75461c4f87
Model: fpadovani/ind-latn-10mb-after-ppt-Dp-100mb-ckpt500_seed10 Source: Original Platform
6046 lines
164 KiB
JSON
6046 lines
164 KiB
JSON
{
|
|
"best_global_step": null,
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 0.2334176230305388,
|
|
"eval_steps": 3000,
|
|
"global_step": 3000,
|
|
"is_hyper_param_search": false,
|
|
"is_local_process_zero": true,
|
|
"is_world_process_zero": true,
|
|
"log_history": [
|
|
{
|
|
"entropy": 7.525209426879883,
|
|
"epoch": 0.00038902937171756465,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 2e-06,
|
|
"loss": 7.1164,
|
|
"mean_token_accuracy": 0.09126382395625114,
|
|
"num_tokens": 8095.0,
|
|
"step": 5
|
|
},
|
|
{
|
|
"entropy": 7.524957656860352,
|
|
"epoch": 0.0007780587434351293,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 4.5e-06,
|
|
"loss": 7.1341,
|
|
"mean_token_accuracy": 0.09478832259774209,
|
|
"num_tokens": 17329.0,
|
|
"step": 10
|
|
},
|
|
{
|
|
"entropy": 7.446990966796875,
|
|
"epoch": 0.001167088115152694,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 7e-06,
|
|
"loss": 6.9396,
|
|
"mean_token_accuracy": 0.09858316257596016,
|
|
"num_tokens": 25729.0,
|
|
"step": 15
|
|
},
|
|
{
|
|
"entropy": 7.479873752593994,
|
|
"epoch": 0.0015561174868702586,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 9.5e-06,
|
|
"loss": 7.0656,
|
|
"mean_token_accuracy": 0.10022840201854706,
|
|
"num_tokens": 33980.0,
|
|
"step": 20
|
|
},
|
|
{
|
|
"entropy": 7.4935675144195555,
|
|
"epoch": 0.0019451468585878235,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 1.2e-05,
|
|
"loss": 6.9001,
|
|
"mean_token_accuracy": 0.10436431169509888,
|
|
"num_tokens": 41675.0,
|
|
"step": 25
|
|
},
|
|
{
|
|
"entropy": 7.4462706565856935,
|
|
"epoch": 0.002334176230305388,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 1.4500000000000002e-05,
|
|
"loss": 6.9849,
|
|
"mean_token_accuracy": 0.09949584901332856,
|
|
"num_tokens": 50277.0,
|
|
"step": 30
|
|
},
|
|
{
|
|
"entropy": 7.490463447570801,
|
|
"epoch": 0.0027232056020229526,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 1.7000000000000003e-05,
|
|
"loss": 7.0679,
|
|
"mean_token_accuracy": 0.09498238340020179,
|
|
"num_tokens": 58790.0,
|
|
"step": 35
|
|
},
|
|
{
|
|
"entropy": 7.469117593765259,
|
|
"epoch": 0.0031122349737405172,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 1.95e-05,
|
|
"loss": 7.1151,
|
|
"mean_token_accuracy": 0.09345170259475707,
|
|
"num_tokens": 67247.0,
|
|
"step": 40
|
|
},
|
|
{
|
|
"entropy": 7.437713384628296,
|
|
"epoch": 0.003501264345458082,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 2.2e-05,
|
|
"loss": 6.9327,
|
|
"mean_token_accuracy": 0.09667690098285675,
|
|
"num_tokens": 75174.0,
|
|
"step": 45
|
|
},
|
|
{
|
|
"entropy": 7.389952373504639,
|
|
"epoch": 0.003890293717175647,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 2.4500000000000003e-05,
|
|
"loss": 6.9055,
|
|
"mean_token_accuracy": 0.10531265288591385,
|
|
"num_tokens": 83203.0,
|
|
"step": 50
|
|
},
|
|
{
|
|
"entropy": 7.395076322555542,
|
|
"epoch": 0.004279323088893211,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 2.7e-05,
|
|
"loss": 6.9499,
|
|
"mean_token_accuracy": 0.10203081965446473,
|
|
"num_tokens": 91798.0,
|
|
"step": 55
|
|
},
|
|
{
|
|
"entropy": 7.40048041343689,
|
|
"epoch": 0.004668352460610776,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 2.95e-05,
|
|
"loss": 6.9907,
|
|
"mean_token_accuracy": 0.09655389487743378,
|
|
"num_tokens": 100869.0,
|
|
"step": 60
|
|
},
|
|
{
|
|
"entropy": 7.454555511474609,
|
|
"epoch": 0.0050573818323283405,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 3.2e-05,
|
|
"loss": 6.9875,
|
|
"mean_token_accuracy": 0.09880984500050545,
|
|
"num_tokens": 109697.0,
|
|
"step": 65
|
|
},
|
|
{
|
|
"entropy": 7.498321151733398,
|
|
"epoch": 0.005446411204045905,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 3.4500000000000005e-05,
|
|
"loss": 7.1231,
|
|
"mean_token_accuracy": 0.09559949561953544,
|
|
"num_tokens": 118656.0,
|
|
"step": 70
|
|
},
|
|
{
|
|
"entropy": 7.496587228775025,
|
|
"epoch": 0.00583544057576347,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 3.7e-05,
|
|
"loss": 7.1172,
|
|
"mean_token_accuracy": 0.09125430211424827,
|
|
"num_tokens": 127748.0,
|
|
"step": 75
|
|
},
|
|
{
|
|
"entropy": 7.504852151870727,
|
|
"epoch": 0.0062244699474810344,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 3.95e-05,
|
|
"loss": 7.0387,
|
|
"mean_token_accuracy": 0.1014796257019043,
|
|
"num_tokens": 136621.0,
|
|
"step": 80
|
|
},
|
|
{
|
|
"entropy": 7.48614993095398,
|
|
"epoch": 0.006613499319198599,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 4.2000000000000004e-05,
|
|
"loss": 6.9412,
|
|
"mean_token_accuracy": 0.102222141623497,
|
|
"num_tokens": 145793.0,
|
|
"step": 85
|
|
},
|
|
{
|
|
"entropy": 7.3585365295410154,
|
|
"epoch": 0.007002528690916164,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 4.45e-05,
|
|
"loss": 6.8998,
|
|
"mean_token_accuracy": 0.09987122416496277,
|
|
"num_tokens": 154466.0,
|
|
"step": 90
|
|
},
|
|
{
|
|
"entropy": 7.381277418136596,
|
|
"epoch": 0.007391558062633729,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 4.7000000000000004e-05,
|
|
"loss": 7.0817,
|
|
"mean_token_accuracy": 0.09664711579680443,
|
|
"num_tokens": 163297.0,
|
|
"step": 95
|
|
},
|
|
{
|
|
"entropy": 7.4567954540252686,
|
|
"epoch": 0.007780587434351294,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 4.9500000000000004e-05,
|
|
"loss": 6.9582,
|
|
"mean_token_accuracy": 0.0995919868350029,
|
|
"num_tokens": 171747.0,
|
|
"step": 100
|
|
},
|
|
{
|
|
"entropy": 7.461597013473511,
|
|
"epoch": 0.008169616806068859,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 5.2e-05,
|
|
"loss": 6.9737,
|
|
"mean_token_accuracy": 0.09625533521175385,
|
|
"num_tokens": 180499.0,
|
|
"step": 105
|
|
},
|
|
{
|
|
"entropy": 7.4339855194091795,
|
|
"epoch": 0.008558646177786422,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 5.45e-05,
|
|
"loss": 6.9069,
|
|
"mean_token_accuracy": 0.10029028877615928,
|
|
"num_tokens": 189227.0,
|
|
"step": 110
|
|
},
|
|
{
|
|
"entropy": 7.355867671966553,
|
|
"epoch": 0.008947675549503988,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 5.7e-05,
|
|
"loss": 6.986,
|
|
"mean_token_accuracy": 0.10084915980696678,
|
|
"num_tokens": 198388.0,
|
|
"step": 115
|
|
},
|
|
{
|
|
"entropy": 7.4226056098937985,
|
|
"epoch": 0.009336704921221552,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 5.9499999999999996e-05,
|
|
"loss": 6.9883,
|
|
"mean_token_accuracy": 0.10193781480193138,
|
|
"num_tokens": 206854.0,
|
|
"step": 120
|
|
},
|
|
{
|
|
"entropy": 7.44698486328125,
|
|
"epoch": 0.009725734292939117,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 6.2e-05,
|
|
"loss": 6.9597,
|
|
"mean_token_accuracy": 0.10039241313934326,
|
|
"num_tokens": 215506.0,
|
|
"step": 125
|
|
},
|
|
{
|
|
"entropy": 7.457604932785034,
|
|
"epoch": 0.010114763664656681,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 6.450000000000001e-05,
|
|
"loss": 6.9474,
|
|
"mean_token_accuracy": 0.09563101530075073,
|
|
"num_tokens": 223717.0,
|
|
"step": 130
|
|
},
|
|
{
|
|
"entropy": 7.4058609962463375,
|
|
"epoch": 0.010503793036374246,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 6.7e-05,
|
|
"loss": 6.9154,
|
|
"mean_token_accuracy": 0.10078920200467109,
|
|
"num_tokens": 232480.0,
|
|
"step": 135
|
|
},
|
|
{
|
|
"entropy": 7.396328163146973,
|
|
"epoch": 0.01089282240809181,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 6.950000000000001e-05,
|
|
"loss": 6.9653,
|
|
"mean_token_accuracy": 0.10731882452964783,
|
|
"num_tokens": 241350.0,
|
|
"step": 140
|
|
},
|
|
{
|
|
"entropy": 7.449981260299682,
|
|
"epoch": 0.011281851779809376,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 7.2e-05,
|
|
"loss": 6.9697,
|
|
"mean_token_accuracy": 0.10272065401077271,
|
|
"num_tokens": 250610.0,
|
|
"step": 145
|
|
},
|
|
{
|
|
"entropy": 7.4221306324005125,
|
|
"epoch": 0.01167088115152694,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 7.45e-05,
|
|
"loss": 6.9118,
|
|
"mean_token_accuracy": 0.10345016792416573,
|
|
"num_tokens": 259672.0,
|
|
"step": 150
|
|
},
|
|
{
|
|
"entropy": 7.369914913177491,
|
|
"epoch": 0.012059910523244505,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 7.7e-05,
|
|
"loss": 6.9904,
|
|
"mean_token_accuracy": 0.09594599083065987,
|
|
"num_tokens": 267826.0,
|
|
"step": 155
|
|
},
|
|
{
|
|
"entropy": 7.477785062789917,
|
|
"epoch": 0.012448939894962069,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 7.950000000000001e-05,
|
|
"loss": 6.995,
|
|
"mean_token_accuracy": 0.09624672085046768,
|
|
"num_tokens": 277324.0,
|
|
"step": 160
|
|
},
|
|
{
|
|
"entropy": 7.4215576171875,
|
|
"epoch": 0.012837969266679634,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 8.2e-05,
|
|
"loss": 6.8296,
|
|
"mean_token_accuracy": 0.10975822508335113,
|
|
"num_tokens": 285482.0,
|
|
"step": 165
|
|
},
|
|
{
|
|
"entropy": 7.35403299331665,
|
|
"epoch": 0.013226998638397198,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 8.450000000000001e-05,
|
|
"loss": 6.893,
|
|
"mean_token_accuracy": 0.10332747399806977,
|
|
"num_tokens": 293684.0,
|
|
"step": 170
|
|
},
|
|
{
|
|
"entropy": 7.344775819778443,
|
|
"epoch": 0.013616028010114764,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 8.7e-05,
|
|
"loss": 6.8705,
|
|
"mean_token_accuracy": 0.10466427579522133,
|
|
"num_tokens": 302605.0,
|
|
"step": 175
|
|
},
|
|
{
|
|
"entropy": 7.469928503036499,
|
|
"epoch": 0.014005057381832327,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 8.95e-05,
|
|
"loss": 6.9479,
|
|
"mean_token_accuracy": 0.10224307030439377,
|
|
"num_tokens": 310849.0,
|
|
"step": 180
|
|
},
|
|
{
|
|
"entropy": 7.377802467346191,
|
|
"epoch": 0.014394086753549893,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 9.2e-05,
|
|
"loss": 6.9647,
|
|
"mean_token_accuracy": 0.09813596233725548,
|
|
"num_tokens": 319752.0,
|
|
"step": 185
|
|
},
|
|
{
|
|
"entropy": 7.5093926906585695,
|
|
"epoch": 0.014783116125267459,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 9.45e-05,
|
|
"loss": 7.0233,
|
|
"mean_token_accuracy": 0.09324661493301392,
|
|
"num_tokens": 328009.0,
|
|
"step": 190
|
|
},
|
|
{
|
|
"entropy": 7.352363014221192,
|
|
"epoch": 0.015172145496985022,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 9.7e-05,
|
|
"loss": 6.909,
|
|
"mean_token_accuracy": 0.10263535231351853,
|
|
"num_tokens": 337414.0,
|
|
"step": 195
|
|
},
|
|
{
|
|
"entropy": 7.411336231231689,
|
|
"epoch": 0.015561174868702588,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 9.95e-05,
|
|
"loss": 6.9275,
|
|
"mean_token_accuracy": 0.10379069447517394,
|
|
"num_tokens": 345419.0,
|
|
"step": 200
|
|
},
|
|
{
|
|
"entropy": 7.4287652492523195,
|
|
"epoch": 0.01595020424042015,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000102,
|
|
"loss": 6.9079,
|
|
"mean_token_accuracy": 0.10015243589878083,
|
|
"num_tokens": 353435.0,
|
|
"step": 205
|
|
},
|
|
{
|
|
"entropy": 7.346658992767334,
|
|
"epoch": 0.016339233612137717,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00010449999999999999,
|
|
"loss": 6.9221,
|
|
"mean_token_accuracy": 0.1055522657930851,
|
|
"num_tokens": 361840.0,
|
|
"step": 210
|
|
},
|
|
{
|
|
"entropy": 7.52528715133667,
|
|
"epoch": 0.016728262983855283,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000107,
|
|
"loss": 7.0276,
|
|
"mean_token_accuracy": 0.09967184960842132,
|
|
"num_tokens": 370873.0,
|
|
"step": 215
|
|
},
|
|
{
|
|
"entropy": 7.3679437160491945,
|
|
"epoch": 0.017117292355572845,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0001095,
|
|
"loss": 6.9343,
|
|
"mean_token_accuracy": 0.09932355582714081,
|
|
"num_tokens": 379558.0,
|
|
"step": 220
|
|
},
|
|
{
|
|
"entropy": 7.469588994979858,
|
|
"epoch": 0.01750632172729041,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000112,
|
|
"loss": 6.9429,
|
|
"mean_token_accuracy": 0.10046415254473687,
|
|
"num_tokens": 387870.0,
|
|
"step": 225
|
|
},
|
|
{
|
|
"entropy": 7.386438465118408,
|
|
"epoch": 0.017895351099007976,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0001145,
|
|
"loss": 7.0274,
|
|
"mean_token_accuracy": 0.10568641722202302,
|
|
"num_tokens": 396442.0,
|
|
"step": 230
|
|
},
|
|
{
|
|
"entropy": 7.447541284561157,
|
|
"epoch": 0.01828438047072554,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00011700000000000001,
|
|
"loss": 6.9675,
|
|
"mean_token_accuracy": 0.10170508250594139,
|
|
"num_tokens": 404764.0,
|
|
"step": 235
|
|
},
|
|
{
|
|
"entropy": 7.413917064666748,
|
|
"epoch": 0.018673409842443103,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00011949999999999999,
|
|
"loss": 6.9034,
|
|
"mean_token_accuracy": 0.10267666056752205,
|
|
"num_tokens": 413355.0,
|
|
"step": 240
|
|
},
|
|
{
|
|
"entropy": 7.331215286254883,
|
|
"epoch": 0.01906243921416067,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000122,
|
|
"loss": 6.8107,
|
|
"mean_token_accuracy": 0.10804717987775803,
|
|
"num_tokens": 421868.0,
|
|
"step": 245
|
|
},
|
|
{
|
|
"entropy": 7.342196226119995,
|
|
"epoch": 0.019451468585878234,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0001245,
|
|
"loss": 6.8674,
|
|
"mean_token_accuracy": 0.10438908636569977,
|
|
"num_tokens": 431106.0,
|
|
"step": 250
|
|
},
|
|
{
|
|
"entropy": 7.457882690429687,
|
|
"epoch": 0.0198404979575958,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.000127,
|
|
"loss": 7.0068,
|
|
"mean_token_accuracy": 0.09497510865330697,
|
|
"num_tokens": 439459.0,
|
|
"step": 255
|
|
},
|
|
{
|
|
"entropy": 7.371812105178833,
|
|
"epoch": 0.020229527329313362,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0001295,
|
|
"loss": 6.8334,
|
|
"mean_token_accuracy": 0.10420059189200401,
|
|
"num_tokens": 447943.0,
|
|
"step": 260
|
|
},
|
|
{
|
|
"entropy": 7.375357580184937,
|
|
"epoch": 0.020618556701030927,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000132,
|
|
"loss": 6.9826,
|
|
"mean_token_accuracy": 0.09710169360041618,
|
|
"num_tokens": 456691.0,
|
|
"step": 265
|
|
},
|
|
{
|
|
"entropy": 7.364774465560913,
|
|
"epoch": 0.021007586072748493,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00013450000000000002,
|
|
"loss": 6.8583,
|
|
"mean_token_accuracy": 0.10362368077039719,
|
|
"num_tokens": 466388.0,
|
|
"step": 270
|
|
},
|
|
{
|
|
"entropy": 7.392491149902344,
|
|
"epoch": 0.02139661544446606,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00013700000000000002,
|
|
"loss": 6.9669,
|
|
"mean_token_accuracy": 0.10099864155054092,
|
|
"num_tokens": 474544.0,
|
|
"step": 275
|
|
},
|
|
{
|
|
"entropy": 7.414118957519531,
|
|
"epoch": 0.02178564481618362,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0001395,
|
|
"loss": 6.9797,
|
|
"mean_token_accuracy": 0.10356927365064621,
|
|
"num_tokens": 483561.0,
|
|
"step": 280
|
|
},
|
|
{
|
|
"entropy": 7.296314764022827,
|
|
"epoch": 0.022174674187901186,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00014199999999999998,
|
|
"loss": 6.8018,
|
|
"mean_token_accuracy": 0.10049450471997261,
|
|
"num_tokens": 492036.0,
|
|
"step": 285
|
|
},
|
|
{
|
|
"entropy": 7.479441213607788,
|
|
"epoch": 0.02256370355961875,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0001445,
|
|
"loss": 6.9413,
|
|
"mean_token_accuracy": 0.10272752419114113,
|
|
"num_tokens": 500978.0,
|
|
"step": 290
|
|
},
|
|
{
|
|
"entropy": 7.315587186813355,
|
|
"epoch": 0.022952732931336317,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000147,
|
|
"loss": 6.9848,
|
|
"mean_token_accuracy": 0.10035317316651345,
|
|
"num_tokens": 509719.0,
|
|
"step": 295
|
|
},
|
|
{
|
|
"entropy": 7.50186858177185,
|
|
"epoch": 0.02334176230305388,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0001495,
|
|
"loss": 6.8866,
|
|
"mean_token_accuracy": 0.1016937792301178,
|
|
"num_tokens": 518422.0,
|
|
"step": 300
|
|
},
|
|
{
|
|
"entropy": 7.289468431472779,
|
|
"epoch": 0.023730791674771445,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.000152,
|
|
"loss": 6.9335,
|
|
"mean_token_accuracy": 0.09595205262303352,
|
|
"num_tokens": 527172.0,
|
|
"step": 305
|
|
},
|
|
{
|
|
"entropy": 7.423691844940185,
|
|
"epoch": 0.02411982104648901,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00015450000000000001,
|
|
"loss": 6.8618,
|
|
"mean_token_accuracy": 0.10495315194129944,
|
|
"num_tokens": 536070.0,
|
|
"step": 310
|
|
},
|
|
{
|
|
"entropy": 7.324627017974853,
|
|
"epoch": 0.024508850418206576,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000157,
|
|
"loss": 6.8709,
|
|
"mean_token_accuracy": 0.10348411202430725,
|
|
"num_tokens": 544556.0,
|
|
"step": 315
|
|
},
|
|
{
|
|
"entropy": 7.411664628982544,
|
|
"epoch": 0.024897879789924138,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0001595,
|
|
"loss": 6.8337,
|
|
"mean_token_accuracy": 0.10683412104845047,
|
|
"num_tokens": 553122.0,
|
|
"step": 320
|
|
},
|
|
{
|
|
"entropy": 7.352542924880981,
|
|
"epoch": 0.025286909161641703,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000162,
|
|
"loss": 6.9213,
|
|
"mean_token_accuracy": 0.09781907498836517,
|
|
"num_tokens": 562265.0,
|
|
"step": 325
|
|
},
|
|
{
|
|
"entropy": 7.3105535984039305,
|
|
"epoch": 0.02567593853335927,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00016450000000000001,
|
|
"loss": 6.8794,
|
|
"mean_token_accuracy": 0.1058124616742134,
|
|
"num_tokens": 570938.0,
|
|
"step": 330
|
|
},
|
|
{
|
|
"entropy": 7.363333702087402,
|
|
"epoch": 0.026064967905076834,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00016700000000000002,
|
|
"loss": 6.8159,
|
|
"mean_token_accuracy": 0.10493286699056625,
|
|
"num_tokens": 578568.0,
|
|
"step": 335
|
|
},
|
|
{
|
|
"entropy": 7.4085417747497555,
|
|
"epoch": 0.026453997276794396,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00016950000000000003,
|
|
"loss": 6.8823,
|
|
"mean_token_accuracy": 0.10770140811800957,
|
|
"num_tokens": 587013.0,
|
|
"step": 340
|
|
},
|
|
{
|
|
"entropy": 7.380347776412964,
|
|
"epoch": 0.026843026648511962,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00017199999999999998,
|
|
"loss": 6.9395,
|
|
"mean_token_accuracy": 0.10302414670586586,
|
|
"num_tokens": 595354.0,
|
|
"step": 345
|
|
},
|
|
{
|
|
"entropy": 7.401273250579834,
|
|
"epoch": 0.027232056020229527,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00017449999999999999,
|
|
"loss": 6.9143,
|
|
"mean_token_accuracy": 0.09726170152425766,
|
|
"num_tokens": 603971.0,
|
|
"step": 350
|
|
},
|
|
{
|
|
"entropy": 7.264584875106811,
|
|
"epoch": 0.027621085391947093,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000177,
|
|
"loss": 6.8246,
|
|
"mean_token_accuracy": 0.10611001029610634,
|
|
"num_tokens": 612097.0,
|
|
"step": 355
|
|
},
|
|
{
|
|
"entropy": 7.374355459213257,
|
|
"epoch": 0.028010114763664655,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0001795,
|
|
"loss": 6.8914,
|
|
"mean_token_accuracy": 0.1076267570257187,
|
|
"num_tokens": 621445.0,
|
|
"step": 360
|
|
},
|
|
{
|
|
"entropy": 7.367084646224976,
|
|
"epoch": 0.02839914413538222,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000182,
|
|
"loss": 6.9642,
|
|
"mean_token_accuracy": 0.10026197507977486,
|
|
"num_tokens": 630041.0,
|
|
"step": 365
|
|
},
|
|
{
|
|
"entropy": 7.286877632141113,
|
|
"epoch": 0.028788173507099786,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0001845,
|
|
"loss": 6.793,
|
|
"mean_token_accuracy": 0.10361501201987267,
|
|
"num_tokens": 638317.0,
|
|
"step": 370
|
|
},
|
|
{
|
|
"entropy": 7.358971881866455,
|
|
"epoch": 0.02917720287881735,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000187,
|
|
"loss": 6.9153,
|
|
"mean_token_accuracy": 0.10330267027020454,
