6046 lines
164 KiB
JSON
6046 lines
164 KiB
JSON
{
|
|
"best_global_step": null,
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 0.27213352685050796,
|
|
"eval_steps": 3000,
|
|
"global_step": 3000,
|
|
"is_hyper_param_search": false,
|
|
"is_local_process_zero": true,
|
|
"is_world_process_zero": true,
|
|
"log_history": [
|
|
{
|
|
"entropy": 10.691939735412598,
|
|
"epoch": 0.00045355587808418,
|
|
"grad_norm": 13.6875,
|
|
"learning_rate": 2e-06,
|
|
"loss": 10.8323,
|
|
"mean_token_accuracy": 0.0,
|
|
"num_tokens": 9883.0,
|
|
"step": 5
|
|
},
|
|
{
|
|
"entropy": 10.69197416305542,
|
|
"epoch": 0.00090711175616836,
|
|
"grad_norm": 12.4375,
|
|
"learning_rate": 4.5e-06,
|
|
"loss": 10.7629,
|
|
"mean_token_accuracy": 0.00031574604799970983,
|
|
"num_tokens": 20400.0,
|
|
"step": 10
|
|
},
|
|
{
|
|
"entropy": 10.691064357757568,
|
|
"epoch": 0.00136066763425254,
|
|
"grad_norm": 9.6875,
|
|
"learning_rate": 7e-06,
|
|
"loss": 10.5051,
|
|
"mean_token_accuracy": 0.027546282985713332,
|
|
"num_tokens": 31503.0,
|
|
"step": 15
|
|
},
|
|
{
|
|
"entropy": 10.68053970336914,
|
|
"epoch": 0.00181422351233672,
|
|
"grad_norm": 6.40625,
|
|
"learning_rate": 9.5e-06,
|
|
"loss": 10.1556,
|
|
"mean_token_accuracy": 0.04329935684800148,
|
|
"num_tokens": 41648.0,
|
|
"step": 20
|
|
},
|
|
{
|
|
"entropy": 10.629761695861816,
|
|
"epoch": 0.0022677793904208998,
|
|
"grad_norm": 4.21875,
|
|
"learning_rate": 1.2e-05,
|
|
"loss": 9.8493,
|
|
"mean_token_accuracy": 0.04506267905235291,
|
|
"num_tokens": 51580.0,
|
|
"step": 25
|
|
},
|
|
{
|
|
"entropy": 10.582753944396973,
|
|
"epoch": 0.00272133526850508,
|
|
"grad_norm": 3.203125,
|
|
"learning_rate": 1.4500000000000002e-05,
|
|
"loss": 9.6753,
|
|
"mean_token_accuracy": 0.046586386114358905,
|
|
"num_tokens": 61612.0,
|
|
"step": 30
|
|
},
|
|
{
|
|
"entropy": 10.568104076385499,
|
|
"epoch": 0.00317489114658926,
|
|
"grad_norm": 2.78125,
|
|
"learning_rate": 1.7000000000000003e-05,
|
|
"loss": 9.6287,
|
|
"mean_token_accuracy": 0.045973442122340204,
|
|
"num_tokens": 71673.0,
|
|
"step": 35
|
|
},
|
|
{
|
|
"entropy": 10.570516300201415,
|
|
"epoch": 0.00362844702467344,
|
|
"grad_norm": 2.6875,
|
|
"learning_rate": 1.95e-05,
|
|
"loss": 9.5556,
|
|
"mean_token_accuracy": 0.05169081836938858,
|
|
"num_tokens": 81437.0,
|
|
"step": 40
|
|
},
|
|
{
|
|
"entropy": 10.541032028198241,
|
|
"epoch": 0.00408200290275762,
|
|
"grad_norm": 2.53125,
|
|
"learning_rate": 2.2e-05,
|
|
"loss": 9.5206,
|
|
"mean_token_accuracy": 0.049654603004455566,
|
|
"num_tokens": 90827.0,
|
|
"step": 45
|
|
},
|
|
{
|
|
"entropy": 10.549186420440673,
|
|
"epoch": 0.0045355587808417995,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 2.4500000000000003e-05,
|
|
"loss": 9.48,
|
|
"mean_token_accuracy": 0.05328560955822468,
|
|
"num_tokens": 100253.0,
|
|
"step": 50
|
|
},
|
|
{
|
|
"entropy": 10.541085529327393,
|
|
"epoch": 0.00498911465892598,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 2.7e-05,
|
|
"loss": 9.3843,
|
|
"mean_token_accuracy": 0.061034252494573595,
|
|
"num_tokens": 110393.0,
|
|
"step": 55
|
|
},
|
|
{
|
|
"entropy": 10.490248107910157,
|
|
"epoch": 0.00544267053701016,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 2.95e-05,
|
|
"loss": 9.3537,
|
|
"mean_token_accuracy": 0.060261032357811925,
|
|
"num_tokens": 121012.0,
|
|
"step": 60
|
|
},
|
|
{
|
|
"entropy": 10.395410060882568,
|
|
"epoch": 0.00589622641509434,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 3.2e-05,
|
|
"loss": 9.287,
|
|
"mean_token_accuracy": 0.06284476146101951,
|
|
"num_tokens": 131118.0,
|
|
"step": 65
|
|
},
|
|
{
|
|
"entropy": 10.410375499725342,
|
|
"epoch": 0.00634978229317852,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 3.4500000000000005e-05,
|
|
"loss": 9.1803,
|
|
"mean_token_accuracy": 0.06393150016665458,
|
|
"num_tokens": 142145.0,
|
|
"step": 70
|
|
},
|
|
{
|
|
"entropy": 10.449656963348389,
|
|
"epoch": 0.006803338171262699,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 3.7e-05,
|
|
"loss": 9.0845,
|
|
"mean_token_accuracy": 0.06696042232215405,
|
|
"num_tokens": 152691.0,
|
|
"step": 75
|
|
},
|
|
{
|
|
"entropy": 10.315881538391114,
|
|
"epoch": 0.00725689404934688,
|
|
"grad_norm": 2.78125,
|
|
"learning_rate": 3.95e-05,
|
|
"loss": 8.9505,
|
|
"mean_token_accuracy": 0.07629339359700679,
|
|
"num_tokens": 162278.0,
|
|
"step": 80
|
|
},
|
|
{
|
|
"entropy": 10.312966537475585,
|
|
"epoch": 0.007710449927431059,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 4.2000000000000004e-05,
|
|
"loss": 8.8565,
|
|
"mean_token_accuracy": 0.07719368785619736,
|
|
"num_tokens": 171942.0,
|
|
"step": 85
|
|
},
|
|
{
|
|
"entropy": 10.19672908782959,
|
|
"epoch": 0.00816400580551524,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 4.45e-05,
|
|
"loss": 8.8517,
|
|
"mean_token_accuracy": 0.07195285111665725,
|
|
"num_tokens": 183194.0,
|
|
"step": 90
|
|
},
|
|
{
|
|
"entropy": 10.182042503356934,
|
|
"epoch": 0.00861756168359942,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 4.7000000000000004e-05,
|
|
"loss": 8.6574,
|
|
"mean_token_accuracy": 0.07674754187464713,
|
|
"num_tokens": 194775.0,
|
|
"step": 95
|
|
},
|
|
{
|
|
"entropy": 10.162378025054931,
|
|
"epoch": 0.009071117561683599,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 4.9500000000000004e-05,
|
|
"loss": 8.6036,
|
|
"mean_token_accuracy": 0.07473644688725471,
|
|
"num_tokens": 204720.0,
|
|
"step": 100
|
|
},
|
|
{
|
|
"entropy": 10.052161598205567,
|
|
"epoch": 0.009524673439767779,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 5.2e-05,
|
|
"loss": 8.4531,
|
|
"mean_token_accuracy": 0.08001778945326805,
|
|
"num_tokens": 214822.0,
|
|
"step": 105
|
|
},
|
|
{
|
|
"entropy": 10.04954490661621,
|
|
"epoch": 0.00997822931785196,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 5.45e-05,
|
|
"loss": 8.3787,
|
|
"mean_token_accuracy": 0.07661775350570679,
|
|
"num_tokens": 225365.0,
|
|
"step": 110
|
|
},
|
|
{
|
|
"entropy": 9.939160346984863,
|
|
"epoch": 0.01043178519593614,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 5.7e-05,
|
|
"loss": 8.282,
|
|
"mean_token_accuracy": 0.07927817553281784,
|
|
"num_tokens": 236145.0,
|
|
"step": 115
|
|
},
|
|
{
|
|
"entropy": 9.821665000915527,
|
|
"epoch": 0.01088534107402032,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 5.9499999999999996e-05,
|
|
"loss": 8.1728,
|
|
"mean_token_accuracy": 0.08287631459534169,
|
|
"num_tokens": 247703.0,
|
|
"step": 120
|
|
},
|
|
{
|
|
"entropy": 9.734042263031006,
|
|
"epoch": 0.011338896952104499,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 6.2e-05,
|
|
"loss": 8.086,
|
|
"mean_token_accuracy": 0.0859085351228714,
|
|
"num_tokens": 258291.0,
|
|
"step": 125
|
|
},
|
|
{
|
|
"entropy": 9.552165699005126,
|
|
"epoch": 0.01179245283018868,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 6.450000000000001e-05,
|
|
"loss": 7.915,
|
|
"mean_token_accuracy": 0.07912573739886283,
|
|
"num_tokens": 268784.0,
|
|
"step": 130
|
|
},
|
|
{
|
|
"entropy": 9.39622163772583,
|
|
"epoch": 0.01224600870827286,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 6.7e-05,
|
|
"loss": 7.8058,
|
|
"mean_token_accuracy": 0.07961424812674522,
|
|
"num_tokens": 279135.0,
|
|
"step": 135
|
|
},
|
|
{
|
|
"entropy": 9.229594898223876,
|
|
"epoch": 0.01269956458635704,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 6.950000000000001e-05,
|
|
"loss": 7.7052,
|
|
"mean_token_accuracy": 0.08270319849252701,
|
|
"num_tokens": 289234.0,
|
|
"step": 140
|
|
},
|
|
{
|
|
"entropy": 8.944133758544922,
|
|
"epoch": 0.013153120464441219,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 7.2e-05,
|
|
"loss": 7.578,
|
|
"mean_token_accuracy": 0.08616896718740463,
|
|
"num_tokens": 299424.0,
|
|
"step": 145
|
|
},
|
|
{
|
|
"entropy": 8.690094184875488,
|
|
"epoch": 0.013606676342525399,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 7.45e-05,
|
|
"loss": 7.4444,
|
|
"mean_token_accuracy": 0.09042754545807838,
|
|
"num_tokens": 310040.0,
|
|
"step": 150
|
|
},
|
|
{
|
|
"entropy": 8.549762439727782,
|
|
"epoch": 0.01406023222060958,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 7.7e-05,
|
|
"loss": 7.4418,
|
|
"mean_token_accuracy": 0.08952978774905204,
|
|
"num_tokens": 319995.0,
|
|
"step": 155
|
|
},
|
|
{
|
|
"entropy": 8.382944869995118,
|
|
"epoch": 0.01451378809869376,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 7.950000000000001e-05,
|
|
"loss": 7.3727,
|
|
"mean_token_accuracy": 0.08898745998740196,
|
|
"num_tokens": 331212.0,
|
|
"step": 160
|
|
},
|
|
{
|
|
"entropy": 8.153345584869385,
|
|
"epoch": 0.014967343976777939,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 8.2e-05,
|
|
"loss": 7.3922,
|
|
"mean_token_accuracy": 0.0851880744099617,
|
|
"num_tokens": 341435.0,
|
|
"step": 165
|
|
},
|
|
{
|
|
"entropy": 8.16848258972168,
|
|
"epoch": 0.015420899854862119,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 8.450000000000001e-05,
|
|
"loss": 7.3169,
|
|
"mean_token_accuracy": 0.09060425236821175,
|
|
"num_tokens": 351415.0,
|
|
"step": 170
|
|
},
|
|
{
|
|
"entropy": 8.10801820755005,
|
|
"epoch": 0.0158744557329463,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 8.7e-05,
|
|
"loss": 7.377,
|
|
"mean_token_accuracy": 0.08710973337292671,
|
|
"num_tokens": 361862.0,
|
|
"step": 175
|
|
},
|
|
{
|
|
"entropy": 7.906155395507812,
|
|
"epoch": 0.01632801161103048,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 8.95e-05,
|
|
"loss": 7.2797,
|
|
"mean_token_accuracy": 0.08494263291358947,
|
|
"num_tokens": 371658.0,
|
|
"step": 180
|
|
},
|
|
{
|
|
"entropy": 7.864446401596069,
|
|
"epoch": 0.01678156748911466,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 9.2e-05,
|
|
"loss": 7.2279,
|
|
"mean_token_accuracy": 0.08928770050406457,
|
|
"num_tokens": 382288.0,
|
|
"step": 185
|
|
},
|
|
{
|
|
"entropy": 7.861935758590699,
|
|
"epoch": 0.01723512336719884,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 9.45e-05,
|
|
"loss": 7.3235,
|
|
"mean_token_accuracy": 0.09150304198265076,
|
|
"num_tokens": 392852.0,
|
|
"step": 190
|
|
},
|
|
{
|
|
"entropy": 7.856825923919677,
|
|
"epoch": 0.01768867924528302,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 9.7e-05,
|
|
"loss": 7.1984,
|
|
"mean_token_accuracy": 0.09069699421525002,
|
|
"num_tokens": 403813.0,
|
|
"step": 195
|
|
},
|
|
{
|
|
"entropy": 7.694656801223755,
|
|
"epoch": 0.018142235123367198,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 9.95e-05,
|
|
"loss": 7.2223,
|
|
"mean_token_accuracy": 0.08859646022319793,
|
|
"num_tokens": 414470.0,
|
|
"step": 200
|
|
},
|
|
{
|
|
"entropy": 7.705080652236939,
|
|
"epoch": 0.018595791001451378,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000102,
|
|
"loss": 7.2239,
|
|
"mean_token_accuracy": 0.09004590287804604,
|
|
"num_tokens": 424949.0,
|
|
"step": 205
|
|
},
|
|
{
|
|
"entropy": 7.736959314346313,
|
|
"epoch": 0.019049346879535557,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00010449999999999999,
|
|
"loss": 7.0639,
|
|
"mean_token_accuracy": 0.09480814039707183,
|
|
"num_tokens": 435133.0,
|
|
"step": 210
|
|
},
|
|
{
|
|
"entropy": 7.6014525413513185,
|
|
"epoch": 0.01950290275761974,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.000107,
|
|
"loss": 7.1543,
|
|
"mean_token_accuracy": 0.0943043127655983,
|
|
"num_tokens": 445789.0,
|
|
"step": 215
|
|
},
|
|
{
|
|
"entropy": 7.600877857208252,
|
|
"epoch": 0.01995645863570392,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0001095,
|
|
"loss": 7.1506,
|
|
"mean_token_accuracy": 0.09123467728495598,
|
|
"num_tokens": 455516.0,
|
|
"step": 220
|
|
},
|
|
{
|
|
"entropy": 7.597001695632935,
|
|
"epoch": 0.0204100145137881,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.000112,
|
|
"loss": 7.1802,
|
|
"mean_token_accuracy": 0.09758866354823112,
|
|
"num_tokens": 466350.0,
|
|
"step": 225
|
|
},
|
|
{
|
|
"entropy": 7.643424654006958,
|
|
"epoch": 0.02086357039187228,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0001145,
|
|
"loss": 7.1326,
|
|
"mean_token_accuracy": 0.0965645931661129,
|
|
"num_tokens": 477342.0,
|
|
"step": 230
|
|
},
|
|
{
|
|
"entropy": 7.578091096878052,
|
|
"epoch": 0.02131712626995646,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.00011700000000000001,
|
|
"loss": 7.1025,
|
|
"mean_token_accuracy": 0.09310675337910652,
|
|
"num_tokens": 487095.0,
|
|
"step": 235
|
|
},
|
|
{
|
|
"entropy": 7.599606895446778,
|
|
"epoch": 0.02177068214804064,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00011949999999999999,
|
|
"loss": 7.0785,
|
|
"mean_token_accuracy": 0.09243985787034034,
|
|
"num_tokens": 498945.0,
|
|
"step": 240
|
|
},
|
|
{
|
|
"entropy": 7.6134318828582765,
|
|
"epoch": 0.022224238026124818,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.000122,
|
|
"loss": 7.1216,
|
|
"mean_token_accuracy": 0.0947557583451271,
|
|
"num_tokens": 508863.0,
|
|
"step": 245
|
|
},
|
|
{
|
|
"entropy": 7.505317640304566,
|
|
"epoch": 0.022677793904208998,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0001245,
|
|
"loss": 7.083,
|
|
"mean_token_accuracy": 0.09349310845136642,
|
|
"num_tokens": 518887.0,
|
|
"step": 250
|
|
},
|
|
{
|
|
"entropy": 7.506907272338867,
|
|
"epoch": 0.023131349782293177,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000127,
|
|
"loss": 7.0638,
|
|
"mean_token_accuracy": 0.0991144374012947,
|
|
"num_tokens": 529198.0,
|
|
"step": 255
|
|
},
|
|
{
|
|
"entropy": 7.526238584518433,
|
|
"epoch": 0.02358490566037736,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0001295,
|
|
"loss": 7.0582,
|
|
"mean_token_accuracy": 0.09299291446805,
|
|
"num_tokens": 540003.0,
|
|
"step": 260
|
|
},
|
|
{
|
|
"entropy": 7.563022041320801,
|
|
"epoch": 0.02403846153846154,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.000132,
|
|
"loss": 7.0378,
|
|
"mean_token_accuracy": 0.09797687977552413,
|
|
"num_tokens": 549243.0,
|
|
"step": 265
|
|
},
|
|
{
|
|
"entropy": 7.543271493911743,
|
|
"epoch": 0.02449201741654572,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00013450000000000002,
|
|
"loss": 7.1975,
|
|
"mean_token_accuracy": 0.09064211472868919,
|
|
"num_tokens": 559721.0,
|
|
"step": 270
|
|
},
|
|
{
|
|
"entropy": 7.47391448020935,
|
|
"epoch": 0.0249455732946299,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00013700000000000002,
|
|
"loss": 7.0127,
|
|
"mean_token_accuracy": 0.09864112585783005,
|
|
"num_tokens": 569034.0,
|
|
"step": 275
|
|
},
|
|
{
|
|
"entropy": 7.420712518692016,
|
|
"epoch": 0.02539912917271408,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0001395,
|
|
"loss": 7.073,
|
|
"mean_token_accuracy": 0.09223218783736228,
|
|
"num_tokens": 580082.0,
|
|
"step": 280
|
|
},
|
|
{
|
|
"entropy": 7.422401809692383,
|
|
"epoch": 0.025852685050798258,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00014199999999999998,
|
|
"loss": 6.9636,
|
|
"mean_token_accuracy": 0.09520288854837418,
|
|
"num_tokens": 590326.0,
|
|
"step": 285
|
|
},
|
|
{
|
|
"entropy": 7.595379972457886,
|
|
"epoch": 0.026306240928882438,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0001445,
|
|
"loss": 7.1377,
|
|
"mean_token_accuracy": 0.0937683179974556,
|
|
"num_tokens": 601745.0,
|
|
"step": 290
|
|
},
|
|
{
|
|
"entropy": 7.418688154220581,
|
|
"epoch": 0.026759796806966617,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.000147,
|
|
"loss": 7.0825,
|
|
"mean_token_accuracy": 0.09572035521268844,
|
|
"num_tokens": 612306.0,
|
|
"step": 295
|
|
},
|
|
{
|
|
"entropy": 7.382623720169067,
|
|
"epoch": 0.027213352685050797,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0001495,
|
|
"loss": 7.0017,
|
|
"mean_token_accuracy": 0.09278988242149352,
|
|
"num_tokens": 623315.0,
|
|
"step": 300
|
|
},
|
|
{
|
|
"entropy": 7.3942585468292235,
|
|
"epoch": 0.027666908563134977,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000152,
|
|
"loss": 6.9455,
|
|
"mean_token_accuracy": 0.09706330373883247,
|
|
"num_tokens": 632981.0,
|
|
"step": 305
|
|
},
|
|
{
|
|
"entropy": 7.5014002323150635,
|
|
"epoch": 0.02812046444121916,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00015450000000000001,
|
|
"loss": 6.9848,
|
|
"mean_token_accuracy": 0.10258090272545814,
|
|
"num_tokens": 642872.0,
|
|
"step": 310
|
|
},
|
|
{
|
|
"entropy": 7.2068887710571286,
|
|
"epoch": 0.02857402031930334,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000157,
|
|
"loss": 6.9519,
|
|
"mean_token_accuracy": 0.09786502793431281,
|
|
"num_tokens": 652756.0,
|
|
"step": 315
|
|
},
|
|
{
|
|
"entropy": 7.3521472930908205,
|
|
"epoch": 0.02902757619738752,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0001595,
|
|
"loss": 6.9107,
|
|
"mean_token_accuracy": 0.09691967144608497,
|
|
"num_tokens": 663537.0,
|
|
"step": 320
|
|
},
|
|
{
|
|
"entropy": 7.311666536331177,
|
|
"epoch": 0.0294811320754717,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.000162,
|
|
"loss": 6.915,
|
|
"mean_token_accuracy": 0.0960552416741848,
|
|
"num_tokens": 673811.0,
|
|
"step": 325
|
|
},
|
|
{
|
|
"entropy": 7.272817134857178,
|
|
"epoch": 0.029934687953555878,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00016450000000000001,
|
|
"loss": 6.91,
|
|
"mean_token_accuracy": 0.09867974072694778,
|
|
"num_tokens": 683733.0,
|
|
"step": 330
|
|
},
|
|
{
|
|
"entropy": 7.3990702629089355,
|
|
"epoch": 0.030388243831640058,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00016700000000000002,
|
|
"loss": 6.9882,
|
|
"mean_token_accuracy": 0.09951149746775627,
|
|
"num_tokens": 693110.0,
|
|
"step": 335
|
|
},
|
|
{
|
|
"entropy": 7.159088897705078,
|
|
"epoch": 0.030841799709724237,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00016950000000000003,
|
|
"loss": 6.7683,
|
|
"mean_token_accuracy": 0.10487765744328499,
|
|
"num_tokens": 703808.0,
|
|
"step": 340
|
|
},
|
|
{
|
|
"entropy": 7.251721620559692,
|
|
"epoch": 0.03129535558780842,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00017199999999999998,
|
|
"loss": 6.9813,
|
|
"mean_token_accuracy": 0.09775393083691597,
|
|
"num_tokens": 715701.0,
|
|
"step": 345
|
|
},
|
|
{
|
|
"entropy": 7.248662281036377,
|
|
"epoch": 0.0317489114658926,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.00017449999999999999,
|
|
"loss": 6.8396,
|
|
"mean_token_accuracy": 0.10250790566205978,
|
|
"num_tokens": 725635.0,
|
|
"step": 350
|
|
},
|
|
{
|
|
"entropy": 7.2260857105255125,
|
|
"epoch": 0.032202467343976776,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000177,
|
|
"loss": 6.8703,
|
|
"mean_token_accuracy": 0.0953724816441536,
|
|
"num_tokens": 734827.0,
|
|
"step": 355
|
|
},
|
|
{
|
|
"entropy": 7.1952399730682375,
|
|
"epoch": 0.03265602322206096,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0001795,
|
|
"loss": 6.7781,
|
|
"mean_token_accuracy": 0.10356629341840744,
|
|
"num_tokens": 744916.0,
|
|
"step": 360
|
|
},
|
|
{
|
|
"entropy": 7.194821214675903,
|
|
"epoch": 0.033109579100145135,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.000182,
|
|
"loss": 6.8991,
|
|
"mean_token_accuracy": 0.10033663883805274,
|
|
"num_tokens": 756021.0,
|
|
"step": 365
|
|
},
|
|
{
|
|
"entropy": 7.260288143157959,
|
|
"epoch": 0.03356313497822932,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0001845,
|
|
"loss": 6.9113,
|
|
"mean_token_accuracy": 0.0992978885769844,
|
|
"num_tokens": 766513.0,
|
|
"step": 370
|
|
},
|
|
{
|
|
"entropy": 7.201397514343261,
|
|
"epoch": 0.034016690856313495,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.000187,
|
|
"loss": 6.8958,
|
|
"mean_token_accuracy": 0.0985984705388546,
|
|
"num_tokens": 776049.0,
|
|
"step": 375
|
|
},
|
|
{
|
|
"entropy": 7.044051551818848,
|
|
"epoch": 0.03447024673439768,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0001895,
