18068 lines
494 KiB
JSON
18068 lines
494 KiB
JSON
{
|
|
"best_global_step": null,
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 0.816400580551524,
|
|
"eval_steps": 3000,
|
|
"global_step": 9000,
|
|
"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
|
|
},
|
|
{
|
|
"entropy": 5.958879184722901,
|
|
"epoch": 0.27258708272859217,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004996263683987316,
|
|
"loss": 5.9397,
|
|
"mean_token_accuracy": 0.135448008030653,
|
|
"num_tokens": 6239746.0,
|
|
"step": 3005
|
|
},
|
|
{
|
|
"entropy": 5.985172605514526,
|
|
"epoch": 0.2730406386066763,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004996245021631033,
|
|
"loss": 5.9173,
|
|
"mean_token_accuracy": 0.13839664533734322,
|
|
"num_tokens": 6250254.0,
|
|
"step": 3010
|
|
},
|
|
{
|
|
"entropy": 5.869852018356323,
|
|
"epoch": 0.27349419448476053,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.000499622631282183,
|
|
"loss": 5.7857,
|
|
"mean_token_accuracy": 0.14560491144657134,
|
|
"num_tokens": 6260289.0,
|
|
"step": 3015
|
|
},
|
|
{
|
|
"entropy": 5.819940757751465,
|
|
"epoch": 0.2739477503628447,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.0004996207557560095,
|
|
"loss": 5.8158,
|
|
"mean_token_accuracy": 0.14539813250303268,
|
|
"num_tokens": 6270613.0,
|
|
"step": 3020
|
|
},
|
|
{
|
|
"entropy": 5.839310836791992,
|
|
"epoch": 0.2744013062409289,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004996188755846216,
|
|
"loss": 5.7273,
|
|
"mean_token_accuracy": 0.14885752648115158,
|
|
"num_tokens": 6281105.0,
|
|
"step": 3025
|
|
},
|
|
{
|
|
"entropy": 5.782553625106812,
|
|
"epoch": 0.27485486211901305,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000499616990768058,
|
|
"loss": 5.7718,
|
|
"mean_token_accuracy": 0.14648960307240486,
|
|
"num_tokens": 6291743.0,
|
|
"step": 3030
|
|
},
|
|
{
|
|
"entropy": 5.850036144256592,
|
|
"epoch": 0.27530841799709727,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004996151013063579,
|
|
"loss": 5.7904,
|
|
"mean_token_accuracy": 0.14614589661359786,
|
|
"num_tokens": 6301972.0,
|
|
"step": 3035
|
|
},
|
|
{
|
|
"entropy": 5.964907217025757,
|
|
"epoch": 0.2757619738751814,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004996132071995601,
|
|
"loss": 5.9164,
|
|
"mean_token_accuracy": 0.1384211391210556,
|
|
"num_tokens": 6313077.0,
|
|
"step": 3040
|
|
},
|
|
{
|
|
"entropy": 5.8856535911560055,
|
|
"epoch": 0.2762155297532656,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004996113084477042,
|
|
"loss": 5.9312,
|
|
"mean_token_accuracy": 0.14106005281209946,
|
|
"num_tokens": 6323259.0,
|
|
"step": 3045
|
|
},
|
|
{
|
|
"entropy": 5.935484266281128,
|
|
"epoch": 0.2766690856313498,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004996094050508291,
|
|
"loss": 5.9297,
|
|
"mean_token_accuracy": 0.14095510616898538,
|
|
"num_tokens": 6332944.0,
|
|
"step": 3050
|
|
},
|
|
{
|
|
"entropy": 5.961835670471191,
|
|
"epoch": 0.27712264150943394,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004996074970089741,
|
|
"loss": 5.8642,
|
|
"mean_token_accuracy": 0.1443409040570259,
|
|
"num_tokens": 6343655.0,
|
|
"step": 3055
|
|
},
|
|
{
|
|
"entropy": 5.947761917114258,
|
|
"epoch": 0.27757619738751815,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004996055843221789,
|
|
"loss": 5.8648,
|
|
"mean_token_accuracy": 0.14549115747213365,
|
|
"num_tokens": 6353764.0,
|
|
"step": 3060
|
|
},
|
|
{
|
|
"entropy": 5.912136363983154,
|
|
"epoch": 0.2780297532656023,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004996036669904831,
|
|
"loss": 5.8709,
|
|
"mean_token_accuracy": 0.14337181076407432,
|
|
"num_tokens": 6364158.0,
|
|
"step": 3065
|
|
},
|
|
{
|
|
"entropy": 6.009150266647339,
|
|
"epoch": 0.2784833091436865,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004996017450139261,
|
|
"loss": 5.9597,
|
|
"mean_token_accuracy": 0.14345912635326385,
|
|
"num_tokens": 6374626.0,
|
|
"step": 3070
|
|
},
|
|
{
|
|
"entropy": 5.861038589477539,
|
|
"epoch": 0.2789368650217707,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004995998183925478,
|
|
"loss": 5.7917,
|
|
"mean_token_accuracy": 0.14217267483472823,
|
|
"num_tokens": 6385828.0,
|
|
"step": 3075
|
|
},
|
|
{
|
|
"entropy": 5.858433866500855,
|
|
"epoch": 0.2793904208998549,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004995978871263881,
|
|
"loss": 5.8631,
|
|
"mean_token_accuracy": 0.14555875808000565,
|
|
"num_tokens": 6394995.0,
|
|
"step": 3080
|
|
},
|
|
{
|
|
"entropy": 5.8555628776550295,
|
|
"epoch": 0.27984397677793904,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004995959512154868,
|
|
"loss": 5.7251,
|
|
"mean_token_accuracy": 0.15479629933834077,
|
|
"num_tokens": 6403851.0,
|
|
"step": 3085
|
|
},
|
|
{
|
|
"entropy": 5.868296670913696,
|
|
"epoch": 0.2802975326560232,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000499594010659884,
|
|
"loss": 5.8663,
|
|
"mean_token_accuracy": 0.14205797165632247,
|
|
"num_tokens": 6415444.0,
|
|
"step": 3090
|
|
},
|
|
{
|
|
"entropy": 5.91460108757019,
|
|
"epoch": 0.2807510885341074,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004995920654596199,
|
|
"loss": 5.8395,
|
|
"mean_token_accuracy": 0.14932074174284934,
|
|
"num_tokens": 6425725.0,
|
|
"step": 3095
|
|
},
|
|
{
|
|
"entropy": 5.898306369781494,
|
|
"epoch": 0.28120464441219156,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004995901156147345,
|
|
"loss": 5.8395,
|
|
"mean_token_accuracy": 0.14300182536244394,
|
|
"num_tokens": 6436897.0,
|
|
"step": 3100
|
|
},
|
|
{
|
|
"entropy": 5.913700866699219,
|
|
"epoch": 0.2816582002902758,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004995881611252684,
|
|
"loss": 5.965,
|
|
"mean_token_accuracy": 0.1330859951674938,
|
|
"num_tokens": 6448785.0,
|
|
"step": 3105
|
|
},
|
|
{
|
|
"entropy": 5.849992322921753,
|
|
"epoch": 0.28211175616835993,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004995862019912619,
|
|
"loss": 5.85,
|
|
"mean_token_accuracy": 0.15349818915128707,
|
|
"num_tokens": 6458471.0,
|
|
"step": 3110
|
|
},
|
|
{
|
|
"entropy": 5.924998188018799,
|
|
"epoch": 0.28256531204644414,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004995842382127555,
|
|
"loss": 5.877,
|
|
"mean_token_accuracy": 0.1460927091538906,
|
|
"num_tokens": 6469405.0,
|
|
"step": 3115
|
|
},
|
|
{
|
|
"entropy": 5.889486837387085,
|
|
"epoch": 0.2830188679245283,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004995822697897897,
|
|
"loss": 5.8027,
|
|
"mean_token_accuracy": 0.14449920505285263,
|
|
"num_tokens": 6480143.0,
|
|
"step": 3120
|
|
},
|
|
{
|
|
"entropy": 5.821135234832764,
|
|
"epoch": 0.2834724238026125,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004995802967224056,
|
|
"loss": 5.7916,
|
|
"mean_token_accuracy": 0.15088085681200028,
|
|
"num_tokens": 6490609.0,
|
|
"step": 3125
|
|
},
|
|
{
|
|
"entropy": 5.939887523651123,
|
|
"epoch": 0.28392597968069666,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004995783190106434,
|
|
"loss": 5.9064,
|
|
"mean_token_accuracy": 0.14183955937623977,
|
|
"num_tokens": 6501982.0,
|
|
"step": 3130
|
|
},
|
|
{
|
|
"entropy": 5.880724811553955,
|
|
"epoch": 0.2843795355587808,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004995763366545445,
|
|
"loss": 5.7333,
|
|
"mean_token_accuracy": 0.1553550824522972,
|
|
"num_tokens": 6511394.0,
|
|
"step": 3135
|
|
},
|
|
{
|
|
"entropy": 5.852282428741455,
|
|
"epoch": 0.284833091436865,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004995743496541497,
|
|
"loss": 5.7882,
|
|
"mean_token_accuracy": 0.1472353495657444,
|
|
"num_tokens": 6522307.0,
|
|
"step": 3140
|
|
},
|
|
{
|
|
"entropy": 5.868274068832397,
|
|
"epoch": 0.2852866473149492,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004995723580095001,
|
|
"loss": 5.8706,
|
|
"mean_token_accuracy": 0.14255028143525122,
|
|
"num_tokens": 6533560.0,
|
|
"step": 3145
|
|
},
|
|
{
|
|
"entropy": 5.819251966476441,
|
|
"epoch": 0.2857402031930334,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.000499570361720637,
|
|
"loss": 5.8307,
|
|
"mean_token_accuracy": 0.14855025410652162,
|
|
"num_tokens": 6543669.0,
|
|
"step": 3150
|
|
},
|
|
{
|
|
"entropy": 5.892589426040649,
|
|
"epoch": 0.28619375907111755,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004995683607876015,
|
|
"loss": 5.8724,
|
|
"mean_token_accuracy": 0.14935246258974075,
|
|
"num_tokens": 6553439.0,
|
|
"step": 3155
|
|
},
|
|
{
|
|
"entropy": 5.932051801681519,
|
|
"epoch": 0.28664731494920176,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004995663552104352,
|
|
"loss": 5.7927,
|
|
"mean_token_accuracy": 0.15133242607116698,
|
|
"num_tokens": 6563631.0,
|
|
"step": 3160
|
|
},
|
|
{
|
|
"entropy": 5.809592628479004,
|
|
"epoch": 0.2871008708272859,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004995643449891793,
|
|
"loss": 5.8032,
|
|
"mean_token_accuracy": 0.14714159369468688,
|
|
"num_tokens": 6574610.0,
|
|
"step": 3165
|
|
},
|
|
{
|
|
"entropy": 5.843514728546142,
|
|
"epoch": 0.2875544267053701,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004995623301238757,
|
|
"loss": 5.7887,
|
|
"mean_token_accuracy": 0.14544542878866196,
|
|
"num_tokens": 6583878.0,
|
|
"step": 3170
|
|
},
|
|
{
|
|
"entropy": 5.893237638473511,
|
|
"epoch": 0.2880079825834543,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004995603106145657,
|
|
"loss": 5.8246,
|
|
"mean_token_accuracy": 0.14911970496177673,
|
|
"num_tokens": 6594844.0,
|
|
"step": 3175
|
|
},
|
|
{
|
|
"entropy": 5.957679510116577,
|
|
"epoch": 0.28846153846153844,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004995582864612913,
|
|
"loss": 5.8756,
|
|
"mean_token_accuracy": 0.1441011093556881,
|
|
"num_tokens": 6605695.0,
|
|
"step": 3180
|
|
},
|
|
{
|
|
"entropy": 5.776202726364136,
|
|
"epoch": 0.28891509433962265,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004995562576640943,
|
|
"loss": 5.7007,
|
|
"mean_token_accuracy": 0.15618097633123398,
|
|
"num_tokens": 6615155.0,
|
|
"step": 3185
|
|
},
|
|
{
|
|
"entropy": 5.849746513366699,
|
|
"epoch": 0.2893686502177068,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004995542242230167,
|
|
"loss": 5.8392,
|
|
"mean_token_accuracy": 0.1439945727586746,
|
|
"num_tokens": 6625095.0,
|
|
"step": 3190
|
|
},
|
|
{
|
|
"entropy": 5.937306308746338,
|
|
"epoch": 0.289822206095791,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004995521861381006,
|
|
"loss": 5.8947,
|
|
"mean_token_accuracy": 0.14612530022859574,
|
|
"num_tokens": 6636483.0,
|
|
"step": 3195
|
|
},
|
|
{
|
|
"entropy": 5.880060768127441,
|
|
"epoch": 0.29027576197387517,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.000499550143409388,
|
|
"loss": 5.8295,
|
|
"mean_token_accuracy": 0.14944281354546546,
|
|
"num_tokens": 6646807.0,
|
|
"step": 3200
|
|
},
|
|
{
|
|
"entropy": 5.923206090927124,
|
|
"epoch": 0.2907293178519594,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004995480960369211,
|
|
"loss": 5.859,
|
|
"mean_token_accuracy": 0.14405411332845688,
|
|
"num_tokens": 6656999.0,
|
|
"step": 3205
|
|
},
|
|
{
|
|
"entropy": 5.9521387100219725,
|
|
"epoch": 0.29118287373004353,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004995460440207425,
|
|
"loss": 5.7856,
|
|
"mean_token_accuracy": 0.1485783725976944,
|
|
"num_tokens": 6667507.0,
|
|
"step": 3210
|
|
},
|
|
{
|
|
"entropy": 5.80417103767395,
|
|
"epoch": 0.29163642960812775,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.0004995439873608945,
|
|
"loss": 5.8614,
|
|
"mean_token_accuracy": 0.14702842235565186,
|
|
"num_tokens": 6678701.0,
|
|
"step": 3215
|
|
},
|
|
{
|
|
"entropy": 5.996509981155396,
|
|
"epoch": 0.2920899854862119,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004995419260574196,
|
|
"loss": 5.9203,
|
|
"mean_token_accuracy": 0.14138441830873488,
|
|
"num_tokens": 6688153.0,
|
|
"step": 3220
|
|
},
|
|
{
|
|
"entropy": 5.804137706756592,
|
|
"epoch": 0.29254354136429606,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004995398601103603,
|
|
"loss": 5.7742,
|
|
"mean_token_accuracy": 0.14464350715279578,
|
|
"num_tokens": 6697992.0,
|
|
"step": 3225
|
|
},
|
|
{
|
|
"entropy": 5.876363611221313,
|
|
"epoch": 0.29299709724238027,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004995377895197597,
|
|
"loss": 5.8138,
|
|
"mean_token_accuracy": 0.15277422666549684,
|
|
"num_tokens": 6708203.0,
|
|
"step": 3230
|
|
},
|
|
{
|
|
"entropy": 5.924364757537842,
|
|
"epoch": 0.2934506531204644,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004995357142856602,
|
|
"loss": 5.8602,
|
|
"mean_token_accuracy": 0.1478705033659935,
|
|
"num_tokens": 6718531.0,
|
|
"step": 3235
|
|
},
|
|
{
|
|
"entropy": 5.851564741134643,
|
|
"epoch": 0.29390420899854863,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.000499533634408105,
|
|
"loss": 5.8488,
|
|
"mean_token_accuracy": 0.14651849120855331,
|
|
"num_tokens": 6729704.0,
|
|
"step": 3240
|
|
},
|
|
{
|
|
"entropy": 5.922415637969971,
|
|
"epoch": 0.2943577648766328,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.000499531549887137,
|
|
"loss": 5.8031,
|
|
"mean_token_accuracy": 0.15899783372879028,
|
|
"num_tokens": 6740736.0,
|
|
"step": 3245
|
|
},
|
|
{
|
|
"entropy": 5.880781555175782,
|
|
"epoch": 0.294811320754717,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004995294607227993,
|
|
"loss": 5.8681,
|
|
"mean_token_accuracy": 0.14151869863271713,
|
|
"num_tokens": 6751462.0,
|
|
"step": 3250
|
|
},
|
|
{
|
|
"entropy": 5.8272419452667235,
|
|
"epoch": 0.29526487663280115,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004995273669151351,
|
|
"loss": 5.7525,
|
|
"mean_token_accuracy": 0.14723548889160157,
|
|
"num_tokens": 6761438.0,
|
|
"step": 3255
|
|
},
|
|
{
|
|
"entropy": 5.87422890663147,
|
|
"epoch": 0.29571843251088537,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000499525268464188,
|
|
"loss": 5.8797,
|
|
"mean_token_accuracy": 0.13691834434866906,
|
|
"num_tokens": 6772906.0,
|
|
"step": 3260
|
|
},
|
|
{
|
|
"entropy": 5.919430732727051,
|
|
"epoch": 0.2961719883889695,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004995231653700009,
|
|
"loss": 5.832,
|
|
"mean_token_accuracy": 0.14906056374311447,
|
|
"num_tokens": 6782412.0,
|
|
"step": 3265
|
|
},
|
|
{
|
|
"entropy": 5.823684120178223,
|
|
"epoch": 0.2966255442670537,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004995210576326176,
|
|
"loss": 5.7617,
|
|
"mean_token_accuracy": 0.14652365446090698,
|
|
"num_tokens": 6793296.0,
|
|
"step": 3270
|
|
},
|
|
{
|
|
"entropy": 5.937224197387695,
|
|
"epoch": 0.2970791001451379,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004995189452520816,
|
|
"loss": 5.8337,
|
|
"mean_token_accuracy": 0.1496664322912693,
|
|
"num_tokens": 6803194.0,
|
|
"step": 3275
|
|
},
|
|
{
|
|
"entropy": 5.8328405857086185,
|
|
"epoch": 0.29753265602322204,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004995168282284366,
|
|
"loss": 5.8272,
|
|
"mean_token_accuracy": 0.1477750986814499,
|
|
"num_tokens": 6813720.0,
|
|
"step": 3280
|
|
},
|
|
{
|
|
"entropy": 5.831604099273681,
|
|
"epoch": 0.29798621190130625,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004995147065617263,
|
|
"loss": 5.6927,
|
|
"mean_token_accuracy": 0.14981145784258842,
|
|
"num_tokens": 6824835.0,
|
|
"step": 3285
|
|
},
|
|
{
|
|
"entropy": 5.885361862182617,
|
|
"epoch": 0.2984397677793904,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004995125802519946,
|
|
"loss": 5.8362,
|
|
"mean_token_accuracy": 0.14518534615635872,
|
|
"num_tokens": 6835913.0,
|
|
"step": 3290
|
|
},
|
|
{
|
|
"entropy": 5.92800350189209,
|
|
"epoch": 0.2988933236574746,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004995104492992857,
|
|
"loss": 5.8293,
|
|
"mean_token_accuracy": 0.14723531454801558,
|
|
"num_tokens": 6846305.0,
|
|
"step": 3295
|
|
},
|
|
{
|
|
"entropy": 5.803650140762329,
|
|
"epoch": 0.2993468795355588,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004995083137036434,
|
|
"loss": 5.8549,
|
|
"mean_token_accuracy": 0.1440051704645157,
|
|
"num_tokens": 6856466.0,
|
|
"step": 3300
|
|
},
|
|
{
|
|
"entropy": 5.9008081436157225,
|
|
"epoch": 0.299800435413643,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004995061734651121,
|
|
"loss": 5.8678,
|
|
"mean_token_accuracy": 0.14289252310991288,
|
|
"num_tokens": 6866982.0,
|
|
"step": 3305
|
|
},
|
|
{
|
|
"entropy": 5.892164897918701,
|
|
"epoch": 0.30025399129172714,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004995040285837358,
|
|
"loss": 5.8759,
|
|
"mean_token_accuracy": 0.1448530837893486,
|
|
"num_tokens": 6876915.0,
|
|
"step": 3310
|
|
},
|
|
{
|
|
"entropy": 5.9458733081817625,
|
|
"epoch": 0.3007075471698113,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004995018790595589,
|
|
"loss": 5.8415,
|
|
"mean_token_accuracy": 0.1469773143529892,
|
|
"num_tokens": 6886962.0,
|
|
"step": 3315
|
|
},
|
|
{
|
|
"entropy": 5.817418050765991,
|
|
"epoch": 0.3011611030478955,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004994997248926261,
|
|
"loss": 5.7322,
|
|
"mean_token_accuracy": 0.15008108466863632,
|
|
"num_tokens": 6897712.0,
|
|
"step": 3320
|
|
},
|
|
{
|
|
"entropy": 5.811979007720947,
|
|
"epoch": 0.30161465892597966,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004994975660829817,
|
|
"loss": 5.7633,
|
|
"mean_token_accuracy": 0.15170645713806152,
|
|
"num_tokens": 6908113.0,
|
|
"step": 3325
|
|
},
|
|
{
|
|
"entropy": 5.814332485198975,
|
|
"epoch": 0.3020682148040639,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004994954026306705,
|
|
"loss": 5.8455,
|
|
"mean_token_accuracy": 0.1410839483141899,
|
|
"num_tokens": 6918348.0,
|
|
"step": 3330
|
|
},
|
|
{
|
|
"entropy": 5.8640532970428465,
|
|
"epoch": 0.30252177068214803,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004994932345357371,
|
|
"loss": 5.7376,
|
|
"mean_token_accuracy": 0.16013350784778596,
|
|
"num_tokens": 6929309.0,
|
|
"step": 3335
|
|
},
|
|
{
|
|
"entropy": 5.850185680389404,
|
|
"epoch": 0.30297532656023224,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004994910617982264,
|
|
"loss": 5.8239,
|
|
"mean_token_accuracy": 0.15335479825735093,
|
|
"num_tokens": 6938023.0,
|
|
"step": 3340
|
|
},
|
|
{
|
|
"entropy": 5.89008207321167,
|
|
"epoch": 0.3034288824383164,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004994888844181833,
|
|
"loss": 5.7687,
|
|
"mean_token_accuracy": 0.15248255282640458,
|
|
"num_tokens": 6948957.0,
|
|
"step": 3345
|
|
},
|
|
{
|
|
"entropy": 5.891032981872558,
|
|
"epoch": 0.3038824383164006,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004994867023956529,
|
|
"loss": 5.7944,
|
|
"mean_token_accuracy": 0.14604247882962226,
|
|
"num_tokens": 6960343.0,
|
|
"step": 3350
|
|
},
|
|
{
|
|
"entropy": 5.824883317947387,
|
|
"epoch": 0.30433599419448476,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004994845157306803,
|
|
"loss": 5.7599,
|
|
"mean_token_accuracy": 0.1555237963795662,
|
|
"num_tokens": 6969858.0,
|
|
"step": 3355
|
|
},
|
|
{
|
|
"entropy": 5.783804941177368,
|
|
"epoch": 0.3047895500725689,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004994823244233107,
|
|
"loss": 5.7386,
|
|
"mean_token_accuracy": 0.1461342416703701,
|
|
"num_tokens": 6980805.0,
|
|
"step": 3360
|
|
},
|
|
{
|
|
"entropy": 5.849851274490357,
|
|
"epoch": 0.3052431059506531,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004994801284735895,
|
|
"loss": 5.7778,
|
|
"mean_token_accuracy": 0.1516255334019661,
|
|
"num_tokens": 6991076.0,
|
|
"step": 3365
|
|
},
|
|
{
|
|
"entropy": 5.833066177368164,
|
|
"epoch": 0.3056966618287373,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004994779278815619,
|
|
"loss": 5.7431,
|
|
"mean_token_accuracy": 0.1499674066901207,
|
|
"num_tokens": 7001179.0,
|
|
"step": 3370
|
|
},
|
|
{
|
|
"entropy": 5.87516975402832,
|
|
"epoch": 0.3061502177068215,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004994757226472736,
|
|
"loss": 5.884,
|
|
"mean_token_accuracy": 0.14582084268331527,
|
|
"num_tokens": 7011284.0,
|
|
"step": 3375
|
|
},
|
|
{
|
|
"entropy": 5.896537160873413,
|
|
"epoch": 0.30660377358490565,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004994735127707702,
|
|
"loss": 5.8938,
|
|
"mean_token_accuracy": 0.14885310232639312,
|
|
"num_tokens": 7021429.0,
|
|
"step": 3380
|
|
},
|
|
{
|
|
"entropy": 5.940958404541016,
|
|
"epoch": 0.30705732946298986,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004994712982520972,
|
|
"loss": 5.8062,
|
|
"mean_token_accuracy": 0.15399947464466096,
|
|
"num_tokens": 7032313.0,
|
|
"step": 3385
|
|
},
|
|
{
|
|
"entropy": 5.8307092666625975,
|
|
"epoch": 0.307510885341074,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004994690790913008,
|
|
"loss": 5.7213,
|
|
"mean_token_accuracy": 0.15415123999118804,
|
|
"num_tokens": 7042791.0,
|
|
"step": 3390
|
|
},
|
|
{
|
|
"entropy": 5.759172677993774,
|
|
"epoch": 0.3079644412191582,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004994668552884265,
|
|
"loss": 5.7435,
|
|
"mean_token_accuracy": 0.1518249973654747,
|
|
"num_tokens": 7054048.0,
|
|
"step": 3395
|
|
},
|
|
{
|
|
"entropy": 5.948722553253174,
|
|
"epoch": 0.3084179970972424,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004994646268435204,
|
|
"loss": 5.8554,
|
|
"mean_token_accuracy": 0.14281615018844604,
|
|
"num_tokens": 7064179.0,
|
|
"step": 3400
|
|
},
|
|
{
|
|
"entropy": 5.822907161712647,
|
|
"epoch": 0.30887155297532654,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004994623937566286,
|
|
"loss": 5.6967,
|
|
"mean_token_accuracy": 0.15609691590070723,
|
|
"num_tokens": 7073570.0,
|
|
"step": 3405
|
|
},
|
|
{
|
|
"entropy": 5.700627851486206,
|
|
"epoch": 0.30932510885341075,
|
|
"grad_norm": 3.515625,
|
|
"learning_rate": 0.0004994601560277974,
|
|
"loss": 5.7584,
|
|
"mean_token_accuracy": 0.15373585373163223,
|
|
"num_tokens": 7083646.0,
|
|
"step": 3410
|
|
},
|
|
{
|
|
"entropy": 5.739640378952027,
|
|
"epoch": 0.3097786647314949,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.000499457913657073,
|
|
"loss": 5.683,
|
|
"mean_token_accuracy": 0.1485663816332817,
|
|
"num_tokens": 7093950.0,
|
|
"step": 3415
|
|
},
|
|
{
|
|
"entropy": 5.8701647281646725,
|
|
"epoch": 0.3102322206095791,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004994556666445016,
|
|
"loss": 5.8153,
|
|
"mean_token_accuracy": 0.14636703729629516,
|
|
"num_tokens": 7103501.0,
|
|
"step": 3420
|
|
},
|
|
{
|
|
"entropy": 5.828254222869873,
|
|
"epoch": 0.31068577648766327,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004994534149901299,
|
|
"loss": 5.7896,
|
|
"mean_token_accuracy": 0.15028128027915955,
|
|
"num_tokens": 7113595.0,
|
|
"step": 3425
|
|
},
|
|
{
|
|
"entropy": 5.871004867553711,
|
|
"epoch": 0.3111393323657475,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004994511586940044,
|
|
"loss": 5.7553,
|
|
"mean_token_accuracy": 0.14996377378702164,
|
|
"num_tokens": 7123314.0,
|
|
"step": 3430
|
|
},
|
|
{
|
|
"entropy": 5.794569110870361,
|
|
"epoch": 0.31159288824383163,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004994488977561717,
|
|
"loss": 5.7229,
|
|
"mean_token_accuracy": 0.15273373425006867,
|
|
"num_tokens": 7132603.0,
|
|
"step": 3435
|
|
},
|
|
{
|
|
"entropy": 5.889085912704468,
|
|
"epoch": 0.31204644412191584,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004994466321766786,
|
|
"loss": 5.7693,
|
|
"mean_token_accuracy": 0.14626731872558593,
|
|
"num_tokens": 7142112.0,
|
|
"step": 3440
|
|
},
|
|
{
|
|
"entropy": 5.870463895797729,
|
|
"epoch": 0.3125,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.000499444361955572,
|
|
"loss": 5.8708,
|
|
"mean_token_accuracy": 0.14073101803660393,
|
|
"num_tokens": 7152862.0,
|
|
"step": 3445
|
|
},
|
|
{
|
|
"entropy": 5.847962331771851,
|
|
"epoch": 0.31295355587808416,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004994420870928988,
|
|
"loss": 5.7976,
|
|
"mean_token_accuracy": 0.15040374025702477,
|
|
"num_tokens": 7163217.0,
|
|
"step": 3450
|
|
},
|
|
{
|
|
"entropy": 5.846856784820557,
|
|
"epoch": 0.31340711175616837,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004994398075887059,
|
|
"loss": 5.8103,
|
|
"mean_token_accuracy": 0.1441519945859909,
|
|
"num_tokens": 7173555.0,
|
|
"step": 3455
|
|
},
|
|
{
|
|
"entropy": 5.851716375350952,
|
|
"epoch": 0.3138606676342525,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004994375234430407,
|
|
"loss": 5.8194,
|
|
"mean_token_accuracy": 0.1495192438364029,
|
|
"num_tokens": 7184011.0,
|
|
"step": 3460
|
|
},
|
|
{
|
|
"entropy": 5.965654373168945,
|
|
"epoch": 0.31431422351233673,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004994352346559504,
|
|
"loss": 5.8129,
|
|
"mean_token_accuracy": 0.14340534433722496,
|
|
"num_tokens": 7194709.0,
|
|
"step": 3465
|
|
},
|
|
{
|
|
"entropy": 5.822262144088745,
|
|
"epoch": 0.3147677793904209,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004994329412274821,
|
|
"loss": 5.7452,
|
|
"mean_token_accuracy": 0.15087789446115493,
|
|
"num_tokens": 7205010.0,
|
|
"step": 3470
|
|
},
|
|
{
|
|
"entropy": 5.87249641418457,
|
|
"epoch": 0.3152213352685051,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004994306431576835,
|
|
"loss": 5.8343,
|
|
"mean_token_accuracy": 0.14334458857774734,
|
|
"num_tokens": 7215673.0,
|
|
"step": 3475
|
|
},
|
|
{
|
|
"entropy": 5.864829349517822,
|
|
"epoch": 0.31567489114658925,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.000499428340446602,
|
|
"loss": 5.7393,
|
|
"mean_token_accuracy": 0.14581746309995652,
|
|
"num_tokens": 7226084.0,
|
|
"step": 3480
|
|
},
|
|
{
|
|
"entropy": 5.927701616287232,
|
|
"epoch": 0.31612844702467346,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004994260330942851,
|
|
"loss": 5.8581,
|
|
"mean_token_accuracy": 0.14685110300779342,
|
|
"num_tokens": 7236155.0,
|
|
"step": 3485
|
|
},
|
|
{
|
|
"entropy": 5.849013614654541,
|
|
"epoch": 0.3165820029027576,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004994237211007808,
|
|
"loss": 5.8153,
|
|
"mean_token_accuracy": 0.1452503725886345,
|
|
"num_tokens": 7246226.0,
|
|
"step": 3490
|
|
},
|
|
{
|
|
"entropy": 5.9544209957122805,
|
|
"epoch": 0.3170355587808418,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004994214044661367,
|
|
"loss": 5.867,
|
|
"mean_token_accuracy": 0.14869623333215715,
|
|
"num_tokens": 7256573.0,
|
|
"step": 3495
|
|
},
|
|
{
|
|
"entropy": 5.792372131347657,
|
|
"epoch": 0.317489114658926,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004994190831904007,
|
|
"loss": 5.7755,
|
|
"mean_token_accuracy": 0.15131996273994447,
|
|
"num_tokens": 7266546.0,
|
|
"step": 3500
|
|
},
|
|
{
|
|
"entropy": 5.813211441040039,
|
|
"epoch": 0.31794267053701014,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000499416757273621,
|
|
"loss": 5.6998,
|
|
"mean_token_accuracy": 0.1527576208114624,
|
|
"num_tokens": 7276902.0,
|
|
"step": 3505
|
|
},
|
|
{
|
|
"entropy": 5.7668062210083,
|
|
"epoch": 0.31839622641509435,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004994144267158454,
|
|
"loss": 5.7249,
|
|
"mean_token_accuracy": 0.14934021681547166,
|
|
"num_tokens": 7286932.0,
|
|
"step": 3510
|
|
},
|
|
{
|
|
"entropy": 5.773153018951416,
|
|
"epoch": 0.3188497822931785,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004994120915171224,
|
|
"loss": 5.7187,
|
|
"mean_token_accuracy": 0.14774317145347596,
|
|
"num_tokens": 7296317.0,
|
|
"step": 3515
|
|
},
|
|
{
|
|
"entropy": 5.840611457824707,
|
|
"epoch": 0.3193033381712627,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004994097516775002,
|
|
"loss": 5.8046,
|
|
"mean_token_accuracy": 0.15059873461723328,
|
|
"num_tokens": 7307127.0,
|
|
"step": 3520
|
|
},
|
|
{
|
|
"entropy": 6.010704231262207,
|
|
"epoch": 0.3197568940493469,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004994074071970271,
|
|
"loss": 5.9297,
|
|
"mean_token_accuracy": 0.13786763176321984,
|
|
"num_tokens": 7318962.0,
|
|
"step": 3525
|
|
},
|
|
{
|
|
"entropy": 5.847193717956543,
|
|
"epoch": 0.3202104499274311,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004994050580757515,
|
|
"loss": 5.7375,
|
|
"mean_token_accuracy": 0.1580265372991562,
|
|
"num_tokens": 7328834.0,
|
|
"step": 3530
|
|
},
|
|
{
|
|
"entropy": 5.82778787612915,
|
|
"epoch": 0.32066400580551524,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004994027043137223,
|
|
"loss": 5.8404,
|
|
"mean_token_accuracy": 0.14816899076104165,
|
|
"num_tokens": 7338454.0,
|
|
"step": 3535
|
|
},
|
|
{
|
|
"entropy": 5.902290487289429,
|
|
"epoch": 0.3211175616835994,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004994003459109879,
|
|
"loss": 5.775,
|
|
"mean_token_accuracy": 0.15195251405239105,
|
|
"num_tokens": 7349604.0,
|
|
"step": 3540
|
|
},
|
|
{
|
|
"entropy": 5.754151678085327,
|
|
"epoch": 0.3215711175616836,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004993979828675972,
|
|
"loss": 5.6986,
|
|
"mean_token_accuracy": 0.1630345344543457,
|
|
"num_tokens": 7359892.0,
|
|
"step": 3545
|
|
},
|
|
{
|
|
"entropy": 5.864100790023803,
|
|
"epoch": 0.32202467343976776,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.000499395615183599,
|
|
"loss": 5.8551,
|
|
"mean_token_accuracy": 0.13787850961089135,
|
|
"num_tokens": 7370430.0,
|
|
"step": 3550
|
|
},
|
|
{
|
|
"entropy": 5.989569902420044,
|
|
"epoch": 0.32247822931785197,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004993932428590422,
|
|
"loss": 5.8823,
|
|
"mean_token_accuracy": 0.1492062494158745,
|
|
"num_tokens": 7380328.0,
|
|
"step": 3555
|
|
},
|
|
{
|
|
"entropy": 5.8746685028076175,
|
|
"epoch": 0.3229317851959361,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004993908658939762,
|
|
"loss": 5.7863,
|
|
"mean_token_accuracy": 0.1424688369035721,
|
|
"num_tokens": 7390155.0,
|
|
"step": 3560
|
|
},
|
|
{
|
|
"entropy": 5.767589282989502,
|
|
"epoch": 0.32338534107402034,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004993884842884496,
|
|
"loss": 5.7555,
|
|
"mean_token_accuracy": 0.14230301976203918,
|
|
"num_tokens": 7400659.0,
|
|
"step": 3565
|
|
},
|
|
{
|
|
"entropy": 5.876905155181885,
|
|
"epoch": 0.3238388969521045,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004993860980425121,
|
|
"loss": 5.7084,
|
|
"mean_token_accuracy": 0.14975891560316085,
|
|
"num_tokens": 7410580.0,
|
|
"step": 3570
|
|
},
|
|
{
|
|
"entropy": 5.772308874130249,
|
|
"epoch": 0.3242924528301887,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004993837071562131,
|
|
"loss": 5.7153,
|
|
"mean_token_accuracy": 0.1530524328351021,
|
|
"num_tokens": 7421119.0,
|
|
"step": 3575
|
|
},
|
|
{
|
|
"entropy": 5.865143728256226,
|
|
"epoch": 0.32474600870827286,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004993813116296017,
|
|
"loss": 5.7948,
|
|
"mean_token_accuracy": 0.1488372266292572,
|
|
"num_tokens": 7431565.0,
|
|
"step": 3580
|
|
},
|
|
{
|
|
"entropy": 5.804593276977539,
|
|
"epoch": 0.325199564586357,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004993789114627275,
|
|
"loss": 5.7803,
|
|
"mean_token_accuracy": 0.14988463148474693,
|
|
"num_tokens": 7441638.0,
|
|
"step": 3585
|
|
},
|
|
{
|
|
"entropy": 5.884509611129761,
|
|
"epoch": 0.3256531204644412,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004993765066556403,
|
|
"loss": 5.8635,
|
|
"mean_token_accuracy": 0.14145209044218063,
|
|
"num_tokens": 7452547.0,
|
|
"step": 3590
|
|
},
|
|
{
|
|
"entropy": 6.058124256134033,
|
|
"epoch": 0.3261066763425254,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004993740972083899,
|
|
"loss": 5.8273,
|
|
"mean_token_accuracy": 0.14561535716056823,
|
|
"num_tokens": 7463009.0,
|
|
"step": 3595
|
|
},
|
|
{
|
|
"entropy": 5.7878905773162845,
|
|
"epoch": 0.3265602322206096,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004993716831210259,
|
|
"loss": 5.7909,
|
|
"mean_token_accuracy": 0.14785151481628417,
|
|
"num_tokens": 7473929.0,
|
|
"step": 3600
|
|
},
|
|
{
|
|
"entropy": 5.814364290237426,
|
|
"epoch": 0.32701378809869375,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004993692643935983,
|
|
"loss": 5.7488,
|
|
"mean_token_accuracy": 0.1513546124100685,
|
|
"num_tokens": 7483480.0,
|
|
"step": 3605
|
|
},
|
|
{
|
|
"entropy": 5.831703853607178,
|
|
"epoch": 0.32746734397677796,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004993668410261571,
|
|
"loss": 5.7732,
|
|
"mean_token_accuracy": 0.15670879930257797,
|
|
"num_tokens": 7492430.0,
|
|
"step": 3610
|
|
},
|
|
{
|
|
"entropy": 5.79875431060791,
|
|
"epoch": 0.3279208998548621,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004993644130187525,
|
|
"loss": 5.7154,
|
|
"mean_token_accuracy": 0.1530866101384163,
|
|
"num_tokens": 7502647.0,
|
|
"step": 3615
|
|
},
|
|
{
|
|
"entropy": 5.8937335968017575,
|
|
"epoch": 0.3283744557329463,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004993619803714347,
|
|
"loss": 5.7763,
|
|
"mean_token_accuracy": 0.1489662602543831,
|
|
"num_tokens": 7512841.0,
|
|
"step": 3620
|
|
},
|
|
{
|
|
"entropy": 5.819048357009888,
|
|
"epoch": 0.3288280116110305,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004993595430842539,
|
|
"loss": 5.7788,
|
|
"mean_token_accuracy": 0.1483454167842865,
|
|
"num_tokens": 7522998.0,
|
|
"step": 3625
|
|
},
|
|
{
|
|
"entropy": 5.798835420608521,
|
|
"epoch": 0.32928156748911463,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004993571011572606,
|
|
"loss": 5.7548,
|
|
"mean_token_accuracy": 0.14865725487470627,
|
|
"num_tokens": 7533918.0,
|
|
"step": 3630
|
|
},
|
|
{
|
|
"entropy": 5.797335433959961,
|
|
"epoch": 0.32973512336719885,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004993546545905053,
|
|
"loss": 5.7506,
|
|
"mean_token_accuracy": 0.14760544002056122,
|
|
"num_tokens": 7543871.0,
|
|
"step": 3635
|
|
},
|
|
{
|
|
"entropy": 5.8824381828308105,
|
|
"epoch": 0.330188679245283,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004993522033840386,
|
|
"loss": 5.8131,
|
|
"mean_token_accuracy": 0.14790321439504622,
|
|
"num_tokens": 7554426.0,
|
|
"step": 3640
|
|
},
|
|
{
|
|
"entropy": 5.838723278045654,
|
|
"epoch": 0.3306422351233672,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.000499349747537911,
|
|
"loss": 5.762,
|
|
"mean_token_accuracy": 0.142730812728405,
|
|
"num_tokens": 7564578.0,
|
|
"step": 3645
|
|
},
|
|
{
|
|
"entropy": 5.806462001800537,
|
|
"epoch": 0.33109579100145137,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004993472870521736,
|
|
"loss": 5.7714,
|
|
"mean_token_accuracy": 0.15052106082439423,
|
|
"num_tokens": 7574167.0,
|
|
"step": 3650
|
|
},
|
|
{
|
|
"entropy": 5.846491432189941,
|
|
"epoch": 0.3315493468795356,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004993448219268771,
|
|
"loss": 5.8119,
|
|
"mean_token_accuracy": 0.14406854510307313,
|
|
"num_tokens": 7584869.0,
|
|
"step": 3655
|
|
},
|
|
{
|
|
"entropy": 5.897862386703491,
|
|
"epoch": 0.33200290275761973,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004993423521620726,
|
|
"loss": 5.8474,
|
|
"mean_token_accuracy": 0.1513499826192856,
|
|
"num_tokens": 7595385.0,
|
|
"step": 3660
|
|
},
|
|
{
|
|
"entropy": 5.896338558197021,
|
|
"epoch": 0.33245645863570394,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004993398777578109,
|
|
"loss": 5.7756,
|
|
"mean_token_accuracy": 0.15635844320058823,
|
|
"num_tokens": 7604498.0,
|
|
"step": 3665
|
|
},
|
|
{
|
|
"entropy": 5.838066625595093,
|
|
"epoch": 0.3329100145137881,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004993373987141435,
|
|
"loss": 5.7877,
|
|
"mean_token_accuracy": 0.15075664073228837,
|
|
"num_tokens": 7615029.0,
|
|
"step": 3670
|
|
},
|
|
{
|
|
"entropy": 5.829625225067138,
|
|
"epoch": 0.33336357039187225,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004993349150311214,
|
|
"loss": 5.7578,
|
|
"mean_token_accuracy": 0.15550185292959212,
|
|
"num_tokens": 7625088.0,
|
|
"step": 3675
|
|
},
|
|
{
|
|
"entropy": 5.873695707321167,
|
|
"epoch": 0.33381712626995647,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004993324267087962,
|
|
"loss": 5.7235,
|
|
"mean_token_accuracy": 0.15278095602989197,
|
|
"num_tokens": 7634668.0,
|
|
"step": 3680
|
|
},
|
|
{
|
|
"entropy": 5.771748781204224,
|
|
"epoch": 0.3342706821480406,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004993299337472192,
|
|
"loss": 5.7393,
|
|
"mean_token_accuracy": 0.14780182838439943,
|
|
"num_tokens": 7644581.0,
|
|
"step": 3685
|
|
},
|
|
{
|
|
"entropy": 5.806529855728149,
|
|
"epoch": 0.33472423802612483,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.000499327436146442,
|
|
"loss": 5.7868,
|
|
"mean_token_accuracy": 0.15356959104537965,
|
|
"num_tokens": 7653772.0,
|
|
"step": 3690
|
|
},
|
|
{
|
|
"entropy": 5.854533910751343,
|
|
"epoch": 0.335177793904209,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004993249339065162,
|
|
"loss": 5.7995,
|
|
"mean_token_accuracy": 0.14647793769836426,
|
|
"num_tokens": 7663489.0,
|
|
"step": 3695
|
|
},
|
|
{
|
|
"entropy": 5.83122410774231,
|
|
"epoch": 0.3356313497822932,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004993224270274937,
|
|
"loss": 5.8487,
|
|
"mean_token_accuracy": 0.14324984103441238,
|
|
"num_tokens": 7674195.0,
|
|
"step": 3700
|
|
},
|
|
{
|
|
"entropy": 5.93805251121521,
|
|
"epoch": 0.33608490566037735,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004993199155094263,
|
|
"loss": 5.7818,
|
|
"mean_token_accuracy": 0.14835535734891891,
|
|
"num_tokens": 7684385.0,
|
|
"step": 3705
|
|
},
|
|
{
|
|
"entropy": 5.856555938720703,
|
|
"epoch": 0.33653846153846156,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004993173993523658,
|
|
"loss": 5.7167,
|
|
"mean_token_accuracy": 0.14758910685777665,
|
|
"num_tokens": 7694025.0,
|
|
"step": 3710
|
|
},
|
|
{
|
|
"entropy": 5.785606622695923,
|
|
"epoch": 0.3369920174165457,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004993148785563643,
|
|
"loss": 5.867,
|
|
"mean_token_accuracy": 0.14351308196783066,
|
|
"num_tokens": 7702568.0,
|
|
"step": 3715
|
|
},
|
|
{
|
|
"entropy": 5.921364879608154,
|
|
"epoch": 0.3374455732946299,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.000499312353121474,
|
|
"loss": 5.7901,
|
|
"mean_token_accuracy": 0.14799848794937134,
|
|
"num_tokens": 7712895.0,
|
|
"step": 3720
|
|
},
|
|
{
|
|
"entropy": 5.888604354858399,
|
|
"epoch": 0.3378991291727141,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004993098230477471,
|
|
"loss": 5.8151,
|
|
"mean_token_accuracy": 0.15019485503435134,
|
|
"num_tokens": 7723182.0,
|
|
"step": 3725
|
|
},
|
|
{
|
|
"entropy": 5.775590276718139,
|
|
"epoch": 0.33835268505079824,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004993072883352358,
|
|
"loss": 5.7256,
|
|
"mean_token_accuracy": 0.1515362799167633,
|
|
"num_tokens": 7732628.0,
|
|
"step": 3730
|
|
},
|
|
{
|
|
"entropy": 5.752090549468994,
|
|
"epoch": 0.33880624092888245,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004993047489839927,
|
|
"loss": 5.7602,
|
|
"mean_token_accuracy": 0.14875489473342896,
|
|
"num_tokens": 7742396.0,
|
|
"step": 3735
|
|
},
|
|
{
|
|
"entropy": 5.858716344833374,
|
|
"epoch": 0.3392597968069666,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004993022049940702,
|
|
"loss": 5.8165,
|
|
"mean_token_accuracy": 0.145614355802536,
|
|
"num_tokens": 7752070.0,
|
|
"step": 3740
|
|
},
|
|
{
|
|
"entropy": 5.987333536148071,
|
|
"epoch": 0.3397133526850508,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004992996563655209,
|
|
"loss": 5.8532,
|
|
"mean_token_accuracy": 0.1467878058552742,
|
|
"num_tokens": 7762471.0,
|
|
"step": 3745
|
|
},
|
|
{
|
|
"entropy": 5.87470383644104,
|
|
"epoch": 0.340166908563135,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004992971030983975,
|
|
"loss": 5.8111,
|
|
"mean_token_accuracy": 0.1498027741909027,
