60145 lines
1.6 MiB
60145 lines
1.6 MiB
{
|
|
"best_global_step": null,
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 2.505846976277982,
|
|
"eval_steps": 3000,
|
|
"global_step": 30000,
|
|
"is_hyper_param_search": false,
|
|
"is_local_process_zero": true,
|
|
"is_world_process_zero": true,
|
|
"log_history": [
|
|
{
|
|
"entropy": 10.742597389221192,
|
|
"epoch": 0.000417641162712997,
|
|
"grad_norm": 5.3125,
|
|
"learning_rate": 2e-06,
|
|
"loss": 10.7497,
|
|
"mean_token_accuracy": 0.00011876485077664257,
|
|
"num_tokens": 9371.0,
|
|
"step": 5
|
|
},
|
|
{
|
|
"entropy": 10.742581462860107,
|
|
"epoch": 0.000835282325425994,
|
|
"grad_norm": 5.15625,
|
|
"learning_rate": 4.5e-06,
|
|
"loss": 10.7312,
|
|
"mean_token_accuracy": 0.0,
|
|
"num_tokens": 18155.0,
|
|
"step": 10
|
|
},
|
|
{
|
|
"entropy": 10.742617225646972,
|
|
"epoch": 0.001252923488138991,
|
|
"grad_norm": 4.96875,
|
|
"learning_rate": 7e-06,
|
|
"loss": 10.7253,
|
|
"mean_token_accuracy": 9.920635493472218e-05,
|
|
"num_tokens": 27776.0,
|
|
"step": 15
|
|
},
|
|
{
|
|
"entropy": 10.742653942108154,
|
|
"epoch": 0.001670564650851988,
|
|
"grad_norm": 5.09375,
|
|
"learning_rate": 9.5e-06,
|
|
"loss": 10.6672,
|
|
"mean_token_accuracy": 0.0005802143830806016,
|
|
"num_tokens": 37166.0,
|
|
"step": 20
|
|
},
|
|
{
|
|
"entropy": 10.74262170791626,
|
|
"epoch": 0.002088205813564985,
|
|
"grad_norm": 5.09375,
|
|
"learning_rate": 1.2e-05,
|
|
"loss": 10.5444,
|
|
"mean_token_accuracy": 0.010037525719963015,
|
|
"num_tokens": 46667.0,
|
|
"step": 25
|
|
},
|
|
{
|
|
"entropy": 10.742273426055908,
|
|
"epoch": 0.002505846976277982,
|
|
"grad_norm": 4.1875,
|
|
"learning_rate": 1.4500000000000002e-05,
|
|
"loss": 10.4193,
|
|
"mean_token_accuracy": 0.0329294515773654,
|
|
"num_tokens": 55738.0,
|
|
"step": 30
|
|
},
|
|
{
|
|
"entropy": 10.74118251800537,
|
|
"epoch": 0.002923488138990979,
|
|
"grad_norm": 3.234375,
|
|
"learning_rate": 1.7000000000000003e-05,
|
|
"loss": 10.3134,
|
|
"mean_token_accuracy": 0.04002654887735844,
|
|
"num_tokens": 65303.0,
|
|
"step": 35
|
|
},
|
|
{
|
|
"entropy": 10.738407230377197,
|
|
"epoch": 0.003341129301703976,
|
|
"grad_norm": 2.78125,
|
|
"learning_rate": 1.95e-05,
|
|
"loss": 10.1216,
|
|
"mean_token_accuracy": 0.041297851502895354,
|
|
"num_tokens": 74876.0,
|
|
"step": 40
|
|
},
|
|
{
|
|
"entropy": 10.734228038787842,
|
|
"epoch": 0.003758770464416973,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 2.2e-05,
|
|
"loss": 10.0124,
|
|
"mean_token_accuracy": 0.04665607586503029,
|
|
"num_tokens": 84683.0,
|
|
"step": 45
|
|
},
|
|
{
|
|
"entropy": 10.730060386657716,
|
|
"epoch": 0.00417641162712997,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 2.4500000000000003e-05,
|
|
"loss": 9.9446,
|
|
"mean_token_accuracy": 0.04418331272900104,
|
|
"num_tokens": 94511.0,
|
|
"step": 50
|
|
},
|
|
{
|
|
"entropy": 10.727671051025391,
|
|
"epoch": 0.004594052789842967,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 2.7e-05,
|
|
"loss": 9.8593,
|
|
"mean_token_accuracy": 0.04506920985877514,
|
|
"num_tokens": 103820.0,
|
|
"step": 55
|
|
},
|
|
{
|
|
"entropy": 10.72537727355957,
|
|
"epoch": 0.005011693952555964,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 2.95e-05,
|
|
"loss": 9.8006,
|
|
"mean_token_accuracy": 0.04406389705836773,
|
|
"num_tokens": 112398.0,
|
|
"step": 60
|
|
},
|
|
{
|
|
"entropy": 10.723227405548096,
|
|
"epoch": 0.005429335115268961,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 3.2e-05,
|
|
"loss": 9.7404,
|
|
"mean_token_accuracy": 0.041664719581604004,
|
|
"num_tokens": 121167.0,
|
|
"step": 65
|
|
},
|
|
{
|
|
"entropy": 10.721342849731446,
|
|
"epoch": 0.005846976277981958,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 3.4500000000000005e-05,
|
|
"loss": 9.67,
|
|
"mean_token_accuracy": 0.04505793582648039,
|
|
"num_tokens": 129399.0,
|
|
"step": 70
|
|
},
|
|
{
|
|
"entropy": 10.717985439300538,
|
|
"epoch": 0.006264617440694955,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 3.7e-05,
|
|
"loss": 9.6274,
|
|
"mean_token_accuracy": 0.043670152127742765,
|
|
"num_tokens": 138512.0,
|
|
"step": 75
|
|
},
|
|
{
|
|
"entropy": 10.714579200744629,
|
|
"epoch": 0.006682258603407952,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 3.95e-05,
|
|
"loss": 9.5989,
|
|
"mean_token_accuracy": 0.0400418970733881,
|
|
"num_tokens": 147712.0,
|
|
"step": 80
|
|
},
|
|
{
|
|
"entropy": 10.709438896179199,
|
|
"epoch": 0.007099899766120949,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 4.2000000000000004e-05,
|
|
"loss": 9.5111,
|
|
"mean_token_accuracy": 0.04463256634771824,
|
|
"num_tokens": 156759.0,
|
|
"step": 85
|
|
},
|
|
{
|
|
"entropy": 10.70057258605957,
|
|
"epoch": 0.007517540928833946,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 4.45e-05,
|
|
"loss": 9.4327,
|
|
"mean_token_accuracy": 0.044699374586343765,
|
|
"num_tokens": 166395.0,
|
|
"step": 90
|
|
},
|
|
{
|
|
"entropy": 10.690051460266114,
|
|
"epoch": 0.007935182091546943,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 4.7000000000000004e-05,
|
|
"loss": 9.3248,
|
|
"mean_token_accuracy": 0.05507284291088581,
|
|
"num_tokens": 174739.0,
|
|
"step": 95
|
|
},
|
|
{
|
|
"entropy": 10.674839115142822,
|
|
"epoch": 0.00835282325425994,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 4.9500000000000004e-05,
|
|
"loss": 9.1931,
|
|
"mean_token_accuracy": 0.05993704758584499,
|
|
"num_tokens": 183010.0,
|
|
"step": 100
|
|
},
|
|
{
|
|
"entropy": 10.653488159179688,
|
|
"epoch": 0.008770464416972937,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 5.2e-05,
|
|
"loss": 9.16,
|
|
"mean_token_accuracy": 0.053666260465979575,
|
|
"num_tokens": 192589.0,
|
|
"step": 105
|
|
},
|
|
{
|
|
"entropy": 10.622858619689941,
|
|
"epoch": 0.009188105579685933,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 5.45e-05,
|
|
"loss": 9.013,
|
|
"mean_token_accuracy": 0.06004327610135078,
|
|
"num_tokens": 201638.0,
|
|
"step": 110
|
|
},
|
|
{
|
|
"entropy": 10.569721031188966,
|
|
"epoch": 0.00960574674239893,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 5.7e-05,
|
|
"loss": 8.89,
|
|
"mean_token_accuracy": 0.05817726403474808,
|
|
"num_tokens": 209862.0,
|
|
"step": 115
|
|
},
|
|
{
|
|
"entropy": 10.519128704071045,
|
|
"epoch": 0.010023387905111928,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 5.9499999999999996e-05,
|
|
"loss": 8.8803,
|
|
"mean_token_accuracy": 0.04828422553837299,
|
|
"num_tokens": 218897.0,
|
|
"step": 120
|
|
},
|
|
{
|
|
"entropy": 10.48040943145752,
|
|
"epoch": 0.010441029067824925,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 6.2e-05,
|
|
"loss": 8.7326,
|
|
"mean_token_accuracy": 0.057341094315052035,
|
|
"num_tokens": 227682.0,
|
|
"step": 125
|
|
},
|
|
{
|
|
"entropy": 10.404988002777099,
|
|
"epoch": 0.010858670230537921,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 6.450000000000001e-05,
|
|
"loss": 8.5531,
|
|
"mean_token_accuracy": 0.05646193064749241,
|
|
"num_tokens": 236170.0,
|
|
"step": 130
|
|
},
|
|
{
|
|
"entropy": 10.337473011016845,
|
|
"epoch": 0.011276311393250919,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 6.7e-05,
|
|
"loss": 8.5016,
|
|
"mean_token_accuracy": 0.054118812829256055,
|
|
"num_tokens": 245710.0,
|
|
"step": 135
|
|
},
|
|
{
|
|
"entropy": 10.269655227661133,
|
|
"epoch": 0.011693952555963916,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 6.950000000000001e-05,
|
|
"loss": 8.3193,
|
|
"mean_token_accuracy": 0.06037080101668835,
|
|
"num_tokens": 254751.0,
|
|
"step": 140
|
|
},
|
|
{
|
|
"entropy": 10.123066329956055,
|
|
"epoch": 0.012111593718676913,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 7.2e-05,
|
|
"loss": 8.1922,
|
|
"mean_token_accuracy": 0.06263931393623352,
|
|
"num_tokens": 264210.0,
|
|
"step": 145
|
|
},
|
|
{
|
|
"entropy": 10.026834297180176,
|
|
"epoch": 0.01252923488138991,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 7.45e-05,
|
|
"loss": 8.1098,
|
|
"mean_token_accuracy": 0.06494732424616814,
|
|
"num_tokens": 272944.0,
|
|
"step": 150
|
|
},
|
|
{
|
|
"entropy": 9.923717784881593,
|
|
"epoch": 0.012946876044102907,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 7.7e-05,
|
|
"loss": 7.9366,
|
|
"mean_token_accuracy": 0.06645521372556687,
|
|
"num_tokens": 281311.0,
|
|
"step": 155
|
|
},
|
|
{
|
|
"entropy": 9.686262702941894,
|
|
"epoch": 0.013364517206815904,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 7.950000000000001e-05,
|
|
"loss": 7.8102,
|
|
"mean_token_accuracy": 0.06696667969226837,
|
|
"num_tokens": 289701.0,
|
|
"step": 160
|
|
},
|
|
{
|
|
"entropy": 9.53008050918579,
|
|
"epoch": 0.013782158369528901,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 8.2e-05,
|
|
"loss": 7.8033,
|
|
"mean_token_accuracy": 0.06480560302734376,
|
|
"num_tokens": 299459.0,
|
|
"step": 165
|
|
},
|
|
{
|
|
"entropy": 9.334712505340576,
|
|
"epoch": 0.014199799532241897,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 8.450000000000001e-05,
|
|
"loss": 7.7276,
|
|
"mean_token_accuracy": 0.06751208230853081,
|
|
"num_tokens": 309343.0,
|
|
"step": 170
|
|
},
|
|
{
|
|
"entropy": 9.117801856994628,
|
|
"epoch": 0.014617440694954895,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 8.7e-05,
|
|
"loss": 7.6628,
|
|
"mean_token_accuracy": 0.06329603157937527,
|
|
"num_tokens": 318840.0,
|
|
"step": 175
|
|
},
|
|
{
|
|
"entropy": 8.88758544921875,
|
|
"epoch": 0.015035081857667892,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 8.95e-05,
|
|
"loss": 7.4494,
|
|
"mean_token_accuracy": 0.07078598737716675,
|
|
"num_tokens": 328689.0,
|
|
"step": 180
|
|
},
|
|
{
|
|
"entropy": 8.713505363464355,
|
|
"epoch": 0.01545272302038089,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 9.2e-05,
|
|
"loss": 7.5296,
|
|
"mean_token_accuracy": 0.07133941762149335,
|
|
"num_tokens": 338209.0,
|
|
"step": 185
|
|
},
|
|
{
|
|
"entropy": 8.533864212036132,
|
|
"epoch": 0.015870364183093885,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 9.45e-05,
|
|
"loss": 7.3715,
|
|
"mean_token_accuracy": 0.07491575330495834,
|
|
"num_tokens": 347270.0,
|
|
"step": 190
|
|
},
|
|
{
|
|
"entropy": 8.331917572021485,
|
|
"epoch": 0.016288005345806884,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 9.7e-05,
|
|
"loss": 7.3864,
|
|
"mean_token_accuracy": 0.07862697467207909,
|
|
"num_tokens": 356366.0,
|
|
"step": 195
|
|
},
|
|
{
|
|
"entropy": 8.292905139923096,
|
|
"epoch": 0.01670564650851988,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 9.95e-05,
|
|
"loss": 7.3321,
|
|
"mean_token_accuracy": 0.07781913727521897,
|
|
"num_tokens": 365980.0,
|
|
"step": 200
|
|
},
|
|
{
|
|
"entropy": 8.17343864440918,
|
|
"epoch": 0.017123287671232876,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.000102,
|
|
"loss": 7.2859,
|
|
"mean_token_accuracy": 0.08276912495493889,
|
|
"num_tokens": 374591.0,
|
|
"step": 205
|
|
},
|
|
{
|
|
"entropy": 8.114312171936035,
|
|
"epoch": 0.017540928833945875,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00010449999999999999,
|
|
"loss": 7.2652,
|
|
"mean_token_accuracy": 0.08255952596664429,
|
|
"num_tokens": 383250.0,
|
|
"step": 210
|
|
},
|
|
{
|
|
"entropy": 8.142033052444457,
|
|
"epoch": 0.01795856999665887,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000107,
|
|
"loss": 7.1955,
|
|
"mean_token_accuracy": 0.07966764494776726,
|
|
"num_tokens": 391502.0,
|
|
"step": 215
|
|
},
|
|
{
|
|
"entropy": 8.033121585845947,
|
|
"epoch": 0.018376211159371866,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0001095,
|
|
"loss": 7.1094,
|
|
"mean_token_accuracy": 0.08625469133257865,
|
|
"num_tokens": 400225.0,
|
|
"step": 220
|
|
},
|
|
{
|
|
"entropy": 8.037012720108033,
|
|
"epoch": 0.018793852322084866,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000112,
|
|
"loss": 7.3113,
|
|
"mean_token_accuracy": 0.07627052702009678,
|
|
"num_tokens": 410008.0,
|
|
"step": 225
|
|
},
|
|
{
|
|
"entropy": 7.976403427124024,
|
|
"epoch": 0.01921149348479786,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0001145,
|
|
"loss": 7.2122,
|
|
"mean_token_accuracy": 0.08434663638472557,
|
|
"num_tokens": 418979.0,
|
|
"step": 230
|
|
},
|
|
{
|
|
"entropy": 7.954119348526001,
|
|
"epoch": 0.01962913464751086,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00011700000000000001,
|
|
"loss": 7.1858,
|
|
"mean_token_accuracy": 0.08367608934640884,
|
|
"num_tokens": 428139.0,
|
|
"step": 235
|
|
},
|
|
{
|
|
"entropy": 7.8628496646881105,
|
|
"epoch": 0.020046775810223856,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00011949999999999999,
|
|
"loss": 7.1046,
|
|
"mean_token_accuracy": 0.08570514917373658,
|
|
"num_tokens": 437113.0,
|
|
"step": 240
|
|
},
|
|
{
|
|
"entropy": 7.932403039932251,
|
|
"epoch": 0.020464416972936852,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000122,
|
|
"loss": 7.2954,
|
|
"mean_token_accuracy": 0.08083686679601669,
|
|
"num_tokens": 446879.0,
|
|
"step": 245
|
|
},
|
|
{
|
|
"entropy": 7.807932806015015,
|
|
"epoch": 0.02088205813564985,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0001245,
|
|
"loss": 7.1784,
|
|
"mean_token_accuracy": 0.08404311686754226,
|
|
"num_tokens": 456362.0,
|
|
"step": 250
|
|
},
|
|
{
|
|
"entropy": 7.829455995559693,
|
|
"epoch": 0.021299699298362847,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000127,
|
|
"loss": 6.9918,
|
|
"mean_token_accuracy": 0.09061411544680595,
|
|
"num_tokens": 464930.0,
|
|
"step": 255
|
|
},
|
|
{
|
|
"entropy": 7.877001619338989,
|
|
"epoch": 0.021717340461075842,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0001295,
|
|
"loss": 7.1647,
|
|
"mean_token_accuracy": 0.08374429196119308,
|
|
"num_tokens": 474303.0,
|
|
"step": 260
|
|
},
|
|
{
|
|
"entropy": 7.794501399993896,
|
|
"epoch": 0.02213498162378884,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000132,
|
|
"loss": 7.1539,
|
|
"mean_token_accuracy": 0.08738574758172035,
|
|
"num_tokens": 483750.0,
|
|
"step": 265
|
|
},
|
|
{
|
|
"entropy": 7.762907552719116,
|
|
"epoch": 0.022552622786501837,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00013450000000000002,
|
|
"loss": 7.0529,
|
|
"mean_token_accuracy": 0.09093769788742065,
|
|
"num_tokens": 493325.0,
|
|
"step": 270
|
|
},
|
|
{
|
|
"entropy": 7.741158294677734,
|
|
"epoch": 0.022970263949214833,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00013700000000000002,
|
|
"loss": 7.0377,
|
|
"mean_token_accuracy": 0.08475295156240463,
|
|
"num_tokens": 501907.0,
|
|
"step": 275
|
|
},
|
|
{
|
|
"entropy": 7.704169273376465,
|
|
"epoch": 0.023387905111927832,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0001395,
|
|
"loss": 7.0759,
|
|
"mean_token_accuracy": 0.09049696251749992,
|
|
"num_tokens": 511522.0,
|
|
"step": 280
|
|
},
|
|
{
|
|
"entropy": 7.68439040184021,
|
|
"epoch": 0.023805546274640828,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00014199999999999998,
|
|
"loss": 7.0277,
|
|
"mean_token_accuracy": 0.08685763627290725,
|
|
"num_tokens": 521287.0,
|
|
"step": 285
|
|
},
|
|
{
|
|
"entropy": 7.689414691925049,
|
|
"epoch": 0.024223187437353827,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0001445,
|
|
"loss": 7.1013,
|
|
"mean_token_accuracy": 0.08630543872714043,
|
|
"num_tokens": 530631.0,
|
|
"step": 290
|
|
},
|
|
{
|
|
"entropy": 7.624138498306275,
|
|
"epoch": 0.024640828600066823,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000147,
|
|
"loss": 6.9712,
|
|
"mean_token_accuracy": 0.09986182302236557,
|
|
"num_tokens": 540386.0,
|
|
"step": 295
|
|
},
|
|
{
|
|
"entropy": 7.671041774749756,
|
|
"epoch": 0.02505846976277982,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0001495,
|
|
"loss": 7.0573,
|
|
"mean_token_accuracy": 0.08439475223422051,
|
|
"num_tokens": 550121.0,
|
|
"step": 300
|
|
},
|
|
{
|
|
"entropy": 7.569111251831055,
|
|
"epoch": 0.025476110925492818,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000152,
|
|
"loss": 6.9112,
|
|
"mean_token_accuracy": 0.09254205971956253,
|
|
"num_tokens": 559460.0,
|
|
"step": 305
|
|
},
|
|
{
|
|
"entropy": 7.6026232719421385,
|
|
"epoch": 0.025893752088205813,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00015450000000000001,
|
|
"loss": 6.8726,
|
|
"mean_token_accuracy": 0.0958409771323204,
|
|
"num_tokens": 568392.0,
|
|
"step": 310
|
|
},
|
|
{
|
|
"entropy": 7.504022693634033,
|
|
"epoch": 0.02631139325091881,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.000157,
|
|
"loss": 6.9599,
|
|
"mean_token_accuracy": 0.09224955886602401,
|
|
"num_tokens": 578248.0,
|
|
"step": 315
|
|
},
|
|
{
|
|
"entropy": 7.5831845760345455,
|
|
"epoch": 0.026729034413631808,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0001595,
|
|
"loss": 7.0295,
|
|
"mean_token_accuracy": 0.08987967744469642,
|
|
"num_tokens": 588164.0,
|
|
"step": 320
|
|
},
|
|
{
|
|
"entropy": 7.5552794456481935,
|
|
"epoch": 0.027146675576344804,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.000162,
|
|
"loss": 6.9487,
|
|
"mean_token_accuracy": 0.09430753514170646,
|
|
"num_tokens": 598715.0,
|
|
"step": 325
|
|
},
|
|
{
|
|
"entropy": 7.5547398090362545,
|
|
"epoch": 0.027564316739057803,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00016450000000000001,
|
|
"loss": 6.8841,
|
|
"mean_token_accuracy": 0.09914051964879037,
|
|
"num_tokens": 606939.0,
|
|
"step": 330
|
|
},
|
|
{
|
|
"entropy": 7.417043685913086,
|
|
"epoch": 0.0279819579017708,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00016700000000000002,
|
|
"loss": 6.9714,
|
|
"mean_token_accuracy": 0.09765534549951553,
|
|
"num_tokens": 615803.0,
|
|
"step": 335
|
|
},
|
|
{
|
|
"entropy": 7.536453628540039,
|
|
"epoch": 0.028399599064483794,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00016950000000000003,
|
|
"loss": 6.8297,
|
|
"mean_token_accuracy": 0.09691216871142387,
|
|
"num_tokens": 624730.0,
|
|
"step": 340
|
|
},
|
|
{
|
|
"entropy": 7.539470243453979,
|
|
"epoch": 0.028817240227196794,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00017199999999999998,
|
|
"loss": 6.931,
|
|
"mean_token_accuracy": 0.09587549567222595,
|
|
"num_tokens": 634082.0,
|
|
"step": 345
|
|
},
|
|
{
|
|
"entropy": 7.414178943634033,
|
|
"epoch": 0.02923488138990979,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00017449999999999999,
|
|
"loss": 6.9083,
|
|
"mean_token_accuracy": 0.09485536590218543,
|
|
"num_tokens": 643367.0,
|
|
"step": 350
|
|
},
|
|
{
|
|
"entropy": 7.387429285049438,
|
|
"epoch": 0.029652522552622785,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000177,
|
|
"loss": 6.7242,
|
|
"mean_token_accuracy": 0.09872433170676231,
|
|
"num_tokens": 651861.0,
|
|
"step": 355
|
|
},
|
|
{
|
|
"entropy": 7.464349985122681,
|
|
"epoch": 0.030070163715335784,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0001795,
|
|
"loss": 6.8556,
|
|
"mean_token_accuracy": 0.09326324984431267,
|
|
"num_tokens": 661064.0,
|
|
"step": 360
|
|
},
|
|
{
|
|
"entropy": 7.392336225509643,
|
|
"epoch": 0.03048780487804878,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000182,
|
|
"loss": 6.8352,
|
|
"mean_token_accuracy": 0.10462646037340165,
|
|
"num_tokens": 669299.0,
|
|
"step": 365
|
|
},
|
|
{
|
|
"entropy": 7.248696994781494,
|
|
"epoch": 0.03090544604076178,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0001845,
|
|
"loss": 6.8988,
|
|
"mean_token_accuracy": 0.09198433235287666,
|
|
"num_tokens": 678631.0,
|
|
"step": 370
|
|
},
|
|
{
|
|
"entropy": 7.445321846008301,
|
|
"epoch": 0.03132308720347477,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000187,
|
|
"loss": 6.8925,
|
|
"mean_token_accuracy": 0.09772585704922676,
|
|
"num_tokens": 688511.0,
|
|
"step": 375
|
|
},
|
|
{
|
|
"entropy": 7.484406995773315,
|
|
"epoch": 0.03174072836618777,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0001895,
|
|
"loss": 6.8465,
|
|
"mean_token_accuracy": 0.09334805831313134,
|
|
"num_tokens": 697956.0,
|
|
"step": 380
|
|
},
|
|
{
|
|
"entropy": 7.3463782787323,
|
|
"epoch": 0.03215836952890077,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000192,
|
|
"loss": 6.7552,
|
|
"mean_token_accuracy": 0.10220230743288994,
|
|
"num_tokens": 706779.0,
|
|
"step": 385
|
|
},
|
|
{
|
|
"entropy": 7.295664262771607,
|
|
"epoch": 0.03257601069161377,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0001945,
|
|
"loss": 6.7444,
|
|
"mean_token_accuracy": 0.09592411890625954,
|
|
"num_tokens": 715749.0,
|
|
"step": 390
|
|
},
|
|
{
|
|
"entropy": 7.331249046325683,
|
|
"epoch": 0.03299365185432676,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00019700000000000002,
|
|
"loss": 6.7177,
|
|
"mean_token_accuracy": 0.09796938598155976,
|
|
"num_tokens": 724756.0,
|
|
"step": 395
|
|
},
|
|
{
|
|
"entropy": 7.257160568237305,
|
|
"epoch": 0.03341129301703976,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00019950000000000002,
|
|
"loss": 6.7422,
|
|
"mean_token_accuracy": 0.09832950606942177,
|
|
"num_tokens": 733288.0,
|
|
"step": 400
|
|
},
|
|
{
|
|
"entropy": 7.405258226394653,
|
|
"epoch": 0.03382893417975276,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.000202,
|
|
"loss": 6.8476,
|
|
"mean_token_accuracy": 0.0943653255701065,
|
|
"num_tokens": 741629.0,
|
|
"step": 405
|
|
},
|
|
{
|
|
"entropy": 7.263295269012451,
|
|
"epoch": 0.03424657534246575,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00020449999999999998,
|
|
"loss": 6.7841,
|
|
"mean_token_accuracy": 0.1012955941259861,
|
|
"num_tokens": 751336.0,
|
|
"step": 410
|
|
},
|
|
{
|
|
"entropy": 7.402045774459839,
|
|
"epoch": 0.03466421650517875,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000207,
|
|
"loss": 6.856,
|
|
"mean_token_accuracy": 0.09290716797113419,
|
|
"num_tokens": 759725.0,
|
|
"step": 415
|
|
},
|
|
{
|
|
"entropy": 7.322671508789062,
|
|
"epoch": 0.03508185766789175,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0002095,
|
|
"loss": 6.845,
|
|
"mean_token_accuracy": 0.09813571646809578,
|
|
"num_tokens": 769752.0,
|
|
"step": 420
|
|
},
|
|
{
|
|
"entropy": 7.268389272689819,
|
|
"epoch": 0.03549949883060474,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000212,
|
|
"loss": 6.7365,
|
|
"mean_token_accuracy": 0.10029055625200271,
|
|
"num_tokens": 779124.0,
|
|
"step": 425
|
|
},
|
|
{
|
|
"entropy": 7.208940410614014,
|
|
"epoch": 0.03591713999331774,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0002145,
|
|
"loss": 6.7024,
|
|
"mean_token_accuracy": 0.10402928516268731,
|
|
"num_tokens": 788892.0,
|
|
"step": 430
|
|
},
|
|
{
|
|
"entropy": 7.189973258972168,
|
|
"epoch": 0.03633478115603074,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00021700000000000002,
|
|
"loss": 6.6662,
|
|
"mean_token_accuracy": 0.10119749382138252,
|
|
"num_tokens": 798265.0,
|
|
"step": 435
|
|
},
|
|
{
|
|
"entropy": 7.194095945358276,
|
|
"epoch": 0.03675242231874373,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0002195,
|
|
"loss": 6.6231,
|
|
"mean_token_accuracy": 0.10882524475455284,
|
|
"num_tokens": 806896.0,
|
|
"step": 440
|
|
},
|
|
{
|
|
"entropy": 7.201065158843994,
|
|
"epoch": 0.03717006348145673,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000222,
|
|
"loss": 6.689,
|
|
"mean_token_accuracy": 0.10466736480593682,
|
|
"num_tokens": 815540.0,
|
|
"step": 445
|
|
},
|
|
{
|
|
"entropy": 7.163028383255005,
|
|
"epoch": 0.03758770464416973,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0002245,
|
|
"loss": 6.7443,
|
|
"mean_token_accuracy": 0.10173500478267669,
|
|
"num_tokens": 824555.0,
|
|
"step": 450
|
|
},
|
|
{
|
|
"entropy": 7.269956779479981,
|
|
"epoch": 0.03800534580688272,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00022700000000000002,
|
|
"loss": 6.7737,
|
|
"mean_token_accuracy": 0.10270200073719024,
|
|
"num_tokens": 833414.0,
|
|
"step": 455
|
|
},
|
|
{
|
|
"entropy": 7.098545503616333,
|
|
"epoch": 0.03842298696959572,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00022950000000000002,
|
|
"loss": 6.6325,
|
|
"mean_token_accuracy": 0.10786343663930893,
|
|
"num_tokens": 842644.0,
|
|
"step": 460
|
|
},
|
|
{
|
|
"entropy": 7.197147083282471,
|
|
"epoch": 0.03884062813230872,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00023200000000000003,
|
|
"loss": 6.6693,
|
|
"mean_token_accuracy": 0.10085522830486297,
|
|
"num_tokens": 851786.0,
|
|
"step": 465
|
|
},
|
|
{
|
|
"entropy": 7.095899295806885,
|
|
"epoch": 0.03925826929502172,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00023449999999999998,
|
|
"loss": 6.7144,
|
|
"mean_token_accuracy": 0.1063760556280613,
|
|
"num_tokens": 861508.0,
|
|
"step": 470
|
|
},
|
|
{
|
|
"entropy": 7.154467391967773,
|
|
"epoch": 0.03967591045773471,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000237,
|
|
"loss": 6.5905,
|
|
"mean_token_accuracy": 0.10809945836663246,
|
|
"num_tokens": 870433.0,
|
|
"step": 475
|
|
},
|
|
{
|
|
"entropy": 7.184867238998413,
|
|
"epoch": 0.04009355162044771,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0002395,
|
|
"loss": 6.6928,
|
|
"mean_token_accuracy": 0.10560849010944366,
|
|
"num_tokens": 879059.0,
|
|
"step": 480
|
|
},
|
|
{
|
|
"entropy": 7.1450403213500975,
|
|
"epoch": 0.04051119278316071,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000242,
|
|
"loss": 6.7403,
|
|
"mean_token_accuracy": 0.09940413013100624,
|
|
"num_tokens": 888009.0,
|
|
"step": 485
|
|
},
|
|
{
|
|
"entropy": 7.092233419418335,
|
|
"epoch": 0.040928833945873704,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0002445,
|
|
"loss": 6.6089,
|
|
"mean_token_accuracy": 0.10285484269261361,
|
|
"num_tokens": 897335.0,
|
|
"step": 490
|
|
},
|
|
{
|
|
"entropy": 7.264479684829712,
|
|
"epoch": 0.0413464751085867,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000247,
|
|
"loss": 6.6248,
|
|
"mean_token_accuracy": 0.10704769417643548,
|
|
"num_tokens": 905802.0,
|
|
"step": 495
|
|
},
|
|
{
|
|
"entropy": 7.013559818267822,
|
|
"epoch": 0.0417641162712997,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0002495,
|
|
"loss": 6.6091,
|
|
"mean_token_accuracy": 0.1084491603076458,
|
|
"num_tokens": 914836.0,
|
|
"step": 500
|
|
},
|
|
{
|
|
"entropy": 6.988007974624634,
|
|
"epoch": 0.042181757434012694,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000252,
|
|
"loss": 6.5574,
|
|
"mean_token_accuracy": 0.11251411363482475,
|
|
"num_tokens": 924254.0,
|
|
"step": 505
|
|
},
|
|
{
|
|
"entropy": 7.116152048110962,
|
|
"epoch": 0.04259939859672569,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0002545,
|
|
"loss": 6.6555,
|
|
"mean_token_accuracy": 0.1060157686471939,
|
|
"num_tokens": 933841.0,
|
|
"step": 510
|
|
},
|
|
{
|
|
"entropy": 7.129690933227539,
|
|
"epoch": 0.04301703975943869,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000257,
|
|
"loss": 6.7157,
|
|
"mean_token_accuracy": 0.10084601864218712,
|
|
"num_tokens": 943304.0,
|
|
"step": 515
|
|
},
|
|
{
|
|
"entropy": 7.06993350982666,
|
|
"epoch": 0.043434680922151685,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0002595,
|
|
"loss": 6.5385,
|
|
"mean_token_accuracy": 0.11060969755053521,
|
|
"num_tokens": 952915.0,
|
|
"step": 520
|
|
},
|
|
{
|
|
"entropy": 7.076866674423218,
|
|
"epoch": 0.043852322084864684,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000262,
|
|
"loss": 6.598,
|
|
"mean_token_accuracy": 0.10570925623178482,
|
|
"num_tokens": 962752.0,
|
|
"step": 525
|
|
},
|
|
{
|
|
"entropy": 7.055672740936279,
|
|
"epoch": 0.04426996324757768,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00026450000000000003,
|
|
"loss": 6.6226,
|
|
"mean_token_accuracy": 0.1023420087993145,
|
|
"num_tokens": 971240.0,
|
|
"step": 530
|
|
},
|
|
{
|
|
"entropy": 7.108932256698608,
|
|
"epoch": 0.044687604410290675,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00026700000000000004,
|
|
"loss": 6.6471,
|
|
"mean_token_accuracy": 0.10342941582202911,
|
|
"num_tokens": 981391.0,
|
|
"step": 535
|
|
},
|
|
{
|
|
"entropy": 7.1047523498535154,
|
|
"epoch": 0.045105245573003674,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00026950000000000005,
|
|
"loss": 6.6554,
|
|
"mean_token_accuracy": 0.10619911253452301,
|
|
"num_tokens": 990551.0,
|
|
"step": 540
|
|
},
|
|
{
|
|
"entropy": 7.004219102859497,
|
|
"epoch": 0.045522886735716674,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00027200000000000005,
|
|
"loss": 6.5787,
|
|
"mean_token_accuracy": 0.11122526898980141,
|
|
"num_tokens": 999593.0,
|
|
"step": 545
|
|
},
|
|
{
|
|
"entropy": 7.028263998031616,
|
|
"epoch": 0.045940527898429666,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0002745,
|
|
"loss": 6.6418,
|
|
"mean_token_accuracy": 0.10322482436895371,
|
|
"num_tokens": 1008785.0,
|
|
"step": 550
|
|
},
|
|
{
|
|
"entropy": 7.000995635986328,
|
|
"epoch": 0.046358169061142665,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000277,
|
|
"loss": 6.632,
|
|
"mean_token_accuracy": 0.10688607320189476,
|
|
"num_tokens": 1016815.0,
|
|
"step": 555
|
|
},
|
|
{
|
|
"entropy": 7.063908100128174,
|
|
"epoch": 0.046775810223855664,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0002795,
|
|
"loss": 6.5161,
|
|
"mean_token_accuracy": 0.11323921233415604,
|
|
"num_tokens": 1026182.0,
|
|
"step": 560
|
|
},
|
|
{
|
|
"entropy": 6.97571029663086,
|
|
"epoch": 0.04719345138656866,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00028199999999999997,
|
|
"loss": 6.4512,
|
|
"mean_token_accuracy": 0.11479591503739357,
|
|
"num_tokens": 1034032.0,
|
|
"step": 565
|
|
},
|
|
{
|
|
"entropy": 6.954489898681641,
|
|
"epoch": 0.047611092549281656,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0002845,
|
|
"loss": 6.6465,
|
|
"mean_token_accuracy": 0.10568908601999283,
|
|
"num_tokens": 1043493.0,
|
|
"step": 570
|
|
},
|
|
{
|
|
"entropy": 7.076480293273926,
|
|
"epoch": 0.048028733711994655,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000287,
|
|
"loss": 6.5541,
|
|
"mean_token_accuracy": 0.1120546206831932,
|
|
"num_tokens": 1052989.0,
|
|
"step": 575
|
|
},
|
|
{
|
|
"entropy": 6.9995513439178465,
|
|
"epoch": 0.048446374874707654,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0002895,
|
|
"loss": 6.5191,
|
|
"mean_token_accuracy": 0.10802618637681008,
|
|
"num_tokens": 1061803.0,
|
|
"step": 580
|
|
},
|
|
{
|
|
"entropy": 6.9974480152130125,
|
|
"epoch": 0.048864016037420646,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000292,
|
|
"loss": 6.6256,
|
|
"mean_token_accuracy": 0.10830648243427277,
|
|
"num_tokens": 1071227.0,
|
|
"step": 585
|
|
},
|
|
{
|
|
"entropy": 7.019133281707764,
|
|
"epoch": 0.049281657200133645,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0002945,
|
|
"loss": 6.6256,
|
|
"mean_token_accuracy": 0.1137481078505516,
|
|
"num_tokens": 1080082.0,
|
|
"step": 590
|
|
},
|
|
{
|
|
"entropy": 6.9460889339447025,
|
|
"epoch": 0.049699298362846644,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000297,
|
|
"loss": 6.463,
|
|
"mean_token_accuracy": 0.11860100626945495,
|
|
"num_tokens": 1089750.0,
|
|
"step": 595
|
|
},
|
|
{
|
|
"entropy": 6.8880175113677975,
|
|
"epoch": 0.05011693952555964,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0002995,
|
|
"loss": 6.4558,
|
|
"mean_token_accuracy": 0.11189346835017204,
|
|
"num_tokens": 1098691.0,
|
|
"step": 600
|
|
},
|
|
{
|
|
"entropy": 7.010653829574585,
|
|
"epoch": 0.050534580688272636,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000302,
|
|
"loss": 6.4992,
|
|
"mean_token_accuracy": 0.11314608827233315,
|
|
"num_tokens": 1107602.0,
|
|
"step": 605
|
|
},
|
|
{
|
|
"entropy": 6.826686143875122,
|
|
"epoch": 0.050952221850985635,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0003045,
|
|
"loss": 6.4167,
|
|
"mean_token_accuracy": 0.11482465639710426,
|
|
"num_tokens": 1116426.0,
|
|
"step": 610
|
|
},
|
|
{
|
|
"entropy": 6.978339052200317,
|
|
"epoch": 0.05136986301369863,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.000307,
|
|
"loss": 6.5929,
|
|
"mean_token_accuracy": 0.10989554226398468,
|
|
"num_tokens": 1126221.0,
|
|
"step": 615
|
|
},
|
|
{
|
|
"entropy": 6.9196573257446286,
|
|
"epoch": 0.051787504176411626,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0003095,
|
|
"loss": 6.4681,
|
|
"mean_token_accuracy": 0.11944901272654533,
|
|
"num_tokens": 1135662.0,
|
|
"step": 620
|
|
},
|
|
{
|
|
"entropy": 6.880191802978516,
|
|
"epoch": 0.052205145339124626,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000312,
|
|
"loss": 6.5525,
|
|
"mean_token_accuracy": 0.11337181329727172,
|
|
"num_tokens": 1143963.0,
|
|
"step": 625
|
|
},
|
|
{
|
|
"entropy": 6.883874082565308,
|
|
"epoch": 0.05262278650183762,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0003145,
|
|
"loss": 6.4554,
|
|
"mean_token_accuracy": 0.1215918242931366,
|
|
"num_tokens": 1152470.0,
|
|
"step": 630
|
|
},
|
|
{
|
|
"entropy": 6.959899091720581,
|
|
"epoch": 0.05304042766455062,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000317,
|
|
"loss": 6.414,
|
|
"mean_token_accuracy": 0.11987600699067116,
|
|
"num_tokens": 1161257.0,
|
|
"step": 635
|
|
},
|
|
{
|
|
"entropy": 6.86087121963501,
|
|
"epoch": 0.053458068827263616,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0003195,
|
|
"loss": 6.533,
|
|
"mean_token_accuracy": 0.10690693482756615,
|
|
"num_tokens": 1170969.0,
|
|
"step": 640
|
|
},
|
|
{
|
|
"entropy": 6.990806341171265,
|
|
"epoch": 0.053875709989976615,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000322,
|
|
"loss": 6.6717,
|
|
"mean_token_accuracy": 0.11218328699469567,
|
|
"num_tokens": 1181127.0,
|
|
"step": 645
|
|
},
|
|
{
|
|
"entropy": 6.9073868751525875,
|
|
"epoch": 0.05429335115268961,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00032450000000000003,
|
|
"loss": 6.4613,
|
|
"mean_token_accuracy": 0.11650743409991264,
|
|
"num_tokens": 1190260.0,
|
|
"step": 650
|
|
},
|
|
{
|
|
"entropy": 6.870417165756225,
|
|
"epoch": 0.05471099231540261,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00032700000000000003,
|
|
"loss": 6.5375,
|
|
"mean_token_accuracy": 0.11634354665875435,
|
|
"num_tokens": 1200013.0,
|
|
"step": 655
|
|
},
|
|
{
|
|
"entropy": 6.948531675338745,
|
|
"epoch": 0.055128633478115606,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00032950000000000004,
|
|
"loss": 6.4582,
|
|
"mean_token_accuracy": 0.11997871845960617,
|
|
"num_tokens": 1209239.0,
|
|
"step": 660
|
|
},
|
|
{
|
|
"entropy": 6.796932411193848,
|
|
"epoch": 0.0555462746408286,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00033200000000000005,
|
|
"loss": 6.4026,
|
|
"mean_token_accuracy": 0.11352865546941757,
|
|
"num_tokens": 1218552.0,
|
|
"step": 665
|
|
},
|
|
{
|
|
"entropy": 6.817508411407471,
|
|
"epoch": 0.0559639158035416,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00033450000000000005,
|
|
"loss": 6.4757,
|
|
"mean_token_accuracy": 0.11437263563275338,
|
|
"num_tokens": 1227632.0,
|
|
"step": 670
|
|
},
|
|
{
|
|
"entropy": 6.864944791793823,
|
|
"epoch": 0.056381556966254597,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000337,
|
|
"loss": 6.5136,
|
|
"mean_token_accuracy": 0.11246693953871727,
|
|
"num_tokens": 1236433.0,
|
|
"step": 675
|
|
},
|
|
{
|
|
"entropy": 6.802402019500732,
|
|
"epoch": 0.05679919812896759,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0003395,
|
|
"loss": 6.5371,
|
|
"mean_token_accuracy": 0.1055721789598465,
|
|
"num_tokens": 1245700.0,
|
|
"step": 680
|
|
},
|
|
{
|
|
"entropy": 6.921284770965576,
|
|
"epoch": 0.05721683929168059,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000342,
|
|
"loss": 6.3732,
|
|
"mean_token_accuracy": 0.11802853867411614,
|
|
"num_tokens": 1254206.0,
|
|
"step": 685
|
|
},
|
|
{
|
|
"entropy": 6.763827323913574,
|
|
"epoch": 0.05763448045439359,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00034449999999999997,
|
|
"loss": 6.4184,
|
|
"mean_token_accuracy": 0.1180158130824566,
|
|
"num_tokens": 1263302.0,
|
|
"step": 690
|
|
},
|
|
{
|
|
"entropy": 6.76256685256958,
|
|
"epoch": 0.05805212161710658,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000347,
|
|
"loss": 6.4661,
|
|
"mean_token_accuracy": 0.11739929467439651,
|
|
"num_tokens": 1272998.0,
|
|
"step": 695
|
|
},
|
|
{
|
|
"entropy": 6.8152045726776125,
|
|
"epoch": 0.05846976277981958,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0003495,
|
|
"loss": 6.4304,
|
|
"mean_token_accuracy": 0.1213896095752716,
|
|
"num_tokens": 1281955.0,
|
|
"step": 700
|
|
},
|
|
{
|
|
"entropy": 6.832838869094848,
|
|
"epoch": 0.05888740394253258,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000352,
|
|
"loss": 6.4577,
|
|
"mean_token_accuracy": 0.11378672420978546,
|
|
"num_tokens": 1291219.0,
|
|
"step": 705
|
|
},
|
|
{
|
|
"entropy": 6.797576570510865,
|
|
"epoch": 0.05930504510524557,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0003545,
|
|
"loss": 6.4718,
|
|
"mean_token_accuracy": 0.11139240860939026,
|
|
"num_tokens": 1300963.0,
|
|
"step": 710
|
|
},
|
|
{
|
|
"entropy": 6.8802446842193605,
|
|
"epoch": 0.05972268626795857,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000357,
|
|
"loss": 6.4965,
|
|
"mean_token_accuracy": 0.11046546846628189,
|
|
"num_tokens": 1310112.0,
|
|
"step": 715
|
|
},
|
|
{
|
|
"entropy": 6.775373268127441,
|
|
"epoch": 0.06014032743067157,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0003595,
|
|
"loss": 6.4278,
|
|
"mean_token_accuracy": 0.12265736609697342,
|
|
"num_tokens": 1319309.0,
|
|
"step": 720
|
|
},
|
|
{
|
|
"entropy": 6.66271562576294,
|
|
"epoch": 0.06055796859338457,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000362,
|
|
"loss": 6.3938,
|
|
"mean_token_accuracy": 0.11732437312602997,
|
|
"num_tokens": 1329049.0,
|
|
"step": 725
|
|
},
|
|
{
|
|
"entropy": 6.728451251983643,
|
|
"epoch": 0.06097560975609756,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0003645,
|
|
"loss": 6.2447,
|
|
"mean_token_accuracy": 0.12135154455900192,
|
|
"num_tokens": 1337770.0,
|
|
"step": 730
|
|
},
|
|
{
|
|
"entropy": 6.623231744766235,
|
|
"epoch": 0.06139325091881056,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000367,
|
|
"loss": 6.3446,
|
|
"mean_token_accuracy": 0.11998333036899567,
|
|
"num_tokens": 1346705.0,
|
|
"step": 735
|
|
},
|
|
{
|
|
"entropy": 6.744262742996216,
|
|
"epoch": 0.06181089208152356,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0003695,
|
|
"loss": 6.405,
|
|
"mean_token_accuracy": 0.11962749883532524,
|
|
"num_tokens": 1354860.0,
|
|
"step": 740
|
|
},
|
|
{
|
|
"entropy": 6.765829467773438,
|
|
"epoch": 0.06222853324423655,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000372,
|
|
"loss": 6.3715,
|
|
"mean_token_accuracy": 0.11659613028168678,
|
|
"num_tokens": 1364140.0,
|
|
"step": 745
|
|
},
|
|
{
|
|
"entropy": 6.757311677932739,
|
|
"epoch": 0.06264617440694954,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0003745,
|
|
"loss": 6.5161,
|
|
"mean_token_accuracy": 0.10866649895906448,
|
|
"num_tokens": 1373645.0,
|
|
"step": 750
|
|
},
|
|
{
|
|
"entropy": 6.791751384735107,
|
|
"epoch": 0.06306381556966255,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000377,
|
|
"loss": 6.3843,
|
|
"mean_token_accuracy": 0.12191172316670418,
|
|
"num_tokens": 1383291.0,
|
|
"step": 755
|
|
},
|
|
{
|
|
"entropy": 6.669790124893188,
|
|
"epoch": 0.06348145673237554,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0003795,
|
|
"loss": 6.3243,
|
|
"mean_token_accuracy": 0.12068940699100494,
|
|
"num_tokens": 1391172.0,
|
|
"step": 760
|
|
},
|
|
{
|
|
"entropy": 6.717700242996216,
|
|
"epoch": 0.06389909789508853,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000382,
|
|
"loss": 6.3198,
|
|
"mean_token_accuracy": 0.12138244062662125,
|
|
"num_tokens": 1400864.0,
|
|
"step": 765
|
|
},
|
|
{
|
|
"entropy": 6.721026468276977,
|
|
"epoch": 0.06431673905780154,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0003845,
|
|
"loss": 6.3758,
|
|
"mean_token_accuracy": 0.1206473708152771,
|
|
"num_tokens": 1410570.0,
|
|
"step": 770
|
|
},
|
|
{
|
|
"entropy": 6.632958030700683,
|
|
"epoch": 0.06473438022051453,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00038700000000000003,
|
|
"loss": 6.35,
|
|
"mean_token_accuracy": 0.12267208248376846,
|
|
"num_tokens": 1419536.0,
|
|
"step": 775
|
|
},
|
|
{
|
|
"entropy": 6.612038612365723,
|
|
"epoch": 0.06515202138322754,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00038950000000000003,
|
|
"loss": 6.2546,
|
|
"mean_token_accuracy": 0.1263652376830578,
|
|
"num_tokens": 1428000.0,
|
|
"step": 780
|
|
},
|
|
{
|
|
"entropy": 6.690039157867432,
|
|
"epoch": 0.06556966254594053,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00039200000000000004,
|
|
"loss": 6.4562,
|
|
"mean_token_accuracy": 0.12093869373202323,
|
|
"num_tokens": 1437789.0,
|
|
"step": 785
|
|
},
|
|
{
|
|
"entropy": 6.636522626876831,
|
|
"epoch": 0.06598730370865352,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00039450000000000005,
|
|
"loss": 6.2563,
|
|
"mean_token_accuracy": 0.12446803748607635,
|
|
"num_tokens": 1446848.0,
|
|
"step": 790
|
|
},
|
|
{
|
|
"entropy": 6.619644260406494,
|
|
"epoch": 0.06640494487136653,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00039700000000000005,
|
|
"loss": 6.3158,
|
|
"mean_token_accuracy": 0.12070081159472465,
|
|
"num_tokens": 1455749.0,
|
|
"step": 795
|
|
},
|
|
{
|
|
"entropy": 6.622030401229859,
|
|
"epoch": 0.06682258603407952,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0003995,
|
|
"loss": 6.2456,
|
|
"mean_token_accuracy": 0.12712132856249808,
|
|
"num_tokens": 1464556.0,
|
|
"step": 800
|
|
},
|
|
{
|
|
"entropy": 6.697847175598144,
|
|
"epoch": 0.06724022719679251,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000402,
|
|
"loss": 6.3663,
|
|
"mean_token_accuracy": 0.12254888191819191,
|
|
"num_tokens": 1473617.0,
|
|
"step": 805
|
|
},
|
|
{
|
|
"entropy": 6.679299306869507,
|
|
"epoch": 0.06765786835950552,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004045,
|
|
"loss": 6.3852,
|
|
"mean_token_accuracy": 0.12291230112314225,
|
|
"num_tokens": 1483006.0,
|
|
"step": 810
|
|
},
|
|
{
|
|
"entropy": 6.704338502883911,
|
|
"epoch": 0.06807550952221851,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00040699999999999997,
|
|
"loss": 6.4006,
|
|
"mean_token_accuracy": 0.12003520801663399,
|
|
"num_tokens": 1493009.0,
|
|
"step": 815
|
|
},
|
|
{
|
|
"entropy": 6.579654169082642,
|
|
"epoch": 0.0684931506849315,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004095,
|
|
"loss": 6.2912,
|
|
"mean_token_accuracy": 0.12424400523304939,
|
|
"num_tokens": 1501261.0,
|
|
"step": 820
|
|
},
|
|
{
|
|
"entropy": 6.61363673210144,
|
|
"epoch": 0.06891079184764451,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.000412,
|
|
"loss": 6.394,
|
|
"mean_token_accuracy": 0.11899233609437943,
|
|
"num_tokens": 1511623.0,
|
|
"step": 825
|
|
},
|
|
{
|
|
"entropy": 6.693784141540528,
|
|
"epoch": 0.0693284330103575,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004145,
|
|
"loss": 6.3861,
|
|
"mean_token_accuracy": 0.11563008949160576,
|
|
"num_tokens": 1521741.0,
|
|
"step": 830
|
|
},
|
|
{
|
|
"entropy": 6.616790151596069,
|
|
"epoch": 0.0697460741730705,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000417,
|
|
"loss": 6.3195,
|
|
"mean_token_accuracy": 0.12150524035096169,
|
|
"num_tokens": 1530988.0,
|
|
"step": 835
|
|
},
|
|
{
|
|
"entropy": 6.543398427963257,
|
|
"epoch": 0.0701637153357835,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004195,
|
|
"loss": 6.158,
|
|
"mean_token_accuracy": 0.12872020676732063,
|
|
"num_tokens": 1539415.0,
|
|
"step": 840
|
|
},
|
|
{
|
|
"entropy": 6.674872541427613,
|
|
"epoch": 0.07058135649849649,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000422,
|
|
"loss": 6.3627,
|
|
"mean_token_accuracy": 0.1207451082766056,
|
|
"num_tokens": 1547969.0,
|
|
"step": 845
|
|
},
|
|
{
|
|
"entropy": 6.544791841506958,
|
|
"epoch": 0.07099899766120948,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004245,
|
|
"loss": 6.2083,
|
|
"mean_token_accuracy": 0.12395204156637192,
|
|
"num_tokens": 1557526.0,
|
|
"step": 850
|
|
},
|
|
{
|
|
"entropy": 6.56576452255249,
|
|
"epoch": 0.07141663882392249,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000427,
|
|
"loss": 6.1961,
|
|
"mean_token_accuracy": 0.12846603170037268,
|
|
"num_tokens": 1565982.0,
|
|
"step": 855
|
|
},
|
|
{
|
|
"entropy": 6.504228305816651,
|
|
"epoch": 0.07183427998663548,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004295,
|
|
"loss": 6.2432,
|
|
"mean_token_accuracy": 0.13052212223410606,
|
|
"num_tokens": 1574492.0,
|
|
"step": 860
|
|
},
|
|
{
|
|
"entropy": 6.504011058807373,
|
|
"epoch": 0.07225192114934847,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000432,
|
|
"loss": 6.2186,
|
|
"mean_token_accuracy": 0.1255444750189781,
|
|
"num_tokens": 1583726.0,
|
|
"step": 865
|
|
},
|
|
{
|
|
"entropy": 6.531704616546631,
|
|
"epoch": 0.07266956231206148,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004345,
|
|
"loss": 6.2342,
|
|
"mean_token_accuracy": 0.11796416938304902,
|
|
"num_tokens": 1593780.0,
|
|
"step": 870
|
|
},
|
|
{
|
|
"entropy": 6.550727891921997,
|
|
"epoch": 0.07308720347477447,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000437,
|
|
"loss": 6.2362,
|
|
"mean_token_accuracy": 0.1253882236778736,
|
|
"num_tokens": 1602746.0,
|
|
"step": 875
|
|
},
|
|
{
|
|
"entropy": 6.606376981735229,
|
|
"epoch": 0.07350484463748747,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004395,
|
|
"loss": 6.2635,
|
|
"mean_token_accuracy": 0.12688489481806756,
|
|
"num_tokens": 1611767.0,
|
|
"step": 880
|
|
},
|
|
{
|
|
"entropy": 6.605551767349243,
|
|
"epoch": 0.07392248580020047,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000442,
|
|
"loss": 6.335,
|
|
"mean_token_accuracy": 0.12890502512454988,
|
|
"num_tokens": 1621568.0,
|
|
"step": 885
|
|
},
|
|
{
|
|
"entropy": 6.594180345535278,
|
|
"epoch": 0.07434012696291346,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004445,
|
|
"loss": 6.2961,
|
|
"mean_token_accuracy": 0.13042845353484153,
|
|
"num_tokens": 1630650.0,
|
|
"step": 890
|
|
},
|
|
{
|
|
"entropy": 6.582787275314331,
|
|
"epoch": 0.07475776812562646,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000447,
|
|
"loss": 6.2881,
|
|
"mean_token_accuracy": 0.12370246201753617,
|
|
"num_tokens": 1640482.0,
|
|
"step": 895
|
|
},
|
|
{
|
|
"entropy": 6.651394557952881,
|
|
"epoch": 0.07517540928833946,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00044950000000000003,
|
|
"loss": 6.3247,
|
|
"mean_token_accuracy": 0.12517691105604173,
|
|
"num_tokens": 1649344.0,
|
|
"step": 900
|
|
},
|
|
{
|
|
"entropy": 6.495271348953247,
|
|
"epoch": 0.07559305045105245,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00045200000000000004,
|
|
"loss": 6.2618,
|
|
"mean_token_accuracy": 0.12706776037812234,
|
|
"num_tokens": 1658962.0,
|
|
"step": 905
|
|
},
|
|
{
|
|
"entropy": 6.504554367065429,
|
|
"epoch": 0.07601069161376545,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00045450000000000004,
|
|
"loss": 6.266,
|
|
"mean_token_accuracy": 0.12863868474960327,
|
|
"num_tokens": 1668615.0,
|
|
"step": 910
|
|
},
|
|
{
|
|
"entropy": 6.574895524978638,
|
|
"epoch": 0.07642833277647845,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00045700000000000005,
|
|
"loss": 6.2168,
|
|
"mean_token_accuracy": 0.12925311848521231,
|
|
"num_tokens": 1679282.0,
|
|
"step": 915
|
|
},
|
|
{
|
|
"entropy": 6.466578817367553,
|
|
"epoch": 0.07684597393919144,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00045950000000000006,
|
|
"loss": 6.3065,
|
|
"mean_token_accuracy": 0.1251588962972164,
|
|
"num_tokens": 1688362.0,
|
|
"step": 920
|
|
},
|
|
{
|
|
"entropy": 6.553056955337524,
|
|
"epoch": 0.07726361510190444,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.000462,
|
|
"loss": 6.1887,
|
|
"mean_token_accuracy": 0.12379047647118568,
|
|
"num_tokens": 1697593.0,
|
|
"step": 925
|
|
},
|
|
{
|
|
"entropy": 6.501152229309082,
|
|
"epoch": 0.07768125626461744,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004645,
|
|
"loss": 6.2696,
|
|
"mean_token_accuracy": 0.1266642227768898,
|
|
"num_tokens": 1706961.0,
|
|
"step": 930
|
|
},
|
|
{
|
|
"entropy": 6.591590833663941,
|
|
"epoch": 0.07809889742733044,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000467,
|
|
"loss": 6.3029,
|
|
"mean_token_accuracy": 0.12989042624831199,
|
|
"num_tokens": 1716222.0,
|
|
"step": 935
|
|
},
|
|
{
|
|
"entropy": 6.465153598785401,
|
|
"epoch": 0.07851653859004344,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004695,
|
|
"loss": 6.1681,
|
|
"mean_token_accuracy": 0.12083110958337784,
|
|
"num_tokens": 1726750.0,
|
|
"step": 940
|
|
},
|
|
{
|
|
"entropy": 6.532292890548706,
|
|
"epoch": 0.07893417975275643,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000472,
|
|
"loss": 6.281,
|
|
"mean_token_accuracy": 0.11997251808643342,
|
|
"num_tokens": 1736262.0,
|
|
"step": 945
|
|
},
|
|
{
|
|
"entropy": 6.490269708633423,
|
|
"epoch": 0.07935182091546943,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004745,
|
|
"loss": 6.2976,
|
|
"mean_token_accuracy": 0.12622648924589158,
|
|
"num_tokens": 1745555.0,
|
|
"step": 950
|
|
},
|
|
{
|
|
"entropy": 6.346992015838623,
|
|
"epoch": 0.07976946207818243,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.000477,
|
|
"loss": 6.1624,
|
|
"mean_token_accuracy": 0.12778715938329696,
|
|
"num_tokens": 1754107.0,
|
|
"step": 955
|
|
},
|
|
{
|
|
"entropy": 6.720982551574707,
|
|
"epoch": 0.08018710324089542,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004795,
|
|
"loss": 6.3498,
|
|
"mean_token_accuracy": 0.12380973473191262,
|
|
"num_tokens": 1762982.0,
|
|
"step": 960
|
|
},
|
|
{
|
|
"entropy": 6.400809383392334,
|
|
"epoch": 0.08060474440360842,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000482,
|
|
"loss": 6.2299,
|
|
"mean_token_accuracy": 0.12820469886064528,
|
|
"num_tokens": 1772545.0,
|
|
"step": 965
|
|
},
|
|
{
|
|
"entropy": 6.63186354637146,
|
|
"epoch": 0.08102238556632142,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004845,
|
|
"loss": 6.3614,
|
|
"mean_token_accuracy": 0.1199867382645607,
|
|
"num_tokens": 1782052.0,
|
|
"step": 970
|
|
},
|
|
{
|
|
"entropy": 6.447825527191162,
|
|
"epoch": 0.08144002672903441,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000487,
|
|
"loss": 6.1631,
|
|
"mean_token_accuracy": 0.12513367608189582,
|
|
"num_tokens": 1791682.0,
|
|
"step": 975
|
|
},
|
|
{
|
|
"entropy": 6.466085052490234,
|
|
"epoch": 0.08185766789174741,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004895,
|
|
"loss": 6.1682,
|
|
"mean_token_accuracy": 0.1323828585445881,
|
|
"num_tokens": 1800526.0,
|
|
"step": 980
|
|
},
|
|
{
|
|
"entropy": 6.538319540023804,
|
|
"epoch": 0.08227530905446041,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000492,
|
|
"loss": 6.2922,
|
|
"mean_token_accuracy": 0.1273337259888649,
|
|
"num_tokens": 1810062.0,
|
|
"step": 985
|
|
},
|
|
{
|
|
"entropy": 6.485649347305298,
|
|
"epoch": 0.0826929502171734,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004945,
|
|
"loss": 6.2886,
|
|
"mean_token_accuracy": 0.12735243514180183,
|
|
"num_tokens": 1818909.0,
|
|
"step": 990
|
|
},
|
|
{
|
|
"entropy": 6.511818504333496,
|
|
"epoch": 0.0831105913798864,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000497,
|
|
"loss": 6.2268,
|
|
"mean_token_accuracy": 0.1313578575849533,
|
|
"num_tokens": 1827978.0,
|
|
"step": 995
|
|
},
|
|
{
|
|
"entropy": 6.385158729553223,
|
|
"epoch": 0.0835282325425994,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004995,
|
|
"loss": 6.1962,
|
|
"mean_token_accuracy": 0.13243770301342012,
|
|
"num_tokens": 1837955.0,
|
|
"step": 1000
|
|
},
|
|
{
|
|
"entropy": 6.5512267589569095,
|
|
"epoch": 0.0839458737053124,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004999999987395534,
|
|
"loss": 6.2897,
|
|
"mean_token_accuracy": 0.1274054653942585,
|
|
"num_tokens": 1847699.0,
|
|
"step": 1005
|
|
},
|
|
{
|
|
"entropy": 6.498107290267944,
|
|
"epoch": 0.08436351486802539,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999999936189888,
|
|
"loss": 6.2363,
|
|
"mean_token_accuracy": 0.12386318743228912,
|
|
"num_tokens": 1856490.0,
|
|
"step": 1010
|
|
},
|
|
{
|
|
"entropy": 6.442971467971802,
|
|
"epoch": 0.0847811560307384,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999999845595285,
|
|
"loss": 6.2339,
|
|
"mean_token_accuracy": 0.1264282323420048,
|
|
"num_tokens": 1865644.0,
|
|
"step": 1015
|
|
},
|
|
{
|
|
"entropy": 6.474472713470459,
|
|
"epoch": 0.08519879719345139,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004999999715611727,
|
|
"loss": 6.1668,
|
|
"mean_token_accuracy": 0.1318289414048195,
|
|
"num_tokens": 1874450.0,
|
|
"step": 1020
|
|
},
|
|
{
|
|
"entropy": 6.359386444091797,
|
|
"epoch": 0.08561643835616438,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999999546239215,
|
|
"loss": 6.1867,
|
|
"mean_token_accuracy": 0.12795957028865815,
|
|
"num_tokens": 1883259.0,
|
|
"step": 1025
|
|
},
|
|
{
|
|
"entropy": 6.465229320526123,
|
|
"epoch": 0.08603407951887738,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004999999337477753,
|
|
"loss": 6.2646,
|
|
"mean_token_accuracy": 0.12190999686717988,
|
|
"num_tokens": 1891897.0,
|
|
"step": 1030
|
|
},
|
|
{
|
|
"entropy": 6.531569147109986,
|
|
"epoch": 0.08645172068159038,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004999999089327344,
|
|
"loss": 6.2369,
|
|
"mean_token_accuracy": 0.1253485880792141,
|
|
"num_tokens": 1901011.0,
|
|
"step": 1035
|
|
},
|
|
{
|
|
"entropy": 6.3279060363769535,
|
|
"epoch": 0.08686936184430337,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999998801787993,
|
|
"loss": 6.1475,
|
|
"mean_token_accuracy": 0.1359507881104946,
|
|
"num_tokens": 1910132.0,
|
|
"step": 1040
|
|
},
|
|
{
|
|
"entropy": 6.536592149734497,
|
|
"epoch": 0.08728700300701638,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999998474859704,
|
|
"loss": 6.2593,
|
|
"mean_token_accuracy": 0.12965355440974236,
|
|
"num_tokens": 1919938.0,
|
|
"step": 1045
|
|
},
|
|
{
|
|
"entropy": 6.347357130050659,
|
|
"epoch": 0.08770464416972937,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999998108542483,
|
|
"loss": 6.1286,
|
|
"mean_token_accuracy": 0.1264238215982914,
|
|
"num_tokens": 1928199.0,
|
|
"step": 1050
|
|
},
|
|
{
|
|
"entropy": 6.376512479782105,
|
|
"epoch": 0.08812228533244236,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004999997702836339,
|
|
"loss": 6.1175,
|
|
"mean_token_accuracy": 0.13022146746516228,
|
|
"num_tokens": 1937133.0,
|
|
"step": 1055
|
|
},
|
|
{
|
|
"entropy": 6.513174438476563,
|
|
"epoch": 0.08853992649515537,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999997257741274,
|
|
"loss": 6.2975,
|
|
"mean_token_accuracy": 0.1291216015815735,
|
|
"num_tokens": 1946580.0,
|
|
"step": 1060
|
|
},
|
|
{
|
|
"entropy": 6.365123176574707,
|
|
"epoch": 0.08895756765786836,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00049999967732573,
|
|
"loss": 6.2097,
|
|
"mean_token_accuracy": 0.12826794609427453,
|
|
"num_tokens": 1955413.0,
|
|
"step": 1065
|
|
},
|
|
{
|
|
"entropy": 6.605544090270996,
|
|
"epoch": 0.08937520882058135,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004999996249384425,
|
|
"loss": 6.2843,
|
|
"mean_token_accuracy": 0.1293049283325672,
|
|
"num_tokens": 1964716.0,
|
|
"step": 1070
|
|
},
|
|
{
|
|
"entropy": 6.295011186599732,
|
|
"epoch": 0.08979284998329436,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999995686122657,
|
|
"loss": 6.143,
|
|
"mean_token_accuracy": 0.1339694581925869,
|
|
"num_tokens": 1974081.0,
|
|
"step": 1075
|
|
},
|
|
{
|
|
"entropy": 6.302339315414429,
|
|
"epoch": 0.09021049114600735,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999995083472006,
|
|
"loss": 6.12,
|
|
"mean_token_accuracy": 0.1303638242185116,
|
|
"num_tokens": 1983035.0,
|
|
"step": 1080
|
|
},
|
|
{
|
|
"entropy": 6.41491436958313,
|
|
"epoch": 0.09062813230872034,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004999994441432481,
|
|
"loss": 6.1119,
|
|
"mean_token_accuracy": 0.14117980897426605,
|
|
"num_tokens": 1992475.0,
|
|
"step": 1085
|
|
},
|
|
{
|
|
"entropy": 6.36792368888855,
|
|
"epoch": 0.09104577347143335,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999993760004097,
|
|
"loss": 6.1813,
|
|
"mean_token_accuracy": 0.12746159359812737,
|
|
"num_tokens": 2002729.0,
|
|
"step": 1090
|
|
},
|
|
{
|
|
"entropy": 6.294451570510864,
|
|
"epoch": 0.09146341463414634,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999993039186864,
|
|
"loss": 6.0415,
|
|
"mean_token_accuracy": 0.13401369303464888,
|
|
"num_tokens": 2011319.0,
|
|
"step": 1095
|
|
},
|
|
{
|
|
"entropy": 6.397387838363647,
|
|
"epoch": 0.09188105579685933,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999992278980794,
|
|
"loss": 6.095,
|
|
"mean_token_accuracy": 0.1325186774134636,
|
|
"num_tokens": 2020456.0,
|
|
"step": 1100
|
|
},
|
|
{
|
|
"entropy": 6.282045221328735,
|
|
"epoch": 0.09229869695957234,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004999991479385901,
|
|
"loss": 6.1684,
|
|
"mean_token_accuracy": 0.1352491483092308,
|
|
"num_tokens": 2029417.0,
|
|
"step": 1105
|
|
},
|
|
{
|
|
"entropy": 6.475615835189819,
|
|
"epoch": 0.09271633812228533,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999990640402198,
|
|
"loss": 6.2484,
|
|
"mean_token_accuracy": 0.13222716152668,
|
|
"num_tokens": 2039290.0,
|
|
"step": 1110
|
|
},
|
|
{
|
|
"entropy": 6.398699712753296,
|
|
"epoch": 0.09313397928499834,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004999989762029701,
|
|
"loss": 6.0758,
|
|
"mean_token_accuracy": 0.13428714573383332,
|
|
"num_tokens": 2048485.0,
|
|
"step": 1115
|
|
},
|
|
{
|
|
"entropy": 6.212140274047852,
|
|
"epoch": 0.09355162044771133,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999988844268425,
|
|
"loss": 6.0653,
|
|
"mean_token_accuracy": 0.13647278472781182,
|
|
"num_tokens": 2057131.0,
|
|
"step": 1120
|
|
},
|
|
{
|
|
"entropy": 6.3156208992004395,
|
|
"epoch": 0.09396926161042432,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999987887118387,
|
|
"loss": 6.0425,
|
|
"mean_token_accuracy": 0.13471427783370019,
|
|
"num_tokens": 2066295.0,
|
|
"step": 1125
|
|
},
|
|
{
|
|
"entropy": 6.2854846000671385,
|
|
"epoch": 0.09438690277313733,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999986890579602,
|
|
"loss": 6.0529,
|
|
"mean_token_accuracy": 0.13778177052736282,
|
|
"num_tokens": 2075656.0,
|
|
"step": 1130
|
|
},
|
|
{
|
|
"entropy": 6.30756311416626,
|
|
"epoch": 0.09480454393585032,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999985854652087,
|
|
"loss": 6.1868,
|
|
"mean_token_accuracy": 0.12809674441814423,
|
|
"num_tokens": 2086046.0,
|
|
"step": 1135
|
|
},
|
|
{
|
|
"entropy": 6.448493432998657,
|
|
"epoch": 0.09522218509856331,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999984779335862,
|
|
"loss": 6.1931,
|
|
"mean_token_accuracy": 0.1333407126367092,
|
|
"num_tokens": 2094808.0,
|
|
"step": 1140
|
|
},
|
|
{
|
|
"entropy": 6.262913179397583,
|
|
"epoch": 0.09563982626127632,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999983664630945,
|
|
"loss": 6.13,
|
|
"mean_token_accuracy": 0.13531602770090104,
|
|
"num_tokens": 2104155.0,
|
|
"step": 1145
|
|
},
|
|
{
|
|
"entropy": 6.3961437225341795,
|
|
"epoch": 0.09605746742398931,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999982510537357,
|
|
"loss": 6.031,
|
|
"mean_token_accuracy": 0.13656094148755074,
|
|
"num_tokens": 2112517.0,
|
|
"step": 1150
|
|
},
|
|
{
|
|
"entropy": 6.132482528686523,
|
|
"epoch": 0.0964751085867023,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999981317055116,
|
|
"loss": 5.9808,
|
|
"mean_token_accuracy": 0.1375528834760189,
|
|
"num_tokens": 2121355.0,
|
|
"step": 1155
|
|
},
|
|
{
|
|
"entropy": 6.379729604721069,
|
|
"epoch": 0.09689274974941531,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004999980084184244,
|
|
"loss": 6.1163,
|
|
"mean_token_accuracy": 0.1360280379652977,
|
|
"num_tokens": 2129278.0,
|
|
"step": 1160
|
|
},
|
|
{
|
|
"entropy": 6.3625894546508786,
|
|
"epoch": 0.0973103909121283,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999978811924762,
|
|
"loss": 6.2693,
|
|
"mean_token_accuracy": 0.12732002511620522,
|
|
"num_tokens": 2139548.0,
|
|
"step": 1165
|
|
},
|
|
{
|
|
"entropy": 6.331307220458984,
|
|
"epoch": 0.09772803207484129,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999977500276693,
|
|
"loss": 6.1653,
|
|
"mean_token_accuracy": 0.13200777843594552,
|
|
"num_tokens": 2148765.0,
|
|
"step": 1170
|
|
},
|
|
{
|
|
"entropy": 6.388595914840698,
|
|
"epoch": 0.0981456732375543,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004999976149240058,
|
|
"loss": 6.0868,
|
|
"mean_token_accuracy": 0.14182495772838594,
|
|
"num_tokens": 2157482.0,
|
|
"step": 1175
|
|
},
|
|
{
|
|
"entropy": 6.323437643051148,
|
|
"epoch": 0.09856331440026729,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999974758814884,
|
|
"loss": 6.1771,
|
|
"mean_token_accuracy": 0.13111152350902558,
|
|
"num_tokens": 2167320.0,
|
|
"step": 1180
|
|
},
|
|
{
|
|
"entropy": 6.291384696960449,
|
|
"epoch": 0.09898095556298028,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999973329001193,
|
|
"loss": 6.1273,
|
|
"mean_token_accuracy": 0.13208657130599022,
|
|
"num_tokens": 2175454.0,
|
|
"step": 1185
|
|
},
|
|
{
|
|
"entropy": 6.33533353805542,
|
|
"epoch": 0.09939859672569329,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999971859799009,
|
|
"loss": 6.0659,
|
|
"mean_token_accuracy": 0.13413866832852364,
|
|
"num_tokens": 2184391.0,
|
|
"step": 1190
|
|
},
|
|
{
|
|
"entropy": 6.168669271469116,
|
|
"epoch": 0.09981623788840628,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999970351208361,
|
|
"loss": 5.9572,
|
|
"mean_token_accuracy": 0.1385273478925228,
|
|
"num_tokens": 2193309.0,
|
|
"step": 1195
|
|
},
|
|
{
|
|
"entropy": 6.358164358139038,
|
|
"epoch": 0.10023387905111927,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999968803229275,
|
|
"loss": 6.101,
|
|
"mean_token_accuracy": 0.12906384244561195,
|
|
"num_tokens": 2202057.0,
|
|
"step": 1200
|
|
},
|
|
{
|
|
"entropy": 6.238880729675293,
|
|
"epoch": 0.10065152021383228,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999967215861775,
|
|
"loss": 6.1872,
|
|
"mean_token_accuracy": 0.12864621803164483,
|
|
"num_tokens": 2212384.0,
|
|
"step": 1205
|
|
},
|
|
{
|
|
"entropy": 6.409511709213257,
|
|
"epoch": 0.10106916137654527,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000499996558910589,
|
|
"loss": 6.1065,
|
|
"mean_token_accuracy": 0.13120872378349305,
|
|
"num_tokens": 2221451.0,
|
|
"step": 1210
|
|
},
|
|
{
|
|
"entropy": 6.193742275238037,
|
|
"epoch": 0.10148680253925826,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000499996392296165,
|
|
"loss": 5.9994,
|
|
"mean_token_accuracy": 0.13083511367440223,
|
|
"num_tokens": 2230440.0,
|
|
"step": 1215
|
|
},
|
|
{
|
|
"entropy": 6.30219783782959,
|
|
"epoch": 0.10190444370197127,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999962217429083,
|
|
"loss": 6.1816,
|
|
"mean_token_accuracy": 0.12673772796988486,
|
|
"num_tokens": 2239985.0,
|
|
"step": 1220
|
|
},
|
|
{
|
|
"entropy": 6.273440933227539,
|
|
"epoch": 0.10232208486468426,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999960472508219,
|
|
"loss": 6.0561,
|
|
"mean_token_accuracy": 0.13513024523854256,
|
|
"num_tokens": 2250391.0,
|
|
"step": 1225
|
|
},
|
|
{
|
|
"entropy": 6.387974548339844,
|
|
"epoch": 0.10273972602739725,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000499995868819909,
|
|
"loss": 6.156,
|
|
"mean_token_accuracy": 0.13272497951984405,
|
|
"num_tokens": 2260620.0,
|
|
"step": 1230
|
|
},
|
|
{
|
|
"entropy": 6.299834966659546,
|
|
"epoch": 0.10315736719011026,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999956864501725,
|
|
"loss": 6.1095,
|
|
"mean_token_accuracy": 0.13380565866827965,
|
|
"num_tokens": 2271176.0,
|
|
"step": 1235
|
|
},
|
|
{
|
|
"entropy": 6.320106744766235,
|
|
"epoch": 0.10357500835282325,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999955001416156,
|
|
"loss": 6.0269,
|
|
"mean_token_accuracy": 0.14122135639190675,
|
|
"num_tokens": 2280371.0,
|
|
"step": 1240
|
|
},
|
|
{
|
|
"entropy": 6.157405948638916,
|
|
"epoch": 0.10399264951553625,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999953098942417,
|
|
"loss": 5.9988,
|
|
"mean_token_accuracy": 0.13865399062633516,
|
|
"num_tokens": 2289015.0,
|
|
"step": 1245
|
|
},
|
|
{
|
|
"entropy": 6.223317098617554,
|
|
"epoch": 0.10441029067824925,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004999951157080541,
|
|
"loss": 6.0702,
|
|
"mean_token_accuracy": 0.13662980124354362,
|
|
"num_tokens": 2297409.0,
|
|
"step": 1250
|
|
},
|
|
{
|
|
"entropy": 6.225243949890137,
|
|
"epoch": 0.10482793184096224,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999949175830561,
|
|
"loss": 6.0985,
|
|
"mean_token_accuracy": 0.1335413746535778,
|
|
"num_tokens": 2307017.0,
|
|
"step": 1255
|
|
},
|
|
{
|
|
"entropy": 6.245915412902832,
|
|
"epoch": 0.10524557300367524,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999947155192514,
|
|
"loss": 5.9299,
|
|
"mean_token_accuracy": 0.14725383818149568,
|
|
"num_tokens": 2316014.0,
|
|
"step": 1260
|
|
},
|
|
{
|
|
"entropy": 6.294537830352783,
|
|
"epoch": 0.10566321416638824,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999945095166433,
|
|
"loss": 6.0469,
|
|
"mean_token_accuracy": 0.13486992120742797,
|
|
"num_tokens": 2326326.0,
|
|
"step": 1265
|
|
},
|
|
{
|
|
"entropy": 6.358298969268799,
|
|
"epoch": 0.10608085532910123,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004999942995752354,
|
|
"loss": 6.1415,
|
|
"mean_token_accuracy": 0.13432925343513488,
|
|
"num_tokens": 2335108.0,
|
|
"step": 1270
|
|
},
|
|
{
|
|
"entropy": 6.230367851257324,
|
|
"epoch": 0.10649849649181423,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999940856950315,
|
|
"loss": 6.0451,
|
|
"mean_token_accuracy": 0.14503730461001396,
|
|
"num_tokens": 2343971.0,
|
|
"step": 1275
|
|
},
|
|
{
|
|
"entropy": 6.33094162940979,
|
|
"epoch": 0.10691613765452723,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999938678760354,
|
|
"loss": 6.1053,
|
|
"mean_token_accuracy": 0.13394634500145913,
|
|
"num_tokens": 2353742.0,
|
|
"step": 1280
|
|
},
|
|
{
|
|
"entropy": 6.234221363067627,
|
|
"epoch": 0.10733377881724022,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999936461182507,
|
|
"loss": 6.0561,
|
|
"mean_token_accuracy": 0.13966468647122382,
|
|
"num_tokens": 2363629.0,
|
|
"step": 1285
|
|
},
|
|
{
|
|
"entropy": 6.106270885467529,
|
|
"epoch": 0.10775141997995323,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999934204216814,
|
|
"loss": 5.913,
|
|
"mean_token_accuracy": 0.14157691672444345,
|
|
"num_tokens": 2372705.0,
|
|
"step": 1290
|
|
},
|
|
{
|
|
"entropy": 6.213513946533203,
|
|
"epoch": 0.10816906114266622,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999931907863315,
|
|
"loss": 6.0353,
|
|
"mean_token_accuracy": 0.13727413564920427,
|
|
"num_tokens": 2382136.0,
|
|
"step": 1295
|
|
},
|
|
{
|
|
"entropy": 6.133555603027344,
|
|
"epoch": 0.10858670230537922,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000499992957212205,
|
|
"loss": 6.0034,
|
|
"mean_token_accuracy": 0.13713872507214547,
|
|
"num_tokens": 2391060.0,
|
|
"step": 1300
|
|
},
|
|
{
|
|
"entropy": 6.358161687850952,
|
|
"epoch": 0.10900434346809222,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999927196993059,
|
|
"loss": 6.1334,
|
|
"mean_token_accuracy": 0.13744667619466783,
|
|
"num_tokens": 2399885.0,
|
|
"step": 1305
|
|
},
|
|
{
|
|
"entropy": 6.278725337982178,
|
|
"epoch": 0.10942198463080521,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999924782476384,
|
|
"loss": 6.0035,
|
|
"mean_token_accuracy": 0.14220317751169204,
|
|
"num_tokens": 2409654.0,
|
|
"step": 1310
|
|
},
|
|
{
|
|
"entropy": 6.199410915374756,
|
|
"epoch": 0.1098396257935182,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999922328572068,
|
|
"loss": 6.0624,
|
|
"mean_token_accuracy": 0.13762215226888658,
|
|
"num_tokens": 2419342.0,
|
|
"step": 1315
|
|
},
|
|
{
|
|
"entropy": 6.141462421417236,
|
|
"epoch": 0.11025726695623121,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999919835280154,
|
|
"loss": 5.9506,
|
|
"mean_token_accuracy": 0.1402168832719326,
|
|
"num_tokens": 2428845.0,
|
|
"step": 1320
|
|
},
|
|
{
|
|
"entropy": 6.255073547363281,
|
|
"epoch": 0.1106749081189442,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999917302600684,
|
|
"loss": 5.9557,
|
|
"mean_token_accuracy": 0.14843129366636276,
|
|
"num_tokens": 2437134.0,
|
|
"step": 1325
|
|
},
|
|
{
|
|
"entropy": 6.033188390731811,
|
|
"epoch": 0.1110925492816572,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999914730533704,
|
|
"loss": 5.7955,
|
|
"mean_token_accuracy": 0.1502596452832222,
|
|
"num_tokens": 2445438.0,
|
|
"step": 1330
|
|
},
|
|
{
|
|
"entropy": 6.2179426670074465,
|
|
"epoch": 0.1115101904443702,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999912119079258,
|
|
"loss": 6.1172,
|
|
"mean_token_accuracy": 0.13575662672519684,
|
|
"num_tokens": 2455039.0,
|
|
"step": 1335
|
|
},
|
|
{
|
|
"entropy": 6.263426494598389,
|
|
"epoch": 0.1119278316070832,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999909468237393,
|
|
"loss": 6.0483,
|
|
"mean_token_accuracy": 0.13733413219451904,
|
|
"num_tokens": 2465170.0,
|
|
"step": 1340
|
|
},
|
|
{
|
|
"entropy": 6.09090895652771,
|
|
"epoch": 0.11234547276979619,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999906778008153,
|
|
"loss": 5.8012,
|
|
"mean_token_accuracy": 0.151080884039402,
|
|
"num_tokens": 2473688.0,
|
|
"step": 1345
|
|
},
|
|
{
|
|
"entropy": 6.165483570098877,
|
|
"epoch": 0.11276311393250919,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999904048391588,
|
|
"loss": 6.0541,
|
|
"mean_token_accuracy": 0.14202144667506217,
|
|
"num_tokens": 2482335.0,
|
|
"step": 1350
|
|
},
|
|
{
|
|
"entropy": 6.1746495246887205,
|
|
"epoch": 0.11318075509522219,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999901279387743,
|
|
"loss": 6.0017,
|
|
"mean_token_accuracy": 0.14338096156716346,
|
|
"num_tokens": 2491808.0,
|
|
"step": 1355
|
|
},
|
|
{
|
|
"entropy": 6.3466249942779545,
|
|
"epoch": 0.11359839625793518,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999898470996669,
|
|
"loss": 6.13,
|
|
"mean_token_accuracy": 0.13258725851774217,
|
|
"num_tokens": 2501422.0,
|
|
"step": 1360
|
|
},
|
|
{
|
|
"entropy": 6.159154224395752,
|
|
"epoch": 0.11401603742064818,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004999895623218415,
|
|
"loss": 5.9181,
|
|
"mean_token_accuracy": 0.14280597865581512,
|
|
"num_tokens": 2511201.0,
|
|
"step": 1365
|
|
},
|
|
{
|
|
"entropy": 6.199628210067749,
|
|
"epoch": 0.11443367858336118,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999892736053027,
|
|
"loss": 5.9659,
|
|
"mean_token_accuracy": 0.13438230976462365,
|
|
"num_tokens": 2519798.0,
|
|
"step": 1370
|
|
},
|
|
{
|
|
"entropy": 6.113333225250244,
|
|
"epoch": 0.11485131974607417,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999889809500561,
|
|
"loss": 5.9528,
|
|
"mean_token_accuracy": 0.14371661543846131,
|
|
"num_tokens": 2529177.0,
|
|
"step": 1375
|
|
},
|
|
{
|
|
"entropy": 6.27652678489685,
|
|
"epoch": 0.11526896090878717,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999886843561065,
|
|
"loss": 5.9321,
|
|
"mean_token_accuracy": 0.14615674763917924,
|
|
"num_tokens": 2537571.0,
|
|
"step": 1380
|
|
},
|
|
{
|
|
"entropy": 6.031244230270386,
|
|
"epoch": 0.11568660207150017,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999883838234592,
|
|
"loss": 5.8548,
|
|
"mean_token_accuracy": 0.14628306329250335,
|
|
"num_tokens": 2546258.0,
|
|
"step": 1385
|
|
},
|
|
{
|
|
"entropy": 6.165388917922973,
|
|
"epoch": 0.11610424323421316,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999880793521194,
|
|
"loss": 5.8668,
|
|
"mean_token_accuracy": 0.13787785470485686,
|
|
"num_tokens": 2555862.0,
|
|
"step": 1390
|
|
},
|
|
{
|
|
"entropy": 5.933096837997437,
|
|
"epoch": 0.11652188439692616,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999877709420924,
|
|
"loss": 5.8877,
|
|
"mean_token_accuracy": 0.14672486782073973,
|
|
"num_tokens": 2564583.0,
|
|
"step": 1395
|
|
},
|
|
{
|
|
"entropy": 6.226252937316895,
|
|
"epoch": 0.11693952555963916,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999874585933837,
|
|
"loss": 5.984,
|
|
"mean_token_accuracy": 0.1394071787595749,
|
|
"num_tokens": 2574217.0,
|
|
"step": 1400
|
|
},
|
|
{
|
|
"entropy": 6.08908052444458,
|
|
"epoch": 0.11735716672235215,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999871423059987,
|
|
"loss": 5.8818,
|
|
"mean_token_accuracy": 0.14752811044454575,
|
|
"num_tokens": 2582821.0,
|
|
"step": 1405
|
|
},
|
|
{
|
|
"entropy": 6.154991292953492,
|
|
"epoch": 0.11777480788506516,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000499986822079943,
|
|
"loss": 6.0467,
|
|
"mean_token_accuracy": 0.13607672825455666,
|
|
"num_tokens": 2592748.0,
|
|
"step": 1410
|
|
},
|
|
{
|
|
"entropy": 6.165617561340332,
|
|
"epoch": 0.11819244904777815,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999864979152221,
|
|
"loss": 5.9434,
|
|
"mean_token_accuracy": 0.14729078263044357,
|
|
"num_tokens": 2602053.0,
|
|
"step": 1415
|
|
},
|
|
{
|
|
"entropy": 6.102991533279419,
|
|
"epoch": 0.11861009021049114,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999861698118417,
|
|
"loss": 6.0165,
|
|
"mean_token_accuracy": 0.14120813012123107,
|
|
"num_tokens": 2610557.0,
|
|
"step": 1420
|
|
},
|
|
{
|
|
"entropy": 6.1263680934906,
|
|
"epoch": 0.11902773137320415,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999858377698076,
|
|
"loss": 5.9156,
|
|
"mean_token_accuracy": 0.13886989206075667,
|
|
"num_tokens": 2619628.0,
|
|
"step": 1425
|
|
},
|
|
{
|
|
"entropy": 6.326252508163452,
|
|
"epoch": 0.11944537253591714,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999855017891256,
|
|
"loss": 6.083,
|
|
"mean_token_accuracy": 0.1396564431488514,
|
|
"num_tokens": 2629284.0,
|
|
"step": 1430
|
|
},
|
|
{
|
|
"entropy": 6.109390592575073,
|
|
"epoch": 0.11986301369863013,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999851618698017,
|
|
"loss": 5.9736,
|
|
"mean_token_accuracy": 0.14895331710577012,
|
|
"num_tokens": 2638001.0,
|
|
"step": 1435
|
|
},
|
|
{
|
|
"entropy": 6.114994764328003,
|
|
"epoch": 0.12028065486134314,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999848180118416,
|
|
"loss": 5.9908,
|
|
"mean_token_accuracy": 0.14804767146706582,
|
|
"num_tokens": 2647071.0,
|
|
"step": 1440
|
|
},
|
|
{
|
|
"entropy": 6.187527418136597,
|
|
"epoch": 0.12069829602405613,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999844702152516,
|
|
"loss": 5.9583,
|
|
"mean_token_accuracy": 0.1474977269768715,
|
|
"num_tokens": 2655826.0,
|
|
"step": 1445
|
|
},
|
|
{
|
|
"entropy": 6.12548508644104,
|
|
"epoch": 0.12111593718676913,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999841184800374,
|
|
"loss": 5.8182,
|
|
"mean_token_accuracy": 0.15077890008687972,
|
|
"num_tokens": 2664431.0,
|
|
"step": 1450
|
|
},
|
|
{
|
|
"entropy": 5.976382827758789,
|
|
"epoch": 0.12153357834948213,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999837628062055,
|
|
"loss": 5.7456,
|
|
"mean_token_accuracy": 0.1526419997215271,
|
|
"num_tokens": 2673631.0,
|
|
"step": 1455
|
|
},
|
|
{
|
|
"entropy": 6.0932858943939205,
|
|
"epoch": 0.12195121951219512,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999834031937621,
|
|
"loss": 6.0214,
|
|
"mean_token_accuracy": 0.1415261410176754,
|
|
"num_tokens": 2683363.0,
|
|
"step": 1460
|
|
},
|
|
{
|
|
"entropy": 6.140729188919067,
|
|
"epoch": 0.12236886067490813,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999830396427133,
|
|
"loss": 5.9755,
|
|
"mean_token_accuracy": 0.13880073204636573,
|
|
"num_tokens": 2692533.0,
|
|
"step": 1465
|
|
},
|
|
{
|
|
"entropy": 6.100193119049072,
|
|
"epoch": 0.12278650183762112,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999826721530657,
|
|
"loss": 5.9625,
|
|
"mean_token_accuracy": 0.14861070960760117,
|
|
"num_tokens": 2701211.0,
|
|
"step": 1470
|
|
},
|
|
{
|
|
"entropy": 6.213804006576538,
|
|
"epoch": 0.12320414300033411,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999823007248255,
|
|
"loss": 5.9654,
|
|
"mean_token_accuracy": 0.14508800357580184,
|
|
"num_tokens": 2709543.0,
|
|
"step": 1475
|
|
},
|
|
{
|
|
"entropy": 6.132544040679932,
|
|
"epoch": 0.12362178416304712,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004999819253579992,
|
|
"loss": 5.9665,
|
|
"mean_token_accuracy": 0.14124592989683152,
|
|
"num_tokens": 2718336.0,
|
|
"step": 1480
|
|
},
|
|
{
|
|
"entropy": 6.176914262771606,
|
|
"epoch": 0.12403942532576011,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999815460525938,
|
|
"loss": 5.9221,
|
|
"mean_token_accuracy": 0.14702423065900802,
|
|
"num_tokens": 2726504.0,
|
|
"step": 1485
|
|
},
|
|
{
|
|
"entropy": 6.065746259689331,
|
|
"epoch": 0.1244570664884731,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999811628086155,
|
|
"loss": 5.9256,
|
|
"mean_token_accuracy": 0.14405364468693732,
|
|
"num_tokens": 2736076.0,
|
|
"step": 1490
|
|
},
|
|
{
|
|
"entropy": 6.031908082962036,
|
|
"epoch": 0.1248747076511861,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000499980775626071,
|
|
"loss": 5.8548,
|
|
"mean_token_accuracy": 0.14717004522681237,
|
|
"num_tokens": 2745497.0,
|
|
"step": 1495
|
|
},
|
|
{
|
|
"entropy": 6.086008548736572,
|
|
"epoch": 0.12529234881389908,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004999803845049674,
|
|
"loss": 6.0051,
|
|
"mean_token_accuracy": 0.14198841154575348,
|
|
"num_tokens": 2754455.0,
|
|
"step": 1500
|
|
},
|
|
{
|
|
"entropy": 6.275413751602173,
|
|
"epoch": 0.1257099899766121,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999799894453112,
|
|
"loss": 6.0214,
|
|
"mean_token_accuracy": 0.14551321789622307,
|
|
"num_tokens": 2763603.0,
|
|
"step": 1505
|
|
},
|
|
{
|
|
"entropy": 6.12061562538147,
|
|
"epoch": 0.1261276311393251,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999795904471095,
|
|
"loss": 5.8695,
|
|
"mean_token_accuracy": 0.14632337167859077,
|
|
"num_tokens": 2772152.0,
|
|
"step": 1510
|
|
},
|
|
{
|
|
"entropy": 6.125328063964844,
|
|
"epoch": 0.12654527230203808,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999791875103694,
|
|
"loss": 5.9827,
|
|
"mean_token_accuracy": 0.14955568239092826,
|
|
"num_tokens": 2781459.0,
|
|
"step": 1515
|
|
},
|
|
{
|
|
"entropy": 6.160517978668213,
|
|
"epoch": 0.12696291346475108,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999787806350977,
|
|
"loss": 5.9352,
|
|
"mean_token_accuracy": 0.1438853219151497,
|
|
"num_tokens": 2791177.0,
|
|
"step": 1520
|
|
},
|
|
{
|
|
"entropy": 6.0033468246459964,
|
|
"epoch": 0.1273805546274641,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999783698213016,
|
|
"loss": 5.926,
|
|
"mean_token_accuracy": 0.15096332877874374,
|
|
"num_tokens": 2800543.0,
|
|
"step": 1525
|
|
},
|
|
{
|
|
"entropy": 6.034644699096679,
|
|
"epoch": 0.12779819579017707,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999779550689885,
|
|
"loss": 5.764,
|
|
"mean_token_accuracy": 0.15348498970270158,
|
|
"num_tokens": 2809301.0,
|
|
"step": 1530
|
|
},
|
|
{
|
|
"entropy": 6.169605159759522,
|
|
"epoch": 0.12821583695289007,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999775363781654,
|
|
"loss": 5.9802,
|
|
"mean_token_accuracy": 0.1403758257627487,
|
|
"num_tokens": 2818269.0,
|
|
"step": 1535
|
|
},
|
|
{
|
|
"entropy": 6.0626365661621096,
|
|
"epoch": 0.12863347811560308,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999771137488395,
|
|
"loss": 5.8292,
|
|
"mean_token_accuracy": 0.14809781610965728,
|
|
"num_tokens": 2827170.0,
|
|
"step": 1540
|
|
},
|
|
{
|
|
"entropy": 6.0085289001464846,
|
|
"epoch": 0.12905111927831608,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999766871810188,
|
|
"loss": 5.8354,
|
|
"mean_token_accuracy": 0.15448207408189774,
|
|
"num_tokens": 2835320.0,
|
|
"step": 1545
|
|
},
|
|
{
|
|
"entropy": 6.026972770690918,
|
|
"epoch": 0.12946876044102906,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999762566747101,
|
|
"loss": 5.9073,
|
|
"mean_token_accuracy": 0.14486387148499488,
|
|
"num_tokens": 2843755.0,
|
|
"step": 1550
|
|
},
|
|
{
|
|
"entropy": 6.129249715805054,
|
|
"epoch": 0.12988640160374207,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999758222299214,
|
|
"loss": 5.9413,
|
|
"mean_token_accuracy": 0.14105947464704513,
|
|
"num_tokens": 2853462.0,
|
|
"step": 1555
|
|
},
|
|
{
|
|
"entropy": 6.067689990997314,
|
|
"epoch": 0.13030404276645507,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999753838466601,
|
|
"loss": 5.8489,
|
|
"mean_token_accuracy": 0.14596890062093734,
|
|
"num_tokens": 2863041.0,
|
|
"step": 1560
|
|
},
|
|
{
|
|
"entropy": 6.222100067138672,
|
|
"epoch": 0.13072168392916805,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999749415249338,
|
|
"loss": 6.0523,
|
|
"mean_token_accuracy": 0.14630843549966813,
|
|
"num_tokens": 2873019.0,
|
|
"step": 1565
|
|
},
|
|
{
|
|
"entropy": 6.015613985061646,
|
|
"epoch": 0.13113932509188106,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999744952647505,
|
|
"loss": 5.8065,
|
|
"mean_token_accuracy": 0.1499025270342827,
|
|
"num_tokens": 2881467.0,
|
|
"step": 1570
|
|
},
|
|
{
|
|
"entropy": 6.0279559135437015,
|
|
"epoch": 0.13155696625459407,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999740450661176,
|
|
"loss": 5.8984,
|
|
"mean_token_accuracy": 0.14618548154830932,
|
|
"num_tokens": 2890914.0,
|
|
"step": 1575
|
|
},
|
|
{
|
|
"entropy": 6.068280839920044,
|
|
"epoch": 0.13197460741730704,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999735909290436,
|
|
"loss": 5.8159,
|
|
"mean_token_accuracy": 0.15112878903746604,
|
|
"num_tokens": 2901164.0,
|
|
"step": 1580
|
|
},
|
|
{
|
|
"entropy": 6.036407995223999,
|
|
"epoch": 0.13239224858002005,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999731328535358,
|
|
"loss": 5.9705,
|
|
"mean_token_accuracy": 0.14157942086458206,
|
|
"num_tokens": 2910560.0,
|
|
"step": 1585
|
|
},
|
|
{
|
|
"entropy": 6.0331549644470215,
|
|
"epoch": 0.13280988974273306,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999726708396026,
|
|
"loss": 5.7769,
|
|
"mean_token_accuracy": 0.1490756705403328,
|
|
"num_tokens": 2918980.0,
|
|
"step": 1590
|
|
},
|
|
{
|
|
"entropy": 6.02565450668335,
|
|
"epoch": 0.13322753090544603,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000499972204887252,
|
|
"loss": 5.9787,
|
|
"mean_token_accuracy": 0.1396894186735153,
|
|
"num_tokens": 2929516.0,
|
|
"step": 1595
|
|
},
|
|
{
|
|
"entropy": 6.176361989974976,
|
|
"epoch": 0.13364517206815904,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999717349964922,
|
|
"loss": 6.0518,
|
|
"mean_token_accuracy": 0.1366614058613777,
|
|
"num_tokens": 2940603.0,
|
|
"step": 1600
|
|
},
|
|
{
|
|
"entropy": 6.116162443161011,
|
|
"epoch": 0.13406281323087205,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999712611673313,
|
|
"loss": 5.8945,
|
|
"mean_token_accuracy": 0.14497055262327194,
|
|
"num_tokens": 2950082.0,
|
|
"step": 1605
|
|
},
|
|
{
|
|
"entropy": 5.9512824535369875,
|
|
"epoch": 0.13448045439358502,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999707833997777,
|
|
"loss": 5.7648,
|
|
"mean_token_accuracy": 0.15802783519029617,
|
|
"num_tokens": 2959098.0,
|
|
"step": 1610
|
|
},
|
|
{
|
|
"entropy": 6.146846580505371,
|
|
"epoch": 0.13489809555629803,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999703016938398,
|
|
"loss": 5.9007,
|
|
"mean_token_accuracy": 0.14953137785196305,
|
|
"num_tokens": 2968585.0,
|
|
"step": 1615
|
|
},
|
|
{
|
|
"entropy": 6.060613203048706,
|
|
"epoch": 0.13531573671901104,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000499969816049526,
|
|
"loss": 5.9204,
|
|
"mean_token_accuracy": 0.14645206406712533,
|
|
"num_tokens": 2978430.0,
|
|
"step": 1620
|
|
},
|
|
{
|
|
"entropy": 6.181136131286621,
|
|
"epoch": 0.13573337788172402,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004999693264668446,
|
|
"loss": 5.9891,
|
|
"mean_token_accuracy": 0.1384026862680912,
|
|
"num_tokens": 2988398.0,
|
|
"step": 1625
|
|
},
|
|
{
|
|
"entropy": 6.1024940490722654,
|
|
"epoch": 0.13615101904443702,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004999688329458045,
|
|
"loss": 6.0009,
|
|
"mean_token_accuracy": 0.14288765341043472,
|
|
"num_tokens": 2999255.0,
|
|
"step": 1630
|
|
},
|
|
{
|
|
"entropy": 6.158026123046875,
|
|
"epoch": 0.13656866020715003,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999683354864141,
|
|
"loss": 5.8668,
|
|
"mean_token_accuracy": 0.15016328170895576,
|
|
"num_tokens": 3008638.0,
|
|
"step": 1635
|
|
},
|
|
{
|
|
"entropy": 6.011956262588501,
|
|
"epoch": 0.136986301369863,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999678340886823,
|
|
"loss": 5.8952,
|
|
"mean_token_accuracy": 0.14607993140816689,
|
|
"num_tokens": 3018070.0,
|
|
"step": 1640
|
|
},
|
|
{
|
|
"entropy": 5.984478425979614,
|
|
"epoch": 0.137403942532576,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999673287526176,
|
|
"loss": 5.862,
|
|
"mean_token_accuracy": 0.1520274721086025,
|
|
"num_tokens": 3027878.0,
|
|
"step": 1645
|
|
},
|
|
{
|
|
"entropy": 6.163523769378662,
|
|
"epoch": 0.13782158369528902,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999668194782291,
|
|
"loss": 6.0371,
|
|
"mean_token_accuracy": 0.14080698117613794,
|
|
"num_tokens": 3037031.0,
|
|
"step": 1650
|
|
},
|
|
{
|
|
"entropy": 6.169953918457031,
|
|
"epoch": 0.138239224858002,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999663062655257,
|
|
"loss": 5.9905,
|
|
"mean_token_accuracy": 0.136997552216053,
|
|
"num_tokens": 3046311.0,
|
|
"step": 1655
|
|
},
|
|
{
|
|
"entropy": 6.062465858459473,
|
|
"epoch": 0.138656866020715,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999657891145162,
|
|
"loss": 5.8028,
|
|
"mean_token_accuracy": 0.14837437868118286,
|
|
"num_tokens": 3055108.0,
|
|
"step": 1660
|
|
},
|
|
{
|
|
"entropy": 5.975989055633545,
|
|
"epoch": 0.139074507183428,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999652680252099,
|
|
"loss": 5.829,
|
|
"mean_token_accuracy": 0.15185758844017982,
|
|
"num_tokens": 3063492.0,
|
|
"step": 1665
|
|
},
|
|
{
|
|
"entropy": 6.1554381370544435,
|
|
"epoch": 0.139492148346141,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999647429976157,
|
|
"loss": 5.8732,
|
|
"mean_token_accuracy": 0.152986741065979,
|
|
"num_tokens": 3072572.0,
|
|
"step": 1670
|
|
},
|
|
{
|
|
"entropy": 6.097223615646362,
|
|
"epoch": 0.139909789508854,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004999642140317429,
|
|
"loss": 5.9321,
|
|
"mean_token_accuracy": 0.14403018429875375,
|
|
"num_tokens": 3082942.0,
|
|
"step": 1675
|
|
},
|
|
{
|
|
"entropy": 6.034411334991455,
|
|
"epoch": 0.140327430671567,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999636811276007,
|
|
"loss": 5.8955,
|
|
"mean_token_accuracy": 0.15122605189681054,
|
|
"num_tokens": 3091410.0,
|
|
"step": 1680
|
|
},
|
|
{
|
|
"entropy": 6.105877351760864,
|
|
"epoch": 0.14074507183427998,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999631442851986,
|
|
"loss": 5.9586,
|
|
"mean_token_accuracy": 0.15086555927991868,
|
|
"num_tokens": 3100626.0,
|
|
"step": 1685
|
|
},
|
|
{
|
|
"entropy": 6.044166851043701,
|
|
"epoch": 0.14116271299699298,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999626035045458,
|
|
"loss": 5.7604,
|
|
"mean_token_accuracy": 0.15637173503637314,
|
|
"num_tokens": 3109339.0,
|
|
"step": 1690
|
|
},
|
|
{
|
|
"entropy": 6.087968540191651,
|
|
"epoch": 0.141580354159706,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999620587856519,
|
|
"loss": 5.879,
|
|
"mean_token_accuracy": 0.1442359484732151,
|
|
"num_tokens": 3118636.0,
|
|
"step": 1695
|
|
},
|
|
{
|
|
"entropy": 5.975955629348755,
|
|
"epoch": 0.14199799532241897,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999615101285262,
|
|
"loss": 5.8571,
|
|
"mean_token_accuracy": 0.14512152522802352,
|
|
"num_tokens": 3128162.0,
|
|
"step": 1700
|
|
},
|
|
{
|
|
"entropy": 6.065919256210327,
|
|
"epoch": 0.14241563648513197,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999609575331786,
|
|
"loss": 5.8685,
|
|
"mean_token_accuracy": 0.15015122443437576,
|
|
"num_tokens": 3136451.0,
|
|
"step": 1705
|
|
},
|
|
{
|
|
"entropy": 6.057447052001953,
|
|
"epoch": 0.14283327764784498,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999604009996186,
|
|
"loss": 5.8614,
|
|
"mean_token_accuracy": 0.14777368754148484,
|
|
"num_tokens": 3146599.0,
|
|
"step": 1710
|
|
},
|
|
{
|
|
"entropy": 6.099114274978637,
|
|
"epoch": 0.14325091881055796,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000499959840527856,
|
|
"loss": 5.916,
|
|
"mean_token_accuracy": 0.14324069395661354,
|
|
"num_tokens": 3155941.0,
|
|
"step": 1715
|
|
},
|
|
{
|
|
"entropy": 6.0154510021209715,
|
|
"epoch": 0.14366855997327097,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999592761179007,
|
|
"loss": 5.8388,
|
|
"mean_token_accuracy": 0.15261219143867494,
|
|
"num_tokens": 3164641.0,
|
|
"step": 1720
|
|
},
|
|
{
|
|
"entropy": 6.028367567062378,
|
|
"epoch": 0.14408620113598397,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999587077697624,
|
|
"loss": 5.872,
|
|
"mean_token_accuracy": 0.15229901447892188,
|
|
"num_tokens": 3173701.0,
|
|
"step": 1725
|
|
},
|
|
{
|
|
"entropy": 5.903607177734375,
|
|
"epoch": 0.14450384229869695,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999581354834512,
|
|
"loss": 5.7215,
|
|
"mean_token_accuracy": 0.1503341905772686,
|
|
"num_tokens": 3182268.0,
|
|
"step": 1730
|
|
},
|
|
{
|
|
"entropy": 5.921892786026001,
|
|
"epoch": 0.14492148346140996,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000499957559258977,
|
|
"loss": 5.8109,
|
|
"mean_token_accuracy": 0.153120157122612,
|
|
"num_tokens": 3191513.0,
|
|
"step": 1735
|
|
},
|
|
{
|
|
"entropy": 6.026451969146729,
|
|
"epoch": 0.14533912462412296,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00049995697909635,
|
|
"loss": 5.7633,
|
|
"mean_token_accuracy": 0.15072803422808648,
|
|
"num_tokens": 3200580.0,
|
|
"step": 1740
|
|
},
|
|
{
|
|
"entropy": 5.919099378585815,
|
|
"epoch": 0.14575676578683594,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999563949955803,
|
|
"loss": 5.8504,
|
|
"mean_token_accuracy": 0.15168591886758803,
|
|
"num_tokens": 3209053.0,
|
|
"step": 1745
|
|
},
|
|
{
|
|
"entropy": 6.004643774032592,
|
|
"epoch": 0.14617440694954895,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000499955806956678,
|
|
"loss": 5.8276,
|
|
"mean_token_accuracy": 0.15193051397800444,
|
|
"num_tokens": 3218241.0,
|
|
"step": 1750
|
|
},
|
|
{
|
|
"entropy": 6.114099073410034,
|
|
"epoch": 0.14659204811226195,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004999552149796536,
|
|
"loss": 5.8861,
|
|
"mean_token_accuracy": 0.14796419218182563,
|
|
"num_tokens": 3227887.0,
|
|
"step": 1755
|
|
},
|
|
{
|
|
"entropy": 5.913031387329101,
|
|
"epoch": 0.14700968927497493,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999546190645175,
|
|
"loss": 5.7115,
|
|
"mean_token_accuracy": 0.15936694741249086,
|
|
"num_tokens": 3237281.0,
|
|
"step": 1760
|
|
},
|
|
{
|
|
"entropy": 5.936592626571655,
|
|
"epoch": 0.14742733043768794,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999540192112799,
|
|
"loss": 5.7418,
|
|
"mean_token_accuracy": 0.1534080371260643,
|
|
"num_tokens": 3246907.0,
|
|
"step": 1765
|
|
},
|
|
{
|
|
"entropy": 5.903944110870361,
|
|
"epoch": 0.14784497160040094,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999534154199514,
|
|
"loss": 5.7581,
|
|
"mean_token_accuracy": 0.15006715506315232,
|
|
"num_tokens": 3256312.0,
|
|
"step": 1770
|
|
},
|
|
{
|
|
"entropy": 6.11810793876648,
|
|
"epoch": 0.14826261276311392,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004999528076905426,
|
|
"loss": 5.8535,
|
|
"mean_token_accuracy": 0.15088604092597963,
|
|
"num_tokens": 3265554.0,
|
|
"step": 1775
|
|
},
|
|
{
|
|
"entropy": 5.8378783702850345,
|
|
"epoch": 0.14868025392582693,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999521960230641,
|
|
"loss": 5.6918,
|
|
"mean_token_accuracy": 0.1556992784142494,
|
|
"num_tokens": 3274731.0,
|
|
"step": 1780
|
|
},
|
|
{
|
|
"entropy": 5.91249713897705,
|
|
"epoch": 0.14909789508853993,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999515804175268,
|
|
"loss": 5.8334,
|
|
"mean_token_accuracy": 0.14639962017536162,
|
|
"num_tokens": 3283518.0,
|
|
"step": 1785
|
|
},
|
|
{
|
|
"entropy": 6.047197675704956,
|
|
"epoch": 0.1495155362512529,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.000499950960873941,
|
|
"loss": 5.8387,
|
|
"mean_token_accuracy": 0.15209829434752464,
|
|
"num_tokens": 3292244.0,
|
|
"step": 1790
|
|
},
|
|
{
|
|
"entropy": 5.9918311595916744,
|
|
"epoch": 0.14993317741396592,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999503373923182,
|
|
"loss": 5.8133,
|
|
"mean_token_accuracy": 0.1558985084295273,
|
|
"num_tokens": 3301198.0,
|
|
"step": 1795
|
|
},
|
|
{
|
|
"entropy": 5.999289274215698,
|
|
"epoch": 0.15035081857667892,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999497099726687,
|
|
"loss": 5.7948,
|
|
"mean_token_accuracy": 0.15358459949493408,
|
|
"num_tokens": 3309983.0,
|
|
"step": 1800
|
|
},
|
|
{
|
|
"entropy": 5.985867929458618,
|
|
"epoch": 0.1507684597393919,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004999490786150039,
|
|
"loss": 5.8671,
|
|
"mean_token_accuracy": 0.152096726000309,
|
|
"num_tokens": 3319313.0,
|
|
"step": 1805
|
|
},
|
|
{
|
|
"entropy": 5.97202959060669,
|
|
"epoch": 0.1511861009021049,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999484433193348,
|
|
"loss": 5.7223,
|
|
"mean_token_accuracy": 0.1539360076189041,
|
|
"num_tokens": 3327497.0,
|
|
"step": 1810
|
|
},
|
|
{
|
|
"entropy": 5.8741857528686525,
|
|
"epoch": 0.15160374206481791,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999478040856722,
|
|
"loss": 5.7321,
|
|
"mean_token_accuracy": 0.15889767706394195,
|
|
"num_tokens": 3337029.0,
|
|
"step": 1815
|
|
},
|
|
{
|
|
"entropy": 5.907070827484131,
|
|
"epoch": 0.1520213832275309,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999471609140276,
|
|
"loss": 5.7154,
|
|
"mean_token_accuracy": 0.15107612311840057,
|
|
"num_tokens": 3346243.0,
|
|
"step": 1820
|
|
},
|
|
{
|
|
"entropy": 6.052509498596192,
|
|
"epoch": 0.1524390243902439,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999465138044122,
|
|
"loss": 5.8601,
|
|
"mean_token_accuracy": 0.14963715374469758,
|
|
"num_tokens": 3354846.0,
|
|
"step": 1825
|
|
},
|
|
{
|
|
"entropy": 5.945438528060913,
|
|
"epoch": 0.1528566655529569,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999458627568373,
|
|
"loss": 5.8311,
|
|
"mean_token_accuracy": 0.14300252199172975,
|
|
"num_tokens": 3364683.0,
|
|
"step": 1830
|
|
},
|
|
{
|
|
"entropy": 5.997858572006225,
|
|
"epoch": 0.15327430671566988,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004999452077713144,
|
|
"loss": 5.7828,
|
|
"mean_token_accuracy": 0.1520732045173645,
|
|
"num_tokens": 3374652.0,
|
|
"step": 1835
|
|
},
|
|
{
|
|
"entropy": 5.954912424087524,
|
|
"epoch": 0.1536919478783829,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999445488478547,
|
|
"loss": 5.7793,
|
|
"mean_token_accuracy": 0.1517012432217598,
|
|
"num_tokens": 3384040.0,
|
|
"step": 1840
|
|
},
|
|
{
|
|
"entropy": 5.916548538208008,
|
|
"epoch": 0.1541095890410959,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00049994388598647,
|
|
"loss": 5.8458,
|
|
"mean_token_accuracy": 0.15544982850551606,
|
|
"num_tokens": 3393185.0,
|
|
"step": 1845
|
|
},
|
|
{
|
|
"entropy": 5.950350522994995,
|
|
"epoch": 0.15452723020380887,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999432191871719,
|
|
"loss": 5.7796,
|
|
"mean_token_accuracy": 0.15568242147564887,
|
|
"num_tokens": 3403077.0,
|
|
"step": 1850
|
|
},
|
|
{
|
|
"entropy": 5.9900336265563965,
|
|
"epoch": 0.15494487136652188,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999425484499718,
|
|
"loss": 5.7456,
|
|
"mean_token_accuracy": 0.16083690375089646,
|
|
"num_tokens": 3412165.0,
|
|
"step": 1855
|
|
},
|
|
{
|
|
"entropy": 5.951553058624268,
|
|
"epoch": 0.1553625125292349,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999418737748817,
|
|
"loss": 5.8265,
|
|
"mean_token_accuracy": 0.1454428181052208,
|
|
"num_tokens": 3421162.0,
|
|
"step": 1860
|
|
},
|
|
{
|
|
"entropy": 6.050862407684326,
|
|
"epoch": 0.15578015369194786,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999411951619134,
|
|
"loss": 5.8793,
|
|
"mean_token_accuracy": 0.14493936151266099,
|
|
"num_tokens": 3430363.0,
|
|
"step": 1865
|
|
},
|
|
{
|
|
"entropy": 5.987689018249512,
|
|
"epoch": 0.15619779485466087,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999405126110786,
|
|
"loss": 5.7929,
|
|
"mean_token_accuracy": 0.15352775007486344,
|
|
"num_tokens": 3439199.0,
|
|
"step": 1870
|
|
},
|
|
{
|
|
"entropy": 6.1002357006073,
|
|
"epoch": 0.15661543601737388,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999398261223895,
|
|
"loss": 5.9129,
|
|
"mean_token_accuracy": 0.14442275017499923,
|
|
"num_tokens": 3448720.0,
|
|
"step": 1875
|
|
},
|
|
{
|
|
"entropy": 5.99772834777832,
|
|
"epoch": 0.15703307718008688,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999391356958579,
|
|
"loss": 5.8939,
|
|
"mean_token_accuracy": 0.14629118889570236,
|
|
"num_tokens": 3458472.0,
|
|
"step": 1880
|
|
},
|
|
{
|
|
"entropy": 5.93433518409729,
|
|
"epoch": 0.15745071834279986,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000499938441331496,
|
|
"loss": 5.8354,
|
|
"mean_token_accuracy": 0.1485055461525917,
|
|
"num_tokens": 3467140.0,
|
|
"step": 1885
|
|
},
|
|
{
|
|
"entropy": 6.078635835647583,
|
|
"epoch": 0.15786835950551287,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999377430293159,
|
|
"loss": 5.8076,
|
|
"mean_token_accuracy": 0.15474040806293488,
|
|
"num_tokens": 3476431.0,
|
|
"step": 1890
|
|
},
|
|
{
|
|
"entropy": 5.902494716644287,
|
|
"epoch": 0.15828600066822587,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999370407893299,
|
|
"loss": 5.7226,
|
|
"mean_token_accuracy": 0.15522852241992952,
|
|
"num_tokens": 3485768.0,
|
|
"step": 1895
|
|
},
|
|
{
|
|
"entropy": 6.016763544082641,
|
|
"epoch": 0.15870364183093885,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999363346115501,
|
|
"loss": 5.8796,
|
|
"mean_token_accuracy": 0.14450376033782958,
|
|
"num_tokens": 3495678.0,
|
|
"step": 1900
|
|
},
|
|
{
|
|
"entropy": 6.002452945709228,
|
|
"epoch": 0.15912128299365186,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999356244959893,
|
|
"loss": 5.8607,
|
|
"mean_token_accuracy": 0.14681571200489998,
|
|
"num_tokens": 3505168.0,
|
|
"step": 1905
|
|
},
|
|
{
|
|
"entropy": 5.89468150138855,
|
|
"epoch": 0.15953892415636486,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999349104426594,
|
|
"loss": 5.8125,
|
|
"mean_token_accuracy": 0.14540216326713562,
|
|
"num_tokens": 3514498.0,
|
|
"step": 1910
|
|
},
|
|
{
|
|
"entropy": 6.03236985206604,
|
|
"epoch": 0.15995656531907784,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999341924515732,
|
|
"loss": 5.7402,
|
|
"mean_token_accuracy": 0.14893507361412048,
|
|
"num_tokens": 3524617.0,
|
|
"step": 1915
|
|
},
|
|
{
|
|
"entropy": 5.950137090682984,
|
|
"epoch": 0.16037420648179085,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999334705227431,
|
|
"loss": 5.7038,
|
|
"mean_token_accuracy": 0.15793468281626702,
|
|
"num_tokens": 3533523.0,
|
|
"step": 1920
|
|
},
|
|
{
|
|
"entropy": 5.93976845741272,
|
|
"epoch": 0.16079184764450385,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.000499932744656182,
|
|
"loss": 5.7803,
|
|
"mean_token_accuracy": 0.15535735040903093,
|
|
"num_tokens": 3542922.0,
|
|
"step": 1925
|
|
},
|
|
{
|
|
"entropy": 5.9716380596160885,
|
|
"epoch": 0.16120948880721683,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999320148519024,
|
|
"loss": 5.7698,
|
|
"mean_token_accuracy": 0.1537807211279869,
|
|
"num_tokens": 3551827.0,
|
|
"step": 1930
|
|
},
|
|
{
|
|
"entropy": 5.912134122848511,
|
|
"epoch": 0.16162712996992984,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999312811099171,
|
|
"loss": 5.7424,
|
|
"mean_token_accuracy": 0.15665630251169205,
|
|
"num_tokens": 3560911.0,
|
|
"step": 1935
|
|
},
|
|
{
|
|
"entropy": 5.943596744537354,
|
|
"epoch": 0.16204477113264285,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999305434302391,
|
|
"loss": 5.774,
|
|
"mean_token_accuracy": 0.15078182965517045,
|
|
"num_tokens": 3569473.0,
|
|
"step": 1940
|
|
},
|
|
{
|
|
"entropy": 5.950336027145386,
|
|
"epoch": 0.16246241229535582,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000499929801812881,
|
|
"loss": 5.7669,
|
|
"mean_token_accuracy": 0.15755152851343154,
|
|
"num_tokens": 3578843.0,
|
|
"step": 1945
|
|
},
|
|
{
|
|
"entropy": 5.934217214584351,
|
|
"epoch": 0.16288005345806883,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999290562578561,
|
|
"loss": 5.7788,
|
|
"mean_token_accuracy": 0.15204366892576218,
|
|
"num_tokens": 3588304.0,
|
|
"step": 1950
|
|
},
|
|
{
|
|
"entropy": 5.915329647064209,
|
|
"epoch": 0.16329769462078184,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999283067651773,
|
|
"loss": 5.8426,
|
|
"mean_token_accuracy": 0.15053938925266266,
|
|
"num_tokens": 3598354.0,
|
|
"step": 1955
|
|
},
|
|
{
|
|
"entropy": 6.05399227142334,
|
|
"epoch": 0.16371533578349481,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999275533348577,
|
|
"loss": 5.8723,
|
|
"mean_token_accuracy": 0.15038531348109246,
|
|
"num_tokens": 3607503.0,
|
|
"step": 1960
|
|
},
|
|
{
|
|
"entropy": 5.811189603805542,
|
|
"epoch": 0.16413297694620782,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999267959669106,
|
|
"loss": 5.6896,
|
|
"mean_token_accuracy": 0.1612261191010475,
|
|
"num_tokens": 3617467.0,
|
|
"step": 1965
|
|
},
|
|
{
|
|
"entropy": 5.984873485565186,
|
|
"epoch": 0.16455061810892083,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999260346613491,
|
|
"loss": 5.7094,
|
|
"mean_token_accuracy": 0.14969066977500917,
|
|
"num_tokens": 3627048.0,
|
|
"step": 1970
|
|
},
|
|
{
|
|
"entropy": 5.889481449127198,
|
|
"epoch": 0.1649682592716338,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999252694181867,
|
|
"loss": 5.7374,
|
|
"mean_token_accuracy": 0.15431074053049088,
|
|
"num_tokens": 3636683.0,
|
|
"step": 1975
|
|
},
|
|
{
|
|
"entropy": 5.81419415473938,
|
|
"epoch": 0.1653859004343468,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999245002374367,
|
|
"loss": 5.6322,
|
|
"mean_token_accuracy": 0.16551566421985625,
|
|
"num_tokens": 3645231.0,
|
|
"step": 1980
|
|
},
|
|
{
|
|
"entropy": 5.923137855529785,
|
|
"epoch": 0.16580354159705982,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004999237271191125,
|
|
"loss": 5.7184,
|
|
"mean_token_accuracy": 0.1556422308087349,
|
|
"num_tokens": 3653851.0,
|
|
"step": 1985
|
|
},
|
|
{
|
|
"entropy": 5.859198522567749,
|
|
"epoch": 0.1662211827597728,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999229500632279,
|
|
"loss": 5.6922,
|
|
"mean_token_accuracy": 0.16142508387565613,
|
|
"num_tokens": 3662720.0,
|
|
"step": 1990
|
|
},
|
|
{
|
|
"entropy": 5.774721765518189,
|
|
"epoch": 0.1666388239224858,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004999221690697961,
|
|
"loss": 5.6495,
|
|
"mean_token_accuracy": 0.15686668008565902,
|
|
"num_tokens": 3671777.0,
|
|
"step": 1995
|
|
},
|
|
{
|
|
"entropy": 5.897257137298584,
|
|
"epoch": 0.1670564650851988,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999213841388312,
|
|
"loss": 5.7188,
|
|
"mean_token_accuracy": 0.16273299157619475,
|
|
"num_tokens": 3681390.0,
|
|
"step": 2000
|
|
},
|
|
{
|
|
"entropy": 5.959281492233276,
|
|
"epoch": 0.16747410624791179,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999205952703466,
|
|
"loss": 5.7871,
|
|
"mean_token_accuracy": 0.15210252553224562,
|
|
"num_tokens": 3690899.0,
|
|
"step": 2005
|
|
},
|
|
{
|
|
"entropy": 6.015440273284912,
|
|
"epoch": 0.1678917474106248,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999198024643563,
|
|
"loss": 5.8759,
|
|
"mean_token_accuracy": 0.14671805500984192,
|
|
"num_tokens": 3699891.0,
|
|
"step": 2010
|
|
},
|
|
{
|
|
"entropy": 5.827287578582764,
|
|
"epoch": 0.1683093885733378,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999190057208741,
|
|
"loss": 5.6696,
|
|
"mean_token_accuracy": 0.1584944322705269,
|
|
"num_tokens": 3709860.0,
|
|
"step": 2015
|
|
},
|
|
{
|
|
"entropy": 5.938063478469848,
|
|
"epoch": 0.16872702973605078,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000499918205039914,
|
|
"loss": 5.803,
|
|
"mean_token_accuracy": 0.15343469232320786,
|
|
"num_tokens": 3718896.0,
|
|
"step": 2020
|
|
},
|
|
{
|
|
"entropy": 5.8418293476104735,
|
|
"epoch": 0.16914467089876378,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999174004214899,
|
|
"loss": 5.6123,
|
|
"mean_token_accuracy": 0.1574483186006546,
|
|
"num_tokens": 3727355.0,
|
|
"step": 2025
|
|
},
|
|
{
|
|
"entropy": 5.841806077957154,
|
|
"epoch": 0.1695623120614768,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999165918656161,
|
|
"loss": 5.7103,
|
|
"mean_token_accuracy": 0.15504993572831155,
|
|
"num_tokens": 3736191.0,
|
|
"step": 2030
|
|
},
|
|
{
|
|
"entropy": 5.958983039855957,
|
|
"epoch": 0.16997995322418977,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999157793723065,
|
|
"loss": 5.7395,
|
|
"mean_token_accuracy": 0.1586153984069824,
|
|
"num_tokens": 3744832.0,
|
|
"step": 2035
|
|
},
|
|
{
|
|
"entropy": 5.84045672416687,
|
|
"epoch": 0.17039759438690277,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999149629415755,
|
|
"loss": 5.7066,
|
|
"mean_token_accuracy": 0.15203840285539627,
|
|
"num_tokens": 3753835.0,
|
|
"step": 2040
|
|
},
|
|
{
|
|
"entropy": 6.055625247955322,
|
|
"epoch": 0.17081523554961578,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999141425734374,
|
|
"loss": 5.7747,
|
|
"mean_token_accuracy": 0.15490478426218032,
|
|
"num_tokens": 3762816.0,
|
|
"step": 2045
|
|
},
|
|
{
|
|
"entropy": 5.835732316970825,
|
|
"epoch": 0.17123287671232876,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004999133182679064,
|
|
"loss": 5.8155,
|
|
"mean_token_accuracy": 0.148703470826149,
|
|
"num_tokens": 3773244.0,
|
|
"step": 2050
|
|
},
|
|
{
|
|
"entropy": 5.953923606872559,
|
|
"epoch": 0.17165051787504176,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999124900249971,
|
|
"loss": 5.6763,
|
|
"mean_token_accuracy": 0.16193537265062333,
|
|
"num_tokens": 3782122.0,
|
|
"step": 2055
|
|
},
|
|
{
|
|
"entropy": 5.870869255065918,
|
|
"epoch": 0.17206815903775477,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999116578447239,
|
|
"loss": 5.6705,
|
|
"mean_token_accuracy": 0.1667713090777397,
|
|
"num_tokens": 3791303.0,
|
|
"step": 2060
|
|
},
|
|
{
|
|
"entropy": 5.876138734817505,
|
|
"epoch": 0.17248580020046775,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004999108217271015,
|
|
"loss": 5.7479,
|
|
"mean_token_accuracy": 0.15425308793783188,
|
|
"num_tokens": 3800991.0,
|
|
"step": 2065
|
|
},
|
|
{
|
|
"entropy": 5.857042074203491,
|
|
"epoch": 0.17290344136318075,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999099816721444,
|
|
"loss": 5.6609,
|
|
"mean_token_accuracy": 0.15457299053668977,
|
|
"num_tokens": 3811293.0,
|
|
"step": 2070
|
|
},
|
|
{
|
|
"entropy": 5.99418363571167,
|
|
"epoch": 0.17332108252589376,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999091376798673,
|
|
"loss": 5.7568,
|
|
"mean_token_accuracy": 0.15130494236946107,
|
|
"num_tokens": 3820013.0,
|
|
"step": 2075
|
|
},
|
|
{
|
|
"entropy": 5.852330875396729,
|
|
"epoch": 0.17373872368860674,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004999082897502849,
|
|
"loss": 5.6497,
|
|
"mean_token_accuracy": 0.16134200170636176,
|
|
"num_tokens": 3829099.0,
|
|
"step": 2080
|
|
},
|
|
{
|
|
"entropy": 5.82087459564209,
|
|
"epoch": 0.17415636485131974,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999074378834123,
|
|
"loss": 5.7483,
|
|
"mean_token_accuracy": 0.15421984121203422,
|
|
"num_tokens": 3838308.0,
|
|
"step": 2085
|
|
},
|
|
{
|
|
"entropy": 5.92053747177124,
|
|
"epoch": 0.17457400601403275,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999065820792644,
|
|
"loss": 5.7005,
|
|
"mean_token_accuracy": 0.15973791033029555,
|
|
"num_tokens": 3847650.0,
|
|
"step": 2090
|
|
},
|
|
{
|
|
"entropy": 5.99317421913147,
|
|
"epoch": 0.17499164717674573,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999057223378559,
|
|
"loss": 5.8778,
|
|
"mean_token_accuracy": 0.1442355714738369,
|
|
"num_tokens": 3857252.0,
|
|
"step": 2095
|
|
},
|
|
{
|
|
"entropy": 5.863450002670288,
|
|
"epoch": 0.17540928833945874,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000499904858659202,
|
|
"loss": 5.7337,
|
|
"mean_token_accuracy": 0.15778396278619766,
|
|
"num_tokens": 3865747.0,
|
|
"step": 2100
|
|
},
|
|
{
|
|
"entropy": 5.886807632446289,
|
|
"epoch": 0.17582692950217174,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999039910433179,
|
|
"loss": 5.6976,
|
|
"mean_token_accuracy": 0.16511771082878113,
|
|
"num_tokens": 3874958.0,
|
|
"step": 2105
|
|
},
|
|
{
|
|
"entropy": 5.78854775428772,
|
|
"epoch": 0.17624457066488472,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004999031194902187,
|
|
"loss": 5.6507,
|
|
"mean_token_accuracy": 0.16393667757511138,
|
|
"num_tokens": 3885216.0,
|
|
"step": 2110
|
|
},
|
|
{
|
|
"entropy": 5.815725708007813,
|
|
"epoch": 0.17666221182759773,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999022439999198,
|
|
"loss": 5.6814,
|
|
"mean_token_accuracy": 0.16577479541301726,
|
|
"num_tokens": 3893973.0,
|
|
"step": 2115
|
|
},
|
|
{
|
|
"entropy": 5.971462154388428,
|
|
"epoch": 0.17707985299031073,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999013645724362,
|
|
"loss": 5.7731,
|
|
"mean_token_accuracy": 0.1582237407565117,
|
|
"num_tokens": 3903532.0,
|
|
"step": 2120
|
|
},
|
|
{
|
|
"entropy": 5.9179940700531,
|
|
"epoch": 0.1774974941530237,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999004812077836,
|
|
"loss": 5.6958,
|
|
"mean_token_accuracy": 0.15923276245594026,
|
|
"num_tokens": 3913427.0,
|
|
"step": 2125
|
|
},
|
|
{
|
|
"entropy": 5.932846403121948,
|
|
"epoch": 0.17791513531573672,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004998995939059773,
|
|
"loss": 5.8206,
|
|
"mean_token_accuracy": 0.145328551530838,
|
|
"num_tokens": 3923870.0,
|
|
"step": 2130
|
|
},
|
|
{
|
|
"entropy": 5.825693130493164,
|
|
"epoch": 0.17833277647844972,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000499898702667033,
|
|
"loss": 5.6408,
|
|
"mean_token_accuracy": 0.1622411608695984,
|
|
"num_tokens": 3933469.0,
|
|
"step": 2135
|
|
},
|
|
{
|
|
"entropy": 5.8633805274963375,
|
|
"epoch": 0.1787504176411627,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004998978074909661,
|
|
"loss": 5.6579,
|
|
"mean_token_accuracy": 0.16844791918992996,
|
|
"num_tokens": 3942427.0,
|
|
"step": 2140
|
|
},
|
|
{
|
|
"entropy": 5.818320178985596,
|
|
"epoch": 0.1791680588038757,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998969083777925,
|
|
"loss": 5.6925,
|
|
"mean_token_accuracy": 0.16658158153295516,
|
|
"num_tokens": 3951250.0,
|
|
"step": 2145
|
|
},
|
|
{
|
|
"entropy": 5.894375801086426,
|
|
"epoch": 0.1795856999665887,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998960053275277,
|
|
"loss": 5.6894,
|
|
"mean_token_accuracy": 0.15957503467798234,
|
|
"num_tokens": 3959969.0,
|
|
"step": 2150
|
|
},
|
|
{
|
|
"entropy": 5.851364850997925,
|
|
"epoch": 0.1800033411293017,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004998950983401875,
|
|
"loss": 5.7232,
|
|
"mean_token_accuracy": 0.15560920387506486,
|
|
"num_tokens": 3968171.0,
|
|
"step": 2155
|
|
},
|
|
{
|
|
"entropy": 5.920967769622803,
|
|
"epoch": 0.1804209822920147,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998941874157882,
|
|
"loss": 5.6209,
|
|
"mean_token_accuracy": 0.16588948369026185,
|
|
"num_tokens": 3976686.0,
|
|
"step": 2160
|
|
},
|
|
{
|
|
"entropy": 5.743179512023926,
|
|
"epoch": 0.1808386234547277,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004998932725543453,
|
|
"loss": 5.7372,
|
|
"mean_token_accuracy": 0.15956501960754393,
|
|
"num_tokens": 3986552.0,
|
|
"step": 2165
|
|
},
|
|
{
|
|
"entropy": 5.888717126846314,
|
|
"epoch": 0.18125626461744068,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004998923537558749,
|
|
"loss": 5.6116,
|
|
"mean_token_accuracy": 0.1573790043592453,
|
|
"num_tokens": 3995501.0,
|
|
"step": 2170
|
|
},
|
|
{
|
|
"entropy": 5.726497554779053,
|
|
"epoch": 0.1816739057801537,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998914310203932,
|
|
"loss": 5.6075,
|
|
"mean_token_accuracy": 0.16367665976285933,
|
|
"num_tokens": 4004423.0,
|
|
"step": 2175
|
|
},
|
|
{
|
|
"entropy": 5.9079173564910885,
|
|
"epoch": 0.1820915469428667,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998905043479163,
|
|
"loss": 5.796,
|
|
"mean_token_accuracy": 0.1520387388765812,
|
|
"num_tokens": 4013324.0,
|
|
"step": 2180
|
|
},
|
|
{
|
|
"entropy": 5.931830978393554,
|
|
"epoch": 0.18250918810557967,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998895737384605,
|
|
"loss": 5.6804,
|
|
"mean_token_accuracy": 0.15867839008569717,
|
|
"num_tokens": 4021896.0,
|
|
"step": 2185
|
|
},
|
|
{
|
|
"entropy": 5.754932498931884,
|
|
"epoch": 0.18292682926829268,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004998886391920418,
|
|
"loss": 5.66,
|
|
"mean_token_accuracy": 0.1559813290834427,
|
|
"num_tokens": 4030590.0,
|
|
"step": 2190
|
|
},
|
|
{
|
|
"entropy": 5.8287865161895756,
|
|
"epoch": 0.18334447043100568,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998877007086769,
|
|
"loss": 5.5567,
|
|
"mean_token_accuracy": 0.17052167057991027,
|
|
"num_tokens": 4040041.0,
|
|
"step": 2195
|
|
},
|
|
{
|
|
"entropy": 5.837833738327026,
|
|
"epoch": 0.18376211159371866,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998867582883821,
|
|
"loss": 5.7246,
|
|
"mean_token_accuracy": 0.150713437050581,
|
|
"num_tokens": 4049119.0,
|
|
"step": 2200
|
|
},
|
|
{
|
|
"entropy": 5.864384412765503,
|
|
"epoch": 0.18417975275643167,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004998858119311739,
|
|
"loss": 5.6599,
|
|
"mean_token_accuracy": 0.15918856784701346,
|
|
"num_tokens": 4059265.0,
|
|
"step": 2205
|
|
},
|
|
{
|
|
"entropy": 5.8326281070709225,
|
|
"epoch": 0.18459739391914468,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004998848616370689,
|
|
"loss": 5.7001,
|
|
"mean_token_accuracy": 0.15809556990861892,
|
|
"num_tokens": 4068363.0,
|
|
"step": 2210
|
|
},
|
|
{
|
|
"entropy": 5.798278284072876,
|
|
"epoch": 0.18501503508185768,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004998839074060837,
|
|
"loss": 5.5881,
|
|
"mean_token_accuracy": 0.16857375651597978,
|
|
"num_tokens": 4077390.0,
|
|
"step": 2215
|
|
},
|
|
{
|
|
"entropy": 5.79602165222168,
|
|
"epoch": 0.18543267624457066,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000499882949238235,
|
|
"loss": 5.6749,
|
|
"mean_token_accuracy": 0.15564524084329606,
|
|
"num_tokens": 4087331.0,
|
|
"step": 2220
|
|
},
|
|
{
|
|
"entropy": 5.975500297546387,
|
|
"epoch": 0.18585031740728367,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998819871335396,
|
|
"loss": 5.8549,
|
|
"mean_token_accuracy": 0.15241608321666716,
|
|
"num_tokens": 4096425.0,
|
|
"step": 2225
|
|
},
|
|
{
|
|
"entropy": 5.81837944984436,
|
|
"epoch": 0.18626795856999667,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998810210920142,
|
|
"loss": 5.6292,
|
|
"mean_token_accuracy": 0.15902866423130035,
|
|
"num_tokens": 4106056.0,
|
|
"step": 2230
|
|
},
|
|
{
|
|
"entropy": 5.7763697624206545,
|
|
"epoch": 0.18668559973270965,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998800511136759,
|
|
"loss": 5.7116,
|
|
"mean_token_accuracy": 0.15947857201099397,
|
|
"num_tokens": 4115133.0,
|
|
"step": 2235
|
|
},
|
|
{
|
|
"entropy": 5.8516068935394285,
|
|
"epoch": 0.18710324089542266,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004998790771985417,
|
|
"loss": 5.6267,
|
|
"mean_token_accuracy": 0.16477923840284348,
|
|
"num_tokens": 4123630.0,
|
|
"step": 2240
|
|
},
|
|
{
|
|
"entropy": 5.774742317199707,
|
|
"epoch": 0.18752088205813566,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004998780993466284,
|
|
"loss": 5.7463,
|
|
"mean_token_accuracy": 0.16099598556756972,
|
|
"num_tokens": 4133337.0,
|
|
"step": 2245
|
|
},
|
|
{
|
|
"entropy": 5.892826843261719,
|
|
"epoch": 0.18793852322084864,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998771175579534,
|
|
"loss": 5.676,
|
|
"mean_token_accuracy": 0.1580575130879879,
|
|
"num_tokens": 4142240.0,
|
|
"step": 2250
|
|
},
|
|
{
|
|
"entropy": 5.782235956192016,
|
|
"epoch": 0.18835616438356165,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004998761318325337,
|
|
"loss": 5.6686,
|
|
"mean_token_accuracy": 0.156616672873497,
|
|
"num_tokens": 4151297.0,
|
|
"step": 2255
|
|
},
|
|
{
|
|
"entropy": 5.789702367782593,
|
|
"epoch": 0.18877380554627465,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998751421703868,
|
|
"loss": 5.6215,
|
|
"mean_token_accuracy": 0.16046866476535798,
|
|
"num_tokens": 4160193.0,
|
|
"step": 2260
|
|
},
|
|
{
|
|
"entropy": 5.877978038787842,
|
|
"epoch": 0.18919144670898763,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004998741485715297,
|
|
"loss": 5.7708,
|
|
"mean_token_accuracy": 0.15555500686168672,
|
|
"num_tokens": 4169948.0,
|
|
"step": 2265
|
|
},
|
|
{
|
|
"entropy": 5.985896205902099,
|
|
"epoch": 0.18960908787170064,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00049987315103598,
|
|
"loss": 5.7972,
|
|
"mean_token_accuracy": 0.15081522166728972,
|
|
"num_tokens": 4179981.0,
|
|
"step": 2270
|
|
},
|
|
{
|
|
"entropy": 5.81521258354187,
|
|
"epoch": 0.19002672903441364,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998721495637551,
|
|
"loss": 5.7957,
|
|
"mean_token_accuracy": 0.15333186388015746,
|
|
"num_tokens": 4189172.0,
|
|
"step": 2275
|
|
},
|
|
{
|
|
"entropy": 5.865990352630615,
|
|
"epoch": 0.19044437019712662,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998711441548726,
|
|
"loss": 5.6126,
|
|
"mean_token_accuracy": 0.16020057201385499,
|
|
"num_tokens": 4197312.0,
|
|
"step": 2280
|
|
},
|
|
{
|
|
"entropy": 5.87011022567749,
|
|
"epoch": 0.19086201135983963,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004998701348093499,
|
|
"loss": 5.6706,
|
|
"mean_token_accuracy": 0.16028127670288086,
|
|
"num_tokens": 4206828.0,
|
|
"step": 2285
|
|
},
|
|
{
|
|
"entropy": 5.936899137496948,
|
|
"epoch": 0.19127965252255263,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000499869121527205,
|
|
"loss": 5.6343,
|
|
"mean_token_accuracy": 0.1662514716386795,
|
|
"num_tokens": 4214835.0,
|
|
"step": 2290
|
|
},
|
|
{
|
|
"entropy": 5.84994478225708,
|
|
"epoch": 0.1916972936852656,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004998681043084553,
|
|
"loss": 5.8139,
|
|
"mean_token_accuracy": 0.14824395328760148,
|
|
"num_tokens": 4225119.0,
|
|
"step": 2295
|
|
},
|
|
{
|
|
"entropy": 5.756076002120972,
|
|
"epoch": 0.19211493484797862,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998670831531188,
|
|
"loss": 5.6526,
|
|
"mean_token_accuracy": 0.15910039842128754,
|
|
"num_tokens": 4235257.0,
|
|
"step": 2300
|
|
},
|
|
{
|
|
"entropy": 5.82043194770813,
|
|
"epoch": 0.19253257601069163,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004998660580612135,
|
|
"loss": 5.7215,
|
|
"mean_token_accuracy": 0.16029210090637208,
|
|
"num_tokens": 4244211.0,
|
|
"step": 2305
|
|
},
|
|
{
|
|
"entropy": 5.849356603622437,
|
|
"epoch": 0.1929502171734046,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998650290327569,
|
|
"loss": 5.7396,
|
|
"mean_token_accuracy": 0.15851273387670517,
|
|
"num_tokens": 4253149.0,
|
|
"step": 2310
|
|
},
|
|
{
|
|
"entropy": 5.765655517578125,
|
|
"epoch": 0.1933678583361176,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998639960677675,
|
|
"loss": 5.6319,
|
|
"mean_token_accuracy": 0.16373072266578675,
|
|
"num_tokens": 4262557.0,
|
|
"step": 2315
|
|
},
|
|
{
|
|
"entropy": 5.830093955993652,
|
|
"epoch": 0.19378549949883062,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004998629591662631,
|
|
"loss": 5.6452,
|
|
"mean_token_accuracy": 0.15700610876083373,
|
|
"num_tokens": 4272881.0,
|
|
"step": 2320
|
|
},
|
|
{
|
|
"entropy": 5.771763753890991,
|
|
"epoch": 0.1942031406615436,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000499861918328262,
|
|
"loss": 5.643,
|
|
"mean_token_accuracy": 0.1647744208574295,
|
|
"num_tokens": 4281158.0,
|
|
"step": 2325
|
|
},
|
|
{
|
|
"entropy": 5.816524362564087,
|
|
"epoch": 0.1946207818242566,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004998608735537822,
|
|
"loss": 5.644,
|
|
"mean_token_accuracy": 0.15966358929872512,
|
|
"num_tokens": 4290319.0,
|
|
"step": 2330
|
|
},
|
|
{
|
|
"entropy": 5.839132690429688,
|
|
"epoch": 0.1950384229869696,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998598248428423,
|
|
"loss": 5.7273,
|
|
"mean_token_accuracy": 0.16326339393854142,
|
|
"num_tokens": 4299276.0,
|
|
"step": 2335
|
|
},
|
|
{
|
|
"entropy": 5.8503776550292965,
|
|
"epoch": 0.19545606414968258,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998587721954604,
|
|
"loss": 5.692,
|
|
"mean_token_accuracy": 0.16148559898138046,
|
|
"num_tokens": 4308291.0,
|
|
"step": 2340
|
|
},
|
|
{
|
|
"entropy": 5.7621392726898195,
|
|
"epoch": 0.1958737053123956,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998577156116551,
|
|
"loss": 5.6517,
|
|
"mean_token_accuracy": 0.1572328507900238,
|
|
"num_tokens": 4316654.0,
|
|
"step": 2345
|
|
},
|
|
{
|
|
"entropy": 5.833258485794067,
|
|
"epoch": 0.1962913464751086,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998566550914448,
|
|
"loss": 5.5887,
|
|
"mean_token_accuracy": 0.15987759977579116,
|
|
"num_tokens": 4325911.0,
|
|
"step": 2350
|
|
},
|
|
{
|
|
"entropy": 5.780224704742432,
|
|
"epoch": 0.19670898763782158,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998555906348481,
|
|
"loss": 5.77,
|
|
"mean_token_accuracy": 0.1557260274887085,
|
|
"num_tokens": 4334846.0,
|
|
"step": 2355
|
|
},
|
|
{
|
|
"entropy": 5.895426082611084,
|
|
"epoch": 0.19712662880053458,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998545222418836,
|
|
"loss": 5.6489,
|
|
"mean_token_accuracy": 0.16278416961431502,
|
|
"num_tokens": 4343728.0,
|
|
"step": 2360
|
|
},
|
|
{
|
|
"entropy": 5.813882684707641,
|
|
"epoch": 0.1975442699632476,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998534499125701,
|
|
"loss": 5.6286,
|
|
"mean_token_accuracy": 0.1627249151468277,
|
|
"num_tokens": 4352774.0,
|
|
"step": 2365
|
|
},
|
|
{
|
|
"entropy": 5.867633724212647,
|
|
"epoch": 0.19796191112596057,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998523736469263,
|
|
"loss": 5.7684,
|
|
"mean_token_accuracy": 0.15933503061532975,
|
|
"num_tokens": 4361663.0,
|
|
"step": 2370
|
|
},
|
|
{
|
|
"entropy": 5.789565467834473,
|
|
"epoch": 0.19837955228867357,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000499851293444971,
|
|
"loss": 5.6116,
|
|
"mean_token_accuracy": 0.1717309609055519,
|
|
"num_tokens": 4370278.0,
|
|
"step": 2375
|
|
},
|
|
{
|
|
"entropy": 5.8761261940002445,
|
|
"epoch": 0.19879719345138658,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004998502093067231,
|
|
"loss": 5.6661,
|
|
"mean_token_accuracy": 0.16252981573343278,
|
|
"num_tokens": 4379010.0,
|
|
"step": 2380
|
|
},
|
|
{
|
|
"entropy": 5.848679161071777,
|
|
"epoch": 0.19921483461409956,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004998491212322017,
|
|
"loss": 5.6362,
|
|
"mean_token_accuracy": 0.15828320235013962,
|
|
"num_tokens": 4388145.0,
|
|
"step": 2385
|
|
},
|
|
{
|
|
"entropy": 5.763821983337403,
|
|
"epoch": 0.19963247577681256,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004998480292214258,
|
|
"loss": 5.773,
|
|
"mean_token_accuracy": 0.15703087002038957,
|
|
"num_tokens": 4396321.0,
|
|
"step": 2390
|
|
},
|
|
{
|
|
"entropy": 5.807074356079101,
|
|
"epoch": 0.20005011693952557,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004998469332744144,
|
|
"loss": 5.5447,
|
|
"mean_token_accuracy": 0.1663380816578865,
|
|
"num_tokens": 4404854.0,
|
|
"step": 2395
|
|
},
|
|
{
|
|
"entropy": 5.64944372177124,
|
|
"epoch": 0.20046775810223855,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004998458333911869,
|
|
"loss": 5.5536,
|
|
"mean_token_accuracy": 0.16941631883382796,
|
|
"num_tokens": 4413890.0,
|
|
"step": 2400
|
|
},
|
|
{
|
|
"entropy": 5.781361818313599,
|
|
"epoch": 0.20088539926495155,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998447295717624,
|
|
"loss": 5.7074,
|
|
"mean_token_accuracy": 0.16001133918762206,
|
|
"num_tokens": 4423019.0,
|
|
"step": 2405
|
|
},
|
|
{
|
|
"entropy": 5.797937536239624,
|
|
"epoch": 0.20130304042766456,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998436218161602,
|
|
"loss": 5.6408,
|
|
"mean_token_accuracy": 0.16225794404745103,
|
|
"num_tokens": 4432340.0,
|
|
"step": 2410
|
|
},
|
|
{
|
|
"entropy": 5.792998313903809,
|
|
"epoch": 0.20172068159037754,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004998425101243999,
|
|
"loss": 5.6188,
|
|
"mean_token_accuracy": 0.16200828105211257,
|
|
"num_tokens": 4441834.0,
|
|
"step": 2415
|
|
},
|
|
{
|
|
"entropy": 5.766503381729126,
|
|
"epoch": 0.20213832275309054,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004998413944965007,
|
|
"loss": 5.6492,
|
|
"mean_token_accuracy": 0.16266501992940902,
|
|
"num_tokens": 4450864.0,
|
|
"step": 2420
|
|
},
|
|
{
|
|
"entropy": 5.73400182723999,
|
|
"epoch": 0.20255596391580355,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004998402749324823,
|
|
"loss": 5.7124,
|
|
"mean_token_accuracy": 0.15515679866075516,
|
|
"num_tokens": 4460697.0,
|
|
"step": 2425
|
|
},
|
|
{
|
|
"entropy": 5.940784645080567,
|
|
"epoch": 0.20297360507851653,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004998391514323642,
|
|
"loss": 5.7285,
|
|
"mean_token_accuracy": 0.15854752361774443,
|
|
"num_tokens": 4469926.0,
|
|
"step": 2430
|
|
},
|
|
{
|
|
"entropy": 5.7850086212158205,
|
|
"epoch": 0.20339124624122953,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004998380239961661,
|
|
"loss": 5.6548,
|
|
"mean_token_accuracy": 0.16090933382511138,
|
|
"num_tokens": 4478818.0,
|
|
"step": 2435
|
|
},
|
|
{
|
|
"entropy": 5.808289384841919,
|
|
"epoch": 0.20380888740394254,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004998368926239078,
|
|
"loss": 5.5844,
|
|
"mean_token_accuracy": 0.16591333746910095,
|
|
"num_tokens": 4487451.0,
|
|
"step": 2440
|
|
},
|
|
{
|
|
"entropy": 5.759612798690796,
|
|
"epoch": 0.20422652856665552,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000499835757315609,
|
|
"loss": 5.6756,
|
|
"mean_token_accuracy": 0.15726785063743592,
|
|
"num_tokens": 4497674.0,
|
|
"step": 2445
|
|
},
|
|
{
|
|
"entropy": 5.7742194652557375,
|
|
"epoch": 0.20464416972936852,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998346180712898,
|
|
"loss": 5.624,
|
|
"mean_token_accuracy": 0.16603823602199555,
|
|
"num_tokens": 4507666.0,
|
|
"step": 2450
|
|
},
|
|
{
|
|
"entropy": 5.790293836593628,
|
|
"epoch": 0.20506181089208153,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998334748909698,
|
|
"loss": 5.7295,
|
|
"mean_token_accuracy": 0.15739290416240692,
|
|
"num_tokens": 4517409.0,
|
|
"step": 2455
|
|
},
|
|
{
|
|
"entropy": 5.786230230331421,
|
|
"epoch": 0.2054794520547945,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998323277746694,
|
|
"loss": 5.5241,
|
|
"mean_token_accuracy": 0.16496848613023757,
|
|
"num_tokens": 4526495.0,
|
|
"step": 2460
|
|
},
|
|
{
|
|
"entropy": 5.7622456550598145,
|
|
"epoch": 0.20589709321750752,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004998311767224081,
|
|
"loss": 5.6131,
|
|
"mean_token_accuracy": 0.17294674664735793,
|
|
"num_tokens": 4535240.0,
|
|
"step": 2465
|
|
},
|
|
{
|
|
"entropy": 5.7548096656799315,
|
|
"epoch": 0.20631473438022052,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004998300217342067,
|
|
"loss": 5.6976,
|
|
"mean_token_accuracy": 0.15931780487298966,
|
|
"num_tokens": 4544716.0,
|
|
"step": 2470
|
|
},
|
|
{
|
|
"entropy": 5.745911979675293,
|
|
"epoch": 0.2067323755429335,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004998288628100851,
|
|
"loss": 5.6222,
|
|
"mean_token_accuracy": 0.16541972160339355,
|
|
"num_tokens": 4553867.0,
|
|
"step": 2475
|
|
},
|
|
{
|
|
"entropy": 5.8166767120361325,
|
|
"epoch": 0.2071500167056465,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004998276999500636,
|
|
"loss": 5.6764,
|
|
"mean_token_accuracy": 0.1619221478700638,
|
|
"num_tokens": 4562529.0,
|
|
"step": 2480
|
|
},
|
|
{
|
|
"entropy": 5.709495973587036,
|
|
"epoch": 0.2075676578683595,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998265331541627,
|
|
"loss": 5.4687,
|
|
"mean_token_accuracy": 0.1788138762116432,
|
|
"num_tokens": 4571041.0,
|
|
"step": 2485
|
|
},
|
|
{
|
|
"entropy": 5.6762677192687985,
|
|
"epoch": 0.2079852990310725,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998253624224026,
|
|
"loss": 5.5986,
|
|
"mean_token_accuracy": 0.1655976355075836,
|
|
"num_tokens": 4579914.0,
|
|
"step": 2490
|
|
},
|
|
{
|
|
"entropy": 5.769092082977295,
|
|
"epoch": 0.2084029401937855,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000499824187754804,
|
|
"loss": 5.6967,
|
|
"mean_token_accuracy": 0.1630502760410309,
|
|
"num_tokens": 4590277.0,
|
|
"step": 2495
|
|
},
|
|
{
|
|
"entropy": 5.757724618911743,
|
|
"epoch": 0.2088205813564985,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998230091513872,
|
|
"loss": 5.6117,
|
|
"mean_token_accuracy": 0.16430521458387376,
|
|
"num_tokens": 4598719.0,
|
|
"step": 2500
|
|
},
|
|
{
|
|
"entropy": 5.7639039039611815,
|
|
"epoch": 0.20923822251921148,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004998218266121731,
|
|
"loss": 5.5588,
|
|
"mean_token_accuracy": 0.16492444276809692,
|
|
"num_tokens": 4607804.0,
|
|
"step": 2505
|
|
},
|
|
{
|
|
"entropy": 5.7059930801391605,
|
|
"epoch": 0.2096558636819245,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004998206401371823,
|
|
"loss": 5.5602,
|
|
"mean_token_accuracy": 0.16498781740665436,
|
|
"num_tokens": 4616529.0,
|
|
"step": 2510
|
|
},
|
|
{
|
|
"entropy": 5.782010936737061,
|
|
"epoch": 0.2100735048446375,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998194497264357,
|
|
"loss": 5.6004,
|
|
"mean_token_accuracy": 0.16248040944337844,
|
|
"num_tokens": 4624545.0,
|
|
"step": 2515
|
|
},
|
|
{
|
|
"entropy": 5.7379570484161375,
|
|
"epoch": 0.21049114600735047,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998182553799538,
|
|
"loss": 5.577,
|
|
"mean_token_accuracy": 0.16051217615604402,
|
|
"num_tokens": 4633316.0,
|
|
"step": 2520
|
|
},
|
|
{
|
|
"entropy": 5.7334644317626955,
|
|
"epoch": 0.21090878717006348,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998170570977579,
|
|
"loss": 5.5426,
|
|
"mean_token_accuracy": 0.16709231436252595,
|
|
"num_tokens": 4643353.0,
|
|
"step": 2525
|
|
},
|
|
{
|
|
"entropy": 5.724237775802612,
|
|
"epoch": 0.21132642833277648,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004998158548798687,
|
|
"loss": 5.6328,
|
|
"mean_token_accuracy": 0.16201059520244598,
|
|
"num_tokens": 4651998.0,
|
|
"step": 2530
|
|
},
|
|
{
|
|
"entropy": 5.776553726196289,
|
|
"epoch": 0.21174406949548946,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998146487263074,
|
|
"loss": 5.6237,
|
|
"mean_token_accuracy": 0.16452135294675826,
|
|
"num_tokens": 4659937.0,
|
|
"step": 2535
|
|
},
|
|
{
|
|
"entropy": 5.748791980743408,
|
|
"epoch": 0.21216171065820247,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004998134386370951,
|
|
"loss": 5.6036,
|
|
"mean_token_accuracy": 0.16133213490247728,
|
|
"num_tokens": 4669396.0,
|
|
"step": 2540
|
|
},
|
|
{
|
|
"entropy": 5.822993564605713,
|
|
"epoch": 0.21257935182091547,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004998122246122529,
|
|
"loss": 5.675,
|
|
"mean_token_accuracy": 0.1632826492190361,
|
|
"num_tokens": 4679320.0,
|
|
"step": 2545
|
|
},
|
|
{
|
|
"entropy": 5.792739677429199,
|
|
"epoch": 0.21299699298362845,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004998110066518021,
|
|
"loss": 5.5965,
|
|
"mean_token_accuracy": 0.16390374004840852,
|
|
"num_tokens": 4688807.0,
|
|
"step": 2550
|
|
},
|
|
{
|
|
"entropy": 5.798362731933594,
|
|
"epoch": 0.21341463414634146,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000499809784755764,
|
|
"loss": 5.6089,
|
|
"mean_token_accuracy": 0.17050699889659882,
|
|
"num_tokens": 4697819.0,
|
|
"step": 2555
|
|
},
|
|
{
|
|
"entropy": 5.6853009223937985,
|
|
"epoch": 0.21383227530905446,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00049980855892416,
|
|
"loss": 5.5795,
|
|
"mean_token_accuracy": 0.16765243858098983,
|
|
"num_tokens": 4706931.0,
|
|
"step": 2560
|
|
},
|
|
{
|
|
"entropy": 5.7483304977417,
|
|
"epoch": 0.21424991647176747,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004998073291570116,
|
|
"loss": 5.5681,
|
|
"mean_token_accuracy": 0.16450838446617128,
|
|
"num_tokens": 4716262.0,
|
|
"step": 2565
|
|
},
|
|
{
|
|
"entropy": 5.734201574325562,
|
|
"epoch": 0.21466755763448045,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004998060954543404,
|
|
"loss": 5.5834,
|
|
"mean_token_accuracy": 0.16493556201457976,
|
|
"num_tokens": 4725415.0,
|
|
"step": 2570
|
|
},
|
|
{
|
|
"entropy": 5.7109521389007565,
|
|
"epoch": 0.21508519879719346,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998048578161678,
|
|
"loss": 5.6546,
|
|
"mean_token_accuracy": 0.16459743529558182,
|
|
"num_tokens": 4734580.0,
|
|
"step": 2575
|
|
},
|
|
{
|
|
"entropy": 5.665662527084351,
|
|
"epoch": 0.21550283995990646,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004998036162425155,
|
|
"loss": 5.465,
|
|
"mean_token_accuracy": 0.17132774442434312,
|
|
"num_tokens": 4742966.0,
|
|
"step": 2580
|
|
},
|
|
{
|
|
"entropy": 5.726974296569824,
|
|
"epoch": 0.21592048112261944,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998023707334055,
|
|
"loss": 5.5987,
|
|
"mean_token_accuracy": 0.16571207493543624,
|
|
"num_tokens": 4751696.0,
|
|
"step": 2585
|
|
},
|
|
{
|
|
"entropy": 5.802803802490234,
|
|
"epoch": 0.21633812228533245,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998011212888592,
|
|
"loss": 5.6628,
|
|
"mean_token_accuracy": 0.16626541465520858,
|
|
"num_tokens": 4760460.0,
|
|
"step": 2590
|
|
},
|
|
{
|
|
"entropy": 5.766793346405029,
|
|
"epoch": 0.21675576344804545,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004997998679088988,
|
|
"loss": 5.5858,
|
|
"mean_token_accuracy": 0.165497525036335,
|
|
"num_tokens": 4769004.0,
|
|
"step": 2595
|
|
},
|
|
{
|
|
"entropy": 5.726294231414795,
|
|
"epoch": 0.21717340461075843,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004997986105935461,
|
|
"loss": 5.5707,
|
|
"mean_token_accuracy": 0.17018312215805054,
|
|
"num_tokens": 4777204.0,
|
|
"step": 2600
|
|
},
|
|
{
|
|
"entropy": 5.815764331817627,
|
|
"epoch": 0.21759104577347144,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004997973493428231,
|
|
"loss": 5.7033,
|
|
"mean_token_accuracy": 0.16050707995891572,
|
|
"num_tokens": 4786766.0,
|
|
"step": 2605
|
|
},
|
|
{
|
|
"entropy": 5.666415119171143,
|
|
"epoch": 0.21800868693618444,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004997960841567519,
|
|
"loss": 5.5961,
|
|
"mean_token_accuracy": 0.16938992440700532,
|
|
"num_tokens": 4796676.0,
|
|
"step": 2610
|
|
},
|
|
{
|
|
"entropy": 5.901765584945679,
|
|
"epoch": 0.21842632809889742,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004997948150353548,
|
|
"loss": 5.5966,
|
|
"mean_token_accuracy": 0.1654299795627594,
|
|
"num_tokens": 4805514.0,
|
|
"step": 2615
|
|
},
|
|
{
|
|
"entropy": 5.714858770370483,
|
|
"epoch": 0.21884396926161043,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004997935419786537,
|
|
"loss": 5.6752,
|
|
"mean_token_accuracy": 0.16269783824682235,
|
|
"num_tokens": 4815487.0,
|
|
"step": 2620
|
|
},
|
|
{
|
|
"entropy": 5.806606769561768,
|
|
"epoch": 0.21926161042432343,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004997922649866712,
|
|
"loss": 5.6183,
|
|
"mean_token_accuracy": 0.16302125453948973,
|
|
"num_tokens": 4825044.0,
|
|
"step": 2625
|
|
},
|
|
{
|
|
"entropy": 5.651657152175903,
|
|
"epoch": 0.2196792515870364,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004997909840594294,
|
|
"loss": 5.4087,
|
|
"mean_token_accuracy": 0.17524338662624359,
|
|
"num_tokens": 4833875.0,
|
|
"step": 2630
|
|
},
|
|
{
|
|
"entropy": 5.638663101196289,
|
|
"epoch": 0.22009689274974942,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004997896991969509,
|
|
"loss": 5.6418,
|
|
"mean_token_accuracy": 0.15811533331871033,
|
|
"num_tokens": 4843317.0,
|
|
"step": 2635
|
|
},
|
|
{
|
|
"entropy": 5.7495684146881105,
|
|
"epoch": 0.22051453391246242,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004997884103992581,
|
|
"loss": 5.6321,
|
|
"mean_token_accuracy": 0.15845716297626494,
|
|
"num_tokens": 4852514.0,
|
|
"step": 2640
|
|
},
|
|
{
|
|
"entropy": 5.695010948181152,
|
|
"epoch": 0.2209321750751754,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004997871176663736,
|
|
"loss": 5.5792,
|
|
"mean_token_accuracy": 0.16959371864795686,
|
|
"num_tokens": 4861260.0,
|
|
"step": 2645
|
|
},
|
|
{
|
|
"entropy": 5.708796119689941,
|
|
"epoch": 0.2213498162378884,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004997858209983201,
|
|
"loss": 5.5333,
|
|
"mean_token_accuracy": 0.16668965592980384,
|
|
"num_tokens": 4869654.0,
|
|
"step": 2650
|
|
},
|
|
{
|
|
"entropy": 5.724199867248535,
|
|
"epoch": 0.22176745740060141,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004997845203951202,
|
|
"loss": 5.5937,
|
|
"mean_token_accuracy": 0.15722348690032958,
|
|
"num_tokens": 4878311.0,
|
|
"step": 2655
|
|
},
|
|
{
|
|
"entropy": 5.7917327880859375,
|
|
"epoch": 0.2221850985633144,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004997832158567967,
|
|
"loss": 5.6604,
|
|
"mean_token_accuracy": 0.15930023267865182,
|
|
"num_tokens": 4887251.0,
|
|
"step": 2660
|
|
},
|
|
{
|
|
"entropy": 5.709334659576416,
|
|
"epoch": 0.2226027397260274,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004997819073833724,
|
|
"loss": 5.5234,
|
|
"mean_token_accuracy": 0.1640756532549858,
|
|
"num_tokens": 4896528.0,
|
|
"step": 2665
|
|
},
|
|
{
|
|
"entropy": 5.699781513214111,
|
|
"epoch": 0.2230203808887404,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004997805949748702,
|
|
"loss": 5.5851,
|
|
"mean_token_accuracy": 0.16082951575517654,
|
|
"num_tokens": 4904962.0,
|
|
"step": 2670
|
|
},
|
|
{
|
|
"entropy": 5.751451635360718,
|
|
"epoch": 0.22343802205145338,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004997792786313132,
|
|
"loss": 5.5949,
|
|
"mean_token_accuracy": 0.16221776455640793,
|
|
"num_tokens": 4914735.0,
|
|
"step": 2675
|
|
},
|
|
{
|
|
"entropy": 5.555906057357788,
|
|
"epoch": 0.2238556632141664,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004997779583527243,
|
|
"loss": 5.4638,
|
|
"mean_token_accuracy": 0.1665905386209488,
|
|
"num_tokens": 4924271.0,
|
|
"step": 2680
|
|
},
|
|
{
|
|
"entropy": 5.8695250988006595,
|
|
"epoch": 0.2242733043768794,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004997766341391268,
|
|
"loss": 5.7047,
|
|
"mean_token_accuracy": 0.155639585852623,
|
|
"num_tokens": 4933928.0,
|
|
"step": 2685
|
|
},
|
|
{
|
|
"entropy": 5.705683994293213,
|
|
"epoch": 0.22469094553959237,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004997753059905437,
|
|
"loss": 5.4135,
|
|
"mean_token_accuracy": 0.1759113550186157,
|
|
"num_tokens": 4942714.0,
|
|
"step": 2690
|
|
},
|
|
{
|
|
"entropy": 5.6081311225891115,
|
|
"epoch": 0.22510858670230538,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004997739739069981,
|
|
"loss": 5.541,
|
|
"mean_token_accuracy": 0.16623980104923247,
|
|
"num_tokens": 4952297.0,
|
|
"step": 2695
|
|
},
|
|
{
|
|
"entropy": 5.701430177688598,
|
|
"epoch": 0.22552622786501839,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004997726378885138,
|
|
"loss": 5.48,
|
|
"mean_token_accuracy": 0.1763035088777542,
|
|
"num_tokens": 4960947.0,
|
|
"step": 2700
|
|
},
|
|
{
|
|
"entropy": 5.713150548934936,
|
|
"epoch": 0.22594386902773136,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004997712979351137,
|
|
"loss": 5.6433,
|
|
"mean_token_accuracy": 0.16017448753118516,
|
|
"num_tokens": 4969705.0,
|
|
"step": 2705
|
|
},
|
|
{
|
|
"entropy": 5.7782330989837645,
|
|
"epoch": 0.22636151019044437,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004997699540468216,
|
|
"loss": 5.6095,
|
|
"mean_token_accuracy": 0.16398101300001144,
|
|
"num_tokens": 4979112.0,
|
|
"step": 2710
|
|
},
|
|
{
|
|
"entropy": 5.707289409637451,
|
|
"epoch": 0.22677915135315738,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004997686062236609,
|
|
"loss": 5.5245,
|
|
"mean_token_accuracy": 0.1688684806227684,
|
|
"num_tokens": 4987894.0,
|
|
"step": 2715
|
|
},
|
|
{
|
|
"entropy": 5.728122043609619,
|
|
"epoch": 0.22719679251587035,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004997672544656553,
|
|
"loss": 5.6685,
|
|
"mean_token_accuracy": 0.1611431822180748,
|
|
"num_tokens": 4997774.0,
|
|
"step": 2720
|
|
},
|
|
{
|
|
"entropy": 5.774860763549805,
|
|
"epoch": 0.22761443367858336,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004997658987728283,
|
|
"loss": 5.5835,
|
|
"mean_token_accuracy": 0.17197922468185425,
|
|
"num_tokens": 5006183.0,
|
|
"step": 2725
|
|
},
|
|
{
|
|
"entropy": 5.711122512817383,
|
|
"epoch": 0.22803207484129637,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004997645391452035,
|
|
"loss": 5.5795,
|
|
"mean_token_accuracy": 0.1666414961218834,
|
|
"num_tokens": 5016909.0,
|
|
"step": 2730
|
|
},
|
|
{
|
|
"entropy": 5.7371501445770265,
|
|
"epoch": 0.22844971600400935,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000499763175582805,
|
|
"loss": 5.6246,
|
|
"mean_token_accuracy": 0.16619712710380555,
|
|
"num_tokens": 5027326.0,
|
|
"step": 2735
|
|
},
|
|
{
|
|
"entropy": 5.773577308654785,
|
|
"epoch": 0.22886735716672235,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004997618080856566,
|
|
"loss": 5.5787,
|
|
"mean_token_accuracy": 0.16747207343578338,
|
|
"num_tokens": 5037043.0,
|
|
"step": 2740
|
|
},
|
|
{
|
|
"entropy": 5.614604187011719,
|
|
"epoch": 0.22928499832943536,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004997604366537823,
|
|
"loss": 5.5621,
|
|
"mean_token_accuracy": 0.16502413600683213,
|
|
"num_tokens": 5045992.0,
|
|
"step": 2745
|
|
},
|
|
{
|
|
"entropy": 5.674044513702393,
|
|
"epoch": 0.22970263949214834,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004997590612872058,
|
|
"loss": 5.5419,
|
|
"mean_token_accuracy": 0.16780618876218795,
|
|
"num_tokens": 5055568.0,
|
|
"step": 2750
|
|
},
|
|
{
|
|
"entropy": 5.761773729324341,
|
|
"epoch": 0.23012028065486134,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004997576819859515,
|
|
"loss": 5.617,
|
|
"mean_token_accuracy": 0.1640057623386383,
|
|
"num_tokens": 5065512.0,
|
|
"step": 2755
|
|
},
|
|
{
|
|
"entropy": 5.6007527828216555,
|
|
"epoch": 0.23053792181757435,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004997562987500434,
|
|
"loss": 5.4683,
|
|
"mean_token_accuracy": 0.17772611379623413,
|
|
"num_tokens": 5074776.0,
|
|
"step": 2760
|
|
},
|
|
{
|
|
"entropy": 5.620506668090821,
|
|
"epoch": 0.23095556298028733,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004997549115795058,
|
|
"loss": 5.518,
|
|
"mean_token_accuracy": 0.16908519864082336,
|
|
"num_tokens": 5084743.0,
|
|
"step": 2765
|
|
},
|
|
{
|
|
"entropy": 5.7845690727233885,
|
|
"epoch": 0.23137320414300033,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000499753520474363,
|
|
"loss": 5.6789,
|
|
"mean_token_accuracy": 0.16238866448402406,
|
|
"num_tokens": 5095387.0,
|
|
"step": 2770
|
|
},
|
|
{
|
|
"entropy": 5.675830888748169,
|
|
"epoch": 0.23179084530571334,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004997521254346391,
|
|
"loss": 5.5874,
|
|
"mean_token_accuracy": 0.16865266785025596,
|
|
"num_tokens": 5104628.0,
|
|
"step": 2775
|
|
},
|
|
{
|
|
"entropy": 5.757327651977539,
|
|
"epoch": 0.23220848646842632,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004997507264603589,
|
|
"loss": 5.5401,
|
|
"mean_token_accuracy": 0.16944464445114135,
|
|
"num_tokens": 5113169.0,
|
|
"step": 2780
|
|
},
|
|
{
|
|
"entropy": 5.695029544830322,
|
|
"epoch": 0.23262612763113932,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004997493235515466,
|
|
"loss": 5.601,
|
|
"mean_token_accuracy": 0.16851502060890197,
|
|
"num_tokens": 5122294.0,
|
|
"step": 2785
|
|
},
|
|
{
|
|
"entropy": 5.605187559127808,
|
|
"epoch": 0.23304376879385233,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004997479167082269,
|
|
"loss": 5.4361,
|
|
"mean_token_accuracy": 0.17638742476701735,
|
|
"num_tokens": 5131191.0,
|
|
"step": 2790
|
|
},
|
|
{
|
|
"entropy": 5.674936103820801,
|
|
"epoch": 0.2334614099565653,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004997465059304243,
|
|
"loss": 5.6504,
|
|
"mean_token_accuracy": 0.167001473903656,
|
|
"num_tokens": 5141974.0,
|
|
"step": 2795
|
|
},
|
|
{
|
|
"entropy": 5.781553602218628,
|
|
"epoch": 0.23387905111927831,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004997450912181637,
|
|
"loss": 5.5828,
|
|
"mean_token_accuracy": 0.16855430603027344,
|
|
"num_tokens": 5151412.0,
|
|
"step": 2800
|
|
},
|
|
{
|
|
"entropy": 5.66849799156189,
|
|
"epoch": 0.23429669228199132,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004997436725714696,
|
|
"loss": 5.5071,
|
|
"mean_token_accuracy": 0.17201763838529588,
|
|
"num_tokens": 5160989.0,
|
|
"step": 2805
|
|
},
|
|
{
|
|
"entropy": 5.687669134140014,
|
|
"epoch": 0.2347143334447043,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004997422499903671,
|
|
"loss": 5.575,
|
|
"mean_token_accuracy": 0.16350428611040116,
|
|
"num_tokens": 5170241.0,
|
|
"step": 2810
|
|
},
|
|
{
|
|
"entropy": 5.852313756942749,
|
|
"epoch": 0.2351319746074173,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000499740823474881,
|
|
"loss": 5.693,
|
|
"mean_token_accuracy": 0.15919099301099776,
|
|
"num_tokens": 5180247.0,
|
|
"step": 2815
|
|
},
|
|
{
|
|
"entropy": 5.683443641662597,
|
|
"epoch": 0.2355496157701303,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004997393930250363,
|
|
"loss": 5.5877,
|
|
"mean_token_accuracy": 0.16531823873519896,
|
|
"num_tokens": 5189144.0,
|
|
"step": 2820
|
|
},
|
|
{
|
|
"entropy": 5.660533905029297,
|
|
"epoch": 0.2359672569328433,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.000499737958640858,
|
|
"loss": 5.6363,
|
|
"mean_token_accuracy": 0.16292943805456161,
|
|
"num_tokens": 5199410.0,
|
|
"step": 2825
|
|
},
|
|
{
|
|
"entropy": 5.772460985183716,
|
|
"epoch": 0.2363848980955563,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004997365203223711,
|
|
"loss": 5.5163,
|
|
"mean_token_accuracy": 0.17269660532474518,
|
|
"num_tokens": 5209032.0,
|
|
"step": 2830
|
|
},
|
|
{
|
|
"entropy": 5.5716253280639645,
|
|
"epoch": 0.2368025392582693,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000499735078069601,
|
|
"loss": 5.4117,
|
|
"mean_token_accuracy": 0.17505983710289003,
|
|
"num_tokens": 5217787.0,
|
|
"step": 2835
|
|
},
|
|
{
|
|
"entropy": 5.610530710220337,
|
|
"epoch": 0.23722018042098228,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004997336318825728,
|
|
"loss": 5.5272,
|
|
"mean_token_accuracy": 0.1705465003848076,
|
|
"num_tokens": 5226962.0,
|
|
"step": 2840
|
|
},
|
|
{
|
|
"entropy": 5.678059244155884,
|
|
"epoch": 0.23763782158369529,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004997321817613119,
|
|
"loss": 5.501,
|
|
"mean_token_accuracy": 0.166815347969532,
|
|
"num_tokens": 5236111.0,
|
|
"step": 2845
|
|
},
|
|
{
|
|
"entropy": 5.748322200775147,
|
|
"epoch": 0.2380554627464083,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004997307277058436,
|
|
"loss": 5.6462,
|
|
"mean_token_accuracy": 0.16232668459415436,
|
|
"num_tokens": 5246628.0,
|
|
"step": 2850
|
|
},
|
|
{
|
|
"entropy": 5.667980480194092,
|
|
"epoch": 0.23847310390912127,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004997292697161935,
|
|
"loss": 5.5754,
|
|
"mean_token_accuracy": 0.16228308975696565,
|
|
"num_tokens": 5255543.0,
|
|
"step": 2855
|
|
},
|
|
{
|
|
"entropy": 5.61335859298706,
|
|
"epoch": 0.23889074507183428,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000499727807792387,
|
|
"loss": 5.4157,
|
|
"mean_token_accuracy": 0.1765509083867073,
|
|
"num_tokens": 5264559.0,
|
|
"step": 2860
|
|
},
|
|
{
|
|
"entropy": 5.593845558166504,
|
|
"epoch": 0.23930838623454728,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004997263419344495,
|
|
"loss": 5.5031,
|
|
"mean_token_accuracy": 0.17075306475162505,
|
|
"num_tokens": 5274599.0,
|
|
"step": 2865
|
|
},
|
|
{
|
|
"entropy": 5.6120987892150875,
|
|
"epoch": 0.23972602739726026,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004997248721424071,
|
|
"loss": 5.4684,
|
|
"mean_token_accuracy": 0.17607724964618682,
|
|
"num_tokens": 5283495.0,
|
|
"step": 2870
|
|
},
|
|
{
|
|
"entropy": 5.748496675491333,
|
|
"epoch": 0.24014366855997327,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004997233984162853,
|
|
"loss": 5.5206,
|
|
"mean_token_accuracy": 0.17262364476919173,
|
|
"num_tokens": 5292064.0,
|
|
"step": 2875
|
|
},
|
|
{
|
|
"entropy": 5.660027360916137,
|
|
"epoch": 0.24056130972268627,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004997219207561099,
|
|
"loss": 5.5373,
|
|
"mean_token_accuracy": 0.16632017493247986,
|
|
"num_tokens": 5301696.0,
|
|
"step": 2880
|
|
},
|
|
{
|
|
"entropy": 5.7199009418487545,
|
|
"epoch": 0.24097895088539925,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004997204391619068,
|
|
"loss": 5.647,
|
|
"mean_token_accuracy": 0.15879270881414415,
|
|
"num_tokens": 5311427.0,
|
|
"step": 2885
|
|
},
|
|
{
|
|
"entropy": 5.826184225082398,
|
|
"epoch": 0.24139659204811226,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004997189536337018,
|
|
"loss": 5.5703,
|
|
"mean_token_accuracy": 0.1678813174366951,
|
|
"num_tokens": 5321406.0,
|
|
"step": 2890
|
|
},
|
|
{
|
|
"entropy": 5.70261926651001,
|
|
"epoch": 0.24181423321082526,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004997174641715211,
|
|
"loss": 5.6536,
|
|
"mean_token_accuracy": 0.16488752663135528,
|
|
"num_tokens": 5332257.0,
|
|
"step": 2895
|
|
},
|
|
{
|
|
"entropy": 5.561820459365845,
|
|
"epoch": 0.24223187437353827,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004997159707753906,
|
|
"loss": 5.391,
|
|
"mean_token_accuracy": 0.17732247412204744,
|
|
"num_tokens": 5341857.0,
|
|
"step": 2900
|
|
},
|
|
{
|
|
"entropy": 5.639991235733032,
|
|
"epoch": 0.24264951553625125,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004997144734453367,
|
|
"loss": 5.5403,
|
|
"mean_token_accuracy": 0.1736094608902931,
|
|
"num_tokens": 5351367.0,
|
|
"step": 2905
|
|
},
|
|
{
|
|
"entropy": 5.567778444290161,
|
|
"epoch": 0.24306715669896425,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004997129721813853,
|
|
"loss": 5.3888,
|
|
"mean_token_accuracy": 0.17335254251956939,
|
|
"num_tokens": 5360627.0,
|
|
"step": 2910
|
|
},
|
|
{
|
|
"entropy": 5.627420234680176,
|
|
"epoch": 0.24348479786167726,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004997114669835629,
|
|
"loss": 5.4713,
|
|
"mean_token_accuracy": 0.17678721398115158,
|
|
"num_tokens": 5369703.0,
|
|
"step": 2915
|
|
},
|
|
{
|
|
"entropy": 5.658342075347901,
|
|
"epoch": 0.24390243902439024,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004997099578518959,
|
|
"loss": 5.5467,
|
|
"mean_token_accuracy": 0.16832583546638488,
|
|
"num_tokens": 5378432.0,
|
|
"step": 2920
|
|
},
|
|
{
|
|
"entropy": 5.573386335372925,
|
|
"epoch": 0.24432008018710324,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004997084447864105,
|
|
"loss": 5.3981,
|
|
"mean_token_accuracy": 0.17398632317781448,
|
|
"num_tokens": 5386489.0,
|
|
"step": 2925
|
|
},
|
|
{
|
|
"entropy": 5.770393562316895,
|
|
"epoch": 0.24473772134981625,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004997069277871333,
|
|
"loss": 5.6219,
|
|
"mean_token_accuracy": 0.16319795697927475,
|
|
"num_tokens": 5395908.0,
|
|
"step": 2930
|
|
},
|
|
{
|
|
"entropy": 5.763458490371704,
|
|
"epoch": 0.24515536251252923,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004997054068540908,
|
|
"loss": 5.5425,
|
|
"mean_token_accuracy": 0.17221789509058,
|
|
"num_tokens": 5404822.0,
|
|
"step": 2935
|
|
},
|
|
{
|
|
"entropy": 5.60934100151062,
|
|
"epoch": 0.24557300367524224,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004997038819873098,
|
|
"loss": 5.4537,
|
|
"mean_token_accuracy": 0.17699288725852966,
|
|
"num_tokens": 5413980.0,
|
|
"step": 2940
|
|
},
|
|
{
|
|
"entropy": 5.652670669555664,
|
|
"epoch": 0.24599064483795524,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004997023531868167,
|
|
"loss": 5.5227,
|
|
"mean_token_accuracy": 0.16705751717090606,
|
|
"num_tokens": 5423538.0,
|
|
"step": 2945
|
|
},
|
|
{
|
|
"entropy": 5.616042518615723,
|
|
"epoch": 0.24640828600066822,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004997008204526386,
|
|
"loss": 5.4503,
|
|
"mean_token_accuracy": 0.17180379182100297,
|
|
"num_tokens": 5431930.0,
|
|
"step": 2950
|
|
},
|
|
{
|
|
"entropy": 5.6258384704589846,
|
|
"epoch": 0.24682592716338123,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004996992837848021,
|
|
"loss": 5.4514,
|
|
"mean_token_accuracy": 0.17689115405082703,
|
|
"num_tokens": 5440721.0,
|
|
"step": 2955
|
|
},
|
|
{
|
|
"entropy": 5.611420965194702,
|
|
"epoch": 0.24724356832609423,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004996977431833342,
|
|
"loss": 5.5153,
|
|
"mean_token_accuracy": 0.1651511862874031,
|
|
"num_tokens": 5449617.0,
|
|
"step": 2960
|
|
},
|
|
{
|
|
"entropy": 5.621954154968262,
|
|
"epoch": 0.2476612094888072,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004996961986482618,
|
|
"loss": 5.5521,
|
|
"mean_token_accuracy": 0.17019403576850892,
|
|
"num_tokens": 5458827.0,
|
|
"step": 2965
|
|
},
|
|
{
|
|
"entropy": 5.697111034393311,
|
|
"epoch": 0.24807885065152022,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004996946501796119,
|
|
"loss": 5.4353,
|
|
"mean_token_accuracy": 0.17367945313453675,
|
|
"num_tokens": 5467348.0,
|
|
"step": 2970
|
|
},
|
|
{
|
|
"entropy": 5.669052839279175,
|
|
"epoch": 0.24849649181423322,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004996930977774118,
|
|
"loss": 5.505,
|
|
"mean_token_accuracy": 0.1617908701300621,
|
|
"num_tokens": 5476645.0,
|
|
"step": 2975
|
|
},
|
|
{
|
|
"entropy": 5.712230110168457,
|
|
"epoch": 0.2489141329769462,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004996915414416885,
|
|
"loss": 5.5382,
|
|
"mean_token_accuracy": 0.16787463724613189,
|
|
"num_tokens": 5486120.0,
|
|
"step": 2980
|
|
},
|
|
{
|
|
"entropy": 5.698201894760132,
|
|
"epoch": 0.2493317741396592,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004996899811724693,
|
|
"loss": 5.5308,
|
|
"mean_token_accuracy": 0.1670474722981453,
|
|
"num_tokens": 5495313.0,
|
|
"step": 2985
|
|
},
|
|
{
|
|
"entropy": 5.647207641601563,
|
|
"epoch": 0.2497494153023722,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004996884169697816,
|
|
"loss": 5.5247,
|
|
"mean_token_accuracy": 0.1688663676381111,
|
|
"num_tokens": 5504587.0,
|
|
"step": 2990
|
|
},
|
|
{
|
|
"entropy": 5.615376949310303,
|
|
"epoch": 0.2501670564650852,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004996868488336526,
|
|
"loss": 5.5488,
|
|
"mean_token_accuracy": 0.16672224402427674,
|
|
"num_tokens": 5514188.0,
|
|
"step": 2995
|
|
},
|
|
{
|
|
"entropy": 5.70684118270874,
|
|
"epoch": 0.25058469762779817,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004996852767641099,
|
|
"loss": 5.5913,
|
|
"mean_token_accuracy": 0.15994588136672974,
|
|
"num_tokens": 5524075.0,
|
|
"step": 3000
|
|
},
|
|
{
|
|
"epoch": 0.25058469762779817,
|
|
"eval_entropy": 5.478494798397265,
|
|
"eval_loss": 5.498563766479492,
|
|
"eval_mean_token_accuracy": 0.17943838510794094,
|
|
"eval_num_tokens": 5524075.0,
|
|
"eval_runtime": 20.9226,
|
|
"eval_samples_per_second": 1804.887,
|
|
"eval_steps_per_second": 225.641,
|
|
"step": 3000
|
|
},
|
|
{
|
|
"entropy": 5.602593278884887,
|
|
"epoch": 0.2510023387905112,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004996837007611811,
|
|
"loss": 5.3595,
|
|
"mean_token_accuracy": 0.17527442872524263,
|
|
"num_tokens": 5533323.0,
|
|
"step": 3005
|
|
},
|
|
{
|
|
"entropy": 5.5606709003448485,
|
|
"epoch": 0.2514199799532242,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004996821208248935,
|
|
"loss": 5.3825,
|
|
"mean_token_accuracy": 0.17830902934074402,
|
|
"num_tokens": 5542288.0,
|
|
"step": 3010
|
|
},
|
|
{
|
|
"entropy": 5.716786861419678,
|
|
"epoch": 0.25183762111593716,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004996805369552749,
|
|
"loss": 5.5523,
|
|
"mean_token_accuracy": 0.16320647895336152,
|
|
"num_tokens": 5550869.0,
|
|
"step": 3015
|
|
},
|
|
{
|
|
"entropy": 5.655161046981812,
|
|
"epoch": 0.2522552622786502,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004996789491523532,
|
|
"loss": 5.4633,
|
|
"mean_token_accuracy": 0.17710816562175752,
|
|
"num_tokens": 5560147.0,
|
|
"step": 3020
|
|
},
|
|
{
|
|
"entropy": 5.5786840438842775,
|
|
"epoch": 0.2526729034413632,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004996773574161559,
|
|
"loss": 5.3677,
|
|
"mean_token_accuracy": 0.17918083518743516,
|
|
"num_tokens": 5568358.0,
|
|
"step": 3025
|
|
},
|
|
{
|
|
"entropy": 5.612635326385498,
|
|
"epoch": 0.25309054460407615,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004996757617467112,
|
|
"loss": 5.4814,
|
|
"mean_token_accuracy": 0.16537049114704133,
|
|
"num_tokens": 5577755.0,
|
|
"step": 3030
|
|
},
|
|
{
|
|
"entropy": 5.682578229904175,
|
|
"epoch": 0.2535081857667892,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004996741621440466,
|
|
"loss": 5.5401,
|
|
"mean_token_accuracy": 0.15776935815811158,
|
|
"num_tokens": 5587515.0,
|
|
"step": 3035
|
|
},
|
|
{
|
|
"entropy": 5.710801124572754,
|
|
"epoch": 0.25392582692950216,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004996725586081906,
|
|
"loss": 5.6639,
|
|
"mean_token_accuracy": 0.16025283336639404,
|
|
"num_tokens": 5597860.0,
|
|
"step": 3040
|
|
},
|
|
{
|
|
"entropy": 5.701569509506226,
|
|
"epoch": 0.25434346809221514,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004996709511391709,
|
|
"loss": 5.5256,
|
|
"mean_token_accuracy": 0.17191781997680664,
|
|
"num_tokens": 5607302.0,
|
|
"step": 3045
|
|
},
|
|
{
|
|
"entropy": 5.640579891204834,
|
|
"epoch": 0.2547611092549282,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004996693397370158,
|
|
"loss": 5.5923,
|
|
"mean_token_accuracy": 0.16542113721370696,
|
|
"num_tokens": 5616345.0,
|
|
"step": 3050
|
|
},
|
|
{
|
|
"entropy": 5.631747817993164,
|
|
"epoch": 0.25517875041764115,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004996677244017534,
|
|
"loss": 5.3853,
|
|
"mean_token_accuracy": 0.173073410987854,
|
|
"num_tokens": 5624745.0,
|
|
"step": 3055
|
|
},
|
|
{
|
|
"entropy": 5.668503999710083,
|
|
"epoch": 0.25559639158035413,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004996661051334121,
|
|
"loss": 5.5228,
|
|
"mean_token_accuracy": 0.16704076677560806,
|
|
"num_tokens": 5634022.0,
|
|
"step": 3060
|
|
},
|
|
{
|
|
"entropy": 5.685352897644043,
|
|
"epoch": 0.25601403274306717,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004996644819320201,
|
|
"loss": 5.461,
|
|
"mean_token_accuracy": 0.17210687100887298,
|
|
"num_tokens": 5643631.0,
|
|
"step": 3065
|
|
},
|
|
{
|
|
"entropy": 5.68446683883667,
|
|
"epoch": 0.25643167390578014,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004996628547976061,
|
|
"loss": 5.5511,
|
|
"mean_token_accuracy": 0.16774857938289642,
|
|
"num_tokens": 5653155.0,
|
|
"step": 3070
|
|
},
|
|
{
|
|
"entropy": 5.601983499526978,
|
|
"epoch": 0.2568493150684932,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004996612237301983,
|
|
"loss": 5.5434,
|
|
"mean_token_accuracy": 0.17165842205286025,
|
|
"num_tokens": 5663091.0,
|
|
"step": 3075
|
|
},
|
|
{
|
|
"entropy": 5.597293710708618,
|
|
"epoch": 0.25726695623120616,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004996595887298254,
|
|
"loss": 5.448,
|
|
"mean_token_accuracy": 0.17855413258075714,
|
|
"num_tokens": 5671885.0,
|
|
"step": 3080
|
|
},
|
|
{
|
|
"entropy": 5.676712846755981,
|
|
"epoch": 0.25768459739391913,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000499657949796516,
|
|
"loss": 5.4666,
|
|
"mean_token_accuracy": 0.17005476504564285,
|
|
"num_tokens": 5680225.0,
|
|
"step": 3085
|
|
},
|
|
{
|
|
"entropy": 5.5222419738769535,
|
|
"epoch": 0.25810223855663217,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004996563069302986,
|
|
"loss": 5.3245,
|
|
"mean_token_accuracy": 0.18394140303134918,
|
|
"num_tokens": 5689456.0,
|
|
"step": 3090
|
|
},
|
|
{
|
|
"entropy": 5.574301099777221,
|
|
"epoch": 0.25851987971934515,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004996546601312023,
|
|
"loss": 5.4456,
|
|
"mean_token_accuracy": 0.1766171708703041,
|
|
"num_tokens": 5698127.0,
|
|
"step": 3095
|
|
},
|
|
{
|
|
"entropy": 5.573929214477539,
|
|
"epoch": 0.2589375208820581,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004996530093992558,
|
|
"loss": 5.4954,
|
|
"mean_token_accuracy": 0.173156276345253,
|
|
"num_tokens": 5706825.0,
|
|
"step": 3100
|
|
},
|
|
{
|
|
"entropy": 5.660216188430786,
|
|
"epoch": 0.25935516204477116,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004996513547344877,
|
|
"loss": 5.4357,
|
|
"mean_token_accuracy": 0.17253331542015077,
|
|
"num_tokens": 5715677.0,
|
|
"step": 3105
|
|
},
|
|
{
|
|
"entropy": 5.5564922332763675,
|
|
"epoch": 0.25977280320748414,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004996496961369274,
|
|
"loss": 5.3672,
|
|
"mean_token_accuracy": 0.17406684905290604,
|
|
"num_tokens": 5725371.0,
|
|
"step": 3110
|
|
},
|
|
{
|
|
"entropy": 5.631770658493042,
|
|
"epoch": 0.2601904443701971,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004996480336066037,
|
|
"loss": 5.4725,
|
|
"mean_token_accuracy": 0.1753530591726303,
|
|
"num_tokens": 5734664.0,
|
|
"step": 3115
|
|
},
|
|
{
|
|
"entropy": 5.629898118972778,
|
|
"epoch": 0.26060808553291015,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004996463671435458,
|
|
"loss": 5.4649,
|
|
"mean_token_accuracy": 0.17245597690343856,
|
|
"num_tokens": 5743870.0,
|
|
"step": 3120
|
|
},
|
|
{
|
|
"entropy": 5.492088651657104,
|
|
"epoch": 0.26102572669562313,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004996446967477829,
|
|
"loss": 5.4726,
|
|
"mean_token_accuracy": 0.175869382917881,
|
|
"num_tokens": 5752855.0,
|
|
"step": 3125
|
|
},
|
|
{
|
|
"entropy": 5.738801383972168,
|
|
"epoch": 0.2614433678583361,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004996430224193441,
|
|
"loss": 5.5367,
|
|
"mean_token_accuracy": 0.17029510140419007,
|
|
"num_tokens": 5762435.0,
|
|
"step": 3130
|
|
},
|
|
{
|
|
"entropy": 5.678168392181396,
|
|
"epoch": 0.26186100902104914,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004996413441582589,
|
|
"loss": 5.5338,
|
|
"mean_token_accuracy": 0.17078250348567964,
|
|
"num_tokens": 5771463.0,
|
|
"step": 3135
|
|
},
|
|
{
|
|
"entropy": 5.6406927585601805,
|
|
"epoch": 0.2622786501837621,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004996396619645564,
|
|
"loss": 5.5302,
|
|
"mean_token_accuracy": 0.16546972393989562,
|
|
"num_tokens": 5780530.0,
|
|
"step": 3140
|
|
},
|
|
{
|
|
"entropy": 5.630699539184571,
|
|
"epoch": 0.2626962913464751,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004996379758382662,
|
|
"loss": 5.4006,
|
|
"mean_token_accuracy": 0.17883287668228148,
|
|
"num_tokens": 5789199.0,
|
|
"step": 3145
|
|
},
|
|
{
|
|
"entropy": 5.73064489364624,
|
|
"epoch": 0.26311393250918813,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.000499636285779418,
|
|
"loss": 5.5918,
|
|
"mean_token_accuracy": 0.16522125601768495,
|
|
"num_tokens": 5799170.0,
|
|
"step": 3150
|
|
},
|
|
{
|
|
"entropy": 5.62532901763916,
|
|
"epoch": 0.2635315736719011,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004996345917880412,
|
|
"loss": 5.5021,
|
|
"mean_token_accuracy": 0.16831852197647096,
|
|
"num_tokens": 5807662.0,
|
|
"step": 3155
|
|
},
|
|
{
|
|
"entropy": 5.549431276321411,
|
|
"epoch": 0.2639492148346141,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004996328938641654,
|
|
"loss": 5.4146,
|
|
"mean_token_accuracy": 0.17468473613262175,
|
|
"num_tokens": 5815790.0,
|
|
"step": 3160
|
|
},
|
|
{
|
|
"entropy": 5.642532205581665,
|
|
"epoch": 0.2643668559973271,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004996311920078204,
|
|
"loss": 5.4266,
|
|
"mean_token_accuracy": 0.17523301988840104,
|
|
"num_tokens": 5824746.0,
|
|
"step": 3165
|
|
},
|
|
{
|
|
"entropy": 5.574083042144776,
|
|
"epoch": 0.2647844971600401,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004996294862190361,
|
|
"loss": 5.4408,
|
|
"mean_token_accuracy": 0.1776533082127571,
|
|
"num_tokens": 5833678.0,
|
|
"step": 3170
|
|
},
|
|
{
|
|
"entropy": 5.630044078826904,
|
|
"epoch": 0.2652021383227531,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000499627776497842,
|
|
"loss": 5.4853,
|
|
"mean_token_accuracy": 0.1765962466597557,
|
|
"num_tokens": 5842218.0,
|
|
"step": 3175
|
|
},
|
|
{
|
|
"entropy": 5.796161222457886,
|
|
"epoch": 0.2656197794854661,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004996260628442686,
|
|
"loss": 5.6637,
|
|
"mean_token_accuracy": 0.1582587666809559,
|
|
"num_tokens": 5853250.0,
|
|
"step": 3180
|
|
},
|
|
{
|
|
"entropy": 5.619317722320557,
|
|
"epoch": 0.2660374206481791,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004996243452583454,
|
|
"loss": 5.3935,
|
|
"mean_token_accuracy": 0.18060708791017532,
|
|
"num_tokens": 5862661.0,
|
|
"step": 3185
|
|
},
|
|
{
|
|
"entropy": 5.644404077529908,
|
|
"epoch": 0.26645506181089207,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004996226237401028,
|
|
"loss": 5.5492,
|
|
"mean_token_accuracy": 0.16795668601989747,
|
|
"num_tokens": 5872327.0,
|
|
"step": 3190
|
|
},
|
|
{
|
|
"entropy": 5.516964340209961,
|
|
"epoch": 0.2668727029736051,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004996208982895706,
|
|
"loss": 5.4026,
|
|
"mean_token_accuracy": 0.17274871319532395,
|
|
"num_tokens": 5881539.0,
|
|
"step": 3195
|
|
},
|
|
{
|
|
"entropy": 5.665464544296265,
|
|
"epoch": 0.2672903441363181,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004996191689067794,
|
|
"loss": 5.511,
|
|
"mean_token_accuracy": 0.17336390018463135,
|
|
"num_tokens": 5891602.0,
|
|
"step": 3200
|
|
},
|
|
{
|
|
"entropy": 5.600575494766235,
|
|
"epoch": 0.26770798529903106,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004996174355917591,
|
|
"loss": 5.5014,
|
|
"mean_token_accuracy": 0.1688656896352768,
|
|
"num_tokens": 5899831.0,
|
|
"step": 3205
|
|
},
|
|
{
|
|
"entropy": 5.702366590499878,
|
|
"epoch": 0.2681256264617441,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004996156983445404,
|
|
"loss": 5.6011,
|
|
"mean_token_accuracy": 0.1662008658051491,
|
|
"num_tokens": 5909193.0,
|
|
"step": 3210
|
|
},
|
|
{
|
|
"entropy": 5.626371002197265,
|
|
"epoch": 0.26854326762445707,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004996139571651534,
|
|
"loss": 5.5028,
|
|
"mean_token_accuracy": 0.1691843181848526,
|
|
"num_tokens": 5919353.0,
|
|
"step": 3215
|
|
},
|
|
{
|
|
"entropy": 5.608973217010498,
|
|
"epoch": 0.26896090878717005,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004996122120536288,
|
|
"loss": 5.4441,
|
|
"mean_token_accuracy": 0.17524013072252273,
|
|
"num_tokens": 5927853.0,
|
|
"step": 3220
|
|
},
|
|
{
|
|
"entropy": 5.546483087539673,
|
|
"epoch": 0.2693785499498831,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004996104630099969,
|
|
"loss": 5.5466,
|
|
"mean_token_accuracy": 0.17366677075624465,
|
|
"num_tokens": 5937943.0,
|
|
"step": 3225
|
|
},
|
|
{
|
|
"entropy": 5.6188586235046385,
|
|
"epoch": 0.26979619111259606,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004996087100342885,
|
|
"loss": 5.4546,
|
|
"mean_token_accuracy": 0.17476439625024795,
|
|
"num_tokens": 5946213.0,
|
|
"step": 3230
|
|
},
|
|
{
|
|
"entropy": 5.604651737213135,
|
|
"epoch": 0.27021383227530904,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004996069531265345,
|
|
"loss": 5.3553,
|
|
"mean_token_accuracy": 0.1729743644595146,
|
|
"num_tokens": 5954997.0,
|
|
"step": 3235
|
|
},
|
|
{
|
|
"entropy": 5.557475423812866,
|
|
"epoch": 0.2706314734380221,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004996051922867653,
|
|
"loss": 5.398,
|
|
"mean_token_accuracy": 0.17867136895656585,
|
|
"num_tokens": 5963947.0,
|
|
"step": 3240
|
|
},
|
|
{
|
|
"entropy": 5.570569610595703,
|
|
"epoch": 0.27104911460073505,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004996034275150118,
|
|
"loss": 5.4299,
|
|
"mean_token_accuracy": 0.1718892514705658,
|
|
"num_tokens": 5972077.0,
|
|
"step": 3245
|
|
},
|
|
{
|
|
"entropy": 5.550575113296508,
|
|
"epoch": 0.27146675576344803,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.000499601658811305,
|
|
"loss": 5.4417,
|
|
"mean_token_accuracy": 0.17238760441541673,
|
|
"num_tokens": 5982649.0,
|
|
"step": 3250
|
|
},
|
|
{
|
|
"entropy": 5.627004861831665,
|
|
"epoch": 0.27188439692616106,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004995998861756758,
|
|
"loss": 5.456,
|
|
"mean_token_accuracy": 0.17346239238977432,
|
|
"num_tokens": 5991349.0,
|
|
"step": 3255
|
|
},
|
|
{
|
|
"entropy": 5.517546892166138,
|
|
"epoch": 0.27230203808887404,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004995981096081552,
|
|
"loss": 5.4488,
|
|
"mean_token_accuracy": 0.1746513530611992,
|
|
"num_tokens": 6000555.0,
|
|
"step": 3260
|
|
},
|
|
{
|
|
"entropy": 5.787107801437378,
|
|
"epoch": 0.272719679251587,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004995963291087744,
|
|
"loss": 5.5607,
|
|
"mean_token_accuracy": 0.1572660341858864,
|
|
"num_tokens": 6009554.0,
|
|
"step": 3265
|
|
},
|
|
{
|
|
"entropy": 5.683590507507324,
|
|
"epoch": 0.27313732041430006,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004995945446775645,
|
|
"loss": 5.6408,
|
|
"mean_token_accuracy": 0.16543456614017488,
|
|
"num_tokens": 6019330.0,
|
|
"step": 3270
|
|
},
|
|
{
|
|
"entropy": 5.659921407699585,
|
|
"epoch": 0.27355496157701303,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004995927563145566,
|
|
"loss": 5.595,
|
|
"mean_token_accuracy": 0.1674351915717125,
|
|
"num_tokens": 6028527.0,
|
|
"step": 3275
|
|
},
|
|
{
|
|
"entropy": 5.632570886611939,
|
|
"epoch": 0.273972602739726,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004995909640197825,
|
|
"loss": 5.4556,
|
|
"mean_token_accuracy": 0.17271459698677064,
|
|
"num_tokens": 6038223.0,
|
|
"step": 3280
|
|
},
|
|
{
|
|
"entropy": 5.521641635894776,
|
|
"epoch": 0.27439024390243905,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004995891677932729,
|
|
"loss": 5.3925,
|
|
"mean_token_accuracy": 0.17719604074954987,
|
|
"num_tokens": 6047459.0,
|
|
"step": 3285
|
|
},
|
|
{
|
|
"entropy": 5.668535614013672,
|
|
"epoch": 0.274807885065152,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004995873676350597,
|
|
"loss": 5.572,
|
|
"mean_token_accuracy": 0.1681835636496544,
|
|
"num_tokens": 6057322.0,
|
|
"step": 3290
|
|
},
|
|
{
|
|
"entropy": 5.71825475692749,
|
|
"epoch": 0.275225526227865,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004995855635451743,
|
|
"loss": 5.6851,
|
|
"mean_token_accuracy": 0.16252846866846085,
|
|
"num_tokens": 6067520.0,
|
|
"step": 3295
|
|
},
|
|
{
|
|
"entropy": 5.674379491806031,
|
|
"epoch": 0.27564316739057804,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004995837555236484,
|
|
"loss": 5.567,
|
|
"mean_token_accuracy": 0.1648716986179352,
|
|
"num_tokens": 6076729.0,
|
|
"step": 3300
|
|
},
|
|
{
|
|
"entropy": 5.628241968154907,
|
|
"epoch": 0.276060808553291,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004995819435705133,
|
|
"loss": 5.5019,
|
|
"mean_token_accuracy": 0.16563906222581865,
|
|
"num_tokens": 6086529.0,
|
|
"step": 3305
|
|
},
|
|
{
|
|
"entropy": 5.659373760223389,
|
|
"epoch": 0.276478449716004,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004995801276858011,
|
|
"loss": 5.5239,
|
|
"mean_token_accuracy": 0.1756095215678215,
|
|
"num_tokens": 6095784.0,
|
|
"step": 3310
|
|
},
|
|
{
|
|
"entropy": 5.733769321441651,
|
|
"epoch": 0.276896090878717,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004995783078695434,
|
|
"loss": 5.5343,
|
|
"mean_token_accuracy": 0.17202824652194976,
|
|
"num_tokens": 6104626.0,
|
|
"step": 3315
|
|
},
|
|
{
|
|
"entropy": 5.577187585830688,
|
|
"epoch": 0.27731373204143,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000499576484121772,
|
|
"loss": 5.4585,
|
|
"mean_token_accuracy": 0.17361778765916824,
|
|
"num_tokens": 6113758.0,
|
|
"step": 3320
|
|
},
|
|
{
|
|
"entropy": 5.681585025787354,
|
|
"epoch": 0.277731373204143,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004995746564425191,
|
|
"loss": 5.4673,
|
|
"mean_token_accuracy": 0.176327845454216,
|
|
"num_tokens": 6123265.0,
|
|
"step": 3325
|
|
},
|
|
{
|
|
"entropy": 5.67174882888794,
|
|
"epoch": 0.278149014366856,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004995728248318163,
|
|
"loss": 5.543,
|
|
"mean_token_accuracy": 0.16984691321849824,
|
|
"num_tokens": 6132855.0,
|
|
"step": 3330
|
|
},
|
|
{
|
|
"entropy": 5.5259589672088625,
|
|
"epoch": 0.278566655529569,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004995709892896961,
|
|
"loss": 5.4113,
|
|
"mean_token_accuracy": 0.17089553028345109,
|
|
"num_tokens": 6142739.0,
|
|
"step": 3335
|
|
},
|
|
{
|
|
"entropy": 5.549342250823974,
|
|
"epoch": 0.278984296692282,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004995691498161903,
|
|
"loss": 5.3696,
|
|
"mean_token_accuracy": 0.1737748771905899,
|
|
"num_tokens": 6152169.0,
|
|
"step": 3340
|
|
},
|
|
{
|
|
"entropy": 5.475606870651245,
|
|
"epoch": 0.279401937854995,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004995673064113313,
|
|
"loss": 5.401,
|
|
"mean_token_accuracy": 0.1780400887131691,
|
|
"num_tokens": 6160235.0,
|
|
"step": 3345
|
|
},
|
|
{
|
|
"entropy": 5.560038232803345,
|
|
"epoch": 0.279819579017708,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004995654590751513,
|
|
"loss": 5.3862,
|
|
"mean_token_accuracy": 0.17502506971359252,
|
|
"num_tokens": 6169440.0,
|
|
"step": 3350
|
|
},
|
|
{
|
|
"entropy": 5.5738129138946535,
|
|
"epoch": 0.28023722018042097,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004995636078076825,
|
|
"loss": 5.4137,
|
|
"mean_token_accuracy": 0.17904069274663925,
|
|
"num_tokens": 6178456.0,
|
|
"step": 3355
|
|
},
|
|
{
|
|
"entropy": 5.509097719192505,
|
|
"epoch": 0.280654861343134,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004995617526089575,
|
|
"loss": 5.4846,
|
|
"mean_token_accuracy": 0.17317838966846466,
|
|
"num_tokens": 6186844.0,
|
|
"step": 3360
|
|
},
|
|
{
|
|
"entropy": 5.606524991989136,
|
|
"epoch": 0.281072502505847,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004995598934790087,
|
|
"loss": 5.4069,
|
|
"mean_token_accuracy": 0.17825868874788284,
|
|
"num_tokens": 6196117.0,
|
|
"step": 3365
|
|
},
|
|
{
|
|
"entropy": 5.594628858566284,
|
|
"epoch": 0.28149014366855996,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004995580304178687,
|
|
"loss": 5.3869,
|
|
"mean_token_accuracy": 0.18268515318632125,
|
|
"num_tokens": 6204636.0,
|
|
"step": 3370
|
|
},
|
|
{
|
|
"entropy": 5.516972541809082,
|
|
"epoch": 0.281907784831273,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004995561634255701,
|
|
"loss": 5.4196,
|
|
"mean_token_accuracy": 0.17650512456893921,
|
|
"num_tokens": 6214537.0,
|
|
"step": 3375
|
|
},
|
|
{
|
|
"entropy": 5.558368825912476,
|
|
"epoch": 0.28232542599398597,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004995542925021455,
|
|
"loss": 5.47,
|
|
"mean_token_accuracy": 0.1726568192243576,
|
|
"num_tokens": 6224753.0,
|
|
"step": 3380
|
|
},
|
|
{
|
|
"entropy": 5.807767534255982,
|
|
"epoch": 0.28274306715669895,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004995524176476277,
|
|
"loss": 5.6607,
|
|
"mean_token_accuracy": 0.17105791866779327,
|
|
"num_tokens": 6233842.0,
|
|
"step": 3385
|
|
},
|
|
{
|
|
"entropy": 5.734399938583374,
|
|
"epoch": 0.283160708319412,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004995505388620497,
|
|
"loss": 5.4957,
|
|
"mean_token_accuracy": 0.17600060850381852,
|
|
"num_tokens": 6243467.0,
|
|
"step": 3390
|
|
},
|
|
{
|
|
"entropy": 5.481904411315918,
|
|
"epoch": 0.28357834948212496,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000499548656145444,
|
|
"loss": 5.5422,
|
|
"mean_token_accuracy": 0.1659504532814026,
|
|
"num_tokens": 6253263.0,
|
|
"step": 3395
|
|
},
|
|
{
|
|
"entropy": 5.611874055862427,
|
|
"epoch": 0.28399599064483794,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004995467694978439,
|
|
"loss": 5.3838,
|
|
"mean_token_accuracy": 0.1848123013973236,
|
|
"num_tokens": 6262249.0,
|
|
"step": 3400
|
|
},
|
|
{
|
|
"entropy": 5.530205106735229,
|
|
"epoch": 0.28441363180755097,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004995448789192823,
|
|
"loss": 5.393,
|
|
"mean_token_accuracy": 0.17520347088575364,
|
|
"num_tokens": 6271154.0,
|
|
"step": 3405
|
|
},
|
|
{
|
|
"entropy": 5.531033277511597,
|
|
"epoch": 0.28483127297026395,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004995429844097922,
|
|
"loss": 5.4804,
|
|
"mean_token_accuracy": 0.17654867917299272,
|
|
"num_tokens": 6280377.0,
|
|
"step": 3410
|
|
},
|
|
{
|
|
"entropy": 5.6426879405975345,
|
|
"epoch": 0.2852489141329769,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004995410859694071,
|
|
"loss": 5.4755,
|
|
"mean_token_accuracy": 0.17208488285541534,
|
|
"num_tokens": 6289941.0,
|
|
"step": 3415
|
|
},
|
|
{
|
|
"entropy": 5.630606269836425,
|
|
"epoch": 0.28566655529568996,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004995391835981599,
|
|
"loss": 5.5237,
|
|
"mean_token_accuracy": 0.1680618032813072,
|
|
"num_tokens": 6299281.0,
|
|
"step": 3420
|
|
},
|
|
{
|
|
"entropy": 5.581368398666382,
|
|
"epoch": 0.28608419645840294,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000499537277296084,
|
|
"loss": 5.4968,
|
|
"mean_token_accuracy": 0.1690795600414276,
|
|
"num_tokens": 6309408.0,
|
|
"step": 3425
|
|
},
|
|
{
|
|
"entropy": 5.590551519393921,
|
|
"epoch": 0.2865018376211159,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004995353670632127,
|
|
"loss": 5.5126,
|
|
"mean_token_accuracy": 0.17588986158370973,
|
|
"num_tokens": 6318979.0,
|
|
"step": 3430
|
|
},
|
|
{
|
|
"entropy": 5.567683458328247,
|
|
"epoch": 0.28691947878382895,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004995334528995797,
|
|
"loss": 5.3332,
|
|
"mean_token_accuracy": 0.1819864720106125,
|
|
"num_tokens": 6327616.0,
|
|
"step": 3435
|
|
},
|
|
{
|
|
"entropy": 5.509003210067749,
|
|
"epoch": 0.28733711994654193,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004995315348052182,
|
|
"loss": 5.3676,
|
|
"mean_token_accuracy": 0.1833025187253952,
|
|
"num_tokens": 6336486.0,
|
|
"step": 3440
|
|
},
|
|
{
|
|
"entropy": 5.576023435592651,
|
|
"epoch": 0.2877547611092549,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000499529612780162,
|
|
"loss": 5.4176,
|
|
"mean_token_accuracy": 0.17563057094812393,
|
|
"num_tokens": 6345671.0,
|
|
"step": 3445
|
|
},
|
|
{
|
|
"entropy": 5.653712558746338,
|
|
"epoch": 0.28817240227196794,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004995276868244446,
|
|
"loss": 5.5246,
|
|
"mean_token_accuracy": 0.16986915171146394,
|
|
"num_tokens": 6354534.0,
|
|
"step": 3450
|
|
},
|
|
{
|
|
"entropy": 5.577525091171265,
|
|
"epoch": 0.2885900434346809,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004995257569380998,
|
|
"loss": 5.3662,
|
|
"mean_token_accuracy": 0.17813971638679504,
|
|
"num_tokens": 6364052.0,
|
|
"step": 3455
|
|
},
|
|
{
|
|
"entropy": 5.6135517120361325,
|
|
"epoch": 0.2890076845973939,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004995238231211614,
|
|
"loss": 5.4969,
|
|
"mean_token_accuracy": 0.17180268615484237,
|
|
"num_tokens": 6373305.0,
|
|
"step": 3460
|
|
},
|
|
{
|
|
"entropy": 5.55221152305603,
|
|
"epoch": 0.28942532576010693,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004995218853736631,
|
|
"loss": 5.4182,
|
|
"mean_token_accuracy": 0.17001649588346482,
|
|
"num_tokens": 6382673.0,
|
|
"step": 3465
|
|
},
|
|
{
|
|
"entropy": 5.610888242721558,
|
|
"epoch": 0.2898429669228199,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004995199436956391,
|
|
"loss": 5.5342,
|
|
"mean_token_accuracy": 0.16178884655237197,
|
|
"num_tokens": 6392122.0,
|
|
"step": 3470
|
|
},
|
|
{
|
|
"entropy": 5.645338344573974,
|
|
"epoch": 0.2902606080855329,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004995179980871231,
|
|
"loss": 5.5279,
|
|
"mean_token_accuracy": 0.16972028613090515,
|
|
"num_tokens": 6401130.0,
|
|
"step": 3475
|
|
},
|
|
{
|
|
"entropy": 5.632619428634643,
|
|
"epoch": 0.2906782492482459,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004995160485481493,
|
|
"loss": 5.4099,
|
|
"mean_token_accuracy": 0.16997333168983458,
|
|
"num_tokens": 6409471.0,
|
|
"step": 3480
|
|
},
|
|
{
|
|
"entropy": 5.522201681137085,
|
|
"epoch": 0.2910958904109589,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.000499514095078752,
|
|
"loss": 5.412,
|
|
"mean_token_accuracy": 0.17568757086992265,
|
|
"num_tokens": 6418902.0,
|
|
"step": 3485
|
|
},
|
|
{
|
|
"entropy": 5.629268074035645,
|
|
"epoch": 0.2915135315736719,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.000499512137678965,
|
|
"loss": 5.5067,
|
|
"mean_token_accuracy": 0.17458643913269042,
|
|
"num_tokens": 6428529.0,
|
|
"step": 3490
|
|
},
|
|
{
|
|
"entropy": 5.6039900302886965,
|
|
"epoch": 0.2919311727363849,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004995101763488229,
|
|
"loss": 5.3625,
|
|
"mean_token_accuracy": 0.176267609000206,
|
|
"num_tokens": 6437460.0,
|
|
"step": 3495
|
|
},
|
|
{
|
|
"entropy": 5.541733264923096,
|
|
"epoch": 0.2923488138990979,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004995082110883599,
|
|
"loss": 5.4092,
|
|
"mean_token_accuracy": 0.17792665511369704,
|
|
"num_tokens": 6446005.0,
|
|
"step": 3500
|
|
},
|
|
{
|
|
"entropy": 5.528889799118042,
|
|
"epoch": 0.29276645506181087,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004995062418976104,
|
|
"loss": 5.4607,
|
|
"mean_token_accuracy": 0.1745197594165802,
|
|
"num_tokens": 6455241.0,
|
|
"step": 3505
|
|
},
|
|
{
|
|
"entropy": 5.619756650924683,
|
|
"epoch": 0.2931840962245239,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004995042687766089,
|
|
"loss": 5.4288,
|
|
"mean_token_accuracy": 0.17538372576236724,
|
|
"num_tokens": 6464748.0,
|
|
"step": 3510
|
|
},
|
|
{
|
|
"entropy": 5.5280955791473385,
|
|
"epoch": 0.2936017373872369,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004995022917253899,
|
|
"loss": 5.4933,
|
|
"mean_token_accuracy": 0.18021770864725112,
|
|
"num_tokens": 6473834.0,
|
|
"step": 3515
|
|
},
|
|
{
|
|
"entropy": 5.5699669361114506,
|
|
"epoch": 0.29401937854994986,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004995003107439882,
|
|
"loss": 5.4346,
|
|
"mean_token_accuracy": 0.17709693014621736,
|
|
"num_tokens": 6482169.0,
|
|
"step": 3520
|
|
},
|
|
{
|
|
"entropy": 5.53997220993042,
|
|
"epoch": 0.2944370197126629,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004994983258324383,
|
|
"loss": 5.3787,
|
|
"mean_token_accuracy": 0.17743246406316757,
|
|
"num_tokens": 6491798.0,
|
|
"step": 3525
|
|
},
|
|
{
|
|
"entropy": 5.479582118988037,
|
|
"epoch": 0.2948546608753759,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004994963369907748,
|
|
"loss": 5.3236,
|
|
"mean_token_accuracy": 0.17699272483587264,
|
|
"num_tokens": 6500143.0,
|
|
"step": 3530
|
|
},
|
|
{
|
|
"entropy": 5.462062168121338,
|
|
"epoch": 0.29527230203808885,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004994943442190328,
|
|
"loss": 5.4531,
|
|
"mean_token_accuracy": 0.17053767442703247,
|
|
"num_tokens": 6509745.0,
|
|
"step": 3535
|
|
},
|
|
{
|
|
"entropy": 5.67592306137085,
|
|
"epoch": 0.2956899432008019,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004994923475172471,
|
|
"loss": 5.5242,
|
|
"mean_token_accuracy": 0.17168646901845933,
|
|
"num_tokens": 6520931.0,
|
|
"step": 3540
|
|
},
|
|
{
|
|
"entropy": 5.62648639678955,
|
|
"epoch": 0.29610758436351486,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004994903468854527,
|
|
"loss": 5.4493,
|
|
"mean_token_accuracy": 0.17539601027965546,
|
|
"num_tokens": 6529774.0,
|
|
"step": 3545
|
|
},
|
|
{
|
|
"entropy": 5.461532068252564,
|
|
"epoch": 0.29652522552622784,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004994883423236843,
|
|
"loss": 5.3806,
|
|
"mean_token_accuracy": 0.17293752282857894,
|
|
"num_tokens": 6538922.0,
|
|
"step": 3550
|
|
},
|
|
{
|
|
"entropy": 5.513239145278931,
|
|
"epoch": 0.2969428666889409,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004994863338319775,
|
|
"loss": 5.4286,
|
|
"mean_token_accuracy": 0.17735143154859542,
|
|
"num_tokens": 6548891.0,
|
|
"step": 3555
|
|
},
|
|
{
|
|
"entropy": 5.494573307037354,
|
|
"epoch": 0.29736050785165385,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004994843214103672,
|
|
"loss": 5.2551,
|
|
"mean_token_accuracy": 0.1761169984936714,
|
|
"num_tokens": 6557025.0,
|
|
"step": 3560
|
|
},
|
|
{
|
|
"entropy": 5.584866857528686,
|
|
"epoch": 0.29777814901436683,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004994823050588886,
|
|
"loss": 5.4271,
|
|
"mean_token_accuracy": 0.17514524310827256,
|
|
"num_tokens": 6567037.0,
|
|
"step": 3565
|
|
},
|
|
{
|
|
"entropy": 5.555587720870972,
|
|
"epoch": 0.29819579017707987,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000499480284777577,
|
|
"loss": 5.4629,
|
|
"mean_token_accuracy": 0.17471245378255845,
|
|
"num_tokens": 6576766.0,
|
|
"step": 3570
|
|
},
|
|
{
|
|
"entropy": 5.570872449874878,
|
|
"epoch": 0.29861343133979285,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004994782605664677,
|
|
"loss": 5.4362,
|
|
"mean_token_accuracy": 0.17735102772712708,
|
|
"num_tokens": 6585576.0,
|
|
"step": 3575
|
|
},
|
|
{
|
|
"entropy": 5.596178579330444,
|
|
"epoch": 0.2990310725025058,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004994762324255965,
|
|
"loss": 5.4857,
|
|
"mean_token_accuracy": 0.17427317202091216,
|
|
"num_tokens": 6594463.0,
|
|
"step": 3580
|
|
},
|
|
{
|
|
"entropy": 5.566938352584839,
|
|
"epoch": 0.29944871366521886,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004994742003549986,
|
|
"loss": 5.3677,
|
|
"mean_token_accuracy": 0.17447261214256288,
|
|
"num_tokens": 6603651.0,
|
|
"step": 3585
|
|
},
|
|
{
|
|
"entropy": 5.614844465255738,
|
|
"epoch": 0.29986635482793184,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004994721643547095,
|
|
"loss": 5.4392,
|
|
"mean_token_accuracy": 0.1780633106827736,
|
|
"num_tokens": 6612950.0,
|
|
"step": 3590
|
|
},
|
|
{
|
|
"entropy": 5.601415967941284,
|
|
"epoch": 0.3002839959906448,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000499470124424765,
|
|
"loss": 5.3823,
|
|
"mean_token_accuracy": 0.17879820615053177,
|
|
"num_tokens": 6622013.0,
|
|
"step": 3595
|
|
},
|
|
{
|
|
"entropy": 5.552940416336059,
|
|
"epoch": 0.30070163715335785,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004994680805652008,
|
|
"loss": 5.4592,
|
|
"mean_token_accuracy": 0.1763960376381874,
|
|
"num_tokens": 6632046.0,
|
|
"step": 3600
|
|
},
|
|
{
|
|
"entropy": 5.561949300765991,
|
|
"epoch": 0.3011192783160708,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004994660327760527,
|
|
"loss": 5.5006,
|
|
"mean_token_accuracy": 0.17833555936813356,
|
|
"num_tokens": 6641169.0,
|
|
"step": 3605
|
|
},
|
|
{
|
|
"entropy": 5.555380964279175,
|
|
"epoch": 0.3015369194787838,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004994639810573565,
|
|
"loss": 5.3107,
|
|
"mean_token_accuracy": 0.18665722012519836,
|
|
"num_tokens": 6649663.0,
|
|
"step": 3610
|
|
},
|
|
{
|
|
"entropy": 5.624287843704224,
|
|
"epoch": 0.30195456064149684,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000499461925409148,
|
|
"loss": 5.5101,
|
|
"mean_token_accuracy": 0.17178054600954057,
|
|
"num_tokens": 6659448.0,
|
|
"step": 3615
|
|
},
|
|
{
|
|
"entropy": 5.6389318943023685,
|
|
"epoch": 0.3023722018042098,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004994598658314634,
|
|
"loss": 5.4612,
|
|
"mean_token_accuracy": 0.1729240134358406,
|
|
"num_tokens": 6670314.0,
|
|
"step": 3620
|
|
},
|
|
{
|
|
"entropy": 5.569744968414307,
|
|
"epoch": 0.3027898429669228,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004994578023243386,
|
|
"loss": 5.4028,
|
|
"mean_token_accuracy": 0.1818447932600975,
|
|
"num_tokens": 6679413.0,
|
|
"step": 3625
|
|
},
|
|
{
|
|
"entropy": 5.564968490600586,
|
|
"epoch": 0.30320748412963583,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004994557348878098,
|
|
"loss": 5.3927,
|
|
"mean_token_accuracy": 0.1806464374065399,
|
|
"num_tokens": 6688439.0,
|
|
"step": 3630
|
|
},
|
|
{
|
|
"entropy": 5.524420499801636,
|
|
"epoch": 0.3036251252923488,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004994536635219133,
|
|
"loss": 5.3662,
|
|
"mean_token_accuracy": 0.1851886883378029,
|
|
"num_tokens": 6697471.0,
|
|
"step": 3635
|
|
},
|
|
{
|
|
"entropy": 5.583075618743896,
|
|
"epoch": 0.3040427664550618,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004994515882266852,
|
|
"loss": 5.4185,
|
|
"mean_token_accuracy": 0.17669300734996796,
|
|
"num_tokens": 6706698.0,
|
|
"step": 3640
|
|
},
|
|
{
|
|
"entropy": 5.51670651435852,
|
|
"epoch": 0.3044604076177748,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004994495090021618,
|
|
"loss": 5.3535,
|
|
"mean_token_accuracy": 0.18122815787792207,
|
|
"num_tokens": 6715676.0,
|
|
"step": 3645
|
|
},
|
|
{
|
|
"entropy": 5.459908151626587,
|
|
"epoch": 0.3048780487804878,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004994474258483796,
|
|
"loss": 5.3835,
|
|
"mean_token_accuracy": 0.18140835911035538,
|
|
"num_tokens": 6723818.0,
|
|
"step": 3650
|
|
},
|
|
{
|
|
"entropy": 5.5700725555419925,
|
|
"epoch": 0.3052956899432008,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004994453387653751,
|
|
"loss": 5.4033,
|
|
"mean_token_accuracy": 0.17778776735067367,
|
|
"num_tokens": 6733450.0,
|
|
"step": 3655
|
|
},
|
|
{
|
|
"entropy": 5.564090013504028,
|
|
"epoch": 0.3057133311059138,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004994432477531847,
|
|
"loss": 5.3523,
|
|
"mean_token_accuracy": 0.1764783501625061,
|
|
"num_tokens": 6743142.0,
|
|
"step": 3660
|
|
},
|
|
{
|
|
"entropy": 5.472638511657715,
|
|
"epoch": 0.3061309722686268,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004994411528118452,
|
|
"loss": 5.3028,
|
|
"mean_token_accuracy": 0.17945352643728257,
|
|
"num_tokens": 6752185.0,
|
|
"step": 3665
|
|
},
|
|
{
|
|
"entropy": 5.502836799621582,
|
|
"epoch": 0.30654861343133977,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004994390539413931,
|
|
"loss": 5.4086,
|
|
"mean_token_accuracy": 0.1835372507572174,
|
|
"num_tokens": 6761549.0,
|
|
"step": 3670
|
|
},
|
|
{
|
|
"entropy": 5.536188411712646,
|
|
"epoch": 0.3069662545940528,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004994369511418652,
|
|
"loss": 5.4247,
|
|
"mean_token_accuracy": 0.17736767381429672,
|
|
"num_tokens": 6770395.0,
|
|
"step": 3675
|
|
},
|
|
{
|
|
"entropy": 5.645047044754028,
|
|
"epoch": 0.3073838957567658,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004994348444132983,
|
|
"loss": 5.4952,
|
|
"mean_token_accuracy": 0.17320885211229325,
|
|
"num_tokens": 6779154.0,
|
|
"step": 3680
|
|
},
|
|
{
|
|
"entropy": 5.490355920791626,
|
|
"epoch": 0.30780153691947876,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004994327337557293,
|
|
"loss": 5.3789,
|
|
"mean_token_accuracy": 0.1852697342634201,
|
|
"num_tokens": 6789263.0,
|
|
"step": 3685
|
|
},
|
|
{
|
|
"entropy": 5.555096244812011,
|
|
"epoch": 0.3082191780821918,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004994306191691952,
|
|
"loss": 5.4717,
|
|
"mean_token_accuracy": 0.17230480462312697,
|
|
"num_tokens": 6797985.0,
|
|
"step": 3690
|
|
},
|
|
{
|
|
"entropy": 5.54058609008789,
|
|
"epoch": 0.30863681924490477,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004994285006537329,
|
|
"loss": 5.3673,
|
|
"mean_token_accuracy": 0.17717754542827607,
|
|
"num_tokens": 6807566.0,
|
|
"step": 3695
|
|
},
|
|
{
|
|
"entropy": 5.4808722019195555,
|
|
"epoch": 0.30905446040761775,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004994263782093796,
|
|
"loss": 5.3947,
|
|
"mean_token_accuracy": 0.17707190960645675,
|
|
"num_tokens": 6815637.0,
|
|
"step": 3700
|
|
},
|
|
{
|
|
"entropy": 5.525970315933227,
|
|
"epoch": 0.3094721015703308,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004994242518361723,
|
|
"loss": 5.2836,
|
|
"mean_token_accuracy": 0.18263801634311677,
|
|
"num_tokens": 6823721.0,
|
|
"step": 3705
|
|
},
|
|
{
|
|
"entropy": 5.606603193283081,
|
|
"epoch": 0.30988974273304376,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004994221215341484,
|
|
"loss": 5.458,
|
|
"mean_token_accuracy": 0.17419039607048034,
|
|
"num_tokens": 6833437.0,
|
|
"step": 3710
|
|
},
|
|
{
|
|
"entropy": 5.537316417694091,
|
|
"epoch": 0.31030738389575674,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004994199873033452,
|
|
"loss": 5.5149,
|
|
"mean_token_accuracy": 0.17269643843173982,
|
|
"num_tokens": 6842287.0,
|
|
"step": 3715
|
|
},
|
|
{
|
|
"entropy": 5.642424583435059,
|
|
"epoch": 0.3107250250584698,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004994178491437999,
|
|
"loss": 5.3587,
|
|
"mean_token_accuracy": 0.17185903638601302,
|
|
"num_tokens": 6851520.0,
|
|
"step": 3720
|
|
},
|
|
{
|
|
"entropy": 5.519375514984131,
|
|
"epoch": 0.31114266622118275,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004994157070555501,
|
|
"loss": 5.4082,
|
|
"mean_token_accuracy": 0.17950767874717713,
|
|
"num_tokens": 6861219.0,
|
|
"step": 3725
|
|
},
|
|
{
|
|
"entropy": 5.587158298492431,
|
|
"epoch": 0.31156030738389573,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004994135610386331,
|
|
"loss": 5.5369,
|
|
"mean_token_accuracy": 0.1727735862135887,
|
|
"num_tokens": 6870525.0,
|
|
"step": 3730
|
|
},
|
|
{
|
|
"entropy": 5.62889609336853,
|
|
"epoch": 0.31197794854660876,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004994114110930867,
|
|
"loss": 5.4523,
|
|
"mean_token_accuracy": 0.17412902265787125,
|
|
"num_tokens": 6880183.0,
|
|
"step": 3735
|
|
},
|
|
{
|
|
"entropy": 5.539847660064697,
|
|
"epoch": 0.31239558970932174,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004994092572189483,
|
|
"loss": 5.5036,
|
|
"mean_token_accuracy": 0.1694844126701355,
|
|
"num_tokens": 6890442.0,
|
|
"step": 3740
|
|
},
|
|
{
|
|
"entropy": 5.562208604812622,
|
|
"epoch": 0.3128132308720348,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004994070994162558,
|
|
"loss": 5.4078,
|
|
"mean_token_accuracy": 0.17751166224479675,
|
|
"num_tokens": 6900091.0,
|
|
"step": 3745
|
|
},
|
|
{
|
|
"entropy": 5.536312770843506,
|
|
"epoch": 0.31323087203474775,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004994049376850471,
|
|
"loss": 5.4316,
|
|
"mean_token_accuracy": 0.17668322771787642,
|
|
"num_tokens": 6910489.0,
|
|
"step": 3750
|
|
},
|
|
{
|
|
"entropy": 5.551783609390259,
|
|
"epoch": 0.31364851319746073,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004994027720253596,
|
|
"loss": 5.4223,
|
|
"mean_token_accuracy": 0.17174892127513885,
|
|
"num_tokens": 6919895.0,
|
|
"step": 3755
|
|
},
|
|
{
|
|
"entropy": 5.688577699661255,
|
|
"epoch": 0.31406615436017377,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004994006024372315,
|
|
"loss": 5.5632,
|
|
"mean_token_accuracy": 0.16963823288679122,
|
|
"num_tokens": 6929511.0,
|
|
"step": 3760
|
|
},
|
|
{
|
|
"entropy": 5.503642606735229,
|
|
"epoch": 0.31448379552288674,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004993984289207007,
|
|
"loss": 5.3159,
|
|
"mean_token_accuracy": 0.18278757035732268,
|
|
"num_tokens": 6938059.0,
|
|
"step": 3765
|
|
},
|
|
{
|
|
"entropy": 5.518787288665772,
|
|
"epoch": 0.3149014366855997,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004993962514758054,
|
|
"loss": 5.3483,
|
|
"mean_token_accuracy": 0.17641351968050004,
|
|
"num_tokens": 6946894.0,
|
|
"step": 3770
|
|
},
|
|
{
|
|
"entropy": 5.626014232635498,
|
|
"epoch": 0.31531907784831276,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004993940701025836,
|
|
"loss": 5.3605,
|
|
"mean_token_accuracy": 0.16906849294900894,
|
|
"num_tokens": 6955494.0,
|
|
"step": 3775
|
|
},
|
|
{
|
|
"entropy": 5.480310583114624,
|
|
"epoch": 0.31573671901102573,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004993918848010734,
|
|
"loss": 5.4729,
|
|
"mean_token_accuracy": 0.1719732776284218,
|
|
"num_tokens": 6964347.0,
|
|
"step": 3780
|
|
},
|
|
{
|
|
"entropy": 5.579901552200317,
|
|
"epoch": 0.3161543601737387,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004993896955713133,
|
|
"loss": 5.4279,
|
|
"mean_token_accuracy": 0.17163396626710892,
|
|
"num_tokens": 6974750.0,
|
|
"step": 3785
|
|
},
|
|
{
|
|
"entropy": 5.583578824996948,
|
|
"epoch": 0.31657200133645175,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004993875024133414,
|
|
"loss": 5.4291,
|
|
"mean_token_accuracy": 0.17758399695158006,
|
|
"num_tokens": 6984228.0,
|
|
"step": 3790
|
|
},
|
|
{
|
|
"entropy": 5.4850465774536135,
|
|
"epoch": 0.3169896424991647,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004993853053271962,
|
|
"loss": 5.4105,
|
|
"mean_token_accuracy": 0.17856047451496124,
|
|
"num_tokens": 6993173.0,
|
|
"step": 3795
|
|
},
|
|
{
|
|
"entropy": 5.710829591751098,
|
|
"epoch": 0.3174072836618777,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004993831043129161,
|
|
"loss": 5.6112,
|
|
"mean_token_accuracy": 0.16447764188051223,
|
|
"num_tokens": 7003486.0,
|
|
"step": 3800
|
|
},
|
|
{
|
|
"entropy": 5.51308650970459,
|
|
"epoch": 0.31782492482459074,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004993808993705397,
|
|
"loss": 5.3517,
|
|