|
|
"loss": 6.8231,
|
|
"mean_token_accuracy": 0.10297032371163369,
|
|
"num_tokens": 786736.0,
|
|
"step": 380
|
|
},
|
|
{
|
|
"entropy": 7.260237407684326,
|
|
"epoch": 0.03492380261248186,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000192,
|
|
"loss": 6.8279,
|
|
"mean_token_accuracy": 0.09664658829569817,
|
|
"num_tokens": 797550.0,
|
|
"step": 385
|
|
},
|
|
{
|
|
"entropy": 7.245859956741333,
|
|
"epoch": 0.03537735849056604,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0001945,
|
|
"loss": 6.8971,
|
|
"mean_token_accuracy": 0.09864228665828705,
|
|
"num_tokens": 808382.0,
|
|
"step": 390
|
|
},
|
|
{
|
|
"entropy": 7.1667686939239506,
|
|
"epoch": 0.03583091436865022,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00019700000000000002,
|
|
"loss": 6.8204,
|
|
"mean_token_accuracy": 0.10059952437877655,
|
|
"num_tokens": 819223.0,
|
|
"step": 395
|
|
},
|
|
{
|
|
"entropy": 7.2114091396331785,
|
|
"epoch": 0.036284470246734396,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00019950000000000002,
|
|
"loss": 6.8042,
|
|
"mean_token_accuracy": 0.09473831579089165,
|
|
"num_tokens": 828994.0,
|
|
"step": 400
|
|
},
|
|
{
|
|
"entropy": 7.191949510574341,
|
|
"epoch": 0.03673802612481858,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000202,
|
|
"loss": 6.9443,
|
|
"mean_token_accuracy": 0.09205318689346313,
|
|
"num_tokens": 840333.0,
|
|
"step": 405
|
|
},
|
|
{
|
|
"entropy": 7.121156358718872,
|
|
"epoch": 0.037191582002902755,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00020449999999999998,
|
|
"loss": 6.7293,
|
|
"mean_token_accuracy": 0.10459425449371337,
|
|
"num_tokens": 851033.0,
|
|
"step": 410
|
|
},
|
|
{
|
|
"entropy": 7.063291597366333,
|
|
"epoch": 0.03764513788098694,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.000207,
|
|
"loss": 6.7723,
|
|
"mean_token_accuracy": 0.09623789712786675,
|
|
"num_tokens": 861588.0,
|
|
"step": 415
|
|
},
|
|
{
|
|
"entropy": 7.116500473022461,
|
|
"epoch": 0.038098693759071114,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0002095,
|
|
"loss": 6.8824,
|
|
"mean_token_accuracy": 0.10527986362576484,
|
|
"num_tokens": 871401.0,
|
|
"step": 420
|
|
},
|
|
{
|
|
"entropy": 7.107698678970337,
|
|
"epoch": 0.0385522496371553,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000212,
|
|
"loss": 6.798,
|
|
"mean_token_accuracy": 0.09808883890509605,
|
|
"num_tokens": 881948.0,
|
|
"step": 425
|
|
},
|
|
{
|
|
"entropy": 7.093855142593384,
|
|
"epoch": 0.03900580551523948,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0002145,
|
|
"loss": 6.7499,
|
|
"mean_token_accuracy": 0.10276206359267234,
|
|
"num_tokens": 891624.0,
|
|
"step": 430
|
|
},
|
|
{
|
|
"entropy": 7.118248414993286,
|
|
"epoch": 0.03945936139332366,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00021700000000000002,
|
|
"loss": 6.8649,
|
|
"mean_token_accuracy": 0.09989958107471467,
|
|
"num_tokens": 902468.0,
|
|
"step": 435
|
|
},
|
|
{
|
|
"entropy": 7.01951036453247,
|
|
"epoch": 0.03991291727140784,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0002195,
|
|
"loss": 6.7933,
|
|
"mean_token_accuracy": 0.10295612290501595,
|
|
"num_tokens": 912508.0,
|
|
"step": 440
|
|
},
|
|
{
|
|
"entropy": 7.089923477172851,
|
|
"epoch": 0.040366473149492016,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000222,
|
|
"loss": 6.8227,
|
|
"mean_token_accuracy": 0.10121235325932502,
|
|
"num_tokens": 923728.0,
|
|
"step": 445
|
|
},
|
|
{
|
|
"entropy": 7.064526224136353,
|
|
"epoch": 0.0408200290275762,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0002245,
|
|
"loss": 6.7884,
|
|
"mean_token_accuracy": 0.10058841332793236,
|
|
"num_tokens": 933197.0,
|
|
"step": 450
|
|
},
|
|
{
|
|
"entropy": 6.956214904785156,
|
|
"epoch": 0.041273584905660375,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00022700000000000002,
|
|
"loss": 6.5999,
|
|
"mean_token_accuracy": 0.10817481204867363,
|
|
"num_tokens": 943385.0,
|
|
"step": 455
|
|
},
|
|
{
|
|
"entropy": 6.93480110168457,
|
|
"epoch": 0.04172714078374456,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00022950000000000002,
|
|
"loss": 6.6521,
|
|
"mean_token_accuracy": 0.10884237810969352,
|
|
"num_tokens": 952674.0,
|
|
"step": 460
|
|
},
|
|
{
|
|
"entropy": 6.947038888931274,
|
|
"epoch": 0.042180696661828734,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00023200000000000003,
|
|
"loss": 6.7395,
|
|
"mean_token_accuracy": 0.10702011436223983,
|
|
"num_tokens": 962406.0,
|
|
"step": 465
|
|
},
|
|
{
|
|
"entropy": 7.075675964355469,
|
|
"epoch": 0.04263425253991292,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00023449999999999998,
|
|
"loss": 6.759,
|
|
"mean_token_accuracy": 0.10087487250566482,
|
|
"num_tokens": 973131.0,
|
|
"step": 470
|
|
},
|
|
{
|
|
"entropy": 6.923453664779663,
|
|
"epoch": 0.0430878084179971,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000237,
|
|
"loss": 6.6279,
|
|
"mean_token_accuracy": 0.10887465253472328,
|
|
"num_tokens": 982777.0,
|
|
"step": 475
|
|
},
|
|
{
|
|
"entropy": 6.913258600234985,
|
|
"epoch": 0.04354136429608128,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0002395,
|
|
"loss": 6.7205,
|
|
"mean_token_accuracy": 0.0963176041841507,
|
|
"num_tokens": 994498.0,
|
|
"step": 480
|
|
},
|
|
{
|
|
"entropy": 6.931819868087769,
|
|
"epoch": 0.04399492017416546,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.000242,
|
|
"loss": 6.7911,
|
|
"mean_token_accuracy": 0.1031719870865345,
|
|
"num_tokens": 1004256.0,
|
|
"step": 485
|
|
},
|
|
{
|
|
"entropy": 7.00779275894165,
|
|
"epoch": 0.044448476052249636,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0002445,
|
|
"loss": 6.7541,
|
|
"mean_token_accuracy": 0.09925626143813134,
|
|
"num_tokens": 1015172.0,
|
|
"step": 490
|
|
},
|
|
{
|
|
"entropy": 6.965081644058228,
|
|
"epoch": 0.04490203193033382,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.000247,
|
|
"loss": 6.6909,
|
|
"mean_token_accuracy": 0.10554371923208236,
|
|
"num_tokens": 1025636.0,
|
|
"step": 495
|
|
},
|
|
{
|
|
"entropy": 6.928272819519043,
|
|
"epoch": 0.045355587808417995,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0002495,
|
|
"loss": 6.7203,
|
|
"mean_token_accuracy": 0.11081329062581062,
|
|
"num_tokens": 1035674.0,
|
|
"step": 500
|
|
},
|
|
{
|
|
"entropy": 6.931467914581299,
|
|
"epoch": 0.04580914368650218,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000252,
|
|
"loss": 6.6966,
|
|
"mean_token_accuracy": 0.10857350751757622,
|
|
"num_tokens": 1045643.0,
|
|
"step": 505
|
|
},
|
|
{
|
|
"entropy": 6.945031785964966,
|
|
"epoch": 0.046262699564586354,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0002545,
|
|
"loss": 6.6697,
|
|
"mean_token_accuracy": 0.10533757880330086,
|
|
"num_tokens": 1056543.0,
|
|
"step": 510
|
|
},
|
|
{
|
|
"entropy": 6.877411794662476,
|
|
"epoch": 0.04671625544267054,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000257,
|
|
"loss": 6.6419,
|
|
"mean_token_accuracy": 0.10245436802506447,
|
|
"num_tokens": 1066828.0,
|
|
"step": 515
|
|
},
|
|
{
|
|
"entropy": 6.901714277267456,
|
|
"epoch": 0.04716981132075472,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0002595,
|
|
"loss": 6.6714,
|
|
"mean_token_accuracy": 0.10999734550714493,
|
|
"num_tokens": 1076230.0,
|
|
"step": 520
|
|
},
|
|
{
|
|
"entropy": 6.883963012695313,
|
|
"epoch": 0.047623367198838897,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000262,
|
|
"loss": 6.707,
|
|
"mean_token_accuracy": 0.10455554500222206,
|
|
"num_tokens": 1086430.0,
|
|
"step": 525
|
|
},
|
|
{
|
|
"entropy": 6.921725177764893,
|
|
"epoch": 0.04807692307692308,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00026450000000000003,
|
|
"loss": 6.6064,
|
|
"mean_token_accuracy": 0.11501444876194,
|
|
"num_tokens": 1096403.0,
|
|
"step": 530
|
|
},
|
|
{
|
|
"entropy": 6.7906153202056885,
|
|
"epoch": 0.048530478955007256,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00026700000000000004,
|
|
"loss": 6.5687,
|
|
"mean_token_accuracy": 0.11038950607180595,
|
|
"num_tokens": 1107289.0,
|
|
"step": 535
|
|
},
|
|
{
|
|
"entropy": 6.942843580245972,
|
|
"epoch": 0.04898403483309144,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00026950000000000005,
|
|
"loss": 6.7614,
|
|
"mean_token_accuracy": 0.09955370277166367,
|
|
"num_tokens": 1118301.0,
|
|
"step": 540
|
|
},
|
|
{
|
|
"entropy": 6.997049474716187,
|
|
"epoch": 0.049437590711175615,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00027200000000000005,
|
|
"loss": 6.737,
|
|
"mean_token_accuracy": 0.10176396444439888,
|
|
"num_tokens": 1129002.0,
|
|
"step": 545
|
|
},
|
|
{
|
|
"entropy": 6.818488597869873,
|
|
"epoch": 0.0498911465892598,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0002745,
|
|
"loss": 6.7196,
|
|
"mean_token_accuracy": 0.10543971955776214,
|
|
"num_tokens": 1139415.0,
|
|
"step": 550
|
|
},
|
|
{
|
|
"entropy": 6.8720558166503904,
|
|
"epoch": 0.050344702467343974,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000277,
|
|
"loss": 6.6889,
|
|
"mean_token_accuracy": 0.10523920580744743,
|
|
"num_tokens": 1151231.0,
|
|
"step": 555
|
|
},
|
|
{
|
|
"entropy": 6.720426321029663,
|
|
"epoch": 0.05079825834542816,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0002795,
|
|
"loss": 6.5739,
|
|
"mean_token_accuracy": 0.10560568794608116,
|
|
"num_tokens": 1161643.0,
|
|
"step": 560
|
|
},
|
|
{
|
|
"entropy": 6.868243741989136,
|
|
"epoch": 0.05125181422351233,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00028199999999999997,
|
|
"loss": 6.624,
|
|
"mean_token_accuracy": 0.10310710221529007,
|
|
"num_tokens": 1173362.0,
|
|
"step": 565
|
|
},
|
|
{
|
|
"entropy": 6.858621978759766,
|
|
"epoch": 0.051705370101596516,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0002845,
|
|
"loss": 6.629,
|
|
"mean_token_accuracy": 0.10223327353596687,
|
|
"num_tokens": 1184812.0,
|
|
"step": 570
|
|
},
|
|
{
|
|
"entropy": 6.851276063919068,
|
|
"epoch": 0.0521589259796807,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000287,
|
|
"loss": 6.5943,
|
|
"mean_token_accuracy": 0.1135420560836792,
|
|
"num_tokens": 1195556.0,
|
|
"step": 575
|
|
},
|
|
{
|
|
"entropy": 6.787323379516602,
|
|
"epoch": 0.052612481857764876,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0002895,
|
|
"loss": 6.6018,
|
|
"mean_token_accuracy": 0.11323990225791931,
|
|
"num_tokens": 1206735.0,
|
|
"step": 580
|
|
},
|
|
{
|
|
"entropy": 6.803449630737305,
|
|
"epoch": 0.05306603773584906,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000292,
|
|
"loss": 6.7011,
|
|
"mean_token_accuracy": 0.10117989927530288,
|
|
"num_tokens": 1216778.0,
|
|
"step": 585
|
|
},
|
|
{
|
|
"entropy": 6.848930168151855,
|
|
"epoch": 0.053519593613933235,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0002945,
|
|
"loss": 6.6297,
|
|
"mean_token_accuracy": 0.1108930803835392,
|
|
"num_tokens": 1227462.0,
|
|
"step": 590
|
|
},
|
|
{
|
|
"entropy": 6.823454809188843,
|
|
"epoch": 0.05397314949201742,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000297,
|
|
"loss": 6.6961,
|
|
"mean_token_accuracy": 0.10993156135082245,
|
|
"num_tokens": 1237378.0,
|
|
"step": 595
|
|
},
|
|
{
|
|
"entropy": 6.806218099594116,
|
|
"epoch": 0.054426705370101594,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0002995,
|
|
"loss": 6.6763,
|
|
"mean_token_accuracy": 0.10614893436431885,
|
|
"num_tokens": 1247599.0,
|
|
"step": 600
|
|
},
|
|
{
|
|
"entropy": 6.748168039321899,
|
|
"epoch": 0.05488026124818578,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000302,
|
|
"loss": 6.5415,
|
|
"mean_token_accuracy": 0.10683367103338241,
|
|
"num_tokens": 1257989.0,
|
|
"step": 605
|
|
},
|
|
{
|
|
"entropy": 6.828956031799317,
|
|
"epoch": 0.05533381712626995,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0003045,
|
|
"loss": 6.6517,
|
|
"mean_token_accuracy": 0.10376828461885453,
|
|
"num_tokens": 1269313.0,
|
|
"step": 610
|
|
},
|
|
{
|
|
"entropy": 6.829959964752197,
|
|
"epoch": 0.055787373004354136,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000307,
|
|
"loss": 6.6361,
|
|
"mean_token_accuracy": 0.10490350201725959,
|
|
"num_tokens": 1280422.0,
|
|
"step": 615
|
|
},
|
|
{
|
|
"entropy": 6.7708775997161865,
|
|
"epoch": 0.05624092888243832,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0003095,
|
|
"loss": 6.6623,
|
|
"mean_token_accuracy": 0.10884316489100457,
|
|
"num_tokens": 1289482.0,
|
|
"step": 620
|
|
},
|
|
{
|
|
"entropy": 6.763772773742676,
|
|
"epoch": 0.056694484760522496,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000312,
|
|
"loss": 6.6181,
|
|
"mean_token_accuracy": 0.10594562590122222,
|
|
"num_tokens": 1299782.0,
|
|
"step": 625
|
|
},
|
|
{
|
|
"entropy": 6.758108377456665,
|
|
"epoch": 0.05714804063860668,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0003145,
|
|
"loss": 6.5993,
|
|
"mean_token_accuracy": 0.11340658813714981,
|
|
"num_tokens": 1311628.0,
|
|
"step": 630
|
|
},
|
|
{
|
|
"entropy": 6.796287631988525,
|
|
"epoch": 0.057601596516690855,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000317,
|
|
"loss": 6.655,
|
|
"mean_token_accuracy": 0.10296097546815872,
|
|
"num_tokens": 1322456.0,
|
|
"step": 635
|
|
},
|
|
{
|
|
"entropy": 6.721327924728394,
|
|
"epoch": 0.05805515239477504,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0003195,
|
|
"loss": 6.5153,
|
|
"mean_token_accuracy": 0.11600816994905472,
|
|
"num_tokens": 1331737.0,
|
|
"step": 640
|
|
},
|
|
{
|
|
"entropy": 6.746915245056153,
|
|
"epoch": 0.058508708272859214,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.000322,
|
|
"loss": 6.5369,
|
|
"mean_token_accuracy": 0.10856858938932419,
|
|
"num_tokens": 1341236.0,
|
|
"step": 645
|
|
},
|
|
{
|
|
"entropy": 6.563586473464966,
|
|
"epoch": 0.0589622641509434,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00032450000000000003,
|
|
"loss": 6.5459,
|
|
"mean_token_accuracy": 0.11117523983120918,
|
|
"num_tokens": 1352885.0,
|
|
"step": 650
|
|
},
|
|
{
|
|
"entropy": 6.767751598358155,
|
|
"epoch": 0.05941582002902757,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00032700000000000003,
|
|
"loss": 6.5208,
|
|
"mean_token_accuracy": 0.10883594155311585,
|
|
"num_tokens": 1363455.0,
|
|
"step": 655
|
|
},
|
|
{
|
|
"entropy": 6.698432683944702,
|
|
"epoch": 0.059869375907111756,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00032950000000000004,
|
|
"loss": 6.5548,
|
|
"mean_token_accuracy": 0.11928504556417466,
|
|
"num_tokens": 1373176.0,
|
|
"step": 660
|
|
},
|
|
{
|
|
"entropy": 6.799010419845581,
|
|
"epoch": 0.06032293178519594,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00033200000000000005,
|
|
"loss": 6.6198,
|
|
"mean_token_accuracy": 0.10528008192777634,
|
|
"num_tokens": 1383122.0,
|
|
"step": 665
|
|
},
|
|
{
|
|
"entropy": 6.690959692001343,
|
|
"epoch": 0.060776487663280115,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00033450000000000005,
|
|
"loss": 6.4729,
|
|
"mean_token_accuracy": 0.11281677708029747,
|
|
"num_tokens": 1392889.0,
|
|
"step": 670
|
|
},
|
|
{
|
|
"entropy": 6.623794364929199,
|
|
"epoch": 0.0612300435413643,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000337,
|
|
"loss": 6.5809,
|
|
"mean_token_accuracy": 0.10769900307059288,
|
|
"num_tokens": 1403450.0,
|
|
"step": 675
|
|
},
|
|
{
|
|
"entropy": 6.742135953903198,
|
|
"epoch": 0.061683599419448475,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0003395,
|
|
"loss": 6.6187,
|
|
"mean_token_accuracy": 0.1039137601852417,
|
|
"num_tokens": 1414075.0,
|
|
"step": 680
|
|
},
|
|
{
|
|
"entropy": 6.662317562103271,
|
|
"epoch": 0.06213715529753266,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000342,
|
|
"loss": 6.5274,
|
|
"mean_token_accuracy": 0.10077093541622162,
|
|
"num_tokens": 1424376.0,
|
|
"step": 685
|
|
},
|
|
{
|
|
"entropy": 6.750758123397827,
|
|
"epoch": 0.06259071117561683,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00034449999999999997,
|
|
"loss": 6.512,
|
|
"mean_token_accuracy": 0.11837425976991653,
|
|
"num_tokens": 1433780.0,
|
|
"step": 690
|
|
},
|
|
{
|
|
"entropy": 6.588320541381836,
|
|
"epoch": 0.06304426705370102,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000347,
|
|
"loss": 6.5228,
|
|
"mean_token_accuracy": 0.1112312689423561,
|
|
"num_tokens": 1444179.0,
|
|
"step": 695
|
|
},
|
|
{
|
|
"entropy": 6.737683391571045,
|
|
"epoch": 0.0634978229317852,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0003495,
|
|
"loss": 6.5988,
|
|
"mean_token_accuracy": 0.10832765325903893,
|
|
"num_tokens": 1455342.0,
|
|
"step": 700
|
|
},
|
|
{
|
|
"entropy": 6.5270322322845455,
|
|
"epoch": 0.06395137880986937,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000352,
|
|
"loss": 6.4367,
|
|
"mean_token_accuracy": 0.11744177639484406,
|
|
"num_tokens": 1465007.0,
|
|
"step": 705
|
|
},
|
|
{
|
|
"entropy": 6.8013591289520265,
|
|
"epoch": 0.06440493468795355,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0003545,
|
|
"loss": 6.6072,
|
|
"mean_token_accuracy": 0.11265634968876839,
|
|
"num_tokens": 1474658.0,
|
|
"step": 710
|
|
},
|
|
{
|
|
"entropy": 6.754550743103027,
|
|
"epoch": 0.06485849056603774,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000357,
|
|
"loss": 6.6558,
|
|
"mean_token_accuracy": 0.10501691550016404,
|
|
"num_tokens": 1485366.0,
|
|
"step": 715
|
|
},
|
|
{
|
|
"entropy": 6.6456946849823,
|
|
"epoch": 0.06531204644412192,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0003595,
|
|
"loss": 6.5397,
|
|
"mean_token_accuracy": 0.11587660536170005,
|
|
"num_tokens": 1496931.0,
|
|
"step": 720
|
|
},
|
|
{
|
|
"entropy": 6.688676929473877,
|
|
"epoch": 0.0657656023222061,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000362,
|
|
"loss": 6.5915,
|
|
"mean_token_accuracy": 0.11367620155215263,
|
|
"num_tokens": 1507134.0,
|
|
"step": 725
|
|
},
|
|
{
|
|
"entropy": 6.569495010375976,
|
|
"epoch": 0.06621915820029027,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0003645,
|
|
"loss": 6.492,
|
|
"mean_token_accuracy": 0.11305128559470176,
|
|
"num_tokens": 1516558.0,
|
|
"step": 730
|
|
},
|
|
{
|
|
"entropy": 6.637685918807984,
|
|
"epoch": 0.06667271407837445,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000367,
|
|
"loss": 6.5268,
|
|
"mean_token_accuracy": 0.11118611544370652,
|
|
"num_tokens": 1526373.0,
|
|
"step": 735
|
|
},
|
|
{
|
|
"entropy": 6.5918787002563475,
|
|
"epoch": 0.06712626995645864,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0003695,
|
|
"loss": 6.4146,
|
|
"mean_token_accuracy": 0.11430680304765702,
|
|
"num_tokens": 1536431.0,
|
|
"step": 740
|
|
},
|
|
{
|
|
"entropy": 6.4868128299713135,
|
|
"epoch": 0.06757982583454282,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000372,
|
|
"loss": 6.3912,
|
|
"mean_token_accuracy": 0.11714110746979714,
|
|
"num_tokens": 1546428.0,
|
|
"step": 745
|
|
},
|
|
{
|
|
"entropy": 6.633748626708984,
|
|
"epoch": 0.06803338171262699,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0003745,
|
|
"loss": 6.5954,
|
|
"mean_token_accuracy": 0.10997304171323777,
|
|
"num_tokens": 1557299.0,
|
|
"step": 750
|
|
},
|
|
{
|
|
"entropy": 6.572169256210327,
|
|
"epoch": 0.06848693759071117,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000377,
|
|
"loss": 6.5201,
|
|
"mean_token_accuracy": 0.11121420338749885,
|
|
"num_tokens": 1567629.0,
|
|
"step": 755
|
|
},
|
|
{
|
|
"entropy": 6.670825052261352,
|
|
"epoch": 0.06894049346879536,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0003795,
|
|
"loss": 6.567,
|
|
"mean_token_accuracy": 0.10907985046505927,
|
|
"num_tokens": 1578305.0,
|
|
"step": 760
|
|
},
|
|
{
|
|
"entropy": 6.6835836410522464,
|
|
