|
|
"entropy": 6.1317285060882565,
|
|
"epoch": 0.17015780311113607,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999621465973583,
|
|
"loss": 6.1442,
|
|
"mean_token_accuracy": 0.1466472938656807,
|
|
"num_tokens": 3380698.0,
|
|
"step": 1515
|
|
},
|
|
{
|
|
"entropy": 6.239275121688843,
|
|
"epoch": 0.17071938001909362,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999614065890495,
|
|
"loss": 6.1503,
|
|
"mean_token_accuracy": 0.14520846977829932,
|
|
"num_tokens": 3391061.0,
|
|
"step": 1520
|
|
},
|
|
{
|
|
"entropy": 6.090221786499024,
|
|
"epoch": 0.17128095692705117,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999606594178821,
|
|
"loss": 6.2056,
|
|
"mean_token_accuracy": 0.1438593976199627,
|
|
"num_tokens": 3403983.0,
|
|
"step": 1525
|
|
},
|
|
{
|
|
"entropy": 6.175626039505005,
|
|
"epoch": 0.1718425338350087,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00049995990508388,
|
|
"loss": 6.1397,
|
|
"mean_token_accuracy": 0.15281769931316375,
|
|
"num_tokens": 3413838.0,
|
|
"step": 1530
|
|
},
|
|
{
|
|
"entropy": 5.981231355667115,
|
|
"epoch": 0.17240411074296624,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004999591435870674,
|
|
"loss": 5.961,
|
|
"mean_token_accuracy": 0.15355922728776933,
|
|
"num_tokens": 3423978.0,
|
|
"step": 1535
|
|
},
|
|
{
|
|
"entropy": 6.136894989013672,
|
|
"epoch": 0.1729656876509238,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999583749274684,
|
|
"loss": 6.1312,
|
|
"mean_token_accuracy": 0.15456196144223214,
|
|
"num_tokens": 3433416.0,
|
|
"step": 1540
|
|
},
|
|
{
|
|
"entropy": 5.982147359848023,
|
|
"epoch": 0.17352726455888134,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004999575991051074,
|
|
"loss": 5.9838,
|
|
"mean_token_accuracy": 0.1558251142501831,
|
|
"num_tokens": 3444983.0,
|
|
"step": 1545
|
|
},
|
|
{
|
|
"entropy": 6.021946763992309,
|
|
"epoch": 0.1740888414668389,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999568161200093,
|
|
"loss": 5.9757,
|
|
"mean_token_accuracy": 0.156097112596035,
|
|
"num_tokens": 3455808.0,
|
|
"step": 1550
|
|
},
|
|
{
|
|
"entropy": 5.985035371780396,
|
|
"epoch": 0.17465041837479642,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004999560259721989,
|
|
"loss": 6.1258,
|
|
"mean_token_accuracy": 0.14893127232789993,
|
|
"num_tokens": 3467503.0,
|
|
"step": 1555
|
|
},
|
|
{
|
|
"entropy": 6.338688659667969,
|
|
"epoch": 0.17521199528275397,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004999552286617014,
|
|
"loss": 6.3017,
|
|
"mean_token_accuracy": 0.14476528465747834,
|
|
"num_tokens": 3479941.0,
|
|
"step": 1560
|
|
},
|
|
{
|
|
"entropy": 6.006549453735351,
|
|
"epoch": 0.17577357219071152,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999544241885421,
|
|
"loss": 5.9989,
|
|
"mean_token_accuracy": 0.16019308269023896,
|
|
"num_tokens": 3491069.0,
|
|
"step": 1565
|
|
},
|
|
{
|
|
"entropy": 6.127226495742798,
|
|
"epoch": 0.17633514909866907,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999536125527467,
|
|
"loss": 6.1753,
|
|
"mean_token_accuracy": 0.14448272734880446,
|
|
"num_tokens": 3502065.0,
|
|
"step": 1570
|
|
},
|
|
{
|
|
"entropy": 6.176832151412964,
|
|
"epoch": 0.17689672600662662,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000499952793754341,
|
|
"loss": 6.1282,
|
|
"mean_token_accuracy": 0.15281856656074524,
|
|
"num_tokens": 3514228.0,
|
|
"step": 1575
|
|
},
|
|
{
|
|
"entropy": 6.0846302032470705,
|
|
"epoch": 0.17745830291458414,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999519677933512,
|
|
"loss": 6.0535,
|
|
"mean_token_accuracy": 0.1507752999663353,
|
|
"num_tokens": 3525801.0,
|
|
"step": 1580
|
|
},
|
|
{
|
|
"entropy": 6.053277921676636,
|
|
"epoch": 0.1780198798225417,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999511346698035,
|
|
"loss": 5.9995,
|
|
"mean_token_accuracy": 0.15059795528650283,
|
|
"num_tokens": 3536431.0,
|
|
"step": 1585
|
|
},
|
|
{
|
|
"entropy": 5.99881501197815,
|
|
"epoch": 0.17858145673049924,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004999502943837244,
|
|
"loss": 6.1027,
|
|
"mean_token_accuracy": 0.14881094694137573,
|
|
"num_tokens": 3549098.0,
|
|
"step": 1590
|
|
},
|
|
{
|
|
"entropy": 6.1661224365234375,
|
|
"epoch": 0.1791430336384568,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999494469351406,
|
|
"loss": 6.0682,
|
|
"mean_token_accuracy": 0.14940569475293158,
|
|
"num_tokens": 3560532.0,
|
|
"step": 1595
|
|
},
|
|
{
|
|
"entropy": 6.003274202346802,
|
|
"epoch": 0.17970461054641435,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999485923240793,
|
|
"loss": 6.0716,
|
|
"mean_token_accuracy": 0.14933864623308182,
|
|
"num_tokens": 3572175.0,
|
|
"step": 1600
|
|
},
|
|
{
|
|
"entropy": 6.1079789161682125,
|
|
"epoch": 0.18026618745437187,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004999477305505675,
|
|
"loss": 5.9988,
|
|
"mean_token_accuracy": 0.1632366694509983,
|
|
"num_tokens": 3582862.0,
|
|
"step": 1605
|
|
},
|
|
{
|
|
"entropy": 6.1130759716033936,
|
|
"epoch": 0.18082776436232942,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999468616146328,
|
|
"loss": 6.1636,
|
|
"mean_token_accuracy": 0.15272294878959655,
|
|
"num_tokens": 3594685.0,
|
|
"step": 1610
|
|
},
|
|
{
|
|
"entropy": 5.947771835327148,
|
|
"epoch": 0.18138934127028697,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999459855163026,
|
|
"loss": 5.9689,
|
|
"mean_token_accuracy": 0.1606626659631729,
|
|
"num_tokens": 3604847.0,
|
|
"step": 1615
|
|
},
|
|
{
|
|
"entropy": 6.14026780128479,
|
|
"epoch": 0.18195091817824452,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.000499945102255605,
|
|
"loss": 6.0664,
|
|
"mean_token_accuracy": 0.15268882662057875,
|
|
"num_tokens": 3615549.0,
|
|
"step": 1620
|
|
},
|
|
{
|
|
"entropy": 5.954753828048706,
|
|
"epoch": 0.18251249508620204,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999442118325682,
|
|
"loss": 5.967,
|
|
"mean_token_accuracy": 0.16526584029197694,
|
|
"num_tokens": 3626300.0,
|
|
"step": 1625
|
|
},
|
|
{
|
|
"entropy": 6.00643219947815,
|
|
"epoch": 0.1830740719941596,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004999433142472205,
|
|
"loss": 5.9874,
|
|
"mean_token_accuracy": 0.15639984607696533,
|
|
"num_tokens": 3637832.0,
|
|
"step": 1630
|
|
},
|
|
{
|
|
"entropy": 6.080643796920777,
|
|
"epoch": 0.18363564890211714,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999424094995902,
|
|
"loss": 6.0342,
|
|
"mean_token_accuracy": 0.14727310091257095,
|
|
"num_tokens": 3649179.0,
|
|
"step": 1635
|
|
},
|
|
{
|
|
"entropy": 6.008195066452027,
|
|
"epoch": 0.1841972258100747,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004999414975897066,
|
|
"loss": 6.0708,
|
|
"mean_token_accuracy": 0.15119689106941223,
|
|
"num_tokens": 3660011.0,
|
|
"step": 1640
|
|
},
|
|
{
|
|
"entropy": 6.162057495117187,
|
|
"epoch": 0.18475880271803224,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004999405785175983,
|
|
"loss": 6.1501,
|
|
"mean_token_accuracy": 0.14309106916189193,
|
|
"num_tokens": 3672791.0,
|
|
"step": 1645
|
|
},
|
|
{
|
|
"entropy": 5.958169221878052,
|
|
"epoch": 0.18532037962598977,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004999396522832949,
|
|
"loss": 5.9647,
|
|
"mean_token_accuracy": 0.14754443913698195,
|
|
"num_tokens": 3684709.0,
|
|
"step": 1650
|
|
},
|
|
{
|
|
"entropy": 5.964678478240967,
|
|
"epoch": 0.18588195653394732,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999387188868256,
|
|
"loss": 5.9426,
|
|
"mean_token_accuracy": 0.1558021366596222,
|
|
"num_tokens": 3694675.0,
|
|
"step": 1655
|
|
},
|
|
{
|
|
"entropy": 5.890969276428223,
|
|
"epoch": 0.18644353344190487,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004999377783282203,
|
|
"loss": 5.9461,
|
|
"mean_token_accuracy": 0.15189632922410964,
|
|
"num_tokens": 3706384.0,
|
|
"step": 1660
|
|
},
|
|
{
|
|
"entropy": 6.1524893283844,
|
|
"epoch": 0.18700511034986242,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004999368306075089,
|
|
"loss": 6.0175,
|
|
"mean_token_accuracy": 0.1526872456073761,
|
|
"num_tokens": 3717419.0,
|
|
"step": 1665
|
|
},
|
|
{
|
|
"entropy": 6.060198020935059,
|
|
"epoch": 0.18756668725781997,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999358757247215,
|
|
"loss": 6.0517,
|
|
"mean_token_accuracy": 0.1526139944791794,
|
|
"num_tokens": 3727306.0,
|
|
"step": 1670
|
|
},
|
|
{
|
|
"entropy": 6.124920654296875,
|
|
"epoch": 0.1881282641657775,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004999349136798886,
|
|
"loss": 6.1765,
|
|
"mean_token_accuracy": 0.14685777351260185,
|
|
"num_tokens": 3739476.0,
|
|
"step": 1675
|
|
},
|
|
{
|
|
"entropy": 6.046180200576782,
|
|
"epoch": 0.18868984107373504,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004999339444730409,
|
|
"loss": 5.9431,
|
|
"mean_token_accuracy": 0.15702874660491944,
|
|
"num_tokens": 3751035.0,
|
|
"step": 1680
|
|
},
|
|
{
|
|
"entropy": 6.048432970046997,
|
|
"epoch": 0.1892514179816926,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999329681042092,
|
|
"loss": 6.0281,
|
|
"mean_token_accuracy": 0.1569201871752739,
|
|
"num_tokens": 3762881.0,
|
|
"step": 1685
|
|
},
|
|
{
|
|
"entropy": 6.009223794937133,
|
|
"epoch": 0.18981299488965014,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999319845734243,
|
|
"loss": 6.0435,
|
|
"mean_token_accuracy": 0.15313177406787873,
|
|
"num_tokens": 3774180.0,
|
|
"step": 1690
|
|
},
|
|
{
|
|
"entropy": 6.0793358325958256,
|
|
"epoch": 0.1903745717976077,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004999309938807181,
|
|
"loss": 6.0413,
|
|
"mean_token_accuracy": 0.15854722559452056,
|
|
"num_tokens": 3784864.0,
|
|
"step": 1695
|
|
},
|
|
{
|
|
"entropy": 6.063125991821289,
|
|
"epoch": 0.19093614870556522,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999299960261216,
|
|
"loss": 6.0034,
|
|
"mean_token_accuracy": 0.15233902782201766,