|
|
"num_tokens": 647297.0,
|
|
"step": 375
|
|
},
|
|
{
|
|
"entropy": 7.467724800109863,
|
|
"epoch": 0.029566232250534917,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0001895,
|
|
"loss": 6.9596,
|
|
"mean_token_accuracy": 0.10418846607208251,
|
|
"num_tokens": 655309.0,
|
|
"step": 380
|
|
},
|
|
{
|
|
"entropy": 7.318552494049072,
|
|
"epoch": 0.02995526162225248,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000192,
|
|
"loss": 6.8423,
|
|
"mean_token_accuracy": 0.09740504622459412,
|
|
"num_tokens": 663879.0,
|
|
"step": 385
|
|
},
|
|
{
|
|
"entropy": 7.267914342880249,
|
|
"epoch": 0.030344290993970045,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0001945,
|
|
"loss": 6.7288,
|
|
"mean_token_accuracy": 0.10926953107118606,
|
|
"num_tokens": 672913.0,
|
|
"step": 390
|
|
},
|
|
{
|
|
"entropy": 7.249853038787842,
|
|
"epoch": 0.03073332036568761,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00019700000000000002,
|
|
"loss": 6.8682,
|
|
"mean_token_accuracy": 0.10577411428093911,
|
|
"num_tokens": 682282.0,
|
|
"step": 395
|
|
},
|
|
{
|
|
"entropy": 7.347216081619263,
|
|
"epoch": 0.031122349737405176,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00019950000000000002,
|
|
"loss": 6.8777,
|
|
"mean_token_accuracy": 0.10061730667948723,
|
|
"num_tokens": 691432.0,
|
|
"step": 400
|
|
},
|
|
{
|
|
"entropy": 7.2628637790679935,
|
|
"epoch": 0.03151137910912274,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.000202,
|
|
"loss": 6.8792,
|
|
"mean_token_accuracy": 0.10118450745940208,
|
|
"num_tokens": 700639.0,
|
|
"step": 405
|
|
},
|
|
{
|
|
"entropy": 7.387156391143799,
|
|
"epoch": 0.0319004084808403,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00020449999999999998,
|
|
"loss": 6.946,
|
|
"mean_token_accuracy": 0.0988673098385334,
|
|
"num_tokens": 709200.0,
|
|
"step": 410
|
|
},
|
|
{
|
|
"entropy": 7.180784082412719,
|
|
"epoch": 0.03228943785255787,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000207,
|
|
"loss": 6.7769,
|
|
"mean_token_accuracy": 0.10579730719327926,
|
|
"num_tokens": 717266.0,
|
|
"step": 415
|
|
},
|
|
{
|
|
"entropy": 7.3383214473724365,
|
|
"epoch": 0.032678467224275434,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0002095,
|
|
"loss": 6.7761,
|
|
"mean_token_accuracy": 0.10209827125072479,
|
|
"num_tokens": 725799.0,
|
|
"step": 420
|
|
},
|
|
{
|
|
"entropy": 7.2920979976654055,
|
|
"epoch": 0.033067496595993,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.000212,
|
|
"loss": 6.9062,
|
|
"mean_token_accuracy": 0.10427533909678459,
|
|
"num_tokens": 734375.0,
|
|
"step": 425
|
|
},
|
|
{
|
|
"entropy": 7.3845654964447025,
|
|
"epoch": 0.033456525967710565,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0002145,
|
|
"loss": 6.9307,
|
|
"mean_token_accuracy": 0.10116986557841301,
|
|
"num_tokens": 743453.0,
|
|
"step": 430
|
|
},
|
|
{
|
|
"entropy": 7.256317663192749,
|
|
"epoch": 0.033845555339428124,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00021700000000000002,
|
|
"loss": 6.7835,
|
|
"mean_token_accuracy": 0.1099538803100586,
|
|
"num_tokens": 752443.0,
|
|
"step": 435
|
|
},
|
|
{
|
|
"entropy": 7.239885091781616,
|
|
"epoch": 0.03423458471114569,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0002195,
|
|
"loss": 6.7755,
|
|
"mean_token_accuracy": 0.103090950101614,
|
|
"num_tokens": 761294.0,
|
|
"step": 440
|
|
},
|
|
{
|
|
"entropy": 7.315788888931275,
|
|
"epoch": 0.034623614082863255,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000222,
|
|
"loss": 6.7633,
|
|
"mean_token_accuracy": 0.10775340422987938,
|
|
"num_tokens": 769489.0,
|
|
"step": 445
|
|
},
|
|
{
|
|
"entropy": 7.27491250038147,
|
|
"epoch": 0.03501264345458082,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0002245,
|
|
"loss": 6.8251,
|
|
"mean_token_accuracy": 0.1056965485215187,
|
|
"num_tokens": 777836.0,
|
|
"step": 450
|
|
},
|
|
{
|
|
"entropy": 7.317339181900024,
|
|
"epoch": 0.035401672826298386,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00022700000000000002,
|
|
"loss": 6.8512,
|
|
"mean_token_accuracy": 0.09845920503139496,
|
|
"num_tokens": 786543.0,
|
|
"step": 455
|
|
},
|
|
{
|
|
"entropy": 7.298014497756958,
|
|
"epoch": 0.03579070219801595,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00022950000000000002,
|
|
"loss": 6.9104,
|
|
"mean_token_accuracy": 0.10431987568736076,
|
|
"num_tokens": 794525.0,
|
|
"step": 460
|
|
},
|
|
{
|
|
"entropy": 7.248893308639526,
|
|
"epoch": 0.03617973156973352,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00023200000000000003,
|
|
"loss": 6.8222,
|
|
"mean_token_accuracy": 0.1065070852637291,
|
|
"num_tokens": 803537.0,
|
|
"step": 465
|
|
},
|
|
{
|
|
"entropy": 7.270473957061768,
|
|
"epoch": 0.03656876094145108,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00023449999999999998,
|
|
"loss": 6.7685,
|
|
"mean_token_accuracy": 0.10664488673210144,
|
|
"num_tokens": 811706.0,
|
|
"step": 470
|
|
},
|
|
{
|
|
"entropy": 7.247415494918823,
|
|
"epoch": 0.03695779031316864,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000237,
|
|
"loss": 6.8359,
|
|
"mean_token_accuracy": 0.10338398665189744,
|
|
"num_tokens": 820182.0,
|
|
"step": 475
|
|
},
|
|
{
|
|
"entropy": 7.244891786575318,
|
|
"epoch": 0.03734681968488621,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0002395,
|
|
"loss": 6.7711,
|
|
"mean_token_accuracy": 0.10853901281952857,
|
|
"num_tokens": 829808.0,
|
|
"step": 480
|
|
},
|
|
{
|
|
"entropy": 7.287813949584961,
|
|
"epoch": 0.03773584905660377,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000242,
|
|
"loss": 6.721,
|
|
"mean_token_accuracy": 0.10383491292595863,
|
|
"num_tokens": 838838.0,
|
|
"step": 485
|
|
},
|
|
{
|
|
"entropy": 7.207957983016968,
|
|
"epoch": 0.03812487842832134,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0002445,
|
|
"loss": 6.8069,
|
|
"mean_token_accuracy": 0.1081025905907154,
|
|
"num_tokens": 847800.0,
|
|
"step": 490
|
|
},
|
|
{
|
|
"entropy": 7.361988687515259,
|
|
"epoch": 0.0385139078000389,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000247,
|
|
"loss": 6.9005,
|
|
"mean_token_accuracy": 0.10296034291386605,
|
|
"num_tokens": 856503.0,
|
|
"step": 495
|
|
},
|
|
{
|
|
"entropy": 7.193755149841309,
|
|
"epoch": 0.03890293717175647,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0002495,
|
|
"loss": 6.7864,
|
|
"mean_token_accuracy": 0.10174561962485314,
|
|
"num_tokens": 865245.0,
|
|
"step": 500
|
|
},
|
|
{
|
|
"entropy": 7.283534049987793,
|
|
"epoch": 0.039291966543474034,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000252,
|
|
"loss": 6.8082,
|
|
"mean_token_accuracy": 0.10216192156076431,
|
|
"num_tokens": 874485.0,
|
|
"step": 505
|
|
},
|
|
{
|
|
"entropy": 7.117496156692505,
|
|
"epoch": 0.0396809959151916,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0002545,
|
|
"loss": 6.6771,
|
|
"mean_token_accuracy": 0.11026940196752548,
|
|
"num_tokens": 883301.0,
|
|
"step": 510
|
|
},
|
|
{
|
|
"entropy": 7.131668567657471,
|
|
"epoch": 0.04007002528690916,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000257,
|
|
"loss": 6.7448,
|
|
"mean_token_accuracy": 0.10374188125133514,
|
|
"num_tokens": 892387.0,
|
|
"step": 515
|
|
},
|
|
{
|
|
"entropy": 7.24387755393982,
|
|
"epoch": 0.040459054658626724,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0002595,
|
|
"loss": 6.732,
|
|
"mean_token_accuracy": 0.11151306107640266,
|
|
"num_tokens": 901522.0,
|
|
"step": 520
|
|
},
|
|
{
|
|
"entropy": 7.128845930099487,
|
|
"epoch": 0.04084808403034429,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000262,
|
|
"loss": 6.6974,
|
|
"mean_token_accuracy": 0.10741285160183907,
|
|
"num_tokens": 909848.0,
|
|
"step": 525
|
|
},
|
|
{
|
|
"entropy": 7.312799263000488,
|
|
"epoch": 0.041237113402061855,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00026450000000000003,
|
|
"loss": 6.9168,
|
|
"mean_token_accuracy": 0.1004093937575817,
|
|
"num_tokens": 919079.0,
|
|
"step": 530
|
|
},
|
|
{
|
|
"entropy": 7.166108179092407,
|
|
"epoch": 0.04162614277377942,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00026700000000000004,
|
|
"loss": 6.6571,
|
|
"mean_token_accuracy": 0.1108947217464447,
|
|
"num_tokens": 927807.0,
|
|
"step": 535
|
|
},
|
|
{
|
|
"entropy": 7.130585718154907,
|
|
"epoch": 0.042015172145496986,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00026950000000000005,
|
|
"loss": 6.7716,
|
|
"mean_token_accuracy": 0.10743746683001518,
|
|
"num_tokens": 936498.0,
|
|
"step": 540
|
|
},
|
|
{
|
|
"entropy": 7.2852715969085695,
|
|
"epoch": 0.04240420151721455,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00027200000000000005,
|
|
"loss": 6.8486,
|
|
"mean_token_accuracy": 0.1115134410560131,
|
|
"num_tokens": 945436.0,
|
|
"step": 545
|
|
},
|
|
{
|
|
"entropy": 7.238163709640503,
|
|
"epoch": 0.04279323088893212,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0002745,
|
|
"loss": 6.76,
|
|
"mean_token_accuracy": 0.10598877593874931,
|
|
"num_tokens": 953990.0,
|
|
"step": 550
|
|
},
|
|
{
|
|
"entropy": 7.096475458145141,
|
|
"epoch": 0.04318226026064968,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.000277,
|
|
"loss": 6.6979,
|
|
"mean_token_accuracy": 0.10942429900169373,
|
|
"num_tokens": 962008.0,
|
|
"step": 555
|
|
},
|
|
{
|
|
"entropy": 7.238119173049927,
|
|
"epoch": 0.04357128963236724,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0002795,
|
|
"loss": 6.8697,
|
|
"mean_token_accuracy": 0.10453333854675292,
|
|
"num_tokens": 970935.0,
|
|
"step": 560
|
|
},
|
|
{
|
|
"entropy": 7.282825183868408,
|
|
"epoch": 0.04396031900408481,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00028199999999999997,
|
|
"loss": 6.8089,
|
|
"mean_token_accuracy": 0.09897146746516228,
|
|
"num_tokens": 979492.0,
|
|
"step": 565
|
|
},
|
|
{
|
|
"entropy": 7.173346710205078,
|
|
"epoch": 0.04434934837580237,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0002845,
|
|
"loss": 6.725,
|
|
"mean_token_accuracy": 0.1077153742313385,
|
|
"num_tokens": 987866.0,
|
|
"step": 570
|
|
},
|
|
{
|
|
"entropy": 7.165633726119995,
|
|
"epoch": 0.04473837774751994,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000287,
|
|
"loss": 6.7609,
|
|
"mean_token_accuracy": 0.11032681092619896,
|
|
"num_tokens": 996760.0,
|
|
"step": 575
|
|
},
|
|
{
|
|
"entropy": 7.229097557067871,
|
|
"epoch": 0.0451274071192375,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0002895,
|
|
"loss": 6.6913,
|
|
"mean_token_accuracy": 0.10864157006144523,
|
|
"num_tokens": 1005432.0,
|
|
"step": 580
|
|
},
|
|
{
|
|
"entropy": 7.137337875366211,
|
|
"epoch": 0.04551643649095507,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.000292,
|
|
"loss": 6.7743,
|
|
"mean_token_accuracy": 0.10533035397529603,
|
|
"num_tokens": 1013729.0,
|
|
"step": 585
|
|
},
|
|
{
|
|
"entropy": 7.049478149414062,
|
|
"epoch": 0.045905465862672634,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0002945,
|
|
"loss": 6.6116,
|
|
"mean_token_accuracy": 0.11751440018415452,
|
|
"num_tokens": 1022485.0,
|
|
"step": 590
|
|
},
|
|
{
|
|
"entropy": 7.1416089057922365,
|
|
"epoch": 0.0462944952343902,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.000297,
|
|
"loss": 6.6885,
|
|
"mean_token_accuracy": 0.10569961667060852,
|
|
"num_tokens": 1030523.0,
|
|
"step": 595
|
|
},
|
|
{
|
|
"entropy": 7.179096317291259,
|
|
"epoch": 0.04668352460610776,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0002995,
|
|
"loss": 6.7869,
|
|
"mean_token_accuracy": 0.10787507370114327,
|
|
"num_tokens": 1039268.0,
|
|
"step": 600
|
|
},
|
|
{
|
|
"entropy": 7.120957326889038,
|
|
"epoch": 0.047072553977825324,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000302,
|
|
"loss": 6.684,
|
|
"mean_token_accuracy": 0.10937019288539887,
|
|
"num_tokens": 1048590.0,
|
|
"step": 605
|
|
},
|
|
{
|
|
"entropy": 7.0393298149108885,
|
|
"epoch": 0.04746158334954289,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0003045,
|
|
"loss": 6.617,
|
|
"mean_token_accuracy": 0.11176003962755203,
|
|
"num_tokens": 1057232.0,
|
|
"step": 610
|
|
},
|
|
{
|
|
"entropy": 7.098176956176758,
|
|
"epoch": 0.047850612721260455,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.000307,
|
|
"loss": 6.6998,
|
|
"mean_token_accuracy": 0.1081328421831131,
|
|
"num_tokens": 1066404.0,
|
|
"step": 615
|
|
},
|
|
{
|
|
"entropy": 7.031232643127441,
|
|
"epoch": 0.04823964209297802,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0003095,
|
|
"loss": 6.7638,
|
|
"mean_token_accuracy": 0.10122817903757095,
|
|
"num_tokens": 1075093.0,
|
|
"step": 620
|
|
},
|
|
{
|
|
"entropy": 7.155955123901367,
|
|
"epoch": 0.048628671464695586,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000312,
|
|
"loss": 6.667,
|
|
"mean_token_accuracy": 0.10735566318035125,
|
|
"num_tokens": 1084454.0,
|
|
"step": 625
|
|
},
|
|
{
|
|
"entropy": 7.108900642395019,
|
|
"epoch": 0.04901770083641315,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0003145,
|
|
"loss": 6.5969,
|
|
"mean_token_accuracy": 0.10924701541662216,
|
|
"num_tokens": 1093452.0,
|
|
"step": 630
|
|
},
|
|
{
|
|
"entropy": 7.034401082992554,
|
|
"epoch": 0.04940673020813072,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.000317,
|
|
"loss": 6.6196,
|
|
"mean_token_accuracy": 0.11470122635364532,
|
|
"num_tokens": 1101814.0,
|
|
"step": 635
|
|
},
|
|
{
|
|
"entropy": 7.051713323593139,
|
|
"epoch": 0.049795759579848276,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0003195,
|
|
"loss": 6.7,
|
|
"mean_token_accuracy": 0.11058250665664673,
|
|
"num_tokens": 1110386.0,
|
|
"step": 640
|
|
},
|
|
{
|
|
"entropy": 7.14307336807251,
|
|
"epoch": 0.05018478895156584,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000322,
|
|
"loss": 6.8031,
|
|
"mean_token_accuracy": 0.10201985463500023,
|
|
"num_tokens": 1120141.0,
|
|
"step": 645
|
|
},
|
|
{
|
|
"entropy": 7.1510227680206295,
|
|
"epoch": 0.05057381832328341,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00032450000000000003,
|
|
"loss": 6.7396,
|
|
"mean_token_accuracy": 0.1102594219148159,
|
|
"num_tokens": 1129920.0,
|
|
"step": 650
|
|
},
|
|
{
|
|
"entropy": 6.983091688156128,
|
|
"epoch": 0.05096284769500097,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00032700000000000003,
|
|
"loss": 6.6196,
|
|
"mean_token_accuracy": 0.11163505613803863,
|
|
"num_tokens": 1138518.0,
|
|
"step": 655
|
|
},
|
|
{
|
|
"entropy": 7.117662715911865,
|
|
"epoch": 0.05135187706671854,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00032950000000000004,
|
|
"loss": 6.7209,
|
|
"mean_token_accuracy": 0.10830123797059059,
|
|
"num_tokens": 1147113.0,
|
|
"step": 660
|
|
},
|
|
{
|
|
"entropy": 7.052978134155273,
|
|
"epoch": 0.0517409064384361,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00033200000000000005,
|
|
"loss": 6.5612,
|
|
"mean_token_accuracy": 0.11946347504854202,
|
|
"num_tokens": 1155886.0,
|
|
"step": 665
|
|
},
|
|
{
|
|
"entropy": 7.017060613632202,
|
|
"epoch": 0.05212993581015367,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00033450000000000005,
|
|
"loss": 6.725,
|
|
"mean_token_accuracy": 0.10746086090803146,
|
|
"num_tokens": 1164200.0,
|
|
"step": 670
|
|
},
|
|
{
|
|
"entropy": 7.051968240737915,
|
|
"epoch": 0.052518965181871234,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000337,
|
|
"loss": 6.5857,
|
|
"mean_token_accuracy": 0.1125464141368866,
|
|
"num_tokens": 1172720.0,
|
|
"step": 675
|
|
},
|
|
{
|
|
"entropy": 6.996215152740478,
|
|
"epoch": 0.05290799455358879,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0003395,
|
|
"loss": 6.5468,
|
|
"mean_token_accuracy": 0.1077719546854496,
|
|
"num_tokens": 1181225.0,
|
|
"step": 680
|
|
},
|
|
{
|
|
"entropy": 7.120228815078735,
|
|
"epoch": 0.05329702392530636,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000342,
|
|
"loss": 6.7546,
|
|
"mean_token_accuracy": 0.10120292380452156,
|
|
"num_tokens": 1190070.0,
|
|
"step": 685
|
|
},
|
|
{
|
|
"entropy": 7.013375902175904,
|
|
"epoch": 0.053686053297023924,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00034449999999999997,
|
|
"loss": 6.6267,
|
|
"mean_token_accuracy": 0.11402207687497139,
|
|
"num_tokens": 1198995.0,
|
|
"step": 690
|
|
},
|
|
{
|
|
"entropy": 7.120525217056274,
|
|
"epoch": 0.05407508266874149,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000347,
|
|
"loss": 6.6744,
|
|
"mean_token_accuracy": 0.11539597958326339,
|
|
"num_tokens": 1207664.0,
|
|
"step": 695
|
|
},
|
|
{
|
|
"entropy": 7.102228593826294,
|
|
"epoch": 0.054464112040459055,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0003495,
|
|
"loss": 6.5789,
|
|
"mean_token_accuracy": 0.12240418270230294,
|
|
"num_tokens": 1216232.0,
|
|
"step": 700
|
|
},
|
|
{
|
|
"entropy": 6.950713348388672,
|
|
"epoch": 0.05485314141217662,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000352,
|
|
"loss": 6.6748,
|
|
"mean_token_accuracy": 0.11159612014889717,
|
|
"num_tokens": 1224106.0,
|
|
"step": 705
|
|
},
|
|
{
|
|
"entropy": 6.960762357711792,
|
|
"epoch": 0.055242170783894186,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0003545,
|
|
"loss": 6.5619,
|
|
"mean_token_accuracy": 0.11645937711000443,
|
|
"num_tokens": 1232514.0,
|
|
"step": 710
|
|
},
|
|
{
|
|
"entropy": 7.127431774139405,
|
|
"epoch": 0.05563120015561175,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.000357,
|
|
"loss": 6.6152,
|
|
"mean_token_accuracy": 0.11127564162015915,
|
|
"num_tokens": 1240178.0,
|
|
"step": 715
|
|
},
|
|
{
|
|
"entropy": 6.829823637008667,
|
|
"epoch": 0.05602022952732931,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0003595,
|
|
"loss": 6.5236,
|
|
"mean_token_accuracy": 0.11545735970139503,
|
|
"num_tokens": 1248635.0,
|
|
"step": 720
|
|
},
|
|
{
|
|
"entropy": 7.094886350631714,
|
|
"epoch": 0.056409258899046875,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000362,
|
|
"loss": 6.6258,
|
|
"mean_token_accuracy": 0.11595786064863205,
|
|
"num_tokens": 1256389.0,
|
|
"step": 725
|
|
},
|
|
{
|
|
"entropy": 6.9064311504364015,
|
|
"epoch": 0.05679828827076444,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0003645,
|
|
"loss": 6.5896,
|
|
"mean_token_accuracy": 0.11666487753391266,
|
|
"num_tokens": 1264035.0,
|
|
"step": 730
|
|
},
|
|
{
|
|
"entropy": 7.034950304031372,
|
|
"epoch": 0.057187317642482006,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000367,
|
|
"loss": 6.5838,
|
|
"mean_token_accuracy": 0.11167205199599266,
|
|
"num_tokens": 1272941.0,
|
|
"step": 735
|
|
},
|
|
{
|
|
"entropy": 6.862753534317017,
|
|
"epoch": 0.05757634701419957,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0003695,
|
|
"loss": 6.5714,
|
|
"mean_token_accuracy": 0.11405754834413528,
|
|
"num_tokens": 1281767.0,
|
|
"step": 740
|
|
},
|
|
{
|
|
"entropy": 7.123349332809449,
|
|
"epoch": 0.05796537638591714,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000372,
|
|
"loss": 6.6469,
|
|
"mean_token_accuracy": 0.11400221288204193,
|
|
"num_tokens": 1290049.0,
|
|
"step": 745
|
|
},
|
|
{
|
|
"entropy": 6.815326452255249,
|
|
"epoch": 0.0583544057576347,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0003745,
|
|
"loss": 6.4981,
|
|
"mean_token_accuracy": 0.12375147640705109,
|
|
"num_tokens": 1299032.0,
|
|
"step": 750
|
|
},
|
|
{
|
|
"entropy": 6.98442530632019,
|
|
"epoch": 0.05874343512935227,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000377,
|
|
"loss": 6.7388,
|
|
"mean_token_accuracy": 0.10899372920393943,
|
|
"num_tokens": 1308508.0,
|
|
"step": 755
|
|
},
|
|
{
|
|
"entropy": 7.064965343475341,
|
|
"epoch": 0.059132464501069834,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0003795,
|
|
"loss": 6.5673,
|
|
"mean_token_accuracy": 0.1138399638235569,