"epoch": 0.06939404934687954,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000382,
|
|
"loss": 6.5758,
|
|
"mean_token_accuracy": 0.10975592210888863,
|
|
"num_tokens": 1588843.0,
|
|
"step": 765
|
|
},
|
|
{
|
|
"entropy": 6.6111774921417235,
|
|
"epoch": 0.06984760522496372,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0003845,
|
|
"loss": 6.5869,
|
|
"mean_token_accuracy": 0.10726779997348786,
|
|
"num_tokens": 1599144.0,
|
|
"step": 770
|
|
},
|
|
{
|
|
"entropy": 6.559026432037354,
|
|
"epoch": 0.07030116110304789,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00038700000000000003,
|
|
"loss": 6.5004,
|
|
"mean_token_accuracy": 0.11508158072829247,
|
|
"num_tokens": 1608933.0,
|
|
"step": 775
|
|
},
|
|
{
|
|
"entropy": 6.675729131698608,
|
|
"epoch": 0.07075471698113207,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00038950000000000003,
|
|
"loss": 6.4774,
|
|
"mean_token_accuracy": 0.11884681731462479,
|
|
"num_tokens": 1618926.0,
|
|
"step": 780
|
|
},
|
|
{
|
|
"entropy": 6.550394296646118,
|
|
"epoch": 0.07120827285921626,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00039200000000000004,
|
|
"loss": 6.4787,
|
|
"mean_token_accuracy": 0.11670367419719696,
|
|
"num_tokens": 1628810.0,
|
|
"step": 785
|
|
},
|
|
{
|
|
"entropy": 6.621820545196533,
|
|
"epoch": 0.07166182873730044,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00039450000000000005,
|
|
"loss": 6.5208,
|
|
"mean_token_accuracy": 0.11667616367340088,
|
|
"num_tokens": 1638087.0,
|
|
"step": 790
|
|
},
|
|
{
|
|
"entropy": 6.551448202133178,
|
|
"epoch": 0.07211538461538461,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00039700000000000005,
|
|
"loss": 6.5028,
|
|
"mean_token_accuracy": 0.11246806755661964,
|
|
"num_tokens": 1648901.0,
|
|
"step": 795
|
|
},
|
|
{
|
|
"entropy": 6.536881732940674,
|
|
"epoch": 0.07256894049346879,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0003995,
|
|
"loss": 6.4789,
|
|
"mean_token_accuracy": 0.11289835795760154,
|
|
"num_tokens": 1659520.0,
|
|
"step": 800
|
|
},
|
|
{
|
|
"entropy": 6.606709718704224,
|
|
"epoch": 0.07302249637155298,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000402,
|
|
"loss": 6.5056,
|
|
"mean_token_accuracy": 0.11811064779758454,
|
|
"num_tokens": 1670368.0,
|
|
"step": 805
|
|
},
|
|
{
|
|
"entropy": 6.547958660125732,
|
|
"epoch": 0.07347605224963716,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004045,
|
|
"loss": 6.4255,
|
|
"mean_token_accuracy": 0.11519890055060386,
|
|
"num_tokens": 1680566.0,
|
|
"step": 810
|
|
},
|
|
{
|
|
"entropy": 6.525753402709961,
|
|
"epoch": 0.07392960812772134,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00040699999999999997,
|
|
"loss": 6.4451,
|
|
"mean_token_accuracy": 0.1210486575961113,
|
|
"num_tokens": 1690360.0,
|
|
"step": 815
|
|
},
|
|
{
|
|
"entropy": 6.6042615413665775,
|
|
"epoch": 0.07438316400580551,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004095,
|
|
"loss": 6.5412,
|
|
"mean_token_accuracy": 0.11525689661502839,
|
|
"num_tokens": 1700558.0,
|
|
"step": 820
|
|
},
|
|
{
|
|
"entropy": 6.546953964233398,
|
|
"epoch": 0.0748367198838897,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000412,
|
|
"loss": 6.4773,
|
|
"mean_token_accuracy": 0.1132320411503315,
|
|
"num_tokens": 1711067.0,
|
|
"step": 825
|
|
},
|
|
{
|
|
"entropy": 6.471474742889404,
|
|
"epoch": 0.07529027576197388,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004145,
|
|
"loss": 6.4551,
|
|
"mean_token_accuracy": 0.11387050226330757,
|
|
"num_tokens": 1721083.0,
|
|
"step": 830
|
|
},
|
|
{
|
|
"entropy": 6.426329278945923,
|
|
"epoch": 0.07574383164005806,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000417,
|
|
"loss": 6.387,
|
|
"mean_token_accuracy": 0.11764025613665581,
|
|
"num_tokens": 1731395.0,
|
|
"step": 835
|
|
},
|
|
{
|
|
"entropy": 6.560748338699341,
|
|
"epoch": 0.07619738751814223,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004195,
|
|
"loss": 6.4163,
|
|
"mean_token_accuracy": 0.12031056880950927,
|
|
"num_tokens": 1741650.0,
|
|
"step": 840
|
|
},
|
|
{
|
|
"entropy": 6.521653699874878,
|
|
"epoch": 0.07665094339622641,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000422,
|
|
"loss": 6.4952,
|
|
"mean_token_accuracy": 0.11156592816114426,
|
|
"num_tokens": 1752775.0,
|
|
"step": 845
|
|
},
|
|
{
|
|
"entropy": 6.523869276046753,
|
|
"epoch": 0.0771044992743106,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004245,
|
|
"loss": 6.5518,
|
|
"mean_token_accuracy": 0.10881832614541054,
|
|
"num_tokens": 1763635.0,
|
|
"step": 850
|
|
},
|
|
{
|
|
"entropy": 6.519516324996948,
|
|
"epoch": 0.07755805515239478,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000427,
|
|
"loss": 6.4713,
|
|
"mean_token_accuracy": 0.11356355622410774,
|
|
"num_tokens": 1773519.0,
|
|
"step": 855
|
|
},
|
|
{
|
|
"entropy": 6.527148103713989,
|
|
"epoch": 0.07801161103047896,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004295,
|
|
"loss": 6.4688,
|
|
"mean_token_accuracy": 0.11615480259060859,
|
|
"num_tokens": 1783643.0,
|
|
"step": 860
|
|
},
|
|
{
|
|
"entropy": 6.563126754760742,
|
|
"epoch": 0.07846516690856313,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000432,
|
|
"loss": 6.4573,
|
|
"mean_token_accuracy": 0.11113109216094016,
|
|
"num_tokens": 1794175.0,
|
|
"step": 865
|
|
},
|
|
{
|
|
"entropy": 6.464490938186645,
|
|
"epoch": 0.07891872278664731,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004345,
|
|
"loss": 6.3923,
|
|
"mean_token_accuracy": 0.11603446528315545,
|
|
"num_tokens": 1804455.0,
|
|
"step": 870
|
|
},
|
|
{
|
|
"entropy": 6.563748025894165,
|
|
"epoch": 0.0793722786647315,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000437,
|
|
"loss": 6.5214,
|
|
"mean_token_accuracy": 0.10870628133416176,
|
|
"num_tokens": 1816711.0,
|
|
"step": 875
|
|
},
|
|
{
|
|
"entropy": 6.4233174324035645,
|
|
"epoch": 0.07982583454281568,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004395,
|
|
"loss": 6.3755,
|
|
"mean_token_accuracy": 0.11397543773055077,
|
|
"num_tokens": 1827110.0,
|
|
"step": 880
|
|
},
|
|
{
|
|
"entropy": 6.4231466293334964,
|
|
"epoch": 0.08027939042089985,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000442,
|
|
"loss": 6.3352,
|
|
"mean_token_accuracy": 0.11892382502555847,
|
|
"num_tokens": 1837131.0,
|
|
"step": 885
|
|
},
|
|
{
|
|
"entropy": 6.53260645866394,
|
|
"epoch": 0.08073294629898403,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004445,
|
|
"loss": 6.4013,
|
|
"mean_token_accuracy": 0.11561454683542252,
|
|
"num_tokens": 1847487.0,
|
|
"step": 890
|
|
},
|
|
{
|
|
"entropy": 6.347210311889649,
|
|
"epoch": 0.08118650217706821,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000447,
|
|
"loss": 6.3894,
|
|
"mean_token_accuracy": 0.11477004811167717,
|
|
"num_tokens": 1857846.0,
|
|
"step": 895
|
|
},
|
|
{
|
|
"entropy": 6.445382356643677,
|
|
"epoch": 0.0816400580551524,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00044950000000000003,
|
|
"loss": 6.4744,
|
|
"mean_token_accuracy": 0.11803903207182884,
|
|
"num_tokens": 1868917.0,
|
|
"step": 900
|
|
},
|
|
{
|
|
"entropy": 6.475826025009155,
|
|
"epoch": 0.08209361393323658,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00045200000000000004,
|
|
"loss": 6.3185,
|
|
"mean_token_accuracy": 0.12133634760975838,
|
|
"num_tokens": 1878702.0,
|
|
"step": 905
|
|
},
|
|
{
|
|
"entropy": 6.4152826309204105,
|
|
"epoch": 0.08254716981132075,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00045450000000000004,
|
|
"loss": 6.4281,
|
|
"mean_token_accuracy": 0.11487874239683152,
|
|
"num_tokens": 1888818.0,
|
|
"step": 910
|
|
},
|
|
{
|
|
"entropy": 6.452651023864746,
|
|
"epoch": 0.08300072568940493,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00045700000000000005,
|
|
"loss": 6.4189,
|
|
"mean_token_accuracy": 0.11924608796834946,
|
|
"num_tokens": 1899418.0,
|
|
"step": 915
|
|
},
|
|
{
|
|
"entropy": 6.365463924407959,
|
|
"epoch": 0.08345428156748912,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00045950000000000006,
|
|
"loss": 6.3128,
|
|
"mean_token_accuracy": 0.12437145933508872,
|
|
"num_tokens": 1909747.0,
|
|
"step": 920
|
|
},
|
|
{
|
|
"entropy": 6.544213724136353,
|
|
"epoch": 0.0839078374455733,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000462,
|
|
"loss": 6.5157,
|
|
"mean_token_accuracy": 0.11182530298829078,
|
|
"num_tokens": 1920580.0,
|
|
"step": 925
|
|
},
|
|
{
|
|
"entropy": 6.49947943687439,
|
|
"epoch": 0.08436139332365747,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004645,
|
|
"loss": 6.4255,
|
|
"mean_token_accuracy": 0.11744101867079734,
|
|
"num_tokens": 1930924.0,
|
|
"step": 930
|
|
},
|
|
{
|
|
"entropy": 6.417445230484009,
|
|
"epoch": 0.08481494920174165,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000467,
|
|
"loss": 6.4568,
|
|
"mean_token_accuracy": 0.11753653734922409,
|
|
"num_tokens": 1943110.0,
|
|
"step": 935
|
|
},
|
|
{
|
|
"entropy": 6.492831611633301,
|
|
"epoch": 0.08526850507982583,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004695,
|
|
"loss": 6.3711,
|
|
"mean_token_accuracy": 0.11840087100863457,
|
|
"num_tokens": 1952620.0,
|
|
"step": 940
|
|
},
|
|
{
|
|
"entropy": 6.451150608062744,
|
|
"epoch": 0.08572206095791002,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000472,
|
|
"loss": 6.4812,
|
|
"mean_token_accuracy": 0.11905809268355369,
|
|
"num_tokens": 1962893.0,
|
|
"step": 945
|
|
},
|
|
{
|
|
"entropy": 6.375366497039795,
|
|
"epoch": 0.0861756168359942,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004745,
|
|
"loss": 6.3692,
|
|
"mean_token_accuracy": 0.1131294883787632,
|
|
"num_tokens": 1973455.0,
|
|
"step": 950
|
|
},
|
|
{
|
|
"entropy": 6.364347743988037,
|
|
"epoch": 0.08662917271407837,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000477,
|
|
"loss": 6.3287,
|
|
"mean_token_accuracy": 0.12613395005464553,
|
|
"num_tokens": 1983559.0,
|
|
"step": 955
|
|
},
|
|
{
|
|
"entropy": 6.371630477905273,
|
|
"epoch": 0.08708272859216255,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004795,
|
|
"loss": 6.3393,
|
|
"mean_token_accuracy": 0.12109395638108253,
|
|
"num_tokens": 1994630.0,
|
|
"step": 960
|
|
},
|
|
{
|
|
"entropy": 6.490744590759277,
|
|
"epoch": 0.08753628447024674,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000482,
|
|
"loss": 6.4846,
|
|
"mean_token_accuracy": 0.12091940119862557,
|
|
"num_tokens": 2005225.0,
|
|
"step": 965
|
|
},
|
|
{
|
|
"entropy": 6.43569803237915,
|
|
"epoch": 0.08798984034833092,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004845,
|
|
"loss": 6.4423,
|
|
"mean_token_accuracy": 0.11586240753531456,
|
|
"num_tokens": 2016431.0,
|
|
"step": 970
|
|
},
|
|
{
|
|
"entropy": 6.4423645496368405,
|
|
"epoch": 0.08844339622641509,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000487,
|
|
"loss": 6.417,
|
|
"mean_token_accuracy": 0.11866187751293182,
|
|
"num_tokens": 2025740.0,
|
|
"step": 975
|
|
},
|
|
{
|
|
"entropy": 6.464833211898804,
|
|
"epoch": 0.08889695210449927,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004895,
|
|
"loss": 6.4715,
|
|
"mean_token_accuracy": 0.11230053454637527,
|
|
"num_tokens": 2037748.0,
|
|
"step": 980
|
|
},
|
|
{
|
|
"entropy": 6.4517669677734375,
|
|
"epoch": 0.08935050798258345,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000492,
|
|
"loss": 6.4799,
|
|
"mean_token_accuracy": 0.11359175741672516,
|
|
"num_tokens": 2047882.0,
|
|
"step": 985
|
|
},
|
|
{
|
|
"entropy": 6.344726705551148,
|
|
"epoch": 0.08980406386066764,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004945,
|
|
"loss": 6.2499,
|
|
"mean_token_accuracy": 0.12739444598555566,
|
|
"num_tokens": 2057291.0,
|
|
"step": 990
|
|
},
|
|
{
|
|
"entropy": 6.410989761352539,
|
|
"epoch": 0.09025761973875182,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000497,
|
|
"loss": 6.3915,
|
|
"mean_token_accuracy": 0.11595515459775925,
|
|
"num_tokens": 2068420.0,
|
|
"step": 995
|
|
},
|
|
{
|
|
"entropy": 6.440128231048584,
|
|
"epoch": 0.09071117561683599,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004995,
|
|
"loss": 6.5057,
|
|
"mean_token_accuracy": 0.11650898307561874,
|
|
"num_tokens": 2077721.0,
|
|
"step": 1000
|
|
},
|
|
{
|
|
"entropy": 6.404371500015259,
|
|
"epoch": 0.09116473149492017,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999999985110217,
|
|
"loss": 6.4196,
|
|
"mean_token_accuracy": 0.11519975513219834,
|
|
"num_tokens": 2087434.0,
|
|
"step": 1005
|
|
},
|
|
{
|
|
"entropy": 6.462897062301636,
|
|
"epoch": 0.09161828737300436,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004999999924620471,
|
|
"loss": 6.4416,
|
|
"mean_token_accuracy": 0.11368417963385583,
|
|
"num_tokens": 2098193.0,
|
|
"step": 1010
|
|
},
|
|
{
|
|
"entropy": 6.384410095214844,
|
|
"epoch": 0.09207184325108854,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004999999817600155,
|
|
"loss": 6.3826,
|
|
"mean_token_accuracy": 0.12369435802102088,
|
|
"num_tokens": 2108201.0,
|
|
"step": 1015
|
|
},
|
|
{
|
|
"entropy": 6.309185791015625,
|
|
"epoch": 0.09252539912917271,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004999999664049268,
|
|
"loss": 6.32,
|
|
"mean_token_accuracy": 0.11705849245190621,
|
|
"num_tokens": 2119036.0,
|
|
"step": 1020
|
|
},
|
|
{
|
|
"entropy": 6.421576452255249,
|
|
"epoch": 0.09297895500725689,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999999463967816,
|
|
"loss": 6.3502,
|
|
"mean_token_accuracy": 0.1220113031566143,
|
|
"num_tokens": 2129487.0,
|
|
"step": 1025
|
|
},
|
|
{
|
|
"entropy": 6.344693613052368,
|
|
"epoch": 0.09343251088534107,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00049999992173558,
|
|
"loss": 6.3793,
|
|
"mean_token_accuracy": 0.11463537812232971,
|
|
"num_tokens": 2139992.0,
|
|
"step": 1030
|
|
},
|
|
{
|
|
"entropy": 6.273680925369263,
|
|
"epoch": 0.09388606676342526,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999998924213228,
|
|
"loss": 6.2978,
|
|
"mean_token_accuracy": 0.12567788735032082,
|
|
"num_tokens": 2149579.0,
|
|
"step": 1035
|
|
},
|
|
{
|
|
"entropy": 6.34424147605896,
|
|
"epoch": 0.09433962264150944,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999998584540105,
|
|
"loss": 6.3323,
|
|
"mean_token_accuracy": 0.11910404115915299,
|
|
"num_tokens": 2159876.0,
|
|
"step": 1040
|
|
},
|
|
{
|
|
"entropy": 6.344080543518066,
|
|
"epoch": 0.09479317851959361,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999998198336437,
|
|
"loss": 6.3607,
|
|
"mean_token_accuracy": 0.11824791878461838,
|
|
"num_tokens": 2169975.0,
|
|
"step": 1045
|
|
},
|
|
{
|
|
"entropy": 6.427093935012818,
|
|
"epoch": 0.09524673439767779,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999997765602233,
|
|
"loss": 6.4922,
|
|
"mean_token_accuracy": 0.11570862457156181,
|
|
"num_tokens": 2180050.0,
|
|
"step": 1050
|
|
},
|
|
{
|
|
"entropy": 6.349902772903443,
|
|
"epoch": 0.09570029027576198,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999997286337502,
|
|
"loss": 6.3077,
|
|
"mean_token_accuracy": 0.12012091800570487,
|
|
"num_tokens": 2189876.0,
|
|
"step": 1055
|
|
},
|
|
{
|
|
"entropy": 6.452189254760742,
|
|
"epoch": 0.09615384615384616,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004999996760542254,
|
|
"loss": 6.4339,
|
|
"mean_token_accuracy": 0.11986624225974082,
|
|
"num_tokens": 2200281.0,
|
|
"step": 1060
|
|
},
|
|
{
|
|
"entropy": 6.32034740447998,
|
|
"epoch": 0.09660740203193033,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00049999961882165,
|
|
"loss": 6.3044,
|
|
"mean_token_accuracy": 0.12321286574006081,
|
|
"num_tokens": 2210369.0,
|
|
"step": 1065
|
|
},
|
|
{
|
|
"entropy": 6.327759885787964,
|
|
"epoch": 0.09706095791001451,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999995569360251,
|
|
"loss": 6.3127,
|
|
"mean_token_accuracy": 0.12402729466557502,
|
|
"num_tokens": 2221990.0,
|
|
"step": 1070
|
|
},
|
|
{
|
|
"entropy": 6.366653490066528,
|
|
"epoch": 0.0975145137880987,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000499999490397352,
|
|
"loss": 6.4474,
|
|
"mean_token_accuracy": 0.11773798763751983,
|
|
"num_tokens": 2233252.0,
|
|
"step": 1075
|
|
},
|
|
{
|
|
"entropy": 6.317323875427246,
|
|
"epoch": 0.09796806966618288,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999994192056321,
|
|
"loss": 6.3302,
|
|
"mean_token_accuracy": 0.1180254340171814,
|
|
"num_tokens": 2243527.0,
|
|
"step": 1080
|
|
},
|
|
{
|
|
"entropy": 6.509728670120239,
|
|
"epoch": 0.09842162554426705,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999993433608669,
|
|
"loss": 6.5429,
|
|
"mean_token_accuracy": 0.11201546043157577,
|
|
"num_tokens": 2255879.0,
|
|
"step": 1085
|
|
},
|
|
{
|
|
"entropy": 6.402245807647705,
|
|
"epoch": 0.09887518142235123,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999992628630579,
|
|
"loss": 6.3557,
|
|
"mean_token_accuracy": 0.11973690539598465,
|
|
"num_tokens": 2266515.0,
|
|
"step": 1090
|
|
},
|
|
{
|
|
"entropy": 6.339201927185059,
|
|
"epoch": 0.09932873730043541,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999991777122069,
|
|
"loss": 6.4273,
|
|
"mean_token_accuracy": 0.12359791249036789,
|
|
"num_tokens": 2276876.0,
|
|
"step": 1095
|
|
},
|
|
{
|
|
"entropy": 6.246776485443116,
|
|
"epoch": 0.0997822931785196,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999990879083156,
|
|
"loss": 6.2678,
|
|
"mean_token_accuracy": 0.12031552121043206,
|
|
"num_tokens": 2287467.0,
|
|
"step": 1100
|
|
},
|
|
{
|
|
"entropy": 6.35769305229187,
|
|
"epoch": 0.10023584905660378,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999989934513857,
|
|
"loss": 6.2462,
|
|
"mean_token_accuracy": 0.12475912868976594,
|
|
"num_tokens": 2297907.0,
|
|
"step": 1105
|
|
},
|
|
{
|
|
"entropy": 6.35407977104187,
|
|
"epoch": 0.10068940493468795,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999988943414193,
|
|
"loss": 6.3535,
|
|
"mean_token_accuracy": 0.1271662712097168,
|
|
"num_tokens": 2307955.0,
|
|
"step": 1110
|
|
},
|
|
{
|
|
"entropy": 6.295737075805664,
|
|
"epoch": 0.10114296081277213,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999987905784184,
|
|
"loss": 6.2987,
|
|
"mean_token_accuracy": 0.12096831873059273,
|
|
"num_tokens": 2318545.0,
|
|
"step": 1115
|
|
},
|
|
{
|
|
"entropy": 6.236451482772827,
|
|
"epoch": 0.10159651669085631,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999986821623853,
|
|
"loss": 6.2202,
|
|
"mean_token_accuracy": 0.12809522673487664,
|
|
"num_tokens": 2327706.0,
|
|
"step": 1120
|
|
},
|
|
{
|
|
"entropy": 6.412763261795044,
|
|
"epoch": 0.1020500725689405,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999985690933219,
|
|
"loss": 6.4203,
|
|
"mean_token_accuracy": 0.11205516159534454,
|
|
"num_tokens": 2337853.0,
|
|
"step": 1125
|
|
},
|
|
{
|
|
"entropy": 6.159422540664673,
|
|
"epoch": 0.10250362844702467,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999984513712311,
|
|
"loss": 6.1984,
|
|
"mean_token_accuracy": 0.12132447883486748,
|
|
"num_tokens": 2348340.0,
|
|
"step": 1130
|
|
},
|
|
{
|
|
"entropy": 6.364528322219849,
|
|
"epoch": 0.10295718432510885,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999983289961146,
|
|
"loss": 6.2307,
|
|
"mean_token_accuracy": 0.1275188758969307,
|
|
"num_tokens": 2358616.0,
|
|
"step": 1135
|
|
},
|
|
{
|
|
"entropy": 6.197306394577026,
|
|
"epoch": 0.10341074020319303,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999982019679755,
|
|
"loss": 6.2656,
|
|
"mean_token_accuracy": 0.12436863258481026,
|
|
"num_tokens": 2368226.0,
|
|
"step": 1140
|
|
},
|
|
{
|
|
"entropy": 6.445528173446656,
|
|
"epoch": 0.10386429608127722,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999980702868164,
|