|
|
"num_tokens": 3797693.0,
|
|
"step": 1700
|
|
},
|
|
{
|
|
"entropy": 6.026073360443116,
|
|
"epoch": 0.19149772561352277,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999289910096669,
|
|
"loss": 6.0425,
|
|
"mean_token_accuracy": 0.1526545524597168,
|
|
"num_tokens": 3809379.0,
|
|
"step": 1705
|
|
},
|
|
{
|
|
"entropy": 5.922689151763916,
|
|
"epoch": 0.19205930252148032,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004999279788313858,
|
|
"loss": 5.8735,
|
|
"mean_token_accuracy": 0.1640583574771881,
|
|
"num_tokens": 3819473.0,
|
|
"step": 1710
|
|
},
|
|
{
|
|
"entropy": 5.850899267196655,
|
|
"epoch": 0.19262087942943787,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004999269594913107,
|
|
"loss": 5.8711,
|
|
"mean_token_accuracy": 0.16054081916809082,
|
|
"num_tokens": 3831037.0,
|
|
"step": 1715
|
|
},
|
|
{
|
|
"entropy": 5.991314029693603,
|
|
"epoch": 0.19318245633739542,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004999259329894739,
|
|
"loss": 6.018,
|
|
"mean_token_accuracy": 0.151178976893425,
|
|
"num_tokens": 3841767.0,
|
|
"step": 1720
|
|
},
|
|
{
|
|
"entropy": 5.9119984149932865,
|
|
"epoch": 0.19374403324535294,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999248993259081,
|
|
"loss": 5.8597,
|
|
"mean_token_accuracy": 0.16238378435373307,
|
|
"num_tokens": 3851629.0,
|
|
"step": 1725
|
|
},
|
|
{
|
|
"entropy": 5.94813723564148,
|
|
"epoch": 0.1943056101533105,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999238585006463,
|
|
"loss": 5.94,
|
|
"mean_token_accuracy": 0.15244577899575235,
|
|
"num_tokens": 3863247.0,
|
|
"step": 1730
|
|
},
|
|
{
|
|
"entropy": 6.0112062931060795,
|
|
"epoch": 0.19486718706126804,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004999228105137218,
|
|
"loss": 5.9176,
|
|
"mean_token_accuracy": 0.15697233527898788,
|
|
"num_tokens": 3873949.0,
|
|
"step": 1735
|
|
},
|
|
{
|
|
"entropy": 5.9939721584320065,
|
|
"epoch": 0.1954287639692256,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999217553651676,
|
|
"loss": 6.0223,
|
|
"mean_token_accuracy": 0.15648642033338547,
|
|
"num_tokens": 3884992.0,
|
|
"step": 1740
|
|
},
|
|
{
|
|
"entropy": 6.029172420501709,
|
|
"epoch": 0.19599034087718312,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004999206930550175,
|
|
"loss": 6.1497,
|
|
"mean_token_accuracy": 0.158347637206316,
|
|
"num_tokens": 3897029.0,
|
|
"step": 1745
|
|
},
|
|
{
|
|
"entropy": 6.016314172744751,
|
|
"epoch": 0.19655191778514067,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004999196235833054,
|
|
"loss": 6.001,
|
|
"mean_token_accuracy": 0.15252462327480315,
|
|
"num_tokens": 3909510.0,
|
|
"step": 1750
|
|
},
|
|
{
|
|
"entropy": 5.9791820526123045,
|
|
"epoch": 0.19711349469309822,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004999185469500651,
|
|
"loss": 5.8895,
|
|
"mean_token_accuracy": 0.15988631993532182,
|
|
"num_tokens": 3920593.0,
|
|
"step": 1755
|
|
},
|
|
{
|
|
"entropy": 6.043954753875733,
|
|
"epoch": 0.19767507160105577,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.000499917463155331,
|
|
"loss": 6.0383,
|
|
"mean_token_accuracy": 0.15022043734788895,
|
|
"num_tokens": 3932215.0,
|
|
"step": 1760
|
|
},
|
|
{
|
|
"entropy": 5.971577739715576,
|
|
"epoch": 0.19823664850901332,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999163721991378,
|
|
"loss": 5.9892,
|
|
"mean_token_accuracy": 0.15806906223297118,
|
|
"num_tokens": 3943876.0,
|
|
"step": 1765
|
|
},
|
|
{
|
|
"entropy": 5.915837717056275,
|
|
"epoch": 0.19879822541697084,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00049991527408152,
|
|
"loss": 5.9785,
|
|
"mean_token_accuracy": 0.1582863599061966,
|
|
"num_tokens": 3954533.0,
|
|
"step": 1770
|
|
},
|
|
{
|
|
"entropy": 6.1025553226470945,
|
|
"epoch": 0.1993598023249284,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004999141688025127,
|
|
"loss": 6.0337,
|
|
"mean_token_accuracy": 0.15851334780454635,
|
|
"num_tokens": 3965722.0,
|
|
"step": 1775
|
|
},
|
|
{
|
|
"entropy": 5.983110094070435,
|
|
"epoch": 0.19992137923288594,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.000499913056362151,
|
|
"loss": 5.9503,
|
|
"mean_token_accuracy": 0.1551786482334137,
|
|
"num_tokens": 3976737.0,
|
|
"step": 1780
|
|
},
|
|
{
|
|
"entropy": 6.036009645462036,
|
|
"epoch": 0.2004829561408435,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999119367604703,
|
|
"loss": 6.0433,
|
|
"mean_token_accuracy": 0.15762924998998643,
|
|
"num_tokens": 3986102.0,
|
|
"step": 1785
|
|
},
|
|
{
|
|
"entropy": 6.072134399414063,
|
|
"epoch": 0.20104453304880104,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004999108099975064,
|
|
"loss": 6.0061,
|
|
"mean_token_accuracy": 0.1530447334051132,
|
|
"num_tokens": 3996534.0,
|
|
"step": 1790
|
|
},
|
|
{
|
|
"entropy": 5.904342555999756,
|
|
"epoch": 0.20160610995675857,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000499909676073295,
|
|
"loss": 5.9275,
|
|
"mean_token_accuracy": 0.1523033708333969,
|
|
"num_tokens": 4006947.0,
|
|
"step": 1795
|
|
},
|
|
{
|
|
"entropy": 5.950516653060913,
|
|
"epoch": 0.20216768686471612,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004999085349878723,
|
|
"loss": 5.9585,
|
|
"mean_token_accuracy": 0.16358500719070435,
|
|
"num_tokens": 4017723.0,
|
|
"step": 1800
|
|
},
|
|
{
|
|
"entropy": 5.962766361236572,
|
|
"epoch": 0.20272926377267367,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999073867412746,
|
|
"loss": 6.0335,
|
|
"mean_token_accuracy": 0.1502598688006401,
|
|
"num_tokens": 4028347.0,
|
|
"step": 1805
|
|
},
|
|
{
|
|
"entropy": 6.021455144882202,
|
|
"epoch": 0.20329084068063122,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999062313335385,
|
|
"loss": 5.8942,
|
|
"mean_token_accuracy": 0.16167644560337066,
|
|
"num_tokens": 4039648.0,
|
|
"step": 1810
|
|
},
|
|
{
|
|
"entropy": 5.977356767654419,
|
|
"epoch": 0.20385241758858877,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004999050687647008,
|
|
"loss": 5.9553,
|
|
"mean_token_accuracy": 0.15589284300804138,
|
|
"num_tokens": 4050786.0,
|
|
"step": 1815
|
|
},
|
|
{
|
|
"entropy": 6.015071296691895,
|
|
"epoch": 0.2044139944965463,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004999038990347984,
|
|
"loss": 5.9929,
|
|
"mean_token_accuracy": 0.16174751073122023,
|
|
"num_tokens": 4061184.0,
|
|
"step": 1820
|
|
},
|
|
{
|
|
"entropy": 6.110763120651245,
|
|
"epoch": 0.20497557140450384,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999027221438688,
|
|
"loss": 6.1276,
|
|
"mean_token_accuracy": 0.15206350088119508,
|
|
"num_tokens": 4073607.0,
|
|
"step": 1825
|
|
},
|
|
{
|
|
"entropy": 5.954882335662842,
|
|
"epoch": 0.2055371483124614,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000499901538091949,
|
|
"loss": 5.9348,
|
|
"mean_token_accuracy": 0.15849609076976776,
|
|
"num_tokens": 4083924.0,
|
|
"step": 1830
|
|
},
|
|
{
|
|
"entropy": 5.934993076324463,
|
|
"epoch": 0.20609872522041894,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999003468790773,
|
|
"loss": 5.9227,
|
|
"mean_token_accuracy": 0.15979374349117278,
|
|
"num_tokens": 4094083.0,
|
|
"step": 1835
|
|
},
|
|
{
|
|
"entropy": 6.010126113891602,
|
|
"epoch": 0.2066603021283765,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004998991485052911,
|
|
"loss": 5.9711,
|
|
"mean_token_accuracy": 0.16147021800279618,
|
|
"num_tokens": 4105124.0,
|
|
"step": 1840
|
|
},
|
|
{
|
|
"entropy": 6.109958982467651,
|
|
"epoch": 0.20722187903633402,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.000499897942970629,
|
|
"loss": 6.1275,
|
|
"mean_token_accuracy": 0.14718503132462502,
|
|
"num_tokens": 4116792.0,
|
|
"step": 1845
|
|
},
|
|
{
|
|
"entropy": 6.114938068389892,
|
|
"epoch": 0.20778345594429157,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.000499896730275129,
|
|
"loss": 6.1146,
|
|
"mean_token_accuracy": 0.1512462429702282,
|
|
"num_tokens": 4127441.0,
|
|
"step": 1850
|
|
},
|
|
{
|
|
"entropy": 5.993119430541992,
|
|
"epoch": 0.20834503285224912,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00049989551041883,
|
|
"loss": 6.0981,
|
|
"mean_token_accuracy": 0.14911631792783736,
|
|
"num_tokens": 4138696.0,
|
|
"step": 1855
|
|
},
|
|
{
|
|
"entropy": 6.001512622833252,
|
|
"epoch": 0.20890660976020667,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998942834017707,
|
|
"loss": 5.9664,
|
|
"mean_token_accuracy": 0.15618520528078078,
|
|
"num_tokens": 4151254.0,
|
|
"step": 1860
|
|
},
|
|
{
|
|
"entropy": 5.903667259216308,
|
|
"epoch": 0.2094681866681642,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004998930492239901,
|
|
"loss": 5.9333,
|
|
"mean_token_accuracy": 0.155420657992363,
|
|
"num_tokens": 4162046.0,
|
|
"step": 1865
|
|
},
|
|
{
|
|
"entropy": 5.980195140838623,
|
|
"epoch": 0.21002976357612174,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998918078855277,
|
|
"loss": 5.8815,
|
|
"mean_token_accuracy": 0.16040604412555695,
|
|
"num_tokens": 4172409.0,
|
|
"step": 1870
|
|
},
|
|
{
|
|
"entropy": 5.9213951587677,
|
|
"epoch": 0.2105913404840793,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004998905593864227,
|
|
"loss": 6.0383,
|
|
"mean_token_accuracy": 0.16037157773971558,
|
|
"num_tokens": 4182949.0,
|
|
"step": 1875
|
|
},
|
|
{
|
|
"entropy": 6.040307188034058,
|
|
"epoch": 0.21115291739203684,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004998893037267153,
|
|
"loss": 5.9975,
|
|
"mean_token_accuracy": 0.15625440329313278,
|
|
"num_tokens": 4194164.0,
|
|
"step": 1880
|
|
},
|
|
{
|
|
"entropy": 6.089320707321167,
|
|
"epoch": 0.2117144942999944,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004998880409064452,
|
|
"loss": 5.9505,
|
|
"mean_token_accuracy": 0.1591552823781967,
|
|
"num_tokens": 4206056.0,
|
|
"step": 1885
|
|
},
|
|
{
|
|
"entropy": 5.8916090965271,
|
|
"epoch": 0.21227607120795192,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004998867709256527,