|
|
"num_tokens": 7772707.0,
|
|
"step": 3750
|
|
},
|
|
{
|
|
"entropy": 5.763695287704468,
|
|
"epoch": 0.3406204644412192,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004992945451927531,
|
|
"loss": 5.7885,
|
|
"mean_token_accuracy": 0.14555259197950363,
|
|
"num_tokens": 7782883.0,
|
|
"step": 3755
|
|
},
|
|
{
|
|
"entropy": 5.843745946884155,
|
|
"epoch": 0.34107402031930334,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004992919826486402,
|
|
"loss": 5.7445,
|
|
"mean_token_accuracy": 0.14721848517656327,
|
|
"num_tokens": 7793876.0,
|
|
"step": 3760
|
|
},
|
|
{
|
|
"entropy": 5.876995658874511,
|
|
"epoch": 0.3415275761973875,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004992894154661118,
|
|
"loss": 5.8008,
|
|
"mean_token_accuracy": 0.1452129989862442,
|
|
"num_tokens": 7804777.0,
|
|
"step": 3765
|
|
},
|
|
{
|
|
"entropy": 5.837781381607056,
|
|
"epoch": 0.3419811320754717,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004992868436452213,
|
|
"loss": 5.7358,
|
|
"mean_token_accuracy": 0.1464160442352295,
|
|
"num_tokens": 7815392.0,
|
|
"step": 3770
|
|
},
|
|
{
|
|
"entropy": 5.848176908493042,
|
|
"epoch": 0.34243468795355586,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004992842671860217,
|
|
"loss": 5.7548,
|
|
"mean_token_accuracy": 0.15367420464754106,
|
|
"num_tokens": 7825909.0,
|
|
"step": 3775
|
|
},
|
|
{
|
|
"entropy": 5.799251651763916,
|
|
"epoch": 0.34288824383164007,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004992816860885662,
|
|
"loss": 5.7141,
|
|
"mean_token_accuracy": 0.15675887688994408,
|
|
"num_tokens": 7836513.0,
|
|
"step": 3780
|
|
},
|
|
{
|
|
"entropy": 5.899875736236572,
|
|
"epoch": 0.3433417997097242,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004992791003529084,
|
|
"loss": 5.8178,
|
|
"mean_token_accuracy": 0.14457211792469024,
|
|
"num_tokens": 7847363.0,
|
|
"step": 3785
|
|
},
|
|
{
|
|
"entropy": 5.771605920791626,
|
|
"epoch": 0.34379535558780844,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004992765099791017,
|
|
"loss": 5.6438,
|
|
"mean_token_accuracy": 0.15770225077867508,
|
|
"num_tokens": 7857510.0,
|
|
"step": 3790
|
|
},
|
|
{
|
|
"entropy": 5.728345155715942,
|
|
"epoch": 0.3442489114658926,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004992739149671995,
|
|
"loss": 5.7539,
|
|
"mean_token_accuracy": 0.1475256159901619,
|
|
"num_tokens": 7868239.0,
|
|
"step": 3795
|
|
},
|
|
{
|
|
"entropy": 5.828153514862061,
|
|
"epoch": 0.3447024673439768,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.0004992713153172556,
|
|
"loss": 5.7376,
|
|
"mean_token_accuracy": 0.1523927077651024,
|
|
"num_tokens": 7878145.0,
|
|
"step": 3800
|
|
},
|
|
{
|
|
"entropy": 5.877768325805664,
|
|
"epoch": 0.34515602322206096,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004992687110293238,
|
|
"loss": 5.8837,
|
|
"mean_token_accuracy": 0.1435710608959198,
|
|
"num_tokens": 7889011.0,
|
|
"step": 3805
|
|
},
|
|
{
|
|
"entropy": 5.886313724517822,
|
|
"epoch": 0.3456095791001451,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004992661021034579,
|
|
"loss": 5.7437,
|
|
"mean_token_accuracy": 0.1526486322283745,
|
|
"num_tokens": 7898400.0,
|
|
"step": 3810
|
|
},
|
|
{
|
|
"entropy": 5.824654531478882,
|
|
"epoch": 0.3460631349782293,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004992634885397118,
|
|
"loss": 5.7714,
|
|
"mean_token_accuracy": 0.153218924254179,
|
|
"num_tokens": 7908598.0,
|
|
"step": 3815
|
|
},
|
|
{
|
|
"entropy": 5.864112329483032,
|
|
"epoch": 0.3465166908563135,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.0004992608703381396,
|
|
"loss": 5.8513,
|
|
"mean_token_accuracy": 0.13871943727135658,
|
|
"num_tokens": 7918870.0,
|
|
"step": 3820
|
|
},
|
|
{
|
|
"entropy": 5.77078537940979,
|
|
"epoch": 0.3469702467343977,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004992582474987955,
|
|
"loss": 5.7228,
|
|
"mean_token_accuracy": 0.1529923766851425,
|
|
"num_tokens": 7928669.0,
|
|
"step": 3825
|
|
},
|
|
{
|
|
"entropy": 5.823331737518311,
|
|
"epoch": 0.34742380261248185,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004992556200217337,
|
|
"loss": 5.7597,
|
|
"mean_token_accuracy": 0.14865635335445404,
|
|
"num_tokens": 7939500.0,
|
|
"step": 3830
|
|
},
|
|
{
|
|
"entropy": 5.77082085609436,
|
|
"epoch": 0.34787735849056606,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004992529879070085,
|
|
"loss": 5.7085,
|
|
"mean_token_accuracy": 0.15079121440649032,
|
|
"num_tokens": 7949411.0,
|
|
"step": 3835
|
|
},
|
|
{
|
|
"entropy": 5.860919952392578,
|
|
"epoch": 0.3483309143686502,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004992503511546745,
|
|
"loss": 5.6855,
|
|
"mean_token_accuracy": 0.15580998584628106,
|
|
"num_tokens": 7959242.0,
|
|
"step": 3840
|
|
},
|
|
{
|
|
"entropy": 5.858591938018799,
|
|
"epoch": 0.3487844702467344,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.0004992477097647859,
|
|
"loss": 5.7569,
|
|
"mean_token_accuracy": 0.14921135529875756,
|
|
"num_tokens": 7969903.0,
|
|
"step": 3845
|
|
},
|
|
{
|
|
"entropy": 5.800677537918091,
|
|
"epoch": 0.3492380261248186,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004992450637373976,
|
|
"loss": 5.8584,
|
|
"mean_token_accuracy": 0.14383849501609802,
|
|
"num_tokens": 7981765.0,
|
|
"step": 3850
|
|
},
|
|
{
|
|
"entropy": 5.8215028762817385,
|
|
"epoch": 0.34969158200290273,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004992424130725642,
|
|
"loss": 5.7196,
|
|
"mean_token_accuracy": 0.15478193014860153,
|
|
"num_tokens": 7992480.0,
|
|
"step": 3855
|
|
},
|
|
{
|
|
"entropy": 5.939544343948365,
|
|
"epoch": 0.35014513788098695,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004992397577703406,
|
|
"loss": 5.8448,
|
|
"mean_token_accuracy": 0.1454885832965374,
|
|
"num_tokens": 8002874.0,
|
|
"step": 3860
|
|
},
|
|
{
|
|
"entropy": 5.930872011184692,
|
|
"epoch": 0.3505986937590711,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004992370978307816,
|
|
"loss": 5.7948,
|
|
"mean_token_accuracy": 0.14592455103993415,
|
|
"num_tokens": 8013582.0,
|
|
"step": 3865
|
|
},
|
|
{
|
|
"entropy": 5.803278875350952,
|
|
"epoch": 0.3510522496371553,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004992344332539424,
|
|
"loss": 5.8452,
|
|
"mean_token_accuracy": 0.14719062745571138,
|
|
"num_tokens": 8023492.0,
|
|
"step": 3870
|
|
},
|
|
{
|
|
"entropy": 5.832758569717408,
|
|
"epoch": 0.35150580551523947,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004992317640398779,
|
|
"loss": 5.7896,
|
|
"mean_token_accuracy": 0.1514344558119774,
|
|
"num_tokens": 8034400.0,
|
|
"step": 3875
|
|
},
|
|
{
|
|
"entropy": 5.846541547775269,
|
|
"epoch": 0.3519593613933237,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004992290901886434,
|
|
"loss": 5.7428,
|
|
"mean_token_accuracy": 0.14580017030239106,
|
|
"num_tokens": 8044779.0,
|
|
"step": 3880
|
|
},
|
|
{
|
|
"entropy": 5.809729337692261,
|
|
"epoch": 0.35241291727140783,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.000499226411700294,
|
|
"loss": 5.817,
|
|
"mean_token_accuracy": 0.152392890304327,
|
|
"num_tokens": 8055017.0,
|
|
"step": 3885
|
|
},
|
|
{
|
|
"entropy": 5.825460529327392,
|
|
"epoch": 0.35286647314949204,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004992237285748855,
|
|
"loss": 5.7631,
|
|
"mean_token_accuracy": 0.1490686446428299,
|
|
"num_tokens": 8065369.0,
|
|
"step": 3890
|
|
},
|
|
{
|
|
"entropy": 5.810965633392334,
|
|
"epoch": 0.3533200290275762,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004992210408124731,
|
|
"loss": 5.7273,
|
|
"mean_token_accuracy": 0.14731293469667434,
|
|
"num_tokens": 8075697.0,
|
|
"step": 3895
|
|
},
|
|
{
|
|
"entropy": 5.816468000411987,
|
|
"epoch": 0.35377358490566035,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004992183484131123,
|
|
"loss": 5.77,
|
|
"mean_token_accuracy": 0.14932163804769516,
|
|
"num_tokens": 8086808.0,
|
|
"step": 3900
|
|
},
|
|
{
|
|
"entropy": 5.838976526260376,
|
|
"epoch": 0.35422714078374457,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004992156513768591,
|
|
"loss": 5.6807,
|
|
"mean_token_accuracy": 0.1584209680557251,
|
|
"num_tokens": 8095933.0,
|
|
"step": 3905
|
|
},
|
|
{
|
|
"entropy": 5.826946640014649,
|
|
"epoch": 0.3546806966618287,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.000499212949703769,
|
|
"loss": 5.7467,
|
|
"mean_token_accuracy": 0.1475004769861698,
|
|
"num_tokens": 8106591.0,
|
|
"step": 3910
|
|
},
|
|
{
|
|
"entropy": 5.946511936187744,
|
|
"epoch": 0.35513425253991293,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004992102433938981,
|
|
"loss": 5.8134,
|
|
"mean_token_accuracy": 0.1470434546470642,
|
|
"num_tokens": 8117189.0,
|
|
"step": 3915
|
|
},
|
|
{
|
|
"entropy": 5.775824356079101,
|
|
"epoch": 0.3555878084179971,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004992075324473021,
|
|
"loss": 5.7303,
|
|
"mean_token_accuracy": 0.1483267366886139,
|
|
"num_tokens": 8128182.0,
|
|
"step": 3920
|
|
},
|
|
{
|
|
"entropy": 5.79977331161499,
|
|
"epoch": 0.3560413642960813,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004992048168640371,
|
|
"loss": 5.7825,
|
|
"mean_token_accuracy": 0.14967008605599402,
|
|
"num_tokens": 8137998.0,
|
|
"step": 3925
|
|
},
|
|
{
|
|
"entropy": 5.905167484283448,
|
|
"epoch": 0.35649492017416545,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004992020966441595,
|
|
"loss": 5.7238,
|
|
"mean_token_accuracy": 0.15360095202922822,
|
|
"num_tokens": 8148512.0,
|
|
"step": 3930
|
|
},
|
|
{
|
|
"entropy": 5.827831888198853,
|
|
"epoch": 0.35694847605224966,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004991993717877254,
|
|
"loss": 5.8453,
|
|
"mean_token_accuracy": 0.1487443283200264,
|
|
"num_tokens": 8160154.0,
|
|
"step": 3935
|
|
},
|
|
{
|
|
"entropy": 5.784213018417359,
|
|
"epoch": 0.3574020319303338,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004991966422947911,
|
|
"loss": 5.7345,
|
|
"mean_token_accuracy": 0.15293765664100648,
|
|
"num_tokens": 8169087.0,
|
|
"step": 3940
|
|
},
|
|
{
|
|
"entropy": 5.776965713500976,
|
|
"epoch": 0.357855587808418,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004991939081654132,
|
|
"loss": 5.6821,
|
|
"mean_token_accuracy": 0.15219976007938385,
|
|
"num_tokens": 8178934.0,
|
|
"step": 3945
|
|
},
|
|
{
|
|
"entropy": 5.852101612091064,
|
|
"epoch": 0.3583091436865022,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.000499191169399648,
|
|
"loss": 5.7385,
|
|
"mean_token_accuracy": 0.14779181852936746,
|
|
"num_tokens": 8189476.0,
|
|
"step": 3950
|
|
},
|
|
{
|
|
"entropy": 5.826294946670532,
|
|
"epoch": 0.35876269956458634,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004991884259975525,
|
|
"loss": 5.7689,
|
|
"mean_token_accuracy": 0.14812640249729156,
|
|
"num_tokens": 8199297.0,
|
|
"step": 3955
|
|
},
|
|
{
|
|
"entropy": 5.7677168369293215,
|
|
"epoch": 0.35921625544267055,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.000499185677959183,
|
|
"loss": 5.702,
|
|
"mean_token_accuracy": 0.15490943789482117,
|
|
"num_tokens": 8209723.0,
|
|
"step": 3960
|
|
},
|
|
{
|
|
"entropy": 5.719799375534057,
|
|
"epoch": 0.3596698113207547,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004991829252845966,
|
|
"loss": 5.725,
|
|
"mean_token_accuracy": 0.14933027178049088,
|
|
"num_tokens": 8220246.0,
|
|
"step": 3965
|
|
},
|
|
{
|
|
"entropy": 5.765957307815552,
|
|
"epoch": 0.3601233671988389,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004991801679738502,
|
|
"loss": 5.8098,
|
|
"mean_token_accuracy": 0.14969587549567223,
|
|
"num_tokens": 8230368.0,
|
|
"step": 3970
|
|
},
|
|
{
|
|
"entropy": 5.888836622238159,
|
|
"epoch": 0.3605769230769231,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004991774060270008,
|
|
"loss": 5.7849,
|
|
"mean_token_accuracy": 0.14979653880000116,
|
|
"num_tokens": 8241658.0,
|
|
"step": 3975
|
|
},
|
|
{
|
|
"entropy": 5.876078271865845,
|
|
"epoch": 0.3610304789550073,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004991746394441055,
|
|
"loss": 5.7625,
|
|
"mean_token_accuracy": 0.15129579454660416,
|
|
"num_tokens": 8252675.0,
|
|
"step": 3980
|
|
},
|
|
{
|
|
"entropy": 5.8728478908538815,
|
|
"epoch": 0.36148403483309144,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004991718682252216,
|
|
"loss": 5.8308,
|
|
"mean_token_accuracy": 0.14199524223804474,
|
|
"num_tokens": 8264492.0,
|
|
"step": 3985
|
|
},
|
|
{
|
|
"entropy": 5.861414003372192,
|
|
"epoch": 0.3619375907111756,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004991690923704063,
|
|
"loss": 5.8043,
|
|
"mean_token_accuracy": 0.1468754529953003,
|
|
"num_tokens": 8275806.0,
|
|
"step": 3990
|
|
},
|
|
{
|
|
"entropy": 5.7705151557922365,
|
|
"epoch": 0.3623911465892598,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004991663118797171,
|
|
"loss": 5.8434,
|
|
"mean_token_accuracy": 0.14178252667188646,
|
|
"num_tokens": 8286478.0,
|
|
"step": 3995
|
|
},
|
|
{
|
|
"entropy": 5.897064113616944,
|
|
"epoch": 0.36284470246734396,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004991635267532113,
|
|
"loss": 5.736,
|
|
"mean_token_accuracy": 0.1468100905418396,
|
|
"num_tokens": 8296612.0,
|
|
"step": 4000
|
|
},
|
|
{
|
|
"entropy": 5.827452564239502,
|
|
"epoch": 0.36329825834542817,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004991607369909468,
|
|
"loss": 5.6949,
|
|
"mean_token_accuracy": 0.15380942299962044,
|
|
"num_tokens": 8306990.0,
|
|
"step": 4005
|
|
},
|
|
{
|
|
"entropy": 5.833603858947754,
|
|
"epoch": 0.3637518142235123,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004991579425929811,
|
|
"loss": 5.8261,
|
|
"mean_token_accuracy": 0.14629884138703347,
|
|
"num_tokens": 8316445.0,
|
|
"step": 4010
|
|
},
|
|
{
|
|
"entropy": 5.928536128997803,
|
|
"epoch": 0.36420537010159654,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.000499155143559372,
|
|
"loss": 5.7363,
|
|
"mean_token_accuracy": 0.15292509347200395,
|
|
"num_tokens": 8327801.0,
|
|
"step": 4015
|
|
},
|
|
{
|
|
"entropy": 5.861473417282104,
|
|
"epoch": 0.3646589259796807,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004991523398901773,
|
|
"loss": 5.758,
|
|
"mean_token_accuracy": 0.1410280466079712,
|
|
"num_tokens": 8338714.0,
|
|
"step": 4020
|
|
},
|
|
{
|
|
"entropy": 5.821960020065307,
|
|
"epoch": 0.3651124818577649,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004991495315854553,
|
|
"loss": 5.8238,
|
|
"mean_token_accuracy": 0.1508706659078598,
|
|
"num_tokens": 8348873.0,
|
|
"step": 4025
|
|
},
|
|
{
|
|
"entropy": 5.8338765621185305,
|
|
"epoch": 0.36556603773584906,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004991467186452637,
|
|
"loss": 5.736,
|
|
"mean_token_accuracy": 0.14726780652999877,
|
|
"num_tokens": 8359913.0,
|
|
"step": 4030
|
|
},
|
|
{
|
|
"entropy": 5.9051182746887205,
|
|
"epoch": 0.3660195936139332,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004991439010696609,
|
|
"loss": 5.8848,
|
|
"mean_token_accuracy": 0.1464948311448097,
|
|
"num_tokens": 8370697.0,
|
|
"step": 4035
|
|
},
|
|
{
|
|
"entropy": 5.810081911087036,
|
|
"epoch": 0.3664731494920174,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004991410788587051,
|
|
"loss": 5.7361,
|
|
"mean_token_accuracy": 0.1557631567120552,
|
|
"num_tokens": 8380263.0,
|
|
"step": 4040
|
|
},
|
|
{
|
|
"entropy": 5.743243885040283,
|
|
"epoch": 0.3669267053701016,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004991382520124547,
|
|
"loss": 5.6837,
|
|
"mean_token_accuracy": 0.1497320204973221,
|
|
"num_tokens": 8390525.0,
|
|
"step": 4045
|
|
},
|
|
{
|
|
"entropy": 5.841325187683106,
|
|
"epoch": 0.3673802612481858,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004991354205309681,
|
|
"loss": 5.8711,
|
|
"mean_token_accuracy": 0.14423007443547248,
|
|
"num_tokens": 8401003.0,
|
|
"step": 4050
|
|
},
|
|
{
|
|
"entropy": 5.945683765411377,
|
|
"epoch": 0.36783381712626995,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.000499132584414304,
|
|
"loss": 5.7648,
|
|
"mean_token_accuracy": 0.1532066524028778,
|
|
"num_tokens": 8411688.0,
|
|
"step": 4055
|
|
},
|
|
{
|
|
"entropy": 5.793200826644897,
|
|
"epoch": 0.36828737300435416,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004991297436625207,
|
|
"loss": 5.7271,
|
|
"mean_token_accuracy": 0.14746315777301788,
|
|
"num_tokens": 8422291.0,
|
|
"step": 4060
|
|
},
|
|
{
|
|
"entropy": 5.770292615890503,
|
|
"epoch": 0.3687409288824383,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004991268982756774,
|
|
"loss": 5.7497,
|
|
"mean_token_accuracy": 0.1400376409292221,
|
|
"num_tokens": 8433275.0,
|
|
"step": 4065
|
|
},
|
|
{
|
|
"entropy": 5.821974849700927,
|
|
"epoch": 0.3691944847605225,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004991240482538327,
|
|
"loss": 5.7172,
|
|
"mean_token_accuracy": 0.15129573345184327,
|
|
"num_tokens": 8443877.0,
|
|
"step": 4070
|
|
},
|
|
{
|
|
"entropy": 5.753021097183227,
|
|
"epoch": 0.3696480406386067,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004991211935970455,
|
|
"loss": 5.5993,
|
|
"mean_token_accuracy": 0.15860457271337508,
|
|
"num_tokens": 8453384.0,
|
|
"step": 4075
|
|
},
|
|
{
|
|
"entropy": 5.8465124607086185,
|
|
"epoch": 0.37010159651669083,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004991183343053748,
|
|
"loss": 5.8092,
|
|
"mean_token_accuracy": 0.14608121365308763,
|
|
"num_tokens": 8464357.0,
|
|
"step": 4080
|
|
},
|
|
{
|
|
"entropy": 5.834251165390015,
|
|
"epoch": 0.37055515239477504,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.00049911547037888,
|
|
"loss": 5.754,
|
|
"mean_token_accuracy": 0.14439125806093217,
|
|
"num_tokens": 8474544.0,
|
|
"step": 4085
|
|
},
|
|
{
|
|
"entropy": 5.841232872009277,
|
|
"epoch": 0.3710087082728592,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004991126018176202,
|
|
"loss": 5.7139,
|
|
"mean_token_accuracy": 0.14939453601837158,
|
|
"num_tokens": 8485383.0,
|
|
"step": 4090
|
|
},
|
|
{
|
|
"entropy": 5.789280891418457,
|
|
"epoch": 0.3714622641509434,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004991097286216545,
|
|
"loss": 5.7472,
|
|
"mean_token_accuracy": 0.15124303996562957,
|
|
"num_tokens": 8497186.0,
|
|
"step": 4095
|
|
},
|
|
{
|
|
"entropy": 5.71776647567749,
|
|
"epoch": 0.37191582002902757,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004991068507910427,
|
|
"loss": 5.6491,
|
|
"mean_token_accuracy": 0.15781550407409667,
|
|
"num_tokens": 8507583.0,
|
|
"step": 4100
|
|
},
|
|
{
|
|
"entropy": 5.858701610565186,
|
|
"epoch": 0.3723693759071118,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.000499103968325844,
|
|
"loss": 5.7401,
|
|
"mean_token_accuracy": 0.15454131364822388,
|
|
"num_tokens": 8518301.0,
|
|
"step": 4105
|
|
},
|
|
{
|
|
"entropy": 5.730893135070801,
|
|
"epoch": 0.37282293178519593,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004991010812261181,
|
|
"loss": 5.5903,
|
|
"mean_token_accuracy": 0.16097321063280107,
|
|
"num_tokens": 8527177.0,
|
|
"step": 4110
|
|
},
|
|
{
|
|
"entropy": 5.769358444213867,
|
|
"epoch": 0.37327648766328014,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004990981894919248,
|
|
"loss": 5.693,
|
|
"mean_token_accuracy": 0.15519624277949334,
|
|
"num_tokens": 8538207.0,
|
|
"step": 4115
|
|
},
|
|
{
|
|
"entropy": 5.869311189651489,
|
|
"epoch": 0.3737300435413643,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004990952931233238,
|
|
"loss": 5.7927,
|
|
"mean_token_accuracy": 0.15326275080442428,
|
|
"num_tokens": 8548001.0,
|
|
"step": 4120
|
|
},
|
|
{
|
|
"entropy": 5.816793584823609,
|
|
"epoch": 0.37418359941944845,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.000499092392120375,
|
|
"loss": 5.7203,
|
|
"mean_token_accuracy": 0.14967464953660964,
|
|
"num_tokens": 8557670.0,
|
|
"step": 4125
|
|
},
|
|
{
|
|
"entropy": 5.683045482635498,
|
|
"epoch": 0.37463715529753266,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.0004990894864831385,
|
|
"loss": 5.6447,
|
|
"mean_token_accuracy": 0.14838514626026153,
|
|
"num_tokens": 8568820.0,
|
|
"step": 4130
|
|
},
|
|
{
|
|
"entropy": 5.810424661636352,
|
|
"epoch": 0.3750907111756168,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004990865762116743,
|
|
"loss": 5.72,
|
|
"mean_token_accuracy": 0.1498174101114273,
|
|
"num_tokens": 8579107.0,
|
|
"step": 4135
|
|
},
|
|
{
|
|
"entropy": 5.6872163772583,
|
|
"epoch": 0.37554426705370103,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004990836613060426,
|
|
"loss": 5.6298,
|
|
"mean_token_accuracy": 0.15544298142194748,
|
|
"num_tokens": 8588487.0,
|
|
"step": 4140
|
|
},
|
|
{
|
|
"entropy": 5.8146415710449215,
|
|
"epoch": 0.3759978229317852,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004990807417663036,
|
|
"loss": 5.6826,
|
|
"mean_token_accuracy": 0.15894482880830765,
|
|
"num_tokens": 8598526.0,
|
|
"step": 4145
|
|
},
|
|
{
|
|
"entropy": 5.78179669380188,
|
|
"epoch": 0.3764513788098694,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004990778175925179,
|
|
"loss": 5.7087,
|
|
"mean_token_accuracy": 0.15587593317031861,
|
|
"num_tokens": 8608734.0,
|
|
"step": 4150
|
|
},
|
|
{
|
|
"entropy": 5.733596324920654,
|
|
"epoch": 0.37690493468795355,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004990748887847457,
|
|
"loss": 5.7009,
|
|
"mean_token_accuracy": 0.15680316239595413,
|
|
"num_tokens": 8619351.0,
|
|
"step": 4155
|
|
},
|
|
{
|
|
"entropy": 5.780179786682129,
|
|
"epoch": 0.37735849056603776,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004990719553430477,
|
|
"loss": 5.7569,
|
|
"mean_token_accuracy": 0.14881235957145691,
|
|
"num_tokens": 8630570.0,
|
|
"step": 4160
|
|
},
|
|
{
|
|
"entropy": 5.869149160385132,
|
|
"epoch": 0.3778120464441219,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004990690172674847,
|
|
"loss": 5.7907,
|
|
"mean_token_accuracy": 0.14882688820362092,
|
|
"num_tokens": 8641081.0,
|
|
"step": 4165
|
|
},
|
|
{
|
|
"entropy": 5.818000078201294,
|
|
"epoch": 0.3782656023222061,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004990660745581172,
|
|
"loss": 5.7505,
|
|
"mean_token_accuracy": 0.15332180112600327,
|
|
"num_tokens": 8651792.0,
|
|
"step": 4170
|
|
},
|
|
{
|
|
"entropy": 5.863195323944092,
|
|
"epoch": 0.3787191582002903,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004990631272150062,
|
|
"loss": 5.7807,
|
|
"mean_token_accuracy": 0.15578781217336654,
|
|
"num_tokens": 8662385.0,
|
|
"step": 4175
|
|
},
|
|
{
|
|
"entropy": 5.813625764846802,
|
|
"epoch": 0.37917271407837444,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004990601752382127,
|
|
"loss": 5.7738,
|
|
"mean_token_accuracy": 0.15300806015729904,
|
|
"num_tokens": 8673963.0,
|
|
"step": 4180
|
|
},
|
|
{
|
|
"entropy": 5.777889728546143,
|
|
"epoch": 0.37962626995645865,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004990572186277975,
|
|
"loss": 5.7038,
|
|
"mean_token_accuracy": 0.151040218770504,
|
|
"num_tokens": 8684560.0,
|
|
"step": 4185
|
|
},
|
|
{
|
|
"entropy": 5.844574594497681,
|
|
"epoch": 0.3800798258345428,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004990542573838221,
|
|
"loss": 5.7213,
|
|
"mean_token_accuracy": 0.1503355860710144,
|
|
"num_tokens": 8694777.0,
|
|
"step": 4190
|
|
},
|
|
{
|
|
"entropy": 5.768202114105224,
|
|
"epoch": 0.380533381712627,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004990512915063475,
|
|
"loss": 5.7156,
|
|
"mean_token_accuracy": 0.14577075690031052,
|
|
"num_tokens": 8705284.0,
|
|
"step": 4195
|
|
},
|
|
{
|
|
"entropy": 5.800690317153931,
|
|
"epoch": 0.38098693759071117,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004990483209954352,
|
|
"loss": 5.6345,
|
|
"mean_token_accuracy": 0.1547250419855118,
|
|
"num_tokens": 8715156.0,
|
|
"step": 4200
|
|
},
|
|
{
|
|
"entropy": 5.959943342208862,
|
|
"epoch": 0.3814404934687954,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.0004990453458511464,
|
|
"loss": 5.8672,
|
|
"mean_token_accuracy": 0.1470291867852211,
|
|
"num_tokens": 8726110.0,
|
|
"step": 4205
|
|
},
|
|
{
|
|
"entropy": 5.8400044441223145,
|
|
"epoch": 0.38189404934687954,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004990423660735428,
|
|
"loss": 5.7056,
|
|
"mean_token_accuracy": 0.15206836611032487,
|
|
"num_tokens": 8736331.0,
|
|
"step": 4210
|
|
},
|
|
{
|
|
"entropy": 5.780660247802734,
|
|
"epoch": 0.3823476052249637,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.000499039381662686,
|
|
"loss": 5.7628,
|
|
"mean_token_accuracy": 0.15221548229455947,
|
|
"num_tokens": 8747126.0,
|
|
"step": 4215
|
|
},
|
|
{
|
|
"entropy": 5.794266891479492,
|
|
"epoch": 0.3828011611030479,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004990363926186377,
|
|
"loss": 5.6882,
|
|
"mean_token_accuracy": 0.15492002815008163,
|
|
"num_tokens": 8757948.0,
|
|
"step": 4220
|
|
},
|
|
{
|
|
"entropy": 5.801687479019165,
|
|
"epoch": 0.38325471698113206,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004990333989414597,
|
|
"loss": 5.6807,
|
|
"mean_token_accuracy": 0.15561317056417465,
|
|
"num_tokens": 8767157.0,
|
|
"step": 4225
|
|
},
|
|
{
|
|
"entropy": 5.817021226882934,
|
|
"epoch": 0.38370827285921627,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004990304006312138,
|
|
"loss": 5.7414,
|
|
"mean_token_accuracy": 0.15308658108115197,
|
|
"num_tokens": 8777456.0,
|
|
"step": 4230
|
|
},
|
|
{
|
|
"entropy": 5.834913682937622,
|
|
"epoch": 0.3841618287373004,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004990273976879622,
|
|
"loss": 5.7314,
|
|
"mean_token_accuracy": 0.14769532680511474,
|
|
"num_tokens": 8788147.0,
|
|
"step": 4235
|
|
},
|
|
{
|
|
"entropy": 5.782855558395386,
|
|
"epoch": 0.38461538461538464,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004990243901117669,
|
|
"loss": 5.7446,
|
|
"mean_token_accuracy": 0.15237949043512344,
|
|
"num_tokens": 8798597.0,
|
|
"step": 4240
|
|
},
|
|
{
|
|
"entropy": 5.880156373977661,
|
|
"epoch": 0.3850689404934688,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004990213779026903,
|
|
"loss": 5.8421,
|
|
"mean_token_accuracy": 0.14258336871862412,
|
|
"num_tokens": 8808644.0,
|
|
"step": 4245
|
|
},
|
|
{
|
|
"entropy": 5.890059137344361,
|
|
"epoch": 0.385522496371553,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004990183610607944,
|
|
"loss": 5.82,
|
|
"mean_token_accuracy": 0.14745595827698707,
|
|
"num_tokens": 8819096.0,
|
|
"step": 4250
|
|
},
|
|
{
|
|
"entropy": 5.921150493621826,
|
|
"epoch": 0.38597605224963716,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004990153395861415,
|
|
"loss": 5.788,
|
|
"mean_token_accuracy": 0.15066457390785218,
|
|
"num_tokens": 8829395.0,
|
|
"step": 4255
|
|
},
|
|
{
|
|
"entropy": 5.76968822479248,
|
|
"epoch": 0.3864296081277213,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.0004990123134787946,
|
|
"loss": 5.6839,
|
|
"mean_token_accuracy": 0.15857364386320114,
|
|
"num_tokens": 8839841.0,
|
|
"step": 4260
|
|
},
|
|
{
|
|
"entropy": 5.795496988296509,
|
|
"epoch": 0.3868831640058055,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004990092827388159,
|
|
"loss": 5.7741,
|
|
"mean_token_accuracy": 0.14829214215278624,
|
|
"num_tokens": 8850675.0,
|
|
"step": 4265
|
|
},
|
|
{
|
|
"entropy": 5.810708332061767,
|
|
"epoch": 0.3873367198838897,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.0004990062473662681,
|
|
"loss": 5.6822,
|
|
"mean_token_accuracy": 0.15104758739471436,
|
|
"num_tokens": 8862065.0,
|
|
"step": 4270
|
|
},
|
|
{
|
|
"entropy": 5.85414080619812,
|
|
"epoch": 0.3877902757619739,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.000499003207361214,
|
|
"loss": 5.7873,
|
|
"mean_token_accuracy": 0.14664969742298126,
|
|
"num_tokens": 8872039.0,
|
|
"step": 4275
|
|
},
|
|
{
|
|
"entropy": 5.804039144515992,
|
|
"epoch": 0.38824383164005805,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004990001627237165,
|
|
"loss": 5.74,
|
|
"mean_token_accuracy": 0.14450578540563583,
|
|
"num_tokens": 8882637.0,
|
|
"step": 4280
|
|
},
|
|
{
|
|
"entropy": 5.853966474533081,
|
|
"epoch": 0.38869738751814226,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004989971134538386,
|
|
"loss": 5.7544,
|
|
"mean_token_accuracy": 0.15939705222845077,
|
|
"num_tokens": 8892659.0,
|
|
"step": 4285
|
|
},
|
|
{
|
|
"entropy": 5.836553001403809,
|
|
"epoch": 0.3891509433962264,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004989940595516432,
|
|
"loss": 5.7398,
|
|
"mean_token_accuracy": 0.1540324307978153,
|
|
"num_tokens": 8902938.0,
|
|
"step": 4290
|
|
},
|
|
{
|
|
"entropy": 5.771514558792115,
|
|
"epoch": 0.3896044992743106,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004989910010171938,
|
|
"loss": 5.7289,
|
|
"mean_token_accuracy": 0.15150050669908524,
|
|
"num_tokens": 8914084.0,
|
|
"step": 4295
|
|
},
|
|
{
|
|
"entropy": 5.721285963058472,
|
|
"epoch": 0.3900580551523948,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004989879378505532,
|
|
"loss": 5.8024,
|
|
"mean_token_accuracy": 0.1427184097468853,
|
|
"num_tokens": 8925289.0,
|
|
"step": 4300
|
|
},
|
|
{
|
|
"entropy": 5.827619647979736,
|
|
"epoch": 0.39051161103047893,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004989848700517849,
|
|
"loss": 5.7478,
|
|
"mean_token_accuracy": 0.1433940462768078,
|
|
"num_tokens": 8935193.0,
|
|
"step": 4305
|
|
},
|
|
{
|
|
"entropy": 5.90316915512085,
|
|
"epoch": 0.39096516690856314,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004989817976209526,
|
|
"loss": 5.7425,
|
|
"mean_token_accuracy": 0.15149454772472382,
|
|
"num_tokens": 8944882.0,
|
|
"step": 4310
|
|
},
|
|
{
|
|
"entropy": 5.884109878540039,
|
|
"epoch": 0.3914187227866473,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004989787205581196,
|
|
"loss": 5.8644,
|
|
"mean_token_accuracy": 0.14161792322993277,
|
|
"num_tokens": 8956226.0,
|
|
"step": 4315
|
|
},
|
|
{
|
|
"entropy": 5.756166315078735,
|
|
"epoch": 0.3918722786647315,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004989756388633496,
|
|
"loss": 5.722,
|
|
"mean_token_accuracy": 0.15241281241178511,
|
|
"num_tokens": 8966933.0,
|
|
"step": 4320
|
|
},
|
|
{
|
|
"entropy": 5.809850406646729,
|
|
"epoch": 0.39232583454281567,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004989725525367063,
|
|
"loss": 5.7099,
|
|
"mean_token_accuracy": 0.14727903604507447,
|
|
"num_tokens": 8977352.0,
|
|
"step": 4325
|
|
},
|
|
{
|
|
"entropy": 5.821715021133423,
|
|
"epoch": 0.3927793904208999,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004989694615782534,
|
|
"loss": 5.7175,
|
|
"mean_token_accuracy": 0.14821901619434358,
|
|
"num_tokens": 8987091.0,
|
|
"step": 4330
|
|
},
|
|
{
|
|
"entropy": 5.801403760910034,
|
|
"epoch": 0.39323294629898403,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004989663659880552,
|
|
"loss": 5.7594,
|
|
"mean_token_accuracy": 0.15159819200634955,
|
|
"num_tokens": 8996618.0,
|
|
"step": 4335
|
|
},
|
|
{
|
|
"entropy": 5.806633806228637,
|
|
"epoch": 0.3936865021770682,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004989632657661754,
|
|
"loss": 5.7832,
|
|
"mean_token_accuracy": 0.142975378036499,
|
|
"num_tokens": 9007618.0,
|
|
"step": 4340
|
|
},
|
|
{
|
|
"entropy": 5.863812828063965,
|
|
"epoch": 0.3941400580551524,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.000498960160912678,
|
|
"loss": 5.738,
|
|
"mean_token_accuracy": 0.14942926466464995,
|
|
"num_tokens": 9018472.0,
|
|
"step": 4345
|
|
},
|
|
{
|
|
"entropy": 5.881016540527344,
|
|
"epoch": 0.39459361393323655,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004989570514276276,
|
|
"loss": 5.7841,
|
|
"mean_token_accuracy": 0.15038543343544006,
|
|
"num_tokens": 9030211.0,
|
|
"step": 4350
|
|
},
|
|
{
|
|
"entropy": 5.824518918991089,
|
|
"epoch": 0.39504716981132076,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004989539373110883,
|
|
"loss": 5.7763,
|
|
"mean_token_accuracy": 0.1506713002920151,
|
|
"num_tokens": 9039582.0,
|
|
"step": 4355
|
|
},
|
|
{
|
|
"entropy": 5.853713321685791,
|
|
"epoch": 0.3955007256894049,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004989508185631245,
|
|
"loss": 5.7896,
|
|
"mean_token_accuracy": 0.15014094859361649,
|
|
"num_tokens": 9050645.0,
|
|
"step": 4360
|
|
},
|
|
{
|
|
"entropy": 5.878240489959717,
|
|
"epoch": 0.39595428156748913,
|
|
"grad_norm": 2.828125,
|
|
"learning_rate": 0.0004989476951838006,
|
|
"loss": 5.8626,
|
|
"mean_token_accuracy": 0.1465392716228962,
|
|
"num_tokens": 9061204.0,
|
|
"step": 4365
|
|
},
|
|
{
|
|
"entropy": 5.797079563140869,
|
|
"epoch": 0.3964078374455733,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004989445671731814,
|
|
"loss": 5.6994,
|
|
"mean_token_accuracy": 0.14646837934851648,
|
|
"num_tokens": 9072646.0,
|
|
"step": 4370
|
|
},
|
|
{
|
|
"entropy": 5.806577920913696,
|
|
"epoch": 0.3968613933236575,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004989414345313315,
|
|
"loss": 5.6603,
|
|
"mean_token_accuracy": 0.1560521364212036,
|
|
"num_tokens": 9082693.0,
|
|
"step": 4375
|
|
},
|
|
{
|
|
"entropy": 5.785579872131348,
|
|
"epoch": 0.39731494920174165,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004989382972583156,
|
|
"loss": 5.7644,
|
|
"mean_token_accuracy": 0.14637374579906465,
|
|
"num_tokens": 9093776.0,
|
|
"step": 4380
|
|
},
|
|
{
|
|
"entropy": 5.823543930053711,
|
|
"epoch": 0.3977685050798258,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004989351553541986,
|
|
"loss": 5.7203,
|
|
"mean_token_accuracy": 0.14628972858190536,
|
|
"num_tokens": 9103744.0,
|
|
"step": 4385
|
|
},
|
|
{
|
|
"entropy": 5.87626805305481,
|
|
"epoch": 0.39822206095791,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004989320088190456,
|
|
"loss": 5.7449,
|
|
"mean_token_accuracy": 0.14754146486520767,
|
|
"num_tokens": 9113588.0,
|
|
"step": 4390
|
|
},
|
|
{
|
|
"entropy": 5.819130325317383,
|
|
"epoch": 0.3986756168359942,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004989288576529216,
|
|
"loss": 5.7556,
|
|
"mean_token_accuracy": 0.14487292245030403,
|
|
"num_tokens": 9123061.0,
|
|
"step": 4395
|
|
},
|
|
{
|
|
"entropy": 5.816460275650025,
|
|
"epoch": 0.3991291727140784,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004989257018558917,
|
|
"loss": 5.8459,
|
|
"mean_token_accuracy": 0.1455293267965317,
|
|
"num_tokens": 9132810.0,
|
|
"step": 4400
|
|
},
|
|
{
|
|
"entropy": 5.832490015029907,
|
|
"epoch": 0.39958272859216254,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004989225414280213,
|
|
"loss": 5.7779,
|
|
"mean_token_accuracy": 0.15219624638557433,
|
|
"num_tokens": 9142539.0,
|
|
"step": 4405
|
|
},
|
|
{
|
|
"entropy": 5.840099477767945,
|
|
"epoch": 0.40003628447024675,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004989193763693756,
|
|
"loss": 5.8218,
|
|
"mean_token_accuracy": 0.14683979749679565,
|
|
"num_tokens": 9153646.0,
|
|
"step": 4410
|
|
},
|
|
{
|
|
"entropy": 5.794438648223877,
|
|
"epoch": 0.4004898403483309,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004989162066800202,
|
|
"loss": 5.6833,
|
|
"mean_token_accuracy": 0.15239149183034897,
|
|
"num_tokens": 9164006.0,
|
|
"step": 4415
|
|
},
|
|
{
|
|
"entropy": 5.7646324157714846,
|
|
"epoch": 0.4009433962264151,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004989130323600205,
|
|
"loss": 5.6939,
|
|
"mean_token_accuracy": 0.15271419584751128,
|
|
"num_tokens": 9173398.0,
|
|
"step": 4420
|
|
},
|
|
{
|
|
"entropy": 5.802749443054199,
|
|
"epoch": 0.40139695210449927,
|
|
"grad_norm": 2.546875,
|
|
"learning_rate": 0.0004989098534094424,
|
|
"loss": 5.7421,
|
|
"mean_token_accuracy": 0.14769546911120415,
|
|
"num_tokens": 9184669.0,
|
|
"step": 4425
|
|
},
|
|
{
|
|
"entropy": 5.854629230499268,
|
|
"epoch": 0.4018505079825834,
|
|
"grad_norm": 2.625,
|
|
"learning_rate": 0.0004989066698283512,
|
|
"loss": 5.7477,
|
|
"mean_token_accuracy": 0.15191508308053017,
|
|
"num_tokens": 9194990.0,
|
|
"step": 4430
|
|
},
|
|
{
|
|
"entropy": 5.821303033828736,
|
|
"epoch": 0.40230406386066764,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004989034816168132,
|
|
"loss": 5.7576,
|
|
"mean_token_accuracy": 0.1518094629049301,
|
|
"num_tokens": 9205548.0,
|
|
"step": 4435
|
|
},
|
|
{
|
|
"entropy": 5.876933431625366,
|
|
"epoch": 0.4027576197387518,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004989002887748941,
|
|
"loss": 5.8676,
|
|
"mean_token_accuracy": 0.14785950928926467,
|
|
"num_tokens": 9217189.0,
|
|
"step": 4440
|
|
},
|
|
{
|
|
"entropy": 5.897108030319214,
|
|
"epoch": 0.403211175616836,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004988970913026601,
|
|
"loss": 5.6841,
|
|
"mean_token_accuracy": 0.15338665544986724,
|
|
"num_tokens": 9226774.0,
|
|
"step": 4445
|
|
},
|
|
{
|
|
"entropy": 5.785064220428467,
|
|
"epoch": 0.40366473149492016,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004988938892001771,
|
|
"loss": 5.6011,
|
|
"mean_token_accuracy": 0.15826690644025804,
|
|
"num_tokens": 9236058.0,
|
|
"step": 4450
|
|
},
|
|
{
|
|
"entropy": 5.826375579833984,
|
|
"epoch": 0.40411828737300437,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004988906824675113,
|
|
"loss": 5.7579,
|
|
"mean_token_accuracy": 0.15533598959445954,
|
|
"num_tokens": 9247204.0,
|
|
"step": 4455
|
|
},
|
|
{
|
|
"entropy": 5.755468320846558,
|
|
"epoch": 0.4045718432510885,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004988874711047293,
|
|
"loss": 5.6998,
|
|
"mean_token_accuracy": 0.15389265343546868,
|
|
"num_tokens": 9257658.0,
|
|
"step": 4460
|
|
},
|
|
{
|
|
"entropy": 5.851498746871949,
|
|
"epoch": 0.40502539912917274,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004988842551118972,
|
|
"loss": 5.6804,
|
|
"mean_token_accuracy": 0.16036645770072938,
|
|
"num_tokens": 9267078.0,
|
|
"step": 4465
|
|
},
|
|
{
|
|
"entropy": 5.778662586212159,
|
|
"epoch": 0.4054789550072569,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004988810344890818,
|
|
"loss": 5.7089,
|
|
"mean_token_accuracy": 0.15287381559610366,
|
|
"num_tokens": 9277653.0,
|
|
"step": 4470
|
|
},
|
|
{
|
|
"entropy": 5.814766693115234,
|
|
"epoch": 0.40593251088534105,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004988778092363494,
|
|
"loss": 5.7226,
|
|
"mean_token_accuracy": 0.14548192843794822,
|
|
"num_tokens": 9287854.0,
|
|
"step": 4475
|
|
},
|
|
{
|
|
"entropy": 5.7822350025177,
|
|
"epoch": 0.40638606676342526,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004988745793537671,
|
|
"loss": 5.6167,
|
|
"mean_token_accuracy": 0.15381321907043458,
|
|
"num_tokens": 9298389.0,
|
|
"step": 4480
|
|
},
|
|
{
|
|
"entropy": 5.788981294631958,
|
|
"epoch": 0.4068396226415094,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004988713448414011,
|
|
"loss": 5.6521,
|
|
"mean_token_accuracy": 0.1534888431429863,
|
|
"num_tokens": 9308350.0,
|
|
"step": 4485
|
|
},
|
|
{
|
|
"entropy": 5.803249788284302,
|
|
"epoch": 0.4072931785195936,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.000498868105699319,
|
|
"loss": 5.7757,
|
|
"mean_token_accuracy": 0.14718539863824845,
|
|
"num_tokens": 9319386.0,
|
|
"step": 4490
|
|
},
|
|
{
|
|
"entropy": 5.938737583160401,
|
|
"epoch": 0.4077467343976778,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004988648619275872,
|
|
"loss": 5.8108,
|
|
"mean_token_accuracy": 0.14430881813168525,
|
|
"num_tokens": 9331151.0,
|
|
"step": 4495
|
|
},
|
|
{
|
|
"entropy": 5.78353066444397,
|
|
"epoch": 0.408200290275762,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004988616135262729,
|
|
"loss": 5.784,
|
|
"mean_token_accuracy": 0.1513584613800049,
|
|
"num_tokens": 9341472.0,
|
|
"step": 4500
|
|
},
|
|
{
|
|
"entropy": 5.890974712371826,
|
|
"epoch": 0.40865384615384615,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004988583604954436,