|
|
"num_tokens": 1317044.0,
|
|
"step": 760
|
|
},
|
|
{
|
|
"entropy": 7.0013751029968265,
|
|
"epoch": 0.05952149387278739,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000382,
|
|
"loss": 6.5988,
|
|
"mean_token_accuracy": 0.11330810338258743,
|
|
"num_tokens": 1325554.0,
|
|
"step": 765
|
|
},
|
|
{
|
|
"entropy": 6.8747217655181885,
|
|
"epoch": 0.05991052324450496,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0003845,
|
|
"loss": 6.4944,
|
|
"mean_token_accuracy": 0.11092947795987129,
|
|
"num_tokens": 1334201.0,
|
|
"step": 770
|
|
},
|
|
{
|
|
"entropy": 6.932094430923462,
|
|
"epoch": 0.060299552616222524,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00038700000000000003,
|
|
"loss": 6.5156,
|
|
"mean_token_accuracy": 0.11926758959889412,
|
|
"num_tokens": 1343061.0,
|
|
"step": 775
|
|
},
|
|
{
|
|
"entropy": 6.882827472686768,
|
|
"epoch": 0.06068858198794009,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00038950000000000003,
|
|
"loss": 6.4792,
|
|
"mean_token_accuracy": 0.12102379724383354,
|
|
"num_tokens": 1352262.0,
|
|
"step": 780
|
|
},
|
|
{
|
|
"entropy": 6.8652026653289795,
|
|
"epoch": 0.061077611359657655,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00039200000000000004,
|
|
"loss": 6.5417,
|
|
"mean_token_accuracy": 0.11120004132390023,
|
|
"num_tokens": 1361400.0,
|
|
"step": 785
|
|
},
|
|
{
|
|
"entropy": 6.9827672958374025,
|
|
"epoch": 0.06146664073137522,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00039450000000000005,
|
|
"loss": 6.6545,
|
|
"mean_token_accuracy": 0.1084800124168396,
|
|
"num_tokens": 1369850.0,
|
|
"step": 790
|
|
},
|
|
{
|
|
"entropy": 6.896434259414673,
|
|
"epoch": 0.061855670103092786,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00039700000000000005,
|
|
"loss": 6.5041,
|
|
"mean_token_accuracy": 0.11742325201630592,
|
|
"num_tokens": 1378342.0,
|
|
"step": 795
|
|
},
|
|
{
|
|
"entropy": 6.971995687484741,
|
|
"epoch": 0.06224469947481035,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0003995,
|
|
"loss": 6.5897,
|
|
"mean_token_accuracy": 0.109882403165102,
|
|
"num_tokens": 1386981.0,
|
|
"step": 800
|
|
},
|
|
{
|
|
"entropy": 6.938254642486572,
|
|
"epoch": 0.06263372884652792,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000402,
|
|
"loss": 6.6818,
|
|
"mean_token_accuracy": 0.10729405432939529,
|
|
"num_tokens": 1395801.0,
|
|
"step": 805
|
|
},
|
|
{
|
|
"entropy": 7.06087851524353,
|
|
"epoch": 0.06302275821824548,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004045,
|
|
"loss": 6.5776,
|
|
"mean_token_accuracy": 0.11447910293936729,
|
|
"num_tokens": 1403715.0,
|
|
"step": 810
|
|
},
|
|
{
|
|
"entropy": 6.9617109298706055,
|
|
"epoch": 0.06341178758996305,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00040699999999999997,
|
|
"loss": 6.6583,
|
|
"mean_token_accuracy": 0.11031345576047898,
|
|
"num_tokens": 1413199.0,
|
|
"step": 815
|
|
},
|
|
{
|
|
"entropy": 6.929412412643432,
|
|
"epoch": 0.0638008169616806,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004095,
|
|
"loss": 6.632,
|
|
"mean_token_accuracy": 0.11478308364748954,
|
|
"num_tokens": 1421918.0,
|
|
"step": 820
|
|
},
|
|
{
|
|
"entropy": 6.956843757629395,
|
|
"epoch": 0.06418984633339817,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000412,
|
|
"loss": 6.5245,
|
|
"mean_token_accuracy": 0.11161991730332374,
|
|
"num_tokens": 1430625.0,
|
|
"step": 825
|
|
},
|
|
{
|
|
"entropy": 6.826650476455688,
|
|
"epoch": 0.06457887570511574,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004145,
|
|
"loss": 6.562,
|
|
"mean_token_accuracy": 0.11291277259588242,
|
|
"num_tokens": 1439158.0,
|
|
"step": 830
|
|
},
|
|
{
|
|
"entropy": 6.870626020431518,
|
|
"epoch": 0.0649679050768333,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000417,
|
|
"loss": 6.527,
|
|
"mean_token_accuracy": 0.11909559741616249,
|
|
"num_tokens": 1448266.0,
|
|
"step": 835
|
|
},
|
|
{
|
|
"entropy": 6.925184917449951,
|
|
"epoch": 0.06535693444855087,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004195,
|
|
"loss": 6.6033,
|
|
"mean_token_accuracy": 0.11738861948251725,
|
|
"num_tokens": 1457322.0,
|
|
"step": 840
|
|
},
|
|
{
|
|
"entropy": 7.063237190246582,
|
|
"epoch": 0.06574596382026843,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000422,
|
|
"loss": 6.7224,
|
|
"mean_token_accuracy": 0.10825124606490136,
|
|
"num_tokens": 1466120.0,
|
|
"step": 845
|
|
},
|
|
{
|
|
"entropy": 6.864966869354248,
|
|
"epoch": 0.066134993191986,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004245,
|
|
"loss": 6.4761,
|
|
"mean_token_accuracy": 0.11677760556340218,
|
|
"num_tokens": 1474965.0,
|
|
"step": 850
|
|
},
|
|
{
|
|
"entropy": 6.859512901306152,
|
|
"epoch": 0.06652402256370356,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000427,
|
|
"loss": 6.5646,
|
|
"mean_token_accuracy": 0.11498897522687912,
|
|
"num_tokens": 1483483.0,
|
|
"step": 855
|
|
},
|
|
{
|
|
"entropy": 6.937557744979858,
|
|
"epoch": 0.06691305193542113,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004295,
|
|
"loss": 6.5105,
|
|
"mean_token_accuracy": 0.1108026348054409,
|
|
"num_tokens": 1492313.0,
|
|
"step": 860
|
|
},
|
|
{
|
|
"entropy": 6.8773322105407715,
|
|
"epoch": 0.06730208130713869,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000432,
|
|
"loss": 6.4427,
|
|
"mean_token_accuracy": 0.11592724919319153,
|
|
"num_tokens": 1501081.0,
|
|
"step": 865
|
|
},
|
|
{
|
|
"entropy": 6.809585762023926,
|
|
"epoch": 0.06769111067885625,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004345,
|
|
"loss": 6.4583,
|
|
"mean_token_accuracy": 0.11120192930102349,
|
|
"num_tokens": 1510169.0,
|
|
"step": 870
|
|
},
|
|
{
|
|
"entropy": 6.838544702529907,
|
|
"epoch": 0.06808014005057382,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000437,
|
|
"loss": 6.4244,
|
|
"mean_token_accuracy": 0.11338047757744789,
|
|
"num_tokens": 1519546.0,
|
|
"step": 875
|
|
},
|
|
{
|
|
"entropy": 6.820107889175415,
|
|
"epoch": 0.06846916942229138,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004395,
|
|
"loss": 6.5435,
|
|
"mean_token_accuracy": 0.1123778223991394,
|
|
"num_tokens": 1529104.0,
|
|
"step": 880
|
|
},
|
|
{
|
|
"entropy": 6.7314704895019535,
|
|
"epoch": 0.06885819879400895,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000442,
|
|
"loss": 6.4938,
|
|
"mean_token_accuracy": 0.12263969853520393,
|
|
"num_tokens": 1537033.0,
|
|
"step": 885
|
|
},
|
|
{
|
|
"entropy": 6.9164563655853275,
|
|
"epoch": 0.06924722816572651,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004445,
|
|
"loss": 6.5018,
|
|
"mean_token_accuracy": 0.11451332420110702,
|
|
"num_tokens": 1545059.0,
|
|
"step": 890
|
|
},
|
|
{
|
|
"entropy": 6.853432083129883,
|
|
"epoch": 0.06963625753744408,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000447,
|
|
"loss": 6.5062,
|
|
"mean_token_accuracy": 0.11352940872311593,
|
|
"num_tokens": 1553784.0,
|
|
"step": 895
|
|
},
|
|
{
|
|
"entropy": 6.785615253448486,
|
|
"epoch": 0.07002528690916164,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00044950000000000003,
|
|
"loss": 6.4413,
|
|
"mean_token_accuracy": 0.11957875341176986,
|
|
"num_tokens": 1562059.0,
|
|
"step": 900
|
|
},
|
|
{
|
|
"entropy": 6.781708908081055,
|
|
"epoch": 0.0704143162808792,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00045200000000000004,
|
|
"loss": 6.5083,
|
|
"mean_token_accuracy": 0.1147128850221634,
|
|
"num_tokens": 1570061.0,
|
|
"step": 905
|
|
},
|
|
{
|
|
"entropy": 6.792767333984375,
|
|
"epoch": 0.07080334565259677,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00045450000000000004,
|
|
"loss": 6.4642,
|
|
"mean_token_accuracy": 0.11603316441178321,
|
|
"num_tokens": 1578261.0,
|
|
"step": 910
|
|
},
|
|
{
|
|
"entropy": 6.81901068687439,
|
|
"epoch": 0.07119237502431433,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00045700000000000005,
|
|
"loss": 6.3991,
|
|
"mean_token_accuracy": 0.11860067769885063,
|
|
"num_tokens": 1586260.0,
|
|
"step": 915
|
|
},
|
|
{
|
|
"entropy": 6.7977457523345945,
|
|
"epoch": 0.0715814043960319,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00045950000000000006,
|
|
"loss": 6.5922,
|
|
"mean_token_accuracy": 0.11235073879361153,
|
|
"num_tokens": 1595234.0,
|
|
"step": 920
|
|
},
|
|
{
|
|
"entropy": 6.873261642456055,
|
|
"epoch": 0.07197043376774946,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000462,
|
|
"loss": 6.4801,
|
|
"mean_token_accuracy": 0.11916077733039857,
|
|
"num_tokens": 1604212.0,
|
|
"step": 925
|
|
},
|
|
{
|
|
"entropy": 6.792505550384521,
|
|
"epoch": 0.07235946313946703,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004645,
|
|
"loss": 6.5283,
|
|
"mean_token_accuracy": 0.11446316465735436,
|
|
"num_tokens": 1612925.0,
|
|
"step": 930
|
|
},
|
|
{
|
|
"entropy": 6.767776250839233,
|
|
"epoch": 0.07274849251118459,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000467,
|
|
"loss": 6.4187,
|
|
"mean_token_accuracy": 0.12004713863134384,
|
|
"num_tokens": 1621804.0,
|
|
"step": 935
|
|
},
|
|
{
|
|
"entropy": 6.757959938049316,
|
|
"epoch": 0.07313752188290217,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004695,
|
|
"loss": 6.3969,
|
|
"mean_token_accuracy": 0.11997036337852478,
|
|
"num_tokens": 1630943.0,
|
|
"step": 940
|
|
},
|
|
{
|
|
"entropy": 6.713178873062134,
|
|
"epoch": 0.07352655125461972,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000472,
|
|
"loss": 6.3106,
|
|
"mean_token_accuracy": 0.12384014949202538,
|
|
"num_tokens": 1638899.0,
|
|
"step": 945
|
|
},
|
|
{
|
|
"entropy": 6.813256025314331,
|
|
"epoch": 0.07391558062633728,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004745,
|
|
"loss": 6.5183,
|
|
"mean_token_accuracy": 0.11929329931735992,
|
|
"num_tokens": 1647485.0,
|
|
"step": 950
|
|
},
|
|
{
|
|
"entropy": 6.792909765243531,
|
|
"epoch": 0.07430460999805485,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.000477,
|
|
"loss": 6.485,
|
|
"mean_token_accuracy": 0.11955598518252372,
|
|
"num_tokens": 1656290.0,
|
|
"step": 955
|
|
},
|
|
{
|
|
"entropy": 6.814577341079712,
|
|
"epoch": 0.07469363936977241,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004795,
|
|
"loss": 6.5025,
|
|
"mean_token_accuracy": 0.11491848975419998,
|
|
"num_tokens": 1665474.0,
|
|
"step": 960
|
|
},
|
|
{
|
|
"entropy": 6.6340234756469725,
|
|
"epoch": 0.07508266874148999,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000482,
|
|
"loss": 6.3785,
|
|
"mean_token_accuracy": 0.12735505029559135,
|
|
"num_tokens": 1673599.0,
|
|
"step": 965
|
|
},
|
|
{
|
|
"entropy": 6.7855254173278805,
|
|
"epoch": 0.07547169811320754,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004845,
|
|
"loss": 6.3513,
|
|
"mean_token_accuracy": 0.11603628024458885,
|
|
"num_tokens": 1683282.0,
|
|
"step": 970
|
|
},
|
|
{
|
|
"entropy": 6.784381628036499,
|
|
"epoch": 0.07586072748492512,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000487,
|
|
"loss": 6.4793,
|
|
"mean_token_accuracy": 0.12123103961348533,
|
|
"num_tokens": 1691094.0,
|
|
"step": 975
|
|
},
|
|
{
|
|
"entropy": 6.6339301586151125,
|
|
"epoch": 0.07624975685664268,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004895,
|
|
"loss": 6.356,
|
|
"mean_token_accuracy": 0.1204170361161232,
|
|
"num_tokens": 1700053.0,
|
|
"step": 980
|
|
},
|
|
{
|
|
"entropy": 6.736316251754761,
|
|
"epoch": 0.07663878622836025,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000492,
|
|
"loss": 6.2828,
|
|
"mean_token_accuracy": 0.12172069922089576,
|
|
"num_tokens": 1707732.0,
|
|
"step": 985
|
|
},
|
|
{
|
|
"entropy": 6.719516134262085,
|
|
"epoch": 0.0770278156000778,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004945,
|
|
"loss": 6.5251,
|
|
"mean_token_accuracy": 0.11388466954231262,
|
|
"num_tokens": 1716406.0,
|
|
"step": 990
|
|
},
|
|
{
|
|
"entropy": 6.887849283218384,
|
|
"epoch": 0.07741684497179536,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000497,
|
|
"loss": 6.5579,
|
|
"mean_token_accuracy": 0.11262270659208298,
|
|
"num_tokens": 1725832.0,
|
|
"step": 995
|
|
},
|
|
{
|
|
"entropy": 6.818440103530884,
|
|
"epoch": 0.07780587434351294,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004995,
|
|
"loss": 6.4678,
|
|
"mean_token_accuracy": 0.11311930790543556,
|
|
"num_tokens": 1734853.0,
|
|
"step": 1000
|
|
},
|
|
{
|
|
"entropy": 6.694705009460449,
|
|
"epoch": 0.0781949037152305,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004999999989075146,
|
|
"loss": 6.4807,
|
|
"mean_token_accuracy": 0.12094770967960358,
|
|
"num_tokens": 1744240.0,
|
|
"step": 1005
|
|
},
|
|
{
|
|
"entropy": 6.865083646774292,
|
|
"epoch": 0.07858393308694807,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004999999944692927,
|
|
"loss": 6.4969,
|
|
"mean_token_accuracy": 0.11460169404745102,
|
|
"num_tokens": 1753334.0,
|
|
"step": 1010
|
|
},
|
|
{
|
|
"entropy": 6.603975772857666,
|
|
"epoch": 0.07897296245866563,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000499999986617054,
|
|
"loss": 6.3948,
|
|
"mean_token_accuracy": 0.11559040769934655,
|
|
"num_tokens": 1762032.0,
|
|
"step": 1015
|
|
},
|
|
{
|
|
"entropy": 6.726358270645141,
|
|
"epoch": 0.0793619918303832,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999999753507986,
|
|
"loss": 6.3834,
|
|
"mean_token_accuracy": 0.11660856455564499,
|
|
"num_tokens": 1770508.0,
|
|
"step": 1020
|
|
},
|
|
{
|
|
"entropy": 6.621751356124878,
|
|
"epoch": 0.07975102120210076,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999999606705267,
|
|
"loss": 6.2867,
|
|
"mean_token_accuracy": 0.12645310387015343,
|
|
"num_tokens": 1780167.0,
|
|
"step": 1025
|
|
},
|
|
{
|
|
"entropy": 6.760381269454956,
|
|
"epoch": 0.08014005057381832,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999999425762385,
|
|
"loss": 6.4923,
|
|
"mean_token_accuracy": 0.11203559264540672,
|
|
"num_tokens": 1788809.0,
|
|
"step": 1030
|
|
},
|
|
{
|
|
"entropy": 6.707613611221314,
|
|
"epoch": 0.08052907994553589,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004999999210679344,
|
|
"loss": 6.4082,
|
|
"mean_token_accuracy": 0.11932154521346092,
|
|
"num_tokens": 1797445.0,
|
|
"step": 1035
|
|
},
|
|
{
|
|
"entropy": 6.708571434020996,
|
|
"epoch": 0.08091810931725345,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004999998961456145,
|
|
"loss": 6.4093,
|
|
"mean_token_accuracy": 0.11497489586472512,
|
|
"num_tokens": 1806488.0,
|
|
"step": 1040
|
|
},
|
|
{
|
|
"entropy": 6.7836400985717775,
|
|
"epoch": 0.08130713868897102,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004999998678092794,
|
|
"loss": 6.4865,
|
|
"mean_token_accuracy": 0.12190944403409958,
|
|
"num_tokens": 1815692.0,
|
|
"step": 1045
|
|
},
|
|
{
|
|
"entropy": 6.733627986907959,
|
|
"epoch": 0.08169616806068858,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004999998360589293,
|
|
"loss": 6.3935,
|
|
"mean_token_accuracy": 0.12152979299426078,
|
|
"num_tokens": 1824599.0,
|
|
"step": 1050
|
|
},
|
|
{
|
|
"entropy": 6.814380025863647,
|
|
"epoch": 0.08208519743240615,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000499999800894565,
|
|
"loss": 6.5522,
|
|
"mean_token_accuracy": 0.11713027730584144,
|
|
"num_tokens": 1833411.0,
|
|
"step": 1055
|
|
},
|
|
{
|
|
"entropy": 6.664803600311279,
|
|
"epoch": 0.08247422680412371,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004999997623161866,
|
|
"loss": 6.3602,
|
|
"mean_token_accuracy": 0.11816268861293792,
|
|
"num_tokens": 1842177.0,
|
|
"step": 1060
|
|
},
|
|
{
|
|
"entropy": 6.589741563796997,
|
|
"epoch": 0.08286325617584128,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004999997203237951,
|
|
"loss": 6.3501,
|
|
"mean_token_accuracy": 0.12157049998641015,
|
|
"num_tokens": 1850176.0,
|
|
"step": 1065
|
|
},
|
|
{
|
|
"entropy": 6.725516271591187,
|
|
"epoch": 0.08325228554755884,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000499999674917391,
|
|
"loss": 6.3956,
|
|
"mean_token_accuracy": 0.12002233043313026,
|
|
"num_tokens": 1859464.0,
|
|
"step": 1070
|
|
},
|
|
{
|
|
"entropy": 6.589758443832397,
|
|
"epoch": 0.0836413149192764,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004999996260969748,
|
|
"loss": 6.3058,
|
|
"mean_token_accuracy": 0.11860100701451301,
|
|
"num_tokens": 1867733.0,
|
|
"step": 1075
|
|
},
|
|
{
|
|
"entropy": 6.651362705230713,
|
|
"epoch": 0.08403034429099397,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004999995738625475,
|
|
"loss": 6.2897,
|
|
"mean_token_accuracy": 0.1241245798766613,
|
|
"num_tokens": 1876010.0,
|
|
"step": 1080
|
|
},
|
|
{
|
|
"entropy": 6.645105648040771,
|
|
"epoch": 0.08441937366271153,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999995182141099,
|
|
"loss": 6.4517,
|
|
"mean_token_accuracy": 0.11694926843047142,
|
|
"num_tokens": 1884906.0,
|
|
"step": 1085
|
|
},
|
|
{
|
|
"entropy": 6.668650484085083,
|
|
"epoch": 0.0848084030344291,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004999994591516626,
|
|
"loss": 6.36,
|
|
"mean_token_accuracy": 0.1204823799431324,
|
|
"num_tokens": 1893464.0,
|
|
"step": 1090
|
|
},
|
|
{
|
|
"entropy": 6.652740049362182,
|
|
"epoch": 0.08519743240614666,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999993966752066,
|
|
"loss": 6.4075,
|
|
"mean_token_accuracy": 0.11751677766442299,
|
|
"num_tokens": 1902769.0,
|
|
"step": 1095
|
|
},
|
|
{
|
|
"entropy": 6.724245500564575,
|
|
"epoch": 0.08558646177786423,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000499999330784743,
|
|
"loss": 6.3414,
|
|
"mean_token_accuracy": 0.11880838871002197,
|
|
"num_tokens": 1911968.0,
|
|
"step": 1100
|
|
},
|
|
{
|
|
"entropy": 6.623199605941773,
|
|
"epoch": 0.08597549114958179,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004999992614802725,
|
|
"loss": 6.3306,
|
|
"mean_token_accuracy": 0.12165946811437607,
|
|
"num_tokens": 1920063.0,
|
|
"step": 1105
|
|
},
|
|
{
|
|
"entropy": 6.5714949607849125,
|
|
"epoch": 0.08636452052129936,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004999991887617966,
|
|
"loss": 6.2931,
|
|
"mean_token_accuracy": 0.12126443311572074,
|
|
"num_tokens": 1929192.0,
|
|
"step": 1110
|
|
},
|
|
{
|
|
"entropy": 6.723468399047851,
|
|
"epoch": 0.08675354989301692,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999991126293158,
|
|
"loss": 6.5039,
|
|
"mean_token_accuracy": 0.11924195289611816,
|
|
"num_tokens": 1939082.0,
|
|
"step": 1115
|
|
},
|
|
{
|
|
"entropy": 6.509707975387573,
|
|
"epoch": 0.08714257926473448,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999990330828318,
|
|
"loss": 6.3622,
|
|
"mean_token_accuracy": 0.11828808337450028,
|
|
"num_tokens": 1948313.0,
|
|
"step": 1120
|
|
},
|
|
{
|
|
"entropy": 6.764839315414429,
|
|
"epoch": 0.08753160863645205,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004999989501223456,
|
|
"loss": 6.3535,
|
|
"mean_token_accuracy": 0.11773044615983963,
|
|
"num_tokens": 1957035.0,
|
|
"step": 1125
|
|
},
|
|
{
|
|
"entropy": 6.571807384490967,
|
|
"epoch": 0.08792063800816961,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999988637478584,
|
|
"loss": 6.356,
|
|
"mean_token_accuracy": 0.11375595852732659,
|
|
"num_tokens": 1966041.0,
|
|
"step": 1130
|
|
},
|
|
{
|
|
"entropy": 6.682859468460083,
|
|
"epoch": 0.08830966737988719,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004999987739593716,
|
|
"loss": 6.3945,
|
|
"mean_token_accuracy": 0.11131789907813072,
|
|
"num_tokens": 1975019.0,
|
|
"step": 1135
|
|
},
|
|
{
|
|
"entropy": 6.595472717285157,
|
|
"epoch": 0.08869869675160474,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004999986807568865,
|
|
"loss": 6.3177,
|
|
"mean_token_accuracy": 0.12635206803679466,
|
|
"num_tokens": 1982930.0,