|
|
"loss": 6.0341,
|
|
"mean_token_accuracy": 0.1535590335726738,
|
|
"num_tokens": 4216660.0,
|
|
"step": 1890
|
|
},
|
|
{
|
|
"entropy": 6.002785873413086,
|
|
"epoch": 0.21283764811590947,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.000499885493784378,
|
|
"loss": 5.9187,
|
|
"mean_token_accuracy": 0.15967616736888884,
|
|
"num_tokens": 4228495.0,
|
|
"step": 1895
|
|
},
|
|
{
|
|
"entropy": 5.95042576789856,
|
|
"epoch": 0.21339922502386702,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004998842094826621,
|
|
"loss": 5.916,
|
|
"mean_token_accuracy": 0.15873922109603883,
|
|
"num_tokens": 4238560.0,
|
|
"step": 1900
|
|
},
|
|
{
|
|
"entropy": 6.099523401260376,
|
|
"epoch": 0.21396080193182457,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004998829180205458,
|
|
"loss": 6.1178,
|
|
"mean_token_accuracy": 0.153577783703804,
|
|
"num_tokens": 4250553.0,
|
|
"step": 1905
|
|
},
|
|
{
|
|
"entropy": 5.987069082260132,
|
|
"epoch": 0.21452237883978212,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004998816193980701,
|
|
"loss": 6.0338,
|
|
"mean_token_accuracy": 0.15206430703401566,
|
|
"num_tokens": 4262050.0,
|
|
"step": 1910
|
|
},
|
|
{
|
|
"entropy": 6.141225290298462,
|
|
"epoch": 0.21508395574773964,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004998803136152764,
|
|
"loss": 5.9872,
|
|
"mean_token_accuracy": 0.15555329471826554,
|
|
"num_tokens": 4273019.0,
|
|
"step": 1915
|
|
},
|
|
{
|
|
"entropy": 5.866562271118164,
|
|
"epoch": 0.2156455326556972,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998790006722063,
|
|
"loss": 5.8698,
|
|
"mean_token_accuracy": 0.1652226209640503,
|
|
"num_tokens": 4283585.0,
|
|
"step": 1920
|
|
},
|
|
{
|
|
"entropy": 5.903815793991089,
|
|
"epoch": 0.21620710956365474,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998776805689016,
|
|
"loss": 5.9505,
|
|
"mean_token_accuracy": 0.15552265867590903,
|
|
"num_tokens": 4294905.0,
|
|
"step": 1925
|
|
},
|
|
{
|
|
"entropy": 6.123217678070068,
|
|
"epoch": 0.2167686864716123,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998763533054045,
|
|
"loss": 6.0647,
|
|
"mean_token_accuracy": 0.16015672981739043,
|
|
"num_tokens": 4305926.0,
|
|
"step": 1930
|
|
},
|
|
{
|
|
"entropy": 5.9090136051177975,
|
|
"epoch": 0.21733026337956984,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004998750188817568,
|
|
"loss": 6.0258,
|
|
"mean_token_accuracy": 0.15124135613441467,
|
|
"num_tokens": 4318297.0,
|
|
"step": 1935
|
|
},
|
|
{
|
|
"entropy": 5.996935319900513,
|
|
"epoch": 0.21789184028752737,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998736772980015,
|
|
"loss": 5.8483,
|
|
"mean_token_accuracy": 0.16015774011611938,
|
|
"num_tokens": 4328795.0,
|
|
"step": 1940
|
|
},
|
|
{
|
|
"entropy": 5.8646955490112305,
|
|
"epoch": 0.21845341719548492,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.000499872328554181,
|
|
"loss": 5.862,
|
|
"mean_token_accuracy": 0.16194941848516464,
|
|
"num_tokens": 4340279.0,
|
|
"step": 1945
|
|
},
|
|
{
|
|
"entropy": 6.046488285064697,
|
|
"epoch": 0.21901499410344247,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004998709726503383,
|
|
"loss": 6.0497,
|
|
"mean_token_accuracy": 0.1511320725083351,
|
|
"num_tokens": 4352157.0,
|
|
"step": 1950
|
|
},
|
|
{
|
|
"entropy": 5.998716926574707,
|
|
"epoch": 0.21957657101140002,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998696095865168,
|
|
"loss": 5.8847,
|
|
"mean_token_accuracy": 0.16323180198669435,
|
|
"num_tokens": 4361909.0,
|
|
"step": 1955
|
|
},
|
|
{
|
|
"entropy": 5.7217999458312985,
|
|
"epoch": 0.22013814791935757,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998682393627595,
|
|
"loss": 5.799,
|
|
"mean_token_accuracy": 0.1613177850842476,
|
|
"num_tokens": 4372177.0,
|
|
"step": 1960
|
|
},
|
|
{
|
|
"entropy": 5.92481837272644,
|
|
"epoch": 0.2206997248273151,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004998668619791104,
|
|
"loss": 5.8547,
|
|
"mean_token_accuracy": 0.16234170347452165,
|
|
"num_tokens": 4382872.0,
|
|
"step": 1965
|
|
},
|
|
{
|
|
"entropy": 5.908624505996704,
|
|
"epoch": 0.22126130173527264,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004998654774356131,
|
|
"loss": 5.9559,
|
|
"mean_token_accuracy": 0.1552143692970276,
|
|
"num_tokens": 4393623.0,
|
|
"step": 1970
|
|
},
|
|
{
|
|
"entropy": 5.96333270072937,
|
|
"epoch": 0.2218228786432302,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004998640857323118,
|
|
"loss": 5.8898,
|
|
"mean_token_accuracy": 0.15621398091316224,
|
|
"num_tokens": 4404215.0,
|
|
"step": 1975
|
|
},
|
|
{
|
|
"entropy": 6.029521846771241,
|
|
"epoch": 0.22238445555118774,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004998626868692509,
|
|
"loss": 6.1434,
|
|
"mean_token_accuracy": 0.15685454457998277,
|
|
"num_tokens": 4415978.0,
|
|
"step": 1980
|
|
},
|
|
{
|
|
"entropy": 6.012211847305298,
|
|
"epoch": 0.2229460324591453,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004998612808464748,
|
|
"loss": 5.8877,
|
|
"mean_token_accuracy": 0.15981114357709886,
|
|
"num_tokens": 4427060.0,
|
|
"step": 1985
|
|
},
|
|
{
|
|
"entropy": 5.914674568176269,
|
|
"epoch": 0.22350760936710282,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004998598676640283,
|
|
"loss": 5.971,
|
|
"mean_token_accuracy": 0.156388621032238,
|
|
"num_tokens": 4438145.0,
|
|
"step": 1990
|
|
},
|
|
{
|
|
"entropy": 6.117107343673706,
|
|
"epoch": 0.22406918627506037,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004998584473219563,
|
|
"loss": 6.0468,
|
|
"mean_token_accuracy": 0.1594668760895729,
|
|
"num_tokens": 4449324.0,
|
|
"step": 1995
|
|
},
|
|
{
|
|
"entropy": 5.848163843154907,
|
|
"epoch": 0.22463076318301792,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004998570198203043,
|
|
"loss": 5.7684,
|
|
"mean_token_accuracy": 0.16067076921463014,
|
|
"num_tokens": 4459728.0,
|
|
"step": 2000
|
|
},
|
|
{
|
|
"entropy": 5.908514308929443,
|
|
"epoch": 0.22519234009097547,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004998555851591175,
|
|
"loss": 5.9773,
|
|
"mean_token_accuracy": 0.16138978004455568,
|
|
"num_tokens": 4471164.0,
|
|
"step": 2005
|
|
},
|
|
{
|
|
"entropy": 6.021873474121094,
|
|
"epoch": 0.225753916998933,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004998541433384416,
|
|
"loss": 6.0352,
|
|
"mean_token_accuracy": 0.15729770064353943,
|
|
"num_tokens": 4483349.0,
|
|
"step": 2010
|
|
},
|
|
{
|
|
"entropy": 6.085103368759155,
|
|
"epoch": 0.22631549390689054,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004998526943583226,
|
|
"loss": 6.0037,
|
|
"mean_token_accuracy": 0.15304621160030366,
|
|
"num_tokens": 4495311.0,
|
|
"step": 2015
|
|
},
|
|
{
|
|
"entropy": 5.900832271575927,
|
|
"epoch": 0.2268770708148481,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004998512382188066,
|
|
"loss": 5.9293,
|
|
"mean_token_accuracy": 0.16477998793125154,
|
|
"num_tokens": 4507017.0,
|
|
"step": 2020
|
|
},
|
|
{
|
|
"entropy": 5.960407686233521,
|
|
"epoch": 0.22743864772280564,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004998497749199401,
|
|
"loss": 5.9688,
|
|
"mean_token_accuracy": 0.15732726454734802,
|
|
"num_tokens": 4517746.0,
|
|
"step": 2025
|
|
},
|
|
{
|
|
"entropy": 6.0614457607269285,
|
|
"epoch": 0.2280002246307632,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004998483044617694,
|
|
"loss": 6.0633,
|
|
"mean_token_accuracy": 0.15260435193777083,
|
|
"num_tokens": 4529149.0,
|
|
"step": 2030
|
|
},
|
|
{
|
|
"entropy": 5.929168272018432,
|
|
"epoch": 0.22856180153872072,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004998468268443416,
|
|
"loss": 5.9371,
|
|
"mean_token_accuracy": 0.1589831829071045,
|
|
"num_tokens": 4540630.0,
|
|
"step": 2035
|
|
},
|
|
{
|
|
"entropy": 5.85460319519043,
|
|
"epoch": 0.22912337844667827,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004998453420677034,
|
|
"loss": 5.8672,
|
|
"mean_token_accuracy": 0.1566688224673271,
|
|
"num_tokens": 4552877.0,
|
|
"step": 2040
|
|
},
|
|
{
|
|
"entropy": 6.016587114334106,
|
|
"epoch": 0.22968495535463582,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998438501319025,
|
|
"loss": 5.9635,
|
|
"mean_token_accuracy": 0.16212720274925232,
|
|
"num_tokens": 4563634.0,
|
|
"step": 2045
|
|
},
|
|
{
|
|
"entropy": 5.904137372970581,
|
|
"epoch": 0.23024653226259337,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998423510369862,
|
|
"loss": 5.8992,
|
|
"mean_token_accuracy": 0.16215125918388368,
|
|
"num_tokens": 4574007.0,
|
|
"step": 2050
|
|
},
|
|
{
|
|
"entropy": 5.954766511917114,
|
|
"epoch": 0.23080810917055092,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004998408447830022,
|
|
"loss": 5.911,
|
|
"mean_token_accuracy": 0.1593327283859253,
|
|
"num_tokens": 4584146.0,
|
|
"step": 2055
|
|
},
|
|
{
|
|
"entropy": 5.965726757049561,
|
|
"epoch": 0.23136968607850844,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004998393313699985,
|
|
"loss": 5.9217,
|
|
"mean_token_accuracy": 0.15980084091424943,
|
|
"num_tokens": 4594839.0,
|
|
"step": 2060
|
|
},
|
|
{
|
|
"entropy": 6.105428791046142,
|
|
"epoch": 0.231931262986466,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004998378107980233,
|
|
"loss": 6.0798,
|
|
"mean_token_accuracy": 0.14904378205537797,
|
|
"num_tokens": 4608229.0,
|
|
"step": 2065
|
|
},
|
|
{
|
|
"entropy": 5.952469778060913,
|
|
"epoch": 0.23249283989442354,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004998362830671249,
|
|
"loss": 5.8784,
|
|
"mean_token_accuracy": 0.15615165382623672,
|
|
"num_tokens": 4619206.0,
|
|
"step": 2070
|
|
},
|
|
{
|
|
"entropy": 5.863278198242187,
|
|
"epoch": 0.2330544168023811,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004998347481773522,
|
|
"loss": 5.9249,
|
|
"mean_token_accuracy": 0.16034539192914962,
|
|
"num_tokens": 4628966.0,
|
|
"step": 2075
|
|
},
|
|
{
|
|
"entropy": 5.915069961547852,
|
|
