8574823600
Model: fpadovani/eng-latn-100mb-after-ppt-Dp-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": 6.907250690460205,
|
|
"epoch": 0.0005615769079575448,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 2e-06,
|
|
"loss": 6.6454,
|
|
"mean_token_accuracy": 0.12325676903128624,
|
|
"num_tokens": 11659.0,
|
|
"step": 5
|
|
},
|
|
{
|
|
"entropy": 6.95299882888794,
|
|
"epoch": 0.0011231538159150896,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 4.5e-06,
|
|
"loss": 6.6251,
|
|
"mean_token_accuracy": 0.12640999108552933,
|
|
"num_tokens": 21794.0,
|
|
"step": 10
|
|
},
|
|
{
|
|
"entropy": 6.88270936012268,
|
|
"epoch": 0.0016847307238726343,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 7e-06,
|
|
"loss": 6.6267,
|
|
"mean_token_accuracy": 0.11778247579932213,
|
|
"num_tokens": 33206.0,
|
|
"step": 15
|
|
},
|
|
{
|
|
"entropy": 6.894813537597656,
|
|
"epoch": 0.0022463076318301792,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 9.5e-06,
|
|
"loss": 6.6672,
|
|
"mean_token_accuracy": 0.11579557210206985,
|
|
"num_tokens": 44487.0,
|
|
"step": 20
|
|
},
|
|
{
|
|
"entropy": 6.8511096954345705,
|
|
"epoch": 0.002807884539787724,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 1.2e-05,
|
|
"loss": 6.7036,
|
|
"mean_token_accuracy": 0.12203121483325959,
|
|
"num_tokens": 56062.0,
|
|
"step": 25
|
|
},
|
|
{
|
|
"entropy": 6.77201623916626,
|
|
"epoch": 0.0033694614477452686,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 1.4500000000000002e-05,
|
|
"loss": 6.5797,
|
|
"mean_token_accuracy": 0.12473140060901641,
|
|
"num_tokens": 67453.0,
|
|
"step": 30
|
|
},
|
|
{
|
|
"entropy": 6.868989038467407,
|
|
"epoch": 0.003931038355702813,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 1.7000000000000003e-05,
|
|
"loss": 6.6964,
|
|
"mean_token_accuracy": 0.12546522542834282,
|
|
"num_tokens": 78527.0,
|
|
"step": 35
|
|
},
|
|
{
|
|
"entropy": 6.834421539306641,
|
|
"epoch": 0.0044926152636603585,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 1.95e-05,
|
|
"loss": 6.5568,
|
|
"mean_token_accuracy": 0.1299024060368538,
|
|
"num_tokens": 89267.0,
|
|
"step": 40
|
|
},
|
|
{
|
|
"entropy": 6.802654600143432,
|
|
"epoch": 0.005054192171617903,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 2.2e-05,
|
|
"loss": 6.567,
|
|
"mean_token_accuracy": 0.12636540681123734,
|
|
"num_tokens": 102035.0,
|
|
"step": 45
|
|
},
|
|
{
|
|
"entropy": 6.78539891242981,
|
|
"epoch": 0.005615769079575448,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 2.4500000000000003e-05,
|
|
"loss": 6.6043,
|
|
"mean_token_accuracy": 0.12845361977815628,
|
|
"num_tokens": 112734.0,
|
|
"step": 50
|
|
},
|
|
{
|
|
"entropy": 6.808405780792237,
|
|
"epoch": 0.006177345987532993,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 2.7e-05,
|
|
"loss": 6.518,
|
|
"mean_token_accuracy": 0.13111241459846495,
|
|
"num_tokens": 123854.0,
|
|
"step": 55
|
|
},
|
|
{
|
|
"entropy": 6.786837434768676,
|
|
"epoch": 0.006738922895490537,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 2.95e-05,
|
|
"loss": 6.5574,
|
|
"mean_token_accuracy": 0.12830817103385925,
|
|
"num_tokens": 133444.0,
|
|
"step": 60
|
|
},
|
|
{
|
|
"entropy": 6.7932250022888185,
|
|
"epoch": 0.007300499803448083,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 3.2e-05,
|
|
"loss": 6.4492,
|
|
"mean_token_accuracy": 0.13187738582491876,
|
|
"num_tokens": 144678.0,
|
|
"step": 65
|
|
},
|
|
{
|
|
"entropy": 6.834688949584961,
|
|
"epoch": 0.007862076711405626,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 3.4500000000000005e-05,
|
|
"loss": 6.5573,
|
|
"mean_token_accuracy": 0.1290239155292511,
|
|
"num_tokens": 155866.0,
|
|
"step": 70
|
|
},
|
|
{
|
|
"entropy": 6.833860158920288,
|
|
"epoch": 0.008423653619363172,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 3.7e-05,
|
|
"loss": 6.5594,
|
|
"mean_token_accuracy": 0.1337614819407463,
|
|
"num_tokens": 166965.0,
|
|
"step": 75
|
|
},
|
|
{
|
|
"entropy": 6.771542024612427,
|
|
"epoch": 0.008985230527320717,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 3.95e-05,
|
|
"loss": 6.5349,
|
|
"mean_token_accuracy": 0.13214125260710716,
|
|
"num_tokens": 177423.0,
|
|
"step": 80
|
|
},
|
|
{
|
|
"entropy": 6.810234785079956,
|
|
"epoch": 0.00954680743527826,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 4.2000000000000004e-05,
|
|
"loss": 6.5843,
|
|
"mean_token_accuracy": 0.13490741923451424,
|
|
"num_tokens": 188687.0,
|
|
"step": 85
|
|
},
|
|
{
|
|
"entropy": 6.790950298309326,
|
|
"epoch": 0.010108384343235806,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 4.45e-05,
|
|
"loss": 6.6447,
|
|
"mean_token_accuracy": 0.1322058655321598,
|
|
"num_tokens": 200173.0,
|
|
"step": 90
|
|
},
|
|
{
|
|
"entropy": 6.904566144943237,
|
|
"epoch": 0.010669961251193351,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 4.7000000000000004e-05,
|
|
"loss": 6.6097,
|
|
"mean_token_accuracy": 0.12937101572752,
|
|
"num_tokens": 210877.0,
|
|
"step": 95
|
|
},
|
|
{
|
|
"entropy": 6.820630264282227,
|
|
"epoch": 0.011231538159150897,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 4.9500000000000004e-05,
|
|
"loss": 6.4946,
|
|
"mean_token_accuracy": 0.1320508226752281,
|
|
"num_tokens": 221770.0,
|
|
"step": 100
|
|
},
|
|
{
|
|
"entropy": 6.799368095397949,
|
|
"epoch": 0.01179311506710844,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 5.2e-05,
|
|
"loss": 6.6108,
|
|
"mean_token_accuracy": 0.13751114308834075,
|
|
"num_tokens": 232140.0,
|
|
"step": 105
|
|
},
|
|
{
|
|
"entropy": 6.9101881980896,
|
|
"epoch": 0.012354691975065986,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 5.45e-05,
|
|
"loss": 6.6995,
|
|
"mean_token_accuracy": 0.1259769469499588,
|
|
"num_tokens": 244186.0,
|
|
"step": 110
|
|
},
|
|
{
|
|
"entropy": 6.848400115966797,
|
|
"epoch": 0.012916268883023531,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 5.7e-05,
|
|
"loss": 6.5407,
|
|
"mean_token_accuracy": 0.13194369077682494,
|
|
"num_tokens": 254805.0,
|
|
"step": 115
|
|
},
|
|
{
|
|
"entropy": 6.698233985900879,
|
|
"epoch": 0.013477845790981074,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 5.9499999999999996e-05,
|
|
"loss": 6.5033,
|
|
"mean_token_accuracy": 0.13761864304542543,
|
|
"num_tokens": 265055.0,
|
|
"step": 120
|
|
},
|
|
{
|
|
"entropy": 6.791996097564697,
|
|
"epoch": 0.01403942269893862,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 6.2e-05,
|
|
"loss": 6.4269,
|
|
"mean_token_accuracy": 0.13726359307765962,
|
|
"num_tokens": 275850.0,
|
|
"step": 125
|
|
},
|
|
{
|
|
"entropy": 6.7355358600616455,
|
|
"epoch": 0.014600999606896165,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 6.450000000000001e-05,
|
|
"loss": 6.4766,
|
|
"mean_token_accuracy": 0.13020233884453775,
|
|
"num_tokens": 286802.0,
|
|
"step": 130
|
|
},
|
|
{
|
|
"entropy": 6.776710081100464,
|
|
"epoch": 0.015162576514853709,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 6.7e-05,
|
|
"loss": 6.5889,
|
|
"mean_token_accuracy": 0.12709178403019905,
|
|
"num_tokens": 297070.0,
|
|
"step": 135
|
|
},
|
|
{
|
|
"entropy": 6.857462978363037,
|
|
"epoch": 0.015724153422811252,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 6.950000000000001e-05,
|
|
"loss": 6.5067,
|
|
"mean_token_accuracy": 0.1300993725657463,
|
|
"num_tokens": 309617.0,
|
|
"step": 140
|
|
},
|
|
{
|
|
"entropy": 6.7578826427459715,
|
|
"epoch": 0.0162857303307688,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 7.2e-05,
|
|
"loss": 6.5446,
|
|
"mean_token_accuracy": 0.12609508857131005,
|
|
"num_tokens": 321310.0,
|
|
"step": 145
|
|
},
|
|
{
|
|
"entropy": 6.758755540847778,
|
|
"epoch": 0.016847307238726343,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 7.45e-05,
|
|
"loss": 6.4748,
|
|
"mean_token_accuracy": 0.1324310265481472,
|
|
"num_tokens": 332243.0,
|
|
"step": 150
|
|
},
|
|
{
|
|
"entropy": 6.731501817703247,
|
|
"epoch": 0.017408884146683887,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 7.7e-05,
|
|
"loss": 6.5059,
|
|
"mean_token_accuracy": 0.12957077771425246,
|
|
"num_tokens": 342847.0,
|
|
"step": 155
|
|
},
|
|
{
|
|
"entropy": 6.806047821044922,
|
|
"epoch": 0.017970461054641434,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 7.950000000000001e-05,
|
|
"loss": 6.4264,
|
|
"mean_token_accuracy": 0.13830571845173836,
|
|
"num_tokens": 353570.0,
|
|
"step": 160
|
|
},
|
|
{
|
|
"entropy": 6.7714825630187985,
|
|
"epoch": 0.018532037962598977,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 8.2e-05,
|
|
"loss": 6.4818,
|
|
"mean_token_accuracy": 0.1378109060227871,
|
|
"num_tokens": 364330.0,
|
|
"step": 165
|
|
},
|
|
{
|
|
"entropy": 6.691267204284668,
|
|
"epoch": 0.01909361487055652,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 8.450000000000001e-05,
|
|
"loss": 6.5244,
|
|
"mean_token_accuracy": 0.13161558136343957,
|
|
"num_tokens": 374930.0,
|
|
"step": 170
|
|
},
|
|
{
|
|
"entropy": 6.84858512878418,
|
|
"epoch": 0.019655191778514068,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 8.7e-05,
|
|
"loss": 6.4959,
|
|
"mean_token_accuracy": 0.1296277239918709,
|
|
"num_tokens": 384690.0,
|
|
"step": 175
|
|
},
|
|
{
|
|
"entropy": 6.797068119049072,
|
|
"epoch": 0.020216768686471612,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 8.95e-05,
|
|
"loss": 6.5289,
|
|
"mean_token_accuracy": 0.13395457416772844,
|
|
"num_tokens": 395753.0,
|
|
"step": 180
|
|
},
|
|
{
|
|
"entropy": 6.726787281036377,
|
|
"epoch": 0.020778345594429155,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 9.2e-05,
|
|
"loss": 6.4848,
|
|
"mean_token_accuracy": 0.1342456102371216,
|
|
"num_tokens": 407049.0,
|
|
"step": 185
|
|
},
|
|
{
|
|
"entropy": 6.7613801002502445,
|
|
"epoch": 0.021339922502386702,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 9.45e-05,
|
|
"loss": 6.511,
|
|
"mean_token_accuracy": 0.13599891290068628,
|
|
"num_tokens": 417942.0,
|
|
"step": 190
|
|
},
|
|
{
|
|
"entropy": 6.74392523765564,
|
|
"epoch": 0.021901499410344246,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 9.7e-05,
|
|
"loss": 6.5347,
|
|
"mean_token_accuracy": 0.13084860444068908,
|
|
"num_tokens": 428151.0,
|
|
"step": 195
|
|
},
|
|
{
|
|
"entropy": 6.873997688293457,
|
|
"epoch": 0.022463076318301793,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 9.95e-05,
|
|
"loss": 6.6172,
|
|
"mean_token_accuracy": 0.12304027304053307,
|
|
"num_tokens": 439837.0,
|
|
"step": 200
|
|
},
|
|
{
|
|
"entropy": 6.6801533699035645,
|
|
"epoch": 0.023024653226259337,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000102,
|
|
"loss": 6.4234,
|
|
"mean_token_accuracy": 0.129472017288208,
|
|
"num_tokens": 450357.0,
|
|
"step": 205
|
|
},
|
|
{
|
|
"entropy": 6.85008544921875,
|
|
"epoch": 0.02358623013421688,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00010449999999999999,
|
|
"loss": 6.4674,
|
|
"mean_token_accuracy": 0.1346777245402336,
|
|
"num_tokens": 461174.0,
|
|
"step": 210
|
|
},
|
|
{
|
|
"entropy": 6.803839302062988,
|
|
"epoch": 0.024147807042174427,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000107,
|
|
"loss": 6.5461,
|
|
"mean_token_accuracy": 0.132686547935009,
|
|
"num_tokens": 472785.0,
|
|
"step": 215
|
|
},
|
|
{
|
|
"entropy": 6.726331377029419,
|
|
"epoch": 0.02470938395013197,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0001095,
|
|
"loss": 6.5429,
|
|
"mean_token_accuracy": 0.1351382851600647,
|
|
"num_tokens": 483248.0,
|
|
"step": 220
|
|
},
|
|
{
|
|
"entropy": 6.723070573806763,
|
|
"epoch": 0.025270960858089515,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000112,
|
|
"loss": 6.3822,
|
|
"mean_token_accuracy": 0.1378464035689831,
|
|
"num_tokens": 494690.0,
|
|
"step": 225
|
|
},
|
|
{
|
|
"entropy": 6.7689587593078615,
|
|
"epoch": 0.025832537766047062,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0001145,
|
|
"loss": 6.6013,
|
|
"mean_token_accuracy": 0.1281190924346447,
|
|
"num_tokens": 506192.0,
|
|
"step": 230
|
|
},
|
|
{
|
|
"entropy": 6.8111066818237305,
|
|
"epoch": 0.026394114674004605,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00011700000000000001,
|
|
"loss": 6.5057,
|
|
"mean_token_accuracy": 0.13290760517120362,
|
|
"num_tokens": 517152.0,
|
|
"step": 235
|
|
},
|
|
{
|
|
"entropy": 6.639764785766602,
|
|
"epoch": 0.02695569158196215,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00011949999999999999,
|
|
"loss": 6.4202,
|
|
"mean_token_accuracy": 0.13568630814552307,
|
|
"num_tokens": 527836.0,
|
|
"step": 240
|
|
},
|
|
{
|
|
"entropy": 6.822380447387696,
|
|
"epoch": 0.027517268489919696,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000122,
|
|
"loss": 6.5896,
|
|
"mean_token_accuracy": 0.13045021742582322,
|
|
"num_tokens": 539491.0,
|
|
"step": 245
|
|
},
|
|
{
|
|
"entropy": 6.886163139343262,
|
|
"epoch": 0.02807884539787724,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0001245,
|
|
"loss": 6.5679,
|
|
"mean_token_accuracy": 0.13087331652641296,
|
|
"num_tokens": 550816.0,
|
|
"step": 250
|
|
},
|
|
{
|
|
"entropy": 6.840306997299194,
|
|
"epoch": 0.028640422305834783,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000127,
|
|
"loss": 6.624,
|
|
"mean_token_accuracy": 0.12609125748276712,
|
|
"num_tokens": 561566.0,
|
|
"step": 255
|
|
},
|
|
{
|
|
"entropy": 6.74591097831726,
|
|
"epoch": 0.02920199921379233,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0001295,
|
|
"loss": 6.5495,
|
|
"mean_token_accuracy": 0.12940011620521547,
|
|
"num_tokens": 573032.0,
|
|
"step": 260
|
|
},
|
|
{
|
|
"entropy": 6.815591430664062,
|
|
"epoch": 0.029763576121749874,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000132,
|
|
"loss": 6.4639,
|
|
"mean_token_accuracy": 0.13757430762052536,
|
|
"num_tokens": 584140.0,
|
|
"step": 265
|
|
},
|
|
{
|
|
"entropy": 6.750753736495971,
|
|
"epoch": 0.030325153029707418,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00013450000000000002,
|
|
"loss": 6.5428,
|
|
"mean_token_accuracy": 0.13629817366600036,
|
|
"num_tokens": 595097.0,
|
|
"step": 270
|
|
},
|
|
{
|
|
"entropy": 6.8167486667633055,
|
|
"epoch": 0.030886729937664965,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00013700000000000002,
|
|
"loss": 6.5745,
|
|
"mean_token_accuracy": 0.13026740923523902,
|
|
"num_tokens": 606797.0,
|
|
"step": 275
|
|
},
|
|
{
|
|
"entropy": 6.7974999904632565,
|
|
"epoch": 0.031448306845622505,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0001395,
|
|
"loss": 6.5443,
|
|
"mean_token_accuracy": 0.1298480361700058,
|
|
"num_tokens": 618187.0,
|
|
"step": 280
|
|
},
|
|
{
|
|
"entropy": 6.741901540756226,
|
|
"epoch": 0.032009883753580055,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00014199999999999998,
|
|
"loss": 6.4842,
|
|
"mean_token_accuracy": 0.13356513679027557,
|
|
"num_tokens": 629829.0,
|
|
"step": 285
|
|
},
|
|
{
|
|
"entropy": 6.724414396286011,
|
|
"epoch": 0.0325714606615376,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0001445,
|
|
"loss": 6.5091,
|
|
"mean_token_accuracy": 0.13159143030643464,
|
|
"num_tokens": 640914.0,
|
|
"step": 290
|
|
},
|
|
{
|
|
"entropy": 6.815596628189087,
|
|
"epoch": 0.03313303756949514,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000147,
|
|
"loss": 6.5293,
|
|
"mean_token_accuracy": 0.13000186085700988,
|
|
"num_tokens": 653057.0,
|
|
"step": 295
|
|
},
|
|
{
|
|
"entropy": 6.669460153579712,
|
|
"epoch": 0.033694614477452686,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0001495,
|
|
"loss": 6.4485,
|
|
"mean_token_accuracy": 0.14079594984650612,
|
|
"num_tokens": 663437.0,
|
|
"step": 300
|
|
},
|
|
{
|
|
"entropy": 6.751016330718994,
|
|
"epoch": 0.03425619138541023,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.000152,
|
|
"loss": 6.5369,
|
|
"mean_token_accuracy": 0.13079639598727227,
|
|
"num_tokens": 675416.0,
|
|
"step": 305
|
|
},
|
|
{
|
|
"entropy": 6.6445365905761715,
|
|
"epoch": 0.03481776829336777,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00015450000000000001,
|
|
"loss": 6.3375,
|
|
"mean_token_accuracy": 0.13328307271003723,
|
|
"num_tokens": 686633.0,
|
|
"step": 310
|
|
},
|
|
{
|
|
"entropy": 6.61797342300415,
|
|
"epoch": 0.035379345201325324,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000157,
|
|
"loss": 6.4539,
|
|
"mean_token_accuracy": 0.13328708410263063,
|
|
"num_tokens": 698065.0,
|
|
"step": 315
|
|
},
|
|
{
|
|
"entropy": 6.7716223239898685,
|
|
"epoch": 0.03594092210928287,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0001595,
|
|
"loss": 6.4572,
|
|
"mean_token_accuracy": 0.13270723596215248,
|
|
"num_tokens": 708652.0,
|
|
"step": 320
|
|
},
|
|
{
|
|
"entropy": 6.836631536483765,
|
|
"epoch": 0.03650249901724041,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000162,
|
|
"loss": 6.633,
|
|
"mean_token_accuracy": 0.12807837575674058,
|
|
"num_tokens": 720199.0,
|
|
"step": 325
|
|
},
|
|
{
|
|
"entropy": 6.755860805511475,
|
|
"epoch": 0.037064075925197955,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00016450000000000001,
|
|
"loss": 6.594,
|
|
"mean_token_accuracy": 0.12865597382187843,
|
|
"num_tokens": 732964.0,
|
|
"step": 330
|
|
},
|
|
{
|
|
"entropy": 6.682922077178955,
|
|
"epoch": 0.0376256528331555,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00016700000000000002,
|
|
"loss": 6.3655,
|
|
"mean_token_accuracy": 0.13459469601511956,
|
|
"num_tokens": 743528.0,
|
|
"step": 335
|
|
},
|
|
{
|
|
"entropy": 6.717207574844361,
|
|
"epoch": 0.03818722974111304,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00016950000000000003,
|
|
"loss": 6.4622,
|
|
"mean_token_accuracy": 0.13458281084895135,
|
|
"num_tokens": 754365.0,
|
|
"step": 340
|
|
},
|
|
{
|
|
"entropy": 6.578363466262817,
|
|
"epoch": 0.03874880664907059,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00017199999999999998,
|
|
"loss": 6.3886,
|
|
"mean_token_accuracy": 0.12879974991083146,
|
|
"num_tokens": 766094.0,
|
|
"step": 345
|
|
},
|
|
{
|
|
"entropy": 6.680249881744385,
|
|
"epoch": 0.039310383557028136,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00017449999999999999,
|
|
"loss": 6.4493,
|
|
"mean_token_accuracy": 0.13100041821599007,
|
|
"num_tokens": 777275.0,
|
|
"step": 350
|
|
},
|
|
{
|
|
"entropy": 6.72165961265564,
|
|
"epoch": 0.03987196046498568,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000177,
|
|
"loss": 6.5285,
|
|
"mean_token_accuracy": 0.13037424385547638,
|
|
"num_tokens": 789436.0,
|
|
"step": 355
|
|
},
|
|
{
|
|
"entropy": 6.754672527313232,
|
|
"epoch": 0.040433537372943223,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0001795,
|
|
"loss": 6.5537,
|
|
"mean_token_accuracy": 0.1309170365333557,
|
|
"num_tokens": 800164.0,
|
|
"step": 360
|
|
},
|
|
{
|
|
"entropy": 6.621752738952637,
|
|
"epoch": 0.04099511428090077,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000182,
|
|
"loss": 6.4161,
|
|
"mean_token_accuracy": 0.13131387978792192,
|
|
"num_tokens": 811797.0,
|
|
"step": 365
|
|
},
|
|
{
|
|
"entropy": 6.678555488586426,
|
|
"epoch": 0.04155669118885831,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0001845,
|
|
"loss": 6.4265,
|
|
"mean_token_accuracy": 0.13252343758940696,
|
|
"num_tokens": 824158.0,
|
|
"step": 370
|
|
},
|
|
{
|
|
"entropy": 6.68765778541565,
|
|
"epoch": 0.04211826809681586,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000187,
|
|
"loss": 6.4324,
|
|
"mean_token_accuracy": 0.13959610983729362,
|
|
"num_tokens": 835803.0,
|
|
"step": 375
|
|
},
|
|
{
|
|
"entropy": 6.701789617538452,
|
|
"epoch": 0.042679845004773405,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0001895,
|
|
"loss": 6.5153,
|
|
"mean_token_accuracy": 0.12811891362071037,
|
|
"num_tokens": 848106.0,
|
|
"step": 380
|
|