|
"loss": 6.4449,
|
|
"mean_token_accuracy": 0.1217611476778984,
|
|
"num_tokens": 2378627.0,
|
|
"step": 1145
|
|
},
|
|
{
|
|
"entropy": 6.300698471069336,
|
|
"epoch": 0.1043178519593614,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999979339526396,
|
|
"loss": 6.3391,
|
|
"mean_token_accuracy": 0.12193103209137916,
|
|
"num_tokens": 2389601.0,
|
|
"step": 1150
|
|
},
|
|
{
|
|
"entropy": 6.353440380096435,
|
|
"epoch": 0.10477140783744557,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999977929654484,
|
|
"loss": 6.3341,
|
|
"mean_token_accuracy": 0.12355378419160842,
|
|
"num_tokens": 2400010.0,
|
|
"step": 1155
|
|
},
|
|
{
|
|
"entropy": 6.193485832214355,
|
|
"epoch": 0.10522496371552975,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999976473252453,
|
|
"loss": 6.2651,
|
|
"mean_token_accuracy": 0.12575532719492913,
|
|
"num_tokens": 2409443.0,
|
|
"step": 1160
|
|
},
|
|
{
|
|
"entropy": 6.352375030517578,
|
|
"epoch": 0.10567851959361393,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999974970320338,
|
|
"loss": 6.2298,
|
|
"mean_token_accuracy": 0.12666020169854164,
|
|
"num_tokens": 2419616.0,
|
|
"step": 1165
|
|
},
|
|
{
|
|
"entropy": 6.147144079208374,
|
|
"epoch": 0.10613207547169812,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999973420858165,
|
|
"loss": 6.21,
|
|
"mean_token_accuracy": 0.12970640361309052,
|
|
"num_tokens": 2430193.0,
|
|
"step": 1170
|
|
},
|
|
{
|
|
"entropy": 6.327436637878418,
|
|
"epoch": 0.10658563134978229,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999971824865968,
|
|
"loss": 6.3592,
|
|
"mean_token_accuracy": 0.12428862676024437,
|
|
"num_tokens": 2440682.0,
|
|
"step": 1175
|
|
},
|
|
{
|
|
"entropy": 6.273407697677612,
|
|
"epoch": 0.10703918722786647,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999970182343782,
|
|
"loss": 6.2968,
|
|
"mean_token_accuracy": 0.13017050549387932,
|
|
"num_tokens": 2452357.0,
|
|
"step": 1180
|
|
},
|
|
{
|
|
"entropy": 6.420224666595459,
|
|
"epoch": 0.10749274310595065,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999968493291638,
|
|
"loss": 6.3124,
|
|
"mean_token_accuracy": 0.1259176842868328,
|
|
"num_tokens": 2463372.0,
|
|
"step": 1185
|
|
},
|
|
{
|
|
"entropy": 6.11242709159851,
|
|
"epoch": 0.10794629898403484,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999966757709573,
|
|
"loss": 6.2185,
|
|
"mean_token_accuracy": 0.1255997322499752,
|
|
"num_tokens": 2473937.0,
|
|
"step": 1190
|
|
},
|
|
{
|
|
"entropy": 6.333364057540893,
|
|
"epoch": 0.10839985486211902,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999964975597622,
|
|
"loss": 6.2463,
|
|
"mean_token_accuracy": 0.12876395285129547,
|
|
"num_tokens": 2484178.0,
|
|
"step": 1195
|
|
},
|
|
{
|
|
"entropy": 6.290256929397583,
|
|
"epoch": 0.10885341074020319,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999963146955821,
|
|
"loss": 6.2757,
|
|
"mean_token_accuracy": 0.12604986280202865,
|
|
"num_tokens": 2493855.0,
|
|
"step": 1200
|
|
},
|
|
{
|
|
"entropy": 6.16634783744812,
|
|
"epoch": 0.10930696661828737,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000499996127178421,
|
|
"loss": 6.1956,
|
|
"mean_token_accuracy": 0.128883396089077,
|
|
"num_tokens": 2502777.0,
|
|
"step": 1205
|
|
},
|
|
{
|
|
"entropy": 6.308694171905517,
|
|
"epoch": 0.10976052249637155,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999959350082825,
|
|
"loss": 6.218,
|
|
"mean_token_accuracy": 0.127637080848217,
|
|
"num_tokens": 2513646.0,
|
|
"step": 1210
|
|
},
|
|
{
|
|
"entropy": 6.315856885910034,
|
|
"epoch": 0.11021407837445574,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999957381851709,
|
|
"loss": 6.29,
|
|
"mean_token_accuracy": 0.13161664754152297,
|
|
"num_tokens": 2523614.0,
|
|
"step": 1215
|
|
},
|
|
{
|
|
"entropy": 6.190816354751587,
|
|
"epoch": 0.1106676342525399,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999955367090901,
|
|
"loss": 6.2384,
|
|
"mean_token_accuracy": 0.13483407124876975,
|
|
"num_tokens": 2533279.0,
|
|
"step": 1220
|
|
},
|
|
{
|
|
"entropy": 6.172196102142334,
|
|
"epoch": 0.11112119013062409,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999953305800441,
|
|
"loss": 6.1165,
|
|
"mean_token_accuracy": 0.12950356379151345,
|
|
"num_tokens": 2542748.0,
|
|
"step": 1225
|
|
},
|
|
{
|
|
"entropy": 6.226431798934937,
|
|
"epoch": 0.11157474600870827,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999951197980374,
|
|
"loss": 6.2074,
|
|
"mean_token_accuracy": 0.12376128509640694,
|
|
"num_tokens": 2553003.0,
|
|
"step": 1230
|
|
},
|
|
{
|
|
"entropy": 6.211793422698975,
|
|
"epoch": 0.11202830188679246,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999949043630744,
|
|
"loss": 6.2499,
|
|
"mean_token_accuracy": 0.1253039300441742,
|
|
"num_tokens": 2563099.0,
|
|
"step": 1235
|
|
},
|
|
{
|
|
"entropy": 6.247184419631958,
|
|
"epoch": 0.11248185776487664,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999946842751593,
|
|
"loss": 6.2433,
|
|
"mean_token_accuracy": 0.129485647380352,
|
|
"num_tokens": 2572816.0,
|
|
"step": 1240
|
|
},
|
|
{
|
|
"entropy": 6.208843231201172,
|
|
"epoch": 0.11293541364296081,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999944595342968,
|
|
"loss": 6.2615,
|
|
"mean_token_accuracy": 0.13151264265179635,
|
|
"num_tokens": 2582633.0,
|
|
"step": 1245
|
|
},
|
|
{
|
|
"entropy": 6.3658373832702635,
|
|
"epoch": 0.11338896952104499,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999942301404916,
|
|
"loss": 6.3094,
|
|
"mean_token_accuracy": 0.12087921500205993,
|
|
"num_tokens": 2593581.0,
|
|
"step": 1250
|
|
},
|
|
{
|
|
"entropy": 6.2705951690673825,
|
|
"epoch": 0.11384252539912917,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999939960937484,
|
|
"loss": 6.3018,
|
|
"mean_token_accuracy": 0.11847401112318039,
|
|
"num_tokens": 2603811.0,
|
|
"step": 1255
|
|
},
|
|
{
|
|
"entropy": 6.270603513717651,
|
|
"epoch": 0.11429608127721336,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999937573940721,
|
|
"loss": 6.3224,
|
|
"mean_token_accuracy": 0.12249375060200692,
|
|
"num_tokens": 2615147.0,
|
|
"step": 1260
|
|
},
|
|
{
|
|
"entropy": 6.228997707366943,
|
|
"epoch": 0.11474963715529753,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999935140414674,
|
|
"loss": 6.1669,
|
|
"mean_token_accuracy": 0.1293345607817173,
|
|
"num_tokens": 2625201.0,
|
|
"step": 1265
|
|
},
|
|
{
|
|
"entropy": 6.2709190368652346,
|
|
"epoch": 0.11520319303338171,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004999932660359395,
|
|
"loss": 6.3101,
|
|
"mean_token_accuracy": 0.1249003492295742,
|
|
"num_tokens": 2635377.0,
|
|
"step": 1270
|
|
},
|
|
{
|
|
"entropy": 6.189292049407959,
|
|
"epoch": 0.11565674891146589,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999930133774936,
|
|
"loss": 6.2372,
|
|
"mean_token_accuracy": 0.12723963409662248,
|
|
"num_tokens": 2645849.0,
|
|
"step": 1275
|
|
},
|
|
{
|
|
"entropy": 6.398007583618164,
|
|
"epoch": 0.11611030478955008,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999927560661348,
|
|
"loss": 6.3526,
|
|
"mean_token_accuracy": 0.12062773033976555,
|
|
"num_tokens": 2657125.0,
|
|
"step": 1280
|
|
},
|
|
{
|
|
"entropy": 6.223501682281494,
|
|
"epoch": 0.11656386066763426,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999924941018685,
|
|
"loss": 6.1835,
|
|
"mean_token_accuracy": 0.12893526181578635,
|
|
"num_tokens": 2667575.0,
|
|
"step": 1285
|
|
},
|
|
{
|
|
"entropy": 6.175991201400757,
|
|
"epoch": 0.11701741654571843,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999922274847,
|
|
"loss": 6.2356,
|
|
"mean_token_accuracy": 0.12373170107603074,
|
|
"num_tokens": 2678287.0,
|
|
"step": 1290
|
|
},
|
|
{
|
|
"entropy": 6.321875476837159,
|
|
"epoch": 0.11747097242380261,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000499991956214635,
|
|
"loss": 6.3511,
|
|
"mean_token_accuracy": 0.13218481838703156,
|
|
"num_tokens": 2687903.0,
|
|
"step": 1295
|
|
},
|
|
{
|
|
"entropy": 6.180214071273804,
|
|
"epoch": 0.1179245283018868,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000499991680291679,
|
|
"loss": 6.1958,
|
|
"mean_token_accuracy": 0.12728189304471016,
|
|
"num_tokens": 2697975.0,
|
|
"step": 1300
|
|
},
|
|
{
|
|
"entropy": 6.23911418914795,
|
|
"epoch": 0.11837808417997098,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999913997158378,
|
|
"loss": 6.212,
|
|
"mean_token_accuracy": 0.12432057186961173,
|
|
"num_tokens": 2708861.0,
|
|
"step": 1305
|
|
},
|
|
{
|
|
"entropy": 6.25122103691101,
|
|
"epoch": 0.11883164005805515,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999911144871169,
|
|
"loss": 6.3343,
|
|
"mean_token_accuracy": 0.1229264110326767,
|
|
"num_tokens": 2718751.0,
|
|
"step": 1310
|
|
},
|
|
{
|
|
"entropy": 6.240471696853637,
|
|
"epoch": 0.11928519593613933,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999908246055226,
|
|
"loss": 6.1875,
|
|
"mean_token_accuracy": 0.12787612676620483,
|
|
"num_tokens": 2728393.0,
|
|
"step": 1315
|
|
},
|
|
{
|
|
"entropy": 6.22295913696289,
|
|
"epoch": 0.11973875181422351,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999905300710607,
|
|
"loss": 6.2265,
|
|
"mean_token_accuracy": 0.12778055742383004,
|
|
"num_tokens": 2738953.0,
|
|
"step": 1320
|
|
},
|
|
{
|
|
"entropy": 6.260966491699219,
|
|
"epoch": 0.1201923076923077,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999902308837373,
|
|
"loss": 6.304,
|
|
"mean_token_accuracy": 0.12310394868254662,
|
|
"num_tokens": 2748598.0,
|
|
"step": 1325
|
|
},
|
|
{
|
|
"entropy": 6.344991064071655,
|
|
"epoch": 0.12064586357039188,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999899270435584,
|
|
"loss": 6.3314,
|
|
"mean_token_accuracy": 0.12434870079159736,
|
|
"num_tokens": 2758543.0,
|
|
"step": 1330
|
|
},
|
|
{
|
|
"entropy": 6.20733380317688,
|
|
"epoch": 0.12109941944847605,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999896185505307,
|
|
"loss": 6.1451,
|
|
"mean_token_accuracy": 0.12950560450553894,
|
|
"num_tokens": 2767686.0,
|
|
"step": 1335
|
|
},
|
|
{
|
|
"entropy": 6.168848514556885,
|
|
"epoch": 0.12155297532656023,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999893054046603,
|
|
"loss": 6.2278,
|
|
"mean_token_accuracy": 0.1261433832347393,
|
|
"num_tokens": 2778826.0,
|
|
"step": 1340
|
|
},
|
|
{
|
|
"entropy": 6.23694486618042,
|
|
"epoch": 0.12200653120464441,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999889876059537,
|
|
"loss": 6.1686,
|
|
"mean_token_accuracy": 0.1320178970694542,
|
|
"num_tokens": 2788798.0,
|
|
"step": 1345
|
|
},
|
|
{
|
|
"entropy": 6.205473756790161,
|
|
"epoch": 0.1224600870827286,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999886651544176,
|
|
"loss": 6.243,
|
|
"mean_token_accuracy": 0.12421647608280181,
|
|
"num_tokens": 2799789.0,
|
|
"step": 1350
|
|
},
|
|
{
|
|
"entropy": 6.292304515838623,
|
|
"epoch": 0.12291364296081277,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999883380500584,
|
|
"loss": 6.3019,
|
|
"mean_token_accuracy": 0.11881196796894074,
|
|
"num_tokens": 2811256.0,
|
|
"step": 1355
|
|
},
|
|
{
|
|
"entropy": 6.227163362503052,
|
|
"epoch": 0.12336719883889695,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999880062928831,
|
|
"loss": 6.1407,
|
|
"mean_token_accuracy": 0.12354236915707588,
|
|
"num_tokens": 2821181.0,
|
|
"step": 1360
|
|
},
|
|
{
|
|
"entropy": 6.2017885684967045,
|
|
"epoch": 0.12382075471698113,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999876698828985,
|
|
"loss": 6.2911,
|
|
"mean_token_accuracy": 0.12848431915044783,
|
|
"num_tokens": 2831844.0,
|
|
"step": 1365
|
|
},
|
|
{
|
|
"entropy": 6.140119552612305,
|
|
"epoch": 0.12427431059506532,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999873288201116,
|
|
"loss": 6.1389,
|
|
"mean_token_accuracy": 0.128109622746706,
|
|
"num_tokens": 2842311.0,
|
|
"step": 1370
|
|
},
|
|
{
|
|
"entropy": 6.265316724777222,
|
|
"epoch": 0.1247278664731495,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999869831045294,
|
|
"loss": 6.1958,
|
|
"mean_token_accuracy": 0.12854474037885666,
|
|
"num_tokens": 2852668.0,
|
|
"step": 1375
|
|
},
|
|
{
|
|
"entropy": 6.160908985137939,
|
|
"epoch": 0.12518142235123367,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999866327361589,
|
|
"loss": 6.2176,
|
|
"mean_token_accuracy": 0.12579773738980293,
|
|
"num_tokens": 2862998.0,
|
|
"step": 1380
|
|
},
|
|
{
|
|
"entropy": 6.213189792633057,
|
|
"epoch": 0.12563497822931785,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999862777150077,
|
|
"loss": 6.1426,
|
|
"mean_token_accuracy": 0.13384611159563065,
|
|
"num_tokens": 2872280.0,
|
|
"step": 1385
|
|
},
|
|
{
|
|
"entropy": 6.110375881195068,
|
|
"epoch": 0.12608853410740203,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999859180410829,
|
|
"loss": 6.1983,
|
|
"mean_token_accuracy": 0.1303381085395813,
|
|
"num_tokens": 2883755.0,
|
|
"step": 1390
|
|
},
|
|
{
|
|
"entropy": 6.233339548110962,
|
|
"epoch": 0.12654208998548622,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999855537143919,
|
|
"loss": 6.2045,
|
|
"mean_token_accuracy": 0.12790499925613402,
|
|
"num_tokens": 2893926.0,
|
|
"step": 1395
|
|
},
|
|
{
|
|
"entropy": 6.063788890838623,
|
|
"epoch": 0.1269956458635704,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999851847349425,
|
|
"loss": 6.1219,
|
|
"mean_token_accuracy": 0.12827676758170128,
|
|
"num_tokens": 2904666.0,
|
|
"step": 1400
|
|
},
|
|
{
|
|
"entropy": 6.179912185668945,
|
|
"epoch": 0.12744920174165458,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999848111027419,
|
|
"loss": 6.0826,
|
|
"mean_token_accuracy": 0.1336699068546295,
|
|
"num_tokens": 2915089.0,
|
|
"step": 1405
|
|
},
|
|
{
|
|
"entropy": 6.247713565826416,
|
|
"epoch": 0.12790275761973874,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999844328177983,
|
|
"loss": 6.2475,
|
|
"mean_token_accuracy": 0.12141420245170594,
|
|
"num_tokens": 2926123.0,
|
|
"step": 1410
|
|
},
|
|
{
|
|
"entropy": 6.126826429367066,
|
|
"epoch": 0.12835631349782292,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999840498801191,
|
|
"loss": 6.0732,
|
|
"mean_token_accuracy": 0.13073234036564826,
|
|
"num_tokens": 2935308.0,
|
|
"step": 1415
|
|
},
|
|
{
|
|
"entropy": 6.148389720916748,
|
|
"epoch": 0.1288098693759071,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999836622897126,
|
|
"loss": 6.1871,
|
|
"mean_token_accuracy": 0.12865355014801025,
|
|
"num_tokens": 2945352.0,
|
|
"step": 1420
|
|
},
|
|
{
|
|
"entropy": 6.213321590423584,
|
|
"epoch": 0.1292634252539913,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999832700465865,
|
|
"loss": 6.1989,
|
|
"mean_token_accuracy": 0.12411043643951417,
|
|
"num_tokens": 2956766.0,
|
|
"step": 1425
|
|
},
|
|
{
|
|
"entropy": 6.172161293029785,
|
|
"epoch": 0.12971698113207547,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999828731507491,
|
|
"loss": 6.1263,
|
|
"mean_token_accuracy": 0.1324382685124874,
|
|
"num_tokens": 2967203.0,
|
|
"step": 1430
|
|
},
|
|
{
|
|
"entropy": 6.163990879058838,
|
|
"epoch": 0.13017053701015965,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999824716022085,
|
|
"loss": 6.1356,
|
|
"mean_token_accuracy": 0.13465460762381554,
|
|
"num_tokens": 2976669.0,
|
|
"step": 1435
|
|
},
|
|
{
|
|
"entropy": 6.156468915939331,
|
|
"epoch": 0.13062409288824384,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004999820654009731,
|
|
"loss": 6.1866,
|
|
"mean_token_accuracy": 0.1345203198492527,
|
|
"num_tokens": 2987009.0,
|
|
"step": 1440
|
|
},
|
|
{
|
|
"entropy": 6.1427467346191404,
|
|
"epoch": 0.13107764876632802,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999816545470513,
|
|
"loss": 6.2045,
|
|
"mean_token_accuracy": 0.13020925000309944,
|
|
"num_tokens": 2998252.0,
|
|
"step": 1445
|
|
},
|
|
{
|
|
"entropy": 6.175037908554077,
|
|
"epoch": 0.1315312046444122,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999812390404514,
|
|
"loss": 6.0761,
|
|
"mean_token_accuracy": 0.13165489509701728,
|
|
"num_tokens": 3009091.0,
|
|
"step": 1450
|
|
},
|
|
{
|
|
"entropy": 6.20917649269104,
|
|
"epoch": 0.13198476052249636,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999808188811823,
|
|
"loss": 6.3049,
|
|
"mean_token_accuracy": 0.12950452715158461,
|
|
"num_tokens": 3018692.0,
|
|
"step": 1455
|
|
},
|
|
{
|
|
"entropy": 6.149243974685669,
|
|
"epoch": 0.13243831640058054,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004999803940692524,
|
|
"loss": 6.0922,
|
|
"mean_token_accuracy": 0.1306043490767479,
|
|
"num_tokens": 3028194.0,
|
|
"step": 1460
|
|
},
|
|
{
|
|
"entropy": 6.147744083404541,
|
|
"epoch": 0.13289187227866472,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999799646046707,
|
|
"loss": 6.108,
|
|
"mean_token_accuracy": 0.13267887458205224,
|
|
"num_tokens": 3037893.0,
|
|
"step": 1465
|
|
},
|
|
{
|
|
"entropy": 6.136689615249634,
|
|
"epoch": 0.1333454281567489,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999795304874461,
|
|
"loss": 6.1956,
|
|
"mean_token_accuracy": 0.12603257223963737,
|
|
"num_tokens": 3048593.0,
|
|
"step": 1470
|
|
},
|
|
{
|
|
"entropy": 6.1764789581298825,
|
|
"epoch": 0.1337989840348331,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999790917175873,
|
|
"loss": 6.1384,
|
|
"mean_token_accuracy": 0.1398916281759739,
|
|
"num_tokens": 3059591.0,
|
|
"step": 1475
|
|
},
|
|
{
|
|
"entropy": 6.148527336120606,
|
|
"epoch": 0.13425253991291727,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999786482951036,
|
|
"loss": 6.1489,
|
|
"mean_token_accuracy": 0.13112814351916313,
|
|
"num_tokens": 3070543.0,
|
|
"step": 1480
|
|
},
|
|
{
|
|
"entropy": 6.194287872314453,
|
|
"epoch": 0.13470609579100146,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999782002200041,
|
|
"loss": 6.1506,
|
|
"mean_token_accuracy": 0.1290934108197689,
|
|
"num_tokens": 3081665.0,
|
|
"step": 1485
|
|
},
|
|
{
|
|
"entropy": 6.116252756118774,
|
|
"epoch": 0.13515965166908564,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999777474922982,
|
|
"loss": 6.1252,
|
|
"mean_token_accuracy": 0.135535828769207,
|
|
"num_tokens": 3092347.0,
|
|
"step": 1490
|
|
},
|
|
{
|
|
"entropy": 6.084321165084839,
|
|
"epoch": 0.13561320754716982,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999772901119951,
|
|
"loss": 6.0665,
|
|
"mean_token_accuracy": 0.140205679833889,
|
|
"num_tokens": 3101953.0,
|
|
"step": 1495
|
|
},
|
|
{
|
|
"entropy": 6.182489442825317,
|
|
"epoch": 0.13606676342525398,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999768280791043,
|
|
"loss": 6.1673,
|
|
"mean_token_accuracy": 0.12897372841835023,
|
|
"num_tokens": 3111555.0,
|
|
"step": 1500
|
|
},
|
|
{
|
|
"entropy": 6.074414539337158,
|
|
"epoch": 0.13652031930333816,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999763613936352,
|
|
"loss": 6.1214,
|
|
"mean_token_accuracy": 0.13250304833054544,
|
|
"num_tokens": 3121263.0,
|
|
"step": 1505
|
|
},
|
|
{
|
|
"entropy": 6.1420024871826175,
|
|
"epoch": 0.13697387518142234,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999758900555979,
|
|
"loss": 6.1528,
|
|
"mean_token_accuracy": 0.1297949396073818,
|
|
"num_tokens": 3131187.0,
|
|
"step": 1510
|
|
},
|
|
{
|
|
"entropy": 6.122401189804077,
|
|
"epoch": 0.13742743105950653,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999754140650017,
|
|
"loss": 6.1055,
|
|
"mean_token_accuracy": 0.1283240534365177,
|
|
"num_tokens": 3141116.0,
|
|
"step": 1515
|
|
},
|
|
{
|
|
"entropy": 6.16475772857666,
|
|
"epoch": 0.1378809869375907,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999749334218567,
|
|
"loss": 6.1595,
|
|