|
|
"step": 1140
|
|
},
|
|
{
|
|
"entropy": 6.661126136779785,
|
|
"epoch": 0.08908772612332232,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004999985841404045,
|
|
"loss": 6.4155,
|
|
"mean_token_accuracy": 0.11563977152109146,
|
|
"num_tokens": 1991888.0,
|
|
"step": 1145
|
|
},
|
|
{
|
|
"entropy": 6.647232627868652,
|
|
"epoch": 0.08947675549503988,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004999984841099271,
|
|
"loss": 6.2743,
|
|
"mean_token_accuracy": 0.11983647644519806,
|
|
"num_tokens": 2000202.0,
|
|
"step": 1150
|
|
},
|
|
{
|
|
"entropy": 6.5404551982879635,
|
|
"epoch": 0.08986578486675743,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000499998380665456,
|
|
"loss": 6.3057,
|
|
"mean_token_accuracy": 0.12251394167542458,
|
|
"num_tokens": 2009281.0,
|
|
"step": 1155
|
|
},
|
|
{
|
|
"entropy": 6.654289579391479,
|
|
"epoch": 0.090254814238475,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999982738069924,
|
|
"loss": 6.3102,
|
|
"mean_token_accuracy": 0.12231542989611625,
|
|
"num_tokens": 2017806.0,
|
|
"step": 1160
|
|
},
|
|
{
|
|
"entropy": 6.654610538482666,
|
|
"epoch": 0.09064384361019256,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999981635345382,
|
|
"loss": 6.3964,
|
|
"mean_token_accuracy": 0.11891458630561828,
|
|
"num_tokens": 2027582.0,
|
|
"step": 1165
|
|
},
|
|
{
|
|
"entropy": 6.530627679824829,
|
|
"epoch": 0.09103287298191014,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999980498480949,
|
|
"loss": 6.2699,
|
|
"mean_token_accuracy": 0.12494958117604256,
|
|
"num_tokens": 2035427.0,
|
|
"step": 1170
|
|
},
|
|
{
|
|
"entropy": 6.712484693527221,
|
|
"epoch": 0.0914219023536277,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999979327476644,
|
|
"loss": 6.4533,
|
|
"mean_token_accuracy": 0.1177413173019886,
|
|
"num_tokens": 2044603.0,
|
|
"step": 1175
|
|
},
|
|
{
|
|
"entropy": 6.584618806838989,
|
|
"epoch": 0.09181093172534527,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999978122332485,
|
|
"loss": 6.2931,
|
|
"mean_token_accuracy": 0.12760861366987228,
|
|
"num_tokens": 2053272.0,
|
|
"step": 1180
|
|
},
|
|
{
|
|
"entropy": 6.628946113586426,
|
|
"epoch": 0.09219996109706283,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999976883048487,
|
|
"loss": 6.3113,
|
|
"mean_token_accuracy": 0.12247533276677132,
|
|
"num_tokens": 2061677.0,
|
|
"step": 1185
|
|
},
|
|
{
|
|
"entropy": 6.565109968185425,
|
|
"epoch": 0.0925889904687804,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999975609624673,
|
|
"loss": 6.3337,
|
|
"mean_token_accuracy": 0.12145892754197121,
|
|
"num_tokens": 2070282.0,
|
|
"step": 1190
|
|
},
|
|
{
|
|
"entropy": 6.7010410785675045,
|
|
"epoch": 0.09297801984049796,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004999974302061059,
|
|
"loss": 6.4161,
|
|
"mean_token_accuracy": 0.11821920722723007,
|
|
"num_tokens": 2078812.0,
|
|
"step": 1195
|
|
},
|
|
{
|
|
"entropy": 6.600937271118164,
|
|
"epoch": 0.09336704921221552,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999972960357666,
|
|
"loss": 6.3138,
|
|
"mean_token_accuracy": 0.11917631253600121,
|
|
"num_tokens": 2087020.0,
|
|
"step": 1200
|
|
},
|
|
{
|
|
"entropy": 6.548227739334107,
|
|
"epoch": 0.09375607858393309,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004999971584514516,
|
|
"loss": 6.2607,
|
|
"mean_token_accuracy": 0.1289692461490631,
|
|
"num_tokens": 2095933.0,
|
|
"step": 1205
|
|
},
|
|
{
|
|
"entropy": 6.49370927810669,
|
|
"epoch": 0.09414510795565065,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999970174531627,
|
|
"loss": 6.2709,
|
|
"mean_token_accuracy": 0.1252399981021881,
|
|
"num_tokens": 2105218.0,
|
|
"step": 1210
|
|
},
|
|
{
|
|
"entropy": 6.519537162780762,
|
|
"epoch": 0.09453413732736822,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004999968730409022,
|
|
"loss": 6.1868,
|
|
"mean_token_accuracy": 0.12397775202989578,
|
|
"num_tokens": 2113808.0,
|
|
"step": 1215
|
|
},
|
|
{
|
|
"entropy": 6.508232164382934,
|
|
"epoch": 0.09492316669908578,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999967252146723,
|
|
"loss": 6.3589,
|
|
"mean_token_accuracy": 0.11807975843548775,
|
|
"num_tokens": 2123014.0,
|
|
"step": 1220
|
|
},
|
|
{
|
|
"entropy": 6.678585195541382,
|
|
"epoch": 0.09531219607080335,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004999965739744752,
|
|
"loss": 6.2823,
|
|
"mean_token_accuracy": 0.12472278475761414,
|
|
"num_tokens": 2131840.0,
|
|
"step": 1225
|
|
},
|
|
{
|
|
"entropy": 6.571667098999024,
|
|
"epoch": 0.09570122544252091,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004999964193203132,
|
|
"loss": 6.3797,
|
|
"mean_token_accuracy": 0.1198837198317051,
|
|
"num_tokens": 2140467.0,
|
|
"step": 1230
|
|
},
|
|
{
|
|
"entropy": 6.62928991317749,
|
|
"epoch": 0.09609025481423847,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999962612521888,
|
|
"loss": 6.3252,
|
|
"mean_token_accuracy": 0.12536743581295012,
|
|
"num_tokens": 2149282.0,
|
|
"step": 1235
|
|
},
|
|
{
|
|
"entropy": 6.576823568344116,
|
|
"epoch": 0.09647928418595604,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999960997701041,
|
|
"loss": 6.3244,
|
|
"mean_token_accuracy": 0.12110247910022735,
|
|
"num_tokens": 2157781.0,
|
|
"step": 1240
|
|
},
|
|
{
|
|
"entropy": 6.597092962265014,
|
|
"epoch": 0.0968683135576736,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999959348740618,
|
|
"loss": 6.2967,
|
|
"mean_token_accuracy": 0.12580249533057214,
|
|
"num_tokens": 2166482.0,
|
|
"step": 1245
|
|
},
|
|
{
|
|
"entropy": 6.499213790893554,
|
|
"epoch": 0.09725734292939117,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999957665640641,
|
|
"loss": 6.3132,
|
|
"mean_token_accuracy": 0.12070827260613441,
|
|
"num_tokens": 2174559.0,
|
|
"step": 1250
|
|
},
|
|
{
|
|
"entropy": 6.5587629795074465,
|
|
"epoch": 0.09764637230110873,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000499995594840114,
|
|
"loss": 6.2106,
|
|
"mean_token_accuracy": 0.12732202261686326,
|
|
"num_tokens": 2182374.0,
|
|
"step": 1255
|
|
},
|
|
{
|
|
"entropy": 6.497962141036988,
|
|
"epoch": 0.0980354016728263,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999954197022138,
|
|
"loss": 6.2986,
|
|
"mean_token_accuracy": 0.1267983116209507,
|
|
"num_tokens": 2191427.0,
|
|
"step": 1260
|
|
},
|
|
{
|
|
"entropy": 6.650804328918457,
|
|
"epoch": 0.09842443104454386,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004999952411503661,
|
|
"loss": 6.3879,
|
|
"mean_token_accuracy": 0.11929038390517235,
|
|
"num_tokens": 2199698.0,
|
|
"step": 1265
|
|
},
|
|
{
|
|
"entropy": 6.565453624725341,
|
|
"epoch": 0.09881346041626143,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999950591845738,
|
|
"loss": 6.2348,
|
|
"mean_token_accuracy": 0.12733448669314384,
|
|
"num_tokens": 2208519.0,
|
|
"step": 1270
|
|
},
|
|
{
|
|
"entropy": 6.464875268936157,
|
|
"epoch": 0.09920248978797899,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999948738048397,
|
|
"loss": 6.2428,
|
|
"mean_token_accuracy": 0.1302006796002388,
|
|
"num_tokens": 2217453.0,
|
|
"step": 1275
|
|
},
|
|
{
|
|
"entropy": 6.554579877853394,
|
|
"epoch": 0.09959151915969655,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004999946850111663,
|
|
"loss": 6.3577,
|
|
"mean_token_accuracy": 0.12167153358459473,
|
|
"num_tokens": 2225623.0,
|
|
"step": 1280
|
|
},
|
|
{
|
|
"entropy": 6.576758623123169,
|
|
"epoch": 0.09998054853141412,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999944928035569,
|
|
"loss": 6.2919,
|
|
"mean_token_accuracy": 0.12363119274377823,
|
|
"num_tokens": 2234519.0,
|
|
"step": 1285
|
|
},
|
|
{
|
|
"entropy": 6.5044145584106445,
|
|
"epoch": 0.10036957790313168,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.000499994297182014,
|
|
"loss": 6.3061,
|
|
"mean_token_accuracy": 0.12101315706968307,
|
|
"num_tokens": 2242994.0,
|
|
"step": 1290
|
|
},
|
|
{
|
|
"entropy": 6.651056385040283,
|
|
"epoch": 0.10075860727484925,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999940981465408,
|
|
"loss": 6.3138,
|
|
"mean_token_accuracy": 0.12628812938928605,
|
|
"num_tokens": 2251687.0,
|
|
"step": 1295
|
|
},
|
|
{
|
|
"entropy": 6.394090366363526,
|
|
"epoch": 0.10114763664656681,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999938956971404,
|
|
"loss": 6.2409,
|
|
"mean_token_accuracy": 0.12676058262586593,
|
|
"num_tokens": 2260751.0,
|
|
"step": 1300
|
|
},
|
|
{
|
|
"entropy": 6.595192193984985,
|
|
"epoch": 0.10153666601828439,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999936898338156,
|
|
"loss": 6.1791,
|
|
"mean_token_accuracy": 0.13165878504514694,
|
|
"num_tokens": 2269125.0,
|
|
"step": 1305
|
|
},
|
|
{
|
|
"entropy": 6.401913452148437,
|
|
"epoch": 0.10192569539000194,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999934805565698,
|
|
"loss": 6.1097,
|
|
"mean_token_accuracy": 0.12795391529798508,
|
|
"num_tokens": 2277098.0,
|
|
"step": 1310
|
|
},
|
|
{
|
|
"entropy": 6.470233392715454,
|
|
"epoch": 0.10231472476171952,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000499993267865406,
|
|
"loss": 6.3887,
|
|
"mean_token_accuracy": 0.1236030898988247,
|
|
"num_tokens": 2285953.0,
|
|
"step": 1315
|
|
},
|
|
{
|
|
"entropy": 6.676652717590332,
|
|
"epoch": 0.10270375413343708,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004999930517603275,
|
|
"loss": 6.3036,
|
|
"mean_token_accuracy": 0.12659136727452278,
|
|
"num_tokens": 2294487.0,
|
|
"step": 1320
|
|
},
|
|
{
|
|
"entropy": 6.545140743255615,
|
|
"epoch": 0.10309278350515463,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999928322413374,
|
|
"loss": 6.3383,
|
|
"mean_token_accuracy": 0.1220410332083702,
|
|
"num_tokens": 2302915.0,
|
|
"step": 1325
|
|
},
|
|
{
|
|
"entropy": 6.493171358108521,
|
|
"epoch": 0.1034818128768722,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004999926093084394,
|
|
"loss": 6.2879,
|
|
"mean_token_accuracy": 0.11915498897433281,
|
|
"num_tokens": 2310769.0,
|
|
"step": 1330
|
|
},
|
|
{
|
|
"entropy": 6.463140153884888,
|
|
"epoch": 0.10387084224858976,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004999923829616365,
|
|
"loss": 6.1782,
|
|
"mean_token_accuracy": 0.12339231967926026,
|
|
"num_tokens": 2319987.0,
|
|
"step": 1335
|
|
},
|
|
{
|
|
"entropy": 6.515197849273681,
|
|
"epoch": 0.10425987162030734,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999921532009323,
|
|
"loss": 6.2932,
|
|
"mean_token_accuracy": 0.1183166541159153,
|
|
"num_tokens": 2328964.0,
|
|
"step": 1340
|
|
},
|
|
{
|
|
"entropy": 6.563854217529297,
|
|
"epoch": 0.1046489009920249,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004999919200263304,
|
|
"loss": 6.2556,
|
|
"mean_token_accuracy": 0.11943673864006996,
|
|
"num_tokens": 2337945.0,
|
|
"step": 1345
|
|
},
|
|
{
|
|
"entropy": 6.530140399932861,
|
|
"epoch": 0.10503793036374247,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004999916834378342,
|
|
"loss": 6.1306,
|
|
"mean_token_accuracy": 0.12886034995317458,
|
|
"num_tokens": 2345989.0,
|
|
"step": 1350
|
|
},
|
|
{
|
|
"entropy": 6.404300594329834,
|
|
"epoch": 0.10542695973546003,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004999914434354472,
|
|
"loss": 6.2652,
|
|
"mean_token_accuracy": 0.12330945879220963,
|
|
"num_tokens": 2353752.0,
|
|
"step": 1355
|
|
},
|
|
{
|
|
"entropy": 6.504211378097534,
|
|
"epoch": 0.10581598910717759,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004999912000191733,
|
|
"loss": 6.2419,
|
|
"mean_token_accuracy": 0.12025356367230415,
|
|
"num_tokens": 2361961.0,
|
|
"step": 1360
|
|
},
|
|
{
|
|
"entropy": 6.423410511016845,
|
|
"epoch": 0.10620501847889516,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000499990953189016,
|
|
"loss": 6.1589,
|
|
"mean_token_accuracy": 0.12905707210302353,
|
|
"num_tokens": 2370148.0,
|
|
"step": 1365
|
|
},
|
|
{
|
|
"entropy": 6.537519788742065,
|
|
"epoch": 0.10659404785061272,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999907029449791,
|
|
"loss": 6.186,
|
|
"mean_token_accuracy": 0.131666212528944,
|
|
"num_tokens": 2379105.0,
|
|
"step": 1370
|
|
},
|
|
{
|
|
"entropy": 6.4747106552124025,
|
|
"epoch": 0.10698307722233029,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999904492870663,
|
|
"loss": 6.2698,
|
|
"mean_token_accuracy": 0.12513106688857079,
|
|
"num_tokens": 2387417.0,
|
|
"step": 1375
|
|
},
|
|
{
|
|
"entropy": 6.521770191192627,
|
|
"epoch": 0.10737210659404785,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999901922152816,
|
|
"loss": 6.2904,
|
|
"mean_token_accuracy": 0.13334674686193465,
|
|
"num_tokens": 2396163.0,
|
|
"step": 1380
|
|
},
|
|
{
|
|
"entropy": 6.347804832458496,
|
|
"epoch": 0.10776113596576542,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999899317296288,
|
|
"loss": 6.1475,
|
|
"mean_token_accuracy": 0.12342875301837922,
|
|
"num_tokens": 2404661.0,
|
|
"step": 1385
|
|
},
|
|
{
|
|
"entropy": 6.447468996047974,
|
|
"epoch": 0.10815016533748298,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004999896678301121,
|
|
"loss": 6.2422,
|
|
"mean_token_accuracy": 0.12361390069127083,
|
|
"num_tokens": 2413459.0,
|
|
"step": 1390
|
|
},
|
|
{
|
|
"entropy": 6.573637056350708,
|
|
"epoch": 0.10853919470920055,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004999894005167352,
|
|
"loss": 6.1903,
|
|
"mean_token_accuracy": 0.1322077475488186,
|
|
"num_tokens": 2421401.0,
|
|
"step": 1395
|
|
},
|
|
{
|
|
"entropy": 6.409449672698974,
|
|
"epoch": 0.10892822408091811,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000499989129789502,
|
|
"loss": 6.2017,
|
|
"mean_token_accuracy": 0.1325265347957611,
|
|
"num_tokens": 2429983.0,
|
|
"step": 1400
|
|
},
|
|
{
|
|
"entropy": 6.544249486923218,
|
|
"epoch": 0.10931725345263567,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999888556484172,
|
|
"loss": 6.3394,
|
|
"mean_token_accuracy": 0.1189575508236885,
|
|
"num_tokens": 2439206.0,
|
|
"step": 1405
|
|
},
|
|
{
|
|
"entropy": 6.494714403152466,
|
|
"epoch": 0.10970628282435324,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999885780934845,
|
|
"loss": 6.252,
|
|
"mean_token_accuracy": 0.1334316536784172,
|
|
"num_tokens": 2448801.0,
|
|
"step": 1410
|
|
},
|
|
{
|
|
"entropy": 6.461113309860229,
|
|
"epoch": 0.1100953121960708,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004999882971247081,
|
|
"loss": 6.2983,
|
|
"mean_token_accuracy": 0.12159521356225014,
|
|
"num_tokens": 2458007.0,
|
|
"step": 1415
|
|
},
|
|
{
|
|
"entropy": 6.482313394546509,
|
|
"epoch": 0.11048434156778837,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004999880127420926,
|
|
"loss": 6.1931,
|
|
"mean_token_accuracy": 0.13716387897729873,
|
|
"num_tokens": 2466574.0,
|
|
"step": 1420
|
|
},
|
|
{
|
|
"entropy": 6.530479192733765,
|
|
"epoch": 0.11087337093950593,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999877249456421,
|
|
"loss": 6.2612,
|
|
"mean_token_accuracy": 0.12397516667842864,
|
|
"num_tokens": 2475263.0,
|
|
"step": 1425
|
|
},
|
|
{
|
|
"entropy": 6.218584966659546,
|
|
"epoch": 0.1112624003112235,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999874337353609,
|
|
"loss": 6.0187,
|
|
"mean_token_accuracy": 0.13271408900618553,
|
|
"num_tokens": 2483738.0,
|
|
"step": 1430
|
|
},
|
|
{
|
|
"entropy": 6.438686561584473,
|
|
"epoch": 0.11165142968294106,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999871391112535,
|
|
"loss": 6.1274,
|
|
"mean_token_accuracy": 0.1266042783856392,
|
|
"num_tokens": 2492937.0,
|
|
"step": 1435
|
|
},
|
|
{
|
|
"entropy": 6.360862302780151,
|
|
"epoch": 0.11204045905465862,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004999868410733244,
|
|
"loss": 6.2129,
|
|
"mean_token_accuracy": 0.12471674755215645,
|
|
"num_tokens": 2500716.0,
|
|
"step": 1440
|
|
},
|
|
{
|
|
"entropy": 6.442197370529175,
|
|
"epoch": 0.11242948842637619,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000499986539621578,
|
|
"loss": 6.1963,
|
|
"mean_token_accuracy": 0.1276423953473568,
|
|
"num_tokens": 2509385.0,
|
|
"step": 1445
|
|
},
|
|
{
|
|
"entropy": 6.529846048355102,
|
|
"epoch": 0.11281851779809375,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999862347560191,
|
|
"loss": 6.2579,
|
|
"mean_token_accuracy": 0.12066849693655968,
|
|
"num_tokens": 2518179.0,
|
|
"step": 1450
|
|
},
|
|
{
|
|
"entropy": 6.494664096832276,
|
|
"epoch": 0.11320754716981132,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999859264766521,
|
|
"loss": 6.2111,
|
|
"mean_token_accuracy": 0.12627880051732063,
|
|
"num_tokens": 2526644.0,
|
|
"step": 1455
|
|
},
|
|
{
|
|
"entropy": 6.364485549926758,
|
|
"epoch": 0.11359657654152888,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999856147834817,
|
|
"loss": 6.1292,
|
|
"mean_token_accuracy": 0.1283652275800705,
|
|
"num_tokens": 2534998.0,
|
|
"step": 1460
|
|
},
|
|
{
|
|
"entropy": 6.485772514343262,
|
|
"epoch": 0.11398560591324645,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999852996765129,
|
|
"loss": 6.2034,
|
|
"mean_token_accuracy": 0.12745219245553016,
|
|
"num_tokens": 2543562.0,
|
|
"step": 1465
|
|
},
|
|
{
|
|
"entropy": 6.43467493057251,
|
|
"epoch": 0.11437463528496401,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999849811557502,
|
|
"loss": 6.2066,
|
|
"mean_token_accuracy": 0.1214485488831997,
|
|
"num_tokens": 2551688.0,
|
|
"step": 1470
|
|
},
|
|
{
|
|
"entropy": 6.4273097038269045,
|
|
"epoch": 0.11476366465668159,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999846592211984,
|
|
"loss": 6.265,
|
|
"mean_token_accuracy": 0.12918860763311385,
|
|
"num_tokens": 2560227.0,
|
|
"step": 1475
|
|
},
|
|
{
|
|
"entropy": 6.4545982837677,
|
|
"epoch": 0.11515269402839914,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999843338728626,
|
|
"loss": 6.1509,
|
|
"mean_token_accuracy": 0.13062360733747483,
|
|
"num_tokens": 2569245.0,
|
|
"step": 1480
|
|
},
|
|
{
|
|
"entropy": 6.416768312454224,
|
|
"epoch": 0.1155417234001167,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004999840051107476,
|
|
"loss": 6.1753,
|
|
"mean_token_accuracy": 0.12632442712783815,
|
|
"num_tokens": 2577706.0,
|
|
"step": 1485
|
|
},
|
|
{
|
|
"entropy": 6.441485500335693,
|
|
"epoch": 0.11593075277183428,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004999836729348584,
|
|
"loss": 6.2026,
|
|
"mean_token_accuracy": 0.1314474403858185,
|
|
"num_tokens": 2586075.0,
|
|
"step": 1490
|
|
},
|
|
{
|
|
"entropy": 6.376056575775147,
|
|
"epoch": 0.11631978214355183,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999833373452,
|
|
"loss": 6.2116,
|
|
"mean_token_accuracy": 0.12364233657717705,
|
|
"num_tokens": 2594965.0,
|
|
"step": 1495
|
|
},
|
|
{
|
|
"entropy": 6.444352674484253,
|
|
"epoch": 0.1167088115152694,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004999829983417778,
|
|
"loss": 6.1165,
|
|
"mean_token_accuracy": 0.13220934048295022,
|
|
"num_tokens": 2603355.0,
|
|
"step": 1500
|
|
},
|
|
{
|
|
"entropy": 6.441127586364746,
|
|
"epoch": 0.11709784088698696,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999826559245965,
|
|
"loss": 6.2668,
|
|
"mean_token_accuracy": 0.12569701820611953,
|
|
"num_tokens": 2611697.0,
|
|
"step": 1505
|
|
},
|
|
{
|
|
"entropy": 6.447865724563599,
|
|
"epoch": 0.11748687025870454,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999823100936615,
|
|
"loss": 6.145,
|
|
"mean_token_accuracy": 0.13168494999408722,
|
|
"num_tokens": 2620821.0,
|
|
"step": 1510
|
|
},
|
|
{
|
|
"entropy": 6.413182401657105,
|
|
"epoch": 0.1178758996304221,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004999819608489781,
|
|
"loss": 6.139,
|
|
"mean_token_accuracy": 0.12816296517848969,