},
|
|
{
|
|
"entropy": 6.676432752609253,
|
|
"epoch": 0.04324142191273095,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000192,
|
|
"loss": 6.5047,
|
|
"mean_token_accuracy": 0.13056822791695594,
|
|
"num_tokens": 859101.0,
|
|
"step": 385
|
|
},
|
|
{
|
|
"entropy": 6.634853458404541,
|
|
"epoch": 0.04380299882068849,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0001945,
|
|
"loss": 6.363,
|
|
"mean_token_accuracy": 0.13974561989307405,
|
|
"num_tokens": 870309.0,
|
|
"step": 390
|
|
},
|
|
{
|
|
"entropy": 6.6745370388031,
|
|
"epoch": 0.044364575728646036,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00019700000000000002,
|
|
"loss": 6.4732,
|
|
"mean_token_accuracy": 0.13085832819342613,
|
|
"num_tokens": 881515.0,
|
|
"step": 395
|
|
},
|
|
{
|
|
"entropy": 6.707674884796143,
|
|
"epoch": 0.044926152636603586,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00019950000000000002,
|
|
"loss": 6.4392,
|
|
"mean_token_accuracy": 0.13565397635102272,
|
|
"num_tokens": 892129.0,
|
|
"step": 400
|
|
},
|
|
{
|
|
"entropy": 6.609837865829467,
|
|
"epoch": 0.04548772954456113,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000202,
|
|
"loss": 6.46,
|
|
"mean_token_accuracy": 0.13184903636574746,
|
|
"num_tokens": 903186.0,
|
|
"step": 405
|
|
},
|
|
{
|
|
"entropy": 6.642455530166626,
|
|
"epoch": 0.046049306452518673,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00020449999999999998,
|
|
"loss": 6.4299,
|
|
"mean_token_accuracy": 0.13762376606464385,
|
|
"num_tokens": 913471.0,
|
|
"step": 410
|
|
},
|
|
{
|
|
"entropy": 6.7312219619750975,
|
|
"epoch": 0.04661088336047622,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.000207,
|
|
"loss": 6.4316,
|
|
"mean_token_accuracy": 0.13134424537420272,
|
|
"num_tokens": 924283.0,
|
|
"step": 415
|
|
},
|
|
{
|
|
"entropy": 6.647944927215576,
|
|
"epoch": 0.04717246026843376,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0002095,
|
|
"loss": 6.4697,
|
|
"mean_token_accuracy": 0.13021936267614365,
|
|
"num_tokens": 934975.0,
|
|
"step": 420
|
|
},
|
|
{
|
|
"entropy": 6.60395565032959,
|
|
"epoch": 0.047734037176391304,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.000212,
|
|
"loss": 6.3365,
|
|
"mean_token_accuracy": 0.14171250090003013,
|
|
"num_tokens": 945587.0,
|
|
"step": 425
|
|
},
|
|
{
|
|
"entropy": 6.608612155914306,
|
|
"epoch": 0.048295614084348855,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0002145,
|
|
"loss": 6.3925,
|
|
"mean_token_accuracy": 0.13692179098725318,
|
|
"num_tokens": 955935.0,
|
|
"step": 430
|
|
},
|
|
{
|
|
"entropy": 6.589728116989136,
|
|
"epoch": 0.0488571909923064,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00021700000000000002,
|
|
"loss": 6.389,
|
|
"mean_token_accuracy": 0.13498958870768546,
|
|
"num_tokens": 967960.0,
|
|
"step": 435
|
|
},
|
|
{
|
|
"entropy": 6.663047790527344,
|
|
"epoch": 0.04941876790026394,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0002195,
|
|
"loss": 6.4281,
|
|
"mean_token_accuracy": 0.13640725910663604,
|
|
"num_tokens": 979680.0,
|
|
"step": 440
|
|
},
|
|
{
|
|
"entropy": 6.576627540588379,
|
|
"epoch": 0.049980344808221486,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000222,
|
|
"loss": 6.512,
|
|
"mean_token_accuracy": 0.13283532932400705,
|
|
"num_tokens": 990600.0,
|
|
"step": 445
|
|
},
|
|
{
|
|
"entropy": 6.744882965087891,
|
|
"epoch": 0.05054192171617903,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0002245,
|
|
"loss": 6.5571,
|
|
"mean_token_accuracy": 0.13367009460926055,
|
|
"num_tokens": 1002331.0,
|
|
"step": 450
|
|
},
|
|
{
|
|
"entropy": 6.614725875854492,
|
|
"epoch": 0.05110349862413657,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00022700000000000002,
|
|
"loss": 6.3702,
|
|
"mean_token_accuracy": 0.1379753105342388,
|
|
"num_tokens": 1013473.0,
|
|
"step": 455
|
|
},
|
|
{
|
|
"entropy": 6.682910823822022,
|
|
"epoch": 0.051665075532094124,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00022950000000000002,
|
|
"loss": 6.4372,
|
|
"mean_token_accuracy": 0.1283923380076885,
|
|
"num_tokens": 1024434.0,
|
|
"step": 460
|
|
},
|
|
{
|
|
"entropy": 6.680650281906128,
|
|
"epoch": 0.05222665244005167,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00023200000000000003,
|
|
"loss": 6.468,
|
|
"mean_token_accuracy": 0.12814455404877662,
|
|
"num_tokens": 1035452.0,
|
|
"step": 465
|
|
},
|
|
{
|
|
"entropy": 6.5947794914245605,
|
|
"epoch": 0.05278822934800921,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00023449999999999998,
|
|
"loss": 6.3441,
|
|
"mean_token_accuracy": 0.13335954174399375,
|
|
"num_tokens": 1046213.0,
|
|
"step": 470
|
|
},
|
|
{
|
|
"entropy": 6.454158306121826,
|
|
"epoch": 0.053349806255966754,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000237,
|
|
"loss": 6.3879,
|
|
"mean_token_accuracy": 0.1338328018784523,
|
|
"num_tokens": 1057469.0,
|
|
"step": 475
|
|
},
|
|
{
|
|
"entropy": 6.801644802093506,
|
|
"epoch": 0.0539113831639243,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0002395,
|
|
"loss": 6.5276,
|
|
"mean_token_accuracy": 0.13049064353108406,
|
|
"num_tokens": 1069543.0,
|
|
"step": 480
|
|
},
|
|
{
|
|
"entropy": 6.555569219589233,
|
|
"epoch": 0.05447296007188184,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000242,
|
|
"loss": 6.3959,
|
|
"mean_token_accuracy": 0.13704427033662797,
|
|
"num_tokens": 1080476.0,
|
|
"step": 485
|
|
},
|
|
{
|
|
"entropy": 6.722979974746704,
|
|
"epoch": 0.05503453697983939,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0002445,
|
|
"loss": 6.514,
|
|
"mean_token_accuracy": 0.13329028636217116,
|
|
"num_tokens": 1091700.0,
|
|
"step": 490
|
|
},
|
|
{
|
|
"entropy": 6.5727941513061525,
|
|
"epoch": 0.055596113887796936,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000247,
|
|
"loss": 6.4015,
|
|
"mean_token_accuracy": 0.1319067433476448,
|
|
"num_tokens": 1103056.0,
|
|
"step": 495
|
|
},
|
|
{
|
|
"entropy": 6.674144220352173,
|
|
"epoch": 0.05615769079575448,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0002495,
|
|
"loss": 6.4715,
|
|
"mean_token_accuracy": 0.13558261916041375,
|
|
"num_tokens": 1114836.0,
|
|
"step": 500
|
|
},
|
|
{
|
|
"entropy": 6.547731256484985,
|
|
"epoch": 0.05671926770371202,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000252,
|
|
"loss": 6.3698,
|
|
"mean_token_accuracy": 0.13027856275439262,
|
|
"num_tokens": 1125993.0,
|
|
"step": 505
|
|
},
|
|
{
|
|
"entropy": 6.658946466445923,
|
|
"epoch": 0.05728084461166957,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0002545,
|
|
"loss": 6.4507,
|
|
"mean_token_accuracy": 0.13343697637319565,
|
|
"num_tokens": 1136719.0,
|
|
"step": 510
|
|
},
|
|
{
|
|
"entropy": 6.56524429321289,
|
|
"epoch": 0.05784242151962711,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.000257,
|
|
"loss": 6.338,
|
|
"mean_token_accuracy": 0.137813039124012,
|
|
"num_tokens": 1146947.0,
|
|
"step": 515
|
|
},
|
|
{
|
|
"entropy": 6.607427501678467,
|
|
"epoch": 0.05840399842758466,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0002595,
|
|
"loss": 6.4617,
|
|
"mean_token_accuracy": 0.1326425388455391,
|
|
"num_tokens": 1157974.0,
|
|
"step": 520
|
|
},
|
|
{
|
|
"entropy": 6.560697078704834,
|
|
"epoch": 0.058965575335542204,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000262,
|
|
"loss": 6.4036,
|
|
"mean_token_accuracy": 0.13357415795326233,
|
|
"num_tokens": 1168573.0,
|
|
"step": 525
|
|
},
|
|
{
|
|
"entropy": 6.574508571624756,
|
|
"epoch": 0.05952715224349975,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00026450000000000003,
|
|
"loss": 6.2877,
|
|
"mean_token_accuracy": 0.13817285895347595,
|
|
"num_tokens": 1178446.0,
|
|
"step": 530
|
|
},
|
|
{
|
|
"entropy": 6.566018009185791,
|
|
"epoch": 0.06008872915145729,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00026700000000000004,
|
|
"loss": 6.3405,
|
|
"mean_token_accuracy": 0.13772412464022638,
|
|
"num_tokens": 1190558.0,
|
|
"step": 535
|
|
},
|
|
{
|
|
"entropy": 6.564810800552368,
|
|
"epoch": 0.060650306059414835,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00026950000000000005,
|
|
"loss": 6.4939,
|
|
"mean_token_accuracy": 0.1318053610622883,
|
|
"num_tokens": 1201929.0,
|
|
"step": 540
|
|
},
|
|
{
|
|
"entropy": 6.502597904205322,
|
|
"epoch": 0.06121188296737238,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00027200000000000005,
|
|
"loss": 6.3444,
|
|
"mean_token_accuracy": 0.13646928146481513,
|
|
"num_tokens": 1213155.0,
|
|
"step": 545
|
|
},
|
|
{
|
|
"entropy": 6.680653238296509,
|
|
"epoch": 0.06177345987532993,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0002745,
|
|
"loss": 6.4053,
|
|
"mean_token_accuracy": 0.13270772770047187,
|
|
"num_tokens": 1223961.0,
|
|
"step": 550
|
|
},
|
|
{
|
|
"entropy": 6.381764841079712,
|
|
"epoch": 0.06233503678328747,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000277,
|
|
"loss": 6.2988,
|
|
"mean_token_accuracy": 0.1437389425933361,
|
|
"num_tokens": 1233888.0,
|
|
"step": 555
|
|
},
|
|
{
|
|
"entropy": 6.593340253829956,
|
|
"epoch": 0.06289661369124501,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0002795,
|
|
"loss": 6.4209,
|
|
"mean_token_accuracy": 0.12833445593714715,
|
|
"num_tokens": 1244405.0,
|
|
"step": 560
|
|
},
|
|
{
|
|
"entropy": 6.558970785140991,
|
|
"epoch": 0.06345819059920256,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00028199999999999997,
|
|
"loss": 6.3654,
|
|
"mean_token_accuracy": 0.13667553216218947,
|
|
"num_tokens": 1257099.0,
|
|
"step": 565
|
|
},
|
|
{
|
|
"entropy": 6.631209850311279,
|
|
"epoch": 0.06401976750716011,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0002845,
|
|
"loss": 6.4699,
|
|
"mean_token_accuracy": 0.13471307903528212,
|
|
"num_tokens": 1267965.0,
|
|
"step": 570
|
|
},
|
|
{
|
|
"entropy": 6.516822481155396,
|
|
"epoch": 0.06458134441511765,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000287,
|
|
"loss": 6.3936,
|
|
"mean_token_accuracy": 0.13442024663090707,
|
|
"num_tokens": 1280075.0,
|
|
"step": 575
|
|
},
|
|
{
|
|
"entropy": 6.609190845489502,
|
|
"epoch": 0.0651429213230752,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0002895,
|
|
"loss": 6.3864,
|
|
"mean_token_accuracy": 0.13422752767801285,
|
|
"num_tokens": 1290574.0,
|
|
"step": 580
|
|
},
|
|
{
|
|
"entropy": 6.4985980033874515,
|
|
"epoch": 0.06570449823103273,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000292,
|
|
"loss": 6.3732,
|
|
"mean_token_accuracy": 0.13692231178283693,
|
|
"num_tokens": 1302680.0,
|
|
"step": 585
|
|
},
|
|
{
|
|
"entropy": 6.57489275932312,
|
|
"epoch": 0.06626607513899029,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0002945,
|
|
"loss": 6.3562,
|
|
"mean_token_accuracy": 0.13580932915210725,
|
|
"num_tokens": 1314577.0,
|
|
"step": 590
|
|
},
|
|
{
|
|
"entropy": 6.555920886993408,
|
|
"epoch": 0.06682765204694784,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000297,
|
|
"loss": 6.4958,
|
|
"mean_token_accuracy": 0.13412591591477394,
|
|
"num_tokens": 1326560.0,
|
|
"step": 595
|
|
},
|
|
{
|
|
"entropy": 6.718612575531006,
|
|
"epoch": 0.06738922895490537,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0002995,
|
|
"loss": 6.553,
|
|
"mean_token_accuracy": 0.12826075702905654,
|
|
"num_tokens": 1339105.0,
|
|
"step": 600
|
|
},
|
|
{
|
|
"entropy": 6.350273942947387,
|
|
"epoch": 0.06795080586286292,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000302,
|
|
"loss": 6.2291,
|
|
"mean_token_accuracy": 0.13848018050193786,
|
|
"num_tokens": 1349914.0,
|
|
"step": 605
|
|
},
|
|
{
|
|
"entropy": 6.579149675369263,
|
|
"epoch": 0.06851238277082046,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0003045,
|
|
"loss": 6.4524,
|
|
"mean_token_accuracy": 0.13018497154116632,
|
|
"num_tokens": 1361700.0,
|
|
"step": 610
|
|
},
|
|
{
|
|
"entropy": 6.584105443954468,
|
|
"epoch": 0.06907395967877801,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000307,
|
|
"loss": 6.456,
|
|
"mean_token_accuracy": 0.13250951543450357,
|
|
"num_tokens": 1373103.0,
|
|
"step": 615
|
|
},
|
|
{
|
|
"entropy": 6.421159172058106,
|
|
"epoch": 0.06963553658673555,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0003095,
|
|
"loss": 6.2674,
|
|
"mean_token_accuracy": 0.13772882893681526,
|
|
"num_tokens": 1383742.0,
|
|
"step": 620
|
|
},
|
|
{
|
|
"entropy": 6.502809143066406,
|
|
"epoch": 0.0701971134946931,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000312,
|
|
"loss": 6.4221,
|
|
"mean_token_accuracy": 0.13373162150382994,
|
|
"num_tokens": 1396656.0,
|
|
"step": 625
|
|
},
|
|
{
|
|
"entropy": 6.531112861633301,
|
|
"epoch": 0.07075869040265065,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0003145,
|
|
"loss": 6.2977,
|
|
"mean_token_accuracy": 0.1519811674952507,
|
|
"num_tokens": 1406709.0,
|
|
"step": 630
|
|
},
|
|
{
|
|
"entropy": 6.507521104812622,
|
|
"epoch": 0.07132026731060818,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000317,
|
|
"loss": 6.3298,
|
|
"mean_token_accuracy": 0.14185064658522606,
|
|
"num_tokens": 1417793.0,
|
|
"step": 635
|
|
},
|
|
{
|
|
"entropy": 6.518734645843506,
|
|
"epoch": 0.07188184421856574,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0003195,
|
|
"loss": 6.418,
|
|
"mean_token_accuracy": 0.14041453301906587,
|
|
"num_tokens": 1429093.0,
|
|
"step": 640
|
|
},
|
|
{
|
|
"entropy": 6.450685930252075,
|
|
"epoch": 0.07244342112652327,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000322,
|
|
"loss": 6.3521,
|
|
"mean_token_accuracy": 0.14151380732655525,
|
|
"num_tokens": 1440907.0,
|
|
"step": 645
|
|
},
|
|
{
|
|
"entropy": 6.5532149314880375,
|
|
"epoch": 0.07300499803448082,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00032450000000000003,
|
|
"loss": 6.4215,
|
|
"mean_token_accuracy": 0.13366219252347947,
|
|
"num_tokens": 1452089.0,
|
|
"step": 650
|
|
},
|
|
{
|
|
"entropy": 6.611659145355224,
|
|
"epoch": 0.07356657494243837,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00032700000000000003,
|
|
"loss": 6.432,
|
|
"mean_token_accuracy": 0.1317155674099922,
|
|
"num_tokens": 1464378.0,
|
|
"step": 655
|
|
},
|
|
{
|
|
"entropy": 6.506606101989746,
|
|
"epoch": 0.07412815185039591,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00032950000000000004,
|
|
"loss": 6.3608,
|
|
"mean_token_accuracy": 0.13717821538448333,
|
|
"num_tokens": 1476678.0,
|
|
"step": 660
|
|
},
|
|
{
|
|
"entropy": 6.418495512008667,
|
|
"epoch": 0.07468972875835346,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00033200000000000005,
|
|
"loss": 6.199,
|
|
"mean_token_accuracy": 0.13983268588781356,
|
|
"num_tokens": 1486808.0,
|
|
"step": 665
|
|
},
|
|
{
|
|
"entropy": 6.513941431045533,
|
|
"epoch": 0.075251305666311,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00033450000000000005,
|
|
"loss": 6.5064,
|
|
"mean_token_accuracy": 0.13336510956287384,
|
|
"num_tokens": 1499281.0,
|
|
"step": 670
|
|
},
|
|
{
|
|
"entropy": 6.550311517715454,
|
|
"epoch": 0.07581288257426855,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.000337,
|
|
"loss": 6.3971,
|
|
"mean_token_accuracy": 0.13824842870235443,
|
|
"num_tokens": 1510202.0,
|
|
"step": 675
|
|
},
|
|
{
|
|
"entropy": 6.478364896774292,
|
|
"epoch": 0.07637445948222608,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0003395,
|
|
"loss": 6.2777,
|
|
"mean_token_accuracy": 0.14033918008208274,
|
|
"num_tokens": 1521492.0,
|
|
"step": 680
|
|
},
|
|
{
|
|
"entropy": 6.363365268707275,
|
|
"epoch": 0.07693603639018363,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000342,
|
|
"loss": 6.2901,
|
|
"mean_token_accuracy": 0.14578976929187776,
|
|
"num_tokens": 1532856.0,
|
|
"step": 685
|
|
},
|
|
{
|
|
"entropy": 6.4714092254638675,
|
|
"epoch": 0.07749761329814119,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00034449999999999997,
|
|
"loss": 6.293,
|
|
"mean_token_accuracy": 0.13803935647010804,
|
|
"num_tokens": 1543408.0,
|
|
"step": 690
|
|
},
|
|
{
|
|
"entropy": 6.445067262649536,
|
|
"epoch": 0.07805919020609872,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000347,
|
|
"loss": 6.3314,
|
|
"mean_token_accuracy": 0.13593096658587456,
|
|
"num_tokens": 1555474.0,
|
|
"step": 695
|
|
},
|
|
{
|
|
"entropy": 6.49391450881958,
|
|
"epoch": 0.07862076711405627,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0003495,
|
|
"loss": 6.4259,
|
|
"mean_token_accuracy": 0.1368790291249752,
|
|
"num_tokens": 1567484.0,
|
|
"step": 700
|
|
},
|
|
{
|
|
"entropy": 6.461107492446899,
|
|
"epoch": 0.07918234402201381,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000352,
|
|
"loss": 6.2683,
|
|
"mean_token_accuracy": 0.14710718691349028,
|
|
"num_tokens": 1578204.0,
|
|
"step": 705
|
|
},
|
|
{
|
|
"entropy": 6.4600510597229,
|
|
"epoch": 0.07974392092997136,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0003545,
|
|
"loss": 6.2575,
|
|
"mean_token_accuracy": 0.14133917540311813,
|
|
"num_tokens": 1589012.0,
|
|
"step": 710
|
|
},
|
|
{
|
|
"entropy": 6.342525625228882,
|
|
"epoch": 0.08030549783792891,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.000357,
|
|
"loss": 6.2677,
|
|
"mean_token_accuracy": 0.14088504314422606,
|
|
"num_tokens": 1601099.0,
|
|
"step": 715
|
|
},
|
|
{
|
|
"entropy": 6.518351411819458,
|
|
"epoch": 0.08086707474588645,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0003595,
|
|
"loss": 6.4327,
|
|
"mean_token_accuracy": 0.13333295062184333,
|
|
"num_tokens": 1612814.0,
|
|
"step": 720
|
|
},
|
|
{
|
|
"entropy": 6.471275472640992,
|
|
"epoch": 0.081428651653844,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000362,
|
|
"loss": 6.3316,
|
|
"mean_token_accuracy": 0.13668572530150414,
|
|
"num_tokens": 1624953.0,
|
|
"step": 725
|
|
},
|
|
{
|
|
"entropy": 6.470378446578979,
|
|
"epoch": 0.08199022856180153,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0003645,
|
|
"loss": 6.3809,
|
|
"mean_token_accuracy": 0.13890909254550934,
|
|
"num_tokens": 1635673.0,
|
|
"step": 730
|
|
},
|
|
{
|
|
"entropy": 6.376466226577759,
|
|
"epoch": 0.08255180546975908,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000367,
|
|
"loss": 6.2719,
|
|
"mean_token_accuracy": 0.1436118446290493,
|
|
"num_tokens": 1647282.0,
|
|
"step": 735
|
|
},
|
|
{
|
|
"entropy": 6.441848707199097,
|
|
"epoch": 0.08311338237771662,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0003695,
|
|
"loss": 6.2867,
|
|
"mean_token_accuracy": 0.14489989280700682,
|
|
"num_tokens": 1658426.0,
|
|
"step": 740
|
|
},
|
|
{
|
|
"entropy": 6.345063209533691,
|
|
"epoch": 0.08367495928567417,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000372,
|
|
"loss": 6.3131,
|
|
"mean_token_accuracy": 0.14454299807548524,
|
|
"num_tokens": 1669958.0,
|
|
"step": 745
|
|
},
|
|
{
|
|
"entropy": 6.474502325057983,
|
|
"epoch": 0.08423653619363172,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0003745,
|
|
"loss": 6.3825,
|
|
"mean_token_accuracy": 0.13400474563241005,
|
|
"num_tokens": 1682409.0,
|
|
"step": 750
|
|
},
|
|
{
|
|
"entropy": 6.442701625823974,
|
|
"epoch": 0.08479811310158926,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000377,
|
|
"loss": 6.3045,
|
|
"mean_token_accuracy": 0.14752128720283508,
|
|
"num_tokens": 1692409.0,
|
|
"step": 755
|
|
},
|
|
{
|
|
"entropy": 6.501216983795166,
|
|
"epoch": 0.08535969000954681,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0003795,
|
|
"loss": 6.3863,
|
|
"mean_token_accuracy": 0.13712989687919616,
|
|
"num_tokens": 1705018.0,
|
|
"step": 760
|
|
},
|
|
{
|
|
"entropy": 6.35915904045105,
|
|
"epoch": 0.08592126691750435,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000382,
|
|
"loss": 6.3271,
|
|
"mean_token_accuracy": 0.1366030417382717,