"mean_token_accuracy": 0.18299903422594072,
|
|
"num_tokens": 7011985.0,
|
|
"step": 3805
|
|
},
|
|
{
|
|
"entropy": 5.504875659942627,
|
|
"epoch": 0.3182425659873037,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004993786905001055,
|
|
"loss": 5.3119,
|
|
"mean_token_accuracy": 0.18059561103582383,
|
|
"num_tokens": 7021148.0,
|
|
"step": 3810
|
|
},
|
|
{
|
|
"entropy": 5.495862054824829,
|
|
"epoch": 0.3186602071500167,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004993764777016524,
|
|
"loss": 5.3649,
|
|
"mean_token_accuracy": 0.17798255681991576,
|
|
"num_tokens": 7030110.0,
|
|
"step": 3815
|
|
},
|
|
{
|
|
"entropy": 5.584918355941772,
|
|
"epoch": 0.31907784831272973,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004993742609752188,
|
|
"loss": 5.4413,
|
|
"mean_token_accuracy": 0.18019713163375856,
|
|
"num_tokens": 7039428.0,
|
|
"step": 3820
|
|
},
|
|
{
|
|
"entropy": 5.676028394699097,
|
|
"epoch": 0.3194954894754427,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004993720403208438,
|
|
"loss": 5.5038,
|
|
"mean_token_accuracy": 0.17248591482639314,
|
|
"num_tokens": 7048703.0,
|
|
"step": 3825
|
|
},
|
|
{
|
|
"entropy": 5.5341957092285154,
|
|
"epoch": 0.3199131306381557,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000499369815738566,
|
|
"loss": 5.4036,
|
|
"mean_token_accuracy": 0.1700318157672882,
|
|
"num_tokens": 7057612.0,
|
|
"step": 3830
|
|
},
|
|
{
|
|
"entropy": 5.555621862411499,
|
|
"epoch": 0.3203307718008687,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004993675872284248,
|
|
"loss": 5.3607,
|
|
"mean_token_accuracy": 0.1777009814977646,
|
|
"num_tokens": 7066660.0,
|
|
"step": 3835
|
|
},
|
|
{
|
|
"entropy": 5.485004472732544,
|
|
"epoch": 0.3207484129635817,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004993653547904586,
|
|
"loss": 5.3339,
|
|
"mean_token_accuracy": 0.17354484349489213,
|
|
"num_tokens": 7075368.0,
|
|
"step": 3840
|
|
},
|
|
{
|
|
"entropy": 5.51584267616272,
|
|
"epoch": 0.3211660541262947,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.000499363118424707,
|
|
"loss": 5.4376,
|
|
"mean_token_accuracy": 0.18095694333314896,
|
|
"num_tokens": 7085276.0,
|
|
"step": 3845
|
|
},
|
|
{
|
|
"entropy": 5.539682483673095,
|
|
"epoch": 0.3215836952890077,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004993608781312088,
|
|
"loss": 5.3994,
|
|
"mean_token_accuracy": 0.1757436066865921,
|
|
"num_tokens": 7094292.0,
|
|
"step": 3850
|
|
},
|
|
{
|
|
"entropy": 5.664052057266235,
|
|
"epoch": 0.3220013364517207,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004993586339100035,
|
|
"loss": 5.6208,
|
|
"mean_token_accuracy": 0.16767174154520034,
|
|
"num_tokens": 7104712.0,
|
|
"step": 3855
|
|
},
|
|
{
|
|
"entropy": 5.6224799156188965,
|
|
"epoch": 0.32241897761443367,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004993563857611301,
|
|
"loss": 5.4174,
|
|
"mean_token_accuracy": 0.1841977894306183,
|
|
"num_tokens": 7113297.0,
|
|
"step": 3860
|
|
},
|
|
{
|
|
"entropy": 5.480200672149659,
|
|
"epoch": 0.3228366187771467,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004993541336846283,
|
|
"loss": 5.4335,
|
|
"mean_token_accuracy": 0.16748614832758904,
|
|
"num_tokens": 7122706.0,
|
|
"step": 3865
|
|
},
|
|
{
|
|
"entropy": 5.542711400985718,
|
|
"epoch": 0.3232542599398597,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004993518776805372,
|
|
"loss": 5.3907,
|
|
"mean_token_accuracy": 0.17922770231962204,
|
|
"num_tokens": 7131939.0,
|
|
"step": 3870
|
|
},
|
|
{
|
|
"entropy": 5.451107168197632,
|
|
"epoch": 0.32367190110257266,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004993496177488965,
|
|
"loss": 5.2662,
|
|
"mean_token_accuracy": 0.18536351174116134,
|
|
"num_tokens": 7141016.0,
|
|
"step": 3875
|
|
},
|
|
{
|
|
"entropy": 5.463331985473633,
|
|
"epoch": 0.3240895422652857,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004993473538897457,
|
|
"loss": 5.2199,
|
|
"mean_token_accuracy": 0.1908682778477669,
|
|
"num_tokens": 7149177.0,
|
|
"step": 3880
|
|
},
|
|
{
|
|
"entropy": 5.517989921569824,
|
|
"epoch": 0.32450718342799867,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004993450861031243,
|
|
"loss": 5.3559,
|
|
"mean_token_accuracy": 0.1834622472524643,
|
|
"num_tokens": 7157839.0,
|
|
"step": 3885
|
|
},
|
|
{
|
|
"entropy": 5.61125168800354,
|
|
"epoch": 0.32492482459071165,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004993428143890722,
|
|
"loss": 5.4994,
|
|
"mean_token_accuracy": 0.17009637653827667,
|
|
"num_tokens": 7167759.0,
|
|
"step": 3890
|
|
},
|
|
{
|
|
"entropy": 5.6287397861480715,
|
|
"epoch": 0.3253424657534247,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004993405387476291,
|
|
"loss": 5.4309,
|
|
"mean_token_accuracy": 0.16932940483093262,
|
|
"num_tokens": 7177141.0,
|
|
"step": 3895
|
|
},
|
|
{
|
|
"entropy": 5.4610847473144535,
|
|
"epoch": 0.32576010691613766,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004993382591788349,
|
|
"loss": 5.3484,
|
|
"mean_token_accuracy": 0.18480813056230544,
|
|
"num_tokens": 7185350.0,
|
|
"step": 3900
|
|
},
|
|
{
|
|
"entropy": 5.475749492645264,
|
|
"epoch": 0.32617774807885064,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004993359756827293,
|
|
"loss": 5.2774,
|
|
"mean_token_accuracy": 0.18510581254959108,
|
|
"num_tokens": 7194073.0,
|
|
"step": 3905
|
|
},
|
|
{
|
|
"entropy": 5.570122957229614,
|
|
"epoch": 0.32659538924156367,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004993336882593524,
|
|
"loss": 5.4658,
|
|
"mean_token_accuracy": 0.17096367180347444,
|
|
"num_tokens": 7203421.0,
|
|
"step": 3910
|
|
},
|
|
{
|
|
"entropy": 5.504409551620483,
|
|
"epoch": 0.32701303040427665,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004993313969087444,
|
|
"loss": 5.2325,
|
|
"mean_token_accuracy": 0.18367886990308763,
|
|
"num_tokens": 7212548.0,
|
|
"step": 3915
|
|
},
|
|
{
|
|
"entropy": 5.52297306060791,
|
|
"epoch": 0.32743067156698963,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004993291016309452,
|
|
"loss": 5.4708,
|
|
"mean_token_accuracy": 0.17318004965782166,
|
|
"num_tokens": 7221668.0,
|
|
"step": 3920
|
|
},
|
|
{
|
|
"entropy": 5.530381393432617,
|
|
"epoch": 0.32784831272970266,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000499326802425995,
|
|
"loss": 5.3636,
|
|
"mean_token_accuracy": 0.1767316937446594,
|
|
"num_tokens": 7231775.0,
|
|
"step": 3925
|
|
},
|
|
{
|
|
"entropy": 5.599203157424927,
|
|
"epoch": 0.32826595389241564,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004993244992939342,
|
|
"loss": 5.4185,
|
|
"mean_token_accuracy": 0.1742442861199379,
|
|
"num_tokens": 7241264.0,
|
|
"step": 3930
|
|
},
|
|
{
|
|
"entropy": 5.563284158706665,
|
|
"epoch": 0.3286835950551286,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000499322192234803,
|
|
"loss": 5.4255,
|
|
"mean_token_accuracy": 0.17522766590118408,
|
|
"num_tokens": 7250519.0,
|
|
"step": 3935
|
|
},
|
|
{
|
|
"entropy": 5.653376913070678,
|
|
"epoch": 0.32910123621784165,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004993198812486418,
|
|
"loss": 5.4749,
|
|
"mean_token_accuracy": 0.17463890612125396,
|
|
"num_tokens": 7259533.0,
|
|
"step": 3940
|
|
},
|
|
{
|
|
"entropy": 5.504630088806152,
|
|
"epoch": 0.32951887738055463,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.000499317566335491,
|
|
"loss": 5.3,
|
|
"mean_token_accuracy": 0.17634646892547606,
|
|
"num_tokens": 7268980.0,
|
|
"step": 3945
|
|
},
|
|
{
|
|
"entropy": 5.512438726425171,
|
|
"epoch": 0.3299365185432676,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004993152474953913,
|
|
"loss": 5.4041,
|
|
"mean_token_accuracy": 0.18160206824541092,
|
|
"num_tokens": 7277126.0,
|
|
"step": 3950
|
|
},
|
|
{
|
|
"entropy": 5.56659083366394,
|
|
"epoch": 0.33035415970598064,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004993129247283831,
|
|
"loss": 5.3623,
|
|
"mean_token_accuracy": 0.18333873450756072,
|
|
"num_tokens": 7286223.0,
|
|
"step": 3955
|
|
},
|
|
{
|
|
"entropy": 5.548340320587158,
|
|
"epoch": 0.3307718008686936,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004993105980345071,
|
|
"loss": 5.3752,
|
|
"mean_token_accuracy": 0.1801811933517456,
|
|
"num_tokens": 7295054.0,
|
|
"step": 3960
|
|
},
|
|
{
|
|
"entropy": 5.519936227798462,
|
|
"epoch": 0.3311894420314066,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004993082674138042,
|
|
"loss": 5.4018,
|
|
"mean_token_accuracy": 0.17907965779304505,
|
|
"num_tokens": 7304502.0,
|
|
"step": 3965
|
|
},
|
|
{
|
|
"entropy": 5.548730421066284,
|
|
"epoch": 0.33160708319411963,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.000499305932866315,
|
|
"loss": 5.3661,
|
|
"mean_token_accuracy": 0.17640268206596374,
|
|
"num_tokens": 7314093.0,
|
|
"step": 3970
|
|
},
|
|
{
|
|
"entropy": 5.584903287887573,
|
|
"epoch": 0.3320247243568326,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004993035943920805,
|
|
"loss": 5.3959,
|
|
"mean_token_accuracy": 0.17537485361099242,
|
|
"num_tokens": 7323059.0,
|
|
"step": 3975
|
|
},
|
|
{
|
|
"entropy": 5.633094596862793,
|
|
"epoch": 0.3324423655195456,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004993012519911416,
|
|
"loss": 5.5284,
|
|
"mean_token_accuracy": 0.17066334784030915,
|
|
"num_tokens": 7332596.0,
|
|
"step": 3980
|
|
},
|
|
{
|
|
"entropy": 5.542002010345459,
|
|
"epoch": 0.3328600066822586,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004992989056635392,
|
|
"loss": 5.3302,
|
|
"mean_token_accuracy": 0.1828303039073944,
|
|
"num_tokens": 7341671.0,
|
|
"step": 3985
|
|
},
|
|
{
|
|
"entropy": 5.49449462890625,
|
|
"epoch": 0.3332776478449716,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004992965554093146,
|
|
"loss": 5.4482,
|
|
"mean_token_accuracy": 0.17449371218681337,
|
|
"num_tokens": 7350344.0,
|
|
"step": 3990
|
|
},
|
|
{
|
|
"entropy": 5.5837198257446286,
|
|
"epoch": 0.3336952890076846,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004992942012285086,
|
|
"loss": 5.4578,
|
|
"mean_token_accuracy": 0.1801720902323723,
|
|
"num_tokens": 7359844.0,
|
|
"step": 3995
|
|
},
|
|
{
|
|
"entropy": 5.56695442199707,
|
|
"epoch": 0.3341129301703976,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004992918431211629,
|
|
"loss": 5.3852,
|
|
"mean_token_accuracy": 0.17716051787137985,
|
|
"num_tokens": 7369377.0,
|
|
"step": 4000
|
|
},
|
|
{
|
|
"entropy": 5.542109727859497,
|
|
"epoch": 0.3345305713331106,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004992894810873183,
|
|
"loss": 5.3539,
|
|
"mean_token_accuracy": 0.17548734098672866,
|
|
"num_tokens": 7378814.0,
|
|
"step": 4005
|
|
},
|
|
{
|
|
"entropy": 5.4964337825775145,
|
|
"epoch": 0.33494821249582357,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004992871151270165,
|
|
"loss": 5.3576,
|
|
"mean_token_accuracy": 0.18033732622861862,
|
|
"num_tokens": 7387333.0,
|
|
"step": 4010
|
|
},
|
|
{
|
|
"entropy": 5.4655951976776125,
|
|
"epoch": 0.3353658536585366,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004992847452402986,
|
|
"loss": 5.3957,
|
|
"mean_token_accuracy": 0.180501726269722,
|
|
"num_tokens": 7396895.0,
|
|
"step": 4015
|
|
},
|
|
{
|
|
"entropy": 5.518776273727417,
|
|
"epoch": 0.3357834948212496,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004992823714272064,
|
|
"loss": 5.3837,
|
|
"mean_token_accuracy": 0.17895213067531585,
|
|
"num_tokens": 7406430.0,
|
|
"step": 4020
|
|
},
|
|
{
|
|
"entropy": 5.536636161804199,
|
|
"epoch": 0.33620113598396256,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004992799936877813,
|
|
"loss": 5.2343,
|
|
"mean_token_accuracy": 0.18902939856052398,
|
|
"num_tokens": 7415224.0,
|
|
"step": 4025
|
|
},
|
|
{
|
|
"entropy": 5.588719654083252,
|
|
"epoch": 0.3366187771466756,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004992776120220649,
|
|
"loss": 5.5551,
|
|
"mean_token_accuracy": 0.16299639493227006,
|
|
"num_tokens": 7424250.0,
|
|
"step": 4030
|
|
},
|
|
{
|
|
"entropy": 5.586339092254638,
|
|
"epoch": 0.3370364183093886,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004992752264300989,
|
|
"loss": 5.3824,
|
|
"mean_token_accuracy": 0.18631240874528884,
|
|
"num_tokens": 7433579.0,
|
|
"step": 4035
|
|
},
|
|
{
|
|
"entropy": 5.4758015155792235,
|
|
"epoch": 0.33745405947210155,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004992728369119252,
|
|
"loss": 5.3442,
|
|
"mean_token_accuracy": 0.18162791579961776,
|
|
"num_tokens": 7442621.0,
|
|
"step": 4040
|
|
},
|
|
{
|
|
"entropy": 5.571116495132446,
|
|
"epoch": 0.3378717006348146,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004992704434675855,
|
|
"loss": 5.4374,
|
|
"mean_token_accuracy": 0.17829461991786957,
|
|
"num_tokens": 7452077.0,
|
|
"step": 4045
|
|
},
|
|
{
|
|
"entropy": 5.502327346801758,
|
|
"epoch": 0.33828934179752757,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004992680460971218,
|
|
"loss": 5.3601,
|
|
"mean_token_accuracy": 0.17589134722948074,
|
|
"num_tokens": 7461146.0,
|
|
"step": 4050
|
|
},
|
|
{
|
|
"entropy": 5.419596338272095,
|
|
"epoch": 0.33870698296024054,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004992656448005758,
|
|
"loss": 5.3586,
|
|
"mean_token_accuracy": 0.1813579112291336,
|
|
"num_tokens": 7470335.0,
|
|
"step": 4055
|
|
},
|
|
{
|
|
"entropy": 5.539237070083618,
|
|
"epoch": 0.3391246241229536,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004992632395779899,
|
|
"loss": 5.3328,
|
|
"mean_token_accuracy": 0.17426132410764694,
|
|
"num_tokens": 7479458.0,
|
|
"step": 4060
|
|
},
|
|
{
|
|
"entropy": 5.450229549407959,
|
|
"epoch": 0.33954226528566656,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004992608304294061,
|
|
"loss": 5.3035,
|
|
"mean_token_accuracy": 0.19210376739501953,
|
|
"num_tokens": 7488005.0,
|
|
"step": 4065
|
|
},
|
|
{
|
|
"entropy": 5.420096445083618,
|
|
"epoch": 0.33995990644837953,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004992584173548664,
|
|
"loss": 5.307,
|
|
"mean_token_accuracy": 0.17884953767061235,
|
|
"num_tokens": 7496807.0,
|
|
"step": 4070
|
|
},
|
|
{
|
|
"entropy": 5.509367942810059,
|
|
"epoch": 0.34037754761109257,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004992560003544131,
|
|
"loss": 5.3321,
|
|
"mean_token_accuracy": 0.18723736256361007,
|
|
"num_tokens": 7505383.0,
|
|
"step": 4075
|
|
},
|
|
{
|
|
"entropy": 5.572503232955933,
|
|
"epoch": 0.34079518877380555,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004992535794280887,
|
|
"loss": 5.403,
|
|
"mean_token_accuracy": 0.18027678579092027,
|
|
"num_tokens": 7515093.0,
|
|
"step": 4080
|
|
},
|
|
{
|
|
"entropy": 5.565121698379516,
|
|
"epoch": 0.3412128299365185,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004992511545759354,
|
|
"loss": 5.3847,
|
|
"mean_token_accuracy": 0.17668999135494232,
|
|
"num_tokens": 7524067.0,
|
|
"step": 4085
|
|
},
|
|
{
|
|
"entropy": 5.432730484008789,
|
|
"epoch": 0.34163047109923156,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004992487257979958,
|
|
"loss": 5.3256,
|
|
"mean_token_accuracy": 0.17488196790218352,
|
|
"num_tokens": 7533197.0,
|
|
"step": 4090
|
|
},
|
|
{
|
|
"entropy": 5.5197220802307125,
|
|
"epoch": 0.34204811226194454,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004992462930943123,
|
|
"loss": 5.3318,
|
|
"mean_token_accuracy": 0.17547912299633026,
|
|
"num_tokens": 7543030.0,
|
|
"step": 4095
|
|
},
|
|
{
|
|
"entropy": 5.533311986923218,
|
|
"epoch": 0.3424657534246575,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004992438564649275,
|
|
"loss": 5.3787,
|
|
"mean_token_accuracy": 0.17519449293613434,
|
|
"num_tokens": 7551556.0,
|
|
"step": 4100
|
|
},
|
|
{
|
|
"entropy": 5.507522869110107,
|
|
"epoch": 0.34288339458737055,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004992414159098841,
|
|
"loss": 5.3129,
|
|
"mean_token_accuracy": 0.18167788684368133,
|
|
"num_tokens": 7559284.0,
|
|
"step": 4105
|
|
},
|
|
{
|
|
"entropy": 5.598392963409424,
|
|
"epoch": 0.3433010357500835,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004992389714292247,
|
|
"loss": 5.4277,
|
|
"mean_token_accuracy": 0.17684440910816193,
|
|
"num_tokens": 7568750.0,
|
|
"step": 4110
|
|
},
|
|
{
|
|
"entropy": 5.456853771209717,
|
|
"epoch": 0.3437186769127965,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004992365230229922,
|
|
"loss": 5.2972,
|
|
"mean_token_accuracy": 0.18591678887605667,
|
|
"num_tokens": 7578309.0,
|
|
"step": 4115
|
|
},
|
|
{
|
|
"entropy": 5.43913836479187,
|
|
"epoch": 0.34413631807550954,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004992340706912295,
|
|
"loss": 5.305,
|
|
"mean_token_accuracy": 0.1826748341321945,
|
|
"num_tokens": 7586760.0,
|
|
"step": 4120
|
|
},
|
|
{
|
|
"entropy": 5.465929222106934,
|
|
"epoch": 0.3445539592382225,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004992316144339794,
|
|
"loss": 5.2855,
|
|
"mean_token_accuracy": 0.18348537087440492,
|
|
"num_tokens": 7595472.0,
|
|
"step": 4125
|
|
},
|
|
{
|
|
"entropy": 5.519556903839112,
|
|
"epoch": 0.3449716004009355,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004992291542512852,
|
|
"loss": 5.4731,
|
|
"mean_token_accuracy": 0.16670606136322022,
|
|
"num_tokens": 7605663.0,
|
|
"step": 4130
|
|
},
|
|
{
|
|
"entropy": 5.583035278320312,
|
|
"epoch": 0.34538924156364853,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004992266901431895,
|
|
"loss": 5.3647,
|
|
"mean_token_accuracy": 0.17722720950841903,
|
|
"num_tokens": 7616110.0,
|
|
"step": 4135
|
|
},
|
|
{
|
|
"entropy": 5.491539525985718,
|
|
"epoch": 0.3458068827263615,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004992242221097358,
|
|
"loss": 5.3302,
|
|
"mean_token_accuracy": 0.17768455743789674,
|
|
"num_tokens": 7625311.0,
|
|
"step": 4140
|
|
},
|
|
{
|
|
"entropy": 5.505361318588257,
|
|
"epoch": 0.3462245238890745,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004992217501509672,
|
|
"loss": 5.3432,
|
|
"mean_token_accuracy": 0.18014439195394516,
|
|
"num_tokens": 7634562.0,
|
|
"step": 4145
|
|
},
|
|
{
|
|
"entropy": 5.481019639968872,
|
|
"epoch": 0.3466421650517875,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.000499219274266927,
|
|
"loss": 5.2885,
|
|
"mean_token_accuracy": 0.1800134226679802,
|
|
"num_tokens": 7643231.0,
|
|
"step": 4150
|
|
},
|
|
{
|
|
"entropy": 5.529042339324951,
|
|
"epoch": 0.3470598062145005,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004992167944576584,
|
|
"loss": 5.4271,
|
|
"mean_token_accuracy": 0.1818411871790886,
|
|
"num_tokens": 7653556.0,
|
|
"step": 4155
|
|
},
|
|
{
|
|
"entropy": 5.492344093322754,
|
|
"epoch": 0.3474774473772135,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000499214310723205,
|
|
"loss": 5.326,
|
|
"mean_token_accuracy": 0.18246453553438186,
|
|
"num_tokens": 7662295.0,
|
|
"step": 4160
|
|
},
|
|
{
|
|
"entropy": 5.448925304412842,
|
|
"epoch": 0.3478950885399265,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004992118230636102,
|
|
"loss": 5.3571,
|
|
"mean_token_accuracy": 0.17766649574041365,
|
|
"num_tokens": 7671429.0,
|
|
"step": 4165
|
|
},
|
|
{
|
|
"entropy": 5.467991352081299,
|
|
"epoch": 0.3483127297026395,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004992093314789176,
|
|
"loss": 5.2605,
|
|
"mean_token_accuracy": 0.17754218429327012,
|
|
"num_tokens": 7680589.0,
|
|
"step": 4170
|
|
},
|
|
{
|
|
"entropy": 5.481946563720703,
|
|
"epoch": 0.34873037086535247,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004992068359691707,
|
|
"loss": 5.3027,
|
|
"mean_token_accuracy": 0.18512812107801438,
|
|
"num_tokens": 7689005.0,
|
|
"step": 4175
|
|
},
|
|
{
|
|
"entropy": 5.3886792182922365,
|
|
"epoch": 0.3491480120280655,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004992043365344132,
|
|
"loss": 5.2412,
|
|
"mean_token_accuracy": 0.18713783770799636,
|
|
"num_tokens": 7698231.0,
|
|
"step": 4180
|
|
},
|
|
{
|
|
"entropy": 5.5312230587005615,
|
|
"epoch": 0.3495656531907785,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004992018331746891,
|
|
"loss": 5.3579,
|
|
"mean_token_accuracy": 0.18098943531513215,
|
|
"num_tokens": 7706678.0,
|
|
"step": 4185
|
|
},
|
|
{
|
|
"entropy": 5.573501062393189,
|
|
"epoch": 0.34998329435349146,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004991993258900418,
|
|
"loss": 5.4105,
|
|
"mean_token_accuracy": 0.17862555086612703,
|
|
"num_tokens": 7715506.0,
|
|
"step": 4190
|
|
},
|
|
{
|
|
"entropy": 5.580753660202026,
|
|
"epoch": 0.3504009355162045,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004991968146805156,
|
|
"loss": 5.3785,
|
|
"mean_token_accuracy": 0.1769071564078331,
|
|
"num_tokens": 7726549.0,
|
|
"step": 4195
|
|
},
|
|
{
|
|
"entropy": 5.509833240509034,
|
|
"epoch": 0.35081857667891747,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004991942995461542,
|
|
"loss": 5.4589,
|
|
"mean_token_accuracy": 0.17415786683559417,
|
|
"num_tokens": 7735563.0,
|
|
"step": 4200
|
|
},
|
|
{
|
|
"entropy": 5.561418914794922,
|
|
"epoch": 0.35123621784163045,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004991917804870018,
|
|
"loss": 5.39,
|
|
"mean_token_accuracy": 0.17825252413749695,
|
|
"num_tokens": 7746144.0,
|
|
"step": 4205
|
|
},
|
|
{
|
|
"entropy": 5.515225028991699,
|
|
"epoch": 0.3516538590043435,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004991892575031024,
|
|
"loss": 5.4043,
|
|
"mean_token_accuracy": 0.17637984901666642,
|
|
"num_tokens": 7755394.0,
|
|
"step": 4210
|
|
},
|
|
{
|
|
"entropy": 5.475852298736572,
|
|
"epoch": 0.35207150016705646,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004991867305945001,
|
|
"loss": 5.3548,
|
|
"mean_token_accuracy": 0.18296674489974976,
|
|
"num_tokens": 7764855.0,
|
|
"step": 4215
|
|
},
|
|
{
|
|
"entropy": 5.428618860244751,
|
|
"epoch": 0.35248914132976944,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004991841997612394,
|
|
"loss": 5.2775,
|
|
"mean_token_accuracy": 0.17634298652410507,
|
|
"num_tokens": 7773394.0,
|
|
"step": 4220
|
|
},
|
|
{
|
|
"entropy": 5.527509641647339,
|
|
"epoch": 0.3529067824924825,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004991816650033643,
|
|
"loss": 5.3273,
|
|
"mean_token_accuracy": 0.17990745604038239,
|
|
"num_tokens": 7783111.0,
|
|
"step": 4225
|
|
},
|
|
{
|
|
"entropy": 5.581513357162476,
|
|
"epoch": 0.35332442365519545,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004991791263209194,
|
|
"loss": 5.4648,
|
|
"mean_token_accuracy": 0.17874054461717606,
|
|
"num_tokens": 7792569.0,
|
|
"step": 4230
|
|
},
|
|
{
|
|
"entropy": 5.539682054519654,
|
|
"epoch": 0.35374206481790843,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004991765837139491,
|
|
"loss": 5.3638,
|
|
"mean_token_accuracy": 0.1848058208823204,
|
|
"num_tokens": 7801483.0,
|
|
"step": 4235
|
|
},
|
|
{
|
|
"entropy": 5.5473864555358885,
|
|
"epoch": 0.35415970598062146,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004991740371824977,
|
|
"loss": 5.475,
|
|
"mean_token_accuracy": 0.17225684374570846,
|
|
"num_tokens": 7812274.0,
|
|
"step": 4240
|
|
},
|
|
{
|
|
"entropy": 5.444568729400634,
|
|
"epoch": 0.35457734714333444,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00049917148672661,
|
|
"loss": 5.308,
|
|
"mean_token_accuracy": 0.18026846498250962,
|
|
"num_tokens": 7821101.0,
|
|
"step": 4245
|
|
},
|
|
{
|
|
"entropy": 5.5830871105194095,
|
|
"epoch": 0.3549949883060474,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004991689323463306,
|
|
"loss": 5.278,
|
|
"mean_token_accuracy": 0.18820747584104539,
|
|
"num_tokens": 7829805.0,
|
|
"step": 4250
|
|
},
|
|
{
|
|
"entropy": 5.527326202392578,
|
|
"epoch": 0.35541262946876045,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004991663740417042,
|
|
"loss": 5.3897,
|
|
"mean_token_accuracy": 0.17147670984268187,
|
|
"num_tokens": 7839772.0,
|
|
"step": 4255
|
|
},
|
|
{
|
|
"entropy": 5.46431040763855,
|
|
"epoch": 0.35583027063147343,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004991638118127757,
|
|
"loss": 5.4657,
|
|
"mean_token_accuracy": 0.16767864674329758,
|
|
"num_tokens": 7850290.0,
|
|
"step": 4260
|
|
},
|
|
{
|
|
"entropy": 5.605262565612793,
|
|
"epoch": 0.3562479117941864,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004991612456595896,
|
|
"loss": 5.4276,
|
|
"mean_token_accuracy": 0.17392627596855165,
|
|
"num_tokens": 7860180.0,
|
|
"step": 4265
|
|
},
|
|
{
|
|
"entropy": 5.400895643234253,
|
|
"epoch": 0.35666555295689945,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004991586755821913,
|
|
"loss": 5.2992,
|
|
"mean_token_accuracy": 0.1876406565308571,
|
|
"num_tokens": 7869625.0,
|
|
"step": 4270
|
|
},
|
|
{
|
|
"entropy": 5.378699493408203,
|
|
"epoch": 0.3570831941196124,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004991561015806254,
|
|
"loss": 5.2522,
|
|
"mean_token_accuracy": 0.17919157296419144,
|
|
"num_tokens": 7878671.0,
|
|
"step": 4275
|
|
},
|
|
{
|
|
"entropy": 5.505584573745727,
|
|
"epoch": 0.3575008352823254,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004991535236549372,
|
|
"loss": 5.3708,
|
|
"mean_token_accuracy": 0.18536537140607834,
|
|
"num_tokens": 7887225.0,
|
|
"step": 4280
|
|
},
|
|
{
|
|
"entropy": 5.392125129699707,
|
|
"epoch": 0.35791847644503844,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004991509418051718,
|
|
"loss": 5.2674,
|
|
"mean_token_accuracy": 0.18982865065336227,
|
|
"num_tokens": 7895504.0,
|
|
"step": 4285
|
|
},
|
|
{
|
|
"entropy": 5.564821434020996,
|
|
"epoch": 0.3583361176077514,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004991483560313743,
|
|
"loss": 5.3296,
|
|
"mean_token_accuracy": 0.1795837849378586,
|
|
"num_tokens": 7904875.0,
|
|
"step": 4290
|
|
},
|
|
{
|
|
"entropy": 5.544165992736817,
|
|
"epoch": 0.3587537587704644,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.00049914576633359,
|
|
"loss": 5.3932,
|
|
"mean_token_accuracy": 0.1829620286822319,
|
|
"num_tokens": 7914747.0,
|
|
"step": 4295
|
|
},
|
|
{
|
|
"entropy": 5.496010780334473,
|
|
"epoch": 0.3591713999331774,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004991431727118643,
|
|
"loss": 5.3625,
|
|
"mean_token_accuracy": 0.17891425043344497,
|
|
"num_tokens": 7923858.0,
|
|
"step": 4300
|
|
},
|
|
{
|
|
"entropy": 5.441442918777466,
|
|
"epoch": 0.3595890410958904,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004991405751662426,
|
|
"loss": 5.3107,
|
|
"mean_token_accuracy": 0.17826237678527831,
|
|
"num_tokens": 7932396.0,
|
|
"step": 4305
|
|
},
|
|
{
|
|
"entropy": 5.509703302383423,
|
|
"epoch": 0.3600066822586034,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004991379736967703,
|
|
"loss": 5.3198,
|
|
"mean_token_accuracy": 0.18312637209892274,
|
|
"num_tokens": 7940763.0,
|
|
"step": 4310
|
|
},
|
|
{
|
|
"entropy": 5.437738275527954,
|
|
"epoch": 0.3604243234213164,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004991353683034929,
|
|
"loss": 5.3267,
|
|
"mean_token_accuracy": 0.17540014386177064,
|
|
"num_tokens": 7949424.0,
|
|
"step": 4315
|
|
},
|
|
{
|
|
"entropy": 5.485245037078857,
|
|
"epoch": 0.3608419645840294,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004991327589864563,
|
|
"loss": 5.2993,
|
|
"mean_token_accuracy": 0.18449853658676146,
|
|
"num_tokens": 7958805.0,
|
|
"step": 4320
|
|
},
|
|
{
|
|
"entropy": 5.59886531829834,
|
|
"epoch": 0.3612596057467424,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004991301457457057,
|
|
"loss": 5.4093,
|
|
"mean_token_accuracy": 0.18323519378900527,
|
|
"num_tokens": 7967859.0,
|
|
"step": 4325
|
|
},
|
|
{
|
|
"entropy": 5.609905862808228,
|
|
"epoch": 0.3616772469094554,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004991275285812873,
|
|
"loss": 5.5313,
|
|
"mean_token_accuracy": 0.16842426657676696,
|
|
"num_tokens": 7978357.0,
|
|
"step": 4330
|
|
},
|
|
{
|
|
"entropy": 5.582861852645874,
|
|
"epoch": 0.3620948880721684,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004991249074932466,
|
|
"loss": 5.3713,
|
|
"mean_token_accuracy": 0.18289734274148942,
|
|
"num_tokens": 7986637.0,
|
|
"step": 4335
|
|
},
|
|
{
|
|
"entropy": 5.452457475662231,
|
|
"epoch": 0.36251252923488136,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004991222824816296,
|
|
"loss": 5.2992,
|
|
"mean_token_accuracy": 0.1832432597875595,
|
|
"num_tokens": 7995954.0,
|
|
"step": 4340
|
|
},
|
|
{
|
|
"entropy": 5.53001594543457,
|
|
"epoch": 0.3629301703975944,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004991196535464824,
|
|
"loss": 5.3821,
|
|
"mean_token_accuracy": 0.1710544377565384,
|
|
"num_tokens": 8005193.0,
|
|
"step": 4345
|
|
},
|
|
{
|
|
"entropy": 5.633359813690186,
|
|
"epoch": 0.3633478115603074,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004991170206878508,
|
|
"loss": 5.3933,
|
|
"mean_token_accuracy": 0.1848797470331192,
|
|
"num_tokens": 8014419.0,
|
|
"step": 4350
|
|
},
|
|
{
|
|
"entropy": 5.475250482559204,
|
|
"epoch": 0.36376545272302035,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000499114383905781,
|
|
"loss": 5.3561,
|
|
"mean_token_accuracy": 0.17914826422929764,
|
|
"num_tokens": 8024133.0,
|
|
"step": 4355
|
|
},
|
|
{
|
|
"entropy": 5.414242506027222,
|
|
"epoch": 0.3641830938857334,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004991117432003192,
|
|
"loss": 5.3087,
|
|
"mean_token_accuracy": 0.18435169905424117,
|
|
"num_tokens": 8033059.0,
|
|
"step": 4360
|
|
},
|
|
{
|
|
"entropy": 5.532291221618652,
|
|
"epoch": 0.36460073504844637,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004991090985715116,
|
|
"loss": 5.3559,
|
|
"mean_token_accuracy": 0.18285473436117172,
|
|
"num_tokens": 8041866.0,
|
|
"step": 4365
|
|
},
|
|
{
|
|
"entropy": 5.484489965438843,
|
|
"epoch": 0.36501837621115935,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004991064500194043,
|
|
"loss": 5.3935,
|
|
"mean_token_accuracy": 0.17530420869588853,
|
|
"num_tokens": 8051541.0,
|
|
"step": 4370
|
|
},
|
|
{
|
|
"entropy": 5.559474945068359,
|
|
"epoch": 0.3654360173738724,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004991037975440439,
|
|
"loss": 5.4684,
|
|
"mean_token_accuracy": 0.17431111484766007,
|
|
"num_tokens": 8061964.0,
|
|
"step": 4375
|
|
},
|
|
{
|
|
"entropy": 5.4441728591918945,
|
|
"epoch": 0.36585365853658536,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004991011411454769,
|
|
"loss": 5.2885,
|
|
"mean_token_accuracy": 0.17922835648059846,
|
|
"num_tokens": 8071006.0,
|
|
"step": 4380
|
|
},
|
|
{
|
|
"entropy": 5.4478785514831545,
|
|
"epoch": 0.36627129969929834,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004990984808237495,
|
|
"loss": 5.2853,
|
|
"mean_token_accuracy": 0.18344878703355788,
|
|
"num_tokens": 8080104.0,
|
|
"step": 4385
|
|
},
|
|
{
|
|
"entropy": 5.5162395477294925,
|
|
"epoch": 0.36668894086201137,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004990958165789086,
|
|
"loss": 5.3393,
|
|
"mean_token_accuracy": 0.18054348081350327,
|
|
"num_tokens": 8089397.0,
|
|
"step": 4390
|
|
},
|
|
{
|
|
"entropy": 5.520235204696656,
|
|
"epoch": 0.36710658202472435,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004990931484110005,
|
|
"loss": 5.3855,
|
|
"mean_token_accuracy": 0.18152005225419998,
|
|
"num_tokens": 8099055.0,
|
|
"step": 4395
|
|
},
|
|
{
|
|
"entropy": 5.469604539871216,
|
|
"epoch": 0.3675242231874373,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004990904763200722,
|
|
"loss": 5.312,
|
|
"mean_token_accuracy": 0.17921042442321777,
|
|
"num_tokens": 8107609.0,
|
|
"step": 4400
|
|
},
|
|
{
|
|
"entropy": 5.584817218780517,
|
|
"epoch": 0.36794186435015036,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004990878003061705,
|
|
"loss": 5.336,
|
|
"mean_token_accuracy": 0.18642372339963914,
|
|
"num_tokens": 8116905.0,
|
|
"step": 4405
|
|
},
|
|
{
|
|
"entropy": 5.436828756332398,
|
|
"epoch": 0.36835950551286334,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004990851203693419,
|
|
"loss": 5.3175,
|
|
"mean_token_accuracy": 0.18151832073926927,
|
|
"num_tokens": 8125580.0,
|
|
"step": 4410
|
|
},
|
|
{
|
|
"entropy": 5.453390455245971,
|
|
"epoch": 0.3687771466755763,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004990824365096336,
|
|
"loss": 5.2437,
|
|
"mean_token_accuracy": 0.17969209402799607,
|
|
"num_tokens": 8134568.0,
|
|
"step": 4415
|
|
},
|
|
{
|
|
"entropy": 5.420157146453858,
|
|
"epoch": 0.36919478783828935,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004990797487270926,
|
|
"loss": 5.2362,
|
|
"mean_token_accuracy": 0.1819555178284645,
|
|
"num_tokens": 8143044.0,
|
|
"step": 4420
|
|
},
|
|
{
|
|
"entropy": 5.3947912693023685,
|
|
"epoch": 0.36961242900100233,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004990770570217659,
|
|
"loss": 5.3487,
|
|
"mean_token_accuracy": 0.17773361653089523,
|
|
"num_tokens": 8153701.0,
|
|
"step": 4425
|
|
},
|
|
{
|
|
"entropy": 5.4455608367919925,
|
|
"epoch": 0.37003007016371536,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004990743613937005,
|
|
"loss": 5.2437,
|
|
"mean_token_accuracy": 0.1832289829850197,
|
|
"num_tokens": 8163264.0,
|
|
"step": 4430
|
|
},
|
|
{
|
|
"entropy": 5.4252534866333,
|
|
"epoch": 0.37044771132642834,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004990716618429436,
|
|
"loss": 5.3598,
|
|
"mean_token_accuracy": 0.1746056079864502,
|
|
"num_tokens": 8173332.0,
|
|
"step": 4435
|
|
},
|
|
{
|
|
"entropy": 5.527809572219849,
|
|
"epoch": 0.3708653524891413,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004990689583695428,
|
|
"loss": 5.3324,
|
|
"mean_token_accuracy": 0.17931413501501084,
|
|
"num_tokens": 8181881.0,
|
|
"step": 4440
|
|
},
|
|
{
|
|
"entropy": 5.585740804672241,
|
|
"epoch": 0.37128299365185435,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000499066250973545,
|
|
"loss": 5.3827,
|
|
"mean_token_accuracy": 0.17656126022338867,
|
|
"num_tokens": 8190771.0,
|
|
"step": 4445
|
|
},
|
|
{
|
|
"entropy": 5.485811710357666,
|
|
"epoch": 0.37170063481456733,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004990635396549978,
|
|
"loss": 5.3198,
|
|
"mean_token_accuracy": 0.18132144212722778,
|
|
"num_tokens": 8200740.0,
|
|
"step": 4450
|
|
},
|
|
{
|
|
"entropy": 5.397424268722534,
|
|
"epoch": 0.3721182759772803,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004990608244139486,
|
|
"loss": 5.3184,
|
|
"mean_token_accuracy": 0.17959628850221634,
|
|
"num_tokens": 8209935.0,
|
|
"step": 4455
|
|
},
|
|
{
|
|
"entropy": 5.448706912994385,
|
|
"epoch": 0.37253591713999334,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000499058105250445,
|
|
"loss": 5.3812,
|
|
"mean_token_accuracy": 0.1757279559969902,
|
|
"num_tokens": 8219137.0,
|
|
"step": 4460
|
|
},
|
|
{
|
|
"entropy": 5.576772546768188,
|
|
"epoch": 0.3729535583027063,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004990553821645346,
|
|
"loss": 5.3446,
|
|
"mean_token_accuracy": 0.18512373119592668,
|
|
"num_tokens": 8228076.0,
|
|
"step": 4465
|
|
},
|
|
{
|
|
"entropy": 5.431705379486084,
|
|
"epoch": 0.3733711994654193,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.000499052655156265,
|
|
"loss": 5.3125,
|
|
"mean_token_accuracy": 0.18290172070264815,
|
|
"num_tokens": 8237581.0,
|
|
"step": 4470
|
|
},
|
|
{
|
|
"entropy": 5.4816020965576175,
|
|
"epoch": 0.37378884062813234,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004990499242256839,
|
|
"loss": 5.3676,
|
|
"mean_token_accuracy": 0.17110753655433655,
|
|
"num_tokens": 8247384.0,
|
|
"step": 4475
|
|
},
|
|
{
|
|
"entropy": 5.565718650817871,
|
|
"epoch": 0.3742064817908453,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004990471893728394,
|
|
"loss": 5.4229,
|
|
"mean_token_accuracy": 0.18246443718671798,
|
|
"num_tokens": 8256383.0,
|
|
"step": 4480
|
|
},
|
|
{
|
|
"entropy": 5.496962594985962,
|
|
"epoch": 0.3746241229535583,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000499044450597779,
|
|
"loss": 5.2883,
|
|
"mean_token_accuracy": 0.1851549506187439,
|
|
"num_tokens": 8264848.0,
|
|
"step": 4485
|
|
},
|
|
{
|
|
"entropy": 5.4337639808654785,
|
|
"epoch": 0.3750417641162713,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004990417079005508,
|
|
"loss": 5.3225,
|
|
"mean_token_accuracy": 0.17415128499269486,
|
|
"num_tokens": 8274403.0,
|
|
"step": 4490
|
|
},
|
|
{
|
|
"entropy": 5.449707460403443,
|
|
"epoch": 0.3754594052789843,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000499038961281203,
|
|
"loss": 5.2412,
|
|
"mean_token_accuracy": 0.18816229254007338,
|
|
"num_tokens": 8282700.0,
|
|
"step": 4495
|
|
},
|
|
{
|
|
"entropy": 5.415894365310669,
|
|
"epoch": 0.3758770464416973,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004990362107397834,
|
|
"loss": 5.2604,
|
|
"mean_token_accuracy": 0.18811499923467637,
|
|
"num_tokens": 8291718.0,
|
|
"step": 4500
|
|
},
|
|
{
|
|
"entropy": 5.445155239105224,
|
|
"epoch": 0.3762946876044103,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004990334562763401,
|
|
"loss": 5.3146,
|
|
"mean_token_accuracy": 0.18061639815568925,
|
|
"num_tokens": 8301113.0,
|
|
"step": 4505
|
|
},
|
|
{
|
|
"entropy": 5.5739223003387455,
|
|
"epoch": 0.3767123287671233,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004990306978909216,
|
|
"loss": 5.4249,
|
|
"mean_token_accuracy": 0.1783556893467903,
|
|
"num_tokens": 8310357.0,
|
|
"step": 4510
|
|
},
|
|
{
|
|
"entropy": 5.497480010986328,
|
|
"epoch": 0.3771299699298363,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004990279355835761,
|
|
"loss": 5.3499,
|
|
"mean_token_accuracy": 0.17866246551275253,
|
|
"num_tokens": 8319680.0,
|
|
"step": 4515
|
|
},
|
|
{
|
|
"entropy": 5.490698766708374,
|
|
"epoch": 0.3775476110925493,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004990251693543519,
|
|
"loss": 5.3772,
|
|
"mean_token_accuracy": 0.17705728113651276,
|
|
"num_tokens": 8329127.0,
|
|
"step": 4520
|
|
},
|
|
{
|
|
"entropy": 5.421241283416748,
|
|
"epoch": 0.3779652522552623,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004990223992032975,
|
|
"loss": 5.2109,
|
|
"mean_token_accuracy": 0.18183238804340363,
|
|
"num_tokens": 8338308.0,
|
|
"step": 4525
|
|
},
|
|
{
|
|
"entropy": 5.459861898422242,
|
|
"epoch": 0.37838289341797526,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004990196251304612,
|
|
"loss": 5.2536,
|
|
"mean_token_accuracy": 0.1817749932408333,
|
|
"num_tokens": 8347491.0,
|
|
"step": 4530
|
|
},
|
|
{
|
|
"entropy": 5.35833101272583,
|
|
"epoch": 0.3788005345806883,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.000499016847135892,
|
|
"loss": 5.2562,
|
|
"mean_token_accuracy": 0.18395913243293763,
|
|
"num_tokens": 8357112.0,
|
|
"step": 4535
|
|
},
|
|
{
|
|
"entropy": 5.438414525985718,
|
|
"epoch": 0.3792181757434013,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.000499014065219638,
|
|
"loss": 5.2624,
|
|
"mean_token_accuracy": 0.18888045400381087,
|
|
"num_tokens": 8366285.0,
|
|
"step": 4540
|
|
},
|
|
{
|
|
"entropy": 5.432564544677734,
|
|
"epoch": 0.37963581690611425,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004990112793817481,
|
|
"loss": 5.1775,
|
|
"mean_token_accuracy": 0.19680214822292327,
|
|
"num_tokens": 8374362.0,
|
|
"step": 4545
|
|
},
|
|
{
|
|
"entropy": 5.461804533004761,
|
|
"epoch": 0.3800534580688273,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004990084896222713,
|
|
"loss": 5.3976,
|
|
"mean_token_accuracy": 0.18095886409282685,
|
|
"num_tokens": 8383297.0,
|
|
"step": 4550
|
|
},
|
|
{
|
|
"entropy": 5.445401191711426,
|
|
"epoch": 0.38047109923154027,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004990056959412562,
|
|
"loss": 5.2877,
|
|
"mean_token_accuracy": 0.18479195684194566,
|
|
"num_tokens": 8391926.0,
|
|
"step": 4555
|
|
},
|
|
{
|
|
"entropy": 5.5135434627532955,
|
|
"epoch": 0.38088874039425324,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004990028983387517,
|
|
"loss": 5.2658,
|
|
"mean_token_accuracy": 0.18396686911582946,
|
|
"num_tokens": 8401226.0,
|
|
"step": 4560
|
|
},
|
|
{
|
|
"entropy": 5.504383659362793,
|
|
"epoch": 0.3813063815569663,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004990000968148068,
|
|
"loss": 5.2947,
|
|
"mean_token_accuracy": 0.18325761556625367,
|
|
"num_tokens": 8409966.0,
|
|
"step": 4565
|
|
},
|
|
{
|
|
"entropy": 5.343247270584106,
|
|
"epoch": 0.38172402271967926,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004989972913694707,
|
|
"loss": 5.137,
|
|
"mean_token_accuracy": 0.19336719512939454,
|
|
"num_tokens": 8418281.0,
|
|
"step": 4570
|
|
},
|
|
{
|
|
"entropy": 5.325301742553711,
|
|
"epoch": 0.38214166388239224,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004989944820027923,
|
|
"loss": 5.2612,
|
|
"mean_token_accuracy": 0.18612614125013352,
|
|
"num_tokens": 8427436.0,
|
|
"step": 4575
|
|
},
|
|
{
|
|
"entropy": 5.455880784988404,
|
|
"epoch": 0.38255930504510527,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004989916687148209,
|
|
"loss": 5.3052,
|
|
"mean_token_accuracy": 0.18906501680612564,
|
|
"num_tokens": 8436066.0,
|
|
"step": 4580
|
|
},
|
|
{
|
|
"entropy": 5.450431489944458,
|
|
"epoch": 0.38297694620781825,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004989888515056057,
|
|
"loss": 5.3032,
|
|
"mean_token_accuracy": 0.18049872815608978,
|
|
"num_tokens": 8445572.0,
|
|
"step": 4585
|
|
},
|
|
{
|
|
"entropy": 5.45234866142273,
|
|
"epoch": 0.3833945873705312,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000498986030375196,
|
|
"loss": 5.3413,
|
|
"mean_token_accuracy": 0.18092950880527497,
|
|
"num_tokens": 8454781.0,
|
|
"step": 4590
|
|
},
|
|
{
|
|
"entropy": 5.455178594589233,
|
|
"epoch": 0.38381222853324426,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004989832053236413,
|
|
"loss": 5.421,
|
|
"mean_token_accuracy": 0.1788090169429779,
|
|
"num_tokens": 8463239.0,
|
|
"step": 4595
|
|
},
|
|
{
|
|
"entropy": 5.526310825347901,
|
|
"epoch": 0.38422986969595724,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000498980376350991,
|
|
"loss": 5.3281,
|
|
"mean_token_accuracy": 0.18151934444904327,
|
|
"num_tokens": 8472664.0,
|
|
"step": 4600
|
|
},
|
|
{
|
|
"entropy": 5.490483808517456,
|
|
"epoch": 0.3846475108586702,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004989775434572945,
|
|
"loss": 5.3892,
|
|
"mean_token_accuracy": 0.1770053118467331,
|
|
"num_tokens": 8483149.0,
|
|
"step": 4605
|
|
},
|
|
{
|
|
"entropy": 5.542194366455078,
|
|
"epoch": 0.38506515202138325,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004989747066426015,
|
|
"loss": 5.328,
|
|
"mean_token_accuracy": 0.1826325237751007,
|
|
"num_tokens": 8492297.0,
|
|
"step": 4610
|
|
},
|
|
{
|
|
"entropy": 5.458335304260254,
|
|
"epoch": 0.38548279318409623,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004989718659069618,
|
|
"loss": 5.391,
|
|
"mean_token_accuracy": 0.17796944677829743,
|
|
"num_tokens": 8502092.0,
|
|
"step": 4615
|
|
},
|
|
{
|
|
"entropy": 5.485839176177978,
|
|
"epoch": 0.3859004343468092,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.000498969021250425,
|
|
"loss": 5.3011,
|
|
"mean_token_accuracy": 0.1888509839773178,
|
|
"num_tokens": 8510816.0,
|
|
"step": 4620
|
|
},
|
|
{
|
|
"entropy": 5.493376874923706,
|
|
"epoch": 0.38631807550952224,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004989661726730407,
|
|
"loss": 5.3257,
|
|
"mean_token_accuracy": 0.1872298002243042,
|
|
"num_tokens": 8520055.0,
|
|
"step": 4625
|
|
},
|
|
{
|
|
"entropy": 5.517747402191162,
|
|
"epoch": 0.3867357166722352,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004989633201748591,
|
|
"loss": 5.3181,
|
|
"mean_token_accuracy": 0.18400509506464005,
|
|
"num_tokens": 8528271.0,
|
|
"step": 4630
|
|
},
|
|
{
|
|
"entropy": 5.408600234985352,
|
|
"epoch": 0.3871533578349482,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004989604637559299,
|
|
"loss": 5.23,
|
|
"mean_token_accuracy": 0.19140341132879257,
|
|
"num_tokens": 8537360.0,
|
|
"step": 4635
|
|
},
|
|
{
|
|
"entropy": 5.343968296051026,
|
|
"epoch": 0.38757099899766123,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004989576034163033,
|
|
"loss": 5.1977,
|
|
"mean_token_accuracy": 0.19754567593336106,
|
|
"num_tokens": 8546574.0,
|
|
"step": 4640
|
|
},
|
|
{
|
|
"entropy": 5.442503499984741,
|
|
"epoch": 0.3879886401603742,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004989547391560293,
|
|
"loss": 5.2907,
|
|
"mean_token_accuracy": 0.17888085693120956,
|
|
"num_tokens": 8555581.0,
|
|
"step": 4645
|
|
},
|
|
{
|
|
"entropy": 5.4283998012542725,
|
|
"epoch": 0.3884062813230872,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.000498951870975158,
|
|
"loss": 5.3173,
|
|
"mean_token_accuracy": 0.1870442271232605,
|
|
"num_tokens": 8564539.0,
|
|
"step": 4650
|
|
},
|
|
{
|
|
"entropy": 5.4952027797698975,
|
|
"epoch": 0.3888239224858002,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004989489988737395,
|
|
"loss": 5.3606,
|
|
"mean_token_accuracy": 0.1791738510131836,
|
|
"num_tokens": 8573804.0,
|
|
"step": 4655
|
|
},
|
|
{
|
|
"entropy": 5.497137784957886,
|
|
"epoch": 0.3892415636485132,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004989461228518243,
|
|
"loss": 5.2993,
|
|
"mean_token_accuracy": 0.18310890942811966,
|
|
"num_tokens": 8583262.0,
|
|
"step": 4660
|
|
},
|
|
{
|
|
"entropy": 5.472321319580078,
|
|
"epoch": 0.3896592048112262,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004989432429094627,
|
|
"loss": 5.3529,
|
|
"mean_token_accuracy": 0.1810036301612854,
|
|
"num_tokens": 8592763.0,
|
|
"step": 4665
|
|
},
|
|
{
|
|
"entropy": 5.512941455841064,
|
|
"epoch": 0.3900768459739392,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004989403590467049,
|
|
"loss": 5.2376,
|
|
"mean_token_accuracy": 0.18580447435379027,
|
|
"num_tokens": 8601884.0,
|
|
"step": 4670
|
|
},
|
|
{
|
|
"entropy": 5.389830827713013,
|
|
"epoch": 0.3904944871366522,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004989374712636017,
|
|
"loss": 5.3553,
|
|
"mean_token_accuracy": 0.17971681356430053,
|
|
"num_tokens": 8611207.0,
|
|
"step": 4675
|
|
},
|
|
{
|
|
"entropy": 5.355565977096558,
|
|
"epoch": 0.39091212829936517,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004989345795602036,
|
|
"loss": 5.1123,
|
|
"mean_token_accuracy": 0.2001250520348549,
|
|
"num_tokens": 8620104.0,
|
|
"step": 4680
|
|
},
|
|
{
|
|
"entropy": 5.455119991302491,
|
|
"epoch": 0.3913297694620782,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004989316839365609,
|
|
"loss": 5.3249,
|
|
"mean_token_accuracy": 0.17869911342859268,
|
|
"num_tokens": 8629552.0,
|
|
"step": 4685
|
|
},
|
|
{
|
|
"entropy": 5.4407007694244385,
|
|
"epoch": 0.3917474106247912,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004989287843927246,
|
|
"loss": 5.2481,
|
|
"mean_token_accuracy": 0.18548665046691895,
|
|
"num_tokens": 8638961.0,
|
|
"step": 4690
|
|
},
|
|
{
|
|
"entropy": 5.48536171913147,
|
|
"epoch": 0.39216505178750416,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004989258809287455,
|
|
"loss": 5.2666,
|
|
"mean_token_accuracy": 0.1833942025899887,
|
|
"num_tokens": 8648051.0,
|
|
"step": 4695
|
|
},
|
|
{
|
|
"entropy": 5.468334913253784,
|
|
"epoch": 0.3925826929502172,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004989229735446743,
|
|
"loss": 5.2606,
|
|
"mean_token_accuracy": 0.18585173040628433,
|
|
"num_tokens": 8656863.0,
|
|
"step": 4700
|
|
},
|
|
{
|
|
"entropy": 5.288018035888672,
|
|
"epoch": 0.39300033411293017,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004989200622405619,
|
|
"loss": 5.1032,
|
|
"mean_token_accuracy": 0.19074878543615342,
|
|
"num_tokens": 8665455.0,
|
|
"step": 4705
|
|
},
|
|
{
|
|
"entropy": 5.3272233486175535,
|
|
"epoch": 0.39341797527564315,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004989171470164592,
|
|
"loss": 5.2113,
|
|
"mean_token_accuracy": 0.18916970044374465,
|
|
"num_tokens": 8674119.0,
|
|
"step": 4710
|
|
},
|
|
{
|
|
"entropy": 5.447572708129883,
|
|
"epoch": 0.3938356164383562,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004989142278724173,
|
|
"loss": 5.3297,
|
|
"mean_token_accuracy": 0.18369702249765396,
|
|
"num_tokens": 8682979.0,
|
|
"step": 4715
|
|
},
|
|
{
|
|
"entropy": 5.475515508651734,
|
|
"epoch": 0.39425325760106916,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004989113048084874,
|
|
"loss": 5.2072,
|
|
"mean_token_accuracy": 0.18288736492395402,
|
|
"num_tokens": 8692392.0,
|
|
"step": 4720
|
|
},
|
|
{
|
|
"entropy": 5.3776037216186525,
|
|
"epoch": 0.39467089876378214,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004989083778247206,
|
|
"loss": 5.2771,
|
|
"mean_token_accuracy": 0.1847996950149536,
|
|
"num_tokens": 8700932.0,
|
|
"step": 4725
|
|
},
|
|
{
|
|
"entropy": 5.558016729354859,
|
|
"epoch": 0.3950885399264952,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000498905446921168,
|
|
"loss": 5.436,
|
|
"mean_token_accuracy": 0.1749883309006691,
|
|
"num_tokens": 8710683.0,
|
|
"step": 4730
|
|
},
|
|
{
|
|
"entropy": 5.387879371643066,
|
|
"epoch": 0.39550618108920815,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004989025120978812,
|
|
"loss": 5.2718,
|
|
"mean_token_accuracy": 0.18771557956933976,
|
|
"num_tokens": 8719939.0,
|
|
"step": 4735
|
|
},
|
|
{
|
|
"entropy": 5.485561561584473,
|
|
"epoch": 0.39592382225192113,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004988995733549113,
|
|
"loss": 5.3359,
|
|
"mean_token_accuracy": 0.1857832118868828,
|
|
"num_tokens": 8729275.0,
|
|
"step": 4740
|
|
},
|
|
{
|
|
"entropy": 5.4087183475494385,
|
|
"epoch": 0.39634146341463417,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004988966306923099,
|
|
"loss": 5.2156,
|
|
"mean_token_accuracy": 0.18902769386768342,
|
|
"num_tokens": 8738048.0,
|
|
"step": 4745
|
|
},
|
|
{
|
|
"entropy": 5.4032769203186035,
|
|
"epoch": 0.39675910457734714,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004988936841101284,
|
|
"loss": 5.2653,
|
|
"mean_token_accuracy": 0.18531980514526367,
|
|
"num_tokens": 8746967.0,
|
|
"step": 4750
|
|
},
|
|
{
|
|
"entropy": 5.339198780059815,
|
|
"epoch": 0.3971767457400601,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004988907336084186,
|
|
"loss": 5.2224,
|
|
"mean_token_accuracy": 0.18994965255260468,
|
|
"num_tokens": 8754908.0,
|
|
"step": 4755
|
|
},
|
|
{
|
|
"entropy": 5.406519651412964,
|
|
"epoch": 0.39759438690277316,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004988877791872319,
|
|
"loss": 5.2574,
|
|
"mean_token_accuracy": 0.19423574358224868,
|
|
"num_tokens": 8764489.0,
|
|
"step": 4760
|
|
},
|
|
{
|
|
"entropy": 5.5614875793457035,
|
|
"epoch": 0.39801202806548613,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004988848208466202,
|
|
"loss": 5.4313,
|
|
"mean_token_accuracy": 0.16883301138877868,
|
|
"num_tokens": 8774365.0,
|
|
"step": 4765
|
|
},
|
|
{
|
|
"entropy": 5.408624649047852,
|
|
"epoch": 0.3984296692281991,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004988818585866351,
|
|
"loss": 5.2257,
|
|
"mean_token_accuracy": 0.18605009764432906,
|
|
"num_tokens": 8783538.0,
|
|
"step": 4770
|
|
},
|
|
{
|
|
"entropy": 5.402309942245483,
|
|
"epoch": 0.39884731039091215,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004988788924073288,
|
|
"loss": 5.3255,
|
|
"mean_token_accuracy": 0.1894812449812889,
|
|
"num_tokens": 8792171.0,
|
|
"step": 4775
|
|
},
|
|
{
|
|
"entropy": 5.459277820587158,
|
|
"epoch": 0.3992649515536251,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004988759223087528,
|
|
"loss": 5.3174,
|
|
"mean_token_accuracy": 0.1798668995499611,
|
|
"num_tokens": 8801325.0,
|
|
"step": 4780
|
|
},
|
|
{
|
|
"entropy": 5.469427108764648,
|
|
"epoch": 0.3996825927163381,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004988729482909595,
|
|
"loss": 5.2532,
|
|
"mean_token_accuracy": 0.1852971598505974,
|
|
"num_tokens": 8810566.0,
|
|
"step": 4785
|
|
},
|
|
{
|
|
"entropy": 5.375425672531128,
|
|
"epoch": 0.40010023387905114,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004988699703540006,
|
|
"loss": 5.2013,
|
|
"mean_token_accuracy": 0.18881352692842485,
|
|
"num_tokens": 8819735.0,
|
|
"step": 4790
|
|
},
|
|
{
|
|
"entropy": 5.40230393409729,
|
|
"epoch": 0.4005178750417641,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004988669884979284,
|
|
"loss": 5.3252,
|
|
"mean_token_accuracy": 0.18047850131988524,
|
|
"num_tokens": 8828820.0,
|
|
"step": 4795
|
|
},
|
|
{
|
|
"entropy": 5.418774223327636,
|
|
"epoch": 0.4009355162044771,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004988640027227951,
|
|
"loss": 5.2248,
|
|
"mean_token_accuracy": 0.18174052387475967,
|
|
"num_tokens": 8837858.0,
|
|
"step": 4800
|
|
},
|
|
{
|
|
"entropy": 5.425327205657959,
|
|
"epoch": 0.4013531573671901,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.000498861013028653,
|
|
"loss": 5.2055,
|
|
"mean_token_accuracy": 0.18545352071523666,
|
|
"num_tokens": 8847172.0,
|
|
"step": 4805
|
|
},
|
|
{
|
|
"entropy": 5.384645223617554,
|
|
"epoch": 0.4017707985299031,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004988580194155544,
|
|
"loss": 5.233,
|
|
"mean_token_accuracy": 0.18156313002109528,
|
|
"num_tokens": 8856700.0,
|
|
"step": 4810
|
|
},
|
|
{
|
|
"entropy": 5.275307989120483,
|
|
"epoch": 0.4021884396926161,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004988550218835517,
|
|
"loss": 5.1187,
|
|
"mean_token_accuracy": 0.1975043758749962,
|
|
"num_tokens": 8866108.0,
|
|
"step": 4815
|
|
},
|
|
{
|
|
"entropy": 5.405415821075439,
|
|
"epoch": 0.4026060808553291,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004988520204326975,
|
|
"loss": 5.2173,
|
|
"mean_token_accuracy": 0.1915104940533638,
|
|
"num_tokens": 8874833.0,
|
|
"step": 4820
|
|
},
|
|
{
|
|
"entropy": 5.45743842124939,
|
|
"epoch": 0.4030237220180421,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004988490150630441,
|
|
"loss": 5.301,
|
|
"mean_token_accuracy": 0.18634421974420548,
|
|
"num_tokens": 8884211.0,
|
|
"step": 4825
|
|
},
|
|
{
|
|
"entropy": 5.4931145191192625,
|
|
"epoch": 0.4034413631807551,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004988460057746443,
|
|
"loss": 5.4088,
|
|
"mean_token_accuracy": 0.18082808703184128,
|
|
"num_tokens": 8893443.0,
|
|
"step": 4830
|
|
},
|
|
{
|
|
"entropy": 5.413536787033081,
|
|
"epoch": 0.4038590043434681,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004988429925675507,
|
|
"loss": 5.2743,
|
|
"mean_token_accuracy": 0.18913335651159285,
|
|
"num_tokens": 8903544.0,
|
|
"step": 4835
|
|
},
|
|
{
|
|
"entropy": 5.441909122467041,
|
|
"epoch": 0.4042766455061811,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004988399754418161,
|
|
"loss": 5.2809,
|
|
"mean_token_accuracy": 0.1874339371919632,
|
|
"num_tokens": 8912270.0,
|
|
"step": 4840
|
|
},
|
|
{
|
|
"entropy": 5.531057119369507,
|
|
"epoch": 0.40469428666889407,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004988369543974932,
|
|
"loss": 5.387,
|
|
"mean_token_accuracy": 0.17393327578902246,
|
|
"num_tokens": 8922155.0,
|
|
"step": 4845
|
|
},
|
|
{
|
|
"entropy": 5.510114336013794,
|
|
"epoch": 0.4051119278316071,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004988339294346351,
|
|
"loss": 5.3852,
|
|
"mean_token_accuracy": 0.18090247809886933,
|
|
"num_tokens": 8931844.0,
|
|
"step": 4850
|
|
},
|
|
{
|
|
"entropy": 5.429131507873535,
|
|
"epoch": 0.4055295689943201,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004988309005532946,
|
|
"loss": 5.2321,
|
|
"mean_token_accuracy": 0.18972109705209733,
|
|
"num_tokens": 8940874.0,
|
|
"step": 4855
|
|
},
|
|
{
|
|
"entropy": 5.40586667060852,
|
|
"epoch": 0.40594721015703306,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004988278677535247,
|
|
"loss": 5.3086,
|
|
"mean_token_accuracy": 0.18382637053728104,
|
|
"num_tokens": 8950108.0,
|
|
"step": 4860
|
|
},
|
|
{
|
|
"entropy": 5.452604484558106,
|
|
"epoch": 0.4063648513197461,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004988248310353788,
|
|
"loss": 5.3177,
|
|
"mean_token_accuracy": 0.18005881905555726,
|
|
"num_tokens": 8960610.0,
|
|
"step": 4865
|
|
},
|
|
{
|
|
"entropy": 5.367214918136597,
|
|
"epoch": 0.40678249248245907,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004988217903989095,
|
|
"loss": 5.259,
|
|
"mean_token_accuracy": 0.18439610600471495,
|
|
"num_tokens": 8969853.0,
|
|
"step": 4870
|
|
},
|
|
{
|
|
"entropy": 5.476442050933838,
|
|
"epoch": 0.40720013364517205,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004988187458441704,
|
|
"loss": 5.2234,
|
|
"mean_token_accuracy": 0.18550434559583664,
|
|
"num_tokens": 8979800.0,
|
|
"step": 4875
|
|
},
|
|
{
|
|
"entropy": 5.430323886871338,
|
|
"epoch": 0.4076177748078851,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004988156973712149,
|
|
"loss": 5.2922,
|
|
"mean_token_accuracy": 0.1802706629037857,
|
|
"num_tokens": 8988667.0,
|
|
"step": 4880
|
|
},
|
|
{
|
|
"entropy": 5.333445930480957,
|
|
"epoch": 0.40803541597059806,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004988126449800961,
|
|
"loss": 5.1509,
|
|
"mean_token_accuracy": 0.19155243933200836,
|
|
"num_tokens": 8997385.0,
|
|
"step": 4885
|
|
},
|
|
{
|
|
"entropy": 5.337029981613159,
|
|
"epoch": 0.40845305713331104,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004988095886708676,
|
|
"loss": 5.1794,
|
|
"mean_token_accuracy": 0.19407922625541688,
|
|
"num_tokens": 9005999.0,
|
|
"step": 4890
|
|
},
|
|
{
|
|
"entropy": 5.460983085632324,
|
|
"epoch": 0.40887069829602407,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004988065284435828,
|
|
"loss": 5.3335,
|
|
"mean_token_accuracy": 0.18845028430223465,
|
|
"num_tokens": 9014837.0,
|
|
"step": 4895
|
|
},
|
|
{
|
|
"entropy": 5.475841856002807,
|
|
"epoch": 0.40928833945873705,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004988034642982954,
|
|
"loss": 5.3624,
|
|
"mean_token_accuracy": 0.1865231767296791,
|
|
"num_tokens": 9023956.0,
|
|
"step": 4900
|
|
},
|
|
{
|
|
"entropy": 5.4807093143463135,
|
|
"epoch": 0.40970598062145,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004988003962350589,
|
|
"loss": 5.3288,
|
|
"mean_token_accuracy": 0.17951313257217408,
|
|
"num_tokens": 9032945.0,
|
|
"step": 4905
|
|
},
|
|
{
|
|
"entropy": 5.44377326965332,
|
|
"epoch": 0.41012362178416306,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000498797324253927,
|
|
"loss": 5.2381,
|
|
"mean_token_accuracy": 0.19179674088954926,
|
|
"num_tokens": 9042109.0,
|
|
"step": 4910
|
|
},
|
|
{
|
|
"entropy": 5.377729606628418,
|
|
"epoch": 0.41054126294687604,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004987942483549537,
|
|
"loss": 5.255,
|
|
"mean_token_accuracy": 0.18214826732873918,
|
|
"num_tokens": 9052210.0,
|
|
"step": 4915
|
|
},
|
|
{
|
|
"entropy": 5.400795888900757,
|
|
"epoch": 0.410958904109589,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004987911685381926,
|
|
"loss": 5.1925,
|
|
"mean_token_accuracy": 0.1923542872071266,
|
|
"num_tokens": 9060089.0,
|
|
"step": 4920
|
|
},
|
|
{
|
|
"entropy": 5.5380675315856935,
|
|
"epoch": 0.41137654527230205,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004987880848036977,
|
|
"loss": 5.3105,
|
|
"mean_token_accuracy": 0.1849738046526909,
|
|
"num_tokens": 9069235.0,
|
|
"step": 4925
|
|
},
|
|
{
|
|
"entropy": 5.398316287994385,
|
|
"epoch": 0.41179418643501503,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004987849971515232,
|
|
"loss": 5.2532,
|
|
"mean_token_accuracy": 0.1917312741279602,
|
|
"num_tokens": 9077509.0,
|
|
"step": 4930
|
|
},
|
|
{
|
|
"entropy": 5.40391321182251,
|
|
"epoch": 0.412211827597728,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004987819055817227,
|
|
"loss": 5.1683,
|
|
"mean_token_accuracy": 0.19981021136045457,
|
|
"num_tokens": 9085493.0,
|
|
"step": 4935
|
|
},
|
|
{
|
|
"entropy": 5.274679708480835,
|
|
"epoch": 0.41262946876044104,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004987788100943507,
|
|
"loss": 5.1485,
|
|
"mean_token_accuracy": 0.18995134830474852,
|
|
"num_tokens": 9094748.0,
|
|
"step": 4940
|
|
},
|
|
{
|
|
"entropy": 5.393630743026733,
|
|
"epoch": 0.413047109923154,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004987757106894613,
|
|
"loss": 5.2245,
|
|
"mean_token_accuracy": 0.18995702564716338,
|
|
"num_tokens": 9103678.0,
|
|
"step": 4945
|
|
},
|
|
{
|
|
"entropy": 5.443596220016479,
|
|
"epoch": 0.413464751085867,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004987726073671086,
|
|
"loss": 5.2733,
|
|
"mean_token_accuracy": 0.18716512024402618,
|
|
"num_tokens": 9112851.0,
|
|
"step": 4950
|
|
},
|
|
{
|
|
"entropy": 5.515263319015503,
|
|
"epoch": 0.41388239224858003,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004987695001273471,
|
|
"loss": 5.5052,
|
|
"mean_token_accuracy": 0.16875243782997132,
|
|
"num_tokens": 9122106.0,
|
|
"step": 4955
|
|
},
|
|
{
|
|
"entropy": 5.4486387252807615,
|
|
"epoch": 0.414300033411293,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004987663889702313,
|
|
"loss": 5.2059,
|
|
"mean_token_accuracy": 0.1922791540622711,
|
|
"num_tokens": 9131580.0,
|
|
"step": 4960
|
|
},
|
|
{
|
|
"entropy": 5.443259859085083,
|
|
"epoch": 0.414717674574006,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004987632738958155,
|
|
"loss": 5.3536,
|
|
"mean_token_accuracy": 0.1818932443857193,
|
|
"num_tokens": 9141642.0,
|
|
"step": 4965
|
|
},
|
|
{
|
|
"entropy": 5.526469326019287,
|
|
"epoch": 0.415135315736719,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004987601549041541,
|
|
"loss": 5.3832,
|
|
"mean_token_accuracy": 0.1804221525788307,
|
|
"num_tokens": 9151192.0,
|
|
"step": 4970
|
|
},
|
|
{
|
|
"entropy": 5.455605936050415,
|
|
"epoch": 0.415552956899432,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004987570319953018,
|
|
"loss": 5.2786,
|
|
"mean_token_accuracy": 0.18481839895248414,
|
|
"num_tokens": 9161316.0,
|
|
"step": 4975
|
|
},
|
|
{
|
|
"entropy": 5.454035758972168,
|
|
"epoch": 0.415970598062145,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004987539051693134,
|
|
"loss": 5.2849,
|
|
"mean_token_accuracy": 0.18582287281751633,
|
|
"num_tokens": 9169535.0,
|
|
"step": 4980
|
|
},
|
|
{
|
|
"entropy": 5.412672090530395,
|
|
"epoch": 0.416388239224858,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004987507744262436,
|
|
"loss": 5.3111,
|
|
"mean_token_accuracy": 0.18136962056159972,
|
|
"num_tokens": 9178187.0,
|
|
"step": 4985
|
|
},
|
|
{
|
|
"entropy": 5.362005805969238,
|
|
"epoch": 0.416805880387571,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004987476397661472,
|
|
"loss": 5.1985,
|
|
"mean_token_accuracy": 0.18647850900888444,
|
|
"num_tokens": 9186342.0,
|
|
"step": 4990
|
|
},
|
|
{
|
|
"entropy": 5.452874612808228,
|
|
"epoch": 0.41722352155028397,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004987445011890789,
|
|
"loss": 5.334,
|
|
"mean_token_accuracy": 0.18385065197944642,
|
|
"num_tokens": 9196470.0,
|
|
"step": 4995
|
|
},
|
|
{
|
|
"entropy": 5.414176321029663,
|
|
"epoch": 0.417641162712997,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000498741358695094,
|
|
"loss": 5.2476,
|
|
"mean_token_accuracy": 0.19388433545827866,
|
|
"num_tokens": 9206587.0,
|
|
"step": 5000
|
|
},
|
|
{
|
|
"entropy": 5.410133504867554,
|
|
"epoch": 0.41805880387571,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.000498738212284247,
|
|
"loss": 5.242,
|
|
"mean_token_accuracy": 0.18349627852439881,
|
|
"num_tokens": 9216459.0,
|
|
"step": 5005
|
|
},
|
|
{
|
|
"entropy": 5.573675489425659,
|
|
"epoch": 0.41847644503842296,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004987350619565934,
|
|
"loss": 5.3523,
|
|
"mean_token_accuracy": 0.18130982518196107,
|
|
"num_tokens": 9227301.0,
|
|
"step": 5010
|
|
},
|
|
{
|
|
"entropy": 5.4957184314727785,
|
|
"epoch": 0.418894086201136,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004987319077121884,
|
|
"loss": 5.2809,
|
|
"mean_token_accuracy": 0.17829721421003342,
|
|
"num_tokens": 9236577.0,
|
|
"step": 5015
|
|
},
|
|
{
|
|
"entropy": 5.362134742736816,
|
|
"epoch": 0.419311727363849,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004987287495510869,
|
|
"loss": 5.2789,
|
|
"mean_token_accuracy": 0.18880894035100937,
|
|
"num_tokens": 9246451.0,
|
|
"step": 5020
|
|
},
|
|
{
|
|
"entropy": 5.370787763595581,
|
|
"epoch": 0.41972936852656195,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004987255874733444,
|
|
"loss": 5.1613,
|
|
"mean_token_accuracy": 0.18581471890211104,
|
|
"num_tokens": 9256108.0,
|
|
"step": 5025
|
|
},
|
|
{
|
|
"entropy": 5.366769075393677,
|
|
"epoch": 0.420147009689275,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004987224214790161,
|
|
"loss": 5.2355,
|
|
"mean_token_accuracy": 0.1906559556722641,
|
|
"num_tokens": 9265173.0,
|
|
"step": 5030
|
|
},
|
|
{
|
|
"entropy": 5.400710725784302,
|
|
"epoch": 0.42056465085198796,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004987192515681575,
|
|
"loss": 5.3162,
|
|
"mean_token_accuracy": 0.1848292425274849,
|
|
"num_tokens": 9273979.0,
|
|
"step": 5035
|
|
},
|
|
{
|
|
"entropy": 5.341616821289063,
|
|
"epoch": 0.42098229201470094,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004987160777408243,
|
|
"loss": 5.2551,
|
|
"mean_token_accuracy": 0.18350231200456618,
|
|
"num_tokens": 9281893.0,
|
|
"step": 5040
|
|
},
|
|
{
|
|
"entropy": 5.483113384246826,
|
|
"epoch": 0.421399933177414,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004987128999970717,
|
|
"loss": 5.3695,
|
|
"mean_token_accuracy": 0.1833135813474655,
|
|
"num_tokens": 9290799.0,
|
|
"step": 5045
|
|
},
|
|
{
|
|
"entropy": 5.514388370513916,
|
|
"epoch": 0.42181757434012696,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004987097183369555,
|
|
"loss": 5.3442,
|
|
"mean_token_accuracy": 0.17365078181028365,
|
|
"num_tokens": 9300562.0,
|
|
"step": 5050
|
|
},
|
|
{
|
|
"entropy": 5.361443138122558,
|
|
"epoch": 0.42223521550283993,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004987065327605315,
|
|
"loss": 5.1097,
|
|
"mean_token_accuracy": 0.1997506558895111,
|
|
"num_tokens": 9308889.0,
|
|
"step": 5055
|
|
},
|
|
{
|
|
"entropy": 5.325141096115113,
|
|
"epoch": 0.42265285666555297,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004987033432678553,
|
|
"loss": 5.2073,
|
|
"mean_token_accuracy": 0.18749006390571593,
|
|
"num_tokens": 9317957.0,
|
|
"step": 5060
|
|
},
|
|
{
|
|
"entropy": 5.502013301849365,
|
|
"epoch": 0.42307049782826595,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004987001498589828,
|
|
"loss": 5.4012,
|
|
"mean_token_accuracy": 0.17834450006484986,
|
|
"num_tokens": 9327849.0,
|
|
"step": 5065
|
|
},
|
|
{
|
|
"entropy": 5.440627956390381,
|
|
"epoch": 0.4234881389909789,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00049869695253397,
|
|
"loss": 5.2616,
|
|
"mean_token_accuracy": 0.180339252948761,
|
|
"num_tokens": 9337165.0,
|
|
"step": 5070
|
|
},
|
|
{
|
|
"entropy": 5.352905988693237,
|
|
"epoch": 0.42390578015369196,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004986937512928727,
|
|
"loss": 5.1771,
|
|
"mean_token_accuracy": 0.1884523794054985,
|
|
"num_tokens": 9346817.0,
|
|
"step": 5075
|
|
},
|
|
{
|
|
"entropy": 5.5156840801239015,
|
|
"epoch": 0.42432342131640494,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000498690546135747,
|
|
"loss": 5.2966,
|
|
"mean_token_accuracy": 0.1840095728635788,
|
|
"num_tokens": 9356420.0,
|
|
"step": 5080
|
|
},
|
|
{
|
|
"entropy": 5.410769605636597,
|
|
"epoch": 0.4247410624791179,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004986873370626491,
|
|
"loss": 5.2288,
|
|
"mean_token_accuracy": 0.18823409378528594,
|
|
"num_tokens": 9365580.0,
|
|
"step": 5085
|
|
},
|
|
{
|
|
"entropy": 5.3939556121826175,
|
|
"epoch": 0.42515870364183095,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000498684124073635,
|
|
"loss": 5.2639,
|
|
"mean_token_accuracy": 0.18051869720220565,
|
|
"num_tokens": 9375116.0,
|
|
"step": 5090
|
|
},
|
|
{
|
|
"entropy": 5.493084716796875,
|
|
"epoch": 0.4255763448045439,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004986809071687612,
|
|
"loss": 5.2404,
|
|
"mean_token_accuracy": 0.18489679247140883,
|
|
"num_tokens": 9384129.0,
|
|
"step": 5095
|
|
},
|
|
{
|
|
"entropy": 5.440520906448365,
|
|
"epoch": 0.4259939859672569,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004986776863480838,
|
|
"loss": 5.2057,
|
|
"mean_token_accuracy": 0.1855569988489151,
|
|
"num_tokens": 9392757.0,
|
|
"step": 5100
|
|
},
|
|
{
|
|
"entropy": 5.303371953964233,
|
|
"epoch": 0.42641162712996994,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004986744616116593,
|
|
"loss": 5.1688,
|
|
"mean_token_accuracy": 0.18864914178848266,
|
|
"num_tokens": 9401753.0,
|
|
"step": 5105
|
|
},
|
|
{
|
|
"entropy": 5.410655164718628,
|
|
"epoch": 0.4268292682926829,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000498671232959544,
|
|
"loss": 5.376,
|
|
"mean_token_accuracy": 0.17809276133775712,
|
|
"num_tokens": 9411400.0,
|
|
"step": 5110
|
|
},
|
|
{
|
|
"entropy": 5.476285028457641,
|
|
"epoch": 0.42724690945539595,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004986680003917947,
|
|
"loss": 5.2376,
|
|
"mean_token_accuracy": 0.18526431173086166,
|
|
"num_tokens": 9420206.0,
|
|
"step": 5115
|
|
},
|
|
{
|
|
"entropy": 5.423188352584839,
|
|
"epoch": 0.42766455061810893,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004986647639084677,
|
|
"loss": 5.224,
|
|
"mean_token_accuracy": 0.19024873226881028,
|
|
"num_tokens": 9428418.0,
|
|
"step": 5120
|
|
},
|
|
{
|
|
"entropy": 5.45528998374939,
|
|
"epoch": 0.4280821917808219,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00049866152350962,
|
|
"loss": 5.2696,
|
|
"mean_token_accuracy": 0.17983853369951247,
|
|
"num_tokens": 9437624.0,
|
|
"step": 5125
|
|
},
|
|
{
|
|
"entropy": 5.353516912460327,
|
|
"epoch": 0.42849983294353494,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004986582791953078,
|
|
"loss": 5.17,
|
|
"mean_token_accuracy": 0.19529253244400024,
|
|
"num_tokens": 9446857.0,
|
|
"step": 5130
|
|
},
|
|
{
|
|
"entropy": 5.384277486801148,
|
|
"epoch": 0.4289174741062479,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004986550309655884,
|
|
"loss": 5.2684,
|
|
"mean_token_accuracy": 0.18311621993780136,
|
|
"num_tokens": 9456024.0,
|
|
"step": 5135
|
|
},
|
|
{
|
|
"entropy": 5.407329177856445,
|
|
"epoch": 0.4293351152689609,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004986517788205184,
|
|
"loss": 5.1772,
|
|
"mean_token_accuracy": 0.19539380967617034,
|
|
"num_tokens": 9464018.0,
|
|
"step": 5140
|
|
},
|
|
{
|
|
"entropy": 5.410005283355713,
|
|
"epoch": 0.42975275643167393,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004986485227601548,
|
|
"loss": 5.3089,
|
|
"mean_token_accuracy": 0.18760735988616944,
|
|
"num_tokens": 9472430.0,
|
|
"step": 5145
|
|
},
|
|
{
|
|
"entropy": 5.392274856567383,
|
|
"epoch": 0.4301703975943869,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004986452627845547,
|
|
"loss": 5.2359,
|
|
"mean_token_accuracy": 0.1965549811720848,
|
|
"num_tokens": 9480592.0,
|
|
"step": 5150
|
|
},
|
|
{
|
|
"entropy": 5.335669231414795,
|
|
"epoch": 0.4305880387570999,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000498641998893775,
|
|
"loss": 5.1734,
|
|
"mean_token_accuracy": 0.19266332387924195,
|
|
"num_tokens": 9489162.0,
|
|
"step": 5155
|
|
},
|
|
{
|
|
"entropy": 5.404368734359741,
|
|
"epoch": 0.4310056799198129,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004986387310878728,
|
|
"loss": 5.243,
|
|
"mean_token_accuracy": 0.18955194801092148,
|
|
"num_tokens": 9499210.0,
|
|
"step": 5160
|
|
},
|
|
{
|
|
"entropy": 5.426062774658203,
|
|
"epoch": 0.4314233210825259,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004986354593669056,
|
|
"loss": 5.2849,
|
|
"mean_token_accuracy": 0.18945134431123734,
|
|
"num_tokens": 9508062.0,
|
|
"step": 5165
|
|
},
|
|
{
|
|
"entropy": 5.460740566253662,
|
|
"epoch": 0.4318409622452389,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004986321837309304,
|
|
"loss": 5.2285,
|
|
"mean_token_accuracy": 0.19201678782701492,
|
|
"num_tokens": 9516756.0,
|
|
"step": 5170
|
|
},
|
|
{
|
|
"entropy": 5.3514862060546875,
|
|
"epoch": 0.4322586034079519,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004986289041800046,
|
|
"loss": 5.217,
|
|
"mean_token_accuracy": 0.19218968600034714,
|
|
"num_tokens": 9525305.0,
|
|
"step": 5175
|
|
},
|
|
{
|
|
"entropy": 5.404515171051026,
|
|
"epoch": 0.4326762445706649,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004986256207141857,
|
|
"loss": 5.1963,
|
|
"mean_token_accuracy": 0.1971699297428131,
|
|
"num_tokens": 9534310.0,
|
|
"step": 5180
|
|
},
|
|
{
|
|
"entropy": 5.482242631912231,
|
|
"epoch": 0.43309388573337787,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004986223333335311,
|
|
"loss": 5.3014,
|
|
"mean_token_accuracy": 0.18381469696760178,
|
|
"num_tokens": 9543648.0,
|
|
"step": 5185
|
|
},
|
|
{
|
|
"entropy": 5.361711120605468,
|
|
"epoch": 0.4335115268960909,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004986190420380985,
|
|
"loss": 5.213,
|
|
"mean_token_accuracy": 0.19145919680595397,
|
|
"num_tokens": 9553081.0,
|
|
"step": 5190
|
|
},
|
|
{
|
|
"entropy": 5.431469583511353,
|
|
"epoch": 0.4339291680588039,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004986157468279453,
|
|
"loss": 5.2669,
|
|
"mean_token_accuracy": 0.18773092627525328,
|
|
"num_tokens": 9563184.0,
|
|
"step": 5195
|
|
},
|
|
{
|
|
"entropy": 5.414912986755371,
|
|
"epoch": 0.43434680922151686,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004986124477031293,
|
|
"loss": 5.2228,
|
|
"mean_token_accuracy": 0.18737793564796448,
|
|
"num_tokens": 9572550.0,
|
|
"step": 5200
|
|
},
|
|
{
|
|
"entropy": 5.357417154312134,
|
|
"epoch": 0.4347644503842299,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004986091446637083,
|
|
"loss": 5.273,
|
|
"mean_token_accuracy": 0.18699531704187394,
|
|
"num_tokens": 9580900.0,
|
|
"step": 5205
|
|
},
|
|
{
|
|
"entropy": 5.410246229171753,
|
|
"epoch": 0.4351820915469429,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00049860583770974,
|
|
"loss": 5.2595,
|
|
"mean_token_accuracy": 0.18967737555503844,
|
|
"num_tokens": 9589340.0,
|
|
"step": 5210
|
|
},
|
|
{
|
|
"entropy": 5.447885990142822,
|
|
"epoch": 0.43559973270965585,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004986025268412823,
|
|
"loss": 5.3718,
|
|
"mean_token_accuracy": 0.18643051236867905,
|
|
"num_tokens": 9599316.0,
|
|
"step": 5215
|
|
},
|
|
{
|
|
"entropy": 5.4523365020751955,
|
|
"epoch": 0.4360173738723689,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004985992120583933,
|
|
"loss": 5.2616,
|
|
"mean_token_accuracy": 0.1854226619005203,
|
|
"num_tokens": 9609350.0,
|
|
"step": 5220
|
|
},
|
|
{
|
|
"entropy": 5.468072843551636,
|
|
"epoch": 0.43643501503508186,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000498595893361131,
|
|
"loss": 5.3206,
|
|
"mean_token_accuracy": 0.18880557864904404,
|
|
"num_tokens": 9618491.0,
|
|
"step": 5225
|
|
},
|
|
{
|
|
"entropy": 5.445502424240113,
|
|
"epoch": 0.43685265619779484,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004985925707495533,
|
|
"loss": 5.3821,
|
|
"mean_token_accuracy": 0.17734698802232743,
|
|
"num_tokens": 9629613.0,
|
|
"step": 5230
|
|
},
|
|
{
|
|
"entropy": 5.373774290084839,
|
|
"epoch": 0.4372702973605079,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004985892442237186,
|
|
"loss": 5.2525,
|
|
"mean_token_accuracy": 0.19087811559438705,
|
|
"num_tokens": 9638035.0,
|
|
"step": 5235
|
|
},
|
|
{
|
|
"entropy": 5.478862714767456,
|
|
"epoch": 0.43768793852322085,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004985859137836851,
|
|
"loss": 5.319,
|
|
"mean_token_accuracy": 0.17996042370796203,
|
|
"num_tokens": 9647378.0,
|
|
"step": 5240
|
|
},
|
|
{
|
|
"entropy": 5.485831451416016,
|
|
"epoch": 0.43810557968593383,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004985825794295109,
|
|
"loss": 5.2293,
|
|
"mean_token_accuracy": 0.1899410903453827,
|
|
"num_tokens": 9655728.0,
|
|
"step": 5245
|
|
},
|
|
{
|
|
"entropy": 5.378673982620239,
|
|
"epoch": 0.43852322084864687,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004985792411612546,
|
|
"loss": 5.2704,
|
|
"mean_token_accuracy": 0.18692253082990645,
|
|
"num_tokens": 9665063.0,
|
|
"step": 5250
|
|
},
|
|
{
|
|
"entropy": 5.424449920654297,
|
|
"epoch": 0.43894086201135984,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004985758989789746,
|
|
"loss": 5.2715,
|
|
"mean_token_accuracy": 0.18209364265203476,
|
|
"num_tokens": 9674406.0,
|
|
"step": 5255
|
|
},
|
|
{
|
|
"entropy": 5.406913375854492,
|
|
"epoch": 0.4393585031740728,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004985725528827293,
|
|
"loss": 5.2101,
|
|
"mean_token_accuracy": 0.18680866211652755,
|
|
"num_tokens": 9683303.0,
|
|
"step": 5260
|
|
},
|
|
{
|
|
"entropy": 5.406108665466308,
|
|
"epoch": 0.43977614433678586,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004985692028725774,
|
|
"loss": 5.2089,
|
|
"mean_token_accuracy": 0.18465999513864517,
|
|
"num_tokens": 9692938.0,
|
|
"step": 5265
|
|
},
|
|
{
|
|
"entropy": 5.433288526535034,
|
|
"epoch": 0.44019378549949884,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004985658489485774,
|
|
"loss": 5.2823,
|
|
"mean_token_accuracy": 0.1838356077671051,
|
|
"num_tokens": 9702192.0,
|
|
"step": 5270
|
|
},
|
|
{
|
|
"entropy": 5.4437394618988035,
|
|
"epoch": 0.4406114266622118,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004985624911107882,
|
|
"loss": 5.2679,
|
|
"mean_token_accuracy": 0.1794508084654808,
|
|
"num_tokens": 9711301.0,
|
|
"step": 5275
|
|
},
|
|
{
|
|
"entropy": 5.388669729232788,
|
|
"epoch": 0.44102906782492485,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004985591293592685,
|
|
"loss": 5.2627,
|
|
"mean_token_accuracy": 0.18056987673044206,
|
|
"num_tokens": 9720768.0,
|
|
"step": 5280
|
|
},
|
|
{
|
|
"entropy": 5.4140290260314945,
|
|
"epoch": 0.4414467089876378,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004985557636940771,
|
|
"loss": 5.2976,
|
|
"mean_token_accuracy": 0.18801358640193938,
|
|
"num_tokens": 9730007.0,
|
|
"step": 5285
|
|
},
|
|
{
|
|
"entropy": 5.492460250854492,
|
|
"epoch": 0.4418643501503508,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000498552394115273,
|
|
"loss": 5.3356,
|
|
"mean_token_accuracy": 0.18004858791828154,
|
|
"num_tokens": 9739546.0,
|
|
"step": 5290
|
|
},
|
|
{
|
|
"entropy": 5.385093545913696,
|
|
"epoch": 0.44228199131306384,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004985490206229151,
|
|
"loss": 5.2072,
|
|
"mean_token_accuracy": 0.1893276423215866,
|
|
"num_tokens": 9749615.0,
|
|
"step": 5295
|
|
},
|
|
{
|
|
"entropy": 5.4636486053466795,
|
|
"epoch": 0.4426996324757768,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004985456432170626,
|
|
"loss": 5.3061,
|
|
"mean_token_accuracy": 0.18105170279741287,
|
|
"num_tokens": 9759285.0,
|
|
"step": 5300
|
|
},
|
|
{
|
|
"entropy": 5.374495506286621,
|
|
"epoch": 0.4431172736384898,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004985422618977744,
|
|
"loss": 5.1792,
|
|
"mean_token_accuracy": 0.18297002613544464,
|
|
"num_tokens": 9769396.0,
|
|
"step": 5305
|
|
},
|
|
{
|
|
"entropy": 5.441941595077514,
|
|
"epoch": 0.44353491480120283,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00049853887666511,
|
|
"loss": 5.2961,
|
|
"mean_token_accuracy": 0.18522798120975495,
|
|
"num_tokens": 9779632.0,
|
|
"step": 5310
|
|
},
|
|
{
|
|
"entropy": 5.456464576721191,
|
|
"epoch": 0.4439525559639158,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004985354875191283,
|
|
"loss": 5.2307,
|
|
"mean_token_accuracy": 0.1865606963634491,
|
|
"num_tokens": 9788090.0,
|
|
"step": 5315
|
|
},
|
|
{
|
|
"entropy": 5.2392005443573,
|
|
"epoch": 0.4443701971266288,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004985320944598889,
|
|
"loss": 5.1363,
|
|
"mean_token_accuracy": 0.19887329787015914,
|
|
"num_tokens": 9795844.0,
|
|
"step": 5320
|
|
},
|
|
{
|
|
"entropy": 5.341764259338379,
|
|
"epoch": 0.4447878382893418,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004985286974874512,
|
|
"loss": 5.1368,
|
|
"mean_token_accuracy": 0.19803263247013092,
|
|
"num_tokens": 9805119.0,
|
|
"step": 5325
|
|
},
|
|
{
|
|
"entropy": 5.4308655738830565,
|
|
"epoch": 0.4452054794520548,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004985252966018745,
|
|
"loss": 5.2606,
|
|
"mean_token_accuracy": 0.1878809705376625,
|
|
"num_tokens": 9813842.0,
|
|
"step": 5330
|
|
},
|
|
{
|
|
"entropy": 5.3994889736175535,
|
|
"epoch": 0.4456231206147678,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004985218918032184,
|
|
"loss": 5.2535,
|
|
"mean_token_accuracy": 0.1783266320824623,
|
|
"num_tokens": 9822872.0,
|
|
"step": 5335
|
|
},
|
|
{
|
|
"entropy": 5.489075231552124,
|
|
"epoch": 0.4460407617774808,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004985184830915426,
|
|
"loss": 5.3732,
|
|
"mean_token_accuracy": 0.18024482429027558,
|
|
"num_tokens": 9832710.0,
|
|
"step": 5340
|
|
},
|
|
{
|
|
"entropy": 5.494144630432129,
|
|
"epoch": 0.4464584029401938,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004985150704669067,
|
|
"loss": 5.2658,
|
|
"mean_token_accuracy": 0.18504762649536133,
|
|
"num_tokens": 9841047.0,
|
|
"step": 5345
|
|
},
|
|
{
|
|
"entropy": 5.448194169998169,
|
|
"epoch": 0.44687604410290677,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004985116539293704,
|
|
"loss": 5.2422,
|
|
"mean_token_accuracy": 0.18845410645008087,
|
|
"num_tokens": 9850168.0,
|
|
"step": 5350
|
|
},
|
|
{
|
|
"entropy": 5.34441065788269,
|
|
"epoch": 0.4472936852656198,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004985082334789936,
|
|
"loss": 5.3037,
|
|
"mean_token_accuracy": 0.1800173655152321,
|
|
"num_tokens": 9859550.0,
|
|
"step": 5355
|
|
},
|
|
{
|
|
"entropy": 5.488778877258301,
|
|
"epoch": 0.4477113264283328,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004985048091158361,
|
|
"loss": 5.2413,
|
|
"mean_token_accuracy": 0.18067245930433273,
|
|
"num_tokens": 9868317.0,
|
|
"step": 5360
|
|
},
|
|
{
|
|
"entropy": 5.518444919586182,
|
|
"epoch": 0.44812896759104576,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004985013808399578,
|
|
"loss": 5.4682,
|
|
"mean_token_accuracy": 0.17326602041721345,
|
|
"num_tokens": 9878421.0,
|
|
"step": 5365
|
|
},
|
|
{
|
|
"entropy": 5.441004753112793,
|
|
"epoch": 0.4485466087537588,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004984979486514189,
|
|
"loss": 5.1946,
|
|
"mean_token_accuracy": 0.19337001740932463,
|
|
"num_tokens": 9887213.0,
|
|
"step": 5370
|
|
},
|
|
{
|
|
"entropy": 5.370984268188477,
|
|
"epoch": 0.44896424991647177,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004984945125502795,
|
|
"loss": 5.3106,
|
|
"mean_token_accuracy": 0.1782525047659874,
|
|
"num_tokens": 9897274.0,
|
|
"step": 5375
|
|
},
|
|
{
|
|
"entropy": 5.324212169647216,
|
|
"epoch": 0.44938189107918475,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004984910725365994,
|
|
"loss": 5.2354,
|
|
"mean_token_accuracy": 0.18489155322313308,
|
|
"num_tokens": 9906765.0,
|
|
"step": 5380
|
|
},
|
|
{
|
|
"entropy": 5.4923529624938965,
|
|
"epoch": 0.4497995322418978,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004984876286104392,
|
|
"loss": 5.2447,
|
|
"mean_token_accuracy": 0.1800004541873932,
|
|
"num_tokens": 9916149.0,
|
|
"step": 5385
|
|
},
|
|
{
|
|
"entropy": 5.422781181335449,
|
|
"epoch": 0.45021717340461076,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004984841807718591,
|
|
"loss": 5.2428,
|
|
"mean_token_accuracy": 0.18369154930114745,
|
|
"num_tokens": 9925657.0,
|
|
"step": 5390
|
|
},
|
|
{
|
|
"entropy": 5.369697713851929,
|
|
"epoch": 0.45063481456732374,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004984807290209193,
|
|
"loss": 5.2541,
|
|
"mean_token_accuracy": 0.17732944786548616,
|
|
"num_tokens": 9934740.0,
|
|
"step": 5395
|
|
},
|
|
{
|
|
"entropy": 5.533233261108398,
|
|
"epoch": 0.45105245573003677,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004984772733576803,
|
|
"loss": 5.3809,
|
|
"mean_token_accuracy": 0.17752125561237336,
|
|
"num_tokens": 9943516.0,
|
|
"step": 5400
|
|
},
|
|
{
|
|
"entropy": 5.430769968032837,
|
|
"epoch": 0.45147009689274975,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004984738137822028,
|
|
"loss": 5.3279,
|
|
"mean_token_accuracy": 0.18029251992702483,
|
|
"num_tokens": 9952998.0,
|
|
"step": 5405
|
|
},
|
|
{
|
|
"entropy": 5.385849094390869,
|
|
"epoch": 0.45188773805546273,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.000498470350294547,
|
|
"loss": 5.1365,
|
|
"mean_token_accuracy": 0.1915778934955597,
|
|
"num_tokens": 9961698.0,
|
|
"step": 5410
|
|
},
|
|
{
|
|
"entropy": 5.405647563934326,
|
|
"epoch": 0.45230537921817576,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004984668828947739,
|
|
"loss": 5.2799,
|
|
"mean_token_accuracy": 0.1811949774622917,
|
|
"num_tokens": 9972015.0,
|
|
"step": 5415
|
|
},
|
|
{
|
|
"entropy": 5.482445859909058,
|
|
"epoch": 0.45272302038088874,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004984634115829439,
|
|
"loss": 5.3477,
|
|
"mean_token_accuracy": 0.18006271719932557,
|
|
"num_tokens": 9981834.0,
|
|
"step": 5420
|
|
},
|
|
{
|
|
"entropy": 5.368338108062744,
|
|
"epoch": 0.4531406615436017,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000498459936359118,
|
|
"loss": 5.2058,
|
|
"mean_token_accuracy": 0.19074418842792512,
|
|
"num_tokens": 9991113.0,
|
|
"step": 5425
|
|
},
|
|
{
|
|
"entropy": 5.409156656265258,
|
|
"epoch": 0.45355830270631475,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004984564572233568,
|
|
"loss": 5.1929,
|
|
"mean_token_accuracy": 0.18956764787435532,
|
|
"num_tokens": 10000048.0,
|
|
"step": 5430
|
|
},
|
|
{
|
|
"entropy": 5.424026346206665,
|
|
"epoch": 0.45397594386902773,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004984529741757216,
|
|
"loss": 5.2397,
|
|
"mean_token_accuracy": 0.18849152326583862,
|
|
"num_tokens": 10009389.0,
|
|
"step": 5435
|
|
},
|
|
{
|
|
"entropy": 5.370808172225952,
|
|
"epoch": 0.4543935850317407,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004984494872162728,
|
|
"loss": 5.0906,
|
|
"mean_token_accuracy": 0.1974114239215851,
|
|
"num_tokens": 10018342.0,
|
|
"step": 5440
|
|
},
|
|
{
|
|
"entropy": 5.4293419361114506,
|
|
"epoch": 0.45481122619445374,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000498445996345072,
|
|
"loss": 5.2809,
|
|
"mean_token_accuracy": 0.19553306102752685,
|
|
"num_tokens": 10027219.0,
|
|
"step": 5445
|
|
},
|
|
{
|
|
"entropy": 5.375585412979126,
|
|
"epoch": 0.4552288673571667,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004984425015621799,
|
|
"loss": 5.1771,
|
|
"mean_token_accuracy": 0.1849798634648323,
|
|
"num_tokens": 10036635.0,
|
|
"step": 5450
|
|
},
|
|
{
|
|
"entropy": 5.359622621536255,
|
|
"epoch": 0.4556465085198797,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000498439002867658,
|
|
"loss": 5.2232,
|
|
"mean_token_accuracy": 0.18533703237771987,
|
|
"num_tokens": 10045655.0,
|
|
"step": 5455
|
|
},
|
|
{
|
|
"entropy": 5.4857409477233885,
|
|
"epoch": 0.45606414968259273,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004984355002615673,
|
|
"loss": 5.2819,
|
|
"mean_token_accuracy": 0.17572323679924012,
|
|
"num_tokens": 10054366.0,
|
|
"step": 5460
|
|
},
|
|
{
|
|
"entropy": 5.413508558273316,
|
|
"epoch": 0.4564817908453057,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004984319937439693,
|
|
"loss": 5.2297,
|
|
"mean_token_accuracy": 0.19253379106521606,
|
|
"num_tokens": 10062548.0,
|
|
"step": 5465
|
|
},
|
|
{
|
|
"entropy": 5.368886852264405,
|
|
"epoch": 0.4568994320080187,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004984284833149252,
|
|
"loss": 5.2346,
|
|
"mean_token_accuracy": 0.1868786096572876,
|
|
"num_tokens": 10071333.0,
|
|
"step": 5470
|
|
},
|
|
{
|
|
"entropy": 5.3347487449646,
|
|
"epoch": 0.4573170731707317,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004984249689744966,
|
|
"loss": 5.1106,
|
|
"mean_token_accuracy": 0.1973042905330658,
|
|
"num_tokens": 10079502.0,
|
|
"step": 5475
|
|
},
|
|
{
|
|
"entropy": 5.36964430809021,
|
|
"epoch": 0.4577347143334447,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000498421450722745,
|
|
"loss": 5.1535,
|
|
"mean_token_accuracy": 0.19379387199878692,
|
|
"num_tokens": 10088648.0,
|
|
"step": 5480
|
|
},
|
|
{
|
|
"entropy": 5.343714666366577,
|
|
"epoch": 0.4581523554961577,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000498417928559732,
|
|
"loss": 5.166,
|
|
"mean_token_accuracy": 0.19369458258152009,
|
|
"num_tokens": 10097742.0,
|
|
"step": 5485
|
|
},
|
|
{
|
|
"entropy": 5.424908399581909,
|
|
"epoch": 0.4585699966588707,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004984144024855191,
|
|
"loss": 5.2786,
|
|
"mean_token_accuracy": 0.18148799389600753,
|
|
"num_tokens": 10107228.0,
|
|
"step": 5490
|
|
},
|
|
{
|
|
"entropy": 5.416803455352783,
|
|
"epoch": 0.4589876378215837,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004984108725001683,
|
|
"loss": 5.1667,
|
|
"mean_token_accuracy": 0.1910475417971611,
|
|
"num_tokens": 10115488.0,
|
|
"step": 5495
|
|
},
|
|
{
|
|
"entropy": 5.320183229446411,
|
|
"epoch": 0.45940527898429667,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004984073386037413,
|
|
"loss": 5.1075,
|
|
"mean_token_accuracy": 0.19790947884321214,
|
|
"num_tokens": 10124235.0,
|
|
"step": 5500
|
|
},
|
|
{
|
|
"entropy": 5.32041072845459,
|
|
"epoch": 0.4598229201470097,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004984038007962997,
|
|
"loss": 5.207,
|
|
"mean_token_accuracy": 0.1984640121459961,
|
|
"num_tokens": 10133208.0,
|
|
"step": 5505
|
|
},
|
|
{
|
|
"entropy": 5.362421655654908,
|
|
"epoch": 0.4602405613097227,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004984002590779059,
|
|
"loss": 5.135,
|
|
"mean_token_accuracy": 0.19263925552368164,
|
|
"num_tokens": 10142754.0,
|
|
"step": 5510
|
|
},
|
|
{
|
|
"entropy": 5.436812019348144,
|
|
"epoch": 0.46065820247243566,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004983967134486215,
|
|
"loss": 5.2499,
|
|
"mean_token_accuracy": 0.1877599313855171,
|
|
"num_tokens": 10152114.0,
|
|
"step": 5515
|
|
},
|
|
{
|
|
"entropy": 5.351143932342529,
|
|
"epoch": 0.4610758436351487,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004983931639085088,
|
|
"loss": 5.1557,
|
|
"mean_token_accuracy": 0.19096697121858597,
|
|
"num_tokens": 10161562.0,
|
|
"step": 5520
|
|
},
|
|
{
|
|
"entropy": 5.45611047744751,
|
|
"epoch": 0.4614934847978617,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004983896104576298,
|
|
"loss": 5.2715,
|
|
"mean_token_accuracy": 0.18681198209524155,
|
|
"num_tokens": 10170461.0,
|
|
"step": 5525
|
|
},
|
|
{
|
|
"entropy": 5.362908458709716,
|
|
"epoch": 0.46191112596057465,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000498386053096047,
|
|
"loss": 5.274,
|
|
"mean_token_accuracy": 0.1872062012553215,
|
|
"num_tokens": 10179243.0,
|
|
"step": 5530
|
|
},
|
|
{
|
|
"entropy": 5.375006246566772,
|
|
"epoch": 0.4623287671232877,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004983824918238221,
|
|
"loss": 5.2075,
|
|
"mean_token_accuracy": 0.1902789369225502,
|
|
"num_tokens": 10187935.0,
|
|
"step": 5535
|
|
},
|
|
{
|
|
"entropy": 5.432381200790405,
|
|
"epoch": 0.46274640828600067,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000498378926641018,
|
|
"loss": 5.2808,
|
|
"mean_token_accuracy": 0.18302738815546035,
|
|
"num_tokens": 10196185.0,
|
|
"step": 5540
|
|
},
|
|
{
|
|
"entropy": 5.3857447624206545,
|
|
"epoch": 0.46316404944871364,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004983753575476969,
|
|
"loss": 5.2658,
|
|
"mean_token_accuracy": 0.18335500210523606,
|
|
"num_tokens": 10205373.0,
|
|
"step": 5545
|
|
},
|
|
{
|
|
"entropy": 5.405973052978515,
|
|
"epoch": 0.4635816906114267,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004983717845439212,
|
|
"loss": 5.243,
|
|
"mean_token_accuracy": 0.19455428719520568,
|
|
"num_tokens": 10214464.0,
|
|
"step": 5550
|
|
},
|
|
{
|
|
"entropy": 5.424784326553345,
|
|
"epoch": 0.46399933177413966,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004983682076297536,
|
|
"loss": 5.3229,
|
|
"mean_token_accuracy": 0.18389758318662644,
|
|
"num_tokens": 10224462.0,
|
|
"step": 5555
|
|
},
|
|
{
|
|
"entropy": 5.459895086288452,
|
|
"epoch": 0.46441697293685263,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004983646268052567,
|
|
"loss": 5.2367,
|
|
"mean_token_accuracy": 0.18775293081998826,
|
|
"num_tokens": 10233123.0,
|
|
"step": 5560
|
|
},
|
|
{
|
|
"entropy": 5.333229207992554,
|
|
"epoch": 0.46483461409956567,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004983610420704931,
|
|
"loss": 5.0822,
|
|
"mean_token_accuracy": 0.19521746039390564,
|
|
"num_tokens": 10241613.0,
|
|
"step": 5565
|
|
},
|
|
{
|
|
"entropy": 5.440250730514526,
|
|
"epoch": 0.46525225526227865,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004983574534255256,
|
|
"loss": 5.4372,
|
|
"mean_token_accuracy": 0.17527129352092743,
|
|
"num_tokens": 10251809.0,
|
|
"step": 5570
|
|
},
|
|
{
|
|
"entropy": 5.352139568328857,
|
|
"epoch": 0.4656698964249916,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000498353860870417,
|
|
"loss": 5.1216,
|
|
"mean_token_accuracy": 0.19288666397333146,
|
|
"num_tokens": 10260198.0,
|
|
"step": 5575
|
|
},
|
|
{
|
|
"entropy": 5.390357160568238,
|
|
"epoch": 0.46608753758770466,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004983502644052303,
|
|
"loss": 5.1815,
|
|
"mean_token_accuracy": 0.19071156680583953,
|
|
"num_tokens": 10268906.0,
|
|
"step": 5580
|
|
},
|
|
{
|
|
"entropy": 5.36174168586731,
|
|
"epoch": 0.46650517875041764,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004983466640300282,
|
|
"loss": 5.1131,
|
|
"mean_token_accuracy": 0.18751837760210038,
|
|
"num_tokens": 10278526.0,
|
|
"step": 5585
|
|
},
|
|
{
|
|
"entropy": 5.390116214752197,
|
|
"epoch": 0.4669228199131306,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004983430597448741,
|
|
"loss": 5.2434,
|
|
"mean_token_accuracy": 0.18560836166143418,
|
|
"num_tokens": 10287428.0,
|
|
"step": 5590
|
|
},
|
|
{
|
|
"entropy": 5.506964445114136,
|
|
"epoch": 0.46734046107584365,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004983394515498308,
|
|
"loss": 5.1983,
|
|
"mean_token_accuracy": 0.1844811961054802,
|
|
"num_tokens": 10297136.0,
|
|
"step": 5595
|
|
},
|
|
{
|
|
"entropy": 5.410887098312378,
|
|
"epoch": 0.46775810223855663,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004983358394449616,
|
|
"loss": 5.2765,
|
|
"mean_token_accuracy": 0.18754280358552933,
|
|
"num_tokens": 10305678.0,
|
|
"step": 5600
|
|
},
|
|
{
|
|
"entropy": 5.2654417037963865,
|
|
"epoch": 0.4681757434012696,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004983322234303297,
|
|
"loss": 5.1988,
|
|
"mean_token_accuracy": 0.18852692395448684,
|
|
"num_tokens": 10314690.0,
|
|
"step": 5605
|
|
},
|
|
{
|
|
"entropy": 5.348377323150634,
|
|
"epoch": 0.46859338456398264,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004983286035059984,
|
|
"loss": 5.1602,
|
|
"mean_token_accuracy": 0.19106952250003814,
|
|
"num_tokens": 10323521.0,
|
|
"step": 5610
|
|
},
|
|
{
|
|
"entropy": 5.4127795696258545,
|
|
"epoch": 0.4690110257266956,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004983249796720311,
|
|
"loss": 5.1905,
|
|
"mean_token_accuracy": 0.19329796284437178,
|
|
"num_tokens": 10333077.0,
|
|
"step": 5615
|
|
},
|
|
{
|
|
"entropy": 5.431782388687134,
|
|
"epoch": 0.4694286668894086,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004983213519284912,
|
|
"loss": 5.2205,
|
|
"mean_token_accuracy": 0.18967044204473496,
|
|
"num_tokens": 10342194.0,
|
|
"step": 5620
|
|
},
|
|
{
|
|
"entropy": 5.323764038085938,
|
|
"epoch": 0.46984630805212163,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004983177202754421,
|
|
"loss": 5.0621,
|
|
"mean_token_accuracy": 0.19803830236196518,
|
|
"num_tokens": 10351009.0,
|
|
"step": 5625
|
|
},
|
|
{
|
|
"entropy": 5.41808853149414,
|
|
"epoch": 0.4702639492148346,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004983140847129476,
|
|
"loss": 5.2783,
|
|
"mean_token_accuracy": 0.18249369263648987,
|
|
"num_tokens": 10360872.0,
|
|
"step": 5630
|
|
},
|
|
{
|
|
"entropy": 5.430299997329712,
|
|
"epoch": 0.4706815903775476,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004983104452410713,
|
|
"loss": 5.1754,
|
|
"mean_token_accuracy": 0.1885490745306015,
|
|
"num_tokens": 10370159.0,
|
|
"step": 5635
|
|
},
|
|
{
|
|
"entropy": 5.383899354934693,
|
|
"epoch": 0.4710992315402606,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004983068018598768,
|
|
"loss": 5.1723,
|
|
"mean_token_accuracy": 0.19473619759082794,
|
|
"num_tokens": 10379219.0,
|
|
"step": 5640
|
|
},
|
|
{
|
|
"entropy": 5.3625024318695065,
|
|
"epoch": 0.4715168727029736,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.000498303154569428,
|
|
"loss": 5.2137,
|
|
"mean_token_accuracy": 0.1863038271665573,
|
|
"num_tokens": 10389425.0,
|
|
"step": 5645
|
|
},
|
|
{
|
|
"entropy": 5.451694583892822,
|
|
"epoch": 0.4719345138656866,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004982995033697887,
|
|
"loss": 5.2286,
|
|
"mean_token_accuracy": 0.19073546230792998,
|
|
"num_tokens": 10398023.0,
|
|
"step": 5650
|
|
},
|
|
{
|
|
"entropy": 5.4090780258178714,
|
|
"epoch": 0.4723521550283996,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004982958482610226,
|
|
"loss": 5.1718,
|
|
"mean_token_accuracy": 0.19427365362644194,
|
|
"num_tokens": 10406578.0,
|
|
"step": 5655
|
|
},
|
|
{
|
|
"entropy": 5.289528942108154,
|
|
"epoch": 0.4727697961911126,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.000498292189243194,
|
|
"loss": 5.1769,
|
|
"mean_token_accuracy": 0.19172403216362,
|
|
"num_tokens": 10416448.0,
|
|
"step": 5660
|
|
},
|
|
{
|
|
"entropy": 5.445108842849732,
|
|
"epoch": 0.47318743735382557,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000498288526316367,
|
|
"loss": 5.1999,
|
|
"mean_token_accuracy": 0.18580440580844879,
|
|
"num_tokens": 10425414.0,
|
|
"step": 5665
|
|
},
|
|
{
|
|
"entropy": 5.403898859024048,
|
|
"epoch": 0.4736050785165386,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004982848594806054,
|
|
"loss": 5.1811,
|
|
"mean_token_accuracy": 0.19948876798152923,
|
|
"num_tokens": 10433900.0,
|
|
"step": 5670
|
|
},
|
|
{
|
|
"entropy": 5.4370215892791744,
|
|
"epoch": 0.4740227196792516,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004982811887359736,
|
|
"loss": 5.3001,
|
|
"mean_token_accuracy": 0.18371444642543794,
|
|
"num_tokens": 10443077.0,
|
|
"step": 5675
|
|
},
|
|
{
|
|
"entropy": 5.398310708999634,
|
|
"epoch": 0.47444036084196456,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004982775140825359,
|
|
"loss": 5.2305,
|
|
"mean_token_accuracy": 0.19003031849861146,
|
|
"num_tokens": 10452791.0,
|
|
"step": 5680
|
|
},
|
|
{
|
|
"entropy": 5.478526496887207,
|
|
"epoch": 0.4748580020046776,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004982738355203565,
|
|
"loss": 5.3936,
|
|
"mean_token_accuracy": 0.18002498000860215,
|
|
"num_tokens": 10462087.0,
|
|
"step": 5685
|
|
},
|
|
{
|
|
"entropy": 5.5195990085601805,
|
|
"epoch": 0.47527564316739057,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004982701530494998,
|
|
"loss": 5.3888,
|
|
"mean_token_accuracy": 0.1750195562839508,
|
|
"num_tokens": 10472576.0,
|
|
"step": 5690
|
|
},
|
|
{
|
|
"entropy": 5.404919528961182,
|
|
"epoch": 0.47569328433010355,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004982664666700304,
|
|
"loss": 5.1181,
|
|
"mean_token_accuracy": 0.20003928244113922,
|
|
"num_tokens": 10481176.0,
|
|
"step": 5695
|
|
},
|
|
{
|
|
"entropy": 5.38076376914978,
|
|
"epoch": 0.4761109254928166,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004982627763820128,
|
|
"loss": 5.2059,
|
|
"mean_token_accuracy": 0.18965410739183425,
|
|
"num_tokens": 10490558.0,
|
|
"step": 5700
|
|
},
|
|
{
|
|
"entropy": 5.408396530151367,
|
|
"epoch": 0.47652856665552956,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004982590821855115,
|
|
"loss": 5.274,
|
|
"mean_token_accuracy": 0.19038996398448943,
|
|
"num_tokens": 10499543.0,
|
|
"step": 5705
|
|
},
|
|
{
|
|
"entropy": 5.362735366821289,
|
|
"epoch": 0.47694620781824254,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004982553840805912,
|
|
"loss": 5.1621,
|
|
"mean_token_accuracy": 0.19401407837867737,
|
|
"num_tokens": 10508162.0,
|
|
"step": 5710
|
|
},
|
|
{
|
|
"entropy": 5.34212818145752,
|
|
"epoch": 0.4773638489809556,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004982516820673167,
|
|
"loss": 5.0836,
|
|
"mean_token_accuracy": 0.1903264433145523,
|
|
"num_tokens": 10516837.0,
|
|
"step": 5715
|
|
},
|
|
{
|
|
"entropy": 5.300382041931153,
|
|
"epoch": 0.47778149014366855,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004982479761457528,
|
|
"loss": 5.2244,
|
|
"mean_token_accuracy": 0.19203804284334183,
|
|
"num_tokens": 10526208.0,
|
|
"step": 5720
|
|
},
|
|
{
|
|
"entropy": 5.444773626327515,
|
|
"epoch": 0.47819913130638153,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004982442663159643,
|
|
"loss": 5.2555,
|
|
"mean_token_accuracy": 0.18101535737514496,
|
|
"num_tokens": 10536002.0,
|
|
"step": 5725
|
|
},
|
|
{
|
|
"entropy": 5.475929498672485,
|
|
"epoch": 0.47861677246909456,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004982405525780162,
|
|
"loss": 5.2441,
|
|
"mean_token_accuracy": 0.18552520126104355,
|
|
"num_tokens": 10545861.0,
|
|
"step": 5730
|
|
},
|
|
{
|
|
"entropy": 5.3596611499786375,
|
|
"epoch": 0.47903441363180754,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004982368349319736,
|
|
"loss": 5.147,
|
|
"mean_token_accuracy": 0.19177533984184264,
|
|
"num_tokens": 10555357.0,
|
|
"step": 5735
|
|
},
|
|
{
|
|
"entropy": 5.350248956680298,
|
|
"epoch": 0.4794520547945205,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004982331133779014,
|
|
"loss": 5.2263,
|
|
"mean_token_accuracy": 0.18407194167375565,
|
|
"num_tokens": 10564744.0,
|
|
"step": 5740
|
|
},
|
|
{
|
|
"entropy": 5.3497522354125975,
|
|
"epoch": 0.47986969595723356,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004982293879158649,
|
|
"loss": 5.1941,
|
|
"mean_token_accuracy": 0.19337435066699982,
|
|
"num_tokens": 10573736.0,
|
|
"step": 5745
|
|
},
|
|
{
|
|
"entropy": 5.380324411392212,
|
|
"epoch": 0.48028733711994653,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004982256585459293,
|
|
"loss": 5.252,
|
|
"mean_token_accuracy": 0.18973010331392287,
|
|
"num_tokens": 10583238.0,
|
|
"step": 5750
|
|
},
|
|
{
|
|
"entropy": 5.468371629714966,
|
|
"epoch": 0.4807049782826595,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004982219252681597,
|
|
"loss": 5.2951,
|
|
"mean_token_accuracy": 0.18508350402116774,
|
|
"num_tokens": 10592316.0,
|
|
"step": 5755
|
|
},
|
|
{
|
|
"entropy": 5.426727151870727,
|
|
"epoch": 0.48112261944537255,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004982181880826218,
|
|
"loss": 5.3192,
|
|
"mean_token_accuracy": 0.19533029198646545,
|
|
"num_tokens": 10601418.0,
|
|
"step": 5760
|
|
},
|
|
{
|
|
"entropy": 5.3590703964233395,
|
|
"epoch": 0.4815402606080855,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004982144469893807,
|
|
"loss": 5.2041,
|
|
"mean_token_accuracy": 0.1928260952234268,
|
|
"num_tokens": 10610513.0,
|
|
"step": 5765
|
|
},
|
|
{
|
|
"entropy": 5.3929990291595455,
|
|
"epoch": 0.4819579017707985,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000498210701988502,
|
|
"loss": 5.1422,
|
|
"mean_token_accuracy": 0.19776597917079924,
|
|
"num_tokens": 10619529.0,
|
|
"step": 5770
|
|
},
|
|
{
|
|
"entropy": 5.492319536209107,
|
|
"epoch": 0.48237554293351154,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004982069530800514,
|
|
"loss": 5.2251,
|
|
"mean_token_accuracy": 0.20145247578620912,
|
|
"num_tokens": 10628263.0,
|
|
"step": 5775
|
|
},
|
|
{
|
|
"entropy": 5.414431095123291,
|
|
"epoch": 0.4827931840962245,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004982032002640943,
|
|
"loss": 5.2551,
|
|
"mean_token_accuracy": 0.19498594105243683,
|
|
"num_tokens": 10637605.0,
|
|
"step": 5780
|
|
},
|
|
{
|
|
"entropy": 5.4010262966156,
|
|
"epoch": 0.48321082525893755,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004981994435406965,
|
|
"loss": 5.3177,
|
|
"mean_token_accuracy": 0.18424908220767974,
|
|
"num_tokens": 10647113.0,
|
|
"step": 5785
|
|
},
|
|
{
|
|
"entropy": 5.342437839508056,
|
|
"epoch": 0.4836284664216505,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004981956829099239,
|
|
"loss": 5.0705,
|
|
"mean_token_accuracy": 0.19768524020910264,
|
|
"num_tokens": 10655464.0,
|
|
"step": 5790
|
|
},
|
|
{
|
|
"entropy": 5.4189153671264645,
|
|
"epoch": 0.4840461075843635,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004981919183718422,
|
|
"loss": 5.1929,
|
|
"mean_token_accuracy": 0.1941748008131981,
|
|
"num_tokens": 10664689.0,
|
|
"step": 5795
|
|
},
|
|
{
|
|
"entropy": 5.292117357254028,
|
|
"epoch": 0.48446374874707654,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004981881499265173,
|
|
"loss": 5.0936,
|
|
"mean_token_accuracy": 0.19338988065719603,
|
|
"num_tokens": 10673440.0,
|
|
"step": 5800
|
|
},
|
|
{
|
|
"entropy": 5.337329292297364,
|
|
"epoch": 0.4848813899097895,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004981843775740151,
|
|
"loss": 5.2323,
|
|
"mean_token_accuracy": 0.19166841208934784,
|
|
"num_tokens": 10683075.0,
|
|
"step": 5805
|
|
},
|
|
{
|
|
"entropy": 5.395388603210449,
|
|
"epoch": 0.4852990310725025,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004981806013144017,
|
|
"loss": 5.1888,
|
|
"mean_token_accuracy": 0.19218732565641403,
|
|
"num_tokens": 10692663.0,
|
|
"step": 5810
|
|
},
|
|
{
|
|
"entropy": 5.365407085418701,
|
|
"epoch": 0.48571667223521553,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004981768211477434,
|
|
"loss": 5.081,
|
|
"mean_token_accuracy": 0.19704576283693315,
|
|
"num_tokens": 10702068.0,
|
|
"step": 5815
|
|
},
|
|
{
|
|
"entropy": 5.358780479431152,
|
|
"epoch": 0.4861343133979285,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.000498173037074106,
|
|
"loss": 5.2354,
|
|
"mean_token_accuracy": 0.18202263861894608,
|
|
"num_tokens": 10711230.0,
|
|
"step": 5820
|
|
},
|
|
{
|
|
"entropy": 5.319102954864502,
|
|
"epoch": 0.4865519545606415,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004981692490935561,
|
|
"loss": 5.2044,
|
|
"mean_token_accuracy": 0.19445421248674394,
|
|
"num_tokens": 10719651.0,
|
|
"step": 5825
|
|
},
|
|
{
|
|
"entropy": 5.340964365005493,
|
|
"epoch": 0.4869695957233545,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004981654572061597,
|
|
"loss": 5.2151,
|
|
"mean_token_accuracy": 0.19404265880584717,
|
|
"num_tokens": 10729342.0,
|
|
"step": 5830
|
|
},
|
|
{
|
|
"entropy": 5.378287601470947,
|
|
"epoch": 0.4873872368860675,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004981616614119836,
|
|
"loss": 5.2188,
|
|
"mean_token_accuracy": 0.19113572984933852,
|
|
"num_tokens": 10738617.0,
|
|
"step": 5835
|
|
},
|
|
{
|
|
"entropy": 5.4555384635925295,
|
|
"epoch": 0.4878048780487805,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004981578617110938,
|
|
"loss": 5.249,
|
|
"mean_token_accuracy": 0.19108872264623641,
|
|
"num_tokens": 10746881.0,
|
|
"step": 5840
|
|
},
|
|
{
|
|
"entropy": 5.3574690341949465,
|
|
"epoch": 0.4882225192114935,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004981540581035571,
|
|
"loss": 5.1101,
|
|
"mean_token_accuracy": 0.19686870127916337,
|
|
"num_tokens": 10755848.0,
|
|
"step": 5845
|
|
},
|
|
{
|
|
"entropy": 5.291342878341675,
|
|
"epoch": 0.4886401603742065,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00049815025058944,
|
|
"loss": 5.1152,
|
|
"mean_token_accuracy": 0.18852638751268386,
|
|
"num_tokens": 10765519.0,
|
|
"step": 5850
|
|
},
|
|
{
|
|
"entropy": 5.288955354690552,
|
|
"epoch": 0.48905780153691947,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004981464391688092,
|
|
"loss": 5.2264,
|
|
"mean_token_accuracy": 0.1883165329694748,
|
|
"num_tokens": 10776408.0,
|
|
"step": 5855
|
|
},
|
|
{
|
|
"entropy": 5.379974412918091,
|
|
"epoch": 0.4894754426996325,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004981426238417312,
|
|
"loss": 5.2238,
|
|
"mean_token_accuracy": 0.1914668157696724,
|
|
"num_tokens": 10785499.0,
|
|
"step": 5860
|
|
},
|
|
{
|
|
"entropy": 5.373927640914917,
|
|
"epoch": 0.4898930838623455,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004981388046082731,
|
|
"loss": 5.1774,
|
|
"mean_token_accuracy": 0.1898777186870575,
|
|
"num_tokens": 10794736.0,
|
|
"step": 5865
|
|
},
|
|
{
|
|
"entropy": 5.354801654815674,
|
|
"epoch": 0.49031072502505846,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004981349814685016,
|
|
"loss": 5.2583,
|
|
"mean_token_accuracy": 0.18822991847991943,
|
|
"num_tokens": 10804125.0,
|
|
"step": 5870
|
|
},
|
|
{
|
|
"entropy": 5.430789422988892,
|
|
"epoch": 0.4907283661877715,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004981311544224838,
|
|
"loss": 5.307,
|
|
"mean_token_accuracy": 0.1887751489877701,
|
|
"num_tokens": 10813465.0,
|
|
"step": 5875
|
|
},
|
|
{
|
|
"entropy": 5.352855205535889,
|
|
"epoch": 0.49114600735048447,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004981273234702864,
|
|
"loss": 5.1316,
|
|
"mean_token_accuracy": 0.19545983374118805,
|
|
"num_tokens": 10821550.0,
|
|
"step": 5880
|
|
},
|
|
{
|
|
"entropy": 5.317874622344971,
|
|
"epoch": 0.49156364851319745,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004981234886119767,
|
|
"loss": 5.1435,
|
|
"mean_token_accuracy": 0.19215249121189118,
|
|
"num_tokens": 10830683.0,
|
|
"step": 5885
|
|
},
|
|
{
|
|
"entropy": 5.393210458755493,
|
|
"epoch": 0.4919812896759105,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004981196498476217,
|
|
"loss": 5.1627,
|
|
"mean_token_accuracy": 0.19862073808908462,
|
|
"num_tokens": 10839492.0,
|
|
"step": 5890
|
|
},
|
|
{
|
|
"entropy": 5.290148782730102,
|
|
"epoch": 0.49239893083862346,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004981158071772887,
|
|
"loss": 5.0956,
|
|
"mean_token_accuracy": 0.19917930364608766,
|
|
"num_tokens": 10847998.0,
|
|
"step": 5895
|
|
},
|
|
{
|
|
"entropy": 5.230513000488282,
|
|
"epoch": 0.49281657200133644,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004981119606010449,
|
|
"loss": 5.0791,
|
|
"mean_token_accuracy": 0.19867262989282608,
|
|
"num_tokens": 10856438.0,
|
|
"step": 5900
|
|
},
|
|
{
|
|
"entropy": 5.26281852722168,
|
|
"epoch": 0.4932342131640495,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004981081101189577,
|
|
"loss": 5.1077,
|
|
"mean_token_accuracy": 0.192747999727726,
|
|
"num_tokens": 10865936.0,
|
|
"step": 5905
|
|
},
|
|
{
|
|
"entropy": 5.326478052139282,
|
|
"epoch": 0.49365185432676245,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004981042557310945,
|
|
"loss": 5.1064,
|
|
"mean_token_accuracy": 0.19702416360378266,
|
|
"num_tokens": 10874621.0,
|
|
"step": 5910
|
|
},
|
|
{
|
|
"entropy": 5.300664663314819,
|
|
"epoch": 0.49406949548947543,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004981003974375227,
|
|
"loss": 5.0667,
|
|
"mean_token_accuracy": 0.19391317218542098,
|
|
"num_tokens": 10883516.0,
|
|
"step": 5915
|
|
},
|
|
{
|
|
"entropy": 5.364432430267334,
|
|
"epoch": 0.49448713665218846,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004980965352383099,
|
|
"loss": 5.2187,
|
|
"mean_token_accuracy": 0.18803293257951736,
|
|
"num_tokens": 10892580.0,
|
|
"step": 5920
|
|
},
|
|
{
|
|
"entropy": 5.390553092956543,
|
|
"epoch": 0.49490477781490144,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004980926691335238,
|
|
"loss": 5.1395,
|
|
"mean_token_accuracy": 0.19519626051187516,
|
|
"num_tokens": 10901227.0,
|
|
"step": 5925
|
|
},
|
|
{
|
|
"entropy": 5.401871061325073,
|
|
"epoch": 0.4953224189776144,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004980887991232318,
|
|
"loss": 5.203,
|
|
"mean_token_accuracy": 0.18491297513246535,
|
|
"num_tokens": 10909454.0,
|
|
"step": 5930
|
|
},
|
|
{
|
|
"entropy": 5.464483308792114,
|
|
"epoch": 0.49574006014032745,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000498084925207502,
|
|
"loss": 5.2759,
|
|
"mean_token_accuracy": 0.18939323127269744,
|
|
"num_tokens": 10919792.0,
|
|
"step": 5935
|
|
},
|
|
{
|
|
"entropy": 5.343497657775879,
|
|
"epoch": 0.49615770130304043,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.000498081047386402,
|
|
"loss": 5.3033,
|
|
"mean_token_accuracy": 0.18820173144340516,
|
|
"num_tokens": 10930523.0,
|
|
"step": 5940
|
|
},
|
|
{
|
|
"entropy": 5.310845947265625,
|
|
"epoch": 0.4965753424657534,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004980771656599998,
|
|
"loss": 5.1732,
|
|
"mean_token_accuracy": 0.19256822913885116,
|
|
"num_tokens": 10940075.0,
|
|
"step": 5945
|
|
},
|
|
{
|
|
"entropy": 5.381923866271973,
|
|
"epoch": 0.49699298362846644,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004980732800283633,
|
|
"loss": 5.1638,
|
|
"mean_token_accuracy": 0.19154672026634217,
|
|
"num_tokens": 10949059.0,
|
|
"step": 5950
|
|
},
|
|
{
|
|
"entropy": 5.320337104797363,
|
|
"epoch": 0.4974106247911794,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004980693904915604,
|
|
"loss": 5.1501,
|
|
"mean_token_accuracy": 0.19438910484313965,
|
|
"num_tokens": 10958313.0,
|
|
"step": 5955
|
|
},
|
|
{
|
|
"entropy": 5.336426544189453,
|
|
"epoch": 0.4978282659538924,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004980654970496595,
|
|
"loss": 5.2016,
|
|
"mean_token_accuracy": 0.18726001381874086,
|
|
"num_tokens": 10967666.0,
|
|
"step": 5960
|
|
},
|
|
{
|
|
"entropy": 5.432378578186035,
|
|
"epoch": 0.49824590711660544,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004980615997027284,
|
|
"loss": 5.2318,
|
|
"mean_token_accuracy": 0.18868058323860168,
|
|
"num_tokens": 10976519.0,
|
|
"step": 5965
|
|
},
|
|
{
|
|
"entropy": 5.457491302490235,
|
|
"epoch": 0.4986635482793184,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004980576984508356,
|
|
"loss": 5.3376,
|
|
"mean_token_accuracy": 0.18108574599027633,
|
|
"num_tokens": 10987138.0,
|
|
"step": 5970
|
|
},
|
|
{
|
|
"entropy": 5.404650020599365,
|
|
"epoch": 0.4990811894420314,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004980537932940492,
|
|
"loss": 5.2079,
|
|
"mean_token_accuracy": 0.19051799178123474,
|
|
"num_tokens": 10996517.0,
|
|
"step": 5975
|
|
},
|
|
{
|
|
"entropy": 5.357486152648926,
|
|
"epoch": 0.4994988306047444,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004980498842324377,
|
|
"loss": 5.0894,
|
|
"mean_token_accuracy": 0.18881412744522094,
|
|
"num_tokens": 11006312.0,
|
|
"step": 5980
|
|
},
|
|
{
|
|
"entropy": 5.333321905136108,
|
|
"epoch": 0.4999164717674574,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004980459712660694,
|
|
"loss": 5.2052,
|
|
"mean_token_accuracy": 0.19695570319890976,
|
|
"num_tokens": 11015535.0,
|
|
"step": 5985
|
|
},
|
|
{
|
|
"entropy": 5.3520020008087155,
|
|
"epoch": 0.5003341129301704,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004980420543950131,
|
|
"loss": 5.1861,
|
|
"mean_token_accuracy": 0.19640239030122758,
|
|
"num_tokens": 11024887.0,
|
|
"step": 5990
|
|
},
|
|
{
|
|
"entropy": 5.249091339111328,
|
|
"epoch": 0.5007517540928834,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004980381336193371,
|
|
"loss": 5.059,
|
|
"mean_token_accuracy": 0.20034665763378143,
|
|
"num_tokens": 11033147.0,
|
|
"step": 5995
|
|
},
|
|
{
|
|
"entropy": 5.33840970993042,
|
|
"epoch": 0.5011693952555963,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004980342089391099,
|
|
"loss": 5.2179,
|
|
"mean_token_accuracy": 0.19177668243646623,
|
|
"num_tokens": 11042726.0,
|
|
"step": 6000
|
|
},
|
|
{
|
|
"epoch": 0.5011693952555963,
|
|
"eval_entropy": 5.128798316985059,
|
|
"eval_loss": 5.161733627319336,
|
|
"eval_mean_token_accuracy": 0.20298875240521067,
|
|
"eval_num_tokens": 11042726.0,
|
|
"eval_runtime": 20.8409,
|
|
"eval_samples_per_second": 1811.965,
|
|
"eval_steps_per_second": 226.526,
|
|
"step": 6000
|
|
},
|
|
{
|
|
"entropy": 5.392579174041748,
|
|
"epoch": 0.5015870364183094,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004980302803544006,
|
|
"loss": 5.2002,
|
|
"mean_token_accuracy": 0.19534078538417815,
|
|
"num_tokens": 11052181.0,
|
|
"step": 6005
|
|
},
|
|
{
|
|
"entropy": 5.389634037017823,
|
|
"epoch": 0.5020046775810224,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004980263478652778,
|
|
"loss": 5.2424,
|
|
"mean_token_accuracy": 0.1902779757976532,
|
|
"num_tokens": 11061586.0,
|
|
"step": 6010
|
|
},
|
|
{
|
|
"entropy": 5.491766691207886,
|
|
"epoch": 0.5024223187437353,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004980224114718102,
|
|
"loss": 5.2533,
|
|
"mean_token_accuracy": 0.1943809226155281,
|
|
"num_tokens": 11070914.0,
|
|
"step": 6015
|
|
},
|
|
{
|
|
"entropy": 5.298935890197754,
|
|
"epoch": 0.5028399599064484,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004980184711740669,
|
|
"loss": 5.0781,
|
|
"mean_token_accuracy": 0.20595989376306534,
|
|
"num_tokens": 11079836.0,
|
|
"step": 6020
|
|
},
|
|
{
|
|
"entropy": 5.2567322731018065,
|
|
"epoch": 0.5032576010691614,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004980145269721168,
|
|
"loss": 5.1011,
|
|
"mean_token_accuracy": 0.19717675745487212,
|
|
"num_tokens": 11088320.0,
|
|
"step": 6025
|
|
},
|
|
{
|
|
"entropy": 5.363692426681519,
|
|
"epoch": 0.5036752422318743,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000498010578866029,
|
|
"loss": 5.2644,
|
|
"mean_token_accuracy": 0.18924812078475953,
|
|
"num_tokens": 11097803.0,
|
|
"step": 6030
|
|
},
|
|
{
|
|
"entropy": 5.472511672973633,
|
|
"epoch": 0.5040928833945874,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004980066268558726,
|
|
"loss": 5.2869,
|
|
"mean_token_accuracy": 0.18986473679542543,
|
|
"num_tokens": 11107218.0,
|
|
"step": 6035
|
|
},
|
|
{
|
|
"entropy": 5.435642051696777,
|
|
"epoch": 0.5045105245573004,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004980026709417167,
|
|
"loss": 5.1853,
|
|
"mean_token_accuracy": 0.18860728293657303,
|
|
"num_tokens": 11115599.0,
|
|
"step": 6040
|
|
},
|
|
{
|
|
"entropy": 5.268574285507202,
|
|
"epoch": 0.5049281657200133,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004979987111236306,
|
|
"loss": 5.0732,
|
|
"mean_token_accuracy": 0.1984765887260437,
|
|
"num_tokens": 11124312.0,
|
|
"step": 6045
|
|
},
|
|
{
|
|
"entropy": 5.257491683959961,
|
|
"epoch": 0.5053458068827263,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004979947474016837,
|
|
"loss": 5.1849,
|
|
"mean_token_accuracy": 0.19398614764213562,
|
|
"num_tokens": 11133117.0,
|
|
"step": 6050
|
|
},
|
|
{
|
|
"entropy": 5.480657625198364,
|
|
"epoch": 0.5057634480454394,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004979907797759453,
|
|
"loss": 5.2499,
|
|
"mean_token_accuracy": 0.190121790766716,
|
|
"num_tokens": 11141972.0,
|
|
"step": 6055
|
|
},
|
|
{
|
|
"entropy": 5.488561344146729,
|
|
"epoch": 0.5061810892081523,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004979868082464849,
|
|
"loss": 5.2525,
|
|
"mean_token_accuracy": 0.19349999725818634,
|
|
"num_tokens": 11151416.0,
|
|
"step": 6060
|
|
},
|
|
{
|
|
"entropy": 5.325757694244385,
|
|
"epoch": 0.5065987303708653,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004979828328133719,
|
|
"loss": 5.2035,
|
|
"mean_token_accuracy": 0.19287971407175064,
|
|
"num_tokens": 11160727.0,
|
|
"step": 6065
|
|
},
|
|
{
|
|
"entropy": 5.335221290588379,
|
|
"epoch": 0.5070163715335784,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004979788534766762,
|
|
"loss": 5.1618,
|
|
"mean_token_accuracy": 0.18678613156080245,
|
|
"num_tokens": 11171350.0,
|
|
"step": 6070
|
|
},
|
|
{
|
|
"entropy": 5.3660393238067625,
|
|
"epoch": 0.5074340126962913,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004979748702364672,
|
|
"loss": 5.1445,
|
|
"mean_token_accuracy": 0.19064127057790756,
|
|
"num_tokens": 11180233.0,
|
|
"step": 6075
|
|
},
|
|
{
|
|
"entropy": 5.3487941265106205,
|
|
"epoch": 0.5078516538590043,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004979708830928147,
|
|
"loss": 5.1259,
|
|
"mean_token_accuracy": 0.19202678948640822,
|
|
"num_tokens": 11189269.0,
|
|
"step": 6080
|
|
},
|
|
{
|
|
"entropy": 5.341992282867432,
|
|
"epoch": 0.5082692950217174,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004979668920457884,
|
|
"loss": 5.2077,
|
|
"mean_token_accuracy": 0.19293300360441207,
|
|
"num_tokens": 11199072.0,
|
|
"step": 6085
|
|
},
|
|
{
|
|
"entropy": 5.33283953666687,
|
|
"epoch": 0.5086869361844303,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004979628970954584,
|
|
"loss": 5.1182,
|
|
"mean_token_accuracy": 0.20168853402137757,
|
|
"num_tokens": 11207164.0,
|
|
"step": 6090
|
|
},
|
|
{
|
|
"entropy": 5.337658071517945,
|
|
"epoch": 0.5091045773471433,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004979588982418944,
|
|
"loss": 5.1689,
|
|
"mean_token_accuracy": 0.18496512472629548,
|
|
"num_tokens": 11216557.0,
|
|
"step": 6095
|
|
},
|
|
{
|
|
"entropy": 5.495877647399903,
|
|
"epoch": 0.5095222185098564,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004979548954851666,
|
|
"loss": 5.3058,
|
|
"mean_token_accuracy": 0.1895919069647789,
|
|
"num_tokens": 11227277.0,
|
|
"step": 6100
|
|
},
|
|
{
|
|
"entropy": 5.3433582305908205,
|
|
"epoch": 0.5099398596725693,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000497950888825345,
|
|
"loss": 5.1017,
|
|
"mean_token_accuracy": 0.20004121214151382,
|
|
"num_tokens": 11236226.0,
|
|
"step": 6105
|
|
},
|
|
{
|
|
"entropy": 5.340034532546997,
|
|
"epoch": 0.5103575008352823,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004979468782624996,
|
|
"loss": 5.2086,
|
|
"mean_token_accuracy": 0.1939321532845497,
|
|
"num_tokens": 11245246.0,
|
|
"step": 6110
|
|
},
|
|
{
|
|
"entropy": 5.377697515487671,
|
|
"epoch": 0.5107751419979953,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004979428637967009,
|
|
"loss": 5.2689,
|
|
"mean_token_accuracy": 0.19204458743333816,
|
|
"num_tokens": 11254437.0,
|
|
"step": 6115
|
|
},
|
|
{
|
|
"entropy": 5.376149463653564,
|
|
"epoch": 0.5111927831607083,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004979388454280189,
|
|
"loss": 5.1101,
|
|
"mean_token_accuracy": 0.19771129190921782,
|
|
"num_tokens": 11262413.0,
|
|
"step": 6120
|
|
},
|
|
{
|
|
"entropy": 5.363088989257813,
|
|
"epoch": 0.5116104243234213,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000497934823156524,
|
|
"loss": 5.2988,
|
|
"mean_token_accuracy": 0.18558404445648194,
|
|
"num_tokens": 11272061.0,
|
|
"step": 6125
|
|
},
|
|
{
|
|
"entropy": 5.37300705909729,
|
|
"epoch": 0.5120280654861343,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004979307969822869,
|
|
"loss": 5.1335,
|
|
"mean_token_accuracy": 0.19915029108524324,
|
|
"num_tokens": 11281623.0,
|
|
"step": 6130
|
|
},
|
|
{
|
|
"entropy": 5.315994024276733,
|
|
"epoch": 0.5124457066488474,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004979267669053776,
|
|
"loss": 5.0069,
|
|
"mean_token_accuracy": 0.2073518916964531,
|
|
"num_tokens": 11290202.0,
|
|
"step": 6135
|
|
},
|
|
{
|
|
"entropy": 5.3649908065795895,
|
|
"epoch": 0.5128633478115603,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004979227329258671,
|
|
"loss": 5.2741,
|
|
"mean_token_accuracy": 0.19212478250265122,
|
|
"num_tokens": 11299040.0,
|
|
"step": 6140
|
|
},
|
|
{
|
|
"entropy": 5.389776039123535,
|
|
"epoch": 0.5132809889742733,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004979186950438256,
|
|
"loss": 5.1925,
|
|
"mean_token_accuracy": 0.19120557904243468,
|
|
"num_tokens": 11307938.0,
|
|
"step": 6145
|
|
},
|
|
{
|
|
"entropy": 5.35956335067749,
|
|
"epoch": 0.5136986301369864,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004979146532593243,
|
|
"loss": 5.1901,
|
|
"mean_token_accuracy": 0.1918809175491333,
|
|
"num_tokens": 11316915.0,
|
|
"step": 6150
|
|
},
|
|
{
|
|
"entropy": 5.390135335922241,
|
|
"epoch": 0.5141162712996993,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004979106075724334,
|
|
"loss": 5.1488,
|
|
"mean_token_accuracy": 0.1926642596721649,
|
|
"num_tokens": 11326634.0,
|
|
"step": 6155
|
|
},
|
|
{
|
|
"entropy": 5.47369532585144,
|
|
"epoch": 0.5145339124624123,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004979065579832242,
|
|
"loss": 5.3053,
|
|
"mean_token_accuracy": 0.18129904568195343,
|
|
"num_tokens": 11336502.0,
|
|
"step": 6160
|
|
},
|
|
{
|
|
"entropy": 5.359502744674683,
|
|
"epoch": 0.5149515536251253,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004979025044917673,
|
|
"loss": 5.2211,
|
|
"mean_token_accuracy": 0.18862180709838866,
|
|
"num_tokens": 11346125.0,
|
|
"step": 6165
|
|
},
|
|
{
|
|
"entropy": 5.447209692001342,
|
|
"epoch": 0.5153691947878383,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004978984470981339,
|
|
"loss": 5.3212,
|
|
"mean_token_accuracy": 0.1809088706970215,
|
|
"num_tokens": 11355713.0,
|
|
"step": 6170
|
|
},
|
|
{
|
|
"entropy": 5.377956771850586,
|
|
"epoch": 0.5157868359505513,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004978943858023946,
|
|
"loss": 5.1436,
|
|
"mean_token_accuracy": 0.19031920284032822,
|
|
"num_tokens": 11364726.0,
|
|
"step": 6175
|
|
},
|
|
{
|
|
"entropy": 5.355219125747681,
|
|
"epoch": 0.5162044771132643,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000497890320604621,
|
|
"loss": 5.1311,
|
|
"mean_token_accuracy": 0.19517320841550828,
|
|
"num_tokens": 11373779.0,
|
|
"step": 6180
|
|
},
|
|
{
|
|
"entropy": 5.271116304397583,
|
|
"epoch": 0.5166221182759773,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000497886251504884,
|
|
"loss": 5.1376,
|
|
"mean_token_accuracy": 0.19319186806678773,
|
|
"num_tokens": 11382641.0,
|
|
"step": 6185
|
|
},
|
|
{
|
|
"entropy": 5.326046276092529,
|
|
"epoch": 0.5170397594386903,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004978821785032549,
|
|
"loss": 5.1059,
|
|
"mean_token_accuracy": 0.19505345970392227,
|
|
"num_tokens": 11392200.0,
|
|
"step": 6190
|
|
},
|
|
{
|
|
"entropy": 5.399134016036987,
|
|
"epoch": 0.5174574006014033,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004978781015998048,
|
|
"loss": 5.2194,
|
|
"mean_token_accuracy": 0.18324108570814132,
|
|
"num_tokens": 11401884.0,
|
|
"step": 6195
|
|
},
|
|
{
|
|
"entropy": 5.401180648803711,
|
|
"epoch": 0.5178750417641163,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004978740207946056,
|
|
"loss": 5.1155,
|
|
"mean_token_accuracy": 0.20493513345718384,
|
|
"num_tokens": 11410710.0,
|
|
"step": 6200
|
|
},
|
|
{
|
|
"entropy": 5.283224391937256,
|
|
"epoch": 0.5182926829268293,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004978699360877281,
|
|
"loss": 5.0792,
|
|
"mean_token_accuracy": 0.20470337867736815,
|
|
"num_tokens": 11419622.0,
|
|
"step": 6205
|
|
},
|
|
{
|
|
"entropy": 5.2955403327941895,
|
|
"epoch": 0.5187103240895423,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004978658474792442,
|
|
"loss": 5.0935,
|
|
"mean_token_accuracy": 0.20088884085416794,
|
|
"num_tokens": 11427631.0,
|
|
"step": 6210
|
|
},
|
|
{
|
|
"entropy": 5.344830656051636,
|
|
"epoch": 0.5191279652522552,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004978617549692253,
|
|
"loss": 5.1592,
|
|
"mean_token_accuracy": 0.19466407001018524,
|
|
"num_tokens": 11437630.0,
|
|
"step": 6215
|
|
},
|
|
{
|
|
"entropy": 5.470110177993774,
|
|
"epoch": 0.5195456064149683,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004978576585577432,
|
|
"loss": 5.3574,
|
|
"mean_token_accuracy": 0.17846949845552446,
|
|
"num_tokens": 11447962.0,
|
|
"step": 6220
|
|
},
|
|
{
|
|
"entropy": 5.456324243545533,
|
|
"epoch": 0.5199632475776813,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004978535582448695,
|
|
"loss": 5.2236,
|
|
"mean_token_accuracy": 0.1870883971452713,
|
|
"num_tokens": 11458154.0,
|
|
"step": 6225
|
|
},
|
|
{
|
|
"entropy": 5.301339769363404,
|
|
"epoch": 0.5203808887403942,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004978494540306761,
|
|
"loss": 5.063,
|
|
"mean_token_accuracy": 0.20015534162521362,
|
|
"num_tokens": 11467449.0,
|
|
"step": 6230
|
|
},
|
|
{
|
|
"entropy": 5.369253540039063,
|
|
"epoch": 0.5207985299031073,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004978453459152346,
|
|
"loss": 5.3532,
|
|
"mean_token_accuracy": 0.1816184863448143,
|
|
"num_tokens": 11477775.0,
|
|
"step": 6235
|
|
},
|
|
{
|
|
"entropy": 5.388203430175781,
|
|
"epoch": 0.5212161710658203,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004978412338986172,
|
|
"loss": 5.1043,
|
|
"mean_token_accuracy": 0.19701416194438934,
|
|
"num_tokens": 11486921.0,
|
|
"step": 6240
|
|
},
|
|
{
|
|
"entropy": 5.292043542861938,
|
|
"epoch": 0.5216338122285332,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004978371179808958,
|
|
"loss": 5.1337,
|
|
"mean_token_accuracy": 0.19857128262519835,
|
|
"num_tokens": 11496562.0,
|
|
"step": 6245
|
|
},
|
|
{
|
|
"entropy": 5.339953660964966,
|
|
"epoch": 0.5220514533912463,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004978329981621424,
|
|
"loss": 5.0972,
|
|
"mean_token_accuracy": 0.19187704026699065,
|
|
"num_tokens": 11504906.0,
|
|
"step": 6250
|
|
},
|
|
{
|
|
"entropy": 5.2793288230896,
|
|
"epoch": 0.5224690945539593,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000497828874442429,
|
|
"loss": 5.1473,
|
|
"mean_token_accuracy": 0.1895140916109085,
|
|
"num_tokens": 11513757.0,
|
|
"step": 6255
|
|
},
|
|
{
|
|
"entropy": 5.297783422470093,
|
|
"epoch": 0.5228867357166722,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.000497824746821828,
|
|
"loss": 5.1575,
|
|
"mean_token_accuracy": 0.19044381976127625,
|
|
"num_tokens": 11523195.0,
|
|
"step": 6260
|
|
},
|
|
{
|
|
"entropy": 5.4000497341156,
|
|
"epoch": 0.5233043768793852,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004978206153004117,
|
|
"loss": 5.2021,
|
|
"mean_token_accuracy": 0.1967186450958252,
|
|
"num_tokens": 11532348.0,
|
|
"step": 6265
|
|
},
|
|
{
|
|
"entropy": 5.387604427337647,
|
|
"epoch": 0.5237220180420983,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004978164798782523,
|
|
"loss": 5.1932,
|
|
"mean_token_accuracy": 0.19440121650695802,
|
|
"num_tokens": 11542356.0,
|
|
"step": 6270
|
|
},
|
|
{
|
|
"entropy": 5.340060567855835,
|
|
"epoch": 0.5241396592048112,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004978123405554221,
|
|
"loss": 5.1859,
|
|
"mean_token_accuracy": 0.1988328918814659,
|
|
"num_tokens": 11550914.0,
|
|
"step": 6275
|
|
},
|
|
{
|
|
"entropy": 5.370529270172119,
|
|
"epoch": 0.5245573003675242,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004978081973319938,
|
|
"loss": 5.1451,
|
|
"mean_token_accuracy": 0.19870750308036805,
|
|
"num_tokens": 11559314.0,
|
|
"step": 6280
|
|
},
|
|
{
|
|
"entropy": 5.313170957565307,
|
|
"epoch": 0.5249749415302373,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004978040502080398,
|
|
"loss": 5.118,
|
|
"mean_token_accuracy": 0.19605566263198854,
|
|
"num_tokens": 11567990.0,
|
|
"step": 6285
|
|
},
|
|
{
|
|
"entropy": 5.331792831420898,
|
|
"epoch": 0.5253925826929502,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004977998991836327,
|
|
"loss": 5.1423,
|
|
"mean_token_accuracy": 0.19811130315065384,
|
|
"num_tokens": 11577133.0,
|
|
"step": 6290
|
|
},
|
|
{
|
|
"entropy": 5.367706727981568,
|
|
"epoch": 0.5258102238556632,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004977957442588451,
|
|
"loss": 5.2204,
|
|
"mean_token_accuracy": 0.1907789871096611,
|
|
"num_tokens": 11585330.0,
|
|
"step": 6295
|
|
},
|
|
{
|
|
"entropy": 5.439990043640137,
|
|
"epoch": 0.5262278650183763,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004977915854337498,
|
|
"loss": 5.1716,
|
|
"mean_token_accuracy": 0.1921030357480049,
|
|
"num_tokens": 11595005.0,
|
|
"step": 6300
|
|
},
|
|
{
|
|
"entropy": 5.291791105270386,
|
|
"epoch": 0.5266455061810892,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004977874227084197,
|
|
"loss": 5.068,
|
|
"mean_token_accuracy": 0.20003140717744827,
|
|
"num_tokens": 11603969.0,
|
|
"step": 6305
|
|
},
|
|
{
|
|
"entropy": 5.287006568908692,
|
|
"epoch": 0.5270631473438022,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004977832560829277,
|
|
"loss": 5.1375,
|
|
"mean_token_accuracy": 0.19020287543535233,
|
|
"num_tokens": 11613118.0,
|
|
"step": 6310
|
|
},
|
|
{
|
|
"entropy": 5.351668500900269,
|
|
"epoch": 0.5274807885065153,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004977790855573464,
|
|
"loss": 5.0607,
|
|
"mean_token_accuracy": 0.2026047885417938,
|
|
"num_tokens": 11621799.0,
|
|
"step": 6315
|
|
},
|
|
{
|
|
"entropy": 5.283554363250732,
|
|
"epoch": 0.5278984296692282,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004977749111317492,
|
|
"loss": 5.1484,
|
|
"mean_token_accuracy": 0.19796689748764038,
|
|
"num_tokens": 11630557.0,
|
|
"step": 6320
|
|
},
|
|
{
|
|
"entropy": 5.3494213104248045,
|
|
"epoch": 0.5283160708319412,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000497770732806209,
|
|
"loss": 5.1706,
|
|
"mean_token_accuracy": 0.198416106402874,
|
|
"num_tokens": 11639179.0,
|
|
"step": 6325
|
|
},
|
|
{
|
|
"entropy": 5.408968734741211,
|
|
"epoch": 0.5287337119946542,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000497766550580799,
|
|
"loss": 5.2689,
|
|
"mean_token_accuracy": 0.18869854658842086,
|
|
"num_tokens": 11648273.0,
|
|
"step": 6330
|
|
},
|
|
{
|
|
"entropy": 5.348643159866333,
|
|
"epoch": 0.5291513531573672,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004977623644555923,
|
|
"loss": 5.1808,
|
|
"mean_token_accuracy": 0.18637329041957856,
|
|
"num_tokens": 11656372.0,
|
|
"step": 6335
|
|
},
|
|
{
|
|
"entropy": 5.365545225143433,
|
|
"epoch": 0.5295689943200802,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004977581744306624,
|
|
"loss": 5.1185,
|
|
"mean_token_accuracy": 0.20012644678354263,
|
|
"num_tokens": 11665007.0,
|
|
"step": 6340
|
|
},
|
|
{
|
|
"entropy": 5.370207166671753,
|
|
"epoch": 0.5299866354827932,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004977539805060824,
|
|
"loss": 5.2293,
|
|
"mean_token_accuracy": 0.19181876629590988,
|
|
"num_tokens": 11674519.0,
|
|
"step": 6345
|
|
},
|
|
{
|
|
"entropy": 5.401744079589844,
|
|
"epoch": 0.5304042766455062,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004977497826819259,
|
|
"loss": 5.1526,
|
|
"mean_token_accuracy": 0.19267868399620056,
|
|
"num_tokens": 11683705.0,
|
|
"step": 6350
|
|
},
|
|
{
|
|
"entropy": 5.315210485458374,
|
|
"epoch": 0.5308219178082192,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004977455809582664,
|
|
"loss": 5.1177,
|
|
"mean_token_accuracy": 0.19677025228738784,
|
|
"num_tokens": 11693152.0,
|
|
"step": 6355
|
|
},
|
|
{
|
|
"entropy": 5.332680559158325,
|
|
"epoch": 0.5312395589709322,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004977413753351772,
|
|
"loss": 5.1507,
|
|
"mean_token_accuracy": 0.18915897011756896,
|
|
"num_tokens": 11702584.0,
|
|
"step": 6360
|
|
},
|
|
{
|
|
"entropy": 5.32446551322937,
|
|
"epoch": 0.5316572001336451,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004977371658127323,
|
|
"loss": 5.1913,
|
|
"mean_token_accuracy": 0.19093988090753555,
|
|
"num_tokens": 11711633.0,
|
|
"step": 6365
|
|
},
|
|
{
|
|
"entropy": 5.349480628967285,
|
|
"epoch": 0.5320748412963582,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004977329523910051,
|
|
"loss": 5.1371,
|
|
"mean_token_accuracy": 0.19278361648321152,
|
|
"num_tokens": 11720116.0,
|
|
"step": 6370
|
|
},
|
|
{
|
|
"entropy": 5.4168623924255375,
|
|
"epoch": 0.5324924824590712,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004977287350700695,
|
|
"loss": 5.2351,
|
|
"mean_token_accuracy": 0.19008343368768693,
|
|
"num_tokens": 11729564.0,
|
|
"step": 6375
|
|
},
|
|
{
|
|
"entropy": 5.3386941909790036,
|
|
"epoch": 0.5329101236217841,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004977245138499993,
|
|
"loss": 5.095,
|
|
"mean_token_accuracy": 0.2036321446299553,
|
|
"num_tokens": 11737935.0,
|
|
"step": 6380
|
|
},
|
|
{
|
|
"entropy": 5.314829730987549,
|
|
"epoch": 0.5333277647844972,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004977202887308684,
|
|
"loss": 5.071,
|
|
"mean_token_accuracy": 0.19733900874853133,
|
|
"num_tokens": 11745989.0,
|
|
"step": 6385
|
|
},
|
|
{
|
|
"entropy": 5.331277656555176,
|
|
"epoch": 0.5337454059472102,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004977160597127507,
|
|
"loss": 5.2443,
|
|
"mean_token_accuracy": 0.1911775141954422,
|
|
"num_tokens": 11755530.0,
|
|
"step": 6390
|
|
},
|
|
{
|
|
"entropy": 5.357501792907715,
|
|
"epoch": 0.5341630471099231,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004977118267957204,
|
|
"loss": 5.198,
|
|
"mean_token_accuracy": 0.18840063512325286,
|
|
"num_tokens": 11764546.0,
|
|
"step": 6395
|
|
},
|
|
{
|
|
"entropy": 5.450428247451782,
|
|
"epoch": 0.5345806882726362,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004977075899798513,
|
|
"loss": 5.3313,
|
|
"mean_token_accuracy": 0.18829478472471237,
|
|
"num_tokens": 11774117.0,
|
|
"step": 6400
|
|
},
|
|
{
|
|
"entropy": 5.377129030227661,
|
|
"epoch": 0.5349983294353492,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000497703349265218,
|
|
"loss": 5.1008,
|
|
"mean_token_accuracy": 0.20352084934711456,
|
|
"num_tokens": 11782952.0,
|
|
"step": 6405
|
|
},
|
|
{
|
|
"entropy": 5.3871293544769285,
|
|
"epoch": 0.5354159705980621,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004976991046518943,
|
|
"loss": 5.2743,
|
|
"mean_token_accuracy": 0.1843955248594284,
|
|
"num_tokens": 11792369.0,
|
|
"step": 6410
|
|
},
|
|
{
|
|
"entropy": 5.359866094589234,
|
|
"epoch": 0.5358336117607752,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004976948561399549,
|
|
"loss": 5.1126,
|
|
"mean_token_accuracy": 0.1998010128736496,
|
|
"num_tokens": 11801365.0,
|
|
"step": 6415
|
|
},
|
|
{
|
|
"entropy": 5.386413145065307,
|
|
"epoch": 0.5362512529234882,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004976906037294738,
|
|
"loss": 5.1722,
|
|
"mean_token_accuracy": 0.19516139179468156,
|
|
"num_tokens": 11809785.0,
|
|
"step": 6420
|
|
},
|
|
{
|
|
"entropy": 5.317812061309814,
|
|
"epoch": 0.5366688940862011,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004976863474205257,
|
|
"loss": 5.0701,
|
|
"mean_token_accuracy": 0.19765079468488694,
|
|
"num_tokens": 11817978.0,
|
|
"step": 6425
|
|
},
|
|
{
|
|
"entropy": 5.354518747329712,
|
|
"epoch": 0.5370865352489141,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004976820872131851,
|
|
"loss": 5.1852,
|
|
"mean_token_accuracy": 0.1935555264353752,
|
|
"num_tokens": 11827796.0,
|
|
"step": 6430
|
|
},
|
|
{
|
|
"entropy": 5.261296987533569,
|
|
"epoch": 0.5375041764116272,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004976778231075266,
|
|
"loss": 5.0466,
|
|
"mean_token_accuracy": 0.19626055508852006,
|
|
"num_tokens": 11836439.0,
|
|
"step": 6435
|
|
},
|
|
{
|
|
"entropy": 5.366777753829956,
|
|
"epoch": 0.5379218175743401,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004976735551036245,
|
|
"loss": 5.248,
|
|
"mean_token_accuracy": 0.1846526250243187,
|
|
"num_tokens": 11845268.0,
|
|
"step": 6440
|
|
},
|
|
{
|
|
"entropy": 5.414008569717407,
|
|
"epoch": 0.5383394587370531,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.000497669283201554,
|
|
"loss": 5.1656,
|
|
"mean_token_accuracy": 0.19413827061653138,
|
|
"num_tokens": 11855185.0,
|
|
"step": 6445
|
|
},
|
|
{
|
|
"entropy": 5.306928062438965,
|
|
"epoch": 0.5387570998997662,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004976650074013895,
|
|
"loss": 5.2031,
|
|
"mean_token_accuracy": 0.1889431208372116,
|
|
"num_tokens": 11865073.0,
|
|
"step": 6450
|
|
},
|
|
{
|
|
"entropy": 5.353112697601318,
|
|
"epoch": 0.5391747410624791,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004976607277032061,
|
|
"loss": 5.1885,
|
|
"mean_token_accuracy": 0.19165299087762833,
|
|
"num_tokens": 11875004.0,
|
|
"step": 6455
|
|
},
|
|
{
|
|
"entropy": 5.39293532371521,
|
|
"epoch": 0.5395923822251921,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004976564441070788,
|
|
"loss": 5.1839,
|
|
"mean_token_accuracy": 0.18849599063396455,
|
|
"num_tokens": 11884905.0,
|
|
"step": 6460
|
|
},
|
|
{
|
|
"entropy": 5.385581302642822,
|
|
"epoch": 0.5400100233879052,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004976521566130823,
|
|
"loss": 5.1747,
|
|
"mean_token_accuracy": 0.18683718591928483,
|
|
"num_tokens": 11894669.0,
|
|
"step": 6465
|
|
},
|
|
{
|
|
"entropy": 5.468428373336792,
|
|
"epoch": 0.5404276645506181,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004976478652212918,
|
|
"loss": 5.3486,
|
|
"mean_token_accuracy": 0.18105758726596832,
|
|
"num_tokens": 11904127.0,
|
|
"step": 6470
|
|
},
|
|
{
|
|
"entropy": 5.39544448852539,
|
|
"epoch": 0.5408453057133311,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004976435699317824,
|
|
"loss": 5.1839,
|
|
"mean_token_accuracy": 0.1931723266839981,
|
|
"num_tokens": 11912031.0,
|
|
"step": 6475
|
|
},
|
|
{
|
|
"entropy": 5.286249876022339,
|
|
"epoch": 0.5412629468760441,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004976392707446293,
|
|
"loss": 5.091,
|
|
"mean_token_accuracy": 0.20129090398550034,
|
|
"num_tokens": 11920961.0,
|
|
"step": 6480
|
|
},
|
|
{
|
|
"entropy": 5.430025577545166,
|
|
"epoch": 0.5416805880387571,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004976349676599078,
|
|
"loss": 5.2408,
|
|
"mean_token_accuracy": 0.19328033179044724,
|
|
"num_tokens": 11930454.0,
|
|
"step": 6485
|
|
},
|
|
{
|
|
"entropy": 5.287836027145386,
|
|
"epoch": 0.5420982292014701,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004976306606776932,
|
|
"loss": 5.0443,
|
|
"mean_token_accuracy": 0.19630483388900757,
|
|
"num_tokens": 11938610.0,
|
|
"step": 6490
|
|
},
|
|
{
|
|
"entropy": 5.32088189125061,
|
|
"epoch": 0.5425158703641831,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004976263497980609,
|
|
"loss": 5.2076,
|
|
"mean_token_accuracy": 0.190990050137043,
|
|
"num_tokens": 11947882.0,
|
|
"step": 6495
|
|
},
|
|
{
|
|
"entropy": 5.345630741119384,
|
|
"epoch": 0.5429335115268961,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004976220350210864,
|
|
"loss": 5.1993,
|
|
"mean_token_accuracy": 0.19136472791433334,
|
|
"num_tokens": 11957552.0,
|
|
"step": 6500
|
|
},
|
|
{
|
|
"entropy": 5.347573947906494,
|
|
"epoch": 0.5433511526896091,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004976177163468451,
|
|
"loss": 5.1188,
|
|
"mean_token_accuracy": 0.19805283546447755,
|
|
"num_tokens": 11967350.0,
|
|
"step": 6505
|
|
},
|
|
{
|
|
"entropy": 5.318794822692871,
|
|
"epoch": 0.5437687938523221,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004976133937754128,
|
|
"loss": 5.1315,
|
|
"mean_token_accuracy": 0.19716765284538268,
|
|
"num_tokens": 11976107.0,
|
|
"step": 6510
|
|
},
|
|
{
|
|
"entropy": 5.346179676055908,
|
|
"epoch": 0.544186435015035,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004976090673068651,
|
|
"loss": 5.1353,
|
|
"mean_token_accuracy": 0.2032754361629486,
|
|
"num_tokens": 11985059.0,
|
|
"step": 6515
|
|
},
|
|
{
|
|
"entropy": 5.351248455047608,
|
|
"epoch": 0.5446040761777481,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004976047369412778,
|
|
"loss": 5.1053,
|
|
"mean_token_accuracy": 0.19469528198242186,
|
|
"num_tokens": 11993453.0,
|
|
"step": 6520
|
|
},
|
|
{
|
|
"entropy": 5.209239292144775,
|
|
"epoch": 0.5450217173404611,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004976004026787266,
|
|
"loss": 5.078,
|
|
"mean_token_accuracy": 0.1995821103453636,
|
|
"num_tokens": 12002524.0,
|
|
"step": 6525
|
|
},
|
|
{
|
|
"entropy": 5.27763819694519,
|
|
"epoch": 0.545439358503174,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004975960645192873,
|
|
"loss": 5.1339,
|
|
"mean_token_accuracy": 0.20042127519845962,
|
|
"num_tokens": 12011516.0,
|
|
"step": 6530
|
|
},
|
|
{
|
|
"entropy": 5.38931794166565,
|
|
"epoch": 0.5458569996658871,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004975917224630359,
|
|
"loss": 5.1692,
|
|
"mean_token_accuracy": 0.1899636819958687,
|
|
"num_tokens": 12020058.0,
|
|
"step": 6535
|
|
},
|
|
{
|
|
"entropy": 5.391335487365723,
|
|
"epoch": 0.5462746408286001,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004975873765100487,
|
|
"loss": 5.2737,
|
|
"mean_token_accuracy": 0.19032340496778488,
|
|
"num_tokens": 12029167.0,
|
|
"step": 6540
|
|
},
|
|
{
|
|
"entropy": 5.414868116378784,
|
|
"epoch": 0.546692281991313,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004975830266604013,
|
|
"loss": 5.2169,
|
|
"mean_token_accuracy": 0.19321169704198837,
|
|
"num_tokens": 12038298.0,
|
|
"step": 6545
|
|
},
|
|
{
|
|
"entropy": 5.3901842594146725,
|
|
"epoch": 0.5471099231540261,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004975786729141702,
|
|
"loss": 5.142,
|
|
"mean_token_accuracy": 0.1915355607867241,
|
|
"num_tokens": 12047437.0,
|
|
"step": 6550
|
|
},
|
|
{
|
|
"entropy": 5.343628978729248,
|
|
"epoch": 0.5475275643167391,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004975743152714314,
|
|
"loss": 5.1977,
|
|
"mean_token_accuracy": 0.1963498279452324,
|
|
"num_tokens": 12055821.0,
|
|
"step": 6555
|
|
},
|
|
{
|
|
"entropy": 5.354809141159057,
|
|
"epoch": 0.547945205479452,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004975699537322616,
|
|
"loss": 5.071,
|
|
"mean_token_accuracy": 0.20276693105697632,
|
|
"num_tokens": 12064378.0,
|
|
"step": 6560
|
|
},
|
|
{
|
|
"entropy": 5.294686222076416,
|
|
"epoch": 0.5483628466421651,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004975655882967366,
|
|
"loss": 5.1261,
|
|
"mean_token_accuracy": 0.19267136305570604,
|
|
"num_tokens": 12073110.0,
|
|
"step": 6565
|
|
},
|
|
{
|
|
"entropy": 5.349828910827637,
|
|
"epoch": 0.5487804878048781,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004975612189649331,
|
|
"loss": 5.1567,
|
|
"mean_token_accuracy": 0.19478155225515364,
|
|
"num_tokens": 12081224.0,
|
|
"step": 6570
|
|
},
|
|
{
|
|
"entropy": 5.3753687858581545,
|
|
"epoch": 0.549198128967591,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004975568457369276,
|
|
"loss": 5.2122,
|
|
"mean_token_accuracy": 0.19452133178710937,
|
|
"num_tokens": 12090279.0,
|
|
"step": 6575
|
|
},
|
|
{
|
|
"entropy": 5.371964836120606,
|
|
"epoch": 0.549615770130304,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004975524686127966,
|
|
"loss": 5.1921,
|
|
"mean_token_accuracy": 0.19338359087705612,
|
|
"num_tokens": 12098818.0,
|
|
"step": 6580
|
|
},
|
|
{
|
|
"entropy": 5.327710771560669,
|
|
"epoch": 0.5500334112930171,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004975480875926168,
|
|
"loss": 5.1468,
|
|
"mean_token_accuracy": 0.20131338834762574,
|
|
"num_tokens": 12107358.0,
|
|
"step": 6585
|
|
},
|
|
{
|
|
"entropy": 5.347161960601807,
|
|
"epoch": 0.55045105245573,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004975437026764648,
|
|
"loss": 5.2072,
|
|
"mean_token_accuracy": 0.18581592291593552,
|
|
"num_tokens": 12116802.0,
|
|
"step": 6590
|
|
},
|
|
{
|
|
"entropy": 5.388274431228638,
|
|
"epoch": 0.550868693618443,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004975393138644175,
|
|
"loss": 5.13,
|
|
"mean_token_accuracy": 0.19624195247888565,
|
|
"num_tokens": 12126347.0,
|
|
"step": 6595
|
|
},
|
|
{
|
|
"entropy": 5.266183519363404,
|
|
"epoch": 0.5512863347811561,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004975349211565515,
|
|
"loss": 5.0938,
|
|
"mean_token_accuracy": 0.19580602645874023,
|
|
"num_tokens": 12136138.0,
|
|
"step": 6600
|
|
},
|
|
{
|
|
"entropy": 5.254367828369141,
|
|
"epoch": 0.551703975943869,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.000497530524552944,
|
|
"loss": 5.1656,
|
|
"mean_token_accuracy": 0.19330661594867707,
|
|
"num_tokens": 12146436.0,
|
|
"step": 6605
|
|
},
|
|
{
|
|
"entropy": 5.370379114151001,
|
|
"epoch": 0.552121617106582,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004975261240536716,
|
|
"loss": 5.178,
|
|
"mean_token_accuracy": 0.19154346436262132,
|
|
"num_tokens": 12157003.0,
|
|
"step": 6610
|
|
},
|
|
{
|
|
"entropy": 5.356114482879638,
|
|
"epoch": 0.5525392582692951,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004975217196588117,
|
|
"loss": 5.108,
|
|
"mean_token_accuracy": 0.2029719516634941,
|
|
"num_tokens": 12166671.0,
|
|
"step": 6615
|
|
},
|
|
{
|
|
"entropy": 5.289737892150879,
|
|
"epoch": 0.552956899432008,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004975173113684413,
|
|
"loss": 5.1529,
|
|
"mean_token_accuracy": 0.1971219703555107,
|
|
"num_tokens": 12176474.0,
|
|
"step": 6620
|
|
},
|
|
{
|
|
"entropy": 5.346948766708374,
|
|
"epoch": 0.553374540594721,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004975128991826374,
|
|
"loss": 5.1435,
|
|
"mean_token_accuracy": 0.19717600494623183,
|
|
"num_tokens": 12185307.0,
|
|
"step": 6625
|
|
},
|
|
{
|
|
"entropy": 5.376376533508301,
|
|
"epoch": 0.553792181757434,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004975084831014774,
|
|
"loss": 5.108,
|
|
"mean_token_accuracy": 0.1940117746591568,
|
|
"num_tokens": 12195179.0,
|
|
"step": 6630
|
|
},
|
|
{
|
|
"entropy": 5.342315626144409,
|
|
"epoch": 0.554209822920147,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004975040631250386,
|
|
"loss": 5.1737,
|
|
"mean_token_accuracy": 0.20250627696514129,
|
|
"num_tokens": 12204083.0,
|
|
"step": 6635
|
|
},
|
|
{
|
|
"entropy": 5.2787923336029055,
|
|
"epoch": 0.55462746408286,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004974996392533983,
|
|
"loss": 5.1052,
|
|
"mean_token_accuracy": 0.20077962279319764,
|
|
"num_tokens": 12213322.0,
|
|
"step": 6640
|
|
},
|
|
{
|
|
"entropy": 5.339088201522827,
|
|
"epoch": 0.555045105245573,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000497495211486634,
|
|
"loss": 5.102,
|
|
"mean_token_accuracy": 0.20010723322629928,
|
|
"num_tokens": 12222305.0,
|
|
"step": 6645
|
|
},
|
|
{
|
|
"entropy": 5.3519268989562985,
|
|
"epoch": 0.555462746408286,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004974907798248232,
|
|
"loss": 5.2078,
|
|
"mean_token_accuracy": 0.1935238003730774,
|
|
"num_tokens": 12232196.0,
|
|
"step": 6650
|
|
},
|
|
{
|
|
"entropy": 5.34990348815918,
|
|
"epoch": 0.555880387570999,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004974863442680434,
|
|
"loss": 5.1518,
|
|
"mean_token_accuracy": 0.19610499292612077,
|
|
"num_tokens": 12241914.0,
|
|
"step": 6655
|
|
},
|
|
{
|
|
"entropy": 5.208635902404785,
|
|
"epoch": 0.556298028733712,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004974819048163725,
|
|
"loss": 5.0471,
|
|
"mean_token_accuracy": 0.20544617623090744,
|
|
"num_tokens": 12250185.0,
|
|
"step": 6660
|
|
},
|
|
{
|
|
"entropy": 5.3693469047546385,
|
|
"epoch": 0.556715669896425,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000497477461469888,
|
|
"loss": 5.2177,
|
|
"mean_token_accuracy": 0.18970588743686675,
|
|
"num_tokens": 12258954.0,
|
|
"step": 6665
|
|
},
|
|
{
|
|
"entropy": 5.409700918197632,
|
|
"epoch": 0.557133311059138,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004974730142286677,
|
|
"loss": 5.2277,
|
|
"mean_token_accuracy": 0.18751125782728195,
|
|
"num_tokens": 12268320.0,
|
|
"step": 6670
|
|
},
|
|
{
|
|
"entropy": 5.318266916275024,
|
|
"epoch": 0.557550952221851,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004974685630927895,
|
|
"loss": 5.1118,
|
|
"mean_token_accuracy": 0.19236804842948912,
|
|
"num_tokens": 12276804.0,
|
|
"step": 6675
|
|
},
|
|
{
|
|
"entropy": 5.417097473144532,
|
|
"epoch": 0.557968593384564,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004974641080623314,
|
|
"loss": 5.1564,
|
|
"mean_token_accuracy": 0.1895575553178787,
|
|
"num_tokens": 12286024.0,
|
|
"step": 6680
|
|
},
|
|
{
|
|
"entropy": 5.3917840957641605,
|
|
"epoch": 0.558386234547277,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004974596491373711,
|
|
"loss": 5.1908,
|
|
"mean_token_accuracy": 0.19468486905097962,
|
|
"num_tokens": 12295154.0,
|
|
"step": 6685
|
|
},
|
|
{
|
|
"entropy": 5.379201126098633,
|
|
"epoch": 0.55880387570999,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004974551863179871,
|
|
"loss": 5.2481,
|
|
"mean_token_accuracy": 0.18427381217479705,
|
|
"num_tokens": 12306349.0,
|
|
"step": 6690
|
|
},
|
|
{
|
|
"entropy": 5.379152107238769,
|
|
"epoch": 0.5592215168727029,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004974507196042572,
|
|
"loss": 5.1937,
|
|
"mean_token_accuracy": 0.19431248158216477,
|
|
"num_tokens": 12315496.0,
|
|
"step": 6695
|
|
},
|
|
{
|
|
"entropy": 5.2494100570678714,
|
|
"epoch": 0.559639158035416,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004974462489962597,
|
|
"loss": 5.0365,
|
|
"mean_token_accuracy": 0.19687401950359346,
|
|
"num_tokens": 12325070.0,
|
|
"step": 6700
|
|
},
|
|
{
|
|
"entropy": 5.340914011001587,
|
|
"epoch": 0.560056799198129,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004974417744940729,
|
|
"loss": 5.1279,
|
|
"mean_token_accuracy": 0.1945287764072418,
|
|
"num_tokens": 12333509.0,
|
|
"step": 6705
|
|
},
|
|
{
|
|
"entropy": 5.373744249343872,
|
|
"epoch": 0.5604744403608419,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000497437296097775,
|
|
"loss": 5.2111,
|
|
"mean_token_accuracy": 0.18823633939027787,
|
|
"num_tokens": 12342495.0,
|
|
"step": 6710
|
|
},
|
|
{
|
|
"entropy": 5.3024890422821045,
|
|
"epoch": 0.560892081523555,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004974328138074445,
|
|
"loss": 5.1165,
|
|
"mean_token_accuracy": 0.19562546163797379,
|
|
"num_tokens": 12351560.0,
|
|
"step": 6715
|
|
},
|
|
{
|
|
"entropy": 5.305520725250244,
|
|
"epoch": 0.561309722686268,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004974283276231599,
|
|
"loss": 5.2097,
|
|
"mean_token_accuracy": 0.1911316066980362,
|
|
"num_tokens": 12360773.0,
|
|
"step": 6720
|
|
},
|
|
{
|
|
"entropy": 5.376407289505005,
|
|
"epoch": 0.5617273638489809,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004974238375449996,
|
|
"loss": 5.2198,
|
|
"mean_token_accuracy": 0.18474843502044677,
|
|
"num_tokens": 12370519.0,
|
|
"step": 6725
|
|
},
|
|
{
|
|
"entropy": 5.372508716583252,
|
|
"epoch": 0.562145005011694,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004974193435730424,
|
|
"loss": 5.21,
|
|
"mean_token_accuracy": 0.19076197743415832,
|
|
"num_tokens": 12380563.0,
|
|
"step": 6730
|
|
},
|
|
{
|
|
"entropy": 5.387130212783814,
|
|
"epoch": 0.562562646174407,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004974148457073668,
|
|
"loss": 5.208,
|
|
"mean_token_accuracy": 0.19575879722833633,
|
|
"num_tokens": 12389291.0,
|
|
"step": 6735
|
|
},
|
|
{
|
|
"entropy": 5.327639245986939,
|
|
"epoch": 0.5629802873371199,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004974103439480517,
|
|
"loss": 5.1789,
|
|
"mean_token_accuracy": 0.19355615079402924,
|
|
"num_tokens": 12399037.0,
|
|
"step": 6740
|
|
},
|
|
{
|
|
"entropy": 5.3151123046875,
|
|
"epoch": 0.563397928499833,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004974058382951757,
|
|
"loss": 4.9895,
|
|
"mean_token_accuracy": 0.20109709799289704,
|
|
"num_tokens": 12407553.0,
|
|
"step": 6745
|
|
},
|
|
{
|
|
"entropy": 5.22309947013855,
|
|
"epoch": 0.563815569662546,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004974013287488177,
|
|
"loss": 5.073,
|
|
"mean_token_accuracy": 0.19609258472919464,
|
|
"num_tokens": 12416298.0,
|
|
"step": 6750
|
|
},
|
|
{
|
|
"entropy": 5.367431354522705,
|
|
"epoch": 0.5642332108252589,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004973968153090569,
|
|
"loss": 5.2276,
|
|
"mean_token_accuracy": 0.186616013944149,
|
|
"num_tokens": 12425918.0,
|
|
"step": 6755
|
|
},
|
|
{
|
|
"entropy": 5.379483604431153,
|
|
"epoch": 0.5646508519879719,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004973922979759722,
|
|
"loss": 5.1491,
|
|
"mean_token_accuracy": 0.1927480846643448,
|
|
"num_tokens": 12434693.0,
|
|
"step": 6760
|
|
},
|
|
{
|
|
"entropy": 5.240261459350586,
|
|
"epoch": 0.565068493150685,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004973877767496424,
|
|
"loss": 5.0175,
|
|
"mean_token_accuracy": 0.20052199065685272,
|
|
"num_tokens": 12444055.0,
|
|
"step": 6765
|
|
},
|
|
{
|
|
"entropy": 5.277566432952881,
|
|
"epoch": 0.5654861343133979,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004973832516301472,
|
|
"loss": 5.0904,
|
|
"mean_token_accuracy": 0.20363982915878295,
|
|
"num_tokens": 12453012.0,
|
|
"step": 6770
|
|
},
|
|
{
|
|
"entropy": 5.274981260299683,
|
|
"epoch": 0.5659037754761109,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004973787226175652,
|
|
"loss": 5.1325,
|
|
"mean_token_accuracy": 0.19542792290449143,
|
|
"num_tokens": 12462292.0,
|
|
"step": 6775
|
|
},
|
|
{
|
|
"entropy": 5.278493928909302,
|
|
"epoch": 0.566321416638824,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004973741897119761,
|
|
"loss": 5.0874,
|
|
"mean_token_accuracy": 0.20897582918405533,
|
|
"num_tokens": 12471178.0,
|
|
"step": 6780
|
|
},
|
|
{
|
|
"entropy": 5.306678676605225,
|
|
"epoch": 0.5667390578015369,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004973696529134592,
|
|
"loss": 5.1201,
|
|
"mean_token_accuracy": 0.2028688222169876,
|
|
"num_tokens": 12479977.0,
|
|
"step": 6785
|
|
},
|
|
{
|
|
"entropy": 5.307732725143433,
|
|
"epoch": 0.5671566989642499,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004973651122220938,
|
|
"loss": 5.1888,
|
|
"mean_token_accuracy": 0.19187885969877244,
|
|
"num_tokens": 12489004.0,
|
|
"step": 6790
|
|
},
|
|
{
|
|
"entropy": 5.419384527206421,
|
|
"epoch": 0.567574340126963,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004973605676379595,
|
|
"loss": 5.1949,
|
|
"mean_token_accuracy": 0.1894410789012909,
|
|
"num_tokens": 12498979.0,
|
|
"step": 6795
|
|
},
|
|
{
|
|
"entropy": 5.382754135131836,
|
|
"epoch": 0.5679919812896759,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004973560191611357,
|
|
"loss": 5.2518,
|
|
"mean_token_accuracy": 0.18889162242412566,
|
|
"num_tokens": 12508293.0,
|
|
"step": 6800
|
|
},
|
|
{
|
|
"entropy": 5.430076217651367,
|
|
"epoch": 0.5684096224523889,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004973514667917021,
|
|
"loss": 5.2651,
|
|
"mean_token_accuracy": 0.190037102997303,
|
|
"num_tokens": 12517828.0,
|
|
"step": 6805
|
|
},
|
|
{
|
|
"entropy": 5.3846653461456295,
|
|
"epoch": 0.5688272636151019,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004973469105297386,
|
|
"loss": 5.1187,
|
|
"mean_token_accuracy": 0.1927657827734947,
|
|
"num_tokens": 12526569.0,
|
|
"step": 6810
|
|
},
|
|
{
|
|
"entropy": 5.353836727142334,
|
|
"epoch": 0.5692449047778149,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004973423503753247,
|
|
"loss": 5.2411,
|
|
"mean_token_accuracy": 0.19148507863283157,
|
|
"num_tokens": 12535706.0,
|
|
"step": 6815
|
|
},
|
|
{
|
|
"entropy": 5.389388847351074,
|
|
"epoch": 0.5696625459405279,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004973377863285403,
|
|
"loss": 5.118,
|
|
"mean_token_accuracy": 0.18832767903804778,
|
|
"num_tokens": 12544689.0,
|
|
"step": 6820
|
|
},
|
|
{
|
|
"entropy": 5.286836814880371,
|
|
"epoch": 0.5700801871032409,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004973332183894653,
|
|
"loss": 5.1008,
|
|
"mean_token_accuracy": 0.1946028009057045,
|
|
"num_tokens": 12553318.0,
|
|
"step": 6825
|
|
},
|
|
{
|
|
"entropy": 5.24740743637085,
|
|
"epoch": 0.5704978282659539,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004973286465581798,
|
|
"loss": 5.0801,
|
|
"mean_token_accuracy": 0.20608279556035997,
|
|
"num_tokens": 12562009.0,
|
|
"step": 6830
|
|
},
|
|
{
|
|
"entropy": 5.379718351364136,
|
|
"epoch": 0.5709154694286669,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004973240708347637,
|
|
"loss": 5.2263,
|
|
"mean_token_accuracy": 0.19497342258691788,
|
|
"num_tokens": 12571043.0,
|
|
"step": 6835
|
|
},
|
|
{
|
|
"entropy": 5.451855421066284,
|
|
"epoch": 0.5713331105913799,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004973194912192971,
|
|
"loss": 5.1315,
|
|
"mean_token_accuracy": 0.194309738278389,
|
|
"num_tokens": 12581151.0,
|
|
"step": 6840
|
|
},
|
|
{
|
|
"entropy": 5.36621675491333,
|
|
"epoch": 0.5717507517540928,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004973149077118602,
|
|
"loss": 5.1751,
|
|
"mean_token_accuracy": 0.19538725912570953,
|
|
"num_tokens": 12590671.0,
|
|
"step": 6845
|
|
},
|
|
{
|
|
"entropy": 5.27402811050415,
|
|
"epoch": 0.5721683929168059,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004973103203125333,
|
|
"loss": 5.2161,
|
|
"mean_token_accuracy": 0.19579629749059677,
|
|
"num_tokens": 12599693.0,
|
|
"step": 6850
|
|
},
|
|
{
|
|
"entropy": 5.327305889129638,
|
|
"epoch": 0.5725860340795189,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004973057290213965,
|
|
"loss": 5.1252,
|
|
"mean_token_accuracy": 0.19855290353298188,
|
|
"num_tokens": 12609238.0,
|
|
"step": 6855
|
|
},
|
|
{
|
|
"entropy": 5.358370113372803,
|
|
"epoch": 0.5730036752422318,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004973011338385304,
|
|
"loss": 5.1266,
|
|
"mean_token_accuracy": 0.19303234070539474,
|
|
"num_tokens": 12618273.0,
|
|
"step": 6860
|
|
},
|
|
{
|
|
"entropy": 5.3325108051300045,
|
|
"epoch": 0.5734213164049449,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004972965347640154,
|
|
"loss": 5.1805,
|
|
"mean_token_accuracy": 0.193036849796772,
|
|
"num_tokens": 12628229.0,
|
|
"step": 6865
|
|
},
|
|
{
|
|
"entropy": 5.366177606582641,
|
|
"epoch": 0.5738389575676579,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000497291931797932,
|
|
"loss": 5.095,
|
|
"mean_token_accuracy": 0.1982719898223877,
|
|
"num_tokens": 12636533.0,
|
|
"step": 6870
|
|
},
|
|
{
|
|
"entropy": 5.293973970413208,
|
|
"epoch": 0.5742565987303708,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004972873249403608,
|
|
"loss": 5.1133,
|
|
"mean_token_accuracy": 0.19605183601379395,
|
|
"num_tokens": 12645503.0,
|
|
"step": 6875
|
|
},
|
|
{
|
|
"entropy": 5.338414239883423,
|
|
"epoch": 0.5746742398930839,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004972827141913822,
|
|
"loss": 5.1332,
|
|
"mean_token_accuracy": 0.18842328786849977,
|
|
"num_tokens": 12654355.0,
|
|
"step": 6880
|
|
},
|
|
{
|
|
"entropy": 5.332372665405273,
|
|
"epoch": 0.5750918810557969,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004972780995510773,
|
|
"loss": 5.1072,
|
|
"mean_token_accuracy": 0.1970501646399498,
|
|
"num_tokens": 12663774.0,
|
|
"step": 6885
|
|
},
|
|
{
|
|
"entropy": 5.250775575637817,
|
|
"epoch": 0.5755095222185098,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004972734810195266,
|
|
"loss": 5.1357,
|
|
"mean_token_accuracy": 0.1956734225153923,
|
|
"num_tokens": 12674436.0,
|
|
"step": 6890
|
|
},
|
|
{
|
|
"entropy": 5.357981634140015,
|
|
"epoch": 0.5759271633812229,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004972688585968112,
|
|
"loss": 5.0935,
|
|
"mean_token_accuracy": 0.1939712405204773,
|
|
"num_tokens": 12682891.0,
|
|
"step": 6895
|
|
},
|
|
{
|
|
"entropy": 5.250308465957642,
|
|
"epoch": 0.5763448045439359,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004972642322830118,
|
|
"loss": 5.0049,
|
|
"mean_token_accuracy": 0.20868447721004485,
|
|
"num_tokens": 12691170.0,
|
|
"step": 6900
|
|
},
|
|
{
|
|
"entropy": 5.268120145797729,
|
|
"epoch": 0.5767624457066488,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004972596020782096,
|
|
"loss": 5.0892,
|
|
"mean_token_accuracy": 0.20168329030275345,
|
|
"num_tokens": 12700314.0,
|
|
"step": 6905
|
|
},
|
|
{
|
|
"entropy": 5.301498794555664,
|
|
"epoch": 0.5771800868693618,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004972549679824853,
|
|
"loss": 5.1515,
|
|
"mean_token_accuracy": 0.1980636477470398,
|
|
"num_tokens": 12709418.0,
|
|
"step": 6910
|
|
},
|
|
{
|
|
"entropy": 5.239022207260132,
|
|
"epoch": 0.5775977280320749,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004972503299959204,
|
|
"loss": 5.1328,
|
|
"mean_token_accuracy": 0.18934394270181656,
|
|
"num_tokens": 12719287.0,
|
|
"step": 6915
|
|
},
|
|
{
|
|
"entropy": 5.342194938659668,
|
|
"epoch": 0.5780153691947878,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000497245688118596,
|
|
"loss": 5.0579,
|
|
"mean_token_accuracy": 0.20184237957000734,
|
|
"num_tokens": 12728836.0,
|
|
"step": 6920
|
|
},
|
|
{
|
|
"entropy": 5.377489757537842,
|
|
"epoch": 0.5784330103575008,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004972410423505932,
|
|
"loss": 5.1802,
|
|
"mean_token_accuracy": 0.1930708572268486,
|
|
"num_tokens": 12738173.0,
|
|
"step": 6925
|
|
},
|
|
{
|
|
"entropy": 5.328310346603393,
|
|
"epoch": 0.5788506515202139,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004972363926919935,
|
|
"loss": 5.1658,
|
|
"mean_token_accuracy": 0.20007263422012328,
|
|
"num_tokens": 12747428.0,
|
|
"step": 6930
|
|
},
|
|
{
|
|
"entropy": 5.356612300872802,
|
|
"epoch": 0.5792682926829268,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004972317391428782,
|
|
"loss": 5.226,
|
|
"mean_token_accuracy": 0.18761636763811113,
|
|
"num_tokens": 12757148.0,
|
|
"step": 6935
|
|
},
|
|
{
|
|
"entropy": 5.403679609298706,
|
|
"epoch": 0.5796859338456398,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004972270817033288,
|
|
"loss": 5.2318,
|
|
"mean_token_accuracy": 0.18417499214410782,
|
|
"num_tokens": 12766820.0,
|
|
"step": 6940
|
|
},
|
|
{
|
|
"entropy": 5.388335800170898,
|
|
"epoch": 0.5801035750083529,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004972224203734269,
|
|
"loss": 5.2165,
|
|
"mean_token_accuracy": 0.19299497902393342,
|
|
"num_tokens": 12776082.0,
|
|
"step": 6945
|
|
},
|
|
{
|
|
"entropy": 5.345056629180908,
|
|
"epoch": 0.5805212161710658,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000497217755153254,
|
|
"loss": 5.1883,
|
|
"mean_token_accuracy": 0.19662619531154632,
|
|
"num_tokens": 12785057.0,
|
|
"step": 6950
|
|
},
|
|
{
|
|
"entropy": 5.330507612228393,
|
|
"epoch": 0.5809388573337788,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004972130860428918,
|
|
"loss": 5.1729,
|
|
"mean_token_accuracy": 0.19887613505125046,
|
|
"num_tokens": 12793599.0,
|
|
"step": 6955
|
|
},
|
|
{
|
|
"entropy": 5.362395000457764,
|
|
"epoch": 0.5813564984964918,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004972084130424222,
|
|
"loss": 5.1677,
|
|
"mean_token_accuracy": 0.19218032956123351,
|
|
"num_tokens": 12803775.0,
|
|
"step": 6960
|
|
},
|
|
{
|
|
"entropy": 5.3146649360656735,
|
|
"epoch": 0.5817741396592048,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004972037361519267,
|
|
"loss": 5.1115,
|
|
"mean_token_accuracy": 0.19620238095521927,
|
|
"num_tokens": 12812327.0,
|
|
"step": 6965
|
|
},
|
|
{
|
|
"entropy": 5.352201986312866,
|
|
"epoch": 0.5821917808219178,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004971990553714874,
|
|
"loss": 5.0605,
|
|
"mean_token_accuracy": 0.20081085860729217,
|
|
"num_tokens": 12821218.0,
|
|
"step": 6970
|
|
},
|
|
{
|
|
"entropy": 5.356791019439697,
|
|
"epoch": 0.5826094219846308,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004971943707011861,
|
|
"loss": 5.1505,
|
|
"mean_token_accuracy": 0.1940755397081375,
|
|
"num_tokens": 12831579.0,
|
|
"step": 6975
|
|
},
|
|
{
|
|
"entropy": 5.359289741516113,
|
|
"epoch": 0.5830270631473438,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000497189682141105,
|
|
"loss": 5.2162,
|
|
"mean_token_accuracy": 0.19426080733537673,
|
|
"num_tokens": 12841026.0,
|
|
"step": 6980
|
|
},
|
|
{
|
|
"entropy": 5.25170931816101,
|
|
"epoch": 0.5834447043100568,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004971849896913259,
|
|
"loss": 5.1494,
|
|
"mean_token_accuracy": 0.19563014209270477,
|
|
"num_tokens": 12850136.0,
|
|
"step": 6985
|
|
},
|
|
{
|
|
"entropy": 5.354822397232056,
|
|
"epoch": 0.5838623454727698,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004971802933519312,
|
|
"loss": 5.2256,
|
|
"mean_token_accuracy": 0.19553592205047607,
|
|
"num_tokens": 12860345.0,
|
|
"step": 6990
|
|
},
|
|
{
|
|
"entropy": 5.304988527297974,
|
|
"epoch": 0.5842799866354828,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004971755931230031,
|
|
"loss": 5.1553,
|
|
"mean_token_accuracy": 0.19274741113185884,
|
|
"num_tokens": 12868995.0,
|
|
"step": 6995
|
|
},
|
|
{
|
|
"entropy": 5.414120864868164,
|
|
"epoch": 0.5846976277981958,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004971708890046236,
|
|
"loss": 5.3066,
|
|
"mean_token_accuracy": 0.18866612911224365,
|
|
"num_tokens": 12878043.0,
|
|
"step": 7000
|
|
},
|
|
{
|
|
"entropy": 5.332791137695312,
|
|
"epoch": 0.5851152689609088,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004971661809968755,
|
|
"loss": 5.1266,
|
|
"mean_token_accuracy": 0.19653817415237426,
|
|
"num_tokens": 12887090.0,
|
|
"step": 7005
|
|
},
|
|
{
|
|
"entropy": 5.29463038444519,
|
|
"epoch": 0.5855329101236217,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004971614690998409,
|
|
"loss": 5.0655,
|
|
"mean_token_accuracy": 0.20885752886533737,
|
|
"num_tokens": 12896349.0,
|
|
"step": 7010
|
|
},
|
|
{
|
|
"entropy": 5.308234930038452,
|
|
"epoch": 0.5859505512863348,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004971567533136024,
|
|
"loss": 5.1114,
|
|
"mean_token_accuracy": 0.19684289246797562,
|
|
"num_tokens": 12905698.0,
|
|
"step": 7015
|
|
},
|
|
{
|
|
"entropy": 5.248376989364624,
|
|
"epoch": 0.5863681924490478,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004971520336382424,
|
|
"loss": 5.1162,
|
|
"mean_token_accuracy": 0.20329161435365678,
|
|
"num_tokens": 12915146.0,
|
|
"step": 7020
|
|
},
|
|
{
|
|
"entropy": 5.191306734085083,
|
|
"epoch": 0.5867858336117607,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004971473100738437,
|
|
"loss": 4.9775,
|
|
"mean_token_accuracy": 0.20541905164718627,
|
|
"num_tokens": 12924933.0,
|
|
"step": 7025
|
|
},
|
|
{
|
|
"entropy": 5.363535928726196,
|
|
"epoch": 0.5872034747744738,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.000497142582620489,
|
|
"loss": 5.2124,
|
|
"mean_token_accuracy": 0.18779776245355606,
|
|
"num_tokens": 12934959.0,
|
|
"step": 7030
|
|
},
|
|
{
|
|
"entropy": 5.307815980911255,
|
|
"epoch": 0.5876211159371868,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004971378512782609,
|
|
"loss": 5.0625,
|
|
"mean_token_accuracy": 0.20597047507762908,
|
|
"num_tokens": 12943470.0,
|
|
"step": 7035
|
|
},
|
|
{
|
|
"entropy": 5.2257318019866945,
|
|
"epoch": 0.5880387570998997,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004971331160472424,
|
|
"loss": 5.0695,
|
|
"mean_token_accuracy": 0.20476973056793213,
|
|
"num_tokens": 12953592.0,
|
|
"step": 7040
|
|
},
|
|
{
|
|
"entropy": 5.3533648490905765,
|
|
"epoch": 0.5884563982626128,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004971283769275163,
|
|
"loss": 5.1954,
|
|
"mean_token_accuracy": 0.1878223314881325,
|
|
"num_tokens": 12962893.0,
|
|
"step": 7045
|
|
},
|
|
{
|
|
"entropy": 5.265210437774658,
|
|
"epoch": 0.5888740394253258,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004971236339191656,
|
|
"loss": 5.082,
|
|
"mean_token_accuracy": 0.20315028429031373,
|
|
"num_tokens": 12971635.0,
|
|
"step": 7050
|
|
},
|
|
{
|
|
"entropy": 5.2263952732086185,
|
|
"epoch": 0.5892916805880387,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004971188870222734,
|
|
"loss": 5.0587,
|
|
"mean_token_accuracy": 0.20553121119737625,
|
|
"num_tokens": 12981040.0,
|
|
"step": 7055
|
|
},
|
|
{
|
|
"entropy": 5.2849376678466795,
|
|
"epoch": 0.5897093217507517,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004971141362369226,
|
|
"loss": 5.0789,
|
|
"mean_token_accuracy": 0.1994106352329254,
|
|
"num_tokens": 12989898.0,
|
|
"step": 7060
|
|
},
|
|
{
|
|
"entropy": 5.298730897903442,
|
|
"epoch": 0.5901269629134648,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004971093815631965,
|
|
"loss": 5.0723,
|
|
"mean_token_accuracy": 0.19711526930332185,
|
|
"num_tokens": 12998584.0,
|
|
"step": 7065
|
|
},
|
|
{
|
|
"entropy": 5.2975461959838865,
|
|
"epoch": 0.5905446040761777,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004971046230011783,
|
|
"loss": 5.107,
|
|
"mean_token_accuracy": 0.19629897624254228,
|
|
"num_tokens": 13008007.0,
|
|
"step": 7070
|
|
},
|
|
{
|
|
"entropy": 5.342353105545044,
|
|
"epoch": 0.5909622452388907,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004970998605509514,
|
|
"loss": 5.2364,
|
|
"mean_token_accuracy": 0.18871966153383254,
|
|
"num_tokens": 13017034.0,
|
|
"step": 7075
|
|
},
|
|
{
|
|
"entropy": 5.407427501678467,
|
|
"epoch": 0.5913798864016038,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000497095094212599,
|
|
"loss": 5.2997,
|
|
"mean_token_accuracy": 0.1838369131088257,
|
|
"num_tokens": 13025916.0,
|
|
"step": 7080
|
|
},
|
|
{
|
|
"entropy": 5.391162633895874,
|
|
"epoch": 0.5917975275643167,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004970903239862047,
|
|
"loss": 5.1711,
|
|
"mean_token_accuracy": 0.18868904262781144,
|
|
"num_tokens": 13035242.0,
|
|
"step": 7085
|
|
},
|
|
{
|
|
"entropy": 5.3094288349151615,
|
|
"epoch": 0.5922151687270297,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004970855498718519,
|
|
"loss": 5.1051,
|
|
"mean_token_accuracy": 0.19548780769109725,
|
|
"num_tokens": 13044123.0,
|
|
"step": 7090
|
|
},
|
|
{
|
|
"entropy": 5.2993566513061525,
|
|
"epoch": 0.5926328098897428,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004970807718696243,
|
|
"loss": 5.1624,
|
|
"mean_token_accuracy": 0.19107201099395751,
|
|
"num_tokens": 13053503.0,
|
|
"step": 7095
|
|
},
|
|
{
|
|
"entropy": 5.342015790939331,
|
|
"epoch": 0.5930504510524557,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004970759899796055,
|
|
"loss": 5.1496,
|
|
"mean_token_accuracy": 0.19394615441560745,
|
|
"num_tokens": 13062106.0,
|
|
"step": 7100
|
|
},
|
|
{
|
|
"entropy": 5.3626923084259035,
|
|
"epoch": 0.5934680922151687,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004970712042018791,
|
|
"loss": 5.1425,
|
|
"mean_token_accuracy": 0.19150077253580094,
|
|
"num_tokens": 13071509.0,
|
|
"step": 7105
|
|
},
|
|
{
|
|
"entropy": 5.263015222549439,
|
|
"epoch": 0.5938857333778818,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004970664145365289,
|
|
"loss": 5.0702,
|
|
"mean_token_accuracy": 0.1999054193496704,
|
|
"num_tokens": 13080469.0,
|
|
"step": 7110
|
|
},
|
|
{
|
|
"entropy": 5.317249155044555,
|
|
"epoch": 0.5943033745405947,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000497061620983639,
|
|
"loss": 5.0394,
|
|
"mean_token_accuracy": 0.20194881409406662,
|
|
"num_tokens": 13089826.0,
|
|
"step": 7115
|
|
},
|
|
{
|
|
"entropy": 5.369497966766358,
|
|
"epoch": 0.5947210157033077,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004970568235432931,
|
|
"loss": 5.2196,
|
|
"mean_token_accuracy": 0.19345467537641525,
|
|
"num_tokens": 13098630.0,
|
|
"step": 7120
|
|
},
|
|
{
|
|
"entropy": 5.316605472564698,
|
|
"epoch": 0.5951386568660207,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004970520222155751,
|
|
"loss": 5.1198,
|
|
"mean_token_accuracy": 0.19804002493619918,
|
|
"num_tokens": 13106819.0,
|
|
"step": 7125
|
|
},
|
|
{
|
|
"entropy": 5.367663240432739,
|
|
"epoch": 0.5955562980287337,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004970472170005692,
|
|
"loss": 5.1313,
|
|
"mean_token_accuracy": 0.19699766784906386,
|
|
"num_tokens": 13115471.0,
|
|
"step": 7130
|
|
},
|
|
{
|
|
"entropy": 5.2743888854980465,
|
|
"epoch": 0.5959739391914467,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004970424078983596,
|
|
"loss": 5.0054,
|
|
"mean_token_accuracy": 0.209335957467556,
|
|
"num_tokens": 13124537.0,
|
|
"step": 7135
|
|
},
|
|
{
|
|
"entropy": 5.292069292068481,
|
|
"epoch": 0.5963915803541597,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004970375949090302,
|
|
"loss": 5.1436,
|
|
"mean_token_accuracy": 0.19772982895374297,
|
|
"num_tokens": 13135326.0,
|
|
"step": 7140
|
|
},
|
|
{
|
|
"entropy": 5.417243432998657,
|
|
"epoch": 0.5968092215168727,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004970327780326655,
|
|
"loss": 5.2354,
|
|
"mean_token_accuracy": 0.18968381881713867,
|
|
"num_tokens": 13145502.0,
|
|
"step": 7145
|
|
},
|
|
{
|
|
"entropy": 5.387653493881226,
|
|
"epoch": 0.5972268626795857,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004970279572693498,
|
|
"loss": 5.146,
|
|
"mean_token_accuracy": 0.20050851851701737,
|
|
"num_tokens": 13154808.0,
|
|
"step": 7150
|
|
},
|
|
{
|
|
"entropy": 5.259207057952881,
|
|
"epoch": 0.5976445038422987,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004970231326191674,
|
|
"loss": 5.2493,
|
|
"mean_token_accuracy": 0.18623579889535904,
|
|
"num_tokens": 13163982.0,
|
|
"step": 7155
|
|
},
|
|
{
|
|
"entropy": 5.332884931564331,
|
|
"epoch": 0.5980621450050116,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004970183040822029,
|
|
"loss": 5.1401,
|
|
"mean_token_accuracy": 0.196553036570549,
|
|
"num_tokens": 13172446.0,
|
|
"step": 7160
|
|
},
|
|
{
|
|
"entropy": 5.365352439880371,
|
|
"epoch": 0.5984797861677247,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004970134716585407,
|
|
"loss": 5.1137,
|
|
"mean_token_accuracy": 0.19348438531160356,
|
|
"num_tokens": 13181671.0,
|
|
"step": 7165
|
|
},
|
|
{
|
|
"entropy": 5.304043531417847,
|
|
"epoch": 0.5988974273304377,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004970086353482654,
|
|
"loss": 5.0449,
|
|
"mean_token_accuracy": 0.19625666588544846,
|
|
"num_tokens": 13190207.0,
|
|
"step": 7170
|
|
},
|
|
{
|
|
"entropy": 5.273567962646484,
|
|
"epoch": 0.5993150684931506,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004970037951514617,
|
|
"loss": 5.0443,
|
|
"mean_token_accuracy": 0.20113227665424346,
|
|
"num_tokens": 13198866.0,
|
|
"step": 7175
|
|
},
|
|
{
|
|
"entropy": 5.301345729827881,
|
|
"epoch": 0.5997327096558637,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004969989510682143,
|
|
"loss": 5.0595,
|
|
"mean_token_accuracy": 0.2027854800224304,
|
|
"num_tokens": 13207921.0,
|
|
"step": 7180
|
|
},
|
|
{
|
|
"entropy": 5.399423408508301,
|
|
"epoch": 0.6001503508185767,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004969941030986082,
|
|
"loss": 5.2385,
|
|
"mean_token_accuracy": 0.19331772476434708,
|
|
"num_tokens": 13217759.0,
|
|
"step": 7185
|
|
},
|
|
{
|
|
"entropy": 5.2552680492401125,
|
|
"epoch": 0.6005679919812896,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.000496989251242728,
|
|
"loss": 5.0112,
|
|
"mean_token_accuracy": 0.20147017538547515,
|
|
"num_tokens": 13226592.0,
|
|
"step": 7190
|
|
},
|
|
{
|
|
"entropy": 5.282441425323486,
|
|
"epoch": 0.6009856331440027,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004969843955006588,
|
|
"loss": 5.0846,
|
|
"mean_token_accuracy": 0.1955637276172638,
|
|
"num_tokens": 13236123.0,
|
|
"step": 7195
|
|
},
|
|
{
|
|
"entropy": 5.317075157165528,
|
|
"epoch": 0.6014032743067157,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004969795358724855,
|
|
"loss": 5.1894,
|
|
"mean_token_accuracy": 0.19167284220457076,
|
|
"num_tokens": 13246169.0,
|
|
"step": 7200
|
|
},
|
|
{
|
|
"entropy": 5.282715368270874,
|
|
"epoch": 0.6018209154694286,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004969746723582932,
|
|
"loss": 5.068,
|
|
"mean_token_accuracy": 0.20560144633054733,
|
|
"num_tokens": 13256141.0,
|
|
"step": 7205
|
|
},
|
|
{
|
|
"entropy": 5.357795715332031,
|
|
"epoch": 0.6022385566321417,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004969698049581672,
|
|
"loss": 5.2254,
|
|
"mean_token_accuracy": 0.19470075219869615,
|
|
"num_tokens": 13265491.0,
|
|
"step": 7210
|
|
},
|
|
{
|
|
"entropy": 5.408079290390015,
|
|
"epoch": 0.6026561977948547,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004969649336721924,
|
|
"loss": 5.2272,
|
|
"mean_token_accuracy": 0.19919759333133696,
|
|
"num_tokens": 13274805.0,
|
|
"step": 7215
|
|
},
|
|
{
|
|
"entropy": 5.410361862182617,
|
|
"epoch": 0.6030738389575676,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004969600585004544,
|
|
"loss": 5.1821,
|
|
"mean_token_accuracy": 0.19047997444868087,
|
|
"num_tokens": 13284589.0,
|
|
"step": 7220
|
|
},
|
|
{
|
|
"entropy": 5.255741548538208,
|
|
"epoch": 0.6034914801202806,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004969551794430383,
|
|
"loss": 5.0199,
|
|
"mean_token_accuracy": 0.20712951868772506,
|
|
"num_tokens": 13293370.0,
|
|
"step": 7225
|
|
},
|
|
{
|
|
"entropy": 5.398855876922608,
|
|
"epoch": 0.6039091212829937,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004969502965000297,
|
|
"loss": 5.2001,
|
|
"mean_token_accuracy": 0.19466075748205186,
|
|
"num_tokens": 13302555.0,
|
|
"step": 7230
|
|
},
|
|
{
|
|
"entropy": 5.287164735794067,
|
|
"epoch": 0.6043267624457066,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000496945409671514,
|
|
"loss": 5.1207,
|
|
"mean_token_accuracy": 0.20137713700532914,
|
|
"num_tokens": 13311632.0,
|
|
"step": 7235
|
|
},
|
|
{
|
|
"entropy": 5.319089078903199,
|
|
"epoch": 0.6047444036084196,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004969405189575768,
|
|
"loss": 5.0785,
|
|
"mean_token_accuracy": 0.2026840031147003,
|
|
"num_tokens": 13320593.0,
|
|
"step": 7240
|
|
},
|
|
{
|
|
"entropy": 5.294135904312133,
|
|
"epoch": 0.6051620447711327,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004969356243583036,
|
|
"loss": 5.0401,
|
|
"mean_token_accuracy": 0.20420426577329637,
|
|
"num_tokens": 13329095.0,
|
|
"step": 7245
|
|
},
|
|
{
|
|
"entropy": 5.234756422042847,
|
|
"epoch": 0.6055796859338456,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004969307258737802,
|
|
"loss": 5.0958,
|
|
"mean_token_accuracy": 0.19960410743951798,
|
|
"num_tokens": 13338404.0,
|
|
"step": 7250
|
|
},
|
|
{
|
|
"entropy": 5.270444250106811,
|
|
"epoch": 0.6059973270965586,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004969258235040921,
|
|
"loss": 5.0669,
|
|
"mean_token_accuracy": 0.20691566914319992,
|
|
"num_tokens": 13347095.0,
|
|
"step": 7255
|
|
},
|
|
{
|
|
"entropy": 5.289247989654541,
|
|
"epoch": 0.6064149682592717,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004969209172493255,
|
|
"loss": 5.13,
|
|
"mean_token_accuracy": 0.19697306752204896,
|
|
"num_tokens": 13356606.0,
|
|
"step": 7260
|
|
},
|
|
{
|
|
"entropy": 5.319506454467773,
|
|
"epoch": 0.6068326094219846,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004969160071095661,
|
|
"loss": 5.1284,
|
|
"mean_token_accuracy": 0.19501465409994126,
|
|
"num_tokens": 13366889.0,
|
|
"step": 7265
|
|
},
|
|
{
|
|
"entropy": 5.345353364944458,
|
|
"epoch": 0.6072502505846976,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004969110930848999,
|
|
"loss": 5.1381,
|
|
"mean_token_accuracy": 0.1954762563109398,
|
|
"num_tokens": 13376761.0,
|
|
"step": 7270
|
|
},
|
|
{
|
|
"entropy": 5.314459133148193,
|
|
"epoch": 0.6076678917474106,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004969061751754129,
|
|
"loss": 5.0622,
|
|
"mean_token_accuracy": 0.20645569264888763,
|
|
"num_tokens": 13386226.0,
|
|
"step": 7275
|
|
},
|
|
{
|
|
"entropy": 5.266441774368286,
|
|
"epoch": 0.6080855329101236,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004969012533811911,
|
|
"loss": 5.0074,
|
|
"mean_token_accuracy": 0.20572338849306107,
|
|
"num_tokens": 13394243.0,
|
|
"step": 7280
|
|
},
|
|
{
|
|
"entropy": 5.287345218658447,
|
|
"epoch": 0.6085031740728366,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004968963277023208,
|
|
"loss": 5.2853,
|
|
"mean_token_accuracy": 0.17963769435882568,
|
|
"num_tokens": 13403708.0,
|
|
"step": 7285
|
|
},
|
|
{
|
|
"entropy": 5.274597883224487,
|
|
"epoch": 0.6089208152355496,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004968913981388882,
|
|
"loss": 5.1087,
|
|
"mean_token_accuracy": 0.20476820915937424,
|
|
"num_tokens": 13412911.0,
|
|
"step": 7290
|
|
},
|
|
{
|
|
"entropy": 5.380892419815064,
|
|
"epoch": 0.6093384563982626,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004968864646909797,
|
|
"loss": 5.2419,
|
|
"mean_token_accuracy": 0.19346756786108016,
|
|
"num_tokens": 13422423.0,
|
|
"step": 7295
|
|
},
|
|
{
|
|
"entropy": 5.321874284744263,
|
|
"epoch": 0.6097560975609756,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004968815273586814,
|
|
"loss": 5.0971,
|
|
"mean_token_accuracy": 0.2003725379705429,
|
|
"num_tokens": 13430984.0,
|
|
"step": 7300
|
|
},
|
|
{
|
|
"entropy": 5.312367868423462,
|
|
"epoch": 0.6101737387236886,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004968765861420799,
|
|
"loss": 5.1513,
|
|
"mean_token_accuracy": 0.1950658842921257,
|
|
"num_tokens": 13440492.0,
|
|
"step": 7305
|
|
},
|
|
{
|
|
"entropy": 5.3808534145355225,
|
|
"epoch": 0.6105913798864016,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004968716410412617,
|
|
"loss": 5.1133,
|
|
"mean_token_accuracy": 0.19727630466222762,
|
|
"num_tokens": 13449222.0,
|
|
"step": 7310
|
|
},
|
|
{
|
|
"entropy": 5.310233306884766,
|
|
"epoch": 0.6110090210491146,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004968666920563134,
|
|
"loss": 5.1067,
|
|
"mean_token_accuracy": 0.20144483149051667,
|
|
"num_tokens": 13459126.0,
|
|
"step": 7315
|
|
},
|
|
{
|
|
"entropy": 5.434738111495972,
|
|
"epoch": 0.6114266622118276,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004968617391873216,
|
|
"loss": 5.2465,
|
|
"mean_token_accuracy": 0.1796099439263344,
|
|
"num_tokens": 13468811.0,
|
|
"step": 7320
|
|
},
|
|
{
|
|
"entropy": 5.33213701248169,
|
|
"epoch": 0.6118443033745405,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004968567824343729,
|
|
"loss": 5.04,
|
|
"mean_token_accuracy": 0.1932415708899498,
|
|
"num_tokens": 13477765.0,
|
|
"step": 7325
|
|
},
|
|
{
|
|
"entropy": 5.318994760513306,
|
|
"epoch": 0.6122619445372536,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004968518217975542,
|
|
"loss": 5.1748,
|
|
"mean_token_accuracy": 0.18547997921705245,
|
|
"num_tokens": 13487184.0,
|
|
"step": 7330
|
|
},
|
|
{
|
|
"entropy": 5.3060770511627195,
|
|
"epoch": 0.6126795856999666,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004968468572769524,
|
|
"loss": 5.1203,
|
|
"mean_token_accuracy": 0.19739150553941726,
|
|
"num_tokens": 13496784.0,
|
|
"step": 7335
|
|
},
|
|
{
|
|
"entropy": 5.322006368637085,
|
|
"epoch": 0.6130972268626795,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004968418888726543,
|
|
"loss": 5.1565,
|
|
"mean_token_accuracy": 0.19425925463438035,
|
|
"num_tokens": 13505824.0,
|
|
"step": 7340
|
|
},
|
|
{
|
|
"entropy": 5.299488306045532,
|
|
"epoch": 0.6135148680253926,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004968369165847469,
|
|
"loss": 5.0041,
|
|
"mean_token_accuracy": 0.20222590416669844,
|
|
"num_tokens": 13515111.0,
|
|
"step": 7345
|
|
},
|
|
{
|
|
"entropy": 5.253536128997803,
|
|
"epoch": 0.6139325091881056,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004968319404133173,
|
|
"loss": 5.0382,
|
|
"mean_token_accuracy": 0.20265664011240006,
|
|
"num_tokens": 13524163.0,
|
|
"step": 7350
|
|
},
|
|
{
|
|
"entropy": 5.273534059524536,
|
|
"epoch": 0.6143501503508185,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004968269603584525,
|
|
"loss": 5.0173,
|
|
"mean_token_accuracy": 0.2090737923979759,
|
|
"num_tokens": 13533368.0,
|
|
"step": 7355
|
|
},
|
|
{
|
|
"entropy": 5.33686089515686,
|
|
"epoch": 0.6147677915135316,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004968219764202397,
|
|
"loss": 5.2172,
|
|
"mean_token_accuracy": 0.19302222728729249,
|
|
"num_tokens": 13543708.0,
|
|
"step": 7360
|
|
},
|
|
{
|
|
"entropy": 5.311557865142822,
|
|
"epoch": 0.6151854326762446,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004968169885987663,
|
|
"loss": 5.1442,
|
|
"mean_token_accuracy": 0.19446005374193193,
|
|
"num_tokens": 13552561.0,
|
|
"step": 7365
|
|
},
|
|
{
|
|
"entropy": 5.411979484558105,
|
|
"epoch": 0.6156030738389575,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004968119968941193,
|
|
"loss": 5.2422,
|
|
"mean_token_accuracy": 0.18597899675369262,
|
|
"num_tokens": 13562050.0,
|
|
"step": 7370
|
|
},
|
|
{
|
|
"entropy": 5.257673883438111,
|
|
"epoch": 0.6160207150016705,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004968070013063866,
|
|
"loss": 5.0711,
|
|
"mean_token_accuracy": 0.19194685220718383,
|
|
"num_tokens": 13571356.0,
|
|
"step": 7375
|
|
},
|
|
{
|
|
"entropy": 5.2729517936706545,
|
|
"epoch": 0.6164383561643836,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004968020018356552,
|
|
"loss": 5.0731,
|
|
"mean_token_accuracy": 0.19190491139888763,
|
|
"num_tokens": 13581357.0,
|
|
"step": 7380
|
|
},
|
|
{
|
|
"entropy": 5.29729528427124,
|
|
"epoch": 0.6168559973270965,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004967969984820128,
|
|
"loss": 5.0621,
|
|
"mean_token_accuracy": 0.1971805661916733,
|
|
"num_tokens": 13589392.0,
|
|
"step": 7385
|
|
},
|
|
{
|
|
"entropy": 5.296608352661133,
|
|
"epoch": 0.6172736384898095,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004967919912455469,
|
|
"loss": 5.032,
|
|
"mean_token_accuracy": 0.2077103450894356,
|
|
"num_tokens": 13598376.0,
|
|
"step": 7390
|
|
},
|
|
{
|
|
"entropy": 5.176263618469238,
|
|
"epoch": 0.6176912796525226,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004967869801263454,
|
|
"loss": 4.9436,
|
|
"mean_token_accuracy": 0.21241846084594726,
|
|
"num_tokens": 13607014.0,
|
|
"step": 7395
|
|
},
|
|
{
|
|
"entropy": 5.236470127105713,
|
|
"epoch": 0.6181089208152355,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004967819651244957,
|
|
"loss": 5.1246,
|
|
"mean_token_accuracy": 0.1940328523516655,
|
|
"num_tokens": 13615700.0,
|
|
"step": 7400
|
|
},
|
|
{
|
|
"entropy": 5.3532181739807125,
|
|
"epoch": 0.6185265619779485,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004967769462400857,
|
|
"loss": 5.1522,
|
|
"mean_token_accuracy": 0.2038279429078102,
|
|
"num_tokens": 13625230.0,
|
|
"step": 7405
|
|
},
|
|
{
|
|
"entropy": 5.44642186164856,
|
|
"epoch": 0.6189442031406616,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004967719234732033,
|
|
"loss": 5.3097,
|
|
"mean_token_accuracy": 0.19283871203660966,
|
|
"num_tokens": 13635258.0,
|
|
"step": 7410
|
|
},
|
|
{
|
|
"entropy": 5.2723753452301025,
|
|
"epoch": 0.6193618443033745,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004967668968239365,
|
|
"loss": 5.0181,
|
|
"mean_token_accuracy": 0.2040007844567299,
|
|
"num_tokens": 13643688.0,
|
|
"step": 7415
|
|
},
|
|
{
|
|
"entropy": 5.283078193664551,
|
|
"epoch": 0.6197794854660875,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004967618662923732,
|
|
"loss": 5.1676,
|
|
"mean_token_accuracy": 0.1946879133582115,
|
|
"num_tokens": 13652894.0,
|
|
"step": 7420
|
|
},
|
|
{
|
|
"entropy": 5.291216707229614,
|
|
"epoch": 0.6201971266288006,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004967568318786016,
|
|
"loss": 5.1051,
|
|
"mean_token_accuracy": 0.1991724491119385,
|
|
"num_tokens": 13662852.0,
|
|
"step": 7425
|
|
},
|
|
{
|
|
"entropy": 5.331347799301147,
|
|
"epoch": 0.6206147677915135,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004967517935827097,
|
|
"loss": 5.0826,
|
|
"mean_token_accuracy": 0.19448151290416718,
|
|
"num_tokens": 13671457.0,
|
|
"step": 7430
|
|
},
|
|
{
|
|
"entropy": 5.307916498184204,
|
|
"epoch": 0.6210324089542265,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004967467514047856,
|
|
"loss": 5.1569,
|
|
"mean_token_accuracy": 0.19908891916275023,
|
|
"num_tokens": 13681002.0,
|
|
"step": 7435
|
|
},
|
|
{
|
|
"entropy": 5.293569469451905,
|
|
"epoch": 0.6214500501169395,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004967417053449178,
|
|
"loss": 5.099,
|
|
"mean_token_accuracy": 0.19786427021026612,
|
|
"num_tokens": 13690677.0,
|
|
"step": 7440
|
|
},
|
|
{
|
|
"entropy": 5.272982358932495,
|
|
"epoch": 0.6218676912796525,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004967366554031945,
|
|
"loss": 4.9354,
|
|
"mean_token_accuracy": 0.20864570438861846,
|
|
"num_tokens": 13699151.0,
|
|
"step": 7445
|
|
},
|
|
{
|
|
"entropy": 5.291828203201294,
|
|
"epoch": 0.6222853324423655,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004967316015797042,
|
|
"loss": 5.1329,
|
|
"mean_token_accuracy": 0.1979476734995842,
|
|
"num_tokens": 13708105.0,
|
|
"step": 7450
|
|
},
|
|
{
|
|
"entropy": 5.321125841140747,
|
|
"epoch": 0.6227029736050785,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004967265438745352,
|
|
"loss": 5.2784,
|
|
"mean_token_accuracy": 0.18992661833763122,
|
|
"num_tokens": 13717094.0,
|
|
"step": 7455
|
|
},
|
|
{
|
|
"entropy": 5.31083312034607,
|
|
"epoch": 0.6231206147677915,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004967214822877763,
|
|
"loss": 5.0979,
|
|
"mean_token_accuracy": 0.202111092209816,
|
|
"num_tokens": 13726639.0,
|
|
"step": 7460
|
|
},
|
|
{
|
|
"entropy": 5.328119993209839,
|
|
"epoch": 0.6235382559305045,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004967164168195159,
|
|
"loss": 5.0626,
|
|
"mean_token_accuracy": 0.1964184656739235,
|
|
"num_tokens": 13735220.0,
|
|
"step": 7465
|
|
},
|
|
{
|
|
"entropy": 5.213564682006836,
|
|
"epoch": 0.6239558970932175,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004967113474698428,
|
|
"loss": 5.038,
|
|
"mean_token_accuracy": 0.2117079883813858,
|
|
"num_tokens": 13743277.0,
|
|
"step": 7470
|
|
},
|
|
{
|
|
"entropy": 5.309726905822754,
|
|
"epoch": 0.6243735382559304,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004967062742388456,
|
|
"loss": 5.0866,
|
|
"mean_token_accuracy": 0.19689328372478485,
|
|
"num_tokens": 13752946.0,
|
|
"step": 7475
|
|
},
|
|
{
|
|
"entropy": 5.353356266021729,
|
|
"epoch": 0.6247911794186435,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004967011971266132,
|
|
"loss": 5.158,
|
|
"mean_token_accuracy": 0.19761786758899688,
|
|
"num_tokens": 13761297.0,
|
|
"step": 7480
|
|
},
|
|
{
|
|
"entropy": 5.300906324386597,
|
|
"epoch": 0.6252088205813565,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004966961161332346,
|
|
"loss": 5.0931,
|
|
"mean_token_accuracy": 0.1933014437556267,
|
|
"num_tokens": 13771238.0,
|
|
"step": 7485
|
|
},
|
|
{
|
|
"entropy": 5.290185832977295,
|
|
"epoch": 0.6256264617440696,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004966910312587985,
|
|
"loss": 5.1196,
|
|
"mean_token_accuracy": 0.1934815987944603,
|
|
"num_tokens": 13781420.0,
|
|
"step": 7490
|
|
},
|
|
{
|
|
"entropy": 5.25551323890686,
|
|
"epoch": 0.6260441029067825,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004966859425033941,
|
|
"loss": 5.0973,
|
|
"mean_token_accuracy": 0.19970676600933074,
|
|
"num_tokens": 13789833.0,
|
|
"step": 7495
|
|
},
|
|
{
|
|
"entropy": 5.3691894054412845,
|
|
"epoch": 0.6264617440694955,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004966808498671104,
|
|
"loss": 5.2065,
|
|
"mean_token_accuracy": 0.18750286102294922,
|
|
"num_tokens": 13799202.0,
|
|
"step": 7500
|
|
},
|
|
{
|
|
"entropy": 5.398705530166626,
|
|
"epoch": 0.6268793852322085,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004966757533500367,
|
|
"loss": 5.1751,
|
|
"mean_token_accuracy": 0.19055218547582625,
|
|
"num_tokens": 13809097.0,
|
|
"step": 7505
|
|
},
|
|
{
|
|
"entropy": 5.289015245437622,
|
|
"epoch": 0.6272970263949215,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000496670652952262,
|
|
"loss": 5.0906,
|
|
"mean_token_accuracy": 0.20338452458381653,
|
|
"num_tokens": 13818437.0,
|
|
"step": 7510
|
|
},
|
|
{
|
|
"entropy": 5.234919691085816,
|
|
"epoch": 0.6277146675576345,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004966655486738757,
|
|
"loss": 5.0904,
|
|
"mean_token_accuracy": 0.20160884261131287,
|
|
"num_tokens": 13827083.0,
|
|
"step": 7515
|
|
},
|
|
{
|
|
"entropy": 5.2574609279632565,
|
|
"epoch": 0.6281323087203475,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004966604405149672,
|
|
"loss": 5.0658,
|
|
"mean_token_accuracy": 0.1986864537000656,
|
|
"num_tokens": 13835905.0,
|
|
"step": 7520
|
|
},
|
|
{
|
|
"entropy": 5.2765950679779055,
|
|
"epoch": 0.6285499498830605,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004966553284756257,
|
|
"loss": 4.9942,
|
|
"mean_token_accuracy": 0.20565129220485687,
|
|
"num_tokens": 13845136.0,
|
|
"step": 7525
|
|
},
|
|
{
|
|
"entropy": 5.277464914321899,
|
|
"epoch": 0.6289675910457735,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004966502125559411,
|
|
"loss": 5.0883,
|
|
"mean_token_accuracy": 0.19836325198411942,
|
|
"num_tokens": 13855087.0,
|
|
"step": 7530
|
|
},
|
|
{
|
|
"entropy": 5.2940673828125,
|
|
"epoch": 0.6293852322084865,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004966450927560026,
|
|
"loss": 5.1278,
|
|
"mean_token_accuracy": 0.1913610130548477,
|
|
"num_tokens": 13864077.0,
|
|
"step": 7535
|
|
},
|
|
{
|
|
"entropy": 5.340163087844848,
|
|
"epoch": 0.6298028733711994,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004966399690759,
|
|
"loss": 5.1162,
|
|
"mean_token_accuracy": 0.1937885284423828,
|
|
"num_tokens": 13873404.0,
|
|
"step": 7540
|
|
},
|
|
{
|
|
"entropy": 5.366912174224853,
|
|
"epoch": 0.6302205145339125,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.000496634841515723,
|
|
"loss": 5.1862,
|
|
"mean_token_accuracy": 0.19290923625230788,
|
|
"num_tokens": 13883231.0,
|
|
"step": 7545
|
|
},
|
|
{
|
|
"entropy": 5.184475564956665,
|
|
"epoch": 0.6306381556966255,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004966297100755613,
|
|
"loss": 4.951,
|
|
"mean_token_accuracy": 0.21052946150302887,
|
|
"num_tokens": 13892314.0,
|
|
"step": 7550
|
|
},
|
|
{
|
|
"entropy": 5.248685216903686,
|
|
"epoch": 0.6310557968593384,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004966245747555047,
|
|
"loss": 5.0437,
|
|
"mean_token_accuracy": 0.20218665599823,
|
|
"num_tokens": 13900771.0,
|
|
"step": 7555
|
|
},
|
|
{
|
|
"entropy": 5.225005292892456,
|
|
"epoch": 0.6314734380220515,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004966194355556432,
|
|
"loss": 5.0302,
|
|
"mean_token_accuracy": 0.20207641571760177,
|
|
"num_tokens": 13909615.0,
|
|
"step": 7560
|
|
},
|
|
{
|
|
"entropy": 5.287607431411743,
|
|
"epoch": 0.6318910791847645,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004966142924760666,
|
|
"loss": 5.1391,
|
|
"mean_token_accuracy": 0.19791716635227202,
|
|
"num_tokens": 13918491.0,
|
|
"step": 7565
|
|
},
|
|
{
|
|
"entropy": 5.286098003387451,
|
|