"mean_token_accuracy": 0.134047494828701,
|
|
"num_tokens": 3150727.0,
|
|
"step": 1520
|
|
},
|
|
{
|
|
"entropy": 6.178267621994019,
|
|
"epoch": 0.1383345428156749,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999744481261726,
|
|
"loss": 6.188,
|
|
"mean_token_accuracy": 0.12995831593871116,
|
|
"num_tokens": 3160977.0,
|
|
"step": 1525
|
|
},
|
|
{
|
|
"entropy": 6.131053876876831,
|
|
"epoch": 0.13878809869375908,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999739581779597,
|
|
"loss": 6.0237,
|
|
"mean_token_accuracy": 0.13834299221634866,
|
|
"num_tokens": 3171177.0,
|
|
"step": 1530
|
|
},
|
|
{
|
|
"entropy": 6.096694660186768,
|
|
"epoch": 0.13924165457184326,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000499973463577228,
|
|
"loss": 6.193,
|
|
"mean_token_accuracy": 0.13165855631232262,
|
|
"num_tokens": 3181691.0,
|
|
"step": 1535
|
|
},
|
|
{
|
|
"entropy": 6.233206558227539,
|
|
"epoch": 0.13969521044992744,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999729643239877,
|
|
"loss": 6.1496,
|
|
"mean_token_accuracy": 0.13230349868535995,
|
|
"num_tokens": 3192546.0,
|
|
"step": 1540
|
|
},
|
|
{
|
|
"entropy": 6.082428359985352,
|
|
"epoch": 0.1401487663280116,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999724604182492,
|
|
"loss": 6.2144,
|
|
"mean_token_accuracy": 0.13026824072003365,
|
|
"num_tokens": 3203068.0,
|
|
"step": 1545
|
|
},
|
|
{
|
|
"entropy": 6.223723411560059,
|
|
"epoch": 0.14060232220609578,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999719518600229,
|
|
"loss": 6.118,
|
|
"mean_token_accuracy": 0.12941280901432037,
|
|
"num_tokens": 3213974.0,
|
|
"step": 1550
|
|
},
|
|
{
|
|
"entropy": 6.0789594650268555,
|
|
"epoch": 0.14105587808417996,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999714386493192,
|
|
"loss": 6.1984,
|
|
"mean_token_accuracy": 0.13254104405641556,
|
|
"num_tokens": 3224787.0,
|
|
"step": 1555
|
|
},
|
|
{
|
|
"entropy": 6.247838258743286,
|
|
"epoch": 0.14150943396226415,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999709207861489,
|
|
"loss": 6.2061,
|
|
"mean_token_accuracy": 0.1280451625585556,
|
|
"num_tokens": 3236072.0,
|
|
"step": 1560
|
|
},
|
|
{
|
|
"entropy": 6.11969223022461,
|
|
"epoch": 0.14196298984034833,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999703982705227,
|
|
"loss": 6.1511,
|
|
"mean_token_accuracy": 0.1358342684805393,
|
|
"num_tokens": 3247029.0,
|
|
"step": 1565
|
|
},
|
|
{
|
|
"entropy": 6.206550121307373,
|
|
"epoch": 0.1424165457184325,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999698711024513,
|
|
"loss": 6.1205,
|
|
"mean_token_accuracy": 0.13635100796818733,
|
|
"num_tokens": 3257536.0,
|
|
"step": 1570
|
|
},
|
|
{
|
|
"entropy": 6.042502069473267,
|
|
"epoch": 0.1428701015965167,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999693392819456,
|
|
"loss": 6.1236,
|
|
"mean_token_accuracy": 0.13696237206459044,
|
|
"num_tokens": 3266821.0,
|
|
"step": 1575
|
|
},
|
|
{
|
|
"entropy": 6.179642629623413,
|
|
"epoch": 0.14332365747460088,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999688028090166,
|
|
"loss": 6.045,
|
|
"mean_token_accuracy": 0.13624384254217148,
|
|
"num_tokens": 3278118.0,
|
|
"step": 1580
|
|
},
|
|
{
|
|
"entropy": 5.984438037872314,
|
|
"epoch": 0.14377721335268506,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999682616836755,
|
|
"loss": 6.0577,
|
|
"mean_token_accuracy": 0.13041958436369896,
|
|
"num_tokens": 3289331.0,
|
|
"step": 1585
|
|
},
|
|
{
|
|
"entropy": 6.199773597717285,
|
|
"epoch": 0.14423076923076922,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999677159059334,
|
|
"loss": 6.1481,
|
|
"mean_token_accuracy": 0.12837196588516236,
|
|
"num_tokens": 3299965.0,
|
|
"step": 1590
|
|
},
|
|
{
|
|
"entropy": 6.125565862655639,
|
|
"epoch": 0.1446843251088534,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999671654758016,
|
|
"loss": 6.2454,
|
|
"mean_token_accuracy": 0.12566872015595437,
|
|
"num_tokens": 3310741.0,
|
|
"step": 1595
|
|
},
|
|
{
|
|
"entropy": 6.205886650085449,
|
|
"epoch": 0.14513788098693758,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999666103932915,
|
|
"loss": 6.173,
|
|
"mean_token_accuracy": 0.13071803301572799,
|
|
"num_tokens": 3321335.0,
|
|
"step": 1600
|
|
},
|
|
{
|
|
"entropy": 6.197109222412109,
|
|
"epoch": 0.14559143686502177,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999660506584145,
|
|
"loss": 6.148,
|
|
"mean_token_accuracy": 0.12749085575342178,
|
|
"num_tokens": 3332032.0,
|
|
"step": 1605
|
|
},
|
|
{
|
|
"entropy": 6.019048070907592,
|
|
"epoch": 0.14604499274310595,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999654862711823,
|
|
"loss": 6.1304,
|
|
"mean_token_accuracy": 0.13608851209282874,
|
|
"num_tokens": 3342122.0,
|
|
"step": 1610
|
|
},
|
|
{
|
|
"entropy": 6.169208431243897,
|
|
"epoch": 0.14649854862119013,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999649172316065,
|
|
"loss": 6.1136,
|
|
"mean_token_accuracy": 0.1308113157749176,
|
|
"num_tokens": 3352680.0,
|
|
"step": 1615
|
|
},
|
|
{
|
|
"entropy": 6.2383091926574705,
|
|
"epoch": 0.14695210449927432,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000499964343539699,
|
|
"loss": 6.1395,
|
|
"mean_token_accuracy": 0.13406497463583947,
|
|
"num_tokens": 3363230.0,
|
|
"step": 1620
|
|
},
|
|
{
|
|
"entropy": 6.094653749465943,
|
|
"epoch": 0.1474056603773585,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999637651954714,
|
|
"loss": 6.1348,
|
|
"mean_token_accuracy": 0.13433574065566062,
|
|
"num_tokens": 3373794.0,
|
|
"step": 1625
|
|
},
|
|
{
|
|
"entropy": 6.197765684127807,
|
|
"epoch": 0.14785921625544268,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999631821989358,
|
|
"loss": 6.1994,
|
|
"mean_token_accuracy": 0.12583935111761094,
|
|
"num_tokens": 3384514.0,
|
|
"step": 1630
|
|
},
|
|
{
|
|
"entropy": 6.256759357452393,
|
|
"epoch": 0.14831277213352684,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999625945501043,
|
|
"loss": 6.2303,
|
|
"mean_token_accuracy": 0.12956068590283393,
|
|
"num_tokens": 3394803.0,
|
|
"step": 1635
|
|
},
|
|
{
|
|
"entropy": 6.122566747665405,
|
|
"epoch": 0.14876632801161102,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000499962002248989,
|
|
"loss": 6.0898,
|
|
"mean_token_accuracy": 0.13396508246660233,
|
|
"num_tokens": 3405151.0,
|
|
"step": 1640
|
|
},
|
|
{
|
|
"entropy": 6.0934981346130375,
|
|
"epoch": 0.1492198838896952,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999614052956024,
|
|
"loss": 6.0583,
|
|
"mean_token_accuracy": 0.1364964097738266,
|
|
"num_tokens": 3414841.0,
|
|
"step": 1645
|
|
},
|
|
{
|
|
"entropy": 6.048268461227417,
|
|
"epoch": 0.1496734397677794,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999608036899563,
|
|
"loss": 6.0788,
|
|
"mean_token_accuracy": 0.13555450439453126,
|
|
"num_tokens": 3425139.0,
|
|
"step": 1650
|
|
},
|
|
{
|
|
"entropy": 6.194241523742676,
|
|
"epoch": 0.15012699564586357,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999601974320636,
|
|
"loss": 6.1343,
|
|
"mean_token_accuracy": 0.13373469784855843,
|
|
"num_tokens": 3436113.0,
|
|
"step": 1655
|
|
},
|
|
{
|
|
"entropy": 6.095238971710205,
|
|
"epoch": 0.15058055152394775,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999595865219367,
|
|
"loss": 6.0556,
|
|
"mean_token_accuracy": 0.13025515004992486,
|
|
"num_tokens": 3445605.0,
|
|
"step": 1660
|
|
},
|
|
{
|
|
"entropy": 6.008597135543823,
|
|
"epoch": 0.15103410740203194,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999589709595881,
|
|
"loss": 6.0895,
|
|
"mean_token_accuracy": 0.1334249906241894,
|
|
"num_tokens": 3456035.0,
|
|
"step": 1665
|
|
},
|
|
{
|
|
"entropy": 6.121166181564331,
|
|
"epoch": 0.15148766328011612,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999583507450308,
|
|
"loss": 5.9982,
|
|
"mean_token_accuracy": 0.13778249844908713,
|
|
"num_tokens": 3465607.0,
|
|
"step": 1670
|
|
},
|
|
{
|
|
"entropy": 6.085819149017334,
|
|
"epoch": 0.1519412191582003,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999577258782774,
|
|
"loss": 6.0603,
|
|
"mean_token_accuracy": 0.13757585138082504,
|
|
"num_tokens": 3475637.0,
|
|
"step": 1675
|
|
},
|
|
{
|
|
"entropy": 6.190000343322754,
|
|
"epoch": 0.15239477503628446,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000499957096359341,
|
|
"loss": 6.2364,
|
|
"mean_token_accuracy": 0.12960681244730948,
|
|
"num_tokens": 3486200.0,
|
|
"step": 1680
|
|
},
|
|
{
|
|
"entropy": 6.079170513153076,
|
|
"epoch": 0.15284833091436864,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999564621882343,
|
|
"loss": 6.0739,
|
|
"mean_token_accuracy": 0.142069224268198,
|
|
"num_tokens": 3495892.0,
|
|
"step": 1685
|
|
},
|
|
{
|
|
"entropy": 6.0179280757904055,
|
|
"epoch": 0.15330188679245282,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999558233649708,
|
|
"loss": 5.9601,
|
|
"mean_token_accuracy": 0.14071570262312888,
|
|
"num_tokens": 3504837.0,
|
|
"step": 1690
|
|
},
|
|
{
|
|
"entropy": 6.181920051574707,
|
|
"epoch": 0.153755442670537,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999551798895636,
|
|
"loss": 6.1237,
|
|
"mean_token_accuracy": 0.13454843834042549,
|
|
"num_tokens": 3514966.0,
|
|
"step": 1695
|
|
},
|
|
{
|
|
"entropy": 6.123470783233643,
|
|
"epoch": 0.1542089985486212,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999545317620258,
|
|
"loss": 6.1948,
|
|
"mean_token_accuracy": 0.1286864012479782,
|
|
"num_tokens": 3526927.0,
|
|
"step": 1700
|
|
},
|
|
{
|
|
"entropy": 6.103703546524048,
|
|
"epoch": 0.15466255442670537,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999538789823711,
|
|
"loss": 6.1362,
|
|
"mean_token_accuracy": 0.13410764262080194,
|
|
"num_tokens": 3537493.0,
|
|
"step": 1705
|
|
},
|
|
{
|
|
"entropy": 6.200163269042969,
|
|
"epoch": 0.15511611030478956,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999532215506127,
|
|
"loss": 6.1782,
|
|
"mean_token_accuracy": 0.13086570724844931,
|
|
"num_tokens": 3548188.0,
|
|
"step": 1710
|
|
},
|
|
{
|
|
"entropy": 6.023609161376953,
|
|
"epoch": 0.15556966618287374,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999525594667645,
|
|
"loss": 6.0613,
|
|
"mean_token_accuracy": 0.13730209618806838,
|
|
"num_tokens": 3558895.0,
|
|
"step": 1715
|
|
},
|
|
{
|
|
"entropy": 6.090526866912842,
|
|
"epoch": 0.15602322206095792,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00049995189273084,
|
|
"loss": 5.9685,
|
|
"mean_token_accuracy": 0.13569305986166,
|
|
"num_tokens": 3569052.0,
|
|
"step": 1720
|
|
},
|
|
{
|
|
"entropy": 6.121201276779175,
|
|
"epoch": 0.15647677793904208,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000499951221342853,
|
|
"loss": 6.1226,
|
|
"mean_token_accuracy": 0.1320158787071705,
|
|
"num_tokens": 3579714.0,
|
|
"step": 1725
|
|
},
|
|
{
|
|
"entropy": 6.001186561584473,
|
|
"epoch": 0.15693033381712626,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004999505453028174,
|
|
"loss": 5.9801,
|
|
"mean_token_accuracy": 0.13680141866207124,
|
|
"num_tokens": 3589305.0,
|
|
"step": 1730
|
|
},
|
|
{
|
|
"entropy": 6.076255941390992,
|
|
"epoch": 0.15738388969521044,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999498646107472,
|
|
"loss": 6.0586,
|
|
"mean_token_accuracy": 0.1337602600455284,
|
|
"num_tokens": 3599848.0,
|
|
"step": 1735
|
|
},
|
|
{
|
|
"entropy": 6.0408961296081545,
|
|
"epoch": 0.15783744557329463,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004999491792666566,
|
|
"loss": 6.1816,
|
|
"mean_token_accuracy": 0.13034821301698685,
|
|
"num_tokens": 3610588.0,
|
|
"step": 1740
|
|
},
|
|
{
|
|
"entropy": 6.26001992225647,
|
|
"epoch": 0.1582910014513788,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999484892705597,
|
|
"loss": 6.1291,
|
|
"mean_token_accuracy": 0.1350434586405754,
|
|
"num_tokens": 3620649.0,
|
|
"step": 1745
|
|
},
|
|
{
|
|
"entropy": 6.085051679611206,
|
|
"epoch": 0.158744557329463,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999477946224705,
|
|
"loss": 6.0635,
|
|
"mean_token_accuracy": 0.13476430699229242,
|
|
"num_tokens": 3630412.0,
|
|
"step": 1750
|
|
},
|
|
{
|
|
"entropy": 6.041621828079224,
|
|
"epoch": 0.15919811320754718,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999470953224037,
|
|
"loss": 6.0457,
|
|
"mean_token_accuracy": 0.13242931589484214,
|
|
"num_tokens": 3640946.0,
|
|
"step": 1755
|
|
},
|
|
{
|
|
"entropy": 6.114254808425903,
|
|
"epoch": 0.15965166908563136,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999463913703735,
|
|
"loss": 6.1408,
|
|
"mean_token_accuracy": 0.13187248036265373,
|
|
"num_tokens": 3651478.0,
|
|
"step": 1760
|
|
},
|
|
{
|
|
"entropy": 6.029904985427857,
|
|
"epoch": 0.16010522496371554,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999456827663948,
|
|
"loss": 5.9905,
|
|
"mean_token_accuracy": 0.13920539617538452,
|
|
"num_tokens": 3661509.0,
|
|
"step": 1765
|
|
},
|
|
{
|
|
"entropy": 6.057517337799072,
|
|
"epoch": 0.1605587808417997,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000499944969510482,
|
|
"loss": 6.0412,
|
|
"mean_token_accuracy": 0.1356307126581669,
|
|
"num_tokens": 3672293.0,
|
|
"step": 1770
|
|
},
|
|
{
|
|
"entropy": 6.089949989318848,
|
|
"epoch": 0.16101233671988388,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999442516026498,
|
|
"loss": 6.0526,
|
|
"mean_token_accuracy": 0.13480686247348786,
|
|
"num_tokens": 3682687.0,
|
|
"step": 1775
|
|
},
|
|
{
|
|
"entropy": 6.129207468032837,
|
|
"epoch": 0.16146589259796806,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004999435290429133,
|
|
"loss": 6.0789,
|
|
"mean_token_accuracy": 0.14450050964951516,
|
|
"num_tokens": 3692787.0,
|
|
"step": 1780
|
|
},
|
|
{
|
|
"entropy": 6.038466596603394,
|
|
"epoch": 0.16191944847605225,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004999428018312872,
|
|
"loss": 6.0478,
|
|
"mean_token_accuracy": 0.13742451071739198,
|
|
"num_tokens": 3703182.0,
|
|
"step": 1785
|
|
},
|
|
{
|
|
"entropy": 6.083740758895874,
|
|
"epoch": 0.16237300435413643,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004999420699677867,
|
|
"loss": 6.1061,
|
|
"mean_token_accuracy": 0.12973477616906165,
|
|
"num_tokens": 3713384.0,
|
|
"step": 1790
|
|
},
|
|
{
|
|
"entropy": 6.063831567764282,
|
|
"epoch": 0.1628265602322206,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999413334524269,
|
|
"loss": 6.0992,
|
|
"mean_token_accuracy": 0.13103547915816308,
|
|
"num_tokens": 3725122.0,
|
|
"step": 1795
|
|
},
|
|
{
|
|
"entropy": 6.214202642440796,
|
|
"epoch": 0.1632801161103048,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999405922852229,
|
|
"loss": 6.1184,
|
|
"mean_token_accuracy": 0.13545257672667504,
|
|
"num_tokens": 3735460.0,
|
|
"step": 1800
|
|
},
|
|
{
|
|
"entropy": 6.04037709236145,
|
|
"epoch": 0.16373367198838898,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999398464661901,
|
|
"loss": 6.0184,
|
|
"mean_token_accuracy": 0.13665979579091073,
|
|
"num_tokens": 3745442.0,
|
|
"step": 1805
|
|
},
|
|
{
|
|
"entropy": 5.931473588943481,
|
|
"epoch": 0.16418722786647316,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999390959953441,
|
|
"loss": 5.9745,
|
|
"mean_token_accuracy": 0.1391763061285019,
|
|
"num_tokens": 3756443.0,
|
|
"step": 1810
|
|
},
|
|
{
|
|
"entropy": 6.160908555984497,
|
|
"epoch": 0.16464078374455732,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004999383408727002,
|
|
"loss": 6.1473,
|
|
"mean_token_accuracy": 0.13380085676908493,
|
|
"num_tokens": 3767502.0,
|
|
"step": 1815
|
|
},
|
|
{
|
|
"entropy": 6.0393414974212645,
|
|
"epoch": 0.1650943396226415,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999375810982741,
|
|
"loss": 6.0104,
|
|
"mean_token_accuracy": 0.13753475695848466,
|
|
"num_tokens": 3778476.0,
|
|
"step": 1820
|
|
},
|
|
{
|
|
"entropy": 6.044342517852783,
|
|
"epoch": 0.16554789550072568,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999368166720815,
|
|
"loss": 6.069,
|
|
"mean_token_accuracy": 0.13943940550088882,
|
|
"num_tokens": 3788616.0,
|
|
"step": 1825
|
|
},
|
|
{
|
|
"entropy": 6.084714126586914,
|
|
"epoch": 0.16600145137880987,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999360475941382,
|
|
"loss": 6.0156,
|
|
"mean_token_accuracy": 0.14626918584108353,
|
|
"num_tokens": 3798257.0,
|
|
"step": 1830
|
|
},
|
|
{
|
|
"entropy": 6.04117636680603,
|
|
"epoch": 0.16645500725689405,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00049993527386446,
|
|
"loss": 6.005,
|
|
"mean_token_accuracy": 0.13517511934041976,
|
|
"num_tokens": 3807833.0,
|
|
"step": 1835
|
|
},
|
|
{
|
|
"entropy": 6.109489679336548,
|
|
"epoch": 0.16690856313497823,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999344954830633,
|
|
"loss": 6.0797,
|
|
"mean_token_accuracy": 0.13237160220742225,
|
|
"num_tokens": 3817246.0,
|
|
"step": 1840
|
|
},
|
|
{
|
|
"entropy": 6.177425670623779,
|
|
"epoch": 0.16736211901306242,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004999337124499638,
|
|
"loss": 6.064,
|
|
"mean_token_accuracy": 0.14445747211575508,
|
|
"num_tokens": 3827709.0,
|
|
"step": 1845
|
|
},
|
|
{
|
|
"entropy": 5.908847332000732,
|
|
"epoch": 0.1678156748911466,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004999329247651777,
|
|
"loss": 6.0674,
|
|
"mean_token_accuracy": 0.14029163047671317,
|
|
"num_tokens": 3837498.0,
|
|
"step": 1850
|
|
},
|
|
{
|
|
"entropy": 6.158235931396485,
|
|
"epoch": 0.16826923076923078,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999321324287213,
|
|
"loss": 6.0969,
|
|
"mean_token_accuracy": 0.13958577588200569,
|
|
"num_tokens": 3849227.0,
|
|
"step": 1855
|
|
},
|
|
{
|
|
"entropy": 5.956509160995483,
|
|
"epoch": 0.16872278664731494,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999313354406114,
|
|
"loss": 6.0774,
|
|
"mean_token_accuracy": 0.13036854714155197,
|
|
"num_tokens": 3859110.0,
|
|
"step": 1860
|
|
},
|
|
{
|
|
"entropy": 6.06641263961792,
|
|
"epoch": 0.16917634252539912,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000499930533800864,
|
|
"loss": 6.0666,
|
|
"mean_token_accuracy": 0.14033757895231247,
|
|
"num_tokens": 3869906.0,
|
|
"step": 1865
|
|
},
|
|
{
|
|
"entropy": 6.1277564525604244,
|
|
"epoch": 0.1696298984034833,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999297275094958,
|
|
"loss": 6.0638,
|
|
"mean_token_accuracy": 0.135610331594944,
|
|
"num_tokens": 3880343.0,
|
|
"step": 1870
|
|
},
|
|
{
|
|
"entropy": 6.04757661819458,
|
|
"epoch": 0.1700834542815675,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999289165665235,
|
|
"loss": 5.9914,
|
|
"mean_token_accuracy": 0.13660356178879737,
|
|
"num_tokens": 3890969.0,
|
|
"step": 1875
|
|
},
|
|
{
|
|
"entropy": 6.006391096115112,
|
|
"epoch": 0.17053701015965167,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999281009719639,
|
|
"loss": 5.9267,
|
|
"mean_token_accuracy": 0.14178500920534134,
|
|
"num_tokens": 3900744.0,
|
|
"step": 1880
|
|
},
|
|
{
|
|
"entropy": 5.981471347808838,
|
|
"epoch": 0.17099056603773585,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999272807258339,
|
|
"loss": 6.0796,
|
|
"mean_token_accuracy": 0.13724706768989564,
|
|
"num_tokens": 3911415.0,
|
|
"step": 1885
|
|
},
|
|
{
|
|
"entropy": 6.117090654373169,
|
|
"epoch": 0.17144412191582004,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999264558281504,
|
|
"loss": 6.0299,
|
|
"mean_token_accuracy": 0.1346352569758892,
|
|
"num_tokens": 3922405.0,
|
|
"step": 1890
|
|
},
|
|
{
|
|
"entropy": 6.084085512161255,
|
|
"epoch": 0.17189767779390422,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999256262789305,
|
|
"loss": 6.0987,
|
|