|
|
"num_tokens": 1715625.0,
|
|
"step": 765
|
|
},
|
|
{
|
|
"entropy": 6.459257507324219,
|
|
"epoch": 0.0864828438254619,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0003845,
|
|
"loss": 6.3949,
|
|
"mean_token_accuracy": 0.13145335242152215,
|
|
"num_tokens": 1727045.0,
|
|
"step": 770
|
|
},
|
|
{
|
|
"entropy": 6.523573160171509,
|
|
"epoch": 0.08704442073341945,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00038700000000000003,
|
|
"loss": 6.4586,
|
|
"mean_token_accuracy": 0.13751968517899513,
|
|
"num_tokens": 1737374.0,
|
|
"step": 775
|
|
},
|
|
{
|
|
"entropy": 6.468965530395508,
|
|
"epoch": 0.08760599764137698,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00038950000000000003,
|
|
"loss": 6.4517,
|
|
"mean_token_accuracy": 0.1402681902050972,
|
|
"num_tokens": 1747788.0,
|
|
"step": 780
|
|
},
|
|
{
|
|
"entropy": 6.297554206848145,
|
|
"epoch": 0.08816757454933453,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00039200000000000004,
|
|
"loss": 6.1546,
|
|
"mean_token_accuracy": 0.14846104085445405,
|
|
"num_tokens": 1757769.0,
|
|
"step": 785
|
|
},
|
|
{
|
|
"entropy": 6.381324434280396,
|
|
"epoch": 0.08872915145729207,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00039450000000000005,
|
|
"loss": 6.2715,
|
|
"mean_token_accuracy": 0.13741729855537416,
|
|
"num_tokens": 1769246.0,
|
|
"step": 790
|
|
},
|
|
{
|
|
"entropy": 6.461723899841308,
|
|
"epoch": 0.08929072836524962,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00039700000000000005,
|
|
"loss": 6.4011,
|
|
"mean_token_accuracy": 0.13841823786497115,
|
|
"num_tokens": 1781306.0,
|
|
"step": 795
|
|
},
|
|
{
|
|
"entropy": 6.396069002151489,
|
|
"epoch": 0.08985230527320717,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0003995,
|
|
"loss": 6.2957,
|
|
"mean_token_accuracy": 0.13979703485965728,
|
|
"num_tokens": 1792888.0,
|
|
"step": 800
|
|
},
|
|
{
|
|
"entropy": 6.42486801147461,
|
|
"epoch": 0.09041388218116471,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000402,
|
|
"loss": 6.3201,
|
|
"mean_token_accuracy": 0.14163311570882797,
|
|
"num_tokens": 1802938.0,
|
|
"step": 805
|
|
},
|
|
{
|
|
"entropy": 6.467221689224243,
|
|
"epoch": 0.09097545908912226,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004045,
|
|
"loss": 6.3228,
|
|
"mean_token_accuracy": 0.13640945702791213,
|
|
"num_tokens": 1814738.0,
|
|
"step": 810
|
|
},
|
|
{
|
|
"entropy": 6.423444128036499,
|
|
"epoch": 0.0915370359970798,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00040699999999999997,
|
|
"loss": 6.4079,
|
|
"mean_token_accuracy": 0.1382846400141716,
|
|
"num_tokens": 1825100.0,
|
|
"step": 815
|
|
},
|
|
{
|
|
"entropy": 6.2810968399047855,
|
|
"epoch": 0.09209861290503735,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004095,
|
|
"loss": 6.2361,
|
|
"mean_token_accuracy": 0.1458885870873928,
|
|
"num_tokens": 1835879.0,
|
|
"step": 820
|
|
},
|
|
{
|
|
"entropy": 6.548891592025757,
|
|
"epoch": 0.09266018981299488,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000412,
|
|
"loss": 6.3787,
|
|
"mean_token_accuracy": 0.13275464922189711,
|
|
"num_tokens": 1848352.0,
|
|
"step": 825
|
|
},
|
|
{
|
|
"entropy": 6.358658218383789,
|
|
"epoch": 0.09322176672095243,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004145,
|
|
"loss": 6.3266,
|
|
"mean_token_accuracy": 0.13629675209522246,
|
|
"num_tokens": 1859687.0,
|
|
"step": 830
|
|
},
|
|
{
|
|
"entropy": 6.3769364833831785,
|
|
"epoch": 0.09378334362890998,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000417,
|
|
"loss": 6.3259,
|
|
"mean_token_accuracy": 0.13939538821578026,
|
|
"num_tokens": 1871438.0,
|
|
"step": 835
|
|
},
|
|
{
|
|
"entropy": 6.295517444610596,
|
|
"epoch": 0.09434492053686752,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004195,
|
|
"loss": 6.195,
|
|
"mean_token_accuracy": 0.1484709143638611,
|
|
"num_tokens": 1881519.0,
|
|
"step": 840
|
|
},
|
|
{
|
|
"entropy": 6.5199895858764645,
|
|
"epoch": 0.09490649744482507,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000422,
|
|
"loss": 6.4049,
|
|
"mean_token_accuracy": 0.13696413338184357,
|
|
"num_tokens": 1892428.0,
|
|
"step": 845
|
|
},
|
|
{
|
|
"entropy": 6.450248670578003,
|
|
"epoch": 0.09546807435278261,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004245,
|
|
"loss": 6.2804,
|
|
"mean_token_accuracy": 0.1426387369632721,
|
|
"num_tokens": 1903760.0,
|
|
"step": 850
|
|
},
|
|
{
|
|
"entropy": 6.360091924667358,
|
|
"epoch": 0.09602965126074016,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000427,
|
|
"loss": 6.359,
|
|
"mean_token_accuracy": 0.13211985379457475,
|
|
"num_tokens": 1915430.0,
|
|
"step": 855
|
|
},
|
|
{
|
|
"entropy": 6.364841318130493,
|
|
"epoch": 0.09659122816869771,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004295,
|
|
"loss": 6.312,
|
|
"mean_token_accuracy": 0.13486656472086905,
|
|
"num_tokens": 1925709.0,
|
|
"step": 860
|
|
},
|
|
{
|
|
"entropy": 6.435139513015747,
|
|
"epoch": 0.09715280507665525,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000432,
|
|
"loss": 6.3714,
|
|
"mean_token_accuracy": 0.13526980876922606,
|
|
"num_tokens": 1938148.0,
|
|
"step": 865
|
|
},
|
|
{
|
|
"entropy": 6.1814793109893795,
|
|
"epoch": 0.0977143819846128,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004345,
|
|
"loss": 6.2161,
|
|
"mean_token_accuracy": 0.14539682120084763,
|
|
"num_tokens": 1949028.0,
|
|
"step": 870
|
|
},
|
|
{
|
|
"entropy": 6.381429719924927,
|
|
"epoch": 0.09827595889257033,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000437,
|
|
"loss": 6.2716,
|
|
"mean_token_accuracy": 0.14102880284190178,
|
|
"num_tokens": 1960353.0,
|
|
"step": 875
|
|
},
|
|
{
|
|
"entropy": 6.478352308273315,
|
|
"epoch": 0.09883753580052788,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004395,
|
|
"loss": 6.4072,
|
|
"mean_token_accuracy": 0.1384950503706932,
|
|
"num_tokens": 1972335.0,
|
|
"step": 880
|
|
},
|
|
{
|
|
"entropy": 6.287540864944458,
|
|
"epoch": 0.09939911270848542,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000442,
|
|
"loss": 6.2435,
|
|
"mean_token_accuracy": 0.13890341594815253,
|
|
"num_tokens": 1982851.0,
|
|
"step": 885
|
|
},
|
|
{
|
|
"entropy": 6.266198635101318,
|
|
"epoch": 0.09996068961644297,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004445,
|
|
"loss": 6.2305,
|
|
"mean_token_accuracy": 0.14235106781125068,
|
|
"num_tokens": 1993931.0,
|
|
"step": 890
|
|
},
|
|
{
|
|
"entropy": 6.41697473526001,
|
|
"epoch": 0.10052226652440052,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000447,
|
|
"loss": 6.3631,
|
|
"mean_token_accuracy": 0.1405455969274044,
|
|
"num_tokens": 2004838.0,
|
|
"step": 895
|
|
},
|
|
{
|
|
"entropy": 6.252490043640137,
|
|
"epoch": 0.10108384343235806,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00044950000000000003,
|
|
"loss": 6.1584,
|
|
"mean_token_accuracy": 0.14193521440029144,
|
|
"num_tokens": 2015620.0,
|
|
"step": 900
|
|
},
|
|
{
|
|
"entropy": 6.32470383644104,
|
|
"epoch": 0.10164542034031561,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00045200000000000004,
|
|
"loss": 6.2855,
|
|
"mean_token_accuracy": 0.1429427184164524,
|
|
"num_tokens": 2027489.0,
|
|
"step": 905
|
|
},
|
|
{
|
|
"entropy": 6.2411714553833,
|
|
"epoch": 0.10220699724827315,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00045450000000000004,
|
|
"loss": 6.1741,
|
|
"mean_token_accuracy": 0.14678896516561507,
|
|
"num_tokens": 2038475.0,
|
|
"step": 910
|
|
},
|
|
{
|
|
"entropy": 6.2395162105560305,
|
|
"epoch": 0.1027685741562307,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00045700000000000005,
|
|
"loss": 6.1705,
|
|
"mean_token_accuracy": 0.1411990463733673,
|
|
"num_tokens": 2048938.0,
|
|
"step": 915
|
|
},
|
|
{
|
|
"entropy": 6.229062700271607,
|
|
"epoch": 0.10333015106418825,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00045950000000000006,
|
|
"loss": 6.2775,
|
|
"mean_token_accuracy": 0.13909629583358765,
|
|
"num_tokens": 2060372.0,
|
|
"step": 920
|
|
},
|
|
{
|
|
"entropy": 6.308560037612915,
|
|
"epoch": 0.10389172797214578,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000462,
|
|
"loss": 6.2487,
|
|
"mean_token_accuracy": 0.13983388617634773,
|
|
"num_tokens": 2071558.0,
|
|
"step": 925
|
|
},
|
|
{
|
|
"entropy": 6.3064391136169435,
|
|
"epoch": 0.10445330488010333,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004645,
|
|
"loss": 6.2987,
|
|
"mean_token_accuracy": 0.1368556186556816,
|
|
"num_tokens": 2082350.0,
|
|
"step": 930
|
|
},
|
|
{
|
|
"entropy": 6.3746119976043705,
|
|
"epoch": 0.10501488178806087,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000467,
|
|
"loss": 6.3368,
|
|
"mean_token_accuracy": 0.1350345179438591,
|
|
"num_tokens": 2093448.0,
|
|
"step": 935
|
|
},
|
|
{
|
|
"entropy": 6.493036365509033,
|
|
"epoch": 0.10557645869601842,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004695,
|
|
"loss": 6.3681,
|
|
"mean_token_accuracy": 0.13741556107997893,
|
|
"num_tokens": 2104171.0,
|
|
"step": 940
|
|
},
|
|
{
|
|
"entropy": 6.2003154277801515,
|
|
"epoch": 0.10613803560397596,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.000472,
|
|
"loss": 6.2705,
|
|
"mean_token_accuracy": 0.1359943650662899,
|
|
"num_tokens": 2114496.0,
|
|
"step": 945
|
|
},
|
|
{
|
|
"entropy": 6.376204109191894,
|
|
"epoch": 0.10669961251193351,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004745,
|
|
"loss": 6.2566,
|
|
"mean_token_accuracy": 0.1408710964024067,
|
|
"num_tokens": 2125930.0,
|
|
"step": 950
|
|
},
|
|
{
|
|
"entropy": 6.257950973510742,
|
|
"epoch": 0.10726118941989106,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000477,
|
|
"loss": 6.2212,
|
|
"mean_token_accuracy": 0.14402413070201875,
|
|
"num_tokens": 2136452.0,
|
|
"step": 955
|
|
},
|
|
{
|
|
"entropy": 6.282464265823364,
|
|
"epoch": 0.1078227663278486,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004795,
|
|
"loss": 6.3404,
|
|
"mean_token_accuracy": 0.13901666328310966,
|
|
"num_tokens": 2148233.0,
|
|
"step": 960
|
|
},
|
|
{
|
|
"entropy": 6.241464614868164,
|
|
"epoch": 0.10838434323580615,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000482,
|
|
"loss": 6.1153,
|
|
"mean_token_accuracy": 0.1443318985402584,
|
|
"num_tokens": 2159475.0,
|
|
"step": 965
|
|
},
|
|
{
|
|
"entropy": 6.1993176460266115,
|
|
"epoch": 0.10894592014376368,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004845,
|
|
"loss": 6.2461,
|
|
"mean_token_accuracy": 0.1433636873960495,
|
|
"num_tokens": 2170042.0,
|
|
"step": 970
|
|
},
|
|
{
|
|
"entropy": 6.288603162765503,
|
|
"epoch": 0.10950749705172123,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000487,
|
|
"loss": 6.2437,
|
|
"mean_token_accuracy": 0.13873123675584792,
|
|
"num_tokens": 2182234.0,
|
|
"step": 975
|
|
},
|
|
{
|
|
"entropy": 6.20459680557251,
|
|
"epoch": 0.11006907395967878,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004895,
|
|
"loss": 6.2355,
|
|
"mean_token_accuracy": 0.14040311500430108,
|
|
"num_tokens": 2192477.0,
|
|
"step": 980
|
|
},
|
|
{
|
|
"entropy": 6.208745098114013,
|
|
"epoch": 0.11063065086763632,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000492,
|
|
"loss": 6.2087,
|
|
"mean_token_accuracy": 0.13950579315423967,
|
|
"num_tokens": 2203082.0,
|
|
"step": 985
|
|
},
|
|
{
|
|
"entropy": 6.242075681686401,
|
|
"epoch": 0.11119222777559387,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004945,
|
|
"loss": 6.178,
|
|
"mean_token_accuracy": 0.14390679448843002,
|
|
"num_tokens": 2213684.0,
|
|
"step": 990
|
|
},
|
|
{
|
|
"entropy": 6.218676996231079,
|
|
"epoch": 0.11175380468355141,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000497,
|
|
"loss": 6.209,
|
|
"mean_token_accuracy": 0.13738821148872377,
|
|
"num_tokens": 2225524.0,
|
|
"step": 995
|
|
},
|
|
{
|
|
"entropy": 6.2625988006591795,
|
|
"epoch": 0.11231538159150896,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004995,
|
|
"loss": 6.1674,
|
|
"mean_token_accuracy": 0.14143801629543304,
|
|
"num_tokens": 2236004.0,
|
|
"step": 1000
|
|
},
|
|
{
|
|
"entropy": 6.335353660583496,
|
|
"epoch": 0.1128769584994665,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000499999997707492,
|
|
"loss": 6.3267,
|
|
"mean_token_accuracy": 0.13301377221941948,
|
|
"num_tokens": 2247730.0,
|
|
"step": 1005
|
|
},
|
|
{
|
|
"entropy": 6.29675931930542,
|
|
"epoch": 0.11343853540742405,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999999883941787,
|
|
"loss": 6.2836,
|
|
"mean_token_accuracy": 0.14176394045352936,
|
|
"num_tokens": 2260132.0,
|
|
"step": 1010
|
|
},
|
|
{
|
|
"entropy": 6.2044346809387205,
|
|
"epoch": 0.1140001123153816,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999999719167785,
|
|
"loss": 6.2477,
|
|
"mean_token_accuracy": 0.14374205321073533,
|
|
"num_tokens": 2270060.0,
|
|
"step": 1015
|
|
},
|
|
{
|
|
"entropy": 6.291596841812134,
|
|
"epoch": 0.11456168922333913,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999999482752917,
|
|
"loss": 6.2676,
|
|
"mean_token_accuracy": 0.14092471450567245,
|
|
"num_tokens": 2281568.0,
|
|
"step": 1020
|
|
},
|
|
{
|
|
"entropy": 6.234738063812256,
|
|
"epoch": 0.11512326613129668,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999999174697195,
|
|
"loss": 6.2891,
|
|
"mean_token_accuracy": 0.13759731277823448,
|
|
"num_tokens": 2293325.0,
|
|
"step": 1025
|
|
},
|
|
{
|
|
"entropy": 6.364012956619263,
|
|
"epoch": 0.11568484303925422,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999998795000627,
|
|
"loss": 6.279,
|
|
"mean_token_accuracy": 0.142484587430954,
|
|
"num_tokens": 2304780.0,
|
|
"step": 1030
|
|
},
|
|
{
|
|
"entropy": 6.17555603981018,
|
|
"epoch": 0.11624641994721177,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999998343663223,
|
|
"loss": 6.2167,
|
|
"mean_token_accuracy": 0.13944805189967155,
|
|
"num_tokens": 2315999.0,
|
|
"step": 1035
|
|
},
|
|
{
|
|
"entropy": 6.316880798339843,
|
|
"epoch": 0.11680799685516932,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999997820685,
|
|
"loss": 6.3785,
|
|
"mean_token_accuracy": 0.1423812247812748,
|
|
"num_tokens": 2326695.0,
|
|
"step": 1040
|
|
},
|
|
{
|
|
"entropy": 6.304249572753906,
|
|
"epoch": 0.11736957376312686,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999997226065974,
|
|
"loss": 6.2032,
|
|
"mean_token_accuracy": 0.14872457087039948,
|
|
"num_tokens": 2336925.0,
|
|
"step": 1045
|
|
},
|
|
{
|
|
"entropy": 6.186109495162964,
|
|
"epoch": 0.11793115067108441,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999996559806163,
|
|
"loss": 6.1183,
|
|
"mean_token_accuracy": 0.14349379688501357,
|
|
"num_tokens": 2347431.0,
|
|
"step": 1050
|
|
},
|
|
{
|
|
"entropy": 6.174486351013184,
|
|
"epoch": 0.11849272757904195,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999995821905589,
|
|
"loss": 6.222,
|
|
"mean_token_accuracy": 0.14372190833091736,
|
|
"num_tokens": 2359894.0,
|
|
"step": 1055
|
|
},
|
|
{
|
|
"entropy": 6.233391332626343,
|
|
"epoch": 0.1190543044869995,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999995012364276,
|
|
"loss": 6.2421,
|
|
"mean_token_accuracy": 0.14038106054067612,
|
|
"num_tokens": 2371181.0,
|
|
"step": 1060
|
|
},
|
|
{
|
|
"entropy": 6.264003944396973,
|
|
"epoch": 0.11961588139495703,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004999994131182248,
|
|
"loss": 6.1404,
|
|
"mean_token_accuracy": 0.14172154366970063,
|
|
"num_tokens": 2381531.0,
|
|
"step": 1065
|
|
},
|
|
{
|
|
"entropy": 6.283302164077758,
|
|
"epoch": 0.12017745830291458,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999993178359535,
|
|
"loss": 6.2758,
|
|
"mean_token_accuracy": 0.14069122895598413,
|
|
"num_tokens": 2391573.0,
|
|
"step": 1070
|
|
},
|
|
{
|
|
"entropy": 6.221704006195068,
|
|
"epoch": 0.12073903521087213,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999992153896166,
|
|
"loss": 6.2438,
|
|
"mean_token_accuracy": 0.14414030984044074,
|
|
"num_tokens": 2402822.0,
|
|
"step": 1075
|
|
},
|
|
{
|
|
"entropy": 6.1785337924957275,
|
|
"epoch": 0.12130061211882967,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004999991057792175,
|
|
"loss": 6.1556,
|
|
"mean_token_accuracy": 0.1388797678053379,
|
|
"num_tokens": 2414322.0,
|
|
"step": 1080
|
|
},
|
|
{
|
|
"entropy": 6.271573257446289,
|
|
"epoch": 0.12186218902678722,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999989890047596,
|
|
"loss": 6.3473,
|
|
"mean_token_accuracy": 0.14235838428139685,
|
|
"num_tokens": 2426560.0,
|
|
"step": 1085
|
|
},
|
|
{
|
|
"entropy": 6.270335340499878,
|
|
"epoch": 0.12242376593474476,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999988650662467,
|
|
"loss": 6.2468,
|
|
"mean_token_accuracy": 0.14222736656665802,
|
|
"num_tokens": 2437723.0,
|
|
"step": 1090
|
|
},
|
|
{
|
|
"entropy": 6.153625774383545,
|
|
"epoch": 0.12298534284270231,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999987339636825,
|
|
"loss": 6.1991,
|
|
"mean_token_accuracy": 0.14895833060145378,
|
|
"num_tokens": 2448497.0,
|
|
"step": 1095
|
|
},
|
|
{
|
|
"entropy": 6.157371854782104,
|
|
"epoch": 0.12354691975065986,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999985956970713,
|
|
"loss": 6.0728,
|
|
"mean_token_accuracy": 0.15379315465688706,
|
|
"num_tokens": 2459089.0,
|
|
"step": 1100
|
|
},
|
|
{
|
|
"entropy": 6.129484939575195,
|
|
"epoch": 0.1241084966586174,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999984502664178,
|
|
"loss": 6.1597,
|
|
"mean_token_accuracy": 0.14950370639562607,
|
|
"num_tokens": 2469882.0,
|
|
"step": 1105
|
|
},
|
|
{
|
|
"entropy": 6.1923255443573,
|
|
"epoch": 0.12467007356657495,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999982976717261,
|
|
"loss": 6.1939,
|
|
"mean_token_accuracy": 0.14724715948104858,
|
|
"num_tokens": 2482120.0,
|
|
"step": 1110
|
|
},
|
|
{
|
|
"entropy": 6.231283187866211,
|
|
"epoch": 0.1252316504745325,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999981379130016,
|
|
"loss": 6.2066,
|
|
"mean_token_accuracy": 0.14431151151657104,
|
|
"num_tokens": 2492626.0,
|
|
"step": 1115
|
|
},
|
|
{
|
|
"entropy": 6.266522312164307,
|
|
"epoch": 0.12579322738249002,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000499997970990249,
|
|
"loss": 6.2584,
|
|
"mean_token_accuracy": 0.1434864081442356,
|
|
"num_tokens": 2506347.0,
|
|
"step": 1120
|
|
},
|
|
{
|
|
"entropy": 6.067158842086792,
|
|
"epoch": 0.12635480429044757,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999977969034737,
|
|
"loss": 6.1402,
|
|
"mean_token_accuracy": 0.15051724016666412,
|
|
"num_tokens": 2516584.0,
|
|
"step": 1125
|
|
},
|
|
{
|
|
"entropy": 6.22009768486023,
|
|
"epoch": 0.12691638119840512,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999976156526814,
|
|
"loss": 6.1856,
|
|
"mean_token_accuracy": 0.14873197600245475,
|
|
"num_tokens": 2526731.0,
|
|
"step": 1130
|
|
},
|
|
{
|
|
"entropy": 6.165716361999512,
|
|
"epoch": 0.12747795810636267,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999974272378776,
|
|
"loss": 6.0988,
|
|
"mean_token_accuracy": 0.1502756729722023,
|
|
"num_tokens": 2537180.0,
|
|
"step": 1135
|
|
},
|
|
{
|
|
"entropy": 6.150550699234008,
|
|
"epoch": 0.12803953501432022,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999972316590685,
|
|
"loss": 6.1675,
|
|
"mean_token_accuracy": 0.14633068516850473,
|
|
"num_tokens": 2547617.0,
|
|
"step": 1140
|
|
},
|
|
{
|
|
"entropy": 6.15447096824646,
|
|
"epoch": 0.12860111192227774,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999970289162604,
|
|
"loss": 6.0589,
|
|
"mean_token_accuracy": 0.15604657232761382,
|
|
"num_tokens": 2557743.0,