|
|
"loss": 5.7534,
|
|
"mean_token_accuracy": 0.1468189090490341,
|
|
"num_tokens": 9351641.0,
|
|
"step": 4505
|
|
},
|
|
{
|
|
"entropy": 5.831851387023926,
|
|
"epoch": 0.40910740203193036,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004988551028351663,
|
|
"loss": 5.7248,
|
|
"mean_token_accuracy": 0.1530272752046585,
|
|
"num_tokens": 9362220.0,
|
|
"step": 4510
|
|
},
|
|
{
|
|
"entropy": 5.753470230102539,
|
|
"epoch": 0.4095609579100145,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.0004988518405455084,
|
|
"loss": 5.6809,
|
|
"mean_token_accuracy": 0.15855793803930282,
|
|
"num_tokens": 9372667.0,
|
|
"step": 4515
|
|
},
|
|
{
|
|
"entropy": 5.71013650894165,
|
|
"epoch": 0.41001451378809867,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004988485736265374,
|
|
"loss": 5.6626,
|
|
"mean_token_accuracy": 0.15513231456279755,
|
|
"num_tokens": 9383133.0,
|
|
"step": 4520
|
|
},
|
|
{
|
|
"entropy": 5.893728303909302,
|
|
"epoch": 0.4104680696661829,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.000498845302078321,
|
|
"loss": 5.7767,
|
|
"mean_token_accuracy": 0.1552646741271019,
|
|
"num_tokens": 9394484.0,
|
|
"step": 4525
|
|
},
|
|
{
|
|
"entropy": 5.881732940673828,
|
|
"epoch": 0.41092162554426703,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004988420259009266,
|
|
"loss": 5.7546,
|
|
"mean_token_accuracy": 0.1457567699253559,
|
|
"num_tokens": 9404360.0,
|
|
"step": 4530
|
|
},
|
|
{
|
|
"entropy": 5.79802098274231,
|
|
"epoch": 0.41137518142235124,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 0.000498838745094422,
|
|
"loss": 5.7456,
|
|
"mean_token_accuracy": 0.15776007771492004,
|
|
"num_tokens": 9414638.0,
|
|
"step": 4535
|
|
},
|
|
{
|
|
"entropy": 5.890639591217041,
|
|
"epoch": 0.4118287373004354,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.0004988354596588751,
|
|
"loss": 5.7998,
|
|
"mean_token_accuracy": 0.14425266459584235,
|
|
"num_tokens": 9424602.0,
|
|
"step": 4540
|
|
},
|
|
{
|
|
"entropy": 5.780306434631347,
|
|
"epoch": 0.4122822931785196,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.0004988321695943539,
|
|
"loss": 5.6926,
|
|
"mean_token_accuracy": 0.1462174102663994,
|
|
"num_tokens": 9434724.0,
|
|
"step": 4545
|
|
},
|
|
{
|
|
"entropy": 5.876906967163086,
|
|
"epoch": 0.41273584905660377,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004988288749009264,
|
|
"loss": 5.8353,
|
|
"mean_token_accuracy": 0.14362881630659102,
|
|
"num_tokens": 9444604.0,
|
|
"step": 4550
|
|
},
|
|
{
|
|
"entropy": 5.931415939331055,
|
|
"epoch": 0.413189404934688,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004988255755786608,
|
|
"loss": 5.6943,
|
|
"mean_token_accuracy": 0.1535832941532135,
|
|
"num_tokens": 9455447.0,
|
|
"step": 4555
|
|
},
|
|
{
|
|
"entropy": 5.800370836257935,
|
|
"epoch": 0.41364296081277213,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004988222716276251,
|
|
"loss": 5.6941,
|
|
"mean_token_accuracy": 0.14634924903512,
|
|
"num_tokens": 9466030.0,
|
|
"step": 4560
|
|
},
|
|
{
|
|
"entropy": 5.8000507831573485,
|
|
"epoch": 0.4140965166908563,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.000498818963047888,
|
|
"loss": 5.784,
|
|
"mean_token_accuracy": 0.14505551978945733,
|
|
"num_tokens": 9476352.0,
|
|
"step": 4565
|
|
},
|
|
{
|
|
"entropy": 5.809683704376221,
|
|
"epoch": 0.4145500725689405,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.0004988156498395176,
|
|
"loss": 5.6833,
|
|
"mean_token_accuracy": 0.15042722076177598,
|
|
"num_tokens": 9486782.0,
|
|
"step": 4570
|
|
},
|
|
{
|
|
"entropy": 5.720265960693359,
|
|
"epoch": 0.41500362844702465,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004988123320025825,
|
|
"loss": 5.7464,
|
|
"mean_token_accuracy": 0.14237145334482193,
|
|
"num_tokens": 9496381.0,
|
|
"step": 4575
|
|
},
|
|
{
|
|
"entropy": 5.881400394439697,
|
|
"epoch": 0.41545718432510886,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004988090095371514,
|
|
"loss": 5.7141,
|
|
"mean_token_accuracy": 0.1511618971824646,
|
|
"num_tokens": 9506848.0,
|
|
"step": 4580
|
|
},
|
|
{
|
|
"entropy": 5.860961961746216,
|
|
"epoch": 0.415910740203193,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004988056824432928,
|
|
"loss": 5.7217,
|
|
"mean_token_accuracy": 0.15837913155555725,
|
|
"num_tokens": 9517454.0,
|
|
"step": 4585
|
|
},
|
|
{
|
|
"entropy": 5.8560021877288815,
|
|
"epoch": 0.41636429608127723,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004988023507210758,
|
|
"loss": 5.7768,
|
|
"mean_token_accuracy": 0.14282424747943878,
|
|
"num_tokens": 9528124.0,
|
|
"step": 4590
|
|
},
|
|
{
|
|
"entropy": 5.789300346374512,
|
|
"epoch": 0.4168178519593614,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.0004987990143705692,
|
|
"loss": 5.657,
|
|
"mean_token_accuracy": 0.15939900577068328,
|
|
"num_tokens": 9537754.0,
|
|
"step": 4595
|
|
},
|
|
{
|
|
"entropy": 5.859958600997925,
|
|
"epoch": 0.4172714078374456,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004987956733918418,
|
|
"loss": 5.7809,
|
|
"mean_token_accuracy": 0.15173441544175148,
|
|
"num_tokens": 9547239.0,
|
|
"step": 4600
|
|
},
|
|
{
|
|
"entropy": 5.76247010231018,
|
|
"epoch": 0.41772496371552975,
|
|
"grad_norm": 2.859375,
|
|
"learning_rate": 0.0004987923277849629,
|
|
"loss": 5.749,
|
|
"mean_token_accuracy": 0.1517804205417633,
|
|
"num_tokens": 9557854.0,
|
|
"step": 4605
|
|
},
|
|
{
|
|
"entropy": 5.802983283996582,
|
|
"epoch": 0.4181785195936139,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004987889775500017,
|
|
"loss": 5.7077,
|
|
"mean_token_accuracy": 0.15349361896514893,
|
|
"num_tokens": 9567524.0,
|
|
"step": 4610
|
|
},
|
|
{
|
|
"entropy": 5.7994297504425045,
|
|
"epoch": 0.4186320754716981,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004987856226870272,
|
|
"loss": 5.6602,
|
|
"mean_token_accuracy": 0.15707680732011794,
|
|
"num_tokens": 9578478.0,
|
|
"step": 4615
|
|
},
|
|
{
|
|
"entropy": 5.7925835132598875,
|
|
"epoch": 0.4190856313497823,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004987822631961092,
|
|
"loss": 5.7887,
|
|
"mean_token_accuracy": 0.14697084799408913,
|
|
"num_tokens": 9588552.0,
|
|
"step": 4620
|
|
},
|
|
{
|
|
"entropy": 5.900826263427734,
|
|
"epoch": 0.4195391872278665,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.000498778899077317,
|
|
"loss": 5.724,
|
|
"mean_token_accuracy": 0.14913754314184188,
|
|
"num_tokens": 9598722.0,
|
|
"step": 4625
|
|
},
|
|
{
|
|
"entropy": 5.903703784942627,
|
|
"epoch": 0.41999274310595064,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.00049877553033072,
|
|
"loss": 5.8056,
|
|
"mean_token_accuracy": 0.14776846021413803,
|
|
"num_tokens": 9608430.0,
|
|
"step": 4630
|
|
},
|
|
{
|
|
"entropy": 5.866693353652954,
|
|
"epoch": 0.42044629898403485,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004987721569563882,
|
|
"loss": 5.758,
|
|
"mean_token_accuracy": 0.15444098860025407,
|
|
"num_tokens": 9618299.0,
|
|
"step": 4635
|
|
},
|
|
{
|
|
"entropy": 5.758925914764404,
|
|
"epoch": 0.420899854862119,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.000498768778954391,
|
|
"loss": 5.6869,
|
|
"mean_token_accuracy": 0.1507744535803795,
|
|
"num_tokens": 9627271.0,
|
|
"step": 4640
|
|
},
|
|
{
|
|
"entropy": 5.765277528762818,
|
|
"epoch": 0.4213534107402032,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004987653963247985,
|
|
"loss": 5.6903,
|
|
"mean_token_accuracy": 0.15712204724550247,
|
|
"num_tokens": 9637670.0,
|
|
"step": 4645
|
|
},
|
|
{
|
|
"entropy": 5.841526508331299,
|
|
"epoch": 0.42180696661828737,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004987620090676805,
|
|
"loss": 5.7219,
|
|
"mean_token_accuracy": 0.15380015224218369,
|
|
"num_tokens": 9647740.0,
|
|
"step": 4650
|
|
},
|
|
{
|
|
"entropy": 5.8366029262542725,
|
|
"epoch": 0.4222605224963715,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004987586171831072,
|
|
"loss": 5.7637,
|
|
"mean_token_accuracy": 0.1503145769238472,
|
|
"num_tokens": 9657917.0,
|
|
"step": 4655
|
|
},
|
|
{
|
|
"entropy": 5.762486696243286,
|
|
"epoch": 0.42271407837445574,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004987552206711487,
|
|
"loss": 5.6918,
|
|
"mean_token_accuracy": 0.15710619539022447,
|
|
"num_tokens": 9668066.0,
|
|
"step": 4660
|
|
},
|
|
{
|
|
"entropy": 5.8115678310394285,
|
|
"epoch": 0.4231676342525399,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004987518195318752,
|
|
"loss": 5.6498,
|
|
"mean_token_accuracy": 0.15243688523769378,
|
|
"num_tokens": 9677636.0,
|
|
"step": 4665
|
|
},
|
|
{
|
|
"entropy": 5.867781496047973,
|
|
"epoch": 0.4236211901306241,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.000498748413765357,
|
|
"loss": 5.8377,
|
|
"mean_token_accuracy": 0.14748723134398461,
|
|
"num_tokens": 9688268.0,
|
|
"step": 4670
|
|
},
|
|
{
|
|
"entropy": 5.835544300079346,
|
|
"epoch": 0.42407474600870826,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004987450033716646,
|
|
"loss": 5.7391,
|
|
"mean_token_accuracy": 0.1544426128268242,
|
|
"num_tokens": 9698238.0,
|
|
"step": 4675
|
|
},
|
|
{
|
|
"entropy": 5.823677968978882,
|
|
"epoch": 0.42452830188679247,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004987415883508686,
|
|
"loss": 5.6951,
|
|
"mean_token_accuracy": 0.15021548718214034,
|
|
"num_tokens": 9709149.0,
|
|
"step": 4680
|
|
},
|
|
{
|
|
"entropy": 5.771041297912598,
|
|
"epoch": 0.4249818577648766,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004987381687030394,
|
|
"loss": 5.7586,
|
|
"mean_token_accuracy": 0.1466877669095993,
|
|
"num_tokens": 9719486.0,
|
|
"step": 4685
|
|
},
|
|
{
|
|
"entropy": 5.784495067596436,
|
|
"epoch": 0.42543541364296084,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004987347444282479,
|
|
"loss": 5.6918,
|
|
"mean_token_accuracy": 0.15039761662483214,
|
|
"num_tokens": 9729891.0,
|
|
"step": 4690
|
|
},
|
|
{
|
|
"entropy": 5.818458509445191,
|
|
"epoch": 0.425888969521045,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004987313155265649,
|
|
"loss": 5.7094,
|
|
"mean_token_accuracy": 0.15848611816763877,
|
|
"num_tokens": 9739418.0,
|
|
"step": 4695
|
|
},
|
|
{
|
|
"entropy": 5.782320213317871,
|
|
"epoch": 0.42634252539912915,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004987278819980613,
|
|
"loss": 5.7544,
|
|
"mean_token_accuracy": 0.15276919007301332,
|
|
"num_tokens": 9750410.0,
|
|
"step": 4700
|
|
},
|
|
{
|
|
"entropy": 5.833681964874268,
|
|
"epoch": 0.42679608127721336,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004987244438428081,
|
|
"loss": 5.8478,
|
|
"mean_token_accuracy": 0.14890251234173774,
|
|
"num_tokens": 9761986.0,
|
|
"step": 4705
|
|
},
|
|
{
|
|
"entropy": 5.861217498779297,
|
|
"epoch": 0.4272496371552975,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004987210010608764,
|
|
"loss": 5.675,
|
|
"mean_token_accuracy": 0.15809816718101502,
|
|
"num_tokens": 9772368.0,
|
|
"step": 4710
|
|
},
|
|
{
|
|
"entropy": 5.840431547164917,
|
|
"epoch": 0.4277031930333817,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004987175536523373,
|
|
"loss": 5.7687,
|
|
"mean_token_accuracy": 0.15153285264968872,
|
|
"num_tokens": 9782249.0,
|
|
"step": 4715
|
|
},
|
|
{
|
|
"entropy": 5.903892135620117,
|
|
"epoch": 0.4281567489114659,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004987141016172622,
|
|
"loss": 5.7235,
|
|
"mean_token_accuracy": 0.15167634487152098,
|
|
"num_tokens": 9791932.0,
|
|
"step": 4720
|
|
},
|
|
{
|
|
"entropy": 5.7715545177459715,
|
|
"epoch": 0.4286103047895501,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004987106449557225,
|
|
"loss": 5.6834,
|
|
"mean_token_accuracy": 0.14576440975069999,
|
|
"num_tokens": 9803226.0,
|
|
"step": 4725
|
|
},
|
|
{
|
|
"entropy": 5.82260537147522,
|
|
"epoch": 0.42906386066763424,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.0004987071836677896,
|
|
"loss": 5.7597,
|
|
"mean_token_accuracy": 0.14706346690654754,
|
|
"num_tokens": 9814036.0,
|
|
"step": 4730
|
|
},
|
|
{
|
|
"entropy": 5.897468614578247,
|
|
"epoch": 0.42951741654571846,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 0.0004987037177535353,
|
|
"loss": 5.7455,
|
|
"mean_token_accuracy": 0.14280677139759063,
|
|
"num_tokens": 9825537.0,
|
|
"step": 4735
|
|
},
|
|
{
|
|
"entropy": 5.824542474746704,
|
|
"epoch": 0.4299709724238026,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004987002472130309,
|
|
"loss": 5.6583,
|
|
"mean_token_accuracy": 0.14865368008613586,
|
|
"num_tokens": 9835437.0,
|
|
"step": 4740
|
|
},
|
|
{
|
|
"entropy": 5.757734489440918,
|
|
"epoch": 0.43042452830188677,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.0004986967720463485,
|
|
"loss": 5.6658,
|
|
"mean_token_accuracy": 0.14633326083421708,
|
|
"num_tokens": 9845834.0,
|
|
"step": 4745
|
|
},
|
|
{
|
|
"entropy": 5.862345170974732,
|
|
"epoch": 0.430878084179971,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004986932922535598,
|
|
"loss": 5.749,
|
|
"mean_token_accuracy": 0.15574838668107988,
|
|
"num_tokens": 9855984.0,
|
|
"step": 4750
|
|
},
|
|
{
|
|
"entropy": 5.840075349807739,
|
|
"epoch": 0.43133164005805513,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.0004986898078347368,
|
|
"loss": 5.7115,
|
|
"mean_token_accuracy": 0.15084850937128066,
|
|
"num_tokens": 9866203.0,
|
|
"step": 4755
|
|
},
|
|
{
|
|
"entropy": 5.747245264053345,
|
|
"epoch": 0.43178519593613934,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004986863187899516,
|
|
"loss": 5.6573,
|
|
"mean_token_accuracy": 0.15622658431529998,
|
|
"num_tokens": 9875940.0,
|
|
"step": 4760
|
|
},
|
|
{
|
|
"entropy": 5.843631267547607,
|
|
"epoch": 0.4322387518142235,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.0004986828251192764,
|
|
"loss": 5.8129,
|
|
"mean_token_accuracy": 0.14796200692653655,
|
|
"num_tokens": 9886769.0,
|
|
"step": 4765
|
|
},
|
|
{
|
|
"entropy": 5.827453851699829,
|
|
"epoch": 0.4326923076923077,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004986793268227833,
|
|
"loss": 5.6781,
|
|
"mean_token_accuracy": 0.1584503948688507,
|
|
"num_tokens": 9897066.0,
|
|
"step": 4770
|
|
},
|
|
{
|
|
"entropy": 5.7666703224182125,
|
|
"epoch": 0.43314586357039186,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004986758239005448,
|
|
"loss": 5.6937,
|
|
"mean_token_accuracy": 0.15196367353200912,
|
|
"num_tokens": 9907113.0,
|
|
"step": 4775
|
|
},
|
|
{
|
|
"entropy": 5.822373628616333,
|
|
"epoch": 0.4335994194484761,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.0004986723163526331,
|
|
"loss": 5.7041,
|
|
"mean_token_accuracy": 0.15160846412181855,
|
|
"num_tokens": 9917410.0,
|
|
"step": 4780
|
|
},
|
|
{
|
|
"entropy": 5.920275545120239,
|
|
"epoch": 0.43405297532656023,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004986688041791209,
|
|
"loss": 5.6623,
|
|
"mean_token_accuracy": 0.15733712017536164,
|
|
"num_tokens": 9927482.0,
|
|
"step": 4785
|
|
},
|
|
{
|
|
"entropy": 5.683720445632934,
|
|
"epoch": 0.4345065312046444,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.000498665287380081,
|
|
"loss": 5.6526,
|
|
"mean_token_accuracy": 0.1548801988363266,
|
|
"num_tokens": 9937623.0,
|
|
"step": 4790
|
|
},
|
|
{
|
|
"entropy": 5.768561315536499,
|
|
"epoch": 0.4349600870827286,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004986617659555859,
|
|
"loss": 5.6815,
|
|
"mean_token_accuracy": 0.1445303425192833,
|
|
"num_tokens": 9947669.0,
|
|
"step": 4795
|
|
},
|
|
{
|
|
"entropy": 5.814534473419189,
|
|
"epoch": 0.43541364296081275,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004986582399057085,
|
|
"loss": 5.676,
|
|
"mean_token_accuracy": 0.14978551864624023,
|
|
"num_tokens": 9958574.0,
|
|
"step": 4800
|
|
},
|
|
{
|
|
"entropy": 5.796423864364624,
|
|
"epoch": 0.43586719883889696,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.0004986547092305216,
|
|
"loss": 5.7087,
|
|
"mean_token_accuracy": 0.15057784467935562,
|
|
"num_tokens": 9969404.0,
|
|
"step": 4805
|
|
},
|
|
{
|
|
"entropy": 5.715034484863281,
|
|
"epoch": 0.4363207547169811,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004986511739300984,
|
|
"loss": 5.6993,
|
|
"mean_token_accuracy": 0.15097863227128983,
|
|
"num_tokens": 9979860.0,
|
|
"step": 4810
|
|
},
|
|
{
|
|
"entropy": 5.806329584121704,
|
|
"epoch": 0.43677431059506533,
|
|
"grad_norm": 3.125,
|
|
"learning_rate": 0.0004986476340045119,
|
|
"loss": 5.7253,
|
|
"mean_token_accuracy": 0.15245338007807732,
|
|
"num_tokens": 9989390.0,
|
|
"step": 4815
|
|
},
|
|
{
|
|
"entropy": 5.770902156829834,
|
|
"epoch": 0.4372278664731495,
|
|
"grad_norm": 2.640625,
|
|
"learning_rate": 0.0004986440894538354,
|
|
"loss": 5.7683,
|
|
"mean_token_accuracy": 0.1453310377895832,
|
|
"num_tokens": 9999853.0,
|
|
"step": 4820
|
|
},
|
|
{
|
|
"entropy": 5.86833610534668,
|
|
"epoch": 0.4376814223512337,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004986405402781421,
|
|
"loss": 5.7106,
|
|
"mean_token_accuracy": 0.14741745889186858,
|
|
"num_tokens": 10010591.0,
|
|
"step": 4825
|
|
},
|
|
{
|
|
"entropy": 5.895445060729981,
|
|
"epoch": 0.43813497822931785,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.0004986369864775054,
|
|
"loss": 5.7029,
|
|
"mean_token_accuracy": 0.15746968388557434,
|
|
"num_tokens": 10020662.0,
|
|
"step": 4830
|
|
},
|
|
{
|
|
"entropy": 5.737722682952881,
|
|
"epoch": 0.438588534107402,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004986334280519989,
|
|
"loss": 5.6887,
|
|
"mean_token_accuracy": 0.15356032699346542,
|
|
"num_tokens": 10029887.0,
|
|
"step": 4835
|
|
},
|
|
{
|
|
"entropy": 5.78506498336792,
|
|
"epoch": 0.4390420899854862,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.000498629865001696,
|
|
"loss": 5.7734,
|
|
"mean_token_accuracy": 0.1432656690478325,
|
|
"num_tokens": 10040535.0,
|
|
"step": 4840
|
|
},
|
|
{
|
|
"entropy": 5.846698236465454,
|
|
"epoch": 0.43949564586357037,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004986262973266706,
|
|
"loss": 5.7041,
|
|
"mean_token_accuracy": 0.14938746839761735,
|
|
"num_tokens": 10051133.0,
|
|
"step": 4845
|
|
},
|
|
{
|
|
"entropy": 5.737699556350708,
|
|
"epoch": 0.4399492017416546,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004986227250269964,
|
|
"loss": 5.6403,
|
|
"mean_token_accuracy": 0.15840096175670623,
|
|
"num_tokens": 10060955.0,
|
|
"step": 4850
|
|
},
|
|
{
|
|
"entropy": 5.754516363143921,
|
|
"epoch": 0.44040275761973874,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004986191481027472,
|
|
"loss": 5.7054,
|
|
"mean_token_accuracy": 0.15085024312138556,
|
|
"num_tokens": 10070800.0,
|
|
"step": 4855
|
|
},
|
|
{
|
|
"entropy": 5.799833726882935,
|
|
"epoch": 0.44085631349782295,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004986155665539971,
|
|
"loss": 5.6972,
|
|
"mean_token_accuracy": 0.15538632571697236,
|
|
"num_tokens": 10080279.0,
|
|
"step": 4860
|
|
},
|
|
{
|
|
"entropy": 5.7664475440979,
|
|
"epoch": 0.4413098693759071,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.00049861198038082,
|
|
"loss": 5.7044,
|
|
"mean_token_accuracy": 0.14653226137161254,
|
|
"num_tokens": 10089441.0,
|
|
"step": 4865
|
|
},
|
|
{
|
|
"entropy": 5.894711446762085,
|
|
"epoch": 0.4417634252539913,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.0004986083895832903,
|
|
"loss": 5.8118,
|
|
"mean_token_accuracy": 0.14082608968019486,
|
|
"num_tokens": 10100642.0,
|
|
"step": 4870
|
|
},
|
|
{
|
|
"entropy": 5.872471046447754,
|
|
"epoch": 0.44221698113207547,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004986047941614821,
|
|
"loss": 5.749,
|
|
"mean_token_accuracy": 0.15137091875076295,
|
|
"num_tokens": 10112434.0,
|
|
"step": 4875
|
|
},
|
|
{
|
|
"entropy": 5.77865195274353,
|
|
"epoch": 0.4426705370101596,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004986011941154696,
|
|
"loss": 5.7504,
|
|
"mean_token_accuracy": 0.1506796345114708,
|
|
"num_tokens": 10123094.0,
|
|
"step": 4880
|
|
},
|
|
{
|
|
"entropy": 5.942609786987305,
|
|
"epoch": 0.44312409288824384,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004985975894453275,
|
|
"loss": 5.7935,
|
|
"mean_token_accuracy": 0.15835359022021295,
|
|
"num_tokens": 10133357.0,
|
|
"step": 4885
|
|
},
|
|
{
|
|
"entropy": 5.7874181270599365,
|
|
"epoch": 0.443577648766328,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004985939801511304,
|
|
"loss": 5.6562,
|
|
"mean_token_accuracy": 0.15655628293752671,
|
|
"num_tokens": 10143561.0,
|
|
"step": 4890
|
|
},
|
|
{
|
|
"entropy": 5.748687791824341,
|
|
"epoch": 0.4440312046444122,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004985903662329527,
|
|
"loss": 5.7435,
|
|
"mean_token_accuracy": 0.1459873951971531,
|
|
"num_tokens": 10154302.0,
|
|
"step": 4895
|
|
},
|
|
{
|
|
"entropy": 5.8301349639892575,
|
|
"epoch": 0.44448476052249636,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004985867476908693,
|
|
"loss": 5.726,
|
|
"mean_token_accuracy": 0.15291691124439238,
|
|
"num_tokens": 10164357.0,
|
|
"step": 4900
|
|
},
|
|
{
|
|
"entropy": 5.749996614456177,
|
|
"epoch": 0.44493831640058057,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004985831245249549,
|
|
"loss": 5.6574,
|
|
"mean_token_accuracy": 0.15303636640310286,
|
|
"num_tokens": 10173456.0,
|
|
"step": 4905
|
|
},
|
|
{
|
|
"entropy": 5.747867584228516,
|
|
"epoch": 0.4453918722786647,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004985794967352846,
|
|
"loss": 5.5875,
|
|
"mean_token_accuracy": 0.1556650996208191,
|
|
"num_tokens": 10182823.0,
|
|
"step": 4910
|
|
},
|
|
{
|
|
"entropy": 5.773955678939819,
|
|
"epoch": 0.44584542815674894,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.0004985758643219334,
|
|
"loss": 5.6849,
|
|
"mean_token_accuracy": 0.15339920967817305,
|
|
"num_tokens": 10192668.0,
|
|
"step": 4915
|
|
},
|
|
{
|
|
"entropy": 5.762610244750976,
|
|
"epoch": 0.4462989840348331,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004985722272849762,
|
|
"loss": 5.64,
|
|
"mean_token_accuracy": 0.15597241818904878,
|
|
"num_tokens": 10202997.0,
|
|
"step": 4920
|
|
},
|
|
{
|
|
"entropy": 5.782825231552124,
|
|
"epoch": 0.44675253991291725,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004985685856244884,
|
|
"loss": 5.6605,
|
|
"mean_token_accuracy": 0.15476631075143815,
|
|
"num_tokens": 10212136.0,
|
|
"step": 4925
|
|
},
|
|
{
|
|
"entropy": 5.7222226619720455,
|
|
"epoch": 0.44720609579100146,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004985649393405453,
|
|
"loss": 5.7605,
|
|
"mean_token_accuracy": 0.15388176888227462,
|
|
"num_tokens": 10221910.0,
|
|
"step": 4930
|
|
},
|
|
{
|
|
"entropy": 5.806464099884034,
|
|
"epoch": 0.4476596516690856,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004985612884332223,
|
|
"loss": 5.7126,
|
|
"mean_token_accuracy": 0.1526092231273651,
|
|
"num_tokens": 10231430.0,
|
|
"step": 4935
|
|
},
|
|
{
|
|
"entropy": 5.784297037124634,
|
|
"epoch": 0.4481132075471698,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 0.0004985576329025949,
|
|
"loss": 5.6452,
|
|
"mean_token_accuracy": 0.1589261770248413,
|
|
"num_tokens": 10242095.0,
|
|
"step": 4940
|
|
},
|
|
{
|
|
"entropy": 5.742293357849121,
|
|
"epoch": 0.448566763425254,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004985539727487385,
|
|
"loss": 5.6367,
|
|
"mean_token_accuracy": 0.1511576235294342,
|
|
"num_tokens": 10252083.0,
|
|
"step": 4945
|
|
},
|
|
{
|
|
"entropy": 5.782474040985107,
|
|
"epoch": 0.4490203193033382,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004985503079717292,
|
|
"loss": 5.7418,
|
|
"mean_token_accuracy": 0.15320956856012344,
|
|
"num_tokens": 10262621.0,
|
|
"step": 4950
|
|
},
|
|
{
|
|
"entropy": 5.908123397827149,
|
|
"epoch": 0.44947387518142234,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004985466385716425,
|
|
"loss": 5.8807,
|
|
"mean_token_accuracy": 0.14101727977395057,
|
|
"num_tokens": 10274406.0,
|
|
"step": 4955
|
|
},
|
|
{
|
|
"entropy": 5.851602983474732,
|
|
"epoch": 0.44992743105950656,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004985429645485543,
|
|
"loss": 5.6811,
|
|
"mean_token_accuracy": 0.14795504212379457,
|
|
"num_tokens": 10284688.0,
|
|
"step": 4960
|
|
},
|
|
{
|
|
"entropy": 5.842687511444092,
|
|
"epoch": 0.4503809869375907,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004985392859025407,
|
|
"loss": 5.7318,
|
|
"mean_token_accuracy": 0.15307743102312088,
|
|
"num_tokens": 10295708.0,
|
|
"step": 4965
|
|
},
|
|
{
|
|
"entropy": 5.841201591491699,
|
|
"epoch": 0.45083454281567487,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 0.0004985356026336776,
|
|
"loss": 5.7051,
|
|
"mean_token_accuracy": 0.14724947661161422,
|
|
"num_tokens": 10306345.0,
|
|
"step": 4970
|
|
},
|
|
{
|
|
"entropy": 5.797213697433472,
|
|
"epoch": 0.4512880986937591,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004985319147420414,
|
|
"loss": 5.6929,
|
|
"mean_token_accuracy": 0.14897643476724626,
|
|
"num_tokens": 10316289.0,
|
|
"step": 4975
|
|
},
|
|
{
|
|
"entropy": 5.752896404266357,
|
|
"epoch": 0.45174165457184323,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004985282222277082,
|
|
"loss": 5.7097,
|
|
"mean_token_accuracy": 0.1546037197113037,
|
|
"num_tokens": 10326355.0,
|
|
"step": 4980
|
|
},
|
|
{
|
|
"entropy": 5.856582164764404,
|
|
"epoch": 0.45219521044992744,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004985245250907544,
|
|
"loss": 5.7639,
|
|
"mean_token_accuracy": 0.1496923163533211,
|
|
"num_tokens": 10336010.0,
|
|
"step": 4985
|
|
},
|
|
{
|
|
"entropy": 5.797954511642456,
|
|
"epoch": 0.4526487663280116,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004985208233312564,
|
|
"loss": 5.6639,
|
|
"mean_token_accuracy": 0.1572360098361969,
|
|
"num_tokens": 10346559.0,
|
|
"step": 4990
|
|
},
|
|
{
|
|
"entropy": 5.830086183547974,
|
|
"epoch": 0.4531023222060958,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004985171169492908,
|
|
"loss": 5.6968,
|
|
"mean_token_accuracy": 0.161420102417469,
|
|
"num_tokens": 10356695.0,
|
|
"step": 4995
|
|
},
|
|
{
|
|
"entropy": 5.8636914730072025,
|
|
"epoch": 0.45355587808417996,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004985134059449344,
|
|
"loss": 5.8988,
|
|
"mean_token_accuracy": 0.1391928419470787,
|
|
"num_tokens": 10367813.0,
|
|
"step": 5000
|
|
},
|
|
{
|
|
"entropy": 5.822160959243774,
|
|
"epoch": 0.4540094339622642,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004985096903182637,
|
|
"loss": 5.6941,
|
|
"mean_token_accuracy": 0.15162536948919297,
|
|
"num_tokens": 10378146.0,
|
|
"step": 5005
|
|
},
|
|
{
|
|
"entropy": 5.8184010028839115,
|
|
"epoch": 0.45446298984034833,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004985059700693557,
|
|
"loss": 5.6652,
|
|
"mean_token_accuracy": 0.15473043769598008,
|
|
"num_tokens": 10389702.0,
|
|
"step": 5010
|
|
},
|
|
{
|
|
"entropy": 5.726432371139526,
|
|
"epoch": 0.4549165457184325,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004985022451982872,
|
|
"loss": 5.6486,
|
|
"mean_token_accuracy": 0.15523469001054763,
|
|
"num_tokens": 10400150.0,
|
|
"step": 5015
|
|
},
|
|
{
|
|
"entropy": 5.768562316894531,
|
|
"epoch": 0.4553701015965167,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004984985157051354,
|
|
"loss": 5.6974,
|
|
"mean_token_accuracy": 0.15065493658185006,
|
|
"num_tokens": 10410928.0,
|
|
"step": 5020
|
|
},
|
|
{
|
|
"entropy": 5.909054613113403,
|
|
"epoch": 0.45582365747460085,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004984947815899774,
|
|
"loss": 5.8095,
|
|
"mean_token_accuracy": 0.14077219292521476,
|
|
"num_tokens": 10422129.0,
|
|
"step": 5025
|
|
},
|
|
{
|
|
"entropy": 5.8900409698486325,
|
|
"epoch": 0.45627721335268506,
|
|
"grad_norm": 2.671875,
|
|
"learning_rate": 0.0004984910428528902,
|
|
"loss": 5.8198,
|
|
"mean_token_accuracy": 0.15190441012382508,
|
|
"num_tokens": 10432536.0,
|
|
"step": 5030
|
|
},
|
|
{
|
|
"entropy": 5.81307315826416,
|
|
"epoch": 0.4567307692307692,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004984872994939514,
|
|
"loss": 5.6729,
|
|
"mean_token_accuracy": 0.15173702389001847,
|
|
"num_tokens": 10442639.0,
|
|
"step": 5035
|
|
},
|
|
{
|
|
"entropy": 5.709221887588501,
|
|
"epoch": 0.45718432510885343,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004984835515132382,
|
|
"loss": 5.6662,
|
|
"mean_token_accuracy": 0.1524081900715828,
|
|
"num_tokens": 10453118.0,
|
|
"step": 5040
|
|
},
|
|
{
|
|
"entropy": 5.77504186630249,
|
|
"epoch": 0.4576378809869376,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004984797989108282,
|
|
"loss": 5.6227,
|
|
"mean_token_accuracy": 0.15486747324466704,
|
|
"num_tokens": 10463717.0,
|
|
"step": 5045
|
|
},
|
|
{
|
|
"entropy": 5.740967559814453,
|
|
"epoch": 0.4580914368650218,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.0004984760416867991,
|
|
"loss": 5.6268,
|
|
"mean_token_accuracy": 0.15707418620586394,
|
|
"num_tokens": 10473566.0,
|
|
"step": 5050
|
|
},
|
|
{
|
|
"entropy": 5.837207460403443,
|
|
"epoch": 0.45854499274310595,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004984722798412286,
|
|
"loss": 5.875,
|
|
"mean_token_accuracy": 0.14405538737773896,
|
|
"num_tokens": 10485517.0,
|
|
"step": 5055
|
|
},
|
|
{
|
|
"entropy": 5.8029149055480955,
|
|
"epoch": 0.4589985486211901,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004984685133741941,
|
|
"loss": 5.7576,
|
|
"mean_token_accuracy": 0.14697242826223372,
|
|
"num_tokens": 10495585.0,
|
|
"step": 5060
|
|
},
|
|
{
|
|
"entropy": 5.974255466461182,
|
|
"epoch": 0.4594521044992743,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.000498464742285774,
|
|
"loss": 5.8296,
|
|
"mean_token_accuracy": 0.14219358265399934,
|
|
"num_tokens": 10507307.0,
|
|
"step": 5065
|
|
},
|
|
{
|
|
"entropy": 5.802126026153564,
|
|
"epoch": 0.45990566037735847,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.000498460966576046,
|
|
"loss": 5.6525,
|
|
"mean_token_accuracy": 0.15711713284254075,
|
|
"num_tokens": 10517504.0,
|
|
"step": 5070
|
|
},
|
|
{
|
|
"entropy": 5.719477128982544,
|
|
"epoch": 0.4603592162554427,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004984571862450884,
|
|
"loss": 5.6994,
|
|
"mean_token_accuracy": 0.156757353246212,
|
|
"num_tokens": 10527805.0,
|
|
"step": 5075
|
|
},
|
|
{
|
|
"entropy": 5.790680837631226,
|
|
"epoch": 0.46081277213352684,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004984534012929791,
|
|
"loss": 5.6448,
|
|
"mean_token_accuracy": 0.15808457583189012,
|
|
"num_tokens": 10537395.0,
|
|
"step": 5080
|
|
},
|
|
{
|
|
"entropy": 5.806749296188355,
|
|
"epoch": 0.46126632801161105,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004984496117197967,
|
|
"loss": 5.661,
|
|
"mean_token_accuracy": 0.15927357822656632,
|
|
"num_tokens": 10547370.0,
|
|
"step": 5085
|
|
},
|
|
{
|
|
"entropy": 5.751757955551147,
|
|
"epoch": 0.4617198838896952,
|
|
"grad_norm": 2.9375,
|
|
"learning_rate": 0.0004984458175256193,
|
|
"loss": 5.7242,
|
|
"mean_token_accuracy": 0.15044082552194596,
|
|
"num_tokens": 10558616.0,
|
|
"step": 5090
|
|
},
|
|
{
|
|
"entropy": 5.748292541503906,
|
|
"epoch": 0.4621734397677794,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.0004984420187105253,
|
|
"loss": 5.6144,
|
|
"mean_token_accuracy": 0.1535917639732361,
|
|
"num_tokens": 10568021.0,
|
|
"step": 5095
|
|
},
|
|
{
|
|
"entropy": 5.787271165847779,
|
|
"epoch": 0.46262699564586357,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.0004984382152745936,
|
|
"loss": 5.6424,
|
|
"mean_token_accuracy": 0.1560645118355751,
|
|
"num_tokens": 10578585.0,
|
|
"step": 5100
|
|
},
|
|
{
|
|
"entropy": 5.743627309799194,
|
|
"epoch": 0.4630805515239477,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004984344072179026,
|
|
"loss": 5.7202,
|
|
"mean_token_accuracy": 0.14723466336727142,
|
|
"num_tokens": 10588908.0,
|
|
"step": 5105
|
|
},
|
|
{
|
|
"entropy": 5.8628967761993405,
|
|
"epoch": 0.46353410740203194,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004984305945405312,
|
|
"loss": 5.6885,
|
|
"mean_token_accuracy": 0.1542614743113518,
|
|
"num_tokens": 10598479.0,
|
|
"step": 5110
|
|
},
|
|
{
|
|
"entropy": 5.825188493728637,
|
|
"epoch": 0.4639876632801161,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.000498426777242558,
|
|
"loss": 5.7072,
|
|
"mean_token_accuracy": 0.14926993921399118,
|
|
"num_tokens": 10609725.0,
|
|
"step": 5115
|
|
},
|
|
{
|
|
"entropy": 5.875491189956665,
|
|
"epoch": 0.4644412191582003,
|
|
"grad_norm": 2.8125,
|
|
"learning_rate": 0.0004984229553240623,
|
|
"loss": 5.7486,
|
|
"mean_token_accuracy": 0.15380418300628662,
|
|
"num_tokens": 10620634.0,
|
|
"step": 5120
|
|
},
|
|
{
|
|
"entropy": 5.79208197593689,
|
|
"epoch": 0.46489477503628446,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004984191287851228,
|
|
"loss": 5.6496,
|
|
"mean_token_accuracy": 0.1518457368016243,
|
|
"num_tokens": 10630626.0,
|
|
"step": 5125
|
|
},
|
|
{
|
|
"entropy": 5.854870986938477,
|
|
"epoch": 0.46534833091436867,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004984152976258188,
|
|
"loss": 5.744,
|
|
"mean_token_accuracy": 0.1433987408876419,
|
|
"num_tokens": 10641033.0,
|
|
"step": 5130
|
|
},
|
|
{
|
|
"entropy": 5.773093795776367,
|
|
"epoch": 0.4658018867924528,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004984114618462296,
|
|
"loss": 5.6728,
|
|
"mean_token_accuracy": 0.157008358836174,
|
|
"num_tokens": 10651333.0,
|
|
"step": 5135
|
|
},
|
|
{
|
|
"entropy": 5.831416845321655,
|
|
"epoch": 0.46625544267053703,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004984076214464343,
|
|
"loss": 5.7365,
|
|
"mean_token_accuracy": 0.14905158132314683,
|
|
"num_tokens": 10661752.0,
|
|
"step": 5140
|
|
},
|
|
{
|
|
"entropy": 5.831983804702759,
|
|
"epoch": 0.4667089985486212,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.0004984037764265126,
|
|
"loss": 5.7934,
|
|
"mean_token_accuracy": 0.14510700330138207,
|
|
"num_tokens": 10672977.0,
|
|
"step": 5145
|
|
},
|
|
{
|
|
"entropy": 5.871959590911866,
|
|
"epoch": 0.46716255442670535,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004983999267865438,
|
|
"loss": 5.699,
|
|
"mean_token_accuracy": 0.1503434360027313,
|
|
"num_tokens": 10683629.0,
|
|
"step": 5150
|
|
},
|
|
{
|
|
"entropy": 5.849706983566284,
|
|
"epoch": 0.46761611030478956,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004983960725266078,
|
|
"loss": 5.7336,
|
|
"mean_token_accuracy": 0.14961588084697724,
|
|
"num_tokens": 10693566.0,
|
|
"step": 5155
|
|
},
|
|
{
|
|
"entropy": 5.834669923782348,
|
|
"epoch": 0.4680696661828737,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004983922136467838,
|
|
"loss": 5.8189,
|
|
"mean_token_accuracy": 0.14934680312871934,
|
|
"num_tokens": 10703437.0,
|
|
"step": 5160
|
|
},
|
|
{
|
|
"entropy": 5.771584939956665,
|
|
"epoch": 0.4685232220609579,
|
|
"grad_norm": 3.453125,
|
|
"learning_rate": 0.000498388350147152,
|
|
"loss": 5.6684,
|
|
"mean_token_accuracy": 0.1507238656282425,
|
|
"num_tokens": 10713614.0,
|
|
"step": 5165
|
|
},
|
|
{
|
|
"entropy": 5.778143882751465,
|
|
"epoch": 0.4689767779390421,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.0004983844820277922,
|
|
"loss": 5.6655,
|
|
"mean_token_accuracy": 0.15385135263204575,
|
|
"num_tokens": 10723460.0,
|
|
"step": 5170
|
|
},
|
|
{
|
|
"entropy": 5.858981895446777,
|
|
"epoch": 0.4694303338171263,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004983806092887843,
|
|
"loss": 5.7319,
|
|
"mean_token_accuracy": 0.15325873494148254,
|
|
"num_tokens": 10734656.0,
|
|
"step": 5175
|
|
},
|
|
{
|
|
"entropy": 5.901455020904541,
|
|
"epoch": 0.46988388969521044,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.0004983767319302086,
|
|
"loss": 5.7835,
|
|
"mean_token_accuracy": 0.1446901760995388,
|
|
"num_tokens": 10745699.0,
|
|
"step": 5180
|
|
},
|
|
{
|
|
"entropy": 5.751908636093139,
|
|
"epoch": 0.47033744557329465,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004983728499521451,
|
|
"loss": 5.7019,
|
|
"mean_token_accuracy": 0.1527523472905159,
|
|
"num_tokens": 10755837.0,
|
|
"step": 5185
|
|
},
|
|
{
|
|
"entropy": 5.7134605884552006,
|
|
"epoch": 0.4707910014513788,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004983689633546741,
|
|
"loss": 5.6559,
|
|
"mean_token_accuracy": 0.14864804670214654,
|
|
"num_tokens": 10766538.0,
|
|
"step": 5190
|
|
},
|
|
{
|
|
"entropy": 5.910651826858521,
|
|
"epoch": 0.47124455732946297,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004983650721378761,
|
|
"loss": 5.8019,
|
|
"mean_token_accuracy": 0.14270213842391968,
|
|
"num_tokens": 10777309.0,
|
|
"step": 5195
|
|
},
|
|
{
|
|
"entropy": 5.823569345474243,
|
|
"epoch": 0.4716981132075472,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004983611763018314,
|
|
"loss": 5.6584,
|
|
"mean_token_accuracy": 0.15261757224798203,
|
|
"num_tokens": 10787747.0,
|
|
"step": 5200
|
|
},
|
|
{
|
|
"entropy": 5.786646938323974,
|
|
"epoch": 0.47215166908563133,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004983572758466208,
|
|
"loss": 5.737,
|
|
"mean_token_accuracy": 0.15750621408224105,
|
|
"num_tokens": 10798857.0,
|
|
"step": 5205
|
|
},
|
|
{
|
|
"entropy": 5.828906869888305,
|
|
"epoch": 0.47260522496371554,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004983533707723247,
|
|
"loss": 5.6847,
|
|
"mean_token_accuracy": 0.15451455861330032,
|
|
"num_tokens": 10808766.0,
|
|
"step": 5210
|
|
},
|
|
{
|
|
"entropy": 5.711640405654907,
|
|
"epoch": 0.4730587808417997,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.0004983494610790241,
|
|
"loss": 5.5887,
|
|
"mean_token_accuracy": 0.15516856759786607,
|
|
"num_tokens": 10819129.0,
|
|
"step": 5215
|
|
},
|
|
{
|
|
"entropy": 5.722329807281494,
|
|
"epoch": 0.4735123367198839,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004983455467667996,
|
|
"loss": 5.6476,
|
|
"mean_token_accuracy": 0.15732542127370835,
|
|
"num_tokens": 10829952.0,
|
|
"step": 5220
|
|
},
|
|
{
|
|
"entropy": 5.8139319896698,
|
|
"epoch": 0.47396589259796806,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.0004983416278357322,
|
|
"loss": 5.7923,
|
|
"mean_token_accuracy": 0.14603560641407967,
|
|
"num_tokens": 10841163.0,
|
|
"step": 5225
|
|
},
|
|
{
|
|
"entropy": 5.918250179290771,
|
|
"epoch": 0.4744194484760523,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004983377042859032,
|
|
"loss": 5.7629,
|
|
"mean_token_accuracy": 0.14654296189546584,
|
|
"num_tokens": 10853047.0,
|
|
"step": 5230
|
|
},
|
|
{
|
|
"entropy": 5.793363475799561,
|
|
"epoch": 0.47487300435413643,
|
|
"grad_norm": 2.734375,
|
|
"learning_rate": 0.0004983337761173936,
|
|
"loss": 5.6738,
|
|
"mean_token_accuracy": 0.14845061898231507,
|
|
"num_tokens": 10863040.0,
|
|
"step": 5235
|
|
},
|
|
{
|
|
"entropy": 5.739855766296387,
|
|
"epoch": 0.4753265602322206,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004983298433302843,
|
|
"loss": 5.6765,
|
|
"mean_token_accuracy": 0.1506304681301117,
|
|
"num_tokens": 10872710.0,
|
|
"step": 5240
|
|
},
|
|
{
|
|
"entropy": 5.826231050491333,
|
|
"epoch": 0.4757801161103048,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004983259059246572,
|
|
"loss": 5.752,
|
|
"mean_token_accuracy": 0.14818743392825126,
|
|
"num_tokens": 10883438.0,
|
|
"step": 5245
|
|
},
|
|
{
|
|
"entropy": 5.831701707839966,
|
|
"epoch": 0.47623367198838895,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.0004983219639005934,
|
|
"loss": 5.6501,
|
|
"mean_token_accuracy": 0.15101292133331298,
|
|
"num_tokens": 10892987.0,
|
|
"step": 5250
|
|
},
|
|
{
|
|
"entropy": 5.759233617782593,
|
|
"epoch": 0.47668722786647316,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.0004983180172581745,
|
|
"loss": 5.6962,
|
|
"mean_token_accuracy": 0.1499043494462967,