|
|
"num_tokens": 2628891.0,
|
|
"step": 1515
|
|
},
|
|
{
|
|
"entropy": 6.4053560256958,
|
|
"epoch": 0.11826492900213967,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999816081905515,
|
|
"loss": 6.2701,
|
|
"mean_token_accuracy": 0.12410432398319245,
|
|
"num_tokens": 2638641.0,
|
|
"step": 1520
|
|
},
|
|
{
|
|
"entropy": 6.446357250213623,
|
|
"epoch": 0.11865395837385723,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004999812521183872,
|
|
"loss": 6.1571,
|
|
"mean_token_accuracy": 0.12258520424365997,
|
|
"num_tokens": 2646898.0,
|
|
"step": 1525
|
|
},
|
|
{
|
|
"entropy": 6.494231557846069,
|
|
"epoch": 0.11904298774557479,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004999808926324903,
|
|
"loss": 6.2181,
|
|
"mean_token_accuracy": 0.11994621977210045,
|
|
"num_tokens": 2655404.0,
|
|
"step": 1530
|
|
},
|
|
{
|
|
"entropy": 6.3410632610321045,
|
|
"epoch": 0.11943201711729236,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999805297328665,
|
|
"loss": 6.0821,
|
|
"mean_token_accuracy": 0.13641492202877997,
|
|
"num_tokens": 2663851.0,
|
|
"step": 1535
|
|
},
|
|
{
|
|
"entropy": 6.395636558532715,
|
|
"epoch": 0.11982104648900992,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004999801634195214,
|
|
"loss": 6.1436,
|
|
"mean_token_accuracy": 0.12901071980595588,
|
|
"num_tokens": 2672231.0,
|
|
"step": 1540
|
|
},
|
|
{
|
|
"entropy": 6.345880556106567,
|
|
"epoch": 0.12021007586072749,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999797936924603,
|
|
"loss": 6.1482,
|
|
"mean_token_accuracy": 0.13240571096539497,
|
|
"num_tokens": 2680198.0,
|
|
"step": 1545
|
|
},
|
|
{
|
|
"entropy": 6.534345436096191,
|
|
"epoch": 0.12059910523244505,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000499979420551689,
|
|
"loss": 6.18,
|
|
"mean_token_accuracy": 0.12448744922876358,
|
|
"num_tokens": 2689208.0,
|
|
"step": 1550
|
|
},
|
|
{
|
|
"entropy": 6.408984041213989,
|
|
"epoch": 0.12098813460416262,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000499979043997213,
|
|
"loss": 6.2361,
|
|
"mean_token_accuracy": 0.1251956507563591,
|
|
"num_tokens": 2698116.0,
|
|
"step": 1555
|
|
},
|
|
{
|
|
"entropy": 6.381083917617798,
|
|
"epoch": 0.12137716397588018,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999786640290381,
|
|
"loss": 6.1402,
|
|
"mean_token_accuracy": 0.12055975571274757,
|
|
"num_tokens": 2707046.0,
|
|
"step": 1560
|
|
},
|
|
{
|
|
"entropy": 6.352626132965088,
|
|
"epoch": 0.12176619334759774,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999782806471701,
|
|
"loss": 6.1304,
|
|
"mean_token_accuracy": 0.12507664933800697,
|
|
"num_tokens": 2714929.0,
|
|
"step": 1565
|
|
},
|
|
{
|
|
"entropy": 6.367618370056152,
|
|
"epoch": 0.12215522271931531,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999778938516147,
|
|
"loss": 6.1508,
|
|
"mean_token_accuracy": 0.1280180834233761,
|
|
"num_tokens": 2723436.0,
|
|
"step": 1570
|
|
},
|
|
{
|
|
"entropy": 6.3616029739379885,
|
|
"epoch": 0.12254425209103287,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000499977503642378,
|
|
"loss": 6.1914,
|
|
"mean_token_accuracy": 0.12718005925416948,
|
|
"num_tokens": 2731935.0,
|
|
"step": 1575
|
|
},
|
|
{
|
|
"entropy": 6.357917261123657,
|
|
"epoch": 0.12293328146275044,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999771100194656,
|
|
"loss": 6.03,
|
|
"mean_token_accuracy": 0.13522375822067262,
|
|
"num_tokens": 2740307.0,
|
|
"step": 1580
|
|
},
|
|
{
|
|
"entropy": 6.297295475006104,
|
|
"epoch": 0.123322310834468,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999767129828837,
|
|
"loss": 6.0432,
|
|
"mean_token_accuracy": 0.13734385818243028,
|
|
"num_tokens": 2749077.0,
|
|
"step": 1585
|
|
},
|
|
{
|
|
"entropy": 6.373191833496094,
|
|
"epoch": 0.12371134020618557,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999763125326383,
|
|
"loss": 6.171,
|
|
"mean_token_accuracy": 0.12406648844480514,
|
|
"num_tokens": 2758133.0,
|
|
"step": 1590
|
|
},
|
|
{
|
|
"entropy": 6.403712177276612,
|
|
"epoch": 0.12410036957790313,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004999759086687355,
|
|
"loss": 6.0809,
|
|
"mean_token_accuracy": 0.13498054668307305,
|
|
"num_tokens": 2766509.0,
|
|
"step": 1595
|
|
},
|
|
{
|
|
"entropy": 6.323156118392944,
|
|
"epoch": 0.1244893989496207,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999755013911813,
|
|
"loss": 6.2524,
|
|
"mean_token_accuracy": 0.12937115207314492,
|
|
"num_tokens": 2775908.0,
|
|
"step": 1600
|
|
},
|
|
{
|
|
"entropy": 6.363321352005005,
|
|
"epoch": 0.12487842832133826,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000499975090699982,
|
|
"loss": 6.0216,
|
|
"mean_token_accuracy": 0.13876289501786232,
|
|
"num_tokens": 2784803.0,
|
|
"step": 1605
|
|
},
|
|
{
|
|
"entropy": 6.361731815338135,
|
|
"epoch": 0.12526745769305583,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999746765951438,
|
|
"loss": 6.1877,
|
|
"mean_token_accuracy": 0.12857512682676314,
|
|
"num_tokens": 2793897.0,
|
|
"step": 1610
|
|
},
|
|
{
|
|
"entropy": 6.381125402450562,
|
|
"epoch": 0.1256564870647734,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999742590766729,
|
|
"loss": 6.0135,
|
|
"mean_token_accuracy": 0.1335058644413948,
|
|
"num_tokens": 2802652.0,
|
|
"step": 1615
|
|
},
|
|
{
|
|
"entropy": 6.288719320297242,
|
|
"epoch": 0.12604551643649095,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004999738381445757,
|
|
"loss": 6.1555,
|
|
"mean_token_accuracy": 0.12538140416145324,
|
|
"num_tokens": 2811527.0,
|
|
"step": 1620
|
|
},
|
|
{
|
|
"entropy": 6.426501035690308,
|
|
"epoch": 0.1264345458082085,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004999734137988586,
|
|
"loss": 6.0233,
|
|
"mean_token_accuracy": 0.13478974401950836,
|
|
"num_tokens": 2819410.0,
|
|
"step": 1625
|
|
},
|
|
{
|
|
"entropy": 6.1437897205352785,
|
|
"epoch": 0.1268235751799261,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000499972986039528,
|
|
"loss": 6.0193,
|
|
"mean_token_accuracy": 0.1394945725798607,
|
|
"num_tokens": 2828079.0,
|
|
"step": 1630
|
|
},
|
|
{
|
|
"entropy": 6.358804178237915,
|
|
"epoch": 0.12721260455164365,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999725548665904,
|
|
"loss": 6.125,
|
|
"mean_token_accuracy": 0.13202060833573342,
|
|
"num_tokens": 2836326.0,
|
|
"step": 1635
|
|
},
|
|
{
|
|
"entropy": 6.331844520568848,
|
|
"epoch": 0.1276016339233612,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999721202800524,
|
|
"loss": 6.1777,
|
|
"mean_token_accuracy": 0.12176662310957909,
|
|
"num_tokens": 2845271.0,
|
|
"step": 1640
|
|
},
|
|
{
|
|
"entropy": 6.287081146240235,
|
|
"epoch": 0.12799066329507877,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999716822799206,
|
|
"loss": 6.0484,
|
|
"mean_token_accuracy": 0.13889054954051971,
|
|
"num_tokens": 2853688.0,
|
|
"step": 1645
|
|
},
|
|
{
|
|
"entropy": 6.34264121055603,
|
|
"epoch": 0.12837969266679633,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999712408662016,
|
|
"loss": 6.1345,
|
|
"mean_token_accuracy": 0.13189240470528601,
|
|
"num_tokens": 2862261.0,
|
|
"step": 1650
|
|
},
|
|
{
|
|
"entropy": 6.361407041549683,
|
|
"epoch": 0.12876872203851392,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999707960389021,
|
|
"loss": 6.1623,
|
|
"mean_token_accuracy": 0.12860116735100746,
|
|
"num_tokens": 2871324.0,
|
|
"step": 1655
|
|
},
|
|
{
|
|
"entropy": 6.39573564529419,
|
|
"epoch": 0.12915775141023147,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999703477980288,
|
|
"loss": 6.2068,
|
|
"mean_token_accuracy": 0.12376175597310066,
|
|
"num_tokens": 2880268.0,
|
|
"step": 1660
|
|
},
|
|
{
|
|
"entropy": 6.376931095123291,
|
|
"epoch": 0.12954678078194903,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999698961435885,
|
|
"loss": 6.1084,
|
|
"mean_token_accuracy": 0.13345540538430214,
|
|
"num_tokens": 2888510.0,
|
|
"step": 1665
|
|
},
|
|
{
|
|
"entropy": 6.306573915481567,
|
|
"epoch": 0.1299358101536666,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999694410755882,
|
|
"loss": 6.0144,
|
|
"mean_token_accuracy": 0.14056088551878929,
|
|
"num_tokens": 2897616.0,
|
|
"step": 1670
|
|
},
|
|
{
|
|
"entropy": 6.2575867652893065,
|
|
"epoch": 0.13032483952538418,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999689825940347,
|
|
"loss": 6.0963,
|
|
"mean_token_accuracy": 0.13638013154268264,
|
|
"num_tokens": 2905703.0,
|
|
"step": 1675
|
|
},
|
|
{
|
|
"entropy": 6.297283267974853,
|
|
"epoch": 0.13071386889710174,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999685206989349,
|
|
"loss": 5.9894,
|
|
"mean_token_accuracy": 0.13844015896320344,
|
|
"num_tokens": 2914881.0,
|
|
"step": 1680
|
|
},
|
|
{
|
|
"entropy": 6.246834802627563,
|
|
"epoch": 0.1311028982688193,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999680553902959,
|
|
"loss": 6.0484,
|
|
"mean_token_accuracy": 0.1338697463274002,
|
|
"num_tokens": 2923563.0,
|
|
"step": 1685
|
|
},
|
|
{
|
|
"entropy": 6.416929101943969,
|
|
"epoch": 0.13149192764053685,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999675866681247,
|
|
"loss": 6.2635,
|
|
"mean_token_accuracy": 0.12606729716062545,
|
|
"num_tokens": 2932821.0,
|
|
"step": 1690
|
|
},
|
|
{
|
|
"entropy": 6.340527868270874,
|
|
"epoch": 0.1318809570122544,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999671145324286,
|
|
"loss": 6.1476,
|
|
"mean_token_accuracy": 0.13183779865503312,
|
|
"num_tokens": 2940926.0,
|
|
"step": 1695
|
|
},
|
|
{
|
|
"entropy": 6.358092355728149,
|
|
"epoch": 0.132269986383972,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999666389832144,
|
|
"loss": 6.0869,
|
|
"mean_token_accuracy": 0.13578122183680535,
|
|
"num_tokens": 2950028.0,
|
|
"step": 1700
|
|
},
|
|
{
|
|
"entropy": 6.280818748474121,
|
|
"epoch": 0.13265901575568956,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004999661600204897,
|
|
"loss": 6.1048,
|
|
"mean_token_accuracy": 0.13189996257424355,
|
|
"num_tokens": 2957636.0,
|
|
"step": 1705
|
|
},
|
|
{
|
|
"entropy": 6.183881616592407,
|
|
"epoch": 0.13304804512740712,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999656776442615,
|
|
"loss": 5.8677,
|
|
"mean_token_accuracy": 0.13509365245699884,
|
|
"num_tokens": 2966544.0,
|
|
"step": 1710
|
|
},
|
|
{
|
|
"entropy": 6.306702184677124,
|
|
"epoch": 0.13343707449912467,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999651918545372,
|
|
"loss": 6.1133,
|
|
"mean_token_accuracy": 0.1262418359518051,
|
|
"num_tokens": 2976236.0,
|
|
"step": 1715
|
|
},
|
|
{
|
|
"entropy": 6.283322811126709,
|
|
"epoch": 0.13382610387084226,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004999647026513243,
|
|
"loss": 6.0487,
|
|
"mean_token_accuracy": 0.1375434212386608,
|
|
"num_tokens": 2984261.0,
|
|
"step": 1720
|
|
},
|
|
{
|
|
"entropy": 6.210408878326416,
|
|
"epoch": 0.13421513324255982,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00049996421003463,
|
|
"loss": 6.0494,
|
|
"mean_token_accuracy": 0.13253966495394706,
|
|
"num_tokens": 2992970.0,
|
|
"step": 1725
|
|
},
|
|
{
|
|
"entropy": 6.381523132324219,
|
|
"epoch": 0.13460416261427738,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004999637140044619,
|
|
"loss": 6.0525,
|
|
"mean_token_accuracy": 0.13889826759696006,
|
|
"num_tokens": 3001356.0,
|
|
"step": 1730
|
|
},
|
|
{
|
|
"entropy": 6.240667819976807,
|
|
"epoch": 0.13499319198599494,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999632145608275,
|
|
"loss": 6.0844,
|
|
"mean_token_accuracy": 0.13955168649554253,
|
|
"num_tokens": 3009509.0,
|
|
"step": 1735
|
|
},
|
|
{
|
|
"entropy": 6.309776020050049,
|
|
"epoch": 0.1353822213577125,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999627117037343,
|
|
"loss": 6.0914,
|
|
"mean_token_accuracy": 0.12833233550190926,
|
|
"num_tokens": 3017675.0,
|
|
"step": 1740
|
|
},
|
|
{
|
|
"entropy": 6.2961413860321045,
|
|
"epoch": 0.13577125072943008,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00049996220543319,
|
|
"loss": 6.0664,
|
|
"mean_token_accuracy": 0.13567132800817489,
|
|
"num_tokens": 3025527.0,
|
|
"step": 1745
|
|
},
|
|
{
|
|
"entropy": 6.275249338150024,
|
|
"epoch": 0.13616028010114764,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999616957492025,
|
|
"loss": 6.0121,
|
|
"mean_token_accuracy": 0.1365427479147911,
|
|
"num_tokens": 3034251.0,
|
|
"step": 1750
|
|
},
|
|
{
|
|
"entropy": 6.229633617401123,
|
|
"epoch": 0.1365493094728652,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999611826517793,
|
|
"loss": 6.2377,
|
|
"mean_token_accuracy": 0.12501248195767403,
|
|
"num_tokens": 3043272.0,
|
|
"step": 1755
|
|
},
|
|
{
|
|
"entropy": 6.347791910171509,
|
|
"epoch": 0.13693833884458276,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999606661409281,
|
|
"loss": 6.0884,
|
|
"mean_token_accuracy": 0.1348442792892456,
|
|
"num_tokens": 3051092.0,
|
|
"step": 1760
|
|
},
|
|
{
|
|
"entropy": 6.319974565505982,
|
|
"epoch": 0.13732736821630034,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999601462166569,
|
|
"loss": 6.0594,
|
|
"mean_token_accuracy": 0.1309550181031227,
|
|
"num_tokens": 3060584.0,
|
|
"step": 1765
|
|
},
|
|
{
|
|
"entropy": 6.226590776443482,
|
|
"epoch": 0.1377163975880179,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999596228789736,
|
|
"loss": 6.0635,
|
|
"mean_token_accuracy": 0.13423156440258027,
|
|
"num_tokens": 3069990.0,
|
|
"step": 1770
|
|
},
|
|
{
|
|
"entropy": 6.335338115692139,
|
|
"epoch": 0.13810542695973546,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999590961278859,
|
|
"loss": 6.0482,
|
|
"mean_token_accuracy": 0.13068760186433792,
|
|
"num_tokens": 3078837.0,
|
|
"step": 1775
|
|
},
|
|
{
|
|
"entropy": 6.172453451156616,
|
|
"epoch": 0.13849445633145302,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999585659634021,
|
|
"loss": 6.0316,
|
|
"mean_token_accuracy": 0.1395242527127266,
|
|
"num_tokens": 3087557.0,
|
|
"step": 1780
|
|
},
|
|
{
|
|
"entropy": 6.260955667495727,
|
|
"epoch": 0.13888348570317058,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999580323855301,
|
|
"loss": 6.0262,
|
|
"mean_token_accuracy": 0.13657170236110688,
|
|
"num_tokens": 3096524.0,
|
|
"step": 1785
|
|
},
|
|
{
|
|
"entropy": 6.351543807983399,
|
|
"epoch": 0.13927251507488816,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999574953942781,
|
|
"loss": 6.1139,
|
|
"mean_token_accuracy": 0.1336659722030163,
|
|
"num_tokens": 3105271.0,
|
|
"step": 1790
|
|
},
|
|
{
|
|
"entropy": 6.237719345092773,
|
|
"epoch": 0.13966154444660572,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999569549896541,
|
|
"loss": 5.9924,
|
|
"mean_token_accuracy": 0.1303889974951744,
|
|
"num_tokens": 3114479.0,
|
|
"step": 1795
|
|
},
|
|
{
|
|
"entropy": 6.231583595275879,
|
|
"epoch": 0.14005057381832328,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999564111716665,
|
|
"loss": 6.0071,
|
|
"mean_token_accuracy": 0.14318212792277335,
|
|
"num_tokens": 3123319.0,
|
|
"step": 1800
|
|
},
|
|
{
|
|
"entropy": 6.270225238800049,
|
|
"epoch": 0.14043960319004084,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999558639403232,
|
|
"loss": 6.0457,
|
|
"mean_token_accuracy": 0.13263603895902634,
|
|
"num_tokens": 3132532.0,
|
|
"step": 1805
|
|
},
|
|
{
|
|
"entropy": 6.358526659011841,
|
|
"epoch": 0.1408286325617584,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999553132956328,
|
|
"loss": 6.1067,
|
|
"mean_token_accuracy": 0.13037939891219139,
|
|
"num_tokens": 3140798.0,
|
|
"step": 1810
|
|
},
|
|
{
|
|
"entropy": 6.238439464569092,
|
|
"epoch": 0.14121766193347599,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999547592376035,
|
|
"loss": 6.0901,
|
|
"mean_token_accuracy": 0.13772427588701247,
|
|
"num_tokens": 3149607.0,
|
|
"step": 1815
|
|
},
|
|
{
|
|
"entropy": 6.2145038604736325,
|
|
"epoch": 0.14160669130519354,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004999542017662438,
|
|
"loss": 5.9226,
|
|
"mean_token_accuracy": 0.14179680794477462,
|
|
"num_tokens": 3157537.0,
|
|
"step": 1820
|
|
},
|
|
{
|
|
"entropy": 6.2342335224151615,
|
|
"epoch": 0.1419957206769111,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004999536408815623,
|
|
"loss": 6.0715,
|
|
"mean_token_accuracy": 0.1310746893286705,
|
|
"num_tokens": 3166351.0,
|
|
"step": 1825
|
|
},
|
|
{
|
|
"entropy": 6.177899360656738,
|
|
"epoch": 0.14238475004862866,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999530765835672,
|
|
"loss": 5.935,
|
|
"mean_token_accuracy": 0.14044117629528047,
|
|
"num_tokens": 3174690.0,
|
|
"step": 1830
|
|
},
|
|
{
|
|
"entropy": 6.239687252044678,
|
|
"epoch": 0.14277377942034625,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999525088722673,
|
|
"loss": 6.0764,
|
|
"mean_token_accuracy": 0.12794848904013634,
|
|
"num_tokens": 3183460.0,
|
|
"step": 1835
|
|
},
|
|
{
|
|
"entropy": 6.237521076202393,
|
|
"epoch": 0.1431628087920638,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999519377476711,
|
|
"loss": 6.0105,
|
|
"mean_token_accuracy": 0.13746723383665085,
|
|
"num_tokens": 3192183.0,
|
|
"step": 1840
|
|
},
|
|
{
|
|
"entropy": 6.266400766372681,
|
|
"epoch": 0.14355183816378136,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999513632097872,
|
|
"loss": 6.0966,
|
|
"mean_token_accuracy": 0.13392534032464026,
|
|
"num_tokens": 3200875.0,
|
|
"step": 1845
|
|
},
|
|
{
|
|
"entropy": 6.223610925674438,
|
|
"epoch": 0.14394086753549892,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999507852586245,
|
|
"loss": 5.9609,
|
|
"mean_token_accuracy": 0.13770486116409303,
|
|
"num_tokens": 3209797.0,
|
|
"step": 1850
|
|
},
|
|
{
|
|
"entropy": 6.276148748397827,
|
|
"epoch": 0.14432989690721648,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999502038941917,
|
|
"loss": 6.0793,
|
|
"mean_token_accuracy": 0.13013245537877083,
|
|
"num_tokens": 3218612.0,
|
|
"step": 1855
|
|
},
|
|
{
|
|
"entropy": 6.2181178569793705,
|
|
"epoch": 0.14471892627893407,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999496191164975,
|
|
"loss": 5.9958,
|
|
"mean_token_accuracy": 0.13566022291779517,
|
|
"num_tokens": 3227364.0,
|
|
"step": 1860
|
|
},
|
|
{
|
|
"entropy": 6.176430511474609,
|
|
"epoch": 0.14510795565065163,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000499949030925551,
|
|
"loss": 6.0201,
|
|
"mean_token_accuracy": 0.13599291145801545,
|
|
"num_tokens": 3236448.0,
|
|
"step": 1865
|
|
},
|
|
{
|
|
"entropy": 6.254899358749389,
|
|
"epoch": 0.14549698502236919,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999484393213609,
|
|
"loss": 5.9486,
|
|
"mean_token_accuracy": 0.1352322556078434,
|
|
"num_tokens": 3244957.0,
|
|
"step": 1870
|
|
},
|
|
{
|
|
"entropy": 6.109967184066773,
|
|
"epoch": 0.14588601439408674,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999478443039363,
|
|
"loss": 6.0408,
|
|
"mean_token_accuracy": 0.1295456551015377,
|
|
"num_tokens": 3253250.0,
|
|
"step": 1875
|
|
},
|
|
{
|
|
"entropy": 6.2762659072875975,
|
|
"epoch": 0.14627504376580433,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999472458732862,
|
|
"loss": 5.943,
|
|
"mean_token_accuracy": 0.14542312696576118,
|
|
"num_tokens": 3261455.0,
|
|
"step": 1880
|
|
},
|
|
{
|
|
"entropy": 6.1596604347229,
|
|
"epoch": 0.1466640731375219,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999466440294198,
|
|
"loss": 5.9906,
|
|
"mean_token_accuracy": 0.13770747035741807,
|
|
"num_tokens": 3270108.0,
|
|
"step": 1885
|
|
},
|
|
{
|
|
"entropy": 6.310276889801026,
|
|
"epoch": 0.14705310250923945,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000499946038772346,
|
|
"loss": 6.1231,
|
|