|
|
"step": 1145
|
|
},
|
|
{
|
|
"entropy": 6.099272203445435,
|
|
"epoch": 0.1291626888302353,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999968190094595,
|
|
"loss": 6.1532,
|
|
"mean_token_accuracy": 0.14685856103897094,
|
|
"num_tokens": 2568351.0,
|
|
"step": 1150
|
|
},
|
|
{
|
|
"entropy": 6.13305516242981,
|
|
"epoch": 0.12972426573819285,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999966019386727,
|
|
"loss": 6.22,
|
|
"mean_token_accuracy": 0.14849678426980972,
|
|
"num_tokens": 2579703.0,
|
|
"step": 1155
|
|
},
|
|
{
|
|
"entropy": 6.29257230758667,
|
|
"epoch": 0.1302858426461504,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999963777039067,
|
|
"loss": 6.1955,
|
|
"mean_token_accuracy": 0.14582142382860183,
|
|
"num_tokens": 2591197.0,
|
|
"step": 1160
|
|
},
|
|
{
|
|
"entropy": 6.143500089645386,
|
|
"epoch": 0.13084741955410795,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000499996146305169,
|
|
"loss": 6.1668,
|
|
"mean_token_accuracy": 0.14330864027142526,
|
|
"num_tokens": 2601836.0,
|
|
"step": 1165
|
|
},
|
|
{
|
|
"entropy": 6.083126783370972,
|
|
"epoch": 0.13140899646206547,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999959077424665,
|
|
"loss": 6.1079,
|
|
"mean_token_accuracy": 0.1498291090130806,
|
|
"num_tokens": 2613513.0,
|
|
"step": 1170
|
|
},
|
|
{
|
|
"entropy": 6.128898954391479,
|
|
"epoch": 0.13197057337002302,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004999956620158072,
|
|
"loss": 6.1413,
|
|
"mean_token_accuracy": 0.14912581145763398,
|
|
"num_tokens": 2625246.0,
|
|
"step": 1175
|
|
},
|
|
{
|
|
"entropy": 6.137507438659668,
|
|
"epoch": 0.13253215027798057,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004999954091251987,
|
|
"loss": 6.1053,
|
|
"mean_token_accuracy": 0.14960974007844924,
|
|
"num_tokens": 2636375.0,
|
|
"step": 1180
|
|
},
|
|
{
|
|
"entropy": 6.159454727172852,
|
|
"epoch": 0.13309372718593812,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999951490706491,
|
|
"loss": 6.2012,
|
|
"mean_token_accuracy": 0.14142030403017997,
|
|
"num_tokens": 2648586.0,
|
|
"step": 1185
|
|
},
|
|
{
|
|
"entropy": 6.1870311260223385,
|
|
"epoch": 0.13365530409389567,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999948818521667,
|
|
"loss": 6.2085,
|
|
"mean_token_accuracy": 0.15162340849637984,
|
|
"num_tokens": 2660847.0,
|
|
"step": 1190
|
|
},
|
|
{
|
|
"entropy": 6.215510368347168,
|
|
"epoch": 0.1342168810018532,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00049999460746976,
|
|
"loss": 6.1379,
|
|
"mean_token_accuracy": 0.14824316501617432,
|
|
"num_tokens": 2671160.0,
|
|
"step": 1195
|
|
},
|
|
{
|
|
"entropy": 6.205865049362183,
|
|
"epoch": 0.13477845790981074,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999943259234377,
|
|
"loss": 6.249,
|
|
"mean_token_accuracy": 0.1429877385497093,
|
|
"num_tokens": 2681622.0,
|
|
"step": 1200
|
|
},
|
|
{
|
|
"entropy": 6.0475321292877195,
|
|
"epoch": 0.1353400348177683,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999940372132089,
|
|
"loss": 6.05,
|
|
"mean_token_accuracy": 0.15074699968099595,
|
|
"num_tokens": 2691503.0,
|
|
"step": 1205
|
|
},
|
|
{
|
|
"entropy": 6.133896541595459,
|
|
"epoch": 0.13590161172572585,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999937413390826,
|
|
"loss": 6.1482,
|
|
"mean_token_accuracy": 0.14561435282230378,
|
|
"num_tokens": 2702207.0,
|
|
"step": 1210
|
|
},
|
|
{
|
|
"entropy": 6.135827493667603,
|
|
"epoch": 0.1364631886336834,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004999934383010683,
|
|
"loss": 6.1481,
|
|
"mean_token_accuracy": 0.1448237679898739,
|
|
"num_tokens": 2713178.0,
|
|
"step": 1215
|
|
},
|
|
{
|
|
"entropy": 6.2300678253173825,
|
|
"epoch": 0.13702476554164092,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999931280991757,
|
|
"loss": 6.1363,
|
|
"mean_token_accuracy": 0.15154407769441605,
|
|
"num_tokens": 2723717.0,
|
|
"step": 1220
|
|
},
|
|
{
|
|
"entropy": 6.124025821685791,
|
|
"epoch": 0.13758634244959847,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999928107334146,
|
|
"loss": 6.2217,
|
|
"mean_token_accuracy": 0.14136773943901063,
|
|
"num_tokens": 2735669.0,
|
|
"step": 1225
|
|
},
|
|
{
|
|
"entropy": 6.099333381652832,
|
|
"epoch": 0.13814791935755602,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999924862037952,
|
|
"loss": 6.1166,
|
|
"mean_token_accuracy": 0.15113521963357926,
|
|
"num_tokens": 2746087.0,
|
|
"step": 1230
|
|
},
|
|
{
|
|
"entropy": 6.119935989379883,
|
|
"epoch": 0.13870949626551357,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999921545103278,
|
|
"loss": 6.1391,
|
|
"mean_token_accuracy": 0.1446000136435032,
|
|
"num_tokens": 2757143.0,
|
|
"step": 1235
|
|
},
|
|
{
|
|
"entropy": 6.234173107147217,
|
|
"epoch": 0.1392710731734711,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999918156530229,
|
|
"loss": 6.2428,
|
|
"mean_token_accuracy": 0.14500228315591812,
|
|
"num_tokens": 2769340.0,
|
|
"step": 1240
|
|
},
|
|
{
|
|
"entropy": 6.175450468063355,
|
|
"epoch": 0.13983265008142864,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999914696318913,
|
|
"loss": 6.1589,
|
|
"mean_token_accuracy": 0.14806368499994277,
|
|
"num_tokens": 2779514.0,
|
|
"step": 1245
|
|
},
|
|
{
|
|
"entropy": 6.119281053543091,
|
|
"epoch": 0.1403942269893862,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999911164469441,
|
|
"loss": 6.0888,
|
|
"mean_token_accuracy": 0.15193744301795958,
|
|
"num_tokens": 2790801.0,
|
|
"step": 1250
|
|
},
|
|
{
|
|
"entropy": 6.1100088596344,
|
|
"epoch": 0.14095580389734375,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999907560981925,
|
|
"loss": 6.0847,
|
|
"mean_token_accuracy": 0.14798859357833863,
|
|
"num_tokens": 2801082.0,
|
|
"step": 1255
|
|
},
|
|
{
|
|
"entropy": 6.083402299880982,
|
|
"epoch": 0.1415173808053013,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999903885856479,
|
|
"loss": 6.1062,
|
|
"mean_token_accuracy": 0.14728771150112152,
|
|
"num_tokens": 2812719.0,
|
|
"step": 1260
|
|
},
|
|
{
|
|
"entropy": 6.076613521575927,
|
|
"epoch": 0.14207895771325882,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000499990013909322,
|
|
"loss": 6.1067,
|
|
"mean_token_accuracy": 0.1431245759129524,
|
|
"num_tokens": 2823766.0,
|
|
"step": 1265
|
|
},
|
|
{
|
|
"entropy": 6.133080291748047,
|
|
"epoch": 0.14264053462121637,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000499989632069227,
|
|
"loss": 6.1957,
|
|
"mean_token_accuracy": 0.14594514071941375,
|
|
"num_tokens": 2834801.0,
|
|
"step": 1270
|
|
},
|
|
{
|
|
"entropy": 6.081394481658935,
|
|
"epoch": 0.14320211152917392,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999892430653747,
|
|
"loss": 6.0072,
|
|
"mean_token_accuracy": 0.15184544026851654,
|
|
"num_tokens": 2845769.0,
|
|
"step": 1275
|
|
},
|
|
{
|
|
"entropy": 6.042043972015381,
|
|
"epoch": 0.14376368843713147,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999888468977776,
|
|
"loss": 6.0533,
|
|
"mean_token_accuracy": 0.15463033318519592,
|
|
"num_tokens": 2856001.0,
|
|
"step": 1280
|
|
},
|
|
{
|
|
"entropy": 6.135152864456177,
|
|
"epoch": 0.14432526534508902,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999884435664485,
|
|
"loss": 6.0896,
|
|
"mean_token_accuracy": 0.14773025661706923,
|
|
"num_tokens": 2867703.0,
|
|
"step": 1285
|
|
},
|
|
{
|
|
"entropy": 5.996362161636353,
|
|
"epoch": 0.14488684225304654,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004999880330714,
|
|
"loss": 6.0314,
|
|
"mean_token_accuracy": 0.15192831605672835,
|
|
"num_tokens": 2878671.0,
|
|
"step": 1290
|
|
},
|
|
{
|
|
"entropy": 6.103845834732056,
|
|
"epoch": 0.1454484191610041,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999876154126453,
|
|
"loss": 6.1468,
|
|
"mean_token_accuracy": 0.14183202311396598,
|
|
"num_tokens": 2890137.0,
|
|
"step": 1295
|
|
},
|
|
{
|
|
"entropy": 6.1058008670806885,
|
|
"epoch": 0.14600999606896164,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999871905901977,
|
|
"loss": 6.0485,
|
|
"mean_token_accuracy": 0.15308912694454194,
|
|
"num_tokens": 2900344.0,
|
|
"step": 1300
|
|
},
|
|
{
|
|
"entropy": 6.0173821449279785,
|
|
"epoch": 0.1465715729769192,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999867586040706,
|
|
"loss": 6.0786,
|
|
"mean_token_accuracy": 0.14948148727416993,
|
|
"num_tokens": 2912270.0,
|
|
"step": 1305
|
|
},
|
|
{
|
|
"entropy": 6.176186656951904,
|
|
"epoch": 0.14713314988487675,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999863194542779,
|
|
"loss": 6.1416,
|
|
"mean_token_accuracy": 0.14145402163267135,
|
|
"num_tokens": 2924677.0,
|
|
"step": 1310
|
|
},
|
|
{
|
|
"entropy": 5.98449125289917,
|
|
"epoch": 0.14769472679283427,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999858731408336,
|
|
"loss": 6.0758,
|
|
"mean_token_accuracy": 0.14689501821994783,
|
|
"num_tokens": 2935794.0,
|
|
"step": 1315
|
|
},
|
|
{
|
|
"entropy": 6.144368124008179,
|
|
"epoch": 0.14825630370079182,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999854196637518,
|
|
"loss": 6.1803,
|
|
"mean_token_accuracy": 0.1436318762600422,
|
|
"num_tokens": 2945958.0,
|
|
"step": 1320
|
|
},
|
|
{
|
|
"entropy": 6.140670251846314,
|
|
"epoch": 0.14881788060874937,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999849590230469,
|
|
"loss": 6.1384,
|
|
"mean_token_accuracy": 0.14359039589762687,
|
|
"num_tokens": 2957536.0,
|
|
"step": 1325
|
|
},
|
|
{
|
|
"entropy": 6.109699487686157,
|
|
"epoch": 0.14937945751670692,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999844912187336,
|
|
"loss": 6.1209,
|
|
"mean_token_accuracy": 0.145068246871233,
|
|
"num_tokens": 2967787.0,
|
|
"step": 1330
|
|
},
|
|
{
|
|
"entropy": 6.110361862182617,
|
|
"epoch": 0.14994103442466447,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000499984016250827,
|
|
"loss": 6.137,
|
|
"mean_token_accuracy": 0.1437262400984764,
|
|
"num_tokens": 2980522.0,
|
|
"step": 1335
|
|
},
|
|
{
|
|
"entropy": 5.966966819763184,
|
|
"epoch": 0.150502611332622,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000499983534119342,
|
|
"loss": 6.0733,
|
|
"mean_token_accuracy": 0.15085284113883973,
|
|
"num_tokens": 2990497.0,
|
|
"step": 1340
|
|
},
|
|
{
|
|
"entropy": 6.219952869415283,
|
|
"epoch": 0.15106418824057954,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004999830448242941,
|
|
"loss": 6.163,
|
|
"mean_token_accuracy": 0.14726221784949303,
|
|
"num_tokens": 3002931.0,
|
|
"step": 1345
|
|
},
|
|
{
|
|
"entropy": 6.013589143753052,
|
|
"epoch": 0.1516257651485371,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004999825483656986,
|
|
"loss": 6.0739,
|
|
"mean_token_accuracy": 0.15152935981750487,
|
|
"num_tokens": 3014137.0,
|
|
"step": 1350
|
|
},
|
|
{
|
|
"entropy": 6.241993951797485,
|
|
"epoch": 0.15218734205649465,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999820447435716,
|
|
"loss": 6.2617,
|
|
"mean_token_accuracy": 0.14130268543958663,
|
|
"num_tokens": 3026145.0,
|
|
"step": 1355
|
|
},
|
|
{
|
|
"entropy": 6.032399415969849,
|
|
"epoch": 0.15274891896445217,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999815339579291,
|
|
"loss": 6.1122,
|
|
"mean_token_accuracy": 0.14616605639457703,
|
|
"num_tokens": 3037068.0,
|
|
"step": 1360
|
|
},
|
|
{
|
|
"entropy": 6.133391094207764,
|
|
"epoch": 0.15331049587240972,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999810160087872,
|
|
"loss": 6.034,
|
|
"mean_token_accuracy": 0.1539703369140625,
|
|
"num_tokens": 3047836.0,
|
|
"step": 1365
|
|
},
|
|
{
|
|
"entropy": 6.099278354644776,
|
|
"epoch": 0.15387207278036727,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004999804908961626,
|
|
"loss": 6.1684,
|
|
"mean_token_accuracy": 0.14856233298778534,
|
|
"num_tokens": 3060309.0,
|
|
"step": 1370
|
|
},
|
|
{
|
|
"entropy": 6.092678594589233,
|
|
"epoch": 0.15443364968832482,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999799586200719,
|
|
"loss": 6.1375,
|
|
"mean_token_accuracy": 0.15069601237773894,
|
|
"num_tokens": 3071789.0,
|
|
"step": 1375
|
|
},
|
|
{
|
|
"entropy": 6.0972583293914795,
|
|
"epoch": 0.15499522659628237,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000499979419180532,
|
|
"loss": 6.0467,
|
|
"mean_token_accuracy": 0.15597807765007018,
|
|
"num_tokens": 3081756.0,
|
|
"step": 1380
|
|
},
|
|
{
|
|
"entropy": 6.030021715164184,
|
|
"epoch": 0.1555568035042399,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999788725775601,
|
|
"loss": 6.1537,
|
|
"mean_token_accuracy": 0.14404376447200776,
|
|
"num_tokens": 3093456.0,
|
|
"step": 1385
|
|
},
|
|
{
|
|
"entropy": 6.176510953903199,
|
|
"epoch": 0.15611838041219744,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999783188111737,
|
|
"loss": 6.083,
|
|
"mean_token_accuracy": 0.15343996584415437,
|
|
"num_tokens": 3104565.0,
|
|
"step": 1390
|
|
},
|
|
{
|
|
"entropy": 6.049490928649902,
|
|
"epoch": 0.156679957320155,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999777578813904,
|
|
"loss": 6.0964,
|
|
"mean_token_accuracy": 0.14417065382003785,
|
|
"num_tokens": 3115577.0,
|
|
"step": 1395
|
|
},
|
|
{
|
|
"entropy": 6.068271827697754,
|
|
"epoch": 0.15724153422811254,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000499977189788228,
|
|
"loss": 5.9898,
|
|
"mean_token_accuracy": 0.1535682797431946,
|
|
"num_tokens": 3126019.0,
|
|
"step": 1400
|
|
},
|
|
{
|
|
"entropy": 6.11846694946289,
|
|
"epoch": 0.1578031111360701,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999766145317046,
|
|
"loss": 6.1593,
|
|
"mean_token_accuracy": 0.14163137823343278,
|
|
"num_tokens": 3136191.0,
|
|
"step": 1405
|
|
},
|
|
{
|
|
"entropy": 6.1475354671478275,
|
|
"epoch": 0.15836468804402762,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999760321118385,
|
|
"loss": 6.0184,
|
|
"mean_token_accuracy": 0.14922462552785873,
|
|
"num_tokens": 3147737.0,
|
|
"step": 1410
|
|
},
|
|
{
|
|
"entropy": 5.963467979431153,
|
|
"epoch": 0.15892626495198517,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004999754425286483,
|
|
"loss": 6.0995,
|
|
"mean_token_accuracy": 0.14720706641674042,
|
|
"num_tokens": 3158494.0,
|
|
"step": 1415
|
|
},
|
|
{
|
|
"entropy": 6.131221580505371,
|
|
"epoch": 0.15948784185994272,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999748457821529,
|
|
"loss": 6.1288,
|
|
"mean_token_accuracy": 0.14769198149442672,
|
|
"num_tokens": 3170550.0,
|
|
"step": 1420
|
|
},
|
|
{
|
|
"entropy": 5.9402268409729,
|
|
"epoch": 0.16004941876790027,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.000499974241872371,
|
|
"loss": 6.1076,
|
|
"mean_token_accuracy": 0.15461537688970567,
|
|
"num_tokens": 3182860.0,
|
|
"step": 1425
|
|
},
|
|
{
|
|
"entropy": 6.07914547920227,
|
|
"epoch": 0.16061099567585782,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999736307993221,
|
|
"loss": 6.105,
|
|
"mean_token_accuracy": 0.14613698273897172,
|
|
"num_tokens": 3193807.0,
|
|
"step": 1430
|
|
},
|
|
{
|
|
"entropy": 5.986855363845825,
|
|
"epoch": 0.16117257258381534,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999730125630255,
|
|
"loss": 5.9808,
|
|
"mean_token_accuracy": 0.15065714865922927,
|
|
"num_tokens": 3203959.0,
|
|
"step": 1435
|
|
},
|
|
{
|
|
"entropy": 6.042674398422241,
|
|
"epoch": 0.1617341494917729,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004999723871635008,
|
|
"loss": 5.9961,
|
|
"mean_token_accuracy": 0.15428200960159302,
|
|
"num_tokens": 3215416.0,
|
|
"step": 1440
|
|
},
|
|
{
|
|
"entropy": 6.139855527877808,
|
|
"epoch": 0.16229572639973044,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999717546007681,
|
|
"loss": 6.1393,
|
|
"mean_token_accuracy": 0.14156408235430717,
|
|
"num_tokens": 3226938.0,
|
|
"step": 1445
|
|
},
|
|
{
|
|
"entropy": 5.931169843673706,
|
|
"epoch": 0.162857303307688,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999711148748476,
|
|
"loss": 5.956,
|
|
"mean_token_accuracy": 0.1564284533262253,
|
|
"num_tokens": 3238406.0,
|
|
"step": 1450
|
|
},
|
|
{
|
|
"entropy": 5.968686246871949,
|
|
"epoch": 0.16341888021564555,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999704679857594,
|
|
"loss": 5.9748,
|
|
"mean_token_accuracy": 0.14992773681879043,
|
|
"num_tokens": 3249695.0,
|
|
"step": 1455
|
|
},
|
|
{
|
|
"entropy": 6.125838279724121,
|
|
"epoch": 0.16398045712360307,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999698139335243,
|
|
"loss": 6.1147,
|
|
"mean_token_accuracy": 0.15428986698389052,
|
|
"num_tokens": 3259656.0,
|
|
"step": 1460
|
|
},
|
|
{
|
|
"entropy": 5.994536018371582,
|
|
"epoch": 0.16454203403156062,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999691527181632,
|
|
"loss": 5.9514,
|
|
"mean_token_accuracy": 0.1599651977419853,
|
|
"num_tokens": 3269712.0,
|
|
"step": 1465
|
|
},
|
|
{
|
|
"entropy": 5.873442840576172,
|
|
"epoch": 0.16510361093951817,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999684843396968,
|
|
"loss": 5.948,
|
|
"mean_token_accuracy": 0.16050935834646224,
|
|
"num_tokens": 3280343.0,
|
|
"step": 1470
|
|
},
|
|
{
|
|
"entropy": 6.029610300064087,
|
|
"epoch": 0.16566518784747572,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999678087981467,
|
|
"loss": 5.9863,
|
|
"mean_token_accuracy": 0.15649282932281494,
|
|
"num_tokens": 3291649.0,
|
|
"step": 1475
|
|
},
|
|
{
|
|
"entropy": 6.136847448348999,
|
|
"epoch": 0.16622676475543324,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004999671260935343,
|
|
"loss": 6.1547,
|
|
"mean_token_accuracy": 0.15154551565647126,
|
|
"num_tokens": 3304190.0,
|
|
"step": 1480
|
|
},
|
|
{
|
|
"entropy": 5.872249698638916,
|
|
"epoch": 0.1667883416633908,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999664362258814,
|
|
"loss": 5.8936,
|
|
"mean_token_accuracy": 0.1636761337518692,
|
|
"num_tokens": 3313966.0,
|
|
"step": 1485
|
|
},
|
|
{
|
|
"entropy": 6.072989749908447,
|
|
"epoch": 0.16734991857134834,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999657391952099,
|
|
"loss": 6.1474,
|
|
"mean_token_accuracy": 0.1493370659649372,
|
|
"num_tokens": 3326017.0,
|
|
"step": 1490
|
|
},
|
|
{
|
|
"entropy": 6.061523818969727,
|
|
"epoch": 0.1679114954793059,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.000499965035001542,
|
|
"loss": 6.0294,
|
|
"mean_token_accuracy": 0.14847790449857712,
|
|
"num_tokens": 3338264.0,
|
|
"step": 1495
|
|
},
|
|
{
|
|
"entropy": 6.020901775360107,
|
|
"epoch": 0.16847307238726345,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999643236449001,
|
|
"loss": 6.0681,
|
|
"mean_token_accuracy": 0.1578044191002846,
|
|
"num_tokens": 3348901.0,
|
|
"step": 1500
|
|
},
|
|
{
|
|
"entropy": 6.05039758682251,
|
|
"epoch": 0.16903464929522097,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999636051253069,
|
|
"loss": 6.0115,
|
|
"mean_token_accuracy": 0.15544183254241944,
|
|
"num_tokens": 3358441.0,
|
|
"step": 1505
|
|
},
|
|
{
|
|
"entropy": 6.062154722213745,
|
|
"epoch": 0.16959622620317852,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999628794427854,
|
|
"loss": 6.0913,
|
|
"mean_token_accuracy": 0.15557602494955064,
|
|
"num_tokens": 3369334.0,
|
|
"step": 1510
|
|
},
|
|
{
|
|
"entropy": 5.989631223678589,
|
|
"epoch": 0.17015780311113607,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999621465973583,
|
|
"loss": 6.0789,
|
|
"mean_token_accuracy": 0.1499525025486946,
|
|
"num_tokens": 3380698.0,
|
|
"step": 1515
|
|
},
|
|
{
|
|
"entropy": 6.214061117172241,
|
|
"epoch": 0.17071938001909362,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999614065890495,
|
|
"loss": 6.0942,
|
|