"epoch": 0.23361599371033864,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004998332061287538,
|
|
"loss": 5.8112,
|
|
"mean_token_accuracy": 0.15875162035226822,
|
|
"num_tokens": 4639935.0,
|
|
"step": 2080
|
|
},
|
|
{
|
|
"entropy": 6.008445787429809,
|
|
"epoch": 0.23417757061829617,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000499831656921379,
|
|
"loss": 6.0489,
|
|
"mean_token_accuracy": 0.1555440604686737,
|
|
"num_tokens": 4651998.0,
|
|
"step": 2085
|
|
},
|
|
{
|
|
"entropy": 6.036960220336914,
|
|
"epoch": 0.23473914752625372,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.000499830100555277,
|
|
"loss": 6.0192,
|
|
"mean_token_accuracy": 0.1560396894812584,
|
|
"num_tokens": 4664002.0,
|
|
"step": 2090
|
|
},
|
|
{
|
|
"entropy": 5.941565656661988,
|
|
"epoch": 0.23530072443421127,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004998285370304974,
|
|
"loss": 5.9088,
|
|
"mean_token_accuracy": 0.1645731508731842,
|
|
"num_tokens": 4675343.0,
|
|
"step": 2095
|
|
},
|
|
{
|
|
"entropy": 5.974581003189087,
|
|
"epoch": 0.23586230134216882,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00049982696634709,
|
|
"loss": 5.9546,
|
|
"mean_token_accuracy": 0.16146257668733596,
|
|
"num_tokens": 4686410.0,
|
|
"step": 2100
|
|
},
|
|
{
|
|
"entropy": 5.937360239028931,
|
|
"epoch": 0.23642387825012637,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004998253885051048,
|
|
"loss": 5.984,
|
|
"mean_token_accuracy": 0.1578327551484108,
|
|
"num_tokens": 4697768.0,
|
|
"step": 2105
|
|
},
|
|
{
|
|
"entropy": 6.069368505477906,
|
|
"epoch": 0.2369854551580839,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000499823803504592,
|
|
"loss": 5.993,
|
|
"mean_token_accuracy": 0.15976879000663757,
|
|
"num_tokens": 4709933.0,
|
|
"step": 2110
|
|
},
|
|
{
|
|
"entropy": 5.981991481781006,
|
|
"epoch": 0.23754703206604144,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004998222113456022,
|
|
"loss": 6.0305,
|
|
"mean_token_accuracy": 0.15242783725261688,
|
|
"num_tokens": 4721385.0,
|
|
"step": 2115
|
|
},
|
|
{
|
|
"entropy": 5.920117902755737,
|
|
"epoch": 0.238108608973999,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004998206120281858,
|
|
"loss": 5.8442,
|
|
"mean_token_accuracy": 0.1651250496506691,
|
|
"num_tokens": 4732562.0,
|
|
"step": 2120
|
|
},
|
|
{
|
|
"entropy": 5.845587635040284,
|
|
"epoch": 0.23867018588195654,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000499819005552394,
|
|
"loss": 5.8581,
|
|
"mean_token_accuracy": 0.15949287563562392,
|
|
"num_tokens": 4742794.0,
|
|
"step": 2125
|
|
},
|
|
{
|
|
"entropy": 5.866573333740234,
|
|
"epoch": 0.23923176278991407,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004998173919182779,
|
|
"loss": 5.8202,
|
|
"mean_token_accuracy": 0.16423655897378922,
|
|
"num_tokens": 4754903.0,
|
|
"step": 2130
|
|
},
|
|
{
|
|
"entropy": 5.91752257347107,
|
|
"epoch": 0.23979333969787162,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000499815771125889,
|
|
"loss": 5.8741,
|
|
"mean_token_accuracy": 0.1597582370042801,
|
|
"num_tokens": 4766165.0,
|
|
"step": 2135
|
|
},
|
|
{
|
|
"entropy": 5.860339212417602,
|
|
"epoch": 0.24035491660582917,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998141431752785,
|
|
"loss": 5.8838,
|
|
"mean_token_accuracy": 0.16476210951805115,
|
|
"num_tokens": 4776551.0,
|
|
"step": 2140
|
|
},
|
|
{
|
|
"entropy": 6.054014873504639,
|
|
"epoch": 0.24091649351378672,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004998125080664987,
|
|
"loss": 6.067,
|
|
"mean_token_accuracy": 0.1543096624314785,
|
|
"num_tokens": 4788344.0,
|
|
"step": 2145
|
|
},
|
|
{
|
|
"entropy": 5.984238958358764,
|
|
"epoch": 0.24147807042174427,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998108657996012,
|
|
"loss": 5.8624,
|
|
"mean_token_accuracy": 0.1560610830783844,
|
|
"num_tokens": 4799314.0,
|
|
"step": 2150
|
|
},
|
|
{
|
|
"entropy": 5.885314512252807,
|
|
"epoch": 0.2420396473297018,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004998092163746387,
|
|
"loss": 5.9116,
|
|
"mean_token_accuracy": 0.16344153732061387,
|
|
"num_tokens": 4809588.0,
|
|
"step": 2155
|
|
},
|
|
{
|
|
"entropy": 5.870743465423584,
|
|
"epoch": 0.24260122423765934,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004998075597916636,
|
|
"loss": 5.7357,
|
|
"mean_token_accuracy": 0.16858597844839096,
|
|
"num_tokens": 4820076.0,
|
|
"step": 2160
|
|
},
|
|
{
|
|
"entropy": 5.9259528636932375,
|
|
"epoch": 0.2431628011456169,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004998058960507286,
|
|
"loss": 6.0033,
|
|
"mean_token_accuracy": 0.1558015376329422,
|
|
"num_tokens": 4831504.0,
|
|
"step": 2165
|
|
},
|
|
{
|
|
"entropy": 5.880033540725708,
|
|
"epoch": 0.24372437805357444,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004998042251518866,
|
|
"loss": 5.8649,
|
|
"mean_token_accuracy": 0.1617542490363121,
|
|
"num_tokens": 4842826.0,
|
|
"step": 2170
|
|
},
|
|
{
|
|
"entropy": 5.8402345180511475,
|
|
"epoch": 0.244285954961532,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004998025470951908,
|
|
"loss": 5.8465,
|
|
"mean_token_accuracy": 0.1644066721200943,
|
|
"num_tokens": 4853279.0,
|
|
"step": 2175
|
|
},
|
|
{
|
|
"entropy": 5.966151905059815,
|
|
"epoch": 0.24484753186948952,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004998008618806949,
|
|
"loss": 5.8979,
|
|
"mean_token_accuracy": 0.16503124088048934,
|
|
"num_tokens": 4863332.0,
|
|
"step": 2180
|
|
},
|
|
{
|
|
"entropy": 5.958868360519409,
|
|
"epoch": 0.24540910877744707,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004997991695084523,
|
|
"loss": 6.0339,
|
|
"mean_token_accuracy": 0.1506052479147911,
|
|
"num_tokens": 4874217.0,
|
|
"step": 2185
|
|
},
|
|
{
|
|
"entropy": 6.0297637462615965,
|
|
"epoch": 0.24597068568540462,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004997974699785169,
|
|
"loss": 5.881,
|
|
"mean_token_accuracy": 0.162646321952343,
|
|
"num_tokens": 4885322.0,
|
|
"step": 2190
|
|
},
|
|
{
|
|
"entropy": 5.715388011932373,
|
|
"epoch": 0.24653226259336217,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004997957632909429,
|
|
"loss": 5.8452,
|
|
"mean_token_accuracy": 0.15895508527755736,
|
|
"num_tokens": 4895546.0,
|
|
"step": 2195
|
|
},
|
|
{
|
|
"entropy": 6.107920455932617,
|
|
"epoch": 0.24709383950131972,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004997940494457846,
|
|
"loss": 6.0395,
|
|
"mean_token_accuracy": 0.15601962208747863,
|
|
"num_tokens": 4906957.0,
|
|
"step": 2200
|
|
},
|
|
{
|
|
"entropy": 6.023680686950684,
|
|
"epoch": 0.24765541640927724,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004997923284430967,
|
|
"loss": 5.9557,
|
|
"mean_token_accuracy": 0.15208095461130142,
|
|
"num_tokens": 4917965.0,
|
|
"step": 2205
|
|
},
|
|
{
|
|
"entropy": 5.857148885726929,
|
|
"epoch": 0.2482169933172348,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004997906002829338,
|
|
"loss": 5.8617,
|
|
"mean_token_accuracy": 0.1620682030916214,
|
|
"num_tokens": 4928585.0,
|
|
"step": 2210
|
|
},
|
|
{
|
|
"entropy": 5.891238260269165,
|
|
"epoch": 0.24877857022519234,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.000499788864965351,
|
|
"loss": 5.8717,
|
|
"mean_token_accuracy": 0.15956535786390305,
|
|
"num_tokens": 4939818.0,
|
|
"step": 2215
|
|
},
|
|
{
|
|
"entropy": 5.967899799346924,
|
|
"epoch": 0.2493401471331499,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004997871224904036,
|
|
"loss": 5.9513,
|
|
"mean_token_accuracy": 0.15834061205387115,
|
|
"num_tokens": 4951752.0,
|
|
"step": 2220
|
|
},
|
|
{
|
|
"entropy": 5.793693161010742,
|
|
"epoch": 0.24990172404110744,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004997853728581468,
|
|
"loss": 5.7895,
|
|
"mean_token_accuracy": 0.1681654319167137,
|
|
"num_tokens": 4961846.0,
|
|
"step": 2225
|
|
},
|
|
{
|
|
"entropy": 5.945404481887818,
|
|
"epoch": 0.250463300949065,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004997836160686368,
|
|
"loss": 5.9361,
|
|
"mean_token_accuracy": 0.15449708849191665,
|
|
"num_tokens": 4973693.0,
|
|
"step": 2230
|
|
},
|
|
{
|
|
"entropy": 5.915171194076538,
|
|
"epoch": 0.25102487785702254,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004997818521219291,
|
|
"loss": 5.8589,
|
|
"mean_token_accuracy": 0.1630162000656128,
|
|
"num_tokens": 4986156.0,
|
|
"step": 2235
|
|
},
|
|
{
|
|
"entropy": 5.906194400787354,
|
|
"epoch": 0.25158645476498004,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004997800810180803,
|
|
"loss": 5.9333,
|
|
"mean_token_accuracy": 0.1587043434381485,
|
|
"num_tokens": 4997615.0,
|
|
"step": 2240
|
|
},
|
|
{
|
|
"entropy": 5.911606407165527,
|
|
"epoch": 0.2521480316729376,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004997783027571464,
|
|
"loss": 5.8738,
|
|
"mean_token_accuracy": 0.1615534693002701,
|
|
"num_tokens": 5007655.0,
|
|
"step": 2245
|
|
},
|
|
{
|
|
"entropy": 5.969314908981323,
|
|
"epoch": 0.25270960858089514,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004997765173391841,
|
|
"loss": 5.9367,
|
|
"mean_token_accuracy": 0.16165156960487365,
|
|
"num_tokens": 5018933.0,
|
|
"step": 2250
|
|
},
|
|
{
|
|
"entropy": 6.040049314498901,
|
|
"epoch": 0.2532711854888527,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004997747247642505,
|
|
"loss": 5.9383,
|
|
"mean_token_accuracy": 0.1602029874920845,
|
|
"num_tokens": 5030495.0,
|
|
"step": 2255
|
|
},
|
|
{
|
|
"entropy": 5.842279529571533,
|
|
"epoch": 0.25383276239681024,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004997729250324023,
|
|
"loss": 5.9816,
|
|
"mean_token_accuracy": 0.15450992733240126,
|
|
"num_tokens": 5041553.0,
|
|
"step": 2260
|
|
},
|
|
{
|
|
"entropy": 5.963804531097412,
|
|
"epoch": 0.2543943393047678,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004997711181436971,
|
|
"loss": 5.9114,
|
|
"mean_token_accuracy": 0.16113370209932326,