"epoch": 0.6323087203474774,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004966091455168652,
|
|
"loss": 5.1458,
|
|
"mean_token_accuracy": 0.18603342324495314,
|
|
"num_tokens": 13927935.0,
|
|
"step": 7570
|
|
},
|
|
{
|
|
"entropy": 5.2674699306488035,
|
|
"epoch": 0.6327263615101905,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004966039946781289,
|
|
"loss": 4.9664,
|
|
"mean_token_accuracy": 0.20871231108903884,
|
|
"num_tokens": 13936524.0,
|
|
"step": 7575
|
|
},
|
|
{
|
|
"entropy": 5.246699714660645,
|
|
"epoch": 0.6331440026729035,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000496598839959948,
|
|
"loss": 5.0452,
|
|
"mean_token_accuracy": 0.19928555488586425,
|
|
"num_tokens": 13945544.0,
|
|
"step": 7580
|
|
},
|
|
{
|
|
"entropy": 5.269837665557861,
|
|
"epoch": 0.6335616438356164,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004965936813624126,
|
|
"loss": 5.0751,
|
|
"mean_token_accuracy": 0.209821717441082,
|
|
"num_tokens": 13955016.0,
|
|
"step": 7585
|
|
},
|
|
{
|
|
"entropy": 5.252441787719727,
|
|
"epoch": 0.6339792849983295,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.000496588518885613,
|
|
"loss": 5.0805,
|
|
"mean_token_accuracy": 0.19764155000448227,
|
|
"num_tokens": 13964045.0,
|
|
"step": 7590
|
|
},
|
|
{
|
|
"entropy": 5.284239625930786,
|
|
"epoch": 0.6343969261610425,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004965833525296397,
|
|
"loss": 5.0816,
|
|
"mean_token_accuracy": 0.1962558686733246,
|
|
"num_tokens": 13973554.0,
|
|
"step": 7595
|
|
},
|
|
{
|
|
"entropy": 5.274340867996216,
|
|
"epoch": 0.6348145673237554,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004965781822945831,
|
|
"loss": 5.0814,
|
|
"mean_token_accuracy": 0.19627740234136581,
|
|
"num_tokens": 13982669.0,
|
|
"step": 7600
|
|
},
|
|
{
|
|
"entropy": 5.392740154266358,
|
|
"epoch": 0.6352322084864684,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004965730081805338,
|
|
"loss": 5.194,
|
|
"mean_token_accuracy": 0.19119200706481934,
|
|
"num_tokens": 13993392.0,
|
|
"step": 7605
|
|
},
|
|
{
|
|
"entropy": 5.368127250671387,
|
|
"epoch": 0.6356498496491815,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004965678301875821,
|
|
"loss": 5.1773,
|
|
"mean_token_accuracy": 0.19042346626520157,
|
|
"num_tokens": 14002659.0,
|
|
"step": 7610
|
|
},
|
|
{
|
|
"entropy": 5.2989928245544435,
|
|
"epoch": 0.6360674908118944,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000496562648315819,
|
|
"loss": 5.1331,
|
|
"mean_token_accuracy": 0.19522275179624557,
|
|
"num_tokens": 14011561.0,
|
|
"step": 7615
|
|
},
|
|
{
|
|
"entropy": 5.306436252593994,
|
|
"epoch": 0.6364851319746074,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000496557462565335,
|
|
"loss": 5.1113,
|
|
"mean_token_accuracy": 0.20070280283689498,
|
|
"num_tokens": 14021286.0,
|
|
"step": 7620
|
|
},
|
|
{
|
|
"entropy": 5.2809803009033205,
|
|
"epoch": 0.6369027731373205,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004965522729362209,
|
|
"loss": 5.1151,
|
|
"mean_token_accuracy": 0.19623906910419464,
|
|
"num_tokens": 14031901.0,
|
|
"step": 7625
|
|
},
|
|
{
|
|
"entropy": 5.326603126525879,
|
|
"epoch": 0.6373204143000334,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004965470794285676,
|
|
"loss": 5.1552,
|
|
"mean_token_accuracy": 0.20101962983608246,
|
|
"num_tokens": 14041000.0,
|
|
"step": 7630
|
|
},
|
|
{
|
|
"entropy": 5.391379261016846,
|
|
"epoch": 0.6377380554627464,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000496541882042466,
|
|
"loss": 5.1994,
|
|
"mean_token_accuracy": 0.19229317009449004,
|
|
"num_tokens": 14050567.0,
|
|
"step": 7635
|
|
},
|
|
{
|
|
"entropy": 5.272978019714356,
|
|
"epoch": 0.6381556966254595,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004965366807780071,
|
|
"loss": 5.0184,
|
|
"mean_token_accuracy": 0.2011002406477928,
|
|
"num_tokens": 14059990.0,
|
|
"step": 7640
|
|
},
|
|
{
|
|
"entropy": 5.318778657913208,
|
|
"epoch": 0.6385733377881724,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004965314756352818,
|
|
"loss": 5.1571,
|
|
"mean_token_accuracy": 0.19478807598352432,
|
|
"num_tokens": 14069317.0,
|
|
"step": 7645
|
|
},
|
|
{
|
|
"entropy": 5.306348896026611,
|
|
"epoch": 0.6389909789508854,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004965262666143816,
|
|
"loss": 5.1121,
|
|
"mean_token_accuracy": 0.20019335448741912,
|
|
"num_tokens": 14078809.0,
|
|
"step": 7650
|
|
},
|
|
{
|
|
"entropy": 5.311046504974366,
|
|
"epoch": 0.6394086201135984,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004965210537153973,
|
|
"loss": 5.1456,
|
|
"mean_token_accuracy": 0.19383479058742523,
|
|
"num_tokens": 14087660.0,
|
|
"step": 7655
|
|
},
|
|
{
|
|
"entropy": 5.320311880111694,
|
|
"epoch": 0.6398262612763114,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004965158369384204,
|
|
"loss": 5.1305,
|
|
"mean_token_accuracy": 0.1954892545938492,
|
|
"num_tokens": 14096585.0,
|
|
"step": 7660
|
|
},
|
|
{
|
|
"entropy": 5.310543727874756,
|
|
"epoch": 0.6402439024390244,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.000496510616283542,
|
|
"loss": 5.0618,
|
|
"mean_token_accuracy": 0.2030956745147705,
|
|
"num_tokens": 14106079.0,
|
|
"step": 7665
|
|
},
|
|
{
|
|
"entropy": 5.290688514709473,
|
|
"epoch": 0.6406615436017374,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004965053917508537,
|
|
"loss": 5.1609,
|
|
"mean_token_accuracy": 0.19612673968076705,
|
|
"num_tokens": 14115988.0,
|
|
"step": 7670
|
|
},
|
|
{
|
|
"entropy": 5.3077010154724125,
|
|
"epoch": 0.6410791847644504,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004965001633404469,
|
|
"loss": 5.2246,
|
|
"mean_token_accuracy": 0.18936279714107512,
|
|
"num_tokens": 14126980.0,
|
|
"step": 7675
|
|
},
|
|
{
|
|
"entropy": 5.361602306365967,
|
|
"epoch": 0.6414968259271634,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004964949310524131,
|
|
"loss": 5.1598,
|
|
"mean_token_accuracy": 0.19588953703641893,
|
|
"num_tokens": 14135780.0,
|
|
"step": 7680
|
|
},
|
|
{
|
|
"entropy": 5.360649919509887,
|
|
"epoch": 0.6419144670898764,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004964896948868439,
|
|
"loss": 5.1737,
|
|
"mean_token_accuracy": 0.18618624955415725,
|
|
"num_tokens": 14145655.0,
|
|
"step": 7685
|
|
},
|
|
{
|
|
"entropy": 5.308623027801514,
|
|
"epoch": 0.6423321082525894,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004964844548438311,
|
|
"loss": 5.062,
|
|
"mean_token_accuracy": 0.20873176902532578,
|
|
"num_tokens": 14154157.0,
|
|
"step": 7690
|
|
},
|
|
{
|
|
"entropy": 5.358855152130127,
|
|
"epoch": 0.6427497494153024,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004964792109234662,
|
|
"loss": 5.1866,
|
|
"mean_token_accuracy": 0.1956228569149971,
|
|
"num_tokens": 14163749.0,
|
|
"step": 7695
|
|
},
|
|
{
|
|
"entropy": 5.32371244430542,
|
|
"epoch": 0.6431673905780154,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004964739631258411,
|
|
"loss": 5.117,
|
|
"mean_token_accuracy": 0.19713355153799056,
|
|
"num_tokens": 14174170.0,
|
|
"step": 7700
|
|
},
|
|
{
|
|
"entropy": 5.288732385635376,
|
|
"epoch": 0.6435850317407283,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004964687114510478,
|
|
"loss": 5.1049,
|
|
"mean_token_accuracy": 0.19329818785190583,
|
|
"num_tokens": 14182625.0,
|
|
"step": 7705
|
|
},
|
|
{
|
|
"entropy": 5.318352460861206,
|
|
"epoch": 0.6440026729034414,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000496463455899178,
|
|
"loss": 5.1001,
|
|
"mean_token_accuracy": 0.1936970353126526,
|
|
"num_tokens": 14192351.0,
|
|
"step": 7710
|
|
},
|
|
{
|
|
"entropy": 5.256820154190064,
|
|
"epoch": 0.6444203140661544,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004964581964703239,
|
|
"loss": 5.022,
|
|
"mean_token_accuracy": 0.2059452250599861,
|
|
"num_tokens": 14201107.0,
|
|
"step": 7715
|
|
},
|
|
{
|
|
"entropy": 5.344346380233764,
|
|
"epoch": 0.6448379552288673,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004964529331645776,
|
|
"loss": 5.0548,
|
|
"mean_token_accuracy": 0.19872754961252212,
|
|
"num_tokens": 14209540.0,
|
|
"step": 7720
|
|
},
|
|
{
|
|
"entropy": 5.24354772567749,
|
|
"epoch": 0.6452555963915804,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000496447665982031,
|
|
"loss": 4.9641,
|
|
"mean_token_accuracy": 0.2039660707116127,
|
|
"num_tokens": 14217944.0,
|
|
"step": 7725
|
|
},
|
|
{
|
|
"entropy": 5.240013885498047,
|
|
"epoch": 0.6456732375542934,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004964423949227765,
|
|
"loss": 5.0298,
|
|
"mean_token_accuracy": 0.20450728088617326,
|
|
"num_tokens": 14226044.0,
|
|
"step": 7730
|
|
},
|
|
{
|
|
"entropy": 5.299234867095947,
|
|
"epoch": 0.6460908787170063,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004964371199869062,
|
|
"loss": 5.1067,
|
|
"mean_token_accuracy": 0.1913927376270294,
|
|
"num_tokens": 14235566.0,
|
|
"step": 7735
|
|
},
|
|
{
|
|
"entropy": 5.274836826324463,
|
|
"epoch": 0.6465085198797194,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004964318411745127,
|
|
"loss": 5.0307,
|
|
"mean_token_accuracy": 0.20680461823940277,
|
|
"num_tokens": 14244511.0,
|
|
"step": 7740
|
|
},
|
|
{
|
|
"entropy": 5.271277618408203,
|
|
"epoch": 0.6469261610424324,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004964265584856883,
|
|
"loss": 5.1153,
|
|
"mean_token_accuracy": 0.19961509108543396,
|
|
"num_tokens": 14254299.0,
|
|
"step": 7745
|
|
},
|
|
{
|
|
"entropy": 5.1947825908660885,
|
|
"epoch": 0.6473438022051453,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004964212719205254,
|
|
"loss": 5.0526,
|
|
"mean_token_accuracy": 0.1965569883584976,
|
|
"num_tokens": 14262915.0,
|
|
"step": 7750
|
|
},
|
|
{
|
|
"entropy": 5.3114409923553465,
|
|
"epoch": 0.6477614433678583,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004964159814791167,
|
|
"loss": 5.0959,
|
|
"mean_token_accuracy": 0.195010207593441,
|
|
"num_tokens": 14272606.0,
|
|
"step": 7755
|
|
},
|
|
{
|
|
"entropy": 5.322947025299072,
|
|
"epoch": 0.6481790845305714,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004964106871615547,
|
|
"loss": 5.1762,
|
|
"mean_token_accuracy": 0.18923254311084747,
|
|
"num_tokens": 14282117.0,
|
|
"step": 7760
|
|
},
|
|
{
|
|
"entropy": 5.252630281448364,
|
|
"epoch": 0.6485967256932843,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000496405388967932,
|
|
"loss": 5.0909,
|
|
"mean_token_accuracy": 0.20270532816648484,
|
|
"num_tokens": 14290421.0,
|
|
"step": 7765
|
|
},
|
|
{
|
|
"entropy": 5.364769744873047,
|
|
"epoch": 0.6490143668559973,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004964000868983416,
|
|
"loss": 5.1926,
|
|
"mean_token_accuracy": 0.19365463107824327,
|
|
"num_tokens": 14299870.0,
|
|
"step": 7770
|
|
},
|
|
{
|
|
"entropy": 5.3733344078063965,
|
|
"epoch": 0.6494320080187104,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004963947809528761,
|
|
"loss": 5.1025,
|
|
"mean_token_accuracy": 0.19596658945083617,
|
|
"num_tokens": 14309916.0,
|
|
"step": 7775
|
|
},
|
|
{
|
|
"entropy": 5.2920379638671875,
|
|
"epoch": 0.6498496491814233,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004963894711316285,
|
|
"loss": 5.0849,
|
|
"mean_token_accuracy": 0.19842049181461335,
|
|
"num_tokens": 14319061.0,
|
|
"step": 7780
|
|
},
|
|
{
|
|
"entropy": 5.2580322265625,
|
|
"epoch": 0.6502672903441363,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004963841574346917,
|
|
"loss": 5.0632,
|
|
"mean_token_accuracy": 0.20437927395105362,
|
|
"num_tokens": 14327241.0,
|
|
"step": 7785
|
|
},
|
|
{
|
|
"entropy": 5.328748655319214,
|
|
"epoch": 0.6506849315068494,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004963788398621587,
|
|
"loss": 5.1593,
|
|
"mean_token_accuracy": 0.19285826086997987,
|
|
"num_tokens": 14336586.0,
|
|
"step": 7790
|
|
},
|
|
{
|
|
"entropy": 5.345679473876953,
|
|
"epoch": 0.6511025726695623,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004963735184141227,
|
|
"loss": 5.1277,
|
|
"mean_token_accuracy": 0.19097969084978103,
|
|
"num_tokens": 14346484.0,
|
|
"step": 7795
|
|
},
|
|
{
|
|
"entropy": 5.3919901847839355,
|
|
"epoch": 0.6515202138322753,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004963681930906768,
|
|
"loss": 5.2006,
|
|
"mean_token_accuracy": 0.1854186996817589,
|
|
"num_tokens": 14356255.0,
|
|
"step": 7800
|
|
},
|
|
{
|
|
"entropy": 5.30468521118164,
|
|
"epoch": 0.6519378549949884,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004963628638919141,
|
|
"loss": 5.1371,
|
|
"mean_token_accuracy": 0.19927368313074112,
|
|
"num_tokens": 14365680.0,
|
|
"step": 7805
|
|
},
|
|
{
|
|
"entropy": 5.314786338806153,
|
|
"epoch": 0.6523554961577013,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004963575308179281,
|
|
"loss": 5.121,
|
|
"mean_token_accuracy": 0.20120913535356522,
|
|
"num_tokens": 14374546.0,
|
|
"step": 7810
|
|
},
|
|
{
|
|
"entropy": 5.354027605056762,
|
|
"epoch": 0.6527731373204143,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004963521938688122,
|
|
"loss": 5.1261,
|
|
"mean_token_accuracy": 0.19885395616292953,
|
|
"num_tokens": 14383624.0,
|
|
"step": 7815
|
|
},
|
|
{
|
|
"entropy": 5.336073207855224,
|
|
"epoch": 0.6531907784831273,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004963468530446596,
|
|
"loss": 5.2309,
|
|
"mean_token_accuracy": 0.19029023349285126,
|
|
"num_tokens": 14392482.0,
|
|
"step": 7820
|
|
},
|
|
{
|
|
"entropy": 5.3378218650817875,
|
|
"epoch": 0.6536084196458403,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004963415083455639,
|
|
"loss": 5.1289,
|
|
"mean_token_accuracy": 0.19663233011960984,
|
|
"num_tokens": 14401940.0,
|
|
"step": 7825
|
|
},
|
|
{
|
|
"entropy": 5.351269769668579,
|
|
"epoch": 0.6540260608085533,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004963361597716186,
|
|
"loss": 5.1819,
|
|
"mean_token_accuracy": 0.19608547687530517,
|
|
"num_tokens": 14411127.0,
|
|
"step": 7830
|
|
},
|
|
{
|
|
"entropy": 5.306780052185059,
|
|
"epoch": 0.6544437019712663,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004963308073229175,
|
|
"loss": 5.0796,
|
|
"mean_token_accuracy": 0.20138038247823714,
|
|
"num_tokens": 14421358.0,
|
|
"step": 7835
|
|
},
|
|
{
|
|
"entropy": 5.334666681289673,
|
|
"epoch": 0.6548613431339793,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004963254509995542,
|
|
"loss": 5.1106,
|
|
"mean_token_accuracy": 0.19146810173988343,
|
|
"num_tokens": 14430507.0,
|
|
"step": 7840
|
|
},
|
|
{
|
|
"entropy": 5.282521343231201,
|
|
"epoch": 0.6552789842966923,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004963200908016224,
|
|
"loss": 5.0872,
|
|
"mean_token_accuracy": 0.201054947078228,
|
|
"num_tokens": 14439723.0,
|
|
"step": 7845
|
|
},
|
|
{
|
|
"entropy": 5.305293369293213,
|
|
"epoch": 0.6556966254594053,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000496314726729216,
|
|
"loss": 5.0607,
|
|
"mean_token_accuracy": 0.20362130254507066,
|
|
"num_tokens": 14449011.0,
|
|
"step": 7850
|
|
},
|
|
{
|
|
"entropy": 5.2757282733917235,
|
|
"epoch": 0.6561142666221182,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004963093587824289,
|
|
"loss": 5.0535,
|
|
"mean_token_accuracy": 0.2070242941379547,
|
|
"num_tokens": 14457676.0,
|
|
"step": 7855
|
|
},
|
|
{
|
|
"entropy": 5.326574611663818,
|
|
"epoch": 0.6565319077848313,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004963039869613551,
|
|
"loss": 5.1288,
|
|
"mean_token_accuracy": 0.19888340532779694,
|
|
"num_tokens": 14466956.0,
|
|
"step": 7860
|
|
},
|
|
{
|
|
"entropy": 5.305872297286987,
|
|
"epoch": 0.6569495489475443,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004962986112660887,
|
|
"loss": 5.0384,
|
|
"mean_token_accuracy": 0.20392645746469498,
|
|
"num_tokens": 14476083.0,
|
|
"step": 7865
|
|
},
|
|
{
|
|
"entropy": 5.366641902923584,
|
|
"epoch": 0.6573671901102572,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004962932316967237,
|
|
"loss": 5.1355,
|
|
"mean_token_accuracy": 0.1912634178996086,
|
|
"num_tokens": 14484980.0,
|
|
"step": 7870
|
|
},
|
|
{
|
|
"entropy": 5.339543724060059,
|
|
"epoch": 0.6577848312729703,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004962878482533544,
|
|
"loss": 5.1557,
|
|
"mean_token_accuracy": 0.1986849457025528,
|
|
"num_tokens": 14493965.0,
|
|
"step": 7875
|
|
},
|
|
{
|
|
"entropy": 5.371400976181031,
|
|
"epoch": 0.6582024724356833,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004962824609360748,
|
|
"loss": 5.1378,
|
|
"mean_token_accuracy": 0.1929267928004265,
|
|
"num_tokens": 14501914.0,
|
|
"step": 7880
|
|
},
|
|
{
|
|
"entropy": 5.264023399353027,
|
|
"epoch": 0.6586201135983962,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004962770697449794,
|
|
"loss": 5.0521,
|
|
"mean_token_accuracy": 0.2027653858065605,
|
|
"num_tokens": 14511447.0,
|
|
"step": 7885
|
|
},
|
|
{
|
|
"entropy": 5.2572324752807615,
|
|
"epoch": 0.6590377547611093,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004962716746801625,
|
|
"loss": 5.0567,
|
|
"mean_token_accuracy": 0.19711564034223555,
|
|
"num_tokens": 14520558.0,
|
|
"step": 7890
|
|
},
|
|
{
|
|
"entropy": 5.27288556098938,
|
|
"epoch": 0.6594553959238223,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004962662757417187,
|
|
"loss": 5.0332,
|
|
"mean_token_accuracy": 0.19598861187696456,
|
|
"num_tokens": 14529995.0,
|
|
"step": 7895
|
|
},
|
|
{
|
|
"entropy": 5.281893110275268,
|
|
"epoch": 0.6598730370865352,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004962608729297424,
|
|
"loss": 5.1839,
|
|
"mean_token_accuracy": 0.18899975717067719,
|
|
"num_tokens": 14538972.0,
|
|
"step": 7900
|
|
},
|
|
{
|
|
"entropy": 5.34423418045044,
|
|
"epoch": 0.6602906782492483,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004962554662443281,
|
|
"loss": 5.1052,
|
|
"mean_token_accuracy": 0.1958961859345436,
|
|
"num_tokens": 14548255.0,
|
|
"step": 7905
|
|
},
|
|
{
|
|
"entropy": 5.350181198120117,
|
|
"epoch": 0.6607083194119613,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004962500556855706,
|
|
"loss": 5.0602,
|
|
"mean_token_accuracy": 0.20099108666181564,
|
|
"num_tokens": 14557265.0,
|
|
"step": 7910
|
|
},
|
|
{
|
|
"entropy": 5.371044874191284,
|
|
"epoch": 0.6611259605746742,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004962446412535645,
|
|
"loss": 5.14,
|
|
"mean_token_accuracy": 0.1972575604915619,
|
|
"num_tokens": 14566650.0,
|
|
"step": 7915
|
|
},
|
|
{
|
|
"entropy": 5.29285831451416,
|
|
"epoch": 0.6615436017373872,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004962392229484046,
|
|
"loss": 5.0137,
|
|
"mean_token_accuracy": 0.2096802905201912,
|
|
"num_tokens": 14575550.0,
|
|
"step": 7920
|
|
},
|
|
{
|
|
"entropy": 5.277502822875976,
|
|
"epoch": 0.6619612429001003,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.000496233800770186,
|
|
"loss": 5.0468,
|
|
"mean_token_accuracy": 0.20320571959018707,
|
|
"num_tokens": 14584459.0,
|
|
"step": 7925
|
|
},
|
|
{
|
|
"entropy": 5.37594165802002,
|
|
"epoch": 0.6623788840628132,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004962283747190033,
|
|
"loss": 5.1841,
|
|
"mean_token_accuracy": 0.19367690682411193,
|
|
"num_tokens": 14593709.0,
|
|
"step": 7930
|
|
},
|
|
{
|
|
"entropy": 5.281787157058716,
|
|
"epoch": 0.6627965252255262,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004962229447949515,
|
|
"loss": 5.0383,
|
|
"mean_token_accuracy": 0.19434078633785248,
|
|
"num_tokens": 14602071.0,
|
|
"step": 7935
|
|
},
|
|
{
|
|
"entropy": 5.352070426940918,
|
|
"epoch": 0.6632141663882393,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004962175109981259,
|
|
"loss": 5.2248,
|
|
"mean_token_accuracy": 0.18860409110784532,
|
|
"num_tokens": 14612842.0,
|
|
"step": 7940
|
|
},
|
|
{
|
|
"entropy": 5.4165356159210205,
|
|
"epoch": 0.6636318075509522,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004962120733286215,
|
|
"loss": 5.2274,
|
|
"mean_token_accuracy": 0.19570623487234115,
|
|
"num_tokens": 14621645.0,
|
|
"step": 7945
|
|
},
|
|
{
|
|
"entropy": 5.270502996444702,
|
|
"epoch": 0.6640494487136652,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004962066317865334,
|
|
"loss": 5.0369,
|
|
"mean_token_accuracy": 0.20039988160133362,
|
|
"num_tokens": 14630447.0,
|
|
"step": 7950
|
|
},
|
|
{
|
|
"entropy": 5.238588285446167,
|
|
"epoch": 0.6644670898763783,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000496201186371957,
|
|
"loss": 5.1231,
|
|
"mean_token_accuracy": 0.2023925691843033,
|
|
"num_tokens": 14639371.0,
|
|
"step": 7955
|
|
},
|
|
{
|
|
"entropy": 5.291700267791748,
|
|
"epoch": 0.6648847310390912,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004961957370849875,
|
|
"loss": 5.0374,
|
|
"mean_token_accuracy": 0.19844225645065308,
|
|
"num_tokens": 14648540.0,
|
|
"step": 7960
|
|
},
|
|
{
|
|
"entropy": 5.343546295166016,
|
|
"epoch": 0.6653023722018042,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004961902839257205,
|
|
"loss": 5.204,
|
|
"mean_token_accuracy": 0.1985940381884575,
|
|
"num_tokens": 14658130.0,
|
|
"step": 7965
|
|
},
|
|
{
|
|
"entropy": 5.351050758361817,
|
|
"epoch": 0.6657200133645172,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004961848268942513,
|
|
"loss": 5.1287,
|
|
"mean_token_accuracy": 0.1935892730951309,
|
|
"num_tokens": 14667538.0,
|
|
"step": 7970
|
|
},
|
|
{
|
|
"entropy": 5.359605836868286,
|
|
"epoch": 0.6661376545272302,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004961793659906754,
|
|
"loss": 5.1256,
|
|
"mean_token_accuracy": 0.19481374472379684,
|
|
"num_tokens": 14677115.0,
|
|
"step": 7975
|
|
},
|
|
{
|
|
"entropy": 5.382454442977905,
|
|
"epoch": 0.6665552956899432,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004961739012150885,
|
|
"loss": 5.0708,
|
|
"mean_token_accuracy": 0.20670475959777831,
|
|
"num_tokens": 14686444.0,
|
|
"step": 7980
|
|
},
|
|
{
|
|
"entropy": 5.291769075393677,
|
|
"epoch": 0.6669729368526562,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004961684325675862,
|
|
"loss": 5.0532,
|
|
"mean_token_accuracy": 0.20149117559194565,
|
|
"num_tokens": 14695951.0,
|
|
"step": 7985
|
|
},
|
|
{
|
|
"entropy": 5.314738845825195,
|
|
"epoch": 0.6673905780153692,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004961629600482643,
|
|
"loss": 5.1815,
|
|
"mean_token_accuracy": 0.19651031494140625,
|
|
"num_tokens": 14705415.0,
|
|
"step": 7990
|
|
},
|
|
{
|
|
"entropy": 5.418278408050537,
|
|
"epoch": 0.6678082191780822,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004961574836572186,
|
|
"loss": 5.1411,
|
|
"mean_token_accuracy": 0.19206517636775972,
|
|
"num_tokens": 14714793.0,
|
|
"step": 7995
|
|
},
|
|
{
|
|
"entropy": 5.219695138931274,
|
|
"epoch": 0.6682258603407952,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004961520033945448,
|
|
"loss": 4.9231,
|
|
"mean_token_accuracy": 0.21136569529771804,
|
|
"num_tokens": 14723820.0,
|
|
"step": 8000
|
|
},
|
|
{
|
|
"entropy": 5.250234985351563,
|
|
"epoch": 0.6686435015035082,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004961465192603391,
|
|
"loss": 5.0428,
|
|
"mean_token_accuracy": 0.2078256979584694,
|
|
"num_tokens": 14733055.0,
|
|
"step": 8005
|
|
},
|
|
{
|
|
"entropy": 5.296591758728027,
|
|
"epoch": 0.6690611426662212,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004961410312546974,
|
|
"loss": 5.0776,
|
|
"mean_token_accuracy": 0.19873370826244355,
|
|
"num_tokens": 14742416.0,
|
|
"step": 8010
|
|
},
|
|
{
|
|
"entropy": 5.26785569190979,
|
|
"epoch": 0.6694787838289342,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004961355393777158,
|
|
"loss": 5.0934,
|
|
"mean_token_accuracy": 0.19436735063791274,
|
|
"num_tokens": 14751384.0,
|
|
"step": 8015
|
|
},
|
|
{
|
|
"entropy": 5.2438493251800535,
|
|
"epoch": 0.6698964249916471,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004961300436294902,
|
|
"loss": 4.9582,
|
|
"mean_token_accuracy": 0.2011357992887497,
|
|
"num_tokens": 14760525.0,
|
|
"step": 8020
|
|
},
|
|
{
|
|
"entropy": 5.290905427932739,
|
|
"epoch": 0.6703140661543602,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004961245440101171,
|
|
"loss": 5.1173,
|
|
"mean_token_accuracy": 0.19173007905483247,
|
|
"num_tokens": 14769405.0,
|
|
"step": 8025
|
|
},
|
|
{
|
|
"entropy": 5.225229740142822,
|
|
"epoch": 0.6707317073170732,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004961190405196928,
|
|
"loss": 5.0026,
|
|
"mean_token_accuracy": 0.1994576022028923,
|
|
"num_tokens": 14778945.0,
|
|
"step": 8030
|
|
},
|
|
{
|
|
"entropy": 5.329796171188354,
|
|
"epoch": 0.6711493484797861,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004961135331583135,
|
|
"loss": 5.1744,
|
|
"mean_token_accuracy": 0.19213393479585647,
|
|
"num_tokens": 14788289.0,
|
|
"step": 8035
|
|
},
|
|
{
|
|
"entropy": 5.2559342861175535,
|
|
"epoch": 0.6715669896424992,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004961080219260755,
|
|
"loss": 5.1005,
|
|
"mean_token_accuracy": 0.19120832532644272,
|
|
"num_tokens": 14797761.0,
|
|
"step": 8040
|
|
},
|
|
{
|
|
"entropy": 5.363939237594605,
|
|
"epoch": 0.6719846308052122,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004961025068230757,
|
|
"loss": 5.1427,
|
|
"mean_token_accuracy": 0.2003529742360115,
|
|
"num_tokens": 14806424.0,
|
|
"step": 8045
|
|
},
|
|
{
|
|
"entropy": 5.286025762557983,
|
|
"epoch": 0.6724022719679251,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004960969878494103,
|
|
"loss": 5.076,
|
|
"mean_token_accuracy": 0.19537848681211473,
|
|
"num_tokens": 14815816.0,
|
|
"step": 8050
|
|
},
|
|
{
|
|
"entropy": 5.212112283706665,
|
|
"epoch": 0.6728199131306382,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004960914650051758,
|
|
"loss": 5.0714,
|
|
"mean_token_accuracy": 0.19653652161359786,
|
|
"num_tokens": 14824877.0,
|
|
"step": 8055
|
|
},
|
|
{
|
|
"entropy": 5.171276235580445,
|
|
"epoch": 0.6732375542933512,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004960859382904691,
|
|
"loss": 4.976,
|
|
"mean_token_accuracy": 0.21297705471515654,
|
|
"num_tokens": 14833095.0,
|
|
"step": 8060
|
|
},
|
|
{
|
|
"entropy": 5.331959581375122,
|
|
"epoch": 0.6736551954560641,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.000496080407705387,
|
|
"loss": 5.121,
|
|
"mean_token_accuracy": 0.19362065345048904,
|
|
"num_tokens": 14842963.0,
|
|
"step": 8065
|
|
},
|
|
{
|
|
"entropy": 5.382730293273926,
|
|
"epoch": 0.6740728366187771,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004960748732500263,
|
|
"loss": 5.1816,
|
|
"mean_token_accuracy": 0.19915306568145752,
|
|
"num_tokens": 14851552.0,
|
|
"step": 8070
|
|
},
|
|
{
|
|
"entropy": 5.3230689525604244,
|
|
"epoch": 0.6744904777814902,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004960693349244838,
|
|
"loss": 5.0883,
|
|
"mean_token_accuracy": 0.20031056106090545,
|
|
"num_tokens": 14859997.0,
|
|
"step": 8075
|
|
},
|
|
{
|
|
"entropy": 5.29914288520813,
|
|
"epoch": 0.6749081189442031,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004960637927288566,
|
|
"loss": 5.0141,
|
|
"mean_token_accuracy": 0.20240161716938018,
|
|
"num_tokens": 14868050.0,
|
|
"step": 8080
|
|
},
|
|
{
|
|
"entropy": 5.309638547897339,
|
|
"epoch": 0.6753257601069161,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004960582466632414,
|
|
"loss": 5.1257,
|
|
"mean_token_accuracy": 0.19337987303733825,
|
|
"num_tokens": 14877774.0,
|
|
"step": 8085
|
|
},
|
|
{
|
|
"entropy": 5.237140083312989,
|
|
"epoch": 0.6757434012696292,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004960526967277356,
|
|
"loss": 5.063,
|
|
"mean_token_accuracy": 0.20347631722688675,
|
|
"num_tokens": 14886971.0,
|
|
"step": 8090
|
|
},
|
|
{
|
|
"entropy": 5.242138051986695,
|
|
"epoch": 0.6761610424323421,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004960471429224363,
|
|
"loss": 5.001,
|
|
"mean_token_accuracy": 0.19711489975452423,
|
|
"num_tokens": 14895815.0,
|
|
"step": 8095
|
|
},
|
|
{
|
|
"entropy": 5.260533094406128,
|
|
"epoch": 0.6765786835950551,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004960415852474406,
|
|
"loss": 5.0181,
|
|
"mean_token_accuracy": 0.2097852572798729,
|
|
"num_tokens": 14904082.0,
|
|
"step": 8100
|
|
},
|
|
{
|
|
"entropy": 5.263446903228759,
|
|
"epoch": 0.6769963247577682,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000496036023702846,
|
|
"loss": 5.0556,
|
|
"mean_token_accuracy": 0.20446614921092987,
|
|
"num_tokens": 14913533.0,
|
|
"step": 8105
|
|
},
|
|
{
|
|
"entropy": 5.258649158477783,
|
|
"epoch": 0.6774139659204811,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004960304582887497,
|
|
"loss": 5.0273,
|
|
"mean_token_accuracy": 0.20526493936777115,
|
|
"num_tokens": 14922063.0,
|
|
"step": 8110
|
|
},
|
|
{
|
|
"entropy": 5.302123355865478,
|
|
"epoch": 0.6778316070831941,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004960248890052493,
|
|
"loss": 5.0685,
|
|
"mean_token_accuracy": 0.1979711025953293,
|
|
"num_tokens": 14930219.0,
|
|
"step": 8115
|
|
},
|
|
{
|
|
"entropy": 5.3335975170135494,
|
|
"epoch": 0.6782492482459072,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000496019315852442,
|
|
"loss": 5.1635,
|
|
"mean_token_accuracy": 0.1981356292963028,
|
|
"num_tokens": 14939463.0,
|
|
"step": 8120
|
|
},
|
|
{
|
|
"entropy": 5.3838402271270756,
|
|
"epoch": 0.6786668894086201,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004960137388304255,
|
|
"loss": 5.0599,
|
|
"mean_token_accuracy": 0.20408004373311997,
|
|
"num_tokens": 14948289.0,
|
|
"step": 8125
|
|
},
|
|
{
|
|
"entropy": 5.294534635543823,
|
|
"epoch": 0.6790845305713331,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004960081579392975,
|
|
"loss": 5.156,
|
|
"mean_token_accuracy": 0.19927862137556077,
|
|
"num_tokens": 14958172.0,
|
|
"step": 8130
|
|
},
|
|
{
|
|
"entropy": 5.263111114501953,
|
|
"epoch": 0.6795021717340461,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004960025731791558,
|
|
"loss": 4.9503,
|
|
"mean_token_accuracy": 0.20457581877708436,
|
|
"num_tokens": 14967362.0,
|
|
"step": 8135
|
|
},
|
|
{
|
|
"entropy": 5.264223575592041,
|
|
"epoch": 0.6799198128967591,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004959969845500979,
|
|
"loss": 5.1582,
|
|
"mean_token_accuracy": 0.1973573535680771,
|
|
"num_tokens": 14975942.0,
|
|
"step": 8140
|
|
},
|
|
{
|
|
"entropy": 5.2520099639892575,
|
|
"epoch": 0.6803374540594721,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004959913920522218,
|
|
"loss": 5.0856,
|
|
"mean_token_accuracy": 0.20315959453582763,
|
|
"num_tokens": 14985428.0,
|
|
"step": 8145
|
|
},
|
|
{
|
|
"entropy": 5.305872964859009,
|
|
"epoch": 0.6807550952221851,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004959857956856254,
|
|
"loss": 5.0405,
|
|
"mean_token_accuracy": 0.19473765045404434,
|
|
"num_tokens": 14994558.0,
|
|
"step": 8150
|
|
},
|
|
{
|
|
"entropy": 5.276914644241333,
|
|
"epoch": 0.6811727363848981,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004959801954504067,
|
|
"loss": 5.0446,
|
|
"mean_token_accuracy": 0.20354918241500855,
|
|
"num_tokens": 15003674.0,
|
|
"step": 8155
|
|
},
|
|
{
|
|
"entropy": 5.314305591583252,
|
|
"epoch": 0.6815903775476111,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004959745913466635,
|
|
"loss": 5.1038,
|
|
"mean_token_accuracy": 0.19496819525957107,
|
|
"num_tokens": 15012569.0,
|
|
"step": 8160
|
|
},
|
|
{
|
|
"entropy": 5.29022445678711,
|
|
"epoch": 0.6820080187103241,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004959689833744942,
|
|
"loss": 5.1093,
|
|
"mean_token_accuracy": 0.20106361657381058,
|
|
"num_tokens": 15021863.0,
|
|
"step": 8165
|
|
},
|
|
{
|
|
"entropy": 5.3149768829345705,
|
|
"epoch": 0.682425659873037,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004959633715339969,
|
|
"loss": 5.1641,
|
|
"mean_token_accuracy": 0.18934969902038573,
|
|
"num_tokens": 15032272.0,
|
|
"step": 8170
|
|
},
|
|
{
|
|
"entropy": 5.278515291213989,
|
|
"epoch": 0.6828433010357501,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004959577558252698,
|
|
"loss": 5.0947,
|
|
"mean_token_accuracy": 0.1965336576104164,
|
|
"num_tokens": 15041066.0,
|
|
"step": 8175
|
|
},
|
|
{
|
|
"entropy": 5.413792943954467,
|
|
"epoch": 0.6832609421984631,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004959521362484112,
|
|
"loss": 5.1795,
|
|
"mean_token_accuracy": 0.19215056598186492,
|
|
"num_tokens": 15050855.0,
|
|
"step": 8180
|
|
},
|
|
{
|
|
"entropy": 5.29156723022461,
|
|
"epoch": 0.683678583361176,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004959465128035195,
|
|
"loss": 5.0583,
|
|
"mean_token_accuracy": 0.20529651790857315,
|
|
"num_tokens": 15060810.0,
|
|
"step": 8185
|
|
},
|
|
{
|
|
"entropy": 5.279203033447265,
|
|
"epoch": 0.6840962245238891,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004959408854906932,
|
|
"loss": 5.0485,
|
|
"mean_token_accuracy": 0.19967632591724396,
|
|
"num_tokens": 15069761.0,
|
|
"step": 8190
|
|
},
|
|
{
|
|
"entropy": 5.249920797348023,
|
|
"epoch": 0.6845138656866021,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004959352543100306,
|
|
"loss": 5.04,
|
|
"mean_token_accuracy": 0.2037558451294899,
|
|
"num_tokens": 15078691.0,
|
|
"step": 8195
|
|
},
|
|
{
|
|
"entropy": 5.227643918991089,
|
|
"epoch": 0.684931506849315,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004959296192616305,
|
|
"loss": 5.0172,
|
|
"mean_token_accuracy": 0.20608447790145873,
|
|
"num_tokens": 15087068.0,
|
|
"step": 8200
|
|
},
|
|
{
|
|
"entropy": 5.2339574813842775,
|
|
"epoch": 0.6853491480120281,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004959239803455916,
|
|
"loss": 4.9284,
|
|
"mean_token_accuracy": 0.20378715246915818,
|
|
"num_tokens": 15095962.0,
|
|
"step": 8205
|
|
},
|
|
{
|
|
"entropy": 5.276957893371582,
|
|
"epoch": 0.6857667891747411,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004959183375620123,
|
|
"loss": 5.0839,
|
|
"mean_token_accuracy": 0.19588572382926941,
|
|
"num_tokens": 15105835.0,
|
|
"step": 8210
|
|
},
|
|
{
|
|
"entropy": 5.30806975364685,
|
|
"epoch": 0.686184430337454,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004959126909109918,
|
|
"loss": 5.0171,
|
|
"mean_token_accuracy": 0.21215804815292358,
|
|
"num_tokens": 15114140.0,
|
|
"step": 8215
|
|
},
|
|
{
|
|
"entropy": 5.294583511352539,
|
|
"epoch": 0.686602071500167,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004959070403926286,
|
|
"loss": 5.1102,
|
|
"mean_token_accuracy": 0.1996056392788887,
|
|
"num_tokens": 15123253.0,
|
|
"step": 8220
|
|
},
|
|
{
|
|
"entropy": 5.359203577041626,
|
|
"epoch": 0.6870197126628801,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004959013860070217,
|
|
"loss": 5.2143,
|
|
"mean_token_accuracy": 0.18856290876865386,
|
|
"num_tokens": 15133699.0,
|
|
"step": 8225
|
|
},
|
|
{
|
|
"entropy": 5.2771283149719235,
|
|
"epoch": 0.687437353825593,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004958957277542701,
|
|
"loss": 4.9794,
|
|
"mean_token_accuracy": 0.20531087666749953,
|
|
"num_tokens": 15142133.0,
|
|
"step": 8230
|
|
},
|
|
{
|
|
"entropy": 5.253825902938843,
|
|
"epoch": 0.687854994988306,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004958900656344731,
|
|
"loss": 5.0634,
|
|
"mean_token_accuracy": 0.20176597386598588,
|
|
"num_tokens": 15151367.0,
|
|
"step": 8235
|
|
},
|
|
{
|
|
"entropy": 5.3135082721710205,
|
|
"epoch": 0.6882726361510191,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004958843996477296,
|
|
"loss": 5.0721,
|
|
"mean_token_accuracy": 0.1943616524338722,
|
|
"num_tokens": 15160938.0,
|
|
"step": 8240
|
|
},
|
|
{
|
|
"entropy": 5.3709173679351805,
|
|
"epoch": 0.688690277313732,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004958787297941386,
|
|
"loss": 5.1449,
|
|
"mean_token_accuracy": 0.18945931047201156,
|
|
"num_tokens": 15170507.0,
|
|
"step": 8245
|
|
},
|
|
{
|
|
"entropy": 5.346620512008667,
|
|
"epoch": 0.689107918476445,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004958730560737998,
|
|
"loss": 5.1351,
|
|
"mean_token_accuracy": 0.19945331215858458,
|
|
"num_tokens": 15179822.0,
|
|
"step": 8250
|
|
},
|
|
{
|
|
"entropy": 5.25492000579834,
|
|
"epoch": 0.6895255596391581,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004958673784868121,
|
|
"loss": 5.0333,
|
|
"mean_token_accuracy": 0.19747120887041092,
|
|
"num_tokens": 15189353.0,
|
|
"step": 8255
|
|
},
|
|
{
|
|
"entropy": 5.342983198165894,
|
|
"epoch": 0.689943200801871,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004958616970332752,
|
|
"loss": 5.1042,
|
|
"mean_token_accuracy": 0.19633375704288483,
|
|
"num_tokens": 15197772.0,
|
|
"step": 8260
|
|
},
|
|
{
|
|
"entropy": 5.28785138130188,
|
|
"epoch": 0.690360841964584,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004958560117132884,
|
|
"loss": 5.0528,
|
|
"mean_token_accuracy": 0.20304337590932847,
|
|
"num_tokens": 15207453.0,
|
|
"step": 8265
|
|
},
|
|
{
|
|
"entropy": 5.266658735275269,
|
|
"epoch": 0.6907784831272971,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004958503225269513,
|
|
"loss": 4.9883,
|
|
"mean_token_accuracy": 0.2039983779191971,
|
|
"num_tokens": 15215787.0,
|
|
"step": 8270
|
|
},
|
|
{
|
|
"entropy": 5.365818119049072,
|
|
"epoch": 0.69119612429001,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004958446294743633,
|
|
"loss": 5.1081,
|
|
"mean_token_accuracy": 0.20084684193134308,
|
|
"num_tokens": 15225148.0,
|
|
"step": 8275
|
|
},
|
|
{
|
|
"entropy": 5.35207724571228,
|
|
"epoch": 0.691613765452723,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004958389325556245,
|
|
"loss": 5.1335,
|
|
"mean_token_accuracy": 0.20135464072227477,
|
|
"num_tokens": 15234533.0,
|
|
"step": 8280
|
|
},
|
|
{
|
|
"entropy": 5.3103758811950685,
|
|
"epoch": 0.692031406615436,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004958332317708341,
|
|
"loss": 5.114,
|
|
"mean_token_accuracy": 0.1895854130387306,
|
|
"num_tokens": 15243805.0,
|
|
"step": 8285
|
|
},
|
|
{
|
|
"entropy": 5.337362337112427,
|
|
"epoch": 0.692449047778149,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004958275271200924,
|
|
"loss": 5.1491,
|
|
"mean_token_accuracy": 0.19990954846143721,
|
|
"num_tokens": 15253298.0,
|
|
"step": 8290
|
|
},
|
|
{
|
|
"entropy": 5.256933403015137,
|
|
"epoch": 0.692866688940862,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004958218186034988,
|
|
"loss": 5.0958,
|
|
"mean_token_accuracy": 0.20100583285093307,
|
|
"num_tokens": 15261860.0,
|
|
"step": 8295
|
|
},
|
|
{
|
|
"entropy": 5.256998109817505,
|
|
"epoch": 0.693284330103575,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004958161062211537,
|
|
"loss": 5.0202,
|
|
"mean_token_accuracy": 0.20656843036413192,
|
|
"num_tokens": 15271021.0,
|
|
"step": 8300
|
|
},
|
|
{
|
|
"entropy": 5.268578004837036,
|
|
"epoch": 0.693701971266288,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004958103899731566,
|
|
"loss": 5.0733,
|
|
"mean_token_accuracy": 0.1962606877088547,
|
|
"num_tokens": 15280489.0,
|
|
"step": 8305
|
|
},
|
|
{
|
|
"entropy": 5.294385290145874,
|
|
"epoch": 0.694119612429001,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004958046698596081,
|
|
"loss": 5.0868,
|
|
"mean_token_accuracy": 0.20690073668956757,
|
|
"num_tokens": 15289387.0,
|
|
"step": 8310
|
|
},
|
|
{
|
|
"entropy": 5.352888441085815,
|
|
"epoch": 0.694537253591714,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004957989458806079,
|
|
"loss": 5.1597,
|
|
"mean_token_accuracy": 0.19498630464076996,
|
|
"num_tokens": 15299334.0,
|
|
"step": 8315
|
|
},
|
|
{
|
|
"entropy": 5.29277024269104,
|
|
"epoch": 0.694954894754427,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004957932180362564,
|
|
"loss": 5.1086,
|
|
"mean_token_accuracy": 0.1986047223210335,
|
|
"num_tokens": 15309174.0,
|
|
"step": 8320
|
|
},
|
|
{
|
|
"entropy": 5.349100828170776,
|
|
"epoch": 0.69537253591714,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004957874863266538,
|
|
"loss": 5.1795,
|
|
"mean_token_accuracy": 0.19804793298244477,
|
|
"num_tokens": 15318722.0,
|
|
"step": 8325
|
|
},
|
|
{
|
|
"entropy": 5.364262199401855,
|
|
"epoch": 0.695790177079853,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004957817507519006,
|
|
"loss": 5.1062,
|
|
"mean_token_accuracy": 0.19870518147945404,
|
|
"num_tokens": 15327606.0,
|
|
"step": 8330
|
|
},
|
|
{
|
|
"entropy": 5.249139070510864,
|
|
"epoch": 0.696207818242566,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004957760113120971,
|
|
"loss": 5.0615,
|
|
"mean_token_accuracy": 0.20379491299390792,
|
|
"num_tokens": 15336520.0,
|
|
"step": 8335
|
|
},
|
|
{
|
|
"entropy": 5.328909063339234,
|
|
"epoch": 0.696625459405279,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004957702680073437,
|
|
"loss": 5.1171,
|
|
"mean_token_accuracy": 0.1945207491517067,
|
|
"num_tokens": 15345437.0,
|
|
"step": 8340
|
|
},
|
|
{
|
|
"entropy": 5.375838708877564,
|
|
"epoch": 0.697043100567992,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004957645208377411,
|
|
"loss": 5.0858,
|
|
"mean_token_accuracy": 0.20251954346895218,
|
|
"num_tokens": 15354660.0,
|
|
"step": 8345
|
|
},
|
|
{
|
|
"entropy": 5.3071235656738285,
|
|
"epoch": 0.6974607417307049,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004957587698033898,
|
|
"loss": 5.0843,
|
|
"mean_token_accuracy": 0.20400189310312272,
|
|
"num_tokens": 15363958.0,
|
|
"step": 8350
|
|
},
|
|
{
|
|
"entropy": 5.235809230804444,
|
|
"epoch": 0.697878382893418,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004957530149043905,
|
|
"loss": 5.0626,
|
|
"mean_token_accuracy": 0.21092468053102492,
|
|
"num_tokens": 15373351.0,
|
|
"step": 8355
|
|
},
|
|
{
|
|
"entropy": 5.328260993957519,
|
|
"epoch": 0.698296024056131,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004957472561408438,
|
|
"loss": 5.0741,
|
|
"mean_token_accuracy": 0.20314389765262603,
|
|
"num_tokens": 15383069.0,
|
|
"step": 8360
|
|
},
|
|
{
|
|
"entropy": 5.283101415634155,
|
|
"epoch": 0.6987136652188439,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004957414935128509,
|
|
"loss": 5.0681,
|
|
"mean_token_accuracy": 0.1992212116718292,
|
|
"num_tokens": 15391394.0,
|
|
"step": 8365
|
|
},
|
|
{
|
|
"entropy": 5.312133693695069,
|
|
"epoch": 0.699131306381557,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004957357270205123,
|
|
"loss": 5.0496,
|
|
"mean_token_accuracy": 0.1943216875195503,
|
|
"num_tokens": 15399993.0,
|
|
"step": 8370
|
|
},
|
|
{
|
|
"entropy": 5.270085096359253,
|
|
"epoch": 0.69954894754427,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004957299566639292,
|
|
"loss": 5.0586,
|
|
"mean_token_accuracy": 0.20217949002981186,
|
|
"num_tokens": 15409886.0,
|
|
"step": 8375
|
|
},
|
|
{
|
|
"entropy": 5.348963069915771,
|
|
"epoch": 0.6999665887069829,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004957241824432025,
|
|
"loss": 5.0543,
|
|
"mean_token_accuracy": 0.20485760867595673,
|
|
"num_tokens": 15419772.0,
|
|
"step": 8380
|
|
},
|
|
{
|
|
"entropy": 5.3304625988006595,
|
|
"epoch": 0.700384229869696,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004957184043584333,
|
|
"loss": 5.0603,
|
|
"mean_token_accuracy": 0.1997678056359291,
|
|
"num_tokens": 15429631.0,
|
|
"step": 8385
|
|
},
|
|
{
|
|
"entropy": 5.235268259048462,
|
|
"epoch": 0.700801871032409,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004957126224097227,
|
|
"loss": 4.9991,
|
|
"mean_token_accuracy": 0.20829747170209884,
|
|
"num_tokens": 15438411.0,
|
|
"step": 8390
|
|
},
|
|
{
|
|
"entropy": 5.178777456283569,
|
|
"epoch": 0.7012195121951219,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.000495706836597172,
|
|
"loss": 5.0422,
|
|
"mean_token_accuracy": 0.20752644389867783,
|
|
"num_tokens": 15448943.0,
|
|
"step": 8395
|
|
},
|
|
{
|
|
"entropy": 5.316345167160034,
|
|
"epoch": 0.7016371533578349,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004957010469208825,
|
|
"loss": 4.9992,
|
|
"mean_token_accuracy": 0.20072227865457534,
|
|
"num_tokens": 15457908.0,
|
|
"step": 8400
|
|
},
|
|
{
|
|
"entropy": 5.3117913722991945,
|
|
"epoch": 0.702054794520548,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004956952533809554,
|
|
"loss": 5.0861,
|
|
"mean_token_accuracy": 0.20061833560466766,
|
|
"num_tokens": 15467390.0,
|
|
"step": 8405
|
|
},
|
|
{
|
|
"entropy": 5.299106454849243,
|
|
"epoch": 0.7024724356832609,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004956894559774923,
|
|
"loss": 5.09,
|
|
"mean_token_accuracy": 0.19801439493894576,
|
|
"num_tokens": 15476419.0,
|
|
"step": 8410
|
|
},
|
|
{
|
|
"entropy": 5.217239713668823,
|
|
"epoch": 0.7028900768459739,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004956836547105947,
|
|
"loss": 4.9567,
|
|
"mean_token_accuracy": 0.20828939527273177,
|
|
"num_tokens": 15485147.0,
|
|
"step": 8415
|
|
},
|
|
{
|
|
"entropy": 5.339694166183472,
|
|
"epoch": 0.703307718008687,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004956778495803641,
|
|
"loss": 5.0693,
|
|
"mean_token_accuracy": 0.20299905836582183,
|
|
"num_tokens": 15493816.0,
|
|
"step": 8420
|
|
},
|
|
{
|
|
"entropy": 5.341966819763184,
|
|
"epoch": 0.7037253591713999,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.000495672040586902,
|
|
"loss": 5.1719,
|
|
"mean_token_accuracy": 0.198117758333683,
|
|
"num_tokens": 15503051.0,
|
|
"step": 8425
|
|
},
|
|
{
|
|
"entropy": 5.27577576637268,
|
|
"epoch": 0.7041430003341129,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004956662277303103,
|
|
"loss": 4.9703,
|
|
"mean_token_accuracy": 0.20579586923122406,
|
|
"num_tokens": 15511854.0,
|
|
"step": 8430
|
|
},
|
|
{
|
|
"entropy": 5.2234395980834964,
|
|
"epoch": 0.704560641496826,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004956604110106905,
|
|
"loss": 5.1022,
|
|
"mean_token_accuracy": 0.20253927260637283,
|
|
"num_tokens": 15521492.0,
|
|
"step": 8435
|
|
},
|
|
{
|
|
"entropy": 5.385797119140625,
|
|
"epoch": 0.7049782826595389,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004956545904281447,
|
|
"loss": 5.175,
|
|
"mean_token_accuracy": 0.19008471965789794,
|
|
"num_tokens": 15530983.0,
|
|
"step": 8440
|
|
},
|
|
{
|
|
"entropy": 5.2986513614654545,
|
|
"epoch": 0.7053959238222519,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004956487659827748,
|
|
"loss": 5.0165,
|
|
"mean_token_accuracy": 0.2094108760356903,
|
|
"num_tokens": 15539722.0,
|
|
"step": 8445
|
|
},
|
|
{
|
|
"entropy": 5.226106739044189,
|
|
"epoch": 0.705813564984965,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004956429376746825,
|
|
"loss": 4.9884,
|
|
"mean_token_accuracy": 0.20108505189418793,
|
|
"num_tokens": 15548738.0,
|
|
"step": 8450
|
|
},
|
|
{
|
|
"entropy": 5.218436145782471,
|
|
"epoch": 0.7062312061476779,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004956371055039701,
|
|
"loss": 5.0367,
|
|
"mean_token_accuracy": 0.207009457051754,
|
|
"num_tokens": 15557520.0,
|
|
"step": 8455
|
|
},
|
|
{
|
|
"entropy": 5.371583795547485,
|
|
"epoch": 0.7066488473103909,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004956312694707395,
|
|
"loss": 5.1095,
|
|
"mean_token_accuracy": 0.18941996544599532,
|
|
"num_tokens": 15567860.0,
|
|
"step": 8460
|
|
},
|
|
{
|
|
"entropy": 5.342587947845459,
|
|
"epoch": 0.7070664884731039,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000495625429575093,
|
|
"loss": 5.1189,
|
|
"mean_token_accuracy": 0.1891679659485817,
|
|
"num_tokens": 15577174.0,
|
|
"step": 8465
|
|
},
|
|
{
|
|
"entropy": 5.208229303359985,
|
|
"epoch": 0.7074841296358169,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004956195858171327,
|
|
"loss": 4.9148,
|
|
"mean_token_accuracy": 0.21200518310070038,
|
|
"num_tokens": 15585476.0,
|
|
"step": 8470
|
|
},
|
|
{
|
|
"entropy": 5.253299045562744,
|
|
"epoch": 0.7079017707985299,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004956137381969611,
|
|
"loss": 5.0509,
|
|
"mean_token_accuracy": 0.20225137025117873,
|
|
"num_tokens": 15595422.0,
|
|
"step": 8475
|
|
},
|
|
{
|
|
"entropy": 5.313663625717163,
|
|
"epoch": 0.7083194119612429,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004956078867146805,
|
|
"loss": 5.1754,
|
|
"mean_token_accuracy": 0.19252022802829744,
|
|
"num_tokens": 15604223.0,
|
|
"step": 8480
|
|
},
|
|
{
|
|
"entropy": 5.360964393615722,
|
|
"epoch": 0.7087370531239559,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004956020313703933,
|
|
"loss": 5.1452,
|
|
"mean_token_accuracy": 0.19828291088342667,
|
|
"num_tokens": 15613715.0,
|
|
"step": 8485
|
|
},
|
|
{
|
|
"entropy": 5.283772993087768,
|
|
"epoch": 0.7091546942866689,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004955961721642018,
|
|
"loss": 4.9514,
|
|
"mean_token_accuracy": 0.21511617302894592,
|
|
"num_tokens": 15623826.0,
|
|
"step": 8490
|
|
},
|
|
{
|
|
"entropy": 5.279223775863647,
|
|
"epoch": 0.7095723354493819,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.000495590309096209,
|
|
"loss": 5.0742,
|
|
"mean_token_accuracy": 0.19097951352596282,
|
|
"num_tokens": 15633311.0,
|
|
"step": 8495
|
|
},
|
|
{
|
|
"entropy": 5.302570962905884,
|
|
"epoch": 0.7099899766120948,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004955844421665171,
|
|
"loss": 5.0585,
|
|
"mean_token_accuracy": 0.2011215418577194,
|
|
"num_tokens": 15642785.0,
|
|
"step": 8500
|
|
},
|
|
{
|
|
"entropy": 5.4760472774505615,
|
|
"epoch": 0.7104076177748079,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004955785713752292,
|
|
"loss": 5.2412,
|
|
"mean_token_accuracy": 0.19061580151319504,
|
|
"num_tokens": 15653009.0,
|
|
"step": 8505
|
|
},
|
|
{
|
|
"entropy": 5.285912990570068,
|
|
"epoch": 0.7108252589375209,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004955726967224479,
|
|
"loss": 5.0509,
|
|
"mean_token_accuracy": 0.20130133628845215,
|
|
"num_tokens": 15661672.0,
|
|
"step": 8510
|
|
},
|
|
{
|
|
"entropy": 5.246235466003418,
|
|
"epoch": 0.7112429001002338,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000495566818208276,
|
|
"loss": 5.0419,
|
|
"mean_token_accuracy": 0.19729198962450029,
|
|
"num_tokens": 15672186.0,
|
|
"step": 8515
|
|
},
|
|
{
|
|
"entropy": 5.253251409530639,
|
|
"epoch": 0.7116605412629469,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004955609358328163,
|
|
"loss": 5.062,
|
|
"mean_token_accuracy": 0.20900222957134246,
|
|
"num_tokens": 15680351.0,
|
|
"step": 8520
|
|
},
|
|
{
|
|
"entropy": 5.31048092842102,
|
|
"epoch": 0.7120781824256599,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004955550495961722,
|
|
"loss": 5.0378,
|
|
"mean_token_accuracy": 0.20055311769247056,
|
|
"num_tokens": 15690140.0,
|
|
"step": 8525
|
|
},
|
|
{
|
|
"entropy": 5.326376867294312,
|
|
"epoch": 0.7124958235883728,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004955491594984462,
|
|
"loss": 5.1456,
|
|
"mean_token_accuracy": 0.19382750391960143,
|
|
"num_tokens": 15699968.0,
|
|
"step": 8530
|
|
},
|
|
{
|
|
"entropy": 5.25221996307373,
|
|
"epoch": 0.7129134647510859,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004955432655397419,
|
|
"loss": 4.9932,
|
|
"mean_token_accuracy": 0.20656435936689377,
|
|
"num_tokens": 15709061.0,
|
|
"step": 8535
|
|
},
|
|
{
|
|
"entropy": 5.32095422744751,
|
|
"epoch": 0.7133311059137989,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004955373677201621,
|
|
"loss": 5.129,
|
|
"mean_token_accuracy": 0.19353578388690948,
|
|
"num_tokens": 15718350.0,
|
|
"step": 8540
|
|
},
|
|
{
|
|
"entropy": 5.292722558975219,
|
|
"epoch": 0.7137487470765118,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004955314660398105,
|
|
"loss": 5.0299,
|
|
"mean_token_accuracy": 0.2031239926815033,
|
|
"num_tokens": 15727120.0,
|
|
"step": 8545
|
|
},
|
|
{
|
|
"entropy": 5.286660861968994,
|
|
"epoch": 0.7141663882392248,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004955255604987899,
|
|
"loss": 5.1276,
|
|
"mean_token_accuracy": 0.19722677916288375,
|
|
"num_tokens": 15735865.0,
|
|
"step": 8550
|
|
},
|
|
{
|
|
"entropy": 5.2603583335876465,
|
|
"epoch": 0.7145840294019379,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.000495519651097204,
|
|
"loss": 5.082,
|
|
"mean_token_accuracy": 0.19790492951869965,
|
|
"num_tokens": 15745239.0,
|
|
"step": 8555
|
|
},
|
|
{
|
|
"entropy": 5.266436433792114,
|
|
"epoch": 0.7150016705646508,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004955137378351561,
|
|
"loss": 4.9968,
|
|
"mean_token_accuracy": 0.20420053005218505,
|
|
"num_tokens": 15754418.0,
|
|
"step": 8560
|
|
},
|
|
{
|
|
"entropy": 5.297505664825439,
|
|
"epoch": 0.7154193117273638,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004955078207127498,
|
|
"loss": 5.0638,
|
|
"mean_token_accuracy": 0.20508573800325394,
|
|
"num_tokens": 15764175.0,
|
|
"step": 8565
|
|
},
|
|
{
|
|
"entropy": 5.310714530944824,
|
|
"epoch": 0.7158369528900769,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004955018997300886,
|
|
"loss": 5.0352,
|
|
"mean_token_accuracy": 0.20058477520942689,
|
|
"num_tokens": 15772766.0,
|
|
"step": 8570
|
|
},
|
|
{
|
|
"entropy": 5.214248323440552,
|
|
"epoch": 0.7162545940527898,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004954959748872764,
|
|
"loss": 5.0591,
|
|
"mean_token_accuracy": 0.20578003525733948,
|
|
"num_tokens": 15781768.0,
|
|
"step": 8575
|
|
},
|
|
{
|
|
"entropy": 5.334406471252441,
|
|
"epoch": 0.7166722352155028,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004954900461844167,
|
|
"loss": 5.1135,
|
|
"mean_token_accuracy": 0.1969414994120598,
|
|
"num_tokens": 15791706.0,
|
|
"step": 8580
|
|
},
|
|
{
|
|
"entropy": 5.366378211975098,
|
|
"epoch": 0.7170898763782159,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004954841136216132,
|
|
"loss": 5.1272,
|
|
"mean_token_accuracy": 0.19717603623867036,
|
|
"num_tokens": 15802015.0,
|
|
"step": 8585
|
|
},
|
|
{
|
|
"entropy": 5.320854663848877,
|
|
"epoch": 0.7175075175409288,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004954781771989701,
|
|
"loss": 5.0665,
|
|
"mean_token_accuracy": 0.2000778377056122,
|
|
"num_tokens": 15811116.0,
|
|
"step": 8590
|
|
},
|
|
{
|
|
"entropy": 5.351994037628174,
|
|
"epoch": 0.7179251587036418,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000495472236916591,
|
|
"loss": 5.0377,
|
|
"mean_token_accuracy": 0.1998966559767723,
|
|
"num_tokens": 15819240.0,
|
|
"step": 8595
|
|
},
|
|
{
|
|
"entropy": 5.286137437820434,
|
|
"epoch": 0.7183427998663549,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004954662927745799,
|
|
"loss": 5.0492,
|
|
"mean_token_accuracy": 0.1938687175512314,
|
|
"num_tokens": 15827740.0,
|
|
"step": 8600
|
|
},
|
|
{
|
|
"entropy": 5.233812236785889,
|
|
"epoch": 0.7187604410290678,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004954603447730411,
|
|
"loss": 5.1066,
|
|
"mean_token_accuracy": 0.19758808612823486,
|
|
"num_tokens": 15836763.0,
|
|
"step": 8605
|
|
},
|
|
{
|
|
"entropy": 5.399864768981933,
|
|
"epoch": 0.7191780821917808,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004954543929120786,
|
|
"loss": 5.1756,
|
|
"mean_token_accuracy": 0.19459035098552704,
|
|
"num_tokens": 15846624.0,
|
|
"step": 8610
|
|
},
|
|
{
|
|
"entropy": 5.343923711776734,
|
|
"epoch": 0.7195957233544938,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004954484371917967,
|
|
"loss": 5.0874,
|
|
"mean_token_accuracy": 0.19594507217407225,
|
|
"num_tokens": 15855713.0,
|
|
"step": 8615
|
|
},
|
|
{
|
|
"entropy": 5.2160741806030275,
|
|
"epoch": 0.7200133645172068,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004954424776122993,
|
|
"loss": 4.9217,
|
|
"mean_token_accuracy": 0.2120089665055275,
|
|
"num_tokens": 15863577.0,
|
|
"step": 8620
|
|
},
|
|
{
|
|
"entropy": 5.294074773788452,
|
|
"epoch": 0.7204310056799198,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004954365141736913,
|
|
"loss": 5.0769,
|
|
"mean_token_accuracy": 0.20392575412988662,
|
|
"num_tokens": 15872479.0,
|
|
"step": 8625
|
|
},
|
|
{
|
|
"entropy": 5.355267095565796,
|
|
"epoch": 0.7208486468426328,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004954305468760765,
|
|
"loss": 5.1697,
|
|
"mean_token_accuracy": 0.2003491461277008,
|
|
"num_tokens": 15882170.0,
|
|
"step": 8630
|
|
},
|
|
{
|
|
"entropy": 5.341642427444458,
|
|
"epoch": 0.7212662880053458,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004954245757195598,
|
|
"loss": 5.0649,
|
|
"mean_token_accuracy": 0.2069210559129715,
|
|
"num_tokens": 15891694.0,
|
|
"step": 8635
|
|
},
|
|
{
|
|
"entropy": 5.319044208526611,
|
|
"epoch": 0.7216839291680588,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004954186007042454,
|
|
"loss": 5.1771,
|
|
"mean_token_accuracy": 0.18936493545770644,
|
|
"num_tokens": 15902232.0,
|
|
"step": 8640
|
|
},
|
|
{
|
|
"entropy": 5.281481456756592,
|
|
"epoch": 0.7221015703307718,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004954126218302382,
|
|
"loss": 5.0232,
|
|
"mean_token_accuracy": 0.20015035271644593,
|
|
"num_tokens": 15912218.0,
|
|
"step": 8645
|
|
},
|
|
{
|
|
"entropy": 5.269867467880249,
|
|
"epoch": 0.7225192114934847,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004954066390976427,
|
|
"loss": 5.0158,
|
|
"mean_token_accuracy": 0.20863578766584395,
|
|
"num_tokens": 15922011.0,
|
|
"step": 8650
|
|
},
|
|
{
|
|
"entropy": 5.1690638065338135,
|
|
"epoch": 0.7229368526561978,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004954006525065639,
|
|
"loss": 4.9903,
|
|
"mean_token_accuracy": 0.20333651453256607,
|
|
"num_tokens": 15930394.0,
|
|
"step": 8655
|
|
},
|
|
{
|
|
"entropy": 5.291082191467285,
|
|
"epoch": 0.7233544938189108,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004953946620571061,
|
|
"loss": 5.085,
|
|
"mean_token_accuracy": 0.197337506711483,
|
|
"num_tokens": 15939880.0,
|
|
"step": 8660
|
|
},
|
|
{
|
|
"entropy": 5.285974216461182,
|
|
"epoch": 0.7237721349816237,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004953886677493746,
|
|
"loss": 4.9699,
|
|
"mean_token_accuracy": 0.20998845845460892,
|
|
"num_tokens": 15948521.0,
|
|
"step": 8665
|
|
},
|
|
{
|
|
"entropy": 5.29067850112915,
|
|
"epoch": 0.7241897761443368,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004953826695834741,
|
|
"loss": 5.0987,
|
|
"mean_token_accuracy": 0.19873740524053574,
|
|
"num_tokens": 15956811.0,
|
|
"step": 8670
|
|
},
|
|
{
|
|
"entropy": 5.2703441143035885,
|
|
"epoch": 0.7246074173070498,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004953766675595098,
|
|
"loss": 5.1187,
|
|
"mean_token_accuracy": 0.20053162127733232,
|
|
"num_tokens": 15967019.0,
|
|
"step": 8675
|
|
},
|
|
{
|
|
"entropy": 5.385362720489502,
|
|
"epoch": 0.7250250584697627,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004953706616775866,
|
|
"loss": 5.1137,
|
|
"mean_token_accuracy": 0.19549519270658494,
|
|
"num_tokens": 15976149.0,
|
|
"step": 8680
|
|
},
|
|
{
|
|
"entropy": 5.302666473388672,
|
|
"epoch": 0.7254426996324758,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004953646519378097,
|
|
"loss": 4.9218,
|
|
"mean_token_accuracy": 0.20791263431310653,
|
|
"num_tokens": 15986711.0,
|
|
"step": 8685
|
|
},
|
|
{
|
|
"entropy": 5.277779483795166,
|
|
"epoch": 0.7258603407951888,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004953586383402844,
|
|
"loss": 5.091,
|
|
"mean_token_accuracy": 0.19872635155916213,
|
|
"num_tokens": 15996482.0,
|
|
"step": 8690
|
|
},
|
|
{
|
|
"entropy": 5.176142930984497,
|
|
"epoch": 0.7262779819579017,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004953526208851157,
|
|
"loss": 4.9632,
|
|
"mean_token_accuracy": 0.2036085918545723,
|
|
"num_tokens": 16005801.0,
|
|
"step": 8695
|
|
},
|
|
{
|
|
"entropy": 5.199421167373657,
|
|
"epoch": 0.7266956231206148,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004953465995724092,
|
|
"loss": 5.0092,
|
|
"mean_token_accuracy": 0.2009180873632431,
|
|
"num_tokens": 16014807.0,
|
|
"step": 8700
|
|
},
|
|
{
|
|
"entropy": 5.310466480255127,
|
|
"epoch": 0.7271132642833278,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004953405744022705,
|
|
"loss": 5.1466,
|
|
"mean_token_accuracy": 0.19814235866069793,
|
|
"num_tokens": 16023326.0,
|
|
"step": 8705
|
|
},
|
|
{
|
|
"entropy": 5.3451879024505615,
|
|
"epoch": 0.7275309054460407,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004953345453748045,
|
|
"loss": 5.0942,
|
|
"mean_token_accuracy": 0.194943343102932,
|
|
"num_tokens": 16031648.0,
|
|
"step": 8710
|
|
},
|
|
{
|
|
"entropy": 5.271716070175171,
|
|
"epoch": 0.7279485466087537,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004953285124901171,
|
|
"loss": 5.0223,
|
|
"mean_token_accuracy": 0.20396826714277266,
|
|
"num_tokens": 16040179.0,
|
|
"step": 8715
|
|
},
|
|
{
|
|
"entropy": 5.303973627090454,
|
|
"epoch": 0.7283661877714668,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.000495322475748314,
|
|
"loss": 5.1873,
|
|
"mean_token_accuracy": 0.1893076092004776,
|
|
"num_tokens": 16050770.0,
|
|
"step": 8720
|
|
},
|
|
{
|
|
"entropy": 5.361210536956787,
|
|
"epoch": 0.7287838289341797,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004953164351495007,
|
|
"loss": 5.0387,
|
|
"mean_token_accuracy": 0.20573963075876237,
|
|
"num_tokens": 16060504.0,
|
|
"step": 8725
|
|
},
|
|
{
|
|
"entropy": 5.220712089538575,
|
|
"epoch": 0.7292014700968927,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004953103906937831,
|
|
"loss": 4.8926,
|
|
"mean_token_accuracy": 0.21957828849554062,
|
|
"num_tokens": 16069240.0,
|
|
"step": 8730
|
|
},
|
|
{
|
|
"entropy": 5.176104211807251,
|
|
"epoch": 0.7296191112596058,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004953043423812669,
|
|
"loss": 5.1434,
|
|
"mean_token_accuracy": 0.19955668449401856,
|
|
"num_tokens": 16079098.0,
|
|
"step": 8735
|
|
},
|
|
{
|
|
"entropy": 5.2147783756256105,
|
|
"epoch": 0.7300367524223187,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004952982902120579,
|
|
"loss": 4.97,
|
|
"mean_token_accuracy": 0.20637630224227904,
|
|
"num_tokens": 16088454.0,
|
|
"step": 8740
|
|
},
|
|
{
|
|
"entropy": 5.328648042678833,
|
|
"epoch": 0.7304543935850317,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004952922341862622,
|
|
"loss": 5.1058,
|
|
"mean_token_accuracy": 0.19543055295944214,
|
|
"num_tokens": 16096985.0,
|
|
"step": 8745
|
|
},
|
|
{
|
|
"entropy": 5.397544193267822,
|
|
"epoch": 0.7308720347477448,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004952861743039858,
|
|
"loss": 5.1971,
|
|
"mean_token_accuracy": 0.1901056155562401,
|
|
"num_tokens": 16105434.0,
|
|
"step": 8750
|
|
},
|
|
{
|
|
"entropy": 5.184029293060303,
|
|
"epoch": 0.7312896759104577,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004952801105653347,
|
|
"loss": 4.9423,
|
|
"mean_token_accuracy": 0.21344213038682938,
|
|
"num_tokens": 16114933.0,
|
|
"step": 8755
|
|
},
|
|
{
|
|
"entropy": 5.333026695251465,
|
|
"epoch": 0.7317073170731707,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004952740429704152,
|
|
"loss": 5.1163,
|
|
"mean_token_accuracy": 0.19112866818904878,
|
|
"num_tokens": 16124954.0,
|
|
"step": 8760
|
|
},
|
|
{
|
|
"entropy": 5.314546346664429,
|
|
"epoch": 0.7321249582358837,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004952679715193334,
|
|
"loss": 4.931,
|
|
"mean_token_accuracy": 0.20849736630916596,
|
|
"num_tokens": 16134442.0,
|
|
"step": 8765
|
|
},
|
|
{
|
|
"entropy": 5.301894617080689,
|
|
"epoch": 0.7325425993985967,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004952618962121956,
|
|
"loss": 5.1039,
|
|
"mean_token_accuracy": 0.1969986751675606,
|
|
"num_tokens": 16143994.0,
|
|
"step": 8770
|
|
},
|
|
{
|
|
"entropy": 5.2608765125274655,
|
|
"epoch": 0.7329602405613097,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004952558170491082,
|
|
"loss": 5.0265,
|
|
"mean_token_accuracy": 0.20228615403175354,
|
|
"num_tokens": 16152931.0,
|
|
"step": 8775
|
|
},
|
|
{
|
|
"entropy": 5.302912044525146,
|
|
"epoch": 0.7333778817240227,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004952497340301776,
|
|
"loss": 5.0227,
|
|
"mean_token_accuracy": 0.1981823980808258,
|
|
"num_tokens": 16162716.0,
|
|
"step": 8780
|
|
},
|
|
{
|
|
"entropy": 5.308622217178344,
|
|
"epoch": 0.7337955228867357,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004952436471555103,
|
|
"loss": 5.0805,
|
|
"mean_token_accuracy": 0.1987333506345749,
|
|
"num_tokens": 16172371.0,
|
|
"step": 8785
|
|
},
|
|
{
|
|
"entropy": 5.302491998672485,
|
|
"epoch": 0.7342131640494487,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004952375564252128,
|
|
"loss": 5.1532,
|
|
"mean_token_accuracy": 0.19661444872617723,
|
|
"num_tokens": 16181823.0,
|
|
"step": 8790
|
|
},
|
|
{
|
|
"entropy": 5.293154573440551,
|
|
"epoch": 0.7346308052121617,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004952314618393919,
|
|
"loss": 5.0655,
|
|
"mean_token_accuracy": 0.20362306535243987,
|
|
"num_tokens": 16190720.0,
|
|
"step": 8795
|
|
},
|
|
{
|
|
"entropy": 5.27875280380249,
|
|
"epoch": 0.7350484463748747,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000495225363398154,
|
|
"loss": 4.9997,
|
|
"mean_token_accuracy": 0.20117570012807845,
|
|
"num_tokens": 16199589.0,
|
|
"step": 8800
|
|
},
|
|
{
|
|
"entropy": 5.353147792816162,
|
|
"epoch": 0.7354660875375877,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004952192611016061,
|
|
"loss": 5.1663,
|
|
"mean_token_accuracy": 0.19834163784980774,
|
|
"num_tokens": 16208800.0,
|
|
"step": 8805
|
|
},
|
|
{
|
|
"entropy": 5.310691833496094,
|
|
"epoch": 0.7358837287003007,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.000495213154949855,
|
|
"loss": 5.1518,
|
|
"mean_token_accuracy": 0.1956395149230957,
|
|
"num_tokens": 16218835.0,
|
|
"step": 8810
|
|
},
|
|
{
|
|
"entropy": 5.350011682510376,
|
|
"epoch": 0.7363013698630136,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004952070449430075,
|
|
"loss": 5.0969,
|
|
"mean_token_accuracy": 0.20128366947174073,
|
|
"num_tokens": 16228441.0,
|
|
"step": 8815
|
|
},
|
|
{
|
|
"entropy": 5.362833547592163,
|
|
"epoch": 0.7367190110257267,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004952009310811706,
|
|
"loss": 5.0783,
|
|
"mean_token_accuracy": 0.2080063506960869,
|
|
"num_tokens": 16237877.0,
|
|
"step": 8820
|
|
},
|
|
{
|
|
"entropy": 5.2682441711425785,
|
|
"epoch": 0.7371366521884397,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004951948133644514,
|
|
"loss": 5.013,
|
|
"mean_token_accuracy": 0.20266563594341278,
|
|
"num_tokens": 16246809.0,
|
|
"step": 8825
|
|
},
|
|
{
|
|
"entropy": 5.324000597000122,
|
|
"epoch": 0.7375542933511526,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000495188691792957,
|
|
"loss": 5.0832,
|
|
"mean_token_accuracy": 0.2116958737373352,
|
|
"num_tokens": 16255754.0,
|
|
"step": 8830
|
|
},
|
|
{
|
|
"entropy": 5.309404754638672,
|
|
"epoch": 0.7379719345138657,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004951825663667943,
|
|
"loss": 5.119,
|
|
"mean_token_accuracy": 0.20001896917819978,
|
|
"num_tokens": 16264861.0,
|
|
"step": 8835
|
|
},
|
|
{
|
|
"entropy": 5.268008613586426,
|
|
"epoch": 0.7383895756765787,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000495176437086071,
|
|
"loss": 5.0394,
|
|
"mean_token_accuracy": 0.20309204012155532,
|
|
"num_tokens": 16273628.0,
|
|
"step": 8840
|
|
},
|
|
{
|
|
"entropy": 5.287184858322144,
|
|
"epoch": 0.7388072168392917,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.000495170303950894,
|
|
"loss": 5.0394,
|
|
"mean_token_accuracy": 0.20065390467643737,
|
|
"num_tokens": 16282958.0,
|
|
"step": 8845
|
|
},
|
|
{
|
|
"entropy": 5.342790222167968,
|
|
"epoch": 0.7392248580020047,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004951641669613708,
|
|
"loss": 5.081,
|
|
"mean_token_accuracy": 0.19833653122186662,
|
|
"num_tokens": 16292763.0,
|
|
"step": 8850
|
|
},
|
|
{
|
|
"entropy": 5.290163946151734,
|
|
"epoch": 0.7396424991647177,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004951580261176088,
|
|
"loss": 5.0637,
|
|
"mean_token_accuracy": 0.20175071358680724,
|
|
"num_tokens": 16302216.0,
|
|
"step": 8855
|
|
},
|
|
{
|
|
"entropy": 5.213641691207886,
|
|
"epoch": 0.7400601403274307,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004951518814197156,
|
|
"loss": 4.9844,
|
|
"mean_token_accuracy": 0.20687176138162613,
|
|
"num_tokens": 16311672.0,
|
|
"step": 8860
|
|
},
|
|
{
|
|
"entropy": 5.289334297180176,
|
|
"epoch": 0.7404777814901436,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004951457328677989,
|
|
"loss": 4.9879,
|
|
"mean_token_accuracy": 0.20168158859014512,
|
|
"num_tokens": 16321027.0,
|
|
"step": 8865
|
|
},
|
|
{
|
|
"entropy": 5.330817413330078,
|
|
"epoch": 0.7408954226528567,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004951395804619659,
|
|
"loss": 5.105,
|
|
"mean_token_accuracy": 0.19175008237361907,
|
|
"num_tokens": 16329471.0,
|
|
"step": 8870
|
|
},
|
|
{
|
|
"entropy": 5.239703941345215,
|
|
"epoch": 0.7413130638155697,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004951334242023247,
|
|
"loss": 5.0449,
|
|
"mean_token_accuracy": 0.2017623022198677,
|
|
"num_tokens": 16339085.0,
|
|
"step": 8875
|
|
},
|
|
{
|
|
"entropy": 5.346188020706177,
|
|
"epoch": 0.7417307049782826,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004951272640889828,
|
|
"loss": 5.1115,
|
|
"mean_token_accuracy": 0.20438565462827682,
|
|
"num_tokens": 16347950.0,
|
|
"step": 8880
|
|
},
|
|
{
|
|
"entropy": 5.27294602394104,
|
|
"epoch": 0.7421483461409957,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004951211001220484,
|
|
"loss": 4.9026,
|
|
"mean_token_accuracy": 0.209273998439312,
|
|
"num_tokens": 16357129.0,
|
|
"step": 8885
|
|
},
|
|
{
|
|
"entropy": 5.2367175102233885,
|
|
"epoch": 0.7425659873037087,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000495114932301629,
|
|
"loss": 5.0269,
|
|
"mean_token_accuracy": 0.20274857431650162,
|
|
"num_tokens": 16365768.0,
|
|
"step": 8890
|
|
},
|
|
{
|
|
"entropy": 5.276386499404907,
|
|
"epoch": 0.7429836284664216,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004951087606278328,
|
|
"loss": 4.9989,
|
|
"mean_token_accuracy": 0.2076172113418579,
|
|
"num_tokens": 16375548.0,
|
|
"step": 8895
|
|
},
|
|
{
|
|
"entropy": 5.308200120925903,
|
|
"epoch": 0.7434012696291347,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004951025851007678,
|
|
"loss": 5.0658,
|
|
"mean_token_accuracy": 0.2082823783159256,
|
|
"num_tokens": 16385472.0,
|
|
"step": 8900
|
|
},
|
|
{
|
|
"entropy": 5.2607502937316895,
|
|
"epoch": 0.7438189107918477,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004950964057205421,
|
|
"loss": 4.9373,
|
|
"mean_token_accuracy": 0.20607596933841704,
|
|
"num_tokens": 16395048.0,
|
|
"step": 8905
|
|
},
|
|
{
|
|
"entropy": 5.358189392089844,
|
|
"epoch": 0.7442365519545606,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.000495090222487264,
|
|
"loss": 5.168,
|
|
"mean_token_accuracy": 0.193108494579792,
|
|
"num_tokens": 16405378.0,
|
|
"step": 8910
|
|
},
|
|
{
|
|
"entropy": 5.2722883224487305,
|
|
"epoch": 0.7446541931172737,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004950840354010415,
|
|
"loss": 5.0344,
|
|
"mean_token_accuracy": 0.20605543553829192,
|
|
"num_tokens": 16415206.0,
|
|
"step": 8915
|
|
},
|
|
{
|
|
"entropy": 5.290538692474366,
|
|
"epoch": 0.7450718342799867,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004950778444619831,
|
|
"loss": 5.0532,
|
|
"mean_token_accuracy": 0.21444262117147445,
|
|
"num_tokens": 16424185.0,
|
|
"step": 8920
|
|
},
|
|
{
|
|
"entropy": 5.269124174118042,
|
|
"epoch": 0.7454894754426996,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.000495071649670197,
|
|
"loss": 5.0342,
|
|
"mean_token_accuracy": 0.20239607542753218,
|
|
"num_tokens": 16433330.0,
|
|
"step": 8925
|
|
},
|
|
{
|
|
"entropy": 5.251119804382324,
|
|
"epoch": 0.7459071166054126,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.000495065451025792,
|
|
"loss": 5.0385,
|
|
"mean_token_accuracy": 0.20068047046661378,
|
|
"num_tokens": 16442777.0,
|
|
"step": 8930
|
|
},
|
|
{
|
|
"entropy": 5.272030162811279,
|
|
"epoch": 0.7463247577681257,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004950592485288761,
|
|
"loss": 5.0313,
|
|
"mean_token_accuracy": 0.20843802988529206,
|
|
"num_tokens": 16451838.0,
|
|
"step": 8935
|
|
},
|
|
{
|
|
"entropy": 5.262492990493774,
|
|
"epoch": 0.7467423989308386,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004950530421795584,
|
|
"loss": 5.0034,
|
|
"mean_token_accuracy": 0.20206386893987655,
|
|
"num_tokens": 16460022.0,
|
|
"step": 8940
|
|
},
|
|
{
|
|
"entropy": 5.227031803131103,
|
|
"epoch": 0.7471600400935516,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004950468319779472,
|
|
"loss": 4.8881,
|
|
"mean_token_accuracy": 0.21292097121477127,
|
|
"num_tokens": 16468891.0,
|
|
"step": 8945
|
|
},
|
|
{
|
|
"entropy": 5.178910493850708,
|
|
"epoch": 0.7475776812562647,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004950406179241515,
|
|
"loss": 4.9798,
|
|
"mean_token_accuracy": 0.21524928212165834,
|
|
"num_tokens": 16478020.0,
|
|
"step": 8950
|
|
},
|
|
{
|
|
"entropy": 5.294888162612915,
|
|
"epoch": 0.7479953224189776,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004950344000182798,
|
|
"loss": 5.1492,
|
|
"mean_token_accuracy": 0.19855829030275346,
|
|
"num_tokens": 16487536.0,
|
|
"step": 8955
|
|
},
|
|
{
|
|
"entropy": 5.33293890953064,
|
|
"epoch": 0.7484129635816906,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004950281782604411,
|
|
"loss": 5.0628,
|
|
"mean_token_accuracy": 0.19553593695163726,
|
|
"num_tokens": 16495786.0,
|
|
"step": 8960
|
|
},
|
|
{
|
|
"entropy": 5.392992734909058,
|
|
"epoch": 0.7488306047444037,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004950219526507442,
|
|
"loss": 5.1313,
|
|
"mean_token_accuracy": 0.19654490202665328,
|
|
"num_tokens": 16505535.0,
|
|
"step": 8965
|
|
},
|
|
{
|
|
"entropy": 5.348032522201538,
|
|
"epoch": 0.7492482459071166,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004950157231892983,
|
|
"loss": 5.1381,
|
|
"mean_token_accuracy": 0.2017208978533745,
|
|
"num_tokens": 16515387.0,
|
|
"step": 8970
|
|
},
|
|
{
|
|
"entropy": 5.280672788619995,
|
|
"epoch": 0.7496658870698296,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004950094898762123,
|
|
"loss": 5.0877,
|
|
"mean_token_accuracy": 0.2006358951330185,
|
|
"num_tokens": 16524421.0,
|
|
"step": 8975
|
|
},
|
|
{
|
|
"entropy": 5.351682472229004,
|
|
"epoch": 0.7500835282325427,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004950032527115954,
|
|
"loss": 5.078,
|
|
"mean_token_accuracy": 0.1996570646762848,
|
|
"num_tokens": 16534533.0,
|
|
"step": 8980
|
|
},
|
|
{
|
|
"entropy": 5.312414073944092,
|
|
"epoch": 0.7505011693952556,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004949970116955566,
|
|
"loss": 5.0823,
|
|
"mean_token_accuracy": 0.19341331273317336,
|
|
"num_tokens": 16543712.0,
|
|
"step": 8985
|
|
},
|
|
{
|
|
"entropy": 5.277249717712403,
|
|
"epoch": 0.7509188105579686,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004949907668282054,
|
|
"loss": 5.0713,
|
|
"mean_token_accuracy": 0.20276295095682145,
|
|
"num_tokens": 16552475.0,
|
|
"step": 8990
|
|
},
|
|
{
|
|
"entropy": 5.320142984390259,
|
|
"epoch": 0.7513364517206816,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000494984518109651,
|
|
"loss": 5.0511,
|
|
"mean_token_accuracy": 0.20469123274087905,
|
|
"num_tokens": 16562237.0,
|
|
"step": 8995
|
|
},
|
|
{
|
|
"entropy": 5.322559356689453,
|
|
"epoch": 0.7517540928833946,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004949782655400028,
|
|
"loss": 5.0621,
|
|
"mean_token_accuracy": 0.20243751555681228,
|
|
"num_tokens": 16570508.0,
|
|
"step": 9000
|
|
},
|
|
{
|
|
"epoch": 0.7517540928833946,
|
|
"eval_entropy": 4.992306073119494,
|
|
"eval_loss": 5.0120134353637695,
|
|
"eval_mean_token_accuracy": 0.214023694042507,
|
|
"eval_num_tokens": 16570508.0,
|
|
"eval_runtime": 20.8829,
|
|
"eval_samples_per_second": 1808.324,
|
|
"eval_steps_per_second": 226.07,
|
|
"step": 9000
|
|
},
|
|
{
|
|
"entropy": 5.1767021179199215,
|
|
"epoch": 0.7521717340461076,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004949720091193704,
|
|
"loss": 4.9614,
|
|
"mean_token_accuracy": 0.20973383337259294,
|
|
"num_tokens": 16578561.0,
|
|
"step": 9005
|
|
},
|
|
{
|
|
"entropy": 5.207372665405273,
|
|
"epoch": 0.7525893752088206,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000494965748847863,
|
|
"loss": 4.9397,
|
|
"mean_token_accuracy": 0.20836803168058396,
|
|
"num_tokens": 16587168.0,
|
|
"step": 9010
|
|
},
|
|
{
|
|
"entropy": 5.2924432277679445,
|
|
"epoch": 0.7530070163715336,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004949594847255905,
|
|
"loss": 5.0971,
|
|
"mean_token_accuracy": 0.19820506721735,
|
|
"num_tokens": 16597252.0,
|
|
"step": 9015
|
|
},
|
|
{
|
|
"entropy": 5.233920478820801,
|
|
"epoch": 0.7534246575342466,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004949532167526625,
|
|
"loss": 4.9273,
|
|
"mean_token_accuracy": 0.21284876763820648,
|
|
"num_tokens": 16607558.0,
|
|
"step": 9020
|
|
},
|
|
{
|
|
"entropy": 5.30990252494812,
|
|
"epoch": 0.7538422986969596,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004949469449291886,
|
|
"loss": 5.132,
|
|
"mean_token_accuracy": 0.1954716607928276,
|
|
"num_tokens": 16617019.0,
|
|
"step": 9025
|
|
},
|
|
{
|
|
"entropy": 5.280575466156006,
|
|
"epoch": 0.7542599398596725,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004949406692552787,
|
|
"loss": 4.9777,
|
|
"mean_token_accuracy": 0.20624036192893982,
|
|
"num_tokens": 16625815.0,
|
|
"step": 9030
|
|
},
|
|
{
|
|
"entropy": 5.332900667190552,
|
|
"epoch": 0.7546775810223856,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004949343897310426,
|
|
"loss": 5.1946,
|
|
"mean_token_accuracy": 0.19692480862140654,
|
|
"num_tokens": 16634876.0,
|
|
"step": 9035
|
|
},
|
|
{
|
|
"entropy": 5.277521419525146,
|
|
"epoch": 0.7550952221850986,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004949281063565904,
|
|
"loss": 5.0679,
|
|
"mean_token_accuracy": 0.19392486214637755,
|
|
"num_tokens": 16643770.0,
|
|
"step": 9040
|
|
},
|
|
{
|
|
"entropy": 5.327452850341797,
|
|
"epoch": 0.7555128633478115,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004949218191320319,
|
|
"loss": 5.0189,
|
|
"mean_token_accuracy": 0.19956471771001816,
|
|
"num_tokens": 16652845.0,
|
|
"step": 9045
|
|
},
|
|
{
|
|
"entropy": 5.228081560134887,
|
|
"epoch": 0.7559305045105246,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004949155280574772,
|
|
"loss": 5.004,
|
|
"mean_token_accuracy": 0.2051224708557129,
|
|
"num_tokens": 16662224.0,
|
|
"step": 9050
|
|
},
|
|
{
|
|
"entropy": 5.259872817993164,
|
|
"epoch": 0.7563481456732376,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004949092331330365,
|
|
"loss": 4.9909,
|
|
"mean_token_accuracy": 0.20357671678066253,
|
|
"num_tokens": 16671114.0,
|
|
"step": 9055
|
|
},
|
|
{
|
|
"entropy": 5.279949378967285,
|
|
"epoch": 0.7567657868359505,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00049490293435882,
|
|
"loss": 5.0722,
|
|
"mean_token_accuracy": 0.19587585479021072,
|
|
"num_tokens": 16680395.0,
|
|
"step": 9060
|
|
},
|
|
{
|
|
"entropy": 5.3000411033630375,
|
|
"epoch": 0.7571834279986636,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004948966317349379,
|
|
"loss": 5.0347,
|
|
"mean_token_accuracy": 0.20271148532629013,
|
|
"num_tokens": 16690251.0,
|
|
"step": 9065
|
|
},
|
|
{
|
|
"entropy": 5.227061796188354,
|
|
"epoch": 0.7576010691613766,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004948903252615006,
|
|
"loss": 4.9214,
|
|
"mean_token_accuracy": 0.2127152979373932,
|
|
"num_tokens": 16698945.0,
|
|
"step": 9070
|
|
},
|
|
{
|
|
"entropy": 5.328841876983643,
|
|
"epoch": 0.7580187103240895,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004948840149386184,
|
|
"loss": 5.1207,
|
|
"mean_token_accuracy": 0.1974414274096489,
|
|
"num_tokens": 16708325.0,
|
|
"step": 9075
|
|
},
|
|
{
|
|
"entropy": 5.257896661758423,
|
|
"epoch": 0.7584363514868026,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000494877700766402,
|
|
"loss": 5.0149,
|
|
"mean_token_accuracy": 0.20404049456119538,
|
|
"num_tokens": 16716392.0,
|
|
"step": 9080
|
|
},
|
|
{
|
|
"entropy": 5.272157335281372,
|
|
"epoch": 0.7588539926495156,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004948713827449616,
|
|
"loss": 5.0401,
|
|
"mean_token_accuracy": 0.20416046380996705,
|
|
"num_tokens": 16725284.0,
|
|
"step": 9085
|
|
},
|
|
{
|
|
"entropy": 5.239689540863037,
|
|
"epoch": 0.7592716338122285,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004948650608744081,
|
|
"loss": 5.0596,
|
|
"mean_token_accuracy": 0.20529814809560776,
|
|
"num_tokens": 16734658.0,
|
|
"step": 9090
|
|
},
|
|
{
|
|
"entropy": 5.380432224273681,
|
|
"epoch": 0.7596892749749415,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000494858735154852,
|
|
"loss": 5.16,
|
|
"mean_token_accuracy": 0.19234798699617386,
|
|
"num_tokens": 16744403.0,
|
|
"step": 9095
|
|
},
|
|
{
|
|
"entropy": 5.366984844207764,
|
|
"epoch": 0.7601069161376546,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004948524055864041,
|
|
"loss": 5.133,
|
|
"mean_token_accuracy": 0.1997056409716606,
|
|
"num_tokens": 16754254.0,
|
|
"step": 9100
|
|
},
|
|
{
|
|
"entropy": 5.326011705398559,
|
|
"epoch": 0.7605245573003675,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004948460721691752,
|
|
"loss": 5.1359,
|
|
"mean_token_accuracy": 0.19720993041992188,
|
|
"num_tokens": 16763941.0,
|
|
"step": 9105
|
|
},
|
|
{
|
|
"entropy": 5.295243883132935,
|
|
"epoch": 0.7609421984630805,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004948397349032762,
|
|
"loss": 5.0422,
|
|
"mean_token_accuracy": 0.20102442502975465,
|
|
"num_tokens": 16773181.0,
|
|
"step": 9110
|
|
},
|
|
{
|
|
"entropy": 5.1932860851287845,
|
|
"epoch": 0.7613598396257936,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000494833393788818,
|
|
"loss": 4.8807,
|
|
"mean_token_accuracy": 0.21331206560134888,
|
|
"num_tokens": 16782622.0,
|
|
"step": 9115
|
|
},
|
|
{
|
|
"entropy": 5.314014720916748,
|
|
"epoch": 0.7617774807885065,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004948270488259117,
|
|
"loss": 5.1199,
|
|
"mean_token_accuracy": 0.20172844231128692,
|
|
"num_tokens": 16792805.0,
|
|
"step": 9120
|
|
},
|
|
{
|
|
"entropy": 5.306127071380615,
|
|
"epoch": 0.7621951219512195,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004948207000146682,
|
|
"loss": 5.0881,
|
|
"mean_token_accuracy": 0.20799920409917833,
|
|
"num_tokens": 16802641.0,
|
|
"step": 9125
|
|
},
|
|
{
|
|
"entropy": 5.340350389480591,
|
|
"epoch": 0.7626127631139326,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004948143473551989,
|
|
"loss": 5.0775,
|
|
"mean_token_accuracy": 0.19613206535577773,
|
|
"num_tokens": 16812037.0,
|
|
"step": 9130
|
|
},
|
|
{
|
|
"entropy": 5.274501514434815,
|
|
"epoch": 0.7630304042766455,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004948079908476147,
|
|
"loss": 5.0327,
|
|
"mean_token_accuracy": 0.21585725247859955,
|
|
"num_tokens": 16820279.0,
|
|
"step": 9135
|
|
},
|
|
{
|
|
"entropy": 5.269076347351074,
|
|
"epoch": 0.7634480454393585,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004948016304920271,
|
|
"loss": 5.0336,
|
|
"mean_token_accuracy": 0.19964986592531203,
|
|
"num_tokens": 16829396.0,
|
|
"step": 9140
|
|
},
|
|
{
|
|
"entropy": 5.275078868865966,
|
|
"epoch": 0.7638656866020715,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004947952662885473,
|
|
"loss": 5.011,
|
|
"mean_token_accuracy": 0.20565113723278045,
|
|
"num_tokens": 16838389.0,
|
|
"step": 9145
|
|
},
|
|
{
|
|
"entropy": 5.271355295181275,
|
|
"epoch": 0.7642833277647845,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000494788898237287,
|
|
"loss": 5.1171,
|
|
"mean_token_accuracy": 0.19436787068843842,
|
|
"num_tokens": 16848012.0,
|
|
"step": 9150
|
|
},
|
|
{
|
|
"entropy": 5.31104211807251,
|
|
"epoch": 0.7647009689274975,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004947825263383573,
|
|
"loss": 5.0785,
|
|
"mean_token_accuracy": 0.20117024183273316,
|
|
"num_tokens": 16857591.0,
|
|
"step": 9155
|
|
},
|
|
{
|
|
"entropy": 5.35554838180542,
|
|
"epoch": 0.7651186100902105,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00049477615059187,
|
|
"loss": 5.0821,
|
|
"mean_token_accuracy": 0.1895461291074753,
|
|
"num_tokens": 16866792.0,
|
|
"step": 9160
|
|
},
|
|
{
|
|
"entropy": 5.259443235397339,
|
|
"epoch": 0.7655362512529235,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004947697709979367,
|
|
"loss": 5.0996,
|
|
"mean_token_accuracy": 0.2034372240304947,
|
|
"num_tokens": 16876602.0,
|
|
"step": 9165
|
|
},
|
|
{
|
|
"entropy": 5.301667547225952,
|
|
"epoch": 0.7659538924156365,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004947633875566688,
|
|
"loss": 5.0758,
|
|
"mean_token_accuracy": 0.1992911234498024,
|
|
"num_tokens": 16886992.0,
|
|
"step": 9170
|
|
},
|
|
{
|
|
"entropy": 5.27959041595459,
|
|
"epoch": 0.7663715335783495,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004947570002681785,
|
|
"loss": 5.0027,
|
|
"mean_token_accuracy": 0.2038028672337532,
|
|
"num_tokens": 16895716.0,
|
|
"step": 9175
|
|
},
|
|
{
|
|
"entropy": 5.241288042068481,
|
|
"epoch": 0.7667891747410625,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004947506091325772,
|
|
"loss": 5.0134,
|
|
"mean_token_accuracy": 0.21356237679719925,
|
|
"num_tokens": 16904568.0,
|
|
"step": 9180
|
|
},
|
|
{
|
|
"entropy": 5.292680788040161,
|
|
"epoch": 0.7672068159037755,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004947442141499771,
|
|
"loss": 5.1022,
|
|
"mean_token_accuracy": 0.19897875487804412,
|
|
"num_tokens": 16913667.0,
|
|
"step": 9185
|
|
},
|
|
{
|
|
"entropy": 5.326617431640625,
|
|
"epoch": 0.7676244570664885,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004947378153204899,
|
|
"loss": 5.0406,
|
|
"mean_token_accuracy": 0.2004725456237793,
|
|
"num_tokens": 16922897.0,
|
|
"step": 9190
|
|
},
|
|
{
|
|
"entropy": 5.349248886108398,
|
|
"epoch": 0.7680420982292014,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004947314126442279,
|
|
"loss": 5.0406,
|
|
"mean_token_accuracy": 0.20128468424081802,
|
|
"num_tokens": 16931559.0,
|
|
"step": 9195
|
|
},
|
|
{
|
|
"entropy": 5.26908860206604,
|
|
"epoch": 0.7684597393919145,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000494725006121303,
|
|
"loss": 5.0244,
|
|
"mean_token_accuracy": 0.20029380321502685,
|
|
"num_tokens": 16940191.0,
|
|
"step": 9200
|
|
},
|
|
{
|
|
"entropy": 5.308033800125122,
|
|
"epoch": 0.7688773805546275,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004947185957518273,
|
|
"loss": 5.0948,
|
|
"mean_token_accuracy": 0.19918156713247298,
|
|
"num_tokens": 16948971.0,
|
|
"step": 9205
|
|
},
|
|
{
|
|
"entropy": 5.313927936553955,
|
|
"epoch": 0.7692950217173404,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004947121815359133,
|
|
"loss": 5.0277,
|
|
"mean_token_accuracy": 0.206220580637455,
|
|
"num_tokens": 16957944.0,
|
|
"step": 9210
|
|
},
|
|
{
|
|
"entropy": 5.229868936538696,
|
|
"epoch": 0.7697126628800535,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004947057634736729,
|
|
"loss": 4.9983,
|
|
"mean_token_accuracy": 0.20346777737140656,
|
|
"num_tokens": 16967418.0,
|
|
"step": 9215
|
|
},
|
|
{
|
|
"entropy": 5.260604810714722,
|
|
"epoch": 0.7701303040427665,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004946993415652186,
|
|
"loss": 4.9869,
|
|
"mean_token_accuracy": 0.20868378430604934,
|
|
"num_tokens": 16977233.0,
|
|
"step": 9220
|
|
},
|
|
{
|
|
"entropy": 5.261973714828491,
|
|
"epoch": 0.7705479452054794,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000494692915810663,
|
|
"loss": 5.0621,
|
|
"mean_token_accuracy": 0.20642494261264802,
|
|
"num_tokens": 16986023.0,
|
|
"step": 9225
|
|
},
|
|
{
|
|
"entropy": 5.281343030929565,
|
|
"epoch": 0.7709655863681925,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004946864862101185,
|
|
"loss": 4.9798,
|
|
"mean_token_accuracy": 0.20381157398223876,
|
|
"num_tokens": 16994987.0,
|
|
"step": 9230
|
|
},
|
|
{
|
|
"entropy": 5.260571432113648,
|
|
"epoch": 0.7713832275309055,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004946800527636975,
|
|
"loss": 5.0105,
|
|
"mean_token_accuracy": 0.19908543974161147,
|
|
"num_tokens": 17003902.0,
|
|
"step": 9235
|
|
},
|
|
{
|
|
"entropy": 5.285253715515137,
|
|
"epoch": 0.7718008686936184,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004946736154715129,
|
|
"loss": 5.1003,
|
|
"mean_token_accuracy": 0.19527377486228942,
|
|
"num_tokens": 17013258.0,
|
|
"step": 9240
|
|
},
|
|
{
|
|
"entropy": 5.367343902587891,
|
|
"epoch": 0.7722185098563314,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004946671743336771,
|
|
"loss": 5.0965,
|
|
"mean_token_accuracy": 0.20139744728803635,
|
|
"num_tokens": 17022258.0,
|
|
"step": 9245
|
|
},
|
|
{
|
|
"entropy": 5.3241571426391605,
|
|
"epoch": 0.7726361510190445,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004946607293503031,
|
|
"loss": 5.019,
|
|
"mean_token_accuracy": 0.2053925946354866,
|
|
"num_tokens": 17031485.0,
|
|
"step": 9250
|
|
},
|
|
{
|
|
"entropy": 5.171794891357422,
|
|
"epoch": 0.7730537921817574,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004946542805215036,
|
|
"loss": 4.9819,
|
|
"mean_token_accuracy": 0.20774541199207305,
|
|
"num_tokens": 17039916.0,
|
|
"step": 9255
|
|
},
|
|
{
|
|
"entropy": 5.177844619750976,
|
|
"epoch": 0.7734714333444704,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004946478278473914,
|
|
"loss": 5.0161,
|
|
"mean_token_accuracy": 0.2033155858516693,
|
|
"num_tokens": 17048153.0,
|
|
"step": 9260
|
|
},
|
|
{
|
|
"entropy": 5.262477922439575,
|
|
"epoch": 0.7738890745071835,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004946413713280797,
|
|
"loss": 5.0453,
|
|
"mean_token_accuracy": 0.20080723911523818,
|
|
"num_tokens": 17057473.0,
|
|
"step": 9265
|
|
},
|
|
{
|
|
"entropy": 5.338902425765991,
|
|
"epoch": 0.7743067156698964,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004946349109636814,
|
|
"loss": 5.0365,
|
|
"mean_token_accuracy": 0.2072010949254036,
|
|
"num_tokens": 17066431.0,
|
|
"step": 9270
|
|
},
|
|
{
|
|
"entropy": 5.333625078201294,
|
|
"epoch": 0.7747243568326094,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004946284467543096,
|
|
"loss": 5.136,
|
|
"mean_token_accuracy": 0.1943159893155098,
|
|
"num_tokens": 17076519.0,
|
|
"step": 9275
|
|
},
|
|
{
|
|
"entropy": 5.3112376689910885,
|
|
"epoch": 0.7751419979953225,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004946219787000776,
|
|
"loss": 5.0759,
|
|
"mean_token_accuracy": 0.20009991973638536,
|
|
"num_tokens": 17084651.0,
|
|
"step": 9280
|
|
},
|
|
{
|
|
"entropy": 5.333436107635498,
|
|
"epoch": 0.7755596391580354,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004946155068010984,
|
|
"loss": 5.1035,
|
|
"mean_token_accuracy": 0.19852675050497054,
|
|
"num_tokens": 17094943.0,
|
|
"step": 9285
|
|
},
|
|
{
|
|
"entropy": 5.28173794746399,
|
|
"epoch": 0.7759772803207484,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004946090310574854,
|
|
"loss": 4.9809,
|
|
"mean_token_accuracy": 0.20821188241243363,
|
|
"num_tokens": 17103548.0,
|
|
"step": 9290
|
|
},
|
|
{
|
|
"entropy": 5.295103359222412,
|
|
"epoch": 0.7763949214834615,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004946025514693519,
|
|
"loss": 4.9481,
|
|
"mean_token_accuracy": 0.20553445667028428,
|
|
"num_tokens": 17112472.0,
|
|
"step": 9295
|
|
},
|
|
{
|
|
"entropy": 5.4018957138061525,
|
|
"epoch": 0.7768125626461744,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004945960680368115,
|
|
"loss": 5.0829,
|
|
"mean_token_accuracy": 0.19831764400005342,
|
|
"num_tokens": 17121536.0,
|
|
"step": 9300
|
|
},
|
|
{
|
|
"entropy": 5.416180658340454,
|
|
"epoch": 0.7772302038088874,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004945895807599775,
|
|
"loss": 5.1467,
|
|
"mean_token_accuracy": 0.19245276004076003,
|
|
"num_tokens": 17130708.0,
|
|
"step": 9305
|
|
},
|
|
{
|
|
"entropy": 5.215561962127685,
|
|
"epoch": 0.7776478449716004,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004945830896389636,
|
|
"loss": 4.9334,
|
|
"mean_token_accuracy": 0.2095179870724678,
|
|
"num_tokens": 17139437.0,
|
|
"step": 9310
|
|
},
|
|
{
|
|
"entropy": 5.276777553558349,
|
|
"epoch": 0.7780654861343134,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004945765946738835,
|
|
"loss": 5.083,
|
|
"mean_token_accuracy": 0.1986304357647896,
|
|
"num_tokens": 17149107.0,
|
|
"step": 9315
|
|
},
|
|
{
|
|
"entropy": 5.3130237579345705,
|
|
"epoch": 0.7784831272970264,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004945700958648507,
|
|
"loss": 5.0785,
|
|
"mean_token_accuracy": 0.19797585159540176,
|
|
"num_tokens": 17158866.0,
|
|
"step": 9320
|
|
},
|
|
{
|
|
"entropy": 5.261892318725586,
|
|
"epoch": 0.7789007684597394,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000494563593211979,
|
|
"loss": 4.9753,
|
|
"mean_token_accuracy": 0.2056022822856903,
|
|
"num_tokens": 17167909.0,
|
|
"step": 9325
|
|
},
|
|
{
|
|
"entropy": 5.2609766006469725,
|
|
"epoch": 0.7793184096224524,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004945570867153826,
|
|
"loss": 5.0885,
|
|
"mean_token_accuracy": 0.19690562188625335,
|
|
"num_tokens": 17176746.0,
|
|
"step": 9330
|
|
},
|
|
{
|
|
"entropy": 5.304251098632813,
|
|
"epoch": 0.7797360507851654,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004945505763751749,
|
|
"loss": 5.0917,
|
|
"mean_token_accuracy": 0.19543183445930482,
|
|
"num_tokens": 17186219.0,
|
|
"step": 9335
|
|
},
|
|
{
|
|
"entropy": 5.298954486846924,
|
|
"epoch": 0.7801536919478784,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004945440621914702,
|
|
"loss": 4.9259,
|
|
"mean_token_accuracy": 0.21116489320993423,
|
|
"num_tokens": 17195811.0,
|
|
"step": 9340
|
|
},
|
|
{
|
|
"entropy": 5.1953223705291744,
|
|
"epoch": 0.7805713331105913,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004945375441643823,
|
|
"loss": 5.0755,
|
|
"mean_token_accuracy": 0.2034341961145401,
|
|
"num_tokens": 17205333.0,
|
|
"step": 9345
|
|
},
|
|
{
|
|
"entropy": 5.299469518661499,
|
|
"epoch": 0.7809889742733044,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004945310222940254,
|
|
"loss": 5.0366,
|
|
"mean_token_accuracy": 0.19907909333705903,
|
|
"num_tokens": 17214493.0,
|
|
"step": 9350
|
|
},
|
|
{
|
|
"entropy": 5.365374946594239,
|
|
"epoch": 0.7814066154360174,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004945244965805138,
|
|
"loss": 5.0419,
|
|
"mean_token_accuracy": 0.20529650002717972,
|
|
"num_tokens": 17223602.0,
|
|
"step": 9355
|
|
},
|
|
{
|
|
"entropy": 5.335985469818115,
|
|
"epoch": 0.7818242565987303,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004945179670239616,
|
|
"loss": 5.0758,
|
|
"mean_token_accuracy": 0.19936992079019547,
|
|
"num_tokens": 17232915.0,
|
|
"step": 9360
|
|
},
|
|
{
|
|
"entropy": 5.320971441268921,
|
|
"epoch": 0.7822418977614434,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004945114336244832,
|
|
"loss": 5.0456,
|
|
"mean_token_accuracy": 0.1973716601729393,
|
|
"num_tokens": 17242489.0,
|
|
"step": 9365
|
|
},
|
|
{
|
|
"entropy": 5.188671016693116,
|
|
"epoch": 0.7826595389241564,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000494504896382193,
|
|
"loss": 4.8118,
|
|
"mean_token_accuracy": 0.2163364425301552,
|
|
"num_tokens": 17251496.0,
|
|
"step": 9370
|
|
},
|
|
{
|
|
"entropy": 5.214679002761841,
|
|
"epoch": 0.7830771800868693,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004944983552972053,
|
|
"loss": 4.9942,
|
|
"mean_token_accuracy": 0.20377425700426102,
|
|
"num_tokens": 17260550.0,
|
|
"step": 9375
|
|
},
|
|
{
|
|
"entropy": 5.271979284286499,
|
|
"epoch": 0.7834948212495824,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004944918103696347,
|
|
"loss": 4.9728,
|
|
"mean_token_accuracy": 0.20010923892259597,
|
|
"num_tokens": 17269085.0,
|
|
"step": 9380
|
|
},
|
|
{
|
|
"entropy": 5.366032314300537,
|
|
"epoch": 0.7839124624122954,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004944852615995956,
|
|
"loss": 5.198,
|
|
"mean_token_accuracy": 0.20187092423439026,
|
|
"num_tokens": 17278766.0,
|
|
"step": 9385
|
|
},
|
|
{
|
|
"entropy": 5.406021165847778,
|
|
"epoch": 0.7843301035750083,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000494478708987203,
|
|
"loss": 5.06,
|
|
"mean_token_accuracy": 0.19868176728487014,
|
|
"num_tokens": 17288316.0,
|
|
"step": 9390
|
|
},
|
|
{
|
|
"entropy": 5.229649305343628,
|
|
"epoch": 0.7847477447377214,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004944721525325713,
|
|
"loss": 4.9167,
|
|
"mean_token_accuracy": 0.20666508078575135,
|
|
"num_tokens": 17297829.0,
|
|
"step": 9395
|
|
},
|
|
{
|
|
"entropy": 5.273958492279053,
|
|
"epoch": 0.7851653859004344,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004944655922358154,
|
|
"loss": 5.0016,
|
|
"mean_token_accuracy": 0.2018284633755684,
|
|
"num_tokens": 17306631.0,
|
|
"step": 9400
|
|
},
|
|
{
|
|
"entropy": 5.26501317024231,
|
|
"epoch": 0.7855830270631473,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004944590280970503,
|
|
"loss": 5.0067,
|
|
"mean_token_accuracy": 0.20416941344738007,
|
|
"num_tokens": 17316829.0,
|
|
"step": 9405
|
|
},
|
|
{
|
|
"entropy": 5.283139324188232,
|
|
"epoch": 0.7860006682258603,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004944524601163905,
|
|
"loss": 5.0208,
|
|
"mean_token_accuracy": 0.2009298622608185,
|
|
"num_tokens": 17326568.0,
|
|
"step": 9410
|
|
},
|
|
{
|
|
"entropy": 5.306204080581665,
|
|
"epoch": 0.7864183093885734,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004944458882939513,
|
|
"loss": 5.0835,
|
|
"mean_token_accuracy": 0.20056407451629638,
|
|
"num_tokens": 17335524.0,
|
|
"step": 9415
|
|
},
|
|
{
|
|
"entropy": 5.39315767288208,
|
|
"epoch": 0.7868359505512863,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004944393126298478,
|
|
"loss": 5.1221,
|
|
"mean_token_accuracy": 0.19416031390428543,
|
|
"num_tokens": 17346198.0,
|
|
"step": 9420
|
|
},
|
|
{
|
|
"entropy": 5.251412725448608,
|
|
"epoch": 0.7872535917139993,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000494432733124195,
|
|
"loss": 4.9666,
|
|
"mean_token_accuracy": 0.21045693457126619,
|
|
"num_tokens": 17354696.0,
|
|
"step": 9425
|
|
},
|
|
{
|
|
"entropy": 5.196813678741455,
|
|
"epoch": 0.7876712328767124,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.000494426149777108,
|
|
"loss": 4.944,
|
|
"mean_token_accuracy": 0.20504340827465056,
|
|
"num_tokens": 17363314.0,
|
|
"step": 9430
|
|
},
|
|
{
|
|
"entropy": 5.226676893234253,
|
|
"epoch": 0.7880888740394253,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.000494419562588702,
|
|
"loss": 4.9947,
|
|
"mean_token_accuracy": 0.21016329824924468,
|
|
"num_tokens": 17372662.0,
|
|
"step": 9435
|
|
},
|
|
{
|
|
"entropy": 5.234115219116211,
|
|
"epoch": 0.7885065152021383,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004944129715590927,
|
|
"loss": 4.9701,
|
|
"mean_token_accuracy": 0.20339612364768983,
|
|
"num_tokens": 17381931.0,
|
|
"step": 9440
|
|
},
|
|
{
|
|
"entropy": 5.330491971969605,
|
|
"epoch": 0.7889241563648514,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000494406376688395,
|
|
"loss": 5.0671,
|
|
"mean_token_accuracy": 0.19536355137825012,
|
|
"num_tokens": 17391210.0,
|
|
"step": 9445
|
|
},
|
|
{
|
|
"entropy": 5.225590372085572,
|
|
"epoch": 0.7893417975275643,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004943997779767248,
|
|
"loss": 4.9328,
|
|
"mean_token_accuracy": 0.2165209487080574,
|
|
"num_tokens": 17401102.0,
|
|
"step": 9450
|
|
},
|
|
{
|
|
"entropy": 5.222544002532959,
|
|
"epoch": 0.7897594386902773,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004943931754241972,
|
|
"loss": 4.9798,
|
|
"mean_token_accuracy": 0.20373812019824983,
|
|
"num_tokens": 17410036.0,
|
|
"step": 9455
|
|
},
|
|
{
|
|
"entropy": 5.255673933029175,
|
|
"epoch": 0.7901770798529903,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.000494386569030928,
|
|
"loss": 5.0323,
|
|
"mean_token_accuracy": 0.19926638454198836,
|
|
"num_tokens": 17419348.0,
|
|
"step": 9460
|
|
},
|
|
{
|
|
"entropy": 5.296061849594116,
|
|
"epoch": 0.7905947210157033,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004943799587970328,
|
|
"loss": 5.0361,
|
|
"mean_token_accuracy": 0.20071749538183212,
|
|
"num_tokens": 17427937.0,
|
|
"step": 9465
|
|
},
|
|
{
|
|
"entropy": 5.224281358718872,
|
|
"epoch": 0.7910123621784163,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004943733447226275,
|
|
"loss": 4.9016,
|
|
"mean_token_accuracy": 0.21215202659368515,
|
|
"num_tokens": 17436259.0,
|
|
"step": 9470
|
|
},
|
|
{
|
|
"entropy": 5.342166805267334,
|
|
"epoch": 0.7914300033411293,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004943667268078277,
|
|
"loss": 5.084,
|
|
"mean_token_accuracy": 0.20154720097780227,
|
|
"num_tokens": 17445202.0,
|
|
"step": 9475
|
|
},
|
|
{
|
|
"entropy": 5.254055738449097,
|
|
"epoch": 0.7918476445038423,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004943601050527493,
|
|
"loss": 4.988,
|
|
"mean_token_accuracy": 0.20560846477746964,
|
|
"num_tokens": 17453928.0,
|
|
"step": 9480
|
|
},
|
|
{
|
|
"entropy": 5.271201419830322,
|
|
"epoch": 0.7922652856665553,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004943534794575081,
|
|
"loss": 5.0149,
|
|
"mean_token_accuracy": 0.2042636454105377,
|
|
"num_tokens": 17462609.0,
|
|
"step": 9485
|
|
},
|
|
{
|
|
"entropy": 5.307225608825684,
|
|
"epoch": 0.7926829268292683,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004943468500222203,
|
|
"loss": 5.03,
|
|
"mean_token_accuracy": 0.20491330027580262,
|
|
"num_tokens": 17471326.0,
|
|
"step": 9490
|
|
},
|
|
{
|
|
"entropy": 5.229542350769043,
|
|
"epoch": 0.7931005679919813,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004943402167470019,
|
|
"loss": 4.9964,
|
|
"mean_token_accuracy": 0.2107575312256813,
|
|
"num_tokens": 17480296.0,
|
|
"step": 9495
|
|
},
|
|
{
|
|
"entropy": 5.2251122951507565,
|
|
"epoch": 0.7935182091546943,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000494333579631969,
|
|
"loss": 4.9284,
|
|
"mean_token_accuracy": 0.2042476013302803,
|
|
"num_tokens": 17489779.0,
|
|
"step": 9500
|
|
},
|
|
{
|
|
"entropy": 5.2869805812835695,
|
|
"epoch": 0.7939358503174073,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004943269386772376,
|
|
"loss": 5.0489,
|
|
"mean_token_accuracy": 0.20046651661396026,
|
|
"num_tokens": 17499796.0,
|
|
"step": 9505
|
|
},
|
|
{
|
|
"entropy": 5.335369062423706,
|
|
"epoch": 0.7943534914801202,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004943202938829243,
|
|
"loss": 5.1443,
|
|
"mean_token_accuracy": 0.19563747197389603,
|
|
"num_tokens": 17509223.0,
|
|
"step": 9510
|
|
},
|
|
{
|
|
"entropy": 5.296935319900513,
|
|
"epoch": 0.7947711326428333,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004943136452491452,
|
|
"loss": 5.0388,
|
|
"mean_token_accuracy": 0.20008025765419007,
|
|
"num_tokens": 17518712.0,
|
|
"step": 9515
|
|
},
|
|
{
|
|
"entropy": 5.238116598129272,
|
|
"epoch": 0.7951887738055463,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004943069927760168,
|
|
"loss": 4.9883,
|
|
"mean_token_accuracy": 0.20782812386751176,
|
|
"num_tokens": 17528648.0,
|
|
"step": 9520
|
|
},
|
|
{
|
|
"entropy": 5.161343383789062,
|
|
"epoch": 0.7956064149682592,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004943003364636554,
|
|
"loss": 4.9847,
|
|
"mean_token_accuracy": 0.20069538652896882,
|
|
"num_tokens": 17537859.0,
|
|
"step": 9525
|
|
},
|
|
{
|
|
"entropy": 5.316619110107422,
|
|
"epoch": 0.7960240561309723,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004942936763121777,
|
|
"loss": 5.1395,
|
|
"mean_token_accuracy": 0.19529732316732407,
|
|
"num_tokens": 17546438.0,
|
|
"step": 9530
|
|
},
|
|
{
|
|
"entropy": 5.2499274730682375,
|
|
"epoch": 0.7964416972936853,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004942870123217002,
|
|
"loss": 4.9569,
|
|
"mean_token_accuracy": 0.21053215265274047,
|
|
"num_tokens": 17554537.0,
|
|
"step": 9535
|
|
},
|
|
{
|
|
"entropy": 5.385514211654663,
|
|
"epoch": 0.7968593384563982,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004942803444923398,
|
|
"loss": 5.1864,
|
|
"mean_token_accuracy": 0.19254078716039658,
|
|
"num_tokens": 17564239.0,
|
|
"step": 9540
|
|
},
|
|
{
|
|
"entropy": 5.268808794021607,
|
|
"epoch": 0.7972769796191113,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004942736728242127,
|
|
"loss": 5.0497,
|
|
"mean_token_accuracy": 0.20318469703197478,
|
|
"num_tokens": 17574437.0,
|
|
"step": 9545
|
|
},
|
|
{
|
|
"entropy": 5.250163650512695,
|
|
"epoch": 0.7976946207818243,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004942669973174363,
|
|
"loss": 4.9888,
|
|
"mean_token_accuracy": 0.20635224431753157,
|
|
"num_tokens": 17583173.0,
|
|
"step": 9550
|
|
},
|
|
{
|
|
"entropy": 5.293168735504151,
|
|
"epoch": 0.7981122619445372,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000494260317972127,
|
|
"loss": 5.0292,
|
|
"mean_token_accuracy": 0.1972663074731827,
|
|
"num_tokens": 17591731.0,
|
|
"step": 9555
|
|
},
|
|
{
|
|
"entropy": 5.30541467666626,
|
|
"epoch": 0.7985299031072502,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004942536347884019,
|
|
"loss": 5.0649,
|
|
"mean_token_accuracy": 0.20194061398506163,
|
|
"num_tokens": 17600778.0,
|
|
"step": 9560
|
|
},
|
|
{
|
|
"entropy": 5.220264863967896,
|
|
"epoch": 0.7989475442699633,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004942469477663782,
|
|
"loss": 5.0326,
|
|
"mean_token_accuracy": 0.21178349554538728,
|
|
"num_tokens": 17609470.0,
|
|
"step": 9565
|
|
},
|
|
{
|
|
"entropy": 5.22754225730896,
|
|
"epoch": 0.7993651854326762,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004942402569061726,
|
|
"loss": 4.9282,
|
|
"mean_token_accuracy": 0.20935079008340834,
|
|
"num_tokens": 17618434.0,
|
|
"step": 9570
|
|
},
|
|
{
|
|
"entropy": 5.216368770599365,
|
|
"epoch": 0.7997828265953892,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004942335622079025,
|
|
"loss": 5.0486,
|
|
"mean_token_accuracy": 0.19940815418958663,
|
|
"num_tokens": 17628170.0,
|
|
"step": 9575
|
|
},
|
|
{
|
|
"entropy": 5.2389692783355715,
|
|
"epoch": 0.8002004677581023,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004942268636716848,
|
|
"loss": 4.9611,
|
|
"mean_token_accuracy": 0.20548074841499328,
|
|
"num_tokens": 17637391.0,
|
|
"step": 9580
|
|
},
|
|
{
|
|
"entropy": 5.275997018814087,
|
|
"epoch": 0.8006181089208152,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004942201612976372,
|
|
"loss": 5.0586,
|
|
"mean_token_accuracy": 0.20423658937215805,
|
|
"num_tokens": 17647466.0,
|
|
"step": 9585
|
|
},
|
|
{
|
|
"entropy": 5.277049112319946,
|
|
"epoch": 0.8010357500835282,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004942134550858767,
|
|
"loss": 4.9855,
|
|
"mean_token_accuracy": 0.209126316010952,
|
|
"num_tokens": 17656155.0,
|
|
"step": 9590
|
|
},
|
|
{
|
|
"entropy": 5.385107898712159,
|
|
"epoch": 0.8014533912462413,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004942067450365208,
|
|
"loss": 5.0747,
|
|
"mean_token_accuracy": 0.20015188902616501,
|
|
"num_tokens": 17665242.0,
|
|
"step": 9595
|
|
},
|
|
{
|
|
"entropy": 5.283998966217041,
|
|
"epoch": 0.8018710324089542,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004942000311496871,
|
|
"loss": 5.0958,
|
|
"mean_token_accuracy": 0.20111240893602372,
|
|
"num_tokens": 17674964.0,
|
|
"step": 9600
|
|
},
|
|
{
|
|
"entropy": 5.351830673217774,
|
|
"epoch": 0.8022886735716672,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004941933134254928,
|
|
"loss": 5.0927,
|
|
"mean_token_accuracy": 0.2037873536348343,
|
|
"num_tokens": 17683275.0,
|
|
"step": 9605
|
|
},
|
|
{
|
|
"entropy": 5.297152185440064,
|
|
"epoch": 0.8027063147343803,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004941865918640559,
|
|
"loss": 5.048,
|
|
"mean_token_accuracy": 0.20206041336059571,
|
|
"num_tokens": 17691841.0,
|
|
"step": 9610
|
|
},
|
|
{
|
|
"entropy": 5.292528247833252,
|
|
"epoch": 0.8031239558970932,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004941798664654937,
|
|
"loss": 4.9972,
|
|
"mean_token_accuracy": 0.2060507968068123,
|
|
"num_tokens": 17701258.0,
|
|
"step": 9615
|
|
},
|
|
{
|
|
"entropy": 5.2792106628417965,
|
|
"epoch": 0.8035415970598062,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004941731372299241,
|
|
"loss": 5.082,
|
|
"mean_token_accuracy": 0.19895916879177095,
|
|
"num_tokens": 17711028.0,
|
|
"step": 9620
|
|
},
|
|
{
|
|
"entropy": 5.31102819442749,
|
|
"epoch": 0.8039592382225192,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004941664041574651,
|
|
"loss": 5.0215,
|
|
"mean_token_accuracy": 0.21228455603122712,
|
|
"num_tokens": 17720175.0,
|
|
"step": 9625
|
|
},
|
|
{
|
|
"entropy": 5.288550138473511,
|
|
"epoch": 0.8043768793852322,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004941596672482343,
|
|
"loss": 4.9978,
|
|
"mean_token_accuracy": 0.20317634344100952,
|
|
"num_tokens": 17730420.0,
|
|
"step": 9630
|
|
},
|
|
{
|
|
"entropy": 5.2999168872833256,
|
|
"epoch": 0.8047945205479452,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004941529265023498,
|
|
"loss": 5.0976,
|
|
"mean_token_accuracy": 0.19421206712722777,
|
|
"num_tokens": 17739802.0,
|
|
"step": 9635
|
|
},
|
|
{
|
|
"entropy": 5.3412566661834715,
|
|
"epoch": 0.8052121617106582,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004941461819199293,
|
|
"loss": 4.9901,
|
|
"mean_token_accuracy": 0.2086260050535202,
|
|
"num_tokens": 17749450.0,
|
|
"step": 9640
|
|
},
|
|
{
|
|
"entropy": 5.405754327774048,
|
|
"epoch": 0.8056298028733712,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004941394335010912,
|
|
"loss": 5.1788,
|
|
"mean_token_accuracy": 0.19541946202516555,
|
|
"num_tokens": 17758733.0,
|
|
"step": 9645
|
|
},
|
|
{
|
|
"entropy": 5.2307861328125,
|
|
"epoch": 0.8060474440360842,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004941326812459535,
|
|
"loss": 5.1042,
|
|
"mean_token_accuracy": 0.1989505708217621,
|
|
"num_tokens": 17769037.0,
|
|
"step": 9650
|
|
},
|
|
{
|
|
"entropy": 5.287183332443237,
|
|
"epoch": 0.8064650851987972,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004941259251546346,
|
|
"loss": 5.0461,
|
|
"mean_token_accuracy": 0.19478376358747482,
|
|
"num_tokens": 17777603.0,
|
|
"step": 9655
|
|
},
|
|
{
|
|
"entropy": 5.292373275756836,
|
|
"epoch": 0.8068827263615101,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004941191652272526,
|
|
"loss": 5.014,
|
|
"mean_token_accuracy": 0.1983320191502571,
|
|
"num_tokens": 17787513.0,
|
|
"step": 9660
|
|
},
|
|
{
|
|
"entropy": 5.241600799560547,
|
|
"epoch": 0.8073003675242232,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004941124014639258,
|
|
"loss": 5.019,
|
|
"mean_token_accuracy": 0.20129087418317795,
|
|
"num_tokens": 17796720.0,
|
|
"step": 9665
|
|
},
|
|
{
|
|
"entropy": 5.264516973495484,
|
|
"epoch": 0.8077180086869362,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004941056338647726,
|
|
"loss": 4.9849,
|
|
"mean_token_accuracy": 0.2036397188901901,
|
|
"num_tokens": 17806024.0,
|
|
"step": 9670
|
|
},
|
|
{
|
|
"entropy": 5.221023321151733,
|
|
"epoch": 0.8081356498496491,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004940988624299116,
|
|
"loss": 4.976,
|
|
"mean_token_accuracy": 0.2046495258808136,
|
|
"num_tokens": 17815247.0,
|
|
"step": 9675
|
|
},
|
|
{
|
|
"entropy": 5.323753118515015,
|
|
"epoch": 0.8085532910123622,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004940920871594613,
|
|
"loss": 5.0366,
|
|
"mean_token_accuracy": 0.20503654927015305,
|
|
"num_tokens": 17824024.0,
|
|
"step": 9680
|
|
},
|
|
{
|
|
"entropy": 5.247210264205933,
|
|
"epoch": 0.8089709321750752,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004940853080535403,
|
|
"loss": 5.0058,
|
|
"mean_token_accuracy": 0.20110260248184203,
|
|
"num_tokens": 17832782.0,
|
|
"step": 9685
|
|
},
|
|
{
|
|
"entropy": 5.293553590774536,
|
|
"epoch": 0.8093885733377881,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004940785251122673,
|
|
"loss": 4.976,
|
|
"mean_token_accuracy": 0.21062718480825424,
|
|
"num_tokens": 17841961.0,
|
|
"step": 9690
|
|
},
|
|
{
|
|
"entropy": 5.254729890823365,
|
|
"epoch": 0.8098062145005012,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004940717383357608,
|
|
"loss": 5.0608,
|
|
"mean_token_accuracy": 0.21443141251802444,
|
|
"num_tokens": 17851364.0,
|
|
"step": 9695
|
|
},
|
|
{
|
|
"entropy": 5.387207984924316,
|
|
"epoch": 0.8102238556632142,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004940649477241401,
|
|
"loss": 5.1303,
|
|
"mean_token_accuracy": 0.19218126833438873,
|
|
"num_tokens": 17860871.0,
|
|
"step": 9700
|
|
},
|
|
{
|
|
"entropy": 5.290140295028687,
|
|
"epoch": 0.8106414968259271,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004940581532775237,
|
|
"loss": 5.0574,
|
|
"mean_token_accuracy": 0.20372044295072556,
|
|
"num_tokens": 17869687.0,
|
|
"step": 9705
|
|
},
|
|
{
|
|
"entropy": 5.257996511459351,
|
|
"epoch": 0.8110591379886402,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004940513549960306,
|
|
"loss": 4.9968,
|
|
"mean_token_accuracy": 0.2021973043680191,
|
|
"num_tokens": 17878815.0,
|
|
"step": 9710
|
|
},
|
|
{
|
|
"entropy": 5.264734983444214,
|
|
"epoch": 0.8114767791513532,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004940445528797798,
|
|
"loss": 4.9303,
|
|
"mean_token_accuracy": 0.20963813066482545,
|
|
"num_tokens": 17888302.0,
|
|
"step": 9715
|
|
},
|
|
{
|
|
"entropy": 5.187796926498413,
|
|
"epoch": 0.8118944203140661,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004940377469288906,
|
|
"loss": 4.8931,
|
|
"mean_token_accuracy": 0.21290806233882903,
|
|
"num_tokens": 17896807.0,
|
|
"step": 9720
|
|
},
|
|
{
|
|
"entropy": 5.287715768814087,
|
|
"epoch": 0.8123120614767791,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004940309371434819,
|
|
"loss": 4.9735,
|
|
"mean_token_accuracy": 0.20826876759529114,
|
|
"num_tokens": 17905988.0,
|
|
"step": 9725
|
|
},
|
|
{
|
|
"entropy": 5.351922559738159,
|
|
"epoch": 0.8127297026394922,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004940241235236731,
|
|
"loss": 5.1055,
|
|
"mean_token_accuracy": 0.1958531156182289,
|
|
"num_tokens": 17915917.0,
|
|
"step": 9730
|
|
},
|
|
{
|
|
"entropy": 5.323018980026245,
|
|
"epoch": 0.8131473438022051,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004940173060695833,
|
|
"loss": 5.0811,
|
|
"mean_token_accuracy": 0.20148218870162965,
|
|
"num_tokens": 17926158.0,
|
|
"step": 9735
|
|
},
|
|
{
|
|
"entropy": 5.257668209075928,
|
|
"epoch": 0.8135649849649181,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004940104847813319,
|
|
"loss": 5.0421,
|
|
"mean_token_accuracy": 0.20052656084299086,
|
|
"num_tokens": 17935488.0,
|
|
"step": 9740
|
|
},
|
|
{
|
|
"entropy": 5.275480699539185,
|
|
"epoch": 0.8139826261276312,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004940036596590384,
|
|
"loss": 4.9568,
|
|
"mean_token_accuracy": 0.20216303765773774,
|
|
"num_tokens": 17944850.0,
|
|
"step": 9745
|
|
},
|
|
{
|
|
"entropy": 5.238033199310303,
|
|
"epoch": 0.8144002672903441,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004939968307028221,
|
|
"loss": 5.0058,
|
|
"mean_token_accuracy": 0.20468695610761642,
|
|
"num_tokens": 17954796.0,
|
|
"step": 9750
|
|
},
|
|
{
|
|
"entropy": 5.234244441986084,
|
|
"epoch": 0.8148179084530571,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004939899979128028,
|
|
"loss": 4.9853,
|
|
"mean_token_accuracy": 0.2116552397608757,
|
|
"num_tokens": 17963875.0,
|
|
"step": 9755
|
|
},
|
|
{
|
|
"entropy": 5.266030788421631,
|
|
"epoch": 0.8152355496157702,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004939831612890999,
|
|
"loss": 5.0129,
|
|
"mean_token_accuracy": 0.2031642124056816,
|
|
"num_tokens": 17972789.0,
|
|
"step": 9760
|
|
},
|
|
{
|
|
"entropy": 5.276300764083862,
|
|
"epoch": 0.8156531907784831,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004939763208318332,
|
|
"loss": 5.0293,
|
|
"mean_token_accuracy": 0.20778004229068756,
|
|
"num_tokens": 17982355.0,
|
|
"step": 9765
|
|
},
|
|
{
|
|
"entropy": 5.331578111648559,
|
|
"epoch": 0.8160708319411961,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004939694765411225,
|
|
"loss": 5.0335,
|
|
"mean_token_accuracy": 0.20019334703683853,
|
|
"num_tokens": 17992046.0,
|
|
"step": 9770
|
|
},
|
|
{
|
|
"entropy": 5.260315847396851,
|
|
"epoch": 0.8164884731039092,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004939626284170874,
|
|
"loss": 4.965,
|
|
"mean_token_accuracy": 0.21675824522972106,
|
|
"num_tokens": 18001440.0,
|
|
"step": 9775
|
|
},
|
|
{
|
|
"entropy": 5.349969720840454,
|
|
"epoch": 0.8169061142666221,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000493955776459848,
|
|
"loss": 5.1015,
|
|
"mean_token_accuracy": 0.19849081188440323,
|
|
"num_tokens": 18010817.0,
|
|
"step": 9780
|
|
},
|
|
{
|
|
"entropy": 5.273048734664917,
|
|
"epoch": 0.8173237554293351,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004939489206695241,
|
|
"loss": 5.0359,
|
|
"mean_token_accuracy": 0.20319301784038543,
|
|
"num_tokens": 18019547.0,
|
|
"step": 9785
|
|
},
|
|
{
|
|
"entropy": 5.2291323184967045,
|
|
"epoch": 0.8177413965920481,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004939420610462359,
|
|
"loss": 5.0386,
|
|
"mean_token_accuracy": 0.20118792802095414,
|
|
"num_tokens": 18029191.0,
|
|
"step": 9790
|
|
},
|
|
{
|
|
"entropy": 5.320718145370483,
|
|
"epoch": 0.8181590377547611,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004939351975901034,
|
|
"loss": 5.0701,
|
|
"mean_token_accuracy": 0.20290120989084243,
|
|
"num_tokens": 18038831.0,
|
|
"step": 9795
|
|
},
|
|
{
|
|
"entropy": 5.286432790756225,
|
|
"epoch": 0.8185766789174741,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004939283303012467,
|
|
"loss": 4.9779,
|
|
"mean_token_accuracy": 0.20698291957378387,
|
|
"num_tokens": 18049243.0,
|
|
"step": 9800
|
|
},
|
|
{
|
|
"entropy": 5.194411182403565,
|
|
"epoch": 0.8189943200801871,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000493921459179786,
|
|
"loss": 4.9542,
|
|
"mean_token_accuracy": 0.20811349004507065,
|
|
"num_tokens": 18057960.0,
|
|
"step": 9805
|
|
},
|
|
{
|
|
"entropy": 5.277448987960815,
|
|
"epoch": 0.8194119612429,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004939145842258418,
|
|
"loss": 5.0815,
|
|
"mean_token_accuracy": 0.19748504161834718,
|
|
"num_tokens": 18066677.0,
|
|
"step": 9810
|
|
},
|
|
{
|
|
"entropy": 5.307441759109497,
|
|
"epoch": 0.8198296024056131,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004939077054395341,
|
|
"loss": 5.0349,
|
|
"mean_token_accuracy": 0.20028697997331618,
|
|
"num_tokens": 18075830.0,
|
|
"step": 9815
|
|
},
|
|
{
|
|
"entropy": 5.26435604095459,
|
|
"epoch": 0.8202472435683261,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004939008228209836,
|
|
"loss": 4.9383,
|
|
"mean_token_accuracy": 0.20332272052764894,
|
|
"num_tokens": 18085335.0,
|
|
"step": 9820
|
|
},
|
|
{
|
|
"entropy": 5.267291641235351,
|
|
"epoch": 0.820664884731039,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004938939363703106,
|
|
"loss": 5.0258,
|
|
"mean_token_accuracy": 0.19696779549121857,
|
|
"num_tokens": 18094531.0,
|
|
"step": 9825
|
|
},
|
|
{
|
|
"entropy": 5.260501098632813,
|
|
"epoch": 0.8210825258937521,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004938870460876359,
|
|
"loss": 4.973,
|
|
"mean_token_accuracy": 0.2061942219734192,
|
|
"num_tokens": 18103593.0,
|
|
"step": 9830
|
|
},
|
|
{
|
|
"entropy": 5.2618958950042725,
|
|
"epoch": 0.8215001670564651,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00049388015197308,
|
|
"loss": 5.0385,
|
|
"mean_token_accuracy": 0.20461765974760054,
|
|
"num_tokens": 18112826.0,
|
|
"step": 9835
|
|
},
|
|
{
|
|
"entropy": 5.297413921356201,
|
|
"epoch": 0.821917808219178,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004938732540267635,
|
|
"loss": 5.0901,
|
|
"mean_token_accuracy": 0.1960194230079651,
|
|
"num_tokens": 18121687.0,
|
|
"step": 9840
|
|
},
|
|
{
|
|
"entropy": 5.2823728084564205,
|
|
"epoch": 0.8223354493818911,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004938663522488072,
|
|
"loss": 4.9599,
|
|
"mean_token_accuracy": 0.2121197000145912,
|
|
"num_tokens": 18130071.0,
|
|
"step": 9845
|
|
},
|
|
{
|
|
"entropy": 5.328467130661011,
|
|
"epoch": 0.8227530905446041,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004938594466393321,
|
|
"loss": 5.1758,
|
|
"mean_token_accuracy": 0.19506560266017914,
|
|
"num_tokens": 18139077.0,
|
|
"step": 9850
|
|
},
|
|
{
|
|
"entropy": 5.326861095428467,
|
|
"epoch": 0.823170731707317,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004938525371984588,
|
|
"loss": 5.0565,
|
|
"mean_token_accuracy": 0.20626935511827468,
|
|
"num_tokens": 18147173.0,
|
|
"step": 9855
|
|
},
|
|
{
|
|
"entropy": 5.275492763519287,
|
|
"epoch": 0.8235883728700301,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004938456239263085,
|
|
"loss": 5.0254,
|
|
"mean_token_accuracy": 0.20502824932336808,
|
|
"num_tokens": 18157061.0,
|
|
"step": 9860
|
|
},
|
|
{
|
|
"entropy": 5.2826619148254395,
|
|
"epoch": 0.8240060140327431,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004938387068230021,
|
|
"loss": 4.9609,
|
|
"mean_token_accuracy": 0.2075473576784134,
|
|
"num_tokens": 18166115.0,
|
|
"step": 9865
|
|
},
|
|
{
|
|
"entropy": 5.22989239692688,
|
|
"epoch": 0.824423655195456,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004938317858886606,
|
|
"loss": 4.9787,
|
|
"mean_token_accuracy": 0.20749273002147675,
|
|
"num_tokens": 18174978.0,
|
|
"step": 9870
|
|
},
|
|
{
|
|
"entropy": 5.2950738906860355,
|
|
"epoch": 0.824841296358169,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004938248611234055,
|
|
"loss": 5.053,
|
|
"mean_token_accuracy": 0.2042671799659729,
|
|
"num_tokens": 18184948.0,
|
|
"step": 9875
|
|
},
|
|
{
|
|
"entropy": 5.315822172164917,
|
|
"epoch": 0.8252589375208821,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004938179325273577,
|
|
"loss": 4.9928,
|
|
"mean_token_accuracy": 0.20614935010671614,
|
|
"num_tokens": 18193443.0,
|
|
"step": 9880
|
|
},
|
|
{
|
|
"entropy": 5.318535184860229,
|
|
"epoch": 0.825676578683595,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004938110001006385,
|
|
"loss": 5.0064,
|
|
"mean_token_accuracy": 0.2060106500983238,
|
|
"num_tokens": 18202512.0,
|
|
"step": 9885
|
|
},
|
|
{
|
|
"entropy": 5.303167152404785,
|
|
"epoch": 0.826094219846308,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004938040638433694,
|
|
"loss": 5.0177,
|
|
"mean_token_accuracy": 0.20338963270187377,
|
|
"num_tokens": 18212328.0,
|
|
"step": 9890
|
|
},
|
|
{
|
|
"entropy": 5.2908491611480715,
|
|
"epoch": 0.8265118610090211,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004937971237556719,
|
|
"loss": 4.9715,
|
|
"mean_token_accuracy": 0.20638042390346528,
|
|
"num_tokens": 18221155.0,
|
|
"step": 9895
|
|
},
|
|
{
|
|
"entropy": 5.284775590896606,
|
|
"epoch": 0.826929502171734,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004937901798376672,
|
|
"loss": 5.0267,
|
|
"mean_token_accuracy": 0.2043670192360878,
|
|
"num_tokens": 18230604.0,
|
|
"step": 9900
|
|
},
|
|
{
|
|
"entropy": 5.276266813278198,
|
|
"epoch": 0.827347143334447,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004937832320894772,
|
|
"loss": 4.9611,
|
|
"mean_token_accuracy": 0.20734262466430664,
|
|
"num_tokens": 18239126.0,
|
|
"step": 9905
|
|
},
|
|
{
|
|
"entropy": 5.265355157852173,
|
|
"epoch": 0.8277647844971601,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004937762805112233,
|
|
"loss": 5.0022,
|
|
"mean_token_accuracy": 0.19618372470140458,
|
|
"num_tokens": 18248634.0,
|
|
"step": 9910
|
|
},
|
|
{
|
|
"entropy": 5.276412057876587,
|
|
"epoch": 0.828182425659873,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004937693251030273,
|
|
"loss": 5.135,
|
|
"mean_token_accuracy": 0.19961361587047577,
|
|
"num_tokens": 18258500.0,
|
|
"step": 9915
|
|
},
|
|
{
|
|
"entropy": 5.319969749450683,
|
|
"epoch": 0.828600066822586,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000493762365865011,
|
|
"loss": 4.9467,
|
|
"mean_token_accuracy": 0.20834760516881942,
|
|
"num_tokens": 18268374.0,
|
|
"step": 9920
|
|
},
|
|
{
|
|
"entropy": 5.279907274246216,
|
|
"epoch": 0.8290177079852991,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004937554027972961,
|
|
"loss": 5.0808,
|
|
"mean_token_accuracy": 0.20224204808473586,
|
|
"num_tokens": 18277667.0,
|
|
"step": 9925
|
|
},
|
|
{
|
|
"entropy": 5.313109397888184,
|
|
"epoch": 0.829435349148012,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004937484359000046,
|
|
"loss": 5.0856,
|
|
"mean_token_accuracy": 0.19987320601940156,
|
|
"num_tokens": 18287516.0,
|
|
"step": 9930
|
|
},
|
|
{
|
|
"entropy": 5.250987148284912,
|
|
"epoch": 0.829852990310725,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004937414651732584,
|
|
"loss": 4.931,
|
|
"mean_token_accuracy": 0.20905919522047042,
|
|
"num_tokens": 18296534.0,
|
|
"step": 9935
|
|
},
|
|
{
|
|
"entropy": 5.276131677627563,
|
|
"epoch": 0.830270631473438,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004937344906171795,
|
|
"loss": 5.077,
|
|
"mean_token_accuracy": 0.2060442104935646,
|
|
"num_tokens": 18305743.0,
|
|
"step": 9940
|
|
},
|
|
{
|
|
"entropy": 5.353442621231079,
|
|
"epoch": 0.830688272636151,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004937275122318902,
|
|
"loss": 5.0886,
|
|
"mean_token_accuracy": 0.20024637132883072,
|
|
"num_tokens": 18315524.0,
|
|
"step": 9945
|
|
},
|
|
{
|
|
"entropy": 5.2776796340942385,
|
|
"epoch": 0.831105913798864,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004937205300175123,
|
|
"loss": 4.9499,
|
|
"mean_token_accuracy": 0.21121760010719298,
|
|
"num_tokens": 18324280.0,
|
|
"step": 9950
|
|
},
|
|
{
|
|
"entropy": 5.338615846633911,
|
|
"epoch": 0.831523554961577,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004937135439741682,
|
|
"loss": 5.041,
|
|
"mean_token_accuracy": 0.20347232818603517,
|
|
"num_tokens": 18332661.0,
|
|
"step": 9955
|
|
},
|
|
{
|
|
"entropy": 5.3068865776062015,
|
|
"epoch": 0.83194119612429,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004937065541019806,
|
|
"loss": 5.1453,
|
|
"mean_token_accuracy": 0.1889631763100624,
|
|
"num_tokens": 18342986.0,
|
|
"step": 9960
|
|
},
|
|
{
|
|
"entropy": 5.34487738609314,
|
|
"epoch": 0.832358837287003,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004936995604010711,
|
|
"loss": 5.0867,
|
|
"mean_token_accuracy": 0.2043716013431549,
|
|
"num_tokens": 18351873.0,
|
|
"step": 9965
|
|
},
|
|
{
|
|
"entropy": 5.3892107009887695,
|
|
"epoch": 0.832776478449716,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004936925628715628,
|
|
"loss": 5.1559,
|
|
"mean_token_accuracy": 0.19914899617433549,
|
|
"num_tokens": 18362174.0,
|
|
"step": 9970
|
|
},
|
|
{
|
|
"entropy": 5.309047508239746,
|
|
"epoch": 0.833194119612429,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004936855615135779,
|
|
"loss": 4.961,
|
|
"mean_token_accuracy": 0.21297989785671234,
|
|
"num_tokens": 18371272.0,
|
|
"step": 9975
|
|
},
|
|
{
|
|
"entropy": 5.325804662704468,
|
|
"epoch": 0.833611760775142,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000493678556327239,
|
|
"loss": 5.0741,
|
|
"mean_token_accuracy": 0.20604854822158813,
|
|
"num_tokens": 18380526.0,
|
|
"step": 9980
|
|
},
|
|
{
|
|
"entropy": 5.252417516708374,
|
|
"epoch": 0.834029401937855,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004936715473126688,
|
|
"loss": 4.9898,
|
|
"mean_token_accuracy": 0.2055755466222763,
|
|
"num_tokens": 18390027.0,
|
|
"step": 9985
|
|
},
|
|
{
|
|
"entropy": 5.209375238418579,
|
|
"epoch": 0.8344470431005679,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00049366453446999,
|
|
"loss": 4.9682,
|
|
"mean_token_accuracy": 0.20910389274358748,
|
|
"num_tokens": 18399012.0,
|
|
"step": 9990
|
|
},
|
|
{
|
|
"entropy": 5.208969020843506,
|
|
"epoch": 0.834864684263281,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004936575177993251,
|
|
"loss": 4.9206,
|
|
"mean_token_accuracy": 0.20752075165510178,
|
|
"num_tokens": 18408891.0,
|
|
"step": 9995
|
|
},
|
|
{
|
|
"entropy": 5.263211059570312,
|
|
"epoch": 0.835282325425994,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004936504973007973,
|
|
"loss": 4.9364,
|
|
"mean_token_accuracy": 0.20904496014118196,
|
|
"num_tokens": 18417909.0,
|
|
"step": 10000
|
|
},
|
|
{
|
|
"entropy": 5.2176923751831055,
|
|
"epoch": 0.8356999665887069,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004936434729745294,
|
|
"loss": 5.0183,
|
|
"mean_token_accuracy": 0.2021762400865555,
|
|
"num_tokens": 18427250.0,
|
|
"step": 10005
|
|
},
|
|
{
|
|
"entropy": 5.279464435577393,
|
|
"epoch": 0.83611760775142,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004936364448206442,
|
|
"loss": 4.987,
|
|
"mean_token_accuracy": 0.204580220580101,
|
|
"num_tokens": 18435851.0,
|
|
"step": 10010
|
|
},
|
|
{
|
|
"entropy": 5.234575986862183,
|
|
"epoch": 0.836535248914133,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004936294128392649,
|
|
"loss": 4.9918,
|
|
"mean_token_accuracy": 0.1984171226620674,
|
|
"num_tokens": 18444535.0,
|
|
"step": 10015
|
|
},
|
|
{
|
|
"entropy": 5.293031787872314,
|
|
"epoch": 0.8369528900768459,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004936223770305146,
|
|
"loss": 5.1164,
|
|
"mean_token_accuracy": 0.20174213945865632,
|
|
"num_tokens": 18454453.0,
|
|
"step": 10020
|
|
},
|
|
{
|
|
"entropy": 5.389978837966919,
|
|
"epoch": 0.837370531239559,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004936153373945165,
|
|
"loss": 5.1418,
|
|
"mean_token_accuracy": 0.19709545522928237,
|
|
"num_tokens": 18465033.0,
|
|
"step": 10025
|
|
},
|
|
{
|
|
"entropy": 5.3353354930877686,
|
|
"epoch": 0.837788172402272,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004936082939313936,
|
|
"loss": 5.0292,
|
|
"mean_token_accuracy": 0.20263568609952926,
|
|
"num_tokens": 18473786.0,
|
|
"step": 10030
|
|
},
|
|
{
|
|
"entropy": 5.206992769241333,
|
|
"epoch": 0.8382058135649849,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004936012466412695,
|
|
"loss": 4.987,
|
|
"mean_token_accuracy": 0.20087777972221374,
|
|
"num_tokens": 18483282.0,
|
|
"step": 10035
|
|
},
|
|
{
|
|
"entropy": 5.381425237655639,
|
|
"epoch": 0.838623454727698,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004935941955242674,
|
|
"loss": 5.1521,
|
|
"mean_token_accuracy": 0.19864945411682128,
|
|
"num_tokens": 18492612.0,
|
|
"step": 10040
|
|
},
|
|
{
|
|
"entropy": 5.295857954025268,
|
|
"epoch": 0.839041095890411,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004935871405805109,
|
|
"loss": 4.9684,
|
|
"mean_token_accuracy": 0.21615595519542694,
|
|
"num_tokens": 18501120.0,
|
|
"step": 10045
|
|
},
|
|
{
|
|
"entropy": 5.2610431671142575,
|
|
"epoch": 0.8394587370531239,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004935800818101232,
|
|
"loss": 5.0656,
|
|
"mean_token_accuracy": 0.1995917871594429,
|
|
"num_tokens": 18510613.0,
|
|
"step": 10050
|
|
},
|
|
{
|
|
"entropy": 5.260000991821289,
|
|
"epoch": 0.8398763782158369,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004935730192132282,
|
|
"loss": 4.9681,
|
|
"mean_token_accuracy": 0.20497325658798218,
|
|
"num_tokens": 18518854.0,
|
|
"step": 10055
|
|
},
|
|
{
|
|
"entropy": 5.325906133651733,
|
|
"epoch": 0.84029401937855,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004935659527899493,
|
|
"loss": 5.0657,
|
|
"mean_token_accuracy": 0.2045937806367874,
|
|
"num_tokens": 18527592.0,
|
|
"step": 10060
|
|
},
|
|
{
|
|
"entropy": 5.237090158462524,
|
|
"epoch": 0.8407116605412629,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004935588825404104,
|
|
"loss": 4.9167,
|
|
"mean_token_accuracy": 0.21674193441867828,
|
|
"num_tokens": 18536396.0,
|
|
"step": 10065
|
|
},
|
|
{
|
|
"entropy": 5.212545442581177,
|
|
"epoch": 0.8411293017039759,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004935518084647351,
|
|
"loss": 4.8951,
|
|
"mean_token_accuracy": 0.21914102435111998,
|
|
"num_tokens": 18545201.0,
|
|
"step": 10070
|
|
},
|
|
{
|
|
"entropy": 5.270266771316528,
|
|
"epoch": 0.841546942866689,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004935447305630474,
|
|
"loss": 5.0878,
|
|
"mean_token_accuracy": 0.20132859349250792,
|
|
"num_tokens": 18554944.0,
|
|
"step": 10075
|
|
},
|
|
{
|
|
"entropy": 5.270673847198486,
|
|
"epoch": 0.8419645840294019,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004935376488354711,
|
|
"loss": 4.9798,
|
|
"mean_token_accuracy": 0.20357297956943513,
|
|
"num_tokens": 18564642.0,
|
|
"step": 10080
|
|
},
|
|
{
|
|
"entropy": 5.296598768234253,
|
|
"epoch": 0.8423822251921149,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004935305632821303,
|
|
"loss": 4.9898,
|
|
"mean_token_accuracy": 0.2068466365337372,
|
|
"num_tokens": 18573897.0,
|
|
"step": 10085
|
|
},
|
|
{
|
|
"entropy": 5.283039236068726,
|
|
"epoch": 0.842799866354828,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004935234739031488,
|
|
"loss": 5.0299,
|
|
"mean_token_accuracy": 0.20671347677707672,
|
|
"num_tokens": 18583174.0,
|
|
"step": 10090
|
|
},
|
|
{
|
|
"entropy": 5.275842952728271,
|
|
"epoch": 0.8432175075175409,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004935163806986508,
|
|
"loss": 4.9425,
|
|
"mean_token_accuracy": 0.20930425077676773,
|
|
"num_tokens": 18592540.0,
|
|
"step": 10095
|
|
},
|
|
{
|
|
"entropy": 5.234079647064209,
|
|
"epoch": 0.8436351486802539,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004935092836687607,
|
|
"loss": 4.9582,
|
|
"mean_token_accuracy": 0.20485835820436477,
|
|
"num_tokens": 18602743.0,
|
|
"step": 10100
|
|
},
|
|
{
|
|
"entropy": 5.2034423828125,
|
|
"epoch": 0.8440527898429669,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004935021828136025,
|
|
"loss": 4.9157,
|
|
"mean_token_accuracy": 0.2104882314801216,
|
|
"num_tokens": 18611544.0,
|
|
"step": 10105
|
|
},
|
|
{
|
|
"entropy": 5.343887567520142,
|
|
"epoch": 0.8444704310056799,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004934950781333005,
|
|
"loss": 5.0314,
|
|
"mean_token_accuracy": 0.20303449183702468,
|
|
"num_tokens": 18620841.0,
|
|
"step": 10110
|
|
},
|
|
{
|
|
"entropy": 5.299557781219482,
|
|
"epoch": 0.8448880721683929,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004934879696279793,
|
|
"loss": 5.0701,
|
|
"mean_token_accuracy": 0.20216573178768157,
|
|
"num_tokens": 18630890.0,
|
|
"step": 10115
|
|
},
|
|
{
|
|
"entropy": 5.332501173019409,
|
|
"epoch": 0.8453057133311059,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004934808572977632,
|
|
"loss": 5.0693,
|
|
"mean_token_accuracy": 0.1973210945725441,
|
|
"num_tokens": 18639768.0,
|
|
"step": 10120
|
|
},
|
|
{
|
|
"entropy": 5.210367345809937,
|
|
"epoch": 0.8457233544938189,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004934737411427765,
|
|
"loss": 4.8895,
|
|
"mean_token_accuracy": 0.21083588302135467,
|
|
"num_tokens": 18649578.0,
|
|
"step": 10125
|
|
},
|
|
{
|
|
"entropy": 5.228143835067749,
|
|
"epoch": 0.8461409956565319,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004934666211631442,
|
|
"loss": 4.9924,
|
|
"mean_token_accuracy": 0.2090206637978554,
|
|
"num_tokens": 18658470.0,
|
|
"step": 10130
|
|
},
|
|
{
|
|
"entropy": 5.260270881652832,
|
|
"epoch": 0.8465586368192449,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004934594973589906,
|
|
"loss": 4.9627,
|
|
"mean_token_accuracy": 0.20124966502189637,
|
|
"num_tokens": 18668037.0,
|
|
"step": 10135
|
|
},
|
|
{
|
|
"entropy": 5.26919322013855,
|
|
"epoch": 0.8469762779819578,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004934523697304406,
|
|
"loss": 5.0782,
|
|
"mean_token_accuracy": 0.19919137209653853,
|
|
"num_tokens": 18677841.0,
|
|
"step": 10140
|
|
},
|
|
{
|
|
"entropy": 5.3400341987609865,
|
|
"epoch": 0.8473939191446709,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004934452382776189,
|
|
"loss": 5.0133,
|
|
"mean_token_accuracy": 0.199882934987545,
|
|
"num_tokens": 18686244.0,
|
|
"step": 10145
|
|
},
|
|
{
|
|
"entropy": 5.283691787719727,
|
|
"epoch": 0.8478115603073839,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004934381030006504,
|
|
"loss": 5.0547,
|
|
"mean_token_accuracy": 0.20212140381336213,
|
|
"num_tokens": 18695129.0,
|
|
"step": 10150
|
|
},
|
|
{
|
|
"entropy": 5.172067451477051,
|
|
"epoch": 0.8482292014700968,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00049343096389966,
|
|
"loss": 4.8854,
|
|
"mean_token_accuracy": 0.2176145538687706,
|
|
"num_tokens": 18703566.0,
|
|
"step": 10155
|
|
},
|
|
{
|
|
"entropy": 5.321353244781494,
|
|
"epoch": 0.8486468426328099,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004934238209747724,
|
|
"loss": 5.08,
|
|
"mean_token_accuracy": 0.19820543229579926,
|
|
"num_tokens": 18713616.0,
|
|
"step": 10160
|
|
},
|
|
{
|
|
"entropy": 5.3626219749450685,
|
|
"epoch": 0.8490644837955229,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004934166742261132,
|
|
"loss": 5.01,
|
|
"mean_token_accuracy": 0.20752353966236115,
|
|
"num_tokens": 18722851.0,
|
|
"step": 10165
|
|
},
|
|
{
|
|
"entropy": 5.302944755554199,
|
|
"epoch": 0.8494821249582358,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000493409523653807,
|
|
"loss": 5.0111,
|
|
"mean_token_accuracy": 0.20677843689918518,
|
|
"num_tokens": 18731961.0,
|
|
"step": 10170
|
|
},
|
|
{
|
|
"entropy": 5.2983826160430905,
|
|
"epoch": 0.8498997661209489,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004934023692579793,
|
|
"loss": 5.1786,
|
|
"mean_token_accuracy": 0.20431944280862807,
|
|
"num_tokens": 18741267.0,
|
|
"step": 10175
|
|
},
|
|
{
|
|
"entropy": 5.335294961929321,
|
|
"epoch": 0.8503174072836619,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004933952110387553,
|
|
"loss": 5.0227,
|
|
"mean_token_accuracy": 0.20469975769519805,
|
|
"num_tokens": 18750266.0,
|
|
"step": 10180
|
|
},
|
|
{
|
|
"entropy": 5.268962717056274,
|
|
"epoch": 0.8507350484463748,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004933880489962602,
|
|
"loss": 5.0046,
|
|
"mean_token_accuracy": 0.20418863892555236,
|
|
"num_tokens": 18759910.0,
|
|
"step": 10185
|
|
},
|
|
{
|
|
"entropy": 5.3556318283081055,
|
|
"epoch": 0.8511526896090879,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004933808831306194,
|
|
"loss": 5.1485,
|
|
"mean_token_accuracy": 0.194237357378006,
|
|
"num_tokens": 18769510.0,
|
|
"step": 10190
|
|
},
|
|
{
|
|
"entropy": 5.236069297790527,
|
|
"epoch": 0.8515703307718009,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004933737134419583,
|
|
"loss": 4.9556,
|
|
"mean_token_accuracy": 0.20543353408575057,
|
|
"num_tokens": 18779893.0,
|
|
"step": 10195
|
|
},
|
|
{
|
|
"entropy": 5.308035469055175,
|
|
"epoch": 0.8519879719345138,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004933665399304025,
|
|
"loss": 5.0148,
|
|
"mean_token_accuracy": 0.2130729541182518,
|
|
"num_tokens": 18788802.0,
|
|
"step": 10200
|
|
},
|
|
{
|
|
"entropy": 5.234163379669189,
|
|
"epoch": 0.8524056130972268,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004933593625960777,
|
|
"loss": 4.9118,
|
|
"mean_token_accuracy": 0.2109411671757698,
|
|
"num_tokens": 18797154.0,
|
|
"step": 10205
|
|
},
|
|
{
|
|
"entropy": 5.266857051849366,
|
|
"epoch": 0.8528232542599399,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004933521814391094,
|
|
"loss": 5.0417,
|
|
"mean_token_accuracy": 0.2085142806172371,
|
|
"num_tokens": 18806151.0,
|
|
"step": 10210
|
|
},
|
|
{
|
|
"entropy": 5.33585844039917,
|
|
"epoch": 0.8532408954226529,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004933449964596232,
|
|
"loss": 4.9471,
|
|
"mean_token_accuracy": 0.21520161032676696,
|
|
"num_tokens": 18815162.0,
|
|
"step": 10215
|
|
},
|
|
{
|
|
"entropy": 5.205343437194824,
|
|
"epoch": 0.8536585365853658,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004933378076577451,
|
|
"loss": 4.9212,
|
|
"mean_token_accuracy": 0.2057916358113289,
|
|
"num_tokens": 18823676.0,
|
|
"step": 10220
|
|
},
|
|
{
|
|
"entropy": 5.351762294769287,
|
|
"epoch": 0.8540761777480789,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004933306150336009,
|
|
"loss": 5.2249,
|
|
"mean_token_accuracy": 0.19383471310138703,
|
|
"num_tokens": 18832991.0,
|
|
"step": 10225
|
|
},
|
|
{
|
|
"entropy": 5.3964050769805905,
|
|
"epoch": 0.8544938189107919,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004933234185873164,
|
|
"loss": 5.0966,
|
|
"mean_token_accuracy": 0.19839687943458556,
|
|
"num_tokens": 18842614.0,
|
|
"step": 10230
|
|
},
|
|
{
|
|
"entropy": 5.373830318450928,
|
|
"epoch": 0.8549114600735048,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004933162183190177,
|
|
"loss": 5.1404,
|
|
"mean_token_accuracy": 0.19562443643808364,
|
|
"num_tokens": 18852747.0,
|
|
"step": 10235
|
|
},
|
|
{
|
|
"entropy": 5.251061058044433,
|
|
"epoch": 0.8553291012362179,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004933090142288308,
|
|
"loss": 5.0091,
|
|
"mean_token_accuracy": 0.20302987694740296,
|
|
"num_tokens": 18862005.0,
|
|
"step": 10240
|
|
},
|
|
{
|
|
"entropy": 5.295311164855957,
|
|
"epoch": 0.8557467423989309,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004933018063168819,
|
|
"loss": 4.9707,
|
|
"mean_token_accuracy": 0.2199796348810196,
|
|
"num_tokens": 18870172.0,
|
|
"step": 10245
|
|
},
|
|
{
|
|
"entropy": 5.31706051826477,
|
|
"epoch": 0.8561643835616438,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000493294594583297,
|
|
"loss": 5.0506,
|
|
"mean_token_accuracy": 0.20717416554689408,
|
|
"num_tokens": 18879428.0,
|
|
"step": 10250
|
|
},
|
|
{
|
|
"entropy": 5.303390455245972,
|
|
"epoch": 0.8565820247243568,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004932873790282026,
|
|
"loss": 4.9896,
|
|
"mean_token_accuracy": 0.2154971867799759,
|
|
"num_tokens": 18888694.0,
|
|
"step": 10255
|
|
},
|
|
{
|
|
"entropy": 5.333094358444214,
|
|
"epoch": 0.8569996658870699,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004932801596517248,
|
|
"loss": 5.0496,
|
|
"mean_token_accuracy": 0.1969591572880745,
|
|
"num_tokens": 18898317.0,
|
|
"step": 10260
|
|
},
|
|
{
|
|
"entropy": 5.237871885299683,
|
|
"epoch": 0.8574173070497828,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004932729364539901,
|
|
"loss": 5.0297,
|
|
"mean_token_accuracy": 0.2007185474038124,
|
|
"num_tokens": 18906749.0,
|
|
"step": 10265
|
|
},
|
|
{
|
|
"entropy": 5.24932107925415,
|
|
"epoch": 0.8578349482124958,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004932657094351248,
|
|
"loss": 4.9268,
|
|
"mean_token_accuracy": 0.2038540616631508,
|
|
"num_tokens": 18915404.0,
|
|
"step": 10270
|
|
},
|
|
{
|
|
"entropy": 5.311759185791016,
|
|
"epoch": 0.8582525893752089,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004932584785952555,
|
|
"loss": 5.0262,
|
|
"mean_token_accuracy": 0.2053885668516159,
|
|
"num_tokens": 18925512.0,
|
|
"step": 10275
|
|
},
|
|
{
|
|
"entropy": 5.239424848556519,
|
|
"epoch": 0.8586702305379218,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000493251243934509,
|
|
"loss": 4.9454,
|
|
"mean_token_accuracy": 0.2159731775522232,
|
|
"num_tokens": 18934278.0,
|
|
"step": 10280
|
|
},
|
|
{
|
|
"entropy": 5.263280725479126,
|
|
"epoch": 0.8590878717006348,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004932440054530116,
|
|
"loss": 5.0363,
|
|
"mean_token_accuracy": 0.20390205830335617,
|
|
"num_tokens": 18943126.0,
|
|
"step": 10285
|
|
},
|
|
{
|
|
"entropy": 5.300428056716919,
|
|
"epoch": 0.8595055128633479,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004932367631508903,
|
|
"loss": 5.0113,
|
|
"mean_token_accuracy": 0.2080025628209114,
|
|
"num_tokens": 18951716.0,
|
|
"step": 10290
|
|
},
|
|
{
|
|
"entropy": 5.291877508163452,
|
|
"epoch": 0.8599231540260608,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004932295170282717,
|
|
"loss": 5.1041,
|
|
"mean_token_accuracy": 0.1983656495809555,
|
|
"num_tokens": 18960692.0,
|
|
"step": 10295
|
|
},
|
|
{
|
|
"entropy": 5.2682994365692135,
|
|
"epoch": 0.8603407951887738,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004932222670852828,
|
|
"loss": 5.0503,
|
|
"mean_token_accuracy": 0.20897567570209502,
|
|
"num_tokens": 18969813.0,
|
|
"step": 10300
|
|
},
|
|
{
|
|
"entropy": 5.276914930343628,
|
|
"epoch": 0.8607584363514869,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004932150133220504,
|
|
"loss": 4.8932,
|
|
"mean_token_accuracy": 0.21474039256572724,
|
|
"num_tokens": 18978536.0,
|
|
"step": 10305
|
|
},
|
|
{
|
|
"entropy": 5.261690282821656,
|
|
"epoch": 0.8611760775141998,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004932077557387015,
|
|
"loss": 4.9917,
|
|
"mean_token_accuracy": 0.2117157205939293,
|
|
"num_tokens": 18987637.0,
|
|
"step": 10310
|
|
},
|
|
{
|
|
"entropy": 5.164496040344238,
|
|
"epoch": 0.8615937186769128,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004932004943353633,
|
|
"loss": 4.8371,
|
|
"mean_token_accuracy": 0.2142604261636734,
|
|
"num_tokens": 18997010.0,
|
|
"step": 10315
|
|
},
|
|
{
|
|
"entropy": 5.237453508377075,
|
|
"epoch": 0.8620113598396258,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004931932291121627,
|
|
"loss": 4.982,
|
|
"mean_token_accuracy": 0.20955340415239335,
|
|
"num_tokens": 19005685.0,
|
|
"step": 10320
|
|
},
|
|
{
|
|
"entropy": 5.253964138031006,
|
|
"epoch": 0.8624290010023388,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004931859600692269,
|
|
"loss": 5.0142,
|
|
"mean_token_accuracy": 0.20397783517837526,
|
|
"num_tokens": 19014836.0,
|
|
"step": 10325
|
|
},
|
|
{
|
|
"entropy": 5.291058444976807,
|
|
"epoch": 0.8628466421650518,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004931786872066833,
|
|
"loss": 5.0441,
|
|
"mean_token_accuracy": 0.20211344510316848,
|
|
"num_tokens": 19024442.0,
|
|
"step": 10330
|
|
},
|
|
{
|
|
"entropy": 5.311799240112305,
|
|
"epoch": 0.8632642833277648,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004931714105246592,
|
|
"loss": 4.9836,
|
|
"mean_token_accuracy": 0.21372086852788924,
|
|
"num_tokens": 19033730.0,
|
|
"step": 10335
|
|
},
|
|
{
|
|
"entropy": 5.263733768463135,
|
|
"epoch": 0.8636819244904778,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004931641300232819,
|
|
"loss": 4.9367,
|
|
"mean_token_accuracy": 0.21760034561157227,
|
|
"num_tokens": 19042765.0,
|
|
"step": 10340
|
|
},
|
|
{
|
|
"entropy": 5.317936515808105,
|
|
"epoch": 0.8640995656531908,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004931568457026789,
|
|
"loss": 4.9392,
|
|
"mean_token_accuracy": 0.20653872936964035,
|
|
"num_tokens": 19051408.0,
|
|
"step": 10345
|
|
},
|
|
{
|
|
"entropy": 5.297897148132324,
|
|
"epoch": 0.8645172068159038,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004931495575629778,
|
|
"loss": 5.0502,
|
|
"mean_token_accuracy": 0.20026125013828278,
|
|
"num_tokens": 19061145.0,
|
|
"step": 10350
|
|
},
|
|
{
|
|
"entropy": 5.254010915756226,
|
|
"epoch": 0.8649348479786167,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000493142265604306,
|
|
"loss": 5.042,
|
|
"mean_token_accuracy": 0.20199861228466034,
|
|
"num_tokens": 19070157.0,
|
|
"step": 10355
|
|
},
|
|
{
|
|
"entropy": 5.228733110427856,
|
|
"epoch": 0.8653524891413298,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004931349698267914,
|
|
"loss": 4.8609,
|
|
"mean_token_accuracy": 0.22068461924791336,
|
|
"num_tokens": 19078532.0,
|
|
"step": 10360
|
|
},
|
|
{
|
|
"entropy": 5.2406251430511475,
|
|
"epoch": 0.8657701303040428,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004931276702305615,
|
|
"loss": 4.9067,
|
|
"mean_token_accuracy": 0.21284476667642593,
|
|
"num_tokens": 19087283.0,
|
|
"step": 10365
|
|
},
|
|
{
|
|
"entropy": 5.306699419021607,
|
|
"epoch": 0.8661877714667557,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004931203668157441,
|
|
"loss": 5.0964,
|
|
"mean_token_accuracy": 0.2053291141986847,
|
|
"num_tokens": 19097568.0,
|
|
"step": 10370
|
|
},
|
|
{
|
|
"entropy": 5.362837266921997,
|
|
"epoch": 0.8666054126294688,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004931130595824672,
|
|
"loss": 5.0662,
|
|
"mean_token_accuracy": 0.20025492906570436,
|
|
"num_tokens": 19107218.0,
|
|
"step": 10375
|
|
},
|
|
{
|
|
"entropy": 5.296062374114991,
|
|
"epoch": 0.8670230537921818,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004931057485308587,
|
|
"loss": 5.0347,
|
|
"mean_token_accuracy": 0.2037366136908531,
|
|
"num_tokens": 19116128.0,
|
|
"step": 10380
|
|
},
|
|
{
|
|
"entropy": 5.197923278808593,
|
|
"epoch": 0.8674406949548947,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004930984336610465,
|
|
"loss": 4.9866,
|
|
"mean_token_accuracy": 0.20974574834108353,
|
|
"num_tokens": 19124885.0,
|
|
"step": 10385
|
|
},
|
|
{
|
|
"entropy": 5.325475263595581,
|
|
"epoch": 0.8678583361176078,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004930911149731587,
|
|
"loss": 5.0609,
|
|
"mean_token_accuracy": 0.20704571902751923,
|
|
"num_tokens": 19134125.0,
|
|
"step": 10390
|
|
},
|
|
{
|
|
"entropy": 5.257022190093994,
|
|
"epoch": 0.8682759772803208,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004930837924673233,
|
|
"loss": 4.9434,
|
|
"mean_token_accuracy": 0.20590798705816268,
|
|
"num_tokens": 19141925.0,
|
|
"step": 10395
|
|
},
|
|
{
|
|
"entropy": 5.285811710357666,
|
|
"epoch": 0.8686936184430337,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004930764661436688,
|
|
"loss": 5.0289,
|
|
"mean_token_accuracy": 0.20406344532966614,
|
|
"num_tokens": 19151440.0,
|
|
"step": 10400
|
|
},
|
|
{
|
|
"entropy": 5.315800333023072,
|
|
"epoch": 0.8691112596057468,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004930691360023231,
|
|
"loss": 5.1078,
|
|
"mean_token_accuracy": 0.20519358962774276,
|
|
"num_tokens": 19161447.0,
|
|
"step": 10405
|
|
},
|
|
{
|
|
"entropy": 5.303775262832642,
|
|
"epoch": 0.8695289007684598,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004930618020434147,
|
|
"loss": 5.0323,
|
|
"mean_token_accuracy": 0.2023095890879631,
|
|
"num_tokens": 19170804.0,
|
|
"step": 10410
|
|
},
|
|
{
|
|
"entropy": 5.393555736541748,
|
|
"epoch": 0.8699465419311727,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004930544642670721,
|
|
"loss": 5.1202,
|
|
"mean_token_accuracy": 0.19721234887838363,
|
|
"num_tokens": 19179898.0,
|
|
"step": 10415
|
|
},
|
|
{
|
|
"entropy": 5.232870101928711,
|
|
"epoch": 0.8703641830938857,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004930471226734235,
|
|
"loss": 4.9481,
|
|
"mean_token_accuracy": 0.21083010882139205,
|
|
"num_tokens": 19188919.0,
|
|
"step": 10420
|
|
},
|
|
{
|
|
"entropy": 5.277183198928833,
|
|
"epoch": 0.8707818242565988,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004930397772625976,
|
|
"loss": 5.0306,
|
|
"mean_token_accuracy": 0.2075921803712845,
|
|
"num_tokens": 19197745.0,
|
|
"step": 10425
|
|
},
|
|
{
|
|
"entropy": 5.277238464355468,
|
|
"epoch": 0.8711994654193117,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000493032428034723,
|
|
"loss": 5.0321,
|
|
"mean_token_accuracy": 0.20863038897514344,
|
|
"num_tokens": 19206681.0,
|
|
"step": 10430
|
|
},
|
|
{
|
|
"entropy": 5.380311965942383,
|
|
"epoch": 0.8716171065820247,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004930250749899282,
|
|
"loss": 5.0319,
|
|
"mean_token_accuracy": 0.2054059088230133,
|
|
"num_tokens": 19215806.0,
|
|
"step": 10435
|
|
},
|
|
{
|
|
"entropy": 5.281986284255981,
|
|
"epoch": 0.8720347477447378,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004930177181283422,
|
|
"loss": 5.048,
|
|
"mean_token_accuracy": 0.20246667712926864,
|
|
"num_tokens": 19224681.0,
|
|
"step": 10440
|
|
},
|
|
{
|
|
"entropy": 5.239447927474975,
|
|
"epoch": 0.8724523889074507,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004930103574500934,
|
|
"loss": 5.045,
|
|
"mean_token_accuracy": 0.2029770776629448,
|
|
"num_tokens": 19232684.0,
|
|
"step": 10445
|
|
},
|
|
{
|
|
"entropy": 5.30054292678833,
|
|
"epoch": 0.8728700300701637,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004930029929553109,
|
|
"loss": 4.9527,
|
|
"mean_token_accuracy": 0.20128995627164842,
|
|
"num_tokens": 19242538.0,
|
|
"step": 10450
|
|
},
|
|
{
|
|
"entropy": 5.244245004653931,
|
|
"epoch": 0.8732876712328768,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004929956246441237,
|
|
"loss": 5.0008,
|
|
"mean_token_accuracy": 0.20038944780826567,
|
|
"num_tokens": 19251146.0,
|
|
"step": 10455
|
|
},
|
|
{
|
|
"entropy": 5.371267318725586,
|
|
"epoch": 0.8737053123955897,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004929882525166608,
|
|
"loss": 5.0144,
|
|
"mean_token_accuracy": 0.2000021755695343,
|
|
"num_tokens": 19259931.0,
|
|
"step": 10460
|
|
},
|
|
{
|
|
"entropy": 5.325706195831299,
|
|
"epoch": 0.8741229535583027,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004929808765730509,
|
|
"loss": 5.0412,
|
|
"mean_token_accuracy": 0.2019277274608612,
|
|
"num_tokens": 19268796.0,
|
|
"step": 10465
|
|
},
|
|
{
|
|
"entropy": 5.270397043228149,
|
|
"epoch": 0.8745405947210158,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004929734968134235,
|
|
"loss": 5.0728,
|
|
"mean_token_accuracy": 0.19787393212318422,
|
|
"num_tokens": 19278396.0,
|
|
"step": 10470
|
|
},
|
|
{
|
|
"entropy": 5.359102725982666,
|
|
"epoch": 0.8749582358837287,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004929661132379076,
|
|
"loss": 5.0749,
|
|
"mean_token_accuracy": 0.19762273579835893,
|
|
"num_tokens": 19287914.0,
|
|
"step": 10475
|
|
},
|
|
{
|
|
"entropy": 5.346466159820556,
|
|
"epoch": 0.8753758770464417,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004929587258466326,
|
|
"loss": 5.0483,
|
|
"mean_token_accuracy": 0.19957538694143295,
|
|
"num_tokens": 19297304.0,
|
|
"step": 10480
|
|
},
|
|
{
|
|
"entropy": 5.329871892929077,
|
|
"epoch": 0.8757935182091547,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004929513346397278,
|
|
"loss": 5.0037,
|
|
"mean_token_accuracy": 0.20976925790309905,
|
|
"num_tokens": 19306245.0,
|
|
"step": 10485
|
|
},
|
|
{
|
|
"entropy": 5.296418523788452,
|
|
"epoch": 0.8762111593718677,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004929439396173223,
|
|
"loss": 5.0139,
|
|
"mean_token_accuracy": 0.20032329112291336,
|
|
"num_tokens": 19316160.0,
|
|
"step": 10490
|
|
},
|
|
{
|
|
"entropy": 5.29181399345398,
|
|
"epoch": 0.8766288005345807,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000492936540779546,
|
|
"loss": 5.0996,
|
|
"mean_token_accuracy": 0.1979194015264511,
|
|
"num_tokens": 19325411.0,
|
|
"step": 10495
|
|
},
|
|
{
|
|
"entropy": 5.359336233139038,
|
|
"epoch": 0.8770464416972937,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004929291381265281,
|
|
"loss": 4.9975,
|
|
"mean_token_accuracy": 0.20435776710510253,
|
|
"num_tokens": 19334297.0,
|
|
"step": 10500
|
|
},
|
|
{
|
|
"entropy": 5.37188024520874,
|
|
"epoch": 0.8774640828600067,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004929217316583985,
|
|
"loss": 5.1017,
|
|
"mean_token_accuracy": 0.19282938838005065,
|
|
"num_tokens": 19344121.0,
|
|
"step": 10505
|
|
},
|
|
{
|
|
"entropy": 5.28780460357666,
|
|
"epoch": 0.8778817240227197,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004929143213752865,
|
|
"loss": 5.0374,
|
|
"mean_token_accuracy": 0.20151905864477157,
|
|
"num_tokens": 19353428.0,
|
|
"step": 10510
|
|
},
|
|
{
|
|
"entropy": 5.309815120697022,
|
|
"epoch": 0.8782993651854327,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000492906907277322,
|
|
"loss": 5.0842,
|
|
"mean_token_accuracy": 0.2049848034977913,
|
|
"num_tokens": 19362661.0,
|
|
"step": 10515
|
|
},
|
|
{
|
|
"entropy": 5.215135478973389,
|
|
"epoch": 0.8787170063481456,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000492899489364635,
|
|
"loss": 4.8873,
|
|
"mean_token_accuracy": 0.21897618621587753,
|
|
"num_tokens": 19371246.0,
|
|
"step": 10520
|
|
},
|
|
{
|
|
"entropy": 5.2584888458251955,
|
|
"epoch": 0.8791346475108587,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004928920676373549,
|
|
"loss": 4.9327,
|
|
"mean_token_accuracy": 0.20861630588769914,
|
|
"num_tokens": 19379777.0,
|
|
"step": 10525
|
|
},
|
|
{
|
|
"entropy": 5.246981287002564,
|
|
"epoch": 0.8795522886735717,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000492884642095612,
|
|
"loss": 4.9912,
|
|
"mean_token_accuracy": 0.20688994377851486,
|
|
"num_tokens": 19388717.0,
|
|
"step": 10530
|
|
},
|
|
{
|
|
"entropy": 5.407645750045776,
|
|
"epoch": 0.8799699298362846,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004928772127395361,
|
|
"loss": 5.1231,
|
|
"mean_token_accuracy": 0.1965832844376564,
|
|
"num_tokens": 19397936.0,
|
|
"step": 10535
|
|
},
|
|
{
|
|
"entropy": 5.4296173572540285,
|
|
"epoch": 0.8803875709989977,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004928697795692575,
|
|
"loss": 5.0834,
|
|
"mean_token_accuracy": 0.19767144620418547,
|
|
"num_tokens": 19406830.0,
|
|
"step": 10540
|
|
},
|
|
{
|
|
"entropy": 5.328914737701416,
|
|
"epoch": 0.8808052121617107,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000492862342584906,
|
|
"loss": 5.0852,
|
|
"mean_token_accuracy": 0.20326122790575027,
|
|
"num_tokens": 19415131.0,
|
|
"step": 10545
|
|
},
|
|
{
|
|
"entropy": 5.2831205368042,
|
|
"epoch": 0.8812228533244236,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000492854901786612,
|
|
"loss": 4.8774,
|
|
"mean_token_accuracy": 0.21782393455505372,
|
|
"num_tokens": 19423585.0,
|
|
"step": 10550
|
|
},
|
|
{
|
|
"entropy": 5.22721757888794,
|
|
"epoch": 0.8816404944871367,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004928474571745058,
|
|
"loss": 4.9054,
|
|
"mean_token_accuracy": 0.21980790048837662,
|
|
"num_tokens": 19431890.0,
|
|
"step": 10555
|
|
},
|
|
{
|
|
"entropy": 5.253408432006836,
|
|
"epoch": 0.8820581356498497,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004928400087487175,
|
|
"loss": 5.059,
|
|
"mean_token_accuracy": 0.20104600340127946,
|
|
"num_tokens": 19441377.0,
|
|
"step": 10560
|
|
},
|
|
{
|
|
"entropy": 5.2876804828643795,
|
|
"epoch": 0.8824757768125626,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004928325565093777,
|
|
"loss": 5.0382,
|
|
"mean_token_accuracy": 0.19772562384605408,
|
|
"num_tokens": 19451003.0,
|
|
"step": 10565
|
|
},
|
|
{
|
|
"entropy": 5.2811237335205075,
|
|
"epoch": 0.8828934179752757,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004928251004566167,
|
|
"loss": 4.9288,
|
|
"mean_token_accuracy": 0.20963248759508132,
|
|
"num_tokens": 19460166.0,
|
|
"step": 10570
|
|
},
|
|
{
|
|
"entropy": 5.246886777877807,
|
|
"epoch": 0.8833110591379887,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004928176405905653,
|
|
"loss": 5.0202,
|
|
"mean_token_accuracy": 0.20592687726020814,
|
|
"num_tokens": 19469417.0,
|
|
"step": 10575
|
|
},
|
|
{
|
|
"entropy": 5.330158948898315,
|
|
"epoch": 0.8837287003007016,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004928101769113537,
|
|
"loss": 5.0923,
|
|
"mean_token_accuracy": 0.20658836215734483,
|
|
"num_tokens": 19479275.0,
|
|
"step": 10580
|
|
},
|
|
{
|
|
"entropy": 5.328742456436157,
|
|
"epoch": 0.8841463414634146,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000492802709419113,
|
|
"loss": 4.9815,
|
|
"mean_token_accuracy": 0.20454305559396743,
|
|
"num_tokens": 19488804.0,
|
|
"step": 10585
|
|
},
|
|
{
|
|
"entropy": 5.310842561721802,
|
|
"epoch": 0.8845639826261277,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004927952381139735,
|
|
"loss": 4.9589,
|
|
"mean_token_accuracy": 0.20788733810186386,
|
|
"num_tokens": 19497701.0,
|
|
"step": 10590
|
|
},
|
|
{
|
|
"entropy": 5.3216719150543215,
|
|
"epoch": 0.8849816237888406,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004927877629960663,
|
|
"loss": 4.9825,
|
|
"mean_token_accuracy": 0.20679265409708023,
|
|
"num_tokens": 19508177.0,
|
|
"step": 10595
|
|
},
|
|
{
|
|
"entropy": 5.250254487991333,
|
|
"epoch": 0.8853992649515536,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004927802840655221,
|
|
"loss": 5.0524,
|
|
"mean_token_accuracy": 0.20582439452409745,
|
|
"num_tokens": 19516866.0,
|
|
"step": 10600
|
|
},
|
|
{
|
|
"entropy": 5.3429969310760494,
|
|
"epoch": 0.8858169061142667,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000492772801322472,
|
|
"loss": 5.0374,
|
|
"mean_token_accuracy": 0.2049921214580536,
|
|
"num_tokens": 19525788.0,
|
|
"step": 10605
|
|
},
|
|
{
|
|
"entropy": 5.314622402191162,
|
|
"epoch": 0.8862345472769796,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004927653147670468,
|
|
"loss": 4.8862,
|
|
"mean_token_accuracy": 0.21266158521175385,
|
|
"num_tokens": 19534748.0,
|
|
"step": 10610
|
|
},
|
|
{
|
|
"entropy": 5.2158294200897215,
|
|
"epoch": 0.8866521884396926,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004927578243993777,
|
|
"loss": 4.95,
|
|
"mean_token_accuracy": 0.20928464978933334,
|
|
"num_tokens": 19544083.0,
|
|
"step": 10615
|
|
},
|
|
{
|
|
"entropy": 5.231951093673706,
|
|
"epoch": 0.8870698296024057,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004927503302195957,
|
|
"loss": 4.9784,
|
|
"mean_token_accuracy": 0.20495544672012328,
|
|
"num_tokens": 19553978.0,
|
|
"step": 10620
|
|
},
|
|
{
|
|
"entropy": 5.345741224288941,
|
|
"epoch": 0.8874874707651186,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.000492742832227832,
|
|
"loss": 5.0564,
|
|
"mean_token_accuracy": 0.20942415297031403,
|
|
"num_tokens": 19563265.0,
|
|
"step": 10625
|
|
},
|
|
{
|
|
"entropy": 5.359615802764893,
|
|
"epoch": 0.8879051119278316,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.000492735330424218,
|
|
"loss": 5.0864,
|
|
"mean_token_accuracy": 0.19267746061086655,
|
|
"num_tokens": 19572904.0,
|
|
"step": 10630
|
|
},
|
|
{
|
|
"entropy": 5.356269598007202,
|
|
"epoch": 0.8883227530905446,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000492727824808885,
|
|
"loss": 5.0792,
|
|
"mean_token_accuracy": 0.20686798989772798,
|
|
"num_tokens": 19581680.0,
|
|
"step": 10635
|
|
},
|
|
{
|
|
"entropy": 5.2298229217529295,
|
|
"epoch": 0.8887403942532576,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004927203153819643,
|
|
"loss": 4.9298,
|
|
"mean_token_accuracy": 0.20364491939544677,
|
|
"num_tokens": 19590885.0,
|
|
"step": 10640
|
|
},
|
|
{
|
|
"entropy": 5.2199465274810795,
|
|
"epoch": 0.8891580354159706,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004927128021435875,
|
|
"loss": 4.9232,
|
|
"mean_token_accuracy": 0.21275381445884706,
|
|
"num_tokens": 19599901.0,
|
|
"step": 10645
|
|
},
|
|
{
|
|
"entropy": 5.3653727054595945,
|
|
"epoch": 0.8895756765786836,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000492705285093886,
|
|
"loss": 5.0768,
|
|
"mean_token_accuracy": 0.19855906814336777,
|
|
"num_tokens": 19608745.0,
|
|
"step": 10650
|
|
},
|
|
{
|
|
"entropy": 5.207261371612549,
|
|
"epoch": 0.8899933177413966,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004926977642329913,
|
|
"loss": 4.8383,
|
|
"mean_token_accuracy": 0.20991399735212327,
|
|
"num_tokens": 19618418.0,
|
|
"step": 10655
|
|
},
|
|
{
|
|
"entropy": 5.179308843612671,
|
|
"epoch": 0.8904109589041096,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004926902395610353,
|
|
"loss": 4.9181,
|
|
"mean_token_accuracy": 0.2046077623963356,
|
|
"num_tokens": 19627118.0,
|
|
"step": 10660
|
|
},
|
|
{
|
|
"entropy": 5.312536096572876,
|
|
"epoch": 0.8908286000668226,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004926827110781496,
|
|
"loss": 5.0831,
|
|
"mean_token_accuracy": 0.20530200153589248,
|
|
"num_tokens": 19636565.0,
|
|
"step": 10665
|
|
},
|
|
{
|
|
"entropy": 5.2458093643188475,
|
|
"epoch": 0.8912462412295356,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000492675178784466,
|
|
"loss": 4.9354,
|
|
"mean_token_accuracy": 0.20531355142593383,
|
|
"num_tokens": 19645038.0,
|
|
"step": 10670
|
|
},
|
|
{
|
|
"entropy": 5.244185972213745,
|
|
"epoch": 0.8916638823922486,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004926676426801164,
|
|
"loss": 4.9783,
|
|
"mean_token_accuracy": 0.20586746484041213,
|
|
"num_tokens": 19654088.0,
|
|
"step": 10675
|
|
},
|
|
{
|
|
"entropy": 5.283861446380615,
|
|
"epoch": 0.8920815235549616,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004926601027652328,
|
|
"loss": 5.0693,
|
|
"mean_token_accuracy": 0.20442845821380615,
|
|
"num_tokens": 19662551.0,
|
|
"step": 10680
|
|
},
|
|
{
|
|
"entropy": 5.328431940078735,
|
|
"epoch": 0.8924991647176745,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000492652559039947,
|
|
"loss": 5.0033,
|
|
"mean_token_accuracy": 0.2042037934064865,
|
|
"num_tokens": 19672405.0,
|
|
"step": 10685
|
|
},
|
|
{
|
|
"entropy": 5.265367698669434,
|
|
"epoch": 0.8929168058803876,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004926450115043912,
|
|
"loss": 4.9948,
|
|
"mean_token_accuracy": 0.204755437374115,
|
|
"num_tokens": 19681288.0,
|
|
"step": 10690
|
|
},
|
|
{
|
|
"entropy": 5.287013149261474,
|
|
"epoch": 0.8933344470431006,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004926374601586975,
|
|
"loss": 4.9243,
|
|
"mean_token_accuracy": 0.21029869168996812,
|
|
"num_tokens": 19690723.0,
|
|
"step": 10695
|
|
},
|
|
{
|
|
"entropy": 5.267658948898315,
|
|
"epoch": 0.8937520882058135,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004926299050029981,
|
|
"loss": 4.9793,
|
|
"mean_token_accuracy": 0.20806861519813538,
|
|
"num_tokens": 19699642.0,
|
|
"step": 10700
|
|
},
|
|
{
|
|
"entropy": 5.243737697601318,
|
|
"epoch": 0.8941697293685266,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004926223460374251,
|
|
"loss": 4.9295,
|
|
"mean_token_accuracy": 0.21498110443353652,
|
|
"num_tokens": 19707563.0,
|
|
"step": 10705
|
|
},
|
|
{
|
|
"entropy": 5.297790002822876,
|
|
"epoch": 0.8945873705312396,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004926147832621111,
|
|
"loss": 5.0743,
|
|
"mean_token_accuracy": 0.2071554332971573,
|
|
"num_tokens": 19717109.0,
|
|
"step": 10710
|
|
},
|
|
{
|
|
"entropy": 5.216282796859741,
|
|
"epoch": 0.8950050116939525,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004926072166771884,
|
|
"loss": 4.8931,
|
|
"mean_token_accuracy": 0.22160657048225402,
|
|
"num_tokens": 19725585.0,
|
|
"step": 10715
|
|
},
|
|
{
|
|
"entropy": 5.171828651428223,
|
|
"epoch": 0.8954226528566656,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004925996462827895,
|
|
"loss": 4.8639,
|
|
"mean_token_accuracy": 0.21658680438995362,
|
|
"num_tokens": 19733502.0,
|
|
"step": 10720
|
|
},
|
|
{
|
|
"entropy": 5.2768614292144775,
|
|
"epoch": 0.8958402940193786,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004925920720790466,
|
|
"loss": 4.9806,
|
|
"mean_token_accuracy": 0.20507069379091264,
|
|
"num_tokens": 19742926.0,
|
|
"step": 10725
|
|
},
|
|
{
|
|
"entropy": 5.205672931671143,
|
|
"epoch": 0.8962579351820915,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004925844940660928,
|
|
"loss": 4.9623,
|
|
"mean_token_accuracy": 0.21342433393001556,
|
|
"num_tokens": 19752488.0,
|
|
"step": 10730
|
|
},
|
|
{
|
|
"entropy": 5.310868167877198,
|
|
"epoch": 0.8966755763448045,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004925769122440606,
|
|
"loss": 5.0981,
|
|
"mean_token_accuracy": 0.19976469725370408,
|
|
"num_tokens": 19762705.0,
|
|
"step": 10735
|
|
},
|
|
{
|
|
"entropy": 5.170697355270386,
|
|
"epoch": 0.8970932175075176,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004925693266130824,
|
|
"loss": 4.8781,
|
|
"mean_token_accuracy": 0.21835984587669371,
|
|
"num_tokens": 19771156.0,
|
|
"step": 10740
|
|
},
|
|
{
|
|
"entropy": 5.256175756454468,
|
|
"epoch": 0.8975108586702305,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004925617371732914,
|
|
"loss": 4.9358,
|
|
"mean_token_accuracy": 0.20618152767419815,
|
|
"num_tokens": 19780788.0,
|
|
"step": 10745
|
|
},
|
|
{
|
|
"entropy": 5.189788770675659,
|
|
"epoch": 0.8979284998329435,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004925541439248203,
|
|
"loss": 4.9265,
|
|
"mean_token_accuracy": 0.2176087647676468,
|
|
"num_tokens": 19790169.0,
|
|
"step": 10750
|
|
},
|
|
{
|
|
"entropy": 5.373470830917358,
|
|
"epoch": 0.8983461409956566,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000492546546867802,
|
|
"loss": 5.1422,
|
|
"mean_token_accuracy": 0.19242381006479264,
|
|
"num_tokens": 19800249.0,
|
|
"step": 10755
|
|
},
|
|
{
|
|
"entropy": 5.251127243041992,
|
|
"epoch": 0.8987637821583695,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004925389460023696,
|
|
"loss": 4.9958,
|
|
"mean_token_accuracy": 0.2054883360862732,
|
|
"num_tokens": 19809797.0,
|
|
"step": 10760
|
|
},
|
|
{
|
|
"entropy": 5.196225976943969,
|
|
"epoch": 0.8991814233210825,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004925313413286559,
|
|
"loss": 4.8812,
|
|
"mean_token_accuracy": 0.2160322204232216,
|
|
"num_tokens": 19818826.0,
|
|
"step": 10765
|
|
},
|
|
{
|
|
"entropy": 5.269199419021606,
|
|
"epoch": 0.8995990644837956,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004925237328467945,
|
|
"loss": 5.0388,
|
|
"mean_token_accuracy": 0.2077295333147049,
|
|
"num_tokens": 19827947.0,
|
|
"step": 10770
|
|
},
|
|
{
|
|
"entropy": 5.355157375335693,
|
|
"epoch": 0.9000167056465085,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004925161205569182,
|
|
"loss": 5.0569,
|
|
"mean_token_accuracy": 0.20308083146810532,
|
|
"num_tokens": 19835734.0,
|
|
"step": 10775
|
|
},
|
|
{
|
|
"entropy": 5.406469345092773,
|
|
"epoch": 0.9004343468092215,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004925085044591604,
|
|
"loss": 5.1613,
|
|
"mean_token_accuracy": 0.19586416184902192,
|
|
"num_tokens": 19845175.0,
|
|
"step": 10780
|
|
},
|
|
{
|
|
"entropy": 5.2762151718139645,
|
|
"epoch": 0.9008519879719346,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004925008845536544,
|
|
"loss": 4.9804,
|
|
"mean_token_accuracy": 0.20715121924877167,
|
|
"num_tokens": 19853684.0,
|
|
"step": 10785
|
|
},
|
|
{
|
|
"entropy": 5.295101833343506,
|
|
"epoch": 0.9012696291346475,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004924932608405336,
|
|
"loss": 4.982,
|
|
"mean_token_accuracy": 0.20433221459388734,
|
|
"num_tokens": 19862813.0,
|
|
"step": 10790
|
|
},
|
|
{
|
|
"entropy": 5.296811246871949,
|
|
"epoch": 0.9016872702973605,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004924856333199315,
|
|
"loss": 5.0199,
|
|
"mean_token_accuracy": 0.20576008558273315,
|
|
"num_tokens": 19871545.0,
|
|
"step": 10795
|
|
},
|
|
{
|
|
"entropy": 5.279951477050782,
|
|
"epoch": 0.9021049114600735,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004924780019919816,
|
|
"loss": 4.9955,
|
|
"mean_token_accuracy": 0.2054675415158272,
|
|
"num_tokens": 19880060.0,
|
|
"step": 10800
|
|
},
|
|
{
|
|
"entropy": 5.244395399093628,
|
|
"epoch": 0.9025225526227865,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004924703668568174,
|
|
"loss": 5.0211,
|
|
"mean_token_accuracy": 0.20388415306806565,
|
|
"num_tokens": 19889151.0,
|
|
"step": 10805
|
|
},
|
|
{
|
|
"entropy": 5.331202793121338,
|
|
"epoch": 0.9029401937854995,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004924627279145728,
|
|
"loss": 4.97,
|
|
"mean_token_accuracy": 0.20639394074678422,
|
|
"num_tokens": 19898087.0,
|
|
"step": 10810
|
|
},
|
|
{
|
|
"entropy": 5.24865951538086,
|
|
"epoch": 0.9033578349482125,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004924550851653814,
|
|
"loss": 4.965,
|
|
"mean_token_accuracy": 0.21553518921136855,
|
|
"num_tokens": 19906196.0,
|
|
"step": 10815
|
|
},
|
|
{
|
|
"entropy": 5.284704256057739,
|
|
"epoch": 0.9037754761109255,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004924474386093769,
|
|
"loss": 5.0098,
|
|
"mean_token_accuracy": 0.20644852817058562,
|
|
"num_tokens": 19915837.0,
|
|
"step": 10820
|
|
},
|
|
{
|
|
"entropy": 5.2688133239746096,
|
|
"epoch": 0.9041931172736385,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004924397882466933,
|
|
"loss": 5.001,
|
|
"mean_token_accuracy": 0.2050878494977951,
|
|
"num_tokens": 19926012.0,
|
|
"step": 10825
|
|
},
|
|
{
|
|
"entropy": 5.243179082870483,
|
|
"epoch": 0.9046107584363515,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004924321340774644,
|
|
"loss": 4.9628,
|
|
"mean_token_accuracy": 0.2105299010872841,
|
|
"num_tokens": 19935987.0,
|
|
"step": 10830
|
|
},
|
|
{
|
|
"entropy": 5.243394231796264,
|
|
"epoch": 0.9050283995990644,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004924244761018243,
|
|
"loss": 4.9833,
|
|
"mean_token_accuracy": 0.204965278506279,
|
|
"num_tokens": 19945865.0,
|
|
"step": 10835
|
|
},
|
|
{
|
|
"entropy": 5.31999363899231,
|
|
"epoch": 0.9054460407617775,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000492416814319907,
|
|
"loss": 5.0726,
|
|
"mean_token_accuracy": 0.2043199881911278,
|
|
"num_tokens": 19954824.0,
|
|
"step": 10840
|
|
},
|
|
{
|
|
"entropy": 5.234289121627808,
|
|
"epoch": 0.9058636819244905,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004924091487318468,
|
|
"loss": 4.9692,
|
|
"mean_token_accuracy": 0.2030353620648384,
|
|
"num_tokens": 19964740.0,
|
|
"step": 10845
|
|
},
|
|
{
|
|
"entropy": 5.232080554962158,
|
|
"epoch": 0.9062813230872034,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004924014793377776,
|
|
"loss": 4.9289,
|
|
"mean_token_accuracy": 0.21160493344068526,
|
|
"num_tokens": 19974310.0,
|
|
"step": 10850
|
|
},
|
|
{
|
|
"entropy": 5.222050380706787,
|
|
"epoch": 0.9066989642499165,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004923938061378339,
|
|
"loss": 4.8703,
|
|
"mean_token_accuracy": 0.21050190329551696,
|
|
"num_tokens": 19982943.0,
|
|
"step": 10855
|
|
},
|
|
{
|
|
"entropy": 5.250167369842529,
|
|
"epoch": 0.9071166054126295,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004923861291321499,
|
|
"loss": 4.9714,
|
|
"mean_token_accuracy": 0.20778299868106842,
|
|
"num_tokens": 19991971.0,
|
|
"step": 10860
|
|
},
|
|
{
|
|
"entropy": 5.336087942123413,
|
|
"epoch": 0.9075342465753424,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004923784483208601,
|
|
"loss": 5.037,
|
|
"mean_token_accuracy": 0.19941984713077546,
|
|
"num_tokens": 20001491.0,
|
|
"step": 10865
|
|
},
|
|
{
|
|
"entropy": 5.242482233047485,
|
|
"epoch": 0.9079518877380555,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004923707637040989,
|
|
"loss": 4.8845,
|
|
"mean_token_accuracy": 0.21396315693855286,
|
|
"num_tokens": 20010605.0,
|
|
"step": 10870
|
|
},
|
|
{
|
|
"entropy": 5.121878004074096,
|
|
"epoch": 0.9083695289007685,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004923630752820008,
|
|
"loss": 4.7886,
|
|
"mean_token_accuracy": 0.21492691487073898,
|
|
"num_tokens": 20019291.0,
|
|
"step": 10875
|
|
},
|
|
{
|
|
"entropy": 5.222338056564331,
|
|
"epoch": 0.9087871700634814,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004923553830547004,
|
|
"loss": 5.085,
|
|
"mean_token_accuracy": 0.195840784907341,
|
|
"num_tokens": 20029048.0,
|
|
"step": 10880
|
|
},
|
|
{
|
|
"entropy": 5.309308242797852,
|
|
"epoch": 0.9092048112261945,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004923476870223324,
|
|
"loss": 5.0307,
|
|
"mean_token_accuracy": 0.20123770833015442,
|
|
"num_tokens": 20037878.0,
|
|
"step": 10885
|
|
},
|
|
{
|
|
"entropy": 5.2229204177856445,
|
|
"epoch": 0.9096224523889075,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004923399871850315,
|
|
"loss": 4.9588,
|
|
"mean_token_accuracy": 0.2096124067902565,
|
|
"num_tokens": 20046662.0,
|
|
"step": 10890
|
|
},
|
|
{
|
|
"entropy": 5.18960976600647,
|
|
"epoch": 0.9100400935516204,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004923322835429326,
|
|
"loss": 4.9292,
|
|
"mean_token_accuracy": 0.21052929162979125,
|
|
"num_tokens": 20055329.0,
|
|
"step": 10895
|
|
},
|
|
{
|
|
"entropy": 5.148437118530273,
|
|
"epoch": 0.9104577347143334,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004923245760961704,
|
|
"loss": 4.8406,
|
|
"mean_token_accuracy": 0.21717104613780974,
|
|
"num_tokens": 20064024.0,
|
|
"step": 10900
|
|
},
|
|
{
|
|
"entropy": 5.2552488327026365,
|
|
"epoch": 0.9108753758770465,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004923168648448799,
|
|
"loss": 5.0419,
|
|
"mean_token_accuracy": 0.20019593983888626,
|
|
"num_tokens": 20073022.0,
|
|
"step": 10905
|
|
},
|
|
{
|
|
"entropy": 5.291287231445312,
|
|
"epoch": 0.9112930170397594,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004923091497891961,
|
|
"loss": 5.0044,
|
|
"mean_token_accuracy": 0.20060400515794755,
|
|
"num_tokens": 20081495.0,
|
|
"step": 10910
|
|
},
|
|
{
|
|
"entropy": 5.279441165924072,
|
|
"epoch": 0.9117106582024724,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004923014309292541,
|
|
"loss": 4.9457,
|
|
"mean_token_accuracy": 0.21415825486183165,
|
|
"num_tokens": 20090545.0,
|
|
"step": 10915
|
|
},
|
|
{
|
|
"entropy": 5.255401611328125,
|
|
"epoch": 0.9121282993651855,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000492293708265189,
|
|
"loss": 5.0246,
|
|
"mean_token_accuracy": 0.20592290461063384,
|
|
"num_tokens": 20100236.0,
|
|
"step": 10920
|
|
},
|
|
{
|
|
"entropy": 5.190516519546509,
|
|
"epoch": 0.9125459405278984,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004922859817971359,
|
|
"loss": 4.9642,
|
|
"mean_token_accuracy": 0.210262168943882,
|
|
"num_tokens": 20109522.0,
|
|
"step": 10925
|
|
},
|
|
{
|
|
"entropy": 5.235836505889893,
|
|
"epoch": 0.9129635816906114,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004922782515252302,
|
|
"loss": 4.8962,
|
|
"mean_token_accuracy": 0.21298593133687974,
|
|
"num_tokens": 20118248.0,
|
|
"step": 10930
|
|
},
|
|
{
|
|
"entropy": 5.200658464431763,
|
|
"epoch": 0.9133812228533245,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004922705174496072,
|
|
"loss": 4.9585,
|
|
"mean_token_accuracy": 0.20346722900867462,
|
|
"num_tokens": 20127096.0,
|
|
"step": 10935
|
|
},
|
|
{
|
|
"entropy": 5.214232921600342,
|
|
"epoch": 0.9137988640160374,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004922627795704022,
|
|
"loss": 4.9587,
|
|
"mean_token_accuracy": 0.20433655232191086,
|
|
"num_tokens": 20136815.0,
|
|
"step": 10940
|
|
},
|
|
{
|
|
"entropy": 5.261284971237183,
|
|
"epoch": 0.9142165051787504,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004922550378877507,
|
|
"loss": 4.9542,
|
|
"mean_token_accuracy": 0.2149657592177391,
|
|
"num_tokens": 20145455.0,
|
|
"step": 10945
|
|
},
|
|
{
|
|
"entropy": 5.284930849075318,
|
|
"epoch": 0.9146341463414634,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004922472924017882,
|
|
"loss": 5.0599,
|
|
"mean_token_accuracy": 0.20481502562761306,
|
|
"num_tokens": 20156139.0,
|
|
"step": 10950
|
|
},
|
|
{
|
|
"entropy": 5.362521553039551,
|
|
"epoch": 0.9150517875041764,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004922395431126506,
|
|
"loss": 5.0348,
|
|
"mean_token_accuracy": 0.20549243092536926,
|
|
"num_tokens": 20166266.0,
|
|
"step": 10955
|
|
},
|
|
{
|
|
"entropy": 5.416420793533325,
|
|
"epoch": 0.9154694286668894,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004922317900204732,
|
|
"loss": 5.0677,
|
|
"mean_token_accuracy": 0.20066986232995987,
|
|
"num_tokens": 20175005.0,
|
|
"step": 10960
|
|
},
|
|
{
|
|
"entropy": 5.168547105789185,
|
|
"epoch": 0.9158870698296024,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004922240331253916,
|
|
"loss": 4.8835,
|
|
"mean_token_accuracy": 0.21400633454322815,
|
|
"num_tokens": 20183488.0,
|
|
"step": 10965
|
|
},
|
|
{
|
|
"entropy": 5.2441362857818605,
|
|
"epoch": 0.9163047109923154,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004922162724275421,
|
|
"loss": 4.9734,
|
|
"mean_token_accuracy": 0.21193478107452393,
|
|
"num_tokens": 20193724.0,
|
|
"step": 10970
|
|
},
|
|
{
|
|
"entropy": 5.263073968887329,
|
|
"epoch": 0.9167223521550284,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004922085079270602,
|
|
"loss": 5.0584,
|
|
"mean_token_accuracy": 0.20677319765090943,
|
|
"num_tokens": 20203733.0,
|
|
"step": 10975
|
|
},
|
|
{
|
|
"entropy": 5.3670989036560055,
|
|
"epoch": 0.9171399933177414,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004922007396240819,
|
|
"loss": 5.0425,
|
|
"mean_token_accuracy": 0.21014897525310516,
|
|
"num_tokens": 20213448.0,
|
|
"step": 10980
|
|
},
|
|
{
|
|
"entropy": 5.320993089675904,
|
|
"epoch": 0.9175576344804544,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004921929675187433,
|
|
"loss": 4.9651,
|
|
"mean_token_accuracy": 0.20755314379930495,
|
|
"num_tokens": 20222837.0,
|
|
"step": 10985
|
|
},
|
|
{
|
|
"entropy": 5.351680946350098,
|
|
"epoch": 0.9179752756431674,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004921851916111802,
|
|
"loss": 5.1355,
|
|
"mean_token_accuracy": 0.1980899006128311,
|
|
"num_tokens": 20232056.0,
|
|
"step": 10990
|
|
},
|
|
{
|
|
"entropy": 5.375345993041992,
|
|
"epoch": 0.9183929168058804,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004921774119015289,
|
|
"loss": 5.0507,
|
|
"mean_token_accuracy": 0.20475190728902817,
|
|
"num_tokens": 20241052.0,
|
|
"step": 10995
|
|
},
|
|
{
|
|
"entropy": 5.37616753578186,
|
|
"epoch": 0.9188105579685933,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004921696283899257,
|
|
"loss": 5.1092,
|
|
"mean_token_accuracy": 0.1991646721959114,
|
|
"num_tokens": 20251015.0,
|
|
"step": 11000
|
|
},
|
|
{
|
|
"entropy": 5.245299911499023,
|
|
"epoch": 0.9192281991313064,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004921618410765067,
|
|
"loss": 4.9514,
|
|
"mean_token_accuracy": 0.20571413040161132,
|
|
"num_tokens": 20259388.0,
|
|
"step": 11005
|
|
},
|
|
{
|
|
"entropy": 5.294223833084106,
|
|
"epoch": 0.9196458402940194,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004921540499614083,
|
|
"loss": 4.9312,
|
|
"mean_token_accuracy": 0.20074452906847,
|
|
"num_tokens": 20268146.0,
|
|
"step": 11010
|
|
},
|
|
{
|
|
"entropy": 5.236671781539917,
|
|
"epoch": 0.9200634814567323,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004921462550447669,
|
|
"loss": 4.9158,
|
|
"mean_token_accuracy": 0.21233065873384477,
|
|
"num_tokens": 20277559.0,
|
|
"step": 11015
|
|
},
|
|
{
|
|
"entropy": 5.266069841384888,
|
|
"epoch": 0.9204811226194454,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004921384563267189,
|
|
"loss": 4.9534,
|
|
"mean_token_accuracy": 0.20886976569890975,
|
|
"num_tokens": 20285661.0,
|
|
"step": 11020
|
|
},
|
|
{
|
|
"entropy": 5.243994903564453,
|
|
"epoch": 0.9208987637821584,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004921306538074008,
|
|
"loss": 5.0358,
|
|
"mean_token_accuracy": 0.20855261087417604,
|
|
"num_tokens": 20294636.0,
|
|
"step": 11025
|
|
},
|
|
{
|
|
"entropy": 5.316732931137085,
|
|
"epoch": 0.9213164049448713,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004921228474869493,
|
|
"loss": 4.9321,
|
|
"mean_token_accuracy": 0.2154439702630043,
|
|
"num_tokens": 20302372.0,
|
|
"step": 11030
|
|
},
|
|
{
|
|
"entropy": 5.293783855438233,
|
|
"epoch": 0.9217340461075844,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000492115037365501,
|
|
"loss": 4.9548,
|
|
"mean_token_accuracy": 0.21032945066690445,
|
|
"num_tokens": 20311974.0,
|
|
"step": 11035
|
|
},
|
|
{
|
|
"entropy": 5.239782476425171,
|
|
"epoch": 0.9221516872702974,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004921072234431925,
|
|
"loss": 4.9744,
|
|
"mean_token_accuracy": 0.2089963212609291,
|
|
"num_tokens": 20321720.0,
|
|
"step": 11040
|
|
},
|
|
{
|
|
"entropy": 5.259523344039917,
|
|
"epoch": 0.9225693284330103,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000492099405720161,
|
|
"loss": 5.0338,
|
|
"mean_token_accuracy": 0.2014230892062187,
|
|
"num_tokens": 20331324.0,
|
|
"step": 11045
|
|
},
|
|
{
|
|
"entropy": 5.395723628997803,
|
|
"epoch": 0.9229869695957233,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004920915841965429,
|
|
"loss": 5.1289,
|
|
"mean_token_accuracy": 0.1988341435790062,
|
|
"num_tokens": 20340921.0,
|
|
"step": 11050
|
|
},
|
|
{
|
|
"entropy": 5.395040130615234,
|
|
"epoch": 0.9234046107584364,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004920837588724753,
|
|
"loss": 4.9965,
|
|
"mean_token_accuracy": 0.20739365220069886,
|
|
"num_tokens": 20349871.0,
|
|
"step": 11055
|
|
},
|
|
{
|
|
"entropy": 5.168009662628174,
|
|
"epoch": 0.9238222519211493,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004920759297480953,
|
|
"loss": 4.7862,
|
|
"mean_token_accuracy": 0.21604011803865433,
|
|
"num_tokens": 20359171.0,
|
|
"step": 11060
|
|
},
|
|
{
|
|
"entropy": 5.255016708374024,
|
|
"epoch": 0.9242398930838623,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004920680968235397,
|
|
"loss": 4.9953,
|
|
"mean_token_accuracy": 0.2181284636259079,
|
|
"num_tokens": 20367779.0,
|
|
"step": 11065
|
|
},
|
|
{
|
|
"entropy": 5.226720952987671,
|
|
"epoch": 0.9246575342465754,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004920602600989459,
|
|
"loss": 4.907,
|
|
"mean_token_accuracy": 0.21906644403934478,
|
|
"num_tokens": 20377568.0,
|
|
"step": 11070
|
|
},
|
|
{
|
|
"entropy": 5.34415636062622,
|
|
"epoch": 0.9250751754092883,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004920524195744509,
|
|
"loss": 5.046,
|
|
"mean_token_accuracy": 0.2030154287815094,
|
|
"num_tokens": 20385915.0,
|
|
"step": 11075
|
|
},
|
|
{
|
|
"entropy": 5.228349399566651,
|
|
"epoch": 0.9254928165720013,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004920445752501921,
|
|
"loss": 4.9184,
|
|
"mean_token_accuracy": 0.21054769605398177,
|
|
"num_tokens": 20394877.0,
|
|
"step": 11080
|
|
},
|
|
{
|
|
"entropy": 5.249534225463867,
|
|
"epoch": 0.9259104577347144,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004920367271263066,
|
|
"loss": 4.9262,
|
|
"mean_token_accuracy": 0.2117575228214264,
|
|
"num_tokens": 20403741.0,
|
|
"step": 11085
|
|
},
|
|
{
|
|
"entropy": 5.280802917480469,
|
|
"epoch": 0.9263280988974273,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004920288752029321,
|
|
"loss": 4.9683,
|
|
"mean_token_accuracy": 0.20721979588270187,
|
|
"num_tokens": 20412702.0,
|
|
"step": 11090
|
|
},
|
|
{
|
|
"entropy": 5.27918553352356,
|
|
"epoch": 0.9267457400601403,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004920210194802059,
|
|
"loss": 4.9889,
|
|
"mean_token_accuracy": 0.2074853777885437,
|
|
"num_tokens": 20421776.0,
|
|
"step": 11095
|
|
},
|
|
{
|
|
"entropy": 5.303801488876343,
|
|
"epoch": 0.9271633812228534,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004920131599582654,
|
|
"loss": 5.0949,
|
|
"mean_token_accuracy": 0.19518010467290878,
|
|
"num_tokens": 20432204.0,
|
|
"step": 11100
|
|
},
|
|
{
|
|
"entropy": 5.315025472640992,
|
|
"epoch": 0.9275810223855663,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004920052966372485,
|
|
"loss": 4.9951,
|
|
"mean_token_accuracy": 0.19930322617292404,
|
|
"num_tokens": 20441344.0,
|
|
"step": 11105
|
|
},
|
|
{
|
|
"entropy": 5.247663974761963,
|
|
"epoch": 0.9279986635482793,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004919974295172926,
|
|
"loss": 4.909,
|
|
"mean_token_accuracy": 0.21379464715719224,
|
|
"num_tokens": 20449800.0,
|
|
"step": 11110
|
|
},
|
|
{
|
|
"entropy": 5.231588459014892,
|
|
"epoch": 0.9284163047109923,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004919895585985353,
|
|
"loss": 4.8505,
|
|
"mean_token_accuracy": 0.22388574630022048,
|
|
"num_tokens": 20458326.0,
|
|
"step": 11115
|
|
},
|
|
{
|
|
"entropy": 5.2991370677948,
|
|
"epoch": 0.9288339458737053,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004919816838811149,
|
|
"loss": 5.1211,
|
|
"mean_token_accuracy": 0.19915229082107544,
|
|
"num_tokens": 20468050.0,
|
|
"step": 11120
|
|
},
|
|
{
|
|
"entropy": 5.266911745071411,
|
|
"epoch": 0.9292515870364183,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004919738053651687,
|
|
"loss": 4.8833,
|
|
"mean_token_accuracy": 0.21326978355646134,
|
|
"num_tokens": 20477046.0,
|
|
"step": 11125
|
|
},
|
|
{
|
|
"entropy": 5.272528457641601,
|
|
"epoch": 0.9296692281991313,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000491965923050835,
|
|
"loss": 4.9921,
|
|
"mean_token_accuracy": 0.20975257754325866,
|
|
"num_tokens": 20486228.0,
|
|
"step": 11130
|
|
},
|
|
{
|
|
"entropy": 5.300780534744263,
|
|
"epoch": 0.9300868693618443,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004919580369382516,
|
|
"loss": 5.0064,
|
|
"mean_token_accuracy": 0.20058976858854294,
|
|
"num_tokens": 20494764.0,
|
|
"step": 11135
|
|
},
|
|
{
|
|
"entropy": 5.278902912139893,
|
|
"epoch": 0.9305045105245573,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004919501470275567,
|
|
"loss": 4.9044,
|
|
"mean_token_accuracy": 0.21128441244363785,
|
|
"num_tokens": 20502805.0,
|
|
"step": 11140
|
|
},
|
|
{
|
|
"entropy": 5.244833755493164,
|
|
"epoch": 0.9309221516872703,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004919422533188882,
|
|
"loss": 4.9672,
|
|
"mean_token_accuracy": 0.20627895295619963,
|
|
"num_tokens": 20512322.0,
|
|
"step": 11145
|
|
},
|
|
{
|
|
"entropy": 5.2312281131744385,
|
|
"epoch": 0.9313397928499833,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004919343558123845,
|
|
"loss": 4.9584,
|
|
"mean_token_accuracy": 0.20781377851963043,
|
|
"num_tokens": 20520680.0,
|
|
"step": 11150
|
|
},
|
|
{
|
|
"entropy": 5.217152070999146,
|
|
"epoch": 0.9317574340126963,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004919264545081838,
|
|
"loss": 4.8278,
|
|
"mean_token_accuracy": 0.22223591953516006,
|
|
"num_tokens": 20528864.0,
|
|
"step": 11155
|
|
},
|
|
{
|
|
"entropy": 5.281461763381958,
|
|
"epoch": 0.9321750751754093,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004919185494064244,
|
|
"loss": 4.9528,
|
|
"mean_token_accuracy": 0.20506721138954162,
|
|
"num_tokens": 20538195.0,
|
|
"step": 11160
|
|
},
|
|
{
|
|
"entropy": 5.234458160400391,
|
|
"epoch": 0.9325927163381222,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004919106405072446,
|
|
"loss": 4.9982,
|
|
"mean_token_accuracy": 0.20177790373563767,
|
|
"num_tokens": 20547312.0,
|
|
"step": 11165
|
|
},
|
|
{
|
|
"entropy": 5.277944707870484,
|
|
"epoch": 0.9330103575008353,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000491902727810783,
|
|
"loss": 5.0296,
|
|
"mean_token_accuracy": 0.19958221316337585,
|
|
"num_tokens": 20557184.0,
|
|
"step": 11170
|
|
},
|
|
{
|
|
"entropy": 5.263872766494751,
|
|
"epoch": 0.9334279986635483,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004918948113171781,
|
|
"loss": 4.9558,
|
|
"mean_token_accuracy": 0.2094264268875122,
|
|
"num_tokens": 20565819.0,
|
|
"step": 11175
|
|
},
|
|
{
|
|
"entropy": 5.245273160934448,
|
|
"epoch": 0.9338456398262612,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004918868910265684,
|
|
"loss": 5.0102,
|
|
"mean_token_accuracy": 0.21310826241970063,
|
|
"num_tokens": 20574761.0,
|
|
"step": 11180
|
|
},
|
|
{
|
|
"entropy": 5.353975248336792,
|
|
"epoch": 0.9342632809889743,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004918789669390927,
|
|
"loss": 5.0708,
|
|
"mean_token_accuracy": 0.19999473989009858,
|
|
"num_tokens": 20584003.0,
|
|
"step": 11185
|
|
},
|
|
{
|
|
"entropy": 5.3034553050994875,
|
|
"epoch": 0.9346809221516873,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004918710390548895,
|
|
"loss": 4.9182,
|
|
"mean_token_accuracy": 0.20792448669672012,
|
|
"num_tokens": 20593123.0,
|
|
"step": 11190
|
|
},
|
|
{
|
|
"entropy": 5.260336971282959,
|
|
"epoch": 0.9350985633144002,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004918631073740977,
|
|
"loss": 5.0135,
|
|
"mean_token_accuracy": 0.2061988204717636,
|
|
"num_tokens": 20602582.0,
|
|
"step": 11195
|
|
},
|
|
{
|
|
"entropy": 5.245416355133057,
|
|
"epoch": 0.9355162044771133,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004918551718968562,
|
|
"loss": 4.9022,
|
|
"mean_token_accuracy": 0.2127738282084465,
|
|
"num_tokens": 20611681.0,
|
|
"step": 11200
|
|
},
|
|
{
|
|
"entropy": 5.222401571273804,
|
|
"epoch": 0.9359338456398263,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000491847232623304,
|
|
"loss": 4.973,
|
|
"mean_token_accuracy": 0.21008606553077697,
|
|
"num_tokens": 20620671.0,
|
|
"step": 11205
|
|
},
|
|
{
|
|
"entropy": 5.255436658859253,
|
|
"epoch": 0.9363514868025392,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004918392895535798,
|
|
"loss": 4.951,
|
|
"mean_token_accuracy": 0.20708223581314086,
|
|
"num_tokens": 20629986.0,
|
|
"step": 11210
|
|
},
|
|
{
|
|
"entropy": 5.234728813171387,
|
|
"epoch": 0.9367691279652522,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000491831342687823,
|
|
"loss": 4.9395,
|
|
"mean_token_accuracy": 0.20146991908550263,
|
|
"num_tokens": 20639274.0,
|
|
"step": 11215
|
|
},
|
|
{
|
|
"entropy": 5.264416837692261,
|
|
"epoch": 0.9371867691279653,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004918233920261723,
|
|
"loss": 4.9448,
|
|
"mean_token_accuracy": 0.2100604459643364,
|
|
"num_tokens": 20647753.0,
|
|
"step": 11220
|
|
},
|
|
{
|
|
"entropy": 5.1743621826171875,
|
|
"epoch": 0.9376044102906782,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004918154375687673,
|
|
"loss": 4.8645,
|
|
"mean_token_accuracy": 0.2156805217266083,
|
|
"num_tokens": 20656226.0,
|
|
"step": 11225
|
|
},
|
|
{
|
|
"entropy": 5.183247852325439,
|
|
"epoch": 0.9380220514533912,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004918074793157472,
|
|
"loss": 4.87,
|
|
"mean_token_accuracy": 0.2159823328256607,
|
|
"num_tokens": 20664682.0,
|
|
"step": 11230
|
|
},
|
|
{
|
|
"entropy": 5.283345317840576,
|
|
"epoch": 0.9384396926161043,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004917995172672511,
|
|
"loss": 4.9607,
|
|
"mean_token_accuracy": 0.2104622170329094,
|
|
"num_tokens": 20672909.0,
|
|
"step": 11235
|
|
},
|
|
{
|
|
"entropy": 5.155306100845337,
|
|
"epoch": 0.9388573337788172,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004917915514234184,
|
|
"loss": 4.8271,
|
|
"mean_token_accuracy": 0.21582880169153212,
|
|
"num_tokens": 20681316.0,
|
|
"step": 11240
|
|
},
|
|
{
|
|
"entropy": 5.27658634185791,
|
|
"epoch": 0.9392749749415302,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004917835817843887,
|
|
"loss": 4.9374,
|
|
"mean_token_accuracy": 0.20264142453670503,
|
|
"num_tokens": 20690360.0,
|
|
"step": 11245
|
|
},
|
|
{
|
|
"entropy": 5.293812417984009,
|
|
"epoch": 0.9396926161042433,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004917756083503014,
|
|
"loss": 5.0009,
|
|
"mean_token_accuracy": 0.203963802754879,
|
|
"num_tokens": 20700398.0,
|
|
"step": 11250
|
|
},
|
|
{
|
|
"entropy": 5.320089101791382,
|
|
"epoch": 0.9401102572669562,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004917676311212962,
|
|
"loss": 5.073,
|
|
"mean_token_accuracy": 0.20118411481380463,
|
|
"num_tokens": 20709705.0,
|
|
"step": 11255
|
|
},
|
|
{
|
|
"entropy": 5.200478363037109,
|
|
"epoch": 0.9405278984296692,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004917596500975127,
|
|
"loss": 4.8916,
|
|
"mean_token_accuracy": 0.21248382180929185,
|
|
"num_tokens": 20717774.0,
|
|
"step": 11260
|
|
},
|
|
{
|
|
"entropy": 5.277456903457642,
|
|
"epoch": 0.9409455395923823,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004917516652790907,
|
|
"loss": 5.031,
|
|
"mean_token_accuracy": 0.20552293211221695,
|
|
"num_tokens": 20725966.0,
|
|
"step": 11265
|
|
},
|
|
{
|
|
"entropy": 5.307353353500366,
|
|
"epoch": 0.9413631807550952,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004917436766661697,
|
|
"loss": 4.9427,
|
|
"mean_token_accuracy": 0.20830944180488586,
|
|
"num_tokens": 20735254.0,
|
|
"step": 11270
|
|
},
|
|
{
|
|
"entropy": 5.240226364135742,
|
|
"epoch": 0.9417808219178082,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00049173568425889,
|
|
"loss": 4.8485,
|
|
"mean_token_accuracy": 0.2170790359377861,
|
|
"num_tokens": 20743331.0,
|
|
"step": 11275
|
|
},
|
|
{
|
|
"entropy": 5.259325122833252,
|
|
"epoch": 0.9421984630805212,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004917276880573911,
|
|
"loss": 4.975,
|
|
"mean_token_accuracy": 0.20236670076847077,
|
|
"num_tokens": 20753966.0,
|
|
"step": 11280
|
|
},
|
|
{
|
|
"entropy": 5.275627517700196,
|
|
"epoch": 0.9426161042432342,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004917196880618132,
|
|
"loss": 4.9168,
|
|
"mean_token_accuracy": 0.21448712795972824,
|
|
"num_tokens": 20762608.0,
|
|
"step": 11285
|
|
},
|
|
{
|
|
"entropy": 5.192218828201294,
|
|
"epoch": 0.9430337454059472,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004917116842722962,
|
|
"loss": 4.8757,
|
|
"mean_token_accuracy": 0.21021183729171752,
|
|
"num_tokens": 20771194.0,
|
|
"step": 11290
|
|
},
|
|
{
|
|
"entropy": 5.259437608718872,
|
|
"epoch": 0.9434513865686602,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004917036766889804,
|
|
"loss": 4.9802,
|
|
"mean_token_accuracy": 0.20911021232604982,
|
|
"num_tokens": 20779700.0,
|
|
"step": 11295
|
|
},
|
|
{
|
|
"entropy": 5.316693210601807,
|
|
"epoch": 0.9438690277313732,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004916956653120058,
|
|
"loss": 5.0725,
|
|
"mean_token_accuracy": 0.20024692565202712,
|
|
"num_tokens": 20788117.0,
|
|
"step": 11300
|
|
},
|
|
{
|
|
"entropy": 5.264907312393189,
|
|
"epoch": 0.9442866688940862,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004916876501415129,
|
|
"loss": 5.0558,
|
|
"mean_token_accuracy": 0.20022192299365998,
|
|
"num_tokens": 20798041.0,
|
|
"step": 11305
|
|
},
|
|
{
|
|
"entropy": 5.293879556655884,
|
|
"epoch": 0.9447043100567992,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004916796311776417,
|
|
"loss": 5.0026,
|
|
"mean_token_accuracy": 0.19762389063835145,
|
|
"num_tokens": 20807423.0,
|
|
"step": 11310
|
|
},
|
|
{
|
|
"entropy": 5.250337839126587,
|
|
"epoch": 0.9451219512195121,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004916716084205328,
|
|
"loss": 4.8904,
|
|
"mean_token_accuracy": 0.2176752507686615,
|
|
"num_tokens": 20816727.0,
|
|
"step": 11315
|
|
},
|
|
{
|
|
"entropy": 5.270186901092529,
|
|
"epoch": 0.9455395923822252,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004916635818703266,
|
|
"loss": 4.9121,
|
|
"mean_token_accuracy": 0.20919148176908492,
|
|
"num_tokens": 20824855.0,
|
|
"step": 11320
|
|
},
|
|
{
|
|
"entropy": 5.197906923294068,
|
|
"epoch": 0.9459572335449382,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004916555515271635,
|
|
"loss": 4.9263,
|
|