"mean_token_accuracy": 0.1346895545721054,
|
|
"num_tokens": 3934715.0,
|
|
"step": 1895
|
|
},
|
|
{
|
|
"entropy": 5.962582588195801,
|
|
"epoch": 0.1723512336719884,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999247920781913,
|
|
"loss": 5.9625,
|
|
"mean_token_accuracy": 0.14006249159574508,
|
|
"num_tokens": 3945410.0,
|
|
"step": 1900
|
|
},
|
|
{
|
|
"entropy": 6.040754938125611,
|
|
"epoch": 0.17280478955007256,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999239532259502,
|
|
"loss": 6.022,
|
|
"mean_token_accuracy": 0.13346246182918547,
|
|
"num_tokens": 3956435.0,
|
|
"step": 1905
|
|
},
|
|
{
|
|
"entropy": 6.0511785507202145,
|
|
"epoch": 0.17325834542815674,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999231097222244,
|
|
"loss": 5.9648,
|
|
"mean_token_accuracy": 0.1416295848786831,
|
|
"num_tokens": 3967855.0,
|
|
"step": 1910
|
|
},
|
|
{
|
|
"entropy": 6.059988403320313,
|
|
"epoch": 0.17371190130624092,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999222615670312,
|
|
"loss": 6.1613,
|
|
"mean_token_accuracy": 0.1296894371509552,
|
|
"num_tokens": 3979467.0,
|
|
"step": 1915
|
|
},
|
|
{
|
|
"entropy": 6.160438489913941,
|
|
"epoch": 0.1741654571843251,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999214087603885,
|
|
"loss": 6.1026,
|
|
"mean_token_accuracy": 0.13720218911767007,
|
|
"num_tokens": 3989624.0,
|
|
"step": 1920
|
|
},
|
|
{
|
|
"entropy": 6.01017427444458,
|
|
"epoch": 0.1746190130624093,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999205513023135,
|
|
"loss": 5.9484,
|
|
"mean_token_accuracy": 0.13784751817584037,
|
|
"num_tokens": 4000408.0,
|
|
"step": 1925
|
|
},
|
|
{
|
|
"entropy": 5.971663951873779,
|
|
"epoch": 0.17507256894049347,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999196891928245,
|
|
"loss": 5.9627,
|
|
"mean_token_accuracy": 0.14002003520727158,
|
|
"num_tokens": 4011110.0,
|
|
"step": 1930
|
|
},
|
|
{
|
|
"entropy": 6.0252245426177975,
|
|
"epoch": 0.17552612481857766,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004999188224319388,
|
|
"loss": 6.0273,
|
|
"mean_token_accuracy": 0.1419824965298176,
|
|
"num_tokens": 4021370.0,
|
|
"step": 1935
|
|
},
|
|
{
|
|
"entropy": 6.083719778060913,
|
|
"epoch": 0.17597968069666184,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999179510196746,
|
|
"loss": 6.0176,
|
|
"mean_token_accuracy": 0.1337435156106949,
|
|
"num_tokens": 4032189.0,
|
|
"step": 1940
|
|
},
|
|
{
|
|
"entropy": 6.030994844436646,
|
|
"epoch": 0.17643323657474602,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999170749560498,
|
|
"loss": 6.0009,
|
|
"mean_token_accuracy": 0.13951044976711274,
|
|
"num_tokens": 4043245.0,
|
|
"step": 1945
|
|
},
|
|
{
|
|
"entropy": 5.954610395431518,
|
|
"epoch": 0.17688679245283018,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999161942410827,
|
|
"loss": 5.9581,
|
|
"mean_token_accuracy": 0.14021288603544235,
|
|
"num_tokens": 4054432.0,
|
|
"step": 1950
|
|
},
|
|
{
|
|
"entropy": 6.065416479110718,
|
|
"epoch": 0.17734034833091436,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004999153088747913,
|
|
"loss": 6.0134,
|
|
"mean_token_accuracy": 0.14068708717823028,
|
|
"num_tokens": 4064696.0,
|
|
"step": 1955
|
|
},
|
|
{
|
|
"entropy": 6.007389259338379,
|
|
"epoch": 0.17779390420899854,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000499914418857194,
|
|
"loss": 6.0498,
|
|
"mean_token_accuracy": 0.1319423608481884,
|
|
"num_tokens": 4075556.0,
|
|
"step": 1960
|
|
},
|
|
{
|
|
"entropy": 6.072854518890381,
|
|
"epoch": 0.17824746008708273,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999135241883092,
|
|
"loss": 6.0347,
|
|
"mean_token_accuracy": 0.13773117437958718,
|
|
"num_tokens": 4086532.0,
|
|
"step": 1965
|
|
},
|
|
{
|
|
"entropy": 6.0589231014251705,
|
|
"epoch": 0.1787010159651669,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004999126248681555,
|
|
"loss": 6.04,
|
|
"mean_token_accuracy": 0.13843712881207465,
|
|
"num_tokens": 4096940.0,
|
|
"step": 1970
|
|
},
|
|
{
|
|
"entropy": 5.971566438674927,
|
|
"epoch": 0.1791545718432511,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999117208967513,
|
|
"loss": 5.9022,
|
|
"mean_token_accuracy": 0.1378993310034275,
|
|
"num_tokens": 4106074.0,
|
|
"step": 1975
|
|
},
|
|
{
|
|
"entropy": 6.018008756637573,
|
|
"epoch": 0.17960812772133528,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999108122741154,
|
|
"loss": 5.9724,
|
|
"mean_token_accuracy": 0.13504682332277299,
|
|
"num_tokens": 4117738.0,
|
|
"step": 1980
|
|
},
|
|
{
|
|
"entropy": 6.027943420410156,
|
|
"epoch": 0.18006168359941946,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999098990002666,
|
|
"loss": 5.9853,
|
|
"mean_token_accuracy": 0.13756806403398514,
|
|
"num_tokens": 4128244.0,
|
|
"step": 1985
|
|
},
|
|
{
|
|
"entropy": 5.966828727722168,
|
|
"epoch": 0.18051523947750364,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999089810752237,
|
|
"loss": 6.0861,
|
|
"mean_token_accuracy": 0.14235653579235077,
|
|
"num_tokens": 4138139.0,
|
|
"step": 1990
|
|
},
|
|
{
|
|
"entropy": 6.050969362258911,
|
|
"epoch": 0.1809687953555878,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000499908058499006,
|
|
"loss": 5.9128,
|
|
"mean_token_accuracy": 0.1413744457066059,
|
|
"num_tokens": 4148150.0,
|
|
"step": 1995
|
|
},
|
|
{
|
|
"entropy": 6.0185212135314945,
|
|
"epoch": 0.18142235123367198,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999071312716321,
|
|
"loss": 6.0106,
|
|
"mean_token_accuracy": 0.13587939217686654,
|
|
"num_tokens": 4160223.0,
|
|
"step": 2000
|
|
},
|
|
{
|
|
"entropy": 5.95493450164795,
|
|
"epoch": 0.18187590711175616,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004999061993931215,
|
|
"loss": 5.9437,
|
|
"mean_token_accuracy": 0.14110832214355468,
|
|
"num_tokens": 4169948.0,
|
|
"step": 2005
|
|
},
|
|
{
|
|
"entropy": 6.005291557312011,
|
|
"epoch": 0.18232946298984035,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999052628634934,
|
|
"loss": 5.9396,
|
|
"mean_token_accuracy": 0.14428384751081466,
|
|
"num_tokens": 4179936.0,
|
|
"step": 2010
|
|
},
|
|
{
|
|
"entropy": 6.0180689811706545,
|
|
"epoch": 0.18278301886792453,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004999043216827671,
|
|
"loss": 5.9833,
|
|
"mean_token_accuracy": 0.14723006561398505,
|
|
"num_tokens": 4189698.0,
|
|
"step": 2015
|
|
},
|
|
{
|
|
"entropy": 6.009299468994141,
|
|
"epoch": 0.1832365747460087,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999033758509621,
|
|
"loss": 6.1257,
|
|
"mean_token_accuracy": 0.13319993391633034,
|
|
"num_tokens": 4200162.0,
|
|
"step": 2020
|
|
},
|
|
{
|
|
"entropy": 6.149590396881104,
|
|
"epoch": 0.1836901306240929,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000499902425368098,
|
|
"loss": 6.0815,
|
|
"mean_token_accuracy": 0.13354766517877578,
|
|
"num_tokens": 4210470.0,
|
|
"step": 2025
|
|
},
|
|
{
|
|
"entropy": 5.932142543792724,
|
|
"epoch": 0.18414368650217708,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004999014702341944,
|
|
"loss": 5.8913,
|
|
"mean_token_accuracy": 0.14411630854010582,
|
|
"num_tokens": 4221062.0,
|
|
"step": 2030
|
|
},
|
|
{
|
|
"entropy": 5.980024766921997,
|
|
"epoch": 0.18459724238026126,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004999005104492712,
|
|
"loss": 5.9284,
|
|
"mean_token_accuracy": 0.14326827973127365,
|
|
"num_tokens": 4231389.0,
|
|
"step": 2035
|
|
},
|
|
{
|
|
"entropy": 5.908800649642944,
|
|
"epoch": 0.18505079825834542,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998995460133481,
|
|
"loss": 5.9101,
|
|
"mean_token_accuracy": 0.13965596854686738,
|
|
"num_tokens": 4241164.0,
|
|
"step": 2040
|
|
},
|
|
{
|
|
"entropy": 5.992084264755249,
|
|
"epoch": 0.1855043541364296,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004998985769264451,
|
|
"loss": 5.9429,
|
|
"mean_token_accuracy": 0.14413947463035584,
|
|
"num_tokens": 4251301.0,
|
|
"step": 2045
|
|
},
|
|
{
|
|
"entropy": 5.983407258987427,
|
|
"epoch": 0.18595791001451378,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004998976031885821,
|
|
"loss": 5.8994,
|
|
"mean_token_accuracy": 0.14310136139392854,
|
|
"num_tokens": 4261600.0,
|
|
"step": 2050
|
|
},
|
|
{
|
|
"entropy": 6.001372003555298,
|
|
"epoch": 0.18641146589259797,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004998966247997794,
|
|
"loss": 5.9863,
|
|
"mean_token_accuracy": 0.13233172073960303,
|
|
"num_tokens": 4271835.0,
|
|
"step": 2055
|
|
},
|
|
{
|
|
"entropy": 5.980549955368042,
|
|
"epoch": 0.18686502177068215,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998956417600572,
|
|
"loss": 6.0495,
|
|
"mean_token_accuracy": 0.13583017364144326,
|
|
"num_tokens": 4282866.0,
|
|
"step": 2060
|
|
},
|
|
{
|
|
"entropy": 5.956373786926269,
|
|
"epoch": 0.18731857764876633,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004998946540694358,
|
|
"loss": 5.8294,
|
|
"mean_token_accuracy": 0.1468118757009506,
|
|
"num_tokens": 4293092.0,
|
|
"step": 2065
|
|
},
|
|
{
|
|
"entropy": 5.973520803451538,
|
|
"epoch": 0.18777213352685052,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004998936617279357,
|
|
"loss": 5.9067,
|
|
"mean_token_accuracy": 0.13692934289574624,
|
|
"num_tokens": 4302944.0,
|
|
"step": 2070
|
|
},
|
|
{
|
|
"entropy": 6.059836578369141,
|
|
"epoch": 0.1882256894049347,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004998926647355773,
|
|
"loss": 6.0568,
|
|
"mean_token_accuracy": 0.1373896986246109,
|
|
"num_tokens": 4314373.0,
|
|
"step": 2075
|
|
},
|
|
{
|
|
"entropy": 5.971044874191284,
|
|
"epoch": 0.18867924528301888,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004998916630923813,
|
|
"loss": 6.0485,
|
|
"mean_token_accuracy": 0.13327606469392778,
|
|
"num_tokens": 4325204.0,
|
|
"step": 2080
|
|
},
|
|
{
|
|
"entropy": 5.9976475715637205,
|
|
"epoch": 0.18913280116110304,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004998906567983685,
|
|
"loss": 5.9668,
|
|
"mean_token_accuracy": 0.13214946836233138,
|
|
"num_tokens": 4335667.0,
|
|
"step": 2085
|
|
},
|
|
{
|
|
"entropy": 5.938468980789184,
|
|
"epoch": 0.18958635703918722,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004998896458535595,
|
|
"loss": 5.8699,
|
|
"mean_token_accuracy": 0.14601458087563515,
|
|
"num_tokens": 4345600.0,
|
|
"step": 2090
|
|
},
|
|
{
|
|
"entropy": 5.8882725715637205,
|
|
"epoch": 0.1900399129172714,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004998886302579752,
|
|
"loss": 5.9109,
|
|
"mean_token_accuracy": 0.14233326613903047,
|
|
"num_tokens": 4355994.0,
|
|
"step": 2095
|
|
},
|
|
{
|
|
"entropy": 5.941480922698974,
|
|
"epoch": 0.19049346879535559,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000499887610011637,
|
|
"loss": 5.9773,
|
|
"mean_token_accuracy": 0.1386798821389675,
|
|
"num_tokens": 4367514.0,
|
|
"step": 2100
|
|
},
|
|
{
|
|
"entropy": 6.065828418731689,
|
|
"epoch": 0.19094702467343977,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004998865851145656,
|
|
"loss": 6.0287,
|
|
"mean_token_accuracy": 0.13639298528432847,
|
|
"num_tokens": 4378186.0,
|
|
"step": 2105
|
|
},
|
|
{
|
|
"entropy": 6.01219220161438,
|
|
"epoch": 0.19140058055152395,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004998855555667822,
|
|
"loss": 5.9504,
|
|
"mean_token_accuracy": 0.14203562438488007,
|
|
"num_tokens": 4388249.0,
|
|
"step": 2110
|
|
},
|
|
{
|
|
"entropy": 5.9509602069854735,
|
|
"epoch": 0.19185413642960814,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998845213683084,
|
|
"loss": 5.9511,
|
|
"mean_token_accuracy": 0.14101598560810089,
|
|
"num_tokens": 4398755.0,
|
|
"step": 2115
|
|
},
|
|
{
|
|
"entropy": 6.0761778354644775,
|
|
"epoch": 0.19230769230769232,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004998834825191652,
|
|
"loss": 6.012,
|
|
"mean_token_accuracy": 0.14403366893529893,
|
|
"num_tokens": 4408336.0,
|
|
"step": 2120
|
|
},
|
|
{
|
|
"entropy": 6.001263093948364,
|
|
"epoch": 0.1927612481857765,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004998824390193743,
|
|
"loss": 5.9641,
|
|
"mean_token_accuracy": 0.1412390351295471,
|
|
"num_tokens": 4418780.0,
|
|
"step": 2125
|
|
},
|
|
{
|
|
"entropy": 5.989875268936157,
|
|
"epoch": 0.19321480406386066,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004998813908689573,
|
|
"loss": 5.9049,
|
|
"mean_token_accuracy": 0.14285448640584947,
|
|
"num_tokens": 4428780.0,
|
|
"step": 2130
|
|
},
|
|
{
|
|
"entropy": 5.930006456375122,
|
|
"epoch": 0.19366835994194484,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004998803380679359,
|
|
"loss": 5.8762,
|
|
"mean_token_accuracy": 0.14344791322946548,
|
|
"num_tokens": 4439058.0,
|
|
"step": 2135
|
|
},
|
|
{
|
|
"entropy": 5.942577266693116,
|
|
"epoch": 0.19412191582002902,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004998792806163317,
|
|
"loss": 5.9551,
|
|
"mean_token_accuracy": 0.14150920659303665,
|
|
"num_tokens": 4450120.0,
|
|
"step": 2140
|
|
},
|
|
{
|
|
"entropy": 6.024294757843018,
|
|
"epoch": 0.1945754716981132,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004998782185141667,
|
|
"loss": 5.982,
|
|
"mean_token_accuracy": 0.14056125581264495,
|
|
"num_tokens": 4460622.0,
|
|
"step": 2145
|
|
},
|
|
{
|
|
"entropy": 5.960634088516235,
|
|
"epoch": 0.1950290275761974,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004998771517614629,
|
|
"loss": 5.9543,
|
|
"mean_token_accuracy": 0.13400557562708854,
|
|
"num_tokens": 4470494.0,
|
|
"step": 2150
|
|
},
|
|
{
|
|
"entropy": 6.062064456939697,
|
|
"epoch": 0.19548258345428157,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004998760803582422,
|
|
"loss": 6.0045,
|
|
"mean_token_accuracy": 0.1384950064122677,
|
|
"num_tokens": 4481135.0,
|
|
"step": 2155
|
|
},
|
|
{
|
|
"entropy": 5.964612913131714,
|
|
"epoch": 0.19593613933236576,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004998750043045269,
|
|
"loss": 5.9767,
|
|
"mean_token_accuracy": 0.13727275878190995,
|
|
"num_tokens": 4491092.0,
|
|
"step": 2160
|
|
},
|
|
{
|
|
"entropy": 5.996477460861206,
|
|
"epoch": 0.19638969521044994,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004998739236003392,
|
|
"loss": 5.975,
|
|
"mean_token_accuracy": 0.14493463039398194,
|
|
"num_tokens": 4501004.0,
|
|
"step": 2165
|
|
},
|
|
{
|
|
"entropy": 6.00132417678833,
|
|
"epoch": 0.1968432510885341,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004998728382457014,
|
|
"loss": 5.9459,
|
|
"mean_token_accuracy": 0.14853413999080659,
|
|
"num_tokens": 4510648.0,
|
|
"step": 2170
|
|
},
|
|
{
|
|
"entropy": 5.998470830917358,
|
|
"epoch": 0.19729680696661828,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004998717482406362,
|
|
"loss": 5.993,
|
|
"mean_token_accuracy": 0.13211097493767737,
|
|
"num_tokens": 4521999.0,
|
|
"step": 2175
|
|
},
|
|
{
|
|
"entropy": 5.93568229675293,
|
|
"epoch": 0.19775036284470246,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004998706535851657,
|
|
"loss": 5.9347,
|
|
"mean_token_accuracy": 0.13946531787514688,
|
|
"num_tokens": 4532209.0,
|
|
"step": 2180
|
|
},
|
|
{
|
|
"entropy": 6.073374080657959,
|
|
"epoch": 0.19820391872278664,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004998695542793129,
|
|
"loss": 6.0389,
|
|
"mean_token_accuracy": 0.13209992721676828,
|
|
"num_tokens": 4542215.0,
|
|
"step": 2185
|
|
},
|
|
{
|
|
"entropy": 5.9528271675109865,
|
|
"epoch": 0.19865747460087083,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004998684503231003,
|
|
"loss": 5.9099,
|
|
"mean_token_accuracy": 0.1399923861026764,
|
|
"num_tokens": 4552424.0,
|
|
"step": 2190
|
|
},
|
|
{
|
|
"entropy": 5.9139893531799315,
|
|
"epoch": 0.199111030478955,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000499867341716551,
|
|
"loss": 6.0183,
|
|
"mean_token_accuracy": 0.13691750392317772,
|
|
"num_tokens": 4562936.0,
|
|
"step": 2195
|
|
},
|
|
{
|
|
"entropy": 6.05651707649231,
|
|
"epoch": 0.1995645863570392,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004998662284596878,
|
|
"loss": 5.9132,
|
|
"mean_token_accuracy": 0.14678076058626174,
|
|
"num_tokens": 4573094.0,
|
|
"step": 2200
|
|
},
|
|
{
|
|
"entropy": 6.008046674728393,
|
|
"epoch": 0.20001814223512338,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004998651105525335,
|
|
"loss": 5.9501,
|
|
"mean_token_accuracy": 0.13911140859127044,
|
|
"num_tokens": 4583194.0,
|
|
"step": 2205
|
|
},
|
|
{
|
|
"entropy": 5.923662614822388,
|
|
"epoch": 0.20047169811320756,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998639879951115,
|
|
"loss": 5.8844,
|
|
"mean_token_accuracy": 0.14621676206588746,
|
|
"num_tokens": 4593352.0,
|
|
"step": 2210
|
|
},
|
|
{
|
|
"entropy": 5.91765398979187,
|
|
"epoch": 0.2009252539912917,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000499862860787445,
|
|
"loss": 5.8657,
|
|
"mean_token_accuracy": 0.14437806457281113,
|
|
"num_tokens": 4603895.0,
|
|
"step": 2215
|
|
},
|
|
{
|
|
"entropy": 5.987819957733154,
|
|
"epoch": 0.2013788098693759,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004998617289295571,
|
|
"loss": 6.0096,
|
|
"mean_token_accuracy": 0.13959661424160003,
|
|
"num_tokens": 4614456.0,
|
|
"step": 2220
|
|
},
|
|
{
|
|
"entropy": 5.925340270996093,
|
|
"epoch": 0.20183236574746008,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004998605924214714,
|
|
"loss": 5.9116,
|
|
"mean_token_accuracy": 0.14096696227788924,
|
|
"num_tokens": 4624139.0,
|
|
"step": 2225
|
|
},
|
|
{
|
|
"entropy": 6.006181907653809,
|
|
"epoch": 0.20228592162554426,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004998594512632114,
|
|
"loss": 5.9403,
|
|
"mean_token_accuracy": 0.14316802397370337,
|
|
"num_tokens": 4634208.0,
|
|
"step": 2230
|
|
},
|
|
{
|
|
"entropy": 5.891085243225097,
|
|
"epoch": 0.20273947750362845,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004998583054548006,
|
|
"loss": 6.0011,
|
|
"mean_token_accuracy": 0.1386461637914181,
|
|
"num_tokens": 4646019.0,
|
|
"step": 2235
|
|
},
|
|
{
|
|
"entropy": 6.067434978485108,
|
|
"epoch": 0.20319303338171263,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004998571549962628,
|
|
"loss": 6.0042,
|
|
"mean_token_accuracy": 0.13608953431248666,
|
|
"num_tokens": 4656604.0,
|
|
"step": 2240
|
|
},
|
|
{
|
|
"entropy": 6.018786478042602,
|
|
"epoch": 0.2036465892597968,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004998559998876216,
|
|
"loss": 5.905,
|
|
"mean_token_accuracy": 0.14071310609579085,
|
|
"num_tokens": 4667373.0,
|
|
"step": 2245
|
|
},
|
|
{
|
|
"entropy": 6.00168890953064,
|
|
"epoch": 0.204100145137881,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004998548401289012,
|
|
"loss": 5.9825,
|
|
"mean_token_accuracy": 0.13470427468419074,
|
|
"num_tokens": 4678351.0,
|
|
"step": 2250
|
|
},
|
|
{
|
|
"entropy": 5.980109548568725,
|
|
"epoch": 0.20455370101596518,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004998536757201253,
|
|
"loss": 5.9328,
|
|
"mean_token_accuracy": 0.13843259811401368,
|
|
"num_tokens": 4688414.0,
|
|
"step": 2255
|
|
},
|
|
{
|
|
"entropy": 5.926772880554199,
|
|
"epoch": 0.20500725689404933,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998525066613181,
|
|
"loss": 5.9745,
|
|
"mean_token_accuracy": 0.14305582344532014,
|
|
"num_tokens": 4699031.0,
|
|
"step": 2260
|
|
},
|
|
{
|
|
"entropy": 5.994556140899658,
|
|
"epoch": 0.20546081277213352,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004998513329525038,
|
|
"loss": 5.8892,
|
|
"mean_token_accuracy": 0.1420019529759884,
|
|
"num_tokens": 4709559.0,
|
|
"step": 2265
|
|
},
|
|
{
|
|
"entropy": 5.835793304443359,
|
|