|
|
"num_tokens": 5052312.0,
|
|
"step": 2265
|
|
},
|
|
{
|
|
"entropy": 6.014153528213501,
|
|
"epoch": 0.25495591621272534,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004997693040981922,
|
|
"loss": 6.0888,
|
|
"mean_token_accuracy": 0.1531001329421997,
|
|
"num_tokens": 5063445.0,
|
|
"step": 2270
|
|
},
|
|
{
|
|
"entropy": 6.010663318634033,
|
|
"epoch": 0.2555174931206829,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004997674828959456,
|
|
"loss": 5.8763,
|
|
"mean_token_accuracy": 0.16219639629125596,
|
|
"num_tokens": 5073052.0,
|
|
"step": 2275
|
|
},
|
|
{
|
|
"entropy": 5.857589530944824,
|
|
"epoch": 0.25607907002864044,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004997656545370151,
|
|
"loss": 5.9201,
|
|
"mean_token_accuracy": 0.16253976821899413,
|
|
"num_tokens": 5084174.0,
|
|
"step": 2280
|
|
},
|
|
{
|
|
"entropy": 6.022715759277344,
|
|
"epoch": 0.256640646936598,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000499763819021459,
|
|
"loss": 5.9051,
|
|
"mean_token_accuracy": 0.16299960166215896,
|
|
"num_tokens": 5094106.0,
|
|
"step": 2285
|
|
},
|
|
{
|
|
"entropy": 5.972675132751465,
|
|
"epoch": 0.2572022238445555,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004997619763493357,
|
|
"loss": 5.9997,
|
|
"mean_token_accuracy": 0.16121359914541245,
|
|
"num_tokens": 5106963.0,
|
|
"step": 2290
|
|
},
|
|
{
|
|
"entropy": 5.864818668365478,
|
|
"epoch": 0.25776380075251304,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.000499760126520704,
|
|
"loss": 5.7925,
|
|
"mean_token_accuracy": 0.15583763271570206,
|
|
"num_tokens": 5119476.0,
|
|
"step": 2295
|
|
},
|
|
{
|
|
"entropy": 5.973382377624512,
|
|
"epoch": 0.2583253776604706,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004997582695356225,
|
|
"loss": 6.0256,
|
|
"mean_token_accuracy": 0.15469253659248353,
|
|
"num_tokens": 5132169.0,
|
|
"step": 2300
|
|
},
|
|
{
|
|
"entropy": 5.877126216888428,
|
|
"epoch": 0.25888695456842814,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004997564053941507,
|
|
"loss": 5.8854,
|
|
"mean_token_accuracy": 0.16001738011837005,
|
|
"num_tokens": 5143354.0,
|
|
"step": 2305
|
|
},
|
|
{
|
|
"entropy": 5.895409488677979,
|
|
"epoch": 0.2594485314763857,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004997545340963478,
|
|
"loss": 5.9458,
|
|
"mean_token_accuracy": 0.15308494120836258,
|
|
"num_tokens": 5154624.0,
|
|
"step": 2310
|
|
},
|
|
{
|
|
"entropy": 5.987952375411988,
|
|
"epoch": 0.26001010838434324,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004997526556422733,
|
|
"loss": 5.8418,
|
|
"mean_token_accuracy": 0.16011188477277755,
|
|
"num_tokens": 5165349.0,
|
|
"step": 2315
|
|
},
|
|
{
|
|
"entropy": 5.847837829589844,
|
|
"epoch": 0.2605716852923008,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004997507700319872,
|
|
"loss": 5.9174,
|
|
"mean_token_accuracy": 0.16073694676160813,
|
|
"num_tokens": 5175874.0,
|
|
"step": 2320
|
|
},
|
|
{
|
|
"entropy": 5.864932250976563,
|
|
"epoch": 0.26113326220025834,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004997488772655492,
|
|
"loss": 5.8153,
|
|
"mean_token_accuracy": 0.16911125481128692,
|
|
"num_tokens": 5186591.0,
|
|
"step": 2325
|
|
},
|
|
{
|
|
"entropy": 5.867122650146484,
|
|
"epoch": 0.2616948391082159,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004997469773430199,
|
|
"loss": 5.9228,
|
|
"mean_token_accuracy": 0.16698685735464097,
|
|
"num_tokens": 5197307.0,
|
|
"step": 2330
|
|
},
|
|
{
|
|
"entropy": 5.876765441894531,
|
|
"epoch": 0.2622564160161734,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004997450702644596,
|
|
"loss": 5.8734,
|
|
"mean_token_accuracy": 0.16059717684984207,
|
|
"num_tokens": 5209868.0,
|
|
"step": 2335
|
|
},
|
|
{
|
|
"entropy": 5.920298910140991,
|
|
"epoch": 0.26281799292413094,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004997431560299292,
|
|
"loss": 5.8907,
|
|
"mean_token_accuracy": 0.16422481536865235,
|
|
"num_tokens": 5220365.0,
|
|
"step": 2340
|
|
},
|
|
{
|
|
"entropy": 5.885955953598023,
|
|
"epoch": 0.2633795698320885,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004997412346394894,
|
|
"loss": 5.8033,
|
|
"mean_token_accuracy": 0.16235794126987457,
|
|
"num_tokens": 5231575.0,
|
|
"step": 2345
|
|
},
|
|
{
|
|
"entropy": 5.947313213348389,
|
|
"epoch": 0.26394114674004604,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004997393060932017,
|
|
"loss": 5.887,
|
|
"mean_token_accuracy": 0.16234982758760452,
|
|
"num_tokens": 5241852.0,
|
|
"step": 2350
|
|
},
|
|
{
|
|
"entropy": 5.920132827758789,
|
|
"epoch": 0.2645027236480036,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004997373703911273,
|
|
"loss": 5.9284,
|
|
"mean_token_accuracy": 0.16154667288064956,
|
|
"num_tokens": 5254536.0,
|
|
"step": 2355
|
|
},
|
|
{
|
|
"entropy": 5.923627662658691,
|
|
"epoch": 0.26506430055596114,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004997354275333277,
|
|
"loss": 5.8557,
|
|
"mean_token_accuracy": 0.1607941135764122,
|
|
"num_tokens": 5264946.0,
|
|
"step": 2360
|
|
},
|
|
{
|
|
"entropy": 5.686444616317749,
|
|
"epoch": 0.2656258774639187,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000499733477519865,
|
|
"loss": 5.6798,
|
|
"mean_token_accuracy": 0.16499558091163635,
|
|
"num_tokens": 5275527.0,
|
|
"step": 2365
|
|
},
|
|
{
|
|
"entropy": 5.865219974517823,
|
|
"epoch": 0.26618745437187624,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004997315203508013,
|
|
"loss": 5.8695,
|
|
"mean_token_accuracy": 0.15666571706533433,
|
|
"num_tokens": 5285471.0,
|
|
"step": 2370
|
|
},
|
|
{
|
|
"entropy": 5.798485612869262,
|
|
"epoch": 0.2667490312798338,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004997295560261988,
|
|
"loss": 5.7753,
|
|
"mean_token_accuracy": 0.1605561688542366,
|
|
"num_tokens": 5295743.0,
|
|
"step": 2375
|
|
},
|
|
{
|
|
"entropy": 5.981579542160034,
|
|
"epoch": 0.26731060818779134,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00049972758454612,
|
|
"loss": 5.9192,
|
|
"mean_token_accuracy": 0.15332525223493576,
|
|
"num_tokens": 5307963.0,
|
|
"step": 2380
|
|
},
|
|
{
|
|
"entropy": 5.880096340179444,
|
|
"epoch": 0.26787218509574884,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004997256059106279,
|
|
"loss": 5.8074,
|
|
"mean_token_accuracy": 0.16239653378725052,
|
|
"num_tokens": 5318394.0,
|
|
"step": 2385
|
|
},
|
|
{
|
|
"entropy": 5.912300062179566,
|
|
"epoch": 0.2684337620037064,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004997236201197853,
|
|
"loss": 6.037,
|
|
"mean_token_accuracy": 0.14811042100191116,
|
|
"num_tokens": 5331728.0,
|
|
"step": 2390
|
|
},
|
|
{
|
|
"entropy": 5.964923286437989,
|
|
"epoch": 0.26899533891166394,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004997216271736554,
|
|
"loss": 5.922,
|
|
"mean_token_accuracy": 0.1677936553955078,
|
|
"num_tokens": 5342825.0,
|
|
"step": 2395
|
|
},
|
|
{
|
|
"entropy": 5.907764720916748,
|
|
"epoch": 0.2695569158196215,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004997196270723018,
|
|
"loss": 5.8239,
|
|
"mean_token_accuracy": 0.1624791741371155,
|
|
"num_tokens": 5354232.0,
|
|
"step": 2400
|
|
},
|
|
{
|
|
"entropy": 5.892585563659668,
|
|
"epoch": 0.27011849272757904,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004997176198157881,
|
|
"loss": 5.9215,
|
|
"mean_token_accuracy": 0.15687112659215927,
|
|
"num_tokens": 5364807.0,
|
|
"step": 2405
|
|
},
|
|
{
|
|
"entropy": 5.903974103927612,
|
|
"epoch": 0.2706800696355366,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004997156054041781,
|
|
"loss": 5.8953,
|
|
"mean_token_accuracy": 0.15242768228054046,
|
|
"num_tokens": 5375593.0,
|
|
"step": 2410
|
|
},
|
|
{
|
|
"entropy": 5.877764558792114,
|
|
"epoch": 0.27124164654349414,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004997135838375362,
|
|
"loss": 5.8406,
|
|
"mean_token_accuracy": 0.16519979536533355,
|
|
"num_tokens": 5386740.0,
|
|
"step": 2415
|
|
},
|
|
{
|
|
"entropy": 5.813501453399658,
|
|
"epoch": 0.2718032234514517,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004997115551159267,
|
|
"loss": 5.8211,
|
|
"mean_token_accuracy": 0.1626619353890419,
|
|
"num_tokens": 5397732.0,
|
|
"step": 2420
|
|
},
|
|
{
|
|
"entropy": 5.987624835968018,
|
|
"epoch": 0.27236480035940924,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000499709519239414,
|
|
"loss": 5.886,
|
|
"mean_token_accuracy": 0.15518247038125993,
|
|
"num_tokens": 5409392.0,
|
|
"step": 2425
|
|
},
|
|
{
|
|
"entropy": 5.722806978225708,
|
|
"epoch": 0.2729263772673668,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004997074762080632,
|
|
"loss": 5.8547,
|
|
"mean_token_accuracy": 0.16847770363092424,
|
|
"num_tokens": 5420903.0,
|
|
"step": 2430
|
|
},
|
|
{
|
|
"entropy": 5.803295469284057,
|
|
"epoch": 0.2734879541753243,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.000499705426021939,
|
|
"loss": 5.7793,
|
|
"mean_token_accuracy": 0.16043397933244705,
|
|
"num_tokens": 5432631.0,
|
|
"step": 2435
|
|
},
|
|
{
|
|
"entropy": 5.865436649322509,
|
|
"epoch": 0.27404953108328184,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000499703368681107,
|
|
"loss": 5.7477,
|
|
"mean_token_accuracy": 0.16816219240427016,
|
|
"num_tokens": 5443463.0,
|
|
"step": 2440
|
|
},
|
|
{
|
|
"entropy": 5.954450368881226,
|
|
"epoch": 0.2746111079912394,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004997013041856326,
|
|
"loss": 6.0624,
|
|
"mean_token_accuracy": 0.15737709179520606,
|
|
"num_tokens": 5455903.0,
|
|
"step": 2445
|
|
},
|
|
{
|
|
"entropy": 5.9812792301177975,
|
|
"epoch": 0.27517268489919694,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004996992325355815,
|
|
"loss": 5.8839,
|
|
"mean_token_accuracy": 0.15456786453723909,
|
|
"num_tokens": 5467201.0,
|
|
"step": 2450
|
|
},
|
|
{
|
|
"entropy": 5.89325475692749,
|
|
"epoch": 0.2757342618071545,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004996971537310198,