|
|
"num_tokens": 10903118.0,
|
|
"step": 5255
|
|
},
|
|
{
|
|
"entropy": 5.76815357208252,
|
|
"epoch": 0.4771407837445573,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004983140659974819,
|
|
"loss": 5.6355,
|
|
"mean_token_accuracy": 0.1572742462158203,
|
|
"num_tokens": 10913084.0,
|
|
"step": 5260
|
|
},
|
|
{
|
|
"entropy": 5.782183504104614,
|
|
"epoch": 0.47759433962264153,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.0004983101101185977,
|
|
"loss": 5.6249,
|
|
"mean_token_accuracy": 0.16095837205648422,
|
|
"num_tokens": 10923002.0,
|
|
"step": 5265
|
|
},
|
|
{
|
|
"entropy": 5.79695348739624,
|
|
"epoch": 0.4780478955007257,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004983061496216035,
|
|
"loss": 5.7592,
|
|
"mean_token_accuracy": 0.1515378013253212,
|
|
"num_tokens": 10933902.0,
|
|
"step": 5270
|
|
},
|
|
{
|
|
"entropy": 5.914425182342529,
|
|
"epoch": 0.4785014513788099,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.0004983021845065812,
|
|
"loss": 5.7215,
|
|
"mean_token_accuracy": 0.1509646564722061,
|
|
"num_tokens": 10944665.0,
|
|
"step": 5275
|
|
},
|
|
{
|
|
"entropy": 5.848713016510009,
|
|
"epoch": 0.47895500725689405,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 0.0004982982147736128,
|
|
"loss": 5.7333,
|
|
"mean_token_accuracy": 0.1508101060986519,
|
|
"num_tokens": 10955104.0,
|
|
"step": 5280
|
|
},
|
|
{
|
|
"entropy": 5.783365154266358,
|
|
"epoch": 0.4794085631349782,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004982942404227805,
|
|
"loss": 5.7647,
|
|
"mean_token_accuracy": 0.1501639798283577,
|
|
"num_tokens": 10966074.0,
|
|
"step": 5285
|
|
},
|
|
{
|
|
"entropy": 5.793298768997192,
|
|
"epoch": 0.4798621190130624,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004982902614541662,
|
|
"loss": 5.6624,
|
|
"mean_token_accuracy": 0.1498418629169464,
|
|
"num_tokens": 10975943.0,
|
|
"step": 5290
|
|
},
|
|
{
|
|
"entropy": 5.807666254043579,
|
|
"epoch": 0.48031567489114657,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.0004982862778678526,
|
|
"loss": 5.7099,
|
|
"mean_token_accuracy": 0.15479816794395446,
|
|
"num_tokens": 10985567.0,
|
|
"step": 5295
|
|
},
|
|
{
|
|
"entropy": 5.70306134223938,
|
|
"epoch": 0.4807692307692308,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.0004982822896639218,
|
|
"loss": 5.602,
|
|
"mean_token_accuracy": 0.15984350740909575,
|
|
"num_tokens": 10995155.0,
|
|
"step": 5300
|
|
},
|
|
{
|
|
"entropy": 5.81755895614624,
|
|
"epoch": 0.48122278664731494,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004982782968424563,
|
|
"loss": 5.6949,
|
|
"mean_token_accuracy": 0.1501569300889969,
|
|
"num_tokens": 11006608.0,
|
|
"step": 5305
|
|
},
|
|
{
|
|
"entropy": 5.852555847167968,
|
|
"epoch": 0.48167634252539915,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.0004982742994035388,
|
|
"loss": 5.7532,
|
|
"mean_token_accuracy": 0.14663399159908294,
|
|
"num_tokens": 11016753.0,
|
|
"step": 5310
|
|
},
|
|
{
|
|
"entropy": 5.839328002929688,
|
|
"epoch": 0.4821298984034833,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004982702973472518,
|
|
"loss": 5.7281,
|
|
"mean_token_accuracy": 0.1561571702361107,
|
|
"num_tokens": 11027234.0,
|
|
"step": 5315
|
|
},
|
|
{
|
|
"entropy": 5.783762979507446,
|
|
"epoch": 0.4825834542815675,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.0004982662906736783,
|
|
"loss": 5.7026,
|
|
"mean_token_accuracy": 0.15801250636577607,
|
|
"num_tokens": 11036885.0,
|
|
"step": 5320
|
|
},
|
|
{
|
|
"entropy": 5.827364730834961,
|
|
"epoch": 0.48303701015965167,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.0004982622793829009,
|
|
"loss": 5.7481,
|
|
"mean_token_accuracy": 0.14987791031599046,
|
|
"num_tokens": 11047417.0,
|
|
"step": 5325
|
|
},
|
|
{
|
|
"entropy": 5.820127344131469,
|
|
"epoch": 0.4834905660377358,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004982582634750027,
|
|
"loss": 5.6639,
|
|
"mean_token_accuracy": 0.14887322336435319,
|
|
"num_tokens": 11057728.0,
|
|
"step": 5330
|
|
},
|
|
{
|
|
"entropy": 5.787255716323853,
|
|
"epoch": 0.48394412191582004,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004982542429500667,
|
|
"loss": 5.7213,
|
|
"mean_token_accuracy": 0.14780182540416717,
|
|
"num_tokens": 11067201.0,
|
|
"step": 5335
|
|
},
|
|
{
|
|
"entropy": 5.820434999465943,
|
|
"epoch": 0.4843976777939042,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004982502178081761,
|
|
"loss": 5.758,
|
|
"mean_token_accuracy": 0.1484843149781227,
|
|
"num_tokens": 11077714.0,
|
|
"step": 5340
|
|
},
|
|
{
|
|
"entropy": 5.861207103729248,
|
|
"epoch": 0.4848512336719884,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004982461880494141,
|
|
"loss": 5.7045,
|
|
"mean_token_accuracy": 0.15382479578256608,
|
|
"num_tokens": 11087790.0,
|
|
"step": 5345
|
|
},
|
|
{
|
|
"entropy": 5.871987390518188,
|
|
"epoch": 0.48530478955007256,
|
|
"grad_norm": 2.65625,
|
|
"learning_rate": 0.000498242153673864,
|
|
"loss": 5.7951,
|
|
"mean_token_accuracy": 0.14940507858991622,
|
|
"num_tokens": 11098351.0,
|
|
"step": 5350
|
|
},
|
|
{
|
|
"entropy": 5.882188415527343,
|
|
"epoch": 0.48575834542815677,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004982381146816094,
|
|
"loss": 5.7614,
|
|
"mean_token_accuracy": 0.14735559076070787,
|
|
"num_tokens": 11108648.0,
|
|
"step": 5355
|
|
},
|
|
{
|
|
"entropy": 5.844276762008667,
|
|
"epoch": 0.4862119013062409,
|
|
"grad_norm": 3.921875,
|
|
"learning_rate": 0.0004982340710727336,
|
|
"loss": 5.7012,
|
|
"mean_token_accuracy": 0.15624714493751526,
|
|
"num_tokens": 11119035.0,
|
|
"step": 5360
|
|
},
|
|
{
|
|
"entropy": 5.82732195854187,
|
|
"epoch": 0.48666545718432513,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004982300228473203,
|
|
"loss": 5.7015,
|
|
"mean_token_accuracy": 0.15547741055488587,
|
|
"num_tokens": 11129468.0,
|
|
"step": 5365
|
|
},
|
|
{
|
|
"entropy": 5.746838140487671,
|
|
"epoch": 0.4871190130624093,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004982259700054533,
|
|
"loss": 5.7228,
|
|
"mean_token_accuracy": 0.1501197710633278,
|
|
"num_tokens": 11139828.0,
|
|
"step": 5370
|
|
},
|
|
{
|
|
"entropy": 5.755753469467163,
|
|
"epoch": 0.48757256894049344,
|
|
"grad_norm": 3.296875,
|
|
"learning_rate": 0.0004982219125472163,
|
|
"loss": 5.6705,
|
|
"mean_token_accuracy": 0.1561184525489807,
|
|
"num_tokens": 11150427.0,
|
|
"step": 5375
|
|
},
|
|
{
|
|
"entropy": 5.759000968933106,
|
|
"epoch": 0.48802612481857766,
|
|
"grad_norm": 2.9375,
|
|
"learning_rate": 0.0004982178504726933,
|
|
"loss": 5.6587,
|
|
"mean_token_accuracy": 0.1554884731769562,
|
|
"num_tokens": 11161358.0,
|
|
"step": 5380
|
|
},
|
|
{
|
|
"entropy": 5.807296991348267,
|
|
"epoch": 0.4884796806966618,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004982137837819682,
|
|
"loss": 5.7884,
|
|
"mean_token_accuracy": 0.1499861791729927,
|
|
"num_tokens": 11171929.0,
|
|
"step": 5385
|
|
},
|
|
{
|
|
"entropy": 5.8052185535430905,
|
|
"epoch": 0.488933236574746,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004982097124751252,
|
|
"loss": 5.7325,
|
|
"mean_token_accuracy": 0.1465311512351036,
|
|
"num_tokens": 11182262.0,
|
|
"step": 5390
|
|
},
|
|
{
|
|
"entropy": 5.811205768585205,
|
|
"epoch": 0.4893867924528302,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004982056365522486,
|
|
"loss": 5.6256,
|
|
"mean_token_accuracy": 0.1551127627491951,
|
|
"num_tokens": 11192722.0,
|
|
"step": 5395
|
|
},
|
|
{
|
|
"entropy": 5.805147171020508,
|
|
"epoch": 0.4898403483309144,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004982015560134225,
|
|
"loss": 5.7015,
|
|
"mean_token_accuracy": 0.14520970433950425,
|
|
"num_tokens": 11202951.0,
|
|
"step": 5400
|
|
},
|
|
{
|
|
"entropy": 5.767069959640503,
|
|
"epoch": 0.49029390420899854,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.0004981974708587312,
|
|
"loss": 5.6291,
|
|
"mean_token_accuracy": 0.15299493372440337,
|
|
"num_tokens": 11212018.0,
|
|
"step": 5405
|
|
},
|
|
{
|
|
"entropy": 5.786797094345093,
|
|
"epoch": 0.49074746008708275,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.0004981933810882594,
|
|
"loss": 5.7443,
|
|
"mean_token_accuracy": 0.14947062432765962,
|
|
"num_tokens": 11222034.0,
|
|
"step": 5410
|
|
},
|
|
{
|
|
"entropy": 5.8002769470214846,
|
|
"epoch": 0.4912010159651669,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004981892867020917,
|
|
"loss": 5.6749,
|
|
"mean_token_accuracy": 0.15354969650506972,
|
|
"num_tokens": 11232105.0,
|
|
"step": 5415
|
|
},
|
|
{
|
|
"entropy": 5.893782138824463,
|
|
"epoch": 0.49165457184325106,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004981851877003125,
|
|
"loss": 5.808,
|
|
"mean_token_accuracy": 0.14583044201135636,
|
|
"num_tokens": 11241452.0,
|
|
"step": 5420
|
|
},
|
|
{
|
|
"entropy": 5.8148712635040285,
|
|
"epoch": 0.4921081277213353,
|
|
"grad_norm": 2.671875,
|
|
"learning_rate": 0.0004981810840830068,
|
|
"loss": 5.6554,
|
|
"mean_token_accuracy": 0.1535477250814438,
|
|
"num_tokens": 11252172.0,
|
|
"step": 5425
|
|
},
|
|
{
|
|
"entropy": 5.768006420135498,
|
|
"epoch": 0.49256168359941943,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004981769758502596,
|
|
"loss": 5.6176,
|
|
"mean_token_accuracy": 0.1569655179977417,
|
|
"num_tokens": 11261660.0,
|
|
"step": 5430
|
|
},
|
|
{
|
|
"entropy": 5.723521661758423,
|
|
"epoch": 0.49301523947750364,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004981728630021555,
|
|
"loss": 5.683,
|
|
"mean_token_accuracy": 0.15691534727811812,
|
|
"num_tokens": 11271423.0,
|
|
"step": 5435
|
|
},
|
|
{
|
|
"entropy": 5.833865833282471,
|
|
"epoch": 0.4934687953555878,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.0004981687455387797,
|
|
"loss": 5.6859,
|
|
"mean_token_accuracy": 0.1534940168261528,
|
|
"num_tokens": 11282596.0,
|
|
"step": 5440
|
|
},
|
|
{
|
|
"entropy": 5.789115333557129,
|
|
"epoch": 0.493922351233672,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.0004981646234602173,
|
|
"loss": 5.657,
|
|
"mean_token_accuracy": 0.1574923425912857,
|
|
"num_tokens": 11292489.0,
|
|
"step": 5445
|
|
},
|
|
{
|
|
"entropy": 5.828164672851562,
|
|
"epoch": 0.49437590711175616,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004981604967665539,
|
|
"loss": 5.7223,
|
|
"mean_token_accuracy": 0.15355284214019777,
|
|
"num_tokens": 11303847.0,
|
|
"step": 5450
|
|
},
|
|
{
|
|
"entropy": 5.722614383697509,
|
|
"epoch": 0.4948294629898404,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004981563654578743,
|
|
"loss": 5.6588,
|
|
"mean_token_accuracy": 0.15813755989074707,
|
|
"num_tokens": 11313945.0,
|
|
"step": 5455
|
|
},
|
|
{
|
|
"entropy": 5.811623859405517,
|
|
"epoch": 0.49528301886792453,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004981522295342643,
|
|
"loss": 5.6877,
|
|
"mean_token_accuracy": 0.15314490497112274,
|
|
"num_tokens": 11323152.0,
|
|
"step": 5460
|
|
},
|
|
{
|
|
"entropy": 5.818774223327637,
|
|
"epoch": 0.4957365747460087,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.0004981480889958092,
|
|
"loss": 5.7324,
|
|
"mean_token_accuracy": 0.15346988290548325,
|
|
"num_tokens": 11334961.0,
|
|
"step": 5465
|
|
},
|
|
{
|
|
"entropy": 5.823841524124146,
|
|
"epoch": 0.4961901306240929,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.0004981439438425949,
|
|
"loss": 5.7,
|
|
"mean_token_accuracy": 0.1509547233581543,
|
|
"num_tokens": 11346172.0,
|
|
"step": 5470
|
|
},
|
|
{
|
|
"entropy": 5.844482898712158,
|
|
"epoch": 0.49664368650217705,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.000498139794074707,
|
|
"loss": 5.7412,
|
|
"mean_token_accuracy": 0.15192751735448837,
|
|
"num_tokens": 11356439.0,
|
|
"step": 5475
|
|
},
|
|
{
|
|
"entropy": 5.779028701782226,
|
|
"epoch": 0.49709724238026126,
|
|
"grad_norm": 4.21875,
|
|
"learning_rate": 0.0004981356396922313,
|
|
"loss": 5.7457,
|
|
"mean_token_accuracy": 0.1459797888994217,
|
|
"num_tokens": 11368230.0,
|
|
"step": 5480
|
|
},
|
|
{
|
|
"entropy": 5.776658916473389,
|
|
"epoch": 0.4975507982583454,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.0004981314806952535,
|
|
"loss": 5.7504,
|
|
"mean_token_accuracy": 0.1563531845808029,
|
|
"num_tokens": 11377613.0,
|
|
"step": 5485
|
|
},
|
|
{
|
|
"entropy": 5.844314098358154,
|
|
"epoch": 0.49800435413642963,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.00049812731708386,
|
|
"loss": 5.6825,
|
|
"mean_token_accuracy": 0.15813061594963074,
|
|
"num_tokens": 11387898.0,
|
|
"step": 5490
|
|
},
|
|
{
|
|
"entropy": 5.868491315841675,
|
|
"epoch": 0.4984579100145138,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.0004981231488581367,
|
|
"loss": 5.7704,
|
|
"mean_token_accuracy": 0.1497861698269844,
|
|
"num_tokens": 11397725.0,
|
|
"step": 5495
|
|
},
|
|
{
|
|
"entropy": 5.815413761138916,
|
|
"epoch": 0.498911465892598,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 0.0004981189760181699,
|
|
"loss": 5.6501,
|
|
"mean_token_accuracy": 0.15616128146648406,
|
|
"num_tokens": 11407193.0,
|
|
"step": 5500
|
|
},
|
|
{
|
|
"entropy": 5.773203563690186,
|
|
"epoch": 0.49936502177068215,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004981147985640456,
|
|
"loss": 5.6549,
|
|
"mean_token_accuracy": 0.151999793946743,
|
|
"num_tokens": 11417133.0,
|
|
"step": 5505
|
|
},
|
|
{
|
|
"entropy": 5.732791996002197,
|
|
"epoch": 0.4998185776487663,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.0004981106164958506,
|
|
"loss": 5.5816,
|
|
"mean_token_accuracy": 0.16263532042503356,
|
|
"num_tokens": 11428194.0,
|
|
"step": 5510
|
|
},
|
|
{
|
|
"entropy": 5.748931980133056,
|
|
"epoch": 0.5002721335268505,
|
|
"grad_norm": 2.828125,
|
|
"learning_rate": 0.0004981064298136712,
|
|
"loss": 5.6426,
|
|
"mean_token_accuracy": 0.15091810673475264,
|
|
"num_tokens": 11438026.0,
|
|
"step": 5515
|
|
},
|
|
{
|
|
"entropy": 5.770444059371949,
|
|
"epoch": 0.5007256894049347,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 0.0004981022385175939,
|
|
"loss": 5.7004,
|
|
"mean_token_accuracy": 0.15599464625120163,
|
|
"num_tokens": 11447455.0,
|
|
"step": 5520
|
|
},
|
|
{
|
|
"entropy": 5.82069878578186,
|
|
"epoch": 0.5011792452830188,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.0004980980426077054,
|
|
"loss": 5.6978,
|
|
"mean_token_accuracy": 0.15249895304441452,
|
|
"num_tokens": 11458331.0,
|
|
"step": 5525
|
|
},
|
|
{
|
|
"entropy": 5.813779544830322,
|
|
"epoch": 0.5016328011611031,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.0004980938420840926,
|
|
"loss": 5.654,
|
|
"mean_token_accuracy": 0.14837791472673417,
|
|
"num_tokens": 11468182.0,
|
|
"step": 5530
|
|
},
|
|
{
|
|
"entropy": 5.819776010513306,
|
|
"epoch": 0.5020863570391872,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004980896369468423,
|
|
"loss": 5.6735,
|
|
"mean_token_accuracy": 0.15344102680683136,
|
|
"num_tokens": 11478727.0,
|
|
"step": 5535
|
|
},
|
|
{
|
|
"entropy": 5.769030523300171,
|
|
"epoch": 0.5025399129172714,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004980854271960415,
|
|
"loss": 5.6935,
|
|
"mean_token_accuracy": 0.1578574597835541,
|
|
"num_tokens": 11489085.0,
|
|
"step": 5540
|
|
},
|
|
{
|
|
"entropy": 5.785058164596558,
|
|
"epoch": 0.5029934687953556,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004980812128317772,
|
|
"loss": 5.7823,
|
|
"mean_token_accuracy": 0.14549713134765624,
|
|
"num_tokens": 11500354.0,
|
|
"step": 5545
|
|
},
|
|
{
|
|
"entropy": 5.875575017929077,
|
|
"epoch": 0.5034470246734397,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004980769938541364,
|
|
"loss": 5.6758,
|
|
"mean_token_accuracy": 0.15565661191940308,
|
|
"num_tokens": 11511272.0,
|
|
"step": 5550
|
|
},
|
|
{
|
|
"entropy": 5.820347309112549,
|
|
"epoch": 0.503900580551524,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004980727702632066,
|
|
"loss": 5.7794,
|
|
"mean_token_accuracy": 0.14426911622285843,
|
|
"num_tokens": 11521133.0,
|
|
"step": 5555
|
|
},
|
|
{
|
|
"entropy": 5.776409053802491,
|
|
"epoch": 0.5043541364296081,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.0004980685420590752,
|
|
"loss": 5.6803,
|
|
"mean_token_accuracy": 0.15292732566595077,
|
|
"num_tokens": 11531797.0,
|
|
"step": 5560
|
|
},
|
|
{
|
|
"entropy": 5.740556383132935,
|
|
"epoch": 0.5048076923076923,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004980643092418294,
|
|
"loss": 5.6319,
|
|
"mean_token_accuracy": 0.15992224663496019,
|
|
"num_tokens": 11540655.0,
|
|
"step": 5565
|
|
},
|
|
{
|
|
"entropy": 5.7666182041168215,
|
|
"epoch": 0.5052612481857764,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004980600718115568,
|
|
"loss": 5.6364,
|
|
"mean_token_accuracy": 0.1610444650053978,
|
|
"num_tokens": 11550697.0,
|
|
"step": 5570
|
|
},
|
|
{
|
|
"entropy": 5.862971830368042,
|
|
"epoch": 0.5057148040638607,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004980558297683452,
|
|
"loss": 5.6558,
|
|
"mean_token_accuracy": 0.15864361375570296,
|
|
"num_tokens": 11560643.0,
|
|
"step": 5575
|
|
},
|
|
{
|
|
"entropy": 5.893351984024048,
|
|
"epoch": 0.5061683599419449,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004980515831122822,
|
|
"loss": 5.7904,
|
|
"mean_token_accuracy": 0.1495205745100975,
|
|
"num_tokens": 11571823.0,
|
|
"step": 5580
|
|
},
|
|
{
|
|
"entropy": 5.69124813079834,
|
|
"epoch": 0.506621915820029,
|
|
"grad_norm": 2.703125,
|
|
"learning_rate": 0.0004980473318434555,
|
|
"loss": 5.5679,
|
|
"mean_token_accuracy": 0.15229919999837876,
|
|
"num_tokens": 11581342.0,
|
|
"step": 5585
|
|
},
|
|
{
|
|
"entropy": 5.670686101913452,
|
|
"epoch": 0.5070754716981132,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004980430759619532,
|
|
"loss": 5.6289,
|
|
"mean_token_accuracy": 0.15128677636384963,
|
|
"num_tokens": 11591683.0,
|
|
"step": 5590
|
|
},
|
|
{
|
|
"entropy": 5.732837772369384,
|
|
"epoch": 0.5075290275761973,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.0004980388154678633,
|
|
"loss": 5.6162,
|
|
"mean_token_accuracy": 0.15577002465724946,
|
|
"num_tokens": 11602416.0,
|
|
"step": 5595
|
|
},
|
|
{
|
|
"entropy": 5.8033887386322025,
|
|
"epoch": 0.5079825834542816,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.0004980345503612738,
|
|
"loss": 5.6906,
|
|
"mean_token_accuracy": 0.151105298101902,
|
|
"num_tokens": 11612686.0,
|
|
"step": 5600
|
|
},
|
|
{
|
|
"entropy": 5.788366889953613,
|
|
"epoch": 0.5084361393323658,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004980302806422729,
|
|
"loss": 5.6929,
|
|
"mean_token_accuracy": 0.15298312157392502,
|
|
"num_tokens": 11621501.0,
|
|
"step": 5605
|
|
},
|
|
{
|
|
"entropy": 5.7911474227905275,
|
|
"epoch": 0.5088896952104499,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004980260063109491,
|
|
"loss": 5.6866,
|
|
"mean_token_accuracy": 0.15597617030143737,
|
|
"num_tokens": 11631562.0,
|
|
"step": 5610
|
|
},
|
|
{
|
|
"entropy": 5.780478191375733,
|
|
"epoch": 0.5093432510885341,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004980217273673906,
|
|
"loss": 5.6583,
|
|
"mean_token_accuracy": 0.15059893652796746,
|
|
"num_tokens": 11641564.0,
|
|
"step": 5615
|
|
},
|
|
{
|
|
"entropy": 5.807359504699707,
|
|
"epoch": 0.5097968069666183,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004980174438116859,
|
|
"loss": 5.7122,
|
|
"mean_token_accuracy": 0.15435375571250914,
|
|
"num_tokens": 11651392.0,
|
|
"step": 5620
|
|
},
|
|
{
|
|
"entropy": 5.830365610122681,
|
|
"epoch": 0.5102503628447025,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004980131556439236,
|
|
"loss": 5.7075,
|
|
"mean_token_accuracy": 0.1523994840681553,
|
|
"num_tokens": 11661101.0,
|
|
"step": 5625
|
|
},
|
|
{
|
|
"entropy": 5.8104228496551515,
|
|
"epoch": 0.5107039187227866,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004980088628641925,
|
|
"loss": 5.6505,
|
|
"mean_token_accuracy": 0.15648772418498993,
|
|
"num_tokens": 11671812.0,
|
|
"step": 5630
|
|
},
|
|
{
|
|
"entropy": 5.764213562011719,
|
|
"epoch": 0.5111574746008708,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.0004980045654725812,
|
|
"loss": 5.5614,
|
|
"mean_token_accuracy": 0.16013796925544738,
|
|
"num_tokens": 11681549.0,
|
|
"step": 5635
|
|
},
|
|
{
|
|
"entropy": 5.734517049789429,
|
|
"epoch": 0.511611030478955,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004980002634691787,
|
|
"loss": 5.6323,
|
|
"mean_token_accuracy": 0.15375378280878066,
|
|
"num_tokens": 11692070.0,
|
|
"step": 5640
|
|
},
|
|
{
|
|
"entropy": 5.672871732711792,
|
|
"epoch": 0.5120645863570392,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.000497995956854074,
|
|
"loss": 5.6884,
|
|
"mean_token_accuracy": 0.15432974994182586,
|
|
"num_tokens": 11702826.0,
|
|
"step": 5645
|
|
},
|
|
{
|
|
"entropy": 5.854795503616333,
|
|
"epoch": 0.5125181422351234,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004979916456273561,
|
|
"loss": 5.8033,
|
|
"mean_token_accuracy": 0.1496042028069496,
|
|
"num_tokens": 11714368.0,
|
|
"step": 5650
|
|
},
|
|
{
|
|
"entropy": 5.9430516242980955,
|
|
"epoch": 0.5129716981132075,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004979873297891141,
|
|
"loss": 5.7142,
|
|
"mean_token_accuracy": 0.1523452430963516,
|
|
"num_tokens": 11724986.0,
|
|
"step": 5655
|
|
},
|
|
{
|
|
"entropy": 5.782175970077515,
|
|
"epoch": 0.5134252539912917,
|
|
"grad_norm": 4.1875,
|
|
"learning_rate": 0.0004979830093394372,
|
|
"loss": 5.6649,
|
|
"mean_token_accuracy": 0.15547989010810853,
|
|
"num_tokens": 11735056.0,
|
|
"step": 5660
|
|
},
|
|
{
|
|
"entropy": 5.754619359970093,
|
|
"epoch": 0.513878809869376,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.0004979786842784149,
|
|
"loss": 5.7305,
|
|
"mean_token_accuracy": 0.1475801281630993,
|
|
"num_tokens": 11746511.0,
|
|
"step": 5665
|
|
},
|
|
{
|
|
"entropy": 5.684448289871216,
|
|
"epoch": 0.5143323657474601,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004979743546061366,
|
|
"loss": 5.6343,
|
|
"mean_token_accuracy": 0.15331252962350844,
|
|
"num_tokens": 11755892.0,
|
|
"step": 5670
|
|
},
|
|
{
|
|
"entropy": 5.8178552150726315,
|
|
"epoch": 0.5147859216255443,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004979700203226918,
|
|
"loss": 5.7322,
|
|
"mean_token_accuracy": 0.14956021532416344,
|
|
"num_tokens": 11766452.0,
|
|
"step": 5675
|
|
},
|
|
{
|
|
"entropy": 5.790278959274292,
|
|
"epoch": 0.5152394775036284,
|
|
"grad_norm": 3.015625,
|
|
"learning_rate": 0.0004979656814281702,
|
|
"loss": 5.6442,
|
|
"mean_token_accuracy": 0.15524719655513763,
|
|
"num_tokens": 11776138.0,
|
|
"step": 5680
|
|
},
|
|
{
|
|
"entropy": 5.867595958709717,
|
|
"epoch": 0.5156930333817126,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004979613379226615,
|
|
"loss": 5.7289,
|
|
"mean_token_accuracy": 0.15170384347438812,
|
|
"num_tokens": 11786174.0,
|
|
"step": 5685
|
|
},
|
|
{
|
|
"entropy": 5.753278112411499,
|
|
"epoch": 0.5161465892597968,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.0004979569898062554,
|
|
"loss": 5.6281,
|
|
"mean_token_accuracy": 0.1571716770529747,
|
|
"num_tokens": 11796202.0,
|
|
"step": 5690
|
|
},
|
|
{
|
|
"entropy": 5.772783041000366,
|
|
"epoch": 0.516600145137881,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.000497952637079042,
|
|
"loss": 5.5941,
|
|
"mean_token_accuracy": 0.1638539105653763,
|
|
"num_tokens": 11806020.0,
|
|
"step": 5695
|
|
},
|
|
{
|
|
"entropy": 5.734279537200928,
|
|
"epoch": 0.5170537010159652,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004979482797411114,
|
|
"loss": 5.6517,
|
|
"mean_token_accuracy": 0.15160437747836114,
|
|
"num_tokens": 11815802.0,
|
|
"step": 5700
|
|
},
|
|
{
|
|
"entropy": 5.728960037231445,
|
|
"epoch": 0.5175072568940493,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004979439177925534,
|
|
"loss": 5.6584,
|
|
"mean_token_accuracy": 0.15317385345697404,
|
|
"num_tokens": 11827391.0,
|
|
"step": 5705
|
|
},
|
|
{
|
|
"entropy": 5.708126592636108,
|
|
"epoch": 0.5179608127721336,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.0004979395512334584,
|
|
"loss": 5.5692,
|
|
"mean_token_accuracy": 0.1625960573554039,
|
|
"num_tokens": 11837229.0,
|
|
"step": 5710
|
|
},
|
|
{
|
|
"entropy": 5.7941161632537845,
|
|
"epoch": 0.5184143686502177,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004979351800639166,
|
|
"loss": 5.734,
|
|
"mean_token_accuracy": 0.15362083166837692,
|
|
"num_tokens": 11847622.0,
|
|
"step": 5715
|
|
},
|
|
{
|
|
"entropy": 5.8385223865509035,
|
|
"epoch": 0.5188679245283019,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004979308042840186,
|
|
"loss": 5.7124,
|
|
"mean_token_accuracy": 0.15736438930034638,
|
|
"num_tokens": 11858013.0,
|
|
"step": 5720
|
|
},
|
|
{
|
|
"entropy": 5.809688663482666,
|
|
"epoch": 0.519321480406386,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.0004979264238938547,
|
|
"loss": 5.6807,
|
|
"mean_token_accuracy": 0.15295029133558274,
|
|
"num_tokens": 11866763.0,
|
|
"step": 5725
|
|
},
|
|
{
|
|
"entropy": 5.701699304580688,
|
|
"epoch": 0.5197750362844702,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004979220388935155,
|
|
"loss": 5.6291,
|
|
"mean_token_accuracy": 0.15494942665100098,
|
|
"num_tokens": 11877731.0,
|
|
"step": 5730
|
|
},
|
|
{
|
|
"entropy": 5.830405569076538,
|
|
"epoch": 0.5202285921625545,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004979176492830918,
|
|
"loss": 5.6566,
|
|
"mean_token_accuracy": 0.1564646691083908,
|
|
"num_tokens": 11887698.0,
|
|
"step": 5735
|
|
},
|
|
{
|
|
"entropy": 5.837483501434326,
|
|
"epoch": 0.5206821480406386,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.0004979132550626742,
|
|
"loss": 5.7678,
|
|
"mean_token_accuracy": 0.15171240121126175,
|
|
"num_tokens": 11898559.0,
|
|
"step": 5740
|
|
},
|
|
{
|
|
"entropy": 5.760894012451172,
|
|
"epoch": 0.5211357039187228,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004979088562323538,
|
|
"loss": 5.6517,
|
|
"mean_token_accuracy": 0.1545734629034996,
|
|
"num_tokens": 11908547.0,
|
|
"step": 5745
|
|
},
|
|
{
|
|
"entropy": 5.849686622619629,
|
|
"epoch": 0.5215892597968069,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004979044527922214,
|
|
"loss": 5.691,
|
|
"mean_token_accuracy": 0.16176672726869584,
|
|
"num_tokens": 11918447.0,
|
|
"step": 5750
|
|
},
|
|
{
|
|
"entropy": 5.835568428039551,
|
|
"epoch": 0.5220428156748912,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004979000447423681,
|
|
"loss": 5.718,
|
|
"mean_token_accuracy": 0.15124733746051788,
|
|
"num_tokens": 11929439.0,
|
|
"step": 5755
|
|
},
|
|
{
|
|
"entropy": 5.731830263137818,
|
|
"epoch": 0.5224963715529753,
|
|
"grad_norm": 2.609375,
|
|
"learning_rate": 0.0004978956320828851,
|
|
"loss": 5.6411,
|
|
"mean_token_accuracy": 0.15208978950977325,
|
|
"num_tokens": 11940693.0,
|
|
"step": 5760
|
|
},
|
|
{
|
|
"entropy": 5.763946151733398,
|
|
"epoch": 0.5229499274310595,
|
|
"grad_norm": 3.0,
|
|
"learning_rate": 0.0004978912148138637,
|
|
"loss": 5.597,
|
|
"mean_token_accuracy": 0.15466375052928924,
|
|
"num_tokens": 11949934.0,
|
|
"step": 5765
|
|
},
|
|
{
|
|
"entropy": 5.754511499404908,
|
|
"epoch": 0.5234034833091437,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.000497886792935395,
|
|
"loss": 5.7148,
|
|
"mean_token_accuracy": 0.15965479016304016,
|
|
"num_tokens": 11960245.0,
|
|
"step": 5770
|
|
},
|
|
{
|
|
"entropy": 5.835350847244262,
|
|
"epoch": 0.5238570391872278,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.0004978823664475707,
|
|
"loss": 5.6011,
|
|
"mean_token_accuracy": 0.1534401074051857,
|
|
"num_tokens": 11970364.0,
|
|
"step": 5775
|
|
},
|
|
{
|
|
"entropy": 5.846774005889893,
|
|
"epoch": 0.5243105950653121,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004978779353504824,
|
|
"loss": 5.7091,
|
|
"mean_token_accuracy": 0.14929343163967132,
|
|
"num_tokens": 11981073.0,
|
|
"step": 5780
|
|
},
|
|
{
|
|
"entropy": 5.7207191467285154,
|
|
"epoch": 0.5247641509433962,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.0004978734996442214,
|
|
"loss": 5.6885,
|
|
"mean_token_accuracy": 0.14204260632395743,
|
|
"num_tokens": 11991420.0,
|
|
"step": 5785
|
|
},
|
|
{
|
|
"entropy": 5.767483806610107,
|
|
"epoch": 0.5252177068214804,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004978690593288798,
|
|
"loss": 5.7101,
|
|
"mean_token_accuracy": 0.14270815402269363,
|
|
"num_tokens": 12002325.0,
|
|
"step": 5790
|
|
},
|
|
{
|
|
"entropy": 5.838377571105957,
|
|
"epoch": 0.5256712626995645,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004978646144045491,
|
|
"loss": 5.6622,
|
|
"mean_token_accuracy": 0.15048326328396797,
|
|
"num_tokens": 12013027.0,
|
|
"step": 5795
|
|
},
|
|
{
|
|
"entropy": 5.8212944030761715,
|
|
"epoch": 0.5261248185776488,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.0004978601648713215,
|
|
"loss": 5.6707,
|
|
"mean_token_accuracy": 0.15283343344926834,
|
|
"num_tokens": 12023821.0,
|
|
"step": 5800
|
|
},
|
|
{
|
|
"entropy": 5.801069211959839,
|
|
"epoch": 0.526578374455733,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004978557107292889,
|
|
"loss": 5.6653,
|
|
"mean_token_accuracy": 0.15791814774274826,
|
|
"num_tokens": 12034315.0,
|
|
"step": 5805
|
|
},
|
|
{
|
|
"entropy": 5.732563400268555,
|
|
"epoch": 0.5270319303338171,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.0004978512519785433,
|
|
"loss": 5.646,
|
|
"mean_token_accuracy": 0.1561321035027504,
|
|
"num_tokens": 12045172.0,
|
|
"step": 5810
|
|
},
|
|
{
|
|
"entropy": 5.74445161819458,
|
|
"epoch": 0.5274854862119013,
|
|
"grad_norm": 3.703125,
|
|
"learning_rate": 0.000497846788619177,
|
|
"loss": 5.6418,
|
|
"mean_token_accuracy": 0.1543836459517479,
|
|
"num_tokens": 12055809.0,
|
|
"step": 5815
|
|
},
|
|
{
|
|
"entropy": 5.775337076187133,
|
|
"epoch": 0.5279390420899854,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.0004978423206512825,
|
|
"loss": 5.6212,
|
|
"mean_token_accuracy": 0.1571818545460701,
|
|
"num_tokens": 12065649.0,
|
|
"step": 5820
|
|
},
|
|
{
|
|
"entropy": 5.770995473861694,
|
|
"epoch": 0.5283925979680697,
|
|
"grad_norm": 2.546875,
|
|
"learning_rate": 0.000497837848074952,
|
|
"loss": 5.7297,
|
|
"mean_token_accuracy": 0.14517660439014435,
|
|
"num_tokens": 12076600.0,
|
|
"step": 5825
|
|
},
|
|
{
|
|
"entropy": 5.794981956481934,
|
|
"epoch": 0.5288461538461539,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.000497833370890278,
|
|
"loss": 5.7276,
|
|
"mean_token_accuracy": 0.1495457574725151,
|
|
"num_tokens": 12087991.0,
|
|
"step": 5830
|
|
},
|
|
{
|
|
"entropy": 5.7484033584594725,
|
|
"epoch": 0.529299709724238,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.0004978288890973529,
|
|
"loss": 5.5982,
|
|
"mean_token_accuracy": 0.15729666352272034,
|
|
"num_tokens": 12097737.0,
|
|
"step": 5835
|
|
},
|
|
{
|
|
"entropy": 5.734858179092408,
|
|
"epoch": 0.5297532656023222,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004978244026962698,
|
|
"loss": 5.5958,
|
|
"mean_token_accuracy": 0.1559059202671051,
|
|
"num_tokens": 12108088.0,
|
|
"step": 5840
|
|
},
|
|
{
|
|
"entropy": 5.824561834335327,
|
|
"epoch": 0.5302068214804064,
|
|
"grad_norm": 2.578125,
|
|
"learning_rate": 0.0004978199116871212,
|
|
"loss": 5.7516,
|
|
"mean_token_accuracy": 0.14970595389604568,
|
|
"num_tokens": 12118633.0,
|
|
"step": 5845
|
|
},
|
|
{
|
|
"entropy": 5.833733129501343,
|
|
"epoch": 0.5306603773584906,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.00049781541607,
|
|
"loss": 5.7448,
|
|
"mean_token_accuracy": 0.15598972886800766,
|
|
"num_tokens": 12129293.0,
|
|
"step": 5850
|
|
},
|
|
{
|
|
"entropy": 5.885995531082154,
|
|
"epoch": 0.5311139332365747,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.0004978109158449993,
|
|
"loss": 5.6941,
|
|
"mean_token_accuracy": 0.15428496152162552,
|
|
"num_tokens": 12140003.0,
|
|
"step": 5855
|
|
},
|
|
{
|
|
"entropy": 5.804030895233154,
|
|
"epoch": 0.5315674891146589,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004978064110122121,
|
|
"loss": 5.74,
|
|
"mean_token_accuracy": 0.1436428152024746,
|
|
"num_tokens": 12151367.0,
|
|
"step": 5860
|
|
},
|
|
{
|
|
"entropy": 5.767576074600219,
|
|
"epoch": 0.532021044992743,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004978019015717314,
|
|
"loss": 5.6862,
|
|
"mean_token_accuracy": 0.14855829924345015,
|
|
"num_tokens": 12162161.0,
|
|
"step": 5865
|
|
},
|
|
{
|
|
"entropy": 5.821201229095459,
|
|
"epoch": 0.5324746008708273,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004977973875236508,
|
|
"loss": 5.6878,
|
|
"mean_token_accuracy": 0.15125086307525634,
|
|
"num_tokens": 12172297.0,
|
|
"step": 5870
|
|
},
|
|
{
|
|
"entropy": 5.777795076370239,
|
|
"epoch": 0.5329281567489115,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004977928688680634,
|
|
"loss": 5.6422,
|
|
"mean_token_accuracy": 0.15870457887649536,
|
|
"num_tokens": 12182204.0,
|
|
"step": 5875
|
|
},
|
|
{
|
|
"entropy": 5.736477279663086,
|
|
"epoch": 0.5333817126269956,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004977883456050626,
|
|
"loss": 5.6563,
|
|
"mean_token_accuracy": 0.15875795036554335,
|
|
"num_tokens": 12192448.0,
|
|
"step": 5880
|
|
},
|
|
{
|
|
"entropy": 5.804166078567505,
|
|
"epoch": 0.5338352685050798,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.000497783817734742,
|
|
"loss": 5.664,
|
|
"mean_token_accuracy": 0.15547409802675247,
|
|
"num_tokens": 12202827.0,
|
|
"step": 5885
|
|
},
|
|
{
|
|
"entropy": 5.754812479019165,
|
|
"epoch": 0.534288824383164,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004977792852571954,
|
|
"loss": 5.6518,
|
|
"mean_token_accuracy": 0.159761381149292,
|
|
"num_tokens": 12213313.0,
|
|
"step": 5890
|
|
},
|
|
{
|
|
"entropy": 5.819279527664184,
|
|
"epoch": 0.5347423802612482,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004977747481725164,
|
|
"loss": 5.6568,
|
|
"mean_token_accuracy": 0.15718502700328826,
|
|
"num_tokens": 12223558.0,
|
|
"step": 5895
|
|
},
|
|
{
|
|
"entropy": 5.9023620128631595,
|
|
"epoch": 0.5351959361393324,
|
|
"grad_norm": 2.53125,
|
|
"learning_rate": 0.0004977702064807987,
|
|
"loss": 5.7099,
|
|
"mean_token_accuracy": 0.15210497453808786,
|
|
"num_tokens": 12235367.0,
|
|
"step": 5900
|
|
},
|
|
{
|
|
"entropy": 5.8268383026123045,
|
|
"epoch": 0.5356494920174165,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004977656601821366,
|
|
"loss": 5.6465,
|
|
"mean_token_accuracy": 0.15551152527332307,
|
|
"num_tokens": 12245690.0,
|
|
"step": 5905
|
|
},
|
|
{
|
|
"entropy": 5.702606582641602,
|
|
"epoch": 0.5361030478955007,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004977611092766238,
|
|
"loss": 5.5843,
|
|
"mean_token_accuracy": 0.15972213745117186,
|
|
"num_tokens": 12256773.0,
|
|
"step": 5910
|
|
},
|
|
{
|
|
"entropy": 5.649114608764648,
|
|
"epoch": 0.5365566037735849,
|
|
"grad_norm": 3.546875,
|
|
"learning_rate": 0.0004977565537643544,
|
|
"loss": 5.6369,
|
|
"mean_token_accuracy": 0.15980817824602128,
|
|
"num_tokens": 12267123.0,
|
|
"step": 5915
|
|
},
|
|
{
|
|
"entropy": 5.711336660385132,
|
|
"epoch": 0.5370101596516691,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.0004977519936454227,
|
|
"loss": 5.5961,
|
|
"mean_token_accuracy": 0.15738640278577803,
|
|
"num_tokens": 12276883.0,
|
|
"step": 5920
|
|
},
|
|
{
|
|
"entropy": 5.780760192871094,
|
|
"epoch": 0.5374637155297532,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.0004977474289199231,
|
|
"loss": 5.6971,
|
|
"mean_token_accuracy": 0.15041918009519578,
|
|
"num_tokens": 12286608.0,
|
|
"step": 5925
|
|
},
|
|
{
|
|
"entropy": 5.856068229675293,
|
|
"epoch": 0.5379172714078374,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004977428595879499,
|
|
"loss": 5.7392,
|
|
"mean_token_accuracy": 0.14627672284841536,
|
|
"num_tokens": 12297005.0,
|
|
"step": 5930
|
|
},
|
|
{
|
|
"entropy": 5.926909971237182,
|
|
"epoch": 0.5383708272859217,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004977382856495975,
|
|
"loss": 5.7715,
|
|
"mean_token_accuracy": 0.14751360639929773,
|
|
"num_tokens": 12307844.0,
|
|
"step": 5935
|
|
},
|
|
{
|
|
"entropy": 5.734508275985718,
|
|
"epoch": 0.5388243831640058,
|
|
"grad_norm": 3.265625,
|
|
"learning_rate": 0.0004977337071049606,
|
|
"loss": 5.602,
|
|
"mean_token_accuracy": 0.15361868292093278,
|
|
"num_tokens": 12318593.0,
|
|
"step": 5940
|
|
},
|
|
{
|
|
"entropy": 5.803959321975708,
|
|
"epoch": 0.53927793904209,
|
|
"grad_norm": 2.890625,
|
|
"learning_rate": 0.000497729123954134,
|
|
"loss": 5.738,
|
|
"mean_token_accuracy": 0.1524718463420868,
|
|
"num_tokens": 12329225.0,
|
|
"step": 5945
|
|
},
|
|
{
|
|
"entropy": 5.830508041381836,
|
|
"epoch": 0.5397314949201741,
|
|
"grad_norm": 3.25,
|
|
"learning_rate": 0.0004977245361972123,
|
|
"loss": 5.6175,
|
|
"mean_token_accuracy": 0.15675749778747558,
|
|
"num_tokens": 12338825.0,
|
|
"step": 5950
|
|
},
|
|
{
|
|
"entropy": 5.816405010223389,
|
|
"epoch": 0.5401850507982583,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004977199438342904,
|
|
"loss": 5.713,
|
|
"mean_token_accuracy": 0.15117572098970414,
|
|
"num_tokens": 12349537.0,
|
|
"step": 5955
|
|
},
|
|
{
|
|
"entropy": 5.80316424369812,
|
|
"epoch": 0.5406386066763426,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.0004977153468654634,
|
|
"loss": 5.6903,
|
|
"mean_token_accuracy": 0.15550419837236404,
|
|
"num_tokens": 12360274.0,
|
|
"step": 5960
|
|
},
|
|
{
|
|
"entropy": 5.836670064926148,
|
|
"epoch": 0.5410921625544267,
|
|
"grad_norm": 3.421875,
|
|
"learning_rate": 0.0004977107452908262,
|
|
"loss": 5.7279,
|
|
"mean_token_accuracy": 0.14425202012062072,
|
|
"num_tokens": 12371575.0,
|
|
"step": 5965
|
|
},
|
|
{
|
|
"entropy": 5.84296875,
|
|
"epoch": 0.5415457184325109,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.000497706139110474,
|
|
"loss": 5.6996,
|
|
"mean_token_accuracy": 0.14984800666570663,
|
|
"num_tokens": 12383486.0,
|
|
"step": 5970
|
|
},
|
|
{
|
|
"entropy": 5.789977788925171,
|
|
"epoch": 0.541999274310595,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.0004977015283245021,
|
|
"loss": 5.612,
|
|
"mean_token_accuracy": 0.1607540026307106,
|
|
"num_tokens": 12394063.0,
|
|
"step": 5975
|
|
},
|
|
{
|
|
"entropy": 5.716253280639648,
|
|
"epoch": 0.5424528301886793,
|
|
"grad_norm": 3.890625,
|
|
"learning_rate": 0.0004976969129330059,
|
|
"loss": 5.6359,
|
|
"mean_token_accuracy": 0.15388800203800201,
|
|
"num_tokens": 12403413.0,
|
|
"step": 5980
|
|
},
|
|
{
|
|
"entropy": 5.834080648422241,
|
|
"epoch": 0.5429063860667634,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.0004976922929360808,
|
|
"loss": 5.6923,
|
|
"mean_token_accuracy": 0.15336927622556687,
|
|
"num_tokens": 12414099.0,
|
|
"step": 5985
|
|
},
|
|
{
|
|
"entropy": 5.805603790283203,
|
|
"epoch": 0.5433599419448476,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004976876683338222,
|
|
"loss": 5.5614,
|
|
"mean_token_accuracy": 0.15590637177228928,
|
|
"num_tokens": 12423665.0,
|
|
"step": 5990
|
|
},
|
|
{
|
|
"entropy": 5.691508340835571,
|
|
"epoch": 0.5438134978229318,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.000497683039126326,
|
|
"loss": 5.6086,
|
|
"mean_token_accuracy": 0.15369207561016082,
|
|
"num_tokens": 12433614.0,
|
|
"step": 5995
|
|
},
|
|
{
|
|
"entropy": 5.756490850448609,
|
|
"epoch": 0.5442670537010159,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004976784053136878,
|
|
"loss": 5.6433,
|
|
"mean_token_accuracy": 0.15434167087078093,
|
|
"num_tokens": 12443669.0,
|
|
"step": 6000
|
|
},
|
|
{
|
|
"epoch": 0.5442670537010159,
|
|
"eval_entropy": 5.587137994183674,
|
|
"eval_loss": 5.719257831573486,
|
|
"eval_mean_token_accuracy": 0.15730181987401587,
|
|
"eval_num_tokens": 12443669.0,
|
|
"eval_runtime": 26.845,
|
|
"eval_samples_per_second": 1317.191,