"mean_token_accuracy": 0.1456768698990345,
|
|
"num_tokens": 3391061.0,
|
|
"step": 1520
|
|
},
|
|
{
|
|
"entropy": 6.012625885009766,
|
|
"epoch": 0.17128095692705117,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999606594178821,
|
|
"loss": 6.1471,
|
|
"mean_token_accuracy": 0.14754906371235849,
|
|
"num_tokens": 3403983.0,
|
|
"step": 1525
|
|
},
|
|
{
|
|
"entropy": 6.164724922180175,
|
|
"epoch": 0.1718425338350087,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00049995990508388,
|
|
"loss": 6.0759,
|
|
"mean_token_accuracy": 0.15379567444324493,
|
|
"num_tokens": 3413838.0,
|
|
"step": 1530
|
|
},
|
|
{
|
|
"entropy": 5.909680509567261,
|
|
"epoch": 0.17240411074296624,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999591435870674,
|
|
"loss": 5.9074,
|
|
"mean_token_accuracy": 0.15706708282232285,
|
|
"num_tokens": 3423978.0,
|
|
"step": 1535
|
|
},
|
|
{
|
|
"entropy": 6.045839118957519,
|
|
"epoch": 0.1729656876509238,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999583749274684,
|
|
"loss": 6.0766,
|
|
"mean_token_accuracy": 0.15526383817195893,
|
|
"num_tokens": 3433416.0,
|
|
"step": 1540
|
|
},
|
|
{
|
|
"entropy": 5.899442911148071,
|
|
"epoch": 0.17352726455888134,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999575991051074,
|
|
"loss": 5.9403,
|
|
"mean_token_accuracy": 0.15632218718528748,
|
|
"num_tokens": 3444983.0,
|
|
"step": 1545
|
|
},
|
|
{
|
|
"entropy": 5.97276668548584,
|
|
"epoch": 0.1740888414668389,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999568161200093,
|
|
"loss": 5.9251,
|
|
"mean_token_accuracy": 0.15755780041217804,
|
|
"num_tokens": 3455808.0,
|
|
"step": 1550
|
|
},
|
|
{
|
|
"entropy": 5.955643653869629,
|
|
"epoch": 0.17465041837479642,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999560259721989,
|
|
"loss": 6.0733,
|
|
"mean_token_accuracy": 0.14496413096785546,
|
|
"num_tokens": 3467503.0,
|
|
"step": 1555
|
|
},
|
|
{
|
|
"entropy": 6.2084818363189695,
|
|
"epoch": 0.17521199528275397,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999552286617014,
|
|
"loss": 6.2662,
|
|
"mean_token_accuracy": 0.1477560058236122,
|
|
"num_tokens": 3479941.0,
|
|
"step": 1560
|
|
},
|
|
{
|
|
"entropy": 5.958353185653687,
|
|
"epoch": 0.17577357219071152,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999544241885421,
|
|
"loss": 5.9351,
|
|
"mean_token_accuracy": 0.16224518567323684,
|
|
"num_tokens": 3491069.0,
|
|
"step": 1565
|
|
},
|
|
{
|
|
"entropy": 6.06676082611084,
|
|
"epoch": 0.17633514909866907,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999536125527467,
|
|
"loss": 6.1282,
|
|
"mean_token_accuracy": 0.1457708492875099,
|
|
"num_tokens": 3502065.0,
|
|
"step": 1570
|
|
},
|
|
{
|
|
"entropy": 6.07559905052185,
|
|
"epoch": 0.17689672600662662,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000499952793754341,
|
|
"loss": 6.0865,
|
|
"mean_token_accuracy": 0.15441752076148987,
|
|
"num_tokens": 3514228.0,
|
|
"step": 1575
|
|
},
|
|
{
|
|
"entropy": 5.995469331741333,
|
|
"epoch": 0.17745830291458414,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999519677933512,
|
|
"loss": 6.0211,
|
|
"mean_token_accuracy": 0.15433061122894287,
|
|
"num_tokens": 3525801.0,
|
|
"step": 1580
|
|
},
|
|
{
|
|
"entropy": 5.998544597625733,
|
|
"epoch": 0.1780198798225417,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999511346698035,
|
|
"loss": 5.9454,
|
|
"mean_token_accuracy": 0.15480177700519562,
|
|
"num_tokens": 3536431.0,
|
|
"step": 1585
|
|
},
|
|
{
|
|
"entropy": 5.968015098571778,
|
|
"epoch": 0.17858145673049924,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004999502943837244,
|
|
"loss": 6.0659,
|
|
"mean_token_accuracy": 0.15099444910883902,
|
|
"num_tokens": 3549098.0,
|
|
"step": 1590
|
|
},
|
|
{
|
|
"entropy": 6.096561050415039,
|
|
"epoch": 0.1791430336384568,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999494469351406,
|
|
"loss": 6.0114,
|
|
"mean_token_accuracy": 0.152137491106987,
|
|
"num_tokens": 3560532.0,
|
|
"step": 1595
|
|
},
|
|
{
|
|
"entropy": 5.961009120941162,
|
|
"epoch": 0.17970461054641435,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999485923240793,
|
|
"loss": 6.0303,
|
|
"mean_token_accuracy": 0.15316579714417458,
|
|
"num_tokens": 3572175.0,
|
|
"step": 1600
|
|
},
|
|
{
|
|
"entropy": 6.033007192611694,
|
|
"epoch": 0.18026618745437187,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999477305505675,
|
|
"loss": 5.9451,
|
|
"mean_token_accuracy": 0.17299906462430953,
|
|
"num_tokens": 3582862.0,
|
|
"step": 1605
|
|
},
|
|
{
|
|
"entropy": 6.030126714706421,
|
|
"epoch": 0.18082776436232942,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999468616146328,
|
|
"loss": 6.1329,
|
|
"mean_token_accuracy": 0.15195471569895744,
|
|
"num_tokens": 3594685.0,
|
|
"step": 1610
|
|
},
|
|
{
|
|
"entropy": 5.915484094619751,
|
|
"epoch": 0.18138934127028697,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999459855163026,
|
|
"loss": 5.9167,
|
|
"mean_token_accuracy": 0.1637891188263893,
|
|
"num_tokens": 3604847.0,
|
|
"step": 1615
|
|
},
|
|
{
|
|
"entropy": 6.032248640060425,
|
|
"epoch": 0.18195091817824452,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000499945102255605,
|
|
"loss": 5.9967,
|
|
"mean_token_accuracy": 0.15529887825250627,
|
|
"num_tokens": 3615549.0,
|
|
"step": 1620
|
|
},
|
|
{
|
|
"entropy": 5.955660629272461,
|
|
"epoch": 0.18251249508620204,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999442118325682,
|
|
"loss": 5.9328,
|
|
"mean_token_accuracy": 0.16356256008148193,
|
|
"num_tokens": 3626300.0,
|
|
"step": 1625
|
|
},
|
|
{
|
|
"entropy": 5.940017890930176,
|
|
"epoch": 0.1830740719941596,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999433142472205,
|
|
"loss": 5.9533,
|
|
"mean_token_accuracy": 0.15708972960710527,
|
|
"num_tokens": 3637832.0,
|
|
"step": 1630
|
|
},
|
|
{
|
|
"entropy": 6.009549951553344,
|
|
"epoch": 0.18363564890211714,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999424094995902,
|
|
"loss": 5.9815,
|
|
"mean_token_accuracy": 0.15054063647985458,
|
|
"num_tokens": 3649179.0,
|
|
"step": 1635
|
|
},
|
|
{
|
|
"entropy": 5.970891094207763,
|
|
"epoch": 0.1841972258100747,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999414975897066,
|
|
"loss": 6.0249,
|
|
"mean_token_accuracy": 0.15206027776002884,
|
|
"num_tokens": 3660011.0,
|
|
"step": 1640
|
|
},
|
|
{
|
|
"entropy": 6.120618104934692,
|
|
"epoch": 0.18475880271803224,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004999405785175983,
|
|
"loss": 6.1014,
|
|
"mean_token_accuracy": 0.1466618612408638,
|
|
"num_tokens": 3672791.0,
|
|
"step": 1645
|
|
},
|
|
{
|
|
"entropy": 5.9426877975463865,
|
|
"epoch": 0.18532037962598977,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999396522832949,
|
|
"loss": 5.9301,
|
|
"mean_token_accuracy": 0.14880775511264802,
|
|
"num_tokens": 3684709.0,
|
|
"step": 1650
|
|
},
|
|
{
|
|
"entropy": 5.8846558094024655,
|
|
"epoch": 0.18588195653394732,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999387188868256,
|
|
"loss": 5.9009,
|
|
"mean_token_accuracy": 0.1574036091566086,
|
|
"num_tokens": 3694675.0,
|
|
"step": 1655
|
|
},
|
|
{
|
|
"entropy": 5.897461223602295,
|
|
"epoch": 0.18644353344190487,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004999377783282203,
|
|
"loss": 5.9052,
|
|
"mean_token_accuracy": 0.15229580998420716,
|
|
"num_tokens": 3706384.0,
|
|
"step": 1660
|
|
},
|
|
{
|
|
"entropy": 6.019663524627686,
|
|
"epoch": 0.18700511034986242,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999368306075089,
|
|
"loss": 5.9767,
|
|
"mean_token_accuracy": 0.15526307225227357,
|
|
"num_tokens": 3717419.0,
|
|
"step": 1665
|
|
},
|
|
{
|
|
"entropy": 5.97164831161499,
|
|
"epoch": 0.18756668725781997,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999358757247215,
|
|
"loss": 6.0001,
|
|
"mean_token_accuracy": 0.15804468095302582,
|
|
"num_tokens": 3727306.0,
|
|
"step": 1670
|
|
},
|
|
{
|
|
"entropy": 6.075372171401978,
|
|
"epoch": 0.1881282641657775,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999349136798886,
|
|
"loss": 6.1408,
|
|
"mean_token_accuracy": 0.1482490971684456,
|
|
"num_tokens": 3739476.0,
|
|
"step": 1675
|
|
},
|
|
{
|
|
"entropy": 5.917860984802246,
|
|
"epoch": 0.18868984107373504,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999339444730409,
|
|
"loss": 5.8937,
|
|
"mean_token_accuracy": 0.16344992816448212,
|
|
"num_tokens": 3751035.0,
|
|
"step": 1680
|
|
},
|
|
{
|
|
"entropy": 5.984053277969361,
|
|
"epoch": 0.1892514179816926,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999329681042092,
|
|
"loss": 5.9851,
|
|
"mean_token_accuracy": 0.15741585195064545,
|
|
"num_tokens": 3762881.0,
|
|
"step": 1685
|
|
},
|
|
{
|
|
"entropy": 5.960563278198242,
|
|
"epoch": 0.18981299488965014,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999319845734243,
|
|
"loss": 5.999,
|
|
"mean_token_accuracy": 0.15340179800987244,
|
|
"num_tokens": 3774180.0,
|
|
"step": 1690
|
|
},
|
|
{
|
|
"entropy": 5.944005250930786,
|
|
"epoch": 0.1903745717976077,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999309938807181,
|
|
"loss": 5.9978,
|
|
"mean_token_accuracy": 0.16235336810350418,
|
|
"num_tokens": 3784864.0,
|
|
"step": 1695
|
|
},
|
|
{
|
|
"entropy": 6.061145496368408,
|
|
"epoch": 0.19093614870556522,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999299960261216,
|
|
"loss": 5.983,
|
|
"mean_token_accuracy": 0.15478956401348115,
|
|
"num_tokens": 3797693.0,
|
|
"step": 1700
|
|
},
|
|
{
|
|
"entropy": 5.940720462799073,
|
|
"epoch": 0.19149772561352277,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999289910096669,
|
|
"loss": 6.0048,
|
|
"mean_token_accuracy": 0.15954993665218353,
|
|
"num_tokens": 3809379.0,
|
|
"step": 1705
|
|
},
|
|
{
|
|
"entropy": 5.869456434249878,
|
|
"epoch": 0.19205930252148032,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999279788313858,
|
|
"loss": 5.8466,
|
|
"mean_token_accuracy": 0.1634460434317589,
|
|
"num_tokens": 3819473.0,
|
|
"step": 1710
|
|
},
|
|
{
|
|
"entropy": 5.839190578460693,
|
|
"epoch": 0.19262087942943787,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999269594913107,
|
|
"loss": 5.8447,
|
|
"mean_token_accuracy": 0.16184932887554168,
|
|
"num_tokens": 3831037.0,
|
|
"step": 1715
|
|
},
|
|
{
|
|
"entropy": 5.890625619888306,
|
|
"epoch": 0.19318245633739542,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999259329894739,
|
|
"loss": 5.9796,
|
|
"mean_token_accuracy": 0.15089921206235885,
|
|
"num_tokens": 3841767.0,
|
|
"step": 1720
|
|
},
|
|
{
|
|
"entropy": 5.863656806945801,
|
|
"epoch": 0.19374403324535294,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999248993259081,
|
|
"loss": 5.8179,
|
|
"mean_token_accuracy": 0.1636965826153755,
|
|
"num_tokens": 3851629.0,
|
|
"step": 1725
|
|
},
|
|
{
|
|
"entropy": 5.859853363037109,
|
|
"epoch": 0.1943056101533105,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999238585006463,
|
|
"loss": 5.8875,
|
|
"mean_token_accuracy": 0.15624083131551741,
|
|
"num_tokens": 3863247.0,
|
|
"step": 1730
|
|
},
|
|
{
|
|
"entropy": 5.972808027267456,
|
|
"epoch": 0.19486718706126804,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999228105137218,
|
|
"loss": 5.8814,
|
|
"mean_token_accuracy": 0.1572691485285759,
|
|
"num_tokens": 3873949.0,
|
|
"step": 1735
|
|
},
|
|
{
|
|
"entropy": 5.924859476089478,
|
|
"epoch": 0.1954287639692256,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999217553651676,
|
|
"loss": 5.9895,
|
|
"mean_token_accuracy": 0.1545493260025978,
|
|
"num_tokens": 3884992.0,
|
|
"step": 1740
|
|
},
|
|
{
|
|
"entropy": 6.055422115325928,
|
|
"epoch": 0.19599034087718312,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999206930550175,
|
|
"loss": 6.1164,
|
|
"mean_token_accuracy": 0.15783915370702745,
|
|
"num_tokens": 3897029.0,
|
|
"step": 1745
|
|
},
|
|
{
|
|
"entropy": 5.9067707538604735,
|
|
"epoch": 0.19655191778514067,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999196235833054,
|
|
"loss": 5.9658,
|
|
"mean_token_accuracy": 0.15075957030057907,
|
|
"num_tokens": 3909510.0,
|
|
"step": 1750
|
|
},
|
|
{
|
|
"entropy": 5.964732027053833,
|
|
"epoch": 0.19711349469309822,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999185469500651,
|
|
"loss": 5.8633,
|
|
"mean_token_accuracy": 0.15894850939512253,
|
|
"num_tokens": 3920593.0,
|
|
"step": 1755
|
|
},
|
|
{
|
|
"entropy": 5.965554332733154,
|
|
"epoch": 0.19767507160105577,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000499917463155331,
|
|
"loss": 5.9988,
|
|
"mean_token_accuracy": 0.150234617292881,
|
|
"num_tokens": 3932215.0,
|
|
"step": 1760
|
|
},
|
|
{
|
|
"entropy": 5.989650630950928,
|
|
"epoch": 0.19823664850901332,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999163721991378,
|
|
"loss": 5.9462,
|
|
"mean_token_accuracy": 0.15746484696865082,
|
|
"num_tokens": 3943876.0,
|
|
"step": 1765
|
|
},
|
|
{
|
|
"entropy": 5.773177862167358,
|
|
"epoch": 0.19879822541697084,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00049991527408152,
|
|
"loss": 5.9507,
|
|
"mean_token_accuracy": 0.15623908042907714,
|
|
"num_tokens": 3954533.0,
|
|
"step": 1770
|
|
},
|
|
{
|
|
"entropy": 6.059681606292725,
|
|
"epoch": 0.1993598023249284,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999141688025127,
|
|
"loss": 5.9939,
|
|
"mean_token_accuracy": 0.16129837930202484,
|
|
"num_tokens": 3965722.0,
|
|
"step": 1775
|
|
},
|
|
{
|
|
"entropy": 5.901776123046875,
|
|
"epoch": 0.19992137923288594,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.000499913056362151,
|
|
"loss": 5.9075,
|
|
"mean_token_accuracy": 0.15883826315402985,
|
|
"num_tokens": 3976737.0,
|
|
"step": 1780
|
|
},
|
|
{
|
|
"entropy": 6.016579627990723,
|
|
"epoch": 0.2004829561408435,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999119367604703,
|
|
"loss": 5.9984,
|
|
"mean_token_accuracy": 0.15875881016254426,
|
|
"num_tokens": 3986102.0,
|
|
"step": 1785
|
|
},
|
|
{
|
|
"entropy": 5.9803629398345945,
|
|
"epoch": 0.20104453304880104,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999108099975064,
|
|
"loss": 5.976,
|
|
"mean_token_accuracy": 0.15650469213724136,
|
|
"num_tokens": 3996534.0,
|
|
"step": 1790
|
|
},
|
|
{
|
|
"entropy": 5.863087463378906,
|
|
"epoch": 0.20160610995675857,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000499909676073295,
|
|
"loss": 5.8881,
|
|
"mean_token_accuracy": 0.15706568509340285,
|
|
"num_tokens": 4006947.0,
|
|
"step": 1795
|
|
},
|
|
{
|
|
"entropy": 5.90200252532959,
|
|
"epoch": 0.20216768686471612,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999085349878723,
|
|
"loss": 5.92,
|
|
"mean_token_accuracy": 0.16723052114248277,
|
|
"num_tokens": 4017723.0,
|
|
"step": 1800
|
|
},
|
|
{
|
|
"entropy": 5.895722150802612,
|
|
"epoch": 0.20272926377267367,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999073867412746,
|
|
"loss": 5.9885,
|
|
"mean_token_accuracy": 0.15485088378190995,
|
|
"num_tokens": 4028347.0,
|
|
"step": 1805
|
|
},
|
|
{
|
|
"entropy": 5.922601175308228,
|
|
"epoch": 0.20329084068063122,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999062313335385,
|
|
"loss": 5.8643,
|
|
"mean_token_accuracy": 0.16550229638814926,
|
|
"num_tokens": 4039648.0,
|
|
"step": 1810
|
|
},
|
|
{
|
|
"entropy": 5.962918710708618,
|
|
"epoch": 0.20385241758858877,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999050687647008,
|
|
"loss": 5.9226,
|
|
"mean_token_accuracy": 0.15441896617412568,
|
|
"num_tokens": 4050786.0,
|
|
"step": 1815
|
|
},
|
|
{
|
|
"entropy": 5.971924304962158,
|
|
"epoch": 0.2044139944965463,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999038990347984,
|
|
"loss": 5.9563,
|
|
"mean_token_accuracy": 0.15948153734207154,
|
|
"num_tokens": 4061184.0,
|
|
"step": 1820
|
|
},
|
|
{
|
|
"entropy": 6.024726390838623,
|
|
"epoch": 0.20497557140450384,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999027221438688,
|
|
"loss": 6.1013,
|
|
"mean_token_accuracy": 0.1498976394534111,
|
|
"num_tokens": 4073607.0,
|
|
"step": 1825
|
|
},
|
|
{
|
|
"entropy": 5.907567167282105,
|
|
"epoch": 0.2055371483124614,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000499901538091949,
|
|
"loss": 5.8961,
|
|
"mean_token_accuracy": 0.15584656596183777,
|
|
"num_tokens": 4083924.0,
|
|
"step": 1830
|
|
},
|
|
{
|
|
"entropy": 5.908780908584594,
|
|
"epoch": 0.20609872522041894,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999003468790773,
|
|
"loss": 5.895,
|
|
"mean_token_accuracy": 0.16026797592639924,
|
|
"num_tokens": 4094083.0,
|
|
"step": 1835
|
|
},
|
|
{
|
|
"entropy": 5.952602481842041,
|
|
"epoch": 0.2066603021283765,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998991485052911,
|
|
"loss": 5.9312,
|
|
"mean_token_accuracy": 0.16474931836128234,
|
|
"num_tokens": 4105124.0,
|
|
"step": 1840
|
|
},
|
|
{
|
|
"entropy": 6.067802858352661,
|
|
"epoch": 0.20722187903633402,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000499897942970629,
|
|
"loss": 6.0896,
|
|
"mean_token_accuracy": 0.14841930121183394,
|
|
"num_tokens": 4116792.0,
|
|
"step": 1845
|
|
},
|
|
{
|
|
"entropy": 6.09526219367981,
|
|
"epoch": 0.20778345594429157,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000499896730275129,
|
|
"loss": 6.0843,
|
|
"mean_token_accuracy": 0.1532771721482277,
|
|
"num_tokens": 4127441.0,
|
|
"step": 1850
|
|
},
|
|
{
|
|
"entropy": 5.940713548660279,
|
|
"epoch": 0.20834503285224912,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00049989551041883,
|
|
"loss": 6.0739,
|
|
"mean_token_accuracy": 0.15080675035715102,
|
|
"num_tokens": 4138696.0,
|
|
"step": 1855
|
|
},
|
|
{
|
|
"entropy": 5.9166515350341795,
|
|
"epoch": 0.20890660976020667,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998942834017707,
|
|
"loss": 5.9439,
|
|
"mean_token_accuracy": 0.15614898800849913,
|
|
"num_tokens": 4151254.0,
|
|
"step": 1860
|
|
},
|
|
{
|
|
"entropy": 5.902920818328857,
|
|
"epoch": 0.2094681866681642,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998930492239901,
|
|
"loss": 5.8982,
|
|
"mean_token_accuracy": 0.15039533078670503,
|
|
"num_tokens": 4162046.0,
|
|
"step": 1865
|
|
},
|
|
{
|
|
"entropy": 5.854731798171997,
|
|
"epoch": 0.21002976357612174,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998918078855277,
|
|
"loss": 5.8424,
|
|
"mean_token_accuracy": 0.1606363594532013,
|
|
"num_tokens": 4172409.0,
|
|
"step": 1870
|
|
},
|
|
{
|
|
"entropy": 5.904069328308106,
|
|
"epoch": 0.2105913404840793,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004998905593864227,
|
|
"loss": 6.0008,
|
|
"mean_token_accuracy": 0.16382352709770204,
|
|
"num_tokens": 4182949.0,
|
|
"step": 1875
|
|
},
|
|
{
|
|
"entropy": 5.930221652984619,
|
|
"epoch": 0.21115291739203684,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998893037267153,
|
|
"loss": 5.9673,
|
|
"mean_token_accuracy": 0.15838558822870255,
|
|
"num_tokens": 4194164.0,
|
|
"step": 1880
|
|
},
|
|
{
|
|
"entropy": 6.024990034103394,
|
|
"epoch": 0.2117144942999944,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004998880409064452,
|
|
"loss": 5.9359,
|
|
"mean_token_accuracy": 0.16012249439954757,
|
|
"num_tokens": 4206056.0,
|
|
"step": 1885
|
|
},
|
|
{
|
|
"entropy": 5.89975209236145,
|
|
"epoch": 0.21227607120795192,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004998867709256527,
|
|
"loss": 5.9935,
|
|
"mean_token_accuracy": 0.15553135573863983,
|
|
"num_tokens": 4216660.0,
|
|
"step": 1890
|
|
},
|
|
{
|
|
"entropy": 5.904560232162476,
|
|
"epoch": 0.21283764811590947,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000499885493784378,