"epoch": 0.2059143686502177,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004998501545937066,
|
|
"loss": 5.8173,
|
|
"mean_token_accuracy": 0.1476012036204338,
|
|
"num_tokens": 4719887.0,
|
|
"step": 2270
|
|
},
|
|
{
|
|
"entropy": 5.935054349899292,
|
|
"epoch": 0.20636792452830188,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000499848971584951,
|
|
"loss": 5.8989,
|
|
"mean_token_accuracy": 0.1409054510295391,
|
|
"num_tokens": 4730105.0,
|
|
"step": 2275
|
|
},
|
|
{
|
|
"entropy": 5.962164735794067,
|
|
"epoch": 0.20682148040638607,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004998477839262611,
|
|
"loss": 5.9575,
|
|
"mean_token_accuracy": 0.13953802660107611,
|
|
"num_tokens": 4740447.0,
|
|
"step": 2280
|
|
},
|
|
{
|
|
"entropy": 5.928989315032959,
|
|
"epoch": 0.20727503628447025,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000499846591617662,
|
|
"loss": 5.9272,
|
|
"mean_token_accuracy": 0.14312953129410744,
|
|
"num_tokens": 4750709.0,
|
|
"step": 2285
|
|
},
|
|
{
|
|
"entropy": 5.949032163619995,
|
|
"epoch": 0.20772859216255443,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004998453946591779,
|
|
"loss": 5.9673,
|
|
"mean_token_accuracy": 0.14141981452703475,
|
|
"num_tokens": 4760349.0,
|
|
"step": 2290
|
|
},
|
|
{
|
|
"entropy": 6.042676591873169,
|
|
"epoch": 0.20818214804063861,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004998441930508339,
|
|
"loss": 6.0217,
|
|
"mean_token_accuracy": 0.13636812418699265,
|
|
"num_tokens": 4770488.0,
|
|
"step": 2295
|
|
},
|
|
{
|
|
"entropy": 5.99560956954956,
|
|
"epoch": 0.2086357039187228,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004998429867926547,
|
|
"loss": 5.9516,
|
|
"mean_token_accuracy": 0.13818990290164948,
|
|
"num_tokens": 4779991.0,
|
|
"step": 2300
|
|
},
|
|
{
|
|
"entropy": 5.914564037322998,
|
|
"epoch": 0.20908925979680695,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004998417758846651,
|
|
"loss": 5.8844,
|
|
"mean_token_accuracy": 0.14226182624697686,
|
|
"num_tokens": 4790160.0,
|
|
"step": 2305
|
|
},
|
|
{
|
|
"entropy": 5.927054691314697,
|
|
"epoch": 0.20954281567489114,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004998405603268903,
|
|
"loss": 5.7898,
|
|
"mean_token_accuracy": 0.14916908890008926,
|
|
"num_tokens": 4800268.0,
|
|
"step": 2310
|
|
},
|
|
{
|
|
"entropy": 5.854596281051636,
|
|
"epoch": 0.20999637155297532,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004998393401193554,
|
|
"loss": 5.8737,
|
|
"mean_token_accuracy": 0.14095887839794158,
|
|
"num_tokens": 4810777.0,
|
|
"step": 2315
|
|
},
|
|
{
|
|
"entropy": 6.093844556808472,
|
|
"epoch": 0.2104499274310595,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004998381152620857,
|
|
"loss": 6.0447,
|
|
"mean_token_accuracy": 0.13425768688321113,
|
|
"num_tokens": 4821966.0,
|
|
"step": 2320
|
|
},
|
|
{
|
|
"entropy": 6.052251672744751,
|
|
"epoch": 0.21090348330914369,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004998368857551067,
|
|
"loss": 5.9375,
|
|
"mean_token_accuracy": 0.1455095313489437,
|
|
"num_tokens": 4832175.0,
|
|
"step": 2325
|
|
},
|
|
{
|
|
"entropy": 5.84284200668335,
|
|
"epoch": 0.21135703918722787,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004998356515984433,
|
|
"loss": 5.8432,
|
|
"mean_token_accuracy": 0.14820571541786193,
|
|
"num_tokens": 4841506.0,
|
|
"step": 2330
|
|
},
|
|
{
|
|
"entropy": 5.887610673904419,
|
|
"epoch": 0.21181059506531205,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004998344127921213,
|
|
"loss": 5.9033,
|
|
"mean_token_accuracy": 0.13908652514219283,
|
|
"num_tokens": 4851169.0,
|
|
"step": 2335
|
|
},
|
|
{
|
|
"entropy": 5.955441951751709,
|
|
"epoch": 0.21226415094339623,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004998331693361666,
|
|
"loss": 5.8309,
|
|
"mean_token_accuracy": 0.14300615340471268,
|
|
"num_tokens": 4860957.0,
|
|
"step": 2340
|
|
},
|
|
{
|
|
"entropy": 6.039245557785034,
|
|
"epoch": 0.21271770682148042,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004998319212306046,
|
|
"loss": 6.0324,
|
|
"mean_token_accuracy": 0.12900658324360847,
|
|
"num_tokens": 4872809.0,
|
|
"step": 2345
|
|
},
|
|
{
|
|
"entropy": 5.892557668685913,
|
|
"epoch": 0.21317126269956457,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000499830668475461,
|
|
"loss": 5.8898,
|
|
"mean_token_accuracy": 0.14457644373178483,
|
|
"num_tokens": 4882487.0,
|
|
"step": 2350
|
|
},
|
|
{
|
|
"entropy": 5.989882373809815,
|
|
"epoch": 0.21362481857764876,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000499829411070762,
|
|
"loss": 5.989,
|
|
"mean_token_accuracy": 0.1365087829530239,
|
|
"num_tokens": 4894084.0,
|
|
"step": 2355
|
|
},
|
|
{
|
|
"entropy": 5.947244024276733,
|
|
"epoch": 0.21407837445573294,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004998281490165335,
|
|
"loss": 5.892,
|
|
"mean_token_accuracy": 0.14107751250267028,
|
|
"num_tokens": 4905336.0,
|
|
"step": 2360
|
|
},
|
|
{
|
|
"entropy": 5.917174339294434,
|
|
"epoch": 0.21453193033381712,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004998268823128016,
|
|
"loss": 5.9134,
|
|
"mean_token_accuracy": 0.14147956743836404,
|
|
"num_tokens": 4916271.0,
|
|
"step": 2365
|
|
},
|
|
{
|
|
"entropy": 5.941757583618164,
|
|
"epoch": 0.2149854862119013,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004998256109595923,
|
|
"loss": 5.9371,
|
|
"mean_token_accuracy": 0.14648856744170188,
|
|
"num_tokens": 4926284.0,
|
|
"step": 2370
|
|
},
|
|
{
|
|
"entropy": 6.002183961868286,
|
|
"epoch": 0.2154390420899855,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004998243349569323,
|
|
"loss": 5.9466,
|
|
"mean_token_accuracy": 0.14225479438900948,
|
|
"num_tokens": 4936771.0,
|
|
"step": 2375
|
|
},
|
|
{
|
|
"entropy": 5.98759355545044,
|
|
"epoch": 0.21589259796806967,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004998230543048477,
|
|
"loss": 6.0056,
|
|
"mean_token_accuracy": 0.142339825630188,
|
|
"num_tokens": 4947148.0,
|
|
"step": 2380
|
|
},
|
|
{
|
|
"entropy": 5.987500143051148,
|
|
"epoch": 0.21634615384615385,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000499821769003365,
|
|
"loss": 5.9377,
|
|
"mean_token_accuracy": 0.14021862521767617,
|
|
"num_tokens": 4957790.0,
|
|
"step": 2385
|
|
},
|
|
{
|
|
"entropy": 5.997272586822509,
|
|
"epoch": 0.21679970972423804,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004998204790525109,
|
|
"loss": 5.9226,
|
|
"mean_token_accuracy": 0.14474812299013137,
|
|
"num_tokens": 4967266.0,
|
|
"step": 2390
|
|
},
|
|
{
|
|
"entropy": 5.935082054138183,
|
|
"epoch": 0.2172532656023222,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004998191844523119,
|
|
"loss": 5.9333,
|
|
"mean_token_accuracy": 0.14002179726958275,
|
|
"num_tokens": 4977147.0,
|
|
"step": 2395
|
|
},
|
|
{
|
|
"entropy": 5.969844818115234,
|
|
"epoch": 0.21770682148040638,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000499817885202795,
|
|
"loss": 5.9435,
|
|
"mean_token_accuracy": 0.14077059850096701,
|
|
"num_tokens": 4986221.0,
|
|
"step": 2400
|
|
},
|
|
{
|
|
"entropy": 5.965543937683106,
|
|
"epoch": 0.21816037735849056,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004998165813039869,
|
|
"loss": 5.928,
|
|
"mean_token_accuracy": 0.14429101943969727,
|
|
"num_tokens": 4997015.0,
|
|
"step": 2405
|
|
},
|
|
{
|
|
"entropy": 5.987357711791992,
|
|
"epoch": 0.21861393323657474,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998152727559145,
|
|
"loss": 5.9535,
|
|
"mean_token_accuracy": 0.1384763464331627,
|
|
"num_tokens": 5007210.0,
|
|
"step": 2410
|
|
},
|
|
{
|
|
"entropy": 5.9590071678161625,
|
|
"epoch": 0.21906748911465893,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000499813959558605,
|
|
"loss": 5.8448,
|
|
"mean_token_accuracy": 0.14687777310609818,
|
|
"num_tokens": 5018522.0,
|
|
"step": 2415
|
|
},
|
|
{
|
|
"entropy": 5.920127916336059,
|
|
"epoch": 0.2195210449927431,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998126417120856,
|
|
"loss": 5.8532,
|
|
"mean_token_accuracy": 0.14418737962841988,
|
|
"num_tokens": 5028704.0,
|
|
"step": 2420
|
|
},
|
|
{
|
|
"entropy": 5.925795173645019,
|
|
"epoch": 0.2199746008708273,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004998113192163835,
|
|
"loss": 5.9707,
|
|
"mean_token_accuracy": 0.1384512260556221,
|
|
"num_tokens": 5038714.0,
|
|
"step": 2425
|
|
},
|
|
{
|
|
"entropy": 5.915235757827759,
|
|
"epoch": 0.22042815674891147,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000499809992071526,
|
|
"loss": 5.8578,
|
|
"mean_token_accuracy": 0.1408664584159851,
|
|
"num_tokens": 5048932.0,
|
|
"step": 2430
|
|
},
|
|
{
|
|
"entropy": 5.9984221935272215,
|
|
"epoch": 0.22088171262699566,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004998086602775406,
|
|
"loss": 5.9102,
|
|
"mean_token_accuracy": 0.140318613499403,
|
|
"num_tokens": 5059027.0,
|
|
"step": 2435
|
|
},
|
|
{
|
|
"entropy": 5.9371038436889645,
|
|
"epoch": 0.2213352685050798,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004998073238344547,
|
|
"loss": 5.9129,
|
|
"mean_token_accuracy": 0.1459469713270664,
|
|
"num_tokens": 5069277.0,
|
|
"step": 2440
|
|
},
|
|
{
|
|
"entropy": 5.962320852279663,
|
|
"epoch": 0.221788824383164,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004998059827422962,
|
|
"loss": 5.9677,
|
|
"mean_token_accuracy": 0.14480481147766114,
|
|
"num_tokens": 5079282.0,
|
|
"step": 2445
|
|
},
|
|
{
|
|
"entropy": 5.982713794708252,
|
|
"epoch": 0.22224238026124818,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004998046370010926,
|
|
"loss": 5.9289,
|
|
"mean_token_accuracy": 0.14125189632177354,
|
|
"num_tokens": 5089847.0,
|
|
"step": 2450
|
|
},
|
|
{
|
|
"entropy": 5.867915201187134,
|
|
"epoch": 0.22269593613933236,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004998032866108718,
|
|
"loss": 5.8794,
|
|
"mean_token_accuracy": 0.14892499893903732,
|
|
"num_tokens": 5099305.0,
|
|
"step": 2455
|
|
},
|
|
{
|
|
"entropy": 5.875945329666138,
|
|
"epoch": 0.22314949201741655,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004998019315716618,
|
|
"loss": 5.7864,
|
|
"mean_token_accuracy": 0.14948971420526505,
|
|
"num_tokens": 5109394.0,
|
|
"step": 2460
|
|
},
|
|
{
|
|
"entropy": 5.978427791595459,
|
|
"epoch": 0.22360304789550073,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004998005718834905,
|
|
"loss": 6.0369,
|
|
"mean_token_accuracy": 0.13315446451306343,
|
|
"num_tokens": 5119999.0,
|
|
"step": 2465
|
|
},
|
|
{
|
|
"entropy": 6.013746356964111,
|
|
"epoch": 0.2240566037735849,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004997992075463862,
|
|
"loss": 6.0137,
|
|
"mean_token_accuracy": 0.13928034231066705,
|
|
"num_tokens": 5130828.0,
|
|
"step": 2470
|
|
},
|
|
{
|
|
"entropy": 6.077896165847778,
|
|
"epoch": 0.2245101596516691,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004997978385603769,
|
|
"loss": 5.936,
|
|
"mean_token_accuracy": 0.1441244065761566,
|
|
"num_tokens": 5140477.0,
|
|
"step": 2475
|
|
},
|
|
{
|
|
"entropy": 5.827495908737182,
|
|
"epoch": 0.22496371552975328,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004997964649254911,
|
|
"loss": 5.9129,
|
|
"mean_token_accuracy": 0.1431684747338295,
|
|
"num_tokens": 5150934.0,
|
|
"step": 2480
|
|
},
|
|
{
|
|
"entropy": 6.012978363037109,
|
|
"epoch": 0.22541727140783743,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004997950866417572,
|
|
"loss": 5.8917,
|
|
"mean_token_accuracy": 0.14228983074426652,
|
|
"num_tokens": 5160446.0,
|
|
"step": 2485
|
|
},
|
|
{
|
|
"entropy": 5.945698070526123,
|
|
"epoch": 0.22587082728592162,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004997937037092034,
|
|
"loss": 5.9799,
|
|
"mean_token_accuracy": 0.13791251853108405,
|
|
"num_tokens": 5171818.0,
|
|
"step": 2490
|
|
},
|
|
{
|
|
"entropy": 5.991513013839722,
|
|
"epoch": 0.2263243831640058,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004997923161278587,
|
|
"loss": 5.9261,
|
|
"mean_token_accuracy": 0.14048070907592775,
|
|
"num_tokens": 5181357.0,
|
|
"step": 2495
|
|
},
|
|
{
|
|
"entropy": 5.976591348648071,
|
|
"epoch": 0.22677793904208998,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004997909238977514,
|
|
"loss": 5.9351,
|
|
"mean_token_accuracy": 0.13984388560056688,
|
|
"num_tokens": 5190952.0,
|
|
"step": 2500
|
|
},
|
|
{
|
|
"entropy": 5.979648303985596,
|
|
"epoch": 0.22723149492017417,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004997895270189108,
|
|
"loss": 5.942,
|
|
"mean_token_accuracy": 0.15530682802200318,
|
|
"num_tokens": 5200757.0,
|
|
"step": 2505
|
|
},
|
|
{
|
|
"entropy": 6.040076065063476,
|
|
"epoch": 0.22768505079825835,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004997881254913653,
|
|
"loss": 5.9891,
|
|
"mean_token_accuracy": 0.13575384318828582,
|
|
"num_tokens": 5212160.0,
|
|
"step": 2510
|
|
},
|
|
{
|
|
"entropy": 5.943009519577027,
|
|
"epoch": 0.22813860667634253,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004997867193151441,
|
|
"loss": 5.9362,
|
|
"mean_token_accuracy": 0.14286721348762513,
|
|
"num_tokens": 5222274.0,
|
|
"step": 2515
|
|
},
|
|
{
|
|
"entropy": 5.955537176132202,
|
|
"epoch": 0.22859216255442671,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004997853084902763,
|
|
"loss": 5.9225,
|
|
"mean_token_accuracy": 0.14721989408135414,
|
|
"num_tokens": 5232657.0,
|
|
"step": 2520
|
|
},
|
|
{
|
|
"entropy": 6.057634258270264,
|
|
"epoch": 0.2290457184325109,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004997838930167911,
|
|
"loss": 5.9874,
|
|
"mean_token_accuracy": 0.14284725338220597,
|
|
"num_tokens": 5242789.0,
|
|
"step": 2525
|
|
},
|
|
{
|
|
"entropy": 5.972007989883423,
|
|
"epoch": 0.22949927431059505,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004997824728947176,
|
|
"loss": 5.9744,
|
|
"mean_token_accuracy": 0.1313949629664421,
|
|
"num_tokens": 5254045.0,
|
|
"step": 2530
|
|
},
|
|
{
|
|
"entropy": 5.916559791564941,
|
|
"epoch": 0.22995283018867924,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004997810481240853,
|
|
"loss": 5.8952,
|
|
"mean_token_accuracy": 0.1435857117176056,
|
|
"num_tokens": 5263356.0,
|
|
"step": 2535
|
|
},
|
|
{
|
|
"entropy": 5.9302077293396,
|
|
"epoch": 0.23040638606676342,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004997796187049238,
|
|
"loss": 5.8347,
|
|
"mean_token_accuracy": 0.14040180593729018,
|
|
"num_tokens": 5273449.0,
|
|
"step": 2540
|
|
},
|
|
{
|
|
"entropy": 5.912052631378174,
|
|
"epoch": 0.2308599419448476,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004997781846372623,
|
|
"loss": 5.9068,
|
|
"mean_token_accuracy": 0.1452646702528,
|
|
"num_tokens": 5284594.0,
|
|
"step": 2545
|
|
},
|
|
{
|
|
"entropy": 5.873109149932861,
|
|
"epoch": 0.23131349782293179,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004997767459211307,
|
|
"loss": 5.8432,
|
|
"mean_token_accuracy": 0.1450057938694954,
|
|
"num_tokens": 5295138.0,
|
|
"step": 2550
|
|
},
|
|
{
|
|
"entropy": 5.952861070632935,
|
|
"epoch": 0.23176705370101597,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004997753025565587,
|
|
"loss": 5.8315,
|
|
"mean_token_accuracy": 0.14779942333698273,
|
|
"num_tokens": 5305430.0,
|
|
"step": 2555
|
|
},
|
|
{
|
|
"entropy": 5.839398622512817,
|
|
"epoch": 0.23222060957910015,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004997738545435763,
|
|
"loss": 5.8083,
|
|
"mean_token_accuracy": 0.14324629306793213,
|
|
"num_tokens": 5315626.0,
|
|
"step": 2560
|
|
},
|
|
{
|
|
"entropy": 5.854900598526001,
|
|
"epoch": 0.23267416545718433,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004997724018822133,
|
|
"loss": 5.8666,
|
|
"mean_token_accuracy": 0.14416230767965316,
|
|
"num_tokens": 5325010.0,
|
|
"step": 2565
|
|
},
|
|
{
|
|
"entropy": 5.936237144470215,
|
|
"epoch": 0.23312772133526852,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004997709445724996,
|
|
"loss": 5.8806,
|
|
"mean_token_accuracy": 0.14533936828374863,
|
|
"num_tokens": 5335835.0,
|
|
"step": 2570
|
|
},
|
|
{
|
|
"entropy": 5.905138731002808,
|
|
"epoch": 0.23358127721335267,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004997694826144656,
|
|
"loss": 5.9236,
|
|
"mean_token_accuracy": 0.14513202160596847,
|
|
"num_tokens": 5346709.0,
|
|
"step": 2575
|
|
},
|
|
{
|
|
"entropy": 5.902335453033447,
|
|
"epoch": 0.23403483309143686,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004997680160081414,
|
|
"loss": 5.8284,
|
|
"mean_token_accuracy": 0.14653799757361413,
|
|
"num_tokens": 5357285.0,
|
|
"step": 2580
|
|
},
|
|
{
|
|
"entropy": 5.973487043380738,
|
|
"epoch": 0.23448838896952104,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004997665447535573,
|
|
"loss": 6.0278,
|
|
"mean_token_accuracy": 0.1390775978565216,
|
|
"num_tokens": 5366662.0,
|
|
"step": 2585
|
|
},
|
|
{
|
|
"entropy": 6.149343061447143,
|
|
"epoch": 0.23494194484760522,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004997650688507438,
|
|
"loss": 6.0375,
|
|
"mean_token_accuracy": 0.13486452773213387,
|
|
"num_tokens": 5377516.0,
|
|
"step": 2590
|
|
},
|
|
{
|
|
"entropy": 5.886330938339233,
|
|
"epoch": 0.2353955007256894,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004997635882997314,
|
|
"loss": 5.8939,
|
|
"mean_token_accuracy": 0.15408131331205369,
|
|
"num_tokens": 5387557.0,
|
|
"step": 2595
|
|
},
|
|
{
|
|
"entropy": 5.851848316192627,
|
|
"epoch": 0.2358490566037736,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004997621031005507,
|
|
"loss": 5.8844,
|
|
"mean_token_accuracy": 0.1519714578986168,
|
|
"num_tokens": 5397862.0,
|
|
"step": 2600
|
|
},
|
|
{
|
|
"entropy": 5.8382651805877686,
|
|
"epoch": 0.23630261248185777,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004997606132532325,
|
|
"loss": 5.9154,
|
|
"mean_token_accuracy": 0.13924724757671356,
|
|
"num_tokens": 5408368.0,
|
|
"step": 2605
|
|
},
|
|
{
|
|
"entropy": 5.978755903244019,
|
|
"epoch": 0.23675616835994195,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004997591187578075,
|
|
"loss": 5.8955,
|
|
"mean_token_accuracy": 0.14127107188105584,
|
|
"num_tokens": 5419315.0,
|
|
"step": 2610
|
|
},
|
|
{
|
|
"entropy": 5.983459186553955,
|
|
"epoch": 0.23720972423802614,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004997576196143067,
|
|
"loss": 5.8621,
|
|
"mean_token_accuracy": 0.13962915763258935,
|
|
"num_tokens": 5429417.0,
|
|
"step": 2615
|
|
},
|
|
{
|
|
"entropy": 5.836444425582886,
|
|
"epoch": 0.2376632801161103,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.000499756115822761,
|
|
"loss": 5.7937,
|
|
"mean_token_accuracy": 0.14924170970916747,
|
|
"num_tokens": 5438697.0,
|
|
"step": 2620
|
|
},
|
|
{
|
|
"entropy": 5.8208709239959715,
|
|
"epoch": 0.23811683599419448,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004997546073832015,
|
|
"loss": 5.868,
|
|
"mean_token_accuracy": 0.14800073951482773,
|
|
"num_tokens": 5448566.0,
|
|
"step": 2625
|
|
},
|
|
{
|
|
"entropy": 5.945734119415283,
|
|
"epoch": 0.23857039187227866,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004997530942956595,
|
|
"loss": 5.8393,
|
|
"mean_token_accuracy": 0.14892902076244355,
|
|
"num_tokens": 5457716.0,
|
|
"step": 2630
|
|
},
|
|
{
|
|
"entropy": 5.8889336585998535,
|
|
"epoch": 0.23902394775036284,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004997515765601662,
|
|
"loss": 5.9133,
|
|
"mean_token_accuracy": 0.14614535719156266,
|
|
"num_tokens": 5467905.0,
|
|
"step": 2635
|
|
},
|
|
{
|
|
"entropy": 5.860836315155029,
|
|
"epoch": 0.23947750362844702,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004997500541767531,
|
|
"loss": 5.7794,
|
|