"mean_token_accuracy": 0.13440992087125778,
|
|
"num_tokens": 3278425.0,
|
|
"step": 1890
|
|
},
|
|
{
|
|
"entropy": 6.235618352890015,
|
|
"epoch": 0.147442131880957,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999454301020741,
|
|
"loss": 6.0429,
|
|
"mean_token_accuracy": 0.13205524757504464,
|
|
"num_tokens": 3288358.0,
|
|
"step": 1895
|
|
},
|
|
{
|
|
"entropy": 6.265941572189331,
|
|
"epoch": 0.14783116125267456,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004999448180186133,
|
|
"loss": 6.039,
|
|
"mean_token_accuracy": 0.1352785974740982,
|
|
"num_tokens": 3297199.0,
|
|
"step": 1900
|
|
},
|
|
{
|
|
"entropy": 6.18539137840271,
|
|
"epoch": 0.14822019062439215,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000499944202521973,
|
|
"loss": 6.047,
|
|
"mean_token_accuracy": 0.13134037628769873,
|
|
"num_tokens": 3306350.0,
|
|
"step": 1905
|
|
},
|
|
{
|
|
"entropy": 6.20574164390564,
|
|
"epoch": 0.1486092199961097,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999435836121624,
|
|
"loss": 5.8873,
|
|
"mean_token_accuracy": 0.13750338256359101,
|
|
"num_tokens": 3314921.0,
|
|
"step": 1910
|
|
},
|
|
{
|
|
"entropy": 6.084950733184814,
|
|
"epoch": 0.14899824936782727,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000499942961289191,
|
|
"loss": 6.018,
|
|
"mean_token_accuracy": 0.14249766021966934,
|
|
"num_tokens": 3323324.0,
|
|
"step": 1915
|
|
},
|
|
{
|
|
"entropy": 6.381536149978638,
|
|
"epoch": 0.14938727873954483,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004999423355530683,
|
|
"loss": 6.1469,
|
|
"mean_token_accuracy": 0.13054955527186393,
|
|
"num_tokens": 3331614.0,
|
|
"step": 1920
|
|
},
|
|
{
|
|
"entropy": 6.248685646057129,
|
|
"epoch": 0.1497763081112624,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004999417064038035,
|
|
"loss": 5.9945,
|
|
"mean_token_accuracy": 0.13594073355197905,
|
|
"num_tokens": 3339573.0,
|
|
"step": 1925
|
|
},
|
|
{
|
|
"entropy": 6.163447618484497,
|
|
"epoch": 0.15016533748297997,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004999410738414065,
|
|
"loss": 5.9538,
|
|
"mean_token_accuracy": 0.14307861253619195,
|
|
"num_tokens": 3347775.0,
|
|
"step": 1930
|
|
},
|
|
{
|
|
"entropy": 6.200021457672119,
|
|
"epoch": 0.15055436685469753,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999404378658866,
|
|
"loss": 5.9128,
|
|
"mean_token_accuracy": 0.1373552069067955,
|
|
"num_tokens": 3356947.0,
|
|
"step": 1935
|
|
},
|
|
{
|
|
"entropy": 6.167617988586426,
|
|
"epoch": 0.1509433962264151,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999397984772536,
|
|
"loss": 6.0098,
|
|
"mean_token_accuracy": 0.13761954754590988,
|
|
"num_tokens": 3365420.0,
|
|
"step": 1940
|
|
},
|
|
{
|
|
"entropy": 6.2827473163604735,
|
|
"epoch": 0.15133242559813265,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999391556755172,
|
|
"loss": 6.1027,
|
|
"mean_token_accuracy": 0.13397282212972642,
|
|
"num_tokens": 3373483.0,
|
|
"step": 1945
|
|
},
|
|
{
|
|
"entropy": 6.290587139129639,
|
|
"epoch": 0.15172145496985023,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999385094606872,
|
|
"loss": 6.0892,
|
|
"mean_token_accuracy": 0.12818740382790567,
|
|
"num_tokens": 3382557.0,
|
|
"step": 1950
|
|
},
|
|
{
|
|
"entropy": 6.261412334442139,
|
|
"epoch": 0.1521104843415678,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999378598327733,
|
|
"loss": 6.0347,
|
|
"mean_token_accuracy": 0.12742510437965393,
|
|
"num_tokens": 3392079.0,
|
|
"step": 1955
|
|
},
|
|
{
|
|
"entropy": 6.222420072555542,
|
|
"epoch": 0.15249951371328535,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999372067917854,
|
|
"loss": 6.1003,
|
|
"mean_token_accuracy": 0.1310837060213089,
|
|
"num_tokens": 3401070.0,
|
|
"step": 1960
|
|
},
|
|
{
|
|
"entropy": 6.165682315826416,
|
|
"epoch": 0.1528885430850029,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999365503377335,
|
|
"loss": 5.9818,
|
|
"mean_token_accuracy": 0.13428688049316406,
|
|
"num_tokens": 3409921.0,
|
|
"step": 1965
|
|
},
|
|
{
|
|
"entropy": 6.244135046005249,
|
|
"epoch": 0.1532775724567205,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999358904706273,
|
|
"loss": 5.9986,
|
|
"mean_token_accuracy": 0.13104057684540749,
|
|
"num_tokens": 3419149.0,
|
|
"step": 1970
|
|
},
|
|
{
|
|
"entropy": 6.156588792800903,
|
|
"epoch": 0.15366660182843805,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004999352271904771,
|
|
"loss": 5.8891,
|
|
"mean_token_accuracy": 0.14492207542061805,
|
|
"num_tokens": 3427435.0,
|
|
"step": 1975
|
|
},
|
|
{
|
|
"entropy": 6.24048261642456,
|
|
"epoch": 0.1540556312001556,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004999345604972928,
|
|
"loss": 6.0975,
|
|
"mean_token_accuracy": 0.1309770740568638,
|
|
"num_tokens": 3436377.0,
|
|
"step": 1980
|
|
},
|
|
{
|
|
"entropy": 6.262222719192505,
|
|
"epoch": 0.15444466057187317,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999338903910846,
|
|
"loss": 5.966,
|
|
"mean_token_accuracy": 0.14030917212367058,
|
|
"num_tokens": 3444997.0,
|
|
"step": 1985
|
|
},
|
|
{
|
|
"entropy": 6.250793886184693,
|
|
"epoch": 0.15483368994359073,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999332168718626,
|
|
"loss": 6.0267,
|
|
"mean_token_accuracy": 0.13967675864696502,
|
|
"num_tokens": 3454254.0,
|
|
"step": 1990
|
|
},
|
|
{
|
|
"entropy": 6.192072057723999,
|
|
"epoch": 0.15522271931530832,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999325399396371,
|
|
"loss": 5.9984,
|
|
"mean_token_accuracy": 0.14047476574778556,
|
|
"num_tokens": 3462853.0,
|
|
"step": 1995
|
|
},
|
|
{
|
|
"entropy": 6.162121677398682,
|
|
"epoch": 0.15561174868702587,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999318595944183,
|
|
"loss": 5.951,
|
|
"mean_token_accuracy": 0.1363219663500786,
|
|
"num_tokens": 3471288.0,
|
|
"step": 2000
|
|
},
|
|
{
|
|
"entropy": 6.123317289352417,
|
|
"epoch": 0.15600077805874343,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999311758362166,
|
|
"loss": 5.8464,
|
|
"mean_token_accuracy": 0.13612058088183404,
|
|
"num_tokens": 3479479.0,
|
|
"step": 2005
|
|
},
|
|
{
|
|
"entropy": 6.14522500038147,
|
|
"epoch": 0.156389807430461,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999304886650422,
|
|
"loss": 5.8684,
|
|
"mean_token_accuracy": 0.1447673887014389,
|
|
"num_tokens": 3488621.0,
|
|
"step": 2010
|
|
},
|
|
{
|
|
"entropy": 6.089516735076904,
|
|
"epoch": 0.15677883680217858,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999297980809058,
|
|
"loss": 5.9238,
|
|
"mean_token_accuracy": 0.1373309776186943,
|
|
"num_tokens": 3497792.0,
|
|
"step": 2015
|
|
},
|
|
{
|
|
"entropy": 6.12142162322998,
|
|
"epoch": 0.15716786617389614,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004999291040838176,
|
|
"loss": 5.9522,
|
|
"mean_token_accuracy": 0.13544787019491195,
|
|
"num_tokens": 3506548.0,
|
|
"step": 2020
|
|
},
|
|
{
|
|
"entropy": 6.127046966552735,
|
|
"epoch": 0.1575568955456137,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999284066737884,
|
|
"loss": 5.932,
|
|
"mean_token_accuracy": 0.14313506335020065,
|
|
"num_tokens": 3515086.0,
|
|
"step": 2025
|
|
},
|
|
{
|
|
"entropy": 6.245706987380982,
|
|
"epoch": 0.15794592491733125,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999277058508285,
|
|
"loss": 5.9765,
|
|
"mean_token_accuracy": 0.1334720067679882,
|
|
"num_tokens": 3523985.0,
|
|
"step": 2030
|
|
},
|
|
{
|
|
"entropy": 6.193225526809693,
|
|
"epoch": 0.1583349542890488,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999270016149486,
|
|
"loss": 6.0321,
|
|
"mean_token_accuracy": 0.1414737358689308,
|
|
"num_tokens": 3532575.0,
|
|
"step": 2035
|
|
},
|
|
{
|
|
"entropy": 6.229839229583741,
|
|
"epoch": 0.1587239836607664,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999262939661596,
|
|
"loss": 6.0292,
|
|
"mean_token_accuracy": 0.13414048179984092,
|
|
"num_tokens": 3541558.0,
|
|
"step": 2040
|
|
},
|
|
{
|
|
"entropy": 6.1485107898712155,
|
|
"epoch": 0.15911301303248396,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999255829044721,
|
|
"loss": 5.9383,
|
|
"mean_token_accuracy": 0.1430905818939209,
|
|
"num_tokens": 3549697.0,
|
|
"step": 2045
|
|
},
|
|
{
|
|
"entropy": 6.240954160690308,
|
|
"epoch": 0.15950204240420152,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999248684298968,
|
|
"loss": 6.1118,
|
|
"mean_token_accuracy": 0.12798432558774947,
|
|
"num_tokens": 3558673.0,
|
|
"step": 2050
|
|
},
|
|
{
|
|
"entropy": 6.225488805770874,
|
|
"epoch": 0.15989107177591907,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999241505424447,
|
|
"loss": 5.963,
|
|
"mean_token_accuracy": 0.14219792932271957,
|
|
"num_tokens": 3567176.0,
|
|
"step": 2055
|
|
},
|
|
{
|
|
"entropy": 6.276889419555664,
|
|
"epoch": 0.16028010114763663,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999234292421265,
|
|
"loss": 6.0934,
|
|
"mean_token_accuracy": 0.13421509712934493,
|
|
"num_tokens": 3576020.0,
|
|
"step": 2060
|
|
},
|
|
{
|
|
"entropy": 6.121796798706055,
|
|
"epoch": 0.16066913051935422,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004999227045289535,
|
|
"loss": 5.9483,
|
|
"mean_token_accuracy": 0.13852609768509866,
|
|
"num_tokens": 3584705.0,
|
|
"step": 2065
|
|
},
|
|
{
|
|
"entropy": 6.239097929000854,
|
|
"epoch": 0.16105815989107178,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999219764029363,
|
|
"loss": 6.1251,
|
|
"mean_token_accuracy": 0.1327233374118805,
|
|
"num_tokens": 3593339.0,
|
|
"step": 2070
|
|
},
|
|
{
|
|
"entropy": 6.17981219291687,
|
|
"epoch": 0.16144718926278934,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999212448640861,
|
|
"loss": 5.8296,
|
|
"mean_token_accuracy": 0.14525919482111932,
|
|
"num_tokens": 3601206.0,
|
|
"step": 2075
|
|
},
|
|
{
|
|
"entropy": 6.023618602752686,
|
|
"epoch": 0.1618362186345069,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999205099124141,
|
|
"loss": 5.9556,
|
|
"mean_token_accuracy": 0.1340252086520195,
|
|
"num_tokens": 3610371.0,
|
|
"step": 2080
|
|
},
|
|
{
|
|
"entropy": 6.26896104812622,
|
|
"epoch": 0.16222524800622448,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999197715479313,
|
|
"loss": 5.9675,
|
|
"mean_token_accuracy": 0.13808080479502677,
|
|
"num_tokens": 3618834.0,
|
|
"step": 2085
|
|
},
|
|
{
|
|
"entropy": 6.081180000305176,
|
|
"epoch": 0.16261427737794204,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999190297706489,
|
|
"loss": 5.9999,
|
|
"mean_token_accuracy": 0.13936789706349373,
|
|
"num_tokens": 3627426.0,
|
|
"step": 2090
|
|
},
|
|
{
|
|
"entropy": 6.239403820037841,
|
|
"epoch": 0.1630033067496596,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999182845805783,
|
|
"loss": 6.0013,
|
|
"mean_token_accuracy": 0.13789541125297547,
|
|
"num_tokens": 3636020.0,
|
|
"step": 2095
|
|
},
|
|
{
|
|
"entropy": 6.242777967453003,
|
|
"epoch": 0.16339233612137716,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999175359777306,
|
|
"loss": 5.9419,
|
|
"mean_token_accuracy": 0.1419316790997982,
|
|
"num_tokens": 3644419.0,
|
|
"step": 2100
|
|
},
|
|
{
|
|
"entropy": 6.171798038482666,
|
|
"epoch": 0.16378136549309472,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999167839621174,
|
|
"loss": 6.043,
|
|
"mean_token_accuracy": 0.13091627210378648,
|
|
"num_tokens": 3653223.0,
|
|
"step": 2105
|
|
},
|
|
{
|
|
"entropy": 6.23285026550293,
|
|
"epoch": 0.1641703948648123,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999160285337501,
|
|
"loss": 6.062,
|
|
"mean_token_accuracy": 0.13183995485305786,
|
|
"num_tokens": 3662409.0,
|
|
"step": 2110
|
|
},
|
|
{
|
|
"entropy": 6.214762258529663,
|
|
"epoch": 0.16455942423652986,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004999152696926399,
|
|
"loss": 6.0226,
|
|
"mean_token_accuracy": 0.13156313672661782,
|
|
"num_tokens": 3670635.0,
|
|
"step": 2115
|
|
},
|
|
{
|
|
"entropy": 6.076648998260498,
|
|
"epoch": 0.16494845360824742,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999145074387985,
|
|
"loss": 5.9493,
|
|
"mean_token_accuracy": 0.14351119846105576,
|
|
"num_tokens": 3679303.0,
|
|
"step": 2120
|
|
},
|
|
{
|
|
"entropy": 6.297281312942505,
|
|
"epoch": 0.16533748297996498,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999137417722374,
|
|
"loss": 6.0999,
|
|
"mean_token_accuracy": 0.1333278849720955,
|
|
"num_tokens": 3689299.0,
|
|
"step": 2125
|
|
},
|
|
{
|
|
"entropy": 6.212060928344727,
|
|
"epoch": 0.16572651235168256,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999129726929684,
|
|
"loss": 6.0309,
|
|
"mean_token_accuracy": 0.141978856921196,
|
|
"num_tokens": 3697843.0,
|
|
"step": 2130
|
|
},
|
|
{
|
|
"entropy": 6.232631540298462,
|
|
"epoch": 0.16611554172340012,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999122002010029,
|
|
"loss": 5.9595,
|
|
"mean_token_accuracy": 0.13919129222631454,
|
|
"num_tokens": 3705876.0,
|
|
"step": 2135
|
|
},
|
|
{
|
|
"entropy": 6.192243671417236,
|
|
"epoch": 0.16650457109511768,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999114242963527,
|
|
"loss": 6.0811,
|
|
"mean_token_accuracy": 0.1308549664914608,
|
|
"num_tokens": 3714835.0,
|
|
"step": 2140
|
|
},
|
|
{
|
|
"entropy": 6.1568906784057615,
|
|
"epoch": 0.16689360046683524,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999106449790298,
|
|
"loss": 5.9421,
|
|
"mean_token_accuracy": 0.13271426409482956,
|
|
"num_tokens": 3723421.0,
|
|
"step": 2145
|
|
},
|
|
{
|
|
"entropy": 6.174701166152954,
|
|
"epoch": 0.1672826298385528,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999098622490458,
|
|
"loss": 5.9582,
|
|
"mean_token_accuracy": 0.1379171997308731,
|
|
"num_tokens": 3731590.0,
|
|
"step": 2150
|
|
},
|
|
{
|
|
"entropy": 6.0976481437683105,
|
|
"epoch": 0.16767165921027039,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999090761064125,
|
|
"loss": 5.8819,
|
|
"mean_token_accuracy": 0.1397905245423317,
|
|
"num_tokens": 3740700.0,
|
|
"step": 2155
|
|
},
|
|
{
|
|
"entropy": 6.141346263885498,
|
|
"epoch": 0.16806068858198794,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000499908286551142,
|
|
"loss": 5.9546,
|
|
"mean_token_accuracy": 0.14155428856611252,
|
|
"num_tokens": 3749516.0,
|
|
"step": 2160
|
|
},
|
|
{
|
|
"entropy": 6.109289598464966,
|
|
"epoch": 0.1684497179537055,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999074935832463,
|
|
"loss": 5.8731,
|
|
"mean_token_accuracy": 0.14581690207123757,
|
|
"num_tokens": 3757696.0,
|
|
"step": 2165
|
|
},
|
|
{
|
|
"entropy": 6.114305877685547,
|
|
"epoch": 0.16883874732542306,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999066972027373,
|
|
"loss": 5.9643,
|
|
"mean_token_accuracy": 0.13819186612963677,
|
|
"num_tokens": 3765786.0,
|
|
"step": 2170
|
|
},
|
|
{
|
|
"entropy": 6.129476547241211,
|
|
"epoch": 0.16922777669714065,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004999058974096271,
|
|
"loss": 5.8694,
|
|
"mean_token_accuracy": 0.14471860826015473,
|
|
"num_tokens": 3773265.0,
|
|
"step": 2175
|
|
},
|
|
{
|
|
"entropy": 6.109765338897705,
|
|
"epoch": 0.1696168060688582,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000499905094203928,
|
|
"loss": 5.9872,
|
|
"mean_token_accuracy": 0.13433021679520607,
|
|
"num_tokens": 3782402.0,
|
|
"step": 2180
|
|
},
|
|
{
|
|
"entropy": 6.180309247970581,
|
|
"epoch": 0.17000583544057576,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000499904287585652,
|
|
"loss": 6.0514,
|
|
"mean_token_accuracy": 0.1314002774655819,
|
|
"num_tokens": 3791901.0,
|
|
"step": 2185
|
|
},
|
|
{
|
|
"entropy": 6.139549350738525,
|
|
"epoch": 0.17039486481229332,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999034775548113,
|
|
"loss": 5.8778,
|
|
"mean_token_accuracy": 0.14060187861323356,
|
|
"num_tokens": 3799872.0,
|
|
"step": 2190
|
|
},
|
|
{
|
|
"entropy": 6.106409025192261,
|
|
"epoch": 0.17078389418401088,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999026641114185,
|
|
"loss": 5.8323,
|
|
"mean_token_accuracy": 0.14609502255916595,
|
|
"num_tokens": 3808949.0,
|
|
"step": 2195
|
|
},
|
|
{
|
|
"entropy": 6.121867275238037,
|
|
"epoch": 0.17117292355572847,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999018472554857,
|
|
"loss": 5.9466,
|
|
"mean_token_accuracy": 0.13920955061912538,
|
|
"num_tokens": 3817429.0,
|
|
"step": 2200
|
|
},
|
|
{
|
|
"entropy": 6.264400291442871,
|
|
"epoch": 0.17156195292744603,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999010269870253,
|
|
"loss": 6.2252,
|
|
"mean_token_accuracy": 0.12967248037457466,
|
|
"num_tokens": 3827101.0,
|
|
"step": 2205
|
|
},
|
|
{
|
|
"entropy": 6.248671436309815,
|
|
"epoch": 0.17195098229916359,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999002033060498,
|
|
"loss": 5.9701,
|
|
"mean_token_accuracy": 0.13611226081848143,
|
|
"num_tokens": 3836147.0,
|
|
"step": 2210
|
|
},
|
|
{
|
|
"entropy": 6.070646286010742,
|
|
"epoch": 0.17234001167088114,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998993762125716,
|
|
"loss": 5.9555,
|
|
"mean_token_accuracy": 0.1376994989812374,
|
|
"num_tokens": 3845300.0,
|
|
"step": 2215
|
|
},
|
|
{
|
|
"entropy": 6.248652124404908,
|
|
"epoch": 0.17272904104259873,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004998985457066034,
|
|
"loss": 5.9556,
|
|
"mean_token_accuracy": 0.14077395275235177,
|
|
"num_tokens": 3853620.0,
|
|
"step": 2220
|
|
},
|
|
{
|
|
"entropy": 6.078034114837647,
|
|
"epoch": 0.1731180704143163,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004998977117881576,
|
|
"loss": 5.952,
|
|
"mean_token_accuracy": 0.14219790250062941,
|
|
"num_tokens": 3861734.0,
|
|
"step": 2225
|
|
},
|
|
{
|
|
"entropy": 6.147058439254761,
|
|
"epoch": 0.17350709978603385,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998968744572472,
|
|
"loss": 5.9706,
|
|
"mean_token_accuracy": 0.13935380205512046,
|
|
"num_tokens": 3870753.0,
|
|
"step": 2230
|
|
},
|
|
{
|
|
"entropy": 6.128642892837524,
|
|
"epoch": 0.1738961291577514,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998960337138845,
|
|
"loss": 5.852,
|
|
"mean_token_accuracy": 0.14278298988938332,
|
|
"num_tokens": 3879382.0,
|
|
"step": 2235
|
|
},
|
|
{
|
|
"entropy": 6.17204442024231,
|
|
"epoch": 0.17428515852946896,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004998951895580826,
|
|
"loss": 6.0249,
|
|
"mean_token_accuracy": 0.13453888818621634,
|
|
"num_tokens": 3888417.0,
|
|
"step": 2240
|
|
},
|
|
{
|
|
"entropy": 6.054234218597412,
|
|
"epoch": 0.17467418790118655,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004998943419898542,
|
|
"loss": 5.8813,
|
|
"mean_token_accuracy": 0.1384780913591385,
|
|
"num_tokens": 3897083.0,
|
|
"step": 2245
|
|
},
|
|
{
|
|
"entropy": 6.077237939834594,
|
|
"epoch": 0.1750632172729041,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998934910092119,
|
|
"loss": 5.8526,
|
|
"mean_token_accuracy": 0.14408235251903534,
|
|
"num_tokens": 3905564.0,
|
|
"step": 2250
|
|
},
|
|
{
|
|
"entropy": 6.146784496307373,
|
|
"epoch": 0.17545224664462167,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998926366161689,
|
|
"loss": 5.9942,
|
|
"mean_token_accuracy": 0.13211930319666862,
|
|
"num_tokens": 3914896.0,
|
|
"step": 2255
|
|
},
|
|
{
|
|
"entropy": 6.1404224872589115,
|
|
"epoch": 0.17584127601633923,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998917788107383,
|
|
"loss": 5.9972,
|
|
"mean_token_accuracy": 0.13836849108338356,
|
|
"num_tokens": 3924151.0,
|
|
"step": 2260
|
|
},
|
|
{
|
|
"entropy": 6.213042545318603,
|
|
"epoch": 0.17623030538805678,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998909175929326,
|
|
"loss": 5.9462,
|
|
"mean_token_accuracy": 0.13971734270453454,