|
|
"loss": 5.8812,
|
|
"mean_token_accuracy": 0.15976034998893737,
|
|
"num_tokens": 4228495.0,
|
|
"step": 1895
|
|
},
|
|
{
|
|
"entropy": 5.912075519561768,
|
|
"epoch": 0.21339922502386702,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004998842094826621,
|
|
"loss": 5.8696,
|
|
"mean_token_accuracy": 0.1601097196340561,
|
|
"num_tokens": 4238560.0,
|
|
"step": 1900
|
|
},
|
|
{
|
|
"entropy": 6.007304859161377,
|
|
"epoch": 0.21396080193182457,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998829180205458,
|
|
"loss": 6.0989,
|
|
"mean_token_accuracy": 0.15267504751682281,
|
|
"num_tokens": 4250553.0,
|
|
"step": 1905
|
|
},
|
|
{
|
|
"entropy": 5.997589445114135,
|
|
"epoch": 0.21452237883978212,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004998816193980701,
|
|
"loss": 5.9946,
|
|
"mean_token_accuracy": 0.15328334122896195,
|
|
"num_tokens": 4262050.0,
|
|
"step": 1910
|
|
},
|
|
{
|
|
"entropy": 6.066816091537476,
|
|
"epoch": 0.21508395574773964,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004998803136152764,
|
|
"loss": 5.9717,
|
|
"mean_token_accuracy": 0.14724281281232834,
|
|
"num_tokens": 4273019.0,
|
|
"step": 1915
|
|
},
|
|
{
|
|
"entropy": 5.860903739929199,
|
|
"epoch": 0.2156455326556972,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998790006722063,
|
|
"loss": 5.8356,
|
|
"mean_token_accuracy": 0.16368041932582855,
|
|
"num_tokens": 4283585.0,
|
|
"step": 1920
|
|
},
|
|
{
|
|
"entropy": 5.8601470470428465,
|
|
"epoch": 0.21620710956365474,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998776805689016,
|
|
"loss": 5.9195,
|
|
"mean_token_accuracy": 0.15469036400318145,
|
|
"num_tokens": 4294905.0,
|
|
"step": 1925
|
|
},
|
|
{
|
|
"entropy": 6.0024792671203615,
|
|
"epoch": 0.2167686864716123,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004998763533054045,
|
|
"loss": 6.0381,
|
|
"mean_token_accuracy": 0.15404224991798401,
|
|
"num_tokens": 4305926.0,
|
|
"step": 1930
|
|
},
|
|
{
|
|
"entropy": 5.8503828048706055,
|
|
"epoch": 0.21733026337956984,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998750188817568,
|
|
"loss": 6.0068,
|
|
"mean_token_accuracy": 0.1558867573738098,
|
|
"num_tokens": 4318297.0,
|
|
"step": 1935
|
|
},
|
|
{
|
|
"entropy": 5.923427248001099,
|
|
"epoch": 0.21789184028752737,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004998736772980015,
|
|
"loss": 5.8309,
|
|
"mean_token_accuracy": 0.16621251851320268,
|
|
"num_tokens": 4328795.0,
|
|
"step": 1940
|
|
},
|
|
{
|
|
"entropy": 5.854658794403076,
|
|
"epoch": 0.21845341719548492,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.000499872328554181,
|
|
"loss": 5.8404,
|
|
"mean_token_accuracy": 0.1629622608423233,
|
|
"num_tokens": 4340279.0,
|
|
"step": 1945
|
|
},
|
|
{
|
|
"entropy": 6.01924500465393,
|
|
"epoch": 0.21901499410344247,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998709726503383,
|
|
"loss": 6.0073,
|
|
"mean_token_accuracy": 0.15287342071533203,
|
|
"num_tokens": 4352157.0,
|
|
"step": 1950
|
|
},
|
|
{
|
|
"entropy": 5.869948482513427,
|
|
"epoch": 0.21957657101140002,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998696095865168,
|
|
"loss": 5.8464,
|
|
"mean_token_accuracy": 0.15993180274963378,
|
|
"num_tokens": 4361909.0,
|
|
"step": 1955
|
|
},
|
|
{
|
|
"entropy": 5.694135141372681,
|
|
"epoch": 0.22013814791935757,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004998682393627595,
|
|
"loss": 5.7801,
|
|
"mean_token_accuracy": 0.15679869204759597,
|
|
"num_tokens": 4372177.0,
|
|
"step": 1960
|
|
},
|
|
{
|
|
"entropy": 5.851674175262451,
|
|
"epoch": 0.2206997248273151,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004998668619791104,
|
|
"loss": 5.8245,
|
|
"mean_token_accuracy": 0.16455647349357605,
|
|
"num_tokens": 4382872.0,
|
|
"step": 1965
|
|
},
|
|
{
|
|
"entropy": 5.910435581207276,
|
|
"epoch": 0.22126130173527264,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004998654774356131,
|
|
"loss": 5.9296,
|
|
"mean_token_accuracy": 0.15243469476699828,
|
|
"num_tokens": 4393623.0,
|
|
"step": 1970
|
|
},
|
|
{
|
|
"entropy": 5.87087049484253,
|
|
"epoch": 0.2218228786432302,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004998640857323118,
|
|
"loss": 5.8629,
|
|
"mean_token_accuracy": 0.15855282992124559,
|
|
"num_tokens": 4404215.0,
|
|
"step": 1975
|
|
},
|
|
{
|
|
"entropy": 5.980984401702881,
|
|
"epoch": 0.22238445555118774,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998626868692509,
|
|
"loss": 6.1252,
|
|
"mean_token_accuracy": 0.1530395619571209,
|
|
"num_tokens": 4415978.0,
|
|
"step": 1980
|
|
},
|
|
{
|
|
"entropy": 5.92978253364563,
|
|
"epoch": 0.2229460324591453,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998612808464748,
|
|
"loss": 5.8779,
|
|
"mean_token_accuracy": 0.1633330002427101,
|
|
"num_tokens": 4427060.0,
|
|
"step": 1985
|
|
},
|
|
{
|
|
"entropy": 5.8504064083099365,
|
|
"epoch": 0.22350760936710282,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004998598676640283,
|
|
"loss": 5.9388,
|
|
"mean_token_accuracy": 0.1539946474134922,
|
|
"num_tokens": 4438145.0,
|
|
"step": 1990
|
|
},
|
|
{
|
|
"entropy": 6.1169726848602295,
|
|
"epoch": 0.22406918627506037,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004998584473219563,
|
|
"loss": 6.0259,
|
|
"mean_token_accuracy": 0.1604885935783386,
|
|
"num_tokens": 4449324.0,
|
|
"step": 1995
|
|
},
|
|
{
|
|
"entropy": 5.830072832107544,
|
|
"epoch": 0.22463076318301792,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998570198203043,
|
|
"loss": 5.7461,
|
|
"mean_token_accuracy": 0.16123024970293046,
|
|
"num_tokens": 4459728.0,
|
|
"step": 2000
|
|
},
|
|
{
|
|
"entropy": 5.833692741394043,
|
|
"epoch": 0.22519234009097547,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998555851591175,
|
|
"loss": 5.9654,
|
|
"mean_token_accuracy": 0.15974030271172523,
|
|
"num_tokens": 4471164.0,
|
|
"step": 2005
|
|
},
|
|
{
|
|
"entropy": 5.977700471878052,
|
|
"epoch": 0.225753916998933,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004998541433384416,
|
|
"loss": 6.0127,
|
|
"mean_token_accuracy": 0.15873760730028152,
|
|
"num_tokens": 4483349.0,
|
|
"step": 2010
|
|
},
|
|
{
|
|
"entropy": 6.0327905178070065,
|
|
"epoch": 0.22631549390689054,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004998526943583226,
|
|
"loss": 5.986,
|
|
"mean_token_accuracy": 0.1547345146536827,
|
|
"num_tokens": 4495311.0,
|
|
"step": 2015
|
|
},
|
|
{
|
|
"entropy": 5.838544273376465,
|
|
"epoch": 0.2268770708148481,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004998512382188066,
|
|
"loss": 5.9097,
|
|
"mean_token_accuracy": 0.15987676233053208,
|
|
"num_tokens": 4507017.0,
|
|
"step": 2020
|
|
},
|
|
{
|
|
"entropy": 5.924619531631469,
|
|
"epoch": 0.22743864772280564,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998497749199401,
|
|
"loss": 5.9415,
|
|
"mean_token_accuracy": 0.1556266188621521,
|
|
"num_tokens": 4517746.0,
|
|
"step": 2025
|
|
},
|
|
{
|
|
"entropy": 5.994407606124878,
|
|
"epoch": 0.2280002246307632,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998483044617694,
|
|
"loss": 6.0424,
|
|
"mean_token_accuracy": 0.1516892984509468,
|
|
"num_tokens": 4529149.0,
|
|
"step": 2030
|
|
},
|
|
{
|
|
"entropy": 5.9190531253814695,
|
|
"epoch": 0.22856180153872072,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998468268443416,
|
|
"loss": 5.9182,
|
|
"mean_token_accuracy": 0.15801755338907242,
|
|
"num_tokens": 4540630.0,
|
|
"step": 2035
|
|
},
|
|
{
|
|
"entropy": 5.837906694412231,
|
|
"epoch": 0.22912337844667827,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998453420677034,
|
|
"loss": 5.8474,
|
|
"mean_token_accuracy": 0.15756188482046127,
|
|
"num_tokens": 4552877.0,
|
|
"step": 2040
|
|
},
|
|
{
|
|
"entropy": 5.93119626045227,
|
|
"epoch": 0.22968495535463582,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004998438501319025,
|
|
"loss": 5.9465,
|
|
"mean_token_accuracy": 0.16055746376514435,
|
|
"num_tokens": 4563634.0,
|
|
"step": 2045
|
|
},
|
|
{
|
|
"entropy": 5.885257625579834,
|
|
"epoch": 0.23024653226259337,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004998423510369862,
|
|
"loss": 5.8801,
|
|
"mean_token_accuracy": 0.16271908730268478,
|
|
"num_tokens": 4574007.0,
|
|
"step": 2050
|
|
},
|
|
{
|
|
"entropy": 5.919662857055664,
|
|
"epoch": 0.23080810917055092,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004998408447830022,
|
|
"loss": 5.8817,
|
|
"mean_token_accuracy": 0.15877689719200133,
|
|
"num_tokens": 4584146.0,
|
|
"step": 2055
|
|
},
|
|
{
|
|
"entropy": 5.917513370513916,
|
|
"epoch": 0.23136968607850844,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998393313699985,
|
|
"loss": 5.8949,
|
|
"mean_token_accuracy": 0.15564839094877242,
|
|
"num_tokens": 4594839.0,
|
|
"step": 2060
|
|
},
|
|
{
|
|
"entropy": 6.0348950862884525,
|
|
"epoch": 0.231931262986466,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998378107980233,
|
|
"loss": 6.0664,
|
|
"mean_token_accuracy": 0.14918494820594788,
|
|
"num_tokens": 4608229.0,
|
|
"step": 2065
|
|
},
|
|
{
|
|
"entropy": 5.948345947265625,
|
|
"epoch": 0.23249283989442354,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998362830671249,
|
|
"loss": 5.868,
|
|
"mean_token_accuracy": 0.15786196440458297,
|
|
"num_tokens": 4619206.0,
|
|
"step": 2070
|
|
},
|
|
{
|
|
"entropy": 5.810974550247193,
|
|
"epoch": 0.2330544168023811,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004998347481773522,
|
|
"loss": 5.9003,
|
|
"mean_token_accuracy": 0.1612463802099228,
|
|
"num_tokens": 4628966.0,
|
|
"step": 2075
|
|
},
|
|
{
|
|
"entropy": 5.922925519943237,
|
|
"epoch": 0.23361599371033864,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004998332061287538,
|
|
"loss": 5.7708,
|
|
"mean_token_accuracy": 0.1643754854798317,
|
|
"num_tokens": 4639935.0,
|
|
"step": 2080
|
|
},
|
|
{
|
|
"entropy": 5.940003728866577,
|
|
"epoch": 0.23417757061829617,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000499831656921379,
|
|
"loss": 6.0308,
|
|
"mean_token_accuracy": 0.15250603705644608,
|
|
"num_tokens": 4651998.0,
|
|
"step": 2085
|
|
},
|
|
{
|
|
"entropy": 6.024502515792847,
|
|
"epoch": 0.23473914752625372,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000499830100555277,
|
|
"loss": 6.0123,
|
|
"mean_token_accuracy": 0.15178350806236268,
|
|
"num_tokens": 4664002.0,
|
|
"step": 2090
|
|
},
|
|
{
|
|
"entropy": 5.8859413146972654,
|
|
"epoch": 0.23530072443421127,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998285370304974,
|
|
"loss": 5.8844,
|
|
"mean_token_accuracy": 0.15997599363327025,
|
|
"num_tokens": 4675343.0,
|
|
"step": 2095
|
|
},
|
|
{
|
|
"entropy": 5.954652452468872,
|
|
"epoch": 0.23586230134216882,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00049982696634709,
|
|
"loss": 5.9424,
|
|
"mean_token_accuracy": 0.1595751538872719,
|
|
"num_tokens": 4686410.0,
|
|
"step": 2100
|
|
},
|
|
{
|
|
"entropy": 5.892966175079346,
|
|
"epoch": 0.23642387825012637,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004998253885051048,
|
|
"loss": 5.9708,
|
|
"mean_token_accuracy": 0.15921736210584642,
|
|
"num_tokens": 4697768.0,
|
|
"step": 2105
|
|
},
|
|
{
|
|
"entropy": 6.021402645111084,
|
|
"epoch": 0.2369854551580839,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000499823803504592,
|
|
"loss": 5.9789,
|
|
"mean_token_accuracy": 0.15751142501831056,
|
|
"num_tokens": 4709933.0,
|
|
"step": 2110
|
|
},
|
|
{
|
|
"entropy": 5.943789482116699,
|
|
"epoch": 0.23754703206604144,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004998222113456022,
|
|
"loss": 6.0011,
|
|
"mean_token_accuracy": 0.15058652609586715,
|
|
"num_tokens": 4721385.0,
|
|
"step": 2115
|
|
},
|
|
{
|
|
"entropy": 5.848850536346435,
|
|
"epoch": 0.238108608973999,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998206120281858,
|
|
"loss": 5.8405,
|
|
"mean_token_accuracy": 0.1643430173397064,
|
|
"num_tokens": 4732562.0,
|
|
"step": 2120
|
|
},
|
|
{
|
|
"entropy": 5.8342078685760494,
|
|
"epoch": 0.23867018588195654,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000499819005552394,
|
|
"loss": 5.845,
|
|
"mean_token_accuracy": 0.16131186932325364,
|
|
"num_tokens": 4742794.0,
|
|
"step": 2125
|
|
},
|
|
{
|
|
"entropy": 5.809117650985717,
|
|
"epoch": 0.23923176278991407,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004998173919182779,
|
|
"loss": 5.8211,
|
|
"mean_token_accuracy": 0.16349539011716843,
|
|
"num_tokens": 4754903.0,
|
|
"step": 2130
|
|
},
|
|
{
|
|
"entropy": 5.895607423782349,
|
|
"epoch": 0.23979333969787162,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000499815771125889,
|
|
"loss": 5.8638,
|
|
"mean_token_accuracy": 0.15568834841251372,
|
|
"num_tokens": 4766165.0,
|
|
"step": 2135
|
|
},
|
|
{
|
|
"entropy": 5.870055103302002,
|
|
"epoch": 0.24035491660582917,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004998141431752785,
|
|
"loss": 5.8605,
|
|
"mean_token_accuracy": 0.16405391991138457,
|
|
"num_tokens": 4776551.0,
|
|
"step": 2140
|
|
},
|
|
{
|
|
"entropy": 5.973432111740112,
|
|
"epoch": 0.24091649351378672,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998125080664987,
|
|
"loss": 6.0518,
|
|
"mean_token_accuracy": 0.1545905739068985,
|
|
"num_tokens": 4788344.0,
|
|
"step": 2145
|
|
},
|
|
{
|
|
"entropy": 5.9314477920532225,
|
|
"epoch": 0.24147807042174427,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998108657996012,
|
|
"loss": 5.8448,
|
|
"mean_token_accuracy": 0.15539077967405318,
|
|
"num_tokens": 4799314.0,
|
|
"step": 2150
|
|
},
|
|
{
|
|
"entropy": 5.852494192123413,
|
|
"epoch": 0.2420396473297018,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998092163746387,
|
|
"loss": 5.9001,
|
|
"mean_token_accuracy": 0.16167995780706407,
|
|
"num_tokens": 4809588.0,
|
|
"step": 2155
|
|
},
|
|
{
|
|
"entropy": 5.873464822769165,
|
|
"epoch": 0.24260122423765934,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998075597916636,
|
|
"loss": 5.7199,
|
|
"mean_token_accuracy": 0.16549544185400009,
|
|
"num_tokens": 4820076.0,
|
|
"step": 2160
|
|
},
|
|
{
|
|
"entropy": 5.871007013320923,
|
|
"epoch": 0.2431628011456169,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998058960507286,
|
|
"loss": 5.9969,
|
|
"mean_token_accuracy": 0.15287212729454042,
|
|
"num_tokens": 4831504.0,
|
|
"step": 2165
|
|
},
|
|
{
|
|
"entropy": 5.903195571899414,
|
|
"epoch": 0.24372437805357444,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004998042251518866,
|
|
"loss": 5.852,
|
|
"mean_token_accuracy": 0.15901218801736833,
|
|
"num_tokens": 4842826.0,
|
|
"step": 2170
|
|
},
|
|
{
|
|
"entropy": 5.77811713218689,
|
|
"epoch": 0.244285954961532,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998025470951908,
|
|
"loss": 5.8241,
|
|
"mean_token_accuracy": 0.1635367751121521,
|
|
"num_tokens": 4853279.0,
|
|
"step": 2175
|
|
},
|
|
{
|
|
"entropy": 5.900368165969849,
|
|
"epoch": 0.24484753186948952,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998008618806949,
|
|
"loss": 5.8797,
|
|
"mean_token_accuracy": 0.1670658990740776,
|
|
"num_tokens": 4863332.0,
|
|
"step": 2180
|
|
},
|
|
{
|
|
"entropy": 5.892571830749512,
|
|
"epoch": 0.24540910877744707,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004997991695084523,
|
|
"loss": 6.0107,
|
|
"mean_token_accuracy": 0.14886087477207183,
|
|
"num_tokens": 4874217.0,
|
|
"step": 2185
|
|
},
|
|
{
|
|
"entropy": 5.966875743865967,
|
|
"epoch": 0.24597068568540462,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004997974699785169,
|
|
"loss": 5.8602,
|
|
"mean_token_accuracy": 0.16415059491991996,
|
|
"num_tokens": 4885322.0,
|
|
"step": 2190
|
|
},
|
|
{
|
|
"entropy": 5.766821432113647,
|
|
"epoch": 0.24653226259336217,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004997957632909429,
|
|
"loss": 5.8141,
|
|
"mean_token_accuracy": 0.16065592169761658,
|
|
"num_tokens": 4895546.0,
|
|
"step": 2195
|
|
},
|
|
{
|
|
"entropy": 6.031574392318726,
|
|
"epoch": 0.24709383950131972,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004997940494457846,
|
|
"loss": 6.0277,
|
|
"mean_token_accuracy": 0.15350462794303893,
|
|
"num_tokens": 4906957.0,
|
|
"step": 2200
|
|
},
|
|
{
|
|
"entropy": 5.988462448120117,
|
|
"epoch": 0.24765541640927724,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004997923284430967,
|
|
"loss": 5.9386,
|
|
"mean_token_accuracy": 0.15301946252584459,
|
|
"num_tokens": 4917965.0,
|
|
"step": 2205
|
|
},
|
|
{
|
|
"entropy": 5.804724073410034,
|
|
"epoch": 0.2482169933172348,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004997906002829338,
|
|
"loss": 5.8381,
|
|
"mean_token_accuracy": 0.16316511780023574,
|
|
"num_tokens": 4928585.0,
|
|
"step": 2210
|
|
},
|
|
{
|
|
"entropy": 5.896196508407593,
|
|
"epoch": 0.24877857022519234,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000499788864965351,
|
|
"loss": 5.8441,
|
|
"mean_token_accuracy": 0.16036625653505326,
|
|
"num_tokens": 4939818.0,
|
|
"step": 2215
|
|
},
|
|
{
|
|
"entropy": 5.913401126861572,
|
|
"epoch": 0.2493401471331499,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004997871224904036,
|
|
"loss": 5.9333,
|
|
"mean_token_accuracy": 0.15534456223249435,
|
|
"num_tokens": 4951752.0,
|
|
"step": 2220
|
|
},
|
|
{
|
|
"entropy": 5.7823755741119385,
|
|
"epoch": 0.24990172404110744,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004997853728581468,
|
|
"loss": 5.769,
|
|
"mean_token_accuracy": 0.16761937439441682,
|
|
"num_tokens": 4961846.0,
|
|
"step": 2225
|
|
},
|
|
{
|
|
"entropy": 5.883668756484985,
|
|
"epoch": 0.250463300949065,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004997836160686368,
|
|
"loss": 5.9231,
|
|
"mean_token_accuracy": 0.15353350937366486,
|
|
"num_tokens": 4973693.0,
|
|
"step": 2230
|
|
},
|
|
{
|
|
"entropy": 5.913628482818604,
|
|
"epoch": 0.25102487785702254,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004997818521219291,
|
|
"loss": 5.8394,
|
|
"mean_token_accuracy": 0.16180141270160675,
|
|
"num_tokens": 4986156.0,
|
|
"step": 2235
|
|
},
|
|
{
|
|
"entropy": 5.8587078094482425,
|
|
"epoch": 0.25158645476498004,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004997800810180803,
|
|
"loss": 5.92,
|
|
"mean_token_accuracy": 0.1600989058613777,
|
|
"num_tokens": 4997615.0,
|
|
"step": 2240
|
|
},
|
|
{
|
|
"entropy": 5.905812120437622,
|
|
"epoch": 0.2521480316729376,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004997783027571464,
|
|
"loss": 5.8608,
|
|
"mean_token_accuracy": 0.16093384325504304,
|
|
"num_tokens": 5007655.0,
|
|
"step": 2245
|
|
},
|
|
{
|
|
"entropy": 5.831983852386474,
|
|
"epoch": 0.25270960858089514,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004997765173391841,
|
|
"loss": 5.9228,
|
|
"mean_token_accuracy": 0.16303323209285736,
|
|
"num_tokens": 5018933.0,
|
|
"step": 2250
|
|
},
|
|
{
|
|
"entropy": 6.02240252494812,
|
|
"epoch": 0.2532711854888527,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004997747247642505,
|
|
"loss": 5.9194,
|
|
"mean_token_accuracy": 0.15804935097694398,
|
|
"num_tokens": 5030495.0,
|
|
"step": 2255
|
|
},
|
|
{
|
|
"entropy": 5.899349594116211,
|
|
"epoch": 0.25383276239681024,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004997729250324023,
|
|
"loss": 5.9707,
|
|
"mean_token_accuracy": 0.15581197887659073,
|
|
"num_tokens": 5041553.0,
|
|
"step": 2260
|
|
},
|
|
{
|
|
"entropy": 5.873454856872558,
|
|
"epoch": 0.2543943393047678,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004997711181436971,
|
|
"loss": 5.8922,
|
|
"mean_token_accuracy": 0.16303403079509735,
|
|
"num_tokens": 5052312.0,
|
|
"step": 2265