"mean_token_accuracy": 0.14639949202537536,
|
|
"num_tokens": 5477840.0,
|
|
"step": 2640
|
|
},
|
|
{
|
|
"entropy": 5.775539827346802,
|
|
"epoch": 0.2399310595065312,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004997485271454516,
|
|
"loss": 5.783,
|
|
"mean_token_accuracy": 0.14732736945152283,
|
|
"num_tokens": 5488336.0,
|
|
"step": 2645
|
|
},
|
|
{
|
|
"entropy": 5.97319803237915,
|
|
"epoch": 0.2403846153846154,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004997469954662933,
|
|
"loss": 5.9824,
|
|
"mean_token_accuracy": 0.1375535361468792,
|
|
"num_tokens": 5499663.0,
|
|
"step": 2650
|
|
},
|
|
{
|
|
"entropy": 5.995337295532226,
|
|
"epoch": 0.24083817126269957,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004997454591393097,
|
|
"loss": 5.8985,
|
|
"mean_token_accuracy": 0.1435574099421501,
|
|
"num_tokens": 5508899.0,
|
|
"step": 2655
|
|
},
|
|
{
|
|
"entropy": 5.879145812988281,
|
|
"epoch": 0.24129172714078376,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004997439181645329,
|
|
"loss": 5.8628,
|
|
"mean_token_accuracy": 0.14226806908845901,
|
|
"num_tokens": 5518523.0,
|
|
"step": 2660
|
|
},
|
|
{
|
|
"entropy": 5.9952600479125975,
|
|
"epoch": 0.2417452830188679,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004997423725419945,
|
|
"loss": 5.9503,
|
|
"mean_token_accuracy": 0.14343410283327102,
|
|
"num_tokens": 5528751.0,
|
|
"step": 2665
|
|
},
|
|
{
|
|
"entropy": 6.054172945022583,
|
|
"epoch": 0.2421988388969521,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004997408222717267,
|
|
"loss": 5.8535,
|
|
"mean_token_accuracy": 0.14445326030254363,
|
|
"num_tokens": 5538769.0,
|
|
"step": 2670
|
|
},
|
|
{
|
|
"entropy": 5.828339338302612,
|
|
"epoch": 0.24265239477503628,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004997392673537612,
|
|
"loss": 5.8943,
|
|
"mean_token_accuracy": 0.14723632782697677,
|
|
"num_tokens": 5549229.0,
|
|
"step": 2675
|
|
},
|
|
{
|
|
"entropy": 6.001218986511231,
|
|
"epoch": 0.24310595065312046,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004997377077881306,
|
|
"loss": 6.0027,
|
|
"mean_token_accuracy": 0.13532417714595796,
|
|
"num_tokens": 5561115.0,
|
|
"step": 2680
|
|
},
|
|
{
|
|
"entropy": 5.941242027282715,
|
|
"epoch": 0.24355950653120464,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004997361435748668,
|
|
"loss": 5.8692,
|
|
"mean_token_accuracy": 0.14536329954862595,
|
|
"num_tokens": 5571995.0,
|
|
"step": 2685
|
|
},
|
|
{
|
|
"entropy": 5.888056325912475,
|
|
"epoch": 0.24401306240928883,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004997345747140024,
|
|
"loss": 5.826,
|
|
"mean_token_accuracy": 0.14596109837293625,
|
|
"num_tokens": 5582477.0,
|
|
"step": 2690
|
|
},
|
|
{
|
|
"entropy": 5.9173914909362795,
|
|
"epoch": 0.244466618287373,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004997330012055695,
|
|
"loss": 5.7922,
|
|
"mean_token_accuracy": 0.15324772000312806,
|
|
"num_tokens": 5592355.0,
|
|
"step": 2695
|
|
},
|
|
{
|
|
"entropy": 5.7889283180236815,
|
|
"epoch": 0.2449201741654572,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004997314230496011,
|
|
"loss": 5.8323,
|
|
"mean_token_accuracy": 0.14904937148094177,
|
|
"num_tokens": 5602448.0,
|
|
"step": 2700
|
|
},
|
|
{
|
|
"entropy": 5.879192256927491,
|
|
"epoch": 0.24537373004354138,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004997298402461296,
|
|
"loss": 5.8207,
|
|
"mean_token_accuracy": 0.14821702241897583,
|
|
"num_tokens": 5613501.0,
|
|
"step": 2705
|
|
},
|
|
{
|
|
"entropy": 5.954217576980591,
|
|
"epoch": 0.24582728592162553,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004997282527951876,
|
|
"loss": 5.8956,
|
|
"mean_token_accuracy": 0.14211225211620332,
|
|
"num_tokens": 5624834.0,
|
|
"step": 2710
|
|
},
|
|
{
|
|
"entropy": 5.956999349594116,
|
|
"epoch": 0.24628084179970972,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004997266606968081,
|
|
"loss": 5.9062,
|
|
"mean_token_accuracy": 0.14094941169023514,
|
|
"num_tokens": 5635200.0,
|
|
"step": 2715
|
|
},
|
|
{
|
|
"entropy": 5.852967071533203,
|
|
"epoch": 0.2467343976777939,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004997250639510241,
|
|
"loss": 5.7953,
|
|
"mean_token_accuracy": 0.14844689518213272,
|
|
"num_tokens": 5645710.0,
|
|
"step": 2720
|
|
},
|
|
{
|
|
"entropy": 5.750450468063354,
|
|
"epoch": 0.24718795355587808,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004997234625578684,
|
|
"loss": 5.7916,
|
|
"mean_token_accuracy": 0.13893610686063768,
|
|
"num_tokens": 5655898.0,
|
|
"step": 2725
|
|
},
|
|
{
|
|
"entropy": 5.899655771255493,
|
|
"epoch": 0.24764150943396226,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004997218565173742,
|
|
"loss": 5.8707,
|
|
"mean_token_accuracy": 0.14310870319604874,
|
|
"num_tokens": 5666412.0,
|
|
"step": 2730
|
|
},
|
|
{
|
|
"entropy": 5.898589086532593,
|
|
"epoch": 0.24809506531204645,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004997202458295748,
|
|
"loss": 5.9183,
|
|
"mean_token_accuracy": 0.14258762449026108,
|
|
"num_tokens": 5676410.0,
|
|
"step": 2735
|
|
},
|
|
{
|
|
"entropy": 5.940978002548218,
|
|
"epoch": 0.24854862119013063,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004997186304945034,
|
|
"loss": 5.8711,
|
|
"mean_token_accuracy": 0.13710892349481582,
|
|
"num_tokens": 5687033.0,
|
|
"step": 2740
|
|
},
|
|
{
|
|
"entropy": 5.84973406791687,
|
|
"epoch": 0.24900217706821481,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004997170105121935,
|
|
"loss": 5.7994,
|
|
"mean_token_accuracy": 0.14377631098031998,
|
|
"num_tokens": 5696310.0,
|
|
"step": 2745
|
|
},
|
|
{
|
|
"entropy": 5.842684984207153,
|
|
"epoch": 0.249455732946299,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004997153858826786,
|
|
"loss": 5.8483,
|
|
"mean_token_accuracy": 0.15185194611549377,
|
|
"num_tokens": 5706275.0,
|
|
"step": 2750
|
|
},
|
|
{
|
|
"entropy": 5.912807130813599,
|
|
"epoch": 0.24990928882438315,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004997137566059922,
|
|
"loss": 5.9279,
|
|
"mean_token_accuracy": 0.1422789663076401,
|
|
"num_tokens": 5716572.0,
|
|
"step": 2755
|
|
},
|
|
{
|
|
"entropy": 5.954165983200073,
|
|
"epoch": 0.25036284470246734,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004997121226821681,
|
|
"loss": 5.8373,
|
|
"mean_token_accuracy": 0.14658476859331132,
|
|
"num_tokens": 5726469.0,
|
|
"step": 2760
|
|
},
|
|
{
|
|
"entropy": 5.846992874145508,
|
|
"epoch": 0.25081640058055155,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00049971048411124,
|
|
"loss": 5.7856,
|
|
"mean_token_accuracy": 0.1450542390346527,
|
|
"num_tokens": 5737126.0,
|
|
"step": 2765
|
|
},
|
|
{
|
|
"entropy": 5.932477760314941,
|
|
"epoch": 0.2512699564586357,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004997088408932418,
|
|
"loss": 5.9739,
|
|
"mean_token_accuracy": 0.14914767369627951,
|
|
"num_tokens": 5747557.0,
|
|
"step": 2770
|
|
},
|
|
{
|
|
"entropy": 5.90068359375,
|
|
"epoch": 0.25172351233671986,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004997071930282076,
|
|
"loss": 5.9454,
|
|
"mean_token_accuracy": 0.13878969848155975,
|
|
"num_tokens": 5758652.0,
|
|
"step": 2775
|
|
},
|
|
{
|
|
"entropy": 5.963881874084473,
|
|
"epoch": 0.25217706821480407,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004997055405161712,
|
|
"loss": 5.8894,
|
|
"mean_token_accuracy": 0.14103187918663024,
|
|
"num_tokens": 5768889.0,
|
|
"step": 2780
|
|
},
|
|
{
|
|
"entropy": 5.9532280445098875,
|
|
"epoch": 0.2526306240928882,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004997038833571671,
|
|
"loss": 5.8383,
|
|
"mean_token_accuracy": 0.14568528681993484,
|
|
"num_tokens": 5779401.0,
|
|
"step": 2785
|
|
},
|
|
{
|
|
"entropy": 5.858279228210449,
|
|
"epoch": 0.25308417997097243,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004997022215512295,
|
|
"loss": 5.8208,
|
|
"mean_token_accuracy": 0.14427980780601501,
|
|
"num_tokens": 5790481.0,
|
|
"step": 2790
|
|
},
|
|
{
|
|
"entropy": 5.93959412574768,
|
|
"epoch": 0.2535377358490566,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004997005550983925,
|
|
"loss": 5.9005,
|
|
"mean_token_accuracy": 0.1436707317829132,
|
|
"num_tokens": 5801050.0,
|
|
"step": 2795
|
|
},
|
|
{
|
|
"entropy": 5.937245941162109,
|
|
"epoch": 0.2539912917271408,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000499698883998691,
|
|
"loss": 5.8902,
|
|
"mean_token_accuracy": 0.1422402374446392,
|
|
"num_tokens": 5812277.0,
|
|
"step": 2800
|
|
},
|
|
{
|
|
"entropy": 5.900210762023926,
|
|
"epoch": 0.25444484760522496,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004996972082521591,
|
|
"loss": 5.902,
|
|
"mean_token_accuracy": 0.1445831313729286,
|
|
"num_tokens": 5822300.0,
|
|
"step": 2805
|
|
},
|
|
{
|
|
"entropy": 5.884892416000366,
|
|
"epoch": 0.25489840348330917,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004996955278588319,
|
|
"loss": 5.8068,
|
|
"mean_token_accuracy": 0.15077413916587828,
|
|
"num_tokens": 5831764.0,
|
|
"step": 2810
|
|
},
|
|
{
|
|
"entropy": 5.913922739028931,
|
|
"epoch": 0.2553519593613933,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004996938428187437,
|
|
"loss": 5.8143,
|
|
"mean_token_accuracy": 0.1524057112634182,
|
|
"num_tokens": 5841651.0,
|
|
"step": 2815
|
|
},
|
|
{
|
|
"entropy": 5.9320954322814945,
|
|
"epoch": 0.2558055152394775,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004996921531319297,
|
|
"loss": 5.8831,
|
|
"mean_token_accuracy": 0.14498303830623627,
|
|
"num_tokens": 5851855.0,
|
|
"step": 2820
|
|
},
|
|
{
|
|
"entropy": 5.932426071166992,
|
|
"epoch": 0.2562590711175617,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004996904587984246,
|
|
"loss": 5.9912,
|
|
"mean_token_accuracy": 0.13337972834706308,
|
|
"num_tokens": 5863190.0,
|
|
"step": 2825
|
|
},
|
|
{
|
|
"entropy": 6.019015502929688,
|
|
"epoch": 0.25671262699564584,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004996887598182636,
|
|
"loss": 5.9354,
|
|
"mean_token_accuracy": 0.14033464342355728,
|
|
"num_tokens": 5873771.0,
|
|
"step": 2830
|
|
},
|
|
{
|
|
"entropy": 5.9573073387146,
|
|
"epoch": 0.25716618287373005,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004996870561914819,
|
|
"loss": 5.9239,
|
|
"mean_token_accuracy": 0.14105542823672296,
|
|
"num_tokens": 5884449.0,
|
|
"step": 2835
|
|
},
|
|
{
|
|
"entropy": 5.962704849243164,
|
|
"epoch": 0.2576197387518142,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004996853479181145,
|
|
"loss": 5.9356,
|
|
"mean_token_accuracy": 0.14173914715647698,
|
|
"num_tokens": 5896134.0,
|
|
"step": 2840
|
|
},
|
|
{
|
|
"entropy": 5.9352422714233395,
|
|
"epoch": 0.2580732946298984,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004996836349981969,
|
|
"loss": 5.8243,
|
|
"mean_token_accuracy": 0.14533241838216782,
|
|
"num_tokens": 5907004.0,
|
|
"step": 2845
|
|
},
|
|
{
|
|
"entropy": 5.864476871490479,
|
|
"epoch": 0.2585268505079826,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004996819174317645,
|
|
"loss": 5.851,
|
|
"mean_token_accuracy": 0.14395025223493577,
|
|
"num_tokens": 5917400.0,
|
|
"step": 2850
|
|
},
|
|
{
|
|
"entropy": 5.9380591869354244,
|
|
"epoch": 0.2589804063860668,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004996801952188528,
|
|
"loss": 5.95,
|
|
"mean_token_accuracy": 0.13919704630970955,
|
|
"num_tokens": 5929008.0,
|
|
"step": 2855
|
|
},
|
|
{
|
|
"entropy": 5.842560720443726,
|
|
"epoch": 0.25943396226415094,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004996784683594973,
|
|
"loss": 5.8327,
|
|
"mean_token_accuracy": 0.14070578664541245,
|
|
"num_tokens": 5939250.0,
|
|
"step": 2860
|
|
},
|
|
{
|
|
"entropy": 5.959221267700196,
|
|
"epoch": 0.2598875181422351,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004996767368537338,
|
|
"loss": 5.817,
|
|
"mean_token_accuracy": 0.13839129433035852,
|
|
"num_tokens": 5950068.0,
|
|
"step": 2865
|
|
},
|
|
{
|
|
"entropy": 5.877241897583008,
|
|
"epoch": 0.2603410740203193,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004996750007015983,
|
|
"loss": 5.7696,
|
|
"mean_token_accuracy": 0.14700621664524077,
|
|
"num_tokens": 5960847.0,
|
|
"step": 2870
|
|
},
|
|
{
|
|
"entropy": 5.894535636901855,
|
|
"epoch": 0.26079462989840346,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004996732599031264,
|
|
"loss": 5.9437,
|
|
"mean_token_accuracy": 0.1424281269311905,
|
|
"num_tokens": 5971372.0,
|
|
"step": 2875
|
|
},
|
|
{
|
|
"entropy": 5.862865686416626,
|
|
"epoch": 0.2612481857764877,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004996715144583543,
|
|
"loss": 5.8244,
|
|
"mean_token_accuracy": 0.1482554256916046,
|
|
"num_tokens": 5981834.0,
|
|
"step": 2880
|
|
},
|
|
{
|
|
"entropy": 5.897699880599975,
|
|
"epoch": 0.26170174165457183,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.000499669764367318,
|
|
"loss": 5.8284,
|
|
"mean_token_accuracy": 0.1392040655016899,
|
|
"num_tokens": 5992256.0,
|
|
"step": 2885
|
|
},
|
|
{
|
|
"entropy": 5.846699953079224,
|
|
"epoch": 0.26215529753265604,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004996680096300537,
|
|
"loss": 5.7288,
|
|
"mean_token_accuracy": 0.1538042202591896,
|
|
"num_tokens": 6002965.0,
|
|
"step": 2890
|
|
},
|
|
{
|
|
"entropy": 5.875544452667237,
|
|
"epoch": 0.2626088534107402,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004996662502465978,
|
|
"loss": 5.8626,
|
|
"mean_token_accuracy": 0.14618532732129097,
|
|
"num_tokens": 6014384.0,
|
|
"step": 2895
|
|
},
|
|
{
|
|
"entropy": 5.852958822250367,
|
|
"epoch": 0.2630624092888244,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004996644862169864,
|
|
"loss": 5.8098,
|
|
"mean_token_accuracy": 0.14801875948905946,
|
|
"num_tokens": 6024191.0,
|
|
"step": 2900
|
|
},
|
|
{
|
|
"entropy": 5.8199280261993405,
|
|
"epoch": 0.26351596516690856,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004996627175412563,
|
|
"loss": 5.8239,
|
|
"mean_token_accuracy": 0.1518359899520874,
|
|
"num_tokens": 6035043.0,
|
|
"step": 2905
|
|
},
|
|
{
|
|
"entropy": 5.853754234313965,
|
|
"epoch": 0.2639695210449927,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.000499660944219444,
|
|
"loss": 5.7854,
|
|
"mean_token_accuracy": 0.14921433106064796,
|
|
"num_tokens": 6043940.0,
|
|
"step": 2910
|
|
},
|
|
{
|
|
"entropy": 5.8335946559906,
|
|
"epoch": 0.2644230769230769,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004996591662515861,
|
|
"loss": 5.8371,
|
|
"mean_token_accuracy": 0.14537594690918923,
|
|
"num_tokens": 6054338.0,
|
|
"step": 2915
|
|
},
|
|
{
|
|
"entropy": 5.961825037002564,
|
|
"epoch": 0.2648766328011611,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004996573836377193,
|
|
"loss": 5.8348,
|
|
"mean_token_accuracy": 0.13997972533106803,
|
|
"num_tokens": 6065150.0,
|
|
"step": 2920
|
|
},
|
|
{
|
|
"entropy": 5.930986785888672,
|
|
"epoch": 0.2653301886792453,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004996555963778806,
|
|
"loss": 5.9492,
|
|
"mean_token_accuracy": 0.1413875937461853,
|
|
"num_tokens": 6076552.0,
|
|
"step": 2925
|
|
},
|
|
{
|
|
"entropy": 5.867830467224121,
|
|
"epoch": 0.26578374455732945,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000499653804472107,
|
|
"loss": 5.8141,
|
|
"mean_token_accuracy": 0.14914955347776412,
|
|
"num_tokens": 6086224.0,
|
|
"step": 2930
|
|
},
|
|
{
|
|
"entropy": 5.865148401260376,
|
|
"epoch": 0.26623730043541366,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004996520079204353,
|
|
"loss": 5.8759,
|
|
"mean_token_accuracy": 0.1438009113073349,
|
|
"num_tokens": 6095607.0,
|
|
"step": 2935
|
|
},
|
|
{
|
|
"entropy": 6.042435073852539,
|
|
"epoch": 0.2666908563134978,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000499650206722903,
|
|
"loss": 5.869,
|
|
"mean_token_accuracy": 0.14277777075767517,
|
|
"num_tokens": 6106338.0,
|
|
"step": 2940
|
|
},
|
|
{
|
|
"entropy": 5.798783254623413,
|
|
"epoch": 0.267144412191582,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004996484008795471,
|
|
"loss": 5.857,
|
|
"mean_token_accuracy": 0.1411480873823166,
|
|
"num_tokens": 6116676.0,
|
|
"step": 2945
|
|
},
|
|
{
|
|
"entropy": 5.893274641036987,
|
|
"epoch": 0.2675979680696662,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.000499646590390405,
|
|
"loss": 5.8818,
|
|
"mean_token_accuracy": 0.14448646381497382,
|
|
"num_tokens": 6127104.0,
|
|
"step": 2950
|
|
},
|
|
{
|
|
"entropy": 5.97404203414917,
|
|
"epoch": 0.26805152394775034,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004996447752555142,
|
|
"loss": 5.8849,
|
|
"mean_token_accuracy": 0.14420673102140427,
|
|
"num_tokens": 6136854.0,
|
|
"step": 2955
|
|
},
|
|
{
|
|
"entropy": 5.874495887756348,
|
|
"epoch": 0.26850507982583455,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004996429554749122,
|
|
"loss": 5.7478,
|
|
"mean_token_accuracy": 0.14988255202770234,
|
|
"num_tokens": 6146949.0,
|
|
"step": 2960
|
|
},
|
|
{
|
|
"entropy": 5.814474868774414,
|
|
"epoch": 0.2689586357039187,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004996411310486367,
|
|
"loss": 5.8163,
|
|
"mean_token_accuracy": 0.14709441363811493,
|
|
"num_tokens": 6156565.0,
|
|
"step": 2965
|
|
},
|
|
{
|
|
"entropy": 5.8766576766967775,
|
|
"epoch": 0.2694121915820029,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004996393019767253,
|
|
"loss": 5.8539,
|
|
"mean_token_accuracy": 0.14178219437599182,
|
|
"num_tokens": 6167547.0,
|
|
"step": 2970
|
|
},
|
|
{
|
|
"entropy": 6.001531267166138,
|
|
"epoch": 0.26986574746008707,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004996374682592158,
|
|
"loss": 5.8851,
|
|
"mean_token_accuracy": 0.13923771157860756,
|
|
"num_tokens": 6177664.0,
|
|
"step": 2975
|
|
},
|
|
{
|
|
"entropy": 5.9096832275390625,
|
|
"epoch": 0.2703193033381713,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004996356298961463,
|
|
"loss": 5.9059,
|
|
"mean_token_accuracy": 0.1396166890859604,
|
|
"num_tokens": 6187917.0,
|
|
"step": 2980
|
|
},
|
|
{
|
|
"entropy": 5.94624695777893,
|
|
"epoch": 0.27077285921625543,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004996337868875549,
|
|
"loss": 5.7766,
|
|
"mean_token_accuracy": 0.15335213392972946,
|
|
"num_tokens": 6197912.0,
|
|
"step": 2985
|
|
},
|
|
{
|
|
"entropy": 5.868017482757568,
|
|
"epoch": 0.27122641509433965,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004996319392334792,
|
|
"loss": 5.856,
|
|
"mean_token_accuracy": 0.14923167005181312,
|
|
"num_tokens": 6207661.0,
|
|
"step": 2990
|
|
},
|
|
{
|
|
"entropy": 5.830333042144775,
|
|
"epoch": 0.2716799709724238,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.000499630086933958,
|
|
"loss": 5.8397,
|
|
"mean_token_accuracy": 0.14484328925609588,
|
|
"num_tokens": 6218178.0,
|
|
"step": 2995
|
|
},
|
|
{
|
|
"entropy": 5.951654672622681,
|
|
"epoch": 0.27213352685050796,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004996282299890292,
|
|
"loss": 5.9512,
|
|
"mean_token_accuracy": 0.1427612841129303,
|
|
"num_tokens": 6229397.0,
|
|
"step": 3000
|
|
},
|
|
{
|
|
"epoch": 0.27213352685050796,
|
|
"eval_entropy": 5.809842018088604,
|
|
"eval_loss": 5.885278701782227,
|
|
"eval_mean_token_accuracy": 0.14895868243152335,
|
|
"eval_num_tokens": 6229397.0,
|
|
"eval_runtime": 26.7157,
|
|
"eval_samples_per_second": 1323.565,
|
|
"eval_steps_per_second": 165.446,
|
|
"step": 3000
|
|
}
|
|
],
|
|
"logging_steps": 5,
|
|
"max_steps": 110230,
|
|
"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": 9122521374720000.0,
|
|
"train_batch_size": 16,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|