|
|
"loss": 5.7582,
|
|
"mean_token_accuracy": 0.16121137291193008,
|
|
"num_tokens": 5478109.0,
|
|
"step": 2455
|
|
},
|
|
{
|
|
"entropy": 5.869486522674561,
|
|
"epoch": 0.27629583871511204,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004996950677720133,
|
|
"loss": 5.8984,
|
|
"mean_token_accuracy": 0.1576277181506157,
|
|
"num_tokens": 5489621.0,
|
|
"step": 2460
|
|
},
|
|
{
|
|
"entropy": 5.821279716491699,
|
|
"epoch": 0.2768574156230696,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.000499692974658629,
|
|
"loss": 5.8327,
|
|
"mean_token_accuracy": 0.16300647109746932,
|
|
"num_tokens": 5500606.0,
|
|
"step": 2465
|
|
},
|
|
{
|
|
"entropy": 5.920242738723755,
|
|
"epoch": 0.27741899253102714,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004996908743909331,
|
|
"loss": 5.7813,
|
|
"mean_token_accuracy": 0.1680440992116928,
|
|
"num_tokens": 5510768.0,
|
|
"step": 2470
|
|
},
|
|
{
|
|
"entropy": 5.775556421279907,
|
|
"epoch": 0.2779805694389847,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004996887669689926,
|
|
"loss": 5.7973,
|
|
"mean_token_accuracy": 0.16250731498003007,
|
|
"num_tokens": 5522210.0,
|
|
"step": 2475
|
|
},
|
|
{
|
|
"entropy": 5.893093776702881,
|
|
"epoch": 0.2785421463469422,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004996866523928747,
|
|
"loss": 5.931,
|
|
"mean_token_accuracy": 0.1568371132016182,
|
|
"num_tokens": 5533055.0,
|
|
"step": 2480
|
|
},
|
|
{
|
|
"entropy": 5.997058773040772,
|
|
"epoch": 0.27910372325489974,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004996845306626467,
|
|
"loss": 5.9507,
|
|
"mean_token_accuracy": 0.15390594601631163,
|
|
"num_tokens": 5544345.0,
|
|
"step": 2485
|
|
},
|
|
{
|
|
"entropy": 5.914350700378418,
|
|
"epoch": 0.2796653001628573,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004996824017783759,
|
|
"loss": 5.8473,
|
|
"mean_token_accuracy": 0.15839995592832565,
|
|
"num_tokens": 5556734.0,
|
|
"step": 2490
|
|
},
|
|
{
|
|
"entropy": 5.818574714660644,
|
|
"epoch": 0.28022687707081484,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004996802657401304,
|
|
"loss": 5.8816,
|
|
"mean_token_accuracy": 0.16247260347008705,
|
|
"num_tokens": 5566874.0,
|
|
"step": 2495
|
|
},
|
|
{
|
|
"entropy": 5.952364873886109,
|
|
"epoch": 0.2807884539787724,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004996781225479781,
|
|
"loss": 5.8857,
|
|
"mean_token_accuracy": 0.1558615043759346,
|
|
"num_tokens": 5578812.0,
|
|
"step": 2500
|
|
},
|
|
{
|
|
"entropy": 5.894041633605957,
|
|
"epoch": 0.28135003088672994,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004996759722019872,
|
|
"loss": 5.9373,
|
|
"mean_token_accuracy": 0.1599496230483055,
|
|
"num_tokens": 5590021.0,
|
|
"step": 2505
|
|
},
|
|
{
|
|
"entropy": 5.947154235839844,
|
|
"epoch": 0.2819116077946875,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004996738147022262,
|
|
"loss": 5.9428,
|
|
"mean_token_accuracy": 0.15261465460062026,
|
|
"num_tokens": 5600921.0,
|
|
"step": 2510
|
|
},
|
|
{
|
|
"entropy": 5.871411657333374,
|
|
"epoch": 0.28247318470264504,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004996716500487638,
|
|
"loss": 5.8606,
|
|
"mean_token_accuracy": 0.1596810534596443,
|
|
"num_tokens": 5610615.0,
|
|
"step": 2515
|
|
},
|
|
{
|
|
"entropy": 5.800993251800537,
|
|
"epoch": 0.2830347616106026,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000499669478241669,
|
|
"loss": 5.7878,
|
|
"mean_token_accuracy": 0.16247710585594177,
|
|
"num_tokens": 5621596.0,
|
|
"step": 2520
|
|
},
|
|
{
|
|
"entropy": 5.969037485122681,
|
|
"epoch": 0.28359633851856014,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004996672992810108,
|
|
"loss": 5.8243,
|
|
"mean_token_accuracy": 0.16356842517852782,
|
|
"num_tokens": 5633047.0,
|
|
"step": 2525
|
|
},
|
|
{
|
|
"entropy": 5.798973751068115,
|
|
"epoch": 0.28415791542651764,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004996651131668587,
|
|
"loss": 5.8104,
|
|
"mean_token_accuracy": 0.16191127747297288,
|
|
"num_tokens": 5644970.0,
|
|
"step": 2530
|
|
},
|
|
{
|
|
"entropy": 5.87383804321289,
|
|
"epoch": 0.2847194923344752,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004996629198992823,
|
|
"loss": 5.9332,
|
|
"mean_token_accuracy": 0.15747836232185364,
|
|
"num_tokens": 5656631.0,
|
|
"step": 2535
|
|
},
|
|
{
|
|
"entropy": 5.888602876663208,
|
|
"epoch": 0.28528106924243274,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004996607194783513,
|
|
"loss": 5.8852,
|
|
"mean_token_accuracy": 0.1580764904618263,
|
|
"num_tokens": 5668808.0,
|
|
"step": 2540
|
|
},
|
|
{
|
|
"entropy": 5.818170499801636,
|
|
"epoch": 0.2858426461503903,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004996585119041359,
|
|
"loss": 5.827,
|
|
"mean_token_accuracy": 0.1570512518286705,
|
|
"num_tokens": 5679493.0,
|
|
"step": 2545
|
|
},
|
|
{
|
|
"entropy": 5.916708993911743,
|
|
"epoch": 0.28640422305834784,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004996562971767063,
|
|
"loss": 5.8515,
|
|
"mean_token_accuracy": 0.16539256125688553,
|
|
"num_tokens": 5689879.0,
|
|
"step": 2550
|
|
},
|
|
{
|
|
"entropy": 5.871814250946045,
|
|
"epoch": 0.2869657999663054,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000499654075296133,
|
|
"loss": 5.9404,
|
|
"mean_token_accuracy": 0.16452383995056152,
|
|
"num_tokens": 5699934.0,
|
|
"step": 2555
|
|
},
|
|
{
|
|
"entropy": 5.8691713333129885,
|
|
"epoch": 0.28752737687426294,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000499651846262487,
|
|
"loss": 5.8705,
|
|
"mean_token_accuracy": 0.166011680662632,
|
|
"num_tokens": 5710171.0,
|
|
"step": 2560
|
|
},
|
|
{
|
|
"entropy": 5.884806299209595,
|
|
"epoch": 0.2880889537822205,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004996496100758389,
|
|
"loss": 5.8656,
|
|
"mean_token_accuracy": 0.15255345776677132,
|
|
"num_tokens": 5721190.0,
|
|
"step": 2565
|
|
},
|
|
{
|
|
"entropy": 6.02195897102356,
|
|
"epoch": 0.28865053069017804,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004996473667362604,
|
|
"loss": 5.9701,
|
|
"mean_token_accuracy": 0.15485327020287515,
|
|
"num_tokens": 5733706.0,
|
|
"step": 2570
|
|
},
|
|
{
|
|
"entropy": 5.805244255065918,
|
|
"epoch": 0.28921210759813554,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004996451162438224,
|
|
"loss": 5.9271,
|
|
"mean_token_accuracy": 0.15993860512971877,
|
|
"num_tokens": 5745712.0,
|
|
"step": 2575
|
|
},
|
|
{
|
|
"entropy": 5.781348705291748,
|
|
"epoch": 0.2897736845060931,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004996428585985967,
|
|
"loss": 5.74,
|
|
"mean_token_accuracy": 0.17483293563127517,
|
|
"num_tokens": 5757915.0,
|
|
"step": 2580
|
|
},
|
|
{
|
|
"entropy": 5.892542028427124,
|
|
"epoch": 0.29033526141405064,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004996405938006553,
|
|
"loss": 5.8859,
|
|
"mean_token_accuracy": 0.16429722160100937,
|
|
"num_tokens": 5768788.0,
|
|
"step": 2585
|
|
},
|
|
{
|
|
"entropy": 5.890336275100708,
|
|
"epoch": 0.2908968383220082,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004996383218500703,
|
|
"loss": 5.8128,
|
|
"mean_token_accuracy": 0.16249943375587464,
|
|
"num_tokens": 5779806.0,
|
|
"step": 2590
|
|
},
|
|
{
|
|
"entropy": 5.772500848770141,
|
|
"epoch": 0.29145841522996574,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000499636042746914,
|
|
"loss": 5.769,
|
|
"mean_token_accuracy": 0.16073892414569854,
|
|
"num_tokens": 5790177.0,
|
|
"step": 2595
|
|
},
|
|
{
|
|
"entropy": 5.839260911941528,
|
|
"epoch": 0.2920199921379233,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000499633756491259,
|
|
"loss": 5.8105,
|
|
"mean_token_accuracy": 0.16765276491641998,
|
|
"num_tokens": 5800251.0,
|
|
"step": 2600
|
|
},
|
|
{
|
|
"entropy": 5.935009479522705,
|
|
"epoch": 0.29258156904588084,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004996314630831781,
|
|
"loss": 5.8968,
|
|
"mean_token_accuracy": 0.16182940155267717,
|
|
"num_tokens": 5812210.0,
|
|
"step": 2605
|
|
},
|
|
{
|
|
"entropy": 5.87156400680542,
|
|
"epoch": 0.2931431459538384,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004996291625227443,
|
|
"loss": 5.8769,
|
|
"mean_token_accuracy": 0.16384392827749253,
|
|
"num_tokens": 5823280.0,
|
|
"step": 2610
|
|
},
|
|
{
|
|
"entropy": 5.972989130020141,
|
|
"epoch": 0.29370472286179594,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004996268548100307,
|
|
"loss": 5.951,
|
|
"mean_token_accuracy": 0.1541149839758873,
|
|
"num_tokens": 5835076.0,
|
|
"step": 2615
|
|
},
|
|
{
|
|
"entropy": 5.791325569152832,
|
|
"epoch": 0.2942662997697535,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000499624539945111,
|
|
"loss": 5.7486,
|
|
"mean_token_accuracy": 0.16788308024406434,
|
|
"num_tokens": 5845376.0,
|
|
"step": 2620
|
|
},
|
|
{
|
|
"entropy": 5.746144151687622,
|
|
"epoch": 0.294827876677711,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004996222179280589,
|
|
"loss": 5.7775,
|
|
"mean_token_accuracy": 0.16059013456106186,
|
|
"num_tokens": 5857124.0,
|
|
"step": 2625
|
|
},
|
|
{
|
|
"entropy": 5.954985284805298,
|
|
"epoch": 0.29538945358566854,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004996198887589481,
|
|
"loss": 5.8689,
|
|
"mean_token_accuracy": 0.15687937289476395,
|
|
"num_tokens": 5868681.0,
|
|
"step": 2630
|
|
},
|
|
{
|
|
"entropy": 5.871660566329956,
|
|
"epoch": 0.2959510304936261,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004996175524378531,
|
|
"loss": 5.8737,
|
|
"mean_token_accuracy": 0.16142140179872513,
|
|
"num_tokens": 5880532.0,
|
|
"step": 2635
|
|
},
|
|
{
|
|
"entropy": 5.9063619613647464,
|
|
"epoch": 0.29651260740158364,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000499615208964848,
|
|
"loss": 5.8278,
|
|
"mean_token_accuracy": 0.1647784188389778,
|
|
"num_tokens": 5891582.0,
|
|
"step": 2640