|
|
},
|
|
{
|
|
"entropy": 5.983870792388916,
|
|
"epoch": 0.25495591621272534,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004997693040981922,
|
|
"loss": 6.0817,
|
|
"mean_token_accuracy": 0.15263137072324753,
|
|
"num_tokens": 5063445.0,
|
|
"step": 2270
|
|
},
|
|
{
|
|
"entropy": 5.986553621292114,
|
|
"epoch": 0.2555174931206829,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004997674828959456,
|
|
"loss": 5.8491,
|
|
"mean_token_accuracy": 0.16022175401449204,
|
|
"num_tokens": 5073052.0,
|
|
"step": 2275
|
|
},
|
|
{
|
|
"entropy": 5.865057420730591,
|
|
"epoch": 0.25607907002864044,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004997656545370151,
|
|
"loss": 5.9049,
|
|
"mean_token_accuracy": 0.16042996644973756,
|
|
"num_tokens": 5084174.0,
|
|
"step": 2280
|
|
},
|
|
{
|
|
"entropy": 5.910764932632446,
|
|
"epoch": 0.256640646936598,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000499763819021459,
|
|
"loss": 5.8863,
|
|
"mean_token_accuracy": 0.1606077790260315,
|
|
"num_tokens": 5094106.0,
|
|
"step": 2285
|
|
},
|
|
{
|
|
"entropy": 5.987953424453735,
|
|
"epoch": 0.2572022238445555,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004997619763493357,
|
|
"loss": 5.9748,
|
|
"mean_token_accuracy": 0.15885440707206727,
|
|
"num_tokens": 5106963.0,
|
|
"step": 2290
|
|
},
|
|
{
|
|
"entropy": 5.774737882614136,
|
|
"epoch": 0.25776380075251304,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000499760126520704,
|
|
"loss": 5.7889,
|
|
"mean_token_accuracy": 0.15251622200012208,
|
|
"num_tokens": 5119476.0,
|
|
"step": 2295
|
|
},
|
|
{
|
|
"entropy": 5.9726386070251465,
|
|
"epoch": 0.2583253776604706,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004997582695356225,
|
|
"loss": 6.0337,
|
|
"mean_token_accuracy": 0.14983026534318925,
|
|
"num_tokens": 5132169.0,
|
|
"step": 2300
|
|
},
|
|
{
|
|
"entropy": 5.869831800460815,
|
|
"epoch": 0.25888695456842814,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004997564053941507,
|
|
"loss": 5.8598,
|
|
"mean_token_accuracy": 0.15989481210708617,
|
|
"num_tokens": 5143354.0,
|
|
"step": 2305
|
|
},
|
|
{
|
|
"entropy": 5.843227052688599,
|
|
"epoch": 0.2594485314763857,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004997545340963478,
|
|
"loss": 5.9274,
|
|
"mean_token_accuracy": 0.15680477470159532,
|
|
"num_tokens": 5154624.0,
|
|
"step": 2310
|
|
},
|
|
{
|
|
"entropy": 5.9521379470825195,
|
|
"epoch": 0.26001010838434324,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004997526556422733,
|
|
"loss": 5.8292,
|
|
"mean_token_accuracy": 0.1580936551094055,
|
|
"num_tokens": 5165349.0,
|
|
"step": 2315
|
|
},
|
|
{
|
|
"entropy": 5.822861623764038,
|
|
"epoch": 0.2605716852923008,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004997507700319872,
|
|
"loss": 5.9123,
|
|
"mean_token_accuracy": 0.1558194637298584,
|
|
"num_tokens": 5175874.0,
|
|
"step": 2320
|
|
},
|
|
{
|
|
"entropy": 5.890210199356079,
|
|
"epoch": 0.26113326220025834,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004997488772655492,
|
|
"loss": 5.7924,
|
|
"mean_token_accuracy": 0.16859100311994552,
|
|
"num_tokens": 5186591.0,
|
|
"step": 2325
|
|
},
|
|
{
|
|
"entropy": 5.807303524017334,
|
|
"epoch": 0.2616948391082159,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004997469773430199,
|
|
"loss": 5.9036,
|
|
"mean_token_accuracy": 0.16755606681108476,
|
|
"num_tokens": 5197307.0,
|
|
"step": 2330
|
|
},
|
|
{
|
|
"entropy": 5.858344030380249,
|
|
"epoch": 0.2622564160161734,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004997450702644596,
|
|
"loss": 5.8595,
|
|
"mean_token_accuracy": 0.15741084516048431,
|
|
"num_tokens": 5209868.0,
|
|
"step": 2335
|
|
},
|
|
{
|
|
"entropy": 5.90931806564331,
|
|
"epoch": 0.26281799292413094,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004997431560299292,
|
|
"loss": 5.8743,
|
|
"mean_token_accuracy": 0.16276440173387527,
|
|
"num_tokens": 5220365.0,
|
|
"step": 2340
|
|
},
|
|
{
|
|
"entropy": 5.818673753738404,
|
|
"epoch": 0.2633795698320885,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004997412346394894,
|
|
"loss": 5.7881,
|
|
"mean_token_accuracy": 0.16023485809564592,
|
|
"num_tokens": 5231575.0,
|
|
"step": 2345
|
|
},
|
|
{
|
|
"entropy": 5.897857189178467,
|
|
"epoch": 0.26394114674004604,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004997393060932017,
|
|
"loss": 5.8785,
|
|
"mean_token_accuracy": 0.1601746052503586,
|
|
"num_tokens": 5241852.0,
|
|
"step": 2350
|
|
},
|
|
{
|
|
"entropy": 5.899834012985229,
|
|
"epoch": 0.2645027236480036,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004997373703911273,
|
|
"loss": 5.9222,
|
|
"mean_token_accuracy": 0.16097686886787416,
|
|
"num_tokens": 5254536.0,
|
|
"step": 2355
|
|
},
|
|
{
|
|
"entropy": 5.932958650588989,
|
|
"epoch": 0.26506430055596114,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004997354275333277,
|
|
"loss": 5.8317,
|
|
"mean_token_accuracy": 0.1640108659863472,
|
|
"num_tokens": 5264946.0,
|
|
"step": 2360
|
|
},
|
|
{
|
|
"entropy": 5.631682395935059,
|
|
"epoch": 0.2656258774639187,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000499733477519865,
|
|
"loss": 5.6754,
|
|
"mean_token_accuracy": 0.16263261884450914,
|
|
"num_tokens": 5275527.0,
|
|
"step": 2365
|
|
},
|
|
{
|
|
"entropy": 5.878888082504273,
|
|
"epoch": 0.26618745437187624,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004997315203508013,
|
|
"loss": 5.8516,
|
|
"mean_token_accuracy": 0.1570986658334732,
|
|
"num_tokens": 5285471.0,
|
|
"step": 2370
|
|
},
|
|
{
|
|
"entropy": 5.764362859725952,
|
|
"epoch": 0.2667490312798338,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004997295560261988,
|
|
"loss": 5.7642,
|
|
"mean_token_accuracy": 0.15874749571084976,
|
|
"num_tokens": 5295743.0,
|
|
"step": 2375
|
|
},
|
|
{
|
|
"entropy": 5.877685689926148,
|
|
"epoch": 0.26731060818779134,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00049972758454612,
|
|
"loss": 5.9113,
|
|
"mean_token_accuracy": 0.1542122907936573,
|
|
"num_tokens": 5307963.0,
|
|
"step": 2380
|
|
},
|
|
{
|
|
"entropy": 5.861995458602905,
|
|
"epoch": 0.26787218509574884,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004997256059106279,
|
|
"loss": 5.8059,
|
|
"mean_token_accuracy": 0.16155965775251388,
|
|
"num_tokens": 5318394.0,
|
|
"step": 2385
|
|
},
|
|
{
|
|
"entropy": 5.900924968719482,
|
|
"epoch": 0.2684337620037064,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004997236201197853,
|
|
"loss": 6.0391,
|
|
"mean_token_accuracy": 0.14638192504644393,
|
|
"num_tokens": 5331728.0,
|
|
"step": 2390
|
|
},
|
|
{
|
|
"entropy": 5.966968250274658,
|
|
"epoch": 0.26899533891166394,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004997216271736554,
|
|
"loss": 5.8965,
|
|
"mean_token_accuracy": 0.1681509181857109,
|
|
"num_tokens": 5342825.0,
|
|
"step": 2395
|
|
},
|
|
{
|
|
"entropy": 5.880633354187012,
|
|
"epoch": 0.2695569158196215,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004997196270723018,
|
|
"loss": 5.8227,
|
|
"mean_token_accuracy": 0.16092611998319625,
|
|
"num_tokens": 5354232.0,
|
|
"step": 2400
|
|
},
|
|
{
|
|
"entropy": 5.8500697135925295,
|
|
"epoch": 0.27011849272757904,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004997176198157881,
|
|
"loss": 5.898,
|
|
"mean_token_accuracy": 0.15567438974976539,
|
|
"num_tokens": 5364807.0,
|
|
"step": 2405
|
|
},
|
|
{
|
|
"entropy": 5.827037715911866,
|
|
"epoch": 0.2706800696355366,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004997156054041781,
|
|
"loss": 5.8845,
|
|
"mean_token_accuracy": 0.160299713909626,
|
|
"num_tokens": 5375593.0,
|
|
"step": 2410
|
|
},
|
|
{
|
|
"entropy": 5.85796971321106,
|
|
"epoch": 0.27124164654349414,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004997135838375362,
|
|
"loss": 5.834,
|
|
"mean_token_accuracy": 0.16348498463630676,
|
|
"num_tokens": 5386740.0,
|
|
"step": 2415
|
|
},
|
|
{
|
|
"entropy": 5.861660146713257,
|
|
"epoch": 0.2718032234514517,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004997115551159267,
|
|
"loss": 5.8209,
|
|
"mean_token_accuracy": 0.16418611854314805,
|
|
"num_tokens": 5397732.0,
|
|
"step": 2420
|
|
},
|
|
{
|
|
"entropy": 5.94402961730957,
|
|
"epoch": 0.27236480035940924,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000499709519239414,
|
|
"loss": 5.8794,
|
|
"mean_token_accuracy": 0.15414437800645828,
|
|
"num_tokens": 5409392.0,
|
|
"step": 2425
|
|
},
|
|
{
|
|
"entropy": 5.664468765258789,
|
|
"epoch": 0.2729263772673668,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004997074762080632,
|
|
"loss": 5.8412,
|
|
"mean_token_accuracy": 0.16693630516529084,
|
|
"num_tokens": 5420903.0,
|
|
"step": 2430
|
|
},
|
|
{
|
|
"entropy": 5.802863931655883,
|
|
"epoch": 0.2734879541753243,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000499705426021939,
|
|
"loss": 5.7761,
|
|
"mean_token_accuracy": 0.15942942947149277,
|
|
"num_tokens": 5432631.0,
|
|
"step": 2435
|
|
},
|
|
{
|
|
"entropy": 5.864587879180908,
|
|
"epoch": 0.27404953108328184,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000499703368681107,
|
|
"loss": 5.7458,
|
|
"mean_token_accuracy": 0.16454415321350097,
|
|
"num_tokens": 5443463.0,
|
|
"step": 2440
|
|
},
|
|
{
|
|
"entropy": 5.8874420642852785,
|
|
"epoch": 0.2746111079912394,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004997013041856326,
|
|
"loss": 6.0522,
|
|
"mean_token_accuracy": 0.15659836456179618,
|
|
"num_tokens": 5455903.0,
|
|
"step": 2445
|
|
},
|
|
{
|
|
"entropy": 5.890227794647217,
|
|
"epoch": 0.27517268489919694,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004996992325355815,
|
|
"loss": 5.8903,
|
|
"mean_token_accuracy": 0.15483457446098328,
|
|
"num_tokens": 5467201.0,
|
|
"step": 2450
|
|
},
|
|
{
|
|
"entropy": 5.875626754760742,
|
|
"epoch": 0.2757342618071545,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004996971537310198,
|
|
"loss": 5.7529,
|
|
"mean_token_accuracy": 0.16340564638376237,
|
|
"num_tokens": 5478109.0,
|
|
"step": 2455
|
|
},
|
|
{
|
|
"entropy": 5.876842784881592,
|
|
"epoch": 0.27629583871511204,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004996950677720133,
|
|
"loss": 5.8787,
|
|
"mean_token_accuracy": 0.15813624560832978,
|
|
"num_tokens": 5489621.0,
|
|
"step": 2460
|
|
},
|
|
{
|
|
"entropy": 5.80870246887207,
|
|
"epoch": 0.2768574156230696,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000499692974658629,
|
|
"loss": 5.8328,
|
|
"mean_token_accuracy": 0.1639888569712639,
|
|
"num_tokens": 5500606.0,
|
|
"step": 2465
|
|
},
|
|
{
|
|
"entropy": 5.865239953994751,
|
|
"epoch": 0.27741899253102714,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004996908743909331,
|
|
"loss": 5.7753,
|
|
"mean_token_accuracy": 0.17143337428569794,
|
|
"num_tokens": 5510768.0,
|
|
"step": 2470
|
|
},
|
|
{
|
|
"entropy": 5.7702569484710695,
|
|
"epoch": 0.2779805694389847,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004996887669689926,
|
|
"loss": 5.8076,
|
|
"mean_token_accuracy": 0.16477752476930618,
|
|
"num_tokens": 5522210.0,
|
|
"step": 2475
|
|
},
|
|
{
|
|
"entropy": 5.871284866333008,
|
|
"epoch": 0.2785421463469422,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004996866523928747,
|
|
"loss": 5.9173,
|
|
"mean_token_accuracy": 0.15478019267320633,
|
|
"num_tokens": 5533055.0,
|
|
"step": 2480
|
|
},
|
|
{
|
|
"entropy": 5.936899280548095,
|
|
"epoch": 0.27910372325489974,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004996845306626467,
|
|
"loss": 5.9302,
|
|
"mean_token_accuracy": 0.15565606355667114,
|
|
"num_tokens": 5544345.0,
|
|
"step": 2485
|
|
},
|
|
{
|
|
"entropy": 5.899860382080078,
|
|
"epoch": 0.2796653001628573,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004996824017783759,
|
|
"loss": 5.8508,
|
|
"mean_token_accuracy": 0.1602659970521927,
|
|
"num_tokens": 5556734.0,
|
|
"step": 2490
|
|
},
|
|
{
|
|
"entropy": 5.805173587799072,
|
|
"epoch": 0.28022687707081484,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004996802657401304,
|
|
"loss": 5.8803,
|
|
"mean_token_accuracy": 0.16296618580818176,
|
|
"num_tokens": 5566874.0,
|
|
"step": 2495
|
|
},
|
|
{
|
|
"entropy": 5.9315550327301025,
|
|
"epoch": 0.2807884539787724,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004996781225479781,
|
|
"loss": 5.8878,
|
|
"mean_token_accuracy": 0.15491053313016892,
|
|
"num_tokens": 5578812.0,
|
|
"step": 2500
|
|
},
|
|
{
|
|
"entropy": 5.847195196151733,
|
|
"epoch": 0.28135003088672994,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004996759722019872,
|
|
"loss": 5.9389,
|
|
"mean_token_accuracy": 0.16007010489702225,
|
|
"num_tokens": 5590021.0,
|
|
"step": 2505
|
|
},
|
|
{
|
|
"entropy": 5.904675149917603,
|
|
"epoch": 0.2819116077946875,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004996738147022262,
|
|
"loss": 5.9373,
|
|
"mean_token_accuracy": 0.150753453373909,
|
|
"num_tokens": 5600921.0,
|
|
"step": 2510
|
|
},
|
|
{
|
|
"entropy": 5.90674614906311,
|
|
"epoch": 0.28247318470264504,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004996716500487638,
|
|
"loss": 5.8641,
|
|
"mean_token_accuracy": 0.15689948797225953,
|
|
"num_tokens": 5610615.0,
|
|
"step": 2515
|
|
},
|
|
{
|
|
"entropy": 5.765136003494263,
|
|
"epoch": 0.2830347616106026,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000499669478241669,
|
|
"loss": 5.7885,
|
|
"mean_token_accuracy": 0.1646771937608719,
|
|
"num_tokens": 5621596.0,
|
|
"step": 2520
|
|
},
|
|
{
|
|
"entropy": 5.968653011322021,
|
|
"epoch": 0.28359633851856014,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004996672992810108,
|
|
"loss": 5.8273,
|
|
"mean_token_accuracy": 0.16271875649690629,
|
|
"num_tokens": 5633047.0,
|
|
"step": 2525
|
|
},
|
|
{
|
|
"entropy": 5.8039604187011715,
|
|
"epoch": 0.28415791542651764,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004996651131668587,
|
|
"loss": 5.811,
|
|
"mean_token_accuracy": 0.15627873688936234,
|
|
"num_tokens": 5644970.0,
|
|
"step": 2530
|
|
},
|
|
{
|
|
"entropy": 5.813772583007813,
|
|
"epoch": 0.2847194923344752,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004996629198992823,
|
|
"loss": 5.939,
|
|
"mean_token_accuracy": 0.15850594341754914,
|
|
"num_tokens": 5656631.0,
|
|
"step": 2535
|
|
},
|
|
{
|
|
"entropy": 5.905940103530884,
|
|
"epoch": 0.28528106924243274,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004996607194783513,
|
|
"loss": 5.8919,
|
|
"mean_token_accuracy": 0.15616682022809983,
|
|
"num_tokens": 5668808.0,
|
|
"step": 2540
|
|
},
|
|
{
|
|
"entropy": 5.760390377044677,
|
|
"epoch": 0.2858426461503903,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004996585119041359,
|
|
"loss": 5.8169,
|
|
"mean_token_accuracy": 0.1564560815691948,
|
|
"num_tokens": 5679493.0,
|
|
"step": 2545
|
|
},
|
|
{
|
|
"entropy": 5.950744247436523,
|
|
"epoch": 0.28640422305834784,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004996562971767063,
|
|
"loss": 5.8465,
|
|
"mean_token_accuracy": 0.16337623000144957,
|
|
"num_tokens": 5689879.0,
|
|
"step": 2550
|
|
},
|
|
{
|
|
"entropy": 5.8402002334594725,
|
|
"epoch": 0.2869657999663054,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000499654075296133,
|
|
"loss": 5.9299,
|
|
"mean_token_accuracy": 0.1620929419994354,
|
|
"num_tokens": 5699934.0,
|
|
"step": 2555
|
|
},
|
|
{
|
|
"entropy": 5.833514976501465,
|
|
"epoch": 0.28752737687426294,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000499651846262487,
|
|
"loss": 5.847,
|
|
"mean_token_accuracy": 0.16643718332052232,
|
|
"num_tokens": 5710171.0,
|
|
"step": 2560
|
|
},
|
|
{
|
|
"entropy": 5.89036922454834,
|
|
"epoch": 0.2880889537822205,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004996496100758389,
|
|
"loss": 5.8521,
|
|
"mean_token_accuracy": 0.15369296669960023,
|
|
"num_tokens": 5721190.0,
|
|
"step": 2565
|
|
},
|
|
{
|
|
"entropy": 5.9653236865997314,
|
|
"epoch": 0.28865053069017804,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004996473667362604,
|
|
"loss": 5.9678,
|
|
"mean_token_accuracy": 0.15457451790571214,
|
|
"num_tokens": 5733706.0,
|
|
"step": 2570
|
|
},
|
|
{
|
|
"entropy": 5.831788444519043,
|
|
"epoch": 0.28921210759813554,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004996451162438224,
|
|
"loss": 5.9374,
|
|
"mean_token_accuracy": 0.1601427301764488,
|
|
"num_tokens": 5745712.0,
|
|
"step": 2575
|
|
},
|
|
{
|
|
"entropy": 5.781694507598877,
|
|
"epoch": 0.2897736845060931,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004996428585985967,
|
|
"loss": 5.7341,
|
|
"mean_token_accuracy": 0.17258975356817247,
|
|
"num_tokens": 5757915.0,
|
|
"step": 2580
|
|
},
|
|
{
|
|
"entropy": 5.880732631683349,
|
|
"epoch": 0.29033526141405064,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004996405938006553,
|
|
"loss": 5.8882,
|
|
"mean_token_accuracy": 0.16366344690322876,
|
|
"num_tokens": 5768788.0,
|
|
"step": 2585
|
|
},
|
|
{
|
|
"entropy": 5.860728406906128,
|
|
"epoch": 0.2908968383220082,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004996383218500703,
|
|
"loss": 5.8124,
|
|
"mean_token_accuracy": 0.1624564841389656,
|
|
"num_tokens": 5779806.0,
|
|
"step": 2590
|
|
},
|
|
{
|
|
"entropy": 5.755586099624634,
|
|
"epoch": 0.29145841522996574,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000499636042746914,
|
|
"loss": 5.7729,
|
|
"mean_token_accuracy": 0.1583534672856331,
|
|
"num_tokens": 5790177.0,
|
|
"step": 2595
|
|
},
|
|
{
|
|
"entropy": 5.843555927276611,
|
|
"epoch": 0.2920199921379233,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000499633756491259,
|
|
"loss": 5.8031,
|
|
"mean_token_accuracy": 0.16728467345237732,
|
|
"num_tokens": 5800251.0,
|
|
"step": 2600
|
|
},
|
|
{
|
|
"entropy": 5.909883689880371,
|
|
"epoch": 0.29258156904588084,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004996314630831781,
|
|
"loss": 5.8989,
|
|
"mean_token_accuracy": 0.1601306065917015,
|
|
"num_tokens": 5812210.0,
|
|
"step": 2605
|
|
},
|
|
{
|
|
"entropy": 5.9030238628387455,
|
|
"epoch": 0.2931431459538384,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004996291625227443,
|
|
"loss": 5.8644,
|
|
"mean_token_accuracy": 0.16422059535980224,
|
|
"num_tokens": 5823280.0,
|
|
"step": 2610
|
|
},
|
|
{
|
|
"entropy": 5.924188566207886,
|
|
"epoch": 0.29370472286179594,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004996268548100307,
|
|
"loss": 5.9502,
|
|
"mean_token_accuracy": 0.15365658402442933,
|
|
"num_tokens": 5835076.0,
|
|
"step": 2615
|
|
},
|
|
{
|
|
"entropy": 5.797477912902832,
|
|
"epoch": 0.2942662997697535,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000499624539945111,
|
|
"loss": 5.7425,
|
|
"mean_token_accuracy": 0.16603392660617827,
|
|
"num_tokens": 5845376.0,
|
|
"step": 2620
|
|
},
|
|
{
|
|
"entropy": 5.711445426940918,
|
|
"epoch": 0.294827876677711,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004996222179280589,
|
|
"loss": 5.7702,
|
|
"mean_token_accuracy": 0.1608809530735016,
|
|
"num_tokens": 5857124.0,
|
|
"step": 2625
|
|
},
|
|
{
|
|
"entropy": 5.9171717166900635,
|
|
"epoch": 0.29538945358566854,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004996198887589481,
|
|
"loss": 5.8885,
|
|
"mean_token_accuracy": 0.15417518019676207,
|
|
"num_tokens": 5868681.0,
|
|
"step": 2630
|
|
},
|
|
{
|
|
"entropy": 5.88248610496521,
|
|
"epoch": 0.2959510304936261,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004996175524378531,
|
|
"loss": 5.8621,
|
|
"mean_token_accuracy": 0.16559387296438216,
|
|
"num_tokens": 5880532.0,
|
|
"step": 2635
|
|
},
|
|
{
|
|
"entropy": 5.840338468551636,
|
|