|
|
"num_tokens": 3933163.0,
|
|
"step": 2265
|
|
},
|
|
{
|
|
"entropy": 6.098297929763794,
|
|
"epoch": 0.17661933475977437,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004998900529627653,
|
|
"loss": 5.8671,
|
|
"mean_token_accuracy": 0.14396204575896263,
|
|
"num_tokens": 3941120.0,
|
|
"step": 2270
|
|
},
|
|
{
|
|
"entropy": 5.991336631774902,
|
|
"epoch": 0.17700836413149193,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998891849202495,
|
|
"loss": 5.7531,
|
|
"mean_token_accuracy": 0.1438086897134781,
|
|
"num_tokens": 3949896.0,
|
|
"step": 2275
|
|
},
|
|
{
|
|
"entropy": 6.120736980438233,
|
|
"epoch": 0.1773973935032095,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000499888313465398,
|
|
"loss": 5.9127,
|
|
"mean_token_accuracy": 0.13862551301717757,
|
|
"num_tokens": 3958794.0,
|
|
"step": 2280
|
|
},
|
|
{
|
|
"entropy": 6.140617322921753,
|
|
"epoch": 0.17778642287492705,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004998874385982247,
|
|
"loss": 5.9773,
|
|
"mean_token_accuracy": 0.14108967706561087,
|
|
"num_tokens": 3967267.0,
|
|
"step": 2285
|
|
},
|
|
{
|
|
"entropy": 6.083899354934692,
|
|
"epoch": 0.17817545224664463,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004998865603187421,
|
|
"loss": 5.892,
|
|
"mean_token_accuracy": 0.14135736748576164,
|
|
"num_tokens": 3976536.0,
|
|
"step": 2290
|
|
},
|
|
{
|
|
"entropy": 6.207363796234131,
|
|
"epoch": 0.1785644816183622,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000499885678626964,
|
|
"loss": 5.9564,
|
|
"mean_token_accuracy": 0.13729356452822686,
|
|
"num_tokens": 3986006.0,
|
|
"step": 2295
|
|
},
|
|
{
|
|
"entropy": 6.016284608840943,
|
|
"epoch": 0.17895351099007975,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004998847935229038,
|
|
"loss": 5.9038,
|
|
"mean_token_accuracy": 0.1368868224322796,
|
|
"num_tokens": 3994478.0,
|
|
"step": 2300
|
|
},
|
|
{
|
|
"entropy": 6.116120862960815,
|
|
"epoch": 0.1793425403617973,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998839050065746,
|
|
"loss": 5.9516,
|
|
"mean_token_accuracy": 0.1373460717499256,
|
|
"num_tokens": 4003190.0,
|
|
"step": 2305
|
|
},
|
|
{
|
|
"entropy": 6.196177530288696,
|
|
"epoch": 0.17973156973351487,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004998830130779902,
|
|
"loss": 5.8728,
|
|
"mean_token_accuracy": 0.1443126007914543,
|
|
"num_tokens": 4011886.0,
|
|
"step": 2310
|
|
},
|
|
{
|
|
"entropy": 5.965580034255981,
|
|
"epoch": 0.18012059910523245,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000499882117737164,
|
|
"loss": 5.7727,
|
|
"mean_token_accuracy": 0.1477213680744171,
|
|
"num_tokens": 4020792.0,
|
|
"step": 2315
|
|
},
|
|
{
|
|
"entropy": 5.96843729019165,
|
|
"epoch": 0.18050962847695,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004998812189841096,
|
|
"loss": 5.7491,
|
|
"mean_token_accuracy": 0.14528555423021317,
|
|
"num_tokens": 4029235.0,
|
|
"step": 2320
|
|
},
|
|
{
|
|
"entropy": 6.036883306503296,
|
|
"epoch": 0.18089865784866757,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004998803168188407,
|
|
"loss": 5.9845,
|
|
"mean_token_accuracy": 0.14515455886721612,
|
|
"num_tokens": 4037341.0,
|
|
"step": 2325
|
|
},
|
|
{
|
|
"entropy": 6.072755193710327,
|
|
"epoch": 0.18128768722038513,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004998794112413708,
|
|
"loss": 5.8554,
|
|
"mean_token_accuracy": 0.14166971370577813,
|
|
"num_tokens": 4046324.0,
|
|
"step": 2330
|
|
},
|
|
{
|
|
"entropy": 6.041338300704956,
|
|
"epoch": 0.18167671659210272,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998785022517137,
|
|
"loss": 5.9319,
|
|
"mean_token_accuracy": 0.1387798421084881,
|
|
"num_tokens": 4054579.0,
|
|
"step": 2335
|
|
},
|
|
{
|
|
"entropy": 6.153178119659424,
|
|
"epoch": 0.18206574596382027,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004998775898498835,
|
|
"loss": 5.8939,
|
|
"mean_token_accuracy": 0.1421814054250717,
|
|
"num_tokens": 4063087.0,
|
|
"step": 2340
|
|
},
|
|
{
|
|
"entropy": 6.121365165710449,
|
|
"epoch": 0.18245477533553783,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998766740358936,
|
|
"loss": 5.9531,
|
|
"mean_token_accuracy": 0.14040177017450334,
|
|
"num_tokens": 4072309.0,
|
|
"step": 2345
|
|
},
|
|
{
|
|
"entropy": 6.092164039611816,
|
|
"epoch": 0.1828438047072554,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004998757548097582,
|
|
"loss": 5.9948,
|
|
"mean_token_accuracy": 0.13580115213990213,
|
|
"num_tokens": 4081017.0,
|
|
"step": 2350
|
|
},
|
|
{
|
|
"entropy": 6.170856666564942,
|
|
"epoch": 0.18323283407897295,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004998748321714911,
|
|
"loss": 6.0183,
|
|
"mean_token_accuracy": 0.13338493853807448,
|
|
"num_tokens": 4089799.0,
|
|
"step": 2355
|
|
},
|
|
{
|
|
"entropy": 6.063455200195312,
|
|
"epoch": 0.18362186345069054,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004998739061211065,
|
|
"loss": 5.9271,
|
|
"mean_token_accuracy": 0.14566840901970862,
|
|
"num_tokens": 4097948.0,
|
|
"step": 2360
|
|
},
|
|
{
|
|
"entropy": 6.108722352981568,
|
|
"epoch": 0.1840108928224081,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004998729766586181,
|
|
"loss": 5.8152,
|
|
"mean_token_accuracy": 0.14332541227340698,
|
|
"num_tokens": 4107050.0,
|
|
"step": 2365
|
|
},
|
|
{
|
|
"entropy": 6.023930311203003,
|
|
"epoch": 0.18439992219412565,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998720437840403,
|
|
"loss": 5.8309,
|
|
"mean_token_accuracy": 0.13776944130659102,
|
|
"num_tokens": 4115547.0,
|
|
"step": 2370
|
|
},
|
|
{
|
|
"entropy": 6.079334878921509,
|
|
"epoch": 0.1847889515658432,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004998711074973871,
|
|
"loss": 5.8328,
|
|
"mean_token_accuracy": 0.14491757974028588,
|
|
"num_tokens": 4124047.0,
|
|
"step": 2375
|
|
},
|
|
{
|
|
"entropy": 5.999879503250122,
|
|
"epoch": 0.1851779809375608,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998701677986728,
|
|
"loss": 5.8029,
|
|
"mean_token_accuracy": 0.14852844551205635,
|
|
"num_tokens": 4132005.0,
|
|
"step": 2380
|
|
},
|
|
{
|
|
"entropy": 6.126709222793579,
|
|
"epoch": 0.18556701030927836,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004998692246879116,
|
|
"loss": 5.9743,
|
|
"mean_token_accuracy": 0.13506074547767638,
|
|
"num_tokens": 4140199.0,
|
|
"step": 2385
|
|
},
|
|
{
|
|
"entropy": 6.115787029266357,
|
|
"epoch": 0.18595603968099592,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998682781651178,
|
|
"loss": 5.9031,
|
|
"mean_token_accuracy": 0.1383533462882042,
|
|
"num_tokens": 4149353.0,
|
|
"step": 2390
|
|
},
|
|
{
|
|
"entropy": 5.986810922622681,
|
|
"epoch": 0.18634506905271347,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998673282303059,
|
|
"loss": 5.8724,
|
|
"mean_token_accuracy": 0.1399594560265541,
|
|
"num_tokens": 4158531.0,
|
|
"step": 2395
|
|
},
|
|
{
|
|
"entropy": 5.963578128814698,
|
|
"epoch": 0.18673409842443103,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998663748834901,
|
|
"loss": 5.6698,
|
|
"mean_token_accuracy": 0.15333113372325896,
|
|
"num_tokens": 4166743.0,
|
|
"step": 2400
|
|
},
|
|
{
|
|
"entropy": 6.126782751083374,
|
|
"epoch": 0.18712312779614862,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004998654181246851,
|
|
"loss": 6.0205,
|
|
"mean_token_accuracy": 0.13510823845863343,
|
|
"num_tokens": 4175416.0,
|
|
"step": 2405
|
|
},
|
|
{
|
|
"entropy": 6.130587100982666,
|
|
"epoch": 0.18751215716786618,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004998644579539052,
|
|
"loss": 5.9563,
|
|
"mean_token_accuracy": 0.13990581631660462,
|
|
"num_tokens": 4185324.0,
|
|
"step": 2410
|
|
},
|
|
{
|
|
"entropy": 6.074210596084595,
|
|
"epoch": 0.18790118653958374,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000499863494371165,
|
|
"loss": 5.8842,
|
|
"mean_token_accuracy": 0.14497815519571305,
|
|
"num_tokens": 4193361.0,
|
|
"step": 2415
|
|
},
|
|
{
|
|
"entropy": 6.126933288574219,
|
|
"epoch": 0.1882902159113013,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998625273764793,
|
|
"loss": 5.9397,
|
|
"mean_token_accuracy": 0.13277981653809548,
|
|
"num_tokens": 4202553.0,
|
|
"step": 2420
|
|
},
|
|
{
|
|
"entropy": 6.058669185638427,
|
|
"epoch": 0.18867924528301888,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004998615569698626,
|
|
"loss": 5.8727,
|
|
"mean_token_accuracy": 0.14963430315256118,
|
|
"num_tokens": 4211585.0,
|
|
"step": 2425
|
|
},
|
|
{
|
|
"entropy": 5.997480392456055,
|
|
"epoch": 0.18906827465473644,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998605831513296,
|
|
"loss": 5.9164,
|
|
"mean_token_accuracy": 0.13643818199634553,
|
|
"num_tokens": 4220829.0,
|
|
"step": 2430
|
|
},
|
|
{
|
|
"entropy": 6.057970905303955,
|
|
"epoch": 0.189457304026454,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004998596059208953,
|
|
"loss": 5.8181,
|
|
"mean_token_accuracy": 0.14352203160524368,
|
|
"num_tokens": 4228658.0,
|
|
"step": 2435
|
|
},
|
|
{
|
|
"entropy": 6.13070707321167,
|
|
"epoch": 0.18984633339817156,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998586252785743,
|
|
"loss": 5.9049,
|
|
"mean_token_accuracy": 0.1442067116498947,
|
|
"num_tokens": 4237650.0,
|
|
"step": 2440
|
|
},
|
|
{
|
|
"entropy": 6.030512046813965,
|
|
"epoch": 0.19023536276988912,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998576412243816,
|
|
"loss": 5.8831,
|
|
"mean_token_accuracy": 0.14705661460757255,
|
|
"num_tokens": 4246701.0,
|
|
"step": 2445
|
|
},
|
|
{
|
|
"entropy": 6.080326223373413,
|
|
"epoch": 0.1906243921416067,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004998566537583321,
|
|
"loss": 5.8482,
|
|
"mean_token_accuracy": 0.14321040436625482,
|
|
"num_tokens": 4254541.0,
|
|
"step": 2450
|
|
},
|
|
{
|
|
"entropy": 6.082454824447632,
|
|
"epoch": 0.19101342151332426,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998556628804408,
|
|
"loss": 5.8831,
|
|
"mean_token_accuracy": 0.14139181822538377,
|
|
"num_tokens": 4263111.0,
|
|
"step": 2455
|
|
},
|
|
{
|
|
"entropy": 6.04579610824585,
|
|
"epoch": 0.19140245088504182,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004998546685907225,
|
|
"loss": 5.8954,
|
|
"mean_token_accuracy": 0.14221663847565652,
|
|
"num_tokens": 4272796.0,
|
|
"step": 2460
|
|
},
|
|
{
|
|
"entropy": 6.009330224990845,
|
|
"epoch": 0.19179148025675938,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998536708891927,
|
|
"loss": 5.8127,
|
|
"mean_token_accuracy": 0.15046731382608414,
|
|
"num_tokens": 4281361.0,
|
|
"step": 2465
|
|
},
|
|
{
|
|
"entropy": 6.070437002182007,
|
|
"epoch": 0.19218050962847694,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998526697758663,
|
|
"loss": 5.8705,
|
|
"mean_token_accuracy": 0.1421242132782936,
|
|
"num_tokens": 4290470.0,
|
|
"step": 2470
|
|
},
|
|
{
|
|
"entropy": 6.059012508392334,
|
|
"epoch": 0.19256953900019452,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004998516652507585,
|
|
"loss": 5.9169,
|
|
"mean_token_accuracy": 0.13801453858613968,
|
|
"num_tokens": 4299087.0,
|
|
"step": 2475
|
|
},
|
|
{
|
|
"entropy": 6.017315196990967,
|
|
"epoch": 0.19295856837191208,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998506573138846,
|
|
"loss": 5.7824,
|
|
"mean_token_accuracy": 0.15042203813791274,
|
|
"num_tokens": 4307572.0,
|
|
"step": 2480
|
|
},
|
|
{
|
|
"entropy": 6.000125503540039,
|
|
"epoch": 0.19334759774362964,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998496459652598,
|
|
"loss": 5.8715,
|
|
"mean_token_accuracy": 0.14248882085084916,
|
|
"num_tokens": 4316337.0,
|
|
"step": 2485
|
|
},
|
|
{
|
|
"entropy": 6.117257308959961,
|
|
"epoch": 0.1937366271153472,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004998486312048995,
|
|
"loss": 5.9536,
|
|
"mean_token_accuracy": 0.14570799991488456,
|
|
"num_tokens": 4326258.0,
|
|
"step": 2490
|
|
},
|
|
{
|
|
"entropy": 6.035017681121826,
|
|
"epoch": 0.19412565648706478,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998476130328193,
|
|
"loss": 5.7979,
|
|
"mean_token_accuracy": 0.14963613897562028,
|
|
"num_tokens": 4334711.0,
|
|
"step": 2495
|
|
},
|
|
{
|
|
"entropy": 6.051698970794678,
|
|
"epoch": 0.19451468585878234,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004998465914490343,
|
|
"loss": 5.8939,
|
|
"mean_token_accuracy": 0.14221276044845582,
|
|
"num_tokens": 4343739.0,
|
|
"step": 2500
|
|
},
|
|
{
|
|
"entropy": 6.042819595336914,
|
|
"epoch": 0.1949037152304999,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00049984556645356,
|
|
"loss": 5.8445,
|
|
"mean_token_accuracy": 0.1475151002407074,
|
|
"num_tokens": 4352905.0,
|
|
"step": 2505
|
|
},
|
|
{
|
|
"entropy": 6.109594774246216,
|
|
"epoch": 0.19529274460221746,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998445380464124,
|
|
"loss": 5.8667,
|
|
"mean_token_accuracy": 0.14822212606668472,
|
|
"num_tokens": 4361333.0,
|
|
"step": 2510
|
|
},
|
|
{
|
|
"entropy": 5.941962146759034,
|
|
"epoch": 0.19568177397393502,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998435062276066,
|
|
"loss": 5.8167,
|
|
"mean_token_accuracy": 0.14410733431577682,
|
|
"num_tokens": 4369872.0,
|
|
"step": 2515
|
|
},
|
|
{
|
|
"entropy": 6.0431900978088375,
|
|
"epoch": 0.1960708033456526,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998424709971586,
|
|
"loss": 5.894,
|
|
"mean_token_accuracy": 0.14601442515850066,
|
|
"num_tokens": 4378097.0,
|
|
"step": 2520
|
|
},
|
|
{
|
|
"entropy": 6.025267696380615,
|
|
"epoch": 0.19645983271737016,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998414323550839,
|
|
"loss": 5.8153,
|
|
"mean_token_accuracy": 0.14793820455670356,
|
|
"num_tokens": 4387414.0,
|
|
"step": 2525
|
|
},
|
|
{
|
|
"entropy": 6.09251389503479,
|
|
"epoch": 0.19684886208908772,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004998403903013984,
|
|
"loss": 5.9085,
|
|
"mean_token_accuracy": 0.14772322848439218,
|
|
"num_tokens": 4395922.0,
|
|
"step": 2530
|
|
},
|
|
{
|
|
"entropy": 5.9777669429779055,
|
|
"epoch": 0.19723789146080528,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998393448361179,
|
|
"loss": 5.8766,
|
|
"mean_token_accuracy": 0.14107875004410744,
|
|
"num_tokens": 4404500.0,
|
|
"step": 2535
|
|
},
|
|
{
|
|
"entropy": 5.933836650848389,
|
|
"epoch": 0.19762692083252287,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000499838295959258,
|
|
"loss": 5.8752,
|
|
"mean_token_accuracy": 0.14383502304553986,
|
|
"num_tokens": 4413433.0,
|
|
"step": 2540
|
|
},
|
|
{
|
|
"entropy": 6.087890243530273,
|
|
"epoch": 0.19801595020424043,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000499837243670835,
|
|
"loss": 5.8942,
|
|
"mean_token_accuracy": 0.14684352204203605,
|
|
"num_tokens": 4421789.0,
|
|
"step": 2545
|
|
},
|
|
{
|
|
"entropy": 5.997798299789428,
|
|
"epoch": 0.19840497957595798,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998361879708646,
|
|
"loss": 5.7573,
|
|
"mean_token_accuracy": 0.15463868230581285,
|
|
"num_tokens": 4430256.0,
|
|
"step": 2550
|
|
},
|
|
{
|
|
"entropy": 5.990434455871582,
|
|
"epoch": 0.19879400894767554,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000499835128859363,
|
|
"loss": 5.8106,
|
|
"mean_token_accuracy": 0.14735610634088517,
|
|
"num_tokens": 4438431.0,
|
|
"step": 2555
|
|
},
|
|
{
|
|
"entropy": 6.06252908706665,
|
|
"epoch": 0.1991830383193931,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998340663363461,
|
|
"loss": 5.8695,
|
|
"mean_token_accuracy": 0.1388321965932846,
|
|
"num_tokens": 4447150.0,
|
|
"step": 2560
|
|
},
|
|
{
|
|
"entropy": 5.991088819503784,
|
|
"epoch": 0.1995720676911107,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004998330004018301,
|
|
"loss": 5.7606,
|
|
"mean_token_accuracy": 0.14833912998437881,
|
|
"num_tokens": 4455181.0,
|
|
"step": 2565
|
|
},
|
|
{
|
|
"entropy": 5.980442047119141,
|
|
"epoch": 0.19996109706282825,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998319310558312,
|
|
"loss": 5.7811,
|
|
"mean_token_accuracy": 0.14660090953111649,
|
|
"num_tokens": 4463361.0,
|
|
"step": 2570
|
|
},
|
|
{
|
|
"entropy": 6.045340967178345,
|
|
"epoch": 0.2003501264345458,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004998308582983657,
|
|
"loss": 5.8407,
|
|
"mean_token_accuracy": 0.1461796782910824,
|
|
"num_tokens": 4471853.0,
|
|
"step": 2575
|
|
},
|
|
{
|
|
"entropy": 5.949068546295166,
|
|
"epoch": 0.20073915580626336,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004998297821294497,
|
|
"loss": 5.774,
|
|
"mean_token_accuracy": 0.1478642612695694,
|
|
"num_tokens": 4480812.0,
|
|
"step": 2580
|
|
},
|
|
{
|
|
"entropy": 6.020922899246216,
|
|
"epoch": 0.20112818517798095,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004998287025490995,
|
|
"loss": 5.8249,
|
|
"mean_token_accuracy": 0.14373451471328735,
|
|
"num_tokens": 4489180.0,
|
|
"step": 2585
|
|
},
|
|
{
|
|
"entropy": 5.996046781539917,
|
|
"epoch": 0.2015172145496985,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998276195573317,
|
|
"loss": 5.8982,
|
|
"mean_token_accuracy": 0.1447764255106449,
|
|
"num_tokens": 4498013.0,
|
|
"step": 2590
|
|
},
|
|
{
|
|
"entropy": 6.1362189769744875,
|
|
"epoch": 0.20190624392141607,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998265331541627,
|
|
"loss": 5.9291,
|
|
"mean_token_accuracy": 0.1334374077618122,
|
|
"num_tokens": 4506767.0,
|
|
"step": 2595
|
|
},
|
|
{
|
|
"entropy": 6.044833755493164,
|
|
"epoch": 0.20229527329313363,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998254433396088,
|
|
"loss": 5.9371,
|
|
"mean_token_accuracy": 0.14291547536849974,
|
|
"num_tokens": 4516657.0,
|
|
"step": 2600
|
|
},
|
|
{
|
|
"entropy": 5.959131669998169,
|
|
"epoch": 0.20268430266485118,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004998243501136867,
|
|
"loss": 5.7745,
|
|
"mean_token_accuracy": 0.15024542286992074,
|
|
"num_tokens": 4524980.0,
|
|
"step": 2605
|
|
},
|
|
{
|
|
"entropy": 5.998394441604614,
|
|
"epoch": 0.20307333203656877,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998232534764129,
|
|
"loss": 5.8389,
|
|
"mean_token_accuracy": 0.14741490185260772,
|
|
"num_tokens": 4533236.0,
|
|
"step": 2610
|
|
},
|
|
{
|
|
"entropy": 5.903755569458008,
|
|
"epoch": 0.20346236140828633,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004998221534278041,
|
|
"loss": 5.7399,
|
|
"mean_token_accuracy": 0.14562903121113777,
|
|
"num_tokens": 4541778.0,
|
|
"step": 2615
|
|
},
|
|
{
|
|
"entropy": 6.064036464691162,
|
|
"epoch": 0.2038513907800039,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998210499678769,
|
|
"loss": 5.8538,
|
|
"mean_token_accuracy": 0.1419381931424141,
|
|
"num_tokens": 4551131.0,
|
|
"step": 2620
|
|
},
|
|
{
|
|
"entropy": 6.035385370254517,
|
|
"epoch": 0.20424042015172145,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998199430966481,
|
|
"loss": 5.8297,
|
|
"mean_token_accuracy": 0.14448252841830253,
|
|
"num_tokens": 4559530.0,
|
|
"step": 2625
|
|
},
|
|
{
|
|
"entropy": 5.848511409759522,
|
|
"epoch": 0.20462944952343903,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004998188328141346,
|
|
"loss": 5.7181,
|
|
"mean_token_accuracy": 0.1512894958257675,
|
|
"num_tokens": 4567533.0,
|
|
"step": 2630
|
|
},
|
|
{
|
|
"entropy": 6.118367338180542,
|
|
"epoch": 0.2050184788951566,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998177191203531,
|
|
"loss": 5.8612,
|
|
"mean_token_accuracy": 0.14240461885929107,
|
|
"num_tokens": 4576414.0,
|
|
"step": 2635
|
|
},
|
|
{
|
|
"entropy": 5.999768924713135,
|
|
"epoch": 0.20540750826687415,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004998166020153204,
|