|
|
},
|
|
{
|
|
"entropy": 5.830147123336792,
|
|
"epoch": 0.2970741843095412,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004996128583400077,
|
|
"loss": 5.8292,
|
|
"mean_token_accuracy": 0.15877834409475328,
|
|
"num_tokens": 5903543.0,
|
|
"step": 2645
|
|
},
|
|
{
|
|
"entropy": 5.811954116821289,
|
|
"epoch": 0.29763576121749874,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004996105005634066,
|
|
"loss": 5.8006,
|
|
"mean_token_accuracy": 0.16823345720767974,
|
|
"num_tokens": 5913140.0,
|
|
"step": 2650
|
|
},
|
|
{
|
|
"entropy": 5.814200782775879,
|
|
"epoch": 0.2981973381254563,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004996081356351202,
|
|
"loss": 5.7642,
|
|
"mean_token_accuracy": 0.16816403865814208,
|
|
"num_tokens": 5924010.0,
|
|
"step": 2655
|
|
},
|
|
{
|
|
"entropy": 5.857581901550293,
|
|
"epoch": 0.29875891503341384,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004996057635552237,
|
|
"loss": 5.9688,
|
|
"mean_token_accuracy": 0.1579844906926155,
|
|
"num_tokens": 5936246.0,
|
|
"step": 2660
|
|
},
|
|
{
|
|
"entropy": 5.925976657867432,
|
|
"epoch": 0.2993204919413714,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004996033843237925,
|
|
"loss": 5.859,
|
|
"mean_token_accuracy": 0.1524143025279045,
|
|
"num_tokens": 5947594.0,
|
|
"step": 2665
|
|
},
|
|
{
|
|
"entropy": 5.971056890487671,
|
|
"epoch": 0.29988206884932894,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004996009979409025,
|
|
"loss": 5.7942,
|
|
"mean_token_accuracy": 0.15486442297697067,
|
|
"num_tokens": 5957660.0,
|
|
"step": 2670
|
|
},
|
|
{
|
|
"entropy": 5.631026124954223,
|
|
"epoch": 0.30044364575728644,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004995986044066295,
|
|
"loss": 5.6228,
|
|
"mean_token_accuracy": 0.17383519262075425,
|
|
"num_tokens": 5968881.0,
|
|
"step": 2675
|
|
},
|
|
{
|
|
"entropy": 5.839225244522095,
|
|
"epoch": 0.301005222665244,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00049959620372105,
|
|
"loss": 5.7885,
|
|
"mean_token_accuracy": 0.16763374209403992,
|
|
"num_tokens": 5980032.0,
|
|
"step": 2680
|
|
},
|
|
{
|
|
"entropy": 5.758896398544311,
|
|
"epoch": 0.30156679957320154,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004995937958842401,
|
|
"loss": 5.8011,
|
|
"mean_token_accuracy": 0.1621689423918724,
|
|
"num_tokens": 5991781.0,
|
|
"step": 2685
|
|
},
|
|
{
|
|
"entropy": 5.819126558303833,
|
|
"epoch": 0.3021283764811591,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004995913808962767,
|
|
"loss": 5.8394,
|
|
"mean_token_accuracy": 0.16058890372514725,
|
|
"num_tokens": 6002303.0,
|
|
"step": 2690
|
|
},
|
|
{
|
|
"entropy": 5.966246271133423,
|
|
"epoch": 0.30268995338911664,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004995889587572366,
|
|
"loss": 5.917,
|
|
"mean_token_accuracy": 0.16286829859018326,
|
|
"num_tokens": 6011523.0,
|
|
"step": 2695
|
|
},
|
|
{
|
|
"entropy": 5.872964239120483,
|
|
"epoch": 0.3032515302970742,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.000499586529467197,
|
|
"loss": 5.7196,
|
|
"mean_token_accuracy": 0.16652795672416687,
|
|
"num_tokens": 6022169.0,
|
|
"step": 2700
|
|
},
|
|
{
|
|
"entropy": 5.7077781677246096,
|
|
"epoch": 0.30381310720503174,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004995840930262351,
|
|
"loss": 5.79,
|
|
"mean_token_accuracy": 0.16523944810032845,
|
|
"num_tokens": 6033393.0,
|
|
"step": 2705
|
|
},
|
|
{
|
|
"entropy": 5.892653083801269,
|
|
"epoch": 0.3043746841129893,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004995816494344287,
|
|
"loss": 5.8429,
|
|
"mean_token_accuracy": 0.15828568935394288,
|
|
"num_tokens": 6045365.0,
|
|
"step": 2710
|
|
},
|
|
{
|
|
"entropy": 5.85001220703125,
|
|
"epoch": 0.30493626102094684,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004995791986918554,
|
|
"loss": 5.868,
|
|
"mean_token_accuracy": 0.16434365063905715,
|
|
"num_tokens": 6057482.0,
|
|
"step": 2715
|
|
},
|
|
{
|
|
"entropy": 5.8889617919921875,
|
|
"epoch": 0.30549783792890434,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004995767407985933,
|
|
"loss": 5.782,
|
|
"mean_token_accuracy": 0.16390661150217056,
|
|
"num_tokens": 6068194.0,
|
|
"step": 2720
|
|
},
|
|
{
|
|
"entropy": 5.786661911010742,
|
|
"epoch": 0.3060594148368619,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004995742757547207,
|
|
"loss": 5.8248,
|
|
"mean_token_accuracy": 0.1641546294093132,
|
|
"num_tokens": 6080540.0,
|
|
"step": 2725
|
|
},
|
|
{
|
|
"entropy": 5.798826599121094,
|
|
"epoch": 0.30662099174481944,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.000499571803560316,
|
|
"loss": 5.8653,
|
|
"mean_token_accuracy": 0.16517645716667176,
|
|
"num_tokens": 6092464.0,
|
|
"step": 2730
|
|
},
|
|
{
|
|
"entropy": 5.9122978210449215,
|
|
"epoch": 0.307182568652777,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004995693242154581,
|
|
"loss": 5.8066,
|
|
"mean_token_accuracy": 0.1669014349579811,
|
|
"num_tokens": 6103242.0,
|
|
"step": 2735
|
|
},
|
|
{
|
|
"entropy": 5.813560438156128,
|
|
"epoch": 0.30774414556073454,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004995668377202258,
|
|
"loss": 5.8616,
|
|
"mean_token_accuracy": 0.16158075183629989,
|
|
"num_tokens": 6116383.0,
|
|
"step": 2740
|
|
},
|
|
{
|
|
"entropy": 5.794858694076538,
|
|
"epoch": 0.3083057224686921,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004995643440746982,
|
|
"loss": 5.6608,
|
|
"mean_token_accuracy": 0.17261848896741866,
|
|
"num_tokens": 6126883.0,
|
|
"step": 2745
|
|
},
|
|
{
|
|
"entropy": 5.796203565597534,
|
|
"epoch": 0.30886729937664964,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004995618432789548,
|
|
"loss": 5.8404,
|
|
"mean_token_accuracy": 0.15857291966676712,
|
|
"num_tokens": 6139613.0,
|
|
"step": 2750
|
|
},
|
|
{
|
|
"entropy": 5.854716825485229,
|
|
"epoch": 0.3094288762846072,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004995593353330753,
|
|
"loss": 5.9133,
|
|
"mean_token_accuracy": 0.16079335808753967,
|
|
"num_tokens": 6151950.0,
|
|
"step": 2755
|
|
},
|
|
{
|
|
"entropy": 5.837777042388916,
|
|
"epoch": 0.30999045319256474,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004995568202371393,
|
|
"loss": 5.7127,
|
|
"mean_token_accuracy": 0.16686528772115708,
|
|
"num_tokens": 6161563.0,
|
|
"step": 2760
|
|
},
|
|
{
|
|
"entropy": 5.712786054611206,
|
|
"epoch": 0.3105520301005223,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004995542979912272,
|
|
"loss": 5.7281,
|
|
"mean_token_accuracy": 0.17184682339429855,
|
|
"num_tokens": 6170966.0,
|
|
"step": 2765
|
|
},
|
|
{
|
|
"entropy": 5.817671155929565,
|
|
"epoch": 0.3111136070084798,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004995517685954192,
|
|
"loss": 5.798,
|
|
"mean_token_accuracy": 0.16531543880701066,
|
|
"num_tokens": 6182563.0,
|
|
"step": 2770
|
|
},
|
|
{
|
|
"entropy": 5.8397852897644045,
|
|
"epoch": 0.31167518391643734,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004995492320497958,
|
|
"loss": 5.8981,
|
|
"mean_token_accuracy": 0.1579633668065071,
|
|
"num_tokens": 6194495.0,
|
|
"step": 2775
|
|
},
|
|
{
|
|
"entropy": 5.866177606582641,
|
|
"epoch": 0.3122367608243949,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004995466883544376,
|
|
"loss": 5.8005,
|
|
"mean_token_accuracy": 0.1617473378777504,
|
|
"num_tokens": 6206594.0,
|
|
"step": 2780
|
|
},
|
|
{
|
|
"entropy": 5.862904596328735,
|
|
"epoch": 0.31279833773235244,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004995441375094258,
|
|
"loss": 5.8319,
|
|
"mean_token_accuracy": 0.15888234823942185,
|
|
"num_tokens": 6218371.0,
|
|
"step": 2785
|
|
},
|
|
{
|
|
"entropy": 5.8452497005462645,
|
|
"epoch": 0.31335991464031,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004995415795148417,
|
|
"loss": 5.7583,
|
|
"mean_token_accuracy": 0.16749636232852935,
|
|
"num_tokens": 6228723.0,
|
|
"step": 2790
|
|
},
|
|
{
|
|
"entropy": 5.830468559265137,
|
|
"epoch": 0.31392149154826754,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004995390143707665,
|
|
"loss": 5.9309,
|
|
"mean_token_accuracy": 0.16207406669855118,
|
|
"num_tokens": 6240535.0,
|
|
"step": 2795
|
|
},
|
|
{
|
|
"entropy": 5.817456340789795,
|
|
"epoch": 0.3144830684562251,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004995364420772821,
|
|
"loss": 5.6419,
|
|
"mean_token_accuracy": 0.17303893119096755,
|
|
"num_tokens": 6250643.0,
|
|
"step": 2800
|
|
},
|
|
{
|
|
"entropy": 5.758491373062133,
|
|
"epoch": 0.31504464536418264,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004995338626344702,
|
|
"loss": 5.7857,
|
|
"mean_token_accuracy": 0.16550625413656234,
|
|
"num_tokens": 6259569.0,
|
|
"step": 2805
|
|
},
|
|
{
|
|
"entropy": 5.837896394729614,
|
|
"epoch": 0.3156062222721402,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.000499531276042413,
|
|
"loss": 5.9132,
|
|
"mean_token_accuracy": 0.1697901740670204,
|
|
"num_tokens": 6271108.0,
|
|
"step": 2810
|
|
},
|
|
{
|
|
"entropy": 5.893266916275024,
|
|
"epoch": 0.31616779918009774,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004995286823011929,
|
|
"loss": 5.7597,
|
|
"mean_token_accuracy": 0.15869502425193788,
|
|
"num_tokens": 6282352.0,
|
|
"step": 2815
|
|
},
|
|
{
|
|
"entropy": 5.788046741485596,
|
|
"epoch": 0.31672937608805524,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004995260814108926,
|
|
"loss": 5.8766,
|
|
"mean_token_accuracy": 0.16228645592927932,
|
|
"num_tokens": 6294946.0,
|
|
"step": 2820
|
|
},
|
|
{
|
|
"entropy": 5.816434526443482,
|
|
"epoch": 0.3172909529960128,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004995234733715947,
|
|
"loss": 5.6936,
|
|
"mean_token_accuracy": 0.16825819313526152,
|
|
"num_tokens": 6305552.0,
|
|
"step": 2825
|
|
},
|
|
{
|
|
"entropy": 5.727196073532104,
|
|
"epoch": 0.31785252990397034,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004995208581833824,
|