|
|
"eval_steps_per_second": 164.649,
|
|
"step": 6000
|
|
},
|
|
{
|
|
"entropy": 5.747743368148804,
|
|
"epoch": 0.5447206095791002,
|
|
"grad_norm": 2.6875,
|
|
"learning_rate": 0.0004976737668960034,
|
|
"loss": 5.6903,
|
|
"mean_token_accuracy": 0.1508556678891182,
|
|
"num_tokens": 12453555.0,
|
|
"step": 6005
|
|
},
|
|
{
|
|
"entropy": 5.83550181388855,
|
|
"epoch": 0.5451741654571843,
|
|
"grad_norm": 3.109375,
|
|
"learning_rate": 0.0004976691238733688,
|
|
"loss": 5.6317,
|
|
"mean_token_accuracy": 0.1612621873617172,
|
|
"num_tokens": 12463940.0,
|
|
"step": 6010
|
|
},
|
|
{
|
|
"entropy": 5.80387282371521,
|
|
"epoch": 0.5456277213352685,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.00049766447624588,
|
|
"loss": 5.6959,
|
|
"mean_token_accuracy": 0.14484051018953323,
|
|
"num_tokens": 12474069.0,
|
|
"step": 6015
|
|
},
|
|
{
|
|
"entropy": 5.817902135848999,
|
|
"epoch": 0.5460812772133526,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.000497659824013633,
|
|
"loss": 5.7273,
|
|
"mean_token_accuracy": 0.15419357419013976,
|
|
"num_tokens": 12485249.0,
|
|
"step": 6020
|
|
},
|
|
{
|
|
"entropy": 5.867844581604004,
|
|
"epoch": 0.5465348330914369,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004976551671767241,
|
|
"loss": 5.7619,
|
|
"mean_token_accuracy": 0.15312980264425277,
|
|
"num_tokens": 12496347.0,
|
|
"step": 6025
|
|
},
|
|
{
|
|
"entropy": 5.7992781639099125,
|
|
"epoch": 0.5469883889695211,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 0.0004976505057352496,
|
|
"loss": 5.6997,
|
|
"mean_token_accuracy": 0.15197809413075447,
|
|
"num_tokens": 12506573.0,
|
|
"step": 6030
|
|
},
|
|
{
|
|
"entropy": 5.7852293968200685,
|
|
"epoch": 0.5474419448476052,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004976458396893059,
|
|
"loss": 5.5997,
|
|
"mean_token_accuracy": 0.1561036542057991,
|
|
"num_tokens": 12516353.0,
|
|
"step": 6035
|
|
},
|
|
{
|
|
"entropy": 5.737716913223267,
|
|
"epoch": 0.5478955007256894,
|
|
"grad_norm": 2.65625,
|
|
"learning_rate": 0.0004976411690389896,
|
|
"loss": 5.6684,
|
|
"mean_token_accuracy": 0.151264488697052,
|
|
"num_tokens": 12526799.0,
|
|
"step": 6040
|
|
},
|
|
{
|
|
"entropy": 5.705054235458374,
|
|
"epoch": 0.5483490566037735,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.000497636493784397,
|
|
"loss": 5.5954,
|
|
"mean_token_accuracy": 0.15787012726068497,
|
|
"num_tokens": 12536603.0,
|
|
"step": 6045
|
|
},
|
|
{
|
|
"entropy": 5.8062633037567135,
|
|
"epoch": 0.5488026124818578,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004976318139256251,
|
|
"loss": 5.676,
|
|
"mean_token_accuracy": 0.15345212668180466,
|
|
"num_tokens": 12547287.0,
|
|
"step": 6050
|
|
},
|
|
{
|
|
"entropy": 5.740772533416748,
|
|
"epoch": 0.549256168359942,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004976271294627706,
|
|
"loss": 5.5663,
|
|
"mean_token_accuracy": 0.1586030140519142,
|
|
"num_tokens": 12557098.0,
|
|
"step": 6055
|
|
},
|
|
{
|
|
"entropy": 5.724259376525879,
|
|
"epoch": 0.5497097242380261,
|
|
"grad_norm": 2.5625,
|
|
"learning_rate": 0.0004976224403959303,
|
|
"loss": 5.664,
|
|
"mean_token_accuracy": 0.15680968761444092,
|
|
"num_tokens": 12567048.0,
|
|
"step": 6060
|
|
},
|
|
{
|
|
"entropy": 5.797675037384034,
|
|
"epoch": 0.5501632801161103,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004976177467252012,
|
|
"loss": 5.6968,
|
|
"mean_token_accuracy": 0.15028865933418273,
|
|
"num_tokens": 12576131.0,
|
|
"step": 6065
|
|
},
|
|
{
|
|
"entropy": 5.885581970214844,
|
|
"epoch": 0.5506168359941945,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004976130484506804,
|
|
"loss": 5.8047,
|
|
"mean_token_accuracy": 0.14640149623155593,
|
|
"num_tokens": 12587719.0,
|
|
"step": 6070
|
|
},
|
|
{
|
|
"entropy": 5.893944358825683,
|
|
"epoch": 0.5510703918722787,
|
|
"grad_norm": 2.8125,
|
|
"learning_rate": 0.0004976083455724649,
|
|
"loss": 5.6677,
|
|
"mean_token_accuracy": 0.15215557664632798,
|
|
"num_tokens": 12597247.0,
|
|
"step": 6075
|
|
},
|
|
{
|
|
"entropy": 5.774308824539185,
|
|
"epoch": 0.5515239477503628,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.0004976036380906523,
|
|
"loss": 5.6777,
|
|
"mean_token_accuracy": 0.15329722911119462,
|
|
"num_tokens": 12606742.0,
|
|
"step": 6080
|
|
},
|
|
{
|
|
"entropy": 5.726920127868652,
|
|
"epoch": 0.551977503628447,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.0004975989260053395,
|
|
"loss": 5.625,
|
|
"mean_token_accuracy": 0.15485107749700547,
|
|
"num_tokens": 12617564.0,
|
|
"step": 6085
|
|
},
|
|
{
|
|
"entropy": 5.780449104309082,
|
|
"epoch": 0.5524310595065312,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.0004975942093166242,
|
|
"loss": 5.6776,
|
|
"mean_token_accuracy": 0.15466462224721908,
|
|
"num_tokens": 12628374.0,
|
|
"step": 6090
|
|
},
|
|
{
|
|
"entropy": 5.843764591217041,
|
|
"epoch": 0.5528846153846154,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004975894880246041,
|
|
"loss": 5.678,
|
|
"mean_token_accuracy": 0.15257733315229416,
|
|
"num_tokens": 12638801.0,
|
|
"step": 6095
|
|
},
|
|
{
|
|
"entropy": 5.763158369064331,
|
|
"epoch": 0.5533381712626996,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004975847621293766,
|
|
"loss": 5.6185,
|
|
"mean_token_accuracy": 0.16029703468084336,
|
|
"num_tokens": 12649044.0,
|
|
"step": 6100
|
|
},
|
|
{
|
|
"entropy": 5.767442750930786,
|
|
"epoch": 0.5537917271407837,
|
|
"grad_norm": 3.8125,
|
|
"learning_rate": 0.0004975800316310394,
|
|
"loss": 5.6621,
|
|
"mean_token_accuracy": 0.15183469504117966,
|
|
"num_tokens": 12659736.0,
|
|
"step": 6105
|
|
},
|
|
{
|
|
"entropy": 5.787349843978882,
|
|
"epoch": 0.5542452830188679,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004975752965296906,
|
|
"loss": 5.6967,
|
|
"mean_token_accuracy": 0.15557172298431396,
|
|
"num_tokens": 12669667.0,
|
|
"step": 6110
|
|
},
|
|
{
|
|
"entropy": 5.911172533035279,
|
|
"epoch": 0.5546988388969522,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004975705568254278,
|
|
"loss": 5.8139,
|
|
"mean_token_accuracy": 0.1463129013776779,
|
|
"num_tokens": 12679630.0,
|
|
"step": 6115
|
|
},
|
|
{
|
|
"entropy": 5.790578985214234,
|
|
"epoch": 0.5551523947750363,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.0004975658125183493,
|
|
"loss": 5.596,
|
|
"mean_token_accuracy": 0.15484105199575424,
|
|
"num_tokens": 12690084.0,
|
|
"step": 6120
|
|
},
|
|
{
|
|
"entropy": 5.8737493515014645,
|
|
"epoch": 0.5556059506531205,
|
|
"grad_norm": 2.671875,
|
|
"learning_rate": 0.000497561063608553,
|
|
"loss": 5.7522,
|
|
"mean_token_accuracy": 0.1477195903658867,
|
|
"num_tokens": 12700862.0,
|
|
"step": 6125
|
|
},
|
|
{
|
|
"entropy": 5.826459360122681,
|
|
"epoch": 0.5560595065312046,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004975563100961372,
|
|
"loss": 5.6197,
|
|
"mean_token_accuracy": 0.15493035316467285,
|
|
"num_tokens": 12711395.0,
|
|
"step": 6130
|
|
},
|
|
{
|
|
"entropy": 5.814093589782715,
|
|
"epoch": 0.5565130624092888,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004975515519812002,
|
|
"loss": 5.7067,
|
|
"mean_token_accuracy": 0.15628682374954223,
|
|
"num_tokens": 12721372.0,
|
|
"step": 6135
|
|
},
|
|
{
|
|
"entropy": 5.722448396682739,
|
|
"epoch": 0.556966618287373,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004975467892638402,
|
|
"loss": 5.6678,
|
|
"mean_token_accuracy": 0.15252027064561843,
|
|
"num_tokens": 12731822.0,
|
|
"step": 6140
|
|
},
|
|
{
|
|
"entropy": 5.7366180419921875,
|
|
"epoch": 0.5574201741654572,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004975420219441561,
|
|
"loss": 5.6571,
|
|
"mean_token_accuracy": 0.1535831645131111,
|
|
"num_tokens": 12741987.0,
|
|
"step": 6145
|
|
},
|
|
{
|
|
"entropy": 5.875377511978149,
|
|
"epoch": 0.5578737300435413,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004975372500222462,
|
|
"loss": 5.781,
|
|
"mean_token_accuracy": 0.14846161007881165,
|
|
"num_tokens": 12752412.0,
|
|
"step": 6150
|
|
},
|
|
{
|
|
"entropy": 5.8635846138000485,
|
|
"epoch": 0.5583272859216255,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004975324734982094,
|
|
"loss": 5.7973,
|
|
"mean_token_accuracy": 0.1468811199069023,
|
|
"num_tokens": 12762464.0,
|
|
"step": 6155
|
|
},
|
|
{
|
|
"entropy": 5.913093519210816,
|
|
"epoch": 0.5587808417997098,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004975276923721442,
|
|
"loss": 5.7736,
|
|
"mean_token_accuracy": 0.15110185295343398,
|
|
"num_tokens": 12772923.0,
|
|
"step": 6160
|
|
},
|
|
{
|
|
"entropy": 5.861691427230835,
|
|
"epoch": 0.5592343976777939,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004975229066441496,
|
|
"loss": 5.7098,
|
|
"mean_token_accuracy": 0.14898271560668946,
|
|
"num_tokens": 12783036.0,
|
|
"step": 6165
|
|
},
|
|
{
|
|
"entropy": 5.722401142120361,
|
|
"epoch": 0.5596879535558781,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.0004975181163143247,
|
|
"loss": 5.6454,
|
|
"mean_token_accuracy": 0.1472291201353073,
|
|
"num_tokens": 12794281.0,
|
|
"step": 6170
|
|
},
|
|
{
|
|
"entropy": 5.76973524093628,
|
|
"epoch": 0.5601415094339622,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004975133213827684,
|
|
"loss": 5.6034,
|
|
"mean_token_accuracy": 0.16035190224647522,
|
|
"num_tokens": 12803606.0,
|
|
"step": 6175
|
|
},
|
|
{
|
|
"entropy": 5.7982298851013185,
|
|
"epoch": 0.5605950653120464,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.0004975085218495798,
|
|
"loss": 5.6517,
|
|
"mean_token_accuracy": 0.15427016317844391,
|
|
"num_tokens": 12813402.0,
|
|
"step": 6180
|
|
},
|
|
{
|
|
"entropy": 5.7683093547821045,
|
|
"epoch": 0.5610486211901307,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004975037177148585,
|
|
"loss": 5.6427,
|
|
"mean_token_accuracy": 0.15330003201961517,
|
|
"num_tokens": 12823510.0,
|
|
"step": 6185
|
|
},
|
|
{
|
|
"entropy": 5.8773030757904055,
|
|
"epoch": 0.5615021770682148,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.0004974989089787035,
|
|
"loss": 5.7297,
|
|
"mean_token_accuracy": 0.14998237788677216,
|
|
"num_tokens": 12834677.0,
|
|
"step": 6190
|
|
},
|
|
{
|
|
"entropy": 5.86367564201355,
|
|
"epoch": 0.561955732946299,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004974940956412143,
|
|
"loss": 5.734,
|
|
"mean_token_accuracy": 0.15423496663570405,
|
|
"num_tokens": 12845050.0,
|
|
"step": 6195
|
|
},
|
|
{
|
|
"entropy": 5.822741508483887,
|
|
"epoch": 0.5624092888243831,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004974892777024905,
|
|
"loss": 5.7878,
|
|
"mean_token_accuracy": 0.14614235013723373,
|
|
"num_tokens": 12854285.0,
|
|
"step": 6200
|
|
},
|
|
{
|
|
"entropy": 5.827732372283935,
|
|
"epoch": 0.5628628447024674,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004974844551626318,
|
|
"loss": 5.6608,
|
|
"mean_token_accuracy": 0.14994238913059235,
|
|
"num_tokens": 12864299.0,
|
|
"step": 6205
|
|
},
|
|
{
|
|
"entropy": 5.783141660690307,
|
|
"epoch": 0.5633164005805515,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004974796280217379,
|
|
"loss": 5.6923,
|
|
"mean_token_accuracy": 0.15380887687206268,
|
|
"num_tokens": 12875047.0,
|
|
"step": 6210
|
|
},
|
|
{
|
|
"entropy": 5.817963314056397,
|
|
"epoch": 0.5637699564586357,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004974747962799086,
|
|
"loss": 5.7046,
|
|
"mean_token_accuracy": 0.15918388664722444,
|
|
"num_tokens": 12884897.0,
|
|
"step": 6215
|
|
},
|
|
{
|
|
"entropy": 5.836350059509277,
|
|
"epoch": 0.5642235123367199,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004974699599372437,
|
|
"loss": 5.5782,
|
|
"mean_token_accuracy": 0.15397312864661217,
|
|
"num_tokens": 12894323.0,
|
|
"step": 6220
|
|
},
|
|
{
|
|
"entropy": 5.742547225952149,
|
|
"epoch": 0.564677068214804,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004974651189938434,
|
|
"loss": 5.7574,
|
|
"mean_token_accuracy": 0.15137399286031722,
|
|
"num_tokens": 12904830.0,
|
|
"step": 6225
|
|
},
|
|
{
|
|
"entropy": 5.7252754211425785,
|
|
"epoch": 0.5651306240928883,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004974602734498079,
|
|
"loss": 5.6971,
|
|
"mean_token_accuracy": 0.1534070447087288,
|
|
"num_tokens": 12915285.0,
|
|
"step": 6230
|
|
},
|
|
{
|
|
"entropy": 5.905260419845581,
|
|
"epoch": 0.5655841799709724,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.000497455423305237,
|
|
"loss": 5.7263,
|
|
"mean_token_accuracy": 0.14713333249092103,
|
|
"num_tokens": 12925646.0,
|
|
"step": 6235
|
|
},
|
|
{
|
|
"entropy": 5.735151720046997,
|
|
"epoch": 0.5660377358490566,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004974505685602314,
|
|
"loss": 5.7015,
|
|
"mean_token_accuracy": 0.14945760518312454,
|
|
"num_tokens": 12936533.0,
|
|
"step": 6240
|
|
},
|
|
{
|
|
"entropy": 5.807971096038818,
|
|
"epoch": 0.5664912917271407,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004974457092148912,
|
|
"loss": 5.7451,
|
|
"mean_token_accuracy": 0.14642843157052993,
|
|
"num_tokens": 12947632.0,
|
|
"step": 6245
|
|
},
|
|
{
|
|
"entropy": 5.918157911300659,
|
|
"epoch": 0.566944847605225,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004974408452693172,
|
|
"loss": 5.6463,
|
|
"mean_token_accuracy": 0.14986635148525237,
|
|
"num_tokens": 12957339.0,
|
|
"step": 6250
|
|
},
|
|
{
|
|
"entropy": 5.832627534866333,
|
|
"epoch": 0.5673984034833092,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004974359767236099,
|
|
"loss": 5.6465,
|
|
"mean_token_accuracy": 0.1551988333463669,
|
|
"num_tokens": 12967406.0,
|
|
"step": 6255
|
|
},
|
|
{
|
|
"entropy": 5.735131931304932,
|
|
"epoch": 0.5678519593613933,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004974311035778698,
|
|
"loss": 5.6883,
|
|
"mean_token_accuracy": 0.1483675830066204,
|
|
"num_tokens": 12977673.0,
|
|
"step": 6260
|
|
},
|
|
{
|
|
"entropy": 5.82387638092041,
|
|
"epoch": 0.5683055152394775,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004974262258321979,
|
|
"loss": 5.7932,
|
|
"mean_token_accuracy": 0.14896491393446923,
|
|
"num_tokens": 12987641.0,
|
|
"step": 6265
|
|
},
|
|
{
|
|
"entropy": 5.88049430847168,
|
|
"epoch": 0.5687590711175616,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004974213434866949,
|
|
"loss": 5.742,
|
|
"mean_token_accuracy": 0.1527087390422821,
|
|
"num_tokens": 12997285.0,
|
|
"step": 6270
|
|
},
|
|
{
|
|
"entropy": 5.75934419631958,
|
|
"epoch": 0.5692126269956459,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.0004974164565414617,
|
|
"loss": 5.5925,
|
|
"mean_token_accuracy": 0.15589440613985062,
|
|
"num_tokens": 13007527.0,
|
|
"step": 6275
|
|
},
|
|
{
|
|
"entropy": 5.798234748840332,
|
|
"epoch": 0.56966618287373,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004974115649965998,
|
|
"loss": 5.6956,
|
|
"mean_token_accuracy": 0.15216642171144484,
|
|
"num_tokens": 13017415.0,
|
|
"step": 6280
|
|
},
|
|
{
|
|
"entropy": 5.755988216400146,
|
|
"epoch": 0.5701197387518142,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004974066688522098,
|
|
"loss": 5.6192,
|
|
"mean_token_accuracy": 0.15360938757658005,
|
|
"num_tokens": 13028045.0,
|
|
"step": 6285
|
|
},
|
|
{
|
|
"entropy": 5.74319019317627,
|
|
"epoch": 0.5705732946298984,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004974017681083934,
|
|
"loss": 5.5472,
|
|
"mean_token_accuracy": 0.15900930017232895,
|
|
"num_tokens": 13037729.0,
|
|
"step": 6290
|
|
},
|
|
{
|
|
"entropy": 5.815383195877075,
|
|
"epoch": 0.5710268505079826,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004973968627652516,
|
|
"loss": 5.7195,
|
|
"mean_token_accuracy": 0.15383805856108665,
|
|
"num_tokens": 13049134.0,
|
|
"step": 6295
|
|
},
|
|
{
|
|
"entropy": 5.783070278167725,
|
|
"epoch": 0.5714804063860668,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.000497391952822886,
|
|
"loss": 5.6433,
|
|
"mean_token_accuracy": 0.15875421613454818,
|
|
"num_tokens": 13059523.0,
|
|
"step": 6300
|
|
},
|
|
{
|
|
"entropy": 5.863404893875122,
|
|
"epoch": 0.5719339622641509,
|
|
"grad_norm": 5.25,
|
|
"learning_rate": 0.0004973870382813983,
|
|
"loss": 5.7575,
|
|
"mean_token_accuracy": 0.14245254844427108,
|
|
"num_tokens": 13069953.0,
|
|
"step": 6305
|
|
},
|
|
{
|
|
"entropy": 5.7256475448608395,
|
|
"epoch": 0.5723875181422351,
|
|
"grad_norm": 3.3125,
|
|
"learning_rate": 0.0004973821191408899,
|
|
"loss": 5.6537,
|
|
"mean_token_accuracy": 0.16015856415033342,
|
|
"num_tokens": 13080349.0,
|
|
"step": 6310
|
|
},
|
|
{
|
|
"entropy": 5.8483531951904295,
|
|
"epoch": 0.5728410740203193,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.0004973771954014626,
|
|
"loss": 5.7382,
|
|
"mean_token_accuracy": 0.151732936501503,
|
|
"num_tokens": 13091298.0,
|
|
"step": 6315
|
|
},
|
|
{
|
|
"entropy": 5.806477880477905,
|
|
"epoch": 0.5732946298984035,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 0.0004973722670632182,
|
|
"loss": 5.6718,
|
|
"mean_token_accuracy": 0.1544908970594406,
|
|
"num_tokens": 13101801.0,
|
|
"step": 6320
|
|
},
|
|
{
|
|
"entropy": 5.812248182296753,
|
|
"epoch": 0.5737481857764877,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004973673341262587,
|
|
"loss": 5.7719,
|
|
"mean_token_accuracy": 0.1490355461835861,
|
|
"num_tokens": 13112735.0,
|
|
"step": 6325
|
|
},
|
|
{
|
|
"entropy": 5.832093191146851,
|
|
"epoch": 0.5742017416545718,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 0.000497362396590686,
|
|
"loss": 5.6858,
|
|
"mean_token_accuracy": 0.15291242748498918,
|
|
"num_tokens": 13123700.0,
|
|
"step": 6330
|
|
},
|
|
{
|
|
"entropy": 5.765924167633057,
|
|
"epoch": 0.574655297532656,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.0004973574544566024,
|
|
"loss": 5.6666,
|
|
"mean_token_accuracy": 0.14967887997627258,
|
|
"num_tokens": 13133311.0,
|
|
"step": 6335
|
|
},
|
|
{
|
|
"entropy": 5.7985289096832275,
|
|
"epoch": 0.5751088534107403,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004973525077241098,
|
|
"loss": 5.6898,
|
|
"mean_token_accuracy": 0.14694971814751626,
|
|
"num_tokens": 13142843.0,
|
|
"step": 6340
|
|
},
|
|
{
|
|
"entropy": 5.851684999465943,
|
|
"epoch": 0.5755624092888244,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004973475563933109,
|
|
"loss": 5.6544,
|
|
"mean_token_accuracy": 0.15128690004348755,
|
|
"num_tokens": 13153020.0,
|
|
"step": 6345
|
|
},
|
|
{
|
|
"entropy": 5.819696140289307,
|
|
"epoch": 0.5760159651669086,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004973426004643077,
|
|
"loss": 5.685,
|
|
"mean_token_accuracy": 0.15233107507228852,
|
|
"num_tokens": 13162655.0,
|
|
"step": 6350
|
|
},
|
|
{
|
|
"entropy": 5.8257874011993405,
|
|
"epoch": 0.5764695210449927,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004973376399372029,
|
|
"loss": 5.7342,
|
|
"mean_token_accuracy": 0.15302710384130477,
|
|
"num_tokens": 13174677.0,
|
|
"step": 6355
|
|
},
|
|
{
|
|
"entropy": 5.74808931350708,
|
|
"epoch": 0.5769230769230769,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004973326748120991,
|
|
"loss": 5.7194,
|
|
"mean_token_accuracy": 0.15407237112522126,
|
|
"num_tokens": 13185855.0,
|
|
"step": 6360
|
|
},
|
|
{
|
|
"entropy": 5.715742683410644,
|
|
"epoch": 0.5773766328011611,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.0004973277050890988,
|
|
"loss": 5.572,
|
|
"mean_token_accuracy": 0.15789375454187393,
|
|
"num_tokens": 13195773.0,
|
|
"step": 6365
|
|
},
|
|
{
|
|
"entropy": 5.747353839874267,
|
|
"epoch": 0.5778301886792453,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 0.0004973227307683049,
|
|
"loss": 5.5478,
|
|
"mean_token_accuracy": 0.16944468766450882,
|
|
"num_tokens": 13205431.0,
|
|
"step": 6370
|
|
},
|
|
{
|
|
"entropy": 5.724392366409302,
|
|
"epoch": 0.5782837445573294,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004973177518498204,
|
|
"loss": 5.6675,
|
|
"mean_token_accuracy": 0.15678295046091079,
|
|
"num_tokens": 13216153.0,
|
|
"step": 6375
|
|
},
|
|
{
|
|
"entropy": 5.722592544555664,
|
|
"epoch": 0.5787373004354136,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004973127683337482,
|
|
"loss": 5.6977,
|
|
"mean_token_accuracy": 0.15110654830932618,
|
|
"num_tokens": 13226443.0,
|
|
"step": 6380
|
|
},
|
|
{
|
|
"entropy": 5.850147342681884,
|
|
"epoch": 0.5791908563134979,
|
|
"grad_norm": 4.15625,
|
|
"learning_rate": 0.0004973077802201911,
|
|
"loss": 5.6741,
|
|
"mean_token_accuracy": 0.16088929027318954,
|
|
"num_tokens": 13235888.0,
|
|
"step": 6385
|
|
},
|
|
{
|
|
"entropy": 5.776350641250611,
|
|
"epoch": 0.579644412191582,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.0004973027875092526,
|
|
"loss": 5.6134,
|
|
"mean_token_accuracy": 0.1592132568359375,
|
|
"num_tokens": 13245556.0,
|
|
"step": 6390
|
|
},
|
|
{
|
|
"entropy": 5.734148263931274,
|
|
"epoch": 0.5800979680696662,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.0004972977902010357,
|
|
"loss": 5.6838,
|
|
"mean_token_accuracy": 0.15303038507699968,
|
|
"num_tokens": 13255961.0,
|
|
"step": 6395
|
|
},
|
|
{
|
|
"entropy": 5.797937870025635,
|
|
"epoch": 0.5805515239477503,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.0004972927882956439,
|
|
"loss": 5.6439,
|
|
"mean_token_accuracy": 0.15867367535829544,
|
|
"num_tokens": 13266078.0,
|
|
"step": 6400
|
|
},
|
|
{
|
|
"entropy": 5.789003801345825,
|
|
"epoch": 0.5810050798258345,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.0004972877817931807,
|
|
"loss": 5.6147,
|
|
"mean_token_accuracy": 0.16338896751403809,
|
|
"num_tokens": 13275744.0,
|
|
"step": 6405
|
|
},
|
|
{
|
|
"entropy": 5.776752758026123,
|
|
"epoch": 0.5814586357039188,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004972827706937493,
|
|
"loss": 5.7052,
|
|
"mean_token_accuracy": 0.1482338786125183,
|
|
"num_tokens": 13286369.0,
|
|
"step": 6410
|
|
},
|
|
{
|
|
"entropy": 5.788866662979126,
|
|
"epoch": 0.5819121915820029,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004972777549974537,
|
|
"loss": 5.6949,
|
|
"mean_token_accuracy": 0.1489218607544899,
|
|
"num_tokens": 13297152.0,
|
|
"step": 6415
|
|
},
|
|
{
|
|
"entropy": 5.965387535095215,
|
|
"epoch": 0.5823657474600871,
|
|
"grad_norm": 2.53125,
|
|
"learning_rate": 0.0004972727347043975,
|
|
"loss": 5.7917,
|
|
"mean_token_accuracy": 0.147888945043087,
|
|
"num_tokens": 13307362.0,
|
|
"step": 6420
|
|
},
|
|
{
|
|
"entropy": 5.798248815536499,
|
|
"epoch": 0.5828193033381712,
|
|
"grad_norm": 3.0,
|
|
"learning_rate": 0.0004972677098146845,
|
|
"loss": 5.7075,
|
|
"mean_token_accuracy": 0.156674425303936,
|
|
"num_tokens": 13317540.0,
|
|
"step": 6425
|
|
},
|
|
{
|
|
"entropy": 5.786098909378052,
|
|
"epoch": 0.5832728592162555,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.0004972626803284185,
|
|
"loss": 5.6126,
|
|
"mean_token_accuracy": 0.1531965523958206,
|
|
"num_tokens": 13328325.0,
|
|
"step": 6430
|
|
},
|
|
{
|
|
"entropy": 5.7550377368927,
|
|
"epoch": 0.5837264150943396,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004972576462457038,
|
|
"loss": 5.6588,
|
|
"mean_token_accuracy": 0.14883019030094147,
|
|
"num_tokens": 13338903.0,
|
|
"step": 6435
|
|
},
|
|
{
|
|
"entropy": 5.788701963424683,
|
|
"epoch": 0.5841799709724238,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004972526075666442,
|
|
"loss": 5.6555,
|
|
"mean_token_accuracy": 0.15499718487262726,
|
|
"num_tokens": 13350177.0,
|
|
"step": 6440
|
|
},
|
|
{
|
|
"entropy": 5.845593500137329,
|
|
"epoch": 0.584633526850508,
|
|
"grad_norm": 2.59375,
|
|
"learning_rate": 0.0004972475642913442,
|
|
"loss": 5.7271,
|
|
"mean_token_accuracy": 0.14860825389623641,
|
|
"num_tokens": 13361428.0,
|
|
"step": 6445
|
|
},
|
|
{
|
|
"entropy": 5.767075157165527,
|
|
"epoch": 0.5850870827285921,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.0004972425164199078,
|
|
"loss": 5.6286,
|
|
"mean_token_accuracy": 0.1638308048248291,
|
|
"num_tokens": 13370144.0,
|
|
"step": 6450
|
|
},
|
|
{
|
|
"entropy": 5.766348218917846,
|
|
"epoch": 0.5855406386066764,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004972374639524396,
|
|
"loss": 5.7869,
|
|
"mean_token_accuracy": 0.15032162964344026,
|
|
"num_tokens": 13380271.0,
|
|
"step": 6455
|
|
},
|
|
{
|
|
"entropy": 5.792541122436523,
|
|
"epoch": 0.5859941944847605,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.000497232406889044,
|
|
"loss": 5.5736,
|
|
"mean_token_accuracy": 0.15999365895986556,
|
|
"num_tokens": 13389832.0,
|
|
"step": 6460
|
|
},
|
|
{
|
|
"entropy": 5.7892321109771725,
|
|
"epoch": 0.5864477503628447,
|
|
"grad_norm": 2.640625,
|
|
"learning_rate": 0.0004972273452298255,
|
|
"loss": 5.6841,
|
|
"mean_token_accuracy": 0.15896934419870376,
|
|
"num_tokens": 13399258.0,
|
|
"step": 6465
|
|
},
|
|
{
|
|
"entropy": 5.794910049438476,
|
|
"epoch": 0.5869013062409288,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004972222789748888,
|
|
"loss": 5.6656,
|
|
"mean_token_accuracy": 0.14969532266259195,
|
|
"num_tokens": 13409650.0,
|
|
"step": 6470
|
|
},
|
|
{
|
|
"entropy": 5.761614799499512,
|
|
"epoch": 0.5873548621190131,
|
|
"grad_norm": 3.359375,
|
|
"learning_rate": 0.0004972172081243389,
|
|
"loss": 5.5964,
|
|
"mean_token_accuracy": 0.1591191679239273,
|
|
"num_tokens": 13419594.0,
|
|
"step": 6475
|
|
},
|
|
{
|
|
"entropy": 5.74503002166748,
|
|
"epoch": 0.5878084179970973,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004972121326782806,
|
|
"loss": 5.5733,
|
|
"mean_token_accuracy": 0.16051651239395143,
|
|
"num_tokens": 13428905.0,
|
|
"step": 6480
|
|
},
|
|
{
|
|
"entropy": 5.781329727172851,
|
|
"epoch": 0.5882619738751814,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004972070526368186,
|
|
"loss": 5.6888,
|
|
"mean_token_accuracy": 0.15131827890872956,
|
|
"num_tokens": 13439827.0,
|
|
"step": 6485
|
|
},
|
|
{
|
|
"entropy": 5.818743133544922,
|
|
"epoch": 0.5887155297532656,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.0004972019680000582,
|
|
"loss": 5.7048,
|
|
"mean_token_accuracy": 0.15345148146152496,
|
|
"num_tokens": 13450591.0,
|
|
"step": 6490
|
|
},
|
|
{
|
|
"entropy": 5.7719474792480465,
|
|
"epoch": 0.5891690856313497,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004971968787681044,
|
|
"loss": 5.6745,
|
|
"mean_token_accuracy": 0.15331637412309645,
|
|
"num_tokens": 13461372.0,
|
|
"step": 6495
|
|
},
|
|
{
|
|
"entropy": 5.8432635307312015,
|
|
"epoch": 0.589622641509434,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.0004971917849410627,
|
|
"loss": 5.6665,
|
|
"mean_token_accuracy": 0.15589578449726105,
|
|
"num_tokens": 13471433.0,
|
|
"step": 6500
|
|
},
|
|
{
|
|
"entropy": 5.774910402297974,
|
|
"epoch": 0.5900761973875182,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004971866865190381,
|
|
"loss": 5.6096,
|
|
"mean_token_accuracy": 0.1573952928185463,
|
|
"num_tokens": 13482311.0,
|
|
"step": 6505
|
|
},
|
|
{
|
|
"entropy": 5.701081466674805,
|
|
"epoch": 0.5905297532656023,
|
|
"grad_norm": 2.859375,
|
|
"learning_rate": 0.0004971815835021362,
|
|
"loss": 5.5801,
|
|
"mean_token_accuracy": 0.15724851489067077,
|
|
"num_tokens": 13492285.0,
|
|
"step": 6510
|
|
},
|
|
{
|
|
"entropy": 5.797769212722779,
|
|
"epoch": 0.5909833091436865,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004971764758904626,
|
|
"loss": 5.7219,
|
|
"mean_token_accuracy": 0.14754825308918953,
|
|
"num_tokens": 13502009.0,
|
|
"step": 6515
|
|
},
|
|
{
|
|
"entropy": 5.75381760597229,
|
|
"epoch": 0.5914368650217707,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004971713636841229,
|
|
"loss": 5.6241,
|
|
"mean_token_accuracy": 0.15921408385038377,
|
|
"num_tokens": 13512895.0,
|
|
"step": 6520
|
|
},
|
|
{
|
|
"entropy": 5.767732763290406,
|
|
"epoch": 0.5918904208998549,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.0004971662468832228,
|
|
"loss": 5.6844,
|
|
"mean_token_accuracy": 0.1508211076259613,
|
|
"num_tokens": 13523360.0,
|
|
"step": 6525
|
|
},
|
|
{
|
|
"entropy": 5.689045667648315,
|
|
"epoch": 0.592343976777939,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.000497161125487868,
|
|
"loss": 5.6496,
|
|
"mean_token_accuracy": 0.15322445183992386,
|
|
"num_tokens": 13534460.0,
|
|
"step": 6530
|
|
},
|
|
{
|
|
"entropy": 5.826561403274536,
|
|
"epoch": 0.5927975326560232,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.0004971559994981645,
|
|
"loss": 5.71,
|
|
"mean_token_accuracy": 0.15079641789197923,
|
|
"num_tokens": 13545258.0,
|
|
"step": 6535
|
|
},
|
|
{
|
|
"entropy": 5.79672679901123,
|
|
"epoch": 0.5932510885341074,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004971508689142184,
|
|
"loss": 5.6243,
|
|
"mean_token_accuracy": 0.15580394566059114,
|
|
"num_tokens": 13556314.0,
|
|
"step": 6540
|
|
},
|
|
{
|
|
"entropy": 5.695740747451782,
|
|
"epoch": 0.5937046444121916,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004971457337361356,
|
|
"loss": 5.5133,
|
|
"mean_token_accuracy": 0.15728529095649718,
|
|
"num_tokens": 13566614.0,
|
|
"step": 6545
|
|
},
|
|
{
|
|
"entropy": 5.7158616065979,
|
|
"epoch": 0.5941582002902758,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004971405939640225,
|
|
"loss": 5.6737,
|
|
"mean_token_accuracy": 0.1531232103705406,
|
|
"num_tokens": 13577525.0,
|
|
"step": 6550
|
|
},
|
|
{
|
|
"entropy": 5.749601554870606,
|
|
"epoch": 0.5946117561683599,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004971354495979854,
|
|
"loss": 5.6414,
|
|
"mean_token_accuracy": 0.15192501544952391,
|
|
"num_tokens": 13588064.0,
|
|
"step": 6555
|
|
},
|
|
{
|
|
"entropy": 5.836508464813233,
|
|
"epoch": 0.5950653120464441,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004971303006381305,
|
|
"loss": 5.6614,
|
|
"mean_token_accuracy": 0.14990201741456985,
|
|
"num_tokens": 13597351.0,
|
|
"step": 6560
|
|
},
|
|
{
|
|
"entropy": 5.7892152786254885,
|
|
"epoch": 0.5955188679245284,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.0004971251470845643,
|
|
"loss": 5.6615,
|
|
"mean_token_accuracy": 0.1539871171116829,
|
|
"num_tokens": 13608555.0,
|
|
"step": 6565
|
|
},
|
|
{
|
|
"entropy": 5.811808252334595,
|
|
"epoch": 0.5959724238026125,
|
|
"grad_norm": 3.59375,
|
|
"learning_rate": 0.0004971199889373935,
|
|
"loss": 5.5654,
|
|
"mean_token_accuracy": 0.16079137325286866,
|
|
"num_tokens": 13617934.0,
|
|
"step": 6570
|
|
},
|
|
{
|
|
"entropy": 5.784776878356934,
|
|
"epoch": 0.5964259796806967,
|
|
"grad_norm": 6.21875,
|
|
"learning_rate": 0.0004971148261967249,
|
|
"loss": 5.6439,
|
|
"mean_token_accuracy": 0.14824899137020112,
|
|
"num_tokens": 13628792.0,
|
|
"step": 6575
|
|
},
|
|
{
|
|
"entropy": 5.627862644195557,
|
|
"epoch": 0.5968795355587808,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004971096588626649,
|
|
"loss": 5.6133,
|
|
"mean_token_accuracy": 0.15427356511354445,
|
|
"num_tokens": 13639556.0,
|
|
"step": 6580
|
|
},
|
|
{
|
|
"entropy": 5.75811128616333,
|
|
"epoch": 0.597333091436865,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004971044869353206,
|
|
"loss": 5.6389,
|
|
"mean_token_accuracy": 0.15479681491851807,
|
|
"num_tokens": 13649806.0,
|
|
"step": 6585
|
|
},
|
|
{
|
|
"entropy": 5.761819362640381,
|
|
"epoch": 0.5977866473149492,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.000497099310414799,
|
|
"loss": 5.6197,
|
|
"mean_token_accuracy": 0.1565105363726616,
|
|
"num_tokens": 13660114.0,
|
|
"step": 6590
|
|
},
|
|
{
|
|
"entropy": 5.803523921966553,
|
|
"epoch": 0.5982402031930334,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004970941293012069,
|
|
"loss": 5.7177,
|
|
"mean_token_accuracy": 0.1446136213839054,
|
|
"num_tokens": 13669498.0,
|
|
"step": 6595
|
|
},
|
|
{
|
|
"entropy": 5.8665166854858395,
|
|
"epoch": 0.5986937590711175,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.0004970889435946518,
|
|
"loss": 5.6877,
|
|
"mean_token_accuracy": 0.1534451112151146,
|
|
"num_tokens": 13679065.0,
|
|
"step": 6600
|
|
},
|
|
{
|
|
"entropy": 5.814449214935303,
|
|
"epoch": 0.5991473149492017,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004970837532952406,
|
|
"loss": 5.7057,
|
|
"mean_token_accuracy": 0.14952020198106766,
|
|
"num_tokens": 13690046.0,
|
|
"step": 6605
|
|
},
|
|
{
|
|
"entropy": 5.679539918899536,
|
|
"epoch": 0.599600870827286,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004970785584030808,
|
|
"loss": 5.5327,
|
|
"mean_token_accuracy": 0.15556963086128234,
|
|
"num_tokens": 13700859.0,
|
|
"step": 6610
|
|
},
|
|
{
|
|
"entropy": 5.774577283859253,
|
|
"epoch": 0.6000544267053701,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004970733589182799,
|
|
"loss": 5.6551,
|
|
"mean_token_accuracy": 0.1568846732378006,
|
|
"num_tokens": 13710774.0,
|
|
"step": 6615
|
|
},
|
|
{
|
|
"entropy": 5.758139276504517,
|
|
"epoch": 0.6005079825834543,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004970681548409452,
|
|
"loss": 5.6323,
|
|
"mean_token_accuracy": 0.14867477491497993,
|
|
"num_tokens": 13720562.0,
|
|
"step": 6620
|
|
},
|
|
{
|
|
"entropy": 5.7717029571533205,
|
|
"epoch": 0.6009615384615384,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.0004970629461711846,
|
|
"loss": 5.6648,
|
|
"mean_token_accuracy": 0.1562247470021248,
|
|
"num_tokens": 13731077.0,
|
|
"step": 6625
|
|
},
|
|
{
|
|
"entropy": 5.838614368438721,
|
|
"epoch": 0.6014150943396226,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004970577329091057,
|
|
"loss": 5.6816,
|
|
"mean_token_accuracy": 0.14774770587682723,
|
|
"num_tokens": 13742006.0,
|
|
"step": 6630
|
|
},
|
|
{
|
|
"entropy": 5.709045839309693,
|
|
"epoch": 0.6018686502177069,
|
|
"grad_norm": 2.59375,
|
|
"learning_rate": 0.0004970525150548162,
|
|
"loss": 5.5565,
|
|
"mean_token_accuracy": 0.15513368248939513,
|
|
"num_tokens": 13752811.0,
|
|
"step": 6635
|
|
},
|
|
{
|
|
"entropy": 5.838441944122314,
|
|
"epoch": 0.602322206095791,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004970472926084242,
|
|
"loss": 5.7157,
|
|
"mean_token_accuracy": 0.14971795231103896,
|
|
"num_tokens": 13763976.0,
|
|
"step": 6640
|
|
},
|
|
{
|
|
"entropy": 5.759917879104615,
|
|
"epoch": 0.6027757619738752,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004970420655700375,
|
|
"loss": 5.6817,
|
|
"mean_token_accuracy": 0.14599033817648888,
|
|
"num_tokens": 13773822.0,
|
|
"step": 6645
|
|
},
|
|
{
|
|
"entropy": 5.743947839736938,
|
|
"epoch": 0.6032293178519593,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.0004970368339397643,
|
|
"loss": 5.6397,
|
|
"mean_token_accuracy": 0.15390206426382064,
|
|
"num_tokens": 13784471.0,
|
|
"step": 6650
|
|
},
|
|
{
|
|
"entropy": 5.7445775985717775,
|
|
"epoch": 0.6036828737300436,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004970315977177129,
|
|
"loss": 5.6674,
|
|
"mean_token_accuracy": 0.1602077767252922,
|
|
"num_tokens": 13794938.0,
|
|
"step": 6655
|
|
},
|
|
{
|
|
"entropy": 5.777162885665893,
|
|
"epoch": 0.6041364296081277,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004970263569039914,
|
|
"loss": 5.6617,
|
|
"mean_token_accuracy": 0.15100730061531067,
|
|
"num_tokens": 13804887.0,
|
|
"step": 6660
|
|
},
|
|
{
|
|
"entropy": 5.768775796890258,
|
|
"epoch": 0.6045899854862119,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004970211114987083,
|
|
"loss": 5.6364,
|
|
"mean_token_accuracy": 0.165377701818943,
|
|
"num_tokens": 13814086.0,
|
|
"step": 6665
|
|
},
|
|
{
|
|
"entropy": 5.714260005950928,
|
|
"epoch": 0.6050435413642961,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004970158615019719,
|
|
"loss": 5.7302,
|
|
"mean_token_accuracy": 0.15276252329349518,
|
|
"num_tokens": 13823689.0,
|
|
"step": 6670
|
|
},
|
|
{
|
|
"entropy": 5.781020736694336,
|
|
"epoch": 0.6054970972423802,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004970106069138912,
|
|
"loss": 5.6772,
|
|
"mean_token_accuracy": 0.15445291697978974,
|
|
"num_tokens": 13833687.0,
|
|
"step": 6675
|
|
},
|
|
{
|
|
"entropy": 5.83794379234314,
|
|
"epoch": 0.6059506531204645,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004970053477345743,
|
|
"loss": 5.6673,
|
|
"mean_token_accuracy": 0.1538187548518181,
|
|
"num_tokens": 13843553.0,
|
|
"step": 6680
|
|
},
|
|
{
|
|
"entropy": 5.869140338897705,
|
|
"epoch": 0.6064042089985486,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004970000839641304,
|
|
"loss": 5.7093,
|
|
"mean_token_accuracy": 0.15285808145999907,
|
|
"num_tokens": 13853865.0,
|
|
"step": 6685
|
|
},
|
|
{
|
|
"entropy": 5.751467227935791,
|
|
"epoch": 0.6068577648766328,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.0004969948156026681,
|
|
"loss": 5.7129,
|
|
"mean_token_accuracy": 0.15951429605484008,
|
|
"num_tokens": 13863977.0,
|
|
"step": 6690
|
|
},
|
|
{
|
|
"entropy": 5.749941825866699,
|
|
"epoch": 0.6073113207547169,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004969895426502965,
|
|
"loss": 5.6416,
|
|
"mean_token_accuracy": 0.15813523679971694,
|
|
"num_tokens": 13873063.0,
|
|
"step": 6695
|
|
},
|
|
{
|
|
"entropy": 5.756564998626709,
|
|
"epoch": 0.6077648766328012,
|
|
"grad_norm": 3.125,
|
|
"learning_rate": 0.0004969842651071246,
|
|
"loss": 5.6655,
|
|
"mean_token_accuracy": 0.15263455957174302,
|
|
"num_tokens": 13883922.0,
|
|
"step": 6700
|
|
},
|
|
{
|
|
"entropy": 5.748463106155396,
|
|
"epoch": 0.6082184325108854,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.0004969789829732615,
|
|
"loss": 5.6679,
|
|
"mean_token_accuracy": 0.1541737586259842,
|
|
"num_tokens": 13894492.0,
|
|
"step": 6705
|
|
},
|
|
{
|
|
"entropy": 5.830241012573242,
|
|
"epoch": 0.6086719883889695,
|
|
"grad_norm": 3.28125,
|
|
"learning_rate": 0.0004969736962488164,
|
|
"loss": 5.6318,
|
|
"mean_token_accuracy": 0.15171009600162505,
|
|
"num_tokens": 13906115.0,
|
|
"step": 6710
|
|
},
|
|
{
|
|
"entropy": 5.84632625579834,
|
|
"epoch": 0.6091255442670537,
|
|
"grad_norm": 3.078125,
|
|
"learning_rate": 0.0004969684049338987,
|
|
"loss": 5.7166,
|
|
"mean_token_accuracy": 0.15598284602165222,
|
|
"num_tokens": 13917023.0,
|
|
"step": 6715
|
|
},
|
|
{
|
|
"entropy": 5.772471570968628,
|
|
"epoch": 0.6095791001451378,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.000496963109028618,
|
|
"loss": 5.6166,
|
|
"mean_token_accuracy": 0.15752025842666625,
|
|
"num_tokens": 13927673.0,
|
|
"step": 6720
|
|
},
|
|
{
|
|
"entropy": 5.843606328964233,
|
|
"epoch": 0.6100326560232221,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004969578085330834,
|
|
"loss": 5.7504,
|
|
"mean_token_accuracy": 0.15184470340609552,
|
|
"num_tokens": 13939456.0,
|
|
"step": 6725
|
|
},
|
|
{
|
|
"entropy": 5.7830828666687015,
|
|
"epoch": 0.6104862119013063,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004969525034474049,
|
|
"loss": 5.6534,
|
|
"mean_token_accuracy": 0.1520907148718834,
|
|
"num_tokens": 13950318.0,
|
|
"step": 6730
|
|
},
|
|
{
|
|
"entropy": 5.759706115722656,
|
|
"epoch": 0.6109397677793904,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.000496947193771692,
|
|
"loss": 5.6901,
|
|
"mean_token_accuracy": 0.1527148336172104,
|
|
"num_tokens": 13961791.0,
|
|
"step": 6735
|
|
},
|
|
{
|
|
"entropy": 5.7276403427124025,
|
|
"epoch": 0.6113933236574746,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.0004969418795060548,
|
|
"loss": 5.6524,
|
|
"mean_token_accuracy": 0.14924755543470383,
|
|
"num_tokens": 13971891.0,
|
|
"step": 6740
|
|
},
|
|
{
|
|
"entropy": 5.775363779067993,
|
|
"epoch": 0.6118468795355588,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004969365606506027,
|
|
"loss": 5.6514,
|
|
"mean_token_accuracy": 0.16066350191831588,
|
|
"num_tokens": 13981517.0,
|
|
"step": 6745
|
|
},
|
|
{
|
|
"entropy": 5.803750371932983,
|
|
"epoch": 0.612300435413643,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 0.0004969312372054461,
|
|
"loss": 5.6989,
|
|
"mean_token_accuracy": 0.1511117547750473,
|
|
"num_tokens": 13991710.0,
|
|
"step": 6750
|
|
},
|
|
{
|
|