|
"loss": 5.7924,
|
|
"mean_token_accuracy": 0.1489753618836403,
|
|
"num_tokens": 4585331.0,
|
|
"step": 2640
|
|
},
|
|
{
|
|
"entropy": 6.012185764312744,
|
|
"epoch": 0.2057965376385917,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004998154814990538,
|
|
"loss": 5.8307,
|
|
"mean_token_accuracy": 0.14780088663101196,
|
|
"num_tokens": 4593526.0,
|
|
"step": 2645
|
|
},
|
|
{
|
|
"entropy": 5.972072982788086,
|
|
"epoch": 0.20618556701030927,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00049981435757157,
|
|
"loss": 5.8305,
|
|
"mean_token_accuracy": 0.1450671598315239,
|
|
"num_tokens": 4602400.0,
|
|
"step": 2650
|
|
},
|
|
{
|
|
"entropy": 5.94981198310852,
|
|
"epoch": 0.20657459638202685,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004998132302328862,
|
|
"loss": 5.7735,
|
|
"mean_token_accuracy": 0.14710604920983314,
|
|
"num_tokens": 4611037.0,
|
|
"step": 2655
|
|
},
|
|
{
|
|
"entropy": 6.004731702804565,
|
|
"epoch": 0.2069636257537444,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998120994830195,
|
|
"loss": 5.7756,
|
|
"mean_token_accuracy": 0.14985849261283873,
|
|
"num_tokens": 4619030.0,
|
|
"step": 2660
|
|
},
|
|
{
|
|
"entropy": 5.977835988998413,
|
|
"epoch": 0.20735265512546197,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000499810965321987,
|
|
"loss": 5.7949,
|
|
"mean_token_accuracy": 0.14194909781217574,
|
|
"num_tokens": 4628649.0,
|
|
"step": 2665
|
|
},
|
|
{
|
|
"entropy": 5.940742921829224,
|
|
"epoch": 0.20774168449717953,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004998098277498059,
|
|
"loss": 5.6989,
|
|
"mean_token_accuracy": 0.14827831983566284,
|
|
"num_tokens": 4636935.0,
|
|
"step": 2670
|
|
},
|
|
{
|
|
"entropy": 5.9714634895324705,
|
|
"epoch": 0.2081307138688971,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004998086867664934,
|
|
"loss": 5.8852,
|
|
"mean_token_accuracy": 0.1452195018529892,
|
|
"num_tokens": 4645532.0,
|
|
"step": 2675
|
|
},
|
|
{
|
|
"entropy": 6.067996883392334,
|
|
"epoch": 0.20851974324061467,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000499807542372067,
|
|
"loss": 5.958,
|
|
"mean_token_accuracy": 0.1363249361515045,
|
|
"num_tokens": 4654433.0,
|
|
"step": 2680
|
|
},
|
|
{
|
|
"entropy": 6.098356103897094,
|
|
"epoch": 0.20890877261233223,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004998063945665439,
|
|
"loss": 5.9518,
|
|
"mean_token_accuracy": 0.1396227262914181,
|
|
"num_tokens": 4662913.0,
|
|
"step": 2685
|
|
},
|
|
{
|
|
"entropy": 6.0581354141235355,
|
|
"epoch": 0.2092978019840498,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004998052433499416,
|
|
"loss": 5.9174,
|
|
"mean_token_accuracy": 0.13971545100212096,
|
|
"num_tokens": 4672270.0,
|
|
"step": 2690
|
|
},
|
|
{
|
|
"entropy": 6.120678234100342,
|
|
"epoch": 0.20968683135576735,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998040887222776,
|
|
"loss": 5.9615,
|
|
"mean_token_accuracy": 0.14097035080194473,
|
|
"num_tokens": 4681428.0,
|
|
"step": 2695
|
|
},
|
|
{
|
|
"entropy": 6.031071949005127,
|
|
"epoch": 0.21007586072748494,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998029306835693,
|
|
"loss": 5.7864,
|
|
"mean_token_accuracy": 0.14907388389110565,
|
|
"num_tokens": 4690492.0,
|
|
"step": 2700
|
|
},
|
|
{
|
|
"entropy": 6.025369882583618,
|
|
"epoch": 0.2104648900992025,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004998017692338344,
|
|
"loss": 5.9018,
|
|
"mean_token_accuracy": 0.14205559343099594,
|
|
"num_tokens": 4699667.0,
|
|
"step": 2705
|
|
},
|
|
{
|
|
"entropy": 5.896922922134399,
|
|
"epoch": 0.21085391947092005,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004998006043730905,
|
|
"loss": 5.5889,
|
|
"mean_token_accuracy": 0.156715589761734,
|
|
"num_tokens": 4708529.0,
|
|
"step": 2710
|
|
},
|
|
{
|
|
"entropy": 5.875597381591797,
|
|
"epoch": 0.2112429488426376,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004997994361013551,
|
|
"loss": 5.8478,
|
|
"mean_token_accuracy": 0.1417768731713295,
|
|
"num_tokens": 4717684.0,
|
|
"step": 2715
|
|
},
|
|
{
|
|
"entropy": 5.999152946472168,
|
|
"epoch": 0.21163197821435517,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004997982644186461,
|
|
"loss": 5.7645,
|
|
"mean_token_accuracy": 0.15027033016085625,
|
|
"num_tokens": 4727067.0,
|
|
"step": 2720
|
|
},
|
|
{
|
|
"entropy": 5.941830015182495,
|
|
"epoch": 0.21202100758607276,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004997970893249813,
|
|
"loss": 5.7409,
|
|
"mean_token_accuracy": 0.15033891201019287,
|
|
"num_tokens": 4735434.0,
|
|
"step": 2725
|
|
},
|
|
{
|
|
"entropy": 5.998355436325073,
|
|
"epoch": 0.21241003695779032,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004997959108203785,
|
|
"loss": 5.7831,
|
|
"mean_token_accuracy": 0.15076861307024955,
|
|
"num_tokens": 4743843.0,
|
|
"step": 2730
|
|
},
|
|
{
|
|
"entropy": 6.021811771392822,
|
|
"epoch": 0.21279906632950787,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004997947289048554,
|
|
"loss": 5.8298,
|
|
"mean_token_accuracy": 0.14842365086078643,
|
|
"num_tokens": 4753228.0,
|
|
"step": 2735
|
|
},
|
|
{
|
|
"entropy": 6.014471864700317,
|
|
"epoch": 0.21318809570122543,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004997935435784302,
|
|
"loss": 5.9131,
|
|
"mean_token_accuracy": 0.14402995258569717,
|
|
"num_tokens": 4763401.0,
|
|
"step": 2740
|
|
},
|
|
{
|
|
"entropy": 5.965554714202881,
|
|
"epoch": 0.21357712507294302,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004997923548411208,
|
|
"loss": 5.7771,
|
|
"mean_token_accuracy": 0.1451819881796837,
|
|
"num_tokens": 4771812.0,
|
|
"step": 2745
|
|
},
|
|
{
|
|
"entropy": 5.930664920806885,
|
|
"epoch": 0.21396615444466058,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000499791162692945,
|
|
"loss": 5.799,
|
|
"mean_token_accuracy": 0.14840952157974244,
|
|
"num_tokens": 4780616.0,
|
|
"step": 2750
|
|
},
|
|
{
|
|
"entropy": 5.959417247772217,
|
|
"epoch": 0.21435518381637814,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004997899671339214,
|
|
"loss": 5.7985,
|
|
"mean_token_accuracy": 0.14958962947130203,
|
|
"num_tokens": 4789886.0,
|
|
"step": 2755
|
|
},
|
|
{
|
|
"entropy": 5.933303451538086,
|
|
"epoch": 0.2147442131880957,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004997887681640675,
|
|
"loss": 5.7753,
|
|
"mean_token_accuracy": 0.14589939936995505,
|
|
"num_tokens": 4799189.0,
|
|
"step": 2760
|
|
},
|
|
{
|
|
"entropy": 6.007724142074585,
|
|
"epoch": 0.21513324255981325,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004997875657834021,
|
|
"loss": 5.821,
|
|
"mean_token_accuracy": 0.15184845104813577,
|
|
"num_tokens": 4807850.0,
|
|
"step": 2765
|
|
},
|
|
{
|
|
"entropy": 6.024917030334473,
|
|
"epoch": 0.21552227193153084,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004997863599919432,
|
|
"loss": 5.7387,
|
|
"mean_token_accuracy": 0.15238860324025155,
|
|
"num_tokens": 4815742.0,
|
|
"step": 2770
|
|
},
|
|
{
|
|
"entropy": 5.997466993331909,
|
|
"epoch": 0.2159113013032484,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004997851507897089,
|
|
"loss": 5.8285,
|
|
"mean_token_accuracy": 0.14630141407251357,
|
|
"num_tokens": 4824761.0,
|
|
"step": 2775
|
|
},
|
|
{
|
|
"entropy": 6.0686828136444095,
|
|
"epoch": 0.21630033067496596,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004997839381767178,
|
|
"loss": 5.9577,
|
|
"mean_token_accuracy": 0.1376100316643715,
|
|
"num_tokens": 4832805.0,
|
|
"step": 2780
|
|
},
|
|
{
|
|
"entropy": 5.969825267791748,
|
|
"epoch": 0.21668936004668352,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004997827221529882,
|
|
"loss": 5.8107,
|
|
"mean_token_accuracy": 0.14742545261979104,
|
|
"num_tokens": 4841938.0,
|
|
"step": 2785
|
|
},
|
|
{
|
|
"entropy": 5.980387020111084,
|
|
"epoch": 0.2170783894184011,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004997815027185386,
|
|
"loss": 5.8302,
|
|
"mean_token_accuracy": 0.1437895864248276,
|
|
"num_tokens": 4849932.0,
|
|
"step": 2790
|
|
},
|
|
{
|
|
"entropy": 5.921569156646728,
|
|
"epoch": 0.21746741879011866,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004997802798733874,
|
|
"loss": 5.6874,
|
|
"mean_token_accuracy": 0.15188782587647437,
|
|
"num_tokens": 4859054.0,
|
|
"step": 2795
|
|
},
|
|
{
|
|
"entropy": 6.0102729320526125,
|
|
"epoch": 0.21785644816183622,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004997790536175534,
|
|
"loss": 5.8669,
|
|
"mean_token_accuracy": 0.14981231167912484,
|
|
"num_tokens": 4867415.0,
|
|
"step": 2800
|
|
},
|
|
{
|
|
"entropy": 6.026336431503296,
|
|
"epoch": 0.21824547753355378,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004997778239510548,
|
|
"loss": 5.8956,
|
|
"mean_token_accuracy": 0.1462355837225914,
|
|
"num_tokens": 4875965.0,
|
|
"step": 2805
|
|
},
|
|
{
|
|
"entropy": 5.998291397094727,
|
|
"epoch": 0.21863450690527134,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004997765908739106,
|
|
"loss": 5.7996,
|
|
"mean_token_accuracy": 0.14824215620756148,
|
|
"num_tokens": 4884629.0,
|
|
"step": 2810
|
|
},
|
|
{
|
|
"entropy": 5.994702625274658,
|
|
"epoch": 0.21902353627698892,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004997753543861395,
|
|
"loss": 5.8435,
|
|
"mean_token_accuracy": 0.1457155279815197,
|
|
"num_tokens": 4893573.0,
|
|
"step": 2815
|
|
},
|
|
{
|
|
"entropy": 5.932880544662476,
|
|
"epoch": 0.21941256564870648,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00049977411448776,
|
|
"loss": 5.7718,
|
|
"mean_token_accuracy": 0.1455760970711708,
|
|
"num_tokens": 4902831.0,
|
|
"step": 2820
|
|
},
|
|
{
|
|
"entropy": 6.032305574417114,
|
|
"epoch": 0.21980159502042404,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004997728711787912,
|
|
"loss": 5.8263,
|
|
"mean_token_accuracy": 0.14247847720980644,
|
|
"num_tokens": 4911360.0,
|
|
"step": 2825
|
|
},
|
|
{
|
|
"entropy": 5.986047887802124,
|
|
"epoch": 0.2201906243921416,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004997716244592518,
|
|
"loss": 5.7947,
|
|
"mean_token_accuracy": 0.142076013982296,
|
|
"num_tokens": 4919758.0,
|
|
"step": 2830
|
|
},
|
|
{
|
|
"entropy": 5.846888208389283,
|
|
"epoch": 0.22057965376385918,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004997703743291607,
|
|
"loss": 5.6693,
|
|
"mean_token_accuracy": 0.15803906843066215,
|
|
"num_tokens": 4928934.0,
|
|
"step": 2835
|
|
},
|
|
{
|
|
"entropy": 5.908144187927246,
|
|
"epoch": 0.22096868313557674,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000499769120788537,
|
|
"loss": 5.7258,
|
|
"mean_token_accuracy": 0.1486142821609974,
|
|
"num_tokens": 4937780.0,
|
|
"step": 2840
|
|
},
|
|
{
|
|
"entropy": 6.082314538955688,
|
|
"epoch": 0.2213577125072943,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004997678638373995,
|
|
"loss": 5.8261,
|
|
"mean_token_accuracy": 0.1448799580335617,
|
|
"num_tokens": 4946862.0,
|
|
"step": 2845
|
|
},
|
|
{
|
|
"entropy": 5.94984769821167,
|
|
"epoch": 0.22174674187901186,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004997666034757676,
|
|
"loss": 5.8049,
|
|
"mean_token_accuracy": 0.1516811653971672,
|
|
"num_tokens": 4954883.0,
|
|
"step": 2850
|
|
},
|
|
{
|
|
"entropy": 5.85023832321167,
|
|
"epoch": 0.22213577125072942,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004997653397036603,
|
|
"loss": 5.6035,
|
|
"mean_token_accuracy": 0.15844471007585526,
|
|
"num_tokens": 4962840.0,
|
|
"step": 2855
|
|
},
|
|
{
|
|
"entropy": 5.935201215744018,
|
|
"epoch": 0.222524800622447,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004997640725210965,
|
|
"loss": 5.8358,
|
|
"mean_token_accuracy": 0.14835945665836334,
|
|
"num_tokens": 4972334.0,
|
|
"step": 2860
|
|
},
|
|
{
|
|
"entropy": 5.970633888244629,
|
|
"epoch": 0.22291382999416456,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004997628019280958,
|
|
"loss": 5.8008,
|
|
"mean_token_accuracy": 0.1477268561720848,
|
|
"num_tokens": 4981032.0,
|
|
"step": 2865
|
|
},
|
|
{
|
|
"entropy": 5.974843454360962,
|
|
"epoch": 0.22330285936588212,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004997615279246773,
|
|
"loss": 5.8054,
|
|
"mean_token_accuracy": 0.14543402120471,
|
|
"num_tokens": 4990502.0,
|
|
"step": 2870
|
|
},
|
|
{
|
|
"entropy": 6.052269506454468,
|
|
"epoch": 0.22369188873759968,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004997602505108603,
|
|
"loss": 5.9916,
|
|
"mean_token_accuracy": 0.13957195803523065,
|
|
"num_tokens": 4999121.0,
|
|
"step": 2875
|
|
},
|
|
{
|
|
"entropy": 5.986846828460694,
|
|
"epoch": 0.22408091810931724,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004997589696866644,
|
|
"loss": 5.7363,
|
|
"mean_token_accuracy": 0.15012581199407576,
|
|
"num_tokens": 5007271.0,
|
|
"step": 2880
|
|
},
|
|
{
|
|
"entropy": 5.880199956893921,
|
|
"epoch": 0.22446994748103483,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004997576854521088,
|
|
"loss": 5.7994,
|
|
"mean_token_accuracy": 0.143898157030344,
|
|
"num_tokens": 5015940.0,
|
|
"step": 2885
|
|
},
|
|
{
|
|
"entropy": 5.899425983428955,
|
|
"epoch": 0.22485897685275238,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000499756397807213,
|
|
"loss": 5.7234,
|
|
"mean_token_accuracy": 0.1511826515197754,
|
|
"num_tokens": 5024294.0,
|
|
"step": 2890
|
|
},
|
|
{
|
|
"entropy": 5.997026634216309,
|
|
"epoch": 0.22524800622446994,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004997551067519966,
|
|
"loss": 5.6722,
|
|
"mean_token_accuracy": 0.1542857527732849,
|
|
"num_tokens": 5033401.0,
|
|
"step": 2895
|
|
},
|
|
{
|
|
"entropy": 5.861394643783569,
|
|
"epoch": 0.2256370355961875,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004997538122864792,
|
|
"loss": 5.7638,
|
|
"mean_token_accuracy": 0.14565517976880074,
|
|
"num_tokens": 5041955.0,
|
|
"step": 2900
|
|
},
|
|
{
|
|
"entropy": 5.918551397323609,
|
|
"epoch": 0.2260260649679051,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004997525144106804,
|
|
"loss": 5.8115,
|
|
"mean_token_accuracy": 0.14099842831492423,
|
|
"num_tokens": 5051132.0,
|
|
"step": 2905
|
|
},
|
|
{
|
|
"entropy": 5.935513830184936,
|
|
"epoch": 0.22641509433962265,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00049975121312462,
|
|
"loss": 5.7359,
|
|
"mean_token_accuracy": 0.15899298340082169,
|
|
"num_tokens": 5059492.0,
|
|
"step": 2910
|
|
},
|
|
{
|
|
"entropy": 5.87189130783081,
|
|
"epoch": 0.2268041237113402,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004997499084283177,
|
|
"loss": 5.7837,
|
|
"mean_token_accuracy": 0.1493110865354538,
|
|
"num_tokens": 5069015.0,
|
|
"step": 2915
|
|
},
|
|
{
|
|
"entropy": 5.9538294792175295,
|
|
"epoch": 0.22719315308305776,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004997486003217932,
|
|
"loss": 5.7948,
|
|
"mean_token_accuracy": 0.14656500220298768,
|
|
"num_tokens": 5077614.0,
|
|
"step": 2920
|
|
},
|
|
{
|
|
"entropy": 5.937190008163452,
|
|
"epoch": 0.22758218245477532,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004997472888050664,
|
|
"loss": 5.724,
|
|
"mean_token_accuracy": 0.15037651658058165,
|
|
"num_tokens": 5086300.0,
|
|
"step": 2925
|
|
},
|
|
{
|
|
"entropy": 5.855981540679932,
|
|
"epoch": 0.2279712118264929,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004997459738781573,
|
|
"loss": 5.7738,
|
|
"mean_token_accuracy": 0.1492456465959549,
|
|
"num_tokens": 5095967.0,
|
|
"step": 2930
|
|
},
|
|
{
|
|
"entropy": 5.961302804946899,
|
|
"epoch": 0.22836024119821047,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004997446555410857,
|
|
"loss": 5.7319,
|
|
"mean_token_accuracy": 0.148114612698555,
|
|
"num_tokens": 5104611.0,
|
|
"step": 2935
|
|
},
|
|
{
|
|
"entropy": 5.902946662902832,
|
|
"epoch": 0.22874927056992803,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004997433337938716,
|
|
"loss": 5.6867,
|
|
"mean_token_accuracy": 0.15346912294626236,
|
|
"num_tokens": 5113452.0,
|
|
"step": 2940
|
|
},
|
|
{
|
|
"entropy": 5.822092819213867,
|
|
"epoch": 0.22913829994164558,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004997420086365351,
|
|
"loss": 5.6718,
|
|
"mean_token_accuracy": 0.15292285978794098,
|
|
"num_tokens": 5121558.0,
|
|
"step": 2945
|
|
},
|
|
{
|
|
"entropy": 5.884310340881347,
|
|
"epoch": 0.22952732931336317,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004997406800690966,
|
|
"loss": 5.6482,
|
|
"mean_token_accuracy": 0.16208126842975618,
|
|
"num_tokens": 5129942.0,
|
|
"step": 2950
|
|
},
|
|
{
|
|
"entropy": 5.936553859710694,
|
|
"epoch": 0.22991635868508073,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004997393480915758,
|
|
"loss": 5.7766,
|
|
"mean_token_accuracy": 0.1436438135802746,
|
|
"num_tokens": 5139012.0,
|
|
"step": 2955
|
|
},
|
|
{
|
|
"entropy": 5.977424049377442,
|
|
"epoch": 0.2303053880567983,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004997380127039931,
|
|
"loss": 5.7831,
|
|
"mean_token_accuracy": 0.14895185455679893,
|
|
"num_tokens": 5148185.0,
|
|
"step": 2960
|
|
},
|
|
{
|
|
"entropy": 5.966456031799316,
|
|
"epoch": 0.23069441742851585,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004997366739063688,
|
|
"loss": 5.808,
|
|
"mean_token_accuracy": 0.14403805360198021,
|
|
"num_tokens": 5157086.0,
|
|
"step": 2965
|
|
},
|
|
{
|
|
"entropy": 6.039245176315307,
|
|
"epoch": 0.2310834468002334,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004997353316987231,
|
|
"loss": 5.871,
|
|
"mean_token_accuracy": 0.1416305460035801,
|
|
"num_tokens": 5165842.0,
|
|
"step": 2970
|
|
},
|
|
{
|
|
"entropy": 5.9533428192138675,
|
|
"epoch": 0.231472476171951,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004997339860810765,
|
|
"loss": 5.8666,
|
|
"mean_token_accuracy": 0.14629089161753656,
|
|
"num_tokens": 5174161.0,
|
|
"step": 2975
|
|
},
|
|
{
|
|
"entropy": 5.932276821136474,
|
|
"epoch": 0.23186150554366855,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004997326370534495,
|
|
"loss": 5.8232,
|
|
"mean_token_accuracy": 0.144809553027153,
|
|
"num_tokens": 5183830.0,
|
|
"step": 2980
|
|
},
|
|
{
|
|
"entropy": 5.911020135879516,
|
|
"epoch": 0.2322505349153861,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004997312846158622,
|
|
"loss": 5.7319,
|
|
"mean_token_accuracy": 0.14793932288885117,
|
|
"num_tokens": 5192248.0,
|
|
"step": 2985
|
|
},
|
|
{
|
|
"entropy": 5.829217910766602,
|
|
"epoch": 0.23263956428710367,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004997299287683355,
|
|
"loss": 5.7053,
|
|
"mean_token_accuracy": 0.15378875881433487,
|
|
"num_tokens": 5201212.0,
|
|
"step": 2990
|
|
},
|
|
{
|
|
"entropy": 5.876448011398315,
|
|
"epoch": 0.23302859365882125,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004997285695108898,
|
|
"loss": 5.7687,
|
|
"mean_token_accuracy": 0.1468915194272995,
|
|
"num_tokens": 5209338.0,
|
|
"step": 2995
|
|
},
|
|
{
|
|
"entropy": 6.041135358810425,
|
|
"epoch": 0.2334176230305388,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004997272068435458,
|
|
"loss": 5.7828,
|
|
"mean_token_accuracy": 0.147082382440567,
|
|
"num_tokens": 5217590.0,
|
|
"step": 3000
|
|
},
|
|
{
|
|
"epoch": 0.2334176230305388,
|
|
"eval_entropy": 5.745479221086988,
|
|
"eval_loss": 5.805346488952637,
|
|
"eval_mean_token_accuracy": 0.15537624003812026,
|
|
"eval_num_tokens": 5217590.0,
|
|
"eval_runtime": 21.6146,
|
|
"eval_samples_per_second": 1922.684,
|
|
"eval_steps_per_second": 240.347,
|
|
"step": 3000
|
|
}
|
|
],
|
|
"logging_steps": 5,
|
|
"max_steps": 128520,
|
|
"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": 1050172329000960.0,
|
|
"train_batch_size": 16,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|