"mean_token_accuracy": 0.21446057111024858,
|
|
"num_tokens": 20833096.0,
|
|
"step": 11325
|
|
},
|
|
{
|
|
"entropy": 5.254100799560547,
|
|
"epoch": 0.9463748747076511,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004916475173911844,
|
|
"loss": 4.8777,
|
|
"mean_token_accuracy": 0.21171997338533402,
|
|
"num_tokens": 20842398.0,
|
|
"step": 11330
|
|
},
|
|
{
|
|
"entropy": 5.386715650558472,
|
|
"epoch": 0.9467925158703642,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004916394794625296,
|
|
"loss": 5.0932,
|
|
"mean_token_accuracy": 0.19939033687114716,
|
|
"num_tokens": 20851745.0,
|
|
"step": 11335
|
|
},
|
|
{
|
|
"entropy": 5.422706842422485,
|
|
"epoch": 0.9472101570330772,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004916314377413399,
|
|
"loss": 5.0041,
|
|
"mean_token_accuracy": 0.20473885238170625,
|
|
"num_tokens": 20860935.0,
|
|
"step": 11340
|
|
},
|
|
{
|
|
"entropy": 5.305401611328125,
|
|
"epoch": 0.9476277981957901,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004916233922277562,
|
|
"loss": 5.0025,
|
|
"mean_token_accuracy": 0.20276060998439788,
|
|
"num_tokens": 20871088.0,
|
|
"step": 11345
|
|
},
|
|
{
|
|
"entropy": 5.244873189926148,
|
|
"epoch": 0.9480454393585032,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004916153429219192,
|
|
"loss": 5.0159,
|
|
"mean_token_accuracy": 0.21051167249679564,
|
|
"num_tokens": 20879313.0,
|
|
"step": 11350
|
|
},
|
|
{
|
|
"entropy": 5.275855207443238,
|
|
"epoch": 0.9484630805212162,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004916072898239699,
|
|
"loss": 4.9565,
|
|
"mean_token_accuracy": 0.20832324475049974,
|
|
"num_tokens": 20888392.0,
|
|
"step": 11355
|
|
},
|
|
{
|
|
"entropy": 5.336981391906738,
|
|
"epoch": 0.9488807216839291,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004915992329340493,
|
|
"loss": 5.0598,
|
|
"mean_token_accuracy": 0.19961524307727813,
|
|
"num_tokens": 20897456.0,
|
|
"step": 11360
|
|
},
|
|
{
|
|
"entropy": 5.292699527740479,
|
|
"epoch": 0.9492983628466422,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004915911722522984,
|
|
"loss": 4.9905,
|
|
"mean_token_accuracy": 0.20827175676822662,
|
|
"num_tokens": 20906621.0,
|
|
"step": 11365
|
|
},
|
|
{
|
|
"entropy": 5.404400825500488,
|
|
"epoch": 0.9497160040093552,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004915831077788583,
|
|
"loss": 5.1709,
|
|
"mean_token_accuracy": 0.19984681457281112,
|
|
"num_tokens": 20916929.0,
|
|
"step": 11370
|
|
},
|
|
{
|
|
"entropy": 5.30355224609375,
|
|
"epoch": 0.9501336451720681,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004915750395138702,
|
|
"loss": 4.9905,
|
|
"mean_token_accuracy": 0.20681142508983613,
|
|
"num_tokens": 20926028.0,
|
|
"step": 11375
|
|
},
|
|
{
|
|
"entropy": 5.324733066558838,
|
|
"epoch": 0.9505512863347811,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004915669674574754,
|
|
"loss": 5.0682,
|
|
"mean_token_accuracy": 0.19354701191186904,
|
|
"num_tokens": 20935516.0,
|
|
"step": 11380
|
|
},
|
|
{
|
|
"entropy": 5.242721176147461,
|
|
"epoch": 0.9509689274974942,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004915588916098151,
|
|
"loss": 4.8652,
|
|
"mean_token_accuracy": 0.21642664074897766,
|
|
"num_tokens": 20944100.0,
|
|
"step": 11385
|
|
},
|
|
{
|
|
"entropy": 5.259535837173462,
|
|
"epoch": 0.9513865686602071,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004915508119710307,
|
|
"loss": 5.0107,
|
|
"mean_token_accuracy": 0.20819492787122726,
|
|
"num_tokens": 20953733.0,
|
|
"step": 11390
|
|
},
|
|
{
|
|
"entropy": 5.335413551330566,
|
|
"epoch": 0.9518042098229201,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004915427285412636,
|
|
"loss": 5.0196,
|
|
"mean_token_accuracy": 0.20083789974451066,
|
|
"num_tokens": 20962413.0,
|
|
"step": 11395
|
|
},
|
|
{
|
|
"entropy": 5.212759780883789,
|
|
"epoch": 0.9522218509856332,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004915346413206555,
|
|
"loss": 4.8859,
|
|
"mean_token_accuracy": 0.21609130054712294,
|
|
"num_tokens": 20971172.0,
|
|
"step": 11400
|
|
},
|
|
{
|
|
"entropy": 5.236460828781128,
|
|
"epoch": 0.9526394921483461,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004915265503093478,
|
|
"loss": 4.8955,
|
|
"mean_token_accuracy": 0.2137727677822113,
|
|
"num_tokens": 20979450.0,
|
|
"step": 11405
|
|
},
|
|
{
|
|
"entropy": 5.258274126052856,
|
|
"epoch": 0.9530571333110591,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004915184555074824,
|
|
"loss": 4.9657,
|
|
"mean_token_accuracy": 0.2026229605078697,
|
|
"num_tokens": 20988518.0,
|
|
"step": 11410
|
|
},
|
|
{
|
|
"entropy": 5.405281448364258,
|
|
"epoch": 0.9534747744737722,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004915103569152005,
|
|
"loss": 5.1327,
|
|
"mean_token_accuracy": 0.19898025393486024,
|
|
"num_tokens": 20998721.0,
|
|
"step": 11415
|
|
},
|
|
{
|
|
"entropy": 5.330988502502441,
|
|
"epoch": 0.9538924156364851,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004915022545326444,
|
|
"loss": 5.0066,
|
|
"mean_token_accuracy": 0.21241801530122756,
|
|
"num_tokens": 21008007.0,
|
|
"step": 11420
|
|
},
|
|
{
|
|
"entropy": 5.276477861404419,
|
|
"epoch": 0.9543100567991981,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004914941483599558,
|
|
"loss": 5.0958,
|
|
"mean_token_accuracy": 0.20037966519594191,
|
|
"num_tokens": 21017199.0,
|
|
"step": 11425
|
|
},
|
|
{
|
|
"entropy": 5.183076667785644,
|
|
"epoch": 0.9547276979619111,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004914860383972763,
|
|
"loss": 4.8931,
|
|
"mean_token_accuracy": 0.2137138217687607,
|
|
"num_tokens": 21025571.0,
|
|
"step": 11430
|
|
},
|
|
{
|
|
"entropy": 5.289412260055542,
|
|
"epoch": 0.9551453391246241,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004914779246447483,
|
|
"loss": 4.9792,
|
|
"mean_token_accuracy": 0.2093399241566658,
|
|
"num_tokens": 21035040.0,
|
|
"step": 11435
|
|
},
|
|
{
|
|
"entropy": 5.3084413528442385,
|
|
"epoch": 0.9555629802873371,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004914698071025136,
|
|
"loss": 5.0034,
|
|
"mean_token_accuracy": 0.2120872989296913,
|
|
"num_tokens": 21044018.0,
|
|
"step": 11440
|
|
},
|
|
{
|
|
"entropy": 5.21974196434021,
|
|
"epoch": 0.9559806214500501,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004914616857707143,
|
|
"loss": 4.9043,
|
|
"mean_token_accuracy": 0.2146401211619377,
|
|
"num_tokens": 21052489.0,
|
|
"step": 11445
|
|
},
|
|
{
|
|
"entropy": 5.26521406173706,
|
|
"epoch": 0.9563982626127631,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004914535606494927,
|
|
"loss": 4.9808,
|
|
"mean_token_accuracy": 0.21472277343273163,
|
|
"num_tokens": 21061153.0,
|
|
"step": 11450
|
|
},
|
|
{
|
|
"entropy": 5.219671678543091,
|
|
"epoch": 0.9568159037754761,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000491445431738991,
|
|
"loss": 4.8714,
|
|
"mean_token_accuracy": 0.2129037097096443,
|
|
"num_tokens": 21069671.0,
|
|
"step": 11455
|
|
},
|
|
{
|
|
"entropy": 5.3590563297271725,
|
|
"epoch": 0.9572335449381891,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004914372990393515,
|
|
"loss": 5.165,
|
|
"mean_token_accuracy": 0.19806600660085677,
|
|
"num_tokens": 21079339.0,
|
|
"step": 11460
|
|
},
|
|
{
|
|
"entropy": 5.279627990722656,
|
|
"epoch": 0.957651186100902,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004914291625507164,
|
|
"loss": 4.8672,
|
|
"mean_token_accuracy": 0.2156984180212021,
|
|
"num_tokens": 21087868.0,
|
|
"step": 11465
|
|
},
|
|
{
|
|
"entropy": 5.279353380203247,
|
|
"epoch": 0.9580688272636151,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004914210222732284,
|
|
"loss": 4.964,
|
|
"mean_token_accuracy": 0.21369007378816604,
|
|
"num_tokens": 21096258.0,
|
|
"step": 11470
|
|
},
|
|
{
|
|
"entropy": 5.254007291793823,
|
|
"epoch": 0.9584864684263281,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004914128782070299,
|
|
"loss": 5.0058,
|
|
"mean_token_accuracy": 0.20108014941215516,
|
|
"num_tokens": 21104504.0,
|
|
"step": 11475
|
|
},
|
|
{
|
|
"entropy": 5.296658372879028,
|
|
"epoch": 0.958904109589041,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004914047303522636,
|
|
"loss": 4.9295,
|
|
"mean_token_accuracy": 0.21082594692707063,
|
|
"num_tokens": 21114402.0,
|
|
"step": 11480
|
|
},
|
|
{
|
|
"entropy": 5.259076309204102,
|
|
"epoch": 0.9593217507517541,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004913965787090718,
|
|
"loss": 4.9438,
|
|
"mean_token_accuracy": 0.20675256103277206,
|
|
"num_tokens": 21123572.0,
|
|
"step": 11485
|
|
},
|
|
{
|
|
"entropy": 5.332728099822998,
|
|
"epoch": 0.9597393919144671,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004913884232775974,
|
|
"loss": 5.158,
|
|
"mean_token_accuracy": 0.1938065245747566,
|
|
"num_tokens": 21132385.0,
|
|
"step": 11490
|
|
},
|
|
{
|
|
"entropy": 5.206088066101074,
|
|
"epoch": 0.96015703307718,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004913802640579833,
|
|
"loss": 4.9119,
|
|
"mean_token_accuracy": 0.21479231417179107,
|
|
"num_tokens": 21140383.0,
|
|
"step": 11495
|
|
},
|
|
{
|
|
"entropy": 5.301038932800293,
|
|
"epoch": 0.9605746742398931,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004913721010503722,
|
|
"loss": 5.0072,
|
|
"mean_token_accuracy": 0.20521082133054733,
|
|
"num_tokens": 21149793.0,
|
|
"step": 11500
|
|
},
|
|
{
|
|
"entropy": 5.288903045654297,
|
|
"epoch": 0.9609923154026061,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000491363934254907,
|
|
"loss": 4.9917,
|
|
"mean_token_accuracy": 0.20400882810354232,
|
|
"num_tokens": 21158955.0,
|
|
"step": 11505
|
|
},
|
|
{
|
|
"entropy": 5.334828090667725,
|
|
"epoch": 0.961409956565319,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004913557636717307,
|
|
"loss": 4.9866,
|
|
"mean_token_accuracy": 0.20568390786647797,
|
|
"num_tokens": 21167900.0,
|
|
"step": 11510
|
|
},
|
|
{
|
|
"entropy": 5.243389225006103,
|
|
"epoch": 0.9618275977280321,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004913475893009864,
|
|
"loss": 4.9336,
|
|
"mean_token_accuracy": 0.2120940640568733,
|
|
"num_tokens": 21177243.0,
|
|
"step": 11515
|
|
},
|
|
{
|
|
"entropy": 5.269658517837525,
|
|
"epoch": 0.9622452388907451,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000491339411142817,
|
|
"loss": 5.0043,
|
|
"mean_token_accuracy": 0.20148182958364486,
|
|
"num_tokens": 21186118.0,
|
|
"step": 11520
|
|
},
|
|
{
|
|
"entropy": 5.292251396179199,
|
|
"epoch": 0.962662880053458,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004913312291973659,
|
|
"loss": 5.0377,
|
|
"mean_token_accuracy": 0.20238784998655318,
|
|
"num_tokens": 21195032.0,
|
|
"step": 11525
|
|
},
|
|
{
|
|
"entropy": 5.292068815231323,
|
|
"epoch": 0.963080521216171,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004913230434647762,
|
|
"loss": 4.9921,
|
|
"mean_token_accuracy": 0.20474038869142533,
|
|
"num_tokens": 21205388.0,
|
|
"step": 11530
|
|
},
|
|
{
|
|
"entropy": 5.245506715774536,
|
|
"epoch": 0.9634981623788841,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004913148539451912,
|
|
"loss": 4.873,
|
|
"mean_token_accuracy": 0.21146152317523956,
|
|
"num_tokens": 21215181.0,
|
|
"step": 11535
|
|
},
|
|
{
|
|
"entropy": 5.200902986526489,
|
|
"epoch": 0.963915803541597,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004913066606387544,
|
|
"loss": 4.8179,
|
|
"mean_token_accuracy": 0.21586035341024398,
|
|
"num_tokens": 21223668.0,
|
|
"step": 11540
|
|
},
|
|
{
|
|
"entropy": 5.238115549087524,
|
|
"epoch": 0.96433344470431,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000491298463545609,
|
|
"loss": 4.9285,
|
|
"mean_token_accuracy": 0.20830414593219757,
|
|
"num_tokens": 21232448.0,
|
|
"step": 11545
|
|
},
|
|
{
|
|
"entropy": 5.219215250015258,
|
|
"epoch": 0.9647510858670231,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004912902626658988,
|
|
"loss": 4.9242,
|
|
"mean_token_accuracy": 0.20706440210342408,
|
|
"num_tokens": 21240777.0,
|
|
"step": 11550
|
|
},
|
|
{
|
|
"entropy": 5.305804061889648,
|
|
"epoch": 0.965168727029736,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004912820579997672,
|
|
"loss": 5.0553,
|
|
"mean_token_accuracy": 0.19662414193153382,
|
|
"num_tokens": 21248803.0,
|
|
"step": 11555
|
|
},
|
|
{
|
|
"entropy": 5.337806940078735,
|
|
"epoch": 0.965586368192449,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004912738495473577,
|
|
"loss": 5.0097,
|
|
"mean_token_accuracy": 0.2070974439382553,
|
|
"num_tokens": 21257861.0,
|
|
"step": 11560
|
|
},
|
|
{
|
|
"entropy": 5.2985375881195065,
|
|
"epoch": 0.9660040093551621,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004912656373088142,
|
|
"loss": 4.9121,
|
|
"mean_token_accuracy": 0.21308131963014604,
|
|
"num_tokens": 21267140.0,
|
|
"step": 11565
|
|
},
|
|
{
|
|
"entropy": 5.291729545593261,
|
|
"epoch": 0.9664216505178751,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004912574212842804,
|
|
"loss": 5.0173,
|
|
"mean_token_accuracy": 0.20834615528583528,
|
|
"num_tokens": 21276313.0,
|
|
"step": 11570
|
|
},
|
|
{
|
|
"entropy": 5.207673692703247,
|
|
"epoch": 0.966839291680588,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004912492014739001,
|
|
"loss": 4.9348,
|
|
"mean_token_accuracy": 0.20610727965831757,
|
|
"num_tokens": 21286156.0,
|
|
"step": 11575
|
|
},
|
|
{
|
|
"entropy": 5.325664281845093,
|
|
"epoch": 0.967256932843301,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004912409778778173,
|
|
"loss": 5.0178,
|
|
"mean_token_accuracy": 0.20817912369966507,
|
|
"num_tokens": 21295420.0,
|
|
"step": 11580
|
|
},
|
|
{
|
|
"entropy": 5.382785320281982,
|
|
"epoch": 0.9676745740060141,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004912327504961758,
|
|
"loss": 5.1729,
|
|
"mean_token_accuracy": 0.19417010396718978,
|
|
"num_tokens": 21306292.0,
|
|
"step": 11585
|
|
},
|
|
{
|
|
"entropy": 5.293606424331665,
|
|
"epoch": 0.968092215168727,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004912245193291198,
|
|
"loss": 5.0095,
|
|
"mean_token_accuracy": 0.20670066475868226,
|
|
"num_tokens": 21315165.0,
|
|
"step": 11590
|
|
},
|
|
{
|
|
"entropy": 5.323351430892944,
|
|
"epoch": 0.96850985633144,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004912162843767932,
|
|
"loss": 4.9903,
|
|
"mean_token_accuracy": 0.2083704724907875,
|
|
"num_tokens": 21324608.0,
|
|
"step": 11595
|
|
},
|
|
{
|
|
"entropy": 5.305003643035889,
|
|
"epoch": 0.9689274974941531,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004912080456393404,
|
|
"loss": 4.9499,
|
|
"mean_token_accuracy": 0.20398494601249695,
|
|
"num_tokens": 21333609.0,
|
|
"step": 11600
|
|
},
|
|
{
|
|
"entropy": 5.356293773651123,
|
|
"epoch": 0.969345138656866,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004911998031169056,
|
|
"loss": 5.0649,
|
|
"mean_token_accuracy": 0.19928715378046036,
|
|
"num_tokens": 21344397.0,
|
|
"step": 11605
|
|
},
|
|
{
|
|
"entropy": 5.334855413436889,
|
|
"epoch": 0.969762779819579,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004911915568096328,
|
|
"loss": 5.0575,
|
|
"mean_token_accuracy": 0.2017696589231491,
|
|
"num_tokens": 21354111.0,
|
|
"step": 11610
|
|
},
|
|
{
|
|
"entropy": 5.180050945281982,
|
|
"epoch": 0.9701804209822921,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004911833067176666,
|
|
"loss": 4.8567,
|
|
"mean_token_accuracy": 0.2104986861348152,
|
|
"num_tokens": 21362807.0,
|
|
"step": 11615
|
|
},
|
|
{
|
|
"entropy": 5.298491382598877,
|
|
"epoch": 0.970598062145005,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004911750528411515,
|
|
"loss": 5.0375,
|
|
"mean_token_accuracy": 0.20231910347938536,
|
|
"num_tokens": 21372609.0,
|
|
"step": 11620
|
|
},
|
|
{
|
|
"entropy": 5.23612494468689,
|
|
"epoch": 0.971015703307718,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004911667951802318,
|
|
"loss": 4.9565,
|
|
"mean_token_accuracy": 0.2098189800977707,
|
|
"num_tokens": 21381182.0,
|
|
"step": 11625
|
|
},
|
|
{
|
|
"entropy": 5.273194026947022,
|
|
"epoch": 0.9714333444704311,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004911585337350524,
|
|
"loss": 4.9653,
|
|
"mean_token_accuracy": 0.20987071692943574,
|
|
"num_tokens": 21389930.0,
|
|
"step": 11630
|
|
},
|
|
{
|
|
"entropy": 5.290770435333252,
|
|
"epoch": 0.971850985633144,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004911502685057573,
|
|
"loss": 5.0108,
|
|
"mean_token_accuracy": 0.20383824706077575,
|
|
"num_tokens": 21399315.0,
|
|
"step": 11635
|
|
},
|
|
{
|
|
"entropy": 5.298996543884277,
|
|
"epoch": 0.972268626795857,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004911419994924918,
|
|
"loss": 5.0227,
|
|
"mean_token_accuracy": 0.2062831625342369,
|
|
"num_tokens": 21408857.0,
|
|
"step": 11640
|
|
},
|
|
{
|
|
"entropy": 5.345471000671386,
|
|
"epoch": 0.97268626795857,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004911337266954004,
|
|
"loss": 4.9407,
|
|
"mean_token_accuracy": 0.2096747025847435,
|
|
"num_tokens": 21417452.0,
|
|
"step": 11645
|
|
},
|
|
{
|
|
"entropy": 5.268736553192139,
|
|
"epoch": 0.973103909121283,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004911254501146279,
|
|
"loss": 4.9797,
|
|
"mean_token_accuracy": 0.21023061573505403,
|
|
"num_tokens": 21427315.0,
|
|
"step": 11650
|
|
},
|
|
{
|
|
"entropy": 5.285159921646118,
|
|
"epoch": 0.973521550283996,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004911171697503193,
|
|
"loss": 5.0232,
|
|
"mean_token_accuracy": 0.20462870746850967,
|
|
"num_tokens": 21437080.0,
|
|
"step": 11655
|
|
},
|
|
{
|
|
"entropy": 5.271046733856201,
|
|
"epoch": 0.973939191446709,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004911088856026194,
|
|
"loss": 4.8927,
|
|
"mean_token_accuracy": 0.2224911093711853,
|
|
"num_tokens": 21445421.0,
|
|
"step": 11660
|
|
},
|
|
{
|
|
"entropy": 5.2641698837280275,
|
|
"epoch": 0.974356832609422,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004911005976716734,
|
|
"loss": 4.9076,
|
|
"mean_token_accuracy": 0.2139680877327919,
|
|
"num_tokens": 21454684.0,
|
|
"step": 11665
|
|
},
|
|
{
|
|
"entropy": 5.196329975128174,
|
|
"epoch": 0.974774473772135,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004910923059576264,
|
|
"loss": 4.886,
|
|
"mean_token_accuracy": 0.21306994408369065,
|
|
"num_tokens": 21464287.0,
|
|
"step": 11670
|
|
},
|
|
{
|
|
"entropy": 5.26487889289856,
|
|
"epoch": 0.975192114934848,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004910840104606234,
|
|
"loss": 5.0016,
|
|
"mean_token_accuracy": 0.20760725289583207,
|
|
"num_tokens": 21472835.0,
|
|
"step": 11675
|
|
},
|
|
{
|
|
"entropy": 5.2392106533050535,
|
|
"epoch": 0.975609756097561,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004910757111808097,
|
|
"loss": 4.8963,
|
|
"mean_token_accuracy": 0.21464416682720183,
|
|
"num_tokens": 21482327.0,
|
|
"step": 11680
|
|
},
|
|
{
|
|
"entropy": 5.290248966217041,
|
|
"epoch": 0.976027397260274,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004910674081183305,
|
|
"loss": 5.0029,
|
|
"mean_token_accuracy": 0.20064066350460052,
|
|
"num_tokens": 21492257.0,
|
|
"step": 11685
|
|
},
|
|
{
|
|
"entropy": 5.24731297492981,
|
|
"epoch": 0.976445038422987,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004910591012733313,
|
|
"loss": 4.9979,
|
|
"mean_token_accuracy": 0.20853362530469893,
|
|
"num_tokens": 21501930.0,
|
|
"step": 11690
|
|
},
|
|
{
|
|
"entropy": 5.328313112258911,
|
|
"epoch": 0.9768626795857,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004910507906459575,
|
|
"loss": 4.9765,
|
|
"mean_token_accuracy": 0.20580680519342423,
|
|
"num_tokens": 21511924.0,
|
|
"step": 11695
|
|
},
|
|
{
|
|
"entropy": 5.29951753616333,
|
|
"epoch": 0.977280320748413,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004910424762363545,
|
|
"loss": 5.0063,
|
|
"mean_token_accuracy": 0.2004636839032173,
|
|
"num_tokens": 21522279.0,
|
|
"step": 11700
|
|
},
|
|
{
|
|
"entropy": 5.235112571716309,
|
|
"epoch": 0.977697961911126,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.000491034158044668,
|
|
"loss": 4.9937,
|
|
"mean_token_accuracy": 0.20750623643398286,
|
|
"num_tokens": 21532016.0,
|
|
"step": 11705
|
|
},
|
|
{
|
|
"entropy": 5.299756240844727,
|
|
"epoch": 0.9781156030738389,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004910258360710434,
|
|
"loss": 5.0489,
|
|
"mean_token_accuracy": 0.20230844020843505,
|
|
"num_tokens": 21541952.0,
|
|
"step": 11710
|
|
},
|
|
{
|
|
"entropy": 5.2382955074310305,
|
|
"epoch": 0.978533244236552,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004910175103156266,
|
|
"loss": 4.8707,
|
|
"mean_token_accuracy": 0.2190218135714531,
|
|
"num_tokens": 21550185.0,
|
|
"step": 11715
|
|
},
|
|
{
|
|
"entropy": 5.278531551361084,
|
|
"epoch": 0.978950885399265,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004910091807785632,
|
|
"loss": 5.0203,
|
|
"mean_token_accuracy": 0.20894922465085983,
|
|
"num_tokens": 21558891.0,
|
|
"step": 11720
|
|
},
|
|
{
|
|
"entropy": 5.266693925857544,
|
|
"epoch": 0.9793685265619779,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004910008474599991,
|
|
"loss": 4.9945,
|
|
"mean_token_accuracy": 0.20724486112594603,
|
|
"num_tokens": 21568808.0,
|
|
"step": 11725
|
|
},
|
|
{
|
|
"entropy": 5.346462535858154,
|
|
"epoch": 0.979786167724691,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004909925103600801,
|
|
"loss": 5.0377,
|
|
"mean_token_accuracy": 0.2024528354406357,
|
|
"num_tokens": 21578838.0,
|
|
"step": 11730
|
|
},
|
|
{
|
|
"entropy": 5.189047336578369,
|
|
"epoch": 0.980203808887404,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004909841694789523,
|
|
"loss": 4.9191,
|
|
"mean_token_accuracy": 0.20829323679208755,
|
|
"num_tokens": 21588008.0,
|
|
"step": 11735
|
|
},
|
|
{
|
|
"entropy": 5.276016759872436,
|
|
"epoch": 0.9806214500501169,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004909758248167616,
|
|
"loss": 5.0176,
|
|
"mean_token_accuracy": 0.20463661551475526,
|
|
"num_tokens": 21597036.0,
|
|
"step": 11740
|
|
},
|
|
{
|
|
"entropy": 5.3263507843017575,
|
|
"epoch": 0.98103909121283,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004909674763736542,
|
|
"loss": 4.9783,
|
|
"mean_token_accuracy": 0.20885300189256667,
|
|
"num_tokens": 21606028.0,
|
|
"step": 11745
|
|
},
|
|
{
|
|
"entropy": 5.330385637283325,
|
|
"epoch": 0.981456732375543,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004909591241497761,
|
|
"loss": 5.0478,
|
|
"mean_token_accuracy": 0.2137303337454796,
|
|
"num_tokens": 21615377.0,
|
|
"step": 11750
|
|
},
|
|
{
|
|
"entropy": 5.3428325176239015,
|
|
"epoch": 0.9818743735382559,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004909507681452736,
|
|
"loss": 5.1325,
|
|
"mean_token_accuracy": 0.19879976511001587,
|
|
"num_tokens": 21625751.0,
|
|
"step": 11755
|
|
},
|
|
{
|
|
"entropy": 5.407093620300293,
|
|
"epoch": 0.9822920147009689,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004909424083602929,
|
|
"loss": 5.0568,
|
|
"mean_token_accuracy": 0.20653210580348969,
|
|
"num_tokens": 21634825.0,
|
|
"step": 11760
|
|
},
|
|
{
|
|
"entropy": 5.3239446640014645,
|
|
"epoch": 0.982709655863682,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004909340447949805,
|
|
"loss": 4.9283,
|
|
"mean_token_accuracy": 0.2110578015446663,
|
|
"num_tokens": 21644286.0,
|
|
"step": 11765
|
|
},
|
|
{
|
|
"entropy": 5.313165473937988,
|
|
"epoch": 0.9831272970263949,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004909256774494827,
|
|
"loss": 5.0278,
|
|
"mean_token_accuracy": 0.20806028991937636,
|
|
"num_tokens": 21653384.0,
|
|
"step": 11770
|
|
},
|
|
{
|
|
"entropy": 5.27933030128479,
|
|
"epoch": 0.9835449381891079,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000490917306323946,
|
|
"loss": 4.938,
|
|
"mean_token_accuracy": 0.21124618649482726,
|
|
"num_tokens": 21662126.0,
|
|
"step": 11775
|
|
},
|
|
{
|
|
"entropy": 5.273025989532471,
|
|
"epoch": 0.983962579351821,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004909089314185169,
|
|
"loss": 4.9637,
|
|
"mean_token_accuracy": 0.20500903576612473,
|
|
"num_tokens": 21671940.0,
|
|
"step": 11780
|
|
},
|
|
{
|
|
"entropy": 5.218639612197876,
|
|
"epoch": 0.9843802205145339,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004909005527333421,
|
|
"loss": 4.8681,
|
|
"mean_token_accuracy": 0.2209738999605179,
|
|
"num_tokens": 21680928.0,
|
|
"step": 11785
|
|
},
|
|
{
|
|
"entropy": 5.1978364944458,
|
|
"epoch": 0.9847978616772469,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004908921702685683,
|
|
"loss": 4.9696,
|
|
"mean_token_accuracy": 0.20935233682394028,
|
|
"num_tokens": 21689712.0,
|
|
"step": 11790
|
|
},
|
|
{
|
|
"entropy": 5.2638105869293215,
|
|
"epoch": 0.98521550283996,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004908837840243421,
|
|
"loss": 4.9273,
|
|
"mean_token_accuracy": 0.21205318421125413,
|
|
"num_tokens": 21698325.0,
|
|
"step": 11795
|
|
},
|
|
{
|
|
"entropy": 5.245266485214233,
|
|
"epoch": 0.9856331440026729,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004908753940008105,
|
|
"loss": 4.9007,
|
|
"mean_token_accuracy": 0.21847618818283082,
|
|
"num_tokens": 21707607.0,
|
|
"step": 11800
|
|
},
|
|
{
|
|
"entropy": 5.19320969581604,
|
|
"epoch": 0.9860507851653859,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004908670001981201,
|
|
"loss": 4.8877,
|
|
"mean_token_accuracy": 0.21420792490243912,
|
|
"num_tokens": 21715887.0,
|
|
"step": 11805
|
|
},
|
|
{
|
|
"entropy": 5.263513612747192,
|
|
"epoch": 0.986468426328099,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004908586026164182,
|
|
"loss": 4.993,
|
|
"mean_token_accuracy": 0.21018393486738204,
|
|
"num_tokens": 21724992.0,
|
|
"step": 11810
|
|
},
|
|
{
|
|
"entropy": 5.308016538619995,
|
|
"epoch": 0.9868860674908119,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004908502012558516,
|
|
"loss": 4.9956,
|
|
"mean_token_accuracy": 0.20734051913022994,
|
|
"num_tokens": 21734317.0,
|
|
"step": 11815
|
|
},
|
|
{
|
|
"entropy": 5.3289838314056395,
|
|
"epoch": 0.9873037086535249,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004908417961165674,
|
|
"loss": 5.0592,
|
|
"mean_token_accuracy": 0.20009820759296418,
|
|
"num_tokens": 21743014.0,
|
|
"step": 11820
|
|
},
|
|
{
|
|
"entropy": 5.336205720901489,
|
|
"epoch": 0.9877213498162379,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004908333871987126,
|
|
"loss": 4.9579,
|
|
"mean_token_accuracy": 0.20861730426549913,
|
|
"num_tokens": 21751058.0,
|
|
"step": 11825
|
|
},
|
|
{
|
|
"entropy": 5.320491981506348,
|
|
"epoch": 0.9881389909789509,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004908249745024347,
|
|
"loss": 5.0336,
|
|
"mean_token_accuracy": 0.20887478142976762,
|
|
"num_tokens": 21760549.0,
|
|
"step": 11830
|
|
},
|
|
{
|
|
"entropy": 5.286648893356324,
|
|
"epoch": 0.9885566321416639,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000490816558027881,
|
|
"loss": 4.9573,
|
|
"mean_token_accuracy": 0.21629133075475693,
|
|
"num_tokens": 21769873.0,
|
|
"step": 11835
|
|
},
|
|
{
|
|
"entropy": 5.316697978973389,
|
|
"epoch": 0.9889742733043769,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004908081377751985,
|
|
"loss": 5.0395,
|
|
"mean_token_accuracy": 0.20972861647605895,
|
|
"num_tokens": 21779036.0,
|
|
"step": 11840
|
|
},
|
|
{
|
|
"entropy": 5.379835557937622,
|
|
"epoch": 0.9893919144670899,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004907997137445347,
|
|
"loss": 5.0702,
|
|
"mean_token_accuracy": 0.1999921277165413,
|
|
"num_tokens": 21787671.0,
|
|
"step": 11845
|
|
},
|
|
{
|
|
"entropy": 5.317583274841309,
|
|
"epoch": 0.9898095556298029,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004907912859360373,
|
|
"loss": 5.0138,
|
|
"mean_token_accuracy": 0.20185888707637786,
|
|
"num_tokens": 21797269.0,
|
|
"step": 11850
|
|
},
|
|
{
|
|
"entropy": 5.351606941223144,
|
|
"epoch": 0.9902271967925159,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004907828543498536,
|
|
"loss": 5.071,
|
|
"mean_token_accuracy": 0.2047065183520317,
|
|
"num_tokens": 21806738.0,
|
|
"step": 11855
|
|
},
|
|
{
|
|
"entropy": 5.285957527160645,
|
|
"epoch": 0.9906448379552288,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004907744189861313,
|
|
"loss": 4.9577,
|
|
"mean_token_accuracy": 0.20922023952007293,
|
|
"num_tokens": 21815612.0,
|
|
"step": 11860
|
|
},
|
|
{
|
|
"entropy": 5.310531759262085,
|
|
"epoch": 0.9910624791179419,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000490765979845018,
|
|
"loss": 4.9871,
|
|
"mean_token_accuracy": 0.20937884598970413,
|
|
"num_tokens": 21824222.0,
|
|
"step": 11865
|
|
},
|
|
{
|
|
"entropy": 5.312347078323365,
|
|
"epoch": 0.9914801202806549,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004907575369266617,
|
|
"loss": 4.9777,
|
|
"mean_token_accuracy": 0.2090429350733757,
|
|
"num_tokens": 21833929.0,
|
|
"step": 11870
|
|
},
|
|
{
|
|
"entropy": 5.261252069473267,
|
|
"epoch": 0.9918977614433678,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004907490902312099,
|
|
"loss": 5.0294,
|
|
"mean_token_accuracy": 0.20546115189790726,
|
|
"num_tokens": 21843261.0,
|
|
"step": 11875
|
|
},
|
|
{
|
|
"entropy": 5.32122278213501,
|
|
"epoch": 0.9923154026060809,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004907406397588106,
|
|
"loss": 5.0764,
|
|
"mean_token_accuracy": 0.20094220340251923,
|
|
"num_tokens": 21853004.0,
|
|
"step": 11880
|
|
},
|
|
{
|
|
"entropy": 5.298301792144775,
|
|
"epoch": 0.9927330437687939,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004907321855096117,
|
|
"loss": 4.9326,
|
|
"mean_token_accuracy": 0.2069837212562561,
|
|
"num_tokens": 21862628.0,
|
|
"step": 11885
|
|
},
|
|
{
|
|
"entropy": 5.24231448173523,
|
|
"epoch": 0.9931506849315068,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004907237274837613,
|
|
"loss": 4.9139,
|
|
"mean_token_accuracy": 0.21116461753845214,
|
|
"num_tokens": 21872041.0,
|
|
"step": 11890
|
|
},
|
|
{
|
|
"entropy": 5.284882068634033,
|
|
"epoch": 0.9935683260942199,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004907152656814072,
|
|
"loss": 5.0107,
|
|
"mean_token_accuracy": 0.19981574565172194,
|
|
"num_tokens": 21881834.0,
|
|
"step": 11895
|
|
},
|
|
{
|
|
"entropy": 5.378417682647705,
|
|
"epoch": 0.9939859672569329,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004907068001026978,
|
|
"loss": 5.1137,
|
|
"mean_token_accuracy": 0.20446072220802308,
|
|
"num_tokens": 21892349.0,
|
|
"step": 11900
|
|
},
|
|
{
|
|
"entropy": 5.320441770553589,
|
|
"epoch": 0.9944036084196458,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004906983307477813,
|
|
"loss": 4.9756,
|
|
"mean_token_accuracy": 0.20961364954710007,
|
|
"num_tokens": 21901427.0,
|
|
"step": 11905
|
|
},
|
|
{
|
|
"entropy": 5.263491535186768,
|
|
"epoch": 0.9948212495823588,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004906898576168057,
|
|
"loss": 4.9201,
|
|
"mean_token_accuracy": 0.2104760780930519,
|
|
"num_tokens": 21910654.0,
|
|
"step": 11910
|
|
},
|
|
{
|
|
"entropy": 5.155521631240845,
|
|
"epoch": 0.9952388907450719,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004906813807099197,
|
|
"loss": 4.9585,
|
|
"mean_token_accuracy": 0.21791013330221176,
|
|
"num_tokens": 21919583.0,
|
|
"step": 11915
|
|
},
|
|
{
|
|
"entropy": 5.160713815689087,
|
|
"epoch": 0.9956565319077848,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004906729000272714,
|
|
"loss": 4.8632,
|
|
"mean_token_accuracy": 0.21212699860334397,
|
|
"num_tokens": 21927843.0,
|
|
"step": 11920
|
|
},
|
|
{
|
|
"entropy": 5.27823281288147,
|
|
"epoch": 0.9960741730704978,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004906644155690095,
|
|
"loss": 4.9417,
|
|
"mean_token_accuracy": 0.20950577557086944,
|
|
"num_tokens": 21937269.0,
|
|
"step": 11925
|
|
},
|
|
{
|
|
"entropy": 5.4290077686309814,
|
|
"epoch": 0.9964918142332109,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004906559273352823,
|
|
"loss": 5.1075,
|
|
"mean_token_accuracy": 0.200825834274292,
|
|
"num_tokens": 21946965.0,
|
|
"step": 11930
|
|
},
|
|
{
|
|
"entropy": 5.309491443634033,
|
|
"epoch": 0.9969094553959238,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004906474353262386,
|
|
"loss": 4.9608,
|
|
"mean_token_accuracy": 0.20751097202301025,
|
|
"num_tokens": 21955957.0,
|
|
"step": 11935
|
|
},
|
|
{
|
|
"entropy": 5.229637813568115,
|
|
"epoch": 0.9973270965586368,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004906389395420269,
|
|
"loss": 4.8988,
|
|
"mean_token_accuracy": 0.21192772388458253,
|
|
"num_tokens": 21965643.0,
|
|
"step": 11940
|
|
},
|
|
{
|
|
"entropy": 5.292104911804199,
|
|
"epoch": 0.9977447377213499,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000490630439982796,
|
|
"loss": 4.9723,
|
|
"mean_token_accuracy": 0.20876029133796692,
|
|
"num_tokens": 21974789.0,
|
|
"step": 11945
|
|
},
|
|
{
|
|
"entropy": 5.214302682876587,
|
|
"epoch": 0.9981623788840628,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004906219366486947,
|
|
"loss": 4.8627,
|
|
"mean_token_accuracy": 0.2213547259569168,
|
|
"num_tokens": 21983411.0,
|
|
"step": 11950
|
|
},
|
|
{
|
|
"entropy": 5.336352014541626,
|
|
"epoch": 0.9985800200467758,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004906134295398719,
|
|
"loss": 4.9779,
|
|
"mean_token_accuracy": 0.20911235511302947,
|
|
"num_tokens": 21992570.0,
|
|
"step": 11955
|
|
},
|
|
{
|
|
"entropy": 5.156963920593261,
|
|
"epoch": 0.9989976612094889,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004906049186564764,
|
|
"loss": 4.8509,
|
|
"mean_token_accuracy": 0.21873552054166795,
|
|
"num_tokens": 22001411.0,
|
|
"step": 11960
|
|
},
|
|
{
|
|
"entropy": 5.383324527740479,
|
|
"epoch": 0.9994153023722018,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004905964039986574,
|
|
"loss": 5.0899,
|
|
"mean_token_accuracy": 0.20052825659513474,
|
|
"num_tokens": 22010882.0,
|
|
"step": 11965
|
|
},
|
|
{
|
|
"entropy": 5.321116828918457,
|
|
"epoch": 0.9998329435349148,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004905878855665637,
|
|
"loss": 5.0811,
|
|
"mean_token_accuracy": 0.2005285605788231,
|
|
"num_tokens": 22020885.0,
|
|
"step": 11970
|
|
},
|
|
{
|
|
"entropy": 5.287244653701782,
|
|
"epoch": 1.0002505846976277,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004905793633603446,
|
|
"loss": 4.8271,
|
|
"mean_token_accuracy": 0.21476868093013762,
|
|
"num_tokens": 22030278.0,
|
|
"step": 11975
|
|
},
|
|
{
|
|
"entropy": 5.343204212188721,
|
|
"epoch": 1.0006682258603408,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004905708373801492,
|
|
"loss": 5.0199,
|
|
"mean_token_accuracy": 0.20292422026395798,
|
|
"num_tokens": 22039601.0,
|
|
"step": 11980
|
|
},
|
|
{
|
|
"entropy": 5.232033777236938,
|
|
"epoch": 1.0010858670230538,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004905623076261269,
|
|
"loss": 4.8632,
|
|
"mean_token_accuracy": 0.21405914127826692,
|
|
"num_tokens": 22049158.0,
|
|
"step": 11985
|
|
},
|
|
{
|
|
"entropy": 5.302607440948487,
|
|
"epoch": 1.0015035081857668,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.000490553774098427,
|
|
"loss": 4.9669,
|
|
"mean_token_accuracy": 0.20085557401180268,
|
|
"num_tokens": 22059278.0,
|
|
"step": 11990
|
|
},
|
|
{
|
|
"entropy": 5.347648191452026,
|
|
"epoch": 1.0019211493484799,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004905452367971986,
|
|
"loss": 4.9186,
|
|
"mean_token_accuracy": 0.21432092487812043,
|
|
"num_tokens": 22068415.0,
|
|
"step": 11995
|
|
},
|
|
{
|
|
"entropy": 5.32201247215271,
|
|
"epoch": 1.0023387905111927,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004905366957225916,
|
|
"loss": 4.8952,
|
|
"mean_token_accuracy": 0.21055176705121995,
|
|
"num_tokens": 22077815.0,
|
|
"step": 12000
|
|
},
|
|
{
|
|
"epoch": 1.0023387905111927,
|
|
"eval_entropy": 4.98001087759794,
|
|
"eval_loss": 4.918286323547363,
|
|
"eval_mean_token_accuracy": 0.22144670719452467,
|
|
"eval_num_tokens": 22077815.0,
|
|
"eval_runtime": 20.9503,
|
|
"eval_samples_per_second": 1802.505,
|
|
"eval_steps_per_second": 225.343,
|
|
"step": 12000
|
|
},
|
|
{
|
|
"entropy": 5.33688063621521,
|
|
"epoch": 1.0027564316739057,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004905281508747552,
|
|
"loss": 4.9849,
|
|
"mean_token_accuracy": 0.20465521961450578,
|
|
"num_tokens": 22087606.0,
|
|
"step": 12005
|
|
},
|
|
{
|
|
"entropy": 5.2549535751342775,
|
|
"epoch": 1.0031740728366187,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004905196022538391,
|
|
"loss": 4.8058,
|
|
"mean_token_accuracy": 0.218599371612072,
|
|
"num_tokens": 22096300.0,
|
|
"step": 12010
|
|
},
|
|
{
|
|
"entropy": 5.340641975402832,
|
|
"epoch": 1.0035917139993318,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000490511049859993,
|
|
"loss": 5.0029,
|
|
"mean_token_accuracy": 0.2097248375415802,
|
|
"num_tokens": 22105750.0,
|
|
"step": 12015
|
|
},
|
|
{
|
|
"entropy": 5.352898740768433,
|
|
"epoch": 1.0040093551620448,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004905024936933664,
|
|
"loss": 4.9821,
|
|
"mean_token_accuracy": 0.21515518873929979,
|
|
"num_tokens": 22115163.0,
|
|
"step": 12020
|
|
},
|
|
{
|
|
"entropy": 5.341146802902221,
|
|
"epoch": 1.0044269963247578,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004904939337541093,
|
|
"loss": 4.9702,
|
|
"mean_token_accuracy": 0.2097815454006195,
|
|
"num_tokens": 22125580.0,
|
|
"step": 12025
|
|
},
|
|
{
|
|
"entropy": 5.207156324386597,
|
|
"epoch": 1.0048446374874707,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004904853700423716,
|
|
"loss": 4.8449,
|
|
"mean_token_accuracy": 0.22272006124258042,
|
|
"num_tokens": 22134985.0,
|
|
"step": 12030
|
|
},
|
|
{
|
|
"entropy": 5.285246992111206,
|
|
"epoch": 1.0052622786501837,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004904768025583031,
|
|
"loss": 4.8584,
|
|
"mean_token_accuracy": 0.21392470747232437,
|
|
"num_tokens": 22142530.0,
|
|
"step": 12035
|
|
},
|
|
{
|
|
"entropy": 5.306007385253906,
|
|
"epoch": 1.0056799198128967,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004904682313020537,
|
|
"loss": 4.9508,
|
|
"mean_token_accuracy": 0.21486891508102418,
|
|
"num_tokens": 22151696.0,
|
|
"step": 12040
|
|
},
|
|
{
|
|
"entropy": 5.2540358543396,
|
|
"epoch": 1.0060975609756098,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004904596562737737,
|
|
"loss": 4.8826,
|
|
"mean_token_accuracy": 0.2089384064078331,
|
|
"num_tokens": 22161286.0,
|
|
"step": 12045
|
|
},
|
|
{
|
|
"entropy": 5.265077304840088,
|
|
"epoch": 1.0065152021383228,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000490451077473613,
|
|
"loss": 4.8485,
|
|
"mean_token_accuracy": 0.22072249054908752,
|
|
"num_tokens": 22169678.0,
|
|
"step": 12050
|
|
},
|
|
{
|
|
"entropy": 5.24460129737854,
|
|
"epoch": 1.0069328433010358,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004904424949017218,
|
|
"loss": 4.9037,
|
|
"mean_token_accuracy": 0.22490696907043456,
|
|
"num_tokens": 22178618.0,
|
|
"step": 12055
|
|
},
|
|
{
|
|
"entropy": 5.217234897613525,
|
|
"epoch": 1.0073504844637486,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004904339085582504,
|
|
"loss": 4.8627,
|
|
"mean_token_accuracy": 0.2142759695649147,
|
|
"num_tokens": 22187574.0,
|
|
"step": 12060
|
|
},
|
|
{
|
|
"entropy": 5.37125244140625,
|
|
"epoch": 1.0077681256264617,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004904253184433491,
|
|
"loss": 5.0355,
|
|
"mean_token_accuracy": 0.20329798012971878,
|
|
"num_tokens": 22198840.0,
|
|
"step": 12065
|
|
},
|
|
{
|
|
"entropy": 5.2858569622039795,
|
|
"epoch": 1.0081857667891747,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004904167245571684,
|
|
"loss": 4.8379,
|
|
"mean_token_accuracy": 0.21725084483623505,
|
|
"num_tokens": 22207166.0,
|
|
"step": 12070
|
|
},
|
|
{
|
|
"entropy": 5.233847284317017,
|
|
"epoch": 1.0086034079518877,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004904081268998586,
|
|
"loss": 4.8738,
|
|
"mean_token_accuracy": 0.2079276442527771,
|
|
"num_tokens": 22216232.0,
|
|
"step": 12075
|
|
},
|
|
{
|
|
"entropy": 5.305522346496582,
|
|
"epoch": 1.0090210491146008,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004903995254715702,
|
|
"loss": 4.8478,
|
|
"mean_token_accuracy": 0.2131372556090355,
|
|
"num_tokens": 22224853.0,
|
|
"step": 12080
|
|
},
|
|
{
|
|
"entropy": 5.223891639709473,
|
|
"epoch": 1.0094386902773138,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004903909202724539,
|
|
"loss": 4.8423,
|
|
"mean_token_accuracy": 0.2171231836080551,
|
|
"num_tokens": 22233971.0,
|
|
"step": 12085
|
|
},
|
|
{
|
|
"entropy": 5.178820848464966,
|
|
"epoch": 1.0098563314400266,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004903823113026602,
|
|
"loss": 4.7528,
|
|
"mean_token_accuracy": 0.22094895094633102,
|
|
"num_tokens": 22242548.0,
|
|
"step": 12090
|
|
},
|
|
{
|
|
"entropy": 5.137172603607178,
|
|
"epoch": 1.0102739726027397,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00049037369856234,
|
|
"loss": 4.7399,
|
|
"mean_token_accuracy": 0.22437500804662705,
|
|
"num_tokens": 22251086.0,
|
|
"step": 12095
|
|
},
|
|
{
|
|
"entropy": 5.286847734451294,
|
|
"epoch": 1.0106916137654527,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004903650820516438,
|
|
"loss": 4.9351,
|
|
"mean_token_accuracy": 0.20436829030513765,
|
|
"num_tokens": 22260035.0,
|
|
"step": 12100
|
|
},
|
|
{
|
|
"entropy": 5.328700113296509,
|
|
"epoch": 1.0111092549281657,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004903564617707227,
|
|
"loss": 4.8378,
|
|
"mean_token_accuracy": 0.22022415101528167,
|
|
"num_tokens": 22269134.0,
|
|
"step": 12105
|
|
},
|
|
{
|
|
"entropy": 5.278768873214721,
|
|
"epoch": 1.0115268960908788,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004903478377197275,
|
|
"loss": 4.9389,
|
|
"mean_token_accuracy": 0.21955397129058837,
|
|
"num_tokens": 22278123.0,
|
|
"step": 12110
|
|
},
|
|
{
|
|
"entropy": 5.243806982040406,
|
|
"epoch": 1.0119445372535918,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004903392098988092,
|
|
"loss": 4.936,
|
|
"mean_token_accuracy": 0.20569716095924379,
|
|
"num_tokens": 22287557.0,
|
|
"step": 12115
|
|
},
|
|
{
|
|
"entropy": 5.279406213760376,
|
|
"epoch": 1.0123621784163046,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004903305783081188,
|
|
"loss": 4.8687,
|
|
"mean_token_accuracy": 0.2175604671239853,
|
|
"num_tokens": 22296705.0,
|
|
"step": 12120
|
|
},
|
|
{
|
|
"entropy": 5.217913436889648,
|
|
"epoch": 1.0127798195790176,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004903219429478075,
|
|
"loss": 4.8414,
|
|
"mean_token_accuracy": 0.21395462304353713,
|
|
"num_tokens": 22305904.0,
|
|
"step": 12125
|
|
},
|
|
{
|
|
"entropy": 5.254189729690552,
|
|
"epoch": 1.0131974607417307,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004903133038180263,
|
|
"loss": 4.873,
|
|
"mean_token_accuracy": 0.21612954884767532,
|
|
"num_tokens": 22315051.0,
|
|
"step": 12130
|
|
},
|
|
{
|
|
"entropy": 5.238156318664551,
|
|
"epoch": 1.0136151019044437,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004903046609189266,
|
|
"loss": 4.9191,
|
|
"mean_token_accuracy": 0.215847447514534,
|
|
"num_tokens": 22324469.0,
|
|
"step": 12135
|
|
},
|
|
{
|
|
"entropy": 5.3610094547271725,
|
|
"epoch": 1.0140327430671567,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004902960142506597,
|
|
"loss": 4.9961,
|
|
"mean_token_accuracy": 0.20541031509637833,
|
|
"num_tokens": 22334407.0,
|
|
"step": 12140
|
|
},
|
|
{
|
|
"entropy": 5.361011648178101,
|
|
"epoch": 1.0144503842298698,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004902873638133768,
|
|
"loss": 4.9919,
|
|
"mean_token_accuracy": 0.20484239906072615,
|
|
"num_tokens": 22342975.0,
|
|
"step": 12145
|
|
},
|
|
{
|
|
"entropy": 5.253829050064087,
|
|
"epoch": 1.0148680253925826,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004902787096072296,
|
|
"loss": 4.8121,
|
|
"mean_token_accuracy": 0.21201975047588348,
|
|
"num_tokens": 22351649.0,
|
|
"step": 12150
|
|
},
|
|
{
|
|
"entropy": 5.2843334674835205,
|
|
"epoch": 1.0152856665552956,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004902700516323693,
|
|
"loss": 4.9145,
|
|
"mean_token_accuracy": 0.20759780704975128,
|
|
"num_tokens": 22361956.0,
|
|
"step": 12155
|
|
},
|
|
{
|
|
"entropy": 5.29724702835083,
|
|
"epoch": 1.0157033077180087,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004902613898889477,
|
|
"loss": 4.9163,
|
|
"mean_token_accuracy": 0.2092845246195793,
|
|
"num_tokens": 22372354.0,
|
|
"step": 12160
|
|
},
|
|
{
|
|
"entropy": 5.233258056640625,
|
|
"epoch": 1.0161209488807217,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004902527243771164,
|
|
"loss": 4.7951,
|
|
"mean_token_accuracy": 0.21819414794445038,
|
|
"num_tokens": 22381225.0,
|
|
"step": 12165
|
|
},
|
|
{
|
|
"entropy": 5.159318256378174,
|
|
"epoch": 1.0165385900434347,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000490244055097027,
|
|
"loss": 4.8041,
|
|
"mean_token_accuracy": 0.2210355669260025,
|
|
"num_tokens": 22390666.0,
|
|
"step": 12170
|
|
},
|
|
{
|
|
"entropy": 5.2269035339355465,
|
|
"epoch": 1.0169562312061478,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004902353820488314,
|
|
"loss": 4.7972,
|
|
"mean_token_accuracy": 0.22569137811660767,
|
|
"num_tokens": 22399528.0,
|
|
"step": 12175
|
|
},
|
|
{
|
|
"entropy": 5.255279111862182,
|
|
"epoch": 1.0173738723688606,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004902267052326812,
|
|
"loss": 4.8168,
|
|
"mean_token_accuracy": 0.22620024532079697,
|
|
"num_tokens": 22408827.0,
|
|
"step": 12180
|
|
},
|
|
{
|
|
"entropy": 5.2124138355255125,
|
|
"epoch": 1.0177915135315736,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004902180246487285,
|
|
"loss": 4.8524,
|
|
"mean_token_accuracy": 0.2139216512441635,
|
|
"num_tokens": 22418098.0,
|
|
"step": 12185
|
|
},
|
|
{
|
|
"entropy": 5.167256307601929,
|
|
"epoch": 1.0182091546942866,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004902093402971254,
|
|
"loss": 4.7222,
|
|
"mean_token_accuracy": 0.22291651219129563,
|
|
"num_tokens": 22427417.0,
|
|
"step": 12190
|
|
},
|
|
{
|
|
"entropy": 5.211392068862915,
|
|
"epoch": 1.0186267958569997,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004902006521780236,
|
|
"loss": 4.9273,
|
|
"mean_token_accuracy": 0.20917229503393173,
|
|
"num_tokens": 22436938.0,
|
|
"step": 12195
|
|
},
|
|
{
|
|
"entropy": 5.242594385147095,
|
|
"epoch": 1.0190444370197127,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004901919602915754,
|
|
"loss": 4.9612,
|
|
"mean_token_accuracy": 0.20073759257793428,
|
|
"num_tokens": 22447361.0,
|
|
"step": 12200
|
|
},
|
|
{
|
|
"entropy": 5.327710866928101,
|
|
"epoch": 1.0194620781824257,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004901832646379328,
|
|
"loss": 4.9858,
|
|
"mean_token_accuracy": 0.20182490944862366,
|
|
"num_tokens": 22457431.0,
|
|
"step": 12205
|
|
},
|
|
{
|
|
"entropy": 5.311217403411865,
|
|
"epoch": 1.0198797193451385,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004901745652172483,
|
|
"loss": 4.9586,
|
|
"mean_token_accuracy": 0.20915098041296004,
|
|
"num_tokens": 22466219.0,
|
|
"step": 12210
|
|
},
|
|
{
|
|
"entropy": 5.311522960662842,
|
|
"epoch": 1.0202973605078516,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000490165862029674,
|
|
"loss": 4.9733,
|
|
"mean_token_accuracy": 0.21020882576704025,
|
|
"num_tokens": 22476231.0,
|
|
"step": 12215
|
|
},
|
|
{
|
|
"entropy": 5.234994506835937,
|
|
"epoch": 1.0207150016705646,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004901571550753622,
|
|
"loss": 4.7647,
|
|
"mean_token_accuracy": 0.2253715366125107,
|
|
"num_tokens": 22484288.0,
|
|
"step": 12220
|
|
},
|
|
{
|
|
"entropy": 5.282567262649536,
|
|
"epoch": 1.0211326428332776,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004901484443544655,
|
|
"loss": 4.9162,
|
|
"mean_token_accuracy": 0.2173297956585884,
|
|
"num_tokens": 22493619.0,
|
|
"step": 12225
|
|
},
|
|
{
|
|
"entropy": 5.218139600753784,
|
|
"epoch": 1.0215502839959907,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004901397298671362,
|
|
"loss": 4.8207,
|
|
"mean_token_accuracy": 0.22035807073116304,
|
|
"num_tokens": 22501606.0,
|
|
"step": 12230
|
|
},
|
|
{
|
|
"entropy": 5.253662729263306,
|
|
"epoch": 1.0219679251587037,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004901310116135271,
|
|
"loss": 4.825,
|
|
"mean_token_accuracy": 0.21622170507907867,
|
|
"num_tokens": 22510410.0,
|
|
"step": 12235
|
|
},
|
|
{
|
|
"entropy": 5.267537355422974,
|
|
"epoch": 1.0223855663214167,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004901222895937905,
|
|
"loss": 4.9272,
|
|
"mean_token_accuracy": 0.21936265528202056,
|
|
"num_tokens": 22518796.0,
|
|
"step": 12240
|
|
},
|
|
{
|
|
"entropy": 5.2464197158813475,
|
|
"epoch": 1.0228032074841296,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004901135638080796,
|
|
"loss": 4.7585,
|
|
"mean_token_accuracy": 0.21891705989837645,
|
|
"num_tokens": 22527532.0,
|
|
"step": 12245
|
|
},
|
|
{
|
|
"entropy": 5.230825281143188,
|
|
"epoch": 1.0232208486468426,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004901048342565465,
|
|
"loss": 4.8421,
|
|
"mean_token_accuracy": 0.21363466531038283,
|
|
"num_tokens": 22536882.0,
|
|
"step": 12250
|
|
},
|
|
{
|
|
"entropy": 5.193243932723999,
|
|
"epoch": 1.0236384898095556,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004900961009393445,
|
|
"loss": 4.7729,
|
|
"mean_token_accuracy": 0.2157750442624092,
|
|
"num_tokens": 22545549.0,
|
|
"step": 12255
|
|
},
|
|
{
|
|
"entropy": 5.2878265380859375,
|
|
"epoch": 1.0240561309722687,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004900873638566263,
|
|
"loss": 4.9876,
|
|
"mean_token_accuracy": 0.20700083673000336,
|
|
"num_tokens": 22554941.0,
|
|
"step": 12260
|
|
},
|
|
{
|
|
"entropy": 5.187461900711059,
|
|
"epoch": 1.0244737721349817,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.000490078623008545,
|
|
"loss": 4.8724,
|
|
"mean_token_accuracy": 0.21458237916231154,
|
|
"num_tokens": 22565159.0,
|
|
"step": 12265
|
|
},
|
|
{
|
|
"entropy": 5.231040287017822,
|
|
"epoch": 1.0248914132976945,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004900698783952533,
|
|
"loss": 4.8213,
|
|
"mean_token_accuracy": 0.21847899705171586,
|
|
"num_tokens": 22574184.0,
|
|
"step": 12270
|
|
},
|
|
{
|
|
"entropy": 5.235248994827271,
|
|
"epoch": 1.0253090544604075,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004900611300169048,
|
|
"loss": 4.9362,
|
|
"mean_token_accuracy": 0.20880208164453506,
|
|
"num_tokens": 22584062.0,
|
|
"step": 12275
|
|
},
|
|
{
|
|
"entropy": 5.292111730575561,
|
|
"epoch": 1.0257266956231206,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004900523778736521,
|
|
"loss": 4.8711,
|
|
"mean_token_accuracy": 0.21688505560159682,
|
|
"num_tokens": 22592845.0,
|
|
"step": 12280
|
|
},
|
|
{
|
|
"entropy": 5.271919775009155,
|
|
"epoch": 1.0261443367858336,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004900436219656488,
|
|
"loss": 4.8738,
|
|
"mean_token_accuracy": 0.20890514254570008,
|
|
"num_tokens": 22602750.0,
|
|
"step": 12285
|
|
},
|
|
{
|
|
"entropy": 5.246266937255859,
|
|
"epoch": 1.0265619779485466,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000490034862293048,
|
|
"loss": 4.9075,
|
|
"mean_token_accuracy": 0.21034188121557235,
|
|
"num_tokens": 22611788.0,
|
|
"step": 12290
|
|
},
|
|
{
|
|
"entropy": 5.218010091781617,
|
|
"epoch": 1.0269796191112597,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004900260988560031,
|
|
"loss": 4.8281,
|
|
"mean_token_accuracy": 0.21251376420259477,
|
|
"num_tokens": 22620234.0,
|
|
"step": 12295
|
|
},
|
|
{
|
|
"entropy": 5.1695475578308105,
|
|
"epoch": 1.0273972602739727,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004900173316546675,
|
|
"loss": 4.7675,
|
|
"mean_token_accuracy": 0.2241442859172821,
|
|
"num_tokens": 22629155.0,
|
|
"step": 12300
|
|
},
|
|
{
|
|
"entropy": 5.3278333187103275,
|
|
"epoch": 1.0278149014366855,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004900085606891947,
|
|
"loss": 4.976,
|
|
"mean_token_accuracy": 0.2019646182656288,
|
|
"num_tokens": 22638647.0,
|
|
"step": 12305
|
|
},
|
|
{
|
|
"entropy": 5.290404224395752,
|
|
"epoch": 1.0282325425993986,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004899997859597382,
|
|
"loss": 4.9011,
|
|
"mean_token_accuracy": 0.2035590663552284,
|
|
"num_tokens": 22648295.0,
|
|
"step": 12310
|
|
},
|
|
{
|
|
"entropy": 5.219697666168213,
|
|
"epoch": 1.0286501837621116,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004899910074664518,
|
|
"loss": 4.8798,
|
|
"mean_token_accuracy": 0.21274126172065735,
|
|
"num_tokens": 22657342.0,
|
|
"step": 12315
|
|
},
|
|
{
|
|
"entropy": 5.22415566444397,
|
|
"epoch": 1.0290678249248246,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004899822252094889,
|
|
"loss": 4.8393,
|
|
"mean_token_accuracy": 0.21675885617733,
|
|
"num_tokens": 22665230.0,
|
|
"step": 12320
|
|
},
|
|
{
|
|
"entropy": 5.205628871917725,
|
|
"epoch": 1.0294854660875377,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004899734391890034,
|
|
"loss": 4.8449,
|
|
"mean_token_accuracy": 0.21535724699497222,
|
|
"num_tokens": 22674385.0,
|
|
"step": 12325
|
|
},
|
|
{
|
|
"entropy": 5.136063575744629,
|
|
"epoch": 1.0299031072502507,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004899646494051491,
|
|
"loss": 4.7339,
|
|
"mean_token_accuracy": 0.22966232448816298,
|
|
"num_tokens": 22683493.0,
|
|
"step": 12330
|
|
},
|
|
{
|
|
"entropy": 5.259289407730103,
|
|
"epoch": 1.0303207484129635,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004899558558580798,
|
|
"loss": 4.8144,
|
|
"mean_token_accuracy": 0.211348095536232,
|
|
"num_tokens": 22691878.0,
|
|
"step": 12335
|
|
},
|
|
{
|
|
"entropy": 5.246351528167724,
|
|
"epoch": 1.0307383895756765,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004899470585479495,
|
|
"loss": 4.8311,
|
|
"mean_token_accuracy": 0.2138791039586067,
|
|
"num_tokens": 22700112.0,
|
|
"step": 12340
|
|
},
|
|
{
|
|
"entropy": 5.246161460876465,
|
|
"epoch": 1.0311560307383896,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004899382574749124,
|
|
"loss": 4.8595,
|
|
"mean_token_accuracy": 0.21825456470251084,
|
|
"num_tokens": 22709218.0,
|
|
"step": 12345
|
|
},
|
|
{
|
|
"entropy": 5.252669906616211,
|
|
"epoch": 1.0315736719011026,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004899294526391221,
|
|
"loss": 4.8741,
|
|
"mean_token_accuracy": 0.2166745990514755,
|
|
"num_tokens": 22718423.0,
|
|
"step": 12350
|
|
},
|
|
{
|
|
"entropy": 5.234964227676391,
|
|
"epoch": 1.0319913130638156,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004899206440407332,
|
|
"loss": 4.9459,
|
|
"mean_token_accuracy": 0.20568607449531556,
|
|
"num_tokens": 22727333.0,
|
|
"step": 12355
|
|
},
|
|
{
|
|
"entropy": 5.28084397315979,
|
|
"epoch": 1.0324089542265287,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004899118316798996,
|
|
"loss": 4.8744,
|
|
"mean_token_accuracy": 0.211395201086998,
|
|
"num_tokens": 22737248.0,
|
|
"step": 12360
|
|
},
|
|
{
|
|
"entropy": 5.236141347885132,
|
|
"epoch": 1.0328265953892415,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004899030155567759,
|
|
"loss": 4.8934,
|
|
"mean_token_accuracy": 0.21013821959495543,
|
|
"num_tokens": 22747515.0,
|
|
"step": 12365
|
|
},
|
|
{
|
|
"entropy": 5.288139963150025,
|
|
"epoch": 1.0332442365519545,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000489894195671516,
|
|
"loss": 4.8928,
|
|
"mean_token_accuracy": 0.21627574414014816,
|
|
"num_tokens": 22756670.0,
|
|
"step": 12370
|
|
},
|
|
{
|
|
"entropy": 5.303247690200806,
|
|
"epoch": 1.0336618777146676,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004898853720242747,
|
|
"loss": 5.0158,
|
|
"mean_token_accuracy": 0.20239486992359162,
|
|
"num_tokens": 22766332.0,
|
|
"step": 12375
|
|
},
|
|
{
|
|
"entropy": 5.274710655212402,
|
|
"epoch": 1.0340795188773806,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004898765446152062,
|
|
"loss": 4.8443,
|
|
"mean_token_accuracy": 0.21857706159353257,
|
|
"num_tokens": 22774999.0,
|
|
"step": 12380
|
|
},
|
|
{
|
|
"entropy": 5.243936491012573,
|
|
"epoch": 1.0344971600400936,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004898677134444652,
|
|
"loss": 4.8879,
|
|
"mean_token_accuracy": 0.20787277519702912,
|
|
"num_tokens": 22784578.0,
|
|
"step": 12385
|
|
},
|
|
{
|
|
"entropy": 5.274090147018432,
|
|
"epoch": 1.0349148012028067,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004898588785122063,
|
|
"loss": 4.8879,
|
|
"mean_token_accuracy": 0.22128744572401046,
|
|
"num_tokens": 22794508.0,
|
|
"step": 12390
|
|
},
|
|
{
|
|
"entropy": 5.297973012924194,
|
|
"epoch": 1.0353324423655195,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004898500398185841,
|
|
"loss": 4.9938,
|
|
"mean_token_accuracy": 0.21094824522733688,
|
|
"num_tokens": 22804399.0,
|
|
"step": 12395
|
|
},
|
|
{
|
|
"entropy": 5.314655447006226,
|
|
"epoch": 1.0357500835282325,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004898411973637532,
|
|
"loss": 4.8979,
|
|
"mean_token_accuracy": 0.20966852456331253,
|
|
"num_tokens": 22814361.0,
|
|
"step": 12400
|
|
},
|
|
{
|
|
"entropy": 5.198535823822022,
|
|
"epoch": 1.0361677246909455,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004898323511478686,
|
|
"loss": 4.8201,
|
|
"mean_token_accuracy": 0.22227233946323394,
|
|
"num_tokens": 22823780.0,
|
|
"step": 12405
|
|
},
|
|
{
|
|
"entropy": 5.199152517318725,
|
|
"epoch": 1.0365853658536586,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004898235011710851,
|
|
"loss": 4.8263,
|
|
"mean_token_accuracy": 0.20881333351135253,
|
|
"num_tokens": 22832575.0,
|
|
"step": 12410
|
|
},
|
|
{
|
|
"entropy": 5.141612768173218,
|
|
"epoch": 1.0370030070163716,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004898146474335577,
|
|
"loss": 4.694,
|
|
"mean_token_accuracy": 0.22464607059955596,
|
|
"num_tokens": 22841822.0,
|
|
"step": 12415
|
|
},
|
|
{
|
|
"entropy": 5.326311445236206,
|
|
"epoch": 1.0374206481790846,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004898057899354412,
|
|
"loss": 4.9362,
|
|
"mean_token_accuracy": 0.20533109158277513,
|
|
"num_tokens": 22851835.0,
|
|
"step": 12420
|
|
},
|
|
{
|
|
"entropy": 5.260351467132568,
|
|
"epoch": 1.0378382893417974,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000489796928676891,
|
|
"loss": 4.8762,
|
|
"mean_token_accuracy": 0.2133066847920418,
|
|
"num_tokens": 22861025.0,
|
|
"step": 12425
|
|
},
|
|
{
|
|
"entropy": 5.222363424301148,
|
|
"epoch": 1.0382559305045105,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004897880636580618,
|
|
"loss": 4.8958,
|
|
"mean_token_accuracy": 0.20730860978364946,
|
|
"num_tokens": 22869721.0,
|
|
"step": 12430
|
|
},
|
|
{
|
|
"entropy": 5.225875616073608,
|
|
"epoch": 1.0386735716672235,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000489779194879109,
|
|
"loss": 4.7773,
|
|
"mean_token_accuracy": 0.22214785516262053,
|
|
"num_tokens": 22878225.0,
|
|
"step": 12435
|
|
},
|
|
{
|
|
"entropy": 5.303024053573608,
|
|
"epoch": 1.0390912128299366,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.000489770322340188,
|
|
"loss": 4.9939,
|
|
"mean_token_accuracy": 0.20397255569696426,
|
|
"num_tokens": 22888598.0,
|
|
"step": 12440
|
|
},
|
|
{
|
|
"entropy": 5.286189794540405,
|
|
"epoch": 1.0395088539926496,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004897614460414539,
|
|
"loss": 4.9181,
|
|
"mean_token_accuracy": 0.20596157163381576,
|
|
"num_tokens": 22897326.0,
|
|
"step": 12445
|
|
},
|
|
{
|
|
"entropy": 5.272188997268676,
|
|
"epoch": 1.0399264951553626,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004897525659830623,
|
|
"loss": 4.892,
|
|
"mean_token_accuracy": 0.21004635244607925,
|
|
"num_tokens": 22906372.0,
|
|
"step": 12450
|
|
},
|
|
{
|
|
"entropy": 5.1476233959197994,
|
|
"epoch": 1.0403441363180754,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004897436821651683,
|
|
"loss": 4.7945,
|
|
"mean_token_accuracy": 0.21882567852735518,
|
|
"num_tokens": 22915987.0,
|
|
"step": 12455
|
|
},
|
|
{
|
|
"entropy": 5.261592817306519,
|
|
"epoch": 1.0407617774807885,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004897347945879278,
|
|
"loss": 4.9057,
|
|
"mean_token_accuracy": 0.21492024064064025,
|
|
"num_tokens": 22926118.0,
|
|
"step": 12460
|
|
},
|
|
{
|
|
"entropy": 5.267887306213379,
|
|
"epoch": 1.0411794186435015,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004897259032514963,
|
|
"loss": 4.8897,
|
|
"mean_token_accuracy": 0.2147431567311287,
|
|
"num_tokens": 22934813.0,
|
|
"step": 12465
|
|
},
|
|
{
|
|
"entropy": 5.290745830535888,
|
|
"epoch": 1.0415970598062145,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004897170081560292,
|
|
"loss": 4.9762,
|
|
"mean_token_accuracy": 0.20521267205476762,
|
|
"num_tokens": 22944579.0,
|
|
"step": 12470
|
|
},
|
|
{
|
|
"entropy": 5.1731892108917235,
|
|
"epoch": 1.0420147009689276,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004897081093016827,
|
|
"loss": 4.8056,
|
|
"mean_token_accuracy": 0.21805884093046188,
|
|
"num_tokens": 22953515.0,
|
|
"step": 12475
|
|
},
|
|
{
|
|
"entropy": 5.308432102203369,
|
|
"epoch": 1.0424323421316406,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004896992066886121,
|
|
"loss": 4.9452,
|
|
"mean_token_accuracy": 0.20521930903196334,
|
|
"num_tokens": 22962599.0,
|
|
"step": 12480
|
|
},
|
|
{
|
|
"entropy": 5.295512056350708,
|
|
"epoch": 1.0428499832943534,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004896903003169735,
|
|
"loss": 4.9213,
|
|
"mean_token_accuracy": 0.21884492933750152,
|
|
"num_tokens": 22971717.0,
|
|
"step": 12485
|
|
},
|
|
{
|
|
"entropy": 5.12877631187439,
|
|
"epoch": 1.0432676244570664,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004896813901869229,
|
|
"loss": 4.6963,
|
|
"mean_token_accuracy": 0.22369424402713775,
|
|
"num_tokens": 22980587.0,
|
|
"step": 12490
|
|
},
|
|
{
|
|
"entropy": 5.258592700958252,
|
|
"epoch": 1.0436852656197795,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004896724762986159,
|
|
"loss": 4.8918,
|
|
"mean_token_accuracy": 0.22188285142183303,
|
|
"num_tokens": 22990197.0,
|
|
"step": 12495
|
|
},
|
|
{
|
|
"entropy": 5.248133134841919,
|
|
"epoch": 1.0441029067824925,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004896635586522089,
|
|
"loss": 4.9721,
|
|
"mean_token_accuracy": 0.20889776945114136,
|
|
"num_tokens": 22999670.0,
|
|
"step": 12500
|
|
},
|
|
{
|
|
"entropy": 5.325403928756714,
|
|
"epoch": 1.0445205479452055,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004896546372478581,
|
|
"loss": 4.8816,
|
|
"mean_token_accuracy": 0.21454250514507295,
|
|
"num_tokens": 23008125.0,
|
|
"step": 12505
|
|
},
|
|
{
|
|
"entropy": 5.204495811462403,
|
|
"epoch": 1.0449381891079186,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004896457120857192,
|
|
"loss": 4.741,
|
|
"mean_token_accuracy": 0.22184273302555085,
|
|
"num_tokens": 23017469.0,
|
|
"step": 12510
|
|
},
|
|
{
|
|
"entropy": 5.154119539260864,
|
|
"epoch": 1.0453558302706314,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000489636783165949,
|
|
"loss": 4.9038,
|
|
"mean_token_accuracy": 0.210226671397686,
|
|
"num_tokens": 23026468.0,
|
|
"step": 12515
|
|
},
|
|
{
|
|
"entropy": 5.30165114402771,
|
|
"epoch": 1.0457734714333444,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004896278504887033,
|
|
"loss": 4.919,
|
|
"mean_token_accuracy": 0.21622417718172074,
|
|
"num_tokens": 23034944.0,
|
|
"step": 12520
|
|
},
|
|
{
|
|
"entropy": 5.202324628829956,
|
|
"epoch": 1.0461911125960575,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000489618914054139,
|
|
"loss": 4.7567,
|
|
"mean_token_accuracy": 0.22307320982217788,
|
|
"num_tokens": 23043834.0,
|
|
"step": 12525
|
|
},
|
|
{
|
|
"entropy": 5.219703674316406,
|
|
"epoch": 1.0466087537587705,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000489609973862412,
|
|
"loss": 4.8593,
|
|
"mean_token_accuracy": 0.2170213595032692,
|
|
"num_tokens": 23052542.0,
|
|
"step": 12530
|
|
},
|
|
{
|
|
"entropy": 5.323325872421265,
|
|
"epoch": 1.0470263949214835,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004896010299136793,
|
|
"loss": 4.9,
|
|
"mean_token_accuracy": 0.2150929942727089,
|
|
"num_tokens": 23061438.0,
|
|
"step": 12535
|
|
},
|
|
{
|
|
"entropy": 5.342754364013672,
|
|
"epoch": 1.0474440360841966,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004895920822080972,
|
|
"loss": 5.007,
|
|
"mean_token_accuracy": 0.2067944422364235,
|
|
"num_tokens": 23071777.0,
|
|
"step": 12540
|
|
},
|
|
{
|
|
"entropy": 5.310712909698486,
|
|
"epoch": 1.0478616772469094,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004895831307458224,
|
|
"loss": 4.8686,
|
|
"mean_token_accuracy": 0.21585914641618728,
|
|
"num_tokens": 23080889.0,
|
|
"step": 12545
|
|
},
|
|
{
|
|
"entropy": 5.240080785751343,
|
|
"epoch": 1.0482793184096224,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004895741755270115,
|
|
"loss": 4.7828,
|
|
"mean_token_accuracy": 0.21873192191123964,
|
|
"num_tokens": 23089737.0,
|
|
"step": 12550
|
|
},
|
|
{
|
|
"entropy": 5.218736934661865,
|
|
"epoch": 1.0486969595723354,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004895652165518215,
|
|
"loss": 4.8452,
|
|
"mean_token_accuracy": 0.21811958849430085,
|
|
"num_tokens": 23098861.0,
|
|
"step": 12555
|
|
},
|
|
{
|
|
"entropy": 5.239730262756348,
|
|
"epoch": 1.0491146007350485,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004895562538204091,
|
|
"loss": 4.9576,
|
|
"mean_token_accuracy": 0.20898807644844056,
|
|
"num_tokens": 23107798.0,
|
|
"step": 12560
|
|
},
|
|
{
|
|
"entropy": 5.270431709289551,
|
|
"epoch": 1.0495322418977615,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004895472873329311,
|
|
"loss": 4.7646,
|
|
"mean_token_accuracy": 0.22054098248481752,
|
|
"num_tokens": 23116698.0,
|
|
"step": 12565
|
|
},
|
|
{
|
|
"entropy": 5.308022546768188,
|
|
"epoch": 1.0499498830604745,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004895383170895447,
|
|
"loss": 4.9468,
|
|
"mean_token_accuracy": 0.20543525665998458,
|
|
"num_tokens": 23125880.0,
|
|
"step": 12570
|
|
},
|
|
{
|
|
"entropy": 5.329310703277588,
|
|
"epoch": 1.0503675242231874,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004895293430904067,
|
|
"loss": 4.9872,
|
|
"mean_token_accuracy": 0.21102734804153442,
|
|
"num_tokens": 23135633.0,
|
|
"step": 12575
|
|
},
|
|
{
|
|
"entropy": 5.177391242980957,
|
|
"epoch": 1.0507851653859004,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004895203653356745,
|
|
"loss": 4.8079,
|
|
"mean_token_accuracy": 0.21286563575267792,
|
|
"num_tokens": 23144952.0,
|
|
"step": 12580
|
|
},
|
|
{
|
|
"entropy": 5.206628942489624,
|
|
"epoch": 1.0512028065486134,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004895113838255049,
|
|
"loss": 4.8386,
|
|
"mean_token_accuracy": 0.21769546568393708,
|
|
"num_tokens": 23154128.0,
|
|
"step": 12585
|
|
},
|
|
{
|
|
"entropy": 5.196801328659058,
|
|
"epoch": 1.0516204477113265,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004895023985600555,
|
|
"loss": 4.7551,
|
|
"mean_token_accuracy": 0.2243789404630661,
|
|
"num_tokens": 23162579.0,
|
|
"step": 12590
|
|
},
|
|
{
|
|
"entropy": 5.236465883255005,
|
|
"epoch": 1.0520380888740395,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004894934095394832,
|
|
"loss": 4.8846,
|
|
"mean_token_accuracy": 0.2154398277401924,
|
|
"num_tokens": 23171889.0,
|
|
"step": 12595
|
|
},
|
|
{
|
|
"entropy": 5.1357017993927006,
|
|
"epoch": 1.0524557300367525,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004894844167639458,
|
|
"loss": 4.7473,
|
|
"mean_token_accuracy": 0.22371862083673477,
|
|
"num_tokens": 23180876.0,
|
|
"step": 12600
|
|
},
|
|
{
|
|
"entropy": 5.200278997421265,
|
|
"epoch": 1.0528733711994653,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004894754202336004,
|
|
"loss": 4.7963,
|
|
"mean_token_accuracy": 0.22279708832502365,
|
|
"num_tokens": 23189567.0,
|
|
"step": 12605
|
|
},
|
|
{
|
|
"entropy": 5.340875959396362,
|
|
"epoch": 1.0532910123621784,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004894664199486047,
|
|
"loss": 4.8088,
|
|
"mean_token_accuracy": 0.2191482588648796,
|
|
"num_tokens": 23198142.0,
|
|
"step": 12610
|
|
},
|
|
{
|
|
"entropy": 5.271886682510376,
|
|
"epoch": 1.0537086535248914,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004894574159091161,
|
|
"loss": 4.9357,
|
|
"mean_token_accuracy": 0.205353082716465,
|
|
"num_tokens": 23207143.0,
|
|
"step": 12615
|
|
},
|
|
{
|
|
"entropy": 5.265033292770386,
|
|
"epoch": 1.0541262946876044,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004894484081152922,
|
|
"loss": 4.8257,
|
|
"mean_token_accuracy": 0.2127431333065033,
|
|
"num_tokens": 23215637.0,
|
|
"step": 12620
|
|
},
|
|
{
|
|
"entropy": 5.290119171142578,
|
|
"epoch": 1.0545439358503175,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004894393965672909,
|
|
"loss": 4.8784,
|
|
"mean_token_accuracy": 0.20768315345048904,
|
|
"num_tokens": 23224402.0,
|
|
"step": 12625
|
|
},
|
|
{
|
|
"entropy": 5.412623262405395,
|
|
"epoch": 1.0549615770130305,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004894303812652698,
|
|
"loss": 5.0945,
|
|
"mean_token_accuracy": 0.20403465628623962,
|
|
"num_tokens": 23232669.0,
|
|
"step": 12630
|
|
},
|
|
{
|
|
"entropy": 5.159027528762818,
|
|
"epoch": 1.0553792181757433,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004894213622093867,
|
|
"loss": 4.8335,
|
|
"mean_token_accuracy": 0.2119513586163521,
|
|
"num_tokens": 23242204.0,
|
|
"step": 12635
|
|
},
|
|
{
|
|
"entropy": 5.239485883712769,
|
|
"epoch": 1.0557968593384564,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004894123393997997,
|
|
"loss": 4.8846,
|
|
"mean_token_accuracy": 0.21236128211021424,
|
|
"num_tokens": 23250765.0,
|
|
"step": 12640
|
|
},
|
|
{
|
|
"entropy": 5.2181117057800295,
|
|
"epoch": 1.0562145005011694,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004894033128366665,
|
|
"loss": 4.8,
|
|
"mean_token_accuracy": 0.213079571723938,
|
|
"num_tokens": 23259986.0,
|
|
"step": 12645
|
|
},
|
|
{
|
|
"entropy": 5.206310224533081,
|
|
"epoch": 1.0566321416638824,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004893942825201453,
|
|
"loss": 4.7459,
|
|
"mean_token_accuracy": 0.22099792659282685,
|
|
"num_tokens": 23268599.0,
|
|
"step": 12650
|
|
},
|
|
{
|
|
"entropy": 5.18853988647461,
|
|
"epoch": 1.0570497828265955,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000489385248450394,
|
|
"loss": 4.8011,
|
|
"mean_token_accuracy": 0.221826933324337,
|
|
"num_tokens": 23277509.0,
|
|
"step": 12655
|
|
},
|
|
{
|
|
"entropy": 5.238329982757568,
|
|
"epoch": 1.0574674239893085,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000489376210627571,
|
|
"loss": 4.8245,
|
|
"mean_token_accuracy": 0.21568035781383516,
|
|
"num_tokens": 23286673.0,
|
|
"step": 12660
|
|
},
|
|
{
|
|
"entropy": 5.272193384170532,
|
|
"epoch": 1.0578850651520213,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004893671690518343,
|
|
"loss": 4.8029,
|
|
"mean_token_accuracy": 0.22597654163837433,
|
|
"num_tokens": 23295775.0,
|
|
"step": 12665
|
|
},
|
|
{
|
|
"entropy": 5.1898030757904055,
|
|
"epoch": 1.0583027063147343,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004893581237233423,
|
|
"loss": 4.8371,
|
|
"mean_token_accuracy": 0.2201521575450897,
|
|
"num_tokens": 23305321.0,
|
|
"step": 12670
|
|
},
|
|
{
|
|
"entropy": 5.2493531703948975,
|
|
"epoch": 1.0587203474774474,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004893490746422533,
|
|
"loss": 4.8301,
|
|
"mean_token_accuracy": 0.21252137869596482,
|
|
"num_tokens": 23313798.0,
|
|
"step": 12675
|
|
},
|
|
{
|
|
"entropy": 5.161060190200805,
|
|
"epoch": 1.0591379886401604,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004893400218087258,
|
|
"loss": 4.7136,
|
|
"mean_token_accuracy": 0.22940206676721572,
|
|
"num_tokens": 23322308.0,
|
|
"step": 12680
|
|
},
|
|
{
|
|
"entropy": 5.243034315109253,
|
|
"epoch": 1.0595556298028734,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004893309652229183,
|
|
"loss": 4.9387,
|
|
"mean_token_accuracy": 0.20927054435014725,
|
|
"num_tokens": 23331311.0,
|
|
"step": 12685
|
|
},
|
|
{
|
|
"entropy": 5.332195377349853,
|
|
"epoch": 1.0599732709655865,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004893219048849891,
|
|
"loss": 4.9899,
|
|
"mean_token_accuracy": 0.2072555363178253,
|
|
"num_tokens": 23340655.0,
|
|
"step": 12690
|
|
},
|
|
{
|
|
"entropy": 5.3745348930358885,
|
|
"epoch": 1.0603909121282993,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004893128407950971,
|
|
"loss": 5.0385,
|
|
"mean_token_accuracy": 0.2032894805073738,
|
|
"num_tokens": 23350999.0,
|
|
"step": 12695
|
|
},
|
|
{
|
|
"entropy": 5.242874717712402,
|
|
"epoch": 1.0608085532910123,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004893037729534007,
|
|
"loss": 4.8493,
|
|
"mean_token_accuracy": 0.21334214508533478,
|
|
"num_tokens": 23359311.0,
|
|
"step": 12700
|
|
},
|
|
{
|
|
"entropy": 5.260963010787964,
|
|
"epoch": 1.0612261944537253,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004892947013600589,
|
|
"loss": 4.8875,
|
|
"mean_token_accuracy": 0.21278003007173538,
|
|
"num_tokens": 23367925.0,
|
|
"step": 12705
|
|
},
|
|
{
|
|
"entropy": 5.285361051559448,
|
|
"epoch": 1.0616438356164384,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004892856260152304,
|
|
"loss": 4.9906,
|
|
"mean_token_accuracy": 0.20609406679868697,
|
|
"num_tokens": 23377159.0,
|
|
"step": 12710
|
|
},
|
|
{
|
|
"entropy": 5.433383989334106,
|
|
"epoch": 1.0620614767791514,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000489276546919074,
|
|
"loss": 5.0354,
|
|
"mean_token_accuracy": 0.203872974216938,
|
|
"num_tokens": 23387699.0,
|
|
"step": 12715
|
|
},
|
|
{
|
|
"entropy": 5.326310729980468,
|
|
"epoch": 1.0624791179418644,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004892674640717488,
|
|
"loss": 4.9358,
|
|
"mean_token_accuracy": 0.20843103975057603,
|
|
"num_tokens": 23397520.0,
|
|
"step": 12720
|
|
},
|
|
{
|
|
"entropy": 5.197593927383423,
|
|
"epoch": 1.0628967591045773,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004892583774734138,
|
|
"loss": 4.8538,
|
|
"mean_token_accuracy": 0.21133932173252107,
|
|
"num_tokens": 23406853.0,
|
|
"step": 12725
|
|
},
|
|
{
|
|
"entropy": 5.201407861709595,
|
|
"epoch": 1.0633144002672903,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004892492871242278,
|
|
"loss": 4.8057,
|
|
"mean_token_accuracy": 0.21800081729888915,
|
|
"num_tokens": 23416235.0,
|
|
"step": 12730
|
|
},
|
|
{
|
|
"entropy": 5.266881322860717,
|
|
"epoch": 1.0637320414300033,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004892401930243504,
|
|
"loss": 4.8743,
|
|
"mean_token_accuracy": 0.21012381017208098,
|
|
"num_tokens": 23425347.0,
|
|
"step": 12735
|
|
},
|
|
{
|
|
"entropy": 5.3433300971984865,
|
|
"epoch": 1.0641496825927164,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004892310951739404,
|
|
"loss": 5.0425,
|
|
"mean_token_accuracy": 0.20780341923236847,
|
|
"num_tokens": 23434905.0,
|
|
"step": 12740
|
|
},
|
|
{
|
|
"entropy": 5.325739431381225,
|
|
"epoch": 1.0645673237554294,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004892219935731571,
|
|
"loss": 4.8539,
|
|
"mean_token_accuracy": 0.21316174417734146,
|
|
"num_tokens": 23444495.0,
|
|
"step": 12745
|
|
},
|
|
{
|
|
"entropy": 5.234795188903808,
|
|
"epoch": 1.0649849649181424,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00048921288822216,
|
|
"loss": 4.8296,
|
|
"mean_token_accuracy": 0.21455989480018617,
|
|
"num_tokens": 23452224.0,
|
|
"step": 12750
|
|
},
|
|
{
|
|
"entropy": 5.24503345489502,
|
|
"epoch": 1.0654026060808552,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004892037791211086,
|
|
"loss": 4.9694,
|
|
"mean_token_accuracy": 0.2096216395497322,
|
|
"num_tokens": 23461987.0,
|
|
"step": 12755
|
|
},
|
|
{
|
|
"entropy": 5.12617859840393,
|
|
"epoch": 1.0658202472435683,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004891946662701621,
|
|
"loss": 4.8025,
|
|
"mean_token_accuracy": 0.22298409044742584,
|
|
"num_tokens": 23470645.0,
|
|
"step": 12760
|
|
},
|
|
{
|
|
"entropy": 5.283561658859253,
|
|
"epoch": 1.0662378884062813,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004891855496694801,
|
|
"loss": 4.969,
|
|
"mean_token_accuracy": 0.20727645605802536,
|
|
"num_tokens": 23480169.0,
|
|
"step": 12765
|
|
},
|
|
{
|
|
"entropy": 5.3262427806854244,
|
|
"epoch": 1.0666555295689943,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004891764293192222,
|
|
"loss": 4.9041,
|
|
"mean_token_accuracy": 0.20949862152338028,
|
|
"num_tokens": 23488630.0,
|
|
"step": 12770
|
|
},
|
|
{
|
|
"entropy": 5.247120904922485,
|
|
"epoch": 1.0670731707317074,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004891673052195482,
|
|
"loss": 4.7783,
|
|
"mean_token_accuracy": 0.21573328971862793,
|
|
"num_tokens": 23497800.0,
|
|
"step": 12775
|
|
},
|
|
{
|
|
"entropy": 5.256953620910645,
|
|
"epoch": 1.0674908118944204,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004891581773706177,
|
|
"loss": 4.9636,
|
|
"mean_token_accuracy": 0.20531099736690522,
|
|
"num_tokens": 23507400.0,
|
|
"step": 12780
|
|
},
|
|
{
|
|
"entropy": 5.323882818222046,
|
|
"epoch": 1.0679084530571332,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004891490457725906,
|
|
"loss": 4.9736,
|
|
"mean_token_accuracy": 0.19991584420204161,
|
|
"num_tokens": 23516441.0,
|
|
"step": 12785
|
|
},
|
|
{
|
|
"entropy": 5.272881507873535,
|
|
"epoch": 1.0683260942198463,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004891399104256266,
|
|
"loss": 4.8408,
|
|
"mean_token_accuracy": 0.2110961526632309,
|
|
"num_tokens": 23525066.0,
|
|
"step": 12790
|
|
},
|
|
{
|
|
"entropy": 5.164448976516724,
|
|
"epoch": 1.0687437353825593,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004891307713298857,
|
|
"loss": 4.7682,
|
|
"mean_token_accuracy": 0.22332222163677215,
|
|
"num_tokens": 23533892.0,
|
|
"step": 12795
|
|
},
|
|
{
|
|
"entropy": 5.234396314620971,
|
|
"epoch": 1.0691613765452723,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000489121628485528,
|
|
"loss": 4.921,
|
|
"mean_token_accuracy": 0.20590850263833999,
|
|
"num_tokens": 23542680.0,
|
|
"step": 12800
|
|
},
|
|
{
|
|
"entropy": 5.208740949630737,
|
|
"epoch": 1.0695790177079854,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004891124818927133,
|
|
"loss": 4.7439,
|
|
"mean_token_accuracy": 0.22733963876962662,
|
|
"num_tokens": 23550573.0,
|
|
"step": 12805
|
|
},
|
|
{
|
|
"entropy": 5.14765510559082,
|
|
"epoch": 1.0699966588706984,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004891033315516019,
|
|
"loss": 4.871,
|
|
"mean_token_accuracy": 0.20837533175945283,
|
|
"num_tokens": 23561281.0,
|
|
"step": 12810
|
|
},
|
|
{
|
|
"entropy": 5.175348997116089,
|
|
"epoch": 1.0704143000334112,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004890941774623541,
|
|
"loss": 4.7753,
|
|
"mean_token_accuracy": 0.22325708270072936,
|
|
"num_tokens": 23569846.0,
|
|
"step": 12815
|
|
},
|
|
{
|
|
"entropy": 5.246774053573608,
|
|
"epoch": 1.0708319411961242,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004890850196251299,
|
|
"loss": 4.775,
|
|
"mean_token_accuracy": 0.22480323761701584,
|
|
"num_tokens": 23578145.0,
|
|
"step": 12820
|
|
},
|
|
{
|
|
"entropy": 5.244913959503174,
|
|
"epoch": 1.0712495823588373,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004890758580400898,
|
|
"loss": 4.8657,
|
|
"mean_token_accuracy": 0.21745838969945908,
|
|
"num_tokens": 23587494.0,
|
|
"step": 12825
|
|
},
|
|
{
|
|
"entropy": 5.301851034164429,
|
|
"epoch": 1.0716672235215503,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004890666927073941,
|
|
"loss": 4.9667,
|
|
"mean_token_accuracy": 0.20601084977388381,
|
|
"num_tokens": 23596599.0,
|
|
"step": 12830
|
|
},
|
|
{
|
|
"entropy": 5.231004095077514,
|
|
"epoch": 1.0720848646842633,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004890575236272032,
|
|
"loss": 4.8993,
|
|
"mean_token_accuracy": 0.21948205232620238,
|
|
"num_tokens": 23606170.0,
|
|
"step": 12835
|
|
},
|
|
{
|
|
"entropy": 5.178211688995361,
|
|
"epoch": 1.0725025058469764,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004890483507996778,
|
|
"loss": 4.7243,
|
|
"mean_token_accuracy": 0.22773199379444123,
|
|
"num_tokens": 23614558.0,
|
|
"step": 12840
|
|
},
|
|
{
|
|
"entropy": 5.276197814941407,
|
|
"epoch": 1.0729201470096892,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004890391742249783,
|
|
"loss": 4.9137,
|
|
"mean_token_accuracy": 0.20629681050777435,
|
|
"num_tokens": 23624125.0,
|
|
"step": 12845
|
|
},
|
|
{
|
|
"entropy": 5.331362676620484,
|
|
"epoch": 1.0733377881724022,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004890299939032654,
|
|
"loss": 4.8673,
|
|
"mean_token_accuracy": 0.21477816253900528,
|
|
"num_tokens": 23633025.0,
|
|
"step": 12850
|
|
},
|
|
{
|
|
"entropy": 5.195815515518189,
|
|
"epoch": 1.0737554293351153,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004890208098346999,
|
|
"loss": 4.8393,
|
|
"mean_token_accuracy": 0.21111361682415009,
|
|
"num_tokens": 23643387.0,
|
|
"step": 12855
|
|
},
|
|
{
|
|
"entropy": 5.27276873588562,
|
|
"epoch": 1.0741730704978283,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004890116220194425,
|
|
"loss": 4.9075,
|
|
"mean_token_accuracy": 0.2139476865530014,
|
|
"num_tokens": 23653486.0,
|
|
"step": 12860
|
|
},
|
|
{
|
|
"entropy": 5.220895195007325,
|
|
"epoch": 1.0745907116605413,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000489002430457654,
|
|
"loss": 4.8141,
|
|
"mean_token_accuracy": 0.21765146255493165,
|
|
"num_tokens": 23663483.0,
|
|
"step": 12865
|
|
},
|
|
{
|
|
"entropy": 5.154907131195069,
|
|
"epoch": 1.0750083528232544,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004889932351494954,
|
|
"loss": 4.8482,
|
|
"mean_token_accuracy": 0.22139590978622437,
|
|
"num_tokens": 23672453.0,
|
|
"step": 12870
|
|
},
|
|
{
|
|
"entropy": 5.225982189178467,
|
|
"epoch": 1.0754259939859672,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004889840360951277,
|
|
"loss": 4.8494,
|
|
"mean_token_accuracy": 0.21532514393329621,
|
|
"num_tokens": 23681351.0,
|
|
"step": 12875
|
|
},
|
|
{
|
|
"entropy": 5.282834005355835,
|
|
"epoch": 1.0758436351486802,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004889748332947118,
|
|
"loss": 4.8396,
|
|
"mean_token_accuracy": 0.2157393217086792,
|
|
"num_tokens": 23689581.0,
|
|
"step": 12880
|
|
},
|
|
{
|
|
"entropy": 5.29621844291687,
|
|
"epoch": 1.0762612763113932,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004889656267484089,
|
|
"loss": 4.9479,
|
|
"mean_token_accuracy": 0.2063759222626686,
|
|
"num_tokens": 23699415.0,
|
|
"step": 12885
|
|
},
|
|
{
|
|
"entropy": 5.263041591644287,
|
|
"epoch": 1.0766789174741063,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00048895641645638,
|
|
"loss": 4.8733,
|
|
"mean_token_accuracy": 0.22042959928512573,
|
|
"num_tokens": 23708933.0,
|
|
"step": 12890
|
|
},
|
|
{
|
|
"entropy": 5.2040527820587155,
|
|
"epoch": 1.0770965586368193,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004889472024187867,
|
|
"loss": 4.9001,
|
|
"mean_token_accuracy": 0.20418200343847276,
|
|
"num_tokens": 23718423.0,
|
|
"step": 12895
|
|
},
|
|
{
|
|
"entropy": 5.266914939880371,
|
|
"epoch": 1.0775141997995323,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00048893798463579,
|
|
"loss": 4.8814,
|
|
"mean_token_accuracy": 0.21385739594697953,
|
|
"num_tokens": 23728131.0,
|
|
"step": 12900
|
|
},
|
|
{
|
|
"entropy": 5.255648756027222,
|
|
"epoch": 1.0779318409622451,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004889287631075513,
|
|
"loss": 4.8798,
|
|
"mean_token_accuracy": 0.21327996402978897,
|
|
"num_tokens": 23737378.0,
|
|
"step": 12905
|
|
},
|
|
{
|
|
"entropy": 5.393601131439209,
|
|
"epoch": 1.0783494821249582,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004889195378342322,
|
|
"loss": 4.9631,
|
|
"mean_token_accuracy": 0.20549146980047225,
|
|
"num_tokens": 23747156.0,
|
|
"step": 12910
|
|
},
|
|
{
|
|
"entropy": 5.313196468353271,
|
|
"epoch": 1.0787671232876712,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004889103088159941,
|
|
"loss": 4.9167,
|
|
"mean_token_accuracy": 0.20896490216255187,
|
|
"num_tokens": 23757090.0,
|
|
"step": 12915
|
|
},
|
|
{
|
|
"entropy": 5.211637783050537,
|
|
"epoch": 1.0791847644503842,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004889010760529986,
|
|
"loss": 4.901,
|
|
"mean_token_accuracy": 0.21270398050546646,
|
|
"num_tokens": 23766679.0,
|
|
"step": 12920
|
|
},
|
|
{
|
|
"entropy": 5.214770030975342,
|
|
"epoch": 1.0796024056130973,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004888918395454071,
|
|
"loss": 4.7799,
|
|
"mean_token_accuracy": 0.23126090615987777,
|
|
"num_tokens": 23775109.0,
|
|
"step": 12925
|
|
},
|
|
{
|
|
"entropy": 5.235091638565064,
|
|
"epoch": 1.0800200467758103,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004888825992933817,
|
|
"loss": 4.8665,
|
|
"mean_token_accuracy": 0.22285349369049073,
|
|
"num_tokens": 23784698.0,
|
|
"step": 12930
|
|
},
|
|
{
|
|
"entropy": 5.162795639038086,
|
|
"epoch": 1.0804376879385231,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004888733552970839,
|
|
"loss": 4.783,
|
|
"mean_token_accuracy": 0.21931341737508775,
|
|
"num_tokens": 23793590.0,
|
|
"step": 12935
|
|
},
|
|
{
|
|
"entropy": 5.234830904006958,
|
|
"epoch": 1.0808553291012362,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004888641075566755,
|
|
"loss": 4.8153,
|
|
"mean_token_accuracy": 0.21681467294692994,
|
|
"num_tokens": 23802421.0,
|
|
"step": 12940
|
|
},
|
|
{
|
|
"entropy": 5.305587816238403,
|
|
"epoch": 1.0812729702639492,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004888548560723184,
|
|
"loss": 4.9384,
|
|
"mean_token_accuracy": 0.20567968487739563,
|
|
"num_tokens": 23811610.0,
|
|
"step": 12945
|
|
},
|
|
{
|
|
"entropy": 5.358579158782959,
|
|
"epoch": 1.0816906114266622,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004888456008441748,
|
|
"loss": 4.9246,
|
|
"mean_token_accuracy": 0.21314588636159898,
|
|
"num_tokens": 23821197.0,
|
|
"step": 12950
|
|
},
|
|
{
|
|
"entropy": 5.305755949020385,
|
|
"epoch": 1.0821082525893753,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004888363418724064,
|
|
"loss": 4.8976,
|
|
"mean_token_accuracy": 0.21083300411701203,
|
|
"num_tokens": 23829757.0,
|
|
"step": 12955
|
|
},
|
|
{
|
|
"entropy": 5.256096267700196,
|
|
"epoch": 1.0825258937520883,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004888270791571756,
|
|
"loss": 4.8789,
|
|
"mean_token_accuracy": 0.20821415036916732,
|
|
"num_tokens": 23839242.0,
|
|
"step": 12960
|
|
},
|
|
{
|
|
"entropy": 5.2185557842254635,
|
|
"epoch": 1.082943534914801,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004888178126986444,
|
|
"loss": 4.8062,
|
|
"mean_token_accuracy": 0.2222756028175354,
|
|
"num_tokens": 23848193.0,
|
|
"step": 12965
|
|
},
|
|
{
|
|
"entropy": 5.206289672851563,
|
|
"epoch": 1.0833611760775141,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004888085424969748,
|
|
"loss": 4.8161,
|
|
"mean_token_accuracy": 0.2184004858136177,
|
|
"num_tokens": 23857623.0,
|
|
"step": 12970
|
|
},
|
|
{
|
|
"entropy": 5.274158000946045,
|
|
"epoch": 1.0837788172402272,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004887992685523295,
|
|
"loss": 4.9401,
|
|
"mean_token_accuracy": 0.20634313374757768,
|
|
"num_tokens": 23866424.0,
|
|
"step": 12975
|
|
},
|
|
{
|
|
"entropy": 5.266625165939331,
|
|
"epoch": 1.0841964584029402,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004887899908648706,
|
|
"loss": 4.9671,
|
|
"mean_token_accuracy": 0.20892710983753204,
|
|
"num_tokens": 23874855.0,
|
|
"step": 12980
|
|
},
|
|
{
|
|
"entropy": 5.29748010635376,
|
|
"epoch": 1.0846140995656532,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004887807094347606,
|
|
"loss": 4.9139,
|
|
"mean_token_accuracy": 0.21877105683088302,
|
|
"num_tokens": 23884634.0,
|
|
"step": 12985
|
|
},
|
|
{
|
|
"entropy": 5.3081128120422365,
|
|
"epoch": 1.0850317407283663,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004887714242621619,
|
|
"loss": 4.9387,
|
|
"mean_token_accuracy": 0.21209346801042556,
|
|
"num_tokens": 23894307.0,
|
|
"step": 12990
|
|
},
|
|
{
|
|
"entropy": 5.284110593795776,
|
|
"epoch": 1.085449381891079,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004887621353472371,
|
|
"loss": 4.8401,
|
|
"mean_token_accuracy": 0.21807993352413177,
|
|
"num_tokens": 23903274.0,
|
|
"step": 12995
|
|
},
|
|
{
|
|
"entropy": 5.253281974792481,
|
|
"epoch": 1.0858670230537921,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004887528426901488,
|
|
"loss": 4.8879,
|
|
"mean_token_accuracy": 0.21700274348258972,
|
|
"num_tokens": 23912787.0,
|
|
"step": 13000
|
|
},
|
|
{
|
|
"entropy": 5.313509750366211,
|
|
"epoch": 1.0862846642165052,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004887435462910597,
|
|
"loss": 4.9246,
|
|
"mean_token_accuracy": 0.20294243544340135,
|
|
"num_tokens": 23921558.0,
|
|
"step": 13005
|
|
},
|
|
{
|
|
"entropy": 5.240981197357177,
|
|
"epoch": 1.0867023053792182,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004887342461501326,
|
|
"loss": 4.833,
|
|
"mean_token_accuracy": 0.21029905676841737,
|
|
"num_tokens": 23929868.0,
|
|
"step": 13010
|
|
},
|
|
{
|
|
"entropy": 5.267163228988648,
|
|
"epoch": 1.0871199465419312,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004887249422675301,
|
|
"loss": 4.9146,
|
|
"mean_token_accuracy": 0.2056149274110794,
|
|
"num_tokens": 23939206.0,
|
|
"step": 13015
|
|
},
|
|
{
|
|
"entropy": 5.295957279205322,
|
|
"epoch": 1.0875375877046443,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004887156346434154,
|
|
"loss": 4.8385,
|
|
"mean_token_accuracy": 0.21635652482509612,
|
|
"num_tokens": 23948213.0,
|
|
"step": 13020
|
|
},
|
|
{
|
|
"entropy": 5.2973119735717775,
|
|
"epoch": 1.087955228867357,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004887063232779513,
|
|
"loss": 4.8759,
|
|
"mean_token_accuracy": 0.20758889764547347,
|
|
"num_tokens": 23957269.0,
|
|
"step": 13025
|
|
},
|
|
{
|
|
"entropy": 5.319609594345093,
|
|
"epoch": 1.08837287003007,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004886970081713006,
|
|
"loss": 4.9792,
|
|
"mean_token_accuracy": 0.20867991149425508,
|
|
"num_tokens": 23967300.0,
|
|
"step": 13030
|
|
},
|
|
{
|
|
"entropy": 5.253187561035157,
|
|
"epoch": 1.0887905111927831,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004886876893236266,
|
|
"loss": 4.8786,
|
|
"mean_token_accuracy": 0.21111573725938798,
|
|
"num_tokens": 23976934.0,
|
|
"step": 13035
|
|
},
|
|
{
|
|
"entropy": 5.2428669929504395,
|
|
"epoch": 1.0892081523554962,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004886783667350925,
|
|
"loss": 4.8707,
|
|
"mean_token_accuracy": 0.215206877887249,
|
|
"num_tokens": 23986119.0,
|
|
"step": 13040
|
|
},
|
|
{
|
|
"entropy": 5.221693515777588,
|
|
"epoch": 1.0896257935182092,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004886690404058613,
|
|
"loss": 4.8752,
|
|
"mean_token_accuracy": 0.21931690126657485,
|
|
"num_tokens": 23996093.0,
|
|
"step": 13045
|
|
},
|
|
{
|
|
"entropy": 5.384117126464844,
|
|
"epoch": 1.0900434346809222,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004886597103360963,
|
|
"loss": 5.0152,
|
|
"mean_token_accuracy": 0.20356177389621735,
|
|
"num_tokens": 24006585.0,
|
|
"step": 13050
|
|
},
|
|
{
|
|
"entropy": 5.323095989227295,
|
|
"epoch": 1.090461075843635,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004886503765259609,
|
|
"loss": 4.946,
|
|
"mean_token_accuracy": 0.20784655213356018,
|
|
"num_tokens": 24016398.0,
|
|
"step": 13055
|
|
},
|
|
{
|
|
"entropy": 5.270521593093872,
|
|
"epoch": 1.090878717006348,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004886410389756186,
|
|
"loss": 4.8055,
|
|
"mean_token_accuracy": 0.21096160411834716,
|
|
"num_tokens": 24025988.0,
|
|
"step": 13060
|
|
},
|
|
{
|
|
"entropy": 5.294621849060059,
|
|
"epoch": 1.0912963581690611,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004886316976852326,
|
|
"loss": 4.8889,
|
|
"mean_token_accuracy": 0.21662607640028,
|
|
"num_tokens": 24036448.0,
|
|
"step": 13065
|
|
},
|
|
{
|
|
"entropy": 5.314312362670899,
|
|
"epoch": 1.0917139993317742,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004886223526549666,
|
|
"loss": 5.0186,
|
|
"mean_token_accuracy": 0.19912010580301284,
|
|
"num_tokens": 24047011.0,
|
|
"step": 13070
|
|
},
|
|
{
|
|
"entropy": 5.258068323135376,
|
|
"epoch": 1.0921316404944872,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004886130038849843,
|
|
"loss": 4.7831,
|
|
"mean_token_accuracy": 0.21857234984636306,
|
|
"num_tokens": 24056332.0,
|
|
"step": 13075
|
|
},
|
|
{
|
|
"entropy": 5.2940908908844,
|
|
"epoch": 1.0925492816572002,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004886036513754491,
|
|
"loss": 4.9572,
|
|
"mean_token_accuracy": 0.2143129900097847,
|
|
"num_tokens": 24065538.0,
|
|
"step": 13080
|
|
},
|
|
{
|
|
"entropy": 5.244616365432739,
|
|
"epoch": 1.092966922819913,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004885942951265251,
|
|
"loss": 4.8822,
|
|
"mean_token_accuracy": 0.21415428519248964,
|
|
"num_tokens": 24074950.0,
|
|
"step": 13085
|
|
},
|
|
{
|
|
"entropy": 5.342571878433228,
|
|
"epoch": 1.093384563982626,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004885849351383756,
|
|
"loss": 4.9397,
|
|
"mean_token_accuracy": 0.20828969031572342,
|
|
"num_tokens": 24084571.0,
|
|
"step": 13090
|
|
},
|
|
{
|
|
"entropy": 5.284383773803711,
|
|
"epoch": 1.093802205145339,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004885755714111649,
|
|
"loss": 4.9368,
|
|
"mean_token_accuracy": 0.21385575979948043,
|
|
"num_tokens": 24093693.0,
|
|
"step": 13095
|
|
},
|
|
{
|
|
"entropy": 5.254420137405395,
|
|
"epoch": 1.0942198463080521,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004885662039450565,
|
|
"loss": 4.8478,
|
|
"mean_token_accuracy": 0.21234063804149628,
|
|
"num_tokens": 24104140.0,
|
|
"step": 13100
|
|
},
|
|
{
|
|
"entropy": 5.3212908744812015,
|
|
"epoch": 1.0946374874707652,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004885568327402149,
|
|
"loss": 4.8459,
|
|
"mean_token_accuracy": 0.21311513632535933,
|
|
"num_tokens": 24113107.0,
|
|
"step": 13105
|
|
},
|
|
{
|
|
"entropy": 5.3180910587310795,
|
|
"epoch": 1.0950551286334782,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004885474577968038,
|
|
"loss": 4.8882,
|
|
"mean_token_accuracy": 0.21377133280038835,
|
|
"num_tokens": 24122271.0,
|
|
"step": 13110
|
|
},
|
|
{
|
|
"entropy": 5.316606426239014,
|
|
"epoch": 1.095472769796191,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004885380791149874,
|
|
"loss": 4.9416,
|
|
"mean_token_accuracy": 0.2065939873456955,
|
|
"num_tokens": 24132068.0,
|
|
"step": 13115
|
|
},
|
|
{
|
|
"entropy": 5.257716321945191,
|
|
"epoch": 1.095890410958904,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004885286966949298,
|
|
"loss": 4.8539,
|
|
"mean_token_accuracy": 0.20893142819404603,
|
|
"num_tokens": 24140429.0,
|
|
"step": 13120
|
|
},
|
|
{
|
|
"entropy": 5.243165111541748,
|
|
"epoch": 1.096308052121617,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004885193105367955,
|
|
"loss": 4.9655,
|
|
"mean_token_accuracy": 0.20797942876815795,
|
|
"num_tokens": 24150563.0,
|
|
"step": 13125
|
|
},
|
|
{
|
|
"entropy": 5.333548974990845,
|
|
"epoch": 1.0967256932843301,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004885099206407486,
|
|
"loss": 4.8702,
|
|
"mean_token_accuracy": 0.21010884195566176,
|
|
"num_tokens": 24159059.0,
|
|
"step": 13130
|
|
},
|
|
{
|
|
"entropy": 5.361559534072876,
|
|
"epoch": 1.0971433344470432,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004885005270069535,
|
|
"loss": 5.007,
|
|
"mean_token_accuracy": 0.2091026335954666,
|
|
"num_tokens": 24168858.0,
|
|
"step": 13135
|
|
},
|
|
{
|
|
"entropy": 5.247330236434936,
|
|
"epoch": 1.0975609756097562,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004884911296355746,
|
|
"loss": 4.9056,
|
|
"mean_token_accuracy": 0.21442289054393768,
|
|
"num_tokens": 24177573.0,
|
|
"step": 13140
|
|
},
|
|
{
|
|
"entropy": 5.290609979629517,
|
|
"epoch": 1.097978616772469,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004884817285267766,
|
|
"loss": 4.835,
|
|
"mean_token_accuracy": 0.2175571784377098,
|
|
"num_tokens": 24186832.0,
|
|
"step": 13145
|
|
},
|
|
{
|
|
"entropy": 5.269421339035034,
|
|
"epoch": 1.098396257935182,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004884723236807239,
|
|
"loss": 4.8665,
|
|
"mean_token_accuracy": 0.21292252093553543,
|
|
"num_tokens": 24195281.0,
|
|
"step": 13150
|
|
},
|
|
{
|
|
"entropy": 5.289570999145508,
|
|
"epoch": 1.098813899097895,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004884629150975814,
|
|
"loss": 4.8824,
|
|
"mean_token_accuracy": 0.2166883170604706,
|
|
"num_tokens": 24204499.0,
|
|
"step": 13155
|
|
},
|
|
{
|
|
"entropy": 5.217087936401367,
|
|
"epoch": 1.099231540260608,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004884535027775135,
|
|
"loss": 4.7527,
|
|
"mean_token_accuracy": 0.2241186112165451,
|
|
"num_tokens": 24213418.0,
|
|
"step": 13160
|
|
},
|
|
{
|
|
"entropy": 5.177638196945191,
|
|
"epoch": 1.0996491814233211,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004884440867206851,
|
|
"loss": 4.7634,
|
|
"mean_token_accuracy": 0.22278998792171478,
|
|
"num_tokens": 24222834.0,
|
|
"step": 13165
|
|
},
|
|
{
|
|
"entropy": 5.22744927406311,
|
|
"epoch": 1.1000668225860342,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000488434666927261,
|
|
"loss": 4.8797,
|
|
"mean_token_accuracy": 0.20938977748155593,
|
|
"num_tokens": 24231821.0,
|
|
"step": 13170
|
|
},
|
|
{
|
|
"entropy": 5.330484199523926,
|
|
"epoch": 1.100484463748747,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004884252433974062,
|
|
"loss": 4.8752,
|
|
"mean_token_accuracy": 0.2122475102543831,
|
|
"num_tokens": 24240694.0,
|
|
"step": 13175
|
|
},
|
|
{
|
|
"entropy": 5.296904993057251,
|
|
"epoch": 1.10090210491146,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004884158161312856,
|
|
"loss": 4.9057,
|
|
"mean_token_accuracy": 0.21260667890310286,
|
|
"num_tokens": 24249927.0,
|
|
"step": 13180
|
|
},
|
|
{
|
|
"entropy": 5.280317640304565,
|
|
"epoch": 1.101319746074173,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004884063851290642,
|
|
"loss": 4.8504,
|
|
"mean_token_accuracy": 0.21274223178625107,
|
|
"num_tokens": 24259174.0,
|
|
"step": 13185
|
|
},
|
|
{
|
|
"entropy": 5.27933702468872,
|
|
"epoch": 1.101737387236886,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004883969503909073,
|
|
"loss": 4.9052,
|
|
"mean_token_accuracy": 0.20883871912956237,
|
|
"num_tokens": 24268381.0,
|
|
"step": 13190
|
|
},
|
|
{
|
|
"entropy": 5.323480939865112,
|
|
"epoch": 1.1021550283995991,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004883875119169798,
|
|
"loss": 4.9408,
|
|
"mean_token_accuracy": 0.20760657638311386,
|
|
"num_tokens": 24277916.0,
|
|
"step": 13195
|
|
},
|
|
{
|
|
"entropy": 5.298346710205078,
|
|
"epoch": 1.1025726695623121,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000488378069707447,
|
|
"loss": 4.9606,
|
|
"mean_token_accuracy": 0.20857729017734528,
|
|
"num_tokens": 24287530.0,
|
|
"step": 13200
|
|
},
|
|
{
|
|
"entropy": 5.312605333328247,
|
|
"epoch": 1.102990310725025,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004883686237624744,
|
|
"loss": 5.077,
|
|
"mean_token_accuracy": 0.1996668115258217,
|
|
"num_tokens": 24298239.0,
|
|
"step": 13205
|
|
},
|
|
{
|
|
"entropy": 5.363008069992065,
|
|
"epoch": 1.103407951887738,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004883591740822271,
|
|
"loss": 4.88,
|
|
"mean_token_accuracy": 0.21105607151985167,
|
|
"num_tokens": 24307001.0,
|
|
"step": 13210
|
|
},
|
|
{
|
|
"entropy": 5.278348159790039,
|
|
"epoch": 1.103825593050451,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004883497206668707,
|
|
"loss": 4.8469,
|
|
"mean_token_accuracy": 0.21925781965255736,
|
|
"num_tokens": 24315995.0,
|
|
"step": 13215
|
|
},
|
|
{
|
|
"entropy": 5.215962266921997,
|
|
"epoch": 1.104243234213164,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004883402635165705,
|
|
"loss": 4.7904,
|
|
"mean_token_accuracy": 0.22126712501049042,
|
|
"num_tokens": 24324421.0,
|
|
"step": 13220
|
|
},
|
|
{
|
|
"entropy": 5.257588195800781,
|
|
"epoch": 1.104660875375877,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004883308026314923,
|
|
"loss": 4.9346,
|
|
"mean_token_accuracy": 0.20851405411958696,
|
|
"num_tokens": 24333715.0,
|
|
"step": 13225
|
|
},
|
|
{
|
|
"entropy": 5.256224346160889,
|
|
"epoch": 1.1050785165385901,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004883213380118016,
|
|
"loss": 4.83,
|
|
"mean_token_accuracy": 0.22057849317789077,
|
|
"num_tokens": 24342085.0,
|
|
"step": 13230
|
|
},
|
|
{
|
|
"entropy": 5.3145623207092285,
|
|
"epoch": 1.105496157701303,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004883118696576642,
|
|
"loss": 4.9425,
|
|
"mean_token_accuracy": 0.20948053449392318,
|
|
"num_tokens": 24350906.0,
|
|
"step": 13235
|
|
},
|
|
{
|
|
"entropy": 5.172192621231079,
|
|
"epoch": 1.105913798864016,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004883023975692457,
|
|
"loss": 4.796,
|
|
"mean_token_accuracy": 0.2146312952041626,
|
|
"num_tokens": 24359948.0,
|
|
"step": 13240
|
|
},
|
|
{
|
|
"entropy": 5.146786546707153,
|
|
"epoch": 1.106331440026729,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004882929217467118,
|
|
"loss": 4.7891,
|
|
"mean_token_accuracy": 0.22188411504030228,
|
|
"num_tokens": 24369440.0,
|
|
"step": 13245
|
|
},
|
|
{
|
|
"entropy": 5.267632722854614,
|
|
"epoch": 1.106749081189442,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004882834421902287,
|
|
"loss": 4.9023,
|
|
"mean_token_accuracy": 0.217054283618927,
|
|
"num_tokens": 24378442.0,
|
|
"step": 13250
|
|
},
|
|
{
|
|
"entropy": 5.24805588722229,
|
|
"epoch": 1.107166722352155,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00048827395889996226,
|
|
"loss": 4.8657,
|
|
"mean_token_accuracy": 0.21462470591068267,
|
|
"num_tokens": 24387750.0,
|
|
"step": 13255
|
|
},
|
|
{
|
|
"entropy": 5.220867919921875,
|
|
"epoch": 1.107584363514868,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004882644718760784,
|
|
"loss": 4.6942,
|
|
"mean_token_accuracy": 0.2271432861685753,
|
|
"num_tokens": 24396380.0,
|
|
"step": 13260
|
|
},
|
|
{
|
|
"entropy": 5.190722513198852,
|
|
"epoch": 1.108002004677581,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00048825498111874325,
|
|
"loss": 4.7734,
|
|
"mean_token_accuracy": 0.22173280864953995,
|
|
"num_tokens": 24405135.0,
|
|
"step": 13265
|
|
},
|
|
{
|
|
"entropy": 5.221589279174805,
|
|
"epoch": 1.108419645840294,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00048824548662812294,
|
|
"loss": 4.8912,
|
|
"mean_token_accuracy": 0.21462031900882722,
|
|
"num_tokens": 24413517.0,
|
|
"step": 13270
|
|
},
|
|
{
|
|
"entropy": 5.300827264785767,
|
|
"epoch": 1.108837287003007,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00048823598840438384,
|
|
"loss": 4.8781,
|
|
"mean_token_accuracy": 0.21618583798408508,
|
|
"num_tokens": 24422170.0,
|
|
"step": 13275
|
|
},
|
|
{
|
|
"entropy": 5.380620670318604,
|
|
"epoch": 1.10925492816572,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00048822648644769194,
|
|
"loss": 5.0515,
|
|
"mean_token_accuracy": 0.20042121708393096,
|
|
"num_tokens": 24431083.0,
|
|
"step": 13280
|
|
},
|
|
{
|
|
"entropy": 5.317094182968139,
|
|
"epoch": 1.109672569328433,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004882169807582138,
|
|
"loss": 4.907,
|
|
"mean_token_accuracy": 0.21104125678539276,
|
|
"num_tokens": 24440582.0,
|
|
"step": 13285
|
|
},
|
|
{
|
|
"entropy": 5.258843660354614,
|
|
"epoch": 1.110090210491146,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004882074713361157,
|
|
"loss": 4.8593,
|
|
"mean_token_accuracy": 0.21963223367929458,
|
|
"num_tokens": 24450047.0,
|
|
"step": 13290
|
|
},
|
|
{
|
|
"entropy": 5.187111759185791,
|
|
"epoch": 1.110507851653859,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004881979581815642,
|
|
"loss": 4.7506,
|
|
"mean_token_accuracy": 0.2230774387717247,
|
|
"num_tokens": 24457955.0,
|
|
"step": 13295
|
|
},
|
|
{
|
|
"entropy": 5.157816219329834,
|
|
"epoch": 1.110925492816572,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004881884412947259,
|
|
"loss": 4.7375,
|
|
"mean_token_accuracy": 0.22246803045272828,
|
|
"num_tokens": 24467394.0,
|
|
"step": 13300
|
|
},
|
|
{
|
|
"entropy": 5.20101900100708,
|
|
"epoch": 1.111343133979285,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00048817892067576726,
|
|
"loss": 4.8045,
|
|
"mean_token_accuracy": 0.22106245458126067,
|
|
"num_tokens": 24476386.0,
|
|
"step": 13305
|
|
},
|
|
{
|
|
"entropy": 5.172140645980835,
|
|
"epoch": 1.111760775141998,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000488169396324855,
|
|
"loss": 4.8518,
|
|
"mean_token_accuracy": 0.21915037781000138,
|
|
"num_tokens": 24484800.0,
|
|
"step": 13310
|
|
},
|
|
{
|
|
"entropy": 5.250047302246093,
|
|
"epoch": 1.112178416304711,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00048815986824215585,
|
|
"loss": 4.8246,
|
|
"mean_token_accuracy": 0.21919767558574677,
|
|
"num_tokens": 24494252.0,
|
|
"step": 13315
|
|
},
|
|
{
|
|
"entropy": 5.297379779815674,
|
|
"epoch": 1.112596057467424,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004881503364278366,
|
|
"loss": 4.8766,
|
|
"mean_token_accuracy": 0.21669656187295913,
|
|
"num_tokens": 24503315.0,
|
|
"step": 13320
|
|
},
|
|
{
|
|
"entropy": 5.274254083633423,
|
|
"epoch": 1.1130136986301369,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004881408008820642,
|
|
"loss": 4.8453,
|
|
"mean_token_accuracy": 0.21772542744874954,
|
|
"num_tokens": 24512660.0,
|
|
"step": 13325
|
|
},
|
|
{
|
|
"entropy": 5.247271299362183,
|
|
"epoch": 1.11343133979285,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00048813126160500555,
|
|
"loss": 4.8654,
|
|
"mean_token_accuracy": 0.21289616972208023,
|
|
"num_tokens": 24521712.0,
|
|
"step": 13330
|
|
},
|
|
{
|
|
"entropy": 5.1636631965637205,
|
|
"epoch": 1.113848980955563,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004881217185968276,
|
|
"loss": 4.8193,
|
|
"mean_token_accuracy": 0.2247433453798294,
|
|
"num_tokens": 24529851.0,
|
|
"step": 13335
|
|
},
|
|
{
|
|
"entropy": 5.279679250717163,
|
|
"epoch": 1.114266622118276,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004881121718576974,
|
|
"loss": 4.8629,
|
|
"mean_token_accuracy": 0.2155037820339203,
|
|
"num_tokens": 24538425.0,
|
|
"step": 13340
|
|
},
|
|
{
|
|
"entropy": 5.2198402881622314,
|
|
"epoch": 1.114684263280989,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00048810262138778213,
|
|
"loss": 4.9518,
|
|
"mean_token_accuracy": 0.21139863282442092,
|
|
"num_tokens": 24547477.0,
|
|
"step": 13345
|
|
},
|
|
{
|
|
"entropy": 5.281708145141602,
|
|
"epoch": 1.115101904443702,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00048809306718724886,
|
|
"loss": 4.9065,
|
|
"mean_token_accuracy": 0.20673473477363585,
|
|
"num_tokens": 24556230.0,
|
|
"step": 13350
|
|
},
|
|
{
|
|
"entropy": 5.260258531570434,
|
|
"epoch": 1.115519545606415,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00048808350925626514,
|
|
"loss": 4.8676,
|
|
"mean_token_accuracy": 0.2165923684835434,
|
|
"num_tokens": 24565021.0,
|
|
"step": 13355
|
|
},
|
|
{
|
|
"entropy": 5.2782727718353275,
|
|
"epoch": 1.115937186769128,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00048807394759499797,
|
|
"loss": 4.8454,
|
|
"mean_token_accuracy": 0.21774390190839768,
|
|
"num_tokens": 24575012.0,
|
|
"step": 13360
|
|
},
|
|
{
|
|
"entropy": 5.34255690574646,
|
|
"epoch": 1.116354827931841,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004880643822036149,
|
|
"loss": 5.0048,
|
|
"mean_token_accuracy": 0.2024964228272438,
|
|
"num_tokens": 24584267.0,
|
|
"step": 13365
|
|
},
|
|
{
|
|
"entropy": 5.300237035751342,
|
|
"epoch": 1.116772469094554,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00048805481308228333,
|
|
"loss": 4.895,
|
|
"mean_token_accuracy": 0.21600398868322374,
|
|
"num_tokens": 24594299.0,
|
|
"step": 13370
|
|
},
|
|
{
|
|
"entropy": 5.283212757110595,
|
|
"epoch": 1.117190110257267,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004880452402311709,
|
|
"loss": 4.9006,
|
|
"mean_token_accuracy": 0.21374878883361817,
|
|
"num_tokens": 24603717.0,
|
|
"step": 13375
|
|
},
|
|
{
|
|
"entropy": 5.295483160018921,
|
|
"epoch": 1.11760775141998,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00048803566365044493,
|
|
"loss": 4.9566,
|
|
"mean_token_accuracy": 0.20913030654191972,
|
|
"num_tokens": 24613141.0,
|
|
"step": 13380
|
|
},
|
|
{
|
|
"entropy": 5.2521013736724855,
|
|
"epoch": 1.1180253925826928,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004880260833402734,
|
|
"loss": 4.8953,
|
|
"mean_token_accuracy": 0.22047676742076874,
|
|
"num_tokens": 24621837.0,
|
|
"step": 13385
|
|
},
|
|
{
|
|
"entropy": 5.350809621810913,
|
|
"epoch": 1.1184430337454059,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00048801649930082375,
|
|
"loss": 4.9209,
|
|
"mean_token_accuracy": 0.2087827205657959,
|
|
"num_tokens": 24630657.0,
|
|
"step": 13390
|
|
},
|
|
{
|
|
"entropy": 5.399842739105225,
|
|
"epoch": 1.118860674908119,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000488006911532264,
|
|
"loss": 5.0105,
|
|
"mean_token_accuracy": 0.19916945397853852,
|
|
"num_tokens": 24639929.0,
|
|
"step": 13395
|
|
},
|
|
{
|
|
"entropy": 5.305797529220581,
|
|
"epoch": 1.119278316070832,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004879973200347617,
|
|
"loss": 4.9461,
|
|
"mean_token_accuracy": 0.21596447825431825,
|
|
"num_tokens": 24648537.0,
|
|
"step": 13400
|
|
},
|
|
{
|
|
"entropy": 5.23604679107666,
|
|
"epoch": 1.119695957233545,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00048798772480848504,
|
|
"loss": 4.9029,
|
|
"mean_token_accuracy": 0.21981456875801086,
|
|
"num_tokens": 24656809.0,
|
|
"step": 13405
|
|
},
|
|
{
|
|
"entropy": 5.248571252822876,
|
|
"epoch": 1.120113598396258,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00048797812585360187,
|
|
"loss": 4.8878,
|
|
"mean_token_accuracy": 0.20701291859149934,
|
|
"num_tokens": 24665523.0,
|
|
"step": 13410
|
|
},
|
|
{
|
|
"entropy": 5.279518127441406,
|
|
"epoch": 1.120531239558971,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00048796852317028024,
|
|
"loss": 4.8408,
|
|
"mean_token_accuracy": 0.21737050712108613,
|
|
"num_tokens": 24675618.0,
|
|
"step": 13415
|
|
},
|
|
{
|
|
"entropy": 5.261980962753296,
|
|
"epoch": 1.1209488807216839,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004879589167586882,
|
|
"loss": 4.883,
|
|
"mean_token_accuracy": 0.21820248514413834,
|
|
"num_tokens": 24684922.0,
|
|
"step": 13420
|
|
},
|
|
{
|
|
"entropy": 5.257414960861206,
|
|
"epoch": 1.121366521884397,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00048794930661899414,
|
|
"loss": 4.9468,
|
|
"mean_token_accuracy": 0.21041895151138307,
|
|
"num_tokens": 24693791.0,
|
|
"step": 13425
|
|
},
|
|
{
|
|
"entropy": 5.233606576919556,
|
|
"epoch": 1.12178416304711,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00048793969275136593,
|
|
"loss": 4.8116,
|
|
"mean_token_accuracy": 0.21604859381914138,
|
|
"num_tokens": 24702661.0,
|
|
"step": 13430
|
|
},
|
|
{
|
|
"entropy": 5.26155834197998,
|
|
"epoch": 1.122201804209823,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004879300751559722,
|
|
"loss": 4.8902,
|
|
"mean_token_accuracy": 0.21194994896650315,
|
|
"num_tokens": 24711019.0,
|
|
"step": 13435
|
|
},
|
|
{
|
|
"entropy": 5.339042854309082,
|
|
"epoch": 1.122619445372536,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004879204538329812,
|
|
"loss": 4.9289,
|
|
"mean_token_accuracy": 0.20742554664611818,
|
|
"num_tokens": 24720456.0,
|
|
"step": 13440
|
|
},
|
|
{
|
|
"entropy": 5.273082828521728,
|
|
"epoch": 1.1230370865352488,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004879108287825614,
|
|
"loss": 4.8714,
|
|
"mean_token_accuracy": 0.2195258542895317,
|
|
"num_tokens": 24729395.0,
|
|
"step": 13445
|
|
},
|
|
{
|
|
"entropy": 5.215933513641358,
|
|
"epoch": 1.1234547276979618,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00048790120000488115,
|
|
"loss": 4.8661,
|
|
"mean_token_accuracy": 0.21700615733861922,
|
|
"num_tokens": 24738543.0,
|
|
"step": 13450
|
|
},
|
|
{
|
|
"entropy": 5.29384331703186,
|
|
"epoch": 1.1238723688606749,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004878915675001092,
|
|
"loss": 4.8765,
|
|
"mean_token_accuracy": 0.2101330578327179,
|
|
"num_tokens": 24747860.0,
|
|
"step": 13455
|
|
},
|
|
{
|
|
"entropy": 5.185804080963135,
|
|
"epoch": 1.124290010023388,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004878819312684141,
|
|
"loss": 4.832,
|
|
"mean_token_accuracy": 0.2126847416162491,
|
|
"num_tokens": 24757457.0,
|
|
"step": 13460
|
|
},
|
|
{
|
|
"entropy": 5.326801443099976,
|
|
"epoch": 1.124707651186101,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004878722913099645,
|
|
"loss": 4.8844,
|
|
"mean_token_accuracy": 0.21128021329641342,
|
|
"num_tokens": 24766844.0,
|
|
"step": 13465
|
|
},
|
|
{
|
|
"entropy": 5.305566453933716,
|
|
"epoch": 1.125125292348814,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004878626476249293,
|
|
"loss": 4.9584,
|
|
"mean_token_accuracy": 0.20470163524150847,
|
|
"num_tokens": 24776041.0,
|
|
"step": 13470
|
|
},
|
|
{
|
|
"entropy": 5.269011211395264,
|
|
"epoch": 1.125542933511527,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004878530002134772,
|
|
"loss": 4.8742,
|
|
"mean_token_accuracy": 0.2190667510032654,
|
|
"num_tokens": 24785515.0,
|
|
"step": 13475
|
|
},
|
|
{
|
|
"entropy": 5.363717412948608,
|
|
"epoch": 1.1259605746742398,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004878433490757771,
|
|
"loss": 4.9344,
|
|
"mean_token_accuracy": 0.21687734574079515,
|
|
"num_tokens": 24795251.0,
|
|
"step": 13480
|
|
},
|
|
{
|
|
"entropy": 5.216241884231567,
|
|
"epoch": 1.1263782158369529,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004878336942119979,
|
|
"loss": 4.8496,
|
|
"mean_token_accuracy": 0.21828902512788773,
|
|
"num_tokens": 24804672.0,
|
|
"step": 13485
|
|
},
|
|
{
|
|
"entropy": 5.273200654983521,
|
|
"epoch": 1.126795856999666,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00048782403562230874,
|
|
"loss": 4.8917,
|
|
"mean_token_accuracy": 0.21693220138549804,
|
|
"num_tokens": 24813520.0,
|
|
"step": 13490
|
|
},
|
|
{
|
|
"entropy": 5.254609727859497,
|
|
"epoch": 1.127213498162379,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004878143733068787,
|
|
"loss": 4.7351,
|
|
"mean_token_accuracy": 0.22602677941322327,
|
|
"num_tokens": 24821368.0,
|
|
"step": 13495
|
|
},
|
|
{
|
|
"entropy": 5.22702374458313,
|
|
"epoch": 1.127631139325092,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004878047072658769,
|
|
"loss": 4.8304,
|
|
"mean_token_accuracy": 0.21328341513872145,
|
|
"num_tokens": 24830071.0,
|
|
"step": 13500
|
|
},
|
|
{
|
|
"entropy": 5.175024938583374,
|
|
"epoch": 1.1280487804878048,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004877950374994725,
|
|
"loss": 4.7566,
|
|
"mean_token_accuracy": 0.22273661941289902,
|
|
"num_tokens": 24838982.0,
|
|
"step": 13505
|
|
},
|
|
{
|
|
"entropy": 5.30128059387207,
|
|
"epoch": 1.1284664216505178,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004877853640078349,
|
|
"loss": 4.9417,
|
|
"mean_token_accuracy": 0.20314504504203795,
|
|
"num_tokens": 24848313.0,
|
|
"step": 13510
|
|
},
|
|
{
|
|
"entropy": 5.2694062232971195,
|
|
"epoch": 1.1288840628132308,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004877756867911333,
|
|
"loss": 4.9035,
|
|
"mean_token_accuracy": 0.21516518145799637,
|
|
"num_tokens": 24857477.0,
|
|
"step": 13515
|
|
},
|
|
{
|
|
"entropy": 5.239373350143433,
|
|
"epoch": 1.1293017039759439,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004877660058495372,
|
|
"loss": 4.8624,
|
|
"mean_token_accuracy": 0.21387197226285934,
|
|
"num_tokens": 24866561.0,
|
|
"step": 13520
|
|
},
|
|
{
|
|
"entropy": 5.27010178565979,
|
|
"epoch": 1.129719345138657,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004877563211832161,
|
|
"loss": 4.9551,
|
|
"mean_token_accuracy": 0.20328208655118943,
|
|
"num_tokens": 24876113.0,
|
|
"step": 13525
|
|
},
|
|
{
|
|
"entropy": 5.38572325706482,
|
|
"epoch": 1.13013698630137,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00048774663279233947,
|
|
"loss": 4.9954,
|
|
"mean_token_accuracy": 0.20648373961448668,
|
|
"num_tokens": 24885974.0,
|
|
"step": 13530
|
|
},
|
|
{
|
|
"entropy": 5.272332334518433,
|
|
"epoch": 1.130554627464083,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00048773694067707693,
|
|
"loss": 4.8405,
|
|
"mean_token_accuracy": 0.2193993330001831,
|
|
"num_tokens": 24895046.0,
|
|
"step": 13535
|
|
},
|
|
{
|
|
"entropy": 5.260845041275024,
|
|
"epoch": 1.1309722686267958,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00048772724483759825,
|
|
"loss": 4.9914,
|
|
"mean_token_accuracy": 0.2100438356399536,
|
|
"num_tokens": 24903315.0,
|
|
"step": 13540
|
|
},
|
|
{
|
|
"entropy": 5.306494522094726,
|
|
"epoch": 1.1313899097895088,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000487717545274073,
|
|
"loss": 4.9752,
|
|
"mean_token_accuracy": 0.20811050534248351,
|
|
"num_tokens": 24912556.0,
|
|
"step": 13545
|
|
},
|
|
{
|
|
"entropy": 5.360071277618408,
|
|
"epoch": 1.1318075509522219,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004877078419866711,
|
|
"loss": 4.9106,
|
|
"mean_token_accuracy": 0.21467335820198058,
|
|
"num_tokens": 24921854.0,
|
|
"step": 13550
|
|
},
|
|
{
|
|
"entropy": 5.241201591491699,
|
|
"epoch": 1.1322251921149349,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00048769813497556236,
|
|
"loss": 4.8596,
|
|
"mean_token_accuracy": 0.21896041333675384,
|
|
"num_tokens": 24930691.0,
|
|
"step": 13555
|
|
},
|
|
{
|
|
"entropy": 5.255487728118896,
|
|
"epoch": 1.132642833277648,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004876884242409168,
|
|
"loss": 4.9203,
|
|
"mean_token_accuracy": 0.2162812978029251,
|
|
"num_tokens": 24940573.0,
|
|
"step": 13560
|
|
},
|
|
{
|
|
"entropy": 5.249113988876343,
|
|
"epoch": 1.1330604744403607,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00048767870978290434,
|
|
"loss": 4.8086,
|
|
"mean_token_accuracy": 0.21294808238744736,
|
|
"num_tokens": 24950902.0,
|
|
"step": 13565
|
|
},
|
|
{
|
|
"entropy": 5.255436754226684,
|
|
"epoch": 1.1334781156030738,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004876689916016951,
|
|
"loss": 4.8406,
|
|
"mean_token_accuracy": 0.21964537352323532,
|
|
"num_tokens": 24960055.0,
|
|
"step": 13570
|
|
},
|
|
{
|
|
"entropy": 5.279968881607056,
|
|
"epoch": 1.1338957567657868,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004876592696974591,
|
|
"loss": 4.8741,
|
|
"mean_token_accuracy": 0.21051753014326097,
|
|
"num_tokens": 24969896.0,
|
|
"step": 13575
|
|
},
|
|
{
|
|
"entropy": 5.299686861038208,
|
|
"epoch": 1.1343133979284998,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004876495440703667,
|
|
"loss": 4.834,
|
|
"mean_token_accuracy": 0.21472468227148056,
|
|
"num_tokens": 24978467.0,
|
|
"step": 13580
|
|
},
|
|
{
|
|
"entropy": 5.243856191635132,
|
|
"epoch": 1.1347310390912129,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004876398147205879,
|
|
"loss": 4.8839,
|
|
"mean_token_accuracy": 0.21529708802700043,
|
|
"num_tokens": 24987038.0,
|
|
"step": 13585
|
|
},
|
|
{
|
|
"entropy": 5.351840877532959,
|
|
"epoch": 1.135148680253926,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004876300816482933,
|
|
"loss": 4.9363,
|
|
"mean_token_accuracy": 0.21152514964342117,
|
|
"num_tokens": 24997228.0,
|
|
"step": 13590
|
|
},
|
|
{
|
|
"entropy": 5.248982906341553,
|
|
"epoch": 1.135566321416639,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004876203448536532,
|
|
"loss": 4.8214,
|
|
"mean_token_accuracy": 0.21323238760232927,
|
|
"num_tokens": 25005784.0,
|
|
"step": 13595
|
|
},
|
|
{
|
|
"entropy": 5.268309211730957,
|
|
"epoch": 1.1359839625793517,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004876106043368381,
|
|
"loss": 4.9229,
|
|
"mean_token_accuracy": 0.21076042354106903,
|
|
"num_tokens": 25015863.0,
|
|
"step": 13600
|
|
},
|
|
{
|
|
"entropy": 5.161695194244385,
|
|
"epoch": 1.1364016037420648,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004876008600980183,
|
|
"loss": 4.7531,
|
|
"mean_token_accuracy": 0.2266981229186058,
|
|
"num_tokens": 25025391.0,
|
|
"step": 13605
|
|
},
|
|
{
|
|
"entropy": 5.308411169052124,
|
|
"epoch": 1.1368192449047778,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00048759111213736455,
|
|
"loss": 4.9694,
|
|
"mean_token_accuracy": 0.20882852375507355,
|
|
"num_tokens": 25035387.0,
|
|
"step": 13610
|
|
},
|
|
{
|
|
"entropy": 5.191502809524536,
|
|
"epoch": 1.1372368860674908,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004875813604550476,
|
|
"loss": 4.7296,
|
|
"mean_token_accuracy": 0.22554003000259398,
|
|
"num_tokens": 25044485.0,
|
|
"step": 13615
|
|
},
|
|
{
|
|
"entropy": 5.2118431568145756,
|
|
"epoch": 1.1376545272302039,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004875716050512379,
|
|
"loss": 4.848,
|
|
"mean_token_accuracy": 0.21343065351247786,
|
|
"num_tokens": 25053079.0,
|
|
"step": 13620
|
|
},
|
|
{
|
|
"entropy": 5.340713262557983,
|
|
"epoch": 1.1380721683929167,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004875618459261065,
|
|
"loss": 4.961,
|
|
"mean_token_accuracy": 0.20659567564725875,
|
|
"num_tokens": 25063262.0,
|
|
"step": 13625
|
|
},
|
|
{
|
|
"entropy": 5.293006229400635,
|
|
"epoch": 1.1384898095556297,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00048755208307982414,
|
|
"loss": 4.8392,
|
|
"mean_token_accuracy": 0.22037013173103331,
|
|
"num_tokens": 25071720.0,
|
|
"step": 13630
|
|
},
|
|
{
|
|
"entropy": 5.204473066329956,
|
|
"epoch": 1.1389074507183428,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004875423165125616,
|
|
"loss": 4.8726,
|
|
"mean_token_accuracy": 0.2142190083861351,
|
|
"num_tokens": 25080460.0,
|
|
"step": 13635
|
|
},
|
|
{
|
|
"entropy": 5.22118730545044,
|
|
"epoch": 1.1393250918810558,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00048753254622449006,
|
|
"loss": 4.8764,
|
|
"mean_token_accuracy": 0.21225495487451554,
|
|
"num_tokens": 25089162.0,
|
|
"step": 13640
|
|
},
|
|
{
|
|
"entropy": 5.232584667205811,
|
|
"epoch": 1.1397427330437688,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004875227722157804,
|
|
"loss": 4.7631,
|
|
"mean_token_accuracy": 0.217538021504879,
|
|
"num_tokens": 25098234.0,
|
|
"step": 13645
|
|
},
|
|
{
|
|
"entropy": 5.206743955612183,
|
|
"epoch": 1.1401603742064819,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004875129944866039,
|
|
"loss": 4.8166,
|
|
"mean_token_accuracy": 0.2171617105603218,
|
|
"num_tokens": 25107832.0,
|
|
"step": 13650
|
|
},
|
|
{
|
|
"entropy": 5.260278701782227,
|
|
"epoch": 1.140578015369195,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004875032130371316,
|
|
"loss": 4.8443,
|
|
"mean_token_accuracy": 0.2167891651391983,
|
|
"num_tokens": 25116118.0,
|
|
"step": 13655
|
|
},
|
|
{
|
|
"entropy": 5.145340776443481,
|
|
"epoch": 1.1409956565319077,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004874934278675347,
|
|
"loss": 4.6927,
|
|
"mean_token_accuracy": 0.22428550571203232,
|
|
"num_tokens": 25125025.0,
|
|
"step": 13660
|
|
},
|
|
{
|
|
"entropy": 5.282260751724243,
|
|
"epoch": 1.1414132976946207,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004874836389779846,
|
|
"loss": 4.9523,
|
|
"mean_token_accuracy": 0.21477939933538437,
|
|
"num_tokens": 25135763.0,
|
|
"step": 13665
|
|
},
|
|
{
|
|
"entropy": 5.4009339809417725,
|
|
"epoch": 1.1418309388573338,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00048747384636865267,
|
|
"loss": 4.9792,
|
|
"mean_token_accuracy": 0.20728751718997956,
|
|
"num_tokens": 25145510.0,
|
|
"step": 13670
|
|
},
|
|
{
|
|
"entropy": 5.3031398296356205,
|
|
"epoch": 1.1422485800200468,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004874640500397103,
|
|
"loss": 4.8406,
|
|
"mean_token_accuracy": 0.21275755316019057,
|
|
"num_tokens": 25153910.0,
|
|
"step": 13675
|
|
},
|
|
{
|
|
"entropy": 5.2443804264068605,
|
|
"epoch": 1.1426662211827598,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004874542499913289,
|
|
"loss": 4.8622,
|
|
"mean_token_accuracy": 0.21285583674907685,
|
|
"num_tokens": 25163357.0,
|
|
"step": 13680
|
|
},
|
|
{
|
|
"entropy": 5.256487607955933,
|
|
"epoch": 1.1430838623454727,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00048744444622368015,
|
|
"loss": 4.8774,
|
|
"mean_token_accuracy": 0.21510632634162902,
|
|
"num_tokens": 25172423.0,
|
|
"step": 13685
|
|
},
|
|
{
|
|
"entropy": 5.24192247390747,
|
|
"epoch": 1.1435015035081857,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00048743463873693576,
|
|
"loss": 4.8221,
|
|
"mean_token_accuracy": 0.21188147962093354,
|
|
"num_tokens": 25181508.0,
|
|
"step": 13690
|
|
},
|
|
{
|
|
"entropy": 5.276925706863404,
|
|
"epoch": 1.1439191446708987,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004874248275312673,
|
|
"loss": 4.9338,
|
|
"mean_token_accuracy": 0.21511436849832535,
|
|
"num_tokens": 25190741.0,
|
|
"step": 13695
|
|
},
|
|
{
|
|
"entropy": 5.337406921386719,
|
|
"epoch": 1.1443367858336118,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00048741501260684644,
|
|
"loss": 4.9981,
|
|
"mean_token_accuracy": 0.2045115828514099,
|
|
"num_tokens": 25201288.0,
|
|
"step": 13700
|
|
},
|
|
{
|
|
"entropy": 5.280719566345215,
|
|
"epoch": 1.1447544269963248,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00048740519396384515,
|
|
"loss": 4.8627,
|
|
"mean_token_accuracy": 0.2210691899061203,
|
|
"num_tokens": 25210111.0,
|
|
"step": 13705
|
|
},
|
|
{
|
|
"entropy": 5.28420467376709,
|
|
"epoch": 1.1451720681590378,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00048739537160243524,
|
|
"loss": 4.9042,
|
|
"mean_token_accuracy": 0.20876525044441224,
|
|
"num_tokens": 25220061.0,
|
|
"step": 13710
|
|
},
|
|
{
|
|
"entropy": 5.2749473571777346,
|
|
"epoch": 1.1455897093217509,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00048738554552278874,
|
|
"loss": 4.8727,
|
|
"mean_token_accuracy": 0.21307254135608672,
|
|
"num_tokens": 25229336.0,
|
|
"step": 13715
|
|
},
|
|
{
|
|
"entropy": 5.2678478240966795,
|
|
"epoch": 1.1460073504844637,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00048737571572507753,
|
|
"loss": 4.8318,
|
|
"mean_token_accuracy": 0.22434635758399962,
|
|
"num_tokens": 25238539.0,
|
|
"step": 13720
|
|
},
|
|
{
|
|
"entropy": 5.269054269790649,
|
|
"epoch": 1.1464249916471767,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00048736588220947384,
|
|
"loss": 4.8858,
|
|
"mean_token_accuracy": 0.20907706916332244,
|
|
"num_tokens": 25247880.0,
|
|
"step": 13725
|
|
},
|
|
{
|
|
"entropy": 5.2703601837158205,
|
|
"epoch": 1.1468426328098897,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00048735604497614974,
|
|
"loss": 4.901,
|
|
"mean_token_accuracy": 0.21622994542121887,
|
|
"num_tokens": 25257295.0,
|
|
"step": 13730
|
|
},
|
|
{
|
|
"entropy": 5.273104572296143,
|
|
"epoch": 1.1472602739726028,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004873462040252775,
|
|
"loss": 4.8904,
|
|
"mean_token_accuracy": 0.21302305907011032,
|
|
"num_tokens": 25266784.0,
|
|
"step": 13735
|
|
},
|
|
{
|
|
"entropy": 5.337120151519775,
|
|
"epoch": 1.1476779151353158,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004873363593570293,
|
|
"loss": 4.9571,
|
|
"mean_token_accuracy": 0.20905491709709167,
|
|
"num_tokens": 25276910.0,
|
|
"step": 13740
|
|
},
|
|
{
|
|
"entropy": 5.324481439590454,
|
|
"epoch": 1.1480955562980286,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004873265109715776,
|
|
"loss": 4.8546,
|
|
"mean_token_accuracy": 0.2200960025191307,
|
|
"num_tokens": 25285776.0,
|
|
"step": 13745
|
|
},
|
|
{
|
|
"entropy": 5.290006256103515,
|
|
"epoch": 1.1485131974607417,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004873166588690947,
|
|
"loss": 4.8376,
|
|
"mean_token_accuracy": 0.21993631571531297,
|
|
"num_tokens": 25294319.0,
|
|
"step": 13750
|
|
},
|
|
{
|
|
"entropy": 5.249959182739258,
|
|
"epoch": 1.1489308386234547,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004873068030497532,
|
|
"loss": 4.8457,
|
|
"mean_token_accuracy": 0.21979946196079253,
|
|
"num_tokens": 25304396.0,
|
|
"step": 13755
|
|
},
|
|
{
|
|
"entropy": 5.2008191585540775,
|
|
"epoch": 1.1493484797861677,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00048729694351372545,
|
|
"loss": 4.7946,
|
|
"mean_token_accuracy": 0.22379758059978486,
|
|
"num_tokens": 25313095.0,
|
|
"step": 13760
|
|
},
|
|
{
|
|
"entropy": 5.292687034606933,
|
|
"epoch": 1.1497661209488808,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004872870802611842,
|
|
"loss": 4.9888,
|
|
"mean_token_accuracy": 0.21225251853466034,
|
|
"num_tokens": 25322948.0,
|
|
"step": 13765
|
|
},
|
|
{
|
|
"entropy": 5.230883169174194,
|
|
"epoch": 1.1501837621115938,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004872772132923021,
|
|
"loss": 4.8363,
|
|
"mean_token_accuracy": 0.21453835517168046,
|
|
"num_tokens": 25332707.0,
|
|
"step": 13770
|
|
},
|
|
{
|
|
"entropy": 5.238774824142456,
|
|
"epoch": 1.1506014032743068,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00048726734260725186,
|
|
"loss": 4.8482,
|
|
"mean_token_accuracy": 0.2151096999645233,
|
|
"num_tokens": 25342029.0,
|
|
"step": 13775
|
|
},
|
|
{
|
|
"entropy": 5.229918098449707,
|
|
"epoch": 1.1510190444370196,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004872574682062063,
|
|
"loss": 4.7607,
|
|
"mean_token_accuracy": 0.2243787631392479,
|
|
"num_tokens": 25350374.0,
|
|
"step": 13780
|
|
},
|
|
{
|
|
"entropy": 5.261537027359009,
|
|
"epoch": 1.1514366855997327,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004872475900893382,
|
|
"loss": 4.9228,
|
|
"mean_token_accuracy": 0.2166041538119316,
|
|
"num_tokens": 25359370.0,
|
|
"step": 13785
|
|
},
|
|
{
|
|
"entropy": 5.243124389648438,
|
|
"epoch": 1.1518543267624457,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004872377082568206,
|
|
"loss": 4.8316,
|
|
"mean_token_accuracy": 0.2200513869524002,
|
|
"num_tokens": 25368329.0,
|
|
"step": 13790
|
|
},
|
|
{
|
|
"entropy": 5.308872222900391,
|
|
"epoch": 1.1522719679251587,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00048722782270882643,
|
|
"loss": 4.9687,
|
|
"mean_token_accuracy": 0.20813584923744202,
|
|
"num_tokens": 25377795.0,
|
|
"step": 13795
|
|
},
|
|
{
|
|
"entropy": 5.329696893692017,
|
|
"epoch": 1.1526896090878718,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004872179334455288,
|
|
"loss": 4.9155,
|
|
"mean_token_accuracy": 0.211460117995739,
|
|
"num_tokens": 25387134.0,
|
|
"step": 13800
|
|
},
|
|
{
|
|
"entropy": 5.355197620391846,
|
|
"epoch": 1.1531072502505846,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00048720804046710074,
|
|
"loss": 4.9422,
|
|
"mean_token_accuracy": 0.2084246888756752,
|
|
"num_tokens": 25396320.0,
|
|
"step": 13805
|
|
},
|
|
{
|
|
"entropy": 5.303622055053711,
|
|
"epoch": 1.1535248914132976,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00048719814377371553,
|
|
"loss": 4.9015,
|
|
"mean_token_accuracy": 0.21105479300022126,
|
|
"num_tokens": 25404727.0,
|
|
"step": 13810
|
|
},
|
|
{
|
|
"entropy": 5.181811952590943,
|
|
"epoch": 1.1539425325760106,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004871882433655464,
|
|
"loss": 4.8278,
|
|
"mean_token_accuracy": 0.21476244330406188,
|
|
"num_tokens": 25414137.0,
|
|
"step": 13815
|
|
},
|
|
{
|
|
"entropy": 5.318673086166382,
|
|
"epoch": 1.1543601737387237,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004871783392427666,
|
|
"loss": 4.8895,
|
|
"mean_token_accuracy": 0.2155558407306671,
|
|
"num_tokens": 25423297.0,
|
|
"step": 13820
|
|
},
|
|
{
|
|
"entropy": 5.40968689918518,
|
|
"epoch": 1.1547778149014367,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004871684314055497,
|
|
"loss": 4.9799,
|
|
"mean_token_accuracy": 0.20710690021514894,
|
|
"num_tokens": 25433185.0,
|
|
"step": 13825
|
|
},
|
|
{
|
|
"entropy": 5.306927680969238,
|
|
"epoch": 1.1551954560641498,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004871585198540689,
|
|
"loss": 4.8856,
|
|
"mean_token_accuracy": 0.22176383584737777,
|
|
"num_tokens": 25441769.0,
|
|
"step": 13830
|
|
},
|
|
{
|
|
"entropy": 5.223139095306396,
|
|
"epoch": 1.1556130972268628,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00048714860458849794,
|
|
"loss": 4.8302,
|
|
"mean_token_accuracy": 0.2161799266934395,
|
|
"num_tokens": 25450650.0,
|
|
"step": 13835
|
|
},
|
|
{
|
|
"entropy": 5.2494409561157225,
|
|
"epoch": 1.1560307383895756,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00048713868560901013,
|
|
"loss": 4.8332,
|
|
"mean_token_accuracy": 0.22578169256448746,
|
|
"num_tokens": 25458721.0,
|
|
"step": 13840
|
|
},
|
|
{
|
|
"entropy": 5.300110912322998,
|
|
"epoch": 1.1564483795522886,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004871287629157794,
|
|
"loss": 4.8995,
|
|
"mean_token_accuracy": 0.2149494931101799,
|
|
"num_tokens": 25468004.0,
|
|
"step": 13845
|
|
},
|
|
{
|
|
"entropy": 5.333184099197387,
|
|
"epoch": 1.1568660207150017,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004871188365089793,
|
|
"loss": 5.0121,
|
|
"mean_token_accuracy": 0.21131540834903717,
|
|
"num_tokens": 25478042.0,
|
|
"step": 13850
|
|
},
|
|
{
|
|
"entropy": 5.354527282714844,
|
|
"epoch": 1.1572836618777147,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004871089063887837,
|
|
"loss": 4.9053,
|
|
"mean_token_accuracy": 0.21250555217266082,
|
|
"num_tokens": 25488439.0,
|
|
"step": 13855
|
|
},
|
|
{
|
|
"entropy": 5.290424489974976,
|
|
"epoch": 1.1577013030404277,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00048709897255536626,
|
|
"loss": 4.8935,
|
|
"mean_token_accuracy": 0.2129376769065857,
|
|
"num_tokens": 25497928.0,
|
|
"step": 13860
|
|
},
|
|
{
|
|
"entropy": 5.316667795181274,
|
|
"epoch": 1.1581189442031405,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004870890350089011,
|
|
"loss": 4.933,
|
|
"mean_token_accuracy": 0.212449249625206,
|
|
"num_tokens": 25506522.0,
|
|
"step": 13865
|
|
},
|
|
{
|
|
"entropy": 5.296707677841186,
|
|
"epoch": 1.1585365853658536,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004870790937495621,
|
|
"loss": 4.9023,
|
|
"mean_token_accuracy": 0.20084939897060394,
|
|
"num_tokens": 25516017.0,
|
|
"step": 13870
|
|
},
|
|
{
|
|
"entropy": 5.284860420227051,
|
|
"epoch": 1.1589542265285666,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00048706914877752325,
|
|
"loss": 4.8668,
|
|
"mean_token_accuracy": 0.2173384189605713,
|
|
"num_tokens": 25525262.0,
|
|
"step": 13875
|
|
},
|
|
{
|
|
"entropy": 5.179403018951416,
|
|
"epoch": 1.1593718676912796,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00048705920009295867,
|
|
"loss": 4.8473,
|
|
"mean_token_accuracy": 0.21863864809274675,
|
|
"num_tokens": 25534479.0,
|
|
"step": 13880
|
|
},
|
|
{
|
|
"entropy": 5.27202582359314,
|
|
"epoch": 1.1597895088539927,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004870492476960426,
|
|
"loss": 4.8789,
|
|
"mean_token_accuracy": 0.21805175095796586,
|
|
"num_tokens": 25543338.0,
|
|
"step": 13885
|
|
},
|
|
{
|
|
"entropy": 5.419294738769532,
|
|
"epoch": 1.1602071500167057,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004870392915869491,
|
|
"loss": 5.0097,
|
|
"mean_token_accuracy": 0.2063686102628708,
|
|
"num_tokens": 25552286.0,
|
|
"step": 13890
|
|
},
|
|
{
|
|
"entropy": 5.342674684524536,
|
|
"epoch": 1.1606247911794187,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004870293317658526,
|
|
"loss": 4.9198,
|
|
"mean_token_accuracy": 0.20889928340911865,
|
|
"num_tokens": 25561978.0,
|
|
"step": 13895
|
|
},
|
|
{
|
|
"entropy": 5.236069011688232,
|
|
"epoch": 1.1610424323421316,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004870193682329275,
|
|
"loss": 4.826,
|
|
"mean_token_accuracy": 0.21892983466386795,
|
|
"num_tokens": 25570139.0,
|
|
"step": 13900
|
|
},
|
|
{
|
|
"entropy": 5.258753538131714,
|
|
"epoch": 1.1614600735048446,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00048700940098834805,
|
|
"loss": 4.8537,
|
|
"mean_token_accuracy": 0.21106000542640685,
|
|
"num_tokens": 25579761.0,
|
|
"step": 13905
|
|
},
|
|
{
|
|
"entropy": 5.253506469726562,
|
|
"epoch": 1.1618777146675576,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004869994300322889,
|
|
"loss": 4.8716,
|
|
"mean_token_accuracy": 0.21221585422754288,
|
|
"num_tokens": 25588740.0,
|
|
"step": 13910
|
|
},
|
|
{
|
|
"entropy": 5.256745052337647,
|
|
"epoch": 1.1622953558302707,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00048698945536492454,
|
|
"loss": 4.908,
|
|
"mean_token_accuracy": 0.21066562533378602,
|
|
"num_tokens": 25597963.0,
|
|
"step": 13915
|
|
},
|
|
{
|
|
"entropy": 5.230707883834839,
|
|
"epoch": 1.1627129969929837,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004869794769864296,
|
|
"loss": 4.873,
|
|
"mean_token_accuracy": 0.21316303312778473,
|
|
"num_tokens": 25606782.0,
|
|
"step": 13920
|
|
},
|
|
{
|
|
"entropy": 5.384146356582642,
|
|
"epoch": 1.1631306381556965,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004869694948969787,
|
|
"loss": 4.9702,
|
|
"mean_token_accuracy": 0.2007288709282875,
|
|
"num_tokens": 25616458.0,
|
|
"step": 13925
|
|
},
|
|
{
|
|
"entropy": 5.343670511245728,
|
|
"epoch": 1.1635482793184095,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00048695950909674666,
|
|
"loss": 4.9283,
|
|
"mean_token_accuracy": 0.2056759625673294,
|
|
"num_tokens": 25625081.0,
|
|
"step": 13930
|
|
},
|
|
{
|
|
"entropy": 5.286416053771973,
|
|
"epoch": 1.1639659204811226,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00048694951958590835,
|
|
"loss": 4.9451,
|
|
"mean_token_accuracy": 0.20673276782035827,
|
|
"num_tokens": 25634000.0,
|
|
"step": 13935
|
|
},
|
|
{
|
|
"entropy": 5.3067498207092285,
|
|
"epoch": 1.1643835616438356,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00048693952636463854,
|
|
"loss": 4.8556,
|
|
"mean_token_accuracy": 0.21781117022037505,
|
|
"num_tokens": 25642715.0,
|
|
"step": 13940
|
|
},
|
|
{
|
|
"entropy": 5.1775353908538815,
|
|
"epoch": 1.1648012028065486,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00048692952943311214,
|
|
"loss": 4.6865,
|
|
"mean_token_accuracy": 0.229061359167099,
|
|
"num_tokens": 25650979.0,
|
|
"step": 13945
|
|
},
|
|
{
|
|
"entropy": 5.264878463745117,
|
|
"epoch": 1.1652188439692617,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004869195287915043,
|
|
"loss": 4.9073,
|
|
"mean_token_accuracy": 0.21405562609434128,
|
|
"num_tokens": 25660860.0,
|
|
"step": 13950
|
|
},
|
|
{
|
|
"entropy": 5.109746885299683,
|
|
"epoch": 1.1656364851319747,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00048690952443999,
|
|
"loss": 4.7033,
|
|
"mean_token_accuracy": 0.22849691212177276,
|
|
"num_tokens": 25670331.0,
|
|
"step": 13955
|
|
},
|
|
{
|
|
"entropy": 5.30588002204895,
|
|
"epoch": 1.1660541262946875,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00048689951637874445,
|
|
"loss": 4.9707,
|
|
"mean_token_accuracy": 0.21301737129688264,
|
|
"num_tokens": 25679276.0,
|
|
"step": 13960
|
|
},
|
|
{
|
|
"entropy": 5.317697286605835,
|
|
"epoch": 1.1664717674574006,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004868895046079428,
|
|
"loss": 4.8922,
|
|
"mean_token_accuracy": 0.21998478919267656,
|
|
"num_tokens": 25688509.0,
|
|
"step": 13965
|
|
},
|
|
{
|
|
"entropy": 5.221651983261109,
|
|
"epoch": 1.1668894086201136,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004868794891277602,
|
|
"loss": 4.7439,
|
|
"mean_token_accuracy": 0.21961688250303268,
|
|
"num_tokens": 25697776.0,
|
|
"step": 13970
|
|
},
|
|
{
|
|
"entropy": 5.212842988967895,
|
|
"epoch": 1.1673070497828266,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004868694699383722,
|
|
"loss": 4.9242,
|
|
"mean_token_accuracy": 0.20620774775743483,
|
|
"num_tokens": 25707528.0,
|
|
"step": 13975
|
|
},
|
|
{
|
|
"entropy": 5.295796537399292,
|
|
"epoch": 1.1677246909455397,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004868594470399541,
|
|
"loss": 4.8571,
|
|
"mean_token_accuracy": 0.21744544357061385,
|
|
"num_tokens": 25716568.0,
|
|
"step": 13980
|
|
},
|
|
{
|
|
"entropy": 5.307967329025269,
|
|
"epoch": 1.1681423321082525,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00048684942043268137,
|
|
"loss": 4.8975,
|
|
"mean_token_accuracy": 0.20828187465667725,
|
|
"num_tokens": 25726441.0,
|
|
"step": 13985
|
|
},
|
|
{
|
|
"entropy": 5.2155413150787355,
|
|
"epoch": 1.1685599732709655,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00048683939011672953,
|
|
"loss": 4.8562,
|
|
"mean_token_accuracy": 0.21843262165784835,
|
|
"num_tokens": 25735386.0,
|
|
"step": 13990
|
|
},
|
|
{
|
|
"entropy": 5.293379449844361,
|
|
"epoch": 1.1689776144336785,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00048682935609227414,
|
|
"loss": 4.8439,
|
|
"mean_token_accuracy": 0.2108369439840317,
|
|
"num_tokens": 25744758.0,
|
|
"step": 13995
|
|
},
|
|
{
|
|
"entropy": 5.235113859176636,
|
|
"epoch": 1.1693952555963916,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00048681931835949083,
|
|
"loss": 4.9004,
|
|
"mean_token_accuracy": 0.21151605248451233,
|
|
"num_tokens": 25753836.0,
|
|
"step": 14000
|
|
},
|
|
{
|
|
"entropy": 5.285754776000976,
|
|
"epoch": 1.1698128967591046,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004868092769185555,
|
|
"loss": 4.9311,
|
|
"mean_token_accuracy": 0.2012794241309166,
|
|
"num_tokens": 25763302.0,
|
|
"step": 14005
|
|
},
|
|
{
|
|
"entropy": 5.2695681095123295,
|
|
"epoch": 1.1702305379218176,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00048679923176964384,
|
|
"loss": 4.7901,
|
|
"mean_token_accuracy": 0.22135670632123947,
|
|
"num_tokens": 25772204.0,
|
|
"step": 14010
|
|
},
|
|
{
|
|
"entropy": 5.264920616149903,
|
|
"epoch": 1.1706481790845307,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004867891829129316,
|
|
"loss": 4.8803,
|
|
"mean_token_accuracy": 0.21377789229154587,
|
|
"num_tokens": 25781762.0,
|
|
"step": 14015
|
|
},
|
|
{
|
|
"entropy": 5.265269565582275,
|
|
"epoch": 1.1710658202472435,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004867791303485948,
|
|
"loss": 4.9393,
|
|
"mean_token_accuracy": 0.2100481480360031,
|
|
"num_tokens": 25791573.0,
|
|
"step": 14020
|
|
},
|
|
{
|
|
"entropy": 5.2634077072143555,
|
|
"epoch": 1.1714834614099565,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004867690740768094,
|
|
"loss": 4.8807,
|
|
"mean_token_accuracy": 0.21862648278474808,
|
|
"num_tokens": 25800777.0,
|
|
"step": 14025
|
|
},
|
|
{
|
|
"entropy": 5.241231250762939,
|
|
"epoch": 1.1719011025726696,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00048675901409775147,
|
|
"loss": 4.8383,
|
|
"mean_token_accuracy": 0.21715591251850128,
|
|
"num_tokens": 25809145.0,
|
|
"step": 14030
|
|
},
|
|
{
|
|
"entropy": 5.18926854133606,
|
|
"epoch": 1.1723187437353826,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00048674895041159714,
|
|
"loss": 4.7746,
|
|
"mean_token_accuracy": 0.22451866865158082,
|
|
"num_tokens": 25817884.0,
|
|
"step": 14035
|
|
},
|
|
{
|
|
"entropy": 5.267607164382935,
|
|
"epoch": 1.1727363848980956,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00048673888301852247,
|
|
"loss": 4.9013,
|
|
"mean_token_accuracy": 0.21320959627628328,
|
|
"num_tokens": 25826953.0,
|
|
"step": 14040
|
|
},
|
|
{
|
|
"entropy": 5.325677919387817,
|
|
"epoch": 1.1731540260608084,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004867288119187039,
|
|
"loss": 4.9352,
|
|
"mean_token_accuracy": 0.21173907965421676,
|
|
"num_tokens": 25835597.0,
|
|
"step": 14045
|
|
},
|
|
{
|
|
"entropy": 5.281623268127442,
|
|
"epoch": 1.1735716672235215,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004867187371123175,
|
|
"loss": 4.9053,
|
|
"mean_token_accuracy": 0.20905899703502656,
|
|
"num_tokens": 25845072.0,
|
|
"step": 14050
|
|
},
|
|
{
|
|
"entropy": 5.266669988632202,
|
|
"epoch": 1.1739893083862345,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00048670865859953984,
|
|
"loss": 4.8033,
|
|
"mean_token_accuracy": 0.2188041925430298,
|
|
"num_tokens": 25854902.0,
|
|
"step": 14055
|
|
},
|
|
{
|
|
"entropy": 5.308465433120728,
|
|
"epoch": 1.1744069495489475,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004866985763805472,
|
|
"loss": 4.9355,
|
|
"mean_token_accuracy": 0.20951370149850845,
|
|
"num_tokens": 25863807.0,
|
|
"step": 14060
|
|
},
|
|
{
|
|
"entropy": 5.291536140441894,
|
|
"epoch": 1.1748245907116606,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004866884904555162,
|
|
"loss": 4.9467,
|
|
"mean_token_accuracy": 0.2053670957684517,
|
|
"num_tokens": 25873709.0,
|
|
"step": 14065
|
|
},
|
|
{
|
|
"entropy": 5.2727251052856445,
|
|
"epoch": 1.1752422318743736,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004866784008246233,
|
|
"loss": 4.9113,
|
|
"mean_token_accuracy": 0.21408339142799376,
|
|
"num_tokens": 25883425.0,
|
|
"step": 14070
|
|
},
|
|
{
|
|
"entropy": 5.2046891212463375,
|
|
"epoch": 1.1756598730370866,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004866683074880453,
|
|
"loss": 4.7784,
|
|
"mean_token_accuracy": 0.22162298411130904,
|
|
"num_tokens": 25892317.0,
|
|
"step": 14075
|
|
},
|
|
{
|
|
"entropy": 5.247200393676758,
|
|
"epoch": 1.1760775141997994,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00048665821044595884,
|
|
"loss": 4.8535,
|
|
"mean_token_accuracy": 0.2172433093190193,
|
|
"num_tokens": 25901733.0,
|
|
"step": 14080
|
|
},
|
|
{
|
|
"entropy": 5.204548740386963,
|
|
"epoch": 1.1764951553625125,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004866481096985405,
|
|
"loss": 4.8304,
|
|
"mean_token_accuracy": 0.2176731452345848,
|
|
"num_tokens": 25911574.0,
|
|
"step": 14085
|
|
},
|
|
{
|
|
"entropy": 5.252797412872314,
|
|
"epoch": 1.1769127965252255,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004866380052459673,
|
|
"loss": 4.9261,
|
|
"mean_token_accuracy": 0.20866089463233947,
|
|
"num_tokens": 25921152.0,
|
|
"step": 14090
|
|
},
|
|
{
|
|
"entropy": 5.338256549835205,
|
|
"epoch": 1.1773304376879385,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004866278970884161,
|
|
"loss": 4.8768,
|
|
"mean_token_accuracy": 0.2088471069931984,
|
|
"num_tokens": 25930455.0,
|
|
"step": 14095
|
|
},
|
|
{
|
|
"entropy": 5.236100149154663,
|
|
"epoch": 1.1777480788506516,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00048661778522606376,
|
|
"loss": 4.8103,
|
|
"mean_token_accuracy": 0.21504587084054946,
|
|
"num_tokens": 25939298.0,
|
|
"step": 14100
|
|
},
|
|
{
|
|
"entropy": 5.218051290512085,
|
|
"epoch": 1.1781657200133644,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00048660766965908736,
|
|
"loss": 4.8645,
|
|
"mean_token_accuracy": 0.21135970205068588,
|
|
"num_tokens": 25948426.0,
|
|
"step": 14105
|
|
},
|
|
{
|
|
"entropy": 5.277697944641114,
|
|
"epoch": 1.1785833611760774,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00048659755038766406,
|
|
"loss": 4.865,
|
|
"mean_token_accuracy": 0.21691957712173462,
|
|
"num_tokens": 25958469.0,
|
|
"step": 14110
|
|
},
|
|
{
|
|
"entropy": 5.249806594848633,
|
|
"epoch": 1.1790010023387905,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00048658742741197086,
|
|
"loss": 4.7767,
|
|
"mean_token_accuracy": 0.23051322400569915,
|
|
"num_tokens": 25967173.0,
|
|
"step": 14115
|
|
},
|
|
{
|
|
"entropy": 5.242997360229492,
|
|
"epoch": 1.1794186435015035,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00048657730073218517,
|
|
"loss": 4.8929,
|
|
"mean_token_accuracy": 0.21696035861968993,
|
|
"num_tokens": 25976474.0,
|
|
"step": 14120
|
|
},
|
|
{
|
|
"entropy": 5.297246885299683,
|
|
"epoch": 1.1798362846642165,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004865671703484841,
|
|
"loss": 4.8732,
|
|
"mean_token_accuracy": 0.21733936965465545,
|
|
"num_tokens": 25984745.0,
|
|
"step": 14125
|
|
},
|
|
{
|
|
"entropy": 5.252665853500366,
|
|
"epoch": 1.1802539258269296,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00048655703626104493,
|
|
"loss": 4.8108,
|
|
"mean_token_accuracy": 0.22127807438373565,
|
|
"num_tokens": 25993265.0,
|
|
"step": 14130
|
|
},
|
|
{
|
|
"entropy": 5.2750012397766115,
|
|
"epoch": 1.1806715669896426,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00048654689847004535,
|
|
"loss": 4.846,
|
|
"mean_token_accuracy": 0.21467218399047852,
|
|
"num_tokens": 26002390.0,
|
|
"step": 14135
|
|
},
|
|
{
|
|
"entropy": 5.342982149124145,
|
|
"epoch": 1.1810892081523554,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004865367569756626,
|
|
"loss": 4.9883,
|
|
"mean_token_accuracy": 0.2171557754278183,
|
|
"num_tokens": 26013086.0,
|
|
"step": 14140
|
|
},
|
|
{
|
|
"entropy": 5.335472488403321,
|
|
"epoch": 1.1815068493150684,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00048652661177807426,
|
|
"loss": 4.8893,
|
|
"mean_token_accuracy": 0.21468782275915146,
|
|
"num_tokens": 26022119.0,
|
|
"step": 14145
|
|
},
|
|
{
|
|
"entropy": 5.283700847625733,
|
|
"epoch": 1.1819244904777815,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00048651646287745803,
|
|
"loss": 4.9287,
|
|
"mean_token_accuracy": 0.2100604310631752,
|
|
"num_tokens": 26031805.0,
|
|
"step": 14150
|
|
},
|
|
{
|
|
"entropy": 5.282706832885742,
|
|
"epoch": 1.1823421316404945,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00048650631027399155,
|
|
"loss": 4.9003,
|
|
"mean_token_accuracy": 0.21225172132253647,
|
|
"num_tokens": 26040965.0,
|
|
"step": 14155
|
|
},
|
|
{
|
|
"entropy": 5.286909437179565,
|
|
"epoch": 1.1827597728032075,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00048649615396785246,
|
|
"loss": 4.8993,
|
|
"mean_token_accuracy": 0.20916713625192643,
|
|
"num_tokens": 26049618.0,
|
|
"step": 14160
|
|
},
|
|
{
|
|
"entropy": 5.275590085983277,
|
|
"epoch": 1.1831774139659206,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00048648599395921863,
|
|
"loss": 4.8472,
|
|
"mean_token_accuracy": 0.21483348459005355,
|
|
"num_tokens": 26058335.0,
|
|
"step": 14165
|
|
},
|
|
{
|
|
"entropy": 5.155168104171753,
|
|
"epoch": 1.1835950551286334,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00048647583024826786,
|
|
"loss": 4.7323,
|
|
"mean_token_accuracy": 0.22726014703512193,
|
|
"num_tokens": 26067361.0,
|
|
"step": 14170
|
|
},
|
|
{
|
|
"entropy": 5.304991912841797,
|
|
"epoch": 1.1840126962913464,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00048646566283517824,
|
|
"loss": 4.9452,
|
|
"mean_token_accuracy": 0.20840476602315902,
|
|
"num_tokens": 26077401.0,
|
|
"step": 14175
|
|
},
|
|
{
|
|
"entropy": 5.211455249786377,
|
|
"epoch": 1.1844303374540595,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00048645549172012756,
|
|
"loss": 4.7743,
|
|
"mean_token_accuracy": 0.22259992063045503,
|
|
"num_tokens": 26086422.0,
|
|
"step": 14180
|
|
},
|
|
{
|
|
"entropy": 5.288153648376465,
|
|
"epoch": 1.1848479786167725,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000486445316903294,
|
|
"loss": 4.9379,
|
|
"mean_token_accuracy": 0.2093539461493492,
|
|
"num_tokens": 26095974.0,
|
|
"step": 14185
|
|
},
|
|
{
|
|
"entropy": 5.237947940826416,
|
|
"epoch": 1.1852656197794855,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004864351383848556,
|
|
"loss": 4.8124,
|
|
"mean_token_accuracy": 0.22141705602407455,
|
|
"num_tokens": 26104782.0,
|
|
"step": 14190
|
|
},
|
|
{
|
|
"entropy": 5.28892765045166,
|
|
"epoch": 1.1856832609421986,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004864249561649906,
|
|
"loss": 4.8966,
|
|
"mean_token_accuracy": 0.21697104275226592,
|
|
"num_tokens": 26113769.0,
|
|
"step": 14195
|
|
},
|
|
{
|
|
"entropy": 5.290374135971069,
|
|
"epoch": 1.1861009021049114,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004864147702438773,
|
|
"loss": 4.9337,
|
|
"mean_token_accuracy": 0.2121882975101471,
|
|
"num_tokens": 26123759.0,
|
|
"step": 14200
|
|
},
|
|
{
|
|
"entropy": 5.264079236984253,
|
|
"epoch": 1.1865185432676244,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000486404580621694,
|
|
"loss": 4.8099,
|
|
"mean_token_accuracy": 0.21639186441898345,
|
|
"num_tokens": 26133392.0,
|
|
"step": 14205
|
|
},
|
|
{
|
|
"entropy": 5.316814517974853,
|
|
"epoch": 1.1869361844303374,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000486394387298619,
|
|
"loss": 4.9674,
|
|
"mean_token_accuracy": 0.2074139565229416,
|
|
"num_tokens": 26142102.0,
|
|
"step": 14210
|
|
},
|
|
{
|
|
"entropy": 5.231172037124634,
|
|
"epoch": 1.1873538255930505,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00048638419027483075,
|
|
"loss": 4.8411,
|
|
"mean_token_accuracy": 0.21798044592142105,
|
|
"num_tokens": 26151504.0,
|
|
"step": 14215
|
|
},
|
|
{
|
|
"entropy": 5.297414302825928,
|
|
"epoch": 1.1877714667557635,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004863739895505079,
|
|
"loss": 4.9885,
|
|
"mean_token_accuracy": 0.20553924292325973,
|
|
"num_tokens": 26160717.0,
|
|
"step": 14220
|
|
},
|
|
{
|
|
"entropy": 5.229414701461792,
|
|
"epoch": 1.1881891079184765,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00048636378512582884,
|
|
"loss": 4.8363,
|
|
"mean_token_accuracy": 0.21140021383762359,
|
|
"num_tokens": 26169788.0,
|
|
"step": 14225
|
|
},
|
|
{
|
|
"entropy": 5.254428577423096,
|
|
"epoch": 1.1886067490811894,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00048635357700097236,
|
|
"loss": 4.8238,
|
|
"mean_token_accuracy": 0.20885974615812303,
|
|
"num_tokens": 26178904.0,
|
|
"step": 14230
|
|
},
|
|
{
|
|
"entropy": 5.306118440628052,
|
|
"epoch": 1.1890243902439024,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004863433651761171,
|
|
"loss": 4.8986,
|
|
"mean_token_accuracy": 0.21250129491090775,
|
|
"num_tokens": 26188832.0,
|
|
"step": 14235
|
|
},
|
|
{
|
|
"entropy": 5.330101108551025,
|
|
"epoch": 1.1894420314066154,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004863331496514418,
|
|
"loss": 4.9652,
|
|
"mean_token_accuracy": 0.21003050357103348,
|
|
"num_tokens": 26199003.0,
|
|
"step": 14240
|
|
},
|
|
{
|
|
"entropy": 5.351752281188965,
|
|
"epoch": 1.1898596725693285,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00048632293042712545,
|
|
"loss": 4.8394,
|
|
"mean_token_accuracy": 0.2104760080575943,
|
|
"num_tokens": 26209001.0,
|
|
"step": 14245
|
|
},
|
|
{
|
|
"entropy": 5.252216100692749,
|
|
"epoch": 1.1902773137320415,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00048631270750334674,
|
|
"loss": 4.8675,
|
|
"mean_token_accuracy": 0.2157977595925331,
|
|
"num_tokens": 26217834.0,
|
|
"step": 14250
|
|
},
|
|
{
|
|
"entropy": 5.29575629234314,
|
|
"epoch": 1.1906949548947545,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00048630248088028474,
|
|
"loss": 4.9222,
|
|
"mean_token_accuracy": 0.2151055946946144,
|
|
"num_tokens": 26226935.0,
|
|
"step": 14255
|
|
},
|
|
{
|
|
"entropy": 5.297951984405517,
|
|
"epoch": 1.1911125960574673,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004862922505581185,
|
|
"loss": 4.911,
|
|
"mean_token_accuracy": 0.2155863329768181,
|
|
"num_tokens": 26236874.0,
|
|
"step": 14260
|
|
},
|
|
{
|
|
"entropy": 5.291000509262085,
|
|
"epoch": 1.1915302372201804,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000486282016537027,
|
|
"loss": 4.8612,
|
|
"mean_token_accuracy": 0.2191222459077835,
|
|
"num_tokens": 26246361.0,
|
|
"step": 14265
|
|
},
|
|
{
|
|
"entropy": 5.197998094558716,
|
|
"epoch": 1.1919478783828934,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00048627177881718954,
|
|
"loss": 4.8108,
|
|
"mean_token_accuracy": 0.22168292850255966,
|
|
"num_tokens": 26255316.0,
|
|
"step": 14270
|
|
},
|
|
{
|
|
"entropy": 5.401647520065308,
|
|
"epoch": 1.1923655195456064,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004862615373987853,
|
|
"loss": 4.9469,
|
|
"mean_token_accuracy": 0.20879973322153092,
|
|
"num_tokens": 26265250.0,
|
|
"step": 14275
|
|
},
|
|
{
|
|
"entropy": 5.207538509368897,
|
|
"epoch": 1.1927831607083195,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004862512922819935,
|
|
"loss": 4.7237,
|
|
"mean_token_accuracy": 0.2249722436070442,
|
|
"num_tokens": 26273858.0,
|
|
"step": 14280
|
|
},
|
|
{
|
|
"entropy": 5.28621015548706,
|
|
"epoch": 1.1932008018710325,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004862410434669936,
|
|
"loss": 4.9742,
|
|
"mean_token_accuracy": 0.21151680797338485,
|
|
"num_tokens": 26283536.0,
|
|
"step": 14285
|
|
},
|
|
{
|
|
"entropy": 5.270149993896484,
|
|
"epoch": 1.1936184430337453,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00048623079095396496,
|
|
"loss": 4.8006,
|
|
"mean_token_accuracy": 0.21966674476861953,
|
|
"num_tokens": 26291761.0,
|
|
"step": 14290
|
|
},
|
|
{
|
|
"entropy": 5.2545617580413815,
|
|
"epoch": 1.1940360841964583,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000486220534743087,
|
|
"loss": 4.848,
|
|
"mean_token_accuracy": 0.20726076662540435,
|
|
"num_tokens": 26301082.0,
|
|
"step": 14295
|
|
},
|
|
{
|
|
"entropy": 5.248863792419433,
|
|
"epoch": 1.1944537253591714,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004862102748345394,
|
|
"loss": 4.9058,
|
|
"mean_token_accuracy": 0.20632270276546477,
|
|
"num_tokens": 26310424.0,
|
|
"step": 14300
|
|
},
|
|
{
|
|
"entropy": 5.287345743179321,
|
|
"epoch": 1.1948713665218844,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00048620001122850164,
|
|
"loss": 4.969,
|
|
"mean_token_accuracy": 0.21015441715717315,
|
|
"num_tokens": 26319442.0,
|
|
"step": 14305
|
|
},
|
|
{
|
|
"entropy": 5.226160764694214,
|
|
"epoch": 1.1952890076845974,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004861897439251535,
|
|
"loss": 4.7999,
|
|
"mean_token_accuracy": 0.21991005092859267,
|
|
"num_tokens": 26327757.0,
|
|
"step": 14310
|
|
},
|
|
{
|
|
"entropy": 5.269315147399903,
|
|
"epoch": 1.1957066488473105,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00048617947292467473,
|
|
"loss": 4.8532,
|
|
"mean_token_accuracy": 0.21732535660266877,
|
|
"num_tokens": 26337327.0,
|
|
"step": 14315
|
|
},
|
|
{
|
|
"entropy": 5.305079460144043,
|
|
"epoch": 1.1961242900100233,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00048616919822724506,
|
|
"loss": 4.9271,
|
|
"mean_token_accuracy": 0.21783028393983841,
|
|
"num_tokens": 26345821.0,
|
|
"step": 14320
|
|
},
|
|
{
|
|
"entropy": 5.288415336608887,
|
|
"epoch": 1.1965419311727363,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00048615891983304436,
|
|
"loss": 4.881,
|
|
"mean_token_accuracy": 0.21573809832334517,
|
|
"num_tokens": 26355423.0,
|
|
"step": 14325
|
|
},
|
|
{
|
|
"entropy": 5.236432313919067,
|
|
"epoch": 1.1969595723354494,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004861486377422526,
|
|
"loss": 4.762,
|
|
"mean_token_accuracy": 0.21987208873033523,
|
|
"num_tokens": 26363770.0,
|
|
"step": 14330
|
|
},
|
|
{
|
|
"entropy": 5.220354413986206,
|
|
"epoch": 1.1973772134981624,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004861383519550498,
|
|
"loss": 4.8173,
|
|
"mean_token_accuracy": 0.21819413751363753,
|
|
"num_tokens": 26373530.0,
|
|
"step": 14335
|
|
},
|
|
{
|
|
"entropy": 5.348572683334351,
|
|
"epoch": 1.1977948546608754,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00048612806247161594,
|
|
"loss": 4.9762,
|
|
"mean_token_accuracy": 0.20434900969266892,
|
|
"num_tokens": 26382960.0,
|
|
"step": 14340
|
|
},
|
|
{
|
|
"entropy": 5.22479100227356,
|
|
"epoch": 1.1982124958235885,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004861177692921313,
|
|
"loss": 4.7668,
|
|
"mean_token_accuracy": 0.22742414921522142,
|
|
"num_tokens": 26392105.0,
|
|
"step": 14345
|
|
},
|
|
{
|
|
"entropy": 5.240310907363892,
|
|
"epoch": 1.1986301369863013,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00048610747241677595,
|
|
"loss": 4.8797,
|
|
"mean_token_accuracy": 0.21708065271377563,
|
|
"num_tokens": 26401780.0,
|
|
"step": 14350
|
|
},
|
|
{
|
|
"entropy": 5.245091819763184,
|
|
"epoch": 1.1990477781490143,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004860971718457302,
|
|
"loss": 4.8752,
|
|
"mean_token_accuracy": 0.21635661125183106,
|
|
"num_tokens": 26410290.0,
|
|
"step": 14355
|
|
},
|
|
{
|
|
"entropy": 5.303373384475708,
|
|
"epoch": 1.1994654193117273,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004860868675791743,
|
|
"loss": 4.8997,
|
|
"mean_token_accuracy": 0.21623397916555404,
|
|
"num_tokens": 26420591.0,
|
|
"step": 14360
|
|
},
|
|
{
|
|
"entropy": 5.341029071807862,
|
|
"epoch": 1.1998830604744404,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00048607655961728876,
|
|
"loss": 4.9195,
|
|
"mean_token_accuracy": 0.20581527650356293,
|
|
"num_tokens": 26429453.0,
|
|
"step": 14365
|
|
},
|
|
{
|
|
"entropy": 5.3321247577667235,
|
|
"epoch": 1.2003007016371534,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000486066247960254,
|
|
"loss": 4.9075,
|
|
"mean_token_accuracy": 0.21396533399820328,
|
|
"num_tokens": 26439111.0,
|
|
"step": 14370
|
|
},
|
|
{
|
|
"entropy": 5.258881998062134,
|
|
"epoch": 1.2007183427998664,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00048605593260825044,
|
|
"loss": 4.821,
|
|
"mean_token_accuracy": 0.22210421711206435,
|
|
"num_tokens": 26448071.0,
|
|
"step": 14375
|
|
},
|
|
{
|
|
"entropy": 5.3353794574737545,
|
|
"epoch": 1.2011359839625793,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00048604561356145875,
|
|
"loss": 4.9918,
|
|
"mean_token_accuracy": 0.2131146863102913,
|
|
"num_tokens": 26457226.0,
|
|
"step": 14380
|
|
},
|
|
{
|
|
"entropy": 5.2923667430877686,
|
|
"epoch": 1.2015536251252923,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00048603529082005955,
|
|
"loss": 4.872,
|
|
"mean_token_accuracy": 0.21626408249139786,
|
|
"num_tokens": 26466052.0,
|
|
"step": 14385
|
|
},
|
|
{
|
|
"entropy": 5.32365870475769,
|
|
"epoch": 1.2019712662880053,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00048602496438423354,
|
|
"loss": 4.8826,
|
|
"mean_token_accuracy": 0.20888697803020478,
|
|
"num_tokens": 26476102.0,
|
|
"step": 14390
|
|
},
|
|
{
|
|
"entropy": 5.256476926803589,
|
|
"epoch": 1.2023889074507184,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004860146342541616,
|
|
"loss": 4.8823,
|
|
"mean_token_accuracy": 0.21264505684375762,
|
|
"num_tokens": 26485775.0,
|
|
"step": 14395
|
|
},
|
|
{
|
|
"entropy": 5.254738426208496,
|
|
"epoch": 1.2028065486134314,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004860043004300244,
|
|
"loss": 4.8531,
|
|
"mean_token_accuracy": 0.21507709920406343,
|
|
"num_tokens": 26495268.0,
|
|
"step": 14400
|
|
},
|
|
{
|
|
"entropy": 5.343999624252319,
|
|
"epoch": 1.2032241897761444,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000485993962912003,
|
|
"loss": 4.9144,
|
|
"mean_token_accuracy": 0.21374761015176774,
|
|
"num_tokens": 26505253.0,
|
|
"step": 14405
|
|
},
|
|
{
|
|
"entropy": 5.269192314147949,
|
|
"epoch": 1.2036418309388572,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004859836217002783,
|
|
"loss": 4.8622,
|
|
"mean_token_accuracy": 0.21690179109573365,
|
|
"num_tokens": 26513609.0,
|
|
"step": 14410
|
|
},
|
|
{
|
|
"entropy": 5.308850240707398,
|
|
"epoch": 1.2040594721015703,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004859732767950313,
|
|
"loss": 4.9351,
|
|
"mean_token_accuracy": 0.2087784841656685,
|
|
"num_tokens": 26523565.0,
|
|
"step": 14415
|
|
},
|
|
{
|
|
"entropy": 5.275409936904907,
|
|
"epoch": 1.2044771132642833,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00048596292819644315,
|
|
"loss": 4.8205,
|
|
"mean_token_accuracy": 0.22033887058496476,
|
|
"num_tokens": 26532554.0,
|
|
"step": 14420
|
|
},
|
|
{
|
|
"entropy": 5.253980016708374,
|
|
"epoch": 1.2048947544269963,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000485952575904695,
|
|
"loss": 4.9531,
|
|
"mean_token_accuracy": 0.21058446615934373,
|
|
"num_tokens": 26541474.0,
|
|
"step": 14425
|
|
},
|
|
{
|
|
"entropy": 5.228180980682373,
|
|
"epoch": 1.2053123955897094,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00048594221991996814,
|
|
"loss": 4.8244,
|
|
"mean_token_accuracy": 0.21837536096572877,
|
|
"num_tokens": 26551095.0,
|
|
"step": 14430
|
|
},
|
|
{
|
|
"entropy": 5.242866849899292,
|
|
"epoch": 1.2057300367524224,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00048593186024244373,
|
|
"loss": 4.8243,
|
|
"mean_token_accuracy": 0.2279058039188385,
|
|
"num_tokens": 26560144.0,
|
|
"step": 14435
|
|
},
|
|
{
|
|
"entropy": 5.1893613815307615,
|
|
"epoch": 1.2061476779151352,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004859214968723033,
|
|
"loss": 4.7593,
|
|
"mean_token_accuracy": 0.22170279920101166,
|
|
"num_tokens": 26568983.0,
|
|
"step": 14440
|
|
},
|
|
{
|
|
"entropy": 5.220506286621093,
|
|
"epoch": 1.2065653190778483,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00048591112980972813,
|
|
"loss": 4.8049,
|
|
"mean_token_accuracy": 0.2230754479765892,
|
|
"num_tokens": 26577229.0,
|
|
"step": 14445
|
|
},
|
|
{
|
|
"entropy": 5.30432620048523,
|
|
"epoch": 1.2069829602405613,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004859007590548997,
|
|
"loss": 4.8725,
|
|
"mean_token_accuracy": 0.21160688549280166,
|
|
"num_tokens": 26585567.0,
|
|
"step": 14450
|
|
},
|
|
{
|
|
"entropy": 5.264838552474975,
|
|
"epoch": 1.2074006014032743,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00048589038460799974,
|
|
"loss": 4.908,
|
|
"mean_token_accuracy": 0.21685008555650712,
|
|
"num_tokens": 26594656.0,
|
|
"step": 14455
|
|
},
|
|
{
|
|
"entropy": 5.2557610988616945,
|
|
"epoch": 1.2078182425659874,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004858800064692097,
|
|
"loss": 4.881,
|
|
"mean_token_accuracy": 0.20496947765350343,
|
|
"num_tokens": 26604002.0,
|
|
"step": 14460
|
|
},
|
|
{
|
|
"entropy": 5.276022720336914,
|
|
"epoch": 1.2082358837287004,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00048586962463871124,
|
|
"loss": 4.8622,
|
|
"mean_token_accuracy": 0.21516236662864685,
|
|
"num_tokens": 26613376.0,
|
|
"step": 14465
|
|
},
|
|
{
|
|
"entropy": 5.401705408096314,
|
|
"epoch": 1.2086535248914134,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00048585923911668625,
|
|
"loss": 5.0122,
|
|
"mean_token_accuracy": 0.20901001691818238,
|
|
"num_tokens": 26623117.0,
|
|
"step": 14470
|
|
},
|
|
{
|
|
"entropy": 5.281592750549317,
|
|
"epoch": 1.2090711660541262,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00048584884990331644,
|
|
"loss": 4.9096,
|
|
"mean_token_accuracy": 0.2111772269010544,
|
|
"num_tokens": 26632855.0,
|
|
"step": 14475
|
|
},
|
|
{
|
|
"entropy": 5.165176439285278,
|
|
"epoch": 1.2094888072168393,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00048583845699878375,
|
|
"loss": 4.6867,
|
|
"mean_token_accuracy": 0.23215150088071823,
|
|
"num_tokens": 26641753.0,
|
|
"step": 14480
|
|
},
|
|
{
|
|
"entropy": 5.1794507026672365,
|
|
"epoch": 1.2099064483795523,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004858280604032701,
|
|
"loss": 4.8279,
|
|
"mean_token_accuracy": 0.22068871408700944,
|
|
"num_tokens": 26650278.0,
|
|
"step": 14485
|
|
},
|
|
{
|
|
"entropy": 5.291289234161377,
|
|
"epoch": 1.2103240895422653,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00048581766011695745,
|
|
"loss": 4.893,
|
|
"mean_token_accuracy": 0.22035497128963472,
|
|
"num_tokens": 26658891.0,
|
|
"step": 14490
|
|
},
|
|
{
|
|
"entropy": 5.288300848007202,
|
|
"epoch": 1.2107417307049784,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00048580725614002785,
|
|
"loss": 4.9197,
|
|
"mean_token_accuracy": 0.20947515815496445,
|
|
"num_tokens": 26668197.0,
|
|
"step": 14495
|
|
},
|
|
{
|
|
"entropy": 5.328019523620606,
|
|
"epoch": 1.2111593718676912,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00048579684847266353,
|
|
"loss": 4.948,
|
|
"mean_token_accuracy": 0.20997326374053954,
|
|
"num_tokens": 26676796.0,
|
|
"step": 14500
|
|
},
|
|
{
|
|
"entropy": 5.226969242095947,
|
|
"epoch": 1.2115770130304042,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004857864371150467,
|
|
"loss": 4.8267,
|
|
"mean_token_accuracy": 0.21793274134397506,
|
|
"num_tokens": 26686237.0,
|
|
"step": 14505
|
|
},
|
|
{
|
|
"entropy": 5.285734176635742,
|
|
"epoch": 1.2119946541931172,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00048577602206735943,
|
|
"loss": 4.8157,
|
|
"mean_token_accuracy": 0.22215263843536376,
|
|
"num_tokens": 26695931.0,
|
|
"step": 14510
|
|
},
|
|
{
|
|
"entropy": 5.214428901672363,
|
|
"epoch": 1.2124122953558303,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004857656033297843,
|
|
"loss": 4.8047,
|
|
"mean_token_accuracy": 0.2246819704771042,
|
|
"num_tokens": 26704326.0,
|
|
"step": 14515
|
|
},
|
|
{
|
|
"entropy": 5.197016668319702,
|
|
"epoch": 1.2128299365185433,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00048575518090250347,
|
|
"loss": 4.7335,
|
|
"mean_token_accuracy": 0.2224571079015732,
|
|
"num_tokens": 26713000.0,
|
|
"step": 14520
|
|
},
|
|
{
|
|
"entropy": 5.296850776672363,
|
|
"epoch": 1.2132475776812564,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004857447547856996,
|
|
"loss": 4.8821,
|
|
"mean_token_accuracy": 0.2097340404987335,
|
|
"num_tokens": 26722014.0,
|
|
"step": 14525
|
|
},
|
|
{
|
|
"entropy": 5.281072378158569,
|
|
"epoch": 1.2136652188439694,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004857343249795552,
|
|
"loss": 4.8443,
|
|
"mean_token_accuracy": 0.21931581795215607,
|
|
"num_tokens": 26730975.0,
|
|
"step": 14530
|
|
},
|
|
{
|
|
"entropy": 5.207539176940918,
|
|
"epoch": 1.2140828600066822,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004857238914842526,
|
|
"loss": 4.9063,
|
|
"mean_token_accuracy": 0.21440516412258148,
|
|
"num_tokens": 26740087.0,
|
|
"step": 14535
|
|
},
|
|
{
|
|
"entropy": 5.2557408809661865,
|
|
"epoch": 1.2145005011693952,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00048571345429997473,
|
|
"loss": 4.906,
|
|
"mean_token_accuracy": 0.20803391933441162,
|
|
"num_tokens": 26749820.0,
|
|
"step": 14540
|
|
},
|
|
{
|
|
"entropy": 5.33833065032959,
|
|
"epoch": 1.2149181423321083,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00048570301342690416,
|
|
"loss": 4.9662,
|
|
"mean_token_accuracy": 0.21338541060686111,
|
|
"num_tokens": 26759850.0,
|
|
"step": 14545
|
|
},
|
|
{
|
|
"entropy": 5.213677930831909,
|
|
"epoch": 1.2153357834948213,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004856925688652238,
|
|
"loss": 4.7242,
|
|
"mean_token_accuracy": 0.22617016583681107,
|
|
"num_tokens": 26769519.0,
|
|
"step": 14550
|
|
},
|
|
{
|
|
"entropy": 5.297413015365601,
|
|
"epoch": 1.2157534246575343,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00048568212061511634,
|
|
"loss": 4.9121,
|
|
"mean_token_accuracy": 0.20078637450933456,
|
|
"num_tokens": 26779999.0,
|
|
"step": 14555
|
|
},
|
|
{
|
|
"entropy": 5.3005987167358395,
|
|
"epoch": 1.2161710658202471,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00048567166867676475,
|
|
"loss": 4.858,
|
|
"mean_token_accuracy": 0.21063812226057052,
|
|
"num_tokens": 26788903.0,
|
|
"step": 14560
|
|
},
|
|
{
|
|
"entropy": 5.3428626537323,
|
|
"epoch": 1.2165887069829602,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00048566121305035207,
|
|
"loss": 4.939,
|
|
"mean_token_accuracy": 0.2097403198480606,
|
|
"num_tokens": 26799161.0,
|
|
"step": 14565
|
|
},
|
|
{
|
|
"entropy": 5.239137029647827,
|
|
"epoch": 1.2170063481456732,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00048565075373606126,
|
|
"loss": 4.811,
|
|
"mean_token_accuracy": 0.21708568036556244,
|
|
"num_tokens": 26807887.0,
|
|
"step": 14570
|
|
},
|
|
{
|
|
"entropy": 5.270034408569336,
|
|
"epoch": 1.2174239893083862,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00048564029073407545,
|
|
"loss": 4.8104,
|
|
"mean_token_accuracy": 0.2199506789445877,
|
|
"num_tokens": 26816466.0,
|
|
"step": 14575
|
|
},
|
|
{
|
|
"entropy": 5.280757808685303,
|
|
"epoch": 1.2178416304710993,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004856298240445778,
|
|
"loss": 4.9463,
|
|
"mean_token_accuracy": 0.210982109606266,
|
|
"num_tokens": 26825847.0,
|
|
"step": 14580
|
|
},
|
|
{
|
|
"entropy": 5.328578090667724,
|
|
"epoch": 1.2182592716338123,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004856193536677515,
|
|
"loss": 4.9216,
|
|
"mean_token_accuracy": 0.2063239708542824,
|
|
"num_tokens": 26835610.0,
|
|
"step": 14585
|
|
},
|
|
{
|
|
"entropy": 5.318467712402343,
|
|
"epoch": 1.2186769127965253,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00048560887960377995,
|
|
"loss": 4.8243,
|
|
"mean_token_accuracy": 0.2136611044406891,
|
|
"num_tokens": 26844319.0,
|
|
"step": 14590
|
|
},
|
|
{
|
|
"entropy": 5.2986814975738525,
|
|
"epoch": 1.2190945539592382,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00048559840185284647,
|
|
"loss": 4.9282,
|
|
"mean_token_accuracy": 0.20739062279462814,
|
|
"num_tokens": 26853508.0,
|
|
"step": 14595
|
|
},
|
|
{
|
|
"entropy": 5.264918565750122,
|
|
"epoch": 1.2195121951219512,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00048558792041513446,
|
|
"loss": 4.8765,
|
|
"mean_token_accuracy": 0.21719129085540773,
|
|
"num_tokens": 26863268.0,
|
|
"step": 14600
|
|
},
|
|
{
|
|
"entropy": 5.291875219345092,
|
|
"epoch": 1.2199298362846642,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004855774352908273,
|
|
"loss": 4.8684,
|
|
"mean_token_accuracy": 0.21217106878757477,
|
|
"num_tokens": 26871879.0,
|
|
"step": 14605
|
|
},
|
|
{
|
|
"entropy": 5.270335721969604,
|
|
"epoch": 1.2203474774473773,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004855669464801088,
|
|
"loss": 4.9724,
|
|
"mean_token_accuracy": 0.20962318778038025,
|
|
"num_tokens": 26880920.0,
|
|
"step": 14610
|
|
},
|
|
{
|
|
"entropy": 5.334642839431763,
|
|
"epoch": 1.2207651186100903,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00048555645398316237,
|
|
"loss": 4.9428,
|
|
"mean_token_accuracy": 0.2118311494588852,
|
|
"num_tokens": 26890020.0,
|
|
"step": 14615
|
|
},
|
|
{
|
|
"entropy": 5.325588941574097,
|
|
"epoch": 1.221182759772803,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004855459578001718,
|
|
"loss": 4.8642,
|
|
"mean_token_accuracy": 0.20544182062149047,
|
|
"num_tokens": 26899486.0,
|
|
"step": 14620
|
|
},
|
|
{
|
|
"entropy": 5.249404764175415,
|
|
"epoch": 1.2216004009355161,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004855354579313208,
|
|
"loss": 4.8697,
|
|
"mean_token_accuracy": 0.21859646141529082,
|
|
"num_tokens": 26908298.0,
|
|
"step": 14625
|
|
},
|
|
{
|
|
"entropy": 5.357993173599243,
|
|
"epoch": 1.2220180420982292,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004855249543767932,
|
|
"loss": 4.8953,
|
|
"mean_token_accuracy": 0.21050601899623872,
|
|
"num_tokens": 26917601.0,
|
|
"step": 14630
|
|
},
|
|
{
|
|
"entropy": 5.241923189163208,
|
|
"epoch": 1.2224356832609422,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00048551444713677285,
|
|
"loss": 4.7451,
|
|
"mean_token_accuracy": 0.22693941593170167,
|
|
"num_tokens": 26926368.0,
|
|
"step": 14635
|
|
},
|
|
{
|
|
"entropy": 5.255865287780762,
|
|
"epoch": 1.2228533244236552,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00048550393621144374,
|
|
"loss": 4.8763,
|
|
"mean_token_accuracy": 0.2065172925591469,
|
|
"num_tokens": 26935424.0,
|
|
"step": 14640
|
|
},
|
|
{
|
|
"entropy": 5.239245986938476,
|
|
"epoch": 1.2232709655863683,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004854934216009898,
|
|
"loss": 4.8085,
|
|
"mean_token_accuracy": 0.2216997116804123,
|
|
"num_tokens": 26944906.0,
|
|
"step": 14645
|
|
},
|
|
{
|
|
"entropy": 5.242288827896118,
|
|
"epoch": 1.2236886067490813,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004854829033055951,
|
|
"loss": 4.7861,
|
|
"mean_token_accuracy": 0.22614532709121704,
|
|
"num_tokens": 26953709.0,
|
|
"step": 14650
|
|
},
|
|
{
|
|
"entropy": 5.204398965835571,
|
|
"epoch": 1.2241062479117941,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004854723813254439,
|
|
"loss": 4.8508,
|
|
"mean_token_accuracy": 0.2162538304924965,
|
|
"num_tokens": 26962726.0,
|
|
"step": 14655
|
|
},
|
|
{
|
|
"entropy": 5.314360761642456,
|
|
"epoch": 1.2245238890745072,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004854618556607203,
|
|
"loss": 4.9319,
|
|
"mean_token_accuracy": 0.20951235592365264,
|
|
"num_tokens": 26972519.0,
|
|
"step": 14660
|
|
},
|
|
{
|
|
"entropy": 5.294365882873535,
|
|
"epoch": 1.2249415302372202,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00048545132631160856,
|
|
"loss": 4.8268,
|
|
"mean_token_accuracy": 0.21148503720760345,
|
|
"num_tokens": 26981251.0,
|
|
"step": 14665
|
|
},
|
|
{
|
|
"entropy": 5.241532516479492,
|
|
"epoch": 1.2253591713999332,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004854407932782931,
|
|
"loss": 4.8318,
|
|
"mean_token_accuracy": 0.21605629622936248,
|
|
"num_tokens": 26990707.0,
|
|
"step": 14670
|
|
},
|
|
{
|
|
"entropy": 5.240707588195801,
|
|
"epoch": 1.2257768125626463,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004854302565609582,
|
|
"loss": 4.8316,
|
|
"mean_token_accuracy": 0.21615566313266754,
|
|
"num_tokens": 26999364.0,
|
|
"step": 14675
|
|
},
|
|
{
|
|
"entropy": 5.3227087497711185,
|
|
"epoch": 1.226194453725359,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00048541971615978833,
|
|
"loss": 4.9077,
|
|
"mean_token_accuracy": 0.2074078366160393,
|
|
"num_tokens": 27008757.0,
|
|
"step": 14680
|
|
},
|
|
{
|
|
"entropy": 5.279827499389649,
|
|
"epoch": 1.226612094888072,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00048540917207496806,
|
|
"loss": 4.8084,
|
|
"mean_token_accuracy": 0.22025478035211563,
|
|
"num_tokens": 27017244.0,
|
|
"step": 14685
|
|
},
|
|
{
|
|
"entropy": 5.2828083515167235,
|
|
"epoch": 1.2270297360507851,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00048539862430668204,
|
|
"loss": 4.8978,
|
|
"mean_token_accuracy": 0.2113216295838356,
|
|
"num_tokens": 27026527.0,
|
|
"step": 14690
|
|
},
|
|
{
|
|
"entropy": 5.230763006210327,
|
|
"epoch": 1.2274473772134982,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00048538807285511474,
|
|
"loss": 4.8334,
|
|
"mean_token_accuracy": 0.22120669782161712,
|
|
"num_tokens": 27034890.0,
|
|
"step": 14695
|
|
},
|
|
{
|
|
"entropy": 5.236389970779419,
|
|
"epoch": 1.2278650183762112,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00048537751772045103,
|
|
"loss": 4.8132,
|
|
"mean_token_accuracy": 0.2269018843770027,
|
|
"num_tokens": 27044122.0,
|
|
"step": 14700
|
|
},
|
|
{
|
|
"entropy": 5.288397645950317,
|
|
"epoch": 1.2282826595389242,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004853669589028757,
|
|
"loss": 4.8597,
|
|
"mean_token_accuracy": 0.21395805329084397,
|
|
"num_tokens": 27053929.0,
|
|
"step": 14705
|
|
},
|
|
{
|
|
"entropy": 5.285385274887085,
|
|
"epoch": 1.2287003007016373,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004853563964025734,
|
|
"loss": 4.8304,
|
|
"mean_token_accuracy": 0.21364526450634003,
|
|
"num_tokens": 27062914.0,
|
|
"step": 14710
|
|
},
|
|
{
|
|
"entropy": 5.221350860595703,
|
|
"epoch": 1.22911794186435,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00048534583021972926,
|
|
"loss": 4.8615,
|
|
"mean_token_accuracy": 0.21342750042676925,
|
|
"num_tokens": 27072121.0,
|
|
"step": 14715
|
|
},
|
|
{
|
|
"entropy": 5.228186130523682,
|
|
"epoch": 1.2295355830270631,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004853352603545281,
|
|
"loss": 4.8203,
|
|
"mean_token_accuracy": 0.21485669165849686,
|
|
"num_tokens": 27081753.0,
|
|
"step": 14720
|
|
},
|
|
{
|
|
"entropy": 5.280810594558716,
|
|
"epoch": 1.2299532241897762,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004853246868071551,
|
|
"loss": 4.8748,
|
|
"mean_token_accuracy": 0.21020575016736984,
|
|
"num_tokens": 27090942.0,
|
|
"step": 14725
|
|
},
|
|
{
|
|
"entropy": 5.261235618591309,
|
|
"epoch": 1.2303708653524892,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00048531410957779533,
|
|
"loss": 4.9003,
|
|
"mean_token_accuracy": 0.2128758653998375,
|
|
"num_tokens": 27100620.0,
|
|
"step": 14730
|
|
},
|
|
{
|
|
"entropy": 5.363924551010132,
|
|
"epoch": 1.2307885065152022,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004853035286666338,
|
|
"loss": 4.92,
|
|
"mean_token_accuracy": 0.21257224828004836,
|
|
"num_tokens": 27110370.0,
|
|
"step": 14735
|
|
},
|
|
{
|
|
"entropy": 5.269014167785644,
|
|
"epoch": 1.231206147677915,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000485292944073856,
|
|
"loss": 4.8138,
|
|
"mean_token_accuracy": 0.22502953857183455,
|
|
"num_tokens": 27119163.0,
|
|
"step": 14740
|
|
},
|
|
{
|
|
"entropy": 5.210812568664551,
|
|
"epoch": 1.231623788840628,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000485282355799647,
|
|
"loss": 4.7907,
|
|
"mean_token_accuracy": 0.22059214860200882,
|
|
"num_tokens": 27127855.0,
|
|
"step": 14745
|
|
},
|
|
{
|
|
"entropy": 5.275664520263672,
|
|
"epoch": 1.232041430003341,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00048527176384419217,
|
|
"loss": 4.8534,
|
|
"mean_token_accuracy": 0.21228248924016951,
|
|
"num_tokens": 27136932.0,
|
|
"step": 14750
|
|
},
|
|
{
|
|
"entropy": 5.2437896728515625,
|
|
"epoch": 1.2324590711660541,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00048526116820767713,
|
|
"loss": 4.8403,
|
|
"mean_token_accuracy": 0.21661580353975296,
|
|
"num_tokens": 27146371.0,
|
|
"step": 14755
|
|
},
|
|
{
|
|
"entropy": 5.243443870544434,
|
|
"epoch": 1.2328767123287672,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004852505688902872,
|
|
"loss": 4.8527,
|
|
"mean_token_accuracy": 0.2159963682293892,
|
|
"num_tokens": 27156473.0,
|
|
"step": 14760
|
|
},
|
|
{
|
|
"entropy": 5.392106342315674,
|
|
"epoch": 1.2332943534914802,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004852399658922079,
|
|
"loss": 4.9785,
|
|
"mean_token_accuracy": 0.20926444679498674,
|
|
"num_tokens": 27165915.0,
|
|
"step": 14765
|
|
},
|
|
{
|
|
"entropy": 5.201574039459229,
|
|
"epoch": 1.2337119946541932,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004852293592136251,
|
|
"loss": 4.7785,
|
|
"mean_token_accuracy": 0.22138311862945556,
|
|
"num_tokens": 27174792.0,
|
|
"step": 14770
|
|
},
|
|
{
|
|
"entropy": 5.265687799453735,
|
|
"epoch": 1.234129635816906,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004852187488547242,
|
|
"loss": 4.8399,
|
|
"mean_token_accuracy": 0.22009023576974868,
|
|
"num_tokens": 27183785.0,
|
|
"step": 14775
|
|
},
|
|
{
|
|
"entropy": 5.356082820892334,
|
|
"epoch": 1.234547276979619,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00048520813481569116,
|
|
"loss": 5.0137,
|
|
"mean_token_accuracy": 0.206134232878685,
|
|
"num_tokens": 27193599.0,
|
|
"step": 14780
|
|
},
|
|
{
|
|
"entropy": 5.337889528274536,
|
|
"epoch": 1.2349649181423321,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004851975170967116,
|
|
"loss": 4.9312,
|
|
"mean_token_accuracy": 0.21179380267858505,
|
|
"num_tokens": 27202191.0,
|
|
"step": 14785
|
|
},
|
|
{
|
|
"entropy": 5.267582368850708,
|
|
"epoch": 1.2353825593050451,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004851868956979715,
|
|
"loss": 4.9045,
|
|
"mean_token_accuracy": 0.21012948155403138,
|
|
"num_tokens": 27210833.0,
|
|
"step": 14790
|
|
},
|
|
{
|
|
"entropy": 5.234970045089722,
|
|
"epoch": 1.2358002004677582,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004851762706196568,
|
|
"loss": 4.8332,
|
|
"mean_token_accuracy": 0.20961230099201203,
|
|
"num_tokens": 27220053.0,
|
|
"step": 14795
|
|
},
|
|
{
|
|
"entropy": 5.330142545700073,
|
|
"epoch": 1.236217841630471,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00048516564186195353,
|
|
"loss": 4.9292,
|
|
"mean_token_accuracy": 0.214675073325634,
|
|
"num_tokens": 27229370.0,
|
|
"step": 14800
|
|
},
|
|
{
|
|
"entropy": 5.155725288391113,
|
|
"epoch": 1.236635482793184,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00048515500942504763,
|
|
"loss": 4.7821,
|
|
"mean_token_accuracy": 0.22688209712505342,
|
|
"num_tokens": 27238923.0,
|
|
"step": 14805
|
|
},
|
|
{
|
|
"entropy": 5.2777024269104,
|
|
"epoch": 1.237053123955897,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00048514437330912544,
|
|
"loss": 4.8862,
|
|
"mean_token_accuracy": 0.21761640459299086,
|
|
"num_tokens": 27247929.0,
|
|
"step": 14810
|
|
},
|
|
{
|
|
"entropy": 5.276091384887695,
|
|
"epoch": 1.23747076511861,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00048513373351437294,
|
|
"loss": 4.841,
|
|
"mean_token_accuracy": 0.21699076890945435,
|
|
"num_tokens": 27257455.0,
|
|
"step": 14815
|
|
},
|
|
{
|
|
"entropy": 5.258977317810059,
|
|
"epoch": 1.2378884062813231,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00048512309004097653,
|
|
"loss": 4.8951,
|
|
"mean_token_accuracy": 0.20860559791326522,
|
|
"num_tokens": 27267718.0,
|
|
"step": 14820
|
|
},
|
|
{
|
|
"entropy": 5.23208794593811,
|
|
"epoch": 1.2383060474440362,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004851124428891226,
|
|
"loss": 4.8066,
|
|
"mean_token_accuracy": 0.21790262907743455,
|
|
"num_tokens": 27276706.0,
|
|
"step": 14825
|
|
},
|
|
{
|
|
"entropy": 5.212944555282593,
|
|
"epoch": 1.2387236886067492,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004851017920589973,
|
|
"loss": 4.7239,
|
|
"mean_token_accuracy": 0.22478490322828293,
|
|
"num_tokens": 27285389.0,
|
|
"step": 14830
|
|
},
|
|
{
|
|
"entropy": 5.291102647781372,
|
|
"epoch": 1.239141329769462,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004850911375507873,
|
|
"loss": 4.9061,
|
|
"mean_token_accuracy": 0.21679034382104873,
|
|
"num_tokens": 27295529.0,
|
|
"step": 14835
|
|
},
|
|
{
|
|
"entropy": 5.310514068603515,
|
|
"epoch": 1.239558970932175,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00048508047936467907,
|
|
"loss": 4.9502,
|
|
"mean_token_accuracy": 0.21269596815109254,
|
|
"num_tokens": 27305358.0,
|
|
"step": 14840
|
|
},
|
|
{
|
|
"entropy": 5.237136363983154,
|
|
"epoch": 1.239976612094888,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00048506981750085914,
|
|
"loss": 4.7765,
|
|
"mean_token_accuracy": 0.2210938185453415,
|
|
"num_tokens": 27314765.0,
|
|
"step": 14845
|
|
},
|
|
{
|
|
"entropy": 5.303550910949707,
|
|
"epoch": 1.240394253257601,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00048505915195951423,
|
|
"loss": 4.8592,
|
|
"mean_token_accuracy": 0.2133936420083046,
|
|
"num_tokens": 27324227.0,
|
|
"step": 14850
|
|
},
|
|
{
|
|
"entropy": 5.3168079376220705,
|
|
"epoch": 1.2408118944203141,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00048504848274083095,
|
|
"loss": 4.8733,
|
|
"mean_token_accuracy": 0.21224427223205566,
|
|
"num_tokens": 27332890.0,
|
|
"step": 14855
|
|
},
|
|
{
|
|
"entropy": 5.24479079246521,
|
|
"epoch": 1.241229535583027,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00048503780984499625,
|
|
"loss": 4.7945,
|
|
"mean_token_accuracy": 0.2262277141213417,
|
|
"num_tokens": 27342411.0,
|
|
"step": 14860
|
|
},
|
|
{
|
|
"entropy": 5.2461936473846436,
|
|
"epoch": 1.24164717674574,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004850271332721968,
|
|
"loss": 4.8441,
|
|
"mean_token_accuracy": 0.21478026509284973,
|
|
"num_tokens": 27351649.0,
|
|
"step": 14865
|
|
},
|
|
{
|
|
"entropy": 5.240424680709839,
|
|
"epoch": 1.242064817908453,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004850164530226196,
|
|
"loss": 4.7736,
|
|
"mean_token_accuracy": 0.2206332266330719,
|
|
"num_tokens": 27360093.0,
|
|
"step": 14870
|
|
},
|
|
{
|
|
"entropy": 5.229906320571899,
|
|
"epoch": 1.242482459071166,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004850057690964515,
|
|
"loss": 4.795,
|
|
"mean_token_accuracy": 0.2174660637974739,
|
|
"num_tokens": 27368593.0,
|
|
"step": 14875
|
|
},
|
|
{
|
|
"entropy": 5.255605220794678,
|
|
"epoch": 1.242900100233879,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00048499508149387973,
|
|
"loss": 4.8931,
|
|
"mean_token_accuracy": 0.20609840154647827,
|
|
"num_tokens": 27378126.0,
|
|
"step": 14880
|
|
},
|
|
{
|
|
"entropy": 5.239598178863526,
|
|
"epoch": 1.2433177413965921,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00048498439021509124,
|
|
"loss": 4.747,
|
|
"mean_token_accuracy": 0.21923812180757524,
|
|
"num_tokens": 27386225.0,
|
|
"step": 14885
|
|
},
|
|
{
|
|
"entropy": 5.294436407089234,
|
|
"epoch": 1.2437353825593052,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004849736952602732,
|
|
"loss": 4.8822,
|
|
"mean_token_accuracy": 0.21322987079620362,
|
|
"num_tokens": 27395629.0,
|
|
"step": 14890
|
|
},
|
|
{
|
|
"entropy": 5.2865002155303955,
|
|
"epoch": 1.244153023722018,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000484962996629613,
|
|
"loss": 4.8854,
|
|
"mean_token_accuracy": 0.22254017740488052,
|
|
"num_tokens": 27404431.0,
|
|
"step": 14895
|
|
},
|
|
{
|
|
"entropy": 5.259862899780273,
|
|
"epoch": 1.244570664884731,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00048495229432329775,
|
|
"loss": 4.8813,
|
|
"mean_token_accuracy": 0.21834188252687453,
|
|
"num_tokens": 27412944.0,
|
|
"step": 14900
|
|
},
|
|
{
|
|
"entropy": 5.243988752365112,
|
|
"epoch": 1.244988306047444,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00048494158834151485,
|
|
"loss": 4.7938,
|
|
"mean_token_accuracy": 0.2166894182562828,
|
|
"num_tokens": 27422006.0,
|
|
"step": 14905
|
|
},
|
|
{
|
|
"entropy": 5.310099649429321,
|
|
"epoch": 1.245405947210157,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00048493087868445176,
|
|
"loss": 4.8866,
|
|
"mean_token_accuracy": 0.2199595957994461,
|
|
"num_tokens": 27431568.0,
|
|
"step": 14910
|
|
},
|
|
{
|
|
"entropy": 5.301585531234741,
|
|
"epoch": 1.24582358837287,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00048492016535229594,
|
|
"loss": 4.8367,
|
|
"mean_token_accuracy": 0.2171729251742363,
|
|
"num_tokens": 27440471.0,
|
|
"step": 14915
|
|
},
|
|
{
|
|
"entropy": 5.203983783721924,
|
|
"epoch": 1.246241229535583,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004849094483452349,
|
|
"loss": 4.7855,
|
|
"mean_token_accuracy": 0.22085929960012435,
|
|
"num_tokens": 27450209.0,
|
|
"step": 14920
|
|
},
|
|
{
|
|
"entropy": 5.317007064819336,
|
|
"epoch": 1.246658870698296,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004848987276634564,
|
|
"loss": 4.9862,
|
|
"mean_token_accuracy": 0.20518159568309785,
|
|
"num_tokens": 27458876.0,
|
|
"step": 14925
|
|
},
|
|
{
|
|
"entropy": 5.336245584487915,
|
|
"epoch": 1.247076511861009,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00048488800330714795,
|
|
"loss": 4.9053,
|
|
"mean_token_accuracy": 0.21860934644937516,
|
|
"num_tokens": 27467526.0,
|
|
"step": 14930
|
|
},
|
|
{
|
|
"entropy": 5.256207227706909,
|
|
"epoch": 1.247494153023722,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00048487727527649733,
|
|
"loss": 4.7824,
|
|
"mean_token_accuracy": 0.21915097832679747,
|
|
"num_tokens": 27477063.0,
|
|
"step": 14935
|
|
},
|
|
{
|
|
"entropy": 5.260677099227905,
|
|
"epoch": 1.247911794186435,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00048486654357169246,
|
|
"loss": 4.8983,
|
|
"mean_token_accuracy": 0.2150811016559601,
|
|
"num_tokens": 27486243.0,
|
|
"step": 14940
|
|
},
|
|
{
|
|
"entropy": 5.286910438537598,
|
|
"epoch": 1.248329435349148,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004848558081929211,
|
|
"loss": 4.8885,
|
|
"mean_token_accuracy": 0.21131252646446227,
|
|
"num_tokens": 27495491.0,
|
|
"step": 14945
|
|
},
|
|
{
|
|
"entropy": 5.26129560470581,
|
|
"epoch": 1.2487470765118611,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004848450691403712,
|
|
"loss": 4.8737,
|
|
"mean_token_accuracy": 0.21263331323862075,
|
|
"num_tokens": 27505105.0,
|
|
"step": 14950
|
|
},
|
|
{
|
|
"entropy": 5.214673757553101,
|
|
"epoch": 1.249164717674574,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004848343264142307,
|
|
"loss": 4.8009,
|
|
"mean_token_accuracy": 0.2183808669447899,
|
|
"num_tokens": 27514457.0,
|
|
"step": 14955
|
|
},
|
|
{
|
|
"entropy": 5.300758361816406,
|
|
"epoch": 1.249582358837287,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004848235800146879,
|
|
"loss": 4.9637,
|
|
"mean_token_accuracy": 0.21082535684108733,
|
|
"num_tokens": 27524073.0,
|
|
"step": 14960
|
|
},
|
|
{
|
|
"entropy": 5.280302095413208,
|
|
"epoch": 1.25,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004848128299419306,
|
|
"loss": 4.8219,
|
|
"mean_token_accuracy": 0.21599761694669722,
|
|
"num_tokens": 27532840.0,
|
|
"step": 14965
|
|
},
|
|
{
|
|
"entropy": 5.308600997924804,
|
|
"epoch": 1.250417641162713,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00048480207619614726,
|
|
"loss": 4.9336,
|
|
"mean_token_accuracy": 0.21012318581342698,
|
|
"num_tokens": 27541775.0,
|
|
"step": 14970
|
|
},
|
|
{
|
|
"entropy": 5.282397794723511,
|
|
"epoch": 1.250835282325426,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000484791318777526,
|
|
"loss": 4.8543,
|
|
"mean_token_accuracy": 0.21930092424154282,
|
|
"num_tokens": 27550668.0,
|
|
"step": 14975
|
|
},
|
|
{
|
|
"entropy": 5.289754056930542,
|
|
"epoch": 1.2512529234881389,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00048478055768625517,
|
|
"loss": 4.8912,
|
|
"mean_token_accuracy": 0.2130553811788559,
|
|
"num_tokens": 27560255.0,
|
|
"step": 14980
|
|
},
|
|
{
|
|
"entropy": 5.172748279571533,
|
|
"epoch": 1.251670564650852,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00048476979292252323,
|
|
"loss": 4.8297,
|
|
"mean_token_accuracy": 0.21807315349578857,
|
|
"num_tokens": 27569028.0,
|
|
"step": 14985
|
|
},
|
|
{
|
|
"entropy": 5.2405811786651615,
|
|
"epoch": 1.252088205813565,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004847590244865185,
|
|
"loss": 4.7564,
|
|
"mean_token_accuracy": 0.2257744014263153,
|
|
"num_tokens": 27577396.0,
|
|
"step": 14990
|
|
},
|
|
{
|
|
"entropy": 5.28857388496399,
|
|
"epoch": 1.252505846976278,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00048474825237842964,
|
|
"loss": 4.9182,
|
|
"mean_token_accuracy": 0.20821880251169206,
|
|
"num_tokens": 27586710.0,
|
|
"step": 14995
|
|
},
|
|
{
|
|
"entropy": 5.1709624290466305,
|
|
"epoch": 1.252923488138991,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000484737476598445,
|
|
"loss": 4.7593,
|
|
"mean_token_accuracy": 0.22051508724689484,
|
|
"num_tokens": 27594842.0,
|
|
"step": 15000
|
|
},
|
|
{
|
|
"epoch": 1.252923488138991,
|
|
"eval_entropy": 4.961925816066284,
|
|
"eval_loss": 4.875884532928467,
|
|
"eval_mean_token_accuracy": 0.22639884216897543,
|
|
"eval_num_tokens": 27594842.0,
|
|
"eval_runtime": 20.8467,
|
|
"eval_samples_per_second": 1811.461,
|
|
"eval_steps_per_second": 226.463,
|
|
"step": 15000
|
|
},
|
|
{
|
|
"entropy": 5.145755290985107,
|
|
"epoch": 1.253341129301704,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00048472669714675357,
|
|
"loss": 4.7607,
|
|
"mean_token_accuracy": 0.2200940802693367,
|
|
"num_tokens": 27604661.0,
|
|
"step": 15005
|
|
},
|
|
{
|
|
"entropy": 5.210931205749512,
|
|
"epoch": 1.253758770464417,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00048471591402354374,
|
|
"loss": 4.7185,
|
|
"mean_token_accuracy": 0.2297748565673828,
|
|
"num_tokens": 27614015.0,
|
|
"step": 15010
|
|
},
|
|
{
|
|
"entropy": 5.315606117248535,
|
|
"epoch": 1.25417641162713,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00048470512722900434,
|
|
"loss": 4.953,
|
|
"mean_token_accuracy": 0.20646064579486847,
|
|
"num_tokens": 27624164.0,
|
|
"step": 15015
|
|
},
|
|
{
|
|
"entropy": 5.242456340789795,
|
|
"epoch": 1.254594052789843,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00048469433676332434,
|
|
"loss": 4.8239,
|
|
"mean_token_accuracy": 0.22573086321353913,
|
|
"num_tokens": 27633993.0,
|
|
"step": 15020
|
|
},
|
|
{
|
|
"entropy": 5.229936361312866,
|
|
"epoch": 1.255011693952556,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004846835426266926,
|
|
"loss": 4.8853,
|
|
"mean_token_accuracy": 0.21468566954135895,
|
|
"num_tokens": 27643772.0,
|
|
"step": 15025
|
|
},
|
|
{
|
|
"entropy": 5.263743209838867,
|
|
"epoch": 1.255429335115269,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004846727448192981,
|
|
"loss": 4.7756,
|
|
"mean_token_accuracy": 0.21965271681547166,
|
|
"num_tokens": 27652511.0,
|
|
"step": 15030
|
|
},
|
|
{
|
|
"entropy": 5.246355962753296,
|
|
"epoch": 1.255846976277982,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00048466194334132964,
|
|
"loss": 4.7631,
|
|
"mean_token_accuracy": 0.21957619488239288,
|
|
"num_tokens": 27661589.0,
|
|
"step": 15035
|
|
},
|
|
{
|
|
"entropy": 5.211206769943237,
|
|
"epoch": 1.2562646174406948,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00048465113819297654,
|
|
"loss": 4.8593,
|
|
"mean_token_accuracy": 0.21720261871814728,
|
|
"num_tokens": 27670299.0,
|
|
"step": 15040
|
|
},
|
|
{
|
|
"entropy": 5.334532356262207,
|
|
"epoch": 1.2566822586034079,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000484640329374428,
|
|
"loss": 4.9568,
|
|
"mean_token_accuracy": 0.2091383770108223,
|
|
"num_tokens": 27679375.0,
|
|
"step": 15045
|
|
},
|
|
{
|
|
"entropy": 5.2319056510925295,
|
|
"epoch": 1.257099899766121,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00048462951688587317,
|
|
"loss": 4.8252,
|
|
"mean_token_accuracy": 0.23035387843847274,
|
|
"num_tokens": 27688754.0,
|
|
"step": 15050
|
|
},
|
|
{
|
|
"entropy": 5.212550067901612,
|
|
"epoch": 1.257517540928834,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00048461870072750117,
|
|
"loss": 4.8479,
|
|
"mean_token_accuracy": 0.21162332743406295,
|
|
"num_tokens": 27697799.0,
|
|
"step": 15055
|
|
},
|
|
{
|
|
"entropy": 5.252862167358399,
|
|
"epoch": 1.257935182091547,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00048460788089950164,
|
|
"loss": 4.7718,
|
|
"mean_token_accuracy": 0.22318474501371383,
|
|
"num_tokens": 27707239.0,
|
|
"step": 15060
|
|
},
|
|
{
|
|
"entropy": 5.2663429260253904,
|
|