"entropy": 5.843258428573608,
|
|
"epoch": 0.6127539912917271,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.0004969259091706948,
|
|
"loss": 5.6309,
|
|
"mean_token_accuracy": 0.1531181588768959,
|
|
"num_tokens": 14001356.0,
|
|
"step": 6755
|
|
},
|
|
{
|
|
"entropy": 5.830201244354248,
|
|
"epoch": 0.6132075471698113,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004969205765464593,
|
|
"loss": 5.6687,
|
|
"mean_token_accuracy": 0.16042326837778093,
|
|
"num_tokens": 14011125.0,
|
|
"step": 6760
|
|
},
|
|
{
|
|
"entropy": 5.7516063213348385,
|
|
"epoch": 0.6136611030478955,
|
|
"grad_norm": 3.984375,
|
|
"learning_rate": 0.0004969152393328497,
|
|
"loss": 5.7335,
|
|
"mean_token_accuracy": 0.1556561604142189,
|
|
"num_tokens": 14021434.0,
|
|
"step": 6765
|
|
},
|
|
{
|
|
"entropy": 5.722778606414795,
|
|
"epoch": 0.6141146589259797,
|
|
"grad_norm": 2.609375,
|
|
"learning_rate": 0.0004969098975299764,
|
|
"loss": 5.6504,
|
|
"mean_token_accuracy": 0.1564916342496872,
|
|
"num_tokens": 14030836.0,
|
|
"step": 6770
|
|
},
|
|
{
|
|
"entropy": 5.8363611698150635,
|
|
"epoch": 0.6145682148040639,
|
|
"grad_norm": 2.671875,
|
|
"learning_rate": 0.0004969045511379499,
|
|
"loss": 5.5904,
|
|
"mean_token_accuracy": 0.15923578143119813,
|
|
"num_tokens": 14040448.0,
|
|
"step": 6775
|
|
},
|
|
{
|
|
"entropy": 5.8388951301574705,
|
|
"epoch": 0.615021770682148,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.0004968992001568806,
|
|
"loss": 5.6531,
|
|
"mean_token_accuracy": 0.15082638263702391,
|
|
"num_tokens": 14049978.0,
|
|
"step": 6780
|
|
},
|
|
{
|
|
"entropy": 5.6803234100341795,
|
|
"epoch": 0.6154753265602322,
|
|
"grad_norm": 2.5625,
|
|
"learning_rate": 0.0004968938445868795,
|
|
"loss": 5.5571,
|
|
"mean_token_accuracy": 0.16090612411499022,
|
|
"num_tokens": 14060508.0,
|
|
"step": 6785
|
|
},
|
|
{
|
|
"entropy": 5.736954593658448,
|
|
"epoch": 0.6159288824383164,
|
|
"grad_norm": 2.78125,
|
|
"learning_rate": 0.0004968884844280569,
|
|
"loss": 5.6225,
|
|
"mean_token_accuracy": 0.15464167445898055,
|
|
"num_tokens": 14071087.0,
|
|
"step": 6790
|
|
},
|
|
{
|
|
"entropy": 5.788089370727539,
|
|
"epoch": 0.6163824383164006,
|
|
"grad_norm": 3.1875,
|
|
"learning_rate": 0.0004968831196805242,
|
|
"loss": 5.6133,
|
|
"mean_token_accuracy": 0.15705024152994157,
|
|
"num_tokens": 14080686.0,
|
|
"step": 6795
|
|
},
|
|
{
|
|
"entropy": 5.793479967117309,
|
|
"epoch": 0.6168359941944848,
|
|
"grad_norm": 4.375,
|
|
"learning_rate": 0.0004968777503443918,
|
|
"loss": 5.6145,
|
|
"mean_token_accuracy": 0.14688779413700104,
|
|
"num_tokens": 14091029.0,
|
|
"step": 6800
|
|
},
|
|
{
|
|
"entropy": 5.820604848861694,
|
|
"epoch": 0.6172895500725689,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004968723764197711,
|
|
"loss": 5.7302,
|
|
"mean_token_accuracy": 0.15448133647441864,
|
|
"num_tokens": 14102302.0,
|
|
"step": 6805
|
|
},
|
|
{
|
|
"entropy": 5.758450174331665,
|
|
"epoch": 0.6177431059506531,
|
|
"grad_norm": 2.546875,
|
|
"learning_rate": 0.000496866997906773,
|
|
"loss": 5.6437,
|
|
"mean_token_accuracy": 0.15994014590978622,
|
|
"num_tokens": 14112853.0,
|
|
"step": 6810
|
|
},
|
|
{
|
|
"entropy": 5.720447254180908,
|
|
"epoch": 0.6181966618287373,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004968616148055089,
|
|
"loss": 5.6266,
|
|
"mean_token_accuracy": 0.15244435667991638,
|
|
"num_tokens": 14122862.0,
|
|
"step": 6815
|
|
},
|
|
{
|
|
"entropy": 5.78267092704773,
|
|
"epoch": 0.6186502177068215,
|
|
"grad_norm": 2.9375,
|
|
"learning_rate": 0.0004968562271160901,
|
|
"loss": 5.6773,
|
|
"mean_token_accuracy": 0.1588394470512867,
|
|
"num_tokens": 14132993.0,
|
|
"step": 6820
|
|
},
|
|
{
|
|
"entropy": 5.807964515686035,
|
|
"epoch": 0.6191037735849056,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.000496850834838628,
|
|
"loss": 5.6572,
|
|
"mean_token_accuracy": 0.16151908338069915,
|
|
"num_tokens": 14143448.0,
|
|
"step": 6825
|
|
},
|
|
{
|
|
"entropy": 5.733871078491211,
|
|
"epoch": 0.6195573294629898,
|
|
"grad_norm": 2.953125,
|
|
"learning_rate": 0.0004968454379732342,
|
|
"loss": 5.6091,
|
|
"mean_token_accuracy": 0.1550980895757675,
|
|
"num_tokens": 14153497.0,
|
|
"step": 6830
|
|
},
|
|
{
|
|
"entropy": 5.825773239135742,
|
|
"epoch": 0.6200108853410741,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.00049684003652002,
|
|
"loss": 5.6833,
|
|
"mean_token_accuracy": 0.15593169927597045,
|
|
"num_tokens": 14163537.0,
|
|
"step": 6835
|
|
},
|
|
{
|
|
"entropy": 5.777164506912231,
|
|
"epoch": 0.6204644412191582,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004968346304790973,
|
|
"loss": 5.6441,
|
|
"mean_token_accuracy": 0.14758117198944093,
|
|
"num_tokens": 14173502.0,
|
|
"step": 6840
|
|
},
|
|
{
|
|
"entropy": 5.742531824111938,
|
|
"epoch": 0.6209179970972424,
|
|
"grad_norm": 4.1875,
|
|
"learning_rate": 0.0004968292198505781,
|
|
"loss": 5.7173,
|
|
"mean_token_accuracy": 0.14918248653411864,
|
|
"num_tokens": 14184700.0,
|
|
"step": 6845
|
|
},
|
|
{
|
|
"entropy": 5.75475287437439,
|
|
"epoch": 0.6213715529753265,
|
|
"grad_norm": 18.25,
|
|
"learning_rate": 0.000496823804634574,
|
|
"loss": 5.6446,
|
|
"mean_token_accuracy": 0.15267936885356903,
|
|
"num_tokens": 14194582.0,
|
|
"step": 6850
|
|
},
|
|
{
|
|
"entropy": 5.8139732837677,
|
|
"epoch": 0.6218251088534107,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004968183848311972,
|
|
"loss": 5.696,
|
|
"mean_token_accuracy": 0.1472626082599163,
|
|
"num_tokens": 14204326.0,
|
|
"step": 6855
|
|
},
|
|
{
|
|
"entropy": 5.788832330703736,
|
|
"epoch": 0.622278664731495,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004968129604405596,
|
|
"loss": 5.6133,
|
|
"mean_token_accuracy": 0.1588970422744751,
|
|
"num_tokens": 14214550.0,
|
|
"step": 6860
|
|
},
|
|
{
|
|
"entropy": 5.798810768127441,
|
|
"epoch": 0.6227322206095791,
|
|
"grad_norm": 2.65625,
|
|
"learning_rate": 0.0004968075314627734,
|
|
"loss": 5.6871,
|
|
"mean_token_accuracy": 0.14665393605828286,
|
|
"num_tokens": 14226882.0,
|
|
"step": 6865
|
|
},
|
|
{
|
|
"entropy": 5.835011196136475,
|
|
"epoch": 0.6231857764876633,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.000496802097897951,
|
|
"loss": 5.6661,
|
|
"mean_token_accuracy": 0.15461646318435668,
|
|
"num_tokens": 14236360.0,
|
|
"step": 6870
|
|
},
|
|
{
|
|
"entropy": 5.806660270690918,
|
|
"epoch": 0.6236393323657474,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004967966597462046,
|
|
"loss": 5.585,
|
|
"mean_token_accuracy": 0.15756107717752457,
|
|
"num_tokens": 14247654.0,
|
|
"step": 6875
|
|
},
|
|
{
|
|
"entropy": 5.718276834487915,
|
|
"epoch": 0.6240928882438317,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004967912170076469,
|
|
"loss": 5.6212,
|
|
"mean_token_accuracy": 0.1535835564136505,
|
|
"num_tokens": 14258143.0,
|
|
"step": 6880
|
|
},
|
|
{
|
|
"entropy": 5.7423478126525875,
|
|
"epoch": 0.6245464441219158,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004967857696823901,
|
|
"loss": 5.6398,
|
|
"mean_token_accuracy": 0.15219745934009551,
|
|
"num_tokens": 14268464.0,
|
|
"step": 6885
|
|
},
|
|
{
|
|
"entropy": 5.8025744438171385,
|
|
"epoch": 0.625,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004967803177705472,
|
|
"loss": 5.7828,
|
|
"mean_token_accuracy": 0.15216079279780387,
|
|
"num_tokens": 14279370.0,
|
|
"step": 6890
|
|
},
|
|
{
|
|
"entropy": 5.757842922210694,
|
|
"epoch": 0.6254535558780842,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004967748612722308,
|
|
"loss": 5.5785,
|
|
"mean_token_accuracy": 0.1600301280617714,
|
|
"num_tokens": 14289693.0,
|
|
"step": 6895
|
|
},
|
|
{
|
|
"entropy": 5.8160813331604,
|
|
"epoch": 0.6259071117561683,
|
|
"grad_norm": 3.90625,
|
|
"learning_rate": 0.0004967694001875538,
|
|
"loss": 5.728,
|
|
"mean_token_accuracy": 0.15318948924541473,
|
|
"num_tokens": 14299812.0,
|
|
"step": 6900
|
|
},
|
|
{
|
|
"entropy": 5.806861925125122,
|
|
"epoch": 0.6263606676342526,
|
|
"grad_norm": 2.921875,
|
|
"learning_rate": 0.000496763934516629,
|
|
"loss": 5.6027,
|
|
"mean_token_accuracy": 0.1589020684361458,
|
|
"num_tokens": 14310189.0,
|
|
"step": 6905
|
|
},
|
|
{
|
|
"entropy": 5.778165483474732,
|
|
"epoch": 0.6268142235123367,
|
|
"grad_norm": 2.921875,
|
|
"learning_rate": 0.0004967584642595696,
|
|
"loss": 5.6661,
|
|
"mean_token_accuracy": 0.1539705604314804,
|
|
"num_tokens": 14320522.0,
|
|
"step": 6910
|
|
},
|
|
{
|
|
"entropy": 5.851005220413208,
|
|
"epoch": 0.6272677793904209,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004967529894164887,
|
|
"loss": 5.7178,
|
|
"mean_token_accuracy": 0.15760016292333603,
|
|
"num_tokens": 14330610.0,
|
|
"step": 6915
|
|
},
|
|
{
|
|
"entropy": 5.760132217407227,
|
|
"epoch": 0.627721335268505,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.0004967475099874992,
|
|
"loss": 5.6599,
|
|
"mean_token_accuracy": 0.15557935535907746,
|
|
"num_tokens": 14340486.0,
|
|
"step": 6920
|
|
},
|
|
{
|
|
"entropy": 5.771120929718018,
|
|
"epoch": 0.6281748911465893,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.000496742025972715,
|
|
"loss": 5.7004,
|
|
"mean_token_accuracy": 0.15341282188892363,
|
|
"num_tokens": 14351926.0,
|
|
"step": 6925
|
|
},
|
|
{
|
|
"entropy": 5.838538789749146,
|
|
"epoch": 0.6286284470246735,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 0.000496736537372249,
|
|
"loss": 5.7068,
|
|
"mean_token_accuracy": 0.15071312338113785,
|
|
"num_tokens": 14362471.0,
|
|
"step": 6930
|
|
},
|
|
{
|
|
"entropy": 5.759868812561035,
|
|
"epoch": 0.6290820029027576,
|
|
"grad_norm": 6.0,
|
|
"learning_rate": 0.0004967310441862151,
|
|
"loss": 5.6236,
|
|
"mean_token_accuracy": 0.15248621255159378,
|
|
"num_tokens": 14373509.0,
|
|
"step": 6935
|
|
},
|
|
{
|
|
"entropy": 5.636255884170533,
|
|
"epoch": 0.6295355587808418,
|
|
"grad_norm": 3.90625,
|
|
"learning_rate": 0.0004967255464147265,
|
|
"loss": 5.5923,
|
|
"mean_token_accuracy": 0.15608540624380113,
|
|
"num_tokens": 14384131.0,
|
|
"step": 6940
|
|
},
|
|
{
|
|
"entropy": 5.726693439483642,
|
|
"epoch": 0.6299891146589259,
|
|
"grad_norm": 2.640625,
|
|
"learning_rate": 0.0004967200440578972,
|
|
"loss": 5.6511,
|
|
"mean_token_accuracy": 0.15662525296211244,
|
|
"num_tokens": 14393752.0,
|
|
"step": 6945
|
|
},
|
|
{
|
|
"entropy": 5.821837091445923,
|
|
"epoch": 0.6304426705370102,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.0004967145371158408,
|
|
"loss": 5.5946,
|
|
"mean_token_accuracy": 0.16085419803857803,
|
|
"num_tokens": 14403196.0,
|
|
"step": 6950
|
|
},
|
|
{
|
|
"entropy": 5.726358938217163,
|
|
"epoch": 0.6308962264150944,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004967090255886714,
|
|
"loss": 5.5548,
|
|
"mean_token_accuracy": 0.15695931911468505,
|
|
"num_tokens": 14412665.0,
|
|
"step": 6955
|
|
},
|
|
{
|
|
"entropy": 5.727782535552978,
|
|
"epoch": 0.6313497822931785,
|
|
"grad_norm": 4.1875,
|
|
"learning_rate": 0.0004967035094765028,
|
|
"loss": 5.5834,
|
|
"mean_token_accuracy": 0.15439184457063676,
|
|
"num_tokens": 14422866.0,
|
|
"step": 6960
|
|
},
|
|
{
|
|
"entropy": 5.767874622344971,
|
|
"epoch": 0.6318033381712627,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.0004966979887794491,
|
|
"loss": 5.658,
|
|
"mean_token_accuracy": 0.15593582540750503,
|
|
"num_tokens": 14433789.0,
|
|
"step": 6965
|
|
},
|
|
{
|
|
"entropy": 5.812677669525146,
|
|
"epoch": 0.6322568940493469,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.0004966924634976245,
|
|
"loss": 5.6208,
|
|
"mean_token_accuracy": 0.15940699875354766,
|
|
"num_tokens": 14443742.0,
|
|
"step": 6970
|
|
},
|
|
{
|
|
"entropy": 5.818565702438354,
|
|
"epoch": 0.6327104499274311,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 0.0004966869336311433,
|
|
"loss": 5.7406,
|
|
"mean_token_accuracy": 0.16035750657320022,
|
|
"num_tokens": 14454692.0,
|
|
"step": 6975
|
|
},
|
|
{
|
|
"entropy": 5.760339975357056,
|
|
"epoch": 0.6331640058055152,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004966813991801197,
|
|
"loss": 5.6669,
|
|
"mean_token_accuracy": 0.15305879712104797,
|
|
"num_tokens": 14464411.0,
|
|
"step": 6980
|
|
},
|
|
{
|
|
"entropy": 5.8635557174682615,
|
|
"epoch": 0.6336175616835994,
|
|
"grad_norm": 2.796875,
|
|
"learning_rate": 0.0004966758601446684,
|
|
"loss": 5.7324,
|
|
"mean_token_accuracy": 0.15030285492539405,
|
|
"num_tokens": 14474957.0,
|
|
"step": 6985
|
|
},
|
|
{
|
|
"entropy": 5.772822713851928,
|
|
"epoch": 0.6340711175616836,
|
|
"grad_norm": 4.15625,
|
|
"learning_rate": 0.0004966703165249038,
|
|
"loss": 5.6163,
|
|
"mean_token_accuracy": 0.15495894849300385,
|
|
"num_tokens": 14485267.0,
|
|
"step": 6990
|
|
},
|
|
{
|
|
"entropy": 5.683677911758423,
|
|
"epoch": 0.6345246734397678,
|
|
"grad_norm": 2.609375,
|
|
"learning_rate": 0.0004966647683209406,
|
|
"loss": 5.5817,
|
|
"mean_token_accuracy": 0.15759727656841277,
|
|
"num_tokens": 14495894.0,
|
|
"step": 6995
|
|
},
|
|
{
|
|
"entropy": 5.808957433700561,
|
|
"epoch": 0.634978229317852,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 0.0004966592155328935,
|
|
"loss": 5.7923,
|
|
"mean_token_accuracy": 0.14456736743450166,
|
|
"num_tokens": 14506317.0,
|
|
"step": 7000
|
|
},
|
|
{
|
|
"entropy": 5.906829690933227,
|
|
"epoch": 0.6354317851959361,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004966536581608771,
|
|
"loss": 5.6652,
|
|
"mean_token_accuracy": 0.15678728967905045,
|
|
"num_tokens": 14516107.0,
|
|
"step": 7005
|
|
},
|
|
{
|
|
"entropy": 5.816624879837036,
|
|
"epoch": 0.6358853410740203,
|
|
"grad_norm": 3.734375,
|
|
"learning_rate": 0.0004966480962050069,
|
|
"loss": 5.6074,
|
|
"mean_token_accuracy": 0.16011085957288743,
|
|
"num_tokens": 14526578.0,
|
|
"step": 7010
|
|
},
|
|
{
|
|
"entropy": 5.694090747833252,
|
|
"epoch": 0.6363388969521045,
|
|
"grad_norm": 3.71875,
|
|
"learning_rate": 0.0004966425296653974,
|
|
"loss": 5.6545,
|
|
"mean_token_accuracy": 0.15831681191921235,
|
|
"num_tokens": 14536427.0,
|
|
"step": 7015
|
|
},
|
|
{
|
|
"entropy": 5.779532384872437,
|
|
"epoch": 0.6367924528301887,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.000496636958542164,
|
|
"loss": 5.6534,
|
|
"mean_token_accuracy": 0.15706139504909516,
|
|
"num_tokens": 14546217.0,
|
|
"step": 7020
|
|
},
|
|
{
|
|
"entropy": 5.821206760406494,
|
|
"epoch": 0.6372460087082729,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.0004966313828354218,
|
|
"loss": 5.6365,
|
|
"mean_token_accuracy": 0.14632668271660804,
|
|
"num_tokens": 14556896.0,
|
|
"step": 7025
|
|
},
|
|
{
|
|
"entropy": 5.796967315673828,
|
|
"epoch": 0.637699564586357,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.000496625802545286,
|
|
"loss": 5.6484,
|
|
"mean_token_accuracy": 0.15730191618204117,
|
|
"num_tokens": 14566957.0,
|
|
"step": 7030
|
|
},
|
|
{
|
|
"entropy": 5.766891241073608,
|
|
"epoch": 0.6381531204644412,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004966202176718723,
|
|
"loss": 5.6771,
|
|
"mean_token_accuracy": 0.1520696610212326,
|
|
"num_tokens": 14577935.0,
|
|
"step": 7035
|
|
},
|
|
{
|
|
"entropy": 5.841264724731445,
|
|
"epoch": 0.6386066763425254,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.0004966146282152959,
|
|
"loss": 5.7497,
|
|
"mean_token_accuracy": 0.15304782390594482,
|
|
"num_tokens": 14589418.0,
|
|
"step": 7040
|
|
},
|
|
{
|
|
"entropy": 5.780355405807495,
|
|
"epoch": 0.6390602322206096,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.0004966090341756726,
|
|
"loss": 5.6604,
|
|
"mean_token_accuracy": 0.1525360032916069,
|
|
"num_tokens": 14600557.0,
|
|
"step": 7045
|
|
},
|
|
{
|
|
"entropy": 5.787223291397095,
|
|
"epoch": 0.6395137880986937,
|
|
"grad_norm": 2.828125,
|
|
"learning_rate": 0.000496603435553118,
|
|
"loss": 5.6941,
|
|
"mean_token_accuracy": 0.15005461424589156,
|
|
"num_tokens": 14611466.0,
|
|
"step": 7050
|
|
},
|
|
{
|
|
"entropy": 5.830280351638794,
|
|
"epoch": 0.6399673439767779,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004965978323477478,
|
|
"loss": 5.6666,
|
|
"mean_token_accuracy": 0.15999540388584138,
|
|
"num_tokens": 14620920.0,
|
|
"step": 7055
|
|
},
|
|
{
|
|
"entropy": 5.749770832061768,
|
|
"epoch": 0.6404208998548622,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.000496592224559678,
|
|
"loss": 5.6391,
|
|
"mean_token_accuracy": 0.1565101996064186,
|
|
"num_tokens": 14632276.0,
|
|
"step": 7060
|
|
},
|
|
{
|
|
"entropy": 5.802860307693481,
|
|
"epoch": 0.6408744557329463,
|
|
"grad_norm": 2.984375,
|
|
"learning_rate": 0.0004965866121890245,
|
|
"loss": 5.6684,
|
|
"mean_token_accuracy": 0.15125177726149558,
|
|
"num_tokens": 14642157.0,
|
|
"step": 7065
|
|
},
|
|
{
|
|
"entropy": 5.779751205444336,
|
|
"epoch": 0.6413280116110305,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004965809952359034,
|
|
"loss": 5.6914,
|
|
"mean_token_accuracy": 0.15314176827669143,
|
|
"num_tokens": 14652064.0,
|
|
"step": 7070
|
|
},
|
|
{
|
|
"entropy": 5.74179048538208,
|
|
"epoch": 0.6417815674891146,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004965753737004309,
|
|
"loss": 5.5452,
|
|
"mean_token_accuracy": 0.16850573122501372,
|
|
"num_tokens": 14662453.0,
|
|
"step": 7075
|
|
},
|
|
{
|
|
"entropy": 5.78868989944458,
|
|
"epoch": 0.6422351233671988,
|
|
"grad_norm": 2.5625,
|
|
"learning_rate": 0.0004965697475827231,
|
|
"loss": 5.6231,
|
|
"mean_token_accuracy": 0.15645025074481964,
|
|
"num_tokens": 14672401.0,
|
|
"step": 7080
|
|
},
|
|
{
|
|
"entropy": 5.757748985290528,
|
|
"epoch": 0.6426886792452831,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004965641168828965,
|
|
"loss": 5.5881,
|
|
"mean_token_accuracy": 0.16255136281251908,
|
|
"num_tokens": 14682303.0,
|
|
"step": 7085
|
|
},
|
|
{
|
|
"entropy": 5.659681272506714,
|
|
"epoch": 0.6431422351233672,
|
|
"grad_norm": 2.546875,
|
|
"learning_rate": 0.0004965584816010676,
|
|
"loss": 5.6187,
|
|
"mean_token_accuracy": 0.15641136169433595,
|
|
"num_tokens": 14692755.0,
|
|
"step": 7090
|
|
},
|
|
{
|
|
"entropy": 5.723596239089966,
|
|
"epoch": 0.6435957910014514,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.0004965528417373528,
|
|
"loss": 5.6507,
|
|
"mean_token_accuracy": 0.1553022474050522,
|
|
"num_tokens": 14702287.0,
|
|
"step": 7095
|
|
},
|
|
{
|
|
"entropy": 5.774320077896118,
|
|
"epoch": 0.6440493468795355,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.0004965471972918688,
|
|
"loss": 5.6367,
|
|
"mean_token_accuracy": 0.1577304020524025,
|
|
"num_tokens": 14712822.0,
|
|
"step": 7100
|
|
},
|
|
{
|
|
"entropy": 5.795932769775391,
|
|
"epoch": 0.6445029027576198,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004965415482647322,
|
|
"loss": 5.6911,
|
|
"mean_token_accuracy": 0.15207866132259368,
|
|
"num_tokens": 14722465.0,
|
|
"step": 7105
|
|
},
|
|
{
|
|
"entropy": 5.873976182937622,
|
|
"epoch": 0.6449564586357039,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.00049653589465606,
|
|
"loss": 5.686,
|
|
"mean_token_accuracy": 0.14748817309737206,
|
|
"num_tokens": 14732383.0,
|
|
"step": 7110
|
|
},
|
|
{
|
|
"entropy": 5.83858470916748,
|
|
"epoch": 0.6454100145137881,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.000496530236465969,
|
|
"loss": 5.6808,
|
|
"mean_token_accuracy": 0.15343698859214783,
|
|
"num_tokens": 14742825.0,
|
|
"step": 7115
|
|
},
|
|
{
|
|
"entropy": 5.761218690872193,
|
|
"epoch": 0.6458635703918723,
|
|
"grad_norm": 2.546875,
|
|
"learning_rate": 0.0004965245736945763,
|
|
"loss": 5.6028,
|
|
"mean_token_accuracy": 0.1588575080037117,
|
|
"num_tokens": 14753940.0,
|
|
"step": 7120
|
|
},
|
|
{
|
|
"entropy": 5.685926914215088,
|
|
"epoch": 0.6463171262699564,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004965189063419989,
|
|
"loss": 5.549,
|
|
"mean_token_accuracy": 0.1539071559906006,
|
|
"num_tokens": 14763444.0,
|
|
"step": 7125
|
|
},
|
|
{
|
|
"entropy": 5.856564664840699,
|
|
"epoch": 0.6467706821480407,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.0004965132344083541,
|
|
"loss": 5.7704,
|
|
"mean_token_accuracy": 0.15244875699281693,
|
|
"num_tokens": 14774525.0,
|
|
"step": 7130
|
|
},
|
|
{
|
|
"entropy": 5.737270069122315,
|
|
"epoch": 0.6472242380261248,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004965075578937593,
|
|
"loss": 5.6001,
|
|
"mean_token_accuracy": 0.15913221538066863,
|
|
"num_tokens": 14785492.0,
|
|
"step": 7135
|
|
},
|
|
{
|
|
"entropy": 5.875925922393799,
|
|
"epoch": 0.647677793904209,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004965018767983316,
|
|
"loss": 5.7962,
|
|
"mean_token_accuracy": 0.15155397430062295,
|
|
"num_tokens": 14797233.0,
|
|
"step": 7140
|
|
},
|
|
{
|
|
"entropy": 5.837768793106079,
|
|
"epoch": 0.6481313497822931,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004964961911221886,
|
|
"loss": 5.694,
|
|
"mean_token_accuracy": 0.1549917936325073,
|
|
"num_tokens": 14807610.0,
|
|
"step": 7145
|
|
},
|
|
{
|
|
"entropy": 5.742002344131469,
|
|
"epoch": 0.6485849056603774,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.000496490500865448,
|
|
"loss": 5.6285,
|
|
"mean_token_accuracy": 0.15471679270267485,
|
|
"num_tokens": 14817597.0,
|
|
"step": 7150
|
|
},
|
|
{
|
|
"entropy": 5.7524909496307375,
|
|
"epoch": 0.6490384615384616,
|
|
"grad_norm": 8.9375,
|
|
"learning_rate": 0.0004964848060282275,
|
|
"loss": 5.6661,
|
|
"mean_token_accuracy": 0.1518331825733185,
|
|
"num_tokens": 14827513.0,
|
|
"step": 7155
|
|
},
|
|
{
|
|
"entropy": 5.748018884658814,
|
|
"epoch": 0.6494920174165457,
|
|
"grad_norm": 2.578125,
|
|
"learning_rate": 0.0004964791066106447,
|
|
"loss": 5.6594,
|
|
"mean_token_accuracy": 0.14663537889719008,
|
|
"num_tokens": 14837784.0,
|
|
"step": 7160
|
|
},
|
|
{
|
|
"entropy": 5.789811134338379,
|
|
"epoch": 0.6499455732946299,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004964734026128175,
|
|
"loss": 5.5844,
|
|
"mean_token_accuracy": 0.15268829762935637,
|
|
"num_tokens": 14847474.0,
|
|
"step": 7165
|
|
},
|
|
{
|
|
"entropy": 5.762783718109131,
|
|
"epoch": 0.650399129172714,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.0004964676940348638,
|
|
"loss": 5.6645,
|
|
"mean_token_accuracy": 0.15334188491106032,
|
|
"num_tokens": 14858131.0,
|
|
"step": 7170
|
|
},
|
|
{
|
|
"entropy": 5.6948158740997314,
|
|
"epoch": 0.6508526850507983,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.000496461980876902,
|
|
"loss": 5.5902,
|
|
"mean_token_accuracy": 0.15793971568346024,
|
|
"num_tokens": 14868043.0,
|
|
"step": 7175
|
|
},
|
|
{
|
|
"entropy": 5.692598724365235,
|
|
"epoch": 0.6513062409288825,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004964562631390498,
|
|
"loss": 5.6761,
|
|
"mean_token_accuracy": 0.15024179071187974,
|
|
"num_tokens": 14879402.0,
|
|
"step": 7180
|
|
},
|
|
{
|
|
"entropy": 5.819049215316772,
|
|
"epoch": 0.6517597968069666,
|
|
"grad_norm": 5.84375,
|
|
"learning_rate": 0.0004964505408214257,
|
|
"loss": 5.6883,
|
|
"mean_token_accuracy": 0.1553433708846569,
|
|
"num_tokens": 14888767.0,
|
|
"step": 7185
|
|
},
|
|
{
|
|
"entropy": 5.888611745834351,
|
|
"epoch": 0.6522133526850508,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.000496444813924148,
|
|
"loss": 5.7497,
|
|
"mean_token_accuracy": 0.1503465563058853,
|
|
"num_tokens": 14899521.0,
|
|
"step": 7190
|
|
},
|
|
{
|
|
"entropy": 5.7849202156066895,
|
|
"epoch": 0.652666908563135,
|
|
"grad_norm": 2.765625,
|
|
"learning_rate": 0.0004964390824473351,
|
|
"loss": 5.6453,
|
|
"mean_token_accuracy": 0.15264408886432648,
|
|
"num_tokens": 14910064.0,
|
|
"step": 7195
|
|
},
|
|
{
|
|
"entropy": 5.717181968688965,
|
|
"epoch": 0.6531204644412192,
|
|
"grad_norm": 3.234375,
|
|
"learning_rate": 0.0004964333463911056,
|
|
"loss": 5.6486,
|
|
"mean_token_accuracy": 0.1549953490495682,
|
|
"num_tokens": 14920615.0,
|
|
"step": 7200
|
|
},
|
|
{
|
|
"entropy": 5.768748188018799,
|
|
"epoch": 0.6535740203193033,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.0004964276057555779,
|
|
"loss": 5.623,
|
|
"mean_token_accuracy": 0.15831194072961807,
|
|
"num_tokens": 14930898.0,
|
|
"step": 7205
|
|
},
|
|
{
|
|
"entropy": 5.765206909179687,
|
|
"epoch": 0.6540275761973875,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.000496421860540871,
|
|
"loss": 5.6272,
|
|
"mean_token_accuracy": 0.15775293558835984,
|
|
"num_tokens": 14941382.0,
|
|
"step": 7210
|
|
},
|
|
{
|
|
"entropy": 5.624998140335083,
|
|
"epoch": 0.6544811320754716,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.0004964161107471036,
|
|
"loss": 5.5546,
|
|
"mean_token_accuracy": 0.15523957312107087,
|
|
"num_tokens": 14951861.0,
|
|
"step": 7215
|
|
},
|
|
{
|
|
"entropy": 5.669314670562744,
|
|
"epoch": 0.6549346879535559,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.0004964103563743946,
|
|
"loss": 5.5826,
|
|
"mean_token_accuracy": 0.1575288936495781,
|
|
"num_tokens": 14963020.0,
|
|
"step": 7220
|
|
},
|
|
{
|
|
"entropy": 5.838380432128906,
|
|
"epoch": 0.6553882438316401,
|
|
"grad_norm": 2.578125,
|
|
"learning_rate": 0.000496404597422863,
|
|
"loss": 5.6188,
|
|
"mean_token_accuracy": 0.15720368474721907,
|
|
"num_tokens": 14973620.0,
|
|
"step": 7225
|
|
},
|
|
{
|
|
"entropy": 5.734775161743164,
|
|
"epoch": 0.6558417997097242,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.000496398833892628,
|
|
"loss": 5.7175,
|
|
"mean_token_accuracy": 0.1475665733218193,
|
|
"num_tokens": 14983969.0,
|
|
"step": 7230
|
|
},
|
|
{
|
|
"entropy": 5.717875051498413,
|
|
"epoch": 0.6562953555878084,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004963930657838086,
|
|
"loss": 5.6719,
|
|
"mean_token_accuracy": 0.1505054220557213,
|
|
"num_tokens": 14994438.0,
|
|
"step": 7235
|
|
},
|
|
{
|
|
"entropy": 5.843153429031372,
|
|
"epoch": 0.6567489114658926,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004963872930965242,
|
|
"loss": 5.699,
|
|
"mean_token_accuracy": 0.155305315554142,
|
|
"num_tokens": 15003207.0,
|
|
"step": 7240
|
|
},
|
|
{
|
|
"entropy": 5.77896466255188,
|
|
"epoch": 0.6572024673439768,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004963815158308941,
|
|
"loss": 5.6389,
|
|
"mean_token_accuracy": 0.15391478836536407,
|
|
"num_tokens": 15013790.0,
|
|
"step": 7245
|
|
},
|
|
{
|
|
"entropy": 5.778300809860229,
|
|
"epoch": 0.657656023222061,
|
|
"grad_norm": 2.546875,
|
|
"learning_rate": 0.0004963757339870379,
|
|
"loss": 5.6989,
|
|
"mean_token_accuracy": 0.15003085732460023,
|
|
"num_tokens": 15023865.0,
|
|
"step": 7250
|
|
},
|
|
{
|
|
"entropy": 5.805723381042481,
|
|
"epoch": 0.6581095791001451,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004963699475650751,
|
|
"loss": 5.6206,
|
|
"mean_token_accuracy": 0.15242163538932801,
|
|
"num_tokens": 15034634.0,
|
|
"step": 7255
|
|
},
|
|
{
|
|
"entropy": 5.688724994659424,
|
|
"epoch": 0.6585631349782293,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004963641565651255,
|
|
"loss": 5.5843,
|
|
"mean_token_accuracy": 0.15689052790403366,
|
|
"num_tokens": 15045480.0,
|
|
"step": 7260
|
|
},
|
|
{
|
|
"entropy": 5.75483250617981,
|
|
"epoch": 0.6590166908563135,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004963583609873084,
|
|
"loss": 5.6091,
|
|
"mean_token_accuracy": 0.15482414066791533,
|
|
"num_tokens": 15055767.0,
|
|
"step": 7265
|
|
},
|
|
{
|
|
"entropy": 5.742184638977051,
|
|
"epoch": 0.6594702467343977,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.0004963525608317443,
|
|
"loss": 5.6595,
|
|
"mean_token_accuracy": 0.15763870850205422,
|
|
"num_tokens": 15065188.0,
|
|
"step": 7270
|
|
},
|
|
{
|
|
"entropy": 5.7832114696502686,
|
|
"epoch": 0.6599238026124818,
|
|
"grad_norm": 2.859375,
|
|
"learning_rate": 0.0004963467560985527,
|
|
"loss": 5.5517,
|
|
"mean_token_accuracy": 0.15959886014461516,
|
|
"num_tokens": 15075239.0,
|
|
"step": 7275
|
|
},
|
|
{
|
|
"entropy": 5.752000141143799,
|
|
"epoch": 0.660377358490566,
|
|
"grad_norm": 2.90625,
|
|
"learning_rate": 0.0004963409467878538,
|
|
"loss": 5.6148,
|
|
"mean_token_accuracy": 0.1531253769993782,
|
|
"num_tokens": 15085536.0,
|
|
"step": 7280
|
|
},
|
|
{
|
|
"entropy": 5.8153458595275875,
|
|
"epoch": 0.6608309143686503,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004963351328997678,
|
|
"loss": 5.7816,
|
|
"mean_token_accuracy": 0.14753858521580696,
|
|
"num_tokens": 15095936.0,
|
|
"step": 7285
|
|
},
|
|
{
|
|
"entropy": 5.833991146087646,
|
|
"epoch": 0.6612844702467344,
|
|
"grad_norm": 2.59375,
|
|
"learning_rate": 0.0004963293144344148,
|
|
"loss": 5.6535,
|
|
"mean_token_accuracy": 0.15266314893960953,
|
|
"num_tokens": 15106325.0,
|
|
"step": 7290
|
|
},
|
|
{
|
|
"entropy": 5.7682592391967775,
|
|
"epoch": 0.6617380261248186,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.0004963234913919151,
|
|
"loss": 5.7054,
|
|
"mean_token_accuracy": 0.15318630784749984,
|
|
"num_tokens": 15115931.0,
|
|
"step": 7295
|
|
},
|
|
{
|
|
"entropy": 5.7971700668334964,
|
|
"epoch": 0.6621915820029027,
|
|
"grad_norm": 2.9375,
|
|
"learning_rate": 0.0004963176637723893,
|
|
"loss": 5.6707,
|
|
"mean_token_accuracy": 0.1473408728837967,
|
|
"num_tokens": 15127135.0,
|
|
"step": 7300
|
|
},
|
|
{
|
|
"entropy": 5.817535829544068,
|
|
"epoch": 0.6626451378809869,
|
|
"grad_norm": 4.40625,
|
|
"learning_rate": 0.0004963118315759578,
|
|
"loss": 5.5924,
|
|
"mean_token_accuracy": 0.15909394025802612,
|
|
"num_tokens": 15137630.0,
|
|
"step": 7305
|
|
},
|
|
{
|
|
"entropy": 5.770307350158691,
|
|
"epoch": 0.6630986937590712,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004963059948027411,
|
|
"loss": 5.6327,
|
|
"mean_token_accuracy": 0.15045290142297746,
|
|
"num_tokens": 15148213.0,
|
|
"step": 7310
|
|
},
|
|
{
|
|
"entropy": 5.739968776702881,
|
|
"epoch": 0.6635522496371553,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004963001534528601,
|
|
"loss": 5.6957,
|
|
"mean_token_accuracy": 0.1551074802875519,
|
|
"num_tokens": 15158935.0,
|
|
"step": 7315
|
|
},
|
|
{
|
|
"entropy": 5.958873510360718,
|
|
"epoch": 0.6640058055152395,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.0004962943075264355,
|
|
"loss": 5.7541,
|
|
"mean_token_accuracy": 0.14737973362207413,
|
|
"num_tokens": 15169340.0,
|
|
"step": 7320
|
|
},
|
|
{
|
|
"entropy": 5.8249119281768795,
|
|
"epoch": 0.6644593613933236,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.0004962884570235884,
|
|
"loss": 5.6232,
|
|
"mean_token_accuracy": 0.16361132264137268,
|
|
"num_tokens": 15179379.0,
|
|
"step": 7325
|
|
},
|
|
{
|
|
"entropy": 5.805804586410522,
|
|
"epoch": 0.6649129172714079,
|
|
"grad_norm": 3.125,
|
|
"learning_rate": 0.0004962826019444394,
|
|
"loss": 5.6561,
|
|
"mean_token_accuracy": 0.15069231912493705,
|
|
"num_tokens": 15190541.0,
|
|
"step": 7330
|
|
},
|
|
{
|
|
"entropy": 5.730593013763428,
|
|
"epoch": 0.665366473149492,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.0004962767422891099,
|
|
"loss": 5.7166,
|
|
"mean_token_accuracy": 0.15048963874578475,
|
|
"num_tokens": 15201037.0,
|
|
"step": 7335
|
|
},
|
|
{
|
|
"entropy": 5.74660177230835,
|
|
"epoch": 0.6658200290275762,
|
|
"grad_norm": 2.546875,
|
|
"learning_rate": 0.000496270878057721,
|
|
"loss": 5.6135,
|
|
"mean_token_accuracy": 0.15499601513147354,
|
|
"num_tokens": 15211251.0,
|
|
"step": 7340
|
|
},
|
|
{
|
|
"entropy": 5.80778317451477,
|
|
"epoch": 0.6662735849056604,
|
|
"grad_norm": 3.234375,
|
|
"learning_rate": 0.0004962650092503939,
|
|
"loss": 5.7003,
|
|
"mean_token_accuracy": 0.15415400862693787,
|
|
"num_tokens": 15222570.0,
|
|
"step": 7345
|
|
},
|
|
{
|
|
"entropy": 5.7889422416687015,
|
|
"epoch": 0.6667271407837445,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 0.0004962591358672502,
|
|
"loss": 5.7097,
|
|
"mean_token_accuracy": 0.14391579180955888,
|
|
"num_tokens": 15234249.0,
|
|
"step": 7350
|
|
},
|
|
{
|
|
"entropy": 5.856886482238769,
|
|
"epoch": 0.6671806966618288,
|
|
"grad_norm": 3.0,
|
|
"learning_rate": 0.000496253257908411,
|
|
"loss": 5.6874,
|
|
"mean_token_accuracy": 0.14728525504469872,
|
|
"num_tokens": 15245700.0,
|
|
"step": 7355
|
|
},
|
|
{
|
|
"entropy": 5.794812297821045,
|
|
"epoch": 0.6676342525399129,
|
|
"grad_norm": 3.328125,
|
|
"learning_rate": 0.0004962473753739981,
|
|
"loss": 5.5625,
|
|
"mean_token_accuracy": 0.1574371039867401,
|
|
"num_tokens": 15256188.0,
|
|
"step": 7360
|
|
},
|
|
{
|
|
"entropy": 5.788038730621338,
|
|
"epoch": 0.6680878084179971,
|
|
"grad_norm": 2.65625,
|
|
"learning_rate": 0.000496241488264133,
|
|
"loss": 5.7095,
|
|
"mean_token_accuracy": 0.1524525210261345,
|
|
"num_tokens": 15266192.0,
|
|
"step": 7365
|
|
},
|
|
{
|
|
"entropy": 5.7125485897064205,
|
|
"epoch": 0.6685413642960812,
|
|
"grad_norm": 2.78125,
|
|
"learning_rate": 0.0004962355965789377,
|
|
"loss": 5.5395,
|
|
"mean_token_accuracy": 0.16337450891733168,
|
|
"num_tokens": 15276153.0,
|
|
"step": 7370
|
|
},
|
|
{
|
|
"entropy": 5.78140549659729,
|
|
"epoch": 0.6689949201741655,
|
|
"grad_norm": 2.734375,
|
|
"learning_rate": 0.0004962297003185338,
|
|
"loss": 5.5682,
|
|
"mean_token_accuracy": 0.15905935019254686,
|
|
"num_tokens": 15286550.0,
|
|
"step": 7375
|
|
},
|
|
{
|
|
"entropy": 5.7345438480377195,
|
|
"epoch": 0.6694484760522497,
|
|
"grad_norm": 2.578125,
|
|
"learning_rate": 0.0004962237994830433,
|
|
"loss": 5.5445,
|
|
"mean_token_accuracy": 0.16051331013441086,
|
|
"num_tokens": 15295744.0,
|
|
"step": 7380
|
|
},
|
|
{
|
|
"entropy": 5.773867893218994,
|
|
"epoch": 0.6699020319303338,
|
|
"grad_norm": 2.625,
|
|
"learning_rate": 0.0004962178940725883,
|
|
"loss": 5.7362,
|
|
"mean_token_accuracy": 0.15151843577623367,
|
|
"num_tokens": 15305714.0,
|
|
"step": 7385
|
|
},
|
|
{
|
|
"entropy": 5.823055791854858,
|
|
"epoch": 0.670355587808418,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004962119840872908,
|
|
"loss": 5.6613,
|
|
"mean_token_accuracy": 0.15356993973255156,
|
|
"num_tokens": 15316242.0,
|
|
"step": 7390
|
|
},
|
|
{
|
|
"entropy": 5.808695125579834,
|
|
"epoch": 0.6708091436865021,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004962060695272733,
|
|
"loss": 5.633,
|
|
"mean_token_accuracy": 0.15865534245967866,
|
|
"num_tokens": 15327866.0,
|
|
"step": 7395
|
|
},
|
|
{
|
|
"entropy": 5.703290224075317,
|
|
"epoch": 0.6712626995645864,
|
|
"grad_norm": 3.625,
|
|
"learning_rate": 0.0004962001503926577,
|
|
"loss": 5.5731,
|
|
"mean_token_accuracy": 0.1596434235572815,
|
|
"num_tokens": 15337637.0,
|
|
"step": 7400
|
|
},
|
|
{
|
|
"entropy": 5.727995681762695,
|
|
"epoch": 0.6717162554426706,
|
|
"grad_norm": 2.953125,
|
|
"learning_rate": 0.0004961942266835667,
|
|
"loss": 5.5836,
|
|
"mean_token_accuracy": 0.16144115775823592,
|
|
"num_tokens": 15348251.0,
|
|
"step": 7405
|
|
},
|
|
{
|
|
"entropy": 5.7869203090667725,
|
|
"epoch": 0.6721698113207547,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.0004961882984001227,
|
|
"loss": 5.6411,
|
|
"mean_token_accuracy": 0.1619863986968994,
|
|
"num_tokens": 15359110.0,
|
|
"step": 7410
|
|
},
|
|
{
|
|
"entropy": 5.761856365203857,
|
|
"epoch": 0.6726233671988389,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004961823655424484,
|
|
"loss": 5.6026,
|
|
"mean_token_accuracy": 0.1580844432115555,
|
|
"num_tokens": 15369262.0,
|
|
"step": 7415
|
|
},
|
|
{
|
|
"entropy": 5.71964659690857,
|
|
"epoch": 0.6730769230769231,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004961764281106664,
|
|
"loss": 5.6207,
|
|
"mean_token_accuracy": 0.15937441885471343,
|
|
"num_tokens": 15379575.0,
|
|
"step": 7420
|
|
},
|
|
{
|
|
"entropy": 5.673692226409912,
|
|
"epoch": 0.6735304789550073,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004961704861048995,
|
|
"loss": 5.6239,
|
|
"mean_token_accuracy": 0.15601730197668076,
|
|
"num_tokens": 15389921.0,
|
|
"step": 7425
|
|
},
|
|
{
|
|
"entropy": 5.743194484710694,
|
|
"epoch": 0.6739840348330914,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.0004961645395252705,
|
|
"loss": 5.6007,
|
|
"mean_token_accuracy": 0.15587552189826964,
|
|
"num_tokens": 15400337.0,
|
|
"step": 7430
|
|
},
|
|
{
|
|
"entropy": 5.856895065307617,
|
|
"epoch": 0.6744375907111756,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004961585883719025,
|
|
"loss": 5.7093,
|
|
"mean_token_accuracy": 0.14908204078674317,
|
|
"num_tokens": 15410991.0,
|
|
"step": 7435
|
|
},
|
|
{
|
|
"entropy": 5.825889444351196,
|
|
"epoch": 0.6748911465892597,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004961526326449186,
|
|
"loss": 5.5921,
|
|
"mean_token_accuracy": 0.15433028638362883,
|
|
"num_tokens": 15422461.0,
|
|
"step": 7440
|
|
},
|
|
{
|
|
"entropy": 5.803991794586182,
|
|
"epoch": 0.675344702467344,
|
|
"grad_norm": 4.09375,
|
|
"learning_rate": 0.0004961466723444419,
|
|
"loss": 5.6539,
|
|
"mean_token_accuracy": 0.15517031997442246,
|
|
"num_tokens": 15433886.0,
|
|
"step": 7445
|
|
},
|
|
{
|
|
"entropy": 5.750954961776733,
|
|
"epoch": 0.6757982583454282,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004961407074705955,
|
|
"loss": 5.6019,
|
|
"mean_token_accuracy": 0.16225959807634355,
|
|
"num_tokens": 15443916.0,
|
|
"step": 7450
|
|
},
|
|
{
|
|
"entropy": 5.822095251083374,
|
|
"epoch": 0.6762518142235123,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004961347380235031,
|
|
"loss": 5.698,
|
|
"mean_token_accuracy": 0.15310790091753007,
|
|
"num_tokens": 15454850.0,
|
|
"step": 7455
|
|
},
|
|
{
|
|
"entropy": 5.751259803771973,
|
|
"epoch": 0.6767053701015965,
|
|
"grad_norm": 4.25,
|
|
"learning_rate": 0.0004961287640032879,
|
|
"loss": 5.6157,
|
|
"mean_token_accuracy": 0.15203067883849145,
|
|
"num_tokens": 15465864.0,
|
|
"step": 7460
|
|
},
|
|
{
|
|
"entropy": 5.746591186523437,
|
|
"epoch": 0.6771589259796807,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.0004961227854100734,
|
|
"loss": 5.6146,
|
|
"mean_token_accuracy": 0.16328380554914473,
|
|
"num_tokens": 15476220.0,
|
|
"step": 7465
|
|
},
|
|
{
|
|
"entropy": 5.759153223037719,
|
|
"epoch": 0.6776124818577649,
|
|
"grad_norm": 3.28125,
|
|
"learning_rate": 0.0004961168022439835,
|
|
"loss": 5.6249,
|
|
"mean_token_accuracy": 0.16504578590393065,
|
|
"num_tokens": 15485520.0,
|
|
"step": 7470
|
|
},
|
|
{
|
|
"entropy": 5.799544143676758,
|
|
"epoch": 0.6780660377358491,
|
|
"grad_norm": 2.578125,
|
|
"learning_rate": 0.0004961108145051417,
|
|
"loss": 5.7505,
|
|
"mean_token_accuracy": 0.15364100486040116,
|
|
"num_tokens": 15495985.0,
|
|
"step": 7475
|
|
},
|
|
{
|
|
"entropy": 5.757096481323242,
|
|
"epoch": 0.6785195936139332,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.000496104822193672,
|
|
"loss": 5.5983,
|
|
"mean_token_accuracy": 0.16195390671491622,
|
|
"num_tokens": 15506197.0,
|
|
"step": 7480
|
|
},
|
|
{
|
|
"entropy": 5.837605762481689,
|
|
"epoch": 0.6789731494920174,
|
|
"grad_norm": 5.75,
|
|
"learning_rate": 0.0004960988253096982,
|
|
"loss": 5.6909,
|
|
"mean_token_accuracy": 0.1498675063252449,
|
|
"num_tokens": 15517118.0,
|
|
"step": 7485
|
|
},
|
|
{
|
|
"entropy": 5.707053899765015,
|
|
"epoch": 0.6794267053701016,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004960928238533443,
|
|
"loss": 5.5396,
|
|
"mean_token_accuracy": 0.16033630073070526,
|
|
"num_tokens": 15527139.0,
|
|
"step": 7490
|
|
},
|
|
{
|
|
"entropy": 5.752808523178101,
|
|
"epoch": 0.6798802612481858,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004960868178247344,
|
|
"loss": 5.6271,
|
|
"mean_token_accuracy": 0.1546788454055786,
|
|
"num_tokens": 15537587.0,
|
|
"step": 7495
|
|
},
|
|
{
|
|
"entropy": 5.838334226608277,
|
|
"epoch": 0.68033381712627,
|
|
"grad_norm": 3.5,
|
|
"learning_rate": 0.0004960808072239929,
|
|
"loss": 5.6495,
|
|
"mean_token_accuracy": 0.1564589560031891,
|
|
"num_tokens": 15548150.0,
|
|
"step": 7500
|
|
},
|
|
{
|
|
"entropy": 5.731853485107422,
|
|
"epoch": 0.6807873730043541,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004960747920512439,
|
|
"loss": 5.5362,
|
|
"mean_token_accuracy": 0.16505801677703857,
|
|
"num_tokens": 15556823.0,
|
|
"step": 7505
|
|
},
|
|
{
|
|
"entropy": 5.73565149307251,
|
|
"epoch": 0.6812409288824384,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.000496068772306612,
|
|
"loss": 5.6197,
|
|
"mean_token_accuracy": 0.15065336227416992,
|
|
"num_tokens": 15567363.0,
|
|
"step": 7510
|
|
},
|
|
{
|
|
"entropy": 5.767732715606689,
|
|
"epoch": 0.6816944847605225,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004960627479902214,
|
|
"loss": 5.5834,
|
|
"mean_token_accuracy": 0.15681105405092238,
|
|
"num_tokens": 15578883.0,
|
|
"step": 7515
|
|
},
|
|
{
|
|
"entropy": 5.794985580444336,
|
|
"epoch": 0.6821480406386067,
|
|
"grad_norm": 2.921875,
|
|
"learning_rate": 0.000496056719102197,
|
|
"loss": 5.6213,
|
|
"mean_token_accuracy": 0.15920538753271102,
|
|
"num_tokens": 15588369.0,
|
|
"step": 7520
|
|
},
|
|
{
|
|
"entropy": 5.785487365722656,
|
|
"epoch": 0.6826015965166908,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004960506856426631,
|
|
"loss": 5.6216,
|
|
"mean_token_accuracy": 0.15542096197605132,
|
|
"num_tokens": 15598067.0,
|
|
"step": 7525
|
|
},
|
|
{
|
|
"entropy": 5.724895048141479,
|
|
"epoch": 0.683055152394775,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004960446476117448,
|
|
"loss": 5.6081,
|
|
"mean_token_accuracy": 0.15449175238609314,
|
|
"num_tokens": 15608371.0,
|
|
"step": 7530
|
|
},
|
|
{
|
|
"entropy": 5.796253490447998,
|
|
"epoch": 0.6835087082728593,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004960386050095668,
|
|
"loss": 5.6445,
|
|
"mean_token_accuracy": 0.15603733509778978,
|
|
"num_tokens": 15618528.0,
|
|
"step": 7535
|
|
},
|
|
{
|
|
"entropy": 5.835066938400269,
|
|
"epoch": 0.6839622641509434,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004960325578362543,
|
|
"loss": 5.6333,
|
|
"mean_token_accuracy": 0.15638719648122787,
|
|
"num_tokens": 15629404.0,
|
|
"step": 7540
|
|
},
|
|
{
|
|
"entropy": 5.783228731155395,
|
|
"epoch": 0.6844158200290276,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.000496026506091932,
|
|
"loss": 5.6377,
|
|
"mean_token_accuracy": 0.15859341770410537,
|
|
"num_tokens": 15638699.0,
|
|
"step": 7545
|
|
},
|
|
{
|
|
"entropy": 5.716060590744019,
|
|
"epoch": 0.6848693759071117,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.0004960204497767253,
|
|
"loss": 5.5937,
|
|
"mean_token_accuracy": 0.1556451916694641,
|
|
"num_tokens": 15648584.0,
|
|
"step": 7550
|
|
},
|
|
{
|
|
"entropy": 5.756268310546875,
|
|
"epoch": 0.685322931785196,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.0004960143888907594,
|
|
"loss": 5.6354,
|
|
"mean_token_accuracy": 0.155658258497715,
|
|
"num_tokens": 15658380.0,
|
|
"step": 7555
|
|
},
|
|
{
|
|
"entropy": 5.776474046707153,
|
|
"epoch": 0.6857764876632801,
|
|
"grad_norm": 2.65625,
|
|
"learning_rate": 0.0004960083234341595,
|
|
"loss": 5.6251,
|
|
"mean_token_accuracy": 0.1513867571949959,
|
|
"num_tokens": 15668985.0,
|
|
"step": 7560
|
|
},
|
|
{
|
|
"entropy": 5.786694049835205,
|
|
"epoch": 0.6862300435413643,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.0004960022534070513,
|
|
"loss": 5.6428,
|
|
"mean_token_accuracy": 0.15910421460866928,
|
|
"num_tokens": 15679580.0,
|
|
"step": 7565
|
|
},
|
|
{
|
|
"entropy": 5.808306264877319,
|
|
"epoch": 0.6866835994194485,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.00049599617880956,
|
|
"loss": 5.568,
|
|
"mean_token_accuracy": 0.15407638102769852,
|
|
"num_tokens": 15689370.0,
|
|
"step": 7570
|
|
},
|
|
{
|
|
"entropy": 5.85495958328247,
|
|
"epoch": 0.6871371552975326,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004959900996418115,
|
|
"loss": 5.6215,
|
|
"mean_token_accuracy": 0.15530932694673538,
|
|
"num_tokens": 15699550.0,
|
|
"step": 7575
|
|
},
|
|
{
|
|
"entropy": 5.779028224945068,
|
|
"epoch": 0.6875907111756169,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.0004959840159039315,
|
|
"loss": 5.5976,
|
|
"mean_token_accuracy": 0.15754030644893646,
|
|
"num_tokens": 15709154.0,
|
|
"step": 7580
|
|
},
|
|
{
|
|
"entropy": 5.738972902297974,
|
|
"epoch": 0.688044267053701,
|
|
"grad_norm": 2.765625,
|
|
"learning_rate": 0.0004959779275960456,
|
|
"loss": 5.6034,
|
|
"mean_token_accuracy": 0.156924332678318,
|
|
"num_tokens": 15718986.0,
|
|
"step": 7585
|
|
},
|
|
{
|
|
"entropy": 5.758720874786377,
|
|
"epoch": 0.6884978229317852,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.00049597183471828,
|
|
"loss": 5.7098,
|
|
"mean_token_accuracy": 0.1517290487885475,
|
|
"num_tokens": 15729831.0,
|
|
"step": 7590
|
|
},
|
|
{
|
|
"entropy": 5.7619225025177006,
|
|
"epoch": 0.6889513788098693,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 0.0004959657372707604,
|
|
"loss": 5.6082,
|
|
"mean_token_accuracy": 0.15668279379606248,
|
|
"num_tokens": 15740744.0,
|
|
"step": 7595
|
|
},
|
|
{
|
|
"entropy": 5.871711540222168,
|
|
"epoch": 0.6894049346879536,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004959596352536132,
|
|
"loss": 5.6682,
|
|
"mean_token_accuracy": 0.1494604229927063,
|
|
"num_tokens": 15751276.0,
|
|
"step": 7600
|
|
},
|
|
{
|
|
"entropy": 5.821166944503784,
|
|
"epoch": 0.6898584905660378,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004959535286669643,
|
|
"loss": 5.7332,
|
|
"mean_token_accuracy": 0.1462290406227112,
|
|
"num_tokens": 15760712.0,
|
|
"step": 7605
|
|
},
|
|
{
|
|
"entropy": 5.755332994461059,
|
|
"epoch": 0.6903120464441219,
|
|
"grad_norm": 2.546875,
|
|
"learning_rate": 0.0004959474175109402,
|
|
"loss": 5.5798,
|
|
"mean_token_accuracy": 0.15510290414094924,
|
|
"num_tokens": 15771181.0,
|
|
"step": 7610
|
|
},
|
|
{
|
|
"entropy": 5.8319721698760985,
|
|
"epoch": 0.6907656023222061,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004959413017856672,
|
|
"loss": 5.6511,
|
|
"mean_token_accuracy": 0.15570543259382247,
|
|
"num_tokens": 15781961.0,
|
|
"step": 7615
|
|
},
|
|
{
|
|
"entropy": 5.7967523574829105,
|
|
"epoch": 0.6912191582002902,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004959351814912716,
|
|
"loss": 5.6091,
|
|
"mean_token_accuracy": 0.1566801279783249,
|
|
"num_tokens": 15791698.0,
|
|
"step": 7620
|
|
},
|
|
{
|
|
"entropy": 5.702476692199707,
|
|
"epoch": 0.6916727140783745,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.0004959290566278803,
|
|
"loss": 5.6507,
|
|
"mean_token_accuracy": 0.16049251705408096,
|
|
"num_tokens": 15801548.0,
|
|
"step": 7625
|
|
},
|
|
{
|
|
"entropy": 5.765924978256225,
|
|
"epoch": 0.6921262699564587,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.0004959229271956199,
|
|
"loss": 5.6014,
|
|
"mean_token_accuracy": 0.15736598521471024,
|
|
"num_tokens": 15811803.0,
|
|
"step": 7630
|
|
},
|
|
{
|
|
"entropy": 5.76936936378479,
|
|
"epoch": 0.6925798258345428,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.0004959167931946169,
|
|
"loss": 5.6614,
|
|
"mean_token_accuracy": 0.15406277179718017,
|
|
"num_tokens": 15822517.0,
|
|
"step": 7635
|
|
},
|
|
{
|
|
"entropy": 5.85416088104248,
|
|
"epoch": 0.693033381712627,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.0004959106546249984,
|
|
"loss": 5.6164,
|
|
"mean_token_accuracy": 0.156121689081192,
|
|
"num_tokens": 15833545.0,
|
|
"step": 7640
|
|
},
|
|
{
|
|
"entropy": 5.821361637115478,
|
|
"epoch": 0.6934869375907112,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.0004959045114868913,
|
|
"loss": 5.652,
|
|
"mean_token_accuracy": 0.15600253492593766,
|
|
"num_tokens": 15843268.0,
|
|
"step": 7645
|
|
},
|
|
{
|
|
"entropy": 5.740662336349487,
|
|
"epoch": 0.6939404934687954,
|
|
"grad_norm": 2.546875,
|
|
"learning_rate": 0.0004958983637804225,
|
|
"loss": 5.6603,
|
|
"mean_token_accuracy": 0.14992515444755555,
|
|
"num_tokens": 15853536.0,
|
|
"step": 7650
|
|
},
|
|
{
|
|
"entropy": 5.813490200042724,
|
|
"epoch": 0.6943940493468795,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.0004958922115057194,
|
|
"loss": 5.7926,
|
|
"mean_token_accuracy": 0.14946000128984452,
|
|
"num_tokens": 15864556.0,
|
|
"step": 7655
|
|
},
|
|
{
|
|
"entropy": 5.789173889160156,
|
|
"epoch": 0.6948476052249637,
|
|
"grad_norm": 3.203125,
|
|
"learning_rate": 0.0004958860546629089,
|
|
"loss": 5.6683,
|
|
"mean_token_accuracy": 0.15467981845140458,
|
|
"num_tokens": 15875549.0,
|
|
"step": 7660
|
|
},
|
|
{
|
|
"entropy": 5.797283411026001,
|
|
"epoch": 0.6953011611030478,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.0004958798932521186,
|
|
"loss": 5.6208,
|
|
"mean_token_accuracy": 0.15316513329744338,
|
|
"num_tokens": 15886267.0,
|
|
"step": 7665
|
|
},
|
|
{
|
|
"entropy": 5.779521131515503,
|
|
"epoch": 0.6957547169811321,
|
|
"grad_norm": 2.75,
|
|
"learning_rate": 0.0004958737272734759,
|
|
"loss": 5.632,
|
|
"mean_token_accuracy": 0.16016377806663512,
|
|
"num_tokens": 15895868.0,
|
|
"step": 7670
|
|
},
|
|
{
|
|
"entropy": 5.828088617324829,
|
|
"epoch": 0.6962082728592163,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004958675567271081,
|
|
"loss": 5.6179,
|
|
"mean_token_accuracy": 0.15991605669260026,
|
|
"num_tokens": 15905730.0,
|
|
"step": 7675
|
|
},
|
|
{
|
|
"entropy": 5.72156400680542,
|
|
"epoch": 0.6966618287373004,
|
|
"grad_norm": 4.09375,
|
|
"learning_rate": 0.000495861381613143,
|
|
"loss": 5.562,
|
|
"mean_token_accuracy": 0.15755248963832855,
|
|
"num_tokens": 15914739.0,
|
|
"step": 7680
|
|
},
|
|
{
|
|
"entropy": 5.748574733734131,
|
|
"epoch": 0.6971153846153846,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.0004958552019317082,
|
|
"loss": 5.7024,
|
|
"mean_token_accuracy": 0.1518580734729767,
|
|
"num_tokens": 15925572.0,
|
|
"step": 7685
|
|
},
|
|
{
|
|
"entropy": 5.821613073348999,
|
|
"epoch": 0.6975689404934688,
|
|
"grad_norm": 2.53125,
|
|
"learning_rate": 0.0004958490176829316,
|
|
"loss": 5.5996,
|
|
"mean_token_accuracy": 0.15947918295860292,
|
|
"num_tokens": 15935404.0,
|
|
"step": 7690
|
|
},
|
|
{
|
|
"entropy": 5.715131044387817,
|
|
"epoch": 0.698022496371553,
|
|
"grad_norm": 3.34375,
|
|
"learning_rate": 0.000495842828866941,
|
|
"loss": 5.5441,
|
|
"mean_token_accuracy": 0.1586695820093155,
|
|
"num_tokens": 15945645.0,
|
|
"step": 7695
|
|
},
|
|
{
|
|
"entropy": 5.725367069244385,
|
|
"epoch": 0.6984760522496372,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 0.0004958366354838645,
|
|
"loss": 5.7413,
|
|
"mean_token_accuracy": 0.14621049761772156,
|
|
"num_tokens": 15956199.0,
|
|
"step": 7700
|
|
},
|
|
{
|
|
"entropy": 5.833576679229736,
|
|
"epoch": 0.6989296081277213,
|
|
"grad_norm": 3.125,
|
|
"learning_rate": 0.00049583043753383,
|
|
"loss": 5.6137,
|
|
"mean_token_accuracy": 0.15554548054933548,
|
|
"num_tokens": 15965735.0,
|
|
"step": 7705
|
|
},
|
|
{
|
|
"entropy": 5.826115322113037,
|
|
"epoch": 0.6993831640058055,
|
|
"grad_norm": 2.703125,
|
|
"learning_rate": 0.0004958242350169658,
|
|
"loss": 5.614,
|
|
"mean_token_accuracy": 0.15189761221408843,
|
|
"num_tokens": 15977309.0,
|
|
"step": 7710
|
|
},
|
|
{
|
|
"entropy": 5.726123428344726,
|
|
"epoch": 0.6998367198838897,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004958180279334001,
|
|
"loss": 5.6235,
|
|
"mean_token_accuracy": 0.15755776464939117,
|
|
"num_tokens": 15987088.0,
|
|
"step": 7715
|
|
},
|
|
{
|
|
"entropy": 5.771232986450196,
|
|
"epoch": 0.7002902757619739,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004958118162832614,
|
|
"loss": 5.5501,
|
|
"mean_token_accuracy": 0.15842127054929733,
|
|
"num_tokens": 15997205.0,
|
|
"step": 7720
|
|
},
|
|
{
|
|
"entropy": 5.831286382675171,
|
|
"epoch": 0.700743831640058,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004958056000666781,
|
|
"loss": 5.6839,
|
|
"mean_token_accuracy": 0.15873701274394988,
|
|
"num_tokens": 16007183.0,
|
|
"step": 7725
|
|
},
|
|
{
|
|
"entropy": 5.806853771209717,
|
|
"epoch": 0.7011973875181422,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004957993792837786,
|
|
"loss": 5.6787,
|
|
"mean_token_accuracy": 0.1472954660654068,
|
|
"num_tokens": 16017552.0,
|
|
"step": 7730
|
|
},
|
|
{
|
|
"entropy": 5.719517374038697,
|
|
"epoch": 0.7016509433962265,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.0004957931539346917,
|
|
"loss": 5.663,
|
|
"mean_token_accuracy": 0.15673764497041703,
|
|
"num_tokens": 16027288.0,
|
|
"step": 7735
|
|
},
|
|
{
|
|
"entropy": 5.825142192840576,
|
|
"epoch": 0.7021044992743106,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 0.0004957869240195462,
|
|
"loss": 5.7078,
|
|
"mean_token_accuracy": 0.152319223433733,
|
|
"num_tokens": 16038417.0,
|
|
"step": 7740
|
|
},
|
|
{
|
|
"entropy": 5.9004319190979,
|
|
"epoch": 0.7025580551523948,
|
|
"grad_norm": 2.5625,
|
|
"learning_rate": 0.0004957806895384707,
|
|
"loss": 5.636,
|
|
"mean_token_accuracy": 0.15459683537483215,
|
|
"num_tokens": 16048845.0,
|
|
"step": 7745
|
|
},
|
|
{
|
|
"entropy": 5.837311887741089,
|
|
"epoch": 0.7030116110304789,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 0.0004957744504915944,
|
|
"loss": 5.6935,
|
|
"mean_token_accuracy": 0.15696683079004287,
|
|
"num_tokens": 16059005.0,
|
|
"step": 7750
|
|
},
|
|
{
|
|
"entropy": 5.7727942943573,
|
|
"epoch": 0.7034651669085631,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.0004957682068790463,
|
|
"loss": 5.6523,
|
|
"mean_token_accuracy": 0.15422814041376115,
|
|
"num_tokens": 16069286.0,
|
|
"step": 7755
|
|
},
|
|
{
|
|
"entropy": 5.792885828018188,
|
|
"epoch": 0.7039187227866474,
|
|
"grad_norm": 4.1875,
|
|
"learning_rate": 0.0004957619587009553,
|
|
"loss": 5.6301,
|
|
"mean_token_accuracy": 0.15323437005281448,
|
|
"num_tokens": 16080393.0,
|
|
"step": 7760
|
|
},
|
|
{
|
|
"entropy": 5.7808308601379395,
|
|
"epoch": 0.7043722786647315,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 0.0004957557059574507,
|
|
"loss": 5.6183,
|
|
"mean_token_accuracy": 0.15699494183063506,
|
|
"num_tokens": 16091070.0,
|
|
"step": 7765
|
|
},
|
|
{
|
|
"entropy": 5.714521503448486,
|
|
"epoch": 0.7048258345428157,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004957494486486618,
|
|
"loss": 5.5752,
|
|
"mean_token_accuracy": 0.16647447347640992,
|
|
"num_tokens": 16101245.0,
|
|
"step": 7770
|
|
},
|
|
{
|
|
"entropy": 5.702424812316894,
|
|
"epoch": 0.7052793904208998,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.0004957431867747182,
|
|
"loss": 5.5875,
|
|
"mean_token_accuracy": 0.1628919094800949,
|
|
"num_tokens": 16111843.0,
|
|
"step": 7775
|
|
},
|
|
{
|
|
"entropy": 5.80188570022583,
|
|
"epoch": 0.7057329462989841,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 0.0004957369203357492,
|
|
"loss": 5.7144,
|
|
"mean_token_accuracy": 0.14785127192735673,
|
|
"num_tokens": 16122228.0,
|
|
"step": 7780
|
|
},
|
|
{
|
|
"entropy": 5.755620908737183,
|
|
"epoch": 0.7061865021770682,
|
|
"grad_norm": 3.5,
|
|
"learning_rate": 0.0004957306493318844,
|
|
"loss": 5.6445,
|
|
"mean_token_accuracy": 0.1530127450823784,
|
|
"num_tokens": 16131973.0,
|
|
"step": 7785
|
|
},
|
|
{
|
|
"entropy": 5.792283391952514,
|
|
"epoch": 0.7066400580551524,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004957243737632535,
|
|
"loss": 5.6164,
|
|
"mean_token_accuracy": 0.16055547297000886,
|
|
"num_tokens": 16142255.0,
|
|
"step": 7790
|
|
},
|
|
{
|
|
"entropy": 5.7291344165802,
|
|
"epoch": 0.7070936139332366,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004957180936299863,
|
|
"loss": 5.5686,
|
|
"mean_token_accuracy": 0.1609934777021408,
|
|
"num_tokens": 16152513.0,
|
|
"step": 7795
|
|
},
|
|
{
|
|
"entropy": 5.819184160232544,
|
|
"epoch": 0.7075471698113207,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004957118089322127,
|
|
"loss": 5.6822,
|
|
"mean_token_accuracy": 0.16078931242227554,
|
|
"num_tokens": 16163031.0,
|
|
"step": 7800
|
|
},
|
|
{
|
|
"entropy": 5.71607027053833,
|
|
"epoch": 0.708000725689405,
|
|
"grad_norm": 2.90625,
|
|
"learning_rate": 0.0004957055196700628,
|
|
"loss": 5.5735,
|
|
"mean_token_accuracy": 0.14988935440778733,
|
|
"num_tokens": 16174086.0,
|
|
"step": 7805
|
|
},
|
|
{
|
|
"entropy": 5.762309265136719,
|
|
"epoch": 0.7084542815674891,
|
|
"grad_norm": 3.84375,
|
|
"learning_rate": 0.0004956992258436663,
|
|
"loss": 5.724,
|
|
"mean_token_accuracy": 0.15170596539974213,
|
|
"num_tokens": 16184883.0,
|
|
"step": 7810
|
|
},
|
|
{
|
|
"entropy": 5.8683515071868895,
|
|
"epoch": 0.7089078374455733,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004956929274531536,
|
|
"loss": 5.5933,
|
|
"mean_token_accuracy": 0.1518934980034828,
|
|
"num_tokens": 16194956.0,
|
|
"step": 7815
|
|
},
|
|
{
|
|
"entropy": 5.77102632522583,
|
|
"epoch": 0.7093613933236574,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.000495686624498655,
|
|
"loss": 5.6881,
|
|
"mean_token_accuracy": 0.15857531130313873,
|
|
"num_tokens": 16205068.0,
|
|
"step": 7820
|
|
},
|
|
{
|
|
"entropy": 5.7692710876464846,
|
|
"epoch": 0.7098149492017417,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004956803169803007,
|
|
"loss": 5.5364,
|
|
"mean_token_accuracy": 0.15733638405799866,
|
|
"num_tokens": 16215594.0,
|
|
"step": 7825
|
|
},
|
|
{
|
|
"entropy": 5.681814813613892,
|
|
"epoch": 0.7102685050798259,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.0004956740048982212,
|
|
"loss": 5.6427,
|
|
"mean_token_accuracy": 0.1533703476190567,
|
|
"num_tokens": 16226199.0,
|
|
"step": 7830
|
|
},
|
|
{
|
|
"entropy": 5.785719776153565,
|
|
"epoch": 0.71072206095791,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 0.0004956676882525472,
|
|
"loss": 5.5662,
|
|
"mean_token_accuracy": 0.15646980404853822,
|
|
"num_tokens": 16235371.0,
|
|
"step": 7835
|
|
},
|
|
{
|
|
"entropy": 5.838504648208618,
|
|
"epoch": 0.7111756168359942,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.000495661367043409,
|
|
"loss": 5.6853,
|
|
"mean_token_accuracy": 0.1534563809633255,
|
|
"num_tokens": 16246331.0,
|
|
"step": 7840
|
|
},
|
|
{
|
|
"entropy": 5.713598442077637,
|
|
"epoch": 0.7116291727140783,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 0.0004956550412709376,
|
|
"loss": 5.648,
|
|
"mean_token_accuracy": 0.14990029633045196,
|
|
"num_tokens": 16257464.0,
|
|
"step": 7845
|
|
},
|
|
{
|
|
"entropy": 5.703852319717408,
|
|
"epoch": 0.7120827285921626,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 0.0004956487109352637,
|
|
"loss": 5.6172,
|
|
"mean_token_accuracy": 0.15680900365114211,
|
|
"num_tokens": 16267904.0,
|
|
"step": 7850
|
|
},
|
|
{
|
|
"entropy": 5.771894073486328,
|
|
"epoch": 0.7125362844702468,
|
|
"grad_norm": 3.234375,
|
|
"learning_rate": 0.0004956423760365181,
|
|
"loss": 5.6422,
|
|
"mean_token_accuracy": 0.15585129112005233,
|
|
"num_tokens": 16278083.0,
|
|
"step": 7855
|
|
},
|
|
{
|
|
"entropy": 5.734930467605591,
|
|
"epoch": 0.7129898403483309,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.0004956360365748321,
|
|
"loss": 5.5455,
|
|
"mean_token_accuracy": 0.16222757548093797,
|
|
"num_tokens": 16287951.0,
|
|
"step": 7860
|
|
},
|
|
{
|
|
"entropy": 5.726211977005005,
|
|
"epoch": 0.7134433962264151,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.0004956296925503367,
|
|
"loss": 5.632,
|
|
"mean_token_accuracy": 0.16094959080219268,
|
|
"num_tokens": 16298644.0,
|
|
"step": 7865
|
|
},
|
|
{
|
|
"entropy": 5.727968025207519,
|
|
"epoch": 0.7138969521044993,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004956233439631628,
|
|
"loss": 5.6091,
|
|
"mean_token_accuracy": 0.15181788802146912,
|
|
"num_tokens": 16308943.0,
|
|
"step": 7870
|
|
},
|
|
{
|
|
"entropy": 5.750738620758057,
|
|
"epoch": 0.7143505079825835,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004956169908134421,
|
|
"loss": 5.6085,
|
|
"mean_token_accuracy": 0.15787046998739243,
|
|
"num_tokens": 16318878.0,
|
|
"step": 7875
|
|
},
|
|
{
|
|
"entropy": 5.714380550384521,
|
|
"epoch": 0.7148040638606676,
|
|
"grad_norm": 2.765625,
|
|
"learning_rate": 0.0004956106331013057,
|
|
"loss": 5.6173,
|
|
"mean_token_accuracy": 0.1586819350719452,
|
|
"num_tokens": 16328670.0,
|
|
"step": 7880
|
|
},
|
|
{
|
|
"entropy": 5.7483092784881595,
|
|
"epoch": 0.7152576197387518,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.0004956042708268853,
|
|
"loss": 5.6599,
|
|
"mean_token_accuracy": 0.15462943762540818,
|
|
"num_tokens": 16339191.0,
|
|
"step": 7885
|
|
},
|
|
{
|
|
"entropy": 5.711631965637207,
|
|
"epoch": 0.715711175616836,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.0004955979039903123,
|
|
"loss": 5.6154,
|
|
"mean_token_accuracy": 0.15172392278909683,
|
|
"num_tokens": 16349651.0,
|
|
"step": 7890
|
|
},
|
|
{
|
|
"entropy": 5.761837291717529,
|
|
"epoch": 0.7161647314949202,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.0004955915325917183,
|
|
"loss": 5.6736,
|
|
"mean_token_accuracy": 0.15036539286375045,
|
|
"num_tokens": 16359891.0,
|
|
"step": 7895
|
|
},
|
|
{
|
|
"entropy": 5.796342182159424,
|
|
"epoch": 0.7166182873730044,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004955851566312354,
|
|
"loss": 5.5855,
|
|
"mean_token_accuracy": 0.1538383409380913,
|
|
"num_tokens": 16370565.0,
|
|
"step": 7900
|
|
},
|
|
{
|
|
"entropy": 5.758976602554322,
|
|
"epoch": 0.7170718432510885,
|
|
"grad_norm": 3.265625,
|
|
"learning_rate": 0.0004955787761089952,
|
|
"loss": 5.5215,
|
|
"mean_token_accuracy": 0.1601907029747963,
|
|
"num_tokens": 16381637.0,
|
|
"step": 7905
|
|
},
|
|
{
|
|
"entropy": 5.8102165222167965,
|
|
"epoch": 0.7175253991291727,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004955723910251296,
|
|
"loss": 5.8005,
|
|
"mean_token_accuracy": 0.14754390418529512,
|
|
"num_tokens": 16393234.0,
|
|
"step": 7910
|
|
},
|
|
{
|
|
"entropy": 5.769054889678955,
|
|
"epoch": 0.717978955007257,
|
|
"grad_norm": 3.046875,
|
|
"learning_rate": 0.0004955660013797709,
|
|
"loss": 5.6997,
|
|
"mean_token_accuracy": 0.15018021762371064,
|
|
"num_tokens": 16403481.0,
|
|
"step": 7915
|
|
},
|
|
{
|
|
"entropy": 5.920592975616455,
|
|
"epoch": 0.7184325108853411,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.000495559607173051,
|
|
"loss": 5.7689,
|
|
"mean_token_accuracy": 0.14970896393060684,
|
|
"num_tokens": 16413964.0,
|
|
"step": 7920
|
|
},
|
|
{
|
|
"entropy": 5.8974508285522464,
|
|
"epoch": 0.7188860667634253,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004955532084051022,
|
|
"loss": 5.6652,
|
|
"mean_token_accuracy": 0.15549319833517075,
|
|
"num_tokens": 16424819.0,
|
|
"step": 7925
|
|
},
|
|
{
|
|
"entropy": 5.732374620437622,
|
|
"epoch": 0.7193396226415094,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.0004955468050760568,
|
|
"loss": 5.6545,
|
|
"mean_token_accuracy": 0.14865286499261857,
|
|
"num_tokens": 16435916.0,
|
|
"step": 7930
|
|
},
|
|
{
|
|
"entropy": 5.744418716430664,
|
|
"epoch": 0.7197931785195936,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004955403971860474,
|
|
"loss": 5.6068,
|
|
"mean_token_accuracy": 0.15125288367271422,
|
|
"num_tokens": 16446921.0,
|
|
"step": 7935
|
|
},
|
|
{
|
|
"entropy": 5.7707848072052,
|
|
"epoch": 0.7202467343976778,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.0004955339847352063,
|
|
"loss": 5.5614,
|
|
"mean_token_accuracy": 0.1599792793393135,
|
|
"num_tokens": 16456582.0,
|
|
"step": 7940
|
|
},
|
|
{
|
|
"entropy": 5.812472677230835,
|
|
"epoch": 0.720700290275762,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004955275677236662,
|
|
"loss": 5.7195,
|
|
"mean_token_accuracy": 0.15281503647565842,
|
|
"num_tokens": 16467664.0,
|
|
"step": 7945
|
|
},
|
|
{
|
|
"entropy": 5.782000589370727,
|
|
"epoch": 0.7211538461538461,
|
|
"grad_norm": 2.671875,
|
|
"learning_rate": 0.0004955211461515599,
|
|
"loss": 5.6066,
|
|
"mean_token_accuracy": 0.157174314558506,
|
|
"num_tokens": 16477455.0,
|
|
"step": 7950
|
|
},
|
|
{
|
|
"entropy": 5.7062602043151855,
|
|
"epoch": 0.7216074020319303,
|
|
"grad_norm": 6.875,
|
|
"learning_rate": 0.00049551472001902,
|
|
"loss": 5.5268,
|
|
"mean_token_accuracy": 0.16334553211927413,
|
|
"num_tokens": 16487692.0,
|
|
"step": 7955
|
|
},
|
|
{
|
|
"entropy": 5.740776824951172,
|
|
"epoch": 0.7220609579100146,
|
|
"grad_norm": 2.90625,
|
|
"learning_rate": 0.0004955082893261796,
|
|
"loss": 5.7124,
|
|
"mean_token_accuracy": 0.1524514600634575,
|
|
"num_tokens": 16498703.0,
|
|
"step": 7960
|
|
},
|
|
{
|
|
"entropy": 5.847306632995606,
|
|
"epoch": 0.7225145137880987,
|
|
"grad_norm": 2.734375,
|
|
"learning_rate": 0.0004955018540731714,
|
|
"loss": 5.7151,
|
|
"mean_token_accuracy": 0.15303010791540145,
|
|
"num_tokens": 16509586.0,
|
|
"step": 7965
|
|
},
|
|
{
|
|
"entropy": 5.774869918823242,
|
|
"epoch": 0.7229680696661829,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.0004954954142601288,
|
|
"loss": 5.669,
|
|
"mean_token_accuracy": 0.15326018631458282,
|
|
"num_tokens": 16520085.0,
|
|
"step": 7970
|
|
},
|
|
{
|
|
"entropy": 5.768806076049804,
|
|
"epoch": 0.723421625544267,
|
|
"grad_norm": 2.546875,
|
|
"learning_rate": 0.0004954889698871849,
|
|
"loss": 5.5816,
|
|
"mean_token_accuracy": 0.15679601430892945,
|
|
"num_tokens": 16529175.0,
|
|
"step": 7975
|
|
},
|
|
{
|
|
"entropy": 5.801292657852173,
|
|
"epoch": 0.7238751814223512,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.0004954825209544728,
|
|
"loss": 5.6627,
|
|
"mean_token_accuracy": 0.15569547265768052,
|
|
"num_tokens": 16539748.0,
|
|
"step": 7980
|
|
},
|
|
{
|
|
"entropy": 5.879402542114258,
|
|
"epoch": 0.7243287373004355,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.000495476067462126,
|
|
"loss": 5.7705,
|
|
"mean_token_accuracy": 0.14737174212932586,
|
|
"num_tokens": 16550336.0,
|
|
"step": 7985
|
|
},
|
|
{
|
|
"entropy": 5.865490293502807,
|
|
"epoch": 0.7247822931785196,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.000495469609410278,
|
|
"loss": 5.6723,
|
|
"mean_token_accuracy": 0.15798801630735398,
|
|
"num_tokens": 16561695.0,
|
|
"step": 7990
|
|
},
|
|
{
|
|
"entropy": 5.79704737663269,
|
|
"epoch": 0.7252358490566038,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.0004954631467990622,
|
|
"loss": 5.6261,
|
|
"mean_token_accuracy": 0.15744501501321792,
|
|
"num_tokens": 16572281.0,
|
|
"step": 7995
|
|
},
|
|
{
|
|
"entropy": 5.883595323562622,
|
|
"epoch": 0.7256894049346879,
|
|
"grad_norm": 6.03125,
|
|
"learning_rate": 0.0004954566796286124,
|
|
"loss": 5.6853,
|
|
"mean_token_accuracy": 0.15826498866081237,
|
|
"num_tokens": 16582593.0,
|
|
"step": 8000
|
|
},
|
|
{
|
|
"entropy": 5.79354305267334,
|
|
"epoch": 0.7261429608127722,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004954502078990623,
|
|
"loss": 5.6157,
|
|
"mean_token_accuracy": 0.1543182373046875,
|
|
"num_tokens": 16593261.0,
|
|
"step": 8005
|
|
},
|
|
{
|
|
"entropy": 5.762522268295288,
|
|
"epoch": 0.7265965166908563,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.0004954437316105457,
|
|
"loss": 5.6177,
|
|
"mean_token_accuracy": 0.1543796181678772,
|
|
"num_tokens": 16603950.0,
|
|
"step": 8010
|
|
},
|
|
{
|
|
"entropy": 5.761196804046631,
|
|
"epoch": 0.7270500725689405,
|
|
"grad_norm": 3.46875,
|
|
"learning_rate": 0.0004954372507631965,
|
|
"loss": 5.6104,
|
|
"mean_token_accuracy": 0.15392357856035233,
|
|
"num_tokens": 16614029.0,
|
|
"step": 8015
|
|
},
|
|
{
|
|
"entropy": 5.839762258529663,
|
|
"epoch": 0.7275036284470247,
|
|
"grad_norm": 2.96875,
|
|
"learning_rate": 0.0004954307653571489,
|
|
"loss": 5.7144,
|
|
"mean_token_accuracy": 0.15072717517614365,
|
|
"num_tokens": 16623986.0,
|
|
"step": 8020
|
|
},
|
|
{
|
|
"entropy": 5.866214752197266,
|
|
"epoch": 0.7279571843251088,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004954242753925367,
|
|
"loss": 5.6753,
|
|
"mean_token_accuracy": 0.15980619192123413,
|
|
"num_tokens": 16635142.0,
|
|
"step": 8025
|
|
},
|
|
{
|
|
"entropy": 5.823565912246704,
|
|
"epoch": 0.7284107402031931,
|
|
"grad_norm": 2.53125,
|
|
"learning_rate": 0.0004954177808694946,
|
|
"loss": 5.6814,
|
|
"mean_token_accuracy": 0.15356374382972718,
|
|
"num_tokens": 16645853.0,
|
|
"step": 8030
|
|
},
|
|
{
|
|
"entropy": 5.74679708480835,
|
|
"epoch": 0.7288642960812772,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 0.0004954112817881565,
|
|
"loss": 5.5504,
|
|
"mean_token_accuracy": 0.15274393409490586,
|
|
"num_tokens": 16658032.0,
|
|
"step": 8035
|
|
},
|
|
{
|
|
"entropy": 5.746969604492188,
|
|
"epoch": 0.7293178519593614,
|
|
"grad_norm": 4.15625,
|
|
"learning_rate": 0.0004954047781486568,
|
|
"loss": 5.6035,
|
|
"mean_token_accuracy": 0.15604862719774246,
|
|
"num_tokens": 16669622.0,
|
|
"step": 8040
|
|
},
|
|
{
|
|
"entropy": 5.749283409118652,
|
|
"epoch": 0.7297714078374455,
|
|
"grad_norm": 5.15625,
|
|
"learning_rate": 0.0004953982699511303,
|
|
"loss": 5.5584,
|
|
"mean_token_accuracy": 0.1570752292871475,
|
|
"num_tokens": 16678951.0,
|
|
"step": 8045
|
|
},
|
|
{
|
|
"entropy": 5.784296321868896,
|
|
"epoch": 0.7302249637155298,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004953917571957114,
|
|
"loss": 5.5633,
|
|
"mean_token_accuracy": 0.16463075280189515,
|
|
"num_tokens": 16688483.0,
|
|
"step": 8050
|
|
},
|
|
{
|
|
"entropy": 5.709265422821045,
|
|
"epoch": 0.730678519593614,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.0004953852398825346,
|
|
"loss": 5.6235,
|
|
"mean_token_accuracy": 0.15600716024637223,
|
|
"num_tokens": 16698925.0,
|
|
"step": 8055
|
|
},
|
|
{
|
|
"entropy": 5.73402624130249,
|
|
"epoch": 0.7311320754716981,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.000495378718011735,
|
|
"loss": 5.6777,
|
|
"mean_token_accuracy": 0.15115438550710678,
|
|
"num_tokens": 16709313.0,
|
|
"step": 8060
|
|
},
|
|
{
|
|
"entropy": 5.788901710510254,
|
|
"epoch": 0.7315856313497823,
|
|
"grad_norm": 3.078125,
|
|
"learning_rate": 0.0004953721915834473,
|
|
"loss": 5.6161,
|
|
"mean_token_accuracy": 0.15761125236749648,
|
|
"num_tokens": 16719966.0,
|
|
"step": 8065
|
|
},
|
|
{
|
|
"entropy": 5.860734605789185,
|
|
"epoch": 0.7320391872278664,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004953656605978067,
|
|
"loss": 5.5925,
|
|
"mean_token_accuracy": 0.15714126080274582,
|
|
"num_tokens": 16730052.0,
|
|
"step": 8070
|
|
},
|
|
{
|
|
"entropy": 5.775921154022217,
|
|
"epoch": 0.7324927431059507,
|
|
"grad_norm": 2.90625,
|
|
"learning_rate": 0.000495359125054948,
|
|
"loss": 5.6285,
|
|
"mean_token_accuracy": 0.1568572126328945,
|
|
"num_tokens": 16740471.0,
|
|
"step": 8075
|
|
},
|
|
{
|
|
"entropy": 5.775655841827392,
|
|
"epoch": 0.7329462989840348,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004953525849550063,
|
|
"loss": 5.6233,
|
|
"mean_token_accuracy": 0.1591525912284851,
|
|
"num_tokens": 16750457.0,
|
|
"step": 8080
|
|
},
|
|
{
|
|
"entropy": 5.6620911121368405,
|
|
"epoch": 0.733399854862119,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004953460402981172,
|
|
"loss": 5.5487,
|
|
"mean_token_accuracy": 0.16263614743947982,
|
|
"num_tokens": 16760063.0,
|
|
"step": 8085
|
|
},
|
|
{
|
|
"entropy": 5.898888826370239,
|
|
"epoch": 0.7338534107402032,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.0004953394910844157,
|
|
"loss": 5.7878,
|
|
"mean_token_accuracy": 0.14993553906679152,
|
|
"num_tokens": 16771819.0,
|
|
"step": 8090
|
|
},
|
|
{
|
|
"entropy": 5.836102628707886,
|
|
"epoch": 0.7343069666182874,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004953329373140374,
|
|
"loss": 5.5963,
|
|
"mean_token_accuracy": 0.16176689714193343,
|
|
"num_tokens": 16781829.0,
|
|
"step": 8095
|
|
},
|
|
{
|
|
"entropy": 5.846488809585571,
|
|
"epoch": 0.7347605224963716,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004953263789871179,
|
|
"loss": 5.7103,
|
|
"mean_token_accuracy": 0.1524574190378189,
|
|
"num_tokens": 16793126.0,
|
|
"step": 8100
|
|
},
|
|
{
|
|
"entropy": 5.776001596450806,
|
|
"epoch": 0.7352140783744557,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.0004953198161037925,
|
|
"loss": 5.6879,
|
|
"mean_token_accuracy": 0.1541047662496567,
|
|
"num_tokens": 16804189.0,
|
|
"step": 8105
|
|
},
|
|
{
|
|
"entropy": 5.744534158706665,
|
|
"epoch": 0.7356676342525399,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004953132486641975,
|
|
"loss": 5.6032,
|
|
"mean_token_accuracy": 0.1552288293838501,
|
|
"num_tokens": 16814560.0,
|
|
"step": 8110
|
|
},
|
|
{
|
|
"entropy": 5.781995820999145,
|
|
"epoch": 0.736121190130624,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.000495306676668468,
|
|
"loss": 5.6297,
|
|
"mean_token_accuracy": 0.15587210953235625,
|
|
"num_tokens": 16826330.0,
|
|
"step": 8115
|
|
},
|
|
{
|
|
"entropy": 5.711146450042724,
|
|
"epoch": 0.7365747460087083,
|
|
"grad_norm": 3.234375,
|
|
"learning_rate": 0.0004953001001167406,
|
|
"loss": 5.5365,
|
|
"mean_token_accuracy": 0.1646862506866455,
|
|
"num_tokens": 16836364.0,
|
|
"step": 8120
|
|
},
|
|
{
|
|
"entropy": 5.829107332229614,
|
|
"epoch": 0.7370283018867925,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.0004952935190091508,
|
|
"loss": 5.8315,
|
|
"mean_token_accuracy": 0.14338433742523193,
|
|
"num_tokens": 16848299.0,
|
|
"step": 8125
|
|
},
|
|
{
|
|
"entropy": 5.8289862155914305,
|
|
"epoch": 0.7374818577648766,
|
|
"grad_norm": 2.5625,
|
|
"learning_rate": 0.0004952869333458349,
|
|
"loss": 5.6399,
|
|
"mean_token_accuracy": 0.15927838832139968,
|
|
"num_tokens": 16858429.0,
|
|
"step": 8130
|
|
},
|
|
{
|
|
"entropy": 5.874411296844483,
|
|
"epoch": 0.7379354136429608,
|
|
"grad_norm": 3.296875,
|
|
"learning_rate": 0.0004952803431269292,
|
|
"loss": 5.7268,
|
|
"mean_token_accuracy": 0.15126429125666618,
|
|
"num_tokens": 16868821.0,
|
|
"step": 8135
|
|
},
|
|
{
|
|
"entropy": 5.712897443771363,
|
|
"epoch": 0.738388969521045,
|
|
"grad_norm": 2.765625,
|
|
"learning_rate": 0.0004952737483525699,
|
|
"loss": 5.6156,
|
|
"mean_token_accuracy": 0.15641525983810425,
|
|
"num_tokens": 16879542.0,
|
|
"step": 8140
|
|
},
|
|
{
|
|
"entropy": 5.749282312393189,
|
|
"epoch": 0.7388425253991292,
|
|
"grad_norm": 3.015625,
|
|
"learning_rate": 0.0004952671490228932,
|
|
"loss": 5.6272,
|
|
"mean_token_accuracy": 0.15467603206634523,
|
|
"num_tokens": 16889800.0,
|
|
"step": 8145
|
|
},
|
|
{
|
|
"entropy": 5.766307926177978,
|
|
"epoch": 0.7392960812772134,
|
|
"grad_norm": 3.953125,
|
|
"learning_rate": 0.0004952605451380357,
|
|
"loss": 5.5974,
|
|
"mean_token_accuracy": 0.15848799049854279,
|
|
"num_tokens": 16899738.0,
|
|
"step": 8150
|
|
},
|
|
{
|
|
"entropy": 5.850952577590943,
|
|
"epoch": 0.7397496371552975,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.0004952539366981342,
|
|
"loss": 5.7495,
|
|
"mean_token_accuracy": 0.1528501883149147,
|
|
"num_tokens": 16910019.0,
|
|
"step": 8155
|
|
},
|
|
{
|
|
"entropy": 5.77600359916687,
|
|
"epoch": 0.7402031930333817,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.000495247323703325,
|
|
"loss": 5.5283,
|
|
"mean_token_accuracy": 0.16275404244661332,
|
|
"num_tokens": 16920166.0,
|
|
"step": 8160
|
|
},
|
|
{
|
|
"entropy": 5.778176259994507,
|
|
"epoch": 0.7406567489114659,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 0.000495240706153745,
|
|
"loss": 5.6118,
|
|
"mean_token_accuracy": 0.16098765581846236,
|
|
"num_tokens": 16930991.0,
|
|
"step": 8165
|
|
},
|
|
{
|
|
"entropy": 5.7715491771698,
|
|
"epoch": 0.7411103047895501,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004952340840495312,
|
|
"loss": 5.6837,
|
|
"mean_token_accuracy": 0.15464678704738616,
|
|
"num_tokens": 16940784.0,
|
|
"step": 8170
|
|
},
|
|
{
|
|
"entropy": 5.73781452178955,
|
|
"epoch": 0.7415638606676342,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004952274573908203,
|
|
"loss": 5.6423,
|
|
"mean_token_accuracy": 0.1558202624320984,
|
|
"num_tokens": 16951269.0,
|
|
"step": 8175
|
|
},
|
|
{
|
|
"entropy": 5.780189132690429,
|
|
"epoch": 0.7420174165457184,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.0004952208261777496,
|
|
"loss": 5.6643,
|
|
"mean_token_accuracy": 0.14743273556232453,
|
|
"num_tokens": 16962131.0,
|
|
"step": 8180
|
|
},
|
|
{
|
|
"entropy": 5.867283010482788,
|
|
"epoch": 0.7424709724238027,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.000495214190410456,
|
|
"loss": 5.6211,
|
|
"mean_token_accuracy": 0.1474756971001625,
|
|
"num_tokens": 16972515.0,
|
|
"step": 8185
|
|
},
|
|
{
|
|
"entropy": 5.856743240356446,
|
|
"epoch": 0.7429245283018868,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004952075500890768,
|
|
"loss": 5.6941,
|
|
"mean_token_accuracy": 0.15181073695421218,
|
|
"num_tokens": 16982872.0,
|
|
"step": 8190
|
|
},
|
|
{
|
|
"entropy": 5.783583736419677,
|
|
"epoch": 0.743378084179971,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.0004952009052137493,
|
|
"loss": 5.7362,
|
|
"mean_token_accuracy": 0.14678692519664766,
|
|
"num_tokens": 16993033.0,
|
|
"step": 8195
|
|
},
|
|
{
|
|
"entropy": 5.7738844871521,
|
|
"epoch": 0.7438316400580551,
|
|
"grad_norm": 2.96875,
|
|
"learning_rate": 0.0004951942557846112,
|
|
"loss": 5.596,
|
|
"mean_token_accuracy": 0.15392670929431915,
|
|
"num_tokens": 17003663.0,
|
|
"step": 8200
|
|
},
|
|
{
|
|
"entropy": 5.84683928489685,
|
|
"epoch": 0.7442851959361393,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.0004951876018017997,
|
|
"loss": 5.68,
|
|
"mean_token_accuracy": 0.15474024116992952,
|
|
"num_tokens": 17014429.0,
|
|
"step": 8205
|
|
},
|
|
{
|
|
"entropy": 5.869251394271851,
|
|
"epoch": 0.7447387518142236,
|
|
"grad_norm": 2.546875,
|
|
"learning_rate": 0.0004951809432654524,
|
|
"loss": 5.654,
|
|
"mean_token_accuracy": 0.1516743168234825,
|
|
"num_tokens": 17024280.0,
|
|
"step": 8210
|
|
},
|
|
{
|
|
"entropy": 5.767379903793335,
|
|
"epoch": 0.7451923076923077,
|
|
"grad_norm": 2.5625,
|
|
"learning_rate": 0.000495174280175707,
|
|
"loss": 5.717,
|
|
"mean_token_accuracy": 0.1539435014128685,
|
|
"num_tokens": 17033513.0,
|
|
"step": 8215
|
|
},
|
|
{
|
|
"entropy": 5.721969032287598,
|
|
"epoch": 0.7456458635703919,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004951676125327015,
|
|
"loss": 5.6122,
|
|
"mean_token_accuracy": 0.16177385449409484,
|
|
"num_tokens": 17043575.0,
|
|
"step": 8220
|
|
},
|
|
{
|
|
"entropy": 5.779006147384644,
|
|
"epoch": 0.746099419448476,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.0004951609403365737,
|
|
"loss": 5.5797,
|
|
"mean_token_accuracy": 0.1582030788064003,
|
|
"num_tokens": 17055142.0,
|
|
"step": 8225
|
|
},
|
|
{
|
|
"entropy": 5.810242366790772,
|
|
"epoch": 0.7465529753265603,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.0004951542635874615,
|
|
"loss": 5.713,
|
|
"mean_token_accuracy": 0.15055353492498397,
|
|
"num_tokens": 17065492.0,
|
|
"step": 8230
|
|
},
|
|
{
|
|
"entropy": 5.7410260200500485,
|
|
"epoch": 0.7470065312046444,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004951475822855029,
|
|
"loss": 5.6216,
|
|
"mean_token_accuracy": 0.1593379184603691,
|
|
"num_tokens": 17075292.0,
|
|
"step": 8235
|
|
},
|
|
{
|
|
"entropy": 5.731707000732422,
|
|
"epoch": 0.7474600870827286,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004951408964308364,
|
|
"loss": 5.574,
|
|
"mean_token_accuracy": 0.16519616097211837,
|
|
"num_tokens": 17086420.0,
|
|
"step": 8240
|
|
},
|
|
{
|
|
"entropy": 5.760078191757202,
|
|
"epoch": 0.7479136429608128,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004951342060236,
|
|
"loss": 5.5976,
|
|
"mean_token_accuracy": 0.16345851868391037,
|
|
"num_tokens": 17096112.0,
|
|
"step": 8245
|
|
},
|
|
{
|
|
"entropy": 5.8259295463562015,
|
|
"epoch": 0.7483671988388969,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.0004951275110639321,
|
|
"loss": 5.6048,
|
|
"mean_token_accuracy": 0.15585166960954666,
|
|
"num_tokens": 17106368.0,
|
|
"step": 8250
|
|
},
|
|
{
|
|
"entropy": 5.845524835586548,
|
|
"epoch": 0.7488207547169812,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 0.0004951208115519712,
|
|
"loss": 5.5985,
|
|
"mean_token_accuracy": 0.1580975353717804,
|
|
"num_tokens": 17117064.0,
|
|
"step": 8255
|
|
},
|
|
{
|
|
"entropy": 5.746245622634888,
|
|
"epoch": 0.7492743105950653,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004951141074878558,
|
|
"loss": 5.6241,
|
|
"mean_token_accuracy": 0.15599410235881805,
|
|
"num_tokens": 17127396.0,
|
|
"step": 8260
|
|
},
|
|
{
|
|
"entropy": 5.713340950012207,
|
|
"epoch": 0.7497278664731495,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004951073988717246,
|
|
"loss": 5.5972,
|
|
"mean_token_accuracy": 0.16201200038194657,
|
|
"num_tokens": 17137056.0,
|
|
"step": 8265
|
|
},
|
|
{
|
|
"entropy": 5.70338888168335,
|
|
"epoch": 0.7501814223512336,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.0004951006857037163,
|
|
"loss": 5.5687,
|
|
"mean_token_accuracy": 0.15553730726242065,
|
|
"num_tokens": 17148054.0,
|
|
"step": 8270
|
|
},
|
|
{
|
|
"entropy": 5.776705694198609,
|
|
"epoch": 0.7506349782293179,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.0004950939679839696,
|
|
"loss": 5.5931,
|
|
"mean_token_accuracy": 0.15089012086391448,
|
|
"num_tokens": 17158554.0,
|
|
"step": 8275
|
|
},
|
|
{
|
|
"entropy": 5.760802841186523,
|
|
"epoch": 0.7510885341074021,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004950872457126237,
|
|
"loss": 5.6206,
|
|
"mean_token_accuracy": 0.15333060473203658,
|
|
"num_tokens": 17168791.0,
|
|
"step": 8280
|
|
},
|
|
{
|
|
"entropy": 5.830760526657104,
|
|
"epoch": 0.7515420899854862,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.0004950805188898175,
|
|
"loss": 5.6114,
|
|
"mean_token_accuracy": 0.15708001405000688,
|
|
"num_tokens": 17179137.0,
|
|
"step": 8285
|
|
},
|
|
{
|
|
"entropy": 5.764456653594971,
|
|
"epoch": 0.7519956458635704,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.00049507378751569,
|
|
"loss": 5.6338,
|
|
"mean_token_accuracy": 0.15995466858148574,
|
|
"num_tokens": 17189876.0,
|
|
"step": 8290
|
|
},
|
|
{
|
|
"entropy": 5.728210163116455,
|
|
"epoch": 0.7524492017416545,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.0004950670515903805,
|
|
"loss": 5.6227,
|
|
"mean_token_accuracy": 0.16226246654987336,
|
|
"num_tokens": 17199917.0,
|
|
"step": 8295
|
|
},
|
|
{
|
|
"entropy": 5.680912637710572,
|
|
"epoch": 0.7529027576197388,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.0004950603111140283,
|
|
"loss": 5.6616,
|
|
"mean_token_accuracy": 0.15982949137687683,
|
|
"num_tokens": 17210226.0,
|
|
"step": 8300
|
|
},
|
|
{
|
|
"entropy": 5.806912136077881,
|
|
"epoch": 0.753356313497823,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004950535660867728,
|
|
"loss": 5.6707,
|
|
"mean_token_accuracy": 0.15212061628699303,
|
|
"num_tokens": 17221568.0,
|
|
"step": 8305
|
|
},
|
|
{
|
|
"entropy": 5.838203239440918,
|
|
"epoch": 0.7538098693759071,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004950468165087535,
|
|
"loss": 5.6882,
|
|
"mean_token_accuracy": 0.15245482325553894,
|
|
"num_tokens": 17232113.0,
|
|
"step": 8310
|
|
},
|
|
{
|
|
"entropy": 5.797420263290405,
|
|
"epoch": 0.7542634252539913,
|
|
"grad_norm": 2.546875,
|
|
"learning_rate": 0.0004950400623801098,
|
|
"loss": 5.5999,
|
|
"mean_token_accuracy": 0.15840950906276702,
|
|
"num_tokens": 17242343.0,
|
|
"step": 8315
|
|
},
|
|
{
|
|
"entropy": 5.760805130004883,
|
|
"epoch": 0.7547169811320755,
|
|
"grad_norm": 4.09375,
|
|
"learning_rate": 0.0004950333037009818,
|
|
"loss": 5.5942,
|
|
"mean_token_accuracy": 0.161812824010849,
|
|
"num_tokens": 17252371.0,
|
|
"step": 8320
|
|
},
|
|
{
|
|
"entropy": 5.794910717010498,
|
|
"epoch": 0.7551705370101597,
|
|
"grad_norm": 4.25,
|
|
"learning_rate": 0.0004950265404715089,
|
|
"loss": 5.7692,
|
|
"mean_token_accuracy": 0.1482568457722664,
|
|
"num_tokens": 17263675.0,
|
|
"step": 8325
|
|
},
|
|
{
|
|
"entropy": 5.812986516952515,
|
|
"epoch": 0.7556240928882438,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.000495019772691831,
|
|
"loss": 5.7185,
|
|
"mean_token_accuracy": 0.1525795951485634,
|
|
"num_tokens": 17273935.0,
|
|
"step": 8330
|
|
},
|
|
{
|
|
"entropy": 5.8421684265136715,
|
|
"epoch": 0.756077648766328,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.0004950130003620882,
|
|
"loss": 5.5925,
|
|
"mean_token_accuracy": 0.1599227637052536,
|
|
"num_tokens": 17284210.0,
|
|
"step": 8335
|
|
},
|
|
{
|
|
"entropy": 5.706677865982056,
|
|
"epoch": 0.7565312046444121,
|
|
"grad_norm": 2.53125,
|
|
"learning_rate": 0.0004950062234824204,
|
|
"loss": 5.6755,
|
|
"mean_token_accuracy": 0.15375422537326813,
|
|
"num_tokens": 17294923.0,
|
|
"step": 8340
|
|
},
|
|
{
|
|
"entropy": 5.774484586715698,
|
|
"epoch": 0.7569847605224964,
|
|
"grad_norm": 2.765625,
|
|
"learning_rate": 0.0004949994420529679,
|
|
"loss": 5.6753,
|
|
"mean_token_accuracy": 0.15490903407335282,
|
|
"num_tokens": 17305324.0,
|
|
"step": 8345
|
|
},
|
|
{
|
|
"entropy": 5.795401620864868,
|
|
"epoch": 0.7574383164005806,
|
|
"grad_norm": 2.8125,
|
|
"learning_rate": 0.0004949926560738709,
|
|
"loss": 5.5969,
|
|
"mean_token_accuracy": 0.1563528910279274,
|
|
"num_tokens": 17316852.0,
|
|
"step": 8350
|
|
},
|
|
{
|
|
"entropy": 5.723483753204346,
|
|
"epoch": 0.7578918722786647,
|
|
"grad_norm": 3.015625,
|
|
"learning_rate": 0.0004949858655452697,
|
|
"loss": 5.5423,
|
|
"mean_token_accuracy": 0.15584311559796332,
|
|
"num_tokens": 17326316.0,
|
|
"step": 8355
|
|
},
|
|
{
|
|
"entropy": 5.7423594951629635,
|
|
"epoch": 0.7583454281567489,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.0004949790704673048,
|
|
"loss": 5.6406,
|
|
"mean_token_accuracy": 0.15444749742746353,
|
|
"num_tokens": 17336653.0,
|
|
"step": 8360
|
|
},
|
|
{
|
|
"entropy": 5.776584720611572,
|
|
"epoch": 0.7587989840348331,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004949722708401166,
|
|
"loss": 5.6558,
|
|
"mean_token_accuracy": 0.15802349746227265,
|
|
"num_tokens": 17348139.0,
|
|
"step": 8365
|
|
},
|
|
{
|
|
"entropy": 5.82897915840149,
|
|
"epoch": 0.7592525399129173,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004949654666638457,
|
|
"loss": 5.6328,
|
|
"mean_token_accuracy": 0.1621692255139351,
|
|
"num_tokens": 17357992.0,
|
|
"step": 8370
|
|
},
|
|
{
|
|
"entropy": 5.785438776016235,
|
|
"epoch": 0.7597060957910015,
|
|
"grad_norm": 3.015625,
|
|
"learning_rate": 0.000494958657938633,
|
|
"loss": 5.6424,
|
|
"mean_token_accuracy": 0.15807949602603913,
|
|
"num_tokens": 17369305.0,
|
|
"step": 8375
|
|
},
|
|
{
|
|
"entropy": 5.701330947875976,
|
|
"epoch": 0.7601596516690856,
|
|
"grad_norm": 3.90625,
|
|
"learning_rate": 0.0004949518446646192,
|
|
"loss": 5.6105,
|
|
"mean_token_accuracy": 0.1528936006128788,
|
|
"num_tokens": 17379322.0,
|
|
"step": 8380
|
|
},
|
|
{
|
|
"entropy": 5.73881721496582,
|
|
"epoch": 0.7606132075471698,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.0004949450268419451,
|
|
"loss": 5.6216,
|
|
"mean_token_accuracy": 0.14900248125195503,
|
|
"num_tokens": 17389184.0,
|
|
"step": 8385
|
|
},
|
|
{
|
|
"entropy": 5.797746467590332,
|
|
"epoch": 0.761066763425254,
|
|
"grad_norm": 2.9375,
|
|
"learning_rate": 0.000494938204470752,
|
|
"loss": 5.6364,
|
|
"mean_token_accuracy": 0.16089818999171257,
|
|
"num_tokens": 17399833.0,
|
|
"step": 8390
|
|
},
|
|
{
|
|
"entropy": 5.765430736541748,
|
|
"epoch": 0.7615203193033382,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004949313775511806,
|
|
"loss": 5.5594,
|
|
"mean_token_accuracy": 0.15703304708003998,
|
|
"num_tokens": 17411191.0,
|
|
"step": 8395
|
|
},
|
|
{
|
|
"entropy": 5.69937481880188,
|
|
"epoch": 0.7619738751814223,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004949245460833723,
|
|
"loss": 5.616,
|
|
"mean_token_accuracy": 0.15062173157930375,
|
|
"num_tokens": 17422790.0,
|
|
"step": 8400
|
|
},
|
|
{
|
|
"entropy": 5.862938022613525,
|
|
"epoch": 0.7624274310595065,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004949177100674684,
|
|
"loss": 5.7387,
|
|
"mean_token_accuracy": 0.15682624876499177,
|
|
"num_tokens": 17432602.0,
|
|
"step": 8405
|
|
},
|
|
{
|
|
"entropy": 5.706834363937378,
|
|
"epoch": 0.7628809869375908,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004949108695036102,
|
|
"loss": 5.5303,
|
|
"mean_token_accuracy": 0.16017062664031984,
|
|
"num_tokens": 17443030.0,
|
|
"step": 8410
|
|
},
|
|
{
|
|
"entropy": 5.772679376602173,
|
|
"epoch": 0.7633345428156749,
|
|
"grad_norm": 2.671875,
|
|
"learning_rate": 0.0004949040243919392,
|
|
"loss": 5.6415,
|
|
"mean_token_accuracy": 0.15577236115932463,
|
|
"num_tokens": 17453806.0,
|
|
"step": 8415
|
|
},
|
|
{
|
|
"entropy": 5.736690521240234,
|
|
"epoch": 0.7637880986937591,
|
|
"grad_norm": 2.734375,
|
|
"learning_rate": 0.0004948971747325968,
|
|
"loss": 5.5333,
|
|
"mean_token_accuracy": 0.15511221438646317,
|
|
"num_tokens": 17463335.0,
|
|
"step": 8420
|
|
},
|
|
{
|
|
"entropy": 5.764866876602173,
|
|
"epoch": 0.7642416545718432,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.000494890320525725,
|
|
"loss": 5.6149,
|
|
"mean_token_accuracy": 0.14867080748081207,
|
|
"num_tokens": 17472907.0,
|
|
"step": 8425
|
|
},
|
|
{
|
|
"entropy": 5.748270845413208,
|
|
"epoch": 0.7646952104499274,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.0004948834617714652,
|
|
"loss": 5.6606,
|
|
"mean_token_accuracy": 0.1582384414970875,
|
|
"num_tokens": 17483375.0,
|
|
"step": 8430
|
|
},
|
|
{
|
|
"entropy": 5.7979706764221195,
|
|
"epoch": 0.7651487663280117,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004948765984699595,
|
|
"loss": 5.5638,
|
|
"mean_token_accuracy": 0.16139178574085236,
|
|
"num_tokens": 17493986.0,
|
|
"step": 8435
|
|
},
|
|
{
|
|
"entropy": 5.766293716430664,
|
|
"epoch": 0.7656023222060958,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.0004948697306213494,
|
|
"loss": 5.6485,
|
|
"mean_token_accuracy": 0.15266308933496475,
|
|
"num_tokens": 17504543.0,
|
|
"step": 8440
|
|
},
|
|
{
|
|
"entropy": 5.7076709270477295,
|
|
"epoch": 0.76605587808418,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004948628582257775,
|
|
"loss": 5.5505,
|
|
"mean_token_accuracy": 0.1596139296889305,
|
|
"num_tokens": 17514972.0,
|
|
"step": 8445
|
|
},
|
|
{
|
|
"entropy": 5.886580848693848,
|
|
"epoch": 0.7665094339622641,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004948559812833857,
|
|
"loss": 5.7257,
|
|
"mean_token_accuracy": 0.14827221781015396,
|
|
"num_tokens": 17526260.0,
|
|
"step": 8450
|
|
},
|
|
{
|
|
"entropy": 5.739270973205566,
|
|
"epoch": 0.7669629898403484,
|
|
"grad_norm": 4.9375,
|
|
"learning_rate": 0.0004948490997943162,
|
|
"loss": 5.6049,
|
|
"mean_token_accuracy": 0.15853278189897538,
|
|
"num_tokens": 17536026.0,
|
|
"step": 8455
|
|
},
|
|
{
|
|
"entropy": 5.7705299854278564,
|
|
"epoch": 0.7674165457184325,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004948422137587111,
|
|
"loss": 5.7013,
|
|
"mean_token_accuracy": 0.15132806599140167,
|
|
"num_tokens": 17548131.0,
|
|
"step": 8460
|
|
},
|
|
{
|
|
"entropy": 5.771652030944824,
|
|
"epoch": 0.7678701015965167,
|
|
"grad_norm": 3.46875,
|
|
"learning_rate": 0.0004948353231767131,
|
|
"loss": 5.5823,
|
|
"mean_token_accuracy": 0.15436308979988098,
|
|
"num_tokens": 17558738.0,
|
|
"step": 8465
|
|
},
|
|
{
|
|
"entropy": 5.786510896682739,
|
|
"epoch": 0.7683236574746009,
|
|
"grad_norm": 2.921875,
|
|
"learning_rate": 0.0004948284280484645,
|
|
"loss": 5.6489,
|
|
"mean_token_accuracy": 0.15169512033462523,
|
|
"num_tokens": 17569883.0,
|
|
"step": 8470
|
|
},
|
|
{
|
|
"entropy": 5.7029438495635985,
|
|
"epoch": 0.768777213352685,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004948215283741081,
|
|
"loss": 5.621,
|
|
"mean_token_accuracy": 0.1621229737997055,
|
|
"num_tokens": 17579533.0,
|
|
"step": 8475
|
|
},
|
|
{
|
|
"entropy": 5.744084739685059,
|
|
"epoch": 0.7692307692307693,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004948146241537866,
|
|
"loss": 5.6096,
|
|
"mean_token_accuracy": 0.15570694506168364,
|
|
"num_tokens": 17589755.0,
|
|
"step": 8480
|
|
},
|
|
{
|
|
"entropy": 5.73251748085022,
|
|
"epoch": 0.7696843251088534,
|
|
"grad_norm": 2.765625,
|
|
"learning_rate": 0.0004948077153876425,
|
|
"loss": 5.6459,
|
|
"mean_token_accuracy": 0.1549517720937729,
|
|
"num_tokens": 17599284.0,
|
|
"step": 8485
|
|
},
|
|
{
|
|
"entropy": 5.8467834949493405,
|
|
"epoch": 0.7701378809869376,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.0004948008020758188,
|
|
"loss": 5.6618,
|
|
"mean_token_accuracy": 0.15252612829208373,
|
|
"num_tokens": 17609669.0,
|
|
"step": 8490
|
|
},
|
|
{
|
|
"entropy": 5.753382015228271,
|
|
"epoch": 0.7705914368650217,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.0004947938842184585,
|
|
"loss": 5.5312,
|
|
"mean_token_accuracy": 0.1642974317073822,
|
|
"num_tokens": 17619640.0,
|
|
"step": 8495
|
|
},
|
|
{
|
|
"entropy": 5.715119743347168,
|
|
"epoch": 0.771044992743106,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004947869618157048,
|
|
"loss": 5.6232,
|
|
"mean_token_accuracy": 0.1575893670320511,
|
|
"num_tokens": 17630482.0,
|
|
"step": 8500
|
|
},
|
|
{
|
|
"entropy": 5.742586517333985,
|
|
"epoch": 0.7714985486211902,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004947800348677006,
|
|
"loss": 5.5515,
|
|
"mean_token_accuracy": 0.15935179740190505,
|
|
"num_tokens": 17639807.0,
|
|
"step": 8505
|
|
},
|
|
{
|
|
"entropy": 5.745264959335327,
|
|
"epoch": 0.7719521044992743,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004947731033745893,
|
|
"loss": 5.6025,
|
|
"mean_token_accuracy": 0.15535742938518524,
|
|
"num_tokens": 17650104.0,
|
|
"step": 8510
|
|
},
|
|
{
|
|
"entropy": 5.754315757751465,
|
|
"epoch": 0.7724056603773585,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.0004947661673365142,
|
|
"loss": 5.6592,
|
|
"mean_token_accuracy": 0.15131727755069732,
|
|
"num_tokens": 17660624.0,
|
|
"step": 8515
|
|
},
|
|
{
|
|
"entropy": 5.747050094604492,
|
|
"epoch": 0.7728592162554426,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.0004947592267536188,
|
|
"loss": 5.6862,
|
|
"mean_token_accuracy": 0.1547555707395077,
|
|
"num_tokens": 17671562.0,
|
|
"step": 8520
|
|
},
|
|
{
|
|
"entropy": 5.796496057510376,
|
|
"epoch": 0.7733127721335269,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.0004947522816260466,
|
|
"loss": 5.575,
|
|
"mean_token_accuracy": 0.1584344282746315,
|
|
"num_tokens": 17682195.0,
|
|
"step": 8525
|
|
},
|
|
{
|
|
"entropy": 5.789107084274292,
|
|
"epoch": 0.773766328011611,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.0004947453319539411,
|
|
"loss": 5.6212,
|
|
"mean_token_accuracy": 0.15470114946365357,
|
|
"num_tokens": 17691928.0,
|
|
"step": 8530
|
|
},
|
|
{
|
|
"entropy": 5.816751337051391,
|
|
"epoch": 0.7742198838896952,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.0004947383777374462,
|
|
"loss": 5.6516,
|
|
"mean_token_accuracy": 0.15368348956108094,
|
|
"num_tokens": 17702768.0,
|
|
"step": 8535
|
|
},
|
|
{
|
|
"entropy": 5.688896369934082,
|
|
"epoch": 0.7746734397677794,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.0004947314189767058,
|
|
"loss": 5.5587,
|
|
"mean_token_accuracy": 0.16728712022304534,
|
|
"num_tokens": 17712460.0,
|
|
"step": 8540
|
|
},
|
|
{
|
|
"entropy": 5.74230637550354,
|
|
"epoch": 0.7751269956458636,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004947244556718635,
|
|
"loss": 5.6324,
|
|
"mean_token_accuracy": 0.15500665754079818,
|
|
"num_tokens": 17723489.0,
|
|
"step": 8545
|
|
},
|
|
{
|
|
"entropy": 5.793928146362305,
|
|
"epoch": 0.7755805515239478,
|
|
"grad_norm": 3.953125,
|
|
"learning_rate": 0.0004947174878230635,
|
|
"loss": 5.6105,
|
|
"mean_token_accuracy": 0.15427273288369178,
|
|
"num_tokens": 17733854.0,
|
|
"step": 8550
|
|
},
|
|
{
|
|
"entropy": 5.75883002281189,
|
|
"epoch": 0.7760341074020319,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004947105154304498,
|
|
"loss": 5.6454,
|
|
"mean_token_accuracy": 0.1525057628750801,
|
|
"num_tokens": 17744296.0,
|
|
"step": 8555
|
|
},
|
|
{
|
|
"entropy": 5.781508922576904,
|
|
"epoch": 0.7764876632801161,
|
|
"grad_norm": 2.78125,
|
|
"learning_rate": 0.0004947035384941667,
|
|
"loss": 5.6554,
|
|
"mean_token_accuracy": 0.15237902402877807,
|
|
"num_tokens": 17753527.0,
|
|
"step": 8560
|
|
},
|
|
{
|
|
"entropy": 5.791226863861084,
|
|
"epoch": 0.7769412191582002,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004946965570143584,
|
|
"loss": 5.6296,
|
|
"mean_token_accuracy": 0.15408586710691452,
|
|
"num_tokens": 17764004.0,
|
|
"step": 8565
|
|
},
|
|
{
|
|
"entropy": 5.784405517578125,
|
|
"epoch": 0.7773947750362845,
|
|
"grad_norm": 3.21875,
|
|
"learning_rate": 0.0004946895709911695,
|
|
"loss": 5.635,
|
|
"mean_token_accuracy": 0.1557800993323326,
|
|
"num_tokens": 17775242.0,
|
|
"step": 8570
|
|
},
|
|
{
|
|
"entropy": 5.793393325805664,
|
|
"epoch": 0.7778483309143687,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.0004946825804247442,
|
|
"loss": 5.6824,
|
|
"mean_token_accuracy": 0.15610207468271256,
|
|
"num_tokens": 17785235.0,
|
|
"step": 8575
|
|
},
|
|
{
|
|
"entropy": 5.842348432540893,
|
|
"epoch": 0.7783018867924528,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.000494675585315227,
|
|
"loss": 5.6766,
|
|
"mean_token_accuracy": 0.15625357627868652,
|
|
"num_tokens": 17795289.0,
|
|
"step": 8580
|
|
},
|
|
{
|
|
"entropy": 5.780657863616943,
|
|
"epoch": 0.778755442670537,
|
|
"grad_norm": 2.625,
|
|
"learning_rate": 0.0004946685856627628,
|
|
"loss": 5.513,
|
|
"mean_token_accuracy": 0.15587281286716462,
|
|
"num_tokens": 17806156.0,
|
|
"step": 8585
|
|
},
|
|
{
|
|
"entropy": 5.761910152435303,
|
|
"epoch": 0.7792089985486212,
|
|
"grad_norm": 2.8125,
|
|
"learning_rate": 0.0004946615814674963,
|
|
"loss": 5.6441,
|
|
"mean_token_accuracy": 0.15001720786094666,
|
|
"num_tokens": 17816228.0,
|
|
"step": 8590
|
|
},
|
|
{
|
|
"entropy": 5.735326528549194,
|
|
"epoch": 0.7796625544267054,
|
|
"grad_norm": 3.34375,
|
|
"learning_rate": 0.0004946545727295724,
|
|
"loss": 5.5831,
|
|
"mean_token_accuracy": 0.15767593830823898,
|
|
"num_tokens": 17826694.0,
|
|
"step": 8595
|
|
},
|
|
{
|
|
"entropy": 5.718439054489136,
|
|
"epoch": 0.7801161103047896,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004946475594491359,
|
|
"loss": 5.5631,
|
|
"mean_token_accuracy": 0.15085123479366302,
|
|
"num_tokens": 17838344.0,
|
|
"step": 8600
|
|
},
|
|
{
|
|
"entropy": 5.62370285987854,
|
|
"epoch": 0.7805696661828737,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004946405416263319,
|
|
"loss": 5.4621,
|
|
"mean_token_accuracy": 0.17144817113876343,
|
|
"num_tokens": 17847830.0,
|
|
"step": 8605
|
|
},
|
|
{
|
|
"entropy": 5.687699174880981,
|
|
"epoch": 0.7810232220609579,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.0004946335192613054,
|
|
"loss": 5.4811,
|
|
"mean_token_accuracy": 0.16238780617713927,
|
|
"num_tokens": 17858214.0,
|
|
"step": 8610
|
|
},
|
|
{
|
|
"entropy": 5.639577436447143,
|
|
"epoch": 0.7814767779390421,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004946264923542019,
|
|
"loss": 5.5558,
|
|
"mean_token_accuracy": 0.16315570324659348,
|
|
"num_tokens": 17867807.0,
|
|
"step": 8615
|
|
},
|
|
{
|
|
"entropy": 5.705491161346435,
|
|
"epoch": 0.7819303338171263,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004946194609051664,
|
|
"loss": 5.6235,
|
|
"mean_token_accuracy": 0.15160861611366272,
|
|
"num_tokens": 17878556.0,
|
|
"step": 8620
|
|
},
|
|
{
|
|
"entropy": 5.710368537902832,
|
|
"epoch": 0.7823838896952104,
|
|
"grad_norm": 4.4375,
|
|
"learning_rate": 0.0004946124249143447,
|
|
"loss": 5.4933,
|
|
"mean_token_accuracy": 0.168972148001194,
|
|
"num_tokens": 17888877.0,
|
|
"step": 8625
|
|
},
|
|
{
|
|
"entropy": 5.675780773162842,
|
|
"epoch": 0.7828374455732946,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.000494605384381882,
|
|
"loss": 5.572,
|
|
"mean_token_accuracy": 0.16354887038469315,
|
|
"num_tokens": 17899443.0,
|
|
"step": 8630
|
|
},
|
|
{
|
|
"entropy": 5.747694969177246,
|
|
"epoch": 0.7832910014513788,
|
|
"grad_norm": 2.796875,
|
|
"learning_rate": 0.0004945983393079239,
|
|
"loss": 5.6799,
|
|
"mean_token_accuracy": 0.1500549003481865,
|
|
"num_tokens": 17910535.0,
|
|
"step": 8635
|
|
},
|
|
{
|
|
"entropy": 5.823499155044556,
|
|
"epoch": 0.783744557329463,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004945912896926163,
|
|
"loss": 5.6937,
|
|
"mean_token_accuracy": 0.15386853665113448,
|
|
"num_tokens": 17921460.0,
|
|
"step": 8640
|
|
},
|
|
{
|
|
"entropy": 5.789236545562744,
|
|
"epoch": 0.7841981132075472,
|
|
"grad_norm": 3.1875,
|
|
"learning_rate": 0.0004945842355361049,
|
|
"loss": 5.5561,
|
|
"mean_token_accuracy": 0.16107206791639328,
|
|
"num_tokens": 17931666.0,
|
|
"step": 8645
|
|
},
|
|
{
|
|
"entropy": 5.717998456954956,
|
|
"epoch": 0.7846516690856313,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004945771768385355,
|
|
"loss": 5.6217,
|
|
"mean_token_accuracy": 0.16032176166772844,
|
|
"num_tokens": 17942855.0,
|
|
"step": 8650
|
|
},
|
|
{
|
|
"entropy": 5.735478734970092,
|
|
"epoch": 0.7851052249637155,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.000494570113600054,
|
|
"loss": 5.6398,
|
|
"mean_token_accuracy": 0.15501087456941604,
|
|
"num_tokens": 17953225.0,
|
|
"step": 8655
|
|
},
|
|
{
|
|
"entropy": 5.7090085506439205,
|
|
"epoch": 0.7855587808417998,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004945630458208068,
|
|
"loss": 5.5957,
|
|
"mean_token_accuracy": 0.15289850533008575,
|
|
"num_tokens": 17964069.0,
|
|
"step": 8660
|
|
},
|
|
{
|
|
"entropy": 5.761651802062988,
|
|
"epoch": 0.7860123367198839,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004945559735009397,
|
|
"loss": 5.6371,
|
|
"mean_token_accuracy": 0.15432742685079576,
|
|
"num_tokens": 17974520.0,
|
|
"step": 8665
|
|
},
|
|
{
|
|
"entropy": 5.854554128646851,
|
|
"epoch": 0.7864658925979681,
|
|
"grad_norm": 3.125,
|
|
"learning_rate": 0.0004945488966405993,
|
|
"loss": 5.6356,
|
|
"mean_token_accuracy": 0.1573382794857025,
|
|
"num_tokens": 17985573.0,
|
|
"step": 8670
|
|
},
|
|
{
|
|
"entropy": 5.716013956069946,
|
|
"epoch": 0.7869194484760522,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004945418152399317,
|
|
"loss": 5.6613,
|
|
"mean_token_accuracy": 0.1530529737472534,
|
|
"num_tokens": 17996551.0,
|
|
"step": 8675
|
|
},
|
|
{
|
|
"entropy": 5.743480968475342,
|
|
"epoch": 0.7873730043541364,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.0004945347292990833,
|
|
"loss": 5.6636,
|
|
"mean_token_accuracy": 0.15610648840665817,
|
|
"num_tokens": 18007569.0,
|
|
"step": 8680
|
|
},
|
|
{
|
|
"entropy": 5.758234119415283,
|
|
"epoch": 0.7878265602322206,
|
|
"grad_norm": 3.671875,
|
|
"learning_rate": 0.0004945276388182008,
|
|
"loss": 5.5407,
|
|
"mean_token_accuracy": 0.1586911991238594,
|
|
"num_tokens": 18018057.0,
|
|
"step": 8685
|
|
},
|
|
{
|
|
"entropy": 5.731079244613648,
|
|
"epoch": 0.7882801161103048,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004945205437974309,
|
|
"loss": 5.6447,
|
|
"mean_token_accuracy": 0.15667132735252381,
|
|
"num_tokens": 18027709.0,
|
|
"step": 8690
|
|
},
|
|
{
|
|
"entropy": 5.757808876037598,
|
|
"epoch": 0.788733671988389,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004945134442369201,
|
|
"loss": 5.5482,
|
|
"mean_token_accuracy": 0.1688195064663887,
|
|
"num_tokens": 18036781.0,
|
|
"step": 8695
|
|
},
|
|
{
|
|
"entropy": 5.765886735916138,
|
|
"epoch": 0.7891872278664731,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004945063401368154,
|
|
"loss": 5.6543,
|
|
"mean_token_accuracy": 0.15439642816781998,
|
|
"num_tokens": 18047027.0,
|
|
"step": 8700
|
|
},
|
|
{
|
|
"entropy": 5.713792896270752,
|
|
"epoch": 0.7896407837445574,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004944992314972637,
|
|
"loss": 5.5992,
|
|
"mean_token_accuracy": 0.15309029966592788,
|
|
"num_tokens": 18057030.0,
|
|
"step": 8705
|
|
},
|
|
{
|
|
"entropy": 5.763031387329102,
|
|
"epoch": 0.7900943396226415,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.0004944921183184118,
|
|
"loss": 5.6437,
|
|
"mean_token_accuracy": 0.1565028965473175,
|
|
"num_tokens": 18067408.0,
|
|
"step": 8710
|
|
},
|
|
{
|
|
"entropy": 5.804215002059936,
|
|
"epoch": 0.7905478955007257,
|
|
"grad_norm": 2.5625,
|
|
"learning_rate": 0.000494485000600407,
|
|
"loss": 5.626,
|
|
"mean_token_accuracy": 0.15673578679561614,
|
|
"num_tokens": 18078756.0,
|
|
"step": 8715
|
|
},
|
|
{
|
|
"entropy": 5.749855661392212,
|
|
"epoch": 0.7910014513788098,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004944778783433965,
|
|
"loss": 5.5731,
|
|
"mean_token_accuracy": 0.16131314635276794,
|
|
"num_tokens": 18088822.0,
|
|
"step": 8720
|
|
},
|
|
{
|
|
"entropy": 5.759881114959716,
|
|
"epoch": 0.791455007256894,
|
|
"grad_norm": 2.625,
|
|
"learning_rate": 0.0004944707515475276,
|
|
"loss": 5.6789,
|
|
"mean_token_accuracy": 0.155691097676754,
|
|
"num_tokens": 18098351.0,
|
|
"step": 8725
|
|
},
|
|
{
|
|
"entropy": 5.7725828170776365,
|
|
"epoch": 0.7919085631349783,
|
|
"grad_norm": 3.3125,
|
|
"learning_rate": 0.0004944636202129475,
|
|
"loss": 5.6158,
|
|
"mean_token_accuracy": 0.15558144003152846,
|
|
"num_tokens": 18109817.0,
|
|
"step": 8730
|
|
},
|
|
{
|
|
"entropy": 5.718410539627075,
|
|
"epoch": 0.7923621190130624,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004944564843398039,
|
|
"loss": 5.6208,
|
|
"mean_token_accuracy": 0.15987396985292435,
|
|
"num_tokens": 18120327.0,
|
|
"step": 8735
|
|
},
|
|
{
|
|
"entropy": 5.750848054885864,
|
|
"epoch": 0.7928156748911466,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.0004944493439282443,
|
|
"loss": 5.6045,
|
|
"mean_token_accuracy": 0.15970960408449172,
|
|
"num_tokens": 18130127.0,
|
|
"step": 8740
|
|
},
|
|
{
|
|
"entropy": 5.867050743103027,
|
|
"epoch": 0.7932692307692307,
|
|
"grad_norm": 2.640625,
|
|
"learning_rate": 0.0004944421989784162,
|
|
"loss": 5.6796,
|
|
"mean_token_accuracy": 0.15051667243242264,
|
|
"num_tokens": 18141429.0,
|
|
"step": 8745
|
|
},
|
|
{
|
|
"entropy": 5.76239595413208,
|
|
"epoch": 0.793722786647315,
|
|
"grad_norm": 2.59375,
|
|
"learning_rate": 0.0004944350494904676,
|
|
"loss": 5.7029,
|
|
"mean_token_accuracy": 0.15482740402221679,
|
|
"num_tokens": 18153675.0,
|
|
"step": 8750
|
|
},
|
|
{
|
|
"entropy": 5.808538150787354,
|
|
"epoch": 0.7941763425253991,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004944278954645463,
|
|
"loss": 5.7204,
|
|
"mean_token_accuracy": 0.1522441327571869,
|
|
"num_tokens": 18163683.0,
|
|
"step": 8755
|
|
},
|
|
{
|
|
"entropy": 5.8042826652526855,
|
|
"epoch": 0.7946298984034833,
|
|
"grad_norm": 2.578125,
|
|
"learning_rate": 0.0004944207369008002,
|
|
"loss": 5.6268,
|
|
"mean_token_accuracy": 0.15396066829562188,
|
|
"num_tokens": 18173793.0,
|
|
"step": 8760
|
|
},
|
|
{
|
|
"entropy": 5.8363574028015135,
|
|
"epoch": 0.7950834542815675,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.0004944135737993773,
|
|
"loss": 5.7354,
|
|
"mean_token_accuracy": 0.14780047833919524,
|
|
"num_tokens": 18185034.0,
|
|
"step": 8765
|
|
},
|
|
{
|
|
"entropy": 5.78611159324646,
|
|
"epoch": 0.7955370101596516,
|
|
"grad_norm": 3.171875,
|
|
"learning_rate": 0.0004944064061604258,
|
|
"loss": 5.6057,
|
|
"mean_token_accuracy": 0.1557180851697922,
|
|
"num_tokens": 18196047.0,
|
|
"step": 8770
|
|
},
|
|
{
|
|
"entropy": 5.724568510055542,
|
|
"epoch": 0.7959905660377359,
|
|
"grad_norm": 3.125,
|
|
"learning_rate": 0.0004943992339840939,
|
|
"loss": 5.598,
|
|
"mean_token_accuracy": 0.1498669244349003,
|
|
"num_tokens": 18205123.0,
|
|
"step": 8775
|
|
},
|
|
{
|
|
"entropy": 5.809069490432739,
|
|
"epoch": 0.79644412191582,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.00049439205727053,
|
|
"loss": 5.6427,
|
|
"mean_token_accuracy": 0.15244297832250595,
|
|
"num_tokens": 18216683.0,
|
|
"step": 8780
|
|
},
|
|
{
|
|
"entropy": 5.72417140007019,
|
|
"epoch": 0.7968976777939042,
|
|
"grad_norm": 4.15625,
|
|
"learning_rate": 0.0004943848760198823,
|
|
"loss": 5.5773,
|
|
"mean_token_accuracy": 0.15676393657922744,
|
|
"num_tokens": 18226230.0,
|
|
"step": 8785
|
|
},
|
|
{
|
|
"entropy": 5.67556939125061,
|
|
"epoch": 0.7973512336719883,
|
|
"grad_norm": 2.65625,
|
|
"learning_rate": 0.0004943776902322995,
|
|
"loss": 5.5738,
|
|
"mean_token_accuracy": 0.1578221306204796,
|
|
"num_tokens": 18236480.0,
|
|
"step": 8790
|
|
},
|
|
{
|
|
"entropy": 5.905447769165039,
|
|
"epoch": 0.7978047895500726,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004943704999079302,
|
|
"loss": 5.7173,
|
|
"mean_token_accuracy": 0.15507023632526398,
|
|
"num_tokens": 18247100.0,
|
|
"step": 8795
|
|
},
|
|
{
|
|
"entropy": 5.801527404785157,
|
|
"epoch": 0.7982583454281568,
|
|
"grad_norm": 3.234375,
|
|
"learning_rate": 0.0004943633050469231,
|
|
"loss": 5.5839,
|
|
"mean_token_accuracy": 0.15771662294864655,
|
|
"num_tokens": 18256958.0,
|
|
"step": 8800
|
|
},
|
|
{
|
|
"entropy": 5.653497505187988,
|
|
"epoch": 0.7987119013062409,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004943561056494269,
|
|
"loss": 5.6602,
|
|
"mean_token_accuracy": 0.15086668729782104,
|
|
"num_tokens": 18267537.0,
|
|
"step": 8805
|
|
},
|
|
{
|
|
"entropy": 5.695418024063111,
|
|
"epoch": 0.7991654571843251,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 0.0004943489017155906,
|
|
"loss": 5.5548,
|
|
"mean_token_accuracy": 0.16429276019334793,
|
|
"num_tokens": 18276717.0,
|
|
"step": 8810
|
|
},
|
|
{
|
|
"entropy": 5.762015438079834,
|
|
"epoch": 0.7996190130624092,
|
|
"grad_norm": 8.1875,
|
|
"learning_rate": 0.0004943416932455631,
|
|
"loss": 5.6258,
|
|
"mean_token_accuracy": 0.15204133987426757,
|
|
"num_tokens": 18286767.0,
|
|
"step": 8815
|
|
},
|
|
{
|
|
"entropy": 5.777064323425293,
|
|
"epoch": 0.8000725689404935,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.0004943344802394935,
|
|
"loss": 5.6469,
|
|
"mean_token_accuracy": 0.15864025354385375,
|
|
"num_tokens": 18296476.0,
|
|
"step": 8820
|
|
},
|
|
{
|
|
"entropy": 5.734442520141601,
|
|
"epoch": 0.8005261248185777,
|
|
"grad_norm": 4.03125,
|
|
"learning_rate": 0.0004943272626975309,
|
|
"loss": 5.5362,
|
|
"mean_token_accuracy": 0.15917353183031083,
|
|
"num_tokens": 18305877.0,
|
|
"step": 8825
|
|
},
|
|
{
|
|
"entropy": 5.745154666900635,
|
|
"epoch": 0.8009796806966618,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004943200406198246,
|
|
"loss": 5.6483,
|
|
"mean_token_accuracy": 0.15773734003305434,
|
|
"num_tokens": 18316671.0,
|
|
"step": 8830
|
|
},
|
|
{
|
|
"entropy": 5.769705724716187,
|
|
"epoch": 0.801433236574746,
|
|
"grad_norm": 4.40625,
|
|
"learning_rate": 0.000494312814006524,
|
|
"loss": 5.5845,
|
|
"mean_token_accuracy": 0.16117432862520217,
|
|
"num_tokens": 18327479.0,
|
|
"step": 8835
|
|
},
|
|
{
|
|
"entropy": 5.789660453796387,
|
|
"epoch": 0.8018867924528302,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004943055828577784,
|
|
"loss": 5.6305,
|
|
"mean_token_accuracy": 0.15419279783964157,
|
|
"num_tokens": 18337693.0,
|
|
"step": 8840
|
|
},
|
|
{
|
|
"entropy": 5.716463327407837,
|
|
"epoch": 0.8023403483309144,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.0004942983471737376,
|
|
"loss": 5.6089,
|
|
"mean_token_accuracy": 0.16132795810699463,
|
|
"num_tokens": 18350293.0,
|
|
"step": 8845
|
|
},
|
|
{
|
|
"entropy": 5.812602853775024,
|
|
"epoch": 0.8027939042089985,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.0004942911069545511,
|
|
"loss": 5.6445,
|
|
"mean_token_accuracy": 0.15608302354812623,
|
|
"num_tokens": 18360744.0,
|
|
"step": 8850
|
|
},
|
|
{
|
|
"entropy": 5.817702150344848,
|
|
"epoch": 0.8032474600870827,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004942838622003686,
|
|
"loss": 5.6084,
|
|
"mean_token_accuracy": 0.15047313123941422,
|
|
"num_tokens": 18370476.0,
|
|
"step": 8855
|
|
},
|
|
{
|
|
"entropy": 5.702783918380737,
|
|
"epoch": 0.8037010159651669,
|
|
"grad_norm": 3.046875,
|
|
"learning_rate": 0.0004942766129113399,
|
|
"loss": 5.5673,
|
|
"mean_token_accuracy": 0.1526488922536373,
|
|
"num_tokens": 18381194.0,
|
|
"step": 8860
|
|
},
|
|
{
|
|
"entropy": 5.811666822433471,
|
|
"epoch": 0.8041545718432511,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004942693590876151,
|
|
"loss": 5.7513,
|
|
"mean_token_accuracy": 0.15307218581438065,
|
|
"num_tokens": 18392170.0,
|
|
"step": 8865
|
|
},
|
|
{
|
|
"entropy": 5.819162273406983,
|
|
"epoch": 0.8046081277213353,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.000494262100729344,
|
|
"loss": 5.7298,
|
|
"mean_token_accuracy": 0.15844600051641464,
|
|
"num_tokens": 18402968.0,
|
|
"step": 8870
|
|
},
|
|
{
|
|
"entropy": 5.68730731010437,
|
|
"epoch": 0.8050616835994194,
|
|
"grad_norm": 4.59375,
|
|
"learning_rate": 0.0004942548378366768,
|
|
"loss": 5.6004,
|
|
"mean_token_accuracy": 0.1573096215724945,
|
|
"num_tokens": 18412633.0,
|
|
"step": 8875
|
|
},
|
|
{
|
|
"entropy": 5.772659969329834,
|
|
"epoch": 0.8055152394775036,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004942475704097635,
|
|
"loss": 5.6447,
|
|
"mean_token_accuracy": 0.15692170709371567,
|
|
"num_tokens": 18421908.0,
|
|
"step": 8880
|
|
},
|
|
{
|
|
"entropy": 5.8357960224151615,
|
|
"epoch": 0.8059687953555879,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004942402984487548,
|
|
"loss": 5.6234,
|
|
"mean_token_accuracy": 0.15884881019592284,
|
|
"num_tokens": 18432205.0,
|
|
"step": 8885
|
|
},
|
|
{
|
|
"entropy": 5.7328160285949705,
|
|
"epoch": 0.806422351233672,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 0.0004942330219538008,
|
|
"loss": 5.5583,
|
|
"mean_token_accuracy": 0.16361750811338424,
|
|
"num_tokens": 18442634.0,
|
|
"step": 8890
|
|
},
|
|
{
|
|
"entropy": 5.7307335376739506,
|
|
"epoch": 0.8068759071117562,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.000494225740925052,
|
|
"loss": 5.6167,
|
|
"mean_token_accuracy": 0.1584385335445404,
|
|
"num_tokens": 18453001.0,
|
|
"step": 8895
|
|
},
|
|
{
|
|
"entropy": 5.80275149345398,
|
|
"epoch": 0.8073294629898403,
|
|
"grad_norm": 3.421875,
|
|
"learning_rate": 0.0004942184553626591,
|
|
"loss": 5.6553,
|
|
"mean_token_accuracy": 0.15413723289966583,
|
|
"num_tokens": 18463572.0,
|
|
"step": 8900
|
|
},
|
|
{
|
|
"entropy": 5.867390918731689,
|
|
"epoch": 0.8077830188679245,
|
|
"grad_norm": 2.71875,
|
|
"learning_rate": 0.0004942111652667726,
|
|
"loss": 5.6846,
|
|
"mean_token_accuracy": 0.148859404027462,
|
|
"num_tokens": 18474130.0,
|
|
"step": 8905
|
|
},
|
|
{
|
|
"entropy": 5.749734258651733,
|
|
"epoch": 0.8082365747460087,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 0.0004942038706375433,
|
|
"loss": 5.6747,
|
|
"mean_token_accuracy": 0.15424139201641082,
|
|
"num_tokens": 18483832.0,
|
|
"step": 8910
|
|
},
|
|
{
|
|
"entropy": 5.817002058029175,
|
|
"epoch": 0.8086901306240929,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004941965714751222,
|
|
"loss": 5.6181,
|
|
"mean_token_accuracy": 0.15063573569059371,
|
|
"num_tokens": 18494133.0,
|
|
"step": 8915
|
|
},
|
|
{
|
|
"entropy": 5.82765383720398,
|
|
"epoch": 0.809143686502177,
|
|
"grad_norm": 2.671875,
|
|
"learning_rate": 0.0004941892677796601,
|
|
"loss": 5.6592,
|
|
"mean_token_accuracy": 0.14768316596746445,
|
|
"num_tokens": 18505411.0,
|
|
"step": 8920
|
|
},
|
|
{
|
|
"entropy": 5.740002632141113,
|
|
"epoch": 0.8095972423802612,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004941819595513081,
|
|
"loss": 5.6036,
|
|
"mean_token_accuracy": 0.1591396689414978,
|
|
"num_tokens": 18515455.0,
|
|
"step": 8925
|
|
},
|
|
{
|
|
"entropy": 5.790988206863403,
|
|
"epoch": 0.8100507982583455,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004941746467902173,
|
|
"loss": 5.6051,
|
|
"mean_token_accuracy": 0.163439479470253,
|
|
"num_tokens": 18525483.0,
|
|
"step": 8930
|
|
},
|
|
{
|
|
"entropy": 5.769948577880859,
|
|
"epoch": 0.8105043541364296,
|
|
"grad_norm": 3.234375,
|
|
"learning_rate": 0.000494167329496539,
|
|
"loss": 5.6055,
|
|
"mean_token_accuracy": 0.15738181620836258,
|
|
"num_tokens": 18535869.0,
|
|
"step": 8935
|
|
},
|
|
{
|
|
"entropy": 5.600489902496338,
|
|
"epoch": 0.8109579100145138,
|
|
"grad_norm": 2.609375,
|
|
"learning_rate": 0.0004941600076704244,
|
|
"loss": 5.5555,
|
|
"mean_token_accuracy": 0.15682200938463212,
|
|
"num_tokens": 18546047.0,
|
|
"step": 8940
|
|
},
|
|
{
|
|
"entropy": 5.79785852432251,
|
|
"epoch": 0.8114114658925979,
|
|
"grad_norm": 2.59375,
|
|
"learning_rate": 0.0004941526813120251,
|
|
"loss": 5.62,
|
|
"mean_token_accuracy": 0.15482563972473146,
|
|
"num_tokens": 18557051.0,
|
|
"step": 8945
|
|
},
|
|
{
|
|
"entropy": 5.812386131286621,
|
|
"epoch": 0.8118650217706821,
|
|
"grad_norm": 2.65625,
|
|
"learning_rate": 0.0004941453504214924,
|
|
"loss": 5.6757,
|
|
"mean_token_accuracy": 0.152674700319767,
|
|
"num_tokens": 18568824.0,
|
|
"step": 8950
|
|
},
|
|
{
|
|
"entropy": 5.800317096710205,
|
|
"epoch": 0.8123185776487664,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004941380149989781,
|
|
"loss": 5.5757,
|
|
"mean_token_accuracy": 0.15907476395368575,
|
|
"num_tokens": 18579708.0,
|
|
"step": 8955
|
|
},
|
|
{
|
|
"entropy": 5.8025445461273195,
|
|
"epoch": 0.8127721335268505,
|
|
"grad_norm": 5.34375,
|
|
"learning_rate": 0.0004941306750446336,
|
|
"loss": 5.6264,
|
|
"mean_token_accuracy": 0.157684263586998,
|
|
"num_tokens": 18589692.0,
|
|
"step": 8960
|
|
},
|
|
{
|
|
"entropy": 5.739159965515137,
|
|
"epoch": 0.8132256894049347,
|
|
"grad_norm": 2.625,
|
|
"learning_rate": 0.000494123330558611,
|
|
"loss": 5.6066,
|
|
"mean_token_accuracy": 0.15774117410182953,
|
|
"num_tokens": 18600916.0,
|
|
"step": 8965
|
|
},
|
|
{
|
|
"entropy": 5.76051959991455,
|
|
"epoch": 0.8136792452830188,
|
|
"grad_norm": 2.625,
|
|
"learning_rate": 0.0004941159815410622,
|
|
"loss": 5.5682,
|
|
"mean_token_accuracy": 0.16080375611782075,
|
|
"num_tokens": 18610888.0,
|
|
"step": 8970
|
|
},
|
|
{
|
|
"entropy": 5.786311912536621,
|
|
"epoch": 0.8141328011611031,
|
|
"grad_norm": 2.6875,
|
|
"learning_rate": 0.000494108627992139,
|
|
"loss": 5.6242,
|
|
"mean_token_accuracy": 0.15001383274793625,
|
|
"num_tokens": 18621392.0,
|
|
"step": 8975
|
|
},
|
|
{
|
|
"entropy": 5.699140119552612,
|
|
"epoch": 0.8145863570391872,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004941012699119936,
|
|
"loss": 5.5832,
|
|
"mean_token_accuracy": 0.1626926526427269,
|
|
"num_tokens": 18631627.0,
|
|
"step": 8980
|
|
},
|
|
{
|
|
"entropy": 5.652145719528198,
|
|
"epoch": 0.8150399129172714,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004940939073007779,
|
|
"loss": 5.4278,
|
|
"mean_token_accuracy": 0.16882453113794327,
|
|
"num_tokens": 18641872.0,
|
|
"step": 8985
|
|
},
|
|
{
|
|
"entropy": 5.748218679428101,
|
|
"epoch": 0.8154934687953556,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004940865401586446,
|
|
"loss": 5.5851,
|
|
"mean_token_accuracy": 0.1589428797364235,
|
|
"num_tokens": 18651417.0,
|
|
"step": 8990
|
|
},
|
|
{
|
|
"entropy": 5.722093105316162,
|
|
"epoch": 0.8159470246734397,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004940791684857458,
|
|
"loss": 5.5865,
|
|
"mean_token_accuracy": 0.16440420895814895,
|
|
"num_tokens": 18661473.0,
|
|
"step": 8995
|
|
},
|
|
{
|
|
"entropy": 5.704001998901367,
|
|
"epoch": 0.816400580551524,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.0004940717922822339,
|
|
"loss": 5.5797,
|
|
"mean_token_accuracy": 0.1616051435470581,
|
|
"num_tokens": 18671079.0,
|
|
"step": 9000
|
|
},
|
|
{
|
|
"epoch": 0.816400580551524,
|
|
"eval_entropy": 5.542448977431561,
|
|
"eval_loss": 5.638240337371826,
|
|
"eval_mean_token_accuracy": 0.16320334714563453,
|
|
"eval_num_tokens": 18671079.0,
|
|
"eval_runtime": 26.6736,
|
|
"eval_samples_per_second": 1325.658,
|
|
"eval_steps_per_second": 165.707,
|
|
"step": 9000
|
|
}
|
|
],
|
|
"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": 2.7324467269632e+16,
|
|
"train_batch_size": 16,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|