|
"loss": 5.7691,
|
|
"mean_token_accuracy": 0.1745617136359215,
|
|
"num_tokens": 6315815.0,
|
|
"step": 2830
|
|
},
|
|
{
|
|
"entropy": 5.8493071556091305,
|
|
"epoch": 0.3184141068119279,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004995182358463388,
|
|
"loss": 5.7964,
|
|
"mean_token_accuracy": 0.1629154123365879,
|
|
"num_tokens": 6327384.0,
|
|
"step": 2835
|
|
},
|
|
{
|
|
"entropy": 5.843144941329956,
|
|
"epoch": 0.31897568371988544,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004995156063605475,
|
|
"loss": 5.7971,
|
|
"mean_token_accuracy": 0.1567796841263771,
|
|
"num_tokens": 6338083.0,
|
|
"step": 2840
|
|
},
|
|
{
|
|
"entropy": 5.861480331420898,
|
|
"epoch": 0.319537260627843,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004995129697260922,
|
|
"loss": 5.787,
|
|
"mean_token_accuracy": 0.16809219717979432,
|
|
"num_tokens": 6349058.0,
|
|
"step": 2845
|
|
},
|
|
{
|
|
"entropy": 5.789098072052002,
|
|
"epoch": 0.32009883753580054,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004995103259430569,
|
|
"loss": 5.7927,
|
|
"mean_token_accuracy": 0.16856566220521926,
|
|
"num_tokens": 6359655.0,
|
|
"step": 2850
|
|
},
|
|
{
|
|
"entropy": 5.902016878128052,
|
|
"epoch": 0.3206604144437581,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004995076750115258,
|
|
"loss": 5.9143,
|
|
"mean_token_accuracy": 0.16268535405397416,
|
|
"num_tokens": 6372088.0,
|
|
"step": 2855
|
|
},
|
|
{
|
|
"entropy": 5.852352237701416,
|
|
"epoch": 0.32122199135171564,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004995050169315832,
|
|
"loss": 5.8272,
|
|
"mean_token_accuracy": 0.16033977046608924,
|
|
"num_tokens": 6382946.0,
|
|
"step": 2860
|
|
},
|
|
{
|
|
"entropy": 5.833240985870361,
|
|
"epoch": 0.32178356825967314,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004995023517033138,
|
|
"loss": 5.831,
|
|
"mean_token_accuracy": 0.1602622725069523,
|
|
"num_tokens": 6392591.0,
|
|
"step": 2865
|
|
},
|
|
{
|
|
"entropy": 5.773062515258789,
|
|
"epoch": 0.3223451451676307,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004994996793268024,
|
|
"loss": 5.7582,
|
|
"mean_token_accuracy": 0.16714053303003312,
|
|
"num_tokens": 6403159.0,
|
|
"step": 2870
|
|
},
|
|
{
|
|
"entropy": 5.8594804286956785,
|
|
"epoch": 0.32290672207558824,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004994969998021342,
|
|
"loss": 5.7763,
|
|
"mean_token_accuracy": 0.16392116546630858,
|
|
"num_tokens": 6414232.0,
|
|
"step": 2875
|
|
},
|
|
{
|
|
"entropy": 5.80814905166626,
|
|
"epoch": 0.3234682989835458,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004994943131293944,
|
|
"loss": 5.75,
|
|
"mean_token_accuracy": 0.17552235275506972,
|
|
"num_tokens": 6425762.0,
|
|
"step": 2880
|
|
},
|
|
{
|
|
"entropy": 5.751522493362427,
|
|
"epoch": 0.32402987589150334,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004994916193086687,
|
|
"loss": 5.8078,
|
|
"mean_token_accuracy": 0.1594655692577362,
|
|
"num_tokens": 6439077.0,
|
|
"step": 2885
|
|
},
|
|
{
|
|
"entropy": 5.91164870262146,
|
|
"epoch": 0.3245914527994609,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004994889183400428,
|
|
"loss": 5.8659,
|
|
"mean_token_accuracy": 0.1664183884859085,
|
|
"num_tokens": 6450425.0,
|
|
"step": 2890
|
|
},
|
|
{
|
|
"entropy": 5.817657470703125,
|
|
"epoch": 0.32515302970741844,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004994862102236025,
|
|
"loss": 5.8467,
|
|
"mean_token_accuracy": 0.16085008457303046,
|
|
"num_tokens": 6461347.0,
|
|
"step": 2895
|
|
},
|
|
{
|
|
"entropy": 5.867591190338135,
|
|
"epoch": 0.325714606615376,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004994834949594342,
|
|
"loss": 5.8231,
|
|
"mean_token_accuracy": 0.16414998173713685,
|
|
"num_tokens": 6472428.0,
|
|
"step": 2900
|
|
},
|
|
{
|
|
"entropy": 5.853135013580323,
|
|
"epoch": 0.32627618352333354,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004994807725476246,
|
|
"loss": 5.7869,
|
|
"mean_token_accuracy": 0.1745881587266922,
|
|
"num_tokens": 6483393.0,
|
|
"step": 2905
|
|
},
|
|
{
|
|
"entropy": 5.785771131515503,
|
|
"epoch": 0.3268377604312911,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004994780429882599,
|
|
"loss": 5.7757,
|
|
"mean_token_accuracy": 0.1680740788578987,
|
|
"num_tokens": 6493520.0,
|
|
"step": 2910
|
|
},
|
|
{
|
|
"entropy": 5.752371883392334,
|
|
"epoch": 0.3273993373392486,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004994753062814274,
|
|
"loss": 5.6963,
|
|
"mean_token_accuracy": 0.17319443970918655,
|
|
"num_tokens": 6505282.0,
|
|
"step": 2915
|
|
},
|
|
{
|
|
"entropy": 5.91207103729248,
|
|
"epoch": 0.32796091424720614,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004994725624272139,
|
|
"loss": 5.8841,
|
|
"mean_token_accuracy": 0.16525036245584487,
|
|
"num_tokens": 6516808.0,
|
|
"step": 2920
|
|
},
|
|
{
|
|
"entropy": 5.796984434127808,
|
|
"epoch": 0.3285224911551637,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004994698114257071,
|
|
"loss": 5.8424,
|
|
"mean_token_accuracy": 0.16388848423957825,
|
|
"num_tokens": 6529184.0,
|
|
"step": 2925
|
|
},
|
|
{
|
|
"entropy": 5.754847717285156,
|
|
"epoch": 0.32908406806312124,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004994670532769944,
|
|
"loss": 5.6797,
|
|
"mean_token_accuracy": 0.17214834541082383,
|
|
"num_tokens": 6539909.0,
|
|
"step": 2930
|
|
},
|
|
{
|
|
"entropy": 5.7354607582092285,
|
|
"epoch": 0.3296456449710788,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004994642879811637,
|
|
"loss": 5.728,
|
|
"mean_token_accuracy": 0.17159772366285325,
|
|
"num_tokens": 6550870.0,
|
|
"step": 2935
|
|
},
|
|
{
|
|
"entropy": 5.773732614517212,
|
|
"epoch": 0.33020722187903634,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.000499461515538303,
|
|
"loss": 5.7816,
|
|
"mean_token_accuracy": 0.16842659711837768,
|
|
"num_tokens": 6561784.0,
|
|
"step": 2940
|
|
},
|
|
{
|
|
"entropy": 5.744688701629639,
|
|
"epoch": 0.3307687987869939,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004994587359485006,
|
|
"loss": 5.7386,
|
|
"mean_token_accuracy": 0.16806551367044448,
|
|
"num_tokens": 6573422.0,
|
|
"step": 2945
|
|
},
|
|
{
|
|
"entropy": 5.877232646942138,
|
|
"epoch": 0.33133037569495144,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.000499455949211845,
|
|
"loss": 5.8162,
|
|
"mean_token_accuracy": 0.16845542192459106,
|
|
"num_tokens": 6584565.0,
|
|
"step": 2950
|
|
},
|
|
{
|
|
"entropy": 5.798536968231201,
|
|
"epoch": 0.331891952602909,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004994531553284248,
|
|
"loss": 5.7309,
|
|
"mean_token_accuracy": 0.1662512257695198,
|
|
"num_tokens": 6594238.0,
|
|
"step": 2955
|
|
},
|
|
{
|
|
"entropy": 5.757019329071045,
|
|
"epoch": 0.3324535295108665,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004994503542983293,
|
|
"loss": 5.7989,
|
|
"mean_token_accuracy": 0.16396647095680236,
|
|
"num_tokens": 6606309.0,
|
|
"step": 2960
|
|
},
|
|
{
|
|
"entropy": 5.9318952560424805,
|
|
"epoch": 0.33301510641882404,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004994475461216472,
|
|
"loss": 5.883,
|
|
"mean_token_accuracy": 0.15782105028629304,
|
|
"num_tokens": 6617916.0,
|
|
"step": 2965
|
|
},
|
|
{
|
|
"entropy": 5.816576623916626,
|
|
"epoch": 0.3335766833267816,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004994447307984684,
|
|
"loss": 5.7429,
|
|
"mean_token_accuracy": 0.16411727666854858,
|
|
"num_tokens": 6627951.0,
|
|
"step": 2970
|
|
},
|
|
{
|
|
"entropy": 5.786376428604126,
|
|
"epoch": 0.33413826023473914,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004994419083288823,
|
|
"loss": 5.8053,
|
|
"mean_token_accuracy": 0.16367775201797485,
|
|
"num_tokens": 6639285.0,
|
|
"step": 2975
|
|
},
|
|
{
|
|
"entropy": 5.791878652572632,
|
|
"epoch": 0.3346998371426967,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004994390787129787,
|
|
"loss": 5.6649,
|
|
"mean_token_accuracy": 0.17057127356529236,
|
|
"num_tokens": 6649973.0,
|
|
"step": 2980
|
|
},
|
|
{
|
|
"entropy": 5.695503759384155,
|
|
"epoch": 0.33526141405065424,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004994362419508478,
|
|
"loss": 5.6906,
|
|
"mean_token_accuracy": 0.17208612114191055,
|
|
"num_tokens": 6660625.0,
|
|
"step": 2985
|
|
},
|
|
{
|
|
"entropy": 5.78005313873291,
|
|
"epoch": 0.3358229909586118,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00049943339804258,
|
|
"loss": 5.7787,
|
|
"mean_token_accuracy": 0.16272861510515213,
|
|
"num_tokens": 6673191.0,
|
|
"step": 2990
|
|
},
|
|
{
|
|
"entropy": 5.845469617843628,
|
|
"epoch": 0.33638456786656934,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004994305469882657,
|
|
"loss": 5.7557,
|
|
"mean_token_accuracy": 0.16925826966762542,
|
|
"num_tokens": 6683993.0,
|
|
"step": 2995
|
|
},
|
|
{
|
|
"entropy": 5.727444458007812,
|
|
"epoch": 0.3369461447745269,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004994276887879957,
|
|
"loss": 5.8048,
|
|
"mean_token_accuracy": 0.16965395361185073,
|
|
"num_tokens": 6694881.0,
|
|
"step": 3000
|
|
},
|
|
{
|
|
"epoch": 0.3369461447745269,
|
|
"eval_entropy": 5.65701306957789,
|
|
"eval_loss": 5.820116996765137,
|
|
"eval_mean_token_accuracy": 0.1707352563135397,
|
|
"eval_num_tokens": 6694881.0,
|
|
"eval_runtime": 23.8089,
|
|
"eval_samples_per_second": 1302.578,
|
|
"eval_steps_per_second": 162.838,
|
|
"step": 3000
|
|
}
|
|
],
|
|
"logging_steps": 5,
|
|
"max_steps": 89030,
|
|
"num_input_tokens_seen": 0,
|
|
"num_train_epochs": 10,
|
|
"save_steps": 3000,
|
|
"stateful_callbacks": {
|
|
"TrainerControl": {
|
|
"args": {
|
|
"should_epoch_stop": false,
|
|
"should_evaluate": false,
|
|
"should_log": false,
|
|
"should_save": true,
|
|
"should_training_stop": false
|
|
},
|
|
"attributes": {}
|
|
}
|
|
},
|
|
"total_flos": 1.0448431460352e+16,
|
|
"train_batch_size": 16,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|