"epoch": 1.25835282325426,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004845970574020637,
|
|
"loss": 4.8105,
|
|
"mean_token_accuracy": 0.21643730700016023,
|
|
"num_tokens": 27716027.0,
|
|
"step": 15065
|
|
},
|
|
{
|
|
"entropy": 5.230315828323365,
|
|
"epoch": 1.258770464416973,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004845862302353771,
|
|
"loss": 4.7171,
|
|
"mean_token_accuracy": 0.23440393209457397,
|
|
"num_tokens": 27724849.0,
|
|
"step": 15070
|
|
},
|
|
{
|
|
"entropy": 5.2138587474823,
|
|
"epoch": 1.2591881055796859,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00048457539939963126,
|
|
"loss": 4.7463,
|
|
"mean_token_accuracy": 0.222755828499794,
|
|
"num_tokens": 27733899.0,
|
|
"step": 15075
|
|
},
|
|
{
|
|
"entropy": 5.233987617492676,
|
|
"epoch": 1.259605746742399,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00048456456489501574,
|
|
"loss": 4.8903,
|
|
"mean_token_accuracy": 0.21611734628677368,
|
|
"num_tokens": 27743967.0,
|
|
"step": 15080
|
|
},
|
|
{
|
|
"entropy": 5.256052827835083,
|
|
"epoch": 1.260023387905112,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004845537267217202,
|
|
"loss": 4.7943,
|
|
"mean_token_accuracy": 0.22089724093675614,
|
|
"num_tokens": 27753105.0,
|
|
"step": 15085
|
|
},
|
|
{
|
|
"entropy": 5.303727531433106,
|
|
"epoch": 1.260441029067825,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004845428848799346,
|
|
"loss": 4.909,
|
|
"mean_token_accuracy": 0.21670802384614946,
|
|
"num_tokens": 27762771.0,
|
|
"step": 15090
|
|
},
|
|
{
|
|
"entropy": 5.224437236785889,
|
|
"epoch": 1.260858670230538,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004845320393698484,
|
|
"loss": 4.7986,
|
|
"mean_token_accuracy": 0.2257997214794159,
|
|
"num_tokens": 27771653.0,
|
|
"step": 15095
|
|
},
|
|
{
|
|
"entropy": 5.240845346450806,
|
|
"epoch": 1.2612763113932508,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004845211901916517,
|
|
"loss": 4.8696,
|
|
"mean_token_accuracy": 0.2161788150668144,
|
|
"num_tokens": 27780585.0,
|
|
"step": 15100
|
|
},
|
|
{
|
|
"entropy": 5.2163393020629885,
|
|
"epoch": 1.2616939525559638,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00048451033734553444,
|
|
"loss": 4.7983,
|
|
"mean_token_accuracy": 0.21700193136930465,
|
|
"num_tokens": 27790625.0,
|
|
"step": 15105
|
|
},
|
|
{
|
|
"entropy": 5.43286099433899,
|
|
"epoch": 1.2621115937186769,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004844994808316864,
|
|
"loss": 5.0641,
|
|
"mean_token_accuracy": 0.20535253286361693,
|
|
"num_tokens": 27800948.0,
|
|
"step": 15110
|
|
},
|
|
{
|
|
"entropy": 5.340651988983154,
|
|
"epoch": 1.26252923488139,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004844886206502979,
|
|
"loss": 4.9404,
|
|
"mean_token_accuracy": 0.21379165649414061,
|
|
"num_tokens": 27809973.0,
|
|
"step": 15115
|
|
},
|
|
{
|
|
"entropy": 5.313256502151489,
|
|
"epoch": 1.262946876044103,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00048447775680155884,
|
|
"loss": 4.8509,
|
|
"mean_token_accuracy": 0.21188030242919922,
|
|
"num_tokens": 27818738.0,
|
|
"step": 15120
|
|
},
|
|
{
|
|
"entropy": 5.220182847976685,
|
|
"epoch": 1.263364517206816,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00048446688928565956,
|
|
"loss": 4.8401,
|
|
"mean_token_accuracy": 0.22398236840963365,
|
|
"num_tokens": 27827537.0,
|
|
"step": 15125
|
|
},
|
|
{
|
|
"entropy": 5.395980167388916,
|
|
"epoch": 1.263782158369529,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004844560181027903,
|
|
"loss": 4.9908,
|
|
"mean_token_accuracy": 0.20308305323123932,
|
|
"num_tokens": 27837498.0,
|
|
"step": 15130
|
|
},
|
|
{
|
|
"entropy": 5.314039468765259,
|
|
"epoch": 1.2641997995322418,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004844451432531412,
|
|
"loss": 4.8853,
|
|
"mean_token_accuracy": 0.2117501065135002,
|
|
"num_tokens": 27847547.0,
|
|
"step": 15135
|
|
},
|
|
{
|
|
"entropy": 5.271157169342041,
|
|
"epoch": 1.2646174406949549,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004844342647369028,
|
|
"loss": 4.8223,
|
|
"mean_token_accuracy": 0.21918607801198958,
|
|
"num_tokens": 27856468.0,
|
|
"step": 15140
|
|
},
|
|
{
|
|
"entropy": 5.31744532585144,
|
|
"epoch": 1.2650350818576679,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00048442338255426555,
|
|
"loss": 4.9807,
|
|
"mean_token_accuracy": 0.21429909765720367,
|
|
"num_tokens": 27865324.0,
|
|
"step": 15145
|
|
},
|
|
{
|
|
"entropy": 5.246741390228271,
|
|
"epoch": 1.265452723020381,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004844124967054199,
|
|
"loss": 4.8632,
|
|
"mean_token_accuracy": 0.21414963006973267,
|
|
"num_tokens": 27875364.0,
|
|
"step": 15150
|
|
},
|
|
{
|
|
"entropy": 5.320226669311523,
|
|
"epoch": 1.265870364183094,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004844016071905564,
|
|
"loss": 4.8166,
|
|
"mean_token_accuracy": 0.2274008184671402,
|
|
"num_tokens": 27884739.0,
|
|
"step": 15155
|
|
},
|
|
{
|
|
"entropy": 5.172783756256104,
|
|
"epoch": 1.2662880053458068,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004843907140098656,
|
|
"loss": 4.7209,
|
|
"mean_token_accuracy": 0.23128895610570907,
|
|
"num_tokens": 27893235.0,
|
|
"step": 15160
|
|
},
|
|
{
|
|
"entropy": 5.2243156909942625,
|
|
"epoch": 1.2667056465085198,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004843798171635384,
|
|
"loss": 4.8735,
|
|
"mean_token_accuracy": 0.21752613186836242,
|
|
"num_tokens": 27902090.0,
|
|
"step": 15165
|
|
},
|
|
{
|
|
"entropy": 5.2981343269348145,
|
|
"epoch": 1.2671232876712328,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004843689166517655,
|
|
"loss": 4.8199,
|
|
"mean_token_accuracy": 0.2166404440999031,
|
|
"num_tokens": 27910702.0,
|
|
"step": 15170
|
|
},
|
|
{
|
|
"entropy": 5.308234977722168,
|
|
"epoch": 1.2675409288339459,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004843580124747377,
|
|
"loss": 4.852,
|
|
"mean_token_accuracy": 0.21816705763339997,
|
|
"num_tokens": 27919296.0,
|
|
"step": 15175
|
|
},
|
|
{
|
|
"entropy": 5.256859207153321,
|
|
"epoch": 1.267958569996659,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00048434710463264585,
|
|
"loss": 4.8452,
|
|
"mean_token_accuracy": 0.2225697562098503,
|
|
"num_tokens": 27929074.0,
|
|
"step": 15180
|
|
},
|
|
{
|
|
"entropy": 5.3055823802947994,
|
|
"epoch": 1.268376211159372,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00048433619312568095,
|
|
"loss": 4.9076,
|
|
"mean_token_accuracy": 0.21200886219739914,
|
|
"num_tokens": 27938227.0,
|
|
"step": 15185
|
|
},
|
|
{
|
|
"entropy": 5.329960346221924,
|
|
"epoch": 1.268793852322085,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00048432527795403405,
|
|
"loss": 4.9097,
|
|
"mean_token_accuracy": 0.208456389605999,
|
|
"num_tokens": 27948050.0,
|
|
"step": 15190
|
|
},
|
|
{
|
|
"entropy": 5.304529619216919,
|
|
"epoch": 1.2692114934847978,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004843143591178962,
|
|
"loss": 4.7961,
|
|
"mean_token_accuracy": 0.2142339214682579,
|
|
"num_tokens": 27957702.0,
|
|
"step": 15195
|
|
},
|
|
{
|
|
"entropy": 5.375745820999145,
|
|
"epoch": 1.2696291346475108,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00048430343661745844,
|
|
"loss": 4.9487,
|
|
"mean_token_accuracy": 0.2040387436747551,
|
|
"num_tokens": 27966085.0,
|
|
"step": 15200
|
|
},
|
|
{
|
|
"entropy": 5.345520496368408,
|
|
"epoch": 1.2700467758102238,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004842925104529122,
|
|
"loss": 4.9192,
|
|
"mean_token_accuracy": 0.20843733847141266,
|
|
"num_tokens": 27976228.0,
|
|
"step": 15205
|
|
},
|
|
{
|
|
"entropy": 5.295340919494629,
|
|
"epoch": 1.2704644169729369,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00048428158062444857,
|
|
"loss": 4.8562,
|
|
"mean_token_accuracy": 0.2207759514451027,
|
|
"num_tokens": 27984910.0,
|
|
"step": 15210
|
|
},
|
|
{
|
|
"entropy": 5.273421764373779,
|
|
"epoch": 1.27088205813565,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00048427064713225894,
|
|
"loss": 4.8314,
|
|
"mean_token_accuracy": 0.21481223851442338,
|
|
"num_tokens": 27993767.0,
|
|
"step": 15215
|
|
},
|
|
{
|
|
"entropy": 5.28258752822876,
|
|
"epoch": 1.2712996992983627,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00048425970997653477,
|
|
"loss": 4.8643,
|
|
"mean_token_accuracy": 0.21814547777175902,
|
|
"num_tokens": 28002587.0,
|
|
"step": 15220
|
|
},
|
|
{
|
|
"entropy": 5.308236408233642,
|
|
"epoch": 1.2717173404610758,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004842487691574675,
|
|
"loss": 4.9035,
|
|
"mean_token_accuracy": 0.21116955876350402,
|
|
"num_tokens": 28011598.0,
|
|
"step": 15225
|
|
},
|
|
{
|
|
"entropy": 5.33001070022583,
|
|
"epoch": 1.2721349816237888,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00048423782467524865,
|
|
"loss": 4.9689,
|
|
"mean_token_accuracy": 0.21540127098560333,
|
|
"num_tokens": 28021321.0,
|
|
"step": 15230
|
|
},
|
|
{
|
|
"entropy": 5.310712194442749,
|
|
"epoch": 1.2725526227865018,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004842268765300698,
|
|
"loss": 4.8794,
|
|
"mean_token_accuracy": 0.21921148598194123,
|
|
"num_tokens": 28031009.0,
|
|
"step": 15235
|
|
},
|
|
{
|
|
"entropy": 5.352626752853394,
|
|
"epoch": 1.2729702639492149,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00048421592472212263,
|
|
"loss": 4.9371,
|
|
"mean_token_accuracy": 0.2065187245607376,
|
|
"num_tokens": 28040330.0,
|
|
"step": 15240
|
|
},
|
|
{
|
|
"entropy": 5.284771966934204,
|
|
"epoch": 1.273387905111928,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00048420496925159886,
|
|
"loss": 4.8668,
|
|
"mean_token_accuracy": 0.21271237283945083,
|
|
"num_tokens": 28048952.0,
|
|
"step": 15245
|
|
},
|
|
{
|
|
"entropy": 5.262752342224121,
|
|
"epoch": 1.273805546274641,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004841940101186903,
|
|
"loss": 4.8548,
|
|
"mean_token_accuracy": 0.2086240157485008,
|
|
"num_tokens": 28058803.0,
|
|
"step": 15250
|
|
},
|
|
{
|
|
"entropy": 5.339647483825684,
|
|
"epoch": 1.2742231874373537,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004841830473235888,
|
|
"loss": 4.8383,
|
|
"mean_token_accuracy": 0.22429825067520143,
|
|
"num_tokens": 28067978.0,
|
|
"step": 15255
|
|
},
|
|
{
|
|
"entropy": 5.192608785629273,
|
|
"epoch": 1.2746408286000668,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00048417208086648625,
|
|
"loss": 4.8085,
|
|
"mean_token_accuracy": 0.22202841490507125,
|
|
"num_tokens": 28077229.0,
|
|
"step": 15260
|
|
},
|
|
{
|
|
"entropy": 5.260610342025757,
|
|
"epoch": 1.2750584697627798,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004841611107475746,
|
|
"loss": 4.8597,
|
|
"mean_token_accuracy": 0.21530555784702302,
|
|
"num_tokens": 28086316.0,
|
|
"step": 15265
|
|
},
|
|
{
|
|
"entropy": 5.4461321353912355,
|
|
"epoch": 1.2754761109254928,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000484150136967046,
|
|
"loss": 5.0272,
|
|
"mean_token_accuracy": 0.20625730752944946,
|
|
"num_tokens": 28096914.0,
|
|
"step": 15270
|
|
},
|
|
{
|
|
"entropy": 5.341934871673584,
|
|
"epoch": 1.2758937520882059,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004841391595250925,
|
|
"loss": 4.9101,
|
|
"mean_token_accuracy": 0.2075797438621521,
|
|
"num_tokens": 28106532.0,
|
|
"step": 15275
|
|
},
|
|
{
|
|
"entropy": 5.304814767837525,
|
|
"epoch": 1.2763113932509187,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004841281784219063,
|
|
"loss": 4.8694,
|
|
"mean_token_accuracy": 0.21445009857416153,
|
|
"num_tokens": 28115052.0,
|
|
"step": 15280
|
|
},
|
|
{
|
|
"entropy": 5.26074252128601,
|
|
"epoch": 1.2767290344136317,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00048411719365767947,
|
|
"loss": 4.7975,
|
|
"mean_token_accuracy": 0.22511734515428544,
|
|
"num_tokens": 28123571.0,
|
|
"step": 15285
|
|
},
|
|
{
|
|
"entropy": 5.206147050857544,
|
|
"epoch": 1.2771466755763448,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00048410620523260455,
|
|
"loss": 4.7592,
|
|
"mean_token_accuracy": 0.22169163674116135,
|
|
"num_tokens": 28131973.0,
|
|
"step": 15290
|
|
},
|
|
{
|
|
"entropy": 5.344128131866455,
|
|
"epoch": 1.2775643167390578,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00048409521314687383,
|
|
"loss": 4.9583,
|
|
"mean_token_accuracy": 0.21140404045581818,
|
|
"num_tokens": 28140965.0,
|
|
"step": 15295
|
|
},
|
|
{
|
|
"entropy": 5.250276041030884,
|
|
"epoch": 1.2779819579017708,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004840842174006797,
|
|
"loss": 4.9245,
|
|
"mean_token_accuracy": 0.21635557115077972,
|
|
"num_tokens": 28150652.0,
|
|
"step": 15300
|
|
},
|
|
{
|
|
"entropy": 5.377749109268189,
|
|
"epoch": 1.2783995990644839,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004840732179942146,
|
|
"loss": 5.0893,
|
|
"mean_token_accuracy": 0.20001883804798126,
|
|
"num_tokens": 28160830.0,
|
|
"step": 15305
|
|
},
|
|
{
|
|
"entropy": 5.3474016189575195,
|
|
"epoch": 1.278817240227197,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004840622149276712,
|
|
"loss": 4.7298,
|
|
"mean_token_accuracy": 0.22234941273927689,
|
|
"num_tokens": 28169423.0,
|
|
"step": 15310
|
|
},
|
|
{
|
|
"entropy": 5.276772212982178,
|
|
"epoch": 1.2792348813899097,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004840512082012421,
|
|
"loss": 4.817,
|
|
"mean_token_accuracy": 0.21776615977287292,
|
|
"num_tokens": 28178997.0,
|
|
"step": 15315
|
|
},
|
|
{
|
|
"entropy": 5.288588190078736,
|
|
"epoch": 1.2796525225526227,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00048404019781511995,
|
|
"loss": 4.843,
|
|
"mean_token_accuracy": 0.21885486841201782,
|
|
"num_tokens": 28188014.0,
|
|
"step": 15320
|
|
},
|
|
{
|
|
"entropy": 5.300122547149658,
|
|
"epoch": 1.2800701637153358,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00048402918376949753,
|
|
"loss": 4.8969,
|
|
"mean_token_accuracy": 0.21078093945980073,
|
|
"num_tokens": 28197800.0,
|
|
"step": 15325
|
|
},
|
|
{
|
|
"entropy": 5.282825660705567,
|
|
"epoch": 1.2804878048780488,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004840181660645676,
|
|
"loss": 4.7921,
|
|
"mean_token_accuracy": 0.2264653667807579,
|
|
"num_tokens": 28207388.0,
|
|
"step": 15330
|
|
},
|
|
{
|
|
"entropy": 5.249730205535888,
|
|
"epoch": 1.2809054460407618,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004840071447005231,
|
|
"loss": 4.8677,
|
|
"mean_token_accuracy": 0.22007115930318832,
|
|
"num_tokens": 28216774.0,
|
|
"step": 15335
|
|
},
|
|
{
|
|
"entropy": 5.292992448806762,
|
|
"epoch": 1.2813230872034747,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000483996119677557,
|
|
"loss": 4.8704,
|
|
"mean_token_accuracy": 0.21966152787208557,
|
|
"num_tokens": 28226402.0,
|
|
"step": 15340
|
|
},
|
|
{
|
|
"entropy": 5.284866142272949,
|
|
"epoch": 1.281740728366188,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00048398509099586225,
|
|
"loss": 4.8768,
|
|
"mean_token_accuracy": 0.2132789671421051,
|
|
"num_tokens": 28235890.0,
|
|
"step": 15345
|
|
},
|
|
{
|
|
"entropy": 5.2649482727050785,
|
|
"epoch": 1.2821583695289007,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00048397405865563186,
|
|
"loss": 4.8346,
|
|
"mean_token_accuracy": 0.21988965272903443,
|
|
"num_tokens": 28244121.0,
|
|
"step": 15350
|
|
},
|
|
{
|
|
"entropy": 5.387158727645874,
|
|
"epoch": 1.2825760106916138,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004839630226570591,
|
|
"loss": 4.9146,
|
|
"mean_token_accuracy": 0.21749134957790375,
|
|
"num_tokens": 28252259.0,
|
|
"step": 15355
|
|
},
|
|
{
|
|
"entropy": 5.292307186126709,
|
|
"epoch": 1.2829936518543268,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000483951983000337,
|
|
"loss": 4.771,
|
|
"mean_token_accuracy": 0.22351538240909577,
|
|
"num_tokens": 28262199.0,
|
|
"step": 15360
|
|
},
|
|
{
|
|
"entropy": 5.317487668991089,
|
|
"epoch": 1.2834112930170398,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000483940939685659,
|
|
"loss": 4.8674,
|
|
"mean_token_accuracy": 0.21545404344797134,
|
|
"num_tokens": 28271120.0,
|
|
"step": 15365
|
|
},
|
|
{
|
|
"entropy": 5.302384757995606,
|
|
"epoch": 1.2838289341797529,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00048392989271321836,
|
|
"loss": 4.8387,
|
|
"mean_token_accuracy": 0.22113635540008544,
|
|
"num_tokens": 28279766.0,
|
|
"step": 15370
|
|
},
|
|
{
|
|
"entropy": 5.27904167175293,
|
|
"epoch": 1.2842465753424657,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004839188420832084,
|
|
"loss": 4.8427,
|
|
"mean_token_accuracy": 0.22217268943786622,
|
|
"num_tokens": 28288872.0,
|
|
"step": 15375
|
|
},
|
|
{
|
|
"entropy": 5.201871919631958,
|
|
"epoch": 1.2846642165051787,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00048390778779582266,
|
|
"loss": 4.8126,
|
|
"mean_token_accuracy": 0.21403192430734636,
|
|
"num_tokens": 28297719.0,
|
|
"step": 15380
|
|
},
|
|
{
|
|
"entropy": 5.301772356033325,
|
|
"epoch": 1.2850818576678917,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00048389672985125467,
|
|
"loss": 4.9031,
|
|
"mean_token_accuracy": 0.21022669076919556,
|
|
"num_tokens": 28306547.0,
|
|
"step": 15385
|
|
},
|
|
{
|
|
"entropy": 5.256704998016358,
|
|
"epoch": 1.2854994988306048,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004838856682496979,
|
|
"loss": 4.866,
|
|
"mean_token_accuracy": 0.21697429716587066,
|
|
"num_tokens": 28316387.0,
|
|
"step": 15390
|
|
},
|
|
{
|
|
"entropy": 5.341765022277832,
|
|
"epoch": 1.2859171399933178,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004838746029913461,
|
|
"loss": 4.9162,
|
|
"mean_token_accuracy": 0.20670831352472305,
|
|
"num_tokens": 28326642.0,
|
|
"step": 15395
|
|
},
|
|
{
|
|
"entropy": 5.283965015411377,
|
|
"epoch": 1.2863347811560306,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000483863534076393,
|
|
"loss": 4.8156,
|
|
"mean_token_accuracy": 0.22137012034654618,
|
|
"num_tokens": 28335647.0,
|
|
"step": 15400
|
|
},
|
|
{
|
|
"entropy": 5.2389274597167965,
|
|
"epoch": 1.2867524223187439,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004838524615050323,
|
|
"loss": 4.8523,
|
|
"mean_token_accuracy": 0.21446475237607956,
|
|
"num_tokens": 28344536.0,
|
|
"step": 15405
|
|
},
|
|
{
|
|
"entropy": 5.30611023902893,
|
|
"epoch": 1.2871700634814567,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004838413852774579,
|
|
"loss": 4.8773,
|
|
"mean_token_accuracy": 0.21219469904899596,
|
|
"num_tokens": 28354121.0,
|
|
"step": 15410
|
|
},
|
|
{
|
|
"entropy": 5.228492593765258,
|
|
"epoch": 1.2875877046441697,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00048383030539386355,
|
|
"loss": 4.8189,
|
|
"mean_token_accuracy": 0.22949260324239731,
|
|
"num_tokens": 28362215.0,
|
|
"step": 15415
|
|
},
|
|
{
|
|
"entropy": 5.320909023284912,
|
|
"epoch": 1.2880053458068828,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004838192218544434,
|
|
"loss": 4.8756,
|
|
"mean_token_accuracy": 0.2177065834403038,
|
|
"num_tokens": 28371323.0,
|
|
"step": 15420
|
|
},
|
|
{
|
|
"entropy": 5.387678718566894,
|
|
"epoch": 1.2884229869695958,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004838081346593915,
|
|
"loss": 4.9457,
|
|
"mean_token_accuracy": 0.2074352979660034,
|
|
"num_tokens": 28380333.0,
|
|
"step": 15425
|
|
},
|
|
{
|
|
"entropy": 5.257230043411255,
|
|
"epoch": 1.2888406281323088,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00048379704380890177,
|
|
"loss": 4.8554,
|
|
"mean_token_accuracy": 0.20955758392810822,
|
|
"num_tokens": 28389021.0,
|
|
"step": 15430
|
|
},
|
|
{
|
|
"entropy": 5.204346609115601,
|
|
"epoch": 1.2892582692950216,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004837859493031685,
|
|
"loss": 4.7882,
|
|
"mean_token_accuracy": 0.21130102425813674,
|
|
"num_tokens": 28398309.0,
|
|
"step": 15435
|
|
},
|
|
{
|
|
"entropy": 5.186147689819336,
|
|
"epoch": 1.2896759104577347,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00048377485114238576,
|
|
"loss": 4.6964,
|
|
"mean_token_accuracy": 0.22528516501188278,
|
|
"num_tokens": 28406946.0,
|
|
"step": 15440
|
|
},
|
|
{
|
|
"entropy": 5.265906572341919,
|
|
"epoch": 1.2900935516204477,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004837637493267481,
|
|
"loss": 4.8506,
|
|
"mean_token_accuracy": 0.2208574116230011,
|
|
"num_tokens": 28416561.0,
|
|
"step": 15445
|
|
},
|
|
{
|
|
"entropy": 5.278252077102661,
|
|
"epoch": 1.2905111927831607,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004837526438564496,
|
|
"loss": 4.7051,
|
|
"mean_token_accuracy": 0.2380034625530243,
|
|
"num_tokens": 28425133.0,
|
|
"step": 15450
|
|
},
|
|
{
|
|
"entropy": 5.2680027961730955,
|
|
"epoch": 1.2909288339458738,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004837415347316849,
|
|
"loss": 4.9093,
|
|
"mean_token_accuracy": 0.207238133251667,
|
|
"num_tokens": 28434282.0,
|
|
"step": 15455
|
|
},
|
|
{
|
|
"entropy": 5.286457347869873,
|
|
"epoch": 1.2913464751085866,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00048373042195264836,
|
|
"loss": 4.9071,
|
|
"mean_token_accuracy": 0.20837466269731522,
|
|
"num_tokens": 28443149.0,
|
|
"step": 15460
|
|
},
|
|
{
|
|
"entropy": 5.349145030975341,
|
|
"epoch": 1.2917641162712998,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004837193055195344,
|
|
"loss": 4.9478,
|
|
"mean_token_accuracy": 0.20793576240539552,
|
|
"num_tokens": 28453294.0,
|
|
"step": 15465
|
|
},
|
|
{
|
|
"entropy": 5.291328287124633,
|
|
"epoch": 1.2921817574340126,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00048370818543253793,
|
|
"loss": 4.7915,
|
|
"mean_token_accuracy": 0.2257762521505356,
|
|
"num_tokens": 28462518.0,
|
|
"step": 15470
|
|
},
|
|
{
|
|
"entropy": 5.2728949069976805,
|
|
"epoch": 1.2925993985967257,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00048369706169185334,
|
|
"loss": 4.8855,
|
|
"mean_token_accuracy": 0.21418222188949584,
|
|
"num_tokens": 28470674.0,
|
|
"step": 15475
|
|
},
|
|
{
|
|
"entropy": 5.273687839508057,
|
|
"epoch": 1.2930170397594387,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00048368593429767555,
|
|
"loss": 4.8869,
|
|
"mean_token_accuracy": 0.2157193273305893,
|
|
"num_tokens": 28480088.0,
|
|
"step": 15480
|
|
},
|
|
{
|
|
"entropy": 5.350749492645264,
|
|
"epoch": 1.2934346809221517,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00048367480325019923,
|
|
"loss": 4.9241,
|
|
"mean_token_accuracy": 0.2121589943766594,
|
|
"num_tokens": 28489533.0,
|
|
"step": 15485
|
|
},
|
|
{
|
|
"entropy": 5.344649839401245,
|
|
"epoch": 1.2938523220848648,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00048366366854961937,
|
|
"loss": 4.8848,
|
|
"mean_token_accuracy": 0.20964589715003967,
|
|
"num_tokens": 28498758.0,
|
|
"step": 15490
|
|
},
|
|
{
|
|
"entropy": 5.233841848373413,
|
|
"epoch": 1.2942699632475776,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004836525301961307,
|
|
"loss": 4.8299,
|
|
"mean_token_accuracy": 0.21798497438430786,
|
|
"num_tokens": 28507633.0,
|
|
"step": 15495
|
|
},
|
|
{
|
|
"entropy": 5.223841571807862,
|
|
"epoch": 1.2946876044102906,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004836413881899285,
|
|
"loss": 4.8183,
|
|
"mean_token_accuracy": 0.21691786050796508,
|
|
"num_tokens": 28516905.0,
|
|
"step": 15500
|
|
},
|
|
{
|
|
"entropy": 5.34234356880188,
|
|
"epoch": 1.2951052455730037,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004836302425312075,
|
|
"loss": 4.9414,
|
|
"mean_token_accuracy": 0.20925931334495546,
|
|
"num_tokens": 28527419.0,
|
|
"step": 15505
|
|
},
|
|
{
|
|
"entropy": 5.205329513549804,
|
|
"epoch": 1.2955228867357167,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004836190932201631,
|
|
"loss": 4.7007,
|
|
"mean_token_accuracy": 0.22691429704427718,
|
|
"num_tokens": 28535950.0,
|
|
"step": 15510
|
|
},
|
|
{
|
|
"entropy": 5.271174430847168,
|
|
"epoch": 1.2959405278984297,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00048360794025699026,
|
|
"loss": 4.8009,
|
|
"mean_token_accuracy": 0.22417024224996568,
|
|
"num_tokens": 28544341.0,
|
|
"step": 15515
|
|
},
|
|
{
|
|
"entropy": 5.330448341369629,
|
|
"epoch": 1.2963581690611425,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004835967836418844,
|
|
"loss": 4.8962,
|
|
"mean_token_accuracy": 0.21641915589570998,
|
|
"num_tokens": 28553805.0,
|
|
"step": 15520
|
|
},
|
|
{
|
|
"entropy": 5.309712839126587,
|
|
"epoch": 1.2967758102238558,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004835856233750407,
|
|
"loss": 4.7934,
|
|
"mean_token_accuracy": 0.21735316067934035,
|
|
"num_tokens": 28562224.0,
|
|
"step": 15525
|
|
},
|
|
{
|
|
"entropy": 5.218863821029663,
|
|
"epoch": 1.2971934513865686,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00048357445945665465,
|
|
"loss": 4.7412,
|
|
"mean_token_accuracy": 0.2221486896276474,
|
|
"num_tokens": 28570771.0,
|
|
"step": 15530
|
|
},
|
|
{
|
|
"entropy": 5.280960178375244,
|
|
"epoch": 1.2976110925492816,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004835632918869215,
|
|
"loss": 4.9421,
|
|
"mean_token_accuracy": 0.21097290217876435,
|
|
"num_tokens": 28580447.0,
|
|
"step": 15535
|
|
},
|
|
{
|
|
"entropy": 5.38236174583435,
|
|
"epoch": 1.2980287337119947,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000483552120666037,
|
|
"loss": 4.9862,
|
|
"mean_token_accuracy": 0.21461764723062515,
|
|
"num_tokens": 28590472.0,
|
|
"step": 15540
|
|
},
|
|
{
|
|
"entropy": 5.3074061393737795,
|
|
"epoch": 1.2984463748747077,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00048354094579419656,
|
|
"loss": 4.8294,
|
|
"mean_token_accuracy": 0.21760340929031372,
|
|
"num_tokens": 28599201.0,
|
|
"step": 15545
|
|
},
|
|
{
|
|
"entropy": 5.232780265808105,
|
|
"epoch": 1.2988640160374207,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004835297672715958,
|
|
"loss": 4.8755,
|
|
"mean_token_accuracy": 0.21118227243423462,
|
|
"num_tokens": 28608499.0,
|
|
"step": 15550
|
|
},
|
|
{
|
|
"entropy": 5.267165946960449,
|
|
"epoch": 1.2992816572001336,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00048351858509843054,
|
|
"loss": 4.8304,
|
|
"mean_token_accuracy": 0.22272368669509887,
|
|
"num_tokens": 28618310.0,
|
|
"step": 15555
|
|
},
|
|
{
|
|
"entropy": 5.351817178726196,
|
|
"epoch": 1.2996992983628466,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004835073992748964,
|
|
"loss": 4.8716,
|
|
"mean_token_accuracy": 0.20734462291002273,
|
|
"num_tokens": 28627374.0,
|
|
"step": 15560
|
|
},
|
|
{
|
|
"entropy": 5.28250207901001,
|
|
"epoch": 1.3001169395255596,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00048349620980118926,
|
|
"loss": 4.8258,
|
|
"mean_token_accuracy": 0.21146264374256135,
|
|
"num_tokens": 28636331.0,
|
|
"step": 15565
|
|
},
|
|
{
|
|
"entropy": 5.248436355590821,
|
|
"epoch": 1.3005345806882727,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000483485016677505,
|
|
"loss": 4.8207,
|
|
"mean_token_accuracy": 0.21729745119810104,
|
|
"num_tokens": 28645006.0,
|
|
"step": 15570
|
|
},
|
|
{
|
|
"entropy": 5.234275913238525,
|
|
"epoch": 1.3009522218509857,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00048347381990403957,
|
|
"loss": 4.8442,
|
|
"mean_token_accuracy": 0.2161802500486374,
|
|
"num_tokens": 28653202.0,
|
|
"step": 15575
|
|
},
|
|
{
|
|
"entropy": 5.302058839797974,
|
|
"epoch": 1.3013698630136985,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00048346261948098895,
|
|
"loss": 4.8534,
|
|
"mean_token_accuracy": 0.21329295188188552,
|
|
"num_tokens": 28662701.0,
|
|
"step": 15580
|
|
},
|
|
{
|
|
"entropy": 5.269669532775879,
|
|
"epoch": 1.3017875041764118,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00048345141540854933,
|
|
"loss": 4.8672,
|
|
"mean_token_accuracy": 0.21196579933166504,
|
|
"num_tokens": 28670967.0,
|
|
"step": 15585
|
|
},
|
|
{
|
|
"entropy": 5.328446388244629,
|
|
"epoch": 1.3022051453391246,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00048344020768691673,
|
|
"loss": 4.9182,
|
|
"mean_token_accuracy": 0.22160238027572632,
|
|
"num_tokens": 28679458.0,
|
|
"step": 15590
|
|
},
|
|
{
|
|
"entropy": 5.245720243453979,
|
|
"epoch": 1.3026227865018376,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004834289963162874,
|
|
"loss": 4.8075,
|
|
"mean_token_accuracy": 0.2165750578045845,
|
|
"num_tokens": 28688497.0,
|
|
"step": 15595
|
|
},
|
|
{
|
|
"entropy": 5.271645450592041,
|
|
"epoch": 1.3030404276645506,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004834177812968576,
|
|
"loss": 4.8408,
|
|
"mean_token_accuracy": 0.21264796555042267,
|
|
"num_tokens": 28697729.0,
|
|
"step": 15600
|
|
},
|
|
{
|
|
"entropy": 5.381086301803589,
|
|
"epoch": 1.3034580688272637,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00048340656262882366,
|
|
"loss": 4.9549,
|
|
"mean_token_accuracy": 0.20701171606779098,
|
|
"num_tokens": 28707778.0,
|
|
"step": 15605
|
|
},
|
|
{
|
|
"entropy": 5.278300714492798,
|
|
"epoch": 1.3038757099899767,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00048339534031238197,
|
|
"loss": 4.8911,
|
|
"mean_token_accuracy": 0.21264438927173615,
|
|
"num_tokens": 28718010.0,
|
|
"step": 15610
|
|
},
|
|
{
|
|
"entropy": 5.279028701782226,
|
|
"epoch": 1.3042933511526895,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000483384114347729,
|
|
"loss": 4.8248,
|
|
"mean_token_accuracy": 0.21900373101234435,
|
|
"num_tokens": 28727279.0,
|
|
"step": 15615
|
|
},
|
|
{
|
|
"entropy": 5.301401233673095,
|
|
"epoch": 1.3047109923154026,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004833728847350613,
|
|
"loss": 4.8816,
|
|
"mean_token_accuracy": 0.22111395597457886,
|
|
"num_tokens": 28736510.0,
|
|
"step": 15620
|
|
},
|
|
{
|
|
"entropy": 5.332191228866577,
|
|
"epoch": 1.3051286334781156,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00048336165147457537,
|
|
"loss": 4.8799,
|
|
"mean_token_accuracy": 0.21717583537101745,
|
|
"num_tokens": 28745226.0,
|
|
"step": 15625
|
|
},
|
|
{
|
|
"entropy": 5.327915668487549,
|
|
"epoch": 1.3055462746408286,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004833504145664681,
|
|
"loss": 4.8262,
|
|
"mean_token_accuracy": 0.2179708793759346,
|
|
"num_tokens": 28754052.0,
|
|
"step": 15630
|
|
},
|
|
{
|
|
"entropy": 5.232195854187012,
|
|
"epoch": 1.3059639158035417,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00048333917401093587,
|
|
"loss": 4.8028,
|
|
"mean_token_accuracy": 0.22139799743890762,
|
|
"num_tokens": 28763580.0,
|
|
"step": 15635
|
|
},
|
|
{
|
|
"entropy": 5.283727025985717,
|
|
"epoch": 1.3063815569662545,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00048332792980817563,
|
|
"loss": 4.8216,
|
|
"mean_token_accuracy": 0.22055216133594513,
|
|
"num_tokens": 28772540.0,
|
|
"step": 15640
|
|
},
|
|
{
|
|
"entropy": 5.319442462921143,
|
|
"epoch": 1.3067991981289677,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004833166819583843,
|
|
"loss": 4.8098,
|
|
"mean_token_accuracy": 0.21570940166711808,
|
|
"num_tokens": 28782027.0,
|
|
"step": 15645
|
|
},
|
|
{
|
|
"entropy": 5.3160608291625975,
|
|
"epoch": 1.3072168392916805,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004833054304617586,
|
|
"loss": 4.8414,
|
|
"mean_token_accuracy": 0.21574851721525193,
|
|
"num_tokens": 28791724.0,
|
|
"step": 15650
|
|
},
|
|
{
|
|
"entropy": 5.27167534828186,
|
|
"epoch": 1.3076344804543936,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00048329417531849567,
|
|
"loss": 4.8677,
|
|
"mean_token_accuracy": 0.21464081555604936,
|
|
"num_tokens": 28800681.0,
|
|
"step": 15655
|
|
},
|
|
{
|
|
"entropy": 5.284883117675781,
|
|
"epoch": 1.3080521216171066,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00048328291652879245,
|
|
"loss": 4.9336,
|
|
"mean_token_accuracy": 0.21782428920269012,
|
|
"num_tokens": 28810121.0,
|
|
"step": 15660
|
|
},
|
|
{
|
|
"entropy": 5.278716325759888,
|
|
"epoch": 1.3084697627798196,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00048327165409284614,
|
|
"loss": 4.9252,
|
|
"mean_token_accuracy": 0.2154465526342392,
|
|
"num_tokens": 28819287.0,
|
|
"step": 15665
|
|
},
|
|
{
|
|
"entropy": 5.401508712768555,
|
|
"epoch": 1.3088874039425327,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004832603880108537,
|
|
"loss": 4.9106,
|
|
"mean_token_accuracy": 0.20516708344221116,
|
|
"num_tokens": 28828907.0,
|
|
"step": 15670
|
|
},
|
|
{
|
|
"entropy": 5.342611455917359,
|
|
"epoch": 1.3093050451052455,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00048324911828301256,
|
|
"loss": 4.8625,
|
|
"mean_token_accuracy": 0.21754033863544464,
|
|
"num_tokens": 28839087.0,
|
|
"step": 15675
|
|
},
|
|
{
|
|
"entropy": 5.368787479400635,
|
|
"epoch": 1.3097226862679585,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004832378449095199,
|
|
"loss": 4.9595,
|
|
"mean_token_accuracy": 0.21032623201608658,
|
|
"num_tokens": 28848956.0,
|
|
"step": 15680
|
|
},
|
|
{
|
|
"entropy": 5.307690000534057,
|
|
"epoch": 1.3101403274306715,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004832265678905731,
|
|
"loss": 4.8574,
|
|
"mean_token_accuracy": 0.21699220389127732,
|
|
"num_tokens": 28858105.0,
|
|
"step": 15685
|
|
},
|
|
{
|
|
"entropy": 5.305127429962158,
|
|
"epoch": 1.3105579685933846,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004832152872263697,
|
|
"loss": 4.9888,
|
|
"mean_token_accuracy": 0.2056853324174881,
|
|
"num_tokens": 28867539.0,
|
|
"step": 15690
|
|
},
|
|
{
|
|
"entropy": 5.282227277755737,
|
|
"epoch": 1.3109756097560976,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004832040029171069,
|
|
"loss": 4.8135,
|
|
"mean_token_accuracy": 0.21732472032308578,
|
|
"num_tokens": 28876536.0,
|
|
"step": 15695
|
|
},
|
|
{
|
|
"entropy": 5.365726184844971,
|
|
"epoch": 1.3113932509188104,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00048319271496298255,
|
|
"loss": 4.917,
|
|
"mean_token_accuracy": 0.20370503515005112,
|
|
"num_tokens": 28885354.0,
|
|
"step": 15700
|
|
},
|
|
{
|
|
"entropy": 5.322581481933594,
|
|
"epoch": 1.3118108920815237,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00048318142336419413,
|
|
"loss": 4.8238,
|
|
"mean_token_accuracy": 0.217371566593647,
|
|
"num_tokens": 28894181.0,
|
|
"step": 15705
|
|
},
|
|
{
|
|
"entropy": 5.255156230926514,
|
|
"epoch": 1.3122285332442365,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00048317012812093926,
|
|
"loss": 4.8191,
|
|
"mean_token_accuracy": 0.22690586894750595,
|
|
"num_tokens": 28903803.0,
|
|
"step": 15710
|
|
},
|
|
{
|
|
"entropy": 5.3341021060943605,
|
|
"epoch": 1.3126461744069495,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004831588292334157,
|
|
"loss": 4.9219,
|
|
"mean_token_accuracy": 0.2179974287748337,
|
|
"num_tokens": 28913192.0,
|
|
"step": 15715
|
|
},
|
|
{
|
|
"entropy": 5.296736240386963,
|
|
"epoch": 1.3130638155696626,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004831475267018213,
|
|
"loss": 4.832,
|
|
"mean_token_accuracy": 0.22062753438949584,
|
|
"num_tokens": 28922413.0,
|
|
"step": 15720
|
|
},
|
|
{
|
|
"entropy": 5.319837236404419,
|
|
"epoch": 1.3134814567323756,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004831362205263538,
|
|
"loss": 4.8798,
|
|
"mean_token_accuracy": 0.21380219608545303,
|
|
"num_tokens": 28933589.0,
|
|
"step": 15725
|
|
},
|
|
{
|
|
"entropy": 5.315175104141235,
|
|
"epoch": 1.3138990978950886,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004831249107072114,
|
|
"loss": 4.8536,
|
|
"mean_token_accuracy": 0.22306685298681259,
|
|
"num_tokens": 28942458.0,
|
|
"step": 15730
|
|
},
|
|
{
|
|
"entropy": 5.300511169433594,
|
|
"epoch": 1.3143167390578014,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00048311359724459175,
|
|
"loss": 4.831,
|
|
"mean_token_accuracy": 0.22050638645887374,
|
|
"num_tokens": 28951834.0,
|
|
"step": 15735
|
|
},
|
|
{
|
|
"entropy": 5.292247486114502,
|
|
"epoch": 1.3147343802205145,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00048310228013869323,
|
|
"loss": 4.8577,
|
|
"mean_token_accuracy": 0.22036093175411225,
|
|
"num_tokens": 28960885.0,
|
|
"step": 15740
|
|
},
|
|
{
|
|
"entropy": 5.301594591140747,
|
|
"epoch": 1.3151520213832275,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004830909593897137,
|
|
"loss": 4.8562,
|
|
"mean_token_accuracy": 0.21724576205015184,
|
|
"num_tokens": 28970922.0,
|
|
"step": 15745
|
|
},
|
|
{
|
|
"entropy": 5.326336002349853,
|
|
"epoch": 1.3155696625459405,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004830796349978515,
|
|
"loss": 4.9487,
|
|
"mean_token_accuracy": 0.21160700917243958,
|
|
"num_tokens": 28980873.0,
|
|
"step": 15750
|
|
},
|
|
{
|
|
"entropy": 5.356478261947632,
|
|
"epoch": 1.3159873037086536,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004830683069633048,
|
|
"loss": 4.9324,
|
|
"mean_token_accuracy": 0.20845704078674315,
|
|
"num_tokens": 28989876.0,
|
|
"step": 15755
|
|
},
|
|
{
|
|
"entropy": 5.310547018051148,
|
|
"epoch": 1.3164049448713664,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004830569752862719,
|
|
"loss": 4.8768,
|
|
"mean_token_accuracy": 0.21243027001619338,
|
|
"num_tokens": 28999480.0,
|
|
"step": 15760
|
|
},
|
|
{
|
|
"entropy": 5.273755884170532,
|
|
"epoch": 1.3168225860340796,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00048304563996695127,
|
|
"loss": 4.9562,
|
|
"mean_token_accuracy": 0.20882046222686768,
|
|
"num_tokens": 29009855.0,
|
|
"step": 15765
|
|
},
|
|
{
|
|
"entropy": 5.318987512588501,
|
|
"epoch": 1.3172402271967925,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00048303430100554126,
|
|
"loss": 4.7712,
|
|
"mean_token_accuracy": 0.2242559611797333,
|
|
"num_tokens": 29018506.0,
|
|
"step": 15770
|
|
},
|
|
{
|
|
"entropy": 5.335133457183838,
|
|
"epoch": 1.3176578683595055,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004830229584022404,
|
|
"loss": 4.8331,
|
|
"mean_token_accuracy": 0.21376304924488068,
|
|
"num_tokens": 29027560.0,
|
|
"step": 15775
|
|
},
|
|
{
|
|
"entropy": 5.185921573638916,
|
|
"epoch": 1.3180755095222185,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004830116121572472,
|
|
"loss": 4.7571,
|
|
"mean_token_accuracy": 0.21424792408943177,
|
|
"num_tokens": 29036038.0,
|
|
"step": 15780
|
|
},
|
|
{
|
|
"entropy": 5.264136791229248,
|
|
"epoch": 1.3184931506849316,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004830002622707604,
|
|
"loss": 4.828,
|
|
"mean_token_accuracy": 0.2213032990694046,
|
|
"num_tokens": 29046074.0,
|
|
"step": 15785
|
|
},
|
|
{
|
|
"entropy": 5.2702868461608885,
|
|
"epoch": 1.3189107918476446,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00048298890874297866,
|
|
"loss": 4.8187,
|
|
"mean_token_accuracy": 0.21467184722423555,
|
|
"num_tokens": 29055750.0,
|
|
"step": 15790
|
|
},
|
|
{
|
|
"entropy": 5.248360872268677,
|
|
"epoch": 1.3193284330103574,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004829775515741007,
|
|
"loss": 4.7935,
|
|
"mean_token_accuracy": 0.2199173927307129,
|
|
"num_tokens": 29065012.0,
|
|
"step": 15795
|
|
},
|
|
{
|
|
"entropy": 5.293356800079346,
|
|
"epoch": 1.3197460741730704,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004829661907643253,
|
|
"loss": 5.0203,
|
|
"mean_token_accuracy": 0.19927343875169753,
|
|
"num_tokens": 29074780.0,
|
|
"step": 15800
|
|
},
|
|
{
|
|
"entropy": 5.351866102218628,
|
|
"epoch": 1.3201637153357835,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004829548263138515,
|
|
"loss": 4.9777,
|
|
"mean_token_accuracy": 0.21116912066936494,
|
|
"num_tokens": 29083321.0,
|
|
"step": 15805
|
|
},
|
|
{
|
|
"entropy": 5.300055980682373,
|
|
"epoch": 1.3205813564984965,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004829434582228781,
|
|
"loss": 4.84,
|
|
"mean_token_accuracy": 0.2099160447716713,
|
|
"num_tokens": 29092110.0,
|
|
"step": 15810
|
|
},
|
|
{
|
|
"entropy": 5.221462535858154,
|
|
"epoch": 1.3209989976612095,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004829320864916042,
|
|
"loss": 4.78,
|
|
"mean_token_accuracy": 0.21375348418951035,
|
|
"num_tokens": 29100451.0,
|
|
"step": 15815
|
|
},
|
|
{
|
|
"entropy": 5.331139087677002,
|
|
"epoch": 1.3214166388239224,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00048292071112022886,
|
|
"loss": 4.859,
|
|
"mean_token_accuracy": 0.20423197746276855,
|
|
"num_tokens": 29110468.0,
|
|
"step": 15820
|
|
},
|
|
{
|
|
"entropy": 5.314853143692017,
|
|
"epoch": 1.3218342799866356,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004829093321089511,
|
|
"loss": 4.9011,
|
|
"mean_token_accuracy": 0.2157817840576172,
|
|
"num_tokens": 29119660.0,
|
|
"step": 15825
|
|
},
|
|
{
|
|
"entropy": 5.384565973281861,
|
|
"epoch": 1.3222519211493484,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004828979494579703,
|
|
"loss": 4.9508,
|
|
"mean_token_accuracy": 0.2062069743871689,
|
|
"num_tokens": 29129145.0,
|
|
"step": 15830
|
|
},
|
|
{
|
|
"entropy": 5.350839900970459,
|
|
"epoch": 1.3226695623120615,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00048288656316748554,
|
|
"loss": 4.9287,
|
|
"mean_token_accuracy": 0.2226443499326706,
|
|
"num_tokens": 29137980.0,
|
|
"step": 15835
|
|
},
|
|
{
|
|
"entropy": 5.280469942092895,
|
|
"epoch": 1.3230872034747745,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00048287517323769634,
|
|
"loss": 4.8066,
|
|
"mean_token_accuracy": 0.22313907891511917,
|
|
"num_tokens": 29147535.0,
|
|
"step": 15840
|
|
},
|
|
{
|
|
"entropy": 5.186825227737427,
|
|
"epoch": 1.3235048446374875,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00048286377966880206,
|
|
"loss": 4.7726,
|
|
"mean_token_accuracy": 0.21871122419834138,
|
|
"num_tokens": 29157162.0,
|
|
"step": 15845
|
|
},
|
|
{
|
|
"entropy": 5.245415163040161,
|
|
"epoch": 1.3239224858002006,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00048285238246100203,
|
|
"loss": 4.8145,
|
|
"mean_token_accuracy": 0.22291669696569444,
|
|
"num_tokens": 29166542.0,
|
|
"step": 15850
|
|
},
|
|
{
|
|
"entropy": 5.31989860534668,
|
|
"epoch": 1.3243401269629134,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004828409816144959,
|
|
"loss": 4.8783,
|
|
"mean_token_accuracy": 0.2228901818394661,
|
|
"num_tokens": 29176040.0,
|
|
"step": 15855
|
|
},
|
|
{
|
|
"entropy": 5.358836269378662,
|
|
"epoch": 1.3247577681256264,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004828295771294831,
|
|
"loss": 4.9577,
|
|
"mean_token_accuracy": 0.21058435440063478,
|
|
"num_tokens": 29184730.0,
|
|
"step": 15860
|
|
},
|
|
{
|
|
"entropy": 5.32158637046814,
|
|
"epoch": 1.3251754092883394,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00048281816900616354,
|
|
"loss": 4.8432,
|
|
"mean_token_accuracy": 0.21773263216018676,
|
|
"num_tokens": 29193671.0,
|
|
"step": 15865
|
|
},
|
|
{
|
|
"entropy": 5.3165857791900635,
|
|
"epoch": 1.3255930504510525,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004828067572447367,
|
|
"loss": 4.8763,
|
|
"mean_token_accuracy": 0.2157406449317932,
|
|
"num_tokens": 29203094.0,
|
|
"step": 15870
|
|
},
|
|
{
|
|
"entropy": 5.2308484554290775,
|
|
"epoch": 1.3260106916137655,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00048279534184540246,
|
|
"loss": 4.8622,
|
|
"mean_token_accuracy": 0.21683792471885682,
|
|
"num_tokens": 29211678.0,
|
|
"step": 15875
|
|
},
|
|
{
|
|
"entropy": 5.398547840118408,
|
|
"epoch": 1.3264283327764783,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004827839228083606,
|
|
"loss": 4.9864,
|
|
"mean_token_accuracy": 0.20547383576631545,
|
|
"num_tokens": 29220993.0,
|
|
"step": 15880
|
|
},
|
|
{
|
|
"entropy": 5.360707759857178,
|
|
"epoch": 1.3268459739391916,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004827725001338111,
|
|
"loss": 4.8334,
|
|
"mean_token_accuracy": 0.21717288345098495,
|
|
"num_tokens": 29230006.0,
|
|
"step": 15885
|
|
},
|
|
{
|
|
"entropy": 5.276854610443115,
|
|
"epoch": 1.3272636151019044,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00048276107382195393,
|
|
"loss": 4.7872,
|
|
"mean_token_accuracy": 0.22518540322780609,
|
|
"num_tokens": 29238906.0,
|
|
"step": 15890
|
|
},
|
|
{
|
|
"entropy": 5.348750209808349,
|
|
"epoch": 1.3276812562646174,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00048274964387298903,
|
|
"loss": 4.9175,
|
|
"mean_token_accuracy": 0.2190336212515831,
|
|
"num_tokens": 29248383.0,
|
|
"step": 15895
|
|
},
|
|
{
|
|
"entropy": 5.278561639785766,
|
|
"epoch": 1.3280988974273304,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004827382102871166,
|
|
"loss": 4.8283,
|
|
"mean_token_accuracy": 0.22056234776973724,
|
|
"num_tokens": 29257999.0,
|
|
"step": 15900
|
|
},
|
|
{
|
|
"entropy": 5.276770877838135,
|
|
"epoch": 1.3285165385900435,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00048272677306453665,
|
|
"loss": 4.8054,
|
|
"mean_token_accuracy": 0.21783913522958756,
|
|
"num_tokens": 29267143.0,
|
|
"step": 15905
|
|
},
|
|
{
|
|
"entropy": 5.32939190864563,
|
|
"epoch": 1.3289341797527565,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00048271533220544955,
|
|
"loss": 4.9563,
|
|
"mean_token_accuracy": 0.21010083854198455,
|
|
"num_tokens": 29276730.0,
|
|
"step": 15910
|
|
},
|
|
{
|
|
"entropy": 5.353422594070435,
|
|
"epoch": 1.3293518209154693,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00048270388771005555,
|
|
"loss": 4.9208,
|
|
"mean_token_accuracy": 0.2124545618891716,
|
|
"num_tokens": 29285480.0,
|
|
"step": 15915
|
|
},
|
|
{
|
|
"entropy": 5.34762659072876,
|
|
"epoch": 1.3297694620781824,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00048269243957855493,
|
|
"loss": 4.9455,
|
|
"mean_token_accuracy": 0.20739963352680207,
|
|
"num_tokens": 29294927.0,
|
|
"step": 15920
|
|
},
|
|
{
|
|
"entropy": 5.3207435131073,
|
|
"epoch": 1.3301871032408954,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004826809878111481,
|
|
"loss": 4.8549,
|
|
"mean_token_accuracy": 0.2169224202632904,
|
|
"num_tokens": 29304567.0,
|
|
"step": 15925
|
|
},
|
|
{
|
|
"entropy": 5.26420578956604,
|
|
"epoch": 1.3306047444036084,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00048266953240803576,
|
|
"loss": 4.8099,
|
|
"mean_token_accuracy": 0.2220679447054863,
|
|
"num_tokens": 29313302.0,
|
|
"step": 15930
|
|
},
|
|
{
|
|
"entropy": 5.3117101192474365,
|
|
"epoch": 1.3310223855663215,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004826580733694182,
|
|
"loss": 4.8364,
|
|
"mean_token_accuracy": 0.21676529496908187,
|
|
"num_tokens": 29322195.0,
|
|
"step": 15935
|
|
},
|
|
{
|
|
"entropy": 5.285670757293701,
|
|
"epoch": 1.3314400267290343,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004826466106954961,
|
|
"loss": 4.966,
|
|
"mean_token_accuracy": 0.20552062541246413,
|
|
"num_tokens": 29331416.0,
|
|
"step": 15940
|
|
},
|
|
{
|
|
"entropy": 5.309853792190552,
|
|
"epoch": 1.3318576678917475,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00048263514438647015,
|
|
"loss": 4.8478,
|
|
"mean_token_accuracy": 0.22179368734359742,
|
|
"num_tokens": 29340497.0,
|
|
"step": 15945
|
|
},
|
|
{
|
|
"entropy": 5.2346193313598635,
|
|
"epoch": 1.3322753090544603,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000482623674442541,
|
|
"loss": 4.8185,
|
|
"mean_token_accuracy": 0.22256653159856796,
|
|
"num_tokens": 29349306.0,
|
|
"step": 15950
|
|
},
|
|
{
|
|
"entropy": 5.331585836410523,
|
|
"epoch": 1.3326929502171734,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004826122008639096,
|
|
"loss": 4.8619,
|
|
"mean_token_accuracy": 0.21693980544805527,
|
|
"num_tokens": 29358452.0,
|
|
"step": 15955
|
|
},
|
|
{
|
|
"entropy": 5.2804608821868895,
|
|
"epoch": 1.3331105913798864,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00048260072365077675,
|
|
"loss": 4.9204,
|
|
"mean_token_accuracy": 0.20944945961236955,
|
|
"num_tokens": 29367640.0,
|
|
"step": 15960
|
|
},
|
|
{
|
|
"entropy": 5.344875049591065,
|
|
"epoch": 1.3335282325425994,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004825892428033432,
|
|
"loss": 4.846,
|
|
"mean_token_accuracy": 0.20793260335922242,
|
|
"num_tokens": 29377352.0,
|
|
"step": 15965
|
|
},
|
|
{
|
|
"entropy": 5.273377513885498,
|
|
"epoch": 1.3339458737053125,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004825777583218102,
|
|
"loss": 4.8331,
|
|
"mean_token_accuracy": 0.21988795846700668,
|
|
"num_tokens": 29386802.0,
|
|
"step": 15970
|
|
},
|
|
{
|
|
"entropy": 5.168824005126953,
|
|
"epoch": 1.3343635148680253,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004825662702063787,
|
|
"loss": 4.7326,
|
|
"mean_token_accuracy": 0.22708417624235153,
|
|
"num_tokens": 29395078.0,
|
|
"step": 15975
|
|
},
|
|
{
|
|
"entropy": 5.349821281433106,
|
|
"epoch": 1.3347811560307383,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004825547784572497,
|
|
"loss": 4.8075,
|
|
"mean_token_accuracy": 0.2180287718772888,
|
|
"num_tokens": 29403837.0,
|
|
"step": 15980
|
|
},
|
|
{
|
|
"entropy": 5.304254674911499,
|
|
"epoch": 1.3351987971934514,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004825432830746245,
|
|
"loss": 4.8389,
|
|
"mean_token_accuracy": 0.21650205552577972,
|
|
"num_tokens": 29412222.0,
|
|
"step": 15985
|
|
},
|
|
{
|
|
"entropy": 5.2822565078735355,
|
|
"epoch": 1.3356164383561644,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004825317840587044,
|
|
"loss": 4.7615,
|
|
"mean_token_accuracy": 0.22776330709457399,
|
|
"num_tokens": 29421632.0,
|
|
"step": 15990
|
|
},
|
|
{
|
|
"entropy": 5.3263161182403564,
|
|
"epoch": 1.3360340795188774,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004825202814096905,
|
|
"loss": 4.9183,
|
|
"mean_token_accuracy": 0.21787445545196532,
|
|
"num_tokens": 29430768.0,
|
|
"step": 15995
|
|
},
|
|
{
|
|
"entropy": 5.416559505462646,
|
|
"epoch": 1.3364517206815905,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004825087751277843,
|
|
"loss": 4.9545,
|
|
"mean_token_accuracy": 0.2149207189679146,
|
|
"num_tokens": 29440280.0,
|
|
"step": 16000
|
|
},
|
|
{
|
|
"entropy": 5.383160495758057,
|
|
"epoch": 1.3368693618443035,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00048249726521318716,
|
|
"loss": 4.8717,
|
|
"mean_token_accuracy": 0.2155604675412178,
|
|
"num_tokens": 29449850.0,
|
|
"step": 16005
|
|
},
|
|
{
|
|
"entropy": 5.2978602886199955,
|
|
"epoch": 1.3372870030070163,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004824857516661008,
|
|
"loss": 4.8097,
|
|
"mean_token_accuracy": 0.22655883133411409,
|
|
"num_tokens": 29459233.0,
|
|
"step": 16010
|
|
},
|
|
{
|
|
"entropy": 5.389116334915161,
|
|
"epoch": 1.3377046441697293,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00048247423448672647,
|
|
"loss": 4.9257,
|
|
"mean_token_accuracy": 0.20797293335199357,
|
|
"num_tokens": 29469351.0,
|
|
"step": 16015
|
|
},
|
|
{
|
|
"entropy": 5.322076749801636,
|
|
"epoch": 1.3381222853324424,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004824627136752659,
|
|
"loss": 4.9261,
|
|
"mean_token_accuracy": 0.20929339230060579,
|
|
"num_tokens": 29477653.0,
|
|
"step": 16020
|
|
},
|
|
{
|
|
"entropy": 5.2980574607849125,
|
|
"epoch": 1.3385399264951554,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004824511892319209,
|
|
"loss": 4.8454,
|
|
"mean_token_accuracy": 0.21762599498033525,
|
|
"num_tokens": 29486944.0,
|
|
"step": 16025
|
|
},
|
|
{
|
|
"entropy": 5.232235956192016,
|
|
"epoch": 1.3389575676578684,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00048243966115689305,
|
|
"loss": 4.8025,
|
|
"mean_token_accuracy": 0.22676217555999756,
|
|
"num_tokens": 29495791.0,
|
|
"step": 16030
|
|
},
|
|
{
|
|
"entropy": 5.399686861038208,
|
|
"epoch": 1.3393752088205813,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004824281294503843,
|
|
"loss": 5.0494,
|
|
"mean_token_accuracy": 0.20568525046110153,
|
|
"num_tokens": 29505403.0,
|
|
"step": 16035
|
|
},
|
|
{
|
|
"entropy": 5.243615674972534,
|
|
"epoch": 1.3397928499832943,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004824165941125964,
|
|
"loss": 4.7277,
|
|
"mean_token_accuracy": 0.22255088835954667,
|
|
"num_tokens": 29515310.0,
|
|
"step": 16040
|
|
},
|
|
{
|
|
"entropy": 5.325041007995606,
|
|
"epoch": 1.3402104911460073,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004824050551437315,
|
|
"loss": 4.9261,
|
|
"mean_token_accuracy": 0.2150541439652443,
|
|
"num_tokens": 29524824.0,
|
|
"step": 16045
|
|
},
|
|
{
|
|
"entropy": 5.311245632171631,
|
|
"epoch": 1.3406281323087204,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004823935125439912,
|
|
"loss": 4.8354,
|
|
"mean_token_accuracy": 0.21304788589477539,
|
|
"num_tokens": 29533667.0,
|
|
"step": 16050
|
|
},
|
|
{
|
|
"entropy": 5.335432338714599,
|
|
"epoch": 1.3410457734714334,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000482381966313578,
|
|
"loss": 4.9722,
|
|
"mean_token_accuracy": 0.21310203820466994,
|
|
"num_tokens": 29541745.0,
|
|
"step": 16055
|
|
},
|
|
{
|
|
"entropy": 5.245119524002075,
|
|
"epoch": 1.3414634146341464,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00048237041645269387,
|
|
"loss": 4.7927,
|
|
"mean_token_accuracy": 0.2188880741596222,
|
|
"num_tokens": 29551004.0,
|
|
"step": 16060
|
|
},
|
|
{
|
|
"entropy": 5.2313062191009525,
|
|
"epoch": 1.3418810557968595,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004823588629615409,
|
|
"loss": 4.8374,
|
|
"mean_token_accuracy": 0.21644213646650315,
|
|
"num_tokens": 29561061.0,
|
|
"step": 16065
|
|
},
|
|
{
|
|
"entropy": 5.174998998641968,
|
|
"epoch": 1.3422986969595723,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00048234730584032143,
|
|
"loss": 4.6755,
|
|
"mean_token_accuracy": 0.22756634801626205,
|
|
"num_tokens": 29569689.0,
|
|
"step": 16070
|
|
},
|
|
{
|
|
"entropy": 5.298877382278443,
|
|
"epoch": 1.3427163381222853,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004823357450892379,
|
|
"loss": 4.9189,
|
|
"mean_token_accuracy": 0.20920671224594117,
|
|
"num_tokens": 29579576.0,
|
|
"step": 16075
|
|
},
|
|
{
|
|
"entropy": 5.308197498321533,
|
|
"epoch": 1.3431339792849983,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004823241807084925,
|
|
"loss": 4.7845,
|
|
"mean_token_accuracy": 0.22491231858730315,
|
|
"num_tokens": 29588531.0,
|
|
"step": 16080
|
|
},
|
|
{
|
|
"entropy": 5.3194373607635494,
|
|
"epoch": 1.3435516204477114,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00048231261269828776,
|
|
"loss": 4.8569,
|
|
"mean_token_accuracy": 0.21740156561136245,
|
|
"num_tokens": 29596838.0,
|
|
"step": 16085
|
|
},
|
|
{
|
|
"entropy": 5.30812931060791,
|
|
"epoch": 1.3439692616104244,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00048230104105882624,
|
|
"loss": 4.8564,
|
|
"mean_token_accuracy": 0.2113465741276741,
|
|
"num_tokens": 29606769.0,
|
|
"step": 16090
|
|
},
|
|
{
|
|
"entropy": 5.371595287322998,
|
|
"epoch": 1.3443869027731372,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004822894657903104,
|
|
"loss": 4.9393,
|
|
"mean_token_accuracy": 0.2062610149383545,
|
|
"num_tokens": 29616994.0,
|
|
"step": 16095
|
|
},
|
|
{
|
|
"entropy": 5.210926628112793,
|
|
"epoch": 1.3448045439358502,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000482277886892943,
|
|
"loss": 4.8118,
|
|
"mean_token_accuracy": 0.22149788588285446,
|
|
"num_tokens": 29626865.0,
|
|
"step": 16100
|
|
},
|
|
{
|
|
"entropy": 5.210928964614868,
|
|
"epoch": 1.3452221850985633,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004822663043669267,
|
|
"loss": 4.7444,
|
|
"mean_token_accuracy": 0.2237505078315735,
|
|
"num_tokens": 29636439.0,
|
|
"step": 16105
|
|
},
|
|
{
|
|
"entropy": 5.2977958679199215,
|
|
"epoch": 1.3456398262612763,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00048225471821246416,
|
|
"loss": 4.7547,
|
|
"mean_token_accuracy": 0.22837678343057632,
|
|
"num_tokens": 29645019.0,
|
|
"step": 16110
|
|
},
|
|
{
|
|
"entropy": 5.337267732620239,
|
|
"epoch": 1.3460574674239894,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004822431284297584,
|
|
"loss": 4.9968,
|
|
"mean_token_accuracy": 0.21077329516410828,
|
|
"num_tokens": 29654660.0,
|
|
"step": 16115
|
|
},
|
|
{
|
|
"entropy": 5.326786613464355,
|
|
"epoch": 1.3464751085867024,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004822315350190122,
|
|
"loss": 4.9052,
|
|
"mean_token_accuracy": 0.20758735686540603,
|
|
"num_tokens": 29662880.0,
|
|
"step": 16120
|
|
},
|
|
{
|
|
"entropy": 5.387733697891235,
|
|
"epoch": 1.3468927497494154,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00048221993798042856,
|
|
"loss": 4.9029,
|
|
"mean_token_accuracy": 0.21192553043365478,
|
|
"num_tokens": 29672336.0,
|
|
"step": 16125
|
|
},
|
|
{
|
|
"entropy": 5.304873085021972,
|
|
"epoch": 1.3473103909121282,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00048220833731421045,
|
|
"loss": 4.8571,
|
|
"mean_token_accuracy": 0.2110915392637253,
|
|
"num_tokens": 29681495.0,
|
|
"step": 16130
|
|
},
|
|
{
|
|
"entropy": 5.32221155166626,
|
|
"epoch": 1.3477280320748413,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004821967330205609,
|
|
"loss": 4.8236,
|
|
"mean_token_accuracy": 0.21989824771881103,
|
|
"num_tokens": 29690214.0,
|
|
"step": 16135
|
|
},
|
|
{
|
|
"entropy": 5.288293790817261,
|
|
"epoch": 1.3481456732375543,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004821851250996832,
|
|
"loss": 4.8775,
|
|
"mean_token_accuracy": 0.2088365823030472,
|
|
"num_tokens": 29699309.0,
|
|
"step": 16140
|
|
},
|
|
{
|
|
"entropy": 5.26884446144104,
|
|
"epoch": 1.3485633144002673,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004821735135517805,
|
|
"loss": 4.8054,
|
|
"mean_token_accuracy": 0.21732977628707886,
|
|
"num_tokens": 29708741.0,
|
|
"step": 16145
|
|
},
|
|
{
|
|
"entropy": 5.336807298660278,
|
|
"epoch": 1.3489809555629804,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004821618983770561,
|
|
"loss": 4.926,
|
|
"mean_token_accuracy": 0.21344830542802812,
|
|
"num_tokens": 29717616.0,
|
|
"step": 16150
|
|
},
|
|
{
|
|
"entropy": 5.335993909835816,
|
|
"epoch": 1.3493985967256932,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00048215027957571326,
|
|
"loss": 4.8033,
|
|
"mean_token_accuracy": 0.21711914241313934,
|
|
"num_tokens": 29726601.0,
|
|
"step": 16155
|
|
},
|
|
{
|
|
"entropy": 5.294578933715821,
|
|
"epoch": 1.3498162378884062,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004821386571479555,
|
|
"loss": 4.8839,
|
|
"mean_token_accuracy": 0.2164502039551735,
|
|
"num_tokens": 29736930.0,
|
|
"step": 16160
|
|
},
|
|
{
|
|
"entropy": 5.1987217426300045,
|
|
"epoch": 1.3502338790511192,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004821270310939861,
|
|
"loss": 4.7577,
|
|
"mean_token_accuracy": 0.22193573266267777,
|
|
"num_tokens": 29745980.0,
|
|
"step": 16165
|
|
},
|
|
{
|
|
"entropy": 5.272208833694458,
|
|
"epoch": 1.3506515202138323,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004821154014140088,
|
|
"loss": 4.8645,
|
|
"mean_token_accuracy": 0.21722299754619598,
|
|
"num_tokens": 29755701.0,
|
|
"step": 16170
|
|
},
|
|
{
|
|
"entropy": 5.288503360748291,
|
|
"epoch": 1.3510691613765453,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004821037681082271,
|
|
"loss": 4.7399,
|
|
"mean_token_accuracy": 0.22895298898220062,
|
|
"num_tokens": 29763503.0,
|
|
"step": 16175
|
|
},
|
|
{
|
|
"entropy": 5.221000671386719,
|
|
"epoch": 1.3514868025392583,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004820921311768446,
|
|
"loss": 4.7281,
|
|
"mean_token_accuracy": 0.22704797387123107,
|
|
"num_tokens": 29771667.0,
|
|
"step": 16180
|
|
},
|
|
{
|
|
"entropy": 5.316294956207275,
|
|
"epoch": 1.3519044437019714,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00048208049062006505,
|
|
"loss": 4.9157,
|
|
"mean_token_accuracy": 0.21446786522865297,
|
|
"num_tokens": 29780836.0,
|
|
"step": 16185
|
|
},
|
|
{
|
|
"entropy": 5.302004289627075,
|
|
"epoch": 1.3523220848646842,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00048206884643809224,
|
|
"loss": 4.8381,
|
|
"mean_token_accuracy": 0.21401331424713135,
|
|
"num_tokens": 29790397.0,
|
|
"step": 16190
|
|
},
|
|
{
|
|
"entropy": 5.283183240890503,
|
|
"epoch": 1.3527397260273972,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00048205719863113014,
|
|
"loss": 4.8945,
|
|
"mean_token_accuracy": 0.21611769795417785,
|
|
"num_tokens": 29799227.0,
|
|
"step": 16195
|
|
},
|
|
{
|
|
"entropy": 5.314777803421021,
|
|
"epoch": 1.3531573671901103,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004820455471993824,
|
|
"loss": 4.8777,
|
|
"mean_token_accuracy": 0.21227826923131943,
|
|
"num_tokens": 29808182.0,
|
|
"step": 16200
|
|
},
|
|
{
|
|
"entropy": 5.323822641372681,
|
|
"epoch": 1.3535750083528233,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00048203389214305326,
|
|
"loss": 4.9156,
|
|
"mean_token_accuracy": 0.21252906024456025,
|
|
"num_tokens": 29817843.0,
|
|
"step": 16205
|
|
},
|
|
{
|
|
"entropy": 5.290650749206543,
|
|
"epoch": 1.3539926495155363,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004820222334623465,
|
|
"loss": 4.8255,
|
|
"mean_token_accuracy": 0.21722138077020645,
|
|
"num_tokens": 29827082.0,
|
|
"step": 16210
|
|
},
|
|
{
|
|
"entropy": 5.3295676708221436,
|
|
"epoch": 1.3544102906782491,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00048201057115746643,
|
|
"loss": 4.8311,
|
|
"mean_token_accuracy": 0.21701987236738204,
|
|
"num_tokens": 29836176.0,
|
|
"step": 16215
|
|
},
|
|
{
|
|
"entropy": 5.251177644729614,
|
|
"epoch": 1.3548279318409622,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004819989052286172,
|
|
"loss": 4.7814,
|
|
"mean_token_accuracy": 0.2237299993634224,
|
|
"num_tokens": 29845252.0,
|
|
"step": 16220
|
|
},
|
|
{
|
|
"entropy": 5.26710615158081,
|
|
"epoch": 1.3552455730036752,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004819872356760028,
|
|
"loss": 4.8225,
|
|
"mean_token_accuracy": 0.2189435452222824,
|
|
"num_tokens": 29854115.0,
|
|
"step": 16225
|
|
},
|
|
{
|
|
"entropy": 5.311855506896973,
|
|
"epoch": 1.3556632141663882,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00048197556249982774,
|
|
"loss": 4.8486,
|
|
"mean_token_accuracy": 0.225045545399189,
|
|
"num_tokens": 29861918.0,
|
|
"step": 16230
|
|
},
|
|
{
|
|
"entropy": 5.317558670043946,
|
|
"epoch": 1.3560808553291013,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004819638857002965,
|
|
"loss": 4.8653,
|
|
"mean_token_accuracy": 0.21848036646842955,
|
|
"num_tokens": 29871421.0,
|
|
"step": 16235
|
|
},
|
|
{
|
|
"entropy": 5.233267498016358,
|
|
"epoch": 1.3564984964918143,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00048195220527761306,
|
|
"loss": 4.8028,
|
|
"mean_token_accuracy": 0.22218319177627563,
|
|
"num_tokens": 29880328.0,
|
|
"step": 16240
|
|
},
|
|
{
|
|
"entropy": 5.357198715209961,
|
|
"epoch": 1.3569161376545273,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00048194052123198236,
|
|
"loss": 4.968,
|
|
"mean_token_accuracy": 0.21028922349214554,
|
|
"num_tokens": 29889777.0,
|
|
"step": 16245
|
|
},
|
|
{
|
|
"entropy": 5.2608929634094235,
|
|
"epoch": 1.3573337788172402,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00048192883356360867,
|
|
"loss": 4.8126,
|
|
"mean_token_accuracy": 0.21746855825185776,
|
|
"num_tokens": 29898638.0,
|
|
"step": 16250
|
|
},
|
|
{
|
|
"entropy": 5.264308500289917,
|
|
"epoch": 1.3577514199799532,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004819171422726966,
|
|
"loss": 4.823,
|
|
"mean_token_accuracy": 0.22062367349863052,
|
|
"num_tokens": 29907856.0,
|
|
"step": 16255
|
|
},
|
|
{
|
|
"entropy": 5.334691858291626,
|
|
"epoch": 1.3581690611426662,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00048190544735945094,
|
|
"loss": 4.909,
|
|
"mean_token_accuracy": 0.2117832064628601,
|
|
"num_tokens": 29916992.0,
|
|
"step": 16260
|
|
},
|
|
{
|
|
"entropy": 5.326459741592407,
|
|
"epoch": 1.3585867023053793,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004818937488240764,
|
|
"loss": 4.8536,
|
|
"mean_token_accuracy": 0.21467535942792892,
|
|
"num_tokens": 29926323.0,
|
|
"step": 16265
|
|
},
|
|
{
|
|
"entropy": 5.301280307769775,
|
|
"epoch": 1.3590043434680923,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00048188204666677775,
|
|
"loss": 4.8716,
|
|
"mean_token_accuracy": 0.2216569185256958,
|
|
"num_tokens": 29935386.0,
|
|
"step": 16270
|
|
},
|
|
{
|
|
"entropy": 5.264480113983154,
|
|
"epoch": 1.359421984630805,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004818703408877598,
|
|
"loss": 4.8719,
|
|
"mean_token_accuracy": 0.21829733103513718,
|
|
"num_tokens": 29944741.0,
|
|
"step": 16275
|
|
},
|
|
{
|
|
"entropy": 5.297180938720703,
|
|
"epoch": 1.3598396257935181,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004818586314872276,
|
|
"loss": 4.8022,
|
|
"mean_token_accuracy": 0.21962831765413285,
|
|
"num_tokens": 29952407.0,
|
|
"step": 16280
|
|
},
|
|
{
|
|
"entropy": 5.290769052505493,
|
|
"epoch": 1.3602572669562312,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00048184691846538596,
|
|
"loss": 4.8279,
|
|
"mean_token_accuracy": 0.2119354322552681,
|
|
"num_tokens": 29962315.0,
|
|
"step": 16285
|
|
},
|
|
{
|
|
"entropy": 5.302811336517334,
|
|
"epoch": 1.3606749081189442,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00048183520182244006,
|
|
"loss": 4.8863,
|
|
"mean_token_accuracy": 0.2162727400660515,
|
|
"num_tokens": 29972070.0,
|
|
"step": 16290
|
|
},
|
|
{
|
|
"entropy": 5.255665302276611,
|
|
"epoch": 1.3610925492816572,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000481823481558595,
|
|
"loss": 4.8093,
|
|
"mean_token_accuracy": 0.2200208216905594,
|
|
"num_tokens": 29980416.0,
|
|
"step": 16295
|
|
},
|
|
{
|
|
"entropy": 5.334734773635864,
|
|
"epoch": 1.3615101904443703,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00048181175767405594,
|
|
"loss": 4.8782,
|
|
"mean_token_accuracy": 0.2160366177558899,
|
|
"num_tokens": 29989436.0,
|
|
"step": 16300
|
|
},
|
|
{
|
|
"entropy": 5.310853338241577,
|
|
"epoch": 1.3619278316070833,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004818000301690282,
|
|
"loss": 4.803,
|
|
"mean_token_accuracy": 0.22000620663166046,
|
|
"num_tokens": 29998295.0,
|
|
"step": 16305
|
|
},
|
|
{
|
|
"entropy": 5.285625362396241,
|
|
"epoch": 1.3623454727697961,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004817882990437169,
|
|
"loss": 4.8384,
|
|
"mean_token_accuracy": 0.2142780289053917,
|
|
"num_tokens": 30007892.0,
|
|
"step": 16310
|
|
},
|
|
{
|
|
"entropy": 5.27595329284668,
|
|
"epoch": 1.3627631139325092,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00048177656429832763,
|
|
"loss": 4.8069,
|
|
"mean_token_accuracy": 0.22326859086751938,
|
|
"num_tokens": 30016477.0,
|
|
"step": 16315
|
|
},
|
|
{
|
|
"entropy": 5.216773128509521,
|
|
"epoch": 1.3631807550952222,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00048176482593306557,
|
|
"loss": 4.7985,
|
|
"mean_token_accuracy": 0.22184861451387405,
|
|
"num_tokens": 30025693.0,
|
|
"step": 16320
|
|
},
|
|
{
|
|
"entropy": 5.3346048355102536,
|
|
"epoch": 1.3635983962579352,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00048175308394813644,
|
|
"loss": 4.82,
|
|
"mean_token_accuracy": 0.2154658928513527,
|
|
"num_tokens": 30034552.0,
|
|
"step": 16325
|
|
},
|
|
{
|
|
"entropy": 5.2404052257537845,
|
|
"epoch": 1.3640160374206483,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004817413383437456,
|
|
"loss": 4.8142,
|
|
"mean_token_accuracy": 0.22233047634363173,
|
|
"num_tokens": 30043584.0,
|
|
"step": 16330
|
|
},
|
|
{
|
|
"entropy": 5.333347034454346,
|
|
"epoch": 1.364433678583361,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00048172958912009886,
|
|
"loss": 4.9328,
|
|
"mean_token_accuracy": 0.21200974732637407,
|
|
"num_tokens": 30053189.0,
|
|
"step": 16335
|
|
},
|
|
{
|
|
"entropy": 5.2593389511108395,
|
|
"epoch": 1.364851319746074,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00048171783627740176,
|
|
"loss": 4.7923,
|
|
"mean_token_accuracy": 0.21217946708202362,
|
|
"num_tokens": 30062144.0,
|
|
"step": 16340
|
|
},
|
|
{
|
|
"entropy": 5.328552150726319,
|
|
"epoch": 1.3652689609087871,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00048170607981586023,
|
|
"loss": 4.8239,
|
|
"mean_token_accuracy": 0.22360611110925674,
|
|
"num_tokens": 30071646.0,
|
|
"step": 16345
|
|
},
|
|
{
|
|
"entropy": 5.369479465484619,
|
|
"epoch": 1.3656866020715002,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004816943197356799,
|
|
"loss": 4.9253,
|
|
"mean_token_accuracy": 0.2143287718296051,
|
|
"num_tokens": 30081322.0,
|
|
"step": 16350
|
|
},
|
|
{
|
|
"entropy": 5.236555719375611,
|
|
"epoch": 1.3661042432342132,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004816825560370667,
|
|
"loss": 4.7932,
|
|
"mean_token_accuracy": 0.2249595120549202,
|
|
"num_tokens": 30090059.0,
|
|
"step": 16355
|
|
},
|
|
{
|
|
"entropy": 5.368001985549927,
|
|
"epoch": 1.3665218843969262,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00048167078872022657,
|
|
"loss": 4.9258,
|
|
"mean_token_accuracy": 0.21336186528205872,
|
|
"num_tokens": 30100924.0,
|
|
"step": 16360
|
|
},
|
|
{
|
|
"entropy": 5.281654405593872,
|
|
"epoch": 1.3669395255596393,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00048165901778536547,
|
|
"loss": 4.797,
|
|
"mean_token_accuracy": 0.22222717851400375,
|
|
"num_tokens": 30109972.0,
|
|
"step": 16365
|
|
},
|
|
{
|
|
"entropy": 5.2713587284088135,
|
|
"epoch": 1.367357166722352,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00048164724323268956,
|
|
"loss": 4.8324,
|
|
"mean_token_accuracy": 0.21656633913516998,
|
|
"num_tokens": 30118705.0,
|
|
"step": 16370
|
|
},
|
|
{
|
|
"entropy": 5.322249078750611,
|
|
"epoch": 1.3677748078850651,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00048163546506240493,
|
|
"loss": 4.9228,
|
|
"mean_token_accuracy": 0.21592748463153838,
|
|
"num_tokens": 30127631.0,
|
|
"step": 16375
|
|
},
|
|
{
|
|
"entropy": 5.2831017017364506,
|
|
"epoch": 1.3681924490477781,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004816236832747177,
|
|
"loss": 4.7865,
|
|
"mean_token_accuracy": 0.22854328602552415,
|
|
"num_tokens": 30136127.0,
|
|
"step": 16380
|
|
},
|
|
{
|
|
"entropy": 5.298264122009277,
|
|
"epoch": 1.3686100902104912,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004816118978698342,
|
|
"loss": 4.7969,
|
|
"mean_token_accuracy": 0.22274765074253083,
|
|
"num_tokens": 30145609.0,
|
|
"step": 16385
|
|
},
|
|
{
|
|
"entropy": 5.444808006286621,
|
|
"epoch": 1.3690277313732042,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004816001088479608,
|
|
"loss": 4.9346,
|
|
"mean_token_accuracy": 0.2054242819547653,
|
|
"num_tokens": 30155705.0,
|
|
"step": 16390
|
|
},
|
|
{
|
|
"entropy": 5.27429428100586,
|
|
"epoch": 1.369445372535917,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004815883162093037,
|
|
"loss": 4.8867,
|
|
"mean_token_accuracy": 0.20919259637594223,
|
|
"num_tokens": 30165549.0,
|
|
"step": 16395
|
|
},
|
|
{
|
|
"entropy": 5.252453374862671,
|
|
"epoch": 1.36986301369863,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00048157651995406954,
|
|
"loss": 4.8317,
|
|
"mean_token_accuracy": 0.21834322363138198,
|
|
"num_tokens": 30174716.0,
|
|
"step": 16400
|
|
},
|
|
{
|
|
"entropy": 5.322256851196289,
|
|
"epoch": 1.370280654861343,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004815647200824647,
|
|
"loss": 4.7939,
|
|
"mean_token_accuracy": 0.22370847165584565,
|
|
"num_tokens": 30184009.0,
|
|
"step": 16405
|
|
},
|
|
{
|
|
"entropy": 5.386941242218017,
|
|
"epoch": 1.3706982960240561,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00048155291659469587,
|
|
"loss": 4.9035,
|
|
"mean_token_accuracy": 0.21285789757966994,
|
|
"num_tokens": 30193731.0,
|
|
"step": 16410
|
|
},
|
|
{
|
|
"entropy": 5.314519596099854,
|
|
"epoch": 1.3711159371867692,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00048154110949096945,
|
|
"loss": 5.0088,
|
|
"mean_token_accuracy": 0.20490265935659407,
|
|
"num_tokens": 30203643.0,
|
|
"step": 16415
|
|
},
|
|
{
|
|
"entropy": 5.300057888031006,
|
|
"epoch": 1.3715335783494822,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004815292987714924,
|
|
"loss": 4.8423,
|
|
"mean_token_accuracy": 0.2159911498427391,
|
|
"num_tokens": 30212436.0,
|
|
"step": 16420
|
|
},
|
|
{
|
|
"entropy": 5.290144395828247,
|
|
"epoch": 1.3719512195121952,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004815174844364714,
|
|
"loss": 4.7961,
|
|
"mean_token_accuracy": 0.22084778994321824,
|
|
"num_tokens": 30221730.0,
|
|
"step": 16425
|
|
},
|
|
{
|
|
"entropy": 5.364835453033447,
|
|
"epoch": 1.372368860674908,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004815056664861133,
|
|
"loss": 4.8599,
|
|
"mean_token_accuracy": 0.2184750497341156,
|
|
"num_tokens": 30230645.0,
|
|
"step": 16430
|
|
},
|
|
{
|
|
"entropy": 5.309720134735107,
|
|
"epoch": 1.372786501837621,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004814938449206248,
|
|
"loss": 4.8234,
|
|
"mean_token_accuracy": 0.22280456721782685,
|
|
"num_tokens": 30239513.0,
|
|
"step": 16435
|
|
},
|
|
{
|
|
"entropy": 5.243803834915161,
|
|
"epoch": 1.373204143000334,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00048148201974021297,
|
|
"loss": 4.8092,
|
|
"mean_token_accuracy": 0.21761584132909775,
|
|
"num_tokens": 30248920.0,
|
|
"step": 16440
|
|
},
|
|
{
|
|
"entropy": 5.240062141418457,
|
|
"epoch": 1.3736217841630471,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000481470190945085,
|
|
"loss": 4.819,
|
|
"mean_token_accuracy": 0.22142200469970702,
|
|
"num_tokens": 30257851.0,
|
|
"step": 16445
|
|
},
|
|
{
|
|
"entropy": 5.265430307388305,
|
|
"epoch": 1.3740394253257602,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004814583585354477,
|
|
"loss": 4.8282,
|
|
"mean_token_accuracy": 0.22724106460809707,
|
|
"num_tokens": 30267676.0,
|
|
"step": 16450
|
|
},
|
|
{
|
|
"entropy": 5.236186075210571,
|
|
"epoch": 1.374457066488473,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00048144652251150836,
|
|
"loss": 4.719,
|
|
"mean_token_accuracy": 0.2274165615439415,
|
|
"num_tokens": 30277744.0,
|
|
"step": 16455
|
|
},
|
|
{
|
|
"entropy": 5.370257711410522,
|
|
"epoch": 1.374874707651186,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000481434682873474,
|
|
"loss": 4.8826,
|
|
"mean_token_accuracy": 0.20727693736553193,
|
|
"num_tokens": 30286578.0,
|
|
"step": 16460
|
|
},
|
|
{
|
|
"entropy": 5.417958116531372,
|
|
"epoch": 1.375292348813899,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004814228396215522,
|
|
"loss": 4.8769,
|
|
"mean_token_accuracy": 0.21798632740974427,
|
|
"num_tokens": 30295896.0,
|
|
"step": 16465
|
|
},
|
|
{
|
|
"entropy": 5.33520359992981,
|
|
"epoch": 1.375709989976612,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004814109927559501,
|
|
"loss": 4.9188,
|
|
"mean_token_accuracy": 0.20971027314662932,
|
|
"num_tokens": 30305397.0,
|
|
"step": 16470
|
|
},
|
|
{
|
|
"entropy": 5.269003677368164,
|
|
"epoch": 1.3761276311393251,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004813991422768751,
|
|
"loss": 4.8986,
|
|
"mean_token_accuracy": 0.21723701506853105,
|
|
"num_tokens": 30314025.0,
|
|
"step": 16475
|
|
},
|
|
{
|
|
"entropy": 5.298538160324097,
|
|
"epoch": 1.3765452723020382,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00048138728818453456,
|
|
"loss": 4.8616,
|
|
"mean_token_accuracy": 0.21700457483530045,
|
|
"num_tokens": 30324384.0,
|
|
"step": 16480
|
|
},
|
|
{
|
|
"entropy": 5.317899513244629,
|
|
"epoch": 1.3769629134647512,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00048137543047913636,
|
|
"loss": 4.8918,
|
|
"mean_token_accuracy": 0.21550340056419373,
|
|
"num_tokens": 30333663.0,
|
|
"step": 16485
|
|
},
|
|
{
|
|
"entropy": 5.311818552017212,
|
|
"epoch": 1.377380554627464,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00048136356916088764,
|
|
"loss": 4.8462,
|
|
"mean_token_accuracy": 0.21006925404071808,
|
|
"num_tokens": 30343603.0,
|
|
"step": 16490
|
|
},
|
|
{
|
|
"entropy": 5.355005216598511,
|
|
"epoch": 1.377798195790177,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00048135170422999624,
|
|
"loss": 4.8987,
|
|
"mean_token_accuracy": 0.211271832883358,
|
|
"num_tokens": 30352680.0,
|
|
"step": 16495
|
|
},
|
|
{
|
|
"entropy": 5.312258195877075,
|
|
"epoch": 1.37821583695289,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00048133983568666994,
|
|
"loss": 4.861,
|
|
"mean_token_accuracy": 0.21722388863563538,
|
|
"num_tokens": 30362597.0,
|
|
"step": 16500
|
|
},
|
|
{
|
|
"entropy": 5.418042516708374,
|
|
"epoch": 1.378633478115603,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004813279635311165,
|
|
"loss": 5.0041,
|
|
"mean_token_accuracy": 0.2064286559820175,
|
|
"num_tokens": 30372037.0,
|
|
"step": 16505
|
|
},
|
|
{
|
|
"entropy": 5.373293685913086,
|
|
"epoch": 1.3790511192783161,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004813160877635436,
|
|
"loss": 4.8574,
|
|
"mean_token_accuracy": 0.21971272081136703,
|
|
"num_tokens": 30380867.0,
|
|
"step": 16510
|
|
},
|
|
{
|
|
"entropy": 5.38096055984497,
|
|
"epoch": 1.379468760441029,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00048130420838415926,
|
|
"loss": 4.9149,
|
|
"mean_token_accuracy": 0.20935314893722534,
|
|
"num_tokens": 30391181.0,
|
|
"step": 16515
|
|
},
|
|
{
|
|
"entropy": 5.362851905822754,
|
|
"epoch": 1.379886401603742,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00048129232539317147,
|
|
"loss": 4.9277,
|
|
"mean_token_accuracy": 0.21328994780778884,
|
|
"num_tokens": 30400519.0,
|
|
"step": 16520
|
|
},
|
|
{
|
|
"entropy": 5.299980783462525,
|
|
"epoch": 1.380304042766455,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00048128043879078816,
|
|
"loss": 4.8316,
|
|
"mean_token_accuracy": 0.21281009018421174,
|
|
"num_tokens": 30409570.0,
|
|
"step": 16525
|
|
},
|
|
{
|
|
"entropy": 5.380396604537964,
|
|
"epoch": 1.380721683929168,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004812685485772175,
|
|
"loss": 4.8486,
|
|
"mean_token_accuracy": 0.21581281423568727,
|
|
"num_tokens": 30418458.0,
|
|
"step": 16530
|
|
},
|
|
{
|
|
"entropy": 5.329050874710083,
|
|
"epoch": 1.381139325091881,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00048125665475266756,
|
|
"loss": 4.8647,
|
|
"mean_token_accuracy": 0.21954190582036973,
|
|
"num_tokens": 30427933.0,
|
|
"step": 16535
|
|
},
|
|
{
|
|
"entropy": 5.391667413711548,
|
|
"epoch": 1.3815569662545941,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00048124475731734667,
|
|
"loss": 4.9394,
|
|
"mean_token_accuracy": 0.2146110489964485,
|
|
"num_tokens": 30436825.0,
|
|
"step": 16540
|
|
},
|
|
{
|
|
"entropy": 5.366901206970215,
|
|
"epoch": 1.3819746074173072,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000481232856271463,
|
|
"loss": 4.8604,
|
|
"mean_token_accuracy": 0.21347984969615935,
|
|
"num_tokens": 30445367.0,
|
|
"step": 16545
|
|
},
|
|
{
|
|
"entropy": 5.386273574829102,
|
|
"epoch": 1.38239224858002,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00048122095161522496,
|
|
"loss": 4.9681,
|
|
"mean_token_accuracy": 0.20961567908525466,
|
|
"num_tokens": 30455236.0,
|
|
"step": 16550
|
|
},
|
|
{
|
|
"entropy": 5.245576810836792,
|
|
"epoch": 1.382809889742733,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004812090433488409,
|
|
"loss": 4.8158,
|
|
"mean_token_accuracy": 0.21420430094003678,
|
|
"num_tokens": 30465003.0,
|
|
"step": 16555
|
|
},
|
|
{
|
|
"entropy": 5.307234287261963,
|
|
"epoch": 1.383227530905446,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00048119713147251944,
|
|
"loss": 4.8056,
|
|
"mean_token_accuracy": 0.2175038054585457,
|
|
"num_tokens": 30473686.0,
|
|
"step": 16560
|
|
},
|
|
{
|
|
"entropy": 5.3354188919067385,
|
|
"epoch": 1.383645172068159,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00048118521598646886,
|
|
"loss": 4.9115,
|
|
"mean_token_accuracy": 0.21777041256427765,
|
|
"num_tokens": 30482684.0,
|
|
"step": 16565
|
|
},
|
|
{
|
|
"entropy": 5.297500944137573,
|
|
"epoch": 1.384062813230872,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00048117329689089793,
|
|
"loss": 4.7803,
|
|
"mean_token_accuracy": 0.21989726424217224,
|
|
"num_tokens": 30491356.0,
|
|
"step": 16570
|
|
},
|
|
{
|
|
"entropy": 5.306126260757447,
|
|
"epoch": 1.384480454393585,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00048116137418601526,
|
|
"loss": 4.8279,
|
|
"mean_token_accuracy": 0.21506818234920502,
|
|
"num_tokens": 30500829.0,
|
|
"step": 16575
|
|
},
|
|
{
|
|
"entropy": 5.27718415260315,
|
|
"epoch": 1.384898095556298,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00048114944787202955,
|
|
"loss": 4.9527,
|
|
"mean_token_accuracy": 0.21461836993694305,
|
|
"num_tokens": 30509759.0,
|
|
"step": 16580
|
|
},
|
|
{
|
|
"entropy": 5.25542516708374,
|
|
"epoch": 1.385315736719011,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00048113751794914974,
|
|
"loss": 4.7798,
|
|
"mean_token_accuracy": 0.2230256199836731,
|
|
"num_tokens": 30518638.0,
|
|
"step": 16585
|
|
},
|
|
{
|
|
"entropy": 5.316255331039429,
|
|
"epoch": 1.385733377881724,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00048112558441758437,
|
|
"loss": 4.8208,
|
|
"mean_token_accuracy": 0.21341222375631333,
|
|
"num_tokens": 30527973.0,
|
|
"step": 16590
|
|
},
|
|
{
|
|
"entropy": 5.284233045578003,
|
|
"epoch": 1.386151019044437,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004811136472775426,
|
|
"loss": 4.7817,
|
|
"mean_token_accuracy": 0.2204662561416626,
|
|
"num_tokens": 30537120.0,
|
|
"step": 16595
|
|
},
|
|
{
|
|
"entropy": 5.385113668441773,
|
|
"epoch": 1.38656866020715,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004811017065292334,
|
|
"loss": 4.8621,
|
|
"mean_token_accuracy": 0.21284181326627732,
|
|
"num_tokens": 30546372.0,
|
|
"step": 16600
|
|
},
|
|
{
|
|
"entropy": 5.355886697769165,
|
|
"epoch": 1.3869863013698631,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00048108976217286576,
|
|
"loss": 4.8621,
|
|
"mean_token_accuracy": 0.21109728068113326,
|
|
"num_tokens": 30555377.0,
|
|
"step": 16605
|
|
},
|
|
{
|
|
"entropy": 5.246590042114258,
|
|
"epoch": 1.387403942532576,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004810778142086487,
|
|
"loss": 4.8368,
|
|
"mean_token_accuracy": 0.22170839458703995,
|
|
"num_tokens": 30565208.0,
|
|
"step": 16610
|
|
},
|
|
{
|
|
"entropy": 5.299555826187134,
|
|
"epoch": 1.387821583695289,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00048106586263679146,
|
|
"loss": 4.868,
|
|
"mean_token_accuracy": 0.2188527002930641,
|
|
"num_tokens": 30573230.0,
|
|
"step": 16615
|
|
},
|
|
{
|
|
"entropy": 5.276099920272827,
|
|
"epoch": 1.388239224858002,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00048105390745750324,
|
|
"loss": 4.7623,
|
|
"mean_token_accuracy": 0.22514562904834748,
|
|
"num_tokens": 30581570.0,
|
|
"step": 16620
|
|
},
|
|
{
|
|
"entropy": 5.295377969741821,
|
|
"epoch": 1.388656866020715,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00048104194867099336,
|
|
"loss": 4.8464,
|
|
"mean_token_accuracy": 0.22137373685836792,
|
|
"num_tokens": 30591091.0,
|
|
"step": 16625
|
|
},
|
|
{
|
|
"entropy": 5.31291356086731,
|
|
"epoch": 1.389074507183428,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00048102998627747116,
|
|
"loss": 4.8243,
|
|
"mean_token_accuracy": 0.22202666699886323,
|
|
"num_tokens": 30601545.0,
|
|
"step": 16630
|
|
},
|
|
{
|
|
"entropy": 5.37315616607666,
|
|
"epoch": 1.3894921483461409,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000481018020277146,
|
|
"loss": 4.8867,
|
|
"mean_token_accuracy": 0.2135753646492958,
|
|
"num_tokens": 30610630.0,
|
|
"step": 16635
|
|
},
|
|
{
|
|
"entropy": 5.250897550582886,
|
|
"epoch": 1.389909789508854,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00048100605067022753,
|
|
"loss": 4.7793,
|
|
"mean_token_accuracy": 0.22433718889951706,
|
|
"num_tokens": 30620015.0,
|
|
"step": 16640
|
|
},
|
|
{
|
|
"entropy": 5.343635702133179,
|
|
"epoch": 1.390327430671567,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00048099407745692504,
|
|
"loss": 4.7953,
|
|
"mean_token_accuracy": 0.22125572413206102,
|
|
"num_tokens": 30628590.0,
|
|
"step": 16645
|
|
},
|
|
{
|
|
"entropy": 5.225025844573975,
|
|
"epoch": 1.39074507183428,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00048098210063744827,
|
|
"loss": 4.8307,
|
|
"mean_token_accuracy": 0.22350571155548096,
|
|
"num_tokens": 30638624.0,
|
|
"step": 16650
|
|
},
|
|
{
|
|
"entropy": 5.276962423324585,
|
|
"epoch": 1.391162712996993,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00048097012021200696,
|
|
"loss": 4.8975,
|
|
"mean_token_accuracy": 0.21096835136413575,
|
|
"num_tokens": 30648247.0,
|
|
"step": 16655
|
|
},
|
|
{
|
|
"entropy": 5.4084155559539795,
|
|
"epoch": 1.391580354159706,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004809581361808108,
|
|
"loss": 4.9729,
|
|
"mean_token_accuracy": 0.21386206448078154,
|
|
"num_tokens": 30659045.0,
|
|
"step": 16660
|
|
},
|
|
{
|
|
"entropy": 5.34789252281189,
|
|
"epoch": 1.391997995322419,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004809461485440694,
|
|
"loss": 4.8691,
|
|
"mean_token_accuracy": 0.21241755783557892,
|
|
"num_tokens": 30668948.0,
|
|
"step": 16665
|
|
},
|
|
{
|
|
"entropy": 5.323529863357544,
|
|
"epoch": 1.392415636485132,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004809341573019929,
|
|
"loss": 4.7863,
|
|
"mean_token_accuracy": 0.2289894163608551,
|
|
"num_tokens": 30678818.0,
|
|
"step": 16670
|
|
},
|
|
{
|
|
"entropy": 5.226621770858765,
|
|
"epoch": 1.392833277647845,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004809221624547911,
|
|
"loss": 4.7505,
|
|
"mean_token_accuracy": 0.22739510983228683,
|
|
"num_tokens": 30687731.0,
|
|
"step": 16675
|
|
},
|
|
{
|
|
"entropy": 5.293884992599487,
|
|
"epoch": 1.393250918810558,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000480910164002674,
|
|
"loss": 4.8388,
|
|
"mean_token_accuracy": 0.21592586636543273,
|
|
"num_tokens": 30696880.0,
|
|
"step": 16680
|
|
},
|
|
{
|
|
"entropy": 5.345160341262817,
|
|
"epoch": 1.393668559973271,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00048089816194585153,
|
|
"loss": 4.828,
|
|
"mean_token_accuracy": 0.2140715464949608,
|
|
"num_tokens": 30706274.0,
|
|
"step": 16685
|
|
},
|
|
{
|
|
"entropy": 5.272036600112915,
|
|
"epoch": 1.394086201135984,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004808861562845339,
|
|
"loss": 4.8234,
|
|
"mean_token_accuracy": 0.2188296765089035,
|
|
"num_tokens": 30715184.0,
|
|
"step": 16690
|
|
},
|
|
{
|
|
"entropy": 5.290482854843139,
|
|
"epoch": 1.3945038422986968,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004808741470189313,
|
|
"loss": 4.7908,
|
|
"mean_token_accuracy": 0.22572192549705505,
|
|
"num_tokens": 30724501.0,
|
|
"step": 16695
|
|
},
|
|
{
|
|
"entropy": 5.3136887550354,
|
|
"epoch": 1.39492148346141,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004808621341492541,
|
|
"loss": 4.7883,
|
|
"mean_token_accuracy": 0.22149976938962937,
|
|
"num_tokens": 30733496.0,
|
|
"step": 16700
|
|
},
|
|
{
|
|
"entropy": 5.240820121765137,
|
|
"epoch": 1.395339124624123,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004808501176757122,
|
|
"loss": 4.7651,
|
|
"mean_token_accuracy": 0.22822606861591338,
|
|
"num_tokens": 30742096.0,
|
|
"step": 16705
|
|
},
|
|
{
|
|
"entropy": 5.182641649246216,
|
|
"epoch": 1.395756765786836,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004808380975985163,
|
|
"loss": 4.7397,
|
|
"mean_token_accuracy": 0.2240258127450943,
|
|
"num_tokens": 30751452.0,
|
|
"step": 16710
|
|
},
|
|
{
|
|
"entropy": 5.273520660400391,
|
|
"epoch": 1.396174406949549,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004808260739178768,
|
|
"loss": 4.8707,
|
|
"mean_token_accuracy": 0.22063401639461516,
|
|
"num_tokens": 30760686.0,
|
|
"step": 16715
|
|
},
|
|
{
|
|
"entropy": 5.284829425811767,
|
|
"epoch": 1.396592048112262,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004808140466340041,
|
|
"loss": 4.8583,
|
|
"mean_token_accuracy": 0.21749306619167327,
|
|
"num_tokens": 30769374.0,
|
|
"step": 16720
|
|
},
|
|
{
|
|
"entropy": 5.287526416778564,
|
|
"epoch": 1.397009689274975,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004808020157471087,
|
|
"loss": 4.8749,
|
|
"mean_token_accuracy": 0.2157551810145378,
|
|
"num_tokens": 30778910.0,
|
|
"step": 16725
|
|
},
|
|
{
|
|
"entropy": 5.323143720626831,
|
|
"epoch": 1.3974273304376879,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00048078998125740136,
|
|
"loss": 4.8354,
|
|
"mean_token_accuracy": 0.2170320674777031,
|
|
"num_tokens": 30787844.0,
|
|
"step": 16730
|
|
},
|
|
{
|
|
"entropy": 5.334855461120606,
|
|
"epoch": 1.3978449716004009,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004807779431650927,
|
|
"loss": 4.8881,
|
|
"mean_token_accuracy": 0.21525783389806746,
|
|
"num_tokens": 30797415.0,
|
|
"step": 16735
|
|
},
|
|
{
|
|
"entropy": 5.320186281204224,
|
|
"epoch": 1.398262612763114,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004807659014703934,
|
|
"loss": 4.8605,
|
|
"mean_token_accuracy": 0.2202631875872612,
|
|
"num_tokens": 30805595.0,
|
|
"step": 16740
|
|
},
|
|
{
|
|
"entropy": 5.323244857788086,
|
|
"epoch": 1.398680253925827,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004807538561735143,
|
|
"loss": 4.8069,
|
|
"mean_token_accuracy": 0.222462497651577,
|
|
"num_tokens": 30813840.0,
|
|
"step": 16745
|
|
},
|
|
{
|
|
"entropy": 5.343084096908569,
|
|
"epoch": 1.39909789508854,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00048074180727466636,
|
|
"loss": 4.7836,
|
|
"mean_token_accuracy": 0.22251623272895812,
|
|
"num_tokens": 30822208.0,
|
|
"step": 16750
|
|
},
|
|
{
|
|
"entropy": 5.321155261993408,
|
|
"epoch": 1.3995155362512528,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00048072975477406036,
|
|
"loss": 4.9709,
|
|
"mean_token_accuracy": 0.20781163573265077,
|
|
"num_tokens": 30831804.0,
|
|
"step": 16755
|
|
},
|
|
{
|
|
"entropy": 5.308188819885254,
|
|
"epoch": 1.399933177413966,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004807176986719074,
|
|
"loss": 4.8402,
|
|
"mean_token_accuracy": 0.22137815952301027,
|
|
"num_tokens": 30841450.0,
|
|
"step": 16760
|
|
},
|
|
{
|
|
"entropy": 5.332633781433105,
|
|
"epoch": 1.4003508185766789,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00048070563896841843,
|
|
"loss": 4.8783,
|
|
"mean_token_accuracy": 0.21576907187700273,
|
|
"num_tokens": 30849906.0,
|
|
"step": 16765
|
|
},
|
|
{
|
|
"entropy": 5.239361715316773,
|
|
"epoch": 1.400768459739392,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00048069357566380474,
|
|
"loss": 4.8733,
|
|
"mean_token_accuracy": 0.21789321303367615,
|
|
"num_tokens": 30859643.0,
|
|
"step": 16770
|
|
},
|
|
{
|
|
"entropy": 5.21994161605835,
|
|
"epoch": 1.401186100902105,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00048068150875827737,
|
|
"loss": 4.7431,
|
|
"mean_token_accuracy": 0.22531598955392837,
|
|
"num_tokens": 30868728.0,
|
|
"step": 16775
|
|
},
|
|
{
|
|
"entropy": 5.31371545791626,
|
|
"epoch": 1.401603742064818,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00048066943825204764,
|
|
"loss": 4.8121,
|
|
"mean_token_accuracy": 0.21572651118040084,
|
|
"num_tokens": 30877253.0,
|
|
"step": 16780
|
|
},
|
|
{
|
|
"entropy": 5.266329383850097,
|
|
"epoch": 1.402021383227531,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004806573641453268,
|
|
"loss": 4.8415,
|
|
"mean_token_accuracy": 0.2152874857187271,
|
|
"num_tokens": 30886118.0,
|
|
"step": 16785
|
|
},
|
|
{
|
|
"entropy": 5.270281791687012,
|
|
"epoch": 1.4024390243902438,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00048064528643832627,
|
|
"loss": 4.8667,
|
|
"mean_token_accuracy": 0.21741884499788283,
|
|
"num_tokens": 30894533.0,
|
|
"step": 16790
|
|
},
|
|
{
|
|
"entropy": 5.307703685760498,
|
|
"epoch": 1.4028566655529568,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00048063320513125747,
|
|
"loss": 4.7367,
|
|
"mean_token_accuracy": 0.21954149156808853,
|
|
"num_tokens": 30904934.0,
|
|
"step": 16795
|
|
},
|
|
{
|
|
"entropy": 5.296180725097656,
|
|
"epoch": 1.4032743067156699,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004806211202243319,
|
|
"loss": 4.7872,
|
|
"mean_token_accuracy": 0.225452983379364,
|
|
"num_tokens": 30913641.0,
|
|
"step": 16800
|
|
},
|
|
{
|
|
"entropy": 5.263496065139771,
|
|
"epoch": 1.403691947878383,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00048060903171776113,
|
|
"loss": 4.7545,
|
|
"mean_token_accuracy": 0.2214334324002266,
|
|
"num_tokens": 30922529.0,
|
|
"step": 16805
|
|
},
|
|
{
|
|
"entropy": 5.242300081253052,
|
|
"epoch": 1.404109589041096,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004805969396117567,
|
|
"loss": 4.8326,
|
|
"mean_token_accuracy": 0.2165903553366661,
|
|
"num_tokens": 30932059.0,
|
|
"step": 16810
|
|
},
|
|
{
|
|
"entropy": 5.391278886795044,
|
|
"epoch": 1.4045272302038088,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00048058484390653037,
|
|
"loss": 4.9489,
|
|
"mean_token_accuracy": 0.21443780958652497,
|
|
"num_tokens": 30941141.0,
|
|
"step": 16815
|
|
},
|
|
{
|
|
"entropy": 5.419521188735962,
|
|
"epoch": 1.404944871366522,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004805727446022939,
|
|
"loss": 4.8813,
|
|
"mean_token_accuracy": 0.21689975410699844,
|
|
"num_tokens": 30949785.0,
|
|
"step": 16820
|
|
},
|
|
{
|
|
"entropy": 5.27129430770874,
|
|
"epoch": 1.4053625125292348,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00048056064169925904,
|
|
"loss": 4.797,
|
|
"mean_token_accuracy": 0.2170259103178978,
|
|
"num_tokens": 30958421.0,
|
|
"step": 16825
|
|
},
|
|
{
|
|
"entropy": 5.185097694396973,
|
|
"epoch": 1.4057801536919479,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00048054853519763786,
|
|
"loss": 4.7478,
|
|
"mean_token_accuracy": 0.22096386402845383,
|
|
"num_tokens": 30968177.0,
|
|
"step": 16830
|
|
},
|
|
{
|
|
"entropy": 5.316499185562134,
|
|
"epoch": 1.406197794854661,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004805364250976421,
|
|
"loss": 4.8288,
|
|
"mean_token_accuracy": 0.21874358355998993,
|
|
"num_tokens": 30978048.0,
|
|
"step": 16835
|
|
},
|
|
{
|
|
"entropy": 5.251766490936279,
|
|
"epoch": 1.406615436017374,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004805243113994837,
|
|
"loss": 4.8572,
|
|
"mean_token_accuracy": 0.21599237471818925,
|
|
"num_tokens": 30988588.0,
|
|
"step": 16840
|
|
},
|
|
{
|
|
"entropy": 5.335757446289063,
|
|
"epoch": 1.407033077180087,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004805121941033749,
|
|
"loss": 4.8399,
|
|
"mean_token_accuracy": 0.2173742339015007,
|
|
"num_tokens": 30998000.0,
|
|
"step": 16845
|
|
},
|
|
{
|
|
"entropy": 5.303969669342041,
|
|
"epoch": 1.4074507183427998,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004805000732095278,
|
|
"loss": 4.8677,
|
|
"mean_token_accuracy": 0.21514104902744294,
|
|
"num_tokens": 31007103.0,
|
|
"step": 16850
|
|
},
|
|
{
|
|
"entropy": 5.286815357208252,
|
|
"epoch": 1.4078683595055128,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004804879487181546,
|
|
"loss": 4.8448,
|
|
"mean_token_accuracy": 0.21513192504644393,
|
|
"num_tokens": 31016658.0,
|
|
"step": 16855
|
|
},
|
|
{
|
|
"entropy": 5.374314069747925,
|
|
"epoch": 1.4082860006682258,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004804758206294675,
|
|
"loss": 4.9745,
|
|
"mean_token_accuracy": 0.2092174395918846,
|
|
"num_tokens": 31026968.0,
|
|
"step": 16860
|
|
},
|
|
{
|
|
"entropy": 5.232562160491943,
|
|
"epoch": 1.4087036418309389,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004804636889436787,
|
|
"loss": 4.7756,
|
|
"mean_token_accuracy": 0.22128861546516418,
|
|
"num_tokens": 31035890.0,
|
|
"step": 16865
|
|
},
|
|
{
|
|
"entropy": 5.291965389251709,
|
|
"epoch": 1.409121282993652,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00048045155366100085,
|
|
"loss": 4.9143,
|
|
"mean_token_accuracy": 0.21348240822553635,
|
|
"num_tokens": 31045203.0,
|
|
"step": 16870
|
|
},
|
|
{
|
|
"entropy": 5.335570859909057,
|
|
"epoch": 1.4095389241563647,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004804394147816462,
|
|
"loss": 4.9216,
|
|
"mean_token_accuracy": 0.21420454382896423,
|
|
"num_tokens": 31055802.0,
|
|
"step": 16875
|
|
},
|
|
{
|
|
"entropy": 5.35024790763855,
|
|
"epoch": 1.409956565319078,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00048042727230582726,
|
|
"loss": 4.8054,
|
|
"mean_token_accuracy": 0.22217515110969543,
|
|
"num_tokens": 31065434.0,
|
|
"step": 16880
|
|
},
|
|
{
|
|
"entropy": 5.250886726379394,
|
|
"epoch": 1.4103742064817908,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004804151262337568,
|
|
"loss": 4.7229,
|
|
"mean_token_accuracy": 0.2296479731798172,
|
|
"num_tokens": 31073931.0,
|
|
"step": 16885
|
|
},
|
|
{
|
|
"entropy": 5.3527655601501465,
|
|
"epoch": 1.4107918476445038,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004804029765656471,
|
|
"loss": 4.9474,
|
|
"mean_token_accuracy": 0.19992574900388718,
|
|
"num_tokens": 31083068.0,
|
|
"step": 16890
|
|
},
|
|
{
|
|
"entropy": 5.2289924144744875,
|
|
"epoch": 1.4112094888072169,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004803908233017111,
|
|
"loss": 4.746,
|
|
"mean_token_accuracy": 0.22993680089712143,
|
|
"num_tokens": 31092306.0,
|
|
"step": 16895
|
|
},
|
|
{
|
|
"entropy": 5.266117429733276,
|
|
"epoch": 1.41162712996993,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004803786664421616,
|
|
"loss": 4.7776,
|
|
"mean_token_accuracy": 0.22985710352659225,
|
|
"num_tokens": 31100540.0,
|
|
"step": 16900
|
|
},
|
|
{
|
|
"entropy": 5.266304683685303,
|
|
"epoch": 1.412044771132643,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00048036650598721125,
|
|
"loss": 4.7849,
|
|
"mean_token_accuracy": 0.22270828038454055,
|
|
"num_tokens": 31110337.0,
|
|
"step": 16905
|
|
},
|
|
{
|
|
"entropy": 5.194018173217773,
|
|
"epoch": 1.4124624122953557,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00048035434193707306,
|
|
"loss": 4.7174,
|
|
"mean_token_accuracy": 0.22309163361787795,
|
|
"num_tokens": 31119985.0,
|
|
"step": 16910
|
|
},
|
|
{
|
|
"entropy": 5.166407299041748,
|
|
"epoch": 1.4128800534580688,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00048034217429195986,
|
|
"loss": 4.6807,
|
|
"mean_token_accuracy": 0.2221182644367218,
|
|
"num_tokens": 31128147.0,
|
|
"step": 16915
|
|
},
|
|
{
|
|
"entropy": 5.332764911651611,
|
|
"epoch": 1.4132976946207818,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00048033000305208485,
|
|
"loss": 4.8909,
|
|
"mean_token_accuracy": 0.21676469296216966,
|
|
"num_tokens": 31137150.0,
|
|
"step": 16920
|
|
},
|
|
{
|
|
"entropy": 5.302383804321289,
|
|
"epoch": 1.4137153357834948,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00048031782821766086,
|
|
"loss": 4.7925,
|
|
"mean_token_accuracy": 0.21856143474578857,
|
|
"num_tokens": 31145847.0,
|
|
"step": 16925
|
|
},
|
|
{
|
|
"entropy": 5.293910360336303,
|
|
"epoch": 1.4141329769462079,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00048030564978890117,
|
|
"loss": 4.8653,
|
|
"mean_token_accuracy": 0.22130077779293061,
|
|
"num_tokens": 31154313.0,
|
|
"step": 16930
|
|
},
|
|
{
|
|
"entropy": 5.336051368713379,
|
|
"epoch": 1.4145506181089207,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000480293467766019,
|
|
"loss": 4.9237,
|
|
"mean_token_accuracy": 0.21217558681964874,
|
|
"num_tokens": 31164104.0,
|
|
"step": 16935
|
|
},
|
|
{
|
|
"entropy": 5.257043266296387,
|
|
"epoch": 1.414968259271634,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004802812821492276,
|
|
"loss": 4.7232,
|
|
"mean_token_accuracy": 0.22789612412452698,
|
|
"num_tokens": 31172833.0,
|
|
"step": 16940
|
|
},
|
|
{
|
|
"entropy": 5.2886511325836185,
|
|
"epoch": 1.4153859004343468,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00048026909293874016,
|
|
"loss": 4.8828,
|
|
"mean_token_accuracy": 0.21391259580850602,
|
|
"num_tokens": 31182557.0,
|
|
"step": 16945
|
|
},
|
|
{
|
|
"entropy": 5.311916446685791,
|
|
"epoch": 1.4158035415970598,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004802569001347702,
|
|
"loss": 4.8513,
|
|
"mean_token_accuracy": 0.22008342146873475,
|
|
"num_tokens": 31191641.0,
|
|
"step": 16950
|
|
},
|
|
{
|
|
"entropy": 5.2369927883148195,
|
|
"epoch": 1.4162211827597728,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00048024470373753114,
|
|
"loss": 4.7798,
|
|
"mean_token_accuracy": 0.21514409631490708,
|
|
"num_tokens": 31200689.0,
|
|
"step": 16955
|
|
},
|
|
{
|
|
"entropy": 5.320467901229859,
|
|
"epoch": 1.4166388239224859,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00048023250374723656,
|
|
"loss": 4.9254,
|
|
"mean_token_accuracy": 0.21475254893302917,
|
|
"num_tokens": 31209745.0,
|
|
"step": 16960
|
|
},
|
|
{
|
|
"entropy": 5.27748212814331,
|
|
"epoch": 1.417056465085199,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004802203001640998,
|
|
"loss": 4.7837,
|
|
"mean_token_accuracy": 0.22103981971740722,
|
|
"num_tokens": 31218802.0,
|
|
"step": 16965
|
|
},
|
|
{
|
|
"entropy": 5.288455533981323,
|
|
"epoch": 1.4174741062479117,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004802080929883348,
|
|
"loss": 4.7792,
|
|
"mean_token_accuracy": 0.22480332106351852,
|
|
"num_tokens": 31227650.0,
|
|
"step": 16970
|
|
},
|
|
{
|
|
"entropy": 5.253355884552002,
|
|
"epoch": 1.4178917474106247,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004801958822201551,
|
|
"loss": 4.7735,
|
|
"mean_token_accuracy": 0.22399461567401885,
|
|
"num_tokens": 31236490.0,
|
|
"step": 16975
|
|
},
|
|
{
|
|
"entropy": 5.2848669528961185,
|
|
"epoch": 1.4183093885733378,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00048018366785977445,
|
|
"loss": 4.811,
|
|
"mean_token_accuracy": 0.21699218451976776,
|
|
"num_tokens": 31245557.0,
|
|
"step": 16980
|
|
},
|
|
{
|
|
"entropy": 5.204228115081787,
|
|
"epoch": 1.4187270297360508,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00048017144990740673,
|
|
"loss": 4.7132,
|
|
"mean_token_accuracy": 0.2283393695950508,
|
|
"num_tokens": 31253804.0,
|
|
"step": 16985
|
|
},
|
|
{
|
|
"entropy": 5.29396276473999,
|
|
"epoch": 1.4191446708987638,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004801592283632658,
|
|
"loss": 4.8385,
|
|
"mean_token_accuracy": 0.22031518518924714,
|
|
"num_tokens": 31262913.0,
|
|
"step": 16990
|
|
},
|
|
{
|
|
"entropy": 5.3175801753997805,
|
|
"epoch": 1.4195623120614766,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00048014700322756567,
|
|
"loss": 4.8002,
|
|
"mean_token_accuracy": 0.22298016995191575,
|
|
"num_tokens": 31271274.0,
|
|
"step": 16995
|
|
},
|
|
{
|
|
"entropy": 5.332675313949585,
|
|
"epoch": 1.41997995322419,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004801347745005203,
|
|
"loss": 4.7901,
|
|
"mean_token_accuracy": 0.2214398130774498,
|
|
"num_tokens": 31280599.0,
|
|
"step": 17000
|
|
},
|
|
{
|
|
"entropy": 5.306594133377075,
|
|
"epoch": 1.4203975943869027,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004801225421823437,
|
|
"loss": 4.8158,
|
|
"mean_token_accuracy": 0.22138666808605195,
|
|
"num_tokens": 31288986.0,
|
|
"step": 17005
|
|
},
|
|
{
|
|
"entropy": 5.332038497924804,
|
|
"epoch": 1.4208152355496158,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00048011030627325015,
|
|
"loss": 4.8423,
|
|
"mean_token_accuracy": 0.22303955554962157,
|
|
"num_tokens": 31298979.0,
|
|
"step": 17010
|
|
},
|
|
{
|
|
"entropy": 5.215326929092408,
|
|
"epoch": 1.4212328767123288,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00048009806677345394,
|
|
"loss": 4.7969,
|
|
"mean_token_accuracy": 0.2228807181119919,
|
|
"num_tokens": 31307502.0,
|
|
"step": 17015
|
|
},
|
|
{
|
|
"entropy": 5.217844152450562,
|
|
"epoch": 1.4216505178750418,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000480085823683169,
|
|
"loss": 4.7586,
|
|
"mean_token_accuracy": 0.22646873891353608,
|
|
"num_tokens": 31316146.0,
|
|
"step": 17020
|
|
},
|
|
{
|
|
"entropy": 5.272209644317627,
|
|
"epoch": 1.4220681590377549,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004800735770026099,
|
|
"loss": 4.8422,
|
|
"mean_token_accuracy": 0.21807880848646163,
|
|
"num_tokens": 31325542.0,
|
|
"step": 17025
|
|
},
|
|
{
|
|
"entropy": 5.2852921962738035,
|
|
"epoch": 1.4224858002004677,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000480061326731991,
|
|
"loss": 4.8523,
|
|
"mean_token_accuracy": 0.2180793985724449,
|
|
"num_tokens": 31334718.0,
|
|
"step": 17030
|
|
},
|
|
{
|
|
"entropy": 5.328717279434204,
|
|
"epoch": 1.4229034413631807,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004800490728715267,
|
|
"loss": 4.8595,
|
|
"mean_token_accuracy": 0.21633462458848954,
|
|
"num_tokens": 31343635.0,
|
|
"step": 17035
|
|
},
|
|
{
|
|
"entropy": 5.306187582015991,
|
|
"epoch": 1.4233210825258937,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004800368154214317,
|
|
"loss": 4.8005,
|
|
"mean_token_accuracy": 0.2192099466919899,
|
|
"num_tokens": 31352488.0,
|
|
"step": 17040
|
|
},
|
|
{
|
|
"entropy": 5.349107551574707,
|
|
"epoch": 1.4237387236886068,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004800245543819203,
|
|
"loss": 4.8751,
|
|
"mean_token_accuracy": 0.2182447835803032,
|
|
"num_tokens": 31361788.0,
|
|
"step": 17045
|
|
},
|
|
{
|
|
"entropy": 5.2530018329620365,
|
|
"epoch": 1.4241563648513198,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00048001228975320736,
|
|
"loss": 4.8848,
|
|
"mean_token_accuracy": 0.21536295115947723,
|
|
"num_tokens": 31371190.0,
|
|
"step": 17050
|
|
},
|
|
{
|
|
"entropy": 5.320019197463989,
|
|
"epoch": 1.4245740060140326,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004800000215355075,
|
|
"loss": 4.8859,
|
|
"mean_token_accuracy": 0.2158515200018883,
|
|
"num_tokens": 31380696.0,
|
|
"step": 17055
|
|
},
|
|
{
|
|
"entropy": 5.4155439853668215,
|
|
"epoch": 1.4249916471767459,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004799877497290355,
|
|
"loss": 4.9158,
|
|
"mean_token_accuracy": 0.2117113322019577,
|
|
"num_tokens": 31390129.0,
|
|
"step": 17060
|
|
},
|
|
{
|
|
"entropy": 5.317198944091797,
|
|
"epoch": 1.4254092883394587,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00047997547433400615,
|
|
"loss": 4.8235,
|
|
"mean_token_accuracy": 0.22163454592227935,
|
|
"num_tokens": 31399697.0,
|
|
"step": 17065
|
|
},
|
|
{
|
|
"entropy": 5.280524158477784,
|
|
"epoch": 1.4258269295021717,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004799631953506345,
|
|
"loss": 4.8323,
|
|
"mean_token_accuracy": 0.21471953094005586,
|
|
"num_tokens": 31408873.0,
|
|
"step": 17070
|
|
},
|
|
{
|
|
"entropy": 5.235987901687622,
|
|
"epoch": 1.4262445706648847,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00047995091277913535,
|
|
"loss": 4.7347,
|
|
"mean_token_accuracy": 0.22478847801685334,
|
|
"num_tokens": 31416980.0,
|
|
"step": 17075
|
|
},
|
|
{
|
|
"entropy": 5.34346981048584,
|
|
"epoch": 1.4266622118275978,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00047993862661972373,
|
|
"loss": 4.8939,
|
|
"mean_token_accuracy": 0.2077559068799019,
|
|
"num_tokens": 31425759.0,
|
|
"step": 17080
|
|
},
|
|
{
|
|
"entropy": 5.348446798324585,
|
|
"epoch": 1.4270798529903108,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004799263368726148,
|
|
"loss": 4.9351,
|
|
"mean_token_accuracy": 0.21443600952625275,
|
|
"num_tokens": 31435481.0,
|
|
"step": 17085
|
|
},
|
|
{
|
|
"entropy": 5.322451162338257,
|
|
"epoch": 1.4274974941530236,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004799140435380237,
|
|
"loss": 4.7811,
|
|
"mean_token_accuracy": 0.21362104564905166,
|
|
"num_tokens": 31443924.0,
|
|
"step": 17090
|
|
},
|
|
{
|
|
"entropy": 5.326956462860108,
|
|
"epoch": 1.4279151353157367,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00047990174661616556,
|
|
"loss": 4.9338,
|
|
"mean_token_accuracy": 0.20608009546995162,
|
|
"num_tokens": 31453982.0,
|
|
"step": 17095
|
|
},
|
|
{
|
|
"entropy": 5.309982538223267,
|
|
"epoch": 1.4283327764784497,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00047988944610725574,
|
|
"loss": 4.8689,
|
|
"mean_token_accuracy": 0.21824966222047806,
|
|
"num_tokens": 31463292.0,
|
|
"step": 17100
|
|
},
|
|
{
|
|
"entropy": 5.288435268402099,
|
|
"epoch": 1.4287504176411627,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004798771420115095,
|
|
"loss": 4.8384,
|
|
"mean_token_accuracy": 0.2172706037759781,
|
|
"num_tokens": 31472314.0,
|
|
"step": 17105
|
|
},
|
|
{
|
|
"entropy": 5.309487247467041,
|
|
"epoch": 1.4291680588038758,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004798648343291423,
|
|
"loss": 4.8463,
|
|
"mean_token_accuracy": 0.21501046419143677,
|
|
"num_tokens": 31482231.0,
|
|
"step": 17110
|
|
},
|
|
{
|
|
"entropy": 5.1956277847290036,
|
|
"epoch": 1.4295856999665886,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00047985252306036966,
|
|
"loss": 4.7421,
|
|
"mean_token_accuracy": 0.22685951143503189,
|
|
"num_tokens": 31491405.0,
|
|
"step": 17115
|
|
},
|
|
{
|
|
"entropy": 5.315702247619629,
|
|
"epoch": 1.4300033411293018,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00047984020820540695,
|
|
"loss": 4.9096,
|
|
"mean_token_accuracy": 0.2076181948184967,
|
|
"num_tokens": 31501662.0,
|
|
"step": 17120
|
|
},
|
|
{
|
|
"entropy": 5.361530065536499,
|
|
"epoch": 1.4304209822920146,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00047982788976446984,
|
|
"loss": 4.8496,
|
|
"mean_token_accuracy": 0.21197468042373657,
|
|
"num_tokens": 31510671.0,
|
|
"step": 17125
|
|
},
|
|
{
|
|
"entropy": 5.263189029693604,
|
|
"epoch": 1.4308386234547277,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000479815567737774,
|
|
"loss": 4.7811,
|
|
"mean_token_accuracy": 0.22856259793043138,
|
|
"num_tokens": 31519309.0,
|
|
"step": 17130
|
|
},
|
|
{
|
|
"entropy": 5.26290225982666,
|
|
"epoch": 1.4312562646174407,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000479803242125535,
|
|
"loss": 4.799,
|
|
"mean_token_accuracy": 0.22227032035589217,
|
|
"num_tokens": 31528540.0,
|
|
"step": 17135
|
|
},
|
|
{
|
|
"entropy": 5.351357650756836,
|
|
"epoch": 1.4316739057801537,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00047979091292796886,
|
|
"loss": 4.861,
|
|
"mean_token_accuracy": 0.21804835498332978,
|
|
"num_tokens": 31538035.0,
|
|
"step": 17140
|
|
},
|
|
{
|
|
"entropy": 5.36680006980896,
|
|
"epoch": 1.4320915469428668,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004797785801452911,
|
|
"loss": 4.9115,
|
|
"mean_token_accuracy": 0.2137612521648407,
|
|
"num_tokens": 31548197.0,
|
|
"step": 17145
|
|
},
|
|
{
|
|
"entropy": 5.321032857894897,
|
|
"epoch": 1.4325091881055796,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004797662437777179,
|
|
"loss": 4.8706,
|
|
"mean_token_accuracy": 0.22352834194898605,
|
|
"num_tokens": 31557268.0,
|
|
"step": 17150
|
|
},
|
|
{
|
|
"entropy": 5.288103818893433,
|
|
"epoch": 1.4329268292682926,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00047975390382546523,
|
|
"loss": 4.8868,
|
|
"mean_token_accuracy": 0.21393256187438964,
|
|
"num_tokens": 31566503.0,
|
|
"step": 17155
|
|
},
|
|
{
|
|
"entropy": 5.2931914806365965,
|
|
"epoch": 1.4333444704310057,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00047974156028874894,
|
|
"loss": 4.8586,
|
|
"mean_token_accuracy": 0.21593163013458253,
|
|
"num_tokens": 31575754.0,
|
|
"step": 17160
|
|
},
|
|
{
|
|
"entropy": 5.314781141281128,
|
|
"epoch": 1.4337621115937187,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004797292131677851,
|
|
"loss": 4.8792,
|
|
"mean_token_accuracy": 0.21217525452375413,
|
|
"num_tokens": 31585172.0,
|
|
"step": 17165
|
|
},
|
|
{
|
|
"entropy": 5.231839609146118,
|
|
"epoch": 1.4341797527564317,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00047971686246279014,
|
|
"loss": 4.9214,
|
|
"mean_token_accuracy": 0.21357122510671617,
|
|
"num_tokens": 31594011.0,
|
|
"step": 17170
|
|
},
|
|
{
|
|
"entropy": 5.221731948852539,
|
|
"epoch": 1.4345973939191445,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004797045081739799,
|
|
"loss": 4.7353,
|
|
"mean_token_accuracy": 0.22720714211463927,
|
|
"num_tokens": 31602598.0,
|
|
"step": 17175
|
|
},
|
|
{
|
|
"entropy": 5.3198967456817625,
|
|
"epoch": 1.4350150350818578,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004796921503015709,
|
|
"loss": 4.8715,
|
|
"mean_token_accuracy": 0.2159906655550003,
|
|
"num_tokens": 31611589.0,
|
|
"step": 17180
|
|
},
|
|
{
|
|
"entropy": 5.327025508880615,
|
|
"epoch": 1.4354326762445706,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00047967978884577944,
|
|
"loss": 4.7989,
|
|
"mean_token_accuracy": 0.21877267211675644,
|
|
"num_tokens": 31620502.0,
|
|
"step": 17185
|
|
},
|
|
{
|
|
"entropy": 5.33629207611084,
|
|
"epoch": 1.4358503174072836,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004796674238068219,
|
|
"loss": 4.8959,
|
|
"mean_token_accuracy": 0.2064294621348381,
|
|
"num_tokens": 31630209.0,
|
|
"step": 17190
|
|
},
|
|
{
|
|
"entropy": 5.339263010025024,
|
|
"epoch": 1.4362679585699967,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00047965505518491474,
|
|
"loss": 4.8512,
|
|
"mean_token_accuracy": 0.21469435691833497,
|
|
"num_tokens": 31639346.0,
|
|
"step": 17195
|
|
},
|
|
{
|
|
"entropy": 5.359213876724243,
|
|
"epoch": 1.4366855997327097,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00047964268298027456,
|
|
"loss": 4.8832,
|
|
"mean_token_accuracy": 0.2129565015435219,
|
|
"num_tokens": 31647482.0,
|
|
"step": 17200
|
|
},
|
|
{
|
|
"entropy": 5.315242004394531,
|
|
"epoch": 1.4371032408954227,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00047963030719311777,
|
|
"loss": 4.8295,
|
|
"mean_token_accuracy": 0.2232433557510376,
|
|
"num_tokens": 31656218.0,
|
|
"step": 17205
|
|
},
|
|
{
|
|
"entropy": 5.357493734359741,
|
|
"epoch": 1.4375208820581356,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004796179278236612,
|
|
"loss": 4.8603,
|
|
"mean_token_accuracy": 0.20772487223148345,
|
|
"num_tokens": 31665306.0,
|
|
"step": 17210
|
|
},
|
|
{
|
|
"entropy": 5.273614168167114,
|
|
"epoch": 1.4379385232208486,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004796055448721215,
|
|
"loss": 4.7585,
|
|
"mean_token_accuracy": 0.2187543570995331,
|
|
"num_tokens": 31673689.0,
|
|
"step": 17215
|
|
},
|
|
{
|
|
"entropy": 5.311200380325317,
|
|
"epoch": 1.4383561643835616,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00047959315833871546,
|
|
"loss": 4.9456,
|
|
"mean_token_accuracy": 0.20856150686740876,
|
|
"num_tokens": 31683742.0,
|
|
"step": 17220
|
|
},
|
|
{
|
|
"entropy": 5.364399814605713,
|
|
"epoch": 1.4387738055462747,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00047958076822365994,
|
|
"loss": 4.8891,
|
|
"mean_token_accuracy": 0.2136528879404068,
|
|
"num_tokens": 31693721.0,
|
|
"step": 17225
|
|
},
|
|
{
|
|
"entropy": 5.326476097106934,
|
|
"epoch": 1.4391914467089877,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00047956837452717185,
|
|
"loss": 4.8002,
|
|
"mean_token_accuracy": 0.22636724263429642,
|
|
"num_tokens": 31703103.0,
|
|
"step": 17230
|
|
},
|
|
{
|
|
"entropy": 5.241429138183594,
|
|
"epoch": 1.4396090878717005,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00047955597724946803,
|
|
"loss": 4.7385,
|
|
"mean_token_accuracy": 0.22544552087783815,
|
|
"num_tokens": 31711718.0,
|
|
"step": 17235
|
|
},
|
|
{
|
|
"entropy": 5.274699401855469,
|
|
"epoch": 1.4400267290344138,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004795435763907656,
|
|
"loss": 4.8646,
|
|
"mean_token_accuracy": 0.22674427330493926,
|
|
"num_tokens": 31721248.0,
|
|
"step": 17240
|
|
},
|
|
{
|
|
"entropy": 5.271042966842652,
|
|
"epoch": 1.4404443701971266,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004795311719512817,
|
|
"loss": 4.8528,
|
|
"mean_token_accuracy": 0.21755938231945038,
|
|
"num_tokens": 31730109.0,
|
|
"step": 17245
|
|
},
|
|
{
|
|
"entropy": 5.445320129394531,
|
|
"epoch": 1.4408620113598396,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00047951876393123344,
|
|
"loss": 5.0719,
|
|
"mean_token_accuracy": 0.19552599340677262,
|
|
"num_tokens": 31739768.0,
|
|
"step": 17250
|
|
},
|
|
{
|
|
"entropy": 5.363088178634643,
|
|
"epoch": 1.4412796525225526,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00047950635233083805,
|
|
"loss": 4.9823,
|
|
"mean_token_accuracy": 0.209570948779583,
|
|
"num_tokens": 31749965.0,
|
|
"step": 17255
|
|
},
|
|
{
|
|
"entropy": 5.268848943710327,
|
|
"epoch": 1.4416972936852657,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00047949393715031275,
|
|
"loss": 4.7799,
|
|
"mean_token_accuracy": 0.22199018001556398,
|
|
"num_tokens": 31759112.0,
|
|
"step": 17260
|
|
},
|
|
{
|
|
"entropy": 5.313366842269898,
|
|
"epoch": 1.4421149348479787,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00047948151838987505,
|
|
"loss": 4.789,
|
|
"mean_token_accuracy": 0.21649463772773742,
|
|
"num_tokens": 31768535.0,
|
|
"step": 17265
|
|
},
|
|
{
|
|
"entropy": 5.265815305709839,
|
|
"epoch": 1.4425325760106915,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00047946909604974205,
|
|
"loss": 4.798,
|
|
"mean_token_accuracy": 0.22104623019695283,
|
|
"num_tokens": 31777088.0,
|
|
"step": 17270
|
|
},
|
|
{
|
|
"entropy": 5.240836191177368,
|
|
"epoch": 1.4429502171734045,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004794566701301315,
|
|
"loss": 4.7404,
|
|
"mean_token_accuracy": 0.22040067613124847,
|
|
"num_tokens": 31785895.0,
|
|
"step": 17275
|
|
},
|
|
{
|
|
"entropy": 5.340627861022949,
|
|
"epoch": 1.4433678583361176,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00047944424063126083,
|
|
"loss": 4.9092,
|
|
"mean_token_accuracy": 0.21674553900957108,
|
|
"num_tokens": 31795404.0,
|
|
"step": 17280
|
|
},
|
|
{
|
|
"entropy": 5.336292839050293,
|
|
"epoch": 1.4437854994988306,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004794318075533477,
|
|
"loss": 4.9018,
|
|
"mean_token_accuracy": 0.20975372493267058,
|
|
"num_tokens": 31804899.0,
|
|
"step": 17285
|
|
},
|
|
{
|
|
"entropy": 5.264790821075439,
|
|
"epoch": 1.4442031406615436,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004794193708966096,
|
|
"loss": 4.8101,
|
|
"mean_token_accuracy": 0.21780010014772416,
|
|
"num_tokens": 31814055.0,
|
|
"step": 17290
|
|
},
|
|
{
|
|
"entropy": 5.250539398193359,
|
|
"epoch": 1.4446207818242565,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00047940693066126445,
|
|
"loss": 4.7987,
|
|
"mean_token_accuracy": 0.2297729641199112,
|
|
"num_tokens": 31823193.0,
|
|
"step": 17295
|
|
},
|
|
{
|
|
"entropy": 5.273737144470215,
|
|
"epoch": 1.4450384229869697,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004793944868475299,
|
|
"loss": 4.819,
|
|
"mean_token_accuracy": 0.21612211912870408,
|
|
"num_tokens": 31832359.0,
|
|
"step": 17300
|
|
},
|
|
{
|
|
"entropy": 5.281488990783691,
|
|
"epoch": 1.4454560641496825,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004793820394556238,
|
|
"loss": 4.7924,
|
|
"mean_token_accuracy": 0.2193562626838684,
|
|
"num_tokens": 31841477.0,
|
|
"step": 17305
|
|
},
|
|
{
|
|
"entropy": 5.3417762279510494,
|
|
"epoch": 1.4458737053123956,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004793695884857641,
|
|
"loss": 4.8879,
|
|
"mean_token_accuracy": 0.21094364821910858,
|
|
"num_tokens": 31851068.0,
|
|
"step": 17310
|
|
},
|
|
{
|
|
"entropy": 5.283700084686279,
|
|
"epoch": 1.4462913464751086,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004793571339381687,
|
|
"loss": 4.7683,
|
|
"mean_token_accuracy": 0.21821187436580658,
|
|
"num_tokens": 31860026.0,
|
|
"step": 17315
|
|
},
|
|
{
|
|
"entropy": 5.3236534118652346,
|
|
"epoch": 1.4467089876378216,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004793446758130558,
|
|
"loss": 4.8095,
|
|
"mean_token_accuracy": 0.2173789083957672,
|
|
"num_tokens": 31868654.0,
|
|
"step": 17320
|
|
},
|
|
{
|
|
"entropy": 5.263491106033325,
|
|
"epoch": 1.4471266288005347,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00047933221411064334,
|
|
"loss": 4.7987,
|
|
"mean_token_accuracy": 0.23007338643074035,
|
|
"num_tokens": 31877801.0,
|
|
"step": 17325
|
|
},
|
|
{
|
|
"entropy": 5.261391592025757,
|
|
"epoch": 1.4475442699632475,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004793197488311494,
|
|
"loss": 4.8299,
|
|
"mean_token_accuracy": 0.21354834139347076,
|
|
"num_tokens": 31887266.0,
|
|
"step": 17330
|
|
},
|
|
{
|
|
"entropy": 5.279554080963135,
|
|
"epoch": 1.4479619111259605,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00047930727997479253,
|
|
"loss": 4.7693,
|
|
"mean_token_accuracy": 0.22315506935119628,
|
|
"num_tokens": 31895957.0,
|
|
"step": 17335
|
|
},
|
|
{
|
|
"entropy": 5.360145378112793,
|
|
"epoch": 1.4483795522886735,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004792948075417906,
|
|
"loss": 4.9284,
|
|
"mean_token_accuracy": 0.2099533274769783,
|
|
"num_tokens": 31904443.0,
|
|
"step": 17340
|
|
},
|
|
{
|
|
"entropy": 5.273453903198242,
|
|
"epoch": 1.4487971934513866,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004792823315323622,
|
|
"loss": 4.8031,
|
|
"mean_token_accuracy": 0.21797117590904236,
|
|
"num_tokens": 31913534.0,
|
|
"step": 17345
|
|
},
|
|
{
|
|
"entropy": 5.338152027130127,
|
|
"epoch": 1.4492148346140996,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004792698519467258,
|
|
"loss": 4.9049,
|
|
"mean_token_accuracy": 0.21152557879686357,
|
|
"num_tokens": 31922905.0,
|
|
"step": 17350
|
|
},
|
|
{
|
|
"entropy": 5.387797689437866,
|
|
"epoch": 1.4496324757768126,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004792573687850997,
|
|
"loss": 4.8991,
|
|
"mean_token_accuracy": 0.21453155428171158,
|
|
"num_tokens": 31932861.0,
|
|
"step": 17355
|
|
},
|
|
{
|
|
"entropy": 5.37198166847229,
|
|
"epoch": 1.4500501169395257,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004792448820477025,
|
|
"loss": 4.8613,
|
|
"mean_token_accuracy": 0.21005114316940307,
|
|
"num_tokens": 31941100.0,
|
|
"step": 17360
|
|
},
|
|
{
|
|
"entropy": 5.2864992141723635,
|
|
"epoch": 1.4504677581022385,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004792323917347528,
|
|
"loss": 4.8562,
|
|
"mean_token_accuracy": 0.21460708230733871,
|
|
"num_tokens": 31949860.0,
|
|
"step": 17365
|
|
},
|
|
{
|
|
"entropy": 5.213762331008911,
|
|
"epoch": 1.4508853992649515,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004792198978464692,
|
|
"loss": 4.7429,
|
|
"mean_token_accuracy": 0.21930678337812423,
|
|
"num_tokens": 31958216.0,
|
|
"step": 17370
|
|
},
|
|
{
|
|
"entropy": 5.255097198486328,
|
|
"epoch": 1.4513030404276646,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004792074003830705,
|
|
"loss": 4.7663,
|
|
"mean_token_accuracy": 0.22676854878664016,
|
|
"num_tokens": 31966967.0,
|
|
"step": 17375
|
|
},
|
|
{
|
|
"entropy": 5.281587219238281,
|
|
"epoch": 1.4517206815903776,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004791948993447754,
|
|
"loss": 4.8151,
|
|
"mean_token_accuracy": 0.22235211730003357,
|
|
"num_tokens": 31976852.0,
|
|
"step": 17380
|
|
},
|
|
{
|
|
"entropy": 5.2325019359588625,
|
|
"epoch": 1.4521383227530906,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004791823947318029,
|
|
"loss": 4.7595,
|
|
"mean_token_accuracy": 0.22374455034732818,
|
|
"num_tokens": 31985966.0,
|
|
"step": 17385
|
|
},
|
|
{
|
|
"entropy": 5.280241346359253,
|
|
"epoch": 1.4525559639158034,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004791698865443717,
|
|
"loss": 4.79,
|
|
"mean_token_accuracy": 0.2261586919426918,
|
|
"num_tokens": 31994897.0,
|
|
"step": 17390
|
|
},
|
|
{
|
|
"entropy": 5.277276706695557,
|
|
"epoch": 1.4529736050785165,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00047915737478270093,
|
|
"loss": 4.8157,
|
|
"mean_token_accuracy": 0.21268099844455718,
|
|
"num_tokens": 32004504.0,
|
|
"step": 17395
|
|
},
|
|
{
|
|
"entropy": 5.306050205230713,
|
|
"epoch": 1.4533912462412295,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004791448594470095,
|
|
"loss": 4.7907,
|
|
"mean_token_accuracy": 0.2205272063612938,
|
|
"num_tokens": 32012907.0,
|
|
"step": 17400
|
|
},
|
|
{
|
|
"entropy": 5.265260982513428,
|
|
"epoch": 1.4538088874039425,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004791323405375167,
|
|
"loss": 4.739,
|
|
"mean_token_accuracy": 0.22330963462591172,
|
|
"num_tokens": 32021778.0,
|
|
"step": 17405
|
|
},
|
|
{
|
|
"entropy": 5.338131856918335,
|
|
"epoch": 1.4542265285666556,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004791198180544415,
|
|
"loss": 4.8444,
|
|
"mean_token_accuracy": 0.21523987352848054,
|
|
"num_tokens": 32030471.0,
|
|
"step": 17410
|
|
},
|
|
{
|
|
"entropy": 5.343870353698731,
|
|
"epoch": 1.4546441697293686,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004791072919980032,
|
|
"loss": 4.9453,
|
|
"mean_token_accuracy": 0.21186422258615495,
|
|
"num_tokens": 32039747.0,
|
|
"step": 17415
|
|
},
|
|
{
|
|
"entropy": 5.3425867557525635,
|
|
"epoch": 1.4550618108920816,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00047909476236842105,
|
|
"loss": 4.8752,
|
|
"mean_token_accuracy": 0.21681613922119142,
|
|
"num_tokens": 32048911.0,
|
|
"step": 17420
|
|
},
|
|
{
|
|
"entropy": 5.369258117675781,
|
|
"epoch": 1.4554794520547945,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004790822291659144,
|
|
"loss": 4.8734,
|
|
"mean_token_accuracy": 0.20779997408390044,
|
|
"num_tokens": 32058942.0,
|
|
"step": 17425
|
|
},
|
|
{
|
|
"entropy": 5.300298643112183,
|
|
"epoch": 1.4558970932175075,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00047906969239070276,
|
|
"loss": 4.9349,
|
|
"mean_token_accuracy": 0.20768627226352693,
|
|
"num_tokens": 32067828.0,
|
|
"step": 17430
|
|
},
|
|
{
|
|
"entropy": 5.274516582489014,
|
|
"epoch": 1.4563147343802205,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00047905715204300543,
|
|
"loss": 4.7912,
|
|
"mean_token_accuracy": 0.22809769511222838,
|
|
"num_tokens": 32077765.0,
|
|
"step": 17435
|
|
},
|
|
{
|
|
"entropy": 5.282214260101318,
|
|
"epoch": 1.4567323755429336,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000479044608123042,
|
|
"loss": 4.8195,
|
|
"mean_token_accuracy": 0.21865882575511933,
|
|
"num_tokens": 32087525.0,
|
|
"step": 17440
|
|
},
|
|
{
|
|
"entropy": 5.425937223434448,
|
|
"epoch": 1.4571500167056466,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004790320606310322,
|
|
"loss": 4.9633,
|
|
"mean_token_accuracy": 0.21105701327323914,
|
|
"num_tokens": 32097005.0,
|
|
"step": 17445
|
|
},
|
|
{
|
|
"entropy": 5.353099632263183,
|
|
"epoch": 1.4575676578683594,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004790195095671956,
|
|
"loss": 4.9071,
|
|
"mean_token_accuracy": 0.21156767308712005,
|
|
"num_tokens": 32106761.0,
|
|
"step": 17450
|
|
},
|
|
{
|
|
"entropy": 5.326380729675293,
|
|
"epoch": 1.4579852990310724,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004790069549317518,
|
|
"loss": 4.8093,
|
|
"mean_token_accuracy": 0.2166868641972542,
|
|
"num_tokens": 32115803.0,
|
|
"step": 17455
|
|
},
|
|
{
|
|
"entropy": 5.162849807739258,
|
|
"epoch": 1.4584029401937855,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004789943967249207,
|
|
"loss": 4.7471,
|
|
"mean_token_accuracy": 0.22838370352983475,
|
|
"num_tokens": 32124889.0,
|
|
"step": 17460
|
|
},
|
|
{
|
|
"entropy": 5.245102405548096,
|
|
"epoch": 1.4588205813564985,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004789818349469222,
|
|
"loss": 4.8362,
|
|
"mean_token_accuracy": 0.22484203577041625,
|
|
"num_tokens": 32133765.0,
|
|
"step": 17465
|
|
},
|
|
{
|
|
"entropy": 5.3413310050964355,
|
|
"epoch": 1.4592382225192115,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00047896926959797615,
|
|
"loss": 4.8697,
|
|
"mean_token_accuracy": 0.2141903132200241,
|
|
"num_tokens": 32142890.0,
|
|
"step": 17470
|
|
},
|
|
{
|
|
"entropy": 5.291785717010498,
|
|
"epoch": 1.4596558636819246,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004789567006783025,
|
|
"loss": 4.8138,
|
|
"mean_token_accuracy": 0.2199429005384445,
|
|
"num_tokens": 32151791.0,
|
|
"step": 17475
|
|
},
|
|
{
|
|
"entropy": 5.270129728317261,
|
|
"epoch": 1.4600735048446376,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004789441281881213,
|
|
"loss": 4.8351,
|
|
"mean_token_accuracy": 0.22426314353942872,
|
|
"num_tokens": 32160313.0,
|
|
"step": 17480
|
|
},
|
|
{
|
|
"entropy": 5.320230340957641,
|
|
"epoch": 1.4604911460073504,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004789315521276526,
|
|
"loss": 4.8084,
|
|
"mean_token_accuracy": 0.2179076686501503,
|
|
"num_tokens": 32170044.0,
|
|
"step": 17485
|
|
},
|
|
{
|
|
"entropy": 5.422908735275269,
|
|
"epoch": 1.4609087871700634,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004789189724971167,
|
|
"loss": 4.8823,
|
|
"mean_token_accuracy": 0.20891248285770417,
|
|
"num_tokens": 32178907.0,
|
|
"step": 17490
|
|
},
|
|
{
|
|
"entropy": 5.271880102157593,
|
|
"epoch": 1.4613264283327765,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00047890638929673366,
|
|
"loss": 4.8137,
|
|
"mean_token_accuracy": 0.21354431211948394,
|
|
"num_tokens": 32188197.0,
|
|
"step": 17495
|
|
},
|
|
{
|
|
"entropy": 5.3174351215362545,
|
|
"epoch": 1.4617440694954895,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004788938025267238,
|
|
"loss": 4.886,
|
|
"mean_token_accuracy": 0.21690189093351364,
|
|
"num_tokens": 32198206.0,
|
|
"step": 17500
|
|
},
|
|
{
|
|
"entropy": 5.419966697692871,
|
|
"epoch": 1.4621617106582026,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00047888121218730756,
|
|
"loss": 4.9522,
|
|
"mean_token_accuracy": 0.2163204699754715,
|
|
"num_tokens": 32207306.0,
|
|
"step": 17505
|
|
},
|
|
{
|
|
"entropy": 5.290495920181274,
|
|
"epoch": 1.4625793518209154,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00047886861827870533,
|
|
"loss": 4.8224,
|
|
"mean_token_accuracy": 0.2185595527291298,
|
|
"num_tokens": 32215945.0,
|
|
"step": 17510
|
|
},
|
|
{
|
|
"entropy": 5.240340375900269,
|
|
"epoch": 1.4629969929836284,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004788560208011375,
|
|
"loss": 4.7308,
|
|
"mean_token_accuracy": 0.22356290966272355,
|
|
"num_tokens": 32224601.0,
|
|
"step": 17515
|
|
},
|
|
{
|
|
"entropy": 5.219143009185791,
|
|
"epoch": 1.4634146341463414,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004788434197548246,
|
|
"loss": 4.7192,
|
|
"mean_token_accuracy": 0.22742687910795212,
|
|
"num_tokens": 32233265.0,
|
|
"step": 17520
|
|
},
|
|
{
|
|
"entropy": 5.283413362503052,
|
|
"epoch": 1.4638322753090545,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004788308151399873,
|
|
"loss": 4.7317,
|
|
"mean_token_accuracy": 0.2290090426802635,
|
|
"num_tokens": 32242749.0,
|
|
"step": 17525
|
|
},
|
|
{
|
|
"entropy": 5.274441909790039,
|
|
"epoch": 1.4642499164717675,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00047881820695684624,
|
|
"loss": 4.8512,
|
|
"mean_token_accuracy": 0.2186196193099022,
|
|
"num_tokens": 32251295.0,
|
|
"step": 17530
|
|
},
|
|
{
|
|
"entropy": 5.240420389175415,
|
|
"epoch": 1.4646675576344805,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004788055952056221,
|
|
"loss": 4.8179,
|
|
"mean_token_accuracy": 0.22223208099603653,
|
|
"num_tokens": 32261099.0,
|
|
"step": 17535
|
|
},
|
|
{
|
|
"entropy": 5.323274278640747,
|
|
"epoch": 1.4650851987971936,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00047879297988653576,
|
|
"loss": 4.8506,
|
|
"mean_token_accuracy": 0.21970323026180266,
|
|
"num_tokens": 32269420.0,
|
|
"step": 17540
|
|
},
|
|
{
|
|
"entropy": 5.313152170181274,
|
|
"epoch": 1.4655028399599064,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00047878036099980795,
|
|
"loss": 4.7627,
|
|
"mean_token_accuracy": 0.22385683357715608,
|
|
"num_tokens": 32278455.0,
|
|
"step": 17545
|
|
},
|
|
{
|
|
"entropy": 5.297255754470825,
|
|
"epoch": 1.4659204811226194,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00047876773854565964,
|
|
"loss": 4.8898,
|
|
"mean_token_accuracy": 0.21370391249656678,
|
|
"num_tokens": 32287292.0,
|
|
"step": 17550
|
|
},
|
|
{
|
|
"entropy": 5.358124256134033,
|
|
"epoch": 1.4663381222853324,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004787551125243118,
|
|
"loss": 4.9218,
|
|
"mean_token_accuracy": 0.21019356548786164,
|
|
"num_tokens": 32296384.0,
|
|
"step": 17555
|
|
},
|
|
{
|
|
"entropy": 5.26129674911499,
|
|
"epoch": 1.4667557634480455,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004787424829359854,
|
|
"loss": 4.8185,
|
|
"mean_token_accuracy": 0.22790880203247071,
|
|
"num_tokens": 32304908.0,
|
|
"step": 17560
|
|
},
|
|
{
|
|
"entropy": 5.27488145828247,
|
|
"epoch": 1.4671734046107585,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004787298497809017,
|
|
"loss": 4.8371,
|
|
"mean_token_accuracy": 0.22258786410093306,
|
|
"num_tokens": 32314843.0,
|
|
"step": 17565
|
|
},
|
|
{
|
|
"entropy": 5.262216949462891,
|
|
"epoch": 1.4675910457734713,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004787172130592817,
|
|
"loss": 4.7403,
|
|
"mean_token_accuracy": 0.228139466047287,
|
|
"num_tokens": 32324101.0,
|
|
"step": 17570
|
|
},
|
|
{
|
|
"entropy": 5.272411346435547,
|
|
"epoch": 1.4680086869361844,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00047870457277134667,
|
|
"loss": 4.8172,
|
|
"mean_token_accuracy": 0.22460807114839554,
|
|
"num_tokens": 32333736.0,
|
|
"step": 17575
|
|
},
|
|
{
|
|
"entropy": 5.282832050323487,
|
|
"epoch": 1.4684263280988974,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004786919289173179,
|
|
"loss": 4.8611,
|
|
"mean_token_accuracy": 0.21773746311664582,
|
|
"num_tokens": 32342369.0,
|
|
"step": 17580
|
|
},
|
|
{
|
|
"entropy": 5.279221630096435,
|
|
"epoch": 1.4688439692616104,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00047867928149741666,
|
|
"loss": 4.8155,
|
|
"mean_token_accuracy": 0.22611204236745835,
|
|
"num_tokens": 32351576.0,
|
|
"step": 17585
|
|
},
|
|
{
|
|
"entropy": 5.403033638000489,
|
|
"epoch": 1.4692616104243235,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00047866663051186444,
|
|
"loss": 4.8661,
|
|
"mean_token_accuracy": 0.21593413800001143,
|
|
"num_tokens": 32360355.0,
|
|
"step": 17590
|
|
},
|
|
{
|
|
"entropy": 5.350135040283203,
|
|
"epoch": 1.4696792515870365,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004786539759608828,
|
|
"loss": 4.8639,
|
|
"mean_token_accuracy": 0.22170693874359132,
|
|
"num_tokens": 32368611.0,
|
|
"step": 17595
|
|
},
|
|
{
|
|
"entropy": 5.3420497417449955,
|
|
"epoch": 1.4700968927497495,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00047864131784469314,
|
|
"loss": 4.8859,
|
|
"mean_token_accuracy": 0.2129635915160179,
|
|
"num_tokens": 32377753.0,
|
|
"step": 17600
|
|
},
|
|
{
|
|
"entropy": 5.368931770324707,
|
|
"epoch": 1.4705145339124623,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000478628656163517,
|
|
"loss": 4.9404,
|
|
"mean_token_accuracy": 0.20734216421842575,
|
|
"num_tokens": 32388135.0,
|
|
"step": 17605
|
|
},
|
|
{
|
|
"entropy": 5.292382431030274,
|
|
"epoch": 1.4709321750751754,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004786159909175762,
|
|
"loss": 4.8443,
|
|
"mean_token_accuracy": 0.21852984577417373,
|
|
"num_tokens": 32397149.0,
|
|
"step": 17610
|
|
},
|
|
{
|
|
"entropy": 5.261622714996338,
|
|
"epoch": 1.4713498162378884,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004786033221070924,
|
|
"loss": 4.7884,
|
|
"mean_token_accuracy": 0.224715955555439,
|
|
"num_tokens": 32405811.0,
|
|
"step": 17615
|
|
},
|
|
{
|
|
"entropy": 5.341516017913818,
|
|
"epoch": 1.4717674574006014,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004785906497322873,
|
|
"loss": 4.7793,
|
|
"mean_token_accuracy": 0.2257031038403511,
|
|
"num_tokens": 32413800.0,
|
|
"step": 17620
|
|
},
|
|
{
|
|
"entropy": 5.302688217163086,
|
|
"epoch": 1.4721850985633145,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00047857797379338284,
|
|
"loss": 4.8264,
|
|
"mean_token_accuracy": 0.22873318642377855,
|
|
"num_tokens": 32422462.0,
|
|
"step": 17625
|
|
},
|
|
{
|
|
"entropy": 5.309845685958862,
|
|
"epoch": 1.4726027397260273,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00047856529429060097,
|
|
"loss": 4.9037,
|
|
"mean_token_accuracy": 0.20999435633420943,
|
|
"num_tokens": 32433149.0,
|
|
"step": 17630
|
|
},
|
|
{
|
|
"entropy": 5.203973388671875,
|
|
"epoch": 1.4730203808887403,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00047855261122416355,
|
|
"loss": 4.7918,
|
|
"mean_token_accuracy": 0.2230030730366707,
|
|
"num_tokens": 32442033.0,
|
|
"step": 17635
|
|
},
|
|
{
|
|
"entropy": 5.37197208404541,
|
|
"epoch": 1.4734380220514534,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004785399245942926,
|
|
"loss": 4.8769,
|
|
"mean_token_accuracy": 0.21555653512477874,
|
|
"num_tokens": 32451189.0,
|
|
"step": 17640
|
|
},
|
|
{
|
|
"entropy": 5.359913873672485,
|
|
"epoch": 1.4738556632141664,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004785272344012104,
|
|
"loss": 4.8005,
|
|
"mean_token_accuracy": 0.22149921506643294,
|
|
"num_tokens": 32459929.0,
|
|
"step": 17645
|
|
},
|
|
{
|
|
"entropy": 5.248632001876831,
|
|
"epoch": 1.4742733043768794,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004785145406451389,
|
|
"loss": 4.8689,
|
|
"mean_token_accuracy": 0.21922674924135208,
|
|
"num_tokens": 32468275.0,
|
|
"step": 17650
|
|
},
|
|
{
|
|
"entropy": 5.28687858581543,
|
|
"epoch": 1.4746909455395925,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004785018433263004,
|
|
"loss": 4.8299,
|
|
"mean_token_accuracy": 0.22082536071538925,
|
|
"num_tokens": 32477833.0,
|
|
"step": 17655
|
|
},
|
|
{
|
|
"entropy": 5.2629437923431395,
|
|
"epoch": 1.4751085867023055,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00047848914244491715,
|
|
"loss": 4.7573,
|
|
"mean_token_accuracy": 0.22263561189174652,
|
|
"num_tokens": 32486458.0,
|
|
"step": 17660
|
|
},
|
|
{
|
|
"entropy": 5.291082572937012,
|
|
"epoch": 1.4755262278650183,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004784764380012115,
|
|
"loss": 4.8083,
|
|
"mean_token_accuracy": 0.2207770213484764,
|
|
"num_tokens": 32495355.0,
|
|
"step": 17665
|
|
},
|
|
{
|
|
"entropy": 5.282553195953369,
|
|
"epoch": 1.4759438690277313,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00047846372999540596,
|
|
"loss": 4.7633,
|
|
"mean_token_accuracy": 0.22341510355472566,
|
|
"num_tokens": 32504083.0,
|
|
"step": 17670
|
|
},
|
|
{
|
|
"entropy": 5.268411588668823,
|
|
"epoch": 1.4763615101904444,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00047845101842772285,
|
|
"loss": 4.8892,
|
|
"mean_token_accuracy": 0.21653029173612595,
|
|
"num_tokens": 32513303.0,
|
|
"step": 17675
|
|
},
|
|
{
|
|
"entropy": 5.327518653869629,
|
|
"epoch": 1.4767791513531574,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00047843830329838475,
|
|
"loss": 4.8657,
|
|
"mean_token_accuracy": 0.2145080879330635,
|
|
"num_tokens": 32522183.0,
|
|
"step": 17680
|
|
},
|
|
{
|
|
"entropy": 5.319719409942627,
|
|
"epoch": 1.4771967925158704,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00047842558460761437,
|
|
"loss": 4.9051,
|
|
"mean_token_accuracy": 0.21627224385738372,
|
|
"num_tokens": 32531443.0,
|
|
"step": 17685
|
|
},
|
|
{
|
|
"entropy": 5.365363264083863,
|
|
"epoch": 1.4776144336785833,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00047841286235563417,
|
|
"loss": 4.7887,
|
|
"mean_token_accuracy": 0.2255273148417473,
|
|
"num_tokens": 32539435.0,
|
|
"step": 17690
|
|
},
|
|
{
|
|
"entropy": 5.247160148620606,
|
|
"epoch": 1.4780320748412963,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00047840013654266707,
|
|
"loss": 4.8111,
|
|
"mean_token_accuracy": 0.2261916220188141,
|
|
"num_tokens": 32548465.0,
|
|
"step": 17695
|
|
},
|
|
{
|
|
"entropy": 5.278184938430786,
|
|
"epoch": 1.4784497160040093,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004783874071689357,
|
|
"loss": 4.7948,
|
|
"mean_token_accuracy": 0.22512311190366746,
|
|
"num_tokens": 32556511.0,
|
|
"step": 17700
|
|
},
|
|
{
|
|
"entropy": 5.355366182327271,
|
|
"epoch": 1.4788673571667224,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00047837467423466284,
|
|
"loss": 4.9714,
|
|
"mean_token_accuracy": 0.21380641609430312,
|
|
"num_tokens": 32566077.0,
|
|
"step": 17705
|
|
},
|
|
{
|
|
"entropy": 5.400937843322754,
|
|
"epoch": 1.4792849983294354,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00047836193774007164,
|
|
"loss": 4.92,
|
|
"mean_token_accuracy": 0.21800977140665054,
|
|
"num_tokens": 32575942.0,
|
|
"step": 17710
|
|
},
|
|
{
|
|
"entropy": 5.286546993255615,
|
|
"epoch": 1.4797026394921484,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004783491976853849,
|
|
"loss": 4.8118,
|
|
"mean_token_accuracy": 0.22911693304777145,
|
|
"num_tokens": 32584595.0,
|
|
"step": 17715
|
|
},
|
|
{
|
|
"entropy": 5.279857397079468,
|
|
"epoch": 1.4801202806548615,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00047833645407082564,
|
|
"loss": 4.797,
|
|
"mean_token_accuracy": 0.21715095043182372,
|
|
"num_tokens": 32594048.0,
|
|
"step": 17720
|
|
},
|
|
{
|
|
"entropy": 5.224676942825317,
|
|
"epoch": 1.4805379218175743,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004783237068966171,
|
|
"loss": 4.6812,
|
|
"mean_token_accuracy": 0.22246488630771638,
|
|
"num_tokens": 32603197.0,
|
|
"step": 17725
|
|
},
|
|
{
|
|
"entropy": 5.237840175628662,
|
|
"epoch": 1.4809555629802873,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00047831095616298225,
|
|
"loss": 4.8099,
|
|
"mean_token_accuracy": 0.2179470494389534,
|
|
"num_tokens": 32612882.0,
|
|
"step": 17730
|
|
},
|
|
{
|
|
"entropy": 5.305687284469604,
|
|
"epoch": 1.4813732041430003,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004782982018701444,
|
|
"loss": 4.8242,
|
|
"mean_token_accuracy": 0.2221212312579155,
|
|
"num_tokens": 32622425.0,
|
|
"step": 17735
|
|
},
|
|
{
|
|
"entropy": 5.417631959915161,
|
|
"epoch": 1.4817908453057134,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004782854440183268,
|
|
"loss": 4.9064,
|
|
"mean_token_accuracy": 0.21992482990026474,
|
|
"num_tokens": 32631295.0,
|
|
"step": 17740
|
|
},
|
|
{
|
|
"entropy": 5.410921812057495,
|
|
"epoch": 1.4822084864684264,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004782726826077528,
|
|
"loss": 4.9023,
|
|
"mean_token_accuracy": 0.2143973708152771,
|
|
"num_tokens": 32639476.0,
|
|
"step": 17745
|
|
},
|
|
{
|
|
"entropy": 5.323650121688843,
|
|
"epoch": 1.4826261276311392,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00047825991763864587,
|
|
"loss": 4.8289,
|
|
"mean_token_accuracy": 0.219064624607563,
|
|
"num_tokens": 32648704.0,
|
|
"step": 17750
|
|
},
|
|
{
|
|
"entropy": 5.303648138046265,
|
|
"epoch": 1.4830437687938522,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00047824714911122934,
|
|
"loss": 4.9191,
|
|
"mean_token_accuracy": 0.21573130190372466,
|
|
"num_tokens": 32658258.0,
|
|
"step": 17755
|
|
},
|
|
{
|
|
"entropy": 5.290957641601563,
|
|
"epoch": 1.4834614099565653,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00047823437702572684,
|
|
"loss": 4.8717,
|
|
"mean_token_accuracy": 0.21896481812000274,
|
|
"num_tokens": 32668002.0,
|
|
"step": 17760
|
|
},
|
|
{
|
|
"entropy": 5.347312498092651,
|
|
"epoch": 1.4838790511192783,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000478221601382362,
|
|
"loss": 4.9082,
|
|
"mean_token_accuracy": 0.21647033989429473,
|
|
"num_tokens": 32677961.0,
|
|
"step": 17765
|
|
},
|
|
{
|
|
"entropy": 5.348909759521485,
|
|
"epoch": 1.4842966922819913,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00047820882218135835,
|
|
"loss": 4.7863,
|
|
"mean_token_accuracy": 0.2241797149181366,
|
|
"num_tokens": 32687523.0,
|
|
"step": 17770
|
|
},
|
|
{
|
|
"entropy": 5.259199619293213,
|
|
"epoch": 1.4847143334447044,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00047819603942293964,
|
|
"loss": 4.7735,
|
|
"mean_token_accuracy": 0.22263827174901962,
|
|
"num_tokens": 32696563.0,
|
|
"step": 17775
|
|
},
|
|
{
|
|
"entropy": 5.327606725692749,
|
|
"epoch": 1.4851319746074174,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004781832531073297,
|
|
"loss": 4.8536,
|
|
"mean_token_accuracy": 0.21618568450212478,
|
|
"num_tokens": 32704928.0,
|
|
"step": 17780
|
|
},
|
|
{
|
|
"entropy": 5.386528158187867,
|
|
"epoch": 1.4855496157701302,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00047817046323475246,
|
|
"loss": 4.8674,
|
|
"mean_token_accuracy": 0.21065648049116134,
|
|
"num_tokens": 32714228.0,
|
|
"step": 17785
|
|
},
|
|
{
|
|
"entropy": 5.344082927703857,
|
|
"epoch": 1.4859672569328433,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004781576698054316,
|
|
"loss": 4.8212,
|
|
"mean_token_accuracy": 0.21618413776159287,
|
|
"num_tokens": 32724164.0,
|
|
"step": 17790
|
|
},
|
|
{
|
|
"entropy": 5.254276752471924,
|
|
"epoch": 1.4863848980955563,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004781448728195912,
|
|
"loss": 4.8397,
|
|
"mean_token_accuracy": 0.22368219792842864,
|
|
"num_tokens": 32732516.0,
|
|
"step": 17795
|
|
},
|
|
{
|
|
"entropy": 5.342838478088379,
|
|
"epoch": 1.4868025392582693,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00047813207227745527,
|
|
"loss": 4.9978,
|
|
"mean_token_accuracy": 0.2065657764673233,
|
|
"num_tokens": 32741819.0,
|
|
"step": 17800
|
|
},
|
|
{
|
|
"entropy": 5.324761056900025,
|
|
"epoch": 1.4872201804209824,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00047811926817924785,
|
|
"loss": 4.7769,
|
|
"mean_token_accuracy": 0.22971998155117035,
|
|
"num_tokens": 32751255.0,
|
|
"step": 17805
|
|
},
|
|
{
|
|
"entropy": 5.417238855361939,
|
|
"epoch": 1.4876378215836952,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00047810646052519324,
|
|
"loss": 4.9334,
|
|
"mean_token_accuracy": 0.2119215175509453,
|
|
"num_tokens": 32760275.0,
|
|
"step": 17810
|
|
},
|
|
{
|
|
"entropy": 5.335812711715699,
|
|
"epoch": 1.4880554627464082,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004780936493155155,
|
|
"loss": 4.8372,
|
|
"mean_token_accuracy": 0.22126812487840652,
|
|
"num_tokens": 32769146.0,
|
|
"step": 17815
|
|
},
|
|
{
|
|
"entropy": 5.336604070663452,
|
|
"epoch": 1.4884731039091212,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00047808083455043893,
|
|
"loss": 4.9383,
|
|
"mean_token_accuracy": 0.21594365537166596,
|
|
"num_tokens": 32778523.0,
|
|
"step": 17820
|
|
},
|
|
{
|
|
"entropy": 5.329917764663696,
|
|
"epoch": 1.4888907450718343,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00047806801623018804,
|
|
"loss": 4.7042,
|
|
"mean_token_accuracy": 0.22859150916337967,
|
|
"num_tokens": 32786746.0,
|
|
"step": 17825
|
|
},
|
|
{
|
|
"entropy": 5.323763704299926,
|
|
"epoch": 1.4893083862345473,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000478055194354987,
|
|
"loss": 4.815,
|
|
"mean_token_accuracy": 0.22542649358510972,
|
|
"num_tokens": 32796396.0,
|
|
"step": 17830
|
|
},
|
|
{
|
|
"entropy": 5.231429529190064,
|
|
"epoch": 1.4897260273972603,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00047804236892506034,
|
|
"loss": 4.8606,
|
|
"mean_token_accuracy": 0.22009647339582444,
|
|
"num_tokens": 32806329.0,
|
|
"step": 17835
|
|
},
|
|
{
|
|
"entropy": 5.286439037322998,
|
|
"epoch": 1.4901436685599734,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00047802953994063266,
|
|
"loss": 4.8146,
|
|
"mean_token_accuracy": 0.21845298409461975,
|
|
"num_tokens": 32815959.0,
|
|
"step": 17840
|
|
},
|
|
{
|
|
"entropy": 5.34973177909851,
|
|
"epoch": 1.4905613097226862,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00047801670740192843,
|
|
"loss": 4.7901,
|
|
"mean_token_accuracy": 0.2225259393453598,
|
|
"num_tokens": 32824762.0,
|
|
"step": 17845
|
|
},
|
|
{
|
|
"entropy": 5.241253471374511,
|
|
"epoch": 1.4909789508853992,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00047800387130917245,
|
|
"loss": 4.7405,
|
|
"mean_token_accuracy": 0.22473234832286834,
|
|
"num_tokens": 32833949.0,
|
|
"step": 17850
|
|
},
|
|
{
|
|
"entropy": 5.30847134590149,
|
|
"epoch": 1.4913965920481123,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00047799103166258926,
|
|
"loss": 4.8772,
|
|
"mean_token_accuracy": 0.2118741050362587,
|
|
"num_tokens": 32843428.0,
|
|
"step": 17855
|
|
},
|
|
{
|
|
"entropy": 5.387098789215088,
|
|
"epoch": 1.4918142332108253,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00047797818846240383,
|
|
"loss": 4.9828,
|
|
"mean_token_accuracy": 0.21071484535932541,
|
|
"num_tokens": 32853878.0,
|
|
"step": 17860
|
|
},
|
|
{
|
|
"entropy": 5.309144020080566,
|
|
"epoch": 1.4922318743735383,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004779653417088408,
|
|
"loss": 4.8404,
|
|
"mean_token_accuracy": 0.2140129715204239,
|
|
"num_tokens": 32863011.0,
|
|
"step": 17865
|
|
},
|
|
{
|
|
"entropy": 5.357756233215332,
|
|
"epoch": 1.4926495155362511,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00047795249140212523,
|
|
"loss": 4.845,
|
|
"mean_token_accuracy": 0.21871012896299363,
|
|
"num_tokens": 32872238.0,
|
|
"step": 17870
|
|
},
|
|
{
|
|
"entropy": 5.338819217681885,
|
|
"epoch": 1.4930671566989642,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00047793963754248195,
|
|
"loss": 4.8348,
|
|
"mean_token_accuracy": 0.21457004249095918,
|
|
"num_tokens": 32880382.0,
|
|
"step": 17875
|
|
},
|
|
{
|
|
"entropy": 5.348593044281006,
|
|
"epoch": 1.4934847978616772,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000477926780130136,
|
|
"loss": 4.8514,
|
|
"mean_token_accuracy": 0.22321203649044036,
|
|
"num_tokens": 32889199.0,
|
|
"step": 17880
|
|
},
|
|
{
|
|
"entropy": 5.400257873535156,
|
|
"epoch": 1.4939024390243902,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00047791391916531255,
|
|
"loss": 4.9765,
|
|
"mean_token_accuracy": 0.20836299806833267,
|
|
"num_tokens": 32898867.0,
|
|
"step": 17885
|
|
},
|
|
{
|
|
"entropy": 5.407901096343994,
|
|
"epoch": 1.4943200801871033,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004779010546482367,
|
|
"loss": 4.9875,
|
|
"mean_token_accuracy": 0.20644728541374208,
|
|
"num_tokens": 32907947.0,
|
|
"step": 17890
|
|
},
|
|
{
|
|
"entropy": 5.37162971496582,
|
|
"epoch": 1.4947377213498163,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004778881865791337,
|
|
"loss": 4.8201,
|
|
"mean_token_accuracy": 0.21358886659145354,
|
|
"num_tokens": 32917045.0,
|
|
"step": 17895
|
|
},
|
|
{
|
|
"entropy": 5.278619909286499,
|
|
"epoch": 1.4951553625125293,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00047787531495822866,
|
|
"loss": 4.7806,
|
|
"mean_token_accuracy": 0.2218656212091446,
|
|
"num_tokens": 32926644.0,
|
|
"step": 17900
|
|
},
|
|
{
|
|
"entropy": 5.2850971698760985,
|
|
"epoch": 1.4955730036752422,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00047786243978574706,
|
|
"loss": 4.8579,
|
|
"mean_token_accuracy": 0.21520263254642485,
|
|
"num_tokens": 32935920.0,
|
|
"step": 17905
|
|
},
|
|
{
|
|
"entropy": 5.328862047195434,
|
|
"epoch": 1.4959906448379552,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00047784956106191435,
|
|
"loss": 4.846,
|
|
"mean_token_accuracy": 0.2176906794309616,
|
|
"num_tokens": 32945561.0,
|
|
"step": 17910
|
|
},
|
|
{
|
|
"entropy": 5.306959819793701,
|
|
"epoch": 1.4964082860006682,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004778366787869559,
|
|
"loss": 4.7949,
|
|
"mean_token_accuracy": 0.22229286432266235,
|
|
"num_tokens": 32955531.0,
|
|
"step": 17915
|
|
},
|
|
{
|
|
"entropy": 5.242870330810547,
|
|
"epoch": 1.4968259271633813,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004778237929610971,
|
|
"loss": 4.6715,
|
|
"mean_token_accuracy": 0.21920000463724137,
|
|
"num_tokens": 32964001.0,
|
|
"step": 17920
|
|
},
|
|
{
|
|
"entropy": 5.317532157897949,
|
|
"epoch": 1.4972435683260943,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004778109035845638,
|
|
"loss": 4.8987,
|
|
"mean_token_accuracy": 0.21592184603214265,
|
|
"num_tokens": 32973707.0,
|
|
"step": 17925
|
|
},
|
|
{
|
|
"entropy": 5.340377759933472,
|
|
"epoch": 1.497661209488807,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00047779801065758146,
|
|
"loss": 4.8495,
|
|
"mean_token_accuracy": 0.21607148349285127,
|
|
"num_tokens": 32983029.0,
|
|
"step": 17930
|
|
},
|
|
{
|
|
"entropy": 5.353391790390015,
|
|
"epoch": 1.4980788506515201,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004777851141803758,
|
|
"loss": 4.8335,
|
|
"mean_token_accuracy": 0.22063299417495727,
|
|
"num_tokens": 32992351.0,
|
|
"step": 17935
|
|
},
|
|
{
|
|
"entropy": 5.221031570434571,
|
|
"epoch": 1.4984964918142332,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004777722141531727,
|
|
"loss": 4.6869,
|
|
"mean_token_accuracy": 0.23361383080482484,
|
|
"num_tokens": 33001090.0,
|
|
"step": 17940
|
|
},
|
|
{
|
|
"entropy": 5.320518207550049,
|
|
"epoch": 1.4989141329769462,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00047775931057619786,
|
|
"loss": 4.9113,
|
|
"mean_token_accuracy": 0.2086124137043953,
|
|
"num_tokens": 33010294.0,
|
|
"step": 17945
|
|
},
|
|
{
|
|
"entropy": 5.333424520492554,
|
|
"epoch": 1.4993317741396592,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004777464034496773,
|
|
"loss": 4.8239,
|
|
"mean_token_accuracy": 0.22160811275243758,
|
|
"num_tokens": 33018633.0,
|
|
"step": 17950
|
|
},
|
|
{
|
|
"entropy": 5.316374826431274,
|
|
"epoch": 1.4997494153023723,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004777334927738368,
|
|
"loss": 4.9032,
|
|
"mean_token_accuracy": 0.2155502289533615,
|
|
"num_tokens": 33028291.0,
|
|
"step": 17955
|
|
},
|
|
{
|
|
"entropy": 5.337996530532837,
|
|
"epoch": 1.5001670564650853,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00047772057854890247,
|
|
"loss": 4.8012,
|
|
"mean_token_accuracy": 0.21713503152132035,
|
|
"num_tokens": 33036603.0,
|
|
"step": 17960
|
|
},
|
|
{
|
|
"entropy": 5.32570071220398,
|
|
"epoch": 1.5005846976277981,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00047770766077510045,
|
|
"loss": 4.8361,
|
|
"mean_token_accuracy": 0.2179764837026596,
|
|
"num_tokens": 33045329.0,
|
|
"step": 17965
|
|
},
|
|
{
|
|
"entropy": 5.280401420593262,
|
|
"epoch": 1.5010023387905111,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00047769473945265685,
|
|
"loss": 4.7965,
|
|
"mean_token_accuracy": 0.22048027366399764,
|
|
"num_tokens": 33054753.0,
|
|
"step": 17970
|
|
},
|
|
{
|
|
"entropy": 5.283018350601196,
|
|
"epoch": 1.5014199799532242,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004776818145817979,
|
|
"loss": 4.7956,
|
|
"mean_token_accuracy": 0.23064898401498796,
|
|
"num_tokens": 33063469.0,
|
|
"step": 17975
|
|
},
|
|
{
|
|
"entropy": 5.328337097167969,
|
|
"epoch": 1.5018376211159372,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00047766888616274973,
|
|
"loss": 4.8801,
|
|
"mean_token_accuracy": 0.21040522307157516,
|
|
"num_tokens": 33072247.0,
|
|
"step": 17980
|
|
},
|
|
{
|
|
"entropy": 5.32094554901123,
|
|
"epoch": 1.5022552622786502,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00047765595419573876,
|
|
"loss": 4.8792,
|
|
"mean_token_accuracy": 0.21453277468681337,
|
|
"num_tokens": 33083505.0,
|
|
"step": 17985
|
|
},
|
|
{
|
|
"entropy": 5.343996334075928,
|
|
"epoch": 1.502672903441363,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00047764301868099136,
|
|
"loss": 4.8631,
|
|
"mean_token_accuracy": 0.22181545197963715,
|
|
"num_tokens": 33094104.0,
|
|
"step": 17990
|
|
},
|
|
{
|
|
"entropy": 5.291272306442261,
|
|
"epoch": 1.5030905446040763,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00047763007961873407,
|
|
"loss": 4.8263,
|
|
"mean_token_accuracy": 0.21918032318353653,
|
|
"num_tokens": 33102936.0,
|
|
"step": 17995
|
|
},
|
|
{
|
|
"entropy": 5.34190182685852,
|
|
"epoch": 1.5035081857667891,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004776171370091933,
|
|
"loss": 4.8104,
|
|
"mean_token_accuracy": 0.22071177363395691,
|
|
"num_tokens": 33111648.0,
|
|
"step": 18000
|
|
},
|
|
{
|
|
"epoch": 1.5035081857667891,
|
|
"eval_entropy": 5.050196050057293,
|
|
"eval_loss": 4.830212116241455,
|
|
"eval_mean_token_accuracy": 0.23063150590675863,
|
|
"eval_num_tokens": 33111648.0,
|
|
"eval_runtime": 20.8484,
|
|
"eval_samples_per_second": 1811.313,
|
|
"eval_steps_per_second": 226.444,
|
|
"step": 18000
|
|
},
|
|
{
|
|
"entropy": 5.3349769592285154,
|
|
"epoch": 1.5039258269295022,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004776041908525956,
|
|
"loss": 4.8549,
|
|
"mean_token_accuracy": 0.21426361054182053,
|
|
"num_tokens": 33120235.0,
|
|
"step": 18005
|
|
},
|
|
{
|
|
"entropy": 5.267163944244385,
|
|
"epoch": 1.5043434680922152,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004775912411491677,
|
|
"loss": 4.8147,
|
|
"mean_token_accuracy": 0.22418376058340073,
|
|
"num_tokens": 33129152.0,
|
|
"step": 18010
|
|
},
|
|
{
|
|
"entropy": 5.219419145584107,
|
|
"epoch": 1.504761109254928,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004775782878991363,
|
|
"loss": 4.7598,
|
|
"mean_token_accuracy": 0.2248355343937874,
|
|
"num_tokens": 33137907.0,
|
|
"step": 18015
|
|
},
|
|
{
|
|
"entropy": 5.246989679336548,
|
|
"epoch": 1.5051787504176413,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00047756533110272813,
|
|
"loss": 4.811,
|
|
"mean_token_accuracy": 0.2227573111653328,
|
|
"num_tokens": 33146001.0,
|
|
"step": 18020
|
|
},
|
|
{
|
|
"entropy": 5.311467123031616,
|
|
"epoch": 1.505596391580354,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00047755237076016997,
|
|
"loss": 4.8239,
|
|
"mean_token_accuracy": 0.21507411301136017,
|
|
"num_tokens": 33155389.0,
|
|
"step": 18025
|
|
},
|
|
{
|
|
"entropy": 5.326077270507812,
|
|
"epoch": 1.506014032743067,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00047753940687168876,
|
|
"loss": 4.8933,
|
|
"mean_token_accuracy": 0.21505793780088425,
|
|
"num_tokens": 33164965.0,
|
|
"step": 18030
|
|
},
|
|
{
|
|
"entropy": 5.322560596466064,
|
|
"epoch": 1.5064316739057801,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004775264394375114,
|
|
"loss": 4.912,
|
|
"mean_token_accuracy": 0.21179645806550979,
|
|
"num_tokens": 33174590.0,
|
|
"step": 18035
|
|
},
|
|
{
|
|
"entropy": 5.300753927230835,
|
|
"epoch": 1.5068493150684932,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000477513468457865,
|
|
"loss": 4.8129,
|
|
"mean_token_accuracy": 0.2112202301621437,
|
|
"num_tokens": 33183063.0,
|
|
"step": 18040
|
|
},
|
|
{
|
|
"entropy": 5.355288505554199,
|
|
"epoch": 1.5072669562312062,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00047750049393297656,
|
|
"loss": 4.9527,
|
|
"mean_token_accuracy": 0.2116619184613228,
|
|
"num_tokens": 33192198.0,
|
|
"step": 18045
|
|
},
|
|
{
|
|
"entropy": 5.405105495452881,
|
|
"epoch": 1.507684597393919,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00047748751586307314,
|
|
"loss": 4.9443,
|
|
"mean_token_accuracy": 0.20851942896842957,
|
|
"num_tokens": 33202445.0,
|
|
"step": 18050
|
|
},
|
|
{
|
|
"entropy": 5.3588121891021725,
|
|
"epoch": 1.5081022385566323,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00047747453424838216,
|
|
"loss": 4.8418,
|
|
"mean_token_accuracy": 0.21619374603033065,
|
|
"num_tokens": 33211017.0,
|
|
"step": 18055
|
|
},
|
|
{
|
|
"entropy": 5.234523010253906,
|
|
"epoch": 1.508519879719345,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00047746154908913065,
|
|
"loss": 4.8183,
|
|
"mean_token_accuracy": 0.22615695148706436,
|
|
"num_tokens": 33220345.0,
|
|
"step": 18060
|
|
},
|
|
{
|
|
"entropy": 5.363945865631104,
|
|
"epoch": 1.5089375208820581,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000477448560385546,
|
|
"loss": 4.8377,
|
|
"mean_token_accuracy": 0.22392840683460236,
|
|
"num_tokens": 33229849.0,
|
|
"step": 18065
|
|
},
|
|
{
|
|
"entropy": 5.318149995803833,
|
|
"epoch": 1.5093551620447712,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004774355681378557,
|
|
"loss": 4.7818,
|
|
"mean_token_accuracy": 0.22067250907421113,
|
|
"num_tokens": 33239079.0,
|
|
"step": 18070
|
|
},
|
|
{
|
|
"entropy": 5.225163984298706,
|
|
"epoch": 1.509772803207484,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00047742257234628703,
|
|
"loss": 4.7555,
|
|
"mean_token_accuracy": 0.22560417801141738,
|
|
"num_tokens": 33248048.0,
|
|
"step": 18075
|
|
},
|
|
{
|
|
"entropy": 5.200251913070678,
|
|
"epoch": 1.5101904443701972,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00047740957301106756,
|
|
"loss": 4.7853,
|
|
"mean_token_accuracy": 0.22395414412021636,
|
|
"num_tokens": 33257173.0,
|
|
"step": 18080
|
|
},
|
|
{
|
|
"entropy": 5.294340038299561,
|
|
"epoch": 1.51060808553291,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000477396570132425,
|
|
"loss": 4.8571,
|
|
"mean_token_accuracy": 0.21561261564493178,
|
|
"num_tokens": 33266800.0,
|
|
"step": 18085
|
|
},
|
|
{
|
|
"entropy": 5.397753524780273,
|
|
"epoch": 1.511025726695623,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00047738356371058673,
|
|
"loss": 4.918,
|
|
"mean_token_accuracy": 0.20780560672283171,
|
|
"num_tokens": 33276061.0,
|
|
"step": 18090
|
|
},
|
|
{
|
|
"entropy": 5.296290540695191,
|
|
"epoch": 1.511443367858336,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004773705537457806,
|
|
"loss": 4.7301,
|
|
"mean_token_accuracy": 0.23197001069784165,
|
|
"num_tokens": 33284786.0,
|
|
"step": 18095
|
|
},
|
|
{
|
|
"entropy": 5.2366838455200195,
|
|
"epoch": 1.5118610090210491,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00047735754023823433,
|
|
"loss": 4.8167,
|
|
"mean_token_accuracy": 0.22045001685619353,
|
|
"num_tokens": 33293849.0,
|
|
"step": 18100
|
|
},
|
|
{
|
|
"entropy": 5.207247686386109,
|
|
"epoch": 1.5122786501837622,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004773445231881757,
|
|
"loss": 4.7111,
|
|
"mean_token_accuracy": 0.2299417957663536,
|
|
"num_tokens": 33303387.0,
|
|
"step": 18105
|
|
},
|
|
{
|
|
"entropy": 5.275587034225464,
|
|
"epoch": 1.512696291346475,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00047733150259583274,
|
|
"loss": 4.7518,
|
|
"mean_token_accuracy": 0.2173924043774605,
|
|
"num_tokens": 33312502.0,
|
|
"step": 18110
|
|
},
|
|
{
|
|
"entropy": 5.249146842956543,
|
|
"epoch": 1.5131139325091882,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00047731847846143325,
|
|
"loss": 4.7762,
|
|
"mean_token_accuracy": 0.22376732230186464,
|
|
"num_tokens": 33321909.0,
|
|
"step": 18115
|
|
},
|
|
{
|
|
"entropy": 5.21838059425354,
|
|
"epoch": 1.513531573671901,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004773054507852052,
|
|
"loss": 4.7533,
|
|
"mean_token_accuracy": 0.22290110290050508,
|
|
"num_tokens": 33331249.0,
|
|
"step": 18120
|
|
},
|
|
{
|
|
"entropy": 5.276964616775513,
|
|
"epoch": 1.513949214834614,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004772924195673768,
|
|
"loss": 4.8143,
|
|
"mean_token_accuracy": 0.21970333009958268,
|
|
"num_tokens": 33340850.0,
|
|
"step": 18125
|
|
},
|
|
{
|
|
"entropy": 5.352364921569825,
|
|
"epoch": 1.5143668559973271,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00047727938480817604,
|
|
"loss": 4.864,
|
|
"mean_token_accuracy": 0.212345689535141,
|
|
"num_tokens": 33350429.0,
|
|
"step": 18130
|
|
},
|
|
{
|
|
"entropy": 5.339038515090943,
|
|
"epoch": 1.51478449716004,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00047726634650783117,
|
|
"loss": 4.8452,
|
|
"mean_token_accuracy": 0.21970382630825042,
|
|
"num_tokens": 33359687.0,
|
|
"step": 18135
|
|
},
|
|
{
|
|
"entropy": 5.318694114685059,
|
|
"epoch": 1.5152021383227532,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004772533046665705,
|
|
"loss": 4.8726,
|
|
"mean_token_accuracy": 0.2181195929646492,
|
|
"num_tokens": 33368177.0,
|
|
"step": 18140
|
|
},
|
|
{
|
|
"entropy": 5.292257642745971,
|
|
"epoch": 1.515619779485466,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004772402592846222,
|
|
"loss": 4.8803,
|
|
"mean_token_accuracy": 0.21666521579027176,
|
|
"num_tokens": 33376604.0,
|
|
"step": 18145
|
|
},
|
|
{
|
|
"entropy": 5.277176094055176,
|
|
"epoch": 1.516037420648179,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00047722721036221467,
|
|
"loss": 4.7811,
|
|
"mean_token_accuracy": 0.22125290483236312,
|
|
"num_tokens": 33385488.0,
|
|
"step": 18150
|
|
},
|
|
{
|
|
"entropy": 5.330071926116943,
|
|
"epoch": 1.516455061810892,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004772141578995765,
|
|
"loss": 4.9008,
|
|
"mean_token_accuracy": 0.21278824359178544,
|
|
"num_tokens": 33394524.0,
|
|
"step": 18155
|
|
},
|
|
{
|
|
"entropy": 5.330311584472656,
|
|
"epoch": 1.516872702973605,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00047720110189693605,
|
|
"loss": 4.8554,
|
|
"mean_token_accuracy": 0.21886575371026992,
|
|
"num_tokens": 33404300.0,
|
|
"step": 18160
|
|
},
|
|
{
|
|
"entropy": 5.285374546051026,
|
|
"epoch": 1.5172903441363181,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00047718804235452193,
|
|
"loss": 4.7974,
|
|
"mean_token_accuracy": 0.2216798931360245,
|
|
"num_tokens": 33414050.0,
|
|
"step": 18165
|
|
},
|
|
{
|
|
"entropy": 5.320185756683349,
|
|
"epoch": 1.517707985299031,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004771749792725628,
|
|
"loss": 4.9275,
|
|
"mean_token_accuracy": 0.21704522669315338,
|
|
"num_tokens": 33423981.0,
|
|
"step": 18170
|
|
},
|
|
{
|
|
"entropy": 5.2635582447052,
|
|
"epoch": 1.5181256264617442,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004771619126512873,
|
|
"loss": 4.6773,
|
|
"mean_token_accuracy": 0.23099760860204696,
|
|
"num_tokens": 33433104.0,
|
|
"step": 18175
|
|
},
|
|
{
|
|
"entropy": 5.341131210327148,
|
|
"epoch": 1.518543267624457,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00047714884249092413,
|
|
"loss": 4.8886,
|
|
"mean_token_accuracy": 0.21285178363323212,
|
|
"num_tokens": 33442034.0,
|
|
"step": 18180
|
|
},
|
|
{
|
|
"entropy": 5.249390935897827,
|
|
"epoch": 1.51896090878717,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004771357687917021,
|
|
"loss": 4.797,
|
|
"mean_token_accuracy": 0.2201176255941391,
|
|
"num_tokens": 33450431.0,
|
|
"step": 18185
|
|
},
|
|
{
|
|
"entropy": 5.344406366348267,
|
|
"epoch": 1.519378549949883,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00047712269155385017,
|
|
"loss": 4.9241,
|
|
"mean_token_accuracy": 0.21565226912498475,
|
|
"num_tokens": 33459790.0,
|
|
"step": 18190
|
|
},
|
|
{
|
|
"entropy": 5.333073472976684,
|
|
"epoch": 1.519796191112596,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00047710961077759736,
|
|
"loss": 4.9106,
|
|
"mean_token_accuracy": 0.218340165913105,
|
|
"num_tokens": 33468802.0,
|
|
"step": 18195
|
|
},
|
|
{
|
|
"entropy": 5.2900416374206545,
|
|
"epoch": 1.5202138322753092,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00047709652646317236,
|
|
"loss": 4.7843,
|
|
"mean_token_accuracy": 0.22159695625305176,
|
|
"num_tokens": 33477756.0,
|
|
"step": 18200
|
|
},
|
|
{
|
|
"entropy": 5.293024492263794,
|
|
"epoch": 1.520631473438022,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00047708343861080447,
|
|
"loss": 4.8947,
|
|
"mean_token_accuracy": 0.2125212535262108,
|
|
"num_tokens": 33487410.0,
|
|
"step": 18205
|
|
},
|
|
{
|
|
"entropy": 5.3590864658355715,
|
|
"epoch": 1.521049114600735,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004770703472207227,
|
|
"loss": 4.8301,
|
|
"mean_token_accuracy": 0.2167205184698105,
|
|
"num_tokens": 33496682.0,
|
|
"step": 18210
|
|
},
|
|
{
|
|
"entropy": 5.422993564605713,
|
|
"epoch": 1.521466755763448,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004770572522931563,
|
|
"loss": 4.9696,
|
|
"mean_token_accuracy": 0.20347459763288497,
|
|
"num_tokens": 33505754.0,
|
|
"step": 18215
|
|
},
|
|
{
|
|
"entropy": 5.305544185638428,
|
|
"epoch": 1.521884396926161,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004770441538283345,
|
|
"loss": 4.8557,
|
|
"mean_token_accuracy": 0.22179422974586488,
|
|
"num_tokens": 33514904.0,
|
|
"step": 18220
|
|
},
|
|
{
|
|
"entropy": 5.292533493041992,
|
|
"epoch": 1.522302038088874,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00047703105182648656,
|
|
"loss": 4.8066,
|
|
"mean_token_accuracy": 0.22165827602148055,
|
|
"num_tokens": 33523684.0,
|
|
"step": 18225
|
|
},
|
|
{
|
|
"entropy": 5.299337673187256,
|
|
"epoch": 1.522719679251587,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004770179462878419,
|
|
"loss": 4.8662,
|
|
"mean_token_accuracy": 0.21463283002376557,
|
|
"num_tokens": 33533066.0,
|
|
"step": 18230
|
|
},
|
|
{
|
|
"entropy": 5.295416831970215,
|
|
"epoch": 1.5231373204143002,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004770048372126299,
|
|
"loss": 4.817,
|
|
"mean_token_accuracy": 0.2124296694993973,
|
|
"num_tokens": 33542048.0,
|
|
"step": 18235
|
|
},
|
|
{
|
|
"entropy": 5.281306648254395,
|
|
"epoch": 1.523554961577013,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004769917246010801,
|
|
"loss": 4.7262,
|
|
"mean_token_accuracy": 0.22453867495059968,
|
|
"num_tokens": 33550785.0,
|
|
"step": 18240
|
|
},
|
|
{
|
|
"entropy": 5.314665031433106,
|
|
"epoch": 1.523972602739726,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004769786084534219,
|
|
"loss": 4.8021,
|
|
"mean_token_accuracy": 0.21295356452465058,
|
|
"num_tokens": 33560141.0,
|
|
"step": 18245
|
|
},
|
|
{
|
|
"entropy": 5.347321939468384,
|
|
"epoch": 1.524390243902439,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00047696548876988517,
|
|
"loss": 4.8632,
|
|
"mean_token_accuracy": 0.21735114157199859,
|
|
"num_tokens": 33568866.0,
|
|
"step": 18250
|
|
},
|
|
{
|
|
"entropy": 5.299843120574951,
|
|
"epoch": 1.5248078850651519,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004769523655506994,
|
|
"loss": 4.8286,
|
|
"mean_token_accuracy": 0.2179970696568489,
|
|
"num_tokens": 33579217.0,
|
|
"step": 18255
|
|
},
|
|
{
|
|
"entropy": 5.369073867797852,
|
|
"epoch": 1.5252255262278651,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004769392387960944,
|
|
"loss": 4.9337,
|
|
"mean_token_accuracy": 0.20669141709804534,
|
|
"num_tokens": 33589608.0,
|
|
"step": 18260
|
|
},
|
|
{
|
|
"entropy": 5.361790990829467,
|
|
"epoch": 1.525643167390578,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004769261085063,
|
|
"loss": 4.8569,
|
|
"mean_token_accuracy": 0.21284402310848236,
|
|
"num_tokens": 33599263.0,
|
|
"step": 18265
|
|
},
|
|
{
|
|
"entropy": 5.247328424453736,
|
|
"epoch": 1.526060808553291,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00047691297468154594,
|
|
"loss": 4.8244,
|
|
"mean_token_accuracy": 0.2224361315369606,
|
|
"num_tokens": 33607946.0,
|
|
"step": 18270
|
|
},
|
|
{
|
|
"entropy": 5.370623922348022,
|
|
"epoch": 1.526478449716004,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004768998373220622,
|
|
"loss": 4.9299,
|
|
"mean_token_accuracy": 0.2169346272945404,
|
|
"num_tokens": 33617194.0,
|
|
"step": 18275
|
|
},
|
|
{
|
|
"entropy": 5.327069425582886,
|
|
"epoch": 1.526896090878717,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004768866964280789,
|
|
"loss": 4.8738,
|
|
"mean_token_accuracy": 0.21386606693267823,
|
|
"num_tokens": 33626796.0,
|
|
"step": 18280
|
|
},
|
|
{
|
|
"entropy": 5.323105382919311,
|
|
"epoch": 1.52731373204143,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00047687355199982584,
|
|
"loss": 4.8152,
|
|
"mean_token_accuracy": 0.21415287107229233,
|
|
"num_tokens": 33636290.0,
|
|
"step": 18285
|
|
},
|
|
{
|
|
"entropy": 5.302848863601684,
|
|
"epoch": 1.5277313732041429,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004768604040375333,
|
|
"loss": 4.8483,
|
|
"mean_token_accuracy": 0.22405791133642197,
|
|
"num_tokens": 33644489.0,
|
|
"step": 18290
|
|
},
|
|
{
|
|
"entropy": 5.24062147140503,
|
|
"epoch": 1.5281490143668561,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00047684725254143137,
|
|
"loss": 4.7168,
|
|
"mean_token_accuracy": 0.2266963928937912,
|
|
"num_tokens": 33653677.0,
|
|
"step": 18295
|
|
},
|
|
{
|
|
"entropy": 5.279771423339843,
|
|
"epoch": 1.528566655529569,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004768340975117504,
|
|
"loss": 4.8019,
|
|
"mean_token_accuracy": 0.22480280548334122,
|
|
"num_tokens": 33662787.0,
|
|
"step": 18300
|
|
},
|
|
{
|
|
"entropy": 5.337520456314087,
|
|
"epoch": 1.528984296692282,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004768209389487205,
|
|
"loss": 4.8387,
|
|
"mean_token_accuracy": 0.23450133800506592,
|
|
"num_tokens": 33671167.0,
|
|
"step": 18305
|
|
},
|
|
{
|
|
"entropy": 5.309630060195923,
|
|
"epoch": 1.529401937854995,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004768077768525722,
|
|
"loss": 4.7504,
|
|
"mean_token_accuracy": 0.22885807752609252,
|
|
"num_tokens": 33679253.0,
|
|
"step": 18310
|
|
},
|
|
{
|
|
"entropy": 5.376660299301148,
|
|
"epoch": 1.5298195790177078,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004767946112235359,
|
|
"loss": 4.8333,
|
|
"mean_token_accuracy": 0.21690309494733812,
|
|
"num_tokens": 33688863.0,
|
|
"step": 18315
|
|
},
|
|
{
|
|
"entropy": 5.3071582317352295,
|
|
"epoch": 1.530237220180421,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000476781442061842,
|
|
"loss": 4.8244,
|
|
"mean_token_accuracy": 0.2180435225367546,
|
|
"num_tokens": 33697201.0,
|
|
"step": 18320
|
|
},
|
|
{
|
|
"entropy": 5.369924163818359,
|
|
"epoch": 1.5306548613431339,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00047676826936772097,
|
|
"loss": 4.9054,
|
|
"mean_token_accuracy": 0.21575696915388107,
|
|
"num_tokens": 33706075.0,
|
|
"step": 18325
|
|
},
|
|
{
|
|
"entropy": 5.329788780212402,
|
|
"epoch": 1.531072502505847,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00047675509314140365,
|
|
"loss": 4.9098,
|
|
"mean_token_accuracy": 0.21088870018720626,
|
|
"num_tokens": 33715290.0,
|
|
"step": 18330
|
|
},
|
|
{
|
|
"entropy": 5.234223461151123,
|
|
"epoch": 1.53149014366856,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004767419133831206,
|
|
"loss": 4.7626,
|
|
"mean_token_accuracy": 0.22935274839401246,
|
|
"num_tokens": 33724508.0,
|
|
"step": 18335
|
|
},
|
|
{
|
|
"entropy": 5.349196481704712,
|
|
"epoch": 1.531907784831273,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00047672873009310234,
|
|
"loss": 4.9025,
|
|
"mean_token_accuracy": 0.215628083050251,
|
|
"num_tokens": 33733333.0,
|
|
"step": 18340
|
|
},
|
|
{
|
|
"entropy": 5.245912885665893,
|
|
"epoch": 1.532325425993986,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00047671554327157996,
|
|
"loss": 4.7587,
|
|
"mean_token_accuracy": 0.2279059410095215,
|
|
"num_tokens": 33741780.0,
|
|
"step": 18345
|
|
},
|
|
{
|
|
"entropy": 5.256316995620727,
|
|
"epoch": 1.5327430671566988,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00047670235291878417,
|
|
"loss": 4.7457,
|
|
"mean_token_accuracy": 0.22157856822013855,
|
|
"num_tokens": 33750259.0,
|
|
"step": 18350
|
|
},
|
|
{
|
|
"entropy": 5.321218872070313,
|
|
"epoch": 1.533160708319412,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004766891590349459,
|
|
"loss": 4.8628,
|
|
"mean_token_accuracy": 0.21117980033159256,
|
|
"num_tokens": 33760383.0,
|
|
"step": 18355
|
|
},
|
|
{
|
|
"entropy": 5.327572345733643,
|
|
"epoch": 1.533578349482125,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004766759616202961,
|
|
"loss": 4.7737,
|
|
"mean_token_accuracy": 0.22233957499265672,
|
|
"num_tokens": 33768524.0,
|
|
"step": 18360
|
|
},
|
|
{
|
|
"entropy": 5.235174226760864,
|
|
"epoch": 1.533995990644838,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004766627606750659,
|
|
"loss": 4.8163,
|
|
"mean_token_accuracy": 0.2237001821398735,
|
|
"num_tokens": 33777448.0,
|
|
"step": 18365
|
|
},
|
|
{
|
|
"entropy": 5.322753620147705,
|
|
"epoch": 1.534413631807551,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004766495561994863,
|
|
"loss": 4.8622,
|
|
"mean_token_accuracy": 0.22442371398210526,
|
|
"num_tokens": 33787316.0,
|
|
"step": 18370
|
|
},
|
|
{
|
|
"entropy": 5.3538721084594725,
|
|
"epoch": 1.534831272970264,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004766363481937885,
|
|
"loss": 4.7618,
|
|
"mean_token_accuracy": 0.22227010726928711,
|
|
"num_tokens": 33796945.0,
|
|
"step": 18375
|
|
},
|
|
{
|
|
"entropy": 5.343156909942627,
|
|
"epoch": 1.535248914132977,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00047662313665820365,
|
|
"loss": 4.913,
|
|
"mean_token_accuracy": 0.2063511610031128,
|
|
"num_tokens": 33807866.0,
|
|
"step": 18380
|
|
},
|
|
{
|
|
"entropy": 5.296334218978882,
|
|
"epoch": 1.5356665552956899,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004766099215929632,
|
|
"loss": 4.8202,
|
|
"mean_token_accuracy": 0.21674508303403855,
|
|
"num_tokens": 33817298.0,
|
|
"step": 18385
|
|
},
|
|
{
|
|
"entropy": 5.3016805171966555,
|
|
"epoch": 1.536084196458403,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00047659670299829833,
|
|
"loss": 4.7951,
|
|
"mean_token_accuracy": 0.2270212233066559,
|
|
"num_tokens": 33826552.0,
|
|
"step": 18390
|
|
},
|
|
{
|
|
"entropy": 5.261700296401978,
|
|
"epoch": 1.536501837621116,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004765834808744405,
|
|
"loss": 4.8387,
|
|
"mean_token_accuracy": 0.2165291890501976,
|
|
"num_tokens": 33836800.0,
|
|
"step": 18395
|
|
},
|
|
{
|
|
"entropy": 5.296518325805664,
|
|
"epoch": 1.536919478783829,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00047657025522162123,
|
|
"loss": 4.8054,
|
|
"mean_token_accuracy": 0.22149488776922227,
|
|
"num_tokens": 33846245.0,
|
|
"step": 18400
|
|
},
|
|
{
|
|
"entropy": 5.327144193649292,
|
|
"epoch": 1.537337119946542,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000476557026040072,
|
|
"loss": 4.7642,
|
|
"mean_token_accuracy": 0.22113107591867448,
|
|
"num_tokens": 33855100.0,
|
|
"step": 18405
|
|
},
|
|
{
|
|
"entropy": 5.220913028717041,
|
|
"epoch": 1.5377547611092548,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00047654379333002446,
|
|
"loss": 4.724,
|
|
"mean_token_accuracy": 0.22082707583904265,
|
|
"num_tokens": 33863307.0,
|
|
"step": 18410
|
|
},
|
|
{
|
|
"entropy": 5.300871706008911,
|
|
"epoch": 1.538172402271968,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00047653055709171013,
|
|
"loss": 4.8392,
|
|
"mean_token_accuracy": 0.21518849730491638,
|
|
"num_tokens": 33871891.0,
|
|
"step": 18415
|
|
},
|
|
{
|
|
"entropy": 5.280083847045899,
|
|
"epoch": 1.5385900434346809,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00047651731732536084,
|
|
"loss": 4.8319,
|
|
"mean_token_accuracy": 0.22229795157909393,
|
|
"num_tokens": 33880913.0,
|
|
"step": 18420
|
|
},
|
|
{
|
|
"entropy": 5.393218469619751,
|
|
"epoch": 1.539007684597394,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00047650407403120845,
|
|
"loss": 4.8813,
|
|
"mean_token_accuracy": 0.21166435480117798,
|
|
"num_tokens": 33889838.0,
|
|
"step": 18425
|
|
},
|
|
{
|
|
"entropy": 5.387116241455078,
|
|
"epoch": 1.539425325760107,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00047649082720948455,
|
|
"loss": 4.8928,
|
|
"mean_token_accuracy": 0.21674295663833618,
|
|
"num_tokens": 33898989.0,
|
|
"step": 18430
|
|
},
|
|
{
|
|
"entropy": 5.371487617492676,
|
|
"epoch": 1.53984296692282,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00047647757686042125,
|
|
"loss": 4.827,
|
|
"mean_token_accuracy": 0.22032123655080796,
|
|
"num_tokens": 33907884.0,
|
|
"step": 18435
|
|
},
|
|
{
|
|
"entropy": 5.317184972763061,
|
|
"epoch": 1.540260608085533,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00047646432298425047,
|
|
"loss": 4.8523,
|
|
"mean_token_accuracy": 0.2168412759900093,
|
|
"num_tokens": 33916762.0,
|
|
"step": 18440
|
|
},
|
|
{
|
|
"entropy": 5.26208872795105,
|
|
"epoch": 1.5406782492482458,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00047645106558120417,
|
|
"loss": 4.7455,
|
|
"mean_token_accuracy": 0.2267468601465225,
|
|
"num_tokens": 33925413.0,
|
|
"step": 18445
|
|
},
|
|
{
|
|
"entropy": 5.26426739692688,
|
|
"epoch": 1.541095890410959,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004764378046515145,
|
|
"loss": 4.7979,
|
|
"mean_token_accuracy": 0.22066534906625748,
|
|
"num_tokens": 33934247.0,
|
|
"step": 18450
|
|
},
|
|
{
|
|
"entropy": 5.272887134552002,
|
|
"epoch": 1.5415135315736719,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004764245401954136,
|
|
"loss": 4.7591,
|
|
"mean_token_accuracy": 0.23012458384037018,
|
|
"num_tokens": 33943610.0,
|
|
"step": 18455
|
|
},
|
|
{
|
|
"entropy": 5.4279279708862305,
|
|
"epoch": 1.541931172736385,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004764112722131337,
|
|
"loss": 5.0565,
|
|
"mean_token_accuracy": 0.1964874565601349,
|
|
"num_tokens": 33953447.0,
|
|
"step": 18460
|
|
},
|
|
{
|
|
"entropy": 5.346304082870484,
|
|
"epoch": 1.542348813899098,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00047639800070490695,
|
|
"loss": 4.872,
|
|
"mean_token_accuracy": 0.22165995389223098,
|
|
"num_tokens": 33962702.0,
|
|
"step": 18465
|
|
},
|
|
{
|
|
"entropy": 5.391213274002075,
|
|
"epoch": 1.5427664550618108,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004763847256709658,
|
|
"loss": 4.8756,
|
|
"mean_token_accuracy": 0.20810626745223998,
|
|
"num_tokens": 33972604.0,
|
|
"step": 18470
|
|
},
|
|
{
|
|
"entropy": 5.388629150390625,
|
|
"epoch": 1.543184096224524,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004763714471115427,
|
|
"loss": 4.9329,
|
|
"mean_token_accuracy": 0.2128515511751175,
|
|
"num_tokens": 33982443.0,
|
|
"step": 18475
|
|
},
|
|
{
|
|
"entropy": 5.330124950408935,
|
|
"epoch": 1.5436017373872368,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004763581650268699,
|
|
"loss": 4.8532,
|
|
"mean_token_accuracy": 0.2195114478468895,
|
|
"num_tokens": 33990688.0,
|
|
"step": 18480
|
|
},
|
|
{
|
|
"entropy": 5.344235229492187,
|
|
"epoch": 1.5440193785499499,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00047634487941718016,
|
|
"loss": 4.8759,
|
|
"mean_token_accuracy": 0.2150549829006195,
|
|
"num_tokens": 33999657.0,
|
|
"step": 18485
|
|
},
|
|
{
|
|
"entropy": 5.345328378677368,
|
|
"epoch": 1.544437019712663,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004763315902827059,
|
|
"loss": 4.9254,
|
|
"mean_token_accuracy": 0.20955876260995865,
|
|
"num_tokens": 34009842.0,
|
|
"step": 18490
|
|
},
|
|
{
|
|
"entropy": 5.450287628173828,
|
|
"epoch": 1.544854660875376,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00047631829762367976,
|
|
"loss": 4.9574,
|
|
"mean_token_accuracy": 0.20656945258378984,
|
|
"num_tokens": 34019600.0,
|
|
"step": 18495
|
|
},
|
|
{
|
|
"entropy": 5.371458053588867,
|
|
"epoch": 1.545272302038089,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004763050014403346,
|
|
"loss": 4.9248,
|
|
"mean_token_accuracy": 0.21234747022390366,
|
|
"num_tokens": 34028256.0,
|
|
"step": 18500
|
|
},
|
|
{
|
|
"entropy": 5.329504013061523,
|
|
"epoch": 1.5456899432008018,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00047629170173290296,
|
|
"loss": 4.8633,
|
|
"mean_token_accuracy": 0.2208024486899376,
|
|
"num_tokens": 34037117.0,
|
|
"step": 18505
|
|
},
|
|
{
|
|
"entropy": 5.315366888046265,
|
|
"epoch": 1.546107584363515,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00047627839850161784,
|
|
"loss": 4.8391,
|
|
"mean_token_accuracy": 0.22416990548372268,
|
|
"num_tokens": 34045697.0,
|
|
"step": 18510
|
|
},
|
|
{
|
|
"entropy": 5.413814687728882,
|
|
"epoch": 1.5465252255262278,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00047626509174671214,
|
|
"loss": 4.9567,
|
|
"mean_token_accuracy": 0.20982799530029297,
|
|
"num_tokens": 34055735.0,
|
|
"step": 18515
|
|
},
|
|
{
|
|
"entropy": 5.383724784851074,
|
|
"epoch": 1.5469428666889409,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004762517814684187,
|
|
"loss": 4.9039,
|
|
"mean_token_accuracy": 0.21378744393587112,
|
|
"num_tokens": 34065780.0,
|
|
"step": 18520
|
|
},
|
|
{
|
|
"entropy": 5.343082666397095,
|
|
"epoch": 1.547360507851654,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00047623846766697056,
|
|
"loss": 4.8237,
|
|
"mean_token_accuracy": 0.21864083409309387,
|
|
"num_tokens": 34075314.0,
|
|
"step": 18525
|
|
},
|
|
{
|
|
"entropy": 5.3669603824615475,
|
|
"epoch": 1.5477781490143667,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00047622515034260077,
|
|
"loss": 4.9087,
|
|
"mean_token_accuracy": 0.21663144379854202,
|
|
"num_tokens": 34085475.0,
|
|
"step": 18530
|
|
},
|
|
{
|
|
"entropy": 5.44616732597351,
|
|
"epoch": 1.54819579017708,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004762118294955426,
|
|
"loss": 4.8746,
|
|
"mean_token_accuracy": 0.21024168878793717,
|
|
"num_tokens": 34094758.0,
|
|
"step": 18535
|
|
},
|
|
{
|
|
"entropy": 5.398808717727661,
|
|
"epoch": 1.5486134313397928,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004761985051260291,
|
|
"loss": 4.9137,
|
|
"mean_token_accuracy": 0.21467082053422928,
|
|
"num_tokens": 34103605.0,
|
|
"step": 18540
|
|
},
|
|
{
|
|
"entropy": 5.283911085128784,
|
|
"epoch": 1.5490310725025058,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00047618517723429366,
|
|
"loss": 4.7821,
|
|
"mean_token_accuracy": 0.22228558361530304,
|
|
"num_tokens": 34112751.0,
|
|
"step": 18545
|
|
},
|
|
{
|
|
"entropy": 5.323326063156128,
|
|
"epoch": 1.5494487136652189,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00047617184582056946,
|
|
"loss": 4.8624,
|
|
"mean_token_accuracy": 0.21428562104701995,
|
|
"num_tokens": 34121814.0,
|
|
"step": 18550
|
|
},
|
|
{
|
|
"entropy": 5.284174919128418,
|
|
"epoch": 1.549866354827932,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00047615851088508995,
|
|
"loss": 4.7878,
|
|
"mean_token_accuracy": 0.22195173799991608,
|
|
"num_tokens": 34130297.0,
|
|
"step": 18555
|
|
},
|
|
{
|
|
"entropy": 5.31257176399231,
|
|
"epoch": 1.550283995990645,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00047614517242808866,
|
|
"loss": 4.7843,
|
|
"mean_token_accuracy": 0.2199394077062607,
|
|
"num_tokens": 34138525.0,
|
|
"step": 18560
|
|
},
|
|
{
|
|
"entropy": 5.232677316665649,
|
|
"epoch": 1.5507016371533577,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00047613183044979885,
|
|
"loss": 4.7001,
|
|
"mean_token_accuracy": 0.2287473663687706,
|
|
"num_tokens": 34147029.0,
|
|
"step": 18565
|
|
},
|
|
{
|
|
"entropy": 5.33637261390686,
|
|
"epoch": 1.551119278316071,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00047611848495045434,
|
|
"loss": 4.8558,
|
|
"mean_token_accuracy": 0.21594537794589996,
|
|
"num_tokens": 34155617.0,
|
|
"step": 18570
|
|
},
|
|
{
|
|
"entropy": 5.376030015945434,
|
|
"epoch": 1.5515369194787838,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00047610513593028867,
|
|
"loss": 4.8579,
|
|
"mean_token_accuracy": 0.21873934417963029,
|
|
"num_tokens": 34164693.0,
|
|
"step": 18575
|
|
},
|
|
{
|
|
"entropy": 5.305140781402588,
|
|
"epoch": 1.5519545606414968,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004760917833895355,
|
|
"loss": 4.8064,
|
|
"mean_token_accuracy": 0.22120079547166824,
|
|
"num_tokens": 34173394.0,
|
|
"step": 18580
|
|
},
|
|
{
|
|
"entropy": 5.306403493881225,
|
|
"epoch": 1.5523722018042099,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004760784273284286,
|
|
"loss": 4.801,
|
|
"mean_token_accuracy": 0.22176970690488815,
|
|
"num_tokens": 34182522.0,
|
|
"step": 18585
|
|
},
|
|
{
|
|
"entropy": 5.295482969284057,
|
|
"epoch": 1.5527898429669227,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004760650677472018,
|
|
"loss": 4.8494,
|
|
"mean_token_accuracy": 0.21665802747011184,
|
|
"num_tokens": 34192456.0,
|
|
"step": 18590
|
|
},
|
|
{
|
|
"entropy": 5.399590063095093,
|
|
"epoch": 1.553207484129636,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000476051704646089,
|
|
"loss": 4.9694,
|
|
"mean_token_accuracy": 0.209366637468338,
|
|
"num_tokens": 34202360.0,
|
|
"step": 18595
|
|
},
|
|
{
|
|
"entropy": 5.327020740509033,
|
|
"epoch": 1.5536251252923488,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000476038338025324,
|
|
"loss": 4.8351,
|
|
"mean_token_accuracy": 0.2140333041548729,
|
|
"num_tokens": 34211892.0,
|
|
"step": 18600
|
|
},
|
|
{
|
|
"entropy": 5.310635232925415,
|
|
"epoch": 1.5540427664550618,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00047602496788514103,
|
|
"loss": 4.8594,
|
|
"mean_token_accuracy": 0.21926874220371245,
|
|
"num_tokens": 34221776.0,
|
|
"step": 18605
|
|
},
|
|
{
|
|
"entropy": 5.28915696144104,
|
|
"epoch": 1.5544604076177748,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004760115942257739,
|
|
"loss": 4.7988,
|
|
"mean_token_accuracy": 0.22264128178358078,
|
|
"num_tokens": 34230564.0,
|
|
"step": 18610
|
|
},
|
|
{
|
|
"entropy": 5.203421592712402,
|
|
"epoch": 1.5548780487804879,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00047599821704745693,
|
|
"loss": 4.8003,
|
|
"mean_token_accuracy": 0.22419535666704177,
|
|
"num_tokens": 34239871.0,
|
|
"step": 18615
|
|
},
|
|
{
|
|
"entropy": 5.330877685546875,
|
|
"epoch": 1.5552956899432009,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004759848363504243,
|
|
"loss": 4.8523,
|
|
"mean_token_accuracy": 0.22176793068647385,
|
|
"num_tokens": 34248881.0,
|
|
"step": 18620
|
|
},
|
|
{
|
|
"entropy": 5.375067710876465,
|
|
"epoch": 1.5557133311059137,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004759714521349101,
|
|
"loss": 4.8109,
|
|
"mean_token_accuracy": 0.22288631051778793,
|
|
"num_tokens": 34257596.0,
|
|
"step": 18625
|
|
},
|
|
{
|
|
"entropy": 5.257914781570435,
|
|
"epoch": 1.556130972268627,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004759580644011487,
|
|
"loss": 4.8349,
|
|
"mean_token_accuracy": 0.21551542431116105,
|
|
"num_tokens": 34267030.0,
|
|
"step": 18630
|
|
},
|
|
{
|
|
"entropy": 5.339950275421143,
|
|
"epoch": 1.5565486134313398,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004759446731493745,
|
|
"loss": 4.8527,
|
|
"mean_token_accuracy": 0.21856367737054824,
|
|
"num_tokens": 34276269.0,
|
|
"step": 18635
|
|
},
|
|
{
|
|
"entropy": 5.3248766422271725,
|
|
"epoch": 1.5569662545940528,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000475931278379822,
|
|
"loss": 4.7925,
|
|
"mean_token_accuracy": 0.22173234820365906,
|
|
"num_tokens": 34285193.0,
|
|
"step": 18640
|
|
},
|
|
{
|
|
"entropy": 5.269678115844727,
|
|
"epoch": 1.5573838957567658,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004759178800927255,
|
|
"loss": 4.7094,
|
|
"mean_token_accuracy": 0.22771860659122467,
|
|
"num_tokens": 34294216.0,
|
|
"step": 18645
|
|
},
|
|
{
|
|
"entropy": 5.324185943603515,
|
|
"epoch": 1.5578015369194786,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004759044782883198,
|
|
"loss": 4.9619,
|
|
"mean_token_accuracy": 0.22529457062482833,
|
|
"num_tokens": 34302546.0,
|
|
"step": 18650
|
|
},
|
|
{
|
|
"entropy": 5.264931726455688,
|
|
"epoch": 1.558219178082192,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004758910729668392,
|
|
"loss": 4.7187,
|
|
"mean_token_accuracy": 0.23005199879407884,
|
|
"num_tokens": 34312176.0,
|
|
"step": 18655
|
|
},
|
|
{
|
|
"entropy": 5.390032196044922,
|
|
"epoch": 1.5586368192449047,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004758776641285187,
|
|
"loss": 4.8639,
|
|
"mean_token_accuracy": 0.21417946964502335,
|
|
"num_tokens": 34321836.0,
|
|
"step": 18660
|
|
},
|
|
{
|
|
"entropy": 5.276456594467163,
|
|
"epoch": 1.5590544604076177,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004758642517735928,
|
|
"loss": 4.8368,
|
|
"mean_token_accuracy": 0.22510630637407303,
|
|
"num_tokens": 34330624.0,
|
|
"step": 18665
|
|
},
|
|
{
|
|
"entropy": 5.274490737915039,
|
|
"epoch": 1.5594721015703308,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00047585083590229643,
|
|
"loss": 4.7721,
|
|
"mean_token_accuracy": 0.22997548282146454,
|
|
"num_tokens": 34339239.0,
|
|
"step": 18670
|
|
},
|
|
{
|
|
"entropy": 5.373441600799561,
|
|
"epoch": 1.5598897427330438,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00047583741651486443,
|
|
"loss": 4.8896,
|
|
"mean_token_accuracy": 0.20845028460025788,
|
|
"num_tokens": 34348823.0,
|
|
"step": 18675
|
|
},
|
|
{
|
|
"entropy": 5.2551830291748045,
|
|
"epoch": 1.5603073838957568,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004758239936115317,
|
|
"loss": 4.7236,
|
|
"mean_token_accuracy": 0.22197165936231614,
|
|
"num_tokens": 34357844.0,
|
|
"step": 18680
|
|
},
|
|
{
|
|
"entropy": 5.320318269729614,
|
|
"epoch": 1.5607250250584697,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00047581056719253324,
|
|
"loss": 4.8021,
|
|
"mean_token_accuracy": 0.2181933969259262,
|
|
"num_tokens": 34367055.0,
|
|
"step": 18685
|
|
},
|
|
{
|
|
"entropy": 5.4227691173553465,
|
|
"epoch": 1.561142666221183,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004757971372581041,
|
|
"loss": 4.9687,
|
|
"mean_token_accuracy": 0.21453351229429246,
|
|
"num_tokens": 34377329.0,
|
|
"step": 18690
|
|
},
|
|
{
|
|
"entropy": 5.356860589981079,
|
|
"epoch": 1.5615603073838957,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00047578370380847935,
|
|
"loss": 4.9802,
|
|
"mean_token_accuracy": 0.2051415979862213,
|
|
"num_tokens": 34386508.0,
|
|
"step": 18695
|
|
},
|
|
{
|
|
"entropy": 5.311890888214111,
|
|
"epoch": 1.5619779485466088,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00047577026684389413,
|
|
"loss": 4.8371,
|
|
"mean_token_accuracy": 0.21852040886878968,
|
|
"num_tokens": 34396075.0,
|
|
"step": 18700
|
|
},
|
|
{
|
|
"entropy": 5.3657286167144775,
|
|
"epoch": 1.5623955897093218,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004757568263645838,
|
|
"loss": 4.8767,
|
|
"mean_token_accuracy": 0.21642185300588607,
|
|
"num_tokens": 34405409.0,
|
|
"step": 18705
|
|
},
|
|
{
|
|
"entropy": 5.3189368724823,
|
|
"epoch": 1.5628132308720346,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004757433823707835,
|
|
"loss": 4.8429,
|
|
"mean_token_accuracy": 0.21829959154129028,
|
|
"num_tokens": 34415559.0,
|
|
"step": 18710
|
|
},
|
|
{
|
|
"entropy": 5.365096235275269,
|
|
"epoch": 1.5632308720347479,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004757299348627287,
|
|
"loss": 4.8436,
|
|
"mean_token_accuracy": 0.22565374672412872,
|
|
"num_tokens": 34424137.0,
|
|
"step": 18715
|
|
},
|
|
{
|
|
"entropy": 5.273004674911499,
|
|
"epoch": 1.5636485131974607,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00047571648384065477,
|
|
"loss": 4.85,
|
|
"mean_token_accuracy": 0.22125523388385773,
|
|
"num_tokens": 34433498.0,
|
|
"step": 18720
|
|
},
|
|
{
|
|
"entropy": 5.31063289642334,
|
|
"epoch": 1.5640661543601737,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004757030293047972,
|
|
"loss": 4.8052,
|
|
"mean_token_accuracy": 0.22359580993652345,
|
|
"num_tokens": 34443218.0,
|
|
"step": 18725
|
|
},
|
|
{
|
|
"entropy": 5.311111211776733,
|
|
"epoch": 1.5644837955228867,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004756895712553915,
|
|
"loss": 4.8237,
|
|
"mean_token_accuracy": 0.2173642784357071,
|
|
"num_tokens": 34452981.0,
|
|
"step": 18730
|
|
},
|
|
{
|
|
"entropy": 5.304569911956787,
|
|
"epoch": 1.5649014366855998,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00047567610969267326,
|
|
"loss": 4.8622,
|
|
"mean_token_accuracy": 0.21205950826406478,
|
|
"num_tokens": 34462763.0,
|
|
"step": 18735
|
|
},
|
|
{
|
|
"entropy": 5.256147623062134,
|
|
"epoch": 1.5653190778483128,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004756626446168782,
|
|
"loss": 4.747,
|
|
"mean_token_accuracy": 0.23156251460313798,
|
|
"num_tokens": 34471841.0,
|
|
"step": 18740
|
|
},
|
|
{
|
|
"entropy": 5.4392622947692875,
|
|
"epoch": 1.5657367190110256,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00047564917602824203,
|
|
"loss": 4.9541,
|
|
"mean_token_accuracy": 0.21528432816267012,
|
|
"num_tokens": 34482280.0,
|
|
"step": 18745
|
|
},
|
|
{
|
|
"entropy": 5.4592698097229,
|
|
"epoch": 1.5661543601737389,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004756357039270004,
|
|
"loss": 4.9949,
|
|
"mean_token_accuracy": 0.2114224687218666,
|
|
"num_tokens": 34492774.0,
|
|
"step": 18750
|
|
},
|
|
{
|
|
"entropy": 5.323215818405151,
|
|
"epoch": 1.5665720013364517,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00047562222831338933,
|
|
"loss": 4.7665,
|
|
"mean_token_accuracy": 0.22085919082164765,
|
|
"num_tokens": 34501626.0,
|
|
"step": 18755
|
|
},
|
|
{
|
|
"entropy": 5.292954683303833,
|
|
"epoch": 1.5669896424991647,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00047560874918764473,
|
|
"loss": 4.865,
|
|
"mean_token_accuracy": 0.2124074101448059,
|
|
"num_tokens": 34510264.0,
|
|
"step": 18760
|
|
},
|
|
{
|
|
"entropy": 5.394419431686401,
|
|
"epoch": 1.5674072836618778,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00047559526655000244,
|
|
"loss": 4.9147,
|
|
"mean_token_accuracy": 0.20729337632656097,
|
|
"num_tokens": 34520540.0,
|
|
"step": 18765
|
|
},
|
|
{
|
|
"entropy": 5.3708325862884525,
|
|
"epoch": 1.5678249248245906,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004755817804006986,
|
|
"loss": 4.8624,
|
|
"mean_token_accuracy": 0.21743908524513245,
|
|
"num_tokens": 34529669.0,
|
|
"step": 18770
|
|
},
|
|
{
|
|
"entropy": 5.320007753372193,
|
|
"epoch": 1.5682425659873038,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004755682907399692,
|
|
"loss": 4.8558,
|
|
"mean_token_accuracy": 0.2221200242638588,
|
|
"num_tokens": 34538802.0,
|
|
"step": 18775
|
|
},
|
|
{
|
|
"entropy": 5.341077041625977,
|
|
"epoch": 1.5686602071500166,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00047555479756805055,
|
|
"loss": 4.9,
|
|
"mean_token_accuracy": 0.2170880153775215,
|
|
"num_tokens": 34547583.0,
|
|
"step": 18780
|
|
},
|
|
{
|
|
"entropy": 5.309667301177979,
|
|
"epoch": 1.5690778483127297,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004755413008851786,
|
|
"loss": 4.7866,
|
|
"mean_token_accuracy": 0.21926579475402833,
|
|
"num_tokens": 34556045.0,
|
|
"step": 18785
|
|
},
|
|
{
|
|
"entropy": 5.2605305194854735,
|
|
"epoch": 1.5694954894754427,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004755278006915899,
|
|
"loss": 4.7009,
|
|
"mean_token_accuracy": 0.22824535071849822,
|
|
"num_tokens": 34564910.0,
|
|
"step": 18790
|
|
},
|
|
{
|
|
"entropy": 5.32786374092102,
|
|
"epoch": 1.5699131306381557,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00047551429698752064,
|
|
"loss": 4.8919,
|
|
"mean_token_accuracy": 0.2123410314321518,
|
|
"num_tokens": 34573274.0,
|
|
"step": 18795
|
|
},
|
|
{
|
|
"entropy": 5.278517198562622,
|
|
"epoch": 1.5703307718008688,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00047550078977320724,
|
|
"loss": 4.789,
|
|
"mean_token_accuracy": 0.22138385772705077,
|
|
"num_tokens": 34583015.0,
|
|
"step": 18800
|
|
},
|
|
{
|
|
"entropy": 5.421412372589112,
|
|
"epoch": 1.5707484129635816,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004754872790488862,
|
|
"loss": 4.9134,
|
|
"mean_token_accuracy": 0.2108479619026184,
|
|
"num_tokens": 34592311.0,
|
|
"step": 18805
|
|
},
|
|
{
|
|
"entropy": 5.338523530960083,
|
|
"epoch": 1.5711660541262948,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000475473764814794,
|
|
"loss": 4.8112,
|
|
"mean_token_accuracy": 0.21908282935619355,
|
|
"num_tokens": 34600806.0,
|
|
"step": 18810
|
|
},
|
|
{
|
|
"entropy": 5.275394105911255,
|
|
"epoch": 1.5715836952890077,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00047546024707116727,
|
|
"loss": 4.7581,
|
|
"mean_token_accuracy": 0.2190888687968254,
|
|
"num_tokens": 34609830.0,
|
|
"step": 18815
|
|
},
|
|
{
|
|
"entropy": 5.343398857116699,
|
|
"epoch": 1.5720013364517207,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00047544672581824256,
|
|
"loss": 4.8055,
|
|
"mean_token_accuracy": 0.21606779992580413,
|
|
"num_tokens": 34618870.0,
|
|
"step": 18820
|
|
},
|
|
{
|
|
"entropy": 5.315543794631958,
|
|
"epoch": 1.5724189776144337,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004754332010562567,
|
|
"loss": 4.7346,
|
|
"mean_token_accuracy": 0.22542910724878312,
|
|
"num_tokens": 34628349.0,
|
|
"step": 18825
|
|
},
|
|
{
|
|
"entropy": 5.305936670303344,
|
|
"epoch": 1.5728366187771465,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004754196727854463,
|
|
"loss": 4.8649,
|
|
"mean_token_accuracy": 0.21514635235071183,
|
|
"num_tokens": 34638492.0,
|
|
"step": 18830
|
|
},
|
|
{
|
|
"entropy": 5.387983989715576,
|
|
"epoch": 1.5732542599398598,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00047540614100604836,
|
|
"loss": 4.9228,
|
|
"mean_token_accuracy": 0.22257393449544907,
|
|
"num_tokens": 34649084.0,
|
|
"step": 18835
|
|
},
|
|
{
|
|
"entropy": 5.346834897994995,
|
|
"epoch": 1.5736719011025726,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004753926057182997,
|
|
"loss": 4.8474,
|
|
"mean_token_accuracy": 0.2211420327425003,
|
|
"num_tokens": 34658392.0,
|
|
"step": 18840
|
|
},
|
|
{
|
|
"entropy": 5.288752794265747,
|
|
"epoch": 1.5740895422652856,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00047537906692243716,
|
|
"loss": 4.8744,
|
|
"mean_token_accuracy": 0.21186643838882446,
|
|
"num_tokens": 34667727.0,
|
|
"step": 18845
|
|
},
|
|
{
|
|
"entropy": 5.355210971832276,
|
|
"epoch": 1.5745071834279987,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000475365524618698,
|
|
"loss": 4.8242,
|
|
"mean_token_accuracy": 0.21855736374855042,
|
|
"num_tokens": 34676260.0,
|
|
"step": 18850
|
|
},
|
|
{
|
|
"entropy": 5.4393762111663815,
|
|
"epoch": 1.5749248245907117,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004753519788073191,
|
|
"loss": 4.951,
|
|
"mean_token_accuracy": 0.20957325845956803,
|
|
"num_tokens": 34685145.0,
|
|
"step": 18855
|
|
},
|
|
{
|
|
"entropy": 5.290892696380615,
|
|
"epoch": 1.5753424657534247,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004753384294885376,
|
|
"loss": 4.7348,
|
|
"mean_token_accuracy": 0.23026515394449235,
|
|
"num_tokens": 34694035.0,
|
|
"step": 18860
|
|
},
|
|
{
|
|
"entropy": 5.293204402923584,
|
|
"epoch": 1.5757601069161375,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004753248766625908,
|
|
"loss": 4.8283,
|
|
"mean_token_accuracy": 0.21581972241401673,
|
|
"num_tokens": 34702634.0,
|
|
"step": 18865
|
|
},
|
|
{
|
|
"entropy": 5.296241998672485,
|
|
"epoch": 1.5761777480788508,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004753113203297159,
|
|
"loss": 4.8317,
|
|
"mean_token_accuracy": 0.21368013620376586,
|
|
"num_tokens": 34711925.0,
|
|
"step": 18870
|
|
},
|
|
{
|
|
"entropy": 5.304551696777343,
|
|
"epoch": 1.5765953892415636,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004752977604901502,
|
|
"loss": 4.7535,
|
|
"mean_token_accuracy": 0.23480982929468155,
|
|
"num_tokens": 34720131.0,
|
|
"step": 18875
|
|
},
|
|
{
|
|
"entropy": 5.313565969467163,
|
|
"epoch": 1.5770130304042767,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00047528419714413107,
|
|
"loss": 4.8749,
|
|
"mean_token_accuracy": 0.21676438599824904,
|
|
"num_tokens": 34728869.0,
|
|
"step": 18880
|
|
},
|
|
{
|
|
"entropy": 5.277946281433105,
|
|
"epoch": 1.5774306715669897,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00047527063029189606,
|
|
"loss": 4.7329,
|
|
"mean_token_accuracy": 0.22833096832036973,
|
|
"num_tokens": 34737343.0,
|
|
"step": 18885
|
|
},
|
|
{
|
|
"entropy": 5.399722719192505,
|
|
"epoch": 1.5778483127297025,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004752570599336825,
|
|
"loss": 4.9201,
|
|
"mean_token_accuracy": 0.2140476807951927,
|
|
"num_tokens": 34746752.0,
|
|
"step": 18890
|
|
},
|
|
{
|
|
"entropy": 5.37776141166687,
|
|
"epoch": 1.5782659538924158,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00047524348606972817,
|
|
"loss": 4.8669,
|
|
"mean_token_accuracy": 0.21781989932060242,
|
|
"num_tokens": 34755672.0,
|
|
"step": 18895
|
|
},
|
|
{
|
|
"entropy": 5.337584209442139,
|
|
"epoch": 1.5786835950551286,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00047522990870027055,
|
|
"loss": 4.869,
|
|
"mean_token_accuracy": 0.21545440703630447,
|
|
"num_tokens": 34764558.0,
|
|
"step": 18900
|
|
},
|
|
{
|
|
"entropy": 5.313819789886475,
|
|
"epoch": 1.5791012362178416,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004752163278255473,
|
|
"loss": 4.8,
|
|
"mean_token_accuracy": 0.21209315955638885,
|
|
"num_tokens": 34773663.0,
|
|
"step": 18905
|
|
},
|
|
{
|
|
"entropy": 5.220689582824707,
|
|
"epoch": 1.5795188773805546,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004752027434457963,
|
|
"loss": 4.7434,
|
|
"mean_token_accuracy": 0.22192640006542205,
|
|
"num_tokens": 34782297.0,
|
|
"step": 18910
|
|
},
|
|
{
|
|
"entropy": 5.430728387832642,
|
|
"epoch": 1.5799365185432677,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004751891555612552,
|
|
"loss": 4.9876,
|
|
"mean_token_accuracy": 0.2042150542140007,
|
|
"num_tokens": 34791734.0,
|
|
"step": 18915
|
|
},
|
|
{
|
|
"entropy": 5.354410600662232,
|
|
"epoch": 1.5803541597059807,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004751755641721621,
|
|
"loss": 4.8406,
|
|
"mean_token_accuracy": 0.22308648228645325,
|
|
"num_tokens": 34801187.0,
|
|
"step": 18920
|
|
},
|
|
{
|
|
"entropy": 5.312365198135376,
|
|
"epoch": 1.5807718008686935,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00047516196927875474,
|
|
"loss": 4.8231,
|
|
"mean_token_accuracy": 0.2225424513220787,
|
|
"num_tokens": 34810084.0,
|
|
"step": 18925
|
|
},
|
|
{
|
|
"entropy": 5.434480333328247,
|
|
"epoch": 1.5811894420314068,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00047514837088127117,
|
|
"loss": 4.9281,
|
|
"mean_token_accuracy": 0.2169284224510193,
|
|
"num_tokens": 34819160.0,
|
|
"step": 18930
|
|
},
|
|
{
|
|
"entropy": 5.283644533157348,
|
|
"epoch": 1.5816070831941196,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004751347689799494,
|
|
"loss": 4.7323,
|
|
"mean_token_accuracy": 0.23534677177667618,
|
|
"num_tokens": 34828272.0,
|
|
"step": 18935
|
|
},
|
|
{
|
|
"entropy": 5.263099575042725,
|
|
"epoch": 1.5820247243568326,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00047512116357502766,
|
|
"loss": 4.7662,
|
|
"mean_token_accuracy": 0.22489613443613052,
|
|
"num_tokens": 34838030.0,
|
|
"step": 18940
|
|
},
|
|
{
|
|
"entropy": 5.2893599510192875,
|
|
"epoch": 1.5824423655195456,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00047510755466674407,
|
|
"loss": 4.8803,
|
|
"mean_token_accuracy": 0.2161555826663971,
|
|
"num_tokens": 34846489.0,
|
|
"step": 18945
|
|
},
|
|
{
|
|
"entropy": 5.334221506118775,
|
|
"epoch": 1.5828600066822585,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00047509394225533685,
|
|
"loss": 4.8326,
|
|
"mean_token_accuracy": 0.22054653018712997,
|
|
"num_tokens": 34855926.0,
|
|
"step": 18950
|
|
},
|
|
{
|
|
"entropy": 5.380084609985351,
|
|
"epoch": 1.5832776478449717,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004750803263410443,
|
|
"loss": 4.8105,
|
|
"mean_token_accuracy": 0.22370714843273162,
|
|
"num_tokens": 34865158.0,
|
|
"step": 18955
|
|
},
|
|
{
|
|
"entropy": 5.315197324752807,
|
|
"epoch": 1.5836952890076845,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004750667069241048,
|
|
"loss": 4.8926,
|
|
"mean_token_accuracy": 0.20750349164009094,
|
|
"num_tokens": 34875429.0,
|
|
"step": 18960
|
|
},
|
|
{
|
|
"entropy": 5.352209424972534,
|
|
"epoch": 1.5841129301703976,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004750530840047568,
|
|
"loss": 4.8705,
|
|
"mean_token_accuracy": 0.22172179520130159,
|
|
"num_tokens": 34885663.0,
|
|
"step": 18965
|
|
},
|
|
{
|
|
"entropy": 5.287906837463379,
|
|
"epoch": 1.5845305713331106,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00047503945758323873,
|
|
"loss": 4.7809,
|
|
"mean_token_accuracy": 0.22336517423391342,
|
|
"num_tokens": 34894976.0,
|
|
"step": 18970
|
|
},
|
|
{
|
|
"entropy": 5.357144594192505,
|
|
"epoch": 1.5849482124958236,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004750258276597892,
|
|
"loss": 4.8056,
|
|
"mean_token_accuracy": 0.22033750265836716,
|
|
"num_tokens": 34905630.0,
|
|
"step": 18975
|
|
},
|
|
{
|
|
"entropy": 5.282482719421386,
|
|
"epoch": 1.5853658536585367,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00047501219423464673,
|
|
"loss": 4.7762,
|
|
"mean_token_accuracy": 0.21905231922864915,
|
|
"num_tokens": 34914906.0,
|
|
"step": 18980
|
|
},
|
|
{
|
|
"entropy": 5.2876818656921385,
|
|
"epoch": 1.5857834948212495,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004749985573080501,
|
|
"loss": 4.7481,
|
|
"mean_token_accuracy": 0.2182350292801857,
|
|
"num_tokens": 34923274.0,
|
|
"step": 18985
|
|
},
|
|
{
|
|
"entropy": 5.322837972640992,
|
|
"epoch": 1.5862011359839627,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000474984916880238,
|
|
"loss": 4.8058,
|
|
"mean_token_accuracy": 0.22692470252513885,
|
|
"num_tokens": 34932085.0,
|
|
"step": 18990
|
|
},
|
|
{
|
|
"entropy": 5.29895544052124,
|
|
"epoch": 1.5866187771466755,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004749712729514491,
|
|
"loss": 4.892,
|
|
"mean_token_accuracy": 0.21637040823698045,
|
|
"num_tokens": 34940871.0,
|
|
"step": 18995
|
|
},
|
|
{
|
|
"entropy": 5.37141637802124,
|
|
"epoch": 1.5870364183093886,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004749576255219225,
|
|
"loss": 4.9383,
|
|
"mean_token_accuracy": 0.2105043739080429,
|
|
"num_tokens": 34950703.0,
|
|
"step": 19000
|
|
},
|
|
{
|
|
"entropy": 5.422506809234619,
|
|
"epoch": 1.5874540594721016,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004749439745918969,
|
|
"loss": 4.8886,
|
|
"mean_token_accuracy": 0.21387770473957063,
|
|
"num_tokens": 34959988.0,
|
|
"step": 19005
|
|
},
|
|
{
|
|
"entropy": 5.371648168563842,
|
|
"epoch": 1.5878717006348144,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00047493032016161134,
|
|
"loss": 4.889,
|
|
"mean_token_accuracy": 0.21336522400379182,
|
|
"num_tokens": 34968608.0,
|
|
"step": 19010
|
|
},
|
|
{
|
|
"entropy": 5.371820068359375,
|
|
"epoch": 1.5882893417975277,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004749166622313049,
|
|
"loss": 4.903,
|
|
"mean_token_accuracy": 0.20822780430316926,
|
|
"num_tokens": 34977200.0,
|
|
"step": 19015
|
|
},
|
|
{
|
|
"entropy": 5.397996950149536,
|
|
"epoch": 1.5887069829602405,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00047490300080121667,
|
|
"loss": 4.8008,
|
|
"mean_token_accuracy": 0.22560485303401948,
|
|
"num_tokens": 34986403.0,
|
|
"step": 19020
|
|
},
|
|
{
|
|
"entropy": 5.340812015533447,
|
|
"epoch": 1.5891246241229535,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00047488933587158585,
|
|
"loss": 4.9108,
|
|
"mean_token_accuracy": 0.21542646139860153,
|
|
"num_tokens": 34995672.0,
|
|
"step": 19025
|
|
},
|
|
{
|
|
"entropy": 5.301647043228149,
|
|
"epoch": 1.5895422652856666,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004748756674426514,
|
|
"loss": 4.9368,
|
|
"mean_token_accuracy": 0.2146086424589157,
|
|
"num_tokens": 35004636.0,
|
|
"step": 19030
|
|
},
|
|
{
|
|
"entropy": 5.306039619445801,
|
|
"epoch": 1.5899599064483796,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000474861995514653,
|
|
"loss": 4.7542,
|
|
"mean_token_accuracy": 0.22633906900882722,
|
|
"num_tokens": 35014023.0,
|
|
"step": 19035
|
|
},
|
|
{
|
|
"entropy": 5.422774124145508,
|
|
"epoch": 1.5903775476110926,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004748483200878297,
|
|
"loss": 4.9471,
|
|
"mean_token_accuracy": 0.21623825579881667,
|
|
"num_tokens": 35023762.0,
|
|
"step": 19040
|
|
},
|
|
{
|
|
"entropy": 5.35252685546875,
|
|
"epoch": 1.5907951887738054,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000474834641162421,
|
|
"loss": 4.7883,
|
|
"mean_token_accuracy": 0.22393913120031356,
|
|
"num_tokens": 35032485.0,
|
|
"step": 19045
|
|
},
|
|
{
|
|
"entropy": 5.345053768157959,
|
|
"epoch": 1.5912128299365187,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00047482095873866635,
|
|
"loss": 4.8897,
|
|
"mean_token_accuracy": 0.20954312831163407,
|
|
"num_tokens": 35041416.0,
|
|
"step": 19050
|
|
},
|
|
{
|
|
"entropy": 5.366445446014405,
|
|
"epoch": 1.5916304710992315,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004748072728168053,
|
|
"loss": 4.8062,
|
|
"mean_token_accuracy": 0.22386783361434937,
|
|
"num_tokens": 35051223.0,
|
|
"step": 19055
|
|
},
|
|
{
|
|
"entropy": 5.321369981765747,
|
|
"epoch": 1.5920481122619445,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004747935833970775,
|
|
"loss": 4.8829,
|
|
"mean_token_accuracy": 0.22040392309427262,
|
|
"num_tokens": 35060935.0,
|
|
"step": 19060
|
|
},
|
|
{
|
|
"entropy": 5.268683910369873,
|
|
"epoch": 1.5924657534246576,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004747798904797225,
|
|
"loss": 4.7749,
|
|
"mean_token_accuracy": 0.22755743116140364,
|
|
"num_tokens": 35070249.0,
|
|
"step": 19065
|
|
},
|
|
{
|
|
"entropy": 5.300106620788574,
|
|
"epoch": 1.5928833945873704,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00047476619406497996,
|
|
"loss": 4.7898,
|
|
"mean_token_accuracy": 0.21895843297243117,
|
|
"num_tokens": 35079040.0,
|
|
"step": 19070
|
|
},
|
|
{
|
|
"entropy": 5.275178527832031,
|
|
"epoch": 1.5933010357500836,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004747524941530898,
|
|
"loss": 4.7741,
|
|
"mean_token_accuracy": 0.22124327570199967,
|
|
"num_tokens": 35087451.0,
|
|
"step": 19075
|
|
},
|
|
{
|
|
"entropy": 5.380113935470581,
|
|
"epoch": 1.5937186769127965,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004747387907442918,
|
|
"loss": 4.8814,
|
|
"mean_token_accuracy": 0.2195889487862587,
|
|
"num_tokens": 35096144.0,
|
|
"step": 19080
|
|
},
|
|
{
|
|
"entropy": 5.407424259185791,
|
|
"epoch": 1.5941363180755095,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00047472508383882586,
|
|
"loss": 4.8655,
|
|
"mean_token_accuracy": 0.2167931988835335,
|
|
"num_tokens": 35105547.0,
|
|
"step": 19085
|
|
},
|
|
{
|
|
"entropy": 5.366646862030029,
|
|
"epoch": 1.5945539592382225,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004747113734369319,
|
|
"loss": 4.817,
|
|
"mean_token_accuracy": 0.22150617241859435,
|
|
"num_tokens": 35114164.0,
|
|
"step": 19090
|
|
},
|
|
{
|
|
"entropy": 5.326542663574219,
|
|
"epoch": 1.5949716004009356,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004746976595388499,
|
|
"loss": 4.8587,
|
|
"mean_token_accuracy": 0.21830397099256516,
|
|
"num_tokens": 35125184.0,
|
|
"step": 19095
|
|
},
|
|
{
|
|
"entropy": 5.3128674030303955,
|
|
"epoch": 1.5953892415636486,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00047468394214482,
|
|
"loss": 4.7619,
|
|
"mean_token_accuracy": 0.22927654683589935,
|
|
"num_tokens": 35134207.0,
|
|
"step": 19100
|
|
},
|
|
{
|
|
"entropy": 5.301178455352783,
|
|
"epoch": 1.5958068827263614,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004746702212550824,
|
|
"loss": 4.8308,
|
|
"mean_token_accuracy": 0.22552416622638702,
|
|
"num_tokens": 35143651.0,
|
|
"step": 19105
|
|
},
|
|
{
|
|
"entropy": 5.30856351852417,
|
|
"epoch": 1.5962245238890747,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00047465649686987717,
|
|
"loss": 4.8508,
|
|
"mean_token_accuracy": 0.2153803899884224,
|
|
"num_tokens": 35152907.0,
|
|
"step": 19110
|
|
},
|
|
{
|
|
"entropy": 5.312064170837402,
|
|
"epoch": 1.5966421650517875,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004746427689894447,
|
|
"loss": 4.7692,
|
|
"mean_token_accuracy": 0.22930071800947188,
|
|
"num_tokens": 35161927.0,
|
|
"step": 19115
|
|
},
|
|
{
|
|
"entropy": 5.340997838973999,
|
|
"epoch": 1.5970598062145005,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004746290376140252,
|
|
"loss": 4.852,
|
|
"mean_token_accuracy": 0.2178358718752861,
|
|
"num_tokens": 35171303.0,
|
|
"step": 19120
|
|
},
|
|
{
|
|
"entropy": 5.407586336135864,
|
|
"epoch": 1.5974774473772135,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004746153027438592,
|
|
"loss": 4.9163,
|
|
"mean_token_accuracy": 0.2188715547323227,
|
|
"num_tokens": 35181160.0,
|
|
"step": 19125
|
|
},
|
|
{
|
|
"entropy": 5.346898794174194,
|
|
"epoch": 1.5978950885399263,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004746015643791869,
|
|
"loss": 4.8966,
|
|
"mean_token_accuracy": 0.21437381356954574,
|
|
"num_tokens": 35190335.0,
|
|
"step": 19130
|
|
},
|
|
{
|
|
"entropy": 5.376919937133789,
|
|
"epoch": 1.5983127297026396,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000474587822520249,
|
|
"loss": 4.8943,
|
|
"mean_token_accuracy": 0.21799647212028503,
|
|
"num_tokens": 35200036.0,
|
|
"step": 19135
|
|
},
|
|
{
|
|
"entropy": 5.36342453956604,
|
|
"epoch": 1.5987303708653524,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004745740771672861,
|
|
"loss": 4.7976,
|
|
"mean_token_accuracy": 0.222974693775177,
|
|
"num_tokens": 35208203.0,
|
|
"step": 19140
|
|
},
|
|
{
|
|
"entropy": 5.26827483177185,
|
|
"epoch": 1.5991480120280654,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004745603283205387,
|
|
"loss": 4.7624,
|
|
"mean_token_accuracy": 0.2271937385201454,
|
|
"num_tokens": 35216963.0,
|
|
"step": 19145
|
|
},
|
|
{
|
|
"entropy": 5.359993982315063,
|
|
"epoch": 1.5995656531907785,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00047454657598024755,
|
|
"loss": 4.8232,
|
|
"mean_token_accuracy": 0.21911332607269288,
|
|
"num_tokens": 35226170.0,
|
|
"step": 19150
|
|
},
|
|
{
|
|
"entropy": 5.2837118148803714,
|
|
"epoch": 1.5999832943534915,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00047453282014665334,
|
|
"loss": 4.7247,
|
|
"mean_token_accuracy": 0.2255568325519562,
|
|
"num_tokens": 35234383.0,
|
|
"step": 19155
|
|
},
|
|
{
|
|
"entropy": 5.266273021697998,
|
|
"epoch": 1.6004009355162045,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00047451906081999695,
|
|
"loss": 4.7238,
|
|
"mean_token_accuracy": 0.22954728305339814,
|
|
"num_tokens": 35242771.0,
|
|
"step": 19160
|
|
},
|
|
{
|
|
"entropy": 5.276978302001953,
|
|
"epoch": 1.6008185766789174,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004745052980005193,
|
|
"loss": 4.8023,
|
|
"mean_token_accuracy": 0.22417520880699157,
|
|
"num_tokens": 35251333.0,
|
|
"step": 19165
|
|
},
|
|
{
|
|
"entropy": 5.3727201461792,
|
|
"epoch": 1.6012362178416306,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004744915316884612,
|
|
"loss": 4.8508,
|
|
"mean_token_accuracy": 0.21301562637090682,
|
|
"num_tokens": 35260423.0,
|
|
"step": 19170
|
|
},
|
|
{
|
|
"entropy": 5.337431859970093,
|
|
"epoch": 1.6016538590043434,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004744777618840637,
|
|
"loss": 4.7848,
|
|
"mean_token_accuracy": 0.2254309117794037,
|
|
"num_tokens": 35268838.0,
|
|
"step": 19175
|
|
},
|
|
{
|
|
"entropy": 5.337160301208496,
|
|
"epoch": 1.6020715001670565,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000474463988587568,
|
|
"loss": 4.9197,
|
|
"mean_token_accuracy": 0.21581682413816453,
|
|
"num_tokens": 35279395.0,
|
|
"step": 19180
|
|
},
|
|
{
|
|
"entropy": 5.375088739395141,
|
|
"epoch": 1.6024891413297695,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00047445021179921495,
|
|
"loss": 4.8401,
|
|
"mean_token_accuracy": 0.21579443216323851,
|
|
"num_tokens": 35289637.0,
|
|
"step": 19185
|
|
},
|
|
{
|
|
"entropy": 5.320774555206299,
|
|
"epoch": 1.6029067824924823,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004744364315192459,
|
|
"loss": 4.8384,
|
|
"mean_token_accuracy": 0.2199197605252266,
|
|
"num_tokens": 35299813.0,
|
|
"step": 19190
|
|
},
|
|
{
|
|
"entropy": 5.328606700897216,
|
|
"epoch": 1.6033244236551956,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00047442264774790203,
|
|
"loss": 4.848,
|
|
"mean_token_accuracy": 0.22168644666671752,
|
|
"num_tokens": 35308162.0,
|
|
"step": 19195
|
|
},
|
|
{
|
|
"entropy": 5.29536657333374,
|
|
"epoch": 1.6037420648179084,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004744088604854248,
|
|
"loss": 4.8175,
|
|
"mean_token_accuracy": 0.22593098431825637,
|
|
"num_tokens": 35317232.0,
|
|
"step": 19200
|
|
},
|
|
{
|
|
"entropy": 5.336257410049439,
|
|
"epoch": 1.6041597059806214,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00047439506973205527,
|
|
"loss": 4.8015,
|
|
"mean_token_accuracy": 0.22012410014867784,
|
|
"num_tokens": 35326011.0,
|
|
"step": 19205
|
|
},
|
|
{
|
|
"entropy": 5.262380933761596,
|
|
"epoch": 1.6045773471433344,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004743812754880351,
|
|
"loss": 4.7271,
|
|
"mean_token_accuracy": 0.22662274092435836,
|
|
"num_tokens": 35333935.0,
|
|
"step": 19210
|
|
},
|
|
{
|
|
"entropy": 5.275657224655151,
|
|
"epoch": 1.6049949883060475,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004743674777536057,
|
|
"loss": 4.8248,
|
|
"mean_token_accuracy": 0.22155556529760362,
|
|
"num_tokens": 35343512.0,
|
|
"step": 19215
|
|
},
|
|
{
|
|
"entropy": 5.328514480590821,
|
|
"epoch": 1.6054126294687605,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004743536765290087,
|
|
"loss": 4.8457,
|
|
"mean_token_accuracy": 0.2176208034157753,
|
|
"num_tokens": 35353276.0,
|
|
"step": 19220
|
|
},
|
|
{
|
|
"entropy": 5.301725101470947,
|
|
"epoch": 1.6058302706314733,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00047433987181448546,
|
|
"loss": 4.8215,
|
|
"mean_token_accuracy": 0.22354250103235246,
|
|
"num_tokens": 35362101.0,
|
|
"step": 19225
|
|
},
|
|
{
|
|
"entropy": 5.273161506652832,
|
|
"epoch": 1.6062479117941866,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004743260636102779,
|
|
"loss": 4.8098,
|
|
"mean_token_accuracy": 0.21730649322271348,
|
|
"num_tokens": 35370998.0,
|
|
"step": 19230
|
|
},
|
|
{
|
|
"entropy": 5.436282348632813,
|
|
"epoch": 1.6066655529568994,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00047431225191662776,
|
|
"loss": 4.9301,
|
|
"mean_token_accuracy": 0.2074878916144371,
|
|
"num_tokens": 35380347.0,
|
|
"step": 19235
|
|
},
|
|
{
|
|
"entropy": 5.380125904083252,
|
|
"epoch": 1.6070831941196124,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00047429843673377664,
|
|
"loss": 4.8157,
|
|
"mean_token_accuracy": 0.2232323482632637,
|
|
"num_tokens": 35388586.0,
|
|
"step": 19240
|
|
},
|
|
{
|
|
"entropy": 5.3212655544281,
|
|
"epoch": 1.6075008352823255,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00047428461806196646,
|
|
"loss": 4.8943,
|
|
"mean_token_accuracy": 0.22004936933517455,
|
|
"num_tokens": 35397649.0,
|
|
"step": 19245
|
|
},
|
|
{
|
|
"entropy": 5.31783127784729,
|
|
"epoch": 1.6079184764450383,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004742707959014393,
|
|
"loss": 4.8382,
|
|
"mean_token_accuracy": 0.22310159206390381,
|
|
"num_tokens": 35405790.0,
|
|
"step": 19250
|
|
},
|
|
{
|
|
"entropy": 5.349321603775024,
|
|
"epoch": 1.6083361176077515,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00047425697025243693,
|
|
"loss": 4.8699,
|
|
"mean_token_accuracy": 0.2105095148086548,
|
|
"num_tokens": 35414389.0,
|
|
"step": 19255
|
|
},
|
|
{
|
|
"entropy": 5.317843294143676,
|
|
"epoch": 1.6087537587704643,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00047424314111520134,
|
|
"loss": 4.8513,
|
|
"mean_token_accuracy": 0.21934032142162324,
|
|
"num_tokens": 35424909.0,
|
|
"step": 19260
|
|
},
|
|
{
|
|
"entropy": 5.323308038711548,
|
|
"epoch": 1.6091713999331774,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004742293084899749,
|
|
"loss": 4.81,
|
|
"mean_token_accuracy": 0.22598304748535156,
|
|
"num_tokens": 35434054.0,
|
|
"step": 19265
|
|
},
|
|
{
|
|
"entropy": 5.325082445144654,
|
|
"epoch": 1.6095890410958904,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004742154723769995,
|
|
"loss": 4.8348,
|
|
"mean_token_accuracy": 0.22113338857889175,
|
|
"num_tokens": 35443722.0,
|
|
"step": 19270
|
|
},
|
|
{
|
|
"entropy": 5.3988431930542,
|
|
"epoch": 1.6100066822586034,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004742016327765175,
|
|
"loss": 4.8544,
|
|
"mean_token_accuracy": 0.2157442793250084,
|
|
"num_tokens": 35453067.0,
|
|
"step": 19275
|
|
},
|
|
{
|
|
"entropy": 5.274615859985351,
|
|
"epoch": 1.6104243234213165,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004741877896887711,
|
|
"loss": 4.74,
|
|
"mean_token_accuracy": 0.22740153223276138,
|
|
"num_tokens": 35462425.0,
|
|
"step": 19280
|
|
},
|
|
{
|
|
"entropy": 5.318864250183106,
|
|
"epoch": 1.6108419645840293,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004741739431140027,
|
|
"loss": 4.7822,
|
|
"mean_token_accuracy": 0.2255476474761963,
|
|
"num_tokens": 35472037.0,
|
|
"step": 19285
|
|
},
|
|
{
|
|
"entropy": 5.316570138931274,
|
|
"epoch": 1.6112596057467425,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00047416009305245474,
|
|
"loss": 4.8476,
|
|
"mean_token_accuracy": 0.21928533613681794,
|
|
"num_tokens": 35481411.0,
|
|
"step": 19290
|
|
},
|
|
{
|
|
"entropy": 5.252789163589478,
|
|
"epoch": 1.6116772469094554,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004741462395043695,
|
|
"loss": 4.7599,
|
|
"mean_token_accuracy": 0.22949206531047822,
|
|
"num_tokens": 35490019.0,
|
|
"step": 19295
|
|
},
|
|
{
|
|
"entropy": 5.306204605102539,
|
|
"epoch": 1.6120948880721684,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00047413238246998975,
|
|
"loss": 4.8638,
|
|
"mean_token_accuracy": 0.22579577416181565,
|
|
"num_tokens": 35499229.0,
|
|
"step": 19300
|
|
},
|
|
{
|
|
"entropy": 5.349823999404907,
|
|
"epoch": 1.6125125292348814,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004741185219495579,
|
|
"loss": 4.7535,
|
|
"mean_token_accuracy": 0.22103792279958726,
|
|
"num_tokens": 35508473.0,
|
|
"step": 19305
|
|
},
|
|
{
|
|
"entropy": 5.3177391529083256,
|
|
"epoch": 1.6129301703975942,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004741046579433166,
|
|
"loss": 4.8335,
|
|
"mean_token_accuracy": 0.2217398390173912,
|
|
"num_tokens": 35517887.0,
|
|
"step": 19310
|
|
},
|
|
{
|
|
"entropy": 5.315888929367065,
|
|
"epoch": 1.6133478115603075,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00047409079045150865,
|
|
"loss": 4.8299,
|
|
"mean_token_accuracy": 0.2185900554060936,
|
|
"num_tokens": 35527470.0,
|
|
"step": 19315
|
|
},
|
|
{
|
|
"entropy": 5.3572914600372314,
|
|
"epoch": 1.6137654527230203,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00047407691947437677,
|
|
"loss": 4.8734,
|
|
"mean_token_accuracy": 0.22310664504766464,
|
|
"num_tokens": 35537670.0,
|
|
"step": 19320
|
|
},
|
|
{
|
|
"entropy": 5.287282466888428,
|
|
"epoch": 1.6141830938857333,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00047406304501216375,
|
|
"loss": 4.8381,
|
|
"mean_token_accuracy": 0.21738937646150588,
|
|
"num_tokens": 35546903.0,
|
|
"step": 19325
|
|
},
|
|
{
|
|
"entropy": 5.328643369674682,
|
|
"epoch": 1.6146007350484464,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00047404916706511255,
|
|
"loss": 4.8098,
|
|
"mean_token_accuracy": 0.21965759992599487,
|
|
"num_tokens": 35556198.0,
|
|
"step": 19330
|
|
},
|
|
{
|
|
"entropy": 5.4151218891143795,
|
|
"epoch": 1.6150183762111594,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.00047403528563346603,
|
|
"loss": 4.9702,
|
|
"mean_token_accuracy": 0.2107398360967636,
|
|
"num_tokens": 35566381.0,
|
|
"step": 19335
|
|
},
|
|
{
|
|
"entropy": 5.28606538772583,
|
|
"epoch": 1.6154360173738724,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00047402140071746743,
|
|
"loss": 4.8065,
|
|
"mean_token_accuracy": 0.22917816787958145,
|
|
"num_tokens": 35575692.0,
|
|
"step": 19340
|
|
},
|
|
{
|
|
"entropy": 5.318668413162231,
|
|
"epoch": 1.6158536585365852,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00047400751231735946,
|
|
"loss": 4.8204,
|
|
"mean_token_accuracy": 0.21764907389879226,
|
|
"num_tokens": 35584783.0,
|
|
"step": 19345
|
|
},
|
|
{
|
|
"entropy": 5.365502262115479,
|
|
"epoch": 1.6162712996992985,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00047399362043338547,
|
|
"loss": 4.8677,
|
|
"mean_token_accuracy": 0.21320993453264236,
|
|
"num_tokens": 35595410.0,
|
|
"step": 19350
|
|
},
|
|
{
|
|
"entropy": 5.31850790977478,
|
|
"epoch": 1.6166889408620113,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004739797250657887,
|
|
"loss": 4.7563,
|
|
"mean_token_accuracy": 0.21946710497140884,
|
|
"num_tokens": 35604950.0,
|
|
"step": 19355
|
|
},
|
|
{
|
|
"entropy": 5.334217596054077,
|
|
"epoch": 1.6171065820247243,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00047396582621481224,
|
|
"loss": 4.8649,
|
|
"mean_token_accuracy": 0.20896225571632385,
|
|
"num_tokens": 35614227.0,
|
|
"step": 19360
|
|
},
|
|
{
|
|
"entropy": 5.309563827514649,
|
|
"epoch": 1.6175242231874374,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00047395192388069955,
|
|
"loss": 4.8607,
|
|
"mean_token_accuracy": 0.21549152731895446,
|
|
"num_tokens": 35623349.0,
|
|
"step": 19365
|
|
},
|
|
{
|
|
"entropy": 5.2865800857543945,
|
|
"epoch": 1.6179418643501502,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00047393801806369396,
|
|
"loss": 4.6935,
|
|
"mean_token_accuracy": 0.23267815858125687,
|
|
"num_tokens": 35632169.0,
|
|
"step": 19370
|
|
},
|
|
{
|
|
"entropy": 5.316283893585205,
|
|
"epoch": 1.6183595055128634,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00047392410876403887,
|
|
"loss": 4.9076,
|
|
"mean_token_accuracy": 0.2131730318069458,
|
|
"num_tokens": 35642121.0,
|
|
"step": 19375
|
|
},
|
|
{
|
|
"entropy": 5.446453619003296,
|
|
"epoch": 1.6187771466755763,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00047391019598197785,
|
|
"loss": 4.8839,
|
|
"mean_token_accuracy": 0.21426323056221008,
|
|
"num_tokens": 35651771.0,
|
|
"step": 19380
|
|
},
|
|
{
|
|
"entropy": 5.339996385574341,
|
|
"epoch": 1.6191947878382893,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004738962797177544,
|
|
"loss": 4.8387,
|
|
"mean_token_accuracy": 0.21851587295532227,
|
|
"num_tokens": 35661422.0,
|
|
"step": 19385
|
|
},
|
|
{
|
|
"entropy": 5.371410083770752,
|
|
"epoch": 1.6196124290010023,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004738823599716121,
|
|
"loss": 4.9358,
|
|
"mean_token_accuracy": 0.20919376909732817,
|
|
"num_tokens": 35672245.0,
|
|
"step": 19390
|
|
},
|
|
{
|
|
"entropy": 5.346766948699951,
|
|
"epoch": 1.6200300701637154,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00047386843674379484,
|
|
"loss": 4.853,
|
|
"mean_token_accuracy": 0.21161638647317887,
|
|
"num_tokens": 35681690.0,
|
|
"step": 19395
|
|
},
|
|
{
|
|
"entropy": 5.286369752883911,
|
|
"epoch": 1.6204477113264284,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004738545100345461,
|
|
"loss": 4.7267,
|
|
"mean_token_accuracy": 0.23488599956035613,
|
|
"num_tokens": 35690265.0,
|
|
"step": 19400
|
|
},
|
|
{
|
|
"entropy": 5.369148874282837,
|
|
"epoch": 1.6208653524891412,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00047384057984410985,
|
|
"loss": 4.874,
|
|
"mean_token_accuracy": 0.2169542670249939,
|
|
"num_tokens": 35699768.0,
|
|
"step": 19405
|
|
},
|
|
{
|
|
"entropy": 5.301404809951782,
|
|
"epoch": 1.6212829936518545,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00047382664617272985,
|
|
"loss": 4.8227,
|
|
"mean_token_accuracy": 0.21753614842891694,
|
|
"num_tokens": 35708785.0,
|
|
"step": 19410
|
|
},
|
|
{
|
|
"entropy": 5.365820026397705,
|
|
"epoch": 1.6217006348145673,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00047381270902065013,
|
|
"loss": 4.8731,
|
|
"mean_token_accuracy": 0.2140580490231514,
|
|
"num_tokens": 35719224.0,
|
|
"step": 19415
|
|
},
|
|
{
|
|
"entropy": 5.385300970077514,
|
|
"epoch": 1.6221182759772803,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00047379876838811463,
|
|
"loss": 4.8783,
|
|
"mean_token_accuracy": 0.21509467363357543,
|
|
"num_tokens": 35727830.0,
|
|
"step": 19420
|
|
},
|
|
{
|
|
"entropy": 5.369791698455811,
|
|
"epoch": 1.6225359171399933,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004737848242753674,
|
|
"loss": 4.8567,
|
|
"mean_token_accuracy": 0.22136381268501282,
|
|
"num_tokens": 35736818.0,
|
|
"step": 19425
|
|
},
|
|
{
|
|
"entropy": 5.315840339660644,
|
|
"epoch": 1.6229535583027062,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004737708766826525,
|
|
"loss": 4.7771,
|
|
"mean_token_accuracy": 0.21747180074453354,
|
|
"num_tokens": 35746009.0,
|
|
"step": 19430
|
|
},
|
|
{
|
|
"entropy": 5.312123155593872,
|
|
"epoch": 1.6233711994654194,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004737569256102142,
|
|
"loss": 4.7073,
|
|
"mean_token_accuracy": 0.22872732281684877,
|
|
"num_tokens": 35754012.0,
|
|
"step": 19435
|
|
},
|
|
{
|
|
"entropy": 5.300389337539673,
|
|
"epoch": 1.6237888406281322,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00047374297105829663,
|
|
"loss": 4.8646,
|
|
"mean_token_accuracy": 0.22073235660791396,
|
|
"num_tokens": 35763709.0,
|
|
"step": 19440
|
|
},
|
|
{
|
|
"entropy": 5.343379926681519,
|
|
"epoch": 1.6242064817908453,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00047372901302714413,
|
|
"loss": 4.8859,
|
|
"mean_token_accuracy": 0.2185371458530426,
|
|
"num_tokens": 35773457.0,
|
|
"step": 19445
|
|
},
|
|
{
|
|
"entropy": 5.27977032661438,
|
|
"epoch": 1.6246241229535583,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00047371505151700105,
|
|
"loss": 4.7418,
|
|
"mean_token_accuracy": 0.22872936725616455,
|
|
"num_tokens": 35781713.0,
|
|
"step": 19450
|
|
},
|
|
{
|
|
"entropy": 5.286924505233765,
|
|
"epoch": 1.6250417641162713,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00047370108652811186,
|
|
"loss": 4.7378,
|
|
"mean_token_accuracy": 0.22434602230787276,
|
|
"num_tokens": 35790796.0,
|
|
"step": 19455
|
|
},
|
|
{
|
|
"entropy": 5.289451265335083,
|
|
"epoch": 1.6254594052789844,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004736871180607209,
|
|
"loss": 4.753,
|
|
"mean_token_accuracy": 0.2218546152114868,
|
|
"num_tokens": 35799919.0,
|
|
"step": 19460
|
|
},
|
|
{
|
|
"entropy": 5.405922174453735,
|
|
"epoch": 1.6258770464416972,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00047367314611507276,
|
|
"loss": 4.9277,
|
|
"mean_token_accuracy": 0.21791574656963347,
|
|
"num_tokens": 35809642.0,
|
|
"step": 19465
|
|
},
|
|
{
|
|
"entropy": 5.390221691131591,
|
|
"epoch": 1.6262946876044104,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00047365917069141215,
|
|
"loss": 4.8498,
|
|
"mean_token_accuracy": 0.21891873925924302,
|
|
"num_tokens": 35819020.0,
|
|
"step": 19470
|
|
},
|
|
{
|
|
"entropy": 5.4482574462890625,
|
|
"epoch": 1.6267123287671232,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004736451917899835,
|
|
"loss": 4.8568,
|
|
"mean_token_accuracy": 0.2183689743280411,
|
|
"num_tokens": 35827657.0,
|
|
"step": 19475
|
|
},
|
|
{
|
|
"entropy": 5.326468896865845,
|
|
"epoch": 1.6271299699298363,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004736312094110317,
|
|
"loss": 4.8475,
|
|
"mean_token_accuracy": 0.21399174630641937,
|
|
"num_tokens": 35836727.0,
|
|
"step": 19480
|
|
},
|
|
{
|
|
"entropy": 5.2412184715271,
|
|
"epoch": 1.6275476110925493,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004736172235548016,
|
|
"loss": 4.7932,
|
|
"mean_token_accuracy": 0.21801301687955857,
|
|
"num_tokens": 35846251.0,
|
|
"step": 19485
|
|
},
|
|
{
|
|
"entropy": 5.345685625076294,
|
|
"epoch": 1.6279652522552621,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004736032342215378,
|
|
"loss": 4.7496,
|
|
"mean_token_accuracy": 0.22172375172376632,
|
|
"num_tokens": 35855736.0,
|
|
"step": 19490
|
|
},
|
|
{
|
|
"entropy": 5.340383720397949,
|
|
"epoch": 1.6283828934179754,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00047358924141148543,
|
|
"loss": 4.7723,
|
|
"mean_token_accuracy": 0.23482287526130677,
|
|
"num_tokens": 35864630.0,
|
|
"step": 19495
|
|
},
|
|
{
|
|
"entropy": 5.368928623199463,
|
|
"epoch": 1.6288005345806882,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00047357524512488925,
|
|
"loss": 4.8681,
|
|
"mean_token_accuracy": 0.2135633111000061,
|
|
"num_tokens": 35874021.0,
|
|
"step": 19500
|
|
},
|
|
{
|
|
"entropy": 5.330666589736938,
|
|
"epoch": 1.6292181757434012,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004735612453619944,
|
|
"loss": 4.8272,
|
|
"mean_token_accuracy": 0.21555425971746445,
|
|
"num_tokens": 35882696.0,
|
|
"step": 19505
|
|
},
|
|
{
|
|
"entropy": 5.413573312759399,
|
|
"epoch": 1.6296358169061143,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000473547242123046,
|
|
"loss": 4.9519,
|
|
"mean_token_accuracy": 0.20785228610038758,
|
|
"num_tokens": 35892887.0,
|
|
"step": 19510
|
|
},
|
|
{
|
|
"entropy": 5.316745376586914,
|
|
"epoch": 1.6300534580688273,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004735332354082891,
|
|
"loss": 4.7511,
|
|
"mean_token_accuracy": 0.22570804357528687,
|
|
"num_tokens": 35901547.0,
|
|
"step": 19515
|
|
},
|
|
{
|
|
"entropy": 5.400396108627319,
|
|
"epoch": 1.6304710992315403,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00047351922521796894,
|
|
"loss": 4.9419,
|
|
"mean_token_accuracy": 0.2185885265469551,
|
|
"num_tokens": 35910982.0,
|
|
"step": 19520
|
|
},
|
|
{
|
|
"entropy": 5.354145526885986,
|
|
"epoch": 1.6308887403942531,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004735052115523307,
|
|
"loss": 4.8586,
|
|
"mean_token_accuracy": 0.21650284975767137,
|
|
"num_tokens": 35920548.0,
|
|
"step": 19525
|
|
},
|
|
{
|
|
"entropy": 5.450076246261597,
|
|
"epoch": 1.6313063815569664,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004734911944116199,
|
|
"loss": 4.8681,
|
|
"mean_token_accuracy": 0.21432718485593796,
|
|
"num_tokens": 35930371.0,
|
|
"step": 19530
|
|
},
|
|
{
|
|
"entropy": 5.338832998275757,
|
|
"epoch": 1.6317240227196792,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00047347717379608184,
|
|
"loss": 4.8987,
|
|
"mean_token_accuracy": 0.21362973749637604,
|
|
"num_tokens": 35939724.0,
|
|
"step": 19535
|
|
},
|
|
{
|
|
"entropy": 5.446009922027588,
|
|
"epoch": 1.6321416638823922,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00047346314970596185,
|
|
"loss": 4.9886,
|
|
"mean_token_accuracy": 0.20647062808275224,
|
|
"num_tokens": 35949432.0,
|
|
"step": 19540
|
|
},
|
|
{
|
|
"entropy": 5.489247989654541,
|
|
"epoch": 1.6325593050451053,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00047344912214150565,
|
|
"loss": 4.9445,
|
|
"mean_token_accuracy": 0.21296210139989852,
|
|
"num_tokens": 35958687.0,
|
|
"step": 19545
|
|
},
|
|
{
|
|
"entropy": 5.335080909729004,
|
|
"epoch": 1.632976946207818,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004734350911029586,
|
|
"loss": 4.8892,
|
|
"mean_token_accuracy": 0.21249944269657134,
|
|
"num_tokens": 35967875.0,
|
|
"step": 19550
|
|
},
|
|
{
|
|
"entropy": 5.317929601669311,
|
|
"epoch": 1.6333945873705313,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00047342105659056645,
|
|
"loss": 4.7844,
|
|
"mean_token_accuracy": 0.22746144086122513,
|
|
"num_tokens": 35977561.0,
|
|
"step": 19555
|
|
},
|
|
{
|
|
"entropy": 5.337922811508179,
|
|
"epoch": 1.6338122285332441,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004734070186045749,
|
|
"loss": 4.8042,
|
|
"mean_token_accuracy": 0.22247435450553893,
|
|
"num_tokens": 35986733.0,
|
|
"step": 19560
|
|
},
|
|
{
|
|
"entropy": 5.32690167427063,
|
|
"epoch": 1.6342298696959572,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004733929771452296,
|
|
"loss": 4.7881,
|
|
"mean_token_accuracy": 0.22127874195575714,
|
|
"num_tokens": 35995779.0,
|
|
"step": 19565
|
|
},
|
|
{
|
|
"entropy": 5.306561422348023,
|
|
"epoch": 1.6346475108586702,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004733789322127764,
|
|
"loss": 4.9044,
|
|
"mean_token_accuracy": 0.21889352798461914,
|
|
"num_tokens": 36004601.0,
|
|
"step": 19570
|
|
},
|
|
{
|
|
"entropy": 5.27778992652893,
|
|
"epoch": 1.6350651520213833,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004733648838074613,
|
|
"loss": 4.7786,
|
|
"mean_token_accuracy": 0.22158322483301163,
|
|
"num_tokens": 36014356.0,
|
|
"step": 19575
|
|
},
|
|
{
|
|
"entropy": 5.30598406791687,
|
|
"epoch": 1.6354827931840963,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00047335083192953,
|
|
"loss": 4.7257,
|
|
"mean_token_accuracy": 0.23023256957530974,
|
|
"num_tokens": 36023084.0,
|
|
"step": 19580
|
|
},
|
|
{
|
|
"entropy": 5.335194158554077,
|
|
"epoch": 1.635900434346809,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004733367765792288,
|
|
"loss": 4.8006,
|
|
"mean_token_accuracy": 0.21890983432531358,
|
|
"num_tokens": 36031462.0,
|
|
"step": 19585
|
|
},
|
|
{
|
|
"entropy": 5.320765733718872,
|
|
"epoch": 1.6363180755095224,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00047332271775680346,
|
|
"loss": 4.7605,
|
|
"mean_token_accuracy": 0.22561126202344894,
|
|
"num_tokens": 36041107.0,
|
|
"step": 19590
|
|
},
|
|
{
|
|
"entropy": 5.307850122451782,
|
|
"epoch": 1.6367357166722352,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004733086554625004,
|
|
"loss": 4.8458,
|
|
"mean_token_accuracy": 0.21833008974790574,
|
|
"num_tokens": 36050026.0,
|
|
"step": 19595
|
|
},
|
|
{
|
|
"entropy": 5.289339542388916,
|
|
"epoch": 1.6371533578349482,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004732945896965654,
|
|
"loss": 4.8303,
|
|
"mean_token_accuracy": 0.22080338299274443,
|
|
"num_tokens": 36058858.0,
|
|
"step": 19600
|
|
},
|
|
{
|
|
"entropy": 5.357577180862426,
|
|
"epoch": 1.6375709989976612,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00047328052045924506,
|
|
"loss": 4.9113,
|
|
"mean_token_accuracy": 0.2156285747885704,
|
|
"num_tokens": 36067995.0,
|
|
"step": 19605
|
|
},
|
|
{
|
|
"entropy": 5.310854768753051,
|
|
"epoch": 1.637988640160374,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004732664477507855,
|
|
"loss": 4.7918,
|
|
"mean_token_accuracy": 0.227165687084198,
|
|
"num_tokens": 36077425.0,
|
|
"step": 19610
|
|
},
|
|
{
|
|
"entropy": 5.312691593170166,
|
|
"epoch": 1.6384062813230873,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00047325237157143314,
|
|
"loss": 4.8159,
|
|
"mean_token_accuracy": 0.21530702263116835,
|
|
"num_tokens": 36086667.0,
|
|
"step": 19615
|
|
},
|
|
{
|
|
"entropy": 5.331459331512451,
|
|
"epoch": 1.6388239224858,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00047323829192143436,
|
|
"loss": 4.7829,
|
|
"mean_token_accuracy": 0.231000417470932,
|
|
"num_tokens": 36095199.0,
|
|
"step": 19620
|
|
},
|
|
{
|
|
"entropy": 5.283569097518921,
|
|
"epoch": 1.6392415636485131,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00047322420880103566,
|
|
"loss": 4.7775,
|
|
"mean_token_accuracy": 0.2246996507048607,
|
|
"num_tokens": 36104587.0,
|
|
"step": 19625
|
|
},
|
|
{
|
|
"entropy": 5.364696502685547,
|
|
"epoch": 1.6396592048112262,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004732101222104836,
|
|
"loss": 4.814,
|
|
"mean_token_accuracy": 0.22391128540039062,
|
|
"num_tokens": 36114017.0,
|
|
"step": 19630
|
|
},
|
|
{
|
|
"entropy": 5.329492712020874,
|
|
"epoch": 1.6400768459739392,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004731960321500247,
|
|
"loss": 4.8411,
|
|
"mean_token_accuracy": 0.21676065027713776,
|
|
"num_tokens": 36122301.0,
|
|
"step": 19635
|
|
},
|
|
{
|
|
"entropy": 5.26802167892456,
|
|
"epoch": 1.6404944871366522,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004731819386199058,
|
|
"loss": 4.8161,
|
|
"mean_token_accuracy": 0.2239148274064064,
|
|
"num_tokens": 36131538.0,
|
|
"step": 19640
|
|
},
|
|
{
|
|
"entropy": 5.346430349349975,
|
|
"epoch": 1.640912128299365,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004731678416203734,
|
|
"loss": 4.813,
|
|
"mean_token_accuracy": 0.21506955921649934,
|
|
"num_tokens": 36140472.0,
|
|
"step": 19645
|
|
},
|
|
{
|
|
"entropy": 5.368073225021362,
|
|
"epoch": 1.6413297694620783,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00047315374115167446,
|
|
"loss": 4.8054,
|
|
"mean_token_accuracy": 0.2289508894085884,
|
|
"num_tokens": 36148947.0,
|
|
"step": 19650
|
|
},
|
|
{
|
|
"entropy": 5.294363212585449,
|
|
"epoch": 1.6417474106247911,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004731396372140558,
|
|
"loss": 4.7757,
|
|
"mean_token_accuracy": 0.22407459169626237,
|
|
"num_tokens": 36157895.0,
|
|
"step": 19655
|
|
},
|
|
{
|
|
"entropy": 5.310103178024292,
|
|
"epoch": 1.6421650517875042,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004731255298077642,
|
|
"loss": 4.811,
|
|
"mean_token_accuracy": 0.23024173676967621,
|
|
"num_tokens": 36168170.0,
|
|
"step": 19660
|
|
},
|
|
{
|
|
"entropy": 5.3525642395019535,
|
|
"epoch": 1.6425826929502172,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00047311141893304675,
|
|
"loss": 4.8756,
|
|
"mean_token_accuracy": 0.21417064666748048,
|
|
"num_tokens": 36176864.0,
|
|
"step": 19665
|
|
},
|
|
{
|
|
"entropy": 5.424006509780884,
|
|
"epoch": 1.64300033411293,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004730973045901505,
|
|
"loss": 4.8697,
|
|
"mean_token_accuracy": 0.21832744628190995,
|
|
"num_tokens": 36186334.0,
|
|
"step": 19670
|
|
},
|
|
{
|
|
"entropy": 5.372613525390625,
|
|
"epoch": 1.6434179752756433,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00047308318677932243,
|
|
"loss": 4.8639,
|
|
"mean_token_accuracy": 0.22326751202344894,
|
|
"num_tokens": 36194688.0,
|
|
"step": 19675
|
|
},
|
|
{
|
|
"entropy": 5.277593421936035,
|
|
"epoch": 1.643835616438356,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004730690655008097,
|
|
"loss": 4.8328,
|
|
"mean_token_accuracy": 0.21853417456150054,
|
|
"num_tokens": 36203962.0,
|
|
"step": 19680
|
|
},
|
|
{
|
|
"entropy": 5.395094585418701,
|
|
"epoch": 1.644253257601069,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004730549407548597,
|
|
"loss": 4.8902,
|
|
"mean_token_accuracy": 0.20936068296432495,
|
|
"num_tokens": 36212780.0,
|
|
"step": 19685
|
|
},
|
|
{
|
|
"entropy": 5.432841825485229,
|
|
"epoch": 1.6446708987637821,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00047304081254171944,
|
|
"loss": 4.8548,
|
|
"mean_token_accuracy": 0.2165484070777893,
|
|
"num_tokens": 36221744.0,
|
|
"step": 19690
|
|
},
|
|
{
|
|
"entropy": 5.369046068191528,
|
|
"epoch": 1.6450885399264952,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004730266808616364,
|
|
"loss": 4.9189,
|
|
"mean_token_accuracy": 0.2191567078232765,
|
|
"num_tokens": 36231261.0,
|
|
"step": 19695
|
|
},
|
|
{
|
|
"entropy": 5.290555000305176,
|
|
"epoch": 1.6455061810892082,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000473012545714858,
|
|
"loss": 4.8305,
|
|
"mean_token_accuracy": 0.21968261748552323,
|
|
"num_tokens": 36240599.0,
|
|
"step": 19700
|
|
},
|
|
{
|
|
"entropy": 5.237027502059936,
|
|
"epoch": 1.645923822251921,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00047299840710163157,
|
|
"loss": 4.7051,
|
|
"mean_token_accuracy": 0.22928525358438492,
|
|
"num_tokens": 36249402.0,
|
|
"step": 19705
|
|
},
|
|
{
|
|
"entropy": 5.366367626190185,
|
|
"epoch": 1.6463414634146343,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004729842650222047,
|
|
"loss": 4.7678,
|
|
"mean_token_accuracy": 0.2239456832408905,
|
|
"num_tokens": 36258379.0,
|
|
"step": 19710
|
|
},
|
|
{
|
|
"entropy": 5.303768157958984,
|
|
"epoch": 1.646759104577347,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00047297011947682494,
|
|
"loss": 4.8257,
|
|
"mean_token_accuracy": 0.22369505912065507,
|
|
"num_tokens": 36267393.0,
|
|
"step": 19715
|
|
},
|
|
{
|
|
"entropy": 5.377106428146362,
|
|
"epoch": 1.6471767457400601,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00047295597046574,
|
|
"loss": 4.868,
|
|
"mean_token_accuracy": 0.22274216413497924,
|
|
"num_tokens": 36277542.0,
|
|
"step": 19720
|
|
},
|
|
{
|
|
"entropy": 5.345974731445312,
|
|
"epoch": 1.6475943869027732,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004729418179891975,
|
|
"loss": 4.8721,
|
|
"mean_token_accuracy": 0.21395675837993622,
|
|
"num_tokens": 36287623.0,
|
|
"step": 19725
|
|
},
|
|
{
|
|
"entropy": 5.273536586761475,
|
|
"epoch": 1.6480120280654862,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004729276620474452,
|
|
"loss": 4.7719,
|
|
"mean_token_accuracy": 0.22755952328443527,
|
|
"num_tokens": 36295828.0,
|
|
"step": 19730
|
|
},
|
|
{
|
|
"entropy": 5.341281175613403,
|
|
"epoch": 1.6484296692281992,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00047291350264073095,
|
|
"loss": 4.8247,
|
|
"mean_token_accuracy": 0.2158269926905632,
|
|
"num_tokens": 36304825.0,
|
|
"step": 19735
|
|
},
|
|
{
|
|
"entropy": 5.341085004806518,
|
|
"epoch": 1.648847310390912,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00047289933976930263,
|
|
"loss": 4.8613,
|
|
"mean_token_accuracy": 0.2166446104645729,
|
|
"num_tokens": 36313691.0,
|
|
"step": 19740
|
|
},
|
|
{
|
|
"entropy": 5.334024572372437,
|
|
"epoch": 1.6492649515536253,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004728851734334081,
|
|
"loss": 4.802,
|
|
"mean_token_accuracy": 0.22402181923389436,
|
|
"num_tokens": 36323291.0,
|
|
"step": 19745
|
|
},
|
|
{
|
|
"entropy": 5.324472522735595,
|
|
"epoch": 1.649682592716338,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004728710036332954,
|
|
"loss": 4.8216,
|
|
"mean_token_accuracy": 0.2189005047082901,
|
|
"num_tokens": 36332859.0,
|
|
"step": 19750
|
|
},
|
|
{
|
|
"entropy": 5.353691482543946,
|
|
"epoch": 1.6501002338790511,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00047285683036921275,
|
|
"loss": 4.8609,
|
|
"mean_token_accuracy": 0.21894217431545257,
|
|
"num_tokens": 36342049.0,
|
|
"step": 19755
|
|
},
|
|
{
|
|
"entropy": 5.289641094207764,
|
|
"epoch": 1.6505178750417642,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00047284265364140794,
|
|
"loss": 4.7819,
|
|
"mean_token_accuracy": 0.22277661561965942,
|
|
"num_tokens": 36351512.0,
|
|
"step": 19760
|
|
},
|
|
{
|
|
"entropy": 5.336726808547974,
|
|
"epoch": 1.650935516204477,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004728284734501295,
|
|
"loss": 4.8812,
|
|
"mean_token_accuracy": 0.21904736012220383,
|
|
"num_tokens": 36361923.0,
|
|
"step": 19765
|
|
},
|
|
{
|
|
"entropy": 5.321461725234985,
|
|
"epoch": 1.6513531573671902,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004728142897956253,
|
|
"loss": 4.8876,
|
|
"mean_token_accuracy": 0.21570289134979248,
|
|
"num_tokens": 36370543.0,
|
|
"step": 19770
|
|
},
|
|
{
|
|
"entropy": 5.297537326812744,
|
|
"epoch": 1.651770798529903,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000472800102678144,
|
|
"loss": 4.7735,
|
|
"mean_token_accuracy": 0.23069225996732712,
|
|
"num_tokens": 36378465.0,
|
|
"step": 19775
|
|
},
|
|
{
|
|
"entropy": 5.375320482254028,
|
|
"epoch": 1.652188439692616,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00047278591209793384,
|
|
"loss": 4.8735,
|
|
"mean_token_accuracy": 0.21252388805150985,
|
|
"num_tokens": 36387540.0,
|
|
"step": 19780
|
|
},
|
|
{
|
|
"entropy": 5.333769512176514,
|
|
"epoch": 1.6526060808553291,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004727717180552431,
|
|
"loss": 4.8419,
|
|
"mean_token_accuracy": 0.21404000222682953,
|
|
"num_tokens": 36397859.0,
|
|
"step": 19785
|
|
},
|
|
{
|
|
"entropy": 5.282950210571289,
|
|
"epoch": 1.6530237220180422,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00047275752055032043,
|
|
"loss": 4.7543,
|
|
"mean_token_accuracy": 0.228403040766716,
|
|
"num_tokens": 36406955.0,
|
|
"step": 19790
|
|
},
|
|
{
|
|
"entropy": 5.274393892288208,
|
|
"epoch": 1.6534413631807552,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00047274331958341434,
|
|
"loss": 4.7517,
|
|
"mean_token_accuracy": 0.22608184516429902,
|
|
"num_tokens": 36415499.0,
|
|
"step": 19795
|
|
},
|
|
{
|
|
"entropy": 5.3184693336486815,
|
|
"epoch": 1.653859004343468,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004727291151547733,
|
|
"loss": 4.8359,
|
|
"mean_token_accuracy": 0.21226955503225325,
|
|
"num_tokens": 36424348.0,
|
|
"step": 19800
|
|
},
|
|
{
|
|
"entropy": 5.276338958740235,
|
|
"epoch": 1.6542766455061813,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004727149072646463,
|
|
"loss": 4.7653,
|
|
"mean_token_accuracy": 0.22091787308454514,
|
|
"num_tokens": 36433134.0,
|
|
"step": 19805
|
|
},
|
|
{
|
|
"entropy": 5.22176833152771,
|
|
"epoch": 1.654694286668894,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00047270069591328175,
|
|
"loss": 4.7181,
|
|
"mean_token_accuracy": 0.231381918489933,
|
|
"num_tokens": 36442300.0,
|
|
"step": 19810
|
|
},
|
|
{
|
|
"entropy": 5.351193428039551,
|
|
"epoch": 1.655111927831607,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00047268648110092857,
|
|
"loss": 4.8961,
|
|
"mean_token_accuracy": 0.21070681810379027,
|
|
"num_tokens": 36452265.0,
|
|
"step": 19815
|
|
},
|
|
{
|
|
"entropy": 5.362208890914917,
|
|
"epoch": 1.6555295689943201,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00047267226282783555,
|
|
"loss": 4.8439,
|
|
"mean_token_accuracy": 0.22177200764417648,
|
|
"num_tokens": 36462009.0,
|
|
"step": 19820
|
|
},
|
|
{
|
|
"entropy": 5.390650367736816,
|
|
"epoch": 1.655947210157033,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004726580410942516,
|
|
"loss": 4.9524,
|
|
"mean_token_accuracy": 0.21351409405469896,
|
|
"num_tokens": 36470799.0,
|
|
"step": 19825
|
|
},
|
|
{
|
|
"entropy": 5.361070966720581,
|
|
"epoch": 1.6563648513197462,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00047264381590042575,
|
|
"loss": 4.8351,
|
|
"mean_token_accuracy": 0.21223322600126265,
|
|
"num_tokens": 36479362.0,
|
|
"step": 19830
|
|
},
|
|
{
|
|
"entropy": 5.297932100296021,
|
|
"epoch": 1.656782492482459,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000472629587246607,
|
|
"loss": 4.7662,
|
|
"mean_token_accuracy": 0.21901931315660478,
|
|
"num_tokens": 36487773.0,
|
|
"step": 19835
|
|
},
|
|
{
|
|
"entropy": 5.263348197937011,
|
|
"epoch": 1.657200133645172,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00047261535513304446,
|
|
"loss": 4.7372,
|
|
"mean_token_accuracy": 0.23249171376228334,
|
|
"num_tokens": 36496133.0,
|
|
"step": 19840
|
|
},
|
|
{
|
|
"entropy": 5.3581867694854735,
|
|
"epoch": 1.657617774807885,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00047260111955998725,
|
|
"loss": 4.8702,
|
|
"mean_token_accuracy": 0.22430098205804824,
|
|
"num_tokens": 36505392.0,
|
|
"step": 19845
|
|
},
|
|
{
|
|
"entropy": 5.3934290409088135,
|
|
"epoch": 1.6580354159705981,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00047258688052768456,
|
|
"loss": 4.8602,
|
|
"mean_token_accuracy": 0.21580443531274796,
|
|
"num_tokens": 36514876.0,
|
|
"step": 19850
|
|
},
|
|
{
|
|
"entropy": 5.2967675685882565,
|
|
"epoch": 1.6584530571333111,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004725726380363857,
|
|
"loss": 4.7966,
|
|
"mean_token_accuracy": 0.22504319101572037,
|
|
"num_tokens": 36523828.0,
|
|
"step": 19855
|
|
},
|
|
{
|
|
"entropy": 5.337872266769409,
|
|
"epoch": 1.658870698296024,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00047255839208634005,
|
|
"loss": 4.8586,
|
|
"mean_token_accuracy": 0.21759358495473863,
|
|
"num_tokens": 36532263.0,
|
|
"step": 19860
|
|
},
|
|
{
|
|
"entropy": 5.295085144042969,
|
|
"epoch": 1.6592883394587372,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00047254414267779686,
|
|
"loss": 4.7633,
|
|
"mean_token_accuracy": 0.221938419342041,
|
|
"num_tokens": 36541015.0,
|
|
"step": 19865
|
|
},
|
|
{
|
|
"entropy": 5.317872142791748,
|
|
"epoch": 1.65970598062145,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00047252988981100576,
|
|
"loss": 4.848,
|
|
"mean_token_accuracy": 0.2151060849428177,
|
|
"num_tokens": 36550254.0,
|
|
"step": 19870
|
|
},
|
|
{
|
|
"entropy": 5.346270513534546,
|
|
"epoch": 1.660123621784163,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004725156334862161,
|
|
"loss": 4.8799,
|
|
"mean_token_accuracy": 0.20703888386487962,
|
|
"num_tokens": 36560941.0,
|
|
"step": 19875
|
|
},
|
|
{
|
|
"entropy": 5.376393365859985,
|
|
"epoch": 1.660541262946876,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00047250137370367755,
|
|
"loss": 4.8799,
|
|
"mean_token_accuracy": 0.2124037504196167,
|
|
"num_tokens": 36570443.0,
|
|
"step": 19880
|
|
},
|
|
{
|
|
"entropy": 5.3590165138244625,
|
|
"epoch": 1.660958904109589,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00047248711046363976,
|
|
"loss": 4.8603,
|
|
"mean_token_accuracy": 0.217452472448349,
|
|
"num_tokens": 36580532.0,
|
|
"step": 19885
|
|
},
|
|
{
|
|
"entropy": 5.351292991638184,
|
|
"epoch": 1.6613765452723022,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004724728437663523,
|
|
"loss": 4.8101,
|
|
"mean_token_accuracy": 0.225749734044075,
|
|
"num_tokens": 36589359.0,
|
|
"step": 19890
|
|
},
|
|
{
|
|
"entropy": 5.375811529159546,
|
|
"epoch": 1.661794186435015,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00047245857361206506,
|
|
"loss": 4.8519,
|
|
"mean_token_accuracy": 0.21804846972227096,
|
|
"num_tokens": 36598229.0,
|
|
"step": 19895
|
|
},
|
|
{
|
|
"entropy": 5.280156469345092,
|
|
"epoch": 1.662211827597728,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00047244430000102785,
|
|
"loss": 4.7971,
|
|
"mean_token_accuracy": 0.22406931221485138,
|
|
"num_tokens": 36607655.0,
|
|
"step": 19900
|
|
},
|
|
{
|
|
"entropy": 5.371337890625,
|
|
"epoch": 1.662629468760441,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004724300229334905,
|
|
"loss": 4.8563,
|
|
"mean_token_accuracy": 0.2125426024198532,
|
|
"num_tokens": 36618060.0,
|
|
"step": 19905
|
|
},
|
|
{
|
|
"entropy": 5.3163549423217775,
|
|
"epoch": 1.663047109923154,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00047241574240970284,
|
|
"loss": 4.8077,
|
|
"mean_token_accuracy": 0.2205881267786026,
|
|
"num_tokens": 36627825.0,
|
|
"step": 19910
|
|
},
|
|
{
|
|
"entropy": 5.305918264389038,
|
|
"epoch": 1.663464751085867,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00047240145842991513,
|
|
"loss": 4.792,
|
|
"mean_token_accuracy": 0.2263641282916069,
|
|
"num_tokens": 36635971.0,
|
|
"step": 19915
|
|
},
|
|
{
|
|
"entropy": 5.248705244064331,
|
|
"epoch": 1.66388239224858,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00047238717099437713,
|
|
"loss": 4.6762,
|
|
"mean_token_accuracy": 0.2275834023952484,
|
|
"num_tokens": 36644340.0,
|
|
"step": 19920
|
|
},
|
|
{
|
|
"entropy": 5.343120193481445,
|
|
"epoch": 1.6643000334112932,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004723728801033392,
|
|
"loss": 4.8256,
|
|
"mean_token_accuracy": 0.21380512565374374,
|
|
"num_tokens": 36654371.0,
|
|
"step": 19925
|
|
},
|
|
{
|
|
"entropy": 5.300578260421753,
|
|
"epoch": 1.664717674574006,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004723585857570514,
|
|
"loss": 4.7,
|
|
"mean_token_accuracy": 0.23367682695388795,
|
|
"num_tokens": 36663633.0,
|
|
"step": 19930
|
|
},
|
|
{
|
|
"entropy": 5.272553873062134,
|
|
"epoch": 1.665135315736719,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000472344287955764,
|
|
"loss": 4.7139,
|
|
"mean_token_accuracy": 0.23855913281440735,
|
|
"num_tokens": 36673004.0,
|
|
"step": 19935
|
|
},
|
|
{
|
|
"entropy": 5.246767854690551,
|
|
"epoch": 1.665552956899432,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004723299866997273,
|
|
"loss": 4.743,
|
|
"mean_token_accuracy": 0.2353493243455887,
|
|
"num_tokens": 36681323.0,
|
|
"step": 19940
|
|
},
|
|
{
|
|
"entropy": 5.365858173370361,
|
|
"epoch": 1.6659705980621449,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004723156819891917,
|
|
"loss": 4.9154,
|
|
"mean_token_accuracy": 0.20818681865930558,
|
|
"num_tokens": 36691128.0,
|
|
"step": 19945
|
|
},
|
|
{
|
|
"entropy": 5.284007120132446,
|
|
"epoch": 1.6663882392248581,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00047230137382440747,
|
|
"loss": 4.7805,
|
|
"mean_token_accuracy": 0.22609909772872924,
|
|
"num_tokens": 36699759.0,
|
|
"step": 19950
|
|
},
|
|
{
|
|
"entropy": 5.256958818435669,
|
|
"epoch": 1.666805880387571,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004722870622056253,
|
|
"loss": 4.8462,
|
|
"mean_token_accuracy": 0.2155100166797638,
|
|
"num_tokens": 36708723.0,
|
|
"step": 19955
|
|
},
|
|
{
|
|
"entropy": 5.308293294906616,
|
|
"epoch": 1.667223521550284,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004722727471330956,
|
|
"loss": 4.7671,
|
|
"mean_token_accuracy": 0.22067958116531372,
|
|
"num_tokens": 36717488.0,
|
|
"step": 19960
|
|
},
|
|
{
|
|
"entropy": 5.2560209274292,
|
|
"epoch": 1.667641162712997,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000472258428607069,
|
|
"loss": 4.7606,
|
|
"mean_token_accuracy": 0.2218269005417824,
|
|
"num_tokens": 36726477.0,
|
|
"step": 19965
|
|
},
|
|
{
|
|
"entropy": 5.320097732543945,
|
|
"epoch": 1.66805880387571,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004722441066277961,
|
|
"loss": 4.7397,
|
|
"mean_token_accuracy": 0.22388902306556702,
|
|
"num_tokens": 36734676.0,
|
|
"step": 19970
|
|
},
|
|
{
|
|
"entropy": 5.334241914749145,
|
|
"epoch": 1.668476445038423,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00047222978119552776,
|
|
"loss": 4.8777,
|
|
"mean_token_accuracy": 0.21435789614915848,
|
|
"num_tokens": 36744425.0,
|
|
"step": 19975
|
|
},
|
|
{
|
|
"entropy": 5.323871994018555,
|
|
"epoch": 1.6688940862011359,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00047221545231051473,
|
|
"loss": 4.834,
|
|
"mean_token_accuracy": 0.21721132099628448,
|
|
"num_tokens": 36754113.0,
|
|
"step": 19980
|
|
},
|
|
{
|
|
"entropy": 5.308092260360718,
|
|
"epoch": 1.6693117273638491,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004722011199730078,
|
|
"loss": 4.7775,
|
|
"mean_token_accuracy": 0.22284530699253083,
|
|
"num_tokens": 36763013.0,
|
|
"step": 19985
|
|
},
|
|
{
|
|
"entropy": 5.2971961975097654,
|
|
"epoch": 1.669729368526562,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004721867841832579,
|
|
"loss": 4.8403,
|
|
"mean_token_accuracy": 0.21683433502912522,
|
|
"num_tokens": 36772115.0,
|
|
"step": 19990
|
|
},
|
|
{
|
|
"entropy": 5.373669385910034,
|
|
"epoch": 1.670147009689275,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004721724449415159,
|
|
"loss": 4.861,
|
|
"mean_token_accuracy": 0.21445745080709458,
|
|
"num_tokens": 36781210.0,
|
|
"step": 19995
|
|
},
|
|
{
|
|
"entropy": 5.432449531555176,
|
|
"epoch": 1.670564650851988,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00047215810224803304,
|
|
"loss": 4.9101,
|
|
"mean_token_accuracy": 0.21426810026168824,
|
|
"num_tokens": 36791131.0,
|
|
"step": 20000
|
|
},
|
|
{
|
|
"entropy": 5.3057355880737305,
|
|
"epoch": 1.6709822920147008,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00047214375610306016,
|
|
"loss": 4.7117,
|
|
"mean_token_accuracy": 0.2311200439929962,
|
|
"num_tokens": 36800618.0,
|
|
"step": 20005
|
|
},
|
|
{
|
|
"entropy": 5.322934246063232,
|
|
"epoch": 1.671399933177414,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00047212940650684853,
|
|
"loss": 4.8627,
|
|
"mean_token_accuracy": 0.21487412005662918,
|
|
"num_tokens": 36809995.0,
|
|
"step": 20010
|
|
},
|
|
{
|
|
"entropy": 5.354308652877807,
|
|
"epoch": 1.671817574340127,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004721150534596495,
|
|
"loss": 4.8733,
|
|
"mean_token_accuracy": 0.21463162451982498,
|
|
"num_tokens": 36818492.0,
|
|
"step": 20015
|
|
},
|
|
{
|
|
"entropy": 5.354475975036621,
|
|
"epoch": 1.67223521550284,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000472100696961714,
|
|
"loss": 4.8077,
|
|
"mean_token_accuracy": 0.220961856842041,
|
|
"num_tokens": 36827280.0,
|
|
"step": 20020
|
|
},
|
|
{
|
|
"entropy": 5.324013328552246,
|
|
"epoch": 1.672652856665553,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004720863370132937,
|
|
"loss": 4.8764,
|
|
"mean_token_accuracy": 0.22000210285186766,
|
|
"num_tokens": 36837931.0,
|
|
"step": 20025
|
|
},
|
|
{
|
|
"entropy": 5.3531571388244625,
|
|
"epoch": 1.673070497828266,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004720719736146398,
|
|
"loss": 4.8984,
|
|
"mean_token_accuracy": 0.21713228076696395,
|
|
"num_tokens": 36847581.0,
|
|
"step": 20030
|
|
},
|
|
{
|
|
"entropy": 5.348424768447876,
|
|
"epoch": 1.673488138990979,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00047205760676600377,
|
|
"loss": 4.808,
|
|
"mean_token_accuracy": 0.21730990409851075,
|
|
"num_tokens": 36857147.0,
|
|
"step": 20035
|
|
},
|
|
{
|
|
"entropy": 5.31234974861145,
|
|
"epoch": 1.6739057801536918,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004720432364676372,
|
|
"loss": 4.8037,
|
|
"mean_token_accuracy": 0.21774123311042787,
|
|
"num_tokens": 36866105.0,
|
|
"step": 20040
|
|
},
|
|
{
|
|
"entropy": 5.348181438446045,
|
|
"epoch": 1.674323421316405,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004720288627197915,
|
|
"loss": 4.7725,
|
|
"mean_token_accuracy": 0.22818531841039658,
|
|
"num_tokens": 36874631.0,
|
|
"step": 20045
|
|
},
|
|
{
|
|
"entropy": 5.303670644760132,
|
|
"epoch": 1.674741062479118,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004720144855227185,
|
|
"loss": 4.7425,
|
|
"mean_token_accuracy": 0.2300627589225769,
|
|
"num_tokens": 36884264.0,
|
|
"step": 20050
|
|
},
|
|
{
|
|
"entropy": 5.38627061843872,
|
|
"epoch": 1.675158703641831,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004720001048766696,
|
|
"loss": 4.8455,
|
|
"mean_token_accuracy": 0.21649623662233353,
|
|
"num_tokens": 36893143.0,
|
|
"step": 20055
|
|
},
|
|
{
|
|
"entropy": 5.414267206192017,
|
|
"epoch": 1.675576344804544,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004719857207818969,
|
|
"loss": 4.8922,
|
|
"mean_token_accuracy": 0.21320904940366744,
|
|
"num_tokens": 36903026.0,
|
|
"step": 20060
|
|
},
|
|
{
|
|
"entropy": 5.425397443771362,
|
|
"epoch": 1.6759939859672568,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000471971333238652,
|
|
"loss": 4.9246,
|
|
"mean_token_accuracy": 0.21479999423027038,
|
|
"num_tokens": 36912737.0,
|
|
"step": 20065
|
|
},
|
|
{
|
|
"entropy": 5.3933424949646,
|
|
"epoch": 1.67641162712997,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00047195694224718684,
|
|
"loss": 4.8859,
|
|
"mean_token_accuracy": 0.21575685441493989,
|
|
"num_tokens": 36921148.0,
|
|
"step": 20070
|
|
},
|
|
{
|
|
"entropy": 5.277033424377441,
|
|
"epoch": 1.6768292682926829,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00047194254780775325,
|
|
"loss": 4.7217,
|
|
"mean_token_accuracy": 0.22983353734016418,
|
|
"num_tokens": 36930043.0,
|
|
"step": 20075
|
|
},
|
|
{
|
|
"entropy": 5.3779150485992435,
|
|
"epoch": 1.677246909455396,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004719281499206034,
|
|
"loss": 4.8815,
|
|
"mean_token_accuracy": 0.21999380141496658,
|
|
"num_tokens": 36939124.0,
|
|
"step": 20080
|
|
},
|
|
{
|
|
"entropy": 5.461601448059082,
|
|
"epoch": 1.677664550618109,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00047191374858598917,
|
|
"loss": 4.9595,
|
|
"mean_token_accuracy": 0.21597303301095963,
|
|
"num_tokens": 36948392.0,
|
|
"step": 20085
|
|
},
|
|
{
|
|
"entropy": 5.3686192512512205,
|
|
"epoch": 1.678082191780822,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004718993438041628,
|
|
"loss": 4.8381,
|
|
"mean_token_accuracy": 0.21508717238903047,
|
|
"num_tokens": 36958019.0,
|
|
"step": 20090
|
|
},
|
|
{
|
|
"entropy": 5.343065881729126,
|
|
"epoch": 1.678499832943535,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00047188493557537634,
|
|
"loss": 4.7959,
|
|
"mean_token_accuracy": 0.2155509352684021,
|
|
"num_tokens": 36966904.0,
|
|
"step": 20095
|
|
},
|
|
{
|
|
"entropy": 5.409378337860107,
|
|
"epoch": 1.6789174741062478,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004718705238998822,
|
|
"loss": 4.8596,
|
|
"mean_token_accuracy": 0.22004503458738328,
|
|
"num_tokens": 36976085.0,
|
|
"step": 20100
|
|
},
|
|
{
|
|
"entropy": 5.338793563842773,
|
|
"epoch": 1.679335115268961,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00047185610877793245,
|
|
"loss": 4.7931,
|
|
"mean_token_accuracy": 0.22810618579387665,
|
|
"num_tokens": 36984345.0,
|
|
"step": 20105
|
|
},
|
|
{
|
|
"entropy": 5.293026351928711,
|
|
"epoch": 1.6797527564316739,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00047184169020977965,
|
|
"loss": 4.7926,
|
|
"mean_token_accuracy": 0.22434153854846955,
|
|
"num_tokens": 36993133.0,
|
|
"step": 20110
|
|
},
|
|
{
|
|
"entropy": 5.321643924713134,
|
|
"epoch": 1.680170397594387,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00047182726819567603,
|
|
"loss": 4.8699,
|
|
"mean_token_accuracy": 0.2183228150010109,
|
|
"num_tokens": 37002797.0,
|
|
"step": 20115
|
|
},
|
|
{
|
|
"entropy": 5.424343919754028,
|
|
"epoch": 1.6805880387571,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00047181284273587414,
|
|
"loss": 4.7918,
|
|
"mean_token_accuracy": 0.21798250675201417,
|
|
"num_tokens": 37012598.0,
|
|
"step": 20120
|
|
},
|
|
{
|
|
"entropy": 5.366627550125122,
|
|
"epoch": 1.6810056799198128,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00047179841383062667,
|
|
"loss": 4.8006,
|
|
"mean_token_accuracy": 0.23106136471033095,
|
|
"num_tokens": 37022006.0,
|
|
"step": 20125
|
|
},
|
|
{
|
|
"entropy": 5.263238000869751,
|
|
"epoch": 1.681423321082526,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00047178398148018606,
|
|
"loss": 4.7415,
|
|
"mean_token_accuracy": 0.22541175782680511,
|
|
"num_tokens": 37030713.0,
|
|
"step": 20130
|
|
},
|
|
{
|
|
"entropy": 5.286446666717529,
|
|
"epoch": 1.6818409622452388,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004717695456848049,
|
|
"loss": 4.8089,
|
|
"mean_token_accuracy": 0.22712857276201248,
|
|
"num_tokens": 37039347.0,
|
|
"step": 20135
|
|
},
|
|
{
|
|
"entropy": 5.384392786026001,
|
|
"epoch": 1.6822586034079519,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004717551064447361,
|
|
"loss": 4.8743,
|
|
"mean_token_accuracy": 0.2137928932905197,
|
|
"num_tokens": 37048010.0,
|
|
"step": 20140
|
|
},
|
|
{
|
|
"entropy": 5.307309961318969,
|
|
"epoch": 1.682676244570665,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004717406637602322,
|
|
"loss": 4.7486,
|
|
"mean_token_accuracy": 0.21717305034399031,
|
|
"num_tokens": 37056517.0,
|
|
"step": 20145
|
|
},
|
|
{
|
|
"entropy": 5.338075113296509,
|
|
"epoch": 1.683093885733378,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004717262176315462,
|
|
"loss": 4.797,
|
|
"mean_token_accuracy": 0.21399285197257994,
|
|
"num_tokens": 37065085.0,
|
|
"step": 20150
|
|
},
|
|
{
|
|
"entropy": 5.319853258132935,
|
|
"epoch": 1.683511526896091,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000471711768058931,
|
|
"loss": 4.7629,
|
|
"mean_token_accuracy": 0.22676407247781755,
|
|
"num_tokens": 37074483.0,
|
|
"step": 20155
|
|
},
|
|
{
|
|
"entropy": 5.369939804077148,
|
|
"epoch": 1.6839291680588038,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004716973150426395,
|
|
"loss": 4.8592,
|
|
"mean_token_accuracy": 0.22004493325948715,
|
|
"num_tokens": 37083679.0,
|
|
"step": 20160
|
|
},
|
|
{
|
|
"entropy": 5.308606243133545,
|
|
"epoch": 1.684346809221517,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00047168285858292477,
|
|
"loss": 4.8151,
|
|
"mean_token_accuracy": 0.22150168418884278,
|
|
"num_tokens": 37092258.0,
|
|
"step": 20165
|
|
},
|
|
{
|
|
"entropy": 5.3406665325164795,
|
|
"epoch": 1.6847644503842298,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00047166839868003984,
|
|
"loss": 4.8937,
|
|
"mean_token_accuracy": 0.21581719815731049,
|
|
"num_tokens": 37101100.0,
|
|
"step": 20170
|
|
},
|
|
{
|
|
"entropy": 5.416512298583984,
|
|
"epoch": 1.6851820915469429,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00047165393533423784,
|
|
"loss": 4.9245,
|
|
"mean_token_accuracy": 0.21246693432331085,
|
|
"num_tokens": 37110876.0,
|
|
"step": 20175
|
|
},
|
|
{
|
|
"entropy": 5.387094974517822,
|
|
"epoch": 1.685599732709656,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00047163946854577194,
|
|
"loss": 4.7939,
|
|
"mean_token_accuracy": 0.2191216379404068,
|
|
"num_tokens": 37119770.0,
|
|
"step": 20180
|
|
},
|
|
{
|
|
"entropy": 5.2915514469146725,
|
|
"epoch": 1.6860173738723687,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004716249983148955,
|
|
"loss": 4.807,
|
|
"mean_token_accuracy": 0.22159902155399322,
|
|
"num_tokens": 37129173.0,
|
|
"step": 20185
|
|
},
|
|
{
|
|
"entropy": 5.270727872848511,
|
|
"epoch": 1.686435015035082,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004716105246418618,
|
|
"loss": 4.7587,
|
|
"mean_token_accuracy": 0.2273146003484726,
|
|
"num_tokens": 37138229.0,
|
|
"step": 20190
|
|
},
|
|
{
|
|
"entropy": 5.404584217071533,
|
|
"epoch": 1.6868526561977948,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004715960475269242,
|
|
"loss": 4.9024,
|
|
"mean_token_accuracy": 0.21602551341056825,
|
|
"num_tokens": 37147792.0,
|
|
"step": 20195
|
|
},
|
|
{
|
|
"entropy": 5.3655987739562985,
|
|
"epoch": 1.6872702973605078,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004715815669703362,
|
|
"loss": 4.7805,
|
|
"mean_token_accuracy": 0.22953448742628096,
|
|
"num_tokens": 37156729.0,
|
|
"step": 20200
|
|
},
|
|
{
|
|
"entropy": 5.295292329788208,
|
|
"epoch": 1.6876879385232209,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00047156708297235115,
|
|
"loss": 4.822,
|
|
"mean_token_accuracy": 0.22224660813808442,
|
|
"num_tokens": 37165678.0,
|
|
"step": 20205
|
|
},
|
|
{
|
|
"entropy": 5.451503610610962,
|
|
"epoch": 1.6881055796859339,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004715525955332227,
|
|
"loss": 4.9342,
|
|
"mean_token_accuracy": 0.21541132032871246,
|
|
"num_tokens": 37174704.0,
|
|
"step": 20210
|
|
},
|
|
{
|
|
"entropy": 5.3901341438293455,
|
|
"epoch": 1.688523220848647,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004715381046532046,
|
|
"loss": 4.8361,
|
|
"mean_token_accuracy": 0.2189823016524315,
|
|
"num_tokens": 37184548.0,
|
|
"step": 20215
|
|
},
|
|
{
|
|
"entropy": 5.276038646697998,
|
|
"epoch": 1.6889408620113597,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004715236103325503,
|
|
"loss": 4.7589,
|
|
"mean_token_accuracy": 0.22066486477851868,
|
|
"num_tokens": 37193668.0,
|
|
"step": 20220
|
|
},
|
|
{
|
|
"entropy": 5.27499623298645,
|
|
"epoch": 1.689358503174073,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00047150911257151364,
|
|
"loss": 4.8146,
|
|
"mean_token_accuracy": 0.2188737541437149,
|
|
"num_tokens": 37202504.0,
|
|
"step": 20225
|
|
},
|
|
{
|
|
"entropy": 5.3595404624938965,
|
|
"epoch": 1.6897761443367858,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004714946113703484,
|
|
"loss": 4.7607,
|
|
"mean_token_accuracy": 0.22930010855197908,
|
|
"num_tokens": 37212140.0,
|
|
"step": 20230
|
|
},
|
|
{
|
|
"entropy": 5.410246992111206,
|
|
"epoch": 1.6901937854994988,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004714801067293086,
|
|
"loss": 4.9484,
|
|
"mean_token_accuracy": 0.2158978134393692,
|
|
"num_tokens": 37221824.0,
|
|
"step": 20235
|
|
},
|
|
{
|
|
"entropy": 5.420230054855347,
|
|
"epoch": 1.6906114266622119,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00047146559864864787,
|
|
"loss": 4.8987,
|
|
"mean_token_accuracy": 0.21862811893224715,
|
|
"num_tokens": 37231877.0,
|
|
"step": 20240
|
|
},
|
|
{
|
|
"entropy": 5.398785972595215,
|
|
"epoch": 1.6910290678249247,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00047145108712862046,
|
|
"loss": 4.8816,
|
|
"mean_token_accuracy": 0.21920872628688812,
|
|
"num_tokens": 37240601.0,
|
|
"step": 20245
|
|
},
|
|
{
|
|
"entropy": 5.265301322937011,
|
|
"epoch": 1.691446708987638,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004714365721694803,
|
|
"loss": 4.7902,
|
|
"mean_token_accuracy": 0.2207883819937706,
|
|
"num_tokens": 37249645.0,
|
|
"step": 20250
|
|
},
|
|
{
|
|
"entropy": 5.3204262256622314,
|
|
"epoch": 1.6918643501503507,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00047142205377148145,
|
|
"loss": 4.7985,
|
|
"mean_token_accuracy": 0.21882465928792955,
|
|
"num_tokens": 37258170.0,
|
|
"step": 20255
|
|
},
|
|
{
|
|
"entropy": 5.3273333549499515,
|
|
"epoch": 1.6922819913130638,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004714075319348781,
|
|
"loss": 4.8624,
|
|
"mean_token_accuracy": 0.2183192178606987,
|
|
"num_tokens": 37268045.0,
|
|
"step": 20260
|
|
},
|
|
{
|
|
"entropy": 5.353000593185425,
|
|
"epoch": 1.6926996324757768,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004713930066599246,
|
|
"loss": 4.8408,
|
|
"mean_token_accuracy": 0.21772244125604628,
|
|
"num_tokens": 37278558.0,
|
|
"step": 20265
|
|
},
|
|
{
|
|
"entropy": 5.3253356456756595,
|
|
"epoch": 1.6931172736384899,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000471378477946875,
|
|
"loss": 4.7186,
|
|
"mean_token_accuracy": 0.2280208021402359,
|
|
"num_tokens": 37287119.0,
|
|
"step": 20270
|
|
},
|
|
{
|
|
"entropy": 5.335617113113403,
|
|
"epoch": 1.6935349148012029,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004713639457959838,
|
|
"loss": 4.8454,
|
|
"mean_token_accuracy": 0.21804729402065276,
|
|
"num_tokens": 37296300.0,
|
|
"step": 20275
|
|
},
|
|
{
|
|
"entropy": 5.3569567680358885,
|
|
"epoch": 1.6939525559639157,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004713494102075053,
|
|
"loss": 4.8132,
|
|
"mean_token_accuracy": 0.21988594383001328,
|
|
"num_tokens": 37305291.0,
|
|
"step": 20280
|
|
},
|
|
{
|
|
"entropy": 5.372012424468994,
|
|
"epoch": 1.694370197126629,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004713348711816942,
|
|
"loss": 4.7914,
|
|
"mean_token_accuracy": 0.22208157628774644,
|
|
"num_tokens": 37314441.0,
|
|
"step": 20285
|
|
},
|
|
{
|
|
"entropy": 5.367743062973022,
|
|
"epoch": 1.6947878382893418,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004713203287188047,
|
|
"loss": 4.8687,
|
|
"mean_token_accuracy": 0.21968641728162766,
|
|
"num_tokens": 37323516.0,
|
|
"step": 20290
|
|
},
|
|
{
|
|
"entropy": 5.372766304016113,
|
|
"epoch": 1.6952054794520548,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004713057828190916,
|
|
"loss": 4.8025,
|
|
"mean_token_accuracy": 0.22332145720720292,
|
|
"num_tokens": 37332651.0,
|
|
"step": 20295
|
|
},
|
|
{
|
|
"entropy": 5.347039699554443,
|
|
"epoch": 1.6956231206147678,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004712912334828094,
|
|
"loss": 4.8479,
|
|
"mean_token_accuracy": 0.21731442213058472,
|
|
"num_tokens": 37341580.0,
|
|
"step": 20300
|
|
},
|
|
{
|
|
"entropy": 5.393910503387451,
|
|
"epoch": 1.6960407617774806,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00047127668071021293,
|
|
"loss": 4.9068,
|
|
"mean_token_accuracy": 0.21379862278699874,
|
|
"num_tokens": 37351385.0,
|
|
"step": 20305
|
|
},
|
|
{
|
|
"entropy": 5.27644910812378,
|
|
"epoch": 1.696458402940194,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000471262124501557,
|
|
"loss": 4.642,
|
|
"mean_token_accuracy": 0.23313185423612595,
|
|
"num_tokens": 37360893.0,
|
|
"step": 20310
|
|
},
|
|
{
|
|
"entropy": 5.322821426391601,
|
|
"epoch": 1.6968760441029067,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004712475648570962,
|
|
"loss": 4.7717,
|
|
"mean_token_accuracy": 0.21862319111824036,
|
|
"num_tokens": 37370301.0,
|
|
"step": 20315
|
|
},
|
|
{
|
|
"entropy": 5.326773309707642,
|
|
"epoch": 1.6972936852656197,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00047123300177708563,
|
|
"loss": 4.8641,
|
|
"mean_token_accuracy": 0.2156633511185646,
|
|
"num_tokens": 37380881.0,
|
|
"step": 20320
|
|
},
|
|
{
|
|
"entropy": 5.278640079498291,
|
|
"epoch": 1.6977113264283328,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004712184352617801,
|
|
"loss": 4.7498,
|
|
"mean_token_accuracy": 0.23148690164089203,
|
|
"num_tokens": 37390167.0,
|
|
"step": 20325
|
|
},
|
|
{
|
|
"entropy": 5.4326500415802,
|
|
"epoch": 1.6981289675910458,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00047120386531143476,
|
|
"loss": 4.9932,
|
|
"mean_token_accuracy": 0.2103126212954521,
|
|
"num_tokens": 37399163.0,
|
|
"step": 20330
|
|
},
|
|
{
|
|
"entropy": 5.43931212425232,
|
|
"epoch": 1.6985466087537588,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00047118929192630453,
|
|
"loss": 4.8983,
|
|
"mean_token_accuracy": 0.21865673810243608,
|
|
"num_tokens": 37409047.0,
|
|
"step": 20335
|
|
},
|
|
{
|
|
"entropy": 5.377465295791626,
|
|
"epoch": 1.6989642499164717,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004711747151066446,
|
|
"loss": 4.7465,
|
|
"mean_token_accuracy": 0.2246784597635269,
|
|
"num_tokens": 37417936.0,
|
|
"step": 20340
|
|
},
|
|
{
|
|
"entropy": 5.242856454849243,
|
|
"epoch": 1.699381891079185,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00047116013485271014,
|
|
"loss": 4.6838,
|
|
"mean_token_accuracy": 0.23198756128549575,
|
|
"num_tokens": 37426453.0,
|
|
"step": 20345
|
|
},
|
|
{
|
|
"entropy": 5.197157716751098,
|
|
"epoch": 1.6997995322418977,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004711455511647564,
|
|
"loss": 4.6321,
|
|
"mean_token_accuracy": 0.24281487762928008,
|
|
"num_tokens": 37435353.0,
|
|
"step": 20350
|
|
},
|
|
{
|
|
"entropy": 5.302297639846802,
|
|
"epoch": 1.7002171734046108,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00047113096404303875,
|
|
"loss": 4.8483,
|
|
"mean_token_accuracy": 0.22159904539585112,
|
|
"num_tokens": 37444895.0,
|
|
"step": 20355
|
|
},
|
|
{
|
|
"entropy": 5.384782123565674,
|
|
"epoch": 1.7006348145673238,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004711163734878124,
|
|
"loss": 4.7673,
|
|
"mean_token_accuracy": 0.2227795422077179,
|
|
"num_tokens": 37454038.0,
|
|
"step": 20360
|
|
},
|
|
{
|
|
"entropy": 5.354452466964721,
|
|
"epoch": 1.7010524557300366,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004711017794993329,
|
|
"loss": 4.836,
|
|
"mean_token_accuracy": 0.21868879199028016,
|
|
"num_tokens": 37463316.0,
|
|
"step": 20365
|
|
},
|
|
{
|
|
"entropy": 5.308090686798096,
|
|
"epoch": 1.7014700968927499,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00047108718207785575,
|
|
"loss": 4.8198,
|
|
"mean_token_accuracy": 0.21777717769145966,
|
|
"num_tokens": 37473341.0,
|
|
"step": 20370
|
|
},
|
|
{
|
|
"entropy": 5.416655731201172,
|
|
"epoch": 1.7018877380554627,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004710725812236364,
|
|
"loss": 4.8687,
|
|
"mean_token_accuracy": 0.22451192885637283,
|
|
"num_tokens": 37482601.0,
|
|
"step": 20375
|
|
},
|
|
{
|
|
"entropy": 5.342301845550537,
|
|
"epoch": 1.7023053792181757,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004710579769369305,
|
|
"loss": 4.7656,
|
|
"mean_token_accuracy": 0.2209479868412018,
|
|
"num_tokens": 37491304.0,
|
|
"step": 20380
|
|
},
|
|
{
|
|
"entropy": 5.23993182182312,
|
|
"epoch": 1.7027230203808887,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004710433692179937,
|
|
"loss": 4.7354,
|
|
"mean_token_accuracy": 0.2232622340321541,
|
|
"num_tokens": 37500848.0,
|
|
"step": 20385
|
|
},
|
|
{
|
|
"entropy": 5.328610134124756,
|
|
"epoch": 1.7031406615436018,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004710287580670818,
|
|
"loss": 4.7278,
|
|
"mean_token_accuracy": 0.2313452661037445,
|
|
"num_tokens": 37509649.0,
|
|
"step": 20390
|
|
},
|
|
{
|
|
"entropy": 5.318402910232544,
|
|
"epoch": 1.7035583027063148,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00047101414348445046,
|
|
"loss": 4.8612,
|
|
"mean_token_accuracy": 0.21614013761281967,
|
|
"num_tokens": 37519207.0,
|
|
"step": 20395
|
|
},
|
|
{
|
|
"entropy": 5.356790447235108,
|
|
"epoch": 1.7039759438690276,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00047099952547035564,
|
|
"loss": 4.8677,
|
|
"mean_token_accuracy": 0.21426312625408173,
|
|
"num_tokens": 37528819.0,
|
|
"step": 20400
|
|
},
|
|
{
|
|
"entropy": 5.355227613449097,
|
|
"epoch": 1.7043935850317409,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004709849040250532,
|
|
"loss": 4.7908,
|
|
"mean_token_accuracy": 0.2204276517033577,
|
|
"num_tokens": 37538439.0,
|
|
"step": 20405
|
|
},
|
|
{
|
|
"entropy": 5.294802713394165,
|
|
"epoch": 1.7048112261944537,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004709702791487991,
|
|
"loss": 4.767,
|
|
"mean_token_accuracy": 0.2239033415913582,
|
|
"num_tokens": 37547758.0,
|
|
"step": 20410
|
|
},
|
|
{
|
|
"entropy": 5.300671768188477,
|
|
"epoch": 1.7052288673571667,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004709556508418494,
|
|
"loss": 4.7977,
|
|
"mean_token_accuracy": 0.22529476135969162,
|
|
"num_tokens": 37556693.0,
|
|
"step": 20415
|
|
},
|
|
{
|
|
"entropy": 5.335372018814087,
|
|
"epoch": 1.7056465085198798,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004709410191044601,
|
|
"loss": 4.8643,
|
|
"mean_token_accuracy": 0.217681322991848,
|
|
"num_tokens": 37564631.0,
|
|
"step": 20420
|
|
},
|
|
{
|
|
"entropy": 5.323000478744507,
|
|
"epoch": 1.7060641496825926,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004709263839368875,
|
|
"loss": 4.7197,
|
|
"mean_token_accuracy": 0.2321915790438652,
|
|
"num_tokens": 37573687.0,
|
|
"step": 20425
|
|
},
|
|
{
|
|
"entropy": 5.298052263259888,
|
|
"epoch": 1.7064817908453058,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004709117453393876,
|
|
"loss": 4.7967,
|
|
"mean_token_accuracy": 0.21828277558088302,
|
|
"num_tokens": 37582652.0,
|
|
"step": 20430
|
|
},
|
|
{
|
|
"entropy": 5.255377149581909,
|
|
"epoch": 1.7068994320080186,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00047089710331221687,
|
|
"loss": 4.684,
|
|
"mean_token_accuracy": 0.23278852552175522,
|
|
"num_tokens": 37591242.0,
|
|
"step": 20435
|
|
},
|
|
{
|
|
"entropy": 5.4211475372314455,
|
|
"epoch": 1.7073170731707317,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004708824578556315,
|
|
"loss": 5.0002,
|
|
"mean_token_accuracy": 0.2127951130270958,
|
|
"num_tokens": 37601527.0,
|
|
"step": 20440
|
|
},
|
|
{
|
|
"entropy": 5.413842105865479,
|
|
"epoch": 1.7077347143334447,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00047086780896988796,
|
|
"loss": 4.8829,
|
|
"mean_token_accuracy": 0.2160310924053192,
|
|
"num_tokens": 37611100.0,
|
|
"step": 20445
|
|
},
|
|
{
|
|
"entropy": 5.360604667663575,
|
|
"epoch": 1.7081523554961577,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00047085315665524257,
|
|
"loss": 4.8095,
|
|
"mean_token_accuracy": 0.2287534609436989,
|
|
"num_tokens": 37619386.0,
|
|
"step": 20450
|
|
},
|
|
{
|
|
"entropy": 5.371468639373779,
|
|
"epoch": 1.7085699966588708,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000470838500911952,
|
|
"loss": 4.9228,
|
|
"mean_token_accuracy": 0.21799169778823851,
|
|
"num_tokens": 37628695.0,
|
|
"step": 20455
|
|
},
|
|
{
|
|
"entropy": 5.368965148925781,
|
|
"epoch": 1.7089876378215836,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004708238417402728,
|
|
"loss": 4.8492,
|
|
"mean_token_accuracy": 0.21488215476274491,
|
|
"num_tokens": 37637588.0,
|
|
"step": 20460
|
|
},
|
|
{
|
|
"entropy": 5.310626602172851,
|
|
"epoch": 1.7094052789842968,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00047080917914046146,
|
|
"loss": 4.7221,
|
|
"mean_token_accuracy": 0.22861775606870652,
|
|
"num_tokens": 37646114.0,
|
|
"step": 20465
|
|
},
|
|
{
|
|
"entropy": 5.389170360565186,
|
|
"epoch": 1.7098229201470097,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00047079451311277473,
|
|
"loss": 4.9401,
|
|
"mean_token_accuracy": 0.21433347314596177,
|
|
"num_tokens": 37654987.0,
|
|
"step": 20470
|
|
},
|
|
{
|
|
"entropy": 5.304504442214966,
|
|
"epoch": 1.7102405613097227,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004707798436574694,
|
|
"loss": 4.8225,
|
|
"mean_token_accuracy": 0.22444592267274857,
|
|
"num_tokens": 37664715.0,
|
|
"step": 20475
|
|
},
|
|
{
|
|
"entropy": 5.40810980796814,
|
|
"epoch": 1.7106582024724357,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00047076517077480223,
|
|
"loss": 4.907,
|
|
"mean_token_accuracy": 0.21582252383232117,
|
|
"num_tokens": 37675016.0,
|
|
"step": 20480
|
|
},
|
|
{
|
|
"entropy": 5.389331388473511,
|
|
"epoch": 1.7110758436351485,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004707504944650301,
|
|
"loss": 4.8345,
|
|
"mean_token_accuracy": 0.21669729948043823,
|
|
"num_tokens": 37683577.0,
|
|
"step": 20485
|
|
},
|
|
{
|
|
"entropy": 5.402756595611573,
|
|
"epoch": 1.7114934847978618,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00047073581472840997,
|
|
"loss": 4.8196,
|
|
"mean_token_accuracy": 0.21707775592803955,
|
|
"num_tokens": 37692681.0,
|
|
"step": 20490
|
|
},
|
|
{
|
|
"entropy": 5.266970539093018,
|
|
"epoch": 1.7119111259605746,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004707211315651988,
|
|
"loss": 4.7416,
|
|
"mean_token_accuracy": 0.22615266144275664,
|
|
"num_tokens": 37701698.0,
|
|
"step": 20495
|
|
},
|
|
{
|
|
"entropy": 5.270098257064819,
|
|
"epoch": 1.7123287671232876,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004707064449756536,
|
|
"loss": 4.8286,
|
|
"mean_token_accuracy": 0.21670783162117005,
|
|
"num_tokens": 37710450.0,
|
|
"step": 20500
|
|
},
|
|
{
|
|
"entropy": 5.322144412994385,
|
|
"epoch": 1.7127464082860007,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00047069175496003147,
|
|
"loss": 4.8599,
|
|
"mean_token_accuracy": 0.22011559158563615,
|
|
"num_tokens": 37719201.0,
|
|
"step": 20505
|
|
},
|
|
{
|
|
"entropy": 5.441975450515747,
|
|
"epoch": 1.7131640494487137,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00047067706151858967,
|
|
"loss": 4.8895,
|
|
"mean_token_accuracy": 0.22080118358135223,
|
|
"num_tokens": 37728671.0,
|
|
"step": 20510
|
|
},
|
|
{
|
|
"entropy": 5.33357834815979,
|
|
"epoch": 1.7135816906114267,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004706623646515854,
|
|
"loss": 4.7871,
|
|
"mean_token_accuracy": 0.22429251223802565,
|
|
"num_tokens": 37737675.0,
|
|
"step": 20515
|
|
},
|
|
{
|
|
"entropy": 5.291724443435669,
|
|
"epoch": 1.7139993317741395,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00047064766435927585,
|
|
"loss": 4.7866,
|
|
"mean_token_accuracy": 0.23227620422840117,
|
|
"num_tokens": 37746299.0,
|
|
"step": 20520
|
|
},
|
|
{
|
|
"entropy": 5.288926219940185,
|
|
"epoch": 1.7144169729368528,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00047063296064191846,
|
|
"loss": 4.6999,
|
|
"mean_token_accuracy": 0.22453450113534928,
|
|
"num_tokens": 37755770.0,
|
|
"step": 20525
|
|
},
|
|
{
|
|
"entropy": 5.32398476600647,
|
|
"epoch": 1.7148346140995656,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00047061825349977067,
|
|
"loss": 4.8214,
|
|
"mean_token_accuracy": 0.22276567071676254,
|
|
"num_tokens": 37765217.0,
|
|
"step": 20530
|
|
},
|
|
{
|
|
"entropy": 5.3765157699584964,
|
|
"epoch": 1.7152522552622786,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00047060354293308976,
|
|
"loss": 4.7962,
|
|
"mean_token_accuracy": 0.2293853282928467,
|
|
"num_tokens": 37773891.0,
|
|
"step": 20535
|
|
},
|
|
{
|
|
"entropy": 5.286283540725708,
|
|
"epoch": 1.7156698964249917,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004705888289421335,
|
|
"loss": 4.8248,
|
|
"mean_token_accuracy": 0.22484108954668044,
|
|
"num_tokens": 37783323.0,
|
|
"step": 20540
|
|
},
|
|
{
|
|
"entropy": 5.373268699645996,
|
|
"epoch": 1.7160875375877045,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004705741115271593,
|
|
"loss": 4.9029,
|
|
"mean_token_accuracy": 0.2140967905521393,
|
|
"num_tokens": 37792436.0,
|
|
"step": 20545
|
|
},
|
|
{
|
|
"entropy": 5.325695037841797,
|
|
"epoch": 1.7165051787504177,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004705593906884249,
|
|
"loss": 4.7965,
|
|
"mean_token_accuracy": 0.22247220873832702,
|
|
"num_tokens": 37802061.0,
|
|
"step": 20550
|
|
},
|
|
{
|
|
"entropy": 5.272588205337525,
|
|
"epoch": 1.7169228199131306,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00047054466642618793,
|
|
"loss": 4.7393,
|
|
"mean_token_accuracy": 0.22734470814466476,
|
|
"num_tokens": 37811101.0,
|
|
"step": 20555
|
|
},
|
|
{
|
|
"entropy": 5.366985273361206,
|
|
"epoch": 1.7173404610758436,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00047052993874070623,
|
|
"loss": 4.8581,
|
|
"mean_token_accuracy": 0.2225163236260414,
|
|
"num_tokens": 37820783.0,
|
|
"step": 20560
|
|
},
|
|
{
|
|
"entropy": 5.307202243804932,
|
|
"epoch": 1.7177581022385566,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00047051520763223754,
|
|
"loss": 4.7663,
|
|
"mean_token_accuracy": 0.22424365431070328,
|
|
"num_tokens": 37830075.0,
|
|
"step": 20565
|
|
},
|
|
{
|
|
"entropy": 5.253970718383789,
|
|
"epoch": 1.7181757434012697,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00047050047310103984,
|
|
"loss": 4.7034,
|
|
"mean_token_accuracy": 0.2191138431429863,
|
|
"num_tokens": 37838344.0,
|
|
"step": 20570
|
|
},
|
|
{
|
|
"entropy": 5.292567873001099,
|
|
"epoch": 1.7185933845639827,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00047048573514737107,
|
|
"loss": 4.8162,
|
|
"mean_token_accuracy": 0.21341225504875183,
|
|
"num_tokens": 37847911.0,
|
|
"step": 20575
|
|
},
|
|
{
|
|
"entropy": 5.2367583274841305,
|
|
"epoch": 1.7190110257266955,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00047047099377148916,
|
|
"loss": 4.7468,
|
|
"mean_token_accuracy": 0.2258659213781357,
|
|
"num_tokens": 37857044.0,
|
|
"step": 20580
|
|
},
|
|
{
|
|
"entropy": 5.378116226196289,
|
|
"epoch": 1.7194286668894088,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004704562489736522,
|
|
"loss": 4.8123,
|
|
"mean_token_accuracy": 0.22800511121749878,
|
|
"num_tokens": 37865912.0,
|
|
"step": 20585
|
|
},
|
|
{
|
|
"entropy": 5.379587078094483,
|
|
"epoch": 1.7198463080521216,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004704415007541184,
|
|
"loss": 4.8896,
|
|
"mean_token_accuracy": 0.21673969328403472,
|
|
"num_tokens": 37875118.0,
|
|
"step": 20590
|
|
},
|
|
{
|
|
"entropy": 5.305255985260009,
|
|
"epoch": 1.7202639492148346,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004704267491131458,
|
|
"loss": 4.7801,
|
|
"mean_token_accuracy": 0.2293965548276901,
|
|
"num_tokens": 37882891.0,
|
|
"step": 20595
|
|
},
|
|
{
|
|
"entropy": 5.279256439208984,
|
|
"epoch": 1.7206815903775476,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00047041199405099273,
|
|
"loss": 4.8132,
|
|
"mean_token_accuracy": 0.22929334342479707,
|
|
"num_tokens": 37892274.0,
|
|
"step": 20600
|
|
},
|
|
{
|
|
"entropy": 5.242782354354858,
|
|
"epoch": 1.7210992315402605,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00047039723556791744,
|
|
"loss": 4.7156,
|
|
"mean_token_accuracy": 0.22905958592891693,
|
|
"num_tokens": 37901061.0,
|
|
"step": 20605
|
|
},
|
|
{
|
|
"entropy": 5.274942111968994,
|
|
"epoch": 1.7215168727029737,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004703824736641785,
|
|
"loss": 4.6976,
|
|
"mean_token_accuracy": 0.23119368851184846,
|
|
"num_tokens": 37910253.0,
|
|
"step": 20610
|
|
},
|
|
{
|
|
"entropy": 5.290258169174194,
|
|
"epoch": 1.7219345138656865,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00047036770834003405,
|
|
"loss": 4.7921,
|
|
"mean_token_accuracy": 0.22468389123678206,
|
|
"num_tokens": 37919453.0,
|
|
"step": 20615
|
|
},
|
|
{
|
|
"entropy": 5.24897346496582,
|
|
"epoch": 1.7223521550283996,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00047035293959574273,
|
|
"loss": 4.6728,
|
|
"mean_token_accuracy": 0.22955697923898696,
|
|
"num_tokens": 37928462.0,
|
|
"step": 20620
|
|
},
|
|
{
|
|
"entropy": 5.359140682220459,
|
|
"epoch": 1.7227697961911126,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000470338167431563,
|
|
"loss": 4.8413,
|
|
"mean_token_accuracy": 0.22733691483736038,
|
|
"num_tokens": 37938631.0,
|
|
"step": 20625
|
|
},
|
|
{
|
|
"entropy": 5.3763786315917965,
|
|
"epoch": 1.7231874373538256,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00047032339184775366,
|
|
"loss": 4.8538,
|
|
"mean_token_accuracy": 0.21222053319215775,
|
|
"num_tokens": 37948490.0,
|
|
"step": 20630
|
|
},
|
|
{
|
|
"entropy": 5.20757155418396,
|
|
"epoch": 1.7236050785165387,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004703086128445731,
|
|
"loss": 4.6921,
|
|
"mean_token_accuracy": 0.23445943146944045,
|
|
"num_tokens": 37957861.0,
|
|
"step": 20635
|
|
},
|
|
{
|
|
"entropy": 5.2555746078491214,
|
|
"epoch": 1.7240227196792515,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004702938304222803,
|
|
"loss": 4.7817,
|
|
"mean_token_accuracy": 0.22556516528129578,
|
|
"num_tokens": 37966587.0,
|
|
"step": 20640
|
|
},
|
|
{
|
|
"entropy": 5.301981258392334,
|
|
"epoch": 1.7244403608419647,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00047027904458113386,
|
|
"loss": 4.8389,
|
|
"mean_token_accuracy": 0.2163667306303978,
|
|
"num_tokens": 37976295.0,
|
|
"step": 20645
|
|
},
|
|
{
|
|
"entropy": 5.496170282363892,
|
|
"epoch": 1.7248580020046775,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004702642553213927,
|
|
"loss": 5.032,
|
|
"mean_token_accuracy": 0.2082500159740448,
|
|
"num_tokens": 37985525.0,
|
|
"step": 20650
|
|
},
|
|
{
|
|
"entropy": 5.396108198165893,
|
|
"epoch": 1.7252756431673906,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00047024946264331564,
|
|
"loss": 4.8754,
|
|
"mean_token_accuracy": 0.21847068071365355,
|
|
"num_tokens": 37995656.0,
|
|
"step": 20655
|
|
},
|
|
{
|
|
"entropy": 5.3414710521697994,
|
|
"epoch": 1.7256932843301036,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004702346665471618,
|
|
"loss": 4.8321,
|
|
"mean_token_accuracy": 0.22351912558078765,
|
|
"num_tokens": 38004790.0,
|
|
"step": 20660
|
|
},
|
|
{
|
|
"entropy": 5.419737863540649,
|
|
"epoch": 1.7261109254928164,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004702198670331901,
|
|
"loss": 4.9441,
|
|
"mean_token_accuracy": 0.2094773456454277,
|
|
"num_tokens": 38014244.0,
|
|
"step": 20665
|
|
},
|
|
{
|
|
"entropy": 5.303154182434082,
|
|
"epoch": 1.7265285666555297,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00047020506410165965,
|
|
"loss": 4.775,
|
|
"mean_token_accuracy": 0.23242257833480834,
|
|
"num_tokens": 38023756.0,
|
|
"step": 20670
|
|
},
|
|
{
|
|
"entropy": 5.313599348068237,
|
|
"epoch": 1.7269462078182425,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00047019025775282955,
|
|
"loss": 4.7628,
|
|
"mean_token_accuracy": 0.22602612525224686,
|
|
"num_tokens": 38033402.0,
|
|
"step": 20675
|
|
},
|
|
{
|
|
"entropy": 5.339718818664551,
|
|
"epoch": 1.7273638489809555,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000470175447986959,
|
|
"loss": 4.8278,
|
|
"mean_token_accuracy": 0.2150781974196434,
|
|
"num_tokens": 38042580.0,
|
|
"step": 20680
|
|
},
|
|
{
|
|
"entropy": 5.333544635772705,
|
|
"epoch": 1.7277814901436686,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004701606348043074,
|
|
"loss": 4.891,
|
|
"mean_token_accuracy": 0.21828218996524812,
|
|
"num_tokens": 38051809.0,
|
|
"step": 20685
|
|
},
|
|
{
|
|
"entropy": 5.295646095275879,
|
|
"epoch": 1.7281991313063816,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004701458182051339,
|
|
"loss": 4.7042,
|
|
"mean_token_accuracy": 0.22790328413248062,
|
|
"num_tokens": 38061053.0,
|
|
"step": 20690
|
|
},
|
|
{
|
|
"entropy": 5.290011596679688,
|
|
"epoch": 1.7286167724690946,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00047013099818969797,
|
|
"loss": 4.7164,
|
|
"mean_token_accuracy": 0.22064153403043746,
|
|
"num_tokens": 38070190.0,
|
|
"step": 20695
|
|
},
|
|
{
|
|
"entropy": 5.2895997047424315,
|
|
"epoch": 1.7290344136318074,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000470116174758259,
|
|
"loss": 4.9225,
|
|
"mean_token_accuracy": 0.2159022718667984,
|
|
"num_tokens": 38078049.0,
|
|
"step": 20700
|
|
},
|
|
{
|
|
"entropy": 5.362542295455933,
|
|
"epoch": 1.7294520547945207,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00047010134791107663,
|
|
"loss": 4.8468,
|
|
"mean_token_accuracy": 0.21689577400684357,
|
|
"num_tokens": 38089130.0,
|
|
"step": 20705
|
|
},
|
|
{
|
|
"entropy": 5.34804368019104,
|
|
"epoch": 1.7298696959572335,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00047008651764841034,
|
|
"loss": 4.7364,
|
|
"mean_token_accuracy": 0.2255866453051567,
|
|
"num_tokens": 38098484.0,
|
|
"step": 20710
|
|
},
|
|
{
|
|
"entropy": 5.331089973449707,
|
|
"epoch": 1.7302873371199465,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00047007168397051956,
|
|
"loss": 4.8304,
|
|
"mean_token_accuracy": 0.2236856147646904,
|
|
"num_tokens": 38107982.0,
|
|
"step": 20715
|
|
},
|
|
{
|
|
"entropy": 5.326601886749268,
|
|
"epoch": 1.7307049782826596,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00047005684687766424,
|
|
"loss": 4.8206,
|
|
"mean_token_accuracy": 0.22543375790119172,
|
|
"num_tokens": 38116816.0,
|
|
"step": 20720
|
|
},
|
|
{
|
|
"entropy": 5.292116308212281,
|
|
"epoch": 1.7311226194453724,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004700420063701041,
|
|
"loss": 4.7306,
|
|
"mean_token_accuracy": 0.22545383423566817,
|
|
"num_tokens": 38125752.0,
|
|
"step": 20725
|
|
},
|
|
{
|
|
"entropy": 5.323092842102051,
|
|
"epoch": 1.7315402606080856,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004700271624480988,
|
|
"loss": 4.8269,
|
|
"mean_token_accuracy": 0.22064004540443422,
|
|
"num_tokens": 38135192.0,
|
|
"step": 20730
|
|
},
|
|
{
|
|
"entropy": 5.386557865142822,
|
|
"epoch": 1.7319579017707984,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00047001231511190826,
|
|
"loss": 4.8601,
|
|
"mean_token_accuracy": 0.20835306942462922,
|
|
"num_tokens": 38144730.0,
|
|
"step": 20735
|
|
},
|
|
{
|
|
"entropy": 5.278432178497314,
|
|
"epoch": 1.7323755429335115,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004699974643617924,
|
|
"loss": 4.7438,
|
|
"mean_token_accuracy": 0.22444045096635817,
|
|
"num_tokens": 38153319.0,
|
|
"step": 20740
|
|
},
|
|
{
|
|
"entropy": 5.327840757369995,
|
|
"epoch": 1.7327931840962245,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004699826101980112,
|
|
"loss": 4.7801,
|
|
"mean_token_accuracy": 0.23094405233860016,
|
|
"num_tokens": 38162067.0,
|
|
"step": 20745
|
|
},
|
|
{
|
|
"entropy": 5.405494117736817,
|
|
"epoch": 1.7332108252589375,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004699677526208248,
|
|
"loss": 4.915,
|
|
"mean_token_accuracy": 0.2179666891694069,
|
|
"num_tokens": 38170901.0,
|
|
"step": 20750
|
|
},
|
|
{
|
|
"entropy": 5.288124132156372,
|
|
"epoch": 1.7336284664216506,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00046995289163049317,
|
|
"loss": 4.8127,
|
|
"mean_token_accuracy": 0.22112846672534942,
|
|
"num_tokens": 38179815.0,
|
|
"step": 20755
|
|
},
|
|
{
|
|
"entropy": 5.335148096084595,
|
|
"epoch": 1.7340461075843634,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00046993802722727646,
|
|
"loss": 4.8312,
|
|
"mean_token_accuracy": 0.2223203092813492,
|
|
"num_tokens": 38188816.0,
|
|
"step": 20760
|
|
},
|
|
{
|
|
"entropy": 5.340242576599121,
|
|
"epoch": 1.7344637487470767,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004699231594114349,
|
|
"loss": 4.7917,
|
|
"mean_token_accuracy": 0.21551012247800827,
|
|
"num_tokens": 38198447.0,
|
|
"step": 20765
|
|
},
|
|
{
|
|
"entropy": 5.3959962844848635,
|
|
"epoch": 1.7348813899097895,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004699082881832289,
|
|
"loss": 4.8757,
|
|
"mean_token_accuracy": 0.21375256329774855,
|
|
"num_tokens": 38207075.0,
|
|
"step": 20770
|
|
},
|
|
{
|
|
"entropy": 5.3925315856933596,
|
|
"epoch": 1.7352990310725025,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00046989341354291864,
|
|
"loss": 4.8637,
|
|
"mean_token_accuracy": 0.21278509199619294,
|
|
"num_tokens": 38216297.0,
|
|
"step": 20775
|
|
},
|
|
{
|
|
"entropy": 5.46162257194519,
|
|
"epoch": 1.7357166722352155,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004698785354907646,
|
|
"loss": 4.9798,
|
|
"mean_token_accuracy": 0.21142458766698838,
|
|
"num_tokens": 38225581.0,
|
|
"step": 20780
|
|
},
|
|
{
|
|
"entropy": 5.305453586578369,
|
|
"epoch": 1.7361343133979283,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004698636540270272,
|
|
"loss": 4.6826,
|
|
"mean_token_accuracy": 0.23198051303625106,
|
|
"num_tokens": 38234214.0,
|
|
"step": 20785
|
|
},
|
|
{
|
|
"entropy": 5.399198913574219,
|
|
"epoch": 1.7365519545606416,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004698487691519671,
|
|
"loss": 4.9033,
|
|
"mean_token_accuracy": 0.21248941719532013,
|
|
"num_tokens": 38243859.0,
|
|
"step": 20790
|
|
},
|
|
{
|
|
"entropy": 5.35770173072815,
|
|
"epoch": 1.7369695957233544,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00046983388086584463,
|
|
"loss": 4.7421,
|
|
"mean_token_accuracy": 0.22239422798156738,
|
|
"num_tokens": 38252667.0,
|
|
"step": 20795
|
|
},
|
|
{
|
|
"entropy": 5.250381660461426,
|
|
"epoch": 1.7373872368860674,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00046981898916892054,
|
|
"loss": 4.6801,
|
|
"mean_token_accuracy": 0.22607546150684357,
|
|
"num_tokens": 38262216.0,
|
|
"step": 20800
|
|
},
|
|
{
|
|
"entropy": 5.350259017944336,
|
|
"epoch": 1.7378048780487805,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00046980409406145555,
|
|
"loss": 4.8419,
|
|
"mean_token_accuracy": 0.21278517544269562,
|
|
"num_tokens": 38271672.0,
|
|
"step": 20805
|
|
},
|
|
{
|
|
"entropy": 5.2476245880126955,
|
|
"epoch": 1.7382225192114935,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004697891955437105,
|
|
"loss": 4.7377,
|
|
"mean_token_accuracy": 0.2365407392382622,
|
|
"num_tokens": 38279907.0,
|
|
"step": 20810
|
|
},
|
|
{
|
|
"entropy": 5.286419868469238,
|
|
"epoch": 1.7386401603742065,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00046977429361594596,
|
|
"loss": 4.731,
|
|
"mean_token_accuracy": 0.23059804737567902,
|
|
"num_tokens": 38289099.0,
|
|
"step": 20815
|
|
},
|
|
{
|
|
"entropy": 5.282220268249512,
|
|
"epoch": 1.7390578015369194,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004697593882784231,
|
|
"loss": 4.7482,
|
|
"mean_token_accuracy": 0.22658233493566513,
|
|
"num_tokens": 38297754.0,
|
|
"step": 20820
|
|
},
|
|
{
|
|
"entropy": 5.361954832077027,
|
|
"epoch": 1.7394754426996326,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004697444795314027,
|
|
"loss": 4.802,
|
|
"mean_token_accuracy": 0.2248758301138878,
|
|
"num_tokens": 38306429.0,
|
|
"step": 20825
|
|
},
|
|
{
|
|
"entropy": 5.383965682983399,
|
|
"epoch": 1.7398930838623454,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00046972956737514573,
|
|
"loss": 4.824,
|
|
"mean_token_accuracy": 0.21863235384225846,
|
|
"num_tokens": 38315505.0,
|
|
"step": 20830
|
|
},
|
|
{
|
|
"entropy": 5.331510972976685,
|
|
"epoch": 1.7403107250250585,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004697146518099133,
|
|
"loss": 4.8444,
|
|
"mean_token_accuracy": 0.22142641842365265,
|
|
"num_tokens": 38324439.0,
|
|
"step": 20835
|
|
},
|
|
{
|
|
"entropy": 5.321283483505249,
|
|
"epoch": 1.7407283661877715,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00046969973283596657,
|
|
"loss": 4.7945,
|
|
"mean_token_accuracy": 0.22414358109235763,
|
|
"num_tokens": 38334145.0,
|
|
"step": 20840
|
|
},
|
|
{
|
|
"entropy": 5.345840930938721,
|
|
"epoch": 1.7411460073504843,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00046968481045356656,
|
|
"loss": 4.7965,
|
|
"mean_token_accuracy": 0.22609489858150483,
|
|
"num_tokens": 38342811.0,
|
|
"step": 20845
|
|
},
|
|
{
|
|
"entropy": 5.267962837219239,
|
|
"epoch": 1.7415636485131976,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00046966988466297464,
|
|
"loss": 4.81,
|
|
"mean_token_accuracy": 0.22360472977161408,
|
|
"num_tokens": 38351072.0,
|
|
"step": 20850
|
|
},
|
|
{
|
|
"entropy": 5.333851909637451,
|
|
"epoch": 1.7419812896759104,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00046965495546445204,
|
|
"loss": 4.7688,
|
|
"mean_token_accuracy": 0.2284257099032402,
|
|
"num_tokens": 38360127.0,
|
|
"step": 20855
|
|
},
|
|
{
|
|
"entropy": 5.319514179229737,
|
|
"epoch": 1.7423989308386234,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00046964002285826016,
|
|
"loss": 4.7666,
|
|
"mean_token_accuracy": 0.21691656112670898,
|
|
"num_tokens": 38368270.0,
|
|
"step": 20860
|
|
},
|
|
{
|
|
"entropy": 5.318014526367188,
|
|
"epoch": 1.7428165720013364,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004696250868446604,
|
|
"loss": 4.8526,
|
|
"mean_token_accuracy": 0.21240720748901368,
|
|
"num_tokens": 38376970.0,
|
|
"step": 20865
|
|
},
|
|
{
|
|
"entropy": 5.359033870697021,
|
|
"epoch": 1.7432342131640495,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00046961014742391425,
|
|
"loss": 4.8849,
|
|
"mean_token_accuracy": 0.2222330629825592,
|
|
"num_tokens": 38387103.0,
|
|
"step": 20870
|
|
},
|
|
{
|
|
"entropy": 5.441559648513794,
|
|
"epoch": 1.7436518543267625,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00046959520459628317,
|
|
"loss": 4.8421,
|
|
"mean_token_accuracy": 0.22145598381757736,
|
|
"num_tokens": 38395890.0,
|
|
"step": 20875
|
|
},
|
|
{
|
|
"entropy": 5.367438077926636,
|
|
"epoch": 1.7440694954894753,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00046958025836202886,
|
|
"loss": 4.891,
|
|
"mean_token_accuracy": 0.2113304242491722,
|
|
"num_tokens": 38405868.0,
|
|
"step": 20880
|
|
},
|
|
{
|
|
"entropy": 5.325844049453735,
|
|
"epoch": 1.7444871366521886,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004695653087214128,
|
|
"loss": 4.91,
|
|
"mean_token_accuracy": 0.2133233666419983,
|
|
"num_tokens": 38414854.0,
|
|
"step": 20885
|
|
},
|
|
{
|
|
"entropy": 5.3183471202850345,
|
|
"epoch": 1.7449047778149014,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00046955035567469695,
|
|
"loss": 4.7571,
|
|
"mean_token_accuracy": 0.22401948124170304,
|
|
"num_tokens": 38424158.0,
|
|
"step": 20890
|
|
},
|
|
{
|
|
"entropy": 5.364337015151977,
|
|
"epoch": 1.7453224189776144,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00046953539922214285,
|
|
"loss": 4.8188,
|
|
"mean_token_accuracy": 0.21869716048240662,
|
|
"num_tokens": 38433200.0,
|
|
"step": 20895
|
|
},
|
|
{
|
|
"entropy": 5.3682338237762455,
|
|
"epoch": 1.7457400601403275,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004695204393640125,
|
|
"loss": 4.7944,
|
|
"mean_token_accuracy": 0.21648218631744384,
|
|
"num_tokens": 38442183.0,
|
|
"step": 20900
|
|
},
|
|
{
|
|
"entropy": 5.333422088623047,
|
|
"epoch": 1.7461577013030403,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00046950547610056766,
|
|
"loss": 4.7651,
|
|
"mean_token_accuracy": 0.21351346522569656,
|
|
"num_tokens": 38451451.0,
|
|
"step": 20905
|
|
},
|
|
{
|
|
"entropy": 5.372439241409301,
|
|
"epoch": 1.7465753424657535,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004694905094320703,
|
|
"loss": 4.8438,
|
|
"mean_token_accuracy": 0.2214444413781166,
|
|
"num_tokens": 38460043.0,
|
|
"step": 20910
|
|
},
|
|
{
|
|
"entropy": 5.315252447128296,
|
|
"epoch": 1.7469929836284663,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00046947553935878253,
|
|
"loss": 4.8483,
|
|
"mean_token_accuracy": 0.21846533715724945,
|
|
"num_tokens": 38470714.0,
|
|
"step": 20915
|
|
},
|
|
{
|
|
"entropy": 5.37929859161377,
|
|
"epoch": 1.7474106247911794,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004694605658809663,
|
|
"loss": 4.8555,
|
|
"mean_token_accuracy": 0.22313384115695953,
|
|
"num_tokens": 38480528.0,
|
|
"step": 20920
|
|
},
|
|
{
|
|
"entropy": 5.28024640083313,
|
|
"epoch": 1.7478282659538924,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004694455889988838,
|
|
"loss": 4.7378,
|
|
"mean_token_accuracy": 0.22258236408233642,
|
|
"num_tokens": 38490101.0,
|
|
"step": 20925
|
|
},
|
|
{
|
|
"entropy": 5.392429351806641,
|
|
"epoch": 1.7482459071166054,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00046943060871279725,
|
|
"loss": 4.9255,
|
|
"mean_token_accuracy": 0.2173715963959694,
|
|
"num_tokens": 38498624.0,
|
|
"step": 20930
|
|
},
|
|
{
|
|
"entropy": 5.357790613174439,
|
|
"epoch": 1.7486635482793185,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00046941562502296886,
|
|
"loss": 4.7099,
|
|
"mean_token_accuracy": 0.22592997103929519,
|
|
"num_tokens": 38506646.0,
|
|
"step": 20935
|
|
},
|
|
{
|
|
"entropy": 5.320473670959473,
|
|
"epoch": 1.7490811894420313,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004694006379296609,
|
|
"loss": 4.75,
|
|
"mean_token_accuracy": 0.22461930066347122,
|
|
"num_tokens": 38516092.0,
|
|
"step": 20940
|
|
},
|
|
{
|
|
"entropy": 5.245939302444458,
|
|
"epoch": 1.7494988306047445,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00046938564743313576,
|
|
"loss": 4.7673,
|
|
"mean_token_accuracy": 0.21714254915714265,
|
|
"num_tokens": 38526486.0,
|
|
"step": 20945
|
|
},
|
|
{
|
|
"entropy": 5.300143098831176,
|
|
"epoch": 1.7499164717674573,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00046937065353365594,
|
|
"loss": 4.7851,
|
|
"mean_token_accuracy": 0.22580774128437042,
|
|
"num_tokens": 38535474.0,
|
|
"step": 20950
|
|
},
|
|
{
|
|
"entropy": 5.416376066207886,
|
|
"epoch": 1.7503341129301704,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00046935565623148383,
|
|
"loss": 4.8199,
|
|
"mean_token_accuracy": 0.221078497171402,
|
|
"num_tokens": 38544598.0,
|
|
"step": 20955
|
|
},
|
|
{
|
|
"entropy": 5.346116065979004,
|
|
"epoch": 1.7507517540928834,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00046934065552688196,
|
|
"loss": 4.858,
|
|
"mean_token_accuracy": 0.22190000712871552,
|
|
"num_tokens": 38553569.0,
|
|
"step": 20960
|
|
},
|
|
{
|
|
"entropy": 5.3494068622589115,
|
|
"epoch": 1.7511693952555962,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004693256514201131,
|
|
"loss": 4.871,
|
|
"mean_token_accuracy": 0.22145143449306487,
|
|
"num_tokens": 38563369.0,
|
|
"step": 20965
|
|
},
|
|
{
|
|
"entropy": 5.415035629272461,
|
|
"epoch": 1.7515870364183095,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00046931064391143976,
|
|
"loss": 4.8302,
|
|
"mean_token_accuracy": 0.22043128460645675,
|
|
"num_tokens": 38573187.0,
|
|
"step": 20970
|
|
},
|
|
{
|
|
"entropy": 5.304089164733886,
|
|
"epoch": 1.7520046775810223,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00046929563300112466,
|
|
"loss": 4.6872,
|
|
"mean_token_accuracy": 0.23901872485876083,
|
|
"num_tokens": 38581014.0,
|
|
"step": 20975
|
|
},
|
|
{
|
|
"entropy": 5.263219738006592,
|
|
"epoch": 1.7524223187437353,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00046928061868943067,
|
|
"loss": 4.7592,
|
|
"mean_token_accuracy": 0.22410522550344467,
|
|
"num_tokens": 38590445.0,
|
|
"step": 20980
|
|
},
|
|
{
|
|
"entropy": 5.305362892150879,
|
|
"epoch": 1.7528399599064484,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004692656009766206,
|
|
"loss": 4.7597,
|
|
"mean_token_accuracy": 0.22790224701166154,
|
|
"num_tokens": 38599372.0,
|
|
"step": 20985
|
|
},
|
|
{
|
|
"entropy": 5.41696195602417,
|
|
"epoch": 1.7532576010691614,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00046925057986295734,
|
|
"loss": 4.9339,
|
|
"mean_token_accuracy": 0.21033544689416886,
|
|
"num_tokens": 38609000.0,
|
|
"step": 20990
|
|
},
|
|
{
|
|
"entropy": 5.352322149276733,
|
|
"epoch": 1.7536752422318744,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00046923555534870385,
|
|
"loss": 4.8099,
|
|
"mean_token_accuracy": 0.2188107490539551,
|
|
"num_tokens": 38618420.0,
|
|
"step": 20995
|
|
},
|
|
{
|
|
"entropy": 5.257270812988281,
|
|
"epoch": 1.7540928833945872,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004692205274341232,
|
|
"loss": 4.7143,
|
|
"mean_token_accuracy": 0.23427766412496567,
|
|
"num_tokens": 38627577.0,
|
|
"step": 21000
|
|
},
|
|
{
|
|
"epoch": 1.7540928833945872,
|
|
"eval_entropy": 5.061046384093469,
|
|
"eval_loss": 4.804836273193359,
|
|
"eval_mean_token_accuracy": 0.23295272014809473,
|
|
"eval_num_tokens": 38627577.0,
|
|
"eval_runtime": 20.9202,
|
|
"eval_samples_per_second": 1805.096,
|
|
"eval_steps_per_second": 225.667,
|
|
"step": 21000
|
|
},
|
|
{
|
|
"entropy": 5.391567087173462,
|
|
"epoch": 1.7545105245573005,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00046920549611947834,
|
|
"loss": 4.8905,
|
|
"mean_token_accuracy": 0.22152048349380493,
|
|
"num_tokens": 38636837.0,
|
|
"step": 21005
|
|
},
|
|
{
|
|
"entropy": 5.3820854187011715,
|
|
"epoch": 1.7549281657200133,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004691904614050326,
|
|
"loss": 4.8486,
|
|
"mean_token_accuracy": 0.2160805806517601,
|
|
"num_tokens": 38646734.0,
|
|
"step": 21010
|
|
},
|
|
{
|
|
"entropy": 5.409066390991211,
|
|
"epoch": 1.7553458068827263,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00046917542329104903,
|
|
"loss": 4.9257,
|
|
"mean_token_accuracy": 0.21770072281360625,
|
|
"num_tokens": 38655990.0,
|
|
"step": 21015
|
|
},
|
|
{
|
|
"entropy": 5.335277891159057,
|
|
"epoch": 1.7557634480454394,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004691603817777909,
|
|
"loss": 4.7282,
|
|
"mean_token_accuracy": 0.22199808359146117,
|
|
"num_tokens": 38665235.0,
|
|
"step": 21020
|
|
},
|
|
{
|
|
"entropy": 5.3194173812866214,
|
|
"epoch": 1.7561810892081522,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00046914533686552166,
|
|
"loss": 4.8244,
|
|
"mean_token_accuracy": 0.21462084203958512,
|
|
"num_tokens": 38675810.0,
|
|
"step": 21025
|
|
},
|
|
{
|
|
"entropy": 5.335348606109619,
|
|
"epoch": 1.7565987303708654,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004691302885545046,
|
|
"loss": 4.7526,
|
|
"mean_token_accuracy": 0.2251807376742363,
|
|
"num_tokens": 38684702.0,
|
|
"step": 21030
|
|
},
|
|
{
|
|
"entropy": 5.342238664627075,
|
|
"epoch": 1.7570163715335783,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004691152368450032,
|
|
"loss": 4.8565,
|
|
"mean_token_accuracy": 0.21915366649627685,
|
|
"num_tokens": 38694704.0,
|
|
"step": 21035
|
|
},
|
|
{
|
|
"entropy": 5.312507677078247,
|
|
"epoch": 1.7574340126962913,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00046910018173728084,
|
|
"loss": 4.7431,
|
|
"mean_token_accuracy": 0.22439194917678834,
|
|
"num_tokens": 38702674.0,
|
|
"step": 21040
|
|
},
|
|
{
|
|
"entropy": 5.3000250339508055,
|
|
"epoch": 1.7578516538590043,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004690851232316012,
|
|
"loss": 4.7246,
|
|
"mean_token_accuracy": 0.23503439128398895,
|
|
"num_tokens": 38711842.0,
|
|
"step": 21045
|
|
},
|
|
{
|
|
"entropy": 5.391276693344116,
|
|
"epoch": 1.7582692950217174,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00046907006132822785,
|
|
"loss": 4.8469,
|
|
"mean_token_accuracy": 0.2223531797528267,
|
|
"num_tokens": 38721258.0,
|
|
"step": 21050
|
|
},
|
|
{
|
|
"entropy": 5.288733720779419,
|
|
"epoch": 1.7586869361844304,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00046905499602742444,
|
|
"loss": 4.8059,
|
|
"mean_token_accuracy": 0.2224823459982872,
|
|
"num_tokens": 38730170.0,
|
|
"step": 21055
|
|
},
|
|
{
|
|
"entropy": 5.315092611312866,
|
|
"epoch": 1.7591045773471432,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00046903992732945485,
|
|
"loss": 4.9436,
|
|
"mean_token_accuracy": 0.21357378214597703,
|
|
"num_tokens": 38739790.0,
|
|
"step": 21060
|
|
},
|
|
{
|
|
"entropy": 5.362158870697021,
|
|
"epoch": 1.7595222185098565,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00046902485523458266,
|
|
"loss": 4.7484,
|
|
"mean_token_accuracy": 0.22713471502065657,
|
|
"num_tokens": 38748793.0,
|
|
"step": 21065
|
|
},
|
|
{
|
|
"entropy": 5.405821800231934,
|
|
"epoch": 1.7599398596725693,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00046900977974307186,
|
|
"loss": 4.8852,
|
|
"mean_token_accuracy": 0.21647584140300752,
|
|
"num_tokens": 38758067.0,
|
|
"step": 21070
|
|
},
|
|
{
|
|
"entropy": 5.242900705337524,
|
|
"epoch": 1.7603575008352823,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004689947008551863,
|
|
"loss": 4.7278,
|
|
"mean_token_accuracy": 0.23314090818166733,
|
|
"num_tokens": 38767374.0,
|
|
"step": 21075
|
|
},
|
|
{
|
|
"entropy": 5.340026617050171,
|
|
"epoch": 1.7607751419979953,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004689796185711901,
|
|
"loss": 4.8658,
|
|
"mean_token_accuracy": 0.21732112318277358,
|
|
"num_tokens": 38776467.0,
|
|
"step": 21080
|
|
},
|
|
{
|
|
"entropy": 5.34798641204834,
|
|
"epoch": 1.7611927831607082,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00046896453289134703,
|
|
"loss": 4.7804,
|
|
"mean_token_accuracy": 0.22870559096336365,
|
|
"num_tokens": 38785916.0,
|
|
"step": 21085
|
|
},
|
|
{
|
|
"entropy": 5.401841735839843,
|
|
"epoch": 1.7616104243234214,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00046894944381592143,
|
|
"loss": 4.8162,
|
|
"mean_token_accuracy": 0.22255780994892121,
|
|
"num_tokens": 38795271.0,
|
|
"step": 21090
|
|
},
|
|
{
|
|
"entropy": 5.312746000289917,
|
|
"epoch": 1.7620280654861342,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00046893435134517735,
|
|
"loss": 4.8366,
|
|
"mean_token_accuracy": 0.22432955652475356,
|
|
"num_tokens": 38804806.0,
|
|
"step": 21095
|
|
},
|
|
{
|
|
"entropy": 5.29525351524353,
|
|
"epoch": 1.7624457066488475,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00046891925547937907,
|
|
"loss": 4.6965,
|
|
"mean_token_accuracy": 0.23031720221042634,
|
|
"num_tokens": 38813465.0,
|
|
"step": 21100
|
|
},
|
|
{
|
|
"entropy": 5.3489490985870365,
|
|
"epoch": 1.7628633478115603,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00046890415621879075,
|
|
"loss": 4.8742,
|
|
"mean_token_accuracy": 0.2120506525039673,
|
|
"num_tokens": 38822208.0,
|
|
"step": 21105
|
|
},
|
|
{
|
|
"entropy": 5.354934978485107,
|
|
"epoch": 1.7632809889742733,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004688890535636767,
|
|
"loss": 4.7848,
|
|
"mean_token_accuracy": 0.2251820147037506,
|
|
"num_tokens": 38831136.0,
|
|
"step": 21110
|
|
},
|
|
{
|
|
"entropy": 5.392121982574463,
|
|
"epoch": 1.7636986301369864,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004688739475143015,
|
|
"loss": 4.8604,
|
|
"mean_token_accuracy": 0.22121517211198807,
|
|
"num_tokens": 38840995.0,
|
|
"step": 21115
|
|
},
|
|
{
|
|
"entropy": 5.410759496688843,
|
|
"epoch": 1.7641162712996992,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00046885883807092944,
|
|
"loss": 4.9046,
|
|
"mean_token_accuracy": 0.21738007366657258,
|
|
"num_tokens": 38850584.0,
|
|
"step": 21120
|
|
},
|
|
{
|
|
"entropy": 5.236608505249023,
|
|
"epoch": 1.7645339124624124,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00046884372523382507,
|
|
"loss": 4.658,
|
|
"mean_token_accuracy": 0.24224987924098967,
|
|
"num_tokens": 38858869.0,
|
|
"step": 21125
|
|
},
|
|
{
|
|
"entropy": 5.33279013633728,
|
|
"epoch": 1.7649515536251252,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00046882860900325296,
|
|
"loss": 4.8677,
|
|
"mean_token_accuracy": 0.21241406947374344,
|
|
"num_tokens": 38868701.0,
|
|
"step": 21130
|
|
},
|
|
{
|
|
"entropy": 5.374946641921997,
|
|
"epoch": 1.7653691947878383,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004688134893794777,
|
|
"loss": 4.9314,
|
|
"mean_token_accuracy": 0.20829507410526277,
|
|
"num_tokens": 38877785.0,
|
|
"step": 21135
|
|
},
|
|
{
|
|
"entropy": 5.45654330253601,
|
|
"epoch": 1.7657868359505513,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00046879836636276405,
|
|
"loss": 4.9179,
|
|
"mean_token_accuracy": 0.21573514640331268,
|
|
"num_tokens": 38888397.0,
|
|
"step": 21140
|
|
},
|
|
{
|
|
"entropy": 5.390010738372803,
|
|
"epoch": 1.7662044771132643,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004687832399533767,
|
|
"loss": 4.9122,
|
|
"mean_token_accuracy": 0.20952266603708267,
|
|
"num_tokens": 38897458.0,
|
|
"step": 21145
|
|
},
|
|
{
|
|
"entropy": 5.402655506134034,
|
|
"epoch": 1.7666221182759774,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004687681101515805,
|
|
"loss": 4.8445,
|
|
"mean_token_accuracy": 0.22570979297161103,
|
|
"num_tokens": 38907536.0,
|
|
"step": 21150
|
|
},
|
|
{
|
|
"entropy": 5.395899105072021,
|
|
"epoch": 1.7670397594386902,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004687529769576403,
|
|
"loss": 4.8621,
|
|
"mean_token_accuracy": 0.22012796252965927,
|
|
"num_tokens": 38917340.0,
|
|
"step": 21155
|
|
},
|
|
{
|
|
"entropy": 5.330655479431153,
|
|
"epoch": 1.7674574006014034,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00046873784037182106,
|
|
"loss": 4.8434,
|
|
"mean_token_accuracy": 0.21525445431470872,
|
|
"num_tokens": 38926964.0,
|
|
"step": 21160
|
|
},
|
|
{
|
|
"entropy": 5.305201435089112,
|
|
"epoch": 1.7678750417641163,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00046872270039438764,
|
|
"loss": 4.7511,
|
|
"mean_token_accuracy": 0.23223549723625184,
|
|
"num_tokens": 38936168.0,
|
|
"step": 21165
|
|
},
|
|
{
|
|
"entropy": 5.390122413635254,
|
|
"epoch": 1.7682926829268293,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004687075570256052,
|
|
"loss": 4.9401,
|
|
"mean_token_accuracy": 0.21756706088781358,
|
|
"num_tokens": 38945633.0,
|
|
"step": 21170
|
|
},
|
|
{
|
|
"entropy": 5.396428012847901,
|
|
"epoch": 1.7687103240895423,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00046869241026573885,
|
|
"loss": 4.8986,
|
|
"mean_token_accuracy": 0.21232820451259612,
|
|
"num_tokens": 38955372.0,
|
|
"step": 21175
|
|
},
|
|
{
|
|
"entropy": 5.344900131225586,
|
|
"epoch": 1.7691279652522551,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00046867726011505365,
|
|
"loss": 4.8162,
|
|
"mean_token_accuracy": 0.22018022537231446,
|
|
"num_tokens": 38965264.0,
|
|
"step": 21180
|
|
},
|
|
{
|
|
"entropy": 5.2993934631347654,
|
|
"epoch": 1.7695456064149684,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004686621065738149,
|
|
"loss": 4.8514,
|
|
"mean_token_accuracy": 0.22063871324062348,
|
|
"num_tokens": 38975129.0,
|
|
"step": 21185
|
|
},
|
|
{
|
|
"entropy": 5.4259498596191404,
|
|
"epoch": 1.7699632475776812,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00046864694964228785,
|
|
"loss": 4.9363,
|
|
"mean_token_accuracy": 0.21339934170246125,
|
|
"num_tokens": 38985152.0,
|
|
"step": 21190
|
|
},
|
|
{
|
|
"entropy": 5.3223308563232425,
|
|
"epoch": 1.7703808887403942,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004686317893207378,
|
|
"loss": 4.7388,
|
|
"mean_token_accuracy": 0.21915649473667145,
|
|
"num_tokens": 38995509.0,
|
|
"step": 21195
|
|
},
|
|
{
|
|
"entropy": 5.31452693939209,
|
|
"epoch": 1.7707985299031073,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004686166256094303,
|
|
"loss": 4.8087,
|
|
"mean_token_accuracy": 0.21818214803934097,
|
|
"num_tokens": 39003743.0,
|
|
"step": 21200
|
|
},
|
|
{
|
|
"entropy": 5.340146780014038,
|
|
"epoch": 1.7712161710658203,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004686014585086307,
|
|
"loss": 4.8491,
|
|
"mean_token_accuracy": 0.21738118529319764,
|
|
"num_tokens": 39013324.0,
|
|
"step": 21205
|
|
},
|
|
{
|
|
"entropy": 5.343484354019165,
|
|
"epoch": 1.7716338122285333,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004685862880186045,
|
|
"loss": 4.8027,
|
|
"mean_token_accuracy": 0.22474362850189208,
|
|
"num_tokens": 39023268.0,
|
|
"step": 21210
|
|
},
|
|
{
|
|
"entropy": 5.3716028213500975,
|
|
"epoch": 1.7720514533912461,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004685711141396173,
|
|
"loss": 4.882,
|
|
"mean_token_accuracy": 0.21614743769168854,
|
|
"num_tokens": 39033516.0,
|
|
"step": 21215
|
|
},
|
|
{
|
|
"entropy": 5.363636445999146,
|
|
"epoch": 1.7724690945539594,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00046855593687193474,
|
|
"loss": 4.8392,
|
|
"mean_token_accuracy": 0.2245599776506424,
|
|
"num_tokens": 39042280.0,
|
|
"step": 21220
|
|
},
|
|
{
|
|
"entropy": 5.289165925979614,
|
|
"epoch": 1.7728867357166722,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004685407562158226,
|
|
"loss": 4.8164,
|
|
"mean_token_accuracy": 0.23183736801147461,
|
|
"num_tokens": 39051748.0,
|
|
"step": 21225
|
|
},
|
|
{
|
|
"entropy": 5.364990186691284,
|
|
"epoch": 1.7733043768793852,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004685255721715465,
|
|
"loss": 4.8615,
|
|
"mean_token_accuracy": 0.2151083767414093,
|
|
"num_tokens": 39061703.0,
|
|
"step": 21230
|
|
},
|
|
{
|
|
"entropy": 5.414002466201782,
|
|
"epoch": 1.7737220180420983,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004685103847393723,
|
|
"loss": 4.8618,
|
|
"mean_token_accuracy": 0.22029326856136322,
|
|
"num_tokens": 39071115.0,
|
|
"step": 21235
|
|
},
|
|
{
|
|
"entropy": 5.324331045150757,
|
|
"epoch": 1.774139659204811,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00046849519391956593,
|
|
"loss": 4.839,
|
|
"mean_token_accuracy": 0.21000996232032776,
|
|
"num_tokens": 39080578.0,
|
|
"step": 21240
|
|
},
|
|
{
|
|
"entropy": 5.3151041030883786,
|
|
"epoch": 1.7745573003675243,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004684799997123932,
|
|
"loss": 4.848,
|
|
"mean_token_accuracy": 0.21807854026556014,
|
|
"num_tokens": 39090242.0,
|
|
"step": 21245
|
|
},
|
|
{
|
|
"entropy": 5.35726637840271,
|
|
"epoch": 1.7749749415302372,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004684648021181203,
|
|
"loss": 4.8724,
|
|
"mean_token_accuracy": 0.2203865572810173,
|
|
"num_tokens": 39099831.0,
|
|
"step": 21250
|
|
},
|
|
{
|
|
"entropy": 5.2664776802062985,
|
|
"epoch": 1.7753925826929502,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00046844960113701307,
|
|
"loss": 4.6582,
|
|
"mean_token_accuracy": 0.23412342369556427,
|
|
"num_tokens": 39109047.0,
|
|
"step": 21255
|
|
},
|
|
{
|
|
"entropy": 5.3422935009002686,
|
|
"epoch": 1.7758102238556632,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00046843439676933776,
|
|
"loss": 4.7858,
|
|
"mean_token_accuracy": 0.22046843022108079,
|
|
"num_tokens": 39117800.0,
|
|
"step": 21260
|
|
},
|
|
{
|
|
"entropy": 5.418313074111938,
|
|
"epoch": 1.7762278650183763,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00046841918901536047,
|
|
"loss": 4.8549,
|
|
"mean_token_accuracy": 0.22146642506122588,
|
|
"num_tokens": 39127019.0,
|
|
"step": 21265
|
|
},
|
|
{
|
|
"entropy": 5.296676111221314,
|
|
"epoch": 1.7766455061810893,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004684039778753474,
|
|
"loss": 4.7343,
|
|
"mean_token_accuracy": 0.22994308769702912,
|
|
"num_tokens": 39135983.0,
|
|
"step": 21270
|
|
},
|
|
{
|
|
"entropy": 5.285355854034424,
|
|
"epoch": 1.777063147343802,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00046838876334956507,
|
|
"loss": 4.7675,
|
|
"mean_token_accuracy": 0.22096860259771348,
|
|
"num_tokens": 39145890.0,
|
|
"step": 21275
|
|
},
|
|
{
|
|
"entropy": 5.358976364135742,
|
|
"epoch": 1.7774807885065154,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004683735454382795,
|
|
"loss": 4.7651,
|
|
"mean_token_accuracy": 0.22440462112426757,
|
|
"num_tokens": 39154884.0,
|
|
"step": 21280
|
|
},
|
|
{
|
|
"entropy": 5.345382833480835,
|
|
"epoch": 1.7778984296692282,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004683583241417573,
|
|
"loss": 4.7918,
|
|
"mean_token_accuracy": 0.2197599560022354,
|
|
"num_tokens": 39164151.0,
|
|
"step": 21285
|
|
},
|
|
{
|
|
"entropy": 5.3825654029846195,
|
|
"epoch": 1.7783160708319412,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004683430994602649,
|
|
"loss": 4.9313,
|
|
"mean_token_accuracy": 0.2141004353761673,
|
|
"num_tokens": 39173987.0,
|
|
"step": 21290
|
|
},
|
|
{
|
|
"entropy": 5.3911596775054935,
|
|
"epoch": 1.7787337119946542,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00046832787139406887,
|
|
"loss": 4.9121,
|
|
"mean_token_accuracy": 0.22044035643339158,
|
|
"num_tokens": 39183665.0,
|
|
"step": 21295
|
|
},
|
|
{
|
|
"entropy": 5.384204387664795,
|
|
"epoch": 1.779151353157367,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004683126399434357,
|
|
"loss": 4.7504,
|
|
"mean_token_accuracy": 0.2315254881978035,
|
|
"num_tokens": 39192897.0,
|
|
"step": 21300
|
|
},
|
|
{
|
|
"entropy": 5.46144437789917,
|
|
"epoch": 1.7795689943200803,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004682974051086321,
|
|
"loss": 4.9369,
|
|
"mean_token_accuracy": 0.21881940215826035,
|
|
"num_tokens": 39202774.0,
|
|
"step": 21305
|
|
},
|
|
{
|
|
"entropy": 5.345961713790894,
|
|
"epoch": 1.7799866354827931,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00046828216688992466,
|
|
"loss": 4.7886,
|
|
"mean_token_accuracy": 0.2193300798535347,
|
|
"num_tokens": 39212154.0,
|
|
"step": 21310
|
|
},
|
|
{
|
|
"entropy": 5.254640913009643,
|
|
"epoch": 1.7804042766455062,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004682669252875803,
|
|
"loss": 4.7328,
|
|
"mean_token_accuracy": 0.22710598409175872,
|
|
"num_tokens": 39221593.0,
|
|
"step": 21315
|
|
},
|
|
{
|
|
"entropy": 5.347976016998291,
|
|
"epoch": 1.7808219178082192,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00046825168030186577,
|
|
"loss": 4.8529,
|
|
"mean_token_accuracy": 0.22022807151079177,
|
|
"num_tokens": 39230522.0,
|
|
"step": 21320
|
|
},
|
|
{
|
|
"entropy": 5.319326257705688,
|
|
"epoch": 1.7812395589709322,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000468236431933048,
|
|
"loss": 4.8609,
|
|
"mean_token_accuracy": 0.21692500710487367,
|
|
"num_tokens": 39240012.0,
|
|
"step": 21325
|
|
},
|
|
{
|
|
"entropy": 5.342963790893554,
|
|
"epoch": 1.7816572001336453,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004682211801813938,
|
|
"loss": 4.7949,
|
|
"mean_token_accuracy": 0.22546567469835282,
|
|
"num_tokens": 39248789.0,
|
|
"step": 21330
|
|
},
|
|
{
|
|
"entropy": 5.435909652709961,
|
|
"epoch": 1.782074841296358,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004682059250471703,
|
|
"loss": 4.8599,
|
|
"mean_token_accuracy": 0.22534992247819902,
|
|
"num_tokens": 39257864.0,
|
|
"step": 21335
|
|
},
|
|
{
|
|
"entropy": 5.3948980331420895,
|
|
"epoch": 1.7824924824590713,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00046819066653064454,
|
|
"loss": 4.7922,
|
|
"mean_token_accuracy": 0.21340446621179582,
|
|
"num_tokens": 39267137.0,
|
|
"step": 21340
|
|
},
|
|
{
|
|
"entropy": 5.324335718154908,
|
|
"epoch": 1.7829101236217841,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00046817540463208357,
|
|
"loss": 4.87,
|
|
"mean_token_accuracy": 0.21562979072332383,
|
|
"num_tokens": 39276511.0,
|
|
"step": 21345
|
|
},
|
|
{
|
|
"entropy": 5.310010194778442,
|
|
"epoch": 1.7833277647844972,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00046816013935175465,
|
|
"loss": 4.7876,
|
|
"mean_token_accuracy": 0.23115962445735933,
|
|
"num_tokens": 39285053.0,
|
|
"step": 21350
|
|
},
|
|
{
|
|
"entropy": 5.268276166915894,
|
|
"epoch": 1.7837454059472102,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000468144870689925,
|
|
"loss": 4.7817,
|
|
"mean_token_accuracy": 0.22261122167110442,
|
|
"num_tokens": 39293536.0,
|
|
"step": 21355
|
|
},
|
|
{
|
|
"entropy": 5.401349782943726,
|
|
"epoch": 1.784163047109923,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004681295986468619,
|
|
"loss": 4.889,
|
|
"mean_token_accuracy": 0.21568322777748108,
|
|
"num_tokens": 39303074.0,
|
|
"step": 21360
|
|
},
|
|
{
|
|
"entropy": 5.355392503738403,
|
|
"epoch": 1.7845806882726363,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004681143232228328,
|
|
"loss": 4.8078,
|
|
"mean_token_accuracy": 0.21862483620643616,
|
|
"num_tokens": 39312148.0,
|
|
"step": 21365
|
|
},
|
|
{
|
|
"entropy": 5.365454769134521,
|
|
"epoch": 1.784998329435349,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00046809904441810486,
|
|
"loss": 4.8528,
|
|
"mean_token_accuracy": 0.22608238011598586,
|
|
"num_tokens": 39321098.0,
|
|
"step": 21370
|
|
},
|
|
{
|
|
"entropy": 5.283417797088623,
|
|
"epoch": 1.7854159705980621,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004680837622329457,
|
|
"loss": 4.6622,
|
|
"mean_token_accuracy": 0.23178208619356155,
|
|
"num_tokens": 39329463.0,
|
|
"step": 21375
|
|
},
|
|
{
|
|
"entropy": 5.330474805831909,
|
|
"epoch": 1.7858336117607752,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00046806847666762305,
|
|
"loss": 4.8218,
|
|
"mean_token_accuracy": 0.22208698093891144,
|
|
"num_tokens": 39339497.0,
|
|
"step": 21380
|
|
},
|
|
{
|
|
"entropy": 5.287147903442383,
|
|
"epoch": 1.7862512529234882,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004680531877224042,
|
|
"loss": 4.6773,
|
|
"mean_token_accuracy": 0.23797102868556977,
|
|
"num_tokens": 39348121.0,
|
|
"step": 21385
|
|
},
|
|
{
|
|
"entropy": 5.297281217575073,
|
|
"epoch": 1.7866688940862012,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00046803789539755686,
|
|
"loss": 4.8582,
|
|
"mean_token_accuracy": 0.22131120711565017,
|
|
"num_tokens": 39358487.0,
|
|
"step": 21390
|
|
},
|
|
{
|
|
"entropy": 5.315872621536255,
|
|
"epoch": 1.787086535248914,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00046802259969334887,
|
|
"loss": 4.8659,
|
|
"mean_token_accuracy": 0.21899228990077974,
|
|
"num_tokens": 39367493.0,
|
|
"step": 21395
|
|
},
|
|
{
|
|
"entropy": 5.28014726638794,
|
|
"epoch": 1.7875041764116273,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004680073006100479,
|
|
"loss": 4.8089,
|
|
"mean_token_accuracy": 0.2225469544529915,
|
|
"num_tokens": 39376616.0,
|
|
"step": 21400
|
|
},
|
|
{
|
|
"entropy": 5.396706867218017,
|
|
"epoch": 1.78792181757434,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00046799199814792186,
|
|
"loss": 4.8565,
|
|
"mean_token_accuracy": 0.21577073037624359,
|
|
"num_tokens": 39387079.0,
|
|
"step": 21405
|
|
},
|
|
{
|
|
"entropy": 5.25217866897583,
|
|
"epoch": 1.7883394587370531,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004679766923072386,
|
|
"loss": 4.704,
|
|
"mean_token_accuracy": 0.22878554910421373,
|
|
"num_tokens": 39396198.0,
|
|
"step": 21410
|
|
},
|
|
{
|
|
"entropy": 5.379284286499024,
|
|
"epoch": 1.7887570998997662,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000467961383088266,
|
|
"loss": 4.9171,
|
|
"mean_token_accuracy": 0.2168014943599701,
|
|
"num_tokens": 39405862.0,
|
|
"step": 21415
|
|
},
|
|
{
|
|
"entropy": 5.373177480697632,
|
|
"epoch": 1.789174741062479,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00046794607049127217,
|
|
"loss": 4.8415,
|
|
"mean_token_accuracy": 0.21971196234226226,
|
|
"num_tokens": 39414352.0,
|
|
"step": 21420
|
|
},
|
|
{
|
|
"entropy": 5.411777067184448,
|
|
"epoch": 1.7895923822251922,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00046793075451652513,
|
|
"loss": 4.8642,
|
|
"mean_token_accuracy": 0.21900019496679307,
|
|
"num_tokens": 39423653.0,
|
|
"step": 21425
|
|
},
|
|
{
|
|
"entropy": 5.36974687576294,
|
|
"epoch": 1.790010023387905,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00046791543516429295,
|
|
"loss": 4.8757,
|
|
"mean_token_accuracy": 0.22274621576070786,
|
|
"num_tokens": 39432741.0,
|
|
"step": 21430
|
|
},
|
|
{
|
|
"entropy": 5.381681251525879,
|
|
"epoch": 1.790427664550618,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00046790011243484387,
|
|
"loss": 4.8557,
|
|
"mean_token_accuracy": 0.2179940864443779,
|
|
"num_tokens": 39441837.0,
|
|
"step": 21435
|
|
},
|
|
{
|
|
"entropy": 5.320331335067749,
|
|
"epoch": 1.7908453057133311,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00046788478632844616,
|
|
"loss": 4.809,
|
|
"mean_token_accuracy": 0.22308923602104186,
|
|
"num_tokens": 39450393.0,
|
|
"step": 21440
|
|
},
|
|
{
|
|
"entropy": 5.2767098903656,
|
|
"epoch": 1.7912629468760441,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00046786945684536806,
|
|
"loss": 4.7308,
|
|
"mean_token_accuracy": 0.22603198140859604,
|
|
"num_tokens": 39460226.0,
|
|
"step": 21445
|
|
},
|
|
{
|
|
"entropy": 5.307002258300781,
|
|
"epoch": 1.7916805880387572,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000467854123985878,
|
|
"loss": 4.7165,
|
|
"mean_token_accuracy": 0.23004019409418106,
|
|
"num_tokens": 39469072.0,
|
|
"step": 21450
|
|
},
|
|
{
|
|
"entropy": 5.308313226699829,
|
|
"epoch": 1.79209822920147,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004678387877502443,
|
|
"loss": 4.762,
|
|
"mean_token_accuracy": 0.22041673213243484,
|
|
"num_tokens": 39477918.0,
|
|
"step": 21455
|
|
},
|
|
{
|
|
"entropy": 5.178896188735962,
|
|
"epoch": 1.7925158703641833,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00046782344813873556,
|
|
"loss": 4.6745,
|
|
"mean_token_accuracy": 0.234441876411438,
|
|
"num_tokens": 39487492.0,
|
|
"step": 21460
|
|
},
|
|
{
|
|
"entropy": 5.287927627563477,
|
|
"epoch": 1.792933511526896,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00046780810515162027,
|
|
"loss": 4.7716,
|
|
"mean_token_accuracy": 0.22757367491722108,
|
|
"num_tokens": 39496255.0,
|
|
"step": 21465
|
|
},
|
|
{
|
|
"entropy": 5.244673728942871,
|
|
"epoch": 1.793351152689609,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00046779275878916694,
|
|
"loss": 4.7681,
|
|
"mean_token_accuracy": 0.23395950645208358,
|
|
"num_tokens": 39504925.0,
|
|
"step": 21470
|
|
},
|
|
{
|
|
"entropy": 5.334796953201294,
|
|
"epoch": 1.7937687938523221,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00046777740905164434,
|
|
"loss": 4.8394,
|
|
"mean_token_accuracy": 0.22033998221158982,
|
|
"num_tokens": 39514289.0,
|
|
"step": 21475
|
|
},
|
|
{
|
|
"entropy": 5.398670339584351,
|
|
"epoch": 1.794186435015035,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00046776205593932114,
|
|
"loss": 4.8516,
|
|
"mean_token_accuracy": 0.221982704102993,
|
|
"num_tokens": 39524421.0,
|
|
"step": 21480
|
|
},
|
|
{
|
|
"entropy": 5.373714828491211,
|
|
"epoch": 1.7946040761777482,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00046774669945246616,
|
|
"loss": 4.7838,
|
|
"mean_token_accuracy": 0.22104454636573792,
|
|
"num_tokens": 39532866.0,
|
|
"step": 21485
|
|
},
|
|
{
|
|
"entropy": 5.397964334487915,
|
|
"epoch": 1.795021717340461,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004677313395913482,
|
|
"loss": 4.8866,
|
|
"mean_token_accuracy": 0.21177667379379272,
|
|
"num_tokens": 39542964.0,
|
|
"step": 21490
|
|
},
|
|
{
|
|
"entropy": 5.380643749237061,
|
|
"epoch": 1.795439358503174,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004677159763562361,
|
|
"loss": 4.8719,
|
|
"mean_token_accuracy": 0.21493024230003357,
|
|
"num_tokens": 39554127.0,
|
|
"step": 21495
|
|
},
|
|
{
|
|
"entropy": 5.291879510879516,
|
|
"epoch": 1.795856999665887,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00046770060974739893,
|
|
"loss": 4.8007,
|
|
"mean_token_accuracy": 0.2236670583486557,
|
|
"num_tokens": 39563600.0,
|
|
"step": 21500
|
|
},
|
|
{
|
|
"entropy": 5.297561502456665,
|
|
"epoch": 1.7962746408286,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004676852397651055,
|
|
"loss": 4.7723,
|
|
"mean_token_accuracy": 0.2215910866856575,
|
|
"num_tokens": 39572502.0,
|
|
"step": 21505
|
|
},
|
|
{
|
|
"entropy": 5.318136215209961,
|
|
"epoch": 1.7966922819913131,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004676698664096251,
|
|
"loss": 4.7037,
|
|
"mean_token_accuracy": 0.22905585914850235,
|
|
"num_tokens": 39581066.0,
|
|
"step": 21510
|
|
},
|
|
{
|
|
"entropy": 5.3250213146209715,
|
|
"epoch": 1.797109923154026,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004676544896812268,
|
|
"loss": 4.7686,
|
|
"mean_token_accuracy": 0.22563111782073975,
|
|
"num_tokens": 39589784.0,
|
|
"step": 21515
|
|
},
|
|
{
|
|
"entropy": 5.353819131851196,
|
|
"epoch": 1.7975275643167392,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00046763910958017973,
|
|
"loss": 4.9245,
|
|
"mean_token_accuracy": 0.21348586231470107,
|
|
"num_tokens": 39598561.0,
|
|
"step": 21520
|
|
},
|
|
{
|
|
"entropy": 5.312294387817383,
|
|
"epoch": 1.797945205479452,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00046762372610675314,
|
|
"loss": 4.7222,
|
|
"mean_token_accuracy": 0.22965348064899443,
|
|
"num_tokens": 39607136.0,
|
|
"step": 21525
|
|
},
|
|
{
|
|
"entropy": 5.377471685409546,
|
|
"epoch": 1.798362846642165,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00046760833926121645,
|
|
"loss": 4.8386,
|
|
"mean_token_accuracy": 0.22368142604827881,
|
|
"num_tokens": 39616371.0,
|
|
"step": 21530
|
|
},
|
|
{
|
|
"entropy": 5.272024774551392,
|
|
"epoch": 1.798780487804878,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00046759294904383887,
|
|
"loss": 4.8206,
|
|
"mean_token_accuracy": 0.2208560287952423,
|
|
"num_tokens": 39625556.0,
|
|
"step": 21535
|
|
},
|
|
{
|
|
"entropy": 5.285622072219849,
|
|
"epoch": 1.799198128967591,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004675775554548899,
|
|
"loss": 4.7454,
|
|
"mean_token_accuracy": 0.22154634594917297,
|
|
"num_tokens": 39635116.0,
|
|
"step": 21540
|
|
},
|
|
{
|
|
"entropy": 5.394057941436768,
|
|
"epoch": 1.7996157701303042,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00046756215849463905,
|
|
"loss": 4.8516,
|
|
"mean_token_accuracy": 0.2143603101372719,
|
|
"num_tokens": 39645523.0,
|
|
"step": 21545
|
|
},
|
|
{
|
|
"entropy": 5.425209951400757,
|
|
"epoch": 1.800033411293017,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00046754675816335577,
|
|
"loss": 4.9032,
|
|
"mean_token_accuracy": 0.21861398071050644,
|
|
"num_tokens": 39654507.0,
|
|
"step": 21550
|
|
},
|
|
{
|
|
"entropy": 5.333800888061523,
|
|
"epoch": 1.80045105245573,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00046753135446130973,
|
|
"loss": 4.8098,
|
|
"mean_token_accuracy": 0.2217814639210701,
|
|
"num_tokens": 39664587.0,
|
|
"step": 21555
|
|
},
|
|
{
|
|
"entropy": 5.376449060440064,
|
|
"epoch": 1.800868693618443,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004675159473887707,
|
|
"loss": 4.9018,
|
|
"mean_token_accuracy": 0.21356830447912217,
|
|
"num_tokens": 39674844.0,
|
|
"step": 21560
|
|
},
|
|
{
|
|
"entropy": 5.325456380844116,
|
|
"epoch": 1.801286334781156,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004675005369460081,
|
|
"loss": 4.7837,
|
|
"mean_token_accuracy": 0.2296168565750122,
|
|
"num_tokens": 39683894.0,
|
|
"step": 21565
|
|
},
|
|
{
|
|
"entropy": 5.300006437301636,
|
|
"epoch": 1.801703975943869,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000467485123133292,
|
|
"loss": 4.8474,
|
|
"mean_token_accuracy": 0.21865759491920472,
|
|
"num_tokens": 39693401.0,
|
|
"step": 21570
|
|
},
|
|
{
|
|
"entropy": 5.289791440963745,
|
|
"epoch": 1.802121617106582,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00046746970595089207,
|
|
"loss": 4.8415,
|
|
"mean_token_accuracy": 0.21517006903886796,
|
|
"num_tokens": 39702506.0,
|
|
"step": 21575
|
|
},
|
|
{
|
|
"entropy": 5.365351390838623,
|
|
"epoch": 1.8025392582692952,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004674542853990783,
|
|
"loss": 4.7815,
|
|
"mean_token_accuracy": 0.2265598237514496,
|
|
"num_tokens": 39711252.0,
|
|
"step": 21580
|
|
},
|
|
{
|
|
"entropy": 5.36640191078186,
|
|
"epoch": 1.802956899432008,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00046743886147812054,
|
|
"loss": 4.8137,
|
|
"mean_token_accuracy": 0.2191891223192215,
|
|
"num_tokens": 39719803.0,
|
|
"step": 21585
|
|
},
|
|
{
|
|
"entropy": 5.294553518295288,
|
|
"epoch": 1.803374540594721,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004674234341882889,
|
|
"loss": 4.7044,
|
|
"mean_token_accuracy": 0.23069656193256377,
|
|
"num_tokens": 39728492.0,
|
|
"step": 21590
|
|
},
|
|
{
|
|
"entropy": 5.37398886680603,
|
|
"epoch": 1.803792181757434,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004674080035298535,
|
|
"loss": 4.9057,
|
|
"mean_token_accuracy": 0.20799989104270936,
|
|
"num_tokens": 39737703.0,
|
|
"step": 21595
|
|
},
|
|
{
|
|
"entropy": 5.344189119338989,
|
|
"epoch": 1.8042098229201469,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004673925695030843,
|
|
"loss": 4.7957,
|
|
"mean_token_accuracy": 0.22139796912670134,
|
|
"num_tokens": 39746529.0,
|
|
"step": 21600
|
|
},
|
|
{
|
|
"entropy": 5.437683486938477,
|
|
"epoch": 1.8046274640828601,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004673771321082517,
|
|
"loss": 4.9893,
|
|
"mean_token_accuracy": 0.21069931089878083,
|
|
"num_tokens": 39756398.0,
|
|
"step": 21605
|
|
},
|
|
{
|
|
"entropy": 5.377500391006469,
|
|
"epoch": 1.805045105245573,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004673616913456258,
|
|
"loss": 4.9027,
|
|
"mean_token_accuracy": 0.21385316997766496,
|
|
"num_tokens": 39766354.0,
|
|
"step": 21610
|
|
},
|
|
{
|
|
"entropy": 5.459893798828125,
|
|
"epoch": 1.805462746408286,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00046734624721547687,
|
|
"loss": 4.9273,
|
|
"mean_token_accuracy": 0.21376698315143586,
|
|
"num_tokens": 39776089.0,
|
|
"step": 21615
|
|
},
|
|
{
|
|
"entropy": 5.359681224822998,
|
|
"epoch": 1.805880387570999,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00046733079971807536,
|
|
"loss": 4.8512,
|
|
"mean_token_accuracy": 0.22341697365045549,
|
|
"num_tokens": 39785390.0,
|
|
"step": 21620
|
|
},
|
|
{
|
|
"entropy": 5.299870872497559,
|
|
"epoch": 1.806298028733712,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00046731534885369175,
|
|
"loss": 4.6488,
|
|
"mean_token_accuracy": 0.24062049239873887,
|
|
"num_tokens": 39793837.0,
|
|
"step": 21625
|
|
},
|
|
{
|
|
"entropy": 5.329631900787353,
|
|
"epoch": 1.806715669896425,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004672998946225965,
|
|
"loss": 4.8047,
|
|
"mean_token_accuracy": 0.22373324781656265,
|
|
"num_tokens": 39802391.0,
|
|
"step": 21630
|
|
},
|
|
{
|
|
"entropy": 5.28034348487854,
|
|
"epoch": 1.8071333110591379,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00046728443702506007,
|
|
"loss": 4.7991,
|
|
"mean_token_accuracy": 0.2215643957257271,
|
|
"num_tokens": 39812110.0,
|
|
"step": 21635
|
|
},
|
|
{
|
|
"entropy": 5.399539184570313,
|
|
"epoch": 1.8075509522218511,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00046726897606135307,
|
|
"loss": 4.813,
|
|
"mean_token_accuracy": 0.21957896053791046,
|
|
"num_tokens": 39821647.0,
|
|
"step": 21640
|
|
},
|
|
{
|
|
"entropy": 5.335121917724609,
|
|
"epoch": 1.807968593384564,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00046725351173174627,
|
|
"loss": 4.7452,
|
|
"mean_token_accuracy": 0.22781633883714675,
|
|
"num_tokens": 39829520.0,
|
|
"step": 21645
|
|
},
|
|
{
|
|
"entropy": 5.377707242965698,
|
|
"epoch": 1.808386234547277,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004672380440365103,
|
|
"loss": 4.8916,
|
|
"mean_token_accuracy": 0.22305624932050705,
|
|
"num_tokens": 39839226.0,
|
|
"step": 21650
|
|
},
|
|
{
|
|
"entropy": 5.389760255813599,
|
|
"epoch": 1.80880387570999,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000467222572975916,
|
|
"loss": 4.8088,
|
|
"mean_token_accuracy": 0.232799032330513,
|
|
"num_tokens": 39847937.0,
|
|
"step": 21655
|
|
},
|
|
{
|
|
"entropy": 5.3019623279571535,
|
|
"epoch": 1.8092215168727028,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004672070985502342,
|
|
"loss": 4.7641,
|
|
"mean_token_accuracy": 0.226020710170269,
|
|
"num_tokens": 39857293.0,
|
|
"step": 21660
|
|
},
|
|
{
|
|
"entropy": 5.258433246612549,
|
|
"epoch": 1.809639158035416,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00046719162075973576,
|
|
"loss": 4.7405,
|
|
"mean_token_accuracy": 0.22467319071292877,
|
|
"num_tokens": 39867058.0,
|
|
"step": 21665
|
|
},
|
|
{
|
|
"entropy": 5.242200422286987,
|
|
"epoch": 1.810056799198129,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004671761396046916,
|
|
"loss": 4.7324,
|
|
"mean_token_accuracy": 0.22897920310497283,
|
|
"num_tokens": 39876166.0,
|
|
"step": 21670
|
|
},
|
|
{
|
|
"entropy": 5.356535768508911,
|
|
"epoch": 1.810474440360842,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004671606550853729,
|
|
"loss": 4.868,
|
|
"mean_token_accuracy": 0.21901453286409378,
|
|
"num_tokens": 39885980.0,
|
|
"step": 21675
|
|
},
|
|
{
|
|
"entropy": 5.375189256668091,
|
|
"epoch": 1.810892081523555,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00046714516720205057,
|
|
"loss": 4.8994,
|
|
"mean_token_accuracy": 0.22049206048250197,
|
|
"num_tokens": 39895263.0,
|
|
"step": 21680
|
|
},
|
|
{
|
|
"entropy": 5.356708765029907,
|
|
"epoch": 1.811309722686268,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00046712967595499585,
|
|
"loss": 4.914,
|
|
"mean_token_accuracy": 0.21474099159240723,
|
|
"num_tokens": 39904052.0,
|
|
"step": 21685
|
|
},
|
|
{
|
|
"entropy": 5.221656751632691,
|
|
"epoch": 1.811727363848981,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004671141813444798,
|
|
"loss": 4.7844,
|
|
"mean_token_accuracy": 0.22429056763648986,
|
|
"num_tokens": 39913411.0,
|
|
"step": 21690
|
|
},
|
|
{
|
|
"entropy": 5.260197019577026,
|
|
"epoch": 1.8121450050116938,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00046709868337077386,
|
|
"loss": 4.7191,
|
|
"mean_token_accuracy": 0.22961765229701997,
|
|
"num_tokens": 39922262.0,
|
|
"step": 21695
|
|
},
|
|
{
|
|
"entropy": 5.392533779144287,
|
|
"epoch": 1.812562646174407,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004670831820341491,
|
|
"loss": 4.942,
|
|
"mean_token_accuracy": 0.21122497022151948,
|
|
"num_tokens": 39932067.0,
|
|
"step": 21700
|
|
},
|
|
{
|
|
"entropy": 5.429979658126831,
|
|
"epoch": 1.81298028733712,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00046706767733487714,
|
|
"loss": 4.8785,
|
|
"mean_token_accuracy": 0.2176689624786377,
|
|
"num_tokens": 39941565.0,
|
|
"step": 21705
|
|
},
|
|
{
|
|
"entropy": 5.348182153701782,
|
|
"epoch": 1.813397928499833,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00046705216927322925,
|
|
"loss": 4.6925,
|
|
"mean_token_accuracy": 0.22942376881837845,
|
|
"num_tokens": 39950569.0,
|
|
"step": 21710
|
|
},
|
|
{
|
|
"entropy": 5.2761250019073485,
|
|
"epoch": 1.813815569662546,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000467036657849477,
|
|
"loss": 4.7416,
|
|
"mean_token_accuracy": 0.2257537618279457,
|
|
"num_tokens": 39959341.0,
|
|
"step": 21715
|
|
},
|
|
{
|
|
"entropy": 5.375205755233765,
|
|
"epoch": 1.8142332108252588,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004670211430638919,
|
|
"loss": 4.8994,
|
|
"mean_token_accuracy": 0.21849223375320434,
|
|
"num_tokens": 39968503.0,
|
|
"step": 21720
|
|
},
|
|
{
|
|
"entropy": 5.391932010650635,
|
|
"epoch": 1.814650851987972,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004670056249167455,
|
|
"loss": 4.8954,
|
|
"mean_token_accuracy": 0.2096862807869911,
|
|
"num_tokens": 39977717.0,
|
|
"step": 21725
|
|
},
|
|
{
|
|
"entropy": 5.294199275970459,
|
|
"epoch": 1.8150684931506849,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004669901034083096,
|
|
"loss": 4.7644,
|
|
"mean_token_accuracy": 0.22038497775793076,
|
|
"num_tokens": 39986066.0,
|
|
"step": 21730
|
|
},
|
|
{
|
|
"entropy": 5.416661357879638,
|
|
"epoch": 1.815486134313398,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00046697457853885576,
|
|
"loss": 4.885,
|
|
"mean_token_accuracy": 0.2141144320368767,
|
|
"num_tokens": 39995067.0,
|
|
"step": 21735
|
|
},
|
|
{
|
|
"entropy": 5.329222869873047,
|
|
"epoch": 1.815903775476111,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004669590503086559,
|
|
"loss": 4.8203,
|
|
"mean_token_accuracy": 0.2220846176147461,
|
|
"num_tokens": 40005102.0,
|
|
"step": 21740
|
|
},
|
|
{
|
|
"entropy": 5.357539415359497,
|
|
"epoch": 1.816321416638824,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00046694351871798175,
|
|
"loss": 4.7453,
|
|
"mean_token_accuracy": 0.2253850907087326,
|
|
"num_tokens": 40013475.0,
|
|
"step": 21745
|
|
},
|
|
{
|
|
"entropy": 5.37548713684082,
|
|
"epoch": 1.816739057801537,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00046692798376710533,
|
|
"loss": 4.8379,
|
|
"mean_token_accuracy": 0.2207666128873825,
|
|
"num_tokens": 40023083.0,
|
|
"step": 21750
|
|
},
|
|
{
|
|
"entropy": 5.223190355300903,
|
|
"epoch": 1.8171566989642498,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00046691244545629847,
|
|
"loss": 4.7227,
|
|
"mean_token_accuracy": 0.2353261485695839,
|
|
"num_tokens": 40031462.0,
|
|
"step": 21755
|
|
},
|
|
{
|
|
"entropy": 5.3923399448394775,
|
|
"epoch": 1.817574340126963,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004668969037858333,
|
|
"loss": 4.8299,
|
|
"mean_token_accuracy": 0.2143377974629402,
|
|
"num_tokens": 40040037.0,
|
|
"step": 21760
|
|
},
|
|
{
|
|
"entropy": 5.382817602157592,
|
|
"epoch": 1.8179919812896759,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00046688135875598184,
|
|
"loss": 4.8041,
|
|
"mean_token_accuracy": 0.22034834921360016,
|
|
"num_tokens": 40049668.0,
|
|
"step": 21765
|
|
},
|
|
{
|
|
"entropy": 5.334941101074219,
|
|
"epoch": 1.818409622452389,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004668658103670161,
|
|
"loss": 4.8138,
|
|
"mean_token_accuracy": 0.21848637461662293,
|
|
"num_tokens": 40058080.0,
|
|
"step": 21770
|
|
},
|
|
{
|
|
"entropy": 5.40368881225586,
|
|
"epoch": 1.818827263615102,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00046685025861920856,
|
|
"loss": 4.8744,
|
|
"mean_token_accuracy": 0.22180753350257873,
|
|
"num_tokens": 40067411.0,
|
|
"step": 21775
|
|
},
|
|
{
|
|
"entropy": 5.326650953292846,
|
|
"epoch": 1.8192449047778148,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004668347035128312,
|
|
"loss": 4.7773,
|
|
"mean_token_accuracy": 0.21801136881113053,
|
|
"num_tokens": 40076481.0,
|
|
"step": 21780
|
|
},
|
|
{
|
|
"entropy": 5.393164157867432,
|
|
"epoch": 1.819662545940528,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00046681914504815653,
|
|
"loss": 4.9294,
|
|
"mean_token_accuracy": 0.21548933833837508,
|
|
"num_tokens": 40084981.0,
|
|
"step": 21785
|
|
},
|
|
{
|
|
"entropy": 5.37808313369751,
|
|
"epoch": 1.8200801871032408,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00046680358322545687,
|
|
"loss": 4.8057,
|
|
"mean_token_accuracy": 0.22330607622861862,
|
|
"num_tokens": 40094219.0,
|
|
"step": 21790
|
|
},
|
|
{
|
|
"entropy": 5.327797603607178,
|
|
"epoch": 1.8204978282659539,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004667880180450045,
|
|
"loss": 4.8133,
|
|
"mean_token_accuracy": 0.22179829329252243,
|
|
"num_tokens": 40103833.0,
|
|
"step": 21795
|
|
},
|
|
{
|
|
"entropy": 5.351362705230713,
|
|
"epoch": 1.8209154694286669,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00046677244950707204,
|
|
"loss": 4.8727,
|
|
"mean_token_accuracy": 0.2162658229470253,
|
|
"num_tokens": 40112906.0,
|
|
"step": 21800
|
|
},
|
|
{
|
|
"entropy": 5.368002939224243,
|
|
"epoch": 1.82133311059138,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004667568776119321,
|
|
"loss": 4.8459,
|
|
"mean_token_accuracy": 0.21579502075910567,
|
|
"num_tokens": 40122080.0,
|
|
"step": 21805
|
|
},
|
|
{
|
|
"entropy": 5.346719598770141,
|
|
"epoch": 1.821750751754093,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004667413023598571,
|
|
"loss": 4.8111,
|
|
"mean_token_accuracy": 0.2245814770460129,
|
|
"num_tokens": 40131765.0,
|
|
"step": 21810
|
|
},
|
|
{
|
|
"entropy": 5.302046012878418,
|
|
"epoch": 1.8221683929168058,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004667257237511199,
|
|
"loss": 4.7471,
|
|
"mean_token_accuracy": 0.22276365458965303,
|
|
"num_tokens": 40141084.0,
|
|
"step": 21815
|
|
},
|
|
{
|
|
"entropy": 5.302569389343262,
|
|
"epoch": 1.822586034079519,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00046671014178599295,
|
|
"loss": 4.7707,
|
|
"mean_token_accuracy": 0.22129413038492202,
|
|
"num_tokens": 40149845.0,
|
|
"step": 21820
|
|
},
|
|
{
|
|
"entropy": 5.348519992828369,
|
|
"epoch": 1.8230036752422318,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00046669455646474936,
|
|
"loss": 4.7993,
|
|
"mean_token_accuracy": 0.21738316267728805,
|
|
"num_tokens": 40159173.0,
|
|
"step": 21825
|
|
},
|
|
{
|
|
"entropy": 5.3662522315979,
|
|
"epoch": 1.8234213164049449,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00046667896778766185,
|
|
"loss": 4.8718,
|
|
"mean_token_accuracy": 0.22247455418109893,
|
|
"num_tokens": 40168949.0,
|
|
"step": 21830
|
|
},
|
|
{
|
|
"entropy": 5.337760496139526,
|
|
"epoch": 1.823838957567658,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00046666337575500315,
|
|
"loss": 4.7578,
|
|
"mean_token_accuracy": 0.21920025944709778,
|
|
"num_tokens": 40178886.0,
|
|
"step": 21835
|
|
},
|
|
{
|
|
"entropy": 5.338619518280029,
|
|
"epoch": 1.8242565987303707,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004666477803670464,
|
|
"loss": 4.7662,
|
|
"mean_token_accuracy": 0.22290413677692414,
|
|
"num_tokens": 40187562.0,
|
|
"step": 21840
|
|
},
|
|
{
|
|
"entropy": 5.336164903640747,
|
|
"epoch": 1.824674239893084,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004666321816240646,
|
|
"loss": 4.8046,
|
|
"mean_token_accuracy": 0.22985025644302368,
|
|
"num_tokens": 40196910.0,
|
|
"step": 21845
|
|
},
|
|
{
|
|
"entropy": 5.33599100112915,
|
|
"epoch": 1.8250918810557968,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004666165795263308,
|
|
"loss": 4.8326,
|
|
"mean_token_accuracy": 0.22346067279577256,
|
|
"num_tokens": 40206238.0,
|
|
"step": 21850
|
|
},
|
|
{
|
|
"entropy": 5.344395589828491,
|
|
"epoch": 1.8255095222185098,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004666009740741181,
|
|
"loss": 4.802,
|
|
"mean_token_accuracy": 0.22809671610593796,
|
|
"num_tokens": 40215191.0,
|
|
"step": 21855
|
|
},
|
|
{
|
|
"entropy": 5.323668718338013,
|
|
"epoch": 1.8259271633812229,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00046658536526769976,
|
|
"loss": 4.8228,
|
|
"mean_token_accuracy": 0.22177471965551376,
|
|
"num_tokens": 40224408.0,
|
|
"step": 21860
|
|
},
|
|
{
|
|
"entropy": 5.34239239692688,
|
|
"epoch": 1.8263448045439359,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004665697531073489,
|
|
"loss": 4.7995,
|
|
"mean_token_accuracy": 0.22176473289728166,
|
|
"num_tokens": 40233733.0,
|
|
"step": 21865
|
|
},
|
|
{
|
|
"entropy": 5.284794473648072,
|
|
"epoch": 1.826762445706649,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000466554137593339,
|
|
"loss": 4.7625,
|
|
"mean_token_accuracy": 0.22982285171747208,
|
|
"num_tokens": 40242897.0,
|
|
"step": 21870
|
|
},
|
|
{
|
|
"entropy": 5.334289169311523,
|
|
"epoch": 1.8271800868693617,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00046653851872594334,
|
|
"loss": 4.8334,
|
|
"mean_token_accuracy": 0.22619782239198685,
|
|
"num_tokens": 40251936.0,
|
|
"step": 21875
|
|
},
|
|
{
|
|
"entropy": 5.402001810073853,
|
|
"epoch": 1.827597728032075,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004665228965054353,
|
|
"loss": 4.8489,
|
|
"mean_token_accuracy": 0.22359500527381898,
|
|
"num_tokens": 40260295.0,
|
|
"step": 21880
|
|
},
|
|
{
|
|
"entropy": 5.384753465652466,
|
|
"epoch": 1.8280153691947878,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004665072709320885,
|
|
"loss": 4.8106,
|
|
"mean_token_accuracy": 0.2144942283630371,
|
|
"num_tokens": 40270058.0,
|
|
"step": 21885
|
|
},
|
|
{
|
|
"entropy": 5.2893908500671385,
|
|
"epoch": 1.8284330103575008,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00046649164200617633,
|
|
"loss": 4.6782,
|
|
"mean_token_accuracy": 0.23674820214509965,
|
|
"num_tokens": 40278599.0,
|
|
"step": 21890
|
|
},
|
|
{
|
|
"entropy": 5.377574682235718,
|
|
"epoch": 1.8288506515202139,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004664760097279725,
|
|
"loss": 4.833,
|
|
"mean_token_accuracy": 0.21682808995246888,
|
|
"num_tokens": 40288591.0,
|
|
"step": 21895
|
|
},
|
|
{
|
|
"entropy": 5.354391193389892,
|
|
"epoch": 1.8292682926829267,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004664603740977506,
|
|
"loss": 4.7967,
|
|
"mean_token_accuracy": 0.2302589610219002,
|
|
"num_tokens": 40297359.0,
|
|
"step": 21900
|
|
},
|
|
{
|
|
"entropy": 5.388369703292847,
|
|
"epoch": 1.82968593384564,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00046644473511578443,
|
|
"loss": 4.9156,
|
|
"mean_token_accuracy": 0.21314858347177507,
|
|
"num_tokens": 40307130.0,
|
|
"step": 21905
|
|
},
|
|
{
|
|
"entropy": 5.378526258468628,
|
|
"epoch": 1.8301035750083527,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00046642909278234775,
|
|
"loss": 4.7731,
|
|
"mean_token_accuracy": 0.2292945936322212,
|
|
"num_tokens": 40316065.0,
|
|
"step": 21910
|
|
},
|
|
{
|
|
"entropy": 5.3242395401000975,
|
|
"epoch": 1.8305212161710658,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004664134470977143,
|
|
"loss": 4.8301,
|
|
"mean_token_accuracy": 0.21906150579452516,
|
|
"num_tokens": 40325808.0,
|
|
"step": 21915
|
|
},
|
|
{
|
|
"entropy": 5.350230360031128,
|
|
"epoch": 1.8309388573337788,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00046639779806215815,
|
|
"loss": 4.8042,
|
|
"mean_token_accuracy": 0.22827284932136535,
|
|
"num_tokens": 40334632.0,
|
|
"step": 21920
|
|
},
|
|
{
|
|
"entropy": 5.333172082901001,
|
|
"epoch": 1.8313564984964918,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004663821456759532,
|
|
"loss": 4.8229,
|
|
"mean_token_accuracy": 0.21555038243532182,
|
|
"num_tokens": 40343803.0,
|
|
"step": 21925
|
|
},
|
|
{
|
|
"entropy": 5.332218742370605,
|
|
"epoch": 1.8317741396592049,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00046636648993937326,
|
|
"loss": 4.7713,
|
|
"mean_token_accuracy": 0.22546025216579438,
|
|
"num_tokens": 40352743.0,
|
|
"step": 21930
|
|
},
|
|
{
|
|
"entropy": 5.368146705627441,
|
|
"epoch": 1.8321917808219177,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004663508308526927,
|
|
"loss": 4.8478,
|
|
"mean_token_accuracy": 0.21994030922651292,
|
|
"num_tokens": 40361421.0,
|
|
"step": 21935
|
|
},
|
|
{
|
|
"entropy": 5.349822950363159,
|
|
"epoch": 1.832609421984631,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00046633516841618547,
|
|
"loss": 4.7888,
|
|
"mean_token_accuracy": 0.22265269607305527,
|
|
"num_tokens": 40369860.0,
|
|
"step": 21940
|
|
},
|
|
{
|
|
"entropy": 5.403954648971558,
|
|
"epoch": 1.8330270631473438,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004663195026301258,
|
|
"loss": 4.8395,
|
|
"mean_token_accuracy": 0.21964534521102905,
|
|
"num_tokens": 40379095.0,
|
|
"step": 21945
|
|
},
|
|
{
|
|
"entropy": 5.375717544555664,
|
|
"epoch": 1.8334447043100568,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004663038334947879,
|
|
"loss": 4.8201,
|
|
"mean_token_accuracy": 0.22165672183036805,
|
|
"num_tokens": 40388373.0,
|
|
"step": 21950
|
|
},
|
|
{
|
|
"entropy": 5.354570579528809,
|
|
"epoch": 1.8338623454727698,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004662881610104461,
|
|
"loss": 4.8281,
|
|
"mean_token_accuracy": 0.21851465106010437,
|
|
"num_tokens": 40398158.0,
|
|
"step": 21955
|
|
},
|
|
{
|
|
"entropy": 5.387217617034912,
|
|
"epoch": 1.8342799866354826,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000466272485177375,
|
|
"loss": 4.902,
|
|
"mean_token_accuracy": 0.20835647583007813,
|
|
"num_tokens": 40407540.0,
|
|
"step": 21960
|
|
},
|
|
{
|
|
"entropy": 5.39547324180603,
|
|
"epoch": 1.834697627798196,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00046625680599584864,
|
|
"loss": 4.9723,
|
|
"mean_token_accuracy": 0.21562197655439377,
|
|
"num_tokens": 40417445.0,
|
|
"step": 21965
|
|
},
|
|
{
|
|
"entropy": 5.413169956207275,
|
|
"epoch": 1.8351152689609087,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00046624112346614166,
|
|
"loss": 4.8702,
|
|
"mean_token_accuracy": 0.21048700511455537,
|
|
"num_tokens": 40426873.0,
|
|
"step": 21970
|
|
},
|
|
{
|
|
"entropy": 5.401558446884155,
|
|
"epoch": 1.8355329101236217,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004662254375885287,
|
|
"loss": 4.8298,
|
|
"mean_token_accuracy": 0.21870196014642715,
|
|
"num_tokens": 40436072.0,
|
|
"step": 21975
|
|
},
|
|
{
|
|
"entropy": 5.347485828399658,
|
|
"epoch": 1.8359505512863348,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00046620974836328425,
|
|
"loss": 4.813,
|
|
"mean_token_accuracy": 0.2245323672890663,
|
|
"num_tokens": 40445599.0,
|
|
"step": 21980
|
|
},
|
|
{
|
|
"entropy": 5.361623764038086,
|
|
"epoch": 1.8363681924490478,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004661940557906829,
|
|
"loss": 4.8953,
|
|
"mean_token_accuracy": 0.21709197610616685,
|
|
"num_tokens": 40454982.0,
|
|
"step": 21985
|
|
},
|
|
{
|
|
"entropy": 5.263458967208862,
|
|
"epoch": 1.8367858336117608,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00046617835987099957,
|
|
"loss": 4.704,
|
|
"mean_token_accuracy": 0.23027122914791107,
|
|
"num_tokens": 40463794.0,
|
|
"step": 21990
|
|
},
|
|
{
|
|
"entropy": 5.301512336730957,
|
|
"epoch": 1.8372034747744737,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000466162660604509,
|
|
"loss": 4.7873,
|
|
"mean_token_accuracy": 0.22709018141031265,
|
|
"num_tokens": 40473139.0,
|
|
"step": 21995
|
|
},
|
|
{
|
|
"entropy": 5.332462120056152,
|
|
"epoch": 1.837621115937187,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00046614695799148575,
|
|
"loss": 4.7999,
|
|
"mean_token_accuracy": 0.22190213650465013,
|
|
"num_tokens": 40481942.0,
|
|
"step": 22000
|
|
},
|
|
{
|
|
"entropy": 5.365628576278686,
|
|
"epoch": 1.8380387570998997,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00046613125203220506,
|
|
"loss": 4.7746,
|
|
"mean_token_accuracy": 0.2271994173526764,
|
|
"num_tokens": 40490428.0,
|
|
"step": 22005
|
|
},
|
|
{
|
|
"entropy": 5.394579601287842,
|
|
"epoch": 1.8384563982626128,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00046611554272694175,
|
|
"loss": 4.8971,
|
|
"mean_token_accuracy": 0.21414828449487686,
|
|
"num_tokens": 40500185.0,
|
|
"step": 22010
|
|
},
|
|
{
|
|
"entropy": 5.321792364120483,
|
|
"epoch": 1.8388740394253258,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004660998300759707,
|
|
"loss": 4.8276,
|
|
"mean_token_accuracy": 0.2222628489136696,
|
|
"num_tokens": 40509205.0,
|
|
"step": 22015
|
|
},
|
|
{
|
|
"entropy": 5.319432544708252,
|
|
"epoch": 1.8392916805880386,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00046608411407956726,
|
|
"loss": 4.7515,
|
|
"mean_token_accuracy": 0.2207288295030594,
|
|
"num_tokens": 40518910.0,
|
|
"step": 22020
|
|
},
|
|
{
|
|
"entropy": 5.393040513992309,
|
|
"epoch": 1.8397093217507519,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00046606839473800626,
|
|
"loss": 4.8266,
|
|
"mean_token_accuracy": 0.22562930434942247,
|
|
"num_tokens": 40526988.0,
|
|
"step": 22025
|
|
},
|
|
{
|
|
"entropy": 5.265941905975342,
|
|
"epoch": 1.8401269629134647,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004660526720515631,
|
|
"loss": 4.7499,
|
|
"mean_token_accuracy": 0.2280072256922722,
|
|
"num_tokens": 40536436.0,
|
|
"step": 22030
|
|
},
|
|
{
|
|
"entropy": 5.330783224105835,
|
|
"epoch": 1.8405446040761777,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004660369460205128,
|
|
"loss": 4.8207,
|
|
"mean_token_accuracy": 0.22104761153459548,
|
|
"num_tokens": 40546341.0,
|
|
"step": 22035
|
|
},
|
|
{
|
|
"entropy": 5.444593143463135,
|
|
"epoch": 1.8409622452388907,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00046602121664513104,
|
|
"loss": 4.9445,
|
|
"mean_token_accuracy": 0.218316450715065,
|
|
"num_tokens": 40556915.0,
|
|
"step": 22040
|
|
},
|
|
{
|
|
"entropy": 5.4285553932189945,
|
|
"epoch": 1.8413798864016038,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00046600548392569283,
|
|
"loss": 4.8448,
|
|
"mean_token_accuracy": 0.21484411507844925,
|
|
"num_tokens": 40566881.0,
|
|
"step": 22045
|
|
},
|
|
{
|
|
"entropy": 5.295056247711182,
|
|
"epoch": 1.8417975275643168,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00046598974786247365,
|
|
"loss": 4.7012,
|
|
"mean_token_accuracy": 0.22449757903814316,
|
|
"num_tokens": 40574845.0,
|
|
"step": 22050
|
|
},
|
|
{
|
|
"entropy": 5.256988573074341,
|
|
"epoch": 1.8422151687270296,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004659740084557491,
|
|
"loss": 4.7109,
|
|
"mean_token_accuracy": 0.23417773097753525,
|
|
"num_tokens": 40583274.0,
|
|
"step": 22055
|
|
},
|
|
{
|
|
"entropy": 5.223049640655518,
|
|
"epoch": 1.8426328098897429,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004659582657057947,
|
|
"loss": 4.7155,
|
|
"mean_token_accuracy": 0.2227085590362549,
|
|
"num_tokens": 40592138.0,
|
|
"step": 22060
|
|
},
|
|
{
|
|
"entropy": 5.279693269729615,
|
|
"epoch": 1.8430504510524557,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000465942519612886,
|
|
"loss": 4.7619,
|
|
"mean_token_accuracy": 0.22830045521259307,
|
|
"num_tokens": 40600453.0,
|
|
"step": 22065
|
|
},
|
|
{
|
|
"entropy": 5.3222919464111325,
|
|
"epoch": 1.8434680922151687,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004659267701772986,
|
|
"loss": 4.8362,
|
|
"mean_token_accuracy": 0.2170238584280014,
|
|
"num_tokens": 40610511.0,
|
|
"step": 22070
|
|
},
|
|
{
|
|
"entropy": 5.307769107818603,
|
|
"epoch": 1.8438857333778818,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004659110173993083,
|
|
"loss": 4.7272,
|
|
"mean_token_accuracy": 0.23194390237331391,
|
|
"num_tokens": 40619819.0,
|
|
"step": 22075
|
|
},
|
|
{
|
|
"entropy": 5.138915920257569,
|
|
"epoch": 1.8443033745405946,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004658952612791908,
|
|
"loss": 4.6139,
|
|
"mean_token_accuracy": 0.2373156487941742,
|
|
"num_tokens": 40628400.0,
|
|
"step": 22080
|
|
},
|
|
{
|
|
"entropy": 5.234152603149414,
|
|
"epoch": 1.8447210157033078,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000465879501817222,
|
|
"loss": 4.7558,
|
|
"mean_token_accuracy": 0.22537985891103746,
|
|
"num_tokens": 40637396.0,
|
|
"step": 22085
|
|
},
|
|
{
|
|
"entropy": 5.404343938827514,
|
|
"epoch": 1.8451386568660206,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00046586373901367774,
|
|
"loss": 4.9592,
|
|
"mean_token_accuracy": 0.21585862189531327,
|
|
"num_tokens": 40645902.0,
|
|
"step": 22090
|
|
},
|
|
{
|
|
"entropy": 5.434461450576782,
|
|
"epoch": 1.8455562980287337,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000465847972868834,
|
|
"loss": 4.8691,
|
|
"mean_token_accuracy": 0.22183208167552948,
|
|
"num_tokens": 40656382.0,
|
|
"step": 22095
|
|
},
|
|
{
|
|
"entropy": 5.36854100227356,
|
|
"epoch": 1.8459739391914467,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004658322033829668,
|
|
"loss": 4.8384,
|
|
"mean_token_accuracy": 0.2166881427168846,
|
|
"num_tokens": 40665471.0,
|
|
"step": 22100
|
|
},
|
|
{
|
|
"entropy": 5.297481107711792,
|
|
"epoch": 1.8463915803541597,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00046581643055635215,
|
|
"loss": 4.7942,
|
|
"mean_token_accuracy": 0.22546106576919556,
|
|
"num_tokens": 40674668.0,
|
|
"step": 22105
|
|
},
|
|
{
|
|
"entropy": 5.308639287948608,
|
|
"epoch": 1.8468092215168728,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00046580065438926624,
|
|
"loss": 4.7476,
|
|
"mean_token_accuracy": 0.226073557138443,
|
|
"num_tokens": 40683779.0,
|
|
"step": 22110
|
|
},
|
|
{
|
|
"entropy": 5.329878044128418,
|
|
"epoch": 1.8472268626795856,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004657848748819851,
|
|
"loss": 4.8443,
|
|
"mean_token_accuracy": 0.2154697448015213,
|
|
"num_tokens": 40692412.0,
|
|
"step": 22115
|
|
},
|
|
{
|
|
"entropy": 5.2419593334198,
|
|
"epoch": 1.8476445038422988,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00046576909203478517,
|
|
"loss": 4.6593,
|
|
"mean_token_accuracy": 0.23608656227588654,
|
|
"num_tokens": 40701652.0,
|
|
"step": 22120
|
|
},
|
|
{
|
|
"entropy": 5.434550714492798,
|
|
"epoch": 1.8480621450050116,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00046575330584794263,
|
|
"loss": 4.9973,
|
|
"mean_token_accuracy": 0.2087620511651039,
|
|
"num_tokens": 40711149.0,
|
|
"step": 22125
|
|
},
|
|
{
|
|
"entropy": 5.365161037445068,
|
|
"epoch": 1.8484797861677247,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004657375163217338,
|
|
"loss": 4.8239,
|
|
"mean_token_accuracy": 0.22593267261981964,
|
|
"num_tokens": 40721014.0,
|
|
"step": 22130
|
|
},
|
|
{
|
|
"entropy": 5.34323787689209,
|
|
"epoch": 1.8488974273304377,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00046572172345643527,
|
|
"loss": 4.8179,
|
|
"mean_token_accuracy": 0.22075466960668563,
|
|
"num_tokens": 40730645.0,
|
|
"step": 22135
|
|
},
|
|
{
|
|
"entropy": 5.2695249080657955,
|
|
"epoch": 1.8493150684931505,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00046570592725232333,
|
|
"loss": 4.7073,
|
|
"mean_token_accuracy": 0.22934768050909043,
|
|
"num_tokens": 40739620.0,
|
|
"step": 22140
|
|
},
|
|
{
|
|
"entropy": 5.259941530227661,
|
|
"epoch": 1.8497327096558638,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004656901277096746,
|
|
"loss": 4.768,
|
|
"mean_token_accuracy": 0.22510144114494324,
|
|
"num_tokens": 40748840.0,
|
|
"step": 22145
|
|
},
|
|
{
|
|
"entropy": 5.414131546020508,
|
|
"epoch": 1.8501503508185766,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004656743248287656,
|
|
"loss": 4.9421,
|
|
"mean_token_accuracy": 0.21063391119241714,
|
|
"num_tokens": 40757798.0,
|
|
"step": 22150
|
|
},
|
|
{
|
|
"entropy": 5.327619171142578,
|
|
"epoch": 1.8505679919812896,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004656585186098731,
|
|
"loss": 4.7402,
|
|
"mean_token_accuracy": 0.22480131536722184,
|
|
"num_tokens": 40766853.0,
|
|
"step": 22155
|
|
},
|
|
{
|
|
"entropy": 5.299325609207154,
|
|
"epoch": 1.8509856331440027,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004656427090532737,
|
|
"loss": 4.747,
|
|
"mean_token_accuracy": 0.23351173102855682,
|
|
"num_tokens": 40775232.0,
|
|
"step": 22160
|
|
},
|
|
{
|
|
"entropy": 5.392861366271973,
|
|
"epoch": 1.8514032743067157,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00046562689615924427,
|
|
"loss": 4.8001,
|
|
"mean_token_accuracy": 0.2261783629655838,
|
|
"num_tokens": 40783759.0,
|
|
"step": 22165
|
|
},
|
|
{
|
|
"entropy": 5.432003688812256,
|
|
"epoch": 1.8518209154694287,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004656110799280615,
|
|
"loss": 4.8499,
|
|
"mean_token_accuracy": 0.21807921677827835,
|
|
"num_tokens": 40792819.0,
|
|
"step": 22170
|
|
},
|
|
{
|
|
"entropy": 5.293496799468994,
|
|
"epoch": 1.8522385566321415,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00046559526036000235,
|
|
"loss": 4.7407,
|
|
"mean_token_accuracy": 0.2296771302819252,
|
|
"num_tokens": 40801956.0,
|
|
"step": 22175
|
|
},
|
|
{
|
|
"entropy": 5.354808282852173,
|
|
"epoch": 1.8526561977948548,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00046557943745534374,
|
|
"loss": 4.8217,
|
|
"mean_token_accuracy": 0.2201542764902115,
|
|
"num_tokens": 40812439.0,
|
|
"step": 22180
|
|
},
|
|
{
|
|
"entropy": 5.401402807235717,
|
|
"epoch": 1.8530738389575676,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00046556361121436265,
|
|
"loss": 4.9043,
|
|
"mean_token_accuracy": 0.21302145719528198,
|
|
"num_tokens": 40822712.0,
|
|
"step": 22185
|
|
},
|
|
{
|
|
"entropy": 5.299106168746948,
|
|
"epoch": 1.8534914801202806,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00046554778163733626,
|
|
"loss": 4.7673,
|
|
"mean_token_accuracy": 0.21516881585121156,
|
|
"num_tokens": 40831242.0,
|
|
"step": 22190
|
|
},
|
|
{
|
|
"entropy": 5.256429290771484,
|
|
"epoch": 1.8539091212829937,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00046553194872454146,
|
|
"loss": 4.7212,
|
|
"mean_token_accuracy": 0.2332335591316223,
|
|
"num_tokens": 40839754.0,
|
|
"step": 22195
|
|
},
|
|
{
|
|
"entropy": 5.354557085037231,
|
|
"epoch": 1.8543267624457065,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00046551611247625565,
|
|
"loss": 4.8627,
|
|
"mean_token_accuracy": 0.21996336281299592,
|
|
"num_tokens": 40848925.0,
|
|
"step": 22200
|
|
},
|
|
{
|
|
"entropy": 5.349648761749267,
|
|
"epoch": 1.8547444036084197,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004655002728927559,
|
|
"loss": 4.8147,
|
|
"mean_token_accuracy": 0.22199276685714722,
|
|
"num_tokens": 40857784.0,
|
|
"step": 22205
|
|
},
|
|
{
|
|
"entropy": 5.243054628372192,
|
|
"epoch": 1.8551620447711326,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00046548442997431966,
|
|
"loss": 4.6334,
|
|
"mean_token_accuracy": 0.24317637383937835,
|
|
"num_tokens": 40866607.0,
|
|
"step": 22210
|
|
},
|
|
{
|
|
"entropy": 5.427901077270508,
|
|
"epoch": 1.8555796859338456,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004654685837212241,
|
|
"loss": 4.8381,
|
|
"mean_token_accuracy": 0.2236845538020134,
|
|
"num_tokens": 40876730.0,
|
|
"step": 22215
|
|
},
|
|
{
|
|
"entropy": 5.310292053222656,
|
|
"epoch": 1.8559973270965586,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004654527341337468,
|
|
"loss": 4.7895,
|
|
"mean_token_accuracy": 0.21514538377523423,
|
|
"num_tokens": 40886482.0,
|
|
"step": 22220
|
|
},
|
|
{
|
|
"entropy": 5.345565509796143,
|
|
"epoch": 1.8564149682592717,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00046543688121216504,
|
|
"loss": 4.8738,
|
|
"mean_token_accuracy": 0.2223155215382576,
|
|
"num_tokens": 40896704.0,
|
|
"step": 22225
|
|
},
|
|
{
|
|
"entropy": 5.328790712356567,
|
|
"epoch": 1.8568326094219847,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004654210249567565,
|
|
"loss": 4.79,
|
|
"mean_token_accuracy": 0.2231317177414894,
|
|
"num_tokens": 40906665.0,
|
|
"step": 22230
|
|
},
|
|
{
|
|
"entropy": 5.344720554351807,
|
|
"epoch": 1.8572502505846975,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004654051653677988,
|
|
"loss": 4.8228,
|
|
"mean_token_accuracy": 0.2211010053753853,
|
|
"num_tokens": 40915838.0,
|
|
"step": 22235
|
|
},
|
|
{
|
|
"entropy": 5.268266868591309,
|
|
"epoch": 1.8576678917474108,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00046538930244556927,
|
|
"loss": 4.7626,
|
|
"mean_token_accuracy": 0.21904680430889129,
|
|
"num_tokens": 40924571.0,
|
|
"step": 22240
|
|
},
|
|
{
|
|
"entropy": 5.309596586227417,
|
|
"epoch": 1.8580855329101236,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00046537343619034593,
|
|
"loss": 4.7665,
|
|
"mean_token_accuracy": 0.22656640708446502,
|
|
"num_tokens": 40934421.0,
|
|
"step": 22245
|
|
},
|
|
{
|
|
"entropy": 5.329681921005249,
|
|
"epoch": 1.8585031740728366,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00046535756660240644,
|
|
"loss": 4.6473,
|
|
"mean_token_accuracy": 0.238775135576725,
|
|
"num_tokens": 40943090.0,
|
|
"step": 22250
|
|
},
|
|
{
|
|
"entropy": 5.353797531127929,
|
|
"epoch": 1.8589208152355496,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004653416936820287,
|
|
"loss": 4.824,
|
|
"mean_token_accuracy": 0.22178999185562134,
|
|
"num_tokens": 40952568.0,
|
|
"step": 22255
|
|
},
|
|
{
|
|
"entropy": 5.250139856338501,
|
|
"epoch": 1.8593384563982625,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004653258174294904,
|
|
"loss": 4.7979,
|
|
"mean_token_accuracy": 0.22627076953649522,
|
|
"num_tokens": 40961122.0,
|
|
"step": 22260
|
|
},
|
|
{
|
|
"entropy": 5.324255084991455,
|
|
"epoch": 1.8597560975609757,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004653099378450696,
|
|
"loss": 4.8329,
|
|
"mean_token_accuracy": 0.2092278391122818,
|
|
"num_tokens": 40971117.0,
|
|
"step": 22265
|
|
},
|
|
{
|
|
"entropy": 5.329768943786621,
|
|
"epoch": 1.8601737387236885,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00046529405492904427,
|
|
"loss": 4.8073,
|
|
"mean_token_accuracy": 0.2229543522000313,
|
|
"num_tokens": 40981151.0,
|
|
"step": 22270
|
|
},
|
|
{
|
|
"entropy": 5.27516918182373,
|
|
"epoch": 1.8605913798864016,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004652781686816925,
|
|
"loss": 4.7248,
|
|
"mean_token_accuracy": 0.22470666766166686,
|
|
"num_tokens": 40990481.0,
|
|
"step": 22275
|
|
},
|
|
{
|
|
"entropy": 5.293833303451538,
|
|
"epoch": 1.8610090210491146,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004652622791032922,
|
|
"loss": 4.7534,
|
|
"mean_token_accuracy": 0.22445281594991684,
|
|
"num_tokens": 40999360.0,
|
|
"step": 22280
|
|
},
|
|
{
|
|
"entropy": 5.364050006866455,
|
|
"epoch": 1.8614266622118276,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00046524638619412187,
|
|
"loss": 4.8982,
|
|
"mean_token_accuracy": 0.21175900250673294,
|
|
"num_tokens": 41009342.0,
|
|
"step": 22285
|
|
},
|
|
{
|
|
"entropy": 5.401388120651245,
|
|
"epoch": 1.8618443033745407,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00046523048995445945,
|
|
"loss": 4.7454,
|
|
"mean_token_accuracy": 0.2254379704594612,
|
|
"num_tokens": 41018219.0,
|
|
"step": 22290
|
|
},
|
|
{
|
|
"entropy": 5.357127380371094,
|
|
"epoch": 1.8622619445372535,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00046521459038458327,
|
|
"loss": 4.8301,
|
|
"mean_token_accuracy": 0.22134848535060883,
|
|
"num_tokens": 41027339.0,
|
|
"step": 22295
|
|
},
|
|
{
|
|
"entropy": 5.335848712921143,
|
|
"epoch": 1.8626795856999667,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00046519868748477186,
|
|
"loss": 4.8133,
|
|
"mean_token_accuracy": 0.22412330210208892,
|
|
"num_tokens": 41036748.0,
|
|
"step": 22300
|
|
},
|
|
{
|
|
"entropy": 5.276674604415893,
|
|
"epoch": 1.8630972268626795,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00046518278125530336,
|
|
"loss": 4.793,
|
|
"mean_token_accuracy": 0.22660579532384872,
|
|
"num_tokens": 41046064.0,
|
|
"step": 22305
|
|
},
|
|
{
|
|
"entropy": 5.288017511367798,
|
|
"epoch": 1.8635148680253926,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004651668716964564,
|
|
"loss": 4.797,
|
|
"mean_token_accuracy": 0.22585859894752502,
|
|
"num_tokens": 41055784.0,
|
|
"step": 22310
|
|
},
|
|
{
|
|
"entropy": 5.32776255607605,
|
|
"epoch": 1.8639325091881056,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00046515095880850937,
|
|
"loss": 4.7521,
|
|
"mean_token_accuracy": 0.2251617506146431,
|
|
"num_tokens": 41065585.0,
|
|
"step": 22315
|
|
},
|
|
{
|
|
"entropy": 5.267065095901489,
|
|
"epoch": 1.8643501503508184,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00046513504259174104,
|
|
"loss": 4.715,
|
|
"mean_token_accuracy": 0.23972115516662598,
|
|
"num_tokens": 41073531.0,
|
|
"step": 22320
|
|
},
|
|
{
|
|
"entropy": 5.37595567703247,
|
|
"epoch": 1.8647677915135317,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004651191230464299,
|
|
"loss": 4.8604,
|
|
"mean_token_accuracy": 0.21966364681720735,
|
|
"num_tokens": 41082370.0,
|
|
"step": 22325
|
|
},
|
|
{
|
|
"entropy": 5.272560119628906,
|
|
"epoch": 1.8651854326762445,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004651032001728546,
|
|
"loss": 4.7879,
|
|
"mean_token_accuracy": 0.21703141778707505,
|
|
"num_tokens": 41091025.0,
|
|
"step": 22330
|
|
},
|
|
{
|
|
"entropy": 5.37418007850647,
|
|
"epoch": 1.8656030738389575,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004650872739712941,
|
|
"loss": 4.8932,
|
|
"mean_token_accuracy": 0.2127779334783554,
|
|
"num_tokens": 41100846.0,
|
|
"step": 22335
|
|
},
|
|
{
|
|
"entropy": 5.360386562347412,
|
|
"epoch": 1.8660207150016705,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00046507134444202694,
|
|
"loss": 4.747,
|
|
"mean_token_accuracy": 0.22715978026390077,
|
|
"num_tokens": 41109885.0,
|
|
"step": 22340
|
|
},
|
|
{
|
|
"entropy": 5.353245782852173,
|
|
"epoch": 1.8664383561643836,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004650554115853321,
|
|
"loss": 4.7729,
|
|
"mean_token_accuracy": 0.22524820119142533,
|
|
"num_tokens": 41118478.0,
|
|
"step": 22345
|
|
},
|
|
{
|
|
"entropy": 5.285497188568115,
|
|
"epoch": 1.8668559973270966,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00046503947540148857,
|
|
"loss": 4.7055,
|
|
"mean_token_accuracy": 0.2360133334994316,
|
|
"num_tokens": 41127605.0,
|
|
"step": 22350
|
|
},
|
|
{
|
|
"entropy": 5.328681182861328,
|
|
"epoch": 1.8672736384898094,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00046502353589077523,
|
|
"loss": 4.8253,
|
|
"mean_token_accuracy": 0.21895793676376343,
|
|
"num_tokens": 41137850.0,
|
|
"step": 22355
|
|
},
|
|
{
|
|
"entropy": 5.299277687072754,
|
|
"epoch": 1.8676912796525227,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00046500759305347116,
|
|
"loss": 4.8011,
|
|
"mean_token_accuracy": 0.23075661659240723,
|
|
"num_tokens": 41147452.0,
|
|
"step": 22360
|
|
},
|
|
{
|
|
"entropy": 5.309336090087891,
|
|
"epoch": 1.8681089208152355,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004649916468898555,
|
|
"loss": 4.6972,
|
|
"mean_token_accuracy": 0.23314722925424575,
|
|
"num_tokens": 41155946.0,
|
|
"step": 22365
|
|
},
|
|
{
|
|
"entropy": 5.361101675033569,
|
|
"epoch": 1.8685265619779485,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004649756974002073,
|
|
"loss": 4.9489,
|
|
"mean_token_accuracy": 0.21392570734024047,
|
|
"num_tokens": 41165048.0,
|
|
"step": 22370
|
|
},
|
|
{
|
|
"entropy": 5.206260251998901,
|
|
"epoch": 1.8689442031406616,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004649597445848059,
|
|
"loss": 4.6212,
|
|
"mean_token_accuracy": 0.23428664803504945,
|
|
"num_tokens": 41174026.0,
|
|
"step": 22375
|
|
},
|
|
{
|
|
"entropy": 5.400841569900512,
|
|
"epoch": 1.8693618443033744,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004649437884439305,
|
|
"loss": 4.8387,
|
|
"mean_token_accuracy": 0.22603985518217087,
|
|
"num_tokens": 41183190.0,
|
|
"step": 22380
|
|
},
|
|
{
|
|
"entropy": 5.272791385650635,
|
|
"epoch": 1.8697794854660876,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004649278289778604,
|
|
"loss": 4.7512,
|
|
"mean_token_accuracy": 0.22164539098739625,
|
|
"num_tokens": 41192070.0,
|
|
"step": 22385
|
|
},
|
|
{
|
|
"entropy": 5.252186965942383,
|
|
"epoch": 1.8701971266288004,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00046491186618687514,
|
|
"loss": 4.7221,
|
|
"mean_token_accuracy": 0.22753649204969406,
|
|
"num_tokens": 41201166.0,
|
|
"step": 22390
|
|
},
|
|
{
|
|
"entropy": 5.324235820770264,
|
|
"epoch": 1.8706147677915135,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00046489590007125397,
|
|
"loss": 4.7846,
|
|
"mean_token_accuracy": 0.23153267800807953,
|
|
"num_tokens": 41208998.0,
|
|
"step": 22395
|
|
},
|
|
{
|
|
"entropy": 5.3297812938690186,
|
|
"epoch": 1.8710324089542265,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004648799306312766,
|
|
"loss": 4.7222,
|
|
"mean_token_accuracy": 0.2287020802497864,
|
|
"num_tokens": 41218206.0,
|
|
"step": 22400
|
|
},
|
|
{
|
|
"entropy": 5.286796617507934,
|
|
"epoch": 1.8714500501169395,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00046486395786722237,
|
|
"loss": 4.7465,
|
|
"mean_token_accuracy": 0.22531970143318175,
|
|
"num_tokens": 41226345.0,
|
|
"step": 22405
|
|
},
|
|
{
|
|
"entropy": 5.2952649116516115,
|
|
"epoch": 1.8718676912796526,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004648479817793711,
|
|
"loss": 4.8051,
|
|
"mean_token_accuracy": 0.2201614573597908,
|
|
"num_tokens": 41235641.0,
|
|
"step": 22410
|
|
},
|
|
{
|
|
"entropy": 5.365191411972046,
|
|
"epoch": 1.8722853324423654,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004648320023680023,
|
|
"loss": 4.8034,
|
|
"mean_token_accuracy": 0.22077424377202987,
|
|
"num_tokens": 41245308.0,
|
|
"step": 22415
|
|
},
|
|
{
|
|
"entropy": 5.3252270221710205,
|
|
"epoch": 1.8727029736050786,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00046481601963339593,
|
|
"loss": 4.8287,
|
|
"mean_token_accuracy": 0.22704480737447738,
|
|
"num_tokens": 41254030.0,
|
|
"step": 22420
|
|
},
|
|
{
|
|
"entropy": 5.361261320114136,
|
|
"epoch": 1.8731206147677915,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00046480003357583154,
|
|
"loss": 4.8252,
|
|
"mean_token_accuracy": 0.2216312274336815,
|
|
"num_tokens": 41263449.0,
|
|
"step": 22425
|
|
},
|
|
{
|
|
"entropy": 5.413030624389648,
|
|
"epoch": 1.8735382559305045,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004647840441955892,
|
|
"loss": 4.8525,
|
|
"mean_token_accuracy": 0.2227820262312889,
|
|
"num_tokens": 41272379.0,
|
|
"step": 22430
|
|
},
|
|
{
|
|
"entropy": 5.324385118484497,
|
|
"epoch": 1.8739558970932175,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004647680514929486,
|
|
"loss": 4.8378,
|
|
"mean_token_accuracy": 0.2279914289712906,
|
|
"num_tokens": 41281384.0,
|
|
"step": 22435
|
|
},
|
|
{
|
|
"entropy": 5.328950071334839,
|
|
"epoch": 1.8743735382559303,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00046475205546818996,
|
|
"loss": 4.7165,
|
|
"mean_token_accuracy": 0.23348942995071412,
|
|
"num_tokens": 41290662.0,
|
|
"step": 22440
|
|
},
|
|
{
|
|
"entropy": 5.319228935241699,
|
|
"epoch": 1.8747911794186436,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004647360561215931,
|
|
"loss": 4.8083,
|
|
"mean_token_accuracy": 0.2218919187784195,
|
|
"num_tokens": 41300278.0,
|
|
"step": 22445
|
|
},
|
|
{
|
|
"entropy": 5.385045433044434,
|
|
"epoch": 1.8752088205813564,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00046472005345343814,
|
|
"loss": 4.8685,
|
|
"mean_token_accuracy": 0.22036394625902175,
|
|
"num_tokens": 41309456.0,
|
|
"step": 22450
|
|
},
|
|
{
|
|
"entropy": 5.3814514636993405,
|
|
"epoch": 1.8756264617440697,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004647040474640054,
|
|
"loss": 4.8829,
|
|
"mean_token_accuracy": 0.21297987401485444,
|
|
"num_tokens": 41318550.0,
|
|
"step": 22455
|
|
},
|
|
{
|
|
"entropy": 5.359160852432251,
|
|
"epoch": 1.8760441029067825,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004646880381535749,
|
|
"loss": 4.8606,
|
|
"mean_token_accuracy": 0.22659406810998917,
|
|
"num_tokens": 41327867.0,
|
|
"step": 22460
|
|
},
|
|
{
|
|
"entropy": 5.265915441513061,
|
|
"epoch": 1.8764617440694955,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000464672025522427,
|
|
"loss": 4.6994,
|
|
"mean_token_accuracy": 0.23112322241067887,
|
|
"num_tokens": 41337151.0,
|
|
"step": 22465
|
|
},
|
|
{
|
|
"entropy": 5.24415168762207,
|
|
"epoch": 1.8768793852322085,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000464656009570842,
|
|
"loss": 4.6776,
|
|
"mean_token_accuracy": 0.23313038051128387,
|
|
"num_tokens": 41346205.0,
|
|
"step": 22470
|
|
},
|
|
{
|
|
"entropy": 5.352377939224243,
|
|
"epoch": 1.8772970263949214,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004646399902991002,
|
|
"loss": 4.7881,
|
|
"mean_token_accuracy": 0.22154654264450074,
|
|
"num_tokens": 41354288.0,
|
|
"step": 22475
|
|
},
|
|
{
|
|
"entropy": 5.303909873962402,
|
|
"epoch": 1.8777146675576346,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004646239677074821,
|
|
"loss": 4.7812,
|
|
"mean_token_accuracy": 0.22183165550231934,
|
|
"num_tokens": 41363366.0,
|
|
"step": 22480
|
|
},
|
|
{
|
|
"entropy": 5.281915616989136,
|
|
"epoch": 1.8781323087203474,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00046460794179626827,
|
|
"loss": 4.7671,
|
|
"mean_token_accuracy": 0.2269712954759598,
|
|
"num_tokens": 41371778.0,
|
|
"step": 22485
|
|
},
|
|
{
|
|
"entropy": 5.291991233825684,
|
|
"epoch": 1.8785499498830605,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004645919125657391,
|
|
"loss": 4.6936,
|
|
"mean_token_accuracy": 0.2342294692993164,
|
|
"num_tokens": 41380035.0,
|
|
"step": 22490
|
|
},
|
|
{
|
|
"entropy": 5.441553163528442,
|
|
"epoch": 1.8789675910457735,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004645758800161754,
|
|
"loss": 4.918,
|
|
"mean_token_accuracy": 0.21492837220430375,
|
|
"num_tokens": 41389819.0,
|
|
"step": 22495
|
|
},
|
|
{
|
|
"entropy": 5.3709321975708,
|
|
"epoch": 1.8793852322084865,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004645598441478577,
|
|
"loss": 4.8474,
|
|
"mean_token_accuracy": 0.2164835214614868,
|
|
"num_tokens": 41398704.0,
|
|
"step": 22500
|
|
},
|
|
{
|
|
"entropy": 5.350135803222656,
|
|
"epoch": 1.8798028733711996,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00046454380496106665,
|
|
"loss": 4.8352,
|
|
"mean_token_accuracy": 0.22142885029315948,
|
|
"num_tokens": 41406634.0,
|
|
"step": 22505
|
|
},
|
|
{
|
|
"entropy": 5.302137136459351,
|
|
"epoch": 1.8802205145339124,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004645277624560832,
|
|
"loss": 4.8453,
|
|
"mean_token_accuracy": 0.21744461953639985,
|
|
"num_tokens": 41416164.0,
|
|
"step": 22510
|
|
},
|
|
{
|
|
"entropy": 5.354367780685425,
|
|
"epoch": 1.8806381556966256,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00046451171663318815,
|
|
"loss": 4.8683,
|
|
"mean_token_accuracy": 0.22115945518016816,
|
|
"num_tokens": 41426100.0,
|
|
"step": 22515
|
|
},
|
|
{
|
|
"entropy": 5.478769397735595,
|
|
"epoch": 1.8810557968593384,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00046449566749266237,
|
|
"loss": 4.9819,
|
|
"mean_token_accuracy": 0.21315766423940657,
|
|
"num_tokens": 41435901.0,
|
|
"step": 22520
|
|
},
|
|
{
|
|
"entropy": 5.388392972946167,
|
|
"epoch": 1.8814734380220515,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004644796150347868,
|
|
"loss": 4.8154,
|
|
"mean_token_accuracy": 0.2255258947610855,
|
|
"num_tokens": 41444416.0,
|
|
"step": 22525
|
|
},
|
|
{
|
|
"entropy": 5.340445566177368,
|
|
"epoch": 1.8818910791847645,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00046446355925984257,
|
|
"loss": 4.8286,
|
|
"mean_token_accuracy": 0.22064280956983567,
|
|
"num_tokens": 41454477.0,
|
|
"step": 22530
|
|
},
|
|
{
|
|
"entropy": 5.343173837661743,
|
|
"epoch": 1.8823087203474773,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00046444750016811064,
|
|
"loss": 4.8789,
|
|
"mean_token_accuracy": 0.21635618358850478,
|
|
"num_tokens": 41464156.0,
|
|
"step": 22535
|
|
},
|
|
{
|
|
"entropy": 5.423571252822876,
|
|
"epoch": 1.8827263615101906,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004644314377598722,
|
|
"loss": 4.8062,
|
|
"mean_token_accuracy": 0.2285446345806122,
|
|
"num_tokens": 41473236.0,
|
|
"step": 22540
|
|
},
|
|
{
|
|
"entropy": 5.348963975906372,
|
|
"epoch": 1.8831440026729034,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004644153720354084,
|
|
"loss": 4.7995,
|
|
"mean_token_accuracy": 0.22583384811878204,
|
|
"num_tokens": 41482562.0,
|
|
"step": 22545
|
|
},
|
|
{
|
|
"entropy": 5.374019002914428,
|
|
"epoch": 1.8835616438356164,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004643993029950005,
|
|
"loss": 4.794,
|
|
"mean_token_accuracy": 0.2198302999138832,
|
|
"num_tokens": 41490405.0,
|
|
"step": 22550
|
|
},
|
|
{
|
|
"entropy": 5.428464269638061,
|
|
"epoch": 1.8839792849983295,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00046438323063892985,
|
|
"loss": 4.9086,
|
|
"mean_token_accuracy": 0.21354684382677078,
|
|
"num_tokens": 41500188.0,
|
|
"step": 22555
|
|
},
|
|
{
|
|
"entropy": 5.322067785263061,
|
|
"epoch": 1.8843969261610425,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00046436715496747774,
|
|
"loss": 4.8319,
|
|
"mean_token_accuracy": 0.21373640298843383,
|
|
"num_tokens": 41509736.0,
|
|
"step": 22560
|
|
},
|
|
{
|
|
"entropy": 5.298238611221313,
|
|
"epoch": 1.8848145673237555,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004643510759809257,
|
|
"loss": 4.8215,
|
|
"mean_token_accuracy": 0.21805029213428498,
|
|
"num_tokens": 41519795.0,
|
|
"step": 22565
|
|
},
|
|
{
|
|
"entropy": 5.41425518989563,
|
|
"epoch": 1.8852322084864683,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004643349936795551,
|
|
"loss": 4.8413,
|
|
"mean_token_accuracy": 0.21636187583208083,
|
|
"num_tokens": 41529602.0,
|
|
"step": 22570
|
|
},
|
|
{
|
|
"entropy": 5.336691284179688,
|
|
"epoch": 1.8856498496491816,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004643189080636475,
|
|
"loss": 4.8457,
|
|
"mean_token_accuracy": 0.21988297551870345,
|
|
"num_tokens": 41538850.0,
|
|
"step": 22575
|
|
},
|
|
{
|
|
"entropy": 5.297491836547851,
|
|
"epoch": 1.8860674908118944,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00046430281913348466,
|
|
"loss": 4.7705,
|
|
"mean_token_accuracy": 0.22568886429071428,
|
|
"num_tokens": 41548099.0,
|
|
"step": 22580
|
|
},
|
|
{
|
|
"entropy": 5.399347496032715,
|
|
"epoch": 1.8864851319746074,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004642867268893481,
|
|
"loss": 4.9633,
|
|
"mean_token_accuracy": 0.21363037079572678,
|
|
"num_tokens": 41557288.0,
|
|
"step": 22585
|
|
},
|
|
{
|
|
"entropy": 5.268162488937378,
|
|
"epoch": 1.8869027731373205,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004642706313315194,
|
|
"loss": 4.7234,
|
|
"mean_token_accuracy": 0.23654391914606093,
|
|
"num_tokens": 41565938.0,
|
|
"step": 22590
|
|
},
|
|
{
|
|
"entropy": 5.393177652359009,
|
|
"epoch": 1.8873204143000333,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00046425453246028056,
|
|
"loss": 4.8853,
|
|
"mean_token_accuracy": 0.21670218408107758,
|
|
"num_tokens": 41574984.0,
|
|
"step": 22595
|
|
},
|
|
{
|
|
"entropy": 5.390892410278321,
|
|
"epoch": 1.8877380554627465,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004642384302759133,
|
|
"loss": 4.7417,
|
|
"mean_token_accuracy": 0.231337970495224,
|
|
"num_tokens": 41584020.0,
|
|
"step": 22600
|
|
},
|
|
{
|
|
"entropy": 5.405983018875122,
|
|
"epoch": 1.8881556966254593,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00046422232477869957,
|
|
"loss": 4.8538,
|
|
"mean_token_accuracy": 0.2168538212776184,
|
|
"num_tokens": 41594146.0,
|
|
"step": 22605
|
|
},
|
|
{
|
|
"entropy": 5.369913625717163,
|
|
"epoch": 1.8885733377881724,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004642062159689213,
|
|
"loss": 4.8858,
|
|
"mean_token_accuracy": 0.22145912945270538,
|
|
"num_tokens": 41603469.0,
|
|
"step": 22610
|
|
},
|
|
{
|
|
"entropy": 5.327575016021728,
|
|
"epoch": 1.8889909789508854,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00046419010384686043,
|
|
"loss": 4.8329,
|
|
"mean_token_accuracy": 0.22283699065446855,
|
|
"num_tokens": 41613940.0,
|
|
"step": 22615
|
|
},
|
|
{
|
|
"entropy": 5.371097421646118,
|
|
"epoch": 1.8894086201135984,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000464173988412799,
|
|
"loss": 4.7794,
|
|
"mean_token_accuracy": 0.2242024779319763,
|
|
"num_tokens": 41623153.0,
|
|
"step": 22620
|
|
},
|
|
{
|
|
"entropy": 5.347549390792847,
|
|
"epoch": 1.8898262612763115,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00046415786966701926,
|
|
"loss": 4.8088,
|
|
"mean_token_accuracy": 0.22310995310544968,
|
|
"num_tokens": 41632396.0,
|
|
"step": 22625
|
|
},
|
|
{
|
|
"entropy": 5.289014148712158,
|
|
"epoch": 1.8902439024390243,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004641417476098034,
|
|
"loss": 4.7174,
|
|
"mean_token_accuracy": 0.2279931664466858,
|
|
"num_tokens": 41640727.0,
|
|
"step": 22630
|
|
},
|
|
{
|
|
"entropy": 5.201699113845825,
|
|
"epoch": 1.8906615436017375,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004641256222414335,
|
|
"loss": 4.6031,
|
|
"mean_token_accuracy": 0.23263025432825088,
|
|
"num_tokens": 41648805.0,
|
|
"step": 22635
|
|
},
|
|
{
|
|
"entropy": 5.327459192276001,
|
|
"epoch": 1.8910791847644504,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004641094935621919,
|
|
"loss": 4.8241,
|
|
"mean_token_accuracy": 0.2280990093946457,
|
|
"num_tokens": 41657356.0,
|
|
"step": 22640
|
|
},
|
|
{
|
|
"entropy": 5.336034297943115,
|
|
"epoch": 1.8914968259271634,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000464093361572361,
|
|
"loss": 4.8025,
|
|
"mean_token_accuracy": 0.22273230105638503,
|
|
"num_tokens": 41666525.0,
|
|
"step": 22645
|
|
},
|
|
{
|
|
"entropy": 5.264099597930908,
|
|
"epoch": 1.8919144670898764,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00046407722627222326,
|
|
"loss": 4.7516,
|
|
"mean_token_accuracy": 0.22521811872720718,
|
|
"num_tokens": 41675113.0,
|
|
"step": 22650
|
|
},
|
|
{
|
|
"entropy": 5.423962831497192,
|
|
"epoch": 1.8923321082525892,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00046406108766206103,
|
|
"loss": 4.9138,
|
|
"mean_token_accuracy": 0.20959573239088058,
|
|
"num_tokens": 41684283.0,
|
|
"step": 22655
|
|
},
|
|
{
|
|
"entropy": 5.346978950500488,
|
|
"epoch": 1.8927497494153025,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00046404494574215683,
|
|
"loss": 4.7635,
|
|
"mean_token_accuracy": 0.2245763510465622,
|
|
"num_tokens": 41693751.0,
|
|
"step": 22660
|
|
},
|
|
{
|
|
"entropy": 5.291957807540894,
|
|
"epoch": 1.8931673905780153,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004640288005127933,
|
|
"loss": 4.7651,
|
|
"mean_token_accuracy": 0.22453050315380096,
|
|
"num_tokens": 41702776.0,
|
|
"step": 22665
|
|
},
|
|
{
|
|
"entropy": 5.267710256576538,
|
|
"epoch": 1.8935850317407283,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004640126519742532,
|
|
"loss": 4.7725,
|
|
"mean_token_accuracy": 0.2269309490919113,
|
|
"num_tokens": 41711567.0,
|
|
"step": 22670
|
|
},
|
|
{
|
|
"entropy": 5.351407718658447,
|
|
"epoch": 1.8940026729034414,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000463996500126819,
|
|
"loss": 4.8232,
|
|
"mean_token_accuracy": 0.22899246364831924,
|
|
"num_tokens": 41720784.0,
|
|
"step": 22675
|
|
},
|
|
{
|
|
"entropy": 5.339949035644532,
|
|
"epoch": 1.8944203140661544,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004639803449707737,
|
|
"loss": 4.7351,
|
|
"mean_token_accuracy": 0.22221162170171738,
|
|
"num_tokens": 41730775.0,
|
|
"step": 22680
|
|
},
|
|
{
|
|
"entropy": 5.297207498550415,
|
|
"epoch": 1.8948379552288674,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00046396418650639993,
|
|
"loss": 4.7361,
|
|
"mean_token_accuracy": 0.23091114908456803,
|
|
"num_tokens": 41740151.0,
|
|
"step": 22685
|
|
},
|
|
{
|
|
"entropy": 5.3277678966522215,
|
|
"epoch": 1.8952555963915803,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00046394802473398065,
|
|
"loss": 4.86,
|
|
"mean_token_accuracy": 0.2199167340993881,
|
|
"num_tokens": 41748469.0,
|
|
"step": 22690
|
|
},
|
|
{
|
|
"entropy": 5.37845287322998,
|
|
"epoch": 1.8956732375542935,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004639318596537986,
|
|
"loss": 4.8123,
|
|
"mean_token_accuracy": 0.21564915478229524,
|
|
"num_tokens": 41757771.0,
|
|
"step": 22695
|
|
},
|
|
{
|
|
"entropy": 5.317691421508789,
|
|
"epoch": 1.8960908787170063,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000463915691266137,
|
|
"loss": 4.7687,
|
|
"mean_token_accuracy": 0.22363734096288682,
|
|
"num_tokens": 41766979.0,
|
|
"step": 22700
|
|
},
|
|
{
|
|
"entropy": 5.232506799697876,
|
|
"epoch": 1.8965085198797194,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004638995195712789,
|
|
"loss": 4.7216,
|
|
"mean_token_accuracy": 0.22505969256162645,
|
|
"num_tokens": 41775094.0,
|
|
"step": 22705
|
|
},
|
|
{
|
|
"entropy": 5.400894260406494,
|
|
"epoch": 1.8969261610424324,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004638833445695073,
|
|
"loss": 4.8704,
|
|
"mean_token_accuracy": 0.223477903008461,
|
|
"num_tokens": 41784608.0,
|
|
"step": 22710
|
|
},
|
|
{
|
|
"entropy": 5.400109195709229,
|
|
"epoch": 1.8973438022051452,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00046386716626110544,
|
|
"loss": 4.8783,
|
|
"mean_token_accuracy": 0.21973977833986283,
|
|
"num_tokens": 41793789.0,
|
|
"step": 22715
|
|
},
|
|
{
|
|
"entropy": 5.3733443260192875,
|
|
"epoch": 1.8977614433678585,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00046385098464635645,
|
|
"loss": 4.8222,
|
|
"mean_token_accuracy": 0.21941734701395035,
|
|
"num_tokens": 41802928.0,
|
|
"step": 22720
|
|
},
|
|
{
|
|
"entropy": 5.440585803985596,
|
|
"epoch": 1.8981790845305713,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004638347997255436,
|
|
"loss": 4.9364,
|
|
"mean_token_accuracy": 0.2148139864206314,
|
|
"num_tokens": 41812231.0,
|
|
"step": 22725
|
|
},
|
|
{
|
|
"entropy": 5.333082485198974,
|
|
"epoch": 1.8985967256932843,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004638186114989504,
|
|
"loss": 4.8266,
|
|
"mean_token_accuracy": 0.2276677206158638,
|
|
"num_tokens": 41820665.0,
|
|
"step": 22730
|
|
},
|
|
{
|
|
"entropy": 5.3604718208312985,
|
|
"epoch": 1.8990143668559973,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004638024199668601,
|
|
"loss": 4.787,
|
|
"mean_token_accuracy": 0.22488851100206375,
|
|
"num_tokens": 41829568.0,
|
|
"step": 22735
|
|
},
|
|
{
|
|
"entropy": 5.287040710449219,
|
|
"epoch": 1.8994320080187104,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004637862251295561,
|
|
"loss": 4.729,
|
|
"mean_token_accuracy": 0.22228167653083802,
|
|
"num_tokens": 41838360.0,
|
|
"step": 22740
|
|
},
|
|
{
|
|
"entropy": 5.332267999649048,
|
|
"epoch": 1.8998496491814234,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000463770026987322,
|
|
"loss": 4.7414,
|
|
"mean_token_accuracy": 0.2228656679391861,
|
|
"num_tokens": 41847050.0,
|
|
"step": 22745
|
|
},
|
|
{
|
|
"entropy": 5.407240200042724,
|
|
"epoch": 1.9002672903441362,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00046375382554044136,
|
|
"loss": 4.8141,
|
|
"mean_token_accuracy": 0.22377554476261138,
|
|
"num_tokens": 41856379.0,
|
|
"step": 22750
|
|
},
|
|
{
|
|
"entropy": 5.367939424514771,
|
|
"epoch": 1.9006849315068495,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004637376207891978,
|
|
"loss": 4.7488,
|
|
"mean_token_accuracy": 0.2322536215186119,
|
|
"num_tokens": 41865139.0,
|
|
"step": 22755
|
|
},
|
|
{
|
|
"entropy": 5.325418901443482,
|
|
"epoch": 1.9011025726695623,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000463721412733875,
|
|
"loss": 4.7943,
|
|
"mean_token_accuracy": 0.2270716741681099,
|
|
"num_tokens": 41873955.0,
|
|
"step": 22760
|
|
},
|
|
{
|
|
"entropy": 5.317761516571045,
|
|
"epoch": 1.9015202138322753,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00046370520137475673,
|
|
"loss": 4.8285,
|
|
"mean_token_accuracy": 0.22254237681627273,
|
|
"num_tokens": 41883771.0,
|
|
"step": 22765
|
|
},
|
|
{
|
|
"entropy": 5.381101846694946,
|
|
"epoch": 1.9019378549949884,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004636889867121268,
|
|
"loss": 4.8105,
|
|
"mean_token_accuracy": 0.22199124246835708,
|
|
"num_tokens": 41893411.0,
|
|
"step": 22770
|
|
},
|
|
{
|
|
"entropy": 5.301739883422852,
|
|
"epoch": 1.9023554961577012,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00046367276874626894,
|
|
"loss": 4.762,
|
|
"mean_token_accuracy": 0.22433813214302062,
|
|
"num_tokens": 41903612.0,
|
|
"step": 22775
|
|
},
|
|
{
|
|
"entropy": 5.348691940307617,
|
|
"epoch": 1.9027731373204144,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004636565474774673,
|
|
"loss": 4.7631,
|
|
"mean_token_accuracy": 0.23066183775663376,
|
|
"num_tokens": 41912754.0,
|
|
"step": 22780
|
|
},
|
|
{
|
|
"entropy": 5.384900093078613,
|
|
"epoch": 1.9031907784831272,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00046364032290600556,
|
|
"loss": 4.8081,
|
|
"mean_token_accuracy": 0.21840860694646835,
|
|
"num_tokens": 41922854.0,
|
|
"step": 22785
|
|
},
|
|
{
|
|
"entropy": 5.287535381317139,
|
|
"epoch": 1.9036084196458403,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000463624095032168,
|
|
"loss": 4.8337,
|
|
"mean_token_accuracy": 0.2237662509083748,
|
|
"num_tokens": 41932259.0,
|
|
"step": 22790
|
|
},
|
|
{
|
|
"entropy": 5.29298357963562,
|
|
"epoch": 1.9040260608085533,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00046360786385623854,
|
|
"loss": 4.705,
|
|
"mean_token_accuracy": 0.2310274213552475,
|
|
"num_tokens": 41940833.0,
|
|
"step": 22795
|
|
},
|
|
{
|
|
"entropy": 5.346249389648437,
|
|
"epoch": 1.9044437019712663,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004635916293785015,
|
|
"loss": 4.8198,
|
|
"mean_token_accuracy": 0.22410718947649003,
|
|
"num_tokens": 41949756.0,
|
|
"step": 22800
|
|
},
|
|
{
|
|
"entropy": 5.406274938583374,
|
|
"epoch": 1.9048613431339794,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004635753915992409,
|
|
"loss": 4.914,
|
|
"mean_token_accuracy": 0.22082435786724092,
|
|
"num_tokens": 41959447.0,
|
|
"step": 22805
|
|
},
|
|
{
|
|
"entropy": 5.425630521774292,
|
|
"epoch": 1.9052789842966922,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000463559150518741,
|
|
"loss": 4.837,
|
|
"mean_token_accuracy": 0.21522256731987,
|
|
"num_tokens": 41968308.0,
|
|
"step": 22810
|
|
},
|
|
{
|
|
"entropy": 5.360799121856689,
|
|
"epoch": 1.9056966254594054,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004635429061372864,
|
|
"loss": 4.7755,
|
|
"mean_token_accuracy": 0.2194485530257225,
|
|
"num_tokens": 41976331.0,
|
|
"step": 22815
|
|
},
|
|
{
|
|
"entropy": 5.354419088363647,
|
|
"epoch": 1.9061142666221182,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00046352665845516113,
|
|
"loss": 4.8567,
|
|
"mean_token_accuracy": 0.2180070012807846,
|
|
"num_tokens": 41985386.0,
|
|
"step": 22820
|
|
},
|
|
{
|
|
"entropy": 5.317965412139893,
|
|
"epoch": 1.9065319077848313,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004635104074726498,
|
|
"loss": 4.7126,
|
|
"mean_token_accuracy": 0.22696897983551026,
|
|
"num_tokens": 41993517.0,
|
|
"step": 22825
|
|
},
|
|
{
|
|
"entropy": 5.254163599014282,
|
|
"epoch": 1.9069495489475443,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004634941531900369,
|
|
"loss": 4.7168,
|
|
"mean_token_accuracy": 0.22181184589862823,
|
|
"num_tokens": 42002624.0,
|
|
"step": 22830
|
|
},
|
|
{
|
|
"entropy": 5.280917644500732,
|
|
"epoch": 1.9073671901102571,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00046347789560760696,
|
|
"loss": 4.8022,
|
|
"mean_token_accuracy": 0.22092570513486862,
|
|
"num_tokens": 42012128.0,
|
|
"step": 22835
|
|
},
|
|
{
|
|
"entropy": 5.316110849380493,
|
|
"epoch": 1.9077848312729704,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004634616347256446,
|
|
"loss": 4.7,
|
|
"mean_token_accuracy": 0.228427255153656,
|
|
"num_tokens": 42021243.0,
|
|
"step": 22840
|
|
},
|
|
{
|
|
"entropy": 5.327328538894653,
|
|
"epoch": 1.9082024724356832,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00046344537054443443,
|
|
"loss": 4.8304,
|
|
"mean_token_accuracy": 0.22289811670780182,
|
|
"num_tokens": 42031397.0,
|
|
"step": 22845
|
|
},
|
|
{
|
|
"entropy": 5.436086177825928,
|
|
"epoch": 1.9086201135983962,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004634291030642613,
|
|
"loss": 4.8222,
|
|
"mean_token_accuracy": 0.22025218456983567,
|
|
"num_tokens": 42040560.0,
|
|
"step": 22850
|
|
},
|
|
{
|
|
"entropy": 5.311260843276978,
|
|
"epoch": 1.9090377547611093,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004634128322854098,
|
|
"loss": 4.7855,
|
|
"mean_token_accuracy": 0.22352129220962524,
|
|
"num_tokens": 42048824.0,
|
|
"step": 22855
|
|
},
|
|
{
|
|
"entropy": 5.340697336196899,
|
|
"epoch": 1.9094553959238223,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004633965582081649,
|
|
"loss": 4.802,
|
|
"mean_token_accuracy": 0.22202707976102828,
|
|
"num_tokens": 42057460.0,
|
|
"step": 22860
|
|
},
|
|
{
|
|
"entropy": 5.333004283905029,
|
|
"epoch": 1.9098730370865353,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00046338028083281154,
|
|
"loss": 4.814,
|
|
"mean_token_accuracy": 0.22184410244226455,
|
|
"num_tokens": 42066829.0,
|
|
"step": 22865
|
|
},
|
|
{
|
|
"entropy": 5.3980354309082035,
|
|
"epoch": 1.9102906782492481,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00046336400015963453,
|
|
"loss": 4.8923,
|
|
"mean_token_accuracy": 0.2153046175837517,
|
|
"num_tokens": 42075518.0,
|
|
"step": 22870
|
|
},
|
|
{
|
|
"entropy": 5.350751686096191,
|
|
"epoch": 1.9107083194119614,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000463347716188919,
|
|
"loss": 4.7444,
|
|
"mean_token_accuracy": 0.2265250042080879,
|
|
"num_tokens": 42083939.0,
|
|
"step": 22875
|
|
},
|
|
{
|
|
"entropy": 5.30185489654541,
|
|
"epoch": 1.9111259605746742,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00046333142892094996,
|
|
"loss": 4.7257,
|
|
"mean_token_accuracy": 0.2278050184249878,
|
|
"num_tokens": 42092229.0,
|
|
"step": 22880
|
|
},
|
|
{
|
|
"entropy": 5.356488418579102,
|
|
"epoch": 1.9115436017373872,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00046331513835601263,
|
|
"loss": 4.7869,
|
|
"mean_token_accuracy": 0.22182031571865082,
|
|
"num_tokens": 42101876.0,
|
|
"step": 22885
|
|
},
|
|
{
|
|
"entropy": 5.352019214630127,
|
|
"epoch": 1.9119612429001003,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00046329884449439207,
|
|
"loss": 4.8045,
|
|
"mean_token_accuracy": 0.22971448302268982,
|
|
"num_tokens": 42110710.0,
|
|
"step": 22890
|
|
},
|
|
{
|
|
"entropy": 5.453985357284546,
|
|
"epoch": 1.912378884062813,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00046328254733637357,
|
|
"loss": 4.9344,
|
|
"mean_token_accuracy": 0.2096916615962982,
|
|
"num_tokens": 42120516.0,
|
|
"step": 22895
|
|
},
|
|
{
|
|
"entropy": 5.368203115463257,
|
|
"epoch": 1.9127965252255263,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004632662468822425,
|
|
"loss": 4.7659,
|
|
"mean_token_accuracy": 0.22583042830228806,
|
|
"num_tokens": 42129030.0,
|
|
"step": 22900
|
|
},
|
|
{
|
|
"entropy": 5.364561319351196,
|
|
"epoch": 1.9132141663882392,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004632499431322842,
|
|
"loss": 4.8879,
|
|
"mean_token_accuracy": 0.21601082384586334,
|
|
"num_tokens": 42138107.0,
|
|
"step": 22905
|
|
},
|
|
{
|
|
"entropy": 5.472171306610107,
|
|
"epoch": 1.9136318075509522,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000463233636086784,
|
|
"loss": 4.9495,
|
|
"mean_token_accuracy": 0.21616242080926895,
|
|
"num_tokens": 42147584.0,
|
|
"step": 22910
|
|
},
|
|
{
|
|
"entropy": 5.371504878997802,
|
|
"epoch": 1.9140494487136652,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00046321732574602735,
|
|
"loss": 4.7491,
|
|
"mean_token_accuracy": 0.2259305238723755,
|
|
"num_tokens": 42156751.0,
|
|
"step": 22915
|
|
},
|
|
{
|
|
"entropy": 5.296944522857666,
|
|
"epoch": 1.9144670898763783,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00046320101211029996,
|
|
"loss": 4.7045,
|
|
"mean_token_accuracy": 0.23260689824819564,
|
|
"num_tokens": 42165204.0,
|
|
"step": 22920
|
|
},
|
|
{
|
|
"entropy": 5.3397650718688965,
|
|
"epoch": 1.9148847310390913,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00046318469517988724,
|
|
"loss": 4.8074,
|
|
"mean_token_accuracy": 0.2239825204014778,
|
|
"num_tokens": 42174028.0,
|
|
"step": 22925
|
|
},
|
|
{
|
|
"entropy": 5.324157285690307,
|
|
"epoch": 1.915302372201804,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000463168374955075,
|
|
"loss": 4.8226,
|
|
"mean_token_accuracy": 0.22616441696882247,
|
|
"num_tokens": 42183658.0,
|
|
"step": 22930
|
|
},
|
|
{
|
|
"entropy": 5.397616577148438,
|
|
"epoch": 1.9157200133645174,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00046315205143614873,
|
|
"loss": 4.7897,
|
|
"mean_token_accuracy": 0.22479767650365828,
|
|
"num_tokens": 42192509.0,
|
|
"step": 22935
|
|
},
|
|
{
|
|
"entropy": 5.429402780532837,
|
|
"epoch": 1.9161376545272302,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00046313572462339437,
|
|
"loss": 4.855,
|
|
"mean_token_accuracy": 0.21973563730716705,
|
|
"num_tokens": 42201919.0,
|
|
"step": 22940
|
|
},
|
|
{
|
|
"entropy": 5.3620750427246096,
|
|
"epoch": 1.9165552956899432,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00046311939451709776,
|
|
"loss": 4.8379,
|
|
"mean_token_accuracy": 0.21960468590259552,
|
|
"num_tokens": 42211027.0,
|
|
"step": 22945
|
|
},
|
|
{
|
|
"entropy": 5.458581447601318,
|
|
"epoch": 1.9169729368526562,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004631030611175447,
|
|
"loss": 4.8727,
|
|
"mean_token_accuracy": 0.21973092406988143,
|
|
"num_tokens": 42219677.0,
|
|
"step": 22950
|
|
},
|
|
{
|
|
"entropy": 5.452214908599854,
|
|
"epoch": 1.917390578015369,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00046308672442502103,
|
|
"loss": 4.869,
|
|
"mean_token_accuracy": 0.21689503490924836,
|
|
"num_tokens": 42228602.0,
|
|
"step": 22955
|
|
},
|
|
{
|
|
"entropy": 5.411986255645752,
|
|
"epoch": 1.9178082191780823,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000463070384439813,
|
|
"loss": 4.8014,
|
|
"mean_token_accuracy": 0.22038799226284028,
|
|
"num_tokens": 42238238.0,
|
|
"step": 22960
|
|
},
|
|
{
|
|
"entropy": 5.358574295043946,
|
|
"epoch": 1.9182258603407951,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004630540411622064,
|
|
"loss": 4.8762,
|
|
"mean_token_accuracy": 0.21948132514953614,
|
|
"num_tokens": 42247499.0,
|
|
"step": 22965
|
|
},
|
|
{
|
|
"entropy": 5.324526071548462,
|
|
"epoch": 1.9186435015035082,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004630376945924875,
|
|
"loss": 4.7639,
|
|
"mean_token_accuracy": 0.23184950947761535,
|
|
"num_tokens": 42256761.0,
|
|
"step": 22970
|
|
},
|
|
{
|
|
"entropy": 5.3963930130004885,
|
|
"epoch": 1.9190611426662212,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004630213447309424,
|
|
"loss": 4.9029,
|
|
"mean_token_accuracy": 0.214429634809494,
|
|
"num_tokens": 42266062.0,
|
|
"step": 22975
|
|
},
|
|
{
|
|
"entropy": 5.382733106613159,
|
|
"epoch": 1.9194787838289342,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00046300499157785725,
|
|
"loss": 4.7327,
|
|
"mean_token_accuracy": 0.22653516680002211,
|
|
"num_tokens": 42275510.0,
|
|
"step": 22980
|
|
},
|
|
{
|
|
"entropy": 5.3866783618927006,
|
|
"epoch": 1.9198964249916473,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00046298863513351854,
|
|
"loss": 4.9098,
|
|
"mean_token_accuracy": 0.2131809413433075,
|
|
"num_tokens": 42284905.0,
|
|
"step": 22985
|
|
},
|
|
{
|
|
"entropy": 5.317132091522216,
|
|
"epoch": 1.92031406615436,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00046297227539821245,
|
|
"loss": 4.825,
|
|
"mean_token_accuracy": 0.22732676416635514,
|
|
"num_tokens": 42294730.0,
|
|
"step": 22990
|
|
},
|
|
{
|
|
"entropy": 5.395043182373047,
|
|
"epoch": 1.9207317073170733,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004629559123722254,
|
|
"loss": 4.8606,
|
|
"mean_token_accuracy": 0.21894442588090895,
|
|
"num_tokens": 42304634.0,
|
|
"step": 22995
|
|
},
|
|
{
|
|
"entropy": 5.341714811325073,
|
|
"epoch": 1.9211493484797861,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00046293954605584393,
|
|
"loss": 4.7302,
|
|
"mean_token_accuracy": 0.2230134055018425,
|
|
"num_tokens": 42313232.0,
|
|
"step": 23000
|
|
},
|
|
{
|
|
"entropy": 5.326078319549561,
|
|
"epoch": 1.9215669896424992,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004629231764493544,
|
|
"loss": 4.8153,
|
|
"mean_token_accuracy": 0.22583523541688919,
|
|
"num_tokens": 42322320.0,
|
|
"step": 23005
|
|
},
|
|
{
|
|
"entropy": 5.377879238128662,
|
|
"epoch": 1.9219846308052122,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004629068035530435,
|
|
"loss": 4.7392,
|
|
"mean_token_accuracy": 0.2262878507375717,
|
|
"num_tokens": 42331424.0,
|
|
"step": 23010
|
|
},
|
|
{
|
|
"entropy": 5.27747163772583,
|
|
"epoch": 1.922402271967925,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004628904273671978,
|
|
"loss": 4.7927,
|
|
"mean_token_accuracy": 0.2184443563222885,
|
|
"num_tokens": 42341759.0,
|
|
"step": 23015
|
|
},
|
|
{
|
|
"entropy": 5.266590547561646,
|
|
"epoch": 1.9228199131306383,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004628740478921041,
|
|
"loss": 4.7954,
|
|
"mean_token_accuracy": 0.22423614412546158,
|
|
"num_tokens": 42351000.0,
|
|
"step": 23020
|
|
},
|
|
{
|
|
"entropy": 5.365396451950073,
|
|
"epoch": 1.923237554293351,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00046285766512804894,
|
|
"loss": 4.7957,
|
|
"mean_token_accuracy": 0.2252248704433441,
|
|
"num_tokens": 42360797.0,
|
|
"step": 23025
|
|
},
|
|
{
|
|
"entropy": 5.297489595413208,
|
|
"epoch": 1.9236551954560641,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00046284127907531925,
|
|
"loss": 4.7055,
|
|
"mean_token_accuracy": 0.23269612789154054,
|
|
"num_tokens": 42370067.0,
|
|
"step": 23030
|
|
},
|
|
{
|
|
"entropy": 5.337820625305175,
|
|
"epoch": 1.9240728366187771,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00046282488973420187,
|
|
"loss": 4.7795,
|
|
"mean_token_accuracy": 0.22158965170383454,
|
|
"num_tokens": 42379857.0,
|
|
"step": 23035
|
|
},
|
|
{
|
|
"entropy": 5.3889501094818115,
|
|
"epoch": 1.9244904777814902,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004628084971049837,
|
|
"loss": 4.754,
|
|
"mean_token_accuracy": 0.22677709758281708,
|
|
"num_tokens": 42388776.0,
|
|
"step": 23040
|
|
},
|
|
{
|
|
"entropy": 5.285422468185425,
|
|
"epoch": 1.9249081189442032,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00046279210118795175,
|
|
"loss": 4.7135,
|
|
"mean_token_accuracy": 0.22471415847539902,
|
|
"num_tokens": 42397362.0,
|
|
"step": 23045
|
|
},
|
|
{
|
|
"entropy": 5.3311999320983885,
|
|
"epoch": 1.925325760106916,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000462775701983393,
|
|
"loss": 4.7952,
|
|
"mean_token_accuracy": 0.21638373881578446,
|
|
"num_tokens": 42405856.0,
|
|
"step": 23050
|
|
},
|
|
{
|
|
"entropy": 5.373071002960205,
|
|
"epoch": 1.9257434012696293,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004627592994915946,
|
|
"loss": 4.8501,
|
|
"mean_token_accuracy": 0.22046791315078734,
|
|
"num_tokens": 42415340.0,
|
|
"step": 23055
|
|
},
|
|
{
|
|
"entropy": 5.385590267181397,
|
|
"epoch": 1.926161042432342,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00046274289371284357,
|
|
"loss": 4.8165,
|
|
"mean_token_accuracy": 0.2275014728307724,
|
|
"num_tokens": 42424113.0,
|
|
"step": 23060
|
|
},
|
|
{
|
|
"entropy": 5.326909399032592,
|
|
"epoch": 1.9265786835950551,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00046272648464742733,
|
|
"loss": 4.6965,
|
|
"mean_token_accuracy": 0.23168404996395112,
|
|
"num_tokens": 42433833.0,
|
|
"step": 23065
|
|
},
|
|
{
|
|
"entropy": 5.321767377853393,
|
|
"epoch": 1.9269963247577682,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004627100722956329,
|
|
"loss": 4.7143,
|
|
"mean_token_accuracy": 0.22826789766550065,
|
|
"num_tokens": 42442652.0,
|
|
"step": 23070
|
|
},
|
|
{
|
|
"entropy": 5.307167911529541,
|
|
"epoch": 1.927413965920481,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00046269365665774773,
|
|
"loss": 4.8271,
|
|
"mean_token_accuracy": 0.22706694155931473,
|
|
"num_tokens": 42452642.0,
|
|
"step": 23075
|
|
},
|
|
{
|
|
"entropy": 5.332990264892578,
|
|
"epoch": 1.9278316070831942,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00046267723773405915,
|
|
"loss": 4.7814,
|
|
"mean_token_accuracy": 0.22703045904636382,
|
|
"num_tokens": 42460623.0,
|
|
"step": 23080
|
|
},
|
|
{
|
|
"entropy": 5.295384168624878,
|
|
"epoch": 1.928249248245907,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00046266081552485467,
|
|
"loss": 4.7632,
|
|
"mean_token_accuracy": 0.22836388349533082,
|
|
"num_tokens": 42469963.0,
|
|
"step": 23085
|
|
},
|
|
{
|
|
"entropy": 5.421449995040893,
|
|
"epoch": 1.92866688940862,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00046264439003042176,
|
|
"loss": 4.8815,
|
|
"mean_token_accuracy": 0.2203097388148308,
|
|
"num_tokens": 42479375.0,
|
|
"step": 23090
|
|
},
|
|
{
|
|
"entropy": 5.338653612136841,
|
|
"epoch": 1.9290845305713331,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00046262796125104785,
|
|
"loss": 4.7503,
|
|
"mean_token_accuracy": 0.2250423327088356,
|
|
"num_tokens": 42487837.0,
|
|
"step": 23095
|
|
},
|
|
{
|
|
"entropy": 5.3704461574554445,
|
|
"epoch": 1.9295021717340461,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004626115291870206,
|
|
"loss": 4.8528,
|
|
"mean_token_accuracy": 0.21504176706075667,
|
|
"num_tokens": 42496666.0,
|
|
"step": 23100
|
|
},
|
|
{
|
|
"entropy": 5.344387674331665,
|
|
"epoch": 1.9299198128967592,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00046259509383862784,
|
|
"loss": 4.7992,
|
|
"mean_token_accuracy": 0.22046858221292495,
|
|
"num_tokens": 42507195.0,
|
|
"step": 23105
|
|
},
|
|
{
|
|
"entropy": 5.371675682067871,
|
|
"epoch": 1.930337454059472,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004625786552061571,
|
|
"loss": 4.721,
|
|
"mean_token_accuracy": 0.22992677390575408,
|
|
"num_tokens": 42515879.0,
|
|
"step": 23110
|
|
},
|
|
{
|
|
"entropy": 5.4279430389404295,
|
|
"epoch": 1.9307550952221852,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004625622132898962,
|
|
"loss": 4.8973,
|
|
"mean_token_accuracy": 0.21573415249586106,
|
|
"num_tokens": 42524877.0,
|
|
"step": 23115
|
|
},
|
|
{
|
|
"entropy": 5.303271865844726,
|
|
"epoch": 1.931172736384898,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00046254576809013297,
|
|
"loss": 4.7968,
|
|
"mean_token_accuracy": 0.22052676677703859,
|
|
"num_tokens": 42534019.0,
|
|
"step": 23120
|
|
},
|
|
{
|
|
"entropy": 5.413978099822998,
|
|
"epoch": 1.931590377547611,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004625293196071554,
|
|
"loss": 4.8764,
|
|
"mean_token_accuracy": 0.21954282373189926,
|
|
"num_tokens": 42543280.0,
|
|
"step": 23125
|
|
},
|
|
{
|
|
"entropy": 5.445626497268677,
|
|
"epoch": 1.9320080187103241,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004625128678412513,
|
|
"loss": 4.8941,
|
|
"mean_token_accuracy": 0.2156203046441078,
|
|
"num_tokens": 42553476.0,
|
|
"step": 23130
|
|
},
|
|
{
|
|
"entropy": 5.332164859771728,
|
|
"epoch": 1.932425659873037,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00046249641279270866,
|
|
"loss": 4.8037,
|
|
"mean_token_accuracy": 0.22545204311609268,
|
|
"num_tokens": 42562502.0,
|
|
"step": 23135
|
|
},
|
|
{
|
|
"entropy": 5.353411912918091,
|
|
"epoch": 1.9328433010357502,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00046247995446181575,
|
|
"loss": 4.8014,
|
|
"mean_token_accuracy": 0.21955363899469377,
|
|
"num_tokens": 42570947.0,
|
|
"step": 23140
|
|
},
|
|
{
|
|
"entropy": 5.360992670059204,
|
|
"epoch": 1.933260942198463,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004624634928488605,
|
|
"loss": 4.7686,
|
|
"mean_token_accuracy": 0.22439190596342087,
|
|
"num_tokens": 42579548.0,
|
|
"step": 23145
|
|
},
|
|
{
|
|
"entropy": 5.3457427501678465,
|
|
"epoch": 1.933678583361176,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004624470279541312,
|
|
"loss": 4.7513,
|
|
"mean_token_accuracy": 0.22840931862592698,
|
|
"num_tokens": 42588006.0,
|
|
"step": 23150
|
|
},
|
|
{
|
|
"entropy": 5.44417634010315,
|
|
"epoch": 1.934096224523889,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00046243055977791597,
|
|
"loss": 4.8698,
|
|
"mean_token_accuracy": 0.22178881764411926,
|
|
"num_tokens": 42597322.0,
|
|
"step": 23155
|
|
},
|
|
{
|
|
"entropy": 5.429265451431275,
|
|
"epoch": 1.934513865686602,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004624140883205033,
|
|
"loss": 4.7765,
|
|
"mean_token_accuracy": 0.22641210556030272,
|
|
"num_tokens": 42605942.0,
|
|
"step": 23160
|
|
},
|
|
{
|
|
"entropy": 5.357011079788208,
|
|
"epoch": 1.9349315068493151,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00046239761358218135,
|
|
"loss": 4.8492,
|
|
"mean_token_accuracy": 0.22234605997800827,
|
|
"num_tokens": 42614870.0,
|
|
"step": 23165
|
|
},
|
|
{
|
|
"entropy": 5.36984806060791,
|
|
"epoch": 1.935349148012028,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004623811355632386,
|
|
"loss": 4.8221,
|
|
"mean_token_accuracy": 0.21981562227010726,
|
|
"num_tokens": 42624324.0,
|
|
"step": 23170
|
|
},
|
|
{
|
|
"entropy": 5.377413368225097,
|
|
"epoch": 1.9357667891747412,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00046236465426396353,
|
|
"loss": 4.8212,
|
|
"mean_token_accuracy": 0.21463316231966018,
|
|
"num_tokens": 42634120.0,
|
|
"step": 23175
|
|
},
|
|
{
|
|
"entropy": 5.329346799850464,
|
|
"epoch": 1.936184430337454,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004623481696846446,
|
|
"loss": 4.7508,
|
|
"mean_token_accuracy": 0.23090596199035646,
|
|
"num_tokens": 42642709.0,
|
|
"step": 23180
|
|
},
|
|
{
|
|
"entropy": 5.345608234405518,
|
|
"epoch": 1.936602071500167,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004623316818255706,
|
|
"loss": 4.7929,
|
|
"mean_token_accuracy": 0.21797361373901367,
|
|
"num_tokens": 42652286.0,
|
|
"step": 23185
|
|
},
|
|
{
|
|
"entropy": 5.336495780944825,
|
|
"epoch": 1.93701971266288,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004623151906870299,
|
|
"loss": 4.7678,
|
|
"mean_token_accuracy": 0.23080508410930634,
|
|
"num_tokens": 42662195.0,
|
|
"step": 23190
|
|
},
|
|
{
|
|
"entropy": 5.405407381057739,
|
|
"epoch": 1.937437353825593,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004622986962693113,
|
|
"loss": 4.8013,
|
|
"mean_token_accuracy": 0.2205159768462181,
|
|
"num_tokens": 42671853.0,
|
|
"step": 23195
|
|
},
|
|
{
|
|
"entropy": 5.382732725143432,
|
|
"epoch": 1.9378549949883062,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004622821985727036,
|
|
"loss": 4.8229,
|
|
"mean_token_accuracy": 0.2194904237985611,
|
|
"num_tokens": 42681677.0,
|
|
"step": 23200
|
|
},
|
|
{
|
|
"entropy": 5.304739475250244,
|
|
"epoch": 1.938272636151019,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004622656975974956,
|
|
"loss": 4.7118,
|
|
"mean_token_accuracy": 0.22898323684930802,
|
|
"num_tokens": 42690686.0,
|
|
"step": 23205
|
|
},
|
|
{
|
|
"entropy": 5.331717252731323,
|
|
"epoch": 1.938690277313732,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00046224919334397616,
|
|
"loss": 4.792,
|
|
"mean_token_accuracy": 0.22277454435825347,
|
|
"num_tokens": 42699967.0,
|
|
"step": 23210
|
|
},
|
|
{
|
|
"entropy": 5.33602557182312,
|
|
"epoch": 1.939107918476445,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00046223268581243416,
|
|
"loss": 4.7994,
|
|
"mean_token_accuracy": 0.229104682803154,
|
|
"num_tokens": 42708185.0,
|
|
"step": 23215
|
|
},
|
|
{
|
|
"entropy": 5.333634281158448,
|
|
"epoch": 1.939525559639158,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00046221617500315866,
|
|
"loss": 4.7997,
|
|
"mean_token_accuracy": 0.21859076023101806,
|
|
"num_tokens": 42717856.0,
|
|
"step": 23220
|
|
},
|
|
{
|
|
"entropy": 5.352754783630371,
|
|
"epoch": 1.939943200801871,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00046219966091643865,
|
|
"loss": 4.7756,
|
|
"mean_token_accuracy": 0.2239677146077156,
|
|
"num_tokens": 42727036.0,
|
|
"step": 23225
|
|
},
|
|
{
|
|
"entropy": 5.364761543273926,
|
|
"epoch": 1.940360841964584,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00046218314355256324,
|
|
"loss": 4.7833,
|
|
"mean_token_accuracy": 0.22635633647441863,
|
|
"num_tokens": 42736593.0,
|
|
"step": 23230
|
|
},
|
|
{
|
|
"entropy": 5.373131561279297,
|
|
"epoch": 1.9407784831272972,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004621666229118216,
|
|
"loss": 4.7916,
|
|
"mean_token_accuracy": 0.23297087252140045,
|
|
"num_tokens": 42745728.0,
|
|
"step": 23235
|
|
},
|
|
{
|
|
"entropy": 5.362151956558227,
|
|
"epoch": 1.94119612429001,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00046215009899450296,
|
|
"loss": 4.7859,
|
|
"mean_token_accuracy": 0.22317458391189576,
|
|
"num_tokens": 42754638.0,
|
|
"step": 23240
|
|
},
|
|
{
|
|
"entropy": 5.34175066947937,
|
|
"epoch": 1.941613765452723,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004621335718008965,
|
|
"loss": 4.724,
|
|
"mean_token_accuracy": 0.23164665549993516,
|
|
"num_tokens": 42763474.0,
|
|
"step": 23245
|
|
},
|
|
{
|
|
"entropy": 5.398498487472534,
|
|
"epoch": 1.942031406615436,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00046211704133129164,
|
|
"loss": 4.8916,
|
|
"mean_token_accuracy": 0.21393152922391892,
|
|
"num_tokens": 42772440.0,
|
|
"step": 23250
|
|
},
|
|
{
|
|
"entropy": 5.343511152267456,
|
|
"epoch": 1.9424490477781489,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00046210050758597776,
|
|
"loss": 4.6833,
|
|
"mean_token_accuracy": 0.2345033884048462,
|
|
"num_tokens": 42780369.0,
|
|
"step": 23255
|
|
},
|
|
{
|
|
"entropy": 5.324027872085571,
|
|
"epoch": 1.9428666889408621,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00046208397056524424,
|
|
"loss": 4.7122,
|
|
"mean_token_accuracy": 0.23065568059682845,
|
|
"num_tokens": 42789652.0,
|
|
"step": 23260
|
|
},
|
|
{
|
|
"entropy": 5.410207319259643,
|
|
"epoch": 1.943284330103575,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004620674302693807,
|
|
"loss": 4.8543,
|
|
"mean_token_accuracy": 0.21698149889707566,
|
|
"num_tokens": 42798067.0,
|
|
"step": 23265
|
|
},
|
|
{
|
|
"entropy": 5.3743514060974125,
|
|
"epoch": 1.943701971266288,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004620508866986765,
|
|
"loss": 4.7622,
|
|
"mean_token_accuracy": 0.22114859521389008,
|
|
"num_tokens": 42806010.0,
|
|
"step": 23270
|
|
},
|
|
{
|
|
"entropy": 5.3669616222381595,
|
|
"epoch": 1.944119612429001,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00046203433985342145,
|
|
"loss": 4.8045,
|
|
"mean_token_accuracy": 0.21888705641031264,
|
|
"num_tokens": 42815596.0,
|
|
"step": 23275
|
|
},
|
|
{
|
|
"entropy": 5.336707592010498,
|
|
"epoch": 1.944537253591714,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004620177897339051,
|
|
"loss": 4.7534,
|
|
"mean_token_accuracy": 0.22457436472177505,
|
|
"num_tokens": 42824953.0,
|
|
"step": 23280
|
|
},
|
|
{
|
|
"entropy": 5.3419740200042725,
|
|
"epoch": 1.944954894754427,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004620012363404173,
|
|
"loss": 4.8822,
|
|
"mean_token_accuracy": 0.21319204717874526,
|
|
"num_tokens": 42833737.0,
|
|
"step": 23285
|
|
},
|
|
{
|
|
"entropy": 5.425252866744995,
|
|
"epoch": 1.9453725359171399,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00046198467967324783,
|
|
"loss": 4.8855,
|
|
"mean_token_accuracy": 0.2190430834889412,
|
|
"num_tokens": 42843674.0,
|
|
"step": 23290
|
|
},
|
|
{
|
|
"entropy": 5.340398454666138,
|
|
"epoch": 1.9457901770798531,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004619681197326863,
|
|
"loss": 4.7057,
|
|
"mean_token_accuracy": 0.2310635969042778,
|
|
"num_tokens": 42852510.0,
|
|
"step": 23295
|
|
},
|
|
{
|
|
"entropy": 5.231046438217163,
|
|
"epoch": 1.946207818242566,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004619515565190229,
|
|
"loss": 4.6212,
|
|
"mean_token_accuracy": 0.24159635454416276,
|
|
"num_tokens": 42860482.0,
|
|
"step": 23300
|
|
},
|
|
{
|
|
"entropy": 5.353284311294556,
|
|
"epoch": 1.946625459405279,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00046193499003254737,
|
|
"loss": 4.8049,
|
|
"mean_token_accuracy": 0.22045551389455795,
|
|
"num_tokens": 42869413.0,
|
|
"step": 23305
|
|
},
|
|
{
|
|
"entropy": 5.440742874145508,
|
|
"epoch": 1.947043100567992,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004619184202735499,
|
|
"loss": 4.9269,
|
|
"mean_token_accuracy": 0.21469709277153015,
|
|
"num_tokens": 42879032.0,
|
|
"step": 23310
|
|
},
|
|
{
|
|
"entropy": 5.363071346282959,
|
|
"epoch": 1.9474607417307048,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004619018472423205,
|
|
"loss": 4.7717,
|
|
"mean_token_accuracy": 0.22745587527751923,
|
|
"num_tokens": 42887989.0,
|
|
"step": 23315
|
|
},
|
|
{
|
|
"entropy": 5.388525915145874,
|
|
"epoch": 1.947878382893418,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00046188527093914925,
|
|
"loss": 4.8596,
|
|
"mean_token_accuracy": 0.2167577102780342,
|
|
"num_tokens": 42897268.0,
|
|
"step": 23320
|
|
},
|
|
{
|
|
"entropy": 5.388361406326294,
|
|
"epoch": 1.948296024056131,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004618686913643264,
|
|
"loss": 4.7643,
|
|
"mean_token_accuracy": 0.22880604416131972,
|
|
"num_tokens": 42906186.0,
|
|
"step": 23325
|
|
},
|
|
{
|
|
"entropy": 5.3267804145812985,
|
|
"epoch": 1.948713665218844,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004618521085181421,
|
|
"loss": 4.7524,
|
|
"mean_token_accuracy": 0.22625206261873246,
|
|
"num_tokens": 42915457.0,
|
|
"step": 23330
|
|
},
|
|
{
|
|
"entropy": 5.391237497329712,
|
|
"epoch": 1.949131306381557,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00046183552240088683,
|
|
"loss": 4.869,
|
|
"mean_token_accuracy": 0.22179103046655654,
|
|
"num_tokens": 42925848.0,
|
|
"step": 23335
|
|
},
|
|
{
|
|
"entropy": 5.34342589378357,
|
|
"epoch": 1.94954894754427,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00046181893301285075,
|
|
"loss": 4.8397,
|
|
"mean_token_accuracy": 0.2269234076142311,
|
|
"num_tokens": 42936084.0,
|
|
"step": 23340
|
|
},
|
|
{
|
|
"entropy": 5.292256116867065,
|
|
"epoch": 1.949966588706983,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004618023403543245,
|
|
"loss": 4.7666,
|
|
"mean_token_accuracy": 0.2304437354207039,
|
|
"num_tokens": 42945303.0,
|
|
"step": 23345
|
|
},
|
|
{
|
|
"entropy": 5.282494306564331,
|
|
"epoch": 1.9503842298696958,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00046178574442559835,
|
|
"loss": 4.797,
|
|
"mean_token_accuracy": 0.21599603891372682,
|
|
"num_tokens": 42955144.0,
|
|
"step": 23350
|
|
},
|
|
{
|
|
"entropy": 5.379127931594849,
|
|
"epoch": 1.950801871032409,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004617691452269629,
|
|
"loss": 4.7551,
|
|
"mean_token_accuracy": 0.2259172424674034,
|
|
"num_tokens": 42964492.0,
|
|
"step": 23355
|
|
},
|
|
{
|
|
"entropy": 5.321474647521972,
|
|
"epoch": 1.951219512195122,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004617525427587087,
|
|
"loss": 4.7887,
|
|
"mean_token_accuracy": 0.2287892296910286,
|
|
"num_tokens": 42973731.0,
|
|
"step": 23360
|
|
},
|
|
{
|
|
"entropy": 5.220123767852783,
|
|
"epoch": 1.951637153357835,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00046173593702112655,
|
|
"loss": 4.684,
|
|
"mean_token_accuracy": 0.23873729705810548,
|
|
"num_tokens": 42981892.0,
|
|
"step": 23365
|
|
},
|
|
{
|
|
"entropy": 5.319464445114136,
|
|
"epoch": 1.952054794520548,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000461719328014507,
|
|
"loss": 4.7597,
|
|
"mean_token_accuracy": 0.23007899671792983,
|
|
"num_tokens": 42990877.0,
|
|
"step": 23370
|
|
},
|
|
{
|
|
"entropy": 5.45333161354065,
|
|
"epoch": 1.9524724356832608,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00046170271573914084,
|
|
"loss": 4.9369,
|
|
"mean_token_accuracy": 0.21121878921985626,
|
|
"num_tokens": 43001371.0,
|
|
"step": 23375
|
|
},
|
|
{
|
|
"entropy": 5.36731972694397,
|
|
"epoch": 1.952890076845974,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00046168610019531894,
|
|
"loss": 4.7465,
|
|
"mean_token_accuracy": 0.22677151411771773,
|
|
"num_tokens": 43010651.0,
|
|
"step": 23380
|
|
},
|
|
{
|
|
"entropy": 5.351078605651855,
|
|
"epoch": 1.9533077180086869,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004616694813833322,
|
|
"loss": 4.7824,
|
|
"mean_token_accuracy": 0.23043666183948516,
|
|
"num_tokens": 43018883.0,
|
|
"step": 23385
|
|
},
|
|
{
|
|
"entropy": 5.3313055515289305,
|
|
"epoch": 1.9537253591714,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004616528593034713,
|
|
"loss": 4.7863,
|
|
"mean_token_accuracy": 0.22236724495887755,
|
|
"num_tokens": 43027760.0,
|
|
"step": 23390
|
|
},
|
|
{
|
|
"entropy": 5.33609299659729,
|
|
"epoch": 1.954143000334113,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004616362339560276,
|
|
"loss": 4.7292,
|
|
"mean_token_accuracy": 0.23094047755002975,
|
|
"num_tokens": 43038227.0,
|
|
"step": 23395
|
|
},
|
|
{
|
|
"entropy": 5.277017211914062,
|
|
"epoch": 1.954560641496826,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00046161960534129193,
|
|
"loss": 4.6758,
|
|
"mean_token_accuracy": 0.2295100897550583,
|
|
"num_tokens": 43046792.0,
|
|
"step": 23400
|
|
},
|
|
{
|
|
"entropy": 5.312854290008545,
|
|
"epoch": 1.954978282659539,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004616029734595555,
|
|
"loss": 4.7618,
|
|
"mean_token_accuracy": 0.2150987505912781,
|
|
"num_tokens": 43055895.0,
|
|
"step": 23405
|
|
},
|
|
{
|
|
"entropy": 5.3673238277435305,
|
|
"epoch": 1.9553959238222518,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004615863383111093,
|
|
"loss": 4.8484,
|
|
"mean_token_accuracy": 0.21901768147945405,
|
|
"num_tokens": 43065631.0,
|
|
"step": 23410
|
|
},
|
|
{
|
|
"entropy": 5.457545280456543,
|
|
"epoch": 1.955813564984965,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004615696998962447,
|
|
"loss": 4.9053,
|
|
"mean_token_accuracy": 0.21419569700956345,
|
|
"num_tokens": 43074757.0,
|
|
"step": 23415
|
|
},
|
|
{
|
|
"entropy": 5.402120542526245,
|
|
"epoch": 1.9562312061476779,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004615530582152529,
|
|
"loss": 4.8317,
|
|
"mean_token_accuracy": 0.22629834711551666,
|
|
"num_tokens": 43084472.0,
|
|
"step": 23420
|
|
},
|
|
{
|
|
"entropy": 5.31369161605835,
|
|
"epoch": 1.956648847310391,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004615364132684253,
|
|
"loss": 4.8416,
|
|
"mean_token_accuracy": 0.21614070534706115,
|
|
"num_tokens": 43092726.0,
|
|
"step": 23425
|
|
},
|
|
{
|
|
"entropy": 5.339618110656739,
|
|
"epoch": 1.957066488473104,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004615197650560532,
|
|
"loss": 4.7669,
|
|
"mean_token_accuracy": 0.22490481436252593,
|
|
"num_tokens": 43101481.0,
|
|
"step": 23430
|
|
},
|
|
{
|
|
"entropy": 5.3540433883667,
|
|
"epoch": 1.9574841296358167,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004615031135784282,
|
|
"loss": 4.7587,
|
|
"mean_token_accuracy": 0.22890387624502181,
|
|
"num_tokens": 43110484.0,
|
|
"step": 23435
|
|
},
|
|
{
|
|
"entropy": 5.36774697303772,
|
|
"epoch": 1.95790177079853,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00046148645883584155,
|
|
"loss": 4.9142,
|
|
"mean_token_accuracy": 0.21900394260883332,
|
|
"num_tokens": 43121532.0,
|
|
"step": 23440
|
|
},
|
|
{
|
|
"entropy": 5.354042053222656,
|
|
"epoch": 1.9583194119612428,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004614698008285851,
|
|
"loss": 4.7634,
|
|
"mean_token_accuracy": 0.23104583472013474,
|
|
"num_tokens": 43130976.0,
|
|
"step": 23445
|
|
},
|
|
{
|
|
"entropy": 5.371915531158447,
|
|
"epoch": 1.9587370531239559,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00046145313955695027,
|
|
"loss": 4.8689,
|
|
"mean_token_accuracy": 0.2163427084684372,
|
|
"num_tokens": 43139907.0,
|
|
"step": 23450
|
|
},
|
|
{
|
|
"entropy": 5.441877222061157,
|
|
"epoch": 1.9591546942866689,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004614364750212288,
|
|
"loss": 4.8803,
|
|
"mean_token_accuracy": 0.2214074492454529,
|
|
"num_tokens": 43149141.0,
|
|
"step": 23455
|
|
},
|
|
{
|
|
"entropy": 5.417590141296387,
|
|
"epoch": 1.959572335449382,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00046141980722171246,
|
|
"loss": 4.8375,
|
|
"mean_token_accuracy": 0.2236052632331848,
|
|
"num_tokens": 43158206.0,
|
|
"step": 23460
|
|
},
|
|
{
|
|
"entropy": 5.328678750991822,
|
|
"epoch": 1.959989976612095,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00046140313615869287,
|
|
"loss": 4.8704,
|
|
"mean_token_accuracy": 0.22186478078365326,
|
|
"num_tokens": 43168365.0,
|
|
"step": 23465
|
|
},
|
|
{
|
|
"entropy": 5.261471796035766,
|
|
"epoch": 1.9604076177748078,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00046138646183246213,
|
|
"loss": 4.6857,
|
|
"mean_token_accuracy": 0.22895148545503616,
|
|
"num_tokens": 43176907.0,
|
|
"step": 23470
|
|
},
|
|
{
|
|
"entropy": 5.298178768157959,
|
|
"epoch": 1.960825258937521,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000461369784243312,
|
|
"loss": 4.7149,
|
|
"mean_token_accuracy": 0.2254865676164627,
|
|
"num_tokens": 43186978.0,
|
|
"step": 23475
|
|
},
|
|
{
|
|
"entropy": 5.285488700866699,
|
|
"epoch": 1.9612429001002338,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00046135310339153455,
|
|
"loss": 4.8141,
|
|
"mean_token_accuracy": 0.22579879611730574,
|
|
"num_tokens": 43196502.0,
|
|
"step": 23480
|
|
},
|
|
{
|
|
"entropy": 5.424386215209961,
|
|
"epoch": 1.9616605412629469,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004613364192774216,
|
|
"loss": 4.9077,
|
|
"mean_token_accuracy": 0.21187632232904435,
|
|
"num_tokens": 43205555.0,
|
|
"step": 23485
|
|
},
|
|
{
|
|
"entropy": 5.368859767913818,
|
|
"epoch": 1.96207818242566,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00046131973190126536,
|
|
"loss": 4.7692,
|
|
"mean_token_accuracy": 0.22475816309452057,
|
|
"num_tokens": 43214043.0,
|
|
"step": 23490
|
|
},
|
|
{
|
|
"entropy": 5.356074571609497,
|
|
"epoch": 1.9624958235883727,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00046130304126335795,
|
|
"loss": 4.8557,
|
|
"mean_token_accuracy": 0.2150520473718643,
|
|
"num_tokens": 43223483.0,
|
|
"step": 23495
|
|
},
|
|
{
|
|
"entropy": 5.369622087478637,
|
|
"epoch": 1.962913464751086,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004612863473639915,
|
|
"loss": 4.7999,
|
|
"mean_token_accuracy": 0.2297448992729187,
|
|
"num_tokens": 43231962.0,
|
|
"step": 23500
|
|
},
|
|
{
|
|
"entropy": 5.328850984573364,
|
|
"epoch": 1.9633311059137988,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00046126965020345834,
|
|
"loss": 4.7895,
|
|
"mean_token_accuracy": 0.228324793279171,
|
|
"num_tokens": 43240532.0,
|
|
"step": 23505
|
|
},
|
|
{
|
|
"entropy": 5.29225378036499,
|
|
"epoch": 1.9637487470765118,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004612529497820508,
|
|
"loss": 4.7335,
|
|
"mean_token_accuracy": 0.23055913895368577,
|
|
"num_tokens": 43249867.0,
|
|
"step": 23510
|
|
},
|
|
{
|
|
"entropy": 5.366824102401734,
|
|
"epoch": 1.9641663882392248,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004612362461000611,
|
|
"loss": 4.8664,
|
|
"mean_token_accuracy": 0.21957335472106934,
|
|
"num_tokens": 43259393.0,
|
|
"step": 23515
|
|
},
|
|
{
|
|
"entropy": 5.449867916107178,
|
|
"epoch": 1.9645840294019379,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00046121953915778175,
|
|
"loss": 4.8843,
|
|
"mean_token_accuracy": 0.22213741540908813,
|
|
"num_tokens": 43269012.0,
|
|
"step": 23520
|
|
},
|
|
{
|
|
"entropy": 5.37756028175354,
|
|
"epoch": 1.965001670564651,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004612028289555052,
|
|
"loss": 4.8417,
|
|
"mean_token_accuracy": 0.21969367414712906,
|
|
"num_tokens": 43278032.0,
|
|
"step": 23525
|
|
},
|
|
{
|
|
"entropy": 5.371086978912354,
|
|
"epoch": 1.9654193117273637,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00046118611549352407,
|
|
"loss": 4.8246,
|
|
"mean_token_accuracy": 0.22688431292772293,
|
|
"num_tokens": 43287352.0,
|
|
"step": 23530
|
|
},
|
|
{
|
|
"entropy": 5.436115550994873,
|
|
"epoch": 1.965836952890077,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004611693987721308,
|
|
"loss": 4.8753,
|
|
"mean_token_accuracy": 0.21752074360847473,
|
|
"num_tokens": 43297048.0,
|
|
"step": 23535
|
|
},
|
|
{
|
|
"entropy": 5.339462471008301,
|
|
"epoch": 1.9662545940527898,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00046115267879161823,
|
|
"loss": 4.772,
|
|
"mean_token_accuracy": 0.22788261920213698,
|
|
"num_tokens": 43306461.0,
|
|
"step": 23540
|
|
},
|
|
{
|
|
"entropy": 5.358826398849487,
|
|
"epoch": 1.9666722352155028,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00046113595555227885,
|
|
"loss": 4.8006,
|
|
"mean_token_accuracy": 0.2244020953774452,
|
|
"num_tokens": 43315906.0,
|
|
"step": 23545
|
|
},
|
|
{
|
|
"entropy": 5.409051132202149,
|
|
"epoch": 1.9670898763782159,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004611192290544055,
|
|
"loss": 4.8518,
|
|
"mean_token_accuracy": 0.22444436252117156,
|
|
"num_tokens": 43325433.0,
|
|
"step": 23550
|
|
},
|
|
{
|
|
"entropy": 5.427072763442993,
|
|
"epoch": 1.9675075175409287,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00046110249929829104,
|
|
"loss": 4.8761,
|
|
"mean_token_accuracy": 0.21794021427631377,
|
|
"num_tokens": 43333510.0,
|
|
"step": 23555
|
|
},
|
|
{
|
|
"entropy": 5.3321412086486815,
|
|
"epoch": 1.967925158703642,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004610857662842283,
|
|
"loss": 4.7567,
|
|
"mean_token_accuracy": 0.22663537561893463,
|
|
"num_tokens": 43342985.0,
|
|
"step": 23560
|
|
},
|
|
{
|
|
"entropy": 5.413552284240723,
|
|
"epoch": 1.9683427998663547,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004610690300125103,
|
|
"loss": 4.785,
|
|
"mean_token_accuracy": 0.22695326656103135,
|
|
"num_tokens": 43352894.0,
|
|
"step": 23565
|
|
},
|
|
{
|
|
"entropy": 5.351281452178955,
|
|
"epoch": 1.9687604410290678,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00046105229048342994,
|
|
"loss": 4.8278,
|
|
"mean_token_accuracy": 0.21720911413431168,
|
|
"num_tokens": 43362667.0,
|
|
"step": 23570
|
|
},
|
|
{
|
|
"entropy": 5.344320297241211,
|
|
"epoch": 1.9691780821917808,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00046103554769728026,
|
|
"loss": 4.7818,
|
|
"mean_token_accuracy": 0.22511996924877167,
|
|
"num_tokens": 43372212.0,
|
|
"step": 23575
|
|
},
|
|
{
|
|
"entropy": 5.327666282653809,
|
|
"epoch": 1.9695957233544938,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004610188016543544,
|
|
"loss": 4.7609,
|
|
"mean_token_accuracy": 0.22924778759479522,
|
|
"num_tokens": 43381958.0,
|
|
"step": 23580
|
|
},
|
|
{
|
|
"entropy": 5.412600469589234,
|
|
"epoch": 1.9700133645172069,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00046100205235494554,
|
|
"loss": 4.8429,
|
|
"mean_token_accuracy": 0.22086251825094222,
|
|
"num_tokens": 43391641.0,
|
|
"step": 23585
|
|
},
|
|
{
|
|
"entropy": 5.400491428375244,
|
|
"epoch": 1.9704310056799197,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00046098529979934677,
|
|
"loss": 4.8284,
|
|
"mean_token_accuracy": 0.21920215636491774,
|
|
"num_tokens": 43401261.0,
|
|
"step": 23590
|
|
},
|
|
{
|
|
"entropy": 5.308386135101318,
|
|
"epoch": 1.970848646842633,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004609685439878515,
|
|
"loss": 4.7169,
|
|
"mean_token_accuracy": 0.22406335473060607,
|
|
"num_tokens": 43409829.0,
|
|
"step": 23595
|
|
},
|
|
{
|
|
"entropy": 5.306794738769531,
|
|
"epoch": 1.9712662880053458,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000460951784920753,
|
|
"loss": 4.7449,
|
|
"mean_token_accuracy": 0.2267272502183914,
|
|
"num_tokens": 43418536.0,
|
|
"step": 23600
|
|
},
|
|
{
|
|
"entropy": 5.325385904312133,
|
|
"epoch": 1.9716839291680588,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004609350225983447,
|
|
"loss": 4.7035,
|
|
"mean_token_accuracy": 0.22881337255239487,
|
|
"num_tokens": 43427667.0,
|
|
"step": 23605
|
|
},
|
|
{
|
|
"entropy": 5.3463012218475345,
|
|
"epoch": 1.9721015703307718,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00046091825702092,
|
|
"loss": 4.7597,
|
|
"mean_token_accuracy": 0.2277602732181549,
|
|
"num_tokens": 43436986.0,
|
|
"step": 23610
|
|
},
|
|
{
|
|
"entropy": 5.383033895492554,
|
|
"epoch": 1.9725192114934846,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00046090148818877244,
|
|
"loss": 4.8791,
|
|
"mean_token_accuracy": 0.213380366563797,
|
|
"num_tokens": 43446969.0,
|
|
"step": 23615
|
|
},
|
|
{
|
|
"entropy": 5.401537036895752,
|
|
"epoch": 1.972936852656198,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004608847161021955,
|
|
"loss": 4.8953,
|
|
"mean_token_accuracy": 0.22157416939735414,
|
|
"num_tokens": 43456160.0,
|
|
"step": 23620
|
|
},
|
|
{
|
|
"entropy": 5.437594699859619,
|
|
"epoch": 1.9733544938189107,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000460867940761483,
|
|
"loss": 4.8641,
|
|
"mean_token_accuracy": 0.21657398343086243,
|
|
"num_tokens": 43465767.0,
|
|
"step": 23625
|
|
},
|
|
{
|
|
"entropy": 5.431388282775879,
|
|
"epoch": 1.9737721349816237,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004608511621669283,
|
|
"loss": 4.8622,
|
|
"mean_token_accuracy": 0.21838846504688264,
|
|
"num_tokens": 43474493.0,
|
|
"step": 23630
|
|
},
|
|
{
|
|
"entropy": 5.330583715438843,
|
|
"epoch": 1.9741897761443368,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00046083438031882534,
|
|
"loss": 4.823,
|
|
"mean_token_accuracy": 0.22408851534128188,
|
|
"num_tokens": 43483410.0,
|
|
"step": 23635
|
|
},
|
|
{
|
|
"entropy": 5.323192071914673,
|
|
"epoch": 1.9746074173070498,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004608175952174679,
|
|
"loss": 4.729,
|
|
"mean_token_accuracy": 0.22723390012979508,
|
|
"num_tokens": 43492532.0,
|
|
"step": 23640
|
|
},
|
|
{
|
|
"entropy": 5.323537731170655,
|
|
"epoch": 1.9750250584697628,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004608008068631498,
|
|
"loss": 4.7509,
|
|
"mean_token_accuracy": 0.23312069177627565,
|
|
"num_tokens": 43501282.0,
|
|
"step": 23645
|
|
},
|
|
{
|
|
"entropy": 5.344193696975708,
|
|
"epoch": 1.9754426996324757,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00046078401525616493,
|
|
"loss": 4.7881,
|
|
"mean_token_accuracy": 0.21815677285194396,
|
|
"num_tokens": 43510355.0,
|
|
"step": 23650
|
|
},
|
|
{
|
|
"entropy": 5.3428953170776365,
|
|
"epoch": 1.975860340795189,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004607672203968072,
|
|
"loss": 4.7879,
|
|
"mean_token_accuracy": 0.2253160834312439,
|
|
"num_tokens": 43519179.0,
|
|
"step": 23655
|
|
},
|
|
{
|
|
"entropy": 5.358962154388427,
|
|
"epoch": 1.9762779819579017,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00046075042228537074,
|
|
"loss": 4.8254,
|
|
"mean_token_accuracy": 0.21866993904113768,
|
|
"num_tokens": 43528306.0,
|
|
"step": 23660
|
|
},
|
|
{
|
|
"entropy": 5.485353660583496,
|
|
"epoch": 1.9766956231206148,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004607336209221494,
|
|
"loss": 4.9249,
|
|
"mean_token_accuracy": 0.21200798600912094,
|
|
"num_tokens": 43537075.0,
|
|
"step": 23665
|
|
},
|
|
{
|
|
"entropy": 5.337583732604981,
|
|
"epoch": 1.9771132642833278,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004607168163074376,
|
|
"loss": 4.8208,
|
|
"mean_token_accuracy": 0.22213230431079864,
|
|
"num_tokens": 43545356.0,
|
|
"step": 23670
|
|
},
|
|
{
|
|
"entropy": 5.374931144714355,
|
|
"epoch": 1.9775309054460406,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004607000084415294,
|
|
"loss": 4.8633,
|
|
"mean_token_accuracy": 0.21985728144645691,
|
|
"num_tokens": 43555012.0,
|
|
"step": 23675
|
|
},
|
|
{
|
|
"entropy": 5.408016633987427,
|
|
"epoch": 1.9779485466087539,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00046068319732471894,
|
|
"loss": 4.9017,
|
|
"mean_token_accuracy": 0.21446389108896255,
|
|
"num_tokens": 43565245.0,
|
|
"step": 23680
|
|
},
|
|
{
|
|
"entropy": 5.473918199539185,
|
|
"epoch": 1.9783661877714667,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004606663829573006,
|
|
"loss": 4.9598,
|
|
"mean_token_accuracy": 0.21176216304302214,
|
|
"num_tokens": 43574246.0,
|
|
"step": 23685
|
|
},
|
|
{
|
|
"entropy": 5.213395309448242,
|
|
"epoch": 1.9787838289341797,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004606495653395688,
|
|
"loss": 4.6108,
|
|
"mean_token_accuracy": 0.24190932959318162,
|
|
"num_tokens": 43582494.0,
|
|
"step": 23690
|
|
},
|
|
{
|
|
"entropy": 5.367194747924804,
|
|
"epoch": 1.9792014700968927,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004606327444718179,
|
|
"loss": 4.8681,
|
|
"mean_token_accuracy": 0.2224407374858856,
|
|
"num_tokens": 43593289.0,
|
|
"step": 23695
|
|
},
|
|
{
|
|
"entropy": 5.3527933120727536,
|
|
"epoch": 1.9796191112596058,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004606159203543423,
|
|
"loss": 4.7675,
|
|
"mean_token_accuracy": 0.2310807466506958,
|
|
"num_tokens": 43602062.0,
|
|
"step": 23700
|
|
},
|
|
{
|
|
"entropy": 5.4164231300354,
|
|
"epoch": 1.9800367524223188,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004605990929874366,
|
|
"loss": 4.857,
|
|
"mean_token_accuracy": 0.21754234731197358,
|
|
"num_tokens": 43610830.0,
|
|
"step": 23705
|
|
},
|
|
{
|
|
"entropy": 5.425853729248047,
|
|
"epoch": 1.9804543935850316,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004605822623713954,
|
|
"loss": 4.8373,
|
|
"mean_token_accuracy": 0.21902762204408646,
|
|
"num_tokens": 43619656.0,
|
|
"step": 23710
|
|
},
|
|
{
|
|
"entropy": 5.381535482406616,
|
|
"epoch": 1.9808720347477449,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00046056542850651333,
|
|
"loss": 4.8425,
|
|
"mean_token_accuracy": 0.22491271942853927,
|
|
"num_tokens": 43629727.0,
|
|
"step": 23715
|
|
},
|
|
{
|
|
"entropy": 5.404457664489746,
|
|
"epoch": 1.9812896759104577,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000460548591393085,
|
|
"loss": 4.8853,
|
|
"mean_token_accuracy": 0.2271382287144661,
|
|
"num_tokens": 43638532.0,
|
|
"step": 23720
|
|
},
|
|
{
|
|
"entropy": 5.392353296279907,
|
|
"epoch": 1.9817073170731707,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00046053175103140533,
|
|
"loss": 4.893,
|
|
"mean_token_accuracy": 0.22489008605480193,
|
|
"num_tokens": 43647679.0,
|
|
"step": 23725
|
|
},
|
|
{
|
|
"entropy": 5.396480083465576,
|
|
"epoch": 1.9821249582358837,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00046051490742176894,
|
|
"loss": 4.7879,
|
|
"mean_token_accuracy": 0.2213339701294899,
|
|
"num_tokens": 43656340.0,
|
|
"step": 23730
|
|
},
|
|
{
|
|
"entropy": 5.344333028793335,
|
|
"epoch": 1.9825425993985966,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004604980605644708,
|
|
"loss": 4.7423,
|
|
"mean_token_accuracy": 0.2210963934659958,
|
|
"num_tokens": 43665721.0,
|
|
"step": 23735
|
|
},
|
|
{
|
|
"entropy": 5.367488193511963,
|
|
"epoch": 1.9829602405613098,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004604812104598059,
|
|
"loss": 4.8217,
|
|
"mean_token_accuracy": 0.22413640916347505,
|
|
"num_tokens": 43674640.0,
|
|
"step": 23740
|
|
},
|
|
{
|
|
"entropy": 5.392829656600952,
|
|
"epoch": 1.9833778817240226,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004604643571080691,
|
|
"loss": 4.8167,
|
|
"mean_token_accuracy": 0.22182524651288987,
|
|
"num_tokens": 43683080.0,
|
|
"step": 23745
|
|
},
|
|
{
|
|
"entropy": 5.342178392410278,
|
|
"epoch": 1.9837955228867357,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00046044750050955546,
|
|
"loss": 4.7476,
|
|
"mean_token_accuracy": 0.23004566133022308,
|
|
"num_tokens": 43691259.0,
|
|
"step": 23750
|
|
},
|
|
{
|
|
"entropy": 5.339042329788208,
|
|
"epoch": 1.9842131640494487,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00046043064066456015,
|
|
"loss": 4.7928,
|
|
"mean_token_accuracy": 0.22971555441617966,
|
|
"num_tokens": 43699881.0,
|
|
"step": 23755
|
|
},
|
|
{
|
|
"entropy": 5.320912075042725,
|
|
"epoch": 1.9846308052121617,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00046041377757337826,
|
|
"loss": 4.8037,
|
|
"mean_token_accuracy": 0.22111751437187194,
|
|
"num_tokens": 43708742.0,
|
|
"step": 23760
|
|
},
|
|
{
|
|
"entropy": 5.345516729354858,
|
|
"epoch": 1.9850484463748748,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00046039691123630496,
|
|
"loss": 4.7874,
|
|
"mean_token_accuracy": 0.22110930383205413,
|
|
"num_tokens": 43718450.0,
|
|
"step": 23765
|
|
},
|
|
{
|
|
"entropy": 5.320247459411621,
|
|
"epoch": 1.9854660875375876,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00046038004165363554,
|
|
"loss": 4.7497,
|
|
"mean_token_accuracy": 0.21757252365350724,
|
|
"num_tokens": 43728340.0,
|
|
"step": 23770
|
|
},
|
|
{
|
|
"entropy": 5.278365278244019,
|
|
"epoch": 1.9858837287003008,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00046036316882566545,
|
|
"loss": 4.7227,
|
|
"mean_token_accuracy": 0.22300610542297364,
|
|
"num_tokens": 43737287.0,
|
|
"step": 23775
|
|
},
|
|
{
|
|
"entropy": 5.289267444610596,
|
|
"epoch": 1.9863013698630136,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00046034629275268997,
|
|
"loss": 4.7293,
|
|
"mean_token_accuracy": 0.23359944224357604,
|
|
"num_tokens": 43745899.0,
|
|
"step": 23780
|
|
},
|
|
{
|
|
"entropy": 5.416254663467408,
|
|
"epoch": 1.9867190110257267,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00046032941343500443,
|
|
"loss": 4.882,
|
|
"mean_token_accuracy": 0.20914383381605148,
|
|
"num_tokens": 43755109.0,
|
|
"step": 23785
|
|
},
|
|
{
|
|
"entropy": 5.335477495193482,
|
|
"epoch": 1.9871366521884397,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00046031253087290455,
|
|
"loss": 4.7098,
|
|
"mean_token_accuracy": 0.23170425444841386,
|
|
"num_tokens": 43764216.0,
|
|
"step": 23790
|
|
},
|
|
{
|
|
"entropy": 5.317900514602661,
|
|
"epoch": 1.9875542933511525,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00046029564506668567,
|
|
"loss": 4.7529,
|
|
"mean_token_accuracy": 0.2182533398270607,
|
|
"num_tokens": 43773267.0,
|
|
"step": 23795
|
|
},
|
|
{
|
|
"entropy": 5.4279858589172365,
|
|
"epoch": 1.9879719345138658,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00046027875601664355,
|
|
"loss": 4.8939,
|
|
"mean_token_accuracy": 0.21504072993993759,
|
|
"num_tokens": 43782558.0,
|
|
"step": 23800
|
|
},
|
|
{
|
|
"entropy": 5.410836839675904,
|
|
"epoch": 1.9883895756765786,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004602618637230737,
|
|
"loss": 4.837,
|
|
"mean_token_accuracy": 0.21867407560348512,
|
|
"num_tokens": 43791861.0,
|
|
"step": 23805
|
|
},
|
|
{
|
|
"entropy": 5.3835320472717285,
|
|
"epoch": 1.9888072168392918,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000460244968186272,
|
|
"loss": 4.7521,
|
|
"mean_token_accuracy": 0.2262359231710434,
|
|
"num_tokens": 43801064.0,
|
|
"step": 23810
|
|
},
|
|
{
|
|
"entropy": 5.342006492614746,
|
|
"epoch": 1.9892248580020047,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00046022806940653415,
|
|
"loss": 4.7753,
|
|
"mean_token_accuracy": 0.22725430577993394,
|
|
"num_tokens": 43810159.0,
|
|
"step": 23815
|
|
},
|
|
{
|
|
"entropy": 5.402822208404541,
|
|
"epoch": 1.9896424991647177,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000460211167384156,
|
|
"loss": 4.8492,
|
|
"mean_token_accuracy": 0.22010598927736283,
|
|
"num_tokens": 43819056.0,
|
|
"step": 23820
|
|
},
|
|
{
|
|
"entropy": 5.358877515792846,
|
|
"epoch": 1.9900601403274307,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00046019426211943334,
|
|
"loss": 4.7954,
|
|
"mean_token_accuracy": 0.22712500840425492,
|
|
"num_tokens": 43828024.0,
|
|
"step": 23825
|
|
},
|
|
{
|
|
"entropy": 5.364017629623413,
|
|
"epoch": 1.9904777814901435,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004601773536126623,
|
|
"loss": 4.7183,
|
|
"mean_token_accuracy": 0.23256685584783554,
|
|
"num_tokens": 43836915.0,
|
|
"step": 23830
|
|
},
|
|
{
|
|
"entropy": 5.3264342784881595,
|
|
"epoch": 1.9908954226528568,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004601604418641387,
|
|
"loss": 4.7812,
|
|
"mean_token_accuracy": 0.22535625994205474,
|
|
"num_tokens": 43845661.0,
|
|
"step": 23835
|
|
},
|
|
{
|
|
"entropy": 5.402400493621826,
|
|
"epoch": 1.9913130638155696,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00046014352687415866,
|
|
"loss": 4.8684,
|
|
"mean_token_accuracy": 0.21913740783929825,
|
|
"num_tokens": 43854876.0,
|
|
"step": 23840
|
|
},
|
|
{
|
|
"entropy": 5.314511728286743,
|
|
"epoch": 1.9917307049782826,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00046012660864301846,
|
|
"loss": 4.7637,
|
|
"mean_token_accuracy": 0.22802350372076036,
|
|
"num_tokens": 43864750.0,
|
|
"step": 23845
|
|
},
|
|
{
|
|
"entropy": 5.384498357772827,
|
|
"epoch": 1.9921483461409957,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00046010968717101404,
|
|
"loss": 4.8776,
|
|
"mean_token_accuracy": 0.21939350962638854,
|
|
"num_tokens": 43874889.0,
|
|
"step": 23850
|
|
},
|
|
{
|
|
"entropy": 5.350533723831177,
|
|
"epoch": 1.9925659873037087,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00046009276245844176,
|
|
"loss": 4.7718,
|
|
"mean_token_accuracy": 0.2203314110636711,
|
|
"num_tokens": 43884462.0,
|
|
"step": 23855
|
|
},
|
|
{
|
|
"entropy": 5.32055630683899,
|
|
"epoch": 1.9929836284664217,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004600758345055979,
|
|
"loss": 4.8026,
|
|
"mean_token_accuracy": 0.21856709569692612,
|
|
"num_tokens": 43893739.0,
|
|
"step": 23860
|
|
},
|
|
{
|
|
"entropy": 5.378103971481323,
|
|
"epoch": 1.9934012696291346,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00046005890331277875,
|
|
"loss": 4.8388,
|
|
"mean_token_accuracy": 0.22133982181549072,
|
|
"num_tokens": 43904172.0,
|
|
"step": 23865
|
|
},
|
|
{
|
|
"entropy": 5.409279251098633,
|
|
"epoch": 1.9938189107918478,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004600419688802807,
|
|
"loss": 4.8499,
|
|
"mean_token_accuracy": 0.22419564723968505,
|
|
"num_tokens": 43912824.0,
|
|
"step": 23870
|
|
},
|
|
{
|
|
"entropy": 5.329760217666626,
|
|
"epoch": 1.9942365519545606,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00046002503120840037,
|
|
"loss": 4.7297,
|
|
"mean_token_accuracy": 0.2243644416332245,
|
|
"num_tokens": 43921704.0,
|
|
"step": 23875
|
|
},
|
|
{
|
|
"entropy": 5.334721183776855,
|
|
"epoch": 1.9946541931172737,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000460008090297434,
|
|
"loss": 4.784,
|
|
"mean_token_accuracy": 0.2226139336824417,
|
|
"num_tokens": 43930400.0,
|
|
"step": 23880
|
|
},
|
|
{
|
|
"entropy": 5.291702032089233,
|
|
"epoch": 1.9950718342799867,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00045999114614767847,
|
|
"loss": 4.7056,
|
|
"mean_token_accuracy": 0.2314440965652466,
|
|
"num_tokens": 43939623.0,
|
|
"step": 23885
|
|
},
|
|
{
|
|
"entropy": 5.378604459762573,
|
|
"epoch": 1.9954894754426995,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004599741987594302,
|
|
"loss": 4.82,
|
|
"mean_token_accuracy": 0.2215191975235939,
|
|
"num_tokens": 43948902.0,
|
|
"step": 23890
|
|
},
|
|
{
|
|
"entropy": 5.365645217895508,
|
|
"epoch": 1.9959071166054128,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004599572481329859,
|
|
"loss": 4.8175,
|
|
"mean_token_accuracy": 0.22230013608932495,
|
|
"num_tokens": 43958747.0,
|
|
"step": 23895
|
|
},
|
|
{
|
|
"entropy": 5.39975528717041,
|
|
"epoch": 1.9963247577681256,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004599402942686423,
|
|
"loss": 4.9034,
|
|
"mean_token_accuracy": 0.21592571288347245,
|
|
"num_tokens": 43968766.0,
|
|
"step": 23900
|
|
},
|
|
{
|
|
"entropy": 5.3818662643432615,
|
|
"epoch": 1.9967423989308386,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004599233371666963,
|
|
"loss": 4.781,
|
|
"mean_token_accuracy": 0.22798403948545456,
|
|
"num_tokens": 43978212.0,
|
|
"step": 23905
|
|
},
|
|
{
|
|
"entropy": 5.379498720169067,
|
|
"epoch": 1.9971600400935516,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004599063768274447,
|
|
"loss": 4.7917,
|
|
"mean_token_accuracy": 0.2227143108844757,
|
|
"num_tokens": 43987167.0,
|
|
"step": 23910
|
|
},
|
|
{
|
|
"entropy": 5.359171581268311,
|
|
"epoch": 1.9975776812562647,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004598894132511843,
|
|
"loss": 4.7246,
|
|
"mean_token_accuracy": 0.23044110387563704,
|
|
"num_tokens": 43995405.0,
|
|
"step": 23915
|
|
},
|
|
{
|
|
"entropy": 5.339365386962891,
|
|
"epoch": 1.9979953224189777,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004598724464382123,
|
|
"loss": 4.8139,
|
|
"mean_token_accuracy": 0.22811462730169296,
|
|
"num_tokens": 44004062.0,
|
|
"step": 23920
|
|
},
|
|
{
|
|
"entropy": 5.376807498931885,
|
|
"epoch": 1.9984129635816905,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00045985547638882553,
|
|
"loss": 4.8474,
|
|
"mean_token_accuracy": 0.22434969544410704,
|
|
"num_tokens": 44013911.0,
|
|
"step": 23925
|
|
},
|
|
{
|
|
"entropy": 5.368422746658325,
|
|
"epoch": 1.9988306047444038,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00045983850310332117,
|
|
"loss": 4.8366,
|
|
"mean_token_accuracy": 0.22264035791158676,
|
|
"num_tokens": 44023366.0,
|
|
"step": 23930
|
|
},
|
|
{
|
|
"entropy": 5.29221544265747,
|
|
"epoch": 1.9992482459071166,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004598215265819963,
|
|
"loss": 4.7172,
|
|
"mean_token_accuracy": 0.23087949603796004,
|
|
"num_tokens": 44031996.0,
|
|
"step": 23935
|
|
},
|
|
{
|
|
"entropy": 5.333285284042359,
|
|
"epoch": 1.9996658870698296,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004598045468251481,
|
|
"loss": 4.7257,
|
|
"mean_token_accuracy": 0.22596232295036317,
|
|
"num_tokens": 44041474.0,
|
|
"step": 23940
|
|
},
|
|
{
|
|
"entropy": 5.386372995376587,
|
|
"epoch": 2.0000835282325427,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004597875638330739,
|
|
"loss": 4.747,
|
|
"mean_token_accuracy": 0.2255583569407463,
|
|
"num_tokens": 44050213.0,
|
|
"step": 23945
|
|
},
|
|
{
|
|
"entropy": 5.28223876953125,
|
|
"epoch": 2.0005011693952555,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00045977057760607096,
|
|
"loss": 4.602,
|
|
"mean_token_accuracy": 0.24121437072753907,
|
|
"num_tokens": 44058686.0,
|
|
"step": 23950
|
|
},
|
|
{
|
|
"entropy": 5.328747034072876,
|
|
"epoch": 2.0009188105579687,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004597535881444366,
|
|
"loss": 4.7539,
|
|
"mean_token_accuracy": 0.23088586181402207,
|
|
"num_tokens": 44068316.0,
|
|
"step": 23955
|
|
},
|
|
{
|
|
"entropy": 5.380005025863648,
|
|
"epoch": 2.0013364517206815,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00045973659544846834,
|
|
"loss": 4.7425,
|
|
"mean_token_accuracy": 0.23199422359466554,
|
|
"num_tokens": 44077474.0,
|
|
"step": 23960
|
|
},
|
|
{
|
|
"entropy": 5.260367441177368,
|
|
"epoch": 2.001754092883395,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004597195995184637,
|
|
"loss": 4.6247,
|
|
"mean_token_accuracy": 0.23961276113986968,
|
|
"num_tokens": 44086334.0,
|
|
"step": 23965
|
|
},
|
|
{
|
|
"entropy": 5.392571830749512,
|
|
"epoch": 2.0021717340461076,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004597026003547201,
|
|
"loss": 4.7678,
|
|
"mean_token_accuracy": 0.22095165252685547,
|
|
"num_tokens": 44095543.0,
|
|
"step": 23970
|
|
},
|
|
{
|
|
"entropy": 5.4398175239562985,
|
|
"epoch": 2.0025893752088204,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00045968559795753493,
|
|
"loss": 4.876,
|
|
"mean_token_accuracy": 0.22549599409103394,
|
|
"num_tokens": 44105162.0,
|
|
"step": 23975
|
|
},
|
|
{
|
|
"entropy": 5.3794087886810305,
|
|
"epoch": 2.0030070163715337,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00045966859232720626,
|
|
"loss": 4.749,
|
|
"mean_token_accuracy": 0.22066006064414978,
|
|
"num_tokens": 44114087.0,
|
|
"step": 23980
|
|
},
|
|
{
|
|
"entropy": 5.438021469116211,
|
|
"epoch": 2.0034246575342465,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004596515834640316,
|
|
"loss": 4.9098,
|
|
"mean_token_accuracy": 0.2147020220756531,
|
|
"num_tokens": 44123186.0,
|
|
"step": 23985
|
|
},
|
|
{
|
|
"entropy": 5.374972248077393,
|
|
"epoch": 2.0038422986969597,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004596345713683086,
|
|
"loss": 4.757,
|
|
"mean_token_accuracy": 0.23102305680513383,
|
|
"num_tokens": 44132126.0,
|
|
"step": 23990
|
|
},
|
|
{
|
|
"entropy": 5.441461038589478,
|
|
"epoch": 2.0042599398596725,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00045961755604033536,
|
|
"loss": 4.831,
|
|
"mean_token_accuracy": 0.22062739431858064,
|
|
"num_tokens": 44141703.0,
|
|
"step": 23995
|
|
},
|
|
{
|
|
"entropy": 5.38232831954956,
|
|
"epoch": 2.0046775810223854,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004596005374804094,
|
|
"loss": 4.7238,
|
|
"mean_token_accuracy": 0.22293147891759874,
|
|
"num_tokens": 44150512.0,
|
|
"step": 24000
|
|
},
|
|
{
|
|
"epoch": 2.0046775810223854,
|
|
"eval_entropy": 5.061549203069098,
|
|
"eval_loss": 4.782820701599121,
|
|
"eval_mean_token_accuracy": 0.23597300898388668,
|
|
"eval_num_tokens": 44150512.0,
|
|
"eval_runtime": 20.9225,
|
|
"eval_samples_per_second": 1804.9,
|
|
"eval_steps_per_second": 225.642,
|
|
"step": 24000
|
|
},
|
|
{
|
|
"entropy": 5.397460079193115,
|
|
"epoch": 2.0050952221850986,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00045958351568882883,
|
|
"loss": 4.73,
|
|
"mean_token_accuracy": 0.2243843451142311,
|
|
"num_tokens": 44160209.0,
|
|
"step": 24005
|
|
},
|
|
{
|
|
"entropy": 5.415165090560913,
|
|
"epoch": 2.0055128633478114,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004595664906658917,
|
|
"loss": 4.7345,
|
|
"mean_token_accuracy": 0.22703062146902084,
|
|
"num_tokens": 44169005.0,
|
|
"step": 24010
|
|
},
|
|
{
|
|
"entropy": 5.3568809032440186,
|
|
"epoch": 2.0059305045105247,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00045954946241189606,
|
|
"loss": 4.802,
|
|
"mean_token_accuracy": 0.21714123487472534,
|
|
"num_tokens": 44178750.0,
|
|
"step": 24015
|
|
},
|
|
{
|
|
"entropy": 5.3828881740570065,
|
|
"epoch": 2.0063481456732375,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00045953243092713986,
|
|
"loss": 4.8459,
|
|
"mean_token_accuracy": 0.21500516384840013,
|
|
"num_tokens": 44188268.0,
|
|
"step": 24020
|
|
},
|
|
{
|
|
"entropy": 5.3432399272918705,
|
|
"epoch": 2.0067657868359507,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00045951539621192137,
|
|
"loss": 4.7049,
|
|
"mean_token_accuracy": 0.23089612275362015,
|
|
"num_tokens": 44197599.0,
|
|
"step": 24025
|
|
},
|
|
{
|
|
"entropy": 5.382998847961426,
|
|
"epoch": 2.0071834279986636,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004594983582665387,
|
|
"loss": 4.8933,
|
|
"mean_token_accuracy": 0.22339923083782195,
|
|
"num_tokens": 44207971.0,
|
|
"step": 24030
|
|
},
|
|
{
|
|
"entropy": 5.436226558685303,
|
|
"epoch": 2.0076010691613764,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004594813170912902,
|
|
"loss": 4.8034,
|
|
"mean_token_accuracy": 0.2174688071012497,
|
|
"num_tokens": 44217387.0,
|
|
"step": 24035
|
|
},
|
|
{
|
|
"entropy": 5.401952123641967,
|
|
"epoch": 2.0080187103240896,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00045946427268647424,
|
|
"loss": 4.7424,
|
|
"mean_token_accuracy": 0.22613875865936278,
|
|
"num_tokens": 44226103.0,
|
|
"step": 24040
|
|
},
|
|
{
|
|
"entropy": 5.337101459503174,
|
|
"epoch": 2.0084363514868024,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00045944722505238914,
|
|
"loss": 4.7331,
|
|
"mean_token_accuracy": 0.22056040316820144,
|
|
"num_tokens": 44236081.0,
|
|
"step": 24045
|
|
},
|
|
{
|
|
"entropy": 5.387843465805053,
|
|
"epoch": 2.0088539926495157,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00045943017418933324,
|
|
"loss": 4.7656,
|
|
"mean_token_accuracy": 0.2261873498558998,
|
|
"num_tokens": 44245934.0,
|
|
"step": 24050
|
|
},
|
|
{
|
|
"entropy": 5.358116149902344,
|
|
"epoch": 2.0092716338122285,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004594131200976053,
|
|
"loss": 4.7468,
|
|
"mean_token_accuracy": 0.22740954905748367,
|
|
"num_tokens": 44255629.0,
|
|
"step": 24055
|
|
},
|
|
{
|
|
"entropy": 5.349789333343506,
|
|
"epoch": 2.0096892749749413,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00045939606277750356,
|
|
"loss": 4.686,
|
|
"mean_token_accuracy": 0.2275781512260437,
|
|
"num_tokens": 44264954.0,
|
|
"step": 24060
|
|
},
|
|
{
|
|
"entropy": 5.31113977432251,
|
|
"epoch": 2.0101069161376546,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004593790022293269,
|
|
"loss": 4.6884,
|
|
"mean_token_accuracy": 0.23728768527507782,
|
|
"num_tokens": 44273739.0,
|
|
"step": 24065
|
|
},
|
|
{
|
|
"entropy": 5.353881072998047,
|
|
"epoch": 2.0105245573003674,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004593619384533738,
|
|
"loss": 4.853,
|
|
"mean_token_accuracy": 0.21391347646713257,
|
|
"num_tokens": 44283365.0,
|
|
"step": 24070
|
|
},
|
|
{
|
|
"entropy": 5.412335062026978,
|
|
"epoch": 2.0109421984630806,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00045934487144994306,
|
|
"loss": 4.7909,
|
|
"mean_token_accuracy": 0.22681202441453935,
|
|
"num_tokens": 44292257.0,
|
|
"step": 24075
|
|
},
|
|
{
|
|
"entropy": 5.523378610610962,
|
|
"epoch": 2.0113598396257935,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00045932780121933354,
|
|
"loss": 4.8855,
|
|
"mean_token_accuracy": 0.22068688422441482,
|
|
"num_tokens": 44302539.0,
|
|
"step": 24080
|
|
},
|
|
{
|
|
"entropy": 5.326548719406128,
|
|
"epoch": 2.0117774807885067,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004593107277618439,
|
|
"loss": 4.7104,
|
|
"mean_token_accuracy": 0.22136333584785461,
|
|
"num_tokens": 44311812.0,
|
|
"step": 24085
|
|
},
|
|
{
|
|
"entropy": 5.261226224899292,
|
|
"epoch": 2.0121951219512195,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004592936510777731,
|
|
"loss": 4.7174,
|
|
"mean_token_accuracy": 0.22941443771123887,
|
|
"num_tokens": 44321015.0,
|
|
"step": 24090
|
|
},
|
|
{
|
|
"entropy": 5.4312098026275635,
|
|
"epoch": 2.0126127631139323,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00045927657116742016,
|
|
"loss": 4.8167,
|
|
"mean_token_accuracy": 0.21469492614269256,
|
|
"num_tokens": 44330066.0,
|
|
"step": 24095
|
|
},
|
|
{
|
|
"entropy": 5.411472225189209,
|
|
"epoch": 2.0130304042766456,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000459259488031084,
|
|
"loss": 4.8811,
|
|
"mean_token_accuracy": 0.21876183450222014,
|
|
"num_tokens": 44339716.0,
|
|
"step": 24100
|
|
},
|
|
{
|
|
"entropy": 5.300905561447143,
|
|
"epoch": 2.0134480454393584,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004592424016690637,
|
|
"loss": 4.6371,
|
|
"mean_token_accuracy": 0.22976453006267547,
|
|
"num_tokens": 44348340.0,
|
|
"step": 24105
|
|
},
|
|
{
|
|
"entropy": 5.284408664703369,
|
|
"epoch": 2.0138656866020717,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00045922531208165843,
|
|
"loss": 4.7401,
|
|
"mean_token_accuracy": 0.22554926723241805,
|
|
"num_tokens": 44358045.0,
|
|
"step": 24110
|
|
},
|
|
{
|
|
"entropy": 5.362460517883301,
|
|
"epoch": 2.0142833277647845,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004592082192691673,
|
|
"loss": 4.7649,
|
|
"mean_token_accuracy": 0.22557685822248458,
|
|
"num_tokens": 44366962.0,
|
|
"step": 24115
|
|
},
|
|
{
|
|
"entropy": 5.309140634536743,
|
|
"epoch": 2.0147009689274973,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00045919112323188955,
|
|
"loss": 4.669,
|
|
"mean_token_accuracy": 0.23586303144693374,
|
|
"num_tokens": 44376178.0,
|
|
"step": 24120
|
|
},
|
|
{
|
|
"entropy": 5.420318222045898,
|
|
"epoch": 2.0151186100902105,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004591740239701244,
|
|
"loss": 4.7437,
|
|
"mean_token_accuracy": 0.22715017795562745,
|
|
"num_tokens": 44385271.0,
|
|
"step": 24125
|
|
},
|
|
{
|
|
"entropy": 5.362804317474366,
|
|
"epoch": 2.0155362512529233,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00045915692148417136,
|
|
"loss": 4.7108,
|
|
"mean_token_accuracy": 0.23504167795181274,
|
|
"num_tokens": 44394900.0,
|
|
"step": 24130
|
|
},
|
|
{
|
|
"entropy": 5.281431531906128,
|
|
"epoch": 2.0159538924156366,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004591398157743297,
|
|
"loss": 4.7168,
|
|
"mean_token_accuracy": 0.23153078109025954,
|
|
"num_tokens": 44403812.0,
|
|
"step": 24135
|
|
},
|
|
{
|
|
"entropy": 5.325395488739014,
|
|
"epoch": 2.0163715335783494,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00045912270684089903,
|
|
"loss": 4.7458,
|
|
"mean_token_accuracy": 0.22498483806848527,
|
|
"num_tokens": 44413301.0,
|
|
"step": 24140
|
|
},
|
|
{
|
|
"entropy": 5.361720848083496,
|
|
"epoch": 2.0167891747410627,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004591055946841786,
|
|
"loss": 4.6775,
|
|
"mean_token_accuracy": 0.2329782783985138,
|
|
"num_tokens": 44422334.0,
|
|
"step": 24145
|
|
},
|
|
{
|
|
"entropy": 5.4088818550109865,
|
|
"epoch": 2.0172068159037755,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00045908847930446815,
|
|
"loss": 5.0139,
|
|
"mean_token_accuracy": 0.21620095819234847,
|
|
"num_tokens": 44432914.0,
|
|
"step": 24150
|
|
},
|
|
{
|
|
"entropy": 5.356890630722046,
|
|
"epoch": 2.0176244570664883,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004590713607020674,
|
|
"loss": 4.6781,
|
|
"mean_token_accuracy": 0.2371186599135399,
|
|
"num_tokens": 44442372.0,
|
|
"step": 24155
|
|
},
|
|
{
|
|
"entropy": 5.349270296096802,
|
|
"epoch": 2.0180420982292016,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00045905423887727584,
|
|
"loss": 4.6622,
|
|
"mean_token_accuracy": 0.23429673463106154,
|
|
"num_tokens": 44450866.0,
|
|
"step": 24160
|
|
},
|
|
{
|
|
"entropy": 5.321485614776611,
|
|
"epoch": 2.0184597393919144,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004590371138303933,
|
|
"loss": 4.734,
|
|
"mean_token_accuracy": 0.22877553403377532,
|
|
"num_tokens": 44460224.0,
|
|
"step": 24165
|
|
},
|
|
{
|
|
"entropy": 5.3636024475097654,
|
|
"epoch": 2.0188773805546276,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004590199855617195,
|
|
"loss": 4.713,
|
|
"mean_token_accuracy": 0.23024595379829407,
|
|
"num_tokens": 44469231.0,
|
|
"step": 24170
|
|
},
|
|
{
|
|
"entropy": 5.355042600631714,
|
|
"epoch": 2.0192950217173404,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004590028540715544,
|
|
"loss": 4.6874,
|
|
"mean_token_accuracy": 0.23010991811752318,
|
|
"num_tokens": 44478415.0,
|
|
"step": 24175
|
|
},
|
|
{
|
|
"entropy": 5.333063173294067,
|
|
"epoch": 2.0197126628800532,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004589857193601978,
|
|
"loss": 4.7328,
|
|
"mean_token_accuracy": 0.23196582049131392,
|
|
"num_tokens": 44486648.0,
|
|
"step": 24180
|
|
},
|
|
{
|
|
"entropy": 5.356508445739746,
|
|
"epoch": 2.0201303040427665,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00045896858142794976,
|
|
"loss": 4.7646,
|
|
"mean_token_accuracy": 0.2230379655957222,
|
|
"num_tokens": 44495111.0,
|
|
"step": 24185
|
|
},
|
|
{
|
|
"entropy": 5.381289052963257,
|
|
"epoch": 2.0205479452054793,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004589514402751103,
|
|
"loss": 4.6765,
|
|
"mean_token_accuracy": 0.23422451466321945,
|
|
"num_tokens": 44504021.0,
|
|
"step": 24190
|
|
},
|
|
{
|
|
"entropy": 5.411710023880005,
|
|
"epoch": 2.0209655863681926,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004589342959019794,
|
|
"loss": 4.7497,
|
|
"mean_token_accuracy": 0.2220349982380867,
|
|
"num_tokens": 44513337.0,
|
|
"step": 24195
|
|
},
|
|
{
|
|
"entropy": 5.301474761962891,
|
|
"epoch": 2.0213832275309054,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004589171483088572,
|
|
"loss": 4.6907,
|
|
"mean_token_accuracy": 0.23299522399902345,
|
|
"num_tokens": 44522206.0,
|
|
"step": 24200
|
|
},
|
|
{
|
|
"entropy": 5.323190450668335,
|
|
"epoch": 2.0218008686936186,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000458899997496044,
|
|
"loss": 4.8534,
|
|
"mean_token_accuracy": 0.22301600277423858,
|
|
"num_tokens": 44531030.0,
|
|
"step": 24205
|
|
},
|
|
{
|
|
"entropy": 5.398072004318237,
|
|
"epoch": 2.0222185098563314,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00045888284346384003,
|
|
"loss": 4.7951,
|
|
"mean_token_accuracy": 0.22821660339832306,
|
|
"num_tokens": 44539844.0,
|
|
"step": 24210
|
|
},
|
|
{
|
|
"entropy": 5.353674840927124,
|
|
"epoch": 2.0226361510190443,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004588656862125454,
|
|
"loss": 4.69,
|
|
"mean_token_accuracy": 0.2360607922077179,
|
|
"num_tokens": 44548420.0,
|
|
"step": 24215
|
|
},
|
|
{
|
|
"entropy": 5.328758382797242,
|
|
"epoch": 2.0230537921817575,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004588485257424608,
|
|
"loss": 4.7376,
|
|
"mean_token_accuracy": 0.23395163267850877,
|
|
"num_tokens": 44557597.0,
|
|
"step": 24220
|
|
},
|
|
{
|
|
"entropy": 5.319436407089233,
|
|
"epoch": 2.0234714333444703,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004588313620538863,
|
|
"loss": 4.7056,
|
|
"mean_token_accuracy": 0.23111499696969987,
|
|
"num_tokens": 44566281.0,
|
|
"step": 24225
|
|
},
|
|
{
|
|
"entropy": 5.393668746948242,
|
|
"epoch": 2.0238890745071836,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004588141951471226,
|
|
"loss": 4.8182,
|
|
"mean_token_accuracy": 0.22567521333694457,
|
|
"num_tokens": 44575937.0,
|
|
"step": 24230
|
|
},
|
|
{
|
|
"entropy": 5.390875577926636,
|
|
"epoch": 2.0243067156698964,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00045879702502247014,
|
|
"loss": 4.8305,
|
|
"mean_token_accuracy": 0.23619001507759094,
|
|
"num_tokens": 44585373.0,
|
|
"step": 24235
|
|
},
|
|
{
|
|
"entropy": 5.394970321655274,
|
|
"epoch": 2.024724356832609,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004587798516802296,
|
|
"loss": 4.7729,
|
|
"mean_token_accuracy": 0.2248786360025406,
|
|
"num_tokens": 44594526.0,
|
|
"step": 24240
|
|
},
|
|
{
|
|
"entropy": 5.367958498001099,
|
|
"epoch": 2.0251419979953225,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00045876267512070146,
|
|
"loss": 4.7841,
|
|
"mean_token_accuracy": 0.2297866538167,
|
|
"num_tokens": 44603128.0,
|
|
"step": 24245
|
|
},
|
|
{
|
|
"entropy": 5.3737959384918215,
|
|
"epoch": 2.0255596391580353,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00045874549534418644,
|
|
"loss": 4.7503,
|
|
"mean_token_accuracy": 0.22298846691846846,
|
|
"num_tokens": 44612492.0,
|
|
"step": 24250
|
|
},
|
|
{
|
|
"entropy": 5.368170595169067,
|
|
"epoch": 2.0259772803207485,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004587283123509855,
|
|
"loss": 4.7547,
|
|
"mean_token_accuracy": 0.21872541606426238,
|
|
"num_tokens": 44621086.0,
|
|
"step": 24255
|
|
},
|
|
{
|
|
"entropy": 5.342848777770996,
|
|
"epoch": 2.0263949214834613,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004587111261413992,
|
|
"loss": 4.6644,
|
|
"mean_token_accuracy": 0.22994436770677568,
|
|
"num_tokens": 44629813.0,
|
|
"step": 24260
|
|
},
|
|
{
|
|
"entropy": 5.405999660491943,
|
|
"epoch": 2.0268125626461746,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004586939367157285,
|
|
"loss": 4.8546,
|
|
"mean_token_accuracy": 0.21854994744062423,
|
|
"num_tokens": 44638888.0,
|
|
"step": 24265
|
|
},
|
|
{
|
|
"entropy": 5.3475971698760985,
|
|
"epoch": 2.0272302038088874,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00045867674407427435,
|
|
"loss": 4.6821,
|
|
"mean_token_accuracy": 0.23464475572109222,
|
|
"num_tokens": 44647617.0,
|
|
"step": 24270
|
|
},
|
|
{
|
|
"entropy": 5.413548231124878,
|
|
"epoch": 2.0276478449716,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00045865954821733767,
|
|
"loss": 4.7027,
|
|
"mean_token_accuracy": 0.22759685814380645,
|
|
"num_tokens": 44657456.0,
|
|
"step": 24275
|
|
},
|
|
{
|
|
"entropy": 5.347628402709961,
|
|
"epoch": 2.0280654861343135,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00045864234914521956,
|
|
"loss": 4.7232,
|
|
"mean_token_accuracy": 0.22217393070459365,
|
|
"num_tokens": 44667008.0,
|
|
"step": 24280
|
|
},
|
|
{
|
|
"entropy": 5.329991245269776,
|
|
"epoch": 2.0284831272970263,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004586251468582211,
|
|
"loss": 4.7426,
|
|
"mean_token_accuracy": 0.23086120039224625,
|
|
"num_tokens": 44675448.0,
|
|
"step": 24285
|
|
},
|
|
{
|
|
"entropy": 5.39494252204895,
|
|
"epoch": 2.0289007684597395,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004586079413566434,
|
|
"loss": 4.826,
|
|
"mean_token_accuracy": 0.21820311695337297,
|
|
"num_tokens": 44684540.0,
|
|
"step": 24290
|
|
},
|
|
{
|
|
"entropy": 5.405147457122803,
|
|
"epoch": 2.0293184096224524,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00045859073264078765,
|
|
"loss": 4.7865,
|
|
"mean_token_accuracy": 0.2263751894235611,
|
|
"num_tokens": 44693734.0,
|
|
"step": 24295
|
|
},
|
|
{
|
|
"entropy": 5.371971988677979,
|
|
"epoch": 2.029736050785165,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00045857352071095514,
|
|
"loss": 4.7523,
|
|
"mean_token_accuracy": 0.2308851569890976,
|
|
"num_tokens": 44702407.0,
|
|
"step": 24300
|
|
},
|
|
{
|
|
"entropy": 5.346470355987549,
|
|
"epoch": 2.0301536919478784,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004585563055674472,
|
|
"loss": 4.6501,
|
|
"mean_token_accuracy": 0.23364203572273254,
|
|
"num_tokens": 44711511.0,
|
|
"step": 24305
|
|
},
|
|
{
|
|
"entropy": 5.35443639755249,
|
|
"epoch": 2.0305713331105912,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00045853908721056526,
|
|
"loss": 4.7673,
|
|
"mean_token_accuracy": 0.22160331010818482,
|
|
"num_tokens": 44720069.0,
|
|
"step": 24310
|
|
},
|
|
{
|
|
"entropy": 5.241220617294312,
|
|
"epoch": 2.0309889742733045,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00045852186564061055,
|
|
"loss": 4.6663,
|
|
"mean_token_accuracy": 0.23723288327455522,
|
|
"num_tokens": 44728549.0,
|
|
"step": 24315
|
|
},
|
|
{
|
|
"entropy": 5.351246070861817,
|
|
"epoch": 2.0314066154360173,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004585046408578847,
|
|
"loss": 4.7902,
|
|
"mean_token_accuracy": 0.2236552894115448,
|
|
"num_tokens": 44737753.0,
|
|
"step": 24320
|
|
},
|
|
{
|
|
"entropy": 5.403314113616943,
|
|
"epoch": 2.0318242565987306,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00045848741286268923,
|
|
"loss": 4.7301,
|
|
"mean_token_accuracy": 0.2252187818288803,
|
|
"num_tokens": 44747591.0,
|
|
"step": 24325
|
|
},
|
|
{
|
|
"entropy": 5.325114679336548,
|
|
"epoch": 2.0322418977614434,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00045847018165532576,
|
|
"loss": 4.8197,
|
|
"mean_token_accuracy": 0.22822651118040085,
|
|
"num_tokens": 44756942.0,
|
|
"step": 24330
|
|
},
|
|
{
|
|
"entropy": 5.350506734848023,
|
|
"epoch": 2.032659538924156,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00045845294723609596,
|
|
"loss": 4.7365,
|
|
"mean_token_accuracy": 0.22969382405281066,
|
|
"num_tokens": 44765492.0,
|
|
"step": 24335
|
|
},
|
|
{
|
|
"entropy": 5.340397596359253,
|
|
"epoch": 2.0330771800868694,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004584357096053014,
|
|
"loss": 4.6474,
|
|
"mean_token_accuracy": 0.22999584227800368,
|
|
"num_tokens": 44774433.0,
|
|
"step": 24340
|
|
},
|
|
{
|
|
"entropy": 5.423374462127685,
|
|
"epoch": 2.0334948212495823,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000458418468763244,
|
|
"loss": 4.8198,
|
|
"mean_token_accuracy": 0.22541963756084443,
|
|
"num_tokens": 44784107.0,
|
|
"step": 24345
|
|
},
|
|
{
|
|
"entropy": 5.361499071121216,
|
|
"epoch": 2.0339124624122955,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004584012247102255,
|
|
"loss": 4.7468,
|
|
"mean_token_accuracy": 0.23140899688005448,
|
|
"num_tokens": 44794234.0,
|
|
"step": 24350
|
|
},
|
|
{
|
|
"entropy": 5.24870662689209,
|
|
"epoch": 2.0343301035750083,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004583839774465479,
|
|
"loss": 4.6288,
|
|
"mean_token_accuracy": 0.23491529673337935,
|
|
"num_tokens": 44802881.0,
|
|
"step": 24355
|
|
},
|
|
{
|
|
"entropy": 5.32332067489624,
|
|
"epoch": 2.034747744737721,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00045836672697251293,
|
|
"loss": 4.7357,
|
|
"mean_token_accuracy": 0.23105445206165315,
|
|
"num_tokens": 44812114.0,
|
|
"step": 24360
|
|
},
|
|
{
|
|
"entropy": 5.433916997909546,
|
|
"epoch": 2.0351653859004344,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004583494732884227,
|
|
"loss": 4.8073,
|
|
"mean_token_accuracy": 0.22191433161497115,
|
|
"num_tokens": 44821227.0,
|
|
"step": 24365
|
|
},
|
|
{
|
|
"entropy": 5.407767248153687,
|
|
"epoch": 2.035583027063147,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004583322163945792,
|
|
"loss": 4.727,
|
|
"mean_token_accuracy": 0.22467360645532608,
|
|
"num_tokens": 44829703.0,
|
|
"step": 24370
|
|
},
|
|
{
|
|
"entropy": 5.393414878845215,
|
|
"epoch": 2.0360006682258605,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004583149562912847,
|
|
"loss": 4.8044,
|
|
"mean_token_accuracy": 0.22090833634138107,
|
|
"num_tokens": 44839400.0,
|
|
"step": 24375
|
|
},
|
|
{
|
|
"entropy": 5.32237434387207,
|
|
"epoch": 2.0364183093885733,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004582976929788411,
|
|
"loss": 4.705,
|
|
"mean_token_accuracy": 0.23267598301172257,
|
|
"num_tokens": 44848994.0,
|
|
"step": 24380
|
|
},
|
|
{
|
|
"entropy": 5.316485071182251,
|
|
"epoch": 2.0368359505512865,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004582804264575508,
|
|
"loss": 4.7177,
|
|
"mean_token_accuracy": 0.2289648860692978,
|
|
"num_tokens": 44857562.0,
|
|
"step": 24385
|
|
},
|
|
{
|
|
"entropy": 5.439713001251221,
|
|
"epoch": 2.0372535917139993,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000458263156727716,
|
|
"loss": 4.8139,
|
|
"mean_token_accuracy": 0.2211947426199913,
|
|
"num_tokens": 44867597.0,
|
|
"step": 24390
|
|
},
|
|
{
|
|
"entropy": 5.372744750976563,
|
|
"epoch": 2.037671232876712,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004582458837896391,
|
|
"loss": 4.7694,
|
|
"mean_token_accuracy": 0.22192604839801788,
|
|
"num_tokens": 44876678.0,
|
|
"step": 24395
|
|
},
|
|
{
|
|
"entropy": 5.266803169250489,
|
|
"epoch": 2.0380888740394254,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00045822860764362235,
|
|
"loss": 4.6893,
|
|
"mean_token_accuracy": 0.22993476837873458,
|
|
"num_tokens": 44885847.0,
|
|
"step": 24400
|
|
},
|
|
{
|
|
"entropy": 5.361221218109131,
|
|
"epoch": 2.038506515202138,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004582113282899683,
|
|
"loss": 4.7844,
|
|
"mean_token_accuracy": 0.2228732332587242,
|
|
"num_tokens": 44896078.0,
|
|
"step": 24405
|
|
},
|
|
{
|
|
"entropy": 5.331596803665161,
|
|
"epoch": 2.0389241563648515,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004581940457289795,
|
|
"loss": 4.6174,
|
|
"mean_token_accuracy": 0.2387644186615944,
|
|
"num_tokens": 44904996.0,
|
|
"step": 24410
|
|
},
|
|
{
|
|
"entropy": 5.285856103897094,
|
|
"epoch": 2.0393417975275643,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004581767599609584,
|
|
"loss": 4.6624,
|
|
"mean_token_accuracy": 0.2376083552837372,
|
|
"num_tokens": 44913488.0,
|
|
"step": 24415
|
|
},
|
|
{
|
|
"entropy": 5.399995040893555,
|
|
"epoch": 2.039759438690277,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004581594709862076,
|
|
"loss": 4.874,
|
|
"mean_token_accuracy": 0.20925332456827164,
|
|
"num_tokens": 44922836.0,
|
|
"step": 24420
|
|
},
|
|
{
|
|
"entropy": 5.31620831489563,
|
|
"epoch": 2.0401770798529903,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00045814217880502973,
|
|
"loss": 4.6731,
|
|
"mean_token_accuracy": 0.22965098917484283,
|
|
"num_tokens": 44932494.0,
|
|
"step": 24425
|
|
},
|
|
{
|
|
"entropy": 5.366072940826416,
|
|
"epoch": 2.040594721015703,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004581248834177276,
|
|
"loss": 4.7121,
|
|
"mean_token_accuracy": 0.22907049357891082,
|
|
"num_tokens": 44941572.0,
|
|
"step": 24430
|
|
},
|
|
{
|
|
"entropy": 5.323949527740479,
|
|
"epoch": 2.0410123621784164,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00045810758482460397,
|
|
"loss": 4.7242,
|
|
"mean_token_accuracy": 0.22788327634334565,
|
|
"num_tokens": 44949914.0,
|
|
"step": 24435
|
|
},
|
|
{
|
|
"entropy": 5.377702713012695,
|
|
"epoch": 2.0414300033411292,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004580902830259617,
|
|
"loss": 4.7757,
|
|
"mean_token_accuracy": 0.22395459711551666,
|
|
"num_tokens": 44958726.0,
|
|
"step": 24440
|
|
},
|
|
{
|
|
"entropy": 5.419974279403687,
|
|
"epoch": 2.0418476445038425,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00045807297802210364,
|
|
"loss": 4.7884,
|
|
"mean_token_accuracy": 0.22376563251018525,
|
|
"num_tokens": 44967204.0,
|
|
"step": 24445
|
|
},
|
|
{
|
|
"entropy": 5.340528535842895,
|
|
"epoch": 2.0422652856665553,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004580556698133327,
|
|
"loss": 4.7342,
|
|
"mean_token_accuracy": 0.22659552991390228,
|
|
"num_tokens": 44977043.0,
|
|
"step": 24450
|
|
},
|
|
{
|
|
"entropy": 5.39487361907959,
|
|
"epoch": 2.042682926829268,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004580383583999519,
|
|
"loss": 4.7915,
|
|
"mean_token_accuracy": 0.21611632853746415,
|
|
"num_tokens": 44986762.0,
|
|
"step": 24455
|
|
},
|
|
{
|
|
"entropy": 5.380189037322998,
|
|
"epoch": 2.0431005679919814,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004580210437822643,
|
|
"loss": 4.7221,
|
|
"mean_token_accuracy": 0.22796788513660432,
|
|
"num_tokens": 44995513.0,
|
|
"step": 24460
|
|
},
|
|
{
|
|
"entropy": 5.351219844818115,
|
|
"epoch": 2.043518209154694,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004580037259605731,
|
|
"loss": 4.8484,
|
|
"mean_token_accuracy": 0.22662021070718766,
|
|
"num_tokens": 45005127.0,
|
|
"step": 24465
|
|
},
|
|
{
|
|
"entropy": 5.419544267654419,
|
|
"epoch": 2.0439358503174074,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004579864049351813,
|
|
"loss": 4.7694,
|
|
"mean_token_accuracy": 0.22477002441883087,
|
|
"num_tokens": 45013994.0,
|
|
"step": 24470
|
|
},
|
|
{
|
|
"entropy": 5.369901037216186,
|
|
"epoch": 2.0443534914801202,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004579690807063923,
|
|
"loss": 4.7894,
|
|
"mean_token_accuracy": 0.22362324148416518,
|
|
"num_tokens": 45024177.0,
|
|
"step": 24475
|
|
},
|
|
{
|
|
"entropy": 5.382665634155273,
|
|
"epoch": 2.0447711326428335,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004579517532745093,
|
|
"loss": 4.7642,
|
|
"mean_token_accuracy": 0.2252146452665329,
|
|
"num_tokens": 45033139.0,
|
|
"step": 24480
|
|
},
|
|
{
|
|
"entropy": 5.406259536743164,
|
|
"epoch": 2.0451887738055463,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00045793442263983563,
|
|
"loss": 4.8309,
|
|
"mean_token_accuracy": 0.2229358062148094,
|
|
"num_tokens": 45043394.0,
|
|
"step": 24485
|
|
},
|
|
{
|
|
"entropy": 5.38897294998169,
|
|
"epoch": 2.045606414968259,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004579170888026747,
|
|
"loss": 4.7539,
|
|
"mean_token_accuracy": 0.2271542951464653,
|
|
"num_tokens": 45052015.0,
|
|
"step": 24490
|
|
},
|
|
{
|
|
"entropy": 5.326177883148193,
|
|
"epoch": 2.0460240561309724,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004578997517633299,
|
|
"loss": 4.6555,
|
|
"mean_token_accuracy": 0.23461304605007172,
|
|
"num_tokens": 45060836.0,
|
|
"step": 24495
|
|
},
|
|
{
|
|
"entropy": 5.327291011810303,
|
|
"epoch": 2.046441697293685,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00045788241152210486,
|
|
"loss": 4.7135,
|
|
"mean_token_accuracy": 0.2227926507592201,
|
|
"num_tokens": 45070007.0,
|
|
"step": 24500
|
|
},
|
|
{
|
|
"entropy": 5.429235410690308,
|
|
"epoch": 2.0468593384563984,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000457865068079303,
|
|
"loss": 4.8071,
|
|
"mean_token_accuracy": 0.22315050214529036,
|
|
"num_tokens": 45079984.0,
|
|
"step": 24505
|
|
},
|
|
{
|
|
"entropy": 5.383999538421631,
|
|
"epoch": 2.0472769796191113,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000457847721435228,
|
|
"loss": 4.6855,
|
|
"mean_token_accuracy": 0.2334592953324318,
|
|
"num_tokens": 45088676.0,
|
|
"step": 24510
|
|
},
|
|
{
|
|
"entropy": 5.369411039352417,
|
|
"epoch": 2.047694620781824,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00045783037159018364,
|
|
"loss": 4.8022,
|
|
"mean_token_accuracy": 0.22604180127382278,
|
|
"num_tokens": 45098232.0,
|
|
"step": 24515
|
|
},
|
|
{
|
|
"entropy": 5.331746292114258,
|
|
"epoch": 2.0481122619445373,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00045781301854447347,
|
|
"loss": 4.7373,
|
|
"mean_token_accuracy": 0.23045262843370437,
|
|
"num_tokens": 45107789.0,
|
|
"step": 24520
|
|
},
|
|
{
|
|
"entropy": 5.382537841796875,
|
|
"epoch": 2.04852990310725,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00045779566229840144,
|
|
"loss": 4.7561,
|
|
"mean_token_accuracy": 0.22269731163978576,
|
|
"num_tokens": 45117824.0,
|
|
"step": 24525
|
|
},
|
|
{
|
|
"entropy": 5.440794897079468,
|
|
"epoch": 2.0489475442699634,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00045777830285227125,
|
|
"loss": 4.889,
|
|
"mean_token_accuracy": 0.21775273680686952,
|
|
"num_tokens": 45127625.0,
|
|
"step": 24530
|
|
},
|
|
{
|
|
"entropy": 5.339394855499267,
|
|
"epoch": 2.049365185432676,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004577609402063868,
|
|
"loss": 4.6971,
|
|
"mean_token_accuracy": 0.23164542019367218,
|
|
"num_tokens": 45135931.0,
|
|
"step": 24535
|
|
},
|
|
{
|
|
"entropy": 5.452150154113769,
|
|
"epoch": 2.049782826595389,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004577435743610522,
|
|
"loss": 4.852,
|
|
"mean_token_accuracy": 0.22837902456521988,
|
|
"num_tokens": 45145690.0,
|
|
"step": 24540
|
|
},
|
|
{
|
|
"entropy": 5.452599906921387,
|
|
"epoch": 2.0502004677581023,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004577262053165713,
|
|
"loss": 4.9174,
|
|
"mean_token_accuracy": 0.2159697100520134,
|
|
"num_tokens": 45155455.0,
|
|
"step": 24545
|
|
},
|
|
{
|
|
"entropy": 5.420417261123657,
|
|
"epoch": 2.050618108920815,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004577088330732483,
|
|
"loss": 4.7776,
|
|
"mean_token_accuracy": 0.23483889400959015,
|
|
"num_tokens": 45164377.0,
|
|
"step": 24550
|
|
},
|
|
{
|
|
"entropy": 5.483632326126099,
|
|
"epoch": 2.0510357500835283,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004576914576313872,
|
|
"loss": 4.8233,
|
|
"mean_token_accuracy": 0.21844120770692826,
|
|
"num_tokens": 45173037.0,
|
|
"step": 24555
|
|
},
|
|
{
|
|
"entropy": 5.399893140792846,
|
|
"epoch": 2.051453391246241,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004576740789912922,
|
|
"loss": 4.7426,
|
|
"mean_token_accuracy": 0.23006001561880113,
|
|
"num_tokens": 45182459.0,
|
|
"step": 24560
|
|
},
|
|
{
|
|
"entropy": 5.279356145858765,
|
|
"epoch": 2.0518710324089544,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004576566971532676,
|
|
"loss": 4.6832,
|
|
"mean_token_accuracy": 0.23972612619400024,
|
|
"num_tokens": 45190744.0,
|
|
"step": 24565
|
|
},
|
|
{
|
|
"entropy": 5.383039283752441,
|
|
"epoch": 2.052288673571667,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004576393121176177,
|
|
"loss": 4.8484,
|
|
"mean_token_accuracy": 0.22483027428388597,
|
|
"num_tokens": 45198852.0,
|
|
"step": 24570
|
|
},
|
|
{
|
|
"entropy": 5.325116682052612,
|
|
"epoch": 2.05270631473438,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00045762192388464675,
|
|
"loss": 4.6869,
|
|
"mean_token_accuracy": 0.24003441929817199,
|
|
"num_tokens": 45207794.0,
|
|
"step": 24575
|
|
},
|
|
{
|
|
"entropy": 5.352684164047242,
|
|
"epoch": 2.0531239558970933,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004576045324546592,
|
|
"loss": 4.7092,
|
|
"mean_token_accuracy": 0.23982757478952407,
|
|
"num_tokens": 45216621.0,
|
|
"step": 24580
|
|
},
|
|
{
|
|
"entropy": 5.349598598480225,
|
|
"epoch": 2.053541597059806,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00045758713782795946,
|
|
"loss": 4.8184,
|
|
"mean_token_accuracy": 0.22134318202733994,
|
|
"num_tokens": 45226801.0,
|
|
"step": 24585
|
|
},
|
|
{
|
|
"entropy": 5.314327907562256,
|
|
"epoch": 2.0539592382225194,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00045756974000485216,
|
|
"loss": 4.7469,
|
|
"mean_token_accuracy": 0.2205469086766243,
|
|
"num_tokens": 45236575.0,
|
|
"step": 24590
|
|
},
|
|
{
|
|
"entropy": 5.403866291046143,
|
|
"epoch": 2.054376879385232,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00045755233898564176,
|
|
"loss": 4.7852,
|
|
"mean_token_accuracy": 0.22139369547367097,
|
|
"num_tokens": 45245868.0,
|
|
"step": 24595
|
|
},
|
|
{
|
|
"entropy": 5.406394052505493,
|
|
"epoch": 2.0547945205479454,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00045753493477063297,
|
|
"loss": 4.8346,
|
|
"mean_token_accuracy": 0.22202795296907424,
|
|
"num_tokens": 45256160.0,
|
|
"step": 24600
|
|
},
|
|
{
|
|
"entropy": 5.309784555435181,
|
|
"epoch": 2.0552121617106582,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004575175273601304,
|
|
"loss": 4.7373,
|
|
"mean_token_accuracy": 0.23097097724676133,
|
|
"num_tokens": 45265128.0,
|
|
"step": 24605
|
|
},
|
|
{
|
|
"entropy": 5.30449948310852,
|
|
"epoch": 2.055629802873371,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00045750011675443886,
|
|
"loss": 4.7024,
|
|
"mean_token_accuracy": 0.22709571570158005,
|
|
"num_tokens": 45274825.0,
|
|
"step": 24610
|
|
},
|
|
{
|
|
"entropy": 5.270273685455322,
|
|
"epoch": 2.0560474440360843,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004574827029538631,
|
|
"loss": 4.6584,
|
|
"mean_token_accuracy": 0.23372844010591506,
|
|
"num_tokens": 45282585.0,
|
|
"step": 24615
|
|
},
|
|
{
|
|
"entropy": 5.326085138320923,
|
|
"epoch": 2.056465085198797,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004574652859587079,
|
|
"loss": 4.7882,
|
|
"mean_token_accuracy": 0.2206298053264618,
|
|
"num_tokens": 45292752.0,
|
|
"step": 24620
|
|
},
|
|
{
|
|
"entropy": 5.358016872406006,
|
|
"epoch": 2.0568827263615104,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00045744786576927825,
|
|
"loss": 4.6819,
|
|
"mean_token_accuracy": 0.23404404819011687,
|
|
"num_tokens": 45302486.0,
|
|
"step": 24625
|
|
},
|
|
{
|
|
"entropy": 5.352846288681031,
|
|
"epoch": 2.057300367524223,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004574304423858791,
|
|
"loss": 4.7959,
|
|
"mean_token_accuracy": 0.21895135790109635,
|
|
"num_tokens": 45311215.0,
|
|
"step": 24630
|
|
},
|
|
{
|
|
"entropy": 5.333528184890747,
|
|
"epoch": 2.057718008686936,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00045741301580881557,
|
|
"loss": 4.7807,
|
|
"mean_token_accuracy": 0.22124574929475785,
|
|
"num_tokens": 45321800.0,
|
|
"step": 24635
|
|
},
|
|
{
|
|
"entropy": 5.274019384384156,
|
|
"epoch": 2.0581356498496493,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004573955860383925,
|
|
"loss": 4.7311,
|
|
"mean_token_accuracy": 0.23845247626304628,
|
|
"num_tokens": 45330621.0,
|
|
"step": 24640
|
|
},
|
|
{
|
|
"entropy": 5.351425504684448,
|
|
"epoch": 2.058553291012362,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004573781530749152,
|
|
"loss": 4.7257,
|
|
"mean_token_accuracy": 0.23736984878778458,
|
|
"num_tokens": 45340295.0,
|
|
"step": 24645
|
|
},
|
|
{
|
|
"entropy": 5.379012155532837,
|
|
"epoch": 2.0589709321750753,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00045736071691868883,
|
|
"loss": 4.8016,
|
|
"mean_token_accuracy": 0.2233588546514511,
|
|
"num_tokens": 45350896.0,
|
|
"step": 24650
|
|
},
|
|
{
|
|
"entropy": 5.276549243927002,
|
|
"epoch": 2.059388573337788,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004573432775700185,
|
|
"loss": 4.6507,
|
|
"mean_token_accuracy": 0.23590527027845382,
|
|
"num_tokens": 45359462.0,
|
|
"step": 24655
|
|
},
|
|
{
|
|
"entropy": 5.444241046905518,
|
|
"epoch": 2.0598062145005014,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004573258350292097,
|
|
"loss": 4.8171,
|
|
"mean_token_accuracy": 0.2184551477432251,
|
|
"num_tokens": 45370272.0,
|
|
"step": 24660
|
|
},
|
|
{
|
|
"entropy": 5.393611192703247,
|
|
"epoch": 2.060223855663214,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004573083892965677,
|
|
"loss": 4.7591,
|
|
"mean_token_accuracy": 0.23475807160139084,
|
|
"num_tokens": 45379745.0,
|
|
"step": 24665
|
|
},
|
|
{
|
|
"entropy": 5.270851469039917,
|
|
"epoch": 2.060641496825927,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004572909403723978,
|
|
"loss": 4.6103,
|
|
"mean_token_accuracy": 0.24612222611904144,
|
|
"num_tokens": 45388599.0,
|
|
"step": 24670
|
|
},
|
|
{
|
|
"entropy": 5.283067655563355,
|
|
"epoch": 2.0610591379886403,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004572734882570057,
|
|
"loss": 4.7243,
|
|
"mean_token_accuracy": 0.2307177037000656,
|
|
"num_tokens": 45397246.0,
|
|
"step": 24675
|
|
},
|
|
{
|
|
"entropy": 5.400209856033325,
|
|
"epoch": 2.061476779151353,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00045725603295069666,
|
|
"loss": 4.7976,
|
|
"mean_token_accuracy": 0.2159995287656784,
|
|
"num_tokens": 45406001.0,
|
|
"step": 24680
|
|
},
|
|
{
|
|
"entropy": 5.292866134643555,
|
|
"epoch": 2.0618944203140663,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004572385744537765,
|
|
"loss": 4.6735,
|
|
"mean_token_accuracy": 0.228641340136528,
|
|
"num_tokens": 45414926.0,
|
|
"step": 24685
|
|
},
|
|
{
|
|
"entropy": 5.382950973510742,
|
|
"epoch": 2.062312061476779,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00045722111276655066,
|
|
"loss": 4.7751,
|
|
"mean_token_accuracy": 0.2214135482907295,
|
|
"num_tokens": 45423918.0,
|
|
"step": 24690
|
|
},
|
|
{
|
|
"entropy": 5.253759574890137,
|
|
"epoch": 2.062729702639492,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00045720364788932486,
|
|
"loss": 4.6419,
|
|
"mean_token_accuracy": 0.23355366736650468,
|
|
"num_tokens": 45433174.0,
|
|
"step": 24695
|
|
},
|
|
{
|
|
"entropy": 5.287618684768677,
|
|
"epoch": 2.063147343802205,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00045718617982240496,
|
|
"loss": 4.7396,
|
|
"mean_token_accuracy": 0.22953377962112426,
|
|
"num_tokens": 45441660.0,
|
|
"step": 24700
|
|
},
|
|
{
|
|
"entropy": 5.388389968872071,
|
|
"epoch": 2.063564984964918,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004571687085660967,
|
|
"loss": 4.7837,
|
|
"mean_token_accuracy": 0.22054422348737718,
|
|
"num_tokens": 45451293.0,
|
|
"step": 24705
|
|
},
|
|
{
|
|
"entropy": 5.415960645675659,
|
|
"epoch": 2.0639826261276313,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00045715123412070594,
|
|
"loss": 4.7684,
|
|
"mean_token_accuracy": 0.22266942858695984,
|
|
"num_tokens": 45460615.0,
|
|
"step": 24710
|
|
},
|
|
{
|
|
"entropy": 5.424771642684936,
|
|
"epoch": 2.064400267290344,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004571337564865385,
|
|
"loss": 4.7452,
|
|
"mean_token_accuracy": 0.22545535415410994,
|
|
"num_tokens": 45469404.0,
|
|
"step": 24715
|
|
},
|
|
{
|
|
"entropy": 5.452198839187622,
|
|
"epoch": 2.0648179084530573,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004571162756639004,
|
|
"loss": 4.8342,
|
|
"mean_token_accuracy": 0.22474520057439804,
|
|
"num_tokens": 45478900.0,
|
|
"step": 24720
|
|
},
|
|
{
|
|
"entropy": 5.289414501190185,
|
|
"epoch": 2.06523554961577,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004570987916530977,
|
|
"loss": 4.6559,
|
|
"mean_token_accuracy": 0.22135296314954758,
|
|
"num_tokens": 45488478.0,
|
|
"step": 24725
|
|
},
|
|
{
|
|
"entropy": 5.326510000228882,
|
|
"epoch": 2.065653190778483,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00045708130445443646,
|
|
"loss": 4.6854,
|
|
"mean_token_accuracy": 0.22461239695549012,
|
|
"num_tokens": 45498421.0,
|
|
"step": 24730
|
|
},
|
|
{
|
|
"entropy": 5.341510200500489,
|
|
"epoch": 2.0660708319411962,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00045706381406822284,
|
|
"loss": 4.747,
|
|
"mean_token_accuracy": 0.22197266966104506,
|
|
"num_tokens": 45507715.0,
|
|
"step": 24735
|
|
},
|
|
{
|
|
"entropy": 5.349908304214478,
|
|
"epoch": 2.066488473103909,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000457046320494763,
|
|
"loss": 4.7739,
|
|
"mean_token_accuracy": 0.2264243796467781,
|
|
"num_tokens": 45516524.0,
|
|
"step": 24740
|
|
},
|
|
{
|
|
"entropy": 5.360632276535034,
|
|
"epoch": 2.0669061142666223,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00045702882373436317,
|
|
"loss": 4.7381,
|
|
"mean_token_accuracy": 0.22690756469964982,
|
|
"num_tokens": 45526058.0,
|
|
"step": 24745
|
|
},
|
|
{
|
|
"entropy": 5.347311687469483,
|
|
"epoch": 2.067323755429335,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004570113237873297,
|
|
"loss": 4.7901,
|
|
"mean_token_accuracy": 0.22396740019321443,
|
|
"num_tokens": 45535441.0,
|
|
"step": 24750
|
|
},
|
|
{
|
|
"entropy": 5.371656227111816,
|
|
"epoch": 2.067741396592048,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00045699382065396893,
|
|
"loss": 4.8303,
|
|
"mean_token_accuracy": 0.21967003643512725,
|
|
"num_tokens": 45544355.0,
|
|
"step": 24755
|
|
},
|
|
{
|
|
"entropy": 5.357279443740845,
|
|
"epoch": 2.068159037754761,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004569763143345872,
|
|
"loss": 4.7189,
|
|
"mean_token_accuracy": 0.22706499844789504,
|
|
"num_tokens": 45553509.0,
|
|
"step": 24760
|
|
},
|
|
{
|
|
"entropy": 5.307345199584961,
|
|
"epoch": 2.068576678917474,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00045695880482949107,
|
|
"loss": 4.586,
|
|
"mean_token_accuracy": 0.24203407615423203,
|
|
"num_tokens": 45563016.0,
|
|
"step": 24765
|
|
},
|
|
{
|
|
"entropy": 5.356969594955444,
|
|
"epoch": 2.0689943200801872,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004569412921389871,
|
|
"loss": 4.7632,
|
|
"mean_token_accuracy": 0.22457700669765474,
|
|
"num_tokens": 45572242.0,
|
|
"step": 24770
|
|
},
|
|
{
|
|
"entropy": 5.300438261032104,
|
|
"epoch": 2.0694119612429,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004569237762633818,
|
|
"loss": 4.6136,
|
|
"mean_token_accuracy": 0.22989027798175812,
|
|
"num_tokens": 45581430.0,
|
|
"step": 24775
|
|
},
|
|
{
|
|
"entropy": 5.319148588180542,
|
|
"epoch": 2.0698296024056133,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00045690625720298166,
|
|
"loss": 4.7191,
|
|
"mean_token_accuracy": 0.22238730043172836,
|
|
"num_tokens": 45590161.0,
|
|
"step": 24780
|
|
},
|
|
{
|
|
"entropy": 5.322426414489746,
|
|
"epoch": 2.070247243568326,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004568887349580937,
|
|
"loss": 4.794,
|
|
"mean_token_accuracy": 0.22188284397125244,
|
|
"num_tokens": 45599243.0,
|
|
"step": 24785
|
|
},
|
|
{
|
|
"entropy": 5.323762273788452,
|
|
"epoch": 2.070664884731039,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00045687120952902447,
|
|
"loss": 4.7316,
|
|
"mean_token_accuracy": 0.23236450254917146,
|
|
"num_tokens": 45607958.0,
|
|
"step": 24790
|
|
},
|
|
{
|
|
"entropy": 5.41298770904541,
|
|
"epoch": 2.071082525893752,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00045685368091608075,
|
|
"loss": 4.823,
|
|
"mean_token_accuracy": 0.22305425107479096,
|
|
"num_tokens": 45617243.0,
|
|
"step": 24795
|
|
},
|
|
{
|
|
"entropy": 5.349467754364014,
|
|
"epoch": 2.071500167056465,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00045683614911956946,
|
|
"loss": 4.7352,
|
|
"mean_token_accuracy": 0.22349953204393386,
|
|
"num_tokens": 45627288.0,
|
|
"step": 24800
|
|
},
|
|
{
|
|
"entropy": 5.393856048583984,
|
|
"epoch": 2.0719178082191783,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004568186141397975,
|
|
"loss": 4.7913,
|
|
"mean_token_accuracy": 0.23022358417510985,
|
|
"num_tokens": 45636345.0,
|
|
"step": 24805
|
|
},
|
|
{
|
|
"entropy": 5.417702341079712,
|
|
"epoch": 2.072335449381891,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00045680107597707186,
|
|
"loss": 4.7447,
|
|
"mean_token_accuracy": 0.22791616171598433,
|
|
"num_tokens": 45645146.0,
|
|
"step": 24810
|
|
},
|
|
{
|
|
"entropy": 5.403923845291137,
|
|
"epoch": 2.072753090544604,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00045678353463169953,
|
|
"loss": 4.8273,
|
|
"mean_token_accuracy": 0.21890632659196854,
|
|
"num_tokens": 45654509.0,
|
|
"step": 24815
|
|
},
|
|
{
|
|
"entropy": 5.357655477523804,
|
|
"epoch": 2.073170731707317,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004567659901039876,
|
|
"loss": 4.6907,
|
|
"mean_token_accuracy": 0.2330747961997986,
|
|
"num_tokens": 45663021.0,
|
|
"step": 24820
|
|
},
|
|
{
|
|
"entropy": 5.315986156463623,
|
|
"epoch": 2.07358837287003,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004567484423942433,
|
|
"loss": 4.7576,
|
|
"mean_token_accuracy": 0.22630721777677537,
|
|
"num_tokens": 45671633.0,
|
|
"step": 24825
|
|
},
|
|
{
|
|
"entropy": 5.418448162078858,
|
|
"epoch": 2.074006014032743,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00045673089150277365,
|
|
"loss": 4.8395,
|
|
"mean_token_accuracy": 0.22307607531547546,
|
|
"num_tokens": 45681974.0,
|
|
"step": 24830
|
|
},
|
|
{
|
|
"entropy": 5.404704904556274,
|
|
"epoch": 2.074423655195456,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00045671333742988604,
|
|
"loss": 4.7656,
|
|
"mean_token_accuracy": 0.22175808548927306,
|
|
"num_tokens": 45691939.0,
|
|
"step": 24835
|
|
},
|
|
{
|
|
"entropy": 5.573681211471557,
|
|
"epoch": 2.0748412963581693,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004566957801758878,
|
|
"loss": 4.9012,
|
|
"mean_token_accuracy": 0.21699209362268448,
|
|
"num_tokens": 45701689.0,
|
|
"step": 24840
|
|
},
|
|
{
|
|
"entropy": 5.300716161727905,
|
|
"epoch": 2.075258937520882,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004566782197410861,
|
|
"loss": 4.6142,
|
|
"mean_token_accuracy": 0.24049526154994966,
|
|
"num_tokens": 45710523.0,
|
|
"step": 24845
|
|
},
|
|
{
|
|
"entropy": 5.320780992507935,
|
|
"epoch": 2.075676578683595,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004566606561257885,
|
|
"loss": 4.7573,
|
|
"mean_token_accuracy": 0.22441162168979645,
|
|
"num_tokens": 45719422.0,
|
|
"step": 24850
|
|
},
|
|
{
|
|
"entropy": 5.342905521392822,
|
|
"epoch": 2.076094219846308,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004566430893303025,
|
|
"loss": 4.7725,
|
|
"mean_token_accuracy": 0.22715501636266708,
|
|
"num_tokens": 45729052.0,
|
|
"step": 24855
|
|
},
|
|
{
|
|
"entropy": 5.31501202583313,
|
|
"epoch": 2.076511861009021,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004566255193549355,
|
|
"loss": 4.7501,
|
|
"mean_token_accuracy": 0.2310745269060135,
|
|
"num_tokens": 45739853.0,
|
|
"step": 24860
|
|
},
|
|
{
|
|
"entropy": 5.262033319473266,
|
|
"epoch": 2.076929502171734,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00045660794619999524,
|
|
"loss": 4.6295,
|
|
"mean_token_accuracy": 0.24123705178499222,
|
|
"num_tokens": 45749433.0,
|
|
"step": 24865
|
|
},
|
|
{
|
|
"entropy": 5.339287662506104,
|
|
"epoch": 2.077347143334447,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004565903698657893,
|
|
"loss": 4.7319,
|
|
"mean_token_accuracy": 0.22902906239032744,
|
|
"num_tokens": 45758771.0,
|
|
"step": 24870
|
|
},
|
|
{
|
|
"entropy": 5.412585592269897,
|
|
"epoch": 2.07776478449716,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00045657279035262534,
|
|
"loss": 4.8817,
|
|
"mean_token_accuracy": 0.2076273277401924,
|
|
"num_tokens": 45767998.0,
|
|
"step": 24875
|
|
},
|
|
{
|
|
"entropy": 5.398457956314087,
|
|
"epoch": 2.078182425659873,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000456555207660811,
|
|
"loss": 4.8646,
|
|
"mean_token_accuracy": 0.22482260763645173,
|
|
"num_tokens": 45777482.0,
|
|
"step": 24880
|
|
},
|
|
{
|
|
"entropy": 5.467352867126465,
|
|
"epoch": 2.078600066822586,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004565376217906543,
|
|
"loss": 4.7728,
|
|
"mean_token_accuracy": 0.21986211091279984,
|
|
"num_tokens": 45786996.0,
|
|
"step": 24885
|
|
},
|
|
{
|
|
"entropy": 5.4596171379089355,
|
|
"epoch": 2.079017707985299,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00045652003274246306,
|
|
"loss": 4.8774,
|
|
"mean_token_accuracy": 0.22141083627939223,
|
|
"num_tokens": 45796654.0,
|
|
"step": 24890
|
|
},
|
|
{
|
|
"entropy": 5.333255624771118,
|
|
"epoch": 2.079435349148012,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004565024405165452,
|
|
"loss": 4.7475,
|
|
"mean_token_accuracy": 0.2304296761751175,
|
|
"num_tokens": 45805086.0,
|
|
"step": 24895
|
|
},
|
|
{
|
|
"entropy": 5.3862720966339115,
|
|
"epoch": 2.0798529903107252,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00045648484511320853,
|
|
"loss": 4.7553,
|
|
"mean_token_accuracy": 0.2300160974264145,
|
|
"num_tokens": 45813034.0,
|
|
"step": 24900
|
|
},
|
|
{
|
|
"entropy": 5.27665901184082,
|
|
"epoch": 2.080270631473438,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00045646724653276117,
|
|
"loss": 4.6422,
|
|
"mean_token_accuracy": 0.23748387396335602,
|
|
"num_tokens": 45821867.0,
|
|
"step": 24905
|
|
},
|
|
{
|
|
"entropy": 5.2551881790161135,
|
|
"epoch": 2.080688272636151,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00045644964477551124,
|
|
"loss": 4.6144,
|
|
"mean_token_accuracy": 0.24088768512010575,
|
|
"num_tokens": 45830640.0,
|
|
"step": 24910
|
|
},
|
|
{
|
|
"entropy": 5.277661323547363,
|
|
"epoch": 2.081105913798864,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000456432039841767,
|
|
"loss": 4.6759,
|
|
"mean_token_accuracy": 0.23664363473653793,
|
|
"num_tokens": 45839334.0,
|
|
"step": 24915
|
|
},
|
|
{
|
|
"entropy": 5.3707481861114506,
|
|
"epoch": 2.081523554961577,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004564144317318364,
|
|
"loss": 4.8049,
|
|
"mean_token_accuracy": 0.2224668011069298,
|
|
"num_tokens": 45849253.0,
|
|
"step": 24920
|
|
},
|
|
{
|
|
"entropy": 5.430300092697143,
|
|
"epoch": 2.08194119612429,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00045639682044602777,
|
|
"loss": 4.7739,
|
|
"mean_token_accuracy": 0.22198178321123124,
|
|
"num_tokens": 45858166.0,
|
|
"step": 24925
|
|
},
|
|
{
|
|
"entropy": 5.450219202041626,
|
|
"epoch": 2.082358837287003,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00045637920598464956,
|
|
"loss": 4.8634,
|
|
"mean_token_accuracy": 0.22251157462596893,
|
|
"num_tokens": 45867658.0,
|
|
"step": 24930
|
|
},
|
|
{
|
|
"entropy": 5.343351554870606,
|
|
"epoch": 2.082776478449716,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00045636158834800987,
|
|
"loss": 4.6956,
|
|
"mean_token_accuracy": 0.23011282235383987,
|
|
"num_tokens": 45876817.0,
|
|
"step": 24935
|
|
},
|
|
{
|
|
"entropy": 5.345300340652466,
|
|
"epoch": 2.083194119612429,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00045634396753641736,
|
|
"loss": 4.7266,
|
|
"mean_token_accuracy": 0.23167186230421066,
|
|
"num_tokens": 45886019.0,
|
|
"step": 24940
|
|
},
|
|
{
|
|
"entropy": 5.398944950103759,
|
|
"epoch": 2.083611760775142,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004563263435501805,
|
|
"loss": 4.7859,
|
|
"mean_token_accuracy": 0.22314279526472092,
|
|
"num_tokens": 45894917.0,
|
|
"step": 24945
|
|
},
|
|
{
|
|
"entropy": 5.406246471405029,
|
|
"epoch": 2.084029401937855,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004563087163896076,
|
|
"loss": 4.6673,
|
|
"mean_token_accuracy": 0.2280312955379486,
|
|
"num_tokens": 45903727.0,
|
|
"step": 24950
|
|
},
|
|
{
|
|
"entropy": 5.331357383728028,
|
|
"epoch": 2.084447043100568,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00045629108605500747,
|
|
"loss": 4.6745,
|
|
"mean_token_accuracy": 0.23288137912750245,
|
|
"num_tokens": 45912217.0,
|
|
"step": 24955
|
|
},
|
|
{
|
|
"entropy": 5.373971748352051,
|
|
"epoch": 2.084864684263281,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00045627345254668864,
|
|
"loss": 4.8099,
|
|
"mean_token_accuracy": 0.22335097342729568,
|
|
"num_tokens": 45921526.0,
|
|
"step": 24960
|
|
},
|
|
{
|
|
"entropy": 5.377131175994873,
|
|
"epoch": 2.085282325425994,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00045625581586495977,
|
|
"loss": 4.8304,
|
|
"mean_token_accuracy": 0.22145879864692689,
|
|
"num_tokens": 45931115.0,
|
|
"step": 24965
|
|
},
|
|
{
|
|
"entropy": 5.384525775909424,
|
|
"epoch": 2.085699966588707,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004562381760101297,
|
|
"loss": 4.8422,
|
|
"mean_token_accuracy": 0.22081774473190308,
|
|
"num_tokens": 45940323.0,
|
|
"step": 24970
|
|
},
|
|
{
|
|
"entropy": 5.394400882720947,
|
|
"epoch": 2.08611760775142,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004562205329825072,
|
|
"loss": 4.7361,
|
|
"mean_token_accuracy": 0.2252225711941719,
|
|
"num_tokens": 45949354.0,
|
|
"step": 24975
|
|
},
|
|
{
|
|
"entropy": 5.338393020629883,
|
|
"epoch": 2.086535248914133,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004562028867824012,
|
|
"loss": 4.7573,
|
|
"mean_token_accuracy": 0.21809712201356887,
|
|
"num_tokens": 45958899.0,
|
|
"step": 24980
|
|
},
|
|
{
|
|
"entropy": 5.375522041320801,
|
|
"epoch": 2.086952890076846,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00045618523741012044,
|
|
"loss": 4.7167,
|
|
"mean_token_accuracy": 0.231799940764904,
|
|
"num_tokens": 45967431.0,
|
|
"step": 24985
|
|
},
|
|
{
|
|
"entropy": 5.277795934677124,
|
|
"epoch": 2.087370531239559,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004561675848659741,
|
|
"loss": 4.7279,
|
|
"mean_token_accuracy": 0.2319658637046814,
|
|
"num_tokens": 45976185.0,
|
|
"step": 24990
|
|
},
|
|
{
|
|
"entropy": 5.266036653518677,
|
|
"epoch": 2.0877881724022718,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00045614992915027103,
|
|
"loss": 4.5889,
|
|
"mean_token_accuracy": 0.2428508833050728,
|
|
"num_tokens": 45984648.0,
|
|
"step": 24995
|
|
},
|
|
{
|
|
"entropy": 5.282194662094116,
|
|
"epoch": 2.088205813564985,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00045613227026332045,
|
|
"loss": 4.6635,
|
|
"mean_token_accuracy": 0.23216931372880936,
|
|
"num_tokens": 45993724.0,
|
|
"step": 25000
|
|
},
|
|
{
|
|
"entropy": 5.317374038696289,
|
|
"epoch": 2.088623454727698,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004561146082054314,
|
|
"loss": 4.7135,
|
|
"mean_token_accuracy": 0.22420018911361694,
|
|
"num_tokens": 46002998.0,
|
|
"step": 25005
|
|
},
|
|
{
|
|
"entropy": 5.324342679977417,
|
|
"epoch": 2.089041095890411,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004560969429769132,
|
|
"loss": 4.7136,
|
|
"mean_token_accuracy": 0.2309127628803253,
|
|
"num_tokens": 46010843.0,
|
|
"step": 25010
|
|
},
|
|
{
|
|
"entropy": 5.277094936370849,
|
|
"epoch": 2.089458737053124,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00045607927457807503,
|
|
"loss": 4.646,
|
|
"mean_token_accuracy": 0.23514231145381928,
|
|
"num_tokens": 46019733.0,
|
|
"step": 25015
|
|
},
|
|
{
|
|
"entropy": 5.385273694992065,
|
|
"epoch": 2.089876378215837,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004560616030092261,
|
|
"loss": 4.8099,
|
|
"mean_token_accuracy": 0.2188909947872162,
|
|
"num_tokens": 46029754.0,
|
|
"step": 25020
|
|
},
|
|
{
|
|
"entropy": 5.351217126846313,
|
|
"epoch": 2.09029401937855,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004560439282706759,
|
|
"loss": 4.6624,
|
|
"mean_token_accuracy": 0.2311645671725273,
|
|
"num_tokens": 46037855.0,
|
|
"step": 25025
|
|
},
|
|
{
|
|
"entropy": 5.375508975982666,
|
|
"epoch": 2.090711660541263,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00045602625036273385,
|
|
"loss": 4.7762,
|
|
"mean_token_accuracy": 0.22123136967420579,
|
|
"num_tokens": 46046176.0,
|
|
"step": 25030
|
|
},
|
|
{
|
|
"entropy": 5.441777563095092,
|
|
"epoch": 2.091129301703976,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00045600856928570944,
|
|
"loss": 4.8208,
|
|
"mean_token_accuracy": 0.2294180363416672,
|
|
"num_tokens": 46055847.0,
|
|
"step": 25035
|
|
},
|
|
{
|
|
"entropy": 5.421140861511231,
|
|
"epoch": 2.091546942866689,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00045599088503991205,
|
|
"loss": 4.7848,
|
|
"mean_token_accuracy": 0.22017060220241547,
|
|
"num_tokens": 46065763.0,
|
|
"step": 25040
|
|
},
|
|
{
|
|
"entropy": 5.364895629882812,
|
|
"epoch": 2.091964584029402,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004559731976256514,
|
|
"loss": 4.7863,
|
|
"mean_token_accuracy": 0.21945644468069075,
|
|
"num_tokens": 46074564.0,
|
|
"step": 25045
|
|
},
|
|
{
|
|
"entropy": 5.366264486312867,
|
|
"epoch": 2.092382225192115,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00045595550704323706,
|
|
"loss": 4.78,
|
|
"mean_token_accuracy": 0.2303968131542206,
|
|
"num_tokens": 46083627.0,
|
|
"step": 25050
|
|
},
|
|
{
|
|
"entropy": 5.3606315612792965,
|
|
"epoch": 2.0927998663548277,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00045593781329297876,
|
|
"loss": 4.7877,
|
|
"mean_token_accuracy": 0.22480550408363342,
|
|
"num_tokens": 46092997.0,
|
|
"step": 25055
|
|
},
|
|
{
|
|
"entropy": 5.428432035446167,
|
|
"epoch": 2.093217507517541,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00045592011637518625,
|
|
"loss": 4.9011,
|
|
"mean_token_accuracy": 0.21531529426574708,
|
|
"num_tokens": 46103266.0,
|
|
"step": 25060
|
|
},
|
|
{
|
|
"entropy": 5.360718822479248,
|
|
"epoch": 2.093635148680254,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00045590241629016933,
|
|
"loss": 4.6209,
|
|
"mean_token_accuracy": 0.23296956866979598,
|
|
"num_tokens": 46112896.0,
|
|
"step": 25065
|
|
},
|
|
{
|
|
"entropy": 5.327370119094849,
|
|
"epoch": 2.094052789842967,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00045588471303823787,
|
|
"loss": 4.7222,
|
|
"mean_token_accuracy": 0.24030878394842148,
|
|
"num_tokens": 46121134.0,
|
|
"step": 25070
|
|
},
|
|
{
|
|
"entropy": 5.320885705947876,
|
|
"epoch": 2.09447043100568,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00045586700661970174,
|
|
"loss": 4.7326,
|
|
"mean_token_accuracy": 0.22797195017337799,
|
|
"num_tokens": 46130617.0,
|
|
"step": 25075
|
|
},
|
|
{
|
|
"entropy": 5.351654005050659,
|
|
"epoch": 2.094888072168393,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00045584929703487107,
|
|
"loss": 4.7753,
|
|
"mean_token_accuracy": 0.22371670752763748,
|
|
"num_tokens": 46140584.0,
|
|
"step": 25080
|
|
},
|
|
{
|
|
"entropy": 5.419725179672241,
|
|
"epoch": 2.095305713331106,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004558315842840556,
|
|
"loss": 4.6943,
|
|
"mean_token_accuracy": 0.22935066521167755,
|
|
"num_tokens": 46150039.0,
|
|
"step": 25085
|
|
},
|
|
{
|
|
"entropy": 5.389332723617554,
|
|
"epoch": 2.0957233544938187,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004558138683675657,
|
|
"loss": 4.7411,
|
|
"mean_token_accuracy": 0.22347957491874695,
|
|
"num_tokens": 46158899.0,
|
|
"step": 25090
|
|
},
|
|
{
|
|
"entropy": 5.347688627243042,
|
|
"epoch": 2.096140995656532,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00045579614928571135,
|
|
"loss": 4.7848,
|
|
"mean_token_accuracy": 0.218346244096756,
|
|
"num_tokens": 46167813.0,
|
|
"step": 25095
|
|
},
|
|
{
|
|
"entropy": 5.2813661098480225,
|
|
"epoch": 2.096558636819245,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004557784270388028,
|
|
"loss": 4.6708,
|
|
"mean_token_accuracy": 0.23344496488571168,
|
|
"num_tokens": 46176440.0,
|
|
"step": 25100
|
|
},
|
|
{
|
|
"entropy": 5.335256910324096,
|
|
"epoch": 2.096976277981958,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00045576070162715025,
|
|
"loss": 4.6736,
|
|
"mean_token_accuracy": 0.2354566603899002,
|
|
"num_tokens": 46186354.0,
|
|
"step": 25105
|
|
},
|
|
{
|
|
"entropy": 5.316839742660522,
|
|
"epoch": 2.097393919144671,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.000455742973051064,
|
|
"loss": 4.6903,
|
|
"mean_token_accuracy": 0.22797414660453796,
|
|
"num_tokens": 46194819.0,
|
|
"step": 25110
|
|
},
|
|
{
|
|
"entropy": 5.373852205276489,
|
|
"epoch": 2.0978115603073837,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004557252413108545,
|
|
"loss": 4.8642,
|
|
"mean_token_accuracy": 0.21651583015918732,
|
|
"num_tokens": 46205687.0,
|
|
"step": 25115
|
|
},
|
|
{
|
|
"entropy": 5.41997504234314,
|
|
"epoch": 2.098229201470097,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00045570750640683207,
|
|
"loss": 4.8712,
|
|
"mean_token_accuracy": 0.2131803274154663,
|
|
"num_tokens": 46214990.0,
|
|
"step": 25120
|
|
},
|
|
{
|
|
"entropy": 5.367510366439819,
|
|
"epoch": 2.0986468426328098,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004556897683393073,
|
|
"loss": 4.7605,
|
|
"mean_token_accuracy": 0.22172411680221557,
|
|
"num_tokens": 46224325.0,
|
|
"step": 25125
|
|
},
|
|
{
|
|
"entropy": 5.393207836151123,
|
|
"epoch": 2.099064483795523,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00045567202710859056,
|
|
"loss": 4.8421,
|
|
"mean_token_accuracy": 0.21849920004606246,
|
|
"num_tokens": 46234199.0,
|
|
"step": 25130
|
|
},
|
|
{
|
|
"entropy": 5.404677963256836,
|
|
"epoch": 2.099482124958236,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004556542827149926,
|
|
"loss": 4.7394,
|
|
"mean_token_accuracy": 0.2286156088113785,
|
|
"num_tokens": 46243633.0,
|
|
"step": 25135
|
|
},
|
|
{
|
|
"entropy": 5.304386711120605,
|
|
"epoch": 2.099899766120949,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004556365351588239,
|
|
"loss": 4.6287,
|
|
"mean_token_accuracy": 0.23680509626865387,
|
|
"num_tokens": 46252994.0,
|
|
"step": 25140
|
|
},
|
|
{
|
|
"entropy": 5.303114128112793,
|
|
"epoch": 2.100317407283662,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00045561878444039526,
|
|
"loss": 4.8178,
|
|
"mean_token_accuracy": 0.23069968223571777,
|
|
"num_tokens": 46262455.0,
|
|
"step": 25145
|
|
},
|
|
{
|
|
"entropy": 5.365910291671753,
|
|
"epoch": 2.1007350484463747,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00045560103056001733,
|
|
"loss": 4.8086,
|
|
"mean_token_accuracy": 0.21550295054912566,
|
|
"num_tokens": 46271864.0,
|
|
"step": 25150
|
|
},
|
|
{
|
|
"entropy": 5.357066249847412,
|
|
"epoch": 2.101152689609088,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000455583273518001,
|
|
"loss": 4.6731,
|
|
"mean_token_accuracy": 0.23401331305503845,
|
|
"num_tokens": 46281244.0,
|
|
"step": 25155
|
|
},
|
|
{
|
|
"entropy": 5.298475170135498,
|
|
"epoch": 2.1015703307718008,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004555655133146571,
|
|
"loss": 4.6944,
|
|
"mean_token_accuracy": 0.22810235917568206,
|
|
"num_tokens": 46291145.0,
|
|
"step": 25160
|
|
},
|
|
{
|
|
"entropy": 5.314256477355957,
|
|
"epoch": 2.101987971934514,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004555477499502965,
|
|
"loss": 4.7768,
|
|
"mean_token_accuracy": 0.22638454288244247,
|
|
"num_tokens": 46300484.0,
|
|
"step": 25165
|
|
},
|
|
{
|
|
"entropy": 5.3942946434021,
|
|
"epoch": 2.102405613097227,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004555299834252303,
|
|
"loss": 4.7412,
|
|
"mean_token_accuracy": 0.2308497503399849,
|
|
"num_tokens": 46309598.0,
|
|
"step": 25170
|
|
},
|
|
{
|
|
"entropy": 5.467367124557495,
|
|
"epoch": 2.1028232542599397,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004555122137397694,
|
|
"loss": 4.8085,
|
|
"mean_token_accuracy": 0.22104108333587646,
|
|
"num_tokens": 46318410.0,
|
|
"step": 25175
|
|
},
|
|
{
|
|
"entropy": 5.466929817199707,
|
|
"epoch": 2.103240895422653,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00045549444089422486,
|
|
"loss": 4.9092,
|
|
"mean_token_accuracy": 0.21039922386407853,
|
|
"num_tokens": 46327011.0,
|
|
"step": 25180
|
|
},
|
|
{
|
|
"entropy": 5.39545202255249,
|
|
"epoch": 2.1036585365853657,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00045547666488890794,
|
|
"loss": 4.7831,
|
|
"mean_token_accuracy": 0.23082932978868484,
|
|
"num_tokens": 46335935.0,
|
|
"step": 25185
|
|
},
|
|
{
|
|
"entropy": 5.3404951095581055,
|
|
"epoch": 2.104076177748079,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004554588857241297,
|
|
"loss": 4.7796,
|
|
"mean_token_accuracy": 0.22483416348695756,
|
|
"num_tokens": 46344820.0,
|
|
"step": 25190
|
|
},
|
|
{
|
|
"entropy": 5.316776943206787,
|
|
"epoch": 2.104493818910792,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00045544110340020155,
|
|
"loss": 4.7136,
|
|
"mean_token_accuracy": 0.22655088156461717,
|
|
"num_tokens": 46353484.0,
|
|
"step": 25195
|
|
},
|
|
{
|
|
"entropy": 5.359583997726441,
|
|
"epoch": 2.104911460073505,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004554233179174346,
|
|
"loss": 4.7865,
|
|
"mean_token_accuracy": 0.21442825496196746,
|
|
"num_tokens": 46362539.0,
|
|
"step": 25200
|
|
},
|
|
{
|
|
"entropy": 5.396735048294067,
|
|
"epoch": 2.105329101236218,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004554055292761403,
|
|
"loss": 4.7835,
|
|
"mean_token_accuracy": 0.2318676382303238,
|
|
"num_tokens": 46372750.0,
|
|
"step": 25205
|
|
},
|
|
{
|
|
"entropy": 5.408140182495117,
|
|
"epoch": 2.1057467423989307,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004553877374766301,
|
|
"loss": 4.7731,
|
|
"mean_token_accuracy": 0.22678581178188323,
|
|
"num_tokens": 46381891.0,
|
|
"step": 25210
|
|
},
|
|
{
|
|
"entropy": 5.359846305847168,
|
|
"epoch": 2.106164383561644,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00045536994251921535,
|
|
"loss": 4.7142,
|
|
"mean_token_accuracy": 0.23331438153982162,
|
|
"num_tokens": 46391013.0,
|
|
"step": 25215
|
|
},
|
|
{
|
|
"entropy": 5.365855360031128,
|
|
"epoch": 2.1065820247243567,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004553521444042077,
|
|
"loss": 4.7225,
|
|
"mean_token_accuracy": 0.22775974422693251,
|
|
"num_tokens": 46400527.0,
|
|
"step": 25220
|
|
},
|
|
{
|
|
"entropy": 5.426879644393921,
|
|
"epoch": 2.10699966588707,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00045533434313191866,
|
|
"loss": 4.839,
|
|
"mean_token_accuracy": 0.21906005442142487,
|
|
"num_tokens": 46409869.0,
|
|
"step": 25225
|
|
},
|
|
{
|
|
"entropy": 5.2970232486724855,
|
|
"epoch": 2.107417307049783,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00045531653870265994,
|
|
"loss": 4.6691,
|
|
"mean_token_accuracy": 0.23273303657770156,
|
|
"num_tokens": 46418644.0,
|
|
"step": 25230
|
|
},
|
|
{
|
|
"entropy": 5.331310653686524,
|
|
"epoch": 2.1078349482124956,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004552987311167431,
|
|
"loss": 4.7224,
|
|
"mean_token_accuracy": 0.2357322484254837,
|
|
"num_tokens": 46427475.0,
|
|
"step": 25235
|
|
},
|
|
{
|
|
"entropy": 5.46616005897522,
|
|
"epoch": 2.108252589375209,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00045528092037447994,
|
|
"loss": 4.903,
|
|
"mean_token_accuracy": 0.21581933796405792,
|
|
"num_tokens": 46437322.0,
|
|
"step": 25240
|
|
},
|
|
{
|
|
"entropy": 5.412020015716553,
|
|
"epoch": 2.1086702305379217,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004552631064761822,
|
|
"loss": 4.7539,
|
|
"mean_token_accuracy": 0.22696929425001144,
|
|
"num_tokens": 46446193.0,
|
|
"step": 25245
|
|
},
|
|
{
|
|
"entropy": 5.347044610977173,
|
|
"epoch": 2.109087871700635,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004552452894221619,
|
|
"loss": 4.6617,
|
|
"mean_token_accuracy": 0.23740881085395812,
|
|
"num_tokens": 46455351.0,
|
|
"step": 25250
|
|
},
|
|
{
|
|
"entropy": 5.370610094070434,
|
|
"epoch": 2.1095055128633478,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00045522746921273084,
|
|
"loss": 4.7824,
|
|
"mean_token_accuracy": 0.22136637270450593,
|
|
"num_tokens": 46464056.0,
|
|
"step": 25255
|
|
},
|
|
{
|
|
"entropy": 5.346927547454834,
|
|
"epoch": 2.109923154026061,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00045520964584820097,
|
|
"loss": 4.6662,
|
|
"mean_token_accuracy": 0.2361921638250351,
|
|
"num_tokens": 46472654.0,
|
|
"step": 25260
|
|
},
|
|
{
|
|
"entropy": 5.360702991485596,
|
|
"epoch": 2.110340795188774,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004551918193288844,
|
|
"loss": 4.7889,
|
|
"mean_token_accuracy": 0.22815436124801636,
|
|
"num_tokens": 46482075.0,
|
|
"step": 25265
|
|
},
|
|
{
|
|
"entropy": 5.297659826278687,
|
|
"epoch": 2.1107584363514866,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00045517398965509297,
|
|
"loss": 4.7098,
|
|
"mean_token_accuracy": 0.22779383808374404,
|
|
"num_tokens": 46490353.0,
|
|
"step": 25270
|
|
},
|
|
{
|
|
"entropy": 5.301954984664917,
|
|
"epoch": 2.1111760775142,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00045515615682713913,
|
|
"loss": 4.6634,
|
|
"mean_token_accuracy": 0.23205984383821487,
|
|
"num_tokens": 46499332.0,
|
|
"step": 25275
|
|
},
|
|
{
|
|
"entropy": 5.403940725326538,
|
|
"epoch": 2.1115937186769127,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00045513832084533484,
|
|
"loss": 4.8236,
|
|
"mean_token_accuracy": 0.22457309067249298,
|
|
"num_tokens": 46508824.0,
|
|
"step": 25280
|
|
},
|
|
{
|
|
"entropy": 5.469573545455932,
|
|
"epoch": 2.112011359839626,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004551204817099924,
|
|
"loss": 4.8155,
|
|
"mean_token_accuracy": 0.22150532007217408,
|
|
"num_tokens": 46518262.0,
|
|
"step": 25285
|
|
},
|
|
{
|
|
"entropy": 5.4080362796783445,
|
|
"epoch": 2.1124290010023388,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00045510263942142416,
|
|
"loss": 4.8168,
|
|
"mean_token_accuracy": 0.22307446002960205,
|
|
"num_tokens": 46527463.0,
|
|
"step": 25290
|
|
},
|
|
{
|
|
"entropy": 5.3704852104187015,
|
|
"epoch": 2.1128466421650516,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004550847939799424,
|
|
"loss": 4.7891,
|
|
"mean_token_accuracy": 0.22084149718284607,
|
|
"num_tokens": 46537380.0,
|
|
"step": 25295
|
|
},
|
|
{
|
|
"entropy": 5.368821811676026,
|
|
"epoch": 2.113264283327765,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00045506694538585956,
|
|
"loss": 4.7381,
|
|
"mean_token_accuracy": 0.22984265238046647,
|
|
"num_tokens": 46546664.0,
|
|
"step": 25300
|
|
},
|
|
{
|
|
"entropy": 5.330706357955933,
|
|
"epoch": 2.1136819244904776,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004550490936394881,
|
|
"loss": 4.7741,
|
|
"mean_token_accuracy": 0.22913794815540314,
|
|
"num_tokens": 46555180.0,
|
|
"step": 25305
|
|
},
|
|
{
|
|
"entropy": 5.497490119934082,
|
|
"epoch": 2.114099565653191,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004550312387411406,
|
|
"loss": 4.8916,
|
|
"mean_token_accuracy": 0.21692889034748078,
|
|
"num_tokens": 46565450.0,
|
|
"step": 25310
|
|
},
|
|
{
|
|
"entropy": 5.447471046447754,
|
|
"epoch": 2.1145172068159037,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004550133806911295,
|
|
"loss": 4.8468,
|
|
"mean_token_accuracy": 0.21725940704345703,
|
|
"num_tokens": 46574453.0,
|
|
"step": 25315
|
|
},
|
|
{
|
|
"entropy": 5.396336889266967,
|
|
"epoch": 2.114934847978617,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004549955194897674,
|
|
"loss": 4.8037,
|
|
"mean_token_accuracy": 0.22684547752141954,
|
|
"num_tokens": 46584341.0,
|
|
"step": 25320
|
|
},
|
|
{
|
|
"entropy": 5.371750020980835,
|
|
"epoch": 2.11535248914133,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00045497765513736717,
|
|
"loss": 4.7438,
|
|
"mean_token_accuracy": 0.2189422592520714,
|
|
"num_tokens": 46593247.0,
|
|
"step": 25325
|
|
},
|
|
{
|
|
"entropy": 5.402415084838867,
|
|
"epoch": 2.1157701303040426,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00045495978763424147,
|
|
"loss": 4.7781,
|
|
"mean_token_accuracy": 0.2247992917895317,
|
|
"num_tokens": 46602410.0,
|
|
"step": 25330
|
|
},
|
|
{
|
|
"entropy": 5.375433492660522,
|
|
"epoch": 2.116187771466756,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00045494191698070295,
|
|
"loss": 4.7181,
|
|
"mean_token_accuracy": 0.23156434893608094,
|
|
"num_tokens": 46611348.0,
|
|
"step": 25335
|
|
},
|
|
{
|
|
"entropy": 5.423616123199463,
|
|
"epoch": 2.1166054126294687,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00045492404317706473,
|
|
"loss": 4.8076,
|
|
"mean_token_accuracy": 0.22584243416786193,
|
|
"num_tokens": 46621416.0,
|
|
"step": 25340
|
|
},
|
|
{
|
|
"entropy": 5.419959354400635,
|
|
"epoch": 2.117023053792182,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004549061662236394,
|
|
"loss": 4.8278,
|
|
"mean_token_accuracy": 0.21940691769123077,
|
|
"num_tokens": 46631839.0,
|
|
"step": 25345
|
|
},
|
|
{
|
|
"entropy": 5.340674114227295,
|
|
"epoch": 2.1174406949548947,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004548882861207402,
|
|
"loss": 4.6828,
|
|
"mean_token_accuracy": 0.23984625339508056,
|
|
"num_tokens": 46640662.0,
|
|
"step": 25350
|
|
},
|
|
{
|
|
"entropy": 5.366677474975586,
|
|
"epoch": 2.1178583361176075,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00045487040286868,
|
|
"loss": 4.7882,
|
|
"mean_token_accuracy": 0.2221937045454979,
|
|
"num_tokens": 46649399.0,
|
|
"step": 25355
|
|
},
|
|
{
|
|
"entropy": 5.341585731506347,
|
|
"epoch": 2.118275977280321,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00045485251646777187,
|
|
"loss": 4.6878,
|
|
"mean_token_accuracy": 0.22687719613313675,
|
|
"num_tokens": 46658020.0,
|
|
"step": 25360
|
|
},
|
|
{
|
|
"entropy": 5.374461698532104,
|
|
"epoch": 2.1186936184430336,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004548346269183289,
|
|
"loss": 4.774,
|
|
"mean_token_accuracy": 0.22425119429826737,
|
|
"num_tokens": 46666815.0,
|
|
"step": 25365
|
|
},
|
|
{
|
|
"entropy": 5.329046249389648,
|
|
"epoch": 2.119111259605747,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00045481673422066444,
|
|
"loss": 4.7206,
|
|
"mean_token_accuracy": 0.22458860129117966,
|
|
"num_tokens": 46675582.0,
|
|
"step": 25370
|
|
},
|
|
{
|
|
"entropy": 5.411424875259399,
|
|
"epoch": 2.1195289007684597,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004547988383750915,
|
|
"loss": 4.9109,
|
|
"mean_token_accuracy": 0.2142823740839958,
|
|
"num_tokens": 46686385.0,
|
|
"step": 25375
|
|
},
|
|
{
|
|
"entropy": 5.413477039337158,
|
|
"epoch": 2.119946541931173,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004547809393819235,
|
|
"loss": 4.7944,
|
|
"mean_token_accuracy": 0.2264533132314682,
|
|
"num_tokens": 46695445.0,
|
|
"step": 25380
|
|
},
|
|
{
|
|
"entropy": 5.441389083862305,
|
|
"epoch": 2.1203641830938857,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004547630372414737,
|
|
"loss": 4.7599,
|
|
"mean_token_accuracy": 0.22976809293031691,
|
|
"num_tokens": 46704562.0,
|
|
"step": 25385
|
|
},
|
|
{
|
|
"entropy": 5.394317722320556,
|
|
"epoch": 2.1207818242565986,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004547451319540557,
|
|
"loss": 4.8121,
|
|
"mean_token_accuracy": 0.22455304861068726,
|
|
"num_tokens": 46713736.0,
|
|
"step": 25390
|
|
},
|
|
{
|
|
"entropy": 5.33385009765625,
|
|
"epoch": 2.121199465419312,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004547272235199826,
|
|
"loss": 4.7093,
|
|
"mean_token_accuracy": 0.22709453701972962,
|
|
"num_tokens": 46723160.0,
|
|
"step": 25395
|
|
},
|
|
{
|
|
"entropy": 5.362745523452759,
|
|
"epoch": 2.1216171065820246,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004547093119395683,
|
|
"loss": 4.7363,
|
|
"mean_token_accuracy": 0.22265269011259078,
|
|
"num_tokens": 46732840.0,
|
|
"step": 25400
|
|
},
|
|
{
|
|
"entropy": 5.329989814758301,
|
|
"epoch": 2.122034747744738,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00045469139721312607,
|
|
"loss": 4.7176,
|
|
"mean_token_accuracy": 0.24137801676988602,
|
|
"num_tokens": 46742483.0,
|
|
"step": 25405
|
|
},
|
|
{
|
|
"entropy": 5.275213527679443,
|
|
"epoch": 2.1224523889074507,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004546734793409697,
|
|
"loss": 4.6967,
|
|
"mean_token_accuracy": 0.22844159752130508,
|
|
"num_tokens": 46751217.0,
|
|
"step": 25410
|
|
},
|
|
{
|
|
"entropy": 5.366234636306762,
|
|
"epoch": 2.1228700300701635,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004546555583234128,
|
|
"loss": 4.7048,
|
|
"mean_token_accuracy": 0.22770241200923919,
|
|
"num_tokens": 46759978.0,
|
|
"step": 25415
|
|
},
|
|
{
|
|
"entropy": 5.391072988510132,
|
|
"epoch": 2.1232876712328768,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000454637634160769,
|
|
"loss": 4.743,
|
|
"mean_token_accuracy": 0.2254280522465706,
|
|
"num_tokens": 46768635.0,
|
|
"step": 25420
|
|
},
|
|
{
|
|
"entropy": 5.41120023727417,
|
|
"epoch": 2.1237053123955896,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004546197068533523,
|
|
"loss": 4.8447,
|
|
"mean_token_accuracy": 0.21839238703250885,
|
|
"num_tokens": 46778123.0,
|
|
"step": 25425
|
|
},
|
|
{
|
|
"entropy": 5.4013715267181395,
|
|
"epoch": 2.124122953558303,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004546017764014764,
|
|
"loss": 4.7952,
|
|
"mean_token_accuracy": 0.22389546185731887,
|
|
"num_tokens": 46787821.0,
|
|
"step": 25430
|
|
},
|
|
{
|
|
"entropy": 5.272259616851807,
|
|
"epoch": 2.1245405947210156,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004545838428054552,
|
|
"loss": 4.7187,
|
|
"mean_token_accuracy": 0.2346959888935089,
|
|
"num_tokens": 46796419.0,
|
|
"step": 25435
|
|
},
|
|
{
|
|
"entropy": 5.370900964736938,
|
|
"epoch": 2.124958235883729,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004545659060656027,
|
|
"loss": 4.7151,
|
|
"mean_token_accuracy": 0.22411196827888488,
|
|
"num_tokens": 46805342.0,
|
|
"step": 25440
|
|
},
|
|
{
|
|
"entropy": 5.460942220687866,
|
|
"epoch": 2.1253758770464417,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004545479661822328,
|
|
"loss": 4.7919,
|
|
"mean_token_accuracy": 0.22603249102830886,
|
|
"num_tokens": 46813432.0,
|
|
"step": 25445
|
|
},
|
|
{
|
|
"entropy": 5.3836287498474125,
|
|
"epoch": 2.1257935182091545,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00045453002315565965,
|
|
"loss": 4.8542,
|
|
"mean_token_accuracy": 0.2222834348678589,
|
|
"num_tokens": 46823023.0,
|
|
"step": 25450
|
|
},
|
|
{
|
|
"entropy": 5.378014993667603,
|
|
"epoch": 2.1262111593718678,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004545120769861974,
|
|
"loss": 4.7332,
|
|
"mean_token_accuracy": 0.23450630009174347,
|
|
"num_tokens": 46832187.0,
|
|
"step": 25455
|
|
},
|
|
{
|
|
"entropy": 5.3783704280853275,
|
|
"epoch": 2.1266288005345806,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004544941276741601,
|
|
"loss": 4.7617,
|
|
"mean_token_accuracy": 0.2285197749733925,
|
|
"num_tokens": 46840122.0,
|
|
"step": 25460
|
|
},
|
|
{
|
|
"entropy": 5.370003747940063,
|
|
"epoch": 2.127046441697294,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00045447617521986205,
|
|
"loss": 4.7137,
|
|
"mean_token_accuracy": 0.2310202106833458,
|
|
"num_tokens": 46848854.0,
|
|
"step": 25465
|
|
},
|
|
{
|
|
"entropy": 5.378884553909302,
|
|
"epoch": 2.1274640828600067,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004544582196236175,
|
|
"loss": 4.7827,
|
|
"mean_token_accuracy": 0.22440667897462846,
|
|
"num_tokens": 46859182.0,
|
|
"step": 25470
|
|
},
|
|
{
|
|
"entropy": 5.357527399063111,
|
|
"epoch": 2.1278817240227195,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004544402608857409,
|
|
"loss": 4.6854,
|
|
"mean_token_accuracy": 0.2321048602461815,
|
|
"num_tokens": 46867856.0,
|
|
"step": 25475
|
|
},
|
|
{
|
|
"entropy": 5.3323082447052,
|
|
"epoch": 2.1282993651854327,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004544222990065464,
|
|
"loss": 4.7432,
|
|
"mean_token_accuracy": 0.22663947194814682,
|
|
"num_tokens": 46876793.0,
|
|
"step": 25480
|
|
},
|
|
{
|
|
"entropy": 5.299347448348999,
|
|
"epoch": 2.1287170063481455,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00045440433398634866,
|
|
"loss": 4.7215,
|
|
"mean_token_accuracy": 0.23178915232419967,
|
|
"num_tokens": 46885342.0,
|
|
"step": 25485
|
|
},
|
|
{
|
|
"entropy": 5.37336802482605,
|
|
"epoch": 2.129134647510859,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004543863658254622,
|
|
"loss": 4.7723,
|
|
"mean_token_accuracy": 0.2233823612332344,
|
|
"num_tokens": 46895742.0,
|
|
"step": 25490
|
|
},
|
|
{
|
|
"entropy": 5.402439165115356,
|
|
"epoch": 2.1295522886735716,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004543683945242013,
|
|
"loss": 4.754,
|
|
"mean_token_accuracy": 0.22856451570987701,
|
|
"num_tokens": 46905130.0,
|
|
"step": 25495
|
|
},
|
|
{
|
|
"entropy": 5.325080537796021,
|
|
"epoch": 2.129969929836285,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00045435042008288093,
|
|
"loss": 4.7162,
|
|
"mean_token_accuracy": 0.2305121600627899,
|
|
"num_tokens": 46913939.0,
|
|
"step": 25500
|
|
},
|
|
{
|
|
"entropy": 5.374012088775634,
|
|
"epoch": 2.1303875709989977,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00045433244250181535,
|
|
"loss": 4.786,
|
|
"mean_token_accuracy": 0.2274991065263748,
|
|
"num_tokens": 46922308.0,
|
|
"step": 25505
|
|
},
|
|
{
|
|
"entropy": 5.394248533248901,
|
|
"epoch": 2.1308052121617105,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00045431446178131966,
|
|
"loss": 4.8566,
|
|
"mean_token_accuracy": 0.22385746985673904,
|
|
"num_tokens": 46931472.0,
|
|
"step": 25510
|
|
},
|
|
{
|
|
"entropy": 5.278803396224975,
|
|
"epoch": 2.1312228533244237,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004542964779217085,
|
|
"loss": 4.6845,
|
|
"mean_token_accuracy": 0.22899451851844788,
|
|
"num_tokens": 46940017.0,
|
|
"step": 25515
|
|
},
|
|
{
|
|
"entropy": 5.2315051555633545,
|
|
"epoch": 2.1316404944871366,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00045427849092329655,
|
|
"loss": 4.6808,
|
|
"mean_token_accuracy": 0.22810709178447724,
|
|
"num_tokens": 46949045.0,
|
|
"step": 25520
|
|
},
|
|
{
|
|
"entropy": 5.330432271957397,
|
|
"epoch": 2.13205813564985,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00045426050078639884,
|
|
"loss": 4.7078,
|
|
"mean_token_accuracy": 0.22828739881515503,
|
|
"num_tokens": 46957845.0,
|
|
"step": 25525
|
|
},
|
|
{
|
|
"entropy": 5.367407178878784,
|
|
"epoch": 2.1324757768125626,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004542425075113303,
|
|
"loss": 4.6989,
|
|
"mean_token_accuracy": 0.2273884415626526,
|
|
"num_tokens": 46966932.0,
|
|
"step": 25530
|
|
},
|
|
{
|
|
"entropy": 5.354869174957275,
|
|
"epoch": 2.132893417975276,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00045422451109840604,
|
|
"loss": 4.778,
|
|
"mean_token_accuracy": 0.22028178721666336,
|
|
"num_tokens": 46976362.0,
|
|
"step": 25535
|
|
},
|
|
{
|
|
"entropy": 5.298830318450928,
|
|
"epoch": 2.1333110591379887,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00045420651154794086,
|
|
"loss": 4.7029,
|
|
"mean_token_accuracy": 0.2329714924097061,
|
|
"num_tokens": 46985311.0,
|
|
"step": 25540
|
|
},
|
|
{
|
|
"entropy": 5.411695432662964,
|
|
"epoch": 2.1337287003007015,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00045418850886025006,
|
|
"loss": 4.7746,
|
|
"mean_token_accuracy": 0.22489850968122482,
|
|
"num_tokens": 46994666.0,
|
|
"step": 25545
|
|
},
|
|
{
|
|
"entropy": 5.338853025436402,
|
|
"epoch": 2.1341463414634148,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00045417050303564867,
|
|
"loss": 4.7223,
|
|
"mean_token_accuracy": 0.22748591303825377,
|
|
"num_tokens": 47003894.0,
|
|
"step": 25550
|
|
},
|
|
{
|
|
"entropy": 5.275294256210327,
|
|
"epoch": 2.1345639826261276,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00045415249407445196,
|
|
"loss": 4.6492,
|
|
"mean_token_accuracy": 0.23699040114879608,
|
|
"num_tokens": 47012556.0,
|
|
"step": 25555
|
|
},
|
|
{
|
|
"entropy": 5.341293525695801,
|
|
"epoch": 2.134981623788841,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004541344819769751,
|
|
"loss": 4.7356,
|
|
"mean_token_accuracy": 0.22635118514299393,
|
|
"num_tokens": 47022085.0,
|
|
"step": 25560
|
|
},
|
|
{
|
|
"entropy": 5.316389894485473,
|
|
"epoch": 2.1353992649515536,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00045411646674353365,
|
|
"loss": 4.6942,
|
|
"mean_token_accuracy": 0.23817168176174164,
|
|
"num_tokens": 47030759.0,
|
|
"step": 25565
|
|
},
|
|
{
|
|
"entropy": 5.36383318901062,
|
|
"epoch": 2.1358169061142664,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00045409844837444283,
|
|
"loss": 4.7633,
|
|
"mean_token_accuracy": 0.22074048966169357,
|
|
"num_tokens": 47039877.0,
|
|
"step": 25570
|
|
},
|
|
{
|
|
"entropy": 5.281466484069824,
|
|
"epoch": 2.1362345472769797,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00045408042687001806,
|
|
"loss": 4.7188,
|
|
"mean_token_accuracy": 0.22791993618011475,
|
|
"num_tokens": 47049500.0,
|
|
"step": 25575
|
|
},
|
|
{
|
|
"entropy": 5.394750499725342,
|
|
"epoch": 2.1366521884396925,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004540624022305749,
|
|
"loss": 4.7903,
|
|
"mean_token_accuracy": 0.22255310863256456,
|
|
"num_tokens": 47059377.0,
|
|
"step": 25580
|
|
},
|
|
{
|
|
"entropy": 5.364715147018432,
|
|
"epoch": 2.1370698296024058,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004540443744564288,
|
|
"loss": 4.756,
|
|
"mean_token_accuracy": 0.22991041392087935,
|
|
"num_tokens": 47068263.0,
|
|
"step": 25585
|
|
},
|
|
{
|
|
"entropy": 5.420015096664429,
|
|
"epoch": 2.1374874707651186,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004540263435478953,
|
|
"loss": 4.89,
|
|
"mean_token_accuracy": 0.21659699082374573,
|
|
"num_tokens": 47077752.0,
|
|
"step": 25590
|
|
},
|
|
{
|
|
"entropy": 5.383623743057251,
|
|
"epoch": 2.1379051119278314,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00045400830950529037,
|
|
"loss": 4.7577,
|
|
"mean_token_accuracy": 0.22667249888181687,
|
|
"num_tokens": 47087013.0,
|
|
"step": 25595
|
|
},
|
|
{
|
|
"entropy": 5.274302959442139,
|
|
"epoch": 2.1383227530905446,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004539902723289294,
|
|
"loss": 4.6866,
|
|
"mean_token_accuracy": 0.23219695389270784,
|
|
"num_tokens": 47096502.0,
|
|
"step": 25600
|
|
},
|
|
{
|
|
"entropy": 5.39038782119751,
|
|
"epoch": 2.1387403942532575,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00045397223201912827,
|
|
"loss": 4.8285,
|
|
"mean_token_accuracy": 0.2274508446455002,
|
|
"num_tokens": 47105347.0,
|
|
"step": 25605
|
|
},
|
|
{
|
|
"entropy": 5.325994062423706,
|
|
"epoch": 2.1391580354159707,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004539541885762028,
|
|
"loss": 4.659,
|
|
"mean_token_accuracy": 0.23257651329040527,
|
|
"num_tokens": 47114137.0,
|
|
"step": 25610
|
|
},
|
|
{
|
|
"entropy": 5.372339105606079,
|
|
"epoch": 2.1395756765786835,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004539361420004689,
|
|
"loss": 4.7895,
|
|
"mean_token_accuracy": 0.22258234322071074,
|
|
"num_tokens": 47123366.0,
|
|
"step": 25615
|
|
},
|
|
{
|
|
"entropy": 5.40915813446045,
|
|
"epoch": 2.139993317741397,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00045391809229224236,
|
|
"loss": 4.7467,
|
|
"mean_token_accuracy": 0.2276761308312416,
|
|
"num_tokens": 47132129.0,
|
|
"step": 25620
|
|
},
|
|
{
|
|
"entropy": 5.3562726974487305,
|
|
"epoch": 2.1404109589041096,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004539000394518393,
|
|
"loss": 4.8461,
|
|
"mean_token_accuracy": 0.22790828198194504,
|
|
"num_tokens": 47142860.0,
|
|
"step": 25625
|
|
},
|
|
{
|
|
"entropy": 5.361336612701416,
|
|
"epoch": 2.1408286000668224,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004538819834795757,
|
|
"loss": 4.8019,
|
|
"mean_token_accuracy": 0.2250615417957306,
|
|
"num_tokens": 47151942.0,
|
|
"step": 25630
|
|
},
|
|
{
|
|
"entropy": 5.359960603713989,
|
|
"epoch": 2.1412462412295357,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00045386392437576765,
|
|
"loss": 4.7762,
|
|
"mean_token_accuracy": 0.22313877940177917,
|
|
"num_tokens": 47160770.0,
|
|
"step": 25635
|
|
},
|
|
{
|
|
"entropy": 5.339232540130615,
|
|
"epoch": 2.1416638823922485,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00045384586214073134,
|
|
"loss": 4.7186,
|
|
"mean_token_accuracy": 0.22311947196722032,
|
|
"num_tokens": 47169514.0,
|
|
"step": 25640
|
|
},
|
|
{
|
|
"entropy": 5.387412643432617,
|
|
"epoch": 2.1420815235549617,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00045382779677478294,
|
|
"loss": 4.7184,
|
|
"mean_token_accuracy": 0.23078778386116028,
|
|
"num_tokens": 47178470.0,
|
|
"step": 25645
|
|
},
|
|
{
|
|
"entropy": 5.238980770111084,
|
|
"epoch": 2.1424991647176745,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00045380972827823866,
|
|
"loss": 4.639,
|
|
"mean_token_accuracy": 0.23552377820014953,
|
|
"num_tokens": 47187694.0,
|
|
"step": 25650
|
|
},
|
|
{
|
|
"entropy": 5.280775928497315,
|
|
"epoch": 2.142916805880388,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004537916566514149,
|
|
"loss": 4.6817,
|
|
"mean_token_accuracy": 0.23053658306598662,
|
|
"num_tokens": 47196205.0,
|
|
"step": 25655
|
|
},
|
|
{
|
|
"entropy": 5.354215335845947,
|
|
"epoch": 2.1433344470431006,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004537735818946279,
|
|
"loss": 4.6818,
|
|
"mean_token_accuracy": 0.22834357917308806,
|
|
"num_tokens": 47205834.0,
|
|
"step": 25660
|
|
},
|
|
{
|
|
"entropy": 5.3278656005859375,
|
|
"epoch": 2.1437520882058134,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004537555040081942,
|
|
"loss": 4.8378,
|
|
"mean_token_accuracy": 0.21984977573156356,
|
|
"num_tokens": 47215763.0,
|
|
"step": 25665
|
|
},
|
|
{
|
|
"entropy": 5.440545511245728,
|
|
"epoch": 2.1441697293685267,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00045373742299243026,
|
|
"loss": 4.8231,
|
|
"mean_token_accuracy": 0.2208309456706047,
|
|
"num_tokens": 47225536.0,
|
|
"step": 25670
|
|
},
|
|
{
|
|
"entropy": 5.39404525756836,
|
|
"epoch": 2.1445873705312395,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00045371933884765246,
|
|
"loss": 4.7923,
|
|
"mean_token_accuracy": 0.21847613900899887,
|
|
"num_tokens": 47235104.0,
|
|
"step": 25675
|
|
},
|
|
{
|
|
"entropy": 5.356334924697876,
|
|
"epoch": 2.1450050116939527,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004537012515741777,
|
|
"loss": 4.744,
|
|
"mean_token_accuracy": 0.22498596906661988,
|
|
"num_tokens": 47244312.0,
|
|
"step": 25680
|
|
},
|
|
{
|
|
"entropy": 5.317743825912475,
|
|
"epoch": 2.1454226528566656,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004536831611723223,
|
|
"loss": 4.7861,
|
|
"mean_token_accuracy": 0.22100625336170196,
|
|
"num_tokens": 47253174.0,
|
|
"step": 25685
|
|
},
|
|
{
|
|
"entropy": 5.379930830001831,
|
|
"epoch": 2.1458402940193784,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004536650676424032,
|
|
"loss": 4.7231,
|
|
"mean_token_accuracy": 0.22485494315624238,
|
|
"num_tokens": 47262742.0,
|
|
"step": 25690
|
|
},
|
|
{
|
|
"entropy": 5.449601697921753,
|
|
"epoch": 2.1462579351820916,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004536469709847369,
|
|
"loss": 4.8064,
|
|
"mean_token_accuracy": 0.22217636108398436,
|
|
"num_tokens": 47271667.0,
|
|
"step": 25695
|
|
},
|
|
{
|
|
"entropy": 5.312098407745362,
|
|
"epoch": 2.1466755763448044,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004536288711996404,
|
|
"loss": 4.6658,
|
|
"mean_token_accuracy": 0.22926115244627,
|
|
"num_tokens": 47280462.0,
|
|
"step": 25700
|
|
},
|
|
{
|
|
"entropy": 5.396351957321167,
|
|
"epoch": 2.1470932175075177,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00045361076828743054,
|
|
"loss": 4.8108,
|
|
"mean_token_accuracy": 0.223170767724514,
|
|
"num_tokens": 47290834.0,
|
|
"step": 25705
|
|
},
|
|
{
|
|
"entropy": 5.352685928344727,
|
|
"epoch": 2.1475108586702305,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004535926622484242,
|
|
"loss": 4.6912,
|
|
"mean_token_accuracy": 0.22967219799757005,
|
|
"num_tokens": 47300002.0,
|
|
"step": 25710
|
|
},
|
|
{
|
|
"entropy": 5.425787353515625,
|
|
"epoch": 2.1479284998329433,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00045357455308293816,
|
|
"loss": 4.8516,
|
|
"mean_token_accuracy": 0.22736880481243132,
|
|
"num_tokens": 47309299.0,
|
|
"step": 25715
|
|
},
|
|
{
|
|
"entropy": 5.321064281463623,
|
|
"epoch": 2.1483461409956566,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004535564407912898,
|
|
"loss": 4.7321,
|
|
"mean_token_accuracy": 0.2309819668531418,
|
|
"num_tokens": 47318680.0,
|
|
"step": 25720
|
|
},
|
|
{
|
|
"entropy": 5.34941873550415,
|
|
"epoch": 2.1487637821583694,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004535383253737959,
|
|
"loss": 4.7575,
|
|
"mean_token_accuracy": 0.21912575513124466,
|
|
"num_tokens": 47329841.0,
|
|
"step": 25725
|
|
},
|
|
{
|
|
"entropy": 5.418654870986939,
|
|
"epoch": 2.1491814233210826,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004535202068307737,
|
|
"loss": 4.807,
|
|
"mean_token_accuracy": 0.21453968435525894,
|
|
"num_tokens": 47338962.0,
|
|
"step": 25730
|
|
},
|
|
{
|
|
"entropy": 5.396681404113769,
|
|
"epoch": 2.1495990644837955,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004535020851625405,
|
|
"loss": 4.787,
|
|
"mean_token_accuracy": 0.22099054604768753,
|
|
"num_tokens": 47348230.0,
|
|
"step": 25735
|
|
},
|
|
{
|
|
"entropy": 5.402753019332886,
|
|
"epoch": 2.1500167056465087,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00045348396036941336,
|
|
"loss": 4.7762,
|
|
"mean_token_accuracy": 0.21948406249284744,
|
|
"num_tokens": 47358694.0,
|
|
"step": 25740
|
|
},
|
|
{
|
|
"entropy": 5.400779342651367,
|
|
"epoch": 2.1504343468092215,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004534658324517097,
|
|
"loss": 4.743,
|
|
"mean_token_accuracy": 0.21982759088277817,
|
|
"num_tokens": 47368617.0,
|
|
"step": 25745
|
|
},
|
|
{
|
|
"entropy": 5.454337406158447,
|
|
"epoch": 2.1508519879719343,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004534477014097468,
|
|
"loss": 4.8555,
|
|
"mean_token_accuracy": 0.22085191011428834,
|
|
"num_tokens": 47377902.0,
|
|
"step": 25750
|
|
},
|
|
{
|
|
"entropy": 5.394212007522583,
|
|
"epoch": 2.1512696291346476,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00045342956724384205,
|
|
"loss": 4.7865,
|
|
"mean_token_accuracy": 0.23180295526981354,
|
|
"num_tokens": 47386337.0,
|
|
"step": 25755
|
|
},
|
|
{
|
|
"entropy": 5.361298322677612,
|
|
"epoch": 2.1516872702973604,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.000453411429954313,
|
|
"loss": 4.7384,
|
|
"mean_token_accuracy": 0.23279656022787093,
|
|
"num_tokens": 47395212.0,
|
|
"step": 25760
|
|
},
|
|
{
|
|
"entropy": 5.358047819137573,
|
|
"epoch": 2.1521049114600737,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004533932895414771,
|
|
"loss": 4.765,
|
|
"mean_token_accuracy": 0.22704824209213256,
|
|
"num_tokens": 47404296.0,
|
|
"step": 25765
|
|
},
|
|
{
|
|
"entropy": 5.340535354614258,
|
|
"epoch": 2.1525225526227865,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00045337514600565196,
|
|
"loss": 4.6855,
|
|
"mean_token_accuracy": 0.23700812608003616,
|
|
"num_tokens": 47413858.0,
|
|
"step": 25770
|
|
},
|
|
{
|
|
"entropy": 5.394547986984253,
|
|
"epoch": 2.1529401937854997,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00045335699934715513,
|
|
"loss": 4.7563,
|
|
"mean_token_accuracy": 0.22407521903514863,
|
|
"num_tokens": 47422502.0,
|
|
"step": 25775
|
|
},
|
|
{
|
|
"entropy": 5.359636878967285,
|
|
"epoch": 2.1533578349482125,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00045333884956630437,
|
|
"loss": 4.7276,
|
|
"mean_token_accuracy": 0.22838956415653228,
|
|
"num_tokens": 47431763.0,
|
|
"step": 25780
|
|
},
|
|
{
|
|
"entropy": 5.454285764694214,
|
|
"epoch": 2.1537754761109253,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00045332069666341733,
|
|
"loss": 4.8861,
|
|
"mean_token_accuracy": 0.21785472631454467,
|
|
"num_tokens": 47441261.0,
|
|
"step": 25785
|
|
},
|
|
{
|
|
"entropy": 5.398948669433594,
|
|
"epoch": 2.1541931172736386,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004533025406388119,
|
|
"loss": 4.8024,
|
|
"mean_token_accuracy": 0.22058825343847274,
|
|
"num_tokens": 47450028.0,
|
|
"step": 25790
|
|
},
|
|
{
|
|
"entropy": 5.416061782836914,
|
|
"epoch": 2.1546107584363514,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004532843814928059,
|
|
"loss": 4.8321,
|
|
"mean_token_accuracy": 0.22652218341827393,
|
|
"num_tokens": 47459617.0,
|
|
"step": 25795
|
|
},
|
|
{
|
|
"entropy": 5.397178077697754,
|
|
"epoch": 2.1550283995990647,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004532662192257172,
|
|
"loss": 4.6804,
|
|
"mean_token_accuracy": 0.2330893024802208,
|
|
"num_tokens": 47468748.0,
|
|
"step": 25800
|
|
},
|
|
{
|
|
"entropy": 5.378011703491211,
|
|
"epoch": 2.1554460407617775,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004532480538378637,
|
|
"loss": 4.6789,
|
|
"mean_token_accuracy": 0.2304944396018982,
|
|
"num_tokens": 47477294.0,
|
|
"step": 25805
|
|
},
|
|
{
|
|
"entropy": 5.411072635650635,
|
|
"epoch": 2.1558636819244903,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00045322988532956344,
|
|
"loss": 4.8325,
|
|
"mean_token_accuracy": 0.21655416637659072,
|
|
"num_tokens": 47486733.0,
|
|
"step": 25810
|
|
},
|
|
{
|
|
"entropy": 5.334699249267578,
|
|
"epoch": 2.1562813230872035,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00045321171370113456,
|
|
"loss": 4.6996,
|
|
"mean_token_accuracy": 0.22684395164251328,
|
|
"num_tokens": 47495472.0,
|
|
"step": 25815
|
|
},
|
|
{
|
|
"entropy": 5.380471992492676,
|
|
"epoch": 2.1566989642499164,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004531935389528951,
|
|
"loss": 4.7933,
|
|
"mean_token_accuracy": 0.22644713073968886,
|
|
"num_tokens": 47505048.0,
|
|
"step": 25820
|
|
},
|
|
{
|
|
"entropy": 5.3306663036346436,
|
|
"epoch": 2.1571166054126296,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004531753610851633,
|
|
"loss": 4.7369,
|
|
"mean_token_accuracy": 0.23079666644334793,
|
|
"num_tokens": 47513635.0,
|
|
"step": 25825
|
|
},
|
|
{
|
|
"entropy": 5.275088596343994,
|
|
"epoch": 2.1575342465753424,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004531571800982573,
|
|
"loss": 4.6873,
|
|
"mean_token_accuracy": 0.22882745563983917,
|
|
"num_tokens": 47522861.0,
|
|
"step": 25830
|
|
},
|
|
{
|
|
"entropy": 5.483554172515869,
|
|
"epoch": 2.1579518877380552,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00045313899599249536,
|
|
"loss": 4.8502,
|
|
"mean_token_accuracy": 0.21925020962953568,
|
|
"num_tokens": 47531986.0,
|
|
"step": 25835
|
|
},
|
|
{
|
|
"entropy": 5.406256866455078,
|
|
"epoch": 2.1583695289007685,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00045312080876819597,
|
|
"loss": 4.7944,
|
|
"mean_token_accuracy": 0.21338598132133485,
|
|
"num_tokens": 47542140.0,
|
|
"step": 25840
|
|
},
|
|
{
|
|
"entropy": 5.28157868385315,
|
|
"epoch": 2.1587871700634813,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004531026184256773,
|
|
"loss": 4.6363,
|
|
"mean_token_accuracy": 0.2335955634713173,
|
|
"num_tokens": 47550921.0,
|
|
"step": 25845
|
|
},
|
|
{
|
|
"entropy": 5.307586622238159,
|
|
"epoch": 2.1592048112261946,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000453084424965258,
|
|
"loss": 4.6227,
|
|
"mean_token_accuracy": 0.23878341019153596,
|
|
"num_tokens": 47560286.0,
|
|
"step": 25850
|
|
},
|
|
{
|
|
"entropy": 5.494336271286011,
|
|
"epoch": 2.1596224523889074,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00045306622838725644,
|
|
"loss": 4.8826,
|
|
"mean_token_accuracy": 0.21286779642105103,
|
|
"num_tokens": 47572089.0,
|
|
"step": 25855
|
|
},
|
|
{
|
|
"entropy": 5.405285882949829,
|
|
"epoch": 2.1600400935516206,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004530480286919912,
|
|
"loss": 4.7481,
|
|
"mean_token_accuracy": 0.22393743991851806,
|
|
"num_tokens": 47581602.0,
|
|
"step": 25860
|
|
},
|
|
{
|
|
"entropy": 5.355505180358887,
|
|
"epoch": 2.1604577347143334,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000453029825879781,
|
|
"loss": 4.7412,
|
|
"mean_token_accuracy": 0.23306675553321837,
|
|
"num_tokens": 47591138.0,
|
|
"step": 25865
|
|
},
|
|
{
|
|
"entropy": 5.3209981441497805,
|
|
"epoch": 2.1608753758770463,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00045301161995094433,
|
|
"loss": 4.6787,
|
|
"mean_token_accuracy": 0.23411506563425064,
|
|
"num_tokens": 47600182.0,
|
|
"step": 25870
|
|
},
|
|
{
|
|
"entropy": 5.43818736076355,
|
|
"epoch": 2.1612930170397595,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00045299341090579995,
|
|
"loss": 4.8922,
|
|
"mean_token_accuracy": 0.21834613084793092,
|
|
"num_tokens": 47610207.0,
|
|
"step": 25875
|
|
},
|
|
{
|
|
"entropy": 5.365955638885498,
|
|
"epoch": 2.1617106582024723,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004529751987446667,
|
|
"loss": 4.7333,
|
|
"mean_token_accuracy": 0.2286724328994751,
|
|
"num_tokens": 47620276.0,
|
|
"step": 25880
|
|
},
|
|
{
|
|
"entropy": 5.355332565307617,
|
|
"epoch": 2.1621282993651856,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004529569834678633,
|
|
"loss": 4.8326,
|
|
"mean_token_accuracy": 0.22702008485794067,
|
|
"num_tokens": 47630187.0,
|
|
"step": 25885
|
|
},
|
|
{
|
|
"entropy": 5.393225049972534,
|
|
"epoch": 2.1625459405278984,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004529387650757088,
|
|
"loss": 4.7457,
|
|
"mean_token_accuracy": 0.21933148056268692,
|
|
"num_tokens": 47639187.0,
|
|
"step": 25890
|
|
},
|
|
{
|
|
"entropy": 5.315832853317261,
|
|
"epoch": 2.1629635816906116,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00045292054356852195,
|
|
"loss": 4.7125,
|
|
"mean_token_accuracy": 0.2294309541583061,
|
|
"num_tokens": 47649272.0,
|
|
"step": 25895
|
|
},
|
|
{
|
|
"entropy": 5.286549806594849,
|
|
"epoch": 2.1633812228533245,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004529023189466219,
|
|
"loss": 4.618,
|
|
"mean_token_accuracy": 0.24390878081321715,
|
|
"num_tokens": 47658046.0,
|
|
"step": 25900
|
|
},
|
|
{
|
|
"entropy": 5.246329069137573,
|
|
"epoch": 2.1637988640160373,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00045288409121032756,
|
|
"loss": 4.616,
|
|
"mean_token_accuracy": 0.24141196608543397,
|
|
"num_tokens": 47666658.0,
|
|
"step": 25905
|
|
},
|
|
{
|
|
"entropy": 5.339252090454101,
|
|
"epoch": 2.1642165051787505,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00045286586035995813,
|
|
"loss": 4.7082,
|
|
"mean_token_accuracy": 0.22803422957658767,
|
|
"num_tokens": 47676455.0,
|
|
"step": 25910
|
|
},
|
|
{
|
|
"entropy": 5.318616819381714,
|
|
"epoch": 2.1646341463414633,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00045284762639583265,
|
|
"loss": 4.6842,
|
|
"mean_token_accuracy": 0.22670807242393493,
|
|
"num_tokens": 47685518.0,
|
|
"step": 25915
|
|
},
|
|
{
|
|
"entropy": 5.304307222366333,
|
|
"epoch": 2.1650517875041766,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00045282938931827046,
|
|
"loss": 4.7574,
|
|
"mean_token_accuracy": 0.23415862768888474,
|
|
"num_tokens": 47695070.0,
|
|
"step": 25920
|
|
},
|
|
{
|
|
"entropy": 5.355651617050171,
|
|
"epoch": 2.1654694286668894,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004528111491275907,
|
|
"loss": 4.7709,
|
|
"mean_token_accuracy": 0.2273676186800003,
|
|
"num_tokens": 47704650.0,
|
|
"step": 25925
|
|
},
|
|
{
|
|
"entropy": 5.374398469924927,
|
|
"epoch": 2.165887069829602,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004527929058241128,
|
|
"loss": 4.7797,
|
|
"mean_token_accuracy": 0.22754137963056564,
|
|
"num_tokens": 47714263.0,
|
|
"step": 25930
|
|
},
|
|
{
|
|
"entropy": 5.42594952583313,
|
|
"epoch": 2.1663047109923155,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00045277465940815603,
|
|
"loss": 4.8003,
|
|
"mean_token_accuracy": 0.22807859480381013,
|
|
"num_tokens": 47723448.0,
|
|
"step": 25935
|
|
},
|
|
{
|
|
"entropy": 5.361016702651978,
|
|
"epoch": 2.1667223521550283,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004527564098800399,
|
|
"loss": 4.6988,
|
|
"mean_token_accuracy": 0.23686958253383636,
|
|
"num_tokens": 47731841.0,
|
|
"step": 25940
|
|
},
|
|
{
|
|
"entropy": 5.274867582321167,
|
|
"epoch": 2.1671399933177415,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004527381572400838,
|
|
"loss": 4.6283,
|
|
"mean_token_accuracy": 0.2308671221137047,
|
|
"num_tokens": 47741422.0,
|
|
"step": 25945
|
|
},
|
|
{
|
|
"entropy": 5.293590402603149,
|
|
"epoch": 2.1675576344804544,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00045271990148860737,
|
|
"loss": 4.699,
|
|
"mean_token_accuracy": 0.22765571773052215,
|
|
"num_tokens": 47750601.0,
|
|
"step": 25950
|
|
},
|
|
{
|
|
"entropy": 5.3842260360717775,
|
|
"epoch": 2.167975275643167,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00045270164262593013,
|
|
"loss": 4.8544,
|
|
"mean_token_accuracy": 0.22053608298301697,
|
|
"num_tokens": 47759992.0,
|
|
"step": 25955
|
|
},
|
|
{
|
|
"entropy": 5.298316431045532,
|
|
"epoch": 2.1683929168058804,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004526833806523717,
|
|
"loss": 4.6455,
|
|
"mean_token_accuracy": 0.22775809466838837,
|
|
"num_tokens": 47769548.0,
|
|
"step": 25960
|
|
},
|
|
{
|
|
"entropy": 5.363567352294922,
|
|
"epoch": 2.1688105579685932,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00045266511556825184,
|
|
"loss": 4.8019,
|
|
"mean_token_accuracy": 0.21999684125185012,
|
|
"num_tokens": 47778998.0,
|
|
"step": 25965
|
|
},
|
|
{
|
|
"entropy": 5.3872819423675535,
|
|
"epoch": 2.1692281991313065,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00045264684737389026,
|
|
"loss": 4.7529,
|
|
"mean_token_accuracy": 0.22339095324277877,
|
|
"num_tokens": 47787931.0,
|
|
"step": 25970
|
|
},
|
|
{
|
|
"entropy": 5.353916215896606,
|
|
"epoch": 2.1696458402940193,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00045262857606960684,
|
|
"loss": 4.7197,
|
|
"mean_token_accuracy": 0.22673820108175277,
|
|
"num_tokens": 47797421.0,
|
|
"step": 25975
|
|
},
|
|
{
|
|
"entropy": 5.389294719696045,
|
|
"epoch": 2.1700634814567326,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00045261030165572134,
|
|
"loss": 4.799,
|
|
"mean_token_accuracy": 0.220089915394783,
|
|
"num_tokens": 47807153.0,
|
|
"step": 25980
|
|
},
|
|
{
|
|
"entropy": 5.424050807952881,
|
|
"epoch": 2.1704811226194454,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004525920241325537,
|
|
"loss": 4.8361,
|
|
"mean_token_accuracy": 0.22419284880161286,
|
|
"num_tokens": 47816840.0,
|
|
"step": 25985
|
|
},
|
|
{
|
|
"entropy": 5.446947813034058,
|
|
"epoch": 2.170898763782158,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004525737435004239,
|
|
"loss": 4.8229,
|
|
"mean_token_accuracy": 0.22595977187156677,
|
|
"num_tokens": 47825997.0,
|
|
"step": 25990
|
|
},
|
|
{
|
|
"entropy": 5.381023168563843,
|
|
"epoch": 2.1713164049448714,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000452555459759652,
|
|
"loss": 4.7474,
|
|
"mean_token_accuracy": 0.23280774652957917,
|
|
"num_tokens": 47834106.0,
|
|
"step": 25995
|
|
},
|
|
{
|
|
"entropy": 5.342404508590699,
|
|
"epoch": 2.1717340461075842,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004525371729105581,
|
|
"loss": 4.7023,
|
|
"mean_token_accuracy": 0.23595003336668013,
|
|
"num_tokens": 47843161.0,
|
|
"step": 26000
|
|
},
|
|
{
|
|
"entropy": 5.3436517238616945,
|
|
"epoch": 2.1721516872702975,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004525188829534622,
|
|
"loss": 4.6916,
|
|
"mean_token_accuracy": 0.2339781865477562,
|
|
"num_tokens": 47852396.0,
|
|
"step": 26005
|
|
},
|
|
{
|
|
"entropy": 5.38686351776123,
|
|
"epoch": 2.1725693284330103,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004525005898886847,
|
|
"loss": 4.7737,
|
|
"mean_token_accuracy": 0.23278718739748,
|
|
"num_tokens": 47861070.0,
|
|
"step": 26010
|
|
},
|
|
{
|
|
"entropy": 5.372256517410278,
|
|
"epoch": 2.1729869695957236,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004524822937165456,
|
|
"loss": 4.8061,
|
|
"mean_token_accuracy": 0.2193442091345787,
|
|
"num_tokens": 47869771.0,
|
|
"step": 26015
|
|
},
|
|
{
|
|
"entropy": 5.408532238006591,
|
|
"epoch": 2.1734046107584364,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00045246399443736536,
|
|
"loss": 4.8084,
|
|
"mean_token_accuracy": 0.22563027888536452,
|
|
"num_tokens": 47879447.0,
|
|
"step": 26020
|
|
},
|
|
{
|
|
"entropy": 5.383467292785644,
|
|
"epoch": 2.173822251921149,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00045244569205146425,
|
|
"loss": 4.7265,
|
|
"mean_token_accuracy": 0.23277349025011063,
|
|
"num_tokens": 47887415.0,
|
|
"step": 26025
|
|
},
|
|
{
|
|
"entropy": 5.438180541992187,
|
|
"epoch": 2.1742398930838625,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004524273865591627,
|
|
"loss": 4.8475,
|
|
"mean_token_accuracy": 0.2197128564119339,
|
|
"num_tokens": 47896898.0,
|
|
"step": 26030
|
|
},
|
|
{
|
|
"entropy": 5.346346712112426,
|
|
"epoch": 2.1746575342465753,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00045240907796078125,
|
|
"loss": 4.7523,
|
|
"mean_token_accuracy": 0.23122134059667587,
|
|
"num_tokens": 47906453.0,
|
|
"step": 26035
|
|
},
|
|
{
|
|
"entropy": 5.42652268409729,
|
|
"epoch": 2.1750751754092885,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004523907662566403,
|
|
"loss": 4.8173,
|
|
"mean_token_accuracy": 0.21540707647800444,
|
|
"num_tokens": 47916614.0,
|
|
"step": 26040
|
|
},
|
|
{
|
|
"entropy": 5.393053245544434,
|
|
"epoch": 2.1754928165720013,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00045237245144706044,
|
|
"loss": 4.7501,
|
|
"mean_token_accuracy": 0.2234147310256958,
|
|
"num_tokens": 47925924.0,
|
|
"step": 26045
|
|
},
|
|
{
|
|
"entropy": 5.43722128868103,
|
|
"epoch": 2.175910457734714,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004523541335323624,
|
|
"loss": 4.8251,
|
|
"mean_token_accuracy": 0.21635308861732483,
|
|
"num_tokens": 47934706.0,
|
|
"step": 26050
|
|
},
|
|
{
|
|
"entropy": 5.450218057632446,
|
|
"epoch": 2.1763280988974274,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004523358125128667,
|
|
"loss": 4.86,
|
|
"mean_token_accuracy": 0.21637779325246811,
|
|
"num_tokens": 47944885.0,
|
|
"step": 26055
|
|
},
|
|
{
|
|
"entropy": 5.383785057067871,
|
|
"epoch": 2.17674574006014,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004523174883888941,
|
|
"loss": 4.7462,
|
|
"mean_token_accuracy": 0.22506624907255174,
|
|
"num_tokens": 47953491.0,
|
|
"step": 26060
|
|
},
|
|
{
|
|
"entropy": 5.422900152206421,
|
|
"epoch": 2.1771633812228535,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004522991611607655,
|
|
"loss": 4.823,
|
|
"mean_token_accuracy": 0.22104415595531463,
|
|
"num_tokens": 47962583.0,
|
|
"step": 26065
|
|
},
|
|
{
|
|
"entropy": 5.3968212604522705,
|
|
"epoch": 2.1775810223855663,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00045228083082880164,
|
|
"loss": 4.7308,
|
|
"mean_token_accuracy": 0.22333173006772994,
|
|
"num_tokens": 47971213.0,
|
|
"step": 26070
|
|
},
|
|
{
|
|
"entropy": 5.460604572296143,
|
|
"epoch": 2.177998663548279,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004522624973933234,
|
|
"loss": 4.9017,
|
|
"mean_token_accuracy": 0.2116509795188904,
|
|
"num_tokens": 47981001.0,
|
|
"step": 26075
|
|
},
|
|
{
|
|
"entropy": 5.412031602859497,
|
|
"epoch": 2.1784163047109923,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00045224416085465195,
|
|
"loss": 4.7743,
|
|
"mean_token_accuracy": 0.22235163897275925,
|
|
"num_tokens": 47989765.0,
|
|
"step": 26080
|
|
},
|
|
{
|
|
"entropy": 5.452148675918579,
|
|
"epoch": 2.178833945873705,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00045222582121310793,
|
|
"loss": 4.7509,
|
|
"mean_token_accuracy": 0.23484649658203124,
|
|
"num_tokens": 47999676.0,
|
|
"step": 26085
|
|
},
|
|
{
|
|
"entropy": 5.379456901550293,
|
|
"epoch": 2.1792515870364184,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00045220747846901266,
|
|
"loss": 4.7717,
|
|
"mean_token_accuracy": 0.22553104311227798,
|
|
"num_tokens": 48009181.0,
|
|
"step": 26090
|
|
},
|
|
{
|
|
"entropy": 5.2561108589172365,
|
|
"epoch": 2.1796692281991312,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00045218913262268717,
|
|
"loss": 4.6278,
|
|
"mean_token_accuracy": 0.24322134256362915,
|
|
"num_tokens": 48018436.0,
|
|
"step": 26095
|
|
},
|
|
{
|
|
"entropy": 5.380129861831665,
|
|
"epoch": 2.1800868693618445,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00045217078367445264,
|
|
"loss": 4.7901,
|
|
"mean_token_accuracy": 0.22564495354890823,
|
|
"num_tokens": 48027527.0,
|
|
"step": 26100
|
|
},
|
|
{
|
|
"entropy": 5.388590383529663,
|
|
"epoch": 2.1805045105245573,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00045215243162463023,
|
|
"loss": 4.7191,
|
|
"mean_token_accuracy": 0.23424494564533233,
|
|
"num_tokens": 48037432.0,
|
|
"step": 26105
|
|
},
|
|
{
|
|
"entropy": 5.41064944267273,
|
|
"epoch": 2.18092215168727,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004521340764735413,
|
|
"loss": 4.8217,
|
|
"mean_token_accuracy": 0.2236853688955307,
|
|
"num_tokens": 48046037.0,
|
|
"step": 26110
|
|
},
|
|
{
|
|
"entropy": 5.3586719036102295,
|
|
"epoch": 2.1813397928499834,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004521157182215071,
|
|
"loss": 4.7138,
|
|
"mean_token_accuracy": 0.22559016942977905,
|
|
"num_tokens": 48055197.0,
|
|
"step": 26115
|
|
},
|
|
{
|
|
"entropy": 5.463117074966431,
|
|
"epoch": 2.181757434012696,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00045209735686884913,
|
|
"loss": 4.9232,
|
|
"mean_token_accuracy": 0.205860036611557,
|
|
"num_tokens": 48064152.0,
|
|
"step": 26120
|
|
},
|
|
{
|
|
"entropy": 5.38301568031311,
|
|
"epoch": 2.1821750751754094,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00045207899241588874,
|
|
"loss": 4.7327,
|
|
"mean_token_accuracy": 0.23012369126081467,
|
|
"num_tokens": 48073765.0,
|
|
"step": 26125
|
|
},
|
|
{
|
|
"entropy": 5.365782928466797,
|
|
"epoch": 2.1825927163381222,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004520606248629474,
|
|
"loss": 4.6807,
|
|
"mean_token_accuracy": 0.23719001561403275,
|
|
"num_tokens": 48082816.0,
|
|
"step": 26130
|
|
},
|
|
{
|
|
"entropy": 5.402808094024659,
|
|
"epoch": 2.1830103575008355,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004520422542103467,
|
|
"loss": 4.7458,
|
|
"mean_token_accuracy": 0.23122961372137069,
|
|
"num_tokens": 48091841.0,
|
|
"step": 26135
|
|
},
|
|
{
|
|
"entropy": 5.312366485595703,
|
|
"epoch": 2.1834279986635483,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004520238804584083,
|
|
"loss": 4.6836,
|
|
"mean_token_accuracy": 0.229449126124382,
|
|
"num_tokens": 48102162.0,
|
|
"step": 26140
|
|
},
|
|
{
|
|
"entropy": 5.360209131240845,
|
|
"epoch": 2.183845639826261,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004520055036074538,
|
|
"loss": 4.7551,
|
|
"mean_token_accuracy": 0.2263647049665451,
|
|
"num_tokens": 48111092.0,
|
|
"step": 26145
|
|
},
|
|
{
|
|
"entropy": 5.2473061084747314,
|
|
"epoch": 2.1842632809889744,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004519871236578048,
|
|
"loss": 4.6279,
|
|
"mean_token_accuracy": 0.231705941259861,
|
|
"num_tokens": 48119643.0,
|
|
"step": 26150
|
|
},
|
|
{
|
|
"entropy": 5.293466091156006,
|
|
"epoch": 2.184680922151687,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004519687406097832,
|
|
"loss": 4.6742,
|
|
"mean_token_accuracy": 0.2345123901963234,
|
|
"num_tokens": 48128685.0,
|
|
"step": 26155
|
|
},
|
|
{
|
|
"entropy": 5.2800267219543455,
|
|
"epoch": 2.1850985633144004,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004519503544637107,
|
|
"loss": 4.7325,
|
|
"mean_token_accuracy": 0.23694444298744202,
|
|
"num_tokens": 48137645.0,
|
|
"step": 26160
|
|
},
|
|
{
|
|
"entropy": 5.394048881530762,
|
|
"epoch": 2.1855162044771133,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00045193196521990935,
|
|
"loss": 4.7806,
|
|
"mean_token_accuracy": 0.22775750160217284,
|
|
"num_tokens": 48147240.0,
|
|
"step": 26165
|
|
},
|
|
{
|
|
"entropy": 5.3777529239654545,
|
|
"epoch": 2.185933845639826,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000451913572878701,
|
|
"loss": 4.7788,
|
|
"mean_token_accuracy": 0.2195443645119667,
|
|
"num_tokens": 48156992.0,
|
|
"step": 26170
|
|
},
|
|
{
|
|
"entropy": 5.4353100776672365,
|
|
"epoch": 2.1863514868025393,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004518951774404076,
|
|
"loss": 4.8047,
|
|
"mean_token_accuracy": 0.21672980785369872,
|
|
"num_tokens": 48165864.0,
|
|
"step": 26175
|
|
},
|
|
{
|
|
"entropy": 5.450677824020386,
|
|
"epoch": 2.186769127965252,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004518767789053511,
|
|
"loss": 4.8261,
|
|
"mean_token_accuracy": 0.224220672249794,
|
|
"num_tokens": 48174676.0,
|
|
"step": 26180
|
|
},
|
|
{
|
|
"entropy": 5.319680643081665,
|
|
"epoch": 2.1871867691279654,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00045185837727385373,
|
|
"loss": 4.6364,
|
|
"mean_token_accuracy": 0.23600905686616896,
|
|
"num_tokens": 48182838.0,
|
|
"step": 26185
|
|
},
|
|
{
|
|
"entropy": 5.4451268196105955,
|
|
"epoch": 2.187604410290678,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004518399725462376,
|
|
"loss": 4.8438,
|
|
"mean_token_accuracy": 0.21973627507686616,
|
|
"num_tokens": 48192087.0,
|
|
"step": 26190
|
|
},
|
|
{
|
|
"entropy": 5.361597108840942,
|
|
"epoch": 2.188022051453391,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004518215647228248,
|
|
"loss": 4.7274,
|
|
"mean_token_accuracy": 0.2237904816865921,
|
|
"num_tokens": 48201020.0,
|
|
"step": 26195
|
|
},
|
|
{
|
|
"entropy": 5.4244836330413815,
|
|
"epoch": 2.1884396926161043,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00045180315380393776,
|
|
"loss": 4.7243,
|
|
"mean_token_accuracy": 0.2287676975131035,
|
|
"num_tokens": 48210672.0,
|
|
"step": 26200
|
|
},
|
|
{
|
|
"entropy": 5.407254457473755,
|
|
"epoch": 2.188857333778817,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004517847397898987,
|
|
"loss": 4.7891,
|
|
"mean_token_accuracy": 0.223003551363945,
|
|
"num_tokens": 48220669.0,
|
|
"step": 26205
|
|
},
|
|
{
|
|
"entropy": 5.310814714431762,
|
|
"epoch": 2.1892749749415303,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00045176632268102994,
|
|
"loss": 4.5902,
|
|
"mean_token_accuracy": 0.2448668047785759,
|
|
"num_tokens": 48230198.0,
|
|
"step": 26210
|
|
},
|
|
{
|
|
"entropy": 5.408667039871216,
|
|
"epoch": 2.189692616104243,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000451747902477654,
|
|
"loss": 4.8457,
|
|
"mean_token_accuracy": 0.21542298048734665,
|
|
"num_tokens": 48239854.0,
|
|
"step": 26215
|
|
},
|
|
{
|
|
"entropy": 5.448745965957642,
|
|
"epoch": 2.1901102572669564,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00045172947918009317,
|
|
"loss": 4.8496,
|
|
"mean_token_accuracy": 0.2165292352437973,
|
|
"num_tokens": 48249239.0,
|
|
"step": 26220
|
|
},
|
|
{
|
|
"entropy": 5.384311056137085,
|
|
"epoch": 2.190527898429669,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004517110527886701,
|
|
"loss": 4.7069,
|
|
"mean_token_accuracy": 0.22952121943235398,
|
|
"num_tokens": 48258196.0,
|
|
"step": 26225
|
|
},
|
|
{
|
|
"entropy": 5.347128868103027,
|
|
"epoch": 2.190945539592382,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004516926233037074,
|
|
"loss": 4.6972,
|
|
"mean_token_accuracy": 0.22400336414575578,
|
|
"num_tokens": 48267102.0,
|
|
"step": 26230
|
|
},
|
|
{
|
|
"entropy": 5.390167665481568,
|
|
"epoch": 2.1913631807550953,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004516741907255276,
|
|
"loss": 4.7729,
|
|
"mean_token_accuracy": 0.22337306439876556,
|
|
"num_tokens": 48276273.0,
|
|
"step": 26235
|
|
},
|
|
{
|
|
"entropy": 5.342447233200073,
|
|
"epoch": 2.191780821917808,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004516557550544534,
|
|
"loss": 4.7556,
|
|
"mean_token_accuracy": 0.22425521314144134,
|
|
"num_tokens": 48284921.0,
|
|
"step": 26240
|
|
},
|
|
{
|
|
"entropy": 5.325759220123291,
|
|
"epoch": 2.1921984630805214,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004516373162908077,
|
|
"loss": 4.772,
|
|
"mean_token_accuracy": 0.23286058902740478,
|
|
"num_tokens": 48293188.0,
|
|
"step": 26245
|
|
},
|
|
{
|
|
"entropy": 5.429482555389404,
|
|
"epoch": 2.192616104243234,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00045161887443491297,
|
|
"loss": 4.7657,
|
|
"mean_token_accuracy": 0.22584767490625382,
|
|
"num_tokens": 48301898.0,
|
|
"step": 26250
|
|
},
|
|
{
|
|
"entropy": 5.417229652404785,
|
|
"epoch": 2.1930337454059474,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00045160042948709235,
|
|
"loss": 4.6612,
|
|
"mean_token_accuracy": 0.24022096991539002,
|
|
"num_tokens": 48310291.0,
|
|
"step": 26255
|
|
},
|
|
{
|
|
"entropy": 5.400797939300537,
|
|
"epoch": 2.1934513865686602,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00045158198144766863,
|
|
"loss": 4.6808,
|
|
"mean_token_accuracy": 0.23646968901157378,
|
|
"num_tokens": 48318922.0,
|
|
"step": 26260
|
|
},
|
|
{
|
|
"entropy": 5.3249749660491945,
|
|
"epoch": 2.193869027731373,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004515635303169648,
|
|
"loss": 4.7243,
|
|
"mean_token_accuracy": 0.23717833757400514,
|
|
"num_tokens": 48327843.0,
|
|
"step": 26265
|
|
},
|
|
{
|
|
"entropy": 5.363675928115844,
|
|
"epoch": 2.1942866688940863,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00045154507609530375,
|
|
"loss": 4.8136,
|
|
"mean_token_accuracy": 0.22652721256017685,
|
|
"num_tokens": 48336756.0,
|
|
"step": 26270
|
|
},
|
|
{
|
|
"entropy": 5.4721849918365475,
|
|
"epoch": 2.194704310056799,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004515266187830087,
|
|
"loss": 4.8907,
|
|
"mean_token_accuracy": 0.21775131076574325,
|
|
"num_tokens": 48346813.0,
|
|
"step": 26275
|
|
},
|
|
{
|
|
"entropy": 5.4222461700439455,
|
|
"epoch": 2.1951219512195124,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00045150815838040275,
|
|
"loss": 4.8058,
|
|
"mean_token_accuracy": 0.22236558496952058,
|
|
"num_tokens": 48355416.0,
|
|
"step": 26280
|
|
},
|
|
{
|
|
"entropy": 5.53259015083313,
|
|
"epoch": 2.195539592382225,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00045148969488780893,
|
|
"loss": 4.8792,
|
|
"mean_token_accuracy": 0.21746049523353578,
|
|
"num_tokens": 48364824.0,
|
|
"step": 26285
|
|
},
|
|
{
|
|
"entropy": 5.361283683776856,
|
|
"epoch": 2.195957233544938,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004514712283055506,
|
|
"loss": 4.732,
|
|
"mean_token_accuracy": 0.2227367118000984,
|
|
"num_tokens": 48375016.0,
|
|
"step": 26290
|
|
},
|
|
{
|
|
"entropy": 5.322117805480957,
|
|
"epoch": 2.1963748747076512,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004514527586339511,
|
|
"loss": 4.6859,
|
|
"mean_token_accuracy": 0.23130838423967362,
|
|
"num_tokens": 48383232.0,
|
|
"step": 26295
|
|
},
|
|
{
|
|
"entropy": 5.443576002120972,
|
|
"epoch": 2.196792515870364,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00045143428587333354,
|
|
"loss": 4.8048,
|
|
"mean_token_accuracy": 0.22060928791761397,
|
|
"num_tokens": 48392374.0,
|
|
"step": 26300
|
|
},
|
|
{
|
|
"entropy": 5.445785856246948,
|
|
"epoch": 2.1972101570330773,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004514158100240214,
|
|
"loss": 4.8588,
|
|
"mean_token_accuracy": 0.2165913388133049,
|
|
"num_tokens": 48401471.0,
|
|
"step": 26305
|
|
},
|
|
{
|
|
"entropy": 5.464274120330811,
|
|
"epoch": 2.19762779819579,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004513973310863383,
|
|
"loss": 4.8321,
|
|
"mean_token_accuracy": 0.2169705256819725,
|
|
"num_tokens": 48410585.0,
|
|
"step": 26310
|
|
},
|
|
{
|
|
"entropy": 5.365324878692627,
|
|
"epoch": 2.198045439358503,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00045137884906060747,
|
|
"loss": 4.72,
|
|
"mean_token_accuracy": 0.22845595479011535,
|
|
"num_tokens": 48419563.0,
|
|
"step": 26315
|
|
},
|
|
{
|
|
"entropy": 5.340550756454467,
|
|
"epoch": 2.198463080521216,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004513603639471526,
|
|
"loss": 4.7183,
|
|
"mean_token_accuracy": 0.22761934250593185,
|
|
"num_tokens": 48429801.0,
|
|
"step": 26320
|
|
},
|
|
{
|
|
"entropy": 5.375749111175537,
|
|
"epoch": 2.198880721683929,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004513418757462973,
|
|
"loss": 4.7255,
|
|
"mean_token_accuracy": 0.2283896178007126,
|
|
"num_tokens": 48437953.0,
|
|
"step": 26325
|
|
},
|
|
{
|
|
"entropy": 5.439268159866333,
|
|
"epoch": 2.1992983628466423,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00045132338445836516,
|
|
"loss": 4.7636,
|
|
"mean_token_accuracy": 0.2293369635939598,
|
|
"num_tokens": 48447733.0,
|
|
"step": 26330
|
|
},
|
|
{
|
|
"entropy": 5.391873025894165,
|
|
"epoch": 2.199716004009355,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00045130489008367997,
|
|
"loss": 4.7074,
|
|
"mean_token_accuracy": 0.2289211258292198,
|
|
"num_tokens": 48456530.0,
|
|
"step": 26335
|
|
},
|
|
{
|
|
"entropy": 5.312036800384521,
|
|
"epoch": 2.2001336451720683,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004512863926225655,
|
|
"loss": 4.7215,
|
|
"mean_token_accuracy": 0.2317403793334961,
|
|
"num_tokens": 48465607.0,
|
|
"step": 26340
|
|
},
|
|
{
|
|
"entropy": 5.350145626068115,
|
|
"epoch": 2.200551286334781,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00045126789207534544,
|
|
"loss": 4.6928,
|
|
"mean_token_accuracy": 0.23384055197238923,
|
|
"num_tokens": 48474112.0,
|
|
"step": 26345
|
|
},
|
|
{
|
|
"entropy": 5.3583399772644045,
|
|
"epoch": 2.200968927497494,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00045124938844234386,
|
|
"loss": 4.6928,
|
|
"mean_token_accuracy": 0.23722120970487595,
|
|
"num_tokens": 48482677.0,
|
|
"step": 26350
|
|
},
|
|
{
|
|
"entropy": 5.380658197402954,
|
|
"epoch": 2.201386568660207,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00045123088172388455,
|
|
"loss": 4.6611,
|
|
"mean_token_accuracy": 0.2357831597328186,
|
|
"num_tokens": 48491313.0,
|
|
"step": 26355
|
|
},
|
|
{
|
|
"entropy": 5.371305751800537,
|
|
"epoch": 2.20180420982292,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00045121237192029154,
|
|
"loss": 4.7775,
|
|
"mean_token_accuracy": 0.23042017966508865,
|
|
"num_tokens": 48501106.0,
|
|
"step": 26360
|
|
},
|
|
{
|
|
"entropy": 5.411451721191407,
|
|
"epoch": 2.2022218509856333,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00045119385903188877,
|
|
"loss": 4.7653,
|
|
"mean_token_accuracy": 0.22481056302785873,
|
|
"num_tokens": 48511219.0,
|
|
"step": 26365
|
|
},
|
|
{
|
|
"entropy": 5.335706806182861,
|
|
"epoch": 2.202639492148346,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004511753430590004,
|
|
"loss": 4.7542,
|
|
"mean_token_accuracy": 0.23532965928316116,
|
|
"num_tokens": 48520436.0,
|
|
"step": 26370
|
|
},
|
|
{
|
|
"entropy": 5.356300258636475,
|
|
"epoch": 2.2030571333110593,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004511568240019507,
|
|
"loss": 4.8001,
|
|
"mean_token_accuracy": 0.22025289833545686,
|
|
"num_tokens": 48531516.0,
|
|
"step": 26375
|
|
},
|
|
{
|
|
"entropy": 5.387106704711914,
|
|
"epoch": 2.203474774473772,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00045113830186106367,
|
|
"loss": 4.6663,
|
|
"mean_token_accuracy": 0.2303552970290184,
|
|
"num_tokens": 48540512.0,
|
|
"step": 26380
|
|
},
|
|
{
|
|
"entropy": 5.443878698348999,
|
|
"epoch": 2.203892415636485,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004511197766366637,
|
|
"loss": 4.805,
|
|
"mean_token_accuracy": 0.21538713723421096,
|
|
"num_tokens": 48550273.0,
|
|
"step": 26385
|
|
},
|
|
{
|
|
"entropy": 5.317212295532227,
|
|
"epoch": 2.2043100567991982,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00045110124832907505,
|
|
"loss": 4.7921,
|
|
"mean_token_accuracy": 0.2333454445004463,
|
|
"num_tokens": 48558606.0,
|
|
"step": 26390
|
|
},
|
|
{
|
|
"entropy": 5.333815336227417,
|
|
"epoch": 2.204727697961911,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004510827169386221,
|
|
"loss": 4.7419,
|
|
"mean_token_accuracy": 0.228470978140831,
|
|
"num_tokens": 48567167.0,
|
|
"step": 26395
|
|
},
|
|
{
|
|
"entropy": 5.375031566619873,
|
|
"epoch": 2.2051453391246243,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004510641824656292,
|
|
"loss": 4.7498,
|
|
"mean_token_accuracy": 0.22718238979578018,
|
|
"num_tokens": 48576275.0,
|
|
"step": 26400
|
|
},
|
|
{
|
|
"entropy": 5.384783792495727,
|
|
"epoch": 2.205562980287337,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004510456449104208,
|
|
"loss": 4.7292,
|
|
"mean_token_accuracy": 0.22897106409072876,
|
|
"num_tokens": 48585217.0,
|
|
"step": 26405
|
|
},
|
|
{
|
|
"entropy": 5.380896377563476,
|
|
"epoch": 2.20598062145005,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004510271042733215,
|
|
"loss": 4.7257,
|
|
"mean_token_accuracy": 0.22460291236639024,
|
|
"num_tokens": 48594583.0,
|
|
"step": 26410
|
|
},
|
|
{
|
|
"entropy": 5.2562493801116945,
|
|
"epoch": 2.206398262612763,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004510085605546559,
|
|
"loss": 4.6516,
|
|
"mean_token_accuracy": 0.2399199277162552,
|
|
"num_tokens": 48603677.0,
|
|
"step": 26415
|
|
},
|
|
{
|
|
"entropy": 5.420642566680908,
|
|
"epoch": 2.206815903775476,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00045099001375474855,
|
|
"loss": 4.8098,
|
|
"mean_token_accuracy": 0.2237902730703354,
|
|
"num_tokens": 48614453.0,
|
|
"step": 26420
|
|
},
|
|
{
|
|
"entropy": 5.312398386001587,
|
|
"epoch": 2.2072335449381892,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00045097146387392423,
|
|
"loss": 4.7448,
|
|
"mean_token_accuracy": 0.23162843883037568,
|
|
"num_tokens": 48622871.0,
|
|
"step": 26425
|
|
},
|
|
{
|
|
"entropy": 5.318217706680298,
|
|
"epoch": 2.207651186100902,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00045095291091250755,
|
|
"loss": 4.6801,
|
|
"mean_token_accuracy": 0.22899388521909714,
|
|
"num_tokens": 48631466.0,
|
|
"step": 26430
|
|
},
|
|
{
|
|
"entropy": 5.330518436431885,
|
|
"epoch": 2.2080688272636153,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004509343548708235,
|
|
"loss": 4.6785,
|
|
"mean_token_accuracy": 0.2380764216184616,
|
|
"num_tokens": 48640020.0,
|
|
"step": 26435
|
|
},
|
|
{
|
|
"entropy": 5.355378150939941,
|
|
"epoch": 2.208486468426328,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004509157957491966,
|
|
"loss": 4.7946,
|
|
"mean_token_accuracy": 0.22703781574964524,
|
|
"num_tokens": 48648428.0,
|
|
"step": 26440
|
|
},
|
|
{
|
|
"entropy": 5.3309167385101315,
|
|
"epoch": 2.208904109589041,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00045089723354795204,
|
|
"loss": 4.6343,
|
|
"mean_token_accuracy": 0.23772406876087188,
|
|
"num_tokens": 48657232.0,
|
|
"step": 26445
|
|
},
|
|
{
|
|
"entropy": 5.253514242172241,
|
|
"epoch": 2.209321750751754,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004508786682674147,
|
|
"loss": 4.6415,
|
|
"mean_token_accuracy": 0.23265154361724855,
|
|
"num_tokens": 48665802.0,
|
|
"step": 26450
|
|
},
|
|
{
|
|
"entropy": 5.352841424942016,
|
|
"epoch": 2.209739391914467,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00045086009990790956,
|
|
"loss": 4.6569,
|
|
"mean_token_accuracy": 0.24081205427646638,
|
|
"num_tokens": 48674622.0,
|
|
"step": 26455
|
|
},
|
|
{
|
|
"entropy": 5.317217254638672,
|
|
"epoch": 2.2101570330771803,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00045084152846976166,
|
|
"loss": 4.737,
|
|
"mean_token_accuracy": 0.23146685510873793,
|
|
"num_tokens": 48683365.0,
|
|
"step": 26460
|
|
},
|
|
{
|
|
"entropy": 5.335719633102417,
|
|
"epoch": 2.210574674239893,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00045082295395329616,
|
|
"loss": 4.7015,
|
|
"mean_token_accuracy": 0.23374384492635727,
|
|
"num_tokens": 48693554.0,
|
|
"step": 26465
|
|
},
|
|
{
|
|
"entropy": 5.352770042419434,
|
|
"epoch": 2.210992315402606,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004508043763588382,
|
|
"loss": 4.7329,
|
|
"mean_token_accuracy": 0.23321735560894014,
|
|
"num_tokens": 48702892.0,
|
|
"step": 26470
|
|
},
|
|
{
|
|
"entropy": 5.393492650985718,
|
|
"epoch": 2.211409956565319,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00045078579568671307,
|
|
"loss": 4.7626,
|
|
"mean_token_accuracy": 0.22533705532550813,
|
|
"num_tokens": 48712036.0,
|
|
"step": 26475
|
|
},
|
|
{
|
|
"entropy": 5.396263456344604,
|
|
"epoch": 2.211827597728032,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004507672119372459,
|
|
"loss": 4.7916,
|
|
"mean_token_accuracy": 0.2261172667145729,
|
|
"num_tokens": 48721462.0,
|
|
"step": 26480
|
|
},
|
|
{
|
|
"entropy": 5.3927854061126705,
|
|
"epoch": 2.212245238890745,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00045074862511076215,
|
|
"loss": 4.7605,
|
|
"mean_token_accuracy": 0.2245310962200165,
|
|
"num_tokens": 48730542.0,
|
|
"step": 26485
|
|
},
|
|
{
|
|
"entropy": 5.377521896362305,
|
|
"epoch": 2.212662880053458,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004507300352075872,
|
|
"loss": 4.7657,
|
|
"mean_token_accuracy": 0.22923006415367125,
|
|
"num_tokens": 48739477.0,
|
|
"step": 26490
|
|
},
|
|
{
|
|
"entropy": 5.400514793395996,
|
|
"epoch": 2.2130805212161713,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00045071144222804646,
|
|
"loss": 4.7729,
|
|
"mean_token_accuracy": 0.23097372204065322,
|
|
"num_tokens": 48748945.0,
|
|
"step": 26495
|
|
},
|
|
{
|
|
"entropy": 5.405605220794678,
|
|
"epoch": 2.213498162378884,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004506928461724654,
|
|
"loss": 4.7951,
|
|
"mean_token_accuracy": 0.22669386118650436,
|
|
"num_tokens": 48757762.0,
|
|
"step": 26500
|
|
},
|
|
{
|
|
"entropy": 5.488488054275512,
|
|
"epoch": 2.213915803541597,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00045067424704116956,
|
|
"loss": 4.9295,
|
|
"mean_token_accuracy": 0.2136015459895134,
|
|
"num_tokens": 48767773.0,
|
|
"step": 26505
|
|
},
|
|
{
|
|
"entropy": 5.395500993728637,
|
|
"epoch": 2.21433344470431,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004506556448344846,
|
|
"loss": 4.7978,
|
|
"mean_token_accuracy": 0.22613329738378524,
|
|
"num_tokens": 48777499.0,
|
|
"step": 26510
|
|
},
|
|
{
|
|
"entropy": 5.364151287078857,
|
|
"epoch": 2.214751085867023,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004506370395527362,
|
|
"loss": 4.691,
|
|
"mean_token_accuracy": 0.23242953568696975,
|
|
"num_tokens": 48786499.0,
|
|
"step": 26515
|
|
},
|
|
{
|
|
"entropy": 5.380894660949707,
|
|
"epoch": 2.215168727029736,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00045061843119624984,
|
|
"loss": 4.7957,
|
|
"mean_token_accuracy": 0.22880268543958665,
|
|
"num_tokens": 48795086.0,
|
|
"step": 26520
|
|
},
|
|
{
|
|
"entropy": 5.320752382278442,
|
|
"epoch": 2.215586368192449,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004505998197653516,
|
|
"loss": 4.6822,
|
|
"mean_token_accuracy": 0.22509655356407166,
|
|
"num_tokens": 48804131.0,
|
|
"step": 26525
|
|
},
|
|
{
|
|
"entropy": 5.371398115158081,
|
|
"epoch": 2.216004009355162,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004505812052603671,
|
|
"loss": 4.7758,
|
|
"mean_token_accuracy": 0.22142037451267244,
|
|
"num_tokens": 48812986.0,
|
|
"step": 26530
|
|
},
|
|
{
|
|
"entropy": 5.5426952838897705,
|
|
"epoch": 2.216421650517875,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004505625876816222,
|
|
"loss": 4.8747,
|
|
"mean_token_accuracy": 0.22280308455228806,
|
|
"num_tokens": 48822200.0,
|
|
"step": 26535
|
|
},
|
|
{
|
|
"entropy": 5.4789448261260985,
|
|
"epoch": 2.216839291680588,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00045054396702944293,
|
|
"loss": 4.7892,
|
|
"mean_token_accuracy": 0.22599238902330399,
|
|
"num_tokens": 48831485.0,
|
|
"step": 26540
|
|
},
|
|
{
|
|
"entropy": 5.203324460983277,
|
|
"epoch": 2.217256932843301,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00045052534330415525,
|
|
"loss": 4.5929,
|
|
"mean_token_accuracy": 0.23798351734876633,
|
|
"num_tokens": 48840515.0,
|
|
"step": 26545
|
|
},
|
|
{
|
|
"entropy": 5.294050502777099,
|
|
"epoch": 2.217674574006014,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00045050671650608513,
|
|
"loss": 4.7556,
|
|
"mean_token_accuracy": 0.22809740155935287,
|
|
"num_tokens": 48849248.0,
|
|
"step": 26550
|
|
},
|
|
{
|
|
"entropy": 5.397607231140137,
|
|
"epoch": 2.2180922151687272,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004504880866355587,
|
|
"loss": 4.7454,
|
|
"mean_token_accuracy": 0.22649518251419068,
|
|
"num_tokens": 48858593.0,
|
|
"step": 26555
|
|
},
|
|
{
|
|
"entropy": 5.436401891708374,
|
|
"epoch": 2.21850985633144,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000450469453692902,
|
|
"loss": 4.8028,
|
|
"mean_token_accuracy": 0.2175636276602745,
|
|
"num_tokens": 48867859.0,
|
|
"step": 26560
|
|
},
|
|
{
|
|
"entropy": 5.387476301193237,
|
|
"epoch": 2.218927497494153,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00045045081767844137,
|
|
"loss": 4.7699,
|
|
"mean_token_accuracy": 0.23928795605897904,
|
|
"num_tokens": 48877556.0,
|
|
"step": 26565
|
|
},
|
|
{
|
|
"entropy": 5.400339555740357,
|
|
"epoch": 2.219345138656866,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000450432178592503,
|
|
"loss": 4.7651,
|
|
"mean_token_accuracy": 0.22851310223340987,
|
|
"num_tokens": 48887468.0,
|
|
"step": 26570
|
|
},
|
|
{
|
|
"entropy": 5.375104522705078,
|
|
"epoch": 2.219762779819579,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004504135364354131,
|
|
"loss": 4.6909,
|
|
"mean_token_accuracy": 0.23506515622138976,
|
|
"num_tokens": 48895683.0,
|
|
"step": 26575
|
|
},
|
|
{
|
|
"entropy": 5.4177717685699465,
|
|
"epoch": 2.220180420982292,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00045039489120749816,
|
|
"loss": 4.8118,
|
|
"mean_token_accuracy": 0.2276450827717781,
|
|
"num_tokens": 48904522.0,
|
|
"step": 26580
|
|
},
|
|
{
|
|
"entropy": 5.4504414081573485,
|
|
"epoch": 2.220598062145005,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004503762429090845,
|
|
"loss": 4.8564,
|
|
"mean_token_accuracy": 0.22349311262369156,
|
|
"num_tokens": 48914091.0,
|
|
"step": 26585
|
|
},
|
|
{
|
|
"entropy": 5.392312622070312,
|
|
"epoch": 2.221015703307718,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004503575915404986,
|
|
"loss": 4.7281,
|
|
"mean_token_accuracy": 0.2273402214050293,
|
|
"num_tokens": 48922652.0,
|
|
"step": 26590
|
|
},
|
|
{
|
|
"entropy": 5.443148183822632,
|
|
"epoch": 2.221433344470431,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000450338937102067,
|
|
"loss": 4.858,
|
|
"mean_token_accuracy": 0.22397394031286239,
|
|
"num_tokens": 48931512.0,
|
|
"step": 26595
|
|
},
|
|
{
|
|
"entropy": 5.389401006698608,
|
|
"epoch": 2.221850985633144,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00045032027959411624,
|
|
"loss": 4.7502,
|
|
"mean_token_accuracy": 0.219487027823925,
|
|
"num_tokens": 48940456.0,
|
|
"step": 26600
|
|
},
|
|
{
|
|
"entropy": 5.4346702098846436,
|
|
"epoch": 2.222268626795857,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.000450301619016973,
|
|
"loss": 4.8659,
|
|
"mean_token_accuracy": 0.21807041764259338,
|
|
"num_tokens": 48951109.0,
|
|
"step": 26605
|
|
},
|
|
{
|
|
"entropy": 5.3874509811401365,
|
|
"epoch": 2.22268626795857,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00045028295537096385,
|
|
"loss": 4.6991,
|
|
"mean_token_accuracy": 0.2283841848373413,
|
|
"num_tokens": 48959586.0,
|
|
"step": 26610
|
|
},
|
|
{
|
|
"entropy": 5.348777961730957,
|
|
"epoch": 2.223103909121283,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00045026428865641563,
|
|
"loss": 4.7141,
|
|
"mean_token_accuracy": 0.2331947550177574,
|
|
"num_tokens": 48968393.0,
|
|
"step": 26615
|
|
},
|
|
{
|
|
"entropy": 5.336112308502197,
|
|
"epoch": 2.223521550283996,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000450245618873655,
|
|
"loss": 4.7749,
|
|
"mean_token_accuracy": 0.22422672510147096,
|
|
"num_tokens": 48977483.0,
|
|
"step": 26620
|
|
},
|
|
{
|
|
"entropy": 5.430292749404908,
|
|
"epoch": 2.223939191446709,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004502269460230089,
|
|
"loss": 4.8124,
|
|
"mean_token_accuracy": 0.221519772708416,
|
|
"num_tokens": 48986568.0,
|
|
"step": 26625
|
|
},
|
|
{
|
|
"entropy": 5.386914968490601,
|
|
"epoch": 2.224356832609422,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004502082701048042,
|
|
"loss": 4.77,
|
|
"mean_token_accuracy": 0.2267031580209732,
|
|
"num_tokens": 48995952.0,
|
|
"step": 26630
|
|
},
|
|
{
|
|
"entropy": 5.383288431167602,
|
|
"epoch": 2.224774473772135,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00045018959111936785,
|
|
"loss": 4.8108,
|
|
"mean_token_accuracy": 0.22221098989248275,
|
|
"num_tokens": 49006168.0,
|
|
"step": 26635
|
|
},
|
|
{
|
|
"entropy": 5.354575347900391,
|
|
"epoch": 2.225192114934848,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004501709090670268,
|
|
"loss": 4.7051,
|
|
"mean_token_accuracy": 0.23088476359844207,
|
|
"num_tokens": 49014903.0,
|
|
"step": 26640
|
|
},
|
|
{
|
|
"entropy": 5.359739446640015,
|
|
"epoch": 2.225609756097561,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004501522239481081,
|
|
"loss": 4.7571,
|
|
"mean_token_accuracy": 0.22945339530706405,
|
|
"num_tokens": 49024801.0,
|
|
"step": 26645
|
|
},
|
|
{
|
|
"entropy": 5.439863967895508,
|
|
"epoch": 2.2260273972602738,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00045013353576293897,
|
|
"loss": 4.7469,
|
|
"mean_token_accuracy": 0.22333430051803588,
|
|
"num_tokens": 49033822.0,
|
|
"step": 26650
|
|
},
|
|
{
|
|
"entropy": 5.435562801361084,
|
|
"epoch": 2.226445038422987,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00045011484451184646,
|
|
"loss": 4.7379,
|
|
"mean_token_accuracy": 0.2285599336028099,
|
|
"num_tokens": 49044074.0,
|
|
"step": 26655
|
|
},
|
|
{
|
|
"entropy": 5.356130075454712,
|
|
"epoch": 2.2268626795857,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00045009615019515783,
|
|
"loss": 4.7609,
|
|
"mean_token_accuracy": 0.2258943125605583,
|
|
"num_tokens": 49053090.0,
|
|
"step": 26660
|
|
},
|
|
{
|
|
"entropy": 5.263904285430908,
|
|
"epoch": 2.227280320748413,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00045007745281320035,
|
|
"loss": 4.7105,
|
|
"mean_token_accuracy": 0.22877068370580672,
|
|
"num_tokens": 49061652.0,
|
|
"step": 26665
|
|
},
|
|
{
|
|
"entropy": 5.314088201522827,
|
|
"epoch": 2.227697961911126,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00045005875236630124,
|
|
"loss": 4.6587,
|
|
"mean_token_accuracy": 0.2354392409324646,
|
|
"num_tokens": 49070196.0,
|
|
"step": 26670
|
|
},
|
|
{
|
|
"entropy": 5.379920530319214,
|
|
"epoch": 2.228115603073839,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00045004004885478797,
|
|
"loss": 4.7493,
|
|
"mean_token_accuracy": 0.2275515541434288,
|
|
"num_tokens": 49079422.0,
|
|
"step": 26675
|
|
},
|
|
{
|
|
"entropy": 5.321505880355835,
|
|
"epoch": 2.228533244236552,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000450021342278988,
|
|
"loss": 4.7361,
|
|
"mean_token_accuracy": 0.22527068257331848,
|
|
"num_tokens": 49089010.0,
|
|
"step": 26680
|
|
},
|
|
{
|
|
"entropy": 5.351991367340088,
|
|
"epoch": 2.228950885399265,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004500026326392287,
|
|
"loss": 4.6685,
|
|
"mean_token_accuracy": 0.24126924723386764,
|
|
"num_tokens": 49097153.0,
|
|
"step": 26685
|
|
},
|
|
{
|
|
"entropy": 5.37234935760498,
|
|
"epoch": 2.229368526561978,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00044998391993583773,
|
|
"loss": 4.7323,
|
|
"mean_token_accuracy": 0.22920198887586593,
|
|
"num_tokens": 49107741.0,
|
|
"step": 26690
|
|
},
|
|
{
|
|
"entropy": 5.427697610855103,
|
|
"epoch": 2.229786167724691,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004499652041691425,
|
|
"loss": 4.7724,
|
|
"mean_token_accuracy": 0.22753166556358337,
|
|
"num_tokens": 49117182.0,
|
|
"step": 26695
|
|
},
|
|
{
|
|
"entropy": 5.401736307144165,
|
|
"epoch": 2.230203808887404,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004499464853394709,
|
|
"loss": 4.826,
|
|
"mean_token_accuracy": 0.22634999006986617,
|
|
"num_tokens": 49128036.0,
|
|
"step": 26700
|
|
},
|
|
{
|
|
"entropy": 5.38282585144043,
|
|
"epoch": 2.230621450050117,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00044992776344715036,
|
|
"loss": 4.7094,
|
|
"mean_token_accuracy": 0.22529392391443254,
|
|
"num_tokens": 49137669.0,
|
|
"step": 26705
|
|
},
|
|
{
|
|
"entropy": 5.389901924133301,
|
|
"epoch": 2.23103909121283,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004499090384925088,
|
|
"loss": 4.7475,
|
|
"mean_token_accuracy": 0.2286282792687416,
|
|
"num_tokens": 49147447.0,
|
|
"step": 26710
|
|
},
|
|
{
|
|
"entropy": 5.355673980712891,
|
|
"epoch": 2.231456732375543,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00044989031047587406,
|
|
"loss": 4.823,
|
|
"mean_token_accuracy": 0.22177538573741912,
|
|
"num_tokens": 49156516.0,
|
|
"step": 26715
|
|
},
|
|
{
|
|
"entropy": 5.444485998153686,
|
|
"epoch": 2.231874373538256,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004498715793975738,
|
|
"loss": 4.8346,
|
|
"mean_token_accuracy": 0.22270854711532592,
|
|
"num_tokens": 49165735.0,
|
|
"step": 26720
|
|
},
|
|
{
|
|
"entropy": 5.389800119400024,
|
|
"epoch": 2.232292014700969,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00044985284525793617,
|
|
"loss": 4.734,
|
|
"mean_token_accuracy": 0.22400192618370057,
|
|
"num_tokens": 49174389.0,
|
|
"step": 26725
|
|
},
|
|
{
|
|
"entropy": 5.33318977355957,
|
|
"epoch": 2.232709655863682,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004498341080572889,
|
|
"loss": 4.7203,
|
|
"mean_token_accuracy": 0.22740822285413742,
|
|
"num_tokens": 49183521.0,
|
|
"step": 26730
|
|
},
|
|
{
|
|
"entropy": 5.317619514465332,
|
|
"epoch": 2.233127297026395,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00044981536779596025,
|
|
"loss": 4.7195,
|
|
"mean_token_accuracy": 0.23219562768936158,
|
|
"num_tokens": 49192971.0,
|
|
"step": 26735
|
|
},
|
|
{
|
|
"entropy": 5.418864631652832,
|
|
"epoch": 2.233544938189108,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004497966244742781,
|
|
"loss": 4.7131,
|
|
"mean_token_accuracy": 0.23151205480098724,
|
|
"num_tokens": 49201502.0,
|
|
"step": 26740
|
|
},
|
|
{
|
|
"entropy": 5.3347619533538815,
|
|
"epoch": 2.2339625793518207,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004497778780925706,
|
|
"loss": 4.6897,
|
|
"mean_token_accuracy": 0.23097605705261232,
|
|
"num_tokens": 49211096.0,
|
|
"step": 26745
|
|
},
|
|
{
|
|
"entropy": 5.405238819122315,
|
|
"epoch": 2.234380220514534,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00044975912865116604,
|
|
"loss": 4.8252,
|
|
"mean_token_accuracy": 0.22641546428203582,
|
|
"num_tokens": 49221447.0,
|
|
"step": 26750
|
|
},
|
|
{
|
|
"entropy": 5.365223455429077,
|
|
"epoch": 2.234797861677247,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00044974037615039253,
|
|
"loss": 4.7308,
|
|
"mean_token_accuracy": 0.23072269111871718,
|
|
"num_tokens": 49229572.0,
|
|
"step": 26755
|
|
},
|
|
{
|
|
"entropy": 5.42956862449646,
|
|
"epoch": 2.23521550283996,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00044972162059057837,
|
|
"loss": 4.7681,
|
|
"mean_token_accuracy": 0.22001273185014725,
|
|
"num_tokens": 49239184.0,
|
|
"step": 26760
|
|
},
|
|
{
|
|
"entropy": 5.3452314853668215,
|
|
"epoch": 2.235633144002673,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00044970286197205196,
|
|
"loss": 4.7475,
|
|
"mean_token_accuracy": 0.22742487788200377,
|
|
"num_tokens": 49248844.0,
|
|
"step": 26765
|
|
},
|
|
{
|
|
"entropy": 5.3825092792510985,
|
|
"epoch": 2.2360507851653857,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004496841002951416,
|
|
"loss": 4.7427,
|
|
"mean_token_accuracy": 0.2232535406947136,
|
|
"num_tokens": 49258028.0,
|
|
"step": 26770
|
|
},
|
|
{
|
|
"entropy": 5.402315616607666,
|
|
"epoch": 2.236468426328099,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004496653355601759,
|
|
"loss": 4.7465,
|
|
"mean_token_accuracy": 0.2260683223605156,
|
|
"num_tokens": 49267590.0,
|
|
"step": 26775
|
|
},
|
|
{
|
|
"entropy": 5.376711034774781,
|
|
"epoch": 2.2368860674908118,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004496465677674832,
|
|
"loss": 4.6698,
|
|
"mean_token_accuracy": 0.23485494256019593,
|
|
"num_tokens": 49275897.0,
|
|
"step": 26780
|
|
},
|
|
{
|
|
"entropy": 5.353020143508911,
|
|
"epoch": 2.237303708653525,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004496277969173921,
|
|
"loss": 4.7697,
|
|
"mean_token_accuracy": 0.2207823857665062,
|
|
"num_tokens": 49285853.0,
|
|
"step": 26785
|
|
},
|
|
{
|
|
"entropy": 5.4092260837554935,
|
|
"epoch": 2.237721349816238,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00044960902301023126,
|
|
"loss": 4.6646,
|
|
"mean_token_accuracy": 0.23687416017055513,
|
|
"num_tokens": 49295129.0,
|
|
"step": 26790
|
|
},
|
|
{
|
|
"entropy": 5.280441761016846,
|
|
"epoch": 2.238138990978951,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004495902460463293,
|
|
"loss": 4.6161,
|
|
"mean_token_accuracy": 0.23963025957345963,
|
|
"num_tokens": 49304117.0,
|
|
"step": 26795
|
|
},
|
|
{
|
|
"entropy": 5.303223037719727,
|
|
"epoch": 2.238556632141664,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004495714660260149,
|
|
"loss": 4.6442,
|
|
"mean_token_accuracy": 0.2355189174413681,
|
|
"num_tokens": 49312872.0,
|
|
"step": 26800
|
|
},
|
|
{
|
|
"entropy": 5.460773086547851,
|
|
"epoch": 2.2389742733043767,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00044955268294961687,
|
|
"loss": 4.8814,
|
|
"mean_token_accuracy": 0.21915910094976426,
|
|
"num_tokens": 49322081.0,
|
|
"step": 26805
|
|
},
|
|
{
|
|
"entropy": 5.4003965854644775,
|
|
"epoch": 2.23939191446709,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00044953389681746405,
|
|
"loss": 4.6762,
|
|
"mean_token_accuracy": 0.23117873519659043,
|
|
"num_tokens": 49331288.0,
|
|
"step": 26810
|
|
},
|
|
{
|
|
"entropy": 5.350405931472778,
|
|
"epoch": 2.2398095556298028,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004495151076298852,
|
|
"loss": 4.765,
|
|
"mean_token_accuracy": 0.22535603791475295,
|
|
"num_tokens": 49341135.0,
|
|
"step": 26815
|
|
},
|
|
{
|
|
"entropy": 5.382250642776489,
|
|
"epoch": 2.240227196792516,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004494963153872093,
|
|
"loss": 4.8171,
|
|
"mean_token_accuracy": 0.22724275887012482,
|
|
"num_tokens": 49350450.0,
|
|
"step": 26820
|
|
},
|
|
{
|
|
"entropy": 5.479473018646241,
|
|
"epoch": 2.240644837955229,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00044947752008976546,
|
|
"loss": 4.7984,
|
|
"mean_token_accuracy": 0.226372429728508,
|
|
"num_tokens": 49358719.0,
|
|
"step": 26825
|
|
},
|
|
{
|
|
"entropy": 5.401285123825073,
|
|
"epoch": 2.241062479117942,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004494587217378826,
|
|
"loss": 4.7007,
|
|
"mean_token_accuracy": 0.23480355888605117,
|
|
"num_tokens": 49366976.0,
|
|
"step": 26830
|
|
},
|
|
{
|
|
"entropy": 5.322954511642456,
|
|
"epoch": 2.241480120280655,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00044943992033188974,
|
|
"loss": 4.7707,
|
|
"mean_token_accuracy": 0.22410963624715804,
|
|
"num_tokens": 49376256.0,
|
|
"step": 26835
|
|
},
|
|
{
|
|
"entropy": 5.301628160476684,
|
|
"epoch": 2.2418977614433677,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004494211158721162,
|
|
"loss": 4.7053,
|
|
"mean_token_accuracy": 0.23350521475076674,
|
|
"num_tokens": 49385120.0,
|
|
"step": 26840
|
|
},
|
|
{
|
|
"entropy": 5.39680323600769,
|
|
"epoch": 2.242315402606081,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000449402308358891,
|
|
"loss": 4.7523,
|
|
"mean_token_accuracy": 0.22381118535995484,
|
|
"num_tokens": 49394960.0,
|
|
"step": 26845
|
|
},
|
|
{
|
|
"entropy": 5.300629186630249,
|
|
"epoch": 2.242733043768794,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004493834977925435,
|
|
"loss": 4.6353,
|
|
"mean_token_accuracy": 0.23342085331678392,
|
|
"num_tokens": 49404332.0,
|
|
"step": 26850
|
|
},
|
|
{
|
|
"entropy": 5.341759157180786,
|
|
"epoch": 2.243150684931507,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00044936468417340294,
|
|
"loss": 4.7003,
|
|
"mean_token_accuracy": 0.23046866804361343,
|
|
"num_tokens": 49413723.0,
|
|
"step": 26855
|
|
},
|
|
{
|
|
"entropy": 5.423443078994751,
|
|
"epoch": 2.24356832609422,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004493458675017987,
|
|
"loss": 4.7762,
|
|
"mean_token_accuracy": 0.22472671568393707,
|
|
"num_tokens": 49423188.0,
|
|
"step": 26860
|
|
},
|
|
{
|
|
"entropy": 5.382220077514648,
|
|
"epoch": 2.2439859672569327,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004493270477780602,
|
|
"loss": 4.7672,
|
|
"mean_token_accuracy": 0.22358109205961227,
|
|
"num_tokens": 49432826.0,
|
|
"step": 26865
|
|
},
|
|
{
|
|
"entropy": 5.356124448776245,
|
|
"epoch": 2.244403608419646,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00044930822500251693,
|
|
"loss": 4.7306,
|
|
"mean_token_accuracy": 0.22801510989665985,
|
|
"num_tokens": 49442538.0,
|
|
"step": 26870
|
|
},
|
|
{
|
|
"entropy": 5.414134693145752,
|
|
"epoch": 2.2448212495823587,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00044928939917549833,
|
|
"loss": 4.7947,
|
|
"mean_token_accuracy": 0.22668550312519073,
|
|
"num_tokens": 49451643.0,
|
|
"step": 26875
|
|
},
|
|
{
|
|
"entropy": 5.406862592697143,
|
|
"epoch": 2.245238890745072,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000449270570297334,
|
|
"loss": 4.7504,
|
|
"mean_token_accuracy": 0.22888447791337968,
|
|
"num_tokens": 49460866.0,
|
|
"step": 26880
|
|
},
|
|
{
|
|
"entropy": 5.375336790084839,
|
|
"epoch": 2.245656531907785,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004492517383683536,
|
|
"loss": 4.7606,
|
|
"mean_token_accuracy": 0.21771778017282487,
|
|
"num_tokens": 49470750.0,
|
|
"step": 26885
|
|
},
|
|
{
|
|
"entropy": 5.307598018646241,
|
|
"epoch": 2.2460741730704976,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00044923290338888674,
|
|
"loss": 4.7515,
|
|
"mean_token_accuracy": 0.22708749324083327,
|
|
"num_tokens": 49479841.0,
|
|
"step": 26890
|
|
},
|
|
{
|
|
"entropy": 5.349849462509155,
|
|
"epoch": 2.246491814233211,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004492140653592632,
|
|
"loss": 4.7467,
|
|
"mean_token_accuracy": 0.2229409024119377,
|
|
"num_tokens": 49488877.0,
|
|
"step": 26895
|
|
},
|
|
{
|
|
"entropy": 5.4404316425323485,
|
|
"epoch": 2.2469094553959237,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00044919522427981276,
|
|
"loss": 4.8101,
|
|
"mean_token_accuracy": 0.2221425488591194,
|
|
"num_tokens": 49498892.0,
|
|
"step": 26900
|
|
},
|
|
{
|
|
"entropy": 5.48241810798645,
|
|
"epoch": 2.247327096558637,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004491763801508652,
|
|
"loss": 4.8435,
|
|
"mean_token_accuracy": 0.21676957607269287,
|
|
"num_tokens": 49507444.0,
|
|
"step": 26905
|
|
},
|
|
{
|
|
"entropy": 5.344045114517212,
|
|
"epoch": 2.2477447377213498,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00044915753297275046,
|
|
"loss": 4.735,
|
|
"mean_token_accuracy": 0.23303641229867936,
|
|
"num_tokens": 49516710.0,
|
|
"step": 26910
|
|
},
|
|
{
|
|
"entropy": 5.3706334114074705,
|
|
"epoch": 2.248162378884063,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00044913868274579856,
|
|
"loss": 4.7974,
|
|
"mean_token_accuracy": 0.2292293593287468,
|
|
"num_tokens": 49526945.0,
|
|
"step": 26915
|
|
},
|
|
{
|
|
"entropy": 5.2889691352844235,
|
|
"epoch": 2.248580020046776,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00044911982947033925,
|
|
"loss": 4.6569,
|
|
"mean_token_accuracy": 0.2346352830529213,
|
|
"num_tokens": 49536058.0,
|
|
"step": 26920
|
|
},
|
|
{
|
|
"entropy": 5.339493989944458,
|
|
"epoch": 2.2489976612094886,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004491009731467028,
|
|
"loss": 4.7149,
|
|
"mean_token_accuracy": 0.2317779079079628,
|
|
"num_tokens": 49544761.0,
|
|
"step": 26925
|
|
},
|
|
{
|
|
"entropy": 5.447426128387451,
|
|
"epoch": 2.249415302372202,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004490821137752193,
|
|
"loss": 4.8482,
|
|
"mean_token_accuracy": 0.21534496396780015,
|
|
"num_tokens": 49553933.0,
|
|
"step": 26930
|
|
},
|
|
{
|
|
"entropy": 5.403221130371094,
|
|
"epoch": 2.2498329435349147,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004490632513562188,
|
|
"loss": 4.7368,
|
|
"mean_token_accuracy": 0.2261601746082306,
|
|
"num_tokens": 49563668.0,
|
|
"step": 26935
|
|
},
|
|
{
|
|
"entropy": 5.4337296962738035,
|
|
"epoch": 2.250250584697628,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004490443858900316,
|
|
"loss": 4.7852,
|
|
"mean_token_accuracy": 0.22447049915790557,
|
|
"num_tokens": 49573830.0,
|
|
"step": 26940
|
|
},
|
|
{
|
|
"entropy": 5.362204265594483,
|
|
"epoch": 2.2506682258603408,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00044902551737698785,
|
|
"loss": 4.7155,
|
|
"mean_token_accuracy": 0.23333728462457656,
|
|
"num_tokens": 49582396.0,
|
|
"step": 26945
|
|
},
|
|
{
|
|
"entropy": 5.367348670959473,
|
|
"epoch": 2.251085867023054,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00044900664581741805,
|
|
"loss": 4.703,
|
|
"mean_token_accuracy": 0.23037444055080414,
|
|
"num_tokens": 49590918.0,
|
|
"step": 26950
|
|
},
|
|
{
|
|
"entropy": 5.401692724227905,
|
|
"epoch": 2.251503508185767,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004489877712116524,
|
|
"loss": 4.7738,
|
|
"mean_token_accuracy": 0.22360292226076126,
|
|
"num_tokens": 49600365.0,
|
|
"step": 26955
|
|
},
|
|
{
|
|
"entropy": 5.392166805267334,
|
|
"epoch": 2.2519211493484796,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004489688935600214,
|
|
"loss": 4.7684,
|
|
"mean_token_accuracy": 0.2315339744091034,
|
|
"num_tokens": 49610002.0,
|
|
"step": 26960
|
|
},
|
|
{
|
|
"entropy": 5.371668100357056,
|
|
"epoch": 2.252338790511193,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00044895001286285557,
|
|
"loss": 4.7236,
|
|
"mean_token_accuracy": 0.23512399196624756,
|
|
"num_tokens": 49619085.0,
|
|
"step": 26965
|
|
},
|
|
{
|
|
"entropy": 5.289110946655273,
|
|
"epoch": 2.2527564316739057,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00044893112912048526,
|
|
"loss": 4.6159,
|
|
"mean_token_accuracy": 0.23925953954458237,
|
|
"num_tokens": 49627753.0,
|
|
"step": 26970
|
|
},
|
|
{
|
|
"entropy": 5.340015935897827,
|
|
"epoch": 2.253174072836619,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004489122423332413,
|
|
"loss": 4.6946,
|
|
"mean_token_accuracy": 0.23293474465608596,
|
|
"num_tokens": 49637377.0,
|
|
"step": 26975
|
|
},
|
|
{
|
|
"entropy": 5.347563648223877,
|
|
"epoch": 2.253591713999332,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00044889335250145415,
|
|
"loss": 4.7795,
|
|
"mean_token_accuracy": 0.22932117134332658,
|
|
"num_tokens": 49645323.0,
|
|
"step": 26980
|
|
},
|
|
{
|
|
"entropy": 5.389743280410767,
|
|
"epoch": 2.2540093551620446,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004488744596254545,
|
|
"loss": 4.7628,
|
|
"mean_token_accuracy": 0.22009522020816802,
|
|
"num_tokens": 49655076.0,
|
|
"step": 26985
|
|
},
|
|
{
|
|
"entropy": 5.353398275375366,
|
|
"epoch": 2.254426996324758,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00044885556370557317,
|
|
"loss": 4.7911,
|
|
"mean_token_accuracy": 0.22930739521980287,
|
|
"num_tokens": 49664518.0,
|
|
"step": 26990
|
|
},
|
|
{
|
|
"entropy": 5.302618789672851,
|
|
"epoch": 2.2548446374874707,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000448836664742141,
|
|
"loss": 4.5683,
|
|
"mean_token_accuracy": 0.2422853961586952,
|
|
"num_tokens": 49673530.0,
|
|
"step": 26995
|
|
},
|
|
{
|
|
"entropy": 5.4206122875213625,
|
|
"epoch": 2.255262278650184,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004488177627354887,
|
|
"loss": 4.8049,
|
|
"mean_token_accuracy": 0.21838244646787644,
|
|
"num_tokens": 49682716.0,
|
|
"step": 27000
|
|
},
|
|
{
|
|
"epoch": 2.255262278650184,
|
|
"eval_entropy": 5.070927549130682,
|
|
"eval_loss": 4.7764387130737305,
|
|
"eval_mean_token_accuracy": 0.23732501840160902,
|
|
"eval_num_tokens": 49682716.0,
|
|
"eval_runtime": 20.8935,
|
|
"eval_samples_per_second": 1807.401,
|
|
"eval_steps_per_second": 225.955,
|
|
"step": 27000
|
|
},
|
|
{
|
|
"entropy": 5.368668174743652,
|
|
"epoch": 2.2556799198128967,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00044879885768594726,
|
|
"loss": 4.686,
|
|
"mean_token_accuracy": 0.22749467492103576,
|
|
"num_tokens": 49691726.0,
|
|
"step": 27005
|
|
},
|
|
{
|
|
"entropy": 5.281498146057129,
|
|
"epoch": 2.2560975609756095,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00044877994959384757,
|
|
"loss": 4.6604,
|
|
"mean_token_accuracy": 0.2272058293223381,
|
|
"num_tokens": 49701021.0,
|
|
"step": 27010
|
|
},
|
|
{
|
|
"entropy": 5.304470777511597,
|
|
"epoch": 2.256515202138323,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004487610384595207,
|
|
"loss": 4.7154,
|
|
"mean_token_accuracy": 0.22799744009971618,
|
|
"num_tokens": 49710583.0,
|
|
"step": 27015
|
|
},
|
|
{
|
|
"entropy": 5.376938438415527,
|
|
"epoch": 2.2569328433010356,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004487421242832977,
|
|
"loss": 4.7925,
|
|
"mean_token_accuracy": 0.22554456293582917,
|
|
"num_tokens": 49718365.0,
|
|
"step": 27020
|
|
},
|
|
{
|
|
"entropy": 5.334223127365112,
|
|
"epoch": 2.257350484463749,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004487232070655097,
|
|
"loss": 4.7053,
|
|
"mean_token_accuracy": 0.23548241406679155,
|
|
"num_tokens": 49728340.0,
|
|
"step": 27025
|
|
},
|
|
{
|
|
"entropy": 5.320151662826538,
|
|
"epoch": 2.2577681256264617,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004487042868064878,
|
|
"loss": 4.6094,
|
|
"mean_token_accuracy": 0.23585756123065948,
|
|
"num_tokens": 49736061.0,
|
|
"step": 27030
|
|
},
|
|
{
|
|
"entropy": 5.3530620574951175,
|
|
"epoch": 2.258185766789175,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004486853635065634,
|
|
"loss": 4.6348,
|
|
"mean_token_accuracy": 0.23378556817770005,
|
|
"num_tokens": 49744797.0,
|
|
"step": 27035
|
|
},
|
|
{
|
|
"entropy": 5.377093315124512,
|
|
"epoch": 2.2586034079518877,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00044866643716606747,
|
|
"loss": 4.711,
|
|
"mean_token_accuracy": 0.23246934711933137,
|
|
"num_tokens": 49754118.0,
|
|
"step": 27040
|
|
},
|
|
{
|
|
"entropy": 5.477370262145996,
|
|
"epoch": 2.2590210491146006,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004486475077853316,
|
|
"loss": 4.9345,
|
|
"mean_token_accuracy": 0.2084823027253151,
|
|
"num_tokens": 49764721.0,
|
|
"step": 27045
|
|
},
|
|
{
|
|
"entropy": 5.43669581413269,
|
|
"epoch": 2.259438690277314,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00044862857536468717,
|
|
"loss": 4.7378,
|
|
"mean_token_accuracy": 0.23287101984024047,
|
|
"num_tokens": 49773013.0,
|
|
"step": 27050
|
|
},
|
|
{
|
|
"entropy": 5.395337438583374,
|
|
"epoch": 2.2598563314400266,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004486096399044654,
|
|
"loss": 4.8595,
|
|
"mean_token_accuracy": 0.21875568032264708,
|
|
"num_tokens": 49781608.0,
|
|
"step": 27055
|
|
},
|
|
{
|
|
"entropy": 5.483937549591064,
|
|
"epoch": 2.26027397260274,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000448590701404998,
|
|
"loss": 4.7985,
|
|
"mean_token_accuracy": 0.22558411955833435,
|
|
"num_tokens": 49791136.0,
|
|
"step": 27060
|
|
},
|
|
{
|
|
"entropy": 5.359665107727051,
|
|
"epoch": 2.2606916137654527,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00044857175986661634,
|
|
"loss": 4.6558,
|
|
"mean_token_accuracy": 0.2363301545381546,
|
|
"num_tokens": 49800656.0,
|
|
"step": 27065
|
|
},
|
|
{
|
|
"entropy": 5.421591091156006,
|
|
"epoch": 2.261109254928166,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004485528152896522,
|
|
"loss": 4.8851,
|
|
"mean_token_accuracy": 0.21345235407352448,
|
|
"num_tokens": 49810528.0,
|
|
"step": 27070
|
|
},
|
|
{
|
|
"entropy": 5.346616411209107,
|
|
"epoch": 2.2615268960908788,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00044853386767443706,
|
|
"loss": 4.7221,
|
|
"mean_token_accuracy": 0.2286324605345726,
|
|
"num_tokens": 49819979.0,
|
|
"step": 27075
|
|
},
|
|
{
|
|
"entropy": 5.39884204864502,
|
|
"epoch": 2.2619445372535916,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00044851491702130265,
|
|
"loss": 4.7691,
|
|
"mean_token_accuracy": 0.22365612536668777,
|
|
"num_tokens": 49828656.0,
|
|
"step": 27080
|
|
},
|
|
{
|
|
"entropy": 5.411187982559204,
|
|
"epoch": 2.262362178416305,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00044849596333058087,
|
|
"loss": 4.815,
|
|
"mean_token_accuracy": 0.21978276073932648,
|
|
"num_tokens": 49838103.0,
|
|
"step": 27085
|
|
},
|
|
{
|
|
"entropy": 5.414150524139404,
|
|
"epoch": 2.2627798195790176,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00044847700660260325,
|
|
"loss": 4.8148,
|
|
"mean_token_accuracy": 0.22327419966459275,
|
|
"num_tokens": 49847863.0,
|
|
"step": 27090
|
|
},
|
|
{
|
|
"entropy": 5.362363052368164,
|
|
"epoch": 2.263197460741731,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004484580468377019,
|
|
"loss": 4.7408,
|
|
"mean_token_accuracy": 0.2292506143450737,
|
|
"num_tokens": 49857608.0,
|
|
"step": 27095
|
|
},
|
|
{
|
|
"entropy": 5.328221178054809,
|
|
"epoch": 2.2636151019044437,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004484390840362086,
|
|
"loss": 4.6777,
|
|
"mean_token_accuracy": 0.23119885623455047,
|
|
"num_tokens": 49867805.0,
|
|
"step": 27100
|
|
},
|
|
{
|
|
"entropy": 5.399573945999146,
|
|
"epoch": 2.2640327430671565,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00044842011819845546,
|
|
"loss": 4.8332,
|
|
"mean_token_accuracy": 0.2194836050271988,
|
|
"num_tokens": 49877456.0,
|
|
"step": 27105
|
|
},
|
|
{
|
|
"entropy": 5.429108476638794,
|
|
"epoch": 2.2644503842298698,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00044840114932477435,
|
|
"loss": 4.7334,
|
|
"mean_token_accuracy": 0.22486352324485778,
|
|
"num_tokens": 49886179.0,
|
|
"step": 27110
|
|
},
|
|
{
|
|
"entropy": 5.41591968536377,
|
|
"epoch": 2.2648680253925826,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004483821774154975,
|
|
"loss": 4.8091,
|
|
"mean_token_accuracy": 0.22955770641565323,
|
|
"num_tokens": 49895765.0,
|
|
"step": 27115
|
|
},
|
|
{
|
|
"entropy": 5.341279983520508,
|
|
"epoch": 2.265285666555296,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00044836320247095674,
|
|
"loss": 4.8283,
|
|
"mean_token_accuracy": 0.21634051352739334,
|
|
"num_tokens": 49904921.0,
|
|
"step": 27120
|
|
},
|
|
{
|
|
"entropy": 5.410868501663208,
|
|
"epoch": 2.2657033077180087,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004483442244914846,
|
|
"loss": 4.775,
|
|
"mean_token_accuracy": 0.2287063404917717,
|
|
"num_tokens": 49913464.0,
|
|
"step": 27125
|
|
},
|
|
{
|
|
"entropy": 5.459866571426391,
|
|
"epoch": 2.2661209488807215,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004483252434774131,
|
|
"loss": 4.8286,
|
|
"mean_token_accuracy": 0.2282079666852951,
|
|
"num_tokens": 49922893.0,
|
|
"step": 27130
|
|
},
|
|
{
|
|
"entropy": 5.327152681350708,
|
|
"epoch": 2.2665385900434347,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004483062594290746,
|
|
"loss": 4.7134,
|
|
"mean_token_accuracy": 0.23733058273792268,
|
|
"num_tokens": 49932011.0,
|
|
"step": 27135
|
|
},
|
|
{
|
|
"entropy": 5.429852533340454,
|
|
"epoch": 2.2669562312061475,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004482872723468014,
|
|
"loss": 4.885,
|
|
"mean_token_accuracy": 0.21651025861501694,
|
|
"num_tokens": 49940971.0,
|
|
"step": 27140
|
|
},
|
|
{
|
|
"entropy": 5.415600919723511,
|
|
"epoch": 2.267373872368861,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00044826828223092584,
|
|
"loss": 4.8023,
|
|
"mean_token_accuracy": 0.22542161047458648,
|
|
"num_tokens": 49951533.0,
|
|
"step": 27145
|
|
},
|
|
{
|
|
"entropy": 5.376659679412842,
|
|
"epoch": 2.2677915135315736,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004482492890817806,
|
|
"loss": 4.7564,
|
|
"mean_token_accuracy": 0.2281288594007492,
|
|
"num_tokens": 49960842.0,
|
|
"step": 27150
|
|
},
|
|
{
|
|
"entropy": 5.447202253341675,
|
|
"epoch": 2.268209154694287,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00044823029289969786,
|
|
"loss": 4.8308,
|
|
"mean_token_accuracy": 0.2260229393839836,
|
|
"num_tokens": 49970814.0,
|
|
"step": 27155
|
|
},
|
|
{
|
|
"entropy": 5.424910354614258,
|
|
"epoch": 2.2686267958569997,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004482112936850104,
|
|
"loss": 4.7952,
|
|
"mean_token_accuracy": 0.23012313693761827,
|
|
"num_tokens": 49980912.0,
|
|
"step": 27160
|
|
},
|
|
{
|
|
"entropy": 5.409082078933716,
|
|
"epoch": 2.2690444370197125,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00044819229143805076,
|
|
"loss": 4.8316,
|
|
"mean_token_accuracy": 0.22919670939445497,
|
|
"num_tokens": 49990404.0,
|
|
"step": 27165
|
|
},
|
|
{
|
|
"entropy": 5.301610374450684,
|
|
"epoch": 2.2694620781824257,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004481732861591516,
|
|
"loss": 4.636,
|
|
"mean_token_accuracy": 0.24347648173570632,
|
|
"num_tokens": 50000569.0,
|
|
"step": 27170
|
|
},
|
|
{
|
|
"entropy": 5.346679449081421,
|
|
"epoch": 2.2698797193451385,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004481542778486456,
|
|
"loss": 4.7942,
|
|
"mean_token_accuracy": 0.22797907441854476,
|
|
"num_tokens": 50009332.0,
|
|
"step": 27175
|
|
},
|
|
{
|
|
"entropy": 5.402194499969482,
|
|
"epoch": 2.270297360507852,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004481352665068654,
|
|
"loss": 4.792,
|
|
"mean_token_accuracy": 0.2213426947593689,
|
|
"num_tokens": 50019184.0,
|
|
"step": 27180
|
|
},
|
|
{
|
|
"entropy": 5.462353992462158,
|
|
"epoch": 2.2707150016705646,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00044811625213414416,
|
|
"loss": 4.8774,
|
|
"mean_token_accuracy": 0.21902430206537246,
|
|
"num_tokens": 50028522.0,
|
|
"step": 27185
|
|
},
|
|
{
|
|
"entropy": 5.45093150138855,
|
|
"epoch": 2.271132642833278,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004480972347308145,
|
|
"loss": 4.7765,
|
|
"mean_token_accuracy": 0.22717125415802003,
|
|
"num_tokens": 50037850.0,
|
|
"step": 27190
|
|
},
|
|
{
|
|
"entropy": 5.274160385131836,
|
|
"epoch": 2.2715502839959907,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004480782142972093,
|
|
"loss": 4.708,
|
|
"mean_token_accuracy": 0.23233463168144225,
|
|
"num_tokens": 50047096.0,
|
|
"step": 27195
|
|
},
|
|
{
|
|
"entropy": 5.365207576751709,
|
|
"epoch": 2.2719679251587035,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00044805919083366175,
|
|
"loss": 4.7392,
|
|
"mean_token_accuracy": 0.22677522152662277,
|
|
"num_tokens": 50055847.0,
|
|
"step": 27200
|
|
},
|
|
{
|
|
"entropy": 5.4651885509490965,
|
|
"epoch": 2.2723855663214167,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00044804016434050466,
|
|
"loss": 4.96,
|
|
"mean_token_accuracy": 0.21429630666971206,
|
|
"num_tokens": 50064498.0,
|
|
"step": 27205
|
|
},
|
|
{
|
|
"entropy": 5.399878883361817,
|
|
"epoch": 2.2728032074841296,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004480211348180712,
|
|
"loss": 4.8131,
|
|
"mean_token_accuracy": 0.22170716375112534,
|
|
"num_tokens": 50072831.0,
|
|
"step": 27210
|
|
},
|
|
{
|
|
"entropy": 5.433202838897705,
|
|
"epoch": 2.273220848646843,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00044800210226669454,
|
|
"loss": 4.8107,
|
|
"mean_token_accuracy": 0.2245914965867996,
|
|
"num_tokens": 50082559.0,
|
|
"step": 27215
|
|
},
|
|
{
|
|
"entropy": 5.3941892147064205,
|
|
"epoch": 2.2736384898095556,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004479830666867078,
|
|
"loss": 4.7469,
|
|
"mean_token_accuracy": 0.22850874364376067,
|
|
"num_tokens": 50091853.0,
|
|
"step": 27220
|
|
},
|
|
{
|
|
"entropy": 5.369069766998291,
|
|
"epoch": 2.2740561309722684,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004479640280784443,
|
|
"loss": 4.726,
|
|
"mean_token_accuracy": 0.2285667061805725,
|
|
"num_tokens": 50100601.0,
|
|
"step": 27225
|
|
},
|
|
{
|
|
"entropy": 5.3695886611938475,
|
|
"epoch": 2.2744737721349817,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004479449864422373,
|
|
"loss": 4.7511,
|
|
"mean_token_accuracy": 0.2279402047395706,
|
|
"num_tokens": 50108841.0,
|
|
"step": 27230
|
|
},
|
|
{
|
|
"entropy": 5.3888218879699705,
|
|
"epoch": 2.2748914132976945,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004479259417784201,
|
|
"loss": 4.7478,
|
|
"mean_token_accuracy": 0.2242590680718422,
|
|
"num_tokens": 50117755.0,
|
|
"step": 27235
|
|
},
|
|
{
|
|
"entropy": 5.356860971450805,
|
|
"epoch": 2.2753090544604078,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00044790689408732623,
|
|
"loss": 4.7031,
|
|
"mean_token_accuracy": 0.2397659182548523,
|
|
"num_tokens": 50127164.0,
|
|
"step": 27240
|
|
},
|
|
{
|
|
"entropy": 5.349197244644165,
|
|
"epoch": 2.2757266956231206,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00044788784336928896,
|
|
"loss": 4.7309,
|
|
"mean_token_accuracy": 0.23409149646759034,
|
|
"num_tokens": 50136537.0,
|
|
"step": 27245
|
|
},
|
|
{
|
|
"entropy": 5.442620468139649,
|
|
"epoch": 2.2761443367858334,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004478687896246419,
|
|
"loss": 4.7625,
|
|
"mean_token_accuracy": 0.21654410660266876,
|
|
"num_tokens": 50146037.0,
|
|
"step": 27250
|
|
},
|
|
{
|
|
"entropy": 5.429419803619385,
|
|
"epoch": 2.2765619779485466,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00044784973285371863,
|
|
"loss": 4.7858,
|
|
"mean_token_accuracy": 0.22028665989637375,
|
|
"num_tokens": 50154607.0,
|
|
"step": 27255
|
|
},
|
|
{
|
|
"entropy": 5.415594291687012,
|
|
"epoch": 2.2769796191112595,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00044783067305685274,
|
|
"loss": 4.7443,
|
|
"mean_token_accuracy": 0.23043568134307862,
|
|
"num_tokens": 50163801.0,
|
|
"step": 27260
|
|
},
|
|
{
|
|
"entropy": 5.437047481536865,
|
|
"epoch": 2.2773972602739727,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004478116102343778,
|
|
"loss": 4.8468,
|
|
"mean_token_accuracy": 0.21488455086946487,
|
|
"num_tokens": 50174237.0,
|
|
"step": 27265
|
|
},
|
|
{
|
|
"entropy": 5.423288583755493,
|
|
"epoch": 2.2778149014366855,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004477925443866277,
|
|
"loss": 4.7603,
|
|
"mean_token_accuracy": 0.22679786384105682,
|
|
"num_tokens": 50184354.0,
|
|
"step": 27270
|
|
},
|
|
{
|
|
"entropy": 5.432046937942505,
|
|
"epoch": 2.278232542599399,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000447773475513936,
|
|
"loss": 4.8072,
|
|
"mean_token_accuracy": 0.22247196286916732,
|
|
"num_tokens": 50194286.0,
|
|
"step": 27275
|
|
},
|
|
{
|
|
"entropy": 5.327525854110718,
|
|
"epoch": 2.2786501837621116,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00044775440361663677,
|
|
"loss": 4.7384,
|
|
"mean_token_accuracy": 0.23075903654098512,
|
|
"num_tokens": 50203631.0,
|
|
"step": 27280
|
|
},
|
|
{
|
|
"entropy": 5.394550323486328,
|
|
"epoch": 2.2790678249248244,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00044773532869506373,
|
|
"loss": 4.8071,
|
|
"mean_token_accuracy": 0.22057446092367172,
|
|
"num_tokens": 50213509.0,
|
|
"step": 27285
|
|
},
|
|
{
|
|
"entropy": 5.467093992233276,
|
|
"epoch": 2.2794854660875377,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004477162507495508,
|
|
"loss": 4.8123,
|
|
"mean_token_accuracy": 0.22677124738693238,
|
|
"num_tokens": 50222747.0,
|
|
"step": 27290
|
|
},
|
|
{
|
|
"entropy": 5.409633779525757,
|
|
"epoch": 2.2799031072502505,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000447697169780432,
|
|
"loss": 4.7747,
|
|
"mean_token_accuracy": 0.23173605352640153,
|
|
"num_tokens": 50232711.0,
|
|
"step": 27295
|
|
},
|
|
{
|
|
"entropy": 5.268697452545166,
|
|
"epoch": 2.2803207484129637,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00044767808578804135,
|
|
"loss": 4.6123,
|
|
"mean_token_accuracy": 0.24145575761795043,
|
|
"num_tokens": 50241253.0,
|
|
"step": 27300
|
|
},
|
|
{
|
|
"entropy": 5.263882160186768,
|
|
"epoch": 2.2807383895756765,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00044765899877271306,
|
|
"loss": 4.6277,
|
|
"mean_token_accuracy": 0.23561156541109085,
|
|
"num_tokens": 50249559.0,
|
|
"step": 27305
|
|
},
|
|
{
|
|
"entropy": 5.406136226654053,
|
|
"epoch": 2.28115603073839,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00044763990873478106,
|
|
"loss": 4.847,
|
|
"mean_token_accuracy": 0.21956128180027007,
|
|
"num_tokens": 50259442.0,
|
|
"step": 27310
|
|
},
|
|
{
|
|
"entropy": 5.455647039413452,
|
|
"epoch": 2.2815736719011026,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00044762081567457966,
|
|
"loss": 4.8212,
|
|
"mean_token_accuracy": 0.2233704909682274,
|
|
"num_tokens": 50268468.0,
|
|
"step": 27315
|
|
},
|
|
{
|
|
"entropy": 5.357231378555298,
|
|
"epoch": 2.2819913130638154,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004476017195924432,
|
|
"loss": 4.6929,
|
|
"mean_token_accuracy": 0.22994651645421982,
|
|
"num_tokens": 50278342.0,
|
|
"step": 27320
|
|
},
|
|
{
|
|
"entropy": 5.316498041152954,
|
|
"epoch": 2.2824089542265287,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00044758262048870574,
|
|
"loss": 4.7034,
|
|
"mean_token_accuracy": 0.2316305696964264,
|
|
"num_tokens": 50287364.0,
|
|
"step": 27325
|
|
},
|
|
{
|
|
"entropy": 5.411946773529053,
|
|
"epoch": 2.2828265953892415,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00044756351836370184,
|
|
"loss": 4.8451,
|
|
"mean_token_accuracy": 0.21879030466079713,
|
|
"num_tokens": 50297306.0,
|
|
"step": 27330
|
|
},
|
|
{
|
|
"entropy": 5.467835092544556,
|
|
"epoch": 2.2832442365519547,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004475444132177659,
|
|
"loss": 4.7436,
|
|
"mean_token_accuracy": 0.2237848773598671,
|
|
"num_tokens": 50306774.0,
|
|
"step": 27335
|
|
},
|
|
{
|
|
"entropy": 5.453675413131714,
|
|
"epoch": 2.2836618777146676,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004475253050512322,
|
|
"loss": 4.7569,
|
|
"mean_token_accuracy": 0.22937989979982376,
|
|
"num_tokens": 50316492.0,
|
|
"step": 27340
|
|
},
|
|
{
|
|
"entropy": 5.3279797554016115,
|
|
"epoch": 2.2840795188773804,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00044750619386443543,
|
|
"loss": 4.7081,
|
|
"mean_token_accuracy": 0.22985824048519135,
|
|
"num_tokens": 50324950.0,
|
|
"step": 27345
|
|
},
|
|
{
|
|
"entropy": 5.46160397529602,
|
|
"epoch": 2.2844971600400936,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00044748707965771005,
|
|
"loss": 4.8826,
|
|
"mean_token_accuracy": 0.20909947007894517,
|
|
"num_tokens": 50334383.0,
|
|
"step": 27350
|
|
},
|
|
{
|
|
"entropy": 5.3779829978942875,
|
|
"epoch": 2.2849148012028064,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00044746796243139077,
|
|
"loss": 4.7888,
|
|
"mean_token_accuracy": 0.2185230791568756,
|
|
"num_tokens": 50343929.0,
|
|
"step": 27355
|
|
},
|
|
{
|
|
"entropy": 5.402411890029907,
|
|
"epoch": 2.2853324423655197,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00044744884218581217,
|
|
"loss": 4.7658,
|
|
"mean_token_accuracy": 0.22469970136880874,
|
|
"num_tokens": 50352975.0,
|
|
"step": 27360
|
|
},
|
|
{
|
|
"entropy": 5.43127589225769,
|
|
"epoch": 2.2857500835282325,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000447429718921309,
|
|
"loss": 4.817,
|
|
"mean_token_accuracy": 0.2229987621307373,
|
|
"num_tokens": 50362800.0,
|
|
"step": 27365
|
|
},
|
|
{
|
|
"entropy": 5.395111417770385,
|
|
"epoch": 2.2861677246909453,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004474105926382161,
|
|
"loss": 4.7826,
|
|
"mean_token_accuracy": 0.22388288676738738,
|
|
"num_tokens": 50372496.0,
|
|
"step": 27370
|
|
},
|
|
{
|
|
"entropy": 5.337351083755493,
|
|
"epoch": 2.2865853658536586,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004473914633368683,
|
|
"loss": 4.7053,
|
|
"mean_token_accuracy": 0.2283079132437706,
|
|
"num_tokens": 50380634.0,
|
|
"step": 27375
|
|
},
|
|
{
|
|
"entropy": 5.358242464065552,
|
|
"epoch": 2.2870030070163714,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004473723310176003,
|
|
"loss": 4.6806,
|
|
"mean_token_accuracy": 0.2366890549659729,
|
|
"num_tokens": 50389318.0,
|
|
"step": 27380
|
|
},
|
|
{
|
|
"entropy": 5.348547077178955,
|
|
"epoch": 2.2874206481790846,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004473531956807471,
|
|
"loss": 4.7763,
|
|
"mean_token_accuracy": 0.2336047038435936,
|
|
"num_tokens": 50398507.0,
|
|
"step": 27385
|
|
},
|
|
{
|
|
"entropy": 5.313892269134522,
|
|
"epoch": 2.2878382893417974,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00044733405732664394,
|
|
"loss": 4.6529,
|
|
"mean_token_accuracy": 0.2348022699356079,
|
|
"num_tokens": 50406905.0,
|
|
"step": 27390
|
|
},
|
|
{
|
|
"entropy": 5.383128070831299,
|
|
"epoch": 2.2882559305045107,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004473149159556255,
|
|
"loss": 4.7155,
|
|
"mean_token_accuracy": 0.2328630119562149,
|
|
"num_tokens": 50415959.0,
|
|
"step": 27395
|
|
},
|
|
{
|
|
"entropy": 5.453711271286011,
|
|
"epoch": 2.2886735716672235,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00044729577156802714,
|
|
"loss": 4.8052,
|
|
"mean_token_accuracy": 0.22590891718864442,
|
|
"num_tokens": 50425364.0,
|
|
"step": 27400
|
|
},
|
|
{
|
|
"entropy": 5.380469417572021,
|
|
"epoch": 2.2890912128299363,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004472766241641839,
|
|
"loss": 4.7869,
|
|
"mean_token_accuracy": 0.2292091190814972,
|
|
"num_tokens": 50434349.0,
|
|
"step": 27405
|
|
},
|
|
{
|
|
"entropy": 5.328064584732056,
|
|
"epoch": 2.2895088539926496,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.000447257473744431,
|
|
"loss": 4.6736,
|
|
"mean_token_accuracy": 0.23206776529550552,
|
|
"num_tokens": 50442964.0,
|
|
"step": 27410
|
|
},
|
|
{
|
|
"entropy": 5.374681854248047,
|
|
"epoch": 2.2899264951553624,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004472383203091036,
|
|
"loss": 4.802,
|
|
"mean_token_accuracy": 0.2266720488667488,
|
|
"num_tokens": 50451625.0,
|
|
"step": 27415
|
|
},
|
|
{
|
|
"entropy": 5.321031475067139,
|
|
"epoch": 2.2903441363180757,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004472191638585371,
|
|
"loss": 4.642,
|
|
"mean_token_accuracy": 0.23237148970365523,
|
|
"num_tokens": 50460062.0,
|
|
"step": 27420
|
|
},
|
|
{
|
|
"entropy": 5.3457084655761715,
|
|
"epoch": 2.2907617774807885,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00044720000439306694,
|
|
"loss": 4.6534,
|
|
"mean_token_accuracy": 0.23861341327428817,
|
|
"num_tokens": 50468207.0,
|
|
"step": 27425
|
|
},
|
|
{
|
|
"entropy": 5.419823265075683,
|
|
"epoch": 2.2911794186435017,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00044718084191302826,
|
|
"loss": 4.7617,
|
|
"mean_token_accuracy": 0.22110513150691985,
|
|
"num_tokens": 50478151.0,
|
|
"step": 27430
|
|
},
|
|
{
|
|
"entropy": 5.409604930877686,
|
|
"epoch": 2.2915970598062145,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00044716167641875685,
|
|
"loss": 4.8012,
|
|
"mean_token_accuracy": 0.2310614511370659,
|
|
"num_tokens": 50487180.0,
|
|
"step": 27435
|
|
},
|
|
{
|
|
"entropy": 5.292560958862305,
|
|
"epoch": 2.2920147009689273,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000447142507910588,
|
|
"loss": 4.7042,
|
|
"mean_token_accuracy": 0.23301960080862044,
|
|
"num_tokens": 50495661.0,
|
|
"step": 27440
|
|
},
|
|
{
|
|
"entropy": 5.409822130203247,
|
|
"epoch": 2.2924323421316406,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00044712333638885726,
|
|
"loss": 4.8037,
|
|
"mean_token_accuracy": 0.22267533838748932,
|
|
"num_tokens": 50505854.0,
|
|
"step": 27445
|
|
},
|
|
{
|
|
"entropy": 5.43970365524292,
|
|
"epoch": 2.2928499832943534,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00044710416185390043,
|
|
"loss": 4.7513,
|
|
"mean_token_accuracy": 0.22464215606451035,
|
|
"num_tokens": 50514788.0,
|
|
"step": 27450
|
|
},
|
|
{
|
|
"entropy": 5.319202852249146,
|
|
"epoch": 2.2932676244570667,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004470849843060531,
|
|
"loss": 4.6795,
|
|
"mean_token_accuracy": 0.23251340985298158,
|
|
"num_tokens": 50523537.0,
|
|
"step": 27455
|
|
},
|
|
{
|
|
"entropy": 5.401678848266601,
|
|
"epoch": 2.2936852656197795,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00044706580374565094,
|
|
"loss": 4.7509,
|
|
"mean_token_accuracy": 0.22273406833410264,
|
|
"num_tokens": 50533165.0,
|
|
"step": 27460
|
|
},
|
|
{
|
|
"entropy": 5.407173013687133,
|
|
"epoch": 2.2941029067824923,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004470466201730298,
|
|
"loss": 4.7437,
|
|
"mean_token_accuracy": 0.23188279569149017,
|
|
"num_tokens": 50541531.0,
|
|
"step": 27465
|
|
},
|
|
{
|
|
"entropy": 5.368304872512818,
|
|
"epoch": 2.2945205479452055,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004470274335885254,
|
|
"loss": 4.6587,
|
|
"mean_token_accuracy": 0.23483158499002457,
|
|
"num_tokens": 50551097.0,
|
|
"step": 27470
|
|
},
|
|
{
|
|
"entropy": 5.3745481967926025,
|
|
"epoch": 2.2949381891079184,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004470082439924737,
|
|
"loss": 4.7503,
|
|
"mean_token_accuracy": 0.22985183000564574,
|
|
"num_tokens": 50559796.0,
|
|
"step": 27475
|
|
},
|
|
{
|
|
"entropy": 5.4112327098846436,
|
|
"epoch": 2.2953558302706316,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004469890513852107,
|
|
"loss": 4.8436,
|
|
"mean_token_accuracy": 0.22173368334770202,
|
|
"num_tokens": 50568671.0,
|
|
"step": 27480
|
|
},
|
|
{
|
|
"entropy": 5.453762245178223,
|
|
"epoch": 2.2957734714333444,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004469698557670724,
|
|
"loss": 4.7405,
|
|
"mean_token_accuracy": 0.22741775810718537,
|
|
"num_tokens": 50577396.0,
|
|
"step": 27485
|
|
},
|
|
{
|
|
"entropy": 5.452701997756958,
|
|
"epoch": 2.2961911125960572,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004469506571383947,
|
|
"loss": 4.765,
|
|
"mean_token_accuracy": 0.22818639427423476,
|
|
"num_tokens": 50587018.0,
|
|
"step": 27490
|
|
},
|
|
{
|
|
"entropy": 5.424410676956176,
|
|
"epoch": 2.2966087537587705,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004469314554995137,
|
|
"loss": 4.7998,
|
|
"mean_token_accuracy": 0.22210677564144135,
|
|
"num_tokens": 50596026.0,
|
|
"step": 27495
|
|
},
|
|
{
|
|
"entropy": 5.304930305480957,
|
|
"epoch": 2.2970263949214833,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00044691225085076577,
|
|
"loss": 4.6775,
|
|
"mean_token_accuracy": 0.2344232827425003,
|
|
"num_tokens": 50604973.0,
|
|
"step": 27500
|
|
},
|
|
{
|
|
"entropy": 5.40302882194519,
|
|
"epoch": 2.2974440360841966,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004468930431924869,
|
|
"loss": 4.8089,
|
|
"mean_token_accuracy": 0.2212339758872986,
|
|
"num_tokens": 50613686.0,
|
|
"step": 27505
|
|
},
|
|
{
|
|
"entropy": 5.444236803054809,
|
|
"epoch": 2.2978616772469094,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00044687383252501337,
|
|
"loss": 4.8206,
|
|
"mean_token_accuracy": 0.2232385739684105,
|
|
"num_tokens": 50622840.0,
|
|
"step": 27510
|
|
},
|
|
{
|
|
"entropy": 5.304307508468628,
|
|
"epoch": 2.2982793184096226,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004468546188486815,
|
|
"loss": 4.7286,
|
|
"mean_token_accuracy": 0.23414536863565444,
|
|
"num_tokens": 50631818.0,
|
|
"step": 27515
|
|
},
|
|
{
|
|
"entropy": 5.3706653118133545,
|
|
"epoch": 2.2986969595723354,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00044683540216382766,
|
|
"loss": 4.764,
|
|
"mean_token_accuracy": 0.22770433574914933,
|
|
"num_tokens": 50640472.0,
|
|
"step": 27520
|
|
},
|
|
{
|
|
"entropy": 5.345012855529785,
|
|
"epoch": 2.2991146007350483,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004468161824707883,
|
|
"loss": 4.6912,
|
|
"mean_token_accuracy": 0.23153943717479705,
|
|
"num_tokens": 50649513.0,
|
|
"step": 27525
|
|
},
|
|
{
|
|
"entropy": 5.345238494873047,
|
|
"epoch": 2.2995322418977615,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00044679695976989985,
|
|
"loss": 4.7683,
|
|
"mean_token_accuracy": 0.2274801716208458,
|
|
"num_tokens": 50659028.0,
|
|
"step": 27530
|
|
},
|
|
{
|
|
"entropy": 5.449474334716797,
|
|
"epoch": 2.2999498830604743,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00044677773406149885,
|
|
"loss": 4.7657,
|
|
"mean_token_accuracy": 0.22202775478363038,
|
|
"num_tokens": 50668888.0,
|
|
"step": 27535
|
|
},
|
|
{
|
|
"entropy": 5.399760675430298,
|
|
"epoch": 2.3003675242231876,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00044675850534592185,
|
|
"loss": 4.7583,
|
|
"mean_token_accuracy": 0.23191530704498292,
|
|
"num_tokens": 50678094.0,
|
|
"step": 27540
|
|
},
|
|
{
|
|
"entropy": 5.290048503875733,
|
|
"epoch": 2.3007851653859004,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00044673927362350545,
|
|
"loss": 4.6505,
|
|
"mean_token_accuracy": 0.24428964108228685,
|
|
"num_tokens": 50686692.0,
|
|
"step": 27545
|
|
},
|
|
{
|
|
"entropy": 5.444054794311524,
|
|
"epoch": 2.3012028065486136,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00044672003889458634,
|
|
"loss": 4.8354,
|
|
"mean_token_accuracy": 0.22200643122196198,
|
|
"num_tokens": 50695579.0,
|
|
"step": 27550
|
|
},
|
|
{
|
|
"entropy": 5.393219232559204,
|
|
"epoch": 2.3016204477113265,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00044670080115950117,
|
|
"loss": 4.7508,
|
|
"mean_token_accuracy": 0.2260976642370224,
|
|
"num_tokens": 50704205.0,
|
|
"step": 27555
|
|
},
|
|
{
|
|
"entropy": 5.449225378036499,
|
|
"epoch": 2.3020380888740393,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00044668156041858696,
|
|
"loss": 4.7834,
|
|
"mean_token_accuracy": 0.22549821734428405,
|
|
"num_tokens": 50713926.0,
|
|
"step": 27560
|
|
},
|
|
{
|
|
"entropy": 5.496738147735596,
|
|
"epoch": 2.3024557300367525,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00044666231667218025,
|
|
"loss": 4.8066,
|
|
"mean_token_accuracy": 0.2221788376569748,
|
|
"num_tokens": 50723732.0,
|
|
"step": 27565
|
|
},
|
|
{
|
|
"entropy": 5.330129337310791,
|
|
"epoch": 2.3028733711994653,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00044664306992061816,
|
|
"loss": 4.6758,
|
|
"mean_token_accuracy": 0.2309804916381836,
|
|
"num_tokens": 50732572.0,
|
|
"step": 27570
|
|
},
|
|
{
|
|
"entropy": 5.422257375717163,
|
|
"epoch": 2.3032910123621786,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00044662382016423747,
|
|
"loss": 4.8169,
|
|
"mean_token_accuracy": 0.22191170006990432,
|
|
"num_tokens": 50741145.0,
|
|
"step": 27575
|
|
},
|
|
{
|
|
"entropy": 5.4452790260314945,
|
|
"epoch": 2.3037086535248914,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004466045674033752,
|
|
"loss": 4.8022,
|
|
"mean_token_accuracy": 0.2229578286409378,
|
|
"num_tokens": 50749966.0,
|
|
"step": 27580
|
|
},
|
|
{
|
|
"entropy": 5.38121976852417,
|
|
"epoch": 2.304126294687604,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004465853116383684,
|
|
"loss": 4.7761,
|
|
"mean_token_accuracy": 0.2279814898967743,
|
|
"num_tokens": 50759263.0,
|
|
"step": 27585
|
|
},
|
|
{
|
|
"entropy": 5.3116553783416744,
|
|
"epoch": 2.3045439358503175,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00044656605286955424,
|
|
"loss": 4.7029,
|
|
"mean_token_accuracy": 0.23093321472406386,
|
|
"num_tokens": 50768071.0,
|
|
"step": 27590
|
|
},
|
|
{
|
|
"entropy": 5.340391302108765,
|
|
"epoch": 2.3049615770130303,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004465467910972698,
|
|
"loss": 4.7361,
|
|
"mean_token_accuracy": 0.234880992770195,
|
|
"num_tokens": 50777658.0,
|
|
"step": 27595
|
|
},
|
|
{
|
|
"entropy": 5.436546516418457,
|
|
"epoch": 2.3053792181757435,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004465275263218523,
|
|
"loss": 4.8295,
|
|
"mean_token_accuracy": 0.2136344239115715,
|
|
"num_tokens": 50788438.0,
|
|
"step": 27600
|
|
},
|
|
{
|
|
"entropy": 5.391183280944825,
|
|
"epoch": 2.3057968593384564,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00044650825854363895,
|
|
"loss": 4.7448,
|
|
"mean_token_accuracy": 0.23263527303934098,
|
|
"num_tokens": 50797459.0,
|
|
"step": 27605
|
|
},
|
|
{
|
|
"entropy": 5.341243314743042,
|
|
"epoch": 2.306214500501169,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004464889877629671,
|
|
"loss": 4.642,
|
|
"mean_token_accuracy": 0.23839631974697112,
|
|
"num_tokens": 50806088.0,
|
|
"step": 27610
|
|
},
|
|
{
|
|
"entropy": 5.311007881164551,
|
|
"epoch": 2.3066321416638824,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004464697139801741,
|
|
"loss": 4.7175,
|
|
"mean_token_accuracy": 0.22496190071105956,
|
|
"num_tokens": 50815567.0,
|
|
"step": 27615
|
|
},
|
|
{
|
|
"entropy": 5.317251062393188,
|
|
"epoch": 2.3070497828265952,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00044645043719559736,
|
|
"loss": 4.7221,
|
|
"mean_token_accuracy": 0.23684382885694505,
|
|
"num_tokens": 50824519.0,
|
|
"step": 27620
|
|
},
|
|
{
|
|
"entropy": 5.424952030181885,
|
|
"epoch": 2.3074674239893085,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00044643115740957437,
|
|
"loss": 4.8251,
|
|
"mean_token_accuracy": 0.22784932255744933,
|
|
"num_tokens": 50834875.0,
|
|
"step": 27625
|
|
},
|
|
{
|
|
"entropy": 5.433204269409179,
|
|
"epoch": 2.3078850651520213,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004464118746224426,
|
|
"loss": 4.7498,
|
|
"mean_token_accuracy": 0.22908651381731032,
|
|
"num_tokens": 50843668.0,
|
|
"step": 27630
|
|
},
|
|
{
|
|
"entropy": 5.452876091003418,
|
|
"epoch": 2.3083027063147346,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004463925888345396,
|
|
"loss": 4.86,
|
|
"mean_token_accuracy": 0.21454392969608307,
|
|
"num_tokens": 50853291.0,
|
|
"step": 27635
|
|
},
|
|
{
|
|
"entropy": 5.385584211349487,
|
|
"epoch": 2.3087203474774474,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00044637330004620307,
|
|
"loss": 4.8145,
|
|
"mean_token_accuracy": 0.2170362114906311,
|
|
"num_tokens": 50863392.0,
|
|
"step": 27640
|
|
},
|
|
{
|
|
"entropy": 5.422999477386474,
|
|
"epoch": 2.3091379886401606,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00044635400825777065,
|
|
"loss": 4.7704,
|
|
"mean_token_accuracy": 0.22996582090854645,
|
|
"num_tokens": 50871857.0,
|
|
"step": 27645
|
|
},
|
|
{
|
|
"entropy": 5.3915159702301025,
|
|
"epoch": 2.3095556298028734,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00044633471346957996,
|
|
"loss": 4.7578,
|
|
"mean_token_accuracy": 0.22811916321516038,
|
|
"num_tokens": 50882171.0,
|
|
"step": 27650
|
|
},
|
|
{
|
|
"entropy": 5.2999725341796875,
|
|
"epoch": 2.3099732709655862,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00044631541568196896,
|
|
"loss": 4.5711,
|
|
"mean_token_accuracy": 0.24551779478788377,
|
|
"num_tokens": 50890925.0,
|
|
"step": 27655
|
|
},
|
|
{
|
|
"entropy": 5.380058717727661,
|
|
"epoch": 2.3103909121282995,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00044629611489527537,
|
|
"loss": 4.7464,
|
|
"mean_token_accuracy": 0.2342848613858223,
|
|
"num_tokens": 50900555.0,
|
|
"step": 27660
|
|
},
|
|
{
|
|
"entropy": 5.306967306137085,
|
|
"epoch": 2.3108085532910123,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004462768111098371,
|
|
"loss": 4.6344,
|
|
"mean_token_accuracy": 0.24037563651800156,
|
|
"num_tokens": 50908763.0,
|
|
"step": 27665
|
|
},
|
|
{
|
|
"entropy": 5.396490430831909,
|
|
"epoch": 2.3112261944537256,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00044625750432599213,
|
|
"loss": 4.6413,
|
|
"mean_token_accuracy": 0.23722822666168214,
|
|
"num_tokens": 50916906.0,
|
|
"step": 27670
|
|
},
|
|
{
|
|
"entropy": 5.427211761474609,
|
|
"epoch": 2.3116438356164384,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00044623819454407844,
|
|
"loss": 4.883,
|
|
"mean_token_accuracy": 0.210234235227108,
|
|
"num_tokens": 50926338.0,
|
|
"step": 27675
|
|
},
|
|
{
|
|
"entropy": 5.354715013504029,
|
|
"epoch": 2.312061476779151,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000446218881764434,
|
|
"loss": 4.7694,
|
|
"mean_token_accuracy": 0.22771754413843154,
|
|
"num_tokens": 50935392.0,
|
|
"step": 27680
|
|
},
|
|
{
|
|
"entropy": 5.401003742218018,
|
|
"epoch": 2.3124791179418644,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00044619956598739686,
|
|
"loss": 4.8129,
|
|
"mean_token_accuracy": 0.2173153653740883,
|
|
"num_tokens": 50945078.0,
|
|
"step": 27685
|
|
},
|
|
{
|
|
"entropy": 5.3925634860992435,
|
|
"epoch": 2.3128967591045773,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00044618024721330523,
|
|
"loss": 4.7569,
|
|
"mean_token_accuracy": 0.22715354710817337,
|
|
"num_tokens": 50955091.0,
|
|
"step": 27690
|
|
},
|
|
{
|
|
"entropy": 5.382073450088501,
|
|
"epoch": 2.3133144002672905,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004461609254424974,
|
|
"loss": 4.8097,
|
|
"mean_token_accuracy": 0.22616259306669234,
|
|
"num_tokens": 50964730.0,
|
|
"step": 27695
|
|
},
|
|
{
|
|
"entropy": 5.348524141311645,
|
|
"epoch": 2.3137320414300033,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00044614160067531157,
|
|
"loss": 4.7208,
|
|
"mean_token_accuracy": 0.23337779492139815,
|
|
"num_tokens": 50973666.0,
|
|
"step": 27700
|
|
},
|
|
{
|
|
"entropy": 5.432016086578369,
|
|
"epoch": 2.314149682592716,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000446122272912086,
|
|
"loss": 4.7963,
|
|
"mean_token_accuracy": 0.22348523437976836,
|
|
"num_tokens": 50983339.0,
|
|
"step": 27705
|
|
},
|
|
{
|
|
"entropy": 5.366238355636597,
|
|
"epoch": 2.3145673237554294,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000446102942153159,
|
|
"loss": 4.7396,
|
|
"mean_token_accuracy": 0.2339622974395752,
|
|
"num_tokens": 50993563.0,
|
|
"step": 27710
|
|
},
|
|
{
|
|
"entropy": 5.420231580734253,
|
|
"epoch": 2.314984964918142,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004460836083988691,
|
|
"loss": 4.7886,
|
|
"mean_token_accuracy": 0.22520800828933715,
|
|
"num_tokens": 51002179.0,
|
|
"step": 27715
|
|
},
|
|
{
|
|
"entropy": 5.341873073577881,
|
|
"epoch": 2.3154026060808555,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00044606427164955466,
|
|
"loss": 4.6761,
|
|
"mean_token_accuracy": 0.23238925486803055,
|
|
"num_tokens": 51010770.0,
|
|
"step": 27720
|
|
},
|
|
{
|
|
"entropy": 5.318904876708984,
|
|
"epoch": 2.3158202472435683,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004460449319055543,
|
|
"loss": 4.7413,
|
|
"mean_token_accuracy": 0.23845135569572448,
|
|
"num_tokens": 51021224.0,
|
|
"step": 27725
|
|
},
|
|
{
|
|
"entropy": 5.360855388641357,
|
|
"epoch": 2.316237888406281,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004460255891672064,
|
|
"loss": 4.6935,
|
|
"mean_token_accuracy": 0.22837506532669066,
|
|
"num_tokens": 51030425.0,
|
|
"step": 27730
|
|
},
|
|
{
|
|
"entropy": 5.450617885589599,
|
|
"epoch": 2.3166555295689943,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00044600624343484985,
|
|
"loss": 4.831,
|
|
"mean_token_accuracy": 0.2263009339570999,
|
|
"num_tokens": 51040135.0,
|
|
"step": 27735
|
|
},
|
|
{
|
|
"entropy": 5.416865634918213,
|
|
"epoch": 2.317073170731707,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004459868947088231,
|
|
"loss": 4.8782,
|
|
"mean_token_accuracy": 0.21897173821926116,
|
|
"num_tokens": 51050696.0,
|
|
"step": 27740
|
|
},
|
|
{
|
|
"entropy": 5.416585636138916,
|
|
"epoch": 2.3174908118944204,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00044596754298946494,
|
|
"loss": 4.7356,
|
|
"mean_token_accuracy": 0.2260397732257843,
|
|
"num_tokens": 51060092.0,
|
|
"step": 27745
|
|
},
|
|
{
|
|
"entropy": 5.391076850891113,
|
|
"epoch": 2.3179084530571332,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00044594818827711416,
|
|
"loss": 4.6806,
|
|
"mean_token_accuracy": 0.2324299246072769,
|
|
"num_tokens": 51069139.0,
|
|
"step": 27750
|
|
},
|
|
{
|
|
"entropy": 5.308386611938476,
|
|
"epoch": 2.3183260942198465,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004459288305721095,
|
|
"loss": 4.6618,
|
|
"mean_token_accuracy": 0.23243300318717958,
|
|
"num_tokens": 51078262.0,
|
|
"step": 27755
|
|
},
|
|
{
|
|
"entropy": 5.328775691986084,
|
|
"epoch": 2.3187437353825593,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00044590946987479,
|
|
"loss": 4.7834,
|
|
"mean_token_accuracy": 0.22728101313114166,
|
|
"num_tokens": 51088679.0,
|
|
"step": 27760
|
|
},
|
|
{
|
|
"entropy": 5.322514963150025,
|
|
"epoch": 2.3191613765452725,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004458901061854944,
|
|
"loss": 4.6889,
|
|
"mean_token_accuracy": 0.23391490131616594,
|
|
"num_tokens": 51097673.0,
|
|
"step": 27765
|
|
},
|
|
{
|
|
"entropy": 5.391067743301392,
|
|
"epoch": 2.3195790177079854,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00044587073950456193,
|
|
"loss": 4.7485,
|
|
"mean_token_accuracy": 0.2331336423754692,
|
|
"num_tokens": 51107546.0,
|
|
"step": 27770
|
|
},
|
|
{
|
|
"entropy": 5.357138586044312,
|
|
"epoch": 2.319996658870698,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004458513698323314,
|
|
"loss": 4.8038,
|
|
"mean_token_accuracy": 0.2229551300406456,
|
|
"num_tokens": 51116860.0,
|
|
"step": 27775
|
|
},
|
|
{
|
|
"entropy": 5.403187894821167,
|
|
"epoch": 2.3204143000334114,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000445831997169142,
|
|
"loss": 4.7737,
|
|
"mean_token_accuracy": 0.23670299351215363,
|
|
"num_tokens": 51125815.0,
|
|
"step": 27780
|
|
},
|
|
{
|
|
"entropy": 5.427082252502442,
|
|
"epoch": 2.3208319411961242,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004458126215153329,
|
|
"loss": 4.7972,
|
|
"mean_token_accuracy": 0.220036780834198,
|
|
"num_tokens": 51134561.0,
|
|
"step": 27785
|
|
},
|
|
{
|
|
"entropy": 5.3799632549285885,
|
|
"epoch": 2.3212495823588375,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00044579324287124324,
|
|
"loss": 4.7472,
|
|
"mean_token_accuracy": 0.2246566191315651,
|
|
"num_tokens": 51143506.0,
|
|
"step": 27790
|
|
},
|
|
{
|
|
"entropy": 5.436016654968261,
|
|
"epoch": 2.3216672235215503,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00044577386123721225,
|
|
"loss": 4.7763,
|
|
"mean_token_accuracy": 0.2232106700539589,
|
|
"num_tokens": 51152632.0,
|
|
"step": 27795
|
|
},
|
|
{
|
|
"entropy": 5.414686298370361,
|
|
"epoch": 2.322084864684263,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00044575447661357925,
|
|
"loss": 4.8635,
|
|
"mean_token_accuracy": 0.2174249693751335,
|
|
"num_tokens": 51162947.0,
|
|
"step": 27800
|
|
},
|
|
{
|
|
"entropy": 5.354566192626953,
|
|
"epoch": 2.3225025058469764,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00044573508900068367,
|
|
"loss": 4.7542,
|
|
"mean_token_accuracy": 0.22793612033128738,
|
|
"num_tokens": 51172030.0,
|
|
"step": 27805
|
|
},
|
|
{
|
|
"entropy": 5.332373046875,
|
|
"epoch": 2.322920147009689,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004457156983988648,
|
|
"loss": 4.6881,
|
|
"mean_token_accuracy": 0.23094082176685332,
|
|
"num_tokens": 51181009.0,
|
|
"step": 27810
|
|
},
|
|
{
|
|
"entropy": 5.433878993988037,
|
|
"epoch": 2.3233377881724024,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00044569630480846214,
|
|
"loss": 4.6917,
|
|
"mean_token_accuracy": 0.23657589703798293,
|
|
"num_tokens": 51189731.0,
|
|
"step": 27815
|
|
},
|
|
{
|
|
"entropy": 5.398463344573974,
|
|
"epoch": 2.3237554293351153,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004456769082298152,
|
|
"loss": 4.7407,
|
|
"mean_token_accuracy": 0.2244195446372032,
|
|
"num_tokens": 51199726.0,
|
|
"step": 27820
|
|
},
|
|
{
|
|
"entropy": 5.3338228225708,
|
|
"epoch": 2.324173070497828,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00044565750866326355,
|
|
"loss": 4.7057,
|
|
"mean_token_accuracy": 0.23165858685970306,
|
|
"num_tokens": 51209068.0,
|
|
"step": 27825
|
|
},
|
|
{
|
|
"entropy": 5.3907793998718265,
|
|
"epoch": 2.3245907116605413,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004456381061091467,
|
|
"loss": 4.6727,
|
|
"mean_token_accuracy": 0.23365464359521865,
|
|
"num_tokens": 51217766.0,
|
|
"step": 27830
|
|
},
|
|
{
|
|
"entropy": 5.418027687072754,
|
|
"epoch": 2.325008352823254,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00044561870056780445,
|
|
"loss": 4.7608,
|
|
"mean_token_accuracy": 0.22868062406778336,
|
|
"num_tokens": 51227134.0,
|
|
"step": 27835
|
|
},
|
|
{
|
|
"entropy": 5.413679027557373,
|
|
"epoch": 2.3254259939859674,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004455992920395766,
|
|
"loss": 4.7455,
|
|
"mean_token_accuracy": 0.22797721475362778,
|
|
"num_tokens": 51236059.0,
|
|
"step": 27840
|
|
},
|
|
{
|
|
"entropy": 5.471476650238037,
|
|
"epoch": 2.32584363514868,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00044557988052480263,
|
|
"loss": 4.8768,
|
|
"mean_token_accuracy": 0.21873923540115356,
|
|
"num_tokens": 51245730.0,
|
|
"step": 27845
|
|
},
|
|
{
|
|
"entropy": 5.376851224899292,
|
|
"epoch": 2.326261276311393,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00044556046602382257,
|
|
"loss": 4.6924,
|
|
"mean_token_accuracy": 0.22907768487930297,
|
|
"num_tokens": 51254633.0,
|
|
"step": 27850
|
|
},
|
|
{
|
|
"entropy": 5.369477367401123,
|
|
"epoch": 2.3266789174741063,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004455410485369763,
|
|
"loss": 4.8104,
|
|
"mean_token_accuracy": 0.21963137835264207,
|
|
"num_tokens": 51264264.0,
|
|
"step": 27855
|
|
},
|
|
{
|
|
"entropy": 5.35605411529541,
|
|
"epoch": 2.327096558636819,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004455216280646037,
|
|
"loss": 4.7938,
|
|
"mean_token_accuracy": 0.22018154263496398,
|
|
"num_tokens": 51273376.0,
|
|
"step": 27860
|
|
},
|
|
{
|
|
"entropy": 5.3130354404449465,
|
|
"epoch": 2.3275141997995323,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004455022046070446,
|
|
"loss": 4.6875,
|
|
"mean_token_accuracy": 0.23232612311840056,
|
|
"num_tokens": 51282623.0,
|
|
"step": 27865
|
|
},
|
|
{
|
|
"entropy": 5.353995084762573,
|
|
"epoch": 2.327931840962245,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00044548277816463925,
|
|
"loss": 4.7382,
|
|
"mean_token_accuracy": 0.23303287327289582,
|
|
"num_tokens": 51291543.0,
|
|
"step": 27870
|
|
},
|
|
{
|
|
"entropy": 5.410568714141846,
|
|
"epoch": 2.3283494821249584,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00044546334873772777,
|
|
"loss": 4.7518,
|
|
"mean_token_accuracy": 0.22918189615011214,
|
|
"num_tokens": 51300455.0,
|
|
"step": 27875
|
|
},
|
|
{
|
|
"entropy": 5.319422721862793,
|
|
"epoch": 2.328767123287671,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00044544391632665004,
|
|
"loss": 4.6002,
|
|
"mean_token_accuracy": 0.2328394114971161,
|
|
"num_tokens": 51308871.0,
|
|
"step": 27880
|
|
},
|
|
{
|
|
"entropy": 5.305160331726074,
|
|
"epoch": 2.3291847644503845,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004454244809317465,
|
|
"loss": 4.6454,
|
|
"mean_token_accuracy": 0.2307150647044182,
|
|
"num_tokens": 51318132.0,
|
|
"step": 27885
|
|
},
|
|
{
|
|
"entropy": 5.419887208938599,
|
|
"epoch": 2.3296024056130973,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00044540504255335717,
|
|
"loss": 4.7479,
|
|
"mean_token_accuracy": 0.22432229667901993,
|
|
"num_tokens": 51326573.0,
|
|
"step": 27890
|
|
},
|
|
{
|
|
"entropy": 5.405976152420044,
|
|
"epoch": 2.33002004677581,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004453856011918225,
|
|
"loss": 4.7151,
|
|
"mean_token_accuracy": 0.2289353772997856,
|
|
"num_tokens": 51336139.0,
|
|
"step": 27895
|
|
},
|
|
{
|
|
"entropy": 5.351135396957398,
|
|
"epoch": 2.3304376879385234,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00044536615684748286,
|
|
"loss": 4.7611,
|
|
"mean_token_accuracy": 0.22516029924154282,
|
|
"num_tokens": 51345163.0,
|
|
"step": 27900
|
|
},
|
|
{
|
|
"entropy": 5.3513236999511715,
|
|
"epoch": 2.330855329101236,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004453467095206785,
|
|
"loss": 4.7386,
|
|
"mean_token_accuracy": 0.23528739511966706,
|
|
"num_tokens": 51354305.0,
|
|
"step": 27905
|
|
},
|
|
{
|
|
"entropy": 5.332611560821533,
|
|
"epoch": 2.3312729702639494,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004453272592117499,
|
|
"loss": 4.6534,
|
|
"mean_token_accuracy": 0.23502030074596406,
|
|
"num_tokens": 51362732.0,
|
|
"step": 27910
|
|
},
|
|
{
|
|
"entropy": 5.385463571548462,
|
|
"epoch": 2.3316906114266622,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004453078059210377,
|
|
"loss": 4.77,
|
|
"mean_token_accuracy": 0.23054973185062408,
|
|
"num_tokens": 51372802.0,
|
|
"step": 27915
|
|
},
|
|
{
|
|
"entropy": 5.302448463439942,
|
|
"epoch": 2.332108252589375,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00044528834964888234,
|
|
"loss": 4.6716,
|
|
"mean_token_accuracy": 0.231083944439888,
|
|
"num_tokens": 51382618.0,
|
|
"step": 27920
|
|
},
|
|
{
|
|
"entropy": 5.328626680374145,
|
|
"epoch": 2.3325258937520883,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00044526889039562444,
|
|
"loss": 4.7424,
|
|
"mean_token_accuracy": 0.23325407803058623,
|
|
"num_tokens": 51392089.0,
|
|
"step": 27925
|
|
},
|
|
{
|
|
"entropy": 5.365963792800903,
|
|
"epoch": 2.332943534914801,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00044524942816160463,
|
|
"loss": 4.7393,
|
|
"mean_token_accuracy": 0.22682122737169266,
|
|
"num_tokens": 51401323.0,
|
|
"step": 27930
|
|
},
|
|
{
|
|
"entropy": 5.383187341690063,
|
|
"epoch": 2.3333611760775144,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00044522996294716374,
|
|
"loss": 4.7721,
|
|
"mean_token_accuracy": 0.23264785408973693,
|
|
"num_tokens": 51410079.0,
|
|
"step": 27935
|
|
},
|
|
{
|
|
"entropy": 5.345304155349732,
|
|
"epoch": 2.333778817240227,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00044521049475264237,
|
|
"loss": 4.7039,
|
|
"mean_token_accuracy": 0.2252722606062889,
|
|
"num_tokens": 51418638.0,
|
|
"step": 27940
|
|
},
|
|
{
|
|
"entropy": 5.446056652069092,
|
|
"epoch": 2.33419645840294,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004451910235783814,
|
|
"loss": 4.9138,
|
|
"mean_token_accuracy": 0.21293172389268875,
|
|
"num_tokens": 51428766.0,
|
|
"step": 27945
|
|
},
|
|
{
|
|
"entropy": 5.419564294815063,
|
|
"epoch": 2.3346140995656532,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00044517154942472166,
|
|
"loss": 4.8134,
|
|
"mean_token_accuracy": 0.2215184822678566,
|
|
"num_tokens": 51437828.0,
|
|
"step": 27950
|
|
},
|
|
{
|
|
"entropy": 5.429622936248779,
|
|
"epoch": 2.335031740728366,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004451520722920042,
|
|
"loss": 4.8011,
|
|
"mean_token_accuracy": 0.22709558755159379,
|
|
"num_tokens": 51448070.0,
|
|
"step": 27955
|
|
},
|
|
{
|
|
"entropy": 5.366362524032593,
|
|
"epoch": 2.3354493818910793,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004451325921805698,
|
|
"loss": 4.6708,
|
|
"mean_token_accuracy": 0.23630050867795943,
|
|
"num_tokens": 51457990.0,
|
|
"step": 27960
|
|
},
|
|
{
|
|
"entropy": 5.361135673522949,
|
|
"epoch": 2.335867023053792,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004451131090907597,
|
|
"loss": 4.7494,
|
|
"mean_token_accuracy": 0.2272970348596573,
|
|
"num_tokens": 51466323.0,
|
|
"step": 27965
|
|
},
|
|
{
|
|
"entropy": 5.366661500930786,
|
|
"epoch": 2.336284664216505,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004450936230229148,
|
|
"loss": 4.7591,
|
|
"mean_token_accuracy": 0.22174677848815919,
|
|
"num_tokens": 51476958.0,
|
|
"step": 27970
|
|
},
|
|
{
|
|
"entropy": 5.351574420928955,
|
|
"epoch": 2.336702305379218,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004450741339773763,
|
|
"loss": 4.7607,
|
|
"mean_token_accuracy": 0.22917828112840652,
|
|
"num_tokens": 51486843.0,
|
|
"step": 27975
|
|
},
|
|
{
|
|
"entropy": 5.36074275970459,
|
|
"epoch": 2.337119946541931,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00044505464195448535,
|
|
"loss": 4.6928,
|
|
"mean_token_accuracy": 0.228116175532341,
|
|
"num_tokens": 51496331.0,
|
|
"step": 27980
|
|
},
|
|
{
|
|
"entropy": 5.417759895324707,
|
|
"epoch": 2.3375375877046443,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00044503514695458325,
|
|
"loss": 4.8239,
|
|
"mean_token_accuracy": 0.22479833364486695,
|
|
"num_tokens": 51505693.0,
|
|
"step": 27985
|
|
},
|
|
{
|
|
"entropy": 5.458752918243408,
|
|
"epoch": 2.337955228867357,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004450156489780112,
|
|
"loss": 4.7572,
|
|
"mean_token_accuracy": 0.2281299650669098,
|
|
"num_tokens": 51514753.0,
|
|
"step": 27990
|
|
},
|
|
{
|
|
"entropy": 5.432691383361816,
|
|
"epoch": 2.3383728700300703,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004449961480251106,
|
|
"loss": 4.762,
|
|
"mean_token_accuracy": 0.2213428407907486,
|
|
"num_tokens": 51524082.0,
|
|
"step": 27995
|
|
},
|
|
{
|
|
"entropy": 5.327742099761963,
|
|
"epoch": 2.338790511192783,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004449766440962227,
|
|
"loss": 4.7201,
|
|
"mean_token_accuracy": 0.22736001312732695,
|
|
"num_tokens": 51533437.0,
|
|
"step": 28000
|
|
},
|
|
{
|
|
"entropy": 5.333599042892456,
|
|
"epoch": 2.3392081523554964,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004449571371916891,
|
|
"loss": 4.6527,
|
|
"mean_token_accuracy": 0.23233525604009628,
|
|
"num_tokens": 51542612.0,
|
|
"step": 28005
|
|
},
|
|
{
|
|
"entropy": 5.360235118865967,
|
|
"epoch": 2.339625793518209,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004449376273118513,
|
|
"loss": 4.6586,
|
|
"mean_token_accuracy": 0.23748538196086882,
|
|
"num_tokens": 51551292.0,
|
|
"step": 28010
|
|
},
|
|
{
|
|
"entropy": 5.397032642364502,
|
|
"epoch": 2.340043434680922,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004449181144570507,
|
|
"loss": 4.7886,
|
|
"mean_token_accuracy": 0.23188962787389755,
|
|
"num_tokens": 51560203.0,
|
|
"step": 28015
|
|
},
|
|
{
|
|
"entropy": 5.413776588439942,
|
|
"epoch": 2.3404610758436353,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000444898598627629,
|
|
"loss": 4.7891,
|
|
"mean_token_accuracy": 0.2250212624669075,
|
|
"num_tokens": 51569716.0,
|
|
"step": 28020
|
|
},
|
|
{
|
|
"entropy": 5.4101756572723385,
|
|
"epoch": 2.340878717006348,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004448790798239278,
|
|
"loss": 4.8218,
|
|
"mean_token_accuracy": 0.21976481676101683,
|
|
"num_tokens": 51578409.0,
|
|
"step": 28025
|
|
},
|
|
{
|
|
"entropy": 5.4242949962615965,
|
|
"epoch": 2.3412963581690613,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00044485955804628884,
|
|
"loss": 4.8869,
|
|
"mean_token_accuracy": 0.22541401535272598,
|
|
"num_tokens": 51587846.0,
|
|
"step": 28030
|
|
},
|
|
{
|
|
"entropy": 5.378638792037964,
|
|
"epoch": 2.341713999331774,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00044484003329505384,
|
|
"loss": 4.7615,
|
|
"mean_token_accuracy": 0.22588582336902618,
|
|
"num_tokens": 51596393.0,
|
|
"step": 28035
|
|
},
|
|
{
|
|
"entropy": 5.3867072582244875,
|
|
"epoch": 2.342131640494487,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004448205055705647,
|
|
"loss": 4.7714,
|
|
"mean_token_accuracy": 0.22752129137516022,
|
|
"num_tokens": 51605521.0,
|
|
"step": 28040
|
|
},
|
|
{
|
|
"entropy": 5.3977193355560305,
|
|
"epoch": 2.3425492816572,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004448009748731631,
|
|
"loss": 4.7925,
|
|
"mean_token_accuracy": 0.22484977841377257,
|
|
"num_tokens": 51614770.0,
|
|
"step": 28045
|
|
},
|
|
{
|
|
"entropy": 5.430860567092895,
|
|
"epoch": 2.342966922819913,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004447814412031911,
|
|
"loss": 4.8152,
|
|
"mean_token_accuracy": 0.2308375507593155,
|
|
"num_tokens": 51623249.0,
|
|
"step": 28050
|
|
},
|
|
{
|
|
"entropy": 5.417605924606323,
|
|
"epoch": 2.3433845639826263,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00044476190456099057,
|
|
"loss": 4.7808,
|
|
"mean_token_accuracy": 0.23032971024513244,
|
|
"num_tokens": 51632974.0,
|
|
"step": 28055
|
|
},
|
|
{
|
|
"entropy": 5.453218460083008,
|
|
"epoch": 2.343802205145339,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004447423649469036,
|
|
"loss": 4.7155,
|
|
"mean_token_accuracy": 0.22733936905860902,
|
|
"num_tokens": 51641204.0,
|
|
"step": 28060
|
|
},
|
|
{
|
|
"entropy": 5.288220310211182,
|
|
"epoch": 2.344219846308052,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004447228223612722,
|
|
"loss": 4.6156,
|
|
"mean_token_accuracy": 0.23234931528568267,
|
|
"num_tokens": 51650316.0,
|
|
"step": 28065
|
|
},
|
|
{
|
|
"entropy": 5.355689954757691,
|
|
"epoch": 2.344637487470765,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004447032768044385,
|
|
"loss": 4.7897,
|
|
"mean_token_accuracy": 0.22609643638134003,
|
|
"num_tokens": 51659164.0,
|
|
"step": 28070
|
|
},
|
|
{
|
|
"entropy": 5.358128786087036,
|
|
"epoch": 2.345055128633478,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004446837282767447,
|
|
"loss": 4.7684,
|
|
"mean_token_accuracy": 0.2248171702027321,
|
|
"num_tokens": 51667982.0,
|
|
"step": 28075
|
|
},
|
|
{
|
|
"entropy": 5.425020933151245,
|
|
"epoch": 2.3454727697961912,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00044466417677853294,
|
|
"loss": 4.7865,
|
|
"mean_token_accuracy": 0.22377495765686034,
|
|
"num_tokens": 51677397.0,
|
|
"step": 28080
|
|
},
|
|
{
|
|
"entropy": 5.457374382019043,
|
|
"epoch": 2.345890410958904,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004446446223101456,
|
|
"loss": 4.8774,
|
|
"mean_token_accuracy": 0.22357428222894668,
|
|
"num_tokens": 51686462.0,
|
|
"step": 28085
|
|
},
|
|
{
|
|
"entropy": 5.43464241027832,
|
|
"epoch": 2.346308052121617,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00044462506487192487,
|
|
"loss": 4.8028,
|
|
"mean_token_accuracy": 0.21906677931547164,
|
|
"num_tokens": 51696654.0,
|
|
"step": 28090
|
|
},
|
|
{
|
|
"entropy": 5.369463539123535,
|
|
"epoch": 2.34672569328433,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00044460550446421323,
|
|
"loss": 4.8351,
|
|
"mean_token_accuracy": 0.22187243700027465,
|
|
"num_tokens": 51706005.0,
|
|
"step": 28095
|
|
},
|
|
{
|
|
"entropy": 5.3670093536376955,
|
|
"epoch": 2.347143334447043,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000444585941087353,
|
|
"loss": 4.7824,
|
|
"mean_token_accuracy": 0.22838353365659714,
|
|
"num_tokens": 51715543.0,
|
|
"step": 28100
|
|
},
|
|
{
|
|
"entropy": 5.402427244186401,
|
|
"epoch": 2.347560975609756,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004445663747416868,
|
|
"loss": 4.75,
|
|
"mean_token_accuracy": 0.2262776419520378,
|
|
"num_tokens": 51723599.0,
|
|
"step": 28105
|
|
},
|
|
{
|
|
"entropy": 5.471283769607544,
|
|
"epoch": 2.347978616772469,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00044454680542755715,
|
|
"loss": 4.8351,
|
|
"mean_token_accuracy": 0.22897904813289643,
|
|
"num_tokens": 51732850.0,
|
|
"step": 28110
|
|
},
|
|
{
|
|
"entropy": 5.451678848266601,
|
|
"epoch": 2.3483962579351823,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004445272331453066,
|
|
"loss": 4.8117,
|
|
"mean_token_accuracy": 0.22642450481653215,
|
|
"num_tokens": 51742601.0,
|
|
"step": 28115
|
|
},
|
|
{
|
|
"entropy": 5.402020835876465,
|
|
"epoch": 2.348813899097895,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00044450765789527777,
|
|
"loss": 4.7854,
|
|
"mean_token_accuracy": 0.22228400856256486,
|
|
"num_tokens": 51751675.0,
|
|
"step": 28120
|
|
},
|
|
{
|
|
"entropy": 5.410405492782592,
|
|
"epoch": 2.3492315402606083,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004444880796778133,
|
|
"loss": 4.8734,
|
|
"mean_token_accuracy": 0.22571224123239517,
|
|
"num_tokens": 51761122.0,
|
|
"step": 28125
|
|
},
|
|
{
|
|
"entropy": 5.460010194778443,
|
|
"epoch": 2.349649181423321,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000444468498493256,
|
|
"loss": 4.8061,
|
|
"mean_token_accuracy": 0.2235198959708214,
|
|
"num_tokens": 51770337.0,
|
|
"step": 28130
|
|
},
|
|
{
|
|
"entropy": 5.370050764083862,
|
|
"epoch": 2.350066822586034,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00044444891434194863,
|
|
"loss": 4.7949,
|
|
"mean_token_accuracy": 0.22400234639644623,
|
|
"num_tokens": 51779630.0,
|
|
"step": 28135
|
|
},
|
|
{
|
|
"entropy": 5.29699068069458,
|
|
"epoch": 2.350484463748747,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004444293272242341,
|
|
"loss": 4.6265,
|
|
"mean_token_accuracy": 0.2453928306698799,
|
|
"num_tokens": 51788885.0,
|
|
"step": 28140
|
|
},
|
|
{
|
|
"entropy": 5.383122968673706,
|
|
"epoch": 2.35090210491146,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00044440973714045517,
|
|
"loss": 4.8055,
|
|
"mean_token_accuracy": 0.21746536940336228,
|
|
"num_tokens": 51798152.0,
|
|
"step": 28145
|
|
},
|
|
{
|
|
"entropy": 5.410893249511719,
|
|
"epoch": 2.3513197460741733,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00044439014409095495,
|
|
"loss": 4.7798,
|
|
"mean_token_accuracy": 0.2309303104877472,
|
|
"num_tokens": 51807853.0,
|
|
"step": 28150
|
|
},
|
|
{
|
|
"entropy": 5.415206813812256,
|
|
"epoch": 2.351737387236886,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004443705480760763,
|
|
"loss": 4.8388,
|
|
"mean_token_accuracy": 0.22501756399869918,
|
|
"num_tokens": 51817403.0,
|
|
"step": 28155
|
|
},
|
|
{
|
|
"entropy": 5.400302696228027,
|
|
"epoch": 2.352155028399599,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00044435094909616243,
|
|
"loss": 4.7699,
|
|
"mean_token_accuracy": 0.22008250951766967,
|
|
"num_tokens": 51826527.0,
|
|
"step": 28160
|
|
},
|
|
{
|
|
"entropy": 5.524401140213013,
|
|
"epoch": 2.352572669562312,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004443313471515562,
|
|
"loss": 4.9007,
|
|
"mean_token_accuracy": 0.22188470810651778,
|
|
"num_tokens": 51835743.0,
|
|
"step": 28165
|
|
},
|
|
{
|
|
"entropy": 5.4100151538848875,
|
|
"epoch": 2.352990310725025,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00044431174224260106,
|
|
"loss": 4.7906,
|
|
"mean_token_accuracy": 0.2234727308154106,
|
|
"num_tokens": 51845465.0,
|
|
"step": 28170
|
|
},
|
|
{
|
|
"entropy": 5.365435314178467,
|
|
"epoch": 2.353407951887738,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00044429213436964,
|
|
"loss": 4.7359,
|
|
"mean_token_accuracy": 0.22159408330917357,
|
|
"num_tokens": 51855242.0,
|
|
"step": 28175
|
|
},
|
|
{
|
|
"entropy": 5.347537183761597,
|
|
"epoch": 2.353825593050451,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00044427252353301637,
|
|
"loss": 4.7001,
|
|
"mean_token_accuracy": 0.24358543753623962,
|
|
"num_tokens": 51864142.0,
|
|
"step": 28180
|
|
},
|
|
{
|
|
"entropy": 5.372950220108033,
|
|
"epoch": 2.354243234213164,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00044425290973307345,
|
|
"loss": 4.7008,
|
|
"mean_token_accuracy": 0.23229392915964125,
|
|
"num_tokens": 51873555.0,
|
|
"step": 28185
|
|
},
|
|
{
|
|
"entropy": 5.2938638687133786,
|
|
"epoch": 2.354660875375877,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00044423329297015463,
|
|
"loss": 4.6722,
|
|
"mean_token_accuracy": 0.2350765883922577,
|
|
"num_tokens": 51882629.0,
|
|
"step": 28190
|
|
},
|
|
{
|
|
"entropy": 5.3995198726654055,
|
|
"epoch": 2.35507851653859,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00044421367324460335,
|
|
"loss": 4.7987,
|
|
"mean_token_accuracy": 0.2258242130279541,
|
|
"num_tokens": 51891639.0,
|
|
"step": 28195
|
|
},
|
|
{
|
|
"entropy": 5.331694507598877,
|
|
"epoch": 2.355496157701303,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004441940505567629,
|
|
"loss": 4.6391,
|
|
"mean_token_accuracy": 0.2332822486758232,
|
|
"num_tokens": 51900187.0,
|
|
"step": 28200
|
|
},
|
|
{
|
|
"entropy": 5.414192152023316,
|
|
"epoch": 2.355913798864016,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00044417442490697704,
|
|
"loss": 4.7552,
|
|
"mean_token_accuracy": 0.22781853079795839,
|
|
"num_tokens": 51909002.0,
|
|
"step": 28205
|
|
},
|
|
{
|
|
"entropy": 5.461511659622192,
|
|
"epoch": 2.356331440026729,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00044415479629558924,
|
|
"loss": 4.875,
|
|
"mean_token_accuracy": 0.21970139741897582,
|
|
"num_tokens": 51919066.0,
|
|
"step": 28210
|
|
},
|
|
{
|
|
"entropy": 5.443761730194092,
|
|
"epoch": 2.356749081189442,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00044413516472294315,
|
|
"loss": 4.7942,
|
|
"mean_token_accuracy": 0.22168324738740922,
|
|
"num_tokens": 51928266.0,
|
|
"step": 28215
|
|
},
|
|
{
|
|
"entropy": 5.447095584869385,
|
|
"epoch": 2.357166722352155,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004441155301893823,
|
|
"loss": 4.8541,
|
|
"mean_token_accuracy": 0.22448060810565948,
|
|
"num_tokens": 51937646.0,
|
|
"step": 28220
|
|
},
|
|
{
|
|
"entropy": 5.34923210144043,
|
|
"epoch": 2.357584363514868,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004440958926952506,
|
|
"loss": 4.5902,
|
|
"mean_token_accuracy": 0.2465558633208275,
|
|
"num_tokens": 51945802.0,
|
|
"step": 28225
|
|
},
|
|
{
|
|
"entropy": 5.414505434036255,
|
|
"epoch": 2.358002004677581,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004440762522408917,
|
|
"loss": 4.826,
|
|
"mean_token_accuracy": 0.21859088093042373,
|
|
"num_tokens": 51956024.0,
|
|
"step": 28230
|
|
},
|
|
{
|
|
"entropy": 5.3977696895599365,
|
|
"epoch": 2.358419645840294,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004440566088266496,
|
|
"loss": 4.7599,
|
|
"mean_token_accuracy": 0.22553872764110566,
|
|
"num_tokens": 51965299.0,
|
|
"step": 28235
|
|
},
|
|
{
|
|
"entropy": 5.395667934417725,
|
|
"epoch": 2.358837287003007,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00044403696245286803,
|
|
"loss": 4.7352,
|
|
"mean_token_accuracy": 0.22709691375494004,
|
|
"num_tokens": 51974138.0,
|
|
"step": 28240
|
|
},
|
|
{
|
|
"entropy": 5.373927783966065,
|
|
"epoch": 2.3592549281657202,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00044401731311989086,
|
|
"loss": 4.7554,
|
|
"mean_token_accuracy": 0.22552344799041749,
|
|
"num_tokens": 51983770.0,
|
|
"step": 28245
|
|
},
|
|
{
|
|
"entropy": 5.3837076187133786,
|
|
"epoch": 2.359672569328433,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004439976608280623,
|
|
"loss": 4.7763,
|
|
"mean_token_accuracy": 0.22701748460531235,
|
|
"num_tokens": 51992294.0,
|
|
"step": 28250
|
|
},
|
|
{
|
|
"entropy": 5.512668609619141,
|
|
"epoch": 2.360090210491146,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00044397800557772614,
|
|
"loss": 4.7979,
|
|
"mean_token_accuracy": 0.22506458908319474,
|
|
"num_tokens": 52001605.0,
|
|
"step": 28255
|
|
},
|
|
{
|
|
"entropy": 5.3919049263000485,
|
|
"epoch": 2.360507851653859,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00044395834736922675,
|
|
"loss": 4.6841,
|
|
"mean_token_accuracy": 0.23332134932279586,
|
|
"num_tokens": 52010335.0,
|
|
"step": 28260
|
|
},
|
|
{
|
|
"entropy": 5.328565549850464,
|
|
"epoch": 2.360925492816572,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004439386862029081,
|
|
"loss": 4.6643,
|
|
"mean_token_accuracy": 0.23264726549386977,
|
|
"num_tokens": 52020170.0,
|
|
"step": 28265
|
|
},
|
|
{
|
|
"entropy": 5.367379903793335,
|
|
"epoch": 2.361343133979285,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004439190220791143,
|
|
"loss": 4.767,
|
|
"mean_token_accuracy": 0.22297452837228776,
|
|
"num_tokens": 52030917.0,
|
|
"step": 28270
|
|
},
|
|
{
|
|
"entropy": 5.398513555526733,
|
|
"epoch": 2.361760775141998,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00044389935499818974,
|
|
"loss": 4.7803,
|
|
"mean_token_accuracy": 0.2266594186425209,
|
|
"num_tokens": 52041172.0,
|
|
"step": 28275
|
|
},
|
|
{
|
|
"entropy": 5.424163389205932,
|
|
"epoch": 2.362178416304711,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004438796849604786,
|
|
"loss": 4.7788,
|
|
"mean_token_accuracy": 0.2248183622956276,
|
|
"num_tokens": 52050955.0,
|
|
"step": 28280
|
|
},
|
|
{
|
|
"entropy": 5.376663541793823,
|
|
"epoch": 2.362596057467424,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00044386001196632536,
|
|
"loss": 4.7212,
|
|
"mean_token_accuracy": 0.23643164038658143,
|
|
"num_tokens": 52060196.0,
|
|
"step": 28285
|
|
},
|
|
{
|
|
"entropy": 5.425475788116455,
|
|
"epoch": 2.363013698630137,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004438403360160744,
|
|
"loss": 4.7633,
|
|
"mean_token_accuracy": 0.22378211170434953,
|
|
"num_tokens": 52069375.0,
|
|
"step": 28290
|
|
},
|
|
{
|
|
"entropy": 5.407533454895019,
|
|
"epoch": 2.36343133979285,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00044382065711007,
|
|
"loss": 4.7295,
|
|
"mean_token_accuracy": 0.2308126151561737,
|
|
"num_tokens": 52078209.0,
|
|
"step": 28295
|
|
},
|
|
{
|
|
"entropy": 5.35393590927124,
|
|
"epoch": 2.363848980955563,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00044380097524865684,
|
|
"loss": 4.7249,
|
|
"mean_token_accuracy": 0.229435895383358,
|
|
"num_tokens": 52086822.0,
|
|
"step": 28300
|
|
},
|
|
{
|
|
"entropy": 5.457857322692871,
|
|
"epoch": 2.3642666221182758,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00044378129043217947,
|
|
"loss": 4.8217,
|
|
"mean_token_accuracy": 0.22812825739383696,
|
|
"num_tokens": 52096011.0,
|
|
"step": 28305
|
|
},
|
|
{
|
|
"entropy": 5.436814165115356,
|
|
"epoch": 2.364684263280989,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004437616026609824,
|
|
"loss": 4.7472,
|
|
"mean_token_accuracy": 0.2278577759861946,
|
|
"num_tokens": 52104348.0,
|
|
"step": 28310
|
|
},
|
|
{
|
|
"entropy": 5.440954065322876,
|
|
"epoch": 2.365101904443702,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00044374191193541037,
|
|
"loss": 4.7358,
|
|
"mean_token_accuracy": 0.23122393637895583,
|
|
"num_tokens": 52113083.0,
|
|
"step": 28315
|
|
},
|
|
{
|
|
"entropy": 5.286584758758545,
|
|
"epoch": 2.365519545606415,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00044372221825580803,
|
|
"loss": 4.603,
|
|
"mean_token_accuracy": 0.23940576165914534,
|
|
"num_tokens": 52121726.0,
|
|
"step": 28320
|
|
},
|
|
{
|
|
"entropy": 5.385490608215332,
|
|
"epoch": 2.365937186769128,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00044370252162252016,
|
|
"loss": 4.8032,
|
|
"mean_token_accuracy": 0.22420756369829178,
|
|
"num_tokens": 52131515.0,
|
|
"step": 28325
|
|
},
|
|
{
|
|
"entropy": 5.406382322311401,
|
|
"epoch": 2.366354827931841,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004436828220358916,
|
|
"loss": 4.7225,
|
|
"mean_token_accuracy": 0.23039429187774657,
|
|
"num_tokens": 52140252.0,
|
|
"step": 28330
|
|
},
|
|
{
|
|
"entropy": 5.432050514221191,
|
|
"epoch": 2.366772469094554,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004436631194962672,
|
|
"loss": 4.8137,
|
|
"mean_token_accuracy": 0.2269454076886177,
|
|
"num_tokens": 52150353.0,
|
|
"step": 28335
|
|
},
|
|
{
|
|
"entropy": 5.347120904922486,
|
|
"epoch": 2.3671901102572668,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00044364341400399186,
|
|
"loss": 4.7089,
|
|
"mean_token_accuracy": 0.22882103472948073,
|
|
"num_tokens": 52160280.0,
|
|
"step": 28340
|
|
},
|
|
{
|
|
"entropy": 5.479483413696289,
|
|
"epoch": 2.36760775141998,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00044362370555941057,
|
|
"loss": 4.8809,
|
|
"mean_token_accuracy": 0.21600629687309264,
|
|
"num_tokens": 52169989.0,
|
|
"step": 28345
|
|
},
|
|
{
|
|
"entropy": 5.4396614074707035,
|
|
"epoch": 2.368025392582693,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004436039941628684,
|
|
"loss": 4.6878,
|
|
"mean_token_accuracy": 0.23121062517166138,
|
|
"num_tokens": 52179535.0,
|
|
"step": 28350
|
|
},
|
|
{
|
|
"entropy": 5.329100799560547,
|
|
"epoch": 2.368443033745406,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004435842798147103,
|
|
"loss": 4.598,
|
|
"mean_token_accuracy": 0.24650306701660157,
|
|
"num_tokens": 52188809.0,
|
|
"step": 28355
|
|
},
|
|
{
|
|
"entropy": 5.326726865768433,
|
|
"epoch": 2.368860674908119,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00044356456251528145,
|
|
"loss": 4.7177,
|
|
"mean_token_accuracy": 0.23091379553079605,
|
|
"num_tokens": 52197758.0,
|
|
"step": 28360
|
|
},
|
|
{
|
|
"entropy": 5.327551221847534,
|
|
"epoch": 2.369278316070832,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004435448422649271,
|
|
"loss": 4.6958,
|
|
"mean_token_accuracy": 0.227715927362442,
|
|
"num_tokens": 52206461.0,
|
|
"step": 28365
|
|
},
|
|
{
|
|
"entropy": 5.419080066680908,
|
|
"epoch": 2.369695957233545,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004435251190639923,
|
|
"loss": 4.753,
|
|
"mean_token_accuracy": 0.227353535592556,
|
|
"num_tokens": 52215786.0,
|
|
"step": 28370
|
|
},
|
|
{
|
|
"entropy": 5.405311536788941,
|
|
"epoch": 2.370113598396258,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00044350539291282247,
|
|
"loss": 4.7494,
|
|
"mean_token_accuracy": 0.2344165176153183,
|
|
"num_tokens": 52224668.0,
|
|
"step": 28375
|
|
},
|
|
{
|
|
"entropy": 5.453671836853028,
|
|
"epoch": 2.370531239558971,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004434856638117629,
|
|
"loss": 4.787,
|
|
"mean_token_accuracy": 0.22321197092533113,
|
|
"num_tokens": 52233999.0,
|
|
"step": 28380
|
|
},
|
|
{
|
|
"entropy": 5.306198024749756,
|
|
"epoch": 2.370948880721684,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00044346593176115904,
|
|
"loss": 4.6764,
|
|
"mean_token_accuracy": 0.23853715360164643,
|
|
"num_tokens": 52243015.0,
|
|
"step": 28385
|
|
},
|
|
{
|
|
"entropy": 5.2730001449584964,
|
|
"epoch": 2.371366521884397,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00044344619676135624,
|
|
"loss": 4.6262,
|
|
"mean_token_accuracy": 0.2475108414888382,
|
|
"num_tokens": 52251748.0,
|
|
"step": 28390
|
|
},
|
|
{
|
|
"entropy": 5.338049411773682,
|
|
"epoch": 2.37178416304711,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004434264588127,
|
|
"loss": 4.6762,
|
|
"mean_token_accuracy": 0.2366912454366684,
|
|
"num_tokens": 52261228.0,
|
|
"step": 28395
|
|
},
|
|
{
|
|
"entropy": 5.419888591766357,
|
|
"epoch": 2.3722018042098227,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00044340671791553586,
|
|
"loss": 4.789,
|
|
"mean_token_accuracy": 0.23286878913640977,
|
|
"num_tokens": 52270464.0,
|
|
"step": 28400
|
|
},
|
|
{
|
|
"entropy": 5.403564500808716,
|
|
"epoch": 2.372619445372536,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004433869740702094,
|
|
"loss": 4.7369,
|
|
"mean_token_accuracy": 0.22887353003025054,
|
|
"num_tokens": 52279888.0,
|
|
"step": 28405
|
|
},
|
|
{
|
|
"entropy": 5.3640156269073485,
|
|
"epoch": 2.373037086535249,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004433672272770663,
|
|
"loss": 4.6698,
|
|
"mean_token_accuracy": 0.23994319438934325,
|
|
"num_tokens": 52288618.0,
|
|
"step": 28410
|
|
},
|
|
{
|
|
"entropy": 5.394039964675903,
|
|
"epoch": 2.373454727697962,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00044334747753645224,
|
|
"loss": 4.8004,
|
|
"mean_token_accuracy": 0.21891293972730635,
|
|
"num_tokens": 52298001.0,
|
|
"step": 28415
|
|
},
|
|
{
|
|
"entropy": 5.384827470779419,
|
|
"epoch": 2.373872368860675,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004433277248487129,
|
|
"loss": 4.7517,
|
|
"mean_token_accuracy": 0.23124140799045562,
|
|
"num_tokens": 52306863.0,
|
|
"step": 28420
|
|
},
|
|
{
|
|
"entropy": 5.399064826965332,
|
|
"epoch": 2.3742900100233877,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004433079692141941,
|
|
"loss": 4.6879,
|
|
"mean_token_accuracy": 0.23100789040327072,
|
|
"num_tokens": 52315445.0,
|
|
"step": 28425
|
|
},
|
|
{
|
|
"entropy": 5.3683922290802,
|
|
"epoch": 2.374707651186101,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00044328821063324177,
|
|
"loss": 4.7236,
|
|
"mean_token_accuracy": 0.23353657871484756,
|
|
"num_tokens": 52324478.0,
|
|
"step": 28430
|
|
},
|
|
{
|
|
"entropy": 5.353582668304443,
|
|
"epoch": 2.3751252923488138,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004432684491062017,
|
|
"loss": 4.7499,
|
|
"mean_token_accuracy": 0.22542851865291597,
|
|
"num_tokens": 52333136.0,
|
|
"step": 28435
|
|
},
|
|
{
|
|
"entropy": 5.401567077636718,
|
|
"epoch": 2.375542933511527,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00044324868463341987,
|
|
"loss": 4.8784,
|
|
"mean_token_accuracy": 0.2144751086831093,
|
|
"num_tokens": 52343490.0,
|
|
"step": 28440
|
|
},
|
|
{
|
|
"entropy": 5.434607458114624,
|
|
"epoch": 2.37596057467424,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00044322891721524233,
|
|
"loss": 4.8055,
|
|
"mean_token_accuracy": 0.2265818953514099,
|
|
"num_tokens": 52352628.0,
|
|
"step": 28445
|
|
},
|
|
{
|
|
"entropy": 5.382171583175659,
|
|
"epoch": 2.376378215836953,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00044320914685201516,
|
|
"loss": 4.7224,
|
|
"mean_token_accuracy": 0.22871158570051192,
|
|
"num_tokens": 52361947.0,
|
|
"step": 28450
|
|
},
|
|
{
|
|
"entropy": 5.406821584701538,
|
|
"epoch": 2.376795856999666,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004431893735440843,
|
|
"loss": 4.7693,
|
|
"mean_token_accuracy": 0.218741013109684,
|
|
"num_tokens": 52371251.0,
|
|
"step": 28455
|
|
},
|
|
{
|
|
"entropy": 5.362784290313721,
|
|
"epoch": 2.3772134981623787,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00044316959729179603,
|
|
"loss": 4.6979,
|
|
"mean_token_accuracy": 0.23985220193862916,
|
|
"num_tokens": 52380681.0,
|
|
"step": 28460
|
|
},
|
|
{
|
|
"entropy": 5.429660701751709,
|
|
"epoch": 2.377631139325092,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00044314981809549656,
|
|
"loss": 4.7099,
|
|
"mean_token_accuracy": 0.2275398775935173,
|
|
"num_tokens": 52390059.0,
|
|
"step": 28465
|
|
},
|
|
{
|
|
"entropy": 5.4290704250335695,
|
|
"epoch": 2.3780487804878048,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004431300359555321,
|
|
"loss": 4.7901,
|
|
"mean_token_accuracy": 0.22154495269060134,
|
|
"num_tokens": 52399574.0,
|
|
"step": 28470
|
|
},
|
|
{
|
|
"entropy": 5.423555135726929,
|
|
"epoch": 2.378466421650518,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000443110250872249,
|
|
"loss": 4.8675,
|
|
"mean_token_accuracy": 0.22465150505304338,
|
|
"num_tokens": 52408926.0,
|
|
"step": 28475
|
|
},
|
|
{
|
|
"entropy": 5.388863611221313,
|
|
"epoch": 2.378884062813231,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004430904628459935,
|
|
"loss": 4.8042,
|
|
"mean_token_accuracy": 0.23119643628597258,
|
|
"num_tokens": 52418052.0,
|
|
"step": 28480
|
|
},
|
|
{
|
|
"entropy": 5.3806922912597654,
|
|
"epoch": 2.379301703975944,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00044307067187711227,
|
|
"loss": 4.703,
|
|
"mean_token_accuracy": 0.2306311160326004,
|
|
"num_tokens": 52427422.0,
|
|
"step": 28485
|
|
},
|
|
{
|
|
"entropy": 5.416671276092529,
|
|
"epoch": 2.379719345138657,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004430508779659516,
|
|
"loss": 4.7853,
|
|
"mean_token_accuracy": 0.22617148011922836,
|
|
"num_tokens": 52436535.0,
|
|
"step": 28490
|
|
},
|
|
{
|
|
"entropy": 5.378588104248047,
|
|
"epoch": 2.3801369863013697,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00044303108111285795,
|
|
"loss": 4.7955,
|
|
"mean_token_accuracy": 0.23377599865198134,
|
|
"num_tokens": 52445640.0,
|
|
"step": 28495
|
|
},
|
|
{
|
|
"entropy": 5.443934726715088,
|
|
"epoch": 2.380554627464083,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00044301128131817805,
|
|
"loss": 4.8656,
|
|
"mean_token_accuracy": 0.22616786807775496,
|
|
"num_tokens": 52454715.0,
|
|
"step": 28500
|
|
},
|
|
{
|
|
"entropy": 5.436970043182373,
|
|
"epoch": 2.380972268626796,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00044299147858225835,
|
|
"loss": 4.848,
|
|
"mean_token_accuracy": 0.22402074933052063,
|
|
"num_tokens": 52464015.0,
|
|
"step": 28505
|
|
},
|
|
{
|
|
"entropy": 5.401380252838135,
|
|
"epoch": 2.381389909789509,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004429716729054456,
|
|
"loss": 4.7856,
|
|
"mean_token_accuracy": 0.2255691945552826,
|
|
"num_tokens": 52472927.0,
|
|
"step": 28510
|
|
},
|
|
{
|
|
"entropy": 5.460753536224365,
|
|
"epoch": 2.381807550952222,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004429518642880866,
|
|
"loss": 4.8564,
|
|
"mean_token_accuracy": 0.22048219293355942,
|
|
"num_tokens": 52482417.0,
|
|
"step": 28515
|
|
},
|
|
{
|
|
"entropy": 5.372438287734985,
|
|
"epoch": 2.3822251921149347,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00044293205273052805,
|
|
"loss": 4.7998,
|
|
"mean_token_accuracy": 0.22779939621686934,
|
|
"num_tokens": 52491294.0,
|
|
"step": 28520
|
|
},
|
|
{
|
|
"entropy": 5.487789535522461,
|
|
"epoch": 2.382642833277648,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004429122382331168,
|
|
"loss": 4.8216,
|
|
"mean_token_accuracy": 0.2244476154446602,
|
|
"num_tokens": 52500253.0,
|
|
"step": 28525
|
|
},
|
|
{
|
|
"entropy": 5.391653060913086,
|
|
"epoch": 2.3830604744403607,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00044289242079619955,
|
|
"loss": 4.7546,
|
|
"mean_token_accuracy": 0.2275500252842903,
|
|
"num_tokens": 52509828.0,
|
|
"step": 28530
|
|
},
|
|
{
|
|
"entropy": 5.373068523406983,
|
|
"epoch": 2.383478115603074,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00044287260042012353,
|
|
"loss": 4.6715,
|
|
"mean_token_accuracy": 0.22728651762008667,
|
|
"num_tokens": 52518781.0,
|
|
"step": 28535
|
|
},
|
|
{
|
|
"entropy": 5.352390146255493,
|
|
"epoch": 2.383895756765787,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004428527771052355,
|
|
"loss": 4.7343,
|
|
"mean_token_accuracy": 0.2250616267323494,
|
|
"num_tokens": 52528102.0,
|
|
"step": 28540
|
|
},
|
|
{
|
|
"entropy": 5.509509801864624,
|
|
"epoch": 2.3843133979284996,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00044283295085188263,
|
|
"loss": 4.8483,
|
|
"mean_token_accuracy": 0.2184962138533592,
|
|
"num_tokens": 52537609.0,
|
|
"step": 28545
|
|
},
|
|
{
|
|
"entropy": 5.398200130462646,
|
|
"epoch": 2.384731039091213,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00044281312166041196,
|
|
"loss": 4.7783,
|
|
"mean_token_accuracy": 0.23155198097229004,
|
|
"num_tokens": 52547169.0,
|
|
"step": 28550
|
|
},
|
|
{
|
|
"entropy": 5.3142718315124515,
|
|
"epoch": 2.3851486802539257,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004427932895311705,
|
|
"loss": 4.7129,
|
|
"mean_token_accuracy": 0.2269053965806961,
|
|
"num_tokens": 52556220.0,
|
|
"step": 28555
|
|
},
|
|
{
|
|
"entropy": 5.399640417098999,
|
|
"epoch": 2.385566321416639,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004427734544645055,
|
|
"loss": 4.8701,
|
|
"mean_token_accuracy": 0.22175949662923813,
|
|
"num_tokens": 52565736.0,
|
|
"step": 28560
|
|
},
|
|
{
|
|
"entropy": 5.427084827423096,
|
|
"epoch": 2.3859839625793517,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00044275361646076427,
|
|
"loss": 4.7534,
|
|
"mean_token_accuracy": 0.22300374656915664,
|
|
"num_tokens": 52575222.0,
|
|
"step": 28565
|
|
},
|
|
{
|
|
"entropy": 5.3996724605560305,
|
|
"epoch": 2.386401603742065,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00044273377552029415,
|
|
"loss": 4.6914,
|
|
"mean_token_accuracy": 0.23261428475379944,
|
|
"num_tokens": 52584726.0,
|
|
"step": 28570
|
|
},
|
|
{
|
|
"entropy": 5.406810522079468,
|
|
"epoch": 2.386819244904778,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004427139316434423,
|
|
"loss": 4.888,
|
|
"mean_token_accuracy": 0.2223397821187973,
|
|
"num_tokens": 52595080.0,
|
|
"step": 28575
|
|
},
|
|
{
|
|
"entropy": 5.42208080291748,
|
|
"epoch": 2.3872368860674906,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004426940848305563,
|
|
"loss": 4.8447,
|
|
"mean_token_accuracy": 0.21809726506471633,
|
|
"num_tokens": 52604692.0,
|
|
"step": 28580
|
|
},
|
|
{
|
|
"entropy": 5.384083080291748,
|
|
"epoch": 2.387654527230204,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004426742350819834,
|
|
"loss": 4.7338,
|
|
"mean_token_accuracy": 0.2255946159362793,
|
|
"num_tokens": 52613697.0,
|
|
"step": 28585
|
|
},
|
|
{
|
|
"entropy": 5.392904663085938,
|
|
"epoch": 2.3880721683929167,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00044265438239807117,
|
|
"loss": 4.7678,
|
|
"mean_token_accuracy": 0.22840639650821687,
|
|
"num_tokens": 52622048.0,
|
|
"step": 28590
|
|
},
|
|
{
|
|
"entropy": 5.331557178497315,
|
|
"epoch": 2.38848980955563,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004426345267791672,
|
|
"loss": 4.6701,
|
|
"mean_token_accuracy": 0.23937548100948333,
|
|
"num_tokens": 52631939.0,
|
|
"step": 28595
|
|
},
|
|
{
|
|
"entropy": 5.348557710647583,
|
|
"epoch": 2.3889074507183428,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00044261466822561907,
|
|
"loss": 4.7079,
|
|
"mean_token_accuracy": 0.2374127134680748,
|
|
"num_tokens": 52641651.0,
|
|
"step": 28600
|
|
},
|
|
{
|
|
"entropy": 5.398337030410767,
|
|
"epoch": 2.389325091881056,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004425948067377744,
|
|
"loss": 4.7536,
|
|
"mean_token_accuracy": 0.22675809264183044,
|
|
"num_tokens": 52650863.0,
|
|
"step": 28605
|
|
},
|
|
{
|
|
"entropy": 5.43191933631897,
|
|
"epoch": 2.389742733043769,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00044257494231598094,
|
|
"loss": 4.7762,
|
|
"mean_token_accuracy": 0.22576041966676713,
|
|
"num_tokens": 52659892.0,
|
|
"step": 28610
|
|
},
|
|
{
|
|
"entropy": 5.426583528518677,
|
|
"epoch": 2.3901603742064816,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004425550749605863,
|
|
"loss": 4.7545,
|
|
"mean_token_accuracy": 0.23043035715818405,
|
|
"num_tokens": 52669381.0,
|
|
"step": 28615
|
|
},
|
|
{
|
|
"entropy": 5.508784532546997,
|
|
"epoch": 2.390578015369195,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00044253520467193855,
|
|
"loss": 4.8026,
|
|
"mean_token_accuracy": 0.22834810614585876,
|
|
"num_tokens": 52678742.0,
|
|
"step": 28620
|
|
},
|
|
{
|
|
"entropy": 5.426791143417359,
|
|
"epoch": 2.3909956565319077,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00044251533145038525,
|
|
"loss": 4.8254,
|
|
"mean_token_accuracy": 0.23111376017332078,
|
|
"num_tokens": 52688494.0,
|
|
"step": 28625
|
|
},
|
|
{
|
|
"entropy": 5.332976675033569,
|
|
"epoch": 2.391413297694621,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004424954552962744,
|
|
"loss": 4.6521,
|
|
"mean_token_accuracy": 0.2300062358379364,
|
|
"num_tokens": 52696778.0,
|
|
"step": 28630
|
|
},
|
|
{
|
|
"entropy": 5.329631042480469,
|
|
"epoch": 2.3918309388573338,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00044247557620995416,
|
|
"loss": 4.7428,
|
|
"mean_token_accuracy": 0.23183609247207643,
|
|
"num_tokens": 52706031.0,
|
|
"step": 28635
|
|
},
|
|
{
|
|
"entropy": 5.355924081802368,
|
|
"epoch": 2.3922485800200466,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004424556941917723,
|
|
"loss": 4.7376,
|
|
"mean_token_accuracy": 0.23130553513765334,
|
|
"num_tokens": 52715513.0,
|
|
"step": 28640
|
|
},
|
|
{
|
|
"entropy": 5.516912221908569,
|
|
"epoch": 2.39266622118276,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00044243580924207686,
|
|
"loss": 4.8852,
|
|
"mean_token_accuracy": 0.21860263198614122,
|
|
"num_tokens": 52724622.0,
|
|
"step": 28645
|
|
},
|
|
{
|
|
"entropy": 5.374783658981324,
|
|
"epoch": 2.3930838623454727,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004424159213612161,
|
|
"loss": 4.7294,
|
|
"mean_token_accuracy": 0.23001540452241898,
|
|
"num_tokens": 52733879.0,
|
|
"step": 28650
|
|
},
|
|
{
|
|
"entropy": 5.287469816207886,
|
|
"epoch": 2.393501503508186,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004423960305495381,
|
|
"loss": 4.6016,
|
|
"mean_token_accuracy": 0.2428205281496048,
|
|
"num_tokens": 52742656.0,
|
|
"step": 28655
|
|
},
|
|
{
|
|
"entropy": 5.396427965164184,
|
|
"epoch": 2.3939191446708987,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004423761368073911,
|
|
"loss": 4.8391,
|
|
"mean_token_accuracy": 0.2221890151500702,
|
|
"num_tokens": 52753073.0,
|
|
"step": 28660
|
|
},
|
|
{
|
|
"entropy": 5.413737392425537,
|
|
"epoch": 2.3943367858336115,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004423562401351234,
|
|
"loss": 4.7961,
|
|
"mean_token_accuracy": 0.2264066144824028,
|
|
"num_tokens": 52761891.0,
|
|
"step": 28665
|
|
},
|
|
{
|
|
"entropy": 5.363567209243774,
|
|
"epoch": 2.394754426996325,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004423363405330833,
|
|
"loss": 4.7152,
|
|
"mean_token_accuracy": 0.22902408391237258,
|
|
"num_tokens": 52772175.0,
|
|
"step": 28670
|
|
},
|
|
{
|
|
"entropy": 5.348560237884522,
|
|
"epoch": 2.3951720681590376,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00044231643800161897,
|
|
"loss": 4.8138,
|
|
"mean_token_accuracy": 0.21830016374588013,
|
|
"num_tokens": 52783073.0,
|
|
"step": 28675
|
|
},
|
|
{
|
|
"entropy": 5.391084051132202,
|
|
"epoch": 2.395589709321751,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004422965325410791,
|
|
"loss": 4.6771,
|
|
"mean_token_accuracy": 0.22760453224182128,
|
|
"num_tokens": 52791949.0,
|
|
"step": 28680
|
|
},
|
|
{
|
|
"entropy": 5.349165248870849,
|
|
"epoch": 2.3960073504844637,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00044227662415181207,
|
|
"loss": 4.6457,
|
|
"mean_token_accuracy": 0.232245934009552,
|
|
"num_tokens": 52800912.0,
|
|
"step": 28685
|
|
},
|
|
{
|
|
"entropy": 5.392408084869385,
|
|
"epoch": 2.396424991647177,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00044225671283416634,
|
|
"loss": 4.7501,
|
|
"mean_token_accuracy": 0.22639445066452027,
|
|
"num_tokens": 52810419.0,
|
|
"step": 28690
|
|
},
|
|
{
|
|
"entropy": 5.363316202163697,
|
|
"epoch": 2.3968426328098897,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00044223679858849057,
|
|
"loss": 4.6993,
|
|
"mean_token_accuracy": 0.2359849140048027,
|
|
"num_tokens": 52819148.0,
|
|
"step": 28695
|
|
},
|
|
{
|
|
"entropy": 5.4215309619903564,
|
|
"epoch": 2.3972602739726026,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004422168814151333,
|
|
"loss": 4.8218,
|
|
"mean_token_accuracy": 0.2177566781640053,
|
|
"num_tokens": 52828494.0,
|
|
"step": 28700
|
|
},
|
|
{
|
|
"entropy": 5.357583713531494,
|
|
"epoch": 2.397677915135316,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00044219696131444326,
|
|
"loss": 4.7802,
|
|
"mean_token_accuracy": 0.22266725897789003,
|
|
"num_tokens": 52837279.0,
|
|
"step": 28705
|
|
},
|
|
{
|
|
"entropy": 5.4159880638122555,
|
|
"epoch": 2.3980955562980286,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00044217703828676913,
|
|
"loss": 4.7656,
|
|
"mean_token_accuracy": 0.23529277443885804,
|
|
"num_tokens": 52846319.0,
|
|
"step": 28710
|
|
},
|
|
{
|
|
"entropy": 5.36517858505249,
|
|
"epoch": 2.398513197460742,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00044215711233245973,
|
|
"loss": 4.7144,
|
|
"mean_token_accuracy": 0.2251345306634903,
|
|
"num_tokens": 52855005.0,
|
|
"step": 28715
|
|
},
|
|
{
|
|
"entropy": 5.443662643432617,
|
|
"epoch": 2.3989308386234547,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00044213718345186394,
|
|
"loss": 4.855,
|
|
"mean_token_accuracy": 0.22742797583341598,
|
|
"num_tokens": 52864805.0,
|
|
"step": 28720
|
|
},
|
|
{
|
|
"entropy": 5.38960223197937,
|
|
"epoch": 2.399348479786168,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00044211725164533045,
|
|
"loss": 4.7718,
|
|
"mean_token_accuracy": 0.23091876059770583,
|
|
"num_tokens": 52873808.0,
|
|
"step": 28725
|
|
},
|
|
{
|
|
"entropy": 5.376420783996582,
|
|
"epoch": 2.3997661209488808,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00044209731691320837,
|
|
"loss": 4.7703,
|
|
"mean_token_accuracy": 0.2274141490459442,
|
|
"num_tokens": 52882564.0,
|
|
"step": 28730
|
|
},
|
|
{
|
|
"entropy": 5.425851726531983,
|
|
"epoch": 2.4001837621115936,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004420773792558467,
|
|
"loss": 4.8117,
|
|
"mean_token_accuracy": 0.2176012486219406,
|
|
"num_tokens": 52891271.0,
|
|
"step": 28735
|
|
},
|
|
{
|
|
"entropy": 5.317887306213379,
|
|
"epoch": 2.400601403274307,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004420574386735943,
|
|
"loss": 4.6955,
|
|
"mean_token_accuracy": 0.229635851085186,
|
|
"num_tokens": 52900075.0,
|
|
"step": 28740
|
|
},
|
|
{
|
|
"entropy": 5.3139245986938475,
|
|
"epoch": 2.4010190444370196,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00044203749516680035,
|
|
"loss": 4.7144,
|
|
"mean_token_accuracy": 0.22737194895744323,
|
|
"num_tokens": 52908744.0,
|
|
"step": 28745
|
|
},
|
|
{
|
|
"entropy": 5.3787633895874025,
|
|
"epoch": 2.401436685599733,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00044201754873581396,
|
|
"loss": 4.7219,
|
|
"mean_token_accuracy": 0.23054239749908448,
|
|
"num_tokens": 52918242.0,
|
|
"step": 28750
|
|
},
|
|
{
|
|
"entropy": 5.444127893447876,
|
|
"epoch": 2.4018543267624457,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00044199759938098437,
|
|
"loss": 4.8085,
|
|
"mean_token_accuracy": 0.22447536885738373,
|
|
"num_tokens": 52927453.0,
|
|
"step": 28755
|
|
},
|
|
{
|
|
"entropy": 5.336135292053223,
|
|
"epoch": 2.4022719679251585,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00044197764710266087,
|
|
"loss": 4.6683,
|
|
"mean_token_accuracy": 0.23876175433397293,
|
|
"num_tokens": 52935467.0,
|
|
"step": 28760
|
|
},
|
|
{
|
|
"entropy": 5.478932476043701,
|
|
"epoch": 2.4026896090878718,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004419576919011926,
|
|
"loss": 4.8714,
|
|
"mean_token_accuracy": 0.2232281193137169,
|
|
"num_tokens": 52944770.0,
|
|
"step": 28765
|
|
},
|
|
{
|
|
"entropy": 5.3926025390625,
|
|
"epoch": 2.4031072502505846,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00044193773377692886,
|
|
"loss": 4.7152,
|
|
"mean_token_accuracy": 0.22964146584272385,
|
|
"num_tokens": 52953679.0,
|
|
"step": 28770
|
|
},
|
|
{
|
|
"entropy": 5.326699829101562,
|
|
"epoch": 2.403524891413298,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00044191777273021933,
|
|
"loss": 4.7047,
|
|
"mean_token_accuracy": 0.22734664976596833,
|
|
"num_tokens": 52962101.0,
|
|
"step": 28775
|
|
},
|
|
{
|
|
"entropy": 5.294408082962036,
|
|
"epoch": 2.4039425325760106,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004418978087614131,
|
|
"loss": 4.7522,
|
|
"mean_token_accuracy": 0.22671517580747605,
|
|
"num_tokens": 52971661.0,
|
|
"step": 28780
|
|
},
|
|
{
|
|
"entropy": 5.4420506954193115,
|
|
"epoch": 2.4043601737387235,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00044187784187085994,
|
|
"loss": 4.806,
|
|
"mean_token_accuracy": 0.22042457461357118,
|
|
"num_tokens": 52981091.0,
|
|
"step": 28785
|
|
},
|
|
{
|
|
"entropy": 5.486559677124023,
|
|
"epoch": 2.4047778149014367,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004418578720589093,
|
|
"loss": 4.8371,
|
|
"mean_token_accuracy": 0.22117818146944046,
|
|
"num_tokens": 52990392.0,
|
|
"step": 28790
|
|
},
|
|
{
|
|
"entropy": 5.404915857315063,
|
|
"epoch": 2.4051954560641495,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004418378993259107,
|
|
"loss": 4.8013,
|
|
"mean_token_accuracy": 0.22390762120485305,
|
|
"num_tokens": 52999203.0,
|
|
"step": 28795
|
|
},
|
|
{
|
|
"entropy": 5.51438274383545,
|
|
"epoch": 2.405613097226863,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004418179236722139,
|
|
"loss": 4.8659,
|
|
"mean_token_accuracy": 0.22773491889238356,
|
|
"num_tokens": 53009421.0,
|
|
"step": 28800
|
|
},
|
|
{
|
|
"entropy": 5.339182281494141,
|
|
"epoch": 2.4060307383895756,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004417979450981685,
|
|
"loss": 4.6945,
|
|
"mean_token_accuracy": 0.2278055652976036,
|
|
"num_tokens": 53018968.0,
|
|
"step": 28805
|
|
},
|
|
{
|
|
"entropy": 5.429933738708496,
|
|
"epoch": 2.406448379552289,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00044177796360412436,
|
|
"loss": 4.7781,
|
|
"mean_token_accuracy": 0.22590832859277726,
|
|
"num_tokens": 53027708.0,
|
|
"step": 28810
|
|
},
|
|
{
|
|
"entropy": 5.429459285736084,
|
|
"epoch": 2.4068660207150017,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004417579791904312,
|
|
"loss": 4.8366,
|
|
"mean_token_accuracy": 0.22852950692176818,
|
|
"num_tokens": 53036373.0,
|
|
"step": 28815
|
|
},
|
|
{
|
|
"entropy": 5.466600608825684,
|
|
"epoch": 2.4072836618777145,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004417379918574388,
|
|
"loss": 4.8932,
|
|
"mean_token_accuracy": 0.22157546132802963,
|
|
"num_tokens": 53046138.0,
|
|
"step": 28820
|
|
},
|
|
{
|
|
"entropy": 5.39372935295105,
|
|
"epoch": 2.4077013030404277,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004417180016054972,
|
|
"loss": 4.7398,
|
|
"mean_token_accuracy": 0.21910093426704408,
|
|
"num_tokens": 53055039.0,
|
|
"step": 28825
|
|
},
|
|
{
|
|
"entropy": 5.3820911884307865,
|
|
"epoch": 2.4081189442031405,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00044169800843495637,
|
|
"loss": 4.7398,
|
|
"mean_token_accuracy": 0.23307161331176757,
|
|
"num_tokens": 53064901.0,
|
|
"step": 28830
|
|
},
|
|
{
|
|
"entropy": 5.3378795146942135,
|
|
"epoch": 2.408536585365854,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004416780123461662,
|
|
"loss": 4.7355,
|
|
"mean_token_accuracy": 0.22729475051164627,
|
|
"num_tokens": 53074138.0,
|
|
"step": 28835
|
|
},
|
|
{
|
|
"entropy": 5.382087326049804,
|
|
"epoch": 2.4089542265285666,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00044165801333947676,
|
|
"loss": 4.6993,
|
|
"mean_token_accuracy": 0.22828260511159898,
|
|
"num_tokens": 53083020.0,
|
|
"step": 28840
|
|
},
|
|
{
|
|
"entropy": 5.353454113006592,
|
|
"epoch": 2.40937186769128,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004416380114152382,
|
|
"loss": 4.7211,
|
|
"mean_token_accuracy": 0.22972376197576522,
|
|
"num_tokens": 53092141.0,
|
|
"step": 28845
|
|
},
|
|
{
|
|
"entropy": 5.354425716400146,
|
|
"epoch": 2.4097895088539927,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00044161800657380076,
|
|
"loss": 4.7256,
|
|
"mean_token_accuracy": 0.23112715482711793,
|
|
"num_tokens": 53101305.0,
|
|
"step": 28850
|
|
},
|
|
{
|
|
"entropy": 5.3943541049957275,
|
|
"epoch": 2.4102071500167055,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004415979988155145,
|
|
"loss": 4.7658,
|
|
"mean_token_accuracy": 0.22467606514692307,
|
|
"num_tokens": 53109946.0,
|
|
"step": 28855
|
|
},
|
|
{
|
|
"entropy": 5.423027276992798,
|
|
"epoch": 2.4106247911794187,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004415779881407297,
|
|
"loss": 4.7676,
|
|
"mean_token_accuracy": 0.22587326765060425,
|
|
"num_tokens": 53118369.0,
|
|
"step": 28860
|
|
},
|
|
{
|
|
"entropy": 5.401029491424561,
|
|
"epoch": 2.4110424323421316,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004415579745497967,
|
|
"loss": 4.7973,
|
|
"mean_token_accuracy": 0.22296251207590104,
|
|
"num_tokens": 53127389.0,
|
|
"step": 28865
|
|
},
|
|
{
|
|
"entropy": 5.402371168136597,
|
|
"epoch": 2.411460073504845,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004415379580430659,
|
|
"loss": 4.8122,
|
|
"mean_token_accuracy": 0.2210391491651535,
|
|
"num_tokens": 53136055.0,
|
|
"step": 28870
|
|
},
|
|
{
|
|
"entropy": 5.38634877204895,
|
|
"epoch": 2.4118777146675576,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00044151793862088766,
|
|
"loss": 4.7632,
|
|
"mean_token_accuracy": 0.22919127643108367,
|
|
"num_tokens": 53145687.0,
|
|
"step": 28875
|
|
},
|
|
{
|
|
"entropy": 5.399991416931153,
|
|
"epoch": 2.4122953558302704,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004414979162836125,
|
|
"loss": 4.7922,
|
|
"mean_token_accuracy": 0.21847742944955825,
|
|
"num_tokens": 53155667.0,
|
|
"step": 28880
|
|
},
|
|
{
|
|
"entropy": 5.4073303699493405,
|
|
"epoch": 2.4127129969929837,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004414778910315909,
|
|
"loss": 4.7088,
|
|
"mean_token_accuracy": 0.2378152385354042,
|
|
"num_tokens": 53164615.0,
|
|
"step": 28885
|
|
},
|
|
{
|
|
"entropy": 5.444249153137207,
|
|
"epoch": 2.4131306381556965,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00044145786286517343,
|
|
"loss": 4.8148,
|
|
"mean_token_accuracy": 0.2194971486926079,
|
|
"num_tokens": 53174139.0,
|
|
"step": 28890
|
|
},
|
|
{
|
|
"entropy": 5.490477180480957,
|
|
"epoch": 2.4135482793184098,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004414378317847107,
|
|
"loss": 4.8401,
|
|
"mean_token_accuracy": 0.21856264322996138,
|
|
"num_tokens": 53182019.0,
|
|
"step": 28895
|
|
},
|
|
{
|
|
"entropy": 5.310101318359375,
|
|
"epoch": 2.4139659204811226,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00044141779779055334,
|
|
"loss": 4.7204,
|
|
"mean_token_accuracy": 0.2233146086335182,
|
|
"num_tokens": 53191312.0,
|
|
"step": 28900
|
|
},
|
|
{
|
|
"entropy": 5.403000974655152,
|
|
"epoch": 2.4143835616438354,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00044139776088305215,
|
|
"loss": 4.7376,
|
|
"mean_token_accuracy": 0.2295011818408966,
|
|
"num_tokens": 53200027.0,
|
|
"step": 28905
|
|
},
|
|
{
|
|
"entropy": 5.400877904891968,
|
|
"epoch": 2.4148012028065486,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00044137772106255793,
|
|
"loss": 4.7868,
|
|
"mean_token_accuracy": 0.2202758327126503,
|
|
"num_tokens": 53209841.0,
|
|
"step": 28910
|
|
},
|
|
{
|
|
"entropy": 5.5594347476959225,
|
|
"epoch": 2.4152188439692615,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00044135767832942136,
|
|
"loss": 4.9736,
|
|
"mean_token_accuracy": 0.21326812505722045,
|
|
"num_tokens": 53219717.0,
|
|
"step": 28915
|
|
},
|
|
{
|
|
"entropy": 5.413306808471679,
|
|
"epoch": 2.4156364851319747,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004413376326839934,
|
|
"loss": 4.6883,
|
|
"mean_token_accuracy": 0.22858195304870604,
|
|
"num_tokens": 53228886.0,
|
|
"step": 28920
|
|
},
|
|
{
|
|
"entropy": 5.436883020401001,
|
|
"epoch": 2.4160541262946875,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00044131758412662493,
|
|
"loss": 4.7607,
|
|
"mean_token_accuracy": 0.22788110971450806,
|
|
"num_tokens": 53237314.0,
|
|
"step": 28925
|
|
},
|
|
{
|
|
"entropy": 5.324565649032593,
|
|
"epoch": 2.4164717674574008,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000441297532657667,
|
|
"loss": 4.7285,
|
|
"mean_token_accuracy": 0.2304214984178543,
|
|
"num_tokens": 53246502.0,
|
|
"step": 28930
|
|
},
|
|
{
|
|
"entropy": 5.37324857711792,
|
|
"epoch": 2.4168894086201136,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004412774782774705,
|
|
"loss": 4.7556,
|
|
"mean_token_accuracy": 0.22371662855148317,
|
|
"num_tokens": 53256004.0,
|
|
"step": 28935
|
|
},
|
|
{
|
|
"entropy": 5.413418292999268,
|
|
"epoch": 2.417307049782827,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004412574209863867,
|
|
"loss": 4.7577,
|
|
"mean_token_accuracy": 0.22270799428224564,
|
|
"num_tokens": 53264301.0,
|
|
"step": 28940
|
|
},
|
|
{
|
|
"entropy": 5.398058032989502,
|
|
"epoch": 2.4177246909455397,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004412373607847666,
|
|
"loss": 4.7052,
|
|
"mean_token_accuracy": 0.23196834921836854,
|
|
"num_tokens": 53272664.0,
|
|
"step": 28945
|
|
},
|
|
{
|
|
"entropy": 5.414920711517334,
|
|
"epoch": 2.4181423321082525,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00044121729767296135,
|
|
"loss": 4.777,
|
|
"mean_token_accuracy": 0.22258162796497344,
|
|
"num_tokens": 53282210.0,
|
|
"step": 28950
|
|
},
|
|
{
|
|
"entropy": 5.433484363555908,
|
|
"epoch": 2.4185599732709657,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00044119723165132225,
|
|
"loss": 4.8394,
|
|
"mean_token_accuracy": 0.22376377135515213,
|
|
"num_tokens": 53291328.0,
|
|
"step": 28955
|
|
},
|
|
{
|
|
"entropy": 5.395645093917847,
|
|
"epoch": 2.4189776144336785,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00044117716272020055,
|
|
"loss": 4.7608,
|
|
"mean_token_accuracy": 0.2287280559539795,
|
|
"num_tokens": 53301332.0,
|
|
"step": 28960
|
|
},
|
|
{
|
|
"entropy": 5.462910795211792,
|
|
"epoch": 2.419395255596392,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004411570908799476,
|
|
"loss": 4.7282,
|
|
"mean_token_accuracy": 0.22605564892292024,
|
|
"num_tokens": 53310699.0,
|
|
"step": 28965
|
|
},
|
|
{
|
|
"entropy": 5.4117897033691404,
|
|
"epoch": 2.4198128967591046,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00044113701613091483,
|
|
"loss": 4.7817,
|
|
"mean_token_accuracy": 0.22547770738601686,
|
|
"num_tokens": 53319760.0,
|
|
"step": 28970
|
|
},
|
|
{
|
|
"entropy": 5.4054797172546385,
|
|
"epoch": 2.4202305379218174,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00044111693847345354,
|
|
"loss": 4.6828,
|
|
"mean_token_accuracy": 0.23204073905944825,
|
|
"num_tokens": 53328781.0,
|
|
"step": 28975
|
|
},
|
|
{
|
|
"entropy": 5.463263320922851,
|
|
"epoch": 2.4206481790845307,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004410968579079153,
|
|
"loss": 4.7229,
|
|
"mean_token_accuracy": 0.22841167449951172,
|
|
"num_tokens": 53337071.0,
|
|
"step": 28980
|
|
},
|
|
{
|
|
"entropy": 5.377997970581054,
|
|
"epoch": 2.4210658202472435,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00044107677443465165,
|
|
"loss": 4.7148,
|
|
"mean_token_accuracy": 0.22957485765218735,
|
|
"num_tokens": 53346480.0,
|
|
"step": 28985
|
|
},
|
|
{
|
|
"entropy": 5.386690998077393,
|
|
"epoch": 2.4214834614099567,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00044105668805401415,
|
|
"loss": 4.791,
|
|
"mean_token_accuracy": 0.23468004465103148,
|
|
"num_tokens": 53355784.0,
|
|
"step": 28990
|
|
},
|
|
{
|
|
"entropy": 5.388214874267578,
|
|
"epoch": 2.4219011025726696,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00044103659876635443,
|
|
"loss": 4.764,
|
|
"mean_token_accuracy": 0.22466825991868972,
|
|
"num_tokens": 53364793.0,
|
|
"step": 28995
|
|
},
|
|
{
|
|
"entropy": 5.492003345489502,
|
|
"epoch": 2.4223187437353824,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004410165065720242,
|
|
"loss": 4.9055,
|
|
"mean_token_accuracy": 0.22175767570734023,
|
|
"num_tokens": 53374473.0,
|
|
"step": 29000
|
|
},
|
|
{
|
|
"entropy": 5.375819301605224,
|
|
"epoch": 2.4227363848980956,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004409964114713752,
|
|
"loss": 4.7196,
|
|
"mean_token_accuracy": 0.23169565796852112,
|
|
"num_tokens": 53383453.0,
|
|
"step": 29005
|
|
},
|
|
{
|
|
"entropy": 5.429189825057984,
|
|
"epoch": 2.4231540260608084,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004409763134647592,
|
|
"loss": 4.8027,
|
|
"mean_token_accuracy": 0.22496295124292373,
|
|
"num_tokens": 53392628.0,
|
|
"step": 29010
|
|
},
|
|
{
|
|
"entropy": 5.439060020446777,
|
|
"epoch": 2.4235716672235217,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000440956212552528,
|
|
"loss": 4.7537,
|
|
"mean_token_accuracy": 0.2300429105758667,
|
|
"num_tokens": 53402614.0,
|
|
"step": 29015
|
|
},
|
|
{
|
|
"entropy": 5.5044105052948,
|
|
"epoch": 2.4239893083862345,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004409361087350336,
|
|
"loss": 4.9297,
|
|
"mean_token_accuracy": 0.21195684373378754,
|
|
"num_tokens": 53412851.0,
|
|
"step": 29020
|
|
},
|
|
{
|
|
"entropy": 5.407605934143066,
|
|
"epoch": 2.4244069495489473,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004409160020126279,
|
|
"loss": 4.7281,
|
|
"mean_token_accuracy": 0.2275592491030693,
|
|
"num_tokens": 53422116.0,
|
|
"step": 29025
|
|
},
|
|
{
|
|
"entropy": 5.378778123855591,
|
|
"epoch": 2.4248245907116606,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004408958923856628,
|
|
"loss": 4.6814,
|
|
"mean_token_accuracy": 0.23645969331264496,
|
|
"num_tokens": 53431213.0,
|
|
"step": 29030
|
|
},
|
|
{
|
|
"entropy": 5.391788673400879,
|
|
"epoch": 2.4252422318743734,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00044087577985449047,
|
|
"loss": 4.7705,
|
|
"mean_token_accuracy": 0.23614350706338882,
|
|
"num_tokens": 53439292.0,
|
|
"step": 29035
|
|
},
|
|
{
|
|
"entropy": 5.398374891281128,
|
|
"epoch": 2.4256598730370866,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004408556644194629,
|
|
"loss": 4.7226,
|
|
"mean_token_accuracy": 0.2342788189649582,
|
|
"num_tokens": 53447932.0,
|
|
"step": 29040
|
|
},
|
|
{
|
|
"entropy": 5.341532611846924,
|
|
"epoch": 2.4260775141997994,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004408355460809323,
|
|
"loss": 4.6814,
|
|
"mean_token_accuracy": 0.23311274349689484,
|
|
"num_tokens": 53457847.0,
|
|
"step": 29045
|
|
},
|
|
{
|
|
"entropy": 5.394429922103882,
|
|
"epoch": 2.4264951553625127,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00044081542483925086,
|
|
"loss": 4.6648,
|
|
"mean_token_accuracy": 0.2345731660723686,
|
|
"num_tokens": 53466106.0,
|
|
"step": 29050
|
|
},
|
|
{
|
|
"entropy": 5.374107360839844,
|
|
"epoch": 2.4269127965252255,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004407953006947708,
|
|
"loss": 4.6825,
|
|
"mean_token_accuracy": 0.24152886122465134,
|
|
"num_tokens": 53474516.0,
|
|
"step": 29055
|
|
},
|
|
{
|
|
"entropy": 5.29725136756897,
|
|
"epoch": 2.4273304376879388,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00044077517364784455,
|
|
"loss": 4.6922,
|
|
"mean_token_accuracy": 0.23370423913002014,
|
|
"num_tokens": 53483640.0,
|
|
"step": 29060
|
|
},
|
|
{
|
|
"entropy": 5.4182531356811525,
|
|
"epoch": 2.4277480788506516,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00044075504369882416,
|
|
"loss": 4.7964,
|
|
"mean_token_accuracy": 0.22445222586393357,
|
|
"num_tokens": 53492987.0,
|
|
"step": 29065
|
|
},
|
|
{
|
|
"entropy": 5.4335874080657955,
|
|
"epoch": 2.4281657200133644,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004407349108480623,
|
|
"loss": 4.7721,
|
|
"mean_token_accuracy": 0.22175837755203248,
|
|
"num_tokens": 53502319.0,
|
|
"step": 29070
|
|
},
|
|
{
|
|
"entropy": 5.411125516891479,
|
|
"epoch": 2.4285833611760776,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00044071477509591126,
|
|
"loss": 4.7462,
|
|
"mean_token_accuracy": 0.2288473516702652,
|
|
"num_tokens": 53511739.0,
|
|
"step": 29075
|
|
},
|
|
{
|
|
"entropy": 5.441852474212647,
|
|
"epoch": 2.4290010023387905,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004406946364427237,
|
|
"loss": 4.8057,
|
|
"mean_token_accuracy": 0.2280283659696579,
|
|
"num_tokens": 53521369.0,
|
|
"step": 29080
|
|
},
|
|
{
|
|
"entropy": 5.439335775375366,
|
|
"epoch": 2.4294186435015037,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00044067449488885207,
|
|
"loss": 4.6793,
|
|
"mean_token_accuracy": 0.23904710114002228,
|
|
"num_tokens": 53530697.0,
|
|
"step": 29085
|
|
},
|
|
{
|
|
"entropy": 5.374714469909668,
|
|
"epoch": 2.4298362846642165,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00044065435043464903,
|
|
"loss": 4.747,
|
|
"mean_token_accuracy": 0.23171672970056534,
|
|
"num_tokens": 53539105.0,
|
|
"step": 29090
|
|
},
|
|
{
|
|
"entropy": 5.413459300994873,
|
|
"epoch": 2.4302539258269293,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004406342030804671,
|
|
"loss": 4.8826,
|
|
"mean_token_accuracy": 0.2228673815727234,
|
|
"num_tokens": 53548537.0,
|
|
"step": 29095
|
|
},
|
|
{
|
|
"entropy": 5.350256776809692,
|
|
"epoch": 2.4306715669896426,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004406140528266591,
|
|
"loss": 4.7096,
|
|
"mean_token_accuracy": 0.22848082929849625,
|
|
"num_tokens": 53557467.0,
|
|
"step": 29100
|
|
},
|
|
{
|
|
"entropy": 5.433300256729126,
|
|
"epoch": 2.4310892081523554,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00044059389967357774,
|
|
"loss": 4.8276,
|
|
"mean_token_accuracy": 0.2238738015294075,
|
|
"num_tokens": 53566970.0,
|
|
"step": 29105
|
|
},
|
|
{
|
|
"entropy": 5.421587133407593,
|
|
"epoch": 2.4315068493150687,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00044057374362157587,
|
|
"loss": 4.7399,
|
|
"mean_token_accuracy": 0.22402438074350356,
|
|
"num_tokens": 53576320.0,
|
|
"step": 29110
|
|
},
|
|
{
|
|
"entropy": 5.35015377998352,
|
|
"epoch": 2.4319244904777815,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00044055358467100627,
|
|
"loss": 4.7082,
|
|
"mean_token_accuracy": 0.23698232769966127,
|
|
"num_tokens": 53585135.0,
|
|
"step": 29115
|
|
},
|
|
{
|
|
"entropy": 5.353194808959961,
|
|
"epoch": 2.4323421316404943,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00044053342282222196,
|
|
"loss": 4.7998,
|
|
"mean_token_accuracy": 0.23000796288251876,
|
|
"num_tokens": 53594138.0,
|
|
"step": 29120
|
|
},
|
|
{
|
|
"entropy": 5.376659107208252,
|
|
"epoch": 2.4327597728032075,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004405132580755758,
|
|
"loss": 4.6564,
|
|
"mean_token_accuracy": 0.232819265127182,
|
|
"num_tokens": 53603133.0,
|
|
"step": 29125
|
|
},
|
|
{
|
|
"entropy": 5.386458063125611,
|
|
"epoch": 2.4331774139659204,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00044049309043142084,
|
|
"loss": 4.7411,
|
|
"mean_token_accuracy": 0.2275395542383194,
|
|
"num_tokens": 53612219.0,
|
|
"step": 29130
|
|
},
|
|
{
|
|
"entropy": 5.3657371520996096,
|
|
"epoch": 2.4335950551286336,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004404729198901101,
|
|
"loss": 4.7311,
|
|
"mean_token_accuracy": 0.21480796337127686,
|
|
"num_tokens": 53621548.0,
|
|
"step": 29135
|
|
},
|
|
{
|
|
"entropy": 5.472486352920532,
|
|
"epoch": 2.4340126962913464,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00044045274645199665,
|
|
"loss": 4.8774,
|
|
"mean_token_accuracy": 0.22226971983909607,
|
|
"num_tokens": 53631376.0,
|
|
"step": 29140
|
|
},
|
|
{
|
|
"entropy": 5.390609073638916,
|
|
"epoch": 2.4344303374540592,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004404325701174338,
|
|
"loss": 4.692,
|
|
"mean_token_accuracy": 0.23231250792741776,
|
|
"num_tokens": 53639965.0,
|
|
"step": 29145
|
|
},
|
|
{
|
|
"entropy": 5.3232887268066404,
|
|
"epoch": 2.4348479786167725,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004404123908867747,
|
|
"loss": 4.6328,
|
|
"mean_token_accuracy": 0.2351301595568657,
|
|
"num_tokens": 53649799.0,
|
|
"step": 29150
|
|
},
|
|
{
|
|
"entropy": 5.320517444610596,
|
|
"epoch": 2.4352656197794853,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00044039220876037255,
|
|
"loss": 4.7286,
|
|
"mean_token_accuracy": 0.23267033845186233,
|
|
"num_tokens": 53658612.0,
|
|
"step": 29155
|
|
},
|
|
{
|
|
"entropy": 5.398121166229248,
|
|
"epoch": 2.4356832609421986,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004403720237385808,
|
|
"loss": 4.7263,
|
|
"mean_token_accuracy": 0.2236850827932358,
|
|
"num_tokens": 53667197.0,
|
|
"step": 29160
|
|
},
|
|
{
|
|
"entropy": 5.275496101379394,
|
|
"epoch": 2.4361009021049114,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00044035183582175264,
|
|
"loss": 4.6546,
|
|
"mean_token_accuracy": 0.2393952414393425,
|
|
"num_tokens": 53675953.0,
|
|
"step": 29165
|
|
},
|
|
{
|
|
"entropy": 5.434111213684082,
|
|
"epoch": 2.4365185432676246,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00044033164501024153,
|
|
"loss": 4.8346,
|
|
"mean_token_accuracy": 0.23082320988178254,
|
|
"num_tokens": 53685135.0,
|
|
"step": 29170
|
|
},
|
|
{
|
|
"entropy": 5.463518333435059,
|
|
"epoch": 2.4369361844303374,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000440311451304401,
|
|
"loss": 4.8011,
|
|
"mean_token_accuracy": 0.22667750716209412,
|
|
"num_tokens": 53694024.0,
|
|
"step": 29175
|
|
},
|
|
{
|
|
"entropy": 5.425216627120972,
|
|
"epoch": 2.4373538255930507,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00044029125470458445,
|
|
"loss": 4.7793,
|
|
"mean_token_accuracy": 0.22327233254909515,
|
|
"num_tokens": 53703699.0,
|
|
"step": 29180
|
|
},
|
|
{
|
|
"entropy": 5.307705736160278,
|
|
"epoch": 2.4377714667557635,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004402710552111456,
|
|
"loss": 4.672,
|
|
"mean_token_accuracy": 0.2297820806503296,
|
|
"num_tokens": 53713121.0,
|
|
"step": 29185
|
|
},
|
|
{
|
|
"entropy": 5.346699285507202,
|
|
"epoch": 2.4381891079184763,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00044025085282443807,
|
|
"loss": 4.6614,
|
|
"mean_token_accuracy": 0.23525966107845306,
|
|
"num_tokens": 53721896.0,
|
|
"step": 29190
|
|
},
|
|
{
|
|
"entropy": 5.354891300201416,
|
|
"epoch": 2.4386067490811896,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00044023064754481535,
|
|
"loss": 4.6889,
|
|
"mean_token_accuracy": 0.23776281476020814,
|
|
"num_tokens": 53731085.0,
|
|
"step": 29195
|
|
},
|
|
{
|
|
"entropy": 5.361129665374756,
|
|
"epoch": 2.4390243902439024,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004402104393726313,
|
|
"loss": 4.7553,
|
|
"mean_token_accuracy": 0.23092814832925795,
|
|
"num_tokens": 53739816.0,
|
|
"step": 29200
|
|
},
|
|
{
|
|
"entropy": 5.347400951385498,
|
|
"epoch": 2.4394420314066156,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004401902283082396,
|
|
"loss": 4.7133,
|
|
"mean_token_accuracy": 0.232633775472641,
|
|
"num_tokens": 53748495.0,
|
|
"step": 29205
|
|
},
|
|
{
|
|
"entropy": 5.489007377624512,
|
|
"epoch": 2.4398596725693285,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00044017001435199413,
|
|
"loss": 4.859,
|
|
"mean_token_accuracy": 0.2219223454594612,
|
|
"num_tokens": 53758622.0,
|
|
"step": 29210
|
|
},
|
|
{
|
|
"entropy": 5.450308513641358,
|
|
"epoch": 2.4402773137320413,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004401497975042487,
|
|
"loss": 4.8438,
|
|
"mean_token_accuracy": 0.21757869124412538,
|
|
"num_tokens": 53769867.0,
|
|
"step": 29215
|
|
},
|
|
{
|
|
"entropy": 5.494561290740966,
|
|
"epoch": 2.4406949548947545,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00044012957776535735,
|
|
"loss": 4.8867,
|
|
"mean_token_accuracy": 0.22050711363554001,
|
|
"num_tokens": 53780217.0,
|
|
"step": 29220
|
|
},
|
|
{
|
|
"entropy": 5.407173299789429,
|
|
"epoch": 2.4411125960574673,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004401093551356739,
|
|
"loss": 4.697,
|
|
"mean_token_accuracy": 0.24045346230268477,
|
|
"num_tokens": 53788977.0,
|
|
"step": 29225
|
|
},
|
|
{
|
|
"entropy": 5.385004472732544,
|
|
"epoch": 2.4415302372201806,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00044008912961555246,
|
|
"loss": 4.7879,
|
|
"mean_token_accuracy": 0.22571144104003907,
|
|
"num_tokens": 53797955.0,
|
|
"step": 29230
|
|
},
|
|
{
|
|
"entropy": 5.341383981704712,
|
|
"epoch": 2.4419478783828934,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004400689012053472,
|
|
"loss": 4.73,
|
|
"mean_token_accuracy": 0.23317317366600038,
|
|
"num_tokens": 53806929.0,
|
|
"step": 29235
|
|
},
|
|
{
|
|
"entropy": 5.357551002502442,
|
|
"epoch": 2.442365519545606,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000440048669905412,
|
|
"loss": 4.7452,
|
|
"mean_token_accuracy": 0.23119966238737105,
|
|
"num_tokens": 53816071.0,
|
|
"step": 29240
|
|
},
|
|
{
|
|
"entropy": 5.391872215270996,
|
|
"epoch": 2.4427831607083195,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00044002843571610124,
|
|
"loss": 4.6974,
|
|
"mean_token_accuracy": 0.2286678969860077,
|
|
"num_tokens": 53824376.0,
|
|
"step": 29245
|
|
},
|
|
{
|
|
"entropy": 5.3677544593811035,
|
|
"epoch": 2.4432008018710323,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000440008198637769,
|
|
"loss": 4.6944,
|
|
"mean_token_accuracy": 0.2407648891210556,
|
|
"num_tokens": 53833504.0,
|
|
"step": 29250
|
|
},
|
|
{
|
|
"entropy": 5.403655242919922,
|
|
"epoch": 2.4436184430337455,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004399879586707697,
|
|
"loss": 4.7524,
|
|
"mean_token_accuracy": 0.2331308051943779,
|
|
"num_tokens": 53842027.0,
|
|
"step": 29255
|
|
},
|
|
{
|
|
"entropy": 5.420906639099121,
|
|
"epoch": 2.4440360841964583,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004399677158154576,
|
|
"loss": 4.753,
|
|
"mean_token_accuracy": 0.23884207755327225,
|
|
"num_tokens": 53849895.0,
|
|
"step": 29260
|
|
},
|
|
{
|
|
"entropy": 5.458617258071899,
|
|
"epoch": 2.444453725359171,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000439947470072187,
|
|
"loss": 4.8444,
|
|
"mean_token_accuracy": 0.22242694199085236,
|
|
"num_tokens": 53860030.0,
|
|
"step": 29265
|
|
},
|
|
{
|
|
"entropy": 5.4024224281311035,
|
|
"epoch": 2.4448713665218844,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004399272214413124,
|
|
"loss": 4.7528,
|
|
"mean_token_accuracy": 0.22583018988370895,
|
|
"num_tokens": 53869298.0,
|
|
"step": 29270
|
|
},
|
|
{
|
|
"entropy": 5.394868230819702,
|
|
"epoch": 2.4452890076845972,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004399069699231883,
|
|
"loss": 4.7146,
|
|
"mean_token_accuracy": 0.22620493173599243,
|
|
"num_tokens": 53878019.0,
|
|
"step": 29275
|
|
},
|
|
{
|
|
"entropy": 5.434627628326416,
|
|
"epoch": 2.4457066488473105,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00043988671551816914,
|
|
"loss": 4.7792,
|
|
"mean_token_accuracy": 0.2251383677124977,
|
|
"num_tokens": 53886783.0,
|
|
"step": 29280
|
|
},
|
|
{
|
|
"entropy": 5.471608352661133,
|
|
"epoch": 2.4461242900100233,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00043986645822660956,
|
|
"loss": 4.7203,
|
|
"mean_token_accuracy": 0.24278703331947327,
|
|
"num_tokens": 53895459.0,
|
|
"step": 29285
|
|
},
|
|
{
|
|
"entropy": 5.389061069488525,
|
|
"epoch": 2.4465419311727366,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00043984619804886423,
|
|
"loss": 4.8365,
|
|
"mean_token_accuracy": 0.22627878785133362,
|
|
"num_tokens": 53904901.0,
|
|
"step": 29290
|
|
},
|
|
{
|
|
"entropy": 5.401166200637817,
|
|
"epoch": 2.4469595723354494,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004398259349852877,
|
|
"loss": 4.7892,
|
|
"mean_token_accuracy": 0.22090153098106385,
|
|
"num_tokens": 53913170.0,
|
|
"step": 29295
|
|
},
|
|
{
|
|
"entropy": 5.340612840652466,
|
|
"epoch": 2.4473772134981626,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00043980566903623487,
|
|
"loss": 4.6343,
|
|
"mean_token_accuracy": 0.23709026277065276,
|
|
"num_tokens": 53921950.0,
|
|
"step": 29300
|
|
},
|
|
{
|
|
"entropy": 5.427225828170776,
|
|
"epoch": 2.4477948546608754,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004397854002020604,
|
|
"loss": 4.8091,
|
|
"mean_token_accuracy": 0.22579798102378845,
|
|
"num_tokens": 53930984.0,
|
|
"step": 29305
|
|
},
|
|
{
|
|
"entropy": 5.444070672988891,
|
|
"epoch": 2.4482124958235882,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00043976512848311906,
|
|
"loss": 4.8069,
|
|
"mean_token_accuracy": 0.2197173222899437,
|
|
"num_tokens": 53941498.0,
|
|
"step": 29310
|
|
},
|
|
{
|
|
"entropy": 5.3437694072723385,
|
|
"epoch": 2.4486301369863015,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004397448538797659,
|
|
"loss": 4.6978,
|
|
"mean_token_accuracy": 0.23257505595684053,
|
|
"num_tokens": 53950229.0,
|
|
"step": 29315
|
|
},
|
|
{
|
|
"entropy": 5.430491209030151,
|
|
"epoch": 2.4490477781490143,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004397245763923557,
|
|
"loss": 4.8363,
|
|
"mean_token_accuracy": 0.22293782383203506,
|
|
"num_tokens": 53959227.0,
|
|
"step": 29320
|
|
},
|
|
{
|
|
"entropy": 5.492558145523072,
|
|
"epoch": 2.4494654193117276,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004397042960212436,
|
|
"loss": 4.8294,
|
|
"mean_token_accuracy": 0.2170194059610367,
|
|
"num_tokens": 53967895.0,
|
|
"step": 29325
|
|
},
|
|
{
|
|
"entropy": 5.486286544799805,
|
|
"epoch": 2.4498830604744404,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004396840127667845,
|
|
"loss": 4.8509,
|
|
"mean_token_accuracy": 0.21713233590126038,
|
|
"num_tokens": 53977822.0,
|
|
"step": 29330
|
|
},
|
|
{
|
|
"entropy": 5.412030744552612,
|
|
"epoch": 2.450300701637153,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004396637266293335,
|
|
"loss": 4.732,
|
|
"mean_token_accuracy": 0.2257121130824089,
|
|
"num_tokens": 53986924.0,
|
|
"step": 29335
|
|
},
|
|
{
|
|
"entropy": 5.4126568794250485,
|
|
"epoch": 2.4507183427998664,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004396434376092458,
|
|
"loss": 4.7546,
|
|
"mean_token_accuracy": 0.23179101198911667,
|
|
"num_tokens": 53996482.0,
|
|
"step": 29340
|
|
},
|
|
{
|
|
"entropy": 5.368023109436035,
|
|
"epoch": 2.4511359839625793,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004396231457068765,
|
|
"loss": 4.679,
|
|
"mean_token_accuracy": 0.24372460693120956,
|
|
"num_tokens": 54005717.0,
|
|
"step": 29345
|
|
},
|
|
{
|
|
"entropy": 5.299197673797607,
|
|
"epoch": 2.4515536251252925,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00043960285092258097,
|
|
"loss": 4.6019,
|
|
"mean_token_accuracy": 0.24166808277368546,
|
|
"num_tokens": 54013825.0,
|
|
"step": 29350
|
|
},
|
|
{
|
|
"entropy": 5.417442083358765,
|
|
"epoch": 2.4519712662880053,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004395825532567143,
|
|
"loss": 4.8465,
|
|
"mean_token_accuracy": 0.22508715689182282,
|
|
"num_tokens": 54022975.0,
|
|
"step": 29355
|
|
},
|
|
{
|
|
"entropy": 5.449370670318603,
|
|
"epoch": 2.452388907450718,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000439562252709632,
|
|
"loss": 4.7422,
|
|
"mean_token_accuracy": 0.22401632219552994,
|
|
"num_tokens": 54031035.0,
|
|
"step": 29360
|
|
},
|
|
{
|
|
"entropy": 5.431995248794555,
|
|
"epoch": 2.4528065486134314,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004395419492816894,
|
|
"loss": 4.7211,
|
|
"mean_token_accuracy": 0.23255174309015275,
|
|
"num_tokens": 54040424.0,
|
|
"step": 29365
|
|
},
|
|
{
|
|
"entropy": 5.369605541229248,
|
|
"epoch": 2.453224189776144,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004395216429732418,
|
|
"loss": 4.7128,
|
|
"mean_token_accuracy": 0.2278625935316086,
|
|
"num_tokens": 54049960.0,
|
|
"step": 29370
|
|
},
|
|
{
|
|
"entropy": 5.410149192810058,
|
|
"epoch": 2.4536418309388575,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00043950133378464485,
|
|
"loss": 4.7639,
|
|
"mean_token_accuracy": 0.21960220038890838,
|
|
"num_tokens": 54058332.0,
|
|
"step": 29375
|
|
},
|
|
{
|
|
"entropy": 5.347137928009033,
|
|
"epoch": 2.4540594721015703,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004394810217162541,
|
|
"loss": 4.6244,
|
|
"mean_token_accuracy": 0.2387206181883812,
|
|
"num_tokens": 54067049.0,
|
|
"step": 29380
|
|
},
|
|
{
|
|
"entropy": 5.3907225131988525,
|
|
"epoch": 2.454477113264283,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004394607067684251,
|
|
"loss": 4.7527,
|
|
"mean_token_accuracy": 0.22760991305112838,
|
|
"num_tokens": 54076200.0,
|
|
"step": 29385
|
|
},
|
|
{
|
|
"entropy": 5.416893339157104,
|
|
"epoch": 2.4548947544269963,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00043944038894151336,
|
|
"loss": 4.7396,
|
|
"mean_token_accuracy": 0.2311014637351036,
|
|
"num_tokens": 54084374.0,
|
|
"step": 29390
|
|
},
|
|
{
|
|
"entropy": 5.4389838695526125,
|
|
"epoch": 2.455312395589709,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004394200682358748,
|
|
"loss": 4.7796,
|
|
"mean_token_accuracy": 0.22605065405368804,
|
|
"num_tokens": 54093618.0,
|
|
"step": 29395
|
|
},
|
|
{
|
|
"entropy": 5.409258079528809,
|
|
"epoch": 2.4557300367524224,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004393997446518649,
|
|
"loss": 4.7268,
|
|
"mean_token_accuracy": 0.23675441592931748,
|
|
"num_tokens": 54102942.0,
|
|
"step": 29400
|
|
},
|
|
{
|
|
"entropy": 5.274274730682373,
|
|
"epoch": 2.456147677915135,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004393794181898397,
|
|
"loss": 4.66,
|
|
"mean_token_accuracy": 0.2326720654964447,
|
|
"num_tokens": 54111331.0,
|
|
"step": 29405
|
|
},
|
|
{
|
|
"entropy": 5.339882659912109,
|
|
"epoch": 2.4565653190778485,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004393590888501548,
|
|
"loss": 4.6781,
|
|
"mean_token_accuracy": 0.23548886328935623,
|
|
"num_tokens": 54119920.0,
|
|
"step": 29410
|
|
},
|
|
{
|
|
"entropy": 5.300230646133423,
|
|
"epoch": 2.4569829602405613,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004393387566331663,
|
|
"loss": 4.6674,
|
|
"mean_token_accuracy": 0.2352127179503441,
|
|
"num_tokens": 54129813.0,
|
|
"step": 29415
|
|
},
|
|
{
|
|
"entropy": 5.381267356872558,
|
|
"epoch": 2.4574006014032745,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00043931842153923,
|
|
"loss": 4.7017,
|
|
"mean_token_accuracy": 0.23169176876544953,
|
|
"num_tokens": 54138369.0,
|
|
"step": 29420
|
|
},
|
|
{
|
|
"entropy": 5.366397523880005,
|
|
"epoch": 2.4578182425659874,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.000439298083568702,
|
|
"loss": 4.714,
|
|
"mean_token_accuracy": 0.22734114974737168,
|
|
"num_tokens": 54147622.0,
|
|
"step": 29425
|
|
},
|
|
{
|
|
"entropy": 5.42147798538208,
|
|
"epoch": 2.4582358837287,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004392777427219382,
|
|
"loss": 4.8423,
|
|
"mean_token_accuracy": 0.22417498826980592,
|
|
"num_tokens": 54156619.0,
|
|
"step": 29430
|
|
},
|
|
{
|
|
"entropy": 5.405901384353638,
|
|
"epoch": 2.4586535248914134,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00043925739899929484,
|
|
"loss": 4.6763,
|
|
"mean_token_accuracy": 0.23473180830478668,
|
|
"num_tokens": 54166525.0,
|
|
"step": 29435
|
|
},
|
|
{
|
|
"entropy": 5.352223348617554,
|
|
"epoch": 2.4590711660541262,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.000439237052401128,
|
|
"loss": 4.7113,
|
|
"mean_token_accuracy": 0.2334265112876892,
|
|
"num_tokens": 54174955.0,
|
|
"step": 29440
|
|
},
|
|
{
|
|
"entropy": 5.3376930236816404,
|
|
"epoch": 2.4594888072168395,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00043921670292779386,
|
|
"loss": 4.7792,
|
|
"mean_token_accuracy": 0.2261305883526802,
|
|
"num_tokens": 54185389.0,
|
|
"step": 29445
|
|
},
|
|
{
|
|
"entropy": 5.389325666427612,
|
|
"epoch": 2.4599064483795523,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004391963505796487,
|
|
"loss": 4.7063,
|
|
"mean_token_accuracy": 0.23489099889993667,
|
|
"num_tokens": 54194797.0,
|
|
"step": 29450
|
|
},
|
|
{
|
|
"entropy": 5.453567934036255,
|
|
"epoch": 2.460324089542265,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004391759953570487,
|
|
"loss": 4.7893,
|
|
"mean_token_accuracy": 0.22765613198280335,
|
|
"num_tokens": 54203815.0,
|
|
"step": 29455
|
|
},
|
|
{
|
|
"entropy": 5.3860166549682615,
|
|
"epoch": 2.4607417307049784,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004391556372603503,
|
|
"loss": 4.7811,
|
|
"mean_token_accuracy": 0.2213971883058548,
|
|
"num_tokens": 54213075.0,
|
|
"step": 29460
|
|
},
|
|
{
|
|
"entropy": 5.496153831481934,
|
|
"epoch": 2.461159371867691,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00043913527628990984,
|
|
"loss": 4.8625,
|
|
"mean_token_accuracy": 0.21990602612495422,
|
|
"num_tokens": 54222551.0,
|
|
"step": 29465
|
|
},
|
|
{
|
|
"entropy": 5.3711190700531,
|
|
"epoch": 2.4615770130304044,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00043911491244608386,
|
|
"loss": 4.6975,
|
|
"mean_token_accuracy": 0.23239782005548476,
|
|
"num_tokens": 54232294.0,
|
|
"step": 29470
|
|
},
|
|
{
|
|
"entropy": 5.4141395568847654,
|
|
"epoch": 2.4619946541931172,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004390945457292288,
|
|
"loss": 4.7627,
|
|
"mean_token_accuracy": 0.2284509614109993,
|
|
"num_tokens": 54241293.0,
|
|
"step": 29475
|
|
},
|
|
{
|
|
"entropy": 5.356642246246338,
|
|
"epoch": 2.46241229535583,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004390741761397012,
|
|
"loss": 4.7323,
|
|
"mean_token_accuracy": 0.23116271197795868,
|
|
"num_tokens": 54249801.0,
|
|
"step": 29480
|
|
},
|
|
{
|
|
"entropy": 5.385291242599488,
|
|
"epoch": 2.4628299365185433,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00043905380367785757,
|
|
"loss": 4.6701,
|
|
"mean_token_accuracy": 0.23144498616456985,
|
|
"num_tokens": 54257747.0,
|
|
"step": 29485
|
|
},
|
|
{
|
|
"entropy": 5.4132568359375,
|
|
"epoch": 2.463247577681256,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004390334283440547,
|
|
"loss": 4.7566,
|
|
"mean_token_accuracy": 0.234796042740345,
|
|
"num_tokens": 54266050.0,
|
|
"step": 29490
|
|
},
|
|
{
|
|
"entropy": 5.430030012130738,
|
|
"epoch": 2.4636652188439694,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00043901305013864923,
|
|
"loss": 4.8059,
|
|
"mean_token_accuracy": 0.22792842239141464,
|
|
"num_tokens": 54275318.0,
|
|
"step": 29495
|
|
},
|
|
{
|
|
"entropy": 5.365076208114624,
|
|
"epoch": 2.464082860006682,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00043899266906199784,
|
|
"loss": 4.7174,
|
|
"mean_token_accuracy": 0.23614775240421296,
|
|
"num_tokens": 54284623.0,
|
|
"step": 29500
|
|
},
|
|
{
|
|
"entropy": 5.4450523853302,
|
|
"epoch": 2.464500501169395,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004389722851144574,
|
|
"loss": 4.8184,
|
|
"mean_token_accuracy": 0.22499468624591829,
|
|
"num_tokens": 54293876.0,
|
|
"step": 29505
|
|
},
|
|
{
|
|
"entropy": 5.437201070785522,
|
|
"epoch": 2.4649181423321083,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00043895189829638485,
|
|
"loss": 4.835,
|
|
"mean_token_accuracy": 0.22047333270311356,
|
|
"num_tokens": 54303133.0,
|
|
"step": 29510
|
|
},
|
|
{
|
|
"entropy": 5.460950613021851,
|
|
"epoch": 2.465335783494821,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004389315086081368,
|
|
"loss": 4.725,
|
|
"mean_token_accuracy": 0.22441258728504182,
|
|
"num_tokens": 54311725.0,
|
|
"step": 29515
|
|
},
|
|
{
|
|
"entropy": 5.418055725097656,
|
|
"epoch": 2.4657534246575343,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00043891111605007043,
|
|
"loss": 4.6657,
|
|
"mean_token_accuracy": 0.2372087836265564,
|
|
"num_tokens": 54320268.0,
|
|
"step": 29520
|
|
},
|
|
{
|
|
"entropy": 5.304630184173584,
|
|
"epoch": 2.466171065820247,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004388907206225427,
|
|
"loss": 4.7028,
|
|
"mean_token_accuracy": 0.23448341339826584,
|
|
"num_tokens": 54328833.0,
|
|
"step": 29525
|
|
},
|
|
{
|
|
"entropy": 5.350352621078491,
|
|
"epoch": 2.4665887069829604,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004388703223259106,
|
|
"loss": 4.6944,
|
|
"mean_token_accuracy": 0.23296321481466292,
|
|
"num_tokens": 54337556.0,
|
|
"step": 29530
|
|
},
|
|
{
|
|
"entropy": 5.442768669128418,
|
|
"epoch": 2.467006348145673,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00043884992116053137,
|
|
"loss": 4.7982,
|
|
"mean_token_accuracy": 0.22837480455636977,
|
|
"num_tokens": 54346170.0,
|
|
"step": 29535
|
|
},
|
|
{
|
|
"entropy": 5.406636476516724,
|
|
"epoch": 2.4674239893083865,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00043882951712676183,
|
|
"loss": 4.7087,
|
|
"mean_token_accuracy": 0.23210199773311616,
|
|
"num_tokens": 54355328.0,
|
|
"step": 29540
|
|
},
|
|
{
|
|
"entropy": 5.3278563022613525,
|
|
"epoch": 2.4678416304710993,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00043880911022495955,
|
|
"loss": 4.6816,
|
|
"mean_token_accuracy": 0.22962758243083953,
|
|
"num_tokens": 54364445.0,
|
|
"step": 29545
|
|
},
|
|
{
|
|
"entropy": 5.4077372550964355,
|
|
"epoch": 2.468259271633812,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004387887004554816,
|
|
"loss": 4.7664,
|
|
"mean_token_accuracy": 0.22661159187555313,
|
|
"num_tokens": 54373407.0,
|
|
"step": 29550
|
|
},
|
|
{
|
|
"entropy": 5.301048803329468,
|
|
"epoch": 2.4686769127965253,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004387682878186852,
|
|
"loss": 4.643,
|
|
"mean_token_accuracy": 0.23958775401115417,
|
|
"num_tokens": 54381116.0,
|
|
"step": 29555
|
|
},
|
|
{
|
|
"entropy": 5.454782867431641,
|
|
"epoch": 2.469094553959238,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004387478723149279,
|
|
"loss": 4.874,
|
|
"mean_token_accuracy": 0.21757148802280427,
|
|
"num_tokens": 54390174.0,
|
|
"step": 29560
|
|
},
|
|
{
|
|
"entropy": 5.446640968322754,
|
|
"epoch": 2.4695121951219514,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00043872745394456697,
|
|
"loss": 4.7109,
|
|
"mean_token_accuracy": 0.23066913038492204,
|
|
"num_tokens": 54399893.0,
|
|
"step": 29565
|
|
},
|
|
{
|
|
"entropy": 5.472256851196289,
|
|
"epoch": 2.4699298362846642,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00043870703270795986,
|
|
"loss": 4.8594,
|
|
"mean_token_accuracy": 0.2242014452815056,
|
|
"num_tokens": 54410037.0,
|
|
"step": 29570
|
|
},
|
|
{
|
|
"entropy": 5.372096872329712,
|
|
"epoch": 2.470347477447377,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004386866086054641,
|
|
"loss": 4.7264,
|
|
"mean_token_accuracy": 0.23263973891735076,
|
|
"num_tokens": 54419128.0,
|
|
"step": 29575
|
|
},
|
|
{
|
|
"entropy": 5.385164642333985,
|
|
"epoch": 2.4707651186100903,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00043866618163743723,
|
|
"loss": 4.6669,
|
|
"mean_token_accuracy": 0.23040491044521333,
|
|
"num_tokens": 54428351.0,
|
|
"step": 29580
|
|
},
|
|
{
|
|
"entropy": 5.361986112594605,
|
|
"epoch": 2.471182759772803,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00043864575180423685,
|
|
"loss": 4.7324,
|
|
"mean_token_accuracy": 0.23294229656457902,
|
|
"num_tokens": 54437728.0,
|
|
"step": 29585
|
|
},
|
|
{
|
|
"entropy": 5.540672731399536,
|
|
"epoch": 2.4716004009355164,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00043862531910622056,
|
|
"loss": 4.8294,
|
|
"mean_token_accuracy": 0.22352757751941682,
|
|
"num_tokens": 54446504.0,
|
|
"step": 29590
|
|
},
|
|
{
|
|
"entropy": 5.443547344207763,
|
|
"epoch": 2.472018042098229,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00043860488354374613,
|
|
"loss": 4.8147,
|
|
"mean_token_accuracy": 0.2239792451262474,
|
|
"num_tokens": 54456078.0,
|
|
"step": 29595
|
|
},
|
|
{
|
|
"entropy": 5.320402574539185,
|
|
"epoch": 2.472435683260942,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00043858444511717126,
|
|
"loss": 4.7114,
|
|
"mean_token_accuracy": 0.2353585034608841,
|
|
"num_tokens": 54465713.0,
|
|
"step": 29600
|
|
},
|
|
{
|
|
"entropy": 5.334977483749389,
|
|
"epoch": 2.4728533244236552,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00043856400382685383,
|
|
"loss": 4.672,
|
|
"mean_token_accuracy": 0.23850174844264985,
|
|
"num_tokens": 54473803.0,
|
|
"step": 29605
|
|
},
|
|
{
|
|
"entropy": 5.381901693344116,
|
|
"epoch": 2.473270965586368,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004385435596731516,
|
|
"loss": 4.769,
|
|
"mean_token_accuracy": 0.2330232709646225,
|
|
"num_tokens": 54482920.0,
|
|
"step": 29610
|
|
},
|
|
{
|
|
"entropy": 5.399132156372071,
|
|
"epoch": 2.4736886067490813,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00043852311265642246,
|
|
"loss": 4.7306,
|
|
"mean_token_accuracy": 0.23237126022577287,
|
|
"num_tokens": 54491556.0,
|
|
"step": 29615
|
|
},
|
|
{
|
|
"entropy": 5.421226596832275,
|
|
"epoch": 2.474106247911794,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00043850266277702446,
|
|
"loss": 4.6951,
|
|
"mean_token_accuracy": 0.2328761711716652,
|
|
"num_tokens": 54500169.0,
|
|
"step": 29620
|
|
},
|
|
{
|
|
"entropy": 5.376243209838867,
|
|
"epoch": 2.4745238890745074,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004384822100353155,
|
|
"loss": 4.6858,
|
|
"mean_token_accuracy": 0.2355754166841507,
|
|
"num_tokens": 54508973.0,
|
|
"step": 29625
|
|
},
|
|
{
|
|
"entropy": 5.3914794921875,
|
|
"epoch": 2.47494153023722,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004384617544316537,
|
|
"loss": 4.7947,
|
|
"mean_token_accuracy": 0.22469882071018218,
|
|
"num_tokens": 54518450.0,
|
|
"step": 29630
|
|
},
|
|
{
|
|
"entropy": 5.39657244682312,
|
|
"epoch": 2.475359171399933,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00043844129596639714,
|
|
"loss": 4.7256,
|
|
"mean_token_accuracy": 0.22955844551324844,
|
|
"num_tokens": 54527986.0,
|
|
"step": 29635
|
|
},
|
|
{
|
|
"entropy": 5.349547815322876,
|
|
"epoch": 2.4757768125626463,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000438420834639904,
|
|
"loss": 4.6624,
|
|
"mean_token_accuracy": 0.23555560410022736,
|
|
"num_tokens": 54536792.0,
|
|
"step": 29640
|
|
},
|
|
{
|
|
"entropy": 5.482886219024659,
|
|
"epoch": 2.476194453725359,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00043840037045253234,
|
|
"loss": 4.9355,
|
|
"mean_token_accuracy": 0.20912824422121049,
|
|
"num_tokens": 54547225.0,
|
|
"step": 29645
|
|
},
|
|
{
|
|
"entropy": 5.479250907897949,
|
|
"epoch": 2.4766120948880723,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004383799034046405,
|
|
"loss": 4.8536,
|
|
"mean_token_accuracy": 0.22896900326013564,
|
|
"num_tokens": 54557732.0,
|
|
"step": 29650
|
|
},
|
|
{
|
|
"entropy": 5.442339086532593,
|
|
"epoch": 2.477029736050785,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004383594334965869,
|
|
"loss": 4.7898,
|
|
"mean_token_accuracy": 0.22280529737472535,
|
|
"num_tokens": 54567510.0,
|
|
"step": 29655
|
|
},
|
|
{
|
|
"entropy": 5.430565404891968,
|
|
"epoch": 2.4774473772134984,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004383389607287297,
|
|
"loss": 4.7988,
|
|
"mean_token_accuracy": 0.2295023426413536,
|
|
"num_tokens": 54577619.0,
|
|
"step": 29660
|
|
},
|
|
{
|
|
"entropy": 5.328941869735718,
|
|
"epoch": 2.477865018376211,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004383184851014274,
|
|
"loss": 4.6577,
|
|
"mean_token_accuracy": 0.231073597073555,
|
|
"num_tokens": 54586752.0,
|
|
"step": 29665
|
|
},
|
|
{
|
|
"entropy": 5.3548990249633786,
|
|
"epoch": 2.478282659538924,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00043829800661503843,
|
|
"loss": 4.7939,
|
|
"mean_token_accuracy": 0.23017909079790116,
|
|
"num_tokens": 54595757.0,
|
|
"step": 29670
|
|
},
|
|
{
|
|
"entropy": 5.403260040283203,
|
|
"epoch": 2.4787003007016373,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00043827752526992125,
|
|
"loss": 4.7866,
|
|
"mean_token_accuracy": 0.2266194775700569,
|
|
"num_tokens": 54605134.0,
|
|
"step": 29675
|
|
},
|
|
{
|
|
"entropy": 5.343146944046021,
|
|
"epoch": 2.47911794186435,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00043825704106643454,
|
|
"loss": 4.6295,
|
|
"mean_token_accuracy": 0.23731585443019867,
|
|
"num_tokens": 54614471.0,
|
|
"step": 29680
|
|
},
|
|
{
|
|
"entropy": 5.391256713867188,
|
|
"epoch": 2.4795355830270633,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00043823655400493676,
|
|
"loss": 4.7747,
|
|
"mean_token_accuracy": 0.22501247823238374,
|
|
"num_tokens": 54623466.0,
|
|
"step": 29685
|
|
},
|
|
{
|
|
"entropy": 5.348179864883423,
|
|
"epoch": 2.479953224189776,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00043821606408578665,
|
|
"loss": 4.7164,
|
|
"mean_token_accuracy": 0.22973864078521727,
|
|
"num_tokens": 54632898.0,
|
|
"step": 29690
|
|
},
|
|
{
|
|
"entropy": 5.48339810371399,
|
|
"epoch": 2.480370865352489,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004381955713093428,
|
|
"loss": 4.7684,
|
|
"mean_token_accuracy": 0.2284852534532547,
|
|
"num_tokens": 54642934.0,
|
|
"step": 29695
|
|
},
|
|
{
|
|
"entropy": 5.374566555023193,
|
|
"epoch": 2.480788506515202,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00043817507567596415,
|
|
"loss": 4.7032,
|
|
"mean_token_accuracy": 0.23256680220365525,
|
|
"num_tokens": 54652602.0,
|
|
"step": 29700
|
|
},
|
|
{
|
|
"entropy": 5.453754711151123,
|
|
"epoch": 2.481206147677915,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00043815457718600933,
|
|
"loss": 4.7951,
|
|
"mean_token_accuracy": 0.22258740067481994,
|
|
"num_tokens": 54661801.0,
|
|
"step": 29705
|
|
},
|
|
{
|
|
"entropy": 5.425589752197266,
|
|
"epoch": 2.4816237888406283,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004381340758398372,
|
|
"loss": 4.7755,
|
|
"mean_token_accuracy": 0.23280534893274307,
|
|
"num_tokens": 54671977.0,
|
|
"step": 29710
|
|
},
|
|
{
|
|
"entropy": 5.374747610092163,
|
|
"epoch": 2.482041430003341,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00043811357163780676,
|
|
"loss": 4.6697,
|
|
"mean_token_accuracy": 0.2354957401752472,
|
|
"num_tokens": 54681820.0,
|
|
"step": 29715
|
|
},
|
|
{
|
|
"entropy": 5.421914577484131,
|
|
"epoch": 2.482459071166054,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004380930645802769,
|
|
"loss": 4.7561,
|
|
"mean_token_accuracy": 0.22738421261310576,
|
|
"num_tokens": 54690713.0,
|
|
"step": 29720
|
|
},
|
|
{
|
|
"entropy": 5.477895975112915,
|
|
"epoch": 2.482876712328767,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004380725546676067,
|
|
"loss": 4.8089,
|
|
"mean_token_accuracy": 0.22187415659427642,
|
|
"num_tokens": 54700808.0,
|
|
"step": 29725
|
|
},
|
|
{
|
|
"entropy": 5.346278333663941,
|
|
"epoch": 2.48329435349148,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00043805204190015503,
|
|
"loss": 4.6908,
|
|
"mean_token_accuracy": 0.23542812764644622,
|
|
"num_tokens": 54708415.0,
|
|
"step": 29730
|
|
},
|
|
{
|
|
"entropy": 5.285972595214844,
|
|
"epoch": 2.4837119946541932,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004380315262782811,
|
|
"loss": 4.6979,
|
|
"mean_token_accuracy": 0.23012011647224426,
|
|
"num_tokens": 54716887.0,
|
|
"step": 29735
|
|
},
|
|
{
|
|
"entropy": 5.442089223861695,
|
|
"epoch": 2.484129635816906,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004380110078023441,
|
|
"loss": 4.8305,
|
|
"mean_token_accuracy": 0.2202567383646965,
|
|
"num_tokens": 54727103.0,
|
|
"step": 29740
|
|
},
|
|
{
|
|
"entropy": 5.360056018829345,
|
|
"epoch": 2.4845472769796193,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004379904864727032,
|
|
"loss": 4.6603,
|
|
"mean_token_accuracy": 0.23070593774318696,
|
|
"num_tokens": 54735405.0,
|
|
"step": 29745
|
|
},
|
|
{
|
|
"entropy": 5.467327070236206,
|
|
"epoch": 2.484964918142332,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00043796996228971766,
|
|
"loss": 4.8077,
|
|
"mean_token_accuracy": 0.21828006356954574,
|
|
"num_tokens": 54745278.0,
|
|
"step": 29750
|
|
},
|
|
{
|
|
"entropy": 5.428986310958862,
|
|
"epoch": 2.485382559305045,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004379494352537467,
|
|
"loss": 4.7389,
|
|
"mean_token_accuracy": 0.23066890239715576,
|
|
"num_tokens": 54753632.0,
|
|
"step": 29755
|
|
},
|
|
{
|
|
"entropy": 5.440625524520874,
|
|
"epoch": 2.485800200467758,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004379289053651498,
|
|
"loss": 4.8268,
|
|
"mean_token_accuracy": 0.2200496956706047,
|
|
"num_tokens": 54763924.0,
|
|
"step": 29760
|
|
},
|
|
{
|
|
"entropy": 5.348038673400879,
|
|
"epoch": 2.486217841630471,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004379083726242862,
|
|
"loss": 4.6312,
|
|
"mean_token_accuracy": 0.23320649713277816,
|
|
"num_tokens": 54772747.0,
|
|
"step": 29765
|
|
},
|
|
{
|
|
"entropy": 5.416998767852784,
|
|
"epoch": 2.4866354827931842,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004378878370315156,
|
|
"loss": 4.8129,
|
|
"mean_token_accuracy": 0.2305615022778511,
|
|
"num_tokens": 54782325.0,
|
|
"step": 29770
|
|
},
|
|
{
|
|
"entropy": 5.368669891357422,
|
|
"epoch": 2.487053123955897,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004378672985871972,
|
|
"loss": 4.7146,
|
|
"mean_token_accuracy": 0.2340730145573616,
|
|
"num_tokens": 54791359.0,
|
|
"step": 29775
|
|
},
|
|
{
|
|
"entropy": 5.363072490692138,
|
|
"epoch": 2.4874707651186103,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00043784675729169076,
|
|
"loss": 4.7443,
|
|
"mean_token_accuracy": 0.22603049427270888,
|
|
"num_tokens": 54800281.0,
|
|
"step": 29780
|
|
},
|
|
{
|
|
"entropy": 5.395896959304809,
|
|
"epoch": 2.487888406281323,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004378262131453558,
|
|
"loss": 4.6794,
|
|
"mean_token_accuracy": 0.23156200647354125,
|
|
"num_tokens": 54808954.0,
|
|
"step": 29785
|
|
},
|
|
{
|
|
"entropy": 5.453318881988525,
|
|
"epoch": 2.488306047444036,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000437805666148552,
|
|
"loss": 4.751,
|
|
"mean_token_accuracy": 0.23503233045339583,
|
|
"num_tokens": 54817542.0,
|
|
"step": 29790
|
|
},
|
|
{
|
|
"entropy": 5.361602258682251,
|
|
"epoch": 2.488723688606749,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00043778511630163905,
|
|
"loss": 4.7253,
|
|
"mean_token_accuracy": 0.23016243427991867,
|
|
"num_tokens": 54826189.0,
|
|
"step": 29795
|
|
},
|
|
{
|
|
"entropy": 5.412879514694214,
|
|
"epoch": 2.489141329769462,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00043776456360497665,
|
|
"loss": 4.7612,
|
|
"mean_token_accuracy": 0.2306131586432457,
|
|
"num_tokens": 54835352.0,
|
|
"step": 29800
|
|
},
|
|
{
|
|
"entropy": 5.459881734848023,
|
|
"epoch": 2.4895589709321753,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004377440080589247,
|
|
"loss": 4.7687,
|
|
"mean_token_accuracy": 0.22599773705005646,
|
|
"num_tokens": 54844917.0,
|
|
"step": 29805
|
|
},
|
|
{
|
|
"entropy": 5.429119873046875,
|
|
"epoch": 2.489976612094888,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000437723449663843,
|
|
"loss": 4.7916,
|
|
"mean_token_accuracy": 0.22765987664461135,
|
|
"num_tokens": 54854489.0,
|
|
"step": 29810
|
|
},
|
|
{
|
|
"entropy": 5.396027231216431,
|
|
"epoch": 2.490394253257601,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004377028884200914,
|
|
"loss": 4.8055,
|
|
"mean_token_accuracy": 0.22437732368707658,
|
|
"num_tokens": 54864462.0,
|
|
"step": 29815
|
|
},
|
|
{
|
|
"entropy": 5.352509546279907,
|
|
"epoch": 2.490811894420314,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004376823243280298,
|
|
"loss": 4.731,
|
|
"mean_token_accuracy": 0.2279799535870552,
|
|
"num_tokens": 54873958.0,
|
|
"step": 29820
|
|
},
|
|
{
|
|
"entropy": 5.394338846206665,
|
|
"epoch": 2.491229535583027,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004376617573880185,
|
|
"loss": 4.7368,
|
|
"mean_token_accuracy": 0.2369504228234291,
|
|
"num_tokens": 54882553.0,
|
|
"step": 29825
|
|
},
|
|
{
|
|
"entropy": 5.404607772827148,
|
|
"epoch": 2.49164717674574,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004376411876004172,
|
|
"loss": 4.7696,
|
|
"mean_token_accuracy": 0.22766860872507094,
|
|
"num_tokens": 54891618.0,
|
|
"step": 29830
|
|
},
|
|
{
|
|
"entropy": 5.438468885421753,
|
|
"epoch": 2.492064817908453,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004376206149655862,
|
|
"loss": 4.7979,
|
|
"mean_token_accuracy": 0.2347666010260582,
|
|
"num_tokens": 54900621.0,
|
|
"step": 29835
|
|
},
|
|
{
|
|
"entropy": 5.406714391708374,
|
|
"epoch": 2.492482459071166,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004376000394838856,
|
|
"loss": 4.706,
|
|
"mean_token_accuracy": 0.22937686443328859,
|
|
"num_tokens": 54909116.0,
|
|
"step": 29840
|
|
},
|
|
{
|
|
"entropy": 5.423512697219849,
|
|
"epoch": 2.492900100233879,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004375794611556755,
|
|
"loss": 4.7216,
|
|
"mean_token_accuracy": 0.22999584078788757,
|
|
"num_tokens": 54917940.0,
|
|
"step": 29845
|
|
},
|
|
{
|
|
"entropy": 5.348629522323608,
|
|
"epoch": 2.493317741396592,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004375588799813163,
|
|
"loss": 4.8144,
|
|
"mean_token_accuracy": 0.22253745347261428,
|
|
"num_tokens": 54927548.0,
|
|
"step": 29850
|
|
},
|
|
{
|
|
"entropy": 5.4283348560333256,
|
|
"epoch": 2.493735382559305,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004375382959611682,
|
|
"loss": 4.804,
|
|
"mean_token_accuracy": 0.22839213758707047,
|
|
"num_tokens": 54937157.0,
|
|
"step": 29855
|
|
},
|
|
{
|
|
"entropy": 5.4500892162323,
|
|
"epoch": 2.494153023722018,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00043751770909559155,
|
|
"loss": 4.7442,
|
|
"mean_token_accuracy": 0.22183617800474167,
|
|
"num_tokens": 54946851.0,
|
|
"step": 29860
|
|
},
|
|
{
|
|
"entropy": 5.41556305885315,
|
|
"epoch": 2.4945706648847312,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00043749711938494693,
|
|
"loss": 4.8247,
|
|
"mean_token_accuracy": 0.21976349353790284,
|
|
"num_tokens": 54956686.0,
|
|
"step": 29865
|
|
},
|
|
{
|
|
"entropy": 5.420173215866089,
|
|
"epoch": 2.494988306047444,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00043747652682959455,
|
|
"loss": 4.7257,
|
|
"mean_token_accuracy": 0.23049283623695374,
|
|
"num_tokens": 54965233.0,
|
|
"step": 29870
|
|
},
|
|
{
|
|
"entropy": 5.427813863754272,
|
|
"epoch": 2.495405947210157,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004374559314298949,
|
|
"loss": 4.759,
|
|
"mean_token_accuracy": 0.23107140213251115,
|
|
"num_tokens": 54973647.0,
|
|
"step": 29875
|
|
},
|
|
{
|
|
"entropy": 5.425726366043091,
|
|
"epoch": 2.49582358837287,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00043743533318620873,
|
|
"loss": 4.7545,
|
|
"mean_token_accuracy": 0.22337893694639205,
|
|
"num_tokens": 54982550.0,
|
|
"step": 29880
|
|
},
|
|
{
|
|
"entropy": 5.354284381866455,
|
|
"epoch": 2.496241229535583,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00043741473209889654,
|
|
"loss": 4.6455,
|
|
"mean_token_accuracy": 0.23646899312734604,
|
|
"num_tokens": 54991137.0,
|
|
"step": 29885
|
|
},
|
|
{
|
|
"entropy": 5.336884355545044,
|
|
"epoch": 2.496658870698296,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004373941281683189,
|
|
"loss": 4.7192,
|
|
"mean_token_accuracy": 0.23342260718345642,
|
|
"num_tokens": 55000271.0,
|
|
"step": 29890
|
|
},
|
|
{
|
|
"entropy": 5.455899858474732,
|
|
"epoch": 2.497076511861009,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004373735213948366,
|
|
"loss": 4.8448,
|
|
"mean_token_accuracy": 0.22347069382667542,
|
|
"num_tokens": 55009379.0,
|
|
"step": 29895
|
|
},
|
|
{
|
|
"entropy": 5.390530681610107,
|
|
"epoch": 2.4974941530237222,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00043735291177881045,
|
|
"loss": 4.715,
|
|
"mean_token_accuracy": 0.23801376223564147,
|
|
"num_tokens": 55018562.0,
|
|
"step": 29900
|
|
},
|
|
{
|
|
"entropy": 5.427022504806518,
|
|
"epoch": 2.497911794186435,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000437332299320601,
|
|
"loss": 4.7891,
|
|
"mean_token_accuracy": 0.22718391865491866,
|
|
"num_tokens": 55027429.0,
|
|
"step": 29905
|
|
},
|
|
{
|
|
"entropy": 5.496936559677124,
|
|
"epoch": 2.498329435349148,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004373116840205693,
|
|
"loss": 4.8042,
|
|
"mean_token_accuracy": 0.22249470055103301,
|
|
"num_tokens": 55037510.0,
|
|
"step": 29910
|
|
},
|
|
{
|
|
"entropy": 5.410091161727905,
|
|
"epoch": 2.498747076511861,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00043729106587907625,
|
|
"loss": 4.7295,
|
|
"mean_token_accuracy": 0.2321137860417366,
|
|
"num_tokens": 55046944.0,
|
|
"step": 29915
|
|
},
|
|
{
|
|
"entropy": 5.347026777267456,
|
|
"epoch": 2.499164717674574,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00043727044489648263,
|
|
"loss": 4.7009,
|
|
"mean_token_accuracy": 0.2304251328110695,
|
|
"num_tokens": 55056281.0,
|
|
"step": 29920
|
|
},
|
|
{
|
|
"entropy": 5.329861068725586,
|
|
"epoch": 2.499582358837287,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004372498210731497,
|
|
"loss": 4.6902,
|
|
"mean_token_accuracy": 0.23348691165447236,
|
|
"num_tokens": 55064764.0,
|
|
"step": 29925
|
|
},
|
|
{
|
|
"entropy": 5.399631309509277,
|
|
"epoch": 2.5,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00043722919440943833,
|
|
"loss": 4.7802,
|
|
"mean_token_accuracy": 0.22308949530124664,
|
|
"num_tokens": 55074054.0,
|
|
"step": 29930
|
|
},
|
|
{
|
|
"entropy": 5.375532960891723,
|
|
"epoch": 2.500417641162713,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004372085649057095,
|
|
"loss": 4.7295,
|
|
"mean_token_accuracy": 0.22837143391370773,
|
|
"num_tokens": 55082623.0,
|
|
"step": 29935
|
|
},
|
|
{
|
|
"entropy": 5.4854999542236325,
|
|
"epoch": 2.500835282325426,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00043718793256232463,
|
|
"loss": 4.8073,
|
|
"mean_token_accuracy": 0.2262749269604683,
|
|
"num_tokens": 55092057.0,
|
|
"step": 29940
|
|
},
|
|
{
|
|
"entropy": 5.412539005279541,
|
|
"epoch": 2.501252923488139,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00043716729737964475,
|
|
"loss": 4.6775,
|
|
"mean_token_accuracy": 0.23189083784818648,
|
|
"num_tokens": 55099887.0,
|
|
"step": 29945
|
|
},
|
|
{
|
|
"entropy": 5.429153490066528,
|
|
"epoch": 2.501670564650852,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00043714665935803103,
|
|
"loss": 4.7243,
|
|
"mean_token_accuracy": 0.22711966186761856,
|
|
"num_tokens": 55108143.0,
|
|
"step": 29950
|
|
},
|
|
{
|
|
"entropy": 5.399541234970092,
|
|
"epoch": 2.502088205813565,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00043712601849784494,
|
|
"loss": 4.8185,
|
|
"mean_token_accuracy": 0.2214548408985138,
|
|
"num_tokens": 55117920.0,
|
|
"step": 29955
|
|
},
|
|
{
|
|
"entropy": 5.5590447902679445,
|
|
"epoch": 2.5025058469762778,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00043710537479944774,
|
|
"loss": 4.8351,
|
|
"mean_token_accuracy": 0.22569011896848679,
|
|
"num_tokens": 55128557.0,
|
|
"step": 29960
|
|
},
|
|
{
|
|
"entropy": 5.366080045700073,
|
|
"epoch": 2.502923488138991,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00043708472826320085,
|
|
"loss": 4.6604,
|
|
"mean_token_accuracy": 0.23271202743053437,
|
|
"num_tokens": 55137886.0,
|
|
"step": 29965
|
|
},
|
|
{
|
|
"entropy": 5.447798538208008,
|
|
"epoch": 2.503341129301704,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004370640788894656,
|
|
"loss": 4.8295,
|
|
"mean_token_accuracy": 0.2232233077287674,
|
|
"num_tokens": 55146986.0,
|
|
"step": 29970
|
|
},
|
|
{
|
|
"entropy": 5.356089639663696,
|
|
"epoch": 2.503758770464417,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004370434266786037,
|
|
"loss": 4.746,
|
|
"mean_token_accuracy": 0.2248506247997284,
|
|
"num_tokens": 55156190.0,
|
|
"step": 29975
|
|
},
|
|
{
|
|
"entropy": 5.4194975852966305,
|
|
"epoch": 2.50417641162713,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004370227716309765,
|
|
"loss": 4.7112,
|
|
"mean_token_accuracy": 0.23489231020212173,
|
|
"num_tokens": 55165591.0,
|
|
"step": 29980
|
|
},
|
|
{
|
|
"entropy": 5.411629295349121,
|
|
"epoch": 2.5045940527898427,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00043700211374694565,
|
|
"loss": 4.7373,
|
|
"mean_token_accuracy": 0.22447068989276886,
|
|
"num_tokens": 55174865.0,
|
|
"step": 29985
|
|
},
|
|
{
|
|
"entropy": 5.473358297348023,
|
|
"epoch": 2.505011693952556,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004369814530268728,
|
|
"loss": 4.768,
|
|
"mean_token_accuracy": 0.22535641342401505,
|
|
"num_tokens": 55183199.0,
|
|
"step": 29990
|
|
},
|
|
{
|
|
"entropy": 5.526672124862671,
|
|
"epoch": 2.505429335115269,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004369607894711196,
|
|
"loss": 4.846,
|
|
"mean_token_accuracy": 0.21820496022701263,
|
|
"num_tokens": 55192258.0,
|
|
"step": 29995
|
|
},
|
|
{
|
|
"entropy": 5.40809817314148,
|
|
"epoch": 2.505846976277982,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004369401230800479,
|
|
"loss": 4.7282,
|
|
"mean_token_accuracy": 0.2327120766043663,
|
|
"num_tokens": 55200886.0,
|
|
"step": 30000
|
|
},
|
|
{
|
|
"epoch": 2.505846976277982,
|
|
"eval_entropy": 5.110122198271716,
|
|
"eval_loss": 4.764552593231201,
|
|
"eval_mean_token_accuracy": 0.239230120484732,
|
|
"eval_num_tokens": 55200886.0,
|
|
"eval_runtime": 20.8856,
|
|
"eval_samples_per_second": 1808.09,
|
|
"eval_steps_per_second": 226.041,
|
|
"step": 30000
|
|
}
|
|
],
|
|
"logging_steps": 5,
|
|
"max_steps": 119720,
|
|
"num_input_tokens_seen": 0,
|
|
"num_train_epochs": 10,
|
|
"save_steps": 3000,
|
|
"stateful_callbacks": {
|
|
"TrainerControl": {
|
|
"args": {
|
|
"should_epoch_stop": false,
|
|
"should_evaluate": false,
|
|
"should_log": false,
|
|
"should_save": true,
|
|
"should_training_stop": false
|
|
},
|
|
"attributes": {}
|
|
}
|
|
},
|
|
"total_flos": 1.211203449962496e+16,
|
|
"train_batch_size": 16,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|