"epoch": 0.29651260740158364,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000499615208964848,
|
|
"loss": 5.8342,
|
|
"mean_token_accuracy": 0.16637962609529494,
|
|
"num_tokens": 5891582.0,
|
|
"step": 2640
|
|
},
|
|
{
|
|
"entropy": 5.8416746139526365,
|
|
"epoch": 0.2970741843095412,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004996128583400077,
|
|
"loss": 5.8178,
|
|
"mean_token_accuracy": 0.15835877358913422,
|
|
"num_tokens": 5903543.0,
|
|
"step": 2645
|
|
},
|
|
{
|
|
"entropy": 5.731740427017212,
|
|
"epoch": 0.29763576121749874,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004996105005634066,
|
|
"loss": 5.7954,
|
|
"mean_token_accuracy": 0.16752633601427078,
|
|
"num_tokens": 5913140.0,
|
|
"step": 2650
|
|
},
|
|
{
|
|
"entropy": 5.834004831314087,
|
|
"epoch": 0.2981973381254563,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004996081356351202,
|
|
"loss": 5.755,
|
|
"mean_token_accuracy": 0.16460932940244674,
|
|
"num_tokens": 5924010.0,
|
|
"step": 2655
|
|
},
|
|
{
|
|
"entropy": 5.876258516311646,
|
|
"epoch": 0.29875891503341384,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004996057635552237,
|
|
"loss": 5.9686,
|
|
"mean_token_accuracy": 0.15854546874761583,
|
|
"num_tokens": 5936246.0,
|
|
"step": 2660
|
|
},
|
|
{
|
|
"entropy": 5.855793046951294,
|
|
"epoch": 0.2993204919413714,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004996033843237925,
|
|
"loss": 5.8589,
|
|
"mean_token_accuracy": 0.15378582924604417,
|
|
"num_tokens": 5947594.0,
|
|
"step": 2665
|
|
},
|
|
{
|
|
"entropy": 5.903825950622559,
|
|
"epoch": 0.29988206884932894,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004996009979409025,
|
|
"loss": 5.7911,
|
|
"mean_token_accuracy": 0.15631641298532487,
|
|
"num_tokens": 5957660.0,
|
|
"step": 2670
|
|
},
|
|
{
|
|
"entropy": 5.682236814498902,
|
|
"epoch": 0.30044364575728644,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004995986044066295,
|
|
"loss": 5.6203,
|
|
"mean_token_accuracy": 0.17106491774320604,
|
|
"num_tokens": 5968881.0,
|
|
"step": 2675
|
|
},
|
|
{
|
|
"entropy": 5.778797912597656,
|
|
"epoch": 0.301005222665244,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00049959620372105,
|
|
"loss": 5.7907,
|
|
"mean_token_accuracy": 0.16492329984903337,
|
|
"num_tokens": 5980032.0,
|
|
"step": 2680
|
|
},
|
|
{
|
|
"entropy": 5.740841341018677,
|
|
"epoch": 0.30156679957320154,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004995937958842401,
|
|
"loss": 5.8008,
|
|
"mean_token_accuracy": 0.16221535503864287,
|
|
"num_tokens": 5991781.0,
|
|
"step": 2685
|
|
},
|
|
{
|
|
"entropy": 5.818138599395752,
|
|
"epoch": 0.3021283764811591,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004995913808962767,
|
|
"loss": 5.8343,
|
|
"mean_token_accuracy": 0.1621527448296547,
|
|
"num_tokens": 6002303.0,
|
|
"step": 2690
|
|
},
|
|
{
|
|
"entropy": 5.8888787746429445,
|
|
"epoch": 0.30268995338911664,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004995889587572366,
|
|
"loss": 5.9065,
|
|
"mean_token_accuracy": 0.1600490316748619,
|
|
"num_tokens": 6011523.0,
|
|
"step": 2695
|
|
},
|
|
{
|
|
"entropy": 5.85958423614502,
|
|
"epoch": 0.3032515302970742,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000499586529467197,
|
|
"loss": 5.7173,
|
|
"mean_token_accuracy": 0.16480220556259156,
|
|
"num_tokens": 6022169.0,
|
|
"step": 2700
|
|
},
|
|
{
|
|
"entropy": 5.674841737747192,
|
|
"epoch": 0.30381310720503174,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004995840930262351,
|
|
"loss": 5.7695,
|
|
"mean_token_accuracy": 0.16273038387298583,
|
|
"num_tokens": 6033393.0,
|
|
"step": 2705
|
|
},
|
|
{
|
|
"entropy": 5.830945682525635,
|
|
"epoch": 0.3043746841129893,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004995816494344287,
|
|
"loss": 5.8442,
|
|
"mean_token_accuracy": 0.15597543269395828,
|
|
"num_tokens": 6045365.0,
|
|
"step": 2710
|
|
},
|
|
{
|
|
"entropy": 5.830998420715332,
|
|
"epoch": 0.30493626102094684,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004995791986918554,
|
|
"loss": 5.8675,
|
|
"mean_token_accuracy": 0.16169115602970124,
|
|
"num_tokens": 6057482.0,
|
|
"step": 2715
|
|
},
|
|
{
|
|
"entropy": 5.871564197540283,
|
|
"epoch": 0.30549783792890434,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004995767407985933,
|
|
"loss": 5.7681,
|
|
"mean_token_accuracy": 0.1672608807682991,
|
|
"num_tokens": 6068194.0,
|
|
"step": 2720
|
|
},
|
|
{
|
|
"entropy": 5.78353214263916,
|
|
"epoch": 0.3060594148368619,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004995742757547207,
|
|
"loss": 5.8293,
|
|
"mean_token_accuracy": 0.16143801659345627,
|
|
"num_tokens": 6080540.0,
|
|
"step": 2725
|
|
},
|
|
{
|
|
"entropy": 5.745278215408325,
|
|
"epoch": 0.30662099174481944,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000499571803560316,
|
|
"loss": 5.8713,
|
|
"mean_token_accuracy": 0.15866425335407258,
|
|
"num_tokens": 6092464.0,
|
|
"step": 2730
|
|
},
|
|
{
|
|
"entropy": 5.87835726737976,
|
|
"epoch": 0.307182568652777,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004995693242154581,
|
|
"loss": 5.8209,
|
|
"mean_token_accuracy": 0.16295599937438965,
|
|
"num_tokens": 6103242.0,
|
|
"step": 2735
|
|
},
|
|
{
|
|
"entropy": 5.812991285324097,
|
|
"epoch": 0.30774414556073454,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004995668377202258,
|
|
"loss": 5.8634,
|
|
"mean_token_accuracy": 0.16028525680303574,
|
|
"num_tokens": 6116383.0,
|
|
"step": 2740
|
|
},
|
|
{
|
|
"entropy": 5.766334486007691,
|
|
"epoch": 0.3083057224686921,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004995643440746982,
|
|
"loss": 5.6643,
|
|
"mean_token_accuracy": 0.17048484236001968,
|
|
"num_tokens": 6126883.0,
|
|
"step": 2745
|
|
},
|
|
{
|
|
"entropy": 5.8382853984832765,
|
|
"epoch": 0.30886729937664964,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004995618432789548,
|
|
"loss": 5.861,
|
|
"mean_token_accuracy": 0.1548911824822426,
|
|
"num_tokens": 6139613.0,
|
|
"step": 2750
|
|
},
|
|
{
|
|
"entropy": 5.867930698394775,
|
|
"epoch": 0.3094288762846072,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004995593353330753,
|
|
"loss": 5.9304,
|
|
"mean_token_accuracy": 0.15693748146295547,
|
|
"num_tokens": 6151950.0,
|
|
"step": 2755
|
|
},
|
|
{
|
|
"entropy": 5.812861728668213,
|
|
"epoch": 0.30999045319256474,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004995568202371393,
|
|
"loss": 5.7224,
|
|
"mean_token_accuracy": 0.17015610337257386,
|
|
"num_tokens": 6161563.0,
|
|
"step": 2760
|
|
},
|
|
{
|
|
"entropy": 5.749365663528442,
|
|
"epoch": 0.3105520301005223,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004995542979912272,
|
|
"loss": 5.7369,
|
|
"mean_token_accuracy": 0.1699253425002098,
|
|
"num_tokens": 6170966.0,
|
|
"step": 2765
|
|
},
|
|
{
|
|
"entropy": 5.7737060546875,
|
|
"epoch": 0.3111136070084798,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004995517685954192,
|
|
"loss": 5.8066,
|
|
"mean_token_accuracy": 0.16174303740262985,
|
|
"num_tokens": 6182563.0,
|
|
"step": 2770
|
|
},
|
|
{
|
|
"entropy": 5.850103712081909,
|
|
"epoch": 0.31167518391643734,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004995492320497958,
|
|
"loss": 5.9185,
|
|
"mean_token_accuracy": 0.15409982949495316,
|
|
"num_tokens": 6194495.0,
|
|
"step": 2775
|
|
},
|
|
{
|
|
"entropy": 5.839843225479126,
|
|
"epoch": 0.3122367608243949,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004995466883544376,
|
|
"loss": 5.8204,
|
|
"mean_token_accuracy": 0.15846606194972992,
|
|
"num_tokens": 6206594.0,
|
|
"step": 2780
|
|
},
|
|
{
|
|
"entropy": 5.840381479263305,
|
|
"epoch": 0.31279833773235244,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004995441375094258,
|
|
"loss": 5.8248,
|
|
"mean_token_accuracy": 0.15951959937810897,
|
|
"num_tokens": 6218371.0,
|
|
"step": 2785
|
|
},
|
|
{
|
|
"entropy": 5.90253176689148,
|
|
"epoch": 0.31335991464031,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004995415795148417,
|
|
"loss": 5.7562,
|
|
"mean_token_accuracy": 0.1673472911119461,
|
|
"num_tokens": 6228723.0,
|
|
"step": 2790
|
|
},
|
|
{
|
|
"entropy": 5.830163764953613,
|
|
"epoch": 0.31392149154826754,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004995390143707665,
|
|
"loss": 5.9485,
|
|
"mean_token_accuracy": 0.1597628489136696,
|
|
"num_tokens": 6240535.0,
|
|
"step": 2795
|
|
},
|
|
{
|
|
"entropy": 5.762459945678711,
|
|
"epoch": 0.3144830684562251,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004995364420772821,
|
|
"loss": 5.6412,
|
|
"mean_token_accuracy": 0.16819480657577515,
|
|
"num_tokens": 6250643.0,
|
|
"step": 2800
|
|
},
|
|
{
|
|
"entropy": 5.762458372116089,
|
|
"epoch": 0.31504464536418264,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004995338626344702,
|
|
"loss": 5.7843,
|
|
"mean_token_accuracy": 0.16505634933710098,
|
|
"num_tokens": 6259569.0,
|
|
"step": 2805
|
|
},
|
|
{
|
|
"entropy": 5.820625829696655,
|
|
"epoch": 0.3156062222721402,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000499531276042413,
|
|
"loss": 5.9333,
|
|
"mean_token_accuracy": 0.16434977650642396,
|
|
"num_tokens": 6271108.0,
|
|
"step": 2810
|
|
},
|
|
{
|
|
"entropy": 5.940713834762573,
|
|
"epoch": 0.31616779918009774,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004995286823011929,
|
|
"loss": 5.7569,
|
|
"mean_token_accuracy": 0.15814750343561174,
|
|
"num_tokens": 6282352.0,
|
|
"step": 2815
|
|
},
|
|
{
|
|
"entropy": 5.755598640441894,
|
|
"epoch": 0.31672937608805524,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004995260814108926,
|
|
"loss": 5.8778,
|
|
"mean_token_accuracy": 0.15963443219661713,
|
|
"num_tokens": 6294946.0,
|
|
"step": 2820
|
|
},
|
|
{
|
|
"entropy": 5.729330968856812,
|
|
"epoch": 0.3172909529960128,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004995234733715947,
|
|
"loss": 5.6965,
|
|
"mean_token_accuracy": 0.16342825293540955,
|
|
"num_tokens": 6305552.0,
|
|
"step": 2825
|
|
},
|
|
{
|
|
"entropy": 5.801796007156372,
|
|
"epoch": 0.31785252990397034,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004995208581833824,
|
|
"loss": 5.7689,
|
|
"mean_token_accuracy": 0.17125651091337205,
|
|
"num_tokens": 6315815.0,
|
|
"step": 2830
|
|
},
|
|
{
|
|
"entropy": 5.7499488353729244,
|
|
"epoch": 0.3184141068119279,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004995182358463388,
|
|
"loss": 5.8121,
|
|
"mean_token_accuracy": 0.16185301691293716,
|
|
"num_tokens": 6327384.0,
|
|
"step": 2835
|
|
},
|
|
{
|
|
"entropy": 5.878792953491211,
|
|
"epoch": 0.31897568371988544,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004995156063605475,
|
|
"loss": 5.7812,
|
|
"mean_token_accuracy": 0.15886088460683823,
|
|
"num_tokens": 6338083.0,
|
|
"step": 2840
|
|
},
|
|
{
|
|
"entropy": 5.884696388244629,
|
|
"epoch": 0.319537260627843,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004995129697260922,
|
|
"loss": 5.7806,
|
|
"mean_token_accuracy": 0.16254436522722243,
|
|
"num_tokens": 6349058.0,
|
|
"step": 2845
|
|
},
|
|
{
|
|
"entropy": 5.763200044631958,
|
|
"epoch": 0.32009883753580054,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004995103259430569,
|
|
"loss": 5.7963,
|
|
"mean_token_accuracy": 0.16049613952636718,
|
|
"num_tokens": 6359655.0,
|
|
"step": 2850
|
|
},
|
|
{
|
|
"entropy": 5.859290027618409,
|
|
"epoch": 0.3206604144437581,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004995076750115258,
|
|
"loss": 5.9237,
|
|
"mean_token_accuracy": 0.15698505491018294,
|
|
"num_tokens": 6372088.0,
|
|
"step": 2855
|
|
},
|
|
{
|
|
"entropy": 5.821562719345093,
|
|
"epoch": 0.32122199135171564,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004995050169315832,
|
|
"loss": 5.8296,
|
|
"mean_token_accuracy": 0.16010505557060242,
|
|
"num_tokens": 6382946.0,
|
|
"step": 2860
|
|
},
|
|
{
|
|
"entropy": 5.839111375808716,
|
|
"epoch": 0.32178356825967314,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004995023517033138,
|
|
"loss": 5.8192,
|
|
"mean_token_accuracy": 0.15969384908676149,
|
|
"num_tokens": 6392591.0,
|
|
"step": 2865
|
|
},
|
|
{
|
|
"entropy": 5.756126356124878,
|
|
"epoch": 0.3223451451676307,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004994996793268024,
|
|
"loss": 5.7604,
|
|
"mean_token_accuracy": 0.16648190021514891,
|
|
"num_tokens": 6403159.0,
|
|
"step": 2870
|
|
},
|
|
{
|
|
"entropy": 5.839804649353027,
|
|
"epoch": 0.32290672207558824,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004994969998021342,
|
|
"loss": 5.7795,
|
|
"mean_token_accuracy": 0.1644168198108673,
|
|
"num_tokens": 6414232.0,
|
|
"step": 2875
|
|
},
|
|
{
|
|
"entropy": 5.806992721557617,
|
|
"epoch": 0.3234682989835458,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004994943131293944,
|
|
"loss": 5.7638,
|
|
"mean_token_accuracy": 0.17432548552751542,
|
|
"num_tokens": 6425762.0,
|
|
"step": 2880
|
|
},
|
|
{
|
|
"entropy": 5.756858587265015,
|
|
"epoch": 0.32402987589150334,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004994916193086687,
|
|
"loss": 5.8069,
|
|
"mean_token_accuracy": 0.15830935537815094,
|
|
"num_tokens": 6439077.0,
|
|
"step": 2885
|
|
},
|
|
{
|
|
"entropy": 5.886305570602417,
|
|
"epoch": 0.3245914527994609,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004994889183400428,
|
|
"loss": 5.8773,
|
|
"mean_token_accuracy": 0.15929146558046342,
|
|
"num_tokens": 6450425.0,
|
|
"step": 2890
|
|
},
|
|
{
|
|
"entropy": 5.817720079421997,
|
|
"epoch": 0.32515302970741844,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004994862102236025,
|
|
"loss": 5.8412,
|
|
"mean_token_accuracy": 0.16064791902899742,
|
|
"num_tokens": 6461347.0,
|
|
"step": 2895
|
|
},
|
|
{
|
|
"entropy": 5.844183015823364,
|
|
"epoch": 0.325714606615376,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004994834949594342,
|
|
"loss": 5.8254,
|
|
"mean_token_accuracy": 0.16305376589298248,
|
|
"num_tokens": 6472428.0,
|
|
"step": 2900
|
|
},
|
|
{
|
|
"entropy": 5.790859222412109,
|
|
"epoch": 0.32627618352333354,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004994807725476246,
|
|
"loss": 5.7773,
|
|
"mean_token_accuracy": 0.17451646625995637,
|
|
"num_tokens": 6483393.0,
|
|
"step": 2905
|
|
},
|
|
{
|
|
"entropy": 5.800299119949341,
|
|
"epoch": 0.3268377604312911,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004994780429882599,
|
|
"loss": 5.7707,
|
|
"mean_token_accuracy": 0.16646299362182618,
|
|
"num_tokens": 6493520.0,
|
|
"step": 2910
|
|
},
|
|
{
|
|
"entropy": 5.733630228042602,
|
|
"epoch": 0.3273993373392486,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004994753062814274,
|
|
"loss": 5.7145,
|
|
"mean_token_accuracy": 0.1693594589829445,
|
|
"num_tokens": 6505282.0,
|
|
"step": 2915
|
|
},
|
|
{
|
|
"entropy": 5.871979188919068,
|
|
"epoch": 0.32796091424720614,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004994725624272139,
|
|
"loss": 5.8873,
|
|
"mean_token_accuracy": 0.16457537859678267,
|
|
"num_tokens": 6516808.0,
|
|
"step": 2920
|
|
},
|
|
{
|
|
"entropy": 5.8417102813720705,
|
|
"epoch": 0.3285224911551637,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004994698114257071,
|
|
"loss": 5.8478,
|
|
"mean_token_accuracy": 0.15840103775262832,
|
|
"num_tokens": 6529184.0,
|
|
"step": 2925
|
|
},
|
|
{
|
|
"entropy": 5.779627275466919,
|
|
"epoch": 0.32908406806312124,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004994670532769944,
|
|
"loss": 5.6786,
|
|
"mean_token_accuracy": 0.17033708542585374,
|
|
"num_tokens": 6539909.0,
|
|
"step": 2930
|
|
},
|
|
{
|
|
"entropy": 5.757491588592529,
|
|
"epoch": 0.3296456449710788,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004994642879811637,
|
|
"loss": 5.7469,
|
|
"mean_token_accuracy": 0.16941402852535248,
|
|
"num_tokens": 6550870.0,
|
|
"step": 2935
|
|
},
|
|
{
|
|
"entropy": 5.731397819519043,
|
|
"epoch": 0.33020722187903634,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000499461515538303,
|
|
"loss": 5.7978,
|
|
"mean_token_accuracy": 0.16825173050165176,
|
|
"num_tokens": 6561784.0,
|
|
"step": 2940
|
|
},
|
|
{
|
|
"entropy": 5.695051193237305,
|
|
"epoch": 0.3307687987869939,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004994587359485006,
|
|
"loss": 5.7558,
|
|
"mean_token_accuracy": 0.16522381603717803,
|
|
"num_tokens": 6573422.0,
|
|
"step": 2945
|
|
},
|
|
{
|
|
"entropy": 5.857944059371948,
|
|
"epoch": 0.33133037569495144,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000499455949211845,
|
|
"loss": 5.8264,
|
|
"mean_token_accuracy": 0.17036428451538085,
|
|
"num_tokens": 6584565.0,
|
|
"step": 2950
|
|
},
|
|
{
|
|
"entropy": 5.805426692962646,
|
|
"epoch": 0.331891952602909,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004994531553284248,
|
|
"loss": 5.7163,
|
|
"mean_token_accuracy": 0.16582873910665513,
|
|
"num_tokens": 6594238.0,
|
|
"step": 2955
|
|
},
|
|
{
|
|
"entropy": 5.6973024845123295,
|
|
"epoch": 0.3324535295108665,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004994503542983293,
|
|
"loss": 5.8091,
|
|
"mean_token_accuracy": 0.16427911669015885,
|
|
"num_tokens": 6606309.0,
|
|
"step": 2960
|
|
},
|
|
{
|
|
"entropy": 5.958718585968017,
|
|
"epoch": 0.33301510641882404,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004994475461216472,
|
|
"loss": 5.8964,
|
|
"mean_token_accuracy": 0.15852140635252,
|
|
"num_tokens": 6617916.0,
|
|
"step": 2965
|
|
},
|
|
{
|
|
"entropy": 5.791497230529785,
|
|
"epoch": 0.3335766833267816,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004994447307984684,
|
|
"loss": 5.7402,
|
|
"mean_token_accuracy": 0.16254918575286864,
|
|
"num_tokens": 6627951.0,
|
|
"step": 2970
|
|
},
|
|
{
|
|
"entropy": 5.758692979812622,
|
|
"epoch": 0.33413826023473914,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004994419083288823,
|
|
"loss": 5.8127,
|
|
"mean_token_accuracy": 0.1611504301428795,
|
|
"num_tokens": 6639285.0,
|
|
"step": 2975
|
|
},
|
|
{
|
|
"entropy": 5.775280380249024,
|
|
"epoch": 0.3346998371426967,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004994390787129787,
|
|
"loss": 5.6681,
|
|
"mean_token_accuracy": 0.17186915576457978,
|
|
"num_tokens": 6649973.0,
|
|
"step": 2980
|
|
},
|
|
{
|
|
"entropy": 5.65654149055481,
|
|
"epoch": 0.33526141405065424,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004994362419508478,
|
|
"loss": 5.6986,
|
|
"mean_token_accuracy": 0.16761759668588638,
|
|
"num_tokens": 6660625.0,
|
|
"step": 2985
|
|
},
|
|
{
|
|
"entropy": 5.793176507949829,
|
|
"epoch": 0.3358229909586118,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00049943339804258,
|
|
"loss": 5.7808,
|
|
"mean_token_accuracy": 0.16183299124240874,
|
|
"num_tokens": 6673191.0,
|
|
"step": 2990
|
|
},
|
|
{
|
|
"entropy": 5.859116125106811,
|
|
"epoch": 0.33638456786656934,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004994305469882657,
|
|
"loss": 5.7747,
|
|
"mean_token_accuracy": 0.16482254564762117,
|
|
"num_tokens": 6683993.0,
|
|
"step": 2995
|
|
},
|
|
{
|
|
"entropy": 5.732059669494629,
|
|
"epoch": 0.3369461447745269,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004994276887879957,
|
|
"loss": 5.8124,
|
|
"mean_token_accuracy": 0.16300738751888275,
|
|
"num_tokens": 6694881.0,
|
|
"step": 3000
|
|
},
|
|
{
|
|
"epoch": 0.3369461447745269,
|
|
"eval_entropy": 5.692985942875998,
|
|
"eval_loss": 5.818831920623779,
|
|
"eval_mean_token_accuracy": 0.16977359401578598,
|
|
"eval_num_tokens": 6694881.0,
|
|
"eval_runtime": 24.0447,
|
|
"eval_samples_per_second": 1289.804,
|
|
"eval_steps_per_second": 161.241,
|
|
"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
|
